From a7ee8839daf21c4a3ca439733e7bed25f32e7954 Mon Sep 17 00:00:00 2001
From: Denis CIOCCA <denis.ciocca@st.com>
Date: Fri, 3 Oct 2014 17:35:35 +0200
Subject: iio:imu: changed structure name from st_sensors to st_sensor_settings

This patch change structure name and related variables names.

Signed-off-by: Denis Ciocca <denis.ciocca@st.com>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 include/linux/iio/common/st_sensors.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index d8257ab60ba..2c476acb87d 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -164,7 +164,7 @@ struct st_sensor_transfer_function {
 };
 
 /**
- * struct st_sensors - ST sensors list
+ * struct st_sensor_settings - ST specific sensor settings
  * @wai: Contents of WhoAmI register.
  * @sensors_supported: List of supported sensors by struct itself.
  * @ch: IIO channels for the sensor.
@@ -177,7 +177,7 @@ struct st_sensor_transfer_function {
  * @multi_read_bit: Use or not particular bit for [I2C/SPI] multi-read.
  * @bootime: samples to discard when sensor passing from power-down to power-up.
  */
-struct st_sensors {
+struct st_sensor_settings {
 	u8 wai;
 	char sensors_supported[ST_SENSORS_MAX_4WAI][ST_SENSORS_MAX_NAME];
 	struct iio_chan_spec *ch;
@@ -196,7 +196,7 @@ struct st_sensors {
  * struct st_sensor_data - ST sensor device status
  * @dev: Pointer to instance of struct device (I2C or SPI).
  * @trig: The trigger in use by the core driver.
- * @sensor: Pointer to the current sensor struct in use.
+ * @sensor_settings: Pointer to the specific sensor settings in use.
  * @current_fullscale: Maximum range of measure by the sensor.
  * @vdd: Pointer to sensor's Vdd power supply
  * @vdd_io: Pointer to sensor's Vdd-IO power supply
@@ -213,7 +213,7 @@ struct st_sensors {
 struct st_sensor_data {
 	struct device *dev;
 	struct iio_trigger *trig;
-	struct st_sensors *sensor;
+	struct st_sensor_settings *sensor_settings;
 	struct st_sensor_fullscale_avl *current_fullscale;
 	struct regulator *vdd;
 	struct regulator *vdd_io;
@@ -279,7 +279,7 @@ int st_sensors_read_info_raw(struct iio_dev *indio_dev,
 				struct iio_chan_spec const *ch, int *val);
 
 int st_sensors_check_device_support(struct iio_dev *indio_dev,
-			int num_sensors_list, const struct st_sensors *sensors);
+	int num_sensors_list, const struct st_sensor_settings *sensor_settings);
 
 ssize_t st_sensors_sysfs_sampling_frequency_avail(struct device *dev,
 				struct device_attribute *attr, char *buf);
-- 
cgit v1.2.3-70-g09d2


From af7e9069543aabd415d7c543f3f89b143ac1a932 Mon Sep 17 00:00:00 2001
From: Jacob Pan <jacob.jun.pan@linux.intel.com>
Date: Mon, 6 Oct 2014 21:17:14 -0700
Subject: mfd: axp20x: Extend axp20x to support axp288 pmic

X-Powers AXP288 is a customized PMIC for Intel Baytrail-CR platforms. Similar
to AXP202/209, AXP288 comes with USB charger, more LDO and BUCK channels, and
AD converters. It also provides extended status and interrupt reporting
capabilities than the devices currently supported in axp20x.c.

In addition to feature extension, this patch also adds ACPI binding for
enumeration.

This consolidated driver should support more X-Powers' PMICs in both device
tree and ACPI enumerated platforms.

Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Reviewed-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/Kconfig        |   3 +-
 drivers/mfd/axp20x.c       | 361 ++++++++++++++++++++++++++++++++++++++-------
 include/linux/mfd/axp20x.h |  59 ++++++++
 3 files changed, 367 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index de5abf24474..c183edb45b5 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -74,7 +74,8 @@ config MFD_AXP20X
 	select REGMAP_IRQ
 	depends on I2C=y
 	help
-	  If you say Y here you get support for the X-Powers AXP202 and AXP209.
+	  If you say Y here you get support for the X-Powers AXP202, AXP209 and
+	  AXP288 power management IC (PMIC).
 	  This driver include only the core APIs. You have to select individual
 	  components like regulators or the PEK (Power Enable Key) under the
 	  corresponding menus.
diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c
index dee653989e3..b2fb7f492c8 100644
--- a/drivers/mfd/axp20x.c
+++ b/drivers/mfd/axp20x.c
@@ -1,9 +1,9 @@
 /*
- * axp20x.c - MFD core driver for the X-Powers AXP202 and AXP209
+ * axp20x.c - MFD core driver for the X-Powers' Power Management ICs
  *
- * AXP20x comprises an adaptive USB-Compatible PWM charger, 2 BUCK DC-DC
- * converters, 5 LDOs, multiple 12-bit ADCs of voltage, current and temperature
- * as well as 4 configurable GPIOs.
+ * AXP20x typically comprises an adaptive USB-Compatible PWM charger, BUCK DC-DC
+ * converters, LDOs, multiple 12-bit ADCs of voltage, current and temperature
+ * as well as configurable GPIOs.
  *
  * Author: Carlo Caione <carlo@caione.org>
  *
@@ -25,9 +25,16 @@
 #include <linux/mfd/core.h>
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
+#include <linux/acpi.h>
 
 #define AXP20X_OFF	0x80
 
+static const char const *axp20x_model_names[] = {
+	"AXP202",
+	"AXP209",
+	"AXP288",
+};
+
 static const struct regmap_range axp20x_writeable_ranges[] = {
 	regmap_reg_range(AXP20X_DATACACHE(0), AXP20X_IRQ5_STATE),
 	regmap_reg_range(AXP20X_DCDC_MODE, AXP20X_FG_RES),
@@ -47,6 +54,25 @@ static const struct regmap_access_table axp20x_volatile_table = {
 	.n_yes_ranges	= ARRAY_SIZE(axp20x_volatile_ranges),
 };
 
+static const struct regmap_range axp288_writeable_ranges[] = {
+	regmap_reg_range(AXP20X_DATACACHE(0), AXP20X_IRQ6_STATE),
+	regmap_reg_range(AXP20X_DCDC_MODE, AXP288_FG_TUNE5),
+};
+
+static const struct regmap_range axp288_volatile_ranges[] = {
+	regmap_reg_range(AXP20X_IRQ1_EN, AXP20X_IPSOUT_V_HIGH_L),
+};
+
+static const struct regmap_access_table axp288_writeable_table = {
+	.yes_ranges	= axp288_writeable_ranges,
+	.n_yes_ranges	= ARRAY_SIZE(axp288_writeable_ranges),
+};
+
+static const struct regmap_access_table axp288_volatile_table = {
+	.yes_ranges	= axp288_volatile_ranges,
+	.n_yes_ranges	= ARRAY_SIZE(axp288_volatile_ranges),
+};
+
 static struct resource axp20x_pek_resources[] = {
 	{
 		.name	= "PEK_DBR",
@@ -61,6 +87,39 @@ static struct resource axp20x_pek_resources[] = {
 	},
 };
 
+static struct resource axp288_battery_resources[] = {
+	{
+		.start = AXP288_IRQ_QWBTU,
+		.end   = AXP288_IRQ_QWBTU,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.start = AXP288_IRQ_WBTU,
+		.end   = AXP288_IRQ_WBTU,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.start = AXP288_IRQ_QWBTO,
+		.end   = AXP288_IRQ_QWBTO,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.start = AXP288_IRQ_WBTO,
+		.end   = AXP288_IRQ_WBTO,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.start = AXP288_IRQ_WL2,
+		.end   = AXP288_IRQ_WL2,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.start = AXP288_IRQ_WL1,
+		.end   = AXP288_IRQ_WL1,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
 static const struct regmap_config axp20x_regmap_config = {
 	.reg_bits	= 8,
 	.val_bits	= 8,
@@ -70,47 +129,96 @@ static const struct regmap_config axp20x_regmap_config = {
 	.cache_type	= REGCACHE_RBTREE,
 };
 
-#define AXP20X_IRQ(_irq, _off, _mask) \
-	[AXP20X_IRQ_##_irq] = { .reg_offset = (_off), .mask = BIT(_mask) }
+static const struct regmap_config axp288_regmap_config = {
+	.reg_bits	= 8,
+	.val_bits	= 8,
+	.wr_table	= &axp288_writeable_table,
+	.volatile_table	= &axp288_volatile_table,
+	.max_register	= AXP288_FG_TUNE5,
+	.cache_type	= REGCACHE_RBTREE,
+};
+
+#define INIT_REGMAP_IRQ(_variant, _irq, _off, _mask)			\
+	[_variant##_IRQ_##_irq] = { .reg_offset = (_off), .mask = BIT(_mask) }
 
 static const struct regmap_irq axp20x_regmap_irqs[] = {
-	AXP20X_IRQ(ACIN_OVER_V,		0, 7),
-	AXP20X_IRQ(ACIN_PLUGIN,		0, 6),
-	AXP20X_IRQ(ACIN_REMOVAL,	0, 5),
-	AXP20X_IRQ(VBUS_OVER_V,		0, 4),
-	AXP20X_IRQ(VBUS_PLUGIN,		0, 3),
-	AXP20X_IRQ(VBUS_REMOVAL,	0, 2),
-	AXP20X_IRQ(VBUS_V_LOW,		0, 1),
-	AXP20X_IRQ(BATT_PLUGIN,		1, 7),
-	AXP20X_IRQ(BATT_REMOVAL,	1, 6),
-	AXP20X_IRQ(BATT_ENT_ACT_MODE,	1, 5),
-	AXP20X_IRQ(BATT_EXIT_ACT_MODE,	1, 4),
-	AXP20X_IRQ(CHARG,		1, 3),
-	AXP20X_IRQ(CHARG_DONE,		1, 2),
-	AXP20X_IRQ(BATT_TEMP_HIGH,	1, 1),
-	AXP20X_IRQ(BATT_TEMP_LOW,	1, 0),
-	AXP20X_IRQ(DIE_TEMP_HIGH,	2, 7),
-	AXP20X_IRQ(CHARG_I_LOW,		2, 6),
-	AXP20X_IRQ(DCDC1_V_LONG,	2, 5),
-	AXP20X_IRQ(DCDC2_V_LONG,	2, 4),
-	AXP20X_IRQ(DCDC3_V_LONG,	2, 3),
-	AXP20X_IRQ(PEK_SHORT,		2, 1),
-	AXP20X_IRQ(PEK_LONG,		2, 0),
-	AXP20X_IRQ(N_OE_PWR_ON,		3, 7),
-	AXP20X_IRQ(N_OE_PWR_OFF,	3, 6),
-	AXP20X_IRQ(VBUS_VALID,		3, 5),
-	AXP20X_IRQ(VBUS_NOT_VALID,	3, 4),
-	AXP20X_IRQ(VBUS_SESS_VALID,	3, 3),
-	AXP20X_IRQ(VBUS_SESS_END,	3, 2),
-	AXP20X_IRQ(LOW_PWR_LVL1,	3, 1),
-	AXP20X_IRQ(LOW_PWR_LVL2,	3, 0),
-	AXP20X_IRQ(TIMER,		4, 7),
-	AXP20X_IRQ(PEK_RIS_EDGE,	4, 6),
-	AXP20X_IRQ(PEK_FAL_EDGE,	4, 5),
-	AXP20X_IRQ(GPIO3_INPUT,		4, 3),
-	AXP20X_IRQ(GPIO2_INPUT,		4, 2),
-	AXP20X_IRQ(GPIO1_INPUT,		4, 1),
-	AXP20X_IRQ(GPIO0_INPUT,		4, 0),
+	INIT_REGMAP_IRQ(AXP20X, ACIN_OVER_V,		0, 7),
+	INIT_REGMAP_IRQ(AXP20X, ACIN_PLUGIN,		0, 6),
+	INIT_REGMAP_IRQ(AXP20X, ACIN_REMOVAL,	        0, 5),
+	INIT_REGMAP_IRQ(AXP20X, VBUS_OVER_V,		0, 4),
+	INIT_REGMAP_IRQ(AXP20X, VBUS_PLUGIN,		0, 3),
+	INIT_REGMAP_IRQ(AXP20X, VBUS_REMOVAL,	        0, 2),
+	INIT_REGMAP_IRQ(AXP20X, VBUS_V_LOW,		0, 1),
+	INIT_REGMAP_IRQ(AXP20X, BATT_PLUGIN,		1, 7),
+	INIT_REGMAP_IRQ(AXP20X, BATT_REMOVAL,	        1, 6),
+	INIT_REGMAP_IRQ(AXP20X, BATT_ENT_ACT_MODE,	1, 5),
+	INIT_REGMAP_IRQ(AXP20X, BATT_EXIT_ACT_MODE,	1, 4),
+	INIT_REGMAP_IRQ(AXP20X, CHARG,		        1, 3),
+	INIT_REGMAP_IRQ(AXP20X, CHARG_DONE,		1, 2),
+	INIT_REGMAP_IRQ(AXP20X, BATT_TEMP_HIGH,	        1, 1),
+	INIT_REGMAP_IRQ(AXP20X, BATT_TEMP_LOW,	        1, 0),
+	INIT_REGMAP_IRQ(AXP20X, DIE_TEMP_HIGH,	        2, 7),
+	INIT_REGMAP_IRQ(AXP20X, CHARG_I_LOW,		2, 6),
+	INIT_REGMAP_IRQ(AXP20X, DCDC1_V_LONG,	        2, 5),
+	INIT_REGMAP_IRQ(AXP20X, DCDC2_V_LONG,	        2, 4),
+	INIT_REGMAP_IRQ(AXP20X, DCDC3_V_LONG,	        2, 3),
+	INIT_REGMAP_IRQ(AXP20X, PEK_SHORT,		2, 1),
+	INIT_REGMAP_IRQ(AXP20X, PEK_LONG,		2, 0),
+	INIT_REGMAP_IRQ(AXP20X, N_OE_PWR_ON,		3, 7),
+	INIT_REGMAP_IRQ(AXP20X, N_OE_PWR_OFF,	        3, 6),
+	INIT_REGMAP_IRQ(AXP20X, VBUS_VALID,		3, 5),
+	INIT_REGMAP_IRQ(AXP20X, VBUS_NOT_VALID,	        3, 4),
+	INIT_REGMAP_IRQ(AXP20X, VBUS_SESS_VALID,	3, 3),
+	INIT_REGMAP_IRQ(AXP20X, VBUS_SESS_END,	        3, 2),
+	INIT_REGMAP_IRQ(AXP20X, LOW_PWR_LVL1,	        3, 1),
+	INIT_REGMAP_IRQ(AXP20X, LOW_PWR_LVL2,	        3, 0),
+	INIT_REGMAP_IRQ(AXP20X, TIMER,		        4, 7),
+	INIT_REGMAP_IRQ(AXP20X, PEK_RIS_EDGE,	        4, 6),
+	INIT_REGMAP_IRQ(AXP20X, PEK_FAL_EDGE,	        4, 5),
+	INIT_REGMAP_IRQ(AXP20X, GPIO3_INPUT,		4, 3),
+	INIT_REGMAP_IRQ(AXP20X, GPIO2_INPUT,		4, 2),
+	INIT_REGMAP_IRQ(AXP20X, GPIO1_INPUT,		4, 1),
+	INIT_REGMAP_IRQ(AXP20X, GPIO0_INPUT,		4, 0),
+};
+
+/* some IRQs are compatible with axp20x models */
+static const struct regmap_irq axp288_regmap_irqs[] = {
+	INIT_REGMAP_IRQ(AXP20X, VBUS_REMOVAL,           0, 2),
+	INIT_REGMAP_IRQ(AXP20X, VBUS_PLUGIN,            0, 3),
+	INIT_REGMAP_IRQ(AXP20X, VBUS_OVER_V,            0, 4),
+
+	INIT_REGMAP_IRQ(AXP20X, CHARG_DONE,             1, 2),
+	INIT_REGMAP_IRQ(AXP20X, CHARG,                  1, 3),
+	INIT_REGMAP_IRQ(AXP288, SAFE_QUIT,              1, 4),
+	INIT_REGMAP_IRQ(AXP288, SAFE_ENTER,             1, 5),
+	INIT_REGMAP_IRQ(AXP20X, BATT_REMOVAL,           1, 6),
+	INIT_REGMAP_IRQ(AXP20X, BATT_PLUGIN,            1, 7),
+
+	INIT_REGMAP_IRQ(AXP288, QWBTU,                  2, 0),
+	INIT_REGMAP_IRQ(AXP288, WBTU,                   2, 1),
+	INIT_REGMAP_IRQ(AXP288, QWBTO,                  2, 2),
+	INIT_REGMAP_IRQ(AXP288, WBTU,                   2, 3),
+	INIT_REGMAP_IRQ(AXP288, QCBTU,                  2, 4),
+	INIT_REGMAP_IRQ(AXP288, CBTU,                   2, 5),
+	INIT_REGMAP_IRQ(AXP288, QCBTO,                  2, 6),
+	INIT_REGMAP_IRQ(AXP288, CBTO,                   2, 7),
+
+	INIT_REGMAP_IRQ(AXP288, WL2,                    3, 0),
+	INIT_REGMAP_IRQ(AXP288, WL1,                    3, 1),
+	INIT_REGMAP_IRQ(AXP288, GPADC,                  3, 2),
+	INIT_REGMAP_IRQ(AXP288, OT,                     3, 7),
+
+	INIT_REGMAP_IRQ(AXP288, GPIO0,                  4, 0),
+	INIT_REGMAP_IRQ(AXP288, GPIO1,                  4, 1),
+	INIT_REGMAP_IRQ(AXP288, POKO,                   4, 2),
+	INIT_REGMAP_IRQ(AXP288, POKL,                   4, 3),
+	INIT_REGMAP_IRQ(AXP288, POKS,                   4, 4),
+	INIT_REGMAP_IRQ(AXP288, POKN,                   4, 5),
+	INIT_REGMAP_IRQ(AXP288, POKP,                   4, 6),
+	INIT_REGMAP_IRQ(AXP20X, TIMER,                  4, 7),
+
+	INIT_REGMAP_IRQ(AXP288, MV_CHNG,                5, 0),
+	INIT_REGMAP_IRQ(AXP288, BC_USB_CHNG,            5, 1),
 };
 
 static const struct of_device_id axp20x_of_match[] = {
@@ -128,16 +236,39 @@ static const struct i2c_device_id axp20x_i2c_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, axp20x_i2c_id);
 
+static struct acpi_device_id axp20x_acpi_match[] = {
+	{
+		.id = "INT33F4",
+		.driver_data = AXP288_ID,
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, axp20x_acpi_match);
+
 static const struct regmap_irq_chip axp20x_regmap_irq_chip = {
 	.name			= "axp20x_irq_chip",
 	.status_base		= AXP20X_IRQ1_STATE,
 	.ack_base		= AXP20X_IRQ1_STATE,
 	.mask_base		= AXP20X_IRQ1_EN,
-	.num_regs		= 5,
+	.mask_invert		= true,
+	.init_ack_masked	= true,
 	.irqs			= axp20x_regmap_irqs,
 	.num_irqs		= ARRAY_SIZE(axp20x_regmap_irqs),
+	.num_regs		= 5,
+
+};
+
+static const struct regmap_irq_chip axp288_regmap_irq_chip = {
+	.name			= "axp288_irq_chip",
+	.status_base		= AXP20X_IRQ1_STATE,
+	.ack_base		= AXP20X_IRQ1_STATE,
+	.mask_base		= AXP20X_IRQ1_EN,
 	.mask_invert		= true,
 	.init_ack_masked	= true,
+	.irqs			= axp288_regmap_irqs,
+	.num_irqs		= ARRAY_SIZE(axp288_regmap_irqs),
+	.num_regs		= 6,
+
 };
 
 static const char * const axp20x_supplies[] = {
@@ -161,36 +292,155 @@ static struct mfd_cell axp20x_cells[] = {
 	},
 };
 
+static struct resource axp288_adc_resources[] = {
+	{
+		.name  = "GPADC",
+		.start = AXP288_IRQ_GPADC,
+		.end   = AXP288_IRQ_GPADC,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct resource axp288_charger_resources[] = {
+	{
+		.start = AXP288_IRQ_OV,
+		.end   = AXP288_IRQ_OV,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.start = AXP288_IRQ_DONE,
+		.end   = AXP288_IRQ_DONE,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.start = AXP288_IRQ_CHARGING,
+		.end   = AXP288_IRQ_CHARGING,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.start = AXP288_IRQ_SAFE_QUIT,
+		.end   = AXP288_IRQ_SAFE_QUIT,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.start = AXP288_IRQ_SAFE_ENTER,
+		.end   = AXP288_IRQ_SAFE_ENTER,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.start = AXP288_IRQ_QCBTU,
+		.end   = AXP288_IRQ_QCBTU,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.start = AXP288_IRQ_CBTU,
+		.end   = AXP288_IRQ_CBTU,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.start = AXP288_IRQ_QCBTO,
+		.end   = AXP288_IRQ_QCBTO,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.start = AXP288_IRQ_CBTO,
+		.end   = AXP288_IRQ_CBTO,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct mfd_cell axp288_cells[] = {
+	{
+		.name = "axp288_adc",
+		.num_resources = ARRAY_SIZE(axp288_adc_resources),
+		.resources = axp288_adc_resources,
+	},
+	{
+		.name = "axp288_charger",
+		.num_resources = ARRAY_SIZE(axp288_charger_resources),
+		.resources = axp288_charger_resources,
+	},
+	{
+		.name = "axp288_battery",
+		.num_resources = ARRAY_SIZE(axp288_battery_resources),
+		.resources = axp288_battery_resources,
+	},
+};
+
 static struct axp20x_dev *axp20x_pm_power_off;
 static void axp20x_power_off(void)
 {
+	if (axp20x_pm_power_off->variant == AXP288_ID)
+		return;
+
 	regmap_write(axp20x_pm_power_off->regmap, AXP20X_OFF_CTRL,
 		     AXP20X_OFF);
 }
 
+static int axp20x_match_device(struct axp20x_dev *axp20x, struct device *dev)
+{
+	const struct acpi_device_id *acpi_id;
+	const struct of_device_id *of_id;
+
+	if (dev->of_node) {
+		of_id = of_match_device(axp20x_of_match, dev);
+		if (!of_id) {
+			dev_err(dev, "Unable to match OF ID\n");
+			return -ENODEV;
+		}
+		axp20x->variant = (long) of_id->data;
+	} else {
+		acpi_id = acpi_match_device(dev->driver->acpi_match_table, dev);
+		if (!acpi_id || !acpi_id->driver_data) {
+			dev_err(dev, "Unable to match ACPI ID and data\n");
+			return -ENODEV;
+		}
+		axp20x->variant = (long) acpi_id->driver_data;
+	}
+
+	switch (axp20x->variant) {
+	case AXP202_ID:
+	case AXP209_ID:
+		axp20x->nr_cells = ARRAY_SIZE(axp20x_cells);
+		axp20x->cells = axp20x_cells;
+		axp20x->regmap_cfg = &axp20x_regmap_config;
+		axp20x->regmap_irq_chip = &axp20x_regmap_irq_chip;
+		break;
+	case AXP288_ID:
+		axp20x->cells = axp288_cells;
+		axp20x->nr_cells = ARRAY_SIZE(axp288_cells);
+		axp20x->regmap_cfg = &axp288_regmap_config;
+		axp20x->regmap_irq_chip = &axp288_regmap_irq_chip;
+		break;
+	default:
+		dev_err(dev, "unsupported AXP20X ID %lu\n", axp20x->variant);
+		return -EINVAL;
+	}
+	dev_info(dev, "AXP20x variant %s found\n",
+		axp20x_model_names[axp20x->variant]);
+
+	return 0;
+}
+
 static int axp20x_i2c_probe(struct i2c_client *i2c,
 			 const struct i2c_device_id *id)
 {
 	struct axp20x_dev *axp20x;
-	const struct of_device_id *of_id;
 	int ret;
 
 	axp20x = devm_kzalloc(&i2c->dev, sizeof(*axp20x), GFP_KERNEL);
 	if (!axp20x)
 		return -ENOMEM;
 
-	of_id = of_match_device(axp20x_of_match, &i2c->dev);
-	if (!of_id) {
-		dev_err(&i2c->dev, "Unable to setup AXP20X data\n");
-		return -ENODEV;
-	}
-	axp20x->variant = (long) of_id->data;
+	ret = axp20x_match_device(axp20x, &i2c->dev);
+	if (ret)
+		return ret;
 
 	axp20x->i2c_client = i2c;
 	axp20x->dev = &i2c->dev;
 	dev_set_drvdata(axp20x->dev, axp20x);
 
-	axp20x->regmap = devm_regmap_init_i2c(i2c, &axp20x_regmap_config);
+	axp20x->regmap = devm_regmap_init_i2c(i2c, axp20x->regmap_cfg);
 	if (IS_ERR(axp20x->regmap)) {
 		ret = PTR_ERR(axp20x->regmap);
 		dev_err(&i2c->dev, "regmap init failed: %d\n", ret);
@@ -199,15 +449,15 @@ static int axp20x_i2c_probe(struct i2c_client *i2c,
 
 	ret = regmap_add_irq_chip(axp20x->regmap, i2c->irq,
 				  IRQF_ONESHOT | IRQF_SHARED, -1,
-				  &axp20x_regmap_irq_chip,
+				  axp20x->regmap_irq_chip,
 				  &axp20x->regmap_irqc);
 	if (ret) {
 		dev_err(&i2c->dev, "failed to add irq chip: %d\n", ret);
 		return ret;
 	}
 
-	ret = mfd_add_devices(axp20x->dev, -1, axp20x_cells,
-			      ARRAY_SIZE(axp20x_cells), NULL, 0, NULL);
+	ret = mfd_add_devices(axp20x->dev, -1, axp20x->cells,
+			axp20x->nr_cells, NULL, 0, NULL);
 
 	if (ret) {
 		dev_err(&i2c->dev, "failed to add MFD devices: %d\n", ret);
@@ -245,6 +495,7 @@ static struct i2c_driver axp20x_i2c_driver = {
 		.name	= "axp20x",
 		.owner	= THIS_MODULE,
 		.of_match_table	= of_match_ptr(axp20x_of_match),
+		.acpi_match_table = ACPI_PTR(axp20x_acpi_match),
 	},
 	.probe		= axp20x_i2c_probe,
 	.remove		= axp20x_i2c_remove,
diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h
index d0e31a2287a..81589d176ae 100644
--- a/include/linux/mfd/axp20x.h
+++ b/include/linux/mfd/axp20x.h
@@ -14,6 +14,8 @@
 enum {
 	AXP202_ID = 0,
 	AXP209_ID,
+	AXP288_ID,
+	NR_AXP20X_VARIANTS,
 };
 
 #define AXP20X_DATACACHE(m)		(0x04 + (m))
@@ -49,11 +51,13 @@ enum {
 #define AXP20X_IRQ3_EN			0x42
 #define AXP20X_IRQ4_EN			0x43
 #define AXP20X_IRQ5_EN			0x44
+#define AXP20X_IRQ6_EN			0x45
 #define AXP20X_IRQ1_STATE		0x48
 #define AXP20X_IRQ2_STATE		0x49
 #define AXP20X_IRQ3_STATE		0x4a
 #define AXP20X_IRQ4_STATE		0x4b
 #define AXP20X_IRQ5_STATE		0x4c
+#define AXP20X_IRQ6_STATE		0x4d
 
 /* ADC */
 #define AXP20X_ACIN_V_ADC_H		0x56
@@ -116,6 +120,15 @@ enum {
 #define AXP20X_CC_CTRL			0xb8
 #define AXP20X_FG_RES			0xb9
 
+/* AXP288 specific registers */
+#define AXP288_PMIC_ADC_H               0x56
+#define AXP288_PMIC_ADC_L               0x57
+#define AXP288_ADC_TS_PIN_CTRL          0x84
+
+#define AXP288_PMIC_ADC_EN              0x84
+#define AXP288_FG_TUNE5			0xed
+
+
 /* Regulators IDs */
 enum {
 	AXP20X_LDO1 = 0,
@@ -169,12 +182,58 @@ enum {
 	AXP20X_IRQ_GPIO0_INPUT,
 };
 
+enum axp288_irqs {
+	AXP288_IRQ_VBUS_FALL     = 2,
+	AXP288_IRQ_VBUS_RISE,
+	AXP288_IRQ_OV,
+	AXP288_IRQ_FALLING_ALT,
+	AXP288_IRQ_RISING_ALT,
+	AXP288_IRQ_OV_ALT,
+	AXP288_IRQ_DONE          = 10,
+	AXP288_IRQ_CHARGING,
+	AXP288_IRQ_SAFE_QUIT,
+	AXP288_IRQ_SAFE_ENTER,
+	AXP288_IRQ_ABSENT,
+	AXP288_IRQ_APPEND,
+	AXP288_IRQ_QWBTU,
+	AXP288_IRQ_WBTU,
+	AXP288_IRQ_QWBTO,
+	AXP288_IRQ_WBTO,
+	AXP288_IRQ_QCBTU,
+	AXP288_IRQ_CBTU,
+	AXP288_IRQ_QCBTO,
+	AXP288_IRQ_CBTO,
+	AXP288_IRQ_WL2,
+	AXP288_IRQ_WL1,
+	AXP288_IRQ_GPADC,
+	AXP288_IRQ_OT            = 31,
+	AXP288_IRQ_GPIO0,
+	AXP288_IRQ_GPIO1,
+	AXP288_IRQ_POKO,
+	AXP288_IRQ_POKL,
+	AXP288_IRQ_POKS,
+	AXP288_IRQ_POKN,
+	AXP288_IRQ_POKP,
+	AXP288_IRQ_TIMER,
+	AXP288_IRQ_MV_CHNG,
+	AXP288_IRQ_BC_USB_CHNG,
+};
+
+#define AXP288_TS_ADC_H		0x58
+#define AXP288_TS_ADC_L		0x59
+#define AXP288_GP_ADC_H		0x5a
+#define AXP288_GP_ADC_L		0x5b
+
 struct axp20x_dev {
 	struct device			*dev;
 	struct i2c_client		*i2c_client;
 	struct regmap			*regmap;
 	struct regmap_irq_chip_data	*regmap_irqc;
 	long				variant;
+	int                             nr_cells;
+	struct mfd_cell                 *cells;
+	const struct regmap_config	*regmap_cfg;
+	const struct regmap_irq_chip	*regmap_irq_chip;
 };
 
 #endif /* __LINUX_MFD_AXP20X_H */
-- 
cgit v1.2.3-70-g09d2


From 66be7d2bcd826344894be09dc385f9f805136b84 Mon Sep 17 00:00:00 2001
From: Henning Rogge <hrogge@gmail.com>
Date: Fri, 12 Sep 2014 08:58:49 +0200
Subject: cfg80211: add ops to query mesh proxy path table

Add two new cfg80211 operations for querying a table with proxied mesh
paths.

Signed-off-by: Henning Rogge <henning.rogge@fkie.fraunhofer.de>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  7 ++++
 include/uapi/linux/nl80211.h |  6 +++
 net/wireless/nl80211.c       | 99 ++++++++++++++++++++++++++++++++++++++++++++
 net/wireless/rdev-ops.h      | 27 +++++++++++-
 net/wireless/trace.h         | 45 ++++++++++++++++++++
 5 files changed, 183 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index a2ddcf2398f..3f3aaa06adb 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2146,6 +2146,8 @@ struct cfg80211_qos_map {
  * @change_mpath: change a given mesh path
  * @get_mpath: get a mesh path for the given parameters
  * @dump_mpath: dump mesh path callback -- resume dump at index @idx
+ * @get_mpp: get a mesh proxy path for the given parameters
+ * @dump_mpp: dump mesh proxy path callback -- resume dump at index @idx
  * @join_mesh: join the mesh network with the specified parameters
  *	(invoked with the wireless_dev mutex held)
  * @leave_mesh: leave the current mesh network
@@ -2396,6 +2398,11 @@ struct cfg80211_ops {
 	int	(*dump_mpath)(struct wiphy *wiphy, struct net_device *dev,
 			      int idx, u8 *dst, u8 *next_hop,
 			      struct mpath_info *pinfo);
+	int	(*get_mpp)(struct wiphy *wiphy, struct net_device *dev,
+			   u8 *dst, u8 *mpp, struct mpath_info *pinfo);
+	int	(*dump_mpp)(struct wiphy *wiphy, struct net_device *dev,
+			    int idx, u8 *dst, u8 *mpp,
+			    struct mpath_info *pinfo);
 	int	(*get_mesh_config)(struct wiphy *wiphy,
 				struct net_device *dev,
 				struct mesh_config *conf);
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 4b28dc07bcb..846071b0cde 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -738,6 +738,10 @@
  *	before removing a station entry entirely, or before disassociating
  *	or similar, cleanup will happen in the driver/device in this case.
  *
+ * @NL80211_CMD_GET_MPP: Get mesh path attributes for mesh proxy path to
+ *	destination %NL80211_ATTR_MAC on the interface identified by
+ *	%NL80211_ATTR_IFINDEX.
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -912,6 +916,8 @@ enum nl80211_commands {
 	NL80211_CMD_ADD_TX_TS,
 	NL80211_CMD_DEL_TX_TS,
 
+	NL80211_CMD_GET_MPP,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index cb9f5a44ffa..d527aa0706c 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4624,6 +4624,96 @@ static int nl80211_del_mpath(struct sk_buff *skb, struct genl_info *info)
 	return rdev_del_mpath(rdev, dev, dst);
 }
 
+static int nl80211_get_mpp(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	int err;
+	struct net_device *dev = info->user_ptr[1];
+	struct mpath_info pinfo;
+	struct sk_buff *msg;
+	u8 *dst = NULL;
+	u8 mpp[ETH_ALEN];
+
+	memset(&pinfo, 0, sizeof(pinfo));
+
+	if (!info->attrs[NL80211_ATTR_MAC])
+		return -EINVAL;
+
+	dst = nla_data(info->attrs[NL80211_ATTR_MAC]);
+
+	if (!rdev->ops->get_mpp)
+		return -EOPNOTSUPP;
+
+	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT)
+		return -EOPNOTSUPP;
+
+	err = rdev_get_mpp(rdev, dev, dst, mpp, &pinfo);
+	if (err)
+		return err;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	if (nl80211_send_mpath(msg, info->snd_portid, info->snd_seq, 0,
+			       dev, dst, mpp, &pinfo) < 0) {
+		nlmsg_free(msg);
+		return -ENOBUFS;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int nl80211_dump_mpp(struct sk_buff *skb,
+			    struct netlink_callback *cb)
+{
+	struct mpath_info pinfo;
+	struct cfg80211_registered_device *rdev;
+	struct wireless_dev *wdev;
+	u8 dst[ETH_ALEN];
+	u8 mpp[ETH_ALEN];
+	int path_idx = cb->args[2];
+	int err;
+
+	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
+	if (err)
+		return err;
+
+	if (!rdev->ops->dump_mpp) {
+		err = -EOPNOTSUPP;
+		goto out_err;
+	}
+
+	if (wdev->iftype != NL80211_IFTYPE_MESH_POINT) {
+		err = -EOPNOTSUPP;
+		goto out_err;
+	}
+
+	while (1) {
+		err = rdev_dump_mpp(rdev, wdev->netdev, path_idx, dst,
+				    mpp, &pinfo);
+		if (err == -ENOENT)
+			break;
+		if (err)
+			goto out_err;
+
+		if (nl80211_send_mpath(skb, NETLINK_CB(cb->skb).portid,
+				       cb->nlh->nlmsg_seq, NLM_F_MULTI,
+				       wdev->netdev, dst, mpp,
+				       &pinfo) < 0)
+			goto out;
+
+		path_idx++;
+	}
+
+ out:
+	cb->args[2] = path_idx;
+	err = skb->len;
+ out_err:
+	nl80211_finish_wdev_dump(rdev);
+	return err;
+}
+
 static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -9773,6 +9863,15 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_GET_MPP,
+		.doit = nl80211_get_mpp,
+		.dumpit = nl80211_dump_mpp,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 	{
 		.cmd = NL80211_CMD_SET_MPATH,
 		.doit = nl80211_set_mpath,
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index f6d457d6a55..c09e697bcb1 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -263,6 +263,18 @@ static inline int rdev_get_mpath(struct cfg80211_registered_device *rdev,
 
 }
 
+static inline int rdev_get_mpp(struct cfg80211_registered_device *rdev,
+			       struct net_device *dev, u8 *dst, u8 *mpp,
+			       struct mpath_info *pinfo)
+{
+	int ret;
+
+	trace_rdev_get_mpp(&rdev->wiphy, dev, dst, mpp);
+	ret = rdev->ops->get_mpp(&rdev->wiphy, dev, dst, mpp, pinfo);
+	trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo);
+	return ret;
+}
+
 static inline int rdev_dump_mpath(struct cfg80211_registered_device *rdev,
 				  struct net_device *dev, int idx, u8 *dst,
 				  u8 *next_hop, struct mpath_info *pinfo)
@@ -271,7 +283,20 @@ static inline int rdev_dump_mpath(struct cfg80211_registered_device *rdev,
 	int ret;
 	trace_rdev_dump_mpath(&rdev->wiphy, dev, idx, dst, next_hop);
 	ret = rdev->ops->dump_mpath(&rdev->wiphy, dev, idx, dst, next_hop,
-				     pinfo);
+				    pinfo);
+	trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo);
+	return ret;
+}
+
+static inline int rdev_dump_mpp(struct cfg80211_registered_device *rdev,
+				struct net_device *dev, int idx, u8 *dst,
+				u8 *mpp, struct mpath_info *pinfo)
+
+{
+	int ret;
+
+	trace_rdev_dump_mpp(&rdev->wiphy, dev, idx, dst, mpp);
+	ret = rdev->ops->dump_mpp(&rdev->wiphy, dev, idx, dst, mpp, pinfo);
 	trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo);
 	return ret;
 }
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 625a6e6d116..8e4f8f04332 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -801,6 +801,51 @@ TRACE_EVENT(rdev_dump_mpath,
 		  MAC_PR_ARG(next_hop))
 );
 
+TRACE_EVENT(rdev_get_mpp,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 u8 *dst, u8 *mpp),
+	TP_ARGS(wiphy, netdev, dst, mpp),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(dst)
+		MAC_ENTRY(mpp)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(dst, dst);
+		MAC_ASSIGN(mpp, mpp);
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", destination: " MAC_PR_FMT
+		  ", mpp: " MAC_PR_FMT, WIPHY_PR_ARG, NETDEV_PR_ARG,
+		  MAC_PR_ARG(dst), MAC_PR_ARG(mpp))
+);
+
+TRACE_EVENT(rdev_dump_mpp,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int idx,
+		 u8 *dst, u8 *mpp),
+	TP_ARGS(wiphy, netdev, idx, mpp, dst),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(dst)
+		MAC_ENTRY(mpp)
+		__field(int, idx)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(dst, dst);
+		MAC_ASSIGN(mpp, mpp);
+		__entry->idx = idx;
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", index: %d, destination: "
+		  MAC_PR_FMT ", mpp: " MAC_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->idx, MAC_PR_ARG(dst),
+		  MAC_PR_ARG(mpp))
+);
+
 TRACE_EVENT(rdev_return_int_mpath_info,
 	TP_PROTO(struct wiphy *wiphy, int ret, struct mpath_info *pinfo),
 	TP_ARGS(wiphy, ret, pinfo),
-- 
cgit v1.2.3-70-g09d2


From 2ba45384e5426b9a4aeb77656dce0bf3250ce54e Mon Sep 17 00:00:00 2001
From: Luciano Coelho <luciano.coelho@intel.com>
Date: Wed, 8 Oct 2014 09:48:35 +0300
Subject: mac80211: add device_timestamp to the ieee80211_channel_switch struct

Some devices may need the device timestamp in order to synchronize the
channel switch.  To pass this value back to the driver, add it to the
channel switch structure and copy the device_timestamp value received
in the rx info structure into it.

Signed-off-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  3 +++
 net/mac80211/mlme.c    | 15 ++++++++++-----
 net/mac80211/trace.h   |  2 ++
 3 files changed, 15 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 0ad1f47d2dc..ec0a5b07055 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1117,6 +1117,8 @@ struct ieee80211_conf {
  *	Function (TSF) timer when the frame containing the channel switch
  *	announcement was received. This is simply the rx.mactime parameter
  *	the driver passed into mac80211.
+ * @device_timestamp: arbitrary timestamp for the device, this is the
+ *	rx.device_timestamp parameter the driver passed to mac80211.
  * @block_tx: Indicates whether transmission must be blocked before the
  *	scheduled channel switch, as indicated by the AP.
  * @chandef: the new channel to switch to
@@ -1124,6 +1126,7 @@ struct ieee80211_conf {
  */
 struct ieee80211_channel_switch {
 	u64 timestamp;
+	u32 device_timestamp;
 	bool block_tx;
 	struct cfg80211_chan_def chandef;
 	u8 count;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 2de88704278..f2e048fa250 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1046,7 +1046,8 @@ static void ieee80211_chswitch_timer(unsigned long data)
 
 static void
 ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
-				 u64 timestamp, struct ieee802_11_elems *elems,
+				 u64 timestamp, u32 device_timestamp,
+				 struct ieee802_11_elems *elems,
 				 bool beacon)
 {
 	struct ieee80211_local *local = sdata->local;
@@ -1154,6 +1155,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 		/* use driver's channel switch callback */
 		struct ieee80211_channel_switch ch_switch = {
 			.timestamp = timestamp,
+			.device_timestamp = device_timestamp,
 			.block_tx = csa_ie.mode,
 			.chandef = csa_ie.chandef,
 			.count = csa_ie.count,
@@ -3203,6 +3205,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems);
 
 	ieee80211_sta_process_chanswitch(sdata, rx_status->mactime,
+					 rx_status->device_timestamp,
 					 &elems, true);
 
 	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_WMM) &&
@@ -3334,8 +3337,9 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 				break;
 
 			ieee80211_sta_process_chanswitch(sdata,
-							 rx_status->mactime,
-							 &elems, false);
+						 rx_status->mactime,
+						 rx_status->device_timestamp,
+						 &elems, false);
 		} else if (mgmt->u.action.category == WLAN_CATEGORY_PUBLIC) {
 			ies_len = skb->len -
 				  offsetof(struct ieee80211_mgmt,
@@ -3356,8 +3360,9 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 				&mgmt->u.action.u.ext_chan_switch.data;
 
 			ieee80211_sta_process_chanswitch(sdata,
-							 rx_status->mactime,
-							 &elems, false);
+						 rx_status->mactime,
+						 rx_status->device_timestamp,
+						 &elems, false);
 		}
 		break;
 	}
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 38fae7ebe98..853c440218d 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -995,6 +995,7 @@ TRACE_EVENT(drv_channel_switch,
 		LOCAL_ENTRY
 		CHANDEF_ENTRY
 		__field(u64, timestamp)
+		__field(u32, device_timestamp)
 		__field(bool, block_tx)
 		__field(u8, count)
 	),
@@ -1003,6 +1004,7 @@ TRACE_EVENT(drv_channel_switch,
 		LOCAL_ASSIGN;
 		CHANDEF_ASSIGN(&ch_switch->chandef)
 		__entry->timestamp = ch_switch->timestamp;
+		__entry->device_timestamp = ch_switch->device_timestamp;
 		__entry->block_tx = ch_switch->block_tx;
 		__entry->count = ch_switch->count;
 	),
-- 
cgit v1.2.3-70-g09d2


From e9a21949b79414dda42a017855b288901c07e613 Mon Sep 17 00:00:00 2001
From: Luciano Coelho <luciano.coelho@intel.com>
Date: Wed, 8 Oct 2014 09:48:36 +0300
Subject: mac80211: add extended channel switching capability if the driver
 supports CSA

The Extended Channel Switching capability bit in the extended
capabilities element must be set if the driver supports CSA on
non-beaconing interfaces.

Since this capability needs to be set during driver registration, the
extended_capabiliities global variable needs to be moved to the local
structure so that it can be modified.

Signed-off-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h  |  5 +++++
 net/mac80211/ieee80211_i.h |  3 +++
 net/mac80211/main.c        | 20 +++++++++++---------
 3 files changed, 19 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index b1be39c7693..5fab17b382b 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1998,6 +1998,11 @@ enum ieee80211_tdls_actioncode {
 	WLAN_TDLS_DISCOVERY_REQUEST = 10,
 };
 
+/* Extended Channel Switching capability to be set in the 1st byte of
+ * the @WLAN_EID_EXT_CAPABILITY information element
+ */
+#define WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING	BIT(2)
+
 /* Interworking capabilities are set in 7th bit of 4th byte of the
  * @WLAN_EID_EXT_CAPABILITY information element
  */
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index c2aaec4dfcf..a9cc4912898 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1307,6 +1307,9 @@ struct ieee80211_local {
 	/* virtual monitor interface */
 	struct ieee80211_sub_if_data __rcu *monitor_sdata;
 	struct cfg80211_chan_def monitor_chandef;
+
+	/* extended capabilities provided by mac80211 */
+	u8 ext_capa[8];
 };
 
 static inline struct ieee80211_sub_if_data *
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 0de7c93bf62..107d1c884de 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -478,11 +478,6 @@ static const struct ieee80211_vht_cap mac80211_vht_capa_mod_mask = {
 	},
 };
 
-static const u8 extended_capabilities[] = {
-	0, 0, 0, 0, 0, 0, 0,
-	WLAN_EXT_CAPA8_OPMODE_NOTIF,
-};
-
 struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 					const struct ieee80211_ops *ops)
 {
@@ -539,10 +534,6 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 			WIPHY_FLAG_REPORTS_OBSS |
 			WIPHY_FLAG_OFFCHAN_TX;
 
-	wiphy->extended_capabilities = extended_capabilities;
-	wiphy->extended_capabilities_mask = extended_capabilities;
-	wiphy->extended_capabilities_len = ARRAY_SIZE(extended_capabilities);
-
 	if (ops->remain_on_channel)
 		wiphy->flags |= WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
 
@@ -591,6 +582,13 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 	wiphy->ht_capa_mod_mask = &mac80211_ht_capa_mod_mask;
 	wiphy->vht_capa_mod_mask = &mac80211_vht_capa_mod_mask;
 
+	local->ext_capa[7] = WLAN_EXT_CAPA8_OPMODE_NOTIF;
+
+	wiphy->extended_capabilities = local->ext_capa;
+	wiphy->extended_capabilities_mask = local->ext_capa;
+	wiphy->extended_capabilities_len =
+		ARRAY_SIZE(local->ext_capa);
+
 	INIT_LIST_HEAD(&local->interfaces);
 
 	__hw_addr_init(&local->mc_list);
@@ -958,6 +956,10 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	if (local->hw.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)
 		local->hw.wiphy->flags |= WIPHY_FLAG_TDLS_EXTERNAL_SETUP;
 
+	/* mac80211 supports eCSA, if the driver supports STA CSA at all */
+	if (local->hw.flags & IEEE80211_HW_CHANCTX_STA_CSA)
+		local->ext_capa[0] |= WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING;
+
 	local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM;
 
 	result = wiphy_register(local->hw.wiphy);
-- 
cgit v1.2.3-70-g09d2


From 6d027bcc8a4e2518ae825b0ff3dd069ab1abfe96 Mon Sep 17 00:00:00 2001
From: Luciano Coelho <luciano.coelho@intel.com>
Date: Wed, 8 Oct 2014 09:48:37 +0300
Subject: mac80211: add pre_channel_switch driver operation

Some drivers may need to prepare for a channel switch also when it is
initiated from the remote side (eg. station, P2P client).  To make
this possible, add a generic callback that can be called for all
interface types.

Signed-off-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    |  7 +++++++
 net/mac80211/cfg.c        | 11 +++++++++++
 net/mac80211/driver-ops.h | 18 ++++++++++++++++++
 net/mac80211/mlme.c       | 25 +++++++++++++++++--------
 net/mac80211/trace.h      | 33 +++++++++++++++++++++++++++++++++
 5 files changed, 86 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index ec0a5b07055..19e4159ce3a 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2832,6 +2832,10 @@ enum ieee80211_roc_type {
  *	transmitted and then call ieee80211_csa_finish().
  *	If the CSA count starts as zero or 1, this function will not be called,
  *	since there won't be any time to beacon before the switch anyway.
+ * @pre_channel_switch: This is an optional callback that is called
+ *	before a channel switch procedure is started (ie. when a STA
+ *	gets a CSA or an userspace initiated channel-switch), allowing
+ *	the driver to prepare for the channel switch.
  *
  * @join_ibss: Join an IBSS (on an IBSS interface); this is called after all
  *	information in bss_conf is set up and the beacon can be retrieved. A
@@ -3038,6 +3042,9 @@ struct ieee80211_ops {
 	void (*channel_switch_beacon)(struct ieee80211_hw *hw,
 				      struct ieee80211_vif *vif,
 				      struct cfg80211_chan_def *chandef);
+	int (*pre_channel_switch)(struct ieee80211_hw *hw,
+				  struct ieee80211_vif *vif,
+				  struct ieee80211_channel_switch *ch_switch);
 
 	int (*join_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
 	void (*leave_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 3a04f2edd3c..647a2f6eb7d 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3104,6 +3104,7 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_channel_switch ch_switch;
 	struct ieee80211_chanctx_conf *conf;
 	struct ieee80211_chanctx *chanctx;
 	int err, changed = 0;
@@ -3139,6 +3140,10 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 		goto out;
 	}
 
+	err = drv_pre_channel_switch(sdata, &ch_switch);
+	if (err)
+		goto out;
+
 	err = ieee80211_vif_reserve_chanctx(sdata, &params->chandef,
 					    chanctx->mode,
 					    params->radar_required);
@@ -3152,6 +3157,12 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 		goto out;
 	}
 
+	ch_switch.timestamp = 0;
+	ch_switch.device_timestamp = 0;
+	ch_switch.block_tx = params->block_tx;
+	ch_switch.chandef = params->chandef;
+	ch_switch.count = params->count;
+
 	err = ieee80211_set_csa_beacon(sdata, params, &changed);
 	if (err) {
 		ieee80211_vif_unreserve_chanctx(sdata);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 196d48c6813..5522672129c 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1196,6 +1196,24 @@ drv_channel_switch_beacon(struct ieee80211_sub_if_data *sdata,
 	}
 }
 
+static inline int
+drv_pre_channel_switch(struct ieee80211_sub_if_data *sdata,
+		       struct ieee80211_channel_switch *ch_switch)
+{
+	struct ieee80211_local *local = sdata->local;
+	int ret = 0;
+
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
+
+	trace_drv_pre_channel_switch(local, sdata, ch_switch);
+	if (local->ops->pre_channel_switch)
+		ret = local->ops->pre_channel_switch(&local->hw, &sdata->vif,
+						     ch_switch);
+	trace_drv_return_int(local, ret);
+	return ret;
+}
+
 static inline int drv_join_ibss(struct ieee80211_local *local,
 				struct ieee80211_sub_if_data *sdata)
 {
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index f2e048fa250..d23d6d97e45 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1057,6 +1057,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_chanctx *chanctx;
 	enum ieee80211_band current_band;
 	struct ieee80211_csa_ie csa_ie;
+	struct ieee80211_channel_switch ch_switch;
 	int res;
 
 	sdata_assert_lock(sdata);
@@ -1128,6 +1129,22 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
+	ch_switch.timestamp = timestamp;
+	ch_switch.device_timestamp = device_timestamp;
+	ch_switch.block_tx = csa_ie.mode;
+	ch_switch.chandef = csa_ie.chandef;
+	ch_switch.count = csa_ie.count;
+
+	if (drv_pre_channel_switch(sdata, &ch_switch)) {
+		sdata_info(sdata,
+			   "preparing for channel switch failed, disconnecting\n");
+		ieee80211_queue_work(&local->hw,
+				     &ifmgd->csa_connection_drop_work);
+		mutex_unlock(&local->chanctx_mtx);
+		mutex_unlock(&local->mtx);
+		return;
+	}
+
 	res = ieee80211_vif_reserve_chanctx(sdata, &csa_ie.chandef,
 					    chanctx->mode, false);
 	if (res) {
@@ -1153,14 +1170,6 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 
 	if (local->ops->channel_switch) {
 		/* use driver's channel switch callback */
-		struct ieee80211_channel_switch ch_switch = {
-			.timestamp = timestamp,
-			.device_timestamp = device_timestamp,
-			.block_tx = csa_ie.mode,
-			.chandef = csa_ie.chandef,
-			.count = csa_ie.count,
-		};
-
 		drv_channel_switch(local, &ch_switch);
 		return;
 	}
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 853c440218d..30476d2c730 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -2108,6 +2108,39 @@ TRACE_EVENT(drv_channel_switch_beacon,
 	)
 );
 
+TRACE_EVENT(drv_pre_channel_switch,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_channel_switch *ch_switch),
+
+	TP_ARGS(local, sdata, ch_switch),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		CHANDEF_ENTRY
+		__field(u64, timestamp)
+		__field(bool, block_tx)
+		__field(u8, count)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		CHANDEF_ASSIGN(&ch_switch->chandef)
+		__entry->timestamp = ch_switch->timestamp;
+		__entry->block_tx = ch_switch->block_tx;
+		__entry->count = ch_switch->count;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT VIF_PR_FMT " prepare channel switch to "
+		CHANDEF_PR_FMT  " count:%d block_tx:%d timestamp:%llu",
+		LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->count,
+		__entry->block_tx, __entry->timestamp
+	)
+);
+
 
 #ifdef CONFIG_MAC80211_MESSAGE_TRACING
 #undef TRACE_SYSTEM
-- 
cgit v1.2.3-70-g09d2


From f1d65583bc5bd43ace8abb9d4f4d9e8da407f708 Mon Sep 17 00:00:00 2001
From: Luciano Coelho <luciano.coelho@intel.com>
Date: Wed, 8 Oct 2014 09:48:38 +0300
Subject: mac80211: add post_channel_switch driver operation

As a counterpart to the pre_channel_switch operation, add a
post_channel_switch operation.  This allows the drivers to go back to
a normal configuration after the channel switch is completed.

Signed-off-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    |  6 ++++++
 net/mac80211/cfg.c        |  7 ++++++-
 net/mac80211/driver-ops.h | 16 ++++++++++++++++
 net/mac80211/mlme.c       |  9 +++++++++
 net/mac80211/trace.h      |  6 ++++++
 5 files changed, 43 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 19e4159ce3a..7861ed875c4 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2836,6 +2836,9 @@ enum ieee80211_roc_type {
  *	before a channel switch procedure is started (ie. when a STA
  *	gets a CSA or an userspace initiated channel-switch), allowing
  *	the driver to prepare for the channel switch.
+ * @post_channel_switch: This is an optional callback that is called
+ *	after a channel switch procedure is completed, allowing the
+ *	driver to go back to a normal configuration.
  *
  * @join_ibss: Join an IBSS (on an IBSS interface); this is called after all
  *	information in bss_conf is set up and the beacon can be retrieved. A
@@ -3046,6 +3049,9 @@ struct ieee80211_ops {
 				  struct ieee80211_vif *vif,
 				  struct ieee80211_channel_switch *ch_switch);
 
+	int (*post_channel_switch)(struct ieee80211_hw *hw,
+				   struct ieee80211_vif *vif);
+
 	int (*join_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
 	void (*leave_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
 	u32 (*get_expected_throughput)(struct ieee80211_sta *sta);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 647a2f6eb7d..9d58b30b096 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2919,7 +2919,6 @@ static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata)
 		return err;
 
 	ieee80211_bss_info_change_notify(sdata, changed);
-	cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef);
 
 	if (sdata->csa_block_tx) {
 		ieee80211_wake_vif_queues(local, sdata,
@@ -2927,6 +2926,12 @@ static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata)
 		sdata->csa_block_tx = false;
 	}
 
+	err = drv_post_channel_switch(sdata);
+	if (err)
+		return err;
+
+	cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef);
+
 	return 0;
 }
 
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 5522672129c..0a609064476 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1214,6 +1214,22 @@ drv_pre_channel_switch(struct ieee80211_sub_if_data *sdata,
 	return ret;
 }
 
+static inline int
+drv_post_channel_switch(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	int ret = 0;
+
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
+
+	trace_drv_post_channel_switch(local, sdata);
+	if (local->ops->post_channel_switch)
+		ret = local->ops->post_channel_switch(&local->hw, &sdata->vif);
+	trace_drv_return_int(local, ret);
+	return ret;
+}
+
 static inline int drv_join_ibss(struct ieee80211_local *local,
 				struct ieee80211_sub_if_data *sdata)
 {
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index d23d6d97e45..cb1a8c3bc73 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1010,6 +1010,15 @@ static void ieee80211_chswitch_work(struct work_struct *work)
 		sdata->csa_block_tx = false;
 	}
 
+	ret = drv_post_channel_switch(sdata);
+	if (ret) {
+		sdata_info(sdata,
+			   "driver post channel switch failed, disconnecting\n");
+		ieee80211_queue_work(&local->hw,
+				     &ifmgd->csa_connection_drop_work);
+		goto out;
+	}
+
 	ieee80211_sta_reset_beacon_monitor(sdata);
 	ieee80211_sta_reset_conn_monitor(sdata);
 
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 30476d2c730..ca0e12dd23c 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -2141,6 +2141,12 @@ TRACE_EVENT(drv_pre_channel_switch,
 	)
 );
 
+DEFINE_EVENT(local_sdata_evt, drv_post_channel_switch,
+	     TP_PROTO(struct ieee80211_local *local,
+		      struct ieee80211_sub_if_data *sdata),
+	     TP_ARGS(local, sdata)
+);
+
 
 #ifdef CONFIG_MAC80211_MESSAGE_TRACING
 #undef TRACE_SYSTEM
-- 
cgit v1.2.3-70-g09d2


From 0f791eb47f8222fd594e6f8a090632344ef23924 Mon Sep 17 00:00:00 2001
From: Luciano Coelho <luciano.coelho@intel.com>
Date: Wed, 8 Oct 2014 09:48:40 +0300
Subject: mac80211: allow channel switch with multiple channel contexts

Channel switch with multiple channel contexts should now work fine.
Remove check that disallows switches when multiple contexts are in
use.

Signed-off-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/iwlegacy/4965-mac.c    |  2 +-
 drivers/net/wireless/iwlegacy/4965.h        |  5 +++--
 drivers/net/wireless/iwlwifi/dvm/mac80211.c |  1 +
 drivers/net/wireless/ti/wlcore/main.c       | 23 ++++++++---------------
 include/net/mac80211.h                      |  1 +
 net/mac80211/driver-ops.h                   |  7 ++++---
 net/mac80211/mlme.c                         | 26 ++++++++++----------------
 net/mac80211/trace.h                        |  9 ++++++---
 8 files changed, 34 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c
index 26fec54dcd0..2748fde4b90 100644
--- a/drivers/net/wireless/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/iwlegacy/4965-mac.c
@@ -6063,7 +6063,7 @@ il4965_mac_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 }
 
 void
-il4965_mac_channel_switch(struct ieee80211_hw *hw,
+il4965_mac_channel_switch(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			  struct ieee80211_channel_switch *ch_switch)
 {
 	struct il_priv *il = hw->priv;
diff --git a/drivers/net/wireless/iwlegacy/4965.h b/drivers/net/wireless/iwlegacy/4965.h
index 337dfcf3bbd..3a57f71b8ed 100644
--- a/drivers/net/wireless/iwlegacy/4965.h
+++ b/drivers/net/wireless/iwlegacy/4965.h
@@ -187,8 +187,9 @@ int il4965_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			    u8 buf_size);
 int il4965_mac_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta);
-void il4965_mac_channel_switch(struct ieee80211_hw *hw,
-			       struct ieee80211_channel_switch *ch_switch);
+void
+il4965_mac_channel_switch(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			  struct ieee80211_channel_switch *ch_switch);
 
 void il4965_led_enable(struct il_priv *il);
 
diff --git a/drivers/net/wireless/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
index 2364a3c09b9..a967bf893a8 100644
--- a/drivers/net/wireless/iwlwifi/dvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
@@ -941,6 +941,7 @@ static int iwlagn_mac_sta_state(struct ieee80211_hw *hw,
 }
 
 static void iwlagn_mac_channel_switch(struct ieee80211_hw *hw,
+				      struct ieee80211_vif *vif,
 				      struct ieee80211_channel_switch *ch_switch)
 {
 	struct iwl_priv *priv = IWL_MAC80211_GET_DVM(hw);
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 575c8f6d400..6ad3fcedab9 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -5177,10 +5177,11 @@ out:
 }
 
 static void wl12xx_op_channel_switch(struct ieee80211_hw *hw,
+				     struct ieee80211_vif *vif,
 				     struct ieee80211_channel_switch *ch_switch)
 {
 	struct wl1271 *wl = hw->priv;
-	struct wl12xx_vif *wlvif;
+	struct wl12xx_vif *wlvif = wl12xx_vif_to_data(vif);
 	int ret;
 
 	wl1271_debug(DEBUG_MAC80211, "mac80211 channel switch");
@@ -5190,14 +5191,8 @@ static void wl12xx_op_channel_switch(struct ieee80211_hw *hw,
 	mutex_lock(&wl->mutex);
 
 	if (unlikely(wl->state == WLCORE_STATE_OFF)) {
-		wl12xx_for_each_wlvif_sta(wl, wlvif) {
-			struct ieee80211_vif *vif = wl12xx_wlvif_to_vif(wlvif);
-
-			if (!test_bit(WLVIF_FLAG_STA_ASSOCIATED, &wlvif->flags))
-				continue;
-
+		if (test_bit(WLVIF_FLAG_STA_ASSOCIATED, &wlvif->flags))
 			ieee80211_chswitch_done(vif, false);
-		}
 		goto out;
 	} else if (unlikely(wl->state != WLCORE_STATE_ON)) {
 		goto out;
@@ -5208,11 +5203,9 @@ static void wl12xx_op_channel_switch(struct ieee80211_hw *hw,
 		goto out;
 
 	/* TODO: change mac80211 to pass vif as param */
-	wl12xx_for_each_wlvif_sta(wl, wlvif) {
-		unsigned long delay_usec;
 
-		if (!test_bit(WLVIF_FLAG_STA_ASSOCIATED, &wlvif->flags))
-			continue;
+	if (test_bit(WLVIF_FLAG_STA_ASSOCIATED, &wlvif->flags)) {
+		unsigned long delay_usec;
 
 		ret = wl->ops->channel_switch(wl, wlvif, ch_switch);
 		if (ret)
@@ -5222,10 +5215,10 @@ static void wl12xx_op_channel_switch(struct ieee80211_hw *hw,
 
 		/* indicate failure 5 seconds after channel switch time */
 		delay_usec = ieee80211_tu_to_usec(wlvif->beacon_int) *
-			     ch_switch->count;
+			ch_switch->count;
 		ieee80211_queue_delayed_work(hw, &wlvif->channel_switch_work,
-				usecs_to_jiffies(delay_usec) +
-				msecs_to_jiffies(5000));
+					     usecs_to_jiffies(delay_usec) +
+					     msecs_to_jiffies(5000));
 	}
 
 out_sleep:
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 7861ed875c4..9bb2fc73aea 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2969,6 +2969,7 @@ struct ieee80211_ops {
 	void (*flush)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		      u32 queues, bool drop);
 	void (*channel_switch)(struct ieee80211_hw *hw,
+			       struct ieee80211_vif *vif,
 			       struct ieee80211_channel_switch *ch_switch);
 	int (*set_antenna)(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant);
 	int (*get_antenna)(struct ieee80211_hw *hw, u32 *tx_ant, u32 *rx_ant);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 0a609064476..1bbb0790264 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -764,12 +764,13 @@ static inline void drv_flush(struct ieee80211_local *local,
 }
 
 static inline void drv_channel_switch(struct ieee80211_local *local,
-				     struct ieee80211_channel_switch *ch_switch)
+				      struct ieee80211_sub_if_data *sdata,
+				      struct ieee80211_channel_switch *ch_switch)
 {
 	might_sleep();
 
-	trace_drv_channel_switch(local, ch_switch);
-	local->ops->channel_switch(&local->hw, ch_switch);
+	trace_drv_channel_switch(local, sdata, ch_switch);
+	local->ops->channel_switch(&local->hw, &sdata->vif, ch_switch);
 	trace_drv_return_void(local);
 }
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 148253c1bd7..fb6561509ca 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1134,21 +1134,15 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 
 	chanctx = container_of(conf, struct ieee80211_chanctx, conf);
 
-	if (local->use_chanctx) {
-		u32 num_chanctx = 0;
-		list_for_each_entry(chanctx, &local->chanctx_list, list)
-		       num_chanctx++;
-
-		if (num_chanctx > 1 ||
-		    !(local->hw.flags & IEEE80211_HW_CHANCTX_STA_CSA)) {
-			sdata_info(sdata,
-				   "not handling chan-switch with channel contexts\n");
-			ieee80211_queue_work(&local->hw,
-					     &ifmgd->csa_connection_drop_work);
-			mutex_unlock(&local->chanctx_mtx);
-			mutex_unlock(&local->mtx);
-			return;
-		}
+	if (local->use_chanctx &&
+	    !(local->hw.flags & IEEE80211_HW_CHANCTX_STA_CSA)) {
+		sdata_info(sdata,
+			   "driver doesn't support chan-switch with channel contexts\n");
+		ieee80211_queue_work(&local->hw,
+				     &ifmgd->csa_connection_drop_work);
+		mutex_unlock(&local->chanctx_mtx);
+		mutex_unlock(&local->mtx);
+		return;
 	}
 
 	ch_switch.timestamp = timestamp;
@@ -1192,7 +1186,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 
 	if (local->ops->channel_switch) {
 		/* use driver's channel switch callback */
-		drv_channel_switch(local, &ch_switch);
+		drv_channel_switch(local, sdata, &ch_switch);
 		return;
 	}
 
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index ca0e12dd23c..976606aebac 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -987,12 +987,14 @@ TRACE_EVENT(drv_flush,
 
 TRACE_EVENT(drv_channel_switch,
 	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
 		 struct ieee80211_channel_switch *ch_switch),
 
-	TP_ARGS(local, ch_switch),
+	TP_ARGS(local, sdata, ch_switch),
 
 	TP_STRUCT__entry(
 		LOCAL_ENTRY
+		VIF_ENTRY
 		CHANDEF_ENTRY
 		__field(u64, timestamp)
 		__field(u32, device_timestamp)
@@ -1002,6 +1004,7 @@ TRACE_EVENT(drv_channel_switch,
 
 	TP_fast_assign(
 		LOCAL_ASSIGN;
+		VIF_ASSIGN;
 		CHANDEF_ASSIGN(&ch_switch->chandef)
 		__entry->timestamp = ch_switch->timestamp;
 		__entry->device_timestamp = ch_switch->device_timestamp;
@@ -1010,8 +1013,8 @@ TRACE_EVENT(drv_channel_switch,
 	),
 
 	TP_printk(
-		LOCAL_PR_FMT " new " CHANDEF_PR_FMT " count:%d",
-		LOCAL_PR_ARG, CHANDEF_PR_ARG, __entry->count
+		LOCAL_PR_FMT VIF_PR_FMT " new " CHANDEF_PR_FMT " count:%d",
+		LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->count
 	)
 );
 
-- 
cgit v1.2.3-70-g09d2


From 68ab61084de3220e2fb0a698c890ba91decddc85 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 15 Oct 2014 14:06:25 +0200
Subject: ALSA: seq: bind seq driver automatically

Currently the sequencer module binding is performed independently from
the card module itself.  The reason behind it is to keep the sequencer
stuff optional and allow the system running without it (e.g. for using
PCM or rawmidi only).  This works in most cases, but a remaining
problem is that the binding isn't done automatically when a new driver
module is probed.  Typically this becomes visible when a hotplug
driver like usb audio is used.

This patch tries to address this and other potential issues.  First,
the seq-binder (seq_device.c) tries to load a missing driver module at
creating a new device object.  This is done asynchronously in a workq
for avoiding the deadlock (modprobe call in module init path).

This action, however, should be enabled only when the sequencer stuff
was already initialized, i.e. snd-seq module was already loaded.  For
that, a new function, snd_seq_autoload_init() is introduced here; this
clears the blocking of autoloading, and also tries to load all pending
driver modules.

Reported-by: Adam Goode <agoode@chromium.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/seq_kernel.h  |  4 ++
 sound/core/seq/seq.c        |  3 ++
 sound/core/seq/seq_device.c | 92 +++++++++++++++++++++++++++++++++------------
 3 files changed, 76 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/sound/seq_kernel.h b/include/sound/seq_kernel.h
index 2398521f099..eea5400fe37 100644
--- a/include/sound/seq_kernel.h
+++ b/include/sound/seq_kernel.h
@@ -108,9 +108,13 @@ int snd_seq_event_port_detach(int client, int port);
 #ifdef CONFIG_MODULES
 void snd_seq_autoload_lock(void);
 void snd_seq_autoload_unlock(void);
+void snd_seq_autoload_init(void);
+#define snd_seq_autoload_exit()	snd_seq_autoload_lock()
 #else
 #define snd_seq_autoload_lock()
 #define snd_seq_autoload_unlock()
+#define snd_seq_autoload_init()
+#define snd_seq_autoload_exit()
 #endif
 
 #endif /* __SOUND_SEQ_KERNEL_H */
diff --git a/sound/core/seq/seq.c b/sound/core/seq/seq.c
index 71211056108..bebdd2e920c 100644
--- a/sound/core/seq/seq.c
+++ b/sound/core/seq/seq.c
@@ -110,6 +110,7 @@ static int __init alsa_seq_init(void)
 	if ((err = snd_seq_system_client_init()) < 0)
 		goto error;
 
+	snd_seq_autoload_init();
  error:
 	snd_seq_autoload_unlock();
 	return err;
@@ -131,6 +132,8 @@ static void __exit alsa_seq_exit(void)
 
 	/* release event memory */
 	snd_sequencer_memory_done();
+
+	snd_seq_autoload_exit();
 }
 
 module_init(alsa_seq_init)
diff --git a/sound/core/seq/seq_device.c b/sound/core/seq/seq_device.c
index 775ea939011..a8e2c601680 100644
--- a/sound/core/seq/seq_device.c
+++ b/sound/core/seq/seq_device.c
@@ -56,6 +56,7 @@ MODULE_LICENSE("GPL");
 #define DRIVER_LOADED		(1<<0)
 #define DRIVER_REQUESTED	(1<<1)
 #define DRIVER_LOCKED		(1<<2)
+#define DRIVER_REQUESTING	(1<<3)
 
 struct ops_list {
 	char id[ID_LEN];	/* driver id */
@@ -127,7 +128,7 @@ static void snd_seq_device_info(struct snd_info_entry *entry,
 
 #ifdef CONFIG_MODULES
 /* avoid auto-loading during module_init() */
-static atomic_t snd_seq_in_init = ATOMIC_INIT(0);
+static atomic_t snd_seq_in_init = ATOMIC_INIT(1); /* blocked as default */
 void snd_seq_autoload_lock(void)
 {
 	atomic_inc(&snd_seq_in_init);
@@ -137,32 +138,72 @@ void snd_seq_autoload_unlock(void)
 {
 	atomic_dec(&snd_seq_in_init);
 }
-#endif
 
-void snd_seq_device_load_drivers(void)
+static void autoload_drivers(void)
 {
-#ifdef CONFIG_MODULES
-	struct ops_list *ops;
+	/* avoid reentrance */
+	if (atomic_inc_return(&snd_seq_in_init) == 1) {
+		struct ops_list *ops;
+
+		mutex_lock(&ops_mutex);
+		list_for_each_entry(ops, &opslist, list) {
+			if ((ops->driver & DRIVER_REQUESTING) &&
+			    !(ops->driver & DRIVER_REQUESTED)) {
+				ops->used++;
+				mutex_unlock(&ops_mutex);
+				ops->driver |= DRIVER_REQUESTED;
+				request_module("snd-%s", ops->id);
+				mutex_lock(&ops_mutex);
+				ops->used--;
+			}
+		}
+		mutex_unlock(&ops_mutex);
+	}
+	atomic_dec(&snd_seq_in_init);
+}
 
-	/* Calling request_module during module_init()
-	 * may cause blocking.
-	 */
-	if (atomic_read(&snd_seq_in_init))
-		return;
+static void call_autoload(struct work_struct *work)
+{
+	autoload_drivers();
+}
 
-	mutex_lock(&ops_mutex);
-	list_for_each_entry(ops, &opslist, list) {
-		if (! (ops->driver & DRIVER_LOADED) &&
-		    ! (ops->driver & DRIVER_REQUESTED)) {
-			ops->used++;
-			mutex_unlock(&ops_mutex);
-			ops->driver |= DRIVER_REQUESTED;
-			request_module("snd-%s", ops->id);
-			mutex_lock(&ops_mutex);
-			ops->used--;
-		}
+static DECLARE_WORK(autoload_work, call_autoload);
+
+static void try_autoload(struct ops_list *ops)
+{
+	if (!ops->driver) {
+		ops->driver |= DRIVER_REQUESTING;
+		schedule_work(&autoload_work);
 	}
+}
+
+static void queue_autoload_drivers(void)
+{
+	struct ops_list *ops;
+
+	mutex_lock(&ops_mutex);
+	list_for_each_entry(ops, &opslist, list)
+		try_autoload(ops);
 	mutex_unlock(&ops_mutex);
+}
+
+void snd_seq_autoload_init(void)
+{
+	atomic_dec(&snd_seq_in_init);
+#ifdef CONFIG_SND_SEQUENCER_MODULE
+	/* initial autoload only when snd-seq is a module */
+	queue_autoload_drivers();
+#endif
+}
+#else
+#define try_autoload(ops) /* NOP */
+#endif
+
+void snd_seq_device_load_drivers(void)
+{
+#ifdef CONFIG_MODULES
+	queue_autoload_drivers();
+	flush_work(&autoload_work);
 #endif
 }
 
@@ -214,13 +255,14 @@ int snd_seq_device_new(struct snd_card *card, int device, char *id, int argsize,
 	ops->num_devices++;
 	mutex_unlock(&ops->reg_mutex);
 
-	unlock_driver(ops);
-	
 	if ((err = snd_device_new(card, SNDRV_DEV_SEQUENCER, dev, &dops)) < 0) {
 		snd_seq_device_free(dev);
 		return err;
 	}
 	
+	try_autoload(ops);
+	unlock_driver(ops);
+
 	if (result)
 		*result = dev;
 
@@ -554,6 +596,9 @@ static int __init alsa_seq_device_init(void)
 
 static void __exit alsa_seq_device_exit(void)
 {
+#ifdef CONFIG_MODULES
+	cancel_work_sync(&autoload_work);
+#endif
 	remove_drivers();
 #ifdef CONFIG_PROC_FS
 	snd_info_free_entry(info_entry);
@@ -570,6 +615,7 @@ EXPORT_SYMBOL(snd_seq_device_new);
 EXPORT_SYMBOL(snd_seq_device_register_driver);
 EXPORT_SYMBOL(snd_seq_device_unregister_driver);
 #ifdef CONFIG_MODULES
+EXPORT_SYMBOL(snd_seq_autoload_init);
 EXPORT_SYMBOL(snd_seq_autoload_lock);
 EXPORT_SYMBOL(snd_seq_autoload_unlock);
 #endif
-- 
cgit v1.2.3-70-g09d2


From 777783e0abae3cab7555bb182776f9ffaa35631a Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Thu, 16 Oct 2014 14:40:38 +0200
Subject: staging: android: binder: move to the "real" part of the kernel

The Android binder code has been "stable" for many years now.  No matter
what comes in the future, we are going to have to support this API, so
might as well move it to the "real" part of the kernel as there's no
real work that needs to be done to the existing code.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/Kconfig                        |    2 +
 drivers/Makefile                       |    1 +
 drivers/android/Kconfig                |   37 +
 drivers/android/Makefile               |    3 +
 drivers/android/binder.c               | 3673 ++++++++++++++++++++++++++++++++
 drivers/android/binder.h               |   30 +
 drivers/android/binder_trace.h         |  329 +++
 drivers/staging/android/Kconfig        |   30 -
 drivers/staging/android/Makefile       |    1 -
 drivers/staging/android/binder.c       | 3673 --------------------------------
 drivers/staging/android/binder.h       |   30 -
 drivers/staging/android/binder_trace.h |  329 ---
 drivers/staging/android/uapi/binder.h  |  351 ---
 include/uapi/linux/Kbuild              |    1 +
 include/uapi/linux/android/Kbuild      |    2 +
 include/uapi/linux/android/binder.h    |  351 +++
 16 files changed, 4429 insertions(+), 4414 deletions(-)
 create mode 100644 drivers/android/Kconfig
 create mode 100644 drivers/android/Makefile
 create mode 100644 drivers/android/binder.c
 create mode 100644 drivers/android/binder.h
 create mode 100644 drivers/android/binder_trace.h
 delete mode 100644 drivers/staging/android/binder.c
 delete mode 100644 drivers/staging/android/binder.h
 delete mode 100644 drivers/staging/android/binder_trace.h
 delete mode 100644 drivers/staging/android/uapi/binder.h
 create mode 100644 include/uapi/linux/android/Kbuild
 create mode 100644 include/uapi/linux/android/binder.h

(limited to 'include')

diff --git a/drivers/Kconfig b/drivers/Kconfig
index 1a693d3f9d5..569ff7886dc 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -182,4 +182,6 @@ source "drivers/ras/Kconfig"
 
 source "drivers/thunderbolt/Kconfig"
 
+source "drivers/android/Kconfig"
+
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index ebee55537a0..60d19820a4d 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -161,3 +161,4 @@ obj-$(CONFIG_POWERCAP)		+= powercap/
 obj-$(CONFIG_MCB)		+= mcb/
 obj-$(CONFIG_RAS)		+= ras/
 obj-$(CONFIG_THUNDERBOLT)	+= thunderbolt/
+obj-$(CONFIG_ANDROID)		+= android/
diff --git a/drivers/android/Kconfig b/drivers/android/Kconfig
new file mode 100644
index 00000000000..bdfc6c6f4f5
--- /dev/null
+++ b/drivers/android/Kconfig
@@ -0,0 +1,37 @@
+menu "Android"
+
+config ANDROID
+	bool "Android Drivers"
+	---help---
+	  Enable support for various drivers needed on the Android platform
+
+if ANDROID
+
+config ANDROID_BINDER_IPC
+	bool "Android Binder IPC Driver"
+	depends on MMU
+	default n
+	---help---
+	  Binder is used in Android for both communication between processes,
+	  and remote method invocation.
+
+	  This means one Android process can call a method/routine in another
+	  Android process, using Binder to identify, invoke and pass arguments
+	  between said processes.
+
+config ANDROID_BINDER_IPC_32BIT
+	bool
+	depends on !64BIT && ANDROID_BINDER_IPC
+	default y
+	---help---
+	  The Binder API has been changed to support both 32 and 64bit
+	  applications in a mixed environment.
+
+	  Enable this to support an old 32-bit Android user-space (v4.4 and
+	  earlier).
+
+	  Note that enabling this will break newer Android user-space.
+
+endif # if ANDROID
+
+endmenu
diff --git a/drivers/android/Makefile b/drivers/android/Makefile
new file mode 100644
index 00000000000..3b7e4b072c5
--- /dev/null
+++ b/drivers/android/Makefile
@@ -0,0 +1,3 @@
+ccflags-y += -I$(src)			# needed for trace events
+
+obj-$(CONFIG_ANDROID_BINDER_IPC)	+= binder.o
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
new file mode 100644
index 00000000000..c69c40d69d5
--- /dev/null
+++ b/drivers/android/binder.c
@@ -0,0 +1,3673 @@
+/* binder.c
+ *
+ * Android IPC Subsystem
+ *
+ * Copyright (C) 2007-2008 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <asm/cacheflush.h>
+#include <linux/fdtable.h>
+#include <linux/file.h>
+#include <linux/freezer.h>
+#include <linux/fs.h>
+#include <linux/list.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/nsproxy.h>
+#include <linux/poll.h>
+#include <linux/debugfs.h>
+#include <linux/rbtree.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/pid_namespace.h>
+
+#include "binder.h"
+#include "binder_trace.h"
+
+static DEFINE_MUTEX(binder_main_lock);
+static DEFINE_MUTEX(binder_deferred_lock);
+static DEFINE_MUTEX(binder_mmap_lock);
+
+static HLIST_HEAD(binder_procs);
+static HLIST_HEAD(binder_deferred_list);
+static HLIST_HEAD(binder_dead_nodes);
+
+static struct dentry *binder_debugfs_dir_entry_root;
+static struct dentry *binder_debugfs_dir_entry_proc;
+static struct binder_node *binder_context_mgr_node;
+static kuid_t binder_context_mgr_uid = INVALID_UID;
+static int binder_last_id;
+static struct workqueue_struct *binder_deferred_workqueue;
+
+#define BINDER_DEBUG_ENTRY(name) \
+static int binder_##name##_open(struct inode *inode, struct file *file) \
+{ \
+	return single_open(file, binder_##name##_show, inode->i_private); \
+} \
+\
+static const struct file_operations binder_##name##_fops = { \
+	.owner = THIS_MODULE, \
+	.open = binder_##name##_open, \
+	.read = seq_read, \
+	.llseek = seq_lseek, \
+	.release = single_release, \
+}
+
+static int binder_proc_show(struct seq_file *m, void *unused);
+BINDER_DEBUG_ENTRY(proc);
+
+/* This is only defined in include/asm-arm/sizes.h */
+#ifndef SZ_1K
+#define SZ_1K                               0x400
+#endif
+
+#ifndef SZ_4M
+#define SZ_4M                               0x400000
+#endif
+
+#define FORBIDDEN_MMAP_FLAGS                (VM_WRITE)
+
+#define BINDER_SMALL_BUF_SIZE (PAGE_SIZE * 64)
+
+enum {
+	BINDER_DEBUG_USER_ERROR             = 1U << 0,
+	BINDER_DEBUG_FAILED_TRANSACTION     = 1U << 1,
+	BINDER_DEBUG_DEAD_TRANSACTION       = 1U << 2,
+	BINDER_DEBUG_OPEN_CLOSE             = 1U << 3,
+	BINDER_DEBUG_DEAD_BINDER            = 1U << 4,
+	BINDER_DEBUG_DEATH_NOTIFICATION     = 1U << 5,
+	BINDER_DEBUG_READ_WRITE             = 1U << 6,
+	BINDER_DEBUG_USER_REFS              = 1U << 7,
+	BINDER_DEBUG_THREADS                = 1U << 8,
+	BINDER_DEBUG_TRANSACTION            = 1U << 9,
+	BINDER_DEBUG_TRANSACTION_COMPLETE   = 1U << 10,
+	BINDER_DEBUG_FREE_BUFFER            = 1U << 11,
+	BINDER_DEBUG_INTERNAL_REFS          = 1U << 12,
+	BINDER_DEBUG_BUFFER_ALLOC           = 1U << 13,
+	BINDER_DEBUG_PRIORITY_CAP           = 1U << 14,
+	BINDER_DEBUG_BUFFER_ALLOC_ASYNC     = 1U << 15,
+};
+static uint32_t binder_debug_mask = BINDER_DEBUG_USER_ERROR |
+	BINDER_DEBUG_FAILED_TRANSACTION | BINDER_DEBUG_DEAD_TRANSACTION;
+module_param_named(debug_mask, binder_debug_mask, uint, S_IWUSR | S_IRUGO);
+
+static bool binder_debug_no_lock;
+module_param_named(proc_no_lock, binder_debug_no_lock, bool, S_IWUSR | S_IRUGO);
+
+static DECLARE_WAIT_QUEUE_HEAD(binder_user_error_wait);
+static int binder_stop_on_user_error;
+
+static int binder_set_stop_on_user_error(const char *val,
+					 struct kernel_param *kp)
+{
+	int ret;
+
+	ret = param_set_int(val, kp);
+	if (binder_stop_on_user_error < 2)
+		wake_up(&binder_user_error_wait);
+	return ret;
+}
+module_param_call(stop_on_user_error, binder_set_stop_on_user_error,
+	param_get_int, &binder_stop_on_user_error, S_IWUSR | S_IRUGO);
+
+#define binder_debug(mask, x...) \
+	do { \
+		if (binder_debug_mask & mask) \
+			pr_info(x); \
+	} while (0)
+
+#define binder_user_error(x...) \
+	do { \
+		if (binder_debug_mask & BINDER_DEBUG_USER_ERROR) \
+			pr_info(x); \
+		if (binder_stop_on_user_error) \
+			binder_stop_on_user_error = 2; \
+	} while (0)
+
+enum binder_stat_types {
+	BINDER_STAT_PROC,
+	BINDER_STAT_THREAD,
+	BINDER_STAT_NODE,
+	BINDER_STAT_REF,
+	BINDER_STAT_DEATH,
+	BINDER_STAT_TRANSACTION,
+	BINDER_STAT_TRANSACTION_COMPLETE,
+	BINDER_STAT_COUNT
+};
+
+struct binder_stats {
+	int br[_IOC_NR(BR_FAILED_REPLY) + 1];
+	int bc[_IOC_NR(BC_DEAD_BINDER_DONE) + 1];
+	int obj_created[BINDER_STAT_COUNT];
+	int obj_deleted[BINDER_STAT_COUNT];
+};
+
+static struct binder_stats binder_stats;
+
+static inline void binder_stats_deleted(enum binder_stat_types type)
+{
+	binder_stats.obj_deleted[type]++;
+}
+
+static inline void binder_stats_created(enum binder_stat_types type)
+{
+	binder_stats.obj_created[type]++;
+}
+
+struct binder_transaction_log_entry {
+	int debug_id;
+	int call_type;
+	int from_proc;
+	int from_thread;
+	int target_handle;
+	int to_proc;
+	int to_thread;
+	int to_node;
+	int data_size;
+	int offsets_size;
+};
+struct binder_transaction_log {
+	int next;
+	int full;
+	struct binder_transaction_log_entry entry[32];
+};
+static struct binder_transaction_log binder_transaction_log;
+static struct binder_transaction_log binder_transaction_log_failed;
+
+static struct binder_transaction_log_entry *binder_transaction_log_add(
+	struct binder_transaction_log *log)
+{
+	struct binder_transaction_log_entry *e;
+
+	e = &log->entry[log->next];
+	memset(e, 0, sizeof(*e));
+	log->next++;
+	if (log->next == ARRAY_SIZE(log->entry)) {
+		log->next = 0;
+		log->full = 1;
+	}
+	return e;
+}
+
+struct binder_work {
+	struct list_head entry;
+	enum {
+		BINDER_WORK_TRANSACTION = 1,
+		BINDER_WORK_TRANSACTION_COMPLETE,
+		BINDER_WORK_NODE,
+		BINDER_WORK_DEAD_BINDER,
+		BINDER_WORK_DEAD_BINDER_AND_CLEAR,
+		BINDER_WORK_CLEAR_DEATH_NOTIFICATION,
+	} type;
+};
+
+struct binder_node {
+	int debug_id;
+	struct binder_work work;
+	union {
+		struct rb_node rb_node;
+		struct hlist_node dead_node;
+	};
+	struct binder_proc *proc;
+	struct hlist_head refs;
+	int internal_strong_refs;
+	int local_weak_refs;
+	int local_strong_refs;
+	binder_uintptr_t ptr;
+	binder_uintptr_t cookie;
+	unsigned has_strong_ref:1;
+	unsigned pending_strong_ref:1;
+	unsigned has_weak_ref:1;
+	unsigned pending_weak_ref:1;
+	unsigned has_async_transaction:1;
+	unsigned accept_fds:1;
+	unsigned min_priority:8;
+	struct list_head async_todo;
+};
+
+struct binder_ref_death {
+	struct binder_work work;
+	binder_uintptr_t cookie;
+};
+
+struct binder_ref {
+	/* Lookups needed: */
+	/*   node + proc => ref (transaction) */
+	/*   desc + proc => ref (transaction, inc/dec ref) */
+	/*   node => refs + procs (proc exit) */
+	int debug_id;
+	struct rb_node rb_node_desc;
+	struct rb_node rb_node_node;
+	struct hlist_node node_entry;
+	struct binder_proc *proc;
+	struct binder_node *node;
+	uint32_t desc;
+	int strong;
+	int weak;
+	struct binder_ref_death *death;
+};
+
+struct binder_buffer {
+	struct list_head entry; /* free and allocated entries by address */
+	struct rb_node rb_node; /* free entry by size or allocated entry */
+				/* by address */
+	unsigned free:1;
+	unsigned allow_user_free:1;
+	unsigned async_transaction:1;
+	unsigned debug_id:29;
+
+	struct binder_transaction *transaction;
+
+	struct binder_node *target_node;
+	size_t data_size;
+	size_t offsets_size;
+	uint8_t data[0];
+};
+
+enum binder_deferred_state {
+	BINDER_DEFERRED_PUT_FILES    = 0x01,
+	BINDER_DEFERRED_FLUSH        = 0x02,
+	BINDER_DEFERRED_RELEASE      = 0x04,
+};
+
+struct binder_proc {
+	struct hlist_node proc_node;
+	struct rb_root threads;
+	struct rb_root nodes;
+	struct rb_root refs_by_desc;
+	struct rb_root refs_by_node;
+	int pid;
+	struct vm_area_struct *vma;
+	struct mm_struct *vma_vm_mm;
+	struct task_struct *tsk;
+	struct files_struct *files;
+	struct hlist_node deferred_work_node;
+	int deferred_work;
+	void *buffer;
+	ptrdiff_t user_buffer_offset;
+
+	struct list_head buffers;
+	struct rb_root free_buffers;
+	struct rb_root allocated_buffers;
+	size_t free_async_space;
+
+	struct page **pages;
+	size_t buffer_size;
+	uint32_t buffer_free;
+	struct list_head todo;
+	wait_queue_head_t wait;
+	struct binder_stats stats;
+	struct list_head delivered_death;
+	int max_threads;
+	int requested_threads;
+	int requested_threads_started;
+	int ready_threads;
+	long default_priority;
+	struct dentry *debugfs_entry;
+};
+
+enum {
+	BINDER_LOOPER_STATE_REGISTERED  = 0x01,
+	BINDER_LOOPER_STATE_ENTERED     = 0x02,
+	BINDER_LOOPER_STATE_EXITED      = 0x04,
+	BINDER_LOOPER_STATE_INVALID     = 0x08,
+	BINDER_LOOPER_STATE_WAITING     = 0x10,
+	BINDER_LOOPER_STATE_NEED_RETURN = 0x20
+};
+
+struct binder_thread {
+	struct binder_proc *proc;
+	struct rb_node rb_node;
+	int pid;
+	int looper;
+	struct binder_transaction *transaction_stack;
+	struct list_head todo;
+	uint32_t return_error; /* Write failed, return error code in read buf */
+	uint32_t return_error2; /* Write failed, return error code in read */
+		/* buffer. Used when sending a reply to a dead process that */
+		/* we are also waiting on */
+	wait_queue_head_t wait;
+	struct binder_stats stats;
+};
+
+struct binder_transaction {
+	int debug_id;
+	struct binder_work work;
+	struct binder_thread *from;
+	struct binder_transaction *from_parent;
+	struct binder_proc *to_proc;
+	struct binder_thread *to_thread;
+	struct binder_transaction *to_parent;
+	unsigned need_reply:1;
+	/* unsigned is_dead:1; */	/* not used at the moment */
+
+	struct binder_buffer *buffer;
+	unsigned int	code;
+	unsigned int	flags;
+	long	priority;
+	long	saved_priority;
+	kuid_t	sender_euid;
+};
+
+static void
+binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer);
+
+static int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
+{
+	struct files_struct *files = proc->files;
+	unsigned long rlim_cur;
+	unsigned long irqs;
+
+	if (files == NULL)
+		return -ESRCH;
+
+	if (!lock_task_sighand(proc->tsk, &irqs))
+		return -EMFILE;
+
+	rlim_cur = task_rlimit(proc->tsk, RLIMIT_NOFILE);
+	unlock_task_sighand(proc->tsk, &irqs);
+
+	return __alloc_fd(files, 0, rlim_cur, flags);
+}
+
+/*
+ * copied from fd_install
+ */
+static void task_fd_install(
+	struct binder_proc *proc, unsigned int fd, struct file *file)
+{
+	if (proc->files)
+		__fd_install(proc->files, fd, file);
+}
+
+/*
+ * copied from sys_close
+ */
+static long task_close_fd(struct binder_proc *proc, unsigned int fd)
+{
+	int retval;
+
+	if (proc->files == NULL)
+		return -ESRCH;
+
+	retval = __close_fd(proc->files, fd);
+	/* can't restart close syscall because file table entry was cleared */
+	if (unlikely(retval == -ERESTARTSYS ||
+		     retval == -ERESTARTNOINTR ||
+		     retval == -ERESTARTNOHAND ||
+		     retval == -ERESTART_RESTARTBLOCK))
+		retval = -EINTR;
+
+	return retval;
+}
+
+static inline void binder_lock(const char *tag)
+{
+	trace_binder_lock(tag);
+	mutex_lock(&binder_main_lock);
+	trace_binder_locked(tag);
+}
+
+static inline void binder_unlock(const char *tag)
+{
+	trace_binder_unlock(tag);
+	mutex_unlock(&binder_main_lock);
+}
+
+static void binder_set_nice(long nice)
+{
+	long min_nice;
+
+	if (can_nice(current, nice)) {
+		set_user_nice(current, nice);
+		return;
+	}
+	min_nice = rlimit_to_nice(current->signal->rlim[RLIMIT_NICE].rlim_cur);
+	binder_debug(BINDER_DEBUG_PRIORITY_CAP,
+		     "%d: nice value %ld not allowed use %ld instead\n",
+		      current->pid, nice, min_nice);
+	set_user_nice(current, min_nice);
+	if (min_nice <= MAX_NICE)
+		return;
+	binder_user_error("%d RLIMIT_NICE not set\n", current->pid);
+}
+
+static size_t binder_buffer_size(struct binder_proc *proc,
+				 struct binder_buffer *buffer)
+{
+	if (list_is_last(&buffer->entry, &proc->buffers))
+		return proc->buffer + proc->buffer_size - (void *)buffer->data;
+	return (size_t)list_entry(buffer->entry.next,
+			  struct binder_buffer, entry) - (size_t)buffer->data;
+}
+
+static void binder_insert_free_buffer(struct binder_proc *proc,
+				      struct binder_buffer *new_buffer)
+{
+	struct rb_node **p = &proc->free_buffers.rb_node;
+	struct rb_node *parent = NULL;
+	struct binder_buffer *buffer;
+	size_t buffer_size;
+	size_t new_buffer_size;
+
+	BUG_ON(!new_buffer->free);
+
+	new_buffer_size = binder_buffer_size(proc, new_buffer);
+
+	binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
+		     "%d: add free buffer, size %zd, at %p\n",
+		      proc->pid, new_buffer_size, new_buffer);
+
+	while (*p) {
+		parent = *p;
+		buffer = rb_entry(parent, struct binder_buffer, rb_node);
+		BUG_ON(!buffer->free);
+
+		buffer_size = binder_buffer_size(proc, buffer);
+
+		if (new_buffer_size < buffer_size)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+	rb_link_node(&new_buffer->rb_node, parent, p);
+	rb_insert_color(&new_buffer->rb_node, &proc->free_buffers);
+}
+
+static void binder_insert_allocated_buffer(struct binder_proc *proc,
+					   struct binder_buffer *new_buffer)
+{
+	struct rb_node **p = &proc->allocated_buffers.rb_node;
+	struct rb_node *parent = NULL;
+	struct binder_buffer *buffer;
+
+	BUG_ON(new_buffer->free);
+
+	while (*p) {
+		parent = *p;
+		buffer = rb_entry(parent, struct binder_buffer, rb_node);
+		BUG_ON(buffer->free);
+
+		if (new_buffer < buffer)
+			p = &parent->rb_left;
+		else if (new_buffer > buffer)
+			p = &parent->rb_right;
+		else
+			BUG();
+	}
+	rb_link_node(&new_buffer->rb_node, parent, p);
+	rb_insert_color(&new_buffer->rb_node, &proc->allocated_buffers);
+}
+
+static struct binder_buffer *binder_buffer_lookup(struct binder_proc *proc,
+						  uintptr_t user_ptr)
+{
+	struct rb_node *n = proc->allocated_buffers.rb_node;
+	struct binder_buffer *buffer;
+	struct binder_buffer *kern_ptr;
+
+	kern_ptr = (struct binder_buffer *)(user_ptr - proc->user_buffer_offset
+		- offsetof(struct binder_buffer, data));
+
+	while (n) {
+		buffer = rb_entry(n, struct binder_buffer, rb_node);
+		BUG_ON(buffer->free);
+
+		if (kern_ptr < buffer)
+			n = n->rb_left;
+		else if (kern_ptr > buffer)
+			n = n->rb_right;
+		else
+			return buffer;
+	}
+	return NULL;
+}
+
+static int binder_update_page_range(struct binder_proc *proc, int allocate,
+				    void *start, void *end,
+				    struct vm_area_struct *vma)
+{
+	void *page_addr;
+	unsigned long user_page_addr;
+	struct vm_struct tmp_area;
+	struct page **page;
+	struct mm_struct *mm;
+
+	binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
+		     "%d: %s pages %p-%p\n", proc->pid,
+		     allocate ? "allocate" : "free", start, end);
+
+	if (end <= start)
+		return 0;
+
+	trace_binder_update_page_range(proc, allocate, start, end);
+
+	if (vma)
+		mm = NULL;
+	else
+		mm = get_task_mm(proc->tsk);
+
+	if (mm) {
+		down_write(&mm->mmap_sem);
+		vma = proc->vma;
+		if (vma && mm != proc->vma_vm_mm) {
+			pr_err("%d: vma mm and task mm mismatch\n",
+				proc->pid);
+			vma = NULL;
+		}
+	}
+
+	if (allocate == 0)
+		goto free_range;
+
+	if (vma == NULL) {
+		pr_err("%d: binder_alloc_buf failed to map pages in userspace, no vma\n",
+			proc->pid);
+		goto err_no_vma;
+	}
+
+	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
+		int ret;
+
+		page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE];
+
+		BUG_ON(*page);
+		*page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
+		if (*page == NULL) {
+			pr_err("%d: binder_alloc_buf failed for page at %p\n",
+				proc->pid, page_addr);
+			goto err_alloc_page_failed;
+		}
+		tmp_area.addr = page_addr;
+		tmp_area.size = PAGE_SIZE + PAGE_SIZE /* guard page? */;
+		ret = map_vm_area(&tmp_area, PAGE_KERNEL, page);
+		if (ret) {
+			pr_err("%d: binder_alloc_buf failed to map page at %p in kernel\n",
+			       proc->pid, page_addr);
+			goto err_map_kernel_failed;
+		}
+		user_page_addr =
+			(uintptr_t)page_addr + proc->user_buffer_offset;
+		ret = vm_insert_page(vma, user_page_addr, page[0]);
+		if (ret) {
+			pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n",
+			       proc->pid, user_page_addr);
+			goto err_vm_insert_page_failed;
+		}
+		/* vm_insert_page does not seem to increment the refcount */
+	}
+	if (mm) {
+		up_write(&mm->mmap_sem);
+		mmput(mm);
+	}
+	return 0;
+
+free_range:
+	for (page_addr = end - PAGE_SIZE; page_addr >= start;
+	     page_addr -= PAGE_SIZE) {
+		page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE];
+		if (vma)
+			zap_page_range(vma, (uintptr_t)page_addr +
+				proc->user_buffer_offset, PAGE_SIZE, NULL);
+err_vm_insert_page_failed:
+		unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
+err_map_kernel_failed:
+		__free_page(*page);
+		*page = NULL;
+err_alloc_page_failed:
+		;
+	}
+err_no_vma:
+	if (mm) {
+		up_write(&mm->mmap_sem);
+		mmput(mm);
+	}
+	return -ENOMEM;
+}
+
+static struct binder_buffer *binder_alloc_buf(struct binder_proc *proc,
+					      size_t data_size,
+					      size_t offsets_size, int is_async)
+{
+	struct rb_node *n = proc->free_buffers.rb_node;
+	struct binder_buffer *buffer;
+	size_t buffer_size;
+	struct rb_node *best_fit = NULL;
+	void *has_page_addr;
+	void *end_page_addr;
+	size_t size;
+
+	if (proc->vma == NULL) {
+		pr_err("%d: binder_alloc_buf, no vma\n",
+		       proc->pid);
+		return NULL;
+	}
+
+	size = ALIGN(data_size, sizeof(void *)) +
+		ALIGN(offsets_size, sizeof(void *));
+
+	if (size < data_size || size < offsets_size) {
+		binder_user_error("%d: got transaction with invalid size %zd-%zd\n",
+				proc->pid, data_size, offsets_size);
+		return NULL;
+	}
+
+	if (is_async &&
+	    proc->free_async_space < size + sizeof(struct binder_buffer)) {
+		binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
+			     "%d: binder_alloc_buf size %zd failed, no async space left\n",
+			      proc->pid, size);
+		return NULL;
+	}
+
+	while (n) {
+		buffer = rb_entry(n, struct binder_buffer, rb_node);
+		BUG_ON(!buffer->free);
+		buffer_size = binder_buffer_size(proc, buffer);
+
+		if (size < buffer_size) {
+			best_fit = n;
+			n = n->rb_left;
+		} else if (size > buffer_size)
+			n = n->rb_right;
+		else {
+			best_fit = n;
+			break;
+		}
+	}
+	if (best_fit == NULL) {
+		pr_err("%d: binder_alloc_buf size %zd failed, no address space\n",
+			proc->pid, size);
+		return NULL;
+	}
+	if (n == NULL) {
+		buffer = rb_entry(best_fit, struct binder_buffer, rb_node);
+		buffer_size = binder_buffer_size(proc, buffer);
+	}
+
+	binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
+		     "%d: binder_alloc_buf size %zd got buffer %p size %zd\n",
+		      proc->pid, size, buffer, buffer_size);
+
+	has_page_addr =
+		(void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK);
+	if (n == NULL) {
+		if (size + sizeof(struct binder_buffer) + 4 >= buffer_size)
+			buffer_size = size; /* no room for other buffers */
+		else
+			buffer_size = size + sizeof(struct binder_buffer);
+	}
+	end_page_addr =
+		(void *)PAGE_ALIGN((uintptr_t)buffer->data + buffer_size);
+	if (end_page_addr > has_page_addr)
+		end_page_addr = has_page_addr;
+	if (binder_update_page_range(proc, 1,
+	    (void *)PAGE_ALIGN((uintptr_t)buffer->data), end_page_addr, NULL))
+		return NULL;
+
+	rb_erase(best_fit, &proc->free_buffers);
+	buffer->free = 0;
+	binder_insert_allocated_buffer(proc, buffer);
+	if (buffer_size != size) {
+		struct binder_buffer *new_buffer = (void *)buffer->data + size;
+
+		list_add(&new_buffer->entry, &buffer->entry);
+		new_buffer->free = 1;
+		binder_insert_free_buffer(proc, new_buffer);
+	}
+	binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
+		     "%d: binder_alloc_buf size %zd got %p\n",
+		      proc->pid, size, buffer);
+	buffer->data_size = data_size;
+	buffer->offsets_size = offsets_size;
+	buffer->async_transaction = is_async;
+	if (is_async) {
+		proc->free_async_space -= size + sizeof(struct binder_buffer);
+		binder_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
+			     "%d: binder_alloc_buf size %zd async free %zd\n",
+			      proc->pid, size, proc->free_async_space);
+	}
+
+	return buffer;
+}
+
+static void *buffer_start_page(struct binder_buffer *buffer)
+{
+	return (void *)((uintptr_t)buffer & PAGE_MASK);
+}
+
+static void *buffer_end_page(struct binder_buffer *buffer)
+{
+	return (void *)(((uintptr_t)(buffer + 1) - 1) & PAGE_MASK);
+}
+
+static void binder_delete_free_buffer(struct binder_proc *proc,
+				      struct binder_buffer *buffer)
+{
+	struct binder_buffer *prev, *next = NULL;
+	int free_page_end = 1;
+	int free_page_start = 1;
+
+	BUG_ON(proc->buffers.next == &buffer->entry);
+	prev = list_entry(buffer->entry.prev, struct binder_buffer, entry);
+	BUG_ON(!prev->free);
+	if (buffer_end_page(prev) == buffer_start_page(buffer)) {
+		free_page_start = 0;
+		if (buffer_end_page(prev) == buffer_end_page(buffer))
+			free_page_end = 0;
+		binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
+			     "%d: merge free, buffer %p share page with %p\n",
+			      proc->pid, buffer, prev);
+	}
+
+	if (!list_is_last(&buffer->entry, &proc->buffers)) {
+		next = list_entry(buffer->entry.next,
+				  struct binder_buffer, entry);
+		if (buffer_start_page(next) == buffer_end_page(buffer)) {
+			free_page_end = 0;
+			if (buffer_start_page(next) ==
+			    buffer_start_page(buffer))
+				free_page_start = 0;
+			binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
+				     "%d: merge free, buffer %p share page with %p\n",
+				      proc->pid, buffer, prev);
+		}
+	}
+	list_del(&buffer->entry);
+	if (free_page_start || free_page_end) {
+		binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
+			     "%d: merge free, buffer %p do not share page%s%s with %p or %p\n",
+			     proc->pid, buffer, free_page_start ? "" : " end",
+			     free_page_end ? "" : " start", prev, next);
+		binder_update_page_range(proc, 0, free_page_start ?
+			buffer_start_page(buffer) : buffer_end_page(buffer),
+			(free_page_end ? buffer_end_page(buffer) :
+			buffer_start_page(buffer)) + PAGE_SIZE, NULL);
+	}
+}
+
+static void binder_free_buf(struct binder_proc *proc,
+			    struct binder_buffer *buffer)
+{
+	size_t size, buffer_size;
+
+	buffer_size = binder_buffer_size(proc, buffer);
+
+	size = ALIGN(buffer->data_size, sizeof(void *)) +
+		ALIGN(buffer->offsets_size, sizeof(void *));
+
+	binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
+		     "%d: binder_free_buf %p size %zd buffer_size %zd\n",
+		      proc->pid, buffer, size, buffer_size);
+
+	BUG_ON(buffer->free);
+	BUG_ON(size > buffer_size);
+	BUG_ON(buffer->transaction != NULL);
+	BUG_ON((void *)buffer < proc->buffer);
+	BUG_ON((void *)buffer > proc->buffer + proc->buffer_size);
+
+	if (buffer->async_transaction) {
+		proc->free_async_space += size + sizeof(struct binder_buffer);
+
+		binder_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
+			     "%d: binder_free_buf size %zd async free %zd\n",
+			      proc->pid, size, proc->free_async_space);
+	}
+
+	binder_update_page_range(proc, 0,
+		(void *)PAGE_ALIGN((uintptr_t)buffer->data),
+		(void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK),
+		NULL);
+	rb_erase(&buffer->rb_node, &proc->allocated_buffers);
+	buffer->free = 1;
+	if (!list_is_last(&buffer->entry, &proc->buffers)) {
+		struct binder_buffer *next = list_entry(buffer->entry.next,
+						struct binder_buffer, entry);
+
+		if (next->free) {
+			rb_erase(&next->rb_node, &proc->free_buffers);
+			binder_delete_free_buffer(proc, next);
+		}
+	}
+	if (proc->buffers.next != &buffer->entry) {
+		struct binder_buffer *prev = list_entry(buffer->entry.prev,
+						struct binder_buffer, entry);
+
+		if (prev->free) {
+			binder_delete_free_buffer(proc, buffer);
+			rb_erase(&prev->rb_node, &proc->free_buffers);
+			buffer = prev;
+		}
+	}
+	binder_insert_free_buffer(proc, buffer);
+}
+
+static struct binder_node *binder_get_node(struct binder_proc *proc,
+					   binder_uintptr_t ptr)
+{
+	struct rb_node *n = proc->nodes.rb_node;
+	struct binder_node *node;
+
+	while (n) {
+		node = rb_entry(n, struct binder_node, rb_node);
+
+		if (ptr < node->ptr)
+			n = n->rb_left;
+		else if (ptr > node->ptr)
+			n = n->rb_right;
+		else
+			return node;
+	}
+	return NULL;
+}
+
+static struct binder_node *binder_new_node(struct binder_proc *proc,
+					   binder_uintptr_t ptr,
+					   binder_uintptr_t cookie)
+{
+	struct rb_node **p = &proc->nodes.rb_node;
+	struct rb_node *parent = NULL;
+	struct binder_node *node;
+
+	while (*p) {
+		parent = *p;
+		node = rb_entry(parent, struct binder_node, rb_node);
+
+		if (ptr < node->ptr)
+			p = &(*p)->rb_left;
+		else if (ptr > node->ptr)
+			p = &(*p)->rb_right;
+		else
+			return NULL;
+	}
+
+	node = kzalloc(sizeof(*node), GFP_KERNEL);
+	if (node == NULL)
+		return NULL;
+	binder_stats_created(BINDER_STAT_NODE);
+	rb_link_node(&node->rb_node, parent, p);
+	rb_insert_color(&node->rb_node, &proc->nodes);
+	node->debug_id = ++binder_last_id;
+	node->proc = proc;
+	node->ptr = ptr;
+	node->cookie = cookie;
+	node->work.type = BINDER_WORK_NODE;
+	INIT_LIST_HEAD(&node->work.entry);
+	INIT_LIST_HEAD(&node->async_todo);
+	binder_debug(BINDER_DEBUG_INTERNAL_REFS,
+		     "%d:%d node %d u%016llx c%016llx created\n",
+		     proc->pid, current->pid, node->debug_id,
+		     (u64)node->ptr, (u64)node->cookie);
+	return node;
+}
+
+static int binder_inc_node(struct binder_node *node, int strong, int internal,
+			   struct list_head *target_list)
+{
+	if (strong) {
+		if (internal) {
+			if (target_list == NULL &&
+			    node->internal_strong_refs == 0 &&
+			    !(node == binder_context_mgr_node &&
+			    node->has_strong_ref)) {
+				pr_err("invalid inc strong node for %d\n",
+					node->debug_id);
+				return -EINVAL;
+			}
+			node->internal_strong_refs++;
+		} else
+			node->local_strong_refs++;
+		if (!node->has_strong_ref && target_list) {
+			list_del_init(&node->work.entry);
+			list_add_tail(&node->work.entry, target_list);
+		}
+	} else {
+		if (!internal)
+			node->local_weak_refs++;
+		if (!node->has_weak_ref && list_empty(&node->work.entry)) {
+			if (target_list == NULL) {
+				pr_err("invalid inc weak node for %d\n",
+					node->debug_id);
+				return -EINVAL;
+			}
+			list_add_tail(&node->work.entry, target_list);
+		}
+	}
+	return 0;
+}
+
+static int binder_dec_node(struct binder_node *node, int strong, int internal)
+{
+	if (strong) {
+		if (internal)
+			node->internal_strong_refs--;
+		else
+			node->local_strong_refs--;
+		if (node->local_strong_refs || node->internal_strong_refs)
+			return 0;
+	} else {
+		if (!internal)
+			node->local_weak_refs--;
+		if (node->local_weak_refs || !hlist_empty(&node->refs))
+			return 0;
+	}
+	if (node->proc && (node->has_strong_ref || node->has_weak_ref)) {
+		if (list_empty(&node->work.entry)) {
+			list_add_tail(&node->work.entry, &node->proc->todo);
+			wake_up_interruptible(&node->proc->wait);
+		}
+	} else {
+		if (hlist_empty(&node->refs) && !node->local_strong_refs &&
+		    !node->local_weak_refs) {
+			list_del_init(&node->work.entry);
+			if (node->proc) {
+				rb_erase(&node->rb_node, &node->proc->nodes);
+				binder_debug(BINDER_DEBUG_INTERNAL_REFS,
+					     "refless node %d deleted\n",
+					     node->debug_id);
+			} else {
+				hlist_del(&node->dead_node);
+				binder_debug(BINDER_DEBUG_INTERNAL_REFS,
+					     "dead node %d deleted\n",
+					     node->debug_id);
+			}
+			kfree(node);
+			binder_stats_deleted(BINDER_STAT_NODE);
+		}
+	}
+
+	return 0;
+}
+
+
+static struct binder_ref *binder_get_ref(struct binder_proc *proc,
+					 uint32_t desc)
+{
+	struct rb_node *n = proc->refs_by_desc.rb_node;
+	struct binder_ref *ref;
+
+	while (n) {
+		ref = rb_entry(n, struct binder_ref, rb_node_desc);
+
+		if (desc < ref->desc)
+			n = n->rb_left;
+		else if (desc > ref->desc)
+			n = n->rb_right;
+		else
+			return ref;
+	}
+	return NULL;
+}
+
+static struct binder_ref *binder_get_ref_for_node(struct binder_proc *proc,
+						  struct binder_node *node)
+{
+	struct rb_node *n;
+	struct rb_node **p = &proc->refs_by_node.rb_node;
+	struct rb_node *parent = NULL;
+	struct binder_ref *ref, *new_ref;
+
+	while (*p) {
+		parent = *p;
+		ref = rb_entry(parent, struct binder_ref, rb_node_node);
+
+		if (node < ref->node)
+			p = &(*p)->rb_left;
+		else if (node > ref->node)
+			p = &(*p)->rb_right;
+		else
+			return ref;
+	}
+	new_ref = kzalloc(sizeof(*ref), GFP_KERNEL);
+	if (new_ref == NULL)
+		return NULL;
+	binder_stats_created(BINDER_STAT_REF);
+	new_ref->debug_id = ++binder_last_id;
+	new_ref->proc = proc;
+	new_ref->node = node;
+	rb_link_node(&new_ref->rb_node_node, parent, p);
+	rb_insert_color(&new_ref->rb_node_node, &proc->refs_by_node);
+
+	new_ref->desc = (node == binder_context_mgr_node) ? 0 : 1;
+	for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) {
+		ref = rb_entry(n, struct binder_ref, rb_node_desc);
+		if (ref->desc > new_ref->desc)
+			break;
+		new_ref->desc = ref->desc + 1;
+	}
+
+	p = &proc->refs_by_desc.rb_node;
+	while (*p) {
+		parent = *p;
+		ref = rb_entry(parent, struct binder_ref, rb_node_desc);
+
+		if (new_ref->desc < ref->desc)
+			p = &(*p)->rb_left;
+		else if (new_ref->desc > ref->desc)
+			p = &(*p)->rb_right;
+		else
+			BUG();
+	}
+	rb_link_node(&new_ref->rb_node_desc, parent, p);
+	rb_insert_color(&new_ref->rb_node_desc, &proc->refs_by_desc);
+	if (node) {
+		hlist_add_head(&new_ref->node_entry, &node->refs);
+
+		binder_debug(BINDER_DEBUG_INTERNAL_REFS,
+			     "%d new ref %d desc %d for node %d\n",
+			      proc->pid, new_ref->debug_id, new_ref->desc,
+			      node->debug_id);
+	} else {
+		binder_debug(BINDER_DEBUG_INTERNAL_REFS,
+			     "%d new ref %d desc %d for dead node\n",
+			      proc->pid, new_ref->debug_id, new_ref->desc);
+	}
+	return new_ref;
+}
+
+static void binder_delete_ref(struct binder_ref *ref)
+{
+	binder_debug(BINDER_DEBUG_INTERNAL_REFS,
+		     "%d delete ref %d desc %d for node %d\n",
+		      ref->proc->pid, ref->debug_id, ref->desc,
+		      ref->node->debug_id);
+
+	rb_erase(&ref->rb_node_desc, &ref->proc->refs_by_desc);
+	rb_erase(&ref->rb_node_node, &ref->proc->refs_by_node);
+	if (ref->strong)
+		binder_dec_node(ref->node, 1, 1);
+	hlist_del(&ref->node_entry);
+	binder_dec_node(ref->node, 0, 1);
+	if (ref->death) {
+		binder_debug(BINDER_DEBUG_DEAD_BINDER,
+			     "%d delete ref %d desc %d has death notification\n",
+			      ref->proc->pid, ref->debug_id, ref->desc);
+		list_del(&ref->death->work.entry);
+		kfree(ref->death);
+		binder_stats_deleted(BINDER_STAT_DEATH);
+	}
+	kfree(ref);
+	binder_stats_deleted(BINDER_STAT_REF);
+}
+
+static int binder_inc_ref(struct binder_ref *ref, int strong,
+			  struct list_head *target_list)
+{
+	int ret;
+
+	if (strong) {
+		if (ref->strong == 0) {
+			ret = binder_inc_node(ref->node, 1, 1, target_list);
+			if (ret)
+				return ret;
+		}
+		ref->strong++;
+	} else {
+		if (ref->weak == 0) {
+			ret = binder_inc_node(ref->node, 0, 1, target_list);
+			if (ret)
+				return ret;
+		}
+		ref->weak++;
+	}
+	return 0;
+}
+
+
+static int binder_dec_ref(struct binder_ref *ref, int strong)
+{
+	if (strong) {
+		if (ref->strong == 0) {
+			binder_user_error("%d invalid dec strong, ref %d desc %d s %d w %d\n",
+					  ref->proc->pid, ref->debug_id,
+					  ref->desc, ref->strong, ref->weak);
+			return -EINVAL;
+		}
+		ref->strong--;
+		if (ref->strong == 0) {
+			int ret;
+
+			ret = binder_dec_node(ref->node, strong, 1);
+			if (ret)
+				return ret;
+		}
+	} else {
+		if (ref->weak == 0) {
+			binder_user_error("%d invalid dec weak, ref %d desc %d s %d w %d\n",
+					  ref->proc->pid, ref->debug_id,
+					  ref->desc, ref->strong, ref->weak);
+			return -EINVAL;
+		}
+		ref->weak--;
+	}
+	if (ref->strong == 0 && ref->weak == 0)
+		binder_delete_ref(ref);
+	return 0;
+}
+
+static void binder_pop_transaction(struct binder_thread *target_thread,
+				   struct binder_transaction *t)
+{
+	if (target_thread) {
+		BUG_ON(target_thread->transaction_stack != t);
+		BUG_ON(target_thread->transaction_stack->from != target_thread);
+		target_thread->transaction_stack =
+			target_thread->transaction_stack->from_parent;
+		t->from = NULL;
+	}
+	t->need_reply = 0;
+	if (t->buffer)
+		t->buffer->transaction = NULL;
+	kfree(t);
+	binder_stats_deleted(BINDER_STAT_TRANSACTION);
+}
+
+static void binder_send_failed_reply(struct binder_transaction *t,
+				     uint32_t error_code)
+{
+	struct binder_thread *target_thread;
+	struct binder_transaction *next;
+
+	BUG_ON(t->flags & TF_ONE_WAY);
+	while (1) {
+		target_thread = t->from;
+		if (target_thread) {
+			if (target_thread->return_error != BR_OK &&
+			   target_thread->return_error2 == BR_OK) {
+				target_thread->return_error2 =
+					target_thread->return_error;
+				target_thread->return_error = BR_OK;
+			}
+			if (target_thread->return_error == BR_OK) {
+				binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
+					     "send failed reply for transaction %d to %d:%d\n",
+					      t->debug_id,
+					      target_thread->proc->pid,
+					      target_thread->pid);
+
+				binder_pop_transaction(target_thread, t);
+				target_thread->return_error = error_code;
+				wake_up_interruptible(&target_thread->wait);
+			} else {
+				pr_err("reply failed, target thread, %d:%d, has error code %d already\n",
+					target_thread->proc->pid,
+					target_thread->pid,
+					target_thread->return_error);
+			}
+			return;
+		}
+		next = t->from_parent;
+
+		binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
+			     "send failed reply for transaction %d, target dead\n",
+			     t->debug_id);
+
+		binder_pop_transaction(target_thread, t);
+		if (next == NULL) {
+			binder_debug(BINDER_DEBUG_DEAD_BINDER,
+				     "reply failed, no target thread at root\n");
+			return;
+		}
+		t = next;
+		binder_debug(BINDER_DEBUG_DEAD_BINDER,
+			     "reply failed, no target thread -- retry %d\n",
+			      t->debug_id);
+	}
+}
+
+static void binder_transaction_buffer_release(struct binder_proc *proc,
+					      struct binder_buffer *buffer,
+					      binder_size_t *failed_at)
+{
+	binder_size_t *offp, *off_end;
+	int debug_id = buffer->debug_id;
+
+	binder_debug(BINDER_DEBUG_TRANSACTION,
+		     "%d buffer release %d, size %zd-%zd, failed at %p\n",
+		     proc->pid, buffer->debug_id,
+		     buffer->data_size, buffer->offsets_size, failed_at);
+
+	if (buffer->target_node)
+		binder_dec_node(buffer->target_node, 1, 0);
+
+	offp = (binder_size_t *)(buffer->data +
+				 ALIGN(buffer->data_size, sizeof(void *)));
+	if (failed_at)
+		off_end = failed_at;
+	else
+		off_end = (void *)offp + buffer->offsets_size;
+	for (; offp < off_end; offp++) {
+		struct flat_binder_object *fp;
+
+		if (*offp > buffer->data_size - sizeof(*fp) ||
+		    buffer->data_size < sizeof(*fp) ||
+		    !IS_ALIGNED(*offp, sizeof(u32))) {
+			pr_err("transaction release %d bad offset %lld, size %zd\n",
+			       debug_id, (u64)*offp, buffer->data_size);
+			continue;
+		}
+		fp = (struct flat_binder_object *)(buffer->data + *offp);
+		switch (fp->type) {
+		case BINDER_TYPE_BINDER:
+		case BINDER_TYPE_WEAK_BINDER: {
+			struct binder_node *node = binder_get_node(proc, fp->binder);
+
+			if (node == NULL) {
+				pr_err("transaction release %d bad node %016llx\n",
+				       debug_id, (u64)fp->binder);
+				break;
+			}
+			binder_debug(BINDER_DEBUG_TRANSACTION,
+				     "        node %d u%016llx\n",
+				     node->debug_id, (u64)node->ptr);
+			binder_dec_node(node, fp->type == BINDER_TYPE_BINDER, 0);
+		} break;
+		case BINDER_TYPE_HANDLE:
+		case BINDER_TYPE_WEAK_HANDLE: {
+			struct binder_ref *ref = binder_get_ref(proc, fp->handle);
+
+			if (ref == NULL) {
+				pr_err("transaction release %d bad handle %d\n",
+				 debug_id, fp->handle);
+				break;
+			}
+			binder_debug(BINDER_DEBUG_TRANSACTION,
+				     "        ref %d desc %d (node %d)\n",
+				     ref->debug_id, ref->desc, ref->node->debug_id);
+			binder_dec_ref(ref, fp->type == BINDER_TYPE_HANDLE);
+		} break;
+
+		case BINDER_TYPE_FD:
+			binder_debug(BINDER_DEBUG_TRANSACTION,
+				     "        fd %d\n", fp->handle);
+			if (failed_at)
+				task_close_fd(proc, fp->handle);
+			break;
+
+		default:
+			pr_err("transaction release %d bad object type %x\n",
+				debug_id, fp->type);
+			break;
+		}
+	}
+}
+
+static void binder_transaction(struct binder_proc *proc,
+			       struct binder_thread *thread,
+			       struct binder_transaction_data *tr, int reply)
+{
+	struct binder_transaction *t;
+	struct binder_work *tcomplete;
+	binder_size_t *offp, *off_end;
+	struct binder_proc *target_proc;
+	struct binder_thread *target_thread = NULL;
+	struct binder_node *target_node = NULL;
+	struct list_head *target_list;
+	wait_queue_head_t *target_wait;
+	struct binder_transaction *in_reply_to = NULL;
+	struct binder_transaction_log_entry *e;
+	uint32_t return_error;
+
+	e = binder_transaction_log_add(&binder_transaction_log);
+	e->call_type = reply ? 2 : !!(tr->flags & TF_ONE_WAY);
+	e->from_proc = proc->pid;
+	e->from_thread = thread->pid;
+	e->target_handle = tr->target.handle;
+	e->data_size = tr->data_size;
+	e->offsets_size = tr->offsets_size;
+
+	if (reply) {
+		in_reply_to = thread->transaction_stack;
+		if (in_reply_to == NULL) {
+			binder_user_error("%d:%d got reply transaction with no transaction stack\n",
+					  proc->pid, thread->pid);
+			return_error = BR_FAILED_REPLY;
+			goto err_empty_call_stack;
+		}
+		binder_set_nice(in_reply_to->saved_priority);
+		if (in_reply_to->to_thread != thread) {
+			binder_user_error("%d:%d got reply transaction with bad transaction stack, transaction %d has target %d:%d\n",
+				proc->pid, thread->pid, in_reply_to->debug_id,
+				in_reply_to->to_proc ?
+				in_reply_to->to_proc->pid : 0,
+				in_reply_to->to_thread ?
+				in_reply_to->to_thread->pid : 0);
+			return_error = BR_FAILED_REPLY;
+			in_reply_to = NULL;
+			goto err_bad_call_stack;
+		}
+		thread->transaction_stack = in_reply_to->to_parent;
+		target_thread = in_reply_to->from;
+		if (target_thread == NULL) {
+			return_error = BR_DEAD_REPLY;
+			goto err_dead_binder;
+		}
+		if (target_thread->transaction_stack != in_reply_to) {
+			binder_user_error("%d:%d got reply transaction with bad target transaction stack %d, expected %d\n",
+				proc->pid, thread->pid,
+				target_thread->transaction_stack ?
+				target_thread->transaction_stack->debug_id : 0,
+				in_reply_to->debug_id);
+			return_error = BR_FAILED_REPLY;
+			in_reply_to = NULL;
+			target_thread = NULL;
+			goto err_dead_binder;
+		}
+		target_proc = target_thread->proc;
+	} else {
+		if (tr->target.handle) {
+			struct binder_ref *ref;
+
+			ref = binder_get_ref(proc, tr->target.handle);
+			if (ref == NULL) {
+				binder_user_error("%d:%d got transaction to invalid handle\n",
+					proc->pid, thread->pid);
+				return_error = BR_FAILED_REPLY;
+				goto err_invalid_target_handle;
+			}
+			target_node = ref->node;
+		} else {
+			target_node = binder_context_mgr_node;
+			if (target_node == NULL) {
+				return_error = BR_DEAD_REPLY;
+				goto err_no_context_mgr_node;
+			}
+		}
+		e->to_node = target_node->debug_id;
+		target_proc = target_node->proc;
+		if (target_proc == NULL) {
+			return_error = BR_DEAD_REPLY;
+			goto err_dead_binder;
+		}
+		if (!(tr->flags & TF_ONE_WAY) && thread->transaction_stack) {
+			struct binder_transaction *tmp;
+
+			tmp = thread->transaction_stack;
+			if (tmp->to_thread != thread) {
+				binder_user_error("%d:%d got new transaction with bad transaction stack, transaction %d has target %d:%d\n",
+					proc->pid, thread->pid, tmp->debug_id,
+					tmp->to_proc ? tmp->to_proc->pid : 0,
+					tmp->to_thread ?
+					tmp->to_thread->pid : 0);
+				return_error = BR_FAILED_REPLY;
+				goto err_bad_call_stack;
+			}
+			while (tmp) {
+				if (tmp->from && tmp->from->proc == target_proc)
+					target_thread = tmp->from;
+				tmp = tmp->from_parent;
+			}
+		}
+	}
+	if (target_thread) {
+		e->to_thread = target_thread->pid;
+		target_list = &target_thread->todo;
+		target_wait = &target_thread->wait;
+	} else {
+		target_list = &target_proc->todo;
+		target_wait = &target_proc->wait;
+	}
+	e->to_proc = target_proc->pid;
+
+	/* TODO: reuse incoming transaction for reply */
+	t = kzalloc(sizeof(*t), GFP_KERNEL);
+	if (t == NULL) {
+		return_error = BR_FAILED_REPLY;
+		goto err_alloc_t_failed;
+	}
+	binder_stats_created(BINDER_STAT_TRANSACTION);
+
+	tcomplete = kzalloc(sizeof(*tcomplete), GFP_KERNEL);
+	if (tcomplete == NULL) {
+		return_error = BR_FAILED_REPLY;
+		goto err_alloc_tcomplete_failed;
+	}
+	binder_stats_created(BINDER_STAT_TRANSACTION_COMPLETE);
+
+	t->debug_id = ++binder_last_id;
+	e->debug_id = t->debug_id;
+
+	if (reply)
+		binder_debug(BINDER_DEBUG_TRANSACTION,
+			     "%d:%d BC_REPLY %d -> %d:%d, data %016llx-%016llx size %lld-%lld\n",
+			     proc->pid, thread->pid, t->debug_id,
+			     target_proc->pid, target_thread->pid,
+			     (u64)tr->data.ptr.buffer,
+			     (u64)tr->data.ptr.offsets,
+			     (u64)tr->data_size, (u64)tr->offsets_size);
+	else
+		binder_debug(BINDER_DEBUG_TRANSACTION,
+			     "%d:%d BC_TRANSACTION %d -> %d - node %d, data %016llx-%016llx size %lld-%lld\n",
+			     proc->pid, thread->pid, t->debug_id,
+			     target_proc->pid, target_node->debug_id,
+			     (u64)tr->data.ptr.buffer,
+			     (u64)tr->data.ptr.offsets,
+			     (u64)tr->data_size, (u64)tr->offsets_size);
+
+	if (!reply && !(tr->flags & TF_ONE_WAY))
+		t->from = thread;
+	else
+		t->from = NULL;
+	t->sender_euid = task_euid(proc->tsk);
+	t->to_proc = target_proc;
+	t->to_thread = target_thread;
+	t->code = tr->code;
+	t->flags = tr->flags;
+	t->priority = task_nice(current);
+
+	trace_binder_transaction(reply, t, target_node);
+
+	t->buffer = binder_alloc_buf(target_proc, tr->data_size,
+		tr->offsets_size, !reply && (t->flags & TF_ONE_WAY));
+	if (t->buffer == NULL) {
+		return_error = BR_FAILED_REPLY;
+		goto err_binder_alloc_buf_failed;
+	}
+	t->buffer->allow_user_free = 0;
+	t->buffer->debug_id = t->debug_id;
+	t->buffer->transaction = t;
+	t->buffer->target_node = target_node;
+	trace_binder_transaction_alloc_buf(t->buffer);
+	if (target_node)
+		binder_inc_node(target_node, 1, 0, NULL);
+
+	offp = (binder_size_t *)(t->buffer->data +
+				 ALIGN(tr->data_size, sizeof(void *)));
+
+	if (copy_from_user(t->buffer->data, (const void __user *)(uintptr_t)
+			   tr->data.ptr.buffer, tr->data_size)) {
+		binder_user_error("%d:%d got transaction with invalid data ptr\n",
+				proc->pid, thread->pid);
+		return_error = BR_FAILED_REPLY;
+		goto err_copy_data_failed;
+	}
+	if (copy_from_user(offp, (const void __user *)(uintptr_t)
+			   tr->data.ptr.offsets, tr->offsets_size)) {
+		binder_user_error("%d:%d got transaction with invalid offsets ptr\n",
+				proc->pid, thread->pid);
+		return_error = BR_FAILED_REPLY;
+		goto err_copy_data_failed;
+	}
+	if (!IS_ALIGNED(tr->offsets_size, sizeof(binder_size_t))) {
+		binder_user_error("%d:%d got transaction with invalid offsets size, %lld\n",
+				proc->pid, thread->pid, (u64)tr->offsets_size);
+		return_error = BR_FAILED_REPLY;
+		goto err_bad_offset;
+	}
+	off_end = (void *)offp + tr->offsets_size;
+	for (; offp < off_end; offp++) {
+		struct flat_binder_object *fp;
+
+		if (*offp > t->buffer->data_size - sizeof(*fp) ||
+		    t->buffer->data_size < sizeof(*fp) ||
+		    !IS_ALIGNED(*offp, sizeof(u32))) {
+			binder_user_error("%d:%d got transaction with invalid offset, %lld\n",
+					  proc->pid, thread->pid, (u64)*offp);
+			return_error = BR_FAILED_REPLY;
+			goto err_bad_offset;
+		}
+		fp = (struct flat_binder_object *)(t->buffer->data + *offp);
+		switch (fp->type) {
+		case BINDER_TYPE_BINDER:
+		case BINDER_TYPE_WEAK_BINDER: {
+			struct binder_ref *ref;
+			struct binder_node *node = binder_get_node(proc, fp->binder);
+
+			if (node == NULL) {
+				node = binder_new_node(proc, fp->binder, fp->cookie);
+				if (node == NULL) {
+					return_error = BR_FAILED_REPLY;
+					goto err_binder_new_node_failed;
+				}
+				node->min_priority = fp->flags & FLAT_BINDER_FLAG_PRIORITY_MASK;
+				node->accept_fds = !!(fp->flags & FLAT_BINDER_FLAG_ACCEPTS_FDS);
+			}
+			if (fp->cookie != node->cookie) {
+				binder_user_error("%d:%d sending u%016llx node %d, cookie mismatch %016llx != %016llx\n",
+					proc->pid, thread->pid,
+					(u64)fp->binder, node->debug_id,
+					(u64)fp->cookie, (u64)node->cookie);
+				return_error = BR_FAILED_REPLY;
+				goto err_binder_get_ref_for_node_failed;
+			}
+			ref = binder_get_ref_for_node(target_proc, node);
+			if (ref == NULL) {
+				return_error = BR_FAILED_REPLY;
+				goto err_binder_get_ref_for_node_failed;
+			}
+			if (fp->type == BINDER_TYPE_BINDER)
+				fp->type = BINDER_TYPE_HANDLE;
+			else
+				fp->type = BINDER_TYPE_WEAK_HANDLE;
+			fp->handle = ref->desc;
+			binder_inc_ref(ref, fp->type == BINDER_TYPE_HANDLE,
+				       &thread->todo);
+
+			trace_binder_transaction_node_to_ref(t, node, ref);
+			binder_debug(BINDER_DEBUG_TRANSACTION,
+				     "        node %d u%016llx -> ref %d desc %d\n",
+				     node->debug_id, (u64)node->ptr,
+				     ref->debug_id, ref->desc);
+		} break;
+		case BINDER_TYPE_HANDLE:
+		case BINDER_TYPE_WEAK_HANDLE: {
+			struct binder_ref *ref = binder_get_ref(proc, fp->handle);
+
+			if (ref == NULL) {
+				binder_user_error("%d:%d got transaction with invalid handle, %d\n",
+						proc->pid,
+						thread->pid, fp->handle);
+				return_error = BR_FAILED_REPLY;
+				goto err_binder_get_ref_failed;
+			}
+			if (ref->node->proc == target_proc) {
+				if (fp->type == BINDER_TYPE_HANDLE)
+					fp->type = BINDER_TYPE_BINDER;
+				else
+					fp->type = BINDER_TYPE_WEAK_BINDER;
+				fp->binder = ref->node->ptr;
+				fp->cookie = ref->node->cookie;
+				binder_inc_node(ref->node, fp->type == BINDER_TYPE_BINDER, 0, NULL);
+				trace_binder_transaction_ref_to_node(t, ref);
+				binder_debug(BINDER_DEBUG_TRANSACTION,
+					     "        ref %d desc %d -> node %d u%016llx\n",
+					     ref->debug_id, ref->desc, ref->node->debug_id,
+					     (u64)ref->node->ptr);
+			} else {
+				struct binder_ref *new_ref;
+
+				new_ref = binder_get_ref_for_node(target_proc, ref->node);
+				if (new_ref == NULL) {
+					return_error = BR_FAILED_REPLY;
+					goto err_binder_get_ref_for_node_failed;
+				}
+				fp->handle = new_ref->desc;
+				binder_inc_ref(new_ref, fp->type == BINDER_TYPE_HANDLE, NULL);
+				trace_binder_transaction_ref_to_ref(t, ref,
+								    new_ref);
+				binder_debug(BINDER_DEBUG_TRANSACTION,
+					     "        ref %d desc %d -> ref %d desc %d (node %d)\n",
+					     ref->debug_id, ref->desc, new_ref->debug_id,
+					     new_ref->desc, ref->node->debug_id);
+			}
+		} break;
+
+		case BINDER_TYPE_FD: {
+			int target_fd;
+			struct file *file;
+
+			if (reply) {
+				if (!(in_reply_to->flags & TF_ACCEPT_FDS)) {
+					binder_user_error("%d:%d got reply with fd, %d, but target does not allow fds\n",
+						proc->pid, thread->pid, fp->handle);
+					return_error = BR_FAILED_REPLY;
+					goto err_fd_not_allowed;
+				}
+			} else if (!target_node->accept_fds) {
+				binder_user_error("%d:%d got transaction with fd, %d, but target does not allow fds\n",
+					proc->pid, thread->pid, fp->handle);
+				return_error = BR_FAILED_REPLY;
+				goto err_fd_not_allowed;
+			}
+
+			file = fget(fp->handle);
+			if (file == NULL) {
+				binder_user_error("%d:%d got transaction with invalid fd, %d\n",
+					proc->pid, thread->pid, fp->handle);
+				return_error = BR_FAILED_REPLY;
+				goto err_fget_failed;
+			}
+			target_fd = task_get_unused_fd_flags(target_proc, O_CLOEXEC);
+			if (target_fd < 0) {
+				fput(file);
+				return_error = BR_FAILED_REPLY;
+				goto err_get_unused_fd_failed;
+			}
+			task_fd_install(target_proc, target_fd, file);
+			trace_binder_transaction_fd(t, fp->handle, target_fd);
+			binder_debug(BINDER_DEBUG_TRANSACTION,
+				     "        fd %d -> %d\n", fp->handle, target_fd);
+			/* TODO: fput? */
+			fp->handle = target_fd;
+		} break;
+
+		default:
+			binder_user_error("%d:%d got transaction with invalid object type, %x\n",
+				proc->pid, thread->pid, fp->type);
+			return_error = BR_FAILED_REPLY;
+			goto err_bad_object_type;
+		}
+	}
+	if (reply) {
+		BUG_ON(t->buffer->async_transaction != 0);
+		binder_pop_transaction(target_thread, in_reply_to);
+	} else if (!(t->flags & TF_ONE_WAY)) {
+		BUG_ON(t->buffer->async_transaction != 0);
+		t->need_reply = 1;
+		t->from_parent = thread->transaction_stack;
+		thread->transaction_stack = t;
+	} else {
+		BUG_ON(target_node == NULL);
+		BUG_ON(t->buffer->async_transaction != 1);
+		if (target_node->has_async_transaction) {
+			target_list = &target_node->async_todo;
+			target_wait = NULL;
+		} else
+			target_node->has_async_transaction = 1;
+	}
+	t->work.type = BINDER_WORK_TRANSACTION;
+	list_add_tail(&t->work.entry, target_list);
+	tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE;
+	list_add_tail(&tcomplete->entry, &thread->todo);
+	if (target_wait)
+		wake_up_interruptible(target_wait);
+	return;
+
+err_get_unused_fd_failed:
+err_fget_failed:
+err_fd_not_allowed:
+err_binder_get_ref_for_node_failed:
+err_binder_get_ref_failed:
+err_binder_new_node_failed:
+err_bad_object_type:
+err_bad_offset:
+err_copy_data_failed:
+	trace_binder_transaction_failed_buffer_release(t->buffer);
+	binder_transaction_buffer_release(target_proc, t->buffer, offp);
+	t->buffer->transaction = NULL;
+	binder_free_buf(target_proc, t->buffer);
+err_binder_alloc_buf_failed:
+	kfree(tcomplete);
+	binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE);
+err_alloc_tcomplete_failed:
+	kfree(t);
+	binder_stats_deleted(BINDER_STAT_TRANSACTION);
+err_alloc_t_failed:
+err_bad_call_stack:
+err_empty_call_stack:
+err_dead_binder:
+err_invalid_target_handle:
+err_no_context_mgr_node:
+	binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
+		     "%d:%d transaction failed %d, size %lld-%lld\n",
+		     proc->pid, thread->pid, return_error,
+		     (u64)tr->data_size, (u64)tr->offsets_size);
+
+	{
+		struct binder_transaction_log_entry *fe;
+
+		fe = binder_transaction_log_add(&binder_transaction_log_failed);
+		*fe = *e;
+	}
+
+	BUG_ON(thread->return_error != BR_OK);
+	if (in_reply_to) {
+		thread->return_error = BR_TRANSACTION_COMPLETE;
+		binder_send_failed_reply(in_reply_to, return_error);
+	} else
+		thread->return_error = return_error;
+}
+
+static int binder_thread_write(struct binder_proc *proc,
+			struct binder_thread *thread,
+			binder_uintptr_t binder_buffer, size_t size,
+			binder_size_t *consumed)
+{
+	uint32_t cmd;
+	void __user *buffer = (void __user *)(uintptr_t)binder_buffer;
+	void __user *ptr = buffer + *consumed;
+	void __user *end = buffer + size;
+
+	while (ptr < end && thread->return_error == BR_OK) {
+		if (get_user(cmd, (uint32_t __user *)ptr))
+			return -EFAULT;
+		ptr += sizeof(uint32_t);
+		trace_binder_command(cmd);
+		if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.bc)) {
+			binder_stats.bc[_IOC_NR(cmd)]++;
+			proc->stats.bc[_IOC_NR(cmd)]++;
+			thread->stats.bc[_IOC_NR(cmd)]++;
+		}
+		switch (cmd) {
+		case BC_INCREFS:
+		case BC_ACQUIRE:
+		case BC_RELEASE:
+		case BC_DECREFS: {
+			uint32_t target;
+			struct binder_ref *ref;
+			const char *debug_string;
+
+			if (get_user(target, (uint32_t __user *)ptr))
+				return -EFAULT;
+			ptr += sizeof(uint32_t);
+			if (target == 0 && binder_context_mgr_node &&
+			    (cmd == BC_INCREFS || cmd == BC_ACQUIRE)) {
+				ref = binder_get_ref_for_node(proc,
+					       binder_context_mgr_node);
+				if (ref->desc != target) {
+					binder_user_error("%d:%d tried to acquire reference to desc 0, got %d instead\n",
+						proc->pid, thread->pid,
+						ref->desc);
+				}
+			} else
+				ref = binder_get_ref(proc, target);
+			if (ref == NULL) {
+				binder_user_error("%d:%d refcount change on invalid ref %d\n",
+					proc->pid, thread->pid, target);
+				break;
+			}
+			switch (cmd) {
+			case BC_INCREFS:
+				debug_string = "IncRefs";
+				binder_inc_ref(ref, 0, NULL);
+				break;
+			case BC_ACQUIRE:
+				debug_string = "Acquire";
+				binder_inc_ref(ref, 1, NULL);
+				break;
+			case BC_RELEASE:
+				debug_string = "Release";
+				binder_dec_ref(ref, 1);
+				break;
+			case BC_DECREFS:
+			default:
+				debug_string = "DecRefs";
+				binder_dec_ref(ref, 0);
+				break;
+			}
+			binder_debug(BINDER_DEBUG_USER_REFS,
+				     "%d:%d %s ref %d desc %d s %d w %d for node %d\n",
+				     proc->pid, thread->pid, debug_string, ref->debug_id,
+				     ref->desc, ref->strong, ref->weak, ref->node->debug_id);
+			break;
+		}
+		case BC_INCREFS_DONE:
+		case BC_ACQUIRE_DONE: {
+			binder_uintptr_t node_ptr;
+			binder_uintptr_t cookie;
+			struct binder_node *node;
+
+			if (get_user(node_ptr, (binder_uintptr_t __user *)ptr))
+				return -EFAULT;
+			ptr += sizeof(binder_uintptr_t);
+			if (get_user(cookie, (binder_uintptr_t __user *)ptr))
+				return -EFAULT;
+			ptr += sizeof(binder_uintptr_t);
+			node = binder_get_node(proc, node_ptr);
+			if (node == NULL) {
+				binder_user_error("%d:%d %s u%016llx no match\n",
+					proc->pid, thread->pid,
+					cmd == BC_INCREFS_DONE ?
+					"BC_INCREFS_DONE" :
+					"BC_ACQUIRE_DONE",
+					(u64)node_ptr);
+				break;
+			}
+			if (cookie != node->cookie) {
+				binder_user_error("%d:%d %s u%016llx node %d cookie mismatch %016llx != %016llx\n",
+					proc->pid, thread->pid,
+					cmd == BC_INCREFS_DONE ?
+					"BC_INCREFS_DONE" : "BC_ACQUIRE_DONE",
+					(u64)node_ptr, node->debug_id,
+					(u64)cookie, (u64)node->cookie);
+				break;
+			}
+			if (cmd == BC_ACQUIRE_DONE) {
+				if (node->pending_strong_ref == 0) {
+					binder_user_error("%d:%d BC_ACQUIRE_DONE node %d has no pending acquire request\n",
+						proc->pid, thread->pid,
+						node->debug_id);
+					break;
+				}
+				node->pending_strong_ref = 0;
+			} else {
+				if (node->pending_weak_ref == 0) {
+					binder_user_error("%d:%d BC_INCREFS_DONE node %d has no pending increfs request\n",
+						proc->pid, thread->pid,
+						node->debug_id);
+					break;
+				}
+				node->pending_weak_ref = 0;
+			}
+			binder_dec_node(node, cmd == BC_ACQUIRE_DONE, 0);
+			binder_debug(BINDER_DEBUG_USER_REFS,
+				     "%d:%d %s node %d ls %d lw %d\n",
+				     proc->pid, thread->pid,
+				     cmd == BC_INCREFS_DONE ? "BC_INCREFS_DONE" : "BC_ACQUIRE_DONE",
+				     node->debug_id, node->local_strong_refs, node->local_weak_refs);
+			break;
+		}
+		case BC_ATTEMPT_ACQUIRE:
+			pr_err("BC_ATTEMPT_ACQUIRE not supported\n");
+			return -EINVAL;
+		case BC_ACQUIRE_RESULT:
+			pr_err("BC_ACQUIRE_RESULT not supported\n");
+			return -EINVAL;
+
+		case BC_FREE_BUFFER: {
+			binder_uintptr_t data_ptr;
+			struct binder_buffer *buffer;
+
+			if (get_user(data_ptr, (binder_uintptr_t __user *)ptr))
+				return -EFAULT;
+			ptr += sizeof(binder_uintptr_t);
+
+			buffer = binder_buffer_lookup(proc, data_ptr);
+			if (buffer == NULL) {
+				binder_user_error("%d:%d BC_FREE_BUFFER u%016llx no match\n",
+					proc->pid, thread->pid, (u64)data_ptr);
+				break;
+			}
+			if (!buffer->allow_user_free) {
+				binder_user_error("%d:%d BC_FREE_BUFFER u%016llx matched unreturned buffer\n",
+					proc->pid, thread->pid, (u64)data_ptr);
+				break;
+			}
+			binder_debug(BINDER_DEBUG_FREE_BUFFER,
+				     "%d:%d BC_FREE_BUFFER u%016llx found buffer %d for %s transaction\n",
+				     proc->pid, thread->pid, (u64)data_ptr,
+				     buffer->debug_id,
+				     buffer->transaction ? "active" : "finished");
+
+			if (buffer->transaction) {
+				buffer->transaction->buffer = NULL;
+				buffer->transaction = NULL;
+			}
+			if (buffer->async_transaction && buffer->target_node) {
+				BUG_ON(!buffer->target_node->has_async_transaction);
+				if (list_empty(&buffer->target_node->async_todo))
+					buffer->target_node->has_async_transaction = 0;
+				else
+					list_move_tail(buffer->target_node->async_todo.next, &thread->todo);
+			}
+			trace_binder_transaction_buffer_release(buffer);
+			binder_transaction_buffer_release(proc, buffer, NULL);
+			binder_free_buf(proc, buffer);
+			break;
+		}
+
+		case BC_TRANSACTION:
+		case BC_REPLY: {
+			struct binder_transaction_data tr;
+
+			if (copy_from_user(&tr, ptr, sizeof(tr)))
+				return -EFAULT;
+			ptr += sizeof(tr);
+			binder_transaction(proc, thread, &tr, cmd == BC_REPLY);
+			break;
+		}
+
+		case BC_REGISTER_LOOPER:
+			binder_debug(BINDER_DEBUG_THREADS,
+				     "%d:%d BC_REGISTER_LOOPER\n",
+				     proc->pid, thread->pid);
+			if (thread->looper & BINDER_LOOPER_STATE_ENTERED) {
+				thread->looper |= BINDER_LOOPER_STATE_INVALID;
+				binder_user_error("%d:%d ERROR: BC_REGISTER_LOOPER called after BC_ENTER_LOOPER\n",
+					proc->pid, thread->pid);
+			} else if (proc->requested_threads == 0) {
+				thread->looper |= BINDER_LOOPER_STATE_INVALID;
+				binder_user_error("%d:%d ERROR: BC_REGISTER_LOOPER called without request\n",
+					proc->pid, thread->pid);
+			} else {
+				proc->requested_threads--;
+				proc->requested_threads_started++;
+			}
+			thread->looper |= BINDER_LOOPER_STATE_REGISTERED;
+			break;
+		case BC_ENTER_LOOPER:
+			binder_debug(BINDER_DEBUG_THREADS,
+				     "%d:%d BC_ENTER_LOOPER\n",
+				     proc->pid, thread->pid);
+			if (thread->looper & BINDER_LOOPER_STATE_REGISTERED) {
+				thread->looper |= BINDER_LOOPER_STATE_INVALID;
+				binder_user_error("%d:%d ERROR: BC_ENTER_LOOPER called after BC_REGISTER_LOOPER\n",
+					proc->pid, thread->pid);
+			}
+			thread->looper |= BINDER_LOOPER_STATE_ENTERED;
+			break;
+		case BC_EXIT_LOOPER:
+			binder_debug(BINDER_DEBUG_THREADS,
+				     "%d:%d BC_EXIT_LOOPER\n",
+				     proc->pid, thread->pid);
+			thread->looper |= BINDER_LOOPER_STATE_EXITED;
+			break;
+
+		case BC_REQUEST_DEATH_NOTIFICATION:
+		case BC_CLEAR_DEATH_NOTIFICATION: {
+			uint32_t target;
+			binder_uintptr_t cookie;
+			struct binder_ref *ref;
+			struct binder_ref_death *death;
+
+			if (get_user(target, (uint32_t __user *)ptr))
+				return -EFAULT;
+			ptr += sizeof(uint32_t);
+			if (get_user(cookie, (binder_uintptr_t __user *)ptr))
+				return -EFAULT;
+			ptr += sizeof(binder_uintptr_t);
+			ref = binder_get_ref(proc, target);
+			if (ref == NULL) {
+				binder_user_error("%d:%d %s invalid ref %d\n",
+					proc->pid, thread->pid,
+					cmd == BC_REQUEST_DEATH_NOTIFICATION ?
+					"BC_REQUEST_DEATH_NOTIFICATION" :
+					"BC_CLEAR_DEATH_NOTIFICATION",
+					target);
+				break;
+			}
+
+			binder_debug(BINDER_DEBUG_DEATH_NOTIFICATION,
+				     "%d:%d %s %016llx ref %d desc %d s %d w %d for node %d\n",
+				     proc->pid, thread->pid,
+				     cmd == BC_REQUEST_DEATH_NOTIFICATION ?
+				     "BC_REQUEST_DEATH_NOTIFICATION" :
+				     "BC_CLEAR_DEATH_NOTIFICATION",
+				     (u64)cookie, ref->debug_id, ref->desc,
+				     ref->strong, ref->weak, ref->node->debug_id);
+
+			if (cmd == BC_REQUEST_DEATH_NOTIFICATION) {
+				if (ref->death) {
+					binder_user_error("%d:%d BC_REQUEST_DEATH_NOTIFICATION death notification already set\n",
+						proc->pid, thread->pid);
+					break;
+				}
+				death = kzalloc(sizeof(*death), GFP_KERNEL);
+				if (death == NULL) {
+					thread->return_error = BR_ERROR;
+					binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
+						     "%d:%d BC_REQUEST_DEATH_NOTIFICATION failed\n",
+						     proc->pid, thread->pid);
+					break;
+				}
+				binder_stats_created(BINDER_STAT_DEATH);
+				INIT_LIST_HEAD(&death->work.entry);
+				death->cookie = cookie;
+				ref->death = death;
+				if (ref->node->proc == NULL) {
+					ref->death->work.type = BINDER_WORK_DEAD_BINDER;
+					if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) {
+						list_add_tail(&ref->death->work.entry, &thread->todo);
+					} else {
+						list_add_tail(&ref->death->work.entry, &proc->todo);
+						wake_up_interruptible(&proc->wait);
+					}
+				}
+			} else {
+				if (ref->death == NULL) {
+					binder_user_error("%d:%d BC_CLEAR_DEATH_NOTIFICATION death notification not active\n",
+						proc->pid, thread->pid);
+					break;
+				}
+				death = ref->death;
+				if (death->cookie != cookie) {
+					binder_user_error("%d:%d BC_CLEAR_DEATH_NOTIFICATION death notification cookie mismatch %016llx != %016llx\n",
+						proc->pid, thread->pid,
+						(u64)death->cookie,
+						(u64)cookie);
+					break;
+				}
+				ref->death = NULL;
+				if (list_empty(&death->work.entry)) {
+					death->work.type = BINDER_WORK_CLEAR_DEATH_NOTIFICATION;
+					if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) {
+						list_add_tail(&death->work.entry, &thread->todo);
+					} else {
+						list_add_tail(&death->work.entry, &proc->todo);
+						wake_up_interruptible(&proc->wait);
+					}
+				} else {
+					BUG_ON(death->work.type != BINDER_WORK_DEAD_BINDER);
+					death->work.type = BINDER_WORK_DEAD_BINDER_AND_CLEAR;
+				}
+			}
+		} break;
+		case BC_DEAD_BINDER_DONE: {
+			struct binder_work *w;
+			binder_uintptr_t cookie;
+			struct binder_ref_death *death = NULL;
+
+			if (get_user(cookie, (binder_uintptr_t __user *)ptr))
+				return -EFAULT;
+
+			ptr += sizeof(void *);
+			list_for_each_entry(w, &proc->delivered_death, entry) {
+				struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work);
+
+				if (tmp_death->cookie == cookie) {
+					death = tmp_death;
+					break;
+				}
+			}
+			binder_debug(BINDER_DEBUG_DEAD_BINDER,
+				     "%d:%d BC_DEAD_BINDER_DONE %016llx found %p\n",
+				     proc->pid, thread->pid, (u64)cookie,
+				     death);
+			if (death == NULL) {
+				binder_user_error("%d:%d BC_DEAD_BINDER_DONE %016llx not found\n",
+					proc->pid, thread->pid, (u64)cookie);
+				break;
+			}
+
+			list_del_init(&death->work.entry);
+			if (death->work.type == BINDER_WORK_DEAD_BINDER_AND_CLEAR) {
+				death->work.type = BINDER_WORK_CLEAR_DEATH_NOTIFICATION;
+				if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) {
+					list_add_tail(&death->work.entry, &thread->todo);
+				} else {
+					list_add_tail(&death->work.entry, &proc->todo);
+					wake_up_interruptible(&proc->wait);
+				}
+			}
+		} break;
+
+		default:
+			pr_err("%d:%d unknown command %d\n",
+			       proc->pid, thread->pid, cmd);
+			return -EINVAL;
+		}
+		*consumed = ptr - buffer;
+	}
+	return 0;
+}
+
+static void binder_stat_br(struct binder_proc *proc,
+			   struct binder_thread *thread, uint32_t cmd)
+{
+	trace_binder_return(cmd);
+	if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.br)) {
+		binder_stats.br[_IOC_NR(cmd)]++;
+		proc->stats.br[_IOC_NR(cmd)]++;
+		thread->stats.br[_IOC_NR(cmd)]++;
+	}
+}
+
+static int binder_has_proc_work(struct binder_proc *proc,
+				struct binder_thread *thread)
+{
+	return !list_empty(&proc->todo) ||
+		(thread->looper & BINDER_LOOPER_STATE_NEED_RETURN);
+}
+
+static int binder_has_thread_work(struct binder_thread *thread)
+{
+	return !list_empty(&thread->todo) || thread->return_error != BR_OK ||
+		(thread->looper & BINDER_LOOPER_STATE_NEED_RETURN);
+}
+
+static int binder_thread_read(struct binder_proc *proc,
+			      struct binder_thread *thread,
+			      binder_uintptr_t binder_buffer, size_t size,
+			      binder_size_t *consumed, int non_block)
+{
+	void __user *buffer = (void __user *)(uintptr_t)binder_buffer;
+	void __user *ptr = buffer + *consumed;
+	void __user *end = buffer + size;
+
+	int ret = 0;
+	int wait_for_proc_work;
+
+	if (*consumed == 0) {
+		if (put_user(BR_NOOP, (uint32_t __user *)ptr))
+			return -EFAULT;
+		ptr += sizeof(uint32_t);
+	}
+
+retry:
+	wait_for_proc_work = thread->transaction_stack == NULL &&
+				list_empty(&thread->todo);
+
+	if (thread->return_error != BR_OK && ptr < end) {
+		if (thread->return_error2 != BR_OK) {
+			if (put_user(thread->return_error2, (uint32_t __user *)ptr))
+				return -EFAULT;
+			ptr += sizeof(uint32_t);
+			binder_stat_br(proc, thread, thread->return_error2);
+			if (ptr == end)
+				goto done;
+			thread->return_error2 = BR_OK;
+		}
+		if (put_user(thread->return_error, (uint32_t __user *)ptr))
+			return -EFAULT;
+		ptr += sizeof(uint32_t);
+		binder_stat_br(proc, thread, thread->return_error);
+		thread->return_error = BR_OK;
+		goto done;
+	}
+
+
+	thread->looper |= BINDER_LOOPER_STATE_WAITING;
+	if (wait_for_proc_work)
+		proc->ready_threads++;
+
+	binder_unlock(__func__);
+
+	trace_binder_wait_for_work(wait_for_proc_work,
+				   !!thread->transaction_stack,
+				   !list_empty(&thread->todo));
+	if (wait_for_proc_work) {
+		if (!(thread->looper & (BINDER_LOOPER_STATE_REGISTERED |
+					BINDER_LOOPER_STATE_ENTERED))) {
+			binder_user_error("%d:%d ERROR: Thread waiting for process work before calling BC_REGISTER_LOOPER or BC_ENTER_LOOPER (state %x)\n",
+				proc->pid, thread->pid, thread->looper);
+			wait_event_interruptible(binder_user_error_wait,
+						 binder_stop_on_user_error < 2);
+		}
+		binder_set_nice(proc->default_priority);
+		if (non_block) {
+			if (!binder_has_proc_work(proc, thread))
+				ret = -EAGAIN;
+		} else
+			ret = wait_event_freezable_exclusive(proc->wait, binder_has_proc_work(proc, thread));
+	} else {
+		if (non_block) {
+			if (!binder_has_thread_work(thread))
+				ret = -EAGAIN;
+		} else
+			ret = wait_event_freezable(thread->wait, binder_has_thread_work(thread));
+	}
+
+	binder_lock(__func__);
+
+	if (wait_for_proc_work)
+		proc->ready_threads--;
+	thread->looper &= ~BINDER_LOOPER_STATE_WAITING;
+
+	if (ret)
+		return ret;
+
+	while (1) {
+		uint32_t cmd;
+		struct binder_transaction_data tr;
+		struct binder_work *w;
+		struct binder_transaction *t = NULL;
+
+		if (!list_empty(&thread->todo)) {
+			w = list_first_entry(&thread->todo, struct binder_work,
+					     entry);
+		} else if (!list_empty(&proc->todo) && wait_for_proc_work) {
+			w = list_first_entry(&proc->todo, struct binder_work,
+					     entry);
+		} else {
+			/* no data added */
+			if (ptr - buffer == 4 &&
+			    !(thread->looper & BINDER_LOOPER_STATE_NEED_RETURN))
+				goto retry;
+			break;
+		}
+
+		if (end - ptr < sizeof(tr) + 4)
+			break;
+
+		switch (w->type) {
+		case BINDER_WORK_TRANSACTION: {
+			t = container_of(w, struct binder_transaction, work);
+		} break;
+		case BINDER_WORK_TRANSACTION_COMPLETE: {
+			cmd = BR_TRANSACTION_COMPLETE;
+			if (put_user(cmd, (uint32_t __user *)ptr))
+				return -EFAULT;
+			ptr += sizeof(uint32_t);
+
+			binder_stat_br(proc, thread, cmd);
+			binder_debug(BINDER_DEBUG_TRANSACTION_COMPLETE,
+				     "%d:%d BR_TRANSACTION_COMPLETE\n",
+				     proc->pid, thread->pid);
+
+			list_del(&w->entry);
+			kfree(w);
+			binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE);
+		} break;
+		case BINDER_WORK_NODE: {
+			struct binder_node *node = container_of(w, struct binder_node, work);
+			uint32_t cmd = BR_NOOP;
+			const char *cmd_name;
+			int strong = node->internal_strong_refs || node->local_strong_refs;
+			int weak = !hlist_empty(&node->refs) || node->local_weak_refs || strong;
+
+			if (weak && !node->has_weak_ref) {
+				cmd = BR_INCREFS;
+				cmd_name = "BR_INCREFS";
+				node->has_weak_ref = 1;
+				node->pending_weak_ref = 1;
+				node->local_weak_refs++;
+			} else if (strong && !node->has_strong_ref) {
+				cmd = BR_ACQUIRE;
+				cmd_name = "BR_ACQUIRE";
+				node->has_strong_ref = 1;
+				node->pending_strong_ref = 1;
+				node->local_strong_refs++;
+			} else if (!strong && node->has_strong_ref) {
+				cmd = BR_RELEASE;
+				cmd_name = "BR_RELEASE";
+				node->has_strong_ref = 0;
+			} else if (!weak && node->has_weak_ref) {
+				cmd = BR_DECREFS;
+				cmd_name = "BR_DECREFS";
+				node->has_weak_ref = 0;
+			}
+			if (cmd != BR_NOOP) {
+				if (put_user(cmd, (uint32_t __user *)ptr))
+					return -EFAULT;
+				ptr += sizeof(uint32_t);
+				if (put_user(node->ptr,
+					     (binder_uintptr_t __user *)ptr))
+					return -EFAULT;
+				ptr += sizeof(binder_uintptr_t);
+				if (put_user(node->cookie,
+					     (binder_uintptr_t __user *)ptr))
+					return -EFAULT;
+				ptr += sizeof(binder_uintptr_t);
+
+				binder_stat_br(proc, thread, cmd);
+				binder_debug(BINDER_DEBUG_USER_REFS,
+					     "%d:%d %s %d u%016llx c%016llx\n",
+					     proc->pid, thread->pid, cmd_name,
+					     node->debug_id,
+					     (u64)node->ptr, (u64)node->cookie);
+			} else {
+				list_del_init(&w->entry);
+				if (!weak && !strong) {
+					binder_debug(BINDER_DEBUG_INTERNAL_REFS,
+						     "%d:%d node %d u%016llx c%016llx deleted\n",
+						     proc->pid, thread->pid,
+						     node->debug_id,
+						     (u64)node->ptr,
+						     (u64)node->cookie);
+					rb_erase(&node->rb_node, &proc->nodes);
+					kfree(node);
+					binder_stats_deleted(BINDER_STAT_NODE);
+				} else {
+					binder_debug(BINDER_DEBUG_INTERNAL_REFS,
+						     "%d:%d node %d u%016llx c%016llx state unchanged\n",
+						     proc->pid, thread->pid,
+						     node->debug_id,
+						     (u64)node->ptr,
+						     (u64)node->cookie);
+				}
+			}
+		} break;
+		case BINDER_WORK_DEAD_BINDER:
+		case BINDER_WORK_DEAD_BINDER_AND_CLEAR:
+		case BINDER_WORK_CLEAR_DEATH_NOTIFICATION: {
+			struct binder_ref_death *death;
+			uint32_t cmd;
+
+			death = container_of(w, struct binder_ref_death, work);
+			if (w->type == BINDER_WORK_CLEAR_DEATH_NOTIFICATION)
+				cmd = BR_CLEAR_DEATH_NOTIFICATION_DONE;
+			else
+				cmd = BR_DEAD_BINDER;
+			if (put_user(cmd, (uint32_t __user *)ptr))
+				return -EFAULT;
+			ptr += sizeof(uint32_t);
+			if (put_user(death->cookie,
+				     (binder_uintptr_t __user *)ptr))
+				return -EFAULT;
+			ptr += sizeof(binder_uintptr_t);
+			binder_stat_br(proc, thread, cmd);
+			binder_debug(BINDER_DEBUG_DEATH_NOTIFICATION,
+				     "%d:%d %s %016llx\n",
+				      proc->pid, thread->pid,
+				      cmd == BR_DEAD_BINDER ?
+				      "BR_DEAD_BINDER" :
+				      "BR_CLEAR_DEATH_NOTIFICATION_DONE",
+				      (u64)death->cookie);
+
+			if (w->type == BINDER_WORK_CLEAR_DEATH_NOTIFICATION) {
+				list_del(&w->entry);
+				kfree(death);
+				binder_stats_deleted(BINDER_STAT_DEATH);
+			} else
+				list_move(&w->entry, &proc->delivered_death);
+			if (cmd == BR_DEAD_BINDER)
+				goto done; /* DEAD_BINDER notifications can cause transactions */
+		} break;
+		}
+
+		if (!t)
+			continue;
+
+		BUG_ON(t->buffer == NULL);
+		if (t->buffer->target_node) {
+			struct binder_node *target_node = t->buffer->target_node;
+
+			tr.target.ptr = target_node->ptr;
+			tr.cookie =  target_node->cookie;
+			t->saved_priority = task_nice(current);
+			if (t->priority < target_node->min_priority &&
+			    !(t->flags & TF_ONE_WAY))
+				binder_set_nice(t->priority);
+			else if (!(t->flags & TF_ONE_WAY) ||
+				 t->saved_priority > target_node->min_priority)
+				binder_set_nice(target_node->min_priority);
+			cmd = BR_TRANSACTION;
+		} else {
+			tr.target.ptr = 0;
+			tr.cookie = 0;
+			cmd = BR_REPLY;
+		}
+		tr.code = t->code;
+		tr.flags = t->flags;
+		tr.sender_euid = from_kuid(current_user_ns(), t->sender_euid);
+
+		if (t->from) {
+			struct task_struct *sender = t->from->proc->tsk;
+
+			tr.sender_pid = task_tgid_nr_ns(sender,
+							task_active_pid_ns(current));
+		} else {
+			tr.sender_pid = 0;
+		}
+
+		tr.data_size = t->buffer->data_size;
+		tr.offsets_size = t->buffer->offsets_size;
+		tr.data.ptr.buffer = (binder_uintptr_t)(
+					(uintptr_t)t->buffer->data +
+					proc->user_buffer_offset);
+		tr.data.ptr.offsets = tr.data.ptr.buffer +
+					ALIGN(t->buffer->data_size,
+					    sizeof(void *));
+
+		if (put_user(cmd, (uint32_t __user *)ptr))
+			return -EFAULT;
+		ptr += sizeof(uint32_t);
+		if (copy_to_user(ptr, &tr, sizeof(tr)))
+			return -EFAULT;
+		ptr += sizeof(tr);
+
+		trace_binder_transaction_received(t);
+		binder_stat_br(proc, thread, cmd);
+		binder_debug(BINDER_DEBUG_TRANSACTION,
+			     "%d:%d %s %d %d:%d, cmd %d size %zd-%zd ptr %016llx-%016llx\n",
+			     proc->pid, thread->pid,
+			     (cmd == BR_TRANSACTION) ? "BR_TRANSACTION" :
+			     "BR_REPLY",
+			     t->debug_id, t->from ? t->from->proc->pid : 0,
+			     t->from ? t->from->pid : 0, cmd,
+			     t->buffer->data_size, t->buffer->offsets_size,
+			     (u64)tr.data.ptr.buffer, (u64)tr.data.ptr.offsets);
+
+		list_del(&t->work.entry);
+		t->buffer->allow_user_free = 1;
+		if (cmd == BR_TRANSACTION && !(t->flags & TF_ONE_WAY)) {
+			t->to_parent = thread->transaction_stack;
+			t->to_thread = thread;
+			thread->transaction_stack = t;
+		} else {
+			t->buffer->transaction = NULL;
+			kfree(t);
+			binder_stats_deleted(BINDER_STAT_TRANSACTION);
+		}
+		break;
+	}
+
+done:
+
+	*consumed = ptr - buffer;
+	if (proc->requested_threads + proc->ready_threads == 0 &&
+	    proc->requested_threads_started < proc->max_threads &&
+	    (thread->looper & (BINDER_LOOPER_STATE_REGISTERED |
+	     BINDER_LOOPER_STATE_ENTERED)) /* the user-space code fails to */
+	     /*spawn a new thread if we leave this out */) {
+		proc->requested_threads++;
+		binder_debug(BINDER_DEBUG_THREADS,
+			     "%d:%d BR_SPAWN_LOOPER\n",
+			     proc->pid, thread->pid);
+		if (put_user(BR_SPAWN_LOOPER, (uint32_t __user *)buffer))
+			return -EFAULT;
+		binder_stat_br(proc, thread, BR_SPAWN_LOOPER);
+	}
+	return 0;
+}
+
+static void binder_release_work(struct list_head *list)
+{
+	struct binder_work *w;
+
+	while (!list_empty(list)) {
+		w = list_first_entry(list, struct binder_work, entry);
+		list_del_init(&w->entry);
+		switch (w->type) {
+		case BINDER_WORK_TRANSACTION: {
+			struct binder_transaction *t;
+
+			t = container_of(w, struct binder_transaction, work);
+			if (t->buffer->target_node &&
+			    !(t->flags & TF_ONE_WAY)) {
+				binder_send_failed_reply(t, BR_DEAD_REPLY);
+			} else {
+				binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
+					"undelivered transaction %d\n",
+					t->debug_id);
+				t->buffer->transaction = NULL;
+				kfree(t);
+				binder_stats_deleted(BINDER_STAT_TRANSACTION);
+			}
+		} break;
+		case BINDER_WORK_TRANSACTION_COMPLETE: {
+			binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
+				"undelivered TRANSACTION_COMPLETE\n");
+			kfree(w);
+			binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE);
+		} break;
+		case BINDER_WORK_DEAD_BINDER_AND_CLEAR:
+		case BINDER_WORK_CLEAR_DEATH_NOTIFICATION: {
+			struct binder_ref_death *death;
+
+			death = container_of(w, struct binder_ref_death, work);
+			binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
+				"undelivered death notification, %016llx\n",
+				(u64)death->cookie);
+			kfree(death);
+			binder_stats_deleted(BINDER_STAT_DEATH);
+		} break;
+		default:
+			pr_err("unexpected work type, %d, not freed\n",
+			       w->type);
+			break;
+		}
+	}
+
+}
+
+static struct binder_thread *binder_get_thread(struct binder_proc *proc)
+{
+	struct binder_thread *thread = NULL;
+	struct rb_node *parent = NULL;
+	struct rb_node **p = &proc->threads.rb_node;
+
+	while (*p) {
+		parent = *p;
+		thread = rb_entry(parent, struct binder_thread, rb_node);
+
+		if (current->pid < thread->pid)
+			p = &(*p)->rb_left;
+		else if (current->pid > thread->pid)
+			p = &(*p)->rb_right;
+		else
+			break;
+	}
+	if (*p == NULL) {
+		thread = kzalloc(sizeof(*thread), GFP_KERNEL);
+		if (thread == NULL)
+			return NULL;
+		binder_stats_created(BINDER_STAT_THREAD);
+		thread->proc = proc;
+		thread->pid = current->pid;
+		init_waitqueue_head(&thread->wait);
+		INIT_LIST_HEAD(&thread->todo);
+		rb_link_node(&thread->rb_node, parent, p);
+		rb_insert_color(&thread->rb_node, &proc->threads);
+		thread->looper |= BINDER_LOOPER_STATE_NEED_RETURN;
+		thread->return_error = BR_OK;
+		thread->return_error2 = BR_OK;
+	}
+	return thread;
+}
+
+static int binder_free_thread(struct binder_proc *proc,
+			      struct binder_thread *thread)
+{
+	struct binder_transaction *t;
+	struct binder_transaction *send_reply = NULL;
+	int active_transactions = 0;
+
+	rb_erase(&thread->rb_node, &proc->threads);
+	t = thread->transaction_stack;
+	if (t && t->to_thread == thread)
+		send_reply = t;
+	while (t) {
+		active_transactions++;
+		binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
+			     "release %d:%d transaction %d %s, still active\n",
+			      proc->pid, thread->pid,
+			     t->debug_id,
+			     (t->to_thread == thread) ? "in" : "out");
+
+		if (t->to_thread == thread) {
+			t->to_proc = NULL;
+			t->to_thread = NULL;
+			if (t->buffer) {
+				t->buffer->transaction = NULL;
+				t->buffer = NULL;
+			}
+			t = t->to_parent;
+		} else if (t->from == thread) {
+			t->from = NULL;
+			t = t->from_parent;
+		} else
+			BUG();
+	}
+	if (send_reply)
+		binder_send_failed_reply(send_reply, BR_DEAD_REPLY);
+	binder_release_work(&thread->todo);
+	kfree(thread);
+	binder_stats_deleted(BINDER_STAT_THREAD);
+	return active_transactions;
+}
+
+static unsigned int binder_poll(struct file *filp,
+				struct poll_table_struct *wait)
+{
+	struct binder_proc *proc = filp->private_data;
+	struct binder_thread *thread = NULL;
+	int wait_for_proc_work;
+
+	binder_lock(__func__);
+
+	thread = binder_get_thread(proc);
+
+	wait_for_proc_work = thread->transaction_stack == NULL &&
+		list_empty(&thread->todo) && thread->return_error == BR_OK;
+
+	binder_unlock(__func__);
+
+	if (wait_for_proc_work) {
+		if (binder_has_proc_work(proc, thread))
+			return POLLIN;
+		poll_wait(filp, &proc->wait, wait);
+		if (binder_has_proc_work(proc, thread))
+			return POLLIN;
+	} else {
+		if (binder_has_thread_work(thread))
+			return POLLIN;
+		poll_wait(filp, &thread->wait, wait);
+		if (binder_has_thread_work(thread))
+			return POLLIN;
+	}
+	return 0;
+}
+
+static int binder_ioctl_write_read(struct file *filp,
+				unsigned int cmd, unsigned long arg,
+				struct binder_thread *thread)
+{
+	int ret = 0;
+	struct binder_proc *proc = filp->private_data;
+	unsigned int size = _IOC_SIZE(cmd);
+	void __user *ubuf = (void __user *)arg;
+	struct binder_write_read bwr;
+
+	if (size != sizeof(struct binder_write_read)) {
+		ret = -EINVAL;
+		goto out;
+	}
+	if (copy_from_user(&bwr, ubuf, sizeof(bwr))) {
+		ret = -EFAULT;
+		goto out;
+	}
+	binder_debug(BINDER_DEBUG_READ_WRITE,
+		     "%d:%d write %lld at %016llx, read %lld at %016llx\n",
+		     proc->pid, thread->pid,
+		     (u64)bwr.write_size, (u64)bwr.write_buffer,
+		     (u64)bwr.read_size, (u64)bwr.read_buffer);
+
+	if (bwr.write_size > 0) {
+		ret = binder_thread_write(proc, thread,
+					  bwr.write_buffer,
+					  bwr.write_size,
+					  &bwr.write_consumed);
+		trace_binder_write_done(ret);
+		if (ret < 0) {
+			bwr.read_consumed = 0;
+			if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
+				ret = -EFAULT;
+			goto out;
+		}
+	}
+	if (bwr.read_size > 0) {
+		ret = binder_thread_read(proc, thread, bwr.read_buffer,
+					 bwr.read_size,
+					 &bwr.read_consumed,
+					 filp->f_flags & O_NONBLOCK);
+		trace_binder_read_done(ret);
+		if (!list_empty(&proc->todo))
+			wake_up_interruptible(&proc->wait);
+		if (ret < 0) {
+			if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
+				ret = -EFAULT;
+			goto out;
+		}
+	}
+	binder_debug(BINDER_DEBUG_READ_WRITE,
+		     "%d:%d wrote %lld of %lld, read return %lld of %lld\n",
+		     proc->pid, thread->pid,
+		     (u64)bwr.write_consumed, (u64)bwr.write_size,
+		     (u64)bwr.read_consumed, (u64)bwr.read_size);
+	if (copy_to_user(ubuf, &bwr, sizeof(bwr))) {
+		ret = -EFAULT;
+		goto out;
+	}
+out:
+	return ret;
+}
+
+static int binder_ioctl_set_ctx_mgr(struct file *filp)
+{
+	int ret = 0;
+	struct binder_proc *proc = filp->private_data;
+	kuid_t curr_euid = current_euid();
+
+	if (binder_context_mgr_node != NULL) {
+		pr_err("BINDER_SET_CONTEXT_MGR already set\n");
+		ret = -EBUSY;
+		goto out;
+	}
+	if (uid_valid(binder_context_mgr_uid)) {
+		if (!uid_eq(binder_context_mgr_uid, curr_euid)) {
+			pr_err("BINDER_SET_CONTEXT_MGR bad uid %d != %d\n",
+			       from_kuid(&init_user_ns, curr_euid),
+			       from_kuid(&init_user_ns,
+					binder_context_mgr_uid));
+			ret = -EPERM;
+			goto out;
+		}
+	} else {
+		binder_context_mgr_uid = curr_euid;
+	}
+	binder_context_mgr_node = binder_new_node(proc, 0, 0);
+	if (binder_context_mgr_node == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	binder_context_mgr_node->local_weak_refs++;
+	binder_context_mgr_node->local_strong_refs++;
+	binder_context_mgr_node->has_strong_ref = 1;
+	binder_context_mgr_node->has_weak_ref = 1;
+out:
+	return ret;
+}
+
+static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	int ret;
+	struct binder_proc *proc = filp->private_data;
+	struct binder_thread *thread;
+	unsigned int size = _IOC_SIZE(cmd);
+	void __user *ubuf = (void __user *)arg;
+
+	/*pr_info("binder_ioctl: %d:%d %x %lx\n",
+			proc->pid, current->pid, cmd, arg);*/
+
+	trace_binder_ioctl(cmd, arg);
+
+	ret = wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
+	if (ret)
+		goto err_unlocked;
+
+	binder_lock(__func__);
+	thread = binder_get_thread(proc);
+	if (thread == NULL) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	switch (cmd) {
+	case BINDER_WRITE_READ:
+		ret = binder_ioctl_write_read(filp, cmd, arg, thread);
+		if (ret)
+			goto err;
+		break;
+	case BINDER_SET_MAX_THREADS:
+		if (copy_from_user(&proc->max_threads, ubuf, sizeof(proc->max_threads))) {
+			ret = -EINVAL;
+			goto err;
+		}
+		break;
+	case BINDER_SET_CONTEXT_MGR:
+		ret = binder_ioctl_set_ctx_mgr(filp);
+		if (ret)
+			goto err;
+		break;
+	case BINDER_THREAD_EXIT:
+		binder_debug(BINDER_DEBUG_THREADS, "%d:%d exit\n",
+			     proc->pid, thread->pid);
+		binder_free_thread(proc, thread);
+		thread = NULL;
+		break;
+	case BINDER_VERSION: {
+		struct binder_version __user *ver = ubuf;
+
+		if (size != sizeof(struct binder_version)) {
+			ret = -EINVAL;
+			goto err;
+		}
+		if (put_user(BINDER_CURRENT_PROTOCOL_VERSION,
+			     &ver->protocol_version)) {
+			ret = -EINVAL;
+			goto err;
+		}
+		break;
+	}
+	default:
+		ret = -EINVAL;
+		goto err;
+	}
+	ret = 0;
+err:
+	if (thread)
+		thread->looper &= ~BINDER_LOOPER_STATE_NEED_RETURN;
+	binder_unlock(__func__);
+	wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
+	if (ret && ret != -ERESTARTSYS)
+		pr_info("%d:%d ioctl %x %lx returned %d\n", proc->pid, current->pid, cmd, arg, ret);
+err_unlocked:
+	trace_binder_ioctl_done(ret);
+	return ret;
+}
+
+static void binder_vma_open(struct vm_area_struct *vma)
+{
+	struct binder_proc *proc = vma->vm_private_data;
+
+	binder_debug(BINDER_DEBUG_OPEN_CLOSE,
+		     "%d open vm area %lx-%lx (%ld K) vma %lx pagep %lx\n",
+		     proc->pid, vma->vm_start, vma->vm_end,
+		     (vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags,
+		     (unsigned long)pgprot_val(vma->vm_page_prot));
+}
+
+static void binder_vma_close(struct vm_area_struct *vma)
+{
+	struct binder_proc *proc = vma->vm_private_data;
+
+	binder_debug(BINDER_DEBUG_OPEN_CLOSE,
+		     "%d close vm area %lx-%lx (%ld K) vma %lx pagep %lx\n",
+		     proc->pid, vma->vm_start, vma->vm_end,
+		     (vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags,
+		     (unsigned long)pgprot_val(vma->vm_page_prot));
+	proc->vma = NULL;
+	proc->vma_vm_mm = NULL;
+	binder_defer_work(proc, BINDER_DEFERRED_PUT_FILES);
+}
+
+static int binder_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return VM_FAULT_SIGBUS;
+}
+
+static struct vm_operations_struct binder_vm_ops = {
+	.open = binder_vma_open,
+	.close = binder_vma_close,
+	.fault = binder_vm_fault,
+};
+
+static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	int ret;
+	struct vm_struct *area;
+	struct binder_proc *proc = filp->private_data;
+	const char *failure_string;
+	struct binder_buffer *buffer;
+
+	if (proc->tsk != current)
+		return -EINVAL;
+
+	if ((vma->vm_end - vma->vm_start) > SZ_4M)
+		vma->vm_end = vma->vm_start + SZ_4M;
+
+	binder_debug(BINDER_DEBUG_OPEN_CLOSE,
+		     "binder_mmap: %d %lx-%lx (%ld K) vma %lx pagep %lx\n",
+		     proc->pid, vma->vm_start, vma->vm_end,
+		     (vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags,
+		     (unsigned long)pgprot_val(vma->vm_page_prot));
+
+	if (vma->vm_flags & FORBIDDEN_MMAP_FLAGS) {
+		ret = -EPERM;
+		failure_string = "bad vm_flags";
+		goto err_bad_arg;
+	}
+	vma->vm_flags = (vma->vm_flags | VM_DONTCOPY) & ~VM_MAYWRITE;
+
+	mutex_lock(&binder_mmap_lock);
+	if (proc->buffer) {
+		ret = -EBUSY;
+		failure_string = "already mapped";
+		goto err_already_mapped;
+	}
+
+	area = get_vm_area(vma->vm_end - vma->vm_start, VM_IOREMAP);
+	if (area == NULL) {
+		ret = -ENOMEM;
+		failure_string = "get_vm_area";
+		goto err_get_vm_area_failed;
+	}
+	proc->buffer = area->addr;
+	proc->user_buffer_offset = vma->vm_start - (uintptr_t)proc->buffer;
+	mutex_unlock(&binder_mmap_lock);
+
+#ifdef CONFIG_CPU_CACHE_VIPT
+	if (cache_is_vipt_aliasing()) {
+		while (CACHE_COLOUR((vma->vm_start ^ (uint32_t)proc->buffer))) {
+			pr_info("binder_mmap: %d %lx-%lx maps %p bad alignment\n", proc->pid, vma->vm_start, vma->vm_end, proc->buffer);
+			vma->vm_start += PAGE_SIZE;
+		}
+	}
+#endif
+	proc->pages = kzalloc(sizeof(proc->pages[0]) * ((vma->vm_end - vma->vm_start) / PAGE_SIZE), GFP_KERNEL);
+	if (proc->pages == NULL) {
+		ret = -ENOMEM;
+		failure_string = "alloc page array";
+		goto err_alloc_pages_failed;
+	}
+	proc->buffer_size = vma->vm_end - vma->vm_start;
+
+	vma->vm_ops = &binder_vm_ops;
+	vma->vm_private_data = proc;
+
+	if (binder_update_page_range(proc, 1, proc->buffer, proc->buffer + PAGE_SIZE, vma)) {
+		ret = -ENOMEM;
+		failure_string = "alloc small buf";
+		goto err_alloc_small_buf_failed;
+	}
+	buffer = proc->buffer;
+	INIT_LIST_HEAD(&proc->buffers);
+	list_add(&buffer->entry, &proc->buffers);
+	buffer->free = 1;
+	binder_insert_free_buffer(proc, buffer);
+	proc->free_async_space = proc->buffer_size / 2;
+	barrier();
+	proc->files = get_files_struct(current);
+	proc->vma = vma;
+	proc->vma_vm_mm = vma->vm_mm;
+
+	/*pr_info("binder_mmap: %d %lx-%lx maps %p\n",
+		 proc->pid, vma->vm_start, vma->vm_end, proc->buffer);*/
+	return 0;
+
+err_alloc_small_buf_failed:
+	kfree(proc->pages);
+	proc->pages = NULL;
+err_alloc_pages_failed:
+	mutex_lock(&binder_mmap_lock);
+	vfree(proc->buffer);
+	proc->buffer = NULL;
+err_get_vm_area_failed:
+err_already_mapped:
+	mutex_unlock(&binder_mmap_lock);
+err_bad_arg:
+	pr_err("binder_mmap: %d %lx-%lx %s failed %d\n",
+	       proc->pid, vma->vm_start, vma->vm_end, failure_string, ret);
+	return ret;
+}
+
+static int binder_open(struct inode *nodp, struct file *filp)
+{
+	struct binder_proc *proc;
+
+	binder_debug(BINDER_DEBUG_OPEN_CLOSE, "binder_open: %d:%d\n",
+		     current->group_leader->pid, current->pid);
+
+	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
+	if (proc == NULL)
+		return -ENOMEM;
+	get_task_struct(current);
+	proc->tsk = current;
+	INIT_LIST_HEAD(&proc->todo);
+	init_waitqueue_head(&proc->wait);
+	proc->default_priority = task_nice(current);
+
+	binder_lock(__func__);
+
+	binder_stats_created(BINDER_STAT_PROC);
+	hlist_add_head(&proc->proc_node, &binder_procs);
+	proc->pid = current->group_leader->pid;
+	INIT_LIST_HEAD(&proc->delivered_death);
+	filp->private_data = proc;
+
+	binder_unlock(__func__);
+
+	if (binder_debugfs_dir_entry_proc) {
+		char strbuf[11];
+
+		snprintf(strbuf, sizeof(strbuf), "%u", proc->pid);
+		proc->debugfs_entry = debugfs_create_file(strbuf, S_IRUGO,
+			binder_debugfs_dir_entry_proc, proc, &binder_proc_fops);
+	}
+
+	return 0;
+}
+
+static int binder_flush(struct file *filp, fl_owner_t id)
+{
+	struct binder_proc *proc = filp->private_data;
+
+	binder_defer_work(proc, BINDER_DEFERRED_FLUSH);
+
+	return 0;
+}
+
+static void binder_deferred_flush(struct binder_proc *proc)
+{
+	struct rb_node *n;
+	int wake_count = 0;
+
+	for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n)) {
+		struct binder_thread *thread = rb_entry(n, struct binder_thread, rb_node);
+
+		thread->looper |= BINDER_LOOPER_STATE_NEED_RETURN;
+		if (thread->looper & BINDER_LOOPER_STATE_WAITING) {
+			wake_up_interruptible(&thread->wait);
+			wake_count++;
+		}
+	}
+	wake_up_interruptible_all(&proc->wait);
+
+	binder_debug(BINDER_DEBUG_OPEN_CLOSE,
+		     "binder_flush: %d woke %d threads\n", proc->pid,
+		     wake_count);
+}
+
+static int binder_release(struct inode *nodp, struct file *filp)
+{
+	struct binder_proc *proc = filp->private_data;
+
+	debugfs_remove(proc->debugfs_entry);
+	binder_defer_work(proc, BINDER_DEFERRED_RELEASE);
+
+	return 0;
+}
+
+static int binder_node_release(struct binder_node *node, int refs)
+{
+	struct binder_ref *ref;
+	int death = 0;
+
+	list_del_init(&node->work.entry);
+	binder_release_work(&node->async_todo);
+
+	if (hlist_empty(&node->refs)) {
+		kfree(node);
+		binder_stats_deleted(BINDER_STAT_NODE);
+
+		return refs;
+	}
+
+	node->proc = NULL;
+	node->local_strong_refs = 0;
+	node->local_weak_refs = 0;
+	hlist_add_head(&node->dead_node, &binder_dead_nodes);
+
+	hlist_for_each_entry(ref, &node->refs, node_entry) {
+		refs++;
+
+		if (!ref->death)
+			continue;
+
+		death++;
+
+		if (list_empty(&ref->death->work.entry)) {
+			ref->death->work.type = BINDER_WORK_DEAD_BINDER;
+			list_add_tail(&ref->death->work.entry,
+				      &ref->proc->todo);
+			wake_up_interruptible(&ref->proc->wait);
+		} else
+			BUG();
+	}
+
+	binder_debug(BINDER_DEBUG_DEAD_BINDER,
+		     "node %d now dead, refs %d, death %d\n",
+		     node->debug_id, refs, death);
+
+	return refs;
+}
+
+static void binder_deferred_release(struct binder_proc *proc)
+{
+	struct binder_transaction *t;
+	struct rb_node *n;
+	int threads, nodes, incoming_refs, outgoing_refs, buffers,
+		active_transactions, page_count;
+
+	BUG_ON(proc->vma);
+	BUG_ON(proc->files);
+
+	hlist_del(&proc->proc_node);
+
+	if (binder_context_mgr_node && binder_context_mgr_node->proc == proc) {
+		binder_debug(BINDER_DEBUG_DEAD_BINDER,
+			     "%s: %d context_mgr_node gone\n",
+			     __func__, proc->pid);
+		binder_context_mgr_node = NULL;
+	}
+
+	threads = 0;
+	active_transactions = 0;
+	while ((n = rb_first(&proc->threads))) {
+		struct binder_thread *thread;
+
+		thread = rb_entry(n, struct binder_thread, rb_node);
+		threads++;
+		active_transactions += binder_free_thread(proc, thread);
+	}
+
+	nodes = 0;
+	incoming_refs = 0;
+	while ((n = rb_first(&proc->nodes))) {
+		struct binder_node *node;
+
+		node = rb_entry(n, struct binder_node, rb_node);
+		nodes++;
+		rb_erase(&node->rb_node, &proc->nodes);
+		incoming_refs = binder_node_release(node, incoming_refs);
+	}
+
+	outgoing_refs = 0;
+	while ((n = rb_first(&proc->refs_by_desc))) {
+		struct binder_ref *ref;
+
+		ref = rb_entry(n, struct binder_ref, rb_node_desc);
+		outgoing_refs++;
+		binder_delete_ref(ref);
+	}
+
+	binder_release_work(&proc->todo);
+	binder_release_work(&proc->delivered_death);
+
+	buffers = 0;
+	while ((n = rb_first(&proc->allocated_buffers))) {
+		struct binder_buffer *buffer;
+
+		buffer = rb_entry(n, struct binder_buffer, rb_node);
+
+		t = buffer->transaction;
+		if (t) {
+			t->buffer = NULL;
+			buffer->transaction = NULL;
+			pr_err("release proc %d, transaction %d, not freed\n",
+			       proc->pid, t->debug_id);
+			/*BUG();*/
+		}
+
+		binder_free_buf(proc, buffer);
+		buffers++;
+	}
+
+	binder_stats_deleted(BINDER_STAT_PROC);
+
+	page_count = 0;
+	if (proc->pages) {
+		int i;
+
+		for (i = 0; i < proc->buffer_size / PAGE_SIZE; i++) {
+			void *page_addr;
+
+			if (!proc->pages[i])
+				continue;
+
+			page_addr = proc->buffer + i * PAGE_SIZE;
+			binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
+				     "%s: %d: page %d at %p not freed\n",
+				     __func__, proc->pid, i, page_addr);
+			unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
+			__free_page(proc->pages[i]);
+			page_count++;
+		}
+		kfree(proc->pages);
+		vfree(proc->buffer);
+	}
+
+	put_task_struct(proc->tsk);
+
+	binder_debug(BINDER_DEBUG_OPEN_CLOSE,
+		     "%s: %d threads %d, nodes %d (ref %d), refs %d, active transactions %d, buffers %d, pages %d\n",
+		     __func__, proc->pid, threads, nodes, incoming_refs,
+		     outgoing_refs, active_transactions, buffers, page_count);
+
+	kfree(proc);
+}
+
+static void binder_deferred_func(struct work_struct *work)
+{
+	struct binder_proc *proc;
+	struct files_struct *files;
+
+	int defer;
+
+	do {
+		binder_lock(__func__);
+		mutex_lock(&binder_deferred_lock);
+		if (!hlist_empty(&binder_deferred_list)) {
+			proc = hlist_entry(binder_deferred_list.first,
+					struct binder_proc, deferred_work_node);
+			hlist_del_init(&proc->deferred_work_node);
+			defer = proc->deferred_work;
+			proc->deferred_work = 0;
+		} else {
+			proc = NULL;
+			defer = 0;
+		}
+		mutex_unlock(&binder_deferred_lock);
+
+		files = NULL;
+		if (defer & BINDER_DEFERRED_PUT_FILES) {
+			files = proc->files;
+			if (files)
+				proc->files = NULL;
+		}
+
+		if (defer & BINDER_DEFERRED_FLUSH)
+			binder_deferred_flush(proc);
+
+		if (defer & BINDER_DEFERRED_RELEASE)
+			binder_deferred_release(proc); /* frees proc */
+
+		binder_unlock(__func__);
+		if (files)
+			put_files_struct(files);
+	} while (proc);
+}
+static DECLARE_WORK(binder_deferred_work, binder_deferred_func);
+
+static void
+binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer)
+{
+	mutex_lock(&binder_deferred_lock);
+	proc->deferred_work |= defer;
+	if (hlist_unhashed(&proc->deferred_work_node)) {
+		hlist_add_head(&proc->deferred_work_node,
+				&binder_deferred_list);
+		queue_work(binder_deferred_workqueue, &binder_deferred_work);
+	}
+	mutex_unlock(&binder_deferred_lock);
+}
+
+static void print_binder_transaction(struct seq_file *m, const char *prefix,
+				     struct binder_transaction *t)
+{
+	seq_printf(m,
+		   "%s %d: %p from %d:%d to %d:%d code %x flags %x pri %ld r%d",
+		   prefix, t->debug_id, t,
+		   t->from ? t->from->proc->pid : 0,
+		   t->from ? t->from->pid : 0,
+		   t->to_proc ? t->to_proc->pid : 0,
+		   t->to_thread ? t->to_thread->pid : 0,
+		   t->code, t->flags, t->priority, t->need_reply);
+	if (t->buffer == NULL) {
+		seq_puts(m, " buffer free\n");
+		return;
+	}
+	if (t->buffer->target_node)
+		seq_printf(m, " node %d",
+			   t->buffer->target_node->debug_id);
+	seq_printf(m, " size %zd:%zd data %p\n",
+		   t->buffer->data_size, t->buffer->offsets_size,
+		   t->buffer->data);
+}
+
+static void print_binder_buffer(struct seq_file *m, const char *prefix,
+				struct binder_buffer *buffer)
+{
+	seq_printf(m, "%s %d: %p size %zd:%zd %s\n",
+		   prefix, buffer->debug_id, buffer->data,
+		   buffer->data_size, buffer->offsets_size,
+		   buffer->transaction ? "active" : "delivered");
+}
+
+static void print_binder_work(struct seq_file *m, const char *prefix,
+			      const char *transaction_prefix,
+			      struct binder_work *w)
+{
+	struct binder_node *node;
+	struct binder_transaction *t;
+
+	switch (w->type) {
+	case BINDER_WORK_TRANSACTION:
+		t = container_of(w, struct binder_transaction, work);
+		print_binder_transaction(m, transaction_prefix, t);
+		break;
+	case BINDER_WORK_TRANSACTION_COMPLETE:
+		seq_printf(m, "%stransaction complete\n", prefix);
+		break;
+	case BINDER_WORK_NODE:
+		node = container_of(w, struct binder_node, work);
+		seq_printf(m, "%snode work %d: u%016llx c%016llx\n",
+			   prefix, node->debug_id,
+			   (u64)node->ptr, (u64)node->cookie);
+		break;
+	case BINDER_WORK_DEAD_BINDER:
+		seq_printf(m, "%shas dead binder\n", prefix);
+		break;
+	case BINDER_WORK_DEAD_BINDER_AND_CLEAR:
+		seq_printf(m, "%shas cleared dead binder\n", prefix);
+		break;
+	case BINDER_WORK_CLEAR_DEATH_NOTIFICATION:
+		seq_printf(m, "%shas cleared death notification\n", prefix);
+		break;
+	default:
+		seq_printf(m, "%sunknown work: type %d\n", prefix, w->type);
+		break;
+	}
+}
+
+static void print_binder_thread(struct seq_file *m,
+				struct binder_thread *thread,
+				int print_always)
+{
+	struct binder_transaction *t;
+	struct binder_work *w;
+	size_t start_pos = m->count;
+	size_t header_pos;
+
+	seq_printf(m, "  thread %d: l %02x\n", thread->pid, thread->looper);
+	header_pos = m->count;
+	t = thread->transaction_stack;
+	while (t) {
+		if (t->from == thread) {
+			print_binder_transaction(m,
+						 "    outgoing transaction", t);
+			t = t->from_parent;
+		} else if (t->to_thread == thread) {
+			print_binder_transaction(m,
+						 "    incoming transaction", t);
+			t = t->to_parent;
+		} else {
+			print_binder_transaction(m, "    bad transaction", t);
+			t = NULL;
+		}
+	}
+	list_for_each_entry(w, &thread->todo, entry) {
+		print_binder_work(m, "    ", "    pending transaction", w);
+	}
+	if (!print_always && m->count == header_pos)
+		m->count = start_pos;
+}
+
+static void print_binder_node(struct seq_file *m, struct binder_node *node)
+{
+	struct binder_ref *ref;
+	struct binder_work *w;
+	int count;
+
+	count = 0;
+	hlist_for_each_entry(ref, &node->refs, node_entry)
+		count++;
+
+	seq_printf(m, "  node %d: u%016llx c%016llx hs %d hw %d ls %d lw %d is %d iw %d",
+		   node->debug_id, (u64)node->ptr, (u64)node->cookie,
+		   node->has_strong_ref, node->has_weak_ref,
+		   node->local_strong_refs, node->local_weak_refs,
+		   node->internal_strong_refs, count);
+	if (count) {
+		seq_puts(m, " proc");
+		hlist_for_each_entry(ref, &node->refs, node_entry)
+			seq_printf(m, " %d", ref->proc->pid);
+	}
+	seq_puts(m, "\n");
+	list_for_each_entry(w, &node->async_todo, entry)
+		print_binder_work(m, "    ",
+				  "    pending async transaction", w);
+}
+
+static void print_binder_ref(struct seq_file *m, struct binder_ref *ref)
+{
+	seq_printf(m, "  ref %d: desc %d %snode %d s %d w %d d %p\n",
+		   ref->debug_id, ref->desc, ref->node->proc ? "" : "dead ",
+		   ref->node->debug_id, ref->strong, ref->weak, ref->death);
+}
+
+static void print_binder_proc(struct seq_file *m,
+			      struct binder_proc *proc, int print_all)
+{
+	struct binder_work *w;
+	struct rb_node *n;
+	size_t start_pos = m->count;
+	size_t header_pos;
+
+	seq_printf(m, "proc %d\n", proc->pid);
+	header_pos = m->count;
+
+	for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n))
+		print_binder_thread(m, rb_entry(n, struct binder_thread,
+						rb_node), print_all);
+	for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n)) {
+		struct binder_node *node = rb_entry(n, struct binder_node,
+						    rb_node);
+		if (print_all || node->has_async_transaction)
+			print_binder_node(m, node);
+	}
+	if (print_all) {
+		for (n = rb_first(&proc->refs_by_desc);
+		     n != NULL;
+		     n = rb_next(n))
+			print_binder_ref(m, rb_entry(n, struct binder_ref,
+						     rb_node_desc));
+	}
+	for (n = rb_first(&proc->allocated_buffers); n != NULL; n = rb_next(n))
+		print_binder_buffer(m, "  buffer",
+				    rb_entry(n, struct binder_buffer, rb_node));
+	list_for_each_entry(w, &proc->todo, entry)
+		print_binder_work(m, "  ", "  pending transaction", w);
+	list_for_each_entry(w, &proc->delivered_death, entry) {
+		seq_puts(m, "  has delivered dead binder\n");
+		break;
+	}
+	if (!print_all && m->count == header_pos)
+		m->count = start_pos;
+}
+
+static const char * const binder_return_strings[] = {
+	"BR_ERROR",
+	"BR_OK",
+	"BR_TRANSACTION",
+	"BR_REPLY",
+	"BR_ACQUIRE_RESULT",
+	"BR_DEAD_REPLY",
+	"BR_TRANSACTION_COMPLETE",
+	"BR_INCREFS",
+	"BR_ACQUIRE",
+	"BR_RELEASE",
+	"BR_DECREFS",
+	"BR_ATTEMPT_ACQUIRE",
+	"BR_NOOP",
+	"BR_SPAWN_LOOPER",
+	"BR_FINISHED",
+	"BR_DEAD_BINDER",
+	"BR_CLEAR_DEATH_NOTIFICATION_DONE",
+	"BR_FAILED_REPLY"
+};
+
+static const char * const binder_command_strings[] = {
+	"BC_TRANSACTION",
+	"BC_REPLY",
+	"BC_ACQUIRE_RESULT",
+	"BC_FREE_BUFFER",
+	"BC_INCREFS",
+	"BC_ACQUIRE",
+	"BC_RELEASE",
+	"BC_DECREFS",
+	"BC_INCREFS_DONE",
+	"BC_ACQUIRE_DONE",
+	"BC_ATTEMPT_ACQUIRE",
+	"BC_REGISTER_LOOPER",
+	"BC_ENTER_LOOPER",
+	"BC_EXIT_LOOPER",
+	"BC_REQUEST_DEATH_NOTIFICATION",
+	"BC_CLEAR_DEATH_NOTIFICATION",
+	"BC_DEAD_BINDER_DONE"
+};
+
+static const char * const binder_objstat_strings[] = {
+	"proc",
+	"thread",
+	"node",
+	"ref",
+	"death",
+	"transaction",
+	"transaction_complete"
+};
+
+static void print_binder_stats(struct seq_file *m, const char *prefix,
+			       struct binder_stats *stats)
+{
+	int i;
+
+	BUILD_BUG_ON(ARRAY_SIZE(stats->bc) !=
+		     ARRAY_SIZE(binder_command_strings));
+	for (i = 0; i < ARRAY_SIZE(stats->bc); i++) {
+		if (stats->bc[i])
+			seq_printf(m, "%s%s: %d\n", prefix,
+				   binder_command_strings[i], stats->bc[i]);
+	}
+
+	BUILD_BUG_ON(ARRAY_SIZE(stats->br) !=
+		     ARRAY_SIZE(binder_return_strings));
+	for (i = 0; i < ARRAY_SIZE(stats->br); i++) {
+		if (stats->br[i])
+			seq_printf(m, "%s%s: %d\n", prefix,
+				   binder_return_strings[i], stats->br[i]);
+	}
+
+	BUILD_BUG_ON(ARRAY_SIZE(stats->obj_created) !=
+		     ARRAY_SIZE(binder_objstat_strings));
+	BUILD_BUG_ON(ARRAY_SIZE(stats->obj_created) !=
+		     ARRAY_SIZE(stats->obj_deleted));
+	for (i = 0; i < ARRAY_SIZE(stats->obj_created); i++) {
+		if (stats->obj_created[i] || stats->obj_deleted[i])
+			seq_printf(m, "%s%s: active %d total %d\n", prefix,
+				binder_objstat_strings[i],
+				stats->obj_created[i] - stats->obj_deleted[i],
+				stats->obj_created[i]);
+	}
+}
+
+static void print_binder_proc_stats(struct seq_file *m,
+				    struct binder_proc *proc)
+{
+	struct binder_work *w;
+	struct rb_node *n;
+	int count, strong, weak;
+
+	seq_printf(m, "proc %d\n", proc->pid);
+	count = 0;
+	for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n))
+		count++;
+	seq_printf(m, "  threads: %d\n", count);
+	seq_printf(m, "  requested threads: %d+%d/%d\n"
+			"  ready threads %d\n"
+			"  free async space %zd\n", proc->requested_threads,
+			proc->requested_threads_started, proc->max_threads,
+			proc->ready_threads, proc->free_async_space);
+	count = 0;
+	for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n))
+		count++;
+	seq_printf(m, "  nodes: %d\n", count);
+	count = 0;
+	strong = 0;
+	weak = 0;
+	for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) {
+		struct binder_ref *ref = rb_entry(n, struct binder_ref,
+						  rb_node_desc);
+		count++;
+		strong += ref->strong;
+		weak += ref->weak;
+	}
+	seq_printf(m, "  refs: %d s %d w %d\n", count, strong, weak);
+
+	count = 0;
+	for (n = rb_first(&proc->allocated_buffers); n != NULL; n = rb_next(n))
+		count++;
+	seq_printf(m, "  buffers: %d\n", count);
+
+	count = 0;
+	list_for_each_entry(w, &proc->todo, entry) {
+		switch (w->type) {
+		case BINDER_WORK_TRANSACTION:
+			count++;
+			break;
+		default:
+			break;
+		}
+	}
+	seq_printf(m, "  pending transactions: %d\n", count);
+
+	print_binder_stats(m, "  ", &proc->stats);
+}
+
+
+static int binder_state_show(struct seq_file *m, void *unused)
+{
+	struct binder_proc *proc;
+	struct binder_node *node;
+	int do_lock = !binder_debug_no_lock;
+
+	if (do_lock)
+		binder_lock(__func__);
+
+	seq_puts(m, "binder state:\n");
+
+	if (!hlist_empty(&binder_dead_nodes))
+		seq_puts(m, "dead nodes:\n");
+	hlist_for_each_entry(node, &binder_dead_nodes, dead_node)
+		print_binder_node(m, node);
+
+	hlist_for_each_entry(proc, &binder_procs, proc_node)
+		print_binder_proc(m, proc, 1);
+	if (do_lock)
+		binder_unlock(__func__);
+	return 0;
+}
+
+static int binder_stats_show(struct seq_file *m, void *unused)
+{
+	struct binder_proc *proc;
+	int do_lock = !binder_debug_no_lock;
+
+	if (do_lock)
+		binder_lock(__func__);
+
+	seq_puts(m, "binder stats:\n");
+
+	print_binder_stats(m, "", &binder_stats);
+
+	hlist_for_each_entry(proc, &binder_procs, proc_node)
+		print_binder_proc_stats(m, proc);
+	if (do_lock)
+		binder_unlock(__func__);
+	return 0;
+}
+
+static int binder_transactions_show(struct seq_file *m, void *unused)
+{
+	struct binder_proc *proc;
+	int do_lock = !binder_debug_no_lock;
+
+	if (do_lock)
+		binder_lock(__func__);
+
+	seq_puts(m, "binder transactions:\n");
+	hlist_for_each_entry(proc, &binder_procs, proc_node)
+		print_binder_proc(m, proc, 0);
+	if (do_lock)
+		binder_unlock(__func__);
+	return 0;
+}
+
+static int binder_proc_show(struct seq_file *m, void *unused)
+{
+	struct binder_proc *proc = m->private;
+	int do_lock = !binder_debug_no_lock;
+
+	if (do_lock)
+		binder_lock(__func__);
+	seq_puts(m, "binder proc state:\n");
+	print_binder_proc(m, proc, 1);
+	if (do_lock)
+		binder_unlock(__func__);
+	return 0;
+}
+
+static void print_binder_transaction_log_entry(struct seq_file *m,
+					struct binder_transaction_log_entry *e)
+{
+	seq_printf(m,
+		   "%d: %s from %d:%d to %d:%d node %d handle %d size %d:%d\n",
+		   e->debug_id, (e->call_type == 2) ? "reply" :
+		   ((e->call_type == 1) ? "async" : "call "), e->from_proc,
+		   e->from_thread, e->to_proc, e->to_thread, e->to_node,
+		   e->target_handle, e->data_size, e->offsets_size);
+}
+
+static int binder_transaction_log_show(struct seq_file *m, void *unused)
+{
+	struct binder_transaction_log *log = m->private;
+	int i;
+
+	if (log->full) {
+		for (i = log->next; i < ARRAY_SIZE(log->entry); i++)
+			print_binder_transaction_log_entry(m, &log->entry[i]);
+	}
+	for (i = 0; i < log->next; i++)
+		print_binder_transaction_log_entry(m, &log->entry[i]);
+	return 0;
+}
+
+static const struct file_operations binder_fops = {
+	.owner = THIS_MODULE,
+	.poll = binder_poll,
+	.unlocked_ioctl = binder_ioctl,
+	.compat_ioctl = binder_ioctl,
+	.mmap = binder_mmap,
+	.open = binder_open,
+	.flush = binder_flush,
+	.release = binder_release,
+};
+
+static struct miscdevice binder_miscdev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "binder",
+	.fops = &binder_fops
+};
+
+BINDER_DEBUG_ENTRY(state);
+BINDER_DEBUG_ENTRY(stats);
+BINDER_DEBUG_ENTRY(transactions);
+BINDER_DEBUG_ENTRY(transaction_log);
+
+static int __init binder_init(void)
+{
+	int ret;
+
+	binder_deferred_workqueue = create_singlethread_workqueue("binder");
+	if (!binder_deferred_workqueue)
+		return -ENOMEM;
+
+	binder_debugfs_dir_entry_root = debugfs_create_dir("binder", NULL);
+	if (binder_debugfs_dir_entry_root)
+		binder_debugfs_dir_entry_proc = debugfs_create_dir("proc",
+						 binder_debugfs_dir_entry_root);
+	ret = misc_register(&binder_miscdev);
+	if (binder_debugfs_dir_entry_root) {
+		debugfs_create_file("state",
+				    S_IRUGO,
+				    binder_debugfs_dir_entry_root,
+				    NULL,
+				    &binder_state_fops);
+		debugfs_create_file("stats",
+				    S_IRUGO,
+				    binder_debugfs_dir_entry_root,
+				    NULL,
+				    &binder_stats_fops);
+		debugfs_create_file("transactions",
+				    S_IRUGO,
+				    binder_debugfs_dir_entry_root,
+				    NULL,
+				    &binder_transactions_fops);
+		debugfs_create_file("transaction_log",
+				    S_IRUGO,
+				    binder_debugfs_dir_entry_root,
+				    &binder_transaction_log,
+				    &binder_transaction_log_fops);
+		debugfs_create_file("failed_transaction_log",
+				    S_IRUGO,
+				    binder_debugfs_dir_entry_root,
+				    &binder_transaction_log_failed,
+				    &binder_transaction_log_fops);
+	}
+	return ret;
+}
+
+device_initcall(binder_init);
+
+#define CREATE_TRACE_POINTS
+#include "binder_trace.h"
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/android/binder.h b/drivers/android/binder.h
new file mode 100644
index 00000000000..5dc6a66b066
--- /dev/null
+++ b/drivers/android/binder.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * Based on, but no longer compatible with, the original
+ * OpenBinder.org binder driver interface, which is:
+ *
+ * Copyright (c) 2005 Palmsource, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_BINDER_H
+#define _LINUX_BINDER_H
+
+#ifdef CONFIG_ANDROID_BINDER_IPC_32BIT
+#define BINDER_IPC_32BIT 1
+#endif
+
+#include <uapi/linux/android/binder.h>
+
+#endif /* _LINUX_BINDER_H */
+
diff --git a/drivers/android/binder_trace.h b/drivers/android/binder_trace.h
new file mode 100644
index 00000000000..7f20f3dc836
--- /dev/null
+++ b/drivers/android/binder_trace.h
@@ -0,0 +1,329 @@
+/*
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM binder
+
+#if !defined(_BINDER_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _BINDER_TRACE_H
+
+#include <linux/tracepoint.h>
+
+struct binder_buffer;
+struct binder_node;
+struct binder_proc;
+struct binder_ref;
+struct binder_thread;
+struct binder_transaction;
+
+TRACE_EVENT(binder_ioctl,
+	TP_PROTO(unsigned int cmd, unsigned long arg),
+	TP_ARGS(cmd, arg),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, cmd)
+		__field(unsigned long, arg)
+	),
+	TP_fast_assign(
+		__entry->cmd = cmd;
+		__entry->arg = arg;
+	),
+	TP_printk("cmd=0x%x arg=0x%lx", __entry->cmd, __entry->arg)
+);
+
+DECLARE_EVENT_CLASS(binder_lock_class,
+	TP_PROTO(const char *tag),
+	TP_ARGS(tag),
+	TP_STRUCT__entry(
+		__field(const char *, tag)
+	),
+	TP_fast_assign(
+		__entry->tag = tag;
+	),
+	TP_printk("tag=%s", __entry->tag)
+);
+
+#define DEFINE_BINDER_LOCK_EVENT(name)	\
+DEFINE_EVENT(binder_lock_class, name,	\
+	TP_PROTO(const char *func), \
+	TP_ARGS(func))
+
+DEFINE_BINDER_LOCK_EVENT(binder_lock);
+DEFINE_BINDER_LOCK_EVENT(binder_locked);
+DEFINE_BINDER_LOCK_EVENT(binder_unlock);
+
+DECLARE_EVENT_CLASS(binder_function_return_class,
+	TP_PROTO(int ret),
+	TP_ARGS(ret),
+	TP_STRUCT__entry(
+		__field(int, ret)
+	),
+	TP_fast_assign(
+		__entry->ret = ret;
+	),
+	TP_printk("ret=%d", __entry->ret)
+);
+
+#define DEFINE_BINDER_FUNCTION_RETURN_EVENT(name)	\
+DEFINE_EVENT(binder_function_return_class, name,	\
+	TP_PROTO(int ret), \
+	TP_ARGS(ret))
+
+DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_ioctl_done);
+DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_write_done);
+DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_read_done);
+
+TRACE_EVENT(binder_wait_for_work,
+	TP_PROTO(bool proc_work, bool transaction_stack, bool thread_todo),
+	TP_ARGS(proc_work, transaction_stack, thread_todo),
+
+	TP_STRUCT__entry(
+		__field(bool, proc_work)
+		__field(bool, transaction_stack)
+		__field(bool, thread_todo)
+	),
+	TP_fast_assign(
+		__entry->proc_work = proc_work;
+		__entry->transaction_stack = transaction_stack;
+		__entry->thread_todo = thread_todo;
+	),
+	TP_printk("proc_work=%d transaction_stack=%d thread_todo=%d",
+		  __entry->proc_work, __entry->transaction_stack,
+		  __entry->thread_todo)
+);
+
+TRACE_EVENT(binder_transaction,
+	TP_PROTO(bool reply, struct binder_transaction *t,
+		 struct binder_node *target_node),
+	TP_ARGS(reply, t, target_node),
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+		__field(int, target_node)
+		__field(int, to_proc)
+		__field(int, to_thread)
+		__field(int, reply)
+		__field(unsigned int, code)
+		__field(unsigned int, flags)
+	),
+	TP_fast_assign(
+		__entry->debug_id = t->debug_id;
+		__entry->target_node = target_node ? target_node->debug_id : 0;
+		__entry->to_proc = t->to_proc->pid;
+		__entry->to_thread = t->to_thread ? t->to_thread->pid : 0;
+		__entry->reply = reply;
+		__entry->code = t->code;
+		__entry->flags = t->flags;
+	),
+	TP_printk("transaction=%d dest_node=%d dest_proc=%d dest_thread=%d reply=%d flags=0x%x code=0x%x",
+		  __entry->debug_id, __entry->target_node,
+		  __entry->to_proc, __entry->to_thread,
+		  __entry->reply, __entry->flags, __entry->code)
+);
+
+TRACE_EVENT(binder_transaction_received,
+	TP_PROTO(struct binder_transaction *t),
+	TP_ARGS(t),
+
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+	),
+	TP_fast_assign(
+		__entry->debug_id = t->debug_id;
+	),
+	TP_printk("transaction=%d", __entry->debug_id)
+);
+
+TRACE_EVENT(binder_transaction_node_to_ref,
+	TP_PROTO(struct binder_transaction *t, struct binder_node *node,
+		 struct binder_ref *ref),
+	TP_ARGS(t, node, ref),
+
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+		__field(int, node_debug_id)
+		__field(binder_uintptr_t, node_ptr)
+		__field(int, ref_debug_id)
+		__field(uint32_t, ref_desc)
+	),
+	TP_fast_assign(
+		__entry->debug_id = t->debug_id;
+		__entry->node_debug_id = node->debug_id;
+		__entry->node_ptr = node->ptr;
+		__entry->ref_debug_id = ref->debug_id;
+		__entry->ref_desc = ref->desc;
+	),
+	TP_printk("transaction=%d node=%d src_ptr=0x%016llx ==> dest_ref=%d dest_desc=%d",
+		  __entry->debug_id, __entry->node_debug_id,
+		  (u64)__entry->node_ptr,
+		  __entry->ref_debug_id, __entry->ref_desc)
+);
+
+TRACE_EVENT(binder_transaction_ref_to_node,
+	TP_PROTO(struct binder_transaction *t, struct binder_ref *ref),
+	TP_ARGS(t, ref),
+
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+		__field(int, ref_debug_id)
+		__field(uint32_t, ref_desc)
+		__field(int, node_debug_id)
+		__field(binder_uintptr_t, node_ptr)
+	),
+	TP_fast_assign(
+		__entry->debug_id = t->debug_id;
+		__entry->ref_debug_id = ref->debug_id;
+		__entry->ref_desc = ref->desc;
+		__entry->node_debug_id = ref->node->debug_id;
+		__entry->node_ptr = ref->node->ptr;
+	),
+	TP_printk("transaction=%d node=%d src_ref=%d src_desc=%d ==> dest_ptr=0x%016llx",
+		  __entry->debug_id, __entry->node_debug_id,
+		  __entry->ref_debug_id, __entry->ref_desc,
+		  (u64)__entry->node_ptr)
+);
+
+TRACE_EVENT(binder_transaction_ref_to_ref,
+	TP_PROTO(struct binder_transaction *t, struct binder_ref *src_ref,
+		 struct binder_ref *dest_ref),
+	TP_ARGS(t, src_ref, dest_ref),
+
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+		__field(int, node_debug_id)
+		__field(int, src_ref_debug_id)
+		__field(uint32_t, src_ref_desc)
+		__field(int, dest_ref_debug_id)
+		__field(uint32_t, dest_ref_desc)
+	),
+	TP_fast_assign(
+		__entry->debug_id = t->debug_id;
+		__entry->node_debug_id = src_ref->node->debug_id;
+		__entry->src_ref_debug_id = src_ref->debug_id;
+		__entry->src_ref_desc = src_ref->desc;
+		__entry->dest_ref_debug_id = dest_ref->debug_id;
+		__entry->dest_ref_desc = dest_ref->desc;
+	),
+	TP_printk("transaction=%d node=%d src_ref=%d src_desc=%d ==> dest_ref=%d dest_desc=%d",
+		  __entry->debug_id, __entry->node_debug_id,
+		  __entry->src_ref_debug_id, __entry->src_ref_desc,
+		  __entry->dest_ref_debug_id, __entry->dest_ref_desc)
+);
+
+TRACE_EVENT(binder_transaction_fd,
+	TP_PROTO(struct binder_transaction *t, int src_fd, int dest_fd),
+	TP_ARGS(t, src_fd, dest_fd),
+
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+		__field(int, src_fd)
+		__field(int, dest_fd)
+	),
+	TP_fast_assign(
+		__entry->debug_id = t->debug_id;
+		__entry->src_fd = src_fd;
+		__entry->dest_fd = dest_fd;
+	),
+	TP_printk("transaction=%d src_fd=%d ==> dest_fd=%d",
+		  __entry->debug_id, __entry->src_fd, __entry->dest_fd)
+);
+
+DECLARE_EVENT_CLASS(binder_buffer_class,
+	TP_PROTO(struct binder_buffer *buf),
+	TP_ARGS(buf),
+	TP_STRUCT__entry(
+		__field(int, debug_id)
+		__field(size_t, data_size)
+		__field(size_t, offsets_size)
+	),
+	TP_fast_assign(
+		__entry->debug_id = buf->debug_id;
+		__entry->data_size = buf->data_size;
+		__entry->offsets_size = buf->offsets_size;
+	),
+	TP_printk("transaction=%d data_size=%zd offsets_size=%zd",
+		  __entry->debug_id, __entry->data_size, __entry->offsets_size)
+);
+
+DEFINE_EVENT(binder_buffer_class, binder_transaction_alloc_buf,
+	TP_PROTO(struct binder_buffer *buffer),
+	TP_ARGS(buffer));
+
+DEFINE_EVENT(binder_buffer_class, binder_transaction_buffer_release,
+	TP_PROTO(struct binder_buffer *buffer),
+	TP_ARGS(buffer));
+
+DEFINE_EVENT(binder_buffer_class, binder_transaction_failed_buffer_release,
+	TP_PROTO(struct binder_buffer *buffer),
+	TP_ARGS(buffer));
+
+TRACE_EVENT(binder_update_page_range,
+	TP_PROTO(struct binder_proc *proc, bool allocate,
+		 void *start, void *end),
+	TP_ARGS(proc, allocate, start, end),
+	TP_STRUCT__entry(
+		__field(int, proc)
+		__field(bool, allocate)
+		__field(size_t, offset)
+		__field(size_t, size)
+	),
+	TP_fast_assign(
+		__entry->proc = proc->pid;
+		__entry->allocate = allocate;
+		__entry->offset = start - proc->buffer;
+		__entry->size = end - start;
+	),
+	TP_printk("proc=%d allocate=%d offset=%zu size=%zu",
+		  __entry->proc, __entry->allocate,
+		  __entry->offset, __entry->size)
+);
+
+TRACE_EVENT(binder_command,
+	TP_PROTO(uint32_t cmd),
+	TP_ARGS(cmd),
+	TP_STRUCT__entry(
+		__field(uint32_t, cmd)
+	),
+	TP_fast_assign(
+		__entry->cmd = cmd;
+	),
+	TP_printk("cmd=0x%x %s",
+		  __entry->cmd,
+		  _IOC_NR(__entry->cmd) < ARRAY_SIZE(binder_command_strings) ?
+			  binder_command_strings[_IOC_NR(__entry->cmd)] :
+			  "unknown")
+);
+
+TRACE_EVENT(binder_return,
+	TP_PROTO(uint32_t cmd),
+	TP_ARGS(cmd),
+	TP_STRUCT__entry(
+		__field(uint32_t, cmd)
+	),
+	TP_fast_assign(
+		__entry->cmd = cmd;
+	),
+	TP_printk("cmd=0x%x %s",
+		  __entry->cmd,
+		  _IOC_NR(__entry->cmd) < ARRAY_SIZE(binder_return_strings) ?
+			  binder_return_strings[_IOC_NR(__entry->cmd)] :
+			  "unknown")
+);
+
+#endif /* _BINDER_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE binder_trace
+#include <trace/define_trace.h>
diff --git a/drivers/staging/android/Kconfig b/drivers/staging/android/Kconfig
index 7a0e2885296..7e012f37792 100644
--- a/drivers/staging/android/Kconfig
+++ b/drivers/staging/android/Kconfig
@@ -1,37 +1,7 @@
 menu "Android"
 
-config ANDROID
-	bool "Android Drivers"
-	---help---
-	  Enable support for various drivers needed on the Android platform
-
 if ANDROID
 
-config ANDROID_BINDER_IPC
-	bool "Android Binder IPC Driver"
-	depends on MMU
-	default n
-	---help---
-	  Binder is used in Android for both communication between processes,
-	  and remote method invocation.
-
-	  This means one Android process can call a method/routine in another
-	  Android process, using Binder to identify, invoke and pass arguments
-	  between said processes.
-
-config ANDROID_BINDER_IPC_32BIT
-	bool
-	depends on !64BIT && ANDROID_BINDER_IPC
-	default y
-	---help---
-	  The Binder API has been changed to support both 32 and 64bit
-	  applications in a mixed environment.
-
-	  Enable this to support an old 32-bit Android user-space (v4.4 and
-	  earlier).
-
-	  Note that enabling this will break newer Android user-space.
-
 config ASHMEM
 	bool "Enable the Anonymous Shared Memory Subsystem"
 	default n
diff --git a/drivers/staging/android/Makefile b/drivers/staging/android/Makefile
index 517ad5ffa42..479b2b86f8c 100644
--- a/drivers/staging/android/Makefile
+++ b/drivers/staging/android/Makefile
@@ -2,7 +2,6 @@ ccflags-y += -I$(src)			# needed for trace events
 
 obj-y					+= ion/
 
-obj-$(CONFIG_ANDROID_BINDER_IPC)	+= binder.o
 obj-$(CONFIG_ASHMEM)			+= ashmem.o
 obj-$(CONFIG_ANDROID_LOGGER)		+= logger.o
 obj-$(CONFIG_ANDROID_TIMED_OUTPUT)	+= timed_output.o
diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c
deleted file mode 100644
index c69c40d69d5..00000000000
--- a/drivers/staging/android/binder.c
+++ /dev/null
@@ -1,3673 +0,0 @@
-/* binder.c
- *
- * Android IPC Subsystem
- *
- * Copyright (C) 2007-2008 Google, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <asm/cacheflush.h>
-#include <linux/fdtable.h>
-#include <linux/file.h>
-#include <linux/freezer.h>
-#include <linux/fs.h>
-#include <linux/list.h>
-#include <linux/miscdevice.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/nsproxy.h>
-#include <linux/poll.h>
-#include <linux/debugfs.h>
-#include <linux/rbtree.h>
-#include <linux/sched.h>
-#include <linux/seq_file.h>
-#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
-#include <linux/slab.h>
-#include <linux/pid_namespace.h>
-
-#include "binder.h"
-#include "binder_trace.h"
-
-static DEFINE_MUTEX(binder_main_lock);
-static DEFINE_MUTEX(binder_deferred_lock);
-static DEFINE_MUTEX(binder_mmap_lock);
-
-static HLIST_HEAD(binder_procs);
-static HLIST_HEAD(binder_deferred_list);
-static HLIST_HEAD(binder_dead_nodes);
-
-static struct dentry *binder_debugfs_dir_entry_root;
-static struct dentry *binder_debugfs_dir_entry_proc;
-static struct binder_node *binder_context_mgr_node;
-static kuid_t binder_context_mgr_uid = INVALID_UID;
-static int binder_last_id;
-static struct workqueue_struct *binder_deferred_workqueue;
-
-#define BINDER_DEBUG_ENTRY(name) \
-static int binder_##name##_open(struct inode *inode, struct file *file) \
-{ \
-	return single_open(file, binder_##name##_show, inode->i_private); \
-} \
-\
-static const struct file_operations binder_##name##_fops = { \
-	.owner = THIS_MODULE, \
-	.open = binder_##name##_open, \
-	.read = seq_read, \
-	.llseek = seq_lseek, \
-	.release = single_release, \
-}
-
-static int binder_proc_show(struct seq_file *m, void *unused);
-BINDER_DEBUG_ENTRY(proc);
-
-/* This is only defined in include/asm-arm/sizes.h */
-#ifndef SZ_1K
-#define SZ_1K                               0x400
-#endif
-
-#ifndef SZ_4M
-#define SZ_4M                               0x400000
-#endif
-
-#define FORBIDDEN_MMAP_FLAGS                (VM_WRITE)
-
-#define BINDER_SMALL_BUF_SIZE (PAGE_SIZE * 64)
-
-enum {
-	BINDER_DEBUG_USER_ERROR             = 1U << 0,
-	BINDER_DEBUG_FAILED_TRANSACTION     = 1U << 1,
-	BINDER_DEBUG_DEAD_TRANSACTION       = 1U << 2,
-	BINDER_DEBUG_OPEN_CLOSE             = 1U << 3,
-	BINDER_DEBUG_DEAD_BINDER            = 1U << 4,
-	BINDER_DEBUG_DEATH_NOTIFICATION     = 1U << 5,
-	BINDER_DEBUG_READ_WRITE             = 1U << 6,
-	BINDER_DEBUG_USER_REFS              = 1U << 7,
-	BINDER_DEBUG_THREADS                = 1U << 8,
-	BINDER_DEBUG_TRANSACTION            = 1U << 9,
-	BINDER_DEBUG_TRANSACTION_COMPLETE   = 1U << 10,
-	BINDER_DEBUG_FREE_BUFFER            = 1U << 11,
-	BINDER_DEBUG_INTERNAL_REFS          = 1U << 12,
-	BINDER_DEBUG_BUFFER_ALLOC           = 1U << 13,
-	BINDER_DEBUG_PRIORITY_CAP           = 1U << 14,
-	BINDER_DEBUG_BUFFER_ALLOC_ASYNC     = 1U << 15,
-};
-static uint32_t binder_debug_mask = BINDER_DEBUG_USER_ERROR |
-	BINDER_DEBUG_FAILED_TRANSACTION | BINDER_DEBUG_DEAD_TRANSACTION;
-module_param_named(debug_mask, binder_debug_mask, uint, S_IWUSR | S_IRUGO);
-
-static bool binder_debug_no_lock;
-module_param_named(proc_no_lock, binder_debug_no_lock, bool, S_IWUSR | S_IRUGO);
-
-static DECLARE_WAIT_QUEUE_HEAD(binder_user_error_wait);
-static int binder_stop_on_user_error;
-
-static int binder_set_stop_on_user_error(const char *val,
-					 struct kernel_param *kp)
-{
-	int ret;
-
-	ret = param_set_int(val, kp);
-	if (binder_stop_on_user_error < 2)
-		wake_up(&binder_user_error_wait);
-	return ret;
-}
-module_param_call(stop_on_user_error, binder_set_stop_on_user_error,
-	param_get_int, &binder_stop_on_user_error, S_IWUSR | S_IRUGO);
-
-#define binder_debug(mask, x...) \
-	do { \
-		if (binder_debug_mask & mask) \
-			pr_info(x); \
-	} while (0)
-
-#define binder_user_error(x...) \
-	do { \
-		if (binder_debug_mask & BINDER_DEBUG_USER_ERROR) \
-			pr_info(x); \
-		if (binder_stop_on_user_error) \
-			binder_stop_on_user_error = 2; \
-	} while (0)
-
-enum binder_stat_types {
-	BINDER_STAT_PROC,
-	BINDER_STAT_THREAD,
-	BINDER_STAT_NODE,
-	BINDER_STAT_REF,
-	BINDER_STAT_DEATH,
-	BINDER_STAT_TRANSACTION,
-	BINDER_STAT_TRANSACTION_COMPLETE,
-	BINDER_STAT_COUNT
-};
-
-struct binder_stats {
-	int br[_IOC_NR(BR_FAILED_REPLY) + 1];
-	int bc[_IOC_NR(BC_DEAD_BINDER_DONE) + 1];
-	int obj_created[BINDER_STAT_COUNT];
-	int obj_deleted[BINDER_STAT_COUNT];
-};
-
-static struct binder_stats binder_stats;
-
-static inline void binder_stats_deleted(enum binder_stat_types type)
-{
-	binder_stats.obj_deleted[type]++;
-}
-
-static inline void binder_stats_created(enum binder_stat_types type)
-{
-	binder_stats.obj_created[type]++;
-}
-
-struct binder_transaction_log_entry {
-	int debug_id;
-	int call_type;
-	int from_proc;
-	int from_thread;
-	int target_handle;
-	int to_proc;
-	int to_thread;
-	int to_node;
-	int data_size;
-	int offsets_size;
-};
-struct binder_transaction_log {
-	int next;
-	int full;
-	struct binder_transaction_log_entry entry[32];
-};
-static struct binder_transaction_log binder_transaction_log;
-static struct binder_transaction_log binder_transaction_log_failed;
-
-static struct binder_transaction_log_entry *binder_transaction_log_add(
-	struct binder_transaction_log *log)
-{
-	struct binder_transaction_log_entry *e;
-
-	e = &log->entry[log->next];
-	memset(e, 0, sizeof(*e));
-	log->next++;
-	if (log->next == ARRAY_SIZE(log->entry)) {
-		log->next = 0;
-		log->full = 1;
-	}
-	return e;
-}
-
-struct binder_work {
-	struct list_head entry;
-	enum {
-		BINDER_WORK_TRANSACTION = 1,
-		BINDER_WORK_TRANSACTION_COMPLETE,
-		BINDER_WORK_NODE,
-		BINDER_WORK_DEAD_BINDER,
-		BINDER_WORK_DEAD_BINDER_AND_CLEAR,
-		BINDER_WORK_CLEAR_DEATH_NOTIFICATION,
-	} type;
-};
-
-struct binder_node {
-	int debug_id;
-	struct binder_work work;
-	union {
-		struct rb_node rb_node;
-		struct hlist_node dead_node;
-	};
-	struct binder_proc *proc;
-	struct hlist_head refs;
-	int internal_strong_refs;
-	int local_weak_refs;
-	int local_strong_refs;
-	binder_uintptr_t ptr;
-	binder_uintptr_t cookie;
-	unsigned has_strong_ref:1;
-	unsigned pending_strong_ref:1;
-	unsigned has_weak_ref:1;
-	unsigned pending_weak_ref:1;
-	unsigned has_async_transaction:1;
-	unsigned accept_fds:1;
-	unsigned min_priority:8;
-	struct list_head async_todo;
-};
-
-struct binder_ref_death {
-	struct binder_work work;
-	binder_uintptr_t cookie;
-};
-
-struct binder_ref {
-	/* Lookups needed: */
-	/*   node + proc => ref (transaction) */
-	/*   desc + proc => ref (transaction, inc/dec ref) */
-	/*   node => refs + procs (proc exit) */
-	int debug_id;
-	struct rb_node rb_node_desc;
-	struct rb_node rb_node_node;
-	struct hlist_node node_entry;
-	struct binder_proc *proc;
-	struct binder_node *node;
-	uint32_t desc;
-	int strong;
-	int weak;
-	struct binder_ref_death *death;
-};
-
-struct binder_buffer {
-	struct list_head entry; /* free and allocated entries by address */
-	struct rb_node rb_node; /* free entry by size or allocated entry */
-				/* by address */
-	unsigned free:1;
-	unsigned allow_user_free:1;
-	unsigned async_transaction:1;
-	unsigned debug_id:29;
-
-	struct binder_transaction *transaction;
-
-	struct binder_node *target_node;
-	size_t data_size;
-	size_t offsets_size;
-	uint8_t data[0];
-};
-
-enum binder_deferred_state {
-	BINDER_DEFERRED_PUT_FILES    = 0x01,
-	BINDER_DEFERRED_FLUSH        = 0x02,
-	BINDER_DEFERRED_RELEASE      = 0x04,
-};
-
-struct binder_proc {
-	struct hlist_node proc_node;
-	struct rb_root threads;
-	struct rb_root nodes;
-	struct rb_root refs_by_desc;
-	struct rb_root refs_by_node;
-	int pid;
-	struct vm_area_struct *vma;
-	struct mm_struct *vma_vm_mm;
-	struct task_struct *tsk;
-	struct files_struct *files;
-	struct hlist_node deferred_work_node;
-	int deferred_work;
-	void *buffer;
-	ptrdiff_t user_buffer_offset;
-
-	struct list_head buffers;
-	struct rb_root free_buffers;
-	struct rb_root allocated_buffers;
-	size_t free_async_space;
-
-	struct page **pages;
-	size_t buffer_size;
-	uint32_t buffer_free;
-	struct list_head todo;
-	wait_queue_head_t wait;
-	struct binder_stats stats;
-	struct list_head delivered_death;
-	int max_threads;
-	int requested_threads;
-	int requested_threads_started;
-	int ready_threads;
-	long default_priority;
-	struct dentry *debugfs_entry;
-};
-
-enum {
-	BINDER_LOOPER_STATE_REGISTERED  = 0x01,
-	BINDER_LOOPER_STATE_ENTERED     = 0x02,
-	BINDER_LOOPER_STATE_EXITED      = 0x04,
-	BINDER_LOOPER_STATE_INVALID     = 0x08,
-	BINDER_LOOPER_STATE_WAITING     = 0x10,
-	BINDER_LOOPER_STATE_NEED_RETURN = 0x20
-};
-
-struct binder_thread {
-	struct binder_proc *proc;
-	struct rb_node rb_node;
-	int pid;
-	int looper;
-	struct binder_transaction *transaction_stack;
-	struct list_head todo;
-	uint32_t return_error; /* Write failed, return error code in read buf */
-	uint32_t return_error2; /* Write failed, return error code in read */
-		/* buffer. Used when sending a reply to a dead process that */
-		/* we are also waiting on */
-	wait_queue_head_t wait;
-	struct binder_stats stats;
-};
-
-struct binder_transaction {
-	int debug_id;
-	struct binder_work work;
-	struct binder_thread *from;
-	struct binder_transaction *from_parent;
-	struct binder_proc *to_proc;
-	struct binder_thread *to_thread;
-	struct binder_transaction *to_parent;
-	unsigned need_reply:1;
-	/* unsigned is_dead:1; */	/* not used at the moment */
-
-	struct binder_buffer *buffer;
-	unsigned int	code;
-	unsigned int	flags;
-	long	priority;
-	long	saved_priority;
-	kuid_t	sender_euid;
-};
-
-static void
-binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer);
-
-static int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
-{
-	struct files_struct *files = proc->files;
-	unsigned long rlim_cur;
-	unsigned long irqs;
-
-	if (files == NULL)
-		return -ESRCH;
-
-	if (!lock_task_sighand(proc->tsk, &irqs))
-		return -EMFILE;
-
-	rlim_cur = task_rlimit(proc->tsk, RLIMIT_NOFILE);
-	unlock_task_sighand(proc->tsk, &irqs);
-
-	return __alloc_fd(files, 0, rlim_cur, flags);
-}
-
-/*
- * copied from fd_install
- */
-static void task_fd_install(
-	struct binder_proc *proc, unsigned int fd, struct file *file)
-{
-	if (proc->files)
-		__fd_install(proc->files, fd, file);
-}
-
-/*
- * copied from sys_close
- */
-static long task_close_fd(struct binder_proc *proc, unsigned int fd)
-{
-	int retval;
-
-	if (proc->files == NULL)
-		return -ESRCH;
-
-	retval = __close_fd(proc->files, fd);
-	/* can't restart close syscall because file table entry was cleared */
-	if (unlikely(retval == -ERESTARTSYS ||
-		     retval == -ERESTARTNOINTR ||
-		     retval == -ERESTARTNOHAND ||
-		     retval == -ERESTART_RESTARTBLOCK))
-		retval = -EINTR;
-
-	return retval;
-}
-
-static inline void binder_lock(const char *tag)
-{
-	trace_binder_lock(tag);
-	mutex_lock(&binder_main_lock);
-	trace_binder_locked(tag);
-}
-
-static inline void binder_unlock(const char *tag)
-{
-	trace_binder_unlock(tag);
-	mutex_unlock(&binder_main_lock);
-}
-
-static void binder_set_nice(long nice)
-{
-	long min_nice;
-
-	if (can_nice(current, nice)) {
-		set_user_nice(current, nice);
-		return;
-	}
-	min_nice = rlimit_to_nice(current->signal->rlim[RLIMIT_NICE].rlim_cur);
-	binder_debug(BINDER_DEBUG_PRIORITY_CAP,
-		     "%d: nice value %ld not allowed use %ld instead\n",
-		      current->pid, nice, min_nice);
-	set_user_nice(current, min_nice);
-	if (min_nice <= MAX_NICE)
-		return;
-	binder_user_error("%d RLIMIT_NICE not set\n", current->pid);
-}
-
-static size_t binder_buffer_size(struct binder_proc *proc,
-				 struct binder_buffer *buffer)
-{
-	if (list_is_last(&buffer->entry, &proc->buffers))
-		return proc->buffer + proc->buffer_size - (void *)buffer->data;
-	return (size_t)list_entry(buffer->entry.next,
-			  struct binder_buffer, entry) - (size_t)buffer->data;
-}
-
-static void binder_insert_free_buffer(struct binder_proc *proc,
-				      struct binder_buffer *new_buffer)
-{
-	struct rb_node **p = &proc->free_buffers.rb_node;
-	struct rb_node *parent = NULL;
-	struct binder_buffer *buffer;
-	size_t buffer_size;
-	size_t new_buffer_size;
-
-	BUG_ON(!new_buffer->free);
-
-	new_buffer_size = binder_buffer_size(proc, new_buffer);
-
-	binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
-		     "%d: add free buffer, size %zd, at %p\n",
-		      proc->pid, new_buffer_size, new_buffer);
-
-	while (*p) {
-		parent = *p;
-		buffer = rb_entry(parent, struct binder_buffer, rb_node);
-		BUG_ON(!buffer->free);
-
-		buffer_size = binder_buffer_size(proc, buffer);
-
-		if (new_buffer_size < buffer_size)
-			p = &parent->rb_left;
-		else
-			p = &parent->rb_right;
-	}
-	rb_link_node(&new_buffer->rb_node, parent, p);
-	rb_insert_color(&new_buffer->rb_node, &proc->free_buffers);
-}
-
-static void binder_insert_allocated_buffer(struct binder_proc *proc,
-					   struct binder_buffer *new_buffer)
-{
-	struct rb_node **p = &proc->allocated_buffers.rb_node;
-	struct rb_node *parent = NULL;
-	struct binder_buffer *buffer;
-
-	BUG_ON(new_buffer->free);
-
-	while (*p) {
-		parent = *p;
-		buffer = rb_entry(parent, struct binder_buffer, rb_node);
-		BUG_ON(buffer->free);
-
-		if (new_buffer < buffer)
-			p = &parent->rb_left;
-		else if (new_buffer > buffer)
-			p = &parent->rb_right;
-		else
-			BUG();
-	}
-	rb_link_node(&new_buffer->rb_node, parent, p);
-	rb_insert_color(&new_buffer->rb_node, &proc->allocated_buffers);
-}
-
-static struct binder_buffer *binder_buffer_lookup(struct binder_proc *proc,
-						  uintptr_t user_ptr)
-{
-	struct rb_node *n = proc->allocated_buffers.rb_node;
-	struct binder_buffer *buffer;
-	struct binder_buffer *kern_ptr;
-
-	kern_ptr = (struct binder_buffer *)(user_ptr - proc->user_buffer_offset
-		- offsetof(struct binder_buffer, data));
-
-	while (n) {
-		buffer = rb_entry(n, struct binder_buffer, rb_node);
-		BUG_ON(buffer->free);
-
-		if (kern_ptr < buffer)
-			n = n->rb_left;
-		else if (kern_ptr > buffer)
-			n = n->rb_right;
-		else
-			return buffer;
-	}
-	return NULL;
-}
-
-static int binder_update_page_range(struct binder_proc *proc, int allocate,
-				    void *start, void *end,
-				    struct vm_area_struct *vma)
-{
-	void *page_addr;
-	unsigned long user_page_addr;
-	struct vm_struct tmp_area;
-	struct page **page;
-	struct mm_struct *mm;
-
-	binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
-		     "%d: %s pages %p-%p\n", proc->pid,
-		     allocate ? "allocate" : "free", start, end);
-
-	if (end <= start)
-		return 0;
-
-	trace_binder_update_page_range(proc, allocate, start, end);
-
-	if (vma)
-		mm = NULL;
-	else
-		mm = get_task_mm(proc->tsk);
-
-	if (mm) {
-		down_write(&mm->mmap_sem);
-		vma = proc->vma;
-		if (vma && mm != proc->vma_vm_mm) {
-			pr_err("%d: vma mm and task mm mismatch\n",
-				proc->pid);
-			vma = NULL;
-		}
-	}
-
-	if (allocate == 0)
-		goto free_range;
-
-	if (vma == NULL) {
-		pr_err("%d: binder_alloc_buf failed to map pages in userspace, no vma\n",
-			proc->pid);
-		goto err_no_vma;
-	}
-
-	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
-		int ret;
-
-		page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE];
-
-		BUG_ON(*page);
-		*page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
-		if (*page == NULL) {
-			pr_err("%d: binder_alloc_buf failed for page at %p\n",
-				proc->pid, page_addr);
-			goto err_alloc_page_failed;
-		}
-		tmp_area.addr = page_addr;
-		tmp_area.size = PAGE_SIZE + PAGE_SIZE /* guard page? */;
-		ret = map_vm_area(&tmp_area, PAGE_KERNEL, page);
-		if (ret) {
-			pr_err("%d: binder_alloc_buf failed to map page at %p in kernel\n",
-			       proc->pid, page_addr);
-			goto err_map_kernel_failed;
-		}
-		user_page_addr =
-			(uintptr_t)page_addr + proc->user_buffer_offset;
-		ret = vm_insert_page(vma, user_page_addr, page[0]);
-		if (ret) {
-			pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n",
-			       proc->pid, user_page_addr);
-			goto err_vm_insert_page_failed;
-		}
-		/* vm_insert_page does not seem to increment the refcount */
-	}
-	if (mm) {
-		up_write(&mm->mmap_sem);
-		mmput(mm);
-	}
-	return 0;
-
-free_range:
-	for (page_addr = end - PAGE_SIZE; page_addr >= start;
-	     page_addr -= PAGE_SIZE) {
-		page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE];
-		if (vma)
-			zap_page_range(vma, (uintptr_t)page_addr +
-				proc->user_buffer_offset, PAGE_SIZE, NULL);
-err_vm_insert_page_failed:
-		unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
-err_map_kernel_failed:
-		__free_page(*page);
-		*page = NULL;
-err_alloc_page_failed:
-		;
-	}
-err_no_vma:
-	if (mm) {
-		up_write(&mm->mmap_sem);
-		mmput(mm);
-	}
-	return -ENOMEM;
-}
-
-static struct binder_buffer *binder_alloc_buf(struct binder_proc *proc,
-					      size_t data_size,
-					      size_t offsets_size, int is_async)
-{
-	struct rb_node *n = proc->free_buffers.rb_node;
-	struct binder_buffer *buffer;
-	size_t buffer_size;
-	struct rb_node *best_fit = NULL;
-	void *has_page_addr;
-	void *end_page_addr;
-	size_t size;
-
-	if (proc->vma == NULL) {
-		pr_err("%d: binder_alloc_buf, no vma\n",
-		       proc->pid);
-		return NULL;
-	}
-
-	size = ALIGN(data_size, sizeof(void *)) +
-		ALIGN(offsets_size, sizeof(void *));
-
-	if (size < data_size || size < offsets_size) {
-		binder_user_error("%d: got transaction with invalid size %zd-%zd\n",
-				proc->pid, data_size, offsets_size);
-		return NULL;
-	}
-
-	if (is_async &&
-	    proc->free_async_space < size + sizeof(struct binder_buffer)) {
-		binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
-			     "%d: binder_alloc_buf size %zd failed, no async space left\n",
-			      proc->pid, size);
-		return NULL;
-	}
-
-	while (n) {
-		buffer = rb_entry(n, struct binder_buffer, rb_node);
-		BUG_ON(!buffer->free);
-		buffer_size = binder_buffer_size(proc, buffer);
-
-		if (size < buffer_size) {
-			best_fit = n;
-			n = n->rb_left;
-		} else if (size > buffer_size)
-			n = n->rb_right;
-		else {
-			best_fit = n;
-			break;
-		}
-	}
-	if (best_fit == NULL) {
-		pr_err("%d: binder_alloc_buf size %zd failed, no address space\n",
-			proc->pid, size);
-		return NULL;
-	}
-	if (n == NULL) {
-		buffer = rb_entry(best_fit, struct binder_buffer, rb_node);
-		buffer_size = binder_buffer_size(proc, buffer);
-	}
-
-	binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
-		     "%d: binder_alloc_buf size %zd got buffer %p size %zd\n",
-		      proc->pid, size, buffer, buffer_size);
-
-	has_page_addr =
-		(void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK);
-	if (n == NULL) {
-		if (size + sizeof(struct binder_buffer) + 4 >= buffer_size)
-			buffer_size = size; /* no room for other buffers */
-		else
-			buffer_size = size + sizeof(struct binder_buffer);
-	}
-	end_page_addr =
-		(void *)PAGE_ALIGN((uintptr_t)buffer->data + buffer_size);
-	if (end_page_addr > has_page_addr)
-		end_page_addr = has_page_addr;
-	if (binder_update_page_range(proc, 1,
-	    (void *)PAGE_ALIGN((uintptr_t)buffer->data), end_page_addr, NULL))
-		return NULL;
-
-	rb_erase(best_fit, &proc->free_buffers);
-	buffer->free = 0;
-	binder_insert_allocated_buffer(proc, buffer);
-	if (buffer_size != size) {
-		struct binder_buffer *new_buffer = (void *)buffer->data + size;
-
-		list_add(&new_buffer->entry, &buffer->entry);
-		new_buffer->free = 1;
-		binder_insert_free_buffer(proc, new_buffer);
-	}
-	binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
-		     "%d: binder_alloc_buf size %zd got %p\n",
-		      proc->pid, size, buffer);
-	buffer->data_size = data_size;
-	buffer->offsets_size = offsets_size;
-	buffer->async_transaction = is_async;
-	if (is_async) {
-		proc->free_async_space -= size + sizeof(struct binder_buffer);
-		binder_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
-			     "%d: binder_alloc_buf size %zd async free %zd\n",
-			      proc->pid, size, proc->free_async_space);
-	}
-
-	return buffer;
-}
-
-static void *buffer_start_page(struct binder_buffer *buffer)
-{
-	return (void *)((uintptr_t)buffer & PAGE_MASK);
-}
-
-static void *buffer_end_page(struct binder_buffer *buffer)
-{
-	return (void *)(((uintptr_t)(buffer + 1) - 1) & PAGE_MASK);
-}
-
-static void binder_delete_free_buffer(struct binder_proc *proc,
-				      struct binder_buffer *buffer)
-{
-	struct binder_buffer *prev, *next = NULL;
-	int free_page_end = 1;
-	int free_page_start = 1;
-
-	BUG_ON(proc->buffers.next == &buffer->entry);
-	prev = list_entry(buffer->entry.prev, struct binder_buffer, entry);
-	BUG_ON(!prev->free);
-	if (buffer_end_page(prev) == buffer_start_page(buffer)) {
-		free_page_start = 0;
-		if (buffer_end_page(prev) == buffer_end_page(buffer))
-			free_page_end = 0;
-		binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
-			     "%d: merge free, buffer %p share page with %p\n",
-			      proc->pid, buffer, prev);
-	}
-
-	if (!list_is_last(&buffer->entry, &proc->buffers)) {
-		next = list_entry(buffer->entry.next,
-				  struct binder_buffer, entry);
-		if (buffer_start_page(next) == buffer_end_page(buffer)) {
-			free_page_end = 0;
-			if (buffer_start_page(next) ==
-			    buffer_start_page(buffer))
-				free_page_start = 0;
-			binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				     "%d: merge free, buffer %p share page with %p\n",
-				      proc->pid, buffer, prev);
-		}
-	}
-	list_del(&buffer->entry);
-	if (free_page_start || free_page_end) {
-		binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
-			     "%d: merge free, buffer %p do not share page%s%s with %p or %p\n",
-			     proc->pid, buffer, free_page_start ? "" : " end",
-			     free_page_end ? "" : " start", prev, next);
-		binder_update_page_range(proc, 0, free_page_start ?
-			buffer_start_page(buffer) : buffer_end_page(buffer),
-			(free_page_end ? buffer_end_page(buffer) :
-			buffer_start_page(buffer)) + PAGE_SIZE, NULL);
-	}
-}
-
-static void binder_free_buf(struct binder_proc *proc,
-			    struct binder_buffer *buffer)
-{
-	size_t size, buffer_size;
-
-	buffer_size = binder_buffer_size(proc, buffer);
-
-	size = ALIGN(buffer->data_size, sizeof(void *)) +
-		ALIGN(buffer->offsets_size, sizeof(void *));
-
-	binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
-		     "%d: binder_free_buf %p size %zd buffer_size %zd\n",
-		      proc->pid, buffer, size, buffer_size);
-
-	BUG_ON(buffer->free);
-	BUG_ON(size > buffer_size);
-	BUG_ON(buffer->transaction != NULL);
-	BUG_ON((void *)buffer < proc->buffer);
-	BUG_ON((void *)buffer > proc->buffer + proc->buffer_size);
-
-	if (buffer->async_transaction) {
-		proc->free_async_space += size + sizeof(struct binder_buffer);
-
-		binder_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
-			     "%d: binder_free_buf size %zd async free %zd\n",
-			      proc->pid, size, proc->free_async_space);
-	}
-
-	binder_update_page_range(proc, 0,
-		(void *)PAGE_ALIGN((uintptr_t)buffer->data),
-		(void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK),
-		NULL);
-	rb_erase(&buffer->rb_node, &proc->allocated_buffers);
-	buffer->free = 1;
-	if (!list_is_last(&buffer->entry, &proc->buffers)) {
-		struct binder_buffer *next = list_entry(buffer->entry.next,
-						struct binder_buffer, entry);
-
-		if (next->free) {
-			rb_erase(&next->rb_node, &proc->free_buffers);
-			binder_delete_free_buffer(proc, next);
-		}
-	}
-	if (proc->buffers.next != &buffer->entry) {
-		struct binder_buffer *prev = list_entry(buffer->entry.prev,
-						struct binder_buffer, entry);
-
-		if (prev->free) {
-			binder_delete_free_buffer(proc, buffer);
-			rb_erase(&prev->rb_node, &proc->free_buffers);
-			buffer = prev;
-		}
-	}
-	binder_insert_free_buffer(proc, buffer);
-}
-
-static struct binder_node *binder_get_node(struct binder_proc *proc,
-					   binder_uintptr_t ptr)
-{
-	struct rb_node *n = proc->nodes.rb_node;
-	struct binder_node *node;
-
-	while (n) {
-		node = rb_entry(n, struct binder_node, rb_node);
-
-		if (ptr < node->ptr)
-			n = n->rb_left;
-		else if (ptr > node->ptr)
-			n = n->rb_right;
-		else
-			return node;
-	}
-	return NULL;
-}
-
-static struct binder_node *binder_new_node(struct binder_proc *proc,
-					   binder_uintptr_t ptr,
-					   binder_uintptr_t cookie)
-{
-	struct rb_node **p = &proc->nodes.rb_node;
-	struct rb_node *parent = NULL;
-	struct binder_node *node;
-
-	while (*p) {
-		parent = *p;
-		node = rb_entry(parent, struct binder_node, rb_node);
-
-		if (ptr < node->ptr)
-			p = &(*p)->rb_left;
-		else if (ptr > node->ptr)
-			p = &(*p)->rb_right;
-		else
-			return NULL;
-	}
-
-	node = kzalloc(sizeof(*node), GFP_KERNEL);
-	if (node == NULL)
-		return NULL;
-	binder_stats_created(BINDER_STAT_NODE);
-	rb_link_node(&node->rb_node, parent, p);
-	rb_insert_color(&node->rb_node, &proc->nodes);
-	node->debug_id = ++binder_last_id;
-	node->proc = proc;
-	node->ptr = ptr;
-	node->cookie = cookie;
-	node->work.type = BINDER_WORK_NODE;
-	INIT_LIST_HEAD(&node->work.entry);
-	INIT_LIST_HEAD(&node->async_todo);
-	binder_debug(BINDER_DEBUG_INTERNAL_REFS,
-		     "%d:%d node %d u%016llx c%016llx created\n",
-		     proc->pid, current->pid, node->debug_id,
-		     (u64)node->ptr, (u64)node->cookie);
-	return node;
-}
-
-static int binder_inc_node(struct binder_node *node, int strong, int internal,
-			   struct list_head *target_list)
-{
-	if (strong) {
-		if (internal) {
-			if (target_list == NULL &&
-			    node->internal_strong_refs == 0 &&
-			    !(node == binder_context_mgr_node &&
-			    node->has_strong_ref)) {
-				pr_err("invalid inc strong node for %d\n",
-					node->debug_id);
-				return -EINVAL;
-			}
-			node->internal_strong_refs++;
-		} else
-			node->local_strong_refs++;
-		if (!node->has_strong_ref && target_list) {
-			list_del_init(&node->work.entry);
-			list_add_tail(&node->work.entry, target_list);
-		}
-	} else {
-		if (!internal)
-			node->local_weak_refs++;
-		if (!node->has_weak_ref && list_empty(&node->work.entry)) {
-			if (target_list == NULL) {
-				pr_err("invalid inc weak node for %d\n",
-					node->debug_id);
-				return -EINVAL;
-			}
-			list_add_tail(&node->work.entry, target_list);
-		}
-	}
-	return 0;
-}
-
-static int binder_dec_node(struct binder_node *node, int strong, int internal)
-{
-	if (strong) {
-		if (internal)
-			node->internal_strong_refs--;
-		else
-			node->local_strong_refs--;
-		if (node->local_strong_refs || node->internal_strong_refs)
-			return 0;
-	} else {
-		if (!internal)
-			node->local_weak_refs--;
-		if (node->local_weak_refs || !hlist_empty(&node->refs))
-			return 0;
-	}
-	if (node->proc && (node->has_strong_ref || node->has_weak_ref)) {
-		if (list_empty(&node->work.entry)) {
-			list_add_tail(&node->work.entry, &node->proc->todo);
-			wake_up_interruptible(&node->proc->wait);
-		}
-	} else {
-		if (hlist_empty(&node->refs) && !node->local_strong_refs &&
-		    !node->local_weak_refs) {
-			list_del_init(&node->work.entry);
-			if (node->proc) {
-				rb_erase(&node->rb_node, &node->proc->nodes);
-				binder_debug(BINDER_DEBUG_INTERNAL_REFS,
-					     "refless node %d deleted\n",
-					     node->debug_id);
-			} else {
-				hlist_del(&node->dead_node);
-				binder_debug(BINDER_DEBUG_INTERNAL_REFS,
-					     "dead node %d deleted\n",
-					     node->debug_id);
-			}
-			kfree(node);
-			binder_stats_deleted(BINDER_STAT_NODE);
-		}
-	}
-
-	return 0;
-}
-
-
-static struct binder_ref *binder_get_ref(struct binder_proc *proc,
-					 uint32_t desc)
-{
-	struct rb_node *n = proc->refs_by_desc.rb_node;
-	struct binder_ref *ref;
-
-	while (n) {
-		ref = rb_entry(n, struct binder_ref, rb_node_desc);
-
-		if (desc < ref->desc)
-			n = n->rb_left;
-		else if (desc > ref->desc)
-			n = n->rb_right;
-		else
-			return ref;
-	}
-	return NULL;
-}
-
-static struct binder_ref *binder_get_ref_for_node(struct binder_proc *proc,
-						  struct binder_node *node)
-{
-	struct rb_node *n;
-	struct rb_node **p = &proc->refs_by_node.rb_node;
-	struct rb_node *parent = NULL;
-	struct binder_ref *ref, *new_ref;
-
-	while (*p) {
-		parent = *p;
-		ref = rb_entry(parent, struct binder_ref, rb_node_node);
-
-		if (node < ref->node)
-			p = &(*p)->rb_left;
-		else if (node > ref->node)
-			p = &(*p)->rb_right;
-		else
-			return ref;
-	}
-	new_ref = kzalloc(sizeof(*ref), GFP_KERNEL);
-	if (new_ref == NULL)
-		return NULL;
-	binder_stats_created(BINDER_STAT_REF);
-	new_ref->debug_id = ++binder_last_id;
-	new_ref->proc = proc;
-	new_ref->node = node;
-	rb_link_node(&new_ref->rb_node_node, parent, p);
-	rb_insert_color(&new_ref->rb_node_node, &proc->refs_by_node);
-
-	new_ref->desc = (node == binder_context_mgr_node) ? 0 : 1;
-	for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) {
-		ref = rb_entry(n, struct binder_ref, rb_node_desc);
-		if (ref->desc > new_ref->desc)
-			break;
-		new_ref->desc = ref->desc + 1;
-	}
-
-	p = &proc->refs_by_desc.rb_node;
-	while (*p) {
-		parent = *p;
-		ref = rb_entry(parent, struct binder_ref, rb_node_desc);
-
-		if (new_ref->desc < ref->desc)
-			p = &(*p)->rb_left;
-		else if (new_ref->desc > ref->desc)
-			p = &(*p)->rb_right;
-		else
-			BUG();
-	}
-	rb_link_node(&new_ref->rb_node_desc, parent, p);
-	rb_insert_color(&new_ref->rb_node_desc, &proc->refs_by_desc);
-	if (node) {
-		hlist_add_head(&new_ref->node_entry, &node->refs);
-
-		binder_debug(BINDER_DEBUG_INTERNAL_REFS,
-			     "%d new ref %d desc %d for node %d\n",
-			      proc->pid, new_ref->debug_id, new_ref->desc,
-			      node->debug_id);
-	} else {
-		binder_debug(BINDER_DEBUG_INTERNAL_REFS,
-			     "%d new ref %d desc %d for dead node\n",
-			      proc->pid, new_ref->debug_id, new_ref->desc);
-	}
-	return new_ref;
-}
-
-static void binder_delete_ref(struct binder_ref *ref)
-{
-	binder_debug(BINDER_DEBUG_INTERNAL_REFS,
-		     "%d delete ref %d desc %d for node %d\n",
-		      ref->proc->pid, ref->debug_id, ref->desc,
-		      ref->node->debug_id);
-
-	rb_erase(&ref->rb_node_desc, &ref->proc->refs_by_desc);
-	rb_erase(&ref->rb_node_node, &ref->proc->refs_by_node);
-	if (ref->strong)
-		binder_dec_node(ref->node, 1, 1);
-	hlist_del(&ref->node_entry);
-	binder_dec_node(ref->node, 0, 1);
-	if (ref->death) {
-		binder_debug(BINDER_DEBUG_DEAD_BINDER,
-			     "%d delete ref %d desc %d has death notification\n",
-			      ref->proc->pid, ref->debug_id, ref->desc);
-		list_del(&ref->death->work.entry);
-		kfree(ref->death);
-		binder_stats_deleted(BINDER_STAT_DEATH);
-	}
-	kfree(ref);
-	binder_stats_deleted(BINDER_STAT_REF);
-}
-
-static int binder_inc_ref(struct binder_ref *ref, int strong,
-			  struct list_head *target_list)
-{
-	int ret;
-
-	if (strong) {
-		if (ref->strong == 0) {
-			ret = binder_inc_node(ref->node, 1, 1, target_list);
-			if (ret)
-				return ret;
-		}
-		ref->strong++;
-	} else {
-		if (ref->weak == 0) {
-			ret = binder_inc_node(ref->node, 0, 1, target_list);
-			if (ret)
-				return ret;
-		}
-		ref->weak++;
-	}
-	return 0;
-}
-
-
-static int binder_dec_ref(struct binder_ref *ref, int strong)
-{
-	if (strong) {
-		if (ref->strong == 0) {
-			binder_user_error("%d invalid dec strong, ref %d desc %d s %d w %d\n",
-					  ref->proc->pid, ref->debug_id,
-					  ref->desc, ref->strong, ref->weak);
-			return -EINVAL;
-		}
-		ref->strong--;
-		if (ref->strong == 0) {
-			int ret;
-
-			ret = binder_dec_node(ref->node, strong, 1);
-			if (ret)
-				return ret;
-		}
-	} else {
-		if (ref->weak == 0) {
-			binder_user_error("%d invalid dec weak, ref %d desc %d s %d w %d\n",
-					  ref->proc->pid, ref->debug_id,
-					  ref->desc, ref->strong, ref->weak);
-			return -EINVAL;
-		}
-		ref->weak--;
-	}
-	if (ref->strong == 0 && ref->weak == 0)
-		binder_delete_ref(ref);
-	return 0;
-}
-
-static void binder_pop_transaction(struct binder_thread *target_thread,
-				   struct binder_transaction *t)
-{
-	if (target_thread) {
-		BUG_ON(target_thread->transaction_stack != t);
-		BUG_ON(target_thread->transaction_stack->from != target_thread);
-		target_thread->transaction_stack =
-			target_thread->transaction_stack->from_parent;
-		t->from = NULL;
-	}
-	t->need_reply = 0;
-	if (t->buffer)
-		t->buffer->transaction = NULL;
-	kfree(t);
-	binder_stats_deleted(BINDER_STAT_TRANSACTION);
-}
-
-static void binder_send_failed_reply(struct binder_transaction *t,
-				     uint32_t error_code)
-{
-	struct binder_thread *target_thread;
-	struct binder_transaction *next;
-
-	BUG_ON(t->flags & TF_ONE_WAY);
-	while (1) {
-		target_thread = t->from;
-		if (target_thread) {
-			if (target_thread->return_error != BR_OK &&
-			   target_thread->return_error2 == BR_OK) {
-				target_thread->return_error2 =
-					target_thread->return_error;
-				target_thread->return_error = BR_OK;
-			}
-			if (target_thread->return_error == BR_OK) {
-				binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
-					     "send failed reply for transaction %d to %d:%d\n",
-					      t->debug_id,
-					      target_thread->proc->pid,
-					      target_thread->pid);
-
-				binder_pop_transaction(target_thread, t);
-				target_thread->return_error = error_code;
-				wake_up_interruptible(&target_thread->wait);
-			} else {
-				pr_err("reply failed, target thread, %d:%d, has error code %d already\n",
-					target_thread->proc->pid,
-					target_thread->pid,
-					target_thread->return_error);
-			}
-			return;
-		}
-		next = t->from_parent;
-
-		binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
-			     "send failed reply for transaction %d, target dead\n",
-			     t->debug_id);
-
-		binder_pop_transaction(target_thread, t);
-		if (next == NULL) {
-			binder_debug(BINDER_DEBUG_DEAD_BINDER,
-				     "reply failed, no target thread at root\n");
-			return;
-		}
-		t = next;
-		binder_debug(BINDER_DEBUG_DEAD_BINDER,
-			     "reply failed, no target thread -- retry %d\n",
-			      t->debug_id);
-	}
-}
-
-static void binder_transaction_buffer_release(struct binder_proc *proc,
-					      struct binder_buffer *buffer,
-					      binder_size_t *failed_at)
-{
-	binder_size_t *offp, *off_end;
-	int debug_id = buffer->debug_id;
-
-	binder_debug(BINDER_DEBUG_TRANSACTION,
-		     "%d buffer release %d, size %zd-%zd, failed at %p\n",
-		     proc->pid, buffer->debug_id,
-		     buffer->data_size, buffer->offsets_size, failed_at);
-
-	if (buffer->target_node)
-		binder_dec_node(buffer->target_node, 1, 0);
-
-	offp = (binder_size_t *)(buffer->data +
-				 ALIGN(buffer->data_size, sizeof(void *)));
-	if (failed_at)
-		off_end = failed_at;
-	else
-		off_end = (void *)offp + buffer->offsets_size;
-	for (; offp < off_end; offp++) {
-		struct flat_binder_object *fp;
-
-		if (*offp > buffer->data_size - sizeof(*fp) ||
-		    buffer->data_size < sizeof(*fp) ||
-		    !IS_ALIGNED(*offp, sizeof(u32))) {
-			pr_err("transaction release %d bad offset %lld, size %zd\n",
-			       debug_id, (u64)*offp, buffer->data_size);
-			continue;
-		}
-		fp = (struct flat_binder_object *)(buffer->data + *offp);
-		switch (fp->type) {
-		case BINDER_TYPE_BINDER:
-		case BINDER_TYPE_WEAK_BINDER: {
-			struct binder_node *node = binder_get_node(proc, fp->binder);
-
-			if (node == NULL) {
-				pr_err("transaction release %d bad node %016llx\n",
-				       debug_id, (u64)fp->binder);
-				break;
-			}
-			binder_debug(BINDER_DEBUG_TRANSACTION,
-				     "        node %d u%016llx\n",
-				     node->debug_id, (u64)node->ptr);
-			binder_dec_node(node, fp->type == BINDER_TYPE_BINDER, 0);
-		} break;
-		case BINDER_TYPE_HANDLE:
-		case BINDER_TYPE_WEAK_HANDLE: {
-			struct binder_ref *ref = binder_get_ref(proc, fp->handle);
-
-			if (ref == NULL) {
-				pr_err("transaction release %d bad handle %d\n",
-				 debug_id, fp->handle);
-				break;
-			}
-			binder_debug(BINDER_DEBUG_TRANSACTION,
-				     "        ref %d desc %d (node %d)\n",
-				     ref->debug_id, ref->desc, ref->node->debug_id);
-			binder_dec_ref(ref, fp->type == BINDER_TYPE_HANDLE);
-		} break;
-
-		case BINDER_TYPE_FD:
-			binder_debug(BINDER_DEBUG_TRANSACTION,
-				     "        fd %d\n", fp->handle);
-			if (failed_at)
-				task_close_fd(proc, fp->handle);
-			break;
-
-		default:
-			pr_err("transaction release %d bad object type %x\n",
-				debug_id, fp->type);
-			break;
-		}
-	}
-}
-
-static void binder_transaction(struct binder_proc *proc,
-			       struct binder_thread *thread,
-			       struct binder_transaction_data *tr, int reply)
-{
-	struct binder_transaction *t;
-	struct binder_work *tcomplete;
-	binder_size_t *offp, *off_end;
-	struct binder_proc *target_proc;
-	struct binder_thread *target_thread = NULL;
-	struct binder_node *target_node = NULL;
-	struct list_head *target_list;
-	wait_queue_head_t *target_wait;
-	struct binder_transaction *in_reply_to = NULL;
-	struct binder_transaction_log_entry *e;
-	uint32_t return_error;
-
-	e = binder_transaction_log_add(&binder_transaction_log);
-	e->call_type = reply ? 2 : !!(tr->flags & TF_ONE_WAY);
-	e->from_proc = proc->pid;
-	e->from_thread = thread->pid;
-	e->target_handle = tr->target.handle;
-	e->data_size = tr->data_size;
-	e->offsets_size = tr->offsets_size;
-
-	if (reply) {
-		in_reply_to = thread->transaction_stack;
-		if (in_reply_to == NULL) {
-			binder_user_error("%d:%d got reply transaction with no transaction stack\n",
-					  proc->pid, thread->pid);
-			return_error = BR_FAILED_REPLY;
-			goto err_empty_call_stack;
-		}
-		binder_set_nice(in_reply_to->saved_priority);
-		if (in_reply_to->to_thread != thread) {
-			binder_user_error("%d:%d got reply transaction with bad transaction stack, transaction %d has target %d:%d\n",
-				proc->pid, thread->pid, in_reply_to->debug_id,
-				in_reply_to->to_proc ?
-				in_reply_to->to_proc->pid : 0,
-				in_reply_to->to_thread ?
-				in_reply_to->to_thread->pid : 0);
-			return_error = BR_FAILED_REPLY;
-			in_reply_to = NULL;
-			goto err_bad_call_stack;
-		}
-		thread->transaction_stack = in_reply_to->to_parent;
-		target_thread = in_reply_to->from;
-		if (target_thread == NULL) {
-			return_error = BR_DEAD_REPLY;
-			goto err_dead_binder;
-		}
-		if (target_thread->transaction_stack != in_reply_to) {
-			binder_user_error("%d:%d got reply transaction with bad target transaction stack %d, expected %d\n",
-				proc->pid, thread->pid,
-				target_thread->transaction_stack ?
-				target_thread->transaction_stack->debug_id : 0,
-				in_reply_to->debug_id);
-			return_error = BR_FAILED_REPLY;
-			in_reply_to = NULL;
-			target_thread = NULL;
-			goto err_dead_binder;
-		}
-		target_proc = target_thread->proc;
-	} else {
-		if (tr->target.handle) {
-			struct binder_ref *ref;
-
-			ref = binder_get_ref(proc, tr->target.handle);
-			if (ref == NULL) {
-				binder_user_error("%d:%d got transaction to invalid handle\n",
-					proc->pid, thread->pid);
-				return_error = BR_FAILED_REPLY;
-				goto err_invalid_target_handle;
-			}
-			target_node = ref->node;
-		} else {
-			target_node = binder_context_mgr_node;
-			if (target_node == NULL) {
-				return_error = BR_DEAD_REPLY;
-				goto err_no_context_mgr_node;
-			}
-		}
-		e->to_node = target_node->debug_id;
-		target_proc = target_node->proc;
-		if (target_proc == NULL) {
-			return_error = BR_DEAD_REPLY;
-			goto err_dead_binder;
-		}
-		if (!(tr->flags & TF_ONE_WAY) && thread->transaction_stack) {
-			struct binder_transaction *tmp;
-
-			tmp = thread->transaction_stack;
-			if (tmp->to_thread != thread) {
-				binder_user_error("%d:%d got new transaction with bad transaction stack, transaction %d has target %d:%d\n",
-					proc->pid, thread->pid, tmp->debug_id,
-					tmp->to_proc ? tmp->to_proc->pid : 0,
-					tmp->to_thread ?
-					tmp->to_thread->pid : 0);
-				return_error = BR_FAILED_REPLY;
-				goto err_bad_call_stack;
-			}
-			while (tmp) {
-				if (tmp->from && tmp->from->proc == target_proc)
-					target_thread = tmp->from;
-				tmp = tmp->from_parent;
-			}
-		}
-	}
-	if (target_thread) {
-		e->to_thread = target_thread->pid;
-		target_list = &target_thread->todo;
-		target_wait = &target_thread->wait;
-	} else {
-		target_list = &target_proc->todo;
-		target_wait = &target_proc->wait;
-	}
-	e->to_proc = target_proc->pid;
-
-	/* TODO: reuse incoming transaction for reply */
-	t = kzalloc(sizeof(*t), GFP_KERNEL);
-	if (t == NULL) {
-		return_error = BR_FAILED_REPLY;
-		goto err_alloc_t_failed;
-	}
-	binder_stats_created(BINDER_STAT_TRANSACTION);
-
-	tcomplete = kzalloc(sizeof(*tcomplete), GFP_KERNEL);
-	if (tcomplete == NULL) {
-		return_error = BR_FAILED_REPLY;
-		goto err_alloc_tcomplete_failed;
-	}
-	binder_stats_created(BINDER_STAT_TRANSACTION_COMPLETE);
-
-	t->debug_id = ++binder_last_id;
-	e->debug_id = t->debug_id;
-
-	if (reply)
-		binder_debug(BINDER_DEBUG_TRANSACTION,
-			     "%d:%d BC_REPLY %d -> %d:%d, data %016llx-%016llx size %lld-%lld\n",
-			     proc->pid, thread->pid, t->debug_id,
-			     target_proc->pid, target_thread->pid,
-			     (u64)tr->data.ptr.buffer,
-			     (u64)tr->data.ptr.offsets,
-			     (u64)tr->data_size, (u64)tr->offsets_size);
-	else
-		binder_debug(BINDER_DEBUG_TRANSACTION,
-			     "%d:%d BC_TRANSACTION %d -> %d - node %d, data %016llx-%016llx size %lld-%lld\n",
-			     proc->pid, thread->pid, t->debug_id,
-			     target_proc->pid, target_node->debug_id,
-			     (u64)tr->data.ptr.buffer,
-			     (u64)tr->data.ptr.offsets,
-			     (u64)tr->data_size, (u64)tr->offsets_size);
-
-	if (!reply && !(tr->flags & TF_ONE_WAY))
-		t->from = thread;
-	else
-		t->from = NULL;
-	t->sender_euid = task_euid(proc->tsk);
-	t->to_proc = target_proc;
-	t->to_thread = target_thread;
-	t->code = tr->code;
-	t->flags = tr->flags;
-	t->priority = task_nice(current);
-
-	trace_binder_transaction(reply, t, target_node);
-
-	t->buffer = binder_alloc_buf(target_proc, tr->data_size,
-		tr->offsets_size, !reply && (t->flags & TF_ONE_WAY));
-	if (t->buffer == NULL) {
-		return_error = BR_FAILED_REPLY;
-		goto err_binder_alloc_buf_failed;
-	}
-	t->buffer->allow_user_free = 0;
-	t->buffer->debug_id = t->debug_id;
-	t->buffer->transaction = t;
-	t->buffer->target_node = target_node;
-	trace_binder_transaction_alloc_buf(t->buffer);
-	if (target_node)
-		binder_inc_node(target_node, 1, 0, NULL);
-
-	offp = (binder_size_t *)(t->buffer->data +
-				 ALIGN(tr->data_size, sizeof(void *)));
-
-	if (copy_from_user(t->buffer->data, (const void __user *)(uintptr_t)
-			   tr->data.ptr.buffer, tr->data_size)) {
-		binder_user_error("%d:%d got transaction with invalid data ptr\n",
-				proc->pid, thread->pid);
-		return_error = BR_FAILED_REPLY;
-		goto err_copy_data_failed;
-	}
-	if (copy_from_user(offp, (const void __user *)(uintptr_t)
-			   tr->data.ptr.offsets, tr->offsets_size)) {
-		binder_user_error("%d:%d got transaction with invalid offsets ptr\n",
-				proc->pid, thread->pid);
-		return_error = BR_FAILED_REPLY;
-		goto err_copy_data_failed;
-	}
-	if (!IS_ALIGNED(tr->offsets_size, sizeof(binder_size_t))) {
-		binder_user_error("%d:%d got transaction with invalid offsets size, %lld\n",
-				proc->pid, thread->pid, (u64)tr->offsets_size);
-		return_error = BR_FAILED_REPLY;
-		goto err_bad_offset;
-	}
-	off_end = (void *)offp + tr->offsets_size;
-	for (; offp < off_end; offp++) {
-		struct flat_binder_object *fp;
-
-		if (*offp > t->buffer->data_size - sizeof(*fp) ||
-		    t->buffer->data_size < sizeof(*fp) ||
-		    !IS_ALIGNED(*offp, sizeof(u32))) {
-			binder_user_error("%d:%d got transaction with invalid offset, %lld\n",
-					  proc->pid, thread->pid, (u64)*offp);
-			return_error = BR_FAILED_REPLY;
-			goto err_bad_offset;
-		}
-		fp = (struct flat_binder_object *)(t->buffer->data + *offp);
-		switch (fp->type) {
-		case BINDER_TYPE_BINDER:
-		case BINDER_TYPE_WEAK_BINDER: {
-			struct binder_ref *ref;
-			struct binder_node *node = binder_get_node(proc, fp->binder);
-
-			if (node == NULL) {
-				node = binder_new_node(proc, fp->binder, fp->cookie);
-				if (node == NULL) {
-					return_error = BR_FAILED_REPLY;
-					goto err_binder_new_node_failed;
-				}
-				node->min_priority = fp->flags & FLAT_BINDER_FLAG_PRIORITY_MASK;
-				node->accept_fds = !!(fp->flags & FLAT_BINDER_FLAG_ACCEPTS_FDS);
-			}
-			if (fp->cookie != node->cookie) {
-				binder_user_error("%d:%d sending u%016llx node %d, cookie mismatch %016llx != %016llx\n",
-					proc->pid, thread->pid,
-					(u64)fp->binder, node->debug_id,
-					(u64)fp->cookie, (u64)node->cookie);
-				return_error = BR_FAILED_REPLY;
-				goto err_binder_get_ref_for_node_failed;
-			}
-			ref = binder_get_ref_for_node(target_proc, node);
-			if (ref == NULL) {
-				return_error = BR_FAILED_REPLY;
-				goto err_binder_get_ref_for_node_failed;
-			}
-			if (fp->type == BINDER_TYPE_BINDER)
-				fp->type = BINDER_TYPE_HANDLE;
-			else
-				fp->type = BINDER_TYPE_WEAK_HANDLE;
-			fp->handle = ref->desc;
-			binder_inc_ref(ref, fp->type == BINDER_TYPE_HANDLE,
-				       &thread->todo);
-
-			trace_binder_transaction_node_to_ref(t, node, ref);
-			binder_debug(BINDER_DEBUG_TRANSACTION,
-				     "        node %d u%016llx -> ref %d desc %d\n",
-				     node->debug_id, (u64)node->ptr,
-				     ref->debug_id, ref->desc);
-		} break;
-		case BINDER_TYPE_HANDLE:
-		case BINDER_TYPE_WEAK_HANDLE: {
-			struct binder_ref *ref = binder_get_ref(proc, fp->handle);
-
-			if (ref == NULL) {
-				binder_user_error("%d:%d got transaction with invalid handle, %d\n",
-						proc->pid,
-						thread->pid, fp->handle);
-				return_error = BR_FAILED_REPLY;
-				goto err_binder_get_ref_failed;
-			}
-			if (ref->node->proc == target_proc) {
-				if (fp->type == BINDER_TYPE_HANDLE)
-					fp->type = BINDER_TYPE_BINDER;
-				else
-					fp->type = BINDER_TYPE_WEAK_BINDER;
-				fp->binder = ref->node->ptr;
-				fp->cookie = ref->node->cookie;
-				binder_inc_node(ref->node, fp->type == BINDER_TYPE_BINDER, 0, NULL);
-				trace_binder_transaction_ref_to_node(t, ref);
-				binder_debug(BINDER_DEBUG_TRANSACTION,
-					     "        ref %d desc %d -> node %d u%016llx\n",
-					     ref->debug_id, ref->desc, ref->node->debug_id,
-					     (u64)ref->node->ptr);
-			} else {
-				struct binder_ref *new_ref;
-
-				new_ref = binder_get_ref_for_node(target_proc, ref->node);
-				if (new_ref == NULL) {
-					return_error = BR_FAILED_REPLY;
-					goto err_binder_get_ref_for_node_failed;
-				}
-				fp->handle = new_ref->desc;
-				binder_inc_ref(new_ref, fp->type == BINDER_TYPE_HANDLE, NULL);
-				trace_binder_transaction_ref_to_ref(t, ref,
-								    new_ref);
-				binder_debug(BINDER_DEBUG_TRANSACTION,
-					     "        ref %d desc %d -> ref %d desc %d (node %d)\n",
-					     ref->debug_id, ref->desc, new_ref->debug_id,
-					     new_ref->desc, ref->node->debug_id);
-			}
-		} break;
-
-		case BINDER_TYPE_FD: {
-			int target_fd;
-			struct file *file;
-
-			if (reply) {
-				if (!(in_reply_to->flags & TF_ACCEPT_FDS)) {
-					binder_user_error("%d:%d got reply with fd, %d, but target does not allow fds\n",
-						proc->pid, thread->pid, fp->handle);
-					return_error = BR_FAILED_REPLY;
-					goto err_fd_not_allowed;
-				}
-			} else if (!target_node->accept_fds) {
-				binder_user_error("%d:%d got transaction with fd, %d, but target does not allow fds\n",
-					proc->pid, thread->pid, fp->handle);
-				return_error = BR_FAILED_REPLY;
-				goto err_fd_not_allowed;
-			}
-
-			file = fget(fp->handle);
-			if (file == NULL) {
-				binder_user_error("%d:%d got transaction with invalid fd, %d\n",
-					proc->pid, thread->pid, fp->handle);
-				return_error = BR_FAILED_REPLY;
-				goto err_fget_failed;
-			}
-			target_fd = task_get_unused_fd_flags(target_proc, O_CLOEXEC);
-			if (target_fd < 0) {
-				fput(file);
-				return_error = BR_FAILED_REPLY;
-				goto err_get_unused_fd_failed;
-			}
-			task_fd_install(target_proc, target_fd, file);
-			trace_binder_transaction_fd(t, fp->handle, target_fd);
-			binder_debug(BINDER_DEBUG_TRANSACTION,
-				     "        fd %d -> %d\n", fp->handle, target_fd);
-			/* TODO: fput? */
-			fp->handle = target_fd;
-		} break;
-
-		default:
-			binder_user_error("%d:%d got transaction with invalid object type, %x\n",
-				proc->pid, thread->pid, fp->type);
-			return_error = BR_FAILED_REPLY;
-			goto err_bad_object_type;
-		}
-	}
-	if (reply) {
-		BUG_ON(t->buffer->async_transaction != 0);
-		binder_pop_transaction(target_thread, in_reply_to);
-	} else if (!(t->flags & TF_ONE_WAY)) {
-		BUG_ON(t->buffer->async_transaction != 0);
-		t->need_reply = 1;
-		t->from_parent = thread->transaction_stack;
-		thread->transaction_stack = t;
-	} else {
-		BUG_ON(target_node == NULL);
-		BUG_ON(t->buffer->async_transaction != 1);
-		if (target_node->has_async_transaction) {
-			target_list = &target_node->async_todo;
-			target_wait = NULL;
-		} else
-			target_node->has_async_transaction = 1;
-	}
-	t->work.type = BINDER_WORK_TRANSACTION;
-	list_add_tail(&t->work.entry, target_list);
-	tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE;
-	list_add_tail(&tcomplete->entry, &thread->todo);
-	if (target_wait)
-		wake_up_interruptible(target_wait);
-	return;
-
-err_get_unused_fd_failed:
-err_fget_failed:
-err_fd_not_allowed:
-err_binder_get_ref_for_node_failed:
-err_binder_get_ref_failed:
-err_binder_new_node_failed:
-err_bad_object_type:
-err_bad_offset:
-err_copy_data_failed:
-	trace_binder_transaction_failed_buffer_release(t->buffer);
-	binder_transaction_buffer_release(target_proc, t->buffer, offp);
-	t->buffer->transaction = NULL;
-	binder_free_buf(target_proc, t->buffer);
-err_binder_alloc_buf_failed:
-	kfree(tcomplete);
-	binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE);
-err_alloc_tcomplete_failed:
-	kfree(t);
-	binder_stats_deleted(BINDER_STAT_TRANSACTION);
-err_alloc_t_failed:
-err_bad_call_stack:
-err_empty_call_stack:
-err_dead_binder:
-err_invalid_target_handle:
-err_no_context_mgr_node:
-	binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
-		     "%d:%d transaction failed %d, size %lld-%lld\n",
-		     proc->pid, thread->pid, return_error,
-		     (u64)tr->data_size, (u64)tr->offsets_size);
-
-	{
-		struct binder_transaction_log_entry *fe;
-
-		fe = binder_transaction_log_add(&binder_transaction_log_failed);
-		*fe = *e;
-	}
-
-	BUG_ON(thread->return_error != BR_OK);
-	if (in_reply_to) {
-		thread->return_error = BR_TRANSACTION_COMPLETE;
-		binder_send_failed_reply(in_reply_to, return_error);
-	} else
-		thread->return_error = return_error;
-}
-
-static int binder_thread_write(struct binder_proc *proc,
-			struct binder_thread *thread,
-			binder_uintptr_t binder_buffer, size_t size,
-			binder_size_t *consumed)
-{
-	uint32_t cmd;
-	void __user *buffer = (void __user *)(uintptr_t)binder_buffer;
-	void __user *ptr = buffer + *consumed;
-	void __user *end = buffer + size;
-
-	while (ptr < end && thread->return_error == BR_OK) {
-		if (get_user(cmd, (uint32_t __user *)ptr))
-			return -EFAULT;
-		ptr += sizeof(uint32_t);
-		trace_binder_command(cmd);
-		if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.bc)) {
-			binder_stats.bc[_IOC_NR(cmd)]++;
-			proc->stats.bc[_IOC_NR(cmd)]++;
-			thread->stats.bc[_IOC_NR(cmd)]++;
-		}
-		switch (cmd) {
-		case BC_INCREFS:
-		case BC_ACQUIRE:
-		case BC_RELEASE:
-		case BC_DECREFS: {
-			uint32_t target;
-			struct binder_ref *ref;
-			const char *debug_string;
-
-			if (get_user(target, (uint32_t __user *)ptr))
-				return -EFAULT;
-			ptr += sizeof(uint32_t);
-			if (target == 0 && binder_context_mgr_node &&
-			    (cmd == BC_INCREFS || cmd == BC_ACQUIRE)) {
-				ref = binder_get_ref_for_node(proc,
-					       binder_context_mgr_node);
-				if (ref->desc != target) {
-					binder_user_error("%d:%d tried to acquire reference to desc 0, got %d instead\n",
-						proc->pid, thread->pid,
-						ref->desc);
-				}
-			} else
-				ref = binder_get_ref(proc, target);
-			if (ref == NULL) {
-				binder_user_error("%d:%d refcount change on invalid ref %d\n",
-					proc->pid, thread->pid, target);
-				break;
-			}
-			switch (cmd) {
-			case BC_INCREFS:
-				debug_string = "IncRefs";
-				binder_inc_ref(ref, 0, NULL);
-				break;
-			case BC_ACQUIRE:
-				debug_string = "Acquire";
-				binder_inc_ref(ref, 1, NULL);
-				break;
-			case BC_RELEASE:
-				debug_string = "Release";
-				binder_dec_ref(ref, 1);
-				break;
-			case BC_DECREFS:
-			default:
-				debug_string = "DecRefs";
-				binder_dec_ref(ref, 0);
-				break;
-			}
-			binder_debug(BINDER_DEBUG_USER_REFS,
-				     "%d:%d %s ref %d desc %d s %d w %d for node %d\n",
-				     proc->pid, thread->pid, debug_string, ref->debug_id,
-				     ref->desc, ref->strong, ref->weak, ref->node->debug_id);
-			break;
-		}
-		case BC_INCREFS_DONE:
-		case BC_ACQUIRE_DONE: {
-			binder_uintptr_t node_ptr;
-			binder_uintptr_t cookie;
-			struct binder_node *node;
-
-			if (get_user(node_ptr, (binder_uintptr_t __user *)ptr))
-				return -EFAULT;
-			ptr += sizeof(binder_uintptr_t);
-			if (get_user(cookie, (binder_uintptr_t __user *)ptr))
-				return -EFAULT;
-			ptr += sizeof(binder_uintptr_t);
-			node = binder_get_node(proc, node_ptr);
-			if (node == NULL) {
-				binder_user_error("%d:%d %s u%016llx no match\n",
-					proc->pid, thread->pid,
-					cmd == BC_INCREFS_DONE ?
-					"BC_INCREFS_DONE" :
-					"BC_ACQUIRE_DONE",
-					(u64)node_ptr);
-				break;
-			}
-			if (cookie != node->cookie) {
-				binder_user_error("%d:%d %s u%016llx node %d cookie mismatch %016llx != %016llx\n",
-					proc->pid, thread->pid,
-					cmd == BC_INCREFS_DONE ?
-					"BC_INCREFS_DONE" : "BC_ACQUIRE_DONE",
-					(u64)node_ptr, node->debug_id,
-					(u64)cookie, (u64)node->cookie);
-				break;
-			}
-			if (cmd == BC_ACQUIRE_DONE) {
-				if (node->pending_strong_ref == 0) {
-					binder_user_error("%d:%d BC_ACQUIRE_DONE node %d has no pending acquire request\n",
-						proc->pid, thread->pid,
-						node->debug_id);
-					break;
-				}
-				node->pending_strong_ref = 0;
-			} else {
-				if (node->pending_weak_ref == 0) {
-					binder_user_error("%d:%d BC_INCREFS_DONE node %d has no pending increfs request\n",
-						proc->pid, thread->pid,
-						node->debug_id);
-					break;
-				}
-				node->pending_weak_ref = 0;
-			}
-			binder_dec_node(node, cmd == BC_ACQUIRE_DONE, 0);
-			binder_debug(BINDER_DEBUG_USER_REFS,
-				     "%d:%d %s node %d ls %d lw %d\n",
-				     proc->pid, thread->pid,
-				     cmd == BC_INCREFS_DONE ? "BC_INCREFS_DONE" : "BC_ACQUIRE_DONE",
-				     node->debug_id, node->local_strong_refs, node->local_weak_refs);
-			break;
-		}
-		case BC_ATTEMPT_ACQUIRE:
-			pr_err("BC_ATTEMPT_ACQUIRE not supported\n");
-			return -EINVAL;
-		case BC_ACQUIRE_RESULT:
-			pr_err("BC_ACQUIRE_RESULT not supported\n");
-			return -EINVAL;
-
-		case BC_FREE_BUFFER: {
-			binder_uintptr_t data_ptr;
-			struct binder_buffer *buffer;
-
-			if (get_user(data_ptr, (binder_uintptr_t __user *)ptr))
-				return -EFAULT;
-			ptr += sizeof(binder_uintptr_t);
-
-			buffer = binder_buffer_lookup(proc, data_ptr);
-			if (buffer == NULL) {
-				binder_user_error("%d:%d BC_FREE_BUFFER u%016llx no match\n",
-					proc->pid, thread->pid, (u64)data_ptr);
-				break;
-			}
-			if (!buffer->allow_user_free) {
-				binder_user_error("%d:%d BC_FREE_BUFFER u%016llx matched unreturned buffer\n",
-					proc->pid, thread->pid, (u64)data_ptr);
-				break;
-			}
-			binder_debug(BINDER_DEBUG_FREE_BUFFER,
-				     "%d:%d BC_FREE_BUFFER u%016llx found buffer %d for %s transaction\n",
-				     proc->pid, thread->pid, (u64)data_ptr,
-				     buffer->debug_id,
-				     buffer->transaction ? "active" : "finished");
-
-			if (buffer->transaction) {
-				buffer->transaction->buffer = NULL;
-				buffer->transaction = NULL;
-			}
-			if (buffer->async_transaction && buffer->target_node) {
-				BUG_ON(!buffer->target_node->has_async_transaction);
-				if (list_empty(&buffer->target_node->async_todo))
-					buffer->target_node->has_async_transaction = 0;
-				else
-					list_move_tail(buffer->target_node->async_todo.next, &thread->todo);
-			}
-			trace_binder_transaction_buffer_release(buffer);
-			binder_transaction_buffer_release(proc, buffer, NULL);
-			binder_free_buf(proc, buffer);
-			break;
-		}
-
-		case BC_TRANSACTION:
-		case BC_REPLY: {
-			struct binder_transaction_data tr;
-
-			if (copy_from_user(&tr, ptr, sizeof(tr)))
-				return -EFAULT;
-			ptr += sizeof(tr);
-			binder_transaction(proc, thread, &tr, cmd == BC_REPLY);
-			break;
-		}
-
-		case BC_REGISTER_LOOPER:
-			binder_debug(BINDER_DEBUG_THREADS,
-				     "%d:%d BC_REGISTER_LOOPER\n",
-				     proc->pid, thread->pid);
-			if (thread->looper & BINDER_LOOPER_STATE_ENTERED) {
-				thread->looper |= BINDER_LOOPER_STATE_INVALID;
-				binder_user_error("%d:%d ERROR: BC_REGISTER_LOOPER called after BC_ENTER_LOOPER\n",
-					proc->pid, thread->pid);
-			} else if (proc->requested_threads == 0) {
-				thread->looper |= BINDER_LOOPER_STATE_INVALID;
-				binder_user_error("%d:%d ERROR: BC_REGISTER_LOOPER called without request\n",
-					proc->pid, thread->pid);
-			} else {
-				proc->requested_threads--;
-				proc->requested_threads_started++;
-			}
-			thread->looper |= BINDER_LOOPER_STATE_REGISTERED;
-			break;
-		case BC_ENTER_LOOPER:
-			binder_debug(BINDER_DEBUG_THREADS,
-				     "%d:%d BC_ENTER_LOOPER\n",
-				     proc->pid, thread->pid);
-			if (thread->looper & BINDER_LOOPER_STATE_REGISTERED) {
-				thread->looper |= BINDER_LOOPER_STATE_INVALID;
-				binder_user_error("%d:%d ERROR: BC_ENTER_LOOPER called after BC_REGISTER_LOOPER\n",
-					proc->pid, thread->pid);
-			}
-			thread->looper |= BINDER_LOOPER_STATE_ENTERED;
-			break;
-		case BC_EXIT_LOOPER:
-			binder_debug(BINDER_DEBUG_THREADS,
-				     "%d:%d BC_EXIT_LOOPER\n",
-				     proc->pid, thread->pid);
-			thread->looper |= BINDER_LOOPER_STATE_EXITED;
-			break;
-
-		case BC_REQUEST_DEATH_NOTIFICATION:
-		case BC_CLEAR_DEATH_NOTIFICATION: {
-			uint32_t target;
-			binder_uintptr_t cookie;
-			struct binder_ref *ref;
-			struct binder_ref_death *death;
-
-			if (get_user(target, (uint32_t __user *)ptr))
-				return -EFAULT;
-			ptr += sizeof(uint32_t);
-			if (get_user(cookie, (binder_uintptr_t __user *)ptr))
-				return -EFAULT;
-			ptr += sizeof(binder_uintptr_t);
-			ref = binder_get_ref(proc, target);
-			if (ref == NULL) {
-				binder_user_error("%d:%d %s invalid ref %d\n",
-					proc->pid, thread->pid,
-					cmd == BC_REQUEST_DEATH_NOTIFICATION ?
-					"BC_REQUEST_DEATH_NOTIFICATION" :
-					"BC_CLEAR_DEATH_NOTIFICATION",
-					target);
-				break;
-			}
-
-			binder_debug(BINDER_DEBUG_DEATH_NOTIFICATION,
-				     "%d:%d %s %016llx ref %d desc %d s %d w %d for node %d\n",
-				     proc->pid, thread->pid,
-				     cmd == BC_REQUEST_DEATH_NOTIFICATION ?
-				     "BC_REQUEST_DEATH_NOTIFICATION" :
-				     "BC_CLEAR_DEATH_NOTIFICATION",
-				     (u64)cookie, ref->debug_id, ref->desc,
-				     ref->strong, ref->weak, ref->node->debug_id);
-
-			if (cmd == BC_REQUEST_DEATH_NOTIFICATION) {
-				if (ref->death) {
-					binder_user_error("%d:%d BC_REQUEST_DEATH_NOTIFICATION death notification already set\n",
-						proc->pid, thread->pid);
-					break;
-				}
-				death = kzalloc(sizeof(*death), GFP_KERNEL);
-				if (death == NULL) {
-					thread->return_error = BR_ERROR;
-					binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
-						     "%d:%d BC_REQUEST_DEATH_NOTIFICATION failed\n",
-						     proc->pid, thread->pid);
-					break;
-				}
-				binder_stats_created(BINDER_STAT_DEATH);
-				INIT_LIST_HEAD(&death->work.entry);
-				death->cookie = cookie;
-				ref->death = death;
-				if (ref->node->proc == NULL) {
-					ref->death->work.type = BINDER_WORK_DEAD_BINDER;
-					if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) {
-						list_add_tail(&ref->death->work.entry, &thread->todo);
-					} else {
-						list_add_tail(&ref->death->work.entry, &proc->todo);
-						wake_up_interruptible(&proc->wait);
-					}
-				}
-			} else {
-				if (ref->death == NULL) {
-					binder_user_error("%d:%d BC_CLEAR_DEATH_NOTIFICATION death notification not active\n",
-						proc->pid, thread->pid);
-					break;
-				}
-				death = ref->death;
-				if (death->cookie != cookie) {
-					binder_user_error("%d:%d BC_CLEAR_DEATH_NOTIFICATION death notification cookie mismatch %016llx != %016llx\n",
-						proc->pid, thread->pid,
-						(u64)death->cookie,
-						(u64)cookie);
-					break;
-				}
-				ref->death = NULL;
-				if (list_empty(&death->work.entry)) {
-					death->work.type = BINDER_WORK_CLEAR_DEATH_NOTIFICATION;
-					if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) {
-						list_add_tail(&death->work.entry, &thread->todo);
-					} else {
-						list_add_tail(&death->work.entry, &proc->todo);
-						wake_up_interruptible(&proc->wait);
-					}
-				} else {
-					BUG_ON(death->work.type != BINDER_WORK_DEAD_BINDER);
-					death->work.type = BINDER_WORK_DEAD_BINDER_AND_CLEAR;
-				}
-			}
-		} break;
-		case BC_DEAD_BINDER_DONE: {
-			struct binder_work *w;
-			binder_uintptr_t cookie;
-			struct binder_ref_death *death = NULL;
-
-			if (get_user(cookie, (binder_uintptr_t __user *)ptr))
-				return -EFAULT;
-
-			ptr += sizeof(void *);
-			list_for_each_entry(w, &proc->delivered_death, entry) {
-				struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work);
-
-				if (tmp_death->cookie == cookie) {
-					death = tmp_death;
-					break;
-				}
-			}
-			binder_debug(BINDER_DEBUG_DEAD_BINDER,
-				     "%d:%d BC_DEAD_BINDER_DONE %016llx found %p\n",
-				     proc->pid, thread->pid, (u64)cookie,
-				     death);
-			if (death == NULL) {
-				binder_user_error("%d:%d BC_DEAD_BINDER_DONE %016llx not found\n",
-					proc->pid, thread->pid, (u64)cookie);
-				break;
-			}
-
-			list_del_init(&death->work.entry);
-			if (death->work.type == BINDER_WORK_DEAD_BINDER_AND_CLEAR) {
-				death->work.type = BINDER_WORK_CLEAR_DEATH_NOTIFICATION;
-				if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) {
-					list_add_tail(&death->work.entry, &thread->todo);
-				} else {
-					list_add_tail(&death->work.entry, &proc->todo);
-					wake_up_interruptible(&proc->wait);
-				}
-			}
-		} break;
-
-		default:
-			pr_err("%d:%d unknown command %d\n",
-			       proc->pid, thread->pid, cmd);
-			return -EINVAL;
-		}
-		*consumed = ptr - buffer;
-	}
-	return 0;
-}
-
-static void binder_stat_br(struct binder_proc *proc,
-			   struct binder_thread *thread, uint32_t cmd)
-{
-	trace_binder_return(cmd);
-	if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.br)) {
-		binder_stats.br[_IOC_NR(cmd)]++;
-		proc->stats.br[_IOC_NR(cmd)]++;
-		thread->stats.br[_IOC_NR(cmd)]++;
-	}
-}
-
-static int binder_has_proc_work(struct binder_proc *proc,
-				struct binder_thread *thread)
-{
-	return !list_empty(&proc->todo) ||
-		(thread->looper & BINDER_LOOPER_STATE_NEED_RETURN);
-}
-
-static int binder_has_thread_work(struct binder_thread *thread)
-{
-	return !list_empty(&thread->todo) || thread->return_error != BR_OK ||
-		(thread->looper & BINDER_LOOPER_STATE_NEED_RETURN);
-}
-
-static int binder_thread_read(struct binder_proc *proc,
-			      struct binder_thread *thread,
-			      binder_uintptr_t binder_buffer, size_t size,
-			      binder_size_t *consumed, int non_block)
-{
-	void __user *buffer = (void __user *)(uintptr_t)binder_buffer;
-	void __user *ptr = buffer + *consumed;
-	void __user *end = buffer + size;
-
-	int ret = 0;
-	int wait_for_proc_work;
-
-	if (*consumed == 0) {
-		if (put_user(BR_NOOP, (uint32_t __user *)ptr))
-			return -EFAULT;
-		ptr += sizeof(uint32_t);
-	}
-
-retry:
-	wait_for_proc_work = thread->transaction_stack == NULL &&
-				list_empty(&thread->todo);
-
-	if (thread->return_error != BR_OK && ptr < end) {
-		if (thread->return_error2 != BR_OK) {
-			if (put_user(thread->return_error2, (uint32_t __user *)ptr))
-				return -EFAULT;
-			ptr += sizeof(uint32_t);
-			binder_stat_br(proc, thread, thread->return_error2);
-			if (ptr == end)
-				goto done;
-			thread->return_error2 = BR_OK;
-		}
-		if (put_user(thread->return_error, (uint32_t __user *)ptr))
-			return -EFAULT;
-		ptr += sizeof(uint32_t);
-		binder_stat_br(proc, thread, thread->return_error);
-		thread->return_error = BR_OK;
-		goto done;
-	}
-
-
-	thread->looper |= BINDER_LOOPER_STATE_WAITING;
-	if (wait_for_proc_work)
-		proc->ready_threads++;
-
-	binder_unlock(__func__);
-
-	trace_binder_wait_for_work(wait_for_proc_work,
-				   !!thread->transaction_stack,
-				   !list_empty(&thread->todo));
-	if (wait_for_proc_work) {
-		if (!(thread->looper & (BINDER_LOOPER_STATE_REGISTERED |
-					BINDER_LOOPER_STATE_ENTERED))) {
-			binder_user_error("%d:%d ERROR: Thread waiting for process work before calling BC_REGISTER_LOOPER or BC_ENTER_LOOPER (state %x)\n",
-				proc->pid, thread->pid, thread->looper);
-			wait_event_interruptible(binder_user_error_wait,
-						 binder_stop_on_user_error < 2);
-		}
-		binder_set_nice(proc->default_priority);
-		if (non_block) {
-			if (!binder_has_proc_work(proc, thread))
-				ret = -EAGAIN;
-		} else
-			ret = wait_event_freezable_exclusive(proc->wait, binder_has_proc_work(proc, thread));
-	} else {
-		if (non_block) {
-			if (!binder_has_thread_work(thread))
-				ret = -EAGAIN;
-		} else
-			ret = wait_event_freezable(thread->wait, binder_has_thread_work(thread));
-	}
-
-	binder_lock(__func__);
-
-	if (wait_for_proc_work)
-		proc->ready_threads--;
-	thread->looper &= ~BINDER_LOOPER_STATE_WAITING;
-
-	if (ret)
-		return ret;
-
-	while (1) {
-		uint32_t cmd;
-		struct binder_transaction_data tr;
-		struct binder_work *w;
-		struct binder_transaction *t = NULL;
-
-		if (!list_empty(&thread->todo)) {
-			w = list_first_entry(&thread->todo, struct binder_work,
-					     entry);
-		} else if (!list_empty(&proc->todo) && wait_for_proc_work) {
-			w = list_first_entry(&proc->todo, struct binder_work,
-					     entry);
-		} else {
-			/* no data added */
-			if (ptr - buffer == 4 &&
-			    !(thread->looper & BINDER_LOOPER_STATE_NEED_RETURN))
-				goto retry;
-			break;
-		}
-
-		if (end - ptr < sizeof(tr) + 4)
-			break;
-
-		switch (w->type) {
-		case BINDER_WORK_TRANSACTION: {
-			t = container_of(w, struct binder_transaction, work);
-		} break;
-		case BINDER_WORK_TRANSACTION_COMPLETE: {
-			cmd = BR_TRANSACTION_COMPLETE;
-			if (put_user(cmd, (uint32_t __user *)ptr))
-				return -EFAULT;
-			ptr += sizeof(uint32_t);
-
-			binder_stat_br(proc, thread, cmd);
-			binder_debug(BINDER_DEBUG_TRANSACTION_COMPLETE,
-				     "%d:%d BR_TRANSACTION_COMPLETE\n",
-				     proc->pid, thread->pid);
-
-			list_del(&w->entry);
-			kfree(w);
-			binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE);
-		} break;
-		case BINDER_WORK_NODE: {
-			struct binder_node *node = container_of(w, struct binder_node, work);
-			uint32_t cmd = BR_NOOP;
-			const char *cmd_name;
-			int strong = node->internal_strong_refs || node->local_strong_refs;
-			int weak = !hlist_empty(&node->refs) || node->local_weak_refs || strong;
-
-			if (weak && !node->has_weak_ref) {
-				cmd = BR_INCREFS;
-				cmd_name = "BR_INCREFS";
-				node->has_weak_ref = 1;
-				node->pending_weak_ref = 1;
-				node->local_weak_refs++;
-			} else if (strong && !node->has_strong_ref) {
-				cmd = BR_ACQUIRE;
-				cmd_name = "BR_ACQUIRE";
-				node->has_strong_ref = 1;
-				node->pending_strong_ref = 1;
-				node->local_strong_refs++;
-			} else if (!strong && node->has_strong_ref) {
-				cmd = BR_RELEASE;
-				cmd_name = "BR_RELEASE";
-				node->has_strong_ref = 0;
-			} else if (!weak && node->has_weak_ref) {
-				cmd = BR_DECREFS;
-				cmd_name = "BR_DECREFS";
-				node->has_weak_ref = 0;
-			}
-			if (cmd != BR_NOOP) {
-				if (put_user(cmd, (uint32_t __user *)ptr))
-					return -EFAULT;
-				ptr += sizeof(uint32_t);
-				if (put_user(node->ptr,
-					     (binder_uintptr_t __user *)ptr))
-					return -EFAULT;
-				ptr += sizeof(binder_uintptr_t);
-				if (put_user(node->cookie,
-					     (binder_uintptr_t __user *)ptr))
-					return -EFAULT;
-				ptr += sizeof(binder_uintptr_t);
-
-				binder_stat_br(proc, thread, cmd);
-				binder_debug(BINDER_DEBUG_USER_REFS,
-					     "%d:%d %s %d u%016llx c%016llx\n",
-					     proc->pid, thread->pid, cmd_name,
-					     node->debug_id,
-					     (u64)node->ptr, (u64)node->cookie);
-			} else {
-				list_del_init(&w->entry);
-				if (!weak && !strong) {
-					binder_debug(BINDER_DEBUG_INTERNAL_REFS,
-						     "%d:%d node %d u%016llx c%016llx deleted\n",
-						     proc->pid, thread->pid,
-						     node->debug_id,
-						     (u64)node->ptr,
-						     (u64)node->cookie);
-					rb_erase(&node->rb_node, &proc->nodes);
-					kfree(node);
-					binder_stats_deleted(BINDER_STAT_NODE);
-				} else {
-					binder_debug(BINDER_DEBUG_INTERNAL_REFS,
-						     "%d:%d node %d u%016llx c%016llx state unchanged\n",
-						     proc->pid, thread->pid,
-						     node->debug_id,
-						     (u64)node->ptr,
-						     (u64)node->cookie);
-				}
-			}
-		} break;
-		case BINDER_WORK_DEAD_BINDER:
-		case BINDER_WORK_DEAD_BINDER_AND_CLEAR:
-		case BINDER_WORK_CLEAR_DEATH_NOTIFICATION: {
-			struct binder_ref_death *death;
-			uint32_t cmd;
-
-			death = container_of(w, struct binder_ref_death, work);
-			if (w->type == BINDER_WORK_CLEAR_DEATH_NOTIFICATION)
-				cmd = BR_CLEAR_DEATH_NOTIFICATION_DONE;
-			else
-				cmd = BR_DEAD_BINDER;
-			if (put_user(cmd, (uint32_t __user *)ptr))
-				return -EFAULT;
-			ptr += sizeof(uint32_t);
-			if (put_user(death->cookie,
-				     (binder_uintptr_t __user *)ptr))
-				return -EFAULT;
-			ptr += sizeof(binder_uintptr_t);
-			binder_stat_br(proc, thread, cmd);
-			binder_debug(BINDER_DEBUG_DEATH_NOTIFICATION,
-				     "%d:%d %s %016llx\n",
-				      proc->pid, thread->pid,
-				      cmd == BR_DEAD_BINDER ?
-				      "BR_DEAD_BINDER" :
-				      "BR_CLEAR_DEATH_NOTIFICATION_DONE",
-				      (u64)death->cookie);
-
-			if (w->type == BINDER_WORK_CLEAR_DEATH_NOTIFICATION) {
-				list_del(&w->entry);
-				kfree(death);
-				binder_stats_deleted(BINDER_STAT_DEATH);
-			} else
-				list_move(&w->entry, &proc->delivered_death);
-			if (cmd == BR_DEAD_BINDER)
-				goto done; /* DEAD_BINDER notifications can cause transactions */
-		} break;
-		}
-
-		if (!t)
-			continue;
-
-		BUG_ON(t->buffer == NULL);
-		if (t->buffer->target_node) {
-			struct binder_node *target_node = t->buffer->target_node;
-
-			tr.target.ptr = target_node->ptr;
-			tr.cookie =  target_node->cookie;
-			t->saved_priority = task_nice(current);
-			if (t->priority < target_node->min_priority &&
-			    !(t->flags & TF_ONE_WAY))
-				binder_set_nice(t->priority);
-			else if (!(t->flags & TF_ONE_WAY) ||
-				 t->saved_priority > target_node->min_priority)
-				binder_set_nice(target_node->min_priority);
-			cmd = BR_TRANSACTION;
-		} else {
-			tr.target.ptr = 0;
-			tr.cookie = 0;
-			cmd = BR_REPLY;
-		}
-		tr.code = t->code;
-		tr.flags = t->flags;
-		tr.sender_euid = from_kuid(current_user_ns(), t->sender_euid);
-
-		if (t->from) {
-			struct task_struct *sender = t->from->proc->tsk;
-
-			tr.sender_pid = task_tgid_nr_ns(sender,
-							task_active_pid_ns(current));
-		} else {
-			tr.sender_pid = 0;
-		}
-
-		tr.data_size = t->buffer->data_size;
-		tr.offsets_size = t->buffer->offsets_size;
-		tr.data.ptr.buffer = (binder_uintptr_t)(
-					(uintptr_t)t->buffer->data +
-					proc->user_buffer_offset);
-		tr.data.ptr.offsets = tr.data.ptr.buffer +
-					ALIGN(t->buffer->data_size,
-					    sizeof(void *));
-
-		if (put_user(cmd, (uint32_t __user *)ptr))
-			return -EFAULT;
-		ptr += sizeof(uint32_t);
-		if (copy_to_user(ptr, &tr, sizeof(tr)))
-			return -EFAULT;
-		ptr += sizeof(tr);
-
-		trace_binder_transaction_received(t);
-		binder_stat_br(proc, thread, cmd);
-		binder_debug(BINDER_DEBUG_TRANSACTION,
-			     "%d:%d %s %d %d:%d, cmd %d size %zd-%zd ptr %016llx-%016llx\n",
-			     proc->pid, thread->pid,
-			     (cmd == BR_TRANSACTION) ? "BR_TRANSACTION" :
-			     "BR_REPLY",
-			     t->debug_id, t->from ? t->from->proc->pid : 0,
-			     t->from ? t->from->pid : 0, cmd,
-			     t->buffer->data_size, t->buffer->offsets_size,
-			     (u64)tr.data.ptr.buffer, (u64)tr.data.ptr.offsets);
-
-		list_del(&t->work.entry);
-		t->buffer->allow_user_free = 1;
-		if (cmd == BR_TRANSACTION && !(t->flags & TF_ONE_WAY)) {
-			t->to_parent = thread->transaction_stack;
-			t->to_thread = thread;
-			thread->transaction_stack = t;
-		} else {
-			t->buffer->transaction = NULL;
-			kfree(t);
-			binder_stats_deleted(BINDER_STAT_TRANSACTION);
-		}
-		break;
-	}
-
-done:
-
-	*consumed = ptr - buffer;
-	if (proc->requested_threads + proc->ready_threads == 0 &&
-	    proc->requested_threads_started < proc->max_threads &&
-	    (thread->looper & (BINDER_LOOPER_STATE_REGISTERED |
-	     BINDER_LOOPER_STATE_ENTERED)) /* the user-space code fails to */
-	     /*spawn a new thread if we leave this out */) {
-		proc->requested_threads++;
-		binder_debug(BINDER_DEBUG_THREADS,
-			     "%d:%d BR_SPAWN_LOOPER\n",
-			     proc->pid, thread->pid);
-		if (put_user(BR_SPAWN_LOOPER, (uint32_t __user *)buffer))
-			return -EFAULT;
-		binder_stat_br(proc, thread, BR_SPAWN_LOOPER);
-	}
-	return 0;
-}
-
-static void binder_release_work(struct list_head *list)
-{
-	struct binder_work *w;
-
-	while (!list_empty(list)) {
-		w = list_first_entry(list, struct binder_work, entry);
-		list_del_init(&w->entry);
-		switch (w->type) {
-		case BINDER_WORK_TRANSACTION: {
-			struct binder_transaction *t;
-
-			t = container_of(w, struct binder_transaction, work);
-			if (t->buffer->target_node &&
-			    !(t->flags & TF_ONE_WAY)) {
-				binder_send_failed_reply(t, BR_DEAD_REPLY);
-			} else {
-				binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
-					"undelivered transaction %d\n",
-					t->debug_id);
-				t->buffer->transaction = NULL;
-				kfree(t);
-				binder_stats_deleted(BINDER_STAT_TRANSACTION);
-			}
-		} break;
-		case BINDER_WORK_TRANSACTION_COMPLETE: {
-			binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
-				"undelivered TRANSACTION_COMPLETE\n");
-			kfree(w);
-			binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE);
-		} break;
-		case BINDER_WORK_DEAD_BINDER_AND_CLEAR:
-		case BINDER_WORK_CLEAR_DEATH_NOTIFICATION: {
-			struct binder_ref_death *death;
-
-			death = container_of(w, struct binder_ref_death, work);
-			binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
-				"undelivered death notification, %016llx\n",
-				(u64)death->cookie);
-			kfree(death);
-			binder_stats_deleted(BINDER_STAT_DEATH);
-		} break;
-		default:
-			pr_err("unexpected work type, %d, not freed\n",
-			       w->type);
-			break;
-		}
-	}
-
-}
-
-static struct binder_thread *binder_get_thread(struct binder_proc *proc)
-{
-	struct binder_thread *thread = NULL;
-	struct rb_node *parent = NULL;
-	struct rb_node **p = &proc->threads.rb_node;
-
-	while (*p) {
-		parent = *p;
-		thread = rb_entry(parent, struct binder_thread, rb_node);
-
-		if (current->pid < thread->pid)
-			p = &(*p)->rb_left;
-		else if (current->pid > thread->pid)
-			p = &(*p)->rb_right;
-		else
-			break;
-	}
-	if (*p == NULL) {
-		thread = kzalloc(sizeof(*thread), GFP_KERNEL);
-		if (thread == NULL)
-			return NULL;
-		binder_stats_created(BINDER_STAT_THREAD);
-		thread->proc = proc;
-		thread->pid = current->pid;
-		init_waitqueue_head(&thread->wait);
-		INIT_LIST_HEAD(&thread->todo);
-		rb_link_node(&thread->rb_node, parent, p);
-		rb_insert_color(&thread->rb_node, &proc->threads);
-		thread->looper |= BINDER_LOOPER_STATE_NEED_RETURN;
-		thread->return_error = BR_OK;
-		thread->return_error2 = BR_OK;
-	}
-	return thread;
-}
-
-static int binder_free_thread(struct binder_proc *proc,
-			      struct binder_thread *thread)
-{
-	struct binder_transaction *t;
-	struct binder_transaction *send_reply = NULL;
-	int active_transactions = 0;
-
-	rb_erase(&thread->rb_node, &proc->threads);
-	t = thread->transaction_stack;
-	if (t && t->to_thread == thread)
-		send_reply = t;
-	while (t) {
-		active_transactions++;
-		binder_debug(BINDER_DEBUG_DEAD_TRANSACTION,
-			     "release %d:%d transaction %d %s, still active\n",
-			      proc->pid, thread->pid,
-			     t->debug_id,
-			     (t->to_thread == thread) ? "in" : "out");
-
-		if (t->to_thread == thread) {
-			t->to_proc = NULL;
-			t->to_thread = NULL;
-			if (t->buffer) {
-				t->buffer->transaction = NULL;
-				t->buffer = NULL;
-			}
-			t = t->to_parent;
-		} else if (t->from == thread) {
-			t->from = NULL;
-			t = t->from_parent;
-		} else
-			BUG();
-	}
-	if (send_reply)
-		binder_send_failed_reply(send_reply, BR_DEAD_REPLY);
-	binder_release_work(&thread->todo);
-	kfree(thread);
-	binder_stats_deleted(BINDER_STAT_THREAD);
-	return active_transactions;
-}
-
-static unsigned int binder_poll(struct file *filp,
-				struct poll_table_struct *wait)
-{
-	struct binder_proc *proc = filp->private_data;
-	struct binder_thread *thread = NULL;
-	int wait_for_proc_work;
-
-	binder_lock(__func__);
-
-	thread = binder_get_thread(proc);
-
-	wait_for_proc_work = thread->transaction_stack == NULL &&
-		list_empty(&thread->todo) && thread->return_error == BR_OK;
-
-	binder_unlock(__func__);
-
-	if (wait_for_proc_work) {
-		if (binder_has_proc_work(proc, thread))
-			return POLLIN;
-		poll_wait(filp, &proc->wait, wait);
-		if (binder_has_proc_work(proc, thread))
-			return POLLIN;
-	} else {
-		if (binder_has_thread_work(thread))
-			return POLLIN;
-		poll_wait(filp, &thread->wait, wait);
-		if (binder_has_thread_work(thread))
-			return POLLIN;
-	}
-	return 0;
-}
-
-static int binder_ioctl_write_read(struct file *filp,
-				unsigned int cmd, unsigned long arg,
-				struct binder_thread *thread)
-{
-	int ret = 0;
-	struct binder_proc *proc = filp->private_data;
-	unsigned int size = _IOC_SIZE(cmd);
-	void __user *ubuf = (void __user *)arg;
-	struct binder_write_read bwr;
-
-	if (size != sizeof(struct binder_write_read)) {
-		ret = -EINVAL;
-		goto out;
-	}
-	if (copy_from_user(&bwr, ubuf, sizeof(bwr))) {
-		ret = -EFAULT;
-		goto out;
-	}
-	binder_debug(BINDER_DEBUG_READ_WRITE,
-		     "%d:%d write %lld at %016llx, read %lld at %016llx\n",
-		     proc->pid, thread->pid,
-		     (u64)bwr.write_size, (u64)bwr.write_buffer,
-		     (u64)bwr.read_size, (u64)bwr.read_buffer);
-
-	if (bwr.write_size > 0) {
-		ret = binder_thread_write(proc, thread,
-					  bwr.write_buffer,
-					  bwr.write_size,
-					  &bwr.write_consumed);
-		trace_binder_write_done(ret);
-		if (ret < 0) {
-			bwr.read_consumed = 0;
-			if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
-				ret = -EFAULT;
-			goto out;
-		}
-	}
-	if (bwr.read_size > 0) {
-		ret = binder_thread_read(proc, thread, bwr.read_buffer,
-					 bwr.read_size,
-					 &bwr.read_consumed,
-					 filp->f_flags & O_NONBLOCK);
-		trace_binder_read_done(ret);
-		if (!list_empty(&proc->todo))
-			wake_up_interruptible(&proc->wait);
-		if (ret < 0) {
-			if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
-				ret = -EFAULT;
-			goto out;
-		}
-	}
-	binder_debug(BINDER_DEBUG_READ_WRITE,
-		     "%d:%d wrote %lld of %lld, read return %lld of %lld\n",
-		     proc->pid, thread->pid,
-		     (u64)bwr.write_consumed, (u64)bwr.write_size,
-		     (u64)bwr.read_consumed, (u64)bwr.read_size);
-	if (copy_to_user(ubuf, &bwr, sizeof(bwr))) {
-		ret = -EFAULT;
-		goto out;
-	}
-out:
-	return ret;
-}
-
-static int binder_ioctl_set_ctx_mgr(struct file *filp)
-{
-	int ret = 0;
-	struct binder_proc *proc = filp->private_data;
-	kuid_t curr_euid = current_euid();
-
-	if (binder_context_mgr_node != NULL) {
-		pr_err("BINDER_SET_CONTEXT_MGR already set\n");
-		ret = -EBUSY;
-		goto out;
-	}
-	if (uid_valid(binder_context_mgr_uid)) {
-		if (!uid_eq(binder_context_mgr_uid, curr_euid)) {
-			pr_err("BINDER_SET_CONTEXT_MGR bad uid %d != %d\n",
-			       from_kuid(&init_user_ns, curr_euid),
-			       from_kuid(&init_user_ns,
-					binder_context_mgr_uid));
-			ret = -EPERM;
-			goto out;
-		}
-	} else {
-		binder_context_mgr_uid = curr_euid;
-	}
-	binder_context_mgr_node = binder_new_node(proc, 0, 0);
-	if (binder_context_mgr_node == NULL) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	binder_context_mgr_node->local_weak_refs++;
-	binder_context_mgr_node->local_strong_refs++;
-	binder_context_mgr_node->has_strong_ref = 1;
-	binder_context_mgr_node->has_weak_ref = 1;
-out:
-	return ret;
-}
-
-static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
-{
-	int ret;
-	struct binder_proc *proc = filp->private_data;
-	struct binder_thread *thread;
-	unsigned int size = _IOC_SIZE(cmd);
-	void __user *ubuf = (void __user *)arg;
-
-	/*pr_info("binder_ioctl: %d:%d %x %lx\n",
-			proc->pid, current->pid, cmd, arg);*/
-
-	trace_binder_ioctl(cmd, arg);
-
-	ret = wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
-	if (ret)
-		goto err_unlocked;
-
-	binder_lock(__func__);
-	thread = binder_get_thread(proc);
-	if (thread == NULL) {
-		ret = -ENOMEM;
-		goto err;
-	}
-
-	switch (cmd) {
-	case BINDER_WRITE_READ:
-		ret = binder_ioctl_write_read(filp, cmd, arg, thread);
-		if (ret)
-			goto err;
-		break;
-	case BINDER_SET_MAX_THREADS:
-		if (copy_from_user(&proc->max_threads, ubuf, sizeof(proc->max_threads))) {
-			ret = -EINVAL;
-			goto err;
-		}
-		break;
-	case BINDER_SET_CONTEXT_MGR:
-		ret = binder_ioctl_set_ctx_mgr(filp);
-		if (ret)
-			goto err;
-		break;
-	case BINDER_THREAD_EXIT:
-		binder_debug(BINDER_DEBUG_THREADS, "%d:%d exit\n",
-			     proc->pid, thread->pid);
-		binder_free_thread(proc, thread);
-		thread = NULL;
-		break;
-	case BINDER_VERSION: {
-		struct binder_version __user *ver = ubuf;
-
-		if (size != sizeof(struct binder_version)) {
-			ret = -EINVAL;
-			goto err;
-		}
-		if (put_user(BINDER_CURRENT_PROTOCOL_VERSION,
-			     &ver->protocol_version)) {
-			ret = -EINVAL;
-			goto err;
-		}
-		break;
-	}
-	default:
-		ret = -EINVAL;
-		goto err;
-	}
-	ret = 0;
-err:
-	if (thread)
-		thread->looper &= ~BINDER_LOOPER_STATE_NEED_RETURN;
-	binder_unlock(__func__);
-	wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
-	if (ret && ret != -ERESTARTSYS)
-		pr_info("%d:%d ioctl %x %lx returned %d\n", proc->pid, current->pid, cmd, arg, ret);
-err_unlocked:
-	trace_binder_ioctl_done(ret);
-	return ret;
-}
-
-static void binder_vma_open(struct vm_area_struct *vma)
-{
-	struct binder_proc *proc = vma->vm_private_data;
-
-	binder_debug(BINDER_DEBUG_OPEN_CLOSE,
-		     "%d open vm area %lx-%lx (%ld K) vma %lx pagep %lx\n",
-		     proc->pid, vma->vm_start, vma->vm_end,
-		     (vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags,
-		     (unsigned long)pgprot_val(vma->vm_page_prot));
-}
-
-static void binder_vma_close(struct vm_area_struct *vma)
-{
-	struct binder_proc *proc = vma->vm_private_data;
-
-	binder_debug(BINDER_DEBUG_OPEN_CLOSE,
-		     "%d close vm area %lx-%lx (%ld K) vma %lx pagep %lx\n",
-		     proc->pid, vma->vm_start, vma->vm_end,
-		     (vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags,
-		     (unsigned long)pgprot_val(vma->vm_page_prot));
-	proc->vma = NULL;
-	proc->vma_vm_mm = NULL;
-	binder_defer_work(proc, BINDER_DEFERRED_PUT_FILES);
-}
-
-static int binder_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	return VM_FAULT_SIGBUS;
-}
-
-static struct vm_operations_struct binder_vm_ops = {
-	.open = binder_vma_open,
-	.close = binder_vma_close,
-	.fault = binder_vm_fault,
-};
-
-static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
-{
-	int ret;
-	struct vm_struct *area;
-	struct binder_proc *proc = filp->private_data;
-	const char *failure_string;
-	struct binder_buffer *buffer;
-
-	if (proc->tsk != current)
-		return -EINVAL;
-
-	if ((vma->vm_end - vma->vm_start) > SZ_4M)
-		vma->vm_end = vma->vm_start + SZ_4M;
-
-	binder_debug(BINDER_DEBUG_OPEN_CLOSE,
-		     "binder_mmap: %d %lx-%lx (%ld K) vma %lx pagep %lx\n",
-		     proc->pid, vma->vm_start, vma->vm_end,
-		     (vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags,
-		     (unsigned long)pgprot_val(vma->vm_page_prot));
-
-	if (vma->vm_flags & FORBIDDEN_MMAP_FLAGS) {
-		ret = -EPERM;
-		failure_string = "bad vm_flags";
-		goto err_bad_arg;
-	}
-	vma->vm_flags = (vma->vm_flags | VM_DONTCOPY) & ~VM_MAYWRITE;
-
-	mutex_lock(&binder_mmap_lock);
-	if (proc->buffer) {
-		ret = -EBUSY;
-		failure_string = "already mapped";
-		goto err_already_mapped;
-	}
-
-	area = get_vm_area(vma->vm_end - vma->vm_start, VM_IOREMAP);
-	if (area == NULL) {
-		ret = -ENOMEM;
-		failure_string = "get_vm_area";
-		goto err_get_vm_area_failed;
-	}
-	proc->buffer = area->addr;
-	proc->user_buffer_offset = vma->vm_start - (uintptr_t)proc->buffer;
-	mutex_unlock(&binder_mmap_lock);
-
-#ifdef CONFIG_CPU_CACHE_VIPT
-	if (cache_is_vipt_aliasing()) {
-		while (CACHE_COLOUR((vma->vm_start ^ (uint32_t)proc->buffer))) {
-			pr_info("binder_mmap: %d %lx-%lx maps %p bad alignment\n", proc->pid, vma->vm_start, vma->vm_end, proc->buffer);
-			vma->vm_start += PAGE_SIZE;
-		}
-	}
-#endif
-	proc->pages = kzalloc(sizeof(proc->pages[0]) * ((vma->vm_end - vma->vm_start) / PAGE_SIZE), GFP_KERNEL);
-	if (proc->pages == NULL) {
-		ret = -ENOMEM;
-		failure_string = "alloc page array";
-		goto err_alloc_pages_failed;
-	}
-	proc->buffer_size = vma->vm_end - vma->vm_start;
-
-	vma->vm_ops = &binder_vm_ops;
-	vma->vm_private_data = proc;
-
-	if (binder_update_page_range(proc, 1, proc->buffer, proc->buffer + PAGE_SIZE, vma)) {
-		ret = -ENOMEM;
-		failure_string = "alloc small buf";
-		goto err_alloc_small_buf_failed;
-	}
-	buffer = proc->buffer;
-	INIT_LIST_HEAD(&proc->buffers);
-	list_add(&buffer->entry, &proc->buffers);
-	buffer->free = 1;
-	binder_insert_free_buffer(proc, buffer);
-	proc->free_async_space = proc->buffer_size / 2;
-	barrier();
-	proc->files = get_files_struct(current);
-	proc->vma = vma;
-	proc->vma_vm_mm = vma->vm_mm;
-
-	/*pr_info("binder_mmap: %d %lx-%lx maps %p\n",
-		 proc->pid, vma->vm_start, vma->vm_end, proc->buffer);*/
-	return 0;
-
-err_alloc_small_buf_failed:
-	kfree(proc->pages);
-	proc->pages = NULL;
-err_alloc_pages_failed:
-	mutex_lock(&binder_mmap_lock);
-	vfree(proc->buffer);
-	proc->buffer = NULL;
-err_get_vm_area_failed:
-err_already_mapped:
-	mutex_unlock(&binder_mmap_lock);
-err_bad_arg:
-	pr_err("binder_mmap: %d %lx-%lx %s failed %d\n",
-	       proc->pid, vma->vm_start, vma->vm_end, failure_string, ret);
-	return ret;
-}
-
-static int binder_open(struct inode *nodp, struct file *filp)
-{
-	struct binder_proc *proc;
-
-	binder_debug(BINDER_DEBUG_OPEN_CLOSE, "binder_open: %d:%d\n",
-		     current->group_leader->pid, current->pid);
-
-	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
-	if (proc == NULL)
-		return -ENOMEM;
-	get_task_struct(current);
-	proc->tsk = current;
-	INIT_LIST_HEAD(&proc->todo);
-	init_waitqueue_head(&proc->wait);
-	proc->default_priority = task_nice(current);
-
-	binder_lock(__func__);
-
-	binder_stats_created(BINDER_STAT_PROC);
-	hlist_add_head(&proc->proc_node, &binder_procs);
-	proc->pid = current->group_leader->pid;
-	INIT_LIST_HEAD(&proc->delivered_death);
-	filp->private_data = proc;
-
-	binder_unlock(__func__);
-
-	if (binder_debugfs_dir_entry_proc) {
-		char strbuf[11];
-
-		snprintf(strbuf, sizeof(strbuf), "%u", proc->pid);
-		proc->debugfs_entry = debugfs_create_file(strbuf, S_IRUGO,
-			binder_debugfs_dir_entry_proc, proc, &binder_proc_fops);
-	}
-
-	return 0;
-}
-
-static int binder_flush(struct file *filp, fl_owner_t id)
-{
-	struct binder_proc *proc = filp->private_data;
-
-	binder_defer_work(proc, BINDER_DEFERRED_FLUSH);
-
-	return 0;
-}
-
-static void binder_deferred_flush(struct binder_proc *proc)
-{
-	struct rb_node *n;
-	int wake_count = 0;
-
-	for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n)) {
-		struct binder_thread *thread = rb_entry(n, struct binder_thread, rb_node);
-
-		thread->looper |= BINDER_LOOPER_STATE_NEED_RETURN;
-		if (thread->looper & BINDER_LOOPER_STATE_WAITING) {
-			wake_up_interruptible(&thread->wait);
-			wake_count++;
-		}
-	}
-	wake_up_interruptible_all(&proc->wait);
-
-	binder_debug(BINDER_DEBUG_OPEN_CLOSE,
-		     "binder_flush: %d woke %d threads\n", proc->pid,
-		     wake_count);
-}
-
-static int binder_release(struct inode *nodp, struct file *filp)
-{
-	struct binder_proc *proc = filp->private_data;
-
-	debugfs_remove(proc->debugfs_entry);
-	binder_defer_work(proc, BINDER_DEFERRED_RELEASE);
-
-	return 0;
-}
-
-static int binder_node_release(struct binder_node *node, int refs)
-{
-	struct binder_ref *ref;
-	int death = 0;
-
-	list_del_init(&node->work.entry);
-	binder_release_work(&node->async_todo);
-
-	if (hlist_empty(&node->refs)) {
-		kfree(node);
-		binder_stats_deleted(BINDER_STAT_NODE);
-
-		return refs;
-	}
-
-	node->proc = NULL;
-	node->local_strong_refs = 0;
-	node->local_weak_refs = 0;
-	hlist_add_head(&node->dead_node, &binder_dead_nodes);
-
-	hlist_for_each_entry(ref, &node->refs, node_entry) {
-		refs++;
-
-		if (!ref->death)
-			continue;
-
-		death++;
-
-		if (list_empty(&ref->death->work.entry)) {
-			ref->death->work.type = BINDER_WORK_DEAD_BINDER;
-			list_add_tail(&ref->death->work.entry,
-				      &ref->proc->todo);
-			wake_up_interruptible(&ref->proc->wait);
-		} else
-			BUG();
-	}
-
-	binder_debug(BINDER_DEBUG_DEAD_BINDER,
-		     "node %d now dead, refs %d, death %d\n",
-		     node->debug_id, refs, death);
-
-	return refs;
-}
-
-static void binder_deferred_release(struct binder_proc *proc)
-{
-	struct binder_transaction *t;
-	struct rb_node *n;
-	int threads, nodes, incoming_refs, outgoing_refs, buffers,
-		active_transactions, page_count;
-
-	BUG_ON(proc->vma);
-	BUG_ON(proc->files);
-
-	hlist_del(&proc->proc_node);
-
-	if (binder_context_mgr_node && binder_context_mgr_node->proc == proc) {
-		binder_debug(BINDER_DEBUG_DEAD_BINDER,
-			     "%s: %d context_mgr_node gone\n",
-			     __func__, proc->pid);
-		binder_context_mgr_node = NULL;
-	}
-
-	threads = 0;
-	active_transactions = 0;
-	while ((n = rb_first(&proc->threads))) {
-		struct binder_thread *thread;
-
-		thread = rb_entry(n, struct binder_thread, rb_node);
-		threads++;
-		active_transactions += binder_free_thread(proc, thread);
-	}
-
-	nodes = 0;
-	incoming_refs = 0;
-	while ((n = rb_first(&proc->nodes))) {
-		struct binder_node *node;
-
-		node = rb_entry(n, struct binder_node, rb_node);
-		nodes++;
-		rb_erase(&node->rb_node, &proc->nodes);
-		incoming_refs = binder_node_release(node, incoming_refs);
-	}
-
-	outgoing_refs = 0;
-	while ((n = rb_first(&proc->refs_by_desc))) {
-		struct binder_ref *ref;
-
-		ref = rb_entry(n, struct binder_ref, rb_node_desc);
-		outgoing_refs++;
-		binder_delete_ref(ref);
-	}
-
-	binder_release_work(&proc->todo);
-	binder_release_work(&proc->delivered_death);
-
-	buffers = 0;
-	while ((n = rb_first(&proc->allocated_buffers))) {
-		struct binder_buffer *buffer;
-
-		buffer = rb_entry(n, struct binder_buffer, rb_node);
-
-		t = buffer->transaction;
-		if (t) {
-			t->buffer = NULL;
-			buffer->transaction = NULL;
-			pr_err("release proc %d, transaction %d, not freed\n",
-			       proc->pid, t->debug_id);
-			/*BUG();*/
-		}
-
-		binder_free_buf(proc, buffer);
-		buffers++;
-	}
-
-	binder_stats_deleted(BINDER_STAT_PROC);
-
-	page_count = 0;
-	if (proc->pages) {
-		int i;
-
-		for (i = 0; i < proc->buffer_size / PAGE_SIZE; i++) {
-			void *page_addr;
-
-			if (!proc->pages[i])
-				continue;
-
-			page_addr = proc->buffer + i * PAGE_SIZE;
-			binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
-				     "%s: %d: page %d at %p not freed\n",
-				     __func__, proc->pid, i, page_addr);
-			unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
-			__free_page(proc->pages[i]);
-			page_count++;
-		}
-		kfree(proc->pages);
-		vfree(proc->buffer);
-	}
-
-	put_task_struct(proc->tsk);
-
-	binder_debug(BINDER_DEBUG_OPEN_CLOSE,
-		     "%s: %d threads %d, nodes %d (ref %d), refs %d, active transactions %d, buffers %d, pages %d\n",
-		     __func__, proc->pid, threads, nodes, incoming_refs,
-		     outgoing_refs, active_transactions, buffers, page_count);
-
-	kfree(proc);
-}
-
-static void binder_deferred_func(struct work_struct *work)
-{
-	struct binder_proc *proc;
-	struct files_struct *files;
-
-	int defer;
-
-	do {
-		binder_lock(__func__);
-		mutex_lock(&binder_deferred_lock);
-		if (!hlist_empty(&binder_deferred_list)) {
-			proc = hlist_entry(binder_deferred_list.first,
-					struct binder_proc, deferred_work_node);
-			hlist_del_init(&proc->deferred_work_node);
-			defer = proc->deferred_work;
-			proc->deferred_work = 0;
-		} else {
-			proc = NULL;
-			defer = 0;
-		}
-		mutex_unlock(&binder_deferred_lock);
-
-		files = NULL;
-		if (defer & BINDER_DEFERRED_PUT_FILES) {
-			files = proc->files;
-			if (files)
-				proc->files = NULL;
-		}
-
-		if (defer & BINDER_DEFERRED_FLUSH)
-			binder_deferred_flush(proc);
-
-		if (defer & BINDER_DEFERRED_RELEASE)
-			binder_deferred_release(proc); /* frees proc */
-
-		binder_unlock(__func__);
-		if (files)
-			put_files_struct(files);
-	} while (proc);
-}
-static DECLARE_WORK(binder_deferred_work, binder_deferred_func);
-
-static void
-binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer)
-{
-	mutex_lock(&binder_deferred_lock);
-	proc->deferred_work |= defer;
-	if (hlist_unhashed(&proc->deferred_work_node)) {
-		hlist_add_head(&proc->deferred_work_node,
-				&binder_deferred_list);
-		queue_work(binder_deferred_workqueue, &binder_deferred_work);
-	}
-	mutex_unlock(&binder_deferred_lock);
-}
-
-static void print_binder_transaction(struct seq_file *m, const char *prefix,
-				     struct binder_transaction *t)
-{
-	seq_printf(m,
-		   "%s %d: %p from %d:%d to %d:%d code %x flags %x pri %ld r%d",
-		   prefix, t->debug_id, t,
-		   t->from ? t->from->proc->pid : 0,
-		   t->from ? t->from->pid : 0,
-		   t->to_proc ? t->to_proc->pid : 0,
-		   t->to_thread ? t->to_thread->pid : 0,
-		   t->code, t->flags, t->priority, t->need_reply);
-	if (t->buffer == NULL) {
-		seq_puts(m, " buffer free\n");
-		return;
-	}
-	if (t->buffer->target_node)
-		seq_printf(m, " node %d",
-			   t->buffer->target_node->debug_id);
-	seq_printf(m, " size %zd:%zd data %p\n",
-		   t->buffer->data_size, t->buffer->offsets_size,
-		   t->buffer->data);
-}
-
-static void print_binder_buffer(struct seq_file *m, const char *prefix,
-				struct binder_buffer *buffer)
-{
-	seq_printf(m, "%s %d: %p size %zd:%zd %s\n",
-		   prefix, buffer->debug_id, buffer->data,
-		   buffer->data_size, buffer->offsets_size,
-		   buffer->transaction ? "active" : "delivered");
-}
-
-static void print_binder_work(struct seq_file *m, const char *prefix,
-			      const char *transaction_prefix,
-			      struct binder_work *w)
-{
-	struct binder_node *node;
-	struct binder_transaction *t;
-
-	switch (w->type) {
-	case BINDER_WORK_TRANSACTION:
-		t = container_of(w, struct binder_transaction, work);
-		print_binder_transaction(m, transaction_prefix, t);
-		break;
-	case BINDER_WORK_TRANSACTION_COMPLETE:
-		seq_printf(m, "%stransaction complete\n", prefix);
-		break;
-	case BINDER_WORK_NODE:
-		node = container_of(w, struct binder_node, work);
-		seq_printf(m, "%snode work %d: u%016llx c%016llx\n",
-			   prefix, node->debug_id,
-			   (u64)node->ptr, (u64)node->cookie);
-		break;
-	case BINDER_WORK_DEAD_BINDER:
-		seq_printf(m, "%shas dead binder\n", prefix);
-		break;
-	case BINDER_WORK_DEAD_BINDER_AND_CLEAR:
-		seq_printf(m, "%shas cleared dead binder\n", prefix);
-		break;
-	case BINDER_WORK_CLEAR_DEATH_NOTIFICATION:
-		seq_printf(m, "%shas cleared death notification\n", prefix);
-		break;
-	default:
-		seq_printf(m, "%sunknown work: type %d\n", prefix, w->type);
-		break;
-	}
-}
-
-static void print_binder_thread(struct seq_file *m,
-				struct binder_thread *thread,
-				int print_always)
-{
-	struct binder_transaction *t;
-	struct binder_work *w;
-	size_t start_pos = m->count;
-	size_t header_pos;
-
-	seq_printf(m, "  thread %d: l %02x\n", thread->pid, thread->looper);
-	header_pos = m->count;
-	t = thread->transaction_stack;
-	while (t) {
-		if (t->from == thread) {
-			print_binder_transaction(m,
-						 "    outgoing transaction", t);
-			t = t->from_parent;
-		} else if (t->to_thread == thread) {
-			print_binder_transaction(m,
-						 "    incoming transaction", t);
-			t = t->to_parent;
-		} else {
-			print_binder_transaction(m, "    bad transaction", t);
-			t = NULL;
-		}
-	}
-	list_for_each_entry(w, &thread->todo, entry) {
-		print_binder_work(m, "    ", "    pending transaction", w);
-	}
-	if (!print_always && m->count == header_pos)
-		m->count = start_pos;
-}
-
-static void print_binder_node(struct seq_file *m, struct binder_node *node)
-{
-	struct binder_ref *ref;
-	struct binder_work *w;
-	int count;
-
-	count = 0;
-	hlist_for_each_entry(ref, &node->refs, node_entry)
-		count++;
-
-	seq_printf(m, "  node %d: u%016llx c%016llx hs %d hw %d ls %d lw %d is %d iw %d",
-		   node->debug_id, (u64)node->ptr, (u64)node->cookie,
-		   node->has_strong_ref, node->has_weak_ref,
-		   node->local_strong_refs, node->local_weak_refs,
-		   node->internal_strong_refs, count);
-	if (count) {
-		seq_puts(m, " proc");
-		hlist_for_each_entry(ref, &node->refs, node_entry)
-			seq_printf(m, " %d", ref->proc->pid);
-	}
-	seq_puts(m, "\n");
-	list_for_each_entry(w, &node->async_todo, entry)
-		print_binder_work(m, "    ",
-				  "    pending async transaction", w);
-}
-
-static void print_binder_ref(struct seq_file *m, struct binder_ref *ref)
-{
-	seq_printf(m, "  ref %d: desc %d %snode %d s %d w %d d %p\n",
-		   ref->debug_id, ref->desc, ref->node->proc ? "" : "dead ",
-		   ref->node->debug_id, ref->strong, ref->weak, ref->death);
-}
-
-static void print_binder_proc(struct seq_file *m,
-			      struct binder_proc *proc, int print_all)
-{
-	struct binder_work *w;
-	struct rb_node *n;
-	size_t start_pos = m->count;
-	size_t header_pos;
-
-	seq_printf(m, "proc %d\n", proc->pid);
-	header_pos = m->count;
-
-	for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n))
-		print_binder_thread(m, rb_entry(n, struct binder_thread,
-						rb_node), print_all);
-	for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n)) {
-		struct binder_node *node = rb_entry(n, struct binder_node,
-						    rb_node);
-		if (print_all || node->has_async_transaction)
-			print_binder_node(m, node);
-	}
-	if (print_all) {
-		for (n = rb_first(&proc->refs_by_desc);
-		     n != NULL;
-		     n = rb_next(n))
-			print_binder_ref(m, rb_entry(n, struct binder_ref,
-						     rb_node_desc));
-	}
-	for (n = rb_first(&proc->allocated_buffers); n != NULL; n = rb_next(n))
-		print_binder_buffer(m, "  buffer",
-				    rb_entry(n, struct binder_buffer, rb_node));
-	list_for_each_entry(w, &proc->todo, entry)
-		print_binder_work(m, "  ", "  pending transaction", w);
-	list_for_each_entry(w, &proc->delivered_death, entry) {
-		seq_puts(m, "  has delivered dead binder\n");
-		break;
-	}
-	if (!print_all && m->count == header_pos)
-		m->count = start_pos;
-}
-
-static const char * const binder_return_strings[] = {
-	"BR_ERROR",
-	"BR_OK",
-	"BR_TRANSACTION",
-	"BR_REPLY",
-	"BR_ACQUIRE_RESULT",
-	"BR_DEAD_REPLY",
-	"BR_TRANSACTION_COMPLETE",
-	"BR_INCREFS",
-	"BR_ACQUIRE",
-	"BR_RELEASE",
-	"BR_DECREFS",
-	"BR_ATTEMPT_ACQUIRE",
-	"BR_NOOP",
-	"BR_SPAWN_LOOPER",
-	"BR_FINISHED",
-	"BR_DEAD_BINDER",
-	"BR_CLEAR_DEATH_NOTIFICATION_DONE",
-	"BR_FAILED_REPLY"
-};
-
-static const char * const binder_command_strings[] = {
-	"BC_TRANSACTION",
-	"BC_REPLY",
-	"BC_ACQUIRE_RESULT",
-	"BC_FREE_BUFFER",
-	"BC_INCREFS",
-	"BC_ACQUIRE",
-	"BC_RELEASE",
-	"BC_DECREFS",
-	"BC_INCREFS_DONE",
-	"BC_ACQUIRE_DONE",
-	"BC_ATTEMPT_ACQUIRE",
-	"BC_REGISTER_LOOPER",
-	"BC_ENTER_LOOPER",
-	"BC_EXIT_LOOPER",
-	"BC_REQUEST_DEATH_NOTIFICATION",
-	"BC_CLEAR_DEATH_NOTIFICATION",
-	"BC_DEAD_BINDER_DONE"
-};
-
-static const char * const binder_objstat_strings[] = {
-	"proc",
-	"thread",
-	"node",
-	"ref",
-	"death",
-	"transaction",
-	"transaction_complete"
-};
-
-static void print_binder_stats(struct seq_file *m, const char *prefix,
-			       struct binder_stats *stats)
-{
-	int i;
-
-	BUILD_BUG_ON(ARRAY_SIZE(stats->bc) !=
-		     ARRAY_SIZE(binder_command_strings));
-	for (i = 0; i < ARRAY_SIZE(stats->bc); i++) {
-		if (stats->bc[i])
-			seq_printf(m, "%s%s: %d\n", prefix,
-				   binder_command_strings[i], stats->bc[i]);
-	}
-
-	BUILD_BUG_ON(ARRAY_SIZE(stats->br) !=
-		     ARRAY_SIZE(binder_return_strings));
-	for (i = 0; i < ARRAY_SIZE(stats->br); i++) {
-		if (stats->br[i])
-			seq_printf(m, "%s%s: %d\n", prefix,
-				   binder_return_strings[i], stats->br[i]);
-	}
-
-	BUILD_BUG_ON(ARRAY_SIZE(stats->obj_created) !=
-		     ARRAY_SIZE(binder_objstat_strings));
-	BUILD_BUG_ON(ARRAY_SIZE(stats->obj_created) !=
-		     ARRAY_SIZE(stats->obj_deleted));
-	for (i = 0; i < ARRAY_SIZE(stats->obj_created); i++) {
-		if (stats->obj_created[i] || stats->obj_deleted[i])
-			seq_printf(m, "%s%s: active %d total %d\n", prefix,
-				binder_objstat_strings[i],
-				stats->obj_created[i] - stats->obj_deleted[i],
-				stats->obj_created[i]);
-	}
-}
-
-static void print_binder_proc_stats(struct seq_file *m,
-				    struct binder_proc *proc)
-{
-	struct binder_work *w;
-	struct rb_node *n;
-	int count, strong, weak;
-
-	seq_printf(m, "proc %d\n", proc->pid);
-	count = 0;
-	for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n))
-		count++;
-	seq_printf(m, "  threads: %d\n", count);
-	seq_printf(m, "  requested threads: %d+%d/%d\n"
-			"  ready threads %d\n"
-			"  free async space %zd\n", proc->requested_threads,
-			proc->requested_threads_started, proc->max_threads,
-			proc->ready_threads, proc->free_async_space);
-	count = 0;
-	for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n))
-		count++;
-	seq_printf(m, "  nodes: %d\n", count);
-	count = 0;
-	strong = 0;
-	weak = 0;
-	for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) {
-		struct binder_ref *ref = rb_entry(n, struct binder_ref,
-						  rb_node_desc);
-		count++;
-		strong += ref->strong;
-		weak += ref->weak;
-	}
-	seq_printf(m, "  refs: %d s %d w %d\n", count, strong, weak);
-
-	count = 0;
-	for (n = rb_first(&proc->allocated_buffers); n != NULL; n = rb_next(n))
-		count++;
-	seq_printf(m, "  buffers: %d\n", count);
-
-	count = 0;
-	list_for_each_entry(w, &proc->todo, entry) {
-		switch (w->type) {
-		case BINDER_WORK_TRANSACTION:
-			count++;
-			break;
-		default:
-			break;
-		}
-	}
-	seq_printf(m, "  pending transactions: %d\n", count);
-
-	print_binder_stats(m, "  ", &proc->stats);
-}
-
-
-static int binder_state_show(struct seq_file *m, void *unused)
-{
-	struct binder_proc *proc;
-	struct binder_node *node;
-	int do_lock = !binder_debug_no_lock;
-
-	if (do_lock)
-		binder_lock(__func__);
-
-	seq_puts(m, "binder state:\n");
-
-	if (!hlist_empty(&binder_dead_nodes))
-		seq_puts(m, "dead nodes:\n");
-	hlist_for_each_entry(node, &binder_dead_nodes, dead_node)
-		print_binder_node(m, node);
-
-	hlist_for_each_entry(proc, &binder_procs, proc_node)
-		print_binder_proc(m, proc, 1);
-	if (do_lock)
-		binder_unlock(__func__);
-	return 0;
-}
-
-static int binder_stats_show(struct seq_file *m, void *unused)
-{
-	struct binder_proc *proc;
-	int do_lock = !binder_debug_no_lock;
-
-	if (do_lock)
-		binder_lock(__func__);
-
-	seq_puts(m, "binder stats:\n");
-
-	print_binder_stats(m, "", &binder_stats);
-
-	hlist_for_each_entry(proc, &binder_procs, proc_node)
-		print_binder_proc_stats(m, proc);
-	if (do_lock)
-		binder_unlock(__func__);
-	return 0;
-}
-
-static int binder_transactions_show(struct seq_file *m, void *unused)
-{
-	struct binder_proc *proc;
-	int do_lock = !binder_debug_no_lock;
-
-	if (do_lock)
-		binder_lock(__func__);
-
-	seq_puts(m, "binder transactions:\n");
-	hlist_for_each_entry(proc, &binder_procs, proc_node)
-		print_binder_proc(m, proc, 0);
-	if (do_lock)
-		binder_unlock(__func__);
-	return 0;
-}
-
-static int binder_proc_show(struct seq_file *m, void *unused)
-{
-	struct binder_proc *proc = m->private;
-	int do_lock = !binder_debug_no_lock;
-
-	if (do_lock)
-		binder_lock(__func__);
-	seq_puts(m, "binder proc state:\n");
-	print_binder_proc(m, proc, 1);
-	if (do_lock)
-		binder_unlock(__func__);
-	return 0;
-}
-
-static void print_binder_transaction_log_entry(struct seq_file *m,
-					struct binder_transaction_log_entry *e)
-{
-	seq_printf(m,
-		   "%d: %s from %d:%d to %d:%d node %d handle %d size %d:%d\n",
-		   e->debug_id, (e->call_type == 2) ? "reply" :
-		   ((e->call_type == 1) ? "async" : "call "), e->from_proc,
-		   e->from_thread, e->to_proc, e->to_thread, e->to_node,
-		   e->target_handle, e->data_size, e->offsets_size);
-}
-
-static int binder_transaction_log_show(struct seq_file *m, void *unused)
-{
-	struct binder_transaction_log *log = m->private;
-	int i;
-
-	if (log->full) {
-		for (i = log->next; i < ARRAY_SIZE(log->entry); i++)
-			print_binder_transaction_log_entry(m, &log->entry[i]);
-	}
-	for (i = 0; i < log->next; i++)
-		print_binder_transaction_log_entry(m, &log->entry[i]);
-	return 0;
-}
-
-static const struct file_operations binder_fops = {
-	.owner = THIS_MODULE,
-	.poll = binder_poll,
-	.unlocked_ioctl = binder_ioctl,
-	.compat_ioctl = binder_ioctl,
-	.mmap = binder_mmap,
-	.open = binder_open,
-	.flush = binder_flush,
-	.release = binder_release,
-};
-
-static struct miscdevice binder_miscdev = {
-	.minor = MISC_DYNAMIC_MINOR,
-	.name = "binder",
-	.fops = &binder_fops
-};
-
-BINDER_DEBUG_ENTRY(state);
-BINDER_DEBUG_ENTRY(stats);
-BINDER_DEBUG_ENTRY(transactions);
-BINDER_DEBUG_ENTRY(transaction_log);
-
-static int __init binder_init(void)
-{
-	int ret;
-
-	binder_deferred_workqueue = create_singlethread_workqueue("binder");
-	if (!binder_deferred_workqueue)
-		return -ENOMEM;
-
-	binder_debugfs_dir_entry_root = debugfs_create_dir("binder", NULL);
-	if (binder_debugfs_dir_entry_root)
-		binder_debugfs_dir_entry_proc = debugfs_create_dir("proc",
-						 binder_debugfs_dir_entry_root);
-	ret = misc_register(&binder_miscdev);
-	if (binder_debugfs_dir_entry_root) {
-		debugfs_create_file("state",
-				    S_IRUGO,
-				    binder_debugfs_dir_entry_root,
-				    NULL,
-				    &binder_state_fops);
-		debugfs_create_file("stats",
-				    S_IRUGO,
-				    binder_debugfs_dir_entry_root,
-				    NULL,
-				    &binder_stats_fops);
-		debugfs_create_file("transactions",
-				    S_IRUGO,
-				    binder_debugfs_dir_entry_root,
-				    NULL,
-				    &binder_transactions_fops);
-		debugfs_create_file("transaction_log",
-				    S_IRUGO,
-				    binder_debugfs_dir_entry_root,
-				    &binder_transaction_log,
-				    &binder_transaction_log_fops);
-		debugfs_create_file("failed_transaction_log",
-				    S_IRUGO,
-				    binder_debugfs_dir_entry_root,
-				    &binder_transaction_log_failed,
-				    &binder_transaction_log_fops);
-	}
-	return ret;
-}
-
-device_initcall(binder_init);
-
-#define CREATE_TRACE_POINTS
-#include "binder_trace.h"
-
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/staging/android/binder.h b/drivers/staging/android/binder.h
deleted file mode 100644
index eb0834656df..00000000000
--- a/drivers/staging/android/binder.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * Copyright (C) 2008 Google, Inc.
- *
- * Based on, but no longer compatible with, the original
- * OpenBinder.org binder driver interface, which is:
- *
- * Copyright (c) 2005 Palmsource, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef _LINUX_BINDER_H
-#define _LINUX_BINDER_H
-
-#ifdef CONFIG_ANDROID_BINDER_IPC_32BIT
-#define BINDER_IPC_32BIT 1
-#endif
-
-#include "uapi/binder.h"
-
-#endif /* _LINUX_BINDER_H */
-
diff --git a/drivers/staging/android/binder_trace.h b/drivers/staging/android/binder_trace.h
deleted file mode 100644
index 7f20f3dc836..00000000000
--- a/drivers/staging/android/binder_trace.h
+++ /dev/null
@@ -1,329 +0,0 @@
-/*
- * Copyright (C) 2012 Google, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM binder
-
-#if !defined(_BINDER_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _BINDER_TRACE_H
-
-#include <linux/tracepoint.h>
-
-struct binder_buffer;
-struct binder_node;
-struct binder_proc;
-struct binder_ref;
-struct binder_thread;
-struct binder_transaction;
-
-TRACE_EVENT(binder_ioctl,
-	TP_PROTO(unsigned int cmd, unsigned long arg),
-	TP_ARGS(cmd, arg),
-
-	TP_STRUCT__entry(
-		__field(unsigned int, cmd)
-		__field(unsigned long, arg)
-	),
-	TP_fast_assign(
-		__entry->cmd = cmd;
-		__entry->arg = arg;
-	),
-	TP_printk("cmd=0x%x arg=0x%lx", __entry->cmd, __entry->arg)
-);
-
-DECLARE_EVENT_CLASS(binder_lock_class,
-	TP_PROTO(const char *tag),
-	TP_ARGS(tag),
-	TP_STRUCT__entry(
-		__field(const char *, tag)
-	),
-	TP_fast_assign(
-		__entry->tag = tag;
-	),
-	TP_printk("tag=%s", __entry->tag)
-);
-
-#define DEFINE_BINDER_LOCK_EVENT(name)	\
-DEFINE_EVENT(binder_lock_class, name,	\
-	TP_PROTO(const char *func), \
-	TP_ARGS(func))
-
-DEFINE_BINDER_LOCK_EVENT(binder_lock);
-DEFINE_BINDER_LOCK_EVENT(binder_locked);
-DEFINE_BINDER_LOCK_EVENT(binder_unlock);
-
-DECLARE_EVENT_CLASS(binder_function_return_class,
-	TP_PROTO(int ret),
-	TP_ARGS(ret),
-	TP_STRUCT__entry(
-		__field(int, ret)
-	),
-	TP_fast_assign(
-		__entry->ret = ret;
-	),
-	TP_printk("ret=%d", __entry->ret)
-);
-
-#define DEFINE_BINDER_FUNCTION_RETURN_EVENT(name)	\
-DEFINE_EVENT(binder_function_return_class, name,	\
-	TP_PROTO(int ret), \
-	TP_ARGS(ret))
-
-DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_ioctl_done);
-DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_write_done);
-DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_read_done);
-
-TRACE_EVENT(binder_wait_for_work,
-	TP_PROTO(bool proc_work, bool transaction_stack, bool thread_todo),
-	TP_ARGS(proc_work, transaction_stack, thread_todo),
-
-	TP_STRUCT__entry(
-		__field(bool, proc_work)
-		__field(bool, transaction_stack)
-		__field(bool, thread_todo)
-	),
-	TP_fast_assign(
-		__entry->proc_work = proc_work;
-		__entry->transaction_stack = transaction_stack;
-		__entry->thread_todo = thread_todo;
-	),
-	TP_printk("proc_work=%d transaction_stack=%d thread_todo=%d",
-		  __entry->proc_work, __entry->transaction_stack,
-		  __entry->thread_todo)
-);
-
-TRACE_EVENT(binder_transaction,
-	TP_PROTO(bool reply, struct binder_transaction *t,
-		 struct binder_node *target_node),
-	TP_ARGS(reply, t, target_node),
-	TP_STRUCT__entry(
-		__field(int, debug_id)
-		__field(int, target_node)
-		__field(int, to_proc)
-		__field(int, to_thread)
-		__field(int, reply)
-		__field(unsigned int, code)
-		__field(unsigned int, flags)
-	),
-	TP_fast_assign(
-		__entry->debug_id = t->debug_id;
-		__entry->target_node = target_node ? target_node->debug_id : 0;
-		__entry->to_proc = t->to_proc->pid;
-		__entry->to_thread = t->to_thread ? t->to_thread->pid : 0;
-		__entry->reply = reply;
-		__entry->code = t->code;
-		__entry->flags = t->flags;
-	),
-	TP_printk("transaction=%d dest_node=%d dest_proc=%d dest_thread=%d reply=%d flags=0x%x code=0x%x",
-		  __entry->debug_id, __entry->target_node,
-		  __entry->to_proc, __entry->to_thread,
-		  __entry->reply, __entry->flags, __entry->code)
-);
-
-TRACE_EVENT(binder_transaction_received,
-	TP_PROTO(struct binder_transaction *t),
-	TP_ARGS(t),
-
-	TP_STRUCT__entry(
-		__field(int, debug_id)
-	),
-	TP_fast_assign(
-		__entry->debug_id = t->debug_id;
-	),
-	TP_printk("transaction=%d", __entry->debug_id)
-);
-
-TRACE_EVENT(binder_transaction_node_to_ref,
-	TP_PROTO(struct binder_transaction *t, struct binder_node *node,
-		 struct binder_ref *ref),
-	TP_ARGS(t, node, ref),
-
-	TP_STRUCT__entry(
-		__field(int, debug_id)
-		__field(int, node_debug_id)
-		__field(binder_uintptr_t, node_ptr)
-		__field(int, ref_debug_id)
-		__field(uint32_t, ref_desc)
-	),
-	TP_fast_assign(
-		__entry->debug_id = t->debug_id;
-		__entry->node_debug_id = node->debug_id;
-		__entry->node_ptr = node->ptr;
-		__entry->ref_debug_id = ref->debug_id;
-		__entry->ref_desc = ref->desc;
-	),
-	TP_printk("transaction=%d node=%d src_ptr=0x%016llx ==> dest_ref=%d dest_desc=%d",
-		  __entry->debug_id, __entry->node_debug_id,
-		  (u64)__entry->node_ptr,
-		  __entry->ref_debug_id, __entry->ref_desc)
-);
-
-TRACE_EVENT(binder_transaction_ref_to_node,
-	TP_PROTO(struct binder_transaction *t, struct binder_ref *ref),
-	TP_ARGS(t, ref),
-
-	TP_STRUCT__entry(
-		__field(int, debug_id)
-		__field(int, ref_debug_id)
-		__field(uint32_t, ref_desc)
-		__field(int, node_debug_id)
-		__field(binder_uintptr_t, node_ptr)
-	),
-	TP_fast_assign(
-		__entry->debug_id = t->debug_id;
-		__entry->ref_debug_id = ref->debug_id;
-		__entry->ref_desc = ref->desc;
-		__entry->node_debug_id = ref->node->debug_id;
-		__entry->node_ptr = ref->node->ptr;
-	),
-	TP_printk("transaction=%d node=%d src_ref=%d src_desc=%d ==> dest_ptr=0x%016llx",
-		  __entry->debug_id, __entry->node_debug_id,
-		  __entry->ref_debug_id, __entry->ref_desc,
-		  (u64)__entry->node_ptr)
-);
-
-TRACE_EVENT(binder_transaction_ref_to_ref,
-	TP_PROTO(struct binder_transaction *t, struct binder_ref *src_ref,
-		 struct binder_ref *dest_ref),
-	TP_ARGS(t, src_ref, dest_ref),
-
-	TP_STRUCT__entry(
-		__field(int, debug_id)
-		__field(int, node_debug_id)
-		__field(int, src_ref_debug_id)
-		__field(uint32_t, src_ref_desc)
-		__field(int, dest_ref_debug_id)
-		__field(uint32_t, dest_ref_desc)
-	),
-	TP_fast_assign(
-		__entry->debug_id = t->debug_id;
-		__entry->node_debug_id = src_ref->node->debug_id;
-		__entry->src_ref_debug_id = src_ref->debug_id;
-		__entry->src_ref_desc = src_ref->desc;
-		__entry->dest_ref_debug_id = dest_ref->debug_id;
-		__entry->dest_ref_desc = dest_ref->desc;
-	),
-	TP_printk("transaction=%d node=%d src_ref=%d src_desc=%d ==> dest_ref=%d dest_desc=%d",
-		  __entry->debug_id, __entry->node_debug_id,
-		  __entry->src_ref_debug_id, __entry->src_ref_desc,
-		  __entry->dest_ref_debug_id, __entry->dest_ref_desc)
-);
-
-TRACE_EVENT(binder_transaction_fd,
-	TP_PROTO(struct binder_transaction *t, int src_fd, int dest_fd),
-	TP_ARGS(t, src_fd, dest_fd),
-
-	TP_STRUCT__entry(
-		__field(int, debug_id)
-		__field(int, src_fd)
-		__field(int, dest_fd)
-	),
-	TP_fast_assign(
-		__entry->debug_id = t->debug_id;
-		__entry->src_fd = src_fd;
-		__entry->dest_fd = dest_fd;
-	),
-	TP_printk("transaction=%d src_fd=%d ==> dest_fd=%d",
-		  __entry->debug_id, __entry->src_fd, __entry->dest_fd)
-);
-
-DECLARE_EVENT_CLASS(binder_buffer_class,
-	TP_PROTO(struct binder_buffer *buf),
-	TP_ARGS(buf),
-	TP_STRUCT__entry(
-		__field(int, debug_id)
-		__field(size_t, data_size)
-		__field(size_t, offsets_size)
-	),
-	TP_fast_assign(
-		__entry->debug_id = buf->debug_id;
-		__entry->data_size = buf->data_size;
-		__entry->offsets_size = buf->offsets_size;
-	),
-	TP_printk("transaction=%d data_size=%zd offsets_size=%zd",
-		  __entry->debug_id, __entry->data_size, __entry->offsets_size)
-);
-
-DEFINE_EVENT(binder_buffer_class, binder_transaction_alloc_buf,
-	TP_PROTO(struct binder_buffer *buffer),
-	TP_ARGS(buffer));
-
-DEFINE_EVENT(binder_buffer_class, binder_transaction_buffer_release,
-	TP_PROTO(struct binder_buffer *buffer),
-	TP_ARGS(buffer));
-
-DEFINE_EVENT(binder_buffer_class, binder_transaction_failed_buffer_release,
-	TP_PROTO(struct binder_buffer *buffer),
-	TP_ARGS(buffer));
-
-TRACE_EVENT(binder_update_page_range,
-	TP_PROTO(struct binder_proc *proc, bool allocate,
-		 void *start, void *end),
-	TP_ARGS(proc, allocate, start, end),
-	TP_STRUCT__entry(
-		__field(int, proc)
-		__field(bool, allocate)
-		__field(size_t, offset)
-		__field(size_t, size)
-	),
-	TP_fast_assign(
-		__entry->proc = proc->pid;
-		__entry->allocate = allocate;
-		__entry->offset = start - proc->buffer;
-		__entry->size = end - start;
-	),
-	TP_printk("proc=%d allocate=%d offset=%zu size=%zu",
-		  __entry->proc, __entry->allocate,
-		  __entry->offset, __entry->size)
-);
-
-TRACE_EVENT(binder_command,
-	TP_PROTO(uint32_t cmd),
-	TP_ARGS(cmd),
-	TP_STRUCT__entry(
-		__field(uint32_t, cmd)
-	),
-	TP_fast_assign(
-		__entry->cmd = cmd;
-	),
-	TP_printk("cmd=0x%x %s",
-		  __entry->cmd,
-		  _IOC_NR(__entry->cmd) < ARRAY_SIZE(binder_command_strings) ?
-			  binder_command_strings[_IOC_NR(__entry->cmd)] :
-			  "unknown")
-);
-
-TRACE_EVENT(binder_return,
-	TP_PROTO(uint32_t cmd),
-	TP_ARGS(cmd),
-	TP_STRUCT__entry(
-		__field(uint32_t, cmd)
-	),
-	TP_fast_assign(
-		__entry->cmd = cmd;
-	),
-	TP_printk("cmd=0x%x %s",
-		  __entry->cmd,
-		  _IOC_NR(__entry->cmd) < ARRAY_SIZE(binder_return_strings) ?
-			  binder_return_strings[_IOC_NR(__entry->cmd)] :
-			  "unknown")
-);
-
-#endif /* _BINDER_TRACE_H */
-
-#undef TRACE_INCLUDE_PATH
-#undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE binder_trace
-#include <trace/define_trace.h>
diff --git a/drivers/staging/android/uapi/binder.h b/drivers/staging/android/uapi/binder.h
deleted file mode 100644
index dba4cef3a8d..00000000000
--- a/drivers/staging/android/uapi/binder.h
+++ /dev/null
@@ -1,351 +0,0 @@
-/*
- * Copyright (C) 2008 Google, Inc.
- *
- * Based on, but no longer compatible with, the original
- * OpenBinder.org binder driver interface, which is:
- *
- * Copyright (c) 2005 Palmsource, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef _UAPI_LINUX_BINDER_H
-#define _UAPI_LINUX_BINDER_H
-
-#include <linux/ioctl.h>
-
-#define B_PACK_CHARS(c1, c2, c3, c4) \
-	((((c1)<<24)) | (((c2)<<16)) | (((c3)<<8)) | (c4))
-#define B_TYPE_LARGE 0x85
-
-enum {
-	BINDER_TYPE_BINDER	= B_PACK_CHARS('s', 'b', '*', B_TYPE_LARGE),
-	BINDER_TYPE_WEAK_BINDER	= B_PACK_CHARS('w', 'b', '*', B_TYPE_LARGE),
-	BINDER_TYPE_HANDLE	= B_PACK_CHARS('s', 'h', '*', B_TYPE_LARGE),
-	BINDER_TYPE_WEAK_HANDLE	= B_PACK_CHARS('w', 'h', '*', B_TYPE_LARGE),
-	BINDER_TYPE_FD		= B_PACK_CHARS('f', 'd', '*', B_TYPE_LARGE),
-};
-
-enum {
-	FLAT_BINDER_FLAG_PRIORITY_MASK = 0xff,
-	FLAT_BINDER_FLAG_ACCEPTS_FDS = 0x100,
-};
-
-#ifdef BINDER_IPC_32BIT
-typedef __u32 binder_size_t;
-typedef __u32 binder_uintptr_t;
-#else
-typedef __u64 binder_size_t;
-typedef __u64 binder_uintptr_t;
-#endif
-
-/*
- * This is the flattened representation of a Binder object for transfer
- * between processes.  The 'offsets' supplied as part of a binder transaction
- * contains offsets into the data where these structures occur.  The Binder
- * driver takes care of re-writing the structure type and data as it moves
- * between processes.
- */
-struct flat_binder_object {
-	/* 8 bytes for large_flat_header. */
-	__u32		type;
-	__u32		flags;
-
-	/* 8 bytes of data. */
-	union {
-		binder_uintptr_t	binder;	/* local object */
-		__u32			handle;	/* remote object */
-	};
-
-	/* extra data associated with local object */
-	binder_uintptr_t	cookie;
-};
-
-/*
- * On 64-bit platforms where user code may run in 32-bits the driver must
- * translate the buffer (and local binder) addresses appropriately.
- */
-
-struct binder_write_read {
-	binder_size_t		write_size;	/* bytes to write */
-	binder_size_t		write_consumed;	/* bytes consumed by driver */
-	binder_uintptr_t	write_buffer;
-	binder_size_t		read_size;	/* bytes to read */
-	binder_size_t		read_consumed;	/* bytes consumed by driver */
-	binder_uintptr_t	read_buffer;
-};
-
-/* Use with BINDER_VERSION, driver fills in fields. */
-struct binder_version {
-	/* driver protocol version -- increment with incompatible change */
-	__s32       protocol_version;
-};
-
-/* This is the current protocol version. */
-#ifdef BINDER_IPC_32BIT
-#define BINDER_CURRENT_PROTOCOL_VERSION 7
-#else
-#define BINDER_CURRENT_PROTOCOL_VERSION 8
-#endif
-
-#define BINDER_WRITE_READ		_IOWR('b', 1, struct binder_write_read)
-#define BINDER_SET_IDLE_TIMEOUT		_IOW('b', 3, __s64)
-#define BINDER_SET_MAX_THREADS		_IOW('b', 5, __u32)
-#define BINDER_SET_IDLE_PRIORITY	_IOW('b', 6, __s32)
-#define BINDER_SET_CONTEXT_MGR		_IOW('b', 7, __s32)
-#define BINDER_THREAD_EXIT		_IOW('b', 8, __s32)
-#define BINDER_VERSION			_IOWR('b', 9, struct binder_version)
-
-/*
- * NOTE: Two special error codes you should check for when calling
- * in to the driver are:
- *
- * EINTR -- The operation has been interupted.  This should be
- * handled by retrying the ioctl() until a different error code
- * is returned.
- *
- * ECONNREFUSED -- The driver is no longer accepting operations
- * from your process.  That is, the process is being destroyed.
- * You should handle this by exiting from your process.  Note
- * that once this error code is returned, all further calls to
- * the driver from any thread will return this same code.
- */
-
-enum transaction_flags {
-	TF_ONE_WAY	= 0x01,	/* this is a one-way call: async, no return */
-	TF_ROOT_OBJECT	= 0x04,	/* contents are the component's root object */
-	TF_STATUS_CODE	= 0x08,	/* contents are a 32-bit status code */
-	TF_ACCEPT_FDS	= 0x10,	/* allow replies with file descriptors */
-};
-
-struct binder_transaction_data {
-	/* The first two are only used for bcTRANSACTION and brTRANSACTION,
-	 * identifying the target and contents of the transaction.
-	 */
-	union {
-		/* target descriptor of command transaction */
-		__u32	handle;
-		/* target descriptor of return transaction */
-		binder_uintptr_t ptr;
-	} target;
-	binder_uintptr_t	cookie;	/* target object cookie */
-	__u32		code;		/* transaction command */
-
-	/* General information about the transaction. */
-	__u32	        flags;
-	pid_t		sender_pid;
-	uid_t		sender_euid;
-	binder_size_t	data_size;	/* number of bytes of data */
-	binder_size_t	offsets_size;	/* number of bytes of offsets */
-
-	/* If this transaction is inline, the data immediately
-	 * follows here; otherwise, it ends with a pointer to
-	 * the data buffer.
-	 */
-	union {
-		struct {
-			/* transaction data */
-			binder_uintptr_t	buffer;
-			/* offsets from buffer to flat_binder_object structs */
-			binder_uintptr_t	offsets;
-		} ptr;
-		__u8	buf[8];
-	} data;
-};
-
-struct binder_ptr_cookie {
-	binder_uintptr_t ptr;
-	binder_uintptr_t cookie;
-};
-
-struct binder_handle_cookie {
-	__u32 handle;
-	binder_uintptr_t cookie;
-} __packed;
-
-struct binder_pri_desc {
-	__s32 priority;
-	__u32 desc;
-};
-
-struct binder_pri_ptr_cookie {
-	__s32 priority;
-	binder_uintptr_t ptr;
-	binder_uintptr_t cookie;
-};
-
-enum binder_driver_return_protocol {
-	BR_ERROR = _IOR('r', 0, __s32),
-	/*
-	 * int: error code
-	 */
-
-	BR_OK = _IO('r', 1),
-	/* No parameters! */
-
-	BR_TRANSACTION = _IOR('r', 2, struct binder_transaction_data),
-	BR_REPLY = _IOR('r', 3, struct binder_transaction_data),
-	/*
-	 * binder_transaction_data: the received command.
-	 */
-
-	BR_ACQUIRE_RESULT = _IOR('r', 4, __s32),
-	/*
-	 * not currently supported
-	 * int: 0 if the last bcATTEMPT_ACQUIRE was not successful.
-	 * Else the remote object has acquired a primary reference.
-	 */
-
-	BR_DEAD_REPLY = _IO('r', 5),
-	/*
-	 * The target of the last transaction (either a bcTRANSACTION or
-	 * a bcATTEMPT_ACQUIRE) is no longer with us.  No parameters.
-	 */
-
-	BR_TRANSACTION_COMPLETE = _IO('r', 6),
-	/*
-	 * No parameters... always refers to the last transaction requested
-	 * (including replies).  Note that this will be sent even for
-	 * asynchronous transactions.
-	 */
-
-	BR_INCREFS = _IOR('r', 7, struct binder_ptr_cookie),
-	BR_ACQUIRE = _IOR('r', 8, struct binder_ptr_cookie),
-	BR_RELEASE = _IOR('r', 9, struct binder_ptr_cookie),
-	BR_DECREFS = _IOR('r', 10, struct binder_ptr_cookie),
-	/*
-	 * void *:	ptr to binder
-	 * void *: cookie for binder
-	 */
-
-	BR_ATTEMPT_ACQUIRE = _IOR('r', 11, struct binder_pri_ptr_cookie),
-	/*
-	 * not currently supported
-	 * int:	priority
-	 * void *: ptr to binder
-	 * void *: cookie for binder
-	 */
-
-	BR_NOOP = _IO('r', 12),
-	/*
-	 * No parameters.  Do nothing and examine the next command.  It exists
-	 * primarily so that we can replace it with a BR_SPAWN_LOOPER command.
-	 */
-
-	BR_SPAWN_LOOPER = _IO('r', 13),
-	/*
-	 * No parameters.  The driver has determined that a process has no
-	 * threads waiting to service incoming transactions.  When a process
-	 * receives this command, it must spawn a new service thread and
-	 * register it via bcENTER_LOOPER.
-	 */
-
-	BR_FINISHED = _IO('r', 14),
-	/*
-	 * not currently supported
-	 * stop threadpool thread
-	 */
-
-	BR_DEAD_BINDER = _IOR('r', 15, binder_uintptr_t),
-	/*
-	 * void *: cookie
-	 */
-	BR_CLEAR_DEATH_NOTIFICATION_DONE = _IOR('r', 16, binder_uintptr_t),
-	/*
-	 * void *: cookie
-	 */
-
-	BR_FAILED_REPLY = _IO('r', 17),
-	/*
-	 * The the last transaction (either a bcTRANSACTION or
-	 * a bcATTEMPT_ACQUIRE) failed (e.g. out of memory).  No parameters.
-	 */
-};
-
-enum binder_driver_command_protocol {
-	BC_TRANSACTION = _IOW('c', 0, struct binder_transaction_data),
-	BC_REPLY = _IOW('c', 1, struct binder_transaction_data),
-	/*
-	 * binder_transaction_data: the sent command.
-	 */
-
-	BC_ACQUIRE_RESULT = _IOW('c', 2, __s32),
-	/*
-	 * not currently supported
-	 * int:  0 if the last BR_ATTEMPT_ACQUIRE was not successful.
-	 * Else you have acquired a primary reference on the object.
-	 */
-
-	BC_FREE_BUFFER = _IOW('c', 3, binder_uintptr_t),
-	/*
-	 * void *: ptr to transaction data received on a read
-	 */
-
-	BC_INCREFS = _IOW('c', 4, __u32),
-	BC_ACQUIRE = _IOW('c', 5, __u32),
-	BC_RELEASE = _IOW('c', 6, __u32),
-	BC_DECREFS = _IOW('c', 7, __u32),
-	/*
-	 * int:	descriptor
-	 */
-
-	BC_INCREFS_DONE = _IOW('c', 8, struct binder_ptr_cookie),
-	BC_ACQUIRE_DONE = _IOW('c', 9, struct binder_ptr_cookie),
-	/*
-	 * void *: ptr to binder
-	 * void *: cookie for binder
-	 */
-
-	BC_ATTEMPT_ACQUIRE = _IOW('c', 10, struct binder_pri_desc),
-	/*
-	 * not currently supported
-	 * int: priority
-	 * int: descriptor
-	 */
-
-	BC_REGISTER_LOOPER = _IO('c', 11),
-	/*
-	 * No parameters.
-	 * Register a spawned looper thread with the device.
-	 */
-
-	BC_ENTER_LOOPER = _IO('c', 12),
-	BC_EXIT_LOOPER = _IO('c', 13),
-	/*
-	 * No parameters.
-	 * These two commands are sent as an application-level thread
-	 * enters and exits the binder loop, respectively.  They are
-	 * used so the binder can have an accurate count of the number
-	 * of looping threads it has available.
-	 */
-
-	BC_REQUEST_DEATH_NOTIFICATION = _IOW('c', 14,
-						struct binder_handle_cookie),
-	/*
-	 * int: handle
-	 * void *: cookie
-	 */
-
-	BC_CLEAR_DEATH_NOTIFICATION = _IOW('c', 15,
-						struct binder_handle_cookie),
-	/*
-	 * int: handle
-	 * void *: cookie
-	 */
-
-	BC_DEAD_BINDER_DONE = _IOW('c', 16, binder_uintptr_t),
-	/*
-	 * void *: cookie
-	 */
-};
-
-#endif /* _UAPI_LINUX_BINDER_H */
-
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 6cad97485ba..5f17fa7bc15 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -1,4 +1,5 @@
 # UAPI Header export list
+header-y += android/
 header-y += byteorder/
 header-y += can/
 header-y += caif/
diff --git a/include/uapi/linux/android/Kbuild b/include/uapi/linux/android/Kbuild
new file mode 100644
index 00000000000..ca011eec252
--- /dev/null
+++ b/include/uapi/linux/android/Kbuild
@@ -0,0 +1,2 @@
+# UAPI Header export list
+header-y += binder.h
diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h
new file mode 100644
index 00000000000..dba4cef3a8d
--- /dev/null
+++ b/include/uapi/linux/android/binder.h
@@ -0,0 +1,351 @@
+/*
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * Based on, but no longer compatible with, the original
+ * OpenBinder.org binder driver interface, which is:
+ *
+ * Copyright (c) 2005 Palmsource, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_LINUX_BINDER_H
+#define _UAPI_LINUX_BINDER_H
+
+#include <linux/ioctl.h>
+
+#define B_PACK_CHARS(c1, c2, c3, c4) \
+	((((c1)<<24)) | (((c2)<<16)) | (((c3)<<8)) | (c4))
+#define B_TYPE_LARGE 0x85
+
+enum {
+	BINDER_TYPE_BINDER	= B_PACK_CHARS('s', 'b', '*', B_TYPE_LARGE),
+	BINDER_TYPE_WEAK_BINDER	= B_PACK_CHARS('w', 'b', '*', B_TYPE_LARGE),
+	BINDER_TYPE_HANDLE	= B_PACK_CHARS('s', 'h', '*', B_TYPE_LARGE),
+	BINDER_TYPE_WEAK_HANDLE	= B_PACK_CHARS('w', 'h', '*', B_TYPE_LARGE),
+	BINDER_TYPE_FD		= B_PACK_CHARS('f', 'd', '*', B_TYPE_LARGE),
+};
+
+enum {
+	FLAT_BINDER_FLAG_PRIORITY_MASK = 0xff,
+	FLAT_BINDER_FLAG_ACCEPTS_FDS = 0x100,
+};
+
+#ifdef BINDER_IPC_32BIT
+typedef __u32 binder_size_t;
+typedef __u32 binder_uintptr_t;
+#else
+typedef __u64 binder_size_t;
+typedef __u64 binder_uintptr_t;
+#endif
+
+/*
+ * This is the flattened representation of a Binder object for transfer
+ * between processes.  The 'offsets' supplied as part of a binder transaction
+ * contains offsets into the data where these structures occur.  The Binder
+ * driver takes care of re-writing the structure type and data as it moves
+ * between processes.
+ */
+struct flat_binder_object {
+	/* 8 bytes for large_flat_header. */
+	__u32		type;
+	__u32		flags;
+
+	/* 8 bytes of data. */
+	union {
+		binder_uintptr_t	binder;	/* local object */
+		__u32			handle;	/* remote object */
+	};
+
+	/* extra data associated with local object */
+	binder_uintptr_t	cookie;
+};
+
+/*
+ * On 64-bit platforms where user code may run in 32-bits the driver must
+ * translate the buffer (and local binder) addresses appropriately.
+ */
+
+struct binder_write_read {
+	binder_size_t		write_size;	/* bytes to write */
+	binder_size_t		write_consumed;	/* bytes consumed by driver */
+	binder_uintptr_t	write_buffer;
+	binder_size_t		read_size;	/* bytes to read */
+	binder_size_t		read_consumed;	/* bytes consumed by driver */
+	binder_uintptr_t	read_buffer;
+};
+
+/* Use with BINDER_VERSION, driver fills in fields. */
+struct binder_version {
+	/* driver protocol version -- increment with incompatible change */
+	__s32       protocol_version;
+};
+
+/* This is the current protocol version. */
+#ifdef BINDER_IPC_32BIT
+#define BINDER_CURRENT_PROTOCOL_VERSION 7
+#else
+#define BINDER_CURRENT_PROTOCOL_VERSION 8
+#endif
+
+#define BINDER_WRITE_READ		_IOWR('b', 1, struct binder_write_read)
+#define BINDER_SET_IDLE_TIMEOUT		_IOW('b', 3, __s64)
+#define BINDER_SET_MAX_THREADS		_IOW('b', 5, __u32)
+#define BINDER_SET_IDLE_PRIORITY	_IOW('b', 6, __s32)
+#define BINDER_SET_CONTEXT_MGR		_IOW('b', 7, __s32)
+#define BINDER_THREAD_EXIT		_IOW('b', 8, __s32)
+#define BINDER_VERSION			_IOWR('b', 9, struct binder_version)
+
+/*
+ * NOTE: Two special error codes you should check for when calling
+ * in to the driver are:
+ *
+ * EINTR -- The operation has been interupted.  This should be
+ * handled by retrying the ioctl() until a different error code
+ * is returned.
+ *
+ * ECONNREFUSED -- The driver is no longer accepting operations
+ * from your process.  That is, the process is being destroyed.
+ * You should handle this by exiting from your process.  Note
+ * that once this error code is returned, all further calls to
+ * the driver from any thread will return this same code.
+ */
+
+enum transaction_flags {
+	TF_ONE_WAY	= 0x01,	/* this is a one-way call: async, no return */
+	TF_ROOT_OBJECT	= 0x04,	/* contents are the component's root object */
+	TF_STATUS_CODE	= 0x08,	/* contents are a 32-bit status code */
+	TF_ACCEPT_FDS	= 0x10,	/* allow replies with file descriptors */
+};
+
+struct binder_transaction_data {
+	/* The first two are only used for bcTRANSACTION and brTRANSACTION,
+	 * identifying the target and contents of the transaction.
+	 */
+	union {
+		/* target descriptor of command transaction */
+		__u32	handle;
+		/* target descriptor of return transaction */
+		binder_uintptr_t ptr;
+	} target;
+	binder_uintptr_t	cookie;	/* target object cookie */
+	__u32		code;		/* transaction command */
+
+	/* General information about the transaction. */
+	__u32	        flags;
+	pid_t		sender_pid;
+	uid_t		sender_euid;
+	binder_size_t	data_size;	/* number of bytes of data */
+	binder_size_t	offsets_size;	/* number of bytes of offsets */
+
+	/* If this transaction is inline, the data immediately
+	 * follows here; otherwise, it ends with a pointer to
+	 * the data buffer.
+	 */
+	union {
+		struct {
+			/* transaction data */
+			binder_uintptr_t	buffer;
+			/* offsets from buffer to flat_binder_object structs */
+			binder_uintptr_t	offsets;
+		} ptr;
+		__u8	buf[8];
+	} data;
+};
+
+struct binder_ptr_cookie {
+	binder_uintptr_t ptr;
+	binder_uintptr_t cookie;
+};
+
+struct binder_handle_cookie {
+	__u32 handle;
+	binder_uintptr_t cookie;
+} __packed;
+
+struct binder_pri_desc {
+	__s32 priority;
+	__u32 desc;
+};
+
+struct binder_pri_ptr_cookie {
+	__s32 priority;
+	binder_uintptr_t ptr;
+	binder_uintptr_t cookie;
+};
+
+enum binder_driver_return_protocol {
+	BR_ERROR = _IOR('r', 0, __s32),
+	/*
+	 * int: error code
+	 */
+
+	BR_OK = _IO('r', 1),
+	/* No parameters! */
+
+	BR_TRANSACTION = _IOR('r', 2, struct binder_transaction_data),
+	BR_REPLY = _IOR('r', 3, struct binder_transaction_data),
+	/*
+	 * binder_transaction_data: the received command.
+	 */
+
+	BR_ACQUIRE_RESULT = _IOR('r', 4, __s32),
+	/*
+	 * not currently supported
+	 * int: 0 if the last bcATTEMPT_ACQUIRE was not successful.
+	 * Else the remote object has acquired a primary reference.
+	 */
+
+	BR_DEAD_REPLY = _IO('r', 5),
+	/*
+	 * The target of the last transaction (either a bcTRANSACTION or
+	 * a bcATTEMPT_ACQUIRE) is no longer with us.  No parameters.
+	 */
+
+	BR_TRANSACTION_COMPLETE = _IO('r', 6),
+	/*
+	 * No parameters... always refers to the last transaction requested
+	 * (including replies).  Note that this will be sent even for
+	 * asynchronous transactions.
+	 */
+
+	BR_INCREFS = _IOR('r', 7, struct binder_ptr_cookie),
+	BR_ACQUIRE = _IOR('r', 8, struct binder_ptr_cookie),
+	BR_RELEASE = _IOR('r', 9, struct binder_ptr_cookie),
+	BR_DECREFS = _IOR('r', 10, struct binder_ptr_cookie),
+	/*
+	 * void *:	ptr to binder
+	 * void *: cookie for binder
+	 */
+
+	BR_ATTEMPT_ACQUIRE = _IOR('r', 11, struct binder_pri_ptr_cookie),
+	/*
+	 * not currently supported
+	 * int:	priority
+	 * void *: ptr to binder
+	 * void *: cookie for binder
+	 */
+
+	BR_NOOP = _IO('r', 12),
+	/*
+	 * No parameters.  Do nothing and examine the next command.  It exists
+	 * primarily so that we can replace it with a BR_SPAWN_LOOPER command.
+	 */
+
+	BR_SPAWN_LOOPER = _IO('r', 13),
+	/*
+	 * No parameters.  The driver has determined that a process has no
+	 * threads waiting to service incoming transactions.  When a process
+	 * receives this command, it must spawn a new service thread and
+	 * register it via bcENTER_LOOPER.
+	 */
+
+	BR_FINISHED = _IO('r', 14),
+	/*
+	 * not currently supported
+	 * stop threadpool thread
+	 */
+
+	BR_DEAD_BINDER = _IOR('r', 15, binder_uintptr_t),
+	/*
+	 * void *: cookie
+	 */
+	BR_CLEAR_DEATH_NOTIFICATION_DONE = _IOR('r', 16, binder_uintptr_t),
+	/*
+	 * void *: cookie
+	 */
+
+	BR_FAILED_REPLY = _IO('r', 17),
+	/*
+	 * The the last transaction (either a bcTRANSACTION or
+	 * a bcATTEMPT_ACQUIRE) failed (e.g. out of memory).  No parameters.
+	 */
+};
+
+enum binder_driver_command_protocol {
+	BC_TRANSACTION = _IOW('c', 0, struct binder_transaction_data),
+	BC_REPLY = _IOW('c', 1, struct binder_transaction_data),
+	/*
+	 * binder_transaction_data: the sent command.
+	 */
+
+	BC_ACQUIRE_RESULT = _IOW('c', 2, __s32),
+	/*
+	 * not currently supported
+	 * int:  0 if the last BR_ATTEMPT_ACQUIRE was not successful.
+	 * Else you have acquired a primary reference on the object.
+	 */
+
+	BC_FREE_BUFFER = _IOW('c', 3, binder_uintptr_t),
+	/*
+	 * void *: ptr to transaction data received on a read
+	 */
+
+	BC_INCREFS = _IOW('c', 4, __u32),
+	BC_ACQUIRE = _IOW('c', 5, __u32),
+	BC_RELEASE = _IOW('c', 6, __u32),
+	BC_DECREFS = _IOW('c', 7, __u32),
+	/*
+	 * int:	descriptor
+	 */
+
+	BC_INCREFS_DONE = _IOW('c', 8, struct binder_ptr_cookie),
+	BC_ACQUIRE_DONE = _IOW('c', 9, struct binder_ptr_cookie),
+	/*
+	 * void *: ptr to binder
+	 * void *: cookie for binder
+	 */
+
+	BC_ATTEMPT_ACQUIRE = _IOW('c', 10, struct binder_pri_desc),
+	/*
+	 * not currently supported
+	 * int: priority
+	 * int: descriptor
+	 */
+
+	BC_REGISTER_LOOPER = _IO('c', 11),
+	/*
+	 * No parameters.
+	 * Register a spawned looper thread with the device.
+	 */
+
+	BC_ENTER_LOOPER = _IO('c', 12),
+	BC_EXIT_LOOPER = _IO('c', 13),
+	/*
+	 * No parameters.
+	 * These two commands are sent as an application-level thread
+	 * enters and exits the binder loop, respectively.  They are
+	 * used so the binder can have an accurate count of the number
+	 * of looping threads it has available.
+	 */
+
+	BC_REQUEST_DEATH_NOTIFICATION = _IOW('c', 14,
+						struct binder_handle_cookie),
+	/*
+	 * int: handle
+	 * void *: cookie
+	 */
+
+	BC_CLEAR_DEATH_NOTIFICATION = _IOW('c', 15,
+						struct binder_handle_cookie),
+	/*
+	 * int: handle
+	 * void *: cookie
+	 */
+
+	BC_DEAD_BINDER_DONE = _IOW('c', 16, binder_uintptr_t),
+	/*
+	 * void *: cookie
+	 */
+};
+
+#endif /* _UAPI_LINUX_BINDER_H */
+
-- 
cgit v1.2.3-70-g09d2


From bc2d62a01b336983b8abd1cb2337f305352f29ef Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Thu, 16 Oct 2014 15:22:30 +0200
Subject: android: uapi: binder.h

add types.h to .h file to pass the checker scripts, and provide a proper
uapi .h file.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/android/binder.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h
index dba4cef3a8d..41420e341e7 100644
--- a/include/uapi/linux/android/binder.h
+++ b/include/uapi/linux/android/binder.h
@@ -20,6 +20,7 @@
 #ifndef _UAPI_LINUX_BINDER_H
 #define _UAPI_LINUX_BINDER_H
 
+#include <linux/types.h>
 #include <linux/ioctl.h>
 
 #define B_PACK_CHARS(c1, c2, c3, c4) \
-- 
cgit v1.2.3-70-g09d2


From 729de41baf63e2172b9d61de61bbd53f231095ca Mon Sep 17 00:00:00 2001
From: Dinh Nguyen <dinguyen@opensource.altera.com>
Date: Fri, 10 Oct 2014 10:21:14 -0500
Subject: reset: add reset_control_status helper function

There are cases where a system will want to read a reset status bit before
doing any other toggling. Add a reset_control_status helper function to the
reset controller API.

Signed-off-by: Dinh Nguyen <dinguyen@opensource.altera.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/reset/core.c             | 15 +++++++++++++++
 include/linux/reset-controller.h |  2 ++
 include/linux/reset.h            |  7 +++++++
 3 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/drivers/reset/core.c b/drivers/reset/core.c
index baeaf82d40d..7955e00d04d 100644
--- a/drivers/reset/core.c
+++ b/drivers/reset/core.c
@@ -125,6 +125,21 @@ int reset_control_deassert(struct reset_control *rstc)
 }
 EXPORT_SYMBOL_GPL(reset_control_deassert);
 
+/**
+ * reset_control_status - returns a negative errno if not supported, a
+ * positive value if the reset line is asserted, or zero if the reset
+ * line is not asserted.
+ * @rstc: reset controller
+ */
+int reset_control_status(struct reset_control *rstc)
+{
+	if (rstc->rcdev->ops->status)
+		return rstc->rcdev->ops->status(rstc->rcdev, rstc->id);
+
+	return -ENOSYS;
+}
+EXPORT_SYMBOL_GPL(reset_control_status);
+
 /**
  * of_reset_control_get - Lookup and obtain a reference to a reset controller.
  * @node: device to be reset by the controller
diff --git a/include/linux/reset-controller.h b/include/linux/reset-controller.h
index 41a4695fde0..ce6b962ffed 100644
--- a/include/linux/reset-controller.h
+++ b/include/linux/reset-controller.h
@@ -12,11 +12,13 @@ struct reset_controller_dev;
  *         things to reset the device
  * @assert: manually assert the reset line, if supported
  * @deassert: manually deassert the reset line, if supported
+ * @status: return the status of the reset line, if supported
  */
 struct reset_control_ops {
 	int (*reset)(struct reset_controller_dev *rcdev, unsigned long id);
 	int (*assert)(struct reset_controller_dev *rcdev, unsigned long id);
 	int (*deassert)(struct reset_controller_dev *rcdev, unsigned long id);
+	int (*status)(struct reset_controller_dev *rcdev, unsigned long id);
 };
 
 struct module;
diff --git a/include/linux/reset.h b/include/linux/reset.h
index 349f150ae12..da5602bd77d 100644
--- a/include/linux/reset.h
+++ b/include/linux/reset.h
@@ -10,6 +10,7 @@ struct reset_control;
 int reset_control_reset(struct reset_control *rstc);
 int reset_control_assert(struct reset_control *rstc);
 int reset_control_deassert(struct reset_control *rstc);
+int reset_control_status(struct reset_control *rstc);
 
 struct reset_control *reset_control_get(struct device *dev, const char *id);
 void reset_control_put(struct reset_control *rstc);
@@ -57,6 +58,12 @@ static inline int reset_control_deassert(struct reset_control *rstc)
 	return 0;
 }
 
+static inline int reset_control_status(struct reset_control *rstc)
+{
+	WARN_ON(1);
+	return 0;
+}
+
 static inline void reset_control_put(struct reset_control *rstc)
 {
 	WARN_ON(1);
-- 
cgit v1.2.3-70-g09d2


From 40eb90a18e93fbd4fd0e6892b31241356c3c8e43 Mon Sep 17 00:00:00 2001
From: Anatol Pomozov <anatol.pomozov@gmail.com>
Date: Fri, 10 Oct 2014 20:46:36 -0700
Subject: ASoC: rt5677: Add option to configure gpio as
 floating/pullup/pulldown

gpio_config is array of 6 elements that allows to set GPIO as
floating, pullup, pulldown.

Sponsored: Google ChromeOS
Signed-off-by: Anatol Pomozov <anatol.pomozov@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/rt5677.txt |  7 ++++
 include/sound/rt5677.h                             |  3 ++
 sound/soc/codecs/rt5677.c                          | 39 ++++++++++++++++++++++
 3 files changed, 49 insertions(+)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/sound/rt5677.txt b/Documentation/devicetree/bindings/sound/rt5677.txt
index 0701b834fc7..f82f0e906cd 100644
--- a/Documentation/devicetree/bindings/sound/rt5677.txt
+++ b/Documentation/devicetree/bindings/sound/rt5677.txt
@@ -27,6 +27,12 @@ Optional properties:
   Boolean. Indicate MIC1/2 input and LOUT1/2/3 outputs are differential,
   rather than single-ended.
 
+- realtek,gpio-config
+  Array of six 8bit elements that configures GPIO.
+    0 - floating (reset value)
+    1 - pull down
+    2 - pull up
+
 Pins on the device (for linking into audio routes):
 
   * IN1P
@@ -56,4 +62,5 @@ rt5677 {
 	realtek,pow-ldo2-gpio =
 		<&gpio TEGRA_GPIO(V, 3) GPIO_ACTIVE_HIGH>;
 	realtek,in1-differential = "true";
+	realtek,gpio-config = /bits/ 8  <0 0 0 0 0 2>;   /* pull up GPIO6 */
 };
diff --git a/include/sound/rt5677.h b/include/sound/rt5677.h
index 082670e3a35..a56b429a1db 100644
--- a/include/sound/rt5677.h
+++ b/include/sound/rt5677.h
@@ -27,6 +27,9 @@ struct rt5677_platform_data {
 	bool lout3_diff;
 	/* DMIC2 clock source selection */
 	enum rt5677_dmic2_clk dmic2_clk_pin;
+
+	/* configures GPIO, 0 - floating, 1 - pulldown, 2 - pullup */
+	u8 gpio_config[6];
 };
 
 #endif
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index 16aa4d99a71..a454df39b7a 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -3309,6 +3309,38 @@ static int rt5677_gpio_direction_in(struct gpio_chip *chip, unsigned offset)
 	return 0;
 }
 
+/** Configures the gpio as
+ *   0 - floating
+ *   1 - pull down
+ *   2 - pull up
+ */
+static void rt5677_gpio_config(struct rt5677_priv *rt5677, unsigned offset,
+		int value)
+{
+	int shift;
+
+	switch (offset) {
+	case RT5677_GPIO1 ... RT5677_GPIO2:
+		shift = 2 * (1 - offset);
+		regmap_update_bits(rt5677->regmap,
+			RT5677_PR_BASE + RT5677_DIG_IN_PIN_ST_CTRL2,
+			0x3 << shift,
+			(value & 0x3) << shift);
+		break;
+
+	case RT5677_GPIO3 ... RT5677_GPIO6:
+		shift = 2 * (9 - offset);
+		regmap_update_bits(rt5677->regmap,
+			RT5677_PR_BASE + RT5677_DIG_IN_PIN_ST_CTRL3,
+			0x3 << shift,
+			(value & 0x3) << shift);
+		break;
+
+	default:
+		break;
+	}
+}
+
 static struct gpio_chip rt5677_template_chip = {
 	.label			= "rt5677",
 	.owner			= THIS_MODULE,
@@ -3353,6 +3385,7 @@ static void rt5677_free_gpio(struct i2c_client *i2c)
 static int rt5677_probe(struct snd_soc_codec *codec)
 {
 	struct rt5677_priv *rt5677 = snd_soc_codec_get_drvdata(codec);
+	int i;
 
 	rt5677->codec = codec;
 
@@ -3371,6 +3404,9 @@ static int rt5677_probe(struct snd_soc_codec *codec)
 	regmap_write(rt5677->regmap, RT5677_DIG_MISC, 0x0020);
 	regmap_write(rt5677->regmap, RT5677_PWR_DSP2, 0x0c00);
 
+	for (i = 0; i < RT5677_GPIO_NUM; i++)
+		rt5677_gpio_config(rt5677, i, rt5677->pdata.gpio_config[i]);
+
 	return 0;
 }
 
@@ -3590,6 +3626,9 @@ static int rt5677_parse_dt(struct rt5677_priv *rt5677, struct device_node *np)
 			(rt5677->pow_ldo2 != -ENOENT))
 		return rt5677->pow_ldo2;
 
+	of_property_read_u8_array(np, "realtek,gpio-config",
+		rt5677->pdata.gpio_config, RT5677_GPIO_NUM);
+
 	return 0;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 76f439df50aba1838e06dd01e5f20dada7473f57 Mon Sep 17 00:00:00 2001
From: Markus Pargmann <mpa@pengutronix.de>
Date: Wed, 8 Oct 2014 15:47:05 +0200
Subject: regulator: Add ena_gpio_initialized to regulator_config

Most drivers do not set the ena_gpio field of struct regulator_config
before passing it to the regulator core. This is fine as long as the
gpio identifier that is passed is a positive integer. But the gpio
identifier 0 is also valid. So we are not able to decide wether we got a
real gpio identifier or not based on a 0 in ena_gpio.

To be able to decide if it is a valid gpio that got passed, this patch
adds a ena_gpio_initialized field that should be set if was initialized
with a correct value, either a gpio >= 0 or a negative error number. The
core then checks if ena_gpio or ena_gpio_initialized before handling it
as a gpio. This way we maintain backwards compatibility and fix the
behaviour for gpio number 0.

Signed-off-by: Markus Pargmann <mpa@pengutronix.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/core.c         | 3 ++-
 include/linux/regulator/driver.h | 4 ++++
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index cd87c0c3703..55a87a2722d 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -3650,7 +3650,8 @@ regulator_register(const struct regulator_desc *regulator_desc,
 
 	dev_set_drvdata(&rdev->dev, rdev);
 
-	if (config->ena_gpio && gpio_is_valid(config->ena_gpio)) {
+	if ((config->ena_gpio || config->ena_gpio_initialized) &&
+	    gpio_is_valid(config->ena_gpio)) {
 		ret = regulator_ena_gpio_request(rdev, config);
 		if (ret != 0) {
 			rdev_err(rdev, "Failed to request enable GPIO%d: %d\n",
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index fc0ee0ce832..28da08e4671 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -301,6 +301,9 @@ struct regulator_desc {
  *           NULL).
  * @regmap: regmap to use for core regmap helpers if dev_get_regulator() is
  *          insufficient.
+ * @ena_gpio_initialized: GPIO controlling regulator enable was properly
+ *                        initialized, meaning that >= 0 is a valid gpio
+ *                        identifier and < 0 is a non existent gpio.
  * @ena_gpio: GPIO controlling regulator enable.
  * @ena_gpio_invert: Sense for GPIO enable control.
  * @ena_gpio_flags: Flags to use when calling gpio_request_one()
@@ -312,6 +315,7 @@ struct regulator_config {
 	struct device_node *of_node;
 	struct regmap *regmap;
 
+	bool ena_gpio_initialized;
 	int ena_gpio;
 	unsigned int ena_gpio_invert:1;
 	unsigned int ena_gpio_flags;
-- 
cgit v1.2.3-70-g09d2


From 5356e0da49e61e0de29a5f61996be66e97425217 Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Date: Thu, 16 Oct 2014 18:48:50 +0200
Subject: regulator: max77802: Add header for operating modes

Add a header file for the max77802 constants that could be shared between
the regulator driver and Device Tree source files. Also, remove standby
and off opmodes since only normal and low power are valid operating modes.

Signed-off-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/max77802.c                   |  1 +
 include/dt-bindings/regulator/maxim,max77802.h | 18 ++++++++++++++++++
 include/linux/mfd/max77686.h                   |  7 -------
 3 files changed, 19 insertions(+), 7 deletions(-)
 create mode 100644 include/dt-bindings/regulator/maxim,max77802.h

(limited to 'include')

diff --git a/drivers/regulator/max77802.c b/drivers/regulator/max77802.c
index 3abf99dbf95..5839c4509e1 100644
--- a/drivers/regulator/max77802.c
+++ b/drivers/regulator/max77802.c
@@ -33,6 +33,7 @@
 #include <linux/regulator/of_regulator.h>
 #include <linux/mfd/max77686.h>
 #include <linux/mfd/max77686-private.h>
+#include <dt-bindings/regulator/maxim,max77802.h>
 
 /* Default ramp delay in case it is not manually set */
 #define MAX77802_RAMP_DELAY		100000		/* uV/us */
diff --git a/include/dt-bindings/regulator/maxim,max77802.h b/include/dt-bindings/regulator/maxim,max77802.h
new file mode 100644
index 00000000000..cf28631d710
--- /dev/null
+++ b/include/dt-bindings/regulator/maxim,max77802.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2014 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Device Tree binding constants for the Maxim 77802 PMIC regulators
+ */
+
+#ifndef _DT_BINDINGS_REGULATOR_MAXIM_MAX77802_H
+#define _DT_BINDINGS_REGULATOR_MAXIM_MAX77802_H
+
+/* Regulator operating modes */
+#define MAX77802_OPMODE_LP	1
+#define MAX77802_OPMODE_NORMAL	3
+
+#endif /* _DT_BINDINGS_REGULATOR_MAXIM_MAX77802_H */
diff --git a/include/linux/mfd/max77686.h b/include/linux/mfd/max77686.h
index 7e6dc4b2b79..553f7d09258 100644
--- a/include/linux/mfd/max77686.h
+++ b/include/linux/mfd/max77686.h
@@ -131,13 +131,6 @@ enum max77686_opmode {
 	MAX77686_OPMODE_STANDBY,
 };
 
-enum max77802_opmode {
-	MAX77802_OPMODE_OFF,
-	MAX77802_OPMODE_STANDBY,
-	MAX77802_OPMODE_LP,
-	MAX77802_OPMODE_NORMAL,
-};
-
 struct max77686_opmode_data {
 	int id;
 	int mode;
-- 
cgit v1.2.3-70-g09d2


From 4cbbdb51cc921f95978360fd7a0652d493dadc3e Mon Sep 17 00:00:00 2001
From: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Date: Thu, 18 Sep 2014 14:56:35 -0500
Subject: pci_ids: Add PCI device IDs for F15h M60h

Add F3, F4 device IDs to be used in amd_nb.c and amd64_edac.c

Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: http://lkml.kernel.org/r/1411070195-10177-1-git-send-email-Aravind.Gopalakrishnan@amd.com
Signed-off-by: Borislav Petkov <bp@suse.de>
---
 include/linux/pci_ids.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 1fa99a30181..97fb9f69aae 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -522,6 +522,8 @@
 #define PCI_DEVICE_ID_AMD_15H_M10H_F3	0x1403
 #define PCI_DEVICE_ID_AMD_15H_M30H_NB_F3 0x141d
 #define PCI_DEVICE_ID_AMD_15H_M30H_NB_F4 0x141e
+#define PCI_DEVICE_ID_AMD_15H_M60H_NB_F3 0x1573
+#define PCI_DEVICE_ID_AMD_15H_M60H_NB_F4 0x1574
 #define PCI_DEVICE_ID_AMD_15H_NB_F0	0x1600
 #define PCI_DEVICE_ID_AMD_15H_NB_F1	0x1601
 #define PCI_DEVICE_ID_AMD_15H_NB_F2	0x1602
-- 
cgit v1.2.3-70-g09d2


From 348fec70213835df18a587353b3bdc0481b37c6b Mon Sep 17 00:00:00 2001
From: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Date: Thu, 18 Sep 2014 14:56:58 -0500
Subject: EDAC: Add DDR3 LRDIMM entries to edac_mem_types

F15hM60h adds support for DDR4 and DDR3 LRDIMMs. Add them here.

Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Link: http://lkml.kernel.org/r/1411070218-10258-1-git-send-email-Aravind.Gopalakrishnan@amd.com
[ Boris: improve comments. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
---
 drivers/edac/edac_mc.c | 3 +++
 include/linux/edac.h   | 4 +++-
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index c3893b0ddb1..129ff9c36a7 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -146,6 +146,9 @@ const char * const edac_mem_types[] = {
 	"Rambus XDR",
 	"Unbuffered DDR3 RAM",
 	"Registered DDR3 RAM",
+	"Load-Reduced DDR3 RAM",
+	"Unbuffered DDR4 RAM",
+	"Registered DDR4 RAM",
 };
 EXPORT_SYMBOL_GPL(edac_mem_types);
 
diff --git a/include/linux/edac.h b/include/linux/edac.h
index e1e68da6f35..da3b72e95db 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -194,7 +194,8 @@ static inline char *mc_event_error_type(const unsigned int err_type)
  * @MEM_DDR3:		DDR3 RAM
  * @MEM_RDDR3:		Registered DDR3 RAM
  *			This is a variant of the DDR3 memories.
- * @MEM_DDR4:		DDR4 RAM
+ * @MEM_LRDDR3		Load-Reduced DDR3 memory.
+ * @MEM_DDR4:		Unbuffered DDR4 RAM
  * @MEM_RDDR4:		Registered DDR4 RAM
  *			This is a variant of the DDR4 memories.
  */
@@ -216,6 +217,7 @@ enum mem_type {
 	MEM_XDR,
 	MEM_DDR3,
 	MEM_RDDR3,
+	MEM_LRDDR3,
 	MEM_DDR4,
 	MEM_RDDR4,
 };
-- 
cgit v1.2.3-70-g09d2


From 89c771e5a62b856f4705f189892c489190edaec1 Mon Sep 17 00:00:00 2001
From: Jouni Malinen <jouni@qca.qualcomm.com>
Date: Fri, 10 Oct 2014 20:52:40 +0300
Subject: cfg80211: Convert del_station() callback to use a param struct

This makes it easier to add new parameters for the del_station calls
without having to modify all drivers that use this.

Signed-off-by: Jouni Malinen <jouni@qca.qualcomm.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c         |  4 ++--
 drivers/net/wireless/ath/wil6210/cfg80211.c        |  5 +++--
 .../net/wireless/brcm80211/brcmfmac/wl_cfg80211.c  |  8 +++----
 drivers/net/wireless/mwifiex/cfg80211.c            |  9 ++++----
 drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c  |  4 +++-
 include/net/cfg80211.h                             | 15 +++++++++++--
 net/mac80211/cfg.c                                 |  6 +++---
 net/wireless/nl80211.c                             |  8 ++++---
 net/wireless/rdev-ops.h                            |  7 +++---
 net/wireless/trace.h                               | 25 +++++++++++++++++++---
 10 files changed, 64 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index ba60e37213e..7a5337877a0 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -2976,11 +2976,11 @@ static int ath6kl_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 static const u8 bcast_addr[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
 
 static int ath6kl_del_station(struct wiphy *wiphy, struct net_device *dev,
-			      const u8 *mac)
+			      struct station_del_parameters *params)
 {
 	struct ath6kl *ar = ath6kl_priv(dev);
 	struct ath6kl_vif *vif = netdev_priv(dev);
-	const u8 *addr = mac ? mac : bcast_addr;
+	const u8 *addr = params->mac ? params->mac : bcast_addr;
 
 	return ath6kl_wmi_ap_set_mlme(ar->wmi, vif->fw_vif_idx, WMI_AP_DEAUTH,
 				      addr, WLAN_REASON_PREV_AUTH_NOT_VALID);
diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index d9f4b30dd34..8fdfa3222a6 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -792,12 +792,13 @@ static int wil_cfg80211_stop_ap(struct wiphy *wiphy,
 }
 
 static int wil_cfg80211_del_station(struct wiphy *wiphy,
-				    struct net_device *dev, const u8 *mac)
+				    struct net_device *dev,
+				    struct station_del_parameters *params)
 {
 	struct wil6210_priv *wil = wiphy_to_wil(wiphy);
 
 	mutex_lock(&wil->mutex);
-	wil6210_disconnect(wil, mac);
+	wil6210_disconnect(wil, params->mac);
 	mutex_unlock(&wil->mutex);
 
 	return 0;
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
index 28fa25b509d..1a2e062d3bf 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
@@ -3998,24 +3998,24 @@ brcmf_cfg80211_change_beacon(struct wiphy *wiphy, struct net_device *ndev,
 
 static int
 brcmf_cfg80211_del_station(struct wiphy *wiphy, struct net_device *ndev,
-			   const u8 *mac)
+			   struct station_del_parameters *params)
 {
 	struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
 	struct brcmf_scb_val_le scbval;
 	struct brcmf_if *ifp = netdev_priv(ndev);
 	s32 err;
 
-	if (!mac)
+	if (!params->mac)
 		return -EFAULT;
 
-	brcmf_dbg(TRACE, "Enter %pM\n", mac);
+	brcmf_dbg(TRACE, "Enter %pM\n", params->mac);
 
 	if (ifp->vif == cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif)
 		ifp = cfg->p2p.bss_idx[P2PAPI_BSSCFG_PRIMARY].vif->ifp;
 	if (!check_vif_up(ifp->vif))
 		return -EIO;
 
-	memcpy(&scbval.ea, mac, ETH_ALEN);
+	memcpy(&scbval.ea, params->mac, ETH_ALEN);
 	scbval.val = cpu_to_le32(WLAN_REASON_DEAUTH_LEAVING);
 	err = brcmf_fil_cmd_data_set(ifp, BRCMF_C_SCB_DEAUTHENTICATE_FOR_REASON,
 				     &scbval, sizeof(scbval));
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index 0dd672954ad..71e29c7055d 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -1239,7 +1239,7 @@ static int mwifiex_cfg80211_change_beacon(struct wiphy *wiphy,
  */
 static int
 mwifiex_cfg80211_del_station(struct wiphy *wiphy, struct net_device *dev,
-			     const u8 *mac)
+			     struct station_del_parameters *params)
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
 	struct mwifiex_sta_node *sta_node;
@@ -1248,7 +1248,7 @@ mwifiex_cfg80211_del_station(struct wiphy *wiphy, struct net_device *dev,
 	if (list_empty(&priv->sta_list) || !priv->bss_started)
 		return 0;
 
-	if (!mac || is_broadcast_ether_addr(mac)) {
+	if (!params->mac || is_broadcast_ether_addr(params->mac)) {
 		wiphy_dbg(wiphy, "%s: NULL/broadcast mac address\n", __func__);
 		list_for_each_entry(sta_node, &priv->sta_list, list) {
 			if (mwifiex_send_cmd(priv, HostCmd_CMD_UAP_STA_DEAUTH,
@@ -1258,9 +1258,10 @@ mwifiex_cfg80211_del_station(struct wiphy *wiphy, struct net_device *dev,
 			mwifiex_uap_del_sta_data(priv, sta_node);
 		}
 	} else {
-		wiphy_dbg(wiphy, "%s: mac address %pM\n", __func__, mac);
+		wiphy_dbg(wiphy, "%s: mac address %pM\n", __func__,
+			  params->mac);
 		spin_lock_irqsave(&priv->sta_list_spinlock, flags);
-		sta_node = mwifiex_get_sta_entry(priv, mac);
+		sta_node = mwifiex_get_sta_entry(priv, params->mac);
 		spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
 		if (sta_node) {
 			if (mwifiex_send_cmd(priv, HostCmd_CMD_UAP_STA_DEAUTH,
diff --git a/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
index bd6953af0a0..3d26955da72 100644
--- a/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
+++ b/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
@@ -2856,8 +2856,10 @@ static int cfg80211_rtw_add_station(struct wiphy *wiphy,
 }
 
 static int cfg80211_rtw_del_station(struct wiphy *wiphy,
-				    struct net_device *ndev, const u8 *mac)
+				    struct net_device *ndev,
+				    struct station_del_parameters *params)
 {
+	const u8 *mac = params->mac;
 	int ret = 0;
 	struct list_head *phead, *plist, *ptmp;
 	u8 updated = 0;
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 3f3aaa06adb..ebb69f67197 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -798,6 +798,17 @@ struct station_parameters {
 	bool opmode_notif_used;
 };
 
+/**
+ * struct station_del_parameters - station deletion parameters
+ *
+ * Used to delete a station entry (or all stations).
+ *
+ * @mac: MAC address of the station to remove or NULL to remove all stations
+ */
+struct station_del_parameters {
+	const u8 *mac;
+};
+
 /**
  * enum cfg80211_station_type - the type of station being modified
  * @CFG80211_STA_AP_CLIENT: client of an AP interface
@@ -2132,7 +2143,7 @@ struct cfg80211_qos_map {
  * @stop_ap: Stop being an AP, including stopping beaconing.
  *
  * @add_station: Add a new station.
- * @del_station: Remove a station; @mac may be NULL to remove all stations.
+ * @del_station: Remove a station
  * @change_station: Modify a given station. Note that flags changes are not much
  *	validated in cfg80211, in particular the auth/assoc/authorized flags
  *	might come to the driver in invalid combinations -- make sure to check
@@ -2378,7 +2389,7 @@ struct cfg80211_ops {
 			       const u8 *mac,
 			       struct station_parameters *params);
 	int	(*del_station)(struct wiphy *wiphy, struct net_device *dev,
-			       const u8 *mac);
+			       struct station_del_parameters *params);
 	int	(*change_station)(struct wiphy *wiphy, struct net_device *dev,
 				  const u8 *mac,
 				  struct station_parameters *params);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 4bb2d34b2dd..a1498416ad5 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1225,14 +1225,14 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev,
-				 const u8 *mac)
+				 struct station_del_parameters *params)
 {
 	struct ieee80211_sub_if_data *sdata;
 
 	sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 
-	if (mac)
-		return sta_info_destroy_addr_bss(sdata, mac);
+	if (params->mac)
+		return sta_info_destroy_addr_bss(sdata, params->mac);
 
 	sta_info_flush(sdata);
 	return 0;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d527aa0706c..40cf7b93792 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4398,10 +4398,12 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct net_device *dev = info->user_ptr[1];
-	u8 *mac_addr = NULL;
+	struct station_del_parameters params;
+
+	memset(&params, 0, sizeof(params));
 
 	if (info->attrs[NL80211_ATTR_MAC])
-		mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]);
+		params.mac = nla_data(info->attrs[NL80211_ATTR_MAC]);
 
 	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP &&
 	    dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP_VLAN &&
@@ -4412,7 +4414,7 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info)
 	if (!rdev->ops->del_station)
 		return -EOPNOTSUPP;
 
-	return rdev_del_station(rdev, dev, mac_addr);
+	return rdev_del_station(rdev, dev, &params);
 }
 
 static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq,
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index c09e697bcb1..71b1db3cc64 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -178,11 +178,12 @@ static inline int rdev_add_station(struct cfg80211_registered_device *rdev,
 }
 
 static inline int rdev_del_station(struct cfg80211_registered_device *rdev,
-				   struct net_device *dev, u8 *mac)
+				   struct net_device *dev,
+				   struct station_del_parameters *params)
 {
 	int ret;
-	trace_rdev_del_station(&rdev->wiphy, dev, mac);
-	ret = rdev->ops->del_station(&rdev->wiphy, dev, mac);
+	trace_rdev_del_station(&rdev->wiphy, dev, params);
+	ret = rdev->ops->del_station(&rdev->wiphy, dev, params);
 	trace_rdev_return_int(&rdev->wiphy, ret);
 	return ret;
 }
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 8e4f8f04332..b1339400631 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -680,9 +680,28 @@ DECLARE_EVENT_CLASS(wiphy_netdev_mac_evt,
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(sta_mac))
 );
 
-DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_del_station,
-	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *mac),
-	TP_ARGS(wiphy, netdev, mac)
+DECLARE_EVENT_CLASS(station_del,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 struct station_del_parameters *params),
+	TP_ARGS(wiphy, netdev, params),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(sta_mac)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(sta_mac, params->mac);
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: " MAC_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(sta_mac))
+);
+
+DEFINE_EVENT(station_del, rdev_del_station,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 struct station_del_parameters *params),
+	TP_ARGS(wiphy, netdev, params)
 );
 
 DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_get_station,
-- 
cgit v1.2.3-70-g09d2


From 988568669d171774b96e59fe35ef575df7f8cffd Mon Sep 17 00:00:00 2001
From: Jouni Malinen <jouni@qca.qualcomm.com>
Date: Mon, 20 Oct 2014 13:20:45 +0300
Subject: cfg80211: Specify frame and reason code for NL80211_CMD_DEL_STATION

The optional NL80211_ATTR_MGMT_SUBTYPE and NL80211_ATTR_REASON_CODE
attributes can now be included in NL80211_CMD_DEL_STATION to indicate to
the driver which frame (Deauthentication/Disassociation) and reason code
in that frame should be used to indicate removal to the specific
station. This is used by drivers that implement AP SME and generate
those frames internally.

Signed-off-by: Jouni Malinen <jouni@qca.qualcomm.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  5 +++++
 include/uapi/linux/nl80211.h |  6 +++++-
 net/wireless/nl80211.c       | 21 +++++++++++++++++++++
 net/wireless/trace.h         | 10 ++++++++--
 4 files changed, 39 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index ebb69f67197..ed896c0b5b8 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -804,9 +804,14 @@ struct station_parameters {
  * Used to delete a station entry (or all stations).
  *
  * @mac: MAC address of the station to remove or NULL to remove all stations
+ * @subtype: Management frame subtype to use for indicating removal
+ *	(10 = Disassociation, 12 = Deauthentication)
+ * @reason_code: Reason code for the Disassociation/Deauthentication frame
  */
 struct station_del_parameters {
 	const u8 *mac;
+	u8 subtype;
+	u16 reason_code;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 846071b0cde..b553c48404d 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -227,7 +227,11 @@
  *	the interface identified by %NL80211_ATTR_IFINDEX.
  * @NL80211_CMD_DEL_STATION: Remove a station identified by %NL80211_ATTR_MAC
  *	or, if no MAC address given, all stations, on the interface identified
- *	by %NL80211_ATTR_IFINDEX.
+ *	by %NL80211_ATTR_IFINDEX. %NL80211_ATTR_MGMT_SUBTYPE and
+ *	%NL80211_ATTR_REASON_CODE can optionally be used to specify which type
+ *	of disconnection indication should be sent to the station
+ *	(Deauthentication or Disassociation frame and reason code for that
+ *	frame).
  *
  * @NL80211_CMD_GET_MPATH: Get mesh path attributes for mesh path to
  * 	destination %NL80211_ATTR_MAC on the interface identified by
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 40cf7b93792..0c0f2045e1f 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4414,6 +4414,27 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info)
 	if (!rdev->ops->del_station)
 		return -EOPNOTSUPP;
 
+	if (info->attrs[NL80211_ATTR_MGMT_SUBTYPE]) {
+		params.subtype =
+			nla_get_u8(info->attrs[NL80211_ATTR_MGMT_SUBTYPE]);
+		if (params.subtype != IEEE80211_STYPE_DISASSOC >> 4 &&
+		    params.subtype != IEEE80211_STYPE_DEAUTH >> 4)
+			return -EINVAL;
+	} else {
+		/* Default to Deauthentication frame */
+		params.subtype = IEEE80211_STYPE_DEAUTH >> 4;
+	}
+
+	if (info->attrs[NL80211_ATTR_REASON_CODE]) {
+		params.reason_code =
+			nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]);
+		if (params.reason_code == 0)
+			return -EINVAL; /* 0 is reserved */
+	} else {
+		/* Default to reason code 2 */
+		params.reason_code = WLAN_REASON_PREV_AUTH_NOT_VALID;
+	}
+
 	return rdev_del_station(rdev, dev, &params);
 }
 
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index b1339400631..cdb2c2ef1ae 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -688,14 +688,20 @@ DECLARE_EVENT_CLASS(station_del,
 		WIPHY_ENTRY
 		NETDEV_ENTRY
 		MAC_ENTRY(sta_mac)
+		__field(u8, subtype)
+		__field(u16, reason_code)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
 		NETDEV_ASSIGN;
 		MAC_ASSIGN(sta_mac, params->mac);
+		__entry->subtype = params->subtype;
+		__entry->reason_code = params->reason_code;
 	),
-	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: " MAC_PR_FMT,
-		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(sta_mac))
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: " MAC_PR_FMT
+		  ", subtype: %u, reason_code: %u",
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(sta_mac),
+		  __entry->subtype, __entry->reason_code)
 );
 
 DEFINE_EVENT(station_del, rdev_del_station,
-- 
cgit v1.2.3-70-g09d2


From 9439eb3ab9d1ece6e4ad7baaa4a7f534f9b9dab0 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 3 Sep 2013 10:44:00 +0100
Subject: asm-generic: io: implement relaxed accessor macros as conditional
 wrappers

{read,write}{b,w,l,q}_relaxed are implemented by some architectures in
order to permit memory-mapped I/O accesses with weaker barrier semantics
than the non-relaxed variants.

This patch adds wrappers to asm-generic so that drivers can rely on the
relaxed accessors being available, even if they don't always provide
weaker ordering guarantees. Since some architectures both include
asm-generic/io.h and define some relaxed accessors, the definitions here
are conditional for the time being.

Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 include/asm-generic/io.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index b8fdc57a733..fc8dc0eb203 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -53,18 +53,27 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
 #endif
 
 #define readb __raw_readb
+#ifndef readb_relaxed
+#define readb_relaxed readb
+#endif
 
 #define readw readw
 static inline u16 readw(const volatile void __iomem *addr)
 {
 	return __le16_to_cpu(__raw_readw(addr));
 }
+#ifndef readw_relaxed
+#define readw_relaxed readw
+#endif
 
 #define readl readl
 static inline u32 readl(const volatile void __iomem *addr)
 {
 	return __le32_to_cpu(__raw_readl(addr));
 }
+#ifndef readl_relaxed
+#define readl_relaxed readl
+#endif
 
 #ifndef __raw_writeb
 static inline void __raw_writeb(u8 b, volatile void __iomem *addr)
@@ -88,8 +97,19 @@ static inline void __raw_writel(u32 b, volatile void __iomem *addr)
 #endif
 
 #define writeb __raw_writeb
+#ifndef writeb_relaxed
+#define writeb_relaxed writeb
+#endif
+
 #define writew(b,addr) __raw_writew(__cpu_to_le16(b),addr)
+#ifndef writew_relaxed
+#define writew_relaxed writew
+#endif
+
 #define writel(b,addr) __raw_writel(__cpu_to_le32(b),addr)
+#ifndef writel_relaxed
+#define writel_relaxed writel
+#endif
 
 #ifdef CONFIG_64BIT
 #ifndef __raw_readq
@@ -104,6 +124,9 @@ static inline u64 readq(const volatile void __iomem *addr)
 {
 	return __le64_to_cpu(__raw_readq(addr));
 }
+#ifndef readq_relaxed
+#define readq_relaxed readq
+#endif
 
 #ifndef __raw_writeq
 static inline void __raw_writeq(u64 b, volatile void __iomem *addr)
@@ -113,6 +136,9 @@ static inline void __raw_writeq(u64 b, volatile void __iomem *addr)
 #endif
 
 #define writeq(b, addr) __raw_writeq(__cpu_to_le64(b), addr)
+#ifndef writeq_relaxed
+#define writeq_relaxed writeq
+#endif
 #endif /* CONFIG_64BIT */
 
 #ifndef PCI_IOBASE
-- 
cgit v1.2.3-70-g09d2


From 34b48db66e08ca1c1bc07cf305d672ac940268dc Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 6 Sep 2014 16:08:05 -0700
Subject: block: remove artifical max_hw_sectors cap

Set max_sectors to the value the drivers provides as hardware limit by
default.  Linux had proper I/O throttling for a long time and doesn't
rely on a artifically small maximum I/O size anymore.  By not limiting
the I/O size by default we remove an annoying tuning step required for
most Linux installation.

Note that both the user, and if absolutely required the driver can still
impose a limit for FS requests below max_hw_sectors_kb.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-settings.c       | 4 +---
 drivers/block/aoe/aoeblk.c | 2 +-
 include/linux/blkdev.h     | 1 -
 3 files changed, 2 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index aa02247d227..6ed2cbe5e8c 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -257,9 +257,7 @@ void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_
 		       __func__, max_hw_sectors);
 	}
 
-	limits->max_hw_sectors = max_hw_sectors;
-	limits->max_sectors = min_t(unsigned int, max_hw_sectors,
-				    BLK_DEF_MAX_SECTORS);
+	limits->max_sectors = limits->max_hw_sectors = max_hw_sectors;
 }
 EXPORT_SYMBOL(blk_limits_max_hw_sectors);
 
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index dd73e1ff175..46c282fff10 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -395,7 +395,7 @@ aoeblk_gdalloc(void *vp)
 	WARN_ON(d->flags & DEVFL_TKILL);
 	WARN_ON(d->gd);
 	WARN_ON(d->flags & DEVFL_UP);
-	blk_queue_max_hw_sectors(q, BLK_DEF_MAX_SECTORS);
+	blk_queue_max_hw_sectors(q, 1024);
 	q->backing_dev_info.name = "aoe";
 	q->backing_dev_info.ra_pages = READ_AHEAD / PAGE_CACHE_SIZE;
 	d->bufpool = mp;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0207a78a8d8..74d14dba6fb 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1186,7 +1186,6 @@ extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
 enum blk_default_limits {
 	BLK_MAX_SEGMENTS	= 128,
 	BLK_SAFE_MAX_SECTORS	= 255,
-	BLK_DEF_MAX_SECTORS	= 1024,
 	BLK_MAX_SEGMENT_SIZE	= 65536,
 	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
 };
-- 
cgit v1.2.3-70-g09d2


From e66fcf722a74786c500957608f3230e843960b42 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Tue, 30 Sep 2014 03:15:04 +0100
Subject: spi-nor: Remove spi_nor::read_id operation

There is currently no useful way to override the default
implementation of this operation.  The returned struct spi_device_id
must have a pointer to struct flash_info in its private data, but this
structure is defined inside spi-nor.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/spi-nor/spi-nor.c | 4 +---
 include/linux/mtd/spi-nor.h   | 3 ---
 2 files changed, 1 insertion(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index c51ee52386a..a98c134e51b 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -904,8 +904,6 @@ static int spi_nor_check(struct spi_nor *nor)
 		return -EINVAL;
 	}
 
-	if (!nor->read_id)
-		nor->read_id = spi_nor_read_id;
 	if (!nor->wait_till_ready)
 		nor->wait_till_ready = spi_nor_wait_till_ready;
 
@@ -935,7 +933,7 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	if (info->jedec_id) {
 		const struct spi_device_id *jid;
 
-		jid = nor->read_id(nor);
+		jid = spi_nor_read_id(nor);
 		if (IS_ERR(jid)) {
 			return PTR_ERR(jid);
 		} else if (jid != id) {
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index 046a0a2e4c4..2f27713b3ae 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -139,8 +139,6 @@ enum spi_nor_ops {
  * @write_xfer:		[OPTIONAL] the writefundamental primitive
  * @read_reg:		[DRIVER-SPECIFIC] read out the register
  * @write_reg:		[DRIVER-SPECIFIC] write data to the register
- * @read_id:		[REPLACEABLE] read out the ID data, and find
- *			the proper spi_device_id
  * @wait_till_ready:	[REPLACEABLE] wait till the NOR becomes ready
  * @read:		[DRIVER-SPECIFIC] read data from the SPI NOR
  * @write:		[DRIVER-SPECIFIC] write data to the SPI NOR
@@ -172,7 +170,6 @@ struct spi_nor {
 	int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len);
 	int (*write_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len,
 			int write_enable);
-	const struct spi_device_id *(*read_id)(struct spi_nor *nor);
 	int (*wait_till_ready)(struct spi_nor *nor);
 
 	int (*read)(struct spi_nor *nor, loff_t from,
-- 
cgit v1.2.3-70-g09d2


From 723e73acd16d2ea08cdbd8b449b7bc69389b94d4 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 22 Oct 2014 09:25:06 +0200
Subject: cfg80211: make WMM TSPEC support flag an nl80211 feature flag

During the review of the corresponding wpa_supplicant patches we
noticed that the only way for it to detect that this functionality
is supported currently is to check for the command support. This
can be misleading though, as the command was also designed to, in
the future, support pure 802.11 TSPECs.

Expose the WMM-TSPEC feature flag to nl80211 so later we can also
expose an 802.11-TSPEC feature flag (if needed) to differentiate
the two cases.

Note: this change isn't needed in 3.18 as there's no driver there
yet that supports the functionality at all.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  6 +-----
 include/uapi/linux/nl80211.h |  5 +++++
 net/wireless/nl80211.c       | 14 ++++++--------
 3 files changed, 12 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index ed896c0b5b8..77aa805d7e7 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2646,13 +2646,9 @@ struct cfg80211_ops {
  * @WIPHY_FLAG_SUPPORTS_5_10_MHZ: Device supports 5 MHz and 10 MHz channels.
  * @WIPHY_FLAG_HAS_CHANNEL_SWITCH: Device supports channel switch in
  *	beaconing mode (AP, IBSS, Mesh, ...).
- * @WIPHY_FLAG_SUPPORTS_WMM_ADMISSION: the device supports setting up WMM
- *	TSPEC sessions (TID aka TSID 0-7) with the NL80211_CMD_ADD_TX_TS
- *	command. Standard IEEE 802.11 TSPEC setup is not yet supported, it
- *	needs to be able to handle Block-Ack agreements and other things.
  */
 enum wiphy_flags {
-	WIPHY_FLAG_SUPPORTS_WMM_ADMISSION	= BIT(0),
+	/* use hole at 0 */
 	/* use hole at 1 */
 	/* use hole at 2 */
 	WIPHY_FLAG_NETNS_OK			= BIT(3),
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index b553c48404d..be1d5def304 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -4052,6 +4052,10 @@ enum nl80211_ap_sme_features {
  *	multiplexing powersave, ie. can turn off all but one chain
  *	and then wake the rest up as required after, for example,
  *	rts/cts handshake.
+ * @NL80211_FEATURE_SUPPORTS_WMM_ADMISSION: the device supports setting up WMM
+ *	TSPEC sessions (TID aka TSID 0-7) with the %NL80211_CMD_ADD_TX_TS
+ *	command. Standard IEEE 802.11 TSPEC setup is not yet supported, it
+ *	needs to be able to handle Block-Ack agreements and other things.
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -4080,6 +4084,7 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_ACKTO_ESTIMATION		= 1 << 23,
 	NL80211_FEATURE_STATIC_SMPS			= 1 << 24,
 	NL80211_FEATURE_DYNAMIC_SMPS			= 1 << 25,
+	NL80211_FEATURE_SUPPORTS_WMM_ADMISSION		= 1 << 26,
 };
 
 /**
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d05fe6d6481..d98d4ea2781 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1514,8 +1514,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			if (rdev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH)
 				CMD(channel_switch, CHANNEL_SWITCH);
 			CMD(set_qos_map, SET_QOS_MAP);
-			if (rdev->wiphy.flags &
-					WIPHY_FLAG_SUPPORTS_WMM_ADMISSION)
+			if (rdev->wiphy.features &
+					NL80211_FEATURE_SUPPORTS_WMM_ADMISSION)
 				CMD(add_tx_ts, ADD_TX_TS);
 		}
 		/* add into the if now */
@@ -9557,7 +9557,7 @@ static int nl80211_add_tx_ts(struct sk_buff *skb, struct genl_info *info)
 	u16 admitted_time = 0;
 	int err;
 
-	if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_WMM_ADMISSION))
+	if (!(rdev->wiphy.features & NL80211_FEATURE_SUPPORTS_WMM_ADMISSION))
 		return -EOPNOTSUPP;
 
 	if (!info->attrs[NL80211_ATTR_TSID] || !info->attrs[NL80211_ATTR_MAC] ||
@@ -9573,12 +9573,10 @@ static int nl80211_add_tx_ts(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 
 	/* WMM uses TIDs 0-7 even for TSPEC */
-	if (tsid < IEEE80211_FIRST_TSPEC_TSID) {
-		if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_WMM_ADMISSION))
-			return -EINVAL;
-	} else {
+	if (tsid >= IEEE80211_FIRST_TSPEC_TSID) {
 		/* TODO: handle 802.11 TSPEC/admission control
-		 * need more attributes for that (e.g. BA session requirement)
+		 * need more attributes for that (e.g. BA session requirement);
+		 * change the WMM adminssion test above to allow both then
 		 */
 		return -EINVAL;
 	}
-- 
cgit v1.2.3-70-g09d2


From 02219b3abca59fca81711bfe7ee78df7abad97ce Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 7 Oct 2014 10:38:50 +0300
Subject: mac80211: add WMM admission control support

Use the currently existing APIs between mac80211 and the low
level driver to implement WMM admission control.

The low level driver needs to report the media time used by
each transmitted packet in ieee80211_tx_status. Based on that
information, mac80211 will modify the QoS parameters of the
admission controlled Access Category when the limit is
reached. Once the original QoS parameters can be restored,
mac80211 will do so.

One issue with this approach is that management frames will
also erroneously be downgraded, but the upside is that the
implementation is simple. In the future, it can be extended
to driver- or device-based implementations that are better.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |   3 +-
 net/mac80211/agg-tx.c      |   5 --
 net/mac80211/cfg.c         |  73 +++++++++++++++++++++++
 net/mac80211/ieee80211_i.h |  38 +++++++++++-
 net/mac80211/mlme.c        | 142 +++++++++++++++++++++++++++++++++++++++++++--
 net/mac80211/status.c      |   3 +-
 net/mac80211/wme.c         |  29 ++++++---
 net/mac80211/wme.h         |   2 -
 8 files changed, 272 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 9bb2fc73aea..9dc5e760632 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -739,7 +739,8 @@ struct ieee80211_tx_info {
 			u8 ampdu_ack_len;
 			u8 ampdu_len;
 			u8 antenna;
-			void *status_driver_data[21 / sizeof(void *)];
+			u16 tx_time;
+			void *status_driver_data[19 / sizeof(void *)];
 		} status;
 		struct {
 			struct ieee80211_tx_rate driver_rates[
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index d6986f3aa5c..9242c60048c 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -149,11 +149,6 @@ void ieee80211_assign_tid_tx(struct sta_info *sta, int tid,
 	rcu_assign_pointer(sta->ampdu_mlme.tid_tx[tid], tid_tx);
 }
 
-static inline int ieee80211_ac_from_tid(int tid)
-{
-	return ieee802_1d_to_ac[tid & 7];
-}
-
 /*
  * When multiple aggregation sessions on multiple stations
  * are being created/destroyed simultaneously, we need to
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 64deb9aa0f8..d6b01ad2f7d 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -20,6 +20,7 @@
 #include "cfg.h"
 #include "rate.h"
 #include "mesh.h"
+#include "wme.h"
 
 static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy,
 						const char *name,
@@ -3585,6 +3586,76 @@ static int ieee80211_set_ap_chanwidth(struct wiphy *wiphy,
 	return ret;
 }
 
+static int ieee80211_add_tx_ts(struct wiphy *wiphy, struct net_device *dev,
+			       u8 tsid, const u8 *peer, u8 up,
+			       u16 admitted_time)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	int ac = ieee802_1d_to_ac[up];
+
+	if (sdata->vif.type != NL80211_IFTYPE_STATION)
+		return -EOPNOTSUPP;
+
+	if (!(sdata->wmm_acm & BIT(up)))
+		return -EINVAL;
+
+	if (ifmgd->tx_tspec[ac].admitted_time)
+		return -EBUSY;
+
+	if (admitted_time) {
+		ifmgd->tx_tspec[ac].admitted_time = 32 * admitted_time;
+		ifmgd->tx_tspec[ac].tsid = tsid;
+		ifmgd->tx_tspec[ac].up = up;
+	}
+
+	return 0;
+}
+
+static int ieee80211_del_tx_ts(struct wiphy *wiphy, struct net_device *dev,
+			       u8 tsid, const u8 *peer)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	struct ieee80211_local *local = wiphy_priv(wiphy);
+	int ac;
+
+	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
+		struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac];
+
+		/* skip unused entries */
+		if (!tx_tspec->admitted_time)
+			continue;
+
+		if (tx_tspec->tsid != tsid)
+			continue;
+
+		/* due to this new packets will be reassigned to non-ACM ACs */
+		tx_tspec->up = -1;
+
+		/* Make sure that all packets have been sent to avoid to
+		 * restore the QoS params on packets that are still on the
+		 * queues.
+		 */
+		synchronize_net();
+		ieee80211_flush_queues(local, sdata);
+
+		/* restore the normal QoS parameters
+		 * (unconditionally to avoid races)
+		 */
+		tx_tspec->action = TX_TSPEC_ACTION_STOP_DOWNGRADE;
+		tx_tspec->downgraded = false;
+		ieee80211_sta_handle_tspec_ac_params(sdata);
+
+		/* finally clear all the data */
+		memset(tx_tspec, 0, sizeof(*tx_tspec));
+
+		return 0;
+	}
+
+	return -ENOENT;
+}
+
 const struct cfg80211_ops mac80211_config_ops = {
 	.add_virtual_intf = ieee80211_add_iface,
 	.del_virtual_intf = ieee80211_del_iface,
@@ -3663,4 +3734,6 @@ const struct cfg80211_ops mac80211_config_ops = {
 	.channel_switch = ieee80211_channel_switch,
 	.set_qos_map = ieee80211_set_qos_map,
 	.set_ap_chanwidth = ieee80211_set_ap_chanwidth,
+	.add_tx_ts = ieee80211_add_tx_ts,
+	.del_tx_ts = ieee80211_del_tx_ts,
 };
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 78d6121eb37..60063be057d 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -399,6 +399,24 @@ struct ieee80211_mgd_assoc_data {
 	u8 ie[];
 };
 
+struct ieee80211_sta_tx_tspec {
+	/* timestamp of the first packet in the time slice */
+	unsigned long time_slice_start;
+
+	u32 admitted_time; /* in usecs, unlike over the air */
+	u8 tsid;
+	s8 up; /* signed to be able to invalidate with -1 during teardown */
+
+	/* consumed TX time in microseconds in the time slice */
+	u32 consumed_tx_time;
+	enum {
+		TX_TSPEC_ACTION_NONE = 0,
+		TX_TSPEC_ACTION_DOWNGRADE,
+		TX_TSPEC_ACTION_STOP_DOWNGRADE,
+	} action;
+	bool downgraded;
+};
+
 struct ieee80211_if_managed {
 	struct timer_list timer;
 	struct timer_list conn_mon_timer;
@@ -509,6 +527,16 @@ struct ieee80211_if_managed {
 
 	u8 tdls_peer[ETH_ALEN] __aligned(2);
 	struct delayed_work tdls_peer_del_work;
+
+	/* WMM-AC TSPEC support */
+	struct ieee80211_sta_tx_tspec tx_tspec[IEEE80211_NUM_ACS];
+	/* Use a separate work struct so that we can do something here
+	 * while the sdata->work is flushing the queues, for example.
+	 * otherwise, in scenarios where we hardly get any traffic out
+	 * on the BE queue, but there's a lot of VO traffic, we might
+	 * get stuck in a downgraded situation and flush takes forever.
+	 */
+	struct delayed_work tx_tspec_wk;
 };
 
 struct ieee80211_if_ibss {
@@ -1459,6 +1487,7 @@ void ieee80211_mgd_conn_tx_status(struct ieee80211_sub_if_data *sdata,
 				  __le16 fc, bool acked);
 void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata);
 void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata);
+void ieee80211_sta_handle_tspec_ac_params(struct ieee80211_sub_if_data *sdata);
 
 /* IBSS code */
 void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local);
@@ -1763,6 +1792,13 @@ static inline bool ieee80211_rx_reorder_ready(struct sk_buff_head *frames)
 	return true;
 }
 
+extern const int ieee802_1d_to_ac[8];
+
+static inline int ieee80211_ac_from_tid(int tid)
+{
+	return ieee802_1d_to_ac[tid & 7];
+}
+
 void ieee80211_dynamic_ps_enable_work(struct work_struct *work);
 void ieee80211_dynamic_ps_disable_work(struct work_struct *work);
 void ieee80211_dynamic_ps_timer(unsigned long data);
@@ -1772,7 +1808,7 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local,
 void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata,
 			     struct ieee80211_hdr *hdr);
 void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
-			     struct ieee80211_hdr *hdr, bool ack);
+			     struct ieee80211_hdr *hdr, bool ack, u16 tx_time);
 
 void ieee80211_wake_queues_by_reason(struct ieee80211_hw *hw,
 				     unsigned long queues,
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index fb6561509ca..4d9b4d165ce 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1606,6 +1606,95 @@ void ieee80211_dfs_cac_timer_work(struct work_struct *work)
 	mutex_unlock(&sdata->local->mtx);
 }
 
+static bool
+__ieee80211_sta_handle_tspec_ac_params(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	bool ret;
+	int ac;
+
+	if (local->hw.queues < IEEE80211_NUM_ACS)
+		return false;
+
+	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
+		struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac];
+		int non_acm_ac;
+		unsigned long now = jiffies;
+
+		if (tx_tspec->action == TX_TSPEC_ACTION_NONE &&
+		    tx_tspec->admitted_time &&
+		    time_after(now, tx_tspec->time_slice_start + HZ)) {
+			tx_tspec->consumed_tx_time = 0;
+			tx_tspec->time_slice_start = now;
+
+			if (tx_tspec->downgraded)
+				tx_tspec->action =
+					TX_TSPEC_ACTION_STOP_DOWNGRADE;
+		}
+
+		switch (tx_tspec->action) {
+		case TX_TSPEC_ACTION_STOP_DOWNGRADE:
+			/* take the original parameters */
+			if (drv_conf_tx(local, sdata, ac, &sdata->tx_conf[ac]))
+				sdata_err(sdata,
+					  "failed to set TX queue parameters for queue %d\n",
+					  ac);
+			tx_tspec->action = TX_TSPEC_ACTION_NONE;
+			tx_tspec->downgraded = false;
+			ret = true;
+			break;
+		case TX_TSPEC_ACTION_DOWNGRADE:
+			if (time_after(now, tx_tspec->time_slice_start + HZ)) {
+				tx_tspec->action = TX_TSPEC_ACTION_NONE;
+				ret = true;
+				break;
+			}
+			/* downgrade next lower non-ACM AC */
+			for (non_acm_ac = ac + 1;
+			     non_acm_ac < IEEE80211_NUM_ACS;
+			     non_acm_ac++)
+				if (!(sdata->wmm_acm & BIT(7 - 2 * non_acm_ac)))
+					break;
+			/* The loop will result in using BK even if it requires
+			 * admission control, such configuration makes no sense
+			 * and we have to transmit somehow - the AC selection
+			 * does the same thing.
+			 */
+			if (drv_conf_tx(local, sdata, ac,
+					&sdata->tx_conf[non_acm_ac]))
+				sdata_err(sdata,
+					  "failed to set TX queue parameters for queue %d\n",
+					  ac);
+			tx_tspec->action = TX_TSPEC_ACTION_NONE;
+			ret = true;
+			schedule_delayed_work(&ifmgd->tx_tspec_wk,
+				tx_tspec->time_slice_start + HZ - now + 1);
+			break;
+		case TX_TSPEC_ACTION_NONE:
+			/* nothing now */
+			break;
+		}
+	}
+
+	return ret;
+}
+
+void ieee80211_sta_handle_tspec_ac_params(struct ieee80211_sub_if_data *sdata)
+{
+	if (__ieee80211_sta_handle_tspec_ac_params(sdata))
+		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_QOS);
+}
+
+static void ieee80211_sta_handle_tspec_ac_params_wk(struct work_struct *work)
+{
+	struct ieee80211_sub_if_data *sdata;
+
+	sdata = container_of(work, struct ieee80211_sub_if_data,
+			     u.mgd.tx_tspec_wk.work);
+	ieee80211_sta_handle_tspec_ac_params(sdata);
+}
+
 /* MLME */
 static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
 				     struct ieee80211_sub_if_data *sdata,
@@ -1690,12 +1779,14 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
 		params.uapsd = uapsd;
 
 		mlme_dbg(sdata,
-			 "WMM queue=%d aci=%d acm=%d aifs=%d cWmin=%d cWmax=%d txop=%d uapsd=%d\n",
+			 "WMM queue=%d aci=%d acm=%d aifs=%d cWmin=%d cWmax=%d txop=%d uapsd=%d, downgraded=%d\n",
 			 queue, aci, acm,
 			 params.aifs, params.cw_min, params.cw_max,
-			 params.txop, params.uapsd);
+			 params.txop, params.uapsd,
+			 ifmgd->tx_tspec[queue].downgraded);
 		sdata->tx_conf[queue] = params;
-		if (drv_conf_tx(local, sdata, queue, &params))
+		if (!ifmgd->tx_tspec[queue].downgraded &&
+		    drv_conf_tx(local, sdata, queue, &params))
 			sdata_err(sdata,
 				  "failed to set TX queue parameters for queue %d\n",
 				  queue);
@@ -1958,6 +2049,10 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	}
 	mutex_unlock(&local->mtx);
 
+	/* existing TX TSPEC sessions no longer exist */
+	memset(ifmgd->tx_tspec, 0, sizeof(ifmgd->tx_tspec));
+	cancel_delayed_work_sync(&ifmgd->tx_tspec_wk);
+
 	sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM;
 }
 
@@ -2010,9 +2105,46 @@ out:
 	mutex_unlock(&local->mtx);
 }
 
+static void ieee80211_sta_tx_wmm_ac_notify(struct ieee80211_sub_if_data *sdata,
+					   struct ieee80211_hdr *hdr,
+					   u16 tx_time)
+{
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	u16 tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK;
+	int ac = ieee80211_ac_from_tid(tid);
+	struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac];
+	unsigned long now = jiffies;
+
+	if (likely(!tx_tspec->admitted_time))
+		return;
+
+	if (time_after(now, tx_tspec->time_slice_start + HZ)) {
+		tx_tspec->consumed_tx_time = 0;
+		tx_tspec->time_slice_start = now;
+
+		if (tx_tspec->downgraded) {
+			tx_tspec->action = TX_TSPEC_ACTION_STOP_DOWNGRADE;
+			schedule_delayed_work(&ifmgd->tx_tspec_wk, 0);
+		}
+	}
+
+	if (tx_tspec->downgraded)
+		return;
+
+	tx_tspec->consumed_tx_time += tx_time;
+
+	if (tx_tspec->consumed_tx_time >= tx_tspec->admitted_time) {
+		tx_tspec->downgraded = true;
+		tx_tspec->action = TX_TSPEC_ACTION_DOWNGRADE;
+		schedule_delayed_work(&ifmgd->tx_tspec_wk, 0);
+	}
+}
+
 void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
-			     struct ieee80211_hdr *hdr, bool ack)
+			     struct ieee80211_hdr *hdr, bool ack, u16 tx_time)
 {
+	ieee80211_sta_tx_wmm_ac_notify(sdata, hdr, tx_time);
+
 	if (!ieee80211_is_data(hdr->frame_control))
 	    return;
 
@@ -3834,6 +3966,8 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata)
 		    (unsigned long) sdata);
 	setup_timer(&ifmgd->chswitch_timer, ieee80211_chswitch_timer,
 		    (unsigned long) sdata);
+	INIT_DELAYED_WORK(&ifmgd->tx_tspec_wk,
+			  ieee80211_sta_handle_tspec_ac_params_wk);
 
 	ifmgd->flags = 0;
 	ifmgd->powersave = sdata->wdev.ps;
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 89290e33daf..9612d89fad5 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -704,7 +704,8 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 
 		if ((sta->sdata->vif.type == NL80211_IFTYPE_STATION) &&
 		    (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS))
-			ieee80211_sta_tx_notify(sta->sdata, (void *) skb->data, acked);
+			ieee80211_sta_tx_notify(sta->sdata, (void *) skb->data,
+						acked, info->status.tx_time);
 
 		if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) {
 			if (info->flags & IEEE80211_TX_STAT_ACK) {
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index 3b873989992..d3c5672d775 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -54,10 +54,18 @@ static int wme_downgrade_ac(struct sk_buff *skb)
 }
 
 static u16 ieee80211_downgrade_queue(struct ieee80211_sub_if_data *sdata,
-				     struct sk_buff *skb)
+				     struct sta_info *sta, struct sk_buff *skb)
 {
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+
 	/* in case we are a client verify acm is not set for this ac */
-	while (unlikely(sdata->wmm_acm & BIT(skb->priority))) {
+	while (sdata->wmm_acm & BIT(skb->priority)) {
+		int ac = ieee802_1d_to_ac[skb->priority];
+
+		if (ifmgd->tx_tspec[ac].admitted_time &&
+		    skb->priority == ifmgd->tx_tspec[ac].up)
+			return ac;
+
 		if (wme_downgrade_ac(skb)) {
 			/*
 			 * This should not really happen. The AP has marked all
@@ -96,7 +104,7 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata,
 	p = ieee80211_get_qos_ctl(hdr);
 	skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK;
 
-	return ieee80211_downgrade_queue(sdata, skb);
+	return ieee80211_downgrade_queue(sdata, NULL, skb);
 }
 
 /* Indicate which queue to use. */
@@ -108,6 +116,7 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 	const u8 *ra = NULL;
 	bool qos = false;
 	struct mac80211_qos_map *qos_map;
+	u16 ret;
 
 	if (local->hw.queues < IEEE80211_NUM_ACS || skb->len < 6) {
 		skb->priority = 0; /* required for correct WPA/11i MIC */
@@ -148,27 +157,29 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 		if (sta)
 			qos = sta->sta.wme;
 	}
-	rcu_read_unlock();
 
 	if (!qos) {
 		skb->priority = 0; /* required for correct WPA/11i MIC */
-		return IEEE80211_AC_BE;
+		ret = IEEE80211_AC_BE;
+		goto out;
 	}
 
 	if (skb->protocol == sdata->control_port_protocol) {
 		skb->priority = 7;
-		return ieee80211_downgrade_queue(sdata, skb);
+		goto downgrade;
 	}
 
 	/* use the data classifier to determine what 802.1d tag the
 	 * data frame has */
-	rcu_read_lock();
 	qos_map = rcu_dereference(sdata->qos_map);
 	skb->priority = cfg80211_classify8021d(skb, qos_map ?
 					       &qos_map->qos_map : NULL);
-	rcu_read_unlock();
 
-	return ieee80211_downgrade_queue(sdata, skb);
+ downgrade:
+	ret = ieee80211_downgrade_queue(sdata, sta, skb);
+ out:
+	rcu_read_unlock();
+	return ret;
 }
 
 /**
diff --git a/net/mac80211/wme.h b/net/mac80211/wme.h
index 7fea4bb8acb..80151edc519 100644
--- a/net/mac80211/wme.h
+++ b/net/mac80211/wme.h
@@ -13,8 +13,6 @@
 #include <linux/netdevice.h>
 #include "ieee80211_i.h"
 
-extern const int ieee802_1d_to_ac[8];
-
 u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata,
 				 struct sk_buff *skb,
 				 struct ieee80211_hdr *hdr);
-- 
cgit v1.2.3-70-g09d2


From 5e3363ad1b7b2e1f197a3f56b01e21cb155ad454 Mon Sep 17 00:00:00 2001
From: Oder Chiou <oder_chiou@realtek.com>
Date: Thu, 16 Oct 2014 11:24:26 -0700
Subject: ASoC: rt5677: add GPIO IRQ support

This allows to enable Mic Jack detection feature

Signed-off-by: Oder Chiou <oder_chiou@realtek.com>
Modified-by: Anatol Pomozov <anatol.pomozov@gmail.com>
Signed-off-by: Anatol Pomozov <anatol.pomozov@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/rt5677.txt |  10 ++
 include/sound/rt5677.h                             |   7 ++
 sound/soc/codecs/rt5677.c                          | 134 +++++++++++++++++++++
 sound/soc/codecs/rt5677.h                          |  49 ++++++++
 4 files changed, 200 insertions(+)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/sound/rt5677.txt b/Documentation/devicetree/bindings/sound/rt5677.txt
index f82f0e906cd..740ff771aa8 100644
--- a/Documentation/devicetree/bindings/sound/rt5677.txt
+++ b/Documentation/devicetree/bindings/sound/rt5677.txt
@@ -33,6 +33,15 @@ Optional properties:
     1 - pull down
     2 - pull up
 
+- realtek,jd1-gpio
+  Configures GPIO Mic Jack detection 1.
+  Select 0 ~ 3 as OFF, GPIO1, GPIO2 and GPIO3 respectively.
+
+- realtek,jd2-gpio
+- realtek,jd3-gpio
+  Configures GPIO Mic Jack detection 2 and 3.
+  Select 0 ~ 3 as OFF, GPIO4, GPIO5 and GPIO6 respectively.
+
 Pins on the device (for linking into audio routes):
 
   * IN1P
@@ -63,4 +72,5 @@ rt5677 {
 		<&gpio TEGRA_GPIO(V, 3) GPIO_ACTIVE_HIGH>;
 	realtek,in1-differential = "true";
 	realtek,gpio-config = /bits/ 8  <0 0 0 0 0 2>;   /* pull up GPIO6 */
+	realtek,jd2-gpio = <3>;  /* Enables Jack detection for GPIO6 */
 };
diff --git a/include/sound/rt5677.h b/include/sound/rt5677.h
index a56b429a1db..d9eb7d861cd 100644
--- a/include/sound/rt5677.h
+++ b/include/sound/rt5677.h
@@ -30,6 +30,13 @@ struct rt5677_platform_data {
 
 	/* configures GPIO, 0 - floating, 1 - pulldown, 2 - pullup */
 	u8 gpio_config[6];
+
+	/* jd1 can select 0 ~ 3 as OFF, GPIO1, GPIO2 and GPIO3 respectively */
+	unsigned int jd1_gpio;
+	/* jd2 and jd3 can select 0 ~ 3 as
+		OFF, GPIO4, GPIO5 and GPIO6 respectively */
+	unsigned int jd2_gpio;
+	unsigned int jd3_gpio;
 };
 
 #endif
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index d17d079fdcf..6c73dfd22a0 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -3614,6 +3614,46 @@ static void rt5677_gpio_config(struct rt5677_priv *rt5677, unsigned offset,
 	}
 }
 
+static int rt5677_to_irq(struct gpio_chip *chip, unsigned offset)
+{
+	struct rt5677_priv *rt5677 = gpio_to_rt5677(chip);
+	struct regmap_irq_chip_data *data = rt5677->irq_data;
+	int irq;
+
+	if (offset >= RT5677_GPIO1 && offset <= RT5677_GPIO3) {
+		if ((rt5677->pdata.jd1_gpio == 1 && offset == RT5677_GPIO1) ||
+			(rt5677->pdata.jd1_gpio == 2 &&
+				offset == RT5677_GPIO2) ||
+			(rt5677->pdata.jd1_gpio == 3 &&
+				offset == RT5677_GPIO3)) {
+			irq = RT5677_IRQ_JD1;
+		} else {
+			return -ENXIO;
+		}
+	}
+
+	if (offset >= RT5677_GPIO4 && offset <= RT5677_GPIO6) {
+		if ((rt5677->pdata.jd2_gpio == 1 && offset == RT5677_GPIO4) ||
+			(rt5677->pdata.jd2_gpio == 2 &&
+				offset == RT5677_GPIO5) ||
+			(rt5677->pdata.jd2_gpio == 3 &&
+				offset == RT5677_GPIO6)) {
+			irq = RT5677_IRQ_JD2;
+		} else if ((rt5677->pdata.jd3_gpio == 1 &&
+				offset == RT5677_GPIO4) ||
+			(rt5677->pdata.jd3_gpio == 2 &&
+				offset == RT5677_GPIO5) ||
+			(rt5677->pdata.jd3_gpio == 3 &&
+				offset == RT5677_GPIO6)) {
+			irq = RT5677_IRQ_JD3;
+		} else {
+			return -ENXIO;
+		}
+	}
+
+	return regmap_irq_get_virq(data, irq);
+}
+
 static struct gpio_chip rt5677_template_chip = {
 	.label			= "rt5677",
 	.owner			= THIS_MODULE,
@@ -3621,6 +3661,7 @@ static struct gpio_chip rt5677_template_chip = {
 	.set			= rt5677_gpio_set,
 	.direction_input	= rt5677_gpio_direction_in,
 	.get			= rt5677_gpio_get,
+	.to_irq			= rt5677_to_irq,
 	.can_sleep		= 1,
 };
 
@@ -3685,6 +3726,31 @@ static int rt5677_probe(struct snd_soc_codec *codec)
 	for (i = 0; i < RT5677_GPIO_NUM; i++)
 		rt5677_gpio_config(rt5677, i, rt5677->pdata.gpio_config[i]);
 
+	if (rt5677->irq_data) {
+		regmap_update_bits(rt5677->regmap, RT5677_GPIO_CTRL1, 0x8000,
+			0x8000);
+		regmap_update_bits(rt5677->regmap, RT5677_DIG_MISC, 0x0018,
+			0x0008);
+
+		if (rt5677->pdata.jd1_gpio)
+			regmap_update_bits(rt5677->regmap, RT5677_JD_CTRL1,
+				RT5677_SEL_GPIO_JD1_MASK,
+				rt5677->pdata.jd1_gpio <<
+				RT5677_SEL_GPIO_JD1_SFT);
+
+		if (rt5677->pdata.jd2_gpio)
+			regmap_update_bits(rt5677->regmap, RT5677_JD_CTRL1,
+				RT5677_SEL_GPIO_JD2_MASK,
+				rt5677->pdata.jd2_gpio <<
+				RT5677_SEL_GPIO_JD2_SFT);
+
+		if (rt5677->pdata.jd3_gpio)
+			regmap_update_bits(rt5677->regmap, RT5677_JD_CTRL1,
+				RT5677_SEL_GPIO_JD3_MASK,
+				rt5677->pdata.jd3_gpio <<
+				RT5677_SEL_GPIO_JD3_SFT);
+	}
+
 	mutex_init(&rt5677->dsp_cmd_lock);
 
 	return 0;
@@ -3915,9 +3981,74 @@ static int rt5677_parse_dt(struct rt5677_priv *rt5677, struct device_node *np)
 	of_property_read_u8_array(np, "realtek,gpio-config",
 		rt5677->pdata.gpio_config, RT5677_GPIO_NUM);
 
+	of_property_read_u32(np, "realtek,jd1-gpio", &rt5677->pdata.jd1_gpio);
+	of_property_read_u32(np, "realtek,jd2-gpio", &rt5677->pdata.jd2_gpio);
+	of_property_read_u32(np, "realtek,jd3-gpio", &rt5677->pdata.jd3_gpio);
+
 	return 0;
 }
 
+static struct regmap_irq rt5677_irqs[] = {
+	[RT5677_IRQ_JD1] = {
+		.reg_offset = 0,
+		.mask = RT5677_EN_IRQ_GPIO_JD1,
+	},
+	[RT5677_IRQ_JD2] = {
+		.reg_offset = 0,
+		.mask = RT5677_EN_IRQ_GPIO_JD2,
+	},
+	[RT5677_IRQ_JD3] = {
+		.reg_offset = 0,
+		.mask = RT5677_EN_IRQ_GPIO_JD3,
+	},
+};
+
+static struct regmap_irq_chip rt5677_irq_chip = {
+	.name = "rt5677",
+	.irqs = rt5677_irqs,
+	.num_irqs = ARRAY_SIZE(rt5677_irqs),
+
+	.num_regs = 1,
+	.status_base = RT5677_IRQ_CTRL1,
+	.mask_base = RT5677_IRQ_CTRL1,
+	.mask_invert = 1,
+};
+
+int rt5677_irq_init(struct i2c_client *i2c)
+{
+	int ret;
+	struct rt5677_priv *rt5677 = i2c_get_clientdata(i2c);
+
+	if (!rt5677->pdata.jd1_gpio &&
+		!rt5677->pdata.jd2_gpio &&
+		!rt5677->pdata.jd3_gpio)
+		return 0;
+
+	if (!i2c->irq) {
+		dev_err(&i2c->dev, "No interrupt specified\n");
+		return -EINVAL;
+	}
+
+	ret = regmap_add_irq_chip(rt5677->regmap, i2c->irq,
+		IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, 0,
+		&rt5677_irq_chip, &rt5677->irq_data);
+
+	if (ret != 0) {
+		dev_err(&i2c->dev, "Failed to register IRQ chip: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+void rt5677_irq_exit(struct i2c_client *i2c)
+{
+	struct rt5677_priv *rt5677 = i2c_get_clientdata(i2c);
+
+	if (rt5677->irq_data)
+		regmap_del_irq_chip(i2c->irq, rt5677->irq_data);
+}
+
 static int rt5677_i2c_probe(struct i2c_client *i2c,
 		    const struct i2c_device_id *id)
 {
@@ -4015,6 +4146,7 @@ static int rt5677_i2c_probe(struct i2c_client *i2c,
 	}
 
 	rt5677_init_gpio(i2c);
+	rt5677_irq_init(i2c);
 
 	return snd_soc_register_codec(&i2c->dev, &soc_codec_dev_rt5677,
 				      rt5677_dai, ARRAY_SIZE(rt5677_dai));
@@ -4022,6 +4154,8 @@ static int rt5677_i2c_probe(struct i2c_client *i2c,
 
 static int rt5677_i2c_remove(struct i2c_client *i2c)
 {
+	rt5677_irq_exit(i2c);
+
 	snd_soc_unregister_codec(&i2c->dev);
 	rt5677_free_gpio(i2c);
 
diff --git a/sound/soc/codecs/rt5677.h b/sound/soc/codecs/rt5677.h
index 20efa4a4c82..d2c743c255a 100644
--- a/sound/soc/codecs/rt5677.h
+++ b/sound/soc/codecs/rt5677.h
@@ -1368,6 +1368,48 @@
 #define RT5677_SEL_SRC_IB01			(0x1 << 0)
 #define RT5677_SEL_SRC_IB01_SFT			0
 
+/* Jack Detect Control 1 (0xb5) */
+#define RT5677_SEL_GPIO_JD1_MASK		(0x3 << 14)
+#define RT5677_SEL_GPIO_JD1_SFT			14
+#define RT5677_SEL_GPIO_JD2_MASK		(0x3 << 12)
+#define RT5677_SEL_GPIO_JD2_SFT			12
+#define RT5677_SEL_GPIO_JD3_MASK		(0x3 << 10)
+#define RT5677_SEL_GPIO_JD3_SFT			10
+
+/* IRQ Control 1 (0xbd) */
+#define RT5677_STA_GPIO_JD1			(0x1 << 15)
+#define RT5677_STA_GPIO_JD1_SFT			15
+#define RT5677_EN_IRQ_GPIO_JD1			(0x1 << 14)
+#define RT5677_EN_IRQ_GPIO_JD1_SFT		14
+#define RT5677_EN_GPIO_JD1_STICKY		(0x1 << 13)
+#define RT5677_EN_GPIO_JD1_STICKY_SFT		13
+#define RT5677_INV_GPIO_JD1			(0x1 << 12)
+#define RT5677_INV_GPIO_JD1_SFT			12
+#define RT5677_STA_GPIO_JD2			(0x1 << 11)
+#define RT5677_STA_GPIO_JD2_SFT			11
+#define RT5677_EN_IRQ_GPIO_JD2			(0x1 << 10)
+#define RT5677_EN_IRQ_GPIO_JD2_SFT		10
+#define RT5677_EN_GPIO_JD2_STICKY		(0x1 << 9)
+#define RT5677_EN_GPIO_JD2_STICKY_SFT		9
+#define RT5677_INV_GPIO_JD2			(0x1 << 8)
+#define RT5677_INV_GPIO_JD2_SFT			8
+#define RT5677_STA_MICBIAS1_OVCD		(0x1 << 7)
+#define RT5677_STA_MICBIAS1_OVCD_SFT		7
+#define RT5677_EN_IRQ_MICBIAS1_OVCD		(0x1 << 6)
+#define RT5677_EN_IRQ_MICBIAS1_OVCD_SFT		6
+#define RT5677_EN_MICBIAS1_OVCD_STICKY		(0x1 << 5)
+#define RT5677_EN_MICBIAS1_OVCD_STICKY_SFT	5
+#define RT5677_INV_MICBIAS1_OVCD		(0x1 << 4)
+#define RT5677_INV_MICBIAS1_OVCD_SFT		4
+#define RT5677_STA_GPIO_JD3			(0x1 << 3)
+#define RT5677_STA_GPIO_JD3_SFT			3
+#define RT5677_EN_IRQ_GPIO_JD3			(0x1 << 2)
+#define RT5677_EN_IRQ_GPIO_JD3_SFT		2
+#define RT5677_EN_GPIO_JD3_STICKY		(0x1 << 1)
+#define RT5677_EN_GPIO_JD3_STICKY_SFT		1
+#define RT5677_INV_GPIO_JD3			(0x1 << 0)
+#define RT5677_INV_GPIO_JD3_SFT			0
+
 /* GPIO status (0xbf) */
 #define RT5677_GPIO6_STATUS_MASK		(0x1 << 5)
 #define RT5677_GPIO6_STATUS_SFT			5
@@ -1545,6 +1587,12 @@ enum {
 	RT5677_GPIO_NUM,
 };
 
+enum {
+	RT5677_IRQ_JD1,
+	RT5677_IRQ_JD2,
+	RT5677_IRQ_JD3,
+};
+
 struct rt5677_priv {
 	struct snd_soc_codec *codec;
 	struct rt5677_platform_data pdata;
@@ -1565,6 +1613,7 @@ struct rt5677_priv {
 	struct gpio_chip gpio_chip;
 #endif
 	bool dsp_vad_en;
+	struct regmap_irq_chip_data *irq_data;
 };
 
 #endif /* __RT5677_H__ */
-- 
cgit v1.2.3-70-g09d2


From 130897ac5ac03adb4604d27497c378c64c7b22dd Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 20 Oct 2014 19:36:39 +0200
Subject: ASoC: dapm: Remove path 'walked' flag

The 'walked' flag was used to avoid walking paths that have already been
walked. But since we started caching the number of inputs and outputs of a
path we never actually get into a situation where we try to walk a path that
has the 'walked' flag set.

There are two cases in which we can end up walking a path multiple times
within a single run of is_connected_output_ep() or is_connected_input_ep().

1) If a path splits up and rejoins later:

	     .--> C ---v
	A -> B         E --> F
	     '--> D ---^

When walking from A to F we'll end up at E twice, once via C and once via D.
But since we do a depth first search we'll fully discover the path and
initialize the number of outputs/inputs of the widget the first time we get
there. The second time we get there we'll use the cached value and not
bother to check any of the paths again. So we'll never see a path where
'walked' is set in this case.

2) If there is a circle:

	A --> B <-- C <-.--> F
	      '--> D ---'

When walking from A to F we'll end up twice at B. But since there is a
circle the 'walking' flag will still be set on B once we get there the
second time. This means we won't look at any of it's outgoing paths. So in
this case we won't ever see a path where 'walked' is set either.

So it is safe to remove the flag. This on one hand means we remove some
always true checks from one of the hottest paths of the DAPM algorithm and
on the other hand means we do not have to do the tedious clearing of the
flag after checking the number inputs or outputs of a widget.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dapm.h |  1 -
 sound/soc/soc-dapm.c     | 49 ++----------------------------------------------
 2 files changed, 2 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 3a4d7da67b8..ebb93f29e4f 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -508,7 +508,6 @@ struct snd_soc_dapm_path {
 
 	/* status */
 	u32 connect:1;	/* source and sink widgets are connected */
-	u32 walked:1;	/* path has been walked */
 	u32 walking:1;  /* path is in the process of being walked */
 	u32 weak:1;	/* path ignored for power management */
 
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 219d73c27a8..f03e0cfc65b 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -754,34 +754,6 @@ static int dapm_new_pga(struct snd_soc_dapm_widget *w)
 	return 0;
 }
 
-/* reset 'walked' bit for each dapm path */
-static void dapm_clear_walk_output(struct snd_soc_dapm_context *dapm,
-				   struct list_head *sink)
-{
-	struct snd_soc_dapm_path *p;
-
-	list_for_each_entry(p, sink, list_source) {
-		if (p->walked) {
-			p->walked = 0;
-			dapm_clear_walk_output(dapm, &p->sink->sinks);
-		}
-	}
-}
-
-static void dapm_clear_walk_input(struct snd_soc_dapm_context *dapm,
-				  struct list_head *source)
-{
-	struct snd_soc_dapm_path *p;
-
-	list_for_each_entry(p, source, list_sink) {
-		if (p->walked) {
-			p->walked = 0;
-			dapm_clear_walk_input(dapm, &p->source->sources);
-		}
-	}
-}
-
-
 /* We implement power down on suspend by checking the power state of
  * the ALSA card - when we are suspending the ALSA state for the card
  * is set to D3.
@@ -904,13 +876,9 @@ static int is_connected_output_ep(struct snd_soc_dapm_widget *widget,
 		if (path->walking)
 			return 1;
 
-		if (path->walked)
-			continue;
-
 		trace_snd_soc_dapm_output_path(widget, path);
 
 		if (path->connect) {
-			path->walked = 1;
 			path->walking = 1;
 
 			/* do we need to add this widget to the list ? */
@@ -1012,13 +980,9 @@ static int is_connected_input_ep(struct snd_soc_dapm_widget *widget,
 		if (path->walking)
 			return 1;
 
-		if (path->walked)
-			continue;
-
 		trace_snd_soc_dapm_input_path(widget, path);
 
 		if (path->connect) {
-			path->walked = 1;
 			path->walking = 1;
 
 			/* do we need to add this widget to the list ? */
@@ -1066,15 +1030,10 @@ int snd_soc_dapm_dai_get_connected_widgets(struct snd_soc_dai *dai, int stream,
 	mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
 	dapm_reset(card);
 
-	if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
+	if (stream == SNDRV_PCM_STREAM_PLAYBACK)
 		paths = is_connected_output_ep(dai->playback_widget, list);
-		dapm_clear_walk_output(&card->dapm,
-				       &dai->playback_widget->sinks);
-	} else {
+	else
 		paths = is_connected_input_ep(dai->capture_widget, list);
-		dapm_clear_walk_input(&card->dapm,
-				      &dai->capture_widget->sources);
-	}
 
 	trace_snd_soc_dapm_connected(paths, stream);
 	mutex_unlock(&card->dapm_mutex);
@@ -1163,9 +1122,7 @@ static int dapm_generic_check_power(struct snd_soc_dapm_widget *w)
 	DAPM_UPDATE_STAT(w, power_checks);
 
 	in = is_connected_input_ep(w, NULL);
-	dapm_clear_walk_input(w->dapm, &w->sources);
 	out = is_connected_output_ep(w, NULL);
-	dapm_clear_walk_output(w->dapm, &w->sinks);
 	return out != 0 && in != 0;
 }
 
@@ -1823,9 +1780,7 @@ static ssize_t dapm_widget_power_read_file(struct file *file,
 		return -ENOMEM;
 
 	in = is_connected_input_ep(w, NULL);
-	dapm_clear_walk_input(w->dapm, &w->sources);
 	out = is_connected_output_ep(w, NULL);
-	dapm_clear_walk_output(w->dapm, &w->sinks);
 
 	ret = snprintf(buf, PAGE_SIZE, "%s: %s%s  in %d out %d",
 		       w->name, w->power ? "On" : "Off",
-- 
cgit v1.2.3-70-g09d2


From a4b4e0461ec5532ad498f0dd0e68993ad79bec2b Mon Sep 17 00:00:00 2001
From: Romain Perier <romain.perier@gmail.com>
Date: Tue, 14 Oct 2014 06:31:09 +0000
Subject: of: Add standard property for poweroff capability

Several drivers create their own devicetree property when they register
poweroff capabilities. This is for example the case for mfd, regulator
or power drivers which define "vendor,system-power-controller" property.
This patch adds support for a standard property "poweroff-source"
which marks the device as able to shutdown the system.

Signed-off-by: Romain Perier <romain.perier@gmail.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/of.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/linux/of.h b/include/linux/of.h
index 6545e7aec7b..27b3ba1e9e5 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -866,4 +866,15 @@ static inline int of_changeset_update_property(struct of_changeset *ocs,
 /* CONFIG_OF_RESOLVE api */
 extern int of_resolve_phandles(struct device_node *tree);
 
+/**
+ * of_system_has_poweroff_source - Tells if poweroff-source is found for device_node
+ * @np: Pointer to the given device_node
+ *
+ * return true if present false otherwise
+ */
+static inline bool of_system_has_poweroff_source(const struct device_node *np)
+{
+	return of_property_read_bool(np, "poweroff-source");
+}
+
 #endif /* _LINUX_OF_H */
-- 
cgit v1.2.3-70-g09d2


From a7f3a768289858f03f5c1866639c8b476c1b8ebc Mon Sep 17 00:00:00 2001
From: Andrei Otcheretianski <andrei.otcheretianski@intel.com>
Date: Wed, 22 Oct 2014 15:22:49 +0300
Subject: mac80211: export IE splitting function

Export ieee80211_ie_split function, so it can be reused by
drivers which need to insert additional elements.

Signed-off-by: Andrei Otcheretianski <andrei.otcheretianski@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     | 28 ++++++++++++++++++++++++++++
 net/mac80211/ieee80211_i.h |  2 --
 net/mac80211/util.c        | 26 +-------------------------
 3 files changed, 29 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 9dc5e760632..96d224357c8 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -4906,4 +4906,32 @@ void ieee80211_update_p2p_noa(struct ieee80211_noa_data *data, u32 tsf);
 void ieee80211_tdls_oper_request(struct ieee80211_vif *vif, const u8 *peer,
 				 enum nl80211_tdls_operation oper,
 				 u16 reason_code, gfp_t gfp);
+
+/**
+ * ieee80211_ie_split - split an IE buffer according to ordering
+ *
+ * @ies: the IE buffer
+ * @ielen: the length of the IE buffer
+ * @ids: an array with element IDs that are allowed before
+ *	the split
+ * @n_ids: the size of the element ID array
+ * @offset: offset where to start splitting in the buffer
+ *
+ * This function splits an IE buffer by updating the @offset
+ * variable to point to the location where the buffer should be
+ * split.
+ *
+ * It assumes that the given IE buffer is well-formed, this
+ * has to be guaranteed by the caller!
+ *
+ * It also assumes that the IEs in the buffer are ordered
+ * correctly, if not the result of using this function will not
+ * be ordered correctly either, i.e. it does no reordering.
+ *
+ * The function returns the offset where the next part of the
+ * buffer starts, which may be @ielen if the entire (remainder)
+ * of the buffer should be used.
+ */
+size_t ieee80211_ie_split(const u8 *ies, size_t ielen,
+			  const u8 *ids, int n_ids, size_t offset);
 #endif /* MAC80211_H */
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 60063be057d..146a818e52b 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1874,8 +1874,6 @@ int __ieee80211_request_smps_ap(struct ieee80211_sub_if_data *sdata,
 void ieee80211_recalc_smps(struct ieee80211_sub_if_data *sdata);
 void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata);
 
-size_t ieee80211_ie_split(const u8 *ies, size_t ielen,
-			  const u8 *ids, int n_ids, size_t offset);
 size_t ieee80211_ie_split_vendor(const u8 *ies, size_t ielen, size_t offset);
 u8 *ieee80211_ie_build_ht_cap(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap,
 			      u16 cap);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index c76c9d7294a..9247a960ea5 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2052,31 +2052,6 @@ static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id)
 	return false;
 }
 
-/**
- * ieee80211_ie_split - split an IE buffer according to ordering
- *
- * @ies: the IE buffer
- * @ielen: the length of the IE buffer
- * @ids: an array with element IDs that are allowed before
- *	the split
- * @n_ids: the size of the element ID array
- * @offset: offset where to start splitting in the buffer
- *
- * This function splits an IE buffer by updating the @offset
- * variable to point to the location where the buffer should be
- * split.
- *
- * It assumes that the given IE buffer is well-formed, this
- * has to be guaranteed by the caller!
- *
- * It also assumes that the IEs in the buffer are ordered
- * correctly, if not the result of using this function will not
- * be ordered correctly either, i.e. it does no reordering.
- *
- * The function returns the offset where the next part of the
- * buffer starts, which may be @ielen if the entire (remainder)
- * of the buffer should be used.
- */
 size_t ieee80211_ie_split(const u8 *ies, size_t ielen,
 			  const u8 *ids, int n_ids, size_t offset)
 {
@@ -2087,6 +2062,7 @@ size_t ieee80211_ie_split(const u8 *ies, size_t ielen,
 
 	return pos;
 }
+EXPORT_SYMBOL(ieee80211_ie_split);
 
 size_t ieee80211_ie_split_vendor(const u8 *ies, size_t ielen, size_t offset)
 {
-- 
cgit v1.2.3-70-g09d2


From 8b94148cfec4c40f4c55308fdcd816bbfe2b4016 Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Wed, 22 Oct 2014 12:32:48 +0300
Subject: mac80211: expose TDLS-initiator value to low level driver

Some drivers need to know which station is the TDLS link initiator.
Expose this value via the mac80211 ieee80211_sta structure.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 3 +++
 net/mac80211/tdls.c    | 8 ++++++--
 2 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 96d224357c8..99dd3ce7484 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1427,6 +1427,8 @@ struct ieee80211_sta_rates {
  * @smps_mode: current SMPS mode (off, static or dynamic)
  * @rates: rate control selection table
  * @tdls: indicates whether the STA is a TDLS peer
+ * @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only
+ *	valid if the STA is a TDLS peer in the first place.
  */
 struct ieee80211_sta {
 	u32 supp_rates[IEEE80211_NUM_BANDS];
@@ -1442,6 +1444,7 @@ struct ieee80211_sta {
 	enum ieee80211_smps_mode smps_mode;
 	struct ieee80211_sta_rates __rcu *rates;
 	bool tdls;
+	bool tdls_initiator;
 
 	/* must be last */
 	u8 drv_priv[0] __aligned(sizeof(void *));
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index 4ea25dec069..b4f368e2cb3 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -562,8 +562,10 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 	/* infer the initiator if we can, to support old userspace */
 	switch (action_code) {
 	case WLAN_TDLS_SETUP_REQUEST:
-		if (sta)
+		if (sta) {
 			set_sta_flag(sta, WLAN_STA_TDLS_INITIATOR);
+			sta->sta.tdls_initiator = false;
+		}
 		/* fall-through */
 	case WLAN_TDLS_SETUP_CONFIRM:
 	case WLAN_TDLS_DISCOVERY_REQUEST:
@@ -575,8 +577,10 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 		 * Make the last packet sent take effect for the initiator
 		 * value.
 		 */
-		if (sta)
+		if (sta) {
 			clear_sta_flag(sta, WLAN_STA_TDLS_INITIATOR);
+			sta->sta.tdls_initiator = true;
+		}
 		/* fall-through */
 	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
 		initiator = false;
-- 
cgit v1.2.3-70-g09d2


From 0fc1e0495fd6e261e75acdbe66b53e769e5ffb81 Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Wed, 22 Oct 2014 12:30:59 +0300
Subject: mac80211: expose API allowing station iteration

Allow drivers to iterate all stations currently uploaded to them.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 16 ++++++++++++++++
 net/mac80211/util.c    | 28 ++++++++++++++++++++++++++++
 2 files changed, 44 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 99dd3ce7484..2b7426a90ff 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -4192,6 +4192,22 @@ void ieee80211_iterate_active_interfaces_rtnl(struct ieee80211_hw *hw,
 						struct ieee80211_vif *vif),
 					      void *data);
 
+/**
+ * ieee80211_iterate_stations_atomic - iterate stations
+ *
+ * This function iterates over all stations associated with a given
+ * hardware that are currently uploaded to the driver and calls the callback
+ * function for them.
+ * This function requires the iterator callback function to be atomic,
+ *
+ * @hw: the hardware struct of which the interfaces should be iterated over
+ * @iterator: the iterator function to call, cannot sleep
+ * @data: first argument of the iterator function
+ */
+void ieee80211_iterate_stations_atomic(struct ieee80211_hw *hw,
+				       void (*iterator)(void *data,
+						struct ieee80211_sta *sta),
+				       void *data);
 /**
  * ieee80211_queue_work - add work onto the mac80211 workqueue
  *
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 9247a960ea5..666aa1306c4 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -693,6 +693,34 @@ void ieee80211_iterate_active_interfaces_rtnl(
 }
 EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_rtnl);
 
+static void __iterate_stations(struct ieee80211_local *local,
+			       void (*iterator)(void *data,
+						struct ieee80211_sta *sta),
+			       void *data)
+{
+	struct sta_info *sta;
+
+	list_for_each_entry_rcu(sta, &local->sta_list, list) {
+		if (!sta->uploaded)
+			continue;
+
+		iterator(data, &sta->sta);
+	}
+}
+
+void ieee80211_iterate_stations_atomic(struct ieee80211_hw *hw,
+			void (*iterator)(void *data,
+					 struct ieee80211_sta *sta),
+			void *data)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
+
+	rcu_read_lock();
+	__iterate_stations(local, iterator, data);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(ieee80211_iterate_stations_atomic);
+
 struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
-- 
cgit v1.2.3-70-g09d2


From 105970f6087ae240b00deaff85773ed9bf381145 Mon Sep 17 00:00:00 2001
From: Kenjiro Nakayama <nakayamakenjiro@gmail.com>
Date: Mon, 20 Oct 2014 18:15:50 +0900
Subject: net: Remove trailing whitespace in tcp.h icmp.c syncookies.c

Remove trailing whitespace in tcp.h icmp.c syncookies.c

Signed-off-by: Kenjiro Nakayama <nakayamakenjiro@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 12 ++++++------
 net/ipv6/icmp.c       |  1 -
 net/ipv6/syncookies.c |  1 -
 3 files changed, 6 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4062b4f0d12..c73fc145ee4 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -55,9 +55,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define MAX_TCP_HEADER	(128 + MAX_HEADER)
 #define MAX_TCP_OPTION_SPACE 40
 
-/* 
+/*
  * Never offer a window over 32767 without using window scaling. Some
- * poor stacks do signed 16bit maths! 
+ * poor stacks do signed 16bit maths!
  */
 #define MAX_TCP_WINDOW		32767U
 
@@ -167,7 +167,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 /*
  *	TCP option
  */
- 
+
 #define TCPOPT_NOP		1	/* Padding */
 #define TCPOPT_EOL		0	/* End of options */
 #define TCPOPT_MSS		2	/* Segment size negotiating */
@@ -1104,16 +1104,16 @@ static inline int tcp_win_from_space(int space)
 		space - (space>>sysctl_tcp_adv_win_scale);
 }
 
-/* Note: caller must be prepared to deal with negative returns */ 
+/* Note: caller must be prepared to deal with negative returns */
 static inline int tcp_space(const struct sock *sk)
 {
 	return tcp_win_from_space(sk->sk_rcvbuf -
 				  atomic_read(&sk->sk_rmem_alloc));
-} 
+}
 
 static inline int tcp_full_space(const struct sock *sk)
 {
-	return tcp_win_from_space(sk->sk_rcvbuf); 
+	return tcp_win_from_space(sk->sk_rcvbuf);
 }
 
 static inline void tcp_openreq_init(struct request_sock *req,
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 97ae70077a4..62c1037d9e8 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -1009,4 +1009,3 @@ struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
 	return table;
 }
 #endif
-
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 2f25cb6347c..0e26e795b70 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -269,4 +269,3 @@ out_free:
 	reqsk_free(req);
 	return NULL;
 }
-
-- 
cgit v1.2.3-70-g09d2


From 16704b129bc1e497862e88253da20b13a1b94b33 Mon Sep 17 00:00:00 2001
From: Sébastien Barré <sebastien.barre@uclouvain.be>
Date: Tue, 21 Oct 2014 15:26:15 +0200
Subject: Removed unused function sctp_addr_is_valid()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

sctp_addr_is_valid() only appeared in its definition.

Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Sébastien Barré <sebastien.barre@uclouvain.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 4ff3f67be62..806e3b5b335 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1116,7 +1116,6 @@ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw, int len,
 sctp_scope_t sctp_scope(const union sctp_addr *);
 int sctp_in_scope(struct net *net, const union sctp_addr *addr, const sctp_scope_t scope);
 int sctp_is_any(struct sock *sk, const union sctp_addr *addr);
-int sctp_addr_is_valid(const union sctp_addr *addr);
 int sctp_is_ep_boundall(struct sock *sk);
 
 
-- 
cgit v1.2.3-70-g09d2


From 6b358aedced8180830727258718c3916bef3e249 Mon Sep 17 00:00:00 2001
From: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Date: Wed, 22 Oct 2014 20:26:44 +0200
Subject: phy: marvell: Add support for 88E3016 FastEthernet PHY
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Marvell 88E3016 is a FastEthernet PHY that also can be found in Marvell
Berlin SoCs as integrated PHY.

Tested-by: Antoine Ténart <antoine.tenart@free-electrons.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c   | 46 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/marvell_phy.h |  1 +
 2 files changed, 47 insertions(+)

(limited to 'include')

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index bd37e45c89c..d2b2f2f795d 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -118,6 +118,9 @@
 
 #define MII_M1116R_CONTROL_REG_MAC	21
 
+#define MII_88E3016_PHY_SPEC_CTRL	0x10
+#define MII_88E3016_DISABLE_SCRAMBLER	0x0200
+#define MII_88E3016_AUTO_MDIX_CROSSOVER	0x0030
 
 MODULE_DESCRIPTION("Marvell PHY driver");
 MODULE_AUTHOR("Andy Fleming");
@@ -434,6 +437,25 @@ static int m88e1116r_config_init(struct phy_device *phydev)
 	return 0;
 }
 
+static int m88e3016_config_init(struct phy_device *phydev)
+{
+	int reg;
+
+	/* Enable Scrambler and Auto-Crossover */
+	reg = phy_read(phydev, MII_88E3016_PHY_SPEC_CTRL);
+	if (reg < 0)
+		return reg;
+
+	reg &= ~MII_88E3016_DISABLE_SCRAMBLER;
+	reg |= MII_88E3016_AUTO_MDIX_CROSSOVER;
+
+	reg = phy_write(phydev, MII_88E3016_PHY_SPEC_CTRL, reg);
+	if (reg < 0)
+		return reg;
+
+	return 0;
+}
+
 static int m88e1111_config_init(struct phy_device *phydev)
 {
 	int err;
@@ -770,6 +792,12 @@ static int marvell_read_status(struct phy_device *phydev)
 	return 0;
 }
 
+static int marvell_aneg_done(struct phy_device *phydev)
+{
+	int retval = phy_read(phydev, MII_M1011_PHY_STATUS);
+	return (retval < 0) ? retval : (retval & MII_M1011_PHY_STATUS_RESOLVED);
+}
+
 static int m88e1121_did_interrupt(struct phy_device *phydev)
 {
 	int imask;
@@ -1050,6 +1078,23 @@ static struct phy_driver marvell_drivers[] = {
 		.suspend = &genphy_suspend,
 		.driver = { .owner = THIS_MODULE },
 	},
+	{
+		.phy_id = MARVELL_PHY_ID_88E3016,
+		.phy_id_mask = MARVELL_PHY_ID_MASK,
+		.name = "Marvell 88E3016",
+		.features = PHY_BASIC_FEATURES,
+		.flags = PHY_HAS_INTERRUPT,
+		.config_aneg = &genphy_config_aneg,
+		.config_init = &m88e3016_config_init,
+		.aneg_done = &marvell_aneg_done,
+		.read_status = &marvell_read_status,
+		.ack_interrupt = &marvell_ack_interrupt,
+		.config_intr = &marvell_config_intr,
+		.did_interrupt = &m88e1121_did_interrupt,
+		.resume = &genphy_resume,
+		.suspend = &genphy_suspend,
+		.driver = { .owner = THIS_MODULE },
+	},
 };
 
 static int __init marvell_init(void)
@@ -1079,6 +1124,7 @@ static struct mdio_device_id __maybe_unused marvell_tbl[] = {
 	{ MARVELL_PHY_ID_88E1318S, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E1116R, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E1510, MARVELL_PHY_ID_MASK },
+	{ MARVELL_PHY_ID_88E3016, MARVELL_PHY_ID_MASK },
 	{ }
 };
 
diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index 8e9a029e093..e6982ac3200 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -16,6 +16,7 @@
 #define MARVELL_PHY_ID_88E1318S		0x01410e90
 #define MARVELL_PHY_ID_88E1116R		0x01410e40
 #define MARVELL_PHY_ID_88E1510		0x01410dd0
+#define MARVELL_PHY_ID_88E3016		0x01410e60
 
 /* struct phy_device dev_flags definitions */
 #define MARVELL_PHY_M1145_FLAGS_RESISTANCE	0x00000001
-- 
cgit v1.2.3-70-g09d2


From e7de17abeda24d8acc316b2e07bd969d03099eea Mon Sep 17 00:00:00 2001
From: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Date: Wed, 22 Oct 2014 20:26:45 +0200
Subject: net: pxa168_eth: Provide phy_interface mode on platform_data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PXA168 Ethernet IP support MII and RMII connection to its PHY.
Currently, pxa168 platform_data does not provide a way to pass that
and there is one user of pxa168 platform_data (mach-mmp/gplug).
Given the pinctrl settings of gplug it uses RMII, so add and pass
a corresponding phy_interface_t.

Tested-by: Antoine Ténart <antoine.tenart@free-electrons.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/mach-mmp/gplugd.c | 2 ++
 include/linux/pxa168_eth.h | 1 +
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/arch/arm/mach-mmp/gplugd.c b/arch/arm/mach-mmp/gplugd.c
index d81b2475e67..3b5794cd035 100644
--- a/arch/arm/mach-mmp/gplugd.c
+++ b/arch/arm/mach-mmp/gplugd.c
@@ -12,6 +12,7 @@
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
 #include <linux/gpio-pxa.h>
+#include <linux/phy.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach-types.h>
@@ -158,6 +159,7 @@ struct pxa168_eth_platform_data gplugd_eth_platform_data = {
 	.port_number = 0,
 	.phy_addr    = 0,
 	.speed       = 0, /* Autonagotiation */
+	.intf        = PHY_INTERFACE_MODE_RMII,
 	.init        = gplugd_eth_init,
 };
 
diff --git a/include/linux/pxa168_eth.h b/include/linux/pxa168_eth.h
index 18d75e79560..37c381120bc 100644
--- a/include/linux/pxa168_eth.h
+++ b/include/linux/pxa168_eth.h
@@ -13,6 +13,7 @@ struct pxa168_eth_platform_data {
 	 */
 	int	speed;		/* 0, SPEED_10, SPEED_100 */
 	int	duplex;		/* DUPLEX_HALF or DUPLEX_FULL */
+	phy_interface_t intf;
 
 	/*
 	 * Override default RX/TX queue sizes if nonzero.
-- 
cgit v1.2.3-70-g09d2


From 70b946f9acf4e805361bd877a7e25cc05e497c52 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Fri, 24 Oct 2014 21:56:58 +0100
Subject: regulator: Return an error from stubbed regulator_get_exclusive()

The user hasn't got a regulator and shouldn't be mislead into thinking
they have one; really we should probably remove this stub entirely (and
may well before the next merge window).

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/regulator/consumer.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index d347c805f92..c0c0a437ec7 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -282,7 +282,7 @@ devm_regulator_get(struct device *dev, const char *id)
 static inline struct regulator *__must_check
 regulator_get_exclusive(struct device *dev, const char *id)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 
 static inline struct regulator *__must_check
-- 
cgit v1.2.3-70-g09d2


From 48ec92fa4f16c0f71e95c31490c03b6c9e0e793b Mon Sep 17 00:00:00 2001
From: Alfonso Acosta <fons@spotify.com>
Date: Tue, 7 Oct 2014 08:44:10 +0000
Subject: Bluetooth: Refactor arguments of mgmt_device_connected

The values of a lot of the mgmt_device_connected() parameters come
straight from a hci_conn object. We can simplify the function by passing
the full hci_conn pointer to it.

Signed-off-by: Alfonso Acosta <fons@spotify.com>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  5 ++---
 net/bluetooth/hci_event.c        | 14 ++++----------
 net/bluetooth/l2cap_core.c       |  4 +---
 net/bluetooth/mgmt.c             | 13 ++++++-------
 4 files changed, 13 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 37ff1aef084..f1407fe0fc5 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1310,9 +1310,8 @@ int mgmt_update_adv_data(struct hci_dev *hdev);
 void mgmt_discoverable_timeout(struct hci_dev *hdev);
 void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 		       bool persistent);
-void mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-			   u8 addr_type, u32 flags, u8 *name, u8 name_len,
-			   u8 *dev_class);
+void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn,
+			   u32 flags, u8 *name, u8 name_len);
 void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			      u8 link_type, u8 addr_type, u8 reason,
 			      bool mgmt_connected);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 8b0a2a6de41..6ee7de26cbb 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1577,8 +1577,7 @@ static void hci_check_pending_name(struct hci_dev *hdev, struct hci_conn *conn,
 	struct inquiry_entry *e;
 
 	if (conn && !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags))
-		mgmt_device_connected(hdev, bdaddr, ACL_LINK, 0x00, 0, name,
-				      name_len, conn->dev_class);
+		mgmt_device_connected(hdev, conn, 0, name, name_len);
 
 	if (discov->state == DISCOVERY_STOPPED)
 		return;
@@ -2536,9 +2535,7 @@ static void hci_remote_features_evt(struct hci_dev *hdev,
 		cp.pscan_rep_mode = 0x02;
 		hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp);
 	} else if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags))
-		mgmt_device_connected(hdev, &conn->dst, conn->type,
-				      conn->dst_type, 0, NULL, 0,
-				      conn->dev_class);
+		mgmt_device_connected(hdev, conn, 0, NULL, 0);
 
 	if (!hci_outgoing_auth_needed(hdev, conn)) {
 		conn->state = BT_CONNECTED;
@@ -3434,9 +3431,7 @@ static void hci_remote_ext_features_evt(struct hci_dev *hdev,
 		cp.pscan_rep_mode = 0x02;
 		hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp);
 	} else if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags))
-		mgmt_device_connected(hdev, &conn->dst, conn->type,
-				      conn->dst_type, 0, NULL, 0,
-				      conn->dev_class);
+		mgmt_device_connected(hdev, conn, 0, NULL, 0);
 
 	if (!hci_outgoing_auth_needed(hdev, conn)) {
 		conn->state = BT_CONNECTED;
@@ -4214,8 +4209,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	}
 
 	if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags))
-		mgmt_device_connected(hdev, &conn->dst, conn->type,
-				      conn->dst_type, 0, NULL, 0, NULL);
+		mgmt_device_connected(hdev, conn, 0, NULL, 0);
 
 	conn->sec_level = BT_SECURITY_LOW;
 	conn->handle = __le16_to_cpu(ev->handle);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index b6f9777e057..2ff5591bee9 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -3873,9 +3873,7 @@ static int l2cap_connect_req(struct l2cap_conn *conn,
 	hci_dev_lock(hdev);
 	if (test_bit(HCI_MGMT, &hdev->dev_flags) &&
 	    !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &hcon->flags))
-		mgmt_device_connected(hdev, &hcon->dst, hcon->type,
-				      hcon->dst_type, 0, NULL, 0,
-				      hcon->dev_class);
+		mgmt_device_connected(hdev, hcon, 0, NULL, 0);
 	hci_dev_unlock(hdev);
 
 	l2cap_connect(conn, cmd, data, L2CAP_CONN_RSP, 0);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index efb71b022ab..fc275dca94f 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -6171,16 +6171,15 @@ static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data,
 	return eir_len;
 }
 
-void mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-			   u8 addr_type, u32 flags, u8 *name, u8 name_len,
-			   u8 *dev_class)
+void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn,
+			   u32 flags, u8 *name, u8 name_len)
 {
 	char buf[512];
 	struct mgmt_ev_device_connected *ev = (void *) buf;
 	u16 eir_len = 0;
 
-	bacpy(&ev->addr.bdaddr, bdaddr);
-	ev->addr.type = link_to_bdaddr(link_type, addr_type);
+	bacpy(&ev->addr.bdaddr, &conn->dst);
+	ev->addr.type = link_to_bdaddr(conn->type, conn->dst_type);
 
 	ev->flags = __cpu_to_le32(flags);
 
@@ -6188,9 +6187,9 @@ void mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		eir_len = eir_append_data(ev->eir, 0, EIR_NAME_COMPLETE,
 					  name, name_len);
 
-	if (dev_class && memcmp(dev_class, "\0\0\0", 3) != 0)
+	if (conn->dev_class && memcmp(conn->dev_class, "\0\0\0", 3) != 0)
 		eir_len = eir_append_data(ev->eir, eir_len,
-					  EIR_CLASS_OF_DEV, dev_class, 3);
+					  EIR_CLASS_OF_DEV, conn->dev_class, 3);
 
 	ev->eir_len = cpu_to_le16(eir_len);
 
-- 
cgit v1.2.3-70-g09d2


From fd45ada9105635a69cbaa2d142d502d402eef6fe Mon Sep 17 00:00:00 2001
From: Alfonso Acosta <fons@spotify.com>
Date: Tue, 7 Oct 2014 08:44:11 +0000
Subject: Bluetooth: Include ADV_IND report in Device Connected event

There are scenarios when autoconnecting to a device after the
reception of an ADV_IND report (action 0x02), in which userland
might want to examine the report's contents.

For instance, the Service Data might have changed and it would be
useful to know ahead of time before starting any GATT procedures.
Also, the ADV_IND may contain Manufacturer Specific data which would
be lost if not propagated to userland. In fact, this patch results
from the need to rebond with a device lacking persistent storage which
notifies about losing its LTK in ADV_IND reports.

This patch appends the ADV_IND report which triggered the
autoconnection to the EIR Data in the Device Connected event.

Signed-off-by: Alfonso Acosta <fons@spotify.com>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  2 ++
 net/bluetooth/hci_event.c        | 32 ++++++++++++++++++++++----------
 net/bluetooth/mgmt.c             | 24 ++++++++++++++++++------
 3 files changed, 42 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index f1407fe0fc5..07ddeed6241 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -398,6 +398,8 @@ struct hci_conn {
 	__u16		le_conn_interval;
 	__u16		le_conn_latency;
 	__u16		le_supv_timeout;
+	__u8		le_adv_data[HCI_MAX_AD_LENGTH];
+	__u8		le_adv_data_len;
 	__s8		rssi;
 	__s8		tx_power;
 	__s8		max_tx_power;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 6ee7de26cbb..96291530606 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -4263,25 +4263,26 @@ static void hci_le_conn_update_complete_evt(struct hci_dev *hdev,
 }
 
 /* This function requires the caller holds hdev->lock */
-static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
-				  u8 addr_type, u8 adv_type)
+static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev,
+					      bdaddr_t *addr,
+					      u8 addr_type, u8 adv_type)
 {
 	struct hci_conn *conn;
 	struct hci_conn_params *params;
 
 	/* If the event is not connectable don't proceed further */
 	if (adv_type != LE_ADV_IND && adv_type != LE_ADV_DIRECT_IND)
-		return;
+		return NULL;
 
 	/* Ignore if the device is blocked */
 	if (hci_bdaddr_list_lookup(&hdev->blacklist, addr, addr_type))
-		return;
+		return NULL;
 
 	/* Most controller will fail if we try to create new connections
 	 * while we have an existing one in slave role.
 	 */
 	if (hdev->conn_hash.le_num_slave > 0)
-		return;
+		return NULL;
 
 	/* If we're not connectable only connect devices that we have in
 	 * our pend_le_conns list.
@@ -4289,7 +4290,7 @@ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
 	params = hci_pend_le_action_lookup(&hdev->pend_le_conns,
 					   addr, addr_type);
 	if (!params)
-		return;
+		return NULL;
 
 	switch (params->auto_connect) {
 	case HCI_AUTO_CONN_DIRECT:
@@ -4298,7 +4299,7 @@ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
 		 * incoming connections from slave devices.
 		 */
 		if (adv_type != LE_ADV_DIRECT_IND)
-			return;
+			return NULL;
 		break;
 	case HCI_AUTO_CONN_ALWAYS:
 		/* Devices advertising with ADV_IND or ADV_DIRECT_IND
@@ -4309,7 +4310,7 @@ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
 		 */
 		break;
 	default:
-		return;
+		return NULL;
 	}
 
 	conn = hci_connect_le(hdev, addr, addr_type, BT_SECURITY_LOW,
@@ -4322,7 +4323,7 @@ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
 		 * count consistent once the connection is established.
 		 */
 		params->conn = hci_conn_get(conn);
-		return;
+		return conn;
 	}
 
 	switch (PTR_ERR(conn)) {
@@ -4335,7 +4336,10 @@ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
 		break;
 	default:
 		BT_DBG("Failed to connect: err %ld", PTR_ERR(conn));
+		return NULL;
 	}
+
+	return NULL;
 }
 
 static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
@@ -4343,6 +4347,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 {
 	struct discovery_state *d = &hdev->discovery;
 	struct smp_irk *irk;
+	struct hci_conn *conn;
 	bool match;
 	u32 flags;
 
@@ -4354,7 +4359,14 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 	}
 
 	/* Check if we have been requested to connect to this device */
-	check_pending_le_conn(hdev, bdaddr, bdaddr_type, type);
+	conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, type);
+	if (conn && type == LE_ADV_IND) {
+		/* Store report for later inclusion by
+		 * mgmt_device_connected
+		 */
+		memcpy(conn->le_adv_data, data, len);
+		conn->le_adv_data_len = len;
+	}
 
 	/* Passive scanning shouldn't trigger any device found events,
 	 * except for devices marked as CONN_REPORT for which we do send
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index fc275dca94f..10caab587cc 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -6183,13 +6183,25 @@ void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn,
 
 	ev->flags = __cpu_to_le32(flags);
 
-	if (name_len > 0)
-		eir_len = eir_append_data(ev->eir, 0, EIR_NAME_COMPLETE,
-					  name, name_len);
+	/* We must ensure that the EIR Data fields are ordered and
+	 * unique. Keep it simple for now and avoid the problem by not
+	 * adding any BR/EDR data to the LE adv.
+	 */
+	if (conn->le_adv_data_len > 0) {
+		memcpy(&ev->eir[eir_len],
+		       conn->le_adv_data, conn->le_adv_data_len);
+		eir_len = conn->le_adv_data_len;
+	} else {
+		if (name_len > 0)
+			eir_len = eir_append_data(ev->eir, 0, EIR_NAME_COMPLETE,
+						  name, name_len);
 
-	if (conn->dev_class && memcmp(conn->dev_class, "\0\0\0", 3) != 0)
-		eir_len = eir_append_data(ev->eir, eir_len,
-					  EIR_CLASS_OF_DEV, conn->dev_class, 3);
+		if (conn->dev_class &&
+		    memcmp(conn->dev_class, "\0\0\0", 3) != 0)
+			eir_len = eir_append_data(ev->eir, eir_len,
+						  EIR_CLASS_OF_DEV,
+						  conn->dev_class, 3);
+	}
 
 	ev->eir_len = cpu_to_le16(eir_len);
 
-- 
cgit v1.2.3-70-g09d2


From 89cbb0638e9b7ba6fab02558f47a29f144df1a19 Mon Sep 17 00:00:00 2001
From: Alfonso Acosta <fons@spotify.com>
Date: Sat, 11 Oct 2014 21:44:47 +0000
Subject: Bluetooth: Defer connection-parameter removal when unpairing

Systematically removing the LE connection parameters and autoconnect
action is inconvenient for rebonding without disconnecting from
userland (i.e. unpairing followed by repairing without
disconnecting). The parameters will be lost after unparing and
userland needs to take care of book-keeping them and re-adding them.

This patch allows userland to forget about parameter management when
rebonding without disconnecting. It defers clearing the connection
parameters when unparing without disconnecting, giving a chance of
keeping the parameters if a repairing happens before the connection is
closed.

Signed-off-by: Alfonso Acosta <fons@spotify.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_conn.c         |  3 +++
 net/bluetooth/mgmt.c             | 51 ++++++++++++++++++++++++++++++----------
 3 files changed, 42 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 07ddeed6241..b8685a77a15 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -555,6 +555,7 @@ enum {
 	HCI_CONN_STK_ENCRYPT,
 	HCI_CONN_AUTH_INITIATOR,
 	HCI_CONN_DROP,
+	HCI_CONN_PARAM_REMOVAL_PEND,
 };
 
 static inline bool hci_conn_ssp_enabled(struct hci_conn *conn)
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index b9517bd1719..11aac06d53c 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -544,6 +544,9 @@ int hci_conn_del(struct hci_conn *conn)
 
 	hci_conn_del_sysfs(conn);
 
+	if (test_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags))
+		hci_conn_params_del(conn->hdev, &conn->dst, conn->dst_type);
+
 	hci_dev_put(hdev);
 
 	hci_conn_put(conn);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 3fd88b06ed5..9c4daf715cf 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2725,10 +2725,40 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	}
 
 	if (cp->addr.type == BDADDR_BREDR) {
+		/* If disconnection is requested, then look up the
+		 * connection. If the remote device is connected, it
+		 * will be later used to terminate the link.
+		 *
+		 * Setting it to NULL explicitly will cause no
+		 * termination of the link.
+		 */
+		if (cp->disconnect)
+			conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK,
+						       &cp->addr.bdaddr);
+		else
+			conn = NULL;
+
 		err = hci_remove_link_key(hdev, &cp->addr.bdaddr);
 	} else {
 		u8 addr_type;
 
+		conn = hci_conn_hash_lookup_ba(hdev, LE_LINK,
+					       &cp->addr.bdaddr);
+		if (conn) {
+			/* Defer clearing up the connection parameters
+			 * until closing to give a chance of keeping
+			 * them if a repairing happens.
+			 */
+			set_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags);
+
+			/* If disconnection is not requested, then
+			 * clear the connection variable so that the
+			 * link is not terminated.
+			 */
+			if (!cp->disconnect)
+				conn = NULL;
+		}
+
 		if (cp->addr.type == BDADDR_LE_PUBLIC)
 			addr_type = ADDR_LE_DEV_PUBLIC;
 		else
@@ -2736,8 +2766,6 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 
 		hci_remove_irk(hdev, &cp->addr.bdaddr, addr_type);
 
-		hci_conn_params_del(hdev, &cp->addr.bdaddr, addr_type);
-
 		err = hci_remove_ltk(hdev, &cp->addr.bdaddr, addr_type);
 	}
 
@@ -2747,17 +2775,9 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 		goto unlock;
 	}
 
-	if (cp->disconnect) {
-		if (cp->addr.type == BDADDR_BREDR)
-			conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK,
-						       &cp->addr.bdaddr);
-		else
-			conn = hci_conn_hash_lookup_ba(hdev, LE_LINK,
-						       &cp->addr.bdaddr);
-	} else {
-		conn = NULL;
-	}
-
+	/* If the connection variable is set, then termination of the
+	 * link is requested.
+	 */
 	if (!conn) {
 		err = cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, 0,
 				   &rp, sizeof(rp));
@@ -3062,6 +3082,11 @@ static void pairing_complete(struct pending_cmd *cmd, u8 status)
 	hci_conn_put(conn);
 
 	mgmt_pending_remove(cmd);
+
+	/* The device is paired so there is no need to remove
+	 * its connection parameters anymore.
+	 */
+	clear_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags);
 }
 
 void mgmt_smp_complete(struct hci_conn *conn, bool complete)
-- 
cgit v1.2.3-70-g09d2


From b3020f0a35fc431f7acf3fba9a5b7376d79932e5 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sat, 25 Oct 2014 05:25:07 +0200
Subject: ieee802154: mac802154: remove FSF address

This patch removes the FSF address in files which belongs to ieee802154
and mac802154.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Cc: Alan Ott <alan@signal11.us>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/net/ieee802154/at86rf230.c | 4 ----
 drivers/net/ieee802154/fakelb.c    | 4 ----
 drivers/net/ieee802154/mrf24j40.c  | 4 ----
 include/linux/nl802154.h           | 4 ----
 include/net/af_ieee802154.h        | 4 ----
 include/net/ieee802154.h           | 4 ----
 include/net/ieee802154_netdev.h    | 4 ----
 include/net/mac802154.h            | 3 ---
 include/net/nl802154.h             | 4 ----
 include/net/wpan-phy.h             | 4 ----
 net/ieee802154/af802154.h          | 4 ----
 net/ieee802154/af_ieee802154.c     | 4 ----
 net/ieee802154/dgram.c             | 4 ----
 net/ieee802154/ieee802154.h        | 4 ----
 net/ieee802154/netlink.c           | 4 ----
 net/ieee802154/nl-mac.c            | 4 ----
 net/ieee802154/nl-phy.c            | 4 ----
 net/ieee802154/nl_policy.c         | 4 ----
 net/ieee802154/raw.c               | 4 ----
 net/ieee802154/wpan-class.c        | 4 ----
 net/mac802154/ieee802154_dev.c     | 4 ----
 net/mac802154/mac802154.h          | 4 ----
 net/mac802154/mac_cmd.c            | 4 ----
 net/mac802154/mib.c                | 4 ----
 net/mac802154/monitor.c            | 4 ----
 net/mac802154/rx.c                 | 4 ----
 net/mac802154/tx.c                 | 4 ----
 net/mac802154/wpan.c               | 4 ----
 28 files changed, 111 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 6ebd665892d..b8b1e40feeb 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
  * Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index 27d83207d24..e4b1b1f66bd 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index b1e73bc6e39..ba9a3960d26 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -13,10 +13,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/spi/spi.h>
diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h
index 20163b9a0ea..167342c2ce6 100644
--- a/include/linux/nl802154.h
+++ b/include/linux/nl802154.h
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  */
 
 #ifndef NL802154_H
diff --git a/include/net/af_ieee802154.h b/include/net/af_ieee802154.h
index 085940f7eee..7d38e2ffd25 100644
--- a/include/net/af_ieee802154.h
+++ b/include/net/af_ieee802154.h
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
diff --git a/include/net/ieee802154.h b/include/net/ieee802154.h
index 0aa7122e8f1..4db4e320b2f 100644
--- a/include/net/ieee802154.h
+++ b/include/net/ieee802154.h
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Pavel Smolenskiy <pavel.smolenskiy@gmail.com>
  * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h
index 3b53c8e405e..f87420689d7 100644
--- a/include/net/ieee802154_netdev.h
+++ b/include/net/ieee802154_netdev.h
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Pavel Smolenskiy <pavel.smolenskiy@gmail.com>
  * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 2e67cdd19cd..f95b98ec50a 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -12,9 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 #ifndef NET_MAC802154_H
 #define NET_MAC802154_H
diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index b23548e0409..b5cdea29d9d 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  */
 
 #ifndef IEEE802154_NL_H
diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h
index 10ab0fc6d4f..65a05f19eb6 100644
--- a/include/net/wpan-phy.h
+++ b/include/net/wpan-phy.h
@@ -10,10 +10,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
  */
diff --git a/net/ieee802154/af802154.h b/net/ieee802154/af802154.h
index 8330a09bfc9..343b63e6f95 100644
--- a/net/ieee802154/af802154.h
+++ b/net/ieee802154/af802154.h
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c
index 29e0de63001..26da1e17973 100644
--- a/net/ieee802154/af_ieee802154.c
+++ b/net/ieee802154/af_ieee802154.c
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
index ef2ad8aaef1..71e99a0994e 100644
--- a/net/ieee802154/dgram.c
+++ b/net/ieee802154/dgram.c
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h
index 5d352f86979..42ae63a345a 100644
--- a/net/ieee802154/ieee802154.h
+++ b/net/ieee802154/ieee802154.h
@@ -10,10 +10,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  */
 #ifndef IEEE_802154_LOCAL_H
 #define IEEE_802154_LOCAL_H
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 9222966f5e6..6c3c2595a20 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index c6bfe22bfa5..78a1529e8bb 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 972baf83411..e943e20bcf0 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index 3a703ab8834..35c43266845 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c
index 9d1f64806f0..3ffcf4a9de0 100644
--- a/net/ieee802154/raw.c
+++ b/net/ieee802154/raw.c
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c
index 4955e0fe588..9a2dfab5648 100644
--- a/net/ieee802154/wpan-class.c
+++ b/net/ieee802154/wpan-class.c
@@ -10,10 +10,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  */
 
 #include <linux/slab.h>
diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c
index b36b2b99657..6af6a2427aa 100644
--- a/net/mac802154/ieee802154_dev.c
+++ b/net/mac802154/ieee802154_dev.c
@@ -14,10 +14,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #include <linux/kernel.h>
diff --git a/net/mac802154/mac802154.h b/net/mac802154/mac802154.h
index 762a6f849c6..e3503c1bc04 100644
--- a/net/mac802154/mac802154.h
+++ b/net/mac802154/mac802154.h
@@ -10,10 +10,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Pavel Smolenskiy <pavel.smolenskiy@gmail.com>
  * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c
index bf809131eef..85f70edbe8d 100644
--- a/net/mac802154/mac_cmd.c
+++ b/net/mac802154/mac_cmd.c
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c
index 868a040fd42..d7e5df872be 100644
--- a/net/mac802154/mib.c
+++ b/net/mac802154/mib.c
@@ -10,10 +10,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
  * Sergey Lapin <slapin@ossfans.org>
diff --git a/net/mac802154/monitor.c b/net/mac802154/monitor.c
index a68230e2b25..81249bb7c93 100644
--- a/net/mac802154/monitor.c
+++ b/net/mac802154/monitor.c
@@ -10,10 +10,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
  * Sergey Lapin <slapin@ossfans.org>
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index a14cf9ede17..e99d9394d13 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -10,10 +10,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Pavel Smolenskiy <pavel.smolenskiy@gmail.com>
  * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c
index fdf4c0e6725..95ea412395c 100644
--- a/net/mac802154/tx.c
+++ b/net/mac802154/tx.c
@@ -10,10 +10,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
  * Sergey Lapin <slapin@ossfans.org>
diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c
index 4ab86a57dca..b11a98d824e 100644
--- a/net/mac802154/wpan.c
+++ b/net/mac802154/wpan.c
@@ -10,10 +10,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
  * Sergey Lapin <slapin@ossfans.org>
-- 
cgit v1.2.3-70-g09d2


From 57205c14ca9147c1907556f77998cf82624d9fd6 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sat, 25 Oct 2014 05:25:09 +0200
Subject: mac802154: fix typo IEEE802515 to IEEE802154

This patch fixs a typo in address filter defines from IEEE802515 to
IEEE802154.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Cc: Alan Ott <alan@signal11.us>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/net/ieee802154/at86rf230.c | 8 ++++----
 drivers/net/ieee802154/cc2520.c    | 8 ++++----
 drivers/net/ieee802154/mrf24j40.c  | 8 ++++----
 include/net/mac802154.h            | 8 ++++----
 net/mac802154/mib.c                | 6 +++---
 5 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index b8b1e40feeb..83a635f1736 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -1097,7 +1097,7 @@ at86rf230_set_hw_addr_filt(struct ieee802154_dev *dev,
 {
 	struct at86rf230_local *lp = dev->priv;
 
-	if (changed & IEEE802515_AFILT_SADDR_CHANGED) {
+	if (changed & IEEE802154_AFILT_SADDR_CHANGED) {
 		u16 addr = le16_to_cpu(filt->short_addr);
 
 		dev_vdbg(&lp->spi->dev,
@@ -1106,7 +1106,7 @@ at86rf230_set_hw_addr_filt(struct ieee802154_dev *dev,
 		__at86rf230_write(lp, RG_SHORT_ADDR_1, addr >> 8);
 	}
 
-	if (changed & IEEE802515_AFILT_PANID_CHANGED) {
+	if (changed & IEEE802154_AFILT_PANID_CHANGED) {
 		u16 pan = le16_to_cpu(filt->pan_id);
 
 		dev_vdbg(&lp->spi->dev,
@@ -1115,7 +1115,7 @@ at86rf230_set_hw_addr_filt(struct ieee802154_dev *dev,
 		__at86rf230_write(lp, RG_PAN_ID_1, pan >> 8);
 	}
 
-	if (changed & IEEE802515_AFILT_IEEEADDR_CHANGED) {
+	if (changed & IEEE802154_AFILT_IEEEADDR_CHANGED) {
 		u8 i, addr[8];
 
 		memcpy(addr, &filt->ieee_addr, 8);
@@ -1125,7 +1125,7 @@ at86rf230_set_hw_addr_filt(struct ieee802154_dev *dev,
 			__at86rf230_write(lp, RG_IEEE_ADDR_0 + i, addr[i]);
 	}
 
-	if (changed & IEEE802515_AFILT_PANC_CHANGED) {
+	if (changed & IEEE802154_AFILT_PANC_CHANGED) {
 		dev_vdbg(&lp->spi->dev,
 			"at86rf230_set_hw_addr_filt called for panc change\n");
 		if (filt->pan_coord)
diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c
index 8a5ac7ab230..571f280204b 100644
--- a/drivers/net/ieee802154/cc2520.c
+++ b/drivers/net/ieee802154/cc2520.c
@@ -593,7 +593,7 @@ cc2520_filter(struct ieee802154_dev *dev,
 {
 	struct cc2520_private *priv = dev->priv;
 
-	if (changed & IEEE802515_AFILT_PANID_CHANGED) {
+	if (changed & IEEE802154_AFILT_PANID_CHANGED) {
 		u16 panid = le16_to_cpu(filt->pan_id);
 
 		dev_vdbg(&priv->spi->dev,
@@ -602,7 +602,7 @@ cc2520_filter(struct ieee802154_dev *dev,
 				 sizeof(panid), (u8 *)&panid);
 	}
 
-	if (changed & IEEE802515_AFILT_IEEEADDR_CHANGED) {
+	if (changed & IEEE802154_AFILT_IEEEADDR_CHANGED) {
 		dev_vdbg(&priv->spi->dev,
 			 "cc2520_filter called for IEEE addr\n");
 		cc2520_write_ram(priv, CC2520RAM_IEEEADDR,
@@ -610,7 +610,7 @@ cc2520_filter(struct ieee802154_dev *dev,
 				 (u8 *)&filt->ieee_addr);
 	}
 
-	if (changed & IEEE802515_AFILT_SADDR_CHANGED) {
+	if (changed & IEEE802154_AFILT_SADDR_CHANGED) {
 		u16 addr = le16_to_cpu(filt->short_addr);
 
 		dev_vdbg(&priv->spi->dev,
@@ -619,7 +619,7 @@ cc2520_filter(struct ieee802154_dev *dev,
 				 sizeof(addr), (u8 *)&addr);
 	}
 
-	if (changed & IEEE802515_AFILT_PANC_CHANGED) {
+	if (changed & IEEE802154_AFILT_PANC_CHANGED) {
 		dev_vdbg(&priv->spi->dev,
 			 "cc2520_filter called for panc change\n");
 		if (filt->pan_coord)
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index ba9a3960d26..0006b9ad512 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -462,7 +462,7 @@ static int mrf24j40_filter(struct ieee802154_dev *dev,
 
 	dev_dbg(printdev(devrec), "filter\n");
 
-	if (changed & IEEE802515_AFILT_SADDR_CHANGED) {
+	if (changed & IEEE802154_AFILT_SADDR_CHANGED) {
 		/* Short Addr */
 		u8 addrh, addrl;
 
@@ -475,7 +475,7 @@ static int mrf24j40_filter(struct ieee802154_dev *dev,
 			"Set short addr to %04hx\n", filt->short_addr);
 	}
 
-	if (changed & IEEE802515_AFILT_IEEEADDR_CHANGED) {
+	if (changed & IEEE802154_AFILT_IEEEADDR_CHANGED) {
 		/* Device Address */
 		u8 i, addr[8];
 
@@ -491,7 +491,7 @@ static int mrf24j40_filter(struct ieee802154_dev *dev,
 #endif
 	}
 
-	if (changed & IEEE802515_AFILT_PANID_CHANGED) {
+	if (changed & IEEE802154_AFILT_PANID_CHANGED) {
 		/* PAN ID */
 		u8 panidl, panidh;
 
@@ -503,7 +503,7 @@ static int mrf24j40_filter(struct ieee802154_dev *dev,
 		dev_dbg(printdev(devrec), "Set PANID to %04hx\n", filt->pan_id);
 	}
 
-	if (changed & IEEE802515_AFILT_PANC_CHANGED) {
+	if (changed & IEEE802154_AFILT_PANC_CHANGED) {
 		/* Pan Coordinator */
 		u8 val;
 		int ret;
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index f95b98ec50a..70351de3a72 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -32,13 +32,13 @@
  */
 
 /* indicates that the Short Address changed */
-#define IEEE802515_AFILT_SADDR_CHANGED		0x00000001
+#define IEEE802154_AFILT_SADDR_CHANGED		0x00000001
 /* indicates that the IEEE Address changed */
-#define IEEE802515_AFILT_IEEEADDR_CHANGED	0x00000002
+#define IEEE802154_AFILT_IEEEADDR_CHANGED	0x00000002
 /* indicates that the PAN ID changed */
-#define IEEE802515_AFILT_PANID_CHANGED		0x00000004
+#define IEEE802154_AFILT_PANID_CHANGED		0x00000004
 /* indicates that PAN Coordinator status changed */
-#define	IEEE802515_AFILT_PANC_CHANGED		0x00000008
+#define IEEE802154_AFILT_PANC_CHANGED		0x00000008
 
 struct ieee802154_hw_addr_filt {
 	__le16	pan_id;		/* Each independent PAN selects a unique
diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c
index d7e5df872be..3ee60429223 100644
--- a/net/mac802154/mib.c
+++ b/net/mac802154/mib.c
@@ -89,7 +89,7 @@ void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val)
 	if ((priv->hw->ops->set_hw_addr_filt) &&
 	    (priv->hw->hw.hw_filt.short_addr != priv->short_addr)) {
 		priv->hw->hw.hw_filt.short_addr = priv->short_addr;
-		set_hw_addr_filt(dev, IEEE802515_AFILT_SADDR_CHANGED);
+		set_hw_addr_filt(dev, IEEE802154_AFILT_SADDR_CHANGED);
 	}
 }
 
@@ -117,7 +117,7 @@ void mac802154_dev_set_ieee_addr(struct net_device *dev)
 	if (mac->ops->set_hw_addr_filt &&
 	    mac->hw.hw_filt.ieee_addr != priv->extended_addr) {
 		mac->hw.hw_filt.ieee_addr = priv->extended_addr;
-		set_hw_addr_filt(dev, IEEE802515_AFILT_IEEEADDR_CHANGED);
+		set_hw_addr_filt(dev, IEEE802154_AFILT_IEEEADDR_CHANGED);
 	}
 }
 
@@ -148,7 +148,7 @@ void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val)
 	if ((priv->hw->ops->set_hw_addr_filt) &&
 	    (priv->hw->hw.hw_filt.pan_id != priv->pan_id)) {
 		priv->hw->hw.hw_filt.pan_id = priv->pan_id;
-		set_hw_addr_filt(dev, IEEE802515_AFILT_PANID_CHANGED);
+		set_hw_addr_filt(dev, IEEE802154_AFILT_PANID_CHANGED);
 	}
 }
 
-- 
cgit v1.2.3-70-g09d2


From 4896167d9761ede678c36999eea0450c355991d4 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sat, 25 Oct 2014 05:25:10 +0200
Subject: ieee802154: wpan-phy: change to __aligned(size)

This patch fix a checkpatch warning that __aligned(size) is preferred
over __attribute__((aligned(size))).

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/wpan-phy.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h
index 65a05f19eb6..fa827c92339 100644
--- a/include/net/wpan-phy.h
+++ b/include/net/wpan-phy.h
@@ -65,7 +65,7 @@ struct wpan_phy {
 			       u8 retries);
 	int (*set_frame_retries)(struct wpan_phy *phy, s8 retries);
 
-	char priv[0] __attribute__((__aligned__(NETDEV_ALIGN)));
+	char priv[0] __aligned(NETDEV_ALIGN);
 };
 
 #define to_phy(_dev)	container_of(_dev, struct wpan_phy, dev)
-- 
cgit v1.2.3-70-g09d2


From e72740d057fea18be17587ff84ecebf09b30ca7d Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sat, 25 Oct 2014 05:25:11 +0200
Subject: ieee802154: wpan-phy: use blank line after function

This patch adds a blank line after function declaration.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/wpan-phy.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h
index fa827c92339..1e9795f116b 100644
--- a/include/net/wpan-phy.h
+++ b/include/net/wpan-phy.h
@@ -75,6 +75,7 @@ static inline void wpan_phy_set_dev(struct wpan_phy *phy, struct device *dev)
 {
 	phy->dev.parent = dev;
 }
+
 int wpan_phy_register(struct wpan_phy *phy);
 void wpan_phy_unregister(struct wpan_phy *phy);
 void wpan_phy_free(struct wpan_phy *phy);
-- 
cgit v1.2.3-70-g09d2


From acd8256723f286b7217801fbed24503f8565b91e Mon Sep 17 00:00:00 2001
From: "Ivan T. Ivanov" <iivanov@mm-sol.com>
Date: Wed, 22 Oct 2014 18:29:43 +0300
Subject: iio: inkern: Add of_xlate function to struct iio_info

When #iio-cells is greater than '0', the driver could provide
a custom of_xlate function that reads the *args* and returns
the appropriate index in registered IIO channels array.

Add simple translation function, suitable for the most 1:1
mapped channels in IIO chips, and use it when driver did not
provide custom implementation.

Signed-off-by: Ivan T. Ivanov <iivanov@mm-sol.com>
Reviewed-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/inkern.c    | 33 ++++++++++++++++++++++++++++-----
 include/linux/iio/iio.h |  8 ++++++++
 2 files changed, 36 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c
index c7497009d60..0cc505d9868 100644
--- a/drivers/iio/inkern.c
+++ b/drivers/iio/inkern.c
@@ -100,6 +100,28 @@ static int iio_dev_node_match(struct device *dev, void *data)
 	return dev->of_node == data && dev->type == &iio_device_type;
 }
 
+/**
+ * __of_iio_simple_xlate - translate iiospec to the IIO channel index
+ * @indio_dev:	pointer to the iio_dev structure
+ * @iiospec:	IIO specifier as found in the device tree
+ *
+ * This is simple translation function, suitable for the most 1:1 mapped
+ * channels in IIO chips. This function performs only one sanity check:
+ * whether IIO index is less than num_channels (that is specified in the
+ * iio_dev).
+ */
+static int __of_iio_simple_xlate(struct iio_dev *indio_dev,
+				const struct of_phandle_args *iiospec)
+{
+	if (!iiospec->args_count)
+		return 0;
+
+	if (iiospec->args[0] >= indio_dev->num_channels)
+		return -EINVAL;
+
+	return iiospec->args[0];
+}
+
 static int __of_iio_channel_get(struct iio_channel *channel,
 				struct device_node *np, int index)
 {
@@ -122,18 +144,19 @@ static int __of_iio_channel_get(struct iio_channel *channel,
 
 	indio_dev = dev_to_iio_dev(idev);
 	channel->indio_dev = indio_dev;
-	index = iiospec.args_count ? iiospec.args[0] : 0;
-	if (index >= indio_dev->num_channels) {
-		err = -EINVAL;
+	if (indio_dev->info->of_xlate)
+		index = indio_dev->info->of_xlate(indio_dev, &iiospec);
+	else
+		index = __of_iio_simple_xlate(indio_dev, &iiospec);
+	if (index < 0)
 		goto err_put;
-	}
 	channel->channel = &indio_dev->channels[index];
 
 	return 0;
 
 err_put:
 	iio_device_put(indio_dev);
-	return err;
+	return index;
 }
 
 static struct iio_channel *of_iio_channel_get(struct device_node *np, int index)
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 15dc6bc2bdd..3642ce7ef51 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -13,6 +13,7 @@
 #include <linux/device.h>
 #include <linux/cdev.h>
 #include <linux/iio/types.h>
+#include <linux/of.h>
 /* IIO TODO LIST */
 /*
  * Provide means of adjusting timer accuracy.
@@ -326,6 +327,11 @@ struct iio_dev;
  * @update_scan_mode:	function to configure device and scan buffer when
  *			channels have changed
  * @debugfs_reg_access:	function to read or write register value of device
+ * @of_xlate:		function pointer to obtain channel specifier index.
+ *			When #iio-cells is greater than '0', the driver could
+ *			provide a custom of_xlate function that reads the
+ *			*args* and returns the appropriate index in registered
+ *			IIO channels array.
  **/
 struct iio_info {
 	struct module			*driver_module;
@@ -385,6 +391,8 @@ struct iio_info {
 	int (*debugfs_reg_access)(struct iio_dev *indio_dev,
 				  unsigned reg, unsigned writeval,
 				  unsigned *readval);
+	int (*of_xlate)(struct iio_dev *indio_dev,
+			const struct of_phandle_args *iiospec);
 };
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 5ad60d36993596f7b3b958500f9c66c5338cd855 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sat, 25 Oct 2014 09:41:02 +0200
Subject: ieee802154: move wpan-phy.h to cfg802154.h

The wpan-phy header contains the wpan_phy struct information. Later this
header will be have similar function like cfg80211 header. The cfg80211
header contains the wiphy struct which is identically the wpan_phy
struct inside 802.15.4 subsystem.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Cc: Alan Ott <alan@signal11.us>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/net/ieee802154/at86rf230.c |   2 +-
 drivers/net/ieee802154/cc2520.c    |   2 +-
 drivers/net/ieee802154/fakehard.c  |   2 +-
 drivers/net/ieee802154/fakelb.c    |   2 +-
 drivers/net/ieee802154/mrf24j40.c  |   2 +-
 include/net/cfg802154.h            | 103 +++++++++++++++++++++++++++++++++++++
 include/net/wpan-phy.h             | 102 ------------------------------------
 net/ieee802154/nl-mac.c            |   2 +-
 net/ieee802154/nl-phy.c            |   2 +-
 net/ieee802154/wpan-class.c        |   2 +-
 net/mac802154/iface.c              |   2 +-
 net/mac802154/mac_cmd.c            |   2 +-
 net/mac802154/main.c               |   2 +-
 net/mac802154/mib.c                |   2 +-
 net/mac802154/monitor.c            |   2 +-
 net/mac802154/tx.c                 |   2 +-
 16 files changed, 117 insertions(+), 116 deletions(-)
 create mode 100644 include/net/cfg802154.h
 delete mode 100644 include/net/wpan-phy.h

(limited to 'include')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 83a635f1736..795ac116602 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -32,7 +32,7 @@
 
 #include <net/ieee802154.h>
 #include <net/mac802154.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 
 struct at86rf230_local;
 /* at86rf2xx chip depend data.
diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c
index 571f280204b..f1770cf892e 100644
--- a/drivers/net/ieee802154/cc2520.c
+++ b/drivers/net/ieee802154/cc2520.c
@@ -23,7 +23,7 @@
 #include <linux/of_gpio.h>
 
 #include <net/mac802154.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 #include <net/ieee802154.h>
 
 #define	SPI_COMMAND_BUFFER	3
diff --git a/drivers/net/ieee802154/fakehard.c b/drivers/net/ieee802154/fakehard.c
index 9ce854f4391..1460bf52049 100644
--- a/drivers/net/ieee802154/fakehard.c
+++ b/drivers/net/ieee802154/fakehard.c
@@ -30,7 +30,7 @@
 #include <net/ieee802154_netdev.h>
 #include <net/ieee802154.h>
 #include <net/nl802154.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 
 struct fakehard_priv {
 	struct wpan_phy *phy;
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index e4b1b1f66bd..e6e2993b7ec 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -25,7 +25,7 @@
 #include <linux/device.h>
 #include <linux/spinlock.h>
 #include <net/mac802154.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 
 static int numlbs = 1;
 
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index 0006b9ad512..bea7349db6a 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -18,7 +18,7 @@
 #include <linux/spi/spi.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 #include <net/mac802154.h>
 #include <net/ieee802154.h>
 
diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
new file mode 100644
index 00000000000..5c674673ef2
--- /dev/null
+++ b/include/net/cfg802154.h
@@ -0,0 +1,103 @@
+/*
+ * Copyright (C) 2007, 2008, 2009 Siemens AG
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Written by:
+ * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+ */
+
+#ifndef __NET_CFG802154_H
+#define __NET_CFG802154_H
+
+#include <linux/netdevice.h>
+#include <linux/mutex.h>
+#include <linux/bug.h>
+
+/* According to the IEEE 802.15.4 stadard the upper most significant bits of
+ * the 32-bit channel bitmaps shall be used as an integer value to specify 32
+ * possible channel pages. The lower 27 bits of the channel bit map shall be
+ * used as a bit mask to specify channel numbers within a channel page.
+ */
+#define WPAN_NUM_CHANNELS	27
+#define WPAN_NUM_PAGES		32
+
+struct wpan_phy {
+	struct mutex pib_lock;
+
+	/*
+	 * This is a PIB according to 802.15.4-2011.
+	 * We do not provide timing-related variables, as they
+	 * aren't used outside of driver
+	 */
+	u8 current_channel;
+	u8 current_page;
+	u32 channels_supported[32];
+	s8 transmit_power;
+	u8 cca_mode;
+	u8 min_be;
+	u8 max_be;
+	u8 csma_retries;
+	s8 frame_retries;
+
+	bool lbt;
+	s32 cca_ed_level;
+
+	struct device dev;
+	int idx;
+
+	struct net_device *(*add_iface)(struct wpan_phy *phy,
+					const char *name, int type);
+	void (*del_iface)(struct wpan_phy *phy, struct net_device *dev);
+
+	int (*set_txpower)(struct wpan_phy *phy, int db);
+	int (*set_lbt)(struct wpan_phy *phy, bool on);
+	int (*set_cca_mode)(struct wpan_phy *phy, u8 cca_mode);
+	int (*set_cca_ed_level)(struct wpan_phy *phy, int level);
+	int (*set_csma_params)(struct wpan_phy *phy, u8 min_be, u8 max_be,
+			       u8 retries);
+	int (*set_frame_retries)(struct wpan_phy *phy, s8 retries);
+
+	char priv[0] __aligned(NETDEV_ALIGN);
+};
+
+#define to_phy(_dev)	container_of(_dev, struct wpan_phy, dev)
+
+struct wpan_phy *wpan_phy_alloc(size_t priv_size);
+static inline void wpan_phy_set_dev(struct wpan_phy *phy, struct device *dev)
+{
+	phy->dev.parent = dev;
+}
+
+int wpan_phy_register(struct wpan_phy *phy);
+void wpan_phy_unregister(struct wpan_phy *phy);
+void wpan_phy_free(struct wpan_phy *phy);
+/* Same semantics as for class_for_each_device */
+int wpan_phy_for_each(int (*fn)(struct wpan_phy *phy, void *data), void *data);
+
+static inline void *wpan_phy_priv(struct wpan_phy *phy)
+{
+	BUG_ON(!phy);
+	return &phy->priv;
+}
+
+struct wpan_phy *wpan_phy_find(const char *str);
+
+static inline void wpan_phy_put(struct wpan_phy *phy)
+{
+	put_device(&phy->dev);
+}
+
+static inline const char *wpan_phy_name(struct wpan_phy *phy)
+{
+	return dev_name(&phy->dev);
+}
+
+#endif /* __NET_CFG802154_H */
diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h
deleted file mode 100644
index 1e9795f116b..00000000000
--- a/include/net/wpan-phy.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/*
- * Copyright (C) 2007, 2008, 2009 Siemens AG
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * Written by:
- * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
- */
-
-#ifndef WPAN_PHY_H
-#define WPAN_PHY_H
-
-#include <linux/netdevice.h>
-#include <linux/mutex.h>
-#include <linux/bug.h>
-
-/* According to the IEEE 802.15.4 stadard the upper most significant bits of
- * the 32-bit channel bitmaps shall be used as an integer value to specify 32
- * possible channel pages. The lower 27 bits of the channel bit map shall be
- * used as a bit mask to specify channel numbers within a channel page.
- */
-#define WPAN_NUM_CHANNELS	27
-#define WPAN_NUM_PAGES		32
-
-struct wpan_phy {
-	struct mutex pib_lock;
-
-	/*
-	 * This is a PIB according to 802.15.4-2011.
-	 * We do not provide timing-related variables, as they
-	 * aren't used outside of driver
-	 */
-	u8 current_channel;
-	u8 current_page;
-	u32 channels_supported[32];
-	s8 transmit_power;
-	u8 cca_mode;
-	u8 min_be;
-	u8 max_be;
-	u8 csma_retries;
-	s8 frame_retries;
-
-	bool lbt;
-	s32 cca_ed_level;
-
-	struct device dev;
-	int idx;
-
-	struct net_device *(*add_iface)(struct wpan_phy *phy,
-					const char *name, int type);
-	void (*del_iface)(struct wpan_phy *phy, struct net_device *dev);
-
-	int (*set_txpower)(struct wpan_phy *phy, int db);
-	int (*set_lbt)(struct wpan_phy *phy, bool on);
-	int (*set_cca_mode)(struct wpan_phy *phy, u8 cca_mode);
-	int (*set_cca_ed_level)(struct wpan_phy *phy, int level);
-	int (*set_csma_params)(struct wpan_phy *phy, u8 min_be, u8 max_be,
-			       u8 retries);
-	int (*set_frame_retries)(struct wpan_phy *phy, s8 retries);
-
-	char priv[0] __aligned(NETDEV_ALIGN);
-};
-
-#define to_phy(_dev)	container_of(_dev, struct wpan_phy, dev)
-
-struct wpan_phy *wpan_phy_alloc(size_t priv_size);
-static inline void wpan_phy_set_dev(struct wpan_phy *phy, struct device *dev)
-{
-	phy->dev.parent = dev;
-}
-
-int wpan_phy_register(struct wpan_phy *phy);
-void wpan_phy_unregister(struct wpan_phy *phy);
-void wpan_phy_free(struct wpan_phy *phy);
-/* Same semantics as for class_for_each_device */
-int wpan_phy_for_each(int (*fn)(struct wpan_phy *phy, void *data), void *data);
-
-static inline void *wpan_phy_priv(struct wpan_phy *phy)
-{
-	BUG_ON(!phy);
-	return &phy->priv;
-}
-
-struct wpan_phy *wpan_phy_find(const char *str);
-
-static inline void wpan_phy_put(struct wpan_phy *phy)
-{
-	put_device(&phy->dev);
-}
-
-static inline const char *wpan_phy_name(struct wpan_phy *phy)
-{
-	return dev_name(&phy->dev);
-}
-#endif
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index 78a1529e8bb..a9c8e3e9838 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -31,7 +31,7 @@
 #include <net/nl802154.h>
 #include <net/ieee802154.h>
 #include <net/ieee802154_netdev.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 
 #include "ieee802154.h"
 
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index e943e20bcf0..0afe760ff51 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -23,7 +23,7 @@
 #include <linux/if_arp.h>
 #include <net/netlink.h>
 #include <net/genetlink.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 #include <net/af_ieee802154.h>
 #include <net/ieee802154_netdev.h>
 #include <net/rtnetlink.h> /* for rtnl_{un,}lock */
diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c
index e4c6fb31a36..760b7d75219 100644
--- a/net/ieee802154/wpan-class.c
+++ b/net/ieee802154/wpan-class.c
@@ -17,7 +17,7 @@
 #include <linux/module.h>
 #include <linux/device.h>
 
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 
 #include "ieee802154.h"
 
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index 5adcbd87a4f..5a604074555 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -27,7 +27,7 @@
 #include <net/mac802154.h>
 #include <net/ieee802154_netdev.h>
 #include <net/ieee802154.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 
 #include "ieee802154_i.h"
 
diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c
index 7c4b05ba2fe..f118ea06d34 100644
--- a/net/mac802154/mac_cmd.c
+++ b/net/mac802154/mac_cmd.c
@@ -23,7 +23,7 @@
 
 #include <net/ieee802154.h>
 #include <net/ieee802154_netdev.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 #include <net/mac802154.h>
 #include <net/nl802154.h>
 
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index d11e42ae10d..9798c741739 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -25,7 +25,7 @@
 #include <net/mac802154.h>
 #include <net/ieee802154_netdev.h>
 #include <net/route.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 
 #include "ieee802154_i.h"
 
diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c
index 91cd3b26024..7c946721619 100644
--- a/net/mac802154/mib.c
+++ b/net/mac802154/mib.c
@@ -21,7 +21,7 @@
 
 #include <net/mac802154.h>
 #include <net/ieee802154_netdev.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 
 #include "ieee802154_i.h"
 
diff --git a/net/mac802154/monitor.c b/net/mac802154/monitor.c
index 2647a9e002e..ca1dedd9b22 100644
--- a/net/mac802154/monitor.c
+++ b/net/mac802154/monitor.c
@@ -25,7 +25,7 @@
 #include <net/ieee802154.h>
 #include <net/mac802154.h>
 #include <net/netlink.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 #include <linux/nl802154.h>
 
 #include "ieee802154_i.h"
diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c
index ef11cc6fa32..8f537bf731c 100644
--- a/net/mac802154/tx.c
+++ b/net/mac802154/tx.c
@@ -23,7 +23,7 @@
 
 #include <net/ieee802154_netdev.h>
 #include <net/mac802154.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 
 #include "ieee802154_i.h"
 
-- 
cgit v1.2.3-70-g09d2


From 4ca24aca55fe1e2a61f3ffaac9015d9c45204729 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sat, 25 Oct 2014 09:41:04 +0200
Subject: ieee802154: move ieee802154 header

This patch moves the ieee802154 header into include/linux instead
include/net. Similar like wireless which have the ieee80211 header
inside of include/linux.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Cc: Alan Ott <alan@signal11.us>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/net/ieee802154/at86rf230.c |   2 +-
 drivers/net/ieee802154/cc2520.c    |   2 +-
 drivers/net/ieee802154/fakehard.c  |   2 +-
 drivers/net/ieee802154/mrf24j40.c  |   2 +-
 include/linux/ieee802154.h         | 189 ++++++++++++++++++++++++++++++++++++
 include/net/ieee802154.h           | 191 -------------------------------------
 include/net/ieee802154_netdev.h    |   2 +-
 net/ieee802154/6lowpan_rtnl.c      |   2 +-
 net/ieee802154/dgram.c             |   2 +-
 net/ieee802154/header_ops.c        |   3 +-
 net/ieee802154/nl-mac.c            |   2 +-
 net/mac802154/iface.c              |   2 +-
 net/mac802154/llsec.c              |   2 +-
 net/mac802154/mac_cmd.c            |   2 +-
 net/mac802154/monitor.c            |   2 +-
 15 files changed, 203 insertions(+), 204 deletions(-)
 create mode 100644 include/linux/ieee802154.h
 delete mode 100644 include/net/ieee802154.h

(limited to 'include')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 795ac116602..a433d20587e 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -29,8 +29,8 @@
 #include <linux/regmap.h>
 #include <linux/skbuff.h>
 #include <linux/of_gpio.h>
+#include <linux/ieee802154.h>
 
-#include <net/ieee802154.h>
 #include <net/mac802154.h>
 #include <net/cfg802154.h>
 
diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c
index f1770cf892e..32b3c8862b4 100644
--- a/drivers/net/ieee802154/cc2520.c
+++ b/drivers/net/ieee802154/cc2520.c
@@ -21,10 +21,10 @@
 #include <linux/skbuff.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/of_gpio.h>
+#include <linux/ieee802154.h>
 
 #include <net/mac802154.h>
 #include <net/cfg802154.h>
-#include <net/ieee802154.h>
 
 #define	SPI_COMMAND_BUFFER	3
 #define	HIGH			1
diff --git a/drivers/net/ieee802154/fakehard.c b/drivers/net/ieee802154/fakehard.c
index 1460bf52049..8be05ade0ce 100644
--- a/drivers/net/ieee802154/fakehard.c
+++ b/drivers/net/ieee802154/fakehard.c
@@ -25,10 +25,10 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/if_arp.h>
+#include <linux/ieee802154.h>
 
 #include <net/af_ieee802154.h>
 #include <net/ieee802154_netdev.h>
-#include <net/ieee802154.h>
 #include <net/nl802154.h>
 #include <net/cfg802154.h>
 
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index bea7349db6a..56a69599ac3 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -18,9 +18,9 @@
 #include <linux/spi/spi.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/ieee802154.h>
 #include <net/cfg802154.h>
 #include <net/mac802154.h>
-#include <net/ieee802154.h>
 
 /* MRF24J40 Short Address Registers */
 #define REG_RXMCR    0x00  /* Receive MAC control */
diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
new file mode 100644
index 00000000000..2dfab2db103
--- /dev/null
+++ b/include/linux/ieee802154.h
@@ -0,0 +1,189 @@
+/*
+ * IEEE802.15.4-2003 specification
+ *
+ * Copyright (C) 2007, 2008 Siemens AG
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Written by:
+ * Pavel Smolenskiy <pavel.smolenskiy@gmail.com>
+ * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
+ * Maxim Osipov <maxim.osipov@siemens.com>
+ * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+ * Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
+ */
+
+#ifndef LINUX_IEEE802154_H
+#define LINUX_IEEE802154_H
+
+#define IEEE802154_MTU			127
+
+#define IEEE802154_FC_TYPE_BEACON	0x0	/* Frame is beacon */
+#define	IEEE802154_FC_TYPE_DATA		0x1	/* Frame is data */
+#define IEEE802154_FC_TYPE_ACK		0x2	/* Frame is acknowledgment */
+#define IEEE802154_FC_TYPE_MAC_CMD	0x3	/* Frame is MAC command */
+
+#define IEEE802154_FC_TYPE_SHIFT		0
+#define IEEE802154_FC_TYPE_MASK		((1 << 3) - 1)
+#define IEEE802154_FC_TYPE(x)		((x & IEEE802154_FC_TYPE_MASK) >> IEEE802154_FC_TYPE_SHIFT)
+#define IEEE802154_FC_SET_TYPE(v, x)	do {	\
+	v = (((v) & ~IEEE802154_FC_TYPE_MASK) | \
+	    (((x) << IEEE802154_FC_TYPE_SHIFT) & IEEE802154_FC_TYPE_MASK)); \
+	} while (0)
+
+#define IEEE802154_FC_SECEN_SHIFT	3
+#define IEEE802154_FC_SECEN		(1 << IEEE802154_FC_SECEN_SHIFT)
+#define IEEE802154_FC_FRPEND_SHIFT	4
+#define IEEE802154_FC_FRPEND		(1 << IEEE802154_FC_FRPEND_SHIFT)
+#define IEEE802154_FC_ACK_REQ_SHIFT	5
+#define IEEE802154_FC_ACK_REQ		(1 << IEEE802154_FC_ACK_REQ_SHIFT)
+#define IEEE802154_FC_INTRA_PAN_SHIFT	6
+#define IEEE802154_FC_INTRA_PAN		(1 << IEEE802154_FC_INTRA_PAN_SHIFT)
+
+#define IEEE802154_FC_SAMODE_SHIFT	14
+#define IEEE802154_FC_SAMODE_MASK	(3 << IEEE802154_FC_SAMODE_SHIFT)
+#define IEEE802154_FC_DAMODE_SHIFT	10
+#define IEEE802154_FC_DAMODE_MASK	(3 << IEEE802154_FC_DAMODE_SHIFT)
+
+#define IEEE802154_FC_VERSION_SHIFT	12
+#define IEEE802154_FC_VERSION_MASK	(3 << IEEE802154_FC_VERSION_SHIFT)
+#define IEEE802154_FC_VERSION(x)	((x & IEEE802154_FC_VERSION_MASK) >> IEEE802154_FC_VERSION_SHIFT)
+
+#define IEEE802154_FC_SAMODE(x)		\
+	(((x) & IEEE802154_FC_SAMODE_MASK) >> IEEE802154_FC_SAMODE_SHIFT)
+
+#define IEEE802154_FC_DAMODE(x)		\
+	(((x) & IEEE802154_FC_DAMODE_MASK) >> IEEE802154_FC_DAMODE_SHIFT)
+
+#define IEEE802154_SCF_SECLEVEL_MASK		7
+#define IEEE802154_SCF_SECLEVEL_SHIFT		0
+#define IEEE802154_SCF_SECLEVEL(x)		(x & IEEE802154_SCF_SECLEVEL_MASK)
+#define IEEE802154_SCF_KEY_ID_MODE_SHIFT	3
+#define IEEE802154_SCF_KEY_ID_MODE_MASK		(3 << IEEE802154_SCF_KEY_ID_MODE_SHIFT)
+#define IEEE802154_SCF_KEY_ID_MODE(x)		\
+	((x & IEEE802154_SCF_KEY_ID_MODE_MASK) >> IEEE802154_SCF_KEY_ID_MODE_SHIFT)
+
+#define IEEE802154_SCF_KEY_IMPLICIT		0
+#define IEEE802154_SCF_KEY_INDEX		1
+#define IEEE802154_SCF_KEY_SHORT_INDEX		2
+#define IEEE802154_SCF_KEY_HW_INDEX		3
+
+#define IEEE802154_SCF_SECLEVEL_NONE		0
+#define IEEE802154_SCF_SECLEVEL_MIC32		1
+#define IEEE802154_SCF_SECLEVEL_MIC64		2
+#define IEEE802154_SCF_SECLEVEL_MIC128		3
+#define IEEE802154_SCF_SECLEVEL_ENC		4
+#define IEEE802154_SCF_SECLEVEL_ENC_MIC32	5
+#define IEEE802154_SCF_SECLEVEL_ENC_MIC64	6
+#define IEEE802154_SCF_SECLEVEL_ENC_MIC128	7
+
+/* MAC footer size */
+#define IEEE802154_MFR_SIZE	2 /* 2 octets */
+
+/* MAC's Command Frames Identifiers */
+#define IEEE802154_CMD_ASSOCIATION_REQ		0x01
+#define IEEE802154_CMD_ASSOCIATION_RESP		0x02
+#define IEEE802154_CMD_DISASSOCIATION_NOTIFY	0x03
+#define IEEE802154_CMD_DATA_REQ			0x04
+#define IEEE802154_CMD_PANID_CONFLICT_NOTIFY	0x05
+#define IEEE802154_CMD_ORPHAN_NOTIFY		0x06
+#define IEEE802154_CMD_BEACON_REQ		0x07
+#define IEEE802154_CMD_COORD_REALIGN_NOTIFY	0x08
+#define IEEE802154_CMD_GTS_REQ			0x09
+
+/*
+ * The return values of MAC operations
+ */
+enum {
+	/*
+	 * The requested operation was completed successfully.
+	 * For a transmission request, this value indicates
+	 * a successful transmission.
+	 */
+	IEEE802154_SUCCESS = 0x0,
+
+	/* The beacon was lost following a synchronization request. */
+	IEEE802154_BEACON_LOSS = 0xe0,
+	/*
+	 * A transmission could not take place due to activity on the
+	 * channel, i.e., the CSMA-CA mechanism has failed.
+	 */
+	IEEE802154_CHNL_ACCESS_FAIL = 0xe1,
+	/* The GTS request has been denied by the PAN coordinator. */
+	IEEE802154_DENINED = 0xe2,
+	/* The attempt to disable the transceiver has failed. */
+	IEEE802154_DISABLE_TRX_FAIL = 0xe3,
+	/*
+	 * The received frame induces a failed security check according to
+	 * the security suite.
+	 */
+	IEEE802154_FAILED_SECURITY_CHECK = 0xe4,
+	/*
+	 * The frame resulting from secure processing has a length that is
+	 * greater than aMACMaxFrameSize.
+	 */
+	IEEE802154_FRAME_TOO_LONG = 0xe5,
+	/*
+	 * The requested GTS transmission failed because the specified GTS
+	 * either did not have a transmit GTS direction or was not defined.
+	 */
+	IEEE802154_INVALID_GTS = 0xe6,
+	/*
+	 * A request to purge an MSDU from the transaction queue was made using
+	 * an MSDU handle that was not found in the transaction table.
+	 */
+	IEEE802154_INVALID_HANDLE = 0xe7,
+	/* A parameter in the primitive is out of the valid range.*/
+	IEEE802154_INVALID_PARAMETER = 0xe8,
+	/* No acknowledgment was received after aMaxFrameRetries. */
+	IEEE802154_NO_ACK = 0xe9,
+	/* A scan operation failed to find any network beacons.*/
+	IEEE802154_NO_BEACON = 0xea,
+	/* No response data were available following a request. */
+	IEEE802154_NO_DATA = 0xeb,
+	/* The operation failed because a short address was not allocated. */
+	IEEE802154_NO_SHORT_ADDRESS = 0xec,
+	/*
+	 * A receiver enable request was unsuccessful because it could not be
+	 * completed within the CAP.
+	 */
+	IEEE802154_OUT_OF_CAP = 0xed,
+	/*
+	 * A PAN identifier conflict has been detected and communicated to the
+	 * PAN coordinator.
+	 */
+	IEEE802154_PANID_CONFLICT = 0xee,
+	/* A coordinator realignment command has been received. */
+	IEEE802154_REALIGMENT = 0xef,
+	/* The transaction has expired and its information discarded. */
+	IEEE802154_TRANSACTION_EXPIRED = 0xf0,
+	/* There is no capacity to store the transaction. */
+	IEEE802154_TRANSACTION_OVERFLOW = 0xf1,
+	/*
+	 * The transceiver was in the transmitter enabled state when the
+	 * receiver was requested to be enabled.
+	 */
+	IEEE802154_TX_ACTIVE = 0xf2,
+	/* The appropriate key is not available in the ACL. */
+	IEEE802154_UNAVAILABLE_KEY = 0xf3,
+	/*
+	 * A SET/GET request was issued with the identifier of a PIB attribute
+	 * that is not supported.
+	 */
+	IEEE802154_UNSUPPORTED_ATTR = 0xf4,
+	/*
+	 * A request to perform a scan operation failed because the MLME was
+	 * in the process of performing a previously initiated scan operation.
+	 */
+	IEEE802154_SCAN_IN_PROGRESS = 0xfc,
+};
+
+
+#endif /* LINUX_IEEE802154_H */
diff --git a/include/net/ieee802154.h b/include/net/ieee802154.h
deleted file mode 100644
index 4db4e320b2f..00000000000
--- a/include/net/ieee802154.h
+++ /dev/null
@@ -1,191 +0,0 @@
-/*
- * IEEE802.15.4-2003 specification
- *
- * Copyright (C) 2007, 2008 Siemens AG
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * Written by:
- * Pavel Smolenskiy <pavel.smolenskiy@gmail.com>
- * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
- * Maxim Osipov <maxim.osipov@siemens.com>
- * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
- * Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
- */
-
-#ifndef NET_IEEE802154_H
-#define NET_IEEE802154_H
-
-#define IEEE802154_MTU			127
-
-#define IEEE802154_FC_TYPE_BEACON	0x0	/* Frame is beacon */
-#define	IEEE802154_FC_TYPE_DATA		0x1	/* Frame is data */
-#define IEEE802154_FC_TYPE_ACK		0x2	/* Frame is acknowledgment */
-#define IEEE802154_FC_TYPE_MAC_CMD	0x3	/* Frame is MAC command */
-
-#define IEEE802154_FC_TYPE_SHIFT		0
-#define IEEE802154_FC_TYPE_MASK		((1 << 3) - 1)
-#define IEEE802154_FC_TYPE(x)		((x & IEEE802154_FC_TYPE_MASK) >> IEEE802154_FC_TYPE_SHIFT)
-#define IEEE802154_FC_SET_TYPE(v, x)	do {	\
-	v = (((v) & ~IEEE802154_FC_TYPE_MASK) | \
-	    (((x) << IEEE802154_FC_TYPE_SHIFT) & IEEE802154_FC_TYPE_MASK)); \
-	} while (0)
-
-#define IEEE802154_FC_SECEN_SHIFT	3
-#define IEEE802154_FC_SECEN		(1 << IEEE802154_FC_SECEN_SHIFT)
-#define IEEE802154_FC_FRPEND_SHIFT	4
-#define IEEE802154_FC_FRPEND		(1 << IEEE802154_FC_FRPEND_SHIFT)
-#define IEEE802154_FC_ACK_REQ_SHIFT	5
-#define IEEE802154_FC_ACK_REQ		(1 << IEEE802154_FC_ACK_REQ_SHIFT)
-#define IEEE802154_FC_INTRA_PAN_SHIFT	6
-#define IEEE802154_FC_INTRA_PAN		(1 << IEEE802154_FC_INTRA_PAN_SHIFT)
-
-#define IEEE802154_FC_SAMODE_SHIFT	14
-#define IEEE802154_FC_SAMODE_MASK	(3 << IEEE802154_FC_SAMODE_SHIFT)
-#define IEEE802154_FC_DAMODE_SHIFT	10
-#define IEEE802154_FC_DAMODE_MASK	(3 << IEEE802154_FC_DAMODE_SHIFT)
-
-#define IEEE802154_FC_VERSION_SHIFT	12
-#define IEEE802154_FC_VERSION_MASK	(3 << IEEE802154_FC_VERSION_SHIFT)
-#define IEEE802154_FC_VERSION(x)	((x & IEEE802154_FC_VERSION_MASK) >> IEEE802154_FC_VERSION_SHIFT)
-
-#define IEEE802154_FC_SAMODE(x)		\
-	(((x) & IEEE802154_FC_SAMODE_MASK) >> IEEE802154_FC_SAMODE_SHIFT)
-
-#define IEEE802154_FC_DAMODE(x)		\
-	(((x) & IEEE802154_FC_DAMODE_MASK) >> IEEE802154_FC_DAMODE_SHIFT)
-
-#define IEEE802154_SCF_SECLEVEL_MASK		7
-#define IEEE802154_SCF_SECLEVEL_SHIFT		0
-#define IEEE802154_SCF_SECLEVEL(x)		(x & IEEE802154_SCF_SECLEVEL_MASK)
-#define IEEE802154_SCF_KEY_ID_MODE_SHIFT	3
-#define IEEE802154_SCF_KEY_ID_MODE_MASK		(3 << IEEE802154_SCF_KEY_ID_MODE_SHIFT)
-#define IEEE802154_SCF_KEY_ID_MODE(x)		\
-	((x & IEEE802154_SCF_KEY_ID_MODE_MASK) >> IEEE802154_SCF_KEY_ID_MODE_SHIFT)
-
-#define IEEE802154_SCF_KEY_IMPLICIT		0
-#define IEEE802154_SCF_KEY_INDEX		1
-#define IEEE802154_SCF_KEY_SHORT_INDEX		2
-#define IEEE802154_SCF_KEY_HW_INDEX		3
-
-#define IEEE802154_SCF_SECLEVEL_NONE		0
-#define IEEE802154_SCF_SECLEVEL_MIC32		1
-#define IEEE802154_SCF_SECLEVEL_MIC64		2
-#define IEEE802154_SCF_SECLEVEL_MIC128		3
-#define IEEE802154_SCF_SECLEVEL_ENC		4
-#define IEEE802154_SCF_SECLEVEL_ENC_MIC32	5
-#define IEEE802154_SCF_SECLEVEL_ENC_MIC64	6
-#define IEEE802154_SCF_SECLEVEL_ENC_MIC128	7
-
-/* MAC footer size */
-#define IEEE802154_MFR_SIZE	2 /* 2 octets */
-
-/* MAC's Command Frames Identifiers */
-#define IEEE802154_CMD_ASSOCIATION_REQ		0x01
-#define IEEE802154_CMD_ASSOCIATION_RESP		0x02
-#define IEEE802154_CMD_DISASSOCIATION_NOTIFY	0x03
-#define IEEE802154_CMD_DATA_REQ			0x04
-#define IEEE802154_CMD_PANID_CONFLICT_NOTIFY	0x05
-#define IEEE802154_CMD_ORPHAN_NOTIFY		0x06
-#define IEEE802154_CMD_BEACON_REQ		0x07
-#define IEEE802154_CMD_COORD_REALIGN_NOTIFY	0x08
-#define IEEE802154_CMD_GTS_REQ			0x09
-
-/*
- * The return values of MAC operations
- */
-enum {
-	/*
-	 * The requested operation was completed successfully.
-	 * For a transmission request, this value indicates
-	 * a successful transmission.
-	 */
-	IEEE802154_SUCCESS = 0x0,
-
-	/* The beacon was lost following a synchronization request. */
-	IEEE802154_BEACON_LOSS = 0xe0,
-	/*
-	 * A transmission could not take place due to activity on the
-	 * channel, i.e., the CSMA-CA mechanism has failed.
-	 */
-	IEEE802154_CHNL_ACCESS_FAIL = 0xe1,
-	/* The GTS request has been denied by the PAN coordinator. */
-	IEEE802154_DENINED = 0xe2,
-	/* The attempt to disable the transceiver has failed. */
-	IEEE802154_DISABLE_TRX_FAIL = 0xe3,
-	/*
-	 * The received frame induces a failed security check according to
-	 * the security suite.
-	 */
-	IEEE802154_FAILED_SECURITY_CHECK = 0xe4,
-	/*
-	 * The frame resulting from secure processing has a length that is
-	 * greater than aMACMaxFrameSize.
-	 */
-	IEEE802154_FRAME_TOO_LONG = 0xe5,
-	/*
-	 * The requested GTS transmission failed because the specified GTS
-	 * either did not have a transmit GTS direction or was not defined.
-	 */
-	IEEE802154_INVALID_GTS = 0xe6,
-	/*
-	 * A request to purge an MSDU from the transaction queue was made using
-	 * an MSDU handle that was not found in the transaction table.
-	 */
-	IEEE802154_INVALID_HANDLE = 0xe7,
-	/* A parameter in the primitive is out of the valid range.*/
-	IEEE802154_INVALID_PARAMETER = 0xe8,
-	/* No acknowledgment was received after aMaxFrameRetries. */
-	IEEE802154_NO_ACK = 0xe9,
-	/* A scan operation failed to find any network beacons.*/
-	IEEE802154_NO_BEACON = 0xea,
-	/* No response data were available following a request. */
-	IEEE802154_NO_DATA = 0xeb,
-	/* The operation failed because a short address was not allocated. */
-	IEEE802154_NO_SHORT_ADDRESS = 0xec,
-	/*
-	 * A receiver enable request was unsuccessful because it could not be
-	 * completed within the CAP.
-	 */
-	IEEE802154_OUT_OF_CAP = 0xed,
-	/*
-	 * A PAN identifier conflict has been detected and communicated to the
-	 * PAN coordinator.
-	 */
-	IEEE802154_PANID_CONFLICT = 0xee,
-	/* A coordinator realignment command has been received. */
-	IEEE802154_REALIGMENT = 0xef,
-	/* The transaction has expired and its information discarded. */
-	IEEE802154_TRANSACTION_EXPIRED = 0xf0,
-	/* There is no capacity to store the transaction. */
-	IEEE802154_TRANSACTION_OVERFLOW = 0xf1,
-	/*
-	 * The transceiver was in the transmitter enabled state when the
-	 * receiver was requested to be enabled.
-	 */
-	IEEE802154_TX_ACTIVE = 0xf2,
-	/* The appropriate key is not available in the ACL. */
-	IEEE802154_UNAVAILABLE_KEY = 0xf3,
-	/*
-	 * A SET/GET request was issued with the identifier of a PIB attribute
-	 * that is not supported.
-	 */
-	IEEE802154_UNSUPPORTED_ATTR = 0xf4,
-	/*
-	 * A request to perform a scan operation failed because the MLME was
-	 * in the process of performing a previously initiated scan operation.
-	 */
-	IEEE802154_SCAN_IN_PROGRESS = 0xfc,
-};
-
-
-#endif
-
-
diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h
index f87420689d7..5e62d758eea 100644
--- a/include/net/ieee802154_netdev.h
+++ b/include/net/ieee802154_netdev.h
@@ -23,10 +23,10 @@
 #ifndef IEEE802154_NETDEVICE_H
 #define IEEE802154_NETDEVICE_H
 
-#include <net/ieee802154.h>
 #include <net/af_ieee802154.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
+#include <linux/ieee802154.h>
 
 struct ieee802154_sechdr {
 #if defined(__LITTLE_ENDIAN_BITFIELD)
diff --git a/net/ieee802154/6lowpan_rtnl.c b/net/ieee802154/6lowpan_rtnl.c
index 0c1a49b51e5..1779a08d110 100644
--- a/net/ieee802154/6lowpan_rtnl.c
+++ b/net/ieee802154/6lowpan_rtnl.c
@@ -49,8 +49,8 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/netdevice.h>
+#include <linux/ieee802154.h>
 #include <net/af_ieee802154.h>
-#include <net/ieee802154.h>
 #include <net/ieee802154_netdev.h>
 #include <net/6lowpan.h>
 #include <net/ipv6.h>
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
index 71e99a0994e..3d58befef46 100644
--- a/net/ieee802154/dgram.c
+++ b/net/ieee802154/dgram.c
@@ -23,9 +23,9 @@
 #include <linux/if_arp.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <linux/ieee802154.h>
 #include <net/sock.h>
 #include <net/af_ieee802154.h>
-#include <net/ieee802154.h>
 #include <net/ieee802154_netdev.h>
 
 #include <asm/ioctls.h>
diff --git a/net/ieee802154/header_ops.c b/net/ieee802154/header_ops.c
index c09294e39ca..a051b699317 100644
--- a/net/ieee802154/header_ops.c
+++ b/net/ieee802154/header_ops.c
@@ -14,8 +14,9 @@
  * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
  */
 
+#include <linux/ieee802154.h>
+
 #include <net/mac802154.h>
-#include <net/ieee802154.h>
 #include <net/ieee802154_netdev.h>
 
 static int
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index a9c8e3e9838..fb6866d1dd3 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -22,6 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/if_arp.h>
 #include <linux/netdevice.h>
+#include <linux/ieee802154.h>
 #include <net/netlink.h>
 #include <net/genetlink.h>
 #include <net/sock.h>
@@ -29,7 +30,6 @@
 #include <linux/export.h>
 #include <net/af_ieee802154.h>
 #include <net/nl802154.h>
-#include <net/ieee802154.h>
 #include <net/ieee802154_netdev.h>
 #include <net/cfg802154.h>
 
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index 5a604074555..03eedc3b23e 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -20,13 +20,13 @@
 #include <linux/netdevice.h>
 #include <linux/module.h>
 #include <linux/if_arp.h>
+#include <linux/ieee802154.h>
 
 #include <net/rtnetlink.h>
 #include <linux/nl802154.h>
 #include <net/af_ieee802154.h>
 #include <net/mac802154.h>
 #include <net/ieee802154_netdev.h>
-#include <net/ieee802154.h>
 #include <net/cfg802154.h>
 
 #include "ieee802154_i.h"
diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c
index 26f876128ae..fa0d5237c2e 100644
--- a/net/mac802154/llsec.c
+++ b/net/mac802154/llsec.c
@@ -17,7 +17,7 @@
 #include <linux/err.h>
 #include <linux/bug.h>
 #include <linux/completion.h>
-#include <net/ieee802154.h>
+#include <linux/ieee802154.h>
 #include <crypto/algapi.h>
 
 #include "ieee802154_i.h"
diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c
index f118ea06d34..ad09d54bc69 100644
--- a/net/mac802154/mac_cmd.c
+++ b/net/mac802154/mac_cmd.c
@@ -20,8 +20,8 @@
 
 #include <linux/skbuff.h>
 #include <linux/if_arp.h>
+#include <linux/ieee802154.h>
 
-#include <net/ieee802154.h>
 #include <net/ieee802154_netdev.h>
 #include <net/cfg802154.h>
 #include <net/mac802154.h>
diff --git a/net/mac802154/monitor.c b/net/mac802154/monitor.c
index ca1dedd9b22..ca82c72a635 100644
--- a/net/mac802154/monitor.c
+++ b/net/mac802154/monitor.c
@@ -21,8 +21,8 @@
 #include <linux/skbuff.h>
 #include <linux/if_arp.h>
 #include <linux/crc-ccitt.h>
+#include <linux/ieee802154.h>
 
-#include <net/ieee802154.h>
 #include <net/mac802154.h>
 #include <net/netlink.h>
 #include <net/cfg802154.h>
-- 
cgit v1.2.3-70-g09d2


From 5a50439775853a8d565115edb63a5ab4bb780479 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sat, 25 Oct 2014 17:16:34 +0200
Subject: ieee802154: rename ieee802154_dev to ieee802154_hw

The identical struct of the wireless stack implementation is named
ieee80211_hw. This is useful to name the variable hw instead of get
confusing with netdev dev variable.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Cc: Alan Ott <alan@signal11.us>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/net/ieee802154/at86rf230.c | 90 +++++++++++++++++++-------------------
 drivers/net/ieee802154/cc2520.c    | 50 ++++++++++-----------
 drivers/net/ieee802154/fakelb.c    | 78 ++++++++++++++++-----------------
 drivers/net/ieee802154/mrf24j40.c  | 48 ++++++++++----------
 include/net/mac802154.h            | 44 +++++++++----------
 net/mac802154/ieee802154_i.h       |  2 +-
 net/mac802154/main.c               | 34 +++++++-------
 net/mac802154/rx.c                 | 12 ++---
 8 files changed, 179 insertions(+), 179 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index a433d20587e..b0d68d7061c 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -77,7 +77,7 @@ struct at86rf230_state_change {
 struct at86rf230_local {
 	struct spi_device *spi;
 
-	struct ieee802154_dev *dev;
+	struct ieee802154_hw *hw;
 	struct at86rf2xx_chip_data *data;
 	struct regmap *regmap;
 
@@ -808,7 +808,7 @@ at86rf230_rx(struct at86rf230_local *lp,
 	/* We do not put CRC into the frame */
 	skb_trim(skb, len - 2);
 
-	ieee802154_rx_irqsafe(lp->dev, skb, lqi);
+	ieee802154_rx_irqsafe(lp->hw, skb, lqi);
 }
 
 static void
@@ -969,9 +969,9 @@ at86rf230_xmit_tx_on(void *context)
 }
 
 static int
-at86rf230_xmit(struct ieee802154_dev *dev, struct sk_buff *skb)
+at86rf230_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
 {
-	struct at86rf230_local *lp = dev->priv;
+	struct at86rf230_local *lp = hw->priv;
 	struct at86rf230_state_change *ctx = &lp->tx;
 
 	void (*tx_complete)(void *context) = at86rf230_write_frame;
@@ -1012,7 +1012,7 @@ at86rf230_xmit(struct ieee802154_dev *dev, struct sk_buff *skb)
 }
 
 static int
-at86rf230_ed(struct ieee802154_dev *dev, u8 *level)
+at86rf230_ed(struct ieee802154_hw *hw, u8 *level)
 {
 	might_sleep();
 	BUG_ON(!level);
@@ -1021,15 +1021,15 @@ at86rf230_ed(struct ieee802154_dev *dev, u8 *level)
 }
 
 static int
-at86rf230_start(struct ieee802154_dev *dev)
+at86rf230_start(struct ieee802154_hw *hw)
 {
-	return at86rf230_sync_state_change(dev->priv, STATE_RX_AACK_ON);
+	return at86rf230_sync_state_change(hw->priv, STATE_RX_AACK_ON);
 }
 
 static void
-at86rf230_stop(struct ieee802154_dev *dev)
+at86rf230_stop(struct ieee802154_hw *hw)
 {
-	at86rf230_sync_state_change(dev->priv, STATE_FORCE_TRX_OFF);
+	at86rf230_sync_state_change(hw->priv, STATE_FORCE_TRX_OFF);
 }
 
 static int
@@ -1064,15 +1064,15 @@ at86rf212_set_channel(struct at86rf230_local *lp, int page, int channel)
 }
 
 static int
-at86rf230_channel(struct ieee802154_dev *dev, int page, int channel)
+at86rf230_channel(struct ieee802154_hw *hw, int page, int channel)
 {
-	struct at86rf230_local *lp = dev->priv;
+	struct at86rf230_local *lp = hw->priv;
 	int rc;
 
 	might_sleep();
 
 	if (page < 0 || page > 31 ||
-	    !(lp->dev->phy->channels_supported[page] & BIT(channel))) {
+	    !(lp->hw->phy->channels_supported[page] & BIT(channel))) {
 		WARN_ON(1);
 		return -EINVAL;
 	}
@@ -1084,18 +1084,18 @@ at86rf230_channel(struct ieee802154_dev *dev, int page, int channel)
 	/* Wait for PLL */
 	usleep_range(lp->data->t_channel_switch,
 		     lp->data->t_channel_switch + 10);
-	dev->phy->current_channel = channel;
-	dev->phy->current_page = page;
+	hw->phy->current_channel = channel;
+	hw->phy->current_page = page;
 
 	return 0;
 }
 
 static int
-at86rf230_set_hw_addr_filt(struct ieee802154_dev *dev,
+at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw,
 			   struct ieee802154_hw_addr_filt *filt,
 			   unsigned long changed)
 {
-	struct at86rf230_local *lp = dev->priv;
+	struct at86rf230_local *lp = hw->priv;
 
 	if (changed & IEEE802154_AFILT_SADDR_CHANGED) {
 		u16 addr = le16_to_cpu(filt->short_addr);
@@ -1138,9 +1138,9 @@ at86rf230_set_hw_addr_filt(struct ieee802154_dev *dev,
 }
 
 static int
-at86rf230_set_txpower(struct ieee802154_dev *dev, int db)
+at86rf230_set_txpower(struct ieee802154_hw *hw, int db)
 {
-	struct at86rf230_local *lp = dev->priv;
+	struct at86rf230_local *lp = hw->priv;
 
 	/* typical maximum output is 5dBm with RG_PHY_TX_PWR 0x60, lower five
 	 * bits decrease power in 1dB steps. 0x60 represents extra PA gain of
@@ -1157,17 +1157,17 @@ at86rf230_set_txpower(struct ieee802154_dev *dev, int db)
 }
 
 static int
-at86rf230_set_lbt(struct ieee802154_dev *dev, bool on)
+at86rf230_set_lbt(struct ieee802154_hw *hw, bool on)
 {
-	struct at86rf230_local *lp = dev->priv;
+	struct at86rf230_local *lp = hw->priv;
 
 	return at86rf230_write_subreg(lp, SR_CSMA_LBT_MODE, on);
 }
 
 static int
-at86rf230_set_cca_mode(struct ieee802154_dev *dev, u8 mode)
+at86rf230_set_cca_mode(struct ieee802154_hw *hw, u8 mode)
 {
-	struct at86rf230_local *lp = dev->priv;
+	struct at86rf230_local *lp = hw->priv;
 
 	return at86rf230_write_subreg(lp, SR_CCA_MODE, mode);
 }
@@ -1185,9 +1185,9 @@ at86rf23x_get_desens_steps(struct at86rf230_local *lp, s32 level)
 }
 
 static int
-at86rf230_set_cca_ed_level(struct ieee802154_dev *dev, s32 level)
+at86rf230_set_cca_ed_level(struct ieee802154_hw *hw, s32 level)
 {
-	struct at86rf230_local *lp = dev->priv;
+	struct at86rf230_local *lp = hw->priv;
 
 	if (level < lp->data->rssi_base_val || level > 30)
 		return -EINVAL;
@@ -1197,10 +1197,10 @@ at86rf230_set_cca_ed_level(struct ieee802154_dev *dev, s32 level)
 }
 
 static int
-at86rf230_set_csma_params(struct ieee802154_dev *dev, u8 min_be, u8 max_be,
+at86rf230_set_csma_params(struct ieee802154_hw *hw, u8 min_be, u8 max_be,
 			  u8 retries)
 {
-	struct at86rf230_local *lp = dev->priv;
+	struct at86rf230_local *lp = hw->priv;
 	int rc;
 
 	if (min_be > max_be || max_be > 8 || retries > 5)
@@ -1218,9 +1218,9 @@ at86rf230_set_csma_params(struct ieee802154_dev *dev, u8 min_be, u8 max_be,
 }
 
 static int
-at86rf230_set_frame_retries(struct ieee802154_dev *dev, s8 retries)
+at86rf230_set_frame_retries(struct ieee802154_hw *hw, s8 retries)
 {
-	struct at86rf230_local *lp = dev->priv;
+	struct at86rf230_local *lp = hw->priv;
 	int rc = 0;
 
 	if (retries < -1 || retries > 15)
@@ -1409,8 +1409,8 @@ at86rf230_detect_device(struct at86rf230_local *lp)
 		return -EINVAL;
 	}
 
-	lp->dev->extra_tx_headroom = 0;
-	lp->dev->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK |
+	lp->hw->extra_tx_headroom = 0;
+	lp->hw->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK |
 			 IEEE802154_HW_TXPOWER | IEEE802154_HW_CSMA;
 
 	switch (part) {
@@ -1421,15 +1421,15 @@ at86rf230_detect_device(struct at86rf230_local *lp)
 	case 3:
 		chip = "at86rf231";
 		lp->data = &at86rf231_data;
-		lp->dev->phy->channels_supported[0] = 0x7FFF800;
+		lp->hw->phy->channels_supported[0] = 0x7FFF800;
 		break;
 	case 7:
 		chip = "at86rf212";
 		if (version == 1) {
 			lp->data = &at86rf212_data;
-			lp->dev->flags |= IEEE802154_HW_LBT;
-			lp->dev->phy->channels_supported[0] = 0x00007FF;
-			lp->dev->phy->channels_supported[2] = 0x00007FF;
+			lp->hw->flags |= IEEE802154_HW_LBT;
+			lp->hw->phy->channels_supported[0] = 0x00007FF;
+			lp->hw->phy->channels_supported[2] = 0x00007FF;
 		} else {
 			rc = -ENOTSUPP;
 		}
@@ -1437,7 +1437,7 @@ at86rf230_detect_device(struct at86rf230_local *lp)
 	case 11:
 		chip = "at86rf233";
 		lp->data = &at86rf233_data;
-		lp->dev->phy->channels_supported[0] = 0x7FFF800;
+		lp->hw->phy->channels_supported[0] = 0x7FFF800;
 		break;
 	default:
 		chip = "unkown";
@@ -1478,7 +1478,7 @@ at86rf230_setup_spi_messages(struct at86rf230_local *lp)
 static int at86rf230_probe(struct spi_device *spi)
 {
 	struct at86rf230_platform_data *pdata;
-	struct ieee802154_dev *dev;
+	struct ieee802154_hw *hw;
 	struct at86rf230_local *lp;
 	unsigned int status;
 	int rc, irq_type;
@@ -1517,14 +1517,14 @@ static int at86rf230_probe(struct spi_device *spi)
 		usleep_range(120, 240);
 	}
 
-	dev = ieee802154_alloc_device(sizeof(*lp), &at86rf230_ops);
-	if (!dev)
+	hw = ieee802154_alloc_hw(sizeof(*lp), &at86rf230_ops);
+	if (!hw)
 		return -ENOMEM;
 
-	lp = dev->priv;
-	lp->dev = dev;
+	lp = hw->priv;
+	lp->hw = hw;
 	lp->spi = spi;
-	dev->parent = &spi->dev;
+	hw->parent = &spi->dev;
 
 	lp->regmap = devm_regmap_init_spi(spi, &at86rf230_regmap_spi_config);
 	if (IS_ERR(lp->regmap)) {
@@ -1564,14 +1564,14 @@ static int at86rf230_probe(struct spi_device *spi)
 	if (rc)
 		goto free_dev;
 
-	rc = ieee802154_register_device(lp->dev);
+	rc = ieee802154_register_hw(lp->hw);
 	if (rc)
 		goto free_dev;
 
 	return rc;
 
 free_dev:
-	ieee802154_free_device(lp->dev);
+	ieee802154_free_hw(lp->hw);
 
 	return rc;
 }
@@ -1582,8 +1582,8 @@ static int at86rf230_remove(struct spi_device *spi)
 
 	/* mask all at86rf230 irq's */
 	at86rf230_write_subreg(lp, SR_IRQ_MASK, 0);
-	ieee802154_unregister_device(lp->dev);
-	ieee802154_free_device(lp->dev);
+	ieee802154_unregister_hw(lp->hw);
+	ieee802154_free_hw(lp->hw);
 	dev_dbg(&spi->dev, "unregistered at86rf230\n");
 
 	return 0;
diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c
index 32b3c8862b4..b827e04d481 100644
--- a/drivers/net/ieee802154/cc2520.c
+++ b/drivers/net/ieee802154/cc2520.c
@@ -193,7 +193,7 @@
 /* Driver private information */
 struct cc2520_private {
 	struct spi_device *spi;		/* SPI device structure */
-	struct ieee802154_dev *dev;	/* IEEE-802.15.4 device */
+	struct ieee802154_hw *hw;	/* IEEE-802.15.4 device */
 	u8 *buf;			/* SPI TX/Rx data buffer */
 	struct mutex buffer_mutex;	/* SPI buffer mutex */
 	bool is_tx;			/* Flag for sync b/w Tx and Rx */
@@ -453,20 +453,20 @@ cc2520_read_rxfifo(struct cc2520_private *priv, u8 *data, u8 len, u8 *lqi)
 	return status;
 }
 
-static int cc2520_start(struct ieee802154_dev *dev)
+static int cc2520_start(struct ieee802154_hw *hw)
 {
-	return cc2520_cmd_strobe(dev->priv, CC2520_CMD_SRXON);
+	return cc2520_cmd_strobe(hw->priv, CC2520_CMD_SRXON);
 }
 
-static void cc2520_stop(struct ieee802154_dev *dev)
+static void cc2520_stop(struct ieee802154_hw *hw)
 {
-	cc2520_cmd_strobe(dev->priv, CC2520_CMD_SRFOFF);
+	cc2520_cmd_strobe(hw->priv, CC2520_CMD_SRFOFF);
 }
 
 static int
-cc2520_tx(struct ieee802154_dev *dev, struct sk_buff *skb)
+cc2520_tx(struct ieee802154_hw *hw, struct sk_buff *skb)
 {
-	struct cc2520_private *priv = dev->priv;
+	struct cc2520_private *priv = hw->priv;
 	unsigned long flags;
 	int rc;
 	u8 status = 0;
@@ -536,7 +536,7 @@ static int cc2520_rx(struct cc2520_private *priv)
 
 	skb_trim(skb, skb->len - 2);
 
-	ieee802154_rx_irqsafe(priv->dev, skb, lqi);
+	ieee802154_rx_irqsafe(priv->hw, skb, lqi);
 
 	dev_vdbg(&priv->spi->dev, "RXFIFO: %x %x\n", len, lqi);
 
@@ -544,9 +544,9 @@ static int cc2520_rx(struct cc2520_private *priv)
 }
 
 static int
-cc2520_ed(struct ieee802154_dev *dev, u8 *level)
+cc2520_ed(struct ieee802154_hw *hw, u8 *level)
 {
-	struct cc2520_private *priv = dev->priv;
+	struct cc2520_private *priv = hw->priv;
 	u8 status = 0xff;
 	u8 rssi;
 	int ret;
@@ -569,9 +569,9 @@ cc2520_ed(struct ieee802154_dev *dev, u8 *level)
 }
 
 static int
-cc2520_set_channel(struct ieee802154_dev *dev, int page, int channel)
+cc2520_set_channel(struct ieee802154_hw *hw, int page, int channel)
 {
-	struct cc2520_private *priv = dev->priv;
+	struct cc2520_private *priv = hw->priv;
 	int ret;
 
 	might_sleep();
@@ -588,10 +588,10 @@ cc2520_set_channel(struct ieee802154_dev *dev, int page, int channel)
 }
 
 static int
-cc2520_filter(struct ieee802154_dev *dev,
+cc2520_filter(struct ieee802154_hw *hw,
 	      struct ieee802154_hw_addr_filt *filt, unsigned long changed)
 {
-	struct cc2520_private *priv = dev->priv;
+	struct cc2520_private *priv = hw->priv;
 
 	if (changed & IEEE802154_AFILT_PANID_CHANGED) {
 		u16 panid = le16_to_cpu(filt->pan_id);
@@ -645,27 +645,27 @@ static int cc2520_register(struct cc2520_private *priv)
 {
 	int ret = -ENOMEM;
 
-	priv->dev = ieee802154_alloc_device(sizeof(*priv), &cc2520_ops);
-	if (!priv->dev)
+	priv->hw = ieee802154_alloc_hw(sizeof(*priv), &cc2520_ops);
+	if (!priv->hw)
 		goto err_ret;
 
-	priv->dev->priv = priv;
-	priv->dev->parent = &priv->spi->dev;
-	priv->dev->extra_tx_headroom = 0;
+	priv->hw->priv = priv;
+	priv->hw->parent = &priv->spi->dev;
+	priv->hw->extra_tx_headroom = 0;
 
 	/* We do support only 2.4 Ghz */
-	priv->dev->phy->channels_supported[0] = 0x7FFF800;
-	priv->dev->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK;
+	priv->hw->phy->channels_supported[0] = 0x7FFF800;
+	priv->hw->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK;
 
 	dev_vdbg(&priv->spi->dev, "registered cc2520\n");
-	ret = ieee802154_register_device(priv->dev);
+	ret = ieee802154_register_hw(priv->hw);
 	if (ret)
 		goto err_free_device;
 
 	return 0;
 
 err_free_device:
-	ieee802154_free_device(priv->dev);
+	ieee802154_free_hw(priv->hw);
 err_ret:
 	return ret;
 }
@@ -1002,8 +1002,8 @@ static int cc2520_remove(struct spi_device *spi)
 	mutex_destroy(&priv->buffer_mutex);
 	flush_work(&priv->fifop_irqwork);
 
-	ieee802154_unregister_device(priv->dev);
-	ieee802154_free_device(priv->dev);
+	ieee802154_unregister_hw(priv->hw);
+	ieee802154_free_hw(priv->hw);
 
 	return 0;
 }
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index e6e2993b7ec..51e3c589d2e 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -30,7 +30,7 @@
 static int numlbs = 1;
 
 struct fakelb_dev_priv {
-	struct ieee802154_dev *dev;
+	struct ieee802154_hw *hw;
 
 	struct list_head list;
 	struct fakelb_priv *fake;
@@ -45,7 +45,7 @@ struct fakelb_priv {
 };
 
 static int
-fakelb_hw_ed(struct ieee802154_dev *dev, u8 *level)
+fakelb_hw_ed(struct ieee802154_hw *hw, u8 *level)
 {
 	might_sleep();
 	BUG_ON(!level);
@@ -55,13 +55,13 @@ fakelb_hw_ed(struct ieee802154_dev *dev, u8 *level)
 }
 
 static int
-fakelb_hw_channel(struct ieee802154_dev *dev, int page, int channel)
+fakelb_hw_channel(struct ieee802154_hw *hw, int page, int channel)
 {
 	pr_debug("set channel to %d\n", channel);
 
 	might_sleep();
-	dev->phy->current_page = page;
-	dev->phy->current_channel = channel;
+	hw->phy->current_page = page;
+	hw->phy->current_channel = channel;
 
 	return 0;
 }
@@ -74,15 +74,15 @@ fakelb_hw_deliver(struct fakelb_dev_priv *priv, struct sk_buff *skb)
 	spin_lock(&priv->lock);
 	if (priv->working) {
 		newskb = pskb_copy(skb, GFP_ATOMIC);
-		ieee802154_rx_irqsafe(priv->dev, newskb, 0xcc);
+		ieee802154_rx_irqsafe(priv->hw, newskb, 0xcc);
 	}
 	spin_unlock(&priv->lock);
 }
 
 static int
-fakelb_hw_xmit(struct ieee802154_dev *dev, struct sk_buff *skb)
+fakelb_hw_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
 {
-	struct fakelb_dev_priv *priv = dev->priv;
+	struct fakelb_dev_priv *priv = hw->priv;
 	struct fakelb_priv *fake = priv->fake;
 
 	might_sleep();
@@ -95,8 +95,8 @@ fakelb_hw_xmit(struct ieee802154_dev *dev, struct sk_buff *skb)
 		struct fakelb_dev_priv *dp;
 		list_for_each_entry(dp, &priv->fake->list, list) {
 			if (dp != priv &&
-			    (dp->dev->phy->current_channel ==
-			     priv->dev->phy->current_channel))
+			    (dp->hw->phy->current_channel ==
+			     priv->hw->phy->current_channel))
 				fakelb_hw_deliver(dp, skb);
 		}
 	}
@@ -106,8 +106,8 @@ fakelb_hw_xmit(struct ieee802154_dev *dev, struct sk_buff *skb)
 }
 
 static int
-fakelb_hw_start(struct ieee802154_dev *dev) {
-	struct fakelb_dev_priv *priv = dev->priv;
+fakelb_hw_start(struct ieee802154_hw *hw) {
+	struct fakelb_dev_priv *priv = hw->priv;
 	int ret = 0;
 
 	spin_lock(&priv->lock);
@@ -121,8 +121,8 @@ fakelb_hw_start(struct ieee802154_dev *dev) {
 }
 
 static void
-fakelb_hw_stop(struct ieee802154_dev *dev) {
-	struct fakelb_dev_priv *priv = dev->priv;
+fakelb_hw_stop(struct ieee802154_hw *hw) {
+	struct fakelb_dev_priv *priv = hw->priv;
 
 	spin_lock(&priv->lock);
 	priv->working = 0;
@@ -146,54 +146,54 @@ static int fakelb_add_one(struct device *dev, struct fakelb_priv *fake)
 {
 	struct fakelb_dev_priv *priv;
 	int err;
-	struct ieee802154_dev *ieee;
+	struct ieee802154_hw *hw;
 
-	ieee = ieee802154_alloc_device(sizeof(*priv), &fakelb_ops);
-	if (!ieee)
+	hw = ieee802154_alloc_hw(sizeof(*priv), &fakelb_ops);
+	if (!hw)
 		return -ENOMEM;
 
-	priv = ieee->priv;
-	priv->dev = ieee;
+	priv = hw->priv;
+	priv->hw = hw;
 
 	/* 868 MHz BPSK	802.15.4-2003 */
-	ieee->phy->channels_supported[0] |= 1;
+	hw->phy->channels_supported[0] |= 1;
 	/* 915 MHz BPSK	802.15.4-2003 */
-	ieee->phy->channels_supported[0] |= 0x7fe;
+	hw->phy->channels_supported[0] |= 0x7fe;
 	/* 2.4 GHz O-QPSK 802.15.4-2003 */
-	ieee->phy->channels_supported[0] |= 0x7FFF800;
+	hw->phy->channels_supported[0] |= 0x7FFF800;
 	/* 868 MHz ASK 802.15.4-2006 */
-	ieee->phy->channels_supported[1] |= 1;
+	hw->phy->channels_supported[1] |= 1;
 	/* 915 MHz ASK 802.15.4-2006 */
-	ieee->phy->channels_supported[1] |= 0x7fe;
+	hw->phy->channels_supported[1] |= 0x7fe;
 	/* 868 MHz O-QPSK 802.15.4-2006 */
-	ieee->phy->channels_supported[2] |= 1;
+	hw->phy->channels_supported[2] |= 1;
 	/* 915 MHz O-QPSK 802.15.4-2006 */
-	ieee->phy->channels_supported[2] |= 0x7fe;
+	hw->phy->channels_supported[2] |= 0x7fe;
 	/* 2.4 GHz CSS 802.15.4a-2007 */
-	ieee->phy->channels_supported[3] |= 0x3fff;
+	hw->phy->channels_supported[3] |= 0x3fff;
 	/* UWB Sub-gigahertz 802.15.4a-2007 */
-	ieee->phy->channels_supported[4] |= 1;
+	hw->phy->channels_supported[4] |= 1;
 	/* UWB Low band 802.15.4a-2007 */
-	ieee->phy->channels_supported[4] |= 0x1e;
+	hw->phy->channels_supported[4] |= 0x1e;
 	/* UWB High band 802.15.4a-2007 */
-	ieee->phy->channels_supported[4] |= 0xffe0;
+	hw->phy->channels_supported[4] |= 0xffe0;
 	/* 750 MHz O-QPSK 802.15.4c-2009 */
-	ieee->phy->channels_supported[5] |= 0xf;
+	hw->phy->channels_supported[5] |= 0xf;
 	/* 750 MHz MPSK 802.15.4c-2009 */
-	ieee->phy->channels_supported[5] |= 0xf0;
+	hw->phy->channels_supported[5] |= 0xf0;
 	/* 950 MHz BPSK 802.15.4d-2009 */
-	ieee->phy->channels_supported[6] |= 0x3ff;
+	hw->phy->channels_supported[6] |= 0x3ff;
 	/* 950 MHz GFSK 802.15.4d-2009 */
-	ieee->phy->channels_supported[6] |= 0x3ffc00;
+	hw->phy->channels_supported[6] |= 0x3ffc00;
 
 	INIT_LIST_HEAD(&priv->list);
 	priv->fake = fake;
 
 	spin_lock_init(&priv->lock);
 
-	ieee->parent = dev;
+	hw->parent = dev;
 
-	err = ieee802154_register_device(ieee);
+	err = ieee802154_register_hw(hw);
 	if (err)
 		goto err_reg;
 
@@ -204,7 +204,7 @@ static int fakelb_add_one(struct device *dev, struct fakelb_priv *fake)
 	return 0;
 
 err_reg:
-	ieee802154_free_device(priv->dev);
+	ieee802154_free_hw(priv->hw);
 	return err;
 }
 
@@ -214,8 +214,8 @@ static void fakelb_del(struct fakelb_dev_priv *priv)
 	list_del(&priv->list);
 	write_unlock_bh(&priv->fake->lock);
 
-	ieee802154_unregister_device(priv->dev);
-	ieee802154_free_device(priv->dev);
+	ieee802154_unregister_hw(priv->hw);
+	ieee802154_free_hw(priv->hw);
 }
 
 static int fakelb_probe(struct platform_device *pdev)
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index 56a69599ac3..2e267c5c44d 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -79,7 +79,7 @@ enum mrf24j40_modules { MRF24J40, MRF24J40MA, MRF24J40MC };
 /* Device Private Data */
 struct mrf24j40 {
 	struct spi_device *spi;
-	struct ieee802154_dev *dev;
+	struct ieee802154_hw *hw;
 
 	struct mutex buffer_mutex; /* only used to protect buf */
 	struct completion tx_complete;
@@ -332,9 +332,9 @@ out:
 	return ret;
 }
 
-static int mrf24j40_tx(struct ieee802154_dev *dev, struct sk_buff *skb)
+static int mrf24j40_tx(struct ieee802154_hw *hw, struct sk_buff *skb)
 {
-	struct mrf24j40 *devrec = dev->priv;
+	struct mrf24j40 *devrec = hw->priv;
 	u8 val;
 	int ret = 0;
 
@@ -383,7 +383,7 @@ err:
 	return ret;
 }
 
-static int mrf24j40_ed(struct ieee802154_dev *dev, u8 *level)
+static int mrf24j40_ed(struct ieee802154_hw *hw, u8 *level)
 {
 	/* TODO: */
 	pr_warn("mrf24j40: ed not implemented\n");
@@ -391,9 +391,9 @@ static int mrf24j40_ed(struct ieee802154_dev *dev, u8 *level)
 	return 0;
 }
 
-static int mrf24j40_start(struct ieee802154_dev *dev)
+static int mrf24j40_start(struct ieee802154_hw *hw)
 {
-	struct mrf24j40 *devrec = dev->priv;
+	struct mrf24j40 *devrec = hw->priv;
 	u8 val;
 	int ret;
 
@@ -408,9 +408,9 @@ static int mrf24j40_start(struct ieee802154_dev *dev)
 	return 0;
 }
 
-static void mrf24j40_stop(struct ieee802154_dev *dev)
+static void mrf24j40_stop(struct ieee802154_hw *hw)
 {
-	struct mrf24j40 *devrec = dev->priv;
+	struct mrf24j40 *devrec = hw->priv;
 	u8 val;
 	int ret;
 
@@ -423,10 +423,10 @@ static void mrf24j40_stop(struct ieee802154_dev *dev)
 	write_short_reg(devrec, REG_INTCON, val);
 }
 
-static int mrf24j40_set_channel(struct ieee802154_dev *dev,
+static int mrf24j40_set_channel(struct ieee802154_hw *hw,
 				int page, int channel)
 {
-	struct mrf24j40 *devrec = dev->priv;
+	struct mrf24j40 *devrec = hw->priv;
 	u8 val;
 	int ret;
 
@@ -454,11 +454,11 @@ static int mrf24j40_set_channel(struct ieee802154_dev *dev,
 	return 0;
 }
 
-static int mrf24j40_filter(struct ieee802154_dev *dev,
+static int mrf24j40_filter(struct ieee802154_hw *hw,
 			   struct ieee802154_hw_addr_filt *filt,
 			   unsigned long changed)
 {
-	struct mrf24j40 *devrec = dev->priv;
+	struct mrf24j40 *devrec = hw->priv;
 
 	dev_dbg(printdev(devrec), "filter\n");
 
@@ -564,7 +564,7 @@ static int mrf24j40_handle_rx(struct mrf24j40 *devrec)
 	/* TODO: Other drivers call ieee20154_rx_irqsafe() here (eg: cc2040,
 	 * also from a workqueue).  I think irqsafe is not necessary here.
 	 * Can someone confirm? */
-	ieee802154_rx_irqsafe(devrec->dev, skb, lqi);
+	ieee802154_rx_irqsafe(devrec->hw, skb, lqi);
 
 	dev_dbg(printdev(devrec), "RX Handled\n");
 
@@ -745,17 +745,17 @@ static int mrf24j40_probe(struct spi_device *spi)
 
 	/* Register with the 802154 subsystem */
 
-	devrec->dev = ieee802154_alloc_device(0, &mrf24j40_ops);
-	if (!devrec->dev)
+	devrec->hw = ieee802154_alloc_hw(0, &mrf24j40_ops);
+	if (!devrec->hw)
 		goto err_ret;
 
-	devrec->dev->priv = devrec;
-	devrec->dev->parent = &devrec->spi->dev;
-	devrec->dev->phy->channels_supported[0] = CHANNEL_MASK;
-	devrec->dev->flags = IEEE802154_HW_OMIT_CKSUM|IEEE802154_HW_AACK;
+	devrec->hw->priv = devrec;
+	devrec->hw->parent = &devrec->spi->dev;
+	devrec->hw->phy->channels_supported[0] = CHANNEL_MASK;
+	devrec->hw->flags = IEEE802154_HW_OMIT_CKSUM|IEEE802154_HW_AACK;
 
 	dev_dbg(printdev(devrec), "registered mrf24j40\n");
-	ret = ieee802154_register_device(devrec->dev);
+	ret = ieee802154_register_hw(devrec->hw);
 	if (ret)
 		goto err_register_device;
 
@@ -780,9 +780,9 @@ static int mrf24j40_probe(struct spi_device *spi)
 
 err_irq:
 err_hw_init:
-	ieee802154_unregister_device(devrec->dev);
+	ieee802154_unregister_hw(devrec->hw);
 err_register_device:
-	ieee802154_free_device(devrec->dev);
+	ieee802154_free_hw(devrec->hw);
 err_ret:
 	return ret;
 }
@@ -793,8 +793,8 @@ static int mrf24j40_remove(struct spi_device *spi)
 
 	dev_dbg(printdev(devrec), "remove\n");
 
-	ieee802154_unregister_device(devrec->dev);
-	ieee802154_free_device(devrec->dev);
+	ieee802154_unregister_hw(devrec->hw);
+	ieee802154_free_hw(devrec->hw);
 	/* TODO: Will ieee802154_free_device() wait until ->xmit() is
 	 * complete? */
 
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 70351de3a72..eb0e1cb9ca9 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -52,7 +52,7 @@ struct ieee802154_hw_addr_filt {
 	u8	pan_coord;
 };
 
-struct ieee802154_dev {
+struct ieee802154_hw {
 	/* filled by the driver */
 	int	extra_tx_headroom;
 	u32	flags;
@@ -159,37 +159,37 @@ struct ieee802154_dev {
  */
 struct ieee802154_ops {
 	struct module	*owner;
-	int		(*start)(struct ieee802154_dev *dev);
-	void		(*stop)(struct ieee802154_dev *dev);
-	int		(*xmit)(struct ieee802154_dev *dev,
+	int		(*start)(struct ieee802154_hw *hw);
+	void		(*stop)(struct ieee802154_hw *hw);
+	int		(*xmit)(struct ieee802154_hw *hw,
 				struct sk_buff *skb);
-	int		(*ed)(struct ieee802154_dev *dev, u8 *level);
-	int		(*set_channel)(struct ieee802154_dev *dev,
+	int		(*ed)(struct ieee802154_hw *hw, u8 *level);
+	int		(*set_channel)(struct ieee802154_hw *hw,
 				       int page,
 				       int channel);
-	int		(*set_hw_addr_filt)(struct ieee802154_dev *dev,
-					  struct ieee802154_hw_addr_filt *filt,
+	int		(*set_hw_addr_filt)(struct ieee802154_hw *hw,
+					    struct ieee802154_hw_addr_filt *filt,
 					    unsigned long changed);
-	int		(*ieee_addr)(struct ieee802154_dev *dev, __le64 addr);
-	int		(*set_txpower)(struct ieee802154_dev *dev, int db);
-	int		(*set_lbt)(struct ieee802154_dev *dev, bool on);
-	int		(*set_cca_mode)(struct ieee802154_dev *dev, u8 mode);
-	int		(*set_cca_ed_level)(struct ieee802154_dev *dev,
+	int		(*ieee_addr)(struct ieee802154_hw *hw, __le64 addr);
+	int		(*set_txpower)(struct ieee802154_hw *hw, int db);
+	int		(*set_lbt)(struct ieee802154_hw *hw, bool on);
+	int		(*set_cca_mode)(struct ieee802154_hw *hw, u8 mode);
+	int		(*set_cca_ed_level)(struct ieee802154_hw *hw,
 					    s32 level);
-	int		(*set_csma_params)(struct ieee802154_dev *dev,
+	int		(*set_csma_params)(struct ieee802154_hw *hw,
 					   u8 min_be, u8 max_be, u8 retries);
-	int		(*set_frame_retries)(struct ieee802154_dev *dev,
+	int		(*set_frame_retries)(struct ieee802154_hw *hw,
 					     s8 retries);
 };
 
-/* Basic interface to register ieee802154 device */
-struct ieee802154_dev *
-ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops);
-void ieee802154_free_device(struct ieee802154_dev *dev);
-int ieee802154_register_device(struct ieee802154_dev *dev);
-void ieee802154_unregister_device(struct ieee802154_dev *dev);
+/* Basic interface to register ieee802154 hwice */
+struct ieee802154_hw *
+ieee802154_alloc_hw(size_t priv_data_len, struct ieee802154_ops *ops);
+void ieee802154_free_hw(struct ieee802154_hw *hw);
+int ieee802154_register_hw(struct ieee802154_hw *hw);
+void ieee802154_unregister_hw(struct ieee802154_hw *hw);
 
-void ieee802154_rx_irqsafe(struct ieee802154_dev *dev, struct sk_buff *skb,
+void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb,
 			   u8 lqi);
 
 #endif /* NET_MAC802154_H */
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index 970b621fc50..0cb98e87645 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -27,7 +27,7 @@
 
 /* mac802154 device private data */
 struct mac802154_priv {
-	struct ieee802154_dev hw;
+	struct ieee802154_hw hw;
 	struct ieee802154_ops *ops;
 
 	/* ieee802154 phy */
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 9798c741739..b0bcc063e9a 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -235,8 +235,8 @@ static int mac802154_set_frame_retries(struct wpan_phy *phy, s8 retries)
 	return priv->ops->set_frame_retries(&priv->hw, retries);
 }
 
-struct ieee802154_dev *
-ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops)
+struct ieee802154_hw *
+ieee802154_alloc_hw(size_t priv_data_len, struct ieee802154_ops *ops)
 {
 	struct wpan_phy *phy;
 	struct mac802154_priv *priv;
@@ -285,9 +285,9 @@ ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops)
 
 	return &priv->hw;
 }
-EXPORT_SYMBOL(ieee802154_alloc_device);
+EXPORT_SYMBOL(ieee802154_alloc_hw);
 
-void ieee802154_free_device(struct ieee802154_dev *hw)
+void ieee802154_free_hw(struct ieee802154_hw *hw)
 {
 	struct mac802154_priv *priv = mac802154_to_priv(hw);
 
@@ -297,49 +297,49 @@ void ieee802154_free_device(struct ieee802154_dev *hw)
 
 	wpan_phy_free(priv->phy);
 }
-EXPORT_SYMBOL(ieee802154_free_device);
+EXPORT_SYMBOL(ieee802154_free_hw);
 
-int ieee802154_register_device(struct ieee802154_dev *dev)
+int ieee802154_register_hw(struct ieee802154_hw *hw)
 {
-	struct mac802154_priv *priv = mac802154_to_priv(dev);
+	struct mac802154_priv *priv = mac802154_to_priv(hw);
 	int rc = -ENOSYS;
 
-	if (dev->flags & IEEE802154_HW_TXPOWER) {
+	if (hw->flags & IEEE802154_HW_TXPOWER) {
 		if (!priv->ops->set_txpower)
 			goto out;
 
 		priv->phy->set_txpower = mac802154_set_txpower;
 	}
 
-	if (dev->flags & IEEE802154_HW_LBT) {
+	if (hw->flags & IEEE802154_HW_LBT) {
 		if (!priv->ops->set_lbt)
 			goto out;
 
 		priv->phy->set_lbt = mac802154_set_lbt;
 	}
 
-	if (dev->flags & IEEE802154_HW_CCA_MODE) {
+	if (hw->flags & IEEE802154_HW_CCA_MODE) {
 		if (!priv->ops->set_cca_mode)
 			goto out;
 
 		priv->phy->set_cca_mode = mac802154_set_cca_mode;
 	}
 
-	if (dev->flags & IEEE802154_HW_CCA_ED_LEVEL) {
+	if (hw->flags & IEEE802154_HW_CCA_ED_LEVEL) {
 		if (!priv->ops->set_cca_ed_level)
 			goto out;
 
 		priv->phy->set_cca_ed_level = mac802154_set_cca_ed_level;
 	}
 
-	if (dev->flags & IEEE802154_HW_CSMA_PARAMS) {
+	if (hw->flags & IEEE802154_HW_CSMA_PARAMS) {
 		if (!priv->ops->set_csma_params)
 			goto out;
 
 		priv->phy->set_csma_params = mac802154_set_csma_params;
 	}
 
-	if (dev->flags & IEEE802154_HW_FRAME_RETRIES) {
+	if (hw->flags & IEEE802154_HW_FRAME_RETRIES) {
 		if (!priv->ops->set_frame_retries)
 			goto out;
 
@@ -377,11 +377,11 @@ out_wq:
 out:
 	return rc;
 }
-EXPORT_SYMBOL(ieee802154_register_device);
+EXPORT_SYMBOL(ieee802154_register_hw);
 
-void ieee802154_unregister_device(struct ieee802154_dev *dev)
+void ieee802154_unregister_hw(struct ieee802154_hw *hw)
 {
-	struct mac802154_priv *priv = mac802154_to_priv(dev);
+	struct mac802154_priv *priv = mac802154_to_priv(hw);
 	struct mac802154_sub_if_data *sdata, *next;
 
 	flush_workqueue(priv->dev_workqueue);
@@ -405,7 +405,7 @@ void ieee802154_unregister_device(struct ieee802154_dev *dev)
 
 	wpan_phy_unregister(priv->phy);
 }
-EXPORT_SYMBOL(ieee802154_unregister_device);
+EXPORT_SYMBOL(ieee802154_unregister_hw);
 
 MODULE_DESCRIPTION("IEEE 802.15.4 implementation");
 MODULE_LICENSE("GPL v2");
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index bc6cffd51f9..62b5c7dfe7f 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -42,12 +42,12 @@
 struct rx_work {
 	struct sk_buff *skb;
 	struct work_struct work;
-	struct ieee802154_dev *dev;
+	struct ieee802154_hw *hw;
 	u8 lqi;
 };
 
 static void
-mac802154_subif_rx(struct ieee802154_dev *hw, struct sk_buff *skb, u8 lqi)
+mac802154_subif_rx(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi)
 {
 	struct mac802154_priv *priv = mac802154_to_priv(hw);
 
@@ -83,14 +83,14 @@ static void mac802154_rx_worker(struct work_struct *work)
 {
 	struct rx_work *rw = container_of(work, struct rx_work, work);
 
-	mac802154_subif_rx(rw->dev, rw->skb, rw->lqi);
+	mac802154_subif_rx(rw->hw, rw->skb, rw->lqi);
 	kfree(rw);
 }
 
 void
-ieee802154_rx_irqsafe(struct ieee802154_dev *dev, struct sk_buff *skb, u8 lqi)
+ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi)
 {
-	struct mac802154_priv *priv = mac802154_to_priv(dev);
+	struct mac802154_priv *priv = mac802154_to_priv(hw);
 	struct rx_work *work;
 
 	if (!skb)
@@ -102,7 +102,7 @@ ieee802154_rx_irqsafe(struct ieee802154_dev *dev, struct sk_buff *skb, u8 lqi)
 
 	INIT_WORK(&work->work, mac802154_rx_worker);
 	work->skb = skb;
-	work->dev = dev;
+	work->hw = hw;
 	work->lqi = lqi;
 
 	queue_work(priv->dev_workqueue, &work->work);
-- 
cgit v1.2.3-70-g09d2


From c6f635faf3bca66cf73f6b3319a054959e367b19 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sat, 25 Oct 2014 17:16:42 +0200
Subject: mac802154: remove ieee802154_addr from driver_ops

This driver_ops callback function is never used by any driver.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/mac802154.h |  1 -
 net/mac802154/main.c    | 10 ----------
 2 files changed, 11 deletions(-)

(limited to 'include')

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index eb0e1cb9ca9..b07d431c0b1 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -170,7 +170,6 @@ struct ieee802154_ops {
 	int		(*set_hw_addr_filt)(struct ieee802154_hw *hw,
 					    struct ieee802154_hw_addr_filt *filt,
 					    unsigned long changed);
-	int		(*ieee_addr)(struct ieee802154_hw *hw, __le64 addr);
 	int		(*set_txpower)(struct ieee802154_hw *hw, int db);
 	int		(*set_lbt)(struct ieee802154_hw *hw, bool on);
 	int		(*set_cca_mode)(struct ieee802154_hw *hw, u8 mode);
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 5ce3184bc67..0e9a6a203f7 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -61,16 +61,6 @@ int mac802154_slave_open(struct net_device *dev)
 			goto err;
 	}
 
-	if (local->ops->ieee_addr) {
-		__le64 addr = ieee802154_devaddr_from_raw(dev->dev_addr);
-
-		res = local->ops->ieee_addr(&local->hw, addr);
-		WARN_ON(res);
-		if (res)
-			goto err;
-		mac802154_dev_set_ieee_addr(dev);
-	}
-
 	netif_start_queue(dev);
 	return 0;
 err:
-- 
cgit v1.2.3-70-g09d2


From dc67c6b30f36d57b70b70547a30e7a8432540c6f Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 26 Oct 2014 09:37:04 +0100
Subject: mac802154: tx: remove xmit channel context switch

This patch removes the channel hopping feature before xmit. There are
several issues to provide a real channel hopping (timing requirements,
etc...).

We don't have any known kernelspace protocol which really use this
feature. And I don't know an real user of this feature.
We simply drop this feature now.

This patch removes also the hold of pib lock which isn't needed by any
real driver xmit callback implementation.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/mac802154.h |  3 +--
 net/mac802154/tx.c      | 58 ++++---------------------------------------------
 2 files changed, 5 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index b07d431c0b1..ba8ddff70bb 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -113,8 +113,7 @@ struct ieee802154_hw {
  *	  skb cntains the buffer starting from the IEEE 802.15.4 header.
  *	  The low-level driver should send the frame based on available
  *	  configuration.
- *	  This function should return zero or negative errno. Called with
- *	  pib_lock held.
+ *	  This function should return zero or negative errno.
  *
  * ed:    Handler that 802.15.4 module calls for Energy Detection.
  *	  This function should place the value for detected energy
diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c
index d0ceb46134d..be8deae1938 100644
--- a/net/mac802154/tx.c
+++ b/net/mac802154/tx.c
@@ -34,8 +34,6 @@ struct wpan_xmit_cb {
 	struct sk_buff *skb;
 	struct work_struct work;
 	struct ieee802154_local *local;
-	u8 chan;
-	u8 page;
 };
 
 static inline struct wpan_xmit_cb *wpan_xmit_cb(const struct sk_buff *skb)
@@ -53,26 +51,10 @@ static void mac802154_xmit_worker(struct work_struct *work)
 	struct sk_buff *skb = cb->skb;
 	int res;
 
-	mutex_lock(&local->phy->pib_lock);
-	if (local->phy->current_channel != cb->chan ||
-	    local->phy->current_page != cb->page) {
-		res = local->ops->set_channel(&local->hw, cb->page, cb->chan);
-		if (res) {
-			pr_debug("set_channel failed\n");
-			goto out;
-		}
-
-		local->phy->current_channel = cb->chan;
-		local->phy->current_page = cb->page;
-	}
-
 	res = local->ops->xmit(&local->hw, skb);
 	if (res)
 		pr_debug("transmission failed\n");
 
-out:
-	mutex_unlock(&local->phy->pib_lock);
-
 	/* Restart the netif queue on each sub_if_data object. */
 	rcu_read_lock();
 	list_for_each_entry_rcu(sdata, &local->interfaces, list)
@@ -82,17 +64,12 @@ out:
 	dev_kfree_skb(skb);
 }
 
-static netdev_tx_t mac802154_tx(struct ieee802154_local *local,
-				struct sk_buff *skb, u8 page, u8 chan)
+static netdev_tx_t
+mac802154_tx(struct ieee802154_local *local, struct sk_buff *skb)
 {
 	struct ieee802154_sub_if_data *sdata;
 	struct wpan_xmit_cb *cb = wpan_xmit_cb(skb);
 
-	if (!(local->phy->channels_supported[page] & (1 << chan))) {
-		WARN_ON(1);
-		goto err_tx;
-	}
-
 	mac802154_monitors_rx(local, skb);
 
 	if (!(local->hw.flags & IEEE802154_HW_OMIT_CKSUM)) {
@@ -115,8 +92,6 @@ static netdev_tx_t mac802154_tx(struct ieee802154_local *local,
 	INIT_WORK(&cb->work, mac802154_xmit_worker);
 	cb->skb = skb;
 	cb->local = local;
-	cb->page = page;
-	cb->chan = chan;
 
 	queue_work(local->workqueue, &cb->work);
 
@@ -130,44 +105,19 @@ err_tx:
 netdev_tx_t mac802154_monitor_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
-	u8 chan, page;
-
-	/* FIXME: locking */
-	chan = sdata->local->phy->current_channel;
-	page = sdata->local->phy->current_page;
-
-	if (chan == MAC802154_CHAN_NONE) /* not initialized */
-		return NETDEV_TX_OK;
-
-	if (WARN_ON(page >= WPAN_NUM_PAGES) ||
-	    WARN_ON(chan >= WPAN_NUM_CHANNELS))
-		return NETDEV_TX_OK;
 
 	skb->skb_iif = dev->ifindex;
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
 
-	return mac802154_tx(sdata->local, skb, page, chan);
+	return mac802154_tx(sdata->local, skb);
 }
 
 netdev_tx_t mac802154_wpan_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
-	u8 chan, page;
 	int rc;
 
-	spin_lock_bh(&sdata->mib_lock);
-	chan = sdata->chan;
-	page = sdata->page;
-	spin_unlock_bh(&sdata->mib_lock);
-
-	if (chan == MAC802154_CHAN_NONE ||
-	    page >= WPAN_NUM_PAGES ||
-	    chan >= WPAN_NUM_CHANNELS) {
-		kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-
 	rc = mac802154_llsec_encrypt(&sdata->sec, skb);
 	if (rc) {
 		pr_warn("encryption failed: %i\n", rc);
@@ -179,5 +129,5 @@ netdev_tx_t mac802154_wpan_xmit(struct sk_buff *skb, struct net_device *dev)
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
 
-	return mac802154_tx(sdata->local, skb, page, chan);
+	return mac802154_tx(sdata->local, skb);
 }
-- 
cgit v1.2.3-70-g09d2


From c20851035126cc1d97c337083f98b797eed155a3 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 26 Oct 2014 09:37:05 +0100
Subject: mac802154: add netdev qeue helpers

This patch adds a new file net/mac802154/util.c which contains utility
functions for drivers, etc. This file contains functions to start and
stop queues for all virtual interfaces, this is useful for asynchronous
handling by driver level.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/mac802154.h |  4 ++++
 net/mac802154/Makefile  |  2 +-
 net/mac802154/util.c    | 55 +++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 60 insertions(+), 1 deletion(-)
 create mode 100644 net/mac802154/util.c

(limited to 'include')

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index ba8ddff70bb..29af5c346eb 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -190,4 +190,8 @@ void ieee802154_unregister_hw(struct ieee802154_hw *hw);
 void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb,
 			   u8 lqi);
 
+void ieee802154_wake_queue(struct ieee802154_hw *hw);
+void ieee802154_stop_queue(struct ieee802154_hw *hw);
+void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb);
+
 #endif /* NET_MAC802154_H */
diff --git a/net/mac802154/Makefile b/net/mac802154/Makefile
index 203f42d511a..e68debaf2a5 100644
--- a/net/mac802154/Makefile
+++ b/net/mac802154/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_MAC802154)	+= mac802154.o
 mac802154-objs		:= main.o rx.o tx.o mac_cmd.o mib.o \
-			   monitor.o iface.o llsec.o
+			   monitor.o iface.o llsec.o util.o
 
 ccflags-y += -D__CHECK_ENDIAN__
diff --git a/net/mac802154/util.c b/net/mac802154/util.c
new file mode 100644
index 00000000000..117e4eff4ca
--- /dev/null
+++ b/net/mac802154/util.c
@@ -0,0 +1,55 @@
+/* This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Authors:
+ * Alexander Aring <aar@pengutronix.de>
+ *
+ * Based on: net/mac80211/util.c
+ */
+
+#include "ieee802154_i.h"
+
+void ieee802154_wake_queue(struct ieee802154_hw *hw)
+{
+	struct ieee802154_local *local = hw_to_local(hw);
+	struct ieee802154_sub_if_data *sdata;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+		if (!sdata->dev)
+			continue;
+
+		netif_wake_queue(sdata->dev);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(ieee802154_wake_queue);
+
+void ieee802154_stop_queue(struct ieee802154_hw *hw)
+{
+	struct ieee802154_local *local = hw_to_local(hw);
+	struct ieee802154_sub_if_data *sdata;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+		if (!sdata->dev)
+			continue;
+
+		netif_stop_queue(sdata->dev);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(ieee802154_stop_queue);
+
+void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb)
+{
+	ieee802154_wake_queue(hw);
+	consume_skb(skb);
+}
+EXPORT_SYMBOL(ieee802154_xmit_complete);
-- 
cgit v1.2.3-70-g09d2


From ed0a5dce0c29f30ee53a87793206156cf38ae70d Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 26 Oct 2014 09:37:08 +0100
Subject: mac802154: tx: add support for xmit_async callback

This patch renames the existsing xmit callback to xmit_sync and
introduces an asynchronous xmit_async function. If ieee802154_ops
doesn't provide the xmit_async callback, then we have a fallback to
the xmit_sync callback.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Cc: Alan Ott <alan@signal11.us>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/net/ieee802154/at86rf230.c |  2 +-
 drivers/net/ieee802154/cc2520.c    |  2 +-
 drivers/net/ieee802154/fakelb.c    |  2 +-
 drivers/net/ieee802154/mrf24j40.c  |  2 +-
 include/net/mac802154.h            | 17 ++++++++++++++---
 net/mac802154/main.c               |  4 ++--
 net/mac802154/tx.c                 | 20 +++++++++++++++-----
 7 files changed, 35 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index b0d68d7061c..06a3e9013d6 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -1237,7 +1237,7 @@ at86rf230_set_frame_retries(struct ieee802154_hw *hw, s8 retries)
 
 static struct ieee802154_ops at86rf230_ops = {
 	.owner = THIS_MODULE,
-	.xmit = at86rf230_xmit,
+	.xmit_sync = at86rf230_xmit,
 	.ed = at86rf230_ed,
 	.set_channel = at86rf230_channel,
 	.start = at86rf230_start,
diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c
index b827e04d481..f6f07f4eb0e 100644
--- a/drivers/net/ieee802154/cc2520.c
+++ b/drivers/net/ieee802154/cc2520.c
@@ -635,7 +635,7 @@ static struct ieee802154_ops cc2520_ops = {
 	.owner = THIS_MODULE,
 	.start = cc2520_start,
 	.stop = cc2520_stop,
-	.xmit = cc2520_tx,
+	.xmit_sync = cc2520_tx,
 	.ed = cc2520_ed,
 	.set_channel = cc2520_set_channel,
 	.set_hw_addr_filt = cc2520_filter,
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index 51e3c589d2e..db0703f0fa4 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -131,7 +131,7 @@ fakelb_hw_stop(struct ieee802154_hw *hw) {
 
 static struct ieee802154_ops fakelb_ops = {
 	.owner = THIS_MODULE,
-	.xmit = fakelb_hw_xmit,
+	.xmit_sync = fakelb_hw_xmit,
 	.ed = fakelb_hw_ed,
 	.set_channel = fakelb_hw_channel,
 	.start = fakelb_hw_start,
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index 2e267c5c44d..3d775afa217 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -581,7 +581,7 @@ out:
 
 static struct ieee802154_ops mrf24j40_ops = {
 	.owner = THIS_MODULE,
-	.xmit = mrf24j40_tx,
+	.xmit_sync = mrf24j40_tx,
 	.ed = mrf24j40_ed,
 	.start = mrf24j40_start,
 	.stop = mrf24j40_stop,
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 29af5c346eb..57b120281af 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -109,7 +109,16 @@ struct ieee802154_hw {
  * stop:  Handler that 802.15.4 module calls for device cleanup.
  *	  This function is called after the last interface is removed.
  *
- * xmit:  Handler that 802.15.4 module calls for each transmitted frame.
+ * xmit_sync:
+ *	  Handler that 802.15.4 module calls for each transmitted frame.
+ *	  skb cntains the buffer starting from the IEEE 802.15.4 header.
+ *	  The low-level driver should send the frame based on available
+ *	  configuration. This is called by a workqueue and useful for
+ *	  synchronous 802.15.4 drivers.
+ *	  This function should return zero or negative errno.
+ *
+ * xmit_async:
+ *	  Handler that 802.15.4 module calls for each transmitted frame.
  *	  skb cntains the buffer starting from the IEEE 802.15.4 header.
  *	  The low-level driver should send the frame based on available
  *	  configuration.
@@ -160,8 +169,10 @@ struct ieee802154_ops {
 	struct module	*owner;
 	int		(*start)(struct ieee802154_hw *hw);
 	void		(*stop)(struct ieee802154_hw *hw);
-	int		(*xmit)(struct ieee802154_hw *hw,
-				struct sk_buff *skb);
+	int		(*xmit_sync)(struct ieee802154_hw *hw,
+				     struct sk_buff *skb);
+	int		(*xmit_async)(struct ieee802154_hw *hw,
+				      struct sk_buff *skb);
 	int		(*ed)(struct ieee802154_hw *hw, u8 *level);
 	int		(*set_channel)(struct ieee802154_hw *hw,
 				       int page,
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 0e9a6a203f7..3c0a824d24a 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -229,8 +229,8 @@ ieee802154_alloc_hw(size_t priv_data_len, struct ieee802154_ops *ops)
 	struct ieee802154_local *local;
 	size_t priv_size;
 
-	if (!ops || !ops->xmit || !ops->ed || !ops->start ||
-	    !ops->stop || !ops->set_channel) {
+	if (!ops || !(ops->xmit_async || ops->xmit_sync) || !ops->ed ||
+	    !ops->start || !ops->stop || !ops->set_channel) {
 		pr_err("undefined IEEE802.15.4 device operations\n");
 		return NULL;
 	}
diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c
index 23139cae076..1a4f6d91ab8 100644
--- a/net/mac802154/tx.c
+++ b/net/mac802154/tx.c
@@ -50,7 +50,7 @@ static void mac802154_xmit_worker(struct work_struct *work)
 	struct sk_buff *skb = cb->skb;
 	int res;
 
-	res = local->ops->xmit(&local->hw, skb);
+	res = local->ops->xmit_sync(&local->hw, skb);
 	if (res) {
 		pr_debug("transmission failed\n");
 		/* Restart the netif queue on each sub_if_data object. */
@@ -66,6 +66,7 @@ static netdev_tx_t
 mac802154_tx(struct ieee802154_local *local, struct sk_buff *skb)
 {
 	struct wpan_xmit_cb *cb = wpan_xmit_cb(skb);
+	int ret;
 
 	mac802154_monitors_rx(local, skb);
 
@@ -83,11 +84,20 @@ mac802154_tx(struct ieee802154_local *local, struct sk_buff *skb)
 	/* Stop the netif queue on each sub_if_data object. */
 	ieee802154_stop_queue(&local->hw);
 
-	INIT_WORK(&cb->work, mac802154_xmit_worker);
-	cb->skb = skb;
-	cb->local = local;
+	/* async is priority, otherwise sync is fallback */
+	if (local->ops->xmit_async) {
+		ret = local->ops->xmit_async(&local->hw, skb);
+		if (ret) {
+			ieee802154_wake_queue(&local->hw);
+			goto err_tx;
+		}
+	} else {
+		INIT_WORK(&cb->work, mac802154_xmit_worker);
+		cb->skb = skb;
+		cb->local = local;
 
-	queue_work(local->workqueue, &cb->work);
+		queue_work(local->workqueue, &cb->work);
+	}
 
 	return NETDEV_TX_OK;
 
-- 
cgit v1.2.3-70-g09d2


From 1e7283a271afcd45713f2813c97de300565a0dd7 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 26 Oct 2014 09:37:14 +0100
Subject: mac802154: tx: add comment at sync xmit callback

This patch adds a warning that xmit_sync callback is deprecated and
should be removed soon. The 802.15.4 subsystem will not accept synced
drivers anymore.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/mac802154.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 57b120281af..942dd53d465 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -117,6 +117,10 @@ struct ieee802154_hw {
  *	  synchronous 802.15.4 drivers.
  *	  This function should return zero or negative errno.
  *
+ *	  WARNING:
+ *	  This will be deprecated soon. We don't accept synced xmit callbacks
+ *	  drivers anymore.
+ *
  * xmit_async:
  *	  Handler that 802.15.4 module calls for each transmitted frame.
  *	  skb cntains the buffer starting from the IEEE 802.15.4 header.
-- 
cgit v1.2.3-70-g09d2


From 1998d90ad424c1ff12ea24816ce158d5262e06a5 Mon Sep 17 00:00:00 2001
From: Ben Greear <greearb@candelatech.com>
Date: Wed, 22 Oct 2014 12:23:00 -0700
Subject: cfg80211: support creating wiphy with suggested name

Kernel will attempt to use the name if it is supplied,
but if name cannot be used for some reason, the default
phyX name will be used instead.

Signed-off-by: Ben Greear <greearb@candelatech.com>
[while at it, use wiphy_name() instead of dev_name(),
 fix format string issue reported by Kees Cook]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 23 ++++++++++++++++++-
 net/wireless/core.c    | 60 +++++++++++++++++++++++++++++++++++++++++---------
 2 files changed, 71 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 77aa805d7e7..39d7996b060 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3184,6 +3184,23 @@ static inline const char *wiphy_name(const struct wiphy *wiphy)
 	return dev_name(&wiphy->dev);
 }
 
+/**
+ * wiphy_new_nm - create a new wiphy for use with cfg80211
+ *
+ * @ops: The configuration operations for this device
+ * @sizeof_priv: The size of the private area to allocate
+ * @requested_name: Request a particular name.
+ *	NULL is valid value, and means use the default phy%d naming.
+ *
+ * Create a new wiphy and associate the given operations with it.
+ * @sizeof_priv bytes are allocated for private use.
+ *
+ * Return: A pointer to the new wiphy. This pointer must be
+ * assigned to each netdev's ieee80211_ptr for proper operation.
+ */
+struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv,
+			   const char *requested_name);
+
 /**
  * wiphy_new - create a new wiphy for use with cfg80211
  *
@@ -3196,7 +3213,11 @@ static inline const char *wiphy_name(const struct wiphy *wiphy)
  * Return: A pointer to the new wiphy. This pointer must be
  * assigned to each netdev's ieee80211_ptr for proper operation.
  */
-struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv);
+static inline struct wiphy *wiphy_new(const struct cfg80211_ops *ops,
+				      int sizeof_priv)
+{
+	return wiphy_new_nm(ops, sizeof_priv, NULL);
+}
 
 /**
  * wiphy_register - register a wiphy with cfg80211
diff --git a/net/wireless/core.c b/net/wireless/core.c
index f52a4cd7017..87bb502bc8d 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -86,11 +86,11 @@ struct wiphy *wiphy_idx_to_wiphy(int wiphy_idx)
 	return &rdev->wiphy;
 }
 
-int cfg80211_dev_rename(struct cfg80211_registered_device *rdev,
-			char *newname)
+static int cfg80211_dev_check_name(struct cfg80211_registered_device *rdev,
+				   const char *newname)
 {
 	struct cfg80211_registered_device *rdev2;
-	int wiphy_idx, taken = -1, result, digits;
+	int wiphy_idx, taken = -1, digits;
 
 	ASSERT_RTNL();
 
@@ -109,15 +109,28 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev,
 			return -EINVAL;
 	}
 
+	/* Ensure another device does not already have this name. */
+	list_for_each_entry(rdev2, &cfg80211_rdev_list, list)
+		if (strcmp(newname, wiphy_name(&rdev2->wiphy)) == 0)
+			return -EINVAL;
+
+	return 0;
+}
+
+int cfg80211_dev_rename(struct cfg80211_registered_device *rdev,
+			char *newname)
+{
+	int result;
+
+	ASSERT_RTNL();
 
 	/* Ignore nop renames */
-	if (strcmp(newname, dev_name(&rdev->wiphy.dev)) == 0)
+	if (strcmp(newname, wiphy_name(&rdev->wiphy)) == 0)
 		return 0;
 
-	/* Ensure another device does not already have this name. */
-	list_for_each_entry(rdev2, &cfg80211_rdev_list, list)
-		if (strcmp(newname, dev_name(&rdev2->wiphy.dev)) == 0)
-			return -EINVAL;
+	result = cfg80211_dev_check_name(rdev, newname);
+	if (result < 0)
+		return result;
 
 	result = device_rename(&rdev->wiphy.dev, newname);
 	if (result)
@@ -309,7 +322,8 @@ static void cfg80211_destroy_iface_wk(struct work_struct *work)
 
 /* exported functions */
 
-struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
+struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv,
+			   const char *requested_name)
 {
 	static atomic_t wiphy_counter = ATOMIC_INIT(0);
 
@@ -346,7 +360,31 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
 	rdev->wiphy_idx--;
 
 	/* give it a proper name */
-	dev_set_name(&rdev->wiphy.dev, PHY_NAME "%d", rdev->wiphy_idx);
+	if (requested_name && requested_name[0]) {
+		int rv;
+
+		rtnl_lock();
+		rv = cfg80211_dev_check_name(rdev, requested_name);
+
+		if (rv < 0) {
+			rtnl_unlock();
+			goto use_default_name;
+		}
+
+		rv = dev_set_name(&rdev->wiphy.dev, "%s", requested_name);
+		rtnl_unlock();
+		if (rv)
+			goto use_default_name;
+	} else {
+use_default_name:
+		/* NOTE:  This is *probably* safe w/out holding rtnl because of
+		 * the restrictions on phy names.  Probably this call could
+		 * fail if some other part of the kernel (re)named a device
+		 * phyX.  But, might should add some locking and check return
+		 * value, and use a different name if this one exists?
+		 */
+		dev_set_name(&rdev->wiphy.dev, PHY_NAME "%d", rdev->wiphy_idx);
+	}
 
 	INIT_LIST_HEAD(&rdev->wdev_list);
 	INIT_LIST_HEAD(&rdev->beacon_registrations);
@@ -406,7 +444,7 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
 
 	return &rdev->wiphy;
 }
-EXPORT_SYMBOL(wiphy_new);
+EXPORT_SYMBOL(wiphy_new_nm);
 
 static int wiphy_verify_combinations(struct wiphy *wiphy)
 {
-- 
cgit v1.2.3-70-g09d2


From ad28757eef268e609677d0e3d8c0bdadde52a711 Mon Sep 17 00:00:00 2001
From: Ben Greear <greearb@candelatech.com>
Date: Wed, 22 Oct 2014 12:23:01 -0700
Subject: mac80211: allow creating wiphy devices with suggested name

Support creating wiphy devices with an optional name.
This will be used by hwsim to have better automated control
over virtual radio creation/deletion.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 28 ++++++++++++++++++++++++++--
 net/mac80211/main.c    |  9 +++++----
 2 files changed, 31 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 2b7426a90ff..bb50e8beec0 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3063,7 +3063,7 @@ struct ieee80211_ops {
 };
 
 /**
- * ieee80211_alloc_hw -  Allocate a new hardware device
+ * ieee80211_alloc_hw_nm - Allocate a new hardware device
  *
  * This must be called once for each hardware device. The returned pointer
  * must be used to refer to this device when calling other functions.
@@ -3073,11 +3073,35 @@ struct ieee80211_ops {
  *
  * @priv_data_len: length of private data
  * @ops: callbacks for this device
+ * @requested_name: Requested name for this device.
+ *	NULL is valid value, and means use the default naming (phy%d)
  *
  * Return: A pointer to the new hardware device, or %NULL on error.
  */
+struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
+					   const struct ieee80211_ops *ops,
+					   const char *requested_name);
+
+/**
+ * ieee80211_alloc_hw - Allocate a new hardware device
+ *
+ * This must be called once for each hardware device. The returned pointer
+ * must be used to refer to this device when calling other functions.
+ * mac80211 allocates a private data area for the driver pointed to by
+ * @priv in &struct ieee80211_hw, the size of this area is given as
+ * @priv_data_len.
+ *
+ * @priv_data_len: length of private data
+ * @ops: callbacks for this device
+ *
+ * Return: A pointer to the new hardware device, or %NULL on error.
+ */
+static inline
 struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
-					const struct ieee80211_ops *ops);
+					const struct ieee80211_ops *ops)
+{
+	return ieee80211_alloc_hw_nm(priv_data_len, ops, NULL);
+}
 
 /**
  * ieee80211_register_hw - Register hardware device
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 9e322dce64e..b189122d4b2 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -478,8 +478,9 @@ static const struct ieee80211_vht_cap mac80211_vht_capa_mod_mask = {
 	},
 };
 
-struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
-					const struct ieee80211_ops *ops)
+struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
+					   const struct ieee80211_ops *ops,
+					   const char *requested_name)
 {
 	struct ieee80211_local *local;
 	int priv_size, i;
@@ -519,7 +520,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 	 */
 	priv_size = ALIGN(sizeof(*local), NETDEV_ALIGN) + priv_data_len;
 
-	wiphy = wiphy_new(&mac80211_config_ops, priv_size);
+	wiphy = wiphy_new_nm(&mac80211_config_ops, priv_size, requested_name);
 
 	if (!wiphy)
 		return NULL;
@@ -649,7 +650,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 
 	return &local->hw;
 }
-EXPORT_SYMBOL(ieee80211_alloc_hw);
+EXPORT_SYMBOL(ieee80211_alloc_hw_nm);
 
 static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 {
-- 
cgit v1.2.3-70-g09d2


From e27513fbd030d8558cfa9250bd62b2baf19dc114 Mon Sep 17 00:00:00 2001
From: Ben Greear <greearb@candelatech.com>
Date: Wed, 22 Oct 2014 12:23:03 -0700
Subject: mac80211: support creating wiphy w/out creating wlanX

This will be helpful when using the mac80211_hwsim
wiphys and automated testing.  Let user create the
vifs as needed, and named as expected.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 7 ++++++-
 net/mac80211/main.c    | 3 ++-
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index bb50e8beec0..1614b2fc3bf 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1583,6 +1583,10 @@ struct ieee80211_tx_control {
  *	a virtual monitor interface when monitor interfaces are the only
  *	active interfaces.
  *
+ * @IEEE80211_HW_NO_AUTO_VIF: The driver would like for no wlanX to
+ *	be created.  It is expected user-space will create vifs as
+ *	desired (and thus have them named as desired).
+ *
  * @IEEE80211_HW_QUEUE_CONTROL: The driver wants to control per-interface
  *	queue mapping in order to use different queues (not just one per AC)
  *	for different virtual interfaces. See the doc section on HW queue
@@ -1629,7 +1633,8 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_SUPPORTS_DYNAMIC_PS		= 1<<12,
 	IEEE80211_HW_MFP_CAPABLE			= 1<<13,
 	IEEE80211_HW_WANT_MONITOR_VIF			= 1<<14,
-	/* free slots */
+	IEEE80211_HW_NO_AUTO_VIF			= 1<<15,
+	/* free slot */
 	IEEE80211_HW_SUPPORTS_UAPSD			= 1<<17,
 	IEEE80211_HW_REPORTS_TX_ACK_STATUS		= 1<<18,
 	IEEE80211_HW_CONNECTION_MONITOR			= 1<<19,
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index b189122d4b2..7d40e3f0a77 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1023,7 +1023,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	}
 
 	/* add one default STA interface if supported */
-	if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION)) {
+	if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) &&
+	    !(hw->flags & IEEE80211_HW_NO_AUTO_VIF)) {
 		result = ieee80211_if_add(local, "wlan%d", NULL,
 					  NL80211_IFTYPE_STATION, NULL);
 		if (result)
-- 
cgit v1.2.3-70-g09d2


From e8f479b11268af3f206d1580f6b0d572d6ecb4f7 Mon Sep 17 00:00:00 2001
From: Ben Greear <greearb@candelatech.com>
Date: Wed, 22 Oct 2014 12:23:05 -0700
Subject: cfg80211: support configuring vif mac addr on create

This is useful when creating virtual interfaces.
Keeps udev from mucking with things it shouldn't, since
the default MAC is never seen by udev when specified on
the cmd-line during creation.

Signed-off-by: Ben Greear <greearb@candelatech.com>
[check for feature flag in nl80211 to force drivers to set it]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 9 ++++++---
 include/uapi/linux/nl80211.h | 4 ++++
 net/wireless/nl80211.c       | 4 +++-
 3 files changed, 13 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 39d7996b060..f67948e1860 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -319,9 +319,12 @@ struct ieee80211_supported_band {
 /**
  * struct vif_params - describes virtual interface parameters
  * @use_4addr: use 4-address frames
- * @macaddr: address to use for this virtual interface. This will only
- * 	be used for non-netdevice interfaces. If this parameter is set
- * 	to zero address the driver may determine the address as needed.
+ * @macaddr: address to use for this virtual interface.
+ *	If this parameter is set to zero address the driver may
+ *	determine the address as needed.
+ *	This feature is only fully supported by drivers that enable the
+ *	%NL80211_FEATURE_MAC_ON_CREATE flag.  Others may support creating
+ **	only p2p devices with specified MAC.
  */
 struct vif_params {
        int use_4addr;
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index be1d5def304..f7daae59248 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -4056,6 +4056,9 @@ enum nl80211_ap_sme_features {
  *	TSPEC sessions (TID aka TSID 0-7) with the %NL80211_CMD_ADD_TX_TS
  *	command. Standard IEEE 802.11 TSPEC setup is not yet supported, it
  *	needs to be able to handle Block-Ack agreements and other things.
+ * @NL80211_FEATURE_MAC_ON_CREATE: Device supports configuring
+ *	the vif's MAC address upon creation.
+ *	See 'macaddr' field in the vif_params (cfg80211.h).
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -4085,6 +4088,7 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_STATIC_SMPS			= 1 << 24,
 	NL80211_FEATURE_DYNAMIC_SMPS			= 1 << 25,
 	NL80211_FEATURE_SUPPORTS_WMM_ADMISSION		= 1 << 26,
+	NL80211_FEATURE_MAC_ON_CREATE			= 1 << 27,
 };
 
 /**
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d98d4ea2781..12736a7cd50 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2605,7 +2605,9 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 	    !(rdev->wiphy.interface_modes & (1 << type)))
 		return -EOPNOTSUPP;
 
-	if (type == NL80211_IFTYPE_P2P_DEVICE && info->attrs[NL80211_ATTR_MAC]) {
+	if ((type == NL80211_IFTYPE_P2P_DEVICE ||
+	     rdev->wiphy.features & NL80211_FEATURE_MAC_ON_CREATE) &&
+	    info->attrs[NL80211_ATTR_MAC]) {
 		nla_memcpy(params.macaddr, info->attrs[NL80211_ATTR_MAC],
 			   ETH_ALEN);
 		if (!is_valid_ether_addr(params.macaddr))
-- 
cgit v1.2.3-70-g09d2


From 593befa6ab74a805e4f503c8c737c3cffa8066b6 Mon Sep 17 00:00:00 2001
From: Dominik Dingel <dingel@linux.vnet.ibm.com>
Date: Thu, 23 Oct 2014 12:07:44 +0200
Subject: mm: introduce mm_forbids_zeropage function

Add a new function stub to allow architectures to disable for
an mm_structthe backing of non-present, anonymous pages with
read-only empty zero pages.

Signed-off-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 include/linux/mm.h | 11 +++++++++++
 mm/huge_memory.c   |  2 +-
 mm/memory.c        |  2 +-
 3 files changed, 13 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 27eb1bfbe70..ab7dadca4ea 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -56,6 +56,17 @@ extern int sysctl_legacy_va_layout;
 #define __pa_symbol(x)  __pa(RELOC_HIDE((unsigned long)(x), 0))
 #endif
 
+/*
+ * To prevent common memory management code establishing
+ * a zero page mapping on a read fault.
+ * This macro should be defined within <asm/pgtable.h>.
+ * s390 does this to prevent multiplexing of hardware bits
+ * related to the physical page in case of virtualization.
+ */
+#ifndef mm_forbids_zeropage
+#define mm_forbids_zeropage(X)	(0)
+#endif
+
 extern unsigned long sysctl_user_reserve_kbytes;
 extern unsigned long sysctl_admin_reserve_kbytes;
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 74c78aa8bc2..7e9c15cb93a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -805,7 +805,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return VM_FAULT_OOM;
 	if (unlikely(khugepaged_enter(vma)))
 		return VM_FAULT_OOM;
-	if (!(flags & FAULT_FLAG_WRITE) &&
+	if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm) &&
 			transparent_hugepage_use_zero_page()) {
 		spinlock_t *ptl;
 		pgtable_t pgtable;
diff --git a/mm/memory.c b/mm/memory.c
index 1cc6bfbd872..d722d4f481c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2640,7 +2640,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return VM_FAULT_SIGBUS;
 
 	/* Use the zero-page for reads */
-	if (!(flags & FAULT_FLAG_WRITE)) {
+	if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm)) {
 		entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
 						vma->vm_page_prot));
 		page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
-- 
cgit v1.2.3-70-g09d2


From f7f242ff004499e0904d3664713dfba01f24c408 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 15 Oct 2014 12:17:34 +0200
Subject: kprobes: introduce weak arch_check_ftrace_location() helper function

Introduce weak arch_check_ftrace_location() helper function which
architectures can override in order to implement handling of kprobes
on function tracer call sites on their own, without depending on
common code or implementing the KPROBES_ON_FTRACE feature.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 include/linux/kprobes.h |  1 +
 kernel/kprobes.c        | 18 +++++++++++-------
 2 files changed, 12 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index f7296e57d61..5297f9fa0ef 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -335,6 +335,7 @@ extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 extern int arch_prepare_kprobe_ftrace(struct kprobe *p);
 #endif
 
+int arch_check_ftrace_location(struct kprobe *p);
 
 /* Get the kprobe at this addr (if any) - called with preemption disabled */
 struct kprobe *get_kprobe(void *addr);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 3995f546d0f..317eb8ad28d 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1410,16 +1410,10 @@ static inline int check_kprobe_rereg(struct kprobe *p)
 	return ret;
 }
 
-static int check_kprobe_address_safe(struct kprobe *p,
-				     struct module **probed_mod)
+int __weak arch_check_ftrace_location(struct kprobe *p)
 {
-	int ret = 0;
 	unsigned long ftrace_addr;
 
-	/*
-	 * If the address is located on a ftrace nop, set the
-	 * breakpoint to the following instruction.
-	 */
 	ftrace_addr = ftrace_location((unsigned long)p->addr);
 	if (ftrace_addr) {
 #ifdef CONFIG_KPROBES_ON_FTRACE
@@ -1431,7 +1425,17 @@ static int check_kprobe_address_safe(struct kprobe *p,
 		return -EINVAL;
 #endif
 	}
+	return 0;
+}
 
+static int check_kprobe_address_safe(struct kprobe *p,
+				     struct module **probed_mod)
+{
+	int ret;
+
+	ret = arch_check_ftrace_location(p);
+	if (ret)
+		return ret;
 	jump_label_lock();
 	preempt_disable();
 
-- 
cgit v1.2.3-70-g09d2


From fcbe08d66f57c368e77ca729dd01e6b539ffb3ff Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Fri, 24 Oct 2014 10:52:29 +0200
Subject: s390/mm: pmdp_get_and_clear_full optimization

Analog to ptep_get_and_clear_full define a variant of the
pmpd_get_and_clear primitive which gets the full hint from the
mmu_gather struct. This allows s390 to avoid a costly instruction
when destroying an address space.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/pgtable.h | 13 +++++++++++++
 include/asm-generic/pgtable.h   | 11 +++++++++++
 mm/huge_memory.c                |  3 ++-
 3 files changed, 26 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 5ef1a266936..5e102422c9a 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1651,6 +1651,19 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
 	return pmd;
 }
 
+#define __HAVE_ARCH_PMDP_GET_AND_CLEAR_FULL
+static inline pmd_t pmdp_get_and_clear_full(struct mm_struct *mm,
+					    unsigned long address,
+					    pmd_t *pmdp, int full)
+{
+	pmd_t pmd = *pmdp;
+
+	if (!full)
+		pmdp_flush_lazy(mm, address, pmdp);
+	pmd_clear(pmdp);
+	return pmd;
+}
+
 #define __HAVE_ARCH_PMDP_CLEAR_FLUSH
 static inline pmd_t pmdp_clear_flush(struct vm_area_struct *vma,
 				     unsigned long address, pmd_t *pmdp)
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 752e30d6390..177d5973b13 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -103,6 +103,17 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_GET_AND_CLEAR_FULL
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline pmd_t pmdp_get_and_clear_full(struct mm_struct *mm,
+					    unsigned long address, pmd_t *pmdp,
+					    int full)
+{
+	return pmdp_get_and_clear(mm, address, pmdp);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
 static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 					    unsigned long address, pte_t *ptep,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7e9c15cb93a..6a37f1b2ed1 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1400,7 +1400,8 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 * pgtable_trans_huge_withdraw after finishing pmdp related
 		 * operations.
 		 */
-		orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd);
+		orig_pmd = pmdp_get_and_clear_full(tlb->mm, addr, pmd,
+						   tlb->fullmm);
 		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
 		pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
 		if (is_huge_zero_pmd(orig_pmd)) {
-- 
cgit v1.2.3-70-g09d2


From f8b361768ea2eaf9b21dfbe7388958ec31798c8b Mon Sep 17 00:00:00 2001
From: Martin Townsend <mtownsend1973@gmail.com>
Date: Thu, 23 Oct 2014 15:40:53 +0100
Subject: 6lowpan: remove skb_deliver from IPHC

Separating skb delivery from decompression ensures that we can support further
decompression schemes and removes the mixed return value of error codes with
NET_RX_FOO.

Signed-off-by: Martin Townsend <mtownsend1973@gmail.com>
Acked-by: Alexander Aring <alex.aring@gmail.com>
Acked-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/6lowpan.h         |  4 +---
 net/6lowpan/iphc.c            | 32 ++++++--------------------------
 net/bluetooth/6lowpan.c       | 14 ++++++++++++--
 net/ieee802154/6lowpan_rtnl.c | 41 ++++++++++++++++++++++++++---------------
 4 files changed, 45 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h
index d184df1d0d4..abfa3593e91 100644
--- a/include/net/6lowpan.h
+++ b/include/net/6lowpan.h
@@ -372,12 +372,10 @@ lowpan_uncompress_size(const struct sk_buff *skb, u16 *dgram_offset)
 	return skb->len + uncomp_header - ret;
 }
 
-typedef int (*skb_delivery_cb)(struct sk_buff *skb, struct net_device *dev);
-
 int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
 		const u8 *saddr, const u8 saddr_type, const u8 saddr_len,
 		const u8 *daddr, const u8 daddr_type, const u8 daddr_len,
-		u8 iphc0, u8 iphc1, skb_delivery_cb skb_deliver);
+		u8 iphc0, u8 iphc1);
 int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev,
 			unsigned short type, const void *_daddr,
 			const void *_saddr, unsigned int len);
diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c
index 747b3ccfc4f..45714fe885f 100644
--- a/net/6lowpan/iphc.c
+++ b/net/6lowpan/iphc.c
@@ -171,29 +171,6 @@ static int uncompress_context_based_src_addr(struct sk_buff *skb,
 	return 0;
 }
 
-static int skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr,
-		       struct net_device *dev, skb_delivery_cb deliver_skb)
-{
-	int stat;
-
-	skb_push(skb, sizeof(struct ipv6hdr));
-	skb_reset_network_header(skb);
-	skb_copy_to_linear_data(skb, hdr, sizeof(struct ipv6hdr));
-
-	skb->protocol = htons(ETH_P_IPV6);
-	skb->pkt_type = PACKET_HOST;
-	skb->dev = dev;
-
-	raw_dump_table(__func__, "raw skb data dump before receiving",
-		       skb->data, skb->len);
-
-	stat = deliver_skb(skb, dev);
-
-	consume_skb(skb);
-
-	return stat;
-}
-
 /* Uncompress function for multicast destination address,
  * when M bit is set.
  */
@@ -327,7 +304,7 @@ static const u8 lowpan_ttl_values[] = { 0, 1, 64, 255 };
 int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
 			const u8 *saddr, const u8 saddr_type, const u8 saddr_len,
 			const u8 *daddr, const u8 daddr_type, const u8 daddr_len,
-			u8 iphc0, u8 iphc1, skb_delivery_cb deliver_skb)
+			u8 iphc0, u8 iphc1)
 {
 	struct ipv6hdr hdr = {};
 	u8 tmp, num_context = 0;
@@ -492,10 +469,13 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
 		hdr.version, ntohs(hdr.payload_len), hdr.nexthdr,
 		hdr.hop_limit, &hdr.daddr);
 
-	raw_dump_table(__func__, "raw header dump", (u8 *)&hdr, sizeof(hdr));
+	skb_push(skb, sizeof(hdr));
+	skb_reset_network_header(skb);
+	skb_copy_to_linear_data(skb, &hdr, sizeof(hdr));
 
-	return skb_deliver(skb, &hdr, dev, deliver_skb);
+	raw_dump_table(__func__, "raw header dump", (u8 *)&hdr, sizeof(hdr));
 
+	return 0;
 drop:
 	kfree_skb(skb);
 	return -EINVAL;
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 6c5c2eff45b..45d9a9fef63 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -252,7 +252,7 @@ static int give_skb_to_upper(struct sk_buff *skb, struct net_device *dev)
 
 	skb_cp = skb_copy(skb, GFP_ATOMIC);
 	if (!skb_cp)
-		return -ENOMEM;
+		return NET_RX_DROP;
 
 	return netif_rx(skb_cp);
 }
@@ -290,7 +290,7 @@ static int process_data(struct sk_buff *skb, struct net_device *netdev,
 	return lowpan_process_data(skb, netdev,
 				   saddr, IEEE802154_ADDR_LONG, EUI64_ADDR_LEN,
 				   daddr, IEEE802154_ADDR_LONG, EUI64_ADDR_LEN,
-				   iphc0, iphc1, give_skb_to_upper);
+				   iphc0, iphc1);
 
 drop:
 	kfree_skb(skb);
@@ -350,6 +350,16 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev,
 			if (ret != NET_RX_SUCCESS)
 				goto drop;
 
+			local_skb->protocol = htons(ETH_P_IPV6);
+			local_skb->pkt_type = PACKET_HOST;
+			local_skb->dev = dev;
+
+			if (give_skb_to_upper(local_skb, dev)
+					!= NET_RX_SUCCESS) {
+				kfree_skb(local_skb);
+				goto drop;
+			}
+
 			dev->stats.rx_bytes += skb->len;
 			dev->stats.rx_packets++;
 
diff --git a/net/ieee802154/6lowpan_rtnl.c b/net/ieee802154/6lowpan_rtnl.c
index 1779a08d110..15c7717c5e0 100644
--- a/net/ieee802154/6lowpan_rtnl.c
+++ b/net/ieee802154/6lowpan_rtnl.c
@@ -141,20 +141,28 @@ static int lowpan_give_skb_to_devices(struct sk_buff *skb,
 	struct sk_buff *skb_cp;
 	int stat = NET_RX_SUCCESS;
 
+	skb->protocol = htons(ETH_P_IPV6);
+	skb->pkt_type = PACKET_HOST;
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(entry, &lowpan_devices, list)
 		if (lowpan_dev_info(entry->ldev)->real_dev == skb->dev) {
 			skb_cp = skb_copy(skb, GFP_ATOMIC);
 			if (!skb_cp) {
-				stat = -ENOMEM;
-				break;
+				kfree_skb(skb);
+				rcu_read_unlock();
+				return NET_RX_DROP;
 			}
 
 			skb_cp->dev = entry->ldev;
 			stat = netif_rx(skb_cp);
+			if (stat == NET_RX_DROP)
+				break;
 		}
 	rcu_read_unlock();
 
+	consume_skb(skb);
+
 	return stat;
 }
 
@@ -190,8 +198,7 @@ static int process_data(struct sk_buff *skb, const struct ieee802154_hdr *hdr)
 
 	return lowpan_process_data(skb, skb->dev, sap, sa.addr_type,
 				   IEEE802154_ADDR_LEN, dap, da.addr_type,
-				   IEEE802154_ADDR_LEN, iphc0, iphc1,
-				   lowpan_give_skb_to_devices);
+				   IEEE802154_ADDR_LEN, iphc0, iphc1);
 
 drop:
 	kfree_skb(skb);
@@ -528,44 +535,48 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	/* check that it's our buffer */
 	if (skb->data[0] == LOWPAN_DISPATCH_IPV6) {
-		skb->protocol = htons(ETH_P_IPV6);
-		skb->pkt_type = PACKET_HOST;
-
 		/* Pull off the 1-byte of 6lowpan header. */
 		skb_pull(skb, 1);
-
-		ret = lowpan_give_skb_to_devices(skb, NULL);
-		if (ret == NET_RX_DROP)
-			goto drop;
+		return lowpan_give_skb_to_devices(skb, NULL);
 	} else {
 		switch (skb->data[0] & 0xe0) {
 		case LOWPAN_DISPATCH_IPHC:	/* ipv6 datagram */
 			ret = process_data(skb, &hdr);
 			if (ret == NET_RX_DROP)
 				goto drop;
-			break;
+
+			return lowpan_give_skb_to_devices(skb, NULL);
 		case LOWPAN_DISPATCH_FRAG1:	/* first fragment header */
 			ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAG1);
 			if (ret == 1) {
 				ret = process_data(skb, &hdr);
 				if (ret == NET_RX_DROP)
 					goto drop;
+
+				return lowpan_give_skb_to_devices(skb, NULL);
+			} else if (ret == -1) {
+				return NET_RX_DROP;
+			} else {
+				return NET_RX_SUCCESS;
 			}
-			break;
 		case LOWPAN_DISPATCH_FRAGN:	/* next fragments headers */
 			ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAGN);
 			if (ret == 1) {
 				ret = process_data(skb, &hdr);
 				if (ret == NET_RX_DROP)
 					goto drop;
+
+				return lowpan_give_skb_to_devices(skb, NULL);
+			} else if (ret == -1) {
+				return NET_RX_DROP;
+			} else {
+				return NET_RX_SUCCESS;
 			}
-			break;
 		default:
 			break;
 		}
 	}
 
-	return NET_RX_SUCCESS;
 drop_skb:
 	kfree_skb(skb);
 drop:
-- 
cgit v1.2.3-70-g09d2


From 01141234f237957ec962dda2f1ca89d9ef180884 Mon Sep 17 00:00:00 2001
From: Martin Townsend <mtownsend1973@gmail.com>
Date: Thu, 23 Oct 2014 15:40:56 +0100
Subject: ieee802154: 6lowpan: rename process_data and lowpan_process_data

As we have decouple decompression from data delivery we can now rename all
occurences of process_data in receive path.

Signed-off-by: Martin Townsend <mtownsend1973@gmail.com>
Acked-by: Alexander Aring <alex.aring@gmail.com>
Acked-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/6lowpan.h         | 10 ++++++----
 net/6lowpan/iphc.c            | 12 +++++++-----
 net/bluetooth/6lowpan.c       | 15 ++++++++-------
 net/ieee802154/6lowpan_rtnl.c | 15 ++++++++-------
 4 files changed, 29 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h
index abfa3593e91..dc03d77ad23 100644
--- a/include/net/6lowpan.h
+++ b/include/net/6lowpan.h
@@ -372,10 +372,12 @@ lowpan_uncompress_size(const struct sk_buff *skb, u16 *dgram_offset)
 	return skb->len + uncomp_header - ret;
 }
 
-int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
-		const u8 *saddr, const u8 saddr_type, const u8 saddr_len,
-		const u8 *daddr, const u8 daddr_type, const u8 daddr_len,
-		u8 iphc0, u8 iphc1);
+int
+lowpan_header_decompress(struct sk_buff *skb, struct net_device *dev,
+			 const u8 *saddr, const u8 saddr_type,
+			 const u8 saddr_len, const u8 *daddr,
+			 const u8 daddr_type, const u8 daddr_len,
+			 u8 iphc0, u8 iphc1);
 int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev,
 			unsigned short type, const void *_daddr,
 			const void *_saddr, unsigned int len);
diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c
index 45714fe885f..73a7065f0c6 100644
--- a/net/6lowpan/iphc.c
+++ b/net/6lowpan/iphc.c
@@ -301,10 +301,12 @@ err:
 /* TTL uncompression values */
 static const u8 lowpan_ttl_values[] = { 0, 1, 64, 255 };
 
-int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
-			const u8 *saddr, const u8 saddr_type, const u8 saddr_len,
-			const u8 *daddr, const u8 daddr_type, const u8 daddr_len,
-			u8 iphc0, u8 iphc1)
+int
+lowpan_header_decompress(struct sk_buff *skb, struct net_device *dev,
+			 const u8 *saddr, const u8 saddr_type,
+			 const u8 saddr_len, const u8 *daddr,
+			 const u8 daddr_type, const u8 daddr_len,
+			 u8 iphc0, u8 iphc1)
 {
 	struct ipv6hdr hdr = {};
 	u8 tmp, num_context = 0;
@@ -480,7 +482,7 @@ drop:
 	kfree_skb(skb);
 	return -EINVAL;
 }
-EXPORT_SYMBOL_GPL(lowpan_process_data);
+EXPORT_SYMBOL_GPL(lowpan_header_decompress);
 
 static u8 lowpan_compress_addr_64(u8 **hc_ptr, u8 shift,
 				  const struct in6_addr *ipaddr,
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 40e2cec7fce..aa6ebbfc5d3 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -257,8 +257,8 @@ static int give_skb_to_upper(struct sk_buff *skb, struct net_device *dev)
 	return netif_rx(skb_cp);
 }
 
-static int process_data(struct sk_buff *skb, struct net_device *netdev,
-			struct l2cap_chan *chan)
+static int iphc_decompress(struct sk_buff *skb, struct net_device *netdev,
+			   struct l2cap_chan *chan)
 {
 	const u8 *saddr, *daddr;
 	u8 iphc0, iphc1;
@@ -287,10 +287,11 @@ static int process_data(struct sk_buff *skb, struct net_device *netdev,
 	if (lowpan_fetch_skb_u8(skb, &iphc1))
 		goto drop;
 
-	return lowpan_process_data(skb, netdev,
-				   saddr, IEEE802154_ADDR_LONG, EUI64_ADDR_LEN,
-				   daddr, IEEE802154_ADDR_LONG, EUI64_ADDR_LEN,
-				   iphc0, iphc1);
+	return lowpan_header_decompress(skb, netdev,
+					saddr, IEEE802154_ADDR_LONG,
+					EUI64_ADDR_LEN, daddr,
+					IEEE802154_ADDR_LONG, EUI64_ADDR_LEN,
+					iphc0, iphc1);
 
 drop:
 	kfree_skb(skb);
@@ -346,7 +347,7 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev,
 			if (!local_skb)
 				goto drop;
 
-			ret = process_data(local_skb, dev, chan);
+			ret = iphc_decompress(local_skb, dev, chan);
 			if (ret < 0)
 				goto drop;
 
diff --git a/net/ieee802154/6lowpan_rtnl.c b/net/ieee802154/6lowpan_rtnl.c
index 21742c82747..519a65452d9 100644
--- a/net/ieee802154/6lowpan_rtnl.c
+++ b/net/ieee802154/6lowpan_rtnl.c
@@ -166,7 +166,8 @@ static int lowpan_give_skb_to_devices(struct sk_buff *skb,
 	return stat;
 }
 
-static int process_data(struct sk_buff *skb, const struct ieee802154_hdr *hdr)
+static int
+iphc_decompress(struct sk_buff *skb, const struct ieee802154_hdr *hdr)
 {
 	u8 iphc0, iphc1;
 	struct ieee802154_addr_sa sa, da;
@@ -196,9 +197,9 @@ static int process_data(struct sk_buff *skb, const struct ieee802154_hdr *hdr)
 	else
 		dap = &da.hwaddr;
 
-	return lowpan_process_data(skb, skb->dev, sap, sa.addr_type,
-				   IEEE802154_ADDR_LEN, dap, da.addr_type,
-				   IEEE802154_ADDR_LEN, iphc0, iphc1);
+	return lowpan_header_decompress(skb, skb->dev, sap, sa.addr_type,
+					IEEE802154_ADDR_LEN, dap, da.addr_type,
+					IEEE802154_ADDR_LEN, iphc0, iphc1);
 
 drop:
 	kfree_skb(skb);
@@ -541,7 +542,7 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev,
 	} else {
 		switch (skb->data[0] & 0xe0) {
 		case LOWPAN_DISPATCH_IPHC:	/* ipv6 datagram */
-			ret = process_data(skb, &hdr);
+			ret = iphc_decompress(skb, &hdr);
 			if (ret < 0)
 				goto drop;
 
@@ -549,7 +550,7 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev,
 		case LOWPAN_DISPATCH_FRAG1:	/* first fragment header */
 			ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAG1);
 			if (ret == 1) {
-				ret = process_data(skb, &hdr);
+				ret = iphc_decompress(skb, &hdr);
 				if (ret < 0)
 					goto drop;
 
@@ -562,7 +563,7 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev,
 		case LOWPAN_DISPATCH_FRAGN:	/* next fragments headers */
 			ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAGN);
 			if (ret == 1) {
-				ret = process_data(skb, &hdr);
+				ret = iphc_decompress(skb, &hdr);
 				if (ret < 0)
 					goto drop;
 
-- 
cgit v1.2.3-70-g09d2


From 344736f29b359790facd0b7a521e367f1715c11c Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Mon, 20 Oct 2014 15:50:30 +0400
Subject: cpuset: simplify cpuset_node_allowed API

Current cpuset API for checking if a zone/node is allowed to allocate
from looks rather awkward. We have hardwall and softwall versions of
cpuset_node_allowed with the softwall version doing literally the same
as the hardwall version if __GFP_HARDWALL is passed to it in gfp flags.
If it isn't, the softwall version may check the given node against the
enclosing hardwall cpuset, which it needs to take the callback lock to
do.

Such a distinction was introduced by commit 02a0e53d8227 ("cpuset:
rework cpuset_zone_allowed api"). Before, we had the only version with
the __GFP_HARDWALL flag determining its behavior. The purpose of the
commit was to avoid sleep-in-atomic bugs when someone would mistakenly
call the function without the __GFP_HARDWALL flag for an atomic
allocation. The suffixes introduced were intended to make the callers
think before using the function.

However, since the callback lock was converted from mutex to spinlock by
the previous patch, the softwall check function cannot sleep, and these
precautions are no longer necessary.

So let's simplify the API back to the single check.

Suggested-by: David Rientjes <rientjes@google.com>
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cpuset.h | 37 +++++++--------------------------
 kernel/cpuset.c        | 55 ++------------------------------------------------
 mm/hugetlb.c           |  2 +-
 mm/oom_kill.c          |  2 +-
 mm/page_alloc.c        |  6 +++---
 mm/slab.c              |  2 +-
 mm/slub.c              |  3 ++-
 mm/vmscan.c            |  5 +++--
 8 files changed, 20 insertions(+), 92 deletions(-)

(limited to 'include')

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 2f073db7392..1b357997cac 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -48,29 +48,16 @@ extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 void cpuset_init_current_mems_allowed(void);
 int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask);
 
-extern int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask);
-extern int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask);
+extern int __cpuset_node_allowed(int node, gfp_t gfp_mask);
 
-static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
+static inline int cpuset_node_allowed(int node, gfp_t gfp_mask)
 {
-	return nr_cpusets() <= 1 ||
-		__cpuset_node_allowed_softwall(node, gfp_mask);
+	return nr_cpusets() <= 1 || __cpuset_node_allowed(node, gfp_mask);
 }
 
-static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
+static inline int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
 {
-	return nr_cpusets() <= 1 ||
-		__cpuset_node_allowed_hardwall(node, gfp_mask);
-}
-
-static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
-{
-	return cpuset_node_allowed_softwall(zone_to_nid(z), gfp_mask);
-}
-
-static inline int cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
-{
-	return cpuset_node_allowed_hardwall(zone_to_nid(z), gfp_mask);
+	return cpuset_node_allowed(zone_to_nid(z), gfp_mask);
 }
 
 extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
@@ -179,22 +166,12 @@ static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
 	return 1;
 }
 
-static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
-{
-	return 1;
-}
-
-static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
-{
-	return 1;
-}
-
-static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
+static inline int cpuset_node_allowed(int node, gfp_t gfp_mask)
 {
 	return 1;
 }
 
-static inline int cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
+static inline int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
 {
 	return 1;
 }
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index f21ba868f0d..38f7433c1cd 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2453,7 +2453,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
 }
 
 /**
- * cpuset_node_allowed_softwall - Can we allocate on a memory node?
+ * cpuset_node_allowed - Can we allocate on a memory node?
  * @node: is this an allowed node?
  * @gfp_mask: memory allocation flags
  *
@@ -2465,13 +2465,6 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
  * flag, yes.
  * Otherwise, no.
  *
- * If __GFP_HARDWALL is set, cpuset_node_allowed_softwall() reduces to
- * cpuset_node_allowed_hardwall().  Otherwise, cpuset_node_allowed_softwall()
- * might sleep, and might allow a node from an enclosing cpuset.
- *
- * cpuset_node_allowed_hardwall() only handles the simpler case of hardwall
- * cpusets, and never sleeps.
- *
  * The __GFP_THISNODE placement logic is really handled elsewhere,
  * by forcibly using a zonelist starting at a specified node, and by
  * (in get_page_from_freelist()) refusing to consider the zones for
@@ -2506,13 +2499,8 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
  *	TIF_MEMDIE   - any node ok
  *	GFP_KERNEL   - any node in enclosing hardwalled cpuset ok
  *	GFP_USER     - only nodes in current tasks mems allowed ok.
- *
- * Rule:
- *    Don't call cpuset_node_allowed_softwall if you can't sleep, unless you
- *    pass in the __GFP_HARDWALL flag set in gfp_flag, which disables
- *    the code that might scan up ancestor cpusets and sleep.
  */
-int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
+int __cpuset_node_allowed(int node, gfp_t gfp_mask)
 {
 	struct cpuset *cs;		/* current cpuset ancestors */
 	int allowed;			/* is allocation in zone z allowed? */
@@ -2520,7 +2508,6 @@ int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
 
 	if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
 		return 1;
-	might_sleep_if(!(gfp_mask & __GFP_HARDWALL));
 	if (node_isset(node, current->mems_allowed))
 		return 1;
 	/*
@@ -2547,44 +2534,6 @@ int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
 	return allowed;
 }
 
-/*
- * cpuset_node_allowed_hardwall - Can we allocate on a memory node?
- * @node: is this an allowed node?
- * @gfp_mask: memory allocation flags
- *
- * If we're in interrupt, yes, we can always allocate.  If __GFP_THISNODE is
- * set, yes, we can always allocate.  If node is in our task's mems_allowed,
- * yes.  If the task has been OOM killed and has access to memory reserves as
- * specified by the TIF_MEMDIE flag, yes.
- * Otherwise, no.
- *
- * The __GFP_THISNODE placement logic is really handled elsewhere,
- * by forcibly using a zonelist starting at a specified node, and by
- * (in get_page_from_freelist()) refusing to consider the zones for
- * any node on the zonelist except the first.  By the time any such
- * calls get to this routine, we should just shut up and say 'yes'.
- *
- * Unlike the cpuset_node_allowed_softwall() variant, above,
- * this variant requires that the node be in the current task's
- * mems_allowed or that we're in interrupt.  It does not scan up the
- * cpuset hierarchy for the nearest enclosing mem_exclusive cpuset.
- * It never sleeps.
- */
-int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
-{
-	if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
-		return 1;
-	if (node_isset(node, current->mems_allowed))
-		return 1;
-	/*
-	 * Allow tasks that have access to memory reserves because they have
-	 * been OOM killed to get memory anywhere.
-	 */
-	if (unlikely(test_thread_flag(TIF_MEMDIE)))
-		return 1;
-	return 0;
-}
-
 /**
  * cpuset_mem_spread_node() - On which node to begin search for a file page
  * cpuset_slab_spread_node() - On which node to begin search for a slab page
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9fd72276992..82da930fa3f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -582,7 +582,7 @@ retry_cpuset:
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 						MAX_NR_ZONES - 1, nodemask) {
-		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask(h))) {
+		if (cpuset_zone_allowed(zone, htlb_alloc_mask(h))) {
 			page = dequeue_huge_page_node(h, zone_to_nid(zone));
 			if (page) {
 				if (avoid_reserve)
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 5340f6b9131..3348280eef8 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -233,7 +233,7 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
 	/* Check this allocation failure is caused by cpuset's wall function */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 			high_zoneidx, nodemask)
-		if (!cpuset_zone_allowed_softwall(zone, gfp_mask))
+		if (!cpuset_zone_allowed(zone, gfp_mask))
 			cpuset_limited = true;
 
 	if (cpuset_limited) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9cd36b82244..ab07b496672 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1962,7 +1962,7 @@ zonelist_scan:
 
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
-	 * See also __cpuset_node_allowed_softwall() comment in kernel/cpuset.c.
+	 * See also __cpuset_node_allowed() comment in kernel/cpuset.c.
 	 */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 						high_zoneidx, nodemask) {
@@ -1973,7 +1973,7 @@ zonelist_scan:
 				continue;
 		if (cpusets_enabled() &&
 			(alloc_flags & ALLOC_CPUSET) &&
-			!cpuset_zone_allowed_softwall(zone, gfp_mask))
+			!cpuset_zone_allowed(zone, gfp_mask))
 				continue;
 		/*
 		 * Distribute pages in proportion to the individual
@@ -2514,7 +2514,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 			alloc_flags |= ALLOC_HARDER;
 		/*
 		 * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
-		 * comment for __cpuset_node_allowed_softwall().
+		 * comment for __cpuset_node_allowed().
 		 */
 		alloc_flags &= ~ALLOC_CPUSET;
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
diff --git a/mm/slab.c b/mm/slab.c
index eb2b2ea3013..063a91bc882 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3012,7 +3012,7 @@ retry:
 	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 		nid = zone_to_nid(zone);
 
-		if (cpuset_zone_allowed_hardwall(zone, flags) &&
+		if (cpuset_zone_allowed(zone, flags | __GFP_HARDWALL) &&
 			get_node(cache, nid) &&
 			get_node(cache, nid)->free_objects) {
 				obj = ____cache_alloc_node(cache,
diff --git a/mm/slub.c b/mm/slub.c
index ae7b9f1ad39..7d12f51d9ba 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1662,7 +1662,8 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 
 			n = get_node(s, zone_to_nid(zone));
 
-			if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
+			if (n && cpuset_zone_allowed(zone,
+						     flags | __GFP_HARDWALL) &&
 					n->nr_partial > s->min_partial) {
 				object = get_partial_node(s, n, c, flags);
 				if (object) {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index dcb47074ae0..38878b2ab1d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2405,7 +2405,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 		 * to global LRU.
 		 */
 		if (global_reclaim(sc)) {
-			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+			if (!cpuset_zone_allowed(zone,
+						 GFP_KERNEL | __GFP_HARDWALL))
 				continue;
 
 			lru_pages += zone_reclaimable_pages(zone);
@@ -3388,7 +3389,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	if (!populated_zone(zone))
 		return;
 
-	if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
 		return;
 	pgdat = zone->zone_pgdat;
 	if (pgdat->kswapd_max_order < order) {
-- 
cgit v1.2.3-70-g09d2


From c5c47e67bcd24638a059b1b5e9ec18c95f8634ca Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Mon, 27 Oct 2014 17:13:30 +0100
Subject: mac802154: rx: use tasklet instead workqueue

Tasklets have much less overhead than workqueues. This patch also
removes the heap allocation for the worker on receiving path.
Like mac80211 we should prefer use a tasklet here instead a workqueue to
getting fast out of interrupt context when ieee802154_rx_irqsafe is
called by driver. Like wireless inside the tasklet context we should
call netif_receive_skb instead netif_rx_ni anymore.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/mac802154.h      |  1 +
 net/mac802154/ieee802154_i.h |  7 +++++++
 net/mac802154/iface.c        |  2 +-
 net/mac802154/main.c         | 30 +++++++++++++++++++++++++++
 net/mac802154/rx.c           | 48 ++++++++------------------------------------
 5 files changed, 47 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 942dd53d465..4c4642ef244 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -202,6 +202,7 @@ void ieee802154_free_hw(struct ieee802154_hw *hw);
 int ieee802154_register_hw(struct ieee802154_hw *hw);
 void ieee802154_unregister_hw(struct ieee802154_hw *hw);
 
+void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb);
 void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb,
 			   u8 lqi);
 
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index ef29c10eeb6..603509a94a8 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -55,11 +55,18 @@ struct ieee802154_local {
 	 * read them using any of protection methods.
 	 */
 	bool running;
+
+	struct tasklet_struct tasklet;
+	struct sk_buff_head skb_queue;
 };
 
 #define	MAC802154_DEVICE_STOPPED	0x00
 #define MAC802154_DEVICE_RUN		0x01
 
+enum {
+	IEEE802154_RX_MSG        = 1,
+};
+
 /* Slave interface definition.
  *
  * Slaves represent typical network interfaces available from userspace.
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index be45dc9257b..311f60c8629 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -376,7 +376,7 @@ void mac802154_wpan_setup(struct net_device *dev)
 
 static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb)
 {
-	return netif_rx_ni(skb);
+	return netif_receive_skb(skb);
 }
 
 static int
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 3c0a824d24a..ff0de0f990c 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -222,6 +222,29 @@ static int mac802154_set_frame_retries(struct wpan_phy *phy, s8 retries)
 	return local->ops->set_frame_retries(&local->hw, retries);
 }
 
+static void ieee802154_tasklet_handler(unsigned long data)
+{
+	struct ieee802154_local *local = (struct ieee802154_local *)data;
+	struct sk_buff *skb;
+
+	while ((skb = skb_dequeue(&local->skb_queue))) {
+		switch (skb->pkt_type) {
+		case IEEE802154_RX_MSG:
+			/* Clear skb->pkt_type in order to not confuse kernel
+			 * netstack.
+			 */
+			skb->pkt_type = 0;
+			ieee802154_rx(&local->hw, skb);
+			break;
+		default:
+			WARN(1, "mac802154: Packet is of unknown type %d\n",
+			     skb->pkt_type);
+			kfree_skb(skb);
+			break;
+		}
+	}
+}
+
 struct ieee802154_hw *
 ieee802154_alloc_hw(size_t priv_data_len, struct ieee802154_ops *ops)
 {
@@ -270,6 +293,12 @@ ieee802154_alloc_hw(size_t priv_data_len, struct ieee802154_ops *ops)
 	INIT_LIST_HEAD(&local->interfaces);
 	mutex_init(&local->iflist_mtx);
 
+	tasklet_init(&local->tasklet,
+		     ieee802154_tasklet_handler,
+		     (unsigned long)local);
+
+	skb_queue_head_init(&local->skb_queue);
+
 	return &local->hw;
 }
 EXPORT_SYMBOL(ieee802154_alloc_hw);
@@ -371,6 +400,7 @@ void ieee802154_unregister_hw(struct ieee802154_hw *hw)
 	struct ieee802154_local *local = hw_to_local(hw);
 	struct ieee802154_sub_if_data *sdata, *next;
 
+	tasklet_kill(&local->tasklet);
 	flush_workqueue(local->workqueue);
 	destroy_workqueue(local->workqueue);
 
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index 53c9e0c10a8..2851a3f7ac0 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -19,7 +19,6 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/workqueue.h>
 #include <linux/netdevice.h>
 #include <linux/crc-ccitt.h>
 
@@ -28,30 +27,11 @@
 
 #include "ieee802154_i.h"
 
-/* The IEEE 802.15.4 standard defines 4 MAC packet types:
- * - beacon frame
- * - MAC command frame
- * - acknowledgement frame
- * - data frame
- *
- * and only the data frame should be pushed to the upper layers, other types
- * are just internal MAC layer management information. So only data packets
- * are going to be sent to the networking queue, all other will be processed
- * right here by using the device workqueue.
- */
-struct rx_work {
-	struct sk_buff *skb;
-	struct work_struct work;
-	struct ieee802154_hw *hw;
-	u8 lqi;
-};
-
 static void
-mac802154_subif_rx(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi)
+mac802154_subif_rx(struct ieee802154_hw *hw, struct sk_buff *skb)
 {
 	struct ieee802154_local *local = hw_to_local(hw);
 
-	mac_cb(skb)->lqi = lqi;
 	skb->protocol = htons(ETH_P_IEEE802154);
 	skb_reset_mac_header(skb);
 
@@ -79,32 +59,20 @@ fail:
 	kfree_skb(skb);
 }
 
-static void mac802154_rx_worker(struct work_struct *work)
+void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb)
 {
-	struct rx_work *rw = container_of(work, struct rx_work, work);
-
-	mac802154_subif_rx(rw->hw, rw->skb, rw->lqi);
-	kfree(rw);
+	mac802154_subif_rx(hw, skb);
 }
+EXPORT_SYMBOL(ieee802154_rx);
 
 void
 ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi)
 {
 	struct ieee802154_local *local = hw_to_local(hw);
-	struct rx_work *work;
 
-	if (!skb)
-		return;
-
-	work = kzalloc(sizeof(*work), GFP_ATOMIC);
-	if (!work)
-		return;
-
-	INIT_WORK(&work->work, mac802154_rx_worker);
-	work->skb = skb;
-	work->hw = hw;
-	work->lqi = lqi;
-
-	queue_work(local->workqueue, &work->work);
+	mac_cb(skb)->lqi = lqi;
+	skb->pkt_type = IEEE802154_RX_MSG;
+	skb_queue_tail(&local->skb_queue, skb);
+	tasklet_schedule(&local->tasklet);
 }
 EXPORT_SYMBOL(ieee802154_rx_irqsafe);
-- 
cgit v1.2.3-70-g09d2


From fa491001e4edae5ed68a562b61ed729968a3ca1c Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Mon, 27 Oct 2014 17:13:40 +0100
Subject: ieee802154: add valid psdu length helper

This patch adds a generic valid psdu length check function helper. This
is useful to check the length field after receiving. For example the
at86rf231 doesn't filter invalid psdu length. Sometimes the CRC can also
be correct. If we get the lqi value with an invalid frame length the
kernel may crash because we dereference an invalid pointer in the
receive buffer.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/ieee802154.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index 2dfab2db103..6e50a2a1d48 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -23,7 +23,10 @@
 #ifndef LINUX_IEEE802154_H
 #define LINUX_IEEE802154_H
 
+#include <linux/types.h>
+
 #define IEEE802154_MTU			127
+#define IEEE802154_MIN_PSDU_LEN		5
 
 #define IEEE802154_FC_TYPE_BEACON	0x0	/* Frame is beacon */
 #define	IEEE802154_FC_TYPE_DATA		0x1	/* Frame is data */
@@ -185,5 +188,13 @@ enum {
 	IEEE802154_SCAN_IN_PROGRESS = 0xfc,
 };
 
+/**
+ * ieee802154_is_valid_psdu_len - check if psdu len is valid
+ * @len: psdu len with (MHR + payload + MFR)
+ */
+static inline bool ieee802154_is_valid_psdu_len(const u8 len)
+{
+	return (len >= IEEE802154_MIN_PSDU_LEN && len <= IEEE802154_MTU);
+}
 
 #endif /* LINUX_IEEE802154_H */
-- 
cgit v1.2.3-70-g09d2


From a59dadbeeaf7d33f2e92dbf5a290965d6df64162 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@openwrt.org>
Date: Sat, 25 Oct 2014 17:19:33 +0200
Subject: ath9k: add support for endian swap of eeprom from platform data

On some devices (especially little-endian ones), the flash EEPROM data
has a different endian, which needs to be detected.
Add a flag to the platform data to allow overriding that behavior

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/net/wireless/ath/ath9k/eeprom_def.c | 31 ++++++++++-------------------
 drivers/net/wireless/ath/ath9k/hw.h         |  1 +
 drivers/net/wireless/ath/ath9k/init.c       |  2 ++
 include/linux/ath9k_platform.h              |  1 +
 4 files changed, 14 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath9k/eeprom_def.c b/drivers/net/wireless/ath/ath9k/eeprom_def.c
index 3218ca99474..122b846b8ec 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom_def.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom_def.c
@@ -262,7 +262,7 @@ static int ath9k_hw_def_check_eeprom(struct ath_hw *ah)
 {
 	struct ar5416_eeprom_def *eep = &ah->eeprom.def;
 	struct ath_common *common = ath9k_hw_common(ah);
-	u16 *eepdata, temp, magic, magic2;
+	u16 *eepdata, temp, magic;
 	u32 sum = 0, el;
 	bool need_swap = false;
 	int i, addr, size;
@@ -272,27 +272,16 @@ static int ath9k_hw_def_check_eeprom(struct ath_hw *ah)
 		return false;
 	}
 
-	if (!ath9k_hw_use_flash(ah)) {
-		ath_dbg(common, EEPROM, "Read Magic = 0x%04X\n", magic);
-
-		if (magic != AR5416_EEPROM_MAGIC) {
-			magic2 = swab16(magic);
-
-			if (magic2 == AR5416_EEPROM_MAGIC) {
-				size = sizeof(struct ar5416_eeprom_def);
-				need_swap = true;
-				eepdata = (u16 *) (&ah->eeprom);
+	if (swab16(magic) == AR5416_EEPROM_MAGIC &&
+	    !(ah->ah_flags & AH_NO_EEP_SWAP)) {
+		size = sizeof(struct ar5416_eeprom_def);
+		need_swap = true;
+		eepdata = (u16 *) (&ah->eeprom);
 
-				for (addr = 0; addr < size / sizeof(u16); addr++) {
-					temp = swab16(*eepdata);
-					*eepdata = temp;
-					eepdata++;
-				}
-			} else {
-				ath_err(common,
-					"Invalid EEPROM Magic. Endianness mismatch.\n");
-				return -EINVAL;
-			}
+		for (addr = 0; addr < size / sizeof(u16); addr++) {
+			temp = swab16(*eepdata);
+			*eepdata = temp;
+			eepdata++;
 		}
 	}
 
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index f204099c38b..c6dba9b4afd 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -731,6 +731,7 @@ enum ath_cal_list {
 #define AH_USE_EEPROM   0x1
 #define AH_UNPLUGGED    0x2 /* The card has been physically removed. */
 #define AH_FASTCC       0x4
+#define AH_NO_EEP_SWAP  0x8 /* Do not swap EEPROM data */
 
 struct ath_hw {
 	struct ath_ops reg_ops;
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index 57a17601b0b..5d9c711b6aa 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -531,6 +531,8 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc,
 		ah->is_clk_25mhz = pdata->is_clk_25mhz;
 		ah->get_mac_revision = pdata->get_mac_revision;
 		ah->external_reset = pdata->external_reset;
+		if (!pdata->endian_check)
+			ah->ah_flags |= AH_NO_EEP_SWAP;
 	}
 
 	common->ops = &ah->reg_ops;
diff --git a/include/linux/ath9k_platform.h b/include/linux/ath9k_platform.h
index a495a959e8a..43501657bce 100644
--- a/include/linux/ath9k_platform.h
+++ b/include/linux/ath9k_platform.h
@@ -31,6 +31,7 @@ struct ath9k_platform_data {
 	u32 gpio_mask;
 	u32 gpio_val;
 
+	bool endian_check;
 	bool is_clk_25mhz;
 	bool tx_gain_buffalo;
 
-- 
cgit v1.2.3-70-g09d2


From 3468968ef766d7bb4ab29c0ef7ebd169a4ac2e96 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@openwrt.org>
Date: Sat, 25 Oct 2014 17:19:34 +0200
Subject: ath9k: allow disabling bands via platform data

Some devices have multiple bands enables in the EEPROM data, even though
they are only calibrated for one. Allow platform data to disable
unsupported bands.

Signed-off-by: Gabor Juhos <juhosg@openwrt.org>
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/net/wireless/ath/ath9k/hw.c   | 24 ++++++++++++++++--------
 drivers/net/wireless/ath/ath9k/hw.h   |  2 ++
 drivers/net/wireless/ath/ath9k/init.c |  2 ++
 include/linux/ath9k_platform.h        |  2 ++
 4 files changed, 22 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 85a78176b80..47f410ed7cd 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -2344,17 +2344,25 @@ int ath9k_hw_fill_cap_info(struct ath_hw *ah)
 	}
 
 	eeval = ah->eep_ops->get_eeprom(ah, EEP_OP_MODE);
-	if ((eeval & (AR5416_OPFLAGS_11G | AR5416_OPFLAGS_11A)) == 0) {
-		ath_err(common,
-			"no band has been marked as supported in EEPROM\n");
-		return -EINVAL;
+
+	if (eeval & AR5416_OPFLAGS_11A) {
+		if (ah->disable_5ghz)
+			ath_warn(common, "disabling 5GHz band\n");
+		else
+			pCap->hw_caps |= ATH9K_HW_CAP_5GHZ;
 	}
 
-	if (eeval & AR5416_OPFLAGS_11A)
-		pCap->hw_caps |= ATH9K_HW_CAP_5GHZ;
+	if (eeval & AR5416_OPFLAGS_11G) {
+		if (ah->disable_2ghz)
+			ath_warn(common, "disabling 2GHz band\n");
+		else
+			pCap->hw_caps |= ATH9K_HW_CAP_2GHZ;
+	}
 
-	if (eeval & AR5416_OPFLAGS_11G)
-		pCap->hw_caps |= ATH9K_HW_CAP_2GHZ;
+	if ((pCap->hw_caps & (ATH9K_HW_CAP_2GHZ | ATH9K_HW_CAP_5GHZ)) == 0) {
+		ath_err(common, "both bands are disabled\n");
+		return -EINVAL;
+	}
 
 	if (AR_SREV_9485(ah) ||
 	    AR_SREV_9285(ah) ||
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index c6dba9b4afd..e49721e85f6 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -930,6 +930,8 @@ struct ath_hw {
 	bool is_clk_25mhz;
 	int (*get_mac_revision)(void);
 	int (*external_reset)(void);
+	bool disable_2ghz;
+	bool disable_5ghz;
 
 	const struct firmware *eeprom_blob;
 
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index 5d9c711b6aa..2294109f79e 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -531,6 +531,8 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc,
 		ah->is_clk_25mhz = pdata->is_clk_25mhz;
 		ah->get_mac_revision = pdata->get_mac_revision;
 		ah->external_reset = pdata->external_reset;
+		ah->disable_2ghz = pdata->disable_2ghz;
+		ah->disable_5ghz = pdata->disable_5ghz;
 		if (!pdata->endian_check)
 			ah->ah_flags |= AH_NO_EEP_SWAP;
 	}
diff --git a/include/linux/ath9k_platform.h b/include/linux/ath9k_platform.h
index 43501657bce..33eb274cd0e 100644
--- a/include/linux/ath9k_platform.h
+++ b/include/linux/ath9k_platform.h
@@ -34,6 +34,8 @@ struct ath9k_platform_data {
 	bool endian_check;
 	bool is_clk_25mhz;
 	bool tx_gain_buffalo;
+	bool disable_2ghz;
+	bool disable_5ghz;
 
 	int (*get_mac_revision)(void);
 	int (*external_reset)(void);
-- 
cgit v1.2.3-70-g09d2


From 5e96d788d93b90e6e1769fb9376ee28bcdc1a041 Mon Sep 17 00:00:00 2001
From: Fabian Frederick <fabf@skynet.be>
Date: Mon, 27 Oct 2014 20:00:41 +0100
Subject: ipx: move extern sysctl_ipx_pprop_broadcasting to header file

include ipx.h from sysctl_net_ipx.c

Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipx.h        | 3 +++
 net/ipx/sysctl_net_ipx.c | 4 +---
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/ipx.h b/include/net/ipx.h
index 0143180fecc..320f47b64a7 100644
--- a/include/net/ipx.h
+++ b/include/net/ipx.h
@@ -42,6 +42,9 @@ struct ipxhdr {
 	struct ipx_address	ipx_source __packed;
 };
 
+/* From af_ipx.c */
+extern int sysctl_ipx_pprop_broadcasting;
+
 static __inline__ struct ipxhdr *ipx_hdr(struct sk_buff *skb)
 {
 	return (struct ipxhdr *)skb_transport_header(skb);
diff --git a/net/ipx/sysctl_net_ipx.c b/net/ipx/sysctl_net_ipx.c
index ad7c03dedaa..0dafcc561ed 100644
--- a/net/ipx/sysctl_net_ipx.c
+++ b/net/ipx/sysctl_net_ipx.c
@@ -9,14 +9,12 @@
 #include <linux/mm.h>
 #include <linux/sysctl.h>
 #include <net/net_namespace.h>
+#include <net/ipx.h>
 
 #ifndef CONFIG_SYSCTL
 #error This file should not be compiled without CONFIG_SYSCTL defined
 #endif
 
-/* From af_ipx.c */
-extern int sysctl_ipx_pprop_broadcasting;
-
 static struct ctl_table ipx_table[] = {
 	{
 		.procname	= "ipx_pprop_broadcasting",
-- 
cgit v1.2.3-70-g09d2


From 8b13eddfdf04cbfa561725cfc42d6868fe896f56 Mon Sep 17 00:00:00 2001
From: Arturo Borrero <arturo.borrero.glez@gmail.com>
Date: Thu, 16 Oct 2014 12:23:29 +0200
Subject: netfilter: refactor NAT redirect IPv4 to use it from nf_tables

This patch refactors the IPv4 code so it can be usable both from xt and
nf_tables.

A similar patch follows-up to handle IPv6.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/ipv4/nf_nat_redirect.h |  9 +++
 net/ipv4/netfilter/Kconfig                   |  6 ++
 net/ipv4/netfilter/Makefile                  |  1 +
 net/ipv4/netfilter/nf_nat_redirect_ipv4.c    | 82 ++++++++++++++++++++++++++++
 net/netfilter/Kconfig                        |  1 +
 net/netfilter/xt_REDIRECT.c                  | 44 +--------------
 6 files changed, 101 insertions(+), 42 deletions(-)
 create mode 100644 include/net/netfilter/ipv4/nf_nat_redirect.h
 create mode 100644 net/ipv4/netfilter/nf_nat_redirect_ipv4.c

(limited to 'include')

diff --git a/include/net/netfilter/ipv4/nf_nat_redirect.h b/include/net/netfilter/ipv4/nf_nat_redirect.h
new file mode 100644
index 00000000000..19e1df3a0a4
--- /dev/null
+++ b/include/net/netfilter/ipv4/nf_nat_redirect.h
@@ -0,0 +1,9 @@
+#ifndef _NF_NAT_REDIRECT_IPV4_H_
+#define _NF_NAT_REDIRECT_IPV4_H_
+
+unsigned int
+nf_nat_redirect_ipv4(struct sk_buff *skb,
+		     const struct nf_nat_ipv4_multi_range_compat *mr,
+		     unsigned int hooknum);
+
+#endif /* _NF_NAT_REDIRECT_IPV4_H_ */
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 4c019d5c3f5..a300e2c32b2 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -104,6 +104,12 @@ config NF_NAT_MASQUERADE_IPV4
 	  This is the kernel functionality to provide NAT in the masquerade
 	  flavour (automatic source address selection).
 
+config NF_NAT_REDIRECT_IPV4
+	tristate "IPv4 redirect support"
+	help
+	  This is the kernel functionality to provide NAT in the redirect
+	  flavour (redirect packets to local machine).
+
 config NFT_MASQ_IPV4
 	tristate "IPv4 masquerading support for nf_tables"
 	depends on NF_TABLES_IPV4
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index f4cef5af096..34e436c9201 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o
 obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o
 obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
 obj-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o
+obj-$(CONFIG_NF_NAT_REDIRECT_IPV4) += nf_nat_redirect_ipv4.o
 
 # NAT protocols (nf_nat)
 obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
diff --git a/net/ipv4/netfilter/nf_nat_redirect_ipv4.c b/net/ipv4/netfilter/nf_nat_redirect_ipv4.c
new file mode 100644
index 00000000000..a220552fc53
--- /dev/null
+++ b/net/ipv4/netfilter/nf_nat_redirect_ipv4.c
@@ -0,0 +1,82 @@
+/*
+ * (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on Rusty Russell's IPv4 REDIRECT target. Development of IPv6
+ * NAT funded by Astaro.
+ */
+
+#include <linux/if.h>
+#include <linux/inetdevice.h>
+#include <linux/ip.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/netfilter.h>
+#include <linux/types.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/addrconf.h>
+#include <net/checksum.h>
+#include <net/protocol.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/ipv4/nf_nat_redirect.h>
+
+unsigned int
+nf_nat_redirect_ipv4(struct sk_buff *skb,
+		     const struct nf_nat_ipv4_multi_range_compat *mr,
+		     unsigned int hooknum)
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	__be32 newdst;
+	struct nf_nat_range newrange;
+
+	NF_CT_ASSERT(hooknum == NF_INET_PRE_ROUTING ||
+		     hooknum == NF_INET_LOCAL_OUT);
+
+	ct = nf_ct_get(skb, &ctinfo);
+	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED));
+
+	/* Local packets: make them go to loopback */
+	if (hooknum == NF_INET_LOCAL_OUT) {
+		newdst = htonl(0x7F000001);
+	} else {
+		struct in_device *indev;
+		struct in_ifaddr *ifa;
+
+		newdst = 0;
+
+		rcu_read_lock();
+		indev = __in_dev_get_rcu(skb->dev);
+		if (indev != NULL) {
+			ifa = indev->ifa_list;
+			newdst = ifa->ifa_local;
+		}
+		rcu_read_unlock();
+
+		if (!newdst)
+			return NF_DROP;
+	}
+
+	/* Transfer from original range. */
+	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
+	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
+	newrange.flags	     = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.ip = newdst;
+	newrange.max_addr.ip = newdst;
+	newrange.min_proto   = mr->range[0].min;
+	newrange.max_proto   = mr->range[0].max;
+
+	/* Hand modified range to generic setup. */
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
+}
+EXPORT_SYMBOL_GPL(nf_nat_redirect_ipv4);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index ae5096ab65e..a0716a3f08b 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -835,6 +835,7 @@ config NETFILTER_XT_TARGET_RATEEST
 config NETFILTER_XT_TARGET_REDIRECT
 	tristate "REDIRECT target support"
 	depends on NF_NAT
+	select NF_NAT_REDIRECT_IPV4
 	---help---
 	REDIRECT is a special case of NAT: all incoming connections are
 	mapped onto the incoming interface's address, causing the packets to
diff --git a/net/netfilter/xt_REDIRECT.c b/net/netfilter/xt_REDIRECT.c
index 22a10309297..b4ffac5fe8e 100644
--- a/net/netfilter/xt_REDIRECT.c
+++ b/net/netfilter/xt_REDIRECT.c
@@ -26,6 +26,7 @@
 #include <net/checksum.h>
 #include <net/protocol.h>
 #include <net/netfilter/nf_nat.h>
+#include <net/netfilter/ipv4/nf_nat_redirect.h>
 
 static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT;
 
@@ -98,48 +99,7 @@ static int redirect_tg4_check(const struct xt_tgchk_param *par)
 static unsigned int
 redirect_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 {
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	__be32 newdst;
-	const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
-	struct nf_nat_range newrange;
-
-	NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
-		     par->hooknum == NF_INET_LOCAL_OUT);
-
-	ct = nf_ct_get(skb, &ctinfo);
-	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED));
-
-	/* Local packets: make them go to loopback */
-	if (par->hooknum == NF_INET_LOCAL_OUT)
-		newdst = htonl(0x7F000001);
-	else {
-		struct in_device *indev;
-		struct in_ifaddr *ifa;
-
-		newdst = 0;
-
-		rcu_read_lock();
-		indev = __in_dev_get_rcu(skb->dev);
-		if (indev && (ifa = indev->ifa_list))
-			newdst = ifa->ifa_local;
-		rcu_read_unlock();
-
-		if (!newdst)
-			return NF_DROP;
-	}
-
-	/* Transfer from original range. */
-	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
-	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
-	newrange.flags	     = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS;
-	newrange.min_addr.ip = newdst;
-	newrange.max_addr.ip = newdst;
-	newrange.min_proto   = mr->range[0].min;
-	newrange.max_proto   = mr->range[0].max;
-
-	/* Hand modified range to generic setup. */
-	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
+	return nf_nat_redirect_ipv4(skb, par->targinfo, par->hooknum);
 }
 
 static struct xt_target redirect_tg_reg[] __read_mostly = {
-- 
cgit v1.2.3-70-g09d2


From 9de920eddb74bf67f1d6af603acc5ed05dcd35e9 Mon Sep 17 00:00:00 2001
From: Arturo Borrero <arturo.borrero.glez@gmail.com>
Date: Fri, 17 Oct 2014 12:37:52 +0200
Subject: netfilter: refactor NAT redirect IPv6 code to use it from nf_tables

This patch refactors the IPv6 code so it can be usable both from xt and
nf_tables.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/ipv6/nf_nat_redirect.h |  8 +++
 net/ipv6/netfilter/Kconfig                   |  6 +++
 net/ipv6/netfilter/Makefile                  |  1 +
 net/ipv6/netfilter/nf_nat_redirect_ipv6.c    | 75 ++++++++++++++++++++++++++++
 net/netfilter/Kconfig                        |  1 +
 net/netfilter/xt_REDIRECT.c                  | 40 +--------------
 6 files changed, 93 insertions(+), 38 deletions(-)
 create mode 100644 include/net/netfilter/ipv6/nf_nat_redirect.h
 create mode 100644 net/ipv6/netfilter/nf_nat_redirect_ipv6.c

(limited to 'include')

diff --git a/include/net/netfilter/ipv6/nf_nat_redirect.h b/include/net/netfilter/ipv6/nf_nat_redirect.h
new file mode 100644
index 00000000000..1ebdffc461c
--- /dev/null
+++ b/include/net/netfilter/ipv6/nf_nat_redirect.h
@@ -0,0 +1,8 @@
+#ifndef _NF_NAT_REDIRECT_IPV6_H_
+#define _NF_NAT_REDIRECT_IPV6_H_
+
+unsigned int
+nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+		     unsigned int hooknum);
+
+#endif /* _NF_NAT_REDIRECT_IPV6_H_ */
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 6af874fc187..462eebbf437 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -82,6 +82,12 @@ config NF_NAT_MASQUERADE_IPV6
 	  This is the kernel functionality to provide NAT in the masquerade
 	  flavour (automatic source address selection) for IPv6.
 
+config NF_NAT_REDIRECT_IPV6
+	tristate "IPv6 redirect support"
+	help
+	  This is the kernel functionality to provide NAT in the redirect
+	  flavour (redirect packet to local machine) for IPv6.
+
 config NFT_MASQ_IPV6
 	tristate "IPv6 masquerade support for nf_tables"
 	depends on NF_TABLES_IPV6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index fbb25f01143..6c2baab10f2 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o
 nf_nat_ipv6-y		:= nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o
 obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o
 obj-$(CONFIG_NF_NAT_MASQUERADE_IPV6) += nf_nat_masquerade_ipv6.o
+obj-$(CONFIG_NF_NAT_REDIRECT_IPV6) += nf_nat_redirect_ipv6.o
 
 # defrag
 nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
diff --git a/net/ipv6/netfilter/nf_nat_redirect_ipv6.c b/net/ipv6/netfilter/nf_nat_redirect_ipv6.c
new file mode 100644
index 00000000000..ea1308aeb04
--- /dev/null
+++ b/net/ipv6/netfilter/nf_nat_redirect_ipv6.c
@@ -0,0 +1,75 @@
+/*
+ * (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on Rusty Russell's IPv4 REDIRECT target. Development of IPv6
+ * NAT funded by Astaro.
+ */
+
+#include <linux/if.h>
+#include <linux/inetdevice.h>
+#include <linux/ip.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/netfilter.h>
+#include <linux/types.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/addrconf.h>
+#include <net/checksum.h>
+#include <net/protocol.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/ipv6/nf_nat_redirect.h>
+
+static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT;
+
+unsigned int
+nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+		     unsigned int hooknum)
+{
+	struct nf_nat_range newrange;
+	struct in6_addr newdst;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (hooknum == NF_INET_LOCAL_OUT) {
+		newdst = loopback_addr;
+	} else {
+		struct inet6_dev *idev;
+		struct inet6_ifaddr *ifa;
+		bool addr = false;
+
+		rcu_read_lock();
+		idev = __in6_dev_get(skb->dev);
+		if (idev != NULL) {
+			list_for_each_entry(ifa, &idev->addr_list, if_list) {
+				newdst = ifa->addr;
+				addr = true;
+				break;
+			}
+		}
+		rcu_read_unlock();
+
+		if (!addr)
+			return NF_DROP;
+	}
+
+	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.in6	= newdst;
+	newrange.max_addr.in6	= newdst;
+	newrange.min_proto	= range->min_proto;
+	newrange.max_proto	= range->max_proto;
+
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
+}
+EXPORT_SYMBOL_GPL(nf_nat_redirect_ipv6);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index a0716a3f08b..49deb4edbac 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -836,6 +836,7 @@ config NETFILTER_XT_TARGET_REDIRECT
 	tristate "REDIRECT target support"
 	depends on NF_NAT
 	select NF_NAT_REDIRECT_IPV4
+	select NF_NAT_REDIRECT_IPV6 if IP6_NF_IPTABLES
 	---help---
 	REDIRECT is a special case of NAT: all incoming connections are
 	mapped onto the incoming interface's address, causing the packets to
diff --git a/net/netfilter/xt_REDIRECT.c b/net/netfilter/xt_REDIRECT.c
index b4ffac5fe8e..b6ec67efd90 100644
--- a/net/netfilter/xt_REDIRECT.c
+++ b/net/netfilter/xt_REDIRECT.c
@@ -27,48 +27,12 @@
 #include <net/protocol.h>
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/ipv4/nf_nat_redirect.h>
-
-static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT;
+#include <net/netfilter/ipv6/nf_nat_redirect.h>
 
 static unsigned int
 redirect_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 {
-	const struct nf_nat_range *range = par->targinfo;
-	struct nf_nat_range newrange;
-	struct in6_addr newdst;
-	enum ip_conntrack_info ctinfo;
-	struct nf_conn *ct;
-
-	ct = nf_ct_get(skb, &ctinfo);
-	if (par->hooknum == NF_INET_LOCAL_OUT)
-		newdst = loopback_addr;
-	else {
-		struct inet6_dev *idev;
-		struct inet6_ifaddr *ifa;
-		bool addr = false;
-
-		rcu_read_lock();
-		idev = __in6_dev_get(skb->dev);
-		if (idev != NULL) {
-			list_for_each_entry(ifa, &idev->addr_list, if_list) {
-				newdst = ifa->addr;
-				addr = true;
-				break;
-			}
-		}
-		rcu_read_unlock();
-
-		if (!addr)
-			return NF_DROP;
-	}
-
-	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
-	newrange.min_addr.in6	= newdst;
-	newrange.max_addr.in6	= newdst;
-	newrange.min_proto	= range->min_proto;
-	newrange.max_proto	= range->max_proto;
-
-	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
+	return nf_nat_redirect_ipv6(skb, par->targinfo, par->hooknum);
 }
 
 static int redirect_tg6_checkentry(const struct xt_tgchk_param *par)
-- 
cgit v1.2.3-70-g09d2


From e9105f1bead4ec3f64904564c7c6268185d6b363 Mon Sep 17 00:00:00 2001
From: Arturo Borrero <arturo.borrero.glez@gmail.com>
Date: Fri, 17 Oct 2014 12:39:09 +0200
Subject: netfilter: nf_tables: add new expression nft_redir

This new expression provides NAT in the redirect flavour, which is to
redirect packets to local machine.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nft_redir.h        | 21 +++++++
 include/uapi/linux/netfilter/nf_tables.h | 16 ++++++
 net/ipv4/netfilter/Kconfig               |  9 +++
 net/ipv4/netfilter/Makefile              |  1 +
 net/ipv4/netfilter/nft_redir_ipv4.c      | 77 +++++++++++++++++++++++++
 net/ipv6/netfilter/Kconfig               |  9 +++
 net/ipv6/netfilter/Makefile              |  1 +
 net/ipv6/netfilter/nft_redir_ipv6.c      | 77 +++++++++++++++++++++++++
 net/netfilter/Kconfig                    |  9 +++
 net/netfilter/Makefile                   |  1 +
 net/netfilter/nft_redir.c                | 98 ++++++++++++++++++++++++++++++++
 11 files changed, 319 insertions(+)
 create mode 100644 include/net/netfilter/nft_redir.h
 create mode 100644 net/ipv4/netfilter/nft_redir_ipv4.c
 create mode 100644 net/ipv6/netfilter/nft_redir_ipv6.c
 create mode 100644 net/netfilter/nft_redir.c

(limited to 'include')

diff --git a/include/net/netfilter/nft_redir.h b/include/net/netfilter/nft_redir.h
new file mode 100644
index 00000000000..a2d67546afa
--- /dev/null
+++ b/include/net/netfilter/nft_redir.h
@@ -0,0 +1,21 @@
+#ifndef _NFT_REDIR_H_
+#define _NFT_REDIR_H_
+
+struct nft_redir {
+	enum nft_registers	sreg_proto_min:8;
+	enum nft_registers	sreg_proto_max:8;
+	u16			flags;
+};
+
+extern const struct nla_policy nft_redir_policy[];
+
+int nft_redir_init(const struct nft_ctx *ctx,
+		   const struct nft_expr *expr,
+		   const struct nlattr * const tb[]);
+
+int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr);
+
+int nft_redir_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
+		       const struct nft_data **data);
+
+#endif /* _NFT_REDIR_H_ */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index f31fe7b660a..16f62a5cf04 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -837,6 +837,22 @@ enum nft_masq_attributes {
 };
 #define NFTA_MASQ_MAX		(__NFTA_MASQ_MAX - 1)
 
+/**
+ * enum nft_redir_attributes - nf_tables redirect expression netlink attributes
+ *
+ * @NFTA_REDIR_REG_PROTO_MIN: source register of proto range start (NLA_U32: nft_registers)
+ * @NFTA_REDIR_REG_PROTO_MAX: source register of proto range end (NLA_U32: nft_registers)
+ * @NFTA_REDIR_FLAGS: NAT flags (see NF_NAT_RANGE_* in linux/netfilter/nf_nat.h) (NLA_U32)
+ */
+enum nft_redir_attributes {
+	NFTA_REDIR_UNSPEC,
+	NFTA_REDIR_REG_PROTO_MIN,
+	NFTA_REDIR_REG_PROTO_MAX,
+	NFTA_REDIR_FLAGS,
+	__NFTA_REDIR_MAX
+};
+#define NFTA_REDIR_MAX		(__NFTA_REDIR_MAX - 1)
+
 /**
  * enum nft_gen_attributes - nf_tables ruleset generation attributes
  *
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index a300e2c32b2..8358b2da154 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -119,6 +119,15 @@ config NFT_MASQ_IPV4
 	  This is the expression that provides IPv4 masquerading support for
 	  nf_tables.
 
+config NFT_REDIR_IPV4
+	tristate "IPv4 redirect support for nf_tables"
+	depends on NF_TABLES_IPV4
+	depends on NFT_REDIR
+	select NF_NAT_REDIRECT_IPV4
+	help
+	  This is the expression that provides IPv4 redirect support for
+	  nf_tables.
+
 config NF_NAT_SNMP_BASIC
 	tristate "Basic SNMP-ALG support"
 	depends on NF_CONNTRACK_SNMP
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 34e436c9201..902bcd1597b 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
 obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
 obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o
+obj-$(CONFIG_NFT_REDIR_IPV4) += nft_redir_ipv4.o
 obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o
 
 # generic IP tables 
diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
new file mode 100644
index 00000000000..643c5967aa2
--- /dev/null
+++ b/net/ipv4/netfilter/nft_redir_ipv4.c
@@ -0,0 +1,77 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/ipv4/nf_nat_redirect.h>
+#include <net/netfilter/nft_redir.h>
+
+static void nft_redir_ipv4_eval(const struct nft_expr *expr,
+				struct nft_data data[NFT_REG_MAX + 1],
+				const struct nft_pktinfo *pkt)
+{
+	struct nft_redir *priv = nft_expr_priv(expr);
+	struct nf_nat_ipv4_multi_range_compat mr;
+	unsigned int verdict;
+
+	memset(&mr, 0, sizeof(mr));
+	if (priv->sreg_proto_min) {
+		mr.range[0].min.all = (__force __be16)
+					data[priv->sreg_proto_min].data[0];
+		mr.range[0].max.all = (__force __be16)
+					data[priv->sreg_proto_max].data[0];
+		mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+	}
+
+	mr.range[0].flags |= priv->flags;
+
+	verdict = nf_nat_redirect_ipv4(pkt->skb, &mr, pkt->ops->hooknum);
+	data[NFT_REG_VERDICT].verdict = verdict;
+}
+
+static struct nft_expr_type nft_redir_ipv4_type;
+static const struct nft_expr_ops nft_redir_ipv4_ops = {
+	.type		= &nft_redir_ipv4_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_redir)),
+	.eval		= nft_redir_ipv4_eval,
+	.init		= nft_redir_init,
+	.dump		= nft_redir_dump,
+	.validate	= nft_redir_validate,
+};
+
+static struct nft_expr_type nft_redir_ipv4_type __read_mostly = {
+	.family		= NFPROTO_IPV4,
+	.name		= "redir",
+	.ops		= &nft_redir_ipv4_ops,
+	.policy		= nft_redir_policy,
+	.maxattr	= NFTA_REDIR_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_redir_ipv4_module_init(void)
+{
+	return nft_register_expr(&nft_redir_ipv4_type);
+}
+
+static void __exit nft_redir_ipv4_module_exit(void)
+{
+	nft_unregister_expr(&nft_redir_ipv4_type);
+}
+
+module_init(nft_redir_ipv4_module_init);
+module_exit(nft_redir_ipv4_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "redir");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 462eebbf437..0dbe5c7953e 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -97,6 +97,15 @@ config NFT_MASQ_IPV6
 	  This is the expression that provides IPv4 masquerading support for
 	  nf_tables.
 
+config NFT_REDIR_IPV6
+	tristate "IPv6 redirect support for nf_tables"
+	depends on NF_TABLES_IPV6
+	depends on NFT_REDIR
+	select NF_NAT_REDIRECT_IPV6
+	help
+	  This is the expression that provides IPv4 redirect support for
+	  nf_tables.
+
 endif # NF_NAT_IPV6
 
 config IP6_NF_IPTABLES
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 6c2baab10f2..d2ac9f5f212 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -37,6 +37,7 @@ obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
 obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
 obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o
+obj-$(CONFIG_NFT_REDIR_IPV6) += nft_redir_ipv6.o
 
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c
new file mode 100644
index 00000000000..83420eeaad1
--- /dev/null
+++ b/net/ipv6/netfilter/nft_redir_ipv6.c
@@ -0,0 +1,77 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nft_redir.h>
+#include <net/netfilter/ipv6/nf_nat_redirect.h>
+
+static void nft_redir_ipv6_eval(const struct nft_expr *expr,
+				struct nft_data data[NFT_REG_MAX + 1],
+				const struct nft_pktinfo *pkt)
+{
+	struct nft_redir *priv = nft_expr_priv(expr);
+	struct nf_nat_range range;
+	unsigned int verdict;
+
+	memset(&range, 0, sizeof(range));
+	if (priv->sreg_proto_min) {
+		range.min_proto.all = (__force __be16)
+					data[priv->sreg_proto_min].data[0];
+		range.max_proto.all = (__force __be16)
+					data[priv->sreg_proto_max].data[0];
+		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+	}
+
+	range.flags |= priv->flags;
+
+	verdict = nf_nat_redirect_ipv6(pkt->skb, &range, pkt->ops->hooknum);
+	data[NFT_REG_VERDICT].verdict = verdict;
+}
+
+static struct nft_expr_type nft_redir_ipv6_type;
+static const struct nft_expr_ops nft_redir_ipv6_ops = {
+	.type		= &nft_redir_ipv6_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_redir)),
+	.eval		= nft_redir_ipv6_eval,
+	.init		= nft_redir_init,
+	.dump		= nft_redir_dump,
+	.validate	= nft_redir_validate,
+};
+
+static struct nft_expr_type nft_redir_ipv6_type __read_mostly = {
+	.family		= NFPROTO_IPV6,
+	.name		= "redir",
+	.ops		= &nft_redir_ipv6_ops,
+	.policy		= nft_redir_policy,
+	.maxattr	= NFTA_REDIR_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_redir_ipv6_module_init(void)
+{
+	return nft_register_expr(&nft_redir_ipv6_type);
+}
+
+static void __exit nft_redir_ipv6_module_exit(void)
+{
+	nft_unregister_expr(&nft_redir_ipv6_type);
+}
+
+module_init(nft_redir_ipv6_module_init);
+module_exit(nft_redir_ipv6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "redir");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 49deb4edbac..373486ae415 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -505,6 +505,15 @@ config NFT_MASQ
 	  This option adds the "masquerade" expression that you can use
 	  to perform NAT in the masquerade flavour.
 
+config NFT_REDIR
+	depends on NF_TABLES
+	depends on NF_CONNTRACK
+	depends on NF_NAT
+	tristate "Netfilter nf_tables redirect support"
+	help
+	  This options adds the "redirect" expression that you can use
+	  to perform NAT in the redirect flavour.
+
 config NFT_NAT
 	depends on NF_TABLES
 	depends on NF_CONNTRACK
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index a9571be3f79..f3eb4680f2e 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -88,6 +88,7 @@ obj-$(CONFIG_NFT_HASH)		+= nft_hash.o
 obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o
 obj-$(CONFIG_NFT_LOG)		+= nft_log.o
 obj-$(CONFIG_NFT_MASQ)		+= nft_masq.o
+obj-$(CONFIG_NFT_REDIR)		+= nft_redir.o
 
 # generic X tables 
 obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
new file mode 100644
index 00000000000..e27b4e35718
--- /dev/null
+++ b/net/netfilter/nft_redir.c
@@ -0,0 +1,98 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_redir.h>
+
+const struct nla_policy nft_redir_policy[NFTA_REDIR_MAX + 1] = {
+	[NFTA_REDIR_REG_PROTO_MIN]	= { .type = NLA_U32 },
+	[NFTA_REDIR_REG_PROTO_MAX]	= { .type = NLA_U32 },
+	[NFTA_REDIR_FLAGS]		= { .type = NLA_U32 },
+};
+EXPORT_SYMBOL_GPL(nft_redir_policy);
+
+int nft_redir_init(const struct nft_ctx *ctx,
+		   const struct nft_expr *expr,
+		   const struct nlattr * const tb[])
+{
+	struct nft_redir *priv = nft_expr_priv(expr);
+	u32 nla_be32;
+	int err;
+
+	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	if (err < 0)
+		return err;
+
+	if (tb[NFTA_REDIR_REG_PROTO_MIN]) {
+		nla_be32 = nla_get_be32(tb[NFTA_REDIR_REG_PROTO_MIN]);
+		priv->sreg_proto_min = ntohl(nla_be32);
+		err = nft_validate_input_register(priv->sreg_proto_min);
+		if (err < 0)
+			return err;
+
+		if (tb[NFTA_REDIR_REG_PROTO_MAX]) {
+			nla_be32 = nla_get_be32(tb[NFTA_REDIR_REG_PROTO_MAX]);
+			priv->sreg_proto_max = ntohl(nla_be32);
+			err = nft_validate_input_register(priv->sreg_proto_max);
+			if (err < 0)
+				return err;
+		} else {
+			priv->sreg_proto_max = priv->sreg_proto_min;
+		}
+	}
+
+	if (tb[NFTA_REDIR_FLAGS]) {
+		priv->flags = ntohl(nla_get_be32(tb[NFTA_REDIR_FLAGS]));
+		if (priv->flags & ~NF_NAT_RANGE_MASK)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_redir_init);
+
+int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_redir *priv = nft_expr_priv(expr);
+
+	if (priv->sreg_proto_min) {
+		if (nla_put_be32(skb, NFTA_REDIR_REG_PROTO_MIN,
+				 htonl(priv->sreg_proto_min)))
+			goto nla_put_failure;
+		if (nla_put_be32(skb, NFTA_REDIR_REG_PROTO_MAX,
+				 htonl(priv->sreg_proto_max)))
+			goto nla_put_failure;
+	}
+
+	if (priv->flags != 0 &&
+	    nla_put_be32(skb, NFTA_REDIR_FLAGS, htonl(priv->flags)))
+			goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+EXPORT_SYMBOL_GPL(nft_redir_dump);
+
+int nft_redir_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
+		       const struct nft_data **data)
+{
+	return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+}
+EXPORT_SYMBOL_GPL(nft_redir_validate);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
-- 
cgit v1.2.3-70-g09d2


From 958501163ddd6ea22a98f94fa0e7ce6d4734e5c4 Mon Sep 17 00:00:00 2001
From: Kyeyoon Park <kyeyoonp@codeaurora.org>
Date: Thu, 23 Oct 2014 14:49:17 -0700
Subject: bridge: Add support for IEEE 802.11 Proxy ARP

This feature is defined in IEEE Std 802.11-2012, 10.23.13. It allows
the AP devices to keep track of the hardware-address-to-IP-address
mapping of the mobile devices within the WLAN network.

The AP will learn this mapping via observing DHCP, ARP, and NS/NA
frames. When a request for such information is made (i.e. ARP request,
Neighbor Solicitation), the AP will respond on behalf of the
associated mobile device. In the process of doing so, the AP will drop
the multicast request frame that was intended to go out to the wireless
medium.

It was recommended at the LKS workshop to do this implementation in
the bridge layer. vxlan.c is already doing something very similar.
The DHCP snooping code will be added to the userspace application
(hostapd) per the recommendation.

This RFC commit is only for IPv4. A similar approach in the bridge
layer will be taken for IPv6 as well.

Signed-off-by: Kyeyoon Park <kyeyoonp@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_link.h |  1 +
 net/bridge/br_forward.c      |  5 ++++
 net/bridge/br_input.c        | 60 ++++++++++++++++++++++++++++++++++++++++++++
 net/bridge/br_netlink.c      |  4 ++-
 net/bridge/br_private.h      |  1 +
 net/bridge/br_sysfs_if.c     |  2 ++
 6 files changed, 72 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 0bdb77e1687..7072d832501 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -243,6 +243,7 @@ enum {
 	IFLA_BRPORT_FAST_LEAVE,	/* multicast fast leave    */
 	IFLA_BRPORT_LEARNING,	/* mac learning */
 	IFLA_BRPORT_UNICAST_FLOOD, /* flood unicast traffic */
+	IFLA_BRPORT_PROXYARP,	/* proxy ARP */
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 992ec49a96a..1510b54e6a2 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -183,6 +183,11 @@ static void br_flood(struct net_bridge *br, struct sk_buff *skb,
 		/* Do not flood unicast traffic to ports that turn it off */
 		if (unicast && !(p->flags & BR_FLOOD))
 			continue;
+
+		/* Do not flood to ports that enable proxy ARP */
+		if (p->flags & BR_PROXYARP)
+			continue;
+
 		prev = maybe_deliver(prev, p, skb, __packet_hook);
 		if (IS_ERR(prev))
 			goto out;
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 6fd5522df69..1f1de715197 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -16,6 +16,8 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/netfilter_bridge.h>
+#include <linux/neighbour.h>
+#include <net/arp.h>
 #include <linux/export.h>
 #include <linux/rculist.h>
 #include "br_private.h"
@@ -57,6 +59,60 @@ static int br_pass_frame_up(struct sk_buff *skb)
 		       netif_receive_skb);
 }
 
+static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br,
+			    u16 vid)
+{
+	struct net_device *dev = br->dev;
+	struct neighbour *n;
+	struct arphdr *parp;
+	u8 *arpptr, *sha;
+	__be32 sip, tip;
+
+	if (dev->flags & IFF_NOARP)
+		return;
+
+	if (!pskb_may_pull(skb, arp_hdr_len(dev))) {
+		dev->stats.tx_dropped++;
+		return;
+	}
+	parp = arp_hdr(skb);
+
+	if (parp->ar_pro != htons(ETH_P_IP) ||
+	    parp->ar_op != htons(ARPOP_REQUEST) ||
+	    parp->ar_hln != dev->addr_len ||
+	    parp->ar_pln != 4)
+		return;
+
+	arpptr = (u8 *)parp + sizeof(struct arphdr);
+	sha = arpptr;
+	arpptr += dev->addr_len;	/* sha */
+	memcpy(&sip, arpptr, sizeof(sip));
+	arpptr += sizeof(sip);
+	arpptr += dev->addr_len;	/* tha */
+	memcpy(&tip, arpptr, sizeof(tip));
+
+	if (ipv4_is_loopback(tip) ||
+	    ipv4_is_multicast(tip))
+		return;
+
+	n = neigh_lookup(&arp_tbl, &tip, dev);
+	if (n) {
+		struct net_bridge_fdb_entry *f;
+
+		if (!(n->nud_state & NUD_VALID)) {
+			neigh_release(n);
+			return;
+		}
+
+		f = __br_fdb_get(br, n->ha, vid);
+		if (f)
+			arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip,
+				 sha, n->ha, sha);
+
+		neigh_release(n);
+	}
+}
+
 /* note: already called with rcu_read_lock */
 int br_handle_frame_finish(struct sk_buff *skb)
 {
@@ -98,6 +154,10 @@ int br_handle_frame_finish(struct sk_buff *skb)
 	dst = NULL;
 
 	if (is_broadcast_ether_addr(dest)) {
+		if (p->flags & BR_PROXYARP &&
+		    skb->protocol == htons(ETH_P_ARP))
+			br_do_proxy_arp(skb, br, vid);
+
 		skb2 = skb;
 		unicast = false;
 	} else if (is_multicast_ether_addr(dest)) {
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 2ff9706647f..86c239b06f6 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -60,7 +60,8 @@ static int br_port_fill_attrs(struct sk_buff *skb,
 	    nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)) ||
 	    nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)) ||
 	    nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(p->flags & BR_LEARNING)) ||
-	    nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)))
+	    nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) ||
+	    nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)))
 		return -EMSGSIZE;
 
 	return 0;
@@ -332,6 +333,7 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 	br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK);
 	br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING);
 	br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD);
+	br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP);
 
 	if (tb[IFLA_BRPORT_COST]) {
 		err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST]));
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 4d783d07130..8f3f0814025 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -172,6 +172,7 @@ struct net_bridge_port
 #define BR_FLOOD		0x00000040
 #define BR_AUTO_MASK (BR_FLOOD | BR_LEARNING)
 #define BR_PROMISC		0x00000080
+#define BR_PROXYARP		0x00000100
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	struct bridge_mcast_own_query	ip4_own_query;
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index e561cd59b8a..2de5d91199e 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -170,6 +170,7 @@ BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD);
 BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK);
 BRPORT_ATTR_FLAG(learning, BR_LEARNING);
 BRPORT_ATTR_FLAG(unicast_flood, BR_FLOOD);
+BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP);
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)
@@ -213,6 +214,7 @@ static const struct brport_attribute *brport_attrs[] = {
 	&brport_attr_multicast_router,
 	&brport_attr_multicast_fast_leave,
 #endif
+	&brport_attr_proxyarp,
 	NULL
 };
 
-- 
cgit v1.2.3-70-g09d2


From 6dd98b0a3e58b7b48a422802b5610b95ef5128eb Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sat, 25 Oct 2014 17:41:59 +0200
Subject: ASoC: dapm: Introduce toplevel widget categories

DAPM widgets can be classified into four categories:
	* supply: Supply widgets do not affect the power state of their
		non-supply widget neighbors and unlike other widgets a
		supply widget is not powered up when it is on an active
		path, but when at least on of its neighbors is powered up.
	* source: A source is a widget that receives data from outside the
		DAPM graph or generates data. This can for example be a
		microphone, the playback DMA or a signal generator. A source
		widget will be considered powered up if there is an active
		path to a sink widget.
	* sink: A sink is a widget that transmits data to somewhere outside
		of the DAPM graph. This can e.g. be a speaker or the capture
		DMA. A sink widget will be considered powered up if there is
		an active path from a source widget.
	* normal: Normal widgets are widgets not covered by the categories
		above. A normal widget will be considered powered up if it
		is on an active path between a source widget and a sink
		widget.

The way the number of input and output paths for a widget is calculated
depends on its category. There are a bunch of factors which decide which
category a widget is. Currently there is no formal classification of these
categories and we calculate the category of the widget based on these
factors whenever we want to know it. This is at least once for every widget
during each power update sequence. The factors which determine the category
of the widgets are mostly static though and if at all change rather seldom.
This patch introduces three new per widget flags, one for each of non-normal
widgets categories. Instead of re-computing the category each time we want
to know them the flags will be checked. For the majority of widgets the
category is solely determined by the widget id, which means it never changes
and only has to be set once when the widget is created. The only widgets
with dynamic categories are:

	snd_soc_dapm_dai_out: Is considered a sink iff the capture stream is
		active, otherwise normal.
	snd_soc_dapm_dai_in: Is considered a source iff the playback stream
		is active, otherwise normal.
	snd_soc_dapm_input: Is considered a sink iff it has no outgoing
		paths, otherwise normal.
	snd_soc_dapm_output: Is considered a source iff it has no incoming
		paths, otherwise normal.
	snd_soc_dapm_line: Is considered a sink iff it has no outgoing paths
		and is considered a source iff it has no incoming paths,
		otherwise normal.

For snd_soc_dapm_dai_out/snd_soc_dapm_dai_in widgets the category will be
updated when a stream is started or stopped. For the other dynamic widgets
the category will be updated when a path connecting to it is added or
removed.

Introducing those new widget categories allows to make
is_connected_{output,input}_ep, which are among the hottest paths of the
DAPM algorithm, more generic and significantly shorter.

The before and after sizes for is_connected_{output,input}_ep are:

On ARM (defconfig + CONFIG_SND_SOC):
	function                                     old     new   delta
	is_connected_output_ep                       480     340    -140
	is_connected_input_ep                        456     352    -104

On amd64 (defconfig + CONFIG_SND_SOC):
	function                                     old     new   delta
	is_connected_output_ep                       579     427    -152
	is_connected_input_ep                        563     427    -136

Which is about a 25%-30% decrease, other architectures are expected to have
similar numbers. At the same time the size of the snd_soc_dapm_widget struct
does not change since the new flags are stored in the same word as the
existing flags.

Note: that since the per widget 'ext' flag was only used to decide whether a
snd_soc_dapm_input or snd_soc_dapm_output widget was a source or a sink it
is now unused and can be removed.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dapm.h |   4 +-
 sound/soc/soc-dapm.c     | 210 +++++++++++++++++++++--------------------------
 2 files changed, 95 insertions(+), 119 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index ebb93f29e4f..8cf3aad3086 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -543,11 +543,13 @@ struct snd_soc_dapm_widget {
 	unsigned char active:1;			/* active stream on DAC, ADC's */
 	unsigned char connected:1;		/* connected codec pin */
 	unsigned char new:1;			/* cnew complete */
-	unsigned char ext:1;			/* has external widgets */
 	unsigned char force:1;			/* force state */
 	unsigned char ignore_suspend:1;         /* kept enabled over suspend */
 	unsigned char new_power:1;		/* power from this run */
 	unsigned char power_checked:1;		/* power checked this run */
+	unsigned char is_supply:1;		/* Widget is a supply type widget */
+	unsigned char is_sink:1;		/* Widget is a sink type widget */
+	unsigned char is_source:1;		/* Widget is a source type widget */
 	int subseq;				/* sort within widget type */
 
 	int (*power_check)(struct snd_soc_dapm_widget *w);
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index c49df10d1c3..2cad5f77ec6 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -821,43 +821,12 @@ static int is_connected_output_ep(struct snd_soc_dapm_widget *widget,
 
 	DAPM_UPDATE_STAT(widget, path_checks);
 
-	switch (widget->id) {
-	case snd_soc_dapm_supply:
-	case snd_soc_dapm_regulator_supply:
-	case snd_soc_dapm_clock_supply:
-	case snd_soc_dapm_kcontrol:
+	if (widget->is_supply)
 		return 0;
-	default:
-		break;
-	}
 
-	switch (widget->id) {
-	case snd_soc_dapm_adc:
-	case snd_soc_dapm_aif_out:
-	case snd_soc_dapm_dai_out:
-		if (widget->active) {
-			widget->outputs = snd_soc_dapm_suspend_check(widget);
-			return widget->outputs;
-		}
-	default:
-		break;
-	}
-
-	if (widget->connected) {
-		/* connected pin ? */
-		if (widget->id == snd_soc_dapm_output && !widget->ext) {
-			widget->outputs = snd_soc_dapm_suspend_check(widget);
-			return widget->outputs;
-		}
-
-		/* connected jack or spk ? */
-		if (widget->id == snd_soc_dapm_hp ||
-		    widget->id == snd_soc_dapm_spk ||
-		    (widget->id == snd_soc_dapm_line &&
-		     !list_empty(&widget->sources))) {
-			widget->outputs = snd_soc_dapm_suspend_check(widget);
-			return widget->outputs;
-		}
+	if (widget->is_sink && widget->connected) {
+		widget->outputs = snd_soc_dapm_suspend_check(widget);
+		return widget->outputs;
 	}
 
 	list_for_each_entry(path, &widget->sinks, list_source) {
@@ -913,55 +882,12 @@ static int is_connected_input_ep(struct snd_soc_dapm_widget *widget,
 
 	DAPM_UPDATE_STAT(widget, path_checks);
 
-	switch (widget->id) {
-	case snd_soc_dapm_supply:
-	case snd_soc_dapm_regulator_supply:
-	case snd_soc_dapm_clock_supply:
-	case snd_soc_dapm_kcontrol:
+	if (widget->is_supply)
 		return 0;
-	default:
-		break;
-	}
-
-	/* active stream ? */
-	switch (widget->id) {
-	case snd_soc_dapm_dac:
-	case snd_soc_dapm_aif_in:
-	case snd_soc_dapm_dai_in:
-		if (widget->active) {
-			widget->inputs = snd_soc_dapm_suspend_check(widget);
-			return widget->inputs;
-		}
-	default:
-		break;
-	}
-
-	if (widget->connected) {
-		/* connected pin ? */
-		if (widget->id == snd_soc_dapm_input && !widget->ext) {
-			widget->inputs = snd_soc_dapm_suspend_check(widget);
-			return widget->inputs;
-		}
 
-		/* connected VMID/Bias for lower pops */
-		if (widget->id == snd_soc_dapm_vmid) {
-			widget->inputs = snd_soc_dapm_suspend_check(widget);
-			return widget->inputs;
-		}
-
-		/* connected jack ? */
-		if (widget->id == snd_soc_dapm_mic ||
-		    (widget->id == snd_soc_dapm_line &&
-		     !list_empty(&widget->sinks))) {
-			widget->inputs = snd_soc_dapm_suspend_check(widget);
-			return widget->inputs;
-		}
-
-		/* signal generator */
-		if (widget->id == snd_soc_dapm_siggen) {
-			widget->inputs = snd_soc_dapm_suspend_check(widget);
-			return widget->inputs;
-		}
+	if (widget->is_source && widget->connected) {
+		widget->inputs = snd_soc_dapm_suspend_check(widget);
+		return widget->inputs;
 	}
 
 	list_for_each_entry(path, &widget->sources, list_sink) {
@@ -1554,18 +1480,11 @@ static void dapm_widget_set_power(struct snd_soc_dapm_widget *w, bool power,
 	list_for_each_entry(path, &w->sources, list_sink)
 		dapm_widget_set_peer_power(path->source, power, path->connect);
 
-	switch (w->id) {
-	case snd_soc_dapm_supply:
-	case snd_soc_dapm_regulator_supply:
-	case snd_soc_dapm_clock_supply:
-	case snd_soc_dapm_kcontrol:
-		/* Supplies can't affect their outputs, only their inputs */
-		break;
-	default:
+	/* Supplies can't affect their outputs, only their inputs */
+	if (!w->is_supply) {
 		list_for_each_entry(path, &w->sinks, list_source)
 			dapm_widget_set_peer_power(path->sink, power,
 						   path->connect);
-		break;
 	}
 
 	if (power)
@@ -2226,6 +2145,53 @@ int snd_soc_dapm_sync(struct snd_soc_dapm_context *dapm)
 }
 EXPORT_SYMBOL_GPL(snd_soc_dapm_sync);
 
+/*
+ * dapm_update_widget_flags() - Re-compute widget sink and source flags
+ * @w: The widget for which to update the flags
+ *
+ * Some widgets have a dynamic category which depends on which neighbors they
+ * are connected to. This function update the category for these widgets.
+ *
+ * This function must be called whenever a path is added or removed to a widget.
+ */
+static void dapm_update_widget_flags(struct snd_soc_dapm_widget *w)
+{
+	struct snd_soc_dapm_path *p;
+
+	switch (w->id) {
+	case snd_soc_dapm_input:
+		w->is_source = 1;
+		list_for_each_entry(p, &w->sources, list_sink) {
+			if (p->source->id == snd_soc_dapm_micbias ||
+				p->source->id == snd_soc_dapm_mic ||
+				p->source->id == snd_soc_dapm_line ||
+				p->source->id == snd_soc_dapm_output) {
+					w->is_source = 0;
+					break;
+			}
+		}
+		break;
+	case snd_soc_dapm_output:
+		w->is_sink = 1;
+		list_for_each_entry(p, &w->sinks, list_source) {
+			if (p->sink->id == snd_soc_dapm_spk ||
+				p->sink->id == snd_soc_dapm_hp ||
+				p->sink->id == snd_soc_dapm_line ||
+				p->sink->id == snd_soc_dapm_input) {
+					w->is_sink = 0;
+					break;
+			}
+		}
+		break;
+	case snd_soc_dapm_line:
+		w->is_sink = !list_empty(&w->sources);
+		w->is_source = !list_empty(&w->sinks);
+		break;
+	default:
+		break;
+	}
+}
+
 static int snd_soc_dapm_add_path(struct snd_soc_dapm_context *dapm,
 	struct snd_soc_dapm_widget *wsource, struct snd_soc_dapm_widget *wsink,
 	const char *control,
@@ -2247,22 +2213,6 @@ static int snd_soc_dapm_add_path(struct snd_soc_dapm_context *dapm,
 	INIT_LIST_HEAD(&path->list_source);
 	INIT_LIST_HEAD(&path->list_sink);
 
-	/* check for external widgets */
-	if (wsink->id == snd_soc_dapm_input) {
-		if (wsource->id == snd_soc_dapm_micbias ||
-			wsource->id == snd_soc_dapm_mic ||
-			wsource->id == snd_soc_dapm_line ||
-			wsource->id == snd_soc_dapm_output)
-			wsink->ext = 1;
-	}
-	if (wsource->id == snd_soc_dapm_output) {
-		if (wsink->id == snd_soc_dapm_spk ||
-			wsink->id == snd_soc_dapm_hp ||
-			wsink->id == snd_soc_dapm_line ||
-			wsink->id == snd_soc_dapm_input)
-			wsource->ext = 1;
-	}
-
 	/* connect static paths */
 	if (control == NULL) {
 		path->connect = 1;
@@ -2294,6 +2244,9 @@ static int snd_soc_dapm_add_path(struct snd_soc_dapm_context *dapm,
 	list_add(&path->list_sink, &wsink->sources);
 	list_add(&path->list_source, &wsource->sinks);
 
+	dapm_update_widget_flags(wsource);
+	dapm_update_widget_flags(wsink);
+
 	dapm_mark_dirty(wsource, "Route added");
 	dapm_mark_dirty(wsink, "Route added");
 
@@ -2377,6 +2330,7 @@ err:
 static int snd_soc_dapm_del_route(struct snd_soc_dapm_context *dapm,
 				  const struct snd_soc_dapm_route *route)
 {
+	struct snd_soc_dapm_widget *wsource, *wsink;
 	struct snd_soc_dapm_path *path, *p;
 	const char *sink;
 	const char *source;
@@ -2414,10 +2368,17 @@ static int snd_soc_dapm_del_route(struct snd_soc_dapm_context *dapm,
 	}
 
 	if (path) {
-		dapm_mark_dirty(path->source, "Route removed");
-		dapm_mark_dirty(path->sink, "Route removed");
+		wsource = path->source;
+		wsink = path->sink;
+
+		dapm_mark_dirty(wsource, "Route removed");
+		dapm_mark_dirty(wsink, "Route removed");
 
 		dapm_free_path(path);
+
+		/* Update any path related flags */
+		dapm_update_widget_flags(wsource);
+		dapm_update_widget_flags(wsink);
 	} else {
 		dev_warn(dapm->dev, "ASoC: Route %s->%s does not exist\n",
 			 source, sink);
@@ -2975,26 +2936,33 @@ snd_soc_dapm_new_control(struct snd_soc_dapm_context *dapm,
 	}
 
 	switch (w->id) {
-	case snd_soc_dapm_switch:
-	case snd_soc_dapm_mixer:
-	case snd_soc_dapm_mixer_named_ctl:
+	case snd_soc_dapm_mic:
+	case snd_soc_dapm_input:
+		w->is_source = 1;
 		w->power_check = dapm_generic_check_power;
 		break;
-	case snd_soc_dapm_mux:
+	case snd_soc_dapm_spk:
+	case snd_soc_dapm_hp:
+	case snd_soc_dapm_output:
+		w->is_sink = 1;
 		w->power_check = dapm_generic_check_power;
 		break;
+	case snd_soc_dapm_vmid:
+	case snd_soc_dapm_siggen:
+		w->is_source = 1;
+		w->power_check = dapm_always_on_check_power;
+		break;
+	case snd_soc_dapm_mux:
+	case snd_soc_dapm_switch:
+	case snd_soc_dapm_mixer:
+	case snd_soc_dapm_mixer_named_ctl:
 	case snd_soc_dapm_adc:
 	case snd_soc_dapm_aif_out:
 	case snd_soc_dapm_dac:
 	case snd_soc_dapm_aif_in:
 	case snd_soc_dapm_pga:
 	case snd_soc_dapm_out_drv:
-	case snd_soc_dapm_input:
-	case snd_soc_dapm_output:
 	case snd_soc_dapm_micbias:
-	case snd_soc_dapm_spk:
-	case snd_soc_dapm_hp:
-	case snd_soc_dapm_mic:
 	case snd_soc_dapm_line:
 	case snd_soc_dapm_dai_link:
 	case snd_soc_dapm_dai_out:
@@ -3005,6 +2973,7 @@ snd_soc_dapm_new_control(struct snd_soc_dapm_context *dapm,
 	case snd_soc_dapm_regulator_supply:
 	case snd_soc_dapm_clock_supply:
 	case snd_soc_dapm_kcontrol:
+		w->is_supply = 1;
 		w->power_check = dapm_supply_check_power;
 		break;
 	default:
@@ -3368,6 +3337,11 @@ static void soc_dapm_dai_stream_event(struct snd_soc_dai *dai, int stream,
 		case SND_SOC_DAPM_STREAM_PAUSE_RELEASE:
 			break;
 		}
+
+		if (w->id == snd_soc_dapm_dai_in)
+			w->is_source = w->active;
+		else
+			w->is_sink = w->active;
 	}
 }
 
-- 
cgit v1.2.3-70-g09d2


From c1862c8bae520a8986dd7c47ce33f16eb7c791c2 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sat, 25 Oct 2014 17:42:00 +0200
Subject: ASoC: dapm: Add a flag to mark paths connected to supply widgets

Supply widgets do not count towards the input and output widgets of their
neighbors and for supply widgets themselves we do not care for the number
of input or output paths. This means that a path that connects to a supply
widget effectively behaves the same as a path that as the weak property set.
This patch adds a new path flag that gets set to true when the path is
connected to at least one supply widget. If a path with the flag set is
encountered in is_connected_{input,output}_ep() is is skipped in the same
way that weak paths are skipped. This slightly brings down the number of
path checks.

Since both the weak and the supply flag are implemented as bitfields which
are stored in the same word there is no runtime overhead due to checking
both rather than just one and also the size of the path struct is not
increased by this patch. Another advantage is that we do not have to handle
supply widgets in is_connected_{input,output}_ep() anymore since it will
never be called for supply widgets. The only exception is from
dapm_widget_power_read_file() where a check is added to special case supply
widgets.

Testing with the ADAU1761, which has a handful of supply widgets, shows the
following changes in the DAPM stats for a playback stream start.

         Power  Path  Neighbour
Before:  34     78    117
After:   34     48    117

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dapm.h |  1 +
 sound/soc/soc-dapm.c     | 23 +++++++++++++----------
 2 files changed, 14 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 8cf3aad3086..e7ebeb71748 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -510,6 +510,7 @@ struct snd_soc_dapm_path {
 	u32 connect:1;	/* source and sink widgets are connected */
 	u32 walking:1;  /* path is in the process of being walked */
 	u32 weak:1;	/* path ignored for power management */
+	u32 is_supply:1;	/* At least one of the connected widgets is a supply */
 
 	int (*connected)(struct snd_soc_dapm_widget *source,
 			 struct snd_soc_dapm_widget *sink);
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 2cad5f77ec6..d89be153a9e 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -821,9 +821,6 @@ static int is_connected_output_ep(struct snd_soc_dapm_widget *widget,
 
 	DAPM_UPDATE_STAT(widget, path_checks);
 
-	if (widget->is_supply)
-		return 0;
-
 	if (widget->is_sink && widget->connected) {
 		widget->outputs = snd_soc_dapm_suspend_check(widget);
 		return widget->outputs;
@@ -832,7 +829,7 @@ static int is_connected_output_ep(struct snd_soc_dapm_widget *widget,
 	list_for_each_entry(path, &widget->sinks, list_source) {
 		DAPM_UPDATE_STAT(widget, neighbour_checks);
 
-		if (path->weak)
+		if (path->weak || path->is_supply)
 			continue;
 
 		if (path->walking)
@@ -882,9 +879,6 @@ static int is_connected_input_ep(struct snd_soc_dapm_widget *widget,
 
 	DAPM_UPDATE_STAT(widget, path_checks);
 
-	if (widget->is_supply)
-		return 0;
-
 	if (widget->is_source && widget->connected) {
 		widget->inputs = snd_soc_dapm_suspend_check(widget);
 		return widget->inputs;
@@ -893,7 +887,7 @@ static int is_connected_input_ep(struct snd_soc_dapm_widget *widget,
 	list_for_each_entry(path, &widget->sources, list_sink) {
 		DAPM_UPDATE_STAT(widget, neighbour_checks);
 
-		if (path->weak)
+		if (path->weak || path->is_supply)
 			continue;
 
 		if (path->walking)
@@ -1691,8 +1685,14 @@ static ssize_t dapm_widget_power_read_file(struct file *file,
 	if (!buf)
 		return -ENOMEM;
 
-	in = is_connected_input_ep(w, NULL);
-	out = is_connected_output_ep(w, NULL);
+	/* Supply widgets are not handled by is_connected_{input,output}_ep() */
+	if (w->is_supply) {
+		in = 0;
+		out = 0;
+	} else {
+		in = is_connected_input_ep(w, NULL);
+		out = is_connected_output_ep(w, NULL);
+	}
 
 	ret = snprintf(buf, PAGE_SIZE, "%s: %s%s  in %d out %d",
 		       w->name, w->power ? "On" : "Off",
@@ -2213,6 +2213,9 @@ static int snd_soc_dapm_add_path(struct snd_soc_dapm_context *dapm,
 	INIT_LIST_HEAD(&path->list_source);
 	INIT_LIST_HEAD(&path->list_sink);
 
+	if (wsource->is_supply || wsink->is_supply)
+		path->is_supply = 1;
+
 	/* connect static paths */
 	if (control == NULL) {
 		path->connect = 1;
-- 
cgit v1.2.3-70-g09d2


From 8be4da29cf5b8ec65e974c36e7ae4d90b381ac5e Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sat, 25 Oct 2014 17:42:01 +0200
Subject: ASoC: dapm: Mark endpoints instead of IO widgets dirty during
 suspend/resume

The state of endpoint widgets is affected by that card's power state.
Endpoint widgets that do no have the ignore_suspend flag set will be
considered inactive during suspend. So they have to be re-checked and marked
dirty after the card's power state changes. Currently the input and output
widgets are marked dirty instead, this works most of the time since
typically a path from one endpoint to another will go via a input or output
widget. But marking the endpoints dirty is technically more correct and will
also work for odd corner cases.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dapm.h |  2 +-
 sound/soc/soc-core.c     |  8 ++++----
 sound/soc/soc-dapm.c     | 15 ++++-----------
 3 files changed, 9 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index e7ebeb71748..43ca1656dab 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -435,7 +435,7 @@ void snd_soc_dapm_auto_nc_pins(struct snd_soc_card *card);
 unsigned int dapm_kcontrol_get_value(const struct snd_kcontrol *kcontrol);
 
 /* Mostly internal - should not normally be used */
-void dapm_mark_io_dirty(struct snd_soc_dapm_context *dapm);
+void dapm_mark_endpoints_dirty(struct snd_soc_card *card);
 
 /* dapm path query */
 int snd_soc_dapm_dai_get_connected_widgets(struct snd_soc_dai *dai, int stream,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 4c8f8a23a0e..443be006112 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -629,8 +629,8 @@ int snd_soc_suspend(struct device *dev)
 					  SND_SOC_DAPM_STREAM_SUSPEND);
 	}
 
-	/* Recheck all analogue paths too */
-	dapm_mark_io_dirty(&card->dapm);
+	/* Recheck all endpoints too, their state is affected by suspend */
+	dapm_mark_endpoints_dirty(card);
 	snd_soc_dapm_sync(&card->dapm);
 
 	/* suspend all CODECs */
@@ -796,8 +796,8 @@ static void soc_resume_deferred(struct work_struct *work)
 	/* userspace can access us now we are back as we were before */
 	snd_power_change_state(card->snd_card, SNDRV_CTL_POWER_D0);
 
-	/* Recheck all analogue paths too */
-	dapm_mark_io_dirty(&card->dapm);
+	/* Recheck all endpoints too, their state is affected by suspend */
+	dapm_mark_endpoints_dirty(card);
 	snd_soc_dapm_sync(&card->dapm);
 }
 
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index d89be153a9e..ffcda7ecd83 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -159,27 +159,20 @@ static void dapm_mark_dirty(struct snd_soc_dapm_widget *w, const char *reason)
 	}
 }
 
-void dapm_mark_io_dirty(struct snd_soc_dapm_context *dapm)
+void dapm_mark_endpoints_dirty(struct snd_soc_card *card)
 {
-	struct snd_soc_card *card = dapm->card;
 	struct snd_soc_dapm_widget *w;
 
 	mutex_lock(&card->dapm_mutex);
 
 	list_for_each_entry(w, &card->widgets, list) {
-		switch (w->id) {
-		case snd_soc_dapm_input:
-		case snd_soc_dapm_output:
-			dapm_mark_dirty(w, "Rechecking inputs and outputs");
-			break;
-		default:
-			break;
-		}
+		if (w->is_sink || w->is_source)
+			dapm_mark_dirty(w, "Rechecking endpoints");
 	}
 
 	mutex_unlock(&card->dapm_mutex);
 }
-EXPORT_SYMBOL_GPL(dapm_mark_io_dirty);
+EXPORT_SYMBOL_GPL(dapm_mark_endpoints_dirty);
 
 /* create a new dapm widget */
 static inline struct snd_soc_dapm_widget *dapm_cnew_widget(
-- 
cgit v1.2.3-70-g09d2


From 92a99ea439c4e27fc6e32eb6d51c5d091c6084bd Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sat, 25 Oct 2014 17:42:03 +0200
Subject: ASoC: dapm: Use more aggressive caching

Currently we cache the number of input and output paths going to/from a
widget only within a power update sequence. But not in between power update
sequences.

But we know how changes to the DAPM graph affect the number of input (form a
source) and output (to a sink) paths of a widget and only need to
recalculate them if a operation has been performed that might have changed
them.
	* Adding/removing or connecting/disconnecting a path means that the for
	  the source of the path the number of output paths can change and for
	  the sink the number of input paths can change.
	* Connecting/disconnecting a widget has the same effect has connecting/
	  disconnecting all paths of the widget. So for the widget itself the
	  number of inputs and outputs can change, for all sinks of the widget
	  the number of inputs can change and for all sources of the widget the
	  number of outputs can change.
	* Activating/Deactivating a stream can either change the number of
	  outputs on the sources of the widget associated with the stream or the
	  number of inputs on the sinks.

Instead of always invalidating all cached numbers of input and output paths
for each power up or down sequence this patch restructures the code to only
invalidate the cached numbers when a operation that might change them has
been performed. This can greatly reduce the number of DAPM power checks for
some very common operations.

Since per DAPM operation typically only either change the number of inputs
or outputs the number of path checks is reduced by at least 50%. The number
of neighbor checks is also reduced about the same percentage, but since the
number of neighbors encountered when walking from sink to source is not the
same as when walking from source to sink the actual numbers will slightly
vary from card to card (e.g. for a mixer we see 1 neighbor when walking from
source to sink, but the number of inputs neighbors when walking from source
to sink).

Bigger improvements can be observed for widgets with multiple connected
inputs and output (e.g. mixers probably being the most widespread form of
this). Previously we had to re-calculate the number of inputs and outputs
on all input and output paths. With this change we only have to re-calculate
the number of outputs on the input path that got changed and the number of
inputs on the output paths.

E.g. imagine the following example:

	A --> B ----.
	            v
	M --> N --> Z <-- S <-- R
	            |
	            v
	            X

Widget Z has multiple input paths, if any change was made that cause Z to be
marked as dirty the power state of Z has to be re-computed. This requires to
know the number of inputs and outputs of Z, which requires to know the
number of inputs and outputs of all widgets on all paths from or to Z.
Previously this meant re-computing all inputs and outputs of all the path
going into or out of Z. With this patch in place only paths that actually
have changed need to be re-computed.

If the system is idle (or the part of the system affected by the changed
path) the number of path checks drops to either 0 or 1, regardless of how
large or complex the DAPM context is. 0 if there is no connected sink and no
connected source. 1 if there is either a connected source or sink, but not
both. The number of neighbor checks again will scale accordingly and will be
a constant number that is the number of inputs or outputs of the widget for
which we did the path check.

When loading a state file or switching between different profiles typically
multiple mixer and mux settings are changed, so we see the benefit of this
patch multiplied for these kinds of operations.

Testing with the ADAU1761 shows the following changes in DAPM stats for
changing a single Mixer switch for a Mixer with 5 inputs while the DAPM
context is idle.

         Power  Path  Neighbour
Before:  2      12    30
After:   2       1     2

For the same switch, but with a active playback stream the stat changed are
as follows.

         Power  Path  Neighbour
Before:  10     20    54
After:   10      7    21

Cumulative numbers for switching the audio profile which changes 7 controls
while the system is idle:

         Power  Path  Neighbour
Before:  16      80   170
After:   16       7    23

Cumulative numbers for switching the audio profile which changes 7 controls
while playback is active:

         Power  Path  Neighbour
Before:  51     123   273
After:   51      29   109

Starting (or stopping) the playback stream:

         Power  Path  Neighbour
Before:  34     34    117
After:   34     17    69

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dapm.h |   1 +
 sound/soc/soc-dapm.c     | 161 ++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 154 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 43ca1656dab..89823cfe6f0 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -569,6 +569,7 @@ struct snd_soc_dapm_widget {
 	struct list_head sinks;
 
 	/* used during DAPM updates */
+	struct list_head work_list;
 	struct list_head power_list;
 	struct list_head dirty;
 	int inputs;
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 8e26c2bc7fd..6bf2c9795df 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -159,6 +159,116 @@ static void dapm_mark_dirty(struct snd_soc_dapm_widget *w, const char *reason)
 	}
 }
 
+/*
+ * dapm_widget_invalidate_input_paths() - Invalidate the cached number of input
+ *  paths
+ * @w: The widget for which to invalidate the cached number of input paths
+ *
+ * The function resets the cached number of inputs for the specified widget and
+ * all widgets that can be reached via outgoing paths from the widget.
+ *
+ * This function must be called if the number of input paths for a widget might
+ * have changed. E.g. if the source state of a widget changes or a path is added
+ * or activated with the widget as the sink.
+ */
+static void dapm_widget_invalidate_input_paths(struct snd_soc_dapm_widget *w)
+{
+	struct snd_soc_dapm_widget *sink;
+	struct snd_soc_dapm_path *p;
+	LIST_HEAD(list);
+
+	dapm_assert_locked(w->dapm);
+
+	if (w->inputs == -1)
+		return;
+
+	w->inputs = -1;
+	list_add_tail(&w->work_list, &list);
+
+	list_for_each_entry(w, &list, work_list) {
+		list_for_each_entry(p, &w->sinks, list_source) {
+			if (p->is_supply || p->weak || !p->connect)
+				continue;
+			sink = p->sink;
+			if (sink->inputs != -1) {
+				sink->inputs = -1;
+				list_add_tail(&sink->work_list, &list);
+			}
+		}
+	}
+}
+
+/*
+ * dapm_widget_invalidate_output_paths() - Invalidate the cached number of
+ *  output paths
+ * @w: The widget for which to invalidate the cached number of output paths
+ *
+ * Resets the cached number of outputs for the specified widget and all widgets
+ * that can be reached via incoming paths from the widget.
+ *
+ * This function must be called if the number of output paths for a widget might
+ * have changed. E.g. if the sink state of a widget changes or a path is added
+ * or activated with the widget as the source.
+ */
+static void dapm_widget_invalidate_output_paths(struct snd_soc_dapm_widget *w)
+{
+	struct snd_soc_dapm_widget *source;
+	struct snd_soc_dapm_path *p;
+	LIST_HEAD(list);
+
+	dapm_assert_locked(w->dapm);
+
+	if (w->outputs == -1)
+		return;
+
+	w->outputs = -1;
+	list_add_tail(&w->work_list, &list);
+
+	list_for_each_entry(w, &list, work_list) {
+		list_for_each_entry(p, &w->sources, list_sink) {
+			if (p->is_supply || p->weak || !p->connect)
+				continue;
+			source = p->source;
+			if (source->outputs != -1) {
+				source->outputs = -1;
+				list_add_tail(&source->work_list, &list);
+			}
+		}
+	}
+}
+
+/*
+ * dapm_path_invalidate() - Invalidates the cached number of inputs and outputs
+ *  for the widgets connected to a path
+ * @p: The path to invalidate
+ *
+ * Resets the cached number of inputs for the sink of the path and the cached
+ * number of outputs for the source of the path.
+ *
+ * This function must be called when a path is added, removed or the connected
+ * state changes.
+ */
+static void dapm_path_invalidate(struct snd_soc_dapm_path *p)
+{
+	/*
+	 * Weak paths or supply paths do not influence the number of input or
+	 * output paths of their neighbors.
+	 */
+	if (p->weak || p->is_supply)
+		return;
+
+	/*
+	 * The number of connected endpoints is the sum of the number of
+	 * connected endpoints of all neighbors. If a node with 0 connected
+	 * endpoints is either connected or disconnected that sum won't change,
+	 * so there is no need to re-check the path.
+	 */
+	if (p->source->inputs != 0)
+		dapm_widget_invalidate_input_paths(p->sink);
+	if (p->sink->outputs != 0)
+		dapm_widget_invalidate_output_paths(p->source);
+}
+
 void dapm_mark_endpoints_dirty(struct snd_soc_card *card)
 {
 	struct snd_soc_dapm_widget *w;
@@ -166,8 +276,13 @@ void dapm_mark_endpoints_dirty(struct snd_soc_card *card)
 	mutex_lock(&card->dapm_mutex);
 
 	list_for_each_entry(w, &card->widgets, list) {
-		if (w->is_sink || w->is_source)
+		if (w->is_sink || w->is_source) {
 			dapm_mark_dirty(w, "Rechecking endpoints");
+			if (w->is_sink)
+				dapm_widget_invalidate_output_paths(w);
+			if (w->is_source)
+				dapm_widget_invalidate_input_paths(w);
+		}
 	}
 
 	mutex_unlock(&card->dapm_mutex);
@@ -379,8 +494,6 @@ static void dapm_reset(struct snd_soc_card *card)
 	list_for_each_entry(w, &card->widgets, list) {
 		w->new_power = w->power;
 		w->power_checked = false;
-		w->inputs = -1;
-		w->outputs = -1;
 	}
 }
 
@@ -931,10 +1044,19 @@ int snd_soc_dapm_dai_get_connected_widgets(struct snd_soc_dai *dai, int stream,
 	struct snd_soc_dapm_widget_list **list)
 {
 	struct snd_soc_card *card = dai->card;
+	struct snd_soc_dapm_widget *w;
 	int paths;
 
 	mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
-	dapm_reset(card);
+
+	/*
+	 * For is_connected_{output,input}_ep fully discover the graph we need
+	 * to reset the cached number of inputs and outputs.
+	 */
+	list_for_each_entry(w, &card->widgets, list) {
+		w->inputs = -1;
+		w->outputs = -1;
+	}
 
 	if (stream == SNDRV_PCM_STREAM_PLAYBACK)
 		paths = is_connected_output_ep(dai->playback_widget, list);
@@ -1846,6 +1968,7 @@ static void soc_dapm_connect_path(struct snd_soc_dapm_path *path,
 	path->connect = connect;
 	dapm_mark_dirty(path->source, reason);
 	dapm_mark_dirty(path->sink, reason);
+	dapm_path_invalidate(path);
 }
 
 /* test and update the power status of a mux widget */
@@ -2084,8 +2207,11 @@ static int snd_soc_dapm_set_pin(struct snd_soc_dapm_context *dapm,
 		return -EINVAL;
 	}
 
-	if (w->connected != status)
+	if (w->connected != status) {
 		dapm_mark_dirty(w, "pin configuration");
+		dapm_widget_invalidate_input_paths(w);
+		dapm_widget_invalidate_output_paths(w);
+	}
 
 	w->connected = status;
 	if (status == 0)
@@ -2267,6 +2393,9 @@ static int snd_soc_dapm_add_path(struct snd_soc_dapm_context *dapm,
 	dapm_mark_dirty(wsource, "Route added");
 	dapm_mark_dirty(wsink, "Route added");
 
+	if (dapm->card->instantiated && path->connect)
+		dapm_path_invalidate(path);
+
 	return 0;
 err:
 	kfree(path);
@@ -2390,6 +2519,8 @@ static int snd_soc_dapm_del_route(struct snd_soc_dapm_context *dapm,
 
 		dapm_mark_dirty(wsource, "Route removed");
 		dapm_mark_dirty(wsink, "Route removed");
+		if (path->connect)
+			dapm_path_invalidate(path);
 
 		dapm_free_path(path);
 
@@ -3007,6 +3138,9 @@ snd_soc_dapm_new_control(struct snd_soc_dapm_context *dapm,
 	INIT_LIST_HEAD(&w->dirty);
 	list_add(&w->list, &dapm->card->widgets);
 
+	w->inputs = -1;
+	w->outputs = -1;
+
 	/* machine layer set ups unconnected pins and insertions */
 	w->connected = 1;
 	return w;
@@ -3355,10 +3489,13 @@ static void soc_dapm_dai_stream_event(struct snd_soc_dai *dai, int stream,
 			break;
 		}
 
-		if (w->id == snd_soc_dapm_dai_in)
+		if (w->id == snd_soc_dapm_dai_in) {
 			w->is_source = w->active;
-		else
+			dapm_widget_invalidate_input_paths(w);
+		} else {
 			w->is_sink = w->active;
+			dapm_widget_invalidate_output_paths(w);
+		}
 	}
 }
 
@@ -3485,7 +3622,15 @@ int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
 	}
 
 	dev_dbg(w->dapm->dev, "ASoC: force enable pin %s\n", pin);
-	w->connected = 1;
+	if (!w->connected) {
+		/*
+		 * w->force does not affect the number of input or output paths,
+		 * so we only have to recheck if w->connected is changed
+		 */
+		dapm_widget_invalidate_input_paths(w);
+		dapm_widget_invalidate_output_paths(w);
+		w->connected = 1;
+	}
 	w->force = 1;
 	dapm_mark_dirty(w, "force enable");
 
-- 
cgit v1.2.3-70-g09d2


From c1b4d1c7774189002bc08766ec10e339dfbc98d6 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sat, 25 Oct 2014 20:25:56 +0200
Subject: ASoC: Use generic control handlers for S8 control

Commit f227b88f0fce ("ASoC: core: Add signed register volume control logic")
added support for signed control to the generic volsw control handler.
This makes it possible to use them for the S8 control as well, rather than
having to use a custom control handler implementation.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  | 19 +++++-------
 sound/soc/soc-core.c | 87 ----------------------------------------------------
 2 files changed, 8 insertions(+), 98 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 7ba7130037a..ad47e9660b2 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -36,6 +36,11 @@
 	{.reg = xreg, .rreg = xreg, .shift = shift_left, \
 	.rshift = shift_right, .max = xmax, .platform_max = xmax, \
 	.invert = xinvert, .autodisable = xautodisable})
+#define SOC_DOUBLE_S_VALUE(xreg, shift_left, shift_right, xmin, xmax, xsign_bit, xinvert, xautodisable) \
+	((unsigned long)&(struct soc_mixer_control) \
+	{.reg = xreg, .rreg = xreg, .shift = shift_left, \
+	.rshift = shift_right, .min = xmin, .max = xmax, .platform_max = xmax, \
+	.sign_bit = xsign_bit, .invert = xinvert, .autodisable = xautodisable})
 #define SOC_SINGLE_VALUE(xreg, xshift, xmax, xinvert, xautodisable) \
 	SOC_DOUBLE_VALUE(xreg, xshift, xshift, xmax, xinvert, xautodisable)
 #define SOC_SINGLE_VALUE_EXT(xreg, xmax, xinvert) \
@@ -171,11 +176,9 @@
 	.access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | \
 		  SNDRV_CTL_ELEM_ACCESS_READWRITE, \
 	.tlv.p  = (tlv_array), \
-	.info   = snd_soc_info_volsw_s8, .get = snd_soc_get_volsw_s8, \
-	.put    = snd_soc_put_volsw_s8, \
-	.private_value = (unsigned long)&(struct soc_mixer_control) \
-		{.reg = xreg, .min = xmin, .max = xmax, \
-		 .platform_max = xmax} }
+	.info = snd_soc_info_volsw, .get = snd_soc_get_volsw,\
+	.put = snd_soc_put_volsw, \
+	.private_value = SOC_DOUBLE_S_VALUE(xreg, 0, 8, xmin, xmax, 7, 0, 0) }
 #define SOC_ENUM_DOUBLE(xreg, xshift_l, xshift_r, xitems, xtexts) \
 {	.reg = xreg, .shift_l = xshift_l, .shift_r = xshift_r, \
 	.items = xitems, .texts = xtexts, \
@@ -545,12 +548,6 @@ int snd_soc_get_volsw_sx(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol);
 int snd_soc_put_volsw_sx(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol);
-int snd_soc_info_volsw_s8(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_info *uinfo);
-int snd_soc_get_volsw_s8(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_value *ucontrol);
-int snd_soc_put_volsw_s8(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_value *ucontrol);
 int snd_soc_info_volsw_range(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_info *uinfo);
 int snd_soc_put_volsw_range(struct snd_kcontrol *kcontrol,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 96ecdc30eb6..47c378abb9a 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2720,93 +2720,6 @@ int snd_soc_put_volsw_sx(struct snd_kcontrol *kcontrol,
 }
 EXPORT_SYMBOL_GPL(snd_soc_put_volsw_sx);
 
-/**
- * snd_soc_info_volsw_s8 - signed mixer info callback
- * @kcontrol: mixer control
- * @uinfo: control element information
- *
- * Callback to provide information about a signed mixer control.
- *
- * Returns 0 for success.
- */
-int snd_soc_info_volsw_s8(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_info *uinfo)
-{
-	struct soc_mixer_control *mc =
-		(struct soc_mixer_control *)kcontrol->private_value;
-	int platform_max;
-	int min = mc->min;
-
-	if (!mc->platform_max)
-		mc->platform_max = mc->max;
-	platform_max = mc->platform_max;
-
-	uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
-	uinfo->count = 2;
-	uinfo->value.integer.min = 0;
-	uinfo->value.integer.max = platform_max - min;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_soc_info_volsw_s8);
-
-/**
- * snd_soc_get_volsw_s8 - signed mixer get callback
- * @kcontrol: mixer control
- * @ucontrol: control element information
- *
- * Callback to get the value of a signed mixer control.
- *
- * Returns 0 for success.
- */
-int snd_soc_get_volsw_s8(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_value *ucontrol)
-{
-	struct soc_mixer_control *mc =
-		(struct soc_mixer_control *)kcontrol->private_value;
-	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
-	unsigned int reg = mc->reg;
-	unsigned int val;
-	int min = mc->min;
-	int ret;
-
-	ret = snd_soc_component_read(component, reg, &val);
-	if (ret)
-		return ret;
-
-	ucontrol->value.integer.value[0] =
-		((signed char)(val & 0xff))-min;
-	ucontrol->value.integer.value[1] =
-		((signed char)((val >> 8) & 0xff))-min;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_soc_get_volsw_s8);
-
-/**
- * snd_soc_put_volsw_sgn - signed mixer put callback
- * @kcontrol: mixer control
- * @ucontrol: control element information
- *
- * Callback to set the value of a signed mixer control.
- *
- * Returns 0 for success.
- */
-int snd_soc_put_volsw_s8(struct snd_kcontrol *kcontrol,
-	struct snd_ctl_elem_value *ucontrol)
-{
-	struct soc_mixer_control *mc =
-		(struct soc_mixer_control *)kcontrol->private_value;
-	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
-	unsigned int reg = mc->reg;
-	int min = mc->min;
-	unsigned int val;
-
-	val = (ucontrol->value.integer.value[0]+min) & 0xff;
-	val |= ((ucontrol->value.integer.value[1]+min) & 0xff) << 8;
-
-	return snd_soc_component_update_bits(component, reg, 0xffff, val);
-}
-EXPORT_SYMBOL_GPL(snd_soc_put_volsw_s8);
-
 /**
  * snd_soc_info_volsw_range - single mixer info callback with range.
  * @kcontrol: mixer control
-- 
cgit v1.2.3-70-g09d2


From 8f9fbf092cd0ae31722b42c9abb427a87d55c18a Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 7 Oct 2014 21:51:08 +0200
Subject: sched: Fix the PREEMPT_ACTIVE check in __trace_sched_switch_state()

task_preempt_count() has nothing to do with the actual preempt counter,
thread_info->saved_preempt_count is only valid right after switch_to().

__trace_sched_switch_state() can use preempt_count(), prev is still the
current task when trace_sched_switch() is called.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
[ Added BUG_ON(). ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20141007195108.GB28002@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/trace/events/sched.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 0a68d5ae584..30fedaf3e56 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -97,16 +97,19 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
 	long state = p->state;
 
 #ifdef CONFIG_PREEMPT
+#ifdef CONFIG_SCHED_DEBUG
+	BUG_ON(p != current);
+#endif /* CONFIG_SCHED_DEBUG */
 	/*
 	 * For all intents and purposes a preempted task is a running task.
 	 */
-	if (task_preempt_count(p) & PREEMPT_ACTIVE)
+	if (preempt_count() & PREEMPT_ACTIVE)
 		state = TASK_RUNNING | TASK_STATE_MAX;
-#endif
+#endif /* CONFIG_PREEMPT */
 
 	return state;
 }
-#endif
+#endif /* CREATE_TRACE_POINTS */
 
 /*
  * Tracepoint for task switches, performed by the scheduler:
-- 
cgit v1.2.3-70-g09d2


From e2336f6e51edda875a49770b616ed5b02a74665b Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Wed, 8 Oct 2014 20:33:48 +0200
Subject: sched: Kill task_preempt_count()

task_preempt_count() is pointless if preemption counter is per-cpu,
currently this is x86 only. It is only valid if the task is not
running, and even in this case the only info it can provide is the
state of PREEMPT_ACTIVE bit.

Change its single caller to check p->on_rq instead, this should be
the same if p->state != TASK_RUNNING, and kill this helper.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Alexander Graf <agraf@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christoph Lameter <cl@linux.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-arch@vger.kernel.org
Link: http://lkml.kernel.org/r/20141008183348.GC17495@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/preempt.h | 3 ---
 include/asm-generic/preempt.h  | 3 ---
 kernel/sched/core.c            | 2 +-
 3 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 400873450e3..8f327184253 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -30,9 +30,6 @@ static __always_inline void preempt_count_set(int pc)
 /*
  * must be macros to avoid header recursion hell
  */
-#define task_preempt_count(p) \
-	(task_thread_info(p)->saved_preempt_count & ~PREEMPT_NEED_RESCHED)
-
 #define init_task_preempt_count(p) do { \
 	task_thread_info(p)->saved_preempt_count = PREEMPT_DISABLED; \
 } while (0)
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index 1cd3f5d767a..eb6f9e6c307 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -23,9 +23,6 @@ static __always_inline void preempt_count_set(int pc)
 /*
  * must be macros to avoid header recursion hell
  */
-#define task_preempt_count(p) \
-	(task_thread_info(p)->preempt_count & ~PREEMPT_NEED_RESCHED)
-
 #define init_task_preempt_count(p) do { \
 	task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
 } while (0)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1b69603c1d3..5c067fd66db 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1054,7 +1054,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 * ttwu() will sort out the placement.
 	 */
 	WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
-			!(task_preempt_count(p) & PREEMPT_ACTIVE));
+			!p->on_rq);
 
 #ifdef CONFIG_LOCKDEP
 	/*
-- 
cgit v1.2.3-70-g09d2


From 5dcb10159b1848b2c91ac2a11745d229f16fc26b Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 14 Oct 2014 11:12:55 +0200
Subject: dt: bindings: ux500: Add header for PM domains specifiers

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/dt-bindings/arm/ux500_pm_domains.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
 create mode 100644 include/dt-bindings/arm/ux500_pm_domains.h

(limited to 'include')

diff --git a/include/dt-bindings/arm/ux500_pm_domains.h b/include/dt-bindings/arm/ux500_pm_domains.h
new file mode 100644
index 00000000000..398a6c0288d
--- /dev/null
+++ b/include/dt-bindings/arm/ux500_pm_domains.h
@@ -0,0 +1,15 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd.
+ *
+ * Author: Ulf Hansson <ulf.hansson@linaro.org>
+ * License terms: GNU General Public License (GPL) version 2
+ */
+#ifndef _DT_BINDINGS_ARM_UX500_PM_DOMAINS_H
+#define _DT_BINDINGS_ARM_UX500_PM_DOMAINS_H
+
+#define DOMAIN_VAPE		0
+
+/* Number of PM domains. */
+#define NR_DOMAINS		(DOMAIN_VAPE + 1)
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From 7f51412a415d87ea8598d14722fb31e4f5701257 Mon Sep 17 00:00:00 2001
From: Juri Lelli <juri.lelli@arm.com>
Date: Fri, 19 Sep 2014 10:22:40 +0100
Subject: sched/deadline: Fix bandwidth check/update when migrating tasks
 between exclusive cpusets

Exclusive cpusets are the only way users can restrict SCHED_DEADLINE tasks
affinity (performing what is commonly called clustered scheduling).
Unfortunately, such thing is currently broken for two reasons:

 - No check is performed when the user tries to attach a task to
   an exlusive cpuset (recall that exclusive cpusets have an
   associated maximum allowed bandwidth).

 - Bandwidths of source and destination cpusets are not correctly
   updated after a task is migrated between them.

This patch fixes both things at once, as they are opposite faces
of the same coin.

The check is performed in cpuset_can_attach(), as there aren't any
points of failure after that function. The updated is split in two
halves. We first reserve bandwidth in the destination cpuset, after
we pass the check in cpuset_can_attach(). And we then release
bandwidth from the source cpuset when the task's affinity is
actually changed. Even if there can be time windows when sched_setattr()
may erroneously fail in the source cpuset, we are fine with it, as
we can't perfom an atomic update of both cpusets at once.

Reported-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Reported-by: Vincent Legout <vincent@legout.info>
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Dario Faggioli <raistlin@linux.it>
Cc: Michael Trimarchi <michael@amarulasolutions.com>
Cc: Fabio Checconi <fchecconi@gmail.com>
Cc: michael@amarulasolutions.com
Cc: luca.abeni@unitn.it
Cc: Li Zefan <lizefan@huawei.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: cgroups@vger.kernel.org
Link: http://lkml.kernel.org/r/1411118561-26323-3-git-send-email-juri.lelli@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h   |  2 ++
 kernel/cpuset.c         | 13 ++-------
 kernel/sched/core.c     | 70 +++++++++++++++++++++++++++++++++++--------------
 kernel/sched/deadline.c | 25 ++++++++++++++++--
 kernel/sched/sched.h    | 19 ++++++++++++++
 5 files changed, 97 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5e344bbe63e..1d1fa081d44 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2052,6 +2052,8 @@ static inline void tsk_restore_flags(struct task_struct *task,
 	task->flags |= orig_flags & flags;
 }
 
+extern int task_can_attach(struct task_struct *p,
+			   const struct cpumask *cs_cpus_allowed);
 #ifdef CONFIG_SMP
 extern void do_set_cpus_allowed(struct task_struct *p,
 			       const struct cpumask *new_mask);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1f107c74087..7af8577fc8f 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1429,17 +1429,8 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
 		goto out_unlock;
 
 	cgroup_taskset_for_each(task, tset) {
-		/*
-		 * Kthreads which disallow setaffinity shouldn't be moved
-		 * to a new cpuset; we don't want to change their cpu
-		 * affinity and isolating such threads by their set of
-		 * allowed nodes is unnecessary.  Thus, cpusets are not
-		 * applicable for such threads.  This prevents checking for
-		 * success of set_cpus_allowed_ptr() on all attached tasks
-		 * before cpus_allowed may be changed.
-		 */
-		ret = -EINVAL;
-		if (task->flags & PF_NO_SETAFFINITY)
+		ret = task_can_attach(task, cs->cpus_allowed);
+		if (ret)
 			goto out_unlock;
 		ret = security_task_setscheduler(task);
 		if (ret)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5c067fd66db..9993feeb8b1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2034,25 +2034,6 @@ static inline int dl_bw_cpus(int i)
 }
 #endif
 
-static inline
-void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
-{
-	dl_b->total_bw -= tsk_bw;
-}
-
-static inline
-void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
-{
-	dl_b->total_bw += tsk_bw;
-}
-
-static inline
-bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
-{
-	return dl_b->bw != -1 &&
-	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
-}
-
 /*
  * We must be sure that accepting a new task (or allowing changing the
  * parameters of an existing one) is consistent with the bandwidth
@@ -4669,6 +4650,57 @@ void init_idle(struct task_struct *idle, int cpu)
 #endif
 }
 
+int task_can_attach(struct task_struct *p,
+		    const struct cpumask *cs_cpus_allowed)
+{
+	int ret = 0;
+
+	/*
+	 * Kthreads which disallow setaffinity shouldn't be moved
+	 * to a new cpuset; we don't want to change their cpu
+	 * affinity and isolating such threads by their set of
+	 * allowed nodes is unnecessary.  Thus, cpusets are not
+	 * applicable for such threads.  This prevents checking for
+	 * success of set_cpus_allowed_ptr() on all attached tasks
+	 * before cpus_allowed may be changed.
+	 */
+	if (p->flags & PF_NO_SETAFFINITY) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+#ifdef CONFIG_SMP
+	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
+					      cs_cpus_allowed)) {
+		unsigned int dest_cpu = cpumask_any_and(cpu_active_mask,
+							cs_cpus_allowed);
+		struct dl_bw *dl_b = dl_bw_of(dest_cpu);
+		bool overflow;
+		int cpus;
+		unsigned long flags;
+
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
+		cpus = dl_bw_cpus(dest_cpu);
+		overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
+		if (overflow)
+			ret = -EBUSY;
+		else {
+			/*
+			 * We reserve space for this task in the destination
+			 * root_domain, as we can't fail after this point.
+			 * We will free resources in the source root_domain
+			 * later on (see set_cpus_allowed_dl()).
+			 */
+			__dl_add(dl_b, p->dl.dl_bw);
+		}
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+	}
+#endif
+out:
+	return ret;
+}
+
 #ifdef CONFIG_SMP
 /*
  * move_queued_task - move a queued task to new rq.
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 9d1e76a2129..8aaa971ffec 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1517,10 +1517,33 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 				const struct cpumask *new_mask)
 {
 	struct rq *rq;
+	struct root_domain *src_rd;
 	int weight;
 
 	BUG_ON(!dl_task(p));
 
+	rq = task_rq(p);
+	src_rd = rq->rd;
+	/*
+	 * Migrating a SCHED_DEADLINE task between exclusive
+	 * cpusets (different root_domains) entails a bandwidth
+	 * update. We already made space for us in the destination
+	 * domain (see cpuset_can_attach()).
+	 */
+	if (!cpumask_intersects(src_rd->span, new_mask)) {
+		struct dl_bw *src_dl_b;
+
+		src_dl_b = dl_bw_of(cpu_of(rq));
+		/*
+		 * We now free resources of the root_domain we are migrating
+		 * off. In the worst case, sched_setattr() may temporary fail
+		 * until we complete the update.
+		 */
+		raw_spin_lock(&src_dl_b->lock);
+		__dl_clear(src_dl_b, p->dl.dl_bw);
+		raw_spin_unlock(&src_dl_b->lock);
+	}
+
 	/*
 	 * Update only if the task is actually running (i.e.,
 	 * it is on the rq AND it is not throttled).
@@ -1537,8 +1560,6 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 	if ((p->nr_cpus_allowed > 1) == (weight > 1))
 		return;
 
-	rq = task_rq(p);
-
 	/*
 	 * The process used to be able to migrate OR it can now migrate
 	 */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 57aacea1cbd..ec3917c5f89 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -176,6 +176,25 @@ struct dl_bw {
 	u64 bw, total_bw;
 };
 
+static inline
+void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
+{
+	dl_b->total_bw -= tsk_bw;
+}
+
+static inline
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
+{
+	dl_b->total_bw += tsk_bw;
+}
+
+static inline
+bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
+{
+	return dl_b->bw != -1 &&
+	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
+}
+
 extern struct mutex sched_domains_mutex;
 
 #ifdef CONFIG_CGROUP_SCHED
-- 
cgit v1.2.3-70-g09d2


From f82f80426f7afcf55953924e71555984a4bd6ce6 Mon Sep 17 00:00:00 2001
From: Juri Lelli <juri.lelli@arm.com>
Date: Tue, 7 Oct 2014 09:52:11 +0100
Subject: sched/deadline: Ensure that updates to exclusive cpusets don't break
 AC

How we deal with updates to exclusive cpusets is currently broken.
As an example, suppose we have an exclusive cpuset composed of
two cpus: A[cpu0,cpu1]. We can assign SCHED_DEADLINE task to it
up to the allowed bandwidth. If we want now to modify cpusetA's
cpumask, we have to check that removing a cpu's amount of
bandwidth doesn't break AC guarantees. This thing isn't checked
in the current code.

This patch fixes the problem above, denying an update if the
new cpumask won't have enough bandwidth for SCHED_DEADLINE tasks
that are currently active.

Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: cgroups@vger.kernel.org
Link: http://lkml.kernel.org/r/5433E6AF.5080105@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  2 ++
 kernel/cpuset.c       | 10 ++++++++++
 kernel/sched/core.c   | 19 +++++++++++++++++++
 3 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1d1fa081d44..320a9779f1b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2052,6 +2052,8 @@ static inline void tsk_restore_flags(struct task_struct *task,
 	task->flags |= orig_flags & flags;
 }
 
+extern int cpuset_cpumask_can_shrink(const struct cpumask *cur,
+				     const struct cpumask *trial);
 extern int task_can_attach(struct task_struct *p,
 			   const struct cpumask *cs_cpus_allowed);
 #ifdef CONFIG_SMP
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 7af8577fc8f..723cfc9d0ad 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -506,6 +506,16 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 			goto out;
 	}
 
+	/*
+	 * We can't shrink if we won't have enough room for SCHED_DEADLINE
+	 * tasks.
+	 */
+	ret = -EBUSY;
+	if (is_cpu_exclusive(cur) &&
+	    !cpuset_cpumask_can_shrink(cur->cpus_allowed,
+				       trial->cpus_allowed))
+		goto out;
+
 	ret = 0;
 out:
 	rcu_read_unlock();
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9993feeb8b1..0456a55fc27 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4650,6 +4650,25 @@ void init_idle(struct task_struct *idle, int cpu)
 #endif
 }
 
+int cpuset_cpumask_can_shrink(const struct cpumask *cur,
+			      const struct cpumask *trial)
+{
+	int ret = 1, trial_cpus;
+	struct dl_bw *cur_dl_b;
+	unsigned long flags;
+
+	cur_dl_b = dl_bw_of(cpumask_any(cur));
+	trial_cpus = cpumask_weight(trial);
+
+	raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
+	if (cur_dl_b->bw != -1 &&
+	    cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw)
+		ret = 0;
+	raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
+
+	return ret;
+}
+
 int task_can_attach(struct task_struct *p,
 		    const struct cpumask *cs_cpus_allowed)
 {
-- 
cgit v1.2.3-70-g09d2


From 61ada528dea028331e99e8ceaed87c683ad25de2 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 24 Sep 2014 10:18:47 +0200
Subject: sched/wait: Provide infrastructure to deal with nested blocking

There are a few places that call blocking primitives from wait loops,
provide infrastructure to support this without the typical
task_struct::state collision.

We record the wakeup in wait_queue_t::flags which leaves
task_struct::state free to be used by others.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: tglx@linutronix.de
Cc: ilya.dryomov@inktank.com
Cc: umgwanakikbuti@gmail.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20140924082242.051202318@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h |  7 +++++-
 kernel/sched/wait.c  | 61 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index e4a8eb9312e..fc0e99395fb 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -13,9 +13,12 @@ typedef struct __wait_queue wait_queue_t;
 typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key);
 int default_wake_function(wait_queue_t *wait, unsigned mode, int flags, void *key);
 
+/* __wait_queue::flags */
+#define WQ_FLAG_EXCLUSIVE	0x01
+#define WQ_FLAG_WOKEN		0x02
+
 struct __wait_queue {
 	unsigned int		flags;
-#define WQ_FLAG_EXCLUSIVE	0x01
 	void			*private;
 	wait_queue_func_t	func;
 	struct list_head	task_list;
@@ -830,6 +833,8 @@ void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int sta
 long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
 void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, unsigned int mode, void *key);
+long wait_woken(wait_queue_t *wait, unsigned mode, long timeout);
+int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 5a62915f47a..4dae1885db6 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -297,6 +297,67 @@ int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *
 }
 EXPORT_SYMBOL(autoremove_wake_function);
 
+
+/*
+ * DEFINE_WAIT_FUNC(wait, woken_wake_func);
+ *
+ * add_wait_queue(&wq, &wait);
+ * for (;;) {
+ *     if (condition)
+ *         break;
+ *
+ *     p->state = mode;				condition = true;
+ *     smp_mb(); // A				smp_wmb(); // C
+ *     if (!wait->flags & WQ_FLAG_WOKEN)	wait->flags |= WQ_FLAG_WOKEN;
+ *         schedule()				try_to_wake_up();
+ *     p->state = TASK_RUNNING;		    ~~~~~~~~~~~~~~~~~~
+ *     wait->flags &= ~WQ_FLAG_WOKEN;		condition = true;
+ *     smp_mb() // B				smp_wmb(); // C
+ *						wait->flags |= WQ_FLAG_WOKEN;
+ * }
+ * remove_wait_queue(&wq, &wait);
+ *
+ */
+long wait_woken(wait_queue_t *wait, unsigned mode, long timeout)
+{
+	set_current_state(mode); /* A */
+	/*
+	 * The above implies an smp_mb(), which matches with the smp_wmb() from
+	 * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
+	 * also observe all state before the wakeup.
+	 */
+	if (!(wait->flags & WQ_FLAG_WOKEN))
+		timeout = schedule_timeout(timeout);
+	__set_current_state(TASK_RUNNING);
+
+	/*
+	 * The below implies an smp_mb(), it too pairs with the smp_wmb() from
+	 * woken_wake_function() such that we must either observe the wait
+	 * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
+	 * an event.
+	 */
+	set_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
+
+	return timeout;
+}
+EXPORT_SYMBOL(wait_woken);
+
+int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+	/*
+	 * Although this function is called under waitqueue lock, LOCK
+	 * doesn't imply write barrier and the users expects write
+	 * barrier semantics on wakeup functions.  The following
+	 * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
+	 * and is paired with set_mb() in wait_woken().
+	 */
+	smp_wmb(); /* C */
+	wait->flags |= WQ_FLAG_WOKEN;
+
+	return default_wake_function(wait, mode, sync, key);
+}
+EXPORT_SYMBOL(woken_wake_function);
+
 int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
 {
 	struct wait_bit_key *key = arg;
-- 
cgit v1.2.3-70-g09d2


From e22b886a8a43b147e1994a9f970f678fc0df2033 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 24 Sep 2014 10:18:48 +0200
Subject: sched/wait: Add might_sleep() checks

Add more might_sleep() checks, suppose someone put a wait_event() like
thing in a wait loop..

Can't put might_sleep() in ___wait_event() because there's the locked
primitives which call ___wait_event() with locks held.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: tglx@linutronix.de
Cc: ilya.dryomov@inktank.com
Cc: umgwanakikbuti@gmail.com
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20140924082242.119255706@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index fc0e99395fb..0421775e0b9 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -261,6 +261,7 @@ __out:	__ret;								\
  */
 #define wait_event(wq, condition)					\
 do {									\
+	might_sleep();							\
 	if (condition)							\
 		break;							\
 	__wait_event(wq, condition);					\
@@ -293,6 +294,7 @@ do {									\
 #define wait_event_timeout(wq, condition, timeout)			\
 ({									\
 	long __ret = timeout;						\
+	might_sleep();							\
 	if (!___wait_cond_timeout(condition))				\
 		__ret = __wait_event_timeout(wq, condition, timeout);	\
 	__ret;								\
@@ -318,6 +320,7 @@ do {									\
  */
 #define wait_event_cmd(wq, condition, cmd1, cmd2)			\
 do {									\
+	might_sleep();							\
 	if (condition)							\
 		break;							\
 	__wait_event_cmd(wq, condition, cmd1, cmd2);			\
@@ -345,6 +348,7 @@ do {									\
 #define wait_event_interruptible(wq, condition)				\
 ({									\
 	int __ret = 0;							\
+	might_sleep();							\
 	if (!(condition))						\
 		__ret = __wait_event_interruptible(wq, condition);	\
 	__ret;								\
@@ -378,6 +382,7 @@ do {									\
 #define wait_event_interruptible_timeout(wq, condition, timeout)	\
 ({									\
 	long __ret = timeout;						\
+	might_sleep();							\
 	if (!___wait_cond_timeout(condition))				\
 		__ret = __wait_event_interruptible_timeout(wq,		\
 						condition, timeout);	\
@@ -428,6 +433,7 @@ do {									\
 #define wait_event_hrtimeout(wq, condition, timeout)			\
 ({									\
 	int __ret = 0;							\
+	might_sleep();							\
 	if (!(condition))						\
 		__ret = __wait_event_hrtimeout(wq, condition, timeout,	\
 					       TASK_UNINTERRUPTIBLE);	\
@@ -453,6 +459,7 @@ do {									\
 #define wait_event_interruptible_hrtimeout(wq, condition, timeout)	\
 ({									\
 	long __ret = 0;							\
+	might_sleep();							\
 	if (!(condition))						\
 		__ret = __wait_event_hrtimeout(wq, condition, timeout,	\
 					       TASK_INTERRUPTIBLE);	\
@@ -466,6 +473,7 @@ do {									\
 #define wait_event_interruptible_exclusive(wq, condition)		\
 ({									\
 	int __ret = 0;							\
+	might_sleep();							\
 	if (!(condition))						\
 		__ret = __wait_event_interruptible_exclusive(wq, condition);\
 	__ret;								\
@@ -640,6 +648,7 @@ do {									\
 #define wait_event_killable(wq, condition)				\
 ({									\
 	int __ret = 0;							\
+	might_sleep();							\
 	if (!(condition))						\
 		__ret = __wait_event_killable(wq, condition);		\
 	__ret;								\
@@ -891,6 +900,7 @@ extern int bit_wait_io_timeout(struct wait_bit_key *);
 static inline int
 wait_on_bit(void *word, int bit, unsigned mode)
 {
+	might_sleep();
 	if (!test_bit(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
@@ -915,6 +925,7 @@ wait_on_bit(void *word, int bit, unsigned mode)
 static inline int
 wait_on_bit_io(void *word, int bit, unsigned mode)
 {
+	might_sleep();
 	if (!test_bit(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
@@ -941,6 +952,7 @@ wait_on_bit_io(void *word, int bit, unsigned mode)
 static inline int
 wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
 {
+	might_sleep();
 	if (!test_bit(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
@@ -968,6 +980,7 @@ wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode
 static inline int
 wait_on_bit_lock(void *word, int bit, unsigned mode)
 {
+	might_sleep();
 	if (!test_and_set_bit(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode);
@@ -991,6 +1004,7 @@ wait_on_bit_lock(void *word, int bit, unsigned mode)
 static inline int
 wait_on_bit_lock_io(void *word, int bit, unsigned mode)
 {
+	might_sleep();
 	if (!test_and_set_bit(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode);
@@ -1016,6 +1030,7 @@ wait_on_bit_lock_io(void *word, int bit, unsigned mode)
 static inline int
 wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
 {
+	might_sleep();
 	if (!test_and_set_bit(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_lock(word, bit, action, mode);
@@ -1034,6 +1049,7 @@ wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned
 static inline
 int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode)
 {
+	might_sleep();
 	if (atomic_read(val) == 0)
 		return 0;
 	return out_of_line_wait_on_atomic_t(val, action, mode);
-- 
cgit v1.2.3-70-g09d2


From 1029a2b52c09e479fd7b07275812ad97868c0fb0 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 24 Sep 2014 10:18:49 +0200
Subject: sched, exit: Deal with nested sleeps

do_wait() is a big wait loop, but we set TASK_RUNNING too late; we end
up calling potential sleeps before we reset it.

Not strictly a bug since we're guaranteed to exit the loop and not
call schedule(); put in annotations to quiet might_sleep().

 WARNING: CPU: 0 PID: 1 at ../kernel/sched/core.c:7123 __might_sleep+0x7e/0x90()
 do not call blocking ops when !TASK_RUNNING; state=1 set at [<ffffffff8109a788>] do_wait+0x88/0x270

 Call Trace:
  [<ffffffff81694991>] dump_stack+0x4e/0x7a
  [<ffffffff8109877c>] warn_slowpath_common+0x8c/0xc0
  [<ffffffff8109886c>] warn_slowpath_fmt+0x4c/0x50
  [<ffffffff810bca6e>] __might_sleep+0x7e/0x90
  [<ffffffff811a1c15>] might_fault+0x55/0xb0
  [<ffffffff8109a3fb>] wait_consider_task+0x90b/0xc10
  [<ffffffff8109a804>] do_wait+0x104/0x270
  [<ffffffff8109b837>] SyS_wait4+0x77/0x100
  [<ffffffff8169d692>] system_call_fastpath+0x16/0x1b

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: tglx@linutronix.de
Cc: umgwanakikbuti@gmail.com
Cc: ilya.dryomov@inktank.com
Cc: Alex Elder <alex.elder@linaro.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Axel Lin <axel.lin@ingics.com>
Cc: Daniel Borkmann <dborkman@redhat.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Guillaume Morin <guillaume@morinfr.org>
Cc: Ionut Alexa <ionut.m.alexa@gmail.com>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Michal Schmidt <mschmidt@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20140924082242.186408915@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/kernel.h | 2 ++
 kernel/exit.c          | 5 +++++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 3d770f5564b..5068a0d9fec 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -175,10 +175,12 @@ extern int _cond_resched(void);
  */
 # define might_sleep() \
 	do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
+# define sched_annotate_sleep()	__set_current_state(TASK_RUNNING)
 #else
   static inline void __might_sleep(const char *file, int line,
 				   int preempt_offset) { }
 # define might_sleep() do { might_resched(); } while (0)
+# define sched_annotate_sleep() do { } while (0)
 #endif
 
 #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0)
diff --git a/kernel/exit.c b/kernel/exit.c
index 5d30019ff95..232c4bc8bcc 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -997,6 +997,8 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 
 		get_task_struct(p);
 		read_unlock(&tasklist_lock);
+		sched_annotate_sleep();
+
 		if ((exit_code & 0x7f) == 0) {
 			why = CLD_EXITED;
 			status = exit_code >> 8;
@@ -1079,6 +1081,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 	 * thread can reap it because we its state == DEAD/TRACE.
 	 */
 	read_unlock(&tasklist_lock);
+	sched_annotate_sleep();
 
 	retval = wo->wo_rusage
 		? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
@@ -1210,6 +1213,7 @@ unlock_sig:
 	pid = task_pid_vnr(p);
 	why = ptrace ? CLD_TRAPPED : CLD_STOPPED;
 	read_unlock(&tasklist_lock);
+	sched_annotate_sleep();
 
 	if (unlikely(wo->wo_flags & WNOWAIT))
 		return wait_noreap_copyout(wo, p, pid, uid, why, exit_code);
@@ -1272,6 +1276,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 	pid = task_pid_vnr(p);
 	get_task_struct(p);
 	read_unlock(&tasklist_lock);
+	sched_annotate_sleep();
 
 	if (!wo->wo_info) {
 		retval = wo->wo_rusage
-- 
cgit v1.2.3-70-g09d2


From 26cabd31259ba43f68026ce3f62b78094124333f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 24 Sep 2014 10:18:54 +0200
Subject: sched, net: Clean up sk_wait_event() vs. might_sleep()

WARNING: CPU: 1 PID: 1744 at kernel/sched/core.c:7104 __might_sleep+0x58/0x90()
do not call blocking ops when !TASK_RUNNING; state=1 set at [<ffffffff81070e10>] prepare_to_wait+0x50 /0xa0

 [<ffffffff8105bc38>] __might_sleep+0x58/0x90
 [<ffffffff8148c671>] lock_sock_nested+0x31/0xb0
 [<ffffffff81498aaa>] sk_stream_wait_memory+0x18a/0x2d0

Which is a false positive because sk_wait_event() will already have
TASK_RUNNING at that point if it would've gone through
schedule_timeout().

So annotate with sched_annotate_sleep(); which goes away on !DEBUG builds.

Reported-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140924082242.524407432@infradead.org
Cc: David S. Miller <davem@davemloft.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: netdev@vger.kernel.org
Cc: tglx@linutronix.de
Cc: ilya.dryomov@inktank.com
Cc: umgwanakikbuti@gmail.com
Cc: oleg@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/net/sock.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 7db3db112ba..e6f235ebf6c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -897,6 +897,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk)
 		if (!__rc) {						\
 			*(__timeo) = schedule_timeout(*(__timeo));	\
 		}							\
+		sched_annotate_sleep();						\
 		lock_sock(__sk);					\
 		__rc = __condition;					\
 		__rc;							\
-- 
cgit v1.2.3-70-g09d2


From 8eb23b9f35aae413140d3fda766a98092c21e9b0 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 24 Sep 2014 10:18:55 +0200
Subject: sched: Debug nested sleeps

Validate we call might_sleep() with TASK_RUNNING, which catches places
where we nest blocking primitives, eg. mutex usage in a wait loop.

Since all blocking is arranged through task_struct::state, nesting
this will cause the inner primitive to set TASK_RUNNING and the outer
will thus not block.

Another observed problem is calling a blocking function from
schedule()->sched_submit_work()->blk_schedule_flush_plug() which will
then destroy the task state for the actual __schedule() call that
comes after it.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: tglx@linutronix.de
Cc: ilya.dryomov@inktank.com
Cc: umgwanakikbuti@gmail.com
Cc: oleg@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20140924082242.591637616@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 46 ++++++++++++++++++++++++++++++++++++++++++++--
 kernel/sched/core.c   | 13 +++++++++++++
 2 files changed, 57 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 320a9779f1b..4648e07f7d6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -243,6 +243,43 @@ extern char ___assert_task_state[1 - 2*!!(
 				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
 				 (task->flags & PF_FROZEN) == 0)
 
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+
+#define __set_task_state(tsk, state_value)			\
+	do {							\
+		(tsk)->task_state_change = _THIS_IP_;		\
+		(tsk)->state = (state_value);			\
+	} while (0)
+#define set_task_state(tsk, state_value)			\
+	do {							\
+		(tsk)->task_state_change = _THIS_IP_;		\
+		set_mb((tsk)->state, (state_value));		\
+	} while (0)
+
+/*
+ * set_current_state() includes a barrier so that the write of current->state
+ * is correctly serialised wrt the caller's subsequent test of whether to
+ * actually sleep:
+ *
+ *	set_current_state(TASK_UNINTERRUPTIBLE);
+ *	if (do_i_need_to_sleep())
+ *		schedule();
+ *
+ * If the caller does not need such serialisation then use __set_current_state()
+ */
+#define __set_current_state(state_value)			\
+	do {							\
+		current->task_state_change = _THIS_IP_;		\
+		current->state = (state_value);			\
+	} while (0)
+#define set_current_state(state_value)				\
+	do {							\
+		current->task_state_change = _THIS_IP_;		\
+		set_mb(current->state, (state_value));		\
+	} while (0)
+
+#else
+
 #define __set_task_state(tsk, state_value)		\
 	do { (tsk)->state = (state_value); } while (0)
 #define set_task_state(tsk, state_value)		\
@@ -259,11 +296,13 @@ extern char ___assert_task_state[1 - 2*!!(
  *
  * If the caller does not need such serialisation then use __set_current_state()
  */
-#define __set_current_state(state_value)			\
+#define __set_current_state(state_value)		\
 	do { current->state = (state_value); } while (0)
-#define set_current_state(state_value)		\
+#define set_current_state(state_value)			\
 	set_mb(current->state, (state_value))
 
+#endif
+
 /* Task command name length */
 #define TASK_COMM_LEN 16
 
@@ -1661,6 +1700,9 @@ struct task_struct {
 	unsigned int	sequential_io;
 	unsigned int	sequential_io_avg;
 #endif
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+	unsigned long	task_state_change;
+#endif
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0456a55fc27..5b4b96b27cd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7298,6 +7298,19 @@ void __might_sleep(const char *file, int line, int preempt_offset)
 {
 	static unsigned long prev_jiffy;	/* ratelimiting */
 
+	/*
+	 * Blocking primitives will set (and therefore destroy) current->state,
+	 * since we will exit with TASK_RUNNING make sure we enter with it,
+	 * otherwise we will destroy state.
+	 */
+	if (WARN(current->state != TASK_RUNNING,
+			"do not call blocking ops when !TASK_RUNNING; "
+			"state=%lx set at [<%p>] %pS\n",
+			current->state,
+			(void *)current->task_state_change,
+			(void *)current->task_state_change))
+		__set_current_state(TASK_RUNNING);
+
 	rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
 	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
 	     !is_idle_task(current)) ||
-- 
cgit v1.2.3-70-g09d2


From 3427445afd26bd2395f29241319283a93f362cd0 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 24 Sep 2014 10:18:56 +0200
Subject: sched: Exclude cond_resched() from nested sleep test

cond_resched() is a preemption point, not strictly a blocking
primitive, so exclude it from the ->state test.

In particular, preemption preserves task_struct::state.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: tglx@linutronix.de
Cc: ilya.dryomov@inktank.com
Cc: umgwanakikbuti@gmail.com
Cc: oleg@redhat.com
Cc: Alex Elder <alex.elder@linaro.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Axel Lin <axel.lin@ingics.com>
Cc: Daniel Borkmann <dborkman@redhat.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20140924082242.656559952@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/kernel.h |  3 +++
 include/linux/sched.h  |  6 +++---
 kernel/sched/core.c    | 12 +++++++++---
 3 files changed, 15 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5068a0d9fec..446d76a87ba 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -162,6 +162,7 @@ extern int _cond_resched(void);
 #endif
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+  void ___might_sleep(const char *file, int line, int preempt_offset);
   void __might_sleep(const char *file, int line, int preempt_offset);
 /**
  * might_sleep - annotation for functions that can sleep
@@ -177,6 +178,8 @@ extern int _cond_resched(void);
 	do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
 # define sched_annotate_sleep()	__set_current_state(TASK_RUNNING)
 #else
+  static inline void ___might_sleep(const char *file, int line,
+				   int preempt_offset) { }
   static inline void __might_sleep(const char *file, int line,
 				   int preempt_offset) { }
 # define might_sleep() do { might_resched(); } while (0)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4648e07f7d6..4400ddc2fe7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2806,7 +2806,7 @@ static inline int signal_pending_state(long state, struct task_struct *p)
 extern int _cond_resched(void);
 
 #define cond_resched() ({			\
-	__might_sleep(__FILE__, __LINE__, 0);	\
+	___might_sleep(__FILE__, __LINE__, 0);	\
 	_cond_resched();			\
 })
 
@@ -2819,14 +2819,14 @@ extern int __cond_resched_lock(spinlock_t *lock);
 #endif
 
 #define cond_resched_lock(lock) ({				\
-	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
+	___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\
 	__cond_resched_lock(lock);				\
 })
 
 extern int __cond_resched_softirq(void);
 
 #define cond_resched_softirq() ({					\
-	__might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);	\
+	___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);	\
 	__cond_resched_softirq();					\
 })
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5b4b96b27cd..b9f78f12ac2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7296,8 +7296,6 @@ static inline int preempt_count_equals(int preempt_offset)
 
 void __might_sleep(const char *file, int line, int preempt_offset)
 {
-	static unsigned long prev_jiffy;	/* ratelimiting */
-
 	/*
 	 * Blocking primitives will set (and therefore destroy) current->state,
 	 * since we will exit with TASK_RUNNING make sure we enter with it,
@@ -7311,6 +7309,14 @@ void __might_sleep(const char *file, int line, int preempt_offset)
 			(void *)current->task_state_change))
 		__set_current_state(TASK_RUNNING);
 
+	___might_sleep(file, line, preempt_offset);
+}
+EXPORT_SYMBOL(__might_sleep);
+
+void ___might_sleep(const char *file, int line, int preempt_offset)
+{
+	static unsigned long prev_jiffy;	/* ratelimiting */
+
 	rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
 	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
 	     !is_idle_task(current)) ||
@@ -7340,7 +7346,7 @@ void __might_sleep(const char *file, int line, int preempt_offset)
 #endif
 	dump_stack();
 }
-EXPORT_SYMBOL(__might_sleep);
+EXPORT_SYMBOL(___might_sleep);
 #endif
 
 #ifdef CONFIG_MAGIC_SYSRQ
-- 
cgit v1.2.3-70-g09d2


From 7b366d5f161c2a69eeafe525105a5a9277982472 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 28 Oct 2014 15:30:00 +0100
Subject: ALSA: jack: Fix kerneldoc comments

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/jack.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/sound/jack.h b/include/sound/jack.h
index 58916573db5..37e612e7741 100644
--- a/include/sound/jack.h
+++ b/include/sound/jack.h
@@ -28,8 +28,9 @@
 struct input_dev;
 
 /**
- * Jack types which can be reported.  These values are used as a
- * bitmask.
+ * enum snd_jack_types: Jack types which can be reported
+ *
+ * These values are used as a bitmask.
  *
  * Note that this must be kept in sync with the lookup table in
  * sound/core/jack.c.
-- 
cgit v1.2.3-70-g09d2


From e3a2e87893125bcd99bd7e1ddf9bfc421e492572 Mon Sep 17 00:00:00 2001
From: Alexandre Courbot <acourbot@nvidia.com>
Date: Thu, 23 Oct 2014 17:27:07 +0900
Subject: gpio: rename gpio_lock_as_irq to gpiochip_lock_as_irq

This function actually operates on a gpio_chip, so its prefix should
reflect that fact for consistency with other functions defined in
gpio/driver.h.

Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/gpio/driver.txt            |  4 ++--
 drivers/gpio/gpio-bcm-kona.c             |  4 ++--
 drivers/gpio/gpio-dwapb.c                |  4 ++--
 drivers/gpio/gpio-em.c                   |  4 ++--
 drivers/gpio/gpio-mcp23s08.c             |  4 ++--
 drivers/gpio/gpio-omap.c                 |  2 +-
 drivers/gpio/gpio-tegra.c                |  4 ++--
 drivers/gpio/gpio-vr41xx.c               |  4 ++--
 drivers/gpio/gpiolib-acpi.c              |  6 +++---
 drivers/gpio/gpiolib-sysfs.c             |  4 ++--
 drivers/gpio/gpiolib.c                   | 16 ++++++++--------
 drivers/pinctrl/pinctrl-at91.c           |  4 ++--
 drivers/pinctrl/samsung/pinctrl-exynos.c |  4 ++--
 drivers/pinctrl/sunxi/pinctrl-sunxi.c    |  6 +++---
 include/linux/gpio.h                     |  7 ++++---
 include/linux/gpio/driver.h              |  4 ++--
 16 files changed, 41 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/Documentation/gpio/driver.txt b/Documentation/gpio/driver.txt
index 31e0b5db55d..90d0f6aba7a 100644
--- a/Documentation/gpio/driver.txt
+++ b/Documentation/gpio/driver.txt
@@ -158,12 +158,12 @@ Locking IRQ usage
 Input GPIOs can be used as IRQ signals. When this happens, a driver is requested
 to mark the GPIO as being used as an IRQ:
 
-	int gpio_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
+	int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
 
 This will prevent the use of non-irq related GPIO APIs until the GPIO IRQ lock
 is released:
 
-	void gpio_unlock_as_irq(struct gpio_chip *chip, unsigned int offset)
+	void gpiochip_unlock_as_irq(struct gpio_chip *chip, unsigned int offset)
 
 When implementing an irqchip inside a GPIO driver, these two functions should
 typically be called in the .startup() and .shutdown() callbacks from the
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index de0801e9767..56fb5ce47aa 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -470,7 +470,7 @@ static int bcm_kona_gpio_irq_reqres(struct irq_data *d)
 {
 	struct bcm_kona_gpio *kona_gpio = irq_data_get_irq_chip_data(d);
 
-	if (gpio_lock_as_irq(&kona_gpio->gpio_chip, d->hwirq)) {
+	if (gpiochip_lock_as_irq(&kona_gpio->gpio_chip, d->hwirq)) {
 		dev_err(kona_gpio->gpio_chip.dev,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			d->hwirq);
@@ -483,7 +483,7 @@ static void bcm_kona_gpio_irq_relres(struct irq_data *d)
 {
 	struct bcm_kona_gpio *kona_gpio = irq_data_get_irq_chip_data(d);
 
-	gpio_unlock_as_irq(&kona_gpio->gpio_chip, d->hwirq);
+	gpiochip_unlock_as_irq(&kona_gpio->gpio_chip, d->hwirq);
 }
 
 static struct irq_chip bcm_gpio_irq_chip = {
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index b43cd84b61f..4beb3783939 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -194,7 +194,7 @@ static int dwapb_irq_reqres(struct irq_data *d)
 	struct dwapb_gpio *gpio = igc->private;
 	struct bgpio_chip *bgc = &gpio->ports[0].bgc;
 
-	if (gpio_lock_as_irq(&bgc->gc, irqd_to_hwirq(d))) {
+	if (gpiochip_lock_as_irq(&bgc->gc, irqd_to_hwirq(d))) {
 		dev_err(gpio->dev, "unable to lock HW IRQ %lu for IRQ\n",
 			irqd_to_hwirq(d));
 		return -EINVAL;
@@ -208,7 +208,7 @@ static void dwapb_irq_relres(struct irq_data *d)
 	struct dwapb_gpio *gpio = igc->private;
 	struct bgpio_chip *bgc = &gpio->ports[0].bgc;
 
-	gpio_unlock_as_irq(&bgc->gc, irqd_to_hwirq(d));
+	gpiochip_unlock_as_irq(&bgc->gc, irqd_to_hwirq(d));
 }
 
 static int dwapb_irq_set_type(struct irq_data *d, u32 type)
diff --git a/drivers/gpio/gpio-em.c b/drivers/gpio/gpio-em.c
index fe49ec3cdb7..21d34d4d473 100644
--- a/drivers/gpio/gpio-em.c
+++ b/drivers/gpio/gpio-em.c
@@ -103,7 +103,7 @@ static int em_gio_irq_reqres(struct irq_data *d)
 {
 	struct em_gio_priv *p = irq_data_get_irq_chip_data(d);
 
-	if (gpio_lock_as_irq(&p->gpio_chip, irqd_to_hwirq(d))) {
+	if (gpiochip_lock_as_irq(&p->gpio_chip, irqd_to_hwirq(d))) {
 		dev_err(p->gpio_chip.dev,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			irqd_to_hwirq(d));
@@ -116,7 +116,7 @@ static void em_gio_irq_relres(struct irq_data *d)
 {
 	struct em_gio_priv *p = irq_data_get_irq_chip_data(d);
 
-	gpio_unlock_as_irq(&p->gpio_chip, irqd_to_hwirq(d));
+	gpiochip_unlock_as_irq(&p->gpio_chip, irqd_to_hwirq(d));
 }
 
 
diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c
index 8488e2fd307..468d10d2ac1 100644
--- a/drivers/gpio/gpio-mcp23s08.c
+++ b/drivers/gpio/gpio-mcp23s08.c
@@ -444,7 +444,7 @@ static int mcp23s08_irq_reqres(struct irq_data *data)
 {
 	struct mcp23s08 *mcp = irq_data_get_irq_chip_data(data);
 
-	if (gpio_lock_as_irq(&mcp->chip, data->hwirq)) {
+	if (gpiochip_lock_as_irq(&mcp->chip, data->hwirq)) {
 		dev_err(mcp->chip.dev,
 			"unable to lock HW IRQ %lu for IRQ usage\n",
 			data->hwirq);
@@ -458,7 +458,7 @@ static void mcp23s08_irq_relres(struct irq_data *data)
 {
 	struct mcp23s08 *mcp = irq_data_get_irq_chip_data(data);
 
-	gpio_unlock_as_irq(&mcp->chip, data->hwirq);
+	gpiochip_unlock_as_irq(&mcp->chip, data->hwirq);
 }
 
 static struct irq_chip mcp23s08_irq_chip = {
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 415682f6921..a38686786e4 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -800,7 +800,7 @@ static void omap_gpio_irq_shutdown(struct irq_data *d)
 	unsigned offset = GPIO_INDEX(bank, gpio);
 
 	spin_lock_irqsave(&bank->lock, flags);
-	gpio_unlock_as_irq(&bank->chip, offset);
+	gpiochip_unlock_as_irq(&bank->chip, offset);
 	bank->irq_usage &= ~(BIT(offset));
 	omap_disable_gpio_module(bank, offset);
 	omap_reset_gpio(bank, gpio);
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 4e8fb8261a8..61bcfa93606 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -233,7 +233,7 @@ static int tegra_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 		return -EINVAL;
 	}
 
-	ret = gpio_lock_as_irq(&tegra_gpio_chip, gpio);
+	ret = gpiochip_lock_as_irq(&tegra_gpio_chip, gpio);
 	if (ret) {
 		dev_err(dev, "unable to lock Tegra GPIO %d as IRQ\n", gpio);
 		return ret;
@@ -263,7 +263,7 @@ static void tegra_gpio_irq_shutdown(struct irq_data *d)
 {
 	int gpio = d->hwirq;
 
-	gpio_unlock_as_irq(&tegra_gpio_chip, gpio);
+	gpiochip_unlock_as_irq(&tegra_gpio_chip, gpio);
 }
 
 static void tegra_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
diff --git a/drivers/gpio/gpio-vr41xx.c b/drivers/gpio/gpio-vr41xx.c
index dbf28fa03f6..cec55226143 100644
--- a/drivers/gpio/gpio-vr41xx.c
+++ b/drivers/gpio/gpio-vr41xx.c
@@ -138,7 +138,7 @@ static void unmask_giuint_low(struct irq_data *d)
 
 static unsigned int startup_giuint(struct irq_data *data)
 {
-	if (gpio_lock_as_irq(&vr41xx_gpio_chip, data->hwirq))
+	if (gpiochip_lock_as_irq(&vr41xx_gpio_chip, data->hwirq))
 		dev_err(vr41xx_gpio_chip.dev,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			data->hwirq);
@@ -150,7 +150,7 @@ static unsigned int startup_giuint(struct irq_data *data)
 static void shutdown_giuint(struct irq_data *data)
 {
 	mask_giuint_low(data);
-	gpio_unlock_as_irq(&vr41xx_gpio_chip, data->hwirq);
+	gpiochip_unlock_as_irq(&vr41xx_gpio_chip, data->hwirq);
 }
 
 static struct irq_chip giuint_low_irq_chip = {
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 05c6275da22..349a7552dd2 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -153,7 +153,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 
 	gpiod_direction_input(desc);
 
-	ret = gpio_lock_as_irq(chip, pin);
+	ret = gpiochip_lock_as_irq(chip, pin);
 	if (ret) {
 		dev_err(chip->dev, "Failed to lock GPIO as interrupt\n");
 		goto fail_free_desc;
@@ -209,7 +209,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 fail_free_event:
 	kfree(event);
 fail_unlock_irq:
-	gpio_unlock_as_irq(chip, pin);
+	gpiochip_unlock_as_irq(chip, pin);
 fail_free_desc:
 	gpiochip_free_own_desc(desc);
 
@@ -280,7 +280,7 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip)
 		desc = event->desc;
 		if (WARN_ON(IS_ERR(desc)))
 			continue;
-		gpio_unlock_as_irq(chip, event->pin);
+		gpiochip_unlock_as_irq(chip, event->pin);
 		gpiochip_free_own_desc(desc);
 		list_del(&event->node);
 		kfree(event);
diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c
index 5f2150b619a..781fbed00fc 100644
--- a/drivers/gpio/gpiolib-sysfs.c
+++ b/drivers/gpio/gpiolib-sysfs.c
@@ -161,7 +161,7 @@ static int gpio_setup_irq(struct gpio_desc *desc, struct device *dev,
 	desc->flags &= ~GPIO_TRIGGER_MASK;
 
 	if (!gpio_flags) {
-		gpio_unlock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
+		gpiochip_unlock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
 		ret = 0;
 		goto free_id;
 	}
@@ -200,7 +200,7 @@ static int gpio_setup_irq(struct gpio_desc *desc, struct device *dev,
 	if (ret < 0)
 		goto free_id;
 
-	ret = gpio_lock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
+	ret = gpiochip_lock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
 	if (ret < 0) {
 		gpiod_warn(desc, "failed to flag the GPIO for IRQ\n");
 		goto free_id;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index e8e98ca25ec..50e18a4b3a9 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -495,7 +495,7 @@ static int gpiochip_irq_reqres(struct irq_data *d)
 {
 	struct gpio_chip *chip = irq_data_get_irq_chip_data(d);
 
-	if (gpio_lock_as_irq(chip, d->hwirq)) {
+	if (gpiochip_lock_as_irq(chip, d->hwirq)) {
 		chip_err(chip,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			d->hwirq);
@@ -508,7 +508,7 @@ static void gpiochip_irq_relres(struct irq_data *d)
 {
 	struct gpio_chip *chip = irq_data_get_irq_chip_data(d);
 
-	gpio_unlock_as_irq(chip, d->hwirq);
+	gpiochip_unlock_as_irq(chip, d->hwirq);
 }
 
 static int gpiochip_to_irq(struct gpio_chip *chip, unsigned offset)
@@ -1332,14 +1332,14 @@ int gpiod_to_irq(const struct gpio_desc *desc)
 EXPORT_SYMBOL_GPL(gpiod_to_irq);
 
 /**
- * gpio_lock_as_irq() - lock a GPIO to be used as IRQ
+ * gpiochip_lock_as_irq() - lock a GPIO to be used as IRQ
  * @chip: the chip the GPIO to lock belongs to
  * @offset: the offset of the GPIO to lock as IRQ
  *
  * This is used directly by GPIO drivers that want to lock down
  * a certain GPIO line to be used for IRQs.
  */
-int gpio_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
+int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
 {
 	if (offset >= chip->ngpio)
 		return -EINVAL;
@@ -1354,24 +1354,24 @@ int gpio_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
 	set_bit(FLAG_USED_AS_IRQ, &chip->desc[offset].flags);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(gpio_lock_as_irq);
+EXPORT_SYMBOL_GPL(gpiochip_lock_as_irq);
 
 /**
- * gpio_unlock_as_irq() - unlock a GPIO used as IRQ
+ * gpiochip_unlock_as_irq() - unlock a GPIO used as IRQ
  * @chip: the chip the GPIO to lock belongs to
  * @offset: the offset of the GPIO to lock as IRQ
  *
  * This is used directly by GPIO drivers that want to indicate
  * that a certain GPIO is no longer used exclusively for IRQ.
  */
-void gpio_unlock_as_irq(struct gpio_chip *chip, unsigned int offset)
+void gpiochip_unlock_as_irq(struct gpio_chip *chip, unsigned int offset)
 {
 	if (offset >= chip->ngpio)
 		return;
 
 	clear_bit(FLAG_USED_AS_IRQ, &chip->desc[offset].flags);
 }
-EXPORT_SYMBOL_GPL(gpio_unlock_as_irq);
+EXPORT_SYMBOL_GPL(gpiochip_unlock_as_irq);
 
 /**
  * gpiod_get_raw_value_cansleep() - return a gpio's raw value
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index 354a81d4092..60867170452 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -1472,7 +1472,7 @@ static unsigned int gpio_irq_startup(struct irq_data *d)
 	unsigned	pin = d->hwirq;
 	int ret;
 
-	ret = gpio_lock_as_irq(&at91_gpio->chip, pin);
+	ret = gpiochip_lock_as_irq(&at91_gpio->chip, pin);
 	if (ret) {
 		dev_err(at91_gpio->chip.dev, "unable to lock pind %lu IRQ\n",
 			d->hwirq);
@@ -1488,7 +1488,7 @@ static void gpio_irq_shutdown(struct irq_data *d)
 	unsigned	pin = d->hwirq;
 
 	gpio_irq_mask(d);
-	gpio_unlock_as_irq(&at91_gpio->chip, pin);
+	gpiochip_unlock_as_irq(&at91_gpio->chip, pin);
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index d7154ed0b0e..fa54a2d1c96 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -180,7 +180,7 @@ static int exynos_irq_request_resources(struct irq_data *irqd)
 	unsigned int con;
 	int ret;
 
-	ret = gpio_lock_as_irq(&bank->gpio_chip, irqd->hwirq);
+	ret = gpiochip_lock_as_irq(&bank->gpio_chip, irqd->hwirq);
 	if (ret) {
 		dev_err(bank->gpio_chip.dev, "unable to lock pin %s-%lu IRQ\n",
 			bank->name, irqd->hwirq);
@@ -233,7 +233,7 @@ static void exynos_irq_release_resources(struct irq_data *irqd)
 
 	spin_unlock_irqrestore(&bank->slock, flags);
 
-	gpio_unlock_as_irq(&bank->gpio_chip, irqd->hwirq);
+	gpiochip_unlock_as_irq(&bank->gpio_chip, irqd->hwirq);
 }
 
 /*
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index ef9d804e55d..3d074433773 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -553,7 +553,7 @@ static int sunxi_pinctrl_irq_request_resources(struct irq_data *d)
 	if (!func)
 		return -EINVAL;
 
-	ret = gpio_lock_as_irq(pctl->chip,
+	ret = gpiochip_lock_as_irq(pctl->chip,
 			pctl->irq_array[d->hwirq] - pctl->desc->pin_base);
 	if (ret) {
 		dev_err(pctl->dev, "unable to lock HW IRQ %lu for IRQ\n",
@@ -571,8 +571,8 @@ static void sunxi_pinctrl_irq_release_resources(struct irq_data *d)
 {
 	struct sunxi_pinctrl *pctl = irq_data_get_irq_chip_data(d);
 
-	gpio_unlock_as_irq(pctl->chip,
-			   pctl->irq_array[d->hwirq] - pctl->desc->pin_base);
+	gpiochip_unlock_as_irq(pctl->chip,
+			      pctl->irq_array[d->hwirq] - pctl->desc->pin_base);
 }
 
 static int sunxi_pinctrl_irq_set_type(struct irq_data *d, unsigned int type)
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index 85aa5d0b935..ab81339a859 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -216,14 +216,15 @@ static inline int gpio_to_irq(unsigned gpio)
 	return -EINVAL;
 }
 
-static inline int gpio_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
+static inline int gpiochip_lock_as_irq(struct gpio_chip *chip,
+				       unsigned int offset)
 {
 	WARN_ON(1);
 	return -EINVAL;
 }
 
-static inline void gpio_unlock_as_irq(struct gpio_chip *chip,
-				      unsigned int offset)
+static inline void gpiochip_unlock_as_irq(struct gpio_chip *chip,
+					  unsigned int offset)
 {
 	WARN_ON(1);
 }
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 249db3057e4..ff200a75501 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -149,8 +149,8 @@ extern struct gpio_chip *gpiochip_find(void *data,
 			      int (*match)(struct gpio_chip *chip, void *data));
 
 /* lock/unlock as IRQ */
-int gpio_lock_as_irq(struct gpio_chip *chip, unsigned int offset);
-void gpio_unlock_as_irq(struct gpio_chip *chip, unsigned int offset);
+int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset);
+void gpiochip_unlock_as_irq(struct gpio_chip *chip, unsigned int offset);
 
 struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc);
 
-- 
cgit v1.2.3-70-g09d2


From 859b2e374a86482004d1b8b94c1666269e1d7fd6 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vinod.koul@intel.com>
Date: Tue, 28 Oct 2014 21:25:13 +0530
Subject: ALSA: compress: fix documentation errors

Some structure documentation was not right so fix it now

Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/compress_driver.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index ae6c3b8ed2f..396e8f73670 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -42,12 +42,11 @@ struct snd_compr_ops;
  * @buffer_size: size of the above buffer
  * @fragment_size: size of buffer fragment in bytes
  * @fragments: number of such fragments
- * @hw_pointer: offset of last location in buffer where DSP copied data
- * @app_pointer: offset of last location in buffer where app wrote data
  * @total_bytes_available: cumulative number of bytes made available in
  *	the ring buffer
  * @total_bytes_transferred: cumulative bytes transferred by offload DSP
  * @sleep: poll sleep
+ * @private_data: driver private data pointer
  */
 struct snd_compr_runtime {
 	snd_pcm_state_t state;
@@ -94,6 +93,8 @@ struct snd_compr_stream {
  * This can be called in during stream creation only to set codec params
  * and the stream properties
  * @get_params: retrieve the codec parameters, mandatory
+ * @set_metadata: Set the metadata values for a stream
+ * @get_metadata: retreives the requested metadata values from stream
  * @trigger: Trigger operations like start, pause, resume, drain, stop.
  * This callback is mandatory
  * @pointer: Retrieve current h/w pointer information. Mandatory
-- 
cgit v1.2.3-70-g09d2


From 4bb1231a5f3262eec8d879386b88b4d48082fd46 Mon Sep 17 00:00:00 2001
From: Prabhakar Lad <prabhakar.csengg@gmail.com>
Date: Sun, 12 Oct 2014 17:40:37 -0300
Subject: [media] media: davinci: vpbe: use fh handling provided by v4l

this patch converts the driver to use fh handling provided by the
v4l core instead of driver doing it.

Signed-off-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/platform/davinci/vpbe_display.c | 189 +++++++++-----------------
 include/media/davinci/vpbe_display.h          |  11 --
 2 files changed, 65 insertions(+), 135 deletions(-)

(limited to 'include')

diff --git a/drivers/media/platform/davinci/vpbe_display.c b/drivers/media/platform/davinci/vpbe_display.c
index fc3bdb6afaf..970242caad4 100644
--- a/drivers/media/platform/davinci/vpbe_display.c
+++ b/drivers/media/platform/davinci/vpbe_display.c
@@ -628,8 +628,8 @@ static int vpbe_try_format(struct vpbe_display *disp_dev,
 static int vpbe_display_querycap(struct file *file, void  *priv,
 			       struct v4l2_capability *cap)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 
 	cap->version = VPBE_DISPLAY_VERSION_CODE;
 	cap->device_caps = V4L2_CAP_VIDEO_OUTPUT | V4L2_CAP_STREAMING;
@@ -646,9 +646,8 @@ static int vpbe_display_querycap(struct file *file, void  *priv,
 static int vpbe_display_s_crop(struct file *file, void *priv,
 			     const struct v4l2_crop *crop)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_layer *layer = fh->layer;
-	struct vpbe_display *disp_dev = fh->disp_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_display *disp_dev = layer->disp_dev;
 	struct vpbe_device *vpbe_dev = disp_dev->vpbe_dev;
 	struct osd_layer_config *cfg = &layer->layer_info.config;
 	struct osd_state *osd_device = disp_dev->osd_device;
@@ -715,11 +714,10 @@ static int vpbe_display_s_crop(struct file *file, void *priv,
 static int vpbe_display_g_crop(struct file *file, void *priv,
 			     struct v4l2_crop *crop)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_layer *layer = fh->layer;
+	struct vpbe_layer *layer = video_drvdata(file);
 	struct osd_layer_config *cfg = &layer->layer_info.config;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
-	struct osd_state *osd_device = fh->disp_dev->osd_device;
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
+	struct osd_state *osd_device = layer->disp_dev->osd_device;
 	struct v4l2_rect *rect = &crop->c;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,
@@ -743,8 +741,8 @@ static int vpbe_display_g_crop(struct file *file, void *priv,
 static int vpbe_display_cropcap(struct file *file, void *priv,
 			      struct v4l2_cropcap *cropcap)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "VIDIOC_CROPCAP ioctl\n");
 
@@ -761,9 +759,8 @@ static int vpbe_display_cropcap(struct file *file, void *priv,
 static int vpbe_display_g_fmt(struct file *file, void *priv,
 				struct v4l2_format *fmt)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_layer *layer = fh->layer;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,
 			"VIDIOC_G_FMT, layer id = %d\n",
@@ -783,9 +780,8 @@ static int vpbe_display_g_fmt(struct file *file, void *priv,
 static int vpbe_display_enum_fmt(struct file *file, void  *priv,
 				   struct v4l2_fmtdesc *fmt)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_layer *layer = fh->layer;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 	unsigned int index = 0;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,
@@ -815,9 +811,8 @@ static int vpbe_display_enum_fmt(struct file *file, void  *priv,
 static int vpbe_display_s_fmt(struct file *file, void *priv,
 				struct v4l2_format *fmt)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_layer *layer = fh->layer;
-	struct vpbe_display *disp_dev = fh->disp_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_display *disp_dev = layer->disp_dev;
 	struct vpbe_device *vpbe_dev = disp_dev->vpbe_dev;
 	struct osd_layer_config *cfg  = &layer->layer_info.config;
 	struct v4l2_pix_format *pixfmt = &fmt->fmt.pix;
@@ -904,9 +899,9 @@ static int vpbe_display_s_fmt(struct file *file, void *priv,
 static int vpbe_display_try_fmt(struct file *file, void *priv,
 				  struct v4l2_format *fmt)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_display *disp_dev = fh->disp_dev;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_display *disp_dev = layer->disp_dev;
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 	struct v4l2_pix_format *pixfmt = &fmt->fmt.pix;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "VIDIOC_TRY_FMT\n");
@@ -930,9 +925,8 @@ static int vpbe_display_try_fmt(struct file *file, void *priv,
 static int vpbe_display_s_std(struct file *file, void *priv,
 				v4l2_std_id std_id)
 {
-	struct vpbe_fh *fh = priv;
-	struct vpbe_layer *layer = fh->layer;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 	int ret;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "VIDIOC_S_STD\n");
@@ -965,8 +959,8 @@ static int vpbe_display_s_std(struct file *file, void *priv,
 static int vpbe_display_g_std(struct file *file, void *priv,
 				v4l2_std_id *std_id)
 {
-	struct vpbe_fh *fh = priv;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,	"VIDIOC_G_STD\n");
 
@@ -988,8 +982,8 @@ static int vpbe_display_g_std(struct file *file, void *priv,
 static int vpbe_display_enum_output(struct file *file, void *priv,
 				    struct v4l2_output *output)
 {
-	struct vpbe_fh *fh = priv;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 	int ret;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,	"VIDIOC_ENUM_OUTPUT\n");
@@ -1016,9 +1010,8 @@ static int vpbe_display_enum_output(struct file *file, void *priv,
 static int vpbe_display_s_output(struct file *file, void *priv,
 				unsigned int i)
 {
-	struct vpbe_fh *fh = priv;
-	struct vpbe_layer *layer = fh->layer;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 	int ret;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,	"VIDIOC_S_OUTPUT\n");
@@ -1047,8 +1040,8 @@ static int vpbe_display_s_output(struct file *file, void *priv,
 static int vpbe_display_g_output(struct file *file, void *priv,
 				unsigned int *i)
 {
-	struct vpbe_fh *fh = priv;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "VIDIOC_G_OUTPUT\n");
 	/* Get the standard from the current encoder */
@@ -1067,8 +1060,8 @@ static int
 vpbe_display_enum_dv_timings(struct file *file, void *priv,
 			struct v4l2_enum_dv_timings *timings)
 {
-	struct vpbe_fh *fh = priv;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 	int ret;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "VIDIOC_ENUM_DV_TIMINGS\n");
@@ -1097,9 +1090,8 @@ static int
 vpbe_display_s_dv_timings(struct file *file, void *priv,
 				struct v4l2_dv_timings *timings)
 {
-	struct vpbe_fh *fh = priv;
-	struct vpbe_layer *layer = fh->layer;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 	int ret;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "VIDIOC_S_DV_TIMINGS\n");
@@ -1135,8 +1127,8 @@ static int
 vpbe_display_g_dv_timings(struct file *file, void *priv,
 				struct v4l2_dv_timings *dv_timings)
 {
-	struct vpbe_fh *fh = priv;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "VIDIOC_G_DV_TIMINGS\n");
 
@@ -1155,10 +1147,9 @@ vpbe_display_g_dv_timings(struct file *file, void *priv,
 static int vpbe_display_streamoff(struct file *file, void *priv,
 				enum v4l2_buf_type buf_type)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_layer *layer = fh->layer;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
-	struct osd_state *osd_device = fh->disp_dev->osd_device;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
+	struct osd_state *osd_device = layer->disp_dev->osd_device;
 	int ret;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,
@@ -1170,12 +1161,6 @@ static int vpbe_display_streamoff(struct file *file, void *priv,
 		return -EINVAL;
 	}
 
-	/* If io is allowed for this file handle, return error */
-	if (!fh->io_allowed) {
-		v4l2_err(&vpbe_dev->v4l2_dev, "No io_allowed\n");
-		return -EACCES;
-	}
-
 	/* If streaming is not started, return error */
 	if (!layer->started) {
 		v4l2_err(&vpbe_dev->v4l2_dev, "streaming not started in layer"
@@ -1194,10 +1179,9 @@ static int vpbe_display_streamoff(struct file *file, void *priv,
 static int vpbe_display_streamon(struct file *file, void *priv,
 			 enum v4l2_buf_type buf_type)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_layer *layer = fh->layer;
-	struct vpbe_display *disp_dev = fh->disp_dev;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_display *disp_dev = layer->disp_dev;
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 	struct osd_state *osd_device = disp_dev->osd_device;
 	int ret;
 
@@ -1212,11 +1196,6 @@ static int vpbe_display_streamon(struct file *file, void *priv,
 		return -EINVAL;
 	}
 
-	/* If file handle is not allowed IO, return error */
-	if (!fh->io_allowed) {
-		v4l2_err(&vpbe_dev->v4l2_dev, "No io_allowed\n");
-		return -EACCES;
-	}
 	/* If Streaming is already started, return error */
 	if (layer->started) {
 		v4l2_err(&vpbe_dev->v4l2_dev, "layer is already streaming\n");
@@ -1239,9 +1218,8 @@ static int vpbe_display_streamon(struct file *file, void *priv,
 static int vpbe_display_dqbuf(struct file *file, void *priv,
 		      struct v4l2_buffer *buf)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_layer *layer = fh->layer;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 	int ret;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,
@@ -1252,11 +1230,6 @@ static int vpbe_display_dqbuf(struct file *file, void *priv,
 		v4l2_err(&vpbe_dev->v4l2_dev, "Invalid buffer type\n");
 		return -EINVAL;
 	}
-	/* If this file handle is not allowed to do IO, return error */
-	if (!fh->io_allowed) {
-		v4l2_err(&vpbe_dev->v4l2_dev, "No io_allowed\n");
-		return -EACCES;
-	}
 	if (file->f_flags & O_NONBLOCK)
 		/* Call videobuf_dqbuf for non blocking mode */
 		ret = vb2_dqbuf(&layer->buffer_queue, buf, 1);
@@ -1270,9 +1243,8 @@ static int vpbe_display_dqbuf(struct file *file, void *priv,
 static int vpbe_display_qbuf(struct file *file, void *priv,
 		     struct v4l2_buffer *p)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_layer *layer = fh->layer;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,
 		"VIDIOC_QBUF, layer id = %d\n",
@@ -1283,21 +1255,14 @@ static int vpbe_display_qbuf(struct file *file, void *priv,
 		return -EINVAL;
 	}
 
-	/* If this file handle is not allowed to do IO, return error */
-	if (!fh->io_allowed) {
-		v4l2_err(&vpbe_dev->v4l2_dev, "No io_allowed\n");
-		return -EACCES;
-	}
-
 	return vb2_qbuf(&layer->buffer_queue, p);
 }
 
 static int vpbe_display_querybuf(struct file *file, void *priv,
 			 struct v4l2_buffer *buf)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_layer *layer = fh->layer;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,
 		"VIDIOC_QUERYBUF, layer id = %d\n",
@@ -1314,9 +1279,8 @@ static int vpbe_display_querybuf(struct file *file, void *priv,
 static int vpbe_display_reqbufs(struct file *file, void *priv,
 			struct v4l2_requestbuffers *req_buf)
 {
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_layer *layer = fh->layer;
-	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_layer *layer = video_drvdata(file);
+	struct vpbe_device *vpbe_dev = layer->disp_dev->vpbe_dev;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "vpbe_display_reqbufs\n");
 
@@ -1330,8 +1294,6 @@ static int vpbe_display_reqbufs(struct file *file, void *priv,
 		v4l2_err(&vpbe_dev->v4l2_dev, "not IO user\n");
 		return -EBUSY;
 	}
-	/* Set io allowed member of file handle to TRUE */
-	fh->io_allowed = 1;
 	/* Increment io usrs member of layer object to 1 */
 	layer->io_usrs = 1;
 	/* Store type of memory requested in layer object */
@@ -1347,30 +1309,22 @@ static int vpbe_display_reqbufs(struct file *file, void *priv,
  */
 static int vpbe_display_open(struct file *file)
 {
-	struct vpbe_fh *fh = NULL;
 	struct vpbe_layer *layer = video_drvdata(file);
-	struct video_device *vdev = video_devdata(file);
 	struct vpbe_display *disp_dev = layer->disp_dev;
 	struct vpbe_device *vpbe_dev = disp_dev->vpbe_dev;
 	struct osd_state *osd_device = disp_dev->osd_device;
 	int err;
 
-	/* Allocate memory for the file handle object */
-	fh = kmalloc(sizeof(struct vpbe_fh), GFP_KERNEL);
-	if (fh == NULL) {
-		v4l2_err(&vpbe_dev->v4l2_dev,
-			"unable to allocate memory for file handle object\n");
-		return -ENOMEM;
+	/* creating context for file descriptor */
+	err = v4l2_fh_open(file);
+	if (err) {
+		v4l2_err(&vpbe_dev->v4l2_dev, "v4l2_fh_open failed\n");
+		return err;
 	}
-	v4l2_fh_init(&fh->fh, vdev);
-	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,
-			"vpbe display open plane = %d\n",
-			layer->device_id);
 
-	/* store pointer to fh in private_data member of filep */
-	file->private_data = fh;
-	fh->layer = layer;
-	fh->disp_dev = disp_dev;
+	/* leaving if layer is already initialized */
+	if (!v4l2_fh_is_singular_file(file))
+		return err;
 
 	if (!layer->usrs) {
 		if (mutex_lock_interruptible(&layer->opslock))
@@ -1383,15 +1337,12 @@ static int vpbe_display_open(struct file *file)
 			/* Couldn't get layer */
 			v4l2_err(&vpbe_dev->v4l2_dev,
 				"Display Manager failed to allocate layer\n");
-			kfree(fh);
+			v4l2_fh_release(file);
 			return -EINVAL;
 		}
 	}
 	/* Increment layer usrs counter */
 	layer->usrs++;
-	/* Set io_allowed member to false */
-	fh->io_allowed = 0;
-	v4l2_fh_add(&fh->fh);
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,
 			"vpbe display device opened successfully\n");
 	return 0;
@@ -1404,26 +1355,21 @@ static int vpbe_display_open(struct file *file)
  */
 static int vpbe_display_release(struct file *file)
 {
-	/* Get the layer object and file handle object */
-	struct vpbe_fh *fh = file->private_data;
-	struct vpbe_layer *layer = fh->layer;
+	struct vpbe_layer *layer = video_drvdata(file);
 	struct osd_layer_config *cfg  = &layer->layer_info.config;
-	struct vpbe_display *disp_dev = fh->disp_dev;
+	struct vpbe_display *disp_dev = layer->disp_dev;
 	struct vpbe_device *vpbe_dev = disp_dev->vpbe_dev;
 	struct osd_state *osd_device = disp_dev->osd_device;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "vpbe_display_release\n");
 
 	mutex_lock(&layer->opslock);
-	/* if this instance is doing IO */
-	if (fh->io_allowed) {
-		/* Reset io_usrs member of layer object */
-		layer->io_usrs = 0;
+	/* Reset io_usrs member of layer object */
+	layer->io_usrs = 0;
 
-		osd_device->ops.disable_layer(osd_device,
-				layer->layer_info.id);
-		layer->started = 0;
-	}
+	osd_device->ops.disable_layer(osd_device,
+			layer->layer_info.id);
+	layer->started = 0;
 
 	/* Decrement layer usrs counter */
 	layer->usrs--;
@@ -1444,14 +1390,9 @@ static int vpbe_display_release(struct file *file)
 				layer->layer_info.id);
 	}
 
-	v4l2_fh_del(&fh->fh);
-	v4l2_fh_exit(&fh->fh);
-	file->private_data = NULL;
+	_vb2_fop_release(file, NULL);
 	mutex_unlock(&layer->opslock);
 
-	/* Free memory allocated to file handle object */
-	kfree(fh);
-
 	disp_dev->cbcr_ofst = 0;
 
 	return 0;
diff --git a/include/media/davinci/vpbe_display.h b/include/media/davinci/vpbe_display.h
index 637749a9143..06ea81576e5 100644
--- a/include/media/davinci/vpbe_display.h
+++ b/include/media/davinci/vpbe_display.h
@@ -131,17 +131,6 @@ struct vpbe_display {
 	struct osd_state *osd_device;
 };
 
-/* File handle structure */
-struct vpbe_fh {
-	struct v4l2_fh fh;
-	/* vpbe device structure */
-	struct vpbe_display *disp_dev;
-	/* pointer to layer object for opened device */
-	struct vpbe_layer *layer;
-	/* Indicates whether this file handle is doing IO */
-	unsigned char io_allowed;
-};
-
 struct buf_config_params {
 	unsigned char min_numbuffers;
 	unsigned char numbuffers[VPBE_DISPLAY_MAX_DEVICES];
-- 
cgit v1.2.3-70-g09d2


From 1b73f03cbf483dbf986cb299f6d6c4ebdfbe6ba7 Mon Sep 17 00:00:00 2001
From: Prabhakar Lad <prabhakar.csengg@gmail.com>
Date: Sun, 12 Oct 2014 17:40:42 -0300
Subject: [media] media: davinci: vpbe: use helpers provided by core if
 streaming is started

this patch uses vb2_is_busy() helper to check if streaming is
actually started, instead of driver managing it.

Signed-off-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/platform/davinci/vpbe_display.c | 34 ++++++++-------------------
 include/media/davinci/vpbe_display.h          |  4 ----
 2 files changed, 10 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/media/platform/davinci/vpbe_display.c b/drivers/media/platform/davinci/vpbe_display.c
index 26d2335fe41..57dc4951c97 100644
--- a/drivers/media/platform/davinci/vpbe_display.c
+++ b/drivers/media/platform/davinci/vpbe_display.c
@@ -152,8 +152,8 @@ static irqreturn_t venc_isr(int irq, void *arg)
 
 	for (i = 0; i < VPBE_DISPLAY_MAX_DEVICES; i++) {
 		layer = disp_dev->dev[i];
-		/* If streaming is started in this layer */
-		if (!layer->started)
+
+		if (!vb2_start_streaming_called(&layer->buffer_queue))
 			continue;
 
 		if (layer->layer_first_int) {
@@ -314,7 +314,6 @@ static int vpbe_start_streaming(struct vb2_queue *vq, unsigned int count)
 	 * if request format is yuv420 semiplanar, need to
 	 * enable both video windows
 	 */
-	layer->started = 1;
 	layer->layer_first_int = 1;
 
 	return ret;
@@ -829,11 +828,9 @@ static int vpbe_display_s_fmt(struct file *file, void *priv,
 			"VIDIOC_S_FMT, layer id = %d\n",
 			layer->device_id);
 
-	/* If streaming is started, return error */
-	if (layer->started) {
-		v4l2_err(&vpbe_dev->v4l2_dev, "Streaming is started\n");
+	if (vb2_is_busy(&layer->buffer_queue))
 		return -EBUSY;
-	}
+
 	if (V4L2_BUF_TYPE_VIDEO_OUTPUT != fmt->type) {
 		v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "invalid type\n");
 		return -EINVAL;
@@ -937,11 +934,9 @@ static int vpbe_display_s_std(struct file *file, void *priv,
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "VIDIOC_S_STD\n");
 
-	/* If streaming is started, return error */
-	if (layer->started) {
-		v4l2_err(&vpbe_dev->v4l2_dev, "Streaming is started\n");
+	if (vb2_is_busy(&layer->buffer_queue))
 		return -EBUSY;
-	}
+
 	if (NULL != vpbe_dev->ops.s_std) {
 		ret = vpbe_dev->ops.s_std(vpbe_dev, std_id);
 		if (ret) {
@@ -1021,11 +1016,10 @@ static int vpbe_display_s_output(struct file *file, void *priv,
 	int ret;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,	"VIDIOC_S_OUTPUT\n");
-	/* If streaming is started, return error */
-	if (layer->started) {
-		v4l2_err(&vpbe_dev->v4l2_dev, "Streaming is started\n");
+
+	if (vb2_is_busy(&layer->buffer_queue))
 		return -EBUSY;
-	}
+
 	if (NULL == vpbe_dev->ops.set_output)
 		return -EINVAL;
 
@@ -1102,12 +1096,8 @@ vpbe_display_s_dv_timings(struct file *file, void *priv,
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "VIDIOC_S_DV_TIMINGS\n");
 
-
-	/* If streaming is started, return error */
-	if (layer->started) {
-		v4l2_err(&vpbe_dev->v4l2_dev, "Streaming is started\n");
+	if (vb2_is_busy(&layer->buffer_queue))
 		return -EBUSY;
-	}
 
 	/* Set the given standard in the encoder */
 	if (!vpbe_dev->ops.s_dv_timings)
@@ -1212,13 +1202,9 @@ static int vpbe_display_release(struct file *file)
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "vpbe_display_release\n");
 
 	mutex_lock(&layer->opslock);
-	/* Reset io_usrs member of layer object */
-	layer->io_usrs = 0;
 
 	osd_device->ops.disable_layer(osd_device,
 			layer->layer_info.id);
-	layer->started = 0;
-
 	/* Decrement layer usrs counter */
 	layer->usrs--;
 	/* If this file handle has initialize encoder device, reset it */
diff --git a/include/media/davinci/vpbe_display.h b/include/media/davinci/vpbe_display.h
index 06ea81576e5..de0843d6f05 100644
--- a/include/media/davinci/vpbe_display.h
+++ b/include/media/davinci/vpbe_display.h
@@ -106,12 +106,8 @@ struct vpbe_layer {
 	unsigned char window_enable;
 	/* number of open instances of the layer */
 	unsigned int usrs;
-	/* number of users performing IO */
-	unsigned int io_usrs;
 	/* Indicates id of the field which is being displayed */
 	unsigned int field_id;
-	/* Indicates whether streaming started */
-	unsigned char started;
 	/* Identifies device object */
 	enum vpbe_display_device_id device_id;
 	/* facilitation of ioctl ops lock by v4l2*/
-- 
cgit v1.2.3-70-g09d2


From 8a93dbc1f4d5c33b444d561a8f4c4ddfc2e7cb74 Mon Sep 17 00:00:00 2001
From: Prabhakar Lad <prabhakar.csengg@gmail.com>
Date: Sun, 12 Oct 2014 17:40:43 -0300
Subject: [media] media: davinci: vpbe: drop unused member memory from
 vpbe_layer

Signed-off-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/davinci/vpbe_display.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/media/davinci/vpbe_display.h b/include/media/davinci/vpbe_display.h
index de0843d6f05..163a02b92c0 100644
--- a/include/media/davinci/vpbe_display.h
+++ b/include/media/davinci/vpbe_display.h
@@ -91,10 +91,6 @@ struct vpbe_layer {
 	/* V4l2 specific parameters */
 	/* Identifies video device for this layer */
 	struct video_device video_dev;
-	/* This field keeps track of type of buffer exchange mechanism user
-	 * has selected
-	 */
-	enum v4l2_memory memory;
 	/* Used to store pixel format */
 	struct v4l2_pix_format pix_fmt;
 	enum v4l2_field buf_field;
-- 
cgit v1.2.3-70-g09d2


From 95f259ca3bf485a0c1f17d9024813d4aab485a23 Mon Sep 17 00:00:00 2001
From: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Date: Sat, 25 Oct 2014 12:08:59 +0200
Subject: net: pxa168_eth: Fix providing of phy_interface mode on platform_data

Do not add phy include to the board file but platform_data include
instead.

Signed-off-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/mach-mmp/gplugd.c | 1 -
 include/linux/pxa168_eth.h | 2 ++
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/arm/mach-mmp/gplugd.c b/arch/arm/mach-mmp/gplugd.c
index 3b5794cd035..22762a1f9f7 100644
--- a/arch/arm/mach-mmp/gplugd.c
+++ b/arch/arm/mach-mmp/gplugd.c
@@ -12,7 +12,6 @@
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
 #include <linux/gpio-pxa.h>
-#include <linux/phy.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach-types.h>
diff --git a/include/linux/pxa168_eth.h b/include/linux/pxa168_eth.h
index 37c381120bc..e1ab6e86cdb 100644
--- a/include/linux/pxa168_eth.h
+++ b/include/linux/pxa168_eth.h
@@ -4,6 +4,8 @@
 #ifndef __LINUX_PXA168_ETH_H
 #define __LINUX_PXA168_ETH_H
 
+#include <linux/phy.h>
+
 struct pxa168_eth_platform_data {
 	int	port_number;
 	int	phy_addr;
-- 
cgit v1.2.3-70-g09d2


From 941d8ebcf773fd5da5c79e1c86e1afaae7032a0b Mon Sep 17 00:00:00 2001
From: Simon Horman <simon.horman@netronome.com>
Date: Mon, 27 Oct 2014 16:12:16 +0900
Subject: datapath: Rename last_action() as nla_is_last() and move to netlink.h

The original motivation for this change was to allow the helper to be used
in files other than actions.c as part of work on an odp select group
action.

It was as pointed out by Thomas Graf that this helper would be best off
living in netlink.h. Furthermore, I think that the generic nature of this
helper means it is best off in netlink.h regardless of if it is used more
than one .c file or not. Thus, I would like it considered independent of
the work on an odp select group action.

Cc: Thomas Graf <tgraf@suug.ch>
Cc: Pravin Shelar <pshelar@nicira.com>
Cc: Andy Zhou <azhou@nicira.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Thomas Graf <tgraf@noironetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h     | 10 ++++++++++
 net/openvswitch/actions.c | 11 +++--------
 2 files changed, 13 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index 7b903e1bdbb..64158353ecb 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1185,4 +1185,14 @@ static inline int nla_validate_nested(const struct nlattr *start, int maxtype,
 #define nla_for_each_nested(pos, nla, rem) \
 	nla_for_each_attr(pos, nla_data(nla), nla_len(nla), rem)
 
+/**
+ * nla_is_last - Test if attribute is last in stream
+ * @nla: attribute to test
+ * @rem: bytes remaining in stream
+ */
+static inline bool nla_is_last(const struct nlattr *nla, int rem)
+{
+	return nla->nla_len == rem;
+}
+
 #endif
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 006886dbee3..922c133b193 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -504,11 +504,6 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 	return ovs_dp_upcall(dp, skb, &upcall);
 }
 
-static bool last_action(const struct nlattr *a, int rem)
-{
-	return a->nla_len == rem;
-}
-
 static int sample(struct datapath *dp, struct sk_buff *skb,
 		  struct sw_flow_key *key, const struct nlattr *attr)
 {
@@ -543,7 +538,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 	 * user space. This skb will be consumed by its caller.
 	 */
 	if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE &&
-		   last_action(a, rem)))
+		   nla_is_last(a, rem)))
 		return output_userspace(dp, skb, key, a);
 
 	skb = skb_clone(skb, GFP_ATOMIC);
@@ -633,7 +628,7 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
 	if (err)
 		return err;
 
-	if (!last_action(a, rem)) {
+	if (!nla_is_last(a, rem)) {
 		/* Recirc action is the not the last action
 		 * of the action list, need to clone the skb.
 		 */
@@ -707,7 +702,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 		case OVS_ACTION_ATTR_RECIRC:
 			err = execute_recirc(dp, skb, key, a, rem);
-			if (last_action(a, rem)) {
+			if (nla_is_last(a, rem)) {
 				/* If this is the last action, the skb has
 				 * been consumed or freed.
 				 * Return immediately.
-- 
cgit v1.2.3-70-g09d2


From 32a173c7f9e9ec2b87142f67e1478cd20084a45b Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 27 Oct 2014 11:37:35 +0200
Subject: net/mlx4_core: Introduce mlx4_get_module_info for cable module info
 reading

Added new MAD_IFC command to read cable module info with attribute id (0xFF60).
Update include/linux/mlx4/device.h with function declaration (mlx4_get_module_info)
and the needed defines/enums for future use.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/port.c | 156 ++++++++++++++++++++++++++++++
 include/linux/mlx4/device.h               |  30 ++++++
 2 files changed, 186 insertions(+)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 94eeb2c7d7e..30eb1ead0fe 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -1311,3 +1311,159 @@ int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id,
 	return 0;
 }
 EXPORT_SYMBOL(mlx4_get_roce_gid_from_slave);
+
+/* Cable Module Info */
+#define MODULE_INFO_MAX_READ 48
+
+#define I2C_ADDR_LOW  0x50
+#define I2C_ADDR_HIGH 0x51
+#define I2C_PAGE_SIZE 256
+
+/* Module Info Data */
+struct mlx4_cable_info {
+	u8	i2c_addr;
+	u8	page_num;
+	__be16	dev_mem_address;
+	__be16	reserved1;
+	__be16	size;
+	__be32	reserved2[2];
+	u8	data[MODULE_INFO_MAX_READ];
+};
+
+enum cable_info_err {
+	 CABLE_INF_INV_PORT      = 0x1,
+	 CABLE_INF_OP_NOSUP      = 0x2,
+	 CABLE_INF_NOT_CONN      = 0x3,
+	 CABLE_INF_NO_EEPRM      = 0x4,
+	 CABLE_INF_PAGE_ERR      = 0x5,
+	 CABLE_INF_INV_ADDR      = 0x6,
+	 CABLE_INF_I2C_ADDR      = 0x7,
+	 CABLE_INF_QSFP_VIO      = 0x8,
+	 CABLE_INF_I2C_BUSY      = 0x9,
+};
+
+#define MAD_STATUS_2_CABLE_ERR(mad_status) ((mad_status >> 8) & 0xFF)
+
+static inline const char *cable_info_mad_err_str(u16 mad_status)
+{
+	u8 err = MAD_STATUS_2_CABLE_ERR(mad_status);
+
+	switch (err) {
+	case CABLE_INF_INV_PORT:
+		return "invalid port selected";
+	case CABLE_INF_OP_NOSUP:
+		return "operation not supported for this port (the port is of type CX4 or internal)";
+	case CABLE_INF_NOT_CONN:
+		return "cable is not connected";
+	case CABLE_INF_NO_EEPRM:
+		return "the connected cable has no EPROM (passive copper cable)";
+	case CABLE_INF_PAGE_ERR:
+		return "page number is greater than 15";
+	case CABLE_INF_INV_ADDR:
+		return "invalid device_address or size (that is, size equals 0 or address+size is greater than 256)";
+	case CABLE_INF_I2C_ADDR:
+		return "invalid I2C slave address";
+	case CABLE_INF_QSFP_VIO:
+		return "at least one cable violates the QSFP specification and ignores the modsel signal";
+	case CABLE_INF_I2C_BUSY:
+		return "I2C bus is constantly busy";
+	}
+	return "Unknown Error";
+}
+
+/**
+ * mlx4_get_module_info - Read cable module eeprom data
+ * @dev: mlx4_dev.
+ * @port: port number.
+ * @offset: byte offset in eeprom to start reading data from.
+ * @size: num of bytes to read.
+ * @data: output buffer to put the requested data into.
+ *
+ * Reads cable module eeprom data, puts the outcome data into
+ * data pointer paramer.
+ * Returns num of read bytes on success or a negative error
+ * code.
+ */
+int mlx4_get_module_info(struct mlx4_dev *dev, u8 port,
+			 u16 offset, u16 size, u8 *data)
+{
+	struct mlx4_cmd_mailbox *inbox, *outbox;
+	struct mlx4_mad_ifc *inmad, *outmad;
+	struct mlx4_cable_info *cable_info;
+	u16 i2c_addr;
+	int ret;
+
+	if (size > MODULE_INFO_MAX_READ)
+		size = MODULE_INFO_MAX_READ;
+
+	inbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(inbox))
+		return PTR_ERR(inbox);
+
+	outbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(outbox)) {
+		mlx4_free_cmd_mailbox(dev, inbox);
+		return PTR_ERR(outbox);
+	}
+
+	inmad = (struct mlx4_mad_ifc *)(inbox->buf);
+	outmad = (struct mlx4_mad_ifc *)(outbox->buf);
+
+	inmad->method = 0x1; /* Get */
+	inmad->class_version = 0x1;
+	inmad->mgmt_class = 0x1;
+	inmad->base_version = 0x1;
+	inmad->attr_id = cpu_to_be16(0xFF60); /* Module Info */
+
+	if (offset < I2C_PAGE_SIZE && offset + size > I2C_PAGE_SIZE)
+		/* Cross pages reads are not allowed
+		 * read until offset 256 in low page
+		 */
+		size -= offset + size - I2C_PAGE_SIZE;
+
+	i2c_addr = I2C_ADDR_LOW;
+	if (offset >= I2C_PAGE_SIZE) {
+		/* Reset offset to high page */
+		i2c_addr = I2C_ADDR_HIGH;
+		offset -= I2C_PAGE_SIZE;
+	}
+
+	cable_info = (struct mlx4_cable_info *)inmad->data;
+	cable_info->dev_mem_address = cpu_to_be16(offset);
+	cable_info->page_num = 0;
+	cable_info->i2c_addr = i2c_addr;
+	cable_info->size = cpu_to_be16(size);
+
+	ret = mlx4_cmd_box(dev, inbox->dma, outbox->dma, port, 3,
+			   MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C,
+			   MLX4_CMD_NATIVE);
+	if (ret)
+		goto out;
+
+	if (be16_to_cpu(outmad->status)) {
+		/* Mad returned with bad status */
+		ret = be16_to_cpu(outmad->status);
+		mlx4_warn(dev,
+			  "MLX4_CMD_MAD_IFC Get Module info attr(%x) port(%d) i2c_addr(%x) offset(%d) size(%d): Response Mad Status(%x) - %s\n",
+			  0xFF60, port, i2c_addr, offset, size,
+			  ret, cable_info_mad_err_str(ret));
+
+		if (i2c_addr == I2C_ADDR_HIGH &&
+		    MAD_STATUS_2_CABLE_ERR(ret) == CABLE_INF_I2C_ADDR)
+			/* Some SFP cables do not support i2c slave
+			 * address 0x51 (high page), abort silently.
+			 */
+			ret = 0;
+		else
+			ret = -ret;
+		goto out;
+	}
+	cable_info = (struct mlx4_cable_info *)outmad->data;
+	memcpy(data, cable_info->data, size);
+	ret = size;
+out:
+	mlx4_free_cmd_mailbox(dev, inbox);
+	mlx4_free_cmd_mailbox(dev, outbox);
+	return ret;
+}
+EXPORT_SYMBOL(mlx4_get_module_info);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 37e4404d022..73910daec31 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -379,6 +379,13 @@ enum {
 #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \
 			     MLX4_EQ_PORT_INFO_MSTR_SM_LID_CHANGE_MASK)
 
+enum mlx4_module_id {
+	MLX4_MODULE_ID_SFP              = 0x3,
+	MLX4_MODULE_ID_QSFP             = 0xC,
+	MLX4_MODULE_ID_QSFP_PLUS        = 0xD,
+	MLX4_MODULE_ID_QSFP28           = 0x11,
+};
+
 static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor)
 {
 	return (major << 32) | (minor << 16) | subminor;
@@ -799,6 +806,26 @@ struct mlx4_init_port_param {
 	u64			si_guid;
 };
 
+#define MAD_IFC_DATA_SZ 192
+/* MAD IFC Mailbox */
+struct mlx4_mad_ifc {
+	u8	base_version;
+	u8	mgmt_class;
+	u8	class_version;
+	u8	method;
+	__be16	status;
+	__be16	class_specific;
+	__be64	tid;
+	__be16	attr_id;
+	__be16	resv;
+	__be32	attr_mod;
+	__be64	mkey;
+	__be16	dr_slid;
+	__be16	dr_dlid;
+	u8	reserved[28];
+	u8	data[MAD_IFC_DATA_SZ];
+} __packed;
+
 #define mlx4_foreach_port(port, dev, type)				\
 	for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++)	\
 		if ((type) == (dev)->caps.port_mask[(port)])
@@ -1283,6 +1310,9 @@ int mlx4_mr_rereg_mem_write(struct mlx4_dev *dev, struct mlx4_mr *mr,
 			    u64 iova, u64 size, int npages,
 			    int page_shift, struct mlx4_mpt_entry *mpt_entry);
 
+int mlx4_get_module_info(struct mlx4_dev *dev, u8 port,
+			 u16 offset, u16 size, u8 *data);
+
 /* Returns true if running in low memory profile (kdump kernel) */
 static inline bool mlx4_low_memory_profile(void)
 {
-- 
cgit v1.2.3-70-g09d2


From 7202da8b7f7131d25411d81aa557e28cd941c5b6 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 27 Oct 2014 11:37:36 +0200
Subject: ethtool, net/mlx4_en: Cable info, get_module_info/eeprom ethtool
 support

Added support for get_module_info/get_module_eeprom ethtool support for cable info reading.

Added new cable types enum in include/uapi/linux/ethtool.h for ethtool use.
+#define ETH_MODULE_SFF_8636            0x3
+#define ETH_MODULE_SFF_8636_LEN        256
+#define ETH_MODULE_SFF_8436            0x4
+#define ETH_MODULE_SFF_8436_LEN        256

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 83 +++++++++++++++++++++++++
 include/uapi/linux/ethtool.h                    |  4 ++
 2 files changed, 87 insertions(+)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index ae83da9cd18..279f4233de5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -35,6 +35,7 @@
 #include <linux/ethtool.h>
 #include <linux/netdevice.h>
 #include <linux/mlx4/driver.h>
+#include <linux/mlx4/device.h>
 #include <linux/in.h>
 #include <net/ip.h>
 
@@ -1309,6 +1310,86 @@ static int mlx4_en_set_tunable(struct net_device *dev,
 	return ret;
 }
 
+static int mlx4_en_get_module_info(struct net_device *dev,
+				   struct ethtool_modinfo *modinfo)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	int ret;
+	u8 data[4];
+
+	/* Read first 2 bytes to get Module & REV ID */
+	ret = mlx4_get_module_info(mdev->dev, priv->port,
+				   0/*offset*/, 2/*size*/, data);
+	if (ret < 2)
+		return -EIO;
+
+	switch (data[0] /* identifier */) {
+	case MLX4_MODULE_ID_QSFP:
+		modinfo->type = ETH_MODULE_SFF_8436;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+		break;
+	case MLX4_MODULE_ID_QSFP_PLUS:
+		if (data[1] >= 0x3) { /* revision id */
+			modinfo->type = ETH_MODULE_SFF_8636;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+		} else {
+			modinfo->type = ETH_MODULE_SFF_8436;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+		}
+		break;
+	case MLX4_MODULE_ID_QSFP28:
+		modinfo->type = ETH_MODULE_SFF_8636;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+		break;
+	case MLX4_MODULE_ID_SFP:
+		modinfo->type = ETH_MODULE_SFF_8472;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		break;
+	default:
+		return -ENOSYS;
+	}
+
+	return 0;
+}
+
+static int mlx4_en_get_module_eeprom(struct net_device *dev,
+				     struct ethtool_eeprom *ee,
+				     u8 *data)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	int offset = ee->offset;
+	int i = 0, ret;
+
+	if (ee->len == 0)
+		return -EINVAL;
+
+	memset(data, 0, ee->len);
+
+	while (i < ee->len) {
+		en_dbg(DRV, priv,
+		       "mlx4_get_module_info i(%d) offset(%d) len(%d)\n",
+		       i, offset, ee->len - i);
+
+		ret = mlx4_get_module_info(mdev->dev, priv->port,
+					   offset, ee->len - i, data + i);
+
+		if (!ret) /* Done reading */
+			return 0;
+
+		if (ret < 0) {
+			en_err(priv,
+			       "mlx4_get_module_info i(%d) offset(%d) bytes_to_read(%d) - FAILED (0x%x)\n",
+			       i, offset, ee->len - i, ret);
+			return 0;
+		}
+
+		i += ret;
+		offset += ret;
+	}
+	return 0;
+}
 
 const struct ethtool_ops mlx4_en_ethtool_ops = {
 	.get_drvinfo = mlx4_en_get_drvinfo,
@@ -1341,6 +1422,8 @@ const struct ethtool_ops mlx4_en_ethtool_ops = {
 	.get_priv_flags = mlx4_en_get_priv_flags,
 	.get_tunable		= mlx4_en_get_tunable,
 	.set_tunable		= mlx4_en_set_tunable,
+	.get_module_info = mlx4_en_get_module_info,
+	.get_module_eeprom = mlx4_en_get_module_eeprom
 };
 
 
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 99b43056a6f..b6acd78b821 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1343,6 +1343,10 @@ enum ethtool_sfeatures_retval_bits {
 #define ETH_MODULE_SFF_8079_LEN		256
 #define ETH_MODULE_SFF_8472		0x2
 #define ETH_MODULE_SFF_8472_LEN		512
+#define ETH_MODULE_SFF_8636		0x3
+#define ETH_MODULE_SFF_8636_LEN		256
+#define ETH_MODULE_SFF_8436		0x4
+#define ETH_MODULE_SFF_8436_LEN		256
 
 /* Reset flags */
 /* The reset() operation must clear the flags for the components which
-- 
cgit v1.2.3-70-g09d2


From adbc7ac5c15eb5e9d70393428345e72a1a897d6a Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 27 Oct 2014 11:37:37 +0200
Subject: net/mlx4_core: Introduce ACCESS_REG CMD and eth_prot_ctrl dev cap

Adding ACCESS REG mlx4 command and use it to implement Query method for
PTYS (Port Type and Speed Register).
Query and store eth_prot_ctrl dev cap.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c |   9 +++
 drivers/net/ethernet/mellanox/mlx4/fw.c  | 118 ++++++++++++++++++++++++++++++-
 include/linux/mlx4/cmd.h                 |   2 +
 include/linux/mlx4/device.h              |  40 ++++++++++-
 4 files changed, 166 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index b16e1b95566..916459effcf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -1338,6 +1338,15 @@ static struct mlx4_cmd_info cmd_info[] = {
 		.verify = NULL,
 		.wrapper = mlx4_QUERY_IF_STAT_wrapper
 	},
+	{
+		.opcode = MLX4_CMD_ACCESS_REG,
+		.has_inbox = true,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = NULL,
+	},
 	/* Native multicast commands are not available for guests */
 	{
 		.opcode = MLX4_CMD_QP_ATTACH,
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 2e88a235e26..6fd9b8581e9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -139,7 +139,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[10] = "TCP/IP offloads/flow-steering for VXLAN support",
 		[11] = "MAD DEMUX (Secure-Host) support",
 		[12] = "Large cache line (>64B) CQE stride support",
-		[13] = "Large cache line (>64B) EQE stride support"
+		[13] = "Large cache line (>64B) EQE stride support",
+		[14] = "Ethernet protocol control support"
 	};
 	int i;
 
@@ -560,6 +561,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET	0x76
 #define QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET	0x77
 #define QUERY_DEV_CAP_CQ_EQ_CACHE_LINE_STRIDE	0x7a
+#define QUERY_DEV_CAP_ETH_PROT_CTRL_OFFSET	0x7a
 #define QUERY_DEV_CAP_RDMARC_ENTRY_SZ_OFFSET	0x80
 #define QUERY_DEV_CAP_QPC_ENTRY_SZ_OFFSET	0x82
 #define QUERY_DEV_CAP_AUX_ENTRY_SZ_OFFSET	0x84
@@ -737,11 +739,12 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	MLX4_GET(size, outbox, QUERY_DEV_CAP_MAX_DESC_SZ_RQ_OFFSET);
 	dev_cap->max_rq_desc_sz = size;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_CQ_EQ_CACHE_LINE_STRIDE);
+	if (field & (1 << 5))
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL;
 	if (field & (1 << 6))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_CQE_STRIDE;
 	if (field & (1 << 7))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_EQE_STRIDE;
-
 	MLX4_GET(dev_cap->bmme_flags, outbox,
 		 QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
 	MLX4_GET(dev_cap->reserved_lkey, outbox,
@@ -2144,3 +2147,114 @@ out:
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	return err;
 }
+
+/* Access Reg commands */
+enum mlx4_access_reg_masks {
+	MLX4_ACCESS_REG_STATUS_MASK = 0x7f,
+	MLX4_ACCESS_REG_METHOD_MASK = 0x7f,
+	MLX4_ACCESS_REG_LEN_MASK = 0x7ff
+};
+
+struct mlx4_access_reg {
+	__be16 constant1;
+	u8 status;
+	u8 resrvd1;
+	__be16 reg_id;
+	u8 method;
+	u8 constant2;
+	__be32 resrvd2[2];
+	__be16 len_const;
+	__be16 resrvd3;
+#define MLX4_ACCESS_REG_HEADER_SIZE (20)
+	u8 reg_data[MLX4_MAILBOX_SIZE-MLX4_ACCESS_REG_HEADER_SIZE];
+} __attribute__((__packed__));
+
+/**
+ * mlx4_ACCESS_REG - Generic access reg command.
+ * @dev: mlx4_dev.
+ * @reg_id: register ID to access.
+ * @method: Access method Read/Write.
+ * @reg_len: register length to Read/Write in bytes.
+ * @reg_data: reg_data pointer to Read/Write From/To.
+ *
+ * Access ConnectX registers FW command.
+ * Returns 0 on success and copies outbox mlx4_access_reg data
+ * field into reg_data or a negative error code.
+ */
+static int mlx4_ACCESS_REG(struct mlx4_dev *dev, u16 reg_id,
+			   enum mlx4_access_reg_method method,
+			   u16 reg_len, void *reg_data)
+{
+	struct mlx4_cmd_mailbox *inbox, *outbox;
+	struct mlx4_access_reg *inbuf, *outbuf;
+	int err;
+
+	inbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(inbox))
+		return PTR_ERR(inbox);
+
+	outbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(outbox)) {
+		mlx4_free_cmd_mailbox(dev, inbox);
+		return PTR_ERR(outbox);
+	}
+
+	inbuf = inbox->buf;
+	outbuf = outbox->buf;
+
+	inbuf->constant1 = cpu_to_be16(0x1<<11 | 0x4);
+	inbuf->constant2 = 0x1;
+	inbuf->reg_id = cpu_to_be16(reg_id);
+	inbuf->method = method & MLX4_ACCESS_REG_METHOD_MASK;
+
+	reg_len = min(reg_len, (u16)(sizeof(inbuf->reg_data)));
+	inbuf->len_const =
+		cpu_to_be16(((reg_len/4 + 1) & MLX4_ACCESS_REG_LEN_MASK) |
+			    ((0x3) << 12));
+
+	memcpy(inbuf->reg_data, reg_data, reg_len);
+	err = mlx4_cmd_box(dev, inbox->dma, outbox->dma, 0, 0,
+			   MLX4_CMD_ACCESS_REG, MLX4_CMD_TIME_CLASS_C,
+			   MLX4_CMD_NATIVE);
+	if (err)
+		goto out;
+
+	if (outbuf->status & MLX4_ACCESS_REG_STATUS_MASK) {
+		err = outbuf->status & MLX4_ACCESS_REG_STATUS_MASK;
+		mlx4_err(dev,
+			 "MLX4_CMD_ACCESS_REG(%x) returned REG status (%x)\n",
+			 reg_id, err);
+		goto out;
+	}
+
+	memcpy(reg_data, outbuf->reg_data, reg_len);
+out:
+	mlx4_free_cmd_mailbox(dev, inbox);
+	mlx4_free_cmd_mailbox(dev, outbox);
+	return err;
+}
+
+/* ConnectX registers IDs */
+enum mlx4_reg_id {
+	MLX4_REG_ID_PTYS = 0x5004,
+};
+
+/**
+ * mlx4_ACCESS_PTYS_REG - Access PTYs (Port Type and Speed)
+ * register
+ * @dev: mlx4_dev.
+ * @method: Access method Read/Write.
+ * @ptys_reg: PTYS register data pointer.
+ *
+ * Access ConnectX PTYS register, to Read/Write Port Type/Speed
+ * configuration
+ * Returns 0 on success or a negative error code.
+ */
+int mlx4_ACCESS_PTYS_REG(struct mlx4_dev *dev,
+			 enum mlx4_access_reg_method method,
+			 struct mlx4_ptys_reg *ptys_reg)
+{
+	return mlx4_ACCESS_REG(dev, MLX4_REG_ID_PTYS,
+			       method, sizeof(*ptys_reg), ptys_reg);
+}
+EXPORT_SYMBOL_GPL(mlx4_ACCESS_PTYS_REG);
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index 379c02648ab..ff5f5deb3dc 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -67,6 +67,8 @@ enum {
 	MLX4_CMD_MAP_ICM_AUX	 = 0xffc,
 	MLX4_CMD_UNMAP_ICM_AUX	 = 0xffb,
 	MLX4_CMD_SET_ICM_SIZE	 = 0xffd,
+	MLX4_CMD_ACCESS_REG	 = 0x3b,
+
 	/*master notify fw on finish for slave's flr*/
 	MLX4_CMD_INFORM_FLR_DONE = 0x5b,
 	MLX4_CMD_GET_OP_REQ      = 0x59,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 73910daec31..181cd9fc90f 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -186,7 +186,8 @@ enum {
 	MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS	= 1LL <<  10,
 	MLX4_DEV_CAP_FLAG2_MAD_DEMUX		= 1LL <<  11,
 	MLX4_DEV_CAP_FLAG2_CQE_STRIDE		= 1LL <<  12,
-	MLX4_DEV_CAP_FLAG2_EQE_STRIDE		= 1LL <<  13
+	MLX4_DEV_CAP_FLAG2_EQE_STRIDE		= 1LL <<  13,
+	MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL        = 1LL <<  14
 };
 
 enum {
@@ -1319,4 +1320,41 @@ static inline bool mlx4_low_memory_profile(void)
 	return is_kdump_kernel();
 }
 
+/* ACCESS REG commands */
+enum mlx4_access_reg_method {
+	MLX4_ACCESS_REG_QUERY = 0x1,
+	MLX4_ACCESS_REG_WRITE = 0x2,
+};
+
+/* ACCESS PTYS Reg command */
+enum mlx4_ptys_proto {
+	MLX4_PTYS_IB = 1<<0,
+	MLX4_PTYS_EN = 1<<2,
+};
+
+struct mlx4_ptys_reg {
+	u8 resrvd1;
+	u8 local_port;
+	u8 resrvd2;
+	u8 proto_mask;
+	__be32 resrvd3[2];
+	__be32 eth_proto_cap;
+	__be16 ib_width_cap;
+	__be16 ib_speed_cap;
+	__be32 resrvd4;
+	__be32 eth_proto_admin;
+	__be16 ib_width_admin;
+	__be16 ib_speed_admin;
+	__be32 resrvd5;
+	__be32 eth_proto_oper;
+	__be16 ib_width_oper;
+	__be16 ib_speed_oper;
+	__be32 resrvd6;
+	__be32 eth_proto_lp_adv;
+} __packed;
+
+int mlx4_ACCESS_PTYS_REG(struct mlx4_dev *dev,
+			 enum mlx4_access_reg_method method,
+			 struct mlx4_ptys_reg *ptys_reg);
+
 #endif /* MLX4_DEVICE_H */
-- 
cgit v1.2.3-70-g09d2


From a53e3e8c1db547981e13d1ebf24a659bd4e87710 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 27 Oct 2014 11:37:38 +0200
Subject: net/mlx4_core: Add ethernet backplane autoneg device capability

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/fw.c | 7 ++++++-
 include/linux/mlx4/device.h             | 3 ++-
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 6fd9b8581e9..72289ef5ebb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -140,7 +140,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[11] = "MAD DEMUX (Secure-Host) support",
 		[12] = "Large cache line (>64B) CQE stride support",
 		[13] = "Large cache line (>64B) EQE stride support",
-		[14] = "Ethernet protocol control support"
+		[14] = "Ethernet protocol control support",
+		[15] = "Ethernet Backplane autoneg support"
 	};
 	int i;
 
@@ -575,6 +576,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_BMME_FLAGS_OFFSET		0x94
 #define QUERY_DEV_CAP_RSVD_LKEY_OFFSET		0x98
 #define QUERY_DEV_CAP_MAX_ICM_SZ_OFFSET		0xa0
+#define QUERY_DEV_CAP_ETH_BACKPL_OFFSET		0x9c
 #define QUERY_DEV_CAP_FW_REASSIGN_MAC		0x9d
 #define QUERY_DEV_CAP_VXLAN			0x9e
 #define QUERY_DEV_CAP_MAD_DEMUX_OFFSET		0xb0
@@ -749,6 +751,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		 QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
 	MLX4_GET(dev_cap->reserved_lkey, outbox,
 		 QUERY_DEV_CAP_RSVD_LKEY_OFFSET);
+	MLX4_GET(field32, outbox, QUERY_DEV_CAP_ETH_BACKPL_OFFSET);
+	if (field32 & (1 << 0))
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_FW_REASSIGN_MAC);
 	if (field & 1<<6)
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 181cd9fc90f..e4c136ebe79 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -187,7 +187,8 @@ enum {
 	MLX4_DEV_CAP_FLAG2_MAD_DEMUX		= 1LL <<  11,
 	MLX4_DEV_CAP_FLAG2_CQE_STRIDE		= 1LL <<  12,
 	MLX4_DEV_CAP_FLAG2_EQE_STRIDE		= 1LL <<  13,
-	MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL        = 1LL <<  14
+	MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL        = 1LL <<  14,
+	MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP	= 1LL <<  15
 };
 
 enum {
-- 
cgit v1.2.3-70-g09d2


From dcf972a334dd76975bf144ca57350c1f3132c947 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 27 Oct 2014 11:37:39 +0200
Subject: ethtool, net/mlx4_en: Add 100M, 20G, 56G speeds ethtool reporting
 support

Added 100M, 20G and 56G ethtool speed reporting support.
Update mlx4_en_test_speed self test with the new speeds.

Defined new link speeds in include/uapi/linux/ethtool.h:
+#define SPEED_20000	20000
+#define SPEED_40000	40000
+#define SPEED_56000	56000

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_port.c     | 15 ++++++++++++---
 drivers/net/ethernet/mellanox/mlx4/en_port.h     |  9 ++++++---
 drivers/net/ethernet/mellanox/mlx4/en_selftest.c | 12 ++++++++----
 include/uapi/linux/ethtool.h                     | 14 +++++++++++++-
 4 files changed, 39 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 0a0261d128b..afd303662d1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -91,15 +91,24 @@ int mlx4_en_QUERY_PORT(struct mlx4_en_dev *mdev, u8 port)
 	 * already synchronized, no need in locking */
 	state->link_state = !!(qport_context->link_up & MLX4_EN_LINK_UP_MASK);
 	switch (qport_context->link_speed & MLX4_EN_SPEED_MASK) {
+	case MLX4_EN_100M_SPEED:
+		state->link_speed = SPEED_100;
+		break;
 	case MLX4_EN_1G_SPEED:
-		state->link_speed = 1000;
+		state->link_speed = SPEED_1000;
 		break;
 	case MLX4_EN_10G_SPEED_XAUI:
 	case MLX4_EN_10G_SPEED_XFI:
-		state->link_speed = 10000;
+		state->link_speed = SPEED_10000;
+		break;
+	case MLX4_EN_20G_SPEED:
+		state->link_speed = SPEED_20000;
 		break;
 	case MLX4_EN_40G_SPEED:
-		state->link_speed = 40000;
+		state->link_speed = SPEED_40000;
+		break;
+	case MLX4_EN_56G_SPEED:
+		state->link_speed = SPEED_56000;
 		break;
 	default:
 		state->link_speed = -1;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.h b/drivers/net/ethernet/mellanox/mlx4/en_port.h
index 745090b49d9..a5fc93bfe5d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.h
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.h
@@ -54,10 +54,13 @@ enum {
 };
 
 enum {
-	MLX4_EN_1G_SPEED	= 0x02,
-	MLX4_EN_10G_SPEED_XFI	= 0x01,
+	MLX4_EN_100M_SPEED	= 0x04,
 	MLX4_EN_10G_SPEED_XAUI	= 0x00,
+	MLX4_EN_10G_SPEED_XFI	= 0x01,
+	MLX4_EN_1G_SPEED	= 0x02,
+	MLX4_EN_20G_SPEED	= 0x08,
 	MLX4_EN_40G_SPEED	= 0x40,
+	MLX4_EN_56G_SPEED	= 0x20,
 	MLX4_EN_OTHER_SPEED	= 0x0f,
 };
 
@@ -68,7 +71,7 @@ struct mlx4_en_query_port_context {
 	__be16 mtu;
 	u8 reserved2;
 	u8 link_speed;
-#define MLX4_EN_SPEED_MASK	0x43
+#define MLX4_EN_SPEED_MASK	0x6f
 	u16 reserved3[5];
 	__be64 mac;
 	u8 transceiver;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
index 49d5afc7cfb..2d8ee66138e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
@@ -129,11 +129,15 @@ static int mlx4_en_test_speed(struct mlx4_en_priv *priv)
 	if (mlx4_en_QUERY_PORT(priv->mdev, priv->port))
 		return -ENOMEM;
 
-	/* The device supports 1G, 10G and 40G speeds */
-	if (priv->port_state.link_speed != 1000 &&
-	    priv->port_state.link_speed != 10000 &&
-	    priv->port_state.link_speed != 40000)
+	/* The device supports 100M, 1G, 10G, 20G, 40G and 56G speed */
+	if (priv->port_state.link_speed != SPEED_100 &&
+	    priv->port_state.link_speed != SPEED_1000 &&
+	    priv->port_state.link_speed != SPEED_10000 &&
+	    priv->port_state.link_speed != SPEED_20000 &&
+	    priv->port_state.link_speed != SPEED_40000 &&
+	    priv->port_state.link_speed != SPEED_56000)
 		return priv->port_state.link_speed;
+
 	return 0;
 }
 
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index b6acd78b821..eb2095b42fb 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1213,6 +1213,10 @@ enum ethtool_sfeatures_retval_bits {
 #define SUPPORTED_40000baseCR4_Full	(1 << 24)
 #define SUPPORTED_40000baseSR4_Full	(1 << 25)
 #define SUPPORTED_40000baseLR4_Full	(1 << 26)
+#define SUPPORTED_56000baseKR4_Full	(1 << 27)
+#define SUPPORTED_56000baseCR4_Full	(1 << 28)
+#define SUPPORTED_56000baseSR4_Full	(1 << 29)
+#define SUPPORTED_56000baseLR4_Full	(1 << 30)
 
 #define ADVERTISED_10baseT_Half		(1 << 0)
 #define ADVERTISED_10baseT_Full		(1 << 1)
@@ -1241,6 +1245,10 @@ enum ethtool_sfeatures_retval_bits {
 #define ADVERTISED_40000baseCR4_Full	(1 << 24)
 #define ADVERTISED_40000baseSR4_Full	(1 << 25)
 #define ADVERTISED_40000baseLR4_Full	(1 << 26)
+#define ADVERTISED_56000baseKR4_Full	(1 << 27)
+#define ADVERTISED_56000baseCR4_Full	(1 << 28)
+#define ADVERTISED_56000baseSR4_Full	(1 << 29)
+#define ADVERTISED_56000baseLR4_Full	(1 << 30)
 
 /* The following are all involved in forcing a particular link
  * mode for the device for setting things.  When getting the
@@ -1248,12 +1256,16 @@ enum ethtool_sfeatures_retval_bits {
  * it was forced up into this mode or autonegotiated.
  */
 
-/* The forced speed, 10Mb, 100Mb, gigabit, 2.5Gb, 10GbE. */
+/* The forced speed, 10Mb, 100Mb, gigabit, [2.5|10|20|40|56]GbE. */
 #define SPEED_10		10
 #define SPEED_100		100
 #define SPEED_1000		1000
 #define SPEED_2500		2500
 #define SPEED_10000		10000
+#define SPEED_20000		20000
+#define SPEED_40000		40000
+#define SPEED_56000		56000
+
 #define SPEED_UNKNOWN		-1
 
 /* Duplex, half or full. */
-- 
cgit v1.2.3-70-g09d2


From 16301861004e50be9c47113cceca62f56516a9a2 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Tue, 28 Oct 2014 18:21:18 +0100
Subject: mac802154: declare struct ieee802154_ops as const

The ieee802154_ops structure should be never changed during runtime.
This patch declare this structure as const to avoid a runtime change.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Cc: Alan Ott <alan@signal11.us>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/net/ieee802154/at86rf230.c | 2 +-
 drivers/net/ieee802154/cc2520.c    | 2 +-
 drivers/net/ieee802154/fakelb.c    | 2 +-
 drivers/net/ieee802154/mrf24j40.c  | 2 +-
 include/net/mac802154.h            | 2 +-
 net/mac802154/ieee802154_i.h       | 2 +-
 net/mac802154/main.c               | 2 +-
 7 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index a1558385bac..662efd3e07b 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -1214,7 +1214,7 @@ at86rf230_set_frame_retries(struct ieee802154_hw *hw, s8 retries)
 	return rc;
 }
 
-static struct ieee802154_ops at86rf230_ops = {
+static const struct ieee802154_ops at86rf230_ops = {
 	.owner = THIS_MODULE,
 	.xmit_async = at86rf230_xmit,
 	.ed = at86rf230_ed,
diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c
index a31b5b62a35..b479c9d560f 100644
--- a/drivers/net/ieee802154/cc2520.c
+++ b/drivers/net/ieee802154/cc2520.c
@@ -631,7 +631,7 @@ cc2520_filter(struct ieee802154_hw *hw,
 	return 0;
 }
 
-static struct ieee802154_ops cc2520_ops = {
+static const struct ieee802154_ops cc2520_ops = {
 	.owner = THIS_MODULE,
 	.start = cc2520_start,
 	.stop = cc2520_stop,
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index db0703f0fa4..2a97cbb3aa0 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -129,7 +129,7 @@ fakelb_hw_stop(struct ieee802154_hw *hw) {
 	spin_unlock(&priv->lock);
 }
 
-static struct ieee802154_ops fakelb_ops = {
+static const struct ieee802154_ops fakelb_ops = {
 	.owner = THIS_MODULE,
 	.xmit_sync = fakelb_hw_xmit,
 	.ed = fakelb_hw_ed,
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index 7abb237cb98..f19cf588de2 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -579,7 +579,7 @@ out:
 	return ret;
 }
 
-static struct ieee802154_ops mrf24j40_ops = {
+static const struct ieee802154_ops mrf24j40_ops = {
 	.owner = THIS_MODULE,
 	.xmit_sync = mrf24j40_tx,
 	.ed = mrf24j40_ed,
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 4c4642ef244..0ea44cda292 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -197,7 +197,7 @@ struct ieee802154_ops {
 
 /* Basic interface to register ieee802154 hwice */
 struct ieee802154_hw *
-ieee802154_alloc_hw(size_t priv_data_len, struct ieee802154_ops *ops);
+ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops);
 void ieee802154_free_hw(struct ieee802154_hw *hw);
 int ieee802154_register_hw(struct ieee802154_hw *hw);
 void ieee802154_unregister_hw(struct ieee802154_hw *hw);
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index 4408c463af3..a379b971b13 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -28,7 +28,7 @@
 /* mac802154 device private data */
 struct ieee802154_local {
 	struct ieee802154_hw hw;
-	struct ieee802154_ops *ops;
+	const struct ieee802154_ops *ops;
 
 	/* ieee802154 phy */
 	struct wpan_phy *phy;
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 2c6d7725982..632707bc47b 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -187,7 +187,7 @@ static void ieee802154_tasklet_handler(unsigned long data)
 }
 
 struct ieee802154_hw *
-ieee802154_alloc_hw(size_t priv_data_len, struct ieee802154_ops *ops)
+ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops)
 {
 	struct wpan_phy *phy;
 	struct ieee802154_local *local;
-- 
cgit v1.2.3-70-g09d2


From e37d2ec82a222f1819e7793a27bc052999a379fb Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Tue, 28 Oct 2014 18:21:19 +0100
Subject: mac802154: ops: declare channel and page as u8

The range of channel and page fits into an unsigned byte range. This
patch changes the set_channel parameter definitions for channel and
page to u8.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Cc: Alan Ott <alan@signal11.us>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/net/ieee802154/at86rf230.c | 8 ++++----
 drivers/net/ieee802154/cc2520.c    | 2 +-
 drivers/net/ieee802154/fakelb.c    | 2 +-
 drivers/net/ieee802154/mrf24j40.c  | 3 +--
 include/net/mac802154.h            | 5 ++---
 5 files changed, 9 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 662efd3e07b..5068c1bd004 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -54,7 +54,7 @@ struct at86rf2xx_chip_data {
 	u16 t_tx_timeout;
 	int rssi_base_val;
 
-	int (*set_channel)(struct at86rf230_local *, int, int);
+	int (*set_channel)(struct at86rf230_local *, u8, u8);
 	int (*get_desense_steps)(struct at86rf230_local *, s32);
 };
 
@@ -1012,13 +1012,13 @@ at86rf230_stop(struct ieee802154_hw *hw)
 }
 
 static int
-at86rf23x_set_channel(struct at86rf230_local *lp, int page, int channel)
+at86rf23x_set_channel(struct at86rf230_local *lp, u8 page, u8 channel)
 {
 	return at86rf230_write_subreg(lp, SR_CHANNEL, channel);
 }
 
 static int
-at86rf212_set_channel(struct at86rf230_local *lp, int page, int channel)
+at86rf212_set_channel(struct at86rf230_local *lp, u8 page, u8 channel)
 {
 	int rc;
 
@@ -1043,7 +1043,7 @@ at86rf212_set_channel(struct at86rf230_local *lp, int page, int channel)
 }
 
 static int
-at86rf230_channel(struct ieee802154_hw *hw, int page, int channel)
+at86rf230_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
 {
 	struct at86rf230_local *lp = hw->priv;
 	int rc;
diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c
index b479c9d560f..78ea2cadeb7 100644
--- a/drivers/net/ieee802154/cc2520.c
+++ b/drivers/net/ieee802154/cc2520.c
@@ -569,7 +569,7 @@ cc2520_ed(struct ieee802154_hw *hw, u8 *level)
 }
 
 static int
-cc2520_set_channel(struct ieee802154_hw *hw, int page, int channel)
+cc2520_set_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
 {
 	struct cc2520_private *priv = hw->priv;
 	int ret;
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index 2a97cbb3aa0..4092e704c4a 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -55,7 +55,7 @@ fakelb_hw_ed(struct ieee802154_hw *hw, u8 *level)
 }
 
 static int
-fakelb_hw_channel(struct ieee802154_hw *hw, int page, int channel)
+fakelb_hw_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
 {
 	pr_debug("set channel to %d\n", channel);
 
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index f19cf588de2..52b3d311675 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -423,8 +423,7 @@ static void mrf24j40_stop(struct ieee802154_hw *hw)
 	write_short_reg(devrec, REG_INTCON, val);
 }
 
-static int mrf24j40_set_channel(struct ieee802154_hw *hw,
-				int page, int channel)
+static int mrf24j40_set_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
 {
 	struct mrf24j40 *devrec = hw->priv;
 	u8 val;
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 0ea44cda292..85a4efca418 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -178,9 +178,8 @@ struct ieee802154_ops {
 	int		(*xmit_async)(struct ieee802154_hw *hw,
 				      struct sk_buff *skb);
 	int		(*ed)(struct ieee802154_hw *hw, u8 *level);
-	int		(*set_channel)(struct ieee802154_hw *hw,
-				       int page,
-				       int channel);
+	int		(*set_channel)(struct ieee802154_hw *hw, u8 page,
+				       u8 channel);
 	int		(*set_hw_addr_filt)(struct ieee802154_hw *hw,
 					    struct ieee802154_hw_addr_filt *filt,
 					    unsigned long changed);
-- 
cgit v1.2.3-70-g09d2


From a543c5989d7711d984608f4e12a73218642ca865 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Tue, 28 Oct 2014 18:21:23 +0100
Subject: mac802154: remove driver ops in wpan-phy

This patch removes the driver ops callbacks inside of wpan_phy struct.
It was used to check if a phy supports this driver ops call. We do this
now via hardware flags.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h |  8 -----
 net/ieee802154/nl-mac.c | 19 ++---------
 net/mac802154/iface.c   | 12 +++----
 net/mac802154/main.c    | 85 -------------------------------------------------
 4 files changed, 8 insertions(+), 116 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 5c674673ef2..440b9bece9c 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -57,14 +57,6 @@ struct wpan_phy {
 					const char *name, int type);
 	void (*del_iface)(struct wpan_phy *phy, struct net_device *dev);
 
-	int (*set_txpower)(struct wpan_phy *phy, int db);
-	int (*set_lbt)(struct wpan_phy *phy, bool on);
-	int (*set_cca_mode)(struct wpan_phy *phy, u8 cca_mode);
-	int (*set_cca_ed_level)(struct wpan_phy *phy, int level);
-	int (*set_csma_params)(struct wpan_phy *phy, u8 min_be, u8 max_be,
-			       u8 retries);
-	int (*set_frame_retries)(struct wpan_phy *phy, s8 retries);
-
 	char priv[0] __aligned(NETDEV_ALIGN);
 };
 
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index fb6866d1dd3..abd0f31bdc6 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -664,20 +664,6 @@ int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info)
 
 	phy = ops->get_phy(dev);
 
-	if ((!phy->set_lbt && info->attrs[IEEE802154_ATTR_LBT_ENABLED]) ||
-	    (!phy->set_cca_mode && info->attrs[IEEE802154_ATTR_CCA_MODE]) ||
-	    (!phy->set_cca_ed_level &&
-	     info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) ||
-	    (!phy->set_csma_params &&
-	     (info->attrs[IEEE802154_ATTR_CSMA_RETRIES] ||
-	      info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] ||
-	      info->attrs[IEEE802154_ATTR_CSMA_MAX_BE])) ||
-	    (!phy->set_frame_retries &&
-	     info->attrs[IEEE802154_ATTR_FRAME_RETRIES])) {
-		rc = -EOPNOTSUPP;
-		goto out_phy;
-	}
-
 	ops->get_mac_params(dev, &params);
 
 	if (info->attrs[IEEE802154_ATTR_TXPOWER])
@@ -708,10 +694,9 @@ int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info)
 
 	wpan_phy_put(phy);
 	dev_put(dev);
-	return rc;
 
-out_phy:
-	wpan_phy_put(phy);
+	return 0;
+
 out:
 	dev_put(dev);
 	return rc;
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index 025cd5aba13..300877a1a0c 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -196,32 +196,32 @@ static int mac802154_wpan_open(struct net_device *dev)
 
 	mutex_lock(&phy->pib_lock);
 
-	if (phy->set_txpower) {
+	if (local->hw.flags & IEEE802154_HW_TXPOWER) {
 		rc = drv_set_tx_power(local, sdata->mac_params.transmit_power);
 		if (rc < 0)
 			goto out;
 	}
 
-	if (phy->set_lbt) {
+	if (local->hw.flags & IEEE802154_HW_LBT) {
 		rc = drv_set_lbt_mode(local, sdata->mac_params.lbt);
 		if (rc < 0)
 			goto out;
 	}
 
-	if (phy->set_cca_mode) {
+	if (local->hw.flags & IEEE802154_HW_CCA_MODE) {
 		rc = drv_set_cca_mode(local, sdata->mac_params.cca_mode);
 		if (rc < 0)
 			goto out;
 	}
 
-	if (phy->set_cca_ed_level) {
+	if (local->hw.flags & IEEE802154_HW_CCA_ED_LEVEL) {
 		rc = drv_set_cca_ed_level(local,
 					  sdata->mac_params.cca_ed_level);
 		if (rc < 0)
 			goto out;
 	}
 
-	if (phy->set_csma_params) {
+	if (local->hw.flags & IEEE802154_HW_CSMA_PARAMS) {
 		rc = drv_set_csma_params(local, sdata->mac_params.min_be,
 					 sdata->mac_params.max_be,
 					 sdata->mac_params.csma_retries);
@@ -229,7 +229,7 @@ static int mac802154_wpan_open(struct net_device *dev)
 			goto out;
 	}
 
-	if (phy->set_frame_retries) {
+	if (local->hw.flags & IEEE802154_HW_FRAME_RETRIES) {
 		rc = drv_set_max_frame_retries(local,
 					       sdata->mac_params.frame_retries);
 		if (rc < 0)
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 24ecc09de2a..9fa9514b3a3 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -121,49 +121,6 @@ err:
 	return ERR_PTR(err);
 }
 
-static int mac802154_set_txpower(struct wpan_phy *phy, int db)
-{
-	struct ieee802154_local *local = wpan_phy_priv(phy);
-
-	return drv_set_tx_power(local, db);
-}
-
-static int mac802154_set_lbt(struct wpan_phy *phy, bool on)
-{
-	struct ieee802154_local *local = wpan_phy_priv(phy);
-
-	return drv_set_lbt_mode(local, on);
-}
-
-static int mac802154_set_cca_mode(struct wpan_phy *phy, u8 mode)
-{
-	struct ieee802154_local *local = wpan_phy_priv(phy);
-
-	return drv_set_cca_mode(local, mode);
-}
-
-static int mac802154_set_cca_ed_level(struct wpan_phy *phy, s32 level)
-{
-	struct ieee802154_local *local = wpan_phy_priv(phy);
-
-	return drv_set_cca_ed_level(local, level);
-}
-
-static int mac802154_set_csma_params(struct wpan_phy *phy, u8 min_be,
-				     u8 max_be, u8 retries)
-{
-	struct ieee802154_local *local = wpan_phy_priv(phy);
-
-	return drv_set_csma_params(local, min_be, max_be, retries);
-}
-
-static int mac802154_set_frame_retries(struct wpan_phy *phy, s8 retries)
-{
-	struct ieee802154_local *local = wpan_phy_priv(phy);
-
-	return drv_set_max_frame_retries(local, retries);
-}
-
 static void ieee802154_tasklet_handler(unsigned long data)
 {
 	struct ieee802154_local *local = (struct ieee802154_local *)data;
@@ -262,48 +219,6 @@ int ieee802154_register_hw(struct ieee802154_hw *hw)
 	struct ieee802154_local *local = hw_to_local(hw);
 	int rc = -ENOSYS;
 
-	if (hw->flags & IEEE802154_HW_TXPOWER) {
-		if (!local->ops->set_txpower)
-			goto out;
-
-		local->phy->set_txpower = mac802154_set_txpower;
-	}
-
-	if (hw->flags & IEEE802154_HW_LBT) {
-		if (!local->ops->set_lbt)
-			goto out;
-
-		local->phy->set_lbt = mac802154_set_lbt;
-	}
-
-	if (hw->flags & IEEE802154_HW_CCA_MODE) {
-		if (!local->ops->set_cca_mode)
-			goto out;
-
-		local->phy->set_cca_mode = mac802154_set_cca_mode;
-	}
-
-	if (hw->flags & IEEE802154_HW_CCA_ED_LEVEL) {
-		if (!local->ops->set_cca_ed_level)
-			goto out;
-
-		local->phy->set_cca_ed_level = mac802154_set_cca_ed_level;
-	}
-
-	if (hw->flags & IEEE802154_HW_CSMA_PARAMS) {
-		if (!local->ops->set_csma_params)
-			goto out;
-
-		local->phy->set_csma_params = mac802154_set_csma_params;
-	}
-
-	if (hw->flags & IEEE802154_HW_FRAME_RETRIES) {
-		if (!local->ops->set_frame_retries)
-			goto out;
-
-		local->phy->set_frame_retries = mac802154_set_frame_retries;
-	}
-
 	local->workqueue =
 		create_singlethread_workqueue(wpan_phy_name(local->phy));
 	if (!local->workqueue) {
-- 
cgit v1.2.3-70-g09d2


From e83280f96f108ee7af8c5669080cf664b0c2b8fb Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 29 Oct 2014 08:20:46 +0100
Subject: ALSA: doc: Fix enum snd_jack_types comments

Follow the proper kerneldoc rule, and complete enum item comments.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/jack.h | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/jack.h b/include/sound/jack.h
index 37e612e7741..67f2bbcd515 100644
--- a/include/sound/jack.h
+++ b/include/sound/jack.h
@@ -28,7 +28,21 @@
 struct input_dev;
 
 /**
- * enum snd_jack_types: Jack types which can be reported
+ * enum snd_jack_types - Jack types which can be reported
+ * @SND_JACK_HEADPHONE: Headphone
+ * @SND_JACK_MICROPHONE: Microphone
+ * @SND_JACK_HEADSET: Headset
+ * @SND_JACK_LINEOUT: Line out
+ * @SND_JACK_MECHANICAL: Mechanical switch
+ * @SND_JACK_VIDEOOUT: Video out
+ * @SND_JACK_AVOUT: AV (Audio Video) out
+ * @SND_JACK_LINEIN:  Line in
+ * @SND_JACK_BTN_0: Button 0
+ * @SND_JACK_BTN_1: Button 1
+ * @SND_JACK_BTN_2: Button 2
+ * @SND_JACK_BTN_3: Button 3
+ * @SND_JACK_BTN_4: Button 4
+ * @SND_JACK_BTN_5: Button 5
  *
  * These values are used as a bitmask.
  *
-- 
cgit v1.2.3-70-g09d2


From f533ccb61edf008e14c9e1b91b48cd2c7397f33d Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 29 Oct 2014 08:22:05 +0100
Subject: ALSA: doc: Fix uapi/sound/compress_offload.h kerneldoc comments

so that make htmldocs works properly.
Since kerneldoc can't handle noname enum properly, name enum
sndrv_compress_encoder.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/uapi/sound/compress_offload.h | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h
index 1964026b5e0..22ed8cb7800 100644
--- a/include/uapi/sound/compress_offload.h
+++ b/include/uapi/sound/compress_offload.h
@@ -32,7 +32,7 @@
 
 #define SNDRV_COMPRESS_VERSION SNDRV_PROTOCOL_VERSION(0, 1, 2)
 /**
- * struct snd_compressed_buffer: compressed buffer
+ * struct snd_compressed_buffer - compressed buffer
  * @fragment_size: size of buffer fragment in bytes
  * @fragments: number of such fragments
  */
@@ -42,7 +42,7 @@ struct snd_compressed_buffer {
 } __attribute__((packed, aligned(4)));
 
 /**
- * struct snd_compr_params: compressed stream params
+ * struct snd_compr_params - compressed stream params
  * @buffer: buffer description
  * @codec: codec parameters
  * @no_wake_mode: dont wake on fragment elapsed
@@ -54,7 +54,7 @@ struct snd_compr_params {
 } __attribute__((packed, aligned(4)));
 
 /**
- * struct snd_compr_tstamp: timestamp descriptor
+ * struct snd_compr_tstamp - timestamp descriptor
  * @byte_offset: Byte offset in ring buffer to DSP
  * @copied_total: Total number of bytes copied from/to ring buffer to/by DSP
  * @pcm_frames: Frames decoded or encoded by DSP. This field will evolve by
@@ -73,7 +73,7 @@ struct snd_compr_tstamp {
 } __attribute__((packed, aligned(4)));
 
 /**
- * struct snd_compr_avail: avail descriptor
+ * struct snd_compr_avail - avail descriptor
  * @avail: Number of bytes available in ring buffer for writing/reading
  * @tstamp: timestamp infomation
  */
@@ -88,7 +88,7 @@ enum snd_compr_direction {
 };
 
 /**
- * struct snd_compr_caps: caps descriptor
+ * struct snd_compr_caps - caps descriptor
  * @codecs: pointer to array of codecs
  * @direction: direction supported. Of type snd_compr_direction
  * @min_fragment_size: minimum fragment supported by DSP
@@ -110,7 +110,7 @@ struct snd_compr_caps {
 } __attribute__((packed, aligned(4)));
 
 /**
- * struct snd_compr_codec_caps: query capability of codec
+ * struct snd_compr_codec_caps - query capability of codec
  * @codec: codec for which capability is queried
  * @num_descriptors: number of codec descriptors
  * @descriptor: array of codec capability descriptor
@@ -122,18 +122,19 @@ struct snd_compr_codec_caps {
 } __attribute__((packed, aligned(4)));
 
 /**
+ * enum sndrv_compress_encoder
  * @SNDRV_COMPRESS_ENCODER_PADDING: no of samples appended by the encoder at the
  * end of the track
  * @SNDRV_COMPRESS_ENCODER_DELAY: no of samples inserted by the encoder at the
  * beginning of the track
  */
-enum {
+enum sndrv_compress_encoder {
 	SNDRV_COMPRESS_ENCODER_PADDING = 1,
 	SNDRV_COMPRESS_ENCODER_DELAY = 2,
 };
 
 /**
- * struct snd_compr_metadata: compressed stream metadata
+ * struct snd_compr_metadata - compressed stream metadata
  * @key: key id
  * @value: key value
  */
-- 
cgit v1.2.3-70-g09d2


From 43059f6ba21177f25ab1b10f95149cff1895806a Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@sonymobile.com>
Date: Wed, 22 Oct 2014 12:58:44 +0300
Subject: pinctrl: Device tree bindings for Qualcomm PMIC GPIO block

This introduced the device tree bindings for the GPIO block found
in PMIC's from Qualcomm.

Signed-off-by: Bjorn Andersson <bjorn.andersson@sonymobile.com>
Signed-off-by: Ivan T. Ivanov <iivanov@mm-sol.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/pinctrl/qcom,pmic-gpio.txt | 215 +++++++++++++++++++++
 include/dt-bindings/pinctrl/qcom,pmic-gpio.h       | 142 ++++++++++++++
 2 files changed, 357 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
 create mode 100644 include/dt-bindings/pinctrl/qcom,pmic-gpio.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
new file mode 100644
index 00000000000..7ed08048516
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
@@ -0,0 +1,215 @@
+Qualcomm PMIC GPIO block
+
+This binding describes the GPIO block(s) found in the 8xxx series of
+PMIC's from Qualcomm.
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be one of:
+		    "qcom,pm8018-gpio"
+		    "qcom,pm8038-gpio"
+		    "qcom,pm8058-gpio"
+		    "qcom,pm8917-gpio"
+		    "qcom,pm8921-gpio"
+		    "qcom,pm8941-gpio"
+		    "qcom,pma8084-gpio"
+
+- reg:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: Register base of the GPIO block and length.
+
+- interrupts:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: Must contain an array of encoded interrupt specifiers for
+		    each available GPIO
+
+- gpio-controller:
+	Usage: required
+	Value type: <none>
+	Definition: Mark the device node as a GPIO controller
+
+- #gpio-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: Must be 2;
+		    the first cell will be used to define gpio number and the
+		    second denotes the flags for this gpio
+
+Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
+a general description of GPIO and interrupt bindings.
+
+Please refer to pinctrl-bindings.txt in this directory for details of the
+common pinctrl bindings used by client devices, including the meaning of the
+phrase "pin configuration node".
+
+The pin configuration nodes act as a container for an arbitrary number of
+subnodes. Each of these subnodes represents some desired configuration for a
+pin or a list of pins. This configuration can include the
+mux function to select on those pin(s), and various pin configuration
+parameters, as listed below.
+
+
+SUBNODES:
+
+The name of each subnode is not important; all subnodes should be enumerated
+and processed purely based on their content.
+
+Each subnode only affects those parameters that are explicitly listed. In
+other words, a subnode that lists a mux function but no pin configuration
+parameters implies no information about any pin configuration parameters.
+Similarly, a pin subnode that describes a pullup parameter implies no
+information about e.g. the mux function.
+
+The following generic properties as defined in pinctrl-bindings.txt are valid
+to specify in a pin configuration subnode:
+
+- pins:
+	Usage: required
+	Value type: <string-array>
+	Definition: List of gpio pins affected by the properties specified in
+		    this subnode.  Valid pins are:
+		    gpio1-gpio6 for pm8018
+		    gpio1-gpio12 for pm8038
+		    gpio1-gpio40 for pm8058
+		    gpio1-gpio38 for pm8917
+		    gpio1-gpio44 for pm8921
+		    gpio1-gpio36 for pm8941
+		    gpio1-gpio22 for pma8084
+
+- function:
+	Usage: required
+	Value type: <string>
+	Definition: Specify the alternative function to be configured for the
+		    specified pins.  Valid values are:
+		    "normal",
+		    "paired",
+		    "func1",
+		    "func2",
+		    "dtest1",
+		    "dtest2",
+		    "dtest3",
+		    "dtest4"
+
+- bias-disable:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins should be configured as no pull.
+
+- bias-pull-down:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins should be configured as pull down.
+
+- bias-pull-up:
+	Usage: optional
+	Value type: <empty>
+	Definition: The specified pins should be configured as pull up.
+
+- qcom,pull-up-strength:
+	Usage: optional
+	Value type: <u32>
+	Definition: Specifies the strength to use for pull up, if selected.
+		    Valid values are; as defined in
+		    <dt-bindings/pinctrl/qcom,pmic-gpio.h>:
+		    1: 30uA                     (PMIC_GPIO_PULL_UP_30)
+		    2: 1.5uA                    (PMIC_GPIO_PULL_UP_1P5)
+		    3: 31.5uA                   (PMIC_GPIO_PULL_UP_31P5)
+		    4: 1.5uA + 30uA boost       (PMIC_GPIO_PULL_UP_1P5_30)
+		    If this property is ommited 30uA strength will be used if
+		    pull up is selected
+
+- bias-high-impedance:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins will put in high-Z mode and disabled.
+
+- input-enable:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins are put in input mode.
+
+- output-high:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins are configured in output mode, driven
+		    high.
+
+- output-low:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins are configured in output mode, driven
+		    low.
+
+- power-source:
+	Usage: optional
+	Value type: <u32>
+	Definition: Selects the power source for the specified pins. Valid
+		    power sources are defined per chip in
+		    <dt-bindings/pinctrl/qcom,pmic-gpio.h>
+
+- qcom,drive-strength:
+	Usage: optional
+	Value type: <u32>
+	Definition: Selects the drive strength for the specified pins. Value
+		    drive strengths are:
+		    0: no (PMIC_GPIO_STRENGTH_NO)
+		    1: high (PMIC_GPIO_STRENGTH_HIGH) 0.9mA @ 1.8V - 1.9mA @ 2.6V
+		    2: medium (PMIC_GPIO_STRENGTH_MED) 0.6mA @ 1.8V - 1.25mA @ 2.6V
+		    3: low (PMIC_GPIO_STRENGTH_LOW) 0.15mA @ 1.8V - 0.3mA @ 2.6V
+		    as defined in <dt-bindings/pinctrl/qcom,pmic-gpio.h>
+
+- drive-push-pull:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins are configured in push-pull mode.
+
+- drive-open-drain:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins are configured in open-drain mode.
+
+- drive-open-source:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins are configured in open-source mode.
+
+Example:
+
+	pm8921_gpio: gpio@150 {
+		compatible = "qcom,pm8921-gpio";
+		reg = <0x150 0x160>;
+		interrupts = <192 1>, <193 1>, <194 1>,
+			     <195 1>, <196 1>, <197 1>,
+			     <198 1>, <199 1>, <200 1>,
+			     <201 1>, <202 1>, <203 1>,
+			     <204 1>, <205 1>, <206 1>,
+			     <207 1>, <208 1>, <209 1>,
+			     <210 1>, <211 1>, <212 1>,
+			     <213 1>, <214 1>, <215 1>,
+			     <216 1>, <217 1>, <218 1>,
+			     <219 1>, <220 1>, <221 1>,
+			     <222 1>, <223 1>, <224 1>,
+			     <225 1>, <226 1>, <227 1>,
+			     <228 1>, <229 1>, <230 1>,
+			     <231 1>, <232 1>, <233 1>,
+			     <234 1>, <235 1>;
+
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		pm8921_gpio_keys: gpio-keys {
+			volume-keys {
+				pins = "gpio20", "gpio21";
+				function = "normal";
+
+				input-enable;
+				bias-pull-up;
+				drive-push-pull;
+				qcom,drive-strength = <PMIC_GPIO_STRENGTH_NO>;
+				power-source = <PM8921_GPIO_S4>;
+			};
+		};
+	};
diff --git a/include/dt-bindings/pinctrl/qcom,pmic-gpio.h b/include/dt-bindings/pinctrl/qcom,pmic-gpio.h
new file mode 100644
index 00000000000..fa74d7cc960
--- /dev/null
+++ b/include/dt-bindings/pinctrl/qcom,pmic-gpio.h
@@ -0,0 +1,142 @@
+/*
+ * This header provides constants for the Qualcomm PMIC GPIO binding.
+ */
+
+#ifndef _DT_BINDINGS_PINCTRL_QCOM_PMIC_GPIO_H
+#define _DT_BINDINGS_PINCTRL_QCOM_PMIC_GPIO_H
+
+#define PMIC_GPIO_PULL_UP_30		0
+#define PMIC_GPIO_PULL_UP_1P5		1
+#define PMIC_GPIO_PULL_UP_31P5		2
+#define PMIC_GPIO_PULL_UP_1P5_30	3
+
+#define PMIC_GPIO_STRENGTH_NO		0
+#define PMIC_GPIO_STRENGTH_HIGH		1
+#define PMIC_GPIO_STRENGTH_MED		2
+#define PMIC_GPIO_STRENGTH_LOW		3
+
+/*
+ * Note: PM8018 GPIO3 and GPIO4 are supporting
+ * only S3 and L2 options (1.8V)
+ */
+#define PM8018_GPIO_L6			0
+#define PM8018_GPIO_L5			1
+#define PM8018_GPIO_S3			2
+#define PM8018_GPIO_L14			3
+#define PM8018_GPIO_L2			4
+#define PM8018_GPIO_L4			5
+#define PM8018_GPIO_VDD			6
+
+/*
+ * Note: PM8038 GPIO7 and GPIO8 are supporting
+ * only L11 and L4 options (1.8V)
+ */
+#define PM8038_GPIO_VPH			0
+#define PM8038_GPIO_BB			1
+#define PM8038_GPIO_L11			2
+#define PM8038_GPIO_L15			3
+#define PM8038_GPIO_L4			4
+#define PM8038_GPIO_L3			5
+#define PM8038_GPIO_L17			6
+
+#define PM8058_GPIO_VPH			0
+#define PM8058_GPIO_BB			1
+#define PM8058_GPIO_S3			2
+#define PM8058_GPIO_L3			3
+#define PM8058_GPIO_L7			4
+#define PM8058_GPIO_L6			5
+#define PM8058_GPIO_L5			6
+#define PM8058_GPIO_L2			7
+
+#define PM8917_GPIO_VPH			0
+#define PM8917_GPIO_S4			2
+#define PM8917_GPIO_L15			3
+#define PM8917_GPIO_L4			4
+#define PM8917_GPIO_L3			5
+#define PM8917_GPIO_L17			6
+
+#define PM8921_GPIO_VPH			0
+#define PM8921_GPIO_BB			1
+#define PM8921_GPIO_S4			2
+#define PM8921_GPIO_L15			3
+#define PM8921_GPIO_L4			4
+#define PM8921_GPIO_L3			5
+#define PM8921_GPIO_L17			6
+
+/*
+ * Note: PM8941 gpios from 15 to 18 are supporting
+ * only S3 and L6 options (1.8V)
+ */
+#define PM8941_GPIO_VPH			0
+#define PM8941_GPIO_L1			1
+#define PM8941_GPIO_S3			2
+#define PM8941_GPIO_L6			3
+
+/*
+ * Note: PMA8084 gpios from 15 to 18 are supporting
+ * only S4 and L6 options (1.8V)
+ */
+#define PMA8084_GPIO_VPH		0
+#define PMA8084_GPIO_L1			1
+#define PMA8084_GPIO_S4			2
+#define PMA8084_GPIO_L6			3
+
+/* To be used with "function" */
+#define PMIC_GPIO_FUNC_NORMAL		"normal"
+#define PMIC_GPIO_FUNC_PAIRED		"paired"
+#define PMIC_GPIO_FUNC_FUNC1		"func1"
+#define PMIC_GPIO_FUNC_FUNC2		"func2"
+#define PMIC_GPIO_FUNC_DTEST1		"dtest1"
+#define PMIC_GPIO_FUNC_DTEST2		"dtest2"
+#define PMIC_GPIO_FUNC_DTEST3		"dtest3"
+#define PMIC_GPIO_FUNC_DTEST4		"dtest4"
+
+#define PM8038_GPIO1_2_LPG_DRV		PMIC_GPIO_FUNC_FUNC1
+#define PM8038_GPIO3_5V_BOOST_EN	PMIC_GPIO_FUNC_FUNC1
+#define PM8038_GPIO4_SSBI_ALT_CLK	PMIC_GPIO_FUNC_FUNC1
+#define PM8038_GPIO5_6_EXT_REG_EN	PMIC_GPIO_FUNC_FUNC1
+#define PM8038_GPIO10_11_EXT_REG_EN	PMIC_GPIO_FUNC_FUNC1
+#define PM8038_GPIO6_7_CLK		PMIC_GPIO_FUNC_FUNC1
+#define PM8038_GPIO9_BAT_ALRM_OUT	PMIC_GPIO_FUNC_FUNC1
+#define PM8038_GPIO6_12_KYPD_DRV	PMIC_GPIO_FUNC_FUNC2
+
+#define PM8058_GPIO7_8_MP3_CLK		PMIC_GPIO_FUNC_FUNC1
+#define PM8058_GPIO7_8_BCLK_19P2MHZ	PMIC_GPIO_FUNC_FUNC2
+#define PM8058_GPIO9_26_KYPD_DRV	PMIC_GPIO_FUNC_FUNC1
+#define PM8058_GPIO21_23_UART_TX	PMIC_GPIO_FUNC_FUNC2
+#define PM8058_GPIO24_26_LPG_DRV	PMIC_GPIO_FUNC_FUNC2
+#define PM8058_GPIO33_BCLK_19P2MHZ	PMIC_GPIO_FUNC_FUNC1
+#define PM8058_GPIO34_35_MP3_CLK	PMIC_GPIO_FUNC_FUNC1
+#define PM8058_GPIO36_BCLK_19P2MHZ	PMIC_GPIO_FUNC_FUNC1
+#define PM8058_GPIO37_UPL_OUT		PMIC_GPIO_FUNC_FUNC1
+#define PM8058_GPIO37_UART_M_RX		PMIC_GPIO_FUNC_FUNC2
+#define PM8058_GPIO38_XO_SLEEP_CLK	PMIC_GPIO_FUNC_FUNC1
+#define PM8058_GPIO38_39_CLK_32KHZ	PMIC_GPIO_FUNC_FUNC2
+#define PM8058_GPIO39_MP3_CLK		PMIC_GPIO_FUNC_FUNC1
+#define PM8058_GPIO40_EXT_BB_EN		PMIC_GPIO_FUNC_FUNC1
+
+#define PM8917_GPIO9_18_KEYP_DRV	PMIC_GPIO_FUNC_FUNC1
+#define PM8917_GPIO20_BAT_ALRM_OUT	PMIC_GPIO_FUNC_FUNC1
+#define PM8917_GPIO21_23_UART_TX	PMIC_GPIO_FUNC_FUNC2
+#define PM8917_GPIO25_26_EXT_REG_EN	PMIC_GPIO_FUNC_FUNC1
+#define PM8917_GPIO37_38_XO_SLEEP_CLK	PMIC_GPIO_FUNC_FUNC1
+#define PM8917_GPIO37_38_MP3_CLK	PMIC_GPIO_FUNC_FUNC2
+
+#define PM8941_GPIO9_14_KYPD_DRV	PMIC_GPIO_FUNC_FUNC1
+#define PM8941_GPIO15_18_DIV_CLK	PMIC_GPIO_FUNC_FUNC1
+#define PM8941_GPIO15_18_SLEEP_CLK	PMIC_GPIO_FUNC_FUNC2
+#define PM8941_GPIO23_26_KYPD_DRV	PMIC_GPIO_FUNC_FUNC1
+#define PM8941_GPIO23_26_LPG_DRV_HI	PMIC_GPIO_FUNC_FUNC2
+#define PM8941_GPIO31_BAT_ALRM_OUT	PMIC_GPIO_FUNC_FUNC1
+#define PM8941_GPIO33_36_LPG_DRV_3D	PMIC_GPIO_FUNC_FUNC1
+#define PM8941_GPIO33_36_LPG_DRV_HI	PMIC_GPIO_FUNC_FUNC2
+
+#define PMA8084_GPIO4_5_LPG_DRV		PMIC_GPIO_FUNC_FUNC1
+#define PMA8084_GPIO7_10_LPG_DRV	PMIC_GPIO_FUNC_FUNC1
+#define PMA8084_GPIO5_14_KEYP_DRV	PMIC_GPIO_FUNC_FUNC2
+#define PMA8084_GPIO19_21_KEYP_DRV	PMIC_GPIO_FUNC_FUNC2
+#define PMA8084_GPIO15_18_DIV_CLK	PMIC_GPIO_FUNC_FUNC1
+#define PMA8084_GPIO15_18_SLEEP_CLK	PMIC_GPIO_FUNC_FUNC2
+#define PMA8084_GPIO22_BAT_ALRM_OUT	PMIC_GPIO_FUNC_FUNC1
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From 89a7117d56d405b49b7d1f8ed30e01188e9d5a05 Mon Sep 17 00:00:00 2001
From: "Ivan T. Ivanov" <iivanov@mm-sol.com>
Date: Wed, 22 Oct 2014 12:58:45 +0300
Subject: pinctrl: Device tree bindings for Qualcomm PMIC MPP block

DeviceTree binding documentation for Qualcomm SPMI PMIC MPP
pinctrl drivers.

Signed-off-by: Ivan T. Ivanov <iivanov@mm-sol.com>
Acked-by: Bjorn Andersson <bjorn.andersson@sonymobile.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/pinctrl/qcom,pmic-mpp.txt  | 162 +++++++++++++++++++++
 include/dt-bindings/pinctrl/qcom,pmic-mpp.h        |  44 ++++++
 2 files changed, 206 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt
 create mode 100644 include/dt-bindings/pinctrl/qcom,pmic-mpp.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt
new file mode 100644
index 00000000000..854774b194e
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.txt
@@ -0,0 +1,162 @@
+Qualcomm PMIC Multi-Purpose Pin (MPP) block
+
+This binding describes the MPP block(s) found in the 8xxx series
+of PMIC's from Qualcomm.
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: Should contain one of:
+		    "qcom,pm8841-mpp",
+		    "qcom,pm8941-mpp",
+		    "qcom,pma8084-mpp",
+
+- reg:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: Register base of the MPP block and length.
+
+- interrupts:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: Must contain an array of encoded interrupt specifiers for
+		    each available MPP
+
+- gpio-controller:
+	Usage: required
+	Value type: <none>
+	Definition: Mark the device node as a GPIO controller
+
+- #gpio-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: Must be 2;
+		    the first cell will be used to define MPP number and the
+		    second denotes the flags for this MPP
+
+Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
+a general description of GPIO and interrupt bindings.
+
+Please refer to pinctrl-bindings.txt in this directory for details of the
+common pinctrl bindings used by client devices, including the meaning of the
+phrase "pin configuration node".
+
+The pin configuration nodes act as a container for an arbitrary number of
+subnodes. Each of these subnodes represents some desired configuration for a
+pin or a list of pins. This configuration can include the
+mux function to select on those pin(s), and various pin configuration
+parameters, as listed below.
+
+SUBNODES:
+
+The name of each subnode is not important; all subnodes should be enumerated
+and processed purely based on their content.
+
+Each subnode only affects those parameters that are explicitly listed. In
+other words, a subnode that lists a mux function but no pin configuration
+parameters implies no information about any pin configuration parameters.
+Similarly, a pin subnode that describes a pullup parameter implies no
+information about e.g. the mux function.
+
+The following generic properties as defined in pinctrl-bindings.txt are valid
+to specify in a pin configuration subnode:
+
+- pins:
+	Usage: required
+	Value type: <string-array>
+	Definition: List of MPP pins affected by the properties specified in
+		    this subnode.  Valid pins are:
+		    mpp1-mpp4 for pm8841
+		    mpp1-mpp8 for pm8941
+		    mpp1-mpp4 for pma8084
+
+- function:
+	Usage: required
+	Value type: <string>
+	Definition: Specify the alternative function to be configured for the
+		    specified pins.  Valid values are:
+		    "normal",
+		    "paired",
+		    "dtest1",
+		    "dtest2",
+		    "dtest3",
+		    "dtest4"
+
+- bias-disable:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins should be configured as no pull.
+
+- bias-pull-up:
+	Usage: optional
+	Value type: <u32>
+	Definition: The specified pins should be configured as pull up.
+		    Valid values are 600, 10000 and 30000 in bidirectional mode
+		    only, i.e. when operating in qcom,analog-mode and input and
+		    outputs are enabled. The hardware ignores the configuration
+		    when operating in other modes.
+
+- bias-high-impedance:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins will put in high-Z mode and disabled.
+
+- input-enable:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins are put in input mode, i.e. their input
+		    buffer is enabled
+
+- output-high:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins are configured in output mode, driven
+		    high.
+
+- output-low:
+	Usage: optional
+	Value type: <none>
+	Definition: The specified pins are configured in output mode, driven
+		    low.
+
+- power-source:
+	Usage: optional
+	Value type: <u32>
+	Definition: Selects the power source for the specified pins. Valid power
+		    sources are defined in <dt-bindings/pinctrl/qcom,pmic-mpp.h>
+
+- qcom,analog-mode:
+	Usage: optional
+	Value type: <none>
+	Definition: Selects Analog mode of operation: combined with input-enable
+		    and/or output-high, output-low MPP could operate as
+		    Bidirectional Logic, Analog Input, Analog Output.
+
+- qcom,amux-route:
+	Usage: optional
+	Value type: <u32>
+	Definition: Selects the source for analog input. Valid values are
+		    defined in <dt-bindings/pinctrl/qcom,pmic-mpp.h>
+		    PMIC_MPP_AMUX_ROUTE_CH5, PMIC_MPP_AMUX_ROUTE_CH6...
+
+Example:
+
+	mpps@a000 {
+		compatible = "qcom,pm8841-mpp";
+		reg = <0xa000>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupts = <4 0xa0 0 0>, <4 0xa1 0 0>, <4 0xa2 0 0>, <4 0xa3 0 0>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&pm8841_default>;
+
+		pm8841_default: default {
+			gpio {
+				pins = "mpp1", "mpp2", "mpp3", "mpp4";
+				function = "normal";
+				input-enable;
+				power-source = <PM8841_MPP_S3>;
+			};
+		};
+	};
diff --git a/include/dt-bindings/pinctrl/qcom,pmic-mpp.h b/include/dt-bindings/pinctrl/qcom,pmic-mpp.h
new file mode 100644
index 00000000000..d2c7dabe322
--- /dev/null
+++ b/include/dt-bindings/pinctrl/qcom,pmic-mpp.h
@@ -0,0 +1,44 @@
+/*
+ * This header provides constants for the Qualcomm PMIC's
+ * Multi-Purpose Pin binding.
+ */
+
+#ifndef _DT_BINDINGS_PINCTRL_QCOM_PMIC_MPP_H
+#define _DT_BINDINGS_PINCTRL_QCOM_PMIC_MPP_H
+
+/* power-source */
+#define PM8841_MPP_VPH			0
+#define PM8841_MPP_S3			2
+
+#define PM8941_MPP_VPH			0
+#define PM8941_MPP_L1			1
+#define PM8941_MPP_S3			2
+#define PM8941_MPP_L6			3
+
+#define PMA8084_MPP_VPH			0
+#define PMA8084_MPP_L1			1
+#define PMA8084_MPP_S4			2
+#define PMA8084_MPP_L6			3
+
+/*
+ * Analog Input - Set the source for analog input.
+ * To be used with "qcom,amux-route" property
+ */
+#define PMIC_MPP_AMUX_ROUTE_CH5		0
+#define PMIC_MPP_AMUX_ROUTE_CH6		1
+#define PMIC_MPP_AMUX_ROUTE_CH7		2
+#define PMIC_MPP_AMUX_ROUTE_CH8		3
+#define PMIC_MPP_AMUX_ROUTE_ABUS1	4
+#define PMIC_MPP_AMUX_ROUTE_ABUS2	5
+#define PMIC_MPP_AMUX_ROUTE_ABUS3	6
+#define PMIC_MPP_AMUX_ROUTE_ABUS4	7
+
+/* To be used with "function" */
+#define PMIC_MPP_FUNC_NORMAL		"normal"
+#define PMIC_MPP_FUNC_PAIRED		"paired"
+#define PMIC_MPP_FUNC_DTEST1		"dtest1"
+#define PMIC_MPP_FUNC_DTEST2		"dtest2"
+#define PMIC_MPP_FUNC_DTEST3		"dtest3"
+#define PMIC_MPP_FUNC_DTEST4		"dtest4"
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From c241c5eea822344639898512780cff823fc7d730 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Tue, 30 Sep 2014 13:18:23 -0400
Subject: HID: fix merge from wacom into the HID tree

While merging wacom from the input to the hid tree, some
comments have been duplicated. We can also integrate the
test for Synaptics devices in the switch case below, so
it is clear that there will be only one place for such
quirks.

No functional changes are expected in this commit.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-core.c | 17 +++++++----------
 include/linux/hid.h    |  4 ----
 2 files changed, 7 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 73bd9e2e42b..aef7c56ca5e 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -779,16 +779,6 @@ static int hid_scan_report(struct hid_device *hid)
 	    (hid->group == HID_GROUP_MULTITOUCH))
 		hid->group = HID_GROUP_MULTITOUCH_WIN_8;
 
-	/*
-	* Vendor specific handlings
-	*/
-	if ((hid->vendor == USB_VENDOR_ID_SYNAPTICS) &&
-	    (hid->group == HID_GROUP_GENERIC) &&
-	    /* only bind to the mouse interface of composite USB devices */
-	    (hid->bus != BUS_USB || hid->type == HID_TYPE_USBMOUSE))
-		/* hid-rmi should take care of them, not hid-generic */
-		hid->group = HID_GROUP_RMI;
-
 	/*
 	 * Vendor specific handlings
 	 */
@@ -796,6 +786,13 @@ static int hid_scan_report(struct hid_device *hid)
 	case USB_VENDOR_ID_WACOM:
 		hid->group = HID_GROUP_WACOM;
 		break;
+	case USB_VENDOR_ID_SYNAPTICS:
+		if ((hid->group == HID_GROUP_GENERIC) &&
+		    (hid->bus != BUS_USB || hid->type == HID_TYPE_USBMOUSE))
+			/* hid-rmi should only bind to the mouse interface of
+			 * composite USB devices */
+			hid->group = HID_GROUP_RMI;
+		break;
 	}
 
 	vfree(parser);
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 78ea9bf941c..5b1ff6110e2 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -312,10 +312,6 @@ struct hid_item {
  * Vendor specific HID device groups
  */
 #define HID_GROUP_RMI				0x0100
-
-/*
- * Vendor specific HID device groups
- */
 #define HID_GROUP_WACOM				0x0101
 
 /*
-- 
cgit v1.2.3-70-g09d2


From d610274b0301e5ef35811fa736036d022f707564 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Tue, 30 Sep 2014 13:18:25 -0400
Subject: HID: logitech-dj: rely on hid groups to separate receivers from dj
 devices

Several benefits here:
- we can drop the macro is_dj_device: I never been really conviced by
  this macro as we could fall into a null pointer anytime. Anyway time
  showed that this never happened.
- we can simplify the hid driver logitech-djdevice, and make it aware
  of any new receiver VID/PID.
- we can use the Wireless PID of the DJ device as the product id of the
  hid device, this way the sysfs will differentiate between different
  DJ devices.

Signed-off-by: Benjamin Tisssoires <benjamin.tissoires@redhat.com>
Tested-by: Andrew de los Reyes <adlr@chromium.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-logitech-dj.c | 38 ++++++++++----------------------------
 drivers/hid/hid-logitech-dj.h | 10 ----------
 include/linux/hid.h           |  1 +
 3 files changed, 11 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index 71f569292ca..42d38d50afd 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -256,11 +256,15 @@ static void logi_dj_recv_add_djhid_device(struct dj_receiver_dev *djrcv_dev,
 	dj_hiddev->dev.parent = &djrcv_hdev->dev;
 	dj_hiddev->bus = BUS_USB;
 	dj_hiddev->vendor = le16_to_cpu(usbdev->descriptor.idVendor);
-	dj_hiddev->product = le16_to_cpu(usbdev->descriptor.idProduct);
+	dj_hiddev->product =
+		(dj_report->report_params[DEVICE_PAIRED_PARAM_EQUAD_ID_MSB]
+									<< 8) |
+		dj_report->report_params[DEVICE_PAIRED_PARAM_EQUAD_ID_LSB];
 	snprintf(dj_hiddev->name, sizeof(dj_hiddev->name),
-		"Logitech Unifying Device. Wireless PID:%02x%02x",
-		dj_report->report_params[DEVICE_PAIRED_PARAM_EQUAD_ID_MSB],
-		dj_report->report_params[DEVICE_PAIRED_PARAM_EQUAD_ID_LSB]);
+		"Logitech Unifying Device. Wireless PID:%04x",
+		dj_hiddev->product);
+
+	dj_hiddev->group = HID_GROUP_LOGITECH_DJ_DEVICE;
 
 	usb_make_path(usbdev, dj_hiddev->phys, sizeof(dj_hiddev->phys));
 	snprintf(tmpstr, sizeof(tmpstr), ":%d", dj_report->device_index);
@@ -714,9 +718,6 @@ static int logi_dj_probe(struct hid_device *hdev,
 	struct dj_receiver_dev *djrcv_dev;
 	int retval;
 
-	if (is_dj_device((struct dj_device *)hdev->driver_data))
-		return -ENODEV;
-
 	dbg_hid("%s called for ifnum %d\n", __func__,
 		intf->cur_altsetting->desc.bInterfaceNumber);
 
@@ -869,22 +870,6 @@ static void logi_dj_remove(struct hid_device *hdev)
 	hid_set_drvdata(hdev, NULL);
 }
 
-static int logi_djdevice_probe(struct hid_device *hdev,
-			 const struct hid_device_id *id)
-{
-	int ret;
-	struct dj_device *dj_dev = hdev->driver_data;
-
-	if (!is_dj_device(dj_dev))
-		return -ENODEV;
-
-	ret = hid_parse(hdev);
-	if (!ret)
-		ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
-
-	return ret;
-}
-
 static const struct hid_device_id logi_dj_receivers[] = {
 	{HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
 		USB_DEVICE_ID_LOGITECH_UNIFYING_RECEIVER)},
@@ -908,17 +893,14 @@ static struct hid_driver logi_djreceiver_driver = {
 
 
 static const struct hid_device_id logi_dj_devices[] = {
-	{HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
-		USB_DEVICE_ID_LOGITECH_UNIFYING_RECEIVER)},
-	{HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
-		USB_DEVICE_ID_LOGITECH_UNIFYING_RECEIVER_2)},
+	{ HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE,
+		USB_VENDOR_ID_LOGITECH, HID_ANY_ID)},
 	{}
 };
 
 static struct hid_driver logi_djdevice_driver = {
 	.name = "logitech-djdevice",
 	.id_table = logi_dj_devices,
-	.probe = logi_djdevice_probe,
 };
 
 
diff --git a/drivers/hid/hid-logitech-dj.h b/drivers/hid/hid-logitech-dj.h
index daeb0aa4bee..b1208c9c057 100644
--- a/drivers/hid/hid-logitech-dj.h
+++ b/drivers/hid/hid-logitech-dj.h
@@ -112,14 +112,4 @@ struct dj_device {
 	u8 device_index;
 };
 
-/**
- * is_dj_device - know if the given dj_device is not the receiver.
- * @dj_dev: the dj device to test
- *
- * This macro tests if a struct dj_device pointer is a device created
- * by the bus enumarator.
- */
-#define is_dj_device(dj_dev) \
-	(&(dj_dev)->dj_receiver_dev->hdev->dev == (dj_dev)->hdev->dev.parent)
-
 #endif
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 5b1ff6110e2..7d6e0556302 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -313,6 +313,7 @@ struct hid_item {
  */
 #define HID_GROUP_RMI				0x0100
 #define HID_GROUP_WACOM				0x0101
+#define HID_GROUP_LOGITECH_DJ_DEVICE		0x0102
 
 /*
  * This is the global environment of the parser. This information is
-- 
cgit v1.2.3-70-g09d2


From de869917c663f44b5b032bff238bad22e15dda56 Mon Sep 17 00:00:00 2001
From: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Date: Thu, 2 Oct 2014 06:45:38 +0200
Subject: mod_devicetable.h: grammar fix in comment

Signed-off-by: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/mod_devicetable.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 44eeef0da18..745def86258 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -69,7 +69,7 @@ struct ieee1394_device_id {
  * @bDeviceClass: Class of device; numbers are assigned
  *	by the USB forum.  Products may choose to implement classes,
  *	or be vendor-specific.  Device classes specify behavior of all
- *	the interfaces on a devices.
+ *	the interfaces on a device.
  * @bDeviceSubClass: Subclass of device; associated with bDeviceClass.
  * @bDeviceProtocol: Protocol of device; associated with bDeviceClass.
  * @bInterfaceClass: Class of interface; numbers are assigned
-- 
cgit v1.2.3-70-g09d2


From 542cb4593104ae306970eb181ea42a01f1a79ed2 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Fri, 3 Oct 2014 11:42:17 +1000
Subject: scsi: Fix "choir" and "beeing" malaprops

Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 Documentation/scsi/scsi_eh.txt | 4 ++--
 drivers/scsi/aha152x.c         | 2 +-
 drivers/scsi/mac_scsi.c        | 2 +-
 include/scsi/scsi_host.h       | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt
index a0c85110a07..8638f61c8c9 100644
--- a/Documentation/scsi/scsi_eh.txt
+++ b/Documentation/scsi/scsi_eh.txt
@@ -172,7 +172,7 @@ ways.
 
  - eh_strategy_handler() callback
 	This is one big callback which should perform whole error
-	handling.  As such, it should do all choirs SCSI midlayer
+	handling.  As such, it should do all chores the SCSI midlayer
 	performs during recovery.  This will be discussed in [2-2].
 
  Once recovery is complete, SCSI EH resumes normal operation by
@@ -428,7 +428,7 @@ scmd->allowed.
 scsi_unjam_host() and it is responsible for whole recovery process.
 On completion, the handler should have made lower layers forget about
 all failed scmds and either ready for new commands or offline.  Also,
-it should perform SCSI EH maintenance choirs to maintain integrity of
+it should perform SCSI EH maintenance chores to maintain integrity of
 SCSI midlayer.  IOW, of the steps described in [2-1-2], all steps
 except for #1 must be implemented by eh_strategy_handler().
 
diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c
index e77b72f7800..ee2407b83af 100644
--- a/drivers/scsi/aha152x.c
+++ b/drivers/scsi/aha152x.c
@@ -345,7 +345,7 @@ CMD_INC_RESID(struct scsi_cmnd *cmd, int inc)
 
 enum {
 	not_issued	= 0x0001,	/* command not yet issued */
-	selecting	= 0x0002, 	/* target is beeing selected */
+	selecting	= 0x0002,	/* target is being selected */
 	identified	= 0x0004,	/* IDENTIFY was sent */
 	disconnected	= 0x0008,	/* target disconnected */
 	completed	= 0x0010,	/* target sent COMMAND COMPLETE */ 
diff --git a/drivers/scsi/mac_scsi.c b/drivers/scsi/mac_scsi.c
index 6a039eb1cbc..dccce08d0ad 100644
--- a/drivers/scsi/mac_scsi.c
+++ b/drivers/scsi/mac_scsi.c
@@ -360,7 +360,7 @@ const char * macscsi_info (struct Scsi_Host *spnt) {
    XXX: Since bus errors in the PDMA routines never happen on my 
    computer, the bus error code is untested. 
    If the code works as intended, a bus error results in Pseudo-DMA 
-   beeing disabled, meaning that the driver switches to slow handshake. 
+   being disabled, meaning that the driver switches to slow handshake.
    If bus errors are NOT extremely rare, this has to be changed. 
 */
 
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index ba203477996..b286b5787c8 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -555,7 +555,7 @@ struct Scsi_Host {
 	 * __devices is protected by the host_lock, but you should
 	 * usually use scsi_device_lookup / shost_for_each_device
 	 * to access it and don't care about locking yourself.
-	 * In the rare case of beeing in irq context you can use
+	 * In the rare case of being in irq context you can use
 	 * their __ prefixed variants with the lock held. NEVER
 	 * access this list directly from a driver.
 	 */
-- 
cgit v1.2.3-70-g09d2


From 9e3680b1750b9a62680b0262c9f438de98b77655 Mon Sep 17 00:00:00 2001
From: Heena Sirwani <heenasirwani@gmail.com>
Date: Wed, 29 Oct 2014 16:01:16 +0530
Subject: timekeeping: Provide fast accessor to the seconds part of
 CLOCK_MONOTONIC

This is the counterpart to get_seconds() based on CLOCK_MONOTONIC. The
use case for this interface are kernel internal coarse grained
timestamps which do neither require the nanoseconds fraction of
current time nor the CLOCK_REALTIME properties. Such timestamps can
currently only retrieved by calling ktime_get_ts64() and using the
tv_sec field of the returned timespec64. That's inefficient as it
involves the read of the clocksource, math operations and must be
protected by the timekeeper sequence counter.

To avoid the sequence counter protection we restrict the return value
to unsigned 32bit on 32bit machines. This covers ~136 years of uptime
and therefor an overflow is not expected to hit anytime soon.

To avoid math in the function we calculate the current seconds portion
of CLOCK_MONOTONIC when the timekeeper gets updated in
tk_update_ktime_data() similar to the CLOCK_REALTIME counterpart
xtime_sec.

[ tglx: Massaged changelog, simplified and commented the update
  	function, added docbook comment ]

Signed-off-by: Heena Sirwani <heenasirwani@gmail.com>
Reviewed-by: Arnd Bergman <arnd@arndb.de>
Cc: John Stultz <john.stultz@linaro.org>
Cc: opw-kernel@googlegroups.com
Link: http://lkml.kernel.org/r/da0b63f4bdf3478909f92becb35861197da3a905.1414578445.git.heenasirwani@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/timekeeper_internal.h |  2 ++
 include/linux/timekeeping.h         |  1 +
 kernel/time/timekeeping.c           | 38 ++++++++++++++++++++++++++++++++-----
 3 files changed, 36 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index 95640dcd189..05af9a33489 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -42,6 +42,7 @@ struct tk_read_base {
  * struct timekeeper - Structure holding internal timekeeping values.
  * @tkr:		The readout base structure
  * @xtime_sec:		Current CLOCK_REALTIME time in seconds
+ * @ktime_sec:		Current CLOCK_MONOTONIC time in seconds
  * @wall_to_monotonic:	CLOCK_REALTIME to CLOCK_MONOTONIC offset
  * @offs_real:		Offset clock monotonic -> clock realtime
  * @offs_boot:		Offset clock monotonic -> clock boottime
@@ -77,6 +78,7 @@ struct tk_read_base {
 struct timekeeper {
 	struct tk_read_base	tkr;
 	u64			xtime_sec;
+	unsigned long		ktime_sec;
 	struct timespec64	wall_to_monotonic;
 	ktime_t			offs_real;
 	ktime_t			offs_boot;
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 1caa6b04fdc..115d55e11bc 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -28,6 +28,7 @@ struct timespec __current_kernel_time(void);
 struct timespec get_monotonic_coarse(void);
 extern void getrawmonotonic(struct timespec *ts);
 extern void ktime_get_ts64(struct timespec64 *ts);
+extern time64_t ktime_get_seconds(void);
 
 extern int __getnstimeofday64(struct timespec64 *tv);
 extern void getnstimeofday64(struct timespec64 *tv);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index ec1791fae96..a693270efaf 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -417,7 +417,8 @@ EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
  */
 static inline void tk_update_ktime_data(struct timekeeper *tk)
 {
-	s64 nsec;
+	u64 seconds;
+	u32 nsec;
 
 	/*
 	 * The xtime based monotonic readout is:
@@ -426,13 +427,22 @@ static inline void tk_update_ktime_data(struct timekeeper *tk)
 	 *	nsec = base_mono + now();
 	 * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec
 	 */
-	nsec = (s64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec);
-	nsec *= NSEC_PER_SEC;
-	nsec += tk->wall_to_monotonic.tv_nsec;
-	tk->tkr.base_mono = ns_to_ktime(nsec);
+	seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec);
+	nsec = (u32) tk->wall_to_monotonic.tv_nsec;
+	tk->tkr.base_mono = ns_to_ktime(seconds * NSEC_PER_SEC + nsec);
 
 	/* Update the monotonic raw base */
 	tk->base_raw = timespec64_to_ktime(tk->raw_time);
+
+	/*
+	 * The sum of the nanoseconds portions of xtime and
+	 * wall_to_monotonic can be greater/equal one second. Take
+	 * this into account before updating tk->ktime_sec.
+	 */
+	nsec += (u32)(tk->tkr.xtime_nsec >> tk->tkr.shift);
+	if (nsec >= NSEC_PER_SEC)
+		seconds++;
+	tk->ktime_sec = seconds;
 }
 
 /* must hold timekeeper_lock */
@@ -648,6 +658,24 @@ void ktime_get_ts64(struct timespec64 *ts)
 }
 EXPORT_SYMBOL_GPL(ktime_get_ts64);
 
+/**
+ * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC
+ *
+ * Returns the seconds portion of CLOCK_MONOTONIC with a single non
+ * serialized read. tk->ktime_sec is of type 'unsigned long' so this
+ * works on both 32 and 64 bit systems. On 32 bit systems the readout
+ * covers ~136 years of uptime which should be enough to prevent
+ * premature wrap arounds.
+ */
+time64_t ktime_get_seconds(void)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+
+	WARN_ON(timekeeping_suspended);
+	return tk->ktime_sec;
+}
+EXPORT_SYMBOL_GPL(ktime_get_seconds);
+
 #ifdef CONFIG_NTP_PPS
 
 /**
-- 
cgit v1.2.3-70-g09d2


From dbe7aa622db96b5cd601f59d09c4f00b98b76079 Mon Sep 17 00:00:00 2001
From: Heena Sirwani <heenasirwani@gmail.com>
Date: Wed, 29 Oct 2014 16:01:50 +0530
Subject: timekeeping: Provide y2038 safe accessor to the seconds portion of
 CLOCK_REALTIME

ktime_get_real_seconds() is the replacement function for get_seconds()
returning the seconds portion of CLOCK_REALTIME in a time64_t. For
64bit the function is equivivalent to get_seconds(), but for 32bit it
protects the readout with the timekeeper sequence count. This is
required because 32-bit machines cannot access 64-bit tk->xtime_sec
variable atomically.

[tglx: Massaged changelog and added docbook comment ]

Signed-off-by: Heena Sirwani <heenasirwani@gmail.com>
Reviewed-by: Arnd Bergman <arnd@arndb.de>
Cc: John Stultz <john.stultz@linaro.org>
Cc: opw-kernel@googlegroups.com
Link: http://lkml.kernel.org/r/7adcfaa8962b8ad58785d9a2456c3f77d93c0ffb.1414578445.git.heenasirwani@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/timekeeping.h |  1 +
 kernel/time/timekeeping.c   | 30 ++++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 115d55e11bc..91454dea2bc 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -29,6 +29,7 @@ struct timespec get_monotonic_coarse(void);
 extern void getrawmonotonic(struct timespec *ts);
 extern void ktime_get_ts64(struct timespec64 *ts);
 extern time64_t ktime_get_seconds(void);
+extern time64_t ktime_get_real_seconds(void);
 
 extern int __getnstimeofday64(struct timespec64 *tv);
 extern void getnstimeofday64(struct timespec64 *tv);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index a693270efaf..0aef92a0a70 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -676,6 +676,36 @@ time64_t ktime_get_seconds(void)
 }
 EXPORT_SYMBOL_GPL(ktime_get_seconds);
 
+/**
+ * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME
+ *
+ * Returns the wall clock seconds since 1970. This replaces the
+ * get_seconds() interface which is not y2038 safe on 32bit systems.
+ *
+ * For 64bit systems the fast access to tk->xtime_sec is preserved. On
+ * 32bit systems the access must be protected with the sequence
+ * counter to provide "atomic" access to the 64bit tk->xtime_sec
+ * value.
+ */
+time64_t ktime_get_real_seconds(void)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+	time64_t seconds;
+	unsigned int seq;
+
+	if (IS_ENABLED(CONFIG_64BIT))
+		return tk->xtime_sec;
+
+	do {
+		seq = read_seqcount_begin(&tk_core.seq);
+		seconds = tk->xtime_sec;
+
+	} while (read_seqcount_retry(&tk_core.seq, seq));
+
+	return seconds;
+}
+EXPORT_SYMBOL_GPL(ktime_get_real_seconds);
+
 #ifdef CONFIG_NTP_PPS
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 74c450521dd8d245b982da62592a18aa6f88b045 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@fb.com>
Date: Wed, 29 Oct 2014 11:14:52 -0600
Subject: blk-mq: add a 'list' parameter to ->queue_rq()

Since we have the notion of a 'last' request in a chain, we can use
this to have the hardware optimize the issuing of requests. Add
a list_head parameter to queue_rq that the driver can use to
temporarily store hw commands for issue when 'last' is true. If we
are doing a chain of requests, pass in a NULL list for the first
request to force issue of that immediately, then batch the remainder
for deferred issue until the last request has been sent.

Instead of adding yet another argument to the hot ->queue_rq path,
encapsulate the passed arguments in a blk_mq_queue_data structure.
This is passed as a constant, and has been tested as faster than
passing 4 (or even 3) args through ->queue_rq. Update drivers for
the new ->queue_rq() prototype. There are no functional changes
in this patch for drivers - if they don't use the passed in list,
then they will just queue requests individually like before.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c                    | 29 +++++++++++++++++++++++++++--
 drivers/block/mtip32xx/mtip32xx.c |  5 +++--
 drivers/block/null_blk.c          | 10 +++++-----
 drivers/block/virtio_blk.c        |  7 ++++---
 drivers/scsi/scsi_lib.c           |  5 +++--
 include/linux/blk-mq.h            |  8 +++++++-
 6 files changed, 49 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 68929bad9a6..7e530382045 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -680,6 +680,8 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	struct request_queue *q = hctx->queue;
 	struct request *rq;
 	LIST_HEAD(rq_list);
+	LIST_HEAD(driver_list);
+	struct list_head *dptr;
 	int queued;
 
 	WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask));
@@ -705,17 +707,28 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		spin_unlock(&hctx->lock);
 	}
 
+	/*
+	 * Start off with dptr being NULL, so we start the first request
+	 * immediately, even if we have more pending.
+	 */
+	dptr = NULL;
+
 	/*
 	 * Now process all the entries, sending them to the driver.
 	 */
 	queued = 0;
 	while (!list_empty(&rq_list)) {
+		struct blk_mq_queue_data bd;
 		int ret;
 
 		rq = list_first_entry(&rq_list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 
-		ret = q->mq_ops->queue_rq(hctx, rq, list_empty(&rq_list));
+		bd.rq = rq;
+		bd.list = dptr;
+		bd.last = list_empty(&rq_list);
+
+		ret = q->mq_ops->queue_rq(hctx, &bd);
 		switch (ret) {
 		case BLK_MQ_RQ_QUEUE_OK:
 			queued++;
@@ -734,6 +747,13 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 
 		if (ret == BLK_MQ_RQ_QUEUE_BUSY)
 			break;
+
+		/*
+		 * We've done the first request. If we have more than 1
+		 * left in the list, set dptr to defer issue.
+		 */
+		if (!dptr && rq_list.next != rq_list.prev)
+			dptr = &driver_list;
 	}
 
 	if (!queued)
@@ -1153,6 +1173,11 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	}
 
 	if (is_sync) {
+		struct blk_mq_queue_data bd = {
+			.rq = rq,
+			.list = NULL,
+			.last = 1
+		};
 		int ret;
 
 		blk_mq_bio_to_request(rq, bio);
@@ -1162,7 +1187,7 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		 * error (busy), just add it to our list as we previously
 		 * would have done
 		 */
-		ret = q->mq_ops->queue_rq(data.hctx, rq, true);
+		ret = q->mq_ops->queue_rq(data.hctx, &bd);
 		if (ret == BLK_MQ_RQ_QUEUE_OK)
 			goto done;
 		else {
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 1bd5f523f8f..3bd7ca9853a 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3775,9 +3775,10 @@ static bool mtip_check_unal_depth(struct blk_mq_hw_ctx *hctx,
 	return false;
 }
 
-static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq,
-		bool last)
+static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
+			 const struct blk_mq_queue_data *bd)
 {
+	struct request *rq = bd->rq;
 	int ret;
 
 	if (unlikely(mtip_check_unal_depth(hctx, rq)))
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 2671a3f02f0..8433bc8ead3 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -313,15 +313,15 @@ static void null_request_fn(struct request_queue *q)
 	}
 }
 
-static int null_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq,
-		bool last)
+static int null_queue_rq(struct blk_mq_hw_ctx *hctx,
+			 const struct blk_mq_queue_data *bd)
 {
-	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
+	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
 
-	cmd->rq = rq;
+	cmd->rq = bd->rq;
 	cmd->nq = hctx->driver_data;
 
-	blk_mq_start_request(rq);
+	blk_mq_start_request(bd->rq);
 
 	null_handle_cmd(cmd);
 	return BLK_MQ_RQ_QUEUE_OK;
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index c6a27d54ad6..cecd3f983e4 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -158,10 +158,11 @@ static void virtblk_done(struct virtqueue *vq)
 	spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
 }
 
-static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
-		bool last)
+static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
+			   const struct blk_mq_queue_data *bd)
 {
 	struct virtio_blk *vblk = hctx->queue->queuedata;
+	struct request *req = bd->rq;
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
 	unsigned long flags;
 	unsigned int num;
@@ -222,7 +223,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
 		return BLK_MQ_RQ_QUEUE_ERROR;
 	}
 
-	if (last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
+	if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
 		notify = true;
 	spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 9eff8a37513..161dcc93ac7 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1858,9 +1858,10 @@ static void scsi_mq_done(struct scsi_cmnd *cmd)
 	blk_mq_complete_request(cmd->request);
 }
 
-static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
-		bool last)
+static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
+			 const struct blk_mq_queue_data *bd)
 {
+	struct request *req = bd->rq;
 	struct request_queue *q = req->q;
 	struct scsi_device *sdev = q->queuedata;
 	struct Scsi_Host *shost = sdev->host;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index c9be1589415..be01d7a687d 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -79,7 +79,13 @@ struct blk_mq_tag_set {
 	struct list_head	tag_list;
 };
 
-typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, struct request *, bool);
+struct blk_mq_queue_data {
+	struct request *rq;
+	struct list_head *list;
+	bool last;
+};
+
+typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *);
 typedef struct blk_mq_hw_ctx *(map_queue_fn)(struct request_queue *, const int);
 typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool);
 typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
-- 
cgit v1.2.3-70-g09d2


From e167dfb53cb85fde7b15f644e9dbef7ba31896b6 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@fb.com>
Date: Wed, 29 Oct 2014 11:18:26 -0600
Subject: blk-mq: add BLK_MQ_F_DEFER_ISSUE support flag

Drivers can now tell blk-mq if they take advantage of the deferred
issue through 'last' or not. If they do, don't do queue-direct
for sync IO. This is a preparation patch for the nvme conversion.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c         | 7 ++++++-
 include/linux/blk-mq.h | 1 +
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 7e530382045..b355b5957cd 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1172,7 +1172,12 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		goto run_queue;
 	}
 
-	if (is_sync) {
+	/*
+	 * If the driver supports defer issued based on 'last', then
+	 * queue it up like normal since we can potentially save some
+	 * CPU this way.
+	 */
+	if (is_sync && !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
 		struct blk_mq_queue_data bd = {
 			.rq = rq,
 			.list = NULL,
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index be01d7a687d..c3b64ec5321 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -146,6 +146,7 @@ enum {
 	BLK_MQ_F_TAG_SHARED	= 1 << 1,
 	BLK_MQ_F_SG_MERGE	= 1 << 2,
 	BLK_MQ_F_SYSFS_UP	= 1 << 3,
+	BLK_MQ_F_DEFER_ISSUE	= 1 << 4,
 
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
-- 
cgit v1.2.3-70-g09d2


From 28f6569ab7d036cd4ee94c26bb76dc1b3f3fc056 Mon Sep 17 00:00:00 2001
From: Pranith Kumar <bobby.prani@gmail.com>
Date: Mon, 22 Sep 2014 14:00:48 -0400
Subject: rcu: Remove redundant TREE_PREEMPT_RCU config option

PREEMPT_RCU and TREE_PREEMPT_RCU serve the same function after
TINY_PREEMPT_RCU has been removed. This patch removes TREE_PREEMPT_RCU
and uses PREEMPT_RCU config option in its place.

Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 Documentation/RCU/rcu.txt                          |  4 ++--
 Documentation/RCU/stallwarn.txt                    |  8 ++++----
 Documentation/RCU/trace.txt                        |  4 ++--
 Documentation/RCU/whatisRCU.txt                    |  2 +-
 include/linux/init_task.h                          |  2 +-
 include/linux/rcupdate.h                           |  6 +++---
 include/linux/sched.h                              |  4 ++--
 include/trace/events/rcu.h                         |  4 ++--
 init/Kconfig                                       | 22 ++++++++--------------
 kernel/rcu/Makefile                                |  2 +-
 kernel/rcu/tree.h                                  | 10 +++++-----
 kernel/rcu/tree_plugin.h                           |  6 +++---
 kernel/rcu/update.c                                |  2 +-
 lib/Kconfig.debug                                  |  2 +-
 .../selftests/rcutorture/configs/rcu/TREE01        |  2 +-
 .../selftests/rcutorture/configs/rcu/TREE02        |  2 +-
 .../selftests/rcutorture/configs/rcu/TREE02-T      |  2 +-
 .../selftests/rcutorture/configs/rcu/TREE03        |  2 +-
 .../selftests/rcutorture/configs/rcu/TREE08        |  2 +-
 .../selftests/rcutorture/configs/rcu/TREE08-T      |  2 +-
 .../selftests/rcutorture/configs/rcu/TREE09        |  2 +-
 .../configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP           |  2 +-
 .../configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp           |  2 +-
 .../configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp           |  2 +-
 .../configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP           |  2 +-
 .../configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp           |  2 +-
 .../configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP          |  2 +-
 .../configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp          |  2 +-
 .../configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp          |  2 +-
 .../configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP          |  2 +-
 .../configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp          |  2 +-
 .../configs/rcu/v3.12/P6---t-nh-SD-smp-hp          |  2 +-
 .../configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP          |  2 +-
 .../configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all      |  2 +-
 .../configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none     |  2 +-
 .../configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp          |  2 +-
 .../configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP           |  2 +-
 .../configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp           |  2 +-
 .../configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp           |  2 +-
 .../configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP           |  2 +-
 .../configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp           |  2 +-
 .../configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP           |  2 +-
 .../configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp           |  2 +-
 .../configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp           |  2 +-
 .../configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP           |  2 +-
 .../configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp           |  2 +-
 .../testing/selftests/rcutorture/doc/TINY_RCU.txt  |  2 +-
 .../selftests/rcutorture/doc/TREE_RCU-kconfig.txt  | 10 +++++-----
 48 files changed, 74 insertions(+), 80 deletions(-)

(limited to 'include')

diff --git a/Documentation/RCU/rcu.txt b/Documentation/RCU/rcu.txt
index bf778332a28..745f429fda7 100644
--- a/Documentation/RCU/rcu.txt
+++ b/Documentation/RCU/rcu.txt
@@ -36,7 +36,7 @@ o	How can the updater tell when a grace period has completed
 	executed in user mode, or executed in the idle loop, we can
 	safely free up that item.
 
-	Preemptible variants of RCU (CONFIG_TREE_PREEMPT_RCU) get the
+	Preemptible variants of RCU (CONFIG_PREEMPT_RCU) get the
 	same effect, but require that the readers manipulate CPU-local
 	counters.  These counters allow limited types of blocking within
 	RCU read-side critical sections.  SRCU also uses CPU-local
@@ -81,7 +81,7 @@ o	I hear that RCU is patented?  What is with that?
 o	I hear that RCU needs work in order to support realtime kernels?
 
 	This work is largely completed.  Realtime-friendly RCU can be
-	enabled via the CONFIG_TREE_PREEMPT_RCU kernel configuration
+	enabled via the CONFIG_PREEMPT_RCU kernel configuration
 	parameter.  However, work is in progress for enabling priority
 	boosting of preempted RCU read-side critical sections.	This is
 	needed if you have CPU-bound realtime threads.
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index ef5a2fd4ff7..783e0720994 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -77,7 +77,7 @@ This message indicates that CPU 5 detected that it was causing a stall,
 and that the stall was affecting RCU-sched.  This message will normally be
 followed by a stack dump of the offending CPU.  On TREE_RCU kernel builds,
 RCU and RCU-sched are implemented by the same underlying mechanism,
-while on TREE_PREEMPT_RCU kernel builds, RCU is instead implemented
+while on PREEMPT_RCU kernel builds, RCU is instead implemented
 by rcu_preempt_state.
 
 On the other hand, if the offending CPU fails to print out a stall-warning
@@ -89,7 +89,7 @@ INFO: rcu_bh_state detected stalls on CPUs/tasks: { 3 5 } (detected by 2, 2502 j
 This message indicates that CPU 2 detected that CPUs 3 and 5 were both
 causing stalls, and that the stall was affecting RCU-bh.  This message
 will normally be followed by stack dumps for each CPU.  Please note that
-TREE_PREEMPT_RCU builds can be stalled by tasks as well as by CPUs,
+PREEMPT_RCU builds can be stalled by tasks as well as by CPUs,
 and that the tasks will be indicated by PID, for example, "P3421".
 It is even possible for a rcu_preempt_state stall to be caused by both
 CPUs -and- tasks, in which case the offending CPUs and tasks will all
@@ -205,10 +205,10 @@ o	A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
 o	A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
 	is running at a higher priority than the RCU softirq threads.
 	This will prevent RCU callbacks from ever being invoked,
-	and in a CONFIG_TREE_PREEMPT_RCU kernel will further prevent
+	and in a CONFIG_PREEMPT_RCU kernel will further prevent
 	RCU grace periods from ever completing.  Either way, the
 	system will eventually run out of memory and hang.  In the
-	CONFIG_TREE_PREEMPT_RCU case, you might see stall-warning
+	CONFIG_PREEMPT_RCU case, you might see stall-warning
 	messages.
 
 o	A hardware or software issue shuts off the scheduler-clock
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 910870b15ac..b63b9bb3bc0 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -8,7 +8,7 @@ The following sections describe the debugfs files and formats, first
 for rcutree and next for rcutiny.
 
 
-CONFIG_TREE_RCU and CONFIG_TREE_PREEMPT_RCU debugfs Files and Formats
+CONFIG_TREE_RCU and CONFIG_PREEMPT_RCU debugfs Files and Formats
 
 These implementations of RCU provide several debugfs directories under the
 top-level directory "rcu":
@@ -18,7 +18,7 @@ rcu/rcu_preempt
 rcu/rcu_sched
 
 Each directory contains files for the corresponding flavor of RCU.
-Note that rcu/rcu_preempt is only present for CONFIG_TREE_PREEMPT_RCU.
+Note that rcu/rcu_preempt is only present for CONFIG_PREEMPT_RCU.
 For CONFIG_TREE_RCU, the RCU flavor maps onto the RCU-sched flavor,
 so that activity for both appears in rcu/rcu_sched.
 
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index e48c57f1943..88dfce182f6 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -137,7 +137,7 @@ rcu_read_lock()
 	Used by a reader to inform the reclaimer that the reader is
 	entering an RCU read-side critical section.  It is illegal
 	to block while in an RCU read-side critical section, though
-	kernels built with CONFIG_TREE_PREEMPT_RCU can preempt RCU
+	kernels built with CONFIG_PREEMPT_RCU can preempt RCU
 	read-side critical sections.  Any RCU-protected data structure
 	accessed during an RCU read-side critical section is guaranteed to
 	remain unreclaimed for the full duration of that critical section.
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 77fc43f8fb7..d996aef8044 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -102,7 +102,7 @@ extern struct group_info init_groups;
 #define INIT_IDS
 #endif
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
 #define INIT_TASK_RCU_TREE_PREEMPT()					\
 	.rcu_blocked_node = NULL,
 #else
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index a4a819ffb2d..295bb4595de 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -57,7 +57,7 @@ enum rcutorture_type {
 	INVALID_RCU_FLAVOR
 };
 
-#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 			    unsigned long *gpnum, unsigned long *completed);
 void rcutorture_record_test_transition(void);
@@ -365,7 +365,7 @@ typedef void call_rcu_func_t(struct rcu_head *head,
 			     void (*func)(struct rcu_head *head));
 void wait_rcu_gp(call_rcu_func_t crf);
 
-#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
 #include <linux/rcutree.h>
 #elif defined(CONFIG_TINY_RCU)
 #include <linux/rcutiny.h>
@@ -852,7 +852,7 @@ static inline void rcu_preempt_sleep_check(void)
  *
  * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU),
  * it is illegal to block while in an RCU read-side critical section.
- * In preemptible RCU implementations (TREE_PREEMPT_RCU) in CONFIG_PREEMPT
+ * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPT
  * kernel builds, RCU read-side critical sections may be preempted,
  * but explicit blocking is illegal.  Finally, in preemptible RCU
  * implementations in real-time (with -rt patchset) kernel builds, RCU
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5e344bbe63e..706a9f74490 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1278,9 +1278,9 @@ struct task_struct {
 	union rcu_special rcu_read_unlock_special;
 	struct list_head rcu_node_entry;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
 	struct rcu_node *rcu_blocked_node;
-#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
 #ifdef CONFIG_TASKS_RCU
 	unsigned long rcu_tasks_nvcsw;
 	bool rcu_tasks_holdout;
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index e335e7d8c6c..c78e88ce5ea 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -36,7 +36,7 @@ TRACE_EVENT(rcu_utilization,
 
 #ifdef CONFIG_RCU_TRACE
 
-#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
 
 /*
  * Tracepoint for grace-period events.  Takes a string identifying the
@@ -345,7 +345,7 @@ TRACE_EVENT(rcu_fqs,
 		  __entry->cpu, __entry->qsevent)
 );
 
-#endif /* #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) */
+#endif /* #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) */
 
 /*
  * Tracepoint for dyntick-idle entry/exit events.  These take a string
diff --git a/init/Kconfig b/init/Kconfig
index 15c299cc7c1..5ac596e2cb4 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -477,7 +477,7 @@ config TREE_RCU
 	  thousands of CPUs.  It also scales down nicely to
 	  smaller systems.
 
-config TREE_PREEMPT_RCU
+config PREEMPT_RCU
 	bool "Preemptible tree-based hierarchical RCU"
 	depends on PREEMPT
 	select IRQ_WORK
@@ -501,12 +501,6 @@ config TINY_RCU
 
 endchoice
 
-config PREEMPT_RCU
-	def_bool TREE_PREEMPT_RCU
-	help
-	  This option enables preemptible-RCU code that is common between
-	  TREE_PREEMPT_RCU and, in the old days, TINY_PREEMPT_RCU.
-
 config TASKS_RCU
 	bool "Task_based RCU implementation using voluntary context switch"
 	default n
@@ -518,7 +512,7 @@ config TASKS_RCU
 	  If unsure, say N.
 
 config RCU_STALL_COMMON
-	def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE )
+	def_bool ( TREE_RCU || PREEMPT_RCU || RCU_TRACE )
 	help
 	  This option enables RCU CPU stall code that is common between
 	  the TINY and TREE variants of RCU.  The purpose is to allow
@@ -576,7 +570,7 @@ config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
 	range 2 64 if 64BIT
 	range 2 32 if !64BIT
-	depends on TREE_RCU || TREE_PREEMPT_RCU
+	depends on TREE_RCU || PREEMPT_RCU
 	default 64 if 64BIT
 	default 32 if !64BIT
 	help
@@ -596,7 +590,7 @@ config RCU_FANOUT_LEAF
 	int "Tree-based hierarchical RCU leaf-level fanout value"
 	range 2 RCU_FANOUT if 64BIT
 	range 2 RCU_FANOUT if !64BIT
-	depends on TREE_RCU || TREE_PREEMPT_RCU
+	depends on TREE_RCU || PREEMPT_RCU
 	default 16
 	help
 	  This option controls the leaf-level fanout of hierarchical
@@ -621,7 +615,7 @@ config RCU_FANOUT_LEAF
 
 config RCU_FANOUT_EXACT
 	bool "Disable tree-based hierarchical RCU auto-balancing"
-	depends on TREE_RCU || TREE_PREEMPT_RCU
+	depends on TREE_RCU || PREEMPT_RCU
 	default n
 	help
 	  This option forces use of the exact RCU_FANOUT value specified,
@@ -652,11 +646,11 @@ config RCU_FAST_NO_HZ
 	  Say N if you are unsure.
 
 config TREE_RCU_TRACE
-	def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU )
+	def_bool RCU_TRACE && ( TREE_RCU || PREEMPT_RCU )
 	select DEBUG_FS
 	help
 	  This option provides tracing for the TREE_RCU and
-	  TREE_PREEMPT_RCU implementations, permitting Makefile to
+	  PREEMPT_RCU implementations, permitting Makefile to
 	  trivially select kernel/rcutree_trace.c.
 
 config RCU_BOOST
@@ -716,7 +710,7 @@ config RCU_BOOST_DELAY
 
 config RCU_NOCB_CPU
 	bool "Offload RCU callback processing from boot-selected CPUs"
-	depends on TREE_RCU || TREE_PREEMPT_RCU
+	depends on TREE_RCU || PREEMPT_RCU
 	default n
 	help
 	  Use this option to reduce OS jitter for aggressive HPC or
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 807ccfbf69b..e6fae503d1b 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -1,6 +1,6 @@
 obj-y += update.o srcu.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_TREE_RCU) += tree.o
-obj-$(CONFIG_TREE_PREEMPT_RCU) += tree.o
+obj-$(CONFIG_PREEMPT_RCU) += tree.o
 obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o
 obj-$(CONFIG_TINY_RCU) += tiny.o
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index bbdc45d8d74..66cde5109c7 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -139,7 +139,7 @@ struct rcu_node {
 	unsigned long expmask;	/* Groups that have ->blkd_tasks */
 				/*  elements that need to drain to allow the */
 				/*  current expedited grace period to */
-				/*  complete (only for TREE_PREEMPT_RCU). */
+				/*  complete (only for PREEMPT_RCU). */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask & expmask. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
@@ -530,10 +530,10 @@ DECLARE_PER_CPU(struct rcu_data, rcu_sched_data);
 extern struct rcu_state rcu_bh_state;
 DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
 extern struct rcu_state rcu_preempt_state;
 DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
-#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
 
 #ifdef CONFIG_RCU_BOOST
 DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
@@ -563,10 +563,10 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 static void rcu_preempt_check_callbacks(int cpu);
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
-#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU)
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PREEMPT_RCU)
 static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 			       bool wake);
-#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */
+#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PREEMPT_RCU) */
 static void __init __rcu_init_preempt(void);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 344f0e66151..6d07fb402e8 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -100,7 +100,7 @@ static void __init rcu_bootup_announce_oddness(void)
 #endif
 }
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
 
 RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);
 static struct rcu_state *rcu_state_p = &rcu_preempt_state;
@@ -932,7 +932,7 @@ void exit_rcu(void)
 	__rcu_read_unlock();
 }
 
-#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+#else /* #ifdef CONFIG_PREEMPT_RCU */
 
 static struct rcu_state *rcu_state_p = &rcu_sched_state;
 
@@ -1083,7 +1083,7 @@ void exit_rcu(void)
 {
 }
 
-#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 #ifdef CONFIG_RCU_BOOST
 
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 3ef8ba58694..27a5b174b2a 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -306,7 +306,7 @@ struct debug_obj_descr rcuhead_debug_descr = {
 EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
 #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
-#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
 void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp,
 			       unsigned long secs,
 			       unsigned long c_old, unsigned long c)
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 4e35a5d767e..12e7b020539 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1252,7 +1252,7 @@ config RCU_CPU_STALL_VERBOSE
 
 config RCU_CPU_STALL_INFO
 	bool "Print additional diagnostics on RCU CPU stall"
-	depends on (TREE_RCU || TREE_PREEMPT_RCU) && DEBUG_KERNEL
+	depends on (TREE_RCU || PREEMPT_RCU) && DEBUG_KERNEL
 	default n
 	help
 	  For each stalled CPU that is aware of the current RCU grace
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
index 38e3895759d..69f8e5878a5 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
@@ -2,7 +2,7 @@ CONFIG_SMP=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
index ea119ba2f7d..fc29c629719 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
@@ -3,7 +3,7 @@ CONFIG_NR_CPUS=8
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
index 19cf9485f48..778ec567a47 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
@@ -3,7 +3,7 @@ CONFIG_NR_CPUS=8
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
index b95f62efd6f..a022f033230 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
@@ -3,7 +3,7 @@ CONFIG_NR_CPUS=8
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=y
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
index 69a2e255bf9..6f8609d2d07 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
@@ -3,7 +3,7 @@ CONFIG_NR_CPUS=16
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
index a0f32fb8f17..4e55bee2d3f 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
@@ -3,7 +3,7 @@ CONFIG_NR_CPUS=16
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
index b7a62a540ad..47e2ecd1844 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE09
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
@@ -3,7 +3,7 @@ CONFIG_NR_CPUS=1
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP
index f72402d7c13..dd7bd4d2d85 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P1-S-T-NH-SD-SMP-HP
@@ -9,7 +9,7 @@ CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SYSFS_DEPRECATED_V2=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp
index 0f3b667d2a9..81d48436282 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P2-2-t-nh-sd-SMP-hp
@@ -10,7 +10,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SYSFS_DEPRECATED_V2=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp
index b035e141bf2..16e22b7815c 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P3-3-T-nh-SD-SMP-hp
@@ -10,7 +10,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SYSFS_DEPRECATED_V2=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP
index 3ccf6a9447f..ea7ed3b9a2d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P4-A-t-NH-sd-SMP-HP
@@ -8,7 +8,7 @@ CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_RT_MUTEXES=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp
index a55c00877fe..24f4d5e40c8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp
@@ -11,7 +11,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_OBJECTS=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP
index 9647c44cf4b..688066322c8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P1-S-T-NH-SD-SMP-HP
@@ -10,7 +10,7 @@ CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SYSFS_DEPRECATED_V2=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp
index 0f3b667d2a9..81d48436282 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P2-2-t-nh-sd-SMP-hp
@@ -10,7 +10,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SYSFS_DEPRECATED_V2=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp
index b035e141bf2..16e22b7815c 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P3-3-T-nh-SD-SMP-hp
@@ -10,7 +10,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SYSFS_DEPRECATED_V2=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP
index 3ccf6a9447f..ea7ed3b9a2d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P4-A-t-NH-sd-SMP-HP
@@ -8,7 +8,7 @@ CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_RT_MUTEXES=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp
index a55c00877fe..24f4d5e40c8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp
@@ -11,7 +11,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_OBJECTS=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp
index f4c9175828b..1be59e4c8ba 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P6---t-nh-SD-smp-hp
@@ -8,7 +8,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SYSFS_DEPRECATED_V2=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP
index 77a8c5b7576..b49ef746309 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP
@@ -14,7 +14,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_PROVE_LOCKING=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all
index 0eecebc6e95..a55a6ac447d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-all
@@ -14,7 +14,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_PROVE_LOCKING=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none
index 0eecebc6e95..a55a6ac447d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-HP-none
@@ -14,7 +14,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_PROVE_LOCKING=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp
index 588bc70420c..3134f46b2f8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P7-4-T-NH-SD-SMP-hp
@@ -14,7 +14,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_PROVE_LOCKING=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP
index 9647c44cf4b..688066322c8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P1-S-T-NH-SD-SMP-HP
@@ -10,7 +10,7 @@ CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SYSFS_DEPRECATED_V2=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp
index 0f3b667d2a9..81d48436282 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P2-2-t-nh-sd-SMP-hp
@@ -10,7 +10,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SYSFS_DEPRECATED_V2=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp
index b035e141bf2..16e22b7815c 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P3-3-T-nh-SD-SMP-hp
@@ -10,7 +10,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SYSFS_DEPRECATED_V2=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP
index 3ccf6a9447f..ea7ed3b9a2d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P4-A-t-NH-sd-SMP-HP
@@ -8,7 +8,7 @@ CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_RT_MUTEXES=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp
index a55c00877fe..24f4d5e40c8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp
@@ -11,7 +11,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_OBJECTS=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP
index 9647c44cf4b..688066322c8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P1-S-T-NH-SD-SMP-HP
@@ -10,7 +10,7 @@ CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SYSFS_DEPRECATED_V2=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp
index 0f3b667d2a9..81d48436282 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P2-2-t-nh-sd-SMP-hp
@@ -10,7 +10,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SYSFS_DEPRECATED_V2=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp
index b035e141bf2..16e22b7815c 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P3-3-T-nh-SD-SMP-hp
@@ -10,7 +10,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SYSFS_DEPRECATED_V2=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP
index 3ccf6a9447f..ea7ed3b9a2d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P4-A-t-NH-sd-SMP-HP
@@ -8,7 +8,7 @@ CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_MODULE_UNLOAD=y
 CONFIG_RT_MUTEXES=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp
index a55c00877fe..24f4d5e40c8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp
@@ -11,7 +11,7 @@ CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_OBJECTS=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
diff --git a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt
index 28db67b54e5..9ef33a743b7 100644
--- a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt
+++ b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt
@@ -34,7 +34,7 @@ CONFIG_PREEMPT
 CONFIG_PREEMPT_RCU
 CONFIG_SMP
 CONFIG_TINY_RCU
-CONFIG_TREE_PREEMPT_RCU
+CONFIG_PREEMPT_RCU
 CONFIG_TREE_RCU
 
 	All forced by CONFIG_TINY_RCU.
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
index ab6e7b4103a..f613755a90b 100644
--- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
@@ -1,5 +1,5 @@
 This document gives a brief rationale for the TREE_RCU-related test
-cases, a group that includes TREE_PREEMPT_RCU.
+cases, a group that includes PREEMPT_RCU.
 
 
 Kconfig Parameters:
@@ -14,7 +14,7 @@ CONFIG_NO_HZ_FULL_SYSIDLE -- Do one.
 CONFIG_PREEMPT -- Do half.  (First three and #8.)
 CONFIG_PROVE_LOCKING -- Do all but two, covering CONFIG_PROVE_RCU and not.
 CONFIG_PROVE_RCU -- Do all but one under CONFIG_PROVE_LOCKING.
-CONFIG_RCU_BOOST -- one of TREE_PREEMPT_RCU.
+CONFIG_RCU_BOOST -- one of PREEMPT_RCU.
 CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing.
 CONFIG_RCU_CPU_STALL_INFO -- Do one.
 CONFIG_RCU_CPU_STALL_VERBOSE -- do one with and without _INFO.
@@ -27,7 +27,7 @@ CONFIG_RCU_NOCB_CPU_ALL -- Do one.
 CONFIG_RCU_NOCB_CPU_NONE -- Do one.
 CONFIG_RCU_NOCB_CPU_ZERO -- Do one.
 CONFIG_RCU_TRACE -- Do half.
-CONFIG_SMP -- Need one !SMP for TREE_PREEMPT_RCU.
+CONFIG_SMP -- Need one !SMP for PREEMPT_RCU.
 RCU-bh: Do one with PREEMPT and one with !PREEMPT.
 RCU-sched: Do one with PREEMPT but not BOOST.
 
@@ -77,7 +77,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT
 
 CONFIG_RCU_STALL_COMMON
 
-	Implied by TREE_RCU and TREE_PREEMPT_RCU.
+	Implied by TREE_RCU and PREEMPT_RCU.
 
 CONFIG_RCU_TORTURE_TEST
 CONFIG_RCU_TORTURE_TEST_RUNNABLE
@@ -88,7 +88,7 @@ CONFIG_RCU_USER_QS
 
 	Redundant with CONFIG_NO_HZ_FULL.
 
-CONFIG_TREE_PREEMPT_RCU
+CONFIG_PREEMPT_RCU
 CONFIG_TREE_RCU
 
 	These are controlled by CONFIG_PREEMPT.
-- 
cgit v1.2.3-70-g09d2


From dca145ffaa8d39ea1904491ac81b92b7049372c0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 27 Oct 2014 21:45:24 -0700
Subject: tcp: allow for bigger reordering level

While testing upcoming Yaogong patch (converting out of order queue
into an RB tree), I hit the max reordering level of linux TCP stack.

Reordering level was limited to 127 for no good reason, and some
network setups [1] can easily reach this limit and get limited
throughput.

Allow a new max limit of 300, and add a sysctl to allow admins to even
allow bigger (or lower) values if needed.

[1] Aggregation of links, per packet load balancing, fabrics not doing
 deep packet inspections, alternative TCP congestion modules...

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yaogong Wang <wygivan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/bonding.txt   |  7 ++-----
 Documentation/networking/ip-sysctl.txt | 10 +++++++++-
 include/linux/tcp.h                    |  4 ++--
 include/net/tcp.h                      |  4 +---
 net/ipv4/sysctl_net_ipv4.c             |  7 +++++++
 net/ipv4/tcp_input.c                   |  3 ++-
 6 files changed, 23 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index eeb5b2e97be..83bf4986bae 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -2230,11 +2230,8 @@ balance-rr: This mode is the only mode that will permit a single
 
 	It is possible to adjust TCP/IP's congestion limits by
 	altering the net.ipv4.tcp_reordering sysctl parameter.  The
-	usual default value is 3, and the maximum useful value is 127.
-	For a four interface balance-rr bond, expect that a single
-	TCP/IP stream will utilize no more than approximately 2.3
-	interface's worth of throughput, even after adjusting
-	tcp_reordering.
+	usual default value is 3. But keep in mind TCP stack is able
+	to automatically increase this when it detects reorders.
 
 	Note that the fraction of packets that will be delivered out of
 	order is highly variable, and is unlikely to be zero.  The level
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 0307e2875f2..9028b879a97 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -376,9 +376,17 @@ tcp_orphan_retries - INTEGER
 	may consume significant resources. Cf. tcp_max_orphans.
 
 tcp_reordering - INTEGER
-	Maximal reordering of packets in a TCP stream.
+	Initial reordering level of packets in a TCP stream.
+	TCP stack can then dynamically adjust flow reordering level
+	between this initial value and tcp_max_reordering
 	Default: 3
 
+tcp_max_reordering - INTEGER
+	Maximal reordering level of packets in a TCP stream.
+	300 is a fairly conservative value, but you might increase it
+	if paths are using per packet load balancing (like bonding rr mode)
+	Default: 300
+
 tcp_retrans_collapse - BOOLEAN
 	Bug-to-bug compatibility with some broken printers.
 	On retransmit try to send bigger packets to work around bugs in
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index c2dee7deefa..f566b856789 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -204,10 +204,10 @@ struct tcp_sock {
 
 	u16	urg_data;	/* Saved octet of OOB data and control flags */
 	u8	ecn_flags;	/* ECN status bits.			*/
-	u8	reordering;	/* Packet reordering metric.		*/
+	u8	keepalive_probes; /* num of allowed keep alive probes	*/
+	u32	reordering;	/* Packet reordering metric.		*/
 	u32	snd_up;		/* Urgent pointer		*/
 
-	u8	keepalive_probes; /* num of allowed keep alive probes	*/
 /*
  *      Options received (usually on last packet, some only on SYN packets).
  */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index c73fc145ee4..3a35b150035 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -70,9 +70,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 /* After receiving this amount of duplicate ACKs fast retransmit starts. */
 #define TCP_FASTRETRANS_THRESH 3
 
-/* Maximal reordering. */
-#define TCP_MAX_REORDERING	127
-
 /* Maximal number of ACKs sent quickly to accelerate slow-start. */
 #define TCP_MAX_QUICKACKS	16U
 
@@ -252,6 +249,7 @@ extern int sysctl_tcp_abort_on_overflow;
 extern int sysctl_tcp_max_orphans;
 extern int sysctl_tcp_fack;
 extern int sysctl_tcp_reordering;
+extern int sysctl_tcp_max_reordering;
 extern int sysctl_tcp_dsack;
 extern long sysctl_tcp_mem[3];
 extern int sysctl_tcp_wmem[3];
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index b3c53c8b331..e0ee384a448 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -495,6 +495,13 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "tcp_max_reordering",
+		.data		= &sysctl_tcp_max_reordering,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 	{
 		.procname	= "tcp_dsack",
 		.data		= &sysctl_tcp_dsack,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a12b455928e..9a18cdd633f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -81,6 +81,7 @@ int sysctl_tcp_window_scaling __read_mostly = 1;
 int sysctl_tcp_sack __read_mostly = 1;
 int sysctl_tcp_fack __read_mostly = 1;
 int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH;
+int sysctl_tcp_max_reordering __read_mostly = 300;
 EXPORT_SYMBOL(sysctl_tcp_reordering);
 int sysctl_tcp_dsack __read_mostly = 1;
 int sysctl_tcp_app_win __read_mostly = 31;
@@ -833,7 +834,7 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
 	if (metric > tp->reordering) {
 		int mib_idx;
 
-		tp->reordering = min(TCP_MAX_REORDERING, metric);
+		tp->reordering = min(sysctl_tcp_max_reordering, metric);
 
 		/* This exciting event is worth to be remembered. 8) */
 		if (ts)
-- 
cgit v1.2.3-70-g09d2


From 7fd2561e4ebdd070ebba6d3326c4c5b13942323f Mon Sep 17 00:00:00 2001
From: Erik Kline <ek@google.com>
Date: Tue, 28 Oct 2014 18:11:14 +0900
Subject: net: ipv6: Add a sysctl to make optimistic addresses useful
 candidates

Add a sysctl that causes an interface's optimistic addresses
to be considered equivalent to other non-deprecated addresses
for source address selection purposes.  Preferred addresses
will still take precedence over optimistic addresses, subject
to other ranking in the source address selection algorithm.

This is useful where different interfaces are connected to
different networks from different ISPs (e.g., a cell network
and a home wifi network).

The current behaviour complies with RFC 3484/6724, and it
makes sense if the host has only one interface, or has
multiple interfaces on the same network (same or cooperating
administrative domain(s), but not in the multiple distinct
networks case.

For example, if a mobile device has an IPv6 address on an LTE
network and then connects to IPv6-enabled wifi, while the wifi
IPv6 address is undergoing DAD, IPv6 connections will try use
the wifi default route with the LTE IPv6 address, and will get
stuck until they time out.

Also, because optimistic nodes can receive frames, issue
an RTM_NEWADDR as soon as DAD starts (with the IFA_F_OPTIMSTIC
flag appropriately set).  A second RTM_NEWADDR is sent if DAD
completes (the address flags have changed), otherwise an
RTM_DELADDR is sent.

Also: add an entry in ip-sysctl.txt for optimistic_dad.

Signed-off-by: Erik Kline <ek@google.com>
Acked-by: Lorenzo Colitti <lorenzo@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 13 ++++++++++
 include/linux/ipv6.h                   |  1 +
 include/uapi/linux/ipv6.h              |  1 +
 net/ipv6/addrconf.c                    | 46 ++++++++++++++++++++++++++++++++--
 4 files changed, 59 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 9028b879a97..368e3251c55 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1460,6 +1460,19 @@ suppress_frag_ndisc - INTEGER
 	1 - (default) discard fragmented neighbor discovery packets
 	0 - allow fragmented neighbor discovery packets
 
+optimistic_dad - BOOLEAN
+	Whether to perform Optimistic Duplicate Address Detection (RFC 4429).
+		0: disabled (default)
+		1: enabled
+
+use_optimistic - BOOLEAN
+	If enabled, do not classify optimistic addresses as deprecated during
+	source address selection.  Preferred addresses will still be chosen
+	before optimistic addresses, subject to other ranking in the source
+	address selection algorithm.
+		0: disabled (default)
+		1: enabled
+
 icmp/*:
 ratelimit - INTEGER
 	Limit the maximal rates for sending ICMPv6 packets.
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index ff560537dd6..7121a2e97ce 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -42,6 +42,7 @@ struct ipv6_devconf {
 	__s32		accept_ra_from_local;
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
 	__s32		optimistic_dad;
+	__s32		use_optimistic;
 #endif
 #ifdef CONFIG_IPV6_MROUTE
 	__s32		mc_forwarding;
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index efa2666f4b8..e863d088b9a 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -164,6 +164,7 @@ enum {
 	DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL,
 	DEVCONF_SUPPRESS_FRAG_NDISC,
 	DEVCONF_ACCEPT_RA_FROM_LOCAL,
+	DEVCONF_USE_OPTIMISTIC,
 	DEVCONF_MAX
 };
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 50b95b2db87..8d12b7c7018 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1170,6 +1170,9 @@ enum {
 	IPV6_SADDR_RULE_PRIVACY,
 	IPV6_SADDR_RULE_ORCHID,
 	IPV6_SADDR_RULE_PREFIX,
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+	IPV6_SADDR_RULE_NOT_OPTIMISTIC,
+#endif
 	IPV6_SADDR_RULE_MAX
 };
 
@@ -1197,6 +1200,15 @@ static inline int ipv6_saddr_preferred(int type)
 	return 0;
 }
 
+static inline bool ipv6_use_optimistic_addr(struct inet6_dev *idev)
+{
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+	return idev && idev->cnf.optimistic_dad && idev->cnf.use_optimistic;
+#else
+	return false;
+#endif
+}
+
 static int ipv6_get_saddr_eval(struct net *net,
 			       struct ipv6_saddr_score *score,
 			       struct ipv6_saddr_dst *dst,
@@ -1257,10 +1269,16 @@ static int ipv6_get_saddr_eval(struct net *net,
 		score->scopedist = ret;
 		break;
 	case IPV6_SADDR_RULE_PREFERRED:
+	    {
 		/* Rule 3: Avoid deprecated and optimistic addresses */
+		u8 avoid = IFA_F_DEPRECATED;
+
+		if (!ipv6_use_optimistic_addr(score->ifa->idev))
+			avoid |= IFA_F_OPTIMISTIC;
 		ret = ipv6_saddr_preferred(score->addr_type) ||
-		      !(score->ifa->flags & (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC));
+		      !(score->ifa->flags & avoid);
 		break;
+	    }
 #ifdef CONFIG_IPV6_MIP6
 	case IPV6_SADDR_RULE_HOA:
 	    {
@@ -1306,6 +1324,14 @@ static int ipv6_get_saddr_eval(struct net *net,
 			ret = score->ifa->prefix_len;
 		score->matchlen = ret;
 		break;
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+	case IPV6_SADDR_RULE_NOT_OPTIMISTIC:
+		/* Optimistic addresses still have lower precedence than other
+		 * preferred addresses.
+		 */
+		ret = !(score->ifa->flags & IFA_F_OPTIMISTIC);
+		break;
+#endif
 	default:
 		ret = 0;
 	}
@@ -3222,8 +3248,15 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 	 * Optimistic nodes can start receiving
 	 * Frames right away
 	 */
-	if (ifp->flags & IFA_F_OPTIMISTIC)
+	if (ifp->flags & IFA_F_OPTIMISTIC) {
 		ip6_ins_rt(ifp->rt);
+		if (ipv6_use_optimistic_addr(idev)) {
+			/* Because optimistic nodes can use this address,
+			 * notify listeners. If DAD fails, RTM_DELADDR is sent.
+			 */
+			ipv6_ifa_notify(RTM_NEWADDR, ifp);
+		}
+	}
 
 	addrconf_dad_kick(ifp);
 out:
@@ -4330,6 +4363,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route;
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
 	array[DEVCONF_OPTIMISTIC_DAD] = cnf->optimistic_dad;
+	array[DEVCONF_USE_OPTIMISTIC] = cnf->use_optimistic;
 #endif
 #ifdef CONFIG_IPV6_MROUTE
 	array[DEVCONF_MC_FORWARDING] = cnf->mc_forwarding;
@@ -5155,6 +5189,14 @@ static struct addrconf_sysctl_table
 			.proc_handler   = proc_dointvec,
 
 		},
+		{
+			.procname       = "use_optimistic",
+			.data           = &ipv6_devconf.use_optimistic,
+			.maxlen         = sizeof(int),
+			.mode           = 0644,
+			.proc_handler   = proc_dointvec,
+
+		},
 #endif
 #ifdef CONFIG_IPV6_MROUTE
 		{
-- 
cgit v1.2.3-70-g09d2


From bc9ad166e38ae1cdcb5323a8aa45dff834d68bfa Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 28 Oct 2014 18:05:13 -0700
Subject: net: introduce napi_schedule_irqoff()

napi_schedule() can be called from any context and has to mask hard
irqs.

Add a variant that can only be called from hard interrupts handlers
or when irqs are already masked.

Many NIC drivers can use it from their hard IRQ handler instead of
generic variant.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 13 +++++++++++++
 net/core/dev.c            | 15 ++++++++++++++-
 2 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 74fd5d37f15..c85e0651224 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -386,6 +386,7 @@ typedef enum rx_handler_result rx_handler_result_t;
 typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb);
 
 void __napi_schedule(struct napi_struct *n);
+void __napi_schedule_irqoff(struct napi_struct *n);
 
 static inline bool napi_disable_pending(struct napi_struct *n)
 {
@@ -420,6 +421,18 @@ static inline void napi_schedule(struct napi_struct *n)
 		__napi_schedule(n);
 }
 
+/**
+ *	napi_schedule_irqoff - schedule NAPI poll
+ *	@n: napi context
+ *
+ * Variant of napi_schedule(), assuming hard irqs are masked.
+ */
+static inline void napi_schedule_irqoff(struct napi_struct *n)
+{
+	if (napi_schedule_prep(n))
+		__napi_schedule_irqoff(n);
+}
+
 /* Try to reschedule poll. Called by dev->poll() after napi_complete().  */
 static inline bool napi_reschedule(struct napi_struct *napi)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index b793e3521a3..759940cdf89 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4372,7 +4372,8 @@ static int process_backlog(struct napi_struct *napi, int quota)
  * __napi_schedule - schedule for receive
  * @n: entry to schedule
  *
- * The entry's receive function will be scheduled to run
+ * The entry's receive function will be scheduled to run.
+ * Consider using __napi_schedule_irqoff() if hard irqs are masked.
  */
 void __napi_schedule(struct napi_struct *n)
 {
@@ -4384,6 +4385,18 @@ void __napi_schedule(struct napi_struct *n)
 }
 EXPORT_SYMBOL(__napi_schedule);
 
+/**
+ * __napi_schedule_irqoff - schedule for receive
+ * @n: entry to schedule
+ *
+ * Variant of __napi_schedule() assuming hard irqs are masked
+ */
+void __napi_schedule_irqoff(struct napi_struct *n)
+{
+	____napi_schedule(this_cpu_ptr(&softnet_data), n);
+}
+EXPORT_SYMBOL(__napi_schedule_irqoff);
+
 void __napi_complete(struct napi_struct *n)
 {
 	BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
-- 
cgit v1.2.3-70-g09d2


From 75fbfd33234a71556bec34b099d98f970190905d Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 29 Oct 2014 19:29:31 +0100
Subject: neigh: optimize neigh_parms_release()

In neigh_parms_release() we loop over all entries to find the entry given in
argument and being able to remove it from the list. By using a double linked
list, we can avoid this loop.

Here are some numbers with 30 000 dummy interfaces configured:

Before the patch:
$ time rmmod dummy
real	2m0.118s
user	0m0.000s
sys	1m50.048s

After the patch:
$ time rmmod dummy
real	1m9.970s
user	0m0.000s
sys	0m47.976s

Suggested-by: Thierry Herbelot <thierry.herbelot@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h |  3 ++-
 net/core/neighbour.c    | 32 +++++++++++++-------------------
 2 files changed, 15 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index f60558d0254..dedfb188b1a 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -69,7 +69,7 @@ struct neigh_parms {
 	struct net *net;
 #endif
 	struct net_device *dev;
-	struct neigh_parms *next;
+	struct list_head list;
 	int	(*neigh_setup)(struct neighbour *);
 	void	(*neigh_cleanup)(struct neighbour *);
 	struct neigh_table *tbl;
@@ -203,6 +203,7 @@ struct neigh_table {
 	void			(*proxy_redo)(struct sk_buff *skb);
 	char			*id;
 	struct neigh_parms	parms;
+	struct list_head	parms_list;
 	int			gc_interval;
 	int			gc_thresh1;
 	int			gc_thresh2;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index ef31fef25e5..edd04116ecb 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -773,7 +773,7 @@ static void neigh_periodic_work(struct work_struct *work)
 	if (time_after(jiffies, tbl->last_rand + 300 * HZ)) {
 		struct neigh_parms *p;
 		tbl->last_rand = jiffies;
-		for (p = &tbl->parms; p; p = p->next)
+		list_for_each_entry(p, &tbl->parms_list, list)
 			p->reachable_time =
 				neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
 	}
@@ -1446,7 +1446,7 @@ static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl,
 {
 	struct neigh_parms *p;
 
-	for (p = &tbl->parms; p; p = p->next) {
+	list_for_each_entry(p, &tbl->parms_list, list) {
 		if ((p->dev && p->dev->ifindex == ifindex && net_eq(neigh_parms_net(p), net)) ||
 		    (!p->dev && !ifindex && net_eq(net, &init_net)))
 			return p;
@@ -1481,8 +1481,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
 		}
 
 		write_lock_bh(&tbl->lock);
-		p->next		= tbl->parms.next;
-		tbl->parms.next = p;
+		list_add(&p->list, &tbl->parms.list);
 		write_unlock_bh(&tbl->lock);
 
 		neigh_parms_data_state_cleanall(p);
@@ -1501,24 +1500,15 @@ static void neigh_rcu_free_parms(struct rcu_head *head)
 
 void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms)
 {
-	struct neigh_parms **p;
-
 	if (!parms || parms == &tbl->parms)
 		return;
 	write_lock_bh(&tbl->lock);
-	for (p = &tbl->parms.next; *p; p = &(*p)->next) {
-		if (*p == parms) {
-			*p = parms->next;
-			parms->dead = 1;
-			write_unlock_bh(&tbl->lock);
-			if (parms->dev)
-				dev_put(parms->dev);
-			call_rcu(&parms->rcu_head, neigh_rcu_free_parms);
-			return;
-		}
-	}
+	list_del(&parms->list);
+	parms->dead = 1;
 	write_unlock_bh(&tbl->lock);
-	neigh_dbg(1, "%s: not found\n", __func__);
+	if (parms->dev)
+		dev_put(parms->dev);
+	call_rcu(&parms->rcu_head, neigh_rcu_free_parms);
 }
 EXPORT_SYMBOL(neigh_parms_release);
 
@@ -1535,6 +1525,8 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl)
 	unsigned long now = jiffies;
 	unsigned long phsize;
 
+	INIT_LIST_HEAD(&tbl->parms_list);
+	list_add(&tbl->parms.list, &tbl->parms_list);
 	write_pnet(&tbl->parms.net, &init_net);
 	atomic_set(&tbl->parms.refcnt, 1);
 	tbl->parms.reachable_time =
@@ -2154,7 +2146,9 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 				       NLM_F_MULTI) <= 0)
 			break;
 
-		for (nidx = 0, p = tbl->parms.next; p; p = p->next) {
+		nidx = 0;
+		p = list_next_entry(&tbl->parms, list);
+		list_for_each_entry_from(p, &tbl->parms_list, list) {
 			if (!net_eq(neigh_parms_net(p), net))
 				continue;
 
-- 
cgit v1.2.3-70-g09d2


From 90a6161df57e7943cdd575ce95c1c62b468407e3 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 29 Oct 2014 21:34:29 +0100
Subject: mac802154: remove tab after define

This patch removes tabs after define in hardware flags declarations.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/mac802154.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 85a4efca418..fe1495796ce 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -74,22 +74,22 @@ struct ieee802154_hw {
  */
 
 /* Indicates that receiver omits FCS and xmitter will add FCS on it's own. */
-#define	IEEE802154_HW_OMIT_CKSUM	0x00000001
+#define IEEE802154_HW_OMIT_CKSUM	0x00000001
 /* Indicates that receiver will autorespond with ACK frames. */
-#define	IEEE802154_HW_AACK		0x00000002
+#define IEEE802154_HW_AACK		0x00000002
 /* Indicates that transceiver will support transmit power setting. */
-#define	IEEE802154_HW_TXPOWER		0x00000004
+#define IEEE802154_HW_TXPOWER		0x00000004
 /* Indicates that transceiver will support listen before transmit. */
-#define	IEEE802154_HW_LBT		0x00000008
+#define IEEE802154_HW_LBT		0x00000008
 /* Indicates that transceiver will support cca mode setting. */
-#define	IEEE802154_HW_CCA_MODE		0x00000010
+#define IEEE802154_HW_CCA_MODE		0x00000010
 /* Indicates that transceiver will support cca ed level setting. */
-#define	IEEE802154_HW_CCA_ED_LEVEL	0x00000020
+#define IEEE802154_HW_CCA_ED_LEVEL	0x00000020
 /* Indicates that transceiver will support csma (max_be, min_be, csma retries)
  * settings. */
-#define	IEEE802154_HW_CSMA_PARAMS	0x00000040
+#define IEEE802154_HW_CSMA_PARAMS	0x00000040
 /* Indicates that transceiver will support ARET frame retries setting. */
-#define	IEEE802154_HW_FRAME_RETRIES	0x00000080
+#define IEEE802154_HW_FRAME_RETRIES	0x00000080
 
 /* This groups the most common CSMA support fields into one. */
 #define IEEE802154_HW_CSMA		(IEEE802154_HW_CCA_MODE | \
-- 
cgit v1.2.3-70-g09d2


From ab79be3eebf28be5315e43d0002ebcc05858af0b Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 29 Oct 2014 21:34:30 +0100
Subject: mac802154: add IEEE802154_HW_ARET hw flag

This patch adds a new IEEE802154_HW_ARET hardware flag for indicating
that the transceiver supports ARET handling. Also remove the
IEEE802154_HW_FRAME_RETRIES from IEEE802154_HW_CSMA flag. Frame retries
handling is part of ARET.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/net/ieee802154/at86rf230.c | 2 +-
 include/net/mac802154.h            | 5 ++++-
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index b83ad0b3868..005458821c5 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -1387,7 +1387,7 @@ at86rf230_detect_device(struct at86rf230_local *lp)
 
 	lp->hw->extra_tx_headroom = 0;
 	lp->hw->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK |
-			 IEEE802154_HW_TXPOWER | IEEE802154_HW_CSMA;
+			IEEE802154_HW_TXPOWER | IEEE802154_HW_ARET;
 
 	switch (part) {
 	case 2:
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index fe1495796ce..c5d79384847 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -94,7 +94,10 @@ struct ieee802154_hw {
 /* This groups the most common CSMA support fields into one. */
 #define IEEE802154_HW_CSMA		(IEEE802154_HW_CCA_MODE | \
 					 IEEE802154_HW_CCA_ED_LEVEL | \
-					 IEEE802154_HW_CSMA_PARAMS | \
+					 IEEE802154_HW_CSMA_PARAMS)
+
+/* This groups the most common ARET support fields into one. */
+#define IEEE802154_HW_ARET		(IEEE802154_HW_CSMA | \
 					 IEEE802154_HW_FRAME_RETRIES)
 
 /* struct ieee802154_ops - callbacks from mac802154 to the driver
-- 
cgit v1.2.3-70-g09d2


From c8fc84ed60f0ec85ab71f6026add1523523e4bd5 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 29 Oct 2014 21:34:31 +0100
Subject: mac802154: add hardware address filter flag

Overdue introduction for address filtering hardware flag. Furthermore we
will check and set address filtering on interface up. This patch
prepares that we can check if an transceiver supports address filtering
option. Currently all mainline driver supports hardware address filtering.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Cc: Alan Ott <alan@signal11.us>
Cc: Varka Bhadram <varkabhadram@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/net/ieee802154/at86rf230.c | 3 ++-
 drivers/net/ieee802154/cc2520.c    | 3 ++-
 drivers/net/ieee802154/mrf24j40.c  | 3 ++-
 include/net/mac802154.h            | 2 ++
 4 files changed, 8 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 005458821c5..622c1b6f7fe 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -1387,7 +1387,8 @@ at86rf230_detect_device(struct at86rf230_local *lp)
 
 	lp->hw->extra_tx_headroom = 0;
 	lp->hw->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK |
-			IEEE802154_HW_TXPOWER | IEEE802154_HW_ARET;
+			IEEE802154_HW_TXPOWER | IEEE802154_HW_ARET |
+			IEEE802154_HW_AFILT;
 
 	switch (part) {
 	case 2:
diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c
index c56d10c7ccf..340671b747b 100644
--- a/drivers/net/ieee802154/cc2520.c
+++ b/drivers/net/ieee802154/cc2520.c
@@ -654,7 +654,8 @@ static int cc2520_register(struct cc2520_private *priv)
 
 	/* We do support only 2.4 Ghz */
 	priv->hw->phy->channels_supported[0] = 0x7FFF800;
-	priv->hw->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK;
+	priv->hw->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK |
+			  IEEE802154_HW_AFILT;
 
 	dev_vdbg(&priv->spi->dev, "registered cc2520\n");
 	ret = ieee802154_register_hw(priv->hw);
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index 52b3d311675..a200fa16bea 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -751,7 +751,8 @@ static int mrf24j40_probe(struct spi_device *spi)
 	devrec->hw->priv = devrec;
 	devrec->hw->parent = &devrec->spi->dev;
 	devrec->hw->phy->channels_supported[0] = CHANNEL_MASK;
-	devrec->hw->flags = IEEE802154_HW_OMIT_CKSUM|IEEE802154_HW_AACK;
+	devrec->hw->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK |
+			    IEEE802154_HW_AFILT;
 
 	dev_dbg(printdev(devrec), "registered mrf24j40\n");
 	ret = ieee802154_register_hw(devrec->hw);
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index c5d79384847..2f523fc1bf8 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -90,6 +90,8 @@ struct ieee802154_hw {
 #define IEEE802154_HW_CSMA_PARAMS	0x00000040
 /* Indicates that transceiver will support ARET frame retries setting. */
 #define IEEE802154_HW_FRAME_RETRIES	0x00000080
+/* Indicates that transceiver will support hardware address filter setting. */
+#define IEEE802154_HW_AFILT		0x00000100
 
 /* This groups the most common CSMA support fields into one. */
 #define IEEE802154_HW_CSMA		(IEEE802154_HW_CCA_MODE | \
-- 
cgit v1.2.3-70-g09d2


From 94b792220ca9c080f4d1da8060f4c892c1b3b025 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 29 Oct 2014 21:34:32 +0100
Subject: mac802154: add support for promiscuous mode

This patch adds a new driver operation to bring the transceiver into
promiscuous mode.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/mac802154.h    |  7 +++++++
 net/mac802154/driver-ops.h | 13 +++++++++++++
 2 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 2f523fc1bf8..166ef6c5218 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -92,6 +92,8 @@ struct ieee802154_hw {
 #define IEEE802154_HW_FRAME_RETRIES	0x00000080
 /* Indicates that transceiver will support hardware address filter setting. */
 #define IEEE802154_HW_AFILT		0x00000100
+/* Indicates that transceiver will support promiscuous mode setting. */
+#define IEEE802154_HW_PROMISCUOUS	0x00000200
 
 /* This groups the most common CSMA support fields into one. */
 #define IEEE802154_HW_CSMA		(IEEE802154_HW_CCA_MODE | \
@@ -173,6 +175,9 @@ struct ieee802154_hw {
  * set_frame_retries
  *	  Sets the retransmission attempt limit. Called with pib_lock held.
  *	  Returns either zero, or negative errno.
+ *
+ * set_promiscuous_mode
+ *	  Enables or disable promiscuous mode.
  */
 struct ieee802154_ops {
 	struct module	*owner;
@@ -197,6 +202,8 @@ struct ieee802154_ops {
 					   u8 min_be, u8 max_be, u8 retries);
 	int		(*set_frame_retries)(struct ieee802154_hw *hw,
 					     s8 retries);
+	int             (*set_promiscuous_mode)(struct ieee802154_hw *hw,
+						const bool on);
 };
 
 /* Basic interface to register ieee802154 hwice */
diff --git a/net/mac802154/driver-ops.h b/net/mac802154/driver-ops.h
index 4b820cfeb53..dfd29ffb8fe 100644
--- a/net/mac802154/driver-ops.h
+++ b/net/mac802154/driver-ops.h
@@ -210,4 +210,17 @@ static inline int drv_set_max_frame_retries(struct ieee802154_local *local,
 	return local->ops->set_frame_retries(&local->hw, max_frame_retries);
 }
 
+static inline int drv_set_promiscuous_mode(struct ieee802154_local *local,
+					   const bool on)
+{
+	might_sleep();
+
+	if (!local->ops->set_promiscuous_mode) {
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+
+	return local->ops->set_promiscuous_mode(&local->hw, on);
+}
+
 #endif /* __MAC802154_DRVIER_OPS */
-- 
cgit v1.2.3-70-g09d2


From 90386a7e3bcce60b6b83d0d1bd65d7b55a77fa60 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 29 Oct 2014 21:34:34 +0100
Subject: mac802154: separate omit tx/rx flags

This patch splits the IEEE802154_HW_OMIT_CKSUM hardware flag into
IEEE802154_HW_TX_OMIT_CKSUM and IEEE802154_HW_RX_OMIT_CKSUM. This is
useful to deliver the received crc from the driver layer to the monitor
interface. At the moment we can't do that without change the xmit
handling.

The received checksum should be visible in monitor mode only.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/mac802154.h | 10 ++++++++--
 net/mac802154/rx.c      |  2 +-
 net/mac802154/tx.c      |  2 +-
 3 files changed, 10 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 166ef6c5218..bc1d40c826e 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -73,8 +73,8 @@ struct ieee802154_hw {
  * however, so you are advised to review these flags carefully.
  */
 
-/* Indicates that receiver omits FCS and xmitter will add FCS on it's own. */
-#define IEEE802154_HW_OMIT_CKSUM	0x00000001
+/* Indicates that xmitter will add FCS on it's own. */
+#define IEEE802154_HW_TX_OMIT_CKSUM	0x00000001
 /* Indicates that receiver will autorespond with ACK frames. */
 #define IEEE802154_HW_AACK		0x00000002
 /* Indicates that transceiver will support transmit power setting. */
@@ -94,6 +94,12 @@ struct ieee802154_hw {
 #define IEEE802154_HW_AFILT		0x00000100
 /* Indicates that transceiver will support promiscuous mode setting. */
 #define IEEE802154_HW_PROMISCUOUS	0x00000200
+/* Indicates that receiver omits FCS. */
+#define IEEE802154_HW_RX_OMIT_CKSUM	0x00000400
+
+/* Indicates that receiver omits FCS and xmitter will add FCS on it's own. */
+#define IEEE802154_HW_OMIT_CKSUM	(IEEE802154_HW_TX_OMIT_CKSUM | \
+					 IEEE802154_HW_RX_OMIT_CKSUM)
 
 /* This groups the most common CSMA support fields into one. */
 #define IEEE802154_HW_CSMA		(IEEE802154_HW_CCA_MODE | \
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index 86394befbf8..2aa80bdcbac 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -255,7 +255,7 @@ void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb)
 
 	WARN_ON_ONCE(softirq_count() == 0);
 
-	if (!(local->hw.flags & IEEE802154_HW_OMIT_CKSUM)) {
+	if (!(local->hw.flags & IEEE802154_HW_RX_OMIT_CKSUM)) {
 		u16 crc;
 
 		if (skb->len < 2) {
diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c
index 77973a84e9a..cc37b77f263 100644
--- a/net/mac802154/tx.c
+++ b/net/mac802154/tx.c
@@ -83,7 +83,7 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb)
 	struct net_device *dev = skb->dev;
 	int ret;
 
-	if (!(local->hw.flags & IEEE802154_HW_OMIT_CKSUM)) {
+	if (!(local->hw.flags & IEEE802154_HW_TX_OMIT_CKSUM)) {
 		u16 crc = crc_ccitt(0, skb->data, skb->len);
 
 		put_unaligned_le16(crc, skb_put(skb, 2));
-- 
cgit v1.2.3-70-g09d2


From ec718f3db9b7968ca5dfb10c85c56ff27149df94 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 29 Oct 2014 21:34:37 +0100
Subject: mac802154: rx: add software checksum filtering check

This patch adds a new hardware flag which indicate that the transceiver
doesn't support check for bad checksum via hardware. Also add a handling of
this while receive.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/mac802154.h |  2 ++
 net/mac802154/rx.c      | 15 +++++++++++++--
 2 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index bc1d40c826e..8f1de6844cb 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -96,6 +96,8 @@ struct ieee802154_hw {
 #define IEEE802154_HW_PROMISCUOUS	0x00000200
 /* Indicates that receiver omits FCS. */
 #define IEEE802154_HW_RX_OMIT_CKSUM	0x00000400
+/* Indicates that receiver will not filter frames with bad checksum. */
+#define IEEE802154_HW_RX_DROP_BAD_CKSUM	0x00000800
 
 /* Indicates that receiver omits FCS and xmitter will add FCS on it's own. */
 #define IEEE802154_HW_OMIT_CKSUM	(IEEE802154_HW_TX_OMIT_CKSUM | \
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index b6a4bbfdbf9..c9f1c72a1af 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -248,6 +248,7 @@ ieee802154_monitors_rx(struct ieee802154_local *local, struct sk_buff *skb)
 void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb)
 {
 	struct ieee802154_local *local = hw_to_local(hw);
+	u16 crc;
 
 	WARN_ON_ONCE(softirq_count() == 0);
 
@@ -256,8 +257,7 @@ void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb)
 	 * solution because the monitor needs a crc here.
 	 */
 	if (local->hw.flags & IEEE802154_HW_RX_OMIT_CKSUM) {
-		u16 crc = crc_ccitt(0, skb->data, skb->len);
-
+		crc = crc_ccitt(0, skb->data, skb->len);
 		put_unaligned_le16(crc, skb_put(skb, 2));
 	}
 
@@ -265,6 +265,17 @@ void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb)
 
 	ieee802154_monitors_rx(local, skb);
 
+	/* Check if transceiver doesn't validate the checksum.
+	 * If not we validate the checksum here.
+	 */
+	if (local->hw.flags & IEEE802154_HW_RX_DROP_BAD_CKSUM) {
+		crc = crc_ccitt(0, skb->data, skb->len);
+		if (crc) {
+			rcu_read_unlock();
+			kfree_skb(skb);
+			return;
+		}
+	}
 	/* remove crc */
 	skb_trim(skb, skb->len - 2);
 
-- 
cgit v1.2.3-70-g09d2


From 1f33c41c03daece85a84b8dcea5733f3efe3e2b0 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 29 Sep 2014 16:08:21 -0700
Subject: seq_file: Rename seq_overflow() to seq_has_overflowed() and make
 public

The return values of seq_printf/puts/putc are frequently misused.

Start down a path to remove all the return value uses of these
functions.

Move the seq_overflow() to a global inlined function called
seq_has_overflowed() that can be used by the users of seq_file() calls.

Update the documentation to not show return types for seq_printf
et al.  Add a description of seq_has_overflowed().

Link: http://lkml.kernel.org/p/848ac7e3d1c31cddf638a8526fa3c59fa6fdeb8a.1412031505.git.joe@perches.com

Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Joe Perches <joe@perches.com>
[ Reworked the original patch from Joe ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 Documentation/filesystems/seq_file.txt | 22 +++++++++++++---------
 fs/seq_file.c                          | 15 ++-------------
 include/linux/seq_file.h               | 15 +++++++++++++++
 3 files changed, 30 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/seq_file.txt b/Documentation/filesystems/seq_file.txt
index 8ea3e90ace0..b797ed38de4 100644
--- a/Documentation/filesystems/seq_file.txt
+++ b/Documentation/filesystems/seq_file.txt
@@ -180,23 +180,19 @@ output must be passed to the seq_file code. Some utility functions have
 been defined which make this task easy.
 
 Most code will simply use seq_printf(), which works pretty much like
-printk(), but which requires the seq_file pointer as an argument. It is
-common to ignore the return value from seq_printf(), but a function
-producing complicated output may want to check that value and quit if
-something non-zero is returned; an error return means that the seq_file
-buffer has been filled and further output will be discarded.
+printk(), but which requires the seq_file pointer as an argument.
 
 For straight character output, the following functions may be used:
 
-	int seq_putc(struct seq_file *m, char c);
-	int seq_puts(struct seq_file *m, const char *s);
-	int seq_escape(struct seq_file *m, const char *s, const char *esc);
+	seq_putc(struct seq_file *m, char c);
+	seq_puts(struct seq_file *m, const char *s);
+	seq_escape(struct seq_file *m, const char *s, const char *esc);
 
 The first two output a single character and a string, just like one would
 expect. seq_escape() is like seq_puts(), except that any character in s
 which is in the string esc will be represented in octal form in the output.
 
-There is also a pair of functions for printing filenames:
+There are also a pair of functions for printing filenames:
 
 	int seq_path(struct seq_file *m, struct path *path, char *esc);
 	int seq_path_root(struct seq_file *m, struct path *path,
@@ -209,6 +205,14 @@ root is desired, it can be used with seq_path_root().  Note that, if it
 turns out that path cannot be reached from root, the value of root will be
 changed in seq_file_root() to a root which *does* work.
 
+A function producing complicated output may want to check
+	bool seq_has_overflowed(struct seq_file *m);
+and avoid further seq_<output> calls if true is returned.
+
+A true return from seq_has_overflowed means that the seq_file buffer will
+be discarded and the seq_show function will attempt to allocate a larger
+buffer and retry printing.
+
 
 Making it all work
 
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 3857b720cb1..353948ba1c5 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -16,17 +16,6 @@
 #include <asm/uaccess.h>
 #include <asm/page.h>
 
-
-/*
- * seq_files have a buffer which can may overflow. When this happens a larger
- * buffer is reallocated and all the data will be printed again.
- * The overflow state is true when m->count == m->size.
- */
-static bool seq_overflow(struct seq_file *m)
-{
-	return m->count == m->size;
-}
-
 static void seq_set_overflow(struct seq_file *m)
 {
 	m->count = m->size;
@@ -124,7 +113,7 @@ static int traverse(struct seq_file *m, loff_t offset)
 			error = 0;
 			m->count = 0;
 		}
-		if (seq_overflow(m))
+		if (seq_has_overflowed(m))
 			goto Eoverflow;
 		if (pos + m->count > offset) {
 			m->from = offset - pos;
@@ -267,7 +256,7 @@ Fill:
 			break;
 		}
 		err = m->op->show(m, p);
-		if (seq_overflow(m) || err) {
+		if (seq_has_overflowed(m) || err) {
 			m->count = offs;
 			if (likely(err <= 0))
 				break;
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 52e0097f61f..cf6a9daaaf6 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -42,6 +42,21 @@ struct seq_operations {
 
 #define SEQ_SKIP 1
 
+/**
+ * seq_has_overflowed - check if the buffer has overflowed
+ * @m: the seq_file handle
+ *
+ * seq_files have a buffer which may overflow. When this happens a larger
+ * buffer is reallocated and all the data will be printed again.
+ * The overflow state is true when m->count == m->size.
+ *
+ * Returns true if the buffer received more than it can hold.
+ */
+static inline bool seq_has_overflowed(struct seq_file *m)
+{
+	return m->count == m->size;
+}
+
 /**
  * seq_get_buf - get buffer to write arbitrary data to
  * @m: the seq_file handle
-- 
cgit v1.2.3-70-g09d2


From 3ab84ee95ba4e28b30fd8ec7c38f5e9f72c4b4b7 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 12 Sep 2014 15:15:20 +0200
Subject: ARM: shmobile: r8a7740 dtsi: Add missing INTCA clock for irqpin
 module

This clock drives the INTCA irqpin controller modules.
Before, it was assumed enabled by the bootloader or reset state.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: devicetree@vger.kernel.org
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 arch/arm/boot/dts/r8a7740.dtsi            | 14 ++++++++++----
 include/dt-bindings/clock/r8a7740-clock.h |  1 +
 2 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/arm/boot/dts/r8a7740.dtsi b/arch/arm/boot/dts/r8a7740.dtsi
index d46c213a17a..502483f4dcc 100644
--- a/arch/arm/boot/dts/r8a7740.dtsi
+++ b/arch/arm/boot/dts/r8a7740.dtsi
@@ -71,6 +71,7 @@
 			      0 149 IRQ_TYPE_LEVEL_HIGH
 			      0 149 IRQ_TYPE_LEVEL_HIGH
 			      0 149 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp2_clks R8A7740_CLK_INTCA>;
 	};
 
 	/* irqpin1: IRQ8 - IRQ15 */
@@ -91,6 +92,7 @@
 			      0 149 IRQ_TYPE_LEVEL_HIGH
 			      0 149 IRQ_TYPE_LEVEL_HIGH
 			      0 149 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp2_clks R8A7740_CLK_INTCA>;
 	};
 
 	/* irqpin2: IRQ16 - IRQ23 */
@@ -111,6 +113,7 @@
 			      0 149 IRQ_TYPE_LEVEL_HIGH
 			      0 149 IRQ_TYPE_LEVEL_HIGH
 			      0 149 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp2_clks R8A7740_CLK_INTCA>;
 	};
 
 	/* irqpin3: IRQ24 - IRQ31 */
@@ -131,6 +134,7 @@
 			      0 149 IRQ_TYPE_LEVEL_HIGH
 			      0 149 IRQ_TYPE_LEVEL_HIGH
 			      0 149 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp2_clks R8A7740_CLK_INTCA>;
 	};
 
 	ether: ethernet@e9a00000 {
@@ -448,8 +452,8 @@
 		mstp2_clks: mstp2_clks@e6150138 {
 			compatible = "renesas,r8a7740-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0xe6150138 4>, <0xe6150040 4>;
-			clocks = <&sub_clk>, <&sub_clk>,
-				 <&cpg_clocks R8A7740_CLK_HP>,
+			clocks = <&sub_clk>, <&cpg_clocks R8A7740_CLK_HP>,
+				 <&sub_clk>, <&cpg_clocks R8A7740_CLK_HP>,
 				 <&cpg_clocks R8A7740_CLK_HP>,
 				 <&cpg_clocks R8A7740_CLK_HP>,
 				 <&cpg_clocks R8A7740_CLK_HP>,
@@ -458,7 +462,8 @@
 				 <&sub_clk>;
 			#clock-cells = <1>;
 			renesas,clock-indices = <
-				R8A7740_CLK_SCIFA6 R8A7740_CLK_SCIFA7
+				R8A7740_CLK_SCIFA6 R8A7740_CLK_INTCA
+				R8A7740_CLK_SCIFA7
 				R8A7740_CLK_DMAC1 R8A7740_CLK_DMAC2
 				R8A7740_CLK_DMAC3 R8A7740_CLK_USBDMAC
 				R8A7740_CLK_SCIFA5 R8A7740_CLK_SCIFB
@@ -467,7 +472,8 @@
 				R8A7740_CLK_SCIFA4
 			>;
 			clock-output-names =
-				"scifa6", "scifa7", "dmac1", "dmac2", "dmac3",
+				"scifa6", "intca",
+				"scifa7", "dmac1", "dmac2", "dmac3",
 				"usbdmac", "scifa5", "scifb", "scifa0", "scifa1",
 				"scifa2", "scifa3", "scifa4";
 		};
diff --git a/include/dt-bindings/clock/r8a7740-clock.h b/include/dt-bindings/clock/r8a7740-clock.h
index f6b4b0fe7a4..476135da0f2 100644
--- a/include/dt-bindings/clock/r8a7740-clock.h
+++ b/include/dt-bindings/clock/r8a7740-clock.h
@@ -40,6 +40,7 @@
 
 /* MSTP2 */
 #define R8A7740_CLK_SCIFA6	30
+#define R8A7740_CLK_INTCA	29
 #define R8A7740_CLK_SCIFA7	22
 #define R8A7740_CLK_DMAC1	18
 #define R8A7740_CLK_DMAC2	17
-- 
cgit v1.2.3-70-g09d2


From 2284ff5f3f7d58e33812f4387c2ac8a09428e4cf Mon Sep 17 00:00:00 2001
From: Kouei Abe <kouei.abe.cp@renesas.com>
Date: Tue, 14 Oct 2014 16:01:40 +0900
Subject: ARM: shmobile: r8a7790: Add RGX clock to device tree

Signed-off-by: Kouei Abe <kouei.abe.cp@renesas.com>
Signed-off-by: Yoshihiro Kaneko <ykaneko0929@gmail.com>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 arch/arm/boot/dts/r8a7790.dtsi            | 9 +++++----
 include/dt-bindings/clock/r8a7790-clock.h | 1 +
 2 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index 7b42b256fe5..602a46ab985 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -977,18 +977,19 @@
 		mstp1_clks: mstp1_clks@e6150134 {
 			compatible = "renesas,r8a7790-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150134 0 4>, <0 0xe6150038 0 4>;
-			clocks = <&m2_clk>, <&p_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
+			clocks = <&m2_clk>, <&p_clk>, <&zg_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
 				 <&cp_clk>, <&zs_clk>, <&zs_clk>, <&zs_clk>,
 				 <&zs_clk>;
 			#clock-cells = <1>;
 			renesas,clock-indices = <
-				R8A7790_CLK_JPU R8A7790_CLK_TMU1 R8A7790_CLK_TMU3 R8A7790_CLK_TMU2
+				R8A7790_CLK_JPU R8A7790_CLK_TMU1 R8A7790_CLK_3DG
+				R8A7790_CLK_TMU3 R8A7790_CLK_TMU2
 				R8A7790_CLK_CMT0 R8A7790_CLK_TMU0 R8A7790_CLK_VSP1_DU1
 				R8A7790_CLK_VSP1_DU0 R8A7790_CLK_VSP1_R R8A7790_CLK_VSP1_S
 			>;
 			clock-output-names =
-				"jpu", "tmu1", "tmu3", "tmu2", "cmt0", "tmu0", "vsp1-du1",
-				"vsp1-du0", "vsp1-rt", "vsp1-sy";
+				"jpu", "tmu1", "3dg", "tmu3", "tmu2", "cmt0", "tmu0",
+				"vsp1-du1", "vsp1-du0", "vsp1-rt", "vsp1-sy";
 		};
 		mstp2_clks: mstp2_clks@e6150138 {
 			compatible = "renesas,r8a7790-mstp-clocks", "renesas,cpg-mstp-clocks";
diff --git a/include/dt-bindings/clock/r8a7790-clock.h b/include/dt-bindings/clock/r8a7790-clock.h
index 8ea7ab0346a..14a3f12d13c 100644
--- a/include/dt-bindings/clock/r8a7790-clock.h
+++ b/include/dt-bindings/clock/r8a7790-clock.h
@@ -28,6 +28,7 @@
 /* MSTP1 */
 #define R8A7790_CLK_JPU		6
 #define R8A7790_CLK_TMU1		11
+#define R8A7790_CLK_3DG			12
 #define R8A7790_CLK_TMU3		21
 #define R8A7790_CLK_TMU2		22
 #define R8A7790_CLK_CMT0		24
-- 
cgit v1.2.3-70-g09d2


From e4d2fd9eb43d12e9b6a7ab842bf6986b4dd75a1d Mon Sep 17 00:00:00 2001
From: Kouei Abe <kouei.abe.cp@renesas.com>
Date: Tue, 14 Oct 2014 16:01:41 +0900
Subject: ARM: shmobile: r8a7791: Add SGX clock to device tree

Signed-off-by: Kouei Abe <kouei.abe.cp@renesas.com>
Signed-off-by: Yoshihiro Kaneko <ykaneko0929@gmail.com>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 arch/arm/boot/dts/r8a7791.dtsi            | 11 ++++++-----
 include/dt-bindings/clock/r8a7791-clock.h |  1 +
 2 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index 1c58ce0a488..98c1b8bef61 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -1,7 +1,7 @@
 /*
  * Device Tree Source for the r8a7791 SoC
  *
- * Copyright (C) 2013 Renesas Electronics Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  * Copyright (C) 2013-2014 Renesas Solutions Corp.
  * Copyright (C) 2014 Cogent Embedded Inc.
  *
@@ -977,17 +977,18 @@
 		mstp1_clks: mstp1_clks@e6150134 {
 			compatible = "renesas,r8a7791-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150134 0 4>, <0 0xe6150038 0 4>;
-			clocks = <&m2_clk>, <&p_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
+			clocks = <&m2_clk>, <&p_clk>, <&zg_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
 				 <&cp_clk>, <&zs_clk>, <&zs_clk>, <&zs_clk>;
 			#clock-cells = <1>;
 			renesas,clock-indices = <
-				R8A7791_CLK_JPU R8A7791_CLK_TMU1 R8A7791_CLK_TMU3 R8A7791_CLK_TMU2
+				R8A7791_CLK_JPU R8A7791_CLK_TMU1 R8A7791_CLK_3DG
+				R8A7791_CLK_TMU3 R8A7791_CLK_TMU2
 				R8A7791_CLK_CMT0 R8A7791_CLK_TMU0 R8A7791_CLK_VSP1_DU1
 				R8A7791_CLK_VSP1_DU0 R8A7791_CLK_VSP1_S
 			>;
 			clock-output-names =
-				"jpu", "tmu1", "tmu3", "tmu2", "cmt0", "tmu0", "vsp1-du1",
-				"vsp1-du0", "vsp1-sy";
+				"jpu", "tmu1", "3dg", "tmu3", "tmu2", "cmt0", "tmu0",
+				"vsp1-du1", "vsp1-du0", "vsp1-sy";
 		};
 		mstp2_clks: mstp2_clks@e6150138 {
 			compatible = "renesas,r8a7791-mstp-clocks", "renesas,cpg-mstp-clocks";
diff --git a/include/dt-bindings/clock/r8a7791-clock.h b/include/dt-bindings/clock/r8a7791-clock.h
index 58c3f49d068..9570b7c2eed 100644
--- a/include/dt-bindings/clock/r8a7791-clock.h
+++ b/include/dt-bindings/clock/r8a7791-clock.h
@@ -27,6 +27,7 @@
 /* MSTP1 */
 #define R8A7791_CLK_JPU		6
 #define R8A7791_CLK_TMU1		11
+#define R8A7791_CLK_3DG			12
 #define R8A7791_CLK_TMU3		21
 #define R8A7791_CLK_TMU2		22
 #define R8A7791_CLK_CMT0		24
-- 
cgit v1.2.3-70-g09d2


From 4ba8f2468ce346642b4ace3cdf4bdd8d29175011 Mon Sep 17 00:00:00 2001
From: Yoshifumi Hosoya <yoshifumi.hosoya.wj@renesas.com>
Date: Tue, 14 Oct 2014 16:01:42 +0900
Subject: ARM: shmobile: r8a7790: Add MMP clock to device tree

Signed-off-by: Yoshifumi Hosoya <yoshifumi.hosoya.wj@renesas.com>
Signed-off-by: Yoshihiro Kaneko <ykaneko0929@gmail.com>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 arch/arm/boot/dts/r8a7790.dtsi            | 22 ++++++++++++++--------
 include/dt-bindings/clock/r8a7790-clock.h | 11 ++++++++++-
 2 files changed, 24 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index 602a46ab985..050e60890d7 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -977,18 +977,24 @@
 		mstp1_clks: mstp1_clks@e6150134 {
 			compatible = "renesas,r8a7790-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150134 0 4>, <0 0xe6150038 0 4>;
-			clocks = <&m2_clk>, <&p_clk>, <&zg_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
-				 <&cp_clk>, <&zs_clk>, <&zs_clk>, <&zs_clk>,
-				 <&zs_clk>;
+			clocks = <&zs_clk>, <&zs_clk>, <&zs_clk>, <&zs_clk>, <&m2_clk>,
+				 <&zs_clk>, <&p_clk>, <&zg_clk>, <&zs_clk>, <&zs_clk>,
+				 <&zs_clk>, <&zs_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
+				 <&cp_clk>, <&zs_clk>, <&zs_clk>, <&zs_clk>, <&zs_clk>;
 			#clock-cells = <1>;
 			renesas,clock-indices = <
-				R8A7790_CLK_JPU R8A7790_CLK_TMU1 R8A7790_CLK_3DG
-				R8A7790_CLK_TMU3 R8A7790_CLK_TMU2
-				R8A7790_CLK_CMT0 R8A7790_CLK_TMU0 R8A7790_CLK_VSP1_DU1
-				R8A7790_CLK_VSP1_DU0 R8A7790_CLK_VSP1_R R8A7790_CLK_VSP1_S
+				R8A7790_CLK_VCP1 R8A7790_CLK_VCP0 R8A7790_CLK_VPC1
+				R8A7790_CLK_VPC0 R8A7790_CLK_JPU R8A7790_CLK_SSP1
+				R8A7790_CLK_TMU1 R8A7790_CLK_3DG R8A7790_CLK_2DDMAC
+				R8A7790_CLK_FDP1_2 R8A7790_CLK_FDP1_1 R8A7790_CLK_FDP1_0
+				R8A7790_CLK_TMU3 R8A7790_CLK_TMU2 R8A7790_CLK_CMT0
+				R8A7790_CLK_TMU0 R8A7790_CLK_VSP1_DU1 R8A7790_CLK_VSP1_DU0
+				R8A7790_CLK_VSP1_R R8A7790_CLK_VSP1_S
 			>;
 			clock-output-names =
-				"jpu", "tmu1", "3dg", "tmu3", "tmu2", "cmt0", "tmu0",
+				"vcp1", "vcp0", "vpc1", "vpc0", "jpu", "ssp1",
+				"tmu1", "3dg", "2ddmac", "fdp1-2", "fdp1-1",
+				"fdp1-0", "tmu3", "tmu2", "cmt0", "tmu0",
 				"vsp1-du1", "vsp1-du0", "vsp1-rt", "vsp1-sy";
 		};
 		mstp2_clks: mstp2_clks@e6150138 {
diff --git a/include/dt-bindings/clock/r8a7790-clock.h b/include/dt-bindings/clock/r8a7790-clock.h
index 14a3f12d13c..e3a3fb80feb 100644
--- a/include/dt-bindings/clock/r8a7790-clock.h
+++ b/include/dt-bindings/clock/r8a7790-clock.h
@@ -26,9 +26,18 @@
 #define R8A7790_CLK_MSIOF0		0
 
 /* MSTP1 */
-#define R8A7790_CLK_JPU		6
+#define R8A7790_CLK_VCP1		0
+#define R8A7790_CLK_VCP0		1
+#define R8A7790_CLK_VPC1		2
+#define R8A7790_CLK_VPC0		3
+#define R8A7790_CLK_JPU			6
+#define R8A7790_CLK_SSP1		9
 #define R8A7790_CLK_TMU1		11
 #define R8A7790_CLK_3DG			12
+#define R8A7790_CLK_2DDMAC		15
+#define R8A7790_CLK_FDP1_2		17
+#define R8A7790_CLK_FDP1_1		18
+#define R8A7790_CLK_FDP1_0		19
 #define R8A7790_CLK_TMU3		21
 #define R8A7790_CLK_TMU2		22
 #define R8A7790_CLK_CMT0		24
-- 
cgit v1.2.3-70-g09d2


From 74d89d25f6b0d84f7cd2fc09dc708177787c1465 Mon Sep 17 00:00:00 2001
From: Yoshifumi Hosoya <yoshifumi.hosoya.wj@renesas.com>
Date: Tue, 14 Oct 2014 16:01:43 +0900
Subject: ARM: shmobile: r8a7791: Add MMP clock to device tree

Signed-off-by: Yoshifumi Hosoya <yoshifumi.hosoya.wj@renesas.com>
Signed-off-by: Yoshihiro Kaneko <ykaneko0929@gmail.com>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 arch/arm/boot/dts/r8a7791.dtsi            | 21 +++++++++++++--------
 include/dt-bindings/clock/r8a7791-clock.h |  8 +++++++-
 2 files changed, 20 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index 98c1b8bef61..6ce78193985 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -977,18 +977,23 @@
 		mstp1_clks: mstp1_clks@e6150134 {
 			compatible = "renesas,r8a7791-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150134 0 4>, <0 0xe6150038 0 4>;
-			clocks = <&m2_clk>, <&p_clk>, <&zg_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
-				 <&cp_clk>, <&zs_clk>, <&zs_clk>, <&zs_clk>;
+			clocks = <&zs_clk>, <&zs_clk>, <&m2_clk>, <&zs_clk>, <&p_clk>,
+				 <&zg_clk>, <&zs_clk>, <&zs_clk>, <&zs_clk>, <&p_clk>,
+				 <&p_clk>, <&rclk_clk>, <&cp_clk>, <&zs_clk>, <&zs_clk>,
+				 <&zs_clk>;
 			#clock-cells = <1>;
 			renesas,clock-indices = <
-				R8A7791_CLK_JPU R8A7791_CLK_TMU1 R8A7791_CLK_3DG
-				R8A7791_CLK_TMU3 R8A7791_CLK_TMU2
-				R8A7791_CLK_CMT0 R8A7791_CLK_TMU0 R8A7791_CLK_VSP1_DU1
-				R8A7791_CLK_VSP1_DU0 R8A7791_CLK_VSP1_S
+				R8A7791_CLK_VCP0 R8A7791_CLK_VPC0 R8A7791_CLK_JPU
+				R8A7791_CLK_SSP1 R8A7791_CLK_TMU1 R8A7791_CLK_3DG
+				R8A7791_CLK_2DDMAC R8A7791_CLK_FDP1_1 R8A7791_CLK_FDP1_0
+				R8A7791_CLK_TMU3 R8A7791_CLK_TMU2 R8A7791_CLK_CMT0
+				R8A7791_CLK_TMU0 R8A7791_CLK_VSP1_DU1 R8A7791_CLK_VSP1_DU0
+				R8A7791_CLK_VSP1_S
 			>;
 			clock-output-names =
-				"jpu", "tmu1", "3dg", "tmu3", "tmu2", "cmt0", "tmu0",
-				"vsp1-du1", "vsp1-du0", "vsp1-sy";
+				"vcp0", "vpc0", "jpu", "ssp1", "tmu1", "3dg",
+				"2ddmac", "fdp1-1", "fdp1-0", "tmu3", "tmu2", "cmt0",
+				"tmu0", "vsp1-du1", "vsp1-du0", "vsp1-sy";
 		};
 		mstp2_clks: mstp2_clks@e6150138 {
 			compatible = "renesas,r8a7791-mstp-clocks", "renesas,cpg-mstp-clocks";
diff --git a/include/dt-bindings/clock/r8a7791-clock.h b/include/dt-bindings/clock/r8a7791-clock.h
index 9570b7c2eed..dcececd9f4d 100644
--- a/include/dt-bindings/clock/r8a7791-clock.h
+++ b/include/dt-bindings/clock/r8a7791-clock.h
@@ -25,9 +25,15 @@
 #define R8A7791_CLK_MSIOF0		0
 
 /* MSTP1 */
-#define R8A7791_CLK_JPU		6
+#define R8A7791_CLK_VCP0		1
+#define R8A7791_CLK_VPC0		3
+#define R8A7791_CLK_JPU			6
+#define R8A7791_CLK_SSP1		9
 #define R8A7791_CLK_TMU1		11
 #define R8A7791_CLK_3DG			12
+#define R8A7791_CLK_2DDMAC		15
+#define R8A7791_CLK_FDP1_1		18
+#define R8A7791_CLK_FDP1_0		19
 #define R8A7791_CLK_TMU3		21
 #define R8A7791_CLK_TMU2		22
 #define R8A7791_CLK_CMT0		24
-- 
cgit v1.2.3-70-g09d2


From f213d8f79a3928eaa2e2936f8ab40761aac04b95 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 30 Oct 2014 13:45:58 +0100
Subject: ALSA: pcm: Use static inline for snd_pcm_lib_alloc_vmalloc_buffer()

... instead of #if 0 hack.  It's more straightforward and obvious.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index e862497f755..5c3310d7d4b 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -942,7 +942,6 @@ int _snd_pcm_lib_alloc_vmalloc_buffer(struct snd_pcm_substream *substream,
 int snd_pcm_lib_free_vmalloc_buffer(struct snd_pcm_substream *substream);
 struct page *snd_pcm_lib_get_vmalloc_page(struct snd_pcm_substream *substream,
 					  unsigned long offset);
-#if 0 /* for kernel-doc */
 /**
  * snd_pcm_lib_alloc_vmalloc_buffer - allocate virtual DMA buffer
  * @substream: the substream to allocate the buffer to
@@ -955,8 +954,13 @@ struct page *snd_pcm_lib_get_vmalloc_page(struct snd_pcm_substream *substream,
  * Return: 1 if the buffer was changed, 0 if not changed, or a negative error
  * code.
  */
-static int snd_pcm_lib_alloc_vmalloc_buffer
-			(struct snd_pcm_substream *substream, size_t size);
+static inline int snd_pcm_lib_alloc_vmalloc_buffer
+			(struct snd_pcm_substream *substream, size_t size)
+{
+	return _snd_pcm_lib_alloc_vmalloc_buffer(substream, size,
+						 GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
+}
+
 /**
  * snd_pcm_lib_alloc_vmalloc_32_buffer - allocate 32-bit-addressable buffer
  * @substream: the substream to allocate the buffer to
@@ -968,15 +972,12 @@ static int snd_pcm_lib_alloc_vmalloc_buffer
  * Return: 1 if the buffer was changed, 0 if not changed, or a negative error
  * code.
  */
-static int snd_pcm_lib_alloc_vmalloc_32_buffer
-			(struct snd_pcm_substream *substream, size_t size);
-#endif
-#define snd_pcm_lib_alloc_vmalloc_buffer(subs, size) \
-	_snd_pcm_lib_alloc_vmalloc_buffer \
-			(subs, size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO)
-#define snd_pcm_lib_alloc_vmalloc_32_buffer(subs, size) \
-	_snd_pcm_lib_alloc_vmalloc_buffer \
-			(subs, size, GFP_KERNEL | GFP_DMA32 | __GFP_ZERO)
+static inline int snd_pcm_lib_alloc_vmalloc_32_buffer
+			(struct snd_pcm_substream *substream, size_t size)
+{
+	return _snd_pcm_lib_alloc_vmalloc_buffer(substream, size,
+						 GFP_KERNEL | GFP_DMA32 | __GFP_ZERO);
+}
 
 #define snd_pcm_get_dma_buf(substream) ((substream)->runtime->dma_buffer_p)
 
-- 
cgit v1.2.3-70-g09d2


From 30b771cf8c3120c5c946811ecc5a9b87a34003a2 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 30 Oct 2014 15:02:50 +0100
Subject: ALSA: pcm: More kerneldoc updates

Add proper kerneldoc comments to the exported functions.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h     | 160 +++++++++++++++++++++++++++++++++++++++++++++---
 sound/core/pcm.c        |  15 ++++-
 sound/core/pcm_native.c |  53 ++++++++++++++++
 3 files changed, 219 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 5c3310d7d4b..f78a5722f5c 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -533,6 +533,12 @@ snd_pcm_debug_name(struct snd_pcm_substream *substream, char *buf, size_t size)
  *  PCM library
  */
 
+/**
+ * snd_pcm_stream_linked - Check whether the substream is linked with others
+ * @substream: substream to check
+ *
+ * Returns true if the given substream is being linked with others.
+ */
 static inline int snd_pcm_stream_linked(struct snd_pcm_substream *substream)
 {
 	return substream->group != &substream->self_group;
@@ -543,6 +549,16 @@ void snd_pcm_stream_unlock(struct snd_pcm_substream *substream);
 void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream);
 void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream);
 unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream);
+
+/**
+ * snd_pcm_stream_lock_irqsave - Lock the PCM stream
+ * @substream: PCM substream
+ * @flags: irq flags
+ *
+ * This locks the PCM stream like snd_pcm_stream_lock() but with the local
+ * IRQ (only when nonatomic is false).  In nonatomic case, this is identical
+ * as snd_pcm_stream_lock().
+ */
 #define snd_pcm_stream_lock_irqsave(substream, flags)		 \
 	do {							 \
 		typecheck(unsigned long, flags);		 \
@@ -551,9 +567,25 @@ unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream);
 void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream,
 				      unsigned long flags);
 
+/**
+ * snd_pcm_group_for_each_entry - iterate over the linked substreams
+ * @s: the iterator
+ * @substream: the substream
+ *
+ * Iterate over the all linked substreams to the given @substream.
+ * When @substream isn't linked with any others, this gives returns @substream
+ * itself once.
+ */
 #define snd_pcm_group_for_each_entry(s, substream) \
 	list_for_each_entry(s, &substream->group->substreams, link_list)
 
+/**
+ * snd_pcm_running - Check whether the substream is in a running state
+ * @substream: substream to check
+ *
+ * Returns true if the given substream is in the state RUNNING, or in the
+ * state DRAINING for playback.
+ */
 static inline int snd_pcm_running(struct snd_pcm_substream *substream)
 {
 	return (substream->runtime->status->state == SNDRV_PCM_STATE_RUNNING ||
@@ -561,45 +593,81 @@ static inline int snd_pcm_running(struct snd_pcm_substream *substream)
 		 substream->stream == SNDRV_PCM_STREAM_PLAYBACK));
 }
 
+/**
+ * bytes_to_samples - Unit conversion of the size from bytes to samples
+ * @runtime: PCM runtime instance
+ * @size: size in bytes
+ */
 static inline ssize_t bytes_to_samples(struct snd_pcm_runtime *runtime, ssize_t size)
 {
 	return size * 8 / runtime->sample_bits;
 }
 
+/**
+ * bytes_to_frames - Unit conversion of the size from bytes to frames
+ * @runtime: PCM runtime instance
+ * @size: size in bytes
+ */
 static inline snd_pcm_sframes_t bytes_to_frames(struct snd_pcm_runtime *runtime, ssize_t size)
 {
 	return size * 8 / runtime->frame_bits;
 }
 
+/**
+ * samples_to_bytes - Unit conversion of the size from samples to bytes
+ * @runtime: PCM runtime instance
+ * @size: size in samples
+ */
 static inline ssize_t samples_to_bytes(struct snd_pcm_runtime *runtime, ssize_t size)
 {
 	return size * runtime->sample_bits / 8;
 }
 
+/**
+ * frames_to_bytes - Unit conversion of the size from frames to bytes
+ * @runtime: PCM runtime instance
+ * @size: size in frames
+ */
 static inline ssize_t frames_to_bytes(struct snd_pcm_runtime *runtime, snd_pcm_sframes_t size)
 {
 	return size * runtime->frame_bits / 8;
 }
 
+/**
+ * frame_aligned - Check whether the byte size is aligned to frames
+ * @runtime: PCM runtime instance
+ * @bytes: size in bytes
+ */
 static inline int frame_aligned(struct snd_pcm_runtime *runtime, ssize_t bytes)
 {
 	return bytes % runtime->byte_align == 0;
 }
 
+/**
+ * snd_pcm_lib_buffer_bytes - Get the buffer size of the current PCM in bytes
+ * @substream: PCM substream
+ */
 static inline size_t snd_pcm_lib_buffer_bytes(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	return frames_to_bytes(runtime, runtime->buffer_size);
 }
 
+/**
+ * snd_pcm_lib_period_bytes - Get the period size of the current PCM in bytes
+ * @substream: PCM substream
+ */
 static inline size_t snd_pcm_lib_period_bytes(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	return frames_to_bytes(runtime, runtime->period_size);
 }
 
-/*
- *  result is: 0 ... (boundary - 1)
+/**
+ * snd_pcm_playback_avail - Get the available (writable) space for playback
+ * @runtime: PCM runtime instance
+ *
+ * Result is between 0 ... (boundary - 1)
  */
 static inline snd_pcm_uframes_t snd_pcm_playback_avail(struct snd_pcm_runtime *runtime)
 {
@@ -611,8 +679,11 @@ static inline snd_pcm_uframes_t snd_pcm_playback_avail(struct snd_pcm_runtime *r
 	return avail;
 }
 
-/*
- *  result is: 0 ... (boundary - 1)
+/**
+ * snd_pcm_playback_avail - Get the available (readable) space for capture
+ * @runtime: PCM runtime instance
+ *
+ * Result is between 0 ... (boundary - 1)
  */
 static inline snd_pcm_uframes_t snd_pcm_capture_avail(struct snd_pcm_runtime *runtime)
 {
@@ -622,11 +693,19 @@ static inline snd_pcm_uframes_t snd_pcm_capture_avail(struct snd_pcm_runtime *ru
 	return avail;
 }
 
+/**
+ * snd_pcm_playback_hw_avail - Get the queued space for playback
+ * @runtime: PCM runtime instance
+ */
 static inline snd_pcm_sframes_t snd_pcm_playback_hw_avail(struct snd_pcm_runtime *runtime)
 {
 	return runtime->buffer_size - snd_pcm_playback_avail(runtime);
 }
 
+/**
+ * snd_pcm_capture_hw_avail - Get the free space for capture
+ * @runtime: PCM runtime instance
+ */
 static inline snd_pcm_sframes_t snd_pcm_capture_hw_avail(struct snd_pcm_runtime *runtime)
 {
 	return runtime->buffer_size - snd_pcm_capture_avail(runtime);
@@ -706,6 +785,20 @@ static inline int snd_pcm_capture_empty(struct snd_pcm_substream *substream)
 	return snd_pcm_capture_avail(runtime) == 0;
 }
 
+/**
+ * snd_pcm_trigger_done - Mark the master substream
+ * @substream: the pcm substream instance
+ * @master: the linked master substream
+ *
+ * When multiple substreams of the same card are linked and the hardware
+ * supports the single-shot operation, the driver calls this in the loop
+ * in snd_pcm_group_for_each_entry() for marking the substream as "done".
+ * Then most of trigger operations are performed only to the given master
+ * substream.
+ *
+ * The trigger_master mark is cleared at timestamp updates at the end
+ * of trigger operations.
+ */
 static inline void snd_pcm_trigger_done(struct snd_pcm_substream *substream, 
 					struct snd_pcm_substream *master)
 {
@@ -881,6 +974,14 @@ unsigned int snd_pcm_rate_bit_to_rate(unsigned int rate_bit);
 unsigned int snd_pcm_rate_mask_intersect(unsigned int rates_a,
 					 unsigned int rates_b);
 
+/**
+ * snd_pcm_set_runtime_buffer - Set the PCM runtime buffer
+ * @substream: PCM substream to set
+ * @bufp: the buffer information, NULL to clear
+ *
+ * Copy the buffer information to runtime->dma_buffer when @bufp is non-NULL.
+ * Otherwise it clears the current buffer information.
+ */
 static inline void snd_pcm_set_runtime_buffer(struct snd_pcm_substream *substream,
 					      struct snd_dma_buffer *bufp)
 {
@@ -906,6 +1007,11 @@ void snd_pcm_timer_resolution_change(struct snd_pcm_substream *substream);
 void snd_pcm_timer_init(struct snd_pcm_substream *substream);
 void snd_pcm_timer_done(struct snd_pcm_substream *substream);
 
+/**
+ * snd_pcm_gettime - Fill the timespec depending on the timestamp mode
+ * @runtime: PCM runtime instance
+ * @tv: timespec to fill
+ */
 static inline void snd_pcm_gettime(struct snd_pcm_runtime *runtime,
 				   struct timespec *tv)
 {
@@ -997,18 +1103,35 @@ struct page *snd_pcm_sgbuf_ops_page(struct snd_pcm_substream *substream,
 #define snd_pcm_sgbuf_ops_page	NULL
 #endif /* SND_DMA_SGBUF */
 
+/**
+ * snd_pcm_sgbuf_get_addr - Get the DMA address at the corresponding offset
+ * @substream: PCM substream
+ * @ofs: byte offset
+ */
 static inline dma_addr_t
 snd_pcm_sgbuf_get_addr(struct snd_pcm_substream *substream, unsigned int ofs)
 {
 	return snd_sgbuf_get_addr(snd_pcm_get_dma_buf(substream), ofs);
 }
 
+/**
+ * snd_pcm_sgbuf_get_ptr - Get the virtual address at the corresponding offset
+ * @substream: PCM substream
+ * @ofs: byte offset
+ */
 static inline void *
 snd_pcm_sgbuf_get_ptr(struct snd_pcm_substream *substream, unsigned int ofs)
 {
 	return snd_sgbuf_get_ptr(snd_pcm_get_dma_buf(substream), ofs);
 }
 
+/**
+ * snd_pcm_sgbuf_chunk_size - Compute the max size that fits within the contig.
+ * page from the given size
+ * @substream: PCM substream
+ * @ofs: byte offset
+ * @size: byte size to examine
+ */
 static inline unsigned int
 snd_pcm_sgbuf_get_chunk_size(struct snd_pcm_substream *substream,
 			     unsigned int ofs, unsigned int size)
@@ -1016,13 +1139,24 @@ snd_pcm_sgbuf_get_chunk_size(struct snd_pcm_substream *substream,
 	return snd_sgbuf_get_chunk_size(snd_pcm_get_dma_buf(substream), ofs, size);
 }
 
-/* handle mmap counter - PCM mmap callback should handle this counter properly */
+/**
+ * snd_pcm_mmap_data_open - increase the mmap counter
+ * @area: VMA
+ *
+ * PCM mmap callback should handle this counter properly
+ */
 static inline void snd_pcm_mmap_data_open(struct vm_area_struct *area)
 {
 	struct snd_pcm_substream *substream = (struct snd_pcm_substream *)area->vm_private_data;
 	atomic_inc(&substream->mmap_count);
 }
 
+/**
+ * snd_pcm_mmap_data_close - decrease the mmap counter
+ * @area: VMA
+ *
+ * PCM mmap callback should handle this counter properly
+ */
 static inline void snd_pcm_mmap_data_close(struct vm_area_struct *area)
 {
 	struct snd_pcm_substream *substream = (struct snd_pcm_substream *)area->vm_private_data;
@@ -1042,6 +1176,11 @@ int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_s
 
 #define snd_pcm_lib_mmap_vmalloc NULL
 
+/**
+ * snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer
+ * @dma: DMA number
+ * @max: pointer to store the max size
+ */
 static inline void snd_pcm_limit_isa_dma_size(int dma, size_t *max)
 {
 	*max = dma < 4 ? 64 * 1024 : 128 * 1024;
@@ -1094,7 +1233,11 @@ struct snd_pcm_chmap {
 	void *private_data;	/* optional: private data pointer */
 };
 
-/* get the PCM substream assigned to the given chmap info */
+/**
+ * snd_pcm_chmap_substream - get the PCM substream assigned to the given chmap info
+ * @info: chmap information
+ * @idx: the substream number index
+ */
 static inline struct snd_pcm_substream *
 snd_pcm_chmap_substream(struct snd_pcm_chmap *info, unsigned int idx)
 {
@@ -1121,7 +1264,10 @@ int snd_pcm_add_chmap_ctls(struct snd_pcm *pcm, int stream,
 			   unsigned long private_value,
 			   struct snd_pcm_chmap **info_ret);
 
-/* Strong-typed conversion of pcm_format to bitwise */
+/**
+ * pcm_format_to_bits - Strong-typed conversion of pcm_format to bitwise
+ * @pcm_format: PCM format
+ */
 static inline u64 pcm_format_to_bits(snd_pcm_format_t pcm_format)
 {
 	return 1ULL << (__force int) pcm_format;
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 42ded997b22..31acc3df62c 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -218,6 +218,10 @@ static char *snd_pcm_format_names[] = {
 	FORMAT(DSD_U32_LE),
 };
 
+/**
+ * snd_pcm_format_name - Return a name string for the given PCM format
+ * @format: PCM format
+ */
 const char *snd_pcm_format_name(snd_pcm_format_t format)
 {
 	if ((__force unsigned int)format >= ARRAY_SIZE(snd_pcm_format_names))
@@ -707,7 +711,6 @@ int snd_pcm_new_stream(struct snd_pcm *pcm, int stream, int substream_count)
 	}
 	return 0;
 }				
-
 EXPORT_SYMBOL(snd_pcm_new_stream);
 
 static int _snd_pcm_new(struct snd_card *card, const char *id, int device,
@@ -1155,6 +1158,15 @@ static int snd_pcm_dev_disconnect(struct snd_device *device)
 	return 0;
 }
 
+/**
+ * snd_pcm_notify - Add/remove the notify list
+ * @notify: PCM notify list
+ * @nfree: 0 = register, 1 = unregister
+ *
+ * This adds the given notifier to the global list so that the callback is
+ * called for each registered PCM devices.  This exists only for PCM OSS
+ * emulation, so far.
+ */
 int snd_pcm_notify(struct snd_pcm_notify *notify, int nfree)
 {
 	struct snd_pcm *pcm;
@@ -1177,7 +1189,6 @@ int snd_pcm_notify(struct snd_pcm_notify *notify, int nfree)
 	mutex_unlock(&register_mutex);
 	return 0;
 }
-
 EXPORT_SYMBOL(snd_pcm_notify);
 
 #ifdef CONFIG_PROC_FS
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 2f7ad10ee7c..4d5795d8b9f 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -74,6 +74,14 @@ static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream);
 static DEFINE_RWLOCK(snd_pcm_link_rwlock);
 static DECLARE_RWSEM(snd_pcm_link_rwsem);
 
+/**
+ * snd_pcm_stream_lock - Lock the PCM stream
+ * @substream: PCM substream
+ *
+ * This locks the PCM stream's spinlock or mutex depending on the nonatomic
+ * flag of the given substream.  This also takes the global link rw lock
+ * (or rw sem), too, for avoiding the race with linked streams.
+ */
 void snd_pcm_stream_lock(struct snd_pcm_substream *substream)
 {
 	if (substream->pcm->nonatomic) {
@@ -86,6 +94,12 @@ void snd_pcm_stream_lock(struct snd_pcm_substream *substream)
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stream_lock);
 
+/**
+ * snd_pcm_stream_lock - Unlock the PCM stream
+ * @substream: PCM substream
+ *
+ * This unlocks the PCM stream that has been locked via snd_pcm_stream_lock().
+ */
 void snd_pcm_stream_unlock(struct snd_pcm_substream *substream)
 {
 	if (substream->pcm->nonatomic) {
@@ -98,6 +112,14 @@ void snd_pcm_stream_unlock(struct snd_pcm_substream *substream)
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock);
 
+/**
+ * snd_pcm_stream_lock_irq - Lock the PCM stream
+ * @substream: PCM substream
+ *
+ * This locks the PCM stream like snd_pcm_stream_lock() and disables the local
+ * IRQ (only when nonatomic is false).  In nonatomic case, this is identical
+ * as snd_pcm_stream_lock().
+ */
 void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream)
 {
 	if (!substream->pcm->nonatomic)
@@ -106,6 +128,12 @@ void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream)
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stream_lock_irq);
 
+/**
+ * snd_pcm_stream_unlock_irq - Unlock the PCM stream
+ * @substream: PCM substream
+ *
+ * This is a counter-part of snd_pcm_stream_lock_irq().
+ */
 void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream)
 {
 	snd_pcm_stream_unlock(substream);
@@ -124,6 +152,13 @@ unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream)
 }
 EXPORT_SYMBOL_GPL(_snd_pcm_stream_lock_irqsave);
 
+/**
+ * snd_pcm_stream_unlock_irqrestore - Unlock the PCM stream
+ * @substream: PCM substream
+ * @flags: irq flags
+ *
+ * This is a counter-part of snd_pcm_stream_lock_irqsave().
+ */
 void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream,
 				      unsigned long flags)
 {
@@ -3312,6 +3347,15 @@ static const struct vm_operations_struct snd_pcm_vm_ops_data_fault = {
 /*
  * mmap the DMA buffer on RAM
  */
+
+/**
+ * snd_pcm_lib_default_mmap - Default PCM data mmap function
+ * @substream: PCM substream
+ * @area: VMA
+ *
+ * This is the default mmap handler for PCM data.  When mmap pcm_ops is NULL,
+ * this function is invoked implicitly.
+ */
 int snd_pcm_lib_default_mmap(struct snd_pcm_substream *substream,
 			     struct vm_area_struct *area)
 {
@@ -3343,6 +3387,15 @@ EXPORT_SYMBOL_GPL(snd_pcm_lib_default_mmap);
  * mmap the DMA buffer on I/O memory area
  */
 #if SNDRV_PCM_INFO_MMAP_IOMEM
+/**
+ * snd_pcm_lib_mmap_iomem - Default PCM data mmap function for I/O mem
+ * @substream: PCM substream
+ * @area: VMA
+ *
+ * When your hardware uses the iomapped pages as the hardware buffer and
+ * wants to mmap it, pass this function as mmap pcm_ops.  Note that this
+ * is supposed to work only on limited architectures.
+ */
 int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream,
 			   struct vm_area_struct *area)
 {
-- 
cgit v1.2.3-70-g09d2


From 85926e0fe8b48fe6227614ddc3a1cb41c0a3c51a Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 30 Oct 2014 15:06:13 +0100
Subject: ALSA: pcm: Convert params_*() with static inline functions

... and add proper kerneldoc comments.
There is no big reason to keep them as macros.  Static inline
functions are safer in general, and suitable for kerneldoc, too.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h | 65 +++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 53 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index f78a5722f5c..29eb09ef296 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -841,18 +841,59 @@ static inline const struct snd_interval *hw_param_interval_c(const struct snd_pc
 	return &params->intervals[var - SNDRV_PCM_HW_PARAM_FIRST_INTERVAL];
 }
 
-#define params_channels(p) \
-	(hw_param_interval_c((p), SNDRV_PCM_HW_PARAM_CHANNELS)->min)
-#define params_rate(p) \
-	(hw_param_interval_c((p), SNDRV_PCM_HW_PARAM_RATE)->min)
-#define params_period_size(p) \
-	(hw_param_interval_c((p), SNDRV_PCM_HW_PARAM_PERIOD_SIZE)->min)
-#define params_periods(p) \
-	(hw_param_interval_c((p), SNDRV_PCM_HW_PARAM_PERIODS)->min)
-#define params_buffer_size(p) \
-	(hw_param_interval_c((p), SNDRV_PCM_HW_PARAM_BUFFER_SIZE)->min)
-#define params_buffer_bytes(p) \
-	(hw_param_interval_c((p), SNDRV_PCM_HW_PARAM_BUFFER_BYTES)->min)
+/**
+ * params_channels - Get the number of channels from the hw params
+ * @p: hw params
+ */
+static inline unsigned int params_channels(const struct snd_pcm_hw_params *p)
+{
+	return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_CHANNELS)->min;
+}
+
+/**
+ * params_channels - Get the sample rate from the hw params
+ * @p: hw params
+ */
+static inline unsigned int params_rate(const struct snd_pcm_hw_params *p)
+{
+	return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_RATE)->min;
+}
+
+/**
+ * params_channels - Get the period size (in frames) from the hw params
+ * @p: hw params
+ */
+static inline unsigned int params_period_size(const struct snd_pcm_hw_params *p)
+{
+	return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_PERIOD_SIZE)->min;
+}
+
+/**
+ * params_channels - Get the number of periods from the hw params
+ * @p: hw params
+ */
+static inline unsigned int params_periods(const struct snd_pcm_hw_params *p)
+{
+	return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_PERIODS)->min;
+}
+
+/**
+ * params_channels - Get the buffer size (in frames) from the hw params
+ * @p: hw params
+ */
+static inline unsigned int params_buffer_size(const struct snd_pcm_hw_params *p)
+{
+	return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_BUFFER_SIZE)->min;
+}
+
+/**
+ * params_channels - Get the buffer size (in bytes) from the hw params
+ * @p: hw params
+ */
+static inline unsigned int params_buffer_bytes(const struct snd_pcm_hw_params *p)
+{
+	return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_BUFFER_BYTES)->min;
+}
 
 int snd_interval_refine(struct snd_interval *i, const struct snd_interval *v);
 void snd_interval_mul(const struct snd_interval *a, const struct snd_interval *b, struct snd_interval *c);
-- 
cgit v1.2.3-70-g09d2


From 384cb2ce819cf08fc8e7c3d306f180f0cefe4674 Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Mon, 27 Oct 2014 10:11:57 +0900
Subject: clk: samsung: exynos4415: Add clocks using common clock framework

This patch adds clock driver of Exynos4415 SoC based on Cortex-A9 using
common clock framework. The CMU (Clock Management Unit) of Exynos4415
controls PLLs(Phase Locked Loops) and generates system clocks for CPU,
busses and function clocks for individual IPs.

Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Tomasz Figa <tomasz.figa@gmail.com>
Signed-off-by: Seung-Woo Kim <sw0312.kim@samsung.com>
Acked-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
---
 drivers/clk/samsung/Makefile           |    1 +
 drivers/clk/samsung/clk-exynos4415.c   | 1142 ++++++++++++++++++++++++++++++++
 include/dt-bindings/clock/exynos4415.h |  360 ++++++++++
 3 files changed, 1503 insertions(+)
 create mode 100644 drivers/clk/samsung/clk-exynos4415.c
 create mode 100644 include/dt-bindings/clock/exynos4415.h

(limited to 'include')

diff --git a/drivers/clk/samsung/Makefile b/drivers/clk/samsung/Makefile
index 6fb4bc602e8..d8535e6df1d 100644
--- a/drivers/clk/samsung/Makefile
+++ b/drivers/clk/samsung/Makefile
@@ -5,6 +5,7 @@
 obj-$(CONFIG_COMMON_CLK)	+= clk.o clk-pll.o
 obj-$(CONFIG_SOC_EXYNOS3250)	+= clk-exynos3250.o
 obj-$(CONFIG_ARCH_EXYNOS4)	+= clk-exynos4.o
+obj-$(CONFIG_SOC_EXYNOS4415)	+= clk-exynos4415.o
 obj-$(CONFIG_SOC_EXYNOS5250)	+= clk-exynos5250.o
 obj-$(CONFIG_SOC_EXYNOS5260)	+= clk-exynos5260.o
 obj-$(CONFIG_SOC_EXYNOS5410)	+= clk-exynos5410.o
diff --git a/drivers/clk/samsung/clk-exynos4415.c b/drivers/clk/samsung/clk-exynos4415.c
new file mode 100644
index 00000000000..c7208c7a3ad
--- /dev/null
+++ b/drivers/clk/samsung/clk-exynos4415.c
@@ -0,0 +1,1142 @@
+/*
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author: Chanwoo Choi <cw00.choi@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Common Clock Framework support for Exynos4415 SoC.
+ */
+
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/syscore_ops.h>
+
+#include <dt-bindings/clock/exynos4415.h>
+
+#include "clk.h"
+#include "clk-pll.h"
+
+#define SRC_LEFTBUS		0x4200
+#define DIV_LEFTBUS		0x4500
+#define GATE_IP_LEFTBUS		0x4800
+#define GATE_IP_IMAGE		0x4930
+#define SRC_RIGHTBUS		0x8200
+#define DIV_RIGHTBUS		0x8500
+#define GATE_IP_RIGHTBUS	0x8800
+#define GATE_IP_PERIR		0x8960
+#define EPLL_LOCK		0xc010
+#define G3D_PLL_LOCK		0xc020
+#define DISP_PLL_LOCK		0xc030
+#define ISP_PLL_LOCK		0xc040
+#define EPLL_CON0		0xc110
+#define EPLL_CON1		0xc114
+#define EPLL_CON2		0xc118
+#define G3D_PLL_CON0		0xc120
+#define G3D_PLL_CON1		0xc124
+#define G3D_PLL_CON2		0xc128
+#define ISP_PLL_CON0		0xc130
+#define ISP_PLL_CON1		0xc134
+#define ISP_PLL_CON2		0xc138
+#define DISP_PLL_CON0		0xc140
+#define DISP_PLL_CON1		0xc144
+#define DISP_PLL_CON2		0xc148
+#define SRC_TOP0		0xc210
+#define SRC_TOP1		0xc214
+#define SRC_CAM			0xc220
+#define SRC_TV			0xc224
+#define SRC_MFC			0xc228
+#define SRC_G3D			0xc22c
+#define SRC_LCD			0xc234
+#define SRC_ISP			0xc238
+#define SRC_MAUDIO		0xc23c
+#define SRC_FSYS		0xc240
+#define SRC_PERIL0		0xc250
+#define SRC_PERIL1		0xc254
+#define SRC_CAM1		0xc258
+#define SRC_TOP_ISP0		0xc25c
+#define SRC_TOP_ISP1		0xc260
+#define SRC_MASK_TOP		0xc310
+#define SRC_MASK_CAM		0xc320
+#define SRC_MASK_TV		0xc324
+#define SRC_MASK_LCD		0xc334
+#define SRC_MASK_ISP		0xc338
+#define SRC_MASK_MAUDIO		0xc33c
+#define SRC_MASK_FSYS		0xc340
+#define SRC_MASK_PERIL0		0xc350
+#define SRC_MASK_PERIL1		0xc354
+#define DIV_TOP			0xc510
+#define DIV_CAM			0xc520
+#define DIV_TV			0xc524
+#define DIV_MFC			0xc528
+#define DIV_G3D			0xc52c
+#define DIV_LCD			0xc534
+#define DIV_ISP			0xc538
+#define DIV_MAUDIO		0xc53c
+#define DIV_FSYS0		0xc540
+#define DIV_FSYS1		0xc544
+#define DIV_FSYS2		0xc548
+#define DIV_PERIL0		0xc550
+#define DIV_PERIL1		0xc554
+#define DIV_PERIL2		0xc558
+#define DIV_PERIL3		0xc55c
+#define DIV_PERIL4		0xc560
+#define DIV_PERIL5		0xc564
+#define DIV_CAM1		0xc568
+#define DIV_TOP_ISP1		0xc56c
+#define DIV_TOP_ISP0		0xc570
+#define CLKDIV2_RATIO		0xc580
+#define GATE_SCLK_CAM		0xc820
+#define GATE_SCLK_TV		0xc824
+#define GATE_SCLK_MFC		0xc828
+#define GATE_SCLK_G3D		0xc82c
+#define GATE_SCLK_LCD		0xc834
+#define GATE_SCLK_MAUDIO	0xc83c
+#define GATE_SCLK_FSYS		0xc840
+#define GATE_SCLK_PERIL		0xc850
+#define GATE_IP_CAM		0xc920
+#define GATE_IP_TV		0xc924
+#define GATE_IP_MFC		0xc928
+#define GATE_IP_G3D		0xc92c
+#define GATE_IP_LCD		0xc934
+#define GATE_IP_FSYS		0xc940
+#define GATE_IP_PERIL		0xc950
+#define GATE_BLOCK		0xc970
+#define APLL_LOCK		0x14000
+#define APLL_CON0		0x14100
+#define SRC_CPU			0x14200
+#define DIV_CPU0		0x14500
+#define DIV_CPU1		0x14504
+
+enum exynos4415_plls {
+	apll, epll, g3d_pll, isp_pll, disp_pll,
+	nr_plls,
+};
+
+/*
+ * Support for CMU save/restore across system suspends
+ */
+#ifdef CONFIG_PM_SLEEP
+static struct samsung_clk_reg_dump *exynos4415_clk_regs;
+static struct samsung_clk_provider *exynos4415_ctx;
+
+static unsigned long exynos4415_cmu_clk_regs[] __initdata = {
+	SRC_LEFTBUS,
+	DIV_LEFTBUS,
+	GATE_IP_LEFTBUS,
+	GATE_IP_IMAGE,
+	SRC_RIGHTBUS,
+	DIV_RIGHTBUS,
+	GATE_IP_RIGHTBUS,
+	GATE_IP_PERIR,
+	EPLL_LOCK,
+	G3D_PLL_LOCK,
+	DISP_PLL_LOCK,
+	ISP_PLL_LOCK,
+	EPLL_CON0,
+	EPLL_CON1,
+	EPLL_CON2,
+	G3D_PLL_CON0,
+	G3D_PLL_CON1,
+	G3D_PLL_CON2,
+	ISP_PLL_CON0,
+	ISP_PLL_CON1,
+	ISP_PLL_CON2,
+	DISP_PLL_CON0,
+	DISP_PLL_CON1,
+	DISP_PLL_CON2,
+	SRC_TOP0,
+	SRC_TOP1,
+	SRC_CAM,
+	SRC_TV,
+	SRC_MFC,
+	SRC_G3D,
+	SRC_LCD,
+	SRC_ISP,
+	SRC_MAUDIO,
+	SRC_FSYS,
+	SRC_PERIL0,
+	SRC_PERIL1,
+	SRC_CAM1,
+	SRC_TOP_ISP0,
+	SRC_TOP_ISP1,
+	SRC_MASK_TOP,
+	SRC_MASK_CAM,
+	SRC_MASK_TV,
+	SRC_MASK_LCD,
+	SRC_MASK_ISP,
+	SRC_MASK_MAUDIO,
+	SRC_MASK_FSYS,
+	SRC_MASK_PERIL0,
+	SRC_MASK_PERIL1,
+	DIV_TOP,
+	DIV_CAM,
+	DIV_TV,
+	DIV_MFC,
+	DIV_G3D,
+	DIV_LCD,
+	DIV_ISP,
+	DIV_MAUDIO,
+	DIV_FSYS0,
+	DIV_FSYS1,
+	DIV_FSYS2,
+	DIV_PERIL0,
+	DIV_PERIL1,
+	DIV_PERIL2,
+	DIV_PERIL3,
+	DIV_PERIL4,
+	DIV_PERIL5,
+	DIV_CAM1,
+	DIV_TOP_ISP1,
+	DIV_TOP_ISP0,
+	CLKDIV2_RATIO,
+	GATE_SCLK_CAM,
+	GATE_SCLK_TV,
+	GATE_SCLK_MFC,
+	GATE_SCLK_G3D,
+	GATE_SCLK_LCD,
+	GATE_SCLK_MAUDIO,
+	GATE_SCLK_FSYS,
+	GATE_SCLK_PERIL,
+	GATE_IP_CAM,
+	GATE_IP_TV,
+	GATE_IP_MFC,
+	GATE_IP_G3D,
+	GATE_IP_LCD,
+	GATE_IP_FSYS,
+	GATE_IP_PERIL,
+	GATE_BLOCK,
+	APLL_LOCK,
+	APLL_CON0,
+	SRC_CPU,
+	DIV_CPU0,
+	DIV_CPU1,
+};
+
+static int exynos4415_clk_suspend(void)
+{
+	samsung_clk_save(exynos4415_ctx->reg_base, exynos4415_clk_regs,
+				ARRAY_SIZE(exynos4415_cmu_clk_regs));
+
+	return 0;
+}
+
+static void exynos4415_clk_resume(void)
+{
+	samsung_clk_restore(exynos4415_ctx->reg_base, exynos4415_clk_regs,
+				ARRAY_SIZE(exynos4415_cmu_clk_regs));
+}
+
+static struct syscore_ops exynos4415_clk_syscore_ops = {
+	.suspend = exynos4415_clk_suspend,
+	.resume = exynos4415_clk_resume,
+};
+
+static void exynos4415_clk_sleep_init(void)
+{
+	exynos4415_clk_regs =
+		samsung_clk_alloc_reg_dump(exynos4415_cmu_clk_regs,
+					ARRAY_SIZE(exynos4415_cmu_clk_regs));
+	if (!exynos4415_clk_regs) {
+		pr_warn("%s: Failed to allocate sleep save data\n", __func__);
+		return;
+	}
+
+	register_syscore_ops(&exynos4415_clk_syscore_ops);
+}
+#else
+static inline void exynos4415_clk_sleep_init(void) { }
+#endif
+
+/* list of all parent clock list */
+PNAME(mout_g3d_pllsrc_p)	= { "fin_pll", };
+
+PNAME(mout_apll_p)		= { "fin_pll", "fout_apll", };
+PNAME(mout_g3d_pll_p)		= { "fin_pll", "fout_g3d_pll", };
+PNAME(mout_isp_pll_p)		= { "fin_pll", "fout_isp_pll", };
+PNAME(mout_disp_pll_p)		= { "fin_pll", "fout_disp_pll", };
+
+PNAME(mout_mpll_user_p)		= { "fin_pll", "div_mpll_pre", };
+PNAME(mout_epll_p)		= { "fin_pll", "fout_epll", };
+PNAME(mout_core_p)		= { "mout_apll", "mout_mpll_user_c", };
+PNAME(mout_hpm_p)		= { "mout_apll", "mout_mpll_user_c", };
+
+PNAME(mout_ebi_p)		= { "div_aclk_200", "div_aclk_160", };
+PNAME(mout_ebi_1_p)		= { "mout_ebi", "mout_g3d_pll", };
+
+PNAME(mout_gdl_p)		= { "mout_mpll_user_l", };
+PNAME(mout_gdr_p)		= { "mout_mpll_user_r", };
+
+PNAME(mout_aclk_266_p)		= { "mout_mpll_user_t", "mout_g3d_pll", };
+
+PNAME(group_epll_g3dpll_p)	= { "mout_epll", "mout_g3d_pll" };
+PNAME(group_sclk_p)		= { "xxti", "xusbxti",
+				    "none", "mout_isp_pll",
+				    "none", "none", "div_mpll_pre",
+				    "mout_epll", "mout_g3d_pll", };
+PNAME(group_spdif_p)		= { "mout_audio0", "mout_audio1",
+				    "mout_audio2", "spdif_extclk", };
+PNAME(group_sclk_audio2_p)	= { "audiocdclk2", "none",
+				    "none", "mout_isp_pll",
+				    "mout_disp_pll", "xusbxti",
+				    "div_mpll_pre", "mout_epll",
+				    "mout_g3d_pll", };
+PNAME(group_sclk_audio1_p)	= { "audiocdclk1", "none",
+				    "none", "mout_isp_pll",
+				    "mout_disp_pll", "xusbxti",
+				    "div_mpll_pre", "mout_epll",
+				    "mout_g3d_pll", };
+PNAME(group_sclk_audio0_p)	= { "audiocdclk0", "none",
+				    "none", "mout_isp_pll",
+				    "mout_disp_pll", "xusbxti",
+				    "div_mpll_pre", "mout_epll",
+				    "mout_g3d_pll", };
+PNAME(group_fimc_lclk_p)	= { "xxti", "xusbxti",
+				    "none", "mout_isp_pll",
+				    "none", "mout_disp_pll",
+				    "mout_mpll_user_t", "mout_epll",
+				    "mout_g3d_pll", };
+PNAME(group_sclk_fimd0_p)	= { "xxti", "xusbxti",
+				    "m_bitclkhsdiv4_4l", "mout_isp_pll",
+				    "mout_disp_pll", "sclk_hdmiphy",
+				    "div_mpll_pre", "mout_epll",
+				    "mout_g3d_pll", };
+PNAME(mout_hdmi_p)		= { "sclk_pixel", "sclk_hdmiphy" };
+PNAME(mout_mfc_p)		= { "mout_mfc_0", "mout_mfc_1" };
+PNAME(mout_g3d_p)		= { "mout_g3d_0", "mout_g3d_1" };
+PNAME(mout_jpeg_p)		= { "mout_jpeg_0", "mout_jpeg_1" };
+PNAME(mout_jpeg1_p)		= { "mout_epll", "mout_g3d_pll" };
+PNAME(group_aclk_isp0_300_p)	= { "mout_isp_pll", "div_mpll_pre" };
+PNAME(group_aclk_isp0_400_user_p) = { "fin_pll", "div_aclk_400_mcuisp" };
+PNAME(group_aclk_isp0_300_user_p) = { "fin_pll", "mout_aclk_isp0_300" };
+PNAME(group_aclk_isp1_300_user_p) = { "fin_pll", "mout_aclk_isp1_300" };
+PNAME(group_mout_mpll_user_t_p)	= { "mout_mpll_user_t" };
+
+static struct samsung_fixed_factor_clock exynos4415_fixed_factor_clks[] __initdata = {
+	/* HACK: fin_pll hardcoded to xusbxti until detection is implemented. */
+	FFACTOR(CLK_FIN_PLL, "fin_pll", "xusbxti", 1, 1, 0),
+};
+
+static struct samsung_fixed_rate_clock exynos4415_fixed_rate_clks[] __initdata = {
+	FRATE(CLK_SCLK_HDMIPHY, "sclk_hdmiphy", NULL, CLK_IS_ROOT, 27000000),
+};
+
+static struct samsung_mux_clock exynos4415_mux_clks[] __initdata = {
+	/*
+	 * NOTE: Following table is sorted by register address in ascending
+	 * order and then bitfield shift in descending order, as it is done
+	 * in the User's Manual. When adding new entries, please make sure
+	 * that the order is preserved, to avoid merge conflicts and make
+	 * further work with defined data easier.
+	 */
+
+	/* SRC_LEFTBUS */
+	MUX(CLK_MOUT_MPLL_USER_L, "mout_mpll_user_l", mout_mpll_user_p,
+		SRC_LEFTBUS, 4, 1),
+	MUX(CLK_MOUT_GDL, "mout_gdl", mout_gdl_p, SRC_LEFTBUS, 0, 1),
+
+	/* SRC_RIGHTBUS */
+	MUX(CLK_MOUT_MPLL_USER_R, "mout_mpll_user_r", mout_mpll_user_p,
+		SRC_RIGHTBUS, 4, 1),
+	MUX(CLK_MOUT_GDR, "mout_gdr", mout_gdr_p, SRC_RIGHTBUS, 0, 1),
+
+	/* SRC_TOP0 */
+	MUX(CLK_MOUT_EBI, "mout_ebi", mout_ebi_p, SRC_TOP0, 28, 1),
+	MUX(CLK_MOUT_ACLK_200, "mout_aclk_200", group_mout_mpll_user_t_p,
+		SRC_TOP0, 24, 1),
+	MUX(CLK_MOUT_ACLK_160, "mout_aclk_160", group_mout_mpll_user_t_p,
+		SRC_TOP0, 20, 1),
+	MUX(CLK_MOUT_ACLK_100, "mout_aclk_100", group_mout_mpll_user_t_p,
+		SRC_TOP0, 16, 1),
+	MUX(CLK_MOUT_ACLK_266, "mout_aclk_266", mout_aclk_266_p,
+		SRC_TOP0, 12, 1),
+	MUX(CLK_MOUT_G3D_PLL, "mout_g3d_pll", mout_g3d_pll_p,
+		SRC_TOP0, 8, 1),
+	MUX(CLK_MOUT_EPLL, "mout_epll", mout_epll_p, SRC_TOP0, 4, 1),
+	MUX(CLK_MOUT_EBI_1, "mout_ebi_1", mout_ebi_1_p, SRC_TOP0, 0, 1),
+
+	/* SRC_TOP1 */
+	MUX(CLK_MOUT_ISP_PLL, "mout_isp_pll", mout_isp_pll_p,
+		SRC_TOP1, 28, 1),
+	MUX(CLK_MOUT_DISP_PLL, "mout_disp_pll", mout_disp_pll_p,
+		SRC_TOP1, 16, 1),
+	MUX(CLK_MOUT_MPLL_USER_T, "mout_mpll_user_t", mout_mpll_user_p,
+		SRC_TOP1, 12, 1),
+	MUX(CLK_MOUT_ACLK_400_MCUISP, "mout_aclk_400_mcuisp",
+		group_mout_mpll_user_t_p, SRC_TOP1, 8, 1),
+	MUX(CLK_MOUT_G3D_PLLSRC, "mout_g3d_pllsrc", mout_g3d_pllsrc_p,
+		SRC_TOP1, 0, 1),
+
+	/* SRC_CAM */
+	MUX(CLK_MOUT_CSIS1, "mout_csis1", group_fimc_lclk_p, SRC_CAM, 28, 4),
+	MUX(CLK_MOUT_CSIS0, "mout_csis0", group_fimc_lclk_p, SRC_CAM, 24, 4),
+	MUX(CLK_MOUT_CAM1, "mout_cam1", group_fimc_lclk_p, SRC_CAM, 20, 4),
+	MUX(CLK_MOUT_FIMC3_LCLK, "mout_fimc3_lclk", group_fimc_lclk_p, SRC_CAM,
+		12, 4),
+	MUX(CLK_MOUT_FIMC2_LCLK, "mout_fimc2_lclk", group_fimc_lclk_p, SRC_CAM,
+		8, 4),
+	MUX(CLK_MOUT_FIMC1_LCLK, "mout_fimc1_lclk", group_fimc_lclk_p, SRC_CAM,
+		4, 4),
+	MUX(CLK_MOUT_FIMC0_LCLK, "mout_fimc0_lclk", group_fimc_lclk_p, SRC_CAM,
+		0, 4),
+
+	/* SRC_TV */
+	MUX(CLK_MOUT_HDMI, "mout_hdmi", mout_hdmi_p, SRC_TV, 0, 1),
+
+	/* SRC_MFC */
+	MUX(CLK_MOUT_MFC, "mout_mfc", mout_mfc_p, SRC_MFC, 8, 1),
+	MUX(CLK_MOUT_MFC_1, "mout_mfc_1", group_epll_g3dpll_p, SRC_MFC, 4, 1),
+	MUX(CLK_MOUT_MFC_0, "mout_mfc_0", group_mout_mpll_user_t_p, SRC_MFC, 0,
+		1),
+
+	/* SRC_G3D */
+	MUX(CLK_MOUT_G3D, "mout_g3d", mout_g3d_p, SRC_G3D, 8, 1),
+	MUX(CLK_MOUT_G3D_1, "mout_g3d_1", group_epll_g3dpll_p, SRC_G3D, 4, 1),
+	MUX(CLK_MOUT_G3D_0, "mout_g3d_0", group_mout_mpll_user_t_p, SRC_G3D, 0,
+		1),
+
+	/* SRC_LCD */
+	MUX(CLK_MOUT_MIPI0, "mout_mipi0", group_fimc_lclk_p, SRC_LCD, 12, 4),
+	MUX(CLK_MOUT_FIMD0, "mout_fimd0", group_sclk_fimd0_p, SRC_LCD, 0, 4),
+
+	/* SRC_ISP */
+	MUX(CLK_MOUT_TSADC_ISP, "mout_tsadc_isp", group_fimc_lclk_p, SRC_ISP,
+		16, 4),
+	MUX(CLK_MOUT_UART_ISP, "mout_uart_isp", group_fimc_lclk_p, SRC_ISP,
+		12, 4),
+	MUX(CLK_MOUT_SPI1_ISP, "mout_spi1_isp", group_fimc_lclk_p, SRC_ISP,
+		8, 4),
+	MUX(CLK_MOUT_SPI0_ISP, "mout_spi0_isp", group_fimc_lclk_p, SRC_ISP,
+		4, 4),
+	MUX(CLK_MOUT_PWM_ISP, "mout_pwm_isp", group_fimc_lclk_p, SRC_ISP,
+		0, 4),
+
+	/* SRC_MAUDIO */
+	MUX(CLK_MOUT_AUDIO0, "mout_audio0", group_sclk_audio0_p, SRC_MAUDIO,
+		0, 4),
+
+	/* SRC_FSYS */
+	MUX(CLK_MOUT_TSADC, "mout_tsadc", group_sclk_p, SRC_FSYS, 28, 4),
+	MUX(CLK_MOUT_MMC2, "mout_mmc2", group_sclk_p, SRC_FSYS, 8, 4),
+	MUX(CLK_MOUT_MMC1, "mout_mmc1", group_sclk_p, SRC_FSYS, 4, 4),
+	MUX(CLK_MOUT_MMC0, "mout_mmc0", group_sclk_p, SRC_FSYS, 0, 4),
+
+	/* SRC_PERIL0 */
+	MUX(CLK_MOUT_UART3, "mout_uart3", group_sclk_p, SRC_PERIL0, 12, 4),
+	MUX(CLK_MOUT_UART2, "mout_uart2", group_sclk_p, SRC_PERIL0, 8, 4),
+	MUX(CLK_MOUT_UART1, "mout_uart1", group_sclk_p, SRC_PERIL0, 4, 4),
+	MUX(CLK_MOUT_UART0, "mout_uart0", group_sclk_p, SRC_PERIL0, 0, 4),
+
+	/* SRC_PERIL1 */
+	MUX(CLK_MOUT_SPI2, "mout_spi2", group_sclk_p, SRC_PERIL1, 24, 4),
+	MUX(CLK_MOUT_SPI1, "mout_spi1", group_sclk_p, SRC_PERIL1, 20, 4),
+	MUX(CLK_MOUT_SPI0, "mout_spi0", group_sclk_p, SRC_PERIL1, 16, 4),
+	MUX(CLK_MOUT_SPDIF, "mout_spdif", group_spdif_p, SRC_PERIL1, 8, 4),
+	MUX(CLK_MOUT_AUDIO2, "mout_audio2", group_sclk_audio2_p, SRC_PERIL1,
+		4, 4),
+	MUX(CLK_MOUT_AUDIO1, "mout_audio1", group_sclk_audio1_p, SRC_PERIL1,
+		0, 4),
+
+	/* SRC_CPU */
+	MUX(CLK_MOUT_MPLL_USER_C, "mout_mpll_user_c", mout_mpll_user_p,
+		SRC_CPU, 24, 1),
+	MUX(CLK_MOUT_HPM, "mout_hpm", mout_hpm_p, SRC_CPU, 20, 1),
+	MUX_F(CLK_MOUT_CORE, "mout_core", mout_core_p, SRC_CPU, 16, 1, 0,
+		CLK_MUX_READ_ONLY),
+	MUX_F(CLK_MOUT_APLL, "mout_apll", mout_apll_p, SRC_CPU, 0, 1,
+		CLK_SET_RATE_PARENT, 0),
+
+	/* SRC_CAM1 */
+	MUX(CLK_MOUT_PXLASYNC_CSIS1_FIMC, "mout_pxlasync_csis1",
+		group_fimc_lclk_p, SRC_CAM1, 20, 1),
+	MUX(CLK_MOUT_PXLASYNC_CSIS0_FIMC, "mout_pxlasync_csis0",
+		group_fimc_lclk_p, SRC_CAM1, 16, 1),
+	MUX(CLK_MOUT_JPEG, "mout_jpeg", mout_jpeg_p, SRC_CAM1, 8, 1),
+	MUX(CLK_MOUT_JPEG1, "mout_jpeg_1", mout_jpeg1_p, SRC_CAM1, 4, 1),
+	MUX(CLK_MOUT_JPEG0, "mout_jpeg_0", group_mout_mpll_user_t_p, SRC_CAM1,
+		0, 1),
+
+	/* SRC_TOP_ISP0 */
+	MUX(CLK_MOUT_ACLK_ISP0_300, "mout_aclk_isp0_300",
+		group_aclk_isp0_300_p, SRC_TOP_ISP0, 8, 1),
+	MUX(CLK_MOUT_ACLK_ISP0_400, "mout_aclk_isp0_400_user",
+		group_aclk_isp0_400_user_p, SRC_TOP_ISP0, 4, 1),
+	MUX(CLK_MOUT_ACLK_ISP0_300_USER, "mout_aclk_isp0_300_user",
+		group_aclk_isp0_300_user_p, SRC_TOP_ISP0, 0, 1),
+
+	/* SRC_TOP_ISP1 */
+	MUX(CLK_MOUT_ACLK_ISP1_300, "mout_aclk_isp1_300",
+		group_aclk_isp0_300_p, SRC_TOP_ISP1, 4, 1),
+	MUX(CLK_MOUT_ACLK_ISP1_300_USER, "mout_aclk_isp1_300_user",
+		group_aclk_isp1_300_user_p, SRC_TOP_ISP1, 0, 1),
+};
+
+static struct samsung_div_clock exynos4415_div_clks[] __initdata = {
+	/*
+	 * NOTE: Following table is sorted by register address in ascending
+	 * order and then bitfield shift in descending order, as it is done
+	 * in the User's Manual. When adding new entries, please make sure
+	 * that the order is preserved, to avoid merge conflicts and make
+	 * further work with defined data easier.
+	 */
+
+	/* DIV_LEFTBUS */
+	DIV(CLK_DIV_GPL, "div_gpl", "div_gdl", DIV_LEFTBUS, 4, 3),
+	DIV(CLK_DIV_GDL, "div_gdl", "mout_gdl", DIV_LEFTBUS, 0, 4),
+
+	/* DIV_RIGHTBUS */
+	DIV(CLK_DIV_GPR, "div_gpr", "div_gdr", DIV_RIGHTBUS, 4, 3),
+	DIV(CLK_DIV_GDR, "div_gdr", "mout_gdr", DIV_RIGHTBUS, 0, 4),
+
+	/* DIV_TOP */
+	DIV(CLK_DIV_ACLK_400_MCUISP, "div_aclk_400_mcuisp",
+		"mout_aclk_400_mcuisp", DIV_TOP, 24, 3),
+	DIV(CLK_DIV_EBI, "div_ebi", "mout_ebi_1", DIV_TOP, 16, 3),
+	DIV(CLK_DIV_ACLK_200, "div_aclk_200", "mout_aclk_200", DIV_TOP, 12, 3),
+	DIV(CLK_DIV_ACLK_160, "div_aclk_160", "mout_aclk_160", DIV_TOP, 8, 3),
+	DIV(CLK_DIV_ACLK_100, "div_aclk_100", "mout_aclk_100", DIV_TOP, 4, 4),
+	DIV(CLK_DIV_ACLK_266, "div_aclk_266", "mout_aclk_266", DIV_TOP, 0, 3),
+
+	/* DIV_CAM */
+	DIV(CLK_DIV_CSIS1, "div_csis1", "mout_csis1", DIV_CAM, 28, 4),
+	DIV(CLK_DIV_CSIS0, "div_csis0", "mout_csis0", DIV_CAM, 24, 4),
+	DIV(CLK_DIV_CAM1, "div_cam1", "mout_cam1", DIV_CAM, 20, 4),
+	DIV(CLK_DIV_FIMC3_LCLK, "div_fimc3_lclk", "mout_fimc3_lclk", DIV_CAM,
+		12, 4),
+	DIV(CLK_DIV_FIMC2_LCLK, "div_fimc2_lclk", "mout_fimc2_lclk", DIV_CAM,
+		8, 4),
+	DIV(CLK_DIV_FIMC1_LCLK, "div_fimc1_lclk", "mout_fimc1_lclk", DIV_CAM,
+		4, 4),
+	DIV(CLK_DIV_FIMC0_LCLK, "div_fimc0_lclk", "mout_fimc0_lclk", DIV_CAM,
+		0, 4),
+
+	/* DIV_TV */
+	DIV(CLK_DIV_TV_BLK, "div_tv_blk", "mout_g3d_pll", DIV_TV, 0, 4),
+
+	/* DIV_MFC */
+	DIV(CLK_DIV_MFC, "div_mfc", "mout_mfc", DIV_MFC, 0, 4),
+
+	/* DIV_G3D */
+	DIV(CLK_DIV_G3D, "div_g3d", "mout_g3d", DIV_G3D, 0, 4),
+
+	/* DIV_LCD */
+	DIV_F(CLK_DIV_MIPI0_PRE, "div_mipi0_pre", "div_mipi0", DIV_LCD, 20, 4,
+		CLK_SET_RATE_PARENT, 0),
+	DIV(CLK_DIV_MIPI0, "div_mipi0", "mout_mipi0", DIV_LCD, 16, 4),
+	DIV(CLK_DIV_FIMD0, "div_fimd0", "mout_fimd0", DIV_LCD, 0, 4),
+
+	/* DIV_ISP */
+	DIV(CLK_DIV_UART_ISP, "div_uart_isp", "mout_uart_isp", DIV_ISP, 28, 4),
+	DIV_F(CLK_DIV_SPI1_ISP_PRE, "div_spi1_isp_pre", "div_spi1_isp",
+		DIV_ISP, 20, 8, CLK_SET_RATE_PARENT, 0),
+	DIV(CLK_DIV_SPI1_ISP, "div_spi1_isp", "mout_spi1_isp", DIV_ISP, 16, 4),
+	DIV_F(CLK_DIV_SPI0_ISP_PRE, "div_spi0_isp_pre", "div_spi0_isp",
+		DIV_ISP, 8, 8, CLK_SET_RATE_PARENT, 0),
+	DIV(CLK_DIV_SPI0_ISP, "div_spi0_isp", "mout_spi0_isp", DIV_ISP, 4, 4),
+	DIV(CLK_DIV_PWM_ISP, "div_pwm_isp", "mout_pwm_isp", DIV_ISP, 0, 4),
+
+	/* DIV_MAUDIO */
+	DIV(CLK_DIV_PCM0, "div_pcm0", "div_audio0", DIV_MAUDIO, 4, 8),
+	DIV(CLK_DIV_AUDIO0, "div_audio0", "mout_audio0", DIV_MAUDIO, 0, 4),
+
+	/* DIV_FSYS0 */
+	DIV_F(CLK_DIV_TSADC_PRE, "div_tsadc_pre", "div_tsadc", DIV_FSYS0, 8, 8,
+		CLK_SET_RATE_PARENT, 0),
+	DIV(CLK_DIV_TSADC, "div_tsadc", "mout_tsadc", DIV_FSYS0, 0, 4),
+
+	/* DIV_FSYS1 */
+	DIV_F(CLK_DIV_MMC1_PRE, "div_mmc1_pre", "div_mmc1", DIV_FSYS1, 24, 8,
+		CLK_SET_RATE_PARENT, 0),
+	DIV(CLK_DIV_MMC1, "div_mmc1", "mout_mmc1", DIV_FSYS1, 16, 4),
+	DIV_F(CLK_DIV_MMC0_PRE, "div_mmc0_pre", "div_mmc0", DIV_FSYS1, 8, 8,
+		CLK_SET_RATE_PARENT, 0),
+	DIV(CLK_DIV_MMC0, "div_mmc0", "mout_mmc0", DIV_FSYS1, 0, 4),
+
+	/* DIV_FSYS2 */
+	DIV_F(CLK_DIV_MMC2_PRE, "div_mmc2_pre", "div_mmc2", DIV_FSYS2, 8, 8,
+		CLK_SET_RATE_PARENT, 0),
+	DIV_F(CLK_DIV_MMC2_PRE, "div_mmc2", "mout_mmc2", DIV_FSYS2, 0, 4,
+		CLK_SET_RATE_PARENT, 0),
+
+	/* DIV_PERIL0 */
+	DIV(CLK_DIV_UART3, "div_uart3", "mout_uart3", DIV_PERIL0, 12, 4),
+	DIV(CLK_DIV_UART2, "div_uart2", "mout_uart2", DIV_PERIL0, 8, 4),
+	DIV(CLK_DIV_UART1, "div_uart1", "mout_uart1", DIV_PERIL0, 4, 4),
+	DIV(CLK_DIV_UART0, "div_uart0", "mout_uart0", DIV_PERIL0, 0, 4),
+
+	/* DIV_PERIL1 */
+	DIV_F(CLK_DIV_SPI1_PRE, "div_spi1_pre", "div_spi1", DIV_PERIL1, 24, 8,
+		CLK_SET_RATE_PARENT, 0),
+	DIV(CLK_DIV_SPI1, "div_spi1", "mout_spi1", DIV_PERIL1, 16, 4),
+	DIV_F(CLK_DIV_SPI0_PRE, "div_spi0_pre", "div_spi0", DIV_PERIL1, 8, 8,
+		CLK_SET_RATE_PARENT, 0),
+	DIV(CLK_DIV_SPI0, "div_spi0", "mout_spi0", DIV_PERIL1, 0, 4),
+
+	/* DIV_PERIL2 */
+	DIV_F(CLK_DIV_SPI2_PRE, "div_spi2_pre", "div_spi2", DIV_PERIL2, 8, 8,
+		CLK_SET_RATE_PARENT, 0),
+	DIV(CLK_DIV_SPI2, "div_spi2", "mout_spi2", DIV_PERIL2, 0, 4),
+
+	/* DIV_PERIL4 */
+	DIV(CLK_DIV_PCM2, "div_pcm2", "div_audio2", DIV_PERIL4, 20, 8),
+	DIV(CLK_DIV_AUDIO2, "div_audio2", "mout_audio2", DIV_PERIL4, 16, 4),
+	DIV(CLK_DIV_PCM1, "div_pcm1", "div_audio1", DIV_PERIL4, 20, 8),
+	DIV(CLK_DIV_AUDIO1, "div_audio1", "mout_audio1", DIV_PERIL4, 0, 4),
+
+	/* DIV_PERIL5 */
+	DIV(CLK_DIV_I2S1, "div_i2s1", "div_audio1", DIV_PERIL5, 0, 6),
+
+	/* DIV_CAM1 */
+	DIV(CLK_DIV_PXLASYNC_CSIS1_FIMC, "div_pxlasync_csis1_fimc",
+		"mout_pxlasync_csis1", DIV_CAM1, 24, 4),
+	DIV(CLK_DIV_PXLASYNC_CSIS0_FIMC, "div_pxlasync_csis0_fimc",
+		"mout_pxlasync_csis0", DIV_CAM1, 20, 4),
+	DIV(CLK_DIV_JPEG, "div_jpeg", "mout_jpeg", DIV_CAM1, 0, 4),
+
+	/* DIV_CPU0 */
+	DIV(CLK_DIV_CORE2, "div_core2", "div_core", DIV_CPU0, 28, 3),
+	DIV_F(CLK_DIV_APLL, "div_apll", "mout_apll", DIV_CPU0, 24, 3,
+			CLK_GET_RATE_NOCACHE, CLK_DIVIDER_READ_ONLY),
+	DIV(CLK_DIV_PCLK_DBG, "div_pclk_dbg", "div_core2", DIV_CPU0, 20, 3),
+	DIV(CLK_DIV_ATB, "div_atb", "div_core2", DIV_CPU0, 16, 3),
+	DIV(CLK_DIV_PERIPH, "div_periph", "div_core2", DIV_CPU0, 12, 3),
+	DIV(CLK_DIV_COREM1, "div_corem1", "div_core2", DIV_CPU0, 8, 3),
+	DIV(CLK_DIV_COREM0, "div_corem0", "div_core2", DIV_CPU0, 4, 3),
+	DIV_F(CLK_DIV_CORE, "div_core", "mout_core", DIV_CPU0, 0, 3,
+		CLK_GET_RATE_NOCACHE, CLK_DIVIDER_READ_ONLY),
+
+	/* DIV_CPU1 */
+	DIV(CLK_DIV_HPM, "div_hpm", "div_copy", DIV_CPU1, 4, 3),
+	DIV(CLK_DIV_COPY, "div_copy", "mout_hpm", DIV_CPU1, 0, 3),
+};
+
+static struct samsung_gate_clock exynos4415_gate_clks[] __initdata = {
+	/*
+	 * NOTE: Following table is sorted by register address in ascending
+	 * order and then bitfield shift in descending order, as it is done
+	 * in the User's Manual. When adding new entries, please make sure
+	 * that the order is preserved, to avoid merge conflicts and make
+	 * further work with defined data easier.
+	 */
+
+	/* GATE_IP_LEFTBUS */
+	GATE(CLK_ASYNC_G3D, "async_g3d", "div_aclk_100", GATE_IP_LEFTBUS, 6,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_ASYNC_MFCL, "async_mfcl", "div_aclk_100", GATE_IP_LEFTBUS, 4,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_ASYNC_TVX, "async_tvx", "div_aclk_100", GATE_IP_LEFTBUS, 3,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_PPMULEFT, "ppmuleft", "div_aclk_100", GATE_IP_LEFTBUS, 1,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_GPIO_LEFT, "gpio_left", "div_aclk_100", GATE_IP_LEFTBUS, 0,
+		CLK_IGNORE_UNUSED, 0),
+
+	/* GATE_IP_IMAGE */
+	GATE(CLK_PPMUIMAGE, "ppmuimage", "div_aclk_100", GATE_IP_IMAGE,
+		9, 0, 0),
+	GATE(CLK_QEMDMA2, "qe_mdma2", "div_aclk_100", GATE_IP_IMAGE,
+		8, 0, 0),
+	GATE(CLK_QEROTATOR, "qe_rotator", "div_aclk_100", GATE_IP_IMAGE,
+		7, 0, 0),
+	GATE(CLK_SMMUMDMA2, "smmu_mdam2", "div_aclk_100", GATE_IP_IMAGE,
+		5, 0, 0),
+	GATE(CLK_SMMUROTATOR, "smmu_rotator", "div_aclk_100", GATE_IP_IMAGE,
+		4, 0, 0),
+	GATE(CLK_MDMA2, "mdma2", "div_aclk_100", GATE_IP_IMAGE, 2, 0, 0),
+	GATE(CLK_ROTATOR, "rotator", "div_aclk_100", GATE_IP_IMAGE, 1, 0, 0),
+
+	/* GATE_IP_RIGHTBUS */
+	GATE(CLK_ASYNC_ISPMX, "async_ispmx", "div_aclk_100",
+		GATE_IP_RIGHTBUS, 9, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_ASYNC_MAUDIOX, "async_maudiox", "div_aclk_100",
+		GATE_IP_RIGHTBUS, 7, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_ASYNC_MFCR, "async_mfcr", "div_aclk_100",
+		GATE_IP_RIGHTBUS, 6, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_ASYNC_FSYSD, "async_fsysd", "div_aclk_100",
+		GATE_IP_RIGHTBUS, 5, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_ASYNC_LCD0X, "async_lcd0x", "div_aclk_100",
+		GATE_IP_RIGHTBUS, 3, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_ASYNC_CAMX, "async_camx", "div_aclk_100",
+		GATE_IP_RIGHTBUS, 2, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_PPMURIGHT, "ppmuright", "div_aclk_100",
+		GATE_IP_RIGHTBUS, 1, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_GPIO_RIGHT, "gpio_right", "div_aclk_100",
+		GATE_IP_RIGHTBUS, 0, CLK_IGNORE_UNUSED, 0),
+
+	/* GATE_IP_PERIR */
+	GATE(CLK_ANTIRBK_APBIF, "antirbk_apbif", "div_aclk_100",
+		GATE_IP_PERIR, 24, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_EFUSE_WRITER_APBIF, "efuse_writer_apbif", "div_aclk_100",
+		GATE_IP_PERIR, 23, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_MONOCNT, "monocnt", "div_aclk_100", GATE_IP_PERIR, 22,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_TZPC6, "tzpc6", "div_aclk_100", GATE_IP_PERIR, 21,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_PROVISIONKEY1, "provisionkey1", "div_aclk_100",
+		GATE_IP_PERIR, 20, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_PROVISIONKEY0, "provisionkey0", "div_aclk_100",
+		GATE_IP_PERIR, 19, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_CMU_ISPPART, "cmu_isppart", "div_aclk_100", GATE_IP_PERIR, 18,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_TMU_APBIF, "tmu_apbif", "div_aclk_100",
+		GATE_IP_PERIR, 17, 0, 0),
+	GATE(CLK_KEYIF, "keyif", "div_aclk_100", GATE_IP_PERIR, 16, 0, 0),
+	GATE(CLK_RTC, "rtc", "div_aclk_100", GATE_IP_PERIR, 15, 0, 0),
+	GATE(CLK_WDT, "wdt", "div_aclk_100", GATE_IP_PERIR, 14, 0, 0),
+	GATE(CLK_MCT, "mct", "div_aclk_100", GATE_IP_PERIR, 13, 0, 0),
+	GATE(CLK_SECKEY, "seckey", "div_aclk_100", GATE_IP_PERIR, 12,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_HDMI_CEC, "hdmi_cec", "div_aclk_100", GATE_IP_PERIR, 11,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_TZPC5, "tzpc5", "div_aclk_100", GATE_IP_PERIR, 10,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_TZPC4, "tzpc4", "div_aclk_100", GATE_IP_PERIR, 9,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_TZPC3, "tzpc3", "div_aclk_100", GATE_IP_PERIR, 8,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_TZPC2, "tzpc2", "div_aclk_100", GATE_IP_PERIR, 7,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_TZPC1, "tzpc1", "div_aclk_100", GATE_IP_PERIR, 6,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_TZPC0, "tzpc0", "div_aclk_100", GATE_IP_PERIR, 5,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_CMU_COREPART, "cmu_corepart", "div_aclk_100", GATE_IP_PERIR, 4,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_CMU_TOPPART, "cmu_toppart", "div_aclk_100", GATE_IP_PERIR, 3,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_PMU_APBIF, "pmu_apbif", "div_aclk_100", GATE_IP_PERIR, 2,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_SYSREG, "sysreg", "div_aclk_100", GATE_IP_PERIR, 1,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_CHIP_ID, "chip_id", "div_aclk_100", GATE_IP_PERIR, 0,
+		CLK_IGNORE_UNUSED, 0),
+
+	/* GATE_SCLK_CAM - non-completed */
+	GATE(CLK_SCLK_PXLAYSNC_CSIS1_FIMC, "sclk_pxlasync_csis1_fimc",
+		"div_pxlasync_csis1_fimc", GATE_SCLK_CAM, 11,
+		CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_PXLAYSNC_CSIS0_FIMC, "sclk_pxlasync_csis0_fimc",
+		"div_pxlasync_csis0_fimc", GATE_SCLK_CAM,
+		10, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_JPEG, "sclk_jpeg", "div_jpeg",
+		GATE_SCLK_CAM, 8, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_CSIS1, "sclk_csis1", "div_csis1",
+		GATE_SCLK_CAM, 7, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_CSIS0, "sclk_csis0", "div_csis0",
+		GATE_SCLK_CAM, 6, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_CAM1, "sclk_cam1", "div_cam1",
+		GATE_SCLK_CAM, 5, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_FIMC3_LCLK, "sclk_fimc3_lclk", "div_fimc3_lclk",
+		GATE_SCLK_CAM, 3, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_FIMC2_LCLK, "sclk_fimc2_lclk", "div_fimc2_lclk",
+		GATE_SCLK_CAM, 2, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_FIMC1_LCLK, "sclk_fimc1_lclk", "div_fimc1_lclk",
+		GATE_SCLK_CAM, 1, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_FIMC0_LCLK, "sclk_fimc0_lclk", "div_fimc0_lclk",
+		GATE_SCLK_CAM, 0, CLK_SET_RATE_PARENT, 0),
+
+	/* GATE_SCLK_TV */
+	GATE(CLK_SCLK_PIXEL, "sclk_pixel", "div_tv_blk",
+		GATE_SCLK_TV, 3, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_HDMI, "sclk_hdmi", "mout_hdmi",
+		GATE_SCLK_TV, 2, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_MIXER, "sclk_mixer", "div_tv_blk",
+		GATE_SCLK_TV, 0, CLK_SET_RATE_PARENT, 0),
+
+	/* GATE_SCLK_MFC */
+	GATE(CLK_SCLK_MFC, "sclk_mfc", "div_mfc",
+		GATE_SCLK_MFC, 0, CLK_SET_RATE_PARENT, 0),
+
+	/* GATE_SCLK_G3D */
+	GATE(CLK_SCLK_G3D, "sclk_g3d", "div_g3d",
+		GATE_SCLK_G3D, 0, CLK_SET_RATE_PARENT, 0),
+
+	/* GATE_SCLK_LCD */
+	GATE(CLK_SCLK_MIPIDPHY4L, "sclk_mipidphy4l", "div_mipi0",
+		GATE_SCLK_LCD, 4, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_MIPI0, "sclk_mipi0", "div_mipi0_pre",
+		GATE_SCLK_LCD, 3, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_MDNIE0, "sclk_mdnie0", "div_fimd0",
+		GATE_SCLK_LCD, 1, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_FIMD0, "sclk_fimd0", "div_fimd0",
+		GATE_SCLK_LCD, 0, CLK_SET_RATE_PARENT, 0),
+
+	/* GATE_SCLK_MAUDIO */
+	GATE(CLK_SCLK_PCM0, "sclk_pcm0", "div_pcm0",
+		GATE_SCLK_MAUDIO, 1, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_AUDIO0, "sclk_audio0", "div_audio0",
+		GATE_SCLK_MAUDIO, 0, CLK_SET_RATE_PARENT, 0),
+
+	/* GATE_SCLK_FSYS */
+	GATE(CLK_SCLK_TSADC, "sclk_tsadc", "div_tsadc_pre",
+		GATE_SCLK_FSYS, 9, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_EBI, "sclk_ebi", "div_ebi",
+		GATE_SCLK_FSYS, 6, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_MMC2, "sclk_mmc2", "div_mmc2_pre",
+		GATE_SCLK_FSYS, 2, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_MMC1, "sclk_mmc1", "div_mmc1_pre",
+		GATE_SCLK_FSYS, 1, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_MMC0, "sclk_mmc0", "div_mmc0_pre",
+		GATE_SCLK_FSYS, 0, CLK_SET_RATE_PARENT, 0),
+
+	/* GATE_SCLK_PERIL */
+	GATE(CLK_SCLK_I2S, "sclk_i2s1", "div_i2s1",
+		GATE_SCLK_PERIL, 18, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_PCM2, "sclk_pcm2", "div_pcm2",
+		GATE_SCLK_PERIL, 16, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_PCM1, "sclk_pcm1", "div_pcm1",
+		GATE_SCLK_PERIL, 15, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_AUDIO2, "sclk_audio2", "div_audio2",
+		GATE_SCLK_PERIL, 14, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_AUDIO1, "sclk_audio1", "div_audio1",
+		GATE_SCLK_PERIL, 13, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_SPDIF, "sclk_spdif", "mout_spdif",
+		GATE_SCLK_PERIL, 10, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_SPI2, "sclk_spi2", "div_spi2_pre",
+		GATE_SCLK_PERIL, 8, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_SPI1, "sclk_spi1", "div_spi1_pre",
+		GATE_SCLK_PERIL, 7, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_SPI0, "sclk_spi0", "div_spi0_pre",
+		GATE_SCLK_PERIL, 6, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_UART3, "sclk_uart3", "div_uart3",
+		GATE_SCLK_PERIL, 3, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_UART2, "sclk_uart2", "div_uart2",
+		GATE_SCLK_PERIL, 2, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_UART1, "sclk_uart1", "div_uart1",
+		GATE_SCLK_PERIL, 1, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_UART0, "sclk_uart0", "div_uart0",
+		GATE_SCLK_PERIL, 0, CLK_SET_RATE_PARENT, 0),
+
+	/* GATE_IP_CAM */
+	GATE(CLK_SMMUFIMC_LITE2, "smmufimc_lite2", "div_aclk_160", GATE_IP_CAM,
+		22, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_FIMC_LITE2, "fimc_lite2", "div_aclk_160", GATE_IP_CAM,
+		20, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_PIXELASYNCM1, "pixelasyncm1", "div_aclk_160", GATE_IP_CAM,
+		18, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_PIXELASYNCM0, "pixelasyncm0", "div_aclk_160", GATE_IP_CAM,
+		17, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_PPMUCAMIF, "ppmucamif", "div_aclk_160", GATE_IP_CAM,
+		16, CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_SMMUJPEG, "smmujpeg", "div_aclk_160", GATE_IP_CAM, 11, 0, 0),
+	GATE(CLK_SMMUFIMC3, "smmufimc3", "div_aclk_160", GATE_IP_CAM, 10, 0, 0),
+	GATE(CLK_SMMUFIMC2, "smmufimc2", "div_aclk_160", GATE_IP_CAM, 9, 0, 0),
+	GATE(CLK_SMMUFIMC1, "smmufimc1", "div_aclk_160", GATE_IP_CAM, 8, 0, 0),
+	GATE(CLK_SMMUFIMC0, "smmufimc0", "div_aclk_160", GATE_IP_CAM, 7, 0, 0),
+	GATE(CLK_JPEG, "jpeg", "div_aclk_160", GATE_IP_CAM, 6, 0, 0),
+	GATE(CLK_CSIS1, "csis1", "div_aclk_160", GATE_IP_CAM, 5, 0, 0),
+	GATE(CLK_CSIS0, "csis0", "div_aclk_160", GATE_IP_CAM, 4, 0, 0),
+	GATE(CLK_FIMC3, "fimc3", "div_aclk_160", GATE_IP_CAM, 3, 0, 0),
+	GATE(CLK_FIMC2, "fimc2", "div_aclk_160", GATE_IP_CAM, 2, 0, 0),
+	GATE(CLK_FIMC1, "fimc1", "div_aclk_160", GATE_IP_CAM, 1, 0, 0),
+	GATE(CLK_FIMC0, "fimc0", "div_aclk_160", GATE_IP_CAM, 0, 0, 0),
+
+	/* GATE_IP_TV */
+	GATE(CLK_PPMUTV, "ppmutv", "div_aclk_100", GATE_IP_TV, 5, 0, 0),
+	GATE(CLK_SMMUTV, "smmutv", "div_aclk_100", GATE_IP_TV, 4, 0, 0),
+	GATE(CLK_HDMI, "hdmi", "div_aclk_100", GATE_IP_TV, 3, 0, 0),
+	GATE(CLK_MIXER, "mixer", "div_aclk_100", GATE_IP_TV, 1, 0, 0),
+	GATE(CLK_VP, "vp", "div_aclk_100", GATE_IP_TV, 0, 0, 0),
+
+	/* GATE_IP_MFC */
+	GATE(CLK_PPMUMFC_R, "ppmumfc_r", "div_aclk_200", GATE_IP_MFC, 4,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_PPMUMFC_L, "ppmumfc_l", "div_aclk_200", GATE_IP_MFC, 3,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_SMMUMFC_R, "smmumfc_r", "div_aclk_200", GATE_IP_MFC, 2, 0, 0),
+	GATE(CLK_SMMUMFC_L, "smmumfc_l", "div_aclk_200", GATE_IP_MFC, 1, 0, 0),
+	GATE(CLK_MFC, "mfc", "div_aclk_200", GATE_IP_MFC, 0, 0, 0),
+
+	/* GATE_IP_G3D */
+	GATE(CLK_PPMUG3D, "ppmug3d", "div_aclk_200", GATE_IP_G3D, 1,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_G3D, "g3d", "div_aclk_200", GATE_IP_G3D, 0, 0, 0),
+
+	/* GATE_IP_LCD */
+	GATE(CLK_PPMULCD0, "ppmulcd0", "div_aclk_160", GATE_IP_LCD, 5,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_SMMUFIMD0, "smmufimd0", "div_aclk_160", GATE_IP_LCD, 4, 0, 0),
+	GATE(CLK_DSIM0, "dsim0", "div_aclk_160", GATE_IP_LCD, 3, 0, 0),
+	GATE(CLK_SMIES, "smies", "div_aclk_160", GATE_IP_LCD, 2, 0, 0),
+	GATE(CLK_MIE0, "mie0", "div_aclk_160", GATE_IP_LCD, 1, 0, 0),
+	GATE(CLK_FIMD0, "fimd0", "div_aclk_160", GATE_IP_LCD, 0, 0, 0),
+
+	/* GATE_IP_FSYS */
+	GATE(CLK_TSADC, "tsadc", "div_aclk_200", GATE_IP_FSYS, 20, 0, 0),
+	GATE(CLK_PPMUFILE, "ppmufile", "div_aclk_200", GATE_IP_FSYS, 17,
+		CLK_IGNORE_UNUSED, 0),
+	GATE(CLK_NFCON, "nfcon", "div_aclk_200", GATE_IP_FSYS, 16, 0, 0),
+	GATE(CLK_USBDEVICE, "usbdevice", "div_aclk_200", GATE_IP_FSYS, 13,
+		0, 0),
+	GATE(CLK_USBHOST, "usbhost", "div_aclk_200", GATE_IP_FSYS, 12, 0, 0),
+	GATE(CLK_SROMC, "sromc", "div_aclk_200", GATE_IP_FSYS, 11, 0, 0),
+	GATE(CLK_SDMMC2, "sdmmc2", "div_aclk_200", GATE_IP_FSYS, 7, 0, 0),
+	GATE(CLK_SDMMC1, "sdmmc1", "div_aclk_200", GATE_IP_FSYS, 6, 0, 0),
+	GATE(CLK_SDMMC0, "sdmmc0", "div_aclk_200", GATE_IP_FSYS, 5, 0, 0),
+	GATE(CLK_PDMA1, "pdma1", "div_aclk_200", GATE_IP_FSYS, 1, 0, 0),
+	GATE(CLK_PDMA0, "pdma0", "div_aclk_200", GATE_IP_FSYS, 0, 0, 0),
+
+	/* GATE_IP_PERIL */
+	GATE(CLK_SPDIF, "spdif", "div_aclk_100", GATE_IP_PERIL, 26, 0, 0),
+	GATE(CLK_PWM, "pwm", "div_aclk_100", GATE_IP_PERIL, 24, 0, 0),
+	GATE(CLK_PCM2, "pcm2", "div_aclk_100", GATE_IP_PERIL, 23, 0, 0),
+	GATE(CLK_PCM1, "pcm1", "div_aclk_100", GATE_IP_PERIL, 22, 0, 0),
+	GATE(CLK_I2S1, "i2s1", "div_aclk_100", GATE_IP_PERIL, 20, 0, 0),
+	GATE(CLK_SPI2, "spi2", "div_aclk_100", GATE_IP_PERIL, 18, 0, 0),
+	GATE(CLK_SPI1, "spi1", "div_aclk_100", GATE_IP_PERIL, 17, 0, 0),
+	GATE(CLK_SPI0, "spi0", "div_aclk_100", GATE_IP_PERIL, 16, 0, 0),
+	GATE(CLK_I2CHDMI, "i2chdmi", "div_aclk_100", GATE_IP_PERIL, 14, 0, 0),
+	GATE(CLK_I2C7, "i2c7", "div_aclk_100", GATE_IP_PERIL, 13, 0, 0),
+	GATE(CLK_I2C6, "i2c6", "div_aclk_100", GATE_IP_PERIL, 12, 0, 0),
+	GATE(CLK_I2C5, "i2c5", "div_aclk_100", GATE_IP_PERIL, 11, 0, 0),
+	GATE(CLK_I2C4, "i2c4", "div_aclk_100", GATE_IP_PERIL, 10, 0, 0),
+	GATE(CLK_I2C3, "i2c3", "div_aclk_100", GATE_IP_PERIL, 9, 0, 0),
+	GATE(CLK_I2C2, "i2c2", "div_aclk_100", GATE_IP_PERIL, 8, 0, 0),
+	GATE(CLK_I2C1, "i2c1", "div_aclk_100", GATE_IP_PERIL, 7, 0, 0),
+	GATE(CLK_I2C0, "i2c0", "div_aclk_100", GATE_IP_PERIL, 6, 0, 0),
+	GATE(CLK_UART3, "uart3", "div_aclk_100", GATE_IP_PERIL, 3, 0, 0),
+	GATE(CLK_UART2, "uart2", "div_aclk_100", GATE_IP_PERIL, 2, 0, 0),
+	GATE(CLK_UART1, "uart1", "div_aclk_100", GATE_IP_PERIL, 1, 0, 0),
+	GATE(CLK_UART0, "uart0", "div_aclk_100", GATE_IP_PERIL, 0, 0, 0),
+};
+
+/*
+ * APLL & MPLL & BPLL & ISP_PLL & DISP_PLL & G3D_PLL
+ */
+static struct samsung_pll_rate_table exynos4415_pll_rates[] = {
+	PLL_35XX_RATE(1600000000, 400, 3,  1),
+	PLL_35XX_RATE(1500000000, 250, 2,  1),
+	PLL_35XX_RATE(1400000000, 175, 3,  0),
+	PLL_35XX_RATE(1300000000, 325, 3,  1),
+	PLL_35XX_RATE(1200000000, 400, 4,  1),
+	PLL_35XX_RATE(1100000000, 275, 3,  1),
+	PLL_35XX_RATE(1066000000, 533, 6,  1),
+	PLL_35XX_RATE(1000000000, 250, 3,  1),
+	PLL_35XX_RATE(960000000,  320, 4,  1),
+	PLL_35XX_RATE(900000000,  300, 4,  1),
+	PLL_35XX_RATE(850000000,  425, 6,  1),
+	PLL_35XX_RATE(800000000,  200, 3,  1),
+	PLL_35XX_RATE(700000000,  175, 3,  1),
+	PLL_35XX_RATE(667000000,  667, 12, 1),
+	PLL_35XX_RATE(600000000,  400, 4,  2),
+	PLL_35XX_RATE(550000000,  275, 3,  2),
+	PLL_35XX_RATE(533000000,  533, 6,  2),
+	PLL_35XX_RATE(520000000,  260, 3,  2),
+	PLL_35XX_RATE(500000000,  250, 3,  2),
+	PLL_35XX_RATE(440000000,  220, 3,  2),
+	PLL_35XX_RATE(400000000,  200, 3,  2),
+	PLL_35XX_RATE(350000000,  175, 3,  2),
+	PLL_35XX_RATE(300000000,  300, 3,  3),
+	PLL_35XX_RATE(266000000,  266, 3,  3),
+	PLL_35XX_RATE(200000000,  200, 3,  3),
+	PLL_35XX_RATE(160000000,  160, 3,  3),
+	PLL_35XX_RATE(100000000,  200, 3,  4),
+	{ /* sentinel */ }
+};
+
+/* EPLL */
+static struct samsung_pll_rate_table exynos4415_epll_rates[] = {
+	PLL_36XX_RATE(800000000, 200, 3, 1,     0),
+	PLL_36XX_RATE(288000000,  96, 2, 2,     0),
+	PLL_36XX_RATE(192000000, 128, 2, 3,     0),
+	PLL_36XX_RATE(144000000,  96, 2, 3,     0),
+	PLL_36XX_RATE(96000000,  128, 2, 4,     0),
+	PLL_36XX_RATE(84000000,  112, 2, 4,     0),
+	PLL_36XX_RATE(80750011,  107, 2, 4, 43691),
+	PLL_36XX_RATE(73728004,   98, 2, 4, 19923),
+	PLL_36XX_RATE(67987602,  271, 3, 5, 62285),
+	PLL_36XX_RATE(65911004,  175, 2, 5, 49982),
+	PLL_36XX_RATE(50000000,  200, 3, 5,     0),
+	PLL_36XX_RATE(49152003,  131, 2, 5,  4719),
+	PLL_36XX_RATE(48000000,  128, 2, 5,     0),
+	PLL_36XX_RATE(45250000,  181, 3, 5,     0),
+	{ /* sentinel */ }
+};
+
+static struct samsung_pll_clock exynos4415_plls[nr_plls] __initdata = {
+	[apll] = PLL(pll_35xx, CLK_FOUT_APLL, "fout_apll", "fin_pll",
+			APLL_LOCK, APLL_CON0, NULL),
+	[epll] = PLL(pll_36xx, CLK_FOUT_EPLL, "fout_epll", "fin_pll",
+			EPLL_LOCK, EPLL_CON0, NULL),
+	[g3d_pll] = PLL(pll_35xx, CLK_FOUT_G3D_PLL, "fout_g3d_pll",
+			"mout_g3d_pllsrc", G3D_PLL_LOCK, G3D_PLL_CON0, NULL),
+	[isp_pll] = PLL(pll_35xx, CLK_FOUT_ISP_PLL, "fout_isp_pll", "fin_pll",
+			ISP_PLL_LOCK, ISP_PLL_CON0, NULL),
+	[disp_pll] = PLL(pll_35xx, CLK_FOUT_DISP_PLL, "fout_disp_pll",
+			"fin_pll", DISP_PLL_LOCK, DISP_PLL_CON0, NULL),
+};
+
+static void __init exynos4415_cmu_init(struct device_node *np)
+{
+	void __iomem *reg_base;
+
+	reg_base = of_iomap(np, 0);
+	if (!reg_base)
+		panic("%s: failed to map registers\n", __func__);
+
+	exynos4415_ctx = samsung_clk_init(np, reg_base, CLK_NR_CLKS);
+	if (!exynos4415_ctx)
+		panic("%s: unable to allocate context.\n", __func__);
+
+	exynos4415_plls[apll].rate_table = exynos4415_pll_rates;
+	exynos4415_plls[epll].rate_table = exynos4415_epll_rates;
+	exynos4415_plls[g3d_pll].rate_table = exynos4415_pll_rates;
+	exynos4415_plls[isp_pll].rate_table = exynos4415_pll_rates;
+	exynos4415_plls[disp_pll].rate_table = exynos4415_pll_rates;
+
+	samsung_clk_register_fixed_factor(exynos4415_ctx,
+				exynos4415_fixed_factor_clks,
+				ARRAY_SIZE(exynos4415_fixed_factor_clks));
+	samsung_clk_register_fixed_rate(exynos4415_ctx,
+				exynos4415_fixed_rate_clks,
+				ARRAY_SIZE(exynos4415_fixed_rate_clks));
+
+	samsung_clk_register_pll(exynos4415_ctx, exynos4415_plls,
+				ARRAY_SIZE(exynos4415_plls), reg_base);
+	samsung_clk_register_mux(exynos4415_ctx, exynos4415_mux_clks,
+				ARRAY_SIZE(exynos4415_mux_clks));
+	samsung_clk_register_div(exynos4415_ctx, exynos4415_div_clks,
+				ARRAY_SIZE(exynos4415_div_clks));
+	samsung_clk_register_gate(exynos4415_ctx, exynos4415_gate_clks,
+				ARRAY_SIZE(exynos4415_gate_clks));
+
+	exynos4415_clk_sleep_init();
+
+	samsung_clk_of_add_provider(np, exynos4415_ctx);
+}
+CLK_OF_DECLARE(exynos4415_cmu, "samsung,exynos4415-cmu", exynos4415_cmu_init);
+
+/*
+ * CMU DMC
+ */
+
+#define MPLL_LOCK		0x008
+#define MPLL_CON0		0x108
+#define MPLL_CON1		0x10c
+#define MPLL_CON2		0x110
+#define BPLL_LOCK		0x118
+#define BPLL_CON0		0x218
+#define BPLL_CON1		0x21c
+#define BPLL_CON2		0x220
+#define SRC_DMC			0x300
+#define DIV_DMC1		0x504
+
+enum exynos4415_dmc_plls {
+	mpll, bpll,
+	nr_dmc_plls,
+};
+
+#ifdef CONFIG_PM_SLEEP
+static struct samsung_clk_reg_dump *exynos4415_dmc_clk_regs;
+static struct samsung_clk_provider *exynos4415_dmc_ctx;
+
+static unsigned long exynos4415_cmu_dmc_clk_regs[] __initdata = {
+	MPLL_LOCK,
+	MPLL_CON0,
+	MPLL_CON1,
+	MPLL_CON2,
+	BPLL_LOCK,
+	BPLL_CON0,
+	BPLL_CON1,
+	BPLL_CON2,
+	SRC_DMC,
+	DIV_DMC1,
+};
+
+static int exynos4415_dmc_clk_suspend(void)
+{
+	samsung_clk_save(exynos4415_dmc_ctx->reg_base,
+				exynos4415_dmc_clk_regs,
+				ARRAY_SIZE(exynos4415_cmu_dmc_clk_regs));
+	return 0;
+}
+
+static void exynos4415_dmc_clk_resume(void)
+{
+	samsung_clk_restore(exynos4415_dmc_ctx->reg_base,
+				exynos4415_dmc_clk_regs,
+				ARRAY_SIZE(exynos4415_cmu_dmc_clk_regs));
+}
+
+static struct syscore_ops exynos4415_dmc_clk_syscore_ops = {
+	.suspend = exynos4415_dmc_clk_suspend,
+	.resume = exynos4415_dmc_clk_resume,
+};
+
+static void exynos4415_dmc_clk_sleep_init(void)
+{
+	exynos4415_dmc_clk_regs =
+		samsung_clk_alloc_reg_dump(exynos4415_cmu_dmc_clk_regs,
+				ARRAY_SIZE(exynos4415_cmu_dmc_clk_regs));
+	if (!exynos4415_dmc_clk_regs) {
+		pr_warn("%s: Failed to allocate sleep save data\n", __func__);
+		return;
+	}
+
+	register_syscore_ops(&exynos4415_dmc_clk_syscore_ops);
+}
+#else
+static inline void exynos4415_dmc_clk_sleep_init(void) { }
+#endif /* CONFIG_PM_SLEEP */
+
+PNAME(mout_mpll_p)		= { "fin_pll", "fout_mpll", };
+PNAME(mout_bpll_p)		= { "fin_pll", "fout_bpll", };
+PNAME(mbpll_p)			= { "mout_mpll", "mout_bpll", };
+
+static struct samsung_mux_clock exynos4415_dmc_mux_clks[] __initdata = {
+	MUX(CLK_DMC_MOUT_MPLL, "mout_mpll", mout_mpll_p, SRC_DMC, 12, 1),
+	MUX(CLK_DMC_MOUT_BPLL, "mout_bpll", mout_bpll_p, SRC_DMC, 10, 1),
+	MUX(CLK_DMC_MOUT_DPHY, "mout_dphy", mbpll_p, SRC_DMC, 8, 1),
+	MUX(CLK_DMC_MOUT_DMC_BUS, "mout_dmc_bus", mbpll_p, SRC_DMC, 4, 1),
+};
+
+static struct samsung_div_clock exynos4415_dmc_div_clks[] __initdata = {
+	DIV(CLK_DMC_DIV_DMC, "div_dmc", "div_dmc_pre", DIV_DMC1, 27, 3),
+	DIV(CLK_DMC_DIV_DPHY, "div_dphy", "mout_dphy", DIV_DMC1, 23, 3),
+	DIV(CLK_DMC_DIV_DMC_PRE, "div_dmc_pre", "mout_dmc_bus",
+		DIV_DMC1, 19, 2),
+	DIV(CLK_DMC_DIV_DMCP, "div_dmcp", "div_dmcd", DIV_DMC1, 15, 3),
+	DIV(CLK_DMC_DIV_DMCD, "div_dmcd", "div_dmc", DIV_DMC1, 11, 3),
+	DIV(CLK_DMC_DIV_MPLL_PRE, "div_mpll_pre", "mout_mpll", DIV_DMC1, 8, 2),
+};
+
+static struct samsung_pll_clock exynos4415_dmc_plls[nr_dmc_plls] __initdata = {
+	[mpll] = PLL(pll_35xx, CLK_DMC_FOUT_MPLL, "fout_mpll", "fin_pll",
+		MPLL_LOCK, MPLL_CON0, NULL),
+	[bpll] = PLL(pll_35xx, CLK_DMC_FOUT_BPLL, "fout_bpll", "fin_pll",
+		BPLL_LOCK, BPLL_CON0, NULL),
+};
+
+static void __init exynos4415_cmu_dmc_init(struct device_node *np)
+{
+	void __iomem *reg_base;
+
+	reg_base = of_iomap(np, 0);
+	if (!reg_base)
+		panic("%s: failed to map registers\n", __func__);
+
+	exynos4415_dmc_ctx = samsung_clk_init(np, reg_base, NR_CLKS_DMC);
+	if (!exynos4415_dmc_ctx)
+		panic("%s: unable to allocate context.\n", __func__);
+
+	exynos4415_dmc_plls[mpll].rate_table = exynos4415_pll_rates;
+	exynos4415_dmc_plls[bpll].rate_table = exynos4415_pll_rates;
+
+	samsung_clk_register_pll(exynos4415_dmc_ctx, exynos4415_dmc_plls,
+				ARRAY_SIZE(exynos4415_dmc_plls), reg_base);
+	samsung_clk_register_mux(exynos4415_dmc_ctx, exynos4415_dmc_mux_clks,
+				ARRAY_SIZE(exynos4415_dmc_mux_clks));
+	samsung_clk_register_div(exynos4415_dmc_ctx, exynos4415_dmc_div_clks,
+				ARRAY_SIZE(exynos4415_dmc_div_clks));
+
+	exynos4415_dmc_clk_sleep_init();
+
+	samsung_clk_of_add_provider(np, exynos4415_dmc_ctx);
+}
+CLK_OF_DECLARE(exynos4415_cmu_dmc, "samsung,exynos4415-cmu-dmc",
+		exynos4415_cmu_dmc_init);
diff --git a/include/dt-bindings/clock/exynos4415.h b/include/dt-bindings/clock/exynos4415.h
new file mode 100644
index 00000000000..7eed5510072
--- /dev/null
+++ b/include/dt-bindings/clock/exynos4415.h
@@ -0,0 +1,360 @@
+/*
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author: Chanwoo Choi <cw00.choi@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Device Tree binding constants for Samsung Exynos4415 clock controllers.
+ */
+
+#ifndef _DT_BINDINGS_CLOCK_SAMSUNG_EXYNOS4415_CLOCK_H
+#define _DT_BINDINGS_CLOCK_SAMSUNG_EXYNOS4415_CLOCK_H
+
+/*
+ * Let each exported clock get a unique index, which is used on DT-enabled
+ * platforms to lookup the clock from a clock specifier. These indices are
+ * therefore considered an ABI and so must not be changed. This implies
+ * that new clocks should be added either in free spaces between clock groups
+ * or at the end.
+ */
+
+/*
+ * Main CMU
+ */
+
+#define CLK_OSCSEL			1
+#define CLK_FIN_PLL			2
+#define CLK_FOUT_APLL			3
+#define CLK_FOUT_MPLL			4
+#define CLK_FOUT_EPLL			5
+#define CLK_FOUT_G3D_PLL		6
+#define CLK_FOUT_ISP_PLL		7
+#define CLK_FOUT_DISP_PLL		8
+
+/* Muxes */
+#define CLK_MOUT_MPLL_USER_L		16
+#define CLK_MOUT_GDL			17
+#define CLK_MOUT_MPLL_USER_R		18
+#define CLK_MOUT_GDR			19
+#define CLK_MOUT_EBI			20
+#define CLK_MOUT_ACLK_200		21
+#define CLK_MOUT_ACLK_160		22
+#define CLK_MOUT_ACLK_100		23
+#define CLK_MOUT_ACLK_266		24
+#define CLK_MOUT_G3D_PLL		25
+#define CLK_MOUT_EPLL			26
+#define CLK_MOUT_EBI_1			27
+#define CLK_MOUT_ISP_PLL		28
+#define CLK_MOUT_DISP_PLL		29
+#define CLK_MOUT_MPLL_USER_T		30
+#define CLK_MOUT_ACLK_400_MCUISP	31
+#define CLK_MOUT_G3D_PLLSRC		32
+#define CLK_MOUT_CSIS1			33
+#define CLK_MOUT_CSIS0			34
+#define CLK_MOUT_CAM1			35
+#define CLK_MOUT_FIMC3_LCLK		36
+#define CLK_MOUT_FIMC2_LCLK		37
+#define CLK_MOUT_FIMC1_LCLK		38
+#define CLK_MOUT_FIMC0_LCLK		39
+#define CLK_MOUT_MFC			40
+#define CLK_MOUT_MFC_1			41
+#define CLK_MOUT_MFC_0			42
+#define CLK_MOUT_G3D			43
+#define CLK_MOUT_G3D_1			44
+#define CLK_MOUT_G3D_0			45
+#define CLK_MOUT_MIPI0			46
+#define CLK_MOUT_FIMD0			47
+#define CLK_MOUT_TSADC_ISP		48
+#define CLK_MOUT_UART_ISP		49
+#define CLK_MOUT_SPI1_ISP		50
+#define CLK_MOUT_SPI0_ISP		51
+#define CLK_MOUT_PWM_ISP		52
+#define CLK_MOUT_AUDIO0			53
+#define CLK_MOUT_TSADC			54
+#define CLK_MOUT_MMC2			55
+#define CLK_MOUT_MMC1			56
+#define CLK_MOUT_MMC0			57
+#define CLK_MOUT_UART3			58
+#define CLK_MOUT_UART2			59
+#define CLK_MOUT_UART1			60
+#define CLK_MOUT_UART0			61
+#define CLK_MOUT_SPI2			62
+#define CLK_MOUT_SPI1			63
+#define CLK_MOUT_SPI0			64
+#define CLK_MOUT_SPDIF			65
+#define CLK_MOUT_AUDIO2			66
+#define CLK_MOUT_AUDIO1			67
+#define CLK_MOUT_MPLL_USER_C		68
+#define CLK_MOUT_HPM			69
+#define CLK_MOUT_CORE			70
+#define CLK_MOUT_APLL			71
+#define CLK_MOUT_PXLASYNC_CSIS1_FIMC	72
+#define CLK_MOUT_PXLASYNC_CSIS0_FIMC	73
+#define CLK_MOUT_JPEG			74
+#define CLK_MOUT_JPEG1			75
+#define CLK_MOUT_JPEG0			76
+#define CLK_MOUT_ACLK_ISP0_300		77
+#define CLK_MOUT_ACLK_ISP0_400		78
+#define CLK_MOUT_ACLK_ISP0_300_USER	79
+#define CLK_MOUT_ACLK_ISP1_300		80
+#define CLK_MOUT_ACLK_ISP1_300_USER	81
+#define CLK_MOUT_HDMI			82
+
+/* Dividers */
+#define CLK_DIV_GPL			90
+#define CLK_DIV_GDL			91
+#define CLK_DIV_GPR			92
+#define CLK_DIV_GDR			93
+#define CLK_DIV_ACLK_400_MCUISP		94
+#define CLK_DIV_EBI			95
+#define CLK_DIV_ACLK_200		96
+#define CLK_DIV_ACLK_160		97
+#define CLK_DIV_ACLK_100		98
+#define CLK_DIV_ACLK_266		99
+#define CLK_DIV_CSIS1			100
+#define CLK_DIV_CSIS0			101
+#define CLK_DIV_CAM1			102
+#define CLK_DIV_FIMC3_LCLK		103
+#define CLK_DIV_FIMC2_LCLK		104
+#define CLK_DIV_FIMC1_LCLK		105
+#define CLK_DIV_FIMC0_LCLK		106
+#define CLK_DIV_TV_BLK			107
+#define CLK_DIV_MFC			108
+#define CLK_DIV_G3D			109
+#define CLK_DIV_MIPI0_PRE		110
+#define CLK_DIV_MIPI0			111
+#define CLK_DIV_FIMD0			112
+#define CLK_DIV_UART_ISP		113
+#define CLK_DIV_SPI1_ISP_PRE		114
+#define CLK_DIV_SPI1_ISP		115
+#define CLK_DIV_SPI0_ISP_PRE		116
+#define CLK_DIV_SPI0_ISP		117
+#define CLK_DIV_PWM_ISP			118
+#define CLK_DIV_PCM0			119
+#define CLK_DIV_AUDIO0			120
+#define CLK_DIV_TSADC_PRE		121
+#define CLK_DIV_TSADC			122
+#define CLK_DIV_MMC1_PRE		123
+#define CLK_DIV_MMC1			124
+#define CLK_DIV_MMC0_PRE		125
+#define CLK_DIV_MMC0			126
+#define CLK_DIV_MMC2_PRE		127
+#define CLK_DIV_MMC2			128
+#define CLK_DIV_UART3			129
+#define CLK_DIV_UART2			130
+#define CLK_DIV_UART1			131
+#define CLK_DIV_UART0			132
+#define CLK_DIV_SPI1_PRE		133
+#define CLK_DIV_SPI1			134
+#define CLK_DIV_SPI0_PRE		135
+#define CLK_DIV_SPI0			136
+#define CLK_DIV_SPI2_PRE		137
+#define CLK_DIV_SPI2			138
+#define CLK_DIV_PCM2			139
+#define CLK_DIV_AUDIO2			140
+#define CLK_DIV_PCM1			141
+#define CLK_DIV_AUDIO1			142
+#define CLK_DIV_I2S1			143
+#define CLK_DIV_PXLASYNC_CSIS1_FIMC	144
+#define CLK_DIV_PXLASYNC_CSIS0_FIMC	145
+#define CLK_DIV_JPEG			146
+#define CLK_DIV_CORE2			147
+#define CLK_DIV_APLL			148
+#define CLK_DIV_PCLK_DBG		149
+#define CLK_DIV_ATB			150
+#define CLK_DIV_PERIPH			151
+#define CLK_DIV_COREM1			152
+#define CLK_DIV_COREM0			153
+#define CLK_DIV_CORE			154
+#define CLK_DIV_HPM			155
+#define CLK_DIV_COPY			156
+
+/* Gates */
+#define CLK_ASYNC_G3D			180
+#define CLK_ASYNC_MFCL			181
+#define CLK_ASYNC_TVX			182
+#define CLK_PPMULEFT			183
+#define CLK_GPIO_LEFT			184
+#define CLK_PPMUIMAGE			185
+#define CLK_QEMDMA2			186
+#define CLK_QEROTATOR			187
+#define CLK_SMMUMDMA2			188
+#define CLK_SMMUROTATOR			189
+#define CLK_MDMA2			190
+#define CLK_ROTATOR			191
+#define CLK_ASYNC_ISPMX			192
+#define CLK_ASYNC_MAUDIOX		193
+#define CLK_ASYNC_MFCR			194
+#define CLK_ASYNC_FSYSD			195
+#define CLK_ASYNC_LCD0X			196
+#define CLK_ASYNC_CAMX			197
+#define CLK_PPMURIGHT			198
+#define CLK_GPIO_RIGHT			199
+#define CLK_ANTIRBK_APBIF		200
+#define CLK_EFUSE_WRITER_APBIF		201
+#define CLK_MONOCNT			202
+#define CLK_TZPC6			203
+#define CLK_PROVISIONKEY1		204
+#define CLK_PROVISIONKEY0		205
+#define CLK_CMU_ISPPART			206
+#define CLK_TMU_APBIF			207
+#define CLK_KEYIF			208
+#define CLK_RTC				209
+#define CLK_WDT				210
+#define CLK_MCT				211
+#define CLK_SECKEY			212
+#define CLK_HDMI_CEC			213
+#define CLK_TZPC5			214
+#define CLK_TZPC4			215
+#define CLK_TZPC3			216
+#define CLK_TZPC2			217
+#define CLK_TZPC1			218
+#define CLK_TZPC0			219
+#define CLK_CMU_COREPART		220
+#define CLK_CMU_TOPPART			221
+#define CLK_PMU_APBIF			222
+#define CLK_SYSREG			223
+#define CLK_CHIP_ID			224
+#define CLK_SMMUFIMC_LITE2		225
+#define CLK_FIMC_LITE2			226
+#define CLK_PIXELASYNCM1		227
+#define CLK_PIXELASYNCM0		228
+#define CLK_PPMUCAMIF			229
+#define CLK_SMMUJPEG			230
+#define CLK_SMMUFIMC3			231
+#define CLK_SMMUFIMC2			232
+#define CLK_SMMUFIMC1			233
+#define CLK_SMMUFIMC0			234
+#define CLK_JPEG			235
+#define CLK_CSIS1			236
+#define CLK_CSIS0			237
+#define CLK_FIMC3			238
+#define CLK_FIMC2			239
+#define CLK_FIMC1			240
+#define CLK_FIMC0			241
+#define CLK_PPMUTV			242
+#define CLK_SMMUTV			243
+#define CLK_HDMI			244
+#define CLK_MIXER			245
+#define CLK_VP				246
+#define CLK_PPMUMFC_R			247
+#define CLK_PPMUMFC_L			248
+#define CLK_SMMUMFC_R			249
+#define CLK_SMMUMFC_L			250
+#define CLK_MFC				251
+#define CLK_PPMUG3D			252
+#define CLK_G3D				253
+#define CLK_PPMULCD0			254
+#define CLK_SMMUFIMD0			255
+#define CLK_DSIM0			256
+#define CLK_SMIES			257
+#define CLK_MIE0			258
+#define CLK_FIMD0			259
+#define CLK_TSADC			260
+#define CLK_PPMUFILE			261
+#define CLK_NFCON			262
+#define CLK_USBDEVICE			263
+#define CLK_USBHOST			264
+#define CLK_SROMC			265
+#define CLK_SDMMC2			266
+#define CLK_SDMMC1			267
+#define CLK_SDMMC0			268
+#define CLK_PDMA1			269
+#define CLK_PDMA0			270
+#define CLK_SPDIF			271
+#define CLK_PWM				272
+#define CLK_PCM2			273
+#define CLK_PCM1			274
+#define CLK_I2S1			275
+#define CLK_SPI2			276
+#define CLK_SPI1			277
+#define CLK_SPI0			278
+#define CLK_I2CHDMI			279
+#define CLK_I2C7			280
+#define CLK_I2C6			281
+#define CLK_I2C5			282
+#define CLK_I2C4			283
+#define CLK_I2C3			284
+#define CLK_I2C2			285
+#define CLK_I2C1			286
+#define CLK_I2C0			287
+#define CLK_UART3			288
+#define CLK_UART2			289
+#define CLK_UART1			290
+#define CLK_UART0			291
+
+/* Special clocks */
+#define CLK_SCLK_PXLAYSNC_CSIS1_FIMC	330
+#define CLK_SCLK_PXLAYSNC_CSIS0_FIMC	331
+#define CLK_SCLK_JPEG			332
+#define CLK_SCLK_CSIS1			333
+#define CLK_SCLK_CSIS0			334
+#define CLK_SCLK_CAM1			335
+#define CLK_SCLK_FIMC3_LCLK		336
+#define CLK_SCLK_FIMC2_LCLK		337
+#define CLK_SCLK_FIMC1_LCLK		338
+#define CLK_SCLK_FIMC0_LCLK		339
+#define CLK_SCLK_PIXEL			340
+#define CLK_SCLK_HDMI			341
+#define CLK_SCLK_MIXER			342
+#define CLK_SCLK_MFC			343
+#define CLK_SCLK_G3D			344
+#define CLK_SCLK_MIPIDPHY4L		345
+#define CLK_SCLK_MIPI0			346
+#define CLK_SCLK_MDNIE0			347
+#define CLK_SCLK_FIMD0			348
+#define CLK_SCLK_PCM0			349
+#define CLK_SCLK_AUDIO0			350
+#define CLK_SCLK_TSADC			351
+#define CLK_SCLK_EBI			352
+#define CLK_SCLK_MMC2			353
+#define CLK_SCLK_MMC1			354
+#define CLK_SCLK_MMC0			355
+#define CLK_SCLK_I2S			356
+#define CLK_SCLK_PCM2			357
+#define CLK_SCLK_PCM1			358
+#define CLK_SCLK_AUDIO2			359
+#define CLK_SCLK_AUDIO1			360
+#define CLK_SCLK_SPDIF			361
+#define CLK_SCLK_SPI2			362
+#define CLK_SCLK_SPI1			363
+#define CLK_SCLK_SPI0			364
+#define CLK_SCLK_UART3			365
+#define CLK_SCLK_UART2			366
+#define CLK_SCLK_UART1			367
+#define CLK_SCLK_UART0			368
+#define CLK_SCLK_HDMIPHY		369
+
+/*
+ * Total number of clocks of main CMU.
+ * NOTE: Must be equal to last clock ID increased by one.
+ */
+#define CLK_NR_CLKS			370
+
+/*
+ * CMU DMC
+ */
+#define CLK_DMC_FOUT_MPLL		1
+#define CLK_DMC_FOUT_BPLL		2
+
+#define CLK_DMC_MOUT_MPLL		3
+#define CLK_DMC_MOUT_BPLL		4
+#define CLK_DMC_MOUT_DPHY		5
+#define CLK_DMC_MOUT_DMC_BUS		6
+
+#define CLK_DMC_DIV_DMC			7
+#define CLK_DMC_DIV_DPHY		8
+#define CLK_DMC_DIV_DMC_PRE		9
+#define CLK_DMC_DIV_DMCP		10
+#define CLK_DMC_DIV_DMCD		11
+#define CLK_DMC_DIV_MPLL_PRE		12
+
+/*
+ * Total number of clocks of CMU_DMC.
+ * NOTE: Must be equal to highest clock ID increased by one.
+ */
+#define NR_CLKS_DMC			13
+
+#endif /* _DT_BINDINGS_CLOCK_SAMSUNG_EXYNOS4415_CLOCK_H */
-- 
cgit v1.2.3-70-g09d2


From 51579c3f1a9192b75365576227d40c7619493285 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Wed, 29 Oct 2014 10:44:58 -0700
Subject: net: dsa: Add support for reporting switch chip temperatures

Some switches provide chip temperature data.
Add support for reporting it through the hwmon subsystem.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  16 +++++++
 net/dsa/Kconfig   |  11 +++++
 net/dsa/dsa.c     | 131 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 158 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index b7655929353..55e75e7e8d4 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -139,6 +139,14 @@ struct dsa_switch {
 	 */
 	struct device		*master_dev;
 
+#ifdef CONFIG_NET_DSA_HWMON
+	/*
+	 * Hardware monitoring information
+	 */
+	char			hwmon_name[IFNAMSIZ + 8];
+	struct device		*hwmon_dev;
+#endif
+
 	/*
 	 * Slave mii_bus and devices for the individual ports.
 	 */
@@ -242,6 +250,14 @@ struct dsa_switch_driver {
 			   struct ethtool_eee *e);
 	int	(*get_eee)(struct dsa_switch *ds, int port,
 			   struct ethtool_eee *e);
+
+#ifdef CONFIG_NET_DSA_HWMON
+	/* Hardware monitoring */
+	int	(*get_temp)(struct dsa_switch *ds, int *temp);
+	int	(*get_temp_limit)(struct dsa_switch *ds, int *temp);
+	int	(*set_temp_limit)(struct dsa_switch *ds, int temp);
+	int	(*get_temp_alarm)(struct dsa_switch *ds, bool *alarm);
+#endif
 };
 
 void register_switch_driver(struct dsa_switch_driver *type);
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index a585fd6352e..5f8ac404535 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -11,6 +11,17 @@ config NET_DSA
 
 if NET_DSA
 
+config NET_DSA_HWMON
+	bool "Distributed Switch Architecture HWMON support"
+	default y
+	depends on HWMON && !(NET_DSA=y && HWMON=m)
+	---help---
+	  Say Y if you want to expose thermal sensor data on switches supported
+	  by the Distributed Switch Architecture.
+
+	  Some of those switches contain thermal sensors. This data is available
+	  via the hwmon sysfs interface and exposes the onboard sensors.
+
 # tagging formats
 config NET_DSA_TAG_BRCM
 	bool
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 22f34cf4cb2..5edbbca89f1 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -9,6 +9,9 @@
  * (at your option) any later version.
  */
 
+#include <linux/ctype.h>
+#include <linux/device.h>
+#include <linux/hwmon.h>
 #include <linux/list.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
@@ -17,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/of_platform.h>
+#include <linux/sysfs.h>
 #include "dsa_priv.h"
 
 char dsa_driver_version[] = "0.1";
@@ -71,6 +75,104 @@ dsa_switch_probe(struct device *host_dev, int sw_addr, char **_name)
 	return ret;
 }
 
+/* hwmon support ************************************************************/
+
+#ifdef CONFIG_NET_DSA_HWMON
+
+static ssize_t temp1_input_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct dsa_switch *ds = dev_get_drvdata(dev);
+	int temp, ret;
+
+	ret = ds->drv->get_temp(ds, &temp);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%d\n", temp * 1000);
+}
+static DEVICE_ATTR_RO(temp1_input);
+
+static ssize_t temp1_max_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	struct dsa_switch *ds = dev_get_drvdata(dev);
+	int temp, ret;
+
+	ret = ds->drv->get_temp_limit(ds, &temp);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%d\n", temp * 1000);
+}
+
+static ssize_t temp1_max_store(struct device *dev,
+			       struct device_attribute *attr, const char *buf,
+			       size_t count)
+{
+	struct dsa_switch *ds = dev_get_drvdata(dev);
+	int temp, ret;
+
+	ret = kstrtoint(buf, 0, &temp);
+	if (ret < 0)
+		return ret;
+
+	ret = ds->drv->set_temp_limit(ds, DIV_ROUND_CLOSEST(temp, 1000));
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+static DEVICE_ATTR(temp1_max, S_IRUGO, temp1_max_show, temp1_max_store);
+
+static ssize_t temp1_max_alarm_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct dsa_switch *ds = dev_get_drvdata(dev);
+	bool alarm;
+	int ret;
+
+	ret = ds->drv->get_temp_alarm(ds, &alarm);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%d\n", alarm);
+}
+static DEVICE_ATTR_RO(temp1_max_alarm);
+
+static struct attribute *dsa_hwmon_attrs[] = {
+	&dev_attr_temp1_input.attr,	/* 0 */
+	&dev_attr_temp1_max.attr,	/* 1 */
+	&dev_attr_temp1_max_alarm.attr,	/* 2 */
+	NULL
+};
+
+static umode_t dsa_hwmon_attrs_visible(struct kobject *kobj,
+				       struct attribute *attr, int index)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct dsa_switch *ds = dev_get_drvdata(dev);
+	struct dsa_switch_driver *drv = ds->drv;
+	umode_t mode = attr->mode;
+
+	if (index == 1) {
+		if (!drv->get_temp_limit)
+			mode = 0;
+		else if (drv->set_temp_limit)
+			mode |= S_IWUSR;
+	} else if (index == 2 && !drv->get_temp_alarm) {
+		mode = 0;
+	}
+	return mode;
+}
+
+static const struct attribute_group dsa_hwmon_group = {
+	.attrs = dsa_hwmon_attrs,
+	.is_visible = dsa_hwmon_attrs_visible,
+};
+__ATTRIBUTE_GROUPS(dsa_hwmon);
+
+#endif /* CONFIG_NET_DSA_HWMON */
 
 /* basic switch operations **************************************************/
 static struct dsa_switch *
@@ -225,6 +327,31 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index,
 		ds->ports[i] = slave_dev;
 	}
 
+#ifdef CONFIG_NET_DSA_HWMON
+	/* If the switch provides a temperature sensor,
+	 * register with hardware monitoring subsystem.
+	 * Treat registration error as non-fatal and ignore it.
+	 */
+	if (drv->get_temp) {
+		const char *netname = netdev_name(dst->master_netdev);
+		char hname[IFNAMSIZ + 1];
+		int i, j;
+
+		/* Create valid hwmon 'name' attribute */
+		for (i = j = 0; i < IFNAMSIZ && netname[i]; i++) {
+			if (isalnum(netname[i]))
+				hname[j++] = netname[i];
+		}
+		hname[j] = '\0';
+		scnprintf(ds->hwmon_name, sizeof(ds->hwmon_name), "%s_dsa%d",
+			  hname, index);
+		ds->hwmon_dev = hwmon_device_register_with_groups(NULL,
+					ds->hwmon_name, ds, dsa_hwmon_groups);
+		if (IS_ERR(ds->hwmon_dev))
+			ds->hwmon_dev = NULL;
+	}
+#endif /* CONFIG_NET_DSA_HWMON */
+
 	return ds;
 
 out_free:
@@ -236,6 +363,10 @@ out:
 
 static void dsa_switch_destroy(struct dsa_switch *ds)
 {
+#ifdef CONFIG_NET_DSA_HWMON
+	if (ds->hwmon_dev)
+		hwmon_device_unregister(ds->hwmon_dev);
+#endif
 }
 
 #ifdef CONFIG_PM_SLEEP
-- 
cgit v1.2.3-70-g09d2


From 6793abb4e8491b1d673ccfd09e1a73d1ff8b9386 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Wed, 29 Oct 2014 10:45:01 -0700
Subject: net: dsa: Add support for switch EEPROM access

On some chips it is possible to access the switch eeprom.
Add infrastructure support for it.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 10 ++++++++++
 net/dsa/dsa.c     |  4 ++++
 net/dsa/slave.c   | 41 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 55 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 55e75e7e8d4..37856a28c8d 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -38,6 +38,9 @@ struct dsa_chip_data {
 	struct device	*host_dev;
 	int		sw_addr;
 
+	/* set to size of eeprom if supported by the switch */
+	int		eeprom_len;
+
 	/* Device tree node pointer for this specific switch chip
 	 * used during switch setup in case additional properties
 	 * and resources needs to be used
@@ -258,6 +261,13 @@ struct dsa_switch_driver {
 	int	(*set_temp_limit)(struct dsa_switch *ds, int temp);
 	int	(*get_temp_alarm)(struct dsa_switch *ds, bool *alarm);
 #endif
+
+	/* EEPROM access */
+	int	(*get_eeprom_len)(struct dsa_switch *ds);
+	int	(*get_eeprom)(struct dsa_switch *ds,
+			      struct ethtool_eeprom *eeprom, u8 *data);
+	int	(*set_eeprom)(struct dsa_switch *ds,
+			      struct ethtool_eeprom *eeprom, u8 *data);
 };
 
 void register_switch_driver(struct dsa_switch_driver *type);
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 5edbbca89f1..b51ef592f0a 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -575,6 +575,7 @@ static int dsa_of_probe(struct platform_device *pdev)
 	const char *port_name;
 	int chip_index, port_index;
 	const unsigned int *sw_addr, *port_reg;
+	u32 eeprom_len;
 	int ret;
 
 	mdio = of_parse_phandle(np, "dsa,mii-bus", 0);
@@ -626,6 +627,9 @@ static int dsa_of_probe(struct platform_device *pdev)
 		if (cd->sw_addr > PHY_MAX_ADDR)
 			continue;
 
+		if (!of_property_read_u32(np, "eeprom-length", &eeprom_len))
+			cd->eeprom_len = eeprom_len;
+
 		for_each_available_child_of_node(child, port) {
 			port_reg = of_get_property(port, "reg", NULL);
 			if (!port_reg)
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 6d1817449c3..ff2fbe79bc5 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -271,6 +271,44 @@ static u32 dsa_slave_get_link(struct net_device *dev)
 	return -EOPNOTSUPP;
 }
 
+static int dsa_slave_get_eeprom_len(struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	if (ds->pd->eeprom_len)
+		return ds->pd->eeprom_len;
+
+	if (ds->drv->get_eeprom_len)
+		return ds->drv->get_eeprom_len(ds);
+
+	return 0;
+}
+
+static int dsa_slave_get_eeprom(struct net_device *dev,
+				struct ethtool_eeprom *eeprom, u8 *data)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	if (ds->drv->get_eeprom)
+		return ds->drv->get_eeprom(ds, eeprom, data);
+
+	return -EOPNOTSUPP;
+}
+
+static int dsa_slave_set_eeprom(struct net_device *dev,
+				struct ethtool_eeprom *eeprom, u8 *data)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	if (ds->drv->set_eeprom)
+		return ds->drv->set_eeprom(ds, eeprom, data);
+
+	return -EOPNOTSUPP;
+}
+
 static void dsa_slave_get_strings(struct net_device *dev,
 				  uint32_t stringset, uint8_t *data)
 {
@@ -387,6 +425,9 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_drvinfo		= dsa_slave_get_drvinfo,
 	.nway_reset		= dsa_slave_nway_reset,
 	.get_link		= dsa_slave_get_link,
+	.get_eeprom_len		= dsa_slave_get_eeprom_len,
+	.get_eeprom		= dsa_slave_get_eeprom,
+	.set_eeprom		= dsa_slave_set_eeprom,
 	.get_strings		= dsa_slave_get_strings,
 	.get_ethtool_stats	= dsa_slave_get_ethtool_stats,
 	.get_sset_count		= dsa_slave_get_sset_count,
-- 
cgit v1.2.3-70-g09d2


From 3d762a0f0ab9cb4a6b5993db3ce56c92f9f90ab2 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Wed, 29 Oct 2014 10:45:04 -0700
Subject: net: dsa: Add support for reading switch registers with ethtool

Add support for reading switch registers with 'ethtool -d'.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  7 +++++++
 net/dsa/slave.c   | 23 +++++++++++++++++++++++
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 37856a28c8d..ed3c34bbb67 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -268,6 +268,13 @@ struct dsa_switch_driver {
 			      struct ethtool_eeprom *eeprom, u8 *data);
 	int	(*set_eeprom)(struct dsa_switch *ds,
 			      struct ethtool_eeprom *eeprom, u8 *data);
+
+	/*
+	 * Register access.
+	 */
+	int	(*get_regs_len)(struct dsa_switch *ds, int port);
+	void	(*get_regs)(struct dsa_switch *ds, int port,
+			    struct ethtool_regs *regs, void *p);
 };
 
 void register_switch_driver(struct dsa_switch_driver *type);
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index ff2fbe79bc5..474f2962590 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -249,6 +249,27 @@ static void dsa_slave_get_drvinfo(struct net_device *dev,
 	strlcpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info));
 }
 
+static int dsa_slave_get_regs_len(struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	if (ds->drv->get_regs_len)
+		return ds->drv->get_regs_len(ds, p->port);
+
+	return -EOPNOTSUPP;
+}
+
+static void
+dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	if (ds->drv->get_regs)
+		ds->drv->get_regs(ds, p->port, regs, _p);
+}
+
 static int dsa_slave_nway_reset(struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
@@ -423,6 +444,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_settings		= dsa_slave_get_settings,
 	.set_settings		= dsa_slave_set_settings,
 	.get_drvinfo		= dsa_slave_get_drvinfo,
+	.get_regs_len		= dsa_slave_get_regs_len,
+	.get_regs		= dsa_slave_get_regs,
 	.nway_reset		= dsa_slave_nway_reset,
 	.get_link		= dsa_slave_get_link,
 	.get_eeprom_len		= dsa_slave_get_eeprom_len,
-- 
cgit v1.2.3-70-g09d2


From c759e5f76b18350ed2417e89588d6358e58e1ad3 Mon Sep 17 00:00:00 2001
From: Maxime Coquelin <maxime.coquelin@st.com>
Date: Fri, 31 Oct 2014 09:47:54 +0100
Subject: reset: stih407: Add reset controllers DT bindings

This patch adds softreset, powerdown and picophy reset controllers
DT bindings for the STiH407 SoC.

Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Maxime Coquelin <maxime.coquelin@st.com>
---
 .../dt-bindings/reset-controller/stih407-resets.h  | 61 ++++++++++++++++++++++
 1 file changed, 61 insertions(+)
 create mode 100644 include/dt-bindings/reset-controller/stih407-resets.h

(limited to 'include')

diff --git a/include/dt-bindings/reset-controller/stih407-resets.h b/include/dt-bindings/reset-controller/stih407-resets.h
new file mode 100644
index 00000000000..02d4328fe47
--- /dev/null
+++ b/include/dt-bindings/reset-controller/stih407-resets.h
@@ -0,0 +1,61 @@
+/*
+ * This header provides constants for the reset controller
+ * based peripheral powerdown requests on the STMicroelectronics
+ * STiH407 SoC.
+ */
+#ifndef _DT_BINDINGS_RESET_CONTROLLER_STIH407
+#define _DT_BINDINGS_RESET_CONTROLLER_STIH407
+
+/* Powerdown requests control 0 */
+#define STIH407_EMISS_POWERDOWN		0
+#define STIH407_NAND_POWERDOWN		1
+
+/* Synp GMAC PowerDown */
+#define STIH407_ETH1_POWERDOWN		2
+
+/* Powerdown requests control 1 */
+#define STIH407_USB3_POWERDOWN		3
+#define STIH407_USB2_PORT1_POWERDOWN	4
+#define STIH407_USB2_PORT0_POWERDOWN	5
+#define STIH407_PCIE1_POWERDOWN		6
+#define STIH407_PCIE0_POWERDOWN		7
+#define STIH407_SATA1_POWERDOWN		8
+#define STIH407_SATA0_POWERDOWN		9
+
+/* Reset defines */
+#define STIH407_ETH1_SOFTRESET		0
+#define STIH407_MMC1_SOFTRESET		1
+#define STIH407_PICOPHY_SOFTRESET	2
+#define STIH407_IRB_SOFTRESET		3
+#define STIH407_PCIE0_SOFTRESET		4
+#define STIH407_PCIE1_SOFTRESET		5
+#define STIH407_SATA0_SOFTRESET		6
+#define STIH407_SATA1_SOFTRESET		7
+#define STIH407_MIPHY0_SOFTRESET	8
+#define STIH407_MIPHY1_SOFTRESET	9
+#define STIH407_MIPHY2_SOFTRESET	10
+#define STIH407_SATA0_PWR_SOFTRESET	11
+#define STIH407_SATA1_PWR_SOFTRESET	12
+#define STIH407_DELTA_SOFTRESET		13
+#define STIH407_BLITTER_SOFTRESET	14
+#define STIH407_HDTVOUT_SOFTRESET	15
+#define STIH407_HDQVDP_SOFTRESET	16
+#define STIH407_VDP_AUX_SOFTRESET	17
+#define STIH407_COMPO_SOFTRESET		18
+#define STIH407_HDMI_TX_PHY_SOFTRESET	19
+#define STIH407_JPEG_DEC_SOFTRESET	20
+#define STIH407_VP8_DEC_SOFTRESET	21
+#define STIH407_GPU_SOFTRESET		22
+#define STIH407_HVA_SOFTRESET		23
+#define STIH407_ERAM_HVA_SOFTRESET	24
+#define STIH407_LPM_SOFTRESET		25
+#define STIH407_KEYSCAN_SOFTRESET	26
+#define STIH407_USB2_PORT0_SOFTRESET	27
+#define STIH407_USB2_PORT1_SOFTRESET	28
+
+/* Picophy reset defines */
+#define STIH407_PICOPHY0_RESET		0
+#define STIH407_PICOPHY1_RESET		1
+#define STIH407_PICOPHY2_RESET		2
+
+#endif /* _DT_BINDINGS_RESET_CONTROLLER_STIH407 */
-- 
cgit v1.2.3-70-g09d2


From 1befe7e49f8d4e706e5ef39fb57dac1da734f163 Mon Sep 17 00:00:00 2001
From: Gabriel FERNANDEZ <gabriel.fernandez@st.com>
Date: Mon, 25 Aug 2014 16:44:00 +0200
Subject: ARM: STi: DT: STiH407: 407 DT Entry for clockgen C0

Patch adds DT entries for clockgen C0

Signed-off-by: Gabriel Fernandez <gabriel.fernandez@linaro.org>
Signed-off-by: Olivier Bideau <olivier.bideau@st.com>
Signed-off-by: Maxime Coquelin <maxime.coquelin@st.com>
---
 arch/arm/boot/dts/stih407-clock.dtsi     | 83 ++++++++++++++++++++++++++++++++
 arch/arm/boot/dts/stih407.dtsi           | 18 +++----
 include/dt-bindings/clock/stih407-clks.h | 11 +++++
 3 files changed, 103 insertions(+), 9 deletions(-)
 create mode 100644 include/dt-bindings/clock/stih407-clks.h

(limited to 'include')

diff --git a/arch/arm/boot/dts/stih407-clock.dtsi b/arch/arm/boot/dts/stih407-clock.dtsi
index 1bfa6799d7c..f85571a956f 100644
--- a/arch/arm/boot/dts/stih407-clock.dtsi
+++ b/arch/arm/boot/dts/stih407-clock.dtsi
@@ -5,6 +5,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <dt-bindings/clock/stih407-clks.h>
 / {
 	clocks {
 		#address-cells = <1>;
@@ -64,5 +65,87 @@
 				clock-output-names = "clk-ic-lmi0";
 			};
 		};
+
+		clk_s_c0_quadfs: clk-s-c0-quadfs@9103000 {
+			#clock-cells = <1>;
+			compatible = "st,stih407-quadfs660-C", "st,quadfs";
+			reg = <0x9103000 0x1000>;
+
+			clocks = <&clk_sysin>;
+
+			clock-output-names = "clk-s-c0-fs0-ch0",
+					     "clk-s-c0-fs0-ch1",
+					     "clk-s-c0-fs0-ch2",
+					     "clk-s-c0-fs0-ch3";
+		};
+
+		clk_s_c0: clockgen-c@09103000 {
+			compatible = "st,clkgen-c32";
+			reg = <0x9103000 0x1000>;
+
+			clk_s_c0_pll0: clk-s-c0-pll0 {
+				#clock-cells = <1>;
+				compatible = "st,stih407-plls-c32-c0_0", "st,clkgen-plls-c32";
+
+				clocks = <&clk_sysin>;
+
+				clock-output-names = "clk-s-c0-pll0-odf-0";
+			};
+
+			clk_s_c0_pll1: clk-s-c0-pll1 {
+				#clock-cells = <1>;
+				compatible = "st,stih407-plls-c32-c0_1", "st,clkgen-plls-c32";
+
+				clocks = <&clk_sysin>;
+
+				clock-output-names = "clk-s-c0-pll1-odf-0";
+			};
+
+			clk_s_c0_flexgen: clk-s-c0-flexgen {
+				#clock-cells = <1>;
+				compatible = "st,flexgen";
+
+				clocks = <&clk_s_c0_pll0 0>,
+					 <&clk_s_c0_pll1 0>,
+					 <&clk_s_c0_quadfs 0>,
+					 <&clk_s_c0_quadfs 1>,
+					 <&clk_s_c0_quadfs 2>,
+					 <&clk_s_c0_quadfs 3>,
+					 <&clk_sysin>;
+
+				clock-output-names = "clk-icn-gpu",
+						     "clk-fdma",
+						     "clk-nand",
+						     "clk-hva",
+						     "clk-proc-stfe",
+						     "clk-proc-tp",
+						     "clk-rx-icn-dmu",
+						     "clk-rx-icn-hva",
+						     "clk-icn-cpu",
+						     "clk-tx-icn-dmu",
+						     "clk-mmc-0",
+						     "clk-mmc-1",
+						     "clk-jpegdec",
+						     "clk-ext2fa9",
+						     "clk-ic-bdisp-0",
+						     "clk-ic-bdisp-1",
+						     "clk-pp-dmu",
+						     "clk-vid-dmu",
+						     "clk-dss-lpc",
+						     "clk-st231-aud-0",
+						     "clk-st231-gp-1",
+						     "clk-st231-dmu",
+						     "clk-icn-lmi",
+						     "clk-tx-icn-disp-1",
+						     "clk-icn-sbc",
+						     "clk-stfe-frc2",
+						     "clk-eth-phy",
+						     "clk-eth-ref-phyclk",
+						     "clk-flash-promip",
+						     "clk-main-disp",
+						     "clk-aux-disp",
+						     "clk-compo-dvp";
+			};
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/stih407.dtsi b/arch/arm/boot/dts/stih407.dtsi
index d2f1aaa870e..50637f5168d 100644
--- a/arch/arm/boot/dts/stih407.dtsi
+++ b/arch/arm/boot/dts/stih407.dtsi
@@ -120,7 +120,7 @@
 			interrupts = <GIC_SPI 122 IRQ_TYPE_NONE>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_serial0>;
-			clocks = <&clk_ext2f_a9>;
+			clocks = <&clk_s_c0_flexgen CLK_EXT2F_A9>;
 
 			status = "disabled";
 		};
@@ -131,7 +131,7 @@
 			interrupts = <GIC_SPI 123 IRQ_TYPE_NONE>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_serial1>;
-			clocks = <&clk_ext2f_a9>;
+			clocks = <&clk_s_c0_flexgen CLK_EXT2F_A9>;
 
 			status = "disabled";
 		};
@@ -142,7 +142,7 @@
 			interrupts = <GIC_SPI 124 IRQ_TYPE_NONE>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_serial2>;
-			clocks = <&clk_ext2f_a9>;
+			clocks = <&clk_s_c0_flexgen CLK_EXT2F_A9>;
 
 			status = "disabled";
 		};
@@ -174,7 +174,7 @@
 			compatible = "st,comms-ssc4-i2c";
 			interrupts = <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>;
 			reg = <0x9840000 0x110>;
-			clocks = <&clk_ext2f_a9>;
+			clocks = <&clk_s_c0_flexgen CLK_EXT2F_A9>;
 			clock-names = "ssc";
 			clock-frequency = <400000>;
 			pinctrl-names = "default";
@@ -187,7 +187,7 @@
 			compatible = "st,comms-ssc4-i2c";
 			reg = <0x9841000 0x110>;
 			interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&clk_ext2f_a9>;
+			clocks = <&clk_s_c0_flexgen CLK_EXT2F_A9>;
 			clock-names = "ssc";
 			clock-frequency = <400000>;
 			pinctrl-names = "default";
@@ -200,7 +200,7 @@
 			compatible = "st,comms-ssc4-i2c";
 			reg = <0x9842000 0x110>;
 			interrupts = <GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&clk_ext2f_a9>;
+			clocks = <&clk_s_c0_flexgen CLK_EXT2F_A9>;
 			clock-names = "ssc";
 			clock-frequency = <400000>;
 			pinctrl-names = "default";
@@ -213,7 +213,7 @@
 			compatible = "st,comms-ssc4-i2c";
 			reg = <0x9843000 0x110>;
 			interrupts = <GIC_SPI 115 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&clk_ext2f_a9>;
+			clocks = <&clk_s_c0_flexgen CLK_EXT2F_A9>;
 			clock-names = "ssc";
 			clock-frequency = <400000>;
 			pinctrl-names = "default";
@@ -226,7 +226,7 @@
 			compatible = "st,comms-ssc4-i2c";
 			reg = <0x9844000 0x110>;
 			interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&clk_ext2f_a9>;
+			clocks = <&clk_s_c0_flexgen CLK_EXT2F_A9>;
 			clock-names = "ssc";
 			clock-frequency = <400000>;
 			pinctrl-names = "default";
@@ -239,7 +239,7 @@
 			compatible = "st,comms-ssc4-i2c";
 			reg = <0x9845000 0x110>;
 			interrupts = <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&clk_ext2f_a9>;
+			clocks = <&clk_s_c0_flexgen CLK_EXT2F_A9>;
 			clock-names = "ssc";
 			clock-frequency = <400000>;
 			pinctrl-names = "default";
diff --git a/include/dt-bindings/clock/stih407-clks.h b/include/dt-bindings/clock/stih407-clks.h
new file mode 100644
index 00000000000..1f9bfe0e47f
--- /dev/null
+++ b/include/dt-bindings/clock/stih407-clks.h
@@ -0,0 +1,11 @@
+/*
+ * This header provides constants clk index STMicroelectronics
+ * STiH407 SoC.
+ */
+#ifndef _DT_BINDINGS_CLK_STIH407
+#define _DT_BINDINGS_CLK_STIH407
+
+/* CLOCKGEN C0 */
+#define CLK_EXT2F_A9		13
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From 532abc3a4a4502e13315d246c545d7567c80b03e Mon Sep 17 00:00:00 2001
From: Naveen Krishna Ch <naveenkrishna.ch@gmail.com>
Date: Mon, 22 Sep 2014 10:17:04 +0530
Subject: clk: samsung: add initial clock support for Exynos7 SoC

Add initial clock support for Exynos7 SoC which is required
to bring up platforms based on Exynos7.

Signed-off-by: Naveen Krishna Ch <naveenkrishna.ch@gmail.com>
Signed-off-by: Abhilash Kesavan <a.kesavan@samsung.com>
Reviewed-by: Thomas Abraham <thomas.ab@samsung.com>
Tested-by: Thomas Abraham <thomas.ab@samsung.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
---
 .../devicetree/bindings/clock/exynos7-clock.txt    |  67 ++++
 drivers/clk/samsung/Makefile                       |   1 +
 drivers/clk/samsung/clk-exynos7.c                  | 425 +++++++++++++++++++++
 include/dt-bindings/clock/exynos7-clk.h            |  49 +++
 4 files changed, 542 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/exynos7-clock.txt
 create mode 100644 drivers/clk/samsung/clk-exynos7.c
 create mode 100644 include/dt-bindings/clock/exynos7-clk.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/exynos7-clock.txt b/Documentation/devicetree/bindings/clock/exynos7-clock.txt
new file mode 100644
index 00000000000..789f76132a8
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/exynos7-clock.txt
@@ -0,0 +1,67 @@
+* Samsung Exynos7 Clock Controller
+
+Exynos7 clock controller has various blocks which are instantiated
+independently from the device-tree. These clock controllers
+generate and supply clocks to various hardware blocks within
+the SoC.
+
+Each clock is assigned an identifier and client nodes can use
+this identifier to specify the clock which they consume. All
+available clocks are defined as preprocessor macros in
+dt-bindings/clock/exynos7-clk.h header and can be used in
+device tree sources.
+
+External clocks:
+
+There are several clocks that are generated outside the SoC. It
+is expected that they are defined using standard clock bindings
+with following clock-output-names:
+
+ - "fin_pll" - PLL input clock from XXTI
+
+Required Properties for Clock Controller:
+
+ - compatible: clock controllers will use one of the following
+	compatible strings to indicate the clock controller
+	functionality.
+
+	- "samsung,exynos7-clock-topc"
+	- "samsung,exynos7-clock-top0"
+	- "samsung,exynos7-clock-peric0"
+	- "samsung,exynos7-clock-peric1"
+	- "samsung,exynos7-clock-peris"
+
+ - reg: physical base address of the controller and the length of
+	memory mapped region.
+
+ - #clock-cells: should be 1.
+
+ - clocks: list of clock identifiers which are fed as the input to
+	the given clock controller. Please refer the next section to
+	find the input clocks for a given controller.
+
+- clock-names: list of names of clocks which are fed as the input
+	to the given clock controller.
+
+Input clocks for top0 clock controller:
+	- fin_pll
+	- dout_sclk_bus0_pll
+	- dout_sclk_bus1_pll
+	- dout_sclk_cc_pll
+	- dout_sclk_mfc_pll
+
+Input clocks for peric0 clock controller:
+	- fin_pll
+	- dout_aclk_peric0_66
+	- sclk_uart0
+
+Input clocks for peric1 clock controller:
+	- fin_pll
+	- dout_aclk_peric1_66
+	- sclk_uart1
+	- sclk_uart2
+	- sclk_uart3
+
+Input clocks for peris clock controller:
+	- fin_pll
+	- dout_aclk_peris_66
diff --git a/drivers/clk/samsung/Makefile b/drivers/clk/samsung/Makefile
index d8535e6df1d..006c6f29431 100644
--- a/drivers/clk/samsung/Makefile
+++ b/drivers/clk/samsung/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_SOC_EXYNOS5420)	+= clk-exynos5420.o
 obj-$(CONFIG_SOC_EXYNOS5440)	+= clk-exynos5440.o
 obj-$(CONFIG_ARCH_EXYNOS)	+= clk-exynos-audss.o
 obj-$(CONFIG_ARCH_EXYNOS)	+= clk-exynos-clkout.o
+obj-$(CONFIG_ARCH_EXYNOS7)	+= clk-exynos7.o
 obj-$(CONFIG_S3C2410_COMMON_CLK)+= clk-s3c2410.o
 obj-$(CONFIG_S3C2410_COMMON_DCLK)+= clk-s3c2410-dclk.o
 obj-$(CONFIG_S3C2412_COMMON_CLK)+= clk-s3c2412.o
diff --git a/drivers/clk/samsung/clk-exynos7.c b/drivers/clk/samsung/clk-exynos7.c
new file mode 100644
index 00000000000..54206d4d408
--- /dev/null
+++ b/drivers/clk/samsung/clk-exynos7.c
@@ -0,0 +1,425 @@
+/*
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author: Naveen Krishna Ch <naveenkrishna.ch@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+*/
+
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+
+#include "clk.h"
+#include <dt-bindings/clock/exynos7-clk.h>
+
+/* Register Offset definitions for CMU_TOPC (0x10570000) */
+#define CC_PLL_LOCK		0x0000
+#define BUS0_PLL_LOCK		0x0004
+#define BUS1_DPLL_LOCK		0x0008
+#define MFC_PLL_LOCK		0x000C
+#define AUD_PLL_LOCK		0x0010
+#define CC_PLL_CON0		0x0100
+#define BUS0_PLL_CON0		0x0110
+#define BUS1_DPLL_CON0		0x0120
+#define MFC_PLL_CON0		0x0130
+#define AUD_PLL_CON0		0x0140
+#define MUX_SEL_TOPC0		0x0200
+#define MUX_SEL_TOPC1		0x0204
+#define MUX_SEL_TOPC3		0x020C
+#define DIV_TOPC1		0x0604
+#define DIV_TOPC3		0x060C
+
+static struct samsung_fixed_factor_clock topc_fixed_factor_clks[] __initdata = {
+	FFACTOR(0, "ffac_topc_bus0_pll_div2", "mout_bus0_pll_ctrl", 1, 2, 0),
+	FFACTOR(0, "ffac_topc_bus0_pll_div4",
+		"ffac_topc_bus0_pll_div2", 1, 2, 0),
+	FFACTOR(0, "ffac_topc_bus1_pll_div2", "mout_bus1_pll_ctrl", 1, 2, 0),
+	FFACTOR(0, "ffac_topc_cc_pll_div2", "mout_cc_pll_ctrl", 1, 2, 0),
+	FFACTOR(0, "ffac_topc_mfc_pll_div2", "mout_mfc_pll_ctrl", 1, 2, 0),
+};
+
+/* List of parent clocks for Muxes in CMU_TOPC */
+PNAME(mout_bus0_pll_ctrl_p)	= { "fin_pll", "fout_bus0_pll" };
+PNAME(mout_bus1_pll_ctrl_p)	= { "fin_pll", "fout_bus1_pll" };
+PNAME(mout_cc_pll_ctrl_p)	= { "fin_pll", "fout_cc_pll" };
+PNAME(mout_mfc_pll_ctrl_p)	= { "fin_pll", "fout_mfc_pll" };
+
+PNAME(mout_topc_group2) = { "mout_sclk_bus0_pll_cmuc",
+	"mout_sclk_bus1_pll_cmuc", "mout_sclk_cc_pll_cmuc",
+	"mout_sclk_mfc_pll_cmuc" };
+
+PNAME(mout_sclk_bus0_pll_cmuc_p) = { "mout_bus0_pll_ctrl",
+	"ffac_topc_bus0_pll_div2", "ffac_topc_bus0_pll_div4"};
+PNAME(mout_sclk_bus1_pll_cmuc_p) = { "mout_bus1_pll_ctrl",
+	"ffac_topc_bus1_pll_div2"};
+PNAME(mout_sclk_cc_pll_cmuc_p) = { "mout_cc_pll_ctrl",
+	"ffac_topc_cc_pll_div2"};
+PNAME(mout_sclk_mfc_pll_cmuc_p) = { "mout_mfc_pll_ctrl",
+	"ffac_topc_mfc_pll_div2"};
+
+
+PNAME(mout_sclk_bus0_pll_out_p) = {"mout_bus0_pll_ctrl",
+	"ffac_topc_bus0_pll_div2"};
+
+static unsigned long topc_clk_regs[] __initdata = {
+	CC_PLL_LOCK,
+	BUS0_PLL_LOCK,
+	BUS1_DPLL_LOCK,
+	MFC_PLL_LOCK,
+	AUD_PLL_LOCK,
+	CC_PLL_CON0,
+	BUS0_PLL_CON0,
+	BUS1_DPLL_CON0,
+	MFC_PLL_CON0,
+	AUD_PLL_CON0,
+	MUX_SEL_TOPC0,
+	MUX_SEL_TOPC1,
+	MUX_SEL_TOPC3,
+	DIV_TOPC1,
+	DIV_TOPC3,
+};
+
+static struct samsung_mux_clock topc_mux_clks[] __initdata = {
+	MUX(0, "mout_bus0_pll_ctrl", mout_bus0_pll_ctrl_p, MUX_SEL_TOPC0, 0, 1),
+	MUX(0, "mout_bus1_pll_ctrl", mout_bus1_pll_ctrl_p, MUX_SEL_TOPC0, 4, 1),
+	MUX(0, "mout_cc_pll_ctrl", mout_cc_pll_ctrl_p, MUX_SEL_TOPC0, 8, 1),
+	MUX(0, "mout_mfc_pll_ctrl", mout_mfc_pll_ctrl_p, MUX_SEL_TOPC0, 12, 1),
+
+	MUX(0, "mout_sclk_bus0_pll_cmuc", mout_sclk_bus0_pll_cmuc_p,
+		MUX_SEL_TOPC0, 16, 2),
+	MUX(0, "mout_sclk_bus1_pll_cmuc", mout_sclk_bus1_pll_cmuc_p,
+		MUX_SEL_TOPC0, 20, 1),
+	MUX(0, "mout_sclk_cc_pll_cmuc", mout_sclk_cc_pll_cmuc_p,
+		MUX_SEL_TOPC0, 24, 1),
+	MUX(0, "mout_sclk_mfc_pll_cmuc", mout_sclk_mfc_pll_cmuc_p,
+		MUX_SEL_TOPC0, 28, 1),
+
+	MUX(0, "mout_sclk_bus0_pll_out", mout_sclk_bus0_pll_out_p,
+		MUX_SEL_TOPC1, 16, 1),
+
+	MUX(0, "mout_aclk_peris_66", mout_topc_group2, MUX_SEL_TOPC3, 24, 2),
+};
+
+static struct samsung_div_clock topc_div_clks[] __initdata = {
+	DIV(DOUT_ACLK_PERIS, "dout_aclk_peris_66", "mout_aclk_peris_66",
+		DIV_TOPC1, 24, 4),
+
+	DIV(DOUT_SCLK_BUS0_PLL, "dout_sclk_bus0_pll", "mout_sclk_bus0_pll_out",
+		DIV_TOPC3, 0, 3),
+	DIV(DOUT_SCLK_BUS1_PLL, "dout_sclk_bus1_pll", "mout_bus1_pll_ctrl",
+		DIV_TOPC3, 8, 3),
+	DIV(DOUT_SCLK_CC_PLL, "dout_sclk_cc_pll", "mout_cc_pll_ctrl",
+		DIV_TOPC3, 12, 3),
+	DIV(DOUT_SCLK_MFC_PLL, "dout_sclk_mfc_pll", "mout_mfc_pll_ctrl",
+		DIV_TOPC3, 16, 3),
+};
+
+static struct samsung_pll_clock topc_pll_clks[] __initdata = {
+	PLL(pll_1451x, 0, "fout_bus0_pll", "fin_pll", BUS0_PLL_LOCK,
+		BUS0_PLL_CON0, NULL),
+	PLL(pll_1452x, 0, "fout_cc_pll", "fin_pll", CC_PLL_LOCK,
+		CC_PLL_CON0, NULL),
+	PLL(pll_1452x, 0, "fout_bus1_pll", "fin_pll", BUS1_DPLL_LOCK,
+		BUS1_DPLL_CON0, NULL),
+	PLL(pll_1452x, 0, "fout_mfc_pll", "fin_pll", MFC_PLL_LOCK,
+		MFC_PLL_CON0, NULL),
+	PLL(pll_1460x, 0, "fout_aud_pll", "fin_pll", AUD_PLL_LOCK,
+		AUD_PLL_CON0, NULL),
+};
+
+static struct samsung_cmu_info topc_cmu_info __initdata = {
+	.pll_clks		= topc_pll_clks,
+	.nr_pll_clks		= ARRAY_SIZE(topc_pll_clks),
+	.mux_clks		= topc_mux_clks,
+	.nr_mux_clks		= ARRAY_SIZE(topc_mux_clks),
+	.div_clks		= topc_div_clks,
+	.nr_div_clks		= ARRAY_SIZE(topc_div_clks),
+	.fixed_factor_clks	= topc_fixed_factor_clks,
+	.nr_fixed_factor_clks	= ARRAY_SIZE(topc_fixed_factor_clks),
+	.nr_clk_ids		= TOPC_NR_CLK,
+	.clk_regs		= topc_clk_regs,
+	.nr_clk_regs		= ARRAY_SIZE(topc_clk_regs),
+};
+
+static void __init exynos7_clk_topc_init(struct device_node *np)
+{
+	samsung_cmu_register_one(np, &topc_cmu_info);
+}
+
+CLK_OF_DECLARE(exynos7_clk_topc, "samsung,exynos7-clock-topc",
+	exynos7_clk_topc_init);
+
+/* Register Offset definitions for CMU_TOP0 (0x105D0000) */
+#define MUX_SEL_TOP00			0x0200
+#define MUX_SEL_TOP01			0x0204
+#define MUX_SEL_TOP03			0x020C
+#define MUX_SEL_TOP0_PERIC3		0x023C
+#define DIV_TOP03			0x060C
+#define DIV_TOP0_PERIC3			0x063C
+#define ENABLE_SCLK_TOP0_PERIC3		0x0A3C
+
+/* List of parent clocks for Muxes in CMU_TOP0 */
+PNAME(mout_bus0_pll_p)	= { "fin_pll", "dout_sclk_bus0_pll" };
+PNAME(mout_bus1_pll_p)	= { "fin_pll", "dout_sclk_bus1_pll" };
+PNAME(mout_cc_pll_p)	= { "fin_pll", "dout_sclk_cc_pll" };
+PNAME(mout_mfc_pll_p)	= { "fin_pll", "dout_sclk_mfc_pll" };
+
+PNAME(mout_top0_half_bus0_pll_p) = {"mout_top0_bus0_pll",
+	"ffac_top0_bus0_pll_div2"};
+PNAME(mout_top0_half_bus1_pll_p) = {"mout_top0_bus1_pll",
+	"ffac_top0_bus1_pll_div2"};
+PNAME(mout_top0_half_cc_pll_p) = {"mout_top0_cc_pll",
+	"ffac_top0_cc_pll_div2"};
+PNAME(mout_top0_half_mfc_pll_p) = {"mout_top0_mfc_pll",
+	"ffac_top0_mfc_pll_div2"};
+
+PNAME(mout_top0_group1) = {"mout_top0_half_bus0_pll",
+	"mout_top0_half_bus1_pll", "mout_top0_half_cc_pll",
+	"mout_top0_half_mfc_pll"};
+
+static unsigned long top0_clk_regs[] __initdata = {
+	MUX_SEL_TOP00,
+	MUX_SEL_TOP01,
+	MUX_SEL_TOP03,
+	MUX_SEL_TOP0_PERIC3,
+	DIV_TOP03,
+	DIV_TOP0_PERIC3,
+	ENABLE_SCLK_TOP0_PERIC3,
+};
+
+static struct samsung_mux_clock top0_mux_clks[] __initdata = {
+	MUX(0, "mout_top0_mfc_pll", mout_mfc_pll_p, MUX_SEL_TOP00, 4, 1),
+	MUX(0, "mout_top0_cc_pll", mout_cc_pll_p, MUX_SEL_TOP00, 8, 1),
+	MUX(0, "mout_top0_bus1_pll", mout_bus1_pll_p, MUX_SEL_TOP00, 12, 1),
+	MUX(0, "mout_top0_bus0_pll", mout_bus0_pll_p, MUX_SEL_TOP00, 16, 1),
+
+	MUX(0, "mout_top0_half_mfc_pll", mout_top0_half_mfc_pll_p,
+		MUX_SEL_TOP01, 4, 1),
+	MUX(0, "mout_top0_half_cc_pll", mout_top0_half_cc_pll_p,
+		MUX_SEL_TOP01, 8, 1),
+	MUX(0, "mout_top0_half_bus1_pll", mout_top0_half_bus1_pll_p,
+		MUX_SEL_TOP01, 12, 1),
+	MUX(0, "mout_top0_half_bus0_pll", mout_top0_half_bus0_pll_p,
+		MUX_SEL_TOP01, 16, 1),
+
+	MUX(0, "mout_aclk_peric1_66", mout_top0_group1, MUX_SEL_TOP03, 12, 2),
+	MUX(0, "mout_aclk_peric0_66", mout_top0_group1, MUX_SEL_TOP03, 20, 2),
+
+	MUX(0, "mout_sclk_uart3", mout_top0_group1, MUX_SEL_TOP0_PERIC3, 4, 2),
+	MUX(0, "mout_sclk_uart2", mout_top0_group1, MUX_SEL_TOP0_PERIC3, 8, 2),
+	MUX(0, "mout_sclk_uart1", mout_top0_group1, MUX_SEL_TOP0_PERIC3, 12, 2),
+	MUX(0, "mout_sclk_uart0", mout_top0_group1, MUX_SEL_TOP0_PERIC3, 16, 2),
+};
+
+static struct samsung_div_clock top0_div_clks[] __initdata = {
+	DIV(DOUT_ACLK_PERIC1, "dout_aclk_peric1_66", "mout_aclk_peric1_66",
+		DIV_TOP03, 12, 6),
+	DIV(DOUT_ACLK_PERIC0, "dout_aclk_peric0_66", "mout_aclk_peric0_66",
+		DIV_TOP03, 20, 6),
+
+	DIV(0, "dout_sclk_uart3", "mout_sclk_uart3", DIV_TOP0_PERIC3, 4, 4),
+	DIV(0, "dout_sclk_uart2", "mout_sclk_uart2", DIV_TOP0_PERIC3, 8, 4),
+	DIV(0, "dout_sclk_uart1", "mout_sclk_uart1", DIV_TOP0_PERIC3, 12, 4),
+	DIV(0, "dout_sclk_uart0", "mout_sclk_uart0", DIV_TOP0_PERIC3, 16, 4),
+};
+
+static struct samsung_gate_clock top0_gate_clks[] __initdata = {
+	GATE(CLK_SCLK_UART3, "sclk_uart3", "dout_sclk_uart3",
+		ENABLE_SCLK_TOP0_PERIC3, 4, 0, 0),
+	GATE(CLK_SCLK_UART2, "sclk_uart2", "dout_sclk_uart2",
+		ENABLE_SCLK_TOP0_PERIC3, 8, 0, 0),
+	GATE(CLK_SCLK_UART1, "sclk_uart1", "dout_sclk_uart1",
+		ENABLE_SCLK_TOP0_PERIC3, 12, 0, 0),
+	GATE(CLK_SCLK_UART0, "sclk_uart0", "dout_sclk_uart0",
+		ENABLE_SCLK_TOP0_PERIC3, 16, 0, 0),
+};
+
+static struct samsung_fixed_factor_clock top0_fixed_factor_clks[] __initdata = {
+	FFACTOR(0, "ffac_top0_bus0_pll_div2", "mout_top0_bus0_pll", 1, 2, 0),
+	FFACTOR(0, "ffac_top0_bus1_pll_div2", "mout_top0_bus1_pll", 1, 2, 0),
+	FFACTOR(0, "ffac_top0_cc_pll_div2", "mout_top0_cc_pll", 1, 2, 0),
+	FFACTOR(0, "ffac_top0_mfc_pll_div2", "mout_top0_mfc_pll", 1, 2, 0),
+};
+
+static struct samsung_cmu_info top0_cmu_info __initdata = {
+	.mux_clks		= top0_mux_clks,
+	.nr_mux_clks		= ARRAY_SIZE(top0_mux_clks),
+	.div_clks		= top0_div_clks,
+	.nr_div_clks		= ARRAY_SIZE(top0_div_clks),
+	.gate_clks		= top0_gate_clks,
+	.nr_gate_clks		= ARRAY_SIZE(top0_gate_clks),
+	.fixed_factor_clks	= top0_fixed_factor_clks,
+	.nr_fixed_factor_clks	= ARRAY_SIZE(top0_fixed_factor_clks),
+	.nr_clk_ids		= TOP0_NR_CLK,
+	.clk_regs		= top0_clk_regs,
+	.nr_clk_regs		= ARRAY_SIZE(top0_clk_regs),
+};
+
+static void __init exynos7_clk_top0_init(struct device_node *np)
+{
+	samsung_cmu_register_one(np, &top0_cmu_info);
+}
+
+CLK_OF_DECLARE(exynos7_clk_top0, "samsung,exynos7-clock-top0",
+	exynos7_clk_top0_init);
+
+/* Register Offset definitions for CMU_PERIC0 (0x13610000) */
+#define MUX_SEL_PERIC0			0x0200
+#define ENABLE_PCLK_PERIC0		0x0900
+#define ENABLE_SCLK_PERIC0		0x0A00
+
+/* List of parent clocks for Muxes in CMU_PERIC0 */
+PNAME(mout_aclk_peric0_66_p)	= { "fin_pll", "dout_aclk_peric0_66" };
+PNAME(mout_sclk_uart0_p)	= { "fin_pll", "sclk_uart0" };
+
+static unsigned long peric0_clk_regs[] __initdata = {
+	MUX_SEL_PERIC0,
+	ENABLE_PCLK_PERIC0,
+	ENABLE_SCLK_PERIC0,
+};
+
+static struct samsung_mux_clock peric0_mux_clks[] __initdata = {
+	MUX(0, "mout_aclk_peric0_66_user", mout_aclk_peric0_66_p,
+		MUX_SEL_PERIC0, 0, 1),
+	MUX(0, "mout_sclk_uart0_user", mout_sclk_uart0_p,
+		MUX_SEL_PERIC0, 16, 1),
+};
+
+static struct samsung_gate_clock peric0_gate_clks[] __initdata = {
+	GATE(PCLK_UART0, "pclk_uart0", "mout_aclk_peric0_66_user",
+		ENABLE_PCLK_PERIC0, 16, 0, 0),
+
+	GATE(SCLK_UART0, "sclk_uart0_user", "mout_sclk_uart0_user",
+		ENABLE_SCLK_PERIC0, 16, 0, 0),
+};
+
+static struct samsung_cmu_info peric0_cmu_info __initdata = {
+	.mux_clks		= peric0_mux_clks,
+	.nr_mux_clks		= ARRAY_SIZE(peric0_mux_clks),
+	.gate_clks		= peric0_gate_clks,
+	.nr_gate_clks		= ARRAY_SIZE(peric0_gate_clks),
+	.nr_clk_ids		= PERIC0_NR_CLK,
+	.clk_regs		= peric0_clk_regs,
+	.nr_clk_regs		= ARRAY_SIZE(peric0_clk_regs),
+};
+
+static void __init exynos7_clk_peric0_init(struct device_node *np)
+{
+	samsung_cmu_register_one(np, &peric0_cmu_info);
+}
+
+/* Register Offset definitions for CMU_PERIC1 (0x14C80000) */
+#define MUX_SEL_PERIC10			0x0200
+#define MUX_SEL_PERIC11			0x0204
+#define ENABLE_PCLK_PERIC1		0x0900
+#define ENABLE_SCLK_PERIC10		0x0A00
+
+CLK_OF_DECLARE(exynos7_clk_peric0, "samsung,exynos7-clock-peric0",
+	exynos7_clk_peric0_init);
+
+/* List of parent clocks for Muxes in CMU_PERIC1 */
+PNAME(mout_aclk_peric1_66_p)	= { "fin_pll", "dout_aclk_peric1_66" };
+PNAME(mout_sclk_uart1_p)	= { "fin_pll", "sclk_uart1" };
+PNAME(mout_sclk_uart2_p)	= { "fin_pll", "sclk_uart2" };
+PNAME(mout_sclk_uart3_p)	= { "fin_pll", "sclk_uart3" };
+
+static unsigned long peric1_clk_regs[] __initdata = {
+	MUX_SEL_PERIC10,
+	MUX_SEL_PERIC11,
+	ENABLE_PCLK_PERIC1,
+	ENABLE_SCLK_PERIC10,
+};
+
+static struct samsung_mux_clock peric1_mux_clks[] __initdata = {
+	MUX(0, "mout_aclk_peric1_66_user", mout_aclk_peric1_66_p,
+		MUX_SEL_PERIC10, 0, 1),
+
+	MUX(0, "mout_sclk_uart1_user", mout_sclk_uart1_p,
+		MUX_SEL_PERIC11, 20, 1),
+	MUX(0, "mout_sclk_uart2_user", mout_sclk_uart2_p,
+		MUX_SEL_PERIC11, 24, 1),
+	MUX(0, "mout_sclk_uart3_user", mout_sclk_uart3_p,
+		MUX_SEL_PERIC11, 28, 1),
+};
+
+static struct samsung_gate_clock peric1_gate_clks[] __initdata = {
+	GATE(PCLK_UART1, "pclk_uart1", "mout_aclk_peric1_66_user",
+		ENABLE_PCLK_PERIC1, 9, 0, 0),
+	GATE(PCLK_UART2, "pclk_uart2", "mout_aclk_peric1_66_user",
+		ENABLE_PCLK_PERIC1, 10, 0, 0),
+	GATE(PCLK_UART3, "pclk_uart3", "mout_aclk_peric1_66_user",
+		ENABLE_PCLK_PERIC1, 11, 0, 0),
+
+	GATE(SCLK_UART1, "sclk_uart1_user", "mout_sclk_uart1_user",
+		ENABLE_SCLK_PERIC10, 9, 0, 0),
+	GATE(SCLK_UART2, "sclk_uart2_user", "mout_sclk_uart2_user",
+		ENABLE_SCLK_PERIC10, 10, 0, 0),
+	GATE(SCLK_UART3, "sclk_uart3_user", "mout_sclk_uart3_user",
+		ENABLE_SCLK_PERIC10, 11, 0, 0),
+};
+
+static struct samsung_cmu_info peric1_cmu_info __initdata = {
+	.mux_clks		= peric1_mux_clks,
+	.nr_mux_clks		= ARRAY_SIZE(peric1_mux_clks),
+	.gate_clks		= peric1_gate_clks,
+	.nr_gate_clks		= ARRAY_SIZE(peric1_gate_clks),
+	.nr_clk_ids		= PERIC1_NR_CLK,
+	.clk_regs		= peric1_clk_regs,
+	.nr_clk_regs		= ARRAY_SIZE(peric1_clk_regs),
+};
+
+static void __init exynos7_clk_peric1_init(struct device_node *np)
+{
+	samsung_cmu_register_one(np, &peric1_cmu_info);
+}
+
+CLK_OF_DECLARE(exynos7_clk_peric1, "samsung,exynos7-clock-peric1",
+	exynos7_clk_peric1_init);
+
+/* Register Offset definitions for CMU_PERIS (0x10040000) */
+#define MUX_SEL_PERIS			0x0200
+#define ENABLE_PCLK_PERIS_SECURE_CHIPID	0x0910
+#define ENABLE_SCLK_PERIS_SECURE_CHIPID	0x0A10
+
+/* List of parent clocks for Muxes in CMU_PERIS */
+PNAME(mout_aclk_peris_66_p) = { "fin_pll", "dout_aclk_peris_66" };
+
+static unsigned long peris_clk_regs[] __initdata = {
+	MUX_SEL_PERIS,
+	ENABLE_PCLK_PERIS_SECURE_CHIPID,
+	ENABLE_SCLK_PERIS_SECURE_CHIPID,
+};
+
+static struct samsung_mux_clock peris_mux_clks[] __initdata = {
+	MUX(0, "mout_aclk_peris_66_user",
+		mout_aclk_peris_66_p, MUX_SEL_PERIS, 0, 1),
+};
+
+static struct samsung_gate_clock peris_gate_clks[] __initdata = {
+	GATE(PCLK_CHIPID, "pclk_chipid", "mout_aclk_peris_66_user",
+		ENABLE_PCLK_PERIS_SECURE_CHIPID, 0, 0, 0),
+	GATE(SCLK_CHIPID, "sclk_chipid", "fin_pll",
+		ENABLE_SCLK_PERIS_SECURE_CHIPID, 0, 0, 0),
+};
+
+static struct samsung_cmu_info peris_cmu_info __initdata = {
+	.mux_clks		= peris_mux_clks,
+	.nr_mux_clks		= ARRAY_SIZE(peris_mux_clks),
+	.gate_clks		= peris_gate_clks,
+	.nr_gate_clks		= ARRAY_SIZE(peris_gate_clks),
+	.nr_clk_ids		= PERIS_NR_CLK,
+	.clk_regs		= peris_clk_regs,
+	.nr_clk_regs		= ARRAY_SIZE(peris_clk_regs),
+};
+
+static void __init exynos7_clk_peris_init(struct device_node *np)
+{
+	samsung_cmu_register_one(np, &peris_cmu_info);
+}
+
+CLK_OF_DECLARE(exynos7_clk_peris, "samsung,exynos7-clock-peris",
+	exynos7_clk_peris_init);
diff --git a/include/dt-bindings/clock/exynos7-clk.h b/include/dt-bindings/clock/exynos7-clk.h
new file mode 100644
index 00000000000..00fd6de1cb2
--- /dev/null
+++ b/include/dt-bindings/clock/exynos7-clk.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author: Naveen Krishna Ch <naveenkrishna.ch@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef _DT_BINDINGS_CLOCK_EXYNOS7_H
+#define _DT_BINDINGS_CLOCK_EXYNOS7_H
+
+/* TOPC */
+#define DOUT_ACLK_PERIS			1
+#define DOUT_SCLK_BUS0_PLL		2
+#define DOUT_SCLK_BUS1_PLL		3
+#define DOUT_SCLK_CC_PLL		4
+#define DOUT_SCLK_MFC_PLL		5
+#define TOPC_NR_CLK			6
+
+/* TOP0 */
+#define DOUT_ACLK_PERIC1		1
+#define DOUT_ACLK_PERIC0		2
+#define CLK_SCLK_UART0			3
+#define CLK_SCLK_UART1			4
+#define CLK_SCLK_UART2			5
+#define CLK_SCLK_UART3			6
+#define TOP0_NR_CLK			7
+
+/* PERIC0 */
+#define PCLK_UART0			1
+#define SCLK_UART0			2
+#define PERIC0_NR_CLK			3
+
+/* PERIC1 */
+#define PCLK_UART1			1
+#define PCLK_UART2			2
+#define PCLK_UART3			3
+#define SCLK_UART1			4
+#define SCLK_UART2			5
+#define SCLK_UART3			6
+#define PERIC1_NR_CLK			7
+
+/* PERIS */
+#define PCLK_CHIPID			1
+#define SCLK_CHIPID			2
+#define PERIS_NR_CLK			3
+
+#endif /* _DT_BINDINGS_CLOCK_EXYNOS7_H */
-- 
cgit v1.2.3-70-g09d2


From 57a2b485fa512be47b479077b5f89e1bfe536709 Mon Sep 17 00:00:00 2001
From: Naveen Krishna Ch <naveenkrishna.ch@gmail.com>
Date: Tue, 21 Oct 2014 11:13:51 +0530
Subject: clk: samsung: exynos7: add clocks for I2C block

Exynos7 supports 12 I2C channels, add the I2C gate clocks to
support them.

Signed-off-by: Naveen Krishna Ch <naveenkrishna.ch@gmail.com>
Signed-off-by: Abhilash Kesavan <a.kesavan@samsung.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
---
 drivers/clk/samsung/clk-exynos7.c       | 24 ++++++++++++++++++++++++
 include/dt-bindings/clock/exynos7-clk.h | 16 ++++++++++++++--
 2 files changed, 38 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/samsung/clk-exynos7.c b/drivers/clk/samsung/clk-exynos7.c
index 54206d4d408..c700f654289 100644
--- a/drivers/clk/samsung/clk-exynos7.c
+++ b/drivers/clk/samsung/clk-exynos7.c
@@ -290,6 +290,20 @@ static struct samsung_mux_clock peric0_mux_clks[] __initdata = {
 };
 
 static struct samsung_gate_clock peric0_gate_clks[] __initdata = {
+	GATE(PCLK_HSI2C0, "pclk_hsi2c0", "mout_aclk_peric0_66_user",
+		ENABLE_PCLK_PERIC0, 8, 0, 0),
+	GATE(PCLK_HSI2C1, "pclk_hsi2c1", "mout_aclk_peric0_66_user",
+		ENABLE_PCLK_PERIC0, 9, 0, 0),
+	GATE(PCLK_HSI2C4, "pclk_hsi2c4", "mout_aclk_peric0_66_user",
+		ENABLE_PCLK_PERIC0, 10, 0, 0),
+	GATE(PCLK_HSI2C5, "pclk_hsi2c5", "mout_aclk_peric0_66_user",
+		ENABLE_PCLK_PERIC0, 11, 0, 0),
+	GATE(PCLK_HSI2C9, "pclk_hsi2c9", "mout_aclk_peric0_66_user",
+		ENABLE_PCLK_PERIC0, 12, 0, 0),
+	GATE(PCLK_HSI2C10, "pclk_hsi2c10", "mout_aclk_peric0_66_user",
+		ENABLE_PCLK_PERIC0, 13, 0, 0),
+	GATE(PCLK_HSI2C11, "pclk_hsi2c11", "mout_aclk_peric0_66_user",
+		ENABLE_PCLK_PERIC0, 14, 0, 0),
 	GATE(PCLK_UART0, "pclk_uart0", "mout_aclk_peric0_66_user",
 		ENABLE_PCLK_PERIC0, 16, 0, 0),
 
@@ -347,6 +361,16 @@ static struct samsung_mux_clock peric1_mux_clks[] __initdata = {
 };
 
 static struct samsung_gate_clock peric1_gate_clks[] __initdata = {
+	GATE(PCLK_HSI2C2, "pclk_hsi2c2", "mout_aclk_peric1_66_user",
+		ENABLE_PCLK_PERIC1, 4, 0, 0),
+	GATE(PCLK_HSI2C3, "pclk_hsi2c3", "mout_aclk_peric1_66_user",
+		ENABLE_PCLK_PERIC1, 5, 0, 0),
+	GATE(PCLK_HSI2C6, "pclk_hsi2c6", "mout_aclk_peric1_66_user",
+		ENABLE_PCLK_PERIC1, 6, 0, 0),
+	GATE(PCLK_HSI2C7, "pclk_hsi2c7", "mout_aclk_peric1_66_user",
+		ENABLE_PCLK_PERIC1, 7, 0, 0),
+	GATE(PCLK_HSI2C8, "pclk_hsi2c8", "mout_aclk_peric1_66_user",
+		ENABLE_PCLK_PERIC1, 8, 0, 0),
 	GATE(PCLK_UART1, "pclk_uart1", "mout_aclk_peric1_66_user",
 		ENABLE_PCLK_PERIC1, 9, 0, 0),
 	GATE(PCLK_UART2, "pclk_uart2", "mout_aclk_peric1_66_user",
diff --git a/include/dt-bindings/clock/exynos7-clk.h b/include/dt-bindings/clock/exynos7-clk.h
index 00fd6de1cb2..6d07b6f1d61 100644
--- a/include/dt-bindings/clock/exynos7-clk.h
+++ b/include/dt-bindings/clock/exynos7-clk.h
@@ -30,7 +30,14 @@
 /* PERIC0 */
 #define PCLK_UART0			1
 #define SCLK_UART0			2
-#define PERIC0_NR_CLK			3
+#define PCLK_HSI2C0			3
+#define PCLK_HSI2C1			4
+#define PCLK_HSI2C4			5
+#define PCLK_HSI2C5			6
+#define PCLK_HSI2C9			7
+#define PCLK_HSI2C10			8
+#define PCLK_HSI2C11			9
+#define PERIC0_NR_CLK			10
 
 /* PERIC1 */
 #define PCLK_UART1			1
@@ -39,7 +46,12 @@
 #define SCLK_UART1			4
 #define SCLK_UART2			5
 #define SCLK_UART3			6
-#define PERIC1_NR_CLK			7
+#define PCLK_HSI2C2			7
+#define PCLK_HSI2C3			8
+#define PCLK_HSI2C6			9
+#define PCLK_HSI2C7			10
+#define PCLK_HSI2C8			11
+#define PERIC1_NR_CLK			12
 
 /* PERIS */
 #define PCLK_CHIPID			1
-- 
cgit v1.2.3-70-g09d2


From 6d0c8c723f0b886f58263c089831fd2bee0b3b57 Mon Sep 17 00:00:00 2001
From: Naveen Krishna Ch <naveenkrishna.ch@gmail.com>
Date: Tue, 21 Oct 2014 11:13:52 +0530
Subject: clk: samsung: exynos7: add clocks for MMC block

Exynos7 supports 3 MMC channels, add the MMC gate clocks to
support them.

Signed-off-by: Naveen Krishna Ch <naveenkrishna.ch@gmail.com>
Signed-off-by: Abhilash Kesavan <a.kesavan@samsung.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
---
 .../devicetree/bindings/clock/exynos7-clock.txt    |  21 ++
 drivers/clk/samsung/clk-exynos7.c                  | 224 +++++++++++++++++++++
 include/dt-bindings/clock/exynos7-clk.h            |  20 ++
 3 files changed, 265 insertions(+)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/exynos7-clock.txt b/Documentation/devicetree/bindings/clock/exynos7-clock.txt
index 789f76132a8..b29cb50048c 100644
--- a/Documentation/devicetree/bindings/clock/exynos7-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos7-clock.txt
@@ -27,9 +27,12 @@ Required Properties for Clock Controller:
 
 	- "samsung,exynos7-clock-topc"
 	- "samsung,exynos7-clock-top0"
+	- "samsung,exynos7-clock-top1"
 	- "samsung,exynos7-clock-peric0"
 	- "samsung,exynos7-clock-peric1"
 	- "samsung,exynos7-clock-peris"
+	- "samsung,exynos7-clock-fsys0"
+	- "samsung,exynos7-clock-fsys1"
 
  - reg: physical base address of the controller and the length of
 	memory mapped region.
@@ -50,6 +53,13 @@ Input clocks for top0 clock controller:
 	- dout_sclk_cc_pll
 	- dout_sclk_mfc_pll
 
+Input clocks for top1 clock controller:
+	- fin_pll
+	- dout_sclk_bus0_pll
+	- dout_sclk_bus1_pll
+	- dout_sclk_cc_pll
+	- dout_sclk_mfc_pll
+
 Input clocks for peric0 clock controller:
 	- fin_pll
 	- dout_aclk_peric0_66
@@ -65,3 +75,14 @@ Input clocks for peric1 clock controller:
 Input clocks for peris clock controller:
 	- fin_pll
 	- dout_aclk_peris_66
+
+Input clocks for fsys0 clock controller:
+	- fin_pll
+	- dout_aclk_fsys0_200
+	- dout_sclk_mmc2
+
+Input clocks for fsys1 clock controller:
+	- fin_pll
+	- dout_aclk_fsys1_200
+	- dout_sclk_mmc0
+	- dout_sclk_mmc1
diff --git a/drivers/clk/samsung/clk-exynos7.c b/drivers/clk/samsung/clk-exynos7.c
index c700f654289..f5e43fab195 100644
--- a/drivers/clk/samsung/clk-exynos7.c
+++ b/drivers/clk/samsung/clk-exynos7.c
@@ -267,6 +267,132 @@ static void __init exynos7_clk_top0_init(struct device_node *np)
 CLK_OF_DECLARE(exynos7_clk_top0, "samsung,exynos7-clock-top0",
 	exynos7_clk_top0_init);
 
+/* Register Offset definitions for CMU_TOP1 (0x105E0000) */
+#define MUX_SEL_TOP10			0x0200
+#define MUX_SEL_TOP11			0x0204
+#define MUX_SEL_TOP13			0x020C
+#define MUX_SEL_TOP1_FSYS0		0x0224
+#define MUX_SEL_TOP1_FSYS1		0x0228
+#define DIV_TOP13			0x060C
+#define DIV_TOP1_FSYS0			0x0624
+#define DIV_TOP1_FSYS1			0x0628
+#define ENABLE_ACLK_TOP13		0x080C
+#define ENABLE_SCLK_TOP1_FSYS0		0x0A24
+#define ENABLE_SCLK_TOP1_FSYS1		0x0A28
+
+/* List of parent clocks for Muxes in CMU_TOP1 */
+PNAME(mout_top1_bus0_pll_p)	= { "fin_pll", "dout_sclk_bus0_pll" };
+PNAME(mout_top1_bus1_pll_p)	= { "fin_pll", "dout_sclk_bus1_pll_b" };
+PNAME(mout_top1_cc_pll_p)	= { "fin_pll", "dout_sclk_cc_pll_b" };
+PNAME(mout_top1_mfc_pll_p)	= { "fin_pll", "dout_sclk_mfc_pll_b" };
+
+PNAME(mout_top1_half_bus0_pll_p) = {"mout_top1_bus0_pll",
+	"ffac_top1_bus0_pll_div2"};
+PNAME(mout_top1_half_bus1_pll_p) = {"mout_top1_bus1_pll",
+	"ffac_top1_bus1_pll_div2"};
+PNAME(mout_top1_half_cc_pll_p) = {"mout_top1_cc_pll",
+	"ffac_top1_cc_pll_div2"};
+PNAME(mout_top1_half_mfc_pll_p) = {"mout_top1_mfc_pll",
+	"ffac_top1_mfc_pll_div2"};
+
+PNAME(mout_top1_group1) = {"mout_top1_half_bus0_pll",
+	"mout_top1_half_bus1_pll", "mout_top1_half_cc_pll",
+	"mout_top1_half_mfc_pll"};
+
+static unsigned long top1_clk_regs[] __initdata = {
+	MUX_SEL_TOP10,
+	MUX_SEL_TOP11,
+	MUX_SEL_TOP13,
+	MUX_SEL_TOP1_FSYS0,
+	MUX_SEL_TOP1_FSYS1,
+	DIV_TOP13,
+	DIV_TOP1_FSYS0,
+	DIV_TOP1_FSYS1,
+	ENABLE_ACLK_TOP13,
+	ENABLE_SCLK_TOP1_FSYS0,
+	ENABLE_SCLK_TOP1_FSYS1,
+};
+
+static struct samsung_mux_clock top1_mux_clks[] __initdata = {
+	MUX(0, "mout_top1_mfc_pll", mout_top1_mfc_pll_p, MUX_SEL_TOP10, 4, 1),
+	MUX(0, "mout_top1_cc_pll", mout_top1_cc_pll_p, MUX_SEL_TOP10, 8, 1),
+	MUX(0, "mout_top1_bus1_pll", mout_top1_bus1_pll_p,
+		MUX_SEL_TOP10, 12, 1),
+	MUX(0, "mout_top1_bus0_pll", mout_top1_bus0_pll_p,
+		MUX_SEL_TOP10, 16, 1),
+
+	MUX(0, "mout_top1_half_mfc_pll", mout_top1_half_mfc_pll_p,
+		MUX_SEL_TOP11, 4, 1),
+	MUX(0, "mout_top1_half_cc_pll", mout_top1_half_cc_pll_p,
+		MUX_SEL_TOP11, 8, 1),
+	MUX(0, "mout_top1_half_bus1_pll", mout_top1_half_bus1_pll_p,
+		MUX_SEL_TOP11, 12, 1),
+	MUX(0, "mout_top1_half_bus0_pll", mout_top1_half_bus0_pll_p,
+		MUX_SEL_TOP11, 16, 1),
+
+	MUX(0, "mout_aclk_fsys1_200", mout_top1_group1, MUX_SEL_TOP13, 24, 2),
+	MUX(0, "mout_aclk_fsys0_200", mout_top1_group1, MUX_SEL_TOP13, 28, 2),
+
+	MUX(0, "mout_sclk_mmc2", mout_top1_group1, MUX_SEL_TOP1_FSYS0, 24, 2),
+
+	MUX(0, "mout_sclk_mmc1", mout_top1_group1, MUX_SEL_TOP1_FSYS1, 24, 2),
+	MUX(0, "mout_sclk_mmc0", mout_top1_group1, MUX_SEL_TOP1_FSYS1, 28, 2),
+};
+
+static struct samsung_div_clock top1_div_clks[] __initdata = {
+	DIV(DOUT_ACLK_FSYS1_200, "dout_aclk_fsys1_200", "mout_aclk_fsys1_200",
+		DIV_TOP13, 24, 4),
+	DIV(DOUT_ACLK_FSYS0_200, "dout_aclk_fsys0_200", "mout_aclk_fsys0_200",
+		DIV_TOP13, 28, 4),
+
+	DIV(DOUT_SCLK_MMC2, "dout_sclk_mmc2", "mout_sclk_mmc2",
+		DIV_TOP1_FSYS0, 24, 4),
+
+	DIV(DOUT_SCLK_MMC1, "dout_sclk_mmc1", "mout_sclk_mmc1",
+		DIV_TOP1_FSYS1, 24, 4),
+	DIV(DOUT_SCLK_MMC0, "dout_sclk_mmc0", "mout_sclk_mmc0",
+		DIV_TOP1_FSYS1, 28, 4),
+};
+
+static struct samsung_gate_clock top1_gate_clks[] __initdata = {
+	GATE(CLK_SCLK_MMC2, "sclk_mmc2", "dout_sclk_mmc2",
+		ENABLE_SCLK_TOP1_FSYS0, 24, CLK_SET_RATE_PARENT, 0),
+
+	GATE(CLK_SCLK_MMC1, "sclk_mmc1", "dout_sclk_mmc1",
+		ENABLE_SCLK_TOP1_FSYS1, 24, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_MMC0, "sclk_mmc0", "dout_sclk_mmc0",
+		ENABLE_SCLK_TOP1_FSYS1, 28, CLK_SET_RATE_PARENT, 0),
+};
+
+static struct samsung_fixed_factor_clock top1_fixed_factor_clks[] __initdata = {
+	FFACTOR(0, "ffac_top1_bus0_pll_div2", "mout_top1_bus0_pll", 1, 2, 0),
+	FFACTOR(0, "ffac_top1_bus1_pll_div2", "mout_top1_bus1_pll", 1, 2, 0),
+	FFACTOR(0, "ffac_top1_cc_pll_div2", "mout_top1_cc_pll", 1, 2, 0),
+	FFACTOR(0, "ffac_top1_mfc_pll_div2", "mout_top1_mfc_pll", 1, 2, 0),
+};
+
+static struct samsung_cmu_info top1_cmu_info __initdata = {
+	.mux_clks		= top1_mux_clks,
+	.nr_mux_clks		= ARRAY_SIZE(top1_mux_clks),
+	.div_clks		= top1_div_clks,
+	.nr_div_clks		= ARRAY_SIZE(top1_div_clks),
+	.gate_clks		= top1_gate_clks,
+	.nr_gate_clks		= ARRAY_SIZE(top1_gate_clks),
+	.fixed_factor_clks	= top1_fixed_factor_clks,
+	.nr_fixed_factor_clks	= ARRAY_SIZE(top1_fixed_factor_clks),
+	.nr_clk_ids		= TOP1_NR_CLK,
+	.clk_regs		= top1_clk_regs,
+	.nr_clk_regs		= ARRAY_SIZE(top1_clk_regs),
+};
+
+static void __init exynos7_clk_top1_init(struct device_node *np)
+{
+	samsung_cmu_register_one(np, &top1_cmu_info);
+}
+
+CLK_OF_DECLARE(exynos7_clk_top1, "samsung,exynos7-clock-top1",
+	exynos7_clk_top1_init);
+
 /* Register Offset definitions for CMU_PERIC0 (0x13610000) */
 #define MUX_SEL_PERIC0			0x0200
 #define ENABLE_PCLK_PERIC0		0x0900
@@ -447,3 +573,101 @@ static void __init exynos7_clk_peris_init(struct device_node *np)
 
 CLK_OF_DECLARE(exynos7_clk_peris, "samsung,exynos7-clock-peris",
 	exynos7_clk_peris_init);
+
+/* Register Offset definitions for CMU_FSYS0 (0x10E90000) */
+#define MUX_SEL_FSYS00			0x0200
+#define MUX_SEL_FSYS01			0x0204
+#define ENABLE_ACLK_FSYS01		0x0804
+
+/*
+ * List of parent clocks for Muxes in CMU_FSYS0
+ */
+PNAME(mout_aclk_fsys0_200_p)	= { "fin_pll", "dout_aclk_fsys0_200" };
+PNAME(mout_sclk_mmc2_p)		= { "fin_pll", "sclk_mmc2" };
+
+static unsigned long fsys0_clk_regs[] __initdata = {
+	MUX_SEL_FSYS00,
+	MUX_SEL_FSYS01,
+	ENABLE_ACLK_FSYS01,
+};
+
+static struct samsung_mux_clock fsys0_mux_clks[] __initdata = {
+	MUX(0, "mout_aclk_fsys0_200_user", mout_aclk_fsys0_200_p,
+		MUX_SEL_FSYS00, 24, 1),
+
+	MUX(0, "mout_sclk_mmc2_user", mout_sclk_mmc2_p, MUX_SEL_FSYS01, 24, 1),
+};
+
+static struct samsung_gate_clock fsys0_gate_clks[] __initdata = {
+	GATE(ACLK_MMC2, "aclk_mmc2", "mout_aclk_fsys0_200_user",
+		ENABLE_ACLK_FSYS01, 31, 0, 0),
+};
+
+static struct samsung_cmu_info fsys0_cmu_info __initdata = {
+	.mux_clks		= fsys0_mux_clks,
+	.nr_mux_clks		= ARRAY_SIZE(fsys0_mux_clks),
+	.gate_clks		= fsys0_gate_clks,
+	.nr_gate_clks		= ARRAY_SIZE(fsys0_gate_clks),
+	.nr_clk_ids		= TOP1_NR_CLK,
+	.clk_regs		= fsys0_clk_regs,
+	.nr_clk_regs		= ARRAY_SIZE(fsys0_clk_regs),
+};
+
+static void __init exynos7_clk_fsys0_init(struct device_node *np)
+{
+	samsung_cmu_register_one(np, &fsys0_cmu_info);
+}
+
+CLK_OF_DECLARE(exynos7_clk_fsys0, "samsung,exynos7-clock-fsys0",
+	exynos7_clk_fsys0_init);
+
+/* Register Offset definitions for CMU_FSYS1 (0x156E0000) */
+#define MUX_SEL_FSYS10			0x0200
+#define MUX_SEL_FSYS11			0x0204
+#define ENABLE_ACLK_FSYS1		0x0800
+
+/*
+ * List of parent clocks for Muxes in CMU_FSYS1
+ */
+PNAME(mout_aclk_fsys1_200_p)	= { "fin_pll",  "dout_aclk_fsys1_200" };
+PNAME(mout_sclk_mmc0_p)		= { "fin_pll", "sclk_mmc0" };
+PNAME(mout_sclk_mmc1_p)		= { "fin_pll", "sclk_mmc1" };
+
+static unsigned long fsys1_clk_regs[] __initdata = {
+	MUX_SEL_FSYS10,
+	MUX_SEL_FSYS11,
+	ENABLE_ACLK_FSYS1,
+};
+
+static struct samsung_mux_clock fsys1_mux_clks[] __initdata = {
+	MUX(0, "mout_aclk_fsys1_200_user", mout_aclk_fsys1_200_p,
+		MUX_SEL_FSYS10, 28, 1),
+
+	MUX(0, "mout_sclk_mmc1_user", mout_sclk_mmc1_p, MUX_SEL_FSYS11, 24, 1),
+	MUX(0, "mout_sclk_mmc0_user", mout_sclk_mmc0_p, MUX_SEL_FSYS11, 28, 1),
+};
+
+static struct samsung_gate_clock fsys1_gate_clks[] __initdata = {
+	GATE(ACLK_MMC1, "aclk_mmc1", "mout_aclk_fsys1_200_user",
+		ENABLE_ACLK_FSYS1, 29, 0, 0),
+	GATE(ACLK_MMC0, "aclk_mmc0", "mout_aclk_fsys1_200_user",
+		ENABLE_ACLK_FSYS1, 30, 0, 0),
+};
+
+static struct samsung_cmu_info fsys1_cmu_info __initdata = {
+	.mux_clks		= fsys1_mux_clks,
+	.nr_mux_clks		= ARRAY_SIZE(fsys1_mux_clks),
+	.gate_clks		= fsys1_gate_clks,
+	.nr_gate_clks		= ARRAY_SIZE(fsys1_gate_clks),
+	.nr_clk_ids		= TOP1_NR_CLK,
+	.clk_regs		= fsys1_clk_regs,
+	.nr_clk_regs		= ARRAY_SIZE(fsys1_clk_regs),
+};
+
+static void __init exynos7_clk_fsys1_init(struct device_node *np)
+{
+	samsung_cmu_register_one(np, &fsys1_cmu_info);
+}
+
+CLK_OF_DECLARE(exynos7_clk_fsys1, "samsung,exynos7-clock-fsys1",
+	exynos7_clk_fsys1_init);
diff --git a/include/dt-bindings/clock/exynos7-clk.h b/include/dt-bindings/clock/exynos7-clk.h
index 6d07b6f1d61..ff63c4e15cc 100644
--- a/include/dt-bindings/clock/exynos7-clk.h
+++ b/include/dt-bindings/clock/exynos7-clk.h
@@ -27,6 +27,17 @@
 #define CLK_SCLK_UART3			6
 #define TOP0_NR_CLK			7
 
+/* TOP1 */
+#define DOUT_ACLK_FSYS1_200		1
+#define DOUT_ACLK_FSYS0_200		2
+#define DOUT_SCLK_MMC2			3
+#define DOUT_SCLK_MMC1			4
+#define DOUT_SCLK_MMC0			5
+#define CLK_SCLK_MMC2			6
+#define CLK_SCLK_MMC1			7
+#define CLK_SCLK_MMC0			8
+#define TOP1_NR_CLK			9
+
 /* PERIC0 */
 #define PCLK_UART0			1
 #define SCLK_UART0			2
@@ -58,4 +69,13 @@
 #define SCLK_CHIPID			2
 #define PERIS_NR_CLK			3
 
+/* FSYS0 */
+#define ACLK_MMC2			1
+#define FSYS0_NR_CLK			2
+
+/* FSYS1 */
+#define ACLK_MMC1			1
+#define ACLK_MMC0			2
+#define FSYS1_NR_CLK			3
+
 #endif /* _DT_BINDINGS_CLOCK_EXYNOS7_H */
-- 
cgit v1.2.3-70-g09d2


From f5e127cd5ee52b3f0edaeeb7a40c0b9599f4e691 Mon Sep 17 00:00:00 2001
From: Naveen Krishna Ch <naveenkrishna.ch@gmail.com>
Date: Tue, 28 Oct 2014 16:48:53 +0530
Subject: clk: samsung: exynos7: add clocks for RTC block

Add clock support for the RTC block in Exynos7.

Signed-off-by: Naveen Krishna Ch <naveenkrishna.ch@gmail.com>
Signed-off-by: Abhilash Kesavan <a.kesavan@samsung.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
---
 .../devicetree/bindings/clock/exynos7-clock.txt    |  5 ++
 drivers/clk/samsung/clk-exynos7.c                  | 54 ++++++++++++++++++++++
 include/dt-bindings/clock/exynos7-clk.h            |  7 ++-
 3 files changed, 65 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/exynos7-clock.txt b/Documentation/devicetree/bindings/clock/exynos7-clock.txt
index b29cb50048c..6d3d5f80c1c 100644
--- a/Documentation/devicetree/bindings/clock/exynos7-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos7-clock.txt
@@ -28,6 +28,7 @@ Required Properties for Clock Controller:
 	- "samsung,exynos7-clock-topc"
 	- "samsung,exynos7-clock-top0"
 	- "samsung,exynos7-clock-top1"
+	- "samsung,exynos7-clock-ccore"
 	- "samsung,exynos7-clock-peric0"
 	- "samsung,exynos7-clock-peric1"
 	- "samsung,exynos7-clock-peris"
@@ -60,6 +61,10 @@ Input clocks for top1 clock controller:
 	- dout_sclk_cc_pll
 	- dout_sclk_mfc_pll
 
+Input clocks for ccore clock controller:
+	- fin_pll
+	- dout_aclk_ccore_133
+
 Input clocks for peric0 clock controller:
 	- fin_pll
 	- dout_aclk_peric0_66
diff --git a/drivers/clk/samsung/clk-exynos7.c b/drivers/clk/samsung/clk-exynos7.c
index f5e43fab195..3a30f43fa92 100644
--- a/drivers/clk/samsung/clk-exynos7.c
+++ b/drivers/clk/samsung/clk-exynos7.c
@@ -29,7 +29,9 @@
 #define AUD_PLL_CON0		0x0140
 #define MUX_SEL_TOPC0		0x0200
 #define MUX_SEL_TOPC1		0x0204
+#define MUX_SEL_TOPC2		0x0208
 #define MUX_SEL_TOPC3		0x020C
+#define DIV_TOPC0		0x0600
 #define DIV_TOPC1		0x0604
 #define DIV_TOPC3		0x060C
 
@@ -78,7 +80,9 @@ static unsigned long topc_clk_regs[] __initdata = {
 	AUD_PLL_CON0,
 	MUX_SEL_TOPC0,
 	MUX_SEL_TOPC1,
+	MUX_SEL_TOPC2,
 	MUX_SEL_TOPC3,
+	DIV_TOPC0,
 	DIV_TOPC1,
 	DIV_TOPC3,
 };
@@ -101,10 +105,15 @@ static struct samsung_mux_clock topc_mux_clks[] __initdata = {
 	MUX(0, "mout_sclk_bus0_pll_out", mout_sclk_bus0_pll_out_p,
 		MUX_SEL_TOPC1, 16, 1),
 
+	MUX(0, "mout_aclk_ccore_133", mout_topc_group2,	MUX_SEL_TOPC2, 4, 2),
+
 	MUX(0, "mout_aclk_peris_66", mout_topc_group2, MUX_SEL_TOPC3, 24, 2),
 };
 
 static struct samsung_div_clock topc_div_clks[] __initdata = {
+	DIV(DOUT_ACLK_CCORE_133, "dout_aclk_ccore_133", "mout_aclk_ccore_133",
+		DIV_TOPC0, 4, 4),
+
 	DIV(DOUT_ACLK_PERIS, "dout_aclk_peris_66", "mout_aclk_peris_66",
 		DIV_TOPC1, 24, 4),
 
@@ -393,6 +402,51 @@ static void __init exynos7_clk_top1_init(struct device_node *np)
 CLK_OF_DECLARE(exynos7_clk_top1, "samsung,exynos7-clock-top1",
 	exynos7_clk_top1_init);
 
+/* Register Offset definitions for CMU_CCORE (0x105B0000) */
+#define MUX_SEL_CCORE			0x0200
+#define DIV_CCORE			0x0600
+#define ENABLE_ACLK_CCORE0		0x0800
+#define ENABLE_ACLK_CCORE1		0x0804
+#define ENABLE_PCLK_CCORE		0x0900
+
+/*
+ * List of parent clocks for Muxes in CMU_CCORE
+ */
+PNAME(mout_aclk_ccore_133_p)	= { "fin_pll", "dout_aclk_ccore_133" };
+
+static unsigned long ccore_clk_regs[] __initdata = {
+	MUX_SEL_CCORE,
+	ENABLE_PCLK_CCORE,
+};
+
+static struct samsung_mux_clock ccore_mux_clks[] __initdata = {
+	MUX(0, "mout_aclk_ccore_133_user", mout_aclk_ccore_133_p,
+		MUX_SEL_CCORE, 1, 1),
+};
+
+static struct samsung_gate_clock ccore_gate_clks[] __initdata = {
+	GATE(PCLK_RTC, "pclk_rtc", "mout_aclk_ccore_133_user",
+		ENABLE_PCLK_CCORE, 8, 0, 0),
+};
+
+static struct samsung_cmu_info ccore_cmu_info __initdata = {
+	.mux_clks		= ccore_mux_clks,
+	.nr_mux_clks		= ARRAY_SIZE(ccore_mux_clks),
+	.gate_clks		= ccore_gate_clks,
+	.nr_gate_clks		= ARRAY_SIZE(ccore_gate_clks),
+	.nr_clk_ids		= CCORE_NR_CLK,
+	.clk_regs		= ccore_clk_regs,
+	.nr_clk_regs		= ARRAY_SIZE(ccore_clk_regs),
+};
+
+static void __init exynos7_clk_ccore_init(struct device_node *np)
+{
+	samsung_cmu_register_one(np, &ccore_cmu_info);
+}
+
+CLK_OF_DECLARE(exynos7_clk_ccore, "samsung,exynos7-clock-ccore",
+	exynos7_clk_ccore_init);
+
 /* Register Offset definitions for CMU_PERIC0 (0x13610000) */
 #define MUX_SEL_PERIC0			0x0200
 #define ENABLE_PCLK_PERIC0		0x0900
diff --git a/include/dt-bindings/clock/exynos7-clk.h b/include/dt-bindings/clock/exynos7-clk.h
index ff63c4e15cc..dd89aa0f84e 100644
--- a/include/dt-bindings/clock/exynos7-clk.h
+++ b/include/dt-bindings/clock/exynos7-clk.h
@@ -16,7 +16,8 @@
 #define DOUT_SCLK_BUS1_PLL		3
 #define DOUT_SCLK_CC_PLL		4
 #define DOUT_SCLK_MFC_PLL		5
-#define TOPC_NR_CLK			6
+#define DOUT_ACLK_CCORE_133		6
+#define TOPC_NR_CLK			7
 
 /* TOP0 */
 #define DOUT_ACLK_PERIC1		1
@@ -38,6 +39,10 @@
 #define CLK_SCLK_MMC0			8
 #define TOP1_NR_CLK			9
 
+/* CCORE */
+#define PCLK_RTC			1
+#define CCORE_NR_CLK			2
+
 /* PERIC0 */
 #define PCLK_UART0			1
 #define SCLK_UART0			2
-- 
cgit v1.2.3-70-g09d2


From 2ab2dfe5d4eef6bad8cdd90dc6bba5a7660273d4 Mon Sep 17 00:00:00 2001
From: Naveen Krishna Ch <naveenkrishna.ch@gmail.com>
Date: Tue, 28 Oct 2014 16:48:54 +0530
Subject: clk: samsung: exynos7: add gate clocks for WDT, TMU and PWM blocks

Add clock support for the watchdog timer, pwm timer and thermal
management unit IPs in Exynos7.

Signed-off-by: Naveen Krishna Ch <naveenkrishna.ch@gmail.com>
Signed-off-by: Abhilash Kesavan <a.kesavan@samsung.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
---
 drivers/clk/samsung/clk-exynos7.c       | 14 ++++++++++++++
 include/dt-bindings/clock/exynos7-clk.h |  9 +++++++--
 2 files changed, 21 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/samsung/clk-exynos7.c b/drivers/clk/samsung/clk-exynos7.c
index 3a30f43fa92..17e5cf4d224 100644
--- a/drivers/clk/samsung/clk-exynos7.c
+++ b/drivers/clk/samsung/clk-exynos7.c
@@ -486,9 +486,12 @@ static struct samsung_gate_clock peric0_gate_clks[] __initdata = {
 		ENABLE_PCLK_PERIC0, 14, 0, 0),
 	GATE(PCLK_UART0, "pclk_uart0", "mout_aclk_peric0_66_user",
 		ENABLE_PCLK_PERIC0, 16, 0, 0),
+	GATE(PCLK_PWM, "pclk_pwm", "mout_aclk_peric0_66_user",
+		ENABLE_PCLK_PERIC0, 21, 0, 0),
 
 	GATE(SCLK_UART0, "sclk_uart0_user", "mout_sclk_uart0_user",
 		ENABLE_SCLK_PERIC0, 16, 0, 0),
+	GATE(SCLK_PWM, "sclk_pwm", "fin_pll", ENABLE_SCLK_PERIC0, 21, 0, 0),
 };
 
 static struct samsung_cmu_info peric0_cmu_info __initdata = {
@@ -586,7 +589,9 @@ CLK_OF_DECLARE(exynos7_clk_peric1, "samsung,exynos7-clock-peric1",
 
 /* Register Offset definitions for CMU_PERIS (0x10040000) */
 #define MUX_SEL_PERIS			0x0200
+#define ENABLE_PCLK_PERIS		0x0900
 #define ENABLE_PCLK_PERIS_SECURE_CHIPID	0x0910
+#define ENABLE_SCLK_PERIS		0x0A00
 #define ENABLE_SCLK_PERIS_SECURE_CHIPID	0x0A10
 
 /* List of parent clocks for Muxes in CMU_PERIS */
@@ -594,7 +599,9 @@ PNAME(mout_aclk_peris_66_p) = { "fin_pll", "dout_aclk_peris_66" };
 
 static unsigned long peris_clk_regs[] __initdata = {
 	MUX_SEL_PERIS,
+	ENABLE_PCLK_PERIS,
 	ENABLE_PCLK_PERIS_SECURE_CHIPID,
+	ENABLE_SCLK_PERIS,
 	ENABLE_SCLK_PERIS_SECURE_CHIPID,
 };
 
@@ -604,10 +611,17 @@ static struct samsung_mux_clock peris_mux_clks[] __initdata = {
 };
 
 static struct samsung_gate_clock peris_gate_clks[] __initdata = {
+	GATE(PCLK_WDT, "pclk_wdt", "mout_aclk_peris_66_user",
+		ENABLE_PCLK_PERIS, 6, 0, 0),
+	GATE(PCLK_TMU, "pclk_tmu_apbif", "mout_aclk_peris_66_user",
+		ENABLE_PCLK_PERIS, 10, 0, 0),
+
 	GATE(PCLK_CHIPID, "pclk_chipid", "mout_aclk_peris_66_user",
 		ENABLE_PCLK_PERIS_SECURE_CHIPID, 0, 0, 0),
 	GATE(SCLK_CHIPID, "sclk_chipid", "fin_pll",
 		ENABLE_SCLK_PERIS_SECURE_CHIPID, 0, 0, 0),
+
+	GATE(SCLK_TMU, "sclk_tmu", "fin_pll", ENABLE_SCLK_PERIS, 10, 0, 0),
 };
 
 static struct samsung_cmu_info peris_cmu_info __initdata = {
diff --git a/include/dt-bindings/clock/exynos7-clk.h b/include/dt-bindings/clock/exynos7-clk.h
index dd89aa0f84e..f255bb7c64b 100644
--- a/include/dt-bindings/clock/exynos7-clk.h
+++ b/include/dt-bindings/clock/exynos7-clk.h
@@ -53,7 +53,9 @@
 #define PCLK_HSI2C9			7
 #define PCLK_HSI2C10			8
 #define PCLK_HSI2C11			9
-#define PERIC0_NR_CLK			10
+#define PCLK_PWM			10
+#define SCLK_PWM			11
+#define PERIC0_NR_CLK			12
 
 /* PERIC1 */
 #define PCLK_UART1			1
@@ -72,7 +74,10 @@
 /* PERIS */
 #define PCLK_CHIPID			1
 #define SCLK_CHIPID			2
-#define PERIS_NR_CLK			3
+#define PCLK_WDT			3
+#define PCLK_TMU			4
+#define SCLK_TMU			5
+#define PERIS_NR_CLK			6
 
 /* FSYS0 */
 #define ACLK_MMC2			1
-- 
cgit v1.2.3-70-g09d2


From 932e98224d5602be17ed61d0e057e9326f12b59d Mon Sep 17 00:00:00 2001
From: Abhilash Kesavan <a.kesavan@samsung.com>
Date: Tue, 28 Oct 2014 16:48:55 +0530
Subject: clk: samsung: exynos7: add gate clock for ADC block

Add clock support for the ADC interface in Exynos7.

Signed-off-by: Abhilash Kesavan <a.kesavan@samsung.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
---
 drivers/clk/samsung/clk-exynos7.c       | 2 ++
 include/dt-bindings/clock/exynos7-clk.h | 3 ++-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/clk/samsung/clk-exynos7.c b/drivers/clk/samsung/clk-exynos7.c
index 17e5cf4d224..ea4483b8d62 100644
--- a/drivers/clk/samsung/clk-exynos7.c
+++ b/drivers/clk/samsung/clk-exynos7.c
@@ -486,6 +486,8 @@ static struct samsung_gate_clock peric0_gate_clks[] __initdata = {
 		ENABLE_PCLK_PERIC0, 14, 0, 0),
 	GATE(PCLK_UART0, "pclk_uart0", "mout_aclk_peric0_66_user",
 		ENABLE_PCLK_PERIC0, 16, 0, 0),
+	GATE(PCLK_ADCIF, "pclk_adcif", "mout_aclk_peric0_66_user",
+		ENABLE_PCLK_PERIC0, 20, 0, 0),
 	GATE(PCLK_PWM, "pclk_pwm", "mout_aclk_peric0_66_user",
 		ENABLE_PCLK_PERIC0, 21, 0, 0),
 
diff --git a/include/dt-bindings/clock/exynos7-clk.h b/include/dt-bindings/clock/exynos7-clk.h
index f255bb7c64b..8e4681b07ae 100644
--- a/include/dt-bindings/clock/exynos7-clk.h
+++ b/include/dt-bindings/clock/exynos7-clk.h
@@ -55,7 +55,8 @@
 #define PCLK_HSI2C11			9
 #define PCLK_PWM			10
 #define SCLK_PWM			11
-#define PERIC0_NR_CLK			12
+#define PCLK_ADCIF			12
+#define PERIC0_NR_CLK			13
 
 /* PERIC1 */
 #define PCLK_UART1			1
-- 
cgit v1.2.3-70-g09d2


From 77deed2bbd64e88b3c31283a6ecf771d637ff161 Mon Sep 17 00:00:00 2001
From: Gabriel FERNANDEZ <gabriel.fernandez@st.com>
Date: Thu, 4 Sep 2014 14:59:00 +0200
Subject: ARM: STi: DT: STiH407: Add all defines for STiH407 DT clocks

This patch adds all clock defines for clockgen C0,D0,D2 and D3

Signed-off-by: Gabriel Fernandez <gabriel.fernandez@linaro.org>
Signed-off-by: Maxime Coquelin <maxime.coquelin@st.com>
---
 include/dt-bindings/clock/stih407-clks.h | 75 ++++++++++++++++++++++++++++++++
 1 file changed, 75 insertions(+)

(limited to 'include')

diff --git a/include/dt-bindings/clock/stih407-clks.h b/include/dt-bindings/clock/stih407-clks.h
index 1f9bfe0e47f..7af2b717b3b 100644
--- a/include/dt-bindings/clock/stih407-clks.h
+++ b/include/dt-bindings/clock/stih407-clks.h
@@ -6,6 +6,81 @@
 #define _DT_BINDINGS_CLK_STIH407
 
 /* CLOCKGEN C0 */
+#define CLK_ICN_GPU		0
+#define CLK_FDMA		1
+#define CLK_NAND		2
+#define CLK_HVA			3
+#define CLK_PROC_STFE		4
+#define CLK_PROC_TP		5
+#define CLK_RX_ICN_DMU		6
+#define CLK_RX_ICN_DISP_0	6
+#define CLK_RX_ICN_DISP_1	6
+#define CLK_RX_ICN_HVA		7
+#define CLK_RX_ICN_TS		7
+#define CLK_ICN_CPU		8
+#define CLK_TX_ICN_DMU		9
+#define CLK_TX_ICN_HVA		9
+#define CLK_TX_ICN_TS		9
+#define CLK_ICN_COMPO		9
+#define CLK_MMC_0		10
+#define CLK_MMC_1		11
+#define CLK_JPEGDEC		12
+#define CLK_ICN_REG		13
+#define CLK_TRACE_A9		13
+#define CLK_PTI_STM		13
 #define CLK_EXT2F_A9		13
+#define CLK_IC_BDISP_0		14
+#define CLK_IC_BDISP_1		15
+#define CLK_PP_DMU		16
+#define CLK_VID_DMU		17
+#define CLK_DSS_LPC		18
+#define CLK_ST231_AUD_0		19
+#define CLK_ST231_GP_0		19
+#define CLK_ST231_GP_1		20
+#define CLK_ST231_DMU		21
+#define CLK_ICN_LMI		22
+#define CLK_TX_ICN_DISP_0	23
+#define CLK_TX_ICN_DISP_1	23
+#define CLK_ICN_SBC		24
+#define CLK_STFE_FRC2		25
+#define CLK_ETH_PHY		26
+#define CLK_ETH_REF_PHYCLK	27
+#define CLK_FLASH_PROMIP	28
+#define CLK_MAIN_DISP		29
+#define CLK_AUX_DISP		30
+#define CLK_COMPO_DVP		31
 
+/* CLOCKGEN D0 */
+#define CLK_PCM_0		0
+#define CLK_PCM_1		1
+#define CLK_PCM_2		2
+#define CLK_SPDIFF		3
+
+/* CLOCKGEN D2 */
+#define CLK_PIX_MAIN_DISP	0
+#define CLK_PIX_PIP		1
+#define CLK_PIX_GDP1		2
+#define CLK_PIX_GDP2		3
+#define CLK_PIX_GDP3		4
+#define CLK_PIX_GDP4		5
+#define CLK_PIX_AUX_DISP	6
+#define CLK_DENC		7
+#define CLK_PIX_HDDAC		8
+#define CLK_HDDAC		9
+#define CLK_SDDAC		10
+#define CLK_PIX_DVO		11
+#define CLK_DVO			12
+#define CLK_PIX_HDMI		13
+#define CLK_TMDS_HDMI		14
+#define CLK_REF_HDMIPHY		15
+
+/* CLOCKGEN D3 */
+#define CLK_STFE_FRC1		0
+#define CLK_TSOUT_0		1
+#define CLK_TSOUT_1		2
+#define CLK_MCHI		3
+#define CLK_VSENS_COMPO		4
+#define CLK_FRC1_REMOTE		5
+#define CLK_LPC_0		6
+#define CLK_LPC_1		7
 #endif
-- 
cgit v1.2.3-70-g09d2


From f3bea49115b21e0995abf41402ad2f4d9c69eda4 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 2 Jul 2014 23:23:31 -0400
Subject: ftrace/x86: Add dynamic allocated trampoline for ftrace_ops

The current method of handling multiple function callbacks is to register
a list function callback that calls all the other callbacks based on
their hash tables and compare it to the function that the callback was
called on. But this is very inefficient.

For example, if you are tracing all functions in the kernel and then
add a kprobe to a function such that the kprobe uses ftrace, the
mcount trampoline will switch from calling the function trace callback
to calling the list callback that will iterate over all registered
ftrace_ops (in this case, the function tracer and the kprobes callback).
That means for every function being traced it checks the hash of the
ftrace_ops for function tracing and kprobes, even though the kprobes
is only set at a single function. The kprobes ftrace_ops is checked
for every function being traced!

Instead of calling the list function for functions that are only being
traced by a single callback, we can call a dynamically allocated
trampoline that calls the callback directly. The function graph tracer
already uses a direct call trampoline when it is being traced by itself
but it is not dynamically allocated. It's trampoline is static in the
kernel core. The infrastructure that called the function graph trampoline
can also be used to call a dynamically allocated one.

For now, only ftrace_ops that are not dynamically allocated can have
a trampoline. That is, users such as function tracer or stack tracer.
kprobes and perf allocate their ftrace_ops, and until there's a safe
way to free the trampoline, it can not be used. The dynamically allocated
ftrace_ops may, although, use the trampoline if the kernel is not
compiled with CONFIG_PREEMPT. But that will come later.

Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/x86/kernel/ftrace.c    | 195 ++++++++++++++++++++++++++++++++++++++++++--
 arch/x86/kernel/mcount_64.S |  25 +++++-
 include/linux/ftrace.h      |   8 ++
 kernel/trace/ftrace.c       |  40 ++++++++-
 4 files changed, 254 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 3386dc9aa33..e4d48f6cad8 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -17,6 +17,7 @@
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/module.h>
@@ -644,13 +645,8 @@ int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
-#endif
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-
-#ifdef CONFIG_DYNAMIC_FTRACE
-extern void ftrace_graph_call(void);
 
+#if defined(CONFIG_X86_64) || defined(CONFIG_FUNCTION_GRAPH_TRACER)
 static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
 {
 	static union ftrace_code_union calc;
@@ -664,6 +660,193 @@ static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
 	 */
 	return calc.code;
 }
+#endif
+
+/* Currently only x86_64 supports dynamic trampolines */
+#ifdef CONFIG_X86_64
+
+#ifdef CONFIG_MODULES
+#include <linux/moduleloader.h>
+/* Module allocation simplifies allocating memory for code */
+static inline void *alloc_tramp(unsigned long size)
+{
+	return module_alloc(size);
+}
+static inline void tramp_free(void *tramp)
+{
+	module_free(NULL, tramp);
+}
+#else
+/* Trampolines can only be created if modules are supported */
+static inline void *alloc_tramp(unsigned long size)
+{
+	return NULL;
+}
+static inline void tramp_free(void *tramp) { }
+#endif
+
+/* Defined as markers to the end of the ftrace default trampolines */
+extern void ftrace_caller_end(void);
+extern void ftrace_regs_caller_end(void);
+extern void ftrace_return(void);
+extern void ftrace_caller_op_ptr(void);
+extern void ftrace_regs_caller_op_ptr(void);
+
+/* movq function_trace_op(%rip), %rdx */
+/* 0x48 0x8b 0x15 <offset-to-ftrace_trace_op (4 bytes)> */
+#define OP_REF_SIZE	7
+
+/*
+ * The ftrace_ops is passed to the function callback. Since the
+ * trampoline only services a single ftrace_ops, we can pass in
+ * that ops directly.
+ *
+ * The ftrace_op_code_union is used to create a pointer to the
+ * ftrace_ops that will be passed to the callback function.
+ */
+union ftrace_op_code_union {
+	char code[OP_REF_SIZE];
+	struct {
+		char op[3];
+		int offset;
+	} __attribute__((packed));
+};
+
+static unsigned long create_trampoline(struct ftrace_ops *ops)
+{
+	unsigned const char *jmp;
+	unsigned long start_offset;
+	unsigned long end_offset;
+	unsigned long op_offset;
+	unsigned long offset;
+	unsigned long size;
+	unsigned long ip;
+	unsigned long *ptr;
+	void *trampoline;
+	/* 48 8b 15 <offset> is movq <offset>(%rip), %rdx */
+	unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
+	union ftrace_op_code_union op_ptr;
+	int ret;
+
+	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
+		start_offset = (unsigned long)ftrace_regs_caller;
+		end_offset = (unsigned long)ftrace_regs_caller_end;
+		op_offset = (unsigned long)ftrace_regs_caller_op_ptr;
+	} else {
+		start_offset = (unsigned long)ftrace_caller;
+		end_offset = (unsigned long)ftrace_caller_end;
+		op_offset = (unsigned long)ftrace_caller_op_ptr;
+	}
+
+	size = end_offset - start_offset;
+
+	/*
+	 * Allocate enough size to store the ftrace_caller code,
+	 * the jmp to ftrace_return, as well as the address of
+	 * the ftrace_ops this trampoline is used for.
+	 */
+	trampoline = alloc_tramp(size + MCOUNT_INSN_SIZE + sizeof(void *));
+	if (!trampoline)
+		return 0;
+
+	/* Copy ftrace_caller onto the trampoline memory */
+	ret = probe_kernel_read(trampoline, (void *)start_offset, size);
+	if (WARN_ON(ret < 0)) {
+		tramp_free(trampoline);
+		return 0;
+	}
+
+	ip = (unsigned long)trampoline + size;
+
+	/* The trampoline ends with a jmp to ftrace_return */
+	jmp = ftrace_jmp_replace(ip, (unsigned long)ftrace_return);
+	memcpy(trampoline + size, jmp, MCOUNT_INSN_SIZE);
+
+	/*
+	 * The address of the ftrace_ops that is used for this trampoline
+	 * is stored at the end of the trampoline. This will be used to
+	 * load the third parameter for the callback. Basically, that
+	 * location at the end of the trampoline takes the place of
+	 * the global function_trace_op variable.
+	 */
+
+	ptr = (unsigned long *)(trampoline + size + MCOUNT_INSN_SIZE);
+	*ptr = (unsigned long)ops;
+
+	op_offset -= start_offset;
+	memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE);
+
+	/* Are we pointing to the reference? */
+	if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0)) {
+		tramp_free(trampoline);
+		return 0;
+	}
+
+	/* Load the contents of ptr into the callback parameter */
+	offset = (unsigned long)ptr;
+	offset -= (unsigned long)trampoline + op_offset + OP_REF_SIZE;
+
+	op_ptr.offset = offset;
+
+	/* put in the new offset to the ftrace_ops */
+	memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
+
+	/* ALLOC_TRAMP flags lets us know we created it */
+	ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
+
+	return (unsigned long)trampoline;
+}
+
+void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
+{
+	ftrace_func_t func;
+	unsigned char *new;
+	unsigned long start_offset;
+	unsigned long call_offset;
+	unsigned long offset;
+	unsigned long ip;
+	int ret;
+
+	if (ops->trampoline) {
+		/*
+		 * The ftrace_ops caller may set up its own trampoline.
+		 * In such a case, this code must not modify it.
+		 */
+		if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
+			return;
+	} else {
+		ops->trampoline = create_trampoline(ops);
+		if (!ops->trampoline)
+			return;
+	}
+
+	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
+		start_offset = (unsigned long)ftrace_regs_caller;
+		call_offset = (unsigned long)ftrace_regs_call;
+	} else {
+		start_offset = (unsigned long)ftrace_caller;
+		call_offset = (unsigned long)ftrace_call;
+	}
+
+	offset = call_offset - start_offset;
+	ip = ops->trampoline + offset;
+
+	func = ftrace_ops_get_func(ops);
+
+	/* Do a safe modify in case the trampoline is executing */
+	new = ftrace_call_replace(ip, (unsigned long)func);
+	ret = update_ftrace_func(ip, new);
+
+	/* The update should never fail */
+	WARN_ON(ret);
+}
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_graph_call(void);
 
 static int ftrace_mod_jmp(unsigned long ip, void *func)
 {
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index c73aecf10d3..42f0cdd20ba 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -28,9 +28,11 @@ ENTRY(function_hook)
 END(function_hook)
 
 /* skip is set if stack has been adjusted */
-.macro ftrace_caller_setup skip=0
+.macro ftrace_caller_setup trace_label skip=0
 	MCOUNT_SAVE_FRAME \skip
 
+	/* Save this location */
+GLOBAL(\trace_label)
 	/* Load the ftrace_ops into the 3rd parameter */
 	movq function_trace_op(%rip), %rdx
 
@@ -46,7 +48,7 @@ END(function_hook)
 .endm
 
 ENTRY(ftrace_caller)
-	ftrace_caller_setup
+	ftrace_caller_setup ftrace_caller_op_ptr
 	/* regs go into 4th parameter (but make it NULL) */
 	movq $0, %rcx
 
@@ -54,7 +56,14 @@ GLOBAL(ftrace_call)
 	call ftrace_stub
 
 	MCOUNT_RESTORE_FRAME
-ftrace_return:
+
+	/*
+	 * The copied trampoline must call ftrace_return as it
+	 * still may need to call the function graph tracer.
+	 */
+GLOBAL(ftrace_caller_end)
+
+GLOBAL(ftrace_return)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 GLOBAL(ftrace_graph_call)
@@ -70,7 +79,7 @@ ENTRY(ftrace_regs_caller)
 	pushfq
 
 	/* skip=8 to skip flags saved in SS */
-	ftrace_caller_setup 8
+	ftrace_caller_setup ftrace_regs_caller_op_ptr 8
 
 	/* Save the rest of pt_regs */
 	movq %r15, R15(%rsp)
@@ -122,6 +131,14 @@ GLOBAL(ftrace_regs_call)
 	/* Restore flags */
 	popfq
 
+	/*
+	 * As this jmp to ftrace_return can be a short jump
+	 * it must not be copied into the trampoline.
+	 * The trampoline will add the code to jump
+	 * to the return.
+	 */
+GLOBAL(ftrace_regs_caller_end)
+
 	jmp ftrace_return
 
 	popfq
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 662697babd4..06e3ca5a508 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -94,6 +94,13 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
  * ADDING  - The ops is in the process of being added.
  * REMOVING - The ops is in the process of being removed.
  * MODIFYING - The ops is in the process of changing its filter functions.
+ * ALLOC_TRAMP - A dynamic trampoline was allocated by the core code.
+ *            The arch specific code sets this flag when it allocated a
+ *            trampoline. This lets the arch know that it can update the
+ *            trampoline in case the callback function changes.
+ *            The ftrace_ops trampoline can be set by the ftrace users, and
+ *            in such cases the arch must not modify it. Only the arch ftrace
+ *            core code should set this flag.
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
@@ -108,6 +115,7 @@ enum {
 	FTRACE_OPS_FL_ADDING			= 1 << 9,
 	FTRACE_OPS_FL_REMOVING			= 1 << 10,
 	FTRACE_OPS_FL_MODIFYING			= 1 << 11,
+	FTRACE_OPS_FL_ALLOC_TRAMP		= 1 << 12,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 31c90fec415..15f85eac7e9 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -387,6 +387,8 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list,
 	return ret;
 }
 
+static void ftrace_update_trampoline(struct ftrace_ops *ops);
+
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
 	if (ops->flags & FTRACE_OPS_FL_DELETED)
@@ -419,6 +421,8 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	} else
 		add_ftrace_ops(&ftrace_ops_list, ops);
 
+	ftrace_update_trampoline(ops);
+
 	if (ftrace_enabled)
 		update_ftrace_function();
 
@@ -3020,9 +3024,6 @@ ftrace_enabled_open(struct inode *inode, struct file *file)
 {
 	struct ftrace_iterator *iter;
 
-	if (unlikely(ftrace_disabled))
-		return -ENODEV;
-
 	iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
 	if (iter) {
 		iter->pg = ftrace_pages_start;
@@ -3975,6 +3976,9 @@ static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
 static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata;
 static int ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer);
 
+static unsigned long save_global_trampoline;
+static unsigned long save_global_flags;
+
 static int __init set_graph_function(char *str)
 {
 	strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
@@ -4696,6 +4700,20 @@ void __init ftrace_init(void)
 	ftrace_disabled = 1;
 }
 
+/* Do nothing if arch does not support this */
+void __weak arch_ftrace_update_trampoline(struct ftrace_ops *ops)
+{
+}
+
+static void ftrace_update_trampoline(struct ftrace_ops *ops)
+{
+	/* Currently, only non dynamic ops can have a trampoline */
+	if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
+		return;
+
+	arch_ftrace_update_trampoline(ops);
+}
+
 #else
 
 static struct ftrace_ops global_ops = {
@@ -4738,6 +4756,10 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 	return 1;
 }
 
+static void ftrace_update_trampoline(struct ftrace_ops *ops)
+{
+}
+
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 __init void ftrace_init_global_array_ops(struct trace_array *tr)
@@ -5522,7 +5544,6 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	update_function_graph_func();
 
 	ret = ftrace_startup(&graph_ops, FTRACE_START_FUNC_RET);
-
 out:
 	mutex_unlock(&ftrace_lock);
 	return ret;
@@ -5543,6 +5564,17 @@ void unregister_ftrace_graph(void)
 	unregister_pm_notifier(&ftrace_suspend_notifier);
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/*
+	 * Function graph does not allocate the trampoline, but
+	 * other global_ops do. We need to reset the ALLOC_TRAMP flag
+	 * if one was used.
+	 */
+	global_ops.trampoline = save_global_trampoline;
+	if (save_global_flags & FTRACE_OPS_FL_ALLOC_TRAMP)
+		global_ops.flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
+#endif
+
  out:
 	mutex_unlock(&ftrace_lock);
 }
-- 
cgit v1.2.3-70-g09d2


From ac7576f4b1da8c9c6bc1ae026c2b9e86ae617ba5 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <miklos@szeredi.hu>
Date: Thu, 30 Oct 2014 17:37:34 +0100
Subject: vfs: make first argument of dir_context.actor typed

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/kernel/osf_sys.c                     |  7 ++++---
 arch/parisc/hpux/fs.c                           |  7 ++++---
 drivers/staging/lustre/lustre/llite/llite_nfs.c |  8 +++++---
 fs/afs/dir.c                                    |  9 +++++----
 fs/compat.c                                     | 21 +++++++++++++--------
 fs/ecryptfs/file.c                              |  6 +++---
 fs/exportfs/expfs.c                             |  5 +++--
 fs/fat/dir.c                                    |  5 +++--
 fs/gfs2/export.c                                |  8 +++++---
 fs/hppfs/hppfs.c                                |  5 +++--
 fs/nfsd/nfs4recover.c                           |  5 +++--
 fs/nfsd/vfs.c                                   | 12 +++++++-----
 fs/nfsd/vfs.h                                   |  4 ++--
 fs/ocfs2/dir.c                                  |  8 +++++---
 fs/ocfs2/journal.c                              |  8 +++++---
 fs/overlayfs/readdir.c                          |  8 +++++---
 fs/readdir.c                                    | 21 ++++++++++++---------
 fs/reiserfs/xattr.c                             | 15 +++++++++------
 include/linux/fs.h                              |  5 ++++-
 19 files changed, 100 insertions(+), 67 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index f9c732e1828..e51f578636a 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -104,11 +104,12 @@ struct osf_dirent_callback {
 };
 
 static int
-osf_filldir(void *__buf, const char *name, int namlen, loff_t offset,
-	    u64 ino, unsigned int d_type)
+osf_filldir(struct dir_context *ctx, const char *name, int namlen,
+	    loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct osf_dirent __user *dirent;
-	struct osf_dirent_callback *buf = (struct osf_dirent_callback *) __buf;
+	struct osf_dirent_callback *buf =
+		container_of(ctx, struct osf_dirent_callback, ctx);
 	unsigned int reclen = ALIGN(NAME_OFFSET + namlen + 1, sizeof(u32));
 	unsigned int d_ino;
 
diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c
index 2bedafea3d9..97a7bf8df34 100644
--- a/arch/parisc/hpux/fs.c
+++ b/arch/parisc/hpux/fs.c
@@ -56,11 +56,12 @@ struct getdents_callback {
 
 #define NAME_OFFSET(de) ((int) ((de)->d_name - (char __user *) (de)))
 
-static int filldir(void * __buf, const char * name, int namlen, loff_t offset,
-		u64 ino, unsigned d_type)
+static int filldir(struct dir_context *ctx, const char *name, int namlen,
+		   loff_t offset, u64 ino, unsigned d_type)
 {
 	struct hpux_dirent __user * dirent;
-	struct getdents_callback * buf = (struct getdents_callback *) __buf;
+	struct getdents_callback *buf =
+		container_of(ctx, struct getdents_callback, ctx);
 	ino_t d_ino;
 	int reclen = ALIGN(NAME_OFFSET(dirent) + namlen + 1, sizeof(long));
 
diff --git a/drivers/staging/lustre/lustre/llite/llite_nfs.c b/drivers/staging/lustre/lustre/llite/llite_nfs.c
index ae3a12ab7fa..243a7840457 100644
--- a/drivers/staging/lustre/lustre/llite/llite_nfs.c
+++ b/drivers/staging/lustre/lustre/llite/llite_nfs.c
@@ -207,13 +207,15 @@ static int ll_encode_fh(struct inode *inode, __u32 *fh, int *plen,
 	return LUSTRE_NFS_FID;
 }
 
-static int ll_nfs_get_name_filldir(void *cookie, const char *name, int namelen,
-				   loff_t hash, u64 ino, unsigned type)
+static int ll_nfs_get_name_filldir(struct dir_context *ctx, const char *name,
+				   int namelen, loff_t hash, u64 ino,
+				   unsigned type)
 {
 	/* It is hack to access lde_fid for comparison with lgd_fid.
 	 * So the input 'name' must be part of the 'lu_dirent'. */
 	struct lu_dirent *lde = container_of0(name, struct lu_dirent, lde_name);
-	struct ll_getname_data *lgd = cookie;
+	struct ll_getname_data *lgd =
+		container_of(ctx, struct ll_getname_data, ctx);
 	struct lu_fid fid;
 
 	fid_le_to_cpu(&fid, &lde->lde_fid);
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index a1645b88fe8..d452f3de543 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -26,7 +26,7 @@ static int afs_readdir(struct file *file, struct dir_context *ctx);
 static int afs_d_revalidate(struct dentry *dentry, unsigned int flags);
 static int afs_d_delete(const struct dentry *dentry);
 static void afs_d_release(struct dentry *dentry);
-static int afs_lookup_filldir(void *_cookie, const char *name, int nlen,
+static int afs_lookup_filldir(struct dir_context *ctx, const char *name, int nlen,
 				  loff_t fpos, u64 ino, unsigned dtype);
 static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		      bool excl);
@@ -391,10 +391,11 @@ static int afs_readdir(struct file *file, struct dir_context *ctx)
  * - if afs_dir_iterate_block() spots this function, it'll pass the FID
  *   uniquifier through dtype
  */
-static int afs_lookup_filldir(void *_cookie, const char *name, int nlen,
-			      loff_t fpos, u64 ino, unsigned dtype)
+static int afs_lookup_filldir(struct dir_context *ctx, const char *name,
+			      int nlen, loff_t fpos, u64 ino, unsigned dtype)
 {
-	struct afs_lookup_cookie *cookie = _cookie;
+	struct afs_lookup_cookie *cookie =
+		container_of(ctx, struct afs_lookup_cookie, ctx);
 
 	_enter("{%s,%u},%s,%u,,%llu,%u",
 	       cookie->name.name, cookie->name.len, name, nlen,
diff --git a/fs/compat.c b/fs/compat.c
index b13df99f353..6fd272d455e 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -847,10 +847,12 @@ struct compat_readdir_callback {
 	int result;
 };
 
-static int compat_fillonedir(void *__buf, const char *name, int namlen,
-			loff_t offset, u64 ino, unsigned int d_type)
+static int compat_fillonedir(struct dir_context *ctx, const char *name,
+			     int namlen, loff_t offset, u64 ino,
+			     unsigned int d_type)
 {
-	struct compat_readdir_callback *buf = __buf;
+	struct compat_readdir_callback *buf =
+		container_of(ctx, struct compat_readdir_callback, ctx);
 	struct compat_old_linux_dirent __user *dirent;
 	compat_ulong_t d_ino;
 
@@ -915,11 +917,12 @@ struct compat_getdents_callback {
 	int error;
 };
 
-static int compat_filldir(void *__buf, const char *name, int namlen,
+static int compat_filldir(struct dir_context *ctx, const char *name, int namlen,
 		loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct compat_linux_dirent __user * dirent;
-	struct compat_getdents_callback *buf = __buf;
+	struct compat_getdents_callback *buf =
+		container_of(ctx, struct compat_getdents_callback, ctx);
 	compat_ulong_t d_ino;
 	int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) +
 		namlen + 2, sizeof(compat_long_t));
@@ -1001,11 +1004,13 @@ struct compat_getdents_callback64 {
 	int error;
 };
 
-static int compat_filldir64(void * __buf, const char * name, int namlen, loff_t offset,
-		     u64 ino, unsigned int d_type)
+static int compat_filldir64(struct dir_context *ctx, const char *name,
+			    int namlen, loff_t offset, u64 ino,
+			    unsigned int d_type)
 {
 	struct linux_dirent64 __user *dirent;
-	struct compat_getdents_callback64 *buf = __buf;
+	struct compat_getdents_callback64 *buf =
+		container_of(ctx, struct compat_getdents_callback64, ctx);
 	int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1,
 		sizeof(u64));
 	u64 off;
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index f5bce909655..80154ec4f8c 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -75,11 +75,11 @@ struct ecryptfs_getdents_callback {
 
 /* Inspired by generic filldir in fs/readdir.c */
 static int
-ecryptfs_filldir(void *dirent, const char *lower_name, int lower_namelen,
-		 loff_t offset, u64 ino, unsigned int d_type)
+ecryptfs_filldir(struct dir_context *ctx, const char *lower_name,
+		 int lower_namelen, loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct ecryptfs_getdents_callback *buf =
-	    (struct ecryptfs_getdents_callback *)dirent;
+		container_of(ctx, struct ecryptfs_getdents_callback, ctx);
 	size_t name_size;
 	char *name;
 	int rc;
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index b01fbfb51f4..a2b350ddd40 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -241,10 +241,11 @@ struct getdents_callback {
  * A rather strange filldir function to capture
  * the name matching the specified inode number.
  */
-static int filldir_one(void * __buf, const char * name, int len,
+static int filldir_one(struct dir_context *ctx, const char *name, int len,
 			loff_t pos, u64 ino, unsigned int d_type)
 {
-	struct getdents_callback *buf = __buf;
+	struct getdents_callback *buf =
+		container_of(ctx, struct getdents_callback, ctx);
 	int result = 0;
 
 	buf->sequence++;
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 3963ede84eb..c5d6bb939d1 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -702,10 +702,11 @@ static int fat_readdir(struct file *file, struct dir_context *ctx)
 }
 
 #define FAT_IOCTL_FILLDIR_FUNC(func, dirent_type)			   \
-static int func(void *__buf, const char *name, int name_len,		   \
+static int func(struct dir_context *ctx, const char *name, int name_len,   \
 			     loff_t offset, u64 ino, unsigned int d_type)  \
 {									   \
-	struct fat_ioctl_filldir_callback *buf = __buf;			   \
+	struct fat_ioctl_filldir_callback *buf =			   \
+		container_of(ctx, struct fat_ioctl_filldir_callback, ctx); \
 	struct dirent_type __user *d1 = buf->dirent;			   \
 	struct dirent_type __user *d2 = d1 + 1;				   \
 									   \
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 8b9b3775e2e..c41d255b6a7 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -69,10 +69,12 @@ struct get_name_filldir {
 	char *name;
 };
 
-static int get_name_filldir(void *opaque, const char *name, int length,
-			    loff_t offset, u64 inum, unsigned int type)
+static int get_name_filldir(struct dir_context *ctx, const char *name,
+			    int length, loff_t offset, u64 inum,
+			    unsigned int type)
 {
-	struct get_name_filldir *gnfd = opaque;
+	struct get_name_filldir *gnfd =
+		container_of(ctx, struct get_name_filldir, ctx);
 
 	if (inum != gnfd->inum.no_addr)
 		return 0;
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index 4338ff32959..5f2755117ce 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -548,10 +548,11 @@ struct hppfs_dirent {
 	struct dentry *dentry;
 };
 
-static int hppfs_filldir(void *d, const char *name, int size,
+static int hppfs_filldir(struct dir_context *ctx, const char *name, int size,
 			 loff_t offset, u64 inode, unsigned int type)
 {
-	struct hppfs_dirent *dirent = d;
+	struct hppfs_dirent *dirent =
+		container_of(ctx, struct hppfs_dirent, ctx);
 
 	if (file_removed(dirent->dentry, name))
 		return 0;
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index a25490ae6c6..0e71a0dd58c 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -245,10 +245,11 @@ struct nfs4_dir_ctx {
 };
 
 static int
-nfsd4_build_namelist(void *arg, const char *name, int namlen,
+nfsd4_build_namelist(struct dir_context *__ctx, const char *name, int namlen,
 		loff_t offset, u64 ino, unsigned int d_type)
 {
-	struct nfs4_dir_ctx *ctx = arg;
+	struct nfs4_dir_ctx *ctx =
+		container_of(__ctx, struct nfs4_dir_ctx, ctx);
 	struct name_list *entry;
 
 	if (namlen != HEXDIR_LEN - 1)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 989129e2d6e..161d2d51b6f 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1819,10 +1819,12 @@ struct readdir_data {
 	int		full;
 };
 
-static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen,
-				 loff_t offset, u64 ino, unsigned int d_type)
+static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name,
+				 int namlen, loff_t offset, u64 ino,
+				 unsigned int d_type)
 {
-	struct readdir_data *buf = __buf;
+	struct readdir_data *buf =
+		container_of(ctx, struct readdir_data, ctx);
 	struct buffered_dirent *de = (void *)(buf->dirent + buf->used);
 	unsigned int reclen;
 
@@ -1842,7 +1844,7 @@ static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen,
 	return 0;
 }
 
-static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func,
+static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
 				    struct readdir_cd *cdp, loff_t *offsetp)
 {
 	struct buffered_dirent *de;
@@ -1926,7 +1928,7 @@ static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func,
  */
 __be32
 nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, 
-	     struct readdir_cd *cdp, filldir_t func)
+	     struct readdir_cd *cdp, nfsd_filldir_t func)
 {
 	__be32		err;
 	struct file	*file;
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index c2ff3f14e5f..b1796d6ee53 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -36,7 +36,7 @@
 /*
  * Callback function for readdir
  */
-typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int);
+typedef int (*nfsd_filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
 
 /* nfsd/vfs.c */
 int		nfsd_racache_init(int);
@@ -95,7 +95,7 @@ __be32		nfsd_rename(struct svc_rqst *,
 __be32		nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type,
 				char *name, int len);
 __be32		nfsd_readdir(struct svc_rqst *, struct svc_fh *,
-			     loff_t *, struct readdir_cd *, filldir_t);
+			     loff_t *, struct readdir_cd *, nfsd_filldir_t);
 __be32		nfsd_statfs(struct svc_rqst *, struct svc_fh *,
 				struct kstatfs *, int access);
 
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 0717662b4ae..c43d9b4a1ec 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -2073,10 +2073,12 @@ struct ocfs2_empty_dir_priv {
 	unsigned seen_other;
 	unsigned dx_dir;
 };
-static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len,
-				   loff_t pos, u64 ino, unsigned type)
+static int ocfs2_empty_dir_filldir(struct dir_context *ctx, const char *name,
+				   int name_len, loff_t pos, u64 ino,
+				   unsigned type)
 {
-	struct ocfs2_empty_dir_priv *p = priv;
+	struct ocfs2_empty_dir_priv *p =
+		container_of(ctx, struct ocfs2_empty_dir_priv, ctx);
 
 	/*
 	 * Check the positions of "." and ".." records to be sure
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 4b0c68849b3..4f502382180 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1982,10 +1982,12 @@ struct ocfs2_orphan_filldir_priv {
 	struct ocfs2_super	*osb;
 };
 
-static int ocfs2_orphan_filldir(void *priv, const char *name, int name_len,
-				loff_t pos, u64 ino, unsigned type)
+static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name,
+				int name_len, loff_t pos, u64 ino,
+				unsigned type)
 {
-	struct ocfs2_orphan_filldir_priv *p = priv;
+	struct ocfs2_orphan_filldir_priv *p =
+		container_of(ctx, struct ocfs2_orphan_filldir_priv, ctx);
 	struct inode *iter;
 
 	if (name_len == 1 && !strncmp(".", name, 1))
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 4e9d7c1fea5..301f64aa8a4 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -180,10 +180,12 @@ static void ovl_cache_put(struct ovl_dir_file *od, struct dentry *dentry)
 	}
 }
 
-static int ovl_fill_merge(void *buf, const char *name, int namelen,
-			  loff_t offset, u64 ino, unsigned int d_type)
+static int ovl_fill_merge(struct dir_context *ctx, const char *name,
+			  int namelen, loff_t offset, u64 ino,
+			  unsigned int d_type)
 {
-	struct ovl_readdir_data *rdd = buf;
+	struct ovl_readdir_data *rdd =
+		container_of(ctx, struct ovl_readdir_data, ctx);
 
 	rdd->count++;
 	if (!rdd->is_merge)
diff --git a/fs/readdir.c b/fs/readdir.c
index 33fd92208cb..ced679179ca 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -74,10 +74,11 @@ struct readdir_callback {
 	int result;
 };
 
-static int fillonedir(void * __buf, const char * name, int namlen, loff_t offset,
-		      u64 ino, unsigned int d_type)
+static int fillonedir(struct dir_context *ctx, const char *name, int namlen,
+		      loff_t offset, u64 ino, unsigned int d_type)
 {
-	struct readdir_callback *buf = (struct readdir_callback *) __buf;
+	struct readdir_callback *buf =
+		container_of(ctx, struct readdir_callback, ctx);
 	struct old_linux_dirent __user * dirent;
 	unsigned long d_ino;
 
@@ -148,11 +149,12 @@ struct getdents_callback {
 	int error;
 };
 
-static int filldir(void * __buf, const char * name, int namlen, loff_t offset,
-		   u64 ino, unsigned int d_type)
+static int filldir(struct dir_context *ctx, const char *name, int namlen,
+		   loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct linux_dirent __user * dirent;
-	struct getdents_callback * buf = (struct getdents_callback *) __buf;
+	struct getdents_callback *buf =
+		container_of(ctx, struct getdents_callback, ctx);
 	unsigned long d_ino;
 	int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2,
 		sizeof(long));
@@ -232,11 +234,12 @@ struct getdents_callback64 {
 	int error;
 };
 
-static int filldir64(void * __buf, const char * name, int namlen, loff_t offset,
-		     u64 ino, unsigned int d_type)
+static int filldir64(struct dir_context *ctx, const char *name, int namlen,
+		     loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct linux_dirent64 __user *dirent;
-	struct getdents_callback64 * buf = (struct getdents_callback64 *) __buf;
+	struct getdents_callback64 *buf =
+		container_of(ctx, struct getdents_callback64, ctx);
 	int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1,
 		sizeof(u64));
 
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 7c36898af40..628248ce2f8 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -188,10 +188,11 @@ struct reiserfs_dentry_buf {
 };
 
 static int
-fill_with_dentries(void *buf, const char *name, int namelen, loff_t offset,
-		    u64 ino, unsigned int d_type)
+fill_with_dentries(struct dir_context *ctx, const char *name, int namelen,
+		   loff_t offset, u64 ino, unsigned int d_type)
 {
-	struct reiserfs_dentry_buf *dbuf = buf;
+	struct reiserfs_dentry_buf *dbuf =
+		container_of(ctx, struct reiserfs_dentry_buf, ctx);
 	struct dentry *dentry;
 
 	WARN_ON_ONCE(!mutex_is_locked(&dbuf->xadir->d_inode->i_mutex));
@@ -824,10 +825,12 @@ struct listxattr_buf {
 	struct dentry *dentry;
 };
 
-static int listxattr_filler(void *buf, const char *name, int namelen,
-			    loff_t offset, u64 ino, unsigned int d_type)
+static int listxattr_filler(struct dir_context *ctx, const char *name,
+			    int namelen, loff_t offset, u64 ino,
+			    unsigned int d_type)
 {
-	struct listxattr_buf *b = (struct listxattr_buf *)buf;
+	struct listxattr_buf *b =
+		container_of(ctx, struct listxattr_buf, ctx);
 	size_t size;
 
 	if (name[0] != '.' ||
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9ab779e8a63..00c8e4f65cb 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1467,7 +1467,10 @@ int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
  * This allows the kernel to read directories into kernel space or
  * to have different dirent layouts depending on the binary type.
  */
-typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
+struct dir_context;
+typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
+			 unsigned);
+
 struct dir_context {
 	const filldir_t actor;
 	loff_t pos;
-- 
cgit v1.2.3-70-g09d2


From a7400222e3eb7d5ce3820d2234905bbeafabd171 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 21 Oct 2014 15:20:42 -0400
Subject: new helper: is_root_inode()

replace open-coded instances

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/coda/coda_linux.c |  6 ------
 fs/coda/coda_linux.h |  1 -
 fs/coda/dir.c        | 12 ++++++------
 fs/ncpfs/dir.c       |  4 ++--
 include/linux/fs.h   |  5 +++++
 5 files changed, 13 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c
index 1326d38960d..f1714cfb589 100644
--- a/fs/coda/coda_linux.c
+++ b/fs/coda/coda_linux.c
@@ -40,12 +40,6 @@ int coda_iscontrol(const char *name, size_t length)
                 (strncmp(name, CODA_CONTROL, CODA_CONTROLLEN) == 0));
 }
 
-/* recognize /coda inode */
-int coda_isroot(struct inode *i)
-{
-    return ( i->i_sb->s_root->d_inode == i );
-}
-
 unsigned short coda_flags_to_cflags(unsigned short flags)
 {
 	unsigned short coda_flags = 0;
diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h
index d42b725b1d2..d6f7a76a1f5 100644
--- a/fs/coda/coda_linux.h
+++ b/fs/coda/coda_linux.h
@@ -52,7 +52,6 @@ int coda_setattr(struct dentry *, struct iattr *);
 
 /* this file:  heloers */
 char *coda_f2s(struct CodaFid *f);
-int coda_isroot(struct inode *i);
 int coda_iscontrol(const char *name, size_t length);
 
 void coda_vattr_to_iattr(struct inode *, struct coda_vattr *);
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 9c3dedc000d..7ff025966e4 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -107,7 +107,7 @@ static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsig
 	}
 
 	/* control object, create inode on the fly */
-	if (coda_isroot(dir) && coda_iscontrol(name, length)) {
+	if (is_root_inode(dir) && coda_iscontrol(name, length)) {
 		inode = coda_cnode_makectl(sb);
 		type = CODA_NOCACHE;
 	} else {
@@ -195,7 +195,7 @@ static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, bool
 	struct CodaFid newfid;
 	struct coda_vattr attrs;
 
-	if (coda_isroot(dir) && coda_iscontrol(name, length))
+	if (is_root_inode(dir) && coda_iscontrol(name, length))
 		return -EPERM;
 
 	error = venus_create(dir->i_sb, coda_i2f(dir), name, length, 
@@ -227,7 +227,7 @@ static int coda_mkdir(struct inode *dir, struct dentry *de, umode_t mode)
 	int error;
 	struct CodaFid newfid;
 
-	if (coda_isroot(dir) && coda_iscontrol(name, len))
+	if (is_root_inode(dir) && coda_iscontrol(name, len))
 		return -EPERM;
 
 	attrs.va_mode = mode;
@@ -261,7 +261,7 @@ static int coda_link(struct dentry *source_de, struct inode *dir_inode,
 	int len = de->d_name.len;
 	int error;
 
-	if (coda_isroot(dir_inode) && coda_iscontrol(name, len))
+	if (is_root_inode(dir_inode) && coda_iscontrol(name, len))
 		return -EPERM;
 
 	error = venus_link(dir_inode->i_sb, coda_i2f(inode),
@@ -287,7 +287,7 @@ static int coda_symlink(struct inode *dir_inode, struct dentry *de,
 	int symlen;
 	int error;
 
-	if (coda_isroot(dir_inode) && coda_iscontrol(name, len))
+	if (is_root_inode(dir_inode) && coda_iscontrol(name, len))
 		return -EPERM;
 
 	symlen = strlen(symname);
@@ -507,7 +507,7 @@ static int coda_dentry_revalidate(struct dentry *de, unsigned int flags)
 		return -ECHILD;
 
 	inode = de->d_inode;
-	if (!inode || coda_isroot(inode))
+	if (!inode || is_root_inode(inode))
 		goto out;
 	if (is_bad_inode(inode))
 		goto bad;
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 7cb751dfbee..461f6be5df2 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -198,8 +198,8 @@ ncp_single_volume(struct ncp_server *server)
 
 static inline int ncp_is_server_root(struct inode *inode)
 {
-	return (!ncp_single_volume(NCP_SERVER(inode)) &&
-		inode == inode->i_sb->s_root->d_inode);
+	return !ncp_single_volume(NCP_SERVER(inode)) &&
+		is_root_inode(inode);
 }
 
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 00c8e4f65cb..1c12c681803 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2789,6 +2789,11 @@ static inline void inode_has_no_xattr(struct inode *inode)
 		inode->i_flags |= S_NOSEC;
 }
 
+static inline bool is_root_inode(struct inode *inode)
+{
+	return inode == inode->i_sb->s_root->d_inode;
+}
+
 static inline bool dir_emit(struct dir_context *ctx,
 			    const char *name, int namelen,
 			    u64 ino, unsigned type)
-- 
cgit v1.2.3-70-g09d2


From a5dd1d72d868ec9c8f44d60ca29900b6a38321b4 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 2 Nov 2014 04:18:35 +0100
Subject: cfg802154: introduce cfg802154_registered_device

This patch introduce the cfg802154_registered_device struct. Like
cfg80211_registered_device in wireless this should contain similar
functionality for cfg802154. This patch should not change any behaviour.
We just adds cfg802154_registered_device as container for wpan_phy struct.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h |  8 +++++++-
 net/ieee802154/core.c   | 39 ++++++++++++++++++++++++++-------------
 net/ieee802154/core.h   | 18 ++++++++++++++++++
 net/ieee802154/sysfs.c  | 15 ++++++++++++---
 net/mac802154/main.c    |  2 +-
 5 files changed, 64 insertions(+), 18 deletions(-)
 create mode 100644 net/ieee802154/core.h

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 440b9bece9c..12de66bda9a 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -29,6 +29,11 @@
 #define WPAN_NUM_CHANNELS	27
 #define WPAN_NUM_PAGES		32
 
+struct wpan_phy;
+
+struct cfg802154_ops {
+};
+
 struct wpan_phy {
 	struct mutex pib_lock;
 
@@ -62,7 +67,8 @@ struct wpan_phy {
 
 #define to_phy(_dev)	container_of(_dev, struct wpan_phy, dev)
 
-struct wpan_phy *wpan_phy_alloc(size_t priv_size);
+struct wpan_phy *
+wpan_phy_alloc(const struct cfg802154_ops *ops, size_t priv_size);
 static inline void wpan_phy_set_dev(struct wpan_phy *phy, struct device *dev)
 {
 	phy->dev.parent = dev;
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index dc294a415d0..ed5b014dbec 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -21,6 +21,7 @@
 
 #include "ieee802154.h"
 #include "sysfs.h"
+#include "core.h"
 
 static DEFINE_MUTEX(wpan_phy_mutex);
 static int wpan_phy_idx;
@@ -76,31 +77,38 @@ static int wpan_phy_idx_valid(int idx)
 	return idx >= 0;
 }
 
-struct wpan_phy *wpan_phy_alloc(size_t priv_size)
+struct wpan_phy *
+wpan_phy_alloc(const struct cfg802154_ops *ops, size_t priv_size)
 {
-	struct wpan_phy *phy = kzalloc(sizeof(*phy) + priv_size,
-			GFP_KERNEL);
+	struct cfg802154_registered_device *rdev;
+	size_t alloc_size;
+
+	alloc_size = sizeof(*rdev) + priv_size;
+	rdev = kzalloc(alloc_size, GFP_KERNEL);
+	if (!rdev)
+		return NULL;
+
+	rdev->ops = ops;
 
-	if (!phy)
-		goto out;
 	mutex_lock(&wpan_phy_mutex);
-	phy->idx = wpan_phy_idx++;
-	if (unlikely(!wpan_phy_idx_valid(phy->idx))) {
+	rdev->wpan_phy.idx = wpan_phy_idx++;
+	if (unlikely(!wpan_phy_idx_valid(rdev->wpan_phy.idx))) {
 		wpan_phy_idx--;
 		mutex_unlock(&wpan_phy_mutex);
-		kfree(phy);
+		kfree(rdev);
 		goto out;
 	}
 	mutex_unlock(&wpan_phy_mutex);
 
-	mutex_init(&phy->pib_lock);
+	mutex_init(&rdev->wpan_phy.pib_lock);
 
-	device_initialize(&phy->dev);
-	dev_set_name(&phy->dev, "wpan-phy%d", phy->idx);
+	device_initialize(&rdev->wpan_phy.dev);
+	dev_set_name(&rdev->wpan_phy.dev, "wpan-phy%d", rdev->wpan_phy.idx);
 
-	phy->dev.class = &wpan_phy_class;
+	rdev->wpan_phy.dev.class = &wpan_phy_class;
+	rdev->wpan_phy.dev.platform_data = rdev;
 
-	return phy;
+	return &rdev->wpan_phy;
 
 out:
 	return NULL;
@@ -125,6 +133,11 @@ void wpan_phy_free(struct wpan_phy *phy)
 }
 EXPORT_SYMBOL(wpan_phy_free);
 
+void cfg802154_dev_free(struct cfg802154_registered_device *rdev)
+{
+	kfree(rdev);
+}
+
 static int __init wpan_phy_class_init(void)
 {
 	int rc;
diff --git a/net/ieee802154/core.h b/net/ieee802154/core.h
new file mode 100644
index 00000000000..26752ca54b4
--- /dev/null
+++ b/net/ieee802154/core.h
@@ -0,0 +1,18 @@
+#ifndef __IEEE802154_CORE_H
+#define __IEEE802154_CORE_H
+
+#include <net/cfg802154.h>
+
+struct cfg802154_registered_device {
+	const struct cfg802154_ops *ops;
+
+	/* must be last because of the way we do wpan_phy_priv(),
+	 * and it should at least be aligned to NETDEV_ALIGN
+	 */
+	struct wpan_phy wpan_phy __aligned(NETDEV_ALIGN);
+};
+
+/* free object */
+void cfg802154_dev_free(struct cfg802154_registered_device *rdev);
+
+#endif /* __IEEE802154_CORE_H */
diff --git a/net/ieee802154/sysfs.c b/net/ieee802154/sysfs.c
index eb9ca6f9912..c6e038099e0 100644
--- a/net/ieee802154/sysfs.c
+++ b/net/ieee802154/sysfs.c
@@ -17,6 +17,15 @@
 
 #include <net/cfg802154.h>
 
+#include "core.h"
+
+static inline struct cfg802154_registered_device *
+dev_to_rdev(struct device *dev)
+{
+	return container_of(dev, struct cfg802154_registered_device,
+			    wpan_phy.dev);
+}
+
 #define MASTER_SHOW_COMPLEX(name, format_string, args...)		\
 static ssize_t name ## _show(struct device *dev,			\
 			    struct device_attribute *attr, char *buf)	\
@@ -60,11 +69,11 @@ static ssize_t channels_supported_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(channels_supported);
 
-static void wpan_phy_release(struct device *d)
+static void wpan_phy_release(struct device *dev)
 {
-	struct wpan_phy *phy = container_of(d, struct wpan_phy, dev);
+	struct cfg802154_registered_device *rdev = dev_to_rdev(dev);
 
-	kfree(phy);
+	cfg802154_dev_free(rdev);
 }
 
 static struct attribute *pmib_attrs[] = {
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 86e533ed377..ebc2bb123cf 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -169,7 +169,7 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops)
 
 	priv_size = ALIGN(sizeof(*local), NETDEV_ALIGN) + priv_data_len;
 
-	phy = wpan_phy_alloc(priv_size);
+	phy = wpan_phy_alloc(NULL, priv_size);
 	if (!phy) {
 		pr_err("failure to allocate master IEEE802.15.4 device\n");
 		return NULL;
-- 
cgit v1.2.3-70-g09d2


From 4a9a816a4f8c79260446811bdf80615b36539949 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 2 Nov 2014 04:18:38 +0100
Subject: cfg802154: convert deprecated iface add and del

This patch removes the wpan_phy callbacks for add and del an interface
on a phy. Instead we introduce deprecated cfg802154 callbacks for this.
Furthermore we introduce a new netlink interface nl802154 which use
different callbacks. The deprecated function is to have a backwards
compatibility with the current netlink interface.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h      |  9 +++++----
 net/ieee802154/nl-phy.c      | 19 ++++++-------------
 net/ieee802154/rdev-ops.h    | 23 +++++++++++++++++++++++
 net/mac802154/cfg.c          | 17 +++++++++++++++++
 net/mac802154/ieee802154_i.h |  4 ++++
 net/mac802154/main.c         |  8 ++------
 6 files changed, 57 insertions(+), 23 deletions(-)
 create mode 100644 net/ieee802154/rdev-ops.h

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 12de66bda9a..864bce2b072 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -32,6 +32,11 @@
 struct wpan_phy;
 
 struct cfg802154_ops {
+	struct net_device * (*add_virtual_intf_deprecated)(struct wpan_phy *wpan_phy,
+							   const char *name,
+							   int type);
+	void (*del_virtual_intf_deprecated)(struct wpan_phy *wpan_phy,
+					    struct net_device *dev);
 };
 
 struct wpan_phy {
@@ -58,10 +63,6 @@ struct wpan_phy {
 	struct device dev;
 	int idx;
 
-	struct net_device *(*add_iface)(struct wpan_phy *phy,
-					const char *name, int type);
-	void (*del_iface)(struct wpan_phy *phy, struct net_device *dev);
-
 	char priv[0] __aligned(NETDEV_ALIGN);
 };
 
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 0afe760ff51..5d914d30e0b 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -30,6 +30,8 @@
 #include <linux/nl802154.h>
 
 #include "ieee802154.h"
+#include "rdev-ops.h"
+#include "core.h"
 
 static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid,
 				  u32 seq, int flags, struct wpan_phy *phy)
@@ -203,11 +205,6 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info)
 	if (!msg)
 		goto out_dev;
 
-	if (!phy->add_iface) {
-		rc = -EINVAL;
-		goto nla_put_failure;
-	}
-
 	if (info->attrs[IEEE802154_ATTR_HW_ADDR] &&
 	    nla_len(info->attrs[IEEE802154_ATTR_HW_ADDR]) !=
 			IEEE802154_ADDR_LEN) {
@@ -223,7 +220,8 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	dev = phy->add_iface(phy, devname, type);
+	dev = rdev_add_virtual_intf_deprecated(wpan_phy_to_rdev(phy), devname,
+					       type);
 	if (IS_ERR(dev)) {
 		rc = PTR_ERR(dev);
 		goto nla_put_failure;
@@ -257,7 +255,7 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info)
 
 dev_unregister:
 	rtnl_lock(); /* del_iface must be called with RTNL lock */
-	phy->del_iface(phy, dev);
+	rdev_del_virtual_intf_deprecated(wpan_phy_to_rdev(phy), dev);
 	dev_put(dev);
 	rtnl_unlock();
 nla_put_failure:
@@ -319,13 +317,8 @@ int ieee802154_del_iface(struct sk_buff *skb, struct genl_info *info)
 	if (!msg)
 		goto out_dev;
 
-	if (!phy->del_iface) {
-		rc = -EINVAL;
-		goto nla_put_failure;
-	}
-
 	rtnl_lock();
-	phy->del_iface(phy, dev);
+	rdev_del_virtual_intf_deprecated(wpan_phy_to_rdev(phy), dev);
 
 	/* We don't have device anymore */
 	dev_put(dev);
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
new file mode 100644
index 00000000000..ac8824ec168
--- /dev/null
+++ b/net/ieee802154/rdev-ops.h
@@ -0,0 +1,23 @@
+#ifndef __CFG802154_RDEV_OPS
+#define __CFG802154_RDEV_OPS
+
+#include <net/cfg802154.h>
+
+#include "core.h"
+
+static inline struct net_device *
+rdev_add_virtual_intf_deprecated(struct cfg802154_registered_device *rdev,
+				 const char *name, int type)
+{
+	return rdev->ops->add_virtual_intf_deprecated(&rdev->wpan_phy, name,
+						      type);
+}
+
+static inline void
+rdev_del_virtual_intf_deprecated(struct cfg802154_registered_device *rdev,
+				 struct net_device *dev)
+{
+	rdev->ops->del_virtual_intf_deprecated(&rdev->wpan_phy, dev);
+}
+
+#endif /* __CFG802154_RDEV_OPS */
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index 105468ec8f2..75a5d258ac2 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -15,5 +15,22 @@
 
 #include <net/cfg802154.h>
 
+#include "ieee802154_i.h"
+
+static struct net_device *
+ieee802154_add_iface_deprecated(struct wpan_phy *wpan_phy,
+				const char *name, int type)
+{
+	return mac802154_add_iface(wpan_phy, name, type);
+}
+
+static void ieee802154_del_iface_deprecated(struct wpan_phy *wpan_phy,
+					    struct net_device *dev)
+{
+	mac802154_del_iface(wpan_phy, dev);
+}
+
 const struct cfg802154_ops mac802154_config_ops = {
+	.add_virtual_intf_deprecated = ieee802154_add_iface_deprecated,
+	.del_virtual_intf_deprecated = ieee802154_del_iface_deprecated,
 };
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index 1086a9d96f8..39af6eaec41 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -174,4 +174,8 @@ void mac802154_get_table(struct net_device *dev,
 			 struct ieee802154_llsec_table **t);
 void mac802154_unlock_table(struct net_device *dev);
 
+struct net_device *
+mac802154_add_iface(struct wpan_phy *phy, const char *name, int type);
+void mac802154_del_iface(struct wpan_phy *phy, struct net_device *dev);
+
 #endif /* __IEEE802154_I_H */
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 785abb1aafb..b34ddbf43c3 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -59,8 +59,7 @@ mac802154_netdev_register(struct wpan_phy *phy, struct net_device *dev)
 	return 0;
 }
 
-static void
-mac802154_del_iface(struct wpan_phy *phy, struct net_device *dev)
+void mac802154_del_iface(struct wpan_phy *phy, struct net_device *dev)
 {
 	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
 
@@ -76,7 +75,7 @@ mac802154_del_iface(struct wpan_phy *phy, struct net_device *dev)
 	unregister_netdevice(sdata->dev);
 }
 
-static struct net_device *
+struct net_device *
 mac802154_add_iface(struct wpan_phy *phy, const char *name, int type)
 {
 	struct net_device *dev;
@@ -221,9 +220,6 @@ int ieee802154_register_hw(struct ieee802154_hw *hw)
 
 	wpan_phy_set_dev(local->phy, local->hw.parent);
 
-	local->phy->add_iface = mac802154_add_iface;
-	local->phy->del_iface = mac802154_del_iface;
-
 	rc = wpan_phy_register(local->phy);
 	if (rc < 0)
 		goto out_wq;
-- 
cgit v1.2.3-70-g09d2


From ab24f50f2a3e3f6a38b4852530534aa99d86b4d1 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 2 Nov 2014 04:18:40 +0100
Subject: mac802154: add helper for converting dev_addr

This patch adds a helper for converting the dev_addr attribute in
netdevice to __le64 type. The dev_addr attribute is a char pointer
and contains the extended address in big endian byte order.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/mac802154.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 8f1de6844cb..c17acbd0dad 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -214,6 +214,15 @@ struct ieee802154_ops {
 						const bool on);
 };
 
+/**
+ * ieee802154_netdev_to_extended_addr - convert __be64 u8 pointer to __le64
+ * @dev_addr: big endian address pointer like netdevice dev_addr attribute
+ */
+static inline __le64 ieee802154_netdev_to_extended_addr(const u8 *dev_addr)
+{
+	return (__le64)swab64(*((__be64 *)dev_addr));
+}
+
 /* Basic interface to register ieee802154 hwice */
 struct ieee802154_hw *
 ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops);
-- 
cgit v1.2.3-70-g09d2


From cb904b0a16305f9b2a98200cc6eb9dc3610278b0 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 2 Nov 2014 04:18:45 +0100
Subject: ieee802154: add extended address validation helper

This patch introduce an extended address validation helper to check if
an extended address is valid or not.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/ieee802154.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index 6e50a2a1d48..9bba5ca7f0a 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -197,4 +197,18 @@ static inline bool ieee802154_is_valid_psdu_len(const u8 len)
 	return (len >= IEEE802154_MIN_PSDU_LEN && len <= IEEE802154_MTU);
 }
 
+/**
+ * ieee802154_is_valid_psdu_len - check if extended addr is valid
+ * @addr: extended addr to check
+ */
+static inline bool ieee802154_is_valid_extended_addr(const __le64 addr)
+{
+	/* These EUI-64 addresses are reserved by IEEE. 0xffffffffffffffff
+	 * is used internally as extended to short address broadcast mapping.
+	 * This is currently a workaround because neighbor discovery can't
+	 * deal with short addresses types right now.
+	 */
+	return ((addr != 0x0000000000000000) || (addr != 0xffffffffffffffff));
+}
+
 #endif /* LINUX_IEEE802154_H */
-- 
cgit v1.2.3-70-g09d2


From 24dfa343716a493472db0555342bb88678efa444 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 2 Nov 2014 02:56:41 +0100
Subject: Bluetooth: Print error message for HCI_Hardware_Error event

When the HCI_Hardware_Error event is send by the controller or
injected by the driver, then at least print an error message.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h |  5 +++++
 net/bluetooth/hci_event.c   | 11 +++++++++++
 2 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 6e8f2496730..ecfa306e137 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1463,6 +1463,11 @@ struct hci_ev_cmd_status {
 	__le16   opcode;
 } __packed;
 
+#define HCI_EV_HARDWARE_ERROR		0x10
+struct hci_ev_hardware_error {
+	__u8     code;
+} __packed;
+
 #define HCI_EV_ROLE_CHANGE		0x12
 struct hci_ev_role_change {
 	__u8     status;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 3dd2550b4c0..2f02ff0ed78 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2925,6 +2925,13 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	}
 }
 
+static void hci_hardware_error_evt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_ev_hardware_error *ev = (void *) skb->data;
+
+	BT_ERR("%s hardware error 0x%2.2x", hdev->name, ev->code);
+}
+
 static void hci_role_change_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_role_change *ev = (void *) skb->data;
@@ -4746,6 +4753,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cmd_status_evt(hdev, skb);
 		break;
 
+	case HCI_EV_HARDWARE_ERROR:
+		hci_hardware_error_evt(hdev, skb);
+		break;
+
 	case HCI_EV_ROLE_CHANGE:
 		hci_role_change_evt(hdev, skb);
 		break;
-- 
cgit v1.2.3-70-g09d2


From 75e0569f7fc22272ec5e3b99bf94c6f0ad43b35f Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 2 Nov 2014 08:15:38 +0100
Subject: Bluetooth: Add hci_reset_dev() for driver triggerd stack reset

Some Bluetooth drivers require to reset the upper stack. To avoid having
all drivers send HCI Hardware Error events, provide a generic function
to wrap the reset functionality.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_core.c         | 18 ++++++++++++++++++
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index b8685a77a15..27ddb905b35 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -856,6 +856,7 @@ int hci_register_dev(struct hci_dev *hdev);
 void hci_unregister_dev(struct hci_dev *hdev);
 int hci_suspend_dev(struct hci_dev *hdev);
 int hci_resume_dev(struct hci_dev *hdev);
+int hci_reset_dev(struct hci_dev *hdev);
 int hci_dev_open(__u16 dev);
 int hci_dev_close(__u16 dev);
 int hci_dev_reset(__u16 dev);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 41b147c36d1..a12e018ee21 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -4248,6 +4248,24 @@ int hci_resume_dev(struct hci_dev *hdev)
 }
 EXPORT_SYMBOL(hci_resume_dev);
 
+/* Reset HCI device */
+int hci_reset_dev(struct hci_dev *hdev)
+{
+	const u8 hw_err[] = { HCI_EV_HARDWARE_ERROR, 0x01, 0x00 };
+	struct sk_buff *skb;
+
+	skb = bt_skb_alloc(3, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	bt_cb(skb)->pkt_type = HCI_EVENT_PKT;
+	memcpy(skb_put(skb, 3), hw_err, 3);
+
+	/* Send Hardware Error to upper stack */
+	return hci_recv_frame(hdev, skb);
+}
+EXPORT_SYMBOL(hci_reset_dev);
+
 /* Receive frame from HCI drivers */
 int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
-- 
cgit v1.2.3-70-g09d2


From a4164eb4dd3f4f2a22f8bf7b26394e8384f3d9a2 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 2 Nov 2014 21:43:01 +0100
Subject: ieee802154: add missing ULL definition

Running make C=2 occurs warning:

constant 0xffffffffffffffff is so big it is unsigned long

This patch fix this warning by adding a ULL to the constant definitions.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Reported-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/ieee802154.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index 9bba5ca7f0a..9da7c011fbb 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -208,7 +208,8 @@ static inline bool ieee802154_is_valid_extended_addr(const __le64 addr)
 	 * This is currently a workaround because neighbor discovery can't
 	 * deal with short addresses types right now.
 	 */
-	return ((addr != 0x0000000000000000) || (addr != 0xffffffffffffffff));
+	return ((addr != 0x0000000000000000ULL) ||
+		(addr != 0xffffffffffffffffULL));
 }
 
 #endif /* LINUX_IEEE802154_H */
-- 
cgit v1.2.3-70-g09d2


From c28bee84c5c49312befe1b442e1044ac2392d80d Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 2 Nov 2014 21:43:02 +0100
Subject: ieee802154: fix byteorder issues

This patch fix byteorder issues which occurs because we compare __le64
with an host byteorder value. Simple add a cpu_to_le64 to convert the
host byteorder values to __le64.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Reported-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/ieee802154.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index 9da7c011fbb..5d9e7459d94 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -24,6 +24,7 @@
 #define LINUX_IEEE802154_H
 
 #include <linux/types.h>
+#include <asm/byteorder.h>
 
 #define IEEE802154_MTU			127
 #define IEEE802154_MIN_PSDU_LEN		5
@@ -208,8 +209,8 @@ static inline bool ieee802154_is_valid_extended_addr(const __le64 addr)
 	 * This is currently a workaround because neighbor discovery can't
 	 * deal with short addresses types right now.
 	 */
-	return ((addr != 0x0000000000000000ULL) ||
-		(addr != 0xffffffffffffffffULL));
+	return ((addr != cpu_to_le64(0x0000000000000000ULL)) ||
+		(addr != cpu_to_le64(0xffffffffffffffffULL)));
 }
 
 #endif /* LINUX_IEEE802154_H */
-- 
cgit v1.2.3-70-g09d2


From f753f7eeb4178ab8eeaf513a4fdf1c20ddf40474 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 2 Nov 2014 21:43:03 +0100
Subject: mac802154: fix byteorder issues

Running make C=2 occurs these warnings:

cast from restricted __be64
incorrect type in argument 1 (different base types)
expected unsigned long long[unsigned] [usertype] val
got restricted __be64 [usertype]<noident>
cast from restricted __be64
cast to restricted __le64

This patch fix these warnings by forcing to __le64 type and using swabp64
instead swab64.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Reported-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/mac802154.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index c17acbd0dad..8b0c26bc076 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -215,12 +215,12 @@ struct ieee802154_ops {
 };
 
 /**
- * ieee802154_netdev_to_extended_addr - convert __be64 u8 pointer to __le64
+ * ieee802154_netdev_to_extended_addr - convert big endian 64 byte void pointer to __le64
  * @dev_addr: big endian address pointer like netdevice dev_addr attribute
  */
-static inline __le64 ieee802154_netdev_to_extended_addr(const u8 *dev_addr)
+static inline __le64 ieee802154_netdev_to_extended_addr(const void *dev_addr)
 {
-	return (__le64)swab64(*((__be64 *)dev_addr));
+	return (__force __le64)swab64p(dev_addr);
 }
 
 /* Basic interface to register ieee802154 hwice */
-- 
cgit v1.2.3-70-g09d2


From 43d6bc46e2d342204693d24ce1c607305d93d8fb Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 2 Nov 2014 20:52:23 +0100
Subject: Bluetooth: Introduce HCI_QUIRK_STRICT_DUPLICATE_FILTER

Some vendors decide to use a strict duplicate filter policy that only
filters on Bluetooth device addresses. This means that when the RSSI
changes, these devices are not reported again. During discovery it is
useful to actually get the RSSI updates.

Since this is specific to each controller, add a new quirk setting
that allows drivers to tell the core what kind of filtering policy
the controller uses.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index ecfa306e137..2e08f5a8946 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -129,6 +129,15 @@ enum {
 	 * during the hdev->setup vendor callback.
 	 */
 	HCI_QUIRK_INVALID_BDADDR,
+
+	/* When this quirk is set, the duplicate filtering during
+	 * scanning is based on Bluetooth devices addresses. To allow
+	 * RSSI based updates, restart scanning if needed.
+	 *
+	 * This quirk can be set before hci_register_dev is called or
+	 * during the hdev->setup vendor callback.
+	 */
+	HCI_QUIRK_STRICT_DUPLICATE_FILTER,
 };
 
 /* HCI device flags */
-- 
cgit v1.2.3-70-g09d2


From 845472e8d50c898c73b4f69f4edad5249b13d6a9 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Mon, 3 Nov 2014 05:16:08 +0100
Subject: Bluetooth: Add hci_conn_lookup_type() helper function

Some drivers require knowledge of what connection handle is assigned
to what connection link type (ACL or SCO/eSCO). Instead of having each
driver implement connection tracking, provide a simple helper function
for lookup of the link type.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h      |  1 +
 include/net/bluetooth/hci_core.h | 20 ++++++++++++++++++++
 2 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 2e08f5a8946..d5f85d7746b 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -274,6 +274,7 @@ enum {
 /* Low Energy links do not have defined link type. Use invented one */
 #define LE_LINK		0x80
 #define AMP_LINK	0x81
+#define INVALID_LINK	0xff
 
 /* LMP features */
 #define LMP_3SLOT	0x01
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 27ddb905b35..4e39a5adfca 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -646,6 +646,26 @@ static inline unsigned int hci_conn_count(struct hci_dev *hdev)
 	return c->acl_num + c->amp_num + c->sco_num + c->le_num;
 }
 
+static inline __u8 hci_conn_lookup_type(struct hci_dev *hdev, __u16 handle)
+{
+	struct hci_conn_hash *h = &hdev->conn_hash;
+	struct hci_conn *c;
+	__u8 type = INVALID_LINK;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(c, &h->list, list) {
+		if (c->handle == handle) {
+			type = c->type;
+			break;
+		}
+	}
+
+	rcu_read_unlock();
+
+	return type;
+}
+
 static inline struct hci_conn *hci_conn_hash_lookup_handle(struct hci_dev *hdev,
 								__u16 handle)
 {
-- 
cgit v1.2.3-70-g09d2


From 7f05db6a20fe4d85bada20d365c78029831b9de1 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Sun, 12 Oct 2014 11:34:00 +0300
Subject: kvm: drop unsupported capabilities, fix documentation

No kernel ever reported KVM_CAP_DEVICE_MSIX, KVM_CAP_DEVICE_MSI,
KVM_CAP_DEVICE_ASSIGNMENT, KVM_CAP_DEVICE_DEASSIGNMENT.

This makes the documentation wrong, and no application ever
written to use these capabilities has a chance to work correctly.
The only way to detect support is to try, and test errno for ENOTTY.
That's unfortunate, but we can't fix the past.

Document the actual semantics, and drop the definitions from
the exported header to make it easier for application
developers to note and fix the bug.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 40 ++++++++++++++++++++++++++++++++-------
 include/uapi/linux/kvm.h          |  8 --------
 2 files changed, 33 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 7610eaa4d49..7a943c23db1 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -68,9 +68,12 @@ description:
 
   Capability: which KVM extension provides this ioctl.  Can be 'basic',
       which means that is will be provided by any kernel that supports
-      API version 12 (see section 4.1), or a KVM_CAP_xyz constant, which
+      API version 12 (see section 4.1), a KVM_CAP_xyz constant, which
       means availability needs to be checked with KVM_CHECK_EXTENSION
-      (see section 4.4).
+      (see section 4.4), or 'none' which means that while not all kernels
+      support this ioctl, there's no capability bit to check its
+      availability: for kernels that don't support the ioctl,
+      the ioctl returns -ENOTTY.
 
   Architectures: which instruction set architectures provide this ioctl.
       x86 includes both i386 and x86_64.
@@ -1257,7 +1260,7 @@ The flags bitmap is defined as:
 
 4.48 KVM_ASSIGN_PCI_DEVICE
 
-Capability: KVM_CAP_DEVICE_ASSIGNMENT
+Capability: none
 Architectures: x86 ia64
 Type: vm ioctl
 Parameters: struct kvm_assigned_pci_dev (in)
@@ -1298,10 +1301,16 @@ Only PCI header type 0 devices with PCI BAR resources are supported by
 device assignment.  The user requesting this ioctl must have read/write
 access to the PCI sysfs resource files associated with the device.
 
+Errors:
+  ENOTTY: kernel does not support this ioctl
+
+  Other error conditions may be defined by individual device types or
+  have their standard meanings.
+
 
 4.49 KVM_DEASSIGN_PCI_DEVICE
 
-Capability: KVM_CAP_DEVICE_DEASSIGNMENT
+Capability: none
 Architectures: x86 ia64
 Type: vm ioctl
 Parameters: struct kvm_assigned_pci_dev (in)
@@ -1309,9 +1318,14 @@ Returns: 0 on success, -1 on error
 
 Ends PCI device assignment, releasing all associated resources.
 
-See KVM_CAP_DEVICE_ASSIGNMENT for the data structure. Only assigned_dev_id is
+See KVM_ASSIGN_PCI_DEVICE for the data structure. Only assigned_dev_id is
 used in kvm_assigned_pci_dev to identify the device.
 
+Errors:
+  ENOTTY: kernel does not support this ioctl
+
+  Other error conditions may be defined by individual device types or
+  have their standard meanings.
 
 4.50 KVM_ASSIGN_DEV_IRQ
 
@@ -1346,6 +1360,12 @@ The following flags are defined:
 It is not valid to specify multiple types per host or guest IRQ. However, the
 IRQ type of host and guest can differ or can even be null.
 
+Errors:
+  ENOTTY: kernel does not support this ioctl
+
+  Other error conditions may be defined by individual device types or
+  have their standard meanings.
+
 
 4.51 KVM_DEASSIGN_DEV_IRQ
 
@@ -1423,7 +1443,7 @@ struct kvm_irq_routing_s390_adapter {
 
 4.53 KVM_ASSIGN_SET_MSIX_NR
 
-Capability: KVM_CAP_DEVICE_MSIX
+Capability: none
 Architectures: x86 ia64
 Type: vm ioctl
 Parameters: struct kvm_assigned_msix_nr (in)
@@ -1445,7 +1465,7 @@ struct kvm_assigned_msix_nr {
 
 4.54 KVM_ASSIGN_SET_MSIX_ENTRY
 
-Capability: KVM_CAP_DEVICE_MSIX
+Capability: none
 Architectures: x86 ia64
 Type: vm ioctl
 Parameters: struct kvm_assigned_msix_entry (in)
@@ -1461,6 +1481,12 @@ struct kvm_assigned_msix_entry {
 	__u16 padding[3];
 };
 
+Errors:
+  ENOTTY: kernel does not support this ioctl
+
+  Other error conditions may be defined by individual device types or
+  have their standard meanings.
+
 
 4.55 KVM_SET_TSC_KHZ
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 60768822b14..6d59e5b39c9 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -647,11 +647,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_MP_STATE 14
 #define KVM_CAP_COALESCED_MMIO 15
 #define KVM_CAP_SYNC_MMU 16  /* Changes to host mmap are reflected in guest */
-#define KVM_CAP_DEVICE_ASSIGNMENT 17
 #define KVM_CAP_IOMMU 18
-#ifdef __KVM_HAVE_MSI
-#define KVM_CAP_DEVICE_MSI 20
-#endif
 /* Bug in KVM_SET_USER_MEMORY_REGION fixed: */
 #define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21
 #define KVM_CAP_USER_NMI 22
@@ -663,10 +659,6 @@ struct kvm_ppc_smmu_info {
 #endif
 #define KVM_CAP_IRQ_ROUTING 25
 #define KVM_CAP_IRQ_INJECT_STATUS 26
-#define KVM_CAP_DEVICE_DEASSIGNMENT 27
-#ifdef __KVM_HAVE_MSIX
-#define KVM_CAP_DEVICE_MSIX 28
-#endif
 #define KVM_CAP_ASSIGN_DEV_IRQ 29
 /* Another bug in KVM_SET_USER_MEMORY_REGION fixed: */
 #define KVM_CAP_JOIN_MEMORY_REGIONS_WORKS 30
-- 
cgit v1.2.3-70-g09d2


From dd63a9c2952ed142c64fd68c1a74d0d6fcac586f Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 3 Nov 2014 10:31:47 +0100
Subject: ASoC: Remove snd_soc_platform_driver suspend/resume callbacks

Those are unused and new drivers should use device driver suspend/resume.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  |  4 ----
 sound/soc/soc-core.c | 10 ----------
 2 files changed, 14 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index ad47e9660b2..edbb07ba4cb 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -857,8 +857,6 @@ struct snd_soc_platform_driver {
 
 	int (*probe)(struct snd_soc_platform *);
 	int (*remove)(struct snd_soc_platform *);
-	int (*suspend)(struct snd_soc_dai *dai);
-	int (*resume)(struct snd_soc_dai *dai);
 	struct snd_soc_component_driver component_driver;
 
 	/* pcm creation and destruction */
@@ -891,8 +889,6 @@ struct snd_soc_platform {
 	struct device *dev;
 	const struct snd_soc_platform_driver *driver;
 
-	unsigned int suspended:1; /* platform is suspended */
-
 	struct list_head list;
 
 	struct snd_soc_component component;
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index a2b51edf6d8..0509d726759 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -592,17 +592,12 @@ int snd_soc_suspend(struct device *dev)
 
 	for (i = 0; i < card->num_rtd; i++) {
 		struct snd_soc_dai *cpu_dai = card->rtd[i].cpu_dai;
-		struct snd_soc_platform *platform = card->rtd[i].platform;
 
 		if (card->rtd[i].dai_link->ignore_suspend)
 			continue;
 
 		if (cpu_dai->driver->suspend && !cpu_dai->driver->ac97_control)
 			cpu_dai->driver->suspend(cpu_dai);
-		if (platform->driver->suspend && !platform->suspended) {
-			platform->driver->suspend(cpu_dai);
-			platform->suspended = 1;
-		}
 	}
 
 	/* close any waiting streams and save state */
@@ -775,17 +770,12 @@ static void soc_resume_deferred(struct work_struct *work)
 
 	for (i = 0; i < card->num_rtd; i++) {
 		struct snd_soc_dai *cpu_dai = card->rtd[i].cpu_dai;
-		struct snd_soc_platform *platform = card->rtd[i].platform;
 
 		if (card->rtd[i].dai_link->ignore_suspend)
 			continue;
 
 		if (cpu_dai->driver->resume && !cpu_dai->driver->ac97_control)
 			cpu_dai->driver->resume(cpu_dai);
-		if (platform->driver->resume && platform->suspended) {
-			platform->driver->resume(cpu_dai);
-			platform->suspended = 0;
-		}
 	}
 
 	if (card->resume_post)
-- 
cgit v1.2.3-70-g09d2


From 2a374b78f5c2b5f31d35f8a7cd004989d6936756 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 3 Nov 2014 10:31:48 +0100
Subject: ASoC: Remove platform field from snd_soc_dai

Typically a DAI does not need direct access to the platform. Currently the
only user of this field is in a platform driver where we have a more direct
way of getting a pointer to the platform. This patch updates the driver to
use the more direct way and then removes the platform field from the
snd_soc_dai struct.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dai.h   | 1 -
 sound/soc/soc-core.c      | 2 --
 sound/soc/txx9/txx9aclc.c | 2 +-
 3 files changed, 1 insertion(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index e8b3080d196..45d0fa10ab9 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -268,7 +268,6 @@ struct snd_soc_dai {
 	unsigned int sample_bits;
 
 	/* parent platform/codec */
-	struct snd_soc_platform *platform;
 	struct snd_soc_codec *codec;
 	struct snd_soc_component *component;
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 0509d726759..e20bb65a163 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1309,7 +1309,6 @@ static int soc_probe_link_dais(struct snd_soc_card *card, int num, int order)
 {
 	struct snd_soc_dai_link *dai_link = &card->dai_link[num];
 	struct snd_soc_pcm_runtime *rtd = &card->rtd[num];
-	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	int i, ret;
 
@@ -1317,7 +1316,6 @@ static int soc_probe_link_dais(struct snd_soc_card *card, int num, int order)
 			card->name, num, order);
 
 	/* config components */
-	cpu_dai->platform = platform;
 	cpu_dai->card = card;
 	for (i = 0; i < rtd->num_codecs; i++)
 		rtd->codec_dais[i]->card = card;
diff --git a/sound/soc/txx9/txx9aclc.c b/sound/soc/txx9/txx9aclc.c
index cd71fd889d8..00b7e2d0269 100644
--- a/sound/soc/txx9/txx9aclc.c
+++ b/sound/soc/txx9/txx9aclc.c
@@ -292,7 +292,7 @@ static int txx9aclc_pcm_new(struct snd_soc_pcm_runtime *rtd)
 	struct snd_card *card = rtd->card->snd_card;
 	struct snd_soc_dai *dai = rtd->cpu_dai;
 	struct snd_pcm *pcm = rtd->pcm;
-	struct platform_device *pdev = to_platform_device(dai->platform->dev);
+	struct platform_device *pdev = to_platform_device(rtd->platform->dev);
 	struct txx9aclc_soc_device *dev;
 	struct resource *r;
 	int i;
-- 
cgit v1.2.3-70-g09d2


From 1a3f83f6493f9d78aa0fe31401fd530b0fe296da Mon Sep 17 00:00:00 2001
From: JD Cole <jd@jdc.me>
Date: Fri, 31 Oct 2014 17:34:42 -0700
Subject: HID: plantronics: fix errant mouse events

This version of the driver prevents Telephony pages which are not mapped as
Consumer Control applications AND are not on the Consumer Page from being
registered by the hid-input driver.

Signed-off-by: JD Cole <jd.cole@plantronics.com>
Reviewed-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/Kconfig           |  7 ++++
 drivers/hid/Makefile          |  1 +
 drivers/hid/hid-core.c        |  1 +
 drivers/hid/hid-ids.h         |  2 ++
 drivers/hid/hid-plantronics.c | 78 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/hid.h           |  3 ++
 6 files changed, 92 insertions(+)
 create mode 100644 drivers/hid/hid-plantronics.c

(limited to 'include')

diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index f42df4dd58d..bf1c74e19c7 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -613,6 +613,13 @@ config HID_PICOLCD_CIR
 	---help---
 	  Provide access to PicoLCD's CIR interface via remote control (LIRC).
 
+config HID_PLANTRONICS
+	tristate "Plantronics USB HID Driver"
+	default !EXPERT
+	depends on HID
+	---help---
+	Provides HID support for Plantronics telephony devices.
+
 config HID_PRIMAX
 	tristate "Primax non-fully HID-compliant devices"
 	depends on HID
diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
index e2850d8af9c..5e7ac59447d 100644
--- a/drivers/hid/Makefile
+++ b/drivers/hid/Makefile
@@ -94,6 +94,7 @@ ifdef CONFIG_DEBUG_FS
 hid-picolcd-y			+= hid-picolcd_debugfs.o
 endif
 
+obj-$(CONFIG_HID_PLANTRONICS)	+= hid-plantronics.o
 obj-$(CONFIG_HID_PRIMAX)	+= hid-primax.o
 obj-$(CONFIG_HID_ROCCAT)	+= hid-roccat.o hid-roccat-common.o \
 	hid-roccat-arvo.o hid-roccat-isku.o hid-roccat-kone.o \
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 73bd9e2e42b..d50313ca64a 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1886,6 +1886,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ORTEK, USB_DEVICE_ID_ORTEK_WKB2000) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PENMOUNT, USB_DEVICE_ID_PENMOUNT_6000) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PETALYNX, USB_DEVICE_ID_PETALYNX_MAXTER_REMOTE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, HID_ANY_ID) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_KEYBOARD) },
 #if IS_ENABLED(CONFIG_HID_ROCCAT)
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ARVO) },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index e23ab8b3062..f9f476db671 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -715,6 +715,8 @@
 #define USB_DEVICE_ID_ORTEK_PKB1700	0x1700
 #define USB_DEVICE_ID_ORTEK_WKB2000	0x2000
 
+#define USB_VENDOR_ID_PLANTRONICS	0x047f
+
 #define USB_VENDOR_ID_PANASONIC		0x04da
 #define USB_DEVICE_ID_PANABOARD_UBT780	0x1044
 #define USB_DEVICE_ID_PANABOARD_UBT880	0x104d
diff --git a/drivers/hid/hid-plantronics.c b/drivers/hid/hid-plantronics.c
new file mode 100644
index 00000000000..215cdbd10de
--- /dev/null
+++ b/drivers/hid/hid-plantronics.c
@@ -0,0 +1,78 @@
+/*
+ *  Plantronics USB HID Driver
+ *
+ *  Copyright (c) 2014 JD Cole <jd.cole@plantronics.com>
+ *  Copyright (c) 2014 Terry Junge <terry.junge@plantronics.com>
+ */
+
+/*
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include "hid-ids.h"
+
+#include <linux/hid.h>
+#include <linux/module.h>
+
+static int plantronics_input_mapping(struct hid_device *hdev,
+				     struct hid_input *hi,
+				     struct hid_field *field,
+				     struct hid_usage *usage,
+				     unsigned long **bit, int *max)
+{
+	if (field->application == HID_CP_CONSUMERCONTROL
+	    && (usage->hid & HID_USAGE_PAGE) == HID_UP_CONSUMER) {
+		hid_dbg(hdev, "usage: %08x (appl: %08x) - defaulted\n",
+			 usage->hid, field->application);
+		return 0;
+	}
+
+	hid_dbg(hdev, "usage: %08x (appl: %08x) - ignored\n",
+		usage->hid, field->application);
+
+	return -1;
+}
+
+static int plantronics_probe(struct hid_device *hdev,
+			     const struct hid_device_id *id)
+{
+	int ret;
+
+	ret = hid_parse(hdev);
+	if (ret) {
+		hid_err(hdev, "parse failed\n");
+		goto err;
+	}
+
+	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
+	if (ret) {
+		hid_err(hdev, "hw start failed\n");
+		goto err;
+	}
+
+	return 0;
+ err:
+	return ret;
+}
+
+static const struct hid_device_id plantronics_devices[] = {
+	{ HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, HID_ANY_ID) },
+	{ }
+};
+MODULE_DEVICE_TABLE(hid, plantronics_devices);
+
+static struct hid_driver plantronics_driver = {
+	.name = "plantronics",
+	.id_table = plantronics_devices,
+	.input_mapping = plantronics_input_mapping,
+	.probe = plantronics_probe,
+};
+module_hid_driver(plantronics_driver);
+
+MODULE_AUTHOR("JD Cole <jd.cole@plantronics.com>");
+MODULE_AUTHOR("Terry Junge <terry.junge@plantronics.com>");
+MODULE_DESCRIPTION("Plantronics USB HID Driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 78ea9bf941c..a63f2aaed64 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -234,6 +234,9 @@ struct hid_item {
 #define HID_DG_BARRELSWITCH	0x000d0044
 #define HID_DG_ERASER		0x000d0045
 #define HID_DG_TABLETPICK	0x000d0046
+
+#define HID_CP_CONSUMERCONTROL	0x000c0001
+
 #define HID_DG_CONFIDENCE	0x000d0047
 #define HID_DG_WIDTH		0x000d0048
 #define HID_DG_HEIGHT		0x000d0049
-- 
cgit v1.2.3-70-g09d2


From a45c30ec59342c47604ea074bcf56a43a8cde8aa Mon Sep 17 00:00:00 2001
From: JD Cole <jd@jdc.me>
Date: Fri, 31 Oct 2014 17:44:42 -0700
Subject: HID: added missing HID Consumer Page identifiers

Adds CA and NAry usage type identifiers.

Signed-off-by: JD Cole <jd.cole@plantronics.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/hid.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'include')

diff --git a/include/linux/hid.h b/include/linux/hid.h
index a63f2aaed64..58a89ed86ac 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -236,6 +236,30 @@ struct hid_item {
 #define HID_DG_TABLETPICK	0x000d0046
 
 #define HID_CP_CONSUMERCONTROL	0x000c0001
+#define HID_CP_NUMERICKEYPAD	0x000c0002
+#define HID_CP_PROGRAMMABLEBUTTONS	0x000c0003
+#define HID_CP_MICROPHONE	0x000c0004
+#define HID_CP_HEADPHONE	0x000c0005
+#define HID_CP_GRAPHICEQUALIZER	0x000c0006
+#define HID_CP_FUNCTIONBUTTONS	0x000c0036
+#define HID_CP_SELECTION	0x000c0080
+#define HID_CP_MEDIASELECTION	0x000c0087
+#define HID_CP_SELECTDISC	0x000c00ba
+#define HID_CP_PLAYBACKSPEED	0x000c00f1
+#define HID_CP_PROXIMITY	0x000c0109
+#define HID_CP_SPEAKERSYSTEM	0x000c0160
+#define HID_CP_CHANNELLEFT	0x000c0161
+#define HID_CP_CHANNELRIGHT	0x000c0162
+#define HID_CP_CHANNELCENTER	0x000c0163
+#define HID_CP_CHANNELFRONT	0x000c0164
+#define HID_CP_CHANNELCENTERFRONT	0x000c0165
+#define HID_CP_CHANNELSIDE	0x000c0166
+#define HID_CP_CHANNELSURROUND	0x000c0167
+#define HID_CP_CHANNELLOWFREQUENCYENHANCEMENT	0x000c0168
+#define HID_CP_CHANNELTOP	0x000c0169
+#define HID_CP_CHANNELUNKNOWN	0x000c016a
+#define HID_CP_APPLICATIONLAUNCHBUTTONS	0x000c0180
+#define HID_CP_GENERICGUIAPPLICATIONCONTROLS	0x000c0200
 
 #define HID_DG_CONFIDENCE	0x000d0047
 #define HID_DG_WIDTH		0x000d0048
-- 
cgit v1.2.3-70-g09d2


From 77d381af73e905c48b992d5d8426376469bc9576 Mon Sep 17 00:00:00 2001
From: Martin Kaiser <martin@kaiser.cx>
Date: Tue, 28 Oct 2014 18:51:01 -0300
Subject: [media] lirc: use kfifo_initialized() on lirc_buffer's fifo

We can use kfifo_initialized() to check if the fifo in lirc_buffer is
initialized or not. There's no need to have a dedicated fifo status
variable in lirc_buffer.

[m.chehab@samsung.com: add the same change to lirc_zilog, to avoid
 breaking compilation of staging drivers]
Signed-off-by: Martin Kaiser <martin@kaiser.cx>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/staging/media/lirc/lirc_zilog.c | 2 +-
 include/media/lirc_dev.h                | 8 ++------
 2 files changed, 3 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/staging/media/lirc/lirc_zilog.c b/drivers/staging/media/lirc/lirc_zilog.c
index 567feba0011..1ccf6262ab3 100644
--- a/drivers/staging/media/lirc/lirc_zilog.c
+++ b/drivers/staging/media/lirc/lirc_zilog.c
@@ -199,7 +199,7 @@ static void release_ir_device(struct kref *ref)
 		lirc_unregister_driver(ir->l.minor);
 		ir->l.minor = MAX_IRCTL_DEVICES;
 	}
-	if (ir->rbuf.fifo_initialized)
+	if (kfifo_initialized(&ir->rbuf.fifo))
 		lirc_buffer_free(&ir->rbuf);
 	list_del(&ir->list);
 	kfree(ir);
diff --git a/include/media/lirc_dev.h b/include/media/lirc_dev.h
index 78f0637ca68..05e7ad5d2c8 100644
--- a/include/media/lirc_dev.h
+++ b/include/media/lirc_dev.h
@@ -29,14 +29,13 @@ struct lirc_buffer {
 	/* Using chunks instead of bytes pretends to simplify boundary checking
 	 * And should allow for some performance fine tunning later */
 	struct kfifo fifo;
-	u8 fifo_initialized;
 };
 
 static inline void lirc_buffer_clear(struct lirc_buffer *buf)
 {
 	unsigned long flags;
 
-	if (buf->fifo_initialized) {
+	if (kfifo_initialized(&buf->fifo)) {
 		spin_lock_irqsave(&buf->fifo_lock, flags);
 		kfifo_reset(&buf->fifo);
 		spin_unlock_irqrestore(&buf->fifo_lock, flags);
@@ -56,17 +55,14 @@ static inline int lirc_buffer_init(struct lirc_buffer *buf,
 	buf->chunk_size = chunk_size;
 	buf->size = size;
 	ret = kfifo_alloc(&buf->fifo, size * chunk_size, GFP_KERNEL);
-	if (ret == 0)
-		buf->fifo_initialized = 1;
 
 	return ret;
 }
 
 static inline void lirc_buffer_free(struct lirc_buffer *buf)
 {
-	if (buf->fifo_initialized) {
+	if (kfifo_initialized(&buf->fifo)) {
 		kfifo_free(&buf->fifo);
-		buf->fifo_initialized = 0;
 	} else
 		WARN(1, "calling %s on an uninitialized lirc_buffer\n",
 		     __func__);
-- 
cgit v1.2.3-70-g09d2


From 6c93b5342374b3ff2a8beac050ed6e07373cbe95 Mon Sep 17 00:00:00 2001
From: Felipe Balbi <balbi@ti.com>
Date: Thu, 18 Sep 2014 09:51:23 -0500
Subject: usb: gadget: composite: introduce setup and os_desc pending flags

These flags we be set to true whenever their
matching request is queued. They will be cleared
to false when that request completes.

Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 include/linux/usb/composite.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index c330f5ef42c..ed3811c09ec 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -427,6 +427,8 @@ static inline struct usb_composite_driver *to_cdriver(
  * @b_vendor_code: bMS_VendorCode part of the OS string
  * @use_os_string: false by default, interested gadgets set it
  * @os_desc_config: the configuration to be used with OS descriptors
+ * @setup_pending: true when setup request is queued but not completed
+ * @os_desc_pending: true when os_desc request is queued but not completed
  *
  * One of these devices is allocated and initialized before the
  * associated device driver's bind() is called.
@@ -488,6 +490,9 @@ struct usb_composite_dev {
 
 	/* protects deactivations and delayed_status counts*/
 	spinlock_t			lock;
+
+	unsigned			setup_pending:1;
+	unsigned			os_desc_pending:1;
 };
 
 extern int usb_string_id(struct usb_composite_dev *c);
-- 
cgit v1.2.3-70-g09d2


From 3a571870856f63064a3a45d7ffa2526d597b7fbe Mon Sep 17 00:00:00 2001
From: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Date: Wed, 8 Oct 2014 12:03:36 +0200
Subject: usb: gadget: configfs: add suspend/resume

USB gadgets composed with configfs lack suspend and resume
methods. This patch uses composite_suspend()/composite_resume()
the same way e.g. composite_setup() or composite_disconnect()
are used in a configfs-based gadget.

Signed-off-by: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/gadget/composite.c | 6 ++----
 drivers/usb/gadget/configfs.c  | 3 +++
 include/linux/usb/composite.h  | 2 ++
 3 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index e071d580346..61783534856 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -2064,8 +2064,7 @@ fail:
 
 /*-------------------------------------------------------------------------*/
 
-static void
-composite_suspend(struct usb_gadget *gadget)
+void composite_suspend(struct usb_gadget *gadget)
 {
 	struct usb_composite_dev	*cdev = get_gadget_data(gadget);
 	struct usb_function		*f;
@@ -2088,8 +2087,7 @@ composite_suspend(struct usb_gadget *gadget)
 	usb_gadget_vbus_draw(gadget, 2);
 }
 
-static void
-composite_resume(struct usb_gadget *gadget)
+void composite_resume(struct usb_gadget *gadget)
 {
 	struct usb_composite_dev	*cdev = get_gadget_data(gadget);
 	struct usb_function		*f;
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 34034333f7f..d25f9f3dfea 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -1453,6 +1453,9 @@ static const struct usb_gadget_driver configfs_driver_template = {
 	.reset          = composite_disconnect,
 	.disconnect     = composite_disconnect,
 
+	.suspend	= composite_suspend,
+	.resume		= composite_resume,
+
 	.max_speed	= USB_SPEED_SUPER,
 	.driver = {
 		.owner          = THIS_MODULE,
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index ed3811c09ec..3d87defcc52 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -506,6 +506,8 @@ extern int usb_string_ids_n(struct usb_composite_dev *c, unsigned n);
 extern void composite_disconnect(struct usb_gadget *gadget);
 extern int composite_setup(struct usb_gadget *gadget,
 		const struct usb_ctrlrequest *ctrl);
+extern void composite_suspend(struct usb_gadget *gadget);
+extern void composite_resume(struct usb_gadget *gadget);
 
 /*
  * Some systems will need runtime overrides for the  product identifiers
-- 
cgit v1.2.3-70-g09d2


From 22835b807e7ca946a4d1fbd4c7af56aa09cd273e Mon Sep 17 00:00:00 2001
From: Felipe Balbi <balbi@ti.com>
Date: Fri, 17 Oct 2014 12:05:12 -0500
Subject: usb: gadget: remove unnecessary 'driver' argument

now that no UDC driver relies on the extra
'driver' argument to ->udc_stop(), we can
safely remove it.

This commit is based on previous work by
Robert Baldyga <r.baldyga@samsung.com> which
can be found at [1]; however that patch turned
out to have a high probability of regressing
many UDC drivers because of a blind search & replace
s/driver/$udc->driver/ which caused the 'driver'
argument to stop_activity() to be a valid non-NULL
pointer when it should be NULL, thus causing UDCs
to mistakenly call gadget driver's ->disconnect()
callback.

[1] http://markmail.org/message/x5zneg4xea4zntab

Acked-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/chipidea/udc.c              | 6 ++----
 drivers/usb/dwc2/gadget.c               | 3 +--
 drivers/usb/dwc3/gadget.c               | 3 +--
 drivers/usb/gadget/udc/amd5536udc.c     | 8 +++-----
 drivers/usb/gadget/udc/at91_udc.c       | 7 +++----
 drivers/usb/gadget/udc/atmel_usba_udc.c | 7 +++----
 drivers/usb/gadget/udc/bcm63xx_udc.c    | 3 +--
 drivers/usb/gadget/udc/dummy_hcd.c      | 6 ++----
 drivers/usb/gadget/udc/fotg210-udc.c    | 3 +--
 drivers/usb/gadget/udc/fsl_qe_udc.c     | 6 ++----
 drivers/usb/gadget/udc/fsl_udc_core.c   | 8 +++-----
 drivers/usb/gadget/udc/fusb300_udc.c    | 3 +--
 drivers/usb/gadget/udc/goku_udc.c       | 6 ++----
 drivers/usb/gadget/udc/gr_udc.c         | 3 +--
 drivers/usb/gadget/udc/lpc32xx_udc.c    | 5 ++---
 drivers/usb/gadget/udc/m66592-udc.c     | 3 +--
 drivers/usb/gadget/udc/mv_u3d_core.c    | 3 +--
 drivers/usb/gadget/udc/mv_udc_core.c    | 5 ++---
 drivers/usb/gadget/udc/net2272.c        | 6 ++----
 drivers/usb/gadget/udc/net2280.c        | 6 ++----
 drivers/usb/gadget/udc/omap_udc.c       | 6 ++----
 drivers/usb/gadget/udc/pch_udc.c        | 7 +++----
 drivers/usb/gadget/udc/pxa25x_udc.c     | 6 ++----
 drivers/usb/gadget/udc/pxa27x_udc.c     | 6 ++----
 drivers/usb/gadget/udc/r8a66597-udc.c   | 3 +--
 drivers/usb/gadget/udc/s3c-hsudc.c      | 3 +--
 drivers/usb/gadget/udc/s3c2410_udc.c    | 6 ++----
 drivers/usb/gadget/udc/udc-core.c       | 2 +-
 drivers/usb/gadget/udc/udc-xilinx.c     | 3 +--
 drivers/usb/musb/musb_gadget.c          | 6 ++----
 drivers/usb/renesas_usbhs/mod_gadget.c  | 3 +--
 include/linux/usb/gadget.h              | 3 +--
 32 files changed, 55 insertions(+), 99 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 0444d3f8971..f4397b29891 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -1544,8 +1544,7 @@ static int ci_udc_pullup(struct usb_gadget *_gadget, int is_on)
 
 static int ci_udc_start(struct usb_gadget *gadget,
 			 struct usb_gadget_driver *driver);
-static int ci_udc_stop(struct usb_gadget *gadget,
-			struct usb_gadget_driver *driver);
+static int ci_udc_stop(struct usb_gadget *gadget);
 /**
  * Device operations part of the API to the USB controller hardware,
  * which don't involve endpoints (or i/o)
@@ -1682,8 +1681,7 @@ static int ci_udc_start(struct usb_gadget *gadget,
 /**
  * ci_udc_stop: unregister a gadget driver
  */
-static int ci_udc_stop(struct usb_gadget *gadget,
-			struct usb_gadget_driver *driver)
+static int ci_udc_stop(struct usb_gadget *gadget)
 {
 	struct ci_hdrc *ci = container_of(gadget, struct ci_hdrc, gadget);
 	unsigned long flags;
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index eee87098bb8..441f1c4b8eb 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -2921,8 +2921,7 @@ err:
  *
  * Stop udc hw block and stay tunned for future transmissions
  */
-static int s3c_hsotg_udc_stop(struct usb_gadget *gadget,
-			  struct usb_gadget_driver *driver)
+static int s3c_hsotg_udc_stop(struct usb_gadget *gadget)
 {
 	struct s3c_hsotg *hsotg = to_hsotg(gadget);
 	unsigned long flags = 0;
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 20e4ee922c4..20dda60b27c 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1630,8 +1630,7 @@ err0:
 	return ret;
 }
 
-static int dwc3_gadget_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int dwc3_gadget_stop(struct usb_gadget *g)
 {
 	struct dwc3		*dwc = gadget_to_dwc(g);
 	unsigned long		flags;
diff --git a/drivers/usb/gadget/udc/amd5536udc.c b/drivers/usb/gadget/udc/amd5536udc.c
index 7d0e0b8a960..606b9009861 100644
--- a/drivers/usb/gadget/udc/amd5536udc.c
+++ b/drivers/usb/gadget/udc/amd5536udc.c
@@ -1401,9 +1401,8 @@ static int udc_wakeup(struct usb_gadget *gadget)
 
 static int amd5536_udc_start(struct usb_gadget *g,
 		struct usb_gadget_driver *driver);
-static int amd5536_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver);
-/* gadget operations */
+static int amd5536_udc_stop(struct usb_gadget *g);
+
 static const struct usb_gadget_ops udc_ops = {
 	.wakeup		= udc_wakeup,
 	.get_frame	= udc_get_frame,
@@ -1962,8 +1961,7 @@ __acquires(dev->lock)
 }
 
 /* Called by gadget driver to unregister itself */
-static int amd5536_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int amd5536_udc_stop(struct usb_gadget *g)
 {
 	struct udc *dev = to_amd5536_udc(g);
 	unsigned long flags;
diff --git a/drivers/usb/gadget/udc/at91_udc.c b/drivers/usb/gadget/udc/at91_udc.c
index 5c4cede5365..f47f16c25f1 100644
--- a/drivers/usb/gadget/udc/at91_udc.c
+++ b/drivers/usb/gadget/udc/at91_udc.c
@@ -984,8 +984,8 @@ static int at91_set_selfpowered(struct usb_gadget *gadget, int is_on)
 
 static int at91_start(struct usb_gadget *gadget,
 		struct usb_gadget_driver *driver);
-static int at91_stop(struct usb_gadget *gadget,
-		struct usb_gadget_driver *driver);
+static int at91_stop(struct usb_gadget *gadget);
+
 static const struct usb_gadget_ops at91_udc_ops = {
 	.get_frame		= at91_get_frame,
 	.wakeup			= at91_wakeup,
@@ -1644,8 +1644,7 @@ static int at91_start(struct usb_gadget *gadget,
 	return 0;
 }
 
-static int at91_stop(struct usb_gadget *gadget,
-		struct usb_gadget_driver *driver)
+static int at91_stop(struct usb_gadget *gadget)
 {
 	struct at91_udc *udc;
 	unsigned long	flags;
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index eaee5f90e9f..c537a6604b4 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -987,8 +987,8 @@ usba_udc_set_selfpowered(struct usb_gadget *gadget, int is_selfpowered)
 
 static int atmel_usba_start(struct usb_gadget *gadget,
 		struct usb_gadget_driver *driver);
-static int atmel_usba_stop(struct usb_gadget *gadget,
-		struct usb_gadget_driver *driver);
+static int atmel_usba_stop(struct usb_gadget *gadget);
+
 static const struct usb_gadget_ops usba_udc_ops = {
 	.get_frame		= usba_udc_get_frame,
 	.wakeup			= usba_udc_wakeup,
@@ -1807,8 +1807,7 @@ static int atmel_usba_start(struct usb_gadget *gadget,
 	return 0;
 }
 
-static int atmel_usba_stop(struct usb_gadget *gadget,
-		struct usb_gadget_driver *driver)
+static int atmel_usba_stop(struct usb_gadget *gadget)
 {
 	struct usba_udc *udc = container_of(gadget, struct usba_udc, gadget);
 	unsigned long flags;
diff --git a/drivers/usb/gadget/udc/bcm63xx_udc.c b/drivers/usb/gadget/udc/bcm63xx_udc.c
index 485c8c2bddc..9319ff27c73 100644
--- a/drivers/usb/gadget/udc/bcm63xx_udc.c
+++ b/drivers/usb/gadget/udc/bcm63xx_udc.c
@@ -1836,8 +1836,7 @@ static int bcm63xx_udc_start(struct usb_gadget *gadget,
  * @gadget: USB slave device.
  * @driver: Driver for USB slave devices.
  */
-static int bcm63xx_udc_stop(struct usb_gadget *gadget,
-		struct usb_gadget_driver *driver)
+static int bcm63xx_udc_stop(struct usb_gadget *gadget)
 {
 	struct bcm63xx_udc *udc = gadget_to_udc(gadget);
 	unsigned long flags;
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index 5c72ade61aa..5bffb75922f 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -851,8 +851,7 @@ static int dummy_pullup(struct usb_gadget *_gadget, int value)
 
 static int dummy_udc_start(struct usb_gadget *g,
 		struct usb_gadget_driver *driver);
-static int dummy_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver);
+static int dummy_udc_stop(struct usb_gadget *g);
 
 static const struct usb_gadget_ops dummy_ops = {
 	.get_frame	= dummy_g_get_frame,
@@ -913,8 +912,7 @@ static int dummy_udc_start(struct usb_gadget *g,
 	return 0;
 }
 
-static int dummy_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int dummy_udc_stop(struct usb_gadget *g)
 {
 	struct dummy_hcd	*dum_hcd = gadget_to_dummy_hcd(g);
 	struct dummy		*dum = dum_hcd->dum;
diff --git a/drivers/usb/gadget/udc/fotg210-udc.c b/drivers/usb/gadget/udc/fotg210-udc.c
index 1d315921bf3..1ca52e11eb9 100644
--- a/drivers/usb/gadget/udc/fotg210-udc.c
+++ b/drivers/usb/gadget/udc/fotg210-udc.c
@@ -1053,8 +1053,7 @@ static void fotg210_init(struct fotg210_udc *fotg210)
 	iowrite32(value, fotg210->reg + FOTG210_DMISGR0);
 }
 
-static int fotg210_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int fotg210_udc_stop(struct usb_gadget *g)
 {
 	struct fotg210_udc *fotg210 = gadget_to_fotg210(g);
 	unsigned long	flags;
diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c
index 6ca61e6b72e..01f29ef622b 100644
--- a/drivers/usb/gadget/udc/fsl_qe_udc.c
+++ b/drivers/usb/gadget/udc/fsl_qe_udc.c
@@ -1887,8 +1887,7 @@ static int qe_get_frame(struct usb_gadget *gadget)
 
 static int fsl_qe_start(struct usb_gadget *gadget,
 		struct usb_gadget_driver *driver);
-static int fsl_qe_stop(struct usb_gadget *gadget,
-		struct usb_gadget_driver *driver);
+static int fsl_qe_stop(struct usb_gadget *gadget);
 
 /* defined in usb_gadget.h */
 static const struct usb_gadget_ops qe_gadget_ops = {
@@ -2308,8 +2307,7 @@ static int fsl_qe_start(struct usb_gadget *gadget,
 	return 0;
 }
 
-static int fsl_qe_stop(struct usb_gadget *gadget,
-		struct usb_gadget_driver *driver)
+static int fsl_qe_stop(struct usb_gadget *gadget)
 {
 	struct qe_udc *udc;
 	struct qe_ep *loop_ep;
diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c
index c3620791a31..b184ed3ef37 100644
--- a/drivers/usb/gadget/udc/fsl_udc_core.c
+++ b/drivers/usb/gadget/udc/fsl_udc_core.c
@@ -1236,9 +1236,8 @@ static int fsl_pullup(struct usb_gadget *gadget, int is_on)
 
 static int fsl_udc_start(struct usb_gadget *g,
 		struct usb_gadget_driver *driver);
-static int fsl_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver);
-/* defined in gadget.h */
+static int fsl_udc_stop(struct usb_gadget *g);
+
 static const struct usb_gadget_ops fsl_gadget_ops = {
 	.get_frame = fsl_get_frame,
 	.wakeup = fsl_wakeup,
@@ -1975,8 +1974,7 @@ static int fsl_udc_start(struct usb_gadget *g,
 }
 
 /* Disconnect from gadget driver */
-static int fsl_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int fsl_udc_stop(struct usb_gadget *g)
 {
 	struct fsl_ep *loop_ep;
 	unsigned long flags;
diff --git a/drivers/usb/gadget/udc/fusb300_udc.c b/drivers/usb/gadget/udc/fusb300_udc.c
index 8286df72add..a1b33f534b5 100644
--- a/drivers/usb/gadget/udc/fusb300_udc.c
+++ b/drivers/usb/gadget/udc/fusb300_udc.c
@@ -1320,8 +1320,7 @@ static int fusb300_udc_start(struct usb_gadget *g,
 	return 0;
 }
 
-static int fusb300_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int fusb300_udc_stop(struct usb_gadget *g)
 {
 	struct fusb300 *fusb300 = to_fusb300(g);
 
diff --git a/drivers/usb/gadget/udc/goku_udc.c b/drivers/usb/gadget/udc/goku_udc.c
index bf9c5ef8b56..5b9176e7202 100644
--- a/drivers/usb/gadget/udc/goku_udc.c
+++ b/drivers/usb/gadget/udc/goku_udc.c
@@ -992,8 +992,7 @@ static int goku_get_frame(struct usb_gadget *_gadget)
 
 static int goku_udc_start(struct usb_gadget *g,
 		struct usb_gadget_driver *driver);
-static int goku_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver);
+static int goku_udc_stop(struct usb_gadget *g);
 
 static const struct usb_gadget_ops goku_ops = {
 	.get_frame	= goku_get_frame,
@@ -1364,8 +1363,7 @@ static void stop_activity(struct goku_udc *dev)
 		udc_enable(dev);
 }
 
-static int goku_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int goku_udc_stop(struct usb_gadget *g)
 {
 	struct goku_udc	*dev = to_goku_udc(g);
 	unsigned long	flags;
diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c
index bde989f566c..320df9a250f 100644
--- a/drivers/usb/gadget/udc/gr_udc.c
+++ b/drivers/usb/gadget/udc/gr_udc.c
@@ -1935,8 +1935,7 @@ static int gr_udc_start(struct usb_gadget *gadget,
 	return 0;
 }
 
-static int gr_udc_stop(struct usb_gadget *gadget,
-		       struct usb_gadget_driver *driver)
+static int gr_udc_stop(struct usb_gadget *gadget)
 {
 	struct gr_udc *dev = to_gr_udc(gadget);
 	unsigned long flags;
diff --git a/drivers/usb/gadget/udc/lpc32xx_udc.c b/drivers/usb/gadget/udc/lpc32xx_udc.c
index cef64b98b6e..4be497d39d9 100644
--- a/drivers/usb/gadget/udc/lpc32xx_udc.c
+++ b/drivers/usb/gadget/udc/lpc32xx_udc.c
@@ -2559,7 +2559,7 @@ static int lpc32xx_pullup(struct usb_gadget *gadget, int is_on)
 }
 
 static int lpc32xx_start(struct usb_gadget *, struct usb_gadget_driver *);
-static int lpc32xx_stop(struct usb_gadget *, struct usb_gadget_driver *);
+static int lpc32xx_stop(struct usb_gadget *);
 
 static const struct usb_gadget_ops lpc32xx_udc_ops = {
 	.get_frame		= lpc32xx_get_frame,
@@ -2961,8 +2961,7 @@ static int lpc32xx_start(struct usb_gadget *gadget,
 	return 0;
 }
 
-static int lpc32xx_stop(struct usb_gadget *gadget,
-			struct usb_gadget_driver *driver)
+static int lpc32xx_stop(struct usb_gadget *gadget)
 {
 	int i;
 	struct lpc32xx_udc *udc = to_udc(gadget);
diff --git a/drivers/usb/gadget/udc/m66592-udc.c b/drivers/usb/gadget/udc/m66592-udc.c
index 898565687a8..311ec5f1cbf 100644
--- a/drivers/usb/gadget/udc/m66592-udc.c
+++ b/drivers/usb/gadget/udc/m66592-udc.c
@@ -1485,8 +1485,7 @@ static int m66592_udc_start(struct usb_gadget *g,
 	return 0;
 }
 
-static int m66592_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int m66592_udc_stop(struct usb_gadget *g)
 {
 	struct m66592 *m66592 = to_m66592(g);
 
diff --git a/drivers/usb/gadget/udc/mv_u3d_core.c b/drivers/usb/gadget/udc/mv_u3d_core.c
index e3ef744c4ff..ea422ac7999 100644
--- a/drivers/usb/gadget/udc/mv_u3d_core.c
+++ b/drivers/usb/gadget/udc/mv_u3d_core.c
@@ -1266,8 +1266,7 @@ static int mv_u3d_start(struct usb_gadget *g,
 	return 0;
 }
 
-static int mv_u3d_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int mv_u3d_stop(struct usb_gadget *g)
 {
 	struct mv_u3d *u3d = container_of(g, struct mv_u3d, gadget);
 	struct mv_usb_platform_data *pdata = dev_get_platdata(u3d->dev);
diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c
index 32d24ff2c4c..f104ac090a9 100644
--- a/drivers/usb/gadget/udc/mv_udc_core.c
+++ b/drivers/usb/gadget/udc/mv_udc_core.c
@@ -1223,7 +1223,7 @@ static int mv_udc_pullup(struct usb_gadget *gadget, int is_on)
 }
 
 static int mv_udc_start(struct usb_gadget *, struct usb_gadget_driver *);
-static int mv_udc_stop(struct usb_gadget *, struct usb_gadget_driver *);
+static int mv_udc_stop(struct usb_gadget *);
 /* device controller usb_gadget_ops structure */
 static const struct usb_gadget_ops mv_ops = {
 
@@ -1371,8 +1371,7 @@ static int mv_udc_start(struct usb_gadget *gadget,
 	return 0;
 }
 
-static int mv_udc_stop(struct usb_gadget *gadget,
-		struct usb_gadget_driver *driver)
+static int mv_udc_stop(struct usb_gadget *gadget)
 {
 	struct mv_udc *udc;
 	unsigned long flags;
diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c
index 4641df5a817..887bea42e5a 100644
--- a/drivers/usb/gadget/udc/net2272.c
+++ b/drivers/usb/gadget/udc/net2272.c
@@ -1169,8 +1169,7 @@ net2272_pullup(struct usb_gadget *_gadget, int is_on)
 
 static int net2272_start(struct usb_gadget *_gadget,
 		struct usb_gadget_driver *driver);
-static int net2272_stop(struct usb_gadget *_gadget,
-		struct usb_gadget_driver *driver);
+static int net2272_stop(struct usb_gadget *_gadget);
 
 static const struct usb_gadget_ops net2272_ops = {
 	.get_frame	= net2272_get_frame,
@@ -1500,8 +1499,7 @@ stop_activity(struct net2272 *dev, struct usb_gadget_driver *driver)
 	net2272_usb_reinit(dev);
 }
 
-static int net2272_stop(struct usb_gadget *_gadget,
-		struct usb_gadget_driver *driver)
+static int net2272_stop(struct usb_gadget *_gadget)
 {
 	struct net2272 *dev;
 	unsigned long flags;
diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c
index a30df8efa2d..bd03a1b4192 100644
--- a/drivers/usb/gadget/udc/net2280.c
+++ b/drivers/usb/gadget/udc/net2280.c
@@ -1548,8 +1548,7 @@ static int net2280_pullup(struct usb_gadget *_gadget, int is_on)
 
 static int net2280_start(struct usb_gadget *_gadget,
 		struct usb_gadget_driver *driver);
-static int net2280_stop(struct usb_gadget *_gadget,
-		struct usb_gadget_driver *driver);
+static int net2280_stop(struct usb_gadget *_gadget);
 
 static const struct usb_gadget_ops net2280_ops = {
 	.get_frame	= net2280_get_frame,
@@ -2432,8 +2431,7 @@ static void stop_activity(struct net2280 *dev, struct usb_gadget_driver *driver)
 	usb_reinit(dev);
 }
 
-static int net2280_stop(struct usb_gadget *_gadget,
-		struct usb_gadget_driver *driver)
+static int net2280_stop(struct usb_gadget *_gadget)
 {
 	struct net2280	*dev;
 	unsigned long	flags;
diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c
index dcdfea46003..534b85c07fe 100644
--- a/drivers/usb/gadget/udc/omap_udc.c
+++ b/drivers/usb/gadget/udc/omap_udc.c
@@ -1311,8 +1311,7 @@ static int omap_pullup(struct usb_gadget *gadget, int is_on)
 
 static int omap_udc_start(struct usb_gadget *g,
 		struct usb_gadget_driver *driver);
-static int omap_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver);
+static int omap_udc_stop(struct usb_gadget *g);
 
 static const struct usb_gadget_ops omap_gadget_ops = {
 	.get_frame		= omap_get_frame,
@@ -2102,8 +2101,7 @@ done:
 	return status;
 }
 
-static int omap_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int omap_udc_stop(struct usb_gadget *g)
 {
 	unsigned long	flags;
 	int		status = -ENODEV;
diff --git a/drivers/usb/gadget/udc/pch_udc.c b/drivers/usb/gadget/udc/pch_udc.c
index ccbe3d4a2a5..6534f36866d 100644
--- a/drivers/usb/gadget/udc/pch_udc.c
+++ b/drivers/usb/gadget/udc/pch_udc.c
@@ -1240,8 +1240,8 @@ static int pch_udc_pcd_vbus_draw(struct usb_gadget *gadget, unsigned int mA)
 
 static int pch_udc_start(struct usb_gadget *g,
 		struct usb_gadget_driver *driver);
-static int pch_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver);
+static int pch_udc_stop(struct usb_gadget *g);
+
 static const struct usb_gadget_ops pch_udc_ops = {
 	.get_frame = pch_udc_pcd_get_frame,
 	.wakeup = pch_udc_pcd_wakeup,
@@ -3008,8 +3008,7 @@ static int pch_udc_start(struct usb_gadget *g,
 	return 0;
 }
 
-static int pch_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int pch_udc_stop(struct usb_gadget *g)
 {
 	struct pch_udc_dev	*dev = to_pch_udc(g);
 
diff --git a/drivers/usb/gadget/udc/pxa25x_udc.c b/drivers/usb/gadget/udc/pxa25x_udc.c
index 098fa57c3b8..2944092cd92 100644
--- a/drivers/usb/gadget/udc/pxa25x_udc.c
+++ b/drivers/usb/gadget/udc/pxa25x_udc.c
@@ -998,8 +998,7 @@ static int pxa25x_udc_vbus_draw(struct usb_gadget *_gadget, unsigned mA)
 
 static int pxa25x_udc_start(struct usb_gadget *g,
 		struct usb_gadget_driver *driver);
-static int pxa25x_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver);
+static int pxa25x_udc_stop(struct usb_gadget *g);
 
 static const struct usb_gadget_ops pxa25x_udc_ops = {
 	.get_frame	= pxa25x_udc_get_frame,
@@ -1311,8 +1310,7 @@ stop_activity(struct pxa25x_udc *dev, struct usb_gadget_driver *driver)
 	udc_reinit(dev);
 }
 
-static int pxa25x_udc_stop(struct usb_gadget*g,
-		struct usb_gadget_driver *driver)
+static int pxa25x_udc_stop(struct usb_gadget*g)
 {
 	struct pxa25x_udc	*dev = to_pxa25x(g);
 
diff --git a/drivers/usb/gadget/udc/pxa27x_udc.c b/drivers/usb/gadget/udc/pxa27x_udc.c
index b90b1f30899..17a0193b5e0 100644
--- a/drivers/usb/gadget/udc/pxa27x_udc.c
+++ b/drivers/usb/gadget/udc/pxa27x_udc.c
@@ -1669,8 +1669,7 @@ static int pxa_udc_vbus_draw(struct usb_gadget *_gadget, unsigned mA)
 
 static int pxa27x_udc_start(struct usb_gadget *g,
 		struct usb_gadget_driver *driver);
-static int pxa27x_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver);
+static int pxa27x_udc_stop(struct usb_gadget *g);
 
 static const struct usb_gadget_ops pxa_udc_ops = {
 	.get_frame	= pxa_udc_get_frame,
@@ -1857,8 +1856,7 @@ static void stop_activity(struct pxa_udc *udc, struct usb_gadget_driver *driver)
  *
  * Returns 0 if no error, -ENODEV, -EINVAL otherwise
  */
-static int pxa27x_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int pxa27x_udc_stop(struct usb_gadget *g)
 {
 	struct pxa_udc *udc = to_pxa(g);
 
diff --git a/drivers/usb/gadget/udc/r8a66597-udc.c b/drivers/usb/gadget/udc/r8a66597-udc.c
index f8186613b53..b63a527baf1 100644
--- a/drivers/usb/gadget/udc/r8a66597-udc.c
+++ b/drivers/usb/gadget/udc/r8a66597-udc.c
@@ -1763,8 +1763,7 @@ static int r8a66597_start(struct usb_gadget *gadget,
 	return 0;
 }
 
-static int r8a66597_stop(struct usb_gadget *gadget,
-		struct usb_gadget_driver *driver)
+static int r8a66597_stop(struct usb_gadget *gadget)
 {
 	struct r8a66597 *r8a66597 = gadget_to_r8a66597(gadget);
 	unsigned long flags;
diff --git a/drivers/usb/gadget/udc/s3c-hsudc.c b/drivers/usb/gadget/udc/s3c-hsudc.c
index de95e9dd957..97d3a914438 100644
--- a/drivers/usb/gadget/udc/s3c-hsudc.c
+++ b/drivers/usb/gadget/udc/s3c-hsudc.c
@@ -1188,8 +1188,7 @@ err_supplies:
 	return ret;
 }
 
-static int s3c_hsudc_stop(struct usb_gadget *gadget,
-		struct usb_gadget_driver *driver)
+static int s3c_hsudc_stop(struct usb_gadget *gadget)
 {
 	struct s3c_hsudc *hsudc = to_hsudc(gadget);
 	unsigned long flags;
diff --git a/drivers/usb/gadget/udc/s3c2410_udc.c b/drivers/usb/gadget/udc/s3c2410_udc.c
index ff423d15bef..2a8e36d3148 100644
--- a/drivers/usb/gadget/udc/s3c2410_udc.c
+++ b/drivers/usb/gadget/udc/s3c2410_udc.c
@@ -1541,8 +1541,7 @@ static int s3c2410_vbus_draw(struct usb_gadget *_gadget, unsigned ma)
 
 static int s3c2410_udc_start(struct usb_gadget *g,
 		struct usb_gadget_driver *driver);
-static int s3c2410_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver);
+static int s3c2410_udc_stop(struct usb_gadget *g);
 
 static const struct usb_gadget_ops s3c2410_ops = {
 	.get_frame		= s3c2410_udc_get_frame,
@@ -1683,8 +1682,7 @@ static int s3c2410_udc_start(struct usb_gadget *g,
 	return 0;
 }
 
-static int s3c2410_udc_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int s3c2410_udc_stop(struct usb_gadget *g)
 {
 	struct s3c2410_udc *udc = to_s3c2410(g);
 
diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c
index 52f457bb0bb..135504b6042 100644
--- a/drivers/usb/gadget/udc/udc-core.c
+++ b/drivers/usb/gadget/udc/udc-core.c
@@ -204,7 +204,7 @@ static inline int usb_gadget_udc_start(struct usb_udc *udc)
  */
 static inline void usb_gadget_udc_stop(struct usb_udc *udc)
 {
-	udc->gadget->ops->udc_stop(udc->gadget, udc->driver);
+	udc->gadget->ops->udc_stop(udc->gadget);
 }
 
 /**
diff --git a/drivers/usb/gadget/udc/udc-xilinx.c b/drivers/usb/gadget/udc/udc-xilinx.c
index ed27e1687a4..1eac56fc384 100644
--- a/drivers/usb/gadget/udc/udc-xilinx.c
+++ b/drivers/usb/gadget/udc/udc-xilinx.c
@@ -1403,8 +1403,7 @@ err:
  *
  * Return: zero always
  */
-static int xudc_stop(struct usb_gadget *gadget,
-		     struct usb_gadget_driver *driver)
+static int xudc_stop(struct usb_gadget *gadget)
 {
 	struct xusb_udc *udc = to_udc(gadget);
 	unsigned long flags;
diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c
index 88d63e0c79f..4ab1896957e 100644
--- a/drivers/usb/musb/musb_gadget.c
+++ b/drivers/usb/musb/musb_gadget.c
@@ -1684,8 +1684,7 @@ static int musb_gadget_pullup(struct usb_gadget *gadget, int is_on)
 
 static int musb_gadget_start(struct usb_gadget *g,
 		struct usb_gadget_driver *driver);
-static int musb_gadget_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver);
+static int musb_gadget_stop(struct usb_gadget *g);
 
 static const struct usb_gadget_ops musb_gadget_operations = {
 	.get_frame		= musb_gadget_get_frame,
@@ -1923,8 +1922,7 @@ static void stop_activity(struct musb *musb, struct usb_gadget_driver *driver)
  *
  * @param driver the gadget driver to unregister
  */
-static int musb_gadget_stop(struct usb_gadget *g,
-		struct usb_gadget_driver *driver)
+static int musb_gadget_stop(struct usb_gadget *g)
 {
 	struct musb	*musb = gadget_to_musb(g);
 	unsigned long	flags;
diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c
index 2d17c10a042..7a452103050 100644
--- a/drivers/usb/renesas_usbhs/mod_gadget.c
+++ b/drivers/usb/renesas_usbhs/mod_gadget.c
@@ -851,8 +851,7 @@ static int usbhsg_gadget_start(struct usb_gadget *gadget,
 	return usbhsg_try_start(priv, USBHSG_STATUS_REGISTERD);
 }
 
-static int usbhsg_gadget_stop(struct usb_gadget *gadget,
-		struct usb_gadget_driver *driver)
+static int usbhsg_gadget_stop(struct usb_gadget *gadget)
 {
 	struct usbhsg_gpriv *gpriv = usbhsg_gadget_to_gpriv(gadget);
 	struct usbhs_priv *priv = usbhsg_gpriv_to_priv(gpriv);
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 522cafe2679..70965fc829d 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -490,8 +490,7 @@ struct usb_gadget_ops {
 	void	(*get_config_params)(struct usb_dcd_config_params *);
 	int	(*udc_start)(struct usb_gadget *,
 			struct usb_gadget_driver *);
-	int	(*udc_stop)(struct usb_gadget *,
-			struct usb_gadget_driver *);
+	int	(*udc_stop)(struct usb_gadget *);
 };
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 02e8c966274f1049cca8d3f17092f8275979b8eb Mon Sep 17 00:00:00 2001
From: Felipe Balbi <balbi@ti.com>
Date: Fri, 17 Oct 2014 18:57:06 -0500
Subject: usb: gadget: udc: core: prepend udc_attach_driver with usb_

No functional changes, just adding a prefix
which should have been there from the start.

Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/gadget/configfs.c     | 2 +-
 drivers/usb/gadget/udc/udc-core.c | 4 ++--
 include/linux/usb/gadget.h        | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index d25f9f3dfea..75648145dc1 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -271,7 +271,7 @@ static ssize_t gadget_dev_desc_UDC_store(struct gadget_info *gi,
 			ret = -EBUSY;
 			goto err;
 		}
-		ret = udc_attach_driver(name, &gi->composite.gadget_driver);
+		ret = usb_udc_attach_driver(name, &gi->composite.gadget_driver);
 		if (ret)
 			goto err;
 		gi->udc_name = name;
diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c
index 135504b6042..e31d574d886 100644
--- a/drivers/usb/gadget/udc/udc-core.c
+++ b/drivers/usb/gadget/udc/udc-core.c
@@ -411,7 +411,7 @@ err1:
 	return ret;
 }
 
-int udc_attach_driver(const char *name, struct usb_gadget_driver *driver)
+int usb_udc_attach_driver(const char *name, struct usb_gadget_driver *driver)
 {
 	struct usb_udc *udc = NULL;
 	int ret = -ENODEV;
@@ -435,7 +435,7 @@ out:
 	mutex_unlock(&udc_lock);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(udc_attach_driver);
+EXPORT_SYMBOL_GPL(usb_udc_attach_driver);
 
 int usb_gadget_probe_driver(struct usb_gadget_driver *driver)
 {
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 70965fc829d..70ddb3943b6 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -924,7 +924,7 @@ extern int usb_add_gadget_udc_release(struct device *parent,
 		struct usb_gadget *gadget, void (*release)(struct device *dev));
 extern int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget);
 extern void usb_del_gadget_udc(struct usb_gadget *gadget);
-extern int udc_attach_driver(const char *name,
+extern int usb_udc_attach_driver(const char *name,
 		struct usb_gadget_driver *driver);
 
 /*-------------------------------------------------------------------------*/
-- 
cgit v1.2.3-70-g09d2


From e47d92545c2972bcf3711e7db80f481e402163c7 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@free-electrons.com>
Date: Thu, 30 Oct 2014 18:41:13 +0100
Subject: usb: move the OTG state from the USB PHY to the OTG structure

Before using the PHY framework instead of the USB PHY one, we need to
move the OTG state into another place, since it won't be available when
USB PHY isn't used. This patch moves the OTG state into the OTG
structure, and makes all the needed modifications in the drivers
using the OTG state.

[ balbi@ti.com : fix build regressions with phy-tahvo.c, musb_dsps.c,
		phy-isp1301-omap, and chipidea's debug.c ]

Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
Acked-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/phy/phy-omap-usb2.c         |  8 +---
 drivers/usb/chipidea/debug.c        |  2 +-
 drivers/usb/chipidea/otg_fsm.c      | 12 ++---
 drivers/usb/common/usb-otg-fsm.c    |  8 ++--
 drivers/usb/host/ohci-omap.c        |  2 +-
 drivers/usb/musb/am35x.c            | 28 +++++------
 drivers/usb/musb/blackfin.c         | 18 +++----
 drivers/usb/musb/da8xx.c            | 28 +++++------
 drivers/usb/musb/davinci.c          | 18 +++----
 drivers/usb/musb/musb_core.c        | 94 ++++++++++++++++++-------------------
 drivers/usb/musb/musb_dsps.c        | 28 +++++------
 drivers/usb/musb/musb_gadget.c      | 36 +++++++-------
 drivers/usb/musb/musb_host.c        |  8 ++--
 drivers/usb/musb/musb_virthub.c     | 22 ++++-----
 drivers/usb/musb/omap2430.c         | 30 ++++++------
 drivers/usb/musb/tusb6010.c         | 40 ++++++++--------
 drivers/usb/musb/ux500.c            | 10 ++--
 drivers/usb/phy/phy-ab8500-usb.c    | 10 ++--
 drivers/usb/phy/phy-fsl-usb.c       | 10 ++--
 drivers/usb/phy/phy-generic.c       |  4 +-
 drivers/usb/phy/phy-gpio-vbus-usb.c | 10 ++--
 drivers/usb/phy/phy-isp1301-omap.c  | 94 ++++++++++++++++++-------------------
 drivers/usb/phy/phy-msm-usb.c       | 34 +++++++-------
 drivers/usb/phy/phy-mv-usb.c        | 46 +++++++++---------
 drivers/usb/phy/phy-tahvo.c         | 24 +++++-----
 include/linux/usb/otg.h             |  2 +
 include/linux/usb/phy.h             |  1 -
 27 files changed, 312 insertions(+), 315 deletions(-)

(limited to 'include')

diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c
index 8c842980834..9f4093590f4 100644
--- a/drivers/phy/phy-omap-usb2.c
+++ b/drivers/phy/phy-omap-usb2.c
@@ -80,11 +80,9 @@ static int omap_usb_start_srp(struct usb_otg *otg)
 
 static int omap_usb_set_host(struct usb_otg *otg, struct usb_bus *host)
 {
-	struct usb_phy	*phy = otg->phy;
-
 	otg->host = host;
 	if (!host)
-		phy->state = OTG_STATE_UNDEFINED;
+		otg->state = OTG_STATE_UNDEFINED;
 
 	return 0;
 }
@@ -92,11 +90,9 @@ static int omap_usb_set_host(struct usb_otg *otg, struct usb_bus *host)
 static int omap_usb_set_peripheral(struct usb_otg *otg,
 		struct usb_gadget *gadget)
 {
-	struct usb_phy	*phy = otg->phy;
-
 	otg->gadget = gadget;
 	if (!gadget)
-		phy->state = OTG_STATE_UNDEFINED;
+		otg->state = OTG_STATE_UNDEFINED;
 
 	return 0;
 }
diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c
index 795d6538d63..f038804d13d 100644
--- a/drivers/usb/chipidea/debug.c
+++ b/drivers/usb/chipidea/debug.c
@@ -220,7 +220,7 @@ static int ci_otg_show(struct seq_file *s, void *unused)
 
 	/* ------ State ----- */
 	seq_printf(s, "OTG state: %s\n\n",
-		usb_otg_state_string(ci->transceiver->state));
+		usb_otg_state_string(ci->transceiver->otg->state));
 
 	/* ------ State Machine Variables ----- */
 	seq_printf(s, "a_bus_drop: %d\n", fsm->a_bus_drop);
diff --git a/drivers/usb/chipidea/otg_fsm.c b/drivers/usb/chipidea/otg_fsm.c
index caaabc58021..8cb2508a6b7 100644
--- a/drivers/usb/chipidea/otg_fsm.c
+++ b/drivers/usb/chipidea/otg_fsm.c
@@ -328,7 +328,7 @@ static void b_ssend_srp_tmout_func(void *ptr, unsigned long indicator)
 	set_tmout(ci, indicator);
 
 	/* only vbus fall below B_sess_vld in b_idle state */
-	if (ci->transceiver->state == OTG_STATE_B_IDLE)
+	if (ci->fsm.otg->state == OTG_STATE_B_IDLE)
 		ci_otg_queue_work(ci);
 }
 
@@ -582,11 +582,11 @@ int ci_otg_fsm_work(struct ci_hdrc *ci)
 	 * when there is no gadget class driver
 	 */
 	if (ci->fsm.id && !(ci->driver) &&
-		ci->transceiver->state < OTG_STATE_A_IDLE)
+		ci->fsm.otg->state < OTG_STATE_A_IDLE)
 		return 0;
 
 	if (otg_statemachine(&ci->fsm)) {
-		if (ci->transceiver->state == OTG_STATE_A_IDLE) {
+		if (ci->fsm.otg->state == OTG_STATE_A_IDLE) {
 			/*
 			 * Further state change for cases:
 			 * a_idle to b_idle; or
@@ -600,7 +600,7 @@ int ci_otg_fsm_work(struct ci_hdrc *ci)
 				ci_otg_queue_work(ci);
 			if (ci->id_event)
 				ci->id_event = false;
-		} else if (ci->transceiver->state == OTG_STATE_B_IDLE) {
+		} else if (ci->fsm.otg->state == OTG_STATE_B_IDLE) {
 			if (ci->fsm.b_sess_vld) {
 				ci->fsm.power_up = 0;
 				/*
@@ -627,7 +627,7 @@ static void ci_otg_fsm_event(struct ci_hdrc *ci)
 	otg_bsess_vld = hw_read_otgsc(ci, OTGSC_BSV);
 	port_conn = hw_read(ci, OP_PORTSC, PORTSC_CCS);
 
-	switch (ci->transceiver->state) {
+	switch (ci->fsm.otg->state) {
 	case OTG_STATE_A_WAIT_BCON:
 		if (port_conn) {
 			fsm->b_conn = 1;
@@ -794,7 +794,7 @@ int ci_hdrc_otg_fsm_init(struct ci_hdrc *ci)
 	ci->transceiver->otg = ci->fsm.otg;
 	ci->fsm.power_up = 1;
 	ci->fsm.id = hw_read_otgsc(ci, OTGSC_ID) ? 1 : 0;
-	ci->transceiver->state = OTG_STATE_UNDEFINED;
+	ci->fsm.otg->state = OTG_STATE_UNDEFINED;
 	ci->fsm.ops = &ci_otg_ops;
 
 	mutex_init(&ci->fsm.lock);
diff --git a/drivers/usb/common/usb-otg-fsm.c b/drivers/usb/common/usb-otg-fsm.c
index 98e8340a5bb..c6b35b77dab 100644
--- a/drivers/usb/common/usb-otg-fsm.c
+++ b/drivers/usb/common/usb-otg-fsm.c
@@ -124,10 +124,10 @@ static void otg_leave_state(struct otg_fsm *fsm, enum usb_otg_state old_state)
 static int otg_set_state(struct otg_fsm *fsm, enum usb_otg_state new_state)
 {
 	state_changed = 1;
-	if (fsm->otg->phy->state == new_state)
+	if (fsm->otg->state == new_state)
 		return 0;
 	VDBG("Set state: %s\n", usb_otg_state_string(new_state));
-	otg_leave_state(fsm, fsm->otg->phy->state);
+	otg_leave_state(fsm, fsm->otg->state);
 	switch (new_state) {
 	case OTG_STATE_B_IDLE:
 		otg_drv_vbus(fsm, 0);
@@ -236,7 +236,7 @@ static int otg_set_state(struct otg_fsm *fsm, enum usb_otg_state new_state)
 		break;
 	}
 
-	fsm->otg->phy->state = new_state;
+	fsm->otg->state = new_state;
 	return 0;
 }
 
@@ -247,7 +247,7 @@ int otg_statemachine(struct otg_fsm *fsm)
 
 	mutex_lock(&fsm->lock);
 
-	state = fsm->otg->phy->state;
+	state = fsm->otg->state;
 	state_changed = 0;
 	/* State machine state change judgement */
 
diff --git a/drivers/usb/host/ohci-omap.c b/drivers/usb/host/ohci-omap.c
index 0231606d47c..cf89b4b17f1 100644
--- a/drivers/usb/host/ohci-omap.c
+++ b/drivers/usb/host/ohci-omap.c
@@ -183,7 +183,7 @@ static void start_hnp(struct ohci_hcd *ohci)
 	otg_start_hnp(hcd->usb_phy->otg);
 
 	local_irq_save(flags);
-	hcd->usb_phy->state = OTG_STATE_A_SUSPEND;
+	hcd->usb_phy->otg.state = OTG_STATE_A_SUSPEND;
 	writel (RH_PS_PSS, &ohci->regs->roothub.portstatus [port]);
 	l = omap_readl(OTG_CTRL);
 	l &= ~OTG_A_BUSREQ;
diff --git a/drivers/usb/musb/am35x.c b/drivers/usb/musb/am35x.c
index a2735df24cc..d836a3e1f8e 100644
--- a/drivers/usb/musb/am35x.c
+++ b/drivers/usb/musb/am35x.c
@@ -149,25 +149,25 @@ static void otg_timer(unsigned long _musb)
 	 */
 	devctl = musb_readb(mregs, MUSB_DEVCTL);
 	dev_dbg(musb->controller, "Poll devctl %02x (%s)\n", devctl,
-		usb_otg_state_string(musb->xceiv->state));
+		usb_otg_state_string(musb->xceiv->otg->state));
 
 	spin_lock_irqsave(&musb->lock, flags);
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_A_WAIT_BCON:
 		devctl &= ~MUSB_DEVCTL_SESSION;
 		musb_writeb(musb->mregs, MUSB_DEVCTL, devctl);
 
 		devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
 		if (devctl & MUSB_DEVCTL_BDEVICE) {
-			musb->xceiv->state = OTG_STATE_B_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 			MUSB_DEV_MODE(musb);
 		} else {
-			musb->xceiv->state = OTG_STATE_A_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 			MUSB_HST_MODE(musb);
 		}
 		break;
 	case OTG_STATE_A_WAIT_VFALL:
-		musb->xceiv->state = OTG_STATE_A_WAIT_VRISE;
+		musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 		musb_writel(musb->ctrl_base, CORE_INTR_SRC_SET_REG,
 			    MUSB_INTR_VBUSERROR << AM35X_INTR_USB_SHIFT);
 		break;
@@ -176,7 +176,7 @@ static void otg_timer(unsigned long _musb)
 		if (devctl & MUSB_DEVCTL_BDEVICE)
 			mod_timer(&otg_workaround, jiffies + POLL_SECONDS * HZ);
 		else
-			musb->xceiv->state = OTG_STATE_A_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 		break;
 	default:
 		break;
@@ -193,9 +193,9 @@ static void am35x_musb_try_idle(struct musb *musb, unsigned long timeout)
 
 	/* Never idle if active, or when VBUS timeout is not set as host */
 	if (musb->is_active || (musb->a_wait_bcon == 0 &&
-				musb->xceiv->state == OTG_STATE_A_WAIT_BCON)) {
+				musb->xceiv->otg->state == OTG_STATE_A_WAIT_BCON)) {
 		dev_dbg(musb->controller, "%s active, deleting timer\n",
-			usb_otg_state_string(musb->xceiv->state));
+			usb_otg_state_string(musb->xceiv->otg->state));
 		del_timer(&otg_workaround);
 		last_timer = jiffies;
 		return;
@@ -208,7 +208,7 @@ static void am35x_musb_try_idle(struct musb *musb, unsigned long timeout)
 	last_timer = timeout;
 
 	dev_dbg(musb->controller, "%s inactive, starting idle timer for %u ms\n",
-		usb_otg_state_string(musb->xceiv->state),
+		usb_otg_state_string(musb->xceiv->otg->state),
 		jiffies_to_msecs(timeout - jiffies));
 	mod_timer(&otg_workaround, timeout);
 }
@@ -278,27 +278,27 @@ static irqreturn_t am35x_musb_interrupt(int irq, void *hci)
 			 * devctl.
 			 */
 			musb->int_usb &= ~MUSB_INTR_VBUSERROR;
-			musb->xceiv->state = OTG_STATE_A_WAIT_VFALL;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VFALL;
 			mod_timer(&otg_workaround, jiffies + POLL_SECONDS * HZ);
 			WARNING("VBUS error workaround (delay coming)\n");
 		} else if (drvvbus) {
 			MUSB_HST_MODE(musb);
 			otg->default_a = 1;
-			musb->xceiv->state = OTG_STATE_A_WAIT_VRISE;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			portstate(musb->port1_status |= USB_PORT_STAT_POWER);
 			del_timer(&otg_workaround);
 		} else {
 			musb->is_active = 0;
 			MUSB_DEV_MODE(musb);
 			otg->default_a = 0;
-			musb->xceiv->state = OTG_STATE_B_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 			portstate(musb->port1_status &= ~USB_PORT_STAT_POWER);
 		}
 
 		/* NOTE: this must complete power-on within 100 ms. */
 		dev_dbg(musb->controller, "VBUS %s (%s)%s, devctl %02x\n",
 				drvvbus ? "on" : "off",
-				usb_otg_state_string(musb->xceiv->state),
+				usb_otg_state_string(musb->xceiv->otg->state),
 				err ? " ERROR" : "",
 				devctl);
 		ret = IRQ_HANDLED;
@@ -324,7 +324,7 @@ eoi:
 	}
 
 	/* Poll for ID change */
-	if (musb->xceiv->state == OTG_STATE_B_IDLE)
+	if (musb->xceiv->otg->state == OTG_STATE_B_IDLE)
 		mod_timer(&otg_workaround, jiffies + POLL_SECONDS * HZ);
 
 	spin_unlock_irqrestore(&musb->lock, flags);
diff --git a/drivers/usb/musb/blackfin.c b/drivers/usb/musb/blackfin.c
index 8554c6f7ab7..f23ce40b4d6 100644
--- a/drivers/usb/musb/blackfin.c
+++ b/drivers/usb/musb/blackfin.c
@@ -185,8 +185,8 @@ static irqreturn_t blackfin_interrupt(int irq, void *__hci)
 	}
 
 	/* Start sampling ID pin, when plug is removed from MUSB */
-	if ((musb->xceiv->state == OTG_STATE_B_IDLE
-		|| musb->xceiv->state == OTG_STATE_A_WAIT_BCON) ||
+	if ((musb->xceiv->otg->state == OTG_STATE_B_IDLE
+		|| musb->xceiv->otg->state == OTG_STATE_A_WAIT_BCON) ||
 		(musb->int_usb & MUSB_INTR_DISCONNECT && is_host_active(musb))) {
 		mod_timer(&musb_conn_timer, jiffies + TIMER_DELAY);
 		musb->a_wait_bcon = TIMER_DELAY;
@@ -205,7 +205,7 @@ static void musb_conn_timer_handler(unsigned long _musb)
 	static u8 toggle;
 
 	spin_lock_irqsave(&musb->lock, flags);
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_A_IDLE:
 	case OTG_STATE_A_WAIT_BCON:
 		/* Start a new session */
@@ -219,7 +219,7 @@ static void musb_conn_timer_handler(unsigned long _musb)
 
 		if (!(val & MUSB_DEVCTL_BDEVICE)) {
 			gpio_set_value(musb->config->gpio_vrsel, 1);
-			musb->xceiv->state = OTG_STATE_A_WAIT_BCON;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_BCON;
 		} else {
 			gpio_set_value(musb->config->gpio_vrsel, 0);
 			/* Ignore VBUSERROR and SUSPEND IRQ */
@@ -229,7 +229,7 @@ static void musb_conn_timer_handler(unsigned long _musb)
 
 			val = MUSB_INTR_SUSPEND | MUSB_INTR_VBUSERROR;
 			musb_writeb(musb->mregs, MUSB_INTRUSB, val);
-			musb->xceiv->state = OTG_STATE_B_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 		}
 		mod_timer(&musb_conn_timer, jiffies + TIMER_DELAY);
 		break;
@@ -245,7 +245,7 @@ static void musb_conn_timer_handler(unsigned long _musb)
 
 		if (!(val & MUSB_DEVCTL_BDEVICE)) {
 			gpio_set_value(musb->config->gpio_vrsel, 1);
-			musb->xceiv->state = OTG_STATE_A_WAIT_BCON;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_BCON;
 		} else {
 			gpio_set_value(musb->config->gpio_vrsel, 0);
 
@@ -280,13 +280,13 @@ static void musb_conn_timer_handler(unsigned long _musb)
 		break;
 	default:
 		dev_dbg(musb->controller, "%s state not handled\n",
-			usb_otg_state_string(musb->xceiv->state));
+			usb_otg_state_string(musb->xceiv->otg->state));
 		break;
 	}
 	spin_unlock_irqrestore(&musb->lock, flags);
 
 	dev_dbg(musb->controller, "state is %s\n",
-		usb_otg_state_string(musb->xceiv->state));
+		usb_otg_state_string(musb->xceiv->otg->state));
 }
 
 static void bfin_musb_enable(struct musb *musb)
@@ -307,7 +307,7 @@ static void bfin_musb_set_vbus(struct musb *musb, int is_on)
 
 	dev_dbg(musb->controller, "VBUS %s, devctl %02x "
 		/* otg %3x conf %08x prcm %08x */ "\n",
-		usb_otg_state_string(musb->xceiv->state),
+		usb_otg_state_string(musb->xceiv->otg->state),
 		musb_readb(musb->mregs, MUSB_DEVCTL));
 }
 
diff --git a/drivers/usb/musb/da8xx.c b/drivers/usb/musb/da8xx.c
index 058775e647a..527c7fe60ec 100644
--- a/drivers/usb/musb/da8xx.c
+++ b/drivers/usb/musb/da8xx.c
@@ -198,20 +198,20 @@ static void otg_timer(unsigned long _musb)
 	 */
 	devctl = musb_readb(mregs, MUSB_DEVCTL);
 	dev_dbg(musb->controller, "Poll devctl %02x (%s)\n", devctl,
-		usb_otg_state_string(musb->xceiv->state));
+		usb_otg_state_string(musb->xceiv->otg->state));
 
 	spin_lock_irqsave(&musb->lock, flags);
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_A_WAIT_BCON:
 		devctl &= ~MUSB_DEVCTL_SESSION;
 		musb_writeb(musb->mregs, MUSB_DEVCTL, devctl);
 
 		devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
 		if (devctl & MUSB_DEVCTL_BDEVICE) {
-			musb->xceiv->state = OTG_STATE_B_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 			MUSB_DEV_MODE(musb);
 		} else {
-			musb->xceiv->state = OTG_STATE_A_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 			MUSB_HST_MODE(musb);
 		}
 		break;
@@ -226,7 +226,7 @@ static void otg_timer(unsigned long _musb)
 			mod_timer(&otg_workaround, jiffies + POLL_SECONDS * HZ);
 			break;
 		}
-		musb->xceiv->state = OTG_STATE_A_WAIT_VRISE;
+		musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 		musb_writel(musb->ctrl_base, DA8XX_USB_INTR_SRC_SET_REG,
 			    MUSB_INTR_VBUSERROR << DA8XX_INTR_USB_SHIFT);
 		break;
@@ -248,7 +248,7 @@ static void otg_timer(unsigned long _musb)
 		if (devctl & MUSB_DEVCTL_BDEVICE)
 			mod_timer(&otg_workaround, jiffies + POLL_SECONDS * HZ);
 		else
-			musb->xceiv->state = OTG_STATE_A_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 		break;
 	default:
 		break;
@@ -265,9 +265,9 @@ static void da8xx_musb_try_idle(struct musb *musb, unsigned long timeout)
 
 	/* Never idle if active, or when VBUS timeout is not set as host */
 	if (musb->is_active || (musb->a_wait_bcon == 0 &&
-				musb->xceiv->state == OTG_STATE_A_WAIT_BCON)) {
+				musb->xceiv->otg->state == OTG_STATE_A_WAIT_BCON)) {
 		dev_dbg(musb->controller, "%s active, deleting timer\n",
-			usb_otg_state_string(musb->xceiv->state));
+			usb_otg_state_string(musb->xceiv->otg->state));
 		del_timer(&otg_workaround);
 		last_timer = jiffies;
 		return;
@@ -280,7 +280,7 @@ static void da8xx_musb_try_idle(struct musb *musb, unsigned long timeout)
 	last_timer = timeout;
 
 	dev_dbg(musb->controller, "%s inactive, starting idle timer for %u ms\n",
-		usb_otg_state_string(musb->xceiv->state),
+		usb_otg_state_string(musb->xceiv->otg->state),
 		jiffies_to_msecs(timeout - jiffies));
 	mod_timer(&otg_workaround, timeout);
 }
@@ -341,26 +341,26 @@ static irqreturn_t da8xx_musb_interrupt(int irq, void *hci)
 			 * devctl.
 			 */
 			musb->int_usb &= ~MUSB_INTR_VBUSERROR;
-			musb->xceiv->state = OTG_STATE_A_WAIT_VFALL;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VFALL;
 			mod_timer(&otg_workaround, jiffies + POLL_SECONDS * HZ);
 			WARNING("VBUS error workaround (delay coming)\n");
 		} else if (drvvbus) {
 			MUSB_HST_MODE(musb);
 			otg->default_a = 1;
-			musb->xceiv->state = OTG_STATE_A_WAIT_VRISE;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			portstate(musb->port1_status |= USB_PORT_STAT_POWER);
 			del_timer(&otg_workaround);
 		} else {
 			musb->is_active = 0;
 			MUSB_DEV_MODE(musb);
 			otg->default_a = 0;
-			musb->xceiv->state = OTG_STATE_B_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 			portstate(musb->port1_status &= ~USB_PORT_STAT_POWER);
 		}
 
 		dev_dbg(musb->controller, "VBUS %s (%s)%s, devctl %02x\n",
 				drvvbus ? "on" : "off",
-				usb_otg_state_string(musb->xceiv->state),
+				usb_otg_state_string(musb->xceiv->otg->state),
 				err ? " ERROR" : "",
 				devctl);
 		ret = IRQ_HANDLED;
@@ -375,7 +375,7 @@ static irqreturn_t da8xx_musb_interrupt(int irq, void *hci)
 		musb_writel(reg_base, DA8XX_USB_END_OF_INTR_REG, 0);
 
 	/* Poll for ID change */
-	if (musb->xceiv->state == OTG_STATE_B_IDLE)
+	if (musb->xceiv->otg->state == OTG_STATE_B_IDLE)
 		mod_timer(&otg_workaround, jiffies + POLL_SECONDS * HZ);
 
 	spin_unlock_irqrestore(&musb->lock, flags);
diff --git a/drivers/usb/musb/davinci.c b/drivers/usb/musb/davinci.c
index 04de3aca938..3c1d9b211b5 100644
--- a/drivers/usb/musb/davinci.c
+++ b/drivers/usb/musb/davinci.c
@@ -214,10 +214,10 @@ static void otg_timer(unsigned long _musb)
 	 */
 	devctl = musb_readb(mregs, MUSB_DEVCTL);
 	dev_dbg(musb->controller, "poll devctl %02x (%s)\n", devctl,
-		usb_otg_state_string(musb->xceiv->state));
+		usb_otg_state_string(musb->xceiv->otg->state));
 
 	spin_lock_irqsave(&musb->lock, flags);
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_A_WAIT_VFALL:
 		/* Wait till VBUS falls below SessionEnd (~0.2V); the 1.3 RTL
 		 * seems to mis-handle session "start" otherwise (or in our
@@ -228,7 +228,7 @@ static void otg_timer(unsigned long _musb)
 			mod_timer(&otg_workaround, jiffies + POLL_SECONDS * HZ);
 			break;
 		}
-		musb->xceiv->state = OTG_STATE_A_WAIT_VRISE;
+		musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 		musb_writel(musb->ctrl_base, DAVINCI_USB_INT_SET_REG,
 			MUSB_INTR_VBUSERROR << DAVINCI_USB_USBINT_SHIFT);
 		break;
@@ -251,7 +251,7 @@ static void otg_timer(unsigned long _musb)
 		if (devctl & MUSB_DEVCTL_BDEVICE)
 			mod_timer(&otg_workaround, jiffies + POLL_SECONDS * HZ);
 		else
-			musb->xceiv->state = OTG_STATE_A_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 		break;
 	default:
 		break;
@@ -325,20 +325,20 @@ static irqreturn_t davinci_musb_interrupt(int irq, void *__hci)
 			 * to stop registering in devctl.
 			 */
 			musb->int_usb &= ~MUSB_INTR_VBUSERROR;
-			musb->xceiv->state = OTG_STATE_A_WAIT_VFALL;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VFALL;
 			mod_timer(&otg_workaround, jiffies + POLL_SECONDS * HZ);
 			WARNING("VBUS error workaround (delay coming)\n");
 		} else if (drvvbus) {
 			MUSB_HST_MODE(musb);
 			otg->default_a = 1;
-			musb->xceiv->state = OTG_STATE_A_WAIT_VRISE;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			portstate(musb->port1_status |= USB_PORT_STAT_POWER);
 			del_timer(&otg_workaround);
 		} else {
 			musb->is_active = 0;
 			MUSB_DEV_MODE(musb);
 			otg->default_a = 0;
-			musb->xceiv->state = OTG_STATE_B_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 			portstate(musb->port1_status &= ~USB_PORT_STAT_POWER);
 		}
 
@@ -348,7 +348,7 @@ static irqreturn_t davinci_musb_interrupt(int irq, void *__hci)
 		davinci_musb_source_power(musb, drvvbus, 0);
 		dev_dbg(musb->controller, "VBUS %s (%s)%s, devctl %02x\n",
 				drvvbus ? "on" : "off",
-				usb_otg_state_string(musb->xceiv->state),
+				usb_otg_state_string(musb->xceiv->otg->state),
 				err ? " ERROR" : "",
 				devctl);
 		retval = IRQ_HANDLED;
@@ -361,7 +361,7 @@ static irqreturn_t davinci_musb_interrupt(int irq, void *__hci)
 	musb_writel(tibase, DAVINCI_USB_EOI_REG, 0);
 
 	/* poll for ID change */
-	if (musb->xceiv->state == OTG_STATE_B_IDLE)
+	if (musb->xceiv->otg->state == OTG_STATE_B_IDLE)
 		mod_timer(&otg_workaround, jiffies + POLL_SECONDS * HZ);
 
 	spin_unlock_irqrestore(&musb->lock, flags);
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index e46e295a383..df9c5fa2772 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -360,23 +360,23 @@ static void musb_otg_timer_func(unsigned long data)
 	unsigned long	flags;
 
 	spin_lock_irqsave(&musb->lock, flags);
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_B_WAIT_ACON:
 		dev_dbg(musb->controller, "HNP: b_wait_acon timeout; back to b_peripheral\n");
 		musb_g_disconnect(musb);
-		musb->xceiv->state = OTG_STATE_B_PERIPHERAL;
+		musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
 		musb->is_active = 0;
 		break;
 	case OTG_STATE_A_SUSPEND:
 	case OTG_STATE_A_WAIT_BCON:
 		dev_dbg(musb->controller, "HNP: %s timeout\n",
-			usb_otg_state_string(musb->xceiv->state));
+			usb_otg_state_string(musb->xceiv->otg->state));
 		musb_platform_set_vbus(musb, 0);
-		musb->xceiv->state = OTG_STATE_A_WAIT_VFALL;
+		musb->xceiv->otg->state = OTG_STATE_A_WAIT_VFALL;
 		break;
 	default:
 		dev_dbg(musb->controller, "HNP: Unhandled mode %s\n",
-			usb_otg_state_string(musb->xceiv->state));
+			usb_otg_state_string(musb->xceiv->otg->state));
 	}
 	spin_unlock_irqrestore(&musb->lock, flags);
 }
@@ -391,19 +391,19 @@ void musb_hnp_stop(struct musb *musb)
 	u8	reg;
 
 	dev_dbg(musb->controller, "HNP: stop from %s\n",
-			usb_otg_state_string(musb->xceiv->state));
+			usb_otg_state_string(musb->xceiv->otg->state));
 
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_A_PERIPHERAL:
 		musb_g_disconnect(musb);
 		dev_dbg(musb->controller, "HNP: back to %s\n",
-			usb_otg_state_string(musb->xceiv->state));
+			usb_otg_state_string(musb->xceiv->otg->state));
 		break;
 	case OTG_STATE_B_HOST:
 		dev_dbg(musb->controller, "HNP: Disabling HR\n");
 		if (hcd)
 			hcd->self.is_b_host = 0;
-		musb->xceiv->state = OTG_STATE_B_PERIPHERAL;
+		musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
 		MUSB_DEV_MODE(musb);
 		reg = musb_readb(mbase, MUSB_POWER);
 		reg |= MUSB_POWER_SUSPENDM;
@@ -412,7 +412,7 @@ void musb_hnp_stop(struct musb *musb)
 		break;
 	default:
 		dev_dbg(musb->controller, "HNP: Stopping in unknown state %s\n",
-			usb_otg_state_string(musb->xceiv->state));
+			usb_otg_state_string(musb->xceiv->otg->state));
 	}
 
 	/*
@@ -449,13 +449,13 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 	 */
 	if (int_usb & MUSB_INTR_RESUME) {
 		handled = IRQ_HANDLED;
-		dev_dbg(musb->controller, "RESUME (%s)\n", usb_otg_state_string(musb->xceiv->state));
+		dev_dbg(musb->controller, "RESUME (%s)\n", usb_otg_state_string(musb->xceiv->otg->state));
 
 		if (devctl & MUSB_DEVCTL_HM) {
 			void __iomem *mbase = musb->mregs;
 			u8 power;
 
-			switch (musb->xceiv->state) {
+			switch (musb->xceiv->otg->state) {
 			case OTG_STATE_A_SUSPEND:
 				/* remote wakeup?  later, GetPortStatus
 				 * will stop RESUME signaling
@@ -482,25 +482,25 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 					&musb->finish_resume_work,
 					msecs_to_jiffies(20));
 
-				musb->xceiv->state = OTG_STATE_A_HOST;
+				musb->xceiv->otg->state = OTG_STATE_A_HOST;
 				musb->is_active = 1;
 				musb_host_resume_root_hub(musb);
 				break;
 			case OTG_STATE_B_WAIT_ACON:
-				musb->xceiv->state = OTG_STATE_B_PERIPHERAL;
+				musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
 				musb->is_active = 1;
 				MUSB_DEV_MODE(musb);
 				break;
 			default:
 				WARNING("bogus %s RESUME (%s)\n",
 					"host",
-					usb_otg_state_string(musb->xceiv->state));
+					usb_otg_state_string(musb->xceiv->otg->state));
 			}
 		} else {
-			switch (musb->xceiv->state) {
+			switch (musb->xceiv->otg->state) {
 			case OTG_STATE_A_SUSPEND:
 				/* possibly DISCONNECT is upcoming */
-				musb->xceiv->state = OTG_STATE_A_HOST;
+				musb->xceiv->otg->state = OTG_STATE_A_HOST;
 				musb_host_resume_root_hub(musb);
 				break;
 			case OTG_STATE_B_WAIT_ACON:
@@ -523,7 +523,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 			default:
 				WARNING("bogus %s RESUME (%s)\n",
 					"peripheral",
-					usb_otg_state_string(musb->xceiv->state));
+					usb_otg_state_string(musb->xceiv->otg->state));
 			}
 		}
 	}
@@ -539,7 +539,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 		}
 
 		dev_dbg(musb->controller, "SESSION_REQUEST (%s)\n",
-			usb_otg_state_string(musb->xceiv->state));
+			usb_otg_state_string(musb->xceiv->otg->state));
 
 		/* IRQ arrives from ID pin sense or (later, if VBUS power
 		 * is removed) SRP.  responses are time critical:
@@ -550,7 +550,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 		 */
 		musb_writeb(mbase, MUSB_DEVCTL, MUSB_DEVCTL_SESSION);
 		musb->ep0_stage = MUSB_EP0_START;
-		musb->xceiv->state = OTG_STATE_A_IDLE;
+		musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 		MUSB_HST_MODE(musb);
 		musb_platform_set_vbus(musb, 1);
 
@@ -576,7 +576,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 		 * REVISIT:  do delays from lots of DEBUG_KERNEL checks
 		 * make trouble here, keeping VBUS < 4.4V ?
 		 */
-		switch (musb->xceiv->state) {
+		switch (musb->xceiv->otg->state) {
 		case OTG_STATE_A_HOST:
 			/* recovery is dicey once we've gotten past the
 			 * initial stages of enumeration, but if VBUS
@@ -605,7 +605,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 
 		dev_printk(ignore ? KERN_DEBUG : KERN_ERR, musb->controller,
 				"VBUS_ERROR in %s (%02x, %s), retry #%d, port1 %08x\n",
-				usb_otg_state_string(musb->xceiv->state),
+				usb_otg_state_string(musb->xceiv->otg->state),
 				devctl,
 				({ char *s;
 				switch (devctl & MUSB_DEVCTL_VBUS) {
@@ -630,10 +630,10 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 
 	if (int_usb & MUSB_INTR_SUSPEND) {
 		dev_dbg(musb->controller, "SUSPEND (%s) devctl %02x\n",
-			usb_otg_state_string(musb->xceiv->state), devctl);
+			usb_otg_state_string(musb->xceiv->otg->state), devctl);
 		handled = IRQ_HANDLED;
 
-		switch (musb->xceiv->state) {
+		switch (musb->xceiv->otg->state) {
 		case OTG_STATE_A_PERIPHERAL:
 			/* We also come here if the cable is removed, since
 			 * this silicon doesn't report ID-no-longer-grounded.
@@ -657,7 +657,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 			musb_g_suspend(musb);
 			musb->is_active = musb->g.b_hnp_enable;
 			if (musb->is_active) {
-				musb->xceiv->state = OTG_STATE_B_WAIT_ACON;
+				musb->xceiv->otg->state = OTG_STATE_B_WAIT_ACON;
 				dev_dbg(musb->controller, "HNP: Setting timer for b_ase0_brst\n");
 				mod_timer(&musb->otg_timer, jiffies
 					+ msecs_to_jiffies(
@@ -670,7 +670,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 					+ msecs_to_jiffies(musb->a_wait_bcon));
 			break;
 		case OTG_STATE_A_HOST:
-			musb->xceiv->state = OTG_STATE_A_SUSPEND;
+			musb->xceiv->otg->state = OTG_STATE_A_SUSPEND;
 			musb->is_active = musb->hcd->self.b_hnp_enable;
 			break;
 		case OTG_STATE_B_HOST:
@@ -713,7 +713,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 			musb->port1_status |= USB_PORT_STAT_LOW_SPEED;
 
 		/* indicate new connection to OTG machine */
-		switch (musb->xceiv->state) {
+		switch (musb->xceiv->otg->state) {
 		case OTG_STATE_B_PERIPHERAL:
 			if (int_usb & MUSB_INTR_SUSPEND) {
 				dev_dbg(musb->controller, "HNP: SUSPEND+CONNECT, now b_host\n");
@@ -725,7 +725,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 		case OTG_STATE_B_WAIT_ACON:
 			dev_dbg(musb->controller, "HNP: CONNECT, now b_host\n");
 b_host:
-			musb->xceiv->state = OTG_STATE_B_HOST;
+			musb->xceiv->otg->state = OTG_STATE_B_HOST;
 			if (musb->hcd)
 				musb->hcd->self.is_b_host = 1;
 			del_timer(&musb->otg_timer);
@@ -733,7 +733,7 @@ b_host:
 		default:
 			if ((devctl & MUSB_DEVCTL_VBUS)
 					== (3 << MUSB_DEVCTL_VBUS_SHIFT)) {
-				musb->xceiv->state = OTG_STATE_A_HOST;
+				musb->xceiv->otg->state = OTG_STATE_A_HOST;
 				if (hcd)
 					hcd->self.is_b_host = 0;
 			}
@@ -743,16 +743,16 @@ b_host:
 		musb_host_poke_root_hub(musb);
 
 		dev_dbg(musb->controller, "CONNECT (%s) devctl %02x\n",
-				usb_otg_state_string(musb->xceiv->state), devctl);
+				usb_otg_state_string(musb->xceiv->otg->state), devctl);
 	}
 
 	if (int_usb & MUSB_INTR_DISCONNECT) {
 		dev_dbg(musb->controller, "DISCONNECT (%s) as %s, devctl %02x\n",
-				usb_otg_state_string(musb->xceiv->state),
+				usb_otg_state_string(musb->xceiv->otg->state),
 				MUSB_MODE(musb), devctl);
 		handled = IRQ_HANDLED;
 
-		switch (musb->xceiv->state) {
+		switch (musb->xceiv->otg->state) {
 		case OTG_STATE_A_HOST:
 		case OTG_STATE_A_SUSPEND:
 			musb_host_resume_root_hub(musb);
@@ -770,7 +770,7 @@ b_host:
 			musb_root_disconnect(musb);
 			if (musb->hcd)
 				musb->hcd->self.is_b_host = 0;
-			musb->xceiv->state = OTG_STATE_B_PERIPHERAL;
+			musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
 			MUSB_DEV_MODE(musb);
 			musb_g_disconnect(musb);
 			break;
@@ -786,7 +786,7 @@ b_host:
 			break;
 		default:
 			WARNING("unhandled DISCONNECT transition (%s)\n",
-				usb_otg_state_string(musb->xceiv->state));
+				usb_otg_state_string(musb->xceiv->otg->state));
 			break;
 		}
 	}
@@ -812,15 +812,15 @@ b_host:
 			}
 		} else {
 			dev_dbg(musb->controller, "BUS RESET as %s\n",
-				usb_otg_state_string(musb->xceiv->state));
-			switch (musb->xceiv->state) {
+				usb_otg_state_string(musb->xceiv->otg->state));
+			switch (musb->xceiv->otg->state) {
 			case OTG_STATE_A_SUSPEND:
 				musb_g_reset(musb);
 				/* FALLTHROUGH */
 			case OTG_STATE_A_WAIT_BCON:	/* OPT TD.4.7-900ms */
 				/* never use invalid T(a_wait_bcon) */
 				dev_dbg(musb->controller, "HNP: in %s, %d msec timeout\n",
-					usb_otg_state_string(musb->xceiv->state),
+					usb_otg_state_string(musb->xceiv->otg->state),
 					TA_WAIT_BCON(musb));
 				mod_timer(&musb->otg_timer, jiffies
 					+ msecs_to_jiffies(TA_WAIT_BCON(musb)));
@@ -831,19 +831,19 @@ b_host:
 				break;
 			case OTG_STATE_B_WAIT_ACON:
 				dev_dbg(musb->controller, "HNP: RESET (%s), to b_peripheral\n",
-					usb_otg_state_string(musb->xceiv->state));
-				musb->xceiv->state = OTG_STATE_B_PERIPHERAL;
+					usb_otg_state_string(musb->xceiv->otg->state));
+				musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
 				musb_g_reset(musb);
 				break;
 			case OTG_STATE_B_IDLE:
-				musb->xceiv->state = OTG_STATE_B_PERIPHERAL;
+				musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
 				/* FALLTHROUGH */
 			case OTG_STATE_B_PERIPHERAL:
 				musb_g_reset(musb);
 				break;
 			default:
 				dev_dbg(musb->controller, "Unhandled BUS RESET as %s\n",
-					usb_otg_state_string(musb->xceiv->state));
+					usb_otg_state_string(musb->xceiv->otg->state));
 			}
 		}
 	}
@@ -1630,7 +1630,7 @@ musb_mode_show(struct device *dev, struct device_attribute *attr, char *buf)
 	int ret = -EINVAL;
 
 	spin_lock_irqsave(&musb->lock, flags);
-	ret = sprintf(buf, "%s\n", usb_otg_state_string(musb->xceiv->state));
+	ret = sprintf(buf, "%s\n", usb_otg_state_string(musb->xceiv->otg->state));
 	spin_unlock_irqrestore(&musb->lock, flags);
 
 	return ret;
@@ -1675,7 +1675,7 @@ musb_vbus_store(struct device *dev, struct device_attribute *attr,
 	spin_lock_irqsave(&musb->lock, flags);
 	/* force T(a_wait_bcon) to be zero/unlimited *OR* valid */
 	musb->a_wait_bcon = val ? max_t(int, val, OTG_TIME_A_WAIT_BCON) : 0 ;
-	if (musb->xceiv->state == OTG_STATE_A_WAIT_BCON)
+	if (musb->xceiv->otg->state == OTG_STATE_A_WAIT_BCON)
 		musb->is_active = 0;
 	musb_platform_try_idle(musb, jiffies + msecs_to_jiffies(val));
 	spin_unlock_irqrestore(&musb->lock, flags);
@@ -1743,8 +1743,8 @@ static void musb_irq_work(struct work_struct *data)
 {
 	struct musb *musb = container_of(data, struct musb, irq_work);
 
-	if (musb->xceiv->state != musb->xceiv_old_state) {
-		musb->xceiv_old_state = musb->xceiv->state;
+	if (musb->xceiv->otg->state != musb->xceiv_old_state) {
+		musb->xceiv_old_state = musb->xceiv->otg->state;
 		sysfs_notify(&musb->controller->kobj, NULL, "mode");
 	}
 }
@@ -1983,10 +1983,10 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 
 	if (musb->xceiv->otg->default_a) {
 		MUSB_HST_MODE(musb);
-		musb->xceiv->state = OTG_STATE_A_IDLE;
+		musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 	} else {
 		MUSB_DEV_MODE(musb);
-		musb->xceiv->state = OTG_STATE_B_IDLE;
+		musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 	}
 
 	switch (musb->port_mode) {
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 759ef1d236b..440333fcf3a 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -179,9 +179,9 @@ static void dsps_musb_try_idle(struct musb *musb, unsigned long timeout)
 
 	/* Never idle if active, or when VBUS timeout is not set as host */
 	if (musb->is_active || (musb->a_wait_bcon == 0 &&
-				musb->xceiv->state == OTG_STATE_A_WAIT_BCON)) {
+			musb->xceiv->otg->state == OTG_STATE_A_WAIT_BCON)) {
 		dev_dbg(musb->controller, "%s active, deleting timer\n",
-				usb_otg_state_string(musb->xceiv->state));
+				usb_otg_state_string(musb->xceiv->otg->state));
 		del_timer(&glue->timer);
 		glue->last_timer = jiffies;
 		return;
@@ -201,7 +201,7 @@ static void dsps_musb_try_idle(struct musb *musb, unsigned long timeout)
 	glue->last_timer = timeout;
 
 	dev_dbg(musb->controller, "%s inactive, starting idle timer for %u ms\n",
-		usb_otg_state_string(musb->xceiv->state),
+		usb_otg_state_string(musb->xceiv->otg->state),
 			jiffies_to_msecs(timeout - jiffies));
 	mod_timer(&glue->timer, timeout);
 }
@@ -265,10 +265,10 @@ static void otg_timer(unsigned long _musb)
 	 */
 	devctl = dsps_readb(mregs, MUSB_DEVCTL);
 	dev_dbg(musb->controller, "Poll devctl %02x (%s)\n", devctl,
-				usb_otg_state_string(musb->xceiv->state));
+				usb_otg_state_string(musb->xceiv->otg->state));
 
 	spin_lock_irqsave(&musb->lock, flags);
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_A_WAIT_BCON:
 		dsps_writeb(musb->mregs, MUSB_DEVCTL, 0);
 		skip_session = 1;
@@ -277,10 +277,10 @@ static void otg_timer(unsigned long _musb)
 	case OTG_STATE_A_IDLE:
 	case OTG_STATE_B_IDLE:
 		if (devctl & MUSB_DEVCTL_BDEVICE) {
-			musb->xceiv->state = OTG_STATE_B_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 			MUSB_DEV_MODE(musb);
 		} else {
-			musb->xceiv->state = OTG_STATE_A_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 			MUSB_HST_MODE(musb);
 		}
 		if (!(devctl & MUSB_DEVCTL_SESSION) && !skip_session)
@@ -288,7 +288,7 @@ static void otg_timer(unsigned long _musb)
 		mod_timer(&glue->timer, jiffies + wrp->poll_seconds * HZ);
 		break;
 	case OTG_STATE_A_WAIT_VFALL:
-		musb->xceiv->state = OTG_STATE_A_WAIT_VRISE;
+		musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 		dsps_writel(musb->ctrl_base, wrp->coreintr_set,
 			    MUSB_INTR_VBUSERROR << wrp->usb_shift);
 		break;
@@ -373,26 +373,26 @@ static irqreturn_t dsps_interrupt(int irq, void *hci)
 			 * devctl.
 			 */
 			musb->int_usb &= ~MUSB_INTR_VBUSERROR;
-			musb->xceiv->state = OTG_STATE_A_WAIT_VFALL;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VFALL;
 			mod_timer(&glue->timer,
 					jiffies + wrp->poll_seconds * HZ);
 			WARNING("VBUS error workaround (delay coming)\n");
 		} else if (drvvbus) {
 			MUSB_HST_MODE(musb);
 			musb->xceiv->otg->default_a = 1;
-			musb->xceiv->state = OTG_STATE_A_WAIT_VRISE;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			del_timer(&glue->timer);
 		} else {
 			musb->is_active = 0;
 			MUSB_DEV_MODE(musb);
 			musb->xceiv->otg->default_a = 0;
-			musb->xceiv->state = OTG_STATE_B_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 		}
 
 		/* NOTE: this must complete power-on within 100 ms. */
 		dev_dbg(musb->controller, "VBUS %s (%s)%s, devctl %02x\n",
 				drvvbus ? "on" : "off",
-				usb_otg_state_string(musb->xceiv->state),
+				usb_otg_state_string(musb->xceiv->otg->state),
 				err ? " ERROR" : "",
 				devctl);
 		ret = IRQ_HANDLED;
@@ -402,7 +402,7 @@ static irqreturn_t dsps_interrupt(int irq, void *hci)
 		ret |= musb_interrupt(musb);
 
 	/* Poll for ID change in OTG port mode */
-	if (musb->xceiv->state == OTG_STATE_B_IDLE &&
+	if (musb->xceiv->otg->state == OTG_STATE_B_IDLE &&
 			musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE)
 		mod_timer(&glue->timer, jiffies + wrp->poll_seconds * HZ);
 out:
@@ -900,7 +900,7 @@ static int dsps_resume(struct device *dev)
 	dsps_writel(mbase, wrp->mode, glue->context.mode);
 	dsps_writel(mbase, wrp->tx_mode, glue->context.tx_mode);
 	dsps_writel(mbase, wrp->rx_mode, glue->context.rx_mode);
-	if (musb->xceiv->state == OTG_STATE_B_IDLE &&
+	if (musb->xceiv->otg->state == OTG_STATE_B_IDLE &&
 	    musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE)
 		mod_timer(&glue->timer, jiffies + wrp->poll_seconds * HZ);
 
diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c
index 4ab1896957e..56c31b769a5 100644
--- a/drivers/usb/musb/musb_gadget.c
+++ b/drivers/usb/musb/musb_gadget.c
@@ -1546,7 +1546,7 @@ static int musb_gadget_wakeup(struct usb_gadget *gadget)
 
 	spin_lock_irqsave(&musb->lock, flags);
 
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_B_PERIPHERAL:
 		/* NOTE:  OTG state machine doesn't include B_SUSPENDED;
 		 * that's part of the standard usb 1.1 state machine, and
@@ -1587,7 +1587,7 @@ static int musb_gadget_wakeup(struct usb_gadget *gadget)
 		goto done;
 	default:
 		dev_dbg(musb->controller, "Unhandled wake: %s\n",
-			usb_otg_state_string(musb->xceiv->state));
+			usb_otg_state_string(musb->xceiv->otg->state));
 		goto done;
 	}
 
@@ -1791,7 +1791,7 @@ int musb_gadget_setup(struct musb *musb)
 
 	MUSB_DEV_MODE(musb);
 	musb->xceiv->otg->default_a = 0;
-	musb->xceiv->state = OTG_STATE_B_IDLE;
+	musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 
 	/* this "gadget" abstracts/virtualizes the controller */
 	musb->g.name = musb_driver_name;
@@ -1857,7 +1857,7 @@ static int musb_gadget_start(struct usb_gadget *g,
 	musb->is_active = 1;
 
 	otg_set_peripheral(otg, &musb->g);
-	musb->xceiv->state = OTG_STATE_B_IDLE;
+	musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 	spin_unlock_irqrestore(&musb->lock, flags);
 
 	musb_start(musb);
@@ -1941,7 +1941,7 @@ static int musb_gadget_stop(struct usb_gadget *g)
 
 	(void) musb_gadget_vbus_draw(&musb->g, 0);
 
-	musb->xceiv->state = OTG_STATE_UNDEFINED;
+	musb->xceiv->otg->state = OTG_STATE_UNDEFINED;
 	stop_activity(musb, NULL);
 	otg_set_peripheral(musb->xceiv->otg, NULL);
 
@@ -1968,7 +1968,7 @@ static int musb_gadget_stop(struct usb_gadget *g)
 void musb_g_resume(struct musb *musb)
 {
 	musb->is_suspended = 0;
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_B_IDLE:
 		break;
 	case OTG_STATE_B_WAIT_ACON:
@@ -1982,7 +1982,7 @@ void musb_g_resume(struct musb *musb)
 		break;
 	default:
 		WARNING("unhandled RESUME transition (%s)\n",
-				usb_otg_state_string(musb->xceiv->state));
+				usb_otg_state_string(musb->xceiv->otg->state));
 	}
 }
 
@@ -1994,10 +1994,10 @@ void musb_g_suspend(struct musb *musb)
 	devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
 	dev_dbg(musb->controller, "devctl %02x\n", devctl);
 
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_B_IDLE:
 		if ((devctl & MUSB_DEVCTL_VBUS) == MUSB_DEVCTL_VBUS)
-			musb->xceiv->state = OTG_STATE_B_PERIPHERAL;
+			musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
 		break;
 	case OTG_STATE_B_PERIPHERAL:
 		musb->is_suspended = 1;
@@ -2012,7 +2012,7 @@ void musb_g_suspend(struct musb *musb)
 		 * A_PERIPHERAL may need care too
 		 */
 		WARNING("unhandled SUSPEND transition (%s)\n",
-				usb_otg_state_string(musb->xceiv->state));
+				usb_otg_state_string(musb->xceiv->otg->state));
 	}
 }
 
@@ -2043,22 +2043,22 @@ void musb_g_disconnect(struct musb *musb)
 		spin_lock(&musb->lock);
 	}
 
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	default:
 		dev_dbg(musb->controller, "Unhandled disconnect %s, setting a_idle\n",
-			usb_otg_state_string(musb->xceiv->state));
-		musb->xceiv->state = OTG_STATE_A_IDLE;
+			usb_otg_state_string(musb->xceiv->otg->state));
+		musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 		MUSB_HST_MODE(musb);
 		break;
 	case OTG_STATE_A_PERIPHERAL:
-		musb->xceiv->state = OTG_STATE_A_WAIT_BCON;
+		musb->xceiv->otg->state = OTG_STATE_A_WAIT_BCON;
 		MUSB_HST_MODE(musb);
 		break;
 	case OTG_STATE_B_WAIT_ACON:
 	case OTG_STATE_B_HOST:
 	case OTG_STATE_B_PERIPHERAL:
 	case OTG_STATE_B_IDLE:
-		musb->xceiv->state = OTG_STATE_B_IDLE;
+		musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 		break;
 	case OTG_STATE_B_SRP_INIT:
 		break;
@@ -2118,13 +2118,13 @@ __acquires(musb->lock)
 		 * In that case, do not rely on devctl for setting
 		 * peripheral mode.
 		 */
-		musb->xceiv->state = OTG_STATE_B_PERIPHERAL;
+		musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
 		musb->g.is_a_peripheral = 0;
 	} else if (devctl & MUSB_DEVCTL_BDEVICE) {
-		musb->xceiv->state = OTG_STATE_B_PERIPHERAL;
+		musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
 		musb->g.is_a_peripheral = 0;
 	} else {
-		musb->xceiv->state = OTG_STATE_A_PERIPHERAL;
+		musb->xceiv->otg->state = OTG_STATE_A_PERIPHERAL;
 		musb->g.is_a_peripheral = 1;
 	}
 
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 855793d701b..23d474d3d7f 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -2463,7 +2463,7 @@ static int musb_bus_suspend(struct usb_hcd *hcd)
 	if (!is_host_active(musb))
 		return 0;
 
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_A_SUSPEND:
 		return 0;
 	case OTG_STATE_A_WAIT_VRISE:
@@ -2473,7 +2473,7 @@ static int musb_bus_suspend(struct usb_hcd *hcd)
 		 */
 		devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
 		if ((devctl & MUSB_DEVCTL_VBUS) == MUSB_DEVCTL_VBUS)
-			musb->xceiv->state = OTG_STATE_A_WAIT_BCON;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_BCON;
 		break;
 	default:
 		break;
@@ -2481,7 +2481,7 @@ static int musb_bus_suspend(struct usb_hcd *hcd)
 
 	if (musb->is_active) {
 		WARNING("trying to suspend as %s while active\n",
-				usb_otg_state_string(musb->xceiv->state));
+				usb_otg_state_string(musb->xceiv->otg->state));
 		return -EBUSY;
 	} else
 		return 0;
@@ -2678,7 +2678,7 @@ int musb_host_setup(struct musb *musb, int power_budget)
 
 	MUSB_HST_MODE(musb);
 	musb->xceiv->otg->default_a = 1;
-	musb->xceiv->state = OTG_STATE_A_IDLE;
+	musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 
 	otg_set_host(musb->xceiv->otg, &hcd->self);
 	hcd->self.otg_port = 1;
diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c
index e2d2d8c9891..a133bd8c5dc 100644
--- a/drivers/usb/musb/musb_virthub.c
+++ b/drivers/usb/musb/musb_virthub.c
@@ -69,7 +69,7 @@ void musb_host_finish_resume(struct work_struct *work)
 	musb->port1_status |= USB_PORT_STAT_C_SUSPEND << 16;
 	usb_hcd_poll_rh_status(musb->hcd);
 	/* NOTE: it might really be A_WAIT_BCON ... */
-	musb->xceiv->state = OTG_STATE_A_HOST;
+	musb->xceiv->otg->state = OTG_STATE_A_HOST;
 
 	spin_unlock_irqrestore(&musb->lock, flags);
 }
@@ -107,9 +107,9 @@ void musb_port_suspend(struct musb *musb, bool do_suspend)
 		dev_dbg(musb->controller, "Root port suspended, power %02x\n", power);
 
 		musb->port1_status |= USB_PORT_STAT_SUSPEND;
-		switch (musb->xceiv->state) {
+		switch (musb->xceiv->otg->state) {
 		case OTG_STATE_A_HOST:
-			musb->xceiv->state = OTG_STATE_A_SUSPEND;
+			musb->xceiv->otg->state = OTG_STATE_A_SUSPEND;
 			musb->is_active = otg->host->b_hnp_enable;
 			if (musb->is_active)
 				mod_timer(&musb->otg_timer, jiffies
@@ -118,13 +118,13 @@ void musb_port_suspend(struct musb *musb, bool do_suspend)
 			musb_platform_try_idle(musb, 0);
 			break;
 		case OTG_STATE_B_HOST:
-			musb->xceiv->state = OTG_STATE_B_WAIT_ACON;
+			musb->xceiv->otg->state = OTG_STATE_B_WAIT_ACON;
 			musb->is_active = otg->host->b_hnp_enable;
 			musb_platform_try_idle(musb, 0);
 			break;
 		default:
 			dev_dbg(musb->controller, "bogus rh suspend? %s\n",
-				usb_otg_state_string(musb->xceiv->state));
+				usb_otg_state_string(musb->xceiv->otg->state));
 		}
 	} else if (power & MUSB_POWER_SUSPENDM) {
 		power &= ~MUSB_POWER_SUSPENDM;
@@ -145,7 +145,7 @@ void musb_port_reset(struct musb *musb, bool do_reset)
 	u8		power;
 	void __iomem	*mbase = musb->mregs;
 
-	if (musb->xceiv->state == OTG_STATE_B_IDLE) {
+	if (musb->xceiv->otg->state == OTG_STATE_B_IDLE) {
 		dev_dbg(musb->controller, "HNP: Returning from HNP; no hub reset from b_idle\n");
 		musb->port1_status &= ~USB_PORT_STAT_RESET;
 		return;
@@ -224,24 +224,24 @@ void musb_root_disconnect(struct musb *musb)
 	usb_hcd_poll_rh_status(musb->hcd);
 	musb->is_active = 0;
 
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_A_SUSPEND:
 		if (otg->host->b_hnp_enable) {
-			musb->xceiv->state = OTG_STATE_A_PERIPHERAL;
+			musb->xceiv->otg->state = OTG_STATE_A_PERIPHERAL;
 			musb->g.is_a_peripheral = 1;
 			break;
 		}
 		/* FALLTHROUGH */
 	case OTG_STATE_A_HOST:
-		musb->xceiv->state = OTG_STATE_A_WAIT_BCON;
+		musb->xceiv->otg->state = OTG_STATE_A_WAIT_BCON;
 		musb->is_active = 0;
 		break;
 	case OTG_STATE_A_WAIT_VFALL:
-		musb->xceiv->state = OTG_STATE_B_IDLE;
+		musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 		break;
 	default:
 		dev_dbg(musb->controller, "host disconnect (%s)\n",
-			usb_otg_state_string(musb->xceiv->state));
+			usb_otg_state_string(musb->xceiv->otg->state));
 	}
 }
 
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index 20fc2a532a2..763649eb498 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -65,15 +65,15 @@ static void musb_do_idle(unsigned long _musb)
 
 	spin_lock_irqsave(&musb->lock, flags);
 
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_A_WAIT_BCON:
 
 		devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
 		if (devctl & MUSB_DEVCTL_BDEVICE) {
-			musb->xceiv->state = OTG_STATE_B_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 			MUSB_DEV_MODE(musb);
 		} else {
-			musb->xceiv->state = OTG_STATE_A_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 			MUSB_HST_MODE(musb);
 		}
 		break;
@@ -90,15 +90,15 @@ static void musb_do_idle(unsigned long _musb)
 			musb->port1_status |= USB_PORT_STAT_C_SUSPEND << 16;
 			usb_hcd_poll_rh_status(musb->hcd);
 			/* NOTE: it might really be A_WAIT_BCON ... */
-			musb->xceiv->state = OTG_STATE_A_HOST;
+			musb->xceiv->otg->state = OTG_STATE_A_HOST;
 		}
 		break;
 	case OTG_STATE_A_HOST:
 		devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
 		if (devctl &  MUSB_DEVCTL_BDEVICE)
-			musb->xceiv->state = OTG_STATE_B_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 		else
-			musb->xceiv->state = OTG_STATE_A_WAIT_BCON;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_BCON;
 	default:
 		break;
 	}
@@ -116,9 +116,9 @@ static void omap2430_musb_try_idle(struct musb *musb, unsigned long timeout)
 
 	/* Never idle if active, or when VBUS timeout is not set as host */
 	if (musb->is_active || ((musb->a_wait_bcon == 0)
-			&& (musb->xceiv->state == OTG_STATE_A_WAIT_BCON))) {
+			&& (musb->xceiv->otg->state == OTG_STATE_A_WAIT_BCON))) {
 		dev_dbg(musb->controller, "%s active, deleting timer\n",
-			usb_otg_state_string(musb->xceiv->state));
+			usb_otg_state_string(musb->xceiv->otg->state));
 		del_timer(&musb_idle_timer);
 		last_timer = jiffies;
 		return;
@@ -135,7 +135,7 @@ static void omap2430_musb_try_idle(struct musb *musb, unsigned long timeout)
 	last_timer = timeout;
 
 	dev_dbg(musb->controller, "%s inactive, for idle timer for %lu ms\n",
-		usb_otg_state_string(musb->xceiv->state),
+		usb_otg_state_string(musb->xceiv->otg->state),
 		(unsigned long)jiffies_to_msecs(timeout - jiffies));
 	mod_timer(&musb_idle_timer, timeout);
 }
@@ -153,7 +153,7 @@ static void omap2430_musb_set_vbus(struct musb *musb, int is_on)
 	devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
 
 	if (is_on) {
-		if (musb->xceiv->state == OTG_STATE_A_IDLE) {
+		if (musb->xceiv->otg->state == OTG_STATE_A_IDLE) {
 			int loops = 100;
 			/* start the session */
 			devctl |= MUSB_DEVCTL_SESSION;
@@ -180,7 +180,7 @@ static void omap2430_musb_set_vbus(struct musb *musb, int is_on)
 		} else {
 			musb->is_active = 1;
 			otg->default_a = 1;
-			musb->xceiv->state = OTG_STATE_A_WAIT_VRISE;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			devctl |= MUSB_DEVCTL_SESSION;
 			MUSB_HST_MODE(musb);
 		}
@@ -192,7 +192,7 @@ static void omap2430_musb_set_vbus(struct musb *musb, int is_on)
 		 */
 
 		otg->default_a = 0;
-		musb->xceiv->state = OTG_STATE_B_IDLE;
+		musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 		devctl &= ~MUSB_DEVCTL_SESSION;
 
 		MUSB_DEV_MODE(musb);
@@ -201,7 +201,7 @@ static void omap2430_musb_set_vbus(struct musb *musb, int is_on)
 
 	dev_dbg(musb->controller, "VBUS %s, devctl %02x "
 		/* otg %3x conf %08x prcm %08x */ "\n",
-		usb_otg_state_string(musb->xceiv->state),
+		usb_otg_state_string(musb->xceiv->otg->state),
 		musb_readb(musb->mregs, MUSB_DEVCTL));
 }
 
@@ -266,7 +266,7 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
 		dev_dbg(dev, "ID GND\n");
 
 		otg->default_a = true;
-		musb->xceiv->state = OTG_STATE_A_IDLE;
+		musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 		musb->xceiv->last_event = USB_EVENT_ID;
 		if (musb->gadget_driver) {
 			pm_runtime_get_sync(dev);
@@ -280,7 +280,7 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue)
 		dev_dbg(dev, "VBUS Connect\n");
 
 		otg->default_a = false;
-		musb->xceiv->state = OTG_STATE_B_IDLE;
+		musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 		musb->xceiv->last_event = USB_EVENT_VBUS;
 		if (musb->gadget_driver)
 			pm_runtime_get_sync(dev);
diff --git a/drivers/usb/musb/tusb6010.c b/drivers/usb/musb/tusb6010.c
index 25f02dfc895..69ca92d6032 100644
--- a/drivers/usb/musb/tusb6010.c
+++ b/drivers/usb/musb/tusb6010.c
@@ -415,13 +415,13 @@ static void musb_do_idle(unsigned long _musb)
 
 	spin_lock_irqsave(&musb->lock, flags);
 
-	switch (musb->xceiv->state) {
+	switch (musb->xceiv->otg->state) {
 	case OTG_STATE_A_WAIT_BCON:
 		if ((musb->a_wait_bcon != 0)
 			&& (musb->idle_timeout == 0
 				|| time_after(jiffies, musb->idle_timeout))) {
 			dev_dbg(musb->controller, "Nothing connected %s, turning off VBUS\n",
-					usb_otg_state_string(musb->xceiv->state));
+					usb_otg_state_string(musb->xceiv->otg->state));
 		}
 		/* FALLTHROUGH */
 	case OTG_STATE_A_IDLE:
@@ -474,9 +474,9 @@ static void tusb_musb_try_idle(struct musb *musb, unsigned long timeout)
 
 	/* Never idle if active, or when VBUS timeout is not set as host */
 	if (musb->is_active || ((musb->a_wait_bcon == 0)
-			&& (musb->xceiv->state == OTG_STATE_A_WAIT_BCON))) {
+			&& (musb->xceiv->otg->state == OTG_STATE_A_WAIT_BCON))) {
 		dev_dbg(musb->controller, "%s active, deleting timer\n",
-			usb_otg_state_string(musb->xceiv->state));
+			usb_otg_state_string(musb->xceiv->otg->state));
 		del_timer(&musb_idle_timer);
 		last_timer = jiffies;
 		return;
@@ -493,7 +493,7 @@ static void tusb_musb_try_idle(struct musb *musb, unsigned long timeout)
 	last_timer = timeout;
 
 	dev_dbg(musb->controller, "%s inactive, for idle timer for %lu ms\n",
-		usb_otg_state_string(musb->xceiv->state),
+		usb_otg_state_string(musb->xceiv->otg->state),
 		(unsigned long)jiffies_to_msecs(timeout - jiffies));
 	mod_timer(&musb_idle_timer, timeout);
 }
@@ -524,7 +524,7 @@ static void tusb_musb_set_vbus(struct musb *musb, int is_on)
 	if (is_on) {
 		timer = OTG_TIMER_MS(OTG_TIME_A_WAIT_VRISE);
 		otg->default_a = 1;
-		musb->xceiv->state = OTG_STATE_A_WAIT_VRISE;
+		musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 		devctl |= MUSB_DEVCTL_SESSION;
 
 		conf |= TUSB_DEV_CONF_USB_HOST_MODE;
@@ -537,16 +537,16 @@ static void tusb_musb_set_vbus(struct musb *musb, int is_on)
 		/* If ID pin is grounded, we want to be a_idle */
 		otg_stat = musb_readl(tbase, TUSB_DEV_OTG_STAT);
 		if (!(otg_stat & TUSB_DEV_OTG_STAT_ID_STATUS)) {
-			switch (musb->xceiv->state) {
+			switch (musb->xceiv->otg->state) {
 			case OTG_STATE_A_WAIT_VRISE:
 			case OTG_STATE_A_WAIT_BCON:
-				musb->xceiv->state = OTG_STATE_A_WAIT_VFALL;
+				musb->xceiv->otg->state = OTG_STATE_A_WAIT_VFALL;
 				break;
 			case OTG_STATE_A_WAIT_VFALL:
-				musb->xceiv->state = OTG_STATE_A_IDLE;
+				musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 				break;
 			default:
-				musb->xceiv->state = OTG_STATE_A_IDLE;
+				musb->xceiv->otg->state = OTG_STATE_A_IDLE;
 			}
 			musb->is_active = 0;
 			otg->default_a = 1;
@@ -554,7 +554,7 @@ static void tusb_musb_set_vbus(struct musb *musb, int is_on)
 		} else {
 			musb->is_active = 0;
 			otg->default_a = 0;
-			musb->xceiv->state = OTG_STATE_B_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 			MUSB_DEV_MODE(musb);
 		}
 
@@ -569,7 +569,7 @@ static void tusb_musb_set_vbus(struct musb *musb, int is_on)
 	musb_writeb(musb->mregs, MUSB_DEVCTL, devctl);
 
 	dev_dbg(musb->controller, "VBUS %s, devctl %02x otg %3x conf %08x prcm %08x\n",
-		usb_otg_state_string(musb->xceiv->state),
+		usb_otg_state_string(musb->xceiv->otg->state),
 		musb_readb(musb->mregs, MUSB_DEVCTL),
 		musb_readl(tbase, TUSB_DEV_OTG_STAT),
 		conf, prcm);
@@ -668,23 +668,23 @@ tusb_otg_ints(struct musb *musb, u32 int_src, void __iomem *tbase)
 
 			if (otg_stat & TUSB_DEV_OTG_STAT_SESS_END) {
 				dev_dbg(musb->controller, "Forcing disconnect (no interrupt)\n");
-				if (musb->xceiv->state != OTG_STATE_B_IDLE) {
+				if (musb->xceiv->otg->state != OTG_STATE_B_IDLE) {
 					/* INTR_DISCONNECT can hide... */
-					musb->xceiv->state = OTG_STATE_B_IDLE;
+					musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 					musb->int_usb |= MUSB_INTR_DISCONNECT;
 				}
 				musb->is_active = 0;
 			}
 			dev_dbg(musb->controller, "vbus change, %s, otg %03x\n",
-				usb_otg_state_string(musb->xceiv->state), otg_stat);
+				usb_otg_state_string(musb->xceiv->otg->state), otg_stat);
 			idle_timeout = jiffies + (1 * HZ);
 			schedule_work(&musb->irq_work);
 
 		} else /* A-dev state machine */ {
 			dev_dbg(musb->controller, "vbus change, %s, otg %03x\n",
-				usb_otg_state_string(musb->xceiv->state), otg_stat);
+				usb_otg_state_string(musb->xceiv->otg->state), otg_stat);
 
-			switch (musb->xceiv->state) {
+			switch (musb->xceiv->otg->state) {
 			case OTG_STATE_A_IDLE:
 				dev_dbg(musb->controller, "Got SRP, turning on VBUS\n");
 				musb_platform_set_vbus(musb, 1);
@@ -731,9 +731,9 @@ tusb_otg_ints(struct musb *musb, u32 int_src, void __iomem *tbase)
 		u8	devctl;
 
 		dev_dbg(musb->controller, "%s timer, %03x\n",
-			usb_otg_state_string(musb->xceiv->state), otg_stat);
+			usb_otg_state_string(musb->xceiv->otg->state), otg_stat);
 
-		switch (musb->xceiv->state) {
+		switch (musb->xceiv->otg->state) {
 		case OTG_STATE_A_WAIT_VRISE:
 			/* VBUS has probably been valid for a while now,
 			 * but may well have bounced out of range a bit
@@ -745,7 +745,7 @@ tusb_otg_ints(struct musb *musb, u32 int_src, void __iomem *tbase)
 					dev_dbg(musb->controller, "devctl %02x\n", devctl);
 					break;
 				}
-				musb->xceiv->state = OTG_STATE_A_WAIT_BCON;
+				musb->xceiv->otg->state = OTG_STATE_A_WAIT_BCON;
 				musb->is_active = 0;
 				idle_timeout = jiffies
 					+ msecs_to_jiffies(musb->a_wait_bcon);
diff --git a/drivers/usb/musb/ux500.c b/drivers/usb/musb/ux500.c
index d0180a70051..1d631d5f4a2 100644
--- a/drivers/usb/musb/ux500.c
+++ b/drivers/usb/musb/ux500.c
@@ -56,7 +56,7 @@ static void ux500_musb_set_vbus(struct musb *musb, int is_on)
 	devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
 
 	if (is_on) {
-		if (musb->xceiv->state == OTG_STATE_A_IDLE) {
+		if (musb->xceiv->otg->state == OTG_STATE_A_IDLE) {
 			/* start the session */
 			devctl |= MUSB_DEVCTL_SESSION;
 			musb_writeb(musb->mregs, MUSB_DEVCTL, devctl);
@@ -76,7 +76,7 @@ static void ux500_musb_set_vbus(struct musb *musb, int is_on)
 		} else {
 			musb->is_active = 1;
 			musb->xceiv->otg->default_a = 1;
-			musb->xceiv->state = OTG_STATE_A_WAIT_VRISE;
+			musb->xceiv->otg->state = OTG_STATE_A_WAIT_VRISE;
 			devctl |= MUSB_DEVCTL_SESSION;
 			MUSB_HST_MODE(musb);
 		}
@@ -102,7 +102,7 @@ static void ux500_musb_set_vbus(struct musb *musb, int is_on)
 		mdelay(200);
 
 	dev_dbg(musb->controller, "VBUS %s, devctl %02x\n",
-		usb_otg_state_string(musb->xceiv->state),
+		usb_otg_state_string(musb->xceiv->otg->state),
 		musb_readb(musb->mregs, MUSB_DEVCTL));
 }
 
@@ -112,7 +112,7 @@ static int musb_otg_notifications(struct notifier_block *nb,
 	struct musb *musb = container_of(nb, struct musb, nb);
 
 	dev_dbg(musb->controller, "musb_otg_notifications %ld %s\n",
-			event, usb_otg_state_string(musb->xceiv->state));
+			event, usb_otg_state_string(musb->xceiv->otg->state));
 
 	switch (event) {
 	case UX500_MUSB_ID:
@@ -127,7 +127,7 @@ static int musb_otg_notifications(struct notifier_block *nb,
 		if (is_host_active(musb))
 			ux500_musb_set_vbus(musb, 0);
 		else
-			musb->xceiv->state = OTG_STATE_B_IDLE;
+			musb->xceiv->otg->state = OTG_STATE_B_IDLE;
 		break;
 	default:
 		dev_dbg(musb->controller, "ID float\n");
diff --git a/drivers/usb/phy/phy-ab8500-usb.c b/drivers/usb/phy/phy-ab8500-usb.c
index 11ab2c45e46..2d5250143ce 100644
--- a/drivers/usb/phy/phy-ab8500-usb.c
+++ b/drivers/usb/phy/phy-ab8500-usb.c
@@ -446,7 +446,7 @@ static int ab9540_usb_link_status_update(struct ab8500_usb *ab,
 		if (event != UX500_MUSB_RIDB)
 			event = UX500_MUSB_NONE;
 		/* Fallback to default B_IDLE as nothing is connected. */
-		ab->phy.state = OTG_STATE_B_IDLE;
+		ab->phy.otg->state = OTG_STATE_B_IDLE;
 		break;
 
 	case USB_LINK_ACA_RID_C_NM_9540:
@@ -584,7 +584,7 @@ static int ab8540_usb_link_status_update(struct ab8500_usb *ab,
 		 * Fallback to default B_IDLE as nothing
 		 * is connected
 		 */
-		ab->phy.state = OTG_STATE_B_IDLE;
+		ab->phy.otg->state = OTG_STATE_B_IDLE;
 		break;
 
 	case USB_LINK_ACA_RID_C_NM_8540:
@@ -693,7 +693,7 @@ static int ab8505_usb_link_status_update(struct ab8500_usb *ab,
 		 * Fallback to default B_IDLE as nothing
 		 * is connected
 		 */
-		ab->phy.state = OTG_STATE_B_IDLE;
+		ab->phy.otg->state = OTG_STATE_B_IDLE;
 		break;
 
 	case USB_LINK_ACA_RID_C_NM_8505:
@@ -776,7 +776,7 @@ static int ab8500_usb_link_status_update(struct ab8500_usb *ab,
 		if (event != UX500_MUSB_RIDB)
 			event = UX500_MUSB_NONE;
 		/* Fallback to default B_IDLE as nothing is connected */
-		ab->phy.state = OTG_STATE_B_IDLE;
+		ab->phy.otg->state = OTG_STATE_B_IDLE;
 		break;
 
 	case USB_LINK_ACA_RID_C_NM_8500:
@@ -1380,7 +1380,7 @@ static int ab8500_usb_probe(struct platform_device *pdev)
 	ab->phy.label		= "ab8500";
 	ab->phy.set_suspend	= ab8500_usb_set_suspend;
 	ab->phy.set_power	= ab8500_usb_set_power;
-	ab->phy.state		= OTG_STATE_UNDEFINED;
+	ab->phy.otg->state	= OTG_STATE_UNDEFINED;
 
 	otg->phy		= &ab->phy;
 	otg->set_host		= ab8500_usb_set_host;
diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c
index f1ea5990a50..15d7a81eece 100644
--- a/drivers/usb/phy/phy-fsl-usb.c
+++ b/drivers/usb/phy/phy-fsl-usb.c
@@ -623,7 +623,7 @@ static int fsl_otg_set_host(struct usb_otg *otg, struct usb_bus *host)
 			/* Mini-A cable connected */
 			struct otg_fsm *fsm = &otg_dev->fsm;
 
-			otg->phy->state = OTG_STATE_UNDEFINED;
+			otg.state = OTG_STATE_UNDEFINED;
 			fsm->protocol = PROTO_UNDEF;
 		}
 	}
@@ -681,7 +681,7 @@ static int fsl_otg_set_power(struct usb_phy *phy, unsigned mA)
 {
 	if (!fsl_otg_dev)
 		return -ENODEV;
-	if (phy->state == OTG_STATE_B_PERIPHERAL)
+	if (phy->otg.state == OTG_STATE_B_PERIPHERAL)
 		pr_info("FSL OTG: Draw %d mA\n", mA);
 
 	return 0;
@@ -714,7 +714,7 @@ static int fsl_otg_start_srp(struct usb_otg *otg)
 {
 	struct fsl_otg *otg_dev;
 
-	if (!otg || otg->phy->state != OTG_STATE_B_IDLE)
+	if (!otg || otg.state != OTG_STATE_B_IDLE)
 		return -ENODEV;
 
 	otg_dev = container_of(otg->phy, struct fsl_otg, phy);
@@ -989,10 +989,10 @@ int usb_otg_start(struct platform_device *pdev)
 	 * Also: record initial state of ID pin
 	 */
 	if (fsl_readl(&p_otg->dr_mem_map->otgsc) & OTGSC_STS_USB_ID) {
-		p_otg->phy.state = OTG_STATE_UNDEFINED;
+		p_otg->phy->otg.state = OTG_STATE_UNDEFINED;
 		p_otg->fsm.id = 1;
 	} else {
-		p_otg->phy.state = OTG_STATE_A_IDLE;
+		p_otg->phy->otg.state = OTG_STATE_A_IDLE;
 		p_otg->fsm.id = 0;
 	}
 
diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c
index 7594e5069ae..280a3458ff6 100644
--- a/drivers/usb/phy/phy-generic.c
+++ b/drivers/usb/phy/phy-generic.c
@@ -123,7 +123,7 @@ static int nop_set_peripheral(struct usb_otg *otg, struct usb_gadget *gadget)
 	}
 
 	otg->gadget = gadget;
-	otg->phy->state = OTG_STATE_B_IDLE;
+	otg->state = OTG_STATE_B_IDLE;
 	return 0;
 }
 
@@ -225,9 +225,9 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop,
 	nop->phy.dev		= nop->dev;
 	nop->phy.label		= "nop-xceiv";
 	nop->phy.set_suspend	= nop_set_suspend;
-	nop->phy.state		= OTG_STATE_UNDEFINED;
 	nop->phy.type		= type;
 
+	nop->phy.otg->state		= OTG_STATE_UNDEFINED;
 	nop->phy.otg->phy		= &nop->phy;
 	nop->phy.otg->set_host		= nop_set_host;
 	nop->phy.otg->set_peripheral	= nop_set_peripheral;
diff --git a/drivers/usb/phy/phy-gpio-vbus-usb.c b/drivers/usb/phy/phy-gpio-vbus-usb.c
index f4b14bd97e1..7a6be3e5dc2 100644
--- a/drivers/usb/phy/phy-gpio-vbus-usb.c
+++ b/drivers/usb/phy/phy-gpio-vbus-usb.c
@@ -121,7 +121,7 @@ static void gpio_vbus_work(struct work_struct *work)
 
 	if (vbus) {
 		status = USB_EVENT_VBUS;
-		gpio_vbus->phy.state = OTG_STATE_B_PERIPHERAL;
+		gpio_vbus->phy.otg->state = OTG_STATE_B_PERIPHERAL;
 		gpio_vbus->phy.last_event = status;
 		usb_gadget_vbus_connect(gpio_vbus->phy.otg->gadget);
 
@@ -143,7 +143,7 @@ static void gpio_vbus_work(struct work_struct *work)
 
 		usb_gadget_vbus_disconnect(gpio_vbus->phy.otg->gadget);
 		status = USB_EVENT_NONE;
-		gpio_vbus->phy.state = OTG_STATE_B_IDLE;
+		gpio_vbus->phy.otg->state = OTG_STATE_B_IDLE;
 		gpio_vbus->phy.last_event = status;
 
 		atomic_notifier_call_chain(&gpio_vbus->phy.notifier,
@@ -196,7 +196,7 @@ static int gpio_vbus_set_peripheral(struct usb_otg *otg,
 		set_vbus_draw(gpio_vbus, 0);
 
 		usb_gadget_vbus_disconnect(otg->gadget);
-		otg->phy->state = OTG_STATE_UNDEFINED;
+		otg->state = OTG_STATE_UNDEFINED;
 
 		otg->gadget = NULL;
 		return 0;
@@ -218,7 +218,7 @@ static int gpio_vbus_set_power(struct usb_phy *phy, unsigned mA)
 
 	gpio_vbus = container_of(phy, struct gpio_vbus_data, phy);
 
-	if (phy->state == OTG_STATE_B_PERIPHERAL)
+	if (phy->otg->state == OTG_STATE_B_PERIPHERAL)
 		set_vbus_draw(gpio_vbus, mA);
 	return 0;
 }
@@ -269,8 +269,8 @@ static int gpio_vbus_probe(struct platform_device *pdev)
 	gpio_vbus->phy.dev = gpio_vbus->dev;
 	gpio_vbus->phy.set_power = gpio_vbus_set_power;
 	gpio_vbus->phy.set_suspend = gpio_vbus_set_suspend;
-	gpio_vbus->phy.state = OTG_STATE_UNDEFINED;
 
+	gpio_vbus->phy.otg->state = OTG_STATE_UNDEFINED;
 	gpio_vbus->phy.otg->phy = &gpio_vbus->phy;
 	gpio_vbus->phy.otg->set_peripheral = gpio_vbus_set_peripheral;
 
diff --git a/drivers/usb/phy/phy-isp1301-omap.c b/drivers/usb/phy/phy-isp1301-omap.c
index 8eea56d3ded..24f84cbbed5 100644
--- a/drivers/usb/phy/phy-isp1301-omap.c
+++ b/drivers/usb/phy/phy-isp1301-omap.c
@@ -234,7 +234,7 @@ isp1301_clear_bits(struct isp1301 *isp, u8 reg, u8 bits)
 
 static inline const char *state_name(struct isp1301 *isp)
 {
-	return usb_otg_state_string(isp->phy.state);
+	return usb_otg_state_string(isp->phy.otg->state);
 }
 
 /*-------------------------------------------------------------------------*/
@@ -249,7 +249,7 @@ static inline const char *state_name(struct isp1301 *isp)
 
 static void power_down(struct isp1301 *isp)
 {
-	isp->phy.state = OTG_STATE_UNDEFINED;
+	isp->phy.otg->state = OTG_STATE_UNDEFINED;
 
 	// isp1301_set_bits(isp, ISP1301_MODE_CONTROL_2, MC2_GLOBAL_PWR_DN);
 	isp1301_set_bits(isp, ISP1301_MODE_CONTROL_1, MC1_SUSPEND);
@@ -339,7 +339,7 @@ static void a_idle(struct isp1301 *isp, const char *tag)
 {
 	u32 l;
 
-	if (isp->phy.state == OTG_STATE_A_IDLE)
+	if (isp->phy.otg->state == OTG_STATE_A_IDLE)
 		return;
 
 	isp->phy.otg->default_a = 1;
@@ -351,7 +351,7 @@ static void a_idle(struct isp1301 *isp, const char *tag)
 		isp->phy.otg->gadget->is_a_peripheral = 1;
 		gadget_suspend(isp);
 	}
-	isp->phy.state = OTG_STATE_A_IDLE;
+	isp->phy.otg->state = OTG_STATE_A_IDLE;
 	l = omap_readl(OTG_CTRL) & OTG_XCEIV_OUTPUTS;
 	omap_writel(l, OTG_CTRL);
 	isp->last_otg_ctrl = l;
@@ -363,7 +363,7 @@ static void b_idle(struct isp1301 *isp, const char *tag)
 {
 	u32 l;
 
-	if (isp->phy.state == OTG_STATE_B_IDLE)
+	if (isp->phy.otg->state == OTG_STATE_B_IDLE)
 		return;
 
 	isp->phy.otg->default_a = 0;
@@ -375,7 +375,7 @@ static void b_idle(struct isp1301 *isp, const char *tag)
 		isp->phy.otg->gadget->is_a_peripheral = 0;
 		gadget_suspend(isp);
 	}
-	isp->phy.state = OTG_STATE_B_IDLE;
+	isp->phy.otg->state = OTG_STATE_B_IDLE;
 	l = omap_readl(OTG_CTRL) & OTG_XCEIV_OUTPUTS;
 	omap_writel(l, OTG_CTRL);
 	isp->last_otg_ctrl = l;
@@ -474,7 +474,7 @@ static void check_state(struct isp1301 *isp, const char *tag)
 	default:
 		break;
 	}
-	if (isp->phy.state == state && !extra)
+	if (isp->phy.otg->state == state && !extra)
 		return;
 	pr_debug("otg: %s FSM %s/%02x, %s, %06x\n", tag,
 		usb_otg_state_string(state), fsm, state_name(isp),
@@ -498,23 +498,23 @@ static void update_otg1(struct isp1301 *isp, u8 int_src)
 
 	if (int_src & INTR_SESS_VLD)
 		otg_ctrl |= OTG_ASESSVLD;
-	else if (isp->phy.state == OTG_STATE_A_WAIT_VFALL) {
+	else if (isp->phy.otg->state == OTG_STATE_A_WAIT_VFALL) {
 		a_idle(isp, "vfall");
 		otg_ctrl &= ~OTG_CTRL_BITS;
 	}
 	if (int_src & INTR_VBUS_VLD)
 		otg_ctrl |= OTG_VBUSVLD;
 	if (int_src & INTR_ID_GND) {		/* default-A */
-		if (isp->phy.state == OTG_STATE_B_IDLE
-				|| isp->phy.state
+		if (isp->phy.otg->state == OTG_STATE_B_IDLE
+				|| isp->phy.otg->state
 					== OTG_STATE_UNDEFINED) {
 			a_idle(isp, "init");
 			return;
 		}
 	} else {				/* default-B */
 		otg_ctrl |= OTG_ID;
-		if (isp->phy.state == OTG_STATE_A_IDLE
-			|| isp->phy.state == OTG_STATE_UNDEFINED) {
+		if (isp->phy.otg->state == OTG_STATE_A_IDLE
+			|| isp->phy.otg->state == OTG_STATE_UNDEFINED) {
 			b_idle(isp, "init");
 			return;
 		}
@@ -548,14 +548,14 @@ static void otg_update_isp(struct isp1301 *isp)
 	isp->last_otg_ctrl = otg_ctrl;
 	otg_ctrl = otg_ctrl & OTG_XCEIV_INPUTS;
 
-	switch (isp->phy.state) {
+	switch (isp->phy.otg->state) {
 	case OTG_STATE_B_IDLE:
 	case OTG_STATE_B_PERIPHERAL:
 	case OTG_STATE_B_SRP_INIT:
 		if (!(otg_ctrl & OTG_PULLUP)) {
 			// if (otg_ctrl & OTG_B_HNPEN) {
 			if (isp->phy.otg->gadget->b_hnp_enable) {
-				isp->phy.state = OTG_STATE_B_WAIT_ACON;
+				isp->phy.otg->state = OTG_STATE_B_WAIT_ACON;
 				pr_debug("  --> b_wait_acon\n");
 			}
 			goto pulldown;
@@ -585,7 +585,7 @@ pulldown:
 	if (!(isp->phy.otg->host))
 		otg_ctrl &= ~OTG_DRV_VBUS;
 
-	switch (isp->phy.state) {
+	switch (isp->phy.otg->state) {
 	case OTG_STATE_A_SUSPEND:
 		if (otg_ctrl & OTG_DRV_VBUS) {
 			set |= OTG1_VBUS_DRV;
@@ -596,7 +596,7 @@ pulldown:
 
 		/* FALLTHROUGH */
 	case OTG_STATE_A_VBUS_ERR:
-		isp->phy.state = OTG_STATE_A_WAIT_VFALL;
+		isp->phy.otg->state = OTG_STATE_A_WAIT_VFALL;
 		pr_debug("  --> a_wait_vfall\n");
 		/* FALLTHROUGH */
 	case OTG_STATE_A_WAIT_VFALL:
@@ -605,7 +605,7 @@ pulldown:
 		break;
 	case OTG_STATE_A_IDLE:
 		if (otg_ctrl & OTG_DRV_VBUS) {
-			isp->phy.state = OTG_STATE_A_WAIT_VRISE;
+			isp->phy.otg->state = OTG_STATE_A_WAIT_VRISE;
 			pr_debug("  --> a_wait_vrise\n");
 		}
 		/* FALLTHROUGH */
@@ -625,17 +625,17 @@ pulldown:
 	if (otg_change & OTG_PULLUP) {
 		u32 l;
 
-		switch (isp->phy.state) {
+		switch (isp->phy.otg->state) {
 		case OTG_STATE_B_IDLE:
 			if (clr & OTG1_DP_PULLUP)
 				break;
-			isp->phy.state = OTG_STATE_B_PERIPHERAL;
+			isp->phy.otg->state = OTG_STATE_B_PERIPHERAL;
 			pr_debug("  --> b_peripheral\n");
 			break;
 		case OTG_STATE_A_SUSPEND:
 			if (clr & OTG1_DP_PULLUP)
 				break;
-			isp->phy.state = OTG_STATE_A_PERIPHERAL;
+			isp->phy.otg->state = OTG_STATE_A_PERIPHERAL;
 			pr_debug("  --> a_peripheral\n");
 			break;
 		default:
@@ -673,7 +673,7 @@ static irqreturn_t omap_otg_irq(int irq, void *_isp)
 		 * remote wakeup (SRP, normal) using their own timer
 		 * to give "check cable and A-device" messages.
 		 */
-		if (isp->phy.state == OTG_STATE_B_SRP_INIT)
+		if (isp->phy.otg->state == OTG_STATE_B_SRP_INIT)
 			b_idle(isp, "srp_timeout");
 
 		omap_writew(B_SRP_TMROUT, OTG_IRQ_SRC);
@@ -691,7 +691,7 @@ static irqreturn_t omap_otg_irq(int irq, void *_isp)
 		omap_writel(otg_ctrl, OTG_CTRL);
 
 		/* subset of b_peripheral()... */
-		isp->phy.state = OTG_STATE_B_PERIPHERAL;
+		isp->phy.otg->state = OTG_STATE_B_PERIPHERAL;
 		pr_debug("  --> b_peripheral\n");
 
 		omap_writew(B_HNP_FAIL, OTG_IRQ_SRC);
@@ -703,7 +703,7 @@ static irqreturn_t omap_otg_irq(int irq, void *_isp)
 				state_name(isp), omap_readl(OTG_CTRL));
 
 		isp1301_defer_work(isp, WORK_UPDATE_OTG);
-		switch (isp->phy.state) {
+		switch (isp->phy.otg->state) {
 		case OTG_STATE_A_IDLE:
 			if (!otg->host)
 				break;
@@ -734,7 +734,7 @@ static irqreturn_t omap_otg_irq(int irq, void *_isp)
 		otg_ctrl |= OTG_BUSDROP;
 		otg_ctrl &= ~OTG_A_BUSREQ & OTG_CTRL_MASK & ~OTG_XCEIV_INPUTS;
 		omap_writel(otg_ctrl, OTG_CTRL);
-		isp->phy.state = OTG_STATE_A_WAIT_VFALL;
+		isp->phy.otg->state = OTG_STATE_A_WAIT_VFALL;
 
 		omap_writew(A_REQ_TMROUT, OTG_IRQ_SRC);
 		ret = IRQ_HANDLED;
@@ -748,7 +748,7 @@ static irqreturn_t omap_otg_irq(int irq, void *_isp)
 		otg_ctrl |= OTG_BUSDROP;
 		otg_ctrl &= ~OTG_A_BUSREQ & OTG_CTRL_MASK & ~OTG_XCEIV_INPUTS;
 		omap_writel(otg_ctrl, OTG_CTRL);
-		isp->phy.state = OTG_STATE_A_VBUS_ERR;
+		isp->phy.otg->state = OTG_STATE_A_VBUS_ERR;
 
 		omap_writew(A_VBUS_ERR, OTG_IRQ_SRC);
 		ret = IRQ_HANDLED;
@@ -769,7 +769,7 @@ static irqreturn_t omap_otg_irq(int irq, void *_isp)
 
 		/* role is peripheral */
 		if (otg_ctrl & OTG_DRIVER_SEL) {
-			switch (isp->phy.state) {
+			switch (isp->phy.otg->state) {
 			case OTG_STATE_A_IDLE:
 				b_idle(isp, __func__);
 				break;
@@ -786,18 +786,18 @@ static irqreturn_t omap_otg_irq(int irq, void *_isp)
 			}
 
 			if (otg->host) {
-				switch (isp->phy.state) {
+				switch (isp->phy.otg->state) {
 				case OTG_STATE_B_WAIT_ACON:
-					isp->phy.state = OTG_STATE_B_HOST;
+					isp->phy.otg->state = OTG_STATE_B_HOST;
 					pr_debug("  --> b_host\n");
 					kick = 1;
 					break;
 				case OTG_STATE_A_WAIT_BCON:
-					isp->phy.state = OTG_STATE_A_HOST;
+					isp->phy.otg->state = OTG_STATE_A_HOST;
 					pr_debug("  --> a_host\n");
 					break;
 				case OTG_STATE_A_PERIPHERAL:
-					isp->phy.state = OTG_STATE_A_WAIT_BCON;
+					isp->phy.otg->state = OTG_STATE_A_WAIT_BCON;
 					pr_debug("  --> a_wait_bcon\n");
 					break;
 				default:
@@ -937,7 +937,7 @@ static void b_peripheral(struct isp1301 *isp)
 	/* UDC driver just set OTG_BSESSVLD */
 	isp1301_set_bits(isp, ISP1301_OTG_CONTROL_1, OTG1_DP_PULLUP);
 	isp1301_clear_bits(isp, ISP1301_OTG_CONTROL_1, OTG1_DP_PULLDOWN);
-	isp->phy.state = OTG_STATE_B_PERIPHERAL;
+	isp->phy.otg->state = OTG_STATE_B_PERIPHERAL;
 	pr_debug("  --> b_peripheral\n");
 	dump_regs(isp, "2periph");
 #endif
@@ -947,7 +947,7 @@ static void isp_update_otg(struct isp1301 *isp, u8 stat)
 {
 	struct usb_otg		*otg = isp->phy.otg;
 	u8			isp_stat, isp_bstat;
-	enum usb_otg_state	state = isp->phy.state;
+	enum usb_otg_state	state = isp->phy.otg->state;
 
 	if (stat & INTR_BDIS_ACON)
 		pr_debug("OTG:  BDIS_ACON, %s\n", state_name(isp));
@@ -970,7 +970,7 @@ static void isp_update_otg(struct isp1301 *isp, u8 stat)
 				 * when HNP is used.
 				 */
 				if (isp_stat & INTR_VBUS_VLD)
-					isp->phy.state = OTG_STATE_A_HOST;
+					isp->phy.otg->state = OTG_STATE_A_HOST;
 				break;
 			case OTG_STATE_A_WAIT_VFALL:
 				if (!(isp_stat & INTR_SESS_VLD))
@@ -978,7 +978,7 @@ static void isp_update_otg(struct isp1301 *isp, u8 stat)
 				break;
 			default:
 				if (!(isp_stat & INTR_VBUS_VLD))
-					isp->phy.state = OTG_STATE_A_VBUS_ERR;
+					isp->phy.otg->state = OTG_STATE_A_VBUS_ERR;
 				break;
 			}
 			isp_bstat = isp1301_get_u8(isp, ISP1301_OTG_STATUS);
@@ -1007,7 +1007,7 @@ static void isp_update_otg(struct isp1301 *isp, u8 stat)
 		if (otg->default_a) {
 			switch (state) {
 			default:
-				isp->phy.state = OTG_STATE_A_WAIT_VFALL;
+				isp->phy.otg->state = OTG_STATE_A_WAIT_VFALL;
 				break;
 			case OTG_STATE_A_WAIT_VFALL:
 				state = OTG_STATE_A_IDLE;
@@ -1020,7 +1020,7 @@ static void isp_update_otg(struct isp1301 *isp, u8 stat)
 				host_suspend(isp);
 				isp1301_clear_bits(isp, ISP1301_MODE_CONTROL_1,
 						MC1_BDIS_ACON_EN);
-				isp->phy.state = OTG_STATE_B_IDLE;
+				isp->phy.otg->state = OTG_STATE_B_IDLE;
 				l = omap_readl(OTG_CTRL) & OTG_CTRL_MASK;
 				l &= ~OTG_CTRL_BITS;
 				omap_writel(l, OTG_CTRL);
@@ -1031,7 +1031,7 @@ static void isp_update_otg(struct isp1301 *isp, u8 stat)
 		}
 		isp_bstat = isp1301_get_u8(isp, ISP1301_OTG_STATUS);
 
-		switch (isp->phy.state) {
+		switch (isp->phy.otg->state) {
 		case OTG_STATE_B_PERIPHERAL:
 		case OTG_STATE_B_WAIT_ACON:
 		case OTG_STATE_B_HOST:
@@ -1071,7 +1071,7 @@ static void isp_update_otg(struct isp1301 *isp, u8 stat)
 		}
 	}
 
-	if (state != isp->phy.state)
+	if (state != isp->phy.otg->state)
 		pr_debug("  isp, %s -> %s\n",
 				usb_otg_state_string(state), state_name(isp));
 
@@ -1129,10 +1129,10 @@ isp1301_work(struct work_struct *work)
 			 * skip A_WAIT_VRISE; hc transitions invisibly
 			 * skip A_WAIT_BCON; same.
 			 */
-			switch (isp->phy.state) {
+			switch (isp->phy.otg->state) {
 			case OTG_STATE_A_WAIT_BCON:
 			case OTG_STATE_A_WAIT_VRISE:
-				isp->phy.state = OTG_STATE_A_HOST;
+				isp->phy.otg->state = OTG_STATE_A_HOST;
 				pr_debug("  --> a_host\n");
 				otg_ctrl = omap_readl(OTG_CTRL);
 				otg_ctrl |= OTG_A_BUSREQ;
@@ -1141,7 +1141,7 @@ isp1301_work(struct work_struct *work)
 				omap_writel(otg_ctrl, OTG_CTRL);
 				break;
 			case OTG_STATE_B_WAIT_ACON:
-				isp->phy.state = OTG_STATE_B_HOST;
+				isp->phy.otg->state = OTG_STATE_B_HOST;
 				pr_debug("  --> b_host (acon)\n");
 				break;
 			case OTG_STATE_B_HOST:
@@ -1368,7 +1368,7 @@ isp1301_set_peripheral(struct usb_otg *otg, struct usb_gadget *gadget)
 	}
 
 	power_up(isp);
-	isp->phy.state = OTG_STATE_B_IDLE;
+	isp->phy.otg->state = OTG_STATE_B_IDLE;
 
 	if (machine_is_omap_h2() || machine_is_omap_h3())
 		isp1301_set_bits(isp, ISP1301_MODE_CONTROL_1, MC1_DAT_SE0);
@@ -1403,7 +1403,7 @@ isp1301_set_power(struct usb_phy *dev, unsigned mA)
 {
 	if (!the_transceiver)
 		return -ENODEV;
-	if (dev->state == OTG_STATE_B_PERIPHERAL)
+	if (dev->otg->state == OTG_STATE_B_PERIPHERAL)
 		enable_vbus_draw(the_transceiver, mA);
 	return 0;
 }
@@ -1414,7 +1414,7 @@ isp1301_start_srp(struct usb_otg *otg)
 	struct isp1301	*isp = container_of(otg->phy, struct isp1301, phy);
 	u32		otg_ctrl;
 
-	if (isp != the_transceiver || isp->phy.state != OTG_STATE_B_IDLE)
+	if (isp != the_transceiver || isp->phy.otg->state != OTG_STATE_B_IDLE)
 		return -ENODEV;
 
 	otg_ctrl = omap_readl(OTG_CTRL);
@@ -1424,7 +1424,7 @@ isp1301_start_srp(struct usb_otg *otg)
 	otg_ctrl |= OTG_B_BUSREQ;
 	otg_ctrl &= ~OTG_A_BUSREQ & OTG_CTRL_MASK;
 	omap_writel(otg_ctrl, OTG_CTRL);
-	isp->phy.state = OTG_STATE_B_SRP_INIT;
+	isp->phy.otg->state = OTG_STATE_B_SRP_INIT;
 
 	pr_debug("otg: SRP, %s ... %06x\n", state_name(isp),
 			omap_readl(OTG_CTRL));
@@ -1452,9 +1452,9 @@ isp1301_start_hnp(struct usb_otg *otg)
 	/* We want hardware to manage most HNP protocol timings.
 	 * So do this part as early as possible...
 	 */
-	switch (isp->phy.state) {
+	switch (isp->phy.otg->state) {
 	case OTG_STATE_B_HOST:
-		isp->phy.state = OTG_STATE_B_PERIPHERAL;
+		isp->phy.otg->state = OTG_STATE_B_PERIPHERAL;
 		/* caller will suspend next */
 		break;
 	case OTG_STATE_A_HOST:
diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c
index 471e69dbcca..18015b7c8af 100644
--- a/drivers/usb/phy/phy-msm-usb.c
+++ b/drivers/usb/phy/phy-msm-usb.c
@@ -721,11 +721,11 @@ static int msm_otg_set_host(struct usb_otg *otg, struct usb_bus *host)
 	}
 
 	if (!host) {
-		if (otg->phy->state == OTG_STATE_A_HOST) {
+		if (otg->state == OTG_STATE_A_HOST) {
 			pm_runtime_get_sync(otg->phy->dev);
 			msm_otg_start_host(otg->phy, 0);
 			otg->host = NULL;
-			otg->phy->state = OTG_STATE_UNDEFINED;
+			otg->state = OTG_STATE_UNDEFINED;
 			schedule_work(&motg->sm_work);
 		} else {
 			otg->host = NULL;
@@ -794,11 +794,11 @@ static int msm_otg_set_peripheral(struct usb_otg *otg,
 	}
 
 	if (!gadget) {
-		if (otg->phy->state == OTG_STATE_B_PERIPHERAL) {
+		if (otg->state == OTG_STATE_B_PERIPHERAL) {
 			pm_runtime_get_sync(otg->phy->dev);
 			msm_otg_start_peripheral(otg->phy, 0);
 			otg->gadget = NULL;
-			otg->phy->state = OTG_STATE_UNDEFINED;
+			otg->state = OTG_STATE_UNDEFINED;
 			schedule_work(&motg->sm_work);
 		} else {
 			otg->gadget = NULL;
@@ -1170,12 +1170,12 @@ static void msm_otg_sm_work(struct work_struct *w)
 	struct msm_otg *motg = container_of(w, struct msm_otg, sm_work);
 	struct usb_otg *otg = motg->phy.otg;
 
-	switch (otg->phy->state) {
+	switch (otg->state) {
 	case OTG_STATE_UNDEFINED:
 		dev_dbg(otg->phy->dev, "OTG_STATE_UNDEFINED state\n");
 		msm_otg_reset(otg->phy);
 		msm_otg_init_sm(motg);
-		otg->phy->state = OTG_STATE_B_IDLE;
+		otg->state = OTG_STATE_B_IDLE;
 		/* FALL THROUGH */
 	case OTG_STATE_B_IDLE:
 		dev_dbg(otg->phy->dev, "OTG_STATE_B_IDLE state\n");
@@ -1183,7 +1183,7 @@ static void msm_otg_sm_work(struct work_struct *w)
 			/* disable BSV bit */
 			writel(readl(USB_OTGSC) & ~OTGSC_BSVIE, USB_OTGSC);
 			msm_otg_start_host(otg->phy, 1);
-			otg->phy->state = OTG_STATE_A_HOST;
+			otg->state = OTG_STATE_A_HOST;
 		} else if (test_bit(B_SESS_VLD, &motg->inputs)) {
 			switch (motg->chg_state) {
 			case USB_CHG_STATE_UNDEFINED:
@@ -1199,13 +1199,13 @@ static void msm_otg_sm_work(struct work_struct *w)
 					msm_otg_notify_charger(motg,
 							IDEV_CHG_MAX);
 					msm_otg_start_peripheral(otg->phy, 1);
-					otg->phy->state
+					otg->state
 						= OTG_STATE_B_PERIPHERAL;
 					break;
 				case USB_SDP_CHARGER:
 					msm_otg_notify_charger(motg, IUNIT);
 					msm_otg_start_peripheral(otg->phy, 1);
-					otg->phy->state
+					otg->state
 						= OTG_STATE_B_PERIPHERAL;
 					break;
 				default:
@@ -1230,7 +1230,7 @@ static void msm_otg_sm_work(struct work_struct *w)
 			motg->chg_type = USB_INVALID_CHARGER;
 		}
 
-		if (otg->phy->state == OTG_STATE_B_IDLE)
+		if (otg->state == OTG_STATE_B_IDLE)
 			pm_runtime_put_sync(otg->phy->dev);
 		break;
 	case OTG_STATE_B_PERIPHERAL:
@@ -1241,7 +1241,7 @@ static void msm_otg_sm_work(struct work_struct *w)
 			msm_otg_start_peripheral(otg->phy, 0);
 			motg->chg_state = USB_CHG_STATE_UNDEFINED;
 			motg->chg_type = USB_INVALID_CHARGER;
-			otg->phy->state = OTG_STATE_B_IDLE;
+			otg->state = OTG_STATE_B_IDLE;
 			msm_otg_reset(otg->phy);
 			schedule_work(w);
 		}
@@ -1250,7 +1250,7 @@ static void msm_otg_sm_work(struct work_struct *w)
 		dev_dbg(otg->phy->dev, "OTG_STATE_A_HOST state\n");
 		if (test_bit(ID, &motg->inputs)) {
 			msm_otg_start_host(otg->phy, 0);
-			otg->phy->state = OTG_STATE_B_IDLE;
+			otg->state = OTG_STATE_B_IDLE;
 			msm_otg_reset(otg->phy);
 			schedule_work(w);
 		}
@@ -1303,7 +1303,7 @@ static int msm_otg_mode_show(struct seq_file *s, void *unused)
 	struct msm_otg *motg = s->private;
 	struct usb_otg *otg = motg->phy.otg;
 
-	switch (otg->phy->state) {
+	switch (otg->state) {
 	case OTG_STATE_A_HOST:
 		seq_puts(s, "host\n");
 		break;
@@ -1353,7 +1353,7 @@ static ssize_t msm_otg_mode_write(struct file *file, const char __user *ubuf,
 
 	switch (req_mode) {
 	case USB_DR_MODE_UNKNOWN:
-		switch (otg->phy->state) {
+		switch (otg->state) {
 		case OTG_STATE_A_HOST:
 		case OTG_STATE_B_PERIPHERAL:
 			set_bit(ID, &motg->inputs);
@@ -1364,7 +1364,7 @@ static ssize_t msm_otg_mode_write(struct file *file, const char __user *ubuf,
 		}
 		break;
 	case USB_DR_MODE_PERIPHERAL:
-		switch (otg->phy->state) {
+		switch (otg->state) {
 		case OTG_STATE_B_IDLE:
 		case OTG_STATE_A_HOST:
 			set_bit(ID, &motg->inputs);
@@ -1375,7 +1375,7 @@ static ssize_t msm_otg_mode_write(struct file *file, const char __user *ubuf,
 		}
 		break;
 	case USB_DR_MODE_HOST:
-		switch (otg->phy->state) {
+		switch (otg->state) {
 		case OTG_STATE_B_IDLE:
 		case OTG_STATE_B_PERIPHERAL:
 			clear_bit(ID, &motg->inputs);
@@ -1769,7 +1769,7 @@ static int msm_otg_runtime_idle(struct device *dev)
 	 * This 1 sec delay also prevents entering into LPM immediately
 	 * after asynchronous interrupt.
 	 */
-	if (otg->phy->state != OTG_STATE_UNDEFINED)
+	if (otg->state != OTG_STATE_UNDEFINED)
 		pm_schedule_suspend(dev, 1000);
 
 	return -EAGAIN;
diff --git a/drivers/usb/phy/phy-mv-usb.c b/drivers/usb/phy/phy-mv-usb.c
index c9517d8bda8..ee87aa7144d 100644
--- a/drivers/usb/phy/phy-mv-usb.c
+++ b/drivers/usb/phy/phy-mv-usb.c
@@ -339,68 +339,68 @@ static void mv_otg_update_state(struct mv_otg *mvotg)
 {
 	struct mv_otg_ctrl *otg_ctrl = &mvotg->otg_ctrl;
 	struct usb_phy *phy = &mvotg->phy;
-	int old_state = phy->state;
+	int old_state = mvotg->phy.otg->state;
 
 	switch (old_state) {
 	case OTG_STATE_UNDEFINED:
-		phy->state = OTG_STATE_B_IDLE;
+		mvotg->phy.otg->state = OTG_STATE_B_IDLE;
 		/* FALL THROUGH */
 	case OTG_STATE_B_IDLE:
 		if (otg_ctrl->id == 0)
-			phy->state = OTG_STATE_A_IDLE;
+			mvotg->phy.otg->state = OTG_STATE_A_IDLE;
 		else if (otg_ctrl->b_sess_vld)
-			phy->state = OTG_STATE_B_PERIPHERAL;
+			mvotg->phy.otg->state = OTG_STATE_B_PERIPHERAL;
 		break;
 	case OTG_STATE_B_PERIPHERAL:
 		if (!otg_ctrl->b_sess_vld || otg_ctrl->id == 0)
-			phy->state = OTG_STATE_B_IDLE;
+			mvotg->phy.otg->state = OTG_STATE_B_IDLE;
 		break;
 	case OTG_STATE_A_IDLE:
 		if (otg_ctrl->id)
-			phy->state = OTG_STATE_B_IDLE;
+			mvotg->phy.otg->state = OTG_STATE_B_IDLE;
 		else if (!(otg_ctrl->a_bus_drop) &&
 			 (otg_ctrl->a_bus_req || otg_ctrl->a_srp_det))
-			phy->state = OTG_STATE_A_WAIT_VRISE;
+			mvotg->phy.otg->state = OTG_STATE_A_WAIT_VRISE;
 		break;
 	case OTG_STATE_A_WAIT_VRISE:
 		if (otg_ctrl->a_vbus_vld)
-			phy->state = OTG_STATE_A_WAIT_BCON;
+			mvotg->phy.otg->state = OTG_STATE_A_WAIT_BCON;
 		break;
 	case OTG_STATE_A_WAIT_BCON:
 		if (otg_ctrl->id || otg_ctrl->a_bus_drop
 		    || otg_ctrl->a_wait_bcon_timeout) {
 			mv_otg_cancel_timer(mvotg, A_WAIT_BCON_TIMER);
 			mvotg->otg_ctrl.a_wait_bcon_timeout = 0;
-			phy->state = OTG_STATE_A_WAIT_VFALL;
+			mvotg->phy.otg->state = OTG_STATE_A_WAIT_VFALL;
 			otg_ctrl->a_bus_req = 0;
 		} else if (!otg_ctrl->a_vbus_vld) {
 			mv_otg_cancel_timer(mvotg, A_WAIT_BCON_TIMER);
 			mvotg->otg_ctrl.a_wait_bcon_timeout = 0;
-			phy->state = OTG_STATE_A_VBUS_ERR;
+			mvotg->phy.otg->state = OTG_STATE_A_VBUS_ERR;
 		} else if (otg_ctrl->b_conn) {
 			mv_otg_cancel_timer(mvotg, A_WAIT_BCON_TIMER);
 			mvotg->otg_ctrl.a_wait_bcon_timeout = 0;
-			phy->state = OTG_STATE_A_HOST;
+			mvotg->phy.otg->state = OTG_STATE_A_HOST;
 		}
 		break;
 	case OTG_STATE_A_HOST:
 		if (otg_ctrl->id || !otg_ctrl->b_conn
 		    || otg_ctrl->a_bus_drop)
-			phy->state = OTG_STATE_A_WAIT_BCON;
+			mvotg->phy.otg->state = OTG_STATE_A_WAIT_BCON;
 		else if (!otg_ctrl->a_vbus_vld)
-			phy->state = OTG_STATE_A_VBUS_ERR;
+			mvotg->phy.otg->state = OTG_STATE_A_VBUS_ERR;
 		break;
 	case OTG_STATE_A_WAIT_VFALL:
 		if (otg_ctrl->id
 		    || (!otg_ctrl->b_conn && otg_ctrl->a_sess_vld)
 		    || otg_ctrl->a_bus_req)
-			phy->state = OTG_STATE_A_IDLE;
+			mvotg->phy.otg->state = OTG_STATE_A_IDLE;
 		break;
 	case OTG_STATE_A_VBUS_ERR:
 		if (otg_ctrl->id || otg_ctrl->a_clr_err
 		    || otg_ctrl->a_bus_drop) {
 			otg_ctrl->a_clr_err = 0;
-			phy->state = OTG_STATE_A_WAIT_VFALL;
+			mvotg->phy.otg->state = OTG_STATE_A_WAIT_VFALL;
 		}
 		break;
 	default:
@@ -420,8 +420,8 @@ static void mv_otg_work(struct work_struct *work)
 run:
 	/* work queue is single thread, or we need spin_lock to protect */
 	phy = &mvotg->phy;
-	otg = phy->otg;
-	old_state = phy->state;
+	otg = mvotg->phy.otg;
+	old_state = otg->state;
 
 	if (!mvotg->active)
 		return;
@@ -429,12 +429,12 @@ run:
 	mv_otg_update_inputs(mvotg);
 	mv_otg_update_state(mvotg);
 
-	if (old_state != phy->state) {
+	if (old_state != mvotg->phy.otg->state) {
 		dev_info(&mvotg->pdev->dev, "change from state %s to %s\n",
 			 state_string[old_state],
-			 state_string[phy->state]);
+			 state_string[mvotg->phy.otg->state]);
 
-		switch (phy->state) {
+		switch (mvotg->phy.otg->state) {
 		case OTG_STATE_B_IDLE:
 			otg->default_a = 0;
 			if (old_state == OTG_STATE_B_PERIPHERAL)
@@ -545,8 +545,8 @@ set_a_bus_req(struct device *dev, struct device_attribute *attr,
 		return -1;
 
 	/* We will use this interface to change to A device */
-	if (mvotg->phy.state != OTG_STATE_B_IDLE
-	    && mvotg->phy.state != OTG_STATE_A_IDLE)
+	if (mvotg->phy.otg->state != OTG_STATE_B_IDLE
+	    && mvotg->phy.otg->state != OTG_STATE_A_IDLE)
 		return -1;
 
 	/* The clock may disabled and we need to set irq for ID detected */
@@ -715,9 +715,9 @@ static int mv_otg_probe(struct platform_device *pdev)
 	mvotg->phy.dev = &pdev->dev;
 	mvotg->phy.otg = otg;
 	mvotg->phy.label = driver_name;
-	mvotg->phy.state = OTG_STATE_UNDEFINED;
 
 	otg->phy = &mvotg->phy;
+	otg->state = OTG_STATE_UNDEFINED;
 	otg->set_host = mv_otg_set_host;
 	otg->set_peripheral = mv_otg_set_peripheral;
 	otg->set_vbus = mv_otg_set_vbus;
diff --git a/drivers/usb/phy/phy-tahvo.c b/drivers/usb/phy/phy-tahvo.c
index cc61ee44b91..04ece535c2f 100644
--- a/drivers/usb/phy/phy-tahvo.c
+++ b/drivers/usb/phy/phy-tahvo.c
@@ -81,33 +81,33 @@ static void check_vbus_state(struct tahvo_usb *tu)
 
 	reg = retu_read(rdev, TAHVO_REG_IDSR);
 	if (reg & TAHVO_STAT_VBUS) {
-		switch (tu->phy.state) {
+		switch (tu->phy.otg->state) {
 		case OTG_STATE_B_IDLE:
 			/* Enable the gadget driver */
 			if (tu->phy.otg->gadget)
 				usb_gadget_vbus_connect(tu->phy.otg->gadget);
-			tu->phy.state = OTG_STATE_B_PERIPHERAL;
+			tu->phy.otg->state = OTG_STATE_B_PERIPHERAL;
 			break;
 		case OTG_STATE_A_IDLE:
 			/*
 			 * Session is now valid assuming the USB hub is driving
 			 * Vbus.
 			 */
-			tu->phy.state = OTG_STATE_A_HOST;
+			tu->phy.otg->state = OTG_STATE_A_HOST;
 			break;
 		default:
 			break;
 		}
 		dev_info(&tu->pt_dev->dev, "USB cable connected\n");
 	} else {
-		switch (tu->phy.state) {
+		switch (tu->phy.otg->state) {
 		case OTG_STATE_B_PERIPHERAL:
 			if (tu->phy.otg->gadget)
 				usb_gadget_vbus_disconnect(tu->phy.otg->gadget);
-			tu->phy.state = OTG_STATE_B_IDLE;
+			tu->phy.otg->state = OTG_STATE_B_IDLE;
 			break;
 		case OTG_STATE_A_HOST:
-			tu->phy.state = OTG_STATE_A_IDLE;
+			tu->phy.otg->state = OTG_STATE_A_IDLE;
 			break;
 		default:
 			break;
@@ -132,14 +132,14 @@ static void tahvo_usb_become_host(struct tahvo_usb *tu)
 	/* Power up the transceiver in USB host mode */
 	retu_write(rdev, TAHVO_REG_USBR, USBR_REGOUT | USBR_NSUSPEND |
 		   USBR_MASTER_SW2 | USBR_MASTER_SW1);
-	tu->phy.state = OTG_STATE_A_IDLE;
+	tu->phy.otg->state = OTG_STATE_A_IDLE;
 
 	check_vbus_state(tu);
 }
 
 static void tahvo_usb_stop_host(struct tahvo_usb *tu)
 {
-	tu->phy.state = OTG_STATE_A_IDLE;
+	tu->phy.otg->state = OTG_STATE_A_IDLE;
 }
 
 static void tahvo_usb_become_peripheral(struct tahvo_usb *tu)
@@ -151,7 +151,7 @@ static void tahvo_usb_become_peripheral(struct tahvo_usb *tu)
 	/* Power up transceiver and set it in USB peripheral mode */
 	retu_write(rdev, TAHVO_REG_USBR, USBR_SLAVE_CONTROL | USBR_REGOUT |
 		   USBR_NSUSPEND | USBR_SLAVE_SW);
-	tu->phy.state = OTG_STATE_B_IDLE;
+	tu->phy.otg->state = OTG_STATE_B_IDLE;
 
 	check_vbus_state(tu);
 }
@@ -160,7 +160,7 @@ static void tahvo_usb_stop_peripheral(struct tahvo_usb *tu)
 {
 	if (tu->phy.otg->gadget)
 		usb_gadget_vbus_disconnect(tu->phy.otg->gadget);
-	tu->phy.state = OTG_STATE_B_IDLE;
+	tu->phy.otg->state = OTG_STATE_B_IDLE;
 }
 
 static void tahvo_usb_power_off(struct tahvo_usb *tu)
@@ -173,7 +173,7 @@ static void tahvo_usb_power_off(struct tahvo_usb *tu)
 
 	/* Power off transceiver */
 	retu_write(rdev, TAHVO_REG_USBR, 0);
-	tu->phy.state = OTG_STATE_UNDEFINED;
+	tu->phy.otg->state = OTG_STATE_UNDEFINED;
 }
 
 static int tahvo_usb_set_suspend(struct usb_phy *dev, int suspend)
@@ -379,7 +379,7 @@ static int tahvo_usb_probe(struct platform_device *pdev)
 	/* Create OTG interface */
 	tahvo_usb_power_off(tu);
 	tu->phy.dev = &pdev->dev;
-	tu->phy.state = OTG_STATE_UNDEFINED;
+	tu->phy.otg->state = OTG_STATE_UNDEFINED;
 	tu->phy.label = DRIVER_NAME;
 	tu->phy.set_suspend = tahvo_usb_set_suspend;
 
diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h
index 154332b7c8c..33d3480c9cd 100644
--- a/include/linux/usb/otg.h
+++ b/include/linux/usb/otg.h
@@ -18,6 +18,8 @@ struct usb_otg {
 	struct usb_bus		*host;
 	struct usb_gadget	*gadget;
 
+	enum usb_otg_state	state;
+
 	/* bind/unbind the host controller */
 	int	(*set_host)(struct usb_otg *otg, struct usb_bus *host);
 
diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h
index 353053a33f2..ac7d7913694 100644
--- a/include/linux/usb/phy.h
+++ b/include/linux/usb/phy.h
@@ -77,7 +77,6 @@ struct usb_phy {
 	unsigned int		 flags;
 
 	enum usb_phy_type	type;
-	enum usb_otg_state	state;
 	enum usb_phy_events	last_event;
 
 	struct usb_otg		*otg;
-- 
cgit v1.2.3-70-g09d2


From 19c1eac2685b62640ca2386a0a885ac2152668c8 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@free-electrons.com>
Date: Thu, 30 Oct 2014 18:41:14 +0100
Subject: usb: rename phy to usb_phy in OTG

This patch prepares the introduction of the generic PHY support in the
USB OTG common functions. The USB PHY member of the OTG structure is
renamed to 'usb_phy' and modifications are done in all drivers accessing
it. Renaming this pointer will allow to keep the compatibility for USB
PHY drivers.

Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/phy/phy-omap-usb2.c         |  6 ++--
 drivers/usb/chipidea/otg_fsm.c      |  2 +-
 drivers/usb/phy/phy-ab8500-usb.c    |  6 ++--
 drivers/usb/phy/phy-fsl-usb.c       | 13 ++++----
 drivers/usb/phy/phy-generic.c       |  2 +-
 drivers/usb/phy/phy-gpio-vbus-usb.c |  4 +--
 drivers/usb/phy/phy-isp1301-omap.c  | 10 +++---
 drivers/usb/phy/phy-msm-usb.c       | 61 +++++++++++++++++++------------------
 drivers/usb/phy/phy-mv-usb.c        |  4 +--
 drivers/usb/phy/phy-tahvo.c         |  8 +++--
 drivers/usb/phy/phy-ulpi.c          |  6 ++--
 include/linux/usb/otg.h             |  2 +-
 12 files changed, 65 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c
index 9f4093590f4..32c3e86b493 100644
--- a/drivers/phy/phy-omap-usb2.c
+++ b/drivers/phy/phy-omap-usb2.c
@@ -60,7 +60,7 @@ EXPORT_SYMBOL_GPL(omap_usb2_set_comparator);
 
 static int omap_usb_set_vbus(struct usb_otg *otg, bool enabled)
 {
-	struct omap_usb *phy = phy_to_omapusb(otg->phy);
+	struct omap_usb *phy = phy_to_omapusb(otg->usb_phy);
 
 	if (!phy->comparator)
 		return -ENODEV;
@@ -70,7 +70,7 @@ static int omap_usb_set_vbus(struct usb_otg *otg, bool enabled)
 
 static int omap_usb_start_srp(struct usb_otg *otg)
 {
-	struct omap_usb *phy = phy_to_omapusb(otg->phy);
+	struct omap_usb *phy = phy_to_omapusb(otg->usb_phy);
 
 	if (!phy->comparator)
 		return -ENODEV;
@@ -251,7 +251,7 @@ static int omap_usb2_probe(struct platform_device *pdev)
 		otg->set_vbus		= omap_usb_set_vbus;
 	if (phy_data->flags & OMAP_USB2_HAS_START_SRP)
 		otg->start_srp		= omap_usb_start_srp;
-	otg->phy		= &phy->phy;
+	otg->usb_phy		= &phy->phy;
 
 	platform_set_drvdata(pdev, phy);
 
diff --git a/drivers/usb/chipidea/otg_fsm.c b/drivers/usb/chipidea/otg_fsm.c
index 8cb2508a6b7..d8490e758a7 100644
--- a/drivers/usb/chipidea/otg_fsm.c
+++ b/drivers/usb/chipidea/otg_fsm.c
@@ -788,7 +788,7 @@ int ci_hdrc_otg_fsm_init(struct ci_hdrc *ci)
 		return -ENOMEM;
 	}
 
-	otg->phy = ci->transceiver;
+	otg->usb_phy = ci->transceiver;
 	otg->gadget = &ci->gadget;
 	ci->fsm.otg = otg;
 	ci->transceiver->otg = ci->fsm.otg;
diff --git a/drivers/usb/phy/phy-ab8500-usb.c b/drivers/usb/phy/phy-ab8500-usb.c
index 2d5250143ce..3a802fa7dae 100644
--- a/drivers/usb/phy/phy-ab8500-usb.c
+++ b/drivers/usb/phy/phy-ab8500-usb.c
@@ -1056,7 +1056,7 @@ static int ab8500_usb_set_peripheral(struct usb_otg *otg,
 	if (!otg)
 		return -ENODEV;
 
-	ab = phy_to_ab(otg->phy);
+	ab = phy_to_ab(otg->usb_phy);
 
 	ab->phy.otg->gadget = gadget;
 
@@ -1080,7 +1080,7 @@ static int ab8500_usb_set_host(struct usb_otg *otg, struct usb_bus *host)
 	if (!otg)
 		return -ENODEV;
 
-	ab = phy_to_ab(otg->phy);
+	ab = phy_to_ab(otg->usb_phy);
 
 	ab->phy.otg->host = host;
 
@@ -1382,7 +1382,7 @@ static int ab8500_usb_probe(struct platform_device *pdev)
 	ab->phy.set_power	= ab8500_usb_set_power;
 	ab->phy.otg->state	= OTG_STATE_UNDEFINED;
 
-	otg->phy		= &ab->phy;
+	otg->usb_phy		= &ab->phy;
 	otg->set_host		= ab8500_usb_set_host;
 	otg->set_peripheral	= ab8500_usb_set_peripheral;
 
diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c
index 15d7a81eece..b7f36b21242 100644
--- a/drivers/usb/phy/phy-fsl-usb.c
+++ b/drivers/usb/phy/phy-fsl-usb.c
@@ -499,7 +499,8 @@ int fsl_otg_start_host(struct otg_fsm *fsm, int on)
 {
 	struct usb_otg *otg = fsm->otg;
 	struct device *dev;
-	struct fsl_otg *otg_dev = container_of(otg->phy, struct fsl_otg, phy);
+	struct fsl_otg *otg_dev =
+		container_of(otg->usb_phy, struct fsl_otg, phy);
 	u32 retval = 0;
 
 	if (!otg->host)
@@ -594,7 +595,7 @@ static int fsl_otg_set_host(struct usb_otg *otg, struct usb_bus *host)
 	if (!otg)
 		return -ENODEV;
 
-	otg_dev = container_of(otg->phy, struct fsl_otg, phy);
+	otg_dev = container_of(otg->usb_phy, struct fsl_otg, phy);
 	if (otg_dev != fsl_otg_dev)
 		return -ENODEV;
 
@@ -644,7 +645,7 @@ static int fsl_otg_set_peripheral(struct usb_otg *otg,
 	if (!otg)
 		return -ENODEV;
 
-	otg_dev = container_of(otg->phy, struct fsl_otg, phy);
+	otg_dev = container_of(otg->usb_phy, struct fsl_otg, phy);
 	VDBG("otg_dev 0x%x\n", (int)otg_dev);
 	VDBG("fsl_otg_dev 0x%x\n", (int)fsl_otg_dev);
 	if (otg_dev != fsl_otg_dev)
@@ -717,7 +718,7 @@ static int fsl_otg_start_srp(struct usb_otg *otg)
 	if (!otg || otg.state != OTG_STATE_B_IDLE)
 		return -ENODEV;
 
-	otg_dev = container_of(otg->phy, struct fsl_otg, phy);
+	otg_dev = container_of(otg->usb_phy, struct fsl_otg, phy);
 	if (otg_dev != fsl_otg_dev)
 		return -ENODEV;
 
@@ -735,7 +736,7 @@ static int fsl_otg_start_hnp(struct usb_otg *otg)
 	if (!otg)
 		return -ENODEV;
 
-	otg_dev = container_of(otg->phy, struct fsl_otg, phy);
+	otg_dev = container_of(otg->usb_phy, struct fsl_otg, phy);
 	if (otg_dev != fsl_otg_dev)
 		return -ENODEV;
 
@@ -857,7 +858,7 @@ static int fsl_otg_conf(struct platform_device *pdev)
 	fsl_otg_tc->phy.dev = &pdev->dev;
 	fsl_otg_tc->phy.set_power = fsl_otg_set_power;
 
-	fsl_otg_tc->phy.otg->phy = &fsl_otg_tc->phy;
+	fsl_otg_tc->phy.otg->usb_phy = &fsl_otg_tc->phy;
 	fsl_otg_tc->phy.otg->set_host = fsl_otg_set_host;
 	fsl_otg_tc->phy.otg->set_peripheral = fsl_otg_set_peripheral;
 	fsl_otg_tc->phy.otg->start_hnp = fsl_otg_start_hnp;
diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c
index 280a3458ff6..0c01bd12cab 100644
--- a/drivers/usb/phy/phy-generic.c
+++ b/drivers/usb/phy/phy-generic.c
@@ -228,7 +228,7 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop,
 	nop->phy.type		= type;
 
 	nop->phy.otg->state		= OTG_STATE_UNDEFINED;
-	nop->phy.otg->phy		= &nop->phy;
+	nop->phy.otg->usb_phy		= &nop->phy;
 	nop->phy.otg->set_host		= nop_set_host;
 	nop->phy.otg->set_peripheral	= nop_set_peripheral;
 
diff --git a/drivers/usb/phy/phy-gpio-vbus-usb.c b/drivers/usb/phy/phy-gpio-vbus-usb.c
index 7a6be3e5dc2..9fcf19ba141 100644
--- a/drivers/usb/phy/phy-gpio-vbus-usb.c
+++ b/drivers/usb/phy/phy-gpio-vbus-usb.c
@@ -180,7 +180,7 @@ static int gpio_vbus_set_peripheral(struct usb_otg *otg,
 	struct platform_device *pdev;
 	int gpio;
 
-	gpio_vbus = container_of(otg->phy, struct gpio_vbus_data, phy);
+	gpio_vbus = container_of(otg->usb_phy, struct gpio_vbus_data, phy);
 	pdev = to_platform_device(gpio_vbus->dev);
 	pdata = dev_get_platdata(gpio_vbus->dev);
 	gpio = pdata->gpio_pullup;
@@ -271,7 +271,7 @@ static int gpio_vbus_probe(struct platform_device *pdev)
 	gpio_vbus->phy.set_suspend = gpio_vbus_set_suspend;
 
 	gpio_vbus->phy.otg->state = OTG_STATE_UNDEFINED;
-	gpio_vbus->phy.otg->phy = &gpio_vbus->phy;
+	gpio_vbus->phy.otg->usb_phy = &gpio_vbus->phy;
 	gpio_vbus->phy.otg->set_peripheral = gpio_vbus_set_peripheral;
 
 	err = devm_gpio_request(&pdev->dev, gpio, "vbus_detect");
diff --git a/drivers/usb/phy/phy-isp1301-omap.c b/drivers/usb/phy/phy-isp1301-omap.c
index 24f84cbbed5..a2dfb2ae520 100644
--- a/drivers/usb/phy/phy-isp1301-omap.c
+++ b/drivers/usb/phy/phy-isp1301-omap.c
@@ -1275,7 +1275,7 @@ static int isp1301_otg_enable(struct isp1301 *isp)
 static int
 isp1301_set_host(struct usb_otg *otg, struct usb_bus *host)
 {
-	struct isp1301	*isp = container_of(otg->phy, struct isp1301, phy);
+	struct isp1301	*isp = container_of(otg->usb_phy, struct isp1301, phy);
 
 	if (isp != the_transceiver)
 		return -ENODEV;
@@ -1331,7 +1331,7 @@ isp1301_set_host(struct usb_otg *otg, struct usb_bus *host)
 static int
 isp1301_set_peripheral(struct usb_otg *otg, struct usb_gadget *gadget)
 {
-	struct isp1301	*isp = container_of(otg->phy, struct isp1301, phy);
+	struct isp1301	*isp = container_of(otg->usb_phy, struct isp1301, phy);
 
 	if (isp != the_transceiver)
 		return -ENODEV;
@@ -1411,7 +1411,7 @@ isp1301_set_power(struct usb_phy *dev, unsigned mA)
 static int
 isp1301_start_srp(struct usb_otg *otg)
 {
-	struct isp1301	*isp = container_of(otg->phy, struct isp1301, phy);
+	struct isp1301	*isp = container_of(otg->usb_phy, struct isp1301, phy);
 	u32		otg_ctrl;
 
 	if (isp != the_transceiver || isp->phy.otg->state != OTG_STATE_B_IDLE)
@@ -1438,7 +1438,7 @@ static int
 isp1301_start_hnp(struct usb_otg *otg)
 {
 #ifdef	CONFIG_USB_OTG
-	struct isp1301	*isp = container_of(otg->phy, struct isp1301, phy);
+	struct isp1301	*isp = container_of(otg->usb_phy, struct isp1301, phy);
 	u32 l;
 
 	if (isp != the_transceiver)
@@ -1583,7 +1583,7 @@ isp1301_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 	isp->phy.label = DRIVER_NAME;
 	isp->phy.set_power = isp1301_set_power,
 
-	isp->phy.otg->phy = &isp->phy;
+	isp->phy.otg->usb_phy = &isp->phy;
 	isp->phy.otg->set_host = isp1301_set_host,
 	isp->phy.otg->set_peripheral = isp1301_set_peripheral,
 	isp->phy.otg->start_srp = isp1301_start_srp,
diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c
index 18015b7c8af..e120d87778b 100644
--- a/drivers/usb/phy/phy-msm-usb.c
+++ b/drivers/usb/phy/phy-msm-usb.c
@@ -708,7 +708,7 @@ static void msm_otg_start_host(struct usb_phy *phy, int on)
 
 static int msm_otg_set_host(struct usb_otg *otg, struct usb_bus *host)
 {
-	struct msm_otg *motg = container_of(otg->phy, struct msm_otg, phy);
+	struct msm_otg *motg = container_of(otg->usb_phy, struct msm_otg, phy);
 	struct usb_hcd *hcd;
 
 	/*
@@ -716,14 +716,14 @@ static int msm_otg_set_host(struct usb_otg *otg, struct usb_bus *host)
 	 * only peripheral configuration.
 	 */
 	if (motg->pdata->mode == USB_DR_MODE_PERIPHERAL) {
-		dev_info(otg->phy->dev, "Host mode is not supported\n");
+		dev_info(otg->usb_phy->dev, "Host mode is not supported\n");
 		return -ENODEV;
 	}
 
 	if (!host) {
 		if (otg->state == OTG_STATE_A_HOST) {
-			pm_runtime_get_sync(otg->phy->dev);
-			msm_otg_start_host(otg->phy, 0);
+			pm_runtime_get_sync(otg->usb_phy->dev);
+			msm_otg_start_host(otg->usb_phy, 0);
 			otg->host = NULL;
 			otg->state = OTG_STATE_UNDEFINED;
 			schedule_work(&motg->sm_work);
@@ -738,14 +738,14 @@ static int msm_otg_set_host(struct usb_otg *otg, struct usb_bus *host)
 	hcd->power_budget = motg->pdata->power_budget;
 
 	otg->host = host;
-	dev_dbg(otg->phy->dev, "host driver registered w/ tranceiver\n");
+	dev_dbg(otg->usb_phy->dev, "host driver registered w/ tranceiver\n");
 
 	/*
 	 * Kick the state machine work, if peripheral is not supported
 	 * or peripheral is already registered with us.
 	 */
 	if (motg->pdata->mode == USB_DR_MODE_HOST || otg->gadget) {
-		pm_runtime_get_sync(otg->phy->dev);
+		pm_runtime_get_sync(otg->usb_phy->dev);
 		schedule_work(&motg->sm_work);
 	}
 
@@ -782,21 +782,21 @@ static void msm_otg_start_peripheral(struct usb_phy *phy, int on)
 static int msm_otg_set_peripheral(struct usb_otg *otg,
 					struct usb_gadget *gadget)
 {
-	struct msm_otg *motg = container_of(otg->phy, struct msm_otg, phy);
+	struct msm_otg *motg = container_of(otg->usb_phy, struct msm_otg, phy);
 
 	/*
 	 * Fail peripheral registration if this board can support
 	 * only host configuration.
 	 */
 	if (motg->pdata->mode == USB_DR_MODE_HOST) {
-		dev_info(otg->phy->dev, "Peripheral mode is not supported\n");
+		dev_info(otg->usb_phy->dev, "Peripheral mode is not supported\n");
 		return -ENODEV;
 	}
 
 	if (!gadget) {
 		if (otg->state == OTG_STATE_B_PERIPHERAL) {
-			pm_runtime_get_sync(otg->phy->dev);
-			msm_otg_start_peripheral(otg->phy, 0);
+			pm_runtime_get_sync(otg->usb_phy->dev);
+			msm_otg_start_peripheral(otg->usb_phy, 0);
 			otg->gadget = NULL;
 			otg->state = OTG_STATE_UNDEFINED;
 			schedule_work(&motg->sm_work);
@@ -807,14 +807,15 @@ static int msm_otg_set_peripheral(struct usb_otg *otg,
 		return 0;
 	}
 	otg->gadget = gadget;
-	dev_dbg(otg->phy->dev, "peripheral driver registered w/ tranceiver\n");
+	dev_dbg(otg->usb_phy->dev,
+		"peripheral driver registered w/ tranceiver\n");
 
 	/*
 	 * Kick the state machine work, if host is not supported
 	 * or host is already registered with us.
 	 */
 	if (motg->pdata->mode == USB_DR_MODE_PERIPHERAL || otg->host) {
-		pm_runtime_get_sync(otg->phy->dev);
+		pm_runtime_get_sync(otg->usb_phy->dev);
 		schedule_work(&motg->sm_work);
 	}
 
@@ -1172,17 +1173,17 @@ static void msm_otg_sm_work(struct work_struct *w)
 
 	switch (otg->state) {
 	case OTG_STATE_UNDEFINED:
-		dev_dbg(otg->phy->dev, "OTG_STATE_UNDEFINED state\n");
-		msm_otg_reset(otg->phy);
+		dev_dbg(otg->usb_phy->dev, "OTG_STATE_UNDEFINED state\n");
+		msm_otg_reset(otg->usb_phy);
 		msm_otg_init_sm(motg);
 		otg->state = OTG_STATE_B_IDLE;
 		/* FALL THROUGH */
 	case OTG_STATE_B_IDLE:
-		dev_dbg(otg->phy->dev, "OTG_STATE_B_IDLE state\n");
+		dev_dbg(otg->usb_phy->dev, "OTG_STATE_B_IDLE state\n");
 		if (!test_bit(ID, &motg->inputs) && otg->host) {
 			/* disable BSV bit */
 			writel(readl(USB_OTGSC) & ~OTGSC_BSVIE, USB_OTGSC);
-			msm_otg_start_host(otg->phy, 1);
+			msm_otg_start_host(otg->usb_phy, 1);
 			otg->state = OTG_STATE_A_HOST;
 		} else if (test_bit(B_SESS_VLD, &motg->inputs)) {
 			switch (motg->chg_state) {
@@ -1198,13 +1199,15 @@ static void msm_otg_sm_work(struct work_struct *w)
 				case USB_CDP_CHARGER:
 					msm_otg_notify_charger(motg,
 							IDEV_CHG_MAX);
-					msm_otg_start_peripheral(otg->phy, 1);
+					msm_otg_start_peripheral(otg->usb_phy,
+								 1);
 					otg->state
 						= OTG_STATE_B_PERIPHERAL;
 					break;
 				case USB_SDP_CHARGER:
 					msm_otg_notify_charger(motg, IUNIT);
-					msm_otg_start_peripheral(otg->phy, 1);
+					msm_otg_start_peripheral(otg->usb_phy,
+								 1);
 					otg->state
 						= OTG_STATE_B_PERIPHERAL;
 					break;
@@ -1222,8 +1225,8 @@ static void msm_otg_sm_work(struct work_struct *w)
 			 * is incremented in charger detection work.
 			 */
 			if (cancel_delayed_work_sync(&motg->chg_work)) {
-				pm_runtime_put_sync(otg->phy->dev);
-				msm_otg_reset(otg->phy);
+				pm_runtime_put_sync(otg->usb_phy->dev);
+				msm_otg_reset(otg->usb_phy);
 			}
 			msm_otg_notify_charger(motg, 0);
 			motg->chg_state = USB_CHG_STATE_UNDEFINED;
@@ -1231,27 +1234,27 @@ static void msm_otg_sm_work(struct work_struct *w)
 		}
 
 		if (otg->state == OTG_STATE_B_IDLE)
-			pm_runtime_put_sync(otg->phy->dev);
+			pm_runtime_put_sync(otg->usb_phy->dev);
 		break;
 	case OTG_STATE_B_PERIPHERAL:
-		dev_dbg(otg->phy->dev, "OTG_STATE_B_PERIPHERAL state\n");
+		dev_dbg(otg->usb_phy->dev, "OTG_STATE_B_PERIPHERAL state\n");
 		if (!test_bit(B_SESS_VLD, &motg->inputs) ||
 				!test_bit(ID, &motg->inputs)) {
 			msm_otg_notify_charger(motg, 0);
-			msm_otg_start_peripheral(otg->phy, 0);
+			msm_otg_start_peripheral(otg->usb_phy, 0);
 			motg->chg_state = USB_CHG_STATE_UNDEFINED;
 			motg->chg_type = USB_INVALID_CHARGER;
 			otg->state = OTG_STATE_B_IDLE;
-			msm_otg_reset(otg->phy);
+			msm_otg_reset(otg->usb_phy);
 			schedule_work(w);
 		}
 		break;
 	case OTG_STATE_A_HOST:
-		dev_dbg(otg->phy->dev, "OTG_STATE_A_HOST state\n");
+		dev_dbg(otg->usb_phy->dev, "OTG_STATE_A_HOST state\n");
 		if (test_bit(ID, &motg->inputs)) {
-			msm_otg_start_host(otg->phy, 0);
+			msm_otg_start_host(otg->usb_phy, 0);
 			otg->state = OTG_STATE_B_IDLE;
-			msm_otg_reset(otg->phy);
+			msm_otg_reset(otg->usb_phy);
 			schedule_work(w);
 		}
 		break;
@@ -1388,7 +1391,7 @@ static ssize_t msm_otg_mode_write(struct file *file, const char __user *ubuf,
 		goto out;
 	}
 
-	pm_runtime_get_sync(otg->phy->dev);
+	pm_runtime_get_sync(otg->usb_phy->dev);
 	schedule_work(&motg->sm_work);
 out:
 	return status;
@@ -1668,7 +1671,7 @@ static int msm_otg_probe(struct platform_device *pdev)
 
 	phy->io_ops = &msm_otg_io_ops;
 
-	phy->otg->phy = &motg->phy;
+	phy->otg->usb_phy = &motg->phy;
 	phy->otg->set_host = msm_otg_set_host;
 	phy->otg->set_peripheral = msm_otg_set_peripheral;
 
diff --git a/drivers/usb/phy/phy-mv-usb.c b/drivers/usb/phy/phy-mv-usb.c
index ee87aa7144d..81d934fdd0c 100644
--- a/drivers/usb/phy/phy-mv-usb.c
+++ b/drivers/usb/phy/phy-mv-usb.c
@@ -56,7 +56,7 @@ static char *state_string[] = {
 
 static int mv_otg_set_vbus(struct usb_otg *otg, bool on)
 {
-	struct mv_otg *mvotg = container_of(otg->phy, struct mv_otg, phy);
+	struct mv_otg *mvotg = container_of(otg->usb_phy, struct mv_otg, phy);
 	if (mvotg->pdata->set_vbus == NULL)
 		return -ENODEV;
 
@@ -716,8 +716,8 @@ static int mv_otg_probe(struct platform_device *pdev)
 	mvotg->phy.otg = otg;
 	mvotg->phy.label = driver_name;
 
-	otg->phy = &mvotg->phy;
 	otg->state = OTG_STATE_UNDEFINED;
+	otg->usb_phy = &mvotg->phy;
 	otg->set_host = mv_otg_set_host;
 	otg->set_peripheral = mv_otg_set_peripheral;
 	otg->set_vbus = mv_otg_set_vbus;
diff --git a/drivers/usb/phy/phy-tahvo.c b/drivers/usb/phy/phy-tahvo.c
index 04ece535c2f..9cabc1a20d1 100644
--- a/drivers/usb/phy/phy-tahvo.c
+++ b/drivers/usb/phy/phy-tahvo.c
@@ -196,7 +196,8 @@ static int tahvo_usb_set_suspend(struct usb_phy *dev, int suspend)
 
 static int tahvo_usb_set_host(struct usb_otg *otg, struct usb_bus *host)
 {
-	struct tahvo_usb *tu = container_of(otg->phy, struct tahvo_usb, phy);
+	struct tahvo_usb *tu = container_of(otg->usb_phy, struct tahvo_usb,
+					    phy);
 
 	dev_dbg(&tu->pt_dev->dev, "%s %p\n", __func__, host);
 
@@ -225,7 +226,8 @@ static int tahvo_usb_set_host(struct usb_otg *otg, struct usb_bus *host)
 static int tahvo_usb_set_peripheral(struct usb_otg *otg,
 				    struct usb_gadget *gadget)
 {
-	struct tahvo_usb *tu = container_of(otg->phy, struct tahvo_usb, phy);
+	struct tahvo_usb *tu = container_of(otg->usb_phy, struct tahvo_usb,
+					    phy);
 
 	dev_dbg(&tu->pt_dev->dev, "%s %p\n", __func__, gadget);
 
@@ -383,7 +385,7 @@ static int tahvo_usb_probe(struct platform_device *pdev)
 	tu->phy.label = DRIVER_NAME;
 	tu->phy.set_suspend = tahvo_usb_set_suspend;
 
-	tu->phy.otg->phy = &tu->phy;
+	tu->phy.otg->usb_phy = &tu->phy;
 	tu->phy.otg->set_host = tahvo_usb_set_host;
 	tu->phy.otg->set_peripheral = tahvo_usb_set_peripheral;
 
diff --git a/drivers/usb/phy/phy-ulpi.c b/drivers/usb/phy/phy-ulpi.c
index 4e3877c329f..f48a7a21e3c 100644
--- a/drivers/usb/phy/phy-ulpi.c
+++ b/drivers/usb/phy/phy-ulpi.c
@@ -211,7 +211,7 @@ static int ulpi_init(struct usb_phy *phy)
 
 static int ulpi_set_host(struct usb_otg *otg, struct usb_bus *host)
 {
-	struct usb_phy *phy = otg->phy;
+	struct usb_phy *phy = otg->usb_phy;
 	unsigned int flags = usb_phy_io_read(phy, ULPI_IFC_CTRL);
 
 	if (!host) {
@@ -237,7 +237,7 @@ static int ulpi_set_host(struct usb_otg *otg, struct usb_bus *host)
 
 static int ulpi_set_vbus(struct usb_otg *otg, bool on)
 {
-	struct usb_phy *phy = otg->phy;
+	struct usb_phy *phy = otg->usb_phy;
 	unsigned int flags = usb_phy_io_read(phy, ULPI_OTG_CTRL);
 
 	flags &= ~(ULPI_OTG_CTRL_DRVVBUS | ULPI_OTG_CTRL_DRVVBUS_EXT);
@@ -276,7 +276,7 @@ otg_ulpi_create(struct usb_phy_io_ops *ops,
 	phy->otg	= otg;
 	phy->init	= ulpi_init;
 
-	otg->phy	= phy;
+	otg->usb_phy	= phy;
 	otg->set_host	= ulpi_set_host;
 	otg->set_vbus	= ulpi_set_vbus;
 
diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h
index 33d3480c9cd..978fbbb0e26 100644
--- a/include/linux/usb/otg.h
+++ b/include/linux/usb/otg.h
@@ -14,7 +14,7 @@
 struct usb_otg {
 	u8			default_a;
 
-	struct usb_phy		*phy;
+	struct usb_phy		*usb_phy;
 	struct usb_bus		*host;
 	struct usb_gadget	*gadget;
 
-- 
cgit v1.2.3-70-g09d2


From 48bcc18076df4e07ef86226ac6ce795f64c84f7f Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@free-electrons.com>
Date: Thu, 30 Oct 2014 18:41:15 +0100
Subject: usb: add support to the generic PHY framework in OTG

This patch adds support of the PHY framework in OTG and keeps the USB
PHY compatibility. Here the only modification is to add PHY member in
the OTG structure, along with the USB PHY one.

Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 include/linux/usb/otg.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h
index 978fbbb0e26..52661c5da69 100644
--- a/include/linux/usb/otg.h
+++ b/include/linux/usb/otg.h
@@ -9,11 +9,14 @@
 #ifndef __LINUX_USB_OTG_H
 #define __LINUX_USB_OTG_H
 
+#include <linux/phy/phy.h>
 #include <linux/usb/phy.h>
 
 struct usb_otg {
 	u8			default_a;
 
+	struct phy		*phy;
+	/* old usb_phy interface */
 	struct usb_phy		*usb_phy;
 	struct usb_bus		*host;
 	struct usb_gadget	*gadget;
-- 
cgit v1.2.3-70-g09d2


From ef44cb4226d132146e44f8ea562a16b27ff61126 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@free-electrons.com>
Date: Thu, 30 Oct 2014 18:41:16 +0100
Subject: usb: allow to supply the PHY in the drivers when using HCD

This patch modify the generic code handling PHYs to allow them to be
supplied from the drivers. This adds checks to ensure no PHY was already
there when looking for one in the generic code. This also makes sure we
do not modify its state in the generic HCD functions, it was provided by
the driver.

Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/chipidea/ci.h          |  5 +++--
 drivers/usb/chipidea/ci_hdrc_imx.c |  2 +-
 drivers/usb/chipidea/ci_hdrc_msm.c |  8 ++++----
 drivers/usb/chipidea/core.c        | 20 ++++++++++----------
 drivers/usb/chipidea/debug.c       |  2 +-
 drivers/usb/chipidea/host.c        |  7 ++++---
 drivers/usb/chipidea/otg_fsm.c     | 16 +++-------------
 drivers/usb/chipidea/udc.c         |  4 ++--
 drivers/usb/core/hcd.c             |  7 ++++---
 include/linux/usb/chipidea.h       |  2 +-
 10 files changed, 33 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h
index ea40626e024..9015139a802 100644
--- a/drivers/usb/chipidea/ci.h
+++ b/drivers/usb/chipidea/ci.h
@@ -161,7 +161,7 @@ struct hw_bank {
  * @test_mode: the selected test mode
  * @platdata: platform specific information supplied by parent device
  * @vbus_active: is VBUS active
- * @transceiver: pointer to USB PHY, if any
+ * @usb_phy: pointer to USB PHY, if any
  * @hcd: pointer to usb_hcd for ehci host driver
  * @debugfs: root dentry for this controller in debugfs
  * @id_event: indicates there is an id event, and handled at ci_otg_work
@@ -177,6 +177,7 @@ struct ci_hdrc {
 	struct ci_role_driver		*roles[CI_ROLE_END];
 	enum ci_role			role;
 	bool				is_otg;
+	struct usb_otg			otg;
 	struct otg_fsm			fsm;
 	struct ci_otg_fsm_timer_list	*fsm_timer;
 	struct work_struct		work;
@@ -201,7 +202,7 @@ struct ci_hdrc {
 
 	struct ci_hdrc_platform_data	*platdata;
 	int				vbus_active;
-	struct usb_phy			*transceiver;
+	struct usb_phy			*usb_phy;
 	struct usb_hcd			*hcd;
 	struct dentry			*debugfs;
 	bool				id_event;
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index a7ab0f15926..6f8b1b1045b 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -147,7 +147,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 		goto err_clk;
 	}
 
-	pdata.phy = data->phy;
+	pdata.usb_phy = data->phy;
 
 	if (imx_platform_flag->flags & CI_HDRC_IMX_IMX28_WRITE_FIX)
 		pdata.flags |= CI_HDRC_IMX28_WRITE_FIX;
diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c
index 4935ac38fd0..3edf969ed79 100644
--- a/drivers/usb/chipidea/ci_hdrc_msm.c
+++ b/drivers/usb/chipidea/ci_hdrc_msm.c
@@ -26,15 +26,15 @@ static void ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event)
 		dev_dbg(dev, "CI_HDRC_CONTROLLER_RESET_EVENT received\n");
 		writel(0, USB_AHBBURST);
 		writel(0, USB_AHBMODE);
-		usb_phy_init(ci->transceiver);
+		usb_phy_init(ci->usb_phy);
 		break;
 	case CI_HDRC_CONTROLLER_STOPPED_EVENT:
 		dev_dbg(dev, "CI_HDRC_CONTROLLER_STOPPED_EVENT received\n");
 		/*
-		 * Put the transceiver in non-driving mode. Otherwise host
+		 * Put the phy in non-driving mode. Otherwise host
 		 * may not detect soft-disconnection.
 		 */
-		usb_phy_notify_disconnect(ci->transceiver, USB_SPEED_UNKNOWN);
+		usb_phy_notify_disconnect(ci->usb_phy, USB_SPEED_UNKNOWN);
 		break;
 	default:
 		dev_dbg(dev, "unknown ci_hdrc event\n");
@@ -68,7 +68,7 @@ static int ci_hdrc_msm_probe(struct platform_device *pdev)
 	if (IS_ERR(phy))
 		return PTR_ERR(phy);
 
-	ci_hdrc_msm_platdata.phy = phy;
+	ci_hdrc_msm_platdata.usb_phy = phy;
 
 	plat_ci = ci_hdrc_add_device(&pdev->dev,
 				pdev->resource, pdev->num_resources,
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 9bdc6bd7343..30f89426bf0 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -312,7 +312,7 @@ static int ci_usb_phy_init(struct ci_hdrc *ci)
 	case USBPHY_INTERFACE_MODE_UTMI:
 	case USBPHY_INTERFACE_MODE_UTMIW:
 	case USBPHY_INTERFACE_MODE_HSIC:
-		ret = usb_phy_init(ci->transceiver);
+		ret = usb_phy_init(ci->usb_phy);
 		if (ret)
 			return ret;
 		hw_phymode_configure(ci);
@@ -320,12 +320,12 @@ static int ci_usb_phy_init(struct ci_hdrc *ci)
 	case USBPHY_INTERFACE_MODE_ULPI:
 	case USBPHY_INTERFACE_MODE_SERIAL:
 		hw_phymode_configure(ci);
-		ret = usb_phy_init(ci->transceiver);
+		ret = usb_phy_init(ci->usb_phy);
 		if (ret)
 			return ret;
 		break;
 	default:
-		ret = usb_phy_init(ci->transceiver);
+		ret = usb_phy_init(ci->usb_phy);
 	}
 
 	return ret;
@@ -605,13 +605,13 @@ static int ci_hdrc_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	if (ci->platdata->phy)
-		ci->transceiver = ci->platdata->phy;
+	if (ci->platdata->usb_phy)
+		ci->usb_phy = ci->platdata->usb_phy;
 	else
-		ci->transceiver = devm_usb_get_phy(dev, USB_PHY_TYPE_USB2);
+		ci->usb_phy = devm_usb_get_phy(dev, USB_PHY_TYPE_USB2);
 
-	if (IS_ERR(ci->transceiver)) {
-		ret = PTR_ERR(ci->transceiver);
+	if (IS_ERR(ci->usb_phy)) {
+		ret = PTR_ERR(ci->usb_phy);
 		/*
 		 * if -ENXIO is returned, it means PHY layer wasn't
 		 * enabled, so it makes no sense to return -EPROBE_DEFER
@@ -728,7 +728,7 @@ static int ci_hdrc_probe(struct platform_device *pdev)
 stop:
 	ci_role_destroy(ci);
 deinit_phy:
-	usb_phy_shutdown(ci->transceiver);
+	usb_phy_shutdown(ci->usb_phy);
 
 	return ret;
 }
@@ -741,7 +741,7 @@ static int ci_hdrc_remove(struct platform_device *pdev)
 	free_irq(ci->irq, ci);
 	ci_role_destroy(ci);
 	ci_hdrc_enter_lpm(ci, true);
-	usb_phy_shutdown(ci->transceiver);
+	usb_phy_shutdown(ci->usb_phy);
 
 	return 0;
 }
diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c
index f038804d13d..268e4236e84 100644
--- a/drivers/usb/chipidea/debug.c
+++ b/drivers/usb/chipidea/debug.c
@@ -220,7 +220,7 @@ static int ci_otg_show(struct seq_file *s, void *unused)
 
 	/* ------ State ----- */
 	seq_printf(s, "OTG state: %s\n\n",
-		usb_otg_state_string(ci->transceiver->otg->state));
+			usb_otg_state_string(ci->otg.state));
 
 	/* ------ State Machine Variables ----- */
 	seq_printf(s, "a_bus_drop: %d\n", fsm->a_bus_drop);
diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c
index ebde7b6ce68..789809f680a 100644
--- a/drivers/usb/chipidea/host.c
+++ b/drivers/usb/chipidea/host.c
@@ -59,7 +59,7 @@ static int host_start(struct ci_hdrc *ci)
 	hcd->has_tt = 1;
 
 	hcd->power_budget = ci->platdata->power_budget;
-	hcd->usb_phy = ci->transceiver;
+	hcd->usb_phy = ci->usb_phy;
 	hcd->tpl_support = ci->platdata->tpl_support;
 
 	ehci = hcd_to_ehci(hcd);
@@ -86,10 +86,11 @@ static int host_start(struct ci_hdrc *ci)
 	if (ret) {
 		goto disable_reg;
 	} else {
-		struct usb_otg *otg = ci->transceiver->otg;
+		struct usb_otg *otg = &ci->otg;
 
 		ci->hcd = hcd;
-		if (otg) {
+
+		if (ci_otg_is_fsm_mode(ci)) {
 			otg->host = &hcd->self;
 			hcd->self.otg_port = 1;
 		}
diff --git a/drivers/usb/chipidea/otg_fsm.c b/drivers/usb/chipidea/otg_fsm.c
index d8490e758a7..862d7cb01b9 100644
--- a/drivers/usb/chipidea/otg_fsm.c
+++ b/drivers/usb/chipidea/otg_fsm.c
@@ -778,20 +778,10 @@ void ci_hdrc_otg_fsm_start(struct ci_hdrc *ci)
 int ci_hdrc_otg_fsm_init(struct ci_hdrc *ci)
 {
 	int retval = 0;
-	struct usb_otg *otg;
 
-	otg = devm_kzalloc(ci->dev,
-			sizeof(struct usb_otg), GFP_KERNEL);
-	if (!otg) {
-		dev_err(ci->dev,
-		"Failed to allocate usb_otg structure for ci hdrc otg!\n");
-		return -ENOMEM;
-	}
-
-	otg->usb_phy = ci->transceiver;
-	otg->gadget = &ci->gadget;
-	ci->fsm.otg = otg;
-	ci->transceiver->otg = ci->fsm.otg;
+	ci->otg.usb_phy = ci->usb_phy;
+	ci->otg.gadget = &ci->gadget;
+	ci->fsm.otg = &ci->otg;
 	ci->fsm.power_up = 1;
 	ci->fsm.id = hw_read_otgsc(ci, OTGSC_ID) ? 1 : 0;
 	ci->fsm.otg->state = OTG_STATE_UNDEFINED;
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index f4397b29891..a2d80ab3d9c 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -1519,8 +1519,8 @@ static int ci_udc_vbus_draw(struct usb_gadget *_gadget, unsigned ma)
 {
 	struct ci_hdrc *ci = container_of(_gadget, struct ci_hdrc, gadget);
 
-	if (ci->transceiver)
-		return usb_phy_set_power(ci->transceiver, ma);
+	if (ci->usb_phy)
+		return usb_phy_set_power(ci->usb_phy, ma);
 	return -ENOTSUPP;
 }
 
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index b84fb141e12..6a2a2fd990a 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2648,7 +2648,7 @@ int usb_add_hcd(struct usb_hcd *hcd,
 		}
 	}
 
-	if (IS_ENABLED(CONFIG_GENERIC_PHY)) {
+	if (IS_ENABLED(CONFIG_GENERIC_PHY) && !hcd->phy) {
 		struct phy *phy = phy_get(hcd->self.controller, "usb");
 
 		if (IS_ERR(phy)) {
@@ -2668,6 +2668,7 @@ int usb_add_hcd(struct usb_hcd *hcd,
 				goto err_phy;
 			}
 			hcd->phy = phy;
+			hcd->remove_phy = 1;
 		}
 	}
 
@@ -2814,7 +2815,7 @@ err_allocate_root_hub:
 err_register_bus:
 	hcd_buffer_destroy(hcd);
 err_create_buf:
-	if (IS_ENABLED(CONFIG_GENERIC_PHY) && hcd->phy) {
+	if (IS_ENABLED(CONFIG_GENERIC_PHY) && hcd->remove_phy && hcd->phy) {
 		phy_power_off(hcd->phy);
 		phy_exit(hcd->phy);
 		phy_put(hcd->phy);
@@ -2898,7 +2899,7 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 	usb_deregister_bus(&hcd->self);
 	hcd_buffer_destroy(hcd);
 
-	if (IS_ENABLED(CONFIG_GENERIC_PHY) && hcd->phy) {
+	if (IS_ENABLED(CONFIG_GENERIC_PHY) && hcd->remove_phy && hcd->phy) {
 		phy_power_off(hcd->phy);
 		phy_exit(hcd->phy);
 		phy_put(hcd->phy);
diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h
index e14c09a45c5..4fe161a84c7 100644
--- a/include/linux/usb/chipidea.h
+++ b/include/linux/usb/chipidea.h
@@ -13,7 +13,7 @@ struct ci_hdrc_platform_data {
 	/* offset of the capability registers */
 	uintptr_t	 capoffset;
 	unsigned	 power_budget;
-	struct usb_phy	*phy;
+	struct usb_phy	*usb_phy;
 	enum usb_phy_interface phy_mode;
 	unsigned long	 flags;
 #define CI_HDRC_REGS_SHARED		BIT(0)
-- 
cgit v1.2.3-70-g09d2


From 1e5e2d3d055436c114e2f16145b83339aed024ff Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@free-electrons.com>
Date: Thu, 30 Oct 2014 18:41:19 +0100
Subject: usb: chipidea: add support to the generic PHY framework

This patch adds support of the PHY framework for ChipIdea drivers.
Changes are done in both the ChipIdea common code and in the drivers
accessing the PHY. This is done by adding a new PHY member in
ChipIdea's structures and by taking care of it in the code.

Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com>
Acked-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/chipidea/ci.h      |  5 ++-
 drivers/usb/chipidea/core.c    | 83 +++++++++++++++++++++++++++++++++---------
 drivers/usb/chipidea/host.c    |  5 ++-
 drivers/usb/chipidea/otg_fsm.c |  6 ++-
 include/linux/usb/chipidea.h   |  2 +
 5 files changed, 80 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h
index 9015139a802..5bbfcc73cf7 100644
--- a/drivers/usb/chipidea/ci.h
+++ b/drivers/usb/chipidea/ci.h
@@ -161,7 +161,8 @@ struct hw_bank {
  * @test_mode: the selected test mode
  * @platdata: platform specific information supplied by parent device
  * @vbus_active: is VBUS active
- * @usb_phy: pointer to USB PHY, if any
+ * @phy: pointer to PHY, if any
+ * @usb_phy: pointer to USB PHY, if any and if using the USB PHY framework
  * @hcd: pointer to usb_hcd for ehci host driver
  * @debugfs: root dentry for this controller in debugfs
  * @id_event: indicates there is an id event, and handled at ci_otg_work
@@ -202,6 +203,8 @@ struct ci_hdrc {
 
 	struct ci_hdrc_platform_data	*platdata;
 	int				vbus_active;
+	struct phy			*phy;
+	/* old usb_phy interface */
 	struct usb_phy			*usb_phy;
 	struct usb_hcd			*hcd;
 	struct dentry			*debugfs;
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 30f89426bf0..60578d9c896 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -47,6 +47,7 @@
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/module.h>
 #include <linux/idr.h>
@@ -298,6 +299,49 @@ static void hw_phymode_configure(struct ci_hdrc *ci)
 	}
 }
 
+/**
+ * _ci_usb_phy_init: initialize phy taking in account both phy and usb_phy
+ * interfaces
+ * @ci: the controller
+ *
+ * This function returns an error code if the phy failed to init
+ */
+static int _ci_usb_phy_init(struct ci_hdrc *ci)
+{
+	int ret;
+
+	if (ci->phy) {
+		ret = phy_init(ci->phy);
+		if (ret)
+			return ret;
+
+		ret = phy_power_on(ci->phy);
+		if (ret) {
+			phy_exit(ci->phy);
+			return ret;
+		}
+	} else {
+		ret = usb_phy_init(ci->usb_phy);
+	}
+
+	return ret;
+}
+
+/**
+ * _ci_usb_phy_exit: deinitialize phy taking in account both phy and usb_phy
+ * interfaces
+ * @ci: the controller
+ */
+static void ci_usb_phy_exit(struct ci_hdrc *ci)
+{
+	if (ci->phy) {
+		phy_power_off(ci->phy);
+		phy_exit(ci->phy);
+	} else {
+		usb_phy_shutdown(ci->usb_phy);
+	}
+}
+
 /**
  * ci_usb_phy_init: initialize phy according to different phy type
  * @ci: the controller
@@ -312,7 +356,7 @@ static int ci_usb_phy_init(struct ci_hdrc *ci)
 	case USBPHY_INTERFACE_MODE_UTMI:
 	case USBPHY_INTERFACE_MODE_UTMIW:
 	case USBPHY_INTERFACE_MODE_HSIC:
-		ret = usb_phy_init(ci->usb_phy);
+		ret = _ci_usb_phy_init(ci);
 		if (ret)
 			return ret;
 		hw_phymode_configure(ci);
@@ -320,12 +364,12 @@ static int ci_usb_phy_init(struct ci_hdrc *ci)
 	case USBPHY_INTERFACE_MODE_ULPI:
 	case USBPHY_INTERFACE_MODE_SERIAL:
 		hw_phymode_configure(ci);
-		ret = usb_phy_init(ci->usb_phy);
+		ret = _ci_usb_phy_init(ci);
 		if (ret)
 			return ret;
 		break;
 	default:
-		ret = usb_phy_init(ci->usb_phy);
+		ret = _ci_usb_phy_init(ci);
 	}
 
 	return ret;
@@ -605,23 +649,26 @@ static int ci_hdrc_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	if (ci->platdata->usb_phy)
+	if (ci->platdata->phy) {
+		ci->phy = ci->platdata->phy;
+	} else if (ci->platdata->usb_phy) {
 		ci->usb_phy = ci->platdata->usb_phy;
-	else
+	} else {
+		ci->phy = devm_phy_get(dev, "usb-phy");
 		ci->usb_phy = devm_usb_get_phy(dev, USB_PHY_TYPE_USB2);
 
-	if (IS_ERR(ci->usb_phy)) {
-		ret = PTR_ERR(ci->usb_phy);
-		/*
-		 * if -ENXIO is returned, it means PHY layer wasn't
-		 * enabled, so it makes no sense to return -EPROBE_DEFER
-		 * in that case, since no PHY driver will ever probe.
-		 */
-		if (ret == -ENXIO)
-			return ret;
+		/* if both generic PHY and USB PHY layers aren't enabled */
+		if (PTR_ERR(ci->phy) == -ENOSYS &&
+				PTR_ERR(ci->usb_phy) == -ENXIO)
+			return -ENXIO;
+
+		if (IS_ERR(ci->phy) && IS_ERR(ci->usb_phy))
+			return -EPROBE_DEFER;
 
-		dev_err(dev, "no usb2 phy configured\n");
-		return -EPROBE_DEFER;
+		if (IS_ERR(ci->phy))
+			ci->phy = NULL;
+		else if (IS_ERR(ci->usb_phy))
+			ci->usb_phy = NULL;
 	}
 
 	ret = ci_usb_phy_init(ci);
@@ -728,7 +775,7 @@ static int ci_hdrc_probe(struct platform_device *pdev)
 stop:
 	ci_role_destroy(ci);
 deinit_phy:
-	usb_phy_shutdown(ci->usb_phy);
+	ci_usb_phy_exit(ci);
 
 	return ret;
 }
@@ -741,7 +788,7 @@ static int ci_hdrc_remove(struct platform_device *pdev)
 	free_irq(ci->irq, ci);
 	ci_role_destroy(ci);
 	ci_hdrc_enter_lpm(ci, true);
-	usb_phy_shutdown(ci->usb_phy);
+	ci_usb_phy_exit(ci);
 
 	return 0;
 }
diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c
index 789809f680a..4f8eb40ad93 100644
--- a/drivers/usb/chipidea/host.c
+++ b/drivers/usb/chipidea/host.c
@@ -59,8 +59,11 @@ static int host_start(struct ci_hdrc *ci)
 	hcd->has_tt = 1;
 
 	hcd->power_budget = ci->platdata->power_budget;
-	hcd->usb_phy = ci->usb_phy;
 	hcd->tpl_support = ci->platdata->tpl_support;
+	if (ci->phy)
+		hcd->phy = ci->phy;
+	else
+		hcd->usb_phy = ci->usb_phy;
 
 	ehci = hcd_to_ehci(hcd);
 	ehci->caps = ci->hw_bank.cap;
diff --git a/drivers/usb/chipidea/otg_fsm.c b/drivers/usb/chipidea/otg_fsm.c
index 862d7cb01b9..3c2ab1ae00f 100644
--- a/drivers/usb/chipidea/otg_fsm.c
+++ b/drivers/usb/chipidea/otg_fsm.c
@@ -779,7 +779,11 @@ int ci_hdrc_otg_fsm_init(struct ci_hdrc *ci)
 {
 	int retval = 0;
 
-	ci->otg.usb_phy = ci->usb_phy;
+	if (ci->phy)
+		ci->otg.phy = ci->phy;
+	else
+		ci->otg.usb_phy = ci->usb_phy;
+
 	ci->otg.gadget = &ci->gadget;
 	ci->fsm.otg = &ci->otg;
 	ci->fsm.power_up = 1;
diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h
index 4fe161a84c7..c01bf4ea27b 100644
--- a/include/linux/usb/chipidea.h
+++ b/include/linux/usb/chipidea.h
@@ -13,6 +13,8 @@ struct ci_hdrc_platform_data {
 	/* offset of the capability registers */
 	uintptr_t	 capoffset;
 	unsigned	 power_budget;
+	struct phy	*phy;
+	/* old usb_phy interface */
 	struct usb_phy	*usb_phy;
 	enum usb_phy_interface phy_mode;
 	unsigned long	 flags;
-- 
cgit v1.2.3-70-g09d2


From c53a2b512b6f2b9b1b6353c1587b8b069997852f Mon Sep 17 00:00:00 2001
From: Huang Rui <ray.huang@amd.com>
Date: Fri, 31 Oct 2014 11:11:15 +0800
Subject: PCI: Add support for AMD Nolan USB3 DRD

This patch adds PCI id for USB3 Dual-Role Device of AMD Nolan (NL) SoC.
It will be used for PCI quirks and DWC3 device driver.

Signed-off-by: Jason Chang <jason.chang@amd.com>
Signed-off-by: Huang Rui <ray.huang@amd.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 include/linux/pci_ids.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 1fa99a30181..5decad77d8e 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -562,6 +562,7 @@
 #define PCI_DEVICE_ID_AMD_8131_BRIDGE	0x7450
 #define PCI_DEVICE_ID_AMD_8131_APIC	0x7451
 #define PCI_DEVICE_ID_AMD_8132_BRIDGE	0x7458
+#define PCI_DEVICE_ID_AMD_NL_USB	0x7912
 #define PCI_DEVICE_ID_AMD_CS5535_IDE    0x208F
 #define PCI_DEVICE_ID_AMD_CS5536_ISA    0x2090
 #define PCI_DEVICE_ID_AMD_CS5536_FLASH  0x2091
-- 
cgit v1.2.3-70-g09d2


From f353d71f75394e518b4d939aea2030d8e239dd41 Mon Sep 17 00:00:00 2001
From: Masanari Iida <standby24x7@gmail.com>
Date: Wed, 22 Oct 2014 00:00:14 +0900
Subject: treewide: Fix typo in Documentation/DocBook/device-drivers

This patch fix speeling typo found in html files within
Documentation/DocBook/device-drivers.
It is because html files are generated from comments in source,
so I have to fix comments in the source.

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 drivers/dma-buf/fence.c | 2 +-
 include/linux/fence.h   | 4 ++--
 include/linux/i2c.h     | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/dma-buf/fence.c b/drivers/dma-buf/fence.c
index 7bb9d65d9a2..e5541117b3e 100644
--- a/drivers/dma-buf/fence.c
+++ b/drivers/dma-buf/fence.c
@@ -283,7 +283,7 @@ EXPORT_SYMBOL(fence_add_callback);
  * @cb:		[in]	the callback to remove
  *
  * Remove a previously queued callback from the fence. This function returns
- * true if the callback is succesfully removed, or false if the fence has
+ * true if the callback is successfully removed, or false if the fence has
  * already been signaled.
  *
  * *WARNING*:
diff --git a/include/linux/fence.h b/include/linux/fence.h
index d174585b874..39efee130d2 100644
--- a/include/linux/fence.h
+++ b/include/linux/fence.h
@@ -128,8 +128,8 @@ struct fence_cb {
  * from irq context, so normal spinlocks can be used.
  *
  * A return value of false indicates the fence already passed,
- * or some failure occured that made it impossible to enable
- * signaling. True indicates succesful enabling.
+ * or some failure occurred that made it impossible to enable
+ * signaling. True indicates successful enabling.
  *
  * fence->status may be set in enable_signaling, but only when false is
  * returned.
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index b556e0ab946..70ee0d3a2be 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -359,7 +359,7 @@ i2c_register_board_info(int busnum, struct i2c_board_info const *info,
  * to name two of the most common.
  *
  * The return codes from the @master_xfer field should indicate the type of
- * error code that occured during the transfer, as documented in the kernel
+ * error code that occurred during the transfer, as documented in the kernel
  * Documentation file Documentation/i2c/fault-codes.
  */
 struct i2c_algorithm {
-- 
cgit v1.2.3-70-g09d2


From 4cdb1e2e3d3495423db558d3bb7ed11d66aabce7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 2 Nov 2014 06:00:12 -0800
Subject: net: shrink struct softnet_data

flow_limit in struct softnet_data is only read from local cpu
and can be moved to fill a hole, reducing softnet_data size by
64 bytes on x86_64

While we are at it, move output_queue, output_queue_tailp and
completion_queue, so that rx / tx paths touch a single cache line.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c85e0651224..5ed05bd764d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2329,10 +2329,7 @@ extern int netdev_flow_limit_table_len;
  * Incoming packets are placed on per-cpu queues
  */
 struct softnet_data {
-	struct Qdisc		*output_queue;
-	struct Qdisc		**output_queue_tailp;
 	struct list_head	poll_list;
-	struct sk_buff		*completion_queue;
 	struct sk_buff_head	process_queue;
 
 	/* stats */
@@ -2340,10 +2337,17 @@ struct softnet_data {
 	unsigned int		time_squeeze;
 	unsigned int		cpu_collision;
 	unsigned int		received_rps;
-
 #ifdef CONFIG_RPS
 	struct softnet_data	*rps_ipi_list;
+#endif
+#ifdef CONFIG_NET_FLOW_LIMIT
+	struct sd_flow_limit __rcu *flow_limit;
+#endif
+	struct Qdisc		*output_queue;
+	struct Qdisc		**output_queue_tailp;
+	struct sk_buff		*completion_queue;
 
+#ifdef CONFIG_RPS
 	/* Elements below can be accessed between CPUs for RPS */
 	struct call_single_data	csd ____cacheline_aligned_in_smp;
 	struct softnet_data	*rps_ipi_next;
@@ -2355,9 +2359,6 @@ struct softnet_data {
 	struct sk_buff_head	input_pkt_queue;
 	struct napi_struct	backlog;
 
-#ifdef CONFIG_NET_FLOW_LIMIT
-	struct sd_flow_limit __rcu *flow_limit;
-#endif
 };
 
 static inline void input_queue_head_incr(struct softnet_data *sd)
-- 
cgit v1.2.3-70-g09d2


From d475c95b4bcff983ac76e8522bfd2d29bcc567d0 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Sun, 2 Nov 2014 16:26:17 +0200
Subject: net/mlx4_core: Add retrieval of CONFIG_DEV parameters

Add code to issue CONFIG_DEV "get" firmware command.

This command is used in order to obtain certain parameters used for
supporting various RX checksumming options and vxlan UDP port.

The GET operation is allowed for VFs too.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Shani Michaeli <shanim@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c           |  4 +-
 drivers/net/ethernet/mellanox/mlx4/fw.c            | 88 +++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h          |  5 ++
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  | 17 +++++
 include/linux/mlx4/cmd.h                           | 29 +++++++
 include/linux/mlx4/device.h                        |  3 +-
 6 files changed, 139 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 1312ccf8b83..3c05e5878b4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -990,11 +990,11 @@ static struct mlx4_cmd_info cmd_info[] = {
 	{
 		.opcode = MLX4_CMD_CONFIG_DEV,
 		.has_inbox = false,
-		.has_outbox = false,
+		.has_outbox = true,
 		.out_is_imm = false,
 		.encode_slave_id = false,
 		.verify = NULL,
-		.wrapper = mlx4_CMD_EPERM_wrapper
+		.wrapper = mlx4_CONFIG_DEV_wrapper
 	},
 	{
 		.opcode = MLX4_CMD_ALLOC_RES,
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index e7639e31fc8..d6dba77ae4b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -141,7 +141,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[12] = "Large cache line (>64B) CQE stride support",
 		[13] = "Large cache line (>64B) EQE stride support",
 		[14] = "Ethernet protocol control support",
-		[15] = "Ethernet Backplane autoneg support"
+		[15] = "Ethernet Backplane autoneg support",
+		[16] = "CONFIG DEV support"
 	};
 	int i;
 
@@ -574,6 +575,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_MTT_ENTRY_SZ_OFFSET	0x90
 #define QUERY_DEV_CAP_D_MPT_ENTRY_SZ_OFFSET	0x92
 #define QUERY_DEV_CAP_BMME_FLAGS_OFFSET		0x94
+#define QUERY_DEV_CAP_CONFIG_DEV_OFFSET		0x94
 #define QUERY_DEV_CAP_RSVD_LKEY_OFFSET		0x98
 #define QUERY_DEV_CAP_MAX_ICM_SZ_OFFSET		0xa0
 #define QUERY_DEV_CAP_ETH_BACKPL_OFFSET		0x9c
@@ -749,6 +751,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_EQE_STRIDE;
 	MLX4_GET(dev_cap->bmme_flags, outbox,
 		 QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
+	MLX4_GET(field, outbox, QUERY_DEV_CAP_CONFIG_DEV_OFFSET);
+	if (field & 0x20)
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_CONFIG_DEV;
 	MLX4_GET(dev_cap->reserved_lkey, outbox,
 		 QUERY_DEV_CAP_RSVD_LKEY_OFFSET);
 	MLX4_GET(field32, outbox, QUERY_DEV_CAP_ETH_BACKPL_OFFSET);
@@ -1849,14 +1854,18 @@ int mlx4_CLOSE_HCA(struct mlx4_dev *dev, int panic)
 
 struct mlx4_config_dev {
 	__be32	update_flags;
-	__be32	rsdv1[3];
+	__be32	rsvd1[3];
 	__be16	vxlan_udp_dport;
 	__be16	rsvd2;
+	__be32	rsvd3[27];
+	__be16	rsvd4;
+	u8	rsvd5;
+	u8	rx_checksum_val;
 };
 
 #define MLX4_VXLAN_UDP_DPORT (1 << 0)
 
-static int mlx4_CONFIG_DEV(struct mlx4_dev *dev, struct mlx4_config_dev *config_dev)
+static int mlx4_CONFIG_DEV_set(struct mlx4_dev *dev, struct mlx4_config_dev *config_dev)
 {
 	int err;
 	struct mlx4_cmd_mailbox *mailbox;
@@ -1874,6 +1883,77 @@ static int mlx4_CONFIG_DEV(struct mlx4_dev *dev, struct mlx4_config_dev *config_
 	return err;
 }
 
+static int mlx4_CONFIG_DEV_get(struct mlx4_dev *dev, struct mlx4_config_dev *config_dev)
+{
+	int err;
+	struct mlx4_cmd_mailbox *mailbox;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 1, MLX4_CMD_CONFIG_DEV,
+			   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
+
+	if (!err)
+		memcpy(config_dev, mailbox->buf, sizeof(*config_dev));
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+
+/* Conversion between the HW values and the actual functionality.
+ * The value represented by the array index,
+ * and the functionality determined by the flags.
+ */
+static const u8 config_dev_csum_flags[] = {
+	[0] =	0,
+	[1] =	MLX4_RX_CSUM_MODE_VAL_NON_TCP_UDP,
+	[2] =	MLX4_RX_CSUM_MODE_VAL_NON_TCP_UDP	|
+		MLX4_RX_CSUM_MODE_L4,
+	[3] =	MLX4_RX_CSUM_MODE_L4			|
+		MLX4_RX_CSUM_MODE_IP_OK_IP_NON_TCP_UDP	|
+		MLX4_RX_CSUM_MODE_MULTI_VLAN
+};
+
+int mlx4_config_dev_retrieval(struct mlx4_dev *dev,
+			      struct mlx4_config_dev_params *params)
+{
+	struct mlx4_config_dev config_dev;
+	int err;
+	u8 csum_mask;
+
+#define CONFIG_DEV_RX_CSUM_MODE_MASK			0x7
+#define CONFIG_DEV_RX_CSUM_MODE_PORT1_BIT_OFFSET	0
+#define CONFIG_DEV_RX_CSUM_MODE_PORT2_BIT_OFFSET	4
+
+	if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_CONFIG_DEV))
+		return -ENOTSUPP;
+
+	err = mlx4_CONFIG_DEV_get(dev, &config_dev);
+	if (err)
+		return err;
+
+	csum_mask = (config_dev.rx_checksum_val >> CONFIG_DEV_RX_CSUM_MODE_PORT1_BIT_OFFSET) &
+			CONFIG_DEV_RX_CSUM_MODE_MASK;
+
+	if (csum_mask >= sizeof(config_dev_csum_flags)/sizeof(config_dev_csum_flags[0]))
+		return -EINVAL;
+	params->rx_csum_flags_port_1 = config_dev_csum_flags[csum_mask];
+
+	csum_mask = (config_dev.rx_checksum_val >> CONFIG_DEV_RX_CSUM_MODE_PORT2_BIT_OFFSET) &
+			CONFIG_DEV_RX_CSUM_MODE_MASK;
+
+	if (csum_mask >= sizeof(config_dev_csum_flags)/sizeof(config_dev_csum_flags[0]))
+		return -EINVAL;
+	params->rx_csum_flags_port_2 = config_dev_csum_flags[csum_mask];
+
+	params->vxlan_udp_dport = be16_to_cpu(config_dev.vxlan_udp_dport);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_config_dev_retrieval);
+
 int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port)
 {
 	struct mlx4_config_dev config_dev;
@@ -1882,7 +1962,7 @@ int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port)
 	config_dev.update_flags    = cpu_to_be32(MLX4_VXLAN_UDP_DPORT);
 	config_dev.vxlan_udp_dport = udp_port;
 
-	return mlx4_CONFIG_DEV(dev, &config_dev);
+	return mlx4_CONFIG_DEV_set(dev, &config_dev);
 }
 EXPORT_SYMBOL_GPL(mlx4_config_vxlan_port);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 254ec7b1ca2..f8fc7bd6f48 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -947,6 +947,11 @@ int mlx4_SW2HW_EQ_wrapper(struct mlx4_dev *dev, int slave,
 			  struct mlx4_cmd_mailbox *inbox,
 			  struct mlx4_cmd_mailbox *outbox,
 			  struct mlx4_cmd_info *cmd);
+int mlx4_CONFIG_DEV_wrapper(struct mlx4_dev *dev, int slave,
+			    struct mlx4_vhcr *vhcr,
+			    struct mlx4_cmd_mailbox *inbox,
+			    struct mlx4_cmd_mailbox *outbox,
+			    struct mlx4_cmd_info *cmd);
 int mlx4_DMA_wrapper(struct mlx4_dev *dev, int slave,
 		     struct mlx4_vhcr *vhcr,
 		     struct mlx4_cmd_mailbox *inbox,
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 5d2498dcf53..d718ca0f88d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2872,6 +2872,23 @@ out_add:
 	return err;
 }
 
+int mlx4_CONFIG_DEV_wrapper(struct mlx4_dev *dev, int slave,
+			    struct mlx4_vhcr *vhcr,
+			    struct mlx4_cmd_mailbox *inbox,
+			    struct mlx4_cmd_mailbox *outbox,
+			    struct mlx4_cmd_info *cmd)
+{
+	int err;
+	u8 get = vhcr->op_modifier;
+
+	if (get != 1)
+		return -EPERM;
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+
+	return err;
+}
+
 static int get_containing_mtt(struct mlx4_dev *dev, int slave, int start,
 			      int len, struct res_mtt **res)
 {
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index ff5f5deb3dc..64d25941b32 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -199,6 +199,33 @@ enum {
 	MLX4_CMD_NATIVE
 };
 
+/*
+ * MLX4_RX_CSUM_MODE_VAL_NON_TCP_UDP -
+ * Receive checksum value is reported in CQE also for non TCP/UDP packets.
+ *
+ * MLX4_RX_CSUM_MODE_L4 -
+ * L4_CSUM bit in CQE, which indicates whether or not L4 checksum
+ * was validated correctly, is supported.
+ *
+ * MLX4_RX_CSUM_MODE_IP_OK_IP_NON_TCP_UDP -
+ * IP_OK CQE's field is supported also for non TCP/UDP IP packets.
+ *
+ * MLX4_RX_CSUM_MODE_MULTI_VLAN -
+ * Receive Checksum offload is supported for packets with more than 2 vlan headers.
+ */
+enum mlx4_rx_csum_mode {
+	MLX4_RX_CSUM_MODE_VAL_NON_TCP_UDP		= 1UL << 0,
+	MLX4_RX_CSUM_MODE_L4				= 1UL << 1,
+	MLX4_RX_CSUM_MODE_IP_OK_IP_NON_TCP_UDP		= 1UL << 2,
+	MLX4_RX_CSUM_MODE_MULTI_VLAN			= 1UL << 3
+};
+
+struct mlx4_config_dev_params {
+	u16	vxlan_udp_dport;
+	u8	rx_csum_flags_port_1;
+	u8	rx_csum_flags_port_2;
+};
+
 struct mlx4_dev;
 
 struct mlx4_cmd_mailbox {
@@ -250,6 +277,8 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos);
 int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting);
 int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_info *ivf);
 int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_state);
+int mlx4_config_dev_retrieval(struct mlx4_dev *dev,
+			      struct mlx4_config_dev_params *params);
 /*
  * mlx4_get_slave_default_vlan -
  * return true if VST ( default vlan)
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index e4c136ebe79..5cc5eac47d1 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -188,7 +188,8 @@ enum {
 	MLX4_DEV_CAP_FLAG2_CQE_STRIDE		= 1LL <<  12,
 	MLX4_DEV_CAP_FLAG2_EQE_STRIDE		= 1LL <<  13,
 	MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL        = 1LL <<  14,
-	MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP	= 1LL <<  15
+	MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP	= 1LL <<  15,
+	MLX4_DEV_CAP_FLAG2_CONFIG_DEV		= 1LL <<  16
 };
 
 enum {
-- 
cgit v1.2.3-70-g09d2


From 946e51f2bf37f1656916eb75bd0742ba33983c28 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 26 Oct 2014 19:19:16 -0400
Subject: move d_rcu from overlapping d_child to overlapping d_alias

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/powerpc/platforms/cell/spufs/inode.c       |  2 +-
 drivers/staging/lustre/lustre/llite/dcache.c    |  2 +-
 drivers/staging/lustre/lustre/llite/llite_lib.c |  2 +-
 drivers/staging/lustre/lustre/llite/namei.c     |  8 ++--
 fs/affs/amigaffs.c                              |  2 +-
 fs/autofs4/expire.c                             | 12 +++---
 fs/autofs4/root.c                               |  2 +-
 fs/ceph/dir.c                                   |  8 ++--
 fs/ceph/inode.c                                 |  2 +-
 fs/cifs/inode.c                                 |  2 +-
 fs/coda/cache.c                                 |  2 +-
 fs/dcache.c                                     | 53 ++++++++++++-------------
 fs/debugfs/inode.c                              |  2 +-
 fs/exportfs/expfs.c                             |  2 +-
 fs/libfs.c                                      | 12 +++---
 fs/ncpfs/dir.c                                  |  2 +-
 fs/ncpfs/ncplib_kernel.h                        |  4 +-
 fs/nfs/getroot.c                                |  2 +-
 fs/notify/fsnotify.c                            |  4 +-
 fs/ocfs2/dcache.c                               |  2 +-
 include/linux/dcache.h                          |  8 ++--
 kernel/trace/trace.c                            |  4 +-
 kernel/trace/trace_events.c                     |  2 +-
 security/selinux/selinuxfs.c                    |  6 +--
 24 files changed, 73 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 87ba7cf99cd..65d633f20d3 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -164,7 +164,7 @@ static void spufs_prune_dir(struct dentry *dir)
 	struct dentry *dentry, *tmp;
 
 	mutex_lock(&dir->d_inode->i_mutex);
-	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_u.d_child) {
+	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) {
 		spin_lock(&dentry->d_lock);
 		if (!(d_unhashed(dentry)) && dentry->d_inode) {
 			dget_dlock(dentry);
diff --git a/drivers/staging/lustre/lustre/llite/dcache.c b/drivers/staging/lustre/lustre/llite/dcache.c
index 439e4875b05..311907b762b 100644
--- a/drivers/staging/lustre/lustre/llite/dcache.c
+++ b/drivers/staging/lustre/lustre/llite/dcache.c
@@ -258,7 +258,7 @@ void ll_invalidate_aliases(struct inode *inode)
 	       inode->i_ino, inode->i_generation, inode);
 
 	ll_lock_dcache(inode);
-	ll_d_hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
+	ll_d_hlist_for_each_entry(dentry, p, &inode->i_dentry, d_u.d_alias) {
 		CDEBUG(D_DENTRY, "dentry in drop %.*s (%p) parent %p "
 		       "inode %p flags %d\n", dentry->d_name.len,
 		       dentry->d_name.name, dentry, dentry->d_parent,
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index a8bcc51057f..f4ca7b75302 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -711,7 +711,7 @@ void lustre_dump_dentry(struct dentry *dentry, int recur)
 		return;
 
 	list_for_each(tmp, &dentry->d_subdirs) {
-		struct dentry *d = list_entry(tmp, struct dentry, d_u.d_child);
+		struct dentry *d = list_entry(tmp, struct dentry, d_child);
 		lustre_dump_dentry(d, recur - 1);
 	}
 }
diff --git a/drivers/staging/lustre/lustre/llite/namei.c b/drivers/staging/lustre/lustre/llite/namei.c
index 7a68c1e027e..6dfd9850926 100644
--- a/drivers/staging/lustre/lustre/llite/namei.c
+++ b/drivers/staging/lustre/lustre/llite/namei.c
@@ -167,14 +167,14 @@ static void ll_invalidate_negative_children(struct inode *dir)
 	struct ll_d_hlist_node *p;
 
 	ll_lock_dcache(dir);
-	ll_d_hlist_for_each_entry(dentry, p, &dir->i_dentry, d_alias) {
+	ll_d_hlist_for_each_entry(dentry, p, &dir->i_dentry, d_u.d_alias) {
 		spin_lock(&dentry->d_lock);
 		if (!list_empty(&dentry->d_subdirs)) {
 			struct dentry *child;
 
 			list_for_each_entry_safe(child, tmp_subdir,
 						 &dentry->d_subdirs,
-						 d_u.d_child) {
+						 d_child) {
 				if (child->d_inode == NULL)
 					d_lustre_invalidate(child, 1);
 			}
@@ -362,7 +362,7 @@ static struct dentry *ll_find_alias(struct inode *inode, struct dentry *dentry)
 	discon_alias = invalid_alias = NULL;
 
 	ll_lock_dcache(inode);
-	ll_d_hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) {
+	ll_d_hlist_for_each_entry(alias, p, &inode->i_dentry, d_u.d_alias) {
 		LASSERT(alias != dentry);
 
 		spin_lock(&alias->d_lock);
@@ -953,7 +953,7 @@ static void ll_get_child_fid(struct inode * dir, struct qstr *name,
 {
 	struct dentry *parent, *child;
 
-	parent = ll_d_hlist_entry(dir->i_dentry, struct dentry, d_alias);
+	parent = ll_d_hlist_entry(dir->i_dentry, struct dentry, d_u.d_alias);
 	child = d_lookup(parent, name);
 	if (child) {
 		if (child->d_inode)
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index abc853968fe..937ce8754b2 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -125,7 +125,7 @@ affs_fix_dcache(struct inode *inode, u32 entry_ino)
 {
 	struct dentry *dentry;
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
 		if (entry_ino == (u32)(long)dentry->d_fsdata) {
 			dentry->d_fsdata = (void *)inode->i_ino;
 			break;
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 683a5b9ce22..dcdec6fd33c 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -85,7 +85,7 @@ static struct dentry *get_next_positive_subdir(struct dentry *prev,
 	spin_lock(&root->d_lock);
 
 	if (prev)
-		next = prev->d_u.d_child.next;
+		next = prev->d_child.next;
 	else {
 		prev = dget_dlock(root);
 		next = prev->d_subdirs.next;
@@ -99,13 +99,13 @@ cont:
 		return NULL;
 	}
 
-	q = list_entry(next, struct dentry, d_u.d_child);
+	q = list_entry(next, struct dentry, d_child);
 
 	spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED);
 	/* Already gone or negative dentry (under construction) - try next */
 	if (!d_count(q) || !simple_positive(q)) {
 		spin_unlock(&q->d_lock);
-		next = q->d_u.d_child.next;
+		next = q->d_child.next;
 		goto cont;
 	}
 	dget_dlock(q);
@@ -155,13 +155,13 @@ again:
 				goto relock;
 			}
 			spin_unlock(&p->d_lock);
-			next = p->d_u.d_child.next;
+			next = p->d_child.next;
 			p = parent;
 			if (next != &parent->d_subdirs)
 				break;
 		}
 	}
-	ret = list_entry(next, struct dentry, d_u.d_child);
+	ret = list_entry(next, struct dentry, d_child);
 
 	spin_lock_nested(&ret->d_lock, DENTRY_D_LOCK_NESTED);
 	/* Negative dentry - try next */
@@ -489,7 +489,7 @@ found:
 	spin_lock(&sbi->lookup_lock);
 	spin_lock(&expired->d_parent->d_lock);
 	spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED);
-	list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child);
+	list_move(&expired->d_parent->d_subdirs, &expired->d_child);
 	spin_unlock(&expired->d_lock);
 	spin_unlock(&expired->d_parent->d_lock);
 	spin_unlock(&sbi->lookup_lock);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index d76d083f2f0..0822c9eacc5 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -687,7 +687,7 @@ static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
 	/* only consider parents below dentrys in the root */
 	if (IS_ROOT(parent->d_parent))
 		return;
-	d_child = &dentry->d_u.d_child;
+	d_child = &dentry->d_child;
 	/* Set parent managed if it's becoming empty */
 	if (d_child->next == &parent->d_subdirs &&
 	    d_child->prev == &parent->d_subdirs)
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index e6d63f8f98c..695e7888fef 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -111,7 +111,7 @@ static int fpos_cmp(loff_t l, loff_t r)
 /*
  * When possible, we try to satisfy a readdir by peeking at the
  * dcache.  We make this work by carefully ordering dentries on
- * d_u.d_child when we initially get results back from the MDS, and
+ * d_child when we initially get results back from the MDS, and
  * falling back to a "normal" sync readdir if any dentries in the dir
  * are dropped.
  *
@@ -147,11 +147,11 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 		p = parent->d_subdirs.prev;
 		dout(" initial p %p/%p\n", p->prev, p->next);
 	} else {
-		p = last->d_u.d_child.prev;
+		p = last->d_child.prev;
 	}
 
 more:
-	dentry = list_entry(p, struct dentry, d_u.d_child);
+	dentry = list_entry(p, struct dentry, d_child);
 	di = ceph_dentry(dentry);
 	while (1) {
 		dout(" p %p/%p %s d_subdirs %p/%p\n", p->prev, p->next,
@@ -174,7 +174,7 @@ more:
 		     !dentry->d_inode ? " null" : "");
 		spin_unlock(&dentry->d_lock);
 		p = p->prev;
-		dentry = list_entry(p, struct dentry, d_u.d_child);
+		dentry = list_entry(p, struct dentry, d_child);
 		di = ceph_dentry(dentry);
 	}
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 7b613900440..7a1df90c777 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1399,7 +1399,7 @@ retry_lookup:
 			/* reorder parent's d_subdirs */
 			spin_lock(&parent->d_lock);
 			spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
-			list_move(&dn->d_u.d_child, &parent->d_subdirs);
+			list_move(&dn->d_child, &parent->d_subdirs);
 			spin_unlock(&dn->d_lock);
 			spin_unlock(&parent->d_lock);
 		}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 197cb503d52..0c3ce464cae 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -895,7 +895,7 @@ inode_has_hashed_dentries(struct inode *inode)
 	struct dentry *dentry;
 
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
 		if (!d_unhashed(dentry) || IS_ROOT(dentry)) {
 			spin_unlock(&inode->i_lock);
 			return true;
diff --git a/fs/coda/cache.c b/fs/coda/cache.c
index 278f8fdeb9e..46ee6f23898 100644
--- a/fs/coda/cache.c
+++ b/fs/coda/cache.c
@@ -92,7 +92,7 @@ static void coda_flag_children(struct dentry *parent, int flag)
 	struct dentry *de;
 
 	spin_lock(&parent->d_lock);
-	list_for_each_entry(de, &parent->d_subdirs, d_u.d_child) {
+	list_for_each_entry(de, &parent->d_subdirs, d_child) {
 		/* don't know what to do with negative dentries */
 		if (de->d_inode ) 
 			coda_flag_inode(de->d_inode, flag);
diff --git a/fs/dcache.c b/fs/dcache.c
index 3ffef7f4e5c..8b4c45e4083 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -44,7 +44,7 @@
 /*
  * Usage:
  * dcache->d_inode->i_lock protects:
- *   - i_dentry, d_alias, d_inode of aliases
+ *   - i_dentry, d_u.d_alias, d_inode of aliases
  * dcache_hash_bucket lock protects:
  *   - the dcache hash table
  * s_anon bl list spinlock protects:
@@ -59,7 +59,7 @@
  *   - d_unhashed()
  *   - d_parent and d_subdirs
  *   - childrens' d_child and d_parent
- *   - d_alias, d_inode
+ *   - d_u.d_alias, d_inode
  *
  * Ordering:
  * dentry->d_inode->i_lock
@@ -252,14 +252,12 @@ static void __d_free(struct rcu_head *head)
 {
 	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
 
-	WARN_ON(!hlist_unhashed(&dentry->d_alias));
 	kmem_cache_free(dentry_cache, dentry); 
 }
 
 static void __d_free_external(struct rcu_head *head)
 {
 	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
-	WARN_ON(!hlist_unhashed(&dentry->d_alias));
 	kfree(external_name(dentry));
 	kmem_cache_free(dentry_cache, dentry); 
 }
@@ -271,6 +269,7 @@ static inline int dname_external(const struct dentry *dentry)
 
 static void dentry_free(struct dentry *dentry)
 {
+	WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias));
 	if (unlikely(dname_external(dentry))) {
 		struct external_name *p = external_name(dentry);
 		if (likely(atomic_dec_and_test(&p->u.count))) {
@@ -311,7 +310,7 @@ static void dentry_iput(struct dentry * dentry)
 	struct inode *inode = dentry->d_inode;
 	if (inode) {
 		dentry->d_inode = NULL;
-		hlist_del_init(&dentry->d_alias);
+		hlist_del_init(&dentry->d_u.d_alias);
 		spin_unlock(&dentry->d_lock);
 		spin_unlock(&inode->i_lock);
 		if (!inode->i_nlink)
@@ -336,7 +335,7 @@ static void dentry_unlink_inode(struct dentry * dentry)
 	struct inode *inode = dentry->d_inode;
 	__d_clear_type(dentry);
 	dentry->d_inode = NULL;
-	hlist_del_init(&dentry->d_alias);
+	hlist_del_init(&dentry->d_u.d_alias);
 	dentry_rcuwalk_barrier(dentry);
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&inode->i_lock);
@@ -496,7 +495,7 @@ static void __dentry_kill(struct dentry *dentry)
 	}
 	/* if it was on the hash then remove it */
 	__d_drop(dentry);
-	list_del(&dentry->d_u.d_child);
+	list_del(&dentry->d_child);
 	/*
 	 * Inform d_walk() that we are no longer attached to the
 	 * dentry tree
@@ -722,7 +721,7 @@ static struct dentry *__d_find_alias(struct inode *inode)
 
 again:
 	discon_alias = NULL;
-	hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
 		spin_lock(&alias->d_lock);
  		if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
 			if (IS_ROOT(alias) &&
@@ -772,7 +771,7 @@ void d_prune_aliases(struct inode *inode)
 	struct dentry *dentry;
 restart:
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
 		spin_lock(&dentry->d_lock);
 		if (!dentry->d_lockref.count) {
 			struct dentry *parent = lock_parent(dentry);
@@ -1050,7 +1049,7 @@ repeat:
 resume:
 	while (next != &this_parent->d_subdirs) {
 		struct list_head *tmp = next;
-		struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
+		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
 		next = tmp->next;
 
 		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
@@ -1102,7 +1101,7 @@ resume:
 			goto rename_retry;
 		}
 		rcu_read_unlock();
-		next = child->d_u.d_child.next;
+		next = child->d_child.next;
 		goto resume;
 	}
 	if (need_seqretry(&rename_lock, seq)) {
@@ -1454,8 +1453,8 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	INIT_HLIST_BL_NODE(&dentry->d_hash);
 	INIT_LIST_HEAD(&dentry->d_lru);
 	INIT_LIST_HEAD(&dentry->d_subdirs);
-	INIT_HLIST_NODE(&dentry->d_alias);
-	INIT_LIST_HEAD(&dentry->d_u.d_child);
+	INIT_HLIST_NODE(&dentry->d_u.d_alias);
+	INIT_LIST_HEAD(&dentry->d_child);
 	d_set_d_op(dentry, dentry->d_sb->s_d_op);
 
 	this_cpu_inc(nr_dentry);
@@ -1485,7 +1484,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
 	 */
 	__dget_dlock(parent);
 	dentry->d_parent = parent;
-	list_add(&dentry->d_u.d_child, &parent->d_subdirs);
+	list_add(&dentry->d_child, &parent->d_subdirs);
 	spin_unlock(&parent->d_lock);
 
 	return dentry;
@@ -1578,7 +1577,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 	spin_lock(&dentry->d_lock);
 	__d_set_type(dentry, add_flags);
 	if (inode)
-		hlist_add_head(&dentry->d_alias, &inode->i_dentry);
+		hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
 	dentry->d_inode = inode;
 	dentry_rcuwalk_barrier(dentry);
 	spin_unlock(&dentry->d_lock);
@@ -1602,7 +1601,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
  
 void d_instantiate(struct dentry *entry, struct inode * inode)
 {
-	BUG_ON(!hlist_unhashed(&entry->d_alias));
+	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
 	if (inode)
 		spin_lock(&inode->i_lock);
 	__d_instantiate(entry, inode);
@@ -1641,7 +1640,7 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry,
 		return NULL;
 	}
 
-	hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
 		/*
 		 * Don't need alias->d_lock here, because aliases with
 		 * d_parent == entry->d_parent are not subject to name or
@@ -1667,7 +1666,7 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
 {
 	struct dentry *result;
 
-	BUG_ON(!hlist_unhashed(&entry->d_alias));
+	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
 
 	if (inode)
 		spin_lock(&inode->i_lock);
@@ -1698,7 +1697,7 @@ EXPORT_SYMBOL(d_instantiate_unique);
  */
 int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode)
 {
-	BUG_ON(!hlist_unhashed(&entry->d_alias));
+	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
 
 	spin_lock(&inode->i_lock);
 	if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) {
@@ -1737,7 +1736,7 @@ static struct dentry * __d_find_any_alias(struct inode *inode)
 
 	if (hlist_empty(&inode->i_dentry))
 		return NULL;
-	alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+	alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
 	__dget(alias);
 	return alias;
 }
@@ -1799,7 +1798,7 @@ static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected)
 	spin_lock(&tmp->d_lock);
 	tmp->d_inode = inode;
 	tmp->d_flags |= add_flags;
-	hlist_add_head(&tmp->d_alias, &inode->i_dentry);
+	hlist_add_head(&tmp->d_u.d_alias, &inode->i_dentry);
 	hlist_bl_lock(&tmp->d_sb->s_anon);
 	hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
 	hlist_bl_unlock(&tmp->d_sb->s_anon);
@@ -2234,7 +2233,7 @@ int d_validate(struct dentry *dentry, struct dentry *dparent)
 	struct dentry *child;
 
 	spin_lock(&dparent->d_lock);
-	list_for_each_entry(child, &dparent->d_subdirs, d_u.d_child) {
+	list_for_each_entry(child, &dparent->d_subdirs, d_child) {
 		if (dentry == child) {
 			spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
 			__dget_dlock(dentry);
@@ -2525,13 +2524,13 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 		/* splicing a tree */
 		dentry->d_parent = target->d_parent;
 		target->d_parent = target;
-		list_del_init(&target->d_u.d_child);
-		list_move(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+		list_del_init(&target->d_child);
+		list_move(&dentry->d_child, &dentry->d_parent->d_subdirs);
 	} else {
 		/* swapping two dentries */
 		swap(dentry->d_parent, target->d_parent);
-		list_move(&target->d_u.d_child, &target->d_parent->d_subdirs);
-		list_move(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+		list_move(&target->d_child, &target->d_parent->d_subdirs);
+		list_move(&dentry->d_child, &dentry->d_parent->d_subdirs);
 		if (exchange)
 			fsnotify_d_move(target);
 		fsnotify_d_move(dentry);
@@ -3320,7 +3319,7 @@ void d_tmpfile(struct dentry *dentry, struct inode *inode)
 {
 	inode_dec_link_count(inode);
 	BUG_ON(dentry->d_name.name != dentry->d_iname ||
-		!hlist_unhashed(&dentry->d_alias) ||
+		!hlist_unhashed(&dentry->d_u.d_alias) ||
 		!d_unlinked(dentry));
 	spin_lock(&dentry->d_parent->d_lock);
 	spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 1e3b99d3db0..05f2960ed7c 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -553,7 +553,7 @@ void debugfs_remove_recursive(struct dentry *dentry)
 	 * use the d_u.d_child as the rcu head and corrupt this list.
 	 */
 	spin_lock(&parent->d_lock);
-	list_for_each_entry(child, &parent->d_subdirs, d_u.d_child) {
+	list_for_each_entry(child, &parent->d_subdirs, d_child) {
 		if (!debugfs_positive(child))
 			continue;
 
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index a2b350ddd40..fdfd206c737 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -50,7 +50,7 @@ find_acceptable_alias(struct dentry *result,
 
 	inode = result->d_inode;
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
 		dget(dentry);
 		spin_unlock(&inode->i_lock);
 		if (toput)
diff --git a/fs/libfs.c b/fs/libfs.c
index 171d2846f2a..005843ce5db 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -114,18 +114,18 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 
 			spin_lock(&dentry->d_lock);
 			/* d_lock not required for cursor */
-			list_del(&cursor->d_u.d_child);
+			list_del(&cursor->d_child);
 			p = dentry->d_subdirs.next;
 			while (n && p != &dentry->d_subdirs) {
 				struct dentry *next;
-				next = list_entry(p, struct dentry, d_u.d_child);
+				next = list_entry(p, struct dentry, d_child);
 				spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
 				if (simple_positive(next))
 					n--;
 				spin_unlock(&next->d_lock);
 				p = p->next;
 			}
-			list_add_tail(&cursor->d_u.d_child, p);
+			list_add_tail(&cursor->d_child, p);
 			spin_unlock(&dentry->d_lock);
 		}
 	}
@@ -150,7 +150,7 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct dentry *cursor = file->private_data;
-	struct list_head *p, *q = &cursor->d_u.d_child;
+	struct list_head *p, *q = &cursor->d_child;
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
@@ -159,7 +159,7 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 		list_move(q, &dentry->d_subdirs);
 
 	for (p = q->next; p != &dentry->d_subdirs; p = p->next) {
-		struct dentry *next = list_entry(p, struct dentry, d_u.d_child);
+		struct dentry *next = list_entry(p, struct dentry, d_child);
 		spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
 		if (!simple_positive(next)) {
 			spin_unlock(&next->d_lock);
@@ -287,7 +287,7 @@ int simple_empty(struct dentry *dentry)
 	int ret = 0;
 
 	spin_lock(&dentry->d_lock);
-	list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child) {
+	list_for_each_entry(child, &dentry->d_subdirs, d_child) {
 		spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
 		if (simple_positive(child)) {
 			spin_unlock(&child->d_lock);
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 461f6be5df2..865d578704c 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -403,7 +403,7 @@ ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos)
 
 	/* If a pointer is invalid, we search the dentry. */
 	spin_lock(&parent->d_lock);
-	list_for_each_entry(dent, &parent->d_subdirs, d_u.d_child) {
+	list_for_each_entry(dent, &parent->d_subdirs, d_child) {
 		if ((unsigned long)dent->d_fsdata == fpos) {
 			if (dent->d_inode)
 				dget(dent);
diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h
index 52cb19d66ec..b785f74bfe3 100644
--- a/fs/ncpfs/ncplib_kernel.h
+++ b/fs/ncpfs/ncplib_kernel.h
@@ -191,7 +191,7 @@ ncp_renew_dentries(struct dentry *parent)
 	struct dentry *dentry;
 
 	spin_lock(&parent->d_lock);
-	list_for_each_entry(dentry, &parent->d_subdirs, d_u.d_child) {
+	list_for_each_entry(dentry, &parent->d_subdirs, d_child) {
 		if (dentry->d_fsdata == NULL)
 			ncp_age_dentry(server, dentry);
 		else
@@ -207,7 +207,7 @@ ncp_invalidate_dircache_entries(struct dentry *parent)
 	struct dentry *dentry;
 
 	spin_lock(&parent->d_lock);
-	list_for_each_entry(dentry, &parent->d_subdirs, d_u.d_child) {
+	list_for_each_entry(dentry, &parent->d_subdirs, d_child) {
 		dentry->d_fsdata = NULL;
 		ncp_age_dentry(server, dentry);
 	}
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 880618a8b04..ebc6a0add5a 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -58,7 +58,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i
 		 */
 		spin_lock(&sb->s_root->d_inode->i_lock);
 		spin_lock(&sb->s_root->d_lock);
-		hlist_del_init(&sb->s_root->d_alias);
+		hlist_del_init(&sb->s_root->d_u.d_alias);
 		spin_unlock(&sb->s_root->d_lock);
 		spin_unlock(&sb->s_root->d_inode->i_lock);
 	}
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 9d3e9c50066..700129940c6 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -63,14 +63,14 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
 	spin_lock(&inode->i_lock);
 	/* run all of the dentries associated with this inode.  Since this is a
 	 * directory, there damn well better only be one item on this list */
-	hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
 		struct dentry *child;
 
 		/* run all of the children of the original inode and fix their
 		 * d_flags to indicate parental interest (their parent is the
 		 * original inode) */
 		spin_lock(&alias->d_lock);
-		list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) {
+		list_for_each_entry(child, &alias->d_subdirs, d_child) {
 			if (!child->d_inode)
 				continue;
 
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index e2e05a106be..92edcfc23c1 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -172,7 +172,7 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode,
 	struct dentry *dentry;
 
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
 		spin_lock(&dentry->d_lock);
 		if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) {
 			trace_ocfs2_find_local_alias(dentry->d_name.len,
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index b2a2a08523b..1c2f1b84468 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -124,15 +124,15 @@ struct dentry {
 	void *d_fsdata;			/* fs-specific data */
 
 	struct list_head d_lru;		/* LRU list */
+	struct list_head d_child;	/* child of parent list */
+	struct list_head d_subdirs;	/* our children */
 	/*
-	 * d_child and d_rcu can share memory
+	 * d_alias and d_rcu can share memory
 	 */
 	union {
-		struct list_head d_child;	/* child of parent list */
+		struct hlist_node d_alias;	/* inode alias list */
 	 	struct rcu_head d_rcu;
 	} d_u;
-	struct list_head d_subdirs;	/* our children */
-	struct hlist_node d_alias;	/* inode alias list */
 };
 
 /*
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8a528392b1f..459a7b1251e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6420,7 +6420,7 @@ static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t m
 	int ret;
 
 	/* Paranoid: Make sure the parent is the "instances" directory */
-	parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+	parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
 	if (WARN_ON_ONCE(parent != trace_instance_dir))
 		return -ENOENT;
 
@@ -6447,7 +6447,7 @@ static int instance_rmdir(struct inode *inode, struct dentry *dentry)
 	int ret;
 
 	/* Paranoid: Make sure the parent is the "instances" directory */
-	parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+	parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
 	if (WARN_ON_ONCE(parent != trace_instance_dir))
 		return -ENOENT;
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 0cc51edde3a..1b0df1e504f 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -461,7 +461,7 @@ static void remove_event_file_dir(struct ftrace_event_file *file)
 
 	if (dir) {
 		spin_lock(&dir->d_lock);	/* probably unneeded */
-		list_for_each_entry(child, &dir->d_subdirs, d_u.d_child) {
+		list_for_each_entry(child, &dir->d_subdirs, d_child) {
 			if (child->d_inode)	/* probably unneeded */
 				child->d_inode->i_private = NULL;
 		}
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index c71737f6d1c..33db1ad4fd1 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -1200,7 +1200,7 @@ static void sel_remove_entries(struct dentry *de)
 	spin_lock(&de->d_lock);
 	node = de->d_subdirs.next;
 	while (node != &de->d_subdirs) {
-		struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
+		struct dentry *d = list_entry(node, struct dentry, d_child);
 
 		spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
 		list_del_init(node);
@@ -1674,12 +1674,12 @@ static void sel_remove_classes(void)
 
 	list_for_each(class_node, &class_dir->d_subdirs) {
 		struct dentry *class_subdir = list_entry(class_node,
-					struct dentry, d_u.d_child);
+					struct dentry, d_child);
 		struct list_head *class_subdir_node;
 
 		list_for_each(class_subdir_node, &class_subdir->d_subdirs) {
 			struct dentry *d = list_entry(class_subdir_node,
-						struct dentry, d_u.d_child);
+						struct dentry, d_child);
 
 			if (d->d_inode)
 				if (d->d_inode->i_mode & S_IFDIR)
-- 
cgit v1.2.3-70-g09d2


From 56b174256b6936ec4c1ed8f3407109ac6929d3ca Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 3 Nov 2014 08:19:53 -0800
Subject: net: add rbnode to struct sk_buff

Yaogong replaces TCP out of order receive queue by an RB tree.

As netem already does a private skb->{next/prev/tstamp} union
with a 'struct rb_node', lets do this in a cleaner way.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yaogong Wang <wygivan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 20 +++++++++++++-------
 net/sched/sch_netem.c  | 27 +++++++--------------------
 2 files changed, 20 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6c8b6f604e7..5ad9675b6fe 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -20,6 +20,7 @@
 #include <linux/time.h>
 #include <linux/bug.h>
 #include <linux/cache.h>
+#include <linux/rbtree.h>
 
 #include <linux/atomic.h>
 #include <asm/types.h>
@@ -440,6 +441,7 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1,
  *	@next: Next buffer in list
  *	@prev: Previous buffer in list
  *	@tstamp: Time we arrived/left
+ *	@rbnode: RB tree node, alternative to next/prev for netem/tcp
  *	@sk: Socket we are owned by
  *	@dev: Device we arrived on/are leaving by
  *	@cb: Control buffer. Free for use by every layer. Put private vars here
@@ -504,15 +506,19 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1,
  */
 
 struct sk_buff {
-	/* These two members must be first. */
-	struct sk_buff		*next;
-	struct sk_buff		*prev;
-
 	union {
-		ktime_t		tstamp;
-		struct skb_mstamp skb_mstamp;
+		struct {
+			/* These two members must be first. */
+			struct sk_buff		*next;
+			struct sk_buff		*prev;
+
+			union {
+				ktime_t		tstamp;
+				struct skb_mstamp skb_mstamp;
+			};
+		};
+		struct rb_node	rbnode; /* used in netem & tcp stack */
 	};
-
 	struct sock		*sk;
 	struct net_device	*dev;
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index b34331967e0..179f1c8c0d8 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -139,33 +139,20 @@ struct netem_sched_data {
 
 /* Time stamp put into socket buffer control block
  * Only valid when skbs are in our internal t(ime)fifo queue.
+ *
+ * As skb->rbnode uses same storage than skb->next, skb->prev and skb->tstamp,
+ * and skb->next & skb->prev are scratch space for a qdisc,
+ * we save skb->tstamp value in skb->cb[] before destroying it.
  */
 struct netem_skb_cb {
 	psched_time_t	time_to_send;
 	ktime_t		tstamp_save;
 };
 
-/* Because space in skb->cb[] is tight, netem overloads skb->next/prev/tstamp
- * to hold a rb_node structure.
- *
- * If struct sk_buff layout is changed, the following checks will complain.
- */
-static struct rb_node *netem_rb_node(struct sk_buff *skb)
-{
-	BUILD_BUG_ON(offsetof(struct sk_buff, next) != 0);
-	BUILD_BUG_ON(offsetof(struct sk_buff, prev) !=
-		     offsetof(struct sk_buff, next) + sizeof(skb->next));
-	BUILD_BUG_ON(offsetof(struct sk_buff, tstamp) !=
-		     offsetof(struct sk_buff, prev) + sizeof(skb->prev));
-	BUILD_BUG_ON(sizeof(struct rb_node) > sizeof(skb->next) +
-					      sizeof(skb->prev) +
-					      sizeof(skb->tstamp));
-	return (struct rb_node *)&skb->next;
-}
 
 static struct sk_buff *netem_rb_to_skb(struct rb_node *rb)
 {
-	return (struct sk_buff *)rb;
+	return container_of(rb, struct sk_buff, rbnode);
 }
 
 static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb)
@@ -403,8 +390,8 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 		else
 			p = &parent->rb_left;
 	}
-	rb_link_node(netem_rb_node(nskb), parent, p);
-	rb_insert_color(netem_rb_node(nskb), &q->t_root);
+	rb_link_node(&nskb->rbnode, parent, p);
+	rb_insert_color(&nskb->rbnode, &q->t_root);
 	sch->q.qlen++;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 98a18b6ffc79baa69f4a0d1bae58faf2a8aef4c8 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 2 Nov 2014 06:44:54 +0100
Subject: netdevice: add ieee802154_ptr to net_device

This patch adds an ieee802154_ptr to the net_device structure.
Furthermore the 802.15.4 subsystem will introduce a nl802154 framework
which is similar like the nl80211 framework and a wpan_dev structure.
The wpan_dev structure will hold additional net_device attributes like
address options which are 802.15.4 specific. In the upcoming nl802154
implementation we will introduce a NL802154_FLAG_NEED_WPAN_DEV like
NL80211_FLAG_NEED_WDEV. For this flag an ieee802154_ptr in net_device is
needed. Additional we can access the wpan_dev attributes in upper layers
like IEEE 802.15.4 6LoWPAN easily. Current solution is a complicated
callback interface and getting these values over subif data structure
in mac802154.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/netdevice.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 74fd5d37f15..c9bcf33efb4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -57,6 +57,8 @@ struct device;
 struct phy_device;
 /* 802.11 specific */
 struct wireless_dev;
+/* 802.15.4 specific */
+struct wpan_dev;
 
 void netdev_set_default_ethtool_ops(struct net_device *dev,
 				    const struct ethtool_ops *ops);
@@ -1572,6 +1574,7 @@ struct net_device {
 	struct inet6_dev __rcu	*ip6_ptr;
 	void			*ax25_ptr;
 	struct wireless_dev	*ieee80211_ptr;
+	struct wpan_dev		*ieee802154_ptr;
 
 /*
  * Cache lines mostly used on receive path (including eth_type_trans())
-- 
cgit v1.2.3-70-g09d2


From 11a7e59405148c855e0a9d13588930ccec02c150 Mon Sep 17 00:00:00 2001
From: Michael Grzeschik <m.grzeschik@pengutronix.de>
Date: Mon, 13 Oct 2014 09:53:03 +0800
Subject: usb: ehci: add ehci_port_power interface

The current EHCI implementation is prepared to toggle the
PORT_POWER bit to enable or disable a USB-Port. In some
cases this port power can not be just toggled by the PORT_POWER
bit, and the gpio-regulator is needed to be toggled too.

This patch defines a port power control interface ehci_port_power for
ehci core use, it toggles PORT_POWER bit as well as calls platform
defined .port_power if it is defined.

Signed-off-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: Peter Chen <peter.chen@freescale.com>
Acked-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/ehci-hcd.c |  9 ++++++++-
 drivers/usb/host/ehci-hub.c | 45 ++++++++++++++++++++++++++++++++-------------
 drivers/usb/host/ehci.h     |  2 ++
 include/linux/usb/hcd.h     |  3 +++
 4 files changed, 45 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 15feaf924b7..df75b8e7d15 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -311,6 +311,7 @@ static void unlink_empty_async_suspended(struct ehci_hcd *ehci);
 static void ehci_work(struct ehci_hcd *ehci);
 static void start_unlink_intr(struct ehci_hcd *ehci, struct ehci_qh *qh);
 static void end_unlink_intr(struct ehci_hcd *ehci, struct ehci_qh *qh);
+static int ehci_port_power(struct ehci_hcd *ehci, int portnum, bool enable);
 
 #include "ehci-timer.c"
 #include "ehci-hub.c"
@@ -329,9 +330,13 @@ static void ehci_turn_off_all_ports(struct ehci_hcd *ehci)
 {
 	int	port = HCS_N_PORTS(ehci->hcs_params);
 
-	while (port--)
+	while (port--) {
 		ehci_writel(ehci, PORT_RWC_BITS,
 				&ehci->regs->port_status[port]);
+		spin_unlock_irq(&ehci->lock);
+		ehci_port_power(ehci, port, false);
+		spin_lock_irq(&ehci->lock);
+	}
 }
 
 /*
@@ -1233,6 +1238,8 @@ void ehci_init_driver(struct hc_driver *drv,
 		drv->hcd_priv_size += over->extra_priv_size;
 		if (over->reset)
 			drv->reset = over->reset;
+		if (over->port_power)
+			drv->port_power = over->port_power;
 	}
 }
 EXPORT_SYMBOL_GPL(ehci_init_driver);
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index 5728829cf6e..118edb7bdca 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -69,10 +69,8 @@ static void ehci_handover_companion_ports(struct ehci_hcd *ehci)
 		if (test_bit(port, &ehci->owned_ports)) {
 			reg = &ehci->regs->port_status[port];
 			status = ehci_readl(ehci, reg) & ~PORT_RWC_BITS;
-			if (!(status & PORT_POWER)) {
-				status |= PORT_POWER;
-				ehci_writel(ehci, status, reg);
-			}
+			if (!(status & PORT_POWER))
+				ehci_port_power(ehci, port, true);
 		}
 	}
 
@@ -952,9 +950,11 @@ int ehci_hub_control(
 			clear_bit(wIndex, &ehci->port_c_suspend);
 			break;
 		case USB_PORT_FEAT_POWER:
-			if (HCS_PPC (ehci->hcs_params))
-				ehci_writel(ehci, temp & ~PORT_POWER,
-						status_reg);
+			if (HCS_PPC(ehci->hcs_params)) {
+				spin_unlock_irqrestore(&ehci->lock, flags);
+				ehci_port_power(ehci, wIndex, false);
+				spin_lock_irqsave(&ehci->lock, flags);
+			}
 			break;
 		case USB_PORT_FEAT_C_CONNECTION:
 			ehci_writel(ehci, temp | PORT_CSC, status_reg);
@@ -1004,9 +1004,9 @@ int ehci_hub_control(
 			 */
 			if (((temp & PORT_OC) || (ehci->need_oc_pp_cycle))
 					&& HCS_PPC(ehci->hcs_params)) {
-				ehci_writel(ehci,
-					temp & ~(PORT_RWC_BITS | PORT_POWER),
-					status_reg);
+				spin_unlock_irqrestore(&ehci->lock, flags);
+				ehci_port_power(ehci, wIndex, false);
+				spin_lock_irqsave(&ehci->lock, flags);
 				temp = ehci_readl(ehci, status_reg);
 			}
 		}
@@ -1187,9 +1187,11 @@ int ehci_hub_control(
 			set_bit(wIndex, &ehci->suspended_ports);
 			break;
 		case USB_PORT_FEAT_POWER:
-			if (HCS_PPC (ehci->hcs_params))
-				ehci_writel(ehci, temp | PORT_POWER,
-						status_reg);
+			if (HCS_PPC(ehci->hcs_params)) {
+				spin_unlock_irqrestore(&ehci->lock, flags);
+				ehci_port_power(ehci, wIndex, true);
+				spin_lock_irqsave(&ehci->lock, flags);
+			}
 			break;
 		case USB_PORT_FEAT_RESET:
 			if (temp & (PORT_SUSPEND|PORT_RESUME))
@@ -1297,3 +1299,20 @@ static int ehci_port_handed_over(struct usb_hcd *hcd, int portnum)
 	reg = &ehci->regs->port_status[portnum - 1];
 	return ehci_readl(ehci, reg) & PORT_OWNER;
 }
+
+static int ehci_port_power(struct ehci_hcd *ehci, int portnum, bool enable)
+{
+	struct usb_hcd *hcd = ehci_to_hcd(ehci);
+	u32 __iomem *status_reg = &ehci->regs->port_status[portnum];
+	u32 temp = ehci_readl(ehci, status_reg) & ~PORT_RWC_BITS;
+
+	if (enable)
+		ehci_writel(ehci, temp | PORT_POWER, status_reg);
+	else
+		ehci_writel(ehci, temp & ~PORT_POWER, status_reg);
+
+	if (hcd->driver->port_power)
+		hcd->driver->port_power(hcd, portnum, enable);
+
+	return 0;
+}
diff --git a/drivers/usb/host/ehci.h b/drivers/usb/host/ehci.h
index eee228a26a0..6f0577b0a5a 100644
--- a/drivers/usb/host/ehci.h
+++ b/drivers/usb/host/ehci.h
@@ -859,6 +859,8 @@ static inline u32 hc32_to_cpup (const struct ehci_hcd *ehci, const __hc32 *x)
 struct ehci_driver_overrides {
 	size_t		extra_priv_size;
 	int		(*reset)(struct usb_hcd *hcd);
+	int		(*port_power)(struct usb_hcd *hcd,
+				int portnum, bool enable);
 };
 
 extern void	ehci_init_driver(struct hc_driver *drv,
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index cd96a2bc338..9cf7e359460 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -379,6 +379,9 @@ struct hc_driver {
 	int	(*disable_usb3_lpm_timeout)(struct usb_hcd *,
 			struct usb_device *, enum usb3_link_state state);
 	int	(*find_raw_port_number)(struct usb_hcd *, int);
+	/* Call for power on/off the port if necessary */
+	int	(*port_power)(struct usb_hcd *hcd, int portnum, bool enable);
+
 };
 
 static inline int hcd_giveback_urb_in_bh(struct usb_hcd *hcd)
-- 
cgit v1.2.3-70-g09d2


From a78186ebe516b6d7df43636603f0998803ab356a Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Fri, 17 Oct 2014 17:57:29 -0700
Subject: f2fs: use highmem for directory pages

This patch fixes to use highmem for directory pages.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/inode.c         | 2 +-
 include/linux/f2fs_fs.h | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 0deead4505e..52d6f54664f 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -156,7 +156,7 @@ make_now:
 		inode->i_op = &f2fs_dir_inode_operations;
 		inode->i_fop = &f2fs_dir_operations;
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
-		mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
+		mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &f2fs_symlink_inode_operations;
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 860313a33a4..6d7381b4130 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -33,7 +33,8 @@
 #define F2FS_META_INO(sbi)	(sbi->meta_ino_num)
 
 /* This flag is used by node and meta inodes, and by recovery */
-#define GFP_F2FS_ZERO	(GFP_NOFS | __GFP_ZERO)
+#define GFP_F2FS_ZERO		(GFP_NOFS | __GFP_ZERO)
+#define GFP_F2FS_HIGH_ZERO	(GFP_NOFS | __GFP_ZERO | __GFP_HIGHMEM)
 
 /*
  * For further optimization on multi-head logs, on-disk layout supports maximum
-- 
cgit v1.2.3-70-g09d2


From 34d67debe02b3b2b035b5bdce0fab75800f9a344 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Wed, 24 Sep 2014 18:15:19 +0800
Subject: f2fs: add infra struct and helper for inline dir

This patch defines macro/inline dentry structure, and adds some helpers for
inline dir infrastructure.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h          | 21 +++++++++++++++++++--
 include/linux/f2fs_fs.h | 19 +++++++++++++++++++
 2 files changed, 38 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index d41d1b72591..4fa0df5f54e 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -46,8 +46,9 @@
 #define F2FS_MOUNT_DISABLE_EXT_IDENTIFY	0x00000040
 #define F2FS_MOUNT_INLINE_XATTR		0x00000080
 #define F2FS_MOUNT_INLINE_DATA		0x00000100
-#define F2FS_MOUNT_FLUSH_MERGE		0x00000200
-#define F2FS_MOUNT_NOBARRIER		0x00000400
+#define F2FS_MOUNT_INLINE_DENTRY	0x00000200
+#define F2FS_MOUNT_FLUSH_MERGE		0x00000400
+#define F2FS_MOUNT_NOBARRIER		0x00000800
 
 #define clear_opt(sbi, option)	(sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
 #define set_opt(sbi, option)	(sbi->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -1058,6 +1059,7 @@ enum {
 	FI_NO_EXTENT,		/* not to use the extent cache */
 	FI_INLINE_XATTR,	/* used for inline xattr */
 	FI_INLINE_DATA,		/* used for inline data*/
+	FI_INLINE_DENTRY,	/* used for inline dentry */
 	FI_APPEND_WRITE,	/* inode has appended data */
 	FI_UPDATE_WRITE,	/* inode has in-place-update data */
 	FI_NEED_IPU,		/* used for ipu per file */
@@ -1104,6 +1106,8 @@ static inline void get_inline_info(struct f2fs_inode_info *fi,
 		set_inode_flag(fi, FI_INLINE_XATTR);
 	if (ri->i_inline & F2FS_INLINE_DATA)
 		set_inode_flag(fi, FI_INLINE_DATA);
+	if (ri->i_inline & F2FS_INLINE_DENTRY)
+		set_inode_flag(fi, FI_INLINE_DENTRY);
 }
 
 static inline void set_raw_inline(struct f2fs_inode_info *fi,
@@ -1115,6 +1119,8 @@ static inline void set_raw_inline(struct f2fs_inode_info *fi,
 		ri->i_inline |= F2FS_INLINE_XATTR;
 	if (is_inode_flag_set(fi, FI_INLINE_DATA))
 		ri->i_inline |= F2FS_INLINE_DATA;
+	if (is_inode_flag_set(fi, FI_INLINE_DENTRY))
+		ri->i_inline |= F2FS_INLINE_DENTRY;
 }
 
 static inline int f2fs_has_inline_xattr(struct inode *inode)
@@ -1165,6 +1171,17 @@ static inline void *inline_data_addr(struct page *page)
 	return (void *)&(ri->i_addr[1]);
 }
 
+static inline int f2fs_has_inline_dentry(struct inode *inode)
+{
+	return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DENTRY);
+}
+
+static inline void *inline_dentry_addr(struct page *page)
+{
+	struct f2fs_inode *ri = F2FS_INODE(page);
+	return (void *)&(ri->i_addr[1]);
+}
+
 static inline int f2fs_readonly(struct super_block *sb)
 {
 	return sb->s_flags & MS_RDONLY;
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 6d7381b4130..63f8303b79b 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -171,6 +171,7 @@ struct f2fs_extent {
 
 #define F2FS_INLINE_XATTR	0x01	/* file inline xattr flag */
 #define F2FS_INLINE_DATA	0x02	/* file inline data flag */
+#define F2FS_INLINE_DENTRY	0x04	/* file inline dentry flag */
 
 #define MAX_INLINE_DATA		(sizeof(__le32) * (DEF_ADDRS_PER_INODE - \
 						F2FS_INLINE_XATTR_ADDRS - 1))
@@ -436,6 +437,24 @@ struct f2fs_dentry_block {
 	__u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN];
 } __packed;
 
+/* for inline dir */
+#define NR_INLINE_DENTRY	(MAX_INLINE_DATA * BITS_PER_BYTE / \
+				((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
+				BITS_PER_BYTE + 1))
+#define INLINE_DENTRY_BITMAP_SIZE	((NR_INLINE_DENTRY + \
+					BITS_PER_BYTE - 1) / BITS_PER_BYTE)
+#define INLINE_RESERVED_SIZE	(MAX_INLINE_DATA - \
+				((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
+				NR_INLINE_DENTRY + INLINE_DENTRY_BITMAP_SIZE))
+
+/* inline directory entry structure */
+struct f2fs_inline_dentry {
+	__u8 dentry_bitmap[INLINE_DENTRY_BITMAP_SIZE];
+	__u8 reserved[INLINE_RESERVED_SIZE];
+	struct f2fs_dir_entry dentry[NR_INLINE_DENTRY];
+	__u8 filename[NR_INLINE_DENTRY][F2FS_SLOT_LEN];
+} __packed;
+
 /* file types used in inode_info->flags */
 enum {
 	F2FS_FT_UNKNOWN,
-- 
cgit v1.2.3-70-g09d2


From 148ebf479aa207406f8208466b3e446f9cd25f4b Mon Sep 17 00:00:00 2001
From: Koji Matsuoka <koji.matsuoka.xm@renesas.com>
Date: Thu, 30 Oct 2014 14:58:55 +0900
Subject: ARM: shmobile: r8a7794: Add VIN clock to device tree

Signed-off-by: Koji Matsuoka <koji.matsuoka.xm@renesas.com>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 arch/arm/boot/dts/r8a7794.dtsi            | 6 +++---
 include/dt-bindings/clock/r8a7794-clock.h | 2 ++
 2 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/arm/boot/dts/r8a7794.dtsi b/arch/arm/boot/dts/r8a7794.dtsi
index 088e79c6551..95f656d22fd 100644
--- a/arch/arm/boot/dts/r8a7794.dtsi
+++ b/arch/arm/boot/dts/r8a7794.dtsi
@@ -517,13 +517,13 @@
 		mstp8_clks: mstp8_clks@e6150990 {
 			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150990 0 4>, <0 0xe61509a0 0 4>;
-			clocks = <&p_clk>;
+			clocks = <&zg_clk>, <&zg_clk>, <&p_clk>;
 			#clock-cells = <1>;
 			renesas,clock-indices = <
-				R8A7794_CLK_ETHER
+				R8A7794_CLK_VIN1 R8A7794_CLK_VIN0 R8A7794_CLK_ETHER
 			>;
 			clock-output-names =
-				"ether";
+				"vin1", "vin0", "ether";
 		};
 		mstp11_clks: mstp11_clks@e615099c {
 			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
diff --git a/include/dt-bindings/clock/r8a7794-clock.h b/include/dt-bindings/clock/r8a7794-clock.h
index 9ac1043e25b..fd7cdee6a66 100644
--- a/include/dt-bindings/clock/r8a7794-clock.h
+++ b/include/dt-bindings/clock/r8a7794-clock.h
@@ -61,6 +61,8 @@
 #define R8A7794_CLK_SCIF0		21
 
 /* MSTP8 */
+#define R8A7794_CLK_VIN1		10
+#define R8A7794_CLK_VIN0		11
 #define R8A7794_CLK_ETHER		13
 
 /* MSTP9 */
-- 
cgit v1.2.3-70-g09d2


From c3377c2da6e594504c900d5ef72374c109e4ca99 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 21 Oct 2014 07:53:02 -0700
Subject: rcu: Remove "cpu" argument to rcu_check_callbacks()

The "cpu" argument was kept around on the off-chance that RCU might
offload scheduler-clock interrupts.  However, this offload approach
has been replaced by NO_HZ_FULL, which offloads -all- RCU processing
from qualifying CPUs.  It is therefore time to remove the "cpu" argument
to rcu_check_callbacks(), which this commit does.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Pranith Kumar <bobby.prani@gmail.com>
---
 include/linux/rcupdate.h | 2 +-
 kernel/rcu/tiny.c        | 2 +-
 kernel/rcu/tree.c        | 6 +++---
 kernel/time/timer.c      | 3 +--
 4 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index a4a819ffb2d..b4ad275d90d 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -260,7 +260,7 @@ static inline int rcu_preempt_depth(void)
 void rcu_init(void);
 void rcu_sched_qs(void);
 void rcu_bh_qs(void);
-void rcu_check_callbacks(int cpu, int user);
+void rcu_check_callbacks(int user);
 struct notifier_block;
 void rcu_idle_enter(void);
 void rcu_idle_exit(void);
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index c0623fc4712..01570c68d23 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -247,7 +247,7 @@ void rcu_bh_qs(void)
  * be called from hardirq context.  It is normally called from the
  * scheduling-clock interrupt.
  */
-void rcu_check_callbacks(int cpu, int user)
+void rcu_check_callbacks(int user)
 {
 	RCU_TRACE(check_cpu_stalls());
 	if (user || rcu_is_cpu_rrupt_from_idle())
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index ab6fcfb4fe1..3107811bba6 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2388,7 +2388,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
  * invoked from the scheduling-clock interrupt.  If rcu_pending returns
  * false, there is no point in invoking rcu_check_callbacks().
  */
-void rcu_check_callbacks(int cpu, int user)
+void rcu_check_callbacks(int user)
 {
 	trace_rcu_utilization(TPS("Start scheduler-tick"));
 	increment_cpu_stall_ticks();
@@ -2420,8 +2420,8 @@ void rcu_check_callbacks(int cpu, int user)
 
 		rcu_bh_qs();
 	}
-	rcu_preempt_check_callbacks(cpu);
-	if (rcu_pending(cpu))
+	rcu_preempt_check_callbacks(smp_processor_id());
+	if (rcu_pending(smp_processor_id()))
 		invoke_rcu_core();
 	if (user)
 		rcu_note_voluntary_context_switch(current);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 3260ffdb368..2d3f5c50493 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1377,12 +1377,11 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 void update_process_times(int user_tick)
 {
 	struct task_struct *p = current;
-	int cpu = smp_processor_id();
 
 	/* Note: this timer irq context must be accounted for as well. */
 	account_process_tick(p, user_tick);
 	run_local_timers();
-	rcu_check_callbacks(cpu, user_tick);
+	rcu_check_callbacks(user_tick);
 #ifdef CONFIG_IRQ_WORK
 	if (in_irq())
 		irq_work_tick();
-- 
cgit v1.2.3-70-g09d2


From 38200cf24702e5d79ce6c8f4c62036c41845c62d Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 21 Oct 2014 12:50:04 -0700
Subject: rcu: Remove "cpu" argument to rcu_note_context_switch()

The "cpu" argument to rcu_note_context_switch() is always the current
CPU, so drop it.  This in turn allows the "cpu" argument to
rcu_preempt_note_context_switch() to be removed, which allows the sole
use of "cpu" in both functions to be replaced with a this_cpu_ptr().
Again, the anticipated cross-CPU uses of these functions has been
replaced by NO_HZ_FULL.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Pranith Kumar <bobby.prani@gmail.com>
---
 include/linux/rcutiny.h  | 2 +-
 include/linux/rcutree.h  | 4 ++--
 kernel/rcu/tree.c        | 4 ++--
 kernel/rcu/tree.h        | 2 +-
 kernel/rcu/tree_plugin.h | 6 +++---
 kernel/sched/core.c      | 2 +-
 kernel/softirq.c         | 2 +-
 7 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 38cc5b1e252..0e536620015 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -78,7 +78,7 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 	call_rcu(head, func);
 }
 
-static inline void rcu_note_context_switch(int cpu)
+static inline void rcu_note_context_switch(void)
 {
 	rcu_sched_qs();
 }
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 3e2f5d43274..7b5484db185 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -30,7 +30,7 @@
 #ifndef __LINUX_RCUTREE_H
 #define __LINUX_RCUTREE_H
 
-void rcu_note_context_switch(int cpu);
+void rcu_note_context_switch(void);
 #ifndef CONFIG_RCU_NOCB_CPU_ALL
 int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies);
 #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
@@ -43,7 +43,7 @@ void rcu_cpu_stall_reset(void);
  */
 static inline void rcu_virt_note_context_switch(int cpu)
 {
-	rcu_note_context_switch(cpu);
+	rcu_note_context_switch();
 }
 
 void synchronize_rcu_bh(void);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1af5e2cdcbe..b591f145924 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -286,11 +286,11 @@ static void rcu_momentary_dyntick_idle(void)
  * and requires special handling for preemptible RCU.
  * The caller must have disabled preemption.
  */
-void rcu_note_context_switch(int cpu)
+void rcu_note_context_switch(void)
 {
 	trace_rcu_utilization(TPS("Start context switch"));
 	rcu_sched_qs();
-	rcu_preempt_note_context_switch(cpu);
+	rcu_preempt_note_context_switch();
 	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
 		rcu_momentary_dyntick_idle();
 	trace_rcu_utilization(TPS("End context switch"));
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 94a26e330c1..238ac39053f 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -547,7 +547,7 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work);
 /* Forward declarations for rcutree_plugin.h */
 static void rcu_bootup_announce(void);
 long rcu_batches_completed(void);
-static void rcu_preempt_note_context_switch(int cpu);
+static void rcu_preempt_note_context_switch(void);
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 7158814b7b4..495d4cce47a 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -156,7 +156,7 @@ static void rcu_preempt_qs(void)
  *
  * Caller must disable preemption.
  */
-static void rcu_preempt_note_context_switch(int cpu)
+static void rcu_preempt_note_context_switch(void)
 {
 	struct task_struct *t = current;
 	unsigned long flags;
@@ -167,7 +167,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 	    !t->rcu_read_unlock_special.b.blocked) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
-		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
+		rdp = this_cpu_ptr(rcu_preempt_state.rda);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
@@ -945,7 +945,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed);
  * Because preemptible RCU does not exist, we never have to check for
  * CPUs being in quiescent states.
  */
-static void rcu_preempt_note_context_switch(int cpu)
+static void rcu_preempt_note_context_switch(void)
 {
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 44999505e1b..cc186945296 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2802,7 +2802,7 @@ need_resched:
 	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
-	rcu_note_context_switch(cpu);
+	rcu_note_context_switch();
 	prev = rq->curr;
 
 	schedule_debug(prev);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 0699add1916..501baa9ac1b 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -656,7 +656,7 @@ static void run_ksoftirqd(unsigned int cpu)
 		 * in the task stack here.
 		 */
 		__do_softirq();
-		rcu_note_context_switch(cpu);
+		rcu_note_context_switch();
 		local_irq_enable();
 		cond_resched();
 		return;
-- 
cgit v1.2.3-70-g09d2


From aa6da5140b784ece799f670bf532096f67aa7785 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 21 Oct 2014 13:23:08 -0700
Subject: rcu: Remove "cpu" argument to rcu_needs_cpu()

The "cpu" argument to rcu_needs_cpu() is always the current CPU, so drop
it.  This in turn allows the "cpu" argument to rcu_cpu_has_callbacks()
to be removed, which allows the uses of "cpu" in both functions to be
replaced with a this_cpu_ptr().  Again, the anticipated cross-CPU uses
of these functions has been replaced by NO_HZ_FULL.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Pranith Kumar <bobby.prani@gmail.com>
---
 include/linux/rcupdate.h |  2 +-
 include/linux/rcutree.h  |  2 +-
 kernel/rcu/tree.c        |  4 ++--
 kernel/rcu/tree_plugin.h | 12 ++++++------
 kernel/time/tick-sched.c |  2 +-
 5 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index b4ad275d90d..4eb810832b1 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -1103,7 +1103,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
 
 #if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL)
-static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
+static inline int rcu_needs_cpu(unsigned long *delta_jiffies)
 {
 	*delta_jiffies = ULONG_MAX;
 	return 0;
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 7b5484db185..52953790dcc 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -32,7 +32,7 @@
 
 void rcu_note_context_switch(void);
 #ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies);
+int rcu_needs_cpu(unsigned long *delta_jiffies);
 #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 void rcu_cpu_stall_reset(void);
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b591f145924..d678a98caf1 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3159,7 +3159,7 @@ static int rcu_pending(void)
  * non-NULL, store an indication of whether all callbacks are lazy.
  * (If there are no callbacks, all of them are deemed to be lazy.)
  */
-static int __maybe_unused rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
+static int __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
 {
 	bool al = true;
 	bool hc = false;
@@ -3167,7 +3167,7 @@ static int __maybe_unused rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
 	struct rcu_state *rsp;
 
 	for_each_rcu_flavor(rsp) {
-		rdp = per_cpu_ptr(rsp->rda, cpu);
+		rdp = this_cpu_ptr(rsp->rda);
 		if (!rdp->nxtlist)
 			continue;
 		hc = true;
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 495d4cce47a..1797b76cb3f 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1512,10 +1512,10 @@ static void rcu_prepare_kthreads(int cpu)
  * any flavor of RCU.
  */
 #ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
+int rcu_needs_cpu(unsigned long *delta_jiffies)
 {
 	*delta_jiffies = ULONG_MAX;
-	return rcu_cpu_has_callbacks(cpu, NULL);
+	return rcu_cpu_has_callbacks(NULL);
 }
 #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 
@@ -1624,15 +1624,15 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
  * The caller must have disabled interrupts.
  */
 #ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(int cpu, unsigned long *dj)
+int rcu_needs_cpu(unsigned long *dj)
 {
-	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
 	/* Snapshot to detect later posting of non-lazy callback. */
 	rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
 
 	/* If no callbacks, RCU doesn't need the CPU. */
-	if (!rcu_cpu_has_callbacks(cpu, &rdtp->all_lazy)) {
+	if (!rcu_cpu_has_callbacks(&rdtp->all_lazy)) {
 		*dj = ULONG_MAX;
 		return 0;
 	}
@@ -1679,7 +1679,7 @@ static void rcu_prepare_for_idle(int cpu)
 	/* Handle nohz enablement switches conservatively. */
 	tne = ACCESS_ONCE(tick_nohz_active);
 	if (tne != rdtp->tick_nohz_enabled_snap) {
-		if (rcu_cpu_has_callbacks(cpu, NULL))
+		if (rcu_cpu_has_callbacks(NULL))
 			invoke_rcu_core(); /* force nohz to see update. */
 		rdtp->tick_nohz_enabled_snap = tne;
 		return;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 7b5741fc411..1f4356037a7 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -585,7 +585,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		last_jiffies = jiffies;
 	} while (read_seqretry(&jiffies_lock, seq));
 
-	if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) ||
+	if (rcu_needs_cpu(&rcu_delta_jiffies) ||
 	    arch_needs_cpu() || irq_work_needs_cpu()) {
 		next_jiffies = last_jiffies + 1;
 		delta_jiffies = 1;
-- 
cgit v1.2.3-70-g09d2


From 36df04bc5273a046f53b5e359febc1225f85aa7b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 29 Oct 2014 12:21:57 +0100
Subject: sched/wait: Reimplement wait_event_freezable()

Provide better implementations of wait_event_freezable() APIs.

The problem is with freezer_do_not_count(), it hides the thread from
the freezer, even though this thread might not actually freeze/sleep
at all.

Cc: oleg@redhat.com
Cc: Rafael Wysocki <rjw@rjwysocki.net>

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Len Brown <len.brown@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: linux-pm@vger.kernel.org
Link: http://lkml.kernel.org/n/tip-d86fz1jmso9wjxa8jfpinp8o@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/freezer.h | 38 ---------------------------------
 include/linux/wait.h    | 57 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index 7fd81b8c489..e203665c0fa 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -265,35 +265,6 @@ static inline int freezable_schedule_hrtimeout_range(ktime_t *expires,
 	__retval;							\
 })
 
-#define wait_event_freezable(wq, condition)				\
-({									\
-	int __retval;							\
-	freezer_do_not_count();						\
-	__retval = wait_event_interruptible(wq, (condition));		\
-	freezer_count();						\
-	__retval;							\
-})
-
-#define wait_event_freezable_timeout(wq, condition, timeout)		\
-({									\
-	long __retval = timeout;					\
-	freezer_do_not_count();						\
-	__retval = wait_event_interruptible_timeout(wq,	(condition),	\
-				__retval);				\
-	freezer_count();						\
-	__retval;							\
-})
-
-#define wait_event_freezable_exclusive(wq, condition)			\
-({									\
-	int __retval;							\
-	freezer_do_not_count();						\
-	__retval = wait_event_interruptible_exclusive(wq, condition);	\
-	freezer_count();						\
-	__retval;							\
-})
-
-
 #else /* !CONFIG_FREEZER */
 static inline bool frozen(struct task_struct *p) { return false; }
 static inline bool freezing(struct task_struct *p) { return false; }
@@ -331,15 +302,6 @@ static inline void set_freezable(void) {}
 #define freezable_schedule_hrtimeout_range(expires, delta, mode)	\
 	schedule_hrtimeout_range(expires, delta, mode)
 
-#define wait_event_freezable(wq, condition)				\
-		wait_event_interruptible(wq, condition)
-
-#define wait_event_freezable_timeout(wq, condition, timeout)		\
-		wait_event_interruptible_timeout(wq, condition, timeout)
-
-#define wait_event_freezable_exclusive(wq, condition)			\
-		wait_event_interruptible_exclusive(wq, condition)
-
 #define wait_event_freezekillable(wq, condition)		\
 		wait_event_killable(wq, condition)
 
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 0421775e0b9..2232ed16635 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -267,6 +267,31 @@ do {									\
 	__wait_event(wq, condition);					\
 } while (0)
 
+#define __wait_event_freezable(wq, condition)				\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
+			    schedule(); try_to_freeze())
+
+/**
+ * wait_event - sleep (or freeze) until a condition gets true
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ *
+ * The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute
+ * to system load) until the @condition evaluates to true. The
+ * @condition is checked each time the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ */
+#define wait_event_freezable(wq, condition)				\
+({									\
+	int __ret = 0;							\
+	might_sleep();							\
+	if (!(condition))						\
+		__ret = __wait_event_freezable(wq, condition);		\
+	__ret;								\
+})
+
 #define __wait_event_timeout(wq, condition, timeout)			\
 	___wait_event(wq, ___wait_cond_timeout(condition),		\
 		      TASK_UNINTERRUPTIBLE, 0, timeout,			\
@@ -300,6 +325,24 @@ do {									\
 	__ret;								\
 })
 
+#define __wait_event_freezable_timeout(wq, condition, timeout)		\
+	___wait_event(wq, ___wait_cond_timeout(condition),		\
+		      TASK_INTERRUPTIBLE, 0, timeout,			\
+		      __ret = schedule_timeout(__ret); try_to_freeze())
+
+/*
+ * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid
+ * increasing load and is freezable.
+ */
+#define wait_event_freezable_timeout(wq, condition, timeout)		\
+({									\
+	long __ret = timeout;						\
+	might_sleep();							\
+	if (!___wait_cond_timeout(condition))				\
+		__ret = __wait_event_freezable_timeout(wq, condition, timeout);	\
+	__ret;								\
+})
+
 #define __wait_event_cmd(wq, condition, cmd1, cmd2)			\
 	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
 			    cmd1; schedule(); cmd2)
@@ -480,6 +523,20 @@ do {									\
 })
 
 
+#define __wait_event_freezable_exclusive(wq, condition)			\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0,		\
+			schedule(); try_to_freeze())
+
+#define wait_event_freezable_exclusive(wq, condition)			\
+({									\
+	int __ret = 0;							\
+	might_sleep();							\
+	if (!(condition))						\
+		__ret = __wait_event_freezable_exclusive(wq, condition);\
+	__ret;								\
+})
+
+
 #define __wait_event_interruptible_locked(wq, condition, exclusive, irq) \
 ({									\
 	int __ret = 0;							\
-- 
cgit v1.2.3-70-g09d2


From 5d4d56582467f3c08dfedd0d995ce2092f384ecc Mon Sep 17 00:00:00 2001
From: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Date: Wed, 29 Oct 2014 14:48:13 +0100
Subject: sched/wait: Remove wait_event_freezekillable()

There is no user.. make it go away.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: oleg@redhat.com
Cc: Rafael Wysocki <rjw@rjwysocki.net>
Cc: Len Brown <len.brown@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: linux-pm@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/freezer.h | 12 ------------
 1 file changed, 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index e203665c0fa..6b7fd9cf5ea 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -246,15 +246,6 @@ static inline int freezable_schedule_hrtimeout_range(ktime_t *expires,
  * defined in <linux/wait.h>
  */
 
-#define wait_event_freezekillable(wq, condition)			\
-({									\
-	int __retval;							\
-	freezer_do_not_count();						\
-	__retval = wait_event_killable(wq, (condition));		\
-	freezer_count();						\
-	__retval;							\
-})
-
 /* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
 #define wait_event_freezekillable_unsafe(wq, condition)			\
 ({									\
@@ -302,9 +293,6 @@ static inline void set_freezable(void) {}
 #define freezable_schedule_hrtimeout_range(expires, delta, mode)	\
 	schedule_hrtimeout_range(expires, delta, mode)
 
-#define wait_event_freezekillable(wq, condition)		\
-		wait_event_killable(wq, condition)
-
 #define wait_event_freezekillable_unsafe(wq, condition)			\
 		wait_event_killable(wq, condition)
 
-- 
cgit v1.2.3-70-g09d2


From 44dba3d5d6a10685fb15bd1954e62016334825e0 Mon Sep 17 00:00:00 2001
From: Iulia Manda <iulia.manda21@gmail.com>
Date: Fri, 31 Oct 2014 02:13:31 +0200
Subject: sched: Refactor task_struct to use numa_faults instead of numa_*
 pointers

This patch simplifies task_struct by removing the four numa_* pointers
in the same array and replacing them with the array pointer. By doing this,
on x86_64, the size of task_struct is reduced by 3 ulong pointers (24 bytes on
x86_64).

A new parameter is added to the task_faults_idx function so that it can return
an index to the correct offset, corresponding with the old precalculated
pointers.

All of the code in sched/ that depended on task_faults_idx and numa_* was
changed in order to match the new logic.

Signed-off-by: Iulia Manda <iulia.manda21@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: mgorman@suse.de
Cc: dave@stgolabs.net
Cc: riel@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141031001331.GA30662@winterfell
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  31 ++++++--------
 kernel/sched/core.c   |   3 +-
 kernel/sched/debug.c  |   4 +-
 kernel/sched/fair.c   | 110 ++++++++++++++++++++++++++------------------------
 kernel/sched/sched.h  |   7 ++++
 5 files changed, 80 insertions(+), 75 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4400ddc2fe7..bd7c14ba86c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1597,27 +1597,22 @@ struct task_struct {
 	struct numa_group *numa_group;
 
 	/*
-	 * Exponential decaying average of faults on a per-node basis.
-	 * Scheduling placement decisions are made based on the these counts.
-	 * The values remain static for the duration of a PTE scan
+	 * numa_faults is an array split into four regions:
+	 * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer
+	 * in this precise order.
+	 *
+	 * faults_memory: Exponential decaying average of faults on a per-node
+	 * basis. Scheduling placement decisions are made based on these
+	 * counts. The values remain static for the duration of a PTE scan.
+	 * faults_cpu: Track the nodes the process was running on when a NUMA
+	 * hinting fault was incurred.
+	 * faults_memory_buffer and faults_cpu_buffer: Record faults per node
+	 * during the current scan window. When the scan completes, the counts
+	 * in faults_memory and faults_cpu decay and these values are copied.
 	 */
-	unsigned long *numa_faults_memory;
+	unsigned long *numa_faults;
 	unsigned long total_numa_faults;
 
-	/*
-	 * numa_faults_buffer records faults per node during the current
-	 * scan window. When the scan completes, the counts in
-	 * numa_faults_memory decay and these values are copied.
-	 */
-	unsigned long *numa_faults_buffer_memory;
-
-	/*
-	 * Track the nodes the process was running on when a NUMA hinting
-	 * fault was incurred.
-	 */
-	unsigned long *numa_faults_cpu;
-	unsigned long *numa_faults_buffer_cpu;
-
 	/*
 	 * numa_faults_locality tracks if faults recorded during the last
 	 * scan window were remote/local. The task scan period is adapted
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index df0569ebec0..72d9d926a03 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1857,8 +1857,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
 	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
 	p->numa_work.next = &p->numa_work;
-	p->numa_faults_memory = NULL;
-	p->numa_faults_buffer_memory = NULL;
+	p->numa_faults = NULL;
 	p->last_task_numa_placement = 0;
 	p->last_sum_exec_runtime = 0;
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index eeb6046d60c..92cc52001e7 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -535,8 +535,8 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)
 			unsigned long nr_faults = -1;
 			int cpu_current, home_node;
 
-			if (p->numa_faults_memory)
-				nr_faults = p->numa_faults_memory[2*node + i];
+			if (p->numa_faults)
+				nr_faults = p->numa_faults[2*node + i];
 
 			cpu_current = !i ? (task_node(p) == node) :
 				(pol && node_isset(node, pol->v.nodes));
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d03d76de7af..826fdf32668 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -896,18 +896,24 @@ pid_t task_numa_group_id(struct task_struct *p)
 	return p->numa_group ? p->numa_group->gid : 0;
 }
 
-static inline int task_faults_idx(int nid, int priv)
+/*
+ * The averaged statistics, shared & private, memory & cpu,
+ * occupy the first half of the array. The second half of the
+ * array is for current counters, which are averaged into the
+ * first set by task_numa_placement.
+ */
+static inline int task_faults_idx(enum numa_faults_stats s, int nid, int priv)
 {
-	return NR_NUMA_HINT_FAULT_TYPES * nid + priv;
+	return NR_NUMA_HINT_FAULT_TYPES * (s * nr_node_ids + nid) + priv;
 }
 
 static inline unsigned long task_faults(struct task_struct *p, int nid)
 {
-	if (!p->numa_faults_memory)
+	if (!p->numa_faults)
 		return 0;
 
-	return p->numa_faults_memory[task_faults_idx(nid, 0)] +
-		p->numa_faults_memory[task_faults_idx(nid, 1)];
+	return p->numa_faults[task_faults_idx(NUMA_MEM, nid, 0)] +
+		p->numa_faults[task_faults_idx(NUMA_MEM, nid, 1)];
 }
 
 static inline unsigned long group_faults(struct task_struct *p, int nid)
@@ -915,14 +921,14 @@ static inline unsigned long group_faults(struct task_struct *p, int nid)
 	if (!p->numa_group)
 		return 0;
 
-	return p->numa_group->faults[task_faults_idx(nid, 0)] +
-		p->numa_group->faults[task_faults_idx(nid, 1)];
+	return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] +
+		p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)];
 }
 
 static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
 {
-	return group->faults_cpu[task_faults_idx(nid, 0)] +
-		group->faults_cpu[task_faults_idx(nid, 1)];
+	return group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 0)] +
+		group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)];
 }
 
 /* Handle placement on systems where not all nodes are directly connected. */
@@ -1001,7 +1007,7 @@ static inline unsigned long task_weight(struct task_struct *p, int nid,
 {
 	unsigned long faults, total_faults;
 
-	if (!p->numa_faults_memory)
+	if (!p->numa_faults)
 		return 0;
 
 	total_faults = p->total_numa_faults;
@@ -1517,7 +1523,7 @@ static void numa_migrate_preferred(struct task_struct *p)
 	unsigned long interval = HZ;
 
 	/* This task has no NUMA fault statistics yet */
-	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory))
+	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
 		return;
 
 	/* Periodically retry migrating the task to the preferred node */
@@ -1779,18 +1785,23 @@ static void task_numa_placement(struct task_struct *p)
 
 	/* Find the node with the highest number of faults */
 	for_each_online_node(nid) {
+		/* Keep track of the offsets in numa_faults array */
+		int mem_idx, membuf_idx, cpu_idx, cpubuf_idx;
 		unsigned long faults = 0, group_faults = 0;
-		int priv, i;
+		int priv;
 
 		for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) {
 			long diff, f_diff, f_weight;
 
-			i = task_faults_idx(nid, priv);
+			mem_idx = task_faults_idx(NUMA_MEM, nid, priv);
+			membuf_idx = task_faults_idx(NUMA_MEMBUF, nid, priv);
+			cpu_idx = task_faults_idx(NUMA_CPU, nid, priv);
+			cpubuf_idx = task_faults_idx(NUMA_CPUBUF, nid, priv);
 
 			/* Decay existing window, copy faults since last scan */
-			diff = p->numa_faults_buffer_memory[i] - p->numa_faults_memory[i] / 2;
-			fault_types[priv] += p->numa_faults_buffer_memory[i];
-			p->numa_faults_buffer_memory[i] = 0;
+			diff = p->numa_faults[membuf_idx] - p->numa_faults[mem_idx] / 2;
+			fault_types[priv] += p->numa_faults[membuf_idx];
+			p->numa_faults[membuf_idx] = 0;
 
 			/*
 			 * Normalize the faults_from, so all tasks in a group
@@ -1800,21 +1811,27 @@ static void task_numa_placement(struct task_struct *p)
 			 * faults are less important.
 			 */
 			f_weight = div64_u64(runtime << 16, period + 1);
-			f_weight = (f_weight * p->numa_faults_buffer_cpu[i]) /
+			f_weight = (f_weight * p->numa_faults[cpubuf_idx]) /
 				   (total_faults + 1);
-			f_diff = f_weight - p->numa_faults_cpu[i] / 2;
-			p->numa_faults_buffer_cpu[i] = 0;
+			f_diff = f_weight - p->numa_faults[cpu_idx] / 2;
+			p->numa_faults[cpubuf_idx] = 0;
 
-			p->numa_faults_memory[i] += diff;
-			p->numa_faults_cpu[i] += f_diff;
-			faults += p->numa_faults_memory[i];
+			p->numa_faults[mem_idx] += diff;
+			p->numa_faults[cpu_idx] += f_diff;
+			faults += p->numa_faults[mem_idx];
 			p->total_numa_faults += diff;
 			if (p->numa_group) {
-				/* safe because we can only change our own group */
-				p->numa_group->faults[i] += diff;
-				p->numa_group->faults_cpu[i] += f_diff;
+				/*
+				 * safe because we can only change our own group
+				 *
+				 * mem_idx represents the offset for a given
+				 * nid and priv in a specific region because it
+				 * is at the beginning of the numa_faults array.
+				 */
+				p->numa_group->faults[mem_idx] += diff;
+				p->numa_group->faults_cpu[mem_idx] += f_diff;
 				p->numa_group->total_faults += diff;
-				group_faults += p->numa_group->faults[i];
+				group_faults += p->numa_group->faults[mem_idx];
 			}
 		}
 
@@ -1886,7 +1903,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 		node_set(task_node(current), grp->active_nodes);
 
 		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
-			grp->faults[i] = p->numa_faults_memory[i];
+			grp->faults[i] = p->numa_faults[i];
 
 		grp->total_faults = p->total_numa_faults;
 
@@ -1945,8 +1962,8 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 	double_lock_irq(&my_grp->lock, &grp->lock);
 
 	for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
-		my_grp->faults[i] -= p->numa_faults_memory[i];
-		grp->faults[i] += p->numa_faults_memory[i];
+		my_grp->faults[i] -= p->numa_faults[i];
+		grp->faults[i] += p->numa_faults[i];
 	}
 	my_grp->total_faults -= p->total_numa_faults;
 	grp->total_faults += p->total_numa_faults;
@@ -1971,14 +1988,14 @@ no_join:
 void task_numa_free(struct task_struct *p)
 {
 	struct numa_group *grp = p->numa_group;
-	void *numa_faults = p->numa_faults_memory;
+	void *numa_faults = p->numa_faults;
 	unsigned long flags;
 	int i;
 
 	if (grp) {
 		spin_lock_irqsave(&grp->lock, flags);
 		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
-			grp->faults[i] -= p->numa_faults_memory[i];
+			grp->faults[i] -= p->numa_faults[i];
 		grp->total_faults -= p->total_numa_faults;
 
 		list_del(&p->numa_entry);
@@ -1988,10 +2005,7 @@ void task_numa_free(struct task_struct *p)
 		put_numa_group(grp);
 	}
 
-	p->numa_faults_memory = NULL;
-	p->numa_faults_buffer_memory = NULL;
-	p->numa_faults_cpu= NULL;
-	p->numa_faults_buffer_cpu = NULL;
+	p->numa_faults = NULL;
 	kfree(numa_faults);
 }
 
@@ -2014,24 +2028,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 		return;
 
 	/* Allocate buffer to track faults on a per-node basis */
-	if (unlikely(!p->numa_faults_memory)) {
-		int size = sizeof(*p->numa_faults_memory) *
+	if (unlikely(!p->numa_faults)) {
+		int size = sizeof(*p->numa_faults) *
 			   NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids;
 
-		p->numa_faults_memory = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
-		if (!p->numa_faults_memory)
+		p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
+		if (!p->numa_faults)
 			return;
 
-		BUG_ON(p->numa_faults_buffer_memory);
-		/*
-		 * The averaged statistics, shared & private, memory & cpu,
-		 * occupy the first half of the array. The second half of the
-		 * array is for current counters, which are averaged into the
-		 * first set by task_numa_placement.
-		 */
-		p->numa_faults_cpu = p->numa_faults_memory + (2 * nr_node_ids);
-		p->numa_faults_buffer_memory = p->numa_faults_memory + (4 * nr_node_ids);
-		p->numa_faults_buffer_cpu = p->numa_faults_memory + (6 * nr_node_ids);
 		p->total_numa_faults = 0;
 		memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
 	}
@@ -2071,8 +2075,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 	if (migrated)
 		p->numa_pages_migrated += pages;
 
-	p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages;
-	p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages;
+	p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages;
+	p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages;
 	p->numa_faults_locality[local] += pages;
 }
 
@@ -5361,7 +5365,7 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
 	struct numa_group *numa_group = rcu_dereference(p->numa_group);
 	int src_nid, dst_nid;
 
-	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory ||
+	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
 	    !(env->sd->flags & SD_NUMA)) {
 		return false;
 	}
@@ -5400,7 +5404,7 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 	if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
 		return false;
 
-	if (!p->numa_faults_memory || !(env->sd->flags & SD_NUMA))
+	if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
 		return false;
 
 	src_nid = cpu_to_node(env->src_cpu);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7e5c1eebc11..31f1e4d2996 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -709,6 +709,13 @@ extern bool find_numa_distance(int distance);
 #endif
 
 #ifdef CONFIG_NUMA_BALANCING
+/* The regions in numa_faults array from task_struct */
+enum numa_faults_stats {
+	NUMA_MEM = 0,
+	NUMA_CPU,
+	NUMA_MEMBUF,
+	NUMA_CPUBUF
+};
 extern void sched_setnuma(struct task_struct *p, int node);
 extern int migrate_task_to(struct task_struct *p, int cpu);
 extern int migrate_swap(struct task_struct *, struct task_struct *);
-- 
cgit v1.2.3-70-g09d2


From 0563921abf01a7a38b5f670c3de05dc0b0b8617d Mon Sep 17 00:00:00 2001
From: Eran Harary <eran.harary@intel.com>
Date: Mon, 3 Nov 2014 20:06:47 +0200
Subject: ieee80211: add "max length of AMPDU" enum for VHT

Maximum length of AMPDU that an STA can receive in VHT.
length = 2 ^ (13 + max_ampdu_length_exp) - 1.

Signed-off-by: Eran Harary <eran.harary@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 5fab17b382b..f65b5446d98 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1274,7 +1274,7 @@ struct ieee80211_ht_cap {
 #define		IEEE80211_HT_AMPDU_PARM_DENSITY_SHIFT	2
 
 /*
- * Maximum length of AMPDU that the STA can receive.
+ * Maximum length of AMPDU that the STA can receive in high-throughput (HT).
  * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets)
  */
 enum ieee80211_max_ampdu_length_exp {
@@ -1284,6 +1284,21 @@ enum ieee80211_max_ampdu_length_exp {
 	IEEE80211_HT_MAX_AMPDU_64K = 3
 };
 
+/*
+ * Maximum length of AMPDU that the STA can receive in VHT.
+ * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets)
+ */
+enum ieee80211_vht_max_ampdu_length_exp {
+	IEEE80211_VHT_MAX_AMPDU_8K = 0,
+	IEEE80211_VHT_MAX_AMPDU_16K = 1,
+	IEEE80211_VHT_MAX_AMPDU_32K = 2,
+	IEEE80211_VHT_MAX_AMPDU_64K = 3,
+	IEEE80211_VHT_MAX_AMPDU_128K = 4,
+	IEEE80211_VHT_MAX_AMPDU_256K = 5,
+	IEEE80211_VHT_MAX_AMPDU_512K = 6,
+	IEEE80211_VHT_MAX_AMPDU_1024K = 7
+};
+
 #define IEEE80211_HT_MAX_AMPDU_FACTOR 13
 
 /* Minimum MPDU start spacing */
-- 
cgit v1.2.3-70-g09d2


From 5b3dc42b1b0db0264bbbe4ae44c15ab97bfd1e93 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@openwrt.org>
Date: Sun, 26 Oct 2014 00:32:53 +0200
Subject: mac80211: add support for driver tx power reporting

The configured tx power is often limited by hardware capabilities,
channel settings, antenna configuration, etc.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
[fix tracing compilation]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    |  5 +++++
 net/mac80211/cfg.c        |  3 +++
 net/mac80211/driver-ops.h | 14 ++++++++++++++
 net/mac80211/trace.h      | 27 +++++++++++++++++++++++++++
 4 files changed, 49 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 1614b2fc3bf..03edbf6f623 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2857,6 +2857,9 @@ enum ieee80211_roc_type {
  * @get_expected_throughput: extract the expected throughput towards the
  *	specified station. The returned value is expressed in Kbps. It returns 0
  *	if the RC algorithm does not have proper data to provide.
+ *
+ * @get_txpower: get current maximum tx power (in dBm) based on configuration
+ *	and hardware limits.
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw,
@@ -3065,6 +3068,8 @@ struct ieee80211_ops {
 	int (*join_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
 	void (*leave_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
 	u32 (*get_expected_throughput)(struct ieee80211_sta *sta);
+	int (*get_txpower)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			   int *dbm);
 };
 
 /**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index fbcc209687c..b9659b8b70f 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2133,6 +2133,9 @@ static int ieee80211_get_tx_power(struct wiphy *wiphy,
 	struct ieee80211_local *local = wiphy_priv(wiphy);
 	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
 
+	if (local->ops->get_txpower)
+		return drv_get_txpower(local, sdata, dbm);
+
 	if (!local->use_chanctx)
 		*dbm = local->hw.conf.power_level;
 	else
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 3df28e0fa04..d1e128e5db4 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1279,4 +1279,18 @@ static inline u32 drv_get_expected_throughput(struct ieee80211_local *local,
 	return ret;
 }
 
+static inline int drv_get_txpower(struct ieee80211_local *local,
+				  struct ieee80211_sub_if_data *sdata, int *dbm)
+{
+	int ret;
+
+	if (!local->ops->get_txpower)
+		return -EOPNOTSUPP;
+
+	ret = local->ops->get_txpower(&local->hw, &sdata->vif, dbm);
+	trace_drv_get_txpower(local, sdata, *dbm, ret);
+
+	return ret;
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 976606aebac..aeeace5ba47 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -2150,6 +2150,33 @@ DEFINE_EVENT(local_sdata_evt, drv_post_channel_switch,
 	     TP_ARGS(local, sdata)
 );
 
+TRACE_EVENT(drv_get_txpower,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 int dbm, int ret),
+
+	TP_ARGS(local, sdata, dbm, ret),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		__field(int, dbm)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		__entry->dbm = dbm;
+		__entry->ret = ret;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT VIF_PR_FMT " dbm:%d ret:%d",
+		LOCAL_PR_ARG, VIF_PR_ARG, __entry->dbm, __entry->ret
+	)
+);
+
 
 #ifdef CONFIG_MAC80211_MESSAGE_TRACING
 #undef TRACE_SYSTEM
-- 
cgit v1.2.3-70-g09d2


From 313665b983fe30af9d0eb274f7e03276e05a1bbf Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 4 Nov 2014 11:30:58 +0100
Subject: ASoC: Remove card field from snd_soc_dai struct

The card field of the snd_soc_dai field is very rarely used. We can use
dai->component->card instead and remove the card field from the snd_soc_dai
struct.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dai.h | 2 --
 sound/soc/soc-core.c    | 7 +------
 sound/soc/soc-dapm.c    | 2 +-
 3 files changed, 2 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index 45d0fa10ab9..373d1775ecb 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -275,8 +275,6 @@ struct snd_soc_dai {
 	unsigned int tx_mask;
 	unsigned int rx_mask;
 
-	struct snd_soc_card *card;
-
 	struct list_head list;
 };
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index ea1df2083bd..f3216fc6d9f 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1315,11 +1315,6 @@ static int soc_probe_link_dais(struct snd_soc_card *card, int num, int order)
 	dev_dbg(card->dev, "ASoC: probe %s dai link %d late %d\n",
 			card->name, num, order);
 
-	/* config components */
-	cpu_dai->card = card;
-	for (i = 0; i < rtd->num_codecs; i++)
-		rtd->codec_dais[i]->card = card;
-
 	/* set default power off timeout */
 	rtd->pmdown_time = pmdown_time;
 
@@ -2314,7 +2309,7 @@ EXPORT_SYMBOL_GPL(snd_soc_add_card_controls);
 int snd_soc_add_dai_controls(struct snd_soc_dai *dai,
 	const struct snd_kcontrol_new *controls, int num_controls)
 {
-	struct snd_card *card = dai->card->snd_card;
+	struct snd_card *card = dai->component->card->snd_card;
 
 	return snd_soc_add_controls(card, dai->dev, controls, num_controls,
 			NULL, dai);
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 6bf2c9795df..c5136bb1f98 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1043,7 +1043,7 @@ static int is_connected_input_ep(struct snd_soc_dapm_widget *widget,
 int snd_soc_dapm_dai_get_connected_widgets(struct snd_soc_dai *dai, int stream,
 	struct snd_soc_dapm_widget_list **list)
 {
-	struct snd_soc_card *card = dai->card;
+	struct snd_soc_card *card = dai->component->card;
 	struct snd_soc_dapm_widget *w;
 	int paths;
 
-- 
cgit v1.2.3-70-g09d2


From 6e0bd6c35b021dc73a81ebd1ef79761233c48b50 Mon Sep 17 00:00:00 2001
From: Rostislav Lisovy <lisovy@gmail.com>
Date: Mon, 3 Nov 2014 10:33:18 +0100
Subject: cfg80211: 802.11p OCB mode handling

This patch adds new iface type (NL80211_IFTYPE_OCB) representing
the OCB (Outside the Context of a BSS) mode.
When establishing a connection to the network a cfg80211_join_ocb
function is called (particular nl80211_command is added as well).
A mandatory parameters during the ocb_join operation are 'center
frequency' and 'channel width (5/10 MHz)'.

Changes done in mac80211 are minimal possible required to avoid
many warnings (warning: enumeration value 'NL80211_IFTYPE_OCB'
not handled in switch) during compilation. Full functionality
(where needed) is added in the following patch.

Signed-off-by: Rostislav Lisovy <rostislav.lisovy@fel.cvut.cz>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 19 ++++++++++
 include/uapi/linux/nl80211.h | 11 ++++++
 net/mac80211/cfg.c           |  1 +
 net/mac80211/chan.c          |  2 +
 net/mac80211/iface.c         |  5 +++
 net/mac80211/util.c          |  3 ++
 net/wireless/Makefile        |  2 +-
 net/wireless/chan.c          |  8 ++++
 net/wireless/core.c          |  3 ++
 net/wireless/core.h          | 12 ++++++
 net/wireless/nl80211.c       | 39 ++++++++++++++++++++
 net/wireless/ocb.c           | 88 ++++++++++++++++++++++++++++++++++++++++++++
 net/wireless/rdev-ops.h      | 21 +++++++++++
 net/wireless/trace.h         | 21 +++++++++++
 net/wireless/util.c          |  5 ++-
 15 files changed, 238 insertions(+), 2 deletions(-)
 create mode 100644 net/wireless/ocb.c

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index f67948e1860..5c3acd07acd 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1358,6 +1358,16 @@ struct mesh_setup {
 	u32 basic_rates;
 };
 
+/**
+ * struct ocb_setup - 802.11p OCB mode setup configuration
+ * @chandef: defines the channel to use
+ *
+ * These parameters are fixed when connecting to the network
+ */
+struct ocb_setup {
+	struct cfg80211_chan_def chandef;
+};
+
 /**
  * struct ieee80211_txq_params - TX queue parameters
  * @ac: AC identifier
@@ -2352,6 +2362,11 @@ struct cfg80211_qos_map {
  *	with the peer followed by immediate teardown when the addition is later
  *	rejected)
  * @del_tx_ts: remove an existing TX TS
+ *
+ * @join_ocb: join the OCB network with the specified parameters
+ *	(invoked with the wireless_dev mutex held)
+ * @leave_ocb: leave the current OCB network
+ *	(invoked with the wireless_dev mutex held)
  */
 struct cfg80211_ops {
 	int	(*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -2433,6 +2448,10 @@ struct cfg80211_ops {
 			     const struct mesh_setup *setup);
 	int	(*leave_mesh)(struct wiphy *wiphy, struct net_device *dev);
 
+	int	(*join_ocb)(struct wiphy *wiphy, struct net_device *dev,
+			    struct ocb_setup *setup);
+	int	(*leave_ocb)(struct wiphy *wiphy, struct net_device *dev);
+
 	int	(*change_bss)(struct wiphy *wiphy, struct net_device *dev,
 			      struct bss_parameters *params);
 
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index f7daae59248..9b3025e4377 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -746,6 +746,11 @@
  *	destination %NL80211_ATTR_MAC on the interface identified by
  *	%NL80211_ATTR_IFINDEX.
  *
+ * @NL80211_CMD_JOIN_OCB: Join the OCB network. The center frequency and
+ *	bandwidth of a channel must be given.
+ * @NL80211_CMD_LEAVE_OCB: Leave the OCB network -- no special arguments, the
+ *	network is determined by the network interface.
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -922,6 +927,9 @@ enum nl80211_commands {
 
 	NL80211_CMD_GET_MPP,
 
+	NL80211_CMD_JOIN_OCB,
+	NL80211_CMD_LEAVE_OCB,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
@@ -2074,6 +2082,8 @@ enum nl80211_attrs {
  *	and therefore can't be created in the normal ways, use the
  *	%NL80211_CMD_START_P2P_DEVICE and %NL80211_CMD_STOP_P2P_DEVICE
  *	commands to create and destroy one
+ * @NL80211_IF_TYPE_OCB: Outside Context of a BSS
+ *	This mode corresponds to the MIB variable dot11OCBActivated=true
  * @NL80211_IFTYPE_MAX: highest interface type number currently defined
  * @NUM_NL80211_IFTYPES: number of defined interface types
  *
@@ -2093,6 +2103,7 @@ enum nl80211_iftype {
 	NL80211_IFTYPE_P2P_CLIENT,
 	NL80211_IFTYPE_P2P_GO,
 	NL80211_IFTYPE_P2P_DEVICE,
+	NL80211_IFTYPE_OCB,
 
 	/* keep last */
 	NUM_NL80211_IFTYPES,
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index b9659b8b70f..1e2afc95ad0 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -230,6 +230,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
 	case NUM_NL80211_IFTYPES:
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_P2P_GO:
+	case NL80211_IFTYPE_OCB:
 		/* shouldn't happen */
 		WARN_ON_ONCE(1);
 		break;
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index ee71bb6f64f..ff1f877e3b6 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -270,6 +270,7 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local,
 		case NL80211_IFTYPE_ADHOC:
 		case NL80211_IFTYPE_WDS:
 		case NL80211_IFTYPE_MESH_POINT:
+		case NL80211_IFTYPE_OCB:
 			width = vif->bss_conf.chandef.width;
 			break;
 		case NL80211_IFTYPE_UNSPECIFIED:
@@ -909,6 +910,7 @@ ieee80211_vif_chanctx_reservation_complete(struct ieee80211_sub_if_data *sdata)
 	case NL80211_IFTYPE_ADHOC:
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_MESH_POINT:
+	case NL80211_IFTYPE_OCB:
 		ieee80211_queue_work(&sdata->local->hw,
 				     &sdata->csa_finalize_work);
 		break;
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 1ffcc070124..d69e7532095 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -521,6 +521,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 	case NL80211_IFTYPE_MONITOR:
 	case NL80211_IFTYPE_ADHOC:
 	case NL80211_IFTYPE_P2P_DEVICE:
+	case NL80211_IFTYPE_OCB:
 		/* no special treatment */
 		break;
 	case NL80211_IFTYPE_UNSPECIFIED:
@@ -631,6 +632,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 		case NL80211_IFTYPE_ADHOC:
 		case NL80211_IFTYPE_AP:
 		case NL80211_IFTYPE_MESH_POINT:
+		case NL80211_IFTYPE_OCB:
 			netif_carrier_off(dev);
 			break;
 		case NL80211_IFTYPE_WDS:
@@ -1351,6 +1353,9 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 		sdata->vif.bss_conf.bssid = sdata->u.mgd.bssid;
 		ieee80211_sta_setup_sdata(sdata);
 		break;
+	case NL80211_IFTYPE_OCB:
+		/* to be implemented in the future */
+		break;
 	case NL80211_IFTYPE_ADHOC:
 		sdata->vif.bss_conf.bssid = sdata->u.ibss.bssid;
 		ieee80211_ibss_setup_sdata(sdata);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 666aa1306c4..d7d69c89ff3 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1841,6 +1841,9 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 			ieee80211_bss_info_change_notify(sdata, changed);
 			sdata_unlock(sdata);
 			break;
+		case NL80211_IFTYPE_OCB:
+			/* to be implemented in the future */
+			break;
 		case NL80211_IFTYPE_ADHOC:
 			changed |= BSS_CHANGED_IBSS;
 			/* fall through */
diff --git a/net/wireless/Makefile b/net/wireless/Makefile
index a761670af31..4c9e39f04ef 100644
--- a/net/wireless/Makefile
+++ b/net/wireless/Makefile
@@ -10,7 +10,7 @@ obj-$(CONFIG_WEXT_SPY) += wext-spy.o
 obj-$(CONFIG_WEXT_PRIV) += wext-priv.o
 
 cfg80211-y += core.o sysfs.o radiotap.o util.o reg.o scan.o nl80211.o
-cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o ap.o trace.o
+cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o ap.o trace.o ocb.o
 cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o
 cfg80211-$(CONFIG_CFG80211_WEXT) += wext-compat.o wext-sme.o
 cfg80211-$(CONFIG_CFG80211_INTERNAL_REGDB) += regdb.o
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 8f39e33e71b..85506f1d078 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -366,6 +366,7 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
 
 		break;
 	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_OCB:
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_MONITOR:
 	case NL80211_IFTYPE_AP_VLAN:
@@ -892,6 +893,13 @@ cfg80211_get_chan_state(struct wireless_dev *wdev,
 				*radar_detect |= BIT(wdev->chandef.width);
 		}
 		return;
+	case NL80211_IFTYPE_OCB:
+		if (wdev->chandef.chan) {
+			*chan = wdev->chandef.chan;
+			*chanmode = CHAN_MODE_SHARED;
+			return;
+		}
+		break;
 	case NL80211_IFTYPE_MONITOR:
 	case NL80211_IFTYPE_AP_VLAN:
 	case NL80211_IFTYPE_WDS:
diff --git a/net/wireless/core.c b/net/wireless/core.c
index da4dcb65ade..a4d27927aba 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -869,6 +869,9 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev,
 	case NL80211_IFTYPE_P2P_GO:
 		__cfg80211_stop_ap(rdev, dev, true);
 		break;
+	case NL80211_IFTYPE_OCB:
+		__cfg80211_leave_ocb(rdev, dev);
+		break;
 	case NL80211_IFTYPE_WDS:
 		/* must be handled by mac80211/driver, has no APIs */
 		break;
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 7e3a3cef7df..61ee664cf2b 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -290,6 +290,18 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev,
 			      struct wireless_dev *wdev,
 			      struct cfg80211_chan_def *chandef);
 
+/* OCB */
+int __cfg80211_join_ocb(struct cfg80211_registered_device *rdev,
+			struct net_device *dev,
+			struct ocb_setup *setup);
+int cfg80211_join_ocb(struct cfg80211_registered_device *rdev,
+		      struct net_device *dev,
+		      struct ocb_setup *setup);
+int __cfg80211_leave_ocb(struct cfg80211_registered_device *rdev,
+			 struct net_device *dev);
+int cfg80211_leave_ocb(struct cfg80211_registered_device *rdev,
+		       struct net_device *dev);
+
 /* AP */
 int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
 		       struct net_device *dev, bool notify);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index f7d918858d3..1a31736914e 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -885,6 +885,7 @@ static int nl80211_key_allowed(struct wireless_dev *wdev)
 			return -ENOLINK;
 		break;
 	case NL80211_IFTYPE_UNSPECIFIED:
+	case NL80211_IFTYPE_OCB:
 	case NL80211_IFTYPE_MONITOR:
 	case NL80211_IFTYPE_P2P_DEVICE:
 	case NL80211_IFTYPE_WDS:
@@ -8275,6 +8276,28 @@ static int nl80211_set_cqm(struct sk_buff *skb, struct genl_info *info)
 	return -EINVAL;
 }
 
+static int nl80211_join_ocb(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct ocb_setup setup = {};
+	int err;
+
+	err = nl80211_parse_chandef(rdev, info, &setup.chandef);
+	if (err)
+		return err;
+
+	return cfg80211_join_ocb(rdev, dev, &setup);
+}
+
+static int nl80211_leave_ocb(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+
+	return cfg80211_leave_ocb(rdev, dev);
+}
+
 static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -10218,6 +10241,22 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_JOIN_OCB,
+		.doit = nl80211_join_ocb,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL80211_CMD_LEAVE_OCB,
+		.doit = nl80211_leave_ocb,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 #ifdef CONFIG_PM
 	{
 		.cmd = NL80211_CMD_GET_WOWLAN,
diff --git a/net/wireless/ocb.c b/net/wireless/ocb.c
new file mode 100644
index 00000000000..c00d4a79231
--- /dev/null
+++ b/net/wireless/ocb.c
@@ -0,0 +1,88 @@
+/*
+ * OCB mode implementation
+ *
+ * Copyright: (c) 2014 Czech Technical University in Prague
+ *            (c) 2014 Volkswagen Group Research
+ * Author:    Rostislav Lisovy <rostislav.lisovy@fel.cvut.cz>
+ * Funded by: Volkswagen Group Research
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/ieee80211.h>
+#include <net/cfg80211.h>
+#include "nl80211.h"
+#include "core.h"
+#include "rdev-ops.h"
+
+int __cfg80211_join_ocb(struct cfg80211_registered_device *rdev,
+			struct net_device *dev,
+			struct ocb_setup *setup)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int err;
+
+	ASSERT_WDEV_LOCK(wdev);
+
+	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_OCB)
+		return -EOPNOTSUPP;
+
+	if (WARN_ON(!setup->chandef.chan))
+		return -EINVAL;
+
+	err = rdev_join_ocb(rdev, dev, setup);
+	if (!err)
+		wdev->chandef = setup->chandef;
+
+	return err;
+}
+
+int cfg80211_join_ocb(struct cfg80211_registered_device *rdev,
+		      struct net_device *dev,
+		      struct ocb_setup *setup)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int err;
+
+	wdev_lock(wdev);
+	err = __cfg80211_join_ocb(rdev, dev, setup);
+	wdev_unlock(wdev);
+
+	return err;
+}
+
+int __cfg80211_leave_ocb(struct cfg80211_registered_device *rdev,
+			 struct net_device *dev)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int err;
+
+	ASSERT_WDEV_LOCK(wdev);
+
+	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_OCB)
+		return -EOPNOTSUPP;
+
+	if (!rdev->ops->leave_ocb)
+		return -EOPNOTSUPP;
+
+	err = rdev_leave_ocb(rdev, dev);
+	if (!err)
+		memset(&wdev->chandef, 0, sizeof(wdev->chandef));
+
+	return err;
+}
+
+int cfg80211_leave_ocb(struct cfg80211_registered_device *rdev,
+		       struct net_device *dev)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int err;
+
+	wdev_lock(wdev);
+	err = __cfg80211_leave_ocb(rdev, dev);
+	wdev_unlock(wdev);
+
+	return err;
+}
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 71b1db3cc64..1b3864cd50c 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -348,6 +348,27 @@ static inline int rdev_leave_mesh(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static inline int rdev_join_ocb(struct cfg80211_registered_device *rdev,
+				struct net_device *dev,
+				struct ocb_setup *setup)
+{
+	int ret;
+	trace_rdev_join_ocb(&rdev->wiphy, dev, setup);
+	ret = rdev->ops->join_ocb(&rdev->wiphy, dev, setup);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+	return ret;
+}
+
+static inline int rdev_leave_ocb(struct cfg80211_registered_device *rdev,
+				 struct net_device *dev)
+{
+	int ret;
+	trace_rdev_leave_ocb(&rdev->wiphy, dev);
+	ret = rdev->ops->leave_ocb(&rdev->wiphy, dev);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+	return ret;
+}
+
 static inline int rdev_change_bss(struct cfg80211_registered_device *rdev,
 				  struct net_device *dev,
 				  struct bss_parameters *params)
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index cdb2c2ef1ae..277a85df910 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -600,6 +600,11 @@ DEFINE_EVENT(wiphy_netdev_evt, rdev_leave_ibss,
 	TP_ARGS(wiphy, netdev)
 );
 
+DEFINE_EVENT(wiphy_netdev_evt, rdev_leave_ocb,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev),
+	TP_ARGS(wiphy, netdev)
+);
+
 DEFINE_EVENT(wiphy_netdev_evt, rdev_flush_pmksa,
 	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev),
 	TP_ARGS(wiphy, netdev)
@@ -1316,6 +1321,22 @@ TRACE_EVENT(rdev_join_ibss,
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(bssid), __entry->ssid)
 );
 
+TRACE_EVENT(rdev_join_ocb,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 const struct ocb_setup *setup),
+	TP_ARGS(wiphy, netdev, setup),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG)
+);
+
 TRACE_EVENT(rdev_set_wiphy_params,
 	TP_PROTO(struct wiphy *wiphy, u32 changed),
 	TP_ARGS(wiphy, changed),
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 5e233a577d0..d0ac795445b 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -442,7 +442,8 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
 		break;
 	case cpu_to_le16(0):
 		if (iftype != NL80211_IFTYPE_ADHOC &&
-		    iftype != NL80211_IFTYPE_STATION)
+		    iftype != NL80211_IFTYPE_STATION &&
+		    iftype != NL80211_IFTYPE_OCB)
 				return -1;
 		break;
 	}
@@ -519,6 +520,7 @@ int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr,
 		memcpy(hdr.addr3, skb->data, ETH_ALEN);
 		hdrlen = 24;
 		break;
+	case NL80211_IFTYPE_OCB:
 	case NL80211_IFTYPE_ADHOC:
 		/* DA SA BSSID */
 		memcpy(hdr.addr1, skb->data, ETH_ALEN);
@@ -937,6 +939,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 			if (dev->ieee80211_ptr->use_4addr)
 				break;
 			/* fall through */
+		case NL80211_IFTYPE_OCB:
 		case NL80211_IFTYPE_P2P_CLIENT:
 		case NL80211_IFTYPE_ADHOC:
 			dev->priv_flags |= IFF_DONT_BRIDGE;
-- 
cgit v1.2.3-70-g09d2


From 239281f803e2efdb77d906ef296086b6917e5d71 Mon Sep 17 00:00:00 2001
From: Rostislav Lisovy <lisovy@gmail.com>
Date: Mon, 3 Nov 2014 10:33:19 +0100
Subject: mac80211: 802.11p OCB mode support

This patch adds 802.11p OCB (Outside the Context of a BSS) mode
support.

When communicating in OCB mode a mandatory wildcard BSSID
(48 '1' bits) is used.

The EDCA parameters handling function was changed to support
802.11p specific values.

The insertion of a newly discovered STAs is done in the similar way
as in the IBSS mode -- through the deferred insertion.

The OCB mode uses a periodic 'housekeeping task' for expiration of
disconnected STAs (in the similar manner as in the MESH mode).

New Kconfig option for verbose OCB debugging outputs is added.

Signed-off-by: Rostislav Lisovy <rostislav.lisovy@fel.cvut.cz>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |   2 +
 net/mac80211/Kconfig       |  11 ++
 net/mac80211/Makefile      |   3 +-
 net/mac80211/cfg.c         |  13 +++
 net/mac80211/chan.c        |   1 +
 net/mac80211/debug.h       |  10 ++
 net/mac80211/driver-ops.h  |   3 +-
 net/mac80211/ieee80211_i.h |  29 ++++++
 net/mac80211/iface.c       |  20 +++-
 net/mac80211/ocb.c         | 250 +++++++++++++++++++++++++++++++++++++++++++++
 net/mac80211/rx.c          |  35 +++++++
 net/mac80211/tx.c          |  15 +++
 net/mac80211/util.c        |  30 ++++--
 net/mac80211/wme.c         |   4 +
 14 files changed, 417 insertions(+), 9 deletions(-)
 create mode 100644 net/mac80211/ocb.c

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 03edbf6f623..db54635d65c 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -263,6 +263,7 @@ struct ieee80211_vif_chanctx_switch {
  * @BSS_CHANGED_BANDWIDTH: The bandwidth used by this interface changed,
  *	note that this is only called when it changes after the channel
  *	context had been assigned.
+ * @BSS_CHANGED_OCB: OCB join status changed
  */
 enum ieee80211_bss_change {
 	BSS_CHANGED_ASSOC		= 1<<0,
@@ -287,6 +288,7 @@ enum ieee80211_bss_change {
 	BSS_CHANGED_P2P_PS		= 1<<19,
 	BSS_CHANGED_BEACON_INFO		= 1<<20,
 	BSS_CHANGED_BANDWIDTH		= 1<<21,
+	BSS_CHANGED_OCB                 = 1<<22,
 
 	/* when adding here, make sure to change ieee80211_reconfig */
 };
diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index 67cf8125d75..75cc6801a43 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -176,6 +176,17 @@ config MAC80211_HT_DEBUG
 
 	  Do not select this option.
 
+config MAC80211_OCB_DEBUG
+	bool "Verbose OCB debugging"
+	depends on MAC80211_DEBUG_MENU
+	---help---
+	  Selecting this option causes mac80211 to print out
+	  very verbose OCB debugging messages. It should not
+	  be selected on production systems as those messages
+	  are remotely triggerable.
+
+	  Do not select this option.
+
 config MAC80211_IBSS_DEBUG
 	bool "Verbose IBSS debugging"
 	depends on MAC80211_DEBUG_MENU
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index 7273d2796dd..e53671b1105 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -27,7 +27,8 @@ mac80211-y := \
 	event.o \
 	chan.o \
 	trace.o mlme.o \
-	tdls.o
+	tdls.o \
+	ocb.o
 
 mac80211-$(CONFIG_MAC80211_LEDS) += led.o
 mac80211-$(CONFIG_MAC80211_DEBUGFS) += \
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 1e2afc95ad0..06185940cbb 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2019,6 +2019,17 @@ static int ieee80211_leave_ibss(struct wiphy *wiphy, struct net_device *dev)
 	return ieee80211_ibss_leave(IEEE80211_DEV_TO_SUB_IF(dev));
 }
 
+static int ieee80211_join_ocb(struct wiphy *wiphy, struct net_device *dev,
+			      struct ocb_setup *setup)
+{
+	return ieee80211_ocb_join(IEEE80211_DEV_TO_SUB_IF(dev), setup);
+}
+
+static int ieee80211_leave_ocb(struct wiphy *wiphy, struct net_device *dev)
+{
+	return ieee80211_ocb_leave(IEEE80211_DEV_TO_SUB_IF(dev));
+}
+
 static int ieee80211_set_mcast_rate(struct wiphy *wiphy, struct net_device *dev,
 				    int rate[IEEE80211_NUM_BANDS])
 {
@@ -3693,6 +3704,8 @@ const struct cfg80211_ops mac80211_config_ops = {
 	.join_mesh = ieee80211_join_mesh,
 	.leave_mesh = ieee80211_leave_mesh,
 #endif
+	.join_ocb = ieee80211_join_ocb,
+	.leave_ocb = ieee80211_leave_ocb,
 	.change_bss = ieee80211_change_bss,
 	.set_txq_params = ieee80211_set_txq_params,
 	.set_monitor_channel = ieee80211_set_monitor_channel,
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index ff1f877e3b6..c7c51422029 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -675,6 +675,7 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local,
 		case NL80211_IFTYPE_ADHOC:
 		case NL80211_IFTYPE_WDS:
 		case NL80211_IFTYPE_MESH_POINT:
+		case NL80211_IFTYPE_OCB:
 			break;
 		default:
 			WARN_ON_ONCE(1);
diff --git a/net/mac80211/debug.h b/net/mac80211/debug.h
index 493d68061f0..1956b3115dd 100644
--- a/net/mac80211/debug.h
+++ b/net/mac80211/debug.h
@@ -2,6 +2,12 @@
 #define __MAC80211_DEBUG_H
 #include <net/cfg80211.h>
 
+#ifdef CONFIG_MAC80211_OCB_DEBUG
+#define MAC80211_OCB_DEBUG 1
+#else
+#define MAC80211_OCB_DEBUG 0
+#endif
+
 #ifdef CONFIG_MAC80211_IBSS_DEBUG
 #define MAC80211_IBSS_DEBUG 1
 #else
@@ -131,6 +137,10 @@ do {									\
 	_sdata_dbg(MAC80211_HT_DEBUG && net_ratelimit(),		\
 		   sdata, fmt, ##__VA_ARGS__)
 
+#define ocb_dbg(sdata, fmt, ...)					\
+	_sdata_dbg(MAC80211_OCB_DEBUG,					\
+		   sdata, fmt, ##__VA_ARGS__)
+
 #define ibss_dbg(sdata, fmt, ...)					\
 	_sdata_dbg(MAC80211_IBSS_DEBUG,					\
 		   sdata, fmt, ##__VA_ARGS__)
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index d1e128e5db4..8e1889ff2e5 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -214,7 +214,8 @@ static inline void drv_bss_info_changed(struct ieee80211_local *local,
 				    BSS_CHANGED_BEACON_ENABLED) &&
 			 sdata->vif.type != NL80211_IFTYPE_AP &&
 			 sdata->vif.type != NL80211_IFTYPE_ADHOC &&
-			 sdata->vif.type != NL80211_IFTYPE_MESH_POINT))
+			 sdata->vif.type != NL80211_IFTYPE_MESH_POINT &&
+			 sdata->vif.type != NL80211_IFTYPE_OCB))
 		return;
 
 	if (WARN_ON_ONCE(sdata->vif.type == NL80211_IFTYPE_P2P_DEVICE ||
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index eb425298fe6..fbd6bee9c95 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -576,6 +576,25 @@ struct ieee80211_if_ibss {
 	} state;
 };
 
+/**
+ * struct ieee80211_if_ocb - OCB mode state
+ *
+ * @housekeeping_timer: timer for periodic invocation of a housekeeping task
+ * @wrkq_flags: OCB deferred task action
+ * @incomplete_lock: delayed STA insertion lock
+ * @incomplete_stations: list of STAs waiting for delayed insertion
+ * @joined: indication if the interface is connected to an OCB network
+ */
+struct ieee80211_if_ocb {
+	struct timer_list housekeeping_timer;
+	unsigned long wrkq_flags;
+
+	spinlock_t incomplete_lock;
+	struct list_head incomplete_stations;
+
+	bool joined;
+};
+
 /**
  * struct ieee80211_mesh_sync_ops - Extensible synchronization framework interface
  *
@@ -869,6 +888,7 @@ struct ieee80211_sub_if_data {
 		struct ieee80211_if_managed mgd;
 		struct ieee80211_if_ibss ibss;
 		struct ieee80211_if_mesh mesh;
+		struct ieee80211_if_ocb ocb;
 		u32 mntr_flags;
 	} u;
 
@@ -1505,6 +1525,15 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata,
 int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata);
 void ieee80211_ibss_stop(struct ieee80211_sub_if_data *sdata);
 
+/* OCB code */
+void ieee80211_ocb_work(struct ieee80211_sub_if_data *sdata);
+void ieee80211_ocb_rx_no_sta(struct ieee80211_sub_if_data *sdata,
+			     const u8 *bssid, const u8 *addr, u32 supp_rates);
+void ieee80211_ocb_setup_sdata(struct ieee80211_sub_if_data *sdata);
+int ieee80211_ocb_join(struct ieee80211_sub_if_data *sdata,
+		       struct ocb_setup *setup);
+int ieee80211_ocb_leave(struct ieee80211_sub_if_data *sdata);
+
 /* mesh code */
 void ieee80211_mesh_work(struct ieee80211_sub_if_data *sdata);
 void ieee80211_mesh_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index d69e7532095..6b631c049eb 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -258,6 +258,15 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata,
 	/* we hold the RTNL here so can safely walk the list */
 	list_for_each_entry(nsdata, &local->interfaces, list) {
 		if (nsdata != sdata && ieee80211_sdata_running(nsdata)) {
+			/*
+			 * Only OCB and monitor mode may coexist
+			 */
+			if ((sdata->vif.type == NL80211_IFTYPE_OCB &&
+			     nsdata->vif.type != NL80211_IFTYPE_MONITOR) ||
+			    (sdata->vif.type != NL80211_IFTYPE_MONITOR &&
+			     nsdata->vif.type == NL80211_IFTYPE_OCB))
+				return -EBUSY;
+
 			/*
 			 * Allow only a single IBSS interface to be up at any
 			 * time. This is restricted because beacon distribution
@@ -1283,6 +1292,9 @@ static void ieee80211_iface_work(struct work_struct *work)
 			break;
 		ieee80211_mesh_work(sdata);
 		break;
+	case NL80211_IFTYPE_OCB:
+		ieee80211_ocb_work(sdata);
+		break;
 	default:
 		break;
 	}
@@ -1302,6 +1314,9 @@ static void ieee80211_recalc_smps_work(struct work_struct *work)
 static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 				  enum nl80211_iftype type)
 {
+	static const u8 bssid_wildcard[ETH_ALEN] = {0xff, 0xff, 0xff,
+						    0xff, 0xff, 0xff};
+
 	/* clear type-dependent union */
 	memset(&sdata->u, 0, sizeof(sdata->u));
 
@@ -1354,7 +1369,8 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 		ieee80211_sta_setup_sdata(sdata);
 		break;
 	case NL80211_IFTYPE_OCB:
-		/* to be implemented in the future */
+		sdata->vif.bss_conf.bssid = bssid_wildcard;
+		ieee80211_ocb_setup_sdata(sdata);
 		break;
 	case NL80211_IFTYPE_ADHOC:
 		sdata->vif.bss_conf.bssid = sdata->u.ibss.bssid;
@@ -1403,6 +1419,7 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_ADHOC:
+	case NL80211_IFTYPE_OCB:
 		/*
 		 * Could maybe also all others here?
 		 * Just not sure how that interacts
@@ -1418,6 +1435,7 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_ADHOC:
+	case NL80211_IFTYPE_OCB:
 		/*
 		 * Could probably support everything
 		 * but WDS here (WDS do_open can fail
diff --git a/net/mac80211/ocb.c b/net/mac80211/ocb.c
new file mode 100644
index 00000000000..358d5f9d820
--- /dev/null
+++ b/net/mac80211/ocb.c
@@ -0,0 +1,250 @@
+/*
+ * OCB mode implementation
+ *
+ * Copyright: (c) 2014 Czech Technical University in Prague
+ *            (c) 2014 Volkswagen Group Research
+ * Author:    Rostislav Lisovy <rostislav.lisovy@fel.cvut.cz>
+ * Funded by: Volkswagen Group Research
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/delay.h>
+#include <linux/if_ether.h>
+#include <linux/skbuff.h>
+#include <linux/if_arp.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <net/mac80211.h>
+#include <asm/unaligned.h>
+
+#include "ieee80211_i.h"
+#include "driver-ops.h"
+#include "rate.h"
+
+#define IEEE80211_OCB_HOUSEKEEPING_INTERVAL		(60 * HZ)
+#define IEEE80211_OCB_PEER_INACTIVITY_LIMIT		(240 * HZ)
+#define IEEE80211_OCB_MAX_STA_ENTRIES			128
+
+/**
+ * enum ocb_deferred_task_flags - mac80211 OCB deferred tasks
+ * @OCB_WORK_HOUSEKEEPING: run the periodic OCB housekeeping tasks
+ *
+ * These flags are used in @wrkq_flags field of &struct ieee80211_if_ocb
+ */
+enum ocb_deferred_task_flags {
+	OCB_WORK_HOUSEKEEPING,
+};
+
+void ieee80211_ocb_rx_no_sta(struct ieee80211_sub_if_data *sdata,
+			     const u8 *bssid, const u8 *addr,
+			     u32 supp_rates)
+{
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_chanctx_conf *chanctx_conf;
+	struct ieee80211_supported_band *sband;
+	enum nl80211_bss_scan_width scan_width;
+	struct sta_info *sta;
+	int band;
+
+	/* XXX: Consider removing the least recently used entry and
+	 *      allow new one to be added.
+	 */
+	if (local->num_sta >= IEEE80211_OCB_MAX_STA_ENTRIES) {
+		net_info_ratelimited("%s: No room for a new OCB STA entry %pM\n",
+				     sdata->name, addr);
+		return;
+	}
+
+	ocb_dbg(sdata, "Adding new OCB station %pM\n", addr);
+
+	rcu_read_lock();
+	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
+	if (WARN_ON_ONCE(!chanctx_conf)) {
+		rcu_read_unlock();
+		return;
+	}
+	band = chanctx_conf->def.chan->band;
+	scan_width = cfg80211_chandef_to_scan_width(&chanctx_conf->def);
+	rcu_read_unlock();
+
+	sta = sta_info_alloc(sdata, addr, GFP_ATOMIC);
+	if (!sta)
+		return;
+
+	sta->last_rx = jiffies;
+
+	/* Add only mandatory rates for now */
+	sband = local->hw.wiphy->bands[band];
+	sta->sta.supp_rates[band] =
+		ieee80211_mandatory_rates(sband, scan_width);
+
+	spin_lock(&ifocb->incomplete_lock);
+	list_add(&sta->list, &ifocb->incomplete_stations);
+	spin_unlock(&ifocb->incomplete_lock);
+	ieee80211_queue_work(&local->hw, &sdata->work);
+}
+
+static struct sta_info *ieee80211_ocb_finish_sta(struct sta_info *sta)
+	__acquires(RCU)
+{
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	u8 addr[ETH_ALEN];
+
+	memcpy(addr, sta->sta.addr, ETH_ALEN);
+
+	ocb_dbg(sdata, "Adding new IBSS station %pM (dev=%s)\n",
+		addr, sdata->name);
+
+	sta_info_move_state(sta, IEEE80211_STA_AUTH);
+	sta_info_move_state(sta, IEEE80211_STA_ASSOC);
+	sta_info_move_state(sta, IEEE80211_STA_AUTHORIZED);
+
+	rate_control_rate_init(sta);
+
+	/* If it fails, maybe we raced another insertion? */
+	if (sta_info_insert_rcu(sta))
+		return sta_info_get(sdata, addr);
+	return sta;
+}
+
+static void ieee80211_ocb_housekeeping(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+
+	ocb_dbg(sdata, "Running ocb housekeeping\n");
+
+	ieee80211_sta_expire(sdata, IEEE80211_OCB_PEER_INACTIVITY_LIMIT);
+
+	mod_timer(&ifocb->housekeeping_timer,
+		  round_jiffies(jiffies + IEEE80211_OCB_HOUSEKEEPING_INTERVAL));
+}
+
+void ieee80211_ocb_work(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+	struct sta_info *sta;
+
+	if (ifocb->joined != true)
+		return;
+
+	sdata_lock(sdata);
+
+	spin_lock_bh(&ifocb->incomplete_lock);
+	while (!list_empty(&ifocb->incomplete_stations)) {
+		sta = list_first_entry(&ifocb->incomplete_stations,
+				       struct sta_info, list);
+		list_del(&sta->list);
+		spin_unlock_bh(&ifocb->incomplete_lock);
+
+		ieee80211_ocb_finish_sta(sta);
+		rcu_read_unlock();
+		spin_lock_bh(&ifocb->incomplete_lock);
+	}
+	spin_unlock_bh(&ifocb->incomplete_lock);
+
+	if (test_and_clear_bit(OCB_WORK_HOUSEKEEPING, &ifocb->wrkq_flags))
+		ieee80211_ocb_housekeeping(sdata);
+
+	sdata_unlock(sdata);
+}
+
+static void ieee80211_ocb_housekeeping_timer(unsigned long data)
+{
+	struct ieee80211_sub_if_data *sdata = (void *)data;
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+
+	set_bit(OCB_WORK_HOUSEKEEPING, &ifocb->wrkq_flags);
+
+	ieee80211_queue_work(&local->hw, &sdata->work);
+}
+
+void ieee80211_ocb_setup_sdata(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+
+	setup_timer(&ifocb->housekeeping_timer,
+		    ieee80211_ocb_housekeeping_timer,
+		    (unsigned long)sdata);
+	INIT_LIST_HEAD(&ifocb->incomplete_stations);
+	spin_lock_init(&ifocb->incomplete_lock);
+}
+
+int ieee80211_ocb_join(struct ieee80211_sub_if_data *sdata,
+		       struct ocb_setup *setup)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+	u32 changed = BSS_CHANGED_OCB;
+	int err;
+
+	if (ifocb->joined == true)
+		return -EINVAL;
+
+	sdata->flags |= IEEE80211_SDATA_OPERATING_GMODE;
+	sdata->smps_mode = IEEE80211_SMPS_OFF;
+	sdata->needed_rx_chains = sdata->local->rx_chains;
+
+	mutex_lock(&sdata->local->mtx);
+	err = ieee80211_vif_use_channel(sdata, &setup->chandef,
+					IEEE80211_CHANCTX_SHARED);
+	mutex_unlock(&sdata->local->mtx);
+	if (err)
+		return err;
+
+	ieee80211_bss_info_change_notify(sdata, changed);
+
+	ifocb->joined = true;
+
+	set_bit(OCB_WORK_HOUSEKEEPING, &ifocb->wrkq_flags);
+	ieee80211_queue_work(&local->hw, &sdata->work);
+
+	netif_carrier_on(sdata->dev);
+	return 0;
+}
+
+int ieee80211_ocb_leave(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+	struct ieee80211_local *local = sdata->local;
+	struct sta_info *sta;
+
+	ifocb->joined = false;
+	sta_info_flush(sdata);
+
+	spin_lock_bh(&ifocb->incomplete_lock);
+	while (!list_empty(&ifocb->incomplete_stations)) {
+		sta = list_first_entry(&ifocb->incomplete_stations,
+				       struct sta_info, list);
+		list_del(&sta->list);
+		spin_unlock_bh(&ifocb->incomplete_lock);
+
+		sta_info_free(local, sta);
+		spin_lock_bh(&ifocb->incomplete_lock);
+	}
+	spin_unlock_bh(&ifocb->incomplete_lock);
+
+	netif_carrier_off(sdata->dev);
+	clear_bit(SDATA_STATE_OFFCHANNEL, &sdata->state);
+	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_OCB);
+
+	mutex_lock(&sdata->local->mtx);
+	ieee80211_vif_release_channel(sdata);
+	mutex_unlock(&sdata->local->mtx);
+
+	skb_queue_purge(&sdata->skb_queue);
+
+	del_timer_sync(&sdata->u.ocb.housekeeping_timer);
+	/* If the timer fired while we waited for it, it will have
+	 * requeued the work. Now the work will be running again
+	 * but will not rearm the timer again because it checks
+	 * whether we are connected to the network or not -- at this
+	 * point we shouldn't be anymore.
+	 */
+
+	return 0;
+}
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index b04ca4049c9..bc63aa0c540 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1032,6 +1032,7 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx)
 		      ieee80211_is_pspoll(hdr->frame_control)) &&
 		     rx->sdata->vif.type != NL80211_IFTYPE_ADHOC &&
 		     rx->sdata->vif.type != NL80211_IFTYPE_WDS &&
+		     rx->sdata->vif.type != NL80211_IFTYPE_OCB &&
 		     (!rx->sta || !test_sta_flag(rx->sta, WLAN_STA_ASSOC)))) {
 		/*
 		 * accept port control frames from the AP even when it's not
@@ -1272,6 +1273,12 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 				sta->last_rx_rate_vht_nss = status->vht_nss;
 			}
 		}
+	} else if (rx->sdata->vif.type == NL80211_IFTYPE_OCB) {
+		u8 *bssid = ieee80211_get_bssid(hdr, rx->skb->len,
+						NL80211_IFTYPE_OCB);
+		/* OCB uses wild-card BSSID */
+		if (is_broadcast_ether_addr(bssid))
+			sta->last_rx = jiffies;
 	} else if (!is_multicast_ether_addr(hdr->addr1)) {
 		/*
 		 * Mesh beacons will update last_rx when if they are found to
@@ -2820,6 +2827,7 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx)
 
 	if (!ieee80211_vif_is_mesh(&sdata->vif) &&
 	    sdata->vif.type != NL80211_IFTYPE_ADHOC &&
+	    sdata->vif.type != NL80211_IFTYPE_OCB &&
 	    sdata->vif.type != NL80211_IFTYPE_STATION)
 		return RX_DROP_MONITOR;
 
@@ -3130,6 +3138,33 @@ static bool prepare_for_handlers(struct ieee80211_rx_data *rx,
 						 BIT(rate_idx));
 		}
 		break;
+	case NL80211_IFTYPE_OCB:
+		if (!bssid)
+			return false;
+		if (ieee80211_is_beacon(hdr->frame_control)) {
+			return false;
+		} else if (!is_broadcast_ether_addr(bssid)) {
+			ocb_dbg(sdata, "BSSID mismatch in OCB mode!\n");
+			return false;
+		} else if (!multicast &&
+			   !ether_addr_equal(sdata->dev->dev_addr,
+					     hdr->addr1)) {
+			/* if we are in promisc mode we also accept
+			 * packets not destined for us
+			 */
+			if (!(sdata->dev->flags & IFF_PROMISC))
+				return false;
+			rx->flags &= ~IEEE80211_RX_RA_MATCH;
+		} else if (!rx->sta) {
+			int rate_idx;
+			if (status->flag & RX_FLAG_HT)
+				rate_idx = 0; /* TODO: HT rates */
+			else
+				rate_idx = status->rate_idx;
+			ieee80211_ocb_rx_no_sta(sdata, bssid, hdr->addr2,
+						BIT(rate_idx));
+		}
+		break;
 	case NL80211_IFTYPE_MESH_POINT:
 		if (!multicast &&
 		    !ether_addr_equal(sdata->vif.addr, hdr->addr1)) {
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 900632a250e..3ffd91f295a 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -296,6 +296,9 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx)
 		 */
 		return TX_DROP;
 
+	if (tx->sdata->vif.type == NL80211_IFTYPE_OCB)
+		return TX_CONTINUE;
+
 	if (tx->sdata->vif.type == NL80211_IFTYPE_WDS)
 		return TX_CONTINUE;
 
@@ -2013,6 +2016,17 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 			goto fail_rcu;
 		band = chanctx_conf->def.chan->band;
 		break;
+	case NL80211_IFTYPE_OCB:
+		/* DA SA BSSID */
+		memcpy(hdr.addr1, skb->data, ETH_ALEN);
+		memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN);
+		eth_broadcast_addr(hdr.addr3);
+		hdrlen = 24;
+		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
+		if (!chanctx_conf)
+			goto fail_rcu;
+		band = chanctx_conf->def.chan->band;
+		break;
 	case NL80211_IFTYPE_ADHOC:
 		/* DA SA BSSID */
 		memcpy(hdr.addr1, skb->data, ETH_ALEN);
@@ -2057,6 +2071,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 	 * EAPOL frames from the local station.
 	 */
 	if (unlikely(!ieee80211_vif_is_mesh(&sdata->vif) &&
+		     (sdata->vif.type != NL80211_IFTYPE_OCB) &&
 		     !multicast && !authorized &&
 		     (cpu_to_be16(ethertype) != sdata->control_port_protocol ||
 		      !ether_addr_equal(sdata->vif.addr, skb->data + ETH_ALEN)))) {
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index d7d69c89ff3..91e16b4d4e3 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1101,6 +1101,7 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_chanctx_conf *chanctx_conf;
 	int ac;
 	bool use_11b, enable_qos;
+	bool is_ocb; /* Use another EDCA parameters if dot11OCBActivated=true */
 	int aCWmin, aCWmax;
 
 	if (!local->ops->conf_tx)
@@ -1125,6 +1126,8 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata,
 	 */
 	enable_qos = (sdata->vif.type != NL80211_IFTYPE_STATION);
 
+	is_ocb = (sdata->vif.type == NL80211_IFTYPE_OCB);
+
 	/* Set defaults according to 802.11-2007 Table 7-37 */
 	aCWmax = 1023;
 	if (use_11b)
@@ -1146,7 +1149,10 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata,
 				qparam.cw_max = aCWmax;
 				qparam.cw_min = aCWmin;
 				qparam.txop = 0;
-				qparam.aifs = 7;
+				if (is_ocb)
+					qparam.aifs = 9;
+				else
+					qparam.aifs = 7;
 				break;
 			/* never happens but let's not leave undefined */
 			default:
@@ -1154,21 +1160,32 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata,
 				qparam.cw_max = aCWmax;
 				qparam.cw_min = aCWmin;
 				qparam.txop = 0;
-				qparam.aifs = 3;
+				if (is_ocb)
+					qparam.aifs = 6;
+				else
+					qparam.aifs = 3;
 				break;
 			case IEEE80211_AC_VI:
 				qparam.cw_max = aCWmin;
 				qparam.cw_min = (aCWmin + 1) / 2 - 1;
-				if (use_11b)
+				if (is_ocb)
+					qparam.txop = 0;
+				else if (use_11b)
 					qparam.txop = 6016/32;
 				else
 					qparam.txop = 3008/32;
-				qparam.aifs = 2;
+
+				if (is_ocb)
+					qparam.aifs = 3;
+				else
+					qparam.aifs = 2;
 				break;
 			case IEEE80211_AC_VO:
 				qparam.cw_max = (aCWmin + 1) / 2 - 1;
 				qparam.cw_min = (aCWmin + 1) / 4 - 1;
-				if (use_11b)
+				if (is_ocb)
+					qparam.txop = 0;
+				else if (use_11b)
 					qparam.txop = 3264/32;
 				else
 					qparam.txop = 1504/32;
@@ -1842,7 +1859,8 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 			sdata_unlock(sdata);
 			break;
 		case NL80211_IFTYPE_OCB:
-			/* to be implemented in the future */
+			changed |= BSS_CHANGED_OCB;
+			ieee80211_bss_info_change_notify(sdata, changed);
 			break;
 		case NL80211_IFTYPE_ADHOC:
 			changed |= BSS_CHANGED_IBSS;
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index d3c5672d775..fdf52db95b3 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -148,6 +148,10 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 	case NL80211_IFTYPE_ADHOC:
 		ra = skb->data;
 		break;
+	case NL80211_IFTYPE_OCB:
+		/* all stations are required to support WME */
+		qos = true;
+		break;
 	default:
 		break;
 	}
-- 
cgit v1.2.3-70-g09d2


From cf2c92d840c1424bcb3bb501147c79c9b067ad77 Mon Sep 17 00:00:00 2001
From: Eliad Peller <eliad@wizery.com>
Date: Tue, 4 Nov 2014 11:43:54 +0200
Subject: mac80211: replace restart_complete() with reconfig_complete()

Drivers might want to know also when mac80211 has
completed reconfiguring after resume (e.g. in order
to know when frames can be passed to mac80211).

Rename restart_complete() to a more-generic reconfig_complete(),
and add a new enum to indicate the reconfiguration type.

Update the current users with the new prototype.

Signed-off-by: Eliad Peller <eliadx.peller@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath10k/core.h      |  2 +-
 drivers/net/wireless/ath/ath10k/mac.c       |  8 ++++++--
 drivers/net/wireless/iwlwifi/mvm/mac80211.c | 20 +++++++++++++++++---
 include/net/mac80211.h                      | 29 +++++++++++++++++++++++------
 net/mac80211/driver-ops.h                   | 10 ++++++----
 net/mac80211/trace.h                        | 23 ++++++++++++++++++++---
 net/mac80211/util.c                         |  5 ++++-
 7 files changed, 77 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index fe531ea6926..cc8f1fc6504 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -321,7 +321,7 @@ enum ath10k_state {
 	 * stopped in ath10k_core_restart() work holding conf_mutex. The state
 	 * RESTARTED means that the device is up and mac80211 has started hw
 	 * reconfiguration. Once mac80211 is done with the reconfiguration we
-	 * set the state to STATE_ON in restart_complete(). */
+	 * set the state to STATE_ON in reconfig_complete(). */
 	ATH10K_STATE_RESTARTING,
 	ATH10K_STATE_RESTARTED,
 
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 46709301a51..f57459a2f51 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -3929,10 +3929,14 @@ exit:
 }
 #endif
 
-static void ath10k_restart_complete(struct ieee80211_hw *hw)
+static void ath10k_reconfig_complete(struct ieee80211_hw *hw,
+				     enum ieee80211_reconfig_type reconfig_type)
 {
 	struct ath10k *ar = hw->priv;
 
+	if (reconfig_type != IEEE80211_RECONFIG_TYPE_RESTART)
+		return;
+
 	mutex_lock(&ar->conf_mutex);
 
 	/* If device failed to restart it will be in a different state, e.g.
@@ -4450,7 +4454,7 @@ static const struct ieee80211_ops ath10k_ops = {
 	.tx_last_beacon			= ath10k_tx_last_beacon,
 	.set_antenna			= ath10k_set_antenna,
 	.get_antenna			= ath10k_get_antenna,
-	.restart_complete		= ath10k_restart_complete,
+	.reconfig_complete		= ath10k_reconfig_complete,
 	.get_survey			= ath10k_get_survey,
 	.set_bitrate_mask		= ath10k_set_bitrate_mask,
 	.sta_rc_update			= ath10k_sta_rc_update,
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index c7a73c68bda..e16c29dc9d4 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -857,9 +857,8 @@ static int iwl_mvm_mac_start(struct ieee80211_hw *hw)
 	return ret;
 }
 
-static void iwl_mvm_mac_restart_complete(struct ieee80211_hw *hw)
+static void iwl_mvm_restart_complete(struct iwl_mvm *mvm)
 {
-	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	int ret;
 
 	mutex_lock(&mvm->mutex);
@@ -877,6 +876,21 @@ static void iwl_mvm_mac_restart_complete(struct ieee80211_hw *hw)
 	mutex_unlock(&mvm->mutex);
 }
 
+static void
+iwl_mvm_mac_reconfig_complete(struct ieee80211_hw *hw,
+			      enum ieee80211_reconfig_type reconfig_type)
+{
+	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
+
+	switch (reconfig_type) {
+	case IEEE80211_RECONFIG_TYPE_RESTART:
+		iwl_mvm_restart_complete(mvm);
+		break;
+	case IEEE80211_RECONFIG_TYPE_SUSPEND:
+		break;
+	}
+}
+
 void __iwl_mvm_mac_stop(struct iwl_mvm *mvm)
 {
 	lockdep_assert_held(&mvm->mutex);
@@ -3014,7 +3028,7 @@ const struct ieee80211_ops iwl_mvm_hw_ops = {
 	.tx = iwl_mvm_mac_tx,
 	.ampdu_action = iwl_mvm_mac_ampdu_action,
 	.start = iwl_mvm_mac_start,
-	.restart_complete = iwl_mvm_mac_restart_complete,
+	.reconfig_complete = iwl_mvm_mac_reconfig_complete,
 	.stop = iwl_mvm_mac_stop,
 	.add_interface = iwl_mvm_mac_add_interface,
 	.remove_interface = iwl_mvm_mac_remove_interface,
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index db54635d65c..5f203a6a5e7 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2388,6 +2388,22 @@ enum ieee80211_roc_type {
 	IEEE80211_ROC_TYPE_MGMT_TX,
 };
 
+/**
+ * enum ieee80211_reconfig_complete_type - reconfig type
+ *
+ * This enum is used by the reconfig_complete() callback to indicate what
+ * reconfiguration type was completed.
+ *
+ * @IEEE80211_RECONFIG_TYPE_RESTART: hw restart type
+ *	(also due to resume() callback returning 1)
+ * @IEEE80211_RECONFIG_TYPE_SUSPEND: suspend type (regardless
+ *	of wowlan configuration)
+ */
+enum ieee80211_reconfig_type {
+	IEEE80211_RECONFIG_TYPE_RESTART,
+	IEEE80211_RECONFIG_TYPE_SUSPEND,
+};
+
 /**
  * struct ieee80211_ops - callbacks from mac80211 to the driver
  *
@@ -2823,11 +2839,11 @@ enum ieee80211_roc_type {
  *	disabled/enabled via @bss_info_changed.
  * @stop_ap: Stop operation on the AP interface.
  *
- * @restart_complete: Called after a call to ieee80211_restart_hw(), when the
- *	reconfiguration has completed. This can help the driver implement the
- *	reconfiguration step. Also called when reconfiguring because the
- *	driver's resume function returned 1, as this is just like an "inline"
- *	hardware restart. This callback may sleep.
+ * @reconfig_complete: Called after a call to ieee80211_restart_hw() and
+ *	during resume, when the reconfiguration has completed.
+ *	This can help the driver implement the reconfiguration step (and
+ *	indicate mac80211 is ready to receive frames).
+ *	This callback may sleep.
  *
  * @ipv6_addr_change: IPv6 address assignment on the given interface changed.
  *	Currently, this is only called for managed or P2P client interfaces.
@@ -3050,7 +3066,8 @@ struct ieee80211_ops {
 				  int n_vifs,
 				  enum ieee80211_chanctx_switch_mode mode);
 
-	void (*restart_complete)(struct ieee80211_hw *hw);
+	void (*reconfig_complete)(struct ieee80211_hw *hw,
+				  enum ieee80211_reconfig_type reconfig_type);
 
 #if IS_ENABLED(CONFIG_IPV6)
 	void (*ipv6_addr_change)(struct ieee80211_hw *hw,
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 8e1889ff2e5..9759dd1f073 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1152,13 +1152,15 @@ static inline void drv_stop_ap(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
-static inline void drv_restart_complete(struct ieee80211_local *local)
+static inline void
+drv_reconfig_complete(struct ieee80211_local *local,
+		      enum ieee80211_reconfig_type reconfig_type)
 {
 	might_sleep();
 
-	trace_drv_restart_complete(local);
-	if (local->ops->restart_complete)
-		local->ops->restart_complete(&local->hw);
+	trace_drv_reconfig_complete(local, reconfig_type);
+	if (local->ops->reconfig_complete)
+		local->ops->reconfig_complete(&local->hw, reconfig_type);
 	trace_drv_return_void(local);
 }
 
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index aeeace5ba47..809a4983eb4 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -1562,9 +1562,26 @@ DEFINE_EVENT(local_sdata_evt, drv_stop_ap,
 	TP_ARGS(local, sdata)
 );
 
-DEFINE_EVENT(local_only_evt, drv_restart_complete,
-	TP_PROTO(struct ieee80211_local *local),
-	TP_ARGS(local)
+TRACE_EVENT(drv_reconfig_complete,
+	TP_PROTO(struct ieee80211_local *local,
+		 enum ieee80211_reconfig_type reconfig_type),
+	TP_ARGS(local, reconfig_type),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		__field(u8, reconfig_type)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		__entry->reconfig_type = reconfig_type;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT  " reconfig_type:%d",
+		LOCAL_PR_ARG, __entry->reconfig_type
+	)
+
 );
 
 #if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 5f7b0e935b6..f9319a5dca6 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1998,7 +1998,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	 * We may want to change that later, however.
 	 */
 	if (!local->suspended || reconfig_due_to_wowlan)
-		drv_restart_complete(local);
+		drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_RESTART);
 
 	if (!local->suspended)
 		return 0;
@@ -2009,6 +2009,9 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	mb();
 	local->resuming = false;
 
+	if (!reconfig_due_to_wowlan)
+		drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_SUSPEND);
+
 	list_for_each_entry(sdata, &local->interfaces, list) {
 		if (!ieee80211_sdata_running(sdata))
 			continue;
-- 
cgit v1.2.3-70-g09d2


From 2b30d411dbc6eddfb5b4f9afd5a2c57b6f4dd96c Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 4 Nov 2014 14:02:40 +0100
Subject: ALSA: pcm: Add xrun_injection proc entry

This patch adds a new proc entry for PCM substreams to inject an
XRUN.  When a PCM substream is running and any value is written to its
xrun_injection proc file, the driver triggers XRUN.  This is a useful
feature for debugging XRUN and error handling code paths.

Note that this entry is enabled only when CONFIG_SND_PCM_XRUN_DEBUG is
set.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/alsa/Procfile.txt |  4 ++++
 include/sound/pcm.h                   |  3 +++
 sound/core/pcm.c                      | 33 +++++++++++++++++++++++++++++++++
 3 files changed, 40 insertions(+)

(limited to 'include')

diff --git a/Documentation/sound/alsa/Procfile.txt b/Documentation/sound/alsa/Procfile.txt
index cfc49567b9d..7f8a0d32590 100644
--- a/Documentation/sound/alsa/Procfile.txt
+++ b/Documentation/sound/alsa/Procfile.txt
@@ -133,6 +133,10 @@ card*/pcm*/sub*/sw_params
 card*/pcm*/sub*/prealloc
 	The buffer pre-allocation information.
 
+card*/pcm*/sub*/xrun_injection
+	Triggers an XRUN to the running stream when any value is
+	written to this proc file.  Used for fault injection.
+	This entry is write-only.
 
 AC97 Codec Information
 ----------------------
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 29eb09ef296..0b8daeed0a3 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -416,7 +416,10 @@ struct snd_pcm_substream {
 	struct snd_info_entry *proc_status_entry;
 	struct snd_info_entry *proc_prealloc_entry;
 	struct snd_info_entry *proc_prealloc_max_entry;
+#ifdef CONFIG_SND_PCM_XRUN_DEBUG
+	struct snd_info_entry *proc_xrun_injection_entry;
 #endif
+#endif /* CONFIG_SND_VERBOSE_PROCFS */
 	/* misc flags */
 	unsigned int hw_opened: 1;
 };
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 31acc3df62c..8f624b7af0c 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -483,6 +483,19 @@ static void snd_pcm_substream_proc_status_read(struct snd_info_entry *entry,
 }
 
 #ifdef CONFIG_SND_PCM_XRUN_DEBUG
+static void snd_pcm_xrun_injection_write(struct snd_info_entry *entry,
+					 struct snd_info_buffer *buffer)
+{
+	struct snd_pcm_substream *substream = entry->private_data;
+	struct snd_pcm_runtime *runtime;
+
+	snd_pcm_stream_lock_irq(substream);
+	runtime = substream->runtime;
+	if (runtime && runtime->status->state == SNDRV_PCM_STATE_RUNNING)
+		snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
+	snd_pcm_stream_unlock_irq(substream);
+}
+
 static void snd_pcm_xrun_debug_read(struct snd_info_entry *entry,
 				    struct snd_info_buffer *buffer)
 {
@@ -614,6 +627,22 @@ static int snd_pcm_substream_proc_init(struct snd_pcm_substream *substream)
 	}
 	substream->proc_status_entry = entry;
 
+#ifdef CONFIG_SND_PCM_XRUN_DEBUG
+	entry = snd_info_create_card_entry(card, "xrun_injection",
+					   substream->proc_root);
+	if (entry) {
+		entry->private_data = substream;
+		entry->c.text.read = NULL;
+		entry->c.text.write = snd_pcm_xrun_injection_write;
+		entry->mode = S_IFREG | S_IWUSR;
+		if (snd_info_register(entry) < 0) {
+			snd_info_free_entry(entry);
+			entry = NULL;
+		}
+	}
+	substream->proc_xrun_injection_entry = entry;
+#endif /* CONFIG_SND_PCM_XRUN_DEBUG */
+
 	return 0;
 }
 
@@ -627,6 +656,10 @@ static int snd_pcm_substream_proc_done(struct snd_pcm_substream *substream)
 	substream->proc_sw_params_entry = NULL;
 	snd_info_free_entry(substream->proc_status_entry);
 	substream->proc_status_entry = NULL;
+#ifdef CONFIG_SND_PCM_XRUN_DEBUG
+	snd_info_free_entry(substream->proc_xrun_injection_entry);
+	substream->proc_xrun_injection_entry = NULL;
+#endif
 	snd_info_free_entry(substream->proc_root);
 	substream->proc_root = NULL;
 	return 0;
-- 
cgit v1.2.3-70-g09d2


From e7a00e4210e4cc980e3ba67ec7301af54061d14b Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sre@kernel.org>
Date: Sun, 6 Apr 2014 12:52:11 +0200
Subject: of: introduce of_property_read_s32

Introduce signed 32bit integer of_property_read method.

Signed-off-by: Sebastian Reichel <sre@kernel.org>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 include/linux/of.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/of.h b/include/linux/of.h
index 29f0adc5f3e..30912939a61 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -760,6 +760,13 @@ static inline int of_property_read_u32(const struct device_node *np,
 	return of_property_read_u32_array(np, propname, out_value, 1);
 }
 
+static inline int of_property_read_s32(const struct device_node *np,
+				       const char *propname,
+				       s32 *out_value)
+{
+	return of_property_read_u32(np, propname, (u32*) out_value);
+}
+
 #define of_property_for_each_u32(np, propname, prop, p, u)	\
 	for (prop = of_find_property(np, propname, NULL),	\
 		p = of_prop_next_u32(prop, NULL, &u);		\
-- 
cgit v1.2.3-70-g09d2


From 5063e25a302e6a83f6590d9a06bd5f6400b17430 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@linaro.org>
Date: Fri, 3 Oct 2014 16:28:27 +0100
Subject: of: Eliminate of_allnodes list

The device tree structure is composed of two lists; the 'allnodes' list
which is a singly linked list containing every node in the tree, and the
child->parent structure where each parent node has a singly linked list
of children. All of the data in the allnodes list can be easily
reproduced with the parent-child lists, so of_allnodes is actually
unnecessary. Remove it entirely which saves a bit of memory and
simplifies the data structure quite a lot.

Signed-off-by: Grant Likely <grant.likely@linaro.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Gaurav Minocha <gaurav.minocha.os@gmail.com>
Cc: Pantelis Antoniou <pantelis@pantelis.antoniou@konsulko.com>
---
 Documentation/devicetree/of_selftest.txt | 20 ++-------
 Documentation/devicetree/todo.txt        |  1 -
 drivers/mfd/vexpress-sysreg.c            |  2 +-
 drivers/of/base.c                        | 53 ++++++++++++++----------
 drivers/of/dynamic.c                     | 13 ------
 drivers/of/fdt.c                         | 30 +++++++-------
 drivers/of/pdt.c                         | 27 ++++--------
 drivers/of/selftest.c                    | 71 +++++++++++++++-----------------
 include/linux/of.h                       | 11 ++---
 include/linux/of_pdt.h                   |  3 +-
 10 files changed, 98 insertions(+), 133 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/of_selftest.txt b/Documentation/devicetree/of_selftest.txt
index 1e3d5c92b5e..57a808b588b 100644
--- a/Documentation/devicetree/of_selftest.txt
+++ b/Documentation/devicetree/of_selftest.txt
@@ -63,7 +63,6 @@ struct device_node {
     struct  device_node *parent;
     struct  device_node *child;
     struct  device_node *sibling;
-    struct  device_node *allnext;   /* next in list of all nodes */
     ...
  };
 
@@ -99,12 +98,6 @@ child11 -> sibling12 -> sibling13 -> sibling14 -> null
 Figure 1: Generic structure of un-flattened device tree
 
 
-*allnext: it is used to link all the nodes of DT into a list. So, for the
- above tree the list would be as follows:
-
-root->child1->child11->sibling12->sibling13->child131->sibling14->sibling2->
-child21->sibling22->sibling23->sibling3->child31->sibling32->sibling4->null
-
 Before executing OF selftest, it is required to attach the test data to
 machine's device tree (if present). So, when selftest_data_add() is called,
 at first it reads the flattened device tree data linked into the kernel image
@@ -131,11 +124,6 @@ root ('/')
  test-child01      null             null             null
 
 
-allnext list:
-
-root->testcase-data->test-child0->test-child01->test-sibling1->test-sibling2
-->test-sibling3->null
-
 Figure 2: Example test data tree to be attached to live tree.
 
 According to the scenario above, the live tree is already present so it isn't
@@ -204,8 +192,6 @@ detached and then moving up the parent nodes are removed, and eventually the
 whole tree). selftest_data_remove() calls detach_node_and_children() that uses
 of_detach_node() to detach the nodes from the live device tree.
 
-To detach a node, of_detach_node() first updates all_next linked list, by
-attaching the previous node's allnext to current node's allnext pointer. And
-then, it either updates the child pointer of given node's parent to its
-sibling or attaches the previous sibling to the given node's sibling, as
-appropriate. That is it :)
+To detach a node, of_detach_node() either updates the child pointer of given
+node's parent to its sibling or attaches the previous sibling to the given
+node's sibling, as appropriate. That is it :)
diff --git a/Documentation/devicetree/todo.txt b/Documentation/devicetree/todo.txt
index c3cf0659bd1..b5139d1de81 100644
--- a/Documentation/devicetree/todo.txt
+++ b/Documentation/devicetree/todo.txt
@@ -2,7 +2,6 @@ Todo list for devicetree:
 
 === General structure ===
 - Switch from custom lists to (h)list_head for nodes and properties structure
-- Remove of_allnodes list and iterate using list of child nodes alone
 
 === CONFIG_OF_DYNAMIC ===
 - Switch to RCU for tree updates and get rid of global spinlock
diff --git a/drivers/mfd/vexpress-sysreg.c b/drivers/mfd/vexpress-sysreg.c
index 9e21e4fc959..8f43ab8fd2d 100644
--- a/drivers/mfd/vexpress-sysreg.c
+++ b/drivers/mfd/vexpress-sysreg.c
@@ -223,7 +223,7 @@ static int vexpress_sysreg_probe(struct platform_device *pdev)
 	vexpress_config_set_master(vexpress_sysreg_get_master());
 
 	/* Confirm board type against DT property, if available */
-	if (of_property_read_u32(of_allnodes, "arm,hbi", &dt_hbi) == 0) {
+	if (of_property_read_u32(of_root, "arm,hbi", &dt_hbi) == 0) {
 		u32 id = vexpress_get_procid(VEXPRESS_SITE_MASTER);
 		u32 hbi = (id >> SYS_PROCIDx_HBI_SHIFT) & SYS_HBI_MASK;
 
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 3823edf2d01..1f61a908a76 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -32,8 +32,8 @@
 
 LIST_HEAD(aliases_lookup);
 
-struct device_node *of_allnodes;
-EXPORT_SYMBOL(of_allnodes);
+struct device_node *of_root;
+EXPORT_SYMBOL(of_root);
 struct device_node *of_chosen;
 struct device_node *of_aliases;
 struct device_node *of_stdout;
@@ -48,7 +48,7 @@ struct kset *of_kset;
  */
 DEFINE_MUTEX(of_mutex);
 
-/* use when traversing tree through the allnext, child, sibling,
+/* use when traversing tree through the child, sibling,
  * or parent members of struct device_node.
  */
 DEFINE_RAW_SPINLOCK(devtree_lock);
@@ -204,7 +204,7 @@ static int __init of_init(void)
 	mutex_unlock(&of_mutex);
 
 	/* Symlink in /proc as required by userspace ABI */
-	if (of_allnodes)
+	if (of_root)
 		proc_symlink("device-tree", NULL, "/sys/firmware/devicetree/base");
 
 	return 0;
@@ -245,6 +245,23 @@ struct property *of_find_property(const struct device_node *np,
 }
 EXPORT_SYMBOL(of_find_property);
 
+struct device_node *__of_find_all_nodes(struct device_node *prev)
+{
+	struct device_node *np;
+	if (!prev) {
+		np = of_root;
+	} else if (prev->child) {
+		np = prev->child;
+	} else {
+		/* Walk back up looking for a sibling, or the end of the structure */
+		np = prev;
+		while (np->parent && !np->sibling)
+			np = np->parent;
+		np = np->sibling; /* Might be null at the end of the tree */
+	}
+	return np;
+}
+
 /**
  * of_find_all_nodes - Get next node in global list
  * @prev:	Previous node or NULL to start iteration
@@ -259,10 +276,8 @@ struct device_node *of_find_all_nodes(struct device_node *prev)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&devtree_lock, flags);
-	np = prev ? prev->allnext : of_allnodes;
-	for (; np != NULL; np = np->allnext)
-		if (of_node_get(np))
-			break;
+	np = __of_find_all_nodes(prev);
+	of_node_get(np);
 	of_node_put(prev);
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	return np;
@@ -736,7 +751,7 @@ struct device_node *of_find_node_by_path(const char *path)
 	unsigned long flags;
 
 	if (strcmp(path, "/") == 0)
-		return of_node_get(of_allnodes);
+		return of_node_get(of_root);
 
 	/* The path could begin with an alias */
 	if (*path != '/') {
@@ -761,7 +776,7 @@ struct device_node *of_find_node_by_path(const char *path)
 	/* Step down the tree matching path components */
 	raw_spin_lock_irqsave(&devtree_lock, flags);
 	if (!np)
-		np = of_node_get(of_allnodes);
+		np = of_node_get(of_root);
 	while (np && *path == '/') {
 		path++; /* Increment past '/' delimiter */
 		np = __of_find_node_by_path(np, path);
@@ -790,8 +805,7 @@ struct device_node *of_find_node_by_name(struct device_node *from,
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&devtree_lock, flags);
-	np = from ? from->allnext : of_allnodes;
-	for (; np; np = np->allnext)
+	for_each_of_allnodes_from(from, np)
 		if (np->name && (of_node_cmp(np->name, name) == 0)
 		    && of_node_get(np))
 			break;
@@ -820,8 +834,7 @@ struct device_node *of_find_node_by_type(struct device_node *from,
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&devtree_lock, flags);
-	np = from ? from->allnext : of_allnodes;
-	for (; np; np = np->allnext)
+	for_each_of_allnodes_from(from, np)
 		if (np->type && (of_node_cmp(np->type, type) == 0)
 		    && of_node_get(np))
 			break;
@@ -852,12 +865,10 @@ struct device_node *of_find_compatible_node(struct device_node *from,
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&devtree_lock, flags);
-	np = from ? from->allnext : of_allnodes;
-	for (; np; np = np->allnext) {
+	for_each_of_allnodes_from(from, np)
 		if (__of_device_is_compatible(np, compatible, type, NULL) &&
 		    of_node_get(np))
 			break;
-	}
 	of_node_put(from);
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	return np;
@@ -884,8 +895,7 @@ struct device_node *of_find_node_with_property(struct device_node *from,
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&devtree_lock, flags);
-	np = from ? from->allnext : of_allnodes;
-	for (; np; np = np->allnext) {
+	for_each_of_allnodes_from(from, np) {
 		for (pp = np->properties; pp; pp = pp->next) {
 			if (of_prop_cmp(pp->name, prop_name) == 0) {
 				of_node_get(np);
@@ -967,8 +977,7 @@ struct device_node *of_find_matching_node_and_match(struct device_node *from,
 		*match = NULL;
 
 	raw_spin_lock_irqsave(&devtree_lock, flags);
-	np = from ? from->allnext : of_allnodes;
-	for (; np; np = np->allnext) {
+	for_each_of_allnodes_from(from, np) {
 		m = __of_match_node(matches, np);
 		if (m && of_node_get(np)) {
 			if (match)
@@ -1025,7 +1034,7 @@ struct device_node *of_find_node_by_phandle(phandle handle)
 		return NULL;
 
 	raw_spin_lock_irqsave(&devtree_lock, flags);
-	for (np = of_allnodes; np; np = np->allnext)
+	for_each_of_allnodes(np)
 		if (np->phandle == handle)
 			break;
 	of_node_get(np);
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index f297891d852..da2509d639c 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -117,8 +117,6 @@ void __of_attach_node(struct device_node *np)
 
 	np->child = NULL;
 	np->sibling = np->parent->child;
-	np->allnext = np->parent->allnext;
-	np->parent->allnext = np;
 	np->parent->child = np;
 	of_node_clear_flag(np, OF_DETACHED);
 }
@@ -154,17 +152,6 @@ void __of_detach_node(struct device_node *np)
 	if (WARN_ON(!parent))
 		return;
 
-	if (of_allnodes == np)
-		of_allnodes = np->allnext;
-	else {
-		struct device_node *prev;
-		for (prev = of_allnodes;
-		     prev->allnext != np;
-		     prev = prev->allnext)
-			;
-		prev->allnext = np->allnext;
-	}
-
 	if (parent->child == np)
 		parent->child = np->sibling;
 	else {
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index d1ffca8b34e..1d30b9f9646 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -145,15 +145,15 @@ static void *unflatten_dt_alloc(void **mem, unsigned long size,
  * @mem: Memory chunk to use for allocating device nodes and properties
  * @p: pointer to node in flat tree
  * @dad: Parent struct device_node
- * @allnextpp: pointer to ->allnext from last allocated device_node
  * @fpsize: Size of the node path up at the current depth.
  */
 static void * unflatten_dt_node(void *blob,
 				void *mem,
 				int *poffset,
 				struct device_node *dad,
-				struct device_node ***allnextpp,
-				unsigned long fpsize)
+				struct device_node **nodepp,
+				unsigned long fpsize,
+				bool dryrun)
 {
 	const __be32 *p;
 	struct device_node *np;
@@ -200,7 +200,7 @@ static void * unflatten_dt_node(void *blob,
 
 	np = unflatten_dt_alloc(&mem, sizeof(struct device_node) + allocl,
 				__alignof__(struct device_node));
-	if (allnextpp) {
+	if (!dryrun) {
 		char *fn;
 		of_node_init(np);
 		np->full_name = fn = ((char *)np) + sizeof(*np);
@@ -222,8 +222,6 @@ static void * unflatten_dt_node(void *blob,
 		memcpy(fn, pathp, l);
 
 		prev_pp = &np->properties;
-		**allnextpp = np;
-		*allnextpp = &np->allnext;
 		if (dad != NULL) {
 			np->parent = dad;
 			/* we temporarily use the next field as `last_child'*/
@@ -254,7 +252,7 @@ static void * unflatten_dt_node(void *blob,
 			has_name = 1;
 		pp = unflatten_dt_alloc(&mem, sizeof(struct property),
 					__alignof__(struct property));
-		if (allnextpp) {
+		if (!dryrun) {
 			/* We accept flattened tree phandles either in
 			 * ePAPR-style "phandle" properties, or the
 			 * legacy "linux,phandle" properties.  If both
@@ -296,7 +294,7 @@ static void * unflatten_dt_node(void *blob,
 		sz = (pa - ps) + 1;
 		pp = unflatten_dt_alloc(&mem, sizeof(struct property) + sz,
 					__alignof__(struct property));
-		if (allnextpp) {
+		if (!dryrun) {
 			pp->name = "name";
 			pp->length = sz;
 			pp->value = pp + 1;
@@ -308,7 +306,7 @@ static void * unflatten_dt_node(void *blob,
 				(char *)pp->value);
 		}
 	}
-	if (allnextpp) {
+	if (!dryrun) {
 		*prev_pp = NULL;
 		np->name = of_get_property(np, "name", NULL);
 		np->type = of_get_property(np, "device_type", NULL);
@@ -324,11 +322,13 @@ static void * unflatten_dt_node(void *blob,
 	if (depth < 0)
 		depth = 0;
 	while (*poffset > 0 && depth > old_depth)
-		mem = unflatten_dt_node(blob, mem, poffset, np, allnextpp,
-					fpsize);
+		mem = unflatten_dt_node(blob, mem, poffset, np, NULL,
+					fpsize, dryrun);
 
 	if (*poffset < 0 && *poffset != -FDT_ERR_NOTFOUND)
 		pr_err("unflatten: error %d processing FDT\n", *poffset);
+	if (nodepp)
+		*nodepp = np;
 
 	return mem;
 }
@@ -352,7 +352,6 @@ static void __unflatten_device_tree(void *blob,
 	unsigned long size;
 	int start;
 	void *mem;
-	struct device_node **allnextp = mynodes;
 
 	pr_debug(" -> unflatten_device_tree()\n");
 
@@ -373,7 +372,7 @@ static void __unflatten_device_tree(void *blob,
 
 	/* First pass, scan for size */
 	start = 0;
-	size = (unsigned long)unflatten_dt_node(blob, NULL, &start, NULL, NULL, 0);
+	size = (unsigned long)unflatten_dt_node(blob, NULL, &start, NULL, NULL, 0, true);
 	size = ALIGN(size, 4);
 
 	pr_debug("  size is %lx, allocating...\n", size);
@@ -388,11 +387,10 @@ static void __unflatten_device_tree(void *blob,
 
 	/* Second pass, do actual unflattening */
 	start = 0;
-	unflatten_dt_node(blob, mem, &start, NULL, &allnextp, 0);
+	unflatten_dt_node(blob, mem, &start, NULL, mynodes, 0, false);
 	if (be32_to_cpup(mem + size) != 0xdeadbeef)
 		pr_warning("End of tree marker overwritten: %08x\n",
 			   be32_to_cpup(mem + size));
-	*allnextp = NULL;
 
 	pr_debug(" <- unflatten_device_tree()\n");
 }
@@ -1041,7 +1039,7 @@ bool __init early_init_dt_scan(void *params)
  */
 void __init unflatten_device_tree(void)
 {
-	__unflatten_device_tree(initial_boot_params, &of_allnodes,
+	__unflatten_device_tree(initial_boot_params, &of_root,
 				early_init_dt_alloc_memory_arch);
 
 	/* Get pointer to "/chosen" and "/aliases" nodes for use everywhere */
diff --git a/drivers/of/pdt.c b/drivers/of/pdt.c
index 36b4035881b..d2acae825af 100644
--- a/drivers/of/pdt.c
+++ b/drivers/of/pdt.c
@@ -25,8 +25,7 @@
 
 static struct of_pdt_ops *of_pdt_prom_ops __initdata;
 
-void __initdata (*of_pdt_build_more)(struct device_node *dp,
-		struct device_node ***nextp);
+void __initdata (*of_pdt_build_more)(struct device_node *dp);
 
 #if defined(CONFIG_SPARC)
 unsigned int of_pdt_unique_id __initdata;
@@ -192,8 +191,7 @@ static struct device_node * __init of_pdt_create_node(phandle node,
 }
 
 static struct device_node * __init of_pdt_build_tree(struct device_node *parent,
-						   phandle node,
-						   struct device_node ***nextp)
+						   phandle node)
 {
 	struct device_node *ret = NULL, *prev_sibling = NULL;
 	struct device_node *dp;
@@ -210,16 +208,12 @@ static struct device_node * __init of_pdt_build_tree(struct device_node *parent,
 			ret = dp;
 		prev_sibling = dp;
 
-		*(*nextp) = dp;
-		*nextp = &dp->allnext;
-
 		dp->full_name = of_pdt_build_full_name(dp);
 
-		dp->child = of_pdt_build_tree(dp,
-				of_pdt_prom_ops->getchild(node), nextp);
+		dp->child = of_pdt_build_tree(dp, of_pdt_prom_ops->getchild(node));
 
 		if (of_pdt_build_more)
-			of_pdt_build_more(dp, nextp);
+			of_pdt_build_more(dp);
 
 		node = of_pdt_prom_ops->getsibling(node);
 	}
@@ -234,20 +228,17 @@ static void * __init kernel_tree_alloc(u64 size, u64 align)
 
 void __init of_pdt_build_devicetree(phandle root_node, struct of_pdt_ops *ops)
 {
-	struct device_node **nextp;
-
 	BUG_ON(!ops);
 	of_pdt_prom_ops = ops;
 
-	of_allnodes = of_pdt_create_node(root_node, NULL);
+	of_root = of_pdt_create_node(root_node, NULL);
 #if defined(CONFIG_SPARC)
-	of_allnodes->path_component_name = "";
+	of_root->path_component_name = "";
 #endif
-	of_allnodes->full_name = "/";
+	of_root->full_name = "/";
 
-	nextp = &of_allnodes->allnext;
-	of_allnodes->child = of_pdt_build_tree(of_allnodes,
-			of_pdt_prom_ops->getchild(of_allnodes->phandle), &nextp);
+	of_root->child = of_pdt_build_tree(of_root,
+				of_pdt_prom_ops->getchild(of_root->phandle));
 
 	/* Get pointer to "/chosen" and "/aliases" nodes for use everywhere */
 	of_alias_scan(kernel_tree_alloc);
diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c
index 11b873c54a7..bf7d99317a9 100644
--- a/drivers/of/selftest.c
+++ b/drivers/of/selftest.c
@@ -148,7 +148,7 @@ static void __init of_selftest_dynamic(void)
 
 static int __init of_selftest_check_node_linkage(struct device_node *np)
 {
-	struct device_node *child, *allnext_index = np;
+	struct device_node *child;
 	int count = 0, rc;
 
 	for_each_child_of_node(np, child) {
@@ -158,14 +158,6 @@ static int __init of_selftest_check_node_linkage(struct device_node *np)
 			return -EINVAL;
 		}
 
-		while (allnext_index && allnext_index != child)
-			allnext_index = allnext_index->allnext;
-		if (allnext_index != child) {
-			pr_err("Node %s is ordered differently in sibling and allnode lists\n",
-				 child->name);
-			return -EINVAL;
-		}
-
 		rc = of_selftest_check_node_linkage(child);
 		if (rc < 0)
 			return rc;
@@ -180,12 +172,12 @@ static void __init of_selftest_check_tree_linkage(void)
 	struct device_node *np;
 	int allnode_count = 0, child_count;
 
-	if (!of_allnodes)
+	if (!of_root)
 		return;
 
 	for_each_of_allnodes(np)
 		allnode_count++;
-	child_count = of_selftest_check_node_linkage(of_allnodes);
+	child_count = of_selftest_check_node_linkage(of_root);
 
 	selftest(child_count > 0, "Device node data structure is corrupted\n");
 	selftest(child_count == allnode_count, "allnodes list size (%i) doesn't match"
@@ -775,33 +767,29 @@ static void update_node_properties(struct device_node *np,
  */
 static int attach_node_and_children(struct device_node *np)
 {
-	struct device_node *next, *root = np, *dup;
+	struct device_node *next, *dup, *child;
 
-	/* skip root node */
-	np = np->child;
-	/* storing a copy in temporary node */
-	dup = np;
+	dup = of_find_node_by_path(np->full_name);
+	if (dup) {
+		update_node_properties(np, dup);
+		return 0;
+	}
 
-	while (dup) {
+	/* Children of the root need to be remembered for removal */
+	if (np->parent == of_root) {
 		if (WARN_ON(last_node_index >= NO_OF_NODES))
 			return -EINVAL;
-		nodes[last_node_index++] = dup;
-		dup = dup->sibling;
+		nodes[last_node_index++] = np;
 	}
-	dup = NULL;
 
-	while (np) {
-		next = np->allnext;
-		dup = of_find_node_by_path(np->full_name);
-		if (dup)
-			update_node_properties(np, dup);
-		else {
-			np->child = NULL;
-			if (np->parent == root)
-				np->parent = of_allnodes;
-			of_attach_node(np);
-		}
-		np = next;
+	child = np->child;
+	np->child = NULL;
+	np->sibling = NULL;
+	of_attach_node(np);
+	while (child) {
+		next = child->sibling;
+		attach_node_and_children(child);
+		child = next;
 	}
 
 	return 0;
@@ -846,10 +834,10 @@ static int __init selftest_data_add(void)
 		return -EINVAL;
 	}
 
-	if (!of_allnodes) {
+	if (!of_root) {
 		/* enabling flag for removing nodes */
 		selftest_live_tree = true;
-		of_allnodes = selftest_data_node;
+		of_root = selftest_data_node;
 
 		for_each_of_allnodes(np)
 			__of_attach_node_sysfs(np);
@@ -859,7 +847,14 @@ static int __init selftest_data_add(void)
 	}
 
 	/* attach the sub-tree to live tree */
-	return attach_node_and_children(selftest_data_node);
+	np = selftest_data_node->child;
+	while (np) {
+		struct device_node *next = np->sibling;
+		np->parent = of_root;
+		attach_node_and_children(np);
+		np = next;
+	}
+	return 0;
 }
 
 /**
@@ -889,10 +884,10 @@ static void selftest_data_remove(void)
 		of_node_put(of_chosen);
 		of_aliases = NULL;
 		of_chosen = NULL;
-		for_each_child_of_node(of_allnodes, np)
+		for_each_child_of_node(of_root, np)
 			detach_node_and_children(np);
-		__of_detach_node_sysfs(of_allnodes);
-		of_allnodes = NULL;
+		__of_detach_node_sysfs(of_root);
+		of_root = NULL;
 		return;
 	}
 
diff --git a/include/linux/of.h b/include/linux/of.h
index 30912939a61..f54da3b699a 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -56,7 +56,6 @@ struct device_node {
 	struct	device_node *child;
 	struct	device_node *sibling;
 	struct	device_node *next;	/* next device of same type */
-	struct	device_node *allnext;	/* next in list of all nodes */
 	struct	kobject kobj;
 	unsigned long _flags;
 	void	*data;
@@ -108,7 +107,7 @@ static inline void of_node_put(struct device_node *node) { }
 #ifdef CONFIG_OF
 
 /* Pointer for first entry in chain of all nodes. */
-extern struct device_node *of_allnodes;
+extern struct device_node *of_root;
 extern struct device_node *of_chosen;
 extern struct device_node *of_aliases;
 extern struct device_node *of_stdout;
@@ -116,7 +115,7 @@ extern raw_spinlock_t devtree_lock;
 
 static inline bool of_have_populated_dt(void)
 {
-	return of_allnodes != NULL;
+	return of_root != NULL;
 }
 
 static inline bool of_node_is_root(const struct device_node *node)
@@ -160,6 +159,7 @@ static inline void of_property_clear_flag(struct property *p, unsigned long flag
 	clear_bit(flag, &p->_flags);
 }
 
+extern struct device_node *__of_find_all_nodes(struct device_node *prev);
 extern struct device_node *of_find_all_nodes(struct device_node *prev);
 
 /*
@@ -215,8 +215,9 @@ static inline const char *of_node_full_name(const struct device_node *np)
 	return np ? np->full_name : "<no-node>";
 }
 
-#define for_each_of_allnodes(dn) \
-	for (dn = of_allnodes; dn; dn = dn->allnext)
+#define for_each_of_allnodes_from(from, dn) \
+	for (dn = __of_find_all_nodes(from); dn; dn = __of_find_all_nodes(dn))
+#define for_each_of_allnodes(dn) for_each_of_allnodes_from(NULL, dn)
 extern struct device_node *of_find_node_by_name(struct device_node *from,
 	const char *name);
 extern struct device_node *of_find_node_by_type(struct device_node *from,
diff --git a/include/linux/of_pdt.h b/include/linux/of_pdt.h
index c65a18a0cfd..7e09244bb67 100644
--- a/include/linux/of_pdt.h
+++ b/include/linux/of_pdt.h
@@ -39,7 +39,6 @@ extern void *prom_early_alloc(unsigned long size);
 /* for building the device tree */
 extern void of_pdt_build_devicetree(phandle root_node, struct of_pdt_ops *ops);
 
-extern void (*of_pdt_build_more)(struct device_node *dp,
-		struct device_node ***nextp);
+extern void (*of_pdt_build_more)(struct device_node *dp);
 
 #endif /* _LINUX_OF_PDT_H */
-- 
cgit v1.2.3-70-g09d2


From 315786ebbf4ad6552b6fd8e0e7b2ea220fcbfdbd Mon Sep 17 00:00:00 2001
From: Olav Haugan <ohaugan@codeaurora.org>
Date: Sat, 25 Oct 2014 09:55:16 -0700
Subject: iommu: Add iommu_map_sg() function

Mapping and unmapping are more often than not in the critical path.
map_sg allows IOMMU driver implementations to optimize the process
of mapping buffers into the IOMMU page tables.

Instead of mapping a buffer one page at a time and requiring potentially
expensive TLB operations for each page, this function allows the driver
to map all pages in one go and defer TLB maintenance until after all
pages have been mapped.

Additionally, the mapping operation would be faster in general since
clients does not have to keep calling map API over and over again for
each physically contiguous chunk of memory that needs to be mapped to a
virtually contiguous region.

Signed-off-by: Olav Haugan <ohaugan@codeaurora.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd_iommu.c      |  1 +
 drivers/iommu/arm-smmu.c       |  1 +
 drivers/iommu/exynos-iommu.c   |  1 +
 drivers/iommu/intel-iommu.c    |  1 +
 drivers/iommu/iommu.c          | 25 +++++++++++++++++++++++++
 drivers/iommu/ipmmu-vmsa.c     |  1 +
 drivers/iommu/msm_iommu.c      |  1 +
 drivers/iommu/omap-iommu.c     |  1 +
 drivers/iommu/shmobile-iommu.c |  1 +
 drivers/iommu/tegra-smmu.c     |  1 +
 include/linux/iommu.h          | 22 ++++++++++++++++++++++
 11 files changed, 56 insertions(+)

(limited to 'include')

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 505a9adac2d..2d84c9edf3b 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3424,6 +3424,7 @@ static const struct iommu_ops amd_iommu_ops = {
 	.detach_dev = amd_iommu_detach_device,
 	.map = amd_iommu_map,
 	.unmap = amd_iommu_unmap,
+	.map_sg = default_iommu_map_sg,
 	.iova_to_phys = amd_iommu_iova_to_phys,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 };
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 60558f79492..e393ae01b5d 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1652,6 +1652,7 @@ static const struct iommu_ops arm_smmu_ops = {
 	.detach_dev	= arm_smmu_detach_dev,
 	.map		= arm_smmu_map,
 	.unmap		= arm_smmu_unmap,
+	.map_sg		= default_iommu_map_sg,
 	.iova_to_phys	= arm_smmu_iova_to_phys,
 	.add_device	= arm_smmu_add_device,
 	.remove_device	= arm_smmu_remove_device,
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 74233186f6f..28372b85d8d 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -1178,6 +1178,7 @@ static const struct iommu_ops exynos_iommu_ops = {
 	.detach_dev = exynos_iommu_detach_device,
 	.map = exynos_iommu_map,
 	.unmap = exynos_iommu_unmap,
+	.map_sg = default_iommu_map_sg,
 	.iova_to_phys = exynos_iommu_iova_to_phys,
 	.add_device = exynos_iommu_add_device,
 	.remove_device = exynos_iommu_remove_device,
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a27d6cb1a79..02cd26a17fe 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4467,6 +4467,7 @@ static const struct iommu_ops intel_iommu_ops = {
 	.detach_dev	= intel_iommu_detach_device,
 	.map		= intel_iommu_map,
 	.unmap		= intel_iommu_unmap,
+	.map_sg		= default_iommu_map_sg,
 	.iova_to_phys	= intel_iommu_iova_to_phys,
 	.add_device	= intel_iommu_add_device,
 	.remove_device	= intel_iommu_remove_device,
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index ed8b04867b1..46727ce9280 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1124,6 +1124,31 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
 }
 EXPORT_SYMBOL_GPL(iommu_unmap);
 
+size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+			 struct scatterlist *sg, unsigned int nents, int prot)
+{
+	int ret;
+	size_t mapped = 0;
+	unsigned int i;
+	struct scatterlist *s;
+
+	for_each_sg(sg, s, nents, i) {
+		phys_addr_t phys = page_to_phys(sg_page(s));
+		size_t page_len = s->offset + s->length;
+
+		ret = iommu_map(domain, iova + mapped, phys, page_len, prot);
+		if (ret) {
+			/* undo mappings already done */
+			iommu_unmap(domain, iova, mapped);
+			mapped = 0;
+			break;
+		}
+		mapped += page_len;
+	}
+
+	return mapped;
+}
+EXPORT_SYMBOL_GPL(default_iommu_map_sg);
 
 int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
 			       phys_addr_t paddr, u64 size, int prot)
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 7dab5cbcc77..e509c58eee9 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -1127,6 +1127,7 @@ static const struct iommu_ops ipmmu_ops = {
 	.detach_dev = ipmmu_detach_device,
 	.map = ipmmu_map,
 	.unmap = ipmmu_unmap,
+	.map_sg = default_iommu_map_sg,
 	.iova_to_phys = ipmmu_iova_to_phys,
 	.add_device = ipmmu_add_device,
 	.remove_device = ipmmu_remove_device,
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 6e3dcc289d5..1c7b78ecf3e 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -681,6 +681,7 @@ static const struct iommu_ops msm_iommu_ops = {
 	.detach_dev = msm_iommu_detach_dev,
 	.map = msm_iommu_map,
 	.unmap = msm_iommu_unmap,
+	.map_sg = default_iommu_map_sg,
 	.iova_to_phys = msm_iommu_iova_to_phys,
 	.pgsize_bitmap = MSM_IOMMU_PGSIZES,
 };
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index 36278870e84..18003c04445 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -1288,6 +1288,7 @@ static const struct iommu_ops omap_iommu_ops = {
 	.detach_dev	= omap_iommu_detach_dev,
 	.map		= omap_iommu_map,
 	.unmap		= omap_iommu_unmap,
+	.map_sg		= default_iommu_map_sg,
 	.iova_to_phys	= omap_iommu_iova_to_phys,
 	.add_device	= omap_iommu_add_device,
 	.remove_device	= omap_iommu_remove_device,
diff --git a/drivers/iommu/shmobile-iommu.c b/drivers/iommu/shmobile-iommu.c
index 1333e6fb340..f1b00774e4d 100644
--- a/drivers/iommu/shmobile-iommu.c
+++ b/drivers/iommu/shmobile-iommu.c
@@ -361,6 +361,7 @@ static const struct iommu_ops shmobile_iommu_ops = {
 	.detach_dev = shmobile_iommu_detach_device,
 	.map = shmobile_iommu_map,
 	.unmap = shmobile_iommu_unmap,
+	.map_sg = default_iommu_map_sg,
 	.iova_to_phys = shmobile_iommu_iova_to_phys,
 	.add_device = shmobile_iommu_add_device,
 	.pgsize_bitmap = SZ_1M | SZ_64K | SZ_4K,
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 3afdf43f732..73e845a6692 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -955,6 +955,7 @@ static const struct iommu_ops smmu_iommu_ops = {
 	.detach_dev	= smmu_iommu_detach_dev,
 	.map		= smmu_iommu_map,
 	.unmap		= smmu_iommu_unmap,
+	.map_sg		= default_iommu_map_sg,
 	.iova_to_phys	= smmu_iommu_iova_to_phys,
 	.pgsize_bitmap	= SMMU_IOMMU_PGSIZES,
 };
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index e6a7c9ff72f..b29a5982e1c 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -22,6 +22,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/types.h>
+#include <linux/scatterlist.h>
 #include <trace/events/iommu.h>
 
 #define IOMMU_READ	(1 << 0)
@@ -97,6 +98,8 @@ enum iommu_attr {
  * @detach_dev: detach device from an iommu domain
  * @map: map a physically contiguous memory region to an iommu domain
  * @unmap: unmap a physically contiguous memory region from an iommu domain
+ * @map_sg: map a scatter-gather list of physically contiguous memory chunks
+ * to an iommu domain
  * @iova_to_phys: translate iova to physical address
  * @add_device: add device to iommu grouping
  * @remove_device: remove device from iommu grouping
@@ -114,6 +117,8 @@ struct iommu_ops {
 		   phys_addr_t paddr, size_t size, int prot);
 	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
 		     size_t size);
+	size_t (*map_sg)(struct iommu_domain *domain, unsigned long iova,
+			 struct scatterlist *sg, unsigned int nents, int prot);
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova);
 	int (*add_device)(struct device *dev);
 	void (*remove_device)(struct device *dev);
@@ -156,6 +161,9 @@ extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
 		     phys_addr_t paddr, size_t size, int prot);
 extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 		       size_t size);
+extern size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+				struct scatterlist *sg,unsigned int nents,
+				int prot);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova);
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
@@ -241,6 +249,13 @@ static inline int report_iommu_fault(struct iommu_domain *domain,
 	return ret;
 }
 
+static inline size_t iommu_map_sg(struct iommu_domain *domain,
+				  unsigned long iova, struct scatterlist *sg,
+				  unsigned int nents, int prot)
+{
+	return domain->ops->map_sg(domain, iova, sg, nents, prot);
+}
+
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
@@ -293,6 +308,13 @@ static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 	return -ENODEV;
 }
 
+static inline size_t iommu_map_sg(struct iommu_domain *domain,
+				  unsigned long iova, struct scatterlist *sg,
+				  unsigned int nents, int prot)
+{
+	return -ENODEV;
+}
+
 static inline int iommu_domain_window_enable(struct iommu_domain *domain,
 					     u32 wnd_nr, phys_addr_t paddr,
 					     u64 size, int prot)
-- 
cgit v1.2.3-70-g09d2


From b75b276bead4850c86e60747babe09be5c13d4d1 Mon Sep 17 00:00:00 2001
From: Matthias Brugger <matthias.bgg@gmail.com>
Date: Tue, 21 Oct 2014 18:27:25 +0200
Subject: of: Request and map make argument name constant

This patch makes the name argument from of_io_request_and_map constant.

Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 drivers/of/address.c       | 2 +-
 include/linux/of_address.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/of/address.c b/drivers/of/address.c
index afdb78299f6..e02828fa3ac 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -871,7 +871,7 @@ EXPORT_SYMBOL(of_iomap);
  *		return PTR_ERR(base);
  */
 void __iomem *of_io_request_and_map(struct device_node *np, int index,
-					char *name)
+					const char *name)
 {
 	struct resource res;
 	void __iomem *mem;
diff --git a/include/linux/of_address.h b/include/linux/of_address.h
index 8cb14eb393d..d88e81be636 100644
--- a/include/linux/of_address.h
+++ b/include/linux/of_address.h
@@ -106,7 +106,7 @@ extern int of_address_to_resource(struct device_node *dev, int index,
 				  struct resource *r);
 void __iomem *of_iomap(struct device_node *node, int index);
 void __iomem *of_io_request_and_map(struct device_node *device,
-					int index, char *name);
+					int index, const char *name);
 #else
 
 #include <linux/io.h>
@@ -123,7 +123,7 @@ static inline void __iomem *of_iomap(struct device_node *device, int index)
 }
 
 static inline void __iomem *of_io_request_and_map(struct device_node *device,
-					int index, char *name)
+					int index, const char *name)
 {
 	return IOMEM_ERR_PTR(-EINVAL);
 }
-- 
cgit v1.2.3-70-g09d2


From 5f563585ab0afa8c35b3627d65c07966f7a5080e Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Thu, 2 Oct 2014 16:01:10 +0200
Subject: of: Fix padding in _OF_DECLARE macro definition

Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 include/linux/of.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/of.h b/include/linux/of.h
index f54da3b699a..3c851a8f23e 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -836,7 +836,7 @@ static inline int of_get_available_child_count(const struct device_node *np)
 		 = { .compatible = compat,				\
 		     .data = (fn == (fn_type)NULL) ? fn : fn  }
 #else
-#define _OF_DECLARE(table, name, compat, fn, fn_type)					\
+#define _OF_DECLARE(table, name, compat, fn, fn_type)			\
 	static const struct of_device_id __of_table_##name		\
 		__attribute__((unused))					\
 		 = { .compatible = compat,				\
-- 
cgit v1.2.3-70-g09d2


From 0d8a52f933f817d0b62955a5a362fb7f2508f06c Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 4 Nov 2014 11:55:09 +0300
Subject: ieee802154: || vs && in ieee802154_is_valid_extended_addr()

The ieee802154_is_valid_extended_addr() always returns true because
there is a typo.  The || should be &&.  Neither 0x0000000000000000ULL
nor 0xffffffffffffffffULL are valid addresses.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/ieee802154.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index 5d9e7459d94..4c032863cd7 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -209,7 +209,7 @@ static inline bool ieee802154_is_valid_extended_addr(const __le64 addr)
 	 * This is currently a workaround because neighbor discovery can't
 	 * deal with short addresses types right now.
 	 */
-	return ((addr != cpu_to_le64(0x0000000000000000ULL)) ||
+	return ((addr != cpu_to_le64(0x0000000000000000ULL)) &&
 		(addr != cpu_to_le64(0xffffffffffffffffULL)));
 }
 
-- 
cgit v1.2.3-70-g09d2


From 6fccf9383b280d463a7dfe1e0d048aff8df8a25e Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Wed, 18 Jun 2014 13:58:57 -0600
Subject: NVMe: Async event request

Submits NVMe asynchronous event requests, one event up to the controller
maximum or number of possible different event types (8), whichever is
smaller. Events successfully returned by the controller are logged.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/block/nvme-core.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/nvme.h      |  1 +
 2 files changed, 43 insertions(+)

(limited to 'include')

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index baee59530d6..42a62bbf4a1 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -207,6 +207,7 @@ static int alloc_cmdid_killable(struct nvme_queue *nvmeq, void *ctx,
 #define CMD_CTX_COMPLETED	(0x310 + CMD_CTX_BASE)
 #define CMD_CTX_INVALID		(0x314 + CMD_CTX_BASE)
 #define CMD_CTX_ABORT		(0x318 + CMD_CTX_BASE)
+#define CMD_CTX_ASYNC		(0x31C + CMD_CTX_BASE)
 
 static void special_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
@@ -229,6 +230,17 @@ static void special_completion(struct nvme_queue *nvmeq, void *ctx,
 				cqe->command_id, le16_to_cpup(&cqe->sq_id));
 		return;
 	}
+	if (ctx == CMD_CTX_ASYNC) {
+		u32 result = le32_to_cpup(&cqe->result);
+		u16 status = le16_to_cpup(&cqe->status) >> 1;
+
+		if (status == NVME_SC_SUCCESS || status == NVME_SC_ABORT_REQ)
+			++nvmeq->dev->event_limit;
+		if (status == NVME_SC_SUCCESS)
+			dev_warn(nvmeq->q_dmadev,
+				"async event result %08x\n", result);
+		return;
+	}
 
 	dev_warn(nvmeq->q_dmadev, "Unknown special completion %p\n", ctx);
 }
@@ -1161,6 +1173,8 @@ static void nvme_cancel_ios(struct nvme_queue *nvmeq, bool timeout)
 			continue;
 		if (info[cmdid].ctx == CMD_CTX_CANCELLED)
 			continue;
+		if (timeout && info[cmdid].ctx == CMD_CTX_ASYNC)
+			continue;
 		if (timeout && nvmeq->dev->initialized) {
 			nvme_abort_cmd(cmdid, nvmeq);
 			continue;
@@ -1842,6 +1856,27 @@ static void nvme_resubmit_bios(struct nvme_queue *nvmeq)
 	}
 }
 
+static int nvme_submit_async_req(struct nvme_queue *nvmeq)
+{
+	struct nvme_command *c;
+	int cmdid;
+
+	cmdid = alloc_cmdid(nvmeq, CMD_CTX_ASYNC, special_completion, 0);
+	if (cmdid < 0)
+		return cmdid;
+
+	c = &nvmeq->sq_cmds[nvmeq->sq_tail];
+	memset(c, 0, sizeof(*c));
+	c->common.opcode = nvme_admin_async_event;
+	c->common.command_id = cmdid;
+
+	if (++nvmeq->sq_tail == nvmeq->q_depth)
+		nvmeq->sq_tail = 0;
+	writel(nvmeq->sq_tail, nvmeq->q_db);
+
+	return 0;
+}
+
 static int nvme_kthread(void *data)
 {
 	struct nvme_dev *dev, *next;
@@ -1875,6 +1910,12 @@ static int nvme_kthread(void *data)
 				nvme_cancel_ios(nvmeq, true);
 				nvme_resubmit_bios(nvmeq);
 				nvme_resubmit_iods(nvmeq);
+
+				while ((i == 0) && (dev->event_limit > 0)) {
+					if (nvme_submit_async_req(nvmeq))
+						break;
+					dev->event_limit--;
+				}
  unlock:
 				spin_unlock_irq(&nvmeq->q_lock);
 			}
@@ -2244,6 +2285,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	dev->oncs = le16_to_cpup(&ctrl->oncs);
 	dev->abort_limit = ctrl->acl + 1;
 	dev->vwc = ctrl->vwc;
+	dev->event_limit = min(ctrl->aerl + 1, 8);
 	memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn));
 	memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn));
 	memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr));
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 2bf403195c0..974efd04a4b 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -99,6 +99,7 @@ struct nvme_dev {
 	u32 stripe_size;
 	u16 oncs;
 	u16 abort_limit;
+	u8 event_limit;
 	u8 vwc;
 	u8 initialized;
 };
-- 
cgit v1.2.3-70-g09d2


From a7dd7957acf798ac406afd6631e64a27ac4a5bf1 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <matthew.r.wilcox@intel.com>
Date: Sat, 28 Jun 2014 09:00:27 -0400
Subject: NVMe: Update list of status codes

Taken from the draft NVMe 1.1b specification.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/uapi/linux/nvme.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/nvme.h b/include/uapi/linux/nvme.h
index 29a7d8619d8..134518b0100 100644
--- a/include/uapi/linux/nvme.h
+++ b/include/uapi/linux/nvme.h
@@ -440,9 +440,15 @@ enum {
 	NVME_SC_FUSED_MISSING		= 0xa,
 	NVME_SC_INVALID_NS		= 0xb,
 	NVME_SC_CMD_SEQ_ERROR		= 0xc,
+	NVME_SC_SGL_INVALID_LAST	= 0xd,
+	NVME_SC_SGL_INVALID_COUNT	= 0xe,
+	NVME_SC_SGL_INVALID_DATA	= 0xf,
+	NVME_SC_SGL_INVALID_METADATA	= 0x10,
+	NVME_SC_SGL_INVALID_TYPE	= 0x11,
 	NVME_SC_LBA_RANGE		= 0x80,
 	NVME_SC_CAP_EXCEEDED		= 0x81,
 	NVME_SC_NS_NOT_READY		= 0x82,
+	NVME_SC_RESERVATION_CONFLICT	= 0x83,
 	NVME_SC_CQ_INVALID		= 0x100,
 	NVME_SC_QID_INVALID		= 0x101,
 	NVME_SC_QUEUE_SIZE		= 0x102,
@@ -454,7 +460,15 @@ enum {
 	NVME_SC_INVALID_VECTOR		= 0x108,
 	NVME_SC_INVALID_LOG_PAGE	= 0x109,
 	NVME_SC_INVALID_FORMAT		= 0x10a,
+	NVME_SC_FIRMWARE_NEEDS_RESET	= 0x10b,
+	NVME_SC_INVALID_QUEUE		= 0x10c,
+	NVME_SC_FEATURE_NOT_SAVEABLE	= 0x10d,
+	NVME_SC_FEATURE_NOT_CHANGEABLE	= 0x10e,
+	NVME_SC_FEATURE_NOT_PER_NS	= 0x10f,
+	NVME_SC_FW_NEEDS_RESET_SUBSYS	= 0x110,
 	NVME_SC_BAD_ATTRIBUTES		= 0x180,
+	NVME_SC_INVALID_PI		= 0x181,
+	NVME_SC_READ_ONLY		= 0x182,
 	NVME_SC_WRITE_FAULT		= 0x280,
 	NVME_SC_READ_ERROR		= 0x281,
 	NVME_SC_GUARD_CHECK		= 0x282,
-- 
cgit v1.2.3-70-g09d2


From 1d0906246095184d1624c643c2088152d330c40a Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Mon, 23 Jun 2014 11:34:01 -0600
Subject: NVMe: Mismatched host/device page size support

Adds support for devices with max page size smaller than the host's.
In the case we encounter such a host/device combination, the driver will
split a page into as many PRP entries as necessary for the device's page
size capabilities. If the device's reported minimum page size is greater
than the host's, the driver will not attempt to enable the device and
return an error instead.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/block/nvme-core.c | 59 ++++++++++++++++++++++++++++++++---------------
 include/linux/nvme.h      |  2 ++
 2 files changed, 42 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 42a62bbf4a1..e60bb0fec7e 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -373,17 +373,17 @@ static __le64 **iod_list(struct nvme_iod *iod)
  * as it only leads to a small amount of wasted memory for the lifetime of
  * the I/O.
  */
-static int nvme_npages(unsigned size)
+static int nvme_npages(unsigned size, struct nvme_dev *dev)
 {
-	unsigned nprps = DIV_ROUND_UP(size + PAGE_SIZE, PAGE_SIZE);
-	return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
+	unsigned nprps = DIV_ROUND_UP(size + dev->page_size, dev->page_size);
+	return DIV_ROUND_UP(8 * nprps, dev->page_size - 8);
 }
 
 static struct nvme_iod *
-nvme_alloc_iod(unsigned nseg, unsigned nbytes, gfp_t gfp)
+nvme_alloc_iod(unsigned nseg, unsigned nbytes, struct nvme_dev *dev, gfp_t gfp)
 {
 	struct nvme_iod *iod = kmalloc(sizeof(struct nvme_iod) +
-				sizeof(__le64 *) * nvme_npages(nbytes) +
+				sizeof(__le64 *) * nvme_npages(nbytes, dev) +
 				sizeof(struct scatterlist) * nseg, gfp);
 
 	if (iod) {
@@ -400,7 +400,7 @@ nvme_alloc_iod(unsigned nseg, unsigned nbytes, gfp_t gfp)
 
 void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
 {
-	const int last_prp = PAGE_SIZE / 8 - 1;
+	const int last_prp = dev->page_size / 8 - 1;
 	int i;
 	__le64 **list = iod_list(iod);
 	dma_addr_t prp_dma = iod->first_dma;
@@ -491,26 +491,27 @@ int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod, int total_len,
 	__le64 **list = iod_list(iod);
 	dma_addr_t prp_dma;
 	int nprps, i;
+	u32 page_size = dev->page_size;
 
-	length -= (PAGE_SIZE - offset);
+	length -= (page_size - offset);
 	if (length <= 0)
 		return total_len;
 
-	dma_len -= (PAGE_SIZE - offset);
+	dma_len -= (page_size - offset);
 	if (dma_len) {
-		dma_addr += (PAGE_SIZE - offset);
+		dma_addr += (page_size - offset);
 	} else {
 		sg = sg_next(sg);
 		dma_addr = sg_dma_address(sg);
 		dma_len = sg_dma_len(sg);
 	}
 
-	if (length <= PAGE_SIZE) {
+	if (length <= page_size) {
 		iod->first_dma = dma_addr;
 		return total_len;
 	}
 
-	nprps = DIV_ROUND_UP(length, PAGE_SIZE);
+	nprps = DIV_ROUND_UP(length, page_size);
 	if (nprps <= (256 / 8)) {
 		pool = dev->prp_small_pool;
 		iod->npages = 0;
@@ -523,13 +524,13 @@ int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod, int total_len,
 	if (!prp_list) {
 		iod->first_dma = dma_addr;
 		iod->npages = -1;
-		return (total_len - length) + PAGE_SIZE;
+		return (total_len - length) + page_size;
 	}
 	list[0] = prp_list;
 	iod->first_dma = prp_dma;
 	i = 0;
 	for (;;) {
-		if (i == PAGE_SIZE / 8) {
+		if (i == page_size >> 3) {
 			__le64 *old_prp_list = prp_list;
 			prp_list = dma_pool_alloc(pool, gfp, &prp_dma);
 			if (!prp_list)
@@ -540,9 +541,9 @@ int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod, int total_len,
 			i = 1;
 		}
 		prp_list[i++] = cpu_to_le64(dma_addr);
-		dma_len -= PAGE_SIZE;
-		dma_addr += PAGE_SIZE;
-		length -= PAGE_SIZE;
+		dma_len -= page_size;
+		dma_addr += page_size;
+		length -= page_size;
 		if (length <= 0)
 			break;
 		if (dma_len > 0)
@@ -749,7 +750,7 @@ static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 	if ((bio->bi_rw & REQ_FLUSH) && psegs)
 		return nvme_split_flush_data(nvmeq, bio);
 
-	iod = nvme_alloc_iod(psegs, bio->bi_iter.bi_size, GFP_ATOMIC);
+	iod = nvme_alloc_iod(psegs, bio->bi_iter.bi_size, ns->dev, GFP_ATOMIC);
 	if (!iod)
 		return -ENOMEM;
 
@@ -1463,6 +1464,24 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	u32 aqa;
 	u64 cap = readq(&dev->bar->cap);
 	struct nvme_queue *nvmeq;
+	unsigned page_shift = PAGE_SHIFT;
+	unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12;
+	unsigned dev_page_max = NVME_CAP_MPSMAX(cap) + 12;
+
+	if (page_shift < dev_page_min) {
+		dev_err(&dev->pci_dev->dev,
+				"Minimum device page size (%u) too large for "
+				"host (%u)\n", 1 << dev_page_min,
+				1 << page_shift);
+		return -ENODEV;
+	}
+	if (page_shift > dev_page_max) {
+		dev_info(&dev->pci_dev->dev,
+				"Device maximum page size (%u) smaller than "
+				"host (%u); enabling work-around\n",
+				1 << dev_page_max, 1 << page_shift);
+		page_shift = dev_page_max;
+	}
 
 	result = nvme_disable_ctrl(dev, cap);
 	if (result < 0)
@@ -1478,8 +1497,10 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	aqa = nvmeq->q_depth - 1;
 	aqa |= aqa << 16;
 
+	dev->page_size = 1 << page_shift;
+
 	dev->ctrl_config = NVME_CC_ENABLE | NVME_CC_CSS_NVM;
-	dev->ctrl_config |= (PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT;
+	dev->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT;
 	dev->ctrl_config |= NVME_CC_ARB_RR | NVME_CC_SHN_NONE;
 	dev->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;
 
@@ -1529,7 +1550,7 @@ struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
 	}
 
 	err = -ENOMEM;
-	iod = nvme_alloc_iod(count, length, GFP_KERNEL);
+	iod = nvme_alloc_iod(count, length, dev, GFP_KERNEL);
 	if (!iod)
 		goto put_pages;
 
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 974efd04a4b..ed09074e555 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -38,6 +38,7 @@ struct nvme_bar {
 #define NVME_CAP_TIMEOUT(cap)	(((cap) >> 24) & 0xff)
 #define NVME_CAP_STRIDE(cap)	(((cap) >> 32) & 0xf)
 #define NVME_CAP_MPSMIN(cap)	(((cap) >> 48) & 0xf)
+#define NVME_CAP_MPSMAX(cap)	(((cap) >> 52) & 0xf)
 
 enum {
 	NVME_CC_ENABLE		= 1 << 0,
@@ -97,6 +98,7 @@ struct nvme_dev {
 	char firmware_rev[8];
 	u32 max_hw_sectors;
 	u32 stripe_size;
+	u32 page_size;
 	u16 oncs;
 	u16 abort_limit;
 	u8 event_limit;
-- 
cgit v1.2.3-70-g09d2


From 7963e521811ed19396d47793cc77d87c643ab891 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 12 Sep 2014 16:07:20 -0600
Subject: NVMe: Passthrough IOCTL for IO commands

The NVME_IOCTL_SUBMIT_IO only works for IO commands with block data
transfers and isn't usable for other NVMe commands like flush,
data set management, or any sort of vendor unique command. The
NVME_IOCTL_ADMIN_CMD, however, can easily be modified to accept arbitrary
IO commands in addition to arbitrary admin commands without breaking
backward compatibility. This patch just adds a new IOCTL to distinguish
if the driver should submit the command on an IO or Admin queue.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/block/nvme-core.c | 17 ++++++++++++-----
 include/uapi/linux/nvme.h |  5 ++++-
 2 files changed, 16 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 93ee55ee377..70be3a151eb 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -1732,10 +1732,10 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	return status;
 }
 
-static int nvme_user_admin_cmd(struct nvme_dev *dev,
-					struct nvme_admin_cmd __user *ucmd)
+static int nvme_user_cmd(struct nvme_dev *dev,
+			struct nvme_passthru_cmd __user *ucmd, bool ioq)
 {
-	struct nvme_admin_cmd cmd;
+	struct nvme_passthru_cmd cmd;
 	struct nvme_command c;
 	int status, length;
 	struct nvme_iod *uninitialized_var(iod);
@@ -1774,6 +1774,9 @@ static int nvme_user_admin_cmd(struct nvme_dev *dev,
 								ADMIN_TIMEOUT;
 	if (length != cmd.data_len)
 		status = -ENOMEM;
+	else if (ioq)
+		status = nvme_submit_sync_cmd(dev, this_cpu_read(*dev->io_queue), &c,
+							&cmd.result, timeout);
 	else
 		status = nvme_submit_sync_cmd(dev, 0, &c, &cmd.result, timeout);
 
@@ -1799,7 +1802,9 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
 		force_successful_syscall_return();
 		return ns->ns_id;
 	case NVME_IOCTL_ADMIN_CMD:
-		return nvme_user_admin_cmd(ns->dev, (void __user *)arg);
+		return nvme_user_cmd(ns->dev, (void __user *)arg, false);
+	case NVME_IOCTL_IO_CMD:
+		return nvme_user_cmd(ns->dev, (void __user *)arg, true);
 	case NVME_IOCTL_SUBMIT_IO:
 		return nvme_submit_io(ns, (void __user *)arg);
 	case SG_GET_VERSION_NUM:
@@ -2743,7 +2748,9 @@ static long nvme_dev_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 	struct nvme_dev *dev = f->private_data;
 	switch (cmd) {
 	case NVME_IOCTL_ADMIN_CMD:
-		return nvme_user_admin_cmd(dev, (void __user *)arg);
+		return nvme_user_cmd(dev, (void __user *)arg, false);
+	case NVME_IOCTL_IO_CMD:
+		return nvme_user_cmd(dev, (void __user *)arg, true);
 	default:
 		return -ENOTTY;
 	}
diff --git a/include/uapi/linux/nvme.h b/include/uapi/linux/nvme.h
index 134518b0100..97106556408 100644
--- a/include/uapi/linux/nvme.h
+++ b/include/uapi/linux/nvme.h
@@ -503,7 +503,7 @@ struct nvme_user_io {
 	__u16	appmask;
 };
 
-struct nvme_admin_cmd {
+struct nvme_passthru_cmd {
 	__u8	opcode;
 	__u8	flags;
 	__u16	rsvd1;
@@ -524,8 +524,11 @@ struct nvme_admin_cmd {
 	__u32	result;
 };
 
+#define nvme_admin_cmd nvme_passthru_cmd
+
 #define NVME_IOCTL_ID		_IO('N', 0x40)
 #define NVME_IOCTL_ADMIN_CMD	_IOWR('N', 0x41, struct nvme_admin_cmd)
 #define NVME_IOCTL_SUBMIT_IO	_IOW('N', 0x42, struct nvme_user_io)
+#define NVME_IOCTL_IO_CMD	_IOWR('N', 0x43, struct nvme_passthru_cmd)
 
 #endif /* _UAPI_LINUX_NVME_H */
-- 
cgit v1.2.3-70-g09d2


From 60e0545cc92ce4172c7069d559568717f64af332 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Mon, 15 Sep 2014 14:08:38 -0600
Subject: NVMe: Updates for 1.1 spec

Updating commands and structures for NVMe 1.1 updates, mostly for nvme
reservations. There are no additional in-kernel uses, but this is for
the uapi.

While doing this, I noticed that the software progress features was
using the wrong value, so updating that value as well.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/uapi/linux/nvme.h | 27 ++++++++++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/nvme.h b/include/uapi/linux/nvme.h
index 97106556408..26386cf3db4 100644
--- a/include/uapi/linux/nvme.h
+++ b/include/uapi/linux/nvme.h
@@ -181,6 +181,22 @@ enum {
 	NVME_LBART_ATTRIB_HIDE	= 1 << 1,
 };
 
+struct nvme_reservation_status {
+	__le32	gen;
+	__u8	rtype;
+	__u8	regctl[2];
+	__u8	resv5[2];
+	__u8	ptpls;
+	__u8	resv10[13];
+	struct {
+		__le16	cntlid;
+		__u8	rcsts;
+		__u8	resv3[5];
+		__le64	hostid;
+		__le64	rkey;
+	} regctl_ds[];
+};
+
 /* I/O commands */
 
 enum nvme_opcode {
@@ -189,7 +205,12 @@ enum nvme_opcode {
 	nvme_cmd_read		= 0x02,
 	nvme_cmd_write_uncor	= 0x04,
 	nvme_cmd_compare	= 0x05,
+	nvme_cmd_write_zeroes	= 0x08,
 	nvme_cmd_dsm		= 0x09,
+	nvme_cmd_resv_register	= 0x0d,
+	nvme_cmd_resv_report	= 0x0e,
+	nvme_cmd_resv_acquire	= 0x11,
+	nvme_cmd_resv_release	= 0x15,
 };
 
 struct nvme_common_command {
@@ -305,7 +326,11 @@ enum {
 	NVME_FEAT_IRQ_CONFIG	= 0x09,
 	NVME_FEAT_WRITE_ATOMIC	= 0x0a,
 	NVME_FEAT_ASYNC_EVENT	= 0x0b,
-	NVME_FEAT_SW_PROGRESS	= 0x0c,
+	NVME_FEAT_AUTO_PST	= 0x0c,
+	NVME_FEAT_SW_PROGRESS	= 0x80,
+	NVME_FEAT_HOST_ID	= 0x81,
+	NVME_FEAT_RESV_MASK	= 0x82,
+	NVME_FEAT_RESV_PERSIST	= 0x83,
 	NVME_LOG_ERROR		= 0x01,
 	NVME_LOG_SMART		= 0x02,
 	NVME_LOG_FW_SLOT	= 0x03,
-- 
cgit v1.2.3-70-g09d2


From a4aea5623d4a54682b6ff5c18196d7802f3e478f Mon Sep 17 00:00:00 2001
From: Matias Bjørling <m@bjorling.me>
Date: Tue, 4 Nov 2014 08:20:14 -0700
Subject: NVMe: Convert to blk-mq

This converts the NVMe driver to a blk-mq request-based driver.

The NVMe driver is currently bio-based and implements queue logic within
itself.  By using blk-mq, a lot of these responsibilities can be moved
and simplified.

The patch is divided into the following blocks:

 * Per-command data and cmdid have been moved into the struct request
   field. The cmdid_data can be retrieved using blk_mq_rq_to_pdu() and id
   maintenance are now handled by blk-mq through the rq->tag field.

 * The logic for splitting bio's has been moved into the blk-mq layer.
   The driver instead notifies the block layer about limited gap support in
   SG lists.

 * blk-mq handles timeouts and is reimplemented within nvme_timeout().
   This both includes abort handling and command cancelation.

 * Assignment of nvme queues to CPUs are replaced with the blk-mq
   version. The current blk-mq strategy is to assign the number of
   mapped queues and CPUs to provide synergy, while the nvme driver
   assign as many nvme hw queues as possible. This can be implemented in
   blk-mq if needed.

 * NVMe queues are merged with the tags structure of blk-mq.

 * blk-mq takes care of setup/teardown of nvme queues and guards invalid
   accesses. Therefore, RCU-usage for nvme queues can be removed.

 * IO tracing and accounting are handled by blk-mq and therefore removed.

 * Queue suspension logic is replaced with the logic from the block
   layer.

Contributions in this patch from:

  Sam Bradshaw <sbradshaw@micron.com>
  Jens Axboe <axboe@fb.com>
  Keith Busch <keith.busch@intel.com>
  Robert Nelson <rlnelson@google.com>

Acked-by: Keith Busch <keith.busch@intel.com>
Acked-by: Jens Axboe <axboe@fb.com>

Updated for new ->queue_rq() prototype.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/block/nvme-core.c | 1366 ++++++++++++++++++---------------------------
 drivers/block/nvme-scsi.c |    8 +-
 include/linux/nvme.h      |   15 +-
 3 files changed, 570 insertions(+), 819 deletions(-)

(limited to 'include')

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index c70eff3673d..39050a3d10f 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -13,9 +13,9 @@
  */
 
 #include <linux/nvme.h>
-#include <linux/bio.h>
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
@@ -33,7 +33,6 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
-#include <linux/percpu.h>
 #include <linux/poison.h>
 #include <linux/ptrace.h>
 #include <linux/sched.h>
@@ -42,9 +41,8 @@
 #include <scsi/sg.h>
 #include <asm-generic/io-64-nonatomic-lo-hi.h>
 
-#include <trace/events/block.h>
-
 #define NVME_Q_DEPTH		1024
+#define NVME_AQ_DEPTH		64
 #define SQ_SIZE(depth)		(depth * sizeof(struct nvme_command))
 #define CQ_SIZE(depth)		(depth * sizeof(struct nvme_completion))
 #define ADMIN_TIMEOUT		(admin_timeout * HZ)
@@ -81,10 +79,12 @@ static wait_queue_head_t nvme_kthread_wait;
 static struct notifier_block nvme_nb;
 
 static void nvme_reset_failed_dev(struct work_struct *ws);
+static int nvme_process_cq(struct nvme_queue *nvmeq);
 
 struct async_cmd_info {
 	struct kthread_work work;
 	struct kthread_worker *worker;
+	struct request *req;
 	u32 result;
 	int status;
 	void *ctx;
@@ -104,10 +104,6 @@ struct nvme_queue {
 	volatile struct nvme_completion *cqes;
 	dma_addr_t sq_dma_addr;
 	dma_addr_t cq_dma_addr;
-	wait_queue_head_t sq_full;
-	wait_queue_t sq_cong_wait;
-	struct bio_list sq_cong;
-	struct list_head iod_bio;
 	u32 __iomem *q_db;
 	u16 q_depth;
 	u16 cq_vector;
@@ -117,10 +113,8 @@ struct nvme_queue {
 	u16 qid;
 	u8 cq_phase;
 	u8 cqe_seen;
-	u8 q_suspended;
-	cpumask_var_t cpu_mask;
 	struct async_cmd_info cmdinfo;
-	unsigned long cmdid_data[];
+	struct blk_mq_hw_ctx *hctx;
 };
 
 /*
@@ -148,62 +142,72 @@ typedef void (*nvme_completion_fn)(struct nvme_queue *, void *,
 struct nvme_cmd_info {
 	nvme_completion_fn fn;
 	void *ctx;
-	unsigned long timeout;
 	int aborted;
+	struct nvme_queue *nvmeq;
 };
 
-static struct nvme_cmd_info *nvme_cmd_info(struct nvme_queue *nvmeq)
+static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+				unsigned int hctx_idx)
 {
-	return (void *)&nvmeq->cmdid_data[BITS_TO_LONGS(nvmeq->q_depth)];
+	struct nvme_dev *dev = data;
+	struct nvme_queue *nvmeq = dev->queues[0];
+
+	WARN_ON(nvmeq->hctx);
+	nvmeq->hctx = hctx;
+	hctx->driver_data = nvmeq;
+	return 0;
 }
 
-static unsigned nvme_queue_extra(int depth)
+static int nvme_admin_init_request(void *data, struct request *req,
+				unsigned int hctx_idx, unsigned int rq_idx,
+				unsigned int numa_node)
 {
-	return DIV_ROUND_UP(depth, 8) + (depth * sizeof(struct nvme_cmd_info));
+	struct nvme_dev *dev = data;
+	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
+	struct nvme_queue *nvmeq = dev->queues[0];
+
+	BUG_ON(!nvmeq);
+	cmd->nvmeq = nvmeq;
+	return 0;
 }
 
-/**
- * alloc_cmdid() - Allocate a Command ID
- * @nvmeq: The queue that will be used for this command
- * @ctx: A pointer that will be passed to the handler
- * @handler: The function to call on completion
- *
- * Allocate a Command ID for a queue.  The data passed in will
- * be passed to the completion handler.  This is implemented by using
- * the bottom two bits of the ctx pointer to store the handler ID.
- * Passing in a pointer that's not 4-byte aligned will cause a BUG.
- * We can change this if it becomes a problem.
- *
- * May be called with local interrupts disabled and the q_lock held,
- * or with interrupts enabled and no locks held.
- */
-static int alloc_cmdid(struct nvme_queue *nvmeq, void *ctx,
-				nvme_completion_fn handler, unsigned timeout)
+static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+			  unsigned int hctx_idx)
 {
-	int depth = nvmeq->q_depth - 1;
-	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
-	int cmdid;
+	struct nvme_dev *dev = data;
+	struct nvme_queue *nvmeq = dev->queues[
+					(hctx_idx % dev->queue_count) + 1];
 
-	do {
-		cmdid = find_first_zero_bit(nvmeq->cmdid_data, depth);
-		if (cmdid >= depth)
-			return -EBUSY;
-	} while (test_and_set_bit(cmdid, nvmeq->cmdid_data));
+	if (!nvmeq->hctx)
+		nvmeq->hctx = hctx;
+
+	/* nvmeq queues are shared between namespaces. We assume here that
+	 * blk-mq map the tags so they match up with the nvme queue tags. */
+	WARN_ON(nvmeq->hctx->tags != hctx->tags);
 
-	info[cmdid].fn = handler;
-	info[cmdid].ctx = ctx;
-	info[cmdid].timeout = jiffies + timeout;
-	info[cmdid].aborted = 0;
-	return cmdid;
+	hctx->driver_data = nvmeq;
+	return 0;
 }
 
-static int alloc_cmdid_killable(struct nvme_queue *nvmeq, void *ctx,
-				nvme_completion_fn handler, unsigned timeout)
+static int nvme_init_request(void *data, struct request *req,
+				unsigned int hctx_idx, unsigned int rq_idx,
+				unsigned int numa_node)
 {
-	int cmdid;
-	wait_event_killable(nvmeq->sq_full,
-		(cmdid = alloc_cmdid(nvmeq, ctx, handler, timeout)) >= 0);
-	return (cmdid < 0) ? -EINTR : cmdid;
+	struct nvme_dev *dev = data;
+	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
+	struct nvme_queue *nvmeq = dev->queues[hctx_idx + 1];
+
+	BUG_ON(!nvmeq);
+	cmd->nvmeq = nvmeq;
+	return 0;
+}
+
+static void nvme_set_info(struct nvme_cmd_info *cmd, void *ctx,
+				nvme_completion_fn handler)
+{
+	cmd->fn = handler;
+	cmd->ctx = ctx;
+	cmd->aborted = 0;
 }
 
 /* Special values must be less than 0x1000 */
@@ -211,18 +215,12 @@ static int alloc_cmdid_killable(struct nvme_queue *nvmeq, void *ctx,
 #define CMD_CTX_CANCELLED	(0x30C + CMD_CTX_BASE)
 #define CMD_CTX_COMPLETED	(0x310 + CMD_CTX_BASE)
 #define CMD_CTX_INVALID		(0x314 + CMD_CTX_BASE)
-#define CMD_CTX_ABORT		(0x318 + CMD_CTX_BASE)
-#define CMD_CTX_ASYNC		(0x31C + CMD_CTX_BASE)
 
 static void special_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
 	if (ctx == CMD_CTX_CANCELLED)
 		return;
-	if (ctx == CMD_CTX_ABORT) {
-		++nvmeq->dev->abort_limit;
-		return;
-	}
 	if (ctx == CMD_CTX_COMPLETED) {
 		dev_warn(nvmeq->q_dmadev,
 				"completed id %d twice on queue %d\n",
@@ -235,110 +233,89 @@ static void special_completion(struct nvme_queue *nvmeq, void *ctx,
 				cqe->command_id, le16_to_cpup(&cqe->sq_id));
 		return;
 	}
-	if (ctx == CMD_CTX_ASYNC) {
-		u32 result = le32_to_cpup(&cqe->result);
-		u16 status = le16_to_cpup(&cqe->status) >> 1;
-
-		if (status == NVME_SC_SUCCESS || status == NVME_SC_ABORT_REQ)
-			++nvmeq->dev->event_limit;
-		if (status == NVME_SC_SUCCESS)
-			dev_warn(nvmeq->q_dmadev,
-				"async event result %08x\n", result);
-		return;
-	}
-
 	dev_warn(nvmeq->q_dmadev, "Unknown special completion %p\n", ctx);
 }
 
-static void async_completion(struct nvme_queue *nvmeq, void *ctx,
-						struct nvme_completion *cqe)
-{
-	struct async_cmd_info *cmdinfo = ctx;
-	cmdinfo->result = le32_to_cpup(&cqe->result);
-	cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
-	queue_kthread_work(cmdinfo->worker, &cmdinfo->work);
-}
-
-/*
- * Called with local interrupts disabled and the q_lock held.  May not sleep.
- */
-static void *free_cmdid(struct nvme_queue *nvmeq, int cmdid,
-						nvme_completion_fn *fn)
+static void *cancel_cmd_info(struct nvme_cmd_info *cmd, nvme_completion_fn *fn)
 {
 	void *ctx;
-	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
 
-	if (cmdid >= nvmeq->q_depth || !info[cmdid].fn) {
-		if (fn)
-			*fn = special_completion;
-		return CMD_CTX_INVALID;
-	}
 	if (fn)
-		*fn = info[cmdid].fn;
-	ctx = info[cmdid].ctx;
-	info[cmdid].fn = special_completion;
-	info[cmdid].ctx = CMD_CTX_COMPLETED;
-	clear_bit(cmdid, nvmeq->cmdid_data);
-	wake_up(&nvmeq->sq_full);
+		*fn = cmd->fn;
+	ctx = cmd->ctx;
+	cmd->fn = special_completion;
+	cmd->ctx = CMD_CTX_CANCELLED;
 	return ctx;
 }
 
-static void *cancel_cmdid(struct nvme_queue *nvmeq, int cmdid,
-						nvme_completion_fn *fn)
+static void async_req_completion(struct nvme_queue *nvmeq, void *ctx,
+						struct nvme_completion *cqe)
 {
-	void *ctx;
-	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
-	if (fn)
-		*fn = info[cmdid].fn;
-	ctx = info[cmdid].ctx;
-	info[cmdid].fn = special_completion;
-	info[cmdid].ctx = CMD_CTX_CANCELLED;
-	return ctx;
-}
+	struct request *req = ctx;
 
-static struct nvme_queue *raw_nvmeq(struct nvme_dev *dev, int qid)
-{
-	return rcu_dereference_raw(dev->queues[qid]);
+	u32 result = le32_to_cpup(&cqe->result);
+	u16 status = le16_to_cpup(&cqe->status) >> 1;
+
+	if (status == NVME_SC_SUCCESS || status == NVME_SC_ABORT_REQ)
+		++nvmeq->dev->event_limit;
+	if (status == NVME_SC_SUCCESS)
+		dev_warn(nvmeq->q_dmadev,
+			"async event result %08x\n", result);
+
+	blk_put_request(req);
 }
 
-static struct nvme_queue *get_nvmeq(struct nvme_dev *dev) __acquires(RCU)
+static void abort_completion(struct nvme_queue *nvmeq, void *ctx,
+						struct nvme_completion *cqe)
 {
-	struct nvme_queue *nvmeq;
-	unsigned queue_id = get_cpu_var(*dev->io_queue);
+	struct request *req = ctx;
+
+	u16 status = le16_to_cpup(&cqe->status) >> 1;
+	u32 result = le32_to_cpup(&cqe->result);
 
-	rcu_read_lock();
-	nvmeq = rcu_dereference(dev->queues[queue_id]);
-	if (nvmeq)
-		return nvmeq;
+	blk_put_request(req);
 
-	rcu_read_unlock();
-	put_cpu_var(*dev->io_queue);
-	return NULL;
+	dev_warn(nvmeq->q_dmadev, "Abort status:%x result:%x", status, result);
+	++nvmeq->dev->abort_limit;
 }
 
-static void put_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
+static void async_completion(struct nvme_queue *nvmeq, void *ctx,
+						struct nvme_completion *cqe)
 {
-	rcu_read_unlock();
-	put_cpu_var(nvmeq->dev->io_queue);
+	struct async_cmd_info *cmdinfo = ctx;
+	cmdinfo->result = le32_to_cpup(&cqe->result);
+	cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
+	queue_kthread_work(cmdinfo->worker, &cmdinfo->work);
+	blk_put_request(cmdinfo->req);
 }
 
-static struct nvme_queue *lock_nvmeq(struct nvme_dev *dev, int q_idx)
-							__acquires(RCU)
+static inline struct nvme_cmd_info *get_cmd_from_tag(struct nvme_queue *nvmeq,
+				  unsigned int tag)
 {
-	struct nvme_queue *nvmeq;
-
-	rcu_read_lock();
-	nvmeq = rcu_dereference(dev->queues[q_idx]);
-	if (nvmeq)
-		return nvmeq;
+	struct blk_mq_hw_ctx *hctx = nvmeq->hctx;
+	struct request *req = blk_mq_tag_to_rq(hctx->tags, tag);
 
-	rcu_read_unlock();
-	return NULL;
+	return blk_mq_rq_to_pdu(req);
 }
 
-static void unlock_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
+/*
+ * Called with local interrupts disabled and the q_lock held.  May not sleep.
+ */
+static void *nvme_finish_cmd(struct nvme_queue *nvmeq, int tag,
+						nvme_completion_fn *fn)
 {
-	rcu_read_unlock();
+	struct nvme_cmd_info *cmd = get_cmd_from_tag(nvmeq, tag);
+	void *ctx;
+	if (tag >= nvmeq->q_depth) {
+		*fn = special_completion;
+		return CMD_CTX_INVALID;
+	}
+	if (fn)
+		*fn = cmd->fn;
+	ctx = cmd->ctx;
+	cmd->fn = special_completion;
+	cmd->ctx = CMD_CTX_COMPLETED;
+	return ctx;
 }
 
 /**
@@ -348,26 +325,29 @@ static void unlock_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
  *
  * Safe to use from interrupt context
  */
-static int nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
+static int __nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
 {
-	unsigned long flags;
-	u16 tail;
-	spin_lock_irqsave(&nvmeq->q_lock, flags);
-	if (nvmeq->q_suspended) {
-		spin_unlock_irqrestore(&nvmeq->q_lock, flags);
-		return -EBUSY;
-	}
-	tail = nvmeq->sq_tail;
+	u16 tail = nvmeq->sq_tail;
+
 	memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
 	if (++tail == nvmeq->q_depth)
 		tail = 0;
 	writel(tail, nvmeq->q_db);
 	nvmeq->sq_tail = tail;
-	spin_unlock_irqrestore(&nvmeq->q_lock, flags);
 
 	return 0;
 }
 
+static int nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
+{
+	unsigned long flags;
+	int ret;
+	spin_lock_irqsave(&nvmeq->q_lock, flags);
+	ret = __nvme_submit_cmd(nvmeq, cmd);
+	spin_unlock_irqrestore(&nvmeq->q_lock, flags);
+	return ret;
+}
+
 static __le64 **iod_list(struct nvme_iod *iod)
 {
 	return ((void *)iod) + iod->offset;
@@ -397,7 +377,6 @@ nvme_alloc_iod(unsigned nseg, unsigned nbytes, struct nvme_dev *dev, gfp_t gfp)
 		iod->length = nbytes;
 		iod->nents = 0;
 		iod->first_dma = 0ULL;
-		iod->start_time = jiffies;
 	}
 
 	return iod;
@@ -421,35 +400,6 @@ void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
 	kfree(iod);
 }
 
-static void nvme_start_io_acct(struct bio *bio)
-{
-	struct gendisk *disk = bio->bi_bdev->bd_disk;
-	if (blk_queue_io_stat(disk->queue)) {
-		const int rw = bio_data_dir(bio);
-		int cpu = part_stat_lock();
-		part_round_stats(cpu, &disk->part0);
-		part_stat_inc(cpu, &disk->part0, ios[rw]);
-		part_stat_add(cpu, &disk->part0, sectors[rw],
-							bio_sectors(bio));
-		part_inc_in_flight(&disk->part0, rw);
-		part_stat_unlock();
-	}
-}
-
-static void nvme_end_io_acct(struct bio *bio, unsigned long start_time)
-{
-	struct gendisk *disk = bio->bi_bdev->bd_disk;
-	if (blk_queue_io_stat(disk->queue)) {
-		const int rw = bio_data_dir(bio);
-		unsigned long duration = jiffies - start_time;
-		int cpu = part_stat_lock();
-		part_stat_add(cpu, &disk->part0, ticks[rw], duration);
-		part_round_stats(cpu, &disk->part0);
-		part_dec_in_flight(&disk->part0, rw);
-		part_stat_unlock();
-	}
-}
-
 static int nvme_error_status(u16 status)
 {
 	switch (status & 0x7ff) {
@@ -462,36 +412,37 @@ static int nvme_error_status(u16 status)
 	}
 }
 
-static void bio_completion(struct nvme_queue *nvmeq, void *ctx,
+static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
 	struct nvme_iod *iod = ctx;
-	struct bio *bio = iod->private;
+	struct request *req = iod->private;
+	struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
+
 	u16 status = le16_to_cpup(&cqe->status) >> 1;
-	int error = 0;
 
 	if (unlikely(status)) {
-		if (!(status & NVME_SC_DNR ||
-				bio->bi_rw & REQ_FAILFAST_MASK) &&
-				(jiffies - iod->start_time) < IOD_TIMEOUT) {
-			if (!waitqueue_active(&nvmeq->sq_full))
-				add_wait_queue(&nvmeq->sq_full,
-							&nvmeq->sq_cong_wait);
-			list_add_tail(&iod->node, &nvmeq->iod_bio);
-			wake_up(&nvmeq->sq_full);
+		if (!(status & NVME_SC_DNR || blk_noretry_request(req))
+		    && (jiffies - req->start_time) < req->timeout) {
+			blk_mq_requeue_request(req);
+			blk_mq_kick_requeue_list(req->q);
 			return;
 		}
-		error = nvme_error_status(status);
-	}
-	if (iod->nents) {
-		dma_unmap_sg(nvmeq->q_dmadev, iod->sg, iod->nents,
-			bio_data_dir(bio) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
-		nvme_end_io_acct(bio, iod->start_time);
-	}
+		req->errors = nvme_error_status(status);
+	} else
+		req->errors = 0;
+
+	if (cmd_rq->aborted)
+		dev_warn(&nvmeq->dev->pci_dev->dev,
+			"completing aborted command with status:%04x\n",
+			status);
+
+	if (iod->nents)
+		dma_unmap_sg(&nvmeq->dev->pci_dev->dev, iod->sg, iod->nents,
+			rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 	nvme_free_iod(nvmeq->dev, iod);
 
-	trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio, error);
-	bio_endio(bio, error);
+	blk_mq_complete_request(req);
 }
 
 /* length is in bytes.  gfp flags indicates whether we may sleep. */
@@ -574,88 +525,25 @@ int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod, int total_len,
 	return total_len;
 }
 
-static int nvme_split_and_submit(struct bio *bio, struct nvme_queue *nvmeq,
-				 int len)
-{
-	struct bio *split = bio_split(bio, len >> 9, GFP_ATOMIC, NULL);
-	if (!split)
-		return -ENOMEM;
-
-	trace_block_split(bdev_get_queue(bio->bi_bdev), bio,
-					split->bi_iter.bi_sector);
-	bio_chain(split, bio);
-
-	if (!waitqueue_active(&nvmeq->sq_full))
-		add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
-	bio_list_add(&nvmeq->sq_cong, split);
-	bio_list_add(&nvmeq->sq_cong, bio);
-	wake_up(&nvmeq->sq_full);
-
-	return 0;
-}
-
-/* NVMe scatterlists require no holes in the virtual address */
-#define BIOVEC_NOT_VIRT_MERGEABLE(vec1, vec2)	((vec2)->bv_offset || \
-			(((vec1)->bv_offset + (vec1)->bv_len) % PAGE_SIZE))
-
-static int nvme_map_bio(struct nvme_queue *nvmeq, struct nvme_iod *iod,
-		struct bio *bio, enum dma_data_direction dma_dir, int psegs)
-{
-	struct bio_vec bvec, bvprv;
-	struct bvec_iter iter;
-	struct scatterlist *sg = NULL;
-	int length = 0, nsegs = 0, split_len = bio->bi_iter.bi_size;
-	int first = 1;
-
-	if (nvmeq->dev->stripe_size)
-		split_len = nvmeq->dev->stripe_size -
-			((bio->bi_iter.bi_sector << 9) &
-			 (nvmeq->dev->stripe_size - 1));
-
-	sg_init_table(iod->sg, psegs);
-	bio_for_each_segment(bvec, bio, iter) {
-		if (!first && BIOVEC_PHYS_MERGEABLE(&bvprv, &bvec)) {
-			sg->length += bvec.bv_len;
-		} else {
-			if (!first && BIOVEC_NOT_VIRT_MERGEABLE(&bvprv, &bvec))
-				return nvme_split_and_submit(bio, nvmeq,
-							     length);
-
-			sg = sg ? sg + 1 : iod->sg;
-			sg_set_page(sg, bvec.bv_page,
-				    bvec.bv_len, bvec.bv_offset);
-			nsegs++;
-		}
-
-		if (split_len - length < bvec.bv_len)
-			return nvme_split_and_submit(bio, nvmeq, split_len);
-		length += bvec.bv_len;
-		bvprv = bvec;
-		first = 0;
-	}
-	iod->nents = nsegs;
-	sg_mark_end(sg);
-	if (dma_map_sg(nvmeq->q_dmadev, iod->sg, iod->nents, dma_dir) == 0)
-		return -ENOMEM;
-
-	BUG_ON(length != bio->bi_iter.bi_size);
-	return length;
-}
-
-static int nvme_submit_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
-		struct bio *bio, struct nvme_iod *iod, int cmdid)
+/*
+ * We reuse the small pool to allocate the 16-byte range here as it is not
+ * worth having a special pool for these or additional cases to handle freeing
+ * the iod.
+ */
+static void nvme_submit_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
+		struct request *req, struct nvme_iod *iod)
 {
 	struct nvme_dsm_range *range =
 				(struct nvme_dsm_range *)iod_list(iod)[0];
 	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
 
 	range->cattr = cpu_to_le32(0);
-	range->nlb = cpu_to_le32(bio->bi_iter.bi_size >> ns->lba_shift);
-	range->slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_iter.bi_sector));
+	range->nlb = cpu_to_le32(blk_rq_bytes(req) >> ns->lba_shift);
+	range->slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
 
 	memset(cmnd, 0, sizeof(*cmnd));
 	cmnd->dsm.opcode = nvme_cmd_dsm;
-	cmnd->dsm.command_id = cmdid;
+	cmnd->dsm.command_id = req->tag;
 	cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
 	cmnd->dsm.prp1 = cpu_to_le64(iod->first_dma);
 	cmnd->dsm.nr = 0;
@@ -664,11 +552,9 @@ static int nvme_submit_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 	if (++nvmeq->sq_tail == nvmeq->q_depth)
 		nvmeq->sq_tail = 0;
 	writel(nvmeq->sq_tail, nvmeq->q_db);
-
-	return 0;
 }
 
-static int nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
+static void nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 								int cmdid)
 {
 	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
@@ -681,49 +567,34 @@ static int nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 	if (++nvmeq->sq_tail == nvmeq->q_depth)
 		nvmeq->sq_tail = 0;
 	writel(nvmeq->sq_tail, nvmeq->q_db);
-
-	return 0;
 }
 
-static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod)
+static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
+							struct nvme_ns *ns)
 {
-	struct bio *bio = iod->private;
-	struct nvme_ns *ns = bio->bi_bdev->bd_disk->private_data;
+	struct request *req = iod->private;
 	struct nvme_command *cmnd;
-	int cmdid;
-	u16 control;
-	u32 dsmgmt;
+	u16 control = 0;
+	u32 dsmgmt = 0;
 
-	cmdid = alloc_cmdid(nvmeq, iod, bio_completion, NVME_IO_TIMEOUT);
-	if (unlikely(cmdid < 0))
-		return cmdid;
-
-	if (bio->bi_rw & REQ_DISCARD)
-		return nvme_submit_discard(nvmeq, ns, bio, iod, cmdid);
-	if (bio->bi_rw & REQ_FLUSH)
-		return nvme_submit_flush(nvmeq, ns, cmdid);
-
-	control = 0;
-	if (bio->bi_rw & REQ_FUA)
+	if (req->cmd_flags & REQ_FUA)
 		control |= NVME_RW_FUA;
-	if (bio->bi_rw & (REQ_FAILFAST_DEV | REQ_RAHEAD))
+	if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
 		control |= NVME_RW_LR;
 
-	dsmgmt = 0;
-	if (bio->bi_rw & REQ_RAHEAD)
+	if (req->cmd_flags & REQ_RAHEAD)
 		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
 
 	cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
 	memset(cmnd, 0, sizeof(*cmnd));
 
-	cmnd->rw.opcode = bio_data_dir(bio) ? nvme_cmd_write : nvme_cmd_read;
-	cmnd->rw.command_id = cmdid;
+	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
+	cmnd->rw.command_id = req->tag;
 	cmnd->rw.nsid = cpu_to_le32(ns->ns_id);
 	cmnd->rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
 	cmnd->rw.prp2 = cpu_to_le64(iod->first_dma);
-	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_iter.bi_sector));
-	cmnd->rw.length =
-		cpu_to_le16((bio->bi_iter.bi_size >> ns->lba_shift) - 1);
+	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
+	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
 	cmnd->rw.control = cpu_to_le16(control);
 	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
 
@@ -734,47 +605,37 @@ static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod)
 	return 0;
 }
 
-static int nvme_split_flush_data(struct nvme_queue *nvmeq, struct bio *bio)
-{
-	struct bio *split = bio_clone(bio, GFP_ATOMIC);
-	if (!split)
-		return -ENOMEM;
-
-	split->bi_iter.bi_size = 0;
-	split->bi_phys_segments = 0;
-	bio->bi_rw &= ~REQ_FLUSH;
-	bio_chain(split, bio);
-
-	if (!waitqueue_active(&nvmeq->sq_full))
-		add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
-	bio_list_add(&nvmeq->sq_cong, split);
-	bio_list_add(&nvmeq->sq_cong, bio);
-	wake_up_process(nvme_thread);
-
-	return 0;
-}
-
-/*
- * Called with local interrupts disabled and the q_lock held.  May not sleep.
- */
-static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
-								struct bio *bio)
+static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
+			 const struct blk_mq_queue_data *bd)
 {
+	struct nvme_ns *ns = hctx->queue->queuedata;
+	struct nvme_queue *nvmeq = hctx->driver_data;
+	struct request *req = bd->rq;
+	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
 	struct nvme_iod *iod;
-	int psegs = bio_phys_segments(ns->queue, bio);
-	int result;
-	unsigned size = !(bio->bi_rw & REQ_DISCARD) ? bio->bi_iter.bi_size :
+	int psegs = req->nr_phys_segments;
+	int result = BLK_MQ_RQ_QUEUE_BUSY;
+	enum dma_data_direction dma_dir;
+	unsigned size = !(req->cmd_flags & REQ_DISCARD) ? blk_rq_bytes(req) :
 						sizeof(struct nvme_dsm_range);
 
-	if ((bio->bi_rw & REQ_FLUSH) && psegs)
-		return nvme_split_flush_data(nvmeq, bio);
+	/*
+	 * Requeued IO has already been prepped
+	 */
+	iod = req->special;
+	if (iod)
+		goto submit_iod;
 
 	iod = nvme_alloc_iod(psegs, size, ns->dev, GFP_ATOMIC);
 	if (!iod)
-		return -ENOMEM;
+		return result;
+
+	iod->private = req;
+	req->special = iod;
 
-	iod->private = bio;
-	if (bio->bi_rw & REQ_DISCARD) {
+	nvme_set_info(cmd, iod, req_completion);
+
+	if (req->cmd_flags & REQ_DISCARD) {
 		void *range;
 		/*
 		 * We reuse the small pool to allocate the 16-byte range here
@@ -784,33 +645,45 @@ static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 		range = dma_pool_alloc(nvmeq->dev->prp_small_pool,
 						GFP_ATOMIC,
 						&iod->first_dma);
-		if (!range) {
-			result = -ENOMEM;
-			goto free_iod;
-		}
+		if (!range)
+			goto finish_cmd;
 		iod_list(iod)[0] = (__le64 *)range;
 		iod->npages = 0;
 	} else if (psegs) {
-		result = nvme_map_bio(nvmeq, iod, bio,
-			bio_data_dir(bio) ? DMA_TO_DEVICE : DMA_FROM_DEVICE,
-			psegs);
-		if (result <= 0)
-			goto free_iod;
-		if (nvme_setup_prps(nvmeq->dev, iod, result, GFP_ATOMIC) !=
-								result) {
-			result = -ENOMEM;
-			goto free_iod;
+		dma_dir = rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
+
+		sg_init_table(iod->sg, psegs);
+		iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
+		if (!iod->nents) {
+			result = BLK_MQ_RQ_QUEUE_ERROR;
+			goto finish_cmd;
 		}
-		nvme_start_io_acct(bio);
-	}
-	if (unlikely(nvme_submit_iod(nvmeq, iod))) {
-		if (!waitqueue_active(&nvmeq->sq_full))
-			add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
-		list_add_tail(&iod->node, &nvmeq->iod_bio);
+
+		if (!dma_map_sg(nvmeq->q_dmadev, iod->sg, iod->nents, dma_dir))
+			goto finish_cmd;
+
+		if (blk_rq_bytes(req) != nvme_setup_prps(nvmeq->dev, iod,
+						blk_rq_bytes(req), GFP_ATOMIC))
+			goto finish_cmd;
 	}
-	return 0;
 
- free_iod:
+	blk_mq_start_request(req);
+
+ submit_iod:
+	spin_lock_irq(&nvmeq->q_lock);
+	if (req->cmd_flags & REQ_DISCARD)
+		nvme_submit_discard(nvmeq, ns, req, iod);
+	else if (req->cmd_flags & REQ_FLUSH)
+		nvme_submit_flush(nvmeq, ns, req->tag);
+	else
+		nvme_submit_iod(nvmeq, iod, ns);
+
+	nvme_process_cq(nvmeq);
+	spin_unlock_irq(&nvmeq->q_lock);
+	return BLK_MQ_RQ_QUEUE_OK;
+
+ finish_cmd:
+	nvme_finish_cmd(nvmeq, req->tag, NULL);
 	nvme_free_iod(nvmeq->dev, iod);
 	return result;
 }
@@ -833,8 +706,7 @@ static int nvme_process_cq(struct nvme_queue *nvmeq)
 			head = 0;
 			phase = !phase;
 		}
-
-		ctx = free_cmdid(nvmeq, cqe.command_id, &fn);
+		ctx = nvme_finish_cmd(nvmeq, cqe.command_id, &fn);
 		fn(nvmeq, ctx, &cqe);
 	}
 
@@ -855,29 +727,13 @@ static int nvme_process_cq(struct nvme_queue *nvmeq)
 	return 1;
 }
 
-static void nvme_make_request(struct request_queue *q, struct bio *bio)
+/* Admin queue isn't initialized as a request queue. If at some point this
+ * happens anyway, make sure to notify the user */
+static int nvme_admin_queue_rq(struct blk_mq_hw_ctx *hctx,
+			       const struct blk_mq_queue_data *bd)
 {
-	struct nvme_ns *ns = q->queuedata;
-	struct nvme_queue *nvmeq = get_nvmeq(ns->dev);
-	int result = -EBUSY;
-
-	if (!nvmeq) {
-		bio_endio(bio, -EIO);
-		return;
-	}
-
-	spin_lock_irq(&nvmeq->q_lock);
-	if (!nvmeq->q_suspended && bio_list_empty(&nvmeq->sq_cong))
-		result = nvme_submit_bio_queue(nvmeq, ns, bio);
-	if (unlikely(result)) {
-		if (!waitqueue_active(&nvmeq->sq_full))
-			add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
-		bio_list_add(&nvmeq->sq_cong, bio);
-	}
-
-	nvme_process_cq(nvmeq);
-	spin_unlock_irq(&nvmeq->q_lock);
-	put_nvmeq(nvmeq);
+	WARN_ON_ONCE(1);
+	return BLK_MQ_RQ_QUEUE_ERROR;
 }
 
 static irqreturn_t nvme_irq(int irq, void *data)
@@ -901,10 +757,11 @@ static irqreturn_t nvme_irq_check(int irq, void *data)
 	return IRQ_WAKE_THREAD;
 }
 
-static void nvme_abort_command(struct nvme_queue *nvmeq, int cmdid)
+static void nvme_abort_cmd_info(struct nvme_queue *nvmeq, struct nvme_cmd_info *
+								cmd_info)
 {
 	spin_lock_irq(&nvmeq->q_lock);
-	cancel_cmdid(nvmeq, cmdid, NULL);
+	cancel_cmd_info(cmd_info, NULL);
 	spin_unlock_irq(&nvmeq->q_lock);
 }
 
@@ -927,45 +784,31 @@ static void sync_completion(struct nvme_queue *nvmeq, void *ctx,
  * Returns 0 on success.  If the result is negative, it's a Linux error code;
  * if the result is positive, it's an NVM Express status code
  */
-static int nvme_submit_sync_cmd(struct nvme_dev *dev, int q_idx,
-						struct nvme_command *cmd,
+static int nvme_submit_sync_cmd(struct request *req, struct nvme_command *cmd,
 						u32 *result, unsigned timeout)
 {
-	int cmdid, ret;
+	int ret;
 	struct sync_cmd_info cmdinfo;
-	struct nvme_queue *nvmeq;
-
-	nvmeq = lock_nvmeq(dev, q_idx);
-	if (!nvmeq)
-		return -ENODEV;
+	struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
+	struct nvme_queue *nvmeq = cmd_rq->nvmeq;
 
 	cmdinfo.task = current;
 	cmdinfo.status = -EINTR;
 
-	cmdid = alloc_cmdid(nvmeq, &cmdinfo, sync_completion, timeout);
-	if (cmdid < 0) {
-		unlock_nvmeq(nvmeq);
-		return cmdid;
-	}
-	cmd->common.command_id = cmdid;
+	cmd->common.command_id = req->tag;
+
+	nvme_set_info(cmd_rq, &cmdinfo, sync_completion);
 
 	set_current_state(TASK_KILLABLE);
 	ret = nvme_submit_cmd(nvmeq, cmd);
 	if (ret) {
-		free_cmdid(nvmeq, cmdid, NULL);
-		unlock_nvmeq(nvmeq);
+		nvme_finish_cmd(nvmeq, req->tag, NULL);
 		set_current_state(TASK_RUNNING);
-		return ret;
 	}
-	unlock_nvmeq(nvmeq);
 	schedule_timeout(timeout);
 
 	if (cmdinfo.status == -EINTR) {
-		nvmeq = lock_nvmeq(dev, q_idx);
-		if (nvmeq) {
-			nvme_abort_command(nvmeq, cmdid);
-			unlock_nvmeq(nvmeq);
-		}
+		nvme_abort_cmd_info(nvmeq, blk_mq_rq_to_pdu(req));
 		return -EINTR;
 	}
 
@@ -975,59 +818,99 @@ static int nvme_submit_sync_cmd(struct nvme_dev *dev, int q_idx,
 	return cmdinfo.status;
 }
 
-static int nvme_submit_async_cmd(struct nvme_queue *nvmeq,
+static int nvme_submit_async_admin_req(struct nvme_dev *dev)
+{
+	struct nvme_queue *nvmeq = dev->queues[0];
+	struct nvme_command c;
+	struct nvme_cmd_info *cmd_info;
+	struct request *req;
+
+	req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_KERNEL, false);
+	if (!req)
+		return -ENOMEM;
+
+	cmd_info = blk_mq_rq_to_pdu(req);
+	nvme_set_info(cmd_info, req, async_req_completion);
+
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = nvme_admin_async_event;
+	c.common.command_id = req->tag;
+
+	return __nvme_submit_cmd(nvmeq, &c);
+}
+
+static int nvme_submit_admin_async_cmd(struct nvme_dev *dev,
 			struct nvme_command *cmd,
 			struct async_cmd_info *cmdinfo, unsigned timeout)
 {
-	int cmdid;
+	struct nvme_queue *nvmeq = dev->queues[0];
+	struct request *req;
+	struct nvme_cmd_info *cmd_rq;
 
-	cmdid = alloc_cmdid_killable(nvmeq, cmdinfo, async_completion, timeout);
-	if (cmdid < 0)
-		return cmdid;
+	req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_KERNEL, false);
+	if (!req)
+		return -ENOMEM;
+
+	req->timeout = timeout;
+	cmd_rq = blk_mq_rq_to_pdu(req);
+	cmdinfo->req = req;
+	nvme_set_info(cmd_rq, cmdinfo, async_completion);
 	cmdinfo->status = -EINTR;
-	cmd->common.command_id = cmdid;
+
+	cmd->common.command_id = req->tag;
+
 	return nvme_submit_cmd(nvmeq, cmd);
 }
 
-int nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
-								u32 *result)
+int __nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
+						u32 *result, unsigned timeout)
 {
-	return nvme_submit_sync_cmd(dev, 0, cmd, result, ADMIN_TIMEOUT);
+	int res;
+	struct request *req;
+
+	req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_KERNEL, false);
+	if (!req)
+		return -ENOMEM;
+	res = nvme_submit_sync_cmd(req, cmd, result, timeout);
+	blk_put_request(req);
+	return res;
 }
 
-int nvme_submit_io_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
+int nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
 								u32 *result)
 {
-	return nvme_submit_sync_cmd(dev, this_cpu_read(*dev->io_queue), cmd,
-						result,	NVME_IO_TIMEOUT);
+	return __nvme_submit_admin_cmd(dev, cmd, result, ADMIN_TIMEOUT);
 }
 
-static int nvme_submit_admin_cmd_async(struct nvme_dev *dev,
-		struct nvme_command *cmd, struct async_cmd_info *cmdinfo)
+int nvme_submit_io_cmd(struct nvme_dev *dev, struct nvme_ns *ns,
+					struct nvme_command *cmd, u32 *result)
 {
-	return nvme_submit_async_cmd(raw_nvmeq(dev, 0), cmd, cmdinfo,
-								ADMIN_TIMEOUT);
+	int res;
+	struct request *req;
+
+	req = blk_mq_alloc_request(ns->queue, WRITE, (GFP_KERNEL|__GFP_WAIT),
+									false);
+	if (!req)
+		return -ENOMEM;
+	res = nvme_submit_sync_cmd(req, cmd, result, NVME_IO_TIMEOUT);
+	blk_put_request(req);
+	return res;
 }
 
 static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
 {
-	int status;
 	struct nvme_command c;
 
 	memset(&c, 0, sizeof(c));
 	c.delete_queue.opcode = opcode;
 	c.delete_queue.qid = cpu_to_le16(id);
 
-	status = nvme_submit_admin_cmd(dev, &c, NULL);
-	if (status)
-		return -EIO;
-	return 0;
+	return nvme_submit_admin_cmd(dev, &c, NULL);
 }
 
 static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
 						struct nvme_queue *nvmeq)
 {
-	int status;
 	struct nvme_command c;
 	int flags = NVME_QUEUE_PHYS_CONTIG | NVME_CQ_IRQ_ENABLED;
 
@@ -1039,16 +922,12 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
 	c.create_cq.cq_flags = cpu_to_le16(flags);
 	c.create_cq.irq_vector = cpu_to_le16(nvmeq->cq_vector);
 
-	status = nvme_submit_admin_cmd(dev, &c, NULL);
-	if (status)
-		return -EIO;
-	return 0;
+	return nvme_submit_admin_cmd(dev, &c, NULL);
 }
 
 static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
 						struct nvme_queue *nvmeq)
 {
-	int status;
 	struct nvme_command c;
 	int flags = NVME_QUEUE_PHYS_CONTIG | NVME_SQ_PRIO_MEDIUM;
 
@@ -1060,10 +939,7 @@ static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
 	c.create_sq.sq_flags = cpu_to_le16(flags);
 	c.create_sq.cqid = cpu_to_le16(qid);
 
-	status = nvme_submit_admin_cmd(dev, &c, NULL);
-	if (status)
-		return -EIO;
-	return 0;
+	return nvme_submit_admin_cmd(dev, &c, NULL);
 }
 
 static int adapter_delete_cq(struct nvme_dev *dev, u16 cqid)
@@ -1119,28 +995,27 @@ int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11,
 }
 
 /**
- * nvme_abort_cmd - Attempt aborting a command
- * @cmdid: Command id of a timed out IO
- * @queue: The queue with timed out IO
+ * nvme_abort_req - Attempt aborting a request
  *
  * Schedule controller reset if the command was already aborted once before and
  * still hasn't been returned to the driver, or if this is the admin queue.
  */
-static void nvme_abort_cmd(int cmdid, struct nvme_queue *nvmeq)
+static void nvme_abort_req(struct request *req)
 {
-	int a_cmdid;
-	struct nvme_command cmd;
+	struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
+	struct nvme_queue *nvmeq = cmd_rq->nvmeq;
 	struct nvme_dev *dev = nvmeq->dev;
-	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
-	struct nvme_queue *adminq;
+	struct request *abort_req;
+	struct nvme_cmd_info *abort_cmd;
+	struct nvme_command cmd;
 
-	if (!nvmeq->qid || info[cmdid].aborted) {
+	if (!nvmeq->qid || cmd_rq->aborted) {
 		if (work_busy(&dev->reset_work))
 			return;
 		list_del_init(&dev->node);
 		dev_warn(&dev->pci_dev->dev,
-			"I/O %d QID %d timeout, reset controller\n", cmdid,
-								nvmeq->qid);
+			"I/O %d QID %d timeout, reset controller\n",
+							req->tag, nvmeq->qid);
 		dev->reset_workfn = nvme_reset_failed_dev;
 		queue_work(nvme_workq, &dev->reset_work);
 		return;
@@ -1149,89 +1024,79 @@ static void nvme_abort_cmd(int cmdid, struct nvme_queue *nvmeq)
 	if (!dev->abort_limit)
 		return;
 
-	adminq = rcu_dereference(dev->queues[0]);
-	a_cmdid = alloc_cmdid(adminq, CMD_CTX_ABORT, special_completion,
-								ADMIN_TIMEOUT);
-	if (a_cmdid < 0)
+	abort_req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_ATOMIC,
+									false);
+	if (!abort_req)
 		return;
 
+	abort_cmd = blk_mq_rq_to_pdu(abort_req);
+	nvme_set_info(abort_cmd, abort_req, abort_completion);
+
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.abort.opcode = nvme_admin_abort_cmd;
-	cmd.abort.cid = cmdid;
+	cmd.abort.cid = req->tag;
 	cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
-	cmd.abort.command_id = a_cmdid;
+	cmd.abort.command_id = abort_req->tag;
 
 	--dev->abort_limit;
-	info[cmdid].aborted = 1;
-	info[cmdid].timeout = jiffies + ADMIN_TIMEOUT;
+	cmd_rq->aborted = 1;
 
-	dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", cmdid,
+	dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", req->tag,
 							nvmeq->qid);
-	nvme_submit_cmd(adminq, &cmd);
+	if (nvme_submit_cmd(dev->queues[0], &cmd) < 0) {
+		dev_warn(nvmeq->q_dmadev,
+				"Could not abort I/O %d QID %d",
+				req->tag, nvmeq->qid);
+		blk_put_request(req);
+	}
 }
 
-/**
- * nvme_cancel_ios - Cancel outstanding I/Os
- * @queue: The queue to cancel I/Os on
- * @timeout: True to only cancel I/Os which have timed out
- */
-static void nvme_cancel_ios(struct nvme_queue *nvmeq, bool timeout)
+static void nvme_cancel_queue_ios(struct blk_mq_hw_ctx *hctx,
+				struct request *req, void *data, bool reserved)
 {
-	int depth = nvmeq->q_depth - 1;
-	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
-	unsigned long now = jiffies;
-	int cmdid;
+	struct nvme_queue *nvmeq = data;
+	void *ctx;
+	nvme_completion_fn fn;
+	struct nvme_cmd_info *cmd;
+	static struct nvme_completion cqe = {
+		.status = cpu_to_le16(NVME_SC_ABORT_REQ << 1),
+	};
 
-	for_each_set_bit(cmdid, nvmeq->cmdid_data, depth) {
-		void *ctx;
-		nvme_completion_fn fn;
-		static struct nvme_completion cqe = {
-			.status = cpu_to_le16(NVME_SC_ABORT_REQ << 1),
-		};
+	cmd = blk_mq_rq_to_pdu(req);
 
-		if (timeout && !time_after(now, info[cmdid].timeout))
-			continue;
-		if (info[cmdid].ctx == CMD_CTX_CANCELLED)
-			continue;
-		if (timeout && info[cmdid].ctx == CMD_CTX_ASYNC)
-			continue;
-		if (timeout && nvmeq->dev->initialized) {
-			nvme_abort_cmd(cmdid, nvmeq);
-			continue;
-		}
-		dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n", cmdid,
-								nvmeq->qid);
-		ctx = cancel_cmdid(nvmeq, cmdid, &fn);
-		fn(nvmeq, ctx, &cqe);
-	}
+	if (cmd->ctx == CMD_CTX_CANCELLED)
+		return;
+
+	dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n",
+						req->tag, nvmeq->qid);
+	ctx = cancel_cmd_info(cmd, &fn);
+	fn(nvmeq, ctx, &cqe);
 }
 
-static void nvme_free_queue(struct nvme_queue *nvmeq)
+static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 {
-	spin_lock_irq(&nvmeq->q_lock);
-	while (bio_list_peek(&nvmeq->sq_cong)) {
-		struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
-		bio_endio(bio, -EIO);
-	}
-	while (!list_empty(&nvmeq->iod_bio)) {
-		static struct nvme_completion cqe = {
-			.status = cpu_to_le16(
-				(NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1),
-		};
-		struct nvme_iod *iod = list_first_entry(&nvmeq->iod_bio,
-							struct nvme_iod,
-							node);
-		list_del(&iod->node);
-		bio_completion(nvmeq, iod, &cqe);
-	}
-	spin_unlock_irq(&nvmeq->q_lock);
+	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
+	struct nvme_queue *nvmeq = cmd->nvmeq;
+
+	dev_warn(nvmeq->q_dmadev, "Timeout I/O %d QID %d\n", req->tag,
+							nvmeq->qid);
+	if (nvmeq->dev->initialized)
+		nvme_abort_req(req);
+
+	/*
+	 * The aborted req will be completed on receiving the abort req.
+	 * We enable the timer again. If hit twice, it'll cause a device reset,
+	 * as the device then is in a faulty state.
+	 */
+	return BLK_EH_RESET_TIMER;
+}
 
+static void nvme_free_queue(struct nvme_queue *nvmeq)
+{
 	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
 				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
 	dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
 					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
-	if (nvmeq->qid)
-		free_cpumask_var(nvmeq->cpu_mask);
 	kfree(nvmeq);
 }
 
@@ -1243,10 +1108,10 @@ static void nvme_free_queues(struct nvme_dev *dev, int lowest)
 	int i;
 
 	for (i = dev->queue_count - 1; i >= lowest; i--) {
-		nvmeq = raw_nvmeq(dev, i);
-		RCU_INIT_POINTER(dev->queues[i], NULL);
+		struct nvme_queue *nvmeq = dev->queues[i];
 		llist_add(&nvmeq->node, &q_list);
 		dev->queue_count--;
+		dev->queues[i] = NULL;
 	}
 	synchronize_rcu();
 	entry = llist_del_all(&q_list);
@@ -1257,19 +1122,12 @@ static void nvme_free_queues(struct nvme_dev *dev, int lowest)
 /**
  * nvme_suspend_queue - put queue into suspended state
  * @nvmeq - queue to suspend
- *
- * Returns 1 if already suspended, 0 otherwise.
  */
 static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 {
 	int vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
 
 	spin_lock_irq(&nvmeq->q_lock);
-	if (nvmeq->q_suspended) {
-		spin_unlock_irq(&nvmeq->q_lock);
-		return 1;
-	}
-	nvmeq->q_suspended = 1;
 	nvmeq->dev->online_queues--;
 	spin_unlock_irq(&nvmeq->q_lock);
 
@@ -1281,15 +1139,18 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 
 static void nvme_clear_queue(struct nvme_queue *nvmeq)
 {
+	struct blk_mq_hw_ctx *hctx = nvmeq->hctx;
+
 	spin_lock_irq(&nvmeq->q_lock);
 	nvme_process_cq(nvmeq);
-	nvme_cancel_ios(nvmeq, false);
+	if (hctx && hctx->tags)
+		blk_mq_tag_busy_iter(hctx, nvme_cancel_queue_ios, nvmeq);
 	spin_unlock_irq(&nvmeq->q_lock);
 }
 
 static void nvme_disable_queue(struct nvme_dev *dev, int qid)
 {
-	struct nvme_queue *nvmeq = raw_nvmeq(dev, qid);
+	struct nvme_queue *nvmeq = dev->queues[qid];
 
 	if (!nvmeq)
 		return;
@@ -1309,8 +1170,7 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 							int depth, int vector)
 {
 	struct device *dmadev = &dev->pci_dev->dev;
-	unsigned extra = nvme_queue_extra(depth);
-	struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq) + extra, GFP_KERNEL);
+	struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq), GFP_KERNEL);
 	if (!nvmeq)
 		return NULL;
 
@@ -1324,9 +1184,6 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	if (!nvmeq->sq_cmds)
 		goto free_cqdma;
 
-	if (qid && !zalloc_cpumask_var(&nvmeq->cpu_mask, GFP_KERNEL))
-		goto free_sqdma;
-
 	nvmeq->q_dmadev = dmadev;
 	nvmeq->dev = dev;
 	snprintf(nvmeq->irqname, sizeof(nvmeq->irqname), "nvme%dq%d",
@@ -1334,22 +1191,15 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	spin_lock_init(&nvmeq->q_lock);
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
-	init_waitqueue_head(&nvmeq->sq_full);
-	bio_list_init(&nvmeq->sq_cong);
-	INIT_LIST_HEAD(&nvmeq->iod_bio);
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
 	nvmeq->q_depth = depth;
 	nvmeq->cq_vector = vector;
 	nvmeq->qid = qid;
-	nvmeq->q_suspended = 1;
 	dev->queue_count++;
-	rcu_assign_pointer(dev->queues[qid], nvmeq);
+	dev->queues[qid] = nvmeq;
 
 	return nvmeq;
 
- free_sqdma:
-	dma_free_coherent(dmadev, SQ_SIZE(depth), (void *)nvmeq->sq_cmds,
-							nvmeq->sq_dma_addr);
  free_cqdma:
 	dma_free_coherent(dmadev, CQ_SIZE(depth), (void *)nvmeq->cqes,
 							nvmeq->cq_dma_addr);
@@ -1372,18 +1222,13 @@ static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue *nvmeq,
 static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
 {
 	struct nvme_dev *dev = nvmeq->dev;
-	unsigned extra = nvme_queue_extra(nvmeq->q_depth);
 
 	spin_lock_irq(&nvmeq->q_lock);
-	init_waitqueue_entry(&nvmeq->sq_cong_wait, nvme_thread);
 	nvmeq->sq_tail = 0;
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
-	memset(nvmeq->cmdid_data, 0, extra);
 	memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
-	nvme_cancel_ios(nvmeq, false);
-	nvmeq->q_suspended = 0;
 	dev->online_queues++;
 	spin_unlock_irq(&nvmeq->q_lock);
 }
@@ -1486,6 +1331,52 @@ static int nvme_shutdown_ctrl(struct nvme_dev *dev)
 	return 0;
 }
 
+static struct blk_mq_ops nvme_mq_admin_ops = {
+	.queue_rq	= nvme_admin_queue_rq,
+	.map_queue	= blk_mq_map_queue,
+	.init_hctx	= nvme_admin_init_hctx,
+	.init_request	= nvme_admin_init_request,
+	.timeout	= nvme_timeout,
+};
+
+static struct blk_mq_ops nvme_mq_ops = {
+	.queue_rq	= nvme_queue_rq,
+	.map_queue	= blk_mq_map_queue,
+	.init_hctx	= nvme_init_hctx,
+	.init_request	= nvme_init_request,
+	.timeout	= nvme_timeout,
+};
+
+static int nvme_alloc_admin_tags(struct nvme_dev *dev)
+{
+	if (!dev->admin_q) {
+		dev->admin_tagset.ops = &nvme_mq_admin_ops;
+		dev->admin_tagset.nr_hw_queues = 1;
+		dev->admin_tagset.queue_depth = NVME_AQ_DEPTH - 1;
+		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
+		dev->admin_tagset.numa_node = dev_to_node(&dev->pci_dev->dev);
+		dev->admin_tagset.cmd_size = sizeof(struct nvme_cmd_info);
+		dev->admin_tagset.driver_data = dev;
+
+		if (blk_mq_alloc_tag_set(&dev->admin_tagset))
+			return -ENOMEM;
+
+		dev->admin_q = blk_mq_init_queue(&dev->admin_tagset);
+		if (!dev->admin_q) {
+			blk_mq_free_tag_set(&dev->admin_tagset);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static void nvme_free_admin_tags(struct nvme_dev *dev)
+{
+	if (dev->admin_q)
+		blk_mq_free_tag_set(&dev->admin_tagset);
+}
+
 static int nvme_configure_admin_queue(struct nvme_dev *dev)
 {
 	int result;
@@ -1515,9 +1406,9 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	if (result < 0)
 		return result;
 
-	nvmeq = raw_nvmeq(dev, 0);
+	nvmeq = dev->queues[0];
 	if (!nvmeq) {
-		nvmeq = nvme_alloc_queue(dev, 0, 64, 0);
+		nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH, 0);
 		if (!nvmeq)
 			return -ENOMEM;
 	}
@@ -1538,13 +1429,23 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 
 	result = nvme_enable_ctrl(dev, cap);
 	if (result)
-		return result;
+		goto free_nvmeq;
+
+	result = nvme_alloc_admin_tags(dev);
+	if (result)
+		goto free_nvmeq;
 
 	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
 	if (result)
-		return result;
+		goto free_tags;
 
 	return result;
+
+ free_tags:
+	nvme_free_admin_tags(dev);
+ free_nvmeq:
+	nvme_free_queues(dev, 0);
+	return result;
 }
 
 struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
@@ -1702,7 +1603,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	if (length != (io.nblocks + 1) << ns->lba_shift)
 		status = -ENOMEM;
 	else
-		status = nvme_submit_io_cmd(dev, &c, NULL);
+		status = nvme_submit_io_cmd(dev, ns, &c, NULL);
 
 	if (meta_len) {
 		if (status == NVME_SC_SUCCESS && !(io.opcode & 1)) {
@@ -1734,8 +1635,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	return status;
 }
 
-static int nvme_user_cmd(struct nvme_dev *dev,
-			struct nvme_passthru_cmd __user *ucmd, bool ioq)
+static int nvme_user_cmd(struct nvme_dev *dev, struct nvme_ns *ns,
+			struct nvme_passthru_cmd __user *ucmd)
 {
 	struct nvme_passthru_cmd cmd;
 	struct nvme_command c;
@@ -1774,13 +1675,23 @@ static int nvme_user_cmd(struct nvme_dev *dev,
 
 	timeout = cmd.timeout_ms ? msecs_to_jiffies(cmd.timeout_ms) :
 								ADMIN_TIMEOUT;
+
 	if (length != cmd.data_len)
 		status = -ENOMEM;
-	else if (ioq)
-		status = nvme_submit_sync_cmd(dev, this_cpu_read(*dev->io_queue), &c,
-							&cmd.result, timeout);
-	else
-		status = nvme_submit_sync_cmd(dev, 0, &c, &cmd.result, timeout);
+	else if (ns) {
+		struct request *req;
+
+		req = blk_mq_alloc_request(ns->queue, WRITE,
+						(GFP_KERNEL|__GFP_WAIT), false);
+		if (!req)
+			status = -ENOMEM;
+		else {
+			status = nvme_submit_sync_cmd(req, &c, &cmd.result,
+								timeout);
+			blk_put_request(req);
+		}
+	} else
+		status = __nvme_submit_admin_cmd(dev, &c, &cmd.result, timeout);
 
 	if (cmd.data_len) {
 		nvme_unmap_user_pages(dev, cmd.opcode & 1, iod);
@@ -1804,9 +1715,9 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
 		force_successful_syscall_return();
 		return ns->ns_id;
 	case NVME_IOCTL_ADMIN_CMD:
-		return nvme_user_cmd(ns->dev, (void __user *)arg, false);
+		return nvme_user_cmd(ns->dev, NULL, (void __user *)arg);
 	case NVME_IOCTL_IO_CMD:
-		return nvme_user_cmd(ns->dev, (void __user *)arg, true);
+		return nvme_user_cmd(ns->dev, ns, (void __user *)arg);
 	case NVME_IOCTL_SUBMIT_IO:
 		return nvme_submit_io(ns, (void __user *)arg);
 	case SG_GET_VERSION_NUM:
@@ -1906,62 +1817,6 @@ static const struct block_device_operations nvme_fops = {
 	.revalidate_disk= nvme_revalidate_disk,
 };
 
-static void nvme_resubmit_iods(struct nvme_queue *nvmeq)
-{
-	struct nvme_iod *iod, *next;
-
-	list_for_each_entry_safe(iod, next, &nvmeq->iod_bio, node) {
-		if (unlikely(nvme_submit_iod(nvmeq, iod)))
-			break;
-		list_del(&iod->node);
-		if (bio_list_empty(&nvmeq->sq_cong) &&
-						list_empty(&nvmeq->iod_bio))
-			remove_wait_queue(&nvmeq->sq_full,
-						&nvmeq->sq_cong_wait);
-	}
-}
-
-static void nvme_resubmit_bios(struct nvme_queue *nvmeq)
-{
-	while (bio_list_peek(&nvmeq->sq_cong)) {
-		struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
-		struct nvme_ns *ns = bio->bi_bdev->bd_disk->private_data;
-
-		if (bio_list_empty(&nvmeq->sq_cong) &&
-						list_empty(&nvmeq->iod_bio))
-			remove_wait_queue(&nvmeq->sq_full,
-							&nvmeq->sq_cong_wait);
-		if (nvme_submit_bio_queue(nvmeq, ns, bio)) {
-			if (!waitqueue_active(&nvmeq->sq_full))
-				add_wait_queue(&nvmeq->sq_full,
-							&nvmeq->sq_cong_wait);
-			bio_list_add_head(&nvmeq->sq_cong, bio);
-			break;
-		}
-	}
-}
-
-static int nvme_submit_async_req(struct nvme_queue *nvmeq)
-{
-	struct nvme_command *c;
-	int cmdid;
-
-	cmdid = alloc_cmdid(nvmeq, CMD_CTX_ASYNC, special_completion, 0);
-	if (cmdid < 0)
-		return cmdid;
-
-	c = &nvmeq->sq_cmds[nvmeq->sq_tail];
-	memset(c, 0, sizeof(*c));
-	c->common.opcode = nvme_admin_async_event;
-	c->common.command_id = cmdid;
-
-	if (++nvmeq->sq_tail == nvmeq->q_depth)
-		nvmeq->sq_tail = 0;
-	writel(nvmeq->sq_tail, nvmeq->q_db);
-
-	return 0;
-}
-
 static int nvme_kthread(void *data)
 {
 	struct nvme_dev *dev, *next;
@@ -1977,34 +1832,26 @@ static int nvme_kthread(void *data)
 					continue;
 				list_del_init(&dev->node);
 				dev_warn(&dev->pci_dev->dev,
-					"Failed status, reset controller\n");
+					"Failed status: %x, reset controller\n",
+					readl(&dev->bar->csts));
 				dev->reset_workfn = nvme_reset_failed_dev;
 				queue_work(nvme_workq, &dev->reset_work);
 				continue;
 			}
-			rcu_read_lock();
 			for (i = 0; i < dev->queue_count; i++) {
-				struct nvme_queue *nvmeq =
-						rcu_dereference(dev->queues[i]);
+				struct nvme_queue *nvmeq = dev->queues[i];
 				if (!nvmeq)
 					continue;
 				spin_lock_irq(&nvmeq->q_lock);
-				if (nvmeq->q_suspended)
-					goto unlock;
 				nvme_process_cq(nvmeq);
-				nvme_cancel_ios(nvmeq, true);
-				nvme_resubmit_bios(nvmeq);
-				nvme_resubmit_iods(nvmeq);
 
 				while ((i == 0) && (dev->event_limit > 0)) {
-					if (nvme_submit_async_req(nvmeq))
+					if (nvme_submit_async_admin_req(dev))
 						break;
 					dev->event_limit--;
 				}
- unlock:
 				spin_unlock_irq(&nvmeq->q_lock);
 			}
-			rcu_read_unlock();
 		}
 		spin_unlock(&dev_list_lock);
 		schedule_timeout(round_jiffies_relative(HZ));
@@ -2027,29 +1874,29 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
 {
 	struct nvme_ns *ns;
 	struct gendisk *disk;
+	int node = dev_to_node(&dev->pci_dev->dev);
 	int lbaf;
 
 	if (rt->attributes & NVME_LBART_ATTRIB_HIDE)
 		return NULL;
 
-	ns = kzalloc(sizeof(*ns), GFP_KERNEL);
+	ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
 	if (!ns)
 		return NULL;
-	ns->queue = blk_alloc_queue(GFP_KERNEL);
+	ns->queue = blk_mq_init_queue(&dev->tagset);
 	if (!ns->queue)
 		goto out_free_ns;
-	ns->queue->queue_flags = QUEUE_FLAG_DEFAULT;
-	queue_flag_clear_unlocked(QUEUE_FLAG_STACKABLE, ns->queue);
 	queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
-	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, ns->queue);
-	blk_queue_make_request(ns->queue, nvme_make_request);
+	queue_flag_set_unlocked(QUEUE_FLAG_SG_GAPS, ns->queue);
+	queue_flag_clear_unlocked(QUEUE_FLAG_IO_STAT, ns->queue);
 	ns->dev = dev;
 	ns->queue->queuedata = ns;
 
-	disk = alloc_disk(0);
+	disk = alloc_disk_node(0, node);
 	if (!disk)
 		goto out_free_queue;
+
 	ns->ns_id = nsid;
 	ns->disk = disk;
 	lbaf = id->flbas & 0xf;
@@ -2058,6 +1905,8 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
 	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
 	if (dev->max_hw_sectors)
 		blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
+	if (dev->stripe_size)
+		blk_queue_chunk_sectors(ns->queue, dev->stripe_size >> 9);
 	if (dev->vwc & NVME_CTRL_VWC_PRESENT)
 		blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA);
 
@@ -2083,143 +1932,19 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
 	return NULL;
 }
 
-static int nvme_find_closest_node(int node)
-{
-	int n, val, min_val = INT_MAX, best_node = node;
-
-	for_each_online_node(n) {
-		if (n == node)
-			continue;
-		val = node_distance(node, n);
-		if (val < min_val) {
-			min_val = val;
-			best_node = n;
-		}
-	}
-	return best_node;
-}
-
-static void nvme_set_queue_cpus(cpumask_t *qmask, struct nvme_queue *nvmeq,
-								int count)
-{
-	int cpu;
-	for_each_cpu(cpu, qmask) {
-		if (cpumask_weight(nvmeq->cpu_mask) >= count)
-			break;
-		if (!cpumask_test_and_set_cpu(cpu, nvmeq->cpu_mask))
-			*per_cpu_ptr(nvmeq->dev->io_queue, cpu) = nvmeq->qid;
-	}
-}
-
-static void nvme_add_cpus(cpumask_t *mask, const cpumask_t *unassigned_cpus,
-	const cpumask_t *new_mask, struct nvme_queue *nvmeq, int cpus_per_queue)
-{
-	int next_cpu;
-	for_each_cpu(next_cpu, new_mask) {
-		cpumask_or(mask, mask, get_cpu_mask(next_cpu));
-		cpumask_or(mask, mask, topology_thread_cpumask(next_cpu));
-		cpumask_and(mask, mask, unassigned_cpus);
-		nvme_set_queue_cpus(mask, nvmeq, cpus_per_queue);
-	}
-}
-
 static void nvme_create_io_queues(struct nvme_dev *dev)
 {
-	unsigned i, max;
+	unsigned i;
 
-	max = min(dev->max_qid, num_online_cpus());
-	for (i = dev->queue_count; i <= max; i++)
+	for (i = dev->queue_count; i <= dev->max_qid; i++)
 		if (!nvme_alloc_queue(dev, i, dev->q_depth, i - 1))
 			break;
 
-	max = min(dev->queue_count - 1, num_online_cpus());
-	for (i = dev->online_queues; i <= max; i++)
-		if (nvme_create_queue(raw_nvmeq(dev, i), i))
+	for (i = dev->online_queues; i <= dev->queue_count - 1; i++)
+		if (nvme_create_queue(dev->queues[i], i))
 			break;
 }
 
-/*
- * If there are fewer queues than online cpus, this will try to optimally
- * assign a queue to multiple cpus by grouping cpus that are "close" together:
- * thread siblings, core, socket, closest node, then whatever else is
- * available.
- */
-static void nvme_assign_io_queues(struct nvme_dev *dev)
-{
-	unsigned cpu, cpus_per_queue, queues, remainder, i;
-	cpumask_var_t unassigned_cpus;
-
-	nvme_create_io_queues(dev);
-
-	queues = min(dev->online_queues - 1, num_online_cpus());
-	if (!queues)
-		return;
-
-	cpus_per_queue = num_online_cpus() / queues;
-	remainder = queues - (num_online_cpus() - queues * cpus_per_queue);
-
-	if (!alloc_cpumask_var(&unassigned_cpus, GFP_KERNEL))
-		return;
-
-	cpumask_copy(unassigned_cpus, cpu_online_mask);
-	cpu = cpumask_first(unassigned_cpus);
-	for (i = 1; i <= queues; i++) {
-		struct nvme_queue *nvmeq = lock_nvmeq(dev, i);
-		cpumask_t mask;
-
-		cpumask_clear(nvmeq->cpu_mask);
-		if (!cpumask_weight(unassigned_cpus)) {
-			unlock_nvmeq(nvmeq);
-			break;
-		}
-
-		mask = *get_cpu_mask(cpu);
-		nvme_set_queue_cpus(&mask, nvmeq, cpus_per_queue);
-		if (cpus_weight(mask) < cpus_per_queue)
-			nvme_add_cpus(&mask, unassigned_cpus,
-				topology_thread_cpumask(cpu),
-				nvmeq, cpus_per_queue);
-		if (cpus_weight(mask) < cpus_per_queue)
-			nvme_add_cpus(&mask, unassigned_cpus,
-				topology_core_cpumask(cpu),
-				nvmeq, cpus_per_queue);
-		if (cpus_weight(mask) < cpus_per_queue)
-			nvme_add_cpus(&mask, unassigned_cpus,
-				cpumask_of_node(cpu_to_node(cpu)),
-				nvmeq, cpus_per_queue);
-		if (cpus_weight(mask) < cpus_per_queue)
-			nvme_add_cpus(&mask, unassigned_cpus,
-				cpumask_of_node(
-					nvme_find_closest_node(
-						cpu_to_node(cpu))),
-				nvmeq, cpus_per_queue);
-		if (cpus_weight(mask) < cpus_per_queue)
-			nvme_add_cpus(&mask, unassigned_cpus,
-				unassigned_cpus,
-				nvmeq, cpus_per_queue);
-
-		WARN(cpumask_weight(nvmeq->cpu_mask) != cpus_per_queue,
-			"nvme%d qid:%d mis-matched queue-to-cpu assignment\n",
-			dev->instance, i);
-
-		irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
-							nvmeq->cpu_mask);
-		cpumask_andnot(unassigned_cpus, unassigned_cpus,
-						nvmeq->cpu_mask);
-		cpu = cpumask_next(cpu, unassigned_cpus);
-		if (remainder && !--remainder)
-			cpus_per_queue++;
-		unlock_nvmeq(nvmeq);
-	}
-	WARN(cpumask_weight(unassigned_cpus), "nvme%d unassigned online cpus\n",
-								dev->instance);
-	i = 0;
-	cpumask_andnot(unassigned_cpus, cpu_possible_mask, cpu_online_mask);
-	for_each_cpu(cpu, unassigned_cpus)
-		*per_cpu_ptr(dev->io_queue, cpu) = (i++ % queues) + 1;
-	free_cpumask_var(unassigned_cpus);
-}
-
 static int set_queue_count(struct nvme_dev *dev, int count)
 {
 	int status;
@@ -2243,33 +1968,9 @@ static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
 	return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
 }
 
-static void nvme_cpu_workfn(struct work_struct *work)
-{
-	struct nvme_dev *dev = container_of(work, struct nvme_dev, cpu_work);
-	if (dev->initialized)
-		nvme_assign_io_queues(dev);
-}
-
-static int nvme_cpu_notify(struct notifier_block *self,
-				unsigned long action, void *hcpu)
-{
-	struct nvme_dev *dev;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_DEAD:
-		spin_lock(&dev_list_lock);
-		list_for_each_entry(dev, &dev_list, node)
-			schedule_work(&dev->cpu_work);
-		spin_unlock(&dev_list_lock);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
 static int nvme_setup_io_queues(struct nvme_dev *dev)
 {
-	struct nvme_queue *adminq = raw_nvmeq(dev, 0);
+	struct nvme_queue *adminq = dev->queues[0];
 	struct pci_dev *pdev = dev->pci_dev;
 	int result, i, vecs, nr_io_queues, size;
 
@@ -2321,14 +2022,12 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	dev->max_qid = nr_io_queues;
 
 	result = queue_request_irq(dev, adminq, adminq->irqname);
-	if (result) {
-		adminq->q_suspended = 1;
+	if (result)
 		goto free_queues;
-	}
 
 	/* Free previously allocated queues that are no longer usable */
 	nvme_free_queues(dev, nr_io_queues + 1);
-	nvme_assign_io_queues(dev);
+	nvme_create_io_queues(dev);
 
 	return 0;
 
@@ -2378,8 +2077,30 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	if (ctrl->mdts)
 		dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9);
 	if ((pdev->vendor == PCI_VENDOR_ID_INTEL) &&
-			(pdev->device == 0x0953) && ctrl->vs[3])
+			(pdev->device == 0x0953) && ctrl->vs[3]) {
+		unsigned int max_hw_sectors;
+
 		dev->stripe_size = 1 << (ctrl->vs[3] + shift);
+		max_hw_sectors = dev->stripe_size >> (shift - 9);
+		if (dev->max_hw_sectors) {
+			dev->max_hw_sectors = min(max_hw_sectors,
+							dev->max_hw_sectors);
+		} else
+			dev->max_hw_sectors = max_hw_sectors;
+	}
+
+	dev->tagset.ops = &nvme_mq_ops;
+	dev->tagset.nr_hw_queues = dev->online_queues - 1;
+	dev->tagset.timeout = NVME_IO_TIMEOUT;
+	dev->tagset.numa_node = dev_to_node(&dev->pci_dev->dev);
+	dev->tagset.queue_depth =
+				min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
+	dev->tagset.cmd_size = sizeof(struct nvme_cmd_info);
+	dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
+	dev->tagset.driver_data = dev;
+
+	if (blk_mq_alloc_tag_set(&dev->tagset))
+		goto out;
 
 	id_ns = mem;
 	for (i = 1; i <= nn; i++) {
@@ -2529,7 +2250,8 @@ static int adapter_async_del_queue(struct nvme_queue *nvmeq, u8 opcode,
 	c.delete_queue.qid = cpu_to_le16(nvmeq->qid);
 
 	init_kthread_work(&nvmeq->cmdinfo.work, fn);
-	return nvme_submit_admin_cmd_async(nvmeq->dev, &c, &nvmeq->cmdinfo);
+	return nvme_submit_admin_async_cmd(nvmeq->dev, &c, &nvmeq->cmdinfo,
+								ADMIN_TIMEOUT);
 }
 
 static void nvme_del_cq_work_handler(struct kthread_work *work)
@@ -2592,7 +2314,7 @@ static void nvme_disable_io_queues(struct nvme_dev *dev)
 	atomic_set(&dq.refcount, 0);
 	dq.worker = &worker;
 	for (i = dev->queue_count - 1; i > 0; i--) {
-		struct nvme_queue *nvmeq = raw_nvmeq(dev, i);
+		struct nvme_queue *nvmeq = dev->queues[i];
 
 		if (nvme_suspend_queue(nvmeq))
 			continue;
@@ -2637,7 +2359,7 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 		csts = readl(&dev->bar->csts);
 	if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
 		for (i = dev->queue_count - 1; i >= 0; i--) {
-			struct nvme_queue *nvmeq = raw_nvmeq(dev, i);
+			struct nvme_queue *nvmeq = dev->queues[i];
 			nvme_suspend_queue(nvmeq);
 			nvme_clear_queue(nvmeq);
 		}
@@ -2649,6 +2371,12 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 	nvme_dev_unmap(dev);
 }
 
+static void nvme_dev_remove_admin(struct nvme_dev *dev)
+{
+	if (dev->admin_q && !blk_queue_dying(dev->admin_q))
+		blk_cleanup_queue(dev->admin_q);
+}
+
 static void nvme_dev_remove(struct nvme_dev *dev)
 {
 	struct nvme_ns *ns;
@@ -2736,7 +2464,7 @@ static void nvme_free_dev(struct kref *kref)
 
 	pci_dev_put(dev->pci_dev);
 	nvme_free_namespaces(dev);
-	free_percpu(dev->io_queue);
+	blk_mq_free_tag_set(&dev->tagset);
 	kfree(dev->queues);
 	kfree(dev->entry);
 	kfree(dev);
@@ -2761,11 +2489,16 @@ static int nvme_dev_release(struct inode *inode, struct file *f)
 static long nvme_dev_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 {
 	struct nvme_dev *dev = f->private_data;
+	struct nvme_ns *ns;
+
 	switch (cmd) {
 	case NVME_IOCTL_ADMIN_CMD:
-		return nvme_user_cmd(dev, (void __user *)arg, false);
+		return nvme_user_cmd(dev, NULL, (void __user *)arg);
 	case NVME_IOCTL_IO_CMD:
-		return nvme_user_cmd(dev, (void __user *)arg, true);
+		if (list_empty(&dev->namespaces))
+			return -ENOTTY;
+		ns = list_first_entry(&dev->namespaces, struct nvme_ns, list);
+		return nvme_user_cmd(dev, ns, (void __user *)arg);
 	default:
 		return -ENOTTY;
 	}
@@ -2779,6 +2512,22 @@ static const struct file_operations nvme_dev_fops = {
 	.compat_ioctl	= nvme_dev_ioctl,
 };
 
+static void nvme_set_irq_hints(struct nvme_dev *dev)
+{
+	struct nvme_queue *nvmeq;
+	int i;
+
+	for (i = 0; i < dev->online_queues; i++) {
+		nvmeq = dev->queues[i];
+
+		if (!nvmeq->hctx)
+			continue;
+
+		irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
+							nvmeq->hctx->cpumask);
+	}
+}
+
 static int nvme_dev_start(struct nvme_dev *dev)
 {
 	int result;
@@ -2810,12 +2559,15 @@ static int nvme_dev_start(struct nvme_dev *dev)
 		result = nvme_thread ? PTR_ERR(nvme_thread) : -EINTR;
 		goto disable;
 	}
-	nvme_init_queue(raw_nvmeq(dev, 0), 0);
+
+	nvme_init_queue(dev->queues[0], 0);
 
 	result = nvme_setup_io_queues(dev);
 	if (result)
 		goto disable;
 
+	nvme_set_irq_hints(dev);
+
 	return result;
 
  disable:
@@ -2866,7 +2618,7 @@ static void nvme_dev_reset(struct nvme_dev *dev)
 {
 	nvme_dev_shutdown(dev);
 	if (nvme_dev_resume(dev)) {
-		dev_err(&dev->pci_dev->dev, "Device failed to resume\n");
+		dev_warn(&dev->pci_dev->dev, "Device failed to resume\n");
 		kref_get(&dev->kref);
 		if (IS_ERR(kthread_run(nvme_remove_dead_ctrl, dev, "nvme%d",
 							dev->instance))) {
@@ -2891,28 +2643,28 @@ static void nvme_reset_workfn(struct work_struct *work)
 
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
-	int result = -ENOMEM;
+	int node, result = -ENOMEM;
 	struct nvme_dev *dev;
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	node = dev_to_node(&pdev->dev);
+	if (node == NUMA_NO_NODE)
+		set_dev_node(&pdev->dev, 0);
+
+	dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
 	if (!dev)
 		return -ENOMEM;
-	dev->entry = kcalloc(num_possible_cpus(), sizeof(*dev->entry),
-								GFP_KERNEL);
+	dev->entry = kzalloc_node(num_possible_cpus() * sizeof(*dev->entry),
+							GFP_KERNEL, node);
 	if (!dev->entry)
 		goto free;
-	dev->queues = kcalloc(num_possible_cpus() + 1, sizeof(void *),
-								GFP_KERNEL);
+	dev->queues = kzalloc_node((num_possible_cpus() + 1) * sizeof(void *),
+							GFP_KERNEL, node);
 	if (!dev->queues)
 		goto free;
-	dev->io_queue = alloc_percpu(unsigned short);
-	if (!dev->io_queue)
-		goto free;
 
 	INIT_LIST_HEAD(&dev->namespaces);
 	dev->reset_workfn = nvme_reset_failed_dev;
 	INIT_WORK(&dev->reset_work, nvme_reset_workfn);
-	INIT_WORK(&dev->cpu_work, nvme_cpu_workfn);
 	dev->pci_dev = pci_dev_get(pdev);
 	pci_set_drvdata(pdev, dev);
 	result = nvme_set_instance(dev);
@@ -2942,11 +2694,14 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (result)
 		goto remove;
 
+	nvme_set_irq_hints(dev);
+
 	dev->initialized = 1;
 	return 0;
 
  remove:
 	nvme_dev_remove(dev);
+	nvme_dev_remove_admin(dev);
 	nvme_free_namespaces(dev);
  shutdown:
 	nvme_dev_shutdown(dev);
@@ -2958,7 +2713,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
  put_pci:
 	pci_dev_put(dev->pci_dev);
  free:
-	free_percpu(dev->io_queue);
 	kfree(dev->queues);
 	kfree(dev->entry);
 	kfree(dev);
@@ -2991,11 +2745,12 @@ static void nvme_remove(struct pci_dev *pdev)
 
 	pci_set_drvdata(pdev, NULL);
 	flush_work(&dev->reset_work);
-	flush_work(&dev->cpu_work);
 	misc_deregister(&dev->miscdev);
+	nvme_dev_remove(dev);
 	nvme_dev_shutdown(dev);
+	nvme_dev_remove_admin(dev);
 	nvme_free_queues(dev, 0);
-	nvme_dev_remove(dev);
+	nvme_free_admin_tags(dev);
 	nvme_release_instance(dev);
 	nvme_release_prp_pools(dev);
 	kref_put(&dev->kref, nvme_free_dev);
@@ -3079,18 +2834,11 @@ static int __init nvme_init(void)
 	else if (result > 0)
 		nvme_major = result;
 
-	nvme_nb.notifier_call = &nvme_cpu_notify;
-	result = register_hotcpu_notifier(&nvme_nb);
-	if (result)
-		goto unregister_blkdev;
-
 	result = pci_register_driver(&nvme_driver);
 	if (result)
-		goto unregister_hotcpu;
+		goto unregister_blkdev;
 	return 0;
 
- unregister_hotcpu:
-	unregister_hotcpu_notifier(&nvme_nb);
  unregister_blkdev:
 	unregister_blkdev(nvme_major, "nvme");
  kill_workq:
diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c
index 046ae3321c5..49f86d1a5aa 100644
--- a/drivers/block/nvme-scsi.c
+++ b/drivers/block/nvme-scsi.c
@@ -2105,7 +2105,7 @@ static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 
 		nvme_offset += unit_num_blocks;
 
-		nvme_sc = nvme_submit_io_cmd(dev, &c, NULL);
+		nvme_sc = nvme_submit_io_cmd(dev, ns, &c, NULL);
 		if (nvme_sc != NVME_SC_SUCCESS) {
 			nvme_unmap_user_pages(dev,
 				(is_write) ? DMA_TO_DEVICE : DMA_FROM_DEVICE,
@@ -2658,7 +2658,7 @@ static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 			c.common.opcode = nvme_cmd_flush;
 			c.common.nsid = cpu_to_le32(ns->ns_id);
 
-			nvme_sc = nvme_submit_io_cmd(ns->dev, &c, NULL);
+			nvme_sc = nvme_submit_io_cmd(ns->dev, ns, &c, NULL);
 			res = nvme_trans_status_code(hdr, nvme_sc);
 			if (res)
 				goto out;
@@ -2686,7 +2686,7 @@ static int nvme_trans_synchronize_cache(struct nvme_ns *ns,
 	c.common.opcode = nvme_cmd_flush;
 	c.common.nsid = cpu_to_le32(ns->ns_id);
 
-	nvme_sc = nvme_submit_io_cmd(ns->dev, &c, NULL);
+	nvme_sc = nvme_submit_io_cmd(ns->dev, ns, &c, NULL);
 
 	res = nvme_trans_status_code(hdr, nvme_sc);
 	if (res)
@@ -2894,7 +2894,7 @@ static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	c.dsm.nr = cpu_to_le32(ndesc - 1);
 	c.dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
 
-	nvme_sc = nvme_submit_io_cmd(dev, &c, NULL);
+	nvme_sc = nvme_submit_io_cmd(dev, ns, &c, NULL);
 	res = nvme_trans_status_code(hdr, nvme_sc);
 
 	dma_free_coherent(&dev->pci_dev->dev, ndesc * sizeof(*range),
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index ed09074e555..258945fcabf 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -19,6 +19,7 @@
 #include <linux/pci.h>
 #include <linux/miscdevice.h>
 #include <linux/kref.h>
+#include <linux/blk-mq.h>
 
 struct nvme_bar {
 	__u64			cap;	/* Controller Capabilities */
@@ -71,8 +72,10 @@ extern unsigned char nvme_io_timeout;
  */
 struct nvme_dev {
 	struct list_head node;
-	struct nvme_queue __rcu **queues;
-	unsigned short __percpu *io_queue;
+	struct nvme_queue **queues;
+	struct request_queue *admin_q;
+	struct blk_mq_tag_set tagset;
+	struct blk_mq_tag_set admin_tagset;
 	u32 __iomem *dbs;
 	struct pci_dev *pci_dev;
 	struct dma_pool *prp_page_pool;
@@ -91,7 +94,6 @@ struct nvme_dev {
 	struct miscdevice miscdev;
 	work_func_t reset_workfn;
 	struct work_struct reset_work;
-	struct work_struct cpu_work;
 	char name[12];
 	char serial[20];
 	char model[40];
@@ -135,7 +137,6 @@ struct nvme_iod {
 	int offset;		/* Of PRP list */
 	int nents;		/* Used in scatterlist */
 	int length;		/* Of data, in bytes */
-	unsigned long start_time;
 	dma_addr_t first_dma;
 	struct list_head node;
 	struct scatterlist sg[0];
@@ -153,12 +154,14 @@ static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
  */
 void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod);
 
-int nvme_setup_prps(struct nvme_dev *, struct nvme_iod *, int , gfp_t);
+int nvme_setup_prps(struct nvme_dev *, struct nvme_iod *, int, gfp_t);
 struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
 				unsigned long addr, unsigned length);
 void nvme_unmap_user_pages(struct nvme_dev *dev, int write,
 			struct nvme_iod *iod);
-int nvme_submit_io_cmd(struct nvme_dev *, struct nvme_command *, u32 *);
+int nvme_submit_io_cmd(struct nvme_dev *, struct nvme_ns *,
+						struct nvme_command *, u32 *);
+int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns);
 int nvme_submit_admin_cmd(struct nvme_dev *, struct nvme_command *,
 							u32 *result);
 int nvme_identify(struct nvme_dev *, unsigned nsid, unsigned cns,
-- 
cgit v1.2.3-70-g09d2


From ffdcd955c3078af3ce117edcfce80fde1a512bed Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Tue, 21 Oct 2014 13:33:55 +0200
Subject: ACPI: Add support for device specific properties

Device Tree is used in many embedded systems to describe the system
configuration to the OS. It supports attaching properties or name-value
pairs to the devices it describe. With these properties one can pass
additional information to the drivers that would not be available
otherwise.

ACPI is another configuration mechanism (among other things) typically
seen, but not limited to, x86 machines. ACPI allows passing arbitrary
data from methods but there has not been mechanism equivalent to Device
Tree until the introduction of _DSD in the recent publication of the
ACPI 5.1 specification.

In order to facilitate ACPI usage in systems where Device Tree is
typically used, it would be beneficial to standardize a way to retrieve
Device Tree style properties from ACPI devices, which is what we do in
this patch.

If a given device described in ACPI namespace wants to export properties it
must implement _DSD method (Device Specific Data, introduced with ACPI 5.1)
that returns the properties in a package of packages. For example:

	Name (_DSD, Package () {
		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
		Package () {
			Package () {"name1", <VALUE1>},
			Package () {"name2", <VALUE2>},
			...
		}
	})

The UUID reserved for properties is daffd814-6eba-4d8c-8a91-bc9bbf4aa301
and is documented in the ACPI 5.1 companion document called "_DSD
Implementation Guide" [1], [2].

We add several helper functions that can be used to extract these
properties and convert them to different Linux data types.

The ultimate goal is that we only have one device property API that
retrieves the requested properties from Device Tree or from ACPI
transparent to the caller.

[1] http://www.uefi.org/sites/default/files/resources/_DSD-implementation-guide-toplevel.htm
[2] http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf

Reviewed-by: Hanjun Guo <hanjun.guo@linaro.org>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Reviewed-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Darren Hart <dvhart@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/Makefile   |   1 +
 drivers/acpi/internal.h |   6 +
 drivers/acpi/property.c | 364 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/acpi/scan.c     |   2 +
 include/acpi/acpi_bus.h |   7 +
 include/linux/acpi.h    |  40 ++++++
 6 files changed, 420 insertions(+)
 create mode 100644 drivers/acpi/property.c

(limited to 'include')

diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index c3b2fcb729f..6d11522f0e4 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -47,6 +47,7 @@ acpi-y				+= int340x_thermal.o
 acpi-y				+= power.o
 acpi-y				+= event.o
 acpi-y				+= sysfs.o
+acpi-y				+= property.o
 acpi-$(CONFIG_X86)		+= acpi_cmos_rtc.o
 acpi-$(CONFIG_DEBUG_FS)		+= debugfs.o
 acpi-$(CONFIG_ACPI_NUMA)	+= numa.o
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 447f6d679b2..163e82f536f 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -173,4 +173,10 @@ static inline void suspend_nvs_restore(void) {}
 bool acpi_osi_is_win8(void);
 #endif
 
+/*--------------------------------------------------------------------------
+				Device properties
+  -------------------------------------------------------------------------- */
+void acpi_init_properties(struct acpi_device *adev);
+void acpi_free_properties(struct acpi_device *adev);
+
 #endif /* _ACPI_INTERNAL_H_ */
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
new file mode 100644
index 00000000000..c4a3e800e82
--- /dev/null
+++ b/drivers/acpi/property.c
@@ -0,0 +1,364 @@
+/*
+ * ACPI device specific properties support.
+ *
+ * Copyright (C) 2014, Intel Corporation
+ * All rights reserved.
+ *
+ * Authors: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *          Darren Hart <dvhart@linux.intel.com>
+ *          Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/export.h>
+
+#include "internal.h"
+
+/* ACPI _DSD device properties UUID: daffd814-6eba-4d8c-8a91-bc9bbf4aa301 */
+static const u8 prp_uuid[16] = {
+	0x14, 0xd8, 0xff, 0xda, 0xba, 0x6e, 0x8c, 0x4d,
+	0x8a, 0x91, 0xbc, 0x9b, 0xbf, 0x4a, 0xa3, 0x01
+};
+
+static bool acpi_property_value_ok(const union acpi_object *value)
+{
+	int j;
+
+	/*
+	 * The value must be an integer, a string, a reference, or a package
+	 * whose every element must be an integer, a string, or a reference.
+	 */
+	switch (value->type) {
+	case ACPI_TYPE_INTEGER:
+	case ACPI_TYPE_STRING:
+	case ACPI_TYPE_LOCAL_REFERENCE:
+		return true;
+
+	case ACPI_TYPE_PACKAGE:
+		for (j = 0; j < value->package.count; j++)
+			switch (value->package.elements[j].type) {
+			case ACPI_TYPE_INTEGER:
+			case ACPI_TYPE_STRING:
+			case ACPI_TYPE_LOCAL_REFERENCE:
+				continue;
+
+			default:
+				return false;
+			}
+
+		return true;
+	}
+	return false;
+}
+
+static bool acpi_properties_format_valid(const union acpi_object *properties)
+{
+	int i;
+
+	for (i = 0; i < properties->package.count; i++) {
+		const union acpi_object *property;
+
+		property = &properties->package.elements[i];
+		/*
+		 * Only two elements allowed, the first one must be a string and
+		 * the second one has to satisfy certain conditions.
+		 */
+		if (property->package.count != 2
+		    || property->package.elements[0].type != ACPI_TYPE_STRING
+		    || !acpi_property_value_ok(&property->package.elements[1]))
+			return false;
+	}
+	return true;
+}
+
+void acpi_init_properties(struct acpi_device *adev)
+{
+	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
+	const union acpi_object *desc;
+	acpi_status status;
+	int i;
+
+	status = acpi_evaluate_object_typed(adev->handle, "_DSD", NULL, &buf,
+					    ACPI_TYPE_PACKAGE);
+	if (ACPI_FAILURE(status))
+		return;
+
+	desc = buf.pointer;
+	if (desc->package.count % 2)
+		goto fail;
+
+	/* Look for the device properties UUID. */
+	for (i = 0; i < desc->package.count; i += 2) {
+		const union acpi_object *uuid, *properties;
+
+		uuid = &desc->package.elements[i];
+		properties = &desc->package.elements[i + 1];
+
+		/*
+		 * The first element must be a UUID and the second one must be
+		 * a package.
+		 */
+		if (uuid->type != ACPI_TYPE_BUFFER || uuid->buffer.length != 16
+		    || properties->type != ACPI_TYPE_PACKAGE)
+			break;
+
+		if (memcmp(uuid->buffer.pointer, prp_uuid, sizeof(prp_uuid)))
+			continue;
+
+		/*
+		 * We found the matching UUID. Now validate the format of the
+		 * package immediately following it.
+		 */
+		if (!acpi_properties_format_valid(properties))
+			break;
+
+		adev->data.pointer = buf.pointer;
+		adev->data.properties = properties;
+		return;
+	}
+
+ fail:
+	dev_warn(&adev->dev, "Returned _DSD data is not valid, skipping\n");
+	ACPI_FREE(buf.pointer);
+}
+
+void acpi_free_properties(struct acpi_device *adev)
+{
+	ACPI_FREE((void *)adev->data.pointer);
+	adev->data.pointer = NULL;
+	adev->data.properties = NULL;
+}
+
+/**
+ * acpi_dev_get_property - return an ACPI property with given name
+ * @adev: ACPI device to get property
+ * @name: Name of the property
+ * @type: Expected property type
+ * @obj: Location to store the property value (if not %NULL)
+ *
+ * Look up a property with @name and store a pointer to the resulting ACPI
+ * object at the location pointed to by @obj if found.
+ *
+ * Callers must not attempt to free the returned objects.  These objects will be
+ * freed by the ACPI core automatically during the removal of @adev.
+ *
+ * Return: %0 if property with @name has been found (success),
+ *         %-EINVAL if the arguments are invalid,
+ *         %-ENODATA if the property doesn't exist,
+ *         %-EPROTO if the property value type doesn't match @type.
+ */
+int acpi_dev_get_property(struct acpi_device *adev, const char *name,
+			  acpi_object_type type, const union acpi_object **obj)
+{
+	const union acpi_object *properties;
+	int i;
+
+	if (!adev || !name)
+		return -EINVAL;
+
+	if (!adev->data.pointer || !adev->data.properties)
+		return -ENODATA;
+
+	properties = adev->data.properties;
+	for (i = 0; i < properties->package.count; i++) {
+		const union acpi_object *propname, *propvalue;
+		const union acpi_object *property;
+
+		property = &properties->package.elements[i];
+
+		propname = &property->package.elements[0];
+		propvalue = &property->package.elements[1];
+
+		if (!strcmp(name, propname->string.pointer)) {
+			if (type != ACPI_TYPE_ANY && propvalue->type != type)
+				return -EPROTO;
+			else if (obj)
+				*obj = propvalue;
+
+			return 0;
+		}
+	}
+	return -ENODATA;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_get_property);
+
+/**
+ * acpi_dev_get_property_array - return an ACPI array property with given name
+ * @adev: ACPI device to get property
+ * @name: Name of the property
+ * @type: Expected type of array elements
+ * @obj: Location to store a pointer to the property value (if not NULL)
+ *
+ * Look up an array property with @name and store a pointer to the resulting
+ * ACPI object at the location pointed to by @obj if found.
+ *
+ * Callers must not attempt to free the returned objects.  Those objects will be
+ * freed by the ACPI core automatically during the removal of @adev.
+ *
+ * Return: %0 if array property (package) with @name has been found (success),
+ *         %-EINVAL if the arguments are invalid,
+ *         %-ENODATA if the property doesn't exist,
+ *         %-EPROTO if the property is not a package or the type of its elements
+ *           doesn't match @type.
+ */
+int acpi_dev_get_property_array(struct acpi_device *adev, const char *name,
+				acpi_object_type type,
+				const union acpi_object **obj)
+{
+	const union acpi_object *prop;
+	int ret, i;
+
+	ret = acpi_dev_get_property(adev, name, ACPI_TYPE_PACKAGE, &prop);
+	if (ret)
+		return ret;
+
+	if (type != ACPI_TYPE_ANY) {
+		/* Check that all elements are of correct type. */
+		for (i = 0; i < prop->package.count; i++)
+			if (prop->package.elements[i].type != type)
+				return -EPROTO;
+	}
+	if (obj)
+		*obj = prop;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_get_property_array);
+
+/**
+ * acpi_dev_get_property_reference - returns handle to the referenced object
+ * @adev: ACPI device to get property
+ * @name: Name of the property
+ * @size_prop: Name of the "size" property in referenced object
+ * @index: Index of the reference to return
+ * @args: Location to store the returned reference with optional arguments
+ *
+ * Find property with @name, verifify that it is a package containing at least
+ * one object reference and if so, store the ACPI device object pointer to the
+ * target object in @args->adev.
+ *
+ * If the reference includes arguments (@size_prop is not %NULL) follow the
+ * reference and check whether or not there is an integer property @size_prop
+ * under the target object and if so, whether or not its value matches the
+ * number of arguments that follow the reference.  If there's more than one
+ * reference in the property value package, @index is used to select the one to
+ * return.
+ *
+ * Return: %0 on success, negative error code on failure.
+ */
+int acpi_dev_get_property_reference(struct acpi_device *adev, const char *name,
+				    const char *size_prop, size_t index,
+				    struct acpi_reference_args *args)
+{
+	const union acpi_object *element, *end;
+	const union acpi_object *obj;
+	struct acpi_device *device;
+	int ret, idx = 0;
+
+	ret = acpi_dev_get_property(adev, name, ACPI_TYPE_ANY, &obj);
+	if (ret)
+		return ret;
+
+	/*
+	 * The simplest case is when the value is a single reference.  Just
+	 * return that reference then.
+	 */
+	if (obj->type == ACPI_TYPE_LOCAL_REFERENCE) {
+		if (size_prop || index)
+			return -EINVAL;
+
+		ret = acpi_bus_get_device(obj->reference.handle, &device);
+		if (ret)
+			return ret;
+
+		args->adev = device;
+		args->nargs = 0;
+		return 0;
+	}
+
+	/*
+	 * If it is not a single reference, then it is a package of
+	 * references followed by number of ints as follows:
+	 *
+	 *  Package () { REF, INT, REF, INT, INT }
+	 *
+	 * The index argument is then used to determine which reference
+	 * the caller wants (along with the arguments).
+	 */
+	if (obj->type != ACPI_TYPE_PACKAGE || index >= obj->package.count)
+		return -EPROTO;
+
+	element = obj->package.elements;
+	end = element + obj->package.count;
+
+	while (element < end) {
+		u32 nargs, i;
+
+		if (element->type != ACPI_TYPE_LOCAL_REFERENCE)
+			return -EPROTO;
+
+		ret = acpi_bus_get_device(element->reference.handle, &device);
+		if (ret)
+			return -ENODEV;
+
+		element++;
+		nargs = 0;
+
+		if (size_prop) {
+			const union acpi_object *prop;
+
+			/*
+			 * Find out how many arguments the refenced object
+			 * expects by reading its size_prop property.
+			 */
+			ret = acpi_dev_get_property(device, size_prop,
+						    ACPI_TYPE_INTEGER, &prop);
+			if (ret)
+				return ret;
+
+			nargs = prop->integer.value;
+			if (nargs > MAX_ACPI_REFERENCE_ARGS
+			    || element + nargs > end)
+				return -EPROTO;
+
+			/*
+			 * Skip to the start of the arguments and verify
+			 * that they all are in fact integers.
+			 */
+			for (i = 0; i < nargs; i++)
+				if (element[i].type != ACPI_TYPE_INTEGER)
+					return -EPROTO;
+		} else {
+			/* assume following integer elements are all args */
+			for (i = 0; element + i < end; i++) {
+				int type = element[i].type;
+
+				if (type == ACPI_TYPE_INTEGER)
+					nargs++;
+				else if (type == ACPI_TYPE_LOCAL_REFERENCE)
+					break;
+				else
+					return -EPROTO;
+			}
+		}
+
+		if (idx++ == index) {
+			args->adev = device;
+			args->nargs = nargs;
+			for (i = 0; i < nargs; i++)
+				args->args[i] = element[i].integer.value;
+
+			return 0;
+		}
+
+		element += nargs;
+	}
+
+	return -EPROTO;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_get_property_reference);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 0476e90b209..40d80ac0552 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -922,6 +922,7 @@ static void acpi_device_release(struct device *dev)
 {
 	struct acpi_device *acpi_dev = to_acpi_device(dev);
 
+	acpi_free_properties(acpi_dev);
 	acpi_free_pnp_ids(&acpi_dev->pnp);
 	acpi_free_power_resources_lists(acpi_dev);
 	kfree(acpi_dev);
@@ -1926,6 +1927,7 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 	acpi_set_device_status(device, sta);
 	acpi_device_get_busid(device);
 	acpi_set_pnp_ids(handle, &device->pnp, type);
+	acpi_init_properties(device);
 	acpi_bus_get_flags(device);
 	device->flags.match_driver = false;
 	device->flags.initialized = true;
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index f34a0835aa4..47578117009 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -337,6 +337,12 @@ struct acpi_device_physical_node {
 	bool put_online:1;
 };
 
+/* ACPI Device Specific Data (_DSD) */
+struct acpi_device_data {
+	const union acpi_object *pointer;
+	const union acpi_object *properties;
+};
+
 /* Device */
 struct acpi_device {
 	int device_type;
@@ -353,6 +359,7 @@ struct acpi_device {
 	struct acpi_device_wakeup wakeup;
 	struct acpi_device_perf performance;
 	struct acpi_device_dir dir;
+	struct acpi_device_data data;
 	struct acpi_scan_handler *handler;
 	struct acpi_hotplug_context *hp;
 	struct acpi_driver *driver;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 407a12f663e..dcdf8738898 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -659,4 +659,44 @@ do {									\
 #endif
 #endif
 
+/* Device properties */
+
+#define MAX_ACPI_REFERENCE_ARGS	8
+struct acpi_reference_args {
+	struct acpi_device *adev;
+	size_t nargs;
+	u64 args[MAX_ACPI_REFERENCE_ARGS];
+};
+
+#ifdef CONFIG_ACPI
+int acpi_dev_get_property(struct acpi_device *adev, const char *name,
+			  acpi_object_type type, const union acpi_object **obj);
+int acpi_dev_get_property_array(struct acpi_device *adev, const char *name,
+				acpi_object_type type,
+				const union acpi_object **obj);
+int acpi_dev_get_property_reference(struct acpi_device *adev, const char *name,
+				    const char *cells_name, size_t index,
+				    struct acpi_reference_args *args);
+#else
+static inline int acpi_dev_get_property(struct acpi_device *adev,
+					const char *name, acpi_object_type type,
+					const union acpi_object **obj)
+{
+	return -ENXIO;
+}
+static inline int acpi_dev_get_property_array(struct acpi_device *adev,
+					      const char *name,
+					      acpi_object_type type,
+					      const union acpi_object **obj)
+{
+	return -ENXIO;
+}
+static inline int acpi_dev_get_property_reference(struct acpi_device *adev,
+				const char *name, const char *cells_name,
+				size_t index, struct acpi_reference_args *args)
+{
+	return -ENXIO;
+}
+#endif
+
 #endif	/*_LINUX_ACPI_H*/
-- 
cgit v1.2.3-70-g09d2


From b31384fa5de37a100507751dfb5c0a49d06cee67 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 4 Nov 2014 01:28:56 +0100
Subject: Driver core: Unified device properties interface for platform
 firmware

Add a uniform interface by which device drivers can request device
properties from the platform firmware by providing a property name
and the corresponding data type.  The purpose of it is to help to
write portable code that won't depend on any particular platform
firmware interface.

The following general helper functions are added:

device_property_present()
device_property_read_u8()
device_property_read_u16()
device_property_read_u32()
device_property_read_u64()
device_property_read_string()
device_property_read_u8_array()
device_property_read_u16_array()
device_property_read_u32_array()
device_property_read_u64_array()
device_property_read_string_array()

The first one allows the caller to check if the given property is
present.  The next 5 of them allow single-valued properties of
various types to be retrieved in a uniform way.  The remaining 5 are
for reading properties with multiple values (arrays of either numbers
or strings).

The interface covers both ACPI and Device Trees.

This change set includes material from Mika Westerberg and Aaron Lu.

Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/property.c  | 178 +++++++++++++++++++++++++++++++++++++++++++++
 drivers/base/Makefile    |   2 +-
 drivers/base/property.c  | 185 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/of/base.c        |  33 +++++++++
 include/linux/acpi.h     |  32 ++++++++
 include/linux/of.h       |  12 +++
 include/linux/property.h |  73 +++++++++++++++++++
 7 files changed, 514 insertions(+), 1 deletion(-)
 create mode 100644 drivers/base/property.c
 create mode 100644 include/linux/property.h

(limited to 'include')

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index c4a3e800e82..2541b1fd1fa 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -362,3 +362,181 @@ int acpi_dev_get_property_reference(struct acpi_device *adev, const char *name,
 	return -EPROTO;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_get_property_reference);
+
+int acpi_dev_prop_get(struct acpi_device *adev, const char *propname,
+		      void **valptr)
+{
+	return acpi_dev_get_property(adev, propname, ACPI_TYPE_ANY,
+				     (const union acpi_object **)valptr);
+}
+
+int acpi_dev_prop_read_single(struct acpi_device *adev, const char *propname,
+			      enum dev_prop_type proptype, void *val)
+{
+	const union acpi_object *obj;
+	int ret;
+
+	if (!val)
+		return -EINVAL;
+
+	if (proptype >= DEV_PROP_U8 && proptype <= DEV_PROP_U64) {
+		ret = acpi_dev_get_property(adev, propname, ACPI_TYPE_INTEGER, &obj);
+		if (ret)
+			return ret;
+
+		switch (proptype) {
+		case DEV_PROP_U8:
+			if (obj->integer.value > U8_MAX)
+				return -EOVERFLOW;
+			*(u8 *)val = obj->integer.value;
+			break;
+		case DEV_PROP_U16:
+			if (obj->integer.value > U16_MAX)
+				return -EOVERFLOW;
+			*(u16 *)val = obj->integer.value;
+			break;
+		case DEV_PROP_U32:
+			if (obj->integer.value > U32_MAX)
+				return -EOVERFLOW;
+			*(u32 *)val = obj->integer.value;
+			break;
+		default:
+			*(u64 *)val = obj->integer.value;
+			break;
+		}
+	} else if (proptype == DEV_PROP_STRING) {
+		ret = acpi_dev_get_property(adev, propname, ACPI_TYPE_STRING, &obj);
+		if (ret)
+			return ret;
+
+		*(char **)val = obj->string.pointer;
+	} else {
+		ret = -EINVAL;
+	}
+	return ret;
+}
+
+static int acpi_copy_property_array_u8(const union acpi_object *items, u8 *val,
+				       size_t nval)
+{
+	int i;
+
+	for (i = 0; i < nval; i++) {
+		if (items[i].type != ACPI_TYPE_INTEGER)
+			return -EPROTO;
+		if (items[i].integer.value > U8_MAX)
+			return -EOVERFLOW;
+
+		val[i] = items[i].integer.value;
+	}
+	return 0;
+}
+
+static int acpi_copy_property_array_u16(const union acpi_object *items,
+					u16 *val, size_t nval)
+{
+	int i;
+
+	for (i = 0; i < nval; i++) {
+		if (items[i].type != ACPI_TYPE_INTEGER)
+			return -EPROTO;
+		if (items[i].integer.value > U16_MAX)
+			return -EOVERFLOW;
+
+		val[i] = items[i].integer.value;
+	}
+	return 0;
+}
+
+static int acpi_copy_property_array_u32(const union acpi_object *items,
+					u32 *val, size_t nval)
+{
+	int i;
+
+	for (i = 0; i < nval; i++) {
+		if (items[i].type != ACPI_TYPE_INTEGER)
+			return -EPROTO;
+		if (items[i].integer.value > U32_MAX)
+			return -EOVERFLOW;
+
+		val[i] = items[i].integer.value;
+	}
+	return 0;
+}
+
+static int acpi_copy_property_array_u64(const union acpi_object *items,
+					u64 *val, size_t nval)
+{
+	int i;
+
+	for (i = 0; i < nval; i++) {
+		if (items[i].type != ACPI_TYPE_INTEGER)
+			return -EPROTO;
+
+		val[i] = items[i].integer.value;
+	}
+	return 0;
+}
+
+static int acpi_copy_property_array_string(const union acpi_object *items,
+					   char **val, size_t nval)
+{
+	int i;
+
+	for (i = 0; i < nval; i++) {
+		if (items[i].type != ACPI_TYPE_STRING)
+			return -EPROTO;
+
+		val[i] = items[i].string.pointer;
+	}
+	return 0;
+}
+
+int acpi_dev_prop_read(struct acpi_device *adev, const char *propname,
+		       enum dev_prop_type proptype, void *val, size_t nval)
+{
+	const union acpi_object *obj;
+	const union acpi_object *items;
+	int ret;
+
+	if (val && nval == 1) {
+		ret = acpi_dev_prop_read_single(adev, propname, proptype, val);
+		if (!ret)
+			return ret;
+	}
+
+	ret = acpi_dev_get_property_array(adev, propname, ACPI_TYPE_ANY, &obj);
+	if (ret)
+		return ret;
+
+	if (!val)
+		return obj->package.count;
+	else if (nval <= 0)
+		return -EINVAL;
+
+	if (nval > obj->package.count)
+		return -EOVERFLOW;
+
+	items = obj->package.elements;
+	switch (proptype) {
+	case DEV_PROP_U8:
+		ret = acpi_copy_property_array_u8(items, (u8 *)val, nval);
+		break;
+	case DEV_PROP_U16:
+		ret = acpi_copy_property_array_u16(items, (u16 *)val, nval);
+		break;
+	case DEV_PROP_U32:
+		ret = acpi_copy_property_array_u32(items, (u32 *)val, nval);
+		break;
+	case DEV_PROP_U64:
+		ret = acpi_copy_property_array_u64(items, (u64 *)val, nval);
+		break;
+	case DEV_PROP_STRING:
+		ret = acpi_copy_property_array_string(items, (char **)val, nval);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 6922cd6850a..53c3fe1aeb2 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -4,7 +4,7 @@ obj-y			:= component.o core.o bus.o dd.o syscore.o \
 			   driver.o class.o platform.o \
 			   cpu.o firmware.o init.o map.o devres.o \
 			   attribute_container.o transport_class.o \
-			   topology.o container.o
+			   topology.o container.o property.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
 obj-$(CONFIG_DMA_CMA) += dma-contiguous.o
 obj-y			+= power/
diff --git a/drivers/base/property.c b/drivers/base/property.c
new file mode 100644
index 00000000000..6a94ef6e83c
--- /dev/null
+++ b/drivers/base/property.c
@@ -0,0 +1,185 @@
+/*
+ * property.c - Unified device property interface.
+ *
+ * Copyright (C) 2014, Intel Corporation
+ * Authors: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *          Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/property.h>
+#include <linux/export.h>
+#include <linux/acpi.h>
+#include <linux/of.h>
+
+/**
+ * device_property_present - check if a property of a device is present
+ * @dev: Device whose property is being checked
+ * @propname: Name of the property
+ *
+ * Check if property @propname is present in the device firmware description.
+ */
+bool device_property_present(struct device *dev, const char *propname)
+{
+	if (IS_ENABLED(CONFIG_OF) && dev->of_node)
+		return of_property_read_bool(dev->of_node, propname);
+
+	return !acpi_dev_prop_get(ACPI_COMPANION(dev), propname, NULL);
+}
+EXPORT_SYMBOL_GPL(device_property_present);
+
+#define OF_DEV_PROP_READ_ARRAY(node, propname, type, val, nval) \
+	(val) ? of_property_read_##type##_array((node), (propname), (val), (nval)) \
+	      : of_property_count_elems_of_size((node), (propname), sizeof(type))
+
+#define DEV_PROP_READ_ARRAY(_dev_, _propname_, _type_, _proptype_, _val_, _nval_) \
+	IS_ENABLED(CONFIG_OF) && _dev_->of_node ? \
+		(OF_DEV_PROP_READ_ARRAY(_dev_->of_node, _propname_, _type_, \
+					_val_, _nval_)) : \
+		acpi_dev_prop_read(ACPI_COMPANION(_dev_), _propname_, \
+				   _proptype_, _val_, _nval_)
+
+/**
+ * device_property_read_u8_array - return a u8 array property of a device
+ * @dev: Device to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Function reads an array of u8 properties with @propname from the device
+ * firmware description and stores them to @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO if the property is not an array of numbers,
+ *	   %-EOVERFLOW if the size of the property is not as expected.
+ */
+int device_property_read_u8_array(struct device *dev, const char *propname,
+				  u8 *val, size_t nval)
+{
+	return DEV_PROP_READ_ARRAY(dev, propname, u8, DEV_PROP_U8, val, nval);
+}
+EXPORT_SYMBOL_GPL(device_property_read_u8_array);
+
+/**
+ * device_property_read_u16_array - return a u16 array property of a device
+ * @dev: Device to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Function reads an array of u16 properties with @propname from the device
+ * firmware description and stores them to @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO if the property is not an array of numbers,
+ *	   %-EOVERFLOW if the size of the property is not as expected.
+ */
+int device_property_read_u16_array(struct device *dev, const char *propname,
+				   u16 *val, size_t nval)
+{
+	return DEV_PROP_READ_ARRAY(dev, propname, u16, DEV_PROP_U16, val, nval);
+}
+EXPORT_SYMBOL_GPL(device_property_read_u16_array);
+
+/**
+ * device_property_read_u32_array - return a u32 array property of a device
+ * @dev: Device to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Function reads an array of u32 properties with @propname from the device
+ * firmware description and stores them to @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO if the property is not an array of numbers,
+ *	   %-EOVERFLOW if the size of the property is not as expected.
+ */
+int device_property_read_u32_array(struct device *dev, const char *propname,
+				   u32 *val, size_t nval)
+{
+	return DEV_PROP_READ_ARRAY(dev, propname, u32, DEV_PROP_U32, val, nval);
+}
+EXPORT_SYMBOL_GPL(device_property_read_u32_array);
+
+/**
+ * device_property_read_u64_array - return a u64 array property of a device
+ * @dev: Device to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Function reads an array of u64 properties with @propname from the device
+ * firmware description and stores them to @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO if the property is not an array of numbers,
+ *	   %-EOVERFLOW if the size of the property is not as expected.
+ */
+int device_property_read_u64_array(struct device *dev, const char *propname,
+				   u64 *val, size_t nval)
+{
+	return DEV_PROP_READ_ARRAY(dev, propname, u64, DEV_PROP_U64, val, nval);
+}
+EXPORT_SYMBOL_GPL(device_property_read_u64_array);
+
+/**
+ * device_property_read_string_array - return a string array property of device
+ * @dev: Device to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Function reads an array of string properties with @propname from the device
+ * firmware description and stores them to @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO or %-EILSEQ if the property is not an array of strings,
+ *	   %-EOVERFLOW if the size of the property is not as expected.
+ */
+int device_property_read_string_array(struct device *dev, const char *propname,
+				      const char **val, size_t nval)
+{
+	return IS_ENABLED(CONFIG_OF) && dev->of_node ?
+		of_property_read_string_array(dev->of_node, propname, val, nval) :
+		acpi_dev_prop_read(ACPI_COMPANION(dev), propname,
+				   DEV_PROP_STRING, val, nval);
+}
+EXPORT_SYMBOL_GPL(device_property_read_string_array);
+
+/**
+ * device_property_read_string - return a string property of a device
+ * @dev: Device to get the property of
+ * @propname: Name of the property
+ * @val: The value is stored here
+ *
+ * Function reads property @propname from the device firmware description and
+ * stores the value into @val if found. The value is checked to be a string.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO or %-EILSEQ if the property type is not a string.
+ */
+int device_property_read_string(struct device *dev, const char *propname,
+				const char **val)
+{
+	return IS_ENABLED(CONFIG_OF) && dev->of_node ?
+		of_property_read_string(dev->of_node, propname, val) :
+		acpi_dev_prop_read(ACPI_COMPANION(dev), propname,
+				   DEV_PROP_STRING, val, 1);
+}
+EXPORT_SYMBOL_GPL(device_property_read_string);
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 3823edf2d01..4c2ccde4242 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1249,6 +1249,39 @@ int of_property_read_u64(const struct device_node *np, const char *propname,
 }
 EXPORT_SYMBOL_GPL(of_property_read_u64);
 
+/**
+ * of_property_read_u64_array - Find and read an array of 64 bit integers
+ * from a property.
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ * @out_values:	pointer to return value, modified only if return value is 0.
+ * @sz:		number of array elements to read
+ *
+ * Search for a property in a device node and read 64-bit value(s) from
+ * it. Returns 0 on success, -EINVAL if the property does not exist,
+ * -ENODATA if property does not have a value, and -EOVERFLOW if the
+ * property data isn't large enough.
+ *
+ * The out_values is modified only if a valid u64 value can be decoded.
+ */
+int of_property_read_u64_array(const struct device_node *np,
+			       const char *propname, u64 *out_values,
+			       size_t sz)
+{
+	const __be32 *val = of_find_property_value_of_size(np, propname,
+						(sz * sizeof(*out_values)));
+
+	if (IS_ERR(val))
+		return PTR_ERR(val);
+
+	while (sz--) {
+		*out_values++ = of_read_number(val, 2);
+		val += 2;
+	}
+	return 0;
+}
+
 /**
  * of_property_read_string - Find and read a string from a property
  * @np:		device node from which the property value is to be read.
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index dcdf8738898..76d64d6a903 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -28,6 +28,7 @@
 #include <linux/errno.h>
 #include <linux/ioport.h>	/* for struct resource */
 #include <linux/device.h>
+#include <linux/property.h>
 
 #ifndef _LINUX
 #define _LINUX
@@ -677,6 +678,13 @@ int acpi_dev_get_property_array(struct acpi_device *adev, const char *name,
 int acpi_dev_get_property_reference(struct acpi_device *adev, const char *name,
 				    const char *cells_name, size_t index,
 				    struct acpi_reference_args *args);
+
+int acpi_dev_prop_get(struct acpi_device *adev, const char *propname,
+		      void **valptr);
+int acpi_dev_prop_read_single(struct acpi_device *adev, const char *propname,
+			      enum dev_prop_type proptype, void *val);
+int acpi_dev_prop_read(struct acpi_device *adev, const char *propname,
+		       enum dev_prop_type proptype, void *val, size_t nval);
 #else
 static inline int acpi_dev_get_property(struct acpi_device *adev,
 					const char *name, acpi_object_type type,
@@ -697,6 +705,30 @@ static inline int acpi_dev_get_property_reference(struct acpi_device *adev,
 {
 	return -ENXIO;
 }
+
+static inline int acpi_dev_prop_get(struct acpi_device *adev,
+				    const char *propname,
+				    void **valptr)
+{
+	return -ENXIO;
+}
+
+static inline int acpi_dev_prop_read_single(struct acpi_device *adev,
+					    const char *propname,
+					    enum dev_prop_type proptype,
+					    void *val)
+{
+	return -ENXIO;
+}
+
+static inline int acpi_dev_prop_read(struct acpi_device *adev,
+				     const char *propname,
+				     enum dev_prop_type proptype,
+				     void *val, size_t nval)
+{
+	return -ENXIO;
+}
+
 #endif
 
 #endif	/*_LINUX_ACPI_H*/
diff --git a/include/linux/of.h b/include/linux/of.h
index 29f0adc5f3e..ce9f6a2b353 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -23,6 +23,7 @@
 #include <linux/spinlock.h>
 #include <linux/topology.h>
 #include <linux/notifier.h>
+#include <linux/property.h>
 
 #include <asm/byteorder.h>
 #include <asm/errno.h>
@@ -263,6 +264,10 @@ extern int of_property_read_u32_array(const struct device_node *np,
 				      size_t sz);
 extern int of_property_read_u64(const struct device_node *np,
 				const char *propname, u64 *out_value);
+extern int of_property_read_u64_array(const struct device_node *np,
+				      const char *propname,
+				      u64 *out_values,
+				      size_t sz);
 
 extern int of_property_read_string(struct device_node *np,
 				   const char *propname,
@@ -477,6 +482,13 @@ static inline int of_property_read_u32_array(const struct device_node *np,
 	return -ENOSYS;
 }
 
+static inline int of_property_read_u64_array(const struct device_node *np,
+					     const char *propname,
+					     u64 *out_values, size_t sz)
+{
+	return -ENOSYS;
+}
+
 static inline int of_property_read_string(struct device_node *np,
 					  const char *propname,
 					  const char **out_string)
diff --git a/include/linux/property.h b/include/linux/property.h
new file mode 100644
index 00000000000..9242fb0221b
--- /dev/null
+++ b/include/linux/property.h
@@ -0,0 +1,73 @@
+/*
+ * property.h - Unified device property interface.
+ *
+ * Copyright (C) 2014, Intel Corporation
+ * Authors: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *          Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _LINUX_PROPERTY_H_
+#define _LINUX_PROPERTY_H_
+
+#include <linux/types.h>
+
+struct device;
+
+enum dev_prop_type {
+	DEV_PROP_U8,
+	DEV_PROP_U16,
+	DEV_PROP_U32,
+	DEV_PROP_U64,
+	DEV_PROP_STRING,
+	DEV_PROP_MAX,
+};
+
+bool device_property_present(struct device *dev, const char *propname);
+int device_property_read_u8_array(struct device *dev, const char *propname,
+				  u8 *val, size_t nval);
+int device_property_read_u16_array(struct device *dev, const char *propname,
+				   u16 *val, size_t nval);
+int device_property_read_u32_array(struct device *dev, const char *propname,
+				   u32 *val, size_t nval);
+int device_property_read_u64_array(struct device *dev, const char *propname,
+				   u64 *val, size_t nval);
+int device_property_read_string_array(struct device *dev, const char *propname,
+				      const char **val, size_t nval);
+int device_property_read_string(struct device *dev, const char *propname,
+				const char **val);
+
+static inline bool device_property_read_bool(struct device *dev,
+					     const char *propname)
+{
+	return device_property_present(dev, propname);
+}
+
+static inline int device_property_read_u8(struct device *dev,
+					  const char *propname, u8 *val)
+{
+	return device_property_read_u8_array(dev, propname, val, 1);
+}
+
+static inline int device_property_read_u16(struct device *dev,
+					   const char *propname, u16 *val)
+{
+	return device_property_read_u16_array(dev, propname, val, 1);
+}
+
+static inline int device_property_read_u32(struct device *dev,
+					   const char *propname, u32 *val)
+{
+	return device_property_read_u32_array(dev, propname, val, 1);
+}
+
+static inline int device_property_read_u64(struct device *dev,
+					   const char *propname, u64 *val)
+{
+	return device_property_read_u64_array(dev, propname, val, 1);
+}
+
+#endif /* _LINUX_PROPERTY_H_ */
-- 
cgit v1.2.3-70-g09d2


From 733e625139fe455b4d910ac63c18c90f7cbe2d6f Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Tue, 21 Oct 2014 13:33:56 +0200
Subject: ACPI: Allow drivers to match using Device Tree compatible property

We have lots of existing Device Tree enabled drivers and allocating
separate _HID for each is not feasible. Instead we allocate special _HID
"PRP0001" that means that the match should be done using Device Tree
compatible property using driver's .of_match_table instead if the driver
is missing .acpi_match_table.

If there is a need to distinguish from where the device is enumerated
(DT/ACPI) driver can check dev->of_node or ACPI_COMPATION(dev).

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/property.c |  39 ++++++++++++++++++
 drivers/acpi/scan.c     | 106 +++++++++++++++++++++++++++++++++++++++++++-----
 include/acpi/acpi_bus.h |   1 +
 include/linux/acpi.h    |   8 +---
 4 files changed, 137 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 2541b1fd1fa..27add91bc27 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -76,6 +76,42 @@ static bool acpi_properties_format_valid(const union acpi_object *properties)
 	return true;
 }
 
+static void acpi_init_of_compatible(struct acpi_device *adev)
+{
+	const union acpi_object *of_compatible;
+	struct acpi_hardware_id *hwid;
+	bool acpi_of = false;
+	int ret;
+
+	/*
+	 * Check if the special PRP0001 ACPI ID is present and in that
+	 * case we fill in Device Tree compatible properties for this
+	 * device.
+	 */
+	list_for_each_entry(hwid, &adev->pnp.ids, list) {
+		if (!strcmp(hwid->id, "PRP0001")) {
+			acpi_of = true;
+			break;
+		}
+	}
+
+	if (!acpi_of)
+		return;
+
+	ret = acpi_dev_get_property_array(adev, "compatible", ACPI_TYPE_STRING,
+					  &of_compatible);
+	if (ret) {
+		ret = acpi_dev_get_property(adev, "compatible",
+					    ACPI_TYPE_STRING, &of_compatible);
+		if (ret) {
+			acpi_handle_warn(adev->handle,
+					 "PRP0001 requires compatible property\n");
+			return;
+		}
+	}
+	adev->data.of_compatible = of_compatible;
+}
+
 void acpi_init_properties(struct acpi_device *adev)
 {
 	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
@@ -119,6 +155,8 @@ void acpi_init_properties(struct acpi_device *adev)
 
 		adev->data.pointer = buf.pointer;
 		adev->data.properties = properties;
+
+		acpi_init_of_compatible(adev);
 		return;
 	}
 
@@ -130,6 +168,7 @@ void acpi_init_properties(struct acpi_device *adev)
 void acpi_free_properties(struct acpi_device *adev)
 {
 	ACPI_FREE((void *)adev->data.pointer);
+	adev->data.of_compatible = NULL;
 	adev->data.pointer = NULL;
 	adev->data.properties = NULL;
 }
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 40d80ac0552..3a8f6644453 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -124,17 +124,56 @@ static int create_modalias(struct acpi_device *acpi_dev, char *modalias,
 	if (list_empty(&acpi_dev->pnp.ids))
 		return 0;
 
-	len = snprintf(modalias, size, "acpi:");
-	size -= len;
-
-	list_for_each_entry(id, &acpi_dev->pnp.ids, list) {
-		count = snprintf(&modalias[len], size, "%s:", id->id);
-		if (count < 0)
-			return -EINVAL;
-		if (count >= size)
-			return -ENOMEM;
-		len += count;
-		size -= count;
+	/*
+	 * If the device has PRP0001 we expose DT compatible modalias
+	 * instead in form of of:NnameTCcompatible.
+	 */
+	if (acpi_dev->data.of_compatible) {
+		struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
+		const union acpi_object *of_compatible, *obj;
+		int i, nval;
+		char *c;
+
+		acpi_get_name(acpi_dev->handle, ACPI_SINGLE_NAME, &buf);
+		/* DT strings are all in lower case */
+		for (c = buf.pointer; *c != '\0'; c++)
+			*c = tolower(*c);
+
+		len = snprintf(modalias, size, "of:N%sT", (char *)buf.pointer);
+		ACPI_FREE(buf.pointer);
+
+		of_compatible = acpi_dev->data.of_compatible;
+		if (of_compatible->type == ACPI_TYPE_PACKAGE) {
+			nval = of_compatible->package.count;
+			obj = of_compatible->package.elements;
+		} else { /* Must be ACPI_TYPE_STRING. */
+			nval = 1;
+			obj = of_compatible;
+		}
+		for (i = 0; i < nval; i++, obj++) {
+			count = snprintf(&modalias[len], size, "C%s",
+					 obj->string.pointer);
+			if (count < 0)
+				return -EINVAL;
+			if (count >= size)
+				return -ENOMEM;
+
+			len += count;
+			size -= count;
+		}
+	} else {
+		len = snprintf(modalias, size, "acpi:");
+		size -= len;
+
+		list_for_each_entry(id, &acpi_dev->pnp.ids, list) {
+			count = snprintf(&modalias[len], size, "%s:", id->id);
+			if (count < 0)
+				return -EINVAL;
+			if (count >= size)
+				return -ENOMEM;
+			len += count;
+			size -= count;
+		}
 	}
 
 	modalias[len] = '\0';
@@ -902,6 +941,51 @@ int acpi_match_device_ids(struct acpi_device *device,
 }
 EXPORT_SYMBOL(acpi_match_device_ids);
 
+/* Performs match against special "PRP0001" shoehorn ACPI ID */
+static bool acpi_of_driver_match_device(struct device *dev,
+					const struct device_driver *drv)
+{
+	const union acpi_object *of_compatible, *obj;
+	struct acpi_device *adev;
+	int i, nval;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return false;
+
+	of_compatible = adev->data.of_compatible;
+	if (!drv->of_match_table || !of_compatible)
+		return false;
+
+	if (of_compatible->type == ACPI_TYPE_PACKAGE) {
+		nval = of_compatible->package.count;
+		obj = of_compatible->package.elements;
+	} else { /* Must be ACPI_TYPE_STRING. */
+		nval = 1;
+		obj = of_compatible;
+	}
+	/* Now we can look for the driver DT compatible strings */
+	for (i = 0; i < nval; i++, obj++) {
+		const struct of_device_id *id;
+
+		for (id = drv->of_match_table; id->compatible[0]; id++)
+			if (!strcasecmp(obj->string.pointer, id->compatible))
+				return true;
+	}
+
+	return false;
+}
+
+bool acpi_driver_match_device(struct device *dev,
+			      const struct device_driver *drv)
+{
+	if (!drv->acpi_match_table)
+		return acpi_of_driver_match_device(dev, drv);
+
+	return !!acpi_match_device(drv->acpi_match_table, dev);
+}
+EXPORT_SYMBOL_GPL(acpi_driver_match_device);
+
 static void acpi_free_power_resources_lists(struct acpi_device *device)
 {
 	int i;
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 47578117009..f59cbf86065 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -341,6 +341,7 @@ struct acpi_device_physical_node {
 struct acpi_device_data {
 	const union acpi_object *pointer;
 	const union acpi_object *properties;
+	const union acpi_object *of_compatible;
 };
 
 /* Device */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 76d64d6a903..38296d686c5 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -424,12 +424,8 @@ extern int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *),
 const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
 					       const struct device *dev);
 
-static inline bool acpi_driver_match_device(struct device *dev,
-					    const struct device_driver *drv)
-{
-	return !!acpi_match_device(drv->acpi_match_table, dev);
-}
-
+extern bool acpi_driver_match_device(struct device *dev,
+				     const struct device_driver *drv);
 int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *);
 int acpi_device_modalias(struct device *, char *, int);
 
-- 
cgit v1.2.3-70-g09d2


From 5c51277a9ababfa44a7f944100bdc9fbda139905 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Mon, 27 Oct 2014 23:29:32 +0100
Subject: leds: leds-gpio: Add support for GPIO descriptors

GPIO descriptors are the preferred way over legacy GPIO numbers
nowadays. Convert the driver to use GPIO descriptors internally but
still allow passing legacy GPIO numbers from platform data to support
existing platforms.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Alexandre Courbot <acourbot@nvidia.com>
Acked-by: Bryan Wu <cooloney@gmail.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/leds/leds-gpio.c | 80 +++++++++++++++++++++++++++---------------------
 include/linux/leds.h     |  1 +
 2 files changed, 46 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c
index b4518c8751c..1ff95ce9487 100644
--- a/drivers/leds/leds-gpio.c
+++ b/drivers/leds/leds-gpio.c
@@ -12,6 +12,7 @@
  */
 #include <linux/err.h>
 #include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/kernel.h>
 #include <linux/leds.h>
 #include <linux/module.h>
@@ -24,11 +25,10 @@
 
 struct gpio_led_data {
 	struct led_classdev cdev;
-	unsigned gpio;
+	struct gpio_desc *gpiod;
 	struct work_struct work;
 	u8 new_level;
 	u8 can_sleep;
-	u8 active_low;
 	u8 blinking;
 	int (*platform_gpio_blink_set)(unsigned gpio, int state,
 			unsigned long *delay_on, unsigned long *delay_off);
@@ -40,12 +40,16 @@ static void gpio_led_work(struct work_struct *work)
 		container_of(work, struct gpio_led_data, work);
 
 	if (led_dat->blinking) {
-		led_dat->platform_gpio_blink_set(led_dat->gpio,
-						 led_dat->new_level,
-						 NULL, NULL);
+		int gpio = desc_to_gpio(led_dat->gpiod);
+		int level = led_dat->new_level;
+
+		if (gpiod_is_active_low(led_dat->gpiod))
+			level = !level;
+
+		led_dat->platform_gpio_blink_set(gpio, level, NULL, NULL);
 		led_dat->blinking = 0;
 	} else
-		gpio_set_value_cansleep(led_dat->gpio, led_dat->new_level);
+		gpiod_set_value_cansleep(led_dat->gpiod, led_dat->new_level);
 }
 
 static void gpio_led_set(struct led_classdev *led_cdev,
@@ -60,9 +64,6 @@ static void gpio_led_set(struct led_classdev *led_cdev,
 	else
 		level = 1;
 
-	if (led_dat->active_low)
-		level = !level;
-
 	/* Setting GPIOs with I2C/etc requires a task context, and we don't
 	 * seem to have a reliable way to know if we're already in one; so
 	 * let's just assume the worst.
@@ -72,11 +73,16 @@ static void gpio_led_set(struct led_classdev *led_cdev,
 		schedule_work(&led_dat->work);
 	} else {
 		if (led_dat->blinking) {
-			led_dat->platform_gpio_blink_set(led_dat->gpio, level,
-							 NULL, NULL);
+			int gpio = desc_to_gpio(led_dat->gpiod);
+
+			if (gpiod_is_active_low(led_dat->gpiod))
+				level = !level;
+
+			led_dat->platform_gpio_blink_set(gpio, level, NULL,
+							 NULL);
 			led_dat->blinking = 0;
 		} else
-			gpio_set_value(led_dat->gpio, level);
+			gpiod_set_value(led_dat->gpiod, level);
 	}
 }
 
@@ -85,9 +91,10 @@ static int gpio_blink_set(struct led_classdev *led_cdev,
 {
 	struct gpio_led_data *led_dat =
 		container_of(led_cdev, struct gpio_led_data, cdev);
+	int gpio = desc_to_gpio(led_dat->gpiod);
 
 	led_dat->blinking = 1;
-	return led_dat->platform_gpio_blink_set(led_dat->gpio, GPIO_LED_BLINK,
+	return led_dat->platform_gpio_blink_set(gpio, GPIO_LED_BLINK,
 						delay_on, delay_off);
 }
 
@@ -97,24 +104,33 @@ static int create_gpio_led(const struct gpio_led *template,
 {
 	int ret, state;
 
-	led_dat->gpio = -1;
+	if (!template->gpiod) {
+		unsigned long flags = 0;
 
-	/* skip leds that aren't available */
-	if (!gpio_is_valid(template->gpio)) {
-		dev_info(parent, "Skipping unavailable LED gpio %d (%s)\n",
-				template->gpio, template->name);
-		return 0;
-	}
+		/* skip leds that aren't available */
+		if (!gpio_is_valid(template->gpio)) {
+			dev_info(parent, "Skipping unavailable LED gpio %d (%s)\n",
+					template->gpio, template->name);
+			return 0;
+		}
 
-	ret = devm_gpio_request(parent, template->gpio, template->name);
-	if (ret < 0)
-		return ret;
+		if (template->active_low)
+			flags |= GPIOF_ACTIVE_LOW;
+
+		ret = devm_gpio_request_one(parent, template->gpio, flags,
+					    template->name);
+		if (ret < 0)
+			return ret;
+
+		led_dat->gpiod = gpio_to_desc(template->gpio);
+		if (IS_ERR(led_dat->gpiod))
+			return PTR_ERR(led_dat->gpiod);
+	}
 
 	led_dat->cdev.name = template->name;
 	led_dat->cdev.default_trigger = template->default_trigger;
-	led_dat->gpio = template->gpio;
-	led_dat->can_sleep = gpio_cansleep(template->gpio);
-	led_dat->active_low = template->active_low;
+	led_dat->gpiod = template->gpiod;
+	led_dat->can_sleep = gpiod_cansleep(template->gpiod);
 	led_dat->blinking = 0;
 	if (blink_set) {
 		led_dat->platform_gpio_blink_set = blink_set;
@@ -122,30 +138,24 @@ static int create_gpio_led(const struct gpio_led *template,
 	}
 	led_dat->cdev.brightness_set = gpio_led_set;
 	if (template->default_state == LEDS_GPIO_DEFSTATE_KEEP)
-		state = !!gpio_get_value_cansleep(led_dat->gpio) ^ led_dat->active_low;
+		state = !!gpiod_get_value_cansleep(led_dat->gpiod);
 	else
 		state = (template->default_state == LEDS_GPIO_DEFSTATE_ON);
 	led_dat->cdev.brightness = state ? LED_FULL : LED_OFF;
 	if (!template->retain_state_suspended)
 		led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME;
 
-	ret = gpio_direction_output(led_dat->gpio, led_dat->active_low ^ state);
+	ret = gpiod_direction_output(led_dat->gpiod, state);
 	if (ret < 0)
 		return ret;
 
 	INIT_WORK(&led_dat->work, gpio_led_work);
 
-	ret = led_classdev_register(parent, &led_dat->cdev);
-	if (ret < 0)
-		return ret;
-
-	return 0;
+	return led_classdev_register(parent, &led_dat->cdev);
 }
 
 static void delete_gpio_led(struct gpio_led_data *led)
 {
-	if (!gpio_is_valid(led->gpio))
-		return;
 	led_classdev_unregister(&led->cdev);
 	cancel_work_sync(&led->work);
 }
diff --git a/include/linux/leds.h b/include/linux/leds.h
index a57611d0c94..f3af5c4d908 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -261,6 +261,7 @@ struct gpio_led {
 	unsigned	retain_state_suspended : 1;
 	unsigned	default_state : 2;
 	/* default_state should be one of LEDS_GPIO_DEFSTATE_(ON|OFF|KEEP) */
+	struct gpio_desc *gpiod;
 };
 #define LEDS_GPIO_DEFSTATE_OFF		0
 #define LEDS_GPIO_DEFSTATE_ON		1
-- 
cgit v1.2.3-70-g09d2


From 633a21d80b4a2cd648aa2dacdb22494ffb2f28f0 Mon Sep 17 00:00:00 2001
From: Aaron Lu <aaron.lu@intel.com>
Date: Tue, 21 Oct 2014 23:30:25 +0200
Subject: input: gpio_keys_polled: Add support for GPIO descriptors

GPIO descriptors are the preferred way over legacy GPIO numbers
nowadays. Convert the driver to use GPIO descriptors internally but
still allow passing legacy GPIO numbers from platform data to support
existing platforms.

Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/input/keyboard/gpio_keys_polled.c | 39 +++++++++++++++++++++----------
 include/linux/gpio_keys.h                 |  3 +++
 2 files changed, 30 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/input/keyboard/gpio_keys_polled.c b/drivers/input/keyboard/gpio_keys_polled.c
index 432d36395f3..b7a514ced50 100644
--- a/drivers/input/keyboard/gpio_keys_polled.c
+++ b/drivers/input/keyboard/gpio_keys_polled.c
@@ -23,6 +23,7 @@
 #include <linux/ioport.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/gpio_keys.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
@@ -51,15 +52,14 @@ static void gpio_keys_polled_check_state(struct input_dev *input,
 	int state;
 
 	if (bdata->can_sleep)
-		state = !!gpio_get_value_cansleep(button->gpio);
+		state = !!gpiod_get_value_cansleep(button->gpiod);
 	else
-		state = !!gpio_get_value(button->gpio);
+		state = !!gpiod_get_value(button->gpiod);
 
 	if (state != bdata->last_state) {
 		unsigned int type = button->type ?: EV_KEY;
 
-		input_event(input, type, button->code,
-			    !!(state ^ button->active_low));
+		input_event(input, type, button->code, state);
 		input_sync(input);
 		bdata->count = 0;
 		bdata->last_state = state;
@@ -259,7 +259,6 @@ static int gpio_keys_polled_probe(struct platform_device *pdev)
 	for (i = 0; i < pdata->nbuttons; i++) {
 		struct gpio_keys_button *button = &pdata->buttons[i];
 		struct gpio_keys_button_data *bdata = &bdev->data[i];
-		unsigned int gpio = button->gpio;
 		unsigned int type = button->type ?: EV_KEY;
 
 		if (button->wakeup) {
@@ -267,15 +266,31 @@ static int gpio_keys_polled_probe(struct platform_device *pdev)
 			return -EINVAL;
 		}
 
-		error = devm_gpio_request_one(&pdev->dev, gpio, GPIOF_IN,
-					      button->desc ? : DRV_NAME);
-		if (error) {
-			dev_err(dev, "unable to claim gpio %u, err=%d\n",
-				gpio, error);
-			return error;
+		/*
+		 * Legacy GPIO number so request the GPIO here and
+		 * convert it to descriptor.
+		 */
+		if (!button->gpiod && gpio_is_valid(button->gpio)) {
+			unsigned flags = 0;
+
+			if (button->active_low)
+				flags |= GPIOF_ACTIVE_LOW;
+
+			error = devm_gpio_request_one(&pdev->dev, button->gpio,
+					flags, button->desc ? : DRV_NAME);
+			if (error) {
+				dev_err(dev, "unable to claim gpio %u, err=%d\n",
+					button->gpio, error);
+				return error;
+			}
+
+			button->gpiod = gpio_to_desc(button->gpio);
 		}
 
-		bdata->can_sleep = gpio_cansleep(gpio);
+		if (IS_ERR(button->gpiod))
+			return PTR_ERR(button->gpiod);
+
+		bdata->can_sleep = gpiod_cansleep(button->gpiod);
 		bdata->last_state = -1;
 		bdata->threshold = DIV_ROUND_UP(button->debounce_interval,
 						pdata->poll_interval);
diff --git a/include/linux/gpio_keys.h b/include/linux/gpio_keys.h
index 8b622468952..ee2d8c6f913 100644
--- a/include/linux/gpio_keys.h
+++ b/include/linux/gpio_keys.h
@@ -2,6 +2,7 @@
 #define _GPIO_KEYS_H
 
 struct device;
+struct gpio_desc;
 
 /**
  * struct gpio_keys_button - configuration parameters
@@ -17,6 +18,7 @@ struct device;
  *			disable button via sysfs
  * @value:		axis value for %EV_ABS
  * @irq:		Irq number in case of interrupt keys
+ * @gpiod:		GPIO descriptor
  */
 struct gpio_keys_button {
 	unsigned int code;
@@ -29,6 +31,7 @@ struct gpio_keys_button {
 	bool can_disable;
 	int value;
 	unsigned int irq;
+	struct gpio_desc *gpiod;
 };
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 8a0662d9ed2968e1186208336a8e1fab3fdfea63 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 4 Nov 2014 14:03:59 +0100
Subject: Driver core: Unified interface for firmware node properties

Add new generic routines are provided for retrieving properties from
device description objects in the platform firmware in case there are
no struct device objects for them (either those objects have not been
created yet or they do not exist at all).

The following functions are provided:

fwnode_property_present()
fwnode_property_read_u8()
fwnode_property_read_u16()
fwnode_property_read_u32()
fwnode_property_read_u64()
fwnode_property_read_string()
fwnode_property_read_u8_array()
fwnode_property_read_u16_array()
fwnode_property_read_u32_array()
fwnode_property_read_u64_array()
fwnode_property_read_string_array()

in analogy with the corresponding functions for struct device added
previously.  For all of them, the first argument is a pointer to struct
fwnode_handle (new type) that allows a device description object
(depending on what platform firmware interface is in use) to be
obtained.

Add a new macro device_for_each_child_node() for iterating over the
children of the device description object associated with a given
device and a new function device_get_child_node_count() returning the
number of a given device's child nodes.

The interface covers both ACPI and Device Trees.

Suggested-by: Grant Likely <grant.likely@linaro.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/scan.c      |  21 ++++
 drivers/base/property.c  | 246 +++++++++++++++++++++++++++++++++++++++++++++++
 include/acpi/acpi_bus.h  |  17 ++++
 include/linux/acpi.h     |  26 +++++
 include/linux/of.h       |  22 +++++
 include/linux/property.h |  70 ++++++++++++++
 6 files changed, 402 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 3a8f6644453..9cb5cca3cfe 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1389,6 +1389,26 @@ int acpi_device_add(struct acpi_device *device,
 	return result;
 }
 
+struct acpi_device *acpi_get_next_child(struct device *dev,
+					struct acpi_device *child)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+	struct list_head *head, *next;
+
+	if (!adev)
+		return NULL;
+
+	head = &adev->children;
+	if (list_empty(head))
+		return NULL;
+
+	if (!child)
+		return list_first_entry(head, struct acpi_device, node);
+
+	next = child->node.next;
+	return next == head ? NULL : list_entry(next, struct acpi_device, node);
+}
+
 /* --------------------------------------------------------------------------
                                  Driver Management
    -------------------------------------------------------------------------- */
@@ -2008,6 +2028,7 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 	device->device_type = type;
 	device->handle = handle;
 	device->parent = acpi_bus_get_parent(handle);
+	device->fwnode.type = FWNODE_ACPI;
 	acpi_set_device_status(device, sta);
 	acpi_device_get_busid(device);
 	acpi_set_pnp_ids(handle, &device->pnp, type);
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 6a94ef6e83c..c45845874d4 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -31,6 +31,22 @@ bool device_property_present(struct device *dev, const char *propname)
 }
 EXPORT_SYMBOL_GPL(device_property_present);
 
+/**
+ * fwnode_property_present - check if a property of a firmware node is present
+ * @fwnode: Firmware node whose property to check
+ * @propname: Name of the property
+ */
+bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname)
+{
+	if (is_of_node(fwnode))
+		return of_property_read_bool(of_node(fwnode), propname);
+	else if (is_acpi_node(fwnode))
+		return !acpi_dev_prop_get(acpi_node(fwnode), propname, NULL);
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(fwnode_property_present);
+
 #define OF_DEV_PROP_READ_ARRAY(node, propname, type, val, nval) \
 	(val) ? of_property_read_##type##_array((node), (propname), (val), (nval)) \
 	      : of_property_count_elems_of_size((node), (propname), sizeof(type))
@@ -183,3 +199,233 @@ int device_property_read_string(struct device *dev, const char *propname,
 				   DEV_PROP_STRING, val, 1);
 }
 EXPORT_SYMBOL_GPL(device_property_read_string);
+
+#define FWNODE_PROP_READ_ARRAY(_fwnode_, _propname_, _type_, _proptype_, _val_, _nval_) \
+({ \
+	int _ret_; \
+	if (is_of_node(_fwnode_)) \
+		_ret_ = OF_DEV_PROP_READ_ARRAY(of_node(_fwnode_), _propname_, \
+					       _type_, _val_, _nval_); \
+	else if (is_acpi_node(_fwnode_)) \
+		_ret_ = acpi_dev_prop_read(acpi_node(_fwnode_), _propname_, \
+					   _proptype_, _val_, _nval_); \
+	else \
+		_ret_ = -ENXIO; \
+	_ret_; \
+})
+
+/**
+ * fwnode_property_read_u8_array - return a u8 array property of firmware node
+ * @fwnode: Firmware node to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Read an array of u8 properties with @propname from @fwnode and stores them to
+ * @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO if the property is not an array of numbers,
+ *	   %-EOVERFLOW if the size of the property is not as expected,
+ *	   %-ENXIO if no suitable firmware interface is present.
+ */
+int fwnode_property_read_u8_array(struct fwnode_handle *fwnode,
+				  const char *propname, u8 *val, size_t nval)
+{
+	return FWNODE_PROP_READ_ARRAY(fwnode, propname, u8, DEV_PROP_U8,
+				      val, nval);
+}
+EXPORT_SYMBOL_GPL(fwnode_property_read_u8_array);
+
+/**
+ * fwnode_property_read_u16_array - return a u16 array property of firmware node
+ * @fwnode: Firmware node to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Read an array of u16 properties with @propname from @fwnode and store them to
+ * @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO if the property is not an array of numbers,
+ *	   %-EOVERFLOW if the size of the property is not as expected,
+ *	   %-ENXIO if no suitable firmware interface is present.
+ */
+int fwnode_property_read_u16_array(struct fwnode_handle *fwnode,
+				   const char *propname, u16 *val, size_t nval)
+{
+	return FWNODE_PROP_READ_ARRAY(fwnode, propname, u16, DEV_PROP_U16,
+				      val, nval);
+}
+EXPORT_SYMBOL_GPL(fwnode_property_read_u16_array);
+
+/**
+ * fwnode_property_read_u32_array - return a u32 array property of firmware node
+ * @fwnode: Firmware node to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Read an array of u32 properties with @propname from @fwnode store them to
+ * @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO if the property is not an array of numbers,
+ *	   %-EOVERFLOW if the size of the property is not as expected,
+ *	   %-ENXIO if no suitable firmware interface is present.
+ */
+int fwnode_property_read_u32_array(struct fwnode_handle *fwnode,
+				   const char *propname, u32 *val, size_t nval)
+{
+	return FWNODE_PROP_READ_ARRAY(fwnode, propname, u32, DEV_PROP_U32,
+				      val, nval);
+}
+EXPORT_SYMBOL_GPL(fwnode_property_read_u32_array);
+
+/**
+ * fwnode_property_read_u64_array - return a u64 array property firmware node
+ * @fwnode: Firmware node to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Read an array of u64 properties with @propname from @fwnode and store them to
+ * @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO if the property is not an array of numbers,
+ *	   %-EOVERFLOW if the size of the property is not as expected,
+ *	   %-ENXIO if no suitable firmware interface is present.
+ */
+int fwnode_property_read_u64_array(struct fwnode_handle *fwnode,
+				   const char *propname, u64 *val, size_t nval)
+{
+	return FWNODE_PROP_READ_ARRAY(fwnode, propname, u64, DEV_PROP_U64,
+				      val, nval);
+}
+EXPORT_SYMBOL_GPL(fwnode_property_read_u64_array);
+
+/**
+ * fwnode_property_read_string_array - return string array property of a node
+ * @fwnode: Firmware node to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Read an string list property @propname from the given firmware node and store
+ * them to @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO if the property is not an array of strings,
+ *	   %-EOVERFLOW if the size of the property is not as expected,
+ *	   %-ENXIO if no suitable firmware interface is present.
+ */
+int fwnode_property_read_string_array(struct fwnode_handle *fwnode,
+				      const char *propname, const char **val,
+				      size_t nval)
+{
+	if (is_of_node(fwnode))
+		return of_property_read_string_array(of_node(fwnode), propname,
+						     val, nval);
+	else if (is_acpi_node(fwnode))
+		return acpi_dev_prop_read(acpi_node(fwnode), propname,
+					  DEV_PROP_STRING, val, nval);
+
+	return -ENXIO;
+}
+EXPORT_SYMBOL_GPL(fwnode_property_read_string_array);
+
+/**
+ * fwnode_property_read_string - return a string property of a firmware node
+ * @fwnode: Firmware node to get the property of
+ * @propname: Name of the property
+ * @val: The value is stored here
+ *
+ * Read property @propname from the given firmware node and store the value into
+ * @val if found.  The value is checked to be a string.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO or %-EILSEQ if the property is not a string,
+ *	   %-ENXIO if no suitable firmware interface is present.
+ */
+int fwnode_property_read_string(struct fwnode_handle *fwnode,
+				const char *propname, const char **val)
+{
+	if (is_of_node(fwnode))
+		return of_property_read_string(of_node(fwnode),propname, val);
+	else if (is_acpi_node(fwnode))
+		return acpi_dev_prop_read(acpi_node(fwnode), propname,
+					  DEV_PROP_STRING, val, 1);
+
+	return -ENXIO;
+}
+EXPORT_SYMBOL_GPL(fwnode_property_read_string);
+
+/**
+ * device_get_next_child_node - Return the next child node handle for a device
+ * @dev: Device to find the next child node for.
+ * @child: Handle to one of the device's child nodes or a null handle.
+ */
+struct fwnode_handle *device_get_next_child_node(struct device *dev,
+						 struct fwnode_handle *child)
+{
+	if (IS_ENABLED(CONFIG_OF) && dev->of_node) {
+		struct device_node *node;
+
+		node = of_get_next_available_child(dev->of_node, of_node(child));
+		if (node)
+			return &node->fwnode;
+	} else if (IS_ENABLED(CONFIG_ACPI)) {
+		struct acpi_device *node;
+
+		node = acpi_get_next_child(dev, acpi_node(child));
+		if (node)
+			return acpi_fwnode_handle(node);
+	}
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(device_get_next_child_node);
+
+/**
+ * fwnode_handle_put - Drop reference to a device node
+ * @fwnode: Pointer to the device node to drop the reference to.
+ *
+ * This has to be used when terminating device_for_each_child_node() iteration
+ * with break or return to prevent stale device node references from being left
+ * behind.
+ */
+void fwnode_handle_put(struct fwnode_handle *fwnode)
+{
+	if (is_of_node(fwnode))
+		of_node_put(of_node(fwnode));
+}
+EXPORT_SYMBOL_GPL(fwnode_handle_put);
+
+/**
+ * device_get_child_node_count - return the number of child nodes for device
+ * @dev: Device to cound the child nodes for
+ */
+unsigned int device_get_child_node_count(struct device *dev)
+{
+	struct fwnode_handle *child;
+	unsigned int count = 0;
+
+	device_for_each_child_node(dev, child)
+		count++;
+
+	return count;
+}
+EXPORT_SYMBOL_GPL(device_get_child_node_count);
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index f59cbf86065..a361f43b197 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -27,6 +27,7 @@
 #define __ACPI_BUS_H__
 
 #include <linux/device.h>
+#include <linux/property.h>
 
 /* TBD: Make dynamic */
 #define ACPI_MAX_HANDLES	10
@@ -348,6 +349,7 @@ struct acpi_device_data {
 struct acpi_device {
 	int device_type;
 	acpi_handle handle;		/* no handle for fixed hardware */
+	struct fwnode_handle fwnode;
 	struct acpi_device *parent;
 	struct list_head children;
 	struct list_head node;
@@ -372,6 +374,21 @@ struct acpi_device {
 	void (*remove)(struct acpi_device *);
 };
 
+static inline bool is_acpi_node(struct fwnode_handle *fwnode)
+{
+	return fwnode && fwnode->type == FWNODE_ACPI;
+}
+
+static inline struct acpi_device *acpi_node(struct fwnode_handle *fwnode)
+{
+	return fwnode ? container_of(fwnode, struct acpi_device, fwnode) : NULL;
+}
+
+static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev)
+{
+	return &adev->fwnode;
+}
+
 static inline void *acpi_driver_data(struct acpi_device *d)
 {
 	return d->driver_data;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 38296d686c5..5b8802216a9 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -440,6 +440,23 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *);
 #define ACPI_COMPANION_SET(dev, adev)	do { } while (0)
 #define ACPI_HANDLE(dev)		(NULL)
 
+struct fwnode_handle;
+
+static inline bool is_acpi_node(struct fwnode_handle *fwnode)
+{
+	return false;
+}
+
+static inline struct acpi_device *acpi_node(struct fwnode_handle *fwnode)
+{
+	return NULL;
+}
+
+static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev)
+{
+	return NULL;
+}
+
 static inline const char *acpi_dev_name(struct acpi_device *adev)
 {
 	return NULL;
@@ -681,6 +698,9 @@ int acpi_dev_prop_read_single(struct acpi_device *adev, const char *propname,
 			      enum dev_prop_type proptype, void *val);
 int acpi_dev_prop_read(struct acpi_device *adev, const char *propname,
 		       enum dev_prop_type proptype, void *val, size_t nval);
+
+struct acpi_device *acpi_get_next_child(struct device *dev,
+					struct acpi_device *child);
 #else
 static inline int acpi_dev_get_property(struct acpi_device *adev,
 					const char *name, acpi_object_type type,
@@ -725,6 +745,12 @@ static inline int acpi_dev_prop_read(struct acpi_device *adev,
 	return -ENXIO;
 }
 
+static inline struct acpi_device *acpi_get_next_child(struct device *dev,
+						      struct acpi_device *child)
+{
+	return NULL;
+}
+
 #endif
 
 #endif	/*_LINUX_ACPI_H*/
diff --git a/include/linux/of.h b/include/linux/of.h
index ce9f6a2b353..cf79be1441d 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -50,6 +50,7 @@ struct device_node {
 	const char *type;
 	phandle phandle;
 	const char *full_name;
+	struct fwnode_handle fwnode;
 
 	struct	property *properties;
 	struct	property *deadprops;	/* removed properties */
@@ -80,6 +81,7 @@ extern struct kobj_type of_node_ktype;
 static inline void of_node_init(struct device_node *node)
 {
 	kobject_init(&node->kobj, &of_node_ktype);
+	node->fwnode.type = FWNODE_OF;
 }
 
 /* true when node is initialized */
@@ -115,6 +117,16 @@ extern struct device_node *of_aliases;
 extern struct device_node *of_stdout;
 extern raw_spinlock_t devtree_lock;
 
+static inline bool is_of_node(struct fwnode_handle *fwnode)
+{
+	return fwnode && fwnode->type == FWNODE_OF;
+}
+
+static inline struct device_node *of_node(struct fwnode_handle *fwnode)
+{
+	return fwnode ? container_of(fwnode, struct device_node, fwnode) : NULL;
+}
+
 static inline bool of_have_populated_dt(void)
 {
 	return of_allnodes != NULL;
@@ -360,6 +372,16 @@ bool of_console_check(struct device_node *dn, char *name, int index);
 
 #else /* CONFIG_OF */
 
+static inline bool is_of_node(struct fwnode_handle *fwnode)
+{
+	return false;
+}
+
+static inline struct device_node *of_node(struct fwnode_handle *fwnode)
+{
+	return NULL;
+}
+
 static inline const char* of_node_full_name(const struct device_node *np)
 {
 	return "<no-node>";
diff --git a/include/linux/property.h b/include/linux/property.h
index 9242fb0221b..a6a3d98bd7e 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -40,6 +40,46 @@ int device_property_read_string_array(struct device *dev, const char *propname,
 int device_property_read_string(struct device *dev, const char *propname,
 				const char **val);
 
+enum fwnode_type {
+	FWNODE_INVALID = 0,
+	FWNODE_OF,
+	FWNODE_ACPI,
+};
+
+struct fwnode_handle {
+	enum fwnode_type type;
+};
+
+bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname);
+int fwnode_property_read_u8_array(struct fwnode_handle *fwnode,
+				  const char *propname, u8 *val,
+				  size_t nval);
+int fwnode_property_read_u16_array(struct fwnode_handle *fwnode,
+				   const char *propname, u16 *val,
+				   size_t nval);
+int fwnode_property_read_u32_array(struct fwnode_handle *fwnode,
+				   const char *propname, u32 *val,
+				   size_t nval);
+int fwnode_property_read_u64_array(struct fwnode_handle *fwnode,
+				   const char *propname, u64 *val,
+				   size_t nval);
+int fwnode_property_read_string_array(struct fwnode_handle *fwnode,
+				      const char *propname, const char **val,
+				      size_t nval);
+int fwnode_property_read_string(struct fwnode_handle *fwnode,
+				const char *propname, const char **val);
+
+struct fwnode_handle *device_get_next_child_node(struct device *dev,
+						 struct fwnode_handle *child);
+
+#define device_for_each_child_node(dev, child) \
+	for (child = device_get_next_child_node(dev, NULL); child; \
+	     child = device_get_next_child_node(dev, child))
+
+void fwnode_handle_put(struct fwnode_handle *fwnode);
+
+unsigned int device_get_child_node_count(struct device *dev);
+
 static inline bool device_property_read_bool(struct device *dev,
 					     const char *propname)
 {
@@ -70,4 +110,34 @@ static inline int device_property_read_u64(struct device *dev,
 	return device_property_read_u64_array(dev, propname, val, 1);
 }
 
+static inline bool fwnode_property_read_bool(struct fwnode_handle *fwnode,
+					     const char *propname)
+{
+	return fwnode_property_present(fwnode, propname);
+}
+
+static inline int fwnode_property_read_u8(struct fwnode_handle *fwnode,
+					  const char *propname, u8 *val)
+{
+	return fwnode_property_read_u8_array(fwnode, propname, val, 1);
+}
+
+static inline int fwnode_property_read_u16(struct fwnode_handle *fwnode,
+					   const char *propname, u16 *val)
+{
+	return fwnode_property_read_u16_array(fwnode, propname, val, 1);
+}
+
+static inline int fwnode_property_read_u32(struct fwnode_handle *fwnode,
+					   const char *propname, u32 *val)
+{
+	return fwnode_property_read_u32_array(fwnode, propname, val, 1);
+}
+
+static inline int fwnode_property_read_u64(struct fwnode_handle *fwnode,
+					   const char *propname, u64 *val)
+{
+	return fwnode_property_read_u64_array(fwnode, propname, val, 1);
+}
+
 #endif /* _LINUX_PROPERTY_H_ */
-- 
cgit v1.2.3-70-g09d2


From 40b7318319281b1bdec804f6435f26cadd329c13 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Tue, 21 Oct 2014 13:33:59 +0200
Subject: gpio: Support for unified device properties interface

Some drivers need to deal with only firmware representation of its
GPIOs. An example would be a GPIO button array driver where each button
is described as a separate firmware node in device tree. Typically these
child nodes do not have physical representation in the Linux device
model.

In order to help device drivers to handle such firmware child nodes we
add dev[m]_get_named_gpiod_from_child() that takes a child firmware
node pointer as its second argument (the first one is the parent device
itself), finds the GPIO using whatever is the underlying firmware
method, and requests the GPIO properly.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Alexandre Courbot <acourbot@nvidia.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/gpio/devres.c         | 32 +++++++++++++++++++++++++
 drivers/gpio/gpiolib.c        | 55 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/gpio/consumer.h |  7 ++++++
 3 files changed, 94 insertions(+)

(limited to 'include')

diff --git a/drivers/gpio/devres.c b/drivers/gpio/devres.c
index 954b9f6b0ef..13dbd3dfc33 100644
--- a/drivers/gpio/devres.c
+++ b/drivers/gpio/devres.c
@@ -108,6 +108,38 @@ struct gpio_desc *__must_check __devm_gpiod_get_index(struct device *dev,
 }
 EXPORT_SYMBOL(__devm_gpiod_get_index);
 
+/**
+ * devm_get_gpiod_from_child - get a GPIO descriptor from a device's child node
+ * @dev:	GPIO consumer
+ * @child:	firmware node (child of @dev)
+ *
+ * GPIO descriptors returned from this function are automatically disposed on
+ * driver detach.
+ */
+struct gpio_desc *devm_get_gpiod_from_child(struct device *dev,
+					    struct fwnode_handle *child)
+{
+	struct gpio_desc **dr;
+	struct gpio_desc *desc;
+
+	dr = devres_alloc(devm_gpiod_release, sizeof(struct gpio_desc *),
+			  GFP_KERNEL);
+	if (!dr)
+		return ERR_PTR(-ENOMEM);
+
+	desc = fwnode_get_named_gpiod(child, "gpios");
+	if (IS_ERR(desc)) {
+		devres_free(dr);
+		return desc;
+	}
+
+	*dr = desc;
+	devres_add(dev, dr);
+
+	return desc;
+}
+EXPORT_SYMBOL(devm_get_gpiod_from_child);
+
 /**
  * devm_gpiod_get_index_optional - Resource-managed gpiod_get_index_optional()
  * @dev: GPIO consumer
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 2bca0495cb4..58659dbe702 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1734,6 +1734,61 @@ struct gpio_desc *__must_check __gpiod_get_index(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(__gpiod_get_index);
 
+/**
+ * fwnode_get_named_gpiod - obtain a GPIO from firmware node
+ * @fwnode:	handle of the firmware node
+ * @propname:	name of the firmware property representing the GPIO
+ *
+ * This function can be used for drivers that get their configuration
+ * from firmware.
+ *
+ * Function properly finds the corresponding GPIO using whatever is the
+ * underlying firmware interface and then makes sure that the GPIO
+ * descriptor is requested before it is returned to the caller.
+ *
+ * In case of error an ERR_PTR() is returned.
+ */
+struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode,
+					 const char *propname)
+{
+	struct gpio_desc *desc = ERR_PTR(-ENODEV);
+	bool active_low = false;
+	int ret;
+
+	if (!fwnode)
+		return ERR_PTR(-EINVAL);
+
+	if (is_of_node(fwnode)) {
+		enum of_gpio_flags flags;
+
+		desc = of_get_named_gpiod_flags(of_node(fwnode), propname, 0,
+						&flags);
+		if (!IS_ERR(desc))
+			active_low = flags & OF_GPIO_ACTIVE_LOW;
+	} else if (is_acpi_node(fwnode)) {
+		struct acpi_gpio_info info;
+
+		desc = acpi_get_gpiod_by_index(acpi_node(fwnode), propname, 0,
+					       &info);
+		if (!IS_ERR(desc))
+			active_low = info.active_low;
+	}
+
+	if (IS_ERR(desc))
+		return desc;
+
+	ret = gpiod_request(desc, NULL);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/* Only value flag can be set from both DT and ACPI is active_low */
+	if (active_low)
+		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
+
+	return desc;
+}
+EXPORT_SYMBOL_GPL(fwnode_get_named_gpiod);
+
 /**
  * gpiod_get_index_optional - obtain an optional GPIO from a multi-index GPIO
  *                            function
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 12f146fa660..00b1b70d68b 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -94,6 +94,13 @@ int gpiod_to_irq(const struct gpio_desc *desc);
 struct gpio_desc *gpio_to_desc(unsigned gpio);
 int desc_to_gpio(const struct gpio_desc *desc);
 
+/* Child properties interface */
+struct fwnode_handle;
+
+struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode,
+					 const char *propname);
+struct gpio_desc *devm_get_gpiod_from_child(struct device *dev,
+					    struct fwnode_handle *child);
 #else /* CONFIG_GPIOLIB */
 
 static inline struct gpio_desc *__must_check __gpiod_get(struct device *dev,
-- 
cgit v1.2.3-70-g09d2


From f028d5242d7ecb0a1bfc80e7bd292201c8612641 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 3 Nov 2014 23:39:41 +0100
Subject: ACPI / GPIO: Driver GPIO mappings for ACPI GPIOs

Provide a way for device drivers using GPIOs described by ACPI
GpioIo resources in _CRS to tell the GPIO subsystem what names
(connection IDs) to associate with specific GPIO pins defined
in there.

To do that, a driver needs to define a mapping table as a
NULL-terminated array of struct acpi_gpio_mapping objects
that each contain a name, a pointer to an array of line data
(struct acpi_gpio_params) objects and the size of that array.

Each struct acpi_gpio_params object consists of three fields,
crs_entry_index, line_index, active_low, representing the index of
the target GpioIo()/GpioInt() resource in _CRS starting from zero,
the index of the target line in that resource starting from zero,
and the active-low flag for that line, respectively.

Next, the mapping table needs to be passed as the second
argument to acpi_dev_add_driver_gpios() that will register it with
the ACPI device object pointed to by its first argument.  That
should be done in the driver's .probe() routine.

On removal, the driver should unregister its GPIO mapping table
by calling acpi_dev_remove_driver_gpios() on the ACPI device
object where that table was previously registered.

Included are fixes from Mika Westerberg.

Acked-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/gpio/gpiolib-acpi.c | 43 +++++++++++++++++++++++++++++++++++++++++--
 include/acpi/acpi_bus.h     |  3 +++
 include/linux/acpi.h        | 30 ++++++++++++++++++++++++++++++
 3 files changed, 74 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 8aa6ca47374..5a4d061e787 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -287,6 +287,41 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip)
 	}
 }
 
+int acpi_dev_add_driver_gpios(struct acpi_device *adev,
+			      const struct acpi_gpio_mapping *gpios)
+{
+	if (adev && gpios) {
+		adev->driver_gpios = gpios;
+		return 0;
+	}
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_add_driver_gpios);
+
+static bool acpi_get_driver_gpio_data(struct acpi_device *adev,
+				      const char *name, int index,
+				      struct acpi_reference_args *args)
+{
+	const struct acpi_gpio_mapping *gm;
+
+	if (!adev->driver_gpios)
+		return false;
+
+	for (gm = adev->driver_gpios; gm->name; gm++)
+		if (!strcmp(name, gm->name) && gm->data && index < gm->size) {
+			const struct acpi_gpio_params *par = gm->data + index;
+
+			args->adev = adev;
+			args->args[0] = par->crs_entry_index;
+			args->args[1] = par->line_index;
+			args->args[2] = par->active_low;
+			args->nargs = 3;
+			return true;
+		}
+
+	return false;
+}
+
 struct acpi_gpio_lookup {
 	struct acpi_gpio_info info;
 	int index;
@@ -372,8 +407,12 @@ struct gpio_desc *acpi_get_gpiod_by_index(struct acpi_device *adev,
 		memset(&args, 0, sizeof(args));
 		ret = acpi_dev_get_property_reference(adev, propname, NULL,
 						      index, &args);
-		if (ret)
-			return ERR_PTR(ret);
+		if (ret) {
+			bool found = acpi_get_driver_gpio_data(adev, propname,
+							       index, &args);
+			if (!found)
+				return ERR_PTR(ret);
+		}
 
 		/*
 		 * The property was found and resolved so need to
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index a361f43b197..7d1ce40e201 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -345,6 +345,8 @@ struct acpi_device_data {
 	const union acpi_object *of_compatible;
 };
 
+struct acpi_gpio_mapping;
+
 /* Device */
 struct acpi_device {
 	int device_type;
@@ -366,6 +368,7 @@ struct acpi_device {
 	struct acpi_scan_handler *handler;
 	struct acpi_hotplug_context *hp;
 	struct acpi_driver *driver;
+	const struct acpi_gpio_mapping *driver_gpios;
 	void *driver_data;
 	struct device dev;
 	unsigned int physical_node_count;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 5b8802216a9..0902426c452 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -673,6 +673,36 @@ do {									\
 #endif
 #endif
 
+struct acpi_gpio_params {
+	unsigned int crs_entry_index;
+	unsigned int line_index;
+	bool active_low;
+};
+
+struct acpi_gpio_mapping {
+	const char *name;
+	const struct acpi_gpio_params *data;
+	unsigned int size;
+};
+
+#if defined(CONFIG_ACPI) && defined(CONFIG_GPIOLIB)
+int acpi_dev_add_driver_gpios(struct acpi_device *adev,
+			      const struct acpi_gpio_mapping *gpios);
+
+static inline void acpi_dev_remove_driver_gpios(struct acpi_device *adev)
+{
+	if (adev)
+		adev->driver_gpios = NULL;
+}
+#else
+static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev,
+			      const struct acpi_gpio_mapping *gpios)
+{
+	return -ENXIO;
+}
+static inline void acpi_dev_remove_driver_gpios(struct acpi_device *adev) {}
+#endif
+
 /* Device properties */
 
 #define MAX_ACPI_REFERENCE_ARGS	8
-- 
cgit v1.2.3-70-g09d2


From c673a2b4008103525a3cf21bedf15ffac37bfef0 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Fri, 31 Oct 2014 13:40:58 +0200
Subject: leds: leds-gpio: Convert gpio_blink_set() to use GPIO descriptors

Commit 21f2aae91e902aad ("leds: leds-gpio: Add support for GPIO
descriptors") already converted most of the driver to use GPIO descriptors.
What is still missing is the platform specific hook gpio_blink_set() and
board files which pass legacy GPIO numbers to this driver in platform data.

In this patch we handle the former and convert gpio_blink_set() to take
GPIO descriptor instead. In order to do this we convert the existing four
users to accept GPIO descriptor and translate it to legacy GPIO number in
the platform code. This effectively "pushes" legacy GPIO number usage from
the driver to platforms.

Also add comment to the remaining block describing that it is legacy code
path and we are getting rid of it eventually.

Suggested-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/arm/mach-s3c24xx/h1940-bluetooth.c       |  4 ++--
 arch/arm/mach-s3c24xx/h1940.h                 |  4 +++-
 arch/arm/mach-s3c24xx/mach-h1940.c            |  3 ++-
 arch/arm/mach-s3c24xx/mach-rx1950.c           |  3 ++-
 arch/arm/plat-orion/gpio.c                    |  3 ++-
 arch/arm/plat-orion/include/plat/orion-gpio.h |  5 ++++-
 drivers/leds/leds-gpio.c                      | 31 +++++++++++----------------
 include/linux/leds.h                          |  2 +-
 8 files changed, 29 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-s3c24xx/h1940-bluetooth.c b/arch/arm/mach-s3c24xx/h1940-bluetooth.c
index b4d14b86436..9c8b1279a4b 100644
--- a/arch/arm/mach-s3c24xx/h1940-bluetooth.c
+++ b/arch/arm/mach-s3c24xx/h1940-bluetooth.c
@@ -41,7 +41,7 @@ static void h1940bt_enable(int on)
 		mdelay(10);
 		gpio_set_value(S3C2410_GPH(1), 0);
 
-		h1940_led_blink_set(-EINVAL, GPIO_LED_BLINK, NULL, NULL);
+		h1940_led_blink_set(NULL, GPIO_LED_BLINK, NULL, NULL);
 	}
 	else {
 		gpio_set_value(S3C2410_GPH(1), 1);
@@ -50,7 +50,7 @@ static void h1940bt_enable(int on)
 		mdelay(10);
 		gpio_set_value(H1940_LATCH_BLUETOOTH_POWER, 0);
 
-		h1940_led_blink_set(-EINVAL, GPIO_LED_NO_BLINK_LOW, NULL, NULL);
+		h1940_led_blink_set(NULL, GPIO_LED_NO_BLINK_LOW, NULL, NULL);
 	}
 }
 
diff --git a/arch/arm/mach-s3c24xx/h1940.h b/arch/arm/mach-s3c24xx/h1940.h
index 2950cc46684..596d9f64c5b 100644
--- a/arch/arm/mach-s3c24xx/h1940.h
+++ b/arch/arm/mach-s3c24xx/h1940.h
@@ -19,8 +19,10 @@
 #define H1940_SUSPEND_RESUMEAT		(0x30081000)
 #define H1940_SUSPEND_CHECK		(0x30080000)
 
+struct gpio_desc;
+
 extern void h1940_pm_return(void);
-extern int h1940_led_blink_set(unsigned gpio, int state,
+extern int h1940_led_blink_set(struct gpio_desc *desc, int state,
 			       unsigned long *delay_on,
 			       unsigned long *delay_off);
 
diff --git a/arch/arm/mach-s3c24xx/mach-h1940.c b/arch/arm/mach-s3c24xx/mach-h1940.c
index d35ddc1d999..d40d4f5244c 100644
--- a/arch/arm/mach-s3c24xx/mach-h1940.c
+++ b/arch/arm/mach-s3c24xx/mach-h1940.c
@@ -359,10 +359,11 @@ static struct platform_device h1940_battery = {
 
 static DEFINE_SPINLOCK(h1940_blink_spin);
 
-int h1940_led_blink_set(unsigned gpio, int state,
+int h1940_led_blink_set(struct gpio_desc *desc, int state,
 	unsigned long *delay_on, unsigned long *delay_off)
 {
 	int blink_gpio, check_gpio1, check_gpio2;
+	int gpio = desc ? desc_to_gpio(desc) : -EINVAL;
 
 	switch (gpio) {
 	case H1940_LATCH_LED_GREEN:
diff --git a/arch/arm/mach-s3c24xx/mach-rx1950.c b/arch/arm/mach-s3c24xx/mach-rx1950.c
index c3f2682d0c6..1d35ff375a0 100644
--- a/arch/arm/mach-s3c24xx/mach-rx1950.c
+++ b/arch/arm/mach-s3c24xx/mach-rx1950.c
@@ -250,9 +250,10 @@ static void rx1950_disable_charger(void)
 
 static DEFINE_SPINLOCK(rx1950_blink_spin);
 
-static int rx1950_led_blink_set(unsigned gpio, int state,
+static int rx1950_led_blink_set(struct gpio_desc *desc, int state,
 	unsigned long *delay_on, unsigned long *delay_off)
 {
+	int gpio = desc_to_gpio(desc);
 	int blink_gpio, check_gpio;
 
 	switch (gpio) {
diff --git a/arch/arm/plat-orion/gpio.c b/arch/arm/plat-orion/gpio.c
index b61a3bcc2fa..b357053f40d 100644
--- a/arch/arm/plat-orion/gpio.c
+++ b/arch/arm/plat-orion/gpio.c
@@ -306,9 +306,10 @@ EXPORT_SYMBOL(orion_gpio_set_blink);
 
 #define ORION_BLINK_HALF_PERIOD 100 /* ms */
 
-int orion_gpio_led_blink_set(unsigned gpio, int state,
+int orion_gpio_led_blink_set(struct gpio_desc *desc, int state,
 	unsigned long *delay_on, unsigned long *delay_off)
 {
+	unsigned gpio = desc_to_gpio(desc);
 
 	if (delay_on && delay_off && !*delay_on && !*delay_off)
 		*delay_on = *delay_off = ORION_BLINK_HALF_PERIOD;
diff --git a/arch/arm/plat-orion/include/plat/orion-gpio.h b/arch/arm/plat-orion/include/plat/orion-gpio.h
index e763988b04b..e856b073a9c 100644
--- a/arch/arm/plat-orion/include/plat/orion-gpio.h
+++ b/arch/arm/plat-orion/include/plat/orion-gpio.h
@@ -14,12 +14,15 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/irqdomain.h>
+
+struct gpio_desc;
+
 /*
  * Orion-specific GPIO API extensions.
  */
 void orion_gpio_set_unused(unsigned pin);
 void orion_gpio_set_blink(unsigned pin, int blink);
-int orion_gpio_led_blink_set(unsigned gpio, int state,
+int orion_gpio_led_blink_set(struct gpio_desc *desc, int state,
 	unsigned long *delay_on, unsigned long *delay_off);
 
 #define GPIO_INPUT_OK		(1 << 0)
diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c
index edd370dbb22..ba4698c32bb 100644
--- a/drivers/leds/leds-gpio.c
+++ b/drivers/leds/leds-gpio.c
@@ -28,7 +28,7 @@ struct gpio_led_data {
 	u8 new_level;
 	u8 can_sleep;
 	u8 blinking;
-	int (*platform_gpio_blink_set)(unsigned gpio, int state,
+	int (*platform_gpio_blink_set)(struct gpio_desc *desc, int state,
 			unsigned long *delay_on, unsigned long *delay_off);
 };
 
@@ -38,13 +38,8 @@ static void gpio_led_work(struct work_struct *work)
 		container_of(work, struct gpio_led_data, work);
 
 	if (led_dat->blinking) {
-		int gpio = desc_to_gpio(led_dat->gpiod);
-		int level = led_dat->new_level;
-
-		if (gpiod_is_active_low(led_dat->gpiod))
-			level = !level;
-
-		led_dat->platform_gpio_blink_set(gpio, level, NULL, NULL);
+		led_dat->platform_gpio_blink_set(led_dat->gpiod,
+					led_dat->new_level, NULL, NULL);
 		led_dat->blinking = 0;
 	} else
 		gpiod_set_value_cansleep(led_dat->gpiod, led_dat->new_level);
@@ -71,13 +66,8 @@ static void gpio_led_set(struct led_classdev *led_cdev,
 		schedule_work(&led_dat->work);
 	} else {
 		if (led_dat->blinking) {
-			int gpio = desc_to_gpio(led_dat->gpiod);
-
-			if (gpiod_is_active_low(led_dat->gpiod))
-				level = !level;
-
-			led_dat->platform_gpio_blink_set(gpio, level, NULL,
-							 NULL);
+			led_dat->platform_gpio_blink_set(led_dat->gpiod, level,
+							 NULL, NULL);
 			led_dat->blinking = 0;
 		} else
 			gpiod_set_value(led_dat->gpiod, level);
@@ -89,20 +79,25 @@ static int gpio_blink_set(struct led_classdev *led_cdev,
 {
 	struct gpio_led_data *led_dat =
 		container_of(led_cdev, struct gpio_led_data, cdev);
-	int gpio = desc_to_gpio(led_dat->gpiod);
 
 	led_dat->blinking = 1;
-	return led_dat->platform_gpio_blink_set(gpio, GPIO_LED_BLINK,
+	return led_dat->platform_gpio_blink_set(led_dat->gpiod, GPIO_LED_BLINK,
 						delay_on, delay_off);
 }
 
 static int create_gpio_led(const struct gpio_led *template,
 	struct gpio_led_data *led_dat, struct device *parent,
-	int (*blink_set)(unsigned, int, unsigned long *, unsigned long *))
+	int (*blink_set)(struct gpio_desc *, int, unsigned long *,
+			 unsigned long *))
 {
 	int ret, state;
 
 	if (!template->gpiod) {
+		/*
+		 * This is the legacy code path for platform code that
+		 * still uses GPIO numbers. Ultimately we would like to get
+		 * rid of this block completely.
+		 */
 		unsigned long flags = 0;
 
 		/* skip leds that aren't available */
diff --git a/include/linux/leds.h b/include/linux/leds.h
index f3af5c4d908..361101fef27 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -274,7 +274,7 @@ struct gpio_led_platform_data {
 #define GPIO_LED_NO_BLINK_LOW	0	/* No blink GPIO state low */
 #define GPIO_LED_NO_BLINK_HIGH	1	/* No blink GPIO state high */
 #define GPIO_LED_BLINK		2	/* Please, blink */
-	int		(*gpio_blink_set)(unsigned gpio, int state,
+	int		(*gpio_blink_set)(struct gpio_desc *desc, int state,
 					unsigned long *delay_on,
 					unsigned long *delay_off);
 };
-- 
cgit v1.2.3-70-g09d2


From f1673381b1481a409238d4552a0700d490c5b36c Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 3 Nov 2014 17:35:02 +0100
Subject: syncookies: split cookie_check_timestamp() into two functions

The function cookie_check_timestamp(), both called from IPv4/6 context,
is being used to decode the echoed timestamp from the SYN/ACK into TCP
options used for follow-up communication with the peer.

We can remove ECN handling from that function, split it into a separate
one, and simply rename the original function into cookie_decode_options().
cookie_decode_options() just fills in tcp_option struct based on the
echoed timestamp received from the peer. Anything that fails in this
function will actually discard the request socket.

While this is the natural place for decoding options such as ECN which
commit 172d69e63c7f ("syncookies: add support for ECN") added, we argue
that in particular for ECN handling, it can be checked at a later point
in time as the request sock would actually not need to be dropped from
this, but just ECN support turned off.

Therefore, we split this functionality into cookie_ecn_ok(), which tells
us if the timestamp indicates ECN support AND the tcp_ecn sysctl is enabled.

This prepares for per-route ECN support: just looking at the tcp_ecn sysctl
won't be enough anymore at that point; if the timestamp indicates ECN
and sysctl tcp_ecn == 0, we will also need to check the ECN dst metric.

This would mean adding a route lookup to cookie_check_timestamp(), which
we definitely want to avoid. As we already do a route lookup at a later
point in cookie_{v4,v6}_check(), we can simply make use of that as well
for the new cookie_ecn_ok() function w/o any additional cost.

Joint work with Daniel Borkmann.

Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     |  9 ++++-----
 net/ipv4/syncookies.c | 31 +++++++++++++++++++++----------
 net/ipv6/syncookies.c |  5 ++---
 3 files changed, 27 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3a35b150035..36c5084964c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -490,17 +490,16 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
 			      u16 *mssp);
 __u32 cookie_v4_init_sequence(struct sock *sk, const struct sk_buff *skb,
 			      __u16 *mss);
-#endif
-
 __u32 cookie_init_timestamp(struct request_sock *req);
-bool cookie_check_timestamp(struct tcp_options_received *opt, struct net *net,
-			    bool *ecn_ok);
+bool cookie_timestamp_decode(struct tcp_options_received *opt);
+bool cookie_ecn_ok(const struct tcp_options_received *opt,
+		   const struct net *net);
 
 /* From net/ipv6/syncookies.c */
 int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
 		      u32 cookie);
 struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);
-#ifdef CONFIG_SYN_COOKIES
+
 u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
 			      const struct tcphdr *th, u16 *mssp);
 __u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb,
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index c3792c0557d..6de772500ee 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -241,10 +241,10 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
  * additional tcp options in the timestamp.
  * This extracts these options from the timestamp echo.
  *
- * return false if we decode an option that should not be.
+ * return false if we decode a tcp option that is disabled
+ * on the host.
  */
-bool cookie_check_timestamp(struct tcp_options_received *tcp_opt,
-			struct net *net, bool *ecn_ok)
+bool cookie_timestamp_decode(struct tcp_options_received *tcp_opt)
 {
 	/* echoed timestamp, lowest bits contain options */
 	u32 options = tcp_opt->rcv_tsecr;
@@ -258,9 +258,6 @@ bool cookie_check_timestamp(struct tcp_options_received *tcp_opt,
 		return false;
 
 	tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0;
-	*ecn_ok = options & TS_OPT_ECN;
-	if (*ecn_ok && !net->ipv4.sysctl_tcp_ecn)
-		return false;
 
 	if (tcp_opt->sack_ok && !sysctl_tcp_sack)
 		return false;
@@ -273,7 +270,22 @@ bool cookie_check_timestamp(struct tcp_options_received *tcp_opt,
 
 	return sysctl_tcp_window_scaling != 0;
 }
-EXPORT_SYMBOL(cookie_check_timestamp);
+EXPORT_SYMBOL(cookie_timestamp_decode);
+
+bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
+		   const struct net *net)
+{
+	bool ecn_ok = tcp_opt->rcv_tsecr & TS_OPT_ECN;
+
+	if (!ecn_ok)
+		return false;
+
+	if (net->ipv4.sysctl_tcp_ecn)
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL(cookie_ecn_ok);
 
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 {
@@ -289,7 +301,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	int mss;
 	struct rtable *rt;
 	__u8 rcv_wscale;
-	bool ecn_ok = false;
 	struct flowi4 fl4;
 
 	if (!sysctl_tcp_syncookies || !th->ack || th->rst)
@@ -310,7 +321,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
 	tcp_parse_options(skb, &tcp_opt, 0, NULL);
 
-	if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok))
+	if (!cookie_timestamp_decode(&tcp_opt))
 		goto out;
 
 	ret = NULL;
@@ -328,7 +339,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	ireq->ir_loc_addr	= ip_hdr(skb)->daddr;
 	ireq->ir_rmt_addr	= ip_hdr(skb)->saddr;
 	ireq->ir_mark		= inet_request_mark(sk, skb);
-	ireq->ecn_ok		= ecn_ok;
 	ireq->snd_wscale	= tcp_opt.snd_wscale;
 	ireq->sack_ok		= tcp_opt.sack_ok;
 	ireq->wscale_ok		= tcp_opt.wscale_ok;
@@ -377,6 +387,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 				  dst_metric(&rt->dst, RTAX_INITRWND));
 
 	ireq->rcv_wscale  = rcv_wscale;
+	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk));
 
 	ret = get_cookie_sock(sk, skb, req, &rt->dst);
 	/* ip_queue_xmit() depends on our flow being setup
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index be291baa2ec..52cc8cb02c0 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -166,7 +166,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	int mss;
 	struct dst_entry *dst;
 	__u8 rcv_wscale;
-	bool ecn_ok = false;
 
 	if (!sysctl_tcp_syncookies || !th->ack || th->rst)
 		goto out;
@@ -186,7 +185,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
 	tcp_parse_options(skb, &tcp_opt, 0, NULL);
 
-	if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok))
+	if (!cookie_timestamp_decode(&tcp_opt))
 		goto out;
 
 	ret = NULL;
@@ -223,7 +222,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 
 	req->expires = 0UL;
 	req->num_retrans = 0;
-	ireq->ecn_ok		= ecn_ok;
 	ireq->snd_wscale	= tcp_opt.snd_wscale;
 	ireq->sack_ok		= tcp_opt.sack_ok;
 	ireq->wscale_ok		= tcp_opt.wscale_ok;
@@ -264,6 +262,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 				  dst_metric(dst, RTAX_INITRWND));
 
 	ireq->rcv_wscale = rcv_wscale;
+	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk));
 
 	ret = get_cookie_sock(sk, skb, req, dst);
 out:
-- 
cgit v1.2.3-70-g09d2


From f7b3bec6f5167efaf56b756abfafb924cb1d3050 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 3 Nov 2014 17:35:03 +0100
Subject: net: allow setting ecn via routing table

This patch allows to set ECN on a per-route basis in case the sysctl
tcp_ecn is not set to 1. In other words, when ECN is set for specific
routes, it provides a tcp_ecn=1 behaviour for that route while the rest
of the stack acts according to the global settings.

One can use 'ip route change dev $dev $net features ecn' to toggle this.

Having a more fine-grained per-route setting can be beneficial for various
reasons, for example, 1) within data centers, or 2) local ISPs may deploy
ECN support for their own video/streaming services [1], etc.

There was a recent measurement study/paper [2] which scanned the Alexa's
publicly available top million websites list from a vantage point in US,
Europe and Asia:

Half of the Alexa list will now happily use ECN (tcp_ecn=2, most likely
blamed to commit 255cac91c3 ("tcp: extend ECN sysctl to allow server-side
only ECN") ;)); the break in connectivity on-path was found is about
1 in 10,000 cases. Timeouts rather than receiving back RSTs were much
more common in the negotiation phase (and mostly seen in the Alexa
middle band, ranks around 50k-150k): from 12-thousand hosts on which
there _may_ be ECN-linked connection failures, only 79 failed with RST
when _not_ failing with RST when ECN is not requested.

It's unclear though, how much equipment in the wild actually marks CE
when buffers start to fill up.

We thought about a fallback to non-ECN for retransmitted SYNs as another
global option (which could perhaps one day be made default), but as Eric
points out, there's much more work needed to detect broken middleboxes.

Two examples Eric mentioned are buggy firewalls that accept only a single
SYN per flow, and middleboxes that successfully let an ECN flow establish,
but later mark CE for all packets (so cwnd converges to 1).

 [1] http://www.ietf.org/proceedings/89/slides/slides-89-tsvarea-1.pdf, p.15
 [2] http://ecn.ethz.ch/

Joint work with Daniel Borkmann.

Reference: http://thread.gmane.org/gmane.linux.network/335797
Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     |  2 +-
 net/ipv4/syncookies.c |  6 +++---
 net/ipv4/tcp_input.c  | 25 +++++++++++++++----------
 net/ipv4/tcp_output.c | 13 +++++++++++--
 net/ipv6/syncookies.c |  2 +-
 5 files changed, 31 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 36c5084964c..f50f29faf76 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -493,7 +493,7 @@ __u32 cookie_v4_init_sequence(struct sock *sk, const struct sk_buff *skb,
 __u32 cookie_init_timestamp(struct request_sock *req);
 bool cookie_timestamp_decode(struct tcp_options_received *opt);
 bool cookie_ecn_ok(const struct tcp_options_received *opt,
-		   const struct net *net);
+		   const struct net *net, const struct dst_entry *dst);
 
 /* From net/ipv6/syncookies.c */
 int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 6de772500ee..45fe60c5238 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -273,7 +273,7 @@ bool cookie_timestamp_decode(struct tcp_options_received *tcp_opt)
 EXPORT_SYMBOL(cookie_timestamp_decode);
 
 bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
-		   const struct net *net)
+		   const struct net *net, const struct dst_entry *dst)
 {
 	bool ecn_ok = tcp_opt->rcv_tsecr & TS_OPT_ECN;
 
@@ -283,7 +283,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
 	if (net->ipv4.sysctl_tcp_ecn)
 		return true;
 
-	return false;
+	return dst_feature(dst, RTAX_FEATURE_ECN);
 }
 EXPORT_SYMBOL(cookie_ecn_ok);
 
@@ -387,7 +387,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 				  dst_metric(&rt->dst, RTAX_INITRWND));
 
 	ireq->rcv_wscale  = rcv_wscale;
-	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk));
+	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), &rt->dst);
 
 	ret = get_cookie_sock(sk, skb, req, &rt->dst);
 	/* ip_queue_xmit() depends on our flow being setup
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4e4617e9041..196b4388116 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5876,20 +5876,22 @@ static inline void pr_drop_req(struct request_sock *req, __u16 port, int family)
  */
 static void tcp_ecn_create_request(struct request_sock *req,
 				   const struct sk_buff *skb,
-				   const struct sock *listen_sk)
+				   const struct sock *listen_sk,
+				   const struct dst_entry *dst)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
 	const struct net *net = sock_net(listen_sk);
 	bool th_ecn = th->ece && th->cwr;
-	bool ect, need_ecn;
+	bool ect, need_ecn, ecn_ok;
 
 	if (!th_ecn)
 		return;
 
 	ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield);
 	need_ecn = tcp_ca_needs_ecn(listen_sk);
+	ecn_ok = net->ipv4.sysctl_tcp_ecn || dst_feature(dst, RTAX_FEATURE_ECN);
 
-	if (!ect && !need_ecn && net->ipv4.sysctl_tcp_ecn)
+	if (!ect && !need_ecn && ecn_ok)
 		inet_rsk(req)->ecn_ok = 1;
 	else if (ect && need_ecn)
 		inet_rsk(req)->ecn_ok = 1;
@@ -5954,13 +5956,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if (security_inet_conn_request(sk, skb, req))
 		goto drop_and_free;
 
-	if (!want_cookie || tmp_opt.tstamp_ok)
-		tcp_ecn_create_request(req, skb, sk);
-
-	if (want_cookie) {
-		isn = cookie_init_sequence(af_ops, sk, skb, &req->mss);
-		req->cookie_ts = tmp_opt.tstamp_ok;
-	} else if (!isn) {
+	if (!want_cookie && !isn) {
 		/* VJ's idea. We save last timestamp seen
 		 * from the destination in peer table, when entering
 		 * state TIME-WAIT, and check against it before
@@ -6008,6 +6004,15 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			goto drop_and_free;
 	}
 
+	tcp_ecn_create_request(req, skb, sk, dst);
+
+	if (want_cookie) {
+		isn = cookie_init_sequence(af_ops, sk, skb, &req->mss);
+		req->cookie_ts = tmp_opt.tstamp_ok;
+		if (!tmp_opt.tstamp_ok)
+			inet_rsk(req)->ecn_ok = 0;
+	}
+
 	tcp_rsk(req)->snt_isn = isn;
 	tcp_openreq_init_rwin(req, sk, dst);
 	fastopen = !want_cookie &&
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a3d453b9474..0b88158dd4a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -333,10 +333,19 @@ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb)
 static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
+		       tcp_ca_needs_ecn(sk);
+
+	if (!use_ecn) {
+		const struct dst_entry *dst = __sk_dst_get(sk);
+
+		if (dst && dst_feature(dst, RTAX_FEATURE_ECN))
+			use_ecn = true;
+	}
 
 	tp->ecn_flags = 0;
-	if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
-	    tcp_ca_needs_ecn(sk)) {
+
+	if (use_ecn) {
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
 		tp->ecn_flags = TCP_ECN_OK;
 		if (tcp_ca_needs_ecn(sk))
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 52cc8cb02c0..7337fc7947e 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -262,7 +262,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 				  dst_metric(dst, RTAX_INITRWND));
 
 	ireq->rcv_wscale = rcv_wscale;
-	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk));
+	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), dst);
 
 	ret = get_cookie_sock(sk, skb, req, dst);
 out:
-- 
cgit v1.2.3-70-g09d2


From b3d208f96d6bb21247108a956dead6a028d5cdb2 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Thu, 23 Oct 2014 19:48:09 -0700
Subject: f2fs: revisit inline_data to avoid data races and potential bugs

This patch simplifies the inline_data usage with the following rule.
1. inline_data is set during the file creation.
2. If new data is requested to be written ranges out of inline_data,
 f2fs converts that inode permanently.
3. There is no cases which converts non-inline_data inode to inline_data.
4. The inline_data flag should be changed under inode page lock.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c          |  89 ++++++++++-----------
 fs/f2fs/f2fs.h          |  24 +++++-
 fs/f2fs/file.c          | 110 ++++++++++++--------------
 fs/f2fs/inline.c        | 203 +++++++++++++++++++++++-------------------------
 fs/f2fs/inode.c         |  33 +++++++-
 fs/f2fs/namei.c         |   3 +
 include/linux/f2fs_fs.h |   1 +
 7 files changed, 251 insertions(+), 212 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index e3788bd206d..ceee1a69c5a 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -737,14 +737,14 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 static int f2fs_read_data_page(struct file *file, struct page *page)
 {
 	struct inode *inode = page->mapping->host;
-	int ret;
+	int ret = -EAGAIN;
 
 	trace_f2fs_readpage(page, DATA);
 
 	/* If the file has inline data, try to read it directly */
 	if (f2fs_has_inline_data(inode))
 		ret = f2fs_read_inline_data(inode, page);
-	else
+	if (ret == -EAGAIN)
 		ret = mpage_readpage(page, get_data_block);
 
 	return ret;
@@ -856,10 +856,11 @@ write:
 	else if (has_not_enough_free_secs(sbi, 0))
 		goto redirty_out;
 
+	err = -EAGAIN;
 	f2fs_lock_op(sbi);
-	if (f2fs_has_inline_data(inode) || f2fs_may_inline(inode))
-		err = f2fs_write_inline_data(inode, page, offset);
-	else
+	if (f2fs_has_inline_data(inode))
+		err = f2fs_write_inline_data(inode, page);
+	if (err == -EAGAIN)
 		err = do_write_data_page(page, &fio);
 	f2fs_unlock_op(sbi);
 done:
@@ -957,24 +958,14 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 
 	f2fs_balance_fs(sbi);
 repeat:
-	err = f2fs_convert_inline_data(inode, pos + len, NULL);
-	if (err)
-		goto fail;
-
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page) {
 		err = -ENOMEM;
 		goto fail;
 	}
 
-	/* to avoid latency during memory pressure */
-	unlock_page(page);
-
 	*pagep = page;
 
-	if (f2fs_has_inline_data(inode) && (pos + len) <= MAX_INLINE_DATA)
-		goto inline_data;
-
 	f2fs_lock_op(sbi);
 
 	/* check inline_data */
@@ -982,32 +973,42 @@ repeat:
 	if (IS_ERR(ipage))
 		goto unlock_fail;
 
+	set_new_dnode(&dn, inode, ipage, ipage, 0);
+
 	if (f2fs_has_inline_data(inode)) {
-		f2fs_put_page(ipage, 1);
-		f2fs_unlock_op(sbi);
-		f2fs_put_page(page, 0);
-		goto repeat;
+		if (pos + len <= MAX_INLINE_DATA) {
+			read_inline_data(page, ipage);
+			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+			sync_inode_page(&dn);
+			goto put_next;
+		} else if (page->index == 0) {
+			err = f2fs_convert_inline_page(&dn, page);
+			if (err)
+				goto unlock_fail;
+		} else {
+			struct page *p = grab_cache_page(inode->i_mapping, 0);
+			if (!p) {
+				err = -ENOMEM;
+				goto unlock_fail;
+			}
+			err = f2fs_convert_inline_page(&dn, p);
+			f2fs_put_page(p, 1);
+			if (err)
+				goto unlock_fail;
+		}
 	}
-
-	set_new_dnode(&dn, inode, ipage, NULL, 0);
 	err = f2fs_reserve_block(&dn, index);
 	if (err)
 		goto unlock_fail;
+put_next:
 	f2fs_put_dnode(&dn);
 	f2fs_unlock_op(sbi);
 
-inline_data:
-	lock_page(page);
-	if (unlikely(page->mapping != mapping)) {
-		f2fs_put_page(page, 1);
-		goto repeat;
-	}
-
-	f2fs_wait_on_page_writeback(page, DATA);
-
 	if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
 		return 0;
 
+	f2fs_wait_on_page_writeback(page, DATA);
+
 	if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
 		unsigned start = pos & (PAGE_CACHE_SIZE - 1);
 		unsigned end = start + len;
@@ -1017,13 +1018,7 @@ inline_data:
 		goto out;
 	}
 
-	if (f2fs_has_inline_data(inode)) {
-		err = f2fs_read_inline_data(inode, page);
-		if (err) {
-			page_cache_release(page);
-			goto fail;
-		}
-	} else if (dn.data_blkaddr == NEW_ADDR) {
+	if (dn.data_blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 	} else {
 		err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
@@ -1049,7 +1044,7 @@ out:
 
 unlock_fail:
 	f2fs_unlock_op(sbi);
-	f2fs_put_page(page, 0);
+	f2fs_put_page(page, 1);
 fail:
 	f2fs_write_failed(mapping, pos + len);
 	return err;
@@ -1102,9 +1097,12 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
 	size_t count = iov_iter_count(iter);
 	int err;
 
-	/* Let buffer I/O handle the inline data case. */
-	if (f2fs_has_inline_data(inode))
-		return 0;
+	/* we don't need to use inline_data strictly */
+	if (f2fs_has_inline_data(inode)) {
+		err = f2fs_convert_inline_inode(inode);
+		if (err)
+			return err;
+	}
 
 	if (check_direct_IO(inode, rw, iter, offset))
 		return 0;
@@ -1170,9 +1168,12 @@ static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
 {
 	struct inode *inode = mapping->host;
 
-	if (f2fs_has_inline_data(inode))
-		return 0;
-
+	/* we don't need to use inline_data strictly */
+	if (f2fs_has_inline_data(inode)) {
+		int err = f2fs_convert_inline_inode(inode);
+		if (err)
+			return err;
+	}
 	return generic_block_bmap(mapping, block, get_data_block);
 }
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 2e9d2e3051f..afe3022ffac 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1101,6 +1101,7 @@ enum {
 	FI_NEED_IPU,		/* used for ipu per file */
 	FI_ATOMIC_FILE,		/* indicate atomic file */
 	FI_VOLATILE_FILE,	/* indicate volatile file */
+	FI_DATA_EXIST,		/* indicate data exists */
 };
 
 static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag)
@@ -1135,6 +1136,8 @@ static inline void get_inline_info(struct f2fs_inode_info *fi,
 		set_inode_flag(fi, FI_INLINE_DATA);
 	if (ri->i_inline & F2FS_INLINE_DENTRY)
 		set_inode_flag(fi, FI_INLINE_DENTRY);
+	if (ri->i_inline & F2FS_DATA_EXIST)
+		set_inode_flag(fi, FI_DATA_EXIST);
 }
 
 static inline void set_raw_inline(struct f2fs_inode_info *fi,
@@ -1148,6 +1151,8 @@ static inline void set_raw_inline(struct f2fs_inode_info *fi,
 		ri->i_inline |= F2FS_INLINE_DATA;
 	if (is_inode_flag_set(fi, FI_INLINE_DENTRY))
 		ri->i_inline |= F2FS_INLINE_DENTRY;
+	if (is_inode_flag_set(fi, FI_DATA_EXIST))
+		ri->i_inline |= F2FS_DATA_EXIST;
 }
 
 static inline int f2fs_has_inline_xattr(struct inode *inode)
@@ -1182,6 +1187,17 @@ static inline int f2fs_has_inline_data(struct inode *inode)
 	return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DATA);
 }
 
+static inline void f2fs_clear_inline_inode(struct inode *inode)
+{
+	clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
+	clear_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+}
+
+static inline int f2fs_exist_data(struct inode *inode)
+{
+	return is_inode_flag_set(F2FS_I(inode), FI_DATA_EXIST);
+}
+
 static inline bool f2fs_is_atomic_file(struct inode *inode)
 {
 	return is_inode_flag_set(F2FS_I(inode), FI_ATOMIC_FILE);
@@ -1590,10 +1606,12 @@ extern const struct inode_operations f2fs_special_inode_operations;
  * inline.c
  */
 bool f2fs_may_inline(struct inode *);
+void read_inline_data(struct page *, struct page *);
 int f2fs_read_inline_data(struct inode *, struct page *);
-int f2fs_convert_inline_data(struct inode *, pgoff_t, struct page *);
-int f2fs_write_inline_data(struct inode *, struct page *, unsigned int);
-void truncate_inline_data(struct inode *, u64);
+int f2fs_convert_inline_page(struct dnode_of_data *, struct page *);
+int f2fs_convert_inline_inode(struct inode *);
+int f2fs_write_inline_data(struct inode *, struct page *);
+void truncate_inline_data(struct page *, u64);
 bool recover_inline_data(struct inode *, struct page *);
 struct f2fs_dir_entry *find_in_inline_dir(struct inode *, struct qstr *,
 							struct page **);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 402e38185b8..832bd91922b 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -35,35 +35,17 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 	struct inode *inode = file_inode(vma->vm_file);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct dnode_of_data dn;
-	struct page *ipage;
 	int err;
 
 	f2fs_balance_fs(sbi);
 
 	sb_start_pagefault(inode->i_sb);
-retry:
-	/* force to convert with normal data indices */
-	err = f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1, page);
-	if (err)
-		goto out;
+
+	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
 
 	/* block allocation */
 	f2fs_lock_op(sbi);
-
-	/* check inline_data */
-	ipage = get_node_page(sbi, inode->i_ino);
-	if (IS_ERR(ipage)) {
-		f2fs_unlock_op(sbi);
-		goto out;
-	}
-
-	if (f2fs_has_inline_data(inode)) {
-		f2fs_put_page(ipage, 1);
-		f2fs_unlock_op(sbi);
-		goto retry;
-	}
-
-	set_new_dnode(&dn, inode, ipage, NULL, 0);
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = f2fs_reserve_block(&dn, page->index);
 	if (err) {
 		f2fs_unlock_op(sbi);
@@ -392,6 +374,15 @@ static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
 
 static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
+	struct inode *inode = file_inode(file);
+
+	/* we don't need to use inline_data strictly */
+	if (f2fs_has_inline_data(inode)) {
+		int err = f2fs_convert_inline_inode(inode);
+		if (err)
+			return err;
+	}
+
 	file_accessed(file);
 	vma->vm_ops = &f2fs_file_vm_ops;
 	return 0;
@@ -433,20 +424,17 @@ void truncate_data_blocks(struct dnode_of_data *dn)
 	truncate_data_blocks_range(dn, ADDRS_PER_BLOCK);
 }
 
-static void truncate_partial_data_page(struct inode *inode, u64 from)
+static int truncate_partial_data_page(struct inode *inode, u64 from)
 {
 	unsigned offset = from & (PAGE_CACHE_SIZE - 1);
 	struct page *page;
 
-	if (f2fs_has_inline_data(inode))
-		return truncate_inline_data(inode, from);
-
 	if (!offset)
-		return;
+		return 0;
 
 	page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, false);
 	if (IS_ERR(page))
-		return;
+		return 0;
 
 	lock_page(page);
 	if (unlikely(!PageUptodate(page) ||
@@ -456,9 +444,9 @@ static void truncate_partial_data_page(struct inode *inode, u64 from)
 	f2fs_wait_on_page_writeback(page, DATA);
 	zero_user(page, offset, PAGE_CACHE_SIZE - offset);
 	set_page_dirty(page);
-
 out:
 	f2fs_put_page(page, 1);
+	return 0;
 }
 
 int truncate_blocks(struct inode *inode, u64 from, bool lock)
@@ -468,33 +456,35 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 	struct dnode_of_data dn;
 	pgoff_t free_from;
 	int count = 0, err = 0;
+	struct page *ipage;
 
 	trace_f2fs_truncate_blocks_enter(inode, from);
 
-	if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode))
-		goto done;
-
 	free_from = (pgoff_t)
-			((from + blocksize - 1) >> (sbi->log_blocksize));
+		((from + blocksize - 1) >> (sbi->log_blocksize));
 
 	if (lock)
 		f2fs_lock_op(sbi);
 
-	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	ipage = get_node_page(sbi, inode->i_ino);
+	if (IS_ERR(ipage)) {
+		err = PTR_ERR(ipage);
+		goto out;
+	}
+
+	if (f2fs_has_inline_data(inode)) {
+		truncate_inline_data(ipage, from);
+		update_inode(inode, ipage);
+		f2fs_put_page(ipage, 1);
+		goto out;
+	}
+
+	set_new_dnode(&dn, inode, ipage, NULL, 0);
 	err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE);
 	if (err) {
 		if (err == -ENOENT)
 			goto free_next;
-		if (lock)
-			f2fs_unlock_op(sbi);
-		trace_f2fs_truncate_blocks_exit(inode, err);
-		return err;
-	}
-
-	/* writepage can convert inline_data under get_donde_of_data */
-	if (f2fs_has_inline_data(inode)) {
-		f2fs_put_dnode(&dn);
-		goto unlock_done;
+		goto out;
 	}
 
 	count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
@@ -510,12 +500,13 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 	f2fs_put_dnode(&dn);
 free_next:
 	err = truncate_inode_blocks(inode, free_from);
-unlock_done:
+
+	/* lastly zero out the first data page */
+	if (!err)
+		err = truncate_partial_data_page(inode, from);
+out:
 	if (lock)
 		f2fs_unlock_op(sbi);
-done:
-	/* lastly zero out the first data page */
-	truncate_partial_data_page(inode, from);
 
 	trace_f2fs_truncate_blocks_exit(inode, err);
 	return err;
@@ -586,10 +577,6 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 		return err;
 
 	if (attr->ia_valid & ATTR_SIZE) {
-		err = f2fs_convert_inline_data(inode, attr->ia_size, NULL);
-		if (err)
-			return err;
-
 		if (attr->ia_size != i_size_read(inode)) {
 			truncate_setsize(inode, attr->ia_size);
 			f2fs_truncate(inode);
@@ -690,9 +677,11 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	if (offset >= inode->i_size)
 		return ret;
 
-	ret = f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1, NULL);
-	if (ret)
-		return ret;
+	if (f2fs_has_inline_data(inode)) {
+		ret = f2fs_convert_inline_inode(inode);
+		if (ret)
+			return ret;
+	}
 
 	pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
 	pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
@@ -746,9 +735,11 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 	if (ret)
 		return ret;
 
-	ret = f2fs_convert_inline_data(inode, offset + len, NULL);
-	if (ret)
-		return ret;
+	if (f2fs_has_inline_data(inode)) {
+		ret = f2fs_convert_inline_inode(inode);
+		if (ret)
+			return ret;
+	}
 
 	pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
 	pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
@@ -899,7 +890,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 
 	set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 
-	return f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1, NULL);
+	return f2fs_convert_inline_inode(inode);
 }
 
 static int f2fs_ioc_commit_atomic_write(struct file *filp)
@@ -933,7 +924,8 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
 		return -EACCES;
 
 	set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
-	return 0;
+
+	return f2fs_convert_inline_inode(inode);
 }
 
 static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index d6677d6bbd8..8b6610906ea 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -15,41 +15,26 @@
 
 bool f2fs_may_inline(struct inode *inode)
 {
-	block_t nr_blocks;
-	loff_t i_size;
-
 	if (!test_opt(F2FS_I_SB(inode), INLINE_DATA))
 		return false;
 
 	if (f2fs_is_atomic_file(inode))
 		return false;
 
-	nr_blocks = F2FS_I(inode)->i_xattr_nid ? 3 : 2;
-	if (inode->i_blocks > nr_blocks)
-		return false;
-
-	i_size = i_size_read(inode);
-	if (i_size > MAX_INLINE_DATA)
+	if (!S_ISREG(inode->i_mode))
 		return false;
 
 	return true;
 }
 
-int f2fs_read_inline_data(struct inode *inode, struct page *page)
+void read_inline_data(struct page *page, struct page *ipage)
 {
-	struct page *ipage;
 	void *src_addr, *dst_addr;
 
-	if (page->index) {
-		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
-		goto out;
-	}
+	if (PageUptodate(page))
+		return;
 
-	ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
-	if (IS_ERR(ipage)) {
-		unlock_page(page);
-		return PTR_ERR(ipage);
-	}
+	f2fs_bug_on(F2FS_P_SB(page), page->index);
 
 	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
 
@@ -59,104 +44,120 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
 	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
 	flush_dcache_page(page);
 	kunmap_atomic(dst_addr);
-	f2fs_put_page(ipage, 1);
-out:
 	SetPageUptodate(page);
-	unlock_page(page);
+}
 
+int f2fs_read_inline_data(struct inode *inode, struct page *page)
+{
+	struct page *ipage;
+
+	ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
+	if (IS_ERR(ipage)) {
+		unlock_page(page);
+		return PTR_ERR(ipage);
+	}
+
+	if (!f2fs_has_inline_data(inode)) {
+		f2fs_put_page(ipage, 1);
+		return -EAGAIN;
+	}
+
+	if (page->index)
+		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+	else
+		read_inline_data(page, ipage);
+
+	SetPageUptodate(page);
+	f2fs_put_page(ipage, 1);
+	unlock_page(page);
 	return 0;
 }
 
-static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
+int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 {
-	int err = 0;
-	struct page *ipage;
-	struct dnode_of_data dn;
 	void *src_addr, *dst_addr;
 	block_t new_blk_addr;
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_io_info fio = {
 		.type = DATA,
 		.rw = WRITE_SYNC | REQ_PRIO,
 	};
+	int err;
 
-	f2fs_lock_op(sbi);
-	ipage = get_node_page(sbi, inode->i_ino);
-	if (IS_ERR(ipage)) {
-		err = PTR_ERR(ipage);
-		goto out;
-	}
+	f2fs_bug_on(F2FS_I_SB(dn->inode), page->index);
 
-	/* someone else converted inline_data already */
-	if (!f2fs_has_inline_data(inode))
-		goto out;
+	if (!f2fs_exist_data(dn->inode))
+		goto clear_out;
 
-	/*
-	 * i_addr[0] is not used for inline data,
-	 * so reserving new block will not destroy inline data
-	 */
-	set_new_dnode(&dn, inode, ipage, NULL, 0);
-	err = f2fs_reserve_block(&dn, 0);
+	err = f2fs_reserve_block(dn, 0);
 	if (err)
-		goto out;
+		return err;
 
 	f2fs_wait_on_page_writeback(page, DATA);
+
+	if (PageUptodate(page))
+		goto no_update;
+
 	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
 
 	/* Copy the whole inline data block */
-	src_addr = inline_data_addr(ipage);
+	src_addr = inline_data_addr(dn->inode_page);
 	dst_addr = kmap_atomic(page);
 	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
 	kunmap_atomic(dst_addr);
 	SetPageUptodate(page);
-
+no_update:
 	/* write data page to try to make data consistent */
 	set_page_writeback(page);
-	write_data_page(page, &dn, &new_blk_addr, &fio);
-	update_extent_cache(new_blk_addr, &dn);
+
+	write_data_page(page, dn, &new_blk_addr, &fio);
+	update_extent_cache(new_blk_addr, dn);
 	f2fs_wait_on_page_writeback(page, DATA);
 
 	/* clear inline data and flag after data writeback */
-	zero_user_segment(ipage, INLINE_DATA_OFFSET,
-				 INLINE_DATA_OFFSET + MAX_INLINE_DATA);
-	clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
-	stat_dec_inline_inode(inode);
-
-	sync_inode_page(&dn);
-	f2fs_put_dnode(&dn);
-out:
-	f2fs_unlock_op(sbi);
-	return err;
+	truncate_inline_data(dn->inode_page, 0);
+clear_out:
+	f2fs_clear_inline_inode(dn->inode);
+	stat_dec_inline_inode(dn->inode);
+	sync_inode_page(dn);
+	f2fs_put_dnode(dn);
+	return 0;
 }
 
-int f2fs_convert_inline_data(struct inode *inode, pgoff_t to_size,
-						struct page *page)
+int f2fs_convert_inline_inode(struct inode *inode)
 {
-	struct page *new_page = page;
-	int err;
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct dnode_of_data dn;
+	struct page *ipage, *page;
+	int err = 0;
 
-	if (!f2fs_has_inline_data(inode))
-		return 0;
-	else if (to_size <= MAX_INLINE_DATA)
-		return 0;
+	page = grab_cache_page(inode->i_mapping, 0);
+	if (!page)
+		return -ENOMEM;
 
-	if (!page || page->index != 0) {
-		new_page = grab_cache_page(inode->i_mapping, 0);
-		if (!new_page)
-			return -ENOMEM;
+	f2fs_lock_op(sbi);
+
+	ipage = get_node_page(sbi, inode->i_ino);
+	if (IS_ERR(ipage)) {
+		f2fs_unlock_op(sbi);
+		return PTR_ERR(ipage);
 	}
 
-	err = __f2fs_convert_inline_data(inode, new_page);
-	if (!page || page->index != 0)
-		f2fs_put_page(new_page, 1);
+	set_new_dnode(&dn, inode, ipage, ipage, 0);
+
+	if (f2fs_has_inline_data(inode))
+		err = f2fs_convert_inline_page(&dn, page);
+
+	f2fs_put_dnode(&dn);
+
+	f2fs_unlock_op(sbi);
+
+	f2fs_put_page(page, 1);
 	return err;
 }
 
-int f2fs_write_inline_data(struct inode *inode,
-				struct page *page, unsigned size)
+int f2fs_write_inline_data(struct inode *inode, struct page *page)
 {
 	void *src_addr, *dst_addr;
-	struct page *ipage;
 	struct dnode_of_data dn;
 	int err;
 
@@ -164,48 +165,39 @@ int f2fs_write_inline_data(struct inode *inode,
 	err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
 	if (err)
 		return err;
-	ipage = dn.inode_page;
 
-	/* Release any data block if it is allocated */
 	if (!f2fs_has_inline_data(inode)) {
-		int count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
-		truncate_data_blocks_range(&dn, count);
-		set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
-		stat_inc_inline_inode(inode);
+		f2fs_put_dnode(&dn);
+		return -EAGAIN;
 	}
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
-	zero_user_segment(ipage, INLINE_DATA_OFFSET,
-				 INLINE_DATA_OFFSET + MAX_INLINE_DATA);
+	f2fs_bug_on(F2FS_I_SB(inode), page->index);
+
+	f2fs_wait_on_page_writeback(dn.inode_page, NODE);
 	src_addr = kmap_atomic(page);
-	dst_addr = inline_data_addr(ipage);
-	memcpy(dst_addr, src_addr, size);
+	dst_addr = inline_data_addr(dn.inode_page);
+	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
 	kunmap_atomic(src_addr);
 
 	set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
+	set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+
 	sync_inode_page(&dn);
 	f2fs_put_dnode(&dn);
-
 	return 0;
 }
 
-void truncate_inline_data(struct inode *inode, u64 from)
+void truncate_inline_data(struct page *ipage, u64 from)
 {
-	struct page *ipage;
+	void *addr;
 
 	if (from >= MAX_INLINE_DATA)
 		return;
 
-	ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
-	if (IS_ERR(ipage))
-		return;
-
 	f2fs_wait_on_page_writeback(ipage, NODE);
 
-	zero_user_segment(ipage, INLINE_DATA_OFFSET + from,
-				INLINE_DATA_OFFSET + MAX_INLINE_DATA);
-	set_page_dirty(ipage);
-	f2fs_put_page(ipage, 1);
+	addr = inline_data_addr(ipage);
+	memset(addr + from, 0, MAX_INLINE_DATA - from);
 }
 
 bool recover_inline_data(struct inode *inode, struct page *npage)
@@ -237,6 +229,10 @@ process_inline:
 		src_addr = inline_data_addr(npage);
 		dst_addr = inline_data_addr(ipage);
 		memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
+
+		set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
+		set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+
 		update_inode(inode, ipage);
 		f2fs_put_page(ipage, 1);
 		return true;
@@ -245,15 +241,12 @@ process_inline:
 	if (f2fs_has_inline_data(inode)) {
 		ipage = get_node_page(sbi, inode->i_ino);
 		f2fs_bug_on(sbi, IS_ERR(ipage));
-		f2fs_wait_on_page_writeback(ipage, NODE);
-		zero_user_segment(ipage, INLINE_DATA_OFFSET,
-				 INLINE_DATA_OFFSET + MAX_INLINE_DATA);
-		clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
+		truncate_inline_data(ipage, 0);
+		f2fs_clear_inline_inode(inode);
 		update_inode(inode, ipage);
 		f2fs_put_page(ipage, 1);
 	} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
 		truncate_blocks(inode, 0, false);
-		set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
 		goto process_inline;
 	}
 	return false;
@@ -366,8 +359,8 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 	set_page_dirty(page);
 
 	/* clear inline dir and flag after data writeback */
-	zero_user_segment(ipage, INLINE_DATA_OFFSET,
-				 INLINE_DATA_OFFSET + MAX_INLINE_DATA);
+	truncate_inline_data(ipage, 0);
+
 	stat_dec_inline_dir(dir);
 	clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
 
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 4131e3cfd1c..9fe110ef8cc 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -67,12 +67,38 @@ static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
 	}
 }
 
+static int __recover_inline_status(struct inode *inode, struct page *ipage)
+{
+	void *inline_data = inline_data_addr(ipage);
+	struct f2fs_inode *ri;
+	void *zbuf;
+
+	zbuf = kzalloc(MAX_INLINE_DATA, GFP_NOFS);
+	if (!zbuf)
+		return -ENOMEM;
+
+	if (!memcmp(zbuf, inline_data, MAX_INLINE_DATA)) {
+		kfree(zbuf);
+		return 0;
+	}
+	kfree(zbuf);
+
+	f2fs_wait_on_page_writeback(ipage, NODE);
+	set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+
+	ri = F2FS_INODE(ipage);
+	set_raw_inline(F2FS_I(inode), ri);
+	set_page_dirty(ipage);
+	return 0;
+}
+
 static int do_read_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct page *node_page;
 	struct f2fs_inode *ri;
+	int err = 0;
 
 	/* Check if ino is within scope */
 	if (check_nid_range(sbi, inode->i_ino)) {
@@ -114,11 +140,15 @@ static int do_read_inode(struct inode *inode)
 	get_extent_info(&fi->ext, ri->i_ext);
 	get_inline_info(fi, ri);
 
+	/* check data exist */
+	if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
+		err = __recover_inline_status(inode, node_page);
+
 	/* get rdev by using inline_info */
 	__get_inode_rdev(inode, ri);
 
 	f2fs_put_page(node_page, 1);
-	return 0;
+	return err;
 }
 
 struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
@@ -329,6 +359,7 @@ void handle_failed_inode(struct inode *inode)
 
 	remove_inode_page(inode);
 
+	clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
 	clear_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
 	alloc_nid_failed(sbi, inode->i_ino);
 	f2fs_unlock_op(sbi);
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index a004a978096..6312dd2e53f 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -55,6 +55,8 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 		goto out;
 	}
 
+	if (f2fs_may_inline(inode))
+		set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
 	if (test_opt(sbi, INLINE_DENTRY) && S_ISDIR(inode->i_mode))
 		set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
 
@@ -133,6 +135,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	alloc_nid_done(sbi, ino);
 
+	stat_inc_inline_inode(inode);
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
 	return 0;
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 63f8303b79b..cc1064f3153 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -172,6 +172,7 @@ struct f2fs_extent {
 #define F2FS_INLINE_XATTR	0x01	/* file inline xattr flag */
 #define F2FS_INLINE_DATA	0x02	/* file inline data flag */
 #define F2FS_INLINE_DENTRY	0x04	/* file inline dentry flag */
+#define F2FS_DATA_EXIST		0x08	/* file inline data exist flag */
 
 #define MAX_INLINE_DATA		(sizeof(__le32) * (DEF_ADDRS_PER_INODE - \
 						F2FS_INLINE_XATTR_ADDRS - 1))
-- 
cgit v1.2.3-70-g09d2


From be138b7b0d4cbfb8a927d9bc333ceffee9908c23 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Thu, 30 Oct 2014 19:01:10 -0700
Subject: f2fs: remove unnecessary macro

Let's remove unused macro.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 include/linux/f2fs_fs.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index cc1064f3153..87f14e90e98 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -177,10 +177,6 @@ struct f2fs_extent {
 #define MAX_INLINE_DATA		(sizeof(__le32) * (DEF_ADDRS_PER_INODE - \
 						F2FS_INLINE_XATTR_ADDRS - 1))
 
-#define INLINE_DATA_OFFSET	(PAGE_CACHE_SIZE - sizeof(struct node_footer) -\
-				sizeof(__le32) * (DEF_ADDRS_PER_INODE + \
-				DEF_NIDS_PER_INODE - 1))
-
 struct f2fs_inode {
 	__le16 i_mode;			/* file mode */
 	__u8 i_advise;			/* file hints */
-- 
cgit v1.2.3-70-g09d2


From e1ccbbc9d5aa01a6c1c9c78acea6515db4f1be71 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Tue, 14 Oct 2014 16:34:47 +0200
Subject: efi: dmi: add support for SMBIOS 3.0 UEFI configuration table

This adds support to the UEFI side for detecting the presence of
a SMBIOS 3.0 64-bit entry point. This allows the actual SMBIOS
structure table to reside at a physical offset over 4 GB, which
cannot be supported by the legacy SMBIOS 32-bit entry point.

Since the firmware can legally provide both entry points, store
the SMBIOS 3.0 entry point in a separate variable, and let the
DMI decoding layer decide which one will be used.

Tested-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Acked-by: Leif Lindholm <leif.lindholm@linaro.org>
Acked-by: Matt Fleming <matt.fleming@intel.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 drivers/firmware/efi/efi.c | 4 ++++
 drivers/xen/efi.c          | 1 +
 include/linux/efi.h        | 6 +++++-
 3 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 8590099ac14..9035c1b74d5 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -30,6 +30,7 @@ struct efi __read_mostly efi = {
 	.acpi       = EFI_INVALID_TABLE_ADDR,
 	.acpi20     = EFI_INVALID_TABLE_ADDR,
 	.smbios     = EFI_INVALID_TABLE_ADDR,
+	.smbios3    = EFI_INVALID_TABLE_ADDR,
 	.sal_systab = EFI_INVALID_TABLE_ADDR,
 	.boot_info  = EFI_INVALID_TABLE_ADDR,
 	.hcdp       = EFI_INVALID_TABLE_ADDR,
@@ -86,6 +87,8 @@ static ssize_t systab_show(struct kobject *kobj,
 		str += sprintf(str, "ACPI=0x%lx\n", efi.acpi);
 	if (efi.smbios != EFI_INVALID_TABLE_ADDR)
 		str += sprintf(str, "SMBIOS=0x%lx\n", efi.smbios);
+	if (efi.smbios3 != EFI_INVALID_TABLE_ADDR)
+		str += sprintf(str, "SMBIOS3=0x%lx\n", efi.smbios3);
 	if (efi.hcdp != EFI_INVALID_TABLE_ADDR)
 		str += sprintf(str, "HCDP=0x%lx\n", efi.hcdp);
 	if (efi.boot_info != EFI_INVALID_TABLE_ADDR)
@@ -260,6 +263,7 @@ static __initdata efi_config_table_type_t common_tables[] = {
 	{MPS_TABLE_GUID, "MPS", &efi.mps},
 	{SAL_SYSTEM_TABLE_GUID, "SALsystab", &efi.sal_systab},
 	{SMBIOS_TABLE_GUID, "SMBIOS", &efi.smbios},
+	{SMBIOS3_TABLE_GUID, "SMBIOS 3.0", &efi.smbios3},
 	{UGA_IO_PROTOCOL_GUID, "UGA", &efi.uga},
 	{NULL_GUID, NULL, NULL},
 };
diff --git a/drivers/xen/efi.c b/drivers/xen/efi.c
index 1f850c97482..f745db27017 100644
--- a/drivers/xen/efi.c
+++ b/drivers/xen/efi.c
@@ -294,6 +294,7 @@ static const struct efi efi_xen __initconst = {
 	.acpi                     = EFI_INVALID_TABLE_ADDR,
 	.acpi20                   = EFI_INVALID_TABLE_ADDR,
 	.smbios                   = EFI_INVALID_TABLE_ADDR,
+	.smbios3                  = EFI_INVALID_TABLE_ADDR,
 	.sal_systab               = EFI_INVALID_TABLE_ADDR,
 	.boot_info                = EFI_INVALID_TABLE_ADDR,
 	.hcdp                     = EFI_INVALID_TABLE_ADDR,
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 0949f9c7e87..0238d612750 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -547,6 +547,9 @@ void efi_native_runtime_setup(void);
 #define SMBIOS_TABLE_GUID    \
     EFI_GUID(  0xeb9d2d31, 0x2d88, 0x11d3, 0x9a, 0x16, 0x0, 0x90, 0x27, 0x3f, 0xc1, 0x4d )
 
+#define SMBIOS3_TABLE_GUID    \
+    EFI_GUID(  0xf2fd1544, 0x9794, 0x4a2c, 0x99, 0x2e, 0xe5, 0xbb, 0xcf, 0x20, 0xe3, 0x94 )
+
 #define SAL_SYSTEM_TABLE_GUID    \
     EFI_GUID(  0xeb9d2d32, 0x2d88, 0x11d3, 0x9a, 0x16, 0x0, 0x90, 0x27, 0x3f, 0xc1, 0x4d )
 
@@ -810,7 +813,8 @@ extern struct efi {
 	unsigned long mps;		/* MPS table */
 	unsigned long acpi;		/* ACPI table  (IA64 ext 0.71) */
 	unsigned long acpi20;		/* ACPI table  (ACPI 2.0) */
-	unsigned long smbios;		/* SM BIOS table */
+	unsigned long smbios;		/* SMBIOS table (32 bit entry point) */
+	unsigned long smbios3;		/* SMBIOS table (64 bit entry point) */
 	unsigned long sal_systab;	/* SAL system table */
 	unsigned long boot_info;	/* boot info table */
 	unsigned long hcdp;		/* HCDP table */
-- 
cgit v1.2.3-70-g09d2


From 6af91949ab7462d0917f436820c263ae9a89322c Mon Sep 17 00:00:00 2001
From: Brian Norris <computersforpeace@gmail.com>
Date: Wed, 6 Aug 2014 18:16:58 -0700
Subject: mtd: m25p80: drop wait-till-ready checks

spi-nor.c should be taking care of these now.

Signed-off-by: Brian Norris <computersforpeace@gmail.com>
Reviewed-by: Marek Vasut <marex@denx.de>
---
 drivers/mtd/devices/m25p80.c | 11 -----------
 include/linux/mtd/spi-nor.h  |  6 ++++++
 2 files changed, 6 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index 5d4482512e3..35e7e9896b1 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -129,16 +129,10 @@ static int m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
 	struct spi_transfer t[2];
 	struct spi_message m;
 	unsigned int dummy = nor->read_dummy;
-	int ret;
 
 	/* convert the dummy cycles to the number of bytes */
 	dummy /= 8;
 
-	/* Wait till previous write/erase is done. */
-	ret = nor->wait_till_ready(nor);
-	if (ret)
-		return ret;
-
 	spi_message_init(&m);
 	memset(t, 0, (sizeof t));
 
@@ -168,11 +162,6 @@ static int m25p80_erase(struct spi_nor *nor, loff_t offset)
 	dev_dbg(nor->dev, "%dKiB at 0x%08x\n",
 		flash->mtd.erasesize / 1024, (u32)offset);
 
-	/* Wait until finished previous write command. */
-	ret = nor->wait_till_ready(nor);
-	if (ret)
-		return ret;
-
 	/* Send write enable, then erase commands. */
 	ret = nor->write_reg(nor, SPINOR_OP_WREN, NULL, 0, 0);
 	if (ret)
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index 2f27713b3ae..d691025d9b0 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -116,6 +116,10 @@ enum spi_nor_ops {
 	SPI_NOR_OPS_UNLOCK,
 };
 
+enum spi_nor_option_flags {
+	SNOR_F_USE_FSR		= BIT(0),
+};
+
 /**
  * struct spi_nor - Structure for defining a the SPI NOR layer
  * @mtd:		point to a mtd_info structure
@@ -129,6 +133,7 @@ enum spi_nor_ops {
  * @program_opcode:	the program opcode
  * @flash_read:		the mode of the read
  * @sst_write_second:	used by the SST write operation
+ * @flags:		flag options for the current SPI-NOR (SNOR_F_*)
  * @cfg:		used by the read_xfer/write_xfer
  * @cmd_buf:		used by the write_reg
  * @prepare:		[OPTIONAL] do some preparations for the
@@ -158,6 +163,7 @@ struct spi_nor {
 	u8			program_opcode;
 	enum read_mode		flash_read;
 	bool			sst_write_second;
+	u32			flags;
 	struct spi_nor_xfer_cfg	cfg;
 	u8			cmd_buf[SPI_NOR_MAX_CMD_SIZE];
 
-- 
cgit v1.2.3-70-g09d2


From b94ed087744c5bc287d2ed706b476693df07151d Mon Sep 17 00:00:00 2001
From: Brian Norris <computersforpeace@gmail.com>
Date: Wed, 6 Aug 2014 18:17:00 -0700
Subject: mtd: spi-nor: drop replaceable wait-till-ready function pointer

We don't need to expose a 'wait-till-ready' interface to drivers. Status
register polling should be handled by the core spi-nor.c library, and as
of now, I see no need to provide a special driver-specific hook for it.

Signed-off-by: Brian Norris <computersforpeace@gmail.com>
Reviewed-by: Marek Vasut <marex@denx.de>
---
 drivers/mtd/spi-nor/spi-nor.c | 28 ++++++++++------------------
 include/linux/mtd/spi-nor.h   |  2 --
 2 files changed, 10 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 93cd1043ef4..bfb67f1e2b7 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -195,6 +195,10 @@ static int spi_nor_ready(struct spi_nor *nor)
 	return sr && fsr;
 }
 
+/*
+ * Service routine to read status register until ready, or timeout occurs.
+ * Returns non-zero if error.
+ */
 static int spi_nor_wait_till_ready(struct spi_nor *nor)
 {
 	unsigned long deadline;
@@ -215,15 +219,6 @@ static int spi_nor_wait_till_ready(struct spi_nor *nor)
 	return -ETIMEDOUT;
 }
 
-/*
- * Service routine to read status register until ready, or timeout occurs.
- * Returns non-zero if error.
- */
-static int wait_till_ready(struct spi_nor *nor)
-{
-	return nor->wait_till_ready(nor);
-}
-
 /*
  * Erase the whole flash memory
  *
@@ -708,7 +703,7 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 
 		/* write one byte. */
 		nor->write(nor, to, 1, retlen, buf);
-		ret = wait_till_ready(nor);
+		ret = spi_nor_wait_till_ready(nor);
 		if (ret)
 			goto time_out;
 	}
@@ -720,7 +715,7 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 
 		/* write two bytes. */
 		nor->write(nor, to, 2, retlen, buf + actual);
-		ret = wait_till_ready(nor);
+		ret = spi_nor_wait_till_ready(nor);
 		if (ret)
 			goto time_out;
 		to += 2;
@@ -729,7 +724,7 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 	nor->sst_write_second = false;
 
 	write_disable(nor);
-	ret = wait_till_ready(nor);
+	ret = spi_nor_wait_till_ready(nor);
 	if (ret)
 		goto time_out;
 
@@ -740,7 +735,7 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 		nor->program_opcode = SPINOR_OP_BP;
 		nor->write(nor, to, 1, retlen, buf + actual);
 
-		ret = wait_till_ready(nor);
+		ret = spi_nor_wait_till_ready(nor);
 		if (ret)
 			goto time_out;
 		write_disable(nor);
@@ -786,7 +781,7 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len,
 			if (page_size > nor->page_size)
 				page_size = nor->page_size;
 
-			ret = wait_till_ready(nor);
+			ret = spi_nor_wait_till_ready(nor);
 			if (ret)
 				goto write_err;
 
@@ -812,7 +807,7 @@ static int macronix_quad_enable(struct spi_nor *nor)
 	nor->cmd_buf[0] = val | SR_QUAD_EN_MX;
 	nor->write_reg(nor, SPINOR_OP_WRSR, nor->cmd_buf, 1, 0);
 
-	if (wait_till_ready(nor))
+	if (spi_nor_wait_till_ready(nor))
 		return 1;
 
 	ret = read_sr(nor);
@@ -892,9 +887,6 @@ static int spi_nor_check(struct spi_nor *nor)
 		return -EINVAL;
 	}
 
-	if (!nor->wait_till_ready)
-		nor->wait_till_ready = spi_nor_wait_till_ready;
-
 	return 0;
 }
 
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index d691025d9b0..63aeccf9ddc 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -144,7 +144,6 @@ enum spi_nor_option_flags {
  * @write_xfer:		[OPTIONAL] the writefundamental primitive
  * @read_reg:		[DRIVER-SPECIFIC] read out the register
  * @write_reg:		[DRIVER-SPECIFIC] write data to the register
- * @wait_till_ready:	[REPLACEABLE] wait till the NOR becomes ready
  * @read:		[DRIVER-SPECIFIC] read data from the SPI NOR
  * @write:		[DRIVER-SPECIFIC] write data to the SPI NOR
  * @erase:		[DRIVER-SPECIFIC] erase a sector of the SPI NOR
@@ -176,7 +175,6 @@ struct spi_nor {
 	int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len);
 	int (*write_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len,
 			int write_enable);
-	int (*wait_till_ready)(struct spi_nor *nor);
 
 	int (*read)(struct spi_nor *nor, loff_t from,
 			size_t len, size_t *retlen, u_char *read_buf);
-- 
cgit v1.2.3-70-g09d2


From 1cbd772d9aaf6c697935cb855860b66cebacf950 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 5 Nov 2014 13:08:20 +0100
Subject: libsas: use ata_dev_classify()

Use the ata device class from libata in libsas instead of checking
the supported command set and switch to using ata_dev_classify()
instead of our own method.

Cc: Tejun Heo <tj@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 drivers/scsi/aic94xx/aic94xx_task.c | 10 +++---
 drivers/scsi/isci/request.c         |  4 +--
 drivers/scsi/libsas/sas_ata.c       | 66 +++++++------------------------------
 drivers/scsi/mvsas/mv_sas.c         |  4 +--
 drivers/scsi/pm8001/pm8001_hwi.c    |  2 +-
 drivers/scsi/pm8001/pm80xx_hwi.c    |  2 +-
 include/scsi/libsas.h               | 11 ++-----
 7 files changed, 25 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/aic94xx/aic94xx_task.c b/drivers/scsi/aic94xx/aic94xx_task.c
index 59b86e260ce..7abbe42e862 100644
--- a/drivers/scsi/aic94xx/aic94xx_task.c
+++ b/drivers/scsi/aic94xx/aic94xx_task.c
@@ -373,10 +373,10 @@ static int asd_build_ata_ascb(struct asd_ascb *ascb, struct sas_task *task,
 
 	if (unlikely(task->ata_task.device_control_reg_update))
 		scb->header.opcode = CONTROL_ATA_DEV;
-	else if (dev->sata_dev.command_set == ATA_COMMAND_SET)
-		scb->header.opcode = INITIATE_ATA_TASK;
-	else
+	else if (dev->sata_dev.class == ATA_DEV_ATAPI)
 		scb->header.opcode = INITIATE_ATAPI_TASK;
+	else
+		scb->header.opcode = INITIATE_ATA_TASK;
 
 	scb->ata_task.proto_conn_rate = (1 << 5); /* STP */
 	if (dev->port->oob_mode == SAS_OOB_MODE)
@@ -387,7 +387,7 @@ static int asd_build_ata_ascb(struct asd_ascb *ascb, struct sas_task *task,
 	if (likely(!task->ata_task.device_control_reg_update))
 		scb->ata_task.fis.flags |= 0x80; /* C=1: update ATA cmd reg */
 	scb->ata_task.fis.flags &= 0xF0; /* PM_PORT field shall be 0 */
-	if (dev->sata_dev.command_set == ATAPI_COMMAND_SET)
+	if (dev->sata_dev.class == ATA_DEV_ATAPI)
 		memcpy(scb->ata_task.atapi_packet, task->ata_task.atapi_packet,
 		       16);
 	scb->ata_task.sister_scb = cpu_to_le16(0xFFFF);
@@ -399,7 +399,7 @@ static int asd_build_ata_ascb(struct asd_ascb *ascb, struct sas_task *task,
 		if (task->ata_task.dma_xfer)
 			flags |= DATA_XFER_MODE_DMA;
 		if (task->ata_task.use_ncq &&
-		    dev->sata_dev.command_set != ATAPI_COMMAND_SET)
+		    dev->sata_dev.class != ATA_DEV_ATAPI)
 			flags |= ATA_Q_TYPE_NCQ;
 		flags |= data_dir_flags[task->data_dir];
 		scb->ata_task.ata_flags = flags;
diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c
index 56e38096f0c..cfd0084f1cd 100644
--- a/drivers/scsi/isci/request.c
+++ b/drivers/scsi/isci/request.c
@@ -694,7 +694,7 @@ sci_io_request_construct_sata(struct isci_request *ireq,
 	}
 
 	/* ATAPI */
-	if (dev->sata_dev.command_set == ATAPI_COMMAND_SET &&
+	if (dev->sata_dev.class == ATA_DEV_ATAPI &&
 	    task->ata_task.fis.command == ATA_CMD_PACKET) {
 		sci_atapi_construct(ireq);
 		return SCI_SUCCESS;
@@ -2980,7 +2980,7 @@ static void sci_request_started_state_enter(struct sci_base_state_machine *sm)
 		state = SCI_REQ_SMP_WAIT_RESP;
 	} else if (task && sas_protocol_ata(task->task_proto) &&
 		   !task->ata_task.use_ncq) {
-		if (dev->sata_dev.command_set == ATAPI_COMMAND_SET &&
+		if (dev->sata_dev.class == ATA_DEV_ATAPI &&
 			task->ata_task.fis.command == ATA_CMD_PACKET) {
 			state = SCI_REQ_ATAPI_WAIT_H2D;
 		} else if (task->data_dir == DMA_NONE) {
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 766098af4eb..9f68db7ed5f 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -138,7 +138,7 @@ static void sas_ata_task_done(struct sas_task *task)
 
 	if (stat->stat == SAS_PROTO_RESPONSE || stat->stat == SAM_STAT_GOOD ||
 	    ((stat->stat == SAM_STAT_CHECK_CONDITION &&
-	      dev->sata_dev.command_set == ATAPI_COMMAND_SET))) {
+	      dev->sata_dev.class == ATA_DEV_ATAPI))) {
 		memcpy(dev->sata_dev.fis, resp->ending_fis, ATA_RESP_FIS_SIZE);
 
 		if (!link->sactive) {
@@ -278,7 +278,7 @@ static struct sas_internal *dev_to_sas_internal(struct domain_device *dev)
 	return to_sas_internal(dev->port->ha->core.shost->transportt);
 }
 
-static void sas_get_ata_command_set(struct domain_device *dev);
+static int sas_get_ata_command_set(struct domain_device *dev);
 
 int sas_get_ata_info(struct domain_device *dev, struct ex_phy *phy)
 {
@@ -303,8 +303,7 @@ int sas_get_ata_info(struct domain_device *dev, struct ex_phy *phy)
 		}
 		memcpy(dev->frame_rcvd, &dev->sata_dev.rps_resp.rps.fis,
 		       sizeof(struct dev_to_host_fis));
-		/* TODO switch to ata_dev_classify() */
-		sas_get_ata_command_set(dev);
+		dev->sata_dev.class = sas_get_ata_command_set(dev);
 	}
 	return 0;
 }
@@ -425,18 +424,7 @@ static int sas_ata_hard_reset(struct ata_link *link, unsigned int *class,
 	if (ret && ret != -EAGAIN)
 		sas_ata_printk(KERN_ERR, dev, "reset failed (errno=%d)\n", ret);
 
-	/* XXX: if the class changes during the reset the upper layer
-	 * should be informed, if the device has gone away we assume
-	 * libsas will eventually delete it
-	 */
-	switch (dev->sata_dev.command_set) {
-	case ATA_COMMAND_SET:
-		*class = ATA_DEV_ATA;
-		break;
-	case ATAPI_COMMAND_SET:
-		*class = ATA_DEV_ATAPI;
-		break;
-	}
+	*class = dev->sata_dev.class;
 
 	ap->cbl = ATA_CBL_SATA;
 	return ret;
@@ -626,50 +614,18 @@ void sas_ata_task_abort(struct sas_task *task)
 	complete(waiting);
 }
 
-static void sas_get_ata_command_set(struct domain_device *dev)
+static int sas_get_ata_command_set(struct domain_device *dev)
 {
 	struct dev_to_host_fis *fis =
 		(struct dev_to_host_fis *) dev->frame_rcvd;
+	struct ata_taskfile tf;
 
 	if (dev->dev_type == SAS_SATA_PENDING)
-		return;
+		return ATA_DEV_UNKNOWN;
+
+	ata_tf_from_fis((const u8 *)fis, &tf);
 
-	if ((fis->sector_count == 1 && /* ATA */
-	     fis->lbal         == 1 &&
-	     fis->lbam         == 0 &&
-	     fis->lbah         == 0 &&
-	     fis->device       == 0)
-	    ||
-	    (fis->sector_count == 0 && /* CE-ATA (mATA) */
-	     fis->lbal         == 0 &&
-	     fis->lbam         == 0xCE &&
-	     fis->lbah         == 0xAA &&
-	     (fis->device & ~0x10) == 0))
-
-		dev->sata_dev.command_set = ATA_COMMAND_SET;
-
-	else if ((fis->interrupt_reason == 1 &&	/* ATAPI */
-		  fis->lbal             == 1 &&
-		  fis->byte_count_low   == 0x14 &&
-		  fis->byte_count_high  == 0xEB &&
-		  (fis->device & ~0x10) == 0))
-
-		dev->sata_dev.command_set = ATAPI_COMMAND_SET;
-
-	else if ((fis->sector_count == 1 && /* SEMB */
-		  fis->lbal         == 1 &&
-		  fis->lbam         == 0x3C &&
-		  fis->lbah         == 0xC3 &&
-		  fis->device       == 0)
-		||
-		 (fis->interrupt_reason == 1 &&	/* SATA PM */
-		  fis->lbal             == 1 &&
-		  fis->byte_count_low   == 0x69 &&
-		  fis->byte_count_high  == 0x96 &&
-		  (fis->device & ~0x10) == 0))
-
-		/* Treat it as a superset? */
-		dev->sata_dev.command_set = ATAPI_COMMAND_SET;
+	return ata_dev_classify(&tf);
 }
 
 void sas_probe_sata(struct asd_sas_port *port)
@@ -775,7 +731,7 @@ int sas_discover_sata(struct domain_device *dev)
 	if (dev->dev_type == SAS_SATA_PM)
 		return -ENODEV;
 
-	sas_get_ata_command_set(dev);
+	dev->sata_dev.class = sas_get_ata_command_set(dev);
 	sas_fill_in_rphy(dev, dev->rphy);
 
 	res = sas_notify_lldd_dev_found(dev);
diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c
index ac52f7c9951..48a493cd285 100644
--- a/drivers/scsi/mvsas/mv_sas.c
+++ b/drivers/scsi/mvsas/mv_sas.c
@@ -479,7 +479,7 @@ static int mvs_task_prep_ata(struct mvs_info *mvi,
 
 	if (task->ata_task.use_ncq)
 		flags |= MCH_FPDMA;
-	if (dev->sata_dev.command_set == ATAPI_COMMAND_SET) {
+	if (dev->sata_dev.class == ATA_DEV_ATAPI) {
 		if (task->ata_task.fis.command != ATA_CMD_ID_ATAPI)
 			flags |= MCH_ATAPI;
 	}
@@ -546,7 +546,7 @@ static int mvs_task_prep_ata(struct mvs_info *mvi,
 		task->ata_task.fis.flags |= 0x80; /* C=1: update ATA cmd reg */
 	/* fill in command FIS and ATAPI CDB */
 	memcpy(buf_cmd, &task->ata_task.fis, sizeof(struct host_to_dev_fis));
-	if (dev->sata_dev.command_set == ATAPI_COMMAND_SET)
+	if (dev->sata_dev.class == ATA_DEV_ATAPI)
 		memcpy(buf_cmd + STP_ATAPI_CMD,
 			task->ata_task.atapi_packet, 16);
 
diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c
index 933f2147195..96dcc097a46 100644
--- a/drivers/scsi/pm8001/pm8001_hwi.c
+++ b/drivers/scsi/pm8001/pm8001_hwi.c
@@ -4367,7 +4367,7 @@ static int pm8001_chip_sata_req(struct pm8001_hba_info *pm8001_ha,
 			PM8001_IO_DBG(pm8001_ha, pm8001_printk("PIO\n"));
 		}
 		if (task->ata_task.use_ncq &&
-			dev->sata_dev.command_set != ATAPI_COMMAND_SET) {
+			dev->sata_dev.class != ATA_DEV_ATAPI) {
 			ATAP = 0x07; /* FPDMA */
 			PM8001_IO_DBG(pm8001_ha, pm8001_printk("FPDMA\n"));
 		}
diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c
index b06443a0db2..05cce463ab0 100644
--- a/drivers/scsi/pm8001/pm80xx_hwi.c
+++ b/drivers/scsi/pm8001/pm80xx_hwi.c
@@ -4077,7 +4077,7 @@ static int pm80xx_chip_sata_req(struct pm8001_hba_info *pm8001_ha,
 			PM8001_IO_DBG(pm8001_ha, pm8001_printk("PIO\n"));
 		}
 		if (task->ata_task.use_ncq &&
-			dev->sata_dev.command_set != ATAPI_COMMAND_SET) {
+		    dev->sata_dev.class != ATA_DEV_ATAPI) {
 			ATAP = 0x07; /* FPDMA */
 			PM8001_IO_DBG(pm8001_ha, pm8001_printk("FPDMA\n"));
 		}
diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h
index ef7872c20da..8528a09a00c 100644
--- a/include/scsi/libsas.h
+++ b/include/scsi/libsas.h
@@ -161,17 +161,12 @@ struct expander_device {
 };
 
 /* ---------- SATA device ---------- */
-enum ata_command_set {
-        ATA_COMMAND_SET   = 0,
-        ATAPI_COMMAND_SET = 1,
-};
-
 #define ATA_RESP_FIS_SIZE 24
 
 struct sata_device {
-        enum   ata_command_set command_set;
-        struct smp_resp        rps_resp; /* report_phy_sata_resp */
-        u8     port_no;        /* port number, if this is a PM (Port) */
+	unsigned int class;
+	struct smp_resp        rps_resp; /* report_phy_sata_resp */
+	u8     port_no;        /* port number, if this is a PM (Port) */
 
 	struct ata_port *ap;
 	struct ata_host ata_host;
-- 
cgit v1.2.3-70-g09d2


From 9162c6579bf90b3f5ddb7e3a6c6fa946c1b4cbeb Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 5 Nov 2014 13:08:21 +0100
Subject: libata: Implement ATA_DEV_ZAC

Add new ATA device type for ZAC devices.

Acked-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 drivers/ata/libata-core.c      | 20 ++++++++++++++------
 drivers/ata/libata-eh.c        |  7 +++++--
 drivers/ata/libata-scsi.c      |  5 +++--
 drivers/ata/libata-transport.c |  1 +
 include/linux/libata.h         |  6 ++++--
 5 files changed, 27 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index c5ba15af87d..5c84fb5c337 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -1043,8 +1043,8 @@ const char *sata_spd_string(unsigned int spd)
  *	None.
  *
  *	RETURNS:
- *	Device type, %ATA_DEV_ATA, %ATA_DEV_ATAPI, %ATA_DEV_PMP or
- *	%ATA_DEV_UNKNOWN the event of failure.
+ *	Device type, %ATA_DEV_ATA, %ATA_DEV_ATAPI, %ATA_DEV_PMP,
+ *	%ATA_DEV_ZAC, or %ATA_DEV_UNKNOWN the event of failure.
  */
 unsigned int ata_dev_classify(const struct ata_taskfile *tf)
 {
@@ -1089,6 +1089,11 @@ unsigned int ata_dev_classify(const struct ata_taskfile *tf)
 		return ATA_DEV_SEMB;
 	}
 
+	if ((tf->lbam == 0xcd) && (tf->lbah == 0xab)) {
+		DPRINTK("found ZAC device by sig\n");
+		return ATA_DEV_ZAC;
+	}
+
 	DPRINTK("unknown device\n");
 	return ATA_DEV_UNKNOWN;
 }
@@ -1329,7 +1334,7 @@ static int ata_hpa_resize(struct ata_device *dev)
 	int rc;
 
 	/* do we need to do it? */
-	if (dev->class != ATA_DEV_ATA ||
+	if ((dev->class != ATA_DEV_ATA && dev->class != ATA_DEV_ZAC) ||
 	    !ata_id_has_lba(dev->id) || !ata_id_hpa_enabled(dev->id) ||
 	    (dev->horkage & ATA_HORKAGE_BROKEN_HPA))
 		return 0;
@@ -1889,6 +1894,7 @@ retry:
 	case ATA_DEV_SEMB:
 		class = ATA_DEV_ATA;	/* some hard drives report SEMB sig */
 	case ATA_DEV_ATA:
+	case ATA_DEV_ZAC:
 		tf.command = ATA_CMD_ID_ATA;
 		break;
 	case ATA_DEV_ATAPI:
@@ -1980,7 +1986,7 @@ retry:
 	rc = -EINVAL;
 	reason = "device reports invalid type";
 
-	if (class == ATA_DEV_ATA) {
+	if (class == ATA_DEV_ATA || class == ATA_DEV_ZAC) {
 		if (!ata_id_is_ata(id) && !ata_id_is_cfa(id))
 			goto err_out;
 		if (ap->host->flags & ATA_HOST_IGNORE_ATA &&
@@ -2015,7 +2021,8 @@ retry:
 			goto retry;
 	}
 
-	if ((flags & ATA_READID_POSTRESET) && class == ATA_DEV_ATA) {
+	if ((flags & ATA_READID_POSTRESET) &&
+	    (class == ATA_DEV_ATA || class == ATA_DEV_ZAC)) {
 		/*
 		 * The exact sequence expected by certain pre-ATA4 drives is:
 		 * SRST RESET
@@ -2280,7 +2287,7 @@ int ata_dev_configure(struct ata_device *dev)
 			sizeof(modelbuf));
 
 	/* ATA-specific feature tests */
-	if (dev->class == ATA_DEV_ATA) {
+	if (dev->class == ATA_DEV_ATA || dev->class == ATA_DEV_ZAC) {
 		if (ata_id_is_cfa(id)) {
 			/* CPRM may make this media unusable */
 			if (id[ATA_ID_CFA_KEY_MGMT] & 1)
@@ -4033,6 +4040,7 @@ int ata_dev_revalidate(struct ata_device *dev, unsigned int new_class,
 	if (ata_class_enabled(new_class) &&
 	    new_class != ATA_DEV_ATA &&
 	    new_class != ATA_DEV_ATAPI &&
+	    new_class != ATA_DEV_ZAC &&
 	    new_class != ATA_DEV_SEMB) {
 		ata_dev_info(dev, "class mismatch %u != %u\n",
 			     dev->class, new_class);
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index dad83df555c..3dbec8954c8 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1809,6 +1809,7 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc,
 
 	switch (qc->dev->class) {
 	case ATA_DEV_ATA:
+	case ATA_DEV_ZAC:
 		if (err & ATA_ICRC)
 			qc->err_mask |= AC_ERR_ATA_BUS;
 		if (err & (ATA_UNC | ATA_AMNF))
@@ -3792,7 +3793,8 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 				struct ata_eh_context *ehc = &link->eh_context;
 				unsigned long tmp;
 
-				if (dev->class != ATA_DEV_ATA)
+				if (dev->class != ATA_DEV_ATA &&
+				    dev->class != ATA_DEV_ZAC)
 					continue;
 				if (!(ehc->i.dev_action[dev->devno] &
 				      ATA_EH_PARK))
@@ -3873,7 +3875,8 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 
 		/* retry flush if necessary */
 		ata_for_each_dev(dev, link, ALL) {
-			if (dev->class != ATA_DEV_ATA)
+			if (dev->class != ATA_DEV_ATA &&
+			    dev->class != ATA_DEV_ZAC)
 				continue;
 			rc = ata_eh_maybe_retry_flush(dev);
 			if (rc)
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 0586f66d70f..bea6e7f4ebf 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -235,7 +235,8 @@ static ssize_t ata_scsi_park_store(struct device *device,
 		rc = -ENODEV;
 		goto unlock;
 	}
-	if (dev->class != ATA_DEV_ATA) {
+	if (dev->class != ATA_DEV_ATA &&
+	    dev->class != ATA_DEV_ZAC) {
 		rc = -EOPNOTSUPP;
 		goto unlock;
 	}
@@ -3412,7 +3413,7 @@ static inline int __ata_scsi_queuecmd(struct scsi_cmnd *scmd,
 	ata_xlat_func_t xlat_func;
 	int rc = 0;
 
-	if (dev->class == ATA_DEV_ATA) {
+	if (dev->class == ATA_DEV_ATA || dev->class == ATA_DEV_ZAC) {
 		if (unlikely(!scmd->cmd_len || scmd->cmd_len > dev->cdb_len))
 			goto bad_cdb_len;
 
diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c
index e3741322822..3227b7c8a05 100644
--- a/drivers/ata/libata-transport.c
+++ b/drivers/ata/libata-transport.c
@@ -143,6 +143,7 @@ static struct {
 	{ ATA_DEV_PMP_UNSUP,		"pmp" },
 	{ ATA_DEV_SEMB,			"semb" },
 	{ ATA_DEV_SEMB_UNSUP,		"semb" },
+	{ ATA_DEV_ZAC,			"zac" },
 	{ ATA_DEV_NONE,			"none" }
 };
 ata_bitfield_name_search(class, ata_class_names)
diff --git a/include/linux/libata.h b/include/linux/libata.h
index bd5fefeaf54..a26daea7f5e 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -191,7 +191,8 @@ enum {
 	ATA_DEV_PMP_UNSUP	= 6,	/* SATA port multiplier (unsupported) */
 	ATA_DEV_SEMB		= 7,	/* SEMB */
 	ATA_DEV_SEMB_UNSUP	= 8,	/* SEMB (unsupported) */
-	ATA_DEV_NONE		= 9,	/* no device */
+	ATA_DEV_ZAC		= 9,	/* ZAC device */
+	ATA_DEV_NONE		= 10,	/* no device */
 
 	/* struct ata_link flags */
 	ATA_LFLAG_NO_HRST	= (1 << 1), /* avoid hardreset */
@@ -1491,7 +1492,8 @@ static inline unsigned int ata_tag_internal(unsigned int tag)
 static inline unsigned int ata_class_enabled(unsigned int class)
 {
 	return class == ATA_DEV_ATA || class == ATA_DEV_ATAPI ||
-		class == ATA_DEV_PMP || class == ATA_DEV_SEMB;
+		class == ATA_DEV_PMP || class == ATA_DEV_SEMB ||
+		class == ATA_DEV_ZAC;
 }
 
 static inline unsigned int ata_class_disabled(unsigned int class)
-- 
cgit v1.2.3-70-g09d2


From 68c4a4f8abc60c9440ede9cd123d48b78325f7a3 Mon Sep 17 00:00:00 2001
From: Sebastian Schmidt <yath@yath.de>
Date: Sun, 19 Oct 2014 20:05:15 +0200
Subject: pstore: Honor dmesg_restrict sysctl on dmesg dumps

When the kernel.dmesg_restrict restriction is in place, only users with
CAP_SYSLOG should be able to access crash dumps (like: attacker is
trying to exploit a bug, watchdog reboots, attacker can happily read
crash dumps and logs).

This puts the restriction on console-* types as well as sensitive
information could have been leaked there.

Other log types are unaffected.

Signed-off-by: Sebastian Schmidt <yath@yath.de>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 fs/pstore/inode.c      | 22 ++++++++++++++++++++++
 include/linux/syslog.h |  1 +
 kernel/printk/printk.c |  2 +-
 3 files changed, 24 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index fafb7a02a5d..50416602774 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -36,6 +36,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/uaccess.h>
+#include <linux/syslog.h>
 
 #include "internal.h"
 
@@ -120,6 +121,18 @@ static const struct seq_operations pstore_ftrace_seq_ops = {
 	.show	= pstore_ftrace_seq_show,
 };
 
+static int pstore_check_syslog_permissions(struct pstore_private *ps)
+{
+	switch (ps->type) {
+	case PSTORE_TYPE_DMESG:
+	case PSTORE_TYPE_CONSOLE:
+		return check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
+			SYSLOG_FROM_READER);
+	default:
+		return 0;
+	}
+}
+
 static ssize_t pstore_file_read(struct file *file, char __user *userbuf,
 						size_t count, loff_t *ppos)
 {
@@ -138,6 +151,10 @@ static int pstore_file_open(struct inode *inode, struct file *file)
 	int err;
 	const struct seq_operations *sops = NULL;
 
+	err = pstore_check_syslog_permissions(ps);
+	if (err)
+		return err;
+
 	if (ps->type == PSTORE_TYPE_FTRACE)
 		sops = &pstore_ftrace_seq_ops;
 
@@ -174,6 +191,11 @@ static const struct file_operations pstore_file_operations = {
 static int pstore_unlink(struct inode *dir, struct dentry *dentry)
 {
 	struct pstore_private *p = dentry->d_inode->i_private;
+	int err;
+
+	err = pstore_check_syslog_permissions(p);
+	if (err)
+		return err;
 
 	if (p->psi->erase)
 		p->psi->erase(p->type, p->id, p->count,
diff --git a/include/linux/syslog.h b/include/linux/syslog.h
index 98a3153c0f9..9def5297dbb 100644
--- a/include/linux/syslog.h
+++ b/include/linux/syslog.h
@@ -48,5 +48,6 @@
 #define SYSLOG_FROM_PROC             1
 
 int do_syslog(int type, char __user *buf, int count, bool from_file);
+int check_syslog_permissions(int type, bool from_file);
 
 #endif /* _LINUX_SYSLOG_H */
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index ced2b84b1cb..c8755e7e1db 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -480,7 +480,7 @@ static int syslog_action_restricted(int type)
 	       type != SYSLOG_ACTION_SIZE_BUFFER;
 }
 
-static int check_syslog_permissions(int type, bool from_file)
+int check_syslog_permissions(int type, bool from_file)
 {
 	/*
 	 * If this is from /proc/kmsg and we've already opened it, then we've
-- 
cgit v1.2.3-70-g09d2


From 37246a583715e2258d7c5cfecbd9fff0f9fa4b5d Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Mon, 27 Oct 2014 16:02:47 -0400
Subject: netfilter: Remove return values for print_conntrack callbacks

The seq_printf() and friends are having their return values removed.
The print_conntrack() returns the result of seq_printf(), which is
meaningless when seq_printf() returns void. Might as well remove the
return values of print_conntrack() as well.

Link: http://lkml.kernel.org/r/20141029220107.465008329@goodmis.org
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Cc: netfilter-devel@vger.kernel.org
Cc: coreteam@netfilter.org
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/net/netfilter/nf_conntrack_l4proto.h          | 2 +-
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c | 5 ++++-
 net/netfilter/nf_conntrack_proto_dccp.c               | 4 ++--
 net/netfilter/nf_conntrack_proto_gre.c                | 8 ++++----
 net/netfilter/nf_conntrack_proto_sctp.c               | 4 ++--
 net/netfilter/nf_conntrack_proto_tcp.c                | 4 ++--
 net/netfilter/nf_conntrack_standalone.c               | 4 ++--
 7 files changed, 17 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index 4c8d573830b..82e4ec002a3 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -60,7 +60,7 @@ struct nf_conntrack_l4proto {
 			   const struct nf_conntrack_tuple *);
 
 	/* Print out the private part of the conntrack. */
-	int (*print_conntrack)(struct seq_file *s, struct nf_conn *);
+	void (*print_conntrack)(struct seq_file *s, struct nf_conn *);
 
 	/* Return the array of timeouts for this protocol. */
 	unsigned int *(*get_timeouts)(struct net *net);
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 4c48e434bb1..91f207c2cb6 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -147,7 +147,10 @@ static int ct_seq_show(struct seq_file *s, void *v)
 		      ? (long)(ct->timeout.expires - jiffies)/HZ : 0) != 0)
 		goto release;
 
-	if (l4proto->print_conntrack && l4proto->print_conntrack(s, ct))
+	if (l4proto->print_conntrack)
+		l4proto->print_conntrack(s, ct);
+
+	if (seq_has_overflowed(s))
 		goto release;
 
 	if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index cb372f96f10..15971177470 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -626,9 +626,9 @@ static int dccp_print_tuple(struct seq_file *s,
 			  ntohs(tuple->dst.u.dccp.port));
 }
 
-static int dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
+static void dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 {
-	return seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]);
+	seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]);
 }
 
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index d5665739e3b..cba607ada06 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -235,11 +235,11 @@ static int gre_print_tuple(struct seq_file *s,
 }
 
 /* print private data for conntrack */
-static int gre_print_conntrack(struct seq_file *s, struct nf_conn *ct)
+static void gre_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 {
-	return seq_printf(s, "timeout=%u, stream_timeout=%u ",
-			  (ct->proto.gre.timeout / HZ),
-			  (ct->proto.gre.stream_timeout / HZ));
+	seq_printf(s, "timeout=%u, stream_timeout=%u ",
+		   (ct->proto.gre.timeout / HZ),
+		   (ct->proto.gre.stream_timeout / HZ));
 }
 
 static unsigned int *gre_get_timeouts(struct net *net)
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 1314d33f6bc..c61f4cd6407 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -175,7 +175,7 @@ static int sctp_print_tuple(struct seq_file *s,
 }
 
 /* Print out the private part of the conntrack. */
-static int sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
+static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 {
 	enum sctp_conntrack state;
 
@@ -183,7 +183,7 @@ static int sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 	state = ct->proto.sctp.state;
 	spin_unlock_bh(&ct->lock);
 
-	return seq_printf(s, "%s ", sctp_conntrack_names[state]);
+	seq_printf(s, "%s ", sctp_conntrack_names[state]);
 }
 
 #define for_each_sctp_chunk(skb, sch, _sch, offset, dataoff, count)	\
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 44d1ea32570..79668fd3db9 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -311,7 +311,7 @@ static int tcp_print_tuple(struct seq_file *s,
 }
 
 /* Print out the private part of the conntrack. */
-static int tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
+static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 {
 	enum tcp_conntrack state;
 
@@ -319,7 +319,7 @@ static int tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 	state = ct->proto.tcp.state;
 	spin_unlock_bh(&ct->lock);
 
-	return seq_printf(s, "%s ", tcp_conntrack_names[state]);
+	seq_printf(s, "%s ", tcp_conntrack_names[state]);
 }
 
 static unsigned int get_conntrack_index(const struct tcphdr *tcph)
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index cf65a1e040d..348aa360278 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -199,8 +199,8 @@ static int ct_seq_show(struct seq_file *s, void *v)
 		       ? (long)(ct->timeout.expires - jiffies)/HZ : 0) != 0)
 		goto release;
 
-	if (l4proto->print_conntrack && l4proto->print_conntrack(s, ct))
-		goto release;
+	if (l4proto->print_conntrack)
+		l4proto->print_conntrack(s, ct);
 
 	if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
 			l3proto, l4proto))
-- 
cgit v1.2.3-70-g09d2


From 824f1fbee7bbbd850cdb62d3f95143fad4719e20 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 29 Sep 2014 16:08:22 -0700
Subject: netfilter: Convert print_tuple functions to return void

Since adding a new function to seq_file (seq_has_overflowed())
there isn't any value for functions called from seq_show to
return anything.   Remove the int returns of the various
print_tuple/<foo>_print_tuple functions.

Link: http://lkml.kernel.org/p/f2e8cf8df433a197daa62cbaf124c900c708edc7.1412031505.git.joe@perches.com

Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Cc: netfilter-devel@vger.kernel.org
Cc: coreteam@netfilter.org
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/net/netfilter/nf_conntrack_core.h             |  2 +-
 include/net/netfilter/nf_conntrack_l3proto.h          |  4 ++--
 include/net/netfilter/nf_conntrack_l4proto.h          |  4 ++--
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c        |  6 +++---
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c | 12 ++++++++----
 net/ipv4/netfilter/nf_conntrack_proto_icmp.c          | 10 +++++-----
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c        |  6 +++---
 net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c        | 10 +++++-----
 net/netfilter/nf_conntrack_l3proto_generic.c          |  5 ++---
 net/netfilter/nf_conntrack_proto_dccp.c               | 10 +++++-----
 net/netfilter/nf_conntrack_proto_generic.c            |  5 ++---
 net/netfilter/nf_conntrack_proto_gre.c                | 10 +++++-----
 net/netfilter/nf_conntrack_proto_sctp.c               | 10 +++++-----
 net/netfilter/nf_conntrack_proto_tcp.c                | 10 +++++-----
 net/netfilter/nf_conntrack_proto_udp.c                | 10 +++++-----
 net/netfilter/nf_conntrack_proto_udplite.c            | 10 +++++-----
 net/netfilter/nf_conntrack_standalone.c               | 15 +++++++--------
 17 files changed, 70 insertions(+), 69 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index cc0c1882760..f2f0fa3bb15 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -72,7 +72,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb)
 	return ret;
 }
 
-int
+void
 print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
             const struct nf_conntrack_l3proto *l3proto,
             const struct nf_conntrack_l4proto *proto);
diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h
index adc1fa3dd7a..cdc920b4c4c 100644
--- a/include/net/netfilter/nf_conntrack_l3proto.h
+++ b/include/net/netfilter/nf_conntrack_l3proto.h
@@ -38,8 +38,8 @@ struct nf_conntrack_l3proto {
 			     const struct nf_conntrack_tuple *orig);
 
 	/* Print out the per-protocol part of the tuple. */
-	int (*print_tuple)(struct seq_file *s,
-			   const struct nf_conntrack_tuple *);
+	void (*print_tuple)(struct seq_file *s,
+			    const struct nf_conntrack_tuple *);
 
 	/*
 	 * Called before tracking. 
diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index 82e4ec002a3..1f7061313d5 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -56,8 +56,8 @@ struct nf_conntrack_l4proto {
 		     u_int8_t pf, unsigned int hooknum);
 
 	/* Print out the per-protocol part of the tuple. Return like seq_* */
-	int (*print_tuple)(struct seq_file *s,
-			   const struct nf_conntrack_tuple *);
+	void (*print_tuple)(struct seq_file *s,
+			    const struct nf_conntrack_tuple *);
 
 	/* Print out the private part of the conntrack. */
 	void (*print_conntrack)(struct seq_file *s, struct nf_conn *);
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index a054fe08343..5c61328b770 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -56,11 +56,11 @@ static bool ipv4_invert_tuple(struct nf_conntrack_tuple *tuple,
 	return true;
 }
 
-static int ipv4_print_tuple(struct seq_file *s,
+static void ipv4_print_tuple(struct seq_file *s,
 			    const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "src=%pI4 dst=%pI4 ",
-			  &tuple->src.u3.ip, &tuple->dst.u3.ip);
+	seq_printf(s, "src=%pI4 dst=%pI4 ",
+		   &tuple->src.u3.ip, &tuple->dst.u3.ip);
 }
 
 static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 91f207c2cb6..d927f9e7213 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -153,8 +153,10 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	if (seq_has_overflowed(s))
 		goto release;
 
-	if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
-			l3proto, l4proto))
+	print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+		    l3proto, l4proto);
+
+	if (seq_has_overflowed(s))
 		goto release;
 
 	if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL))
@@ -164,8 +166,10 @@ static int ct_seq_show(struct seq_file *s, void *v)
 		if (seq_printf(s, "[UNREPLIED] "))
 			goto release;
 
-	if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
-			l3proto, l4proto))
+	print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+		    l3proto, l4proto);
+
+	if (seq_has_overflowed(s))
 		goto release;
 
 	if (seq_print_acct(s, ct, IP_CT_DIR_REPLY))
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index b91b2641add..80d5554b9a8 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -72,13 +72,13 @@ static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int icmp_print_tuple(struct seq_file *s,
+static void icmp_print_tuple(struct seq_file *s,
 			    const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "type=%u code=%u id=%u ",
-			  tuple->dst.u.icmp.type,
-			  tuple->dst.u.icmp.code,
-			  ntohs(tuple->src.u.icmp.id));
+	seq_printf(s, "type=%u code=%u id=%u ",
+		   tuple->dst.u.icmp.type,
+		   tuple->dst.u.icmp.code,
+		   ntohs(tuple->src.u.icmp.id));
 }
 
 static unsigned int *icmp_get_timeouts(struct net *net)
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 4cbc6b290dd..b68d0e59c1f 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -60,11 +60,11 @@ static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple,
 	return true;
 }
 
-static int ipv6_print_tuple(struct seq_file *s,
+static void ipv6_print_tuple(struct seq_file *s,
 			    const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "src=%pI6 dst=%pI6 ",
-			  tuple->src.u3.ip6, tuple->dst.u3.ip6);
+	seq_printf(s, "src=%pI6 dst=%pI6 ",
+		   tuple->src.u3.ip6, tuple->dst.u3.ip6);
 }
 
 static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index b3807c5cb88..90388d60648 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -84,13 +84,13 @@ static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int icmpv6_print_tuple(struct seq_file *s,
+static void icmpv6_print_tuple(struct seq_file *s,
 			      const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "type=%u code=%u id=%u ",
-			  tuple->dst.u.icmp.type,
-			  tuple->dst.u.icmp.code,
-			  ntohs(tuple->src.u.icmp.id));
+	seq_printf(s, "type=%u code=%u id=%u ",
+		   tuple->dst.u.icmp.type,
+		   tuple->dst.u.icmp.code,
+		   ntohs(tuple->src.u.icmp.id));
 }
 
 static unsigned int *icmpv6_get_timeouts(struct net *net)
diff --git a/net/netfilter/nf_conntrack_l3proto_generic.c b/net/netfilter/nf_conntrack_l3proto_generic.c
index e7eb807fe07..cf9ace70bec 100644
--- a/net/netfilter/nf_conntrack_l3proto_generic.c
+++ b/net/netfilter/nf_conntrack_l3proto_generic.c
@@ -49,10 +49,9 @@ static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple,
 	return true;
 }
 
-static int generic_print_tuple(struct seq_file *s,
-			    const struct nf_conntrack_tuple *tuple)
+static void generic_print_tuple(struct seq_file *s,
+				const struct nf_conntrack_tuple *tuple)
 {
-	return 0;
 }
 
 static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index 15971177470..6dd995c7c72 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -618,12 +618,12 @@ out_invalid:
 	return -NF_ACCEPT;
 }
 
-static int dccp_print_tuple(struct seq_file *s,
-			    const struct nf_conntrack_tuple *tuple)
+static void dccp_print_tuple(struct seq_file *s,
+			     const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "sport=%hu dport=%hu ",
-			  ntohs(tuple->src.u.dccp.port),
-			  ntohs(tuple->dst.u.dccp.port));
+	seq_printf(s, "sport=%hu dport=%hu ",
+		   ntohs(tuple->src.u.dccp.port),
+		   ntohs(tuple->dst.u.dccp.port));
 }
 
 static void dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c
index 957c1db6665..60865f11030 100644
--- a/net/netfilter/nf_conntrack_proto_generic.c
+++ b/net/netfilter/nf_conntrack_proto_generic.c
@@ -63,10 +63,9 @@ static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int generic_print_tuple(struct seq_file *s,
-			       const struct nf_conntrack_tuple *tuple)
+static void generic_print_tuple(struct seq_file *s,
+				const struct nf_conntrack_tuple *tuple)
 {
-	return 0;
 }
 
 static unsigned int *generic_get_timeouts(struct net *net)
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index cba607ada06..7648674f29c 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -226,12 +226,12 @@ static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
 }
 
 /* print gre part of tuple */
-static int gre_print_tuple(struct seq_file *s,
-			   const struct nf_conntrack_tuple *tuple)
+static void gre_print_tuple(struct seq_file *s,
+			    const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "srckey=0x%x dstkey=0x%x ",
-			  ntohs(tuple->src.u.gre.key),
-			  ntohs(tuple->dst.u.gre.key));
+	seq_printf(s, "srckey=0x%x dstkey=0x%x ",
+		   ntohs(tuple->src.u.gre.key),
+		   ntohs(tuple->dst.u.gre.key));
 }
 
 /* print private data for conntrack */
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index c61f4cd6407..b45da90fad3 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -166,12 +166,12 @@ static bool sctp_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int sctp_print_tuple(struct seq_file *s,
-			    const struct nf_conntrack_tuple *tuple)
+static void sctp_print_tuple(struct seq_file *s,
+			     const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "sport=%hu dport=%hu ",
-			  ntohs(tuple->src.u.sctp.port),
-			  ntohs(tuple->dst.u.sctp.port));
+	seq_printf(s, "sport=%hu dport=%hu ",
+		   ntohs(tuple->src.u.sctp.port),
+		   ntohs(tuple->dst.u.sctp.port));
 }
 
 /* Print out the private part of the conntrack. */
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 79668fd3db9..36a3ac8ee9f 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -302,12 +302,12 @@ static bool tcp_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int tcp_print_tuple(struct seq_file *s,
-			   const struct nf_conntrack_tuple *tuple)
+static void tcp_print_tuple(struct seq_file *s,
+			    const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "sport=%hu dport=%hu ",
-			  ntohs(tuple->src.u.tcp.port),
-			  ntohs(tuple->dst.u.tcp.port));
+	seq_printf(s, "sport=%hu dport=%hu ",
+		   ntohs(tuple->src.u.tcp.port),
+		   ntohs(tuple->dst.u.tcp.port));
 }
 
 /* Print out the private part of the conntrack. */
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index 9d7721cbce4..6957281ffee 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -63,12 +63,12 @@ static bool udp_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int udp_print_tuple(struct seq_file *s,
-			   const struct nf_conntrack_tuple *tuple)
+static void udp_print_tuple(struct seq_file *s,
+			    const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "sport=%hu dport=%hu ",
-			  ntohs(tuple->src.u.udp.port),
-			  ntohs(tuple->dst.u.udp.port));
+	seq_printf(s, "sport=%hu dport=%hu ",
+		   ntohs(tuple->src.u.udp.port),
+		   ntohs(tuple->dst.u.udp.port));
 }
 
 static unsigned int *udp_get_timeouts(struct net *net)
diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c
index 2750e6c69f8..c5903d1649f 100644
--- a/net/netfilter/nf_conntrack_proto_udplite.c
+++ b/net/netfilter/nf_conntrack_proto_udplite.c
@@ -71,12 +71,12 @@ static bool udplite_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int udplite_print_tuple(struct seq_file *s,
-			       const struct nf_conntrack_tuple *tuple)
+static void udplite_print_tuple(struct seq_file *s,
+				const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "sport=%hu dport=%hu ",
-			  ntohs(tuple->src.u.udp.port),
-			  ntohs(tuple->dst.u.udp.port));
+	seq_printf(s, "sport=%hu dport=%hu ",
+		   ntohs(tuple->src.u.udp.port),
+		   ntohs(tuple->dst.u.udp.port));
 }
 
 static unsigned int *udplite_get_timeouts(struct net *net)
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 348aa360278..23a0dcab21d 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -36,12 +36,13 @@
 MODULE_LICENSE("GPL");
 
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
-int
+void
 print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
             const struct nf_conntrack_l3proto *l3proto,
             const struct nf_conntrack_l4proto *l4proto)
 {
-	return l3proto->print_tuple(s, tuple) || l4proto->print_tuple(s, tuple);
+	l3proto->print_tuple(s, tuple);
+	l4proto->print_tuple(s, tuple);
 }
 EXPORT_SYMBOL_GPL(print_tuple);
 
@@ -202,9 +203,8 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	if (l4proto->print_conntrack)
 		l4proto->print_conntrack(s, ct);
 
-	if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
-			l3proto, l4proto))
-		goto release;
+	print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+		    l3proto, l4proto);
 
 	if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL))
 		goto release;
@@ -213,9 +213,8 @@ static int ct_seq_show(struct seq_file *s, void *v)
 		if (seq_printf(s, "[UNREPLIED] "))
 			goto release;
 
-	if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
-			l3proto, l4proto))
-		goto release;
+	print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+		    l3proto, l4proto);
 
 	if (seq_print_acct(s, ct, IP_CT_DIR_REPLY))
 		goto release;
-- 
cgit v1.2.3-70-g09d2


From a3816ab0e8fe542a89a53b82506a8ddac063fbe3 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 29 Sep 2014 16:08:25 -0700
Subject: fs: Convert show_fdinfo functions to void

seq_printf functions shouldn't really check the return value.
Checking seq_has_overflowed() occasionally is used instead.

Update vfs documentation.

Link: http://lkml.kernel.org/p/e37e6e7b76acbdcc3bb4ab2a57c8f8ca1ae11b9a.1412031505.git.joe@perches.com

Cc: David S. Miller <davem@davemloft.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Joe Perches <joe@perches.com>
[ did a few clean ups ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 Documentation/filesystems/vfs.txt |  2 +-
 drivers/net/tun.c                 |  4 +-
 fs/eventfd.c                      |  9 ++---
 fs/eventpoll.c                    | 13 +++----
 fs/notify/fdinfo.c                | 78 ++++++++++++++++-----------------------
 fs/notify/fdinfo.h                |  4 +-
 fs/proc/fd.c                      |  3 +-
 fs/signalfd.c                     |  4 +-
 fs/timerfd.c                      | 27 +++++++-------
 include/linux/fs.h                |  2 +-
 10 files changed, 63 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index fceff7c00a3..af1dbc1823b 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -828,7 +828,7 @@ struct file_operations {
 	ssize_t (*splice_read)(struct file *, struct pipe_inode_info *, size_t, unsigned int);
 	int (*setlease)(struct file *, long arg, struct file_lock **, void **);
 	long (*fallocate)(struct file *, int mode, loff_t offset, loff_t len);
-	int (*show_fdinfo)(struct seq_file *m, struct file *f);
+	void (*show_fdinfo)(struct seq_file *m, struct file *f);
 };
 
 Again, all methods are called without any locks being held, unless
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 186ce541c65..a3420e09168 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2209,7 +2209,7 @@ static int tun_chr_close(struct inode *inode, struct file *file)
 }
 
 #ifdef CONFIG_PROC_FS
-static int tun_chr_show_fdinfo(struct seq_file *m, struct file *f)
+static void tun_chr_show_fdinfo(struct seq_file *m, struct file *f)
 {
 	struct tun_struct *tun;
 	struct ifreq ifr;
@@ -2225,7 +2225,7 @@ static int tun_chr_show_fdinfo(struct seq_file *m, struct file *f)
 	if (tun)
 		tun_put(tun);
 
-	return seq_printf(m, "iff:\t%s\n", ifr.ifr_name);
+	seq_printf(m, "iff:\t%s\n", ifr.ifr_name);
 }
 #endif
 
diff --git a/fs/eventfd.c b/fs/eventfd.c
index d6a88e7812f..4b0a226024f 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -287,17 +287,14 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c
 }
 
 #ifdef CONFIG_PROC_FS
-static int eventfd_show_fdinfo(struct seq_file *m, struct file *f)
+static void eventfd_show_fdinfo(struct seq_file *m, struct file *f)
 {
 	struct eventfd_ctx *ctx = f->private_data;
-	int ret;
 
 	spin_lock_irq(&ctx->wqh.lock);
-	ret = seq_printf(m, "eventfd-count: %16llx\n",
-			 (unsigned long long)ctx->count);
+	seq_printf(m, "eventfd-count: %16llx\n",
+		   (unsigned long long)ctx->count);
 	spin_unlock_irq(&ctx->wqh.lock);
-
-	return ret;
 }
 #endif
 
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 7bcfff900f0..d77f9449135 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -870,25 +870,22 @@ static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
 }
 
 #ifdef CONFIG_PROC_FS
-static int ep_show_fdinfo(struct seq_file *m, struct file *f)
+static void ep_show_fdinfo(struct seq_file *m, struct file *f)
 {
 	struct eventpoll *ep = f->private_data;
 	struct rb_node *rbp;
-	int ret = 0;
 
 	mutex_lock(&ep->mtx);
 	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		struct epitem *epi = rb_entry(rbp, struct epitem, rbn);
 
-		ret = seq_printf(m, "tfd: %8d events: %8x data: %16llx\n",
-				 epi->ffd.fd, epi->event.events,
-				 (long long)epi->event.data);
-		if (ret)
+		seq_printf(m, "tfd: %8d events: %8x data: %16llx\n",
+			   epi->ffd.fd, epi->event.events,
+			   (long long)epi->event.data);
+		if (seq_has_overflowed(m))
 			break;
 	}
 	mutex_unlock(&ep->mtx);
-
-	return ret;
 }
 #endif
 
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index 9d7e2b9659c..6ffd220eb14 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -20,25 +20,24 @@
 
 #if defined(CONFIG_INOTIFY_USER) || defined(CONFIG_FANOTIFY)
 
-static int show_fdinfo(struct seq_file *m, struct file *f,
-		       int (*show)(struct seq_file *m, struct fsnotify_mark *mark))
+static void show_fdinfo(struct seq_file *m, struct file *f,
+			void (*show)(struct seq_file *m,
+				     struct fsnotify_mark *mark))
 {
 	struct fsnotify_group *group = f->private_data;
 	struct fsnotify_mark *mark;
-	int ret = 0;
 
 	mutex_lock(&group->mark_mutex);
 	list_for_each_entry(mark, &group->marks_list, g_list) {
-		ret = show(m, mark);
-		if (ret)
+		show(m, mark);
+		if (seq_has_overflowed(m))
 			break;
 	}
 	mutex_unlock(&group->mark_mutex);
-	return ret;
 }
 
 #if defined(CONFIG_EXPORTFS)
-static int show_mark_fhandle(struct seq_file *m, struct inode *inode)
+static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
 {
 	struct {
 		struct file_handle handle;
@@ -52,71 +51,62 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode)
 	ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, 0);
 	if ((ret == FILEID_INVALID) || (ret < 0)) {
 		WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret);
-		return 0;
+		return;
 	}
 
 	f.handle.handle_type = ret;
 	f.handle.handle_bytes = size * sizeof(u32);
 
-	ret = seq_printf(m, "fhandle-bytes:%x fhandle-type:%x f_handle:",
-			 f.handle.handle_bytes, f.handle.handle_type);
+	seq_printf(m, "fhandle-bytes:%x fhandle-type:%x f_handle:",
+		   f.handle.handle_bytes, f.handle.handle_type);
 
 	for (i = 0; i < f.handle.handle_bytes; i++)
-		ret |= seq_printf(m, "%02x", (int)f.handle.f_handle[i]);
-
-	return ret;
+		seq_printf(m, "%02x", (int)f.handle.f_handle[i]);
 }
 #else
-static int show_mark_fhandle(struct seq_file *m, struct inode *inode)
+static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
 {
-	return 0;
 }
 #endif
 
 #ifdef CONFIG_INOTIFY_USER
 
-static int inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
+static void inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
 {
 	struct inotify_inode_mark *inode_mark;
 	struct inode *inode;
-	int ret = 0;
 
 	if (!(mark->flags & (FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_INODE)))
-		return 0;
+		return;
 
 	inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark);
 	inode = igrab(mark->i.inode);
 	if (inode) {
-		ret = seq_printf(m, "inotify wd:%x ino:%lx sdev:%x "
-				 "mask:%x ignored_mask:%x ",
-				 inode_mark->wd, inode->i_ino,
-				 inode->i_sb->s_dev,
-				 mark->mask, mark->ignored_mask);
-		ret |= show_mark_fhandle(m, inode);
-		ret |= seq_putc(m, '\n');
+		seq_printf(m, "inotify wd:%x ino:%lx sdev:%x mask:%x ignored_mask:%x ",
+			   inode_mark->wd, inode->i_ino, inode->i_sb->s_dev,
+			   mark->mask, mark->ignored_mask);
+		show_mark_fhandle(m, inode);
+		seq_putc(m, '\n');
 		iput(inode);
 	}
-
-	return ret;
 }
 
-int inotify_show_fdinfo(struct seq_file *m, struct file *f)
+void inotify_show_fdinfo(struct seq_file *m, struct file *f)
 {
-	return show_fdinfo(m, f, inotify_fdinfo);
+	show_fdinfo(m, f, inotify_fdinfo);
 }
 
 #endif /* CONFIG_INOTIFY_USER */
 
 #ifdef CONFIG_FANOTIFY
 
-static int fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
+static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
 {
 	unsigned int mflags = 0;
 	struct inode *inode;
-	int ret = 0;
 
 	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE))
-		return 0;
+		return;
 
 	if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
 		mflags |= FAN_MARK_IGNORED_SURV_MODIFY;
@@ -124,26 +114,22 @@ static int fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
 	if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) {
 		inode = igrab(mark->i.inode);
 		if (!inode)
-			goto out;
-		ret = seq_printf(m, "fanotify ino:%lx sdev:%x "
-				 "mflags:%x mask:%x ignored_mask:%x ",
-				 inode->i_ino, inode->i_sb->s_dev,
-				 mflags, mark->mask, mark->ignored_mask);
-		ret |= show_mark_fhandle(m, inode);
-		ret |= seq_putc(m, '\n');
+			return;
+		seq_printf(m, "fanotify ino:%lx sdev:%x mflags:%x mask:%x ignored_mask:%x ",
+			   inode->i_ino, inode->i_sb->s_dev,
+			   mflags, mark->mask, mark->ignored_mask);
+		show_mark_fhandle(m, inode);
+		seq_putc(m, '\n');
 		iput(inode);
 	} else if (mark->flags & FSNOTIFY_MARK_FLAG_VFSMOUNT) {
 		struct mount *mnt = real_mount(mark->m.mnt);
 
-		ret = seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x "
-				 "ignored_mask:%x\n", mnt->mnt_id, mflags,
-				 mark->mask, mark->ignored_mask);
+		seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x ignored_mask:%x\n",
+			   mnt->mnt_id, mflags, mark->mask, mark->ignored_mask);
 	}
-out:
-	return ret;
 }
 
-int fanotify_show_fdinfo(struct seq_file *m, struct file *f)
+void fanotify_show_fdinfo(struct seq_file *m, struct file *f)
 {
 	struct fsnotify_group *group = f->private_data;
 	unsigned int flags = 0;
@@ -169,7 +155,7 @@ int fanotify_show_fdinfo(struct seq_file *m, struct file *f)
 	seq_printf(m, "fanotify flags:%x event-flags:%x\n",
 		   flags, group->fanotify_data.f_flags);
 
-	return show_fdinfo(m, f, fanotify_fdinfo);
+	show_fdinfo(m, f, fanotify_fdinfo);
 }
 
 #endif /* CONFIG_FANOTIFY */
diff --git a/fs/notify/fdinfo.h b/fs/notify/fdinfo.h
index 556afda990e..9664c4904d6 100644
--- a/fs/notify/fdinfo.h
+++ b/fs/notify/fdinfo.h
@@ -10,11 +10,11 @@ struct file;
 #ifdef CONFIG_PROC_FS
 
 #ifdef CONFIG_INOTIFY_USER
-extern int inotify_show_fdinfo(struct seq_file *m, struct file *f);
+void inotify_show_fdinfo(struct seq_file *m, struct file *f);
 #endif
 
 #ifdef CONFIG_FANOTIFY
-extern int fanotify_show_fdinfo(struct seq_file *m, struct file *f);
+void fanotify_show_fdinfo(struct seq_file *m, struct file *f);
 #endif
 
 #else /* CONFIG_PROC_FS */
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index e11d7c590bb..8e5ad83b629 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -53,7 +53,8 @@ static int seq_show(struct seq_file *m, void *v)
 			   (long long)file->f_pos, f_flags,
 			   real_mount(file->f_path.mnt)->mnt_id);
 		if (file->f_op->show_fdinfo)
-			ret = file->f_op->show_fdinfo(m, file);
+			file->f_op->show_fdinfo(m, file);
+		ret = seq_has_overflowed(m);
 		fput(file);
 	}
 
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 424b7b65321..7e412ad7483 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -230,7 +230,7 @@ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count,
 }
 
 #ifdef CONFIG_PROC_FS
-static int signalfd_show_fdinfo(struct seq_file *m, struct file *f)
+static void signalfd_show_fdinfo(struct seq_file *m, struct file *f)
 {
 	struct signalfd_ctx *ctx = f->private_data;
 	sigset_t sigmask;
@@ -238,8 +238,6 @@ static int signalfd_show_fdinfo(struct seq_file *m, struct file *f)
 	sigmask = ctx->sigmask;
 	signotset(&sigmask);
 	render_sigset_t(m, "sigmask:\t", &sigmask);
-
-	return 0;
 }
 #endif
 
diff --git a/fs/timerfd.c b/fs/timerfd.c
index b46ffa94372..b94fa6c3c6e 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -288,7 +288,7 @@ static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
 }
 
 #ifdef CONFIG_PROC_FS
-static int timerfd_show(struct seq_file *m, struct file *file)
+static void timerfd_show(struct seq_file *m, struct file *file)
 {
 	struct timerfd_ctx *ctx = file->private_data;
 	struct itimerspec t;
@@ -298,18 +298,19 @@ static int timerfd_show(struct seq_file *m, struct file *file)
 	t.it_interval = ktime_to_timespec(ctx->tintv);
 	spin_unlock_irq(&ctx->wqh.lock);
 
-	return seq_printf(m,
-			  "clockid: %d\n"
-			  "ticks: %llu\n"
-			  "settime flags: 0%o\n"
-			  "it_value: (%llu, %llu)\n"
-			  "it_interval: (%llu, %llu)\n",
-			  ctx->clockid, (unsigned long long)ctx->ticks,
-			  ctx->settime_flags,
-			  (unsigned long long)t.it_value.tv_sec,
-			  (unsigned long long)t.it_value.tv_nsec,
-			  (unsigned long long)t.it_interval.tv_sec,
-			  (unsigned long long)t.it_interval.tv_nsec);
+	seq_printf(m,
+		   "clockid: %d\n"
+		   "ticks: %llu\n"
+		   "settime flags: 0%o\n"
+		   "it_value: (%llu, %llu)\n"
+		   "it_interval: (%llu, %llu)\n",
+		   ctx->clockid,
+		   (unsigned long long)ctx->ticks,
+		   ctx->settime_flags,
+		   (unsigned long long)t.it_value.tv_sec,
+		   (unsigned long long)t.it_value.tv_nsec,
+		   (unsigned long long)t.it_interval.tv_sec,
+		   (unsigned long long)t.it_interval.tv_nsec);
 }
 #else
 #define timerfd_show NULL
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a957d4366c2..01dd9052a14 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1491,7 +1491,7 @@ struct file_operations {
 	int (*setlease)(struct file *, long, struct file_lock **, void **);
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);
-	int (*show_fdinfo)(struct seq_file *m, struct file *f);
+	void (*show_fdinfo)(struct seq_file *m, struct file *f);
 };
 
 struct inode_operations {
-- 
cgit v1.2.3-70-g09d2


From 9761536e1d9e9e1f325fb04d4ad46b15a39eb94a Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 29 Sep 2014 16:08:26 -0700
Subject: debugfs: Have debugfs_print_regs32() return void

The seq_printf() will soon just return void, and seq_has_overflowed()
should be used instead to see if the seq can no longer accept input.

As the return value of debugfs_print_regs32() has no users and
the seq_file descriptor should be checked with seq_has_overflowed()
instead of return values of functions, it is better to just have
debugfs_print_regs32() also return void.

Link: http://lkml.kernel.org/p/2634b19eb1c04a9d31148c1fe6f1f3819be95349.1412031505.git.joe@perches.com

Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Joe Perches <joe@perches.com>
[ original change only updated seq_printf() return, added return of
  void to debugfs_print_regs32() as well ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 Documentation/filesystems/debugfs.txt |  2 +-
 fs/debugfs/file.c                     | 15 ++++++++-------
 include/linux/debugfs.h               |  7 +++----
 3 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt
index 3a863f69272..88ab81c7910 100644
--- a/Documentation/filesystems/debugfs.txt
+++ b/Documentation/filesystems/debugfs.txt
@@ -140,7 +140,7 @@ file.
 				     struct dentry *parent,
 				     struct debugfs_regset32 *regset);
 
-    int debugfs_print_regs32(struct seq_file *s, struct debugfs_reg32 *regs,
+    void debugfs_print_regs32(struct seq_file *s, struct debugfs_reg32 *regs,
 			 int nregs, void __iomem *base, char *prefix);
 
 The "base" argument may be 0, but you may want to build the reg32 array
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 76c08c2beb2..8e0f2f41018 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -692,18 +692,19 @@ EXPORT_SYMBOL_GPL(debugfs_create_u32_array);
  * because some peripherals have several blocks of identical registers,
  * for example configuration of dma channels
  */
-int debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs,
-			   int nregs, void __iomem *base, char *prefix)
+void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs,
+			  int nregs, void __iomem *base, char *prefix)
 {
-	int i, ret = 0;
+	int i;
 
 	for (i = 0; i < nregs; i++, regs++) {
 		if (prefix)
-			ret += seq_printf(s, "%s", prefix);
-		ret += seq_printf(s, "%s = 0x%08x\n", regs->name,
-				  readl(base + regs->offset));
+			seq_printf(s, "%s", prefix);
+		seq_printf(s, "%s = 0x%08x\n", regs->name,
+			   readl(base + regs->offset));
+		if (seq_has_overflowed(s))
+			break;
 	}
-	return ret;
 }
 EXPORT_SYMBOL_GPL(debugfs_print_regs32);
 
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index 4d0b4d1aa13..d84f8c254a8 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -92,8 +92,8 @@ struct dentry *debugfs_create_regset32(const char *name, umode_t mode,
 				     struct dentry *parent,
 				     struct debugfs_regset32 *regset);
 
-int debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs,
-			 int nregs, void __iomem *base, char *prefix);
+void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs,
+			  int nregs, void __iomem *base, char *prefix);
 
 struct dentry *debugfs_create_u32_array(const char *name, umode_t mode,
 					struct dentry *parent,
@@ -233,10 +233,9 @@ static inline struct dentry *debugfs_create_regset32(const char *name,
 	return ERR_PTR(-ENODEV);
 }
 
-static inline int debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs,
+static inline void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs,
 			 int nregs, void __iomem *base, char *prefix)
 {
-	return 0;
 }
 
 static inline bool debugfs_initialized(void)
-- 
cgit v1.2.3-70-g09d2


From b4c9f578cb9608f7de0c89aa637a6af4a48061ef Mon Sep 17 00:00:00 2001
From: Jingoo Han <jg1.han@samsung.com>
Date: Tue, 4 Nov 2014 11:01:47 +0900
Subject: usb: dwc3: exynos: remove non-DT support for Exynos Specific Glue
 layer

DWC3 Exynos Specific Glue layer can be used only for Exynos SoCs.
In addition, non-DT for EXYNOS SoCs is not supported from v3.11;
thus, there is no need to support non-DT for DWC3 Exynos Specific
Glue layer.

The 'linux/platform_data/dwc3-exynos.h' file has been used for
non-DT support. Thus, the 'dwc3-exynos.h' file is removed, because
it is not used anymore.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/dwc3/Kconfig                  |  2 +-
 drivers/usb/dwc3/dwc3-exynos.c            |  5 +----
 include/linux/platform_data/dwc3-exynos.h | 24 ------------------------
 3 files changed, 2 insertions(+), 29 deletions(-)
 delete mode 100644 include/linux/platform_data/dwc3-exynos.h

(limited to 'include')

diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig
index f4e5cc60db0..58b5b2cde4c 100644
--- a/drivers/usb/dwc3/Kconfig
+++ b/drivers/usb/dwc3/Kconfig
@@ -55,7 +55,7 @@ config USB_DWC3_OMAP
 
 config USB_DWC3_EXYNOS
 	tristate "Samsung Exynos Platform"
-	depends on ARCH_EXYNOS || COMPILE_TEST
+	depends on ARCH_EXYNOS && OF || COMPILE_TEST
 	default USB_DWC3
 	help
 	  Recent Exynos5 SoCs ship with one DesignWare Core USB3 IP inside,
diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c
index 3951a65fea0..4369c6658ec 100644
--- a/drivers/usb/dwc3/dwc3-exynos.c
+++ b/drivers/usb/dwc3/dwc3-exynos.c
@@ -20,7 +20,6 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/platform_device.h>
-#include <linux/platform_data/dwc3-exynos.h>
 #include <linux/dma-mapping.h>
 #include <linux/clk.h>
 #include <linux/usb/otg.h>
@@ -205,13 +204,11 @@ static int dwc3_exynos_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_OF
 static const struct of_device_id exynos_dwc3_match[] = {
 	{ .compatible = "samsung,exynos5250-dwusb3" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, exynos_dwc3_match);
-#endif
 
 #ifdef CONFIG_PM_SLEEP
 static int dwc3_exynos_suspend(struct device *dev)
@@ -266,7 +263,7 @@ static struct platform_driver dwc3_exynos_driver = {
 	.remove		= dwc3_exynos_remove,
 	.driver		= {
 		.name	= "exynos-dwc3",
-		.of_match_table = of_match_ptr(exynos_dwc3_match),
+		.of_match_table = exynos_dwc3_match,
 		.pm	= DEV_PM_OPS,
 	},
 };
diff --git a/include/linux/platform_data/dwc3-exynos.h b/include/linux/platform_data/dwc3-exynos.h
deleted file mode 100644
index 5eb7da9b377..00000000000
--- a/include/linux/platform_data/dwc3-exynos.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/**
- * dwc3-exynos.h - Samsung EXYNOS DWC3 Specific Glue layer, header.
- *
- * Copyright (c) 2012 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * Author: Anton Tikhomirov <av.tikhomirov@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef _DWC3_EXYNOS_H_
-#define _DWC3_EXYNOS_H_
-
-struct dwc3_exynos_data {
-	int phy_type;
-	int (*phy_init)(struct platform_device *pdev, int type);
-	int (*phy_exit)(struct platform_device *pdev, int type);
-};
-
-#endif /* _DWC3_EXYNOS_H_ */
-- 
cgit v1.2.3-70-g09d2


From 60ba032ed76e851d30d4fa514847285252147d07 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 5 Nov 2014 00:29:07 +0100
Subject: ACPI / property: Drop size_prop from
 acpi_dev_get_property_reference()

The size_prop argument of the recently added function
acpi_dev_get_property_reference() is not used by the only current
caller of that function and is very unlikely to be used at any time
going forward.

Namely, for a property whose value is a list of items each containing
a references to a device object possibly accompanied by some integers,
the number of items in the list can always be computed as the number
of elements of type ACPI_TYPE_LOCAL_REFERENCE in the property package.
Thus it should never be necessary to provide an additional "cells"
property with a value equal to the number of items in that list.  It
also should never be necessary to provide a "cells" property specifying
how many integers are supposed to be following each reference.

For this reason, drop the size_prop argument from
acpi_dev_get_property_reference() and update its caller accordingly.

Link: http://marc.info/?l=linux-kernel&m=141511255610556&w=2
Suggested-by: Grant Likely <grant.likely@linaro.org>
Acked-by: Grant Likely <grant.likely@linaro.org>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Tested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/property.c     | 62 ++++++++++++---------------------------------
 drivers/gpio/gpiolib-acpi.c |  2 +-
 include/linux/acpi.h        |  4 +--
 3 files changed, 19 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 27add91bc27..0d083736e25 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -273,25 +273,21 @@ EXPORT_SYMBOL_GPL(acpi_dev_get_property_array);
  * acpi_dev_get_property_reference - returns handle to the referenced object
  * @adev: ACPI device to get property
  * @name: Name of the property
- * @size_prop: Name of the "size" property in referenced object
  * @index: Index of the reference to return
  * @args: Location to store the returned reference with optional arguments
  *
  * Find property with @name, verifify that it is a package containing at least
  * one object reference and if so, store the ACPI device object pointer to the
- * target object in @args->adev.
+ * target object in @args->adev.  If the reference includes arguments, store
+ * them in the @args->args[] array.
  *
- * If the reference includes arguments (@size_prop is not %NULL) follow the
- * reference and check whether or not there is an integer property @size_prop
- * under the target object and if so, whether or not its value matches the
- * number of arguments that follow the reference.  If there's more than one
- * reference in the property value package, @index is used to select the one to
- * return.
+ * If there's more than one reference in the property value package, @index is
+ * used to select the one to return.
  *
  * Return: %0 on success, negative error code on failure.
  */
-int acpi_dev_get_property_reference(struct acpi_device *adev, const char *name,
-				    const char *size_prop, size_t index,
+int acpi_dev_get_property_reference(struct acpi_device *adev,
+				    const char *name, size_t index,
 				    struct acpi_reference_args *args)
 {
 	const union acpi_object *element, *end;
@@ -308,7 +304,7 @@ int acpi_dev_get_property_reference(struct acpi_device *adev, const char *name,
 	 * return that reference then.
 	 */
 	if (obj->type == ACPI_TYPE_LOCAL_REFERENCE) {
-		if (size_prop || index)
+		if (index)
 			return -EINVAL;
 
 		ret = acpi_bus_get_device(obj->reference.handle, &device);
@@ -348,42 +344,16 @@ int acpi_dev_get_property_reference(struct acpi_device *adev, const char *name,
 		element++;
 		nargs = 0;
 
-		if (size_prop) {
-			const union acpi_object *prop;
-
-			/*
-			 * Find out how many arguments the refenced object
-			 * expects by reading its size_prop property.
-			 */
-			ret = acpi_dev_get_property(device, size_prop,
-						    ACPI_TYPE_INTEGER, &prop);
-			if (ret)
-				return ret;
-
-			nargs = prop->integer.value;
-			if (nargs > MAX_ACPI_REFERENCE_ARGS
-			    || element + nargs > end)
-				return -EPROTO;
+		/* assume following integer elements are all args */
+		for (i = 0; element + i < end; i++) {
+			int type = element[i].type;
 
-			/*
-			 * Skip to the start of the arguments and verify
-			 * that they all are in fact integers.
-			 */
-			for (i = 0; i < nargs; i++)
-				if (element[i].type != ACPI_TYPE_INTEGER)
-					return -EPROTO;
-		} else {
-			/* assume following integer elements are all args */
-			for (i = 0; element + i < end; i++) {
-				int type = element[i].type;
-
-				if (type == ACPI_TYPE_INTEGER)
-					nargs++;
-				else if (type == ACPI_TYPE_LOCAL_REFERENCE)
-					break;
-				else
-					return -EPROTO;
-			}
+			if (type == ACPI_TYPE_INTEGER)
+				nargs++;
+			else if (type == ACPI_TYPE_LOCAL_REFERENCE)
+				break;
+			else
+				return -EPROTO;
 		}
 
 		if (idx++ == index) {
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 5a4d061e787..ba98bb59a58 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -405,7 +405,7 @@ struct gpio_desc *acpi_get_gpiod_by_index(struct acpi_device *adev,
 		dev_dbg(&adev->dev, "GPIO: looking up %s\n", propname);
 
 		memset(&args, 0, sizeof(args));
-		ret = acpi_dev_get_property_reference(adev, propname, NULL,
+		ret = acpi_dev_get_property_reference(adev, propname,
 						      index, &args);
 		if (ret) {
 			bool found = acpi_get_driver_gpio_data(adev, propname,
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 0902426c452..10f2ed95645 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -718,8 +718,8 @@ int acpi_dev_get_property(struct acpi_device *adev, const char *name,
 int acpi_dev_get_property_array(struct acpi_device *adev, const char *name,
 				acpi_object_type type,
 				const union acpi_object **obj);
-int acpi_dev_get_property_reference(struct acpi_device *adev, const char *name,
-				    const char *cells_name, size_t index,
+int acpi_dev_get_property_reference(struct acpi_device *adev,
+				    const char *name, size_t index,
 				    struct acpi_reference_args *args);
 
 int acpi_dev_prop_get(struct acpi_device *adev, const char *propname,
-- 
cgit v1.2.3-70-g09d2


From 53f9ee61b46d81a43d8c6694d136896e8f49a7b8 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 5 Nov 2014 20:51:12 +0100
Subject: ieee802154: rework wpan_phy index assignment

This patch reworks the wpan_phy index incrementation. It's now similar
like wireless wiphy index incrementation. We move the wpan_phy index
attribute inside of cfg802154_registered_device and use atomic
operations instead locking mechanism via wpan_phy_mutex.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h |  1 -
 net/ieee802154/core.c   | 30 +++++++++++-------------------
 net/ieee802154/core.h   |  3 +++
 3 files changed, 14 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 864bce2b072..29c6de5a426 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -61,7 +61,6 @@ struct wpan_phy {
 	s32 cca_ed_level;
 
 	struct device dev;
-	int idx;
 
 	char priv[0] __aligned(NETDEV_ALIGN);
 };
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index ed5b014dbec..d1cd0edfb14 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -23,9 +23,6 @@
 #include "sysfs.h"
 #include "core.h"
 
-static DEFINE_MUTEX(wpan_phy_mutex);
-static int wpan_phy_idx;
-
 static int wpan_phy_match(struct device *dev, const void *data)
 {
 	return !strcmp(dev_name(dev), (const char *)data);
@@ -72,14 +69,10 @@ int wpan_phy_for_each(int (*fn)(struct wpan_phy *phy, void *data),
 }
 EXPORT_SYMBOL(wpan_phy_for_each);
 
-static int wpan_phy_idx_valid(int idx)
-{
-	return idx >= 0;
-}
-
 struct wpan_phy *
 wpan_phy_alloc(const struct cfg802154_ops *ops, size_t priv_size)
 {
+	static atomic_t wpan_phy_counter = ATOMIC_INIT(0);
 	struct cfg802154_registered_device *rdev;
 	size_t alloc_size;
 
@@ -90,28 +83,27 @@ wpan_phy_alloc(const struct cfg802154_ops *ops, size_t priv_size)
 
 	rdev->ops = ops;
 
-	mutex_lock(&wpan_phy_mutex);
-	rdev->wpan_phy.idx = wpan_phy_idx++;
-	if (unlikely(!wpan_phy_idx_valid(rdev->wpan_phy.idx))) {
-		wpan_phy_idx--;
-		mutex_unlock(&wpan_phy_mutex);
+	rdev->wpan_phy_idx = atomic_inc_return(&wpan_phy_counter);
+
+	if (unlikely(rdev->wpan_phy_idx < 0)) {
+		/* ugh, wrapped! */
+		atomic_dec(&wpan_phy_counter);
 		kfree(rdev);
-		goto out;
+		return NULL;
 	}
-	mutex_unlock(&wpan_phy_mutex);
+
+	/* atomic_inc_return makes it start at 1, make it start at 0 */
+	rdev->wpan_phy_idx--;
 
 	mutex_init(&rdev->wpan_phy.pib_lock);
 
 	device_initialize(&rdev->wpan_phy.dev);
-	dev_set_name(&rdev->wpan_phy.dev, "wpan-phy%d", rdev->wpan_phy.idx);
+	dev_set_name(&rdev->wpan_phy.dev, "wpan-phy%d", rdev->wpan_phy_idx);
 
 	rdev->wpan_phy.dev.class = &wpan_phy_class;
 	rdev->wpan_phy.dev.platform_data = rdev;
 
 	return &rdev->wpan_phy;
-
-out:
-	return NULL;
 }
 EXPORT_SYMBOL(wpan_phy_alloc);
 
diff --git a/net/ieee802154/core.h b/net/ieee802154/core.h
index 1bc17258715..fea60b3a884 100644
--- a/net/ieee802154/core.h
+++ b/net/ieee802154/core.h
@@ -6,6 +6,9 @@
 struct cfg802154_registered_device {
 	const struct cfg802154_ops *ops;
 
+	/* wpan_phy index, internal only */
+	int wpan_phy_idx;
+
 	/* must be last because of the way we do wpan_phy_priv(),
 	 * and it should at least be aligned to NETDEV_ALIGN
 	 */
-- 
cgit v1.2.3-70-g09d2


From 9f3295b9ea8e54a6c65231d267f069edf420b64f Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 5 Nov 2014 20:51:13 +0100
Subject: ieee802154: remove nl802154 unused functions

The include/net/nl802154.h file contains a lot of prototypes which are
not used inside of ieee802154 subsystem. This patch removes this file
and make the only one used prototype "ieee802154_nl_start_confirm" as
static declaration in ieee802154/nl-mac.c

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 MAINTAINERS             |   1 -
 include/net/nl802154.h  | 122 -------------------------------
 net/ieee802154/nl-mac.c | 187 ++----------------------------------------------
 net/mac802154/mac_cmd.c |   6 --
 4 files changed, 6 insertions(+), 310 deletions(-)
 delete mode 100644 include/net/nl802154.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 7ec37a396ff..b42eb50b742 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4699,7 +4699,6 @@ F:	net/mac802154/
 F:	drivers/net/ieee802154/
 F:	include/linux/nl802154.h
 F:	include/linux/ieee802154.h
-F:	include/net/nl802154.h
 F:	include/net/mac802154.h
 F:	include/net/af_ieee802154.h
 F:	include/net/cfg802154.h
diff --git a/include/net/nl802154.h b/include/net/nl802154.h
deleted file mode 100644
index b5cdea29d9d..00000000000
--- a/include/net/nl802154.h
+++ /dev/null
@@ -1,122 +0,0 @@
-/*
- * nl802154.h
- *
- * Copyright (C) 2007, 2008, 2009 Siemens AG
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef IEEE802154_NL_H
-#define IEEE802154_NL_H
-
-struct net_device;
-struct ieee802154_addr;
-
-/**
- * ieee802154_nl_assoc_indic - Notify userland of an association request.
- * @dev: The network device on which this association request was
- *       received.
- * @addr: The address of the device requesting association.
- * @cap: The capability information field from the device.
- *
- * This informs a userland coordinator of a device requesting to
- * associate with the PAN controlled by the coordinator.
- *
- * Note: This is in section 7.3.1 of the IEEE 802.15.4-2006 document.
- */
-int ieee802154_nl_assoc_indic(struct net_device *dev,
-		struct ieee802154_addr *addr, u8 cap);
-
-/**
- * ieee802154_nl_assoc_confirm - Notify userland of association.
- * @dev: The device which has completed association.
- * @short_addr: The short address assigned to the device.
- * @status: The status of the association.
- *
- * Inform userland of the result of an association request. If the
- * association request included asking the coordinator to allocate
- * a short address then it is returned in @short_addr.
- *
- * Note: This is in section 7.3.2 of the IEEE 802.15.4 document.
- */
-int ieee802154_nl_assoc_confirm(struct net_device *dev,
-		__le16 short_addr, u8 status);
-
-/**
- * ieee802154_nl_disassoc_indic - Notify userland of disassociation.
- * @dev: The device on which disassociation was indicated.
- * @addr: The device which is disassociating.
- * @reason: The reason for the disassociation.
- *
- * Inform userland that a device has disassociated from the network.
- *
- * Note: This is in section 7.3.3 of the IEEE 802.15.4 document.
- */
-int ieee802154_nl_disassoc_indic(struct net_device *dev,
-		struct ieee802154_addr *addr, u8 reason);
-
-/**
- * ieee802154_nl_disassoc_confirm - Notify userland of disassociation
- * completion.
- * @dev: The device on which disassociation was ordered.
- * @status: The result of the disassociation.
- *
- * Inform userland of the result of requesting that a device
- * disassociate, or the result of requesting that we disassociate from
- * a PAN managed by another coordinator.
- *
- * Note: This is in section 7.1.4.3 of the IEEE 802.15.4 document.
- */
-int ieee802154_nl_disassoc_confirm(struct net_device *dev,
-		u8 status);
-
-/**
- * ieee802154_nl_scan_confirm - Notify userland of completion of scan.
- * @dev: The device which was instructed to scan.
- * @status: The status of the scan operation.
- * @scan_type: What type of scan was performed.
- * @unscanned: Any channels that the device was unable to scan.
- * @edl: The energy levels (if a passive scan).
- *
- *
- * Note: This is in section 7.1.11 of the IEEE 802.15.4 document.
- * Note: This API does not permit the return of an active scan result.
- */
-int ieee802154_nl_scan_confirm(struct net_device *dev,
-		u8 status, u8 scan_type, u32 unscanned, u8 page,
-		u8 *edl/*, struct list_head *pan_desc_list */);
-
-/**
- * ieee802154_nl_beacon_indic - Notify userland of a received beacon.
- * @dev: The device on which a beacon was received.
- * @panid: The PAN of the coordinator.
- * @coord_addr: The short address of the coordinator on that PAN.
- *
- * Note: This is in section 7.1.5 of the IEEE 802.15.4 document.
- * Note: This API does not provide extended information such as what
- * channel the PAN is on or what the LQI of the beacon frame was on
- * receipt.
- * Note: This API cannot indicate a beacon frame for a coordinator
- *       operating in long addressing mode.
- */
-int ieee802154_nl_beacon_indic(struct net_device *dev, __le16 panid,
-		__le16 coord_addr);
-
-/**
- * ieee802154_nl_start_confirm - Notify userland of completion of start.
- * @dev: The device which was instructed to scan.
- * @status: The status of the scan operation.
- *
- * Note: This is in section 7.1.14 of the IEEE 802.15.4 document.
- */
-int ieee802154_nl_start_confirm(struct net_device *dev, u8 status);
-
-#endif
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index cc2919dbe5e..91a1855e521 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -29,7 +29,6 @@
 #include <linux/nl802154.h>
 #include <linux/export.h>
 #include <net/af_ieee802154.h>
-#include <net/nl802154.h>
 #include <net/ieee802154_netdev.h>
 #include <net/cfg802154.h>
 
@@ -55,186 +54,7 @@ static __le16 nla_get_shortaddr(const struct nlattr *nla)
 	return cpu_to_le16(nla_get_u16(nla));
 }
 
-int ieee802154_nl_assoc_indic(struct net_device *dev,
-			      struct ieee802154_addr *addr,
-			      u8 cap)
-{
-	struct sk_buff *msg;
-
-	pr_debug("%s\n", __func__);
-
-	if (addr->mode != IEEE802154_ADDR_LONG) {
-		pr_err("%s: received non-long source address!\n", __func__);
-		return -EINVAL;
-	}
-
-	msg = ieee802154_nl_create(0, IEEE802154_ASSOCIATE_INDIC);
-	if (!msg)
-		return -ENOBUFS;
-
-	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
-	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
-	    nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
-		    dev->dev_addr) ||
-	    nla_put_hwaddr(msg, IEEE802154_ATTR_SRC_HW_ADDR,
-			   addr->extended_addr) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_CAPABILITY, cap))
-		goto nla_put_failure;
-
-	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
-
-nla_put_failure:
-	nlmsg_free(msg);
-	return -ENOBUFS;
-}
-EXPORT_SYMBOL(ieee802154_nl_assoc_indic);
-
-int ieee802154_nl_assoc_confirm(struct net_device *dev, __le16 short_addr,
-				u8 status)
-{
-	struct sk_buff *msg;
-
-	pr_debug("%s\n", __func__);
-
-	msg = ieee802154_nl_create(0, IEEE802154_ASSOCIATE_CONF);
-	if (!msg)
-		return -ENOBUFS;
-
-	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
-	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
-	    nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
-		    dev->dev_addr) ||
-	    nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_STATUS, status))
-		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
-
-nla_put_failure:
-	nlmsg_free(msg);
-	return -ENOBUFS;
-}
-EXPORT_SYMBOL(ieee802154_nl_assoc_confirm);
-
-int ieee802154_nl_disassoc_indic(struct net_device *dev,
-				 struct ieee802154_addr *addr,
-				 u8 reason)
-{
-	struct sk_buff *msg;
-
-	pr_debug("%s\n", __func__);
-
-	msg = ieee802154_nl_create(0, IEEE802154_DISASSOCIATE_INDIC);
-	if (!msg)
-		return -ENOBUFS;
-
-	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
-	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
-	    nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
-		    dev->dev_addr))
-		goto nla_put_failure;
-	if (addr->mode == IEEE802154_ADDR_LONG) {
-		if (nla_put_hwaddr(msg, IEEE802154_ATTR_SRC_HW_ADDR,
-				   addr->extended_addr))
-			goto nla_put_failure;
-	} else {
-		if (nla_put_shortaddr(msg, IEEE802154_ATTR_SRC_SHORT_ADDR,
-				      addr->short_addr))
-			goto nla_put_failure;
-	}
-	if (nla_put_u8(msg, IEEE802154_ATTR_REASON, reason))
-		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
-
-nla_put_failure:
-	nlmsg_free(msg);
-	return -ENOBUFS;
-}
-EXPORT_SYMBOL(ieee802154_nl_disassoc_indic);
-
-int ieee802154_nl_disassoc_confirm(struct net_device *dev, u8 status)
-{
-	struct sk_buff *msg;
-
-	pr_debug("%s\n", __func__);
-
-	msg = ieee802154_nl_create(0, IEEE802154_DISASSOCIATE_CONF);
-	if (!msg)
-		return -ENOBUFS;
-
-	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
-	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
-	    nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
-		    dev->dev_addr) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_STATUS, status))
-		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
-
-nla_put_failure:
-	nlmsg_free(msg);
-	return -ENOBUFS;
-}
-EXPORT_SYMBOL(ieee802154_nl_disassoc_confirm);
-
-int ieee802154_nl_beacon_indic(struct net_device *dev, __le16 panid,
-			       __le16 coord_addr)
-{
-	struct sk_buff *msg;
-
-	pr_debug("%s\n", __func__);
-
-	msg = ieee802154_nl_create(0, IEEE802154_BEACON_NOTIFY_INDIC);
-	if (!msg)
-		return -ENOBUFS;
-
-	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
-	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
-	    nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
-		    dev->dev_addr) ||
-	    nla_put_shortaddr(msg, IEEE802154_ATTR_COORD_SHORT_ADDR,
-			      coord_addr) ||
-	    nla_put_shortaddr(msg, IEEE802154_ATTR_COORD_PAN_ID, panid))
-		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
-
-nla_put_failure:
-	nlmsg_free(msg);
-	return -ENOBUFS;
-}
-EXPORT_SYMBOL(ieee802154_nl_beacon_indic);
-
-int ieee802154_nl_scan_confirm(struct net_device *dev,
-			       u8 status, u8 scan_type,
-			       u32 unscanned, u8 page,
-			       u8 *edl/* , struct list_head *pan_desc_list */)
-{
-	struct sk_buff *msg;
-
-	pr_debug("%s\n", __func__);
-
-	msg = ieee802154_nl_create(0, IEEE802154_SCAN_CONF);
-	if (!msg)
-		return -ENOBUFS;
-
-	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
-	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
-	    nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
-		    dev->dev_addr) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_STATUS, status) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_SCAN_TYPE, scan_type) ||
-	    nla_put_u32(msg, IEEE802154_ATTR_CHANNELS, unscanned) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_PAGE, page) ||
-	    (edl &&
-	     nla_put(msg, IEEE802154_ATTR_ED_LIST, 27, edl)))
-		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
-
-nla_put_failure:
-	nlmsg_free(msg);
-	return -ENOBUFS;
-}
-EXPORT_SYMBOL(ieee802154_nl_scan_confirm);
-
-int ieee802154_nl_start_confirm(struct net_device *dev, u8 status)
+static int ieee802154_nl_start_confirm(struct net_device *dev, u8 status)
 {
 	struct sk_buff *msg;
 
@@ -530,6 +350,11 @@ int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info)
 	ret = ieee802154_mlme_ops(dev)->start_req(dev, &addr, channel, page,
 		bcn_ord, sf_ord, pan_coord, blx, coord_realign);
 
+	/* FIXME: add validation for unused parameters to be sane
+	 * for SoftMAC
+	 */
+	ieee802154_nl_start_confirm(dev, IEEE802154_SUCCESS);
+
 out:
 	dev_put(dev);
 	return ret;
diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c
index 9c2d6f61f19..e1ad83e3589 100644
--- a/net/mac802154/mac_cmd.c
+++ b/net/mac802154/mac_cmd.c
@@ -25,7 +25,6 @@
 #include <net/ieee802154_netdev.h>
 #include <net/cfg802154.h>
 #include <net/mac802154.h>
-#include <net/nl802154.h>
 
 #include "ieee802154_i.h"
 #include "driver-ops.h"
@@ -65,11 +64,6 @@ static int mac802154_mlme_start_req(struct net_device *dev,
 		rc = ops->llsec->set_params(dev, &params, changed);
 	}
 
-	/* FIXME: add validation for unused parameters to be sane
-	 * for SoftMAC
-	 */
-	ieee802154_nl_start_confirm(dev, IEEE802154_SUCCESS);
-
 	return rc;
 }
 
-- 
cgit v1.2.3-70-g09d2


From d5ae67bacd9654b0e26b9f248249e9ee1b6e338b Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 5 Nov 2014 20:51:17 +0100
Subject: ieee802154: rework interface registration

This patch meld mac802154_netdev_register into ieee802154_if_add
function. Also we have now only one alloc_netdev call with one interface
setup routine "ieee802154_if_setup" instead two different one for each
interface type. This patch checks via runtime the interface type and do
different handling now. Additional we add the wpan_dev struct in
ieee802154_sub_if_data and set the new ieee802154_ptr while netdev
registration. This behaviour is very similar the mac80211 netdev
registration functionality.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h      |   4 ++
 net/mac802154/cfg.c          |   8 ++-
 net/mac802154/ieee802154_i.h |   4 ++
 net/mac802154/iface.c        | 158 +++++++++++++++++++++----------------------
 4 files changed, 92 insertions(+), 82 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 29c6de5a426..57333f1ee75 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -65,6 +65,10 @@ struct wpan_phy {
 	char priv[0] __aligned(NETDEV_ALIGN);
 };
 
+struct wpan_dev {
+	struct wpan_phy *wpan_phy;
+};
+
 #define to_phy(_dev)	container_of(_dev, struct wpan_phy, dev)
 
 struct wpan_phy *
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index 0a08f66512b..d2c4e8f8972 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -13,6 +13,7 @@
  * Based on: net/mac80211/cfg.c
  */
 
+#include <net/rtnetlink.h>
 #include <net/cfg802154.h>
 
 #include "ieee802154_i.h"
@@ -23,8 +24,13 @@ ieee802154_add_iface_deprecated(struct wpan_phy *wpan_phy,
 				const char *name, int type)
 {
 	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+	struct net_device *dev;
 
-	return ieee802154_if_add(local, name, NULL, type);
+	rtnl_lock();
+	dev = ieee802154_if_add(local, name, NULL, type);
+	rtnl_unlock();
+
+	return dev;
 }
 
 static void ieee802154_del_iface_deprecated(struct wpan_phy *wpan_phy,
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index 3ad85404fc9..748dc5afe36 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -20,6 +20,7 @@
 #define __IEEE802154_I_H
 
 #include <linux/mutex.h>
+#include <net/cfg802154.h>
 #include <net/mac802154.h>
 #include <net/ieee802154_netdev.h>
 
@@ -73,11 +74,14 @@ enum ieee802154_sdata_state_bits {
 struct ieee802154_sub_if_data {
 	struct list_head list; /* the ieee802154_priv->slaves list */
 
+	struct wpan_dev wpan_dev;
+
 	struct ieee802154_local *local;
 	struct net_device *dev;
 
 	int type;
 	unsigned long state;
+	char name[IFNAMSIZ];
 
 	spinlock_t mib_lock;
 
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index 78cb38124a2..f9ed608aa26 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -381,30 +381,23 @@ static void mac802154_wpan_free(struct net_device *dev)
 	free_netdev(dev);
 }
 
-void mac802154_wpan_setup(struct net_device *dev)
+static void ieee802154_if_setup(struct net_device *dev)
 {
-	struct ieee802154_sub_if_data *sdata;
-
 	dev->addr_len		= IEEE802154_ADDR_LEN;
 	memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN);
 
 	dev->hard_header_len	= MAC802154_FRAME_HARD_HEADER_LEN;
-	dev->header_ops		= &mac802154_header_ops;
 	dev->needed_tailroom	= 2 + 16; /* FCS + MIC */
 	dev->mtu		= IEEE802154_MTU;
 	dev->tx_queue_len	= 300;
-	dev->type		= ARPHRD_IEEE802154;
 	dev->flags		= IFF_NOARP | IFF_BROADCAST;
+}
 
-	dev->destructor		= mac802154_wpan_free;
-	dev->netdev_ops		= &mac802154_wpan_ops;
-	dev->ml_priv		= &mac802154_mlme_wpan;
-
-	sdata = IEEE802154_DEV_TO_SUB_IF(dev);
-	sdata->type = IEEE802154_DEV_WPAN;
-
-	spin_lock_init(&sdata->mib_lock);
-	mutex_init(&sdata->sec_mtx);
+static int
+ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, int type)
+{
+	/* set some type-dependent values */
+	sdata->type = type;
 
 	get_random_bytes(&sdata->bsn, 1);
 	get_random_bytes(&sdata->dsn, 1);
@@ -419,54 +412,28 @@ void mac802154_wpan_setup(struct net_device *dev)
 	sdata->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
 	sdata->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
 
-	sdata->promisuous_mode = false;
-
-	mac802154_llsec_init(&sdata->sec);
-}
-
-void mac802154_monitor_setup(struct net_device *dev)
-{
-	struct ieee802154_sub_if_data *sdata;
-
-	dev->needed_tailroom	= 2; /* room for FCS */
-	dev->mtu		= IEEE802154_MTU;
-	dev->tx_queue_len	= 10;
-	dev->type		= ARPHRD_IEEE802154_MONITOR;
-	dev->flags		= IFF_NOARP | IFF_BROADCAST;
-
-	dev->destructor		= free_netdev;
-	dev->netdev_ops		= &mac802154_monitor_ops;
-	dev->ml_priv		= &mac802154_mlme_reduced;
-
-	sdata = IEEE802154_DEV_TO_SUB_IF(dev);
-	sdata->type = IEEE802154_DEV_MONITOR;
-
-	sdata->promisuous_mode = true;
-}
-
-static int
-mac802154_netdev_register(struct ieee802154_local *local,
-			  struct net_device *dev)
-{
-	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
-	int err;
-
-	sdata->dev = dev;
-	sdata->local = local;
-
-	dev->needed_headroom = local->hw.extra_tx_headroom;
-
-	SET_NETDEV_DEV(dev, &local->phy->dev);
+	switch (type) {
+	case IEEE802154_DEV_WPAN:
+		sdata->dev->header_ops = &mac802154_header_ops;
+		sdata->dev->destructor = mac802154_wpan_free;
+		sdata->dev->netdev_ops = &mac802154_wpan_ops;
+		sdata->dev->ml_priv = &mac802154_mlme_wpan;
+		sdata->promisuous_mode = false;
 
-	err = register_netdev(dev);
-	if (err < 0)
-		return err;
+		spin_lock_init(&sdata->mib_lock);
+		mutex_init(&sdata->sec_mtx);
 
-	rtnl_lock();
-	mutex_lock(&local->iflist_mtx);
-	list_add_tail_rcu(&sdata->list, &local->interfaces);
-	mutex_unlock(&local->iflist_mtx);
-	rtnl_unlock();
+		mac802154_llsec_init(&sdata->sec);
+		break;
+	case IEEE802154_DEV_MONITOR:
+		sdata->dev->destructor = free_netdev;
+		sdata->dev->netdev_ops = &mac802154_monitor_ops;
+		sdata->dev->ml_priv = &mac802154_mlme_reduced;
+		sdata->promisuous_mode = true;
+		break;
+	default:
+		BUG();
+	}
 
 	return 0;
 }
@@ -475,38 +442,67 @@ struct net_device *
 ieee802154_if_add(struct ieee802154_local *local, const char *name,
 		  struct wpan_dev **new_wpan_dev, int type)
 {
-	struct net_device *dev;
-	int err = -ENOMEM;
+	struct net_device *ndev = NULL;
+	struct ieee802154_sub_if_data *sdata = NULL;
+	int ret = -ENOMEM;
+
+	ASSERT_RTNL();
+
+	ndev = alloc_netdev(sizeof(*sdata), name, NET_NAME_UNKNOWN,
+			    ieee802154_if_setup);
+	if (!ndev)
+		return ERR_PTR(-ENOMEM);
+
+	ndev->needed_headroom = local->hw.extra_tx_headroom;
+
+	ret = dev_alloc_name(ndev, ndev->name);
+	if (ret < 0)
+		goto err;
 
 	switch (type) {
-	case IEEE802154_DEV_MONITOR:
-		dev = alloc_netdev(sizeof(struct ieee802154_sub_if_data),
-				   name, NET_NAME_UNKNOWN,
-				   mac802154_monitor_setup);
-		break;
 	case IEEE802154_DEV_WPAN:
-		dev = alloc_netdev(sizeof(struct ieee802154_sub_if_data),
-				   name, NET_NAME_UNKNOWN,
-				   mac802154_wpan_setup);
+		ndev->type = ARPHRD_IEEE802154;
 		break;
-	default:
-		dev = NULL;
-		err = -EINVAL;
+	case IEEE802154_DEV_MONITOR:
+		ndev->type = ARPHRD_IEEE802154_MONITOR;
 		break;
+	default:
+		ret = -EINVAL;
+		goto err;
 	}
-	if (!dev)
+
+	/* TODO check this */
+	SET_NETDEV_DEV(ndev, &local->phy->dev);
+	sdata = netdev_priv(ndev);
+	ndev->ieee802154_ptr = &sdata->wpan_dev;
+	memcpy(sdata->name, ndev->name, IFNAMSIZ);
+	sdata->dev = ndev;
+	sdata->wpan_dev.wpan_phy = local->hw.phy;
+	sdata->local = local;
+
+	/* setup type-dependent data */
+	ret = ieee802154_setup_sdata(sdata, type);
+	if (ret)
 		goto err;
 
-	err = mac802154_netdev_register(local, dev);
-	if (err)
-		goto err_free;
+	if (ndev) {
+		ret = register_netdevice(ndev);
+		if (ret < 0)
+			goto err;
+	}
+
+	mutex_lock(&local->iflist_mtx);
+	list_add_tail_rcu(&sdata->list, &local->interfaces);
+	mutex_unlock(&local->iflist_mtx);
 
-	return dev;
+	if (new_wpan_dev)
+		*new_wpan_dev = &sdata->wpan_dev;
+
+	return ndev;
 
-err_free:
-	free_netdev(dev);
 err:
-	return ERR_PTR(err);
+	free_netdev(ndev);
+	return ERR_PTR(ret);
 }
 
 void ieee802154_if_remove(struct ieee802154_sub_if_data *sdata)
-- 
cgit v1.2.3-70-g09d2


From bd28a11f25f2c2a563620e7be588dc4dd8a91396 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 5 Nov 2014 20:51:18 +0100
Subject: ieee802154: remove mlme get_phy callback

This patch removes the get_phy callback from mlme ops structure. Instead
we doing a dereference via ieee802154_ptr dev pointer. For backwards
compatibility we need to run get_device after dereference wpan_phy via
ieee802154_ptr.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/ieee802154_netdev.h | 12 ------------
 net/ieee802154/6lowpan_rtnl.c   |  8 --------
 net/ieee802154/nl-mac.c         |  6 ++++--
 net/ieee802154/nl-phy.c         |  3 ++-
 net/mac802154/iface.c           |  1 -
 net/mac802154/mac_cmd.c         | 14 --------------
 6 files changed, 6 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h
index 5e62d758eea..83bb8a73d23 100644
--- a/include/net/ieee802154_netdev.h
+++ b/include/net/ieee802154_netdev.h
@@ -423,8 +423,6 @@ struct ieee802154_mlme_ops {
 
 	/* The fields below are required. */
 
-	struct wpan_phy *(*get_phy)(const struct net_device *dev);
-
 	/*
 	 * FIXME: these should become the part of PIB/MIB interface.
 	 * However we still don't have IB interface of any kind
@@ -434,16 +432,6 @@ struct ieee802154_mlme_ops {
 	u8 (*get_dsn)(const struct net_device *dev);
 };
 
-/* The IEEE 802.15.4 standard defines 2 type of the devices:
- * - FFD - full functionality device
- * - RFD - reduce functionality device
- *
- * So 2 sets of mlme operations are needed
- */
-struct ieee802154_reduced_mlme_ops {
-	struct wpan_phy *(*get_phy)(const struct net_device *dev);
-};
-
 static inline struct ieee802154_mlme_ops *
 ieee802154_mlme_ops(const struct net_device *dev)
 {
diff --git a/net/ieee802154/6lowpan_rtnl.c b/net/ieee802154/6lowpan_rtnl.c
index 659f7b25ea1..a96b64c9a73 100644
--- a/net/ieee802154/6lowpan_rtnl.c
+++ b/net/ieee802154/6lowpan_rtnl.c
@@ -407,13 +407,6 @@ static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 }
 
-static struct wpan_phy *lowpan_get_phy(const struct net_device *dev)
-{
-	struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
-
-	return ieee802154_mlme_ops(real_dev)->get_phy(real_dev);
-}
-
 static __le16 lowpan_get_pan_id(const struct net_device *dev)
 {
 	struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
@@ -465,7 +458,6 @@ static const struct net_device_ops lowpan_netdev_ops = {
 
 static struct ieee802154_mlme_ops lowpan_mlme = {
 	.get_pan_id = lowpan_get_pan_id,
-	.get_phy = lowpan_get_phy,
 	.get_short_addr = lowpan_get_short_addr,
 	.get_dsn = lowpan_get_dsn,
 };
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index 91a1855e521..7127b9d1a68 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -94,8 +94,9 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
 		goto out;
 
 	ops = ieee802154_mlme_ops(dev);
-	phy = ops->get_phy(dev);
+	phy = dev->ieee802154_ptr->wpan_phy;
 	BUG_ON(!phy);
+	get_device(&phy->dev);
 
 	short_addr = ops->get_short_addr(dev);
 	pan_id = ops->get_pan_id(dev);
@@ -493,7 +494,8 @@ int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info)
 	    !info->attrs[IEEE802154_ATTR_FRAME_RETRIES])
 		goto out;
 
-	phy = ops->get_phy(dev);
+	phy = dev->ieee802154_ptr->wpan_phy;
+	get_device(&phy->dev);
 
 	ops->get_mac_params(dev, &params);
 
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 397ca126d9a..80a946dddd9 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -287,8 +287,9 @@ int ieee802154_del_iface(struct sk_buff *skb, struct genl_info *info)
 	if (!dev)
 		return -ENODEV;
 
-	phy = ieee802154_mlme_ops(dev)->get_phy(dev);
+	phy = dev->ieee802154_ptr->wpan_phy;
 	BUG_ON(!phy);
+	get_device(&phy->dev);
 
 	rc = -EINVAL;
 	/* phy name is optional, but should be checked if it's given */
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index f9ed608aa26..2e2638e72ae 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -428,7 +428,6 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, int type)
 	case IEEE802154_DEV_MONITOR:
 		sdata->dev->destructor = free_netdev;
 		sdata->dev->netdev_ops = &mac802154_monitor_ops;
-		sdata->dev->ml_priv = &mac802154_mlme_reduced;
 		sdata->promisuous_mode = true;
 		break;
 	default:
diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c
index e1ad83e3589..00b2b214770 100644
--- a/net/mac802154/mac_cmd.c
+++ b/net/mac802154/mac_cmd.c
@@ -67,15 +67,6 @@ static int mac802154_mlme_start_req(struct net_device *dev,
 	return rc;
 }
 
-static struct wpan_phy *mac802154_get_phy(const struct net_device *dev)
-{
-	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
-
-	BUG_ON(dev->type != ARPHRD_IEEE802154);
-
-	return to_phy(get_device(&sdata->local->phy->dev));
-}
-
 static int mac802154_set_mac_params(struct net_device *dev,
 				    const struct ieee802154_mac_params *params)
 {
@@ -134,12 +125,7 @@ static struct ieee802154_llsec_ops mac802154_llsec_ops = {
 	.unlock_table = mac802154_unlock_table,
 };
 
-struct ieee802154_reduced_mlme_ops mac802154_mlme_reduced = {
-	.get_phy = mac802154_get_phy,
-};
-
 struct ieee802154_mlme_ops mac802154_mlme_wpan = {
-	.get_phy = mac802154_get_phy,
 	.start_req = mac802154_mlme_start_req,
 	.get_pan_id = mac802154_dev_get_pan_id,
 	.get_short_addr = mac802154_dev_get_short_addr,
-- 
cgit v1.2.3-70-g09d2


From 7c118c1a866454cf2091fd84404d0915a27b0eef Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 5 Nov 2014 20:51:20 +0100
Subject: mac802154: add ieee802154_vif struct

This patch adds an ieee802154_vif similar like the ieee80211_vif which
holds the interface type and maybe further more attributes like the
ieee80211_vif structure.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Cc: Varka Bhadram <varkabhadram@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/net/ieee802154/at86rf230.c |  1 +
 drivers/net/ieee802154/cc2520.c    |  1 +
 include/net/mac802154.h            |  8 ++++++++
 net/mac802154/ieee802154_i.h       |  3 ++-
 net/mac802154/iface.c              | 11 ++++++-----
 net/mac802154/rx.c                 |  4 ++--
 6 files changed, 20 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index f68ebba91b1..bf477851415 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -1533,6 +1533,7 @@ static int at86rf230_probe(struct spi_device *spi)
 	lp->hw = hw;
 	lp->spi = spi;
 	hw->parent = &spi->dev;
+	hw->vif_data_size = sizeof(*lp);
 
 	lp->regmap = devm_regmap_init_spi(spi, &at86rf230_regmap_spi_config);
 	if (IS_ERR(lp->regmap)) {
diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c
index 340671b747b..ccbb082f339 100644
--- a/drivers/net/ieee802154/cc2520.c
+++ b/drivers/net/ieee802154/cc2520.c
@@ -651,6 +651,7 @@ static int cc2520_register(struct cc2520_private *priv)
 	priv->hw->priv = priv;
 	priv->hw->parent = &priv->spi->dev;
 	priv->hw->extra_tx_headroom = 0;
+	priv->hw->vif_data_size = sizeof(*priv);
 
 	/* We do support only 2.4 Ghz */
 	priv->hw->phy->channels_supported[0] = 0x7FFF800;
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 8b0c26bc076..10711a6409f 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -52,6 +52,13 @@ struct ieee802154_hw_addr_filt {
 	u8	pan_coord;
 };
 
+struct ieee802154_vif {
+	int type;
+
+	/* must be last */
+	u8 drv_priv[0] __aligned(sizeof(void *));
+};
+
 struct ieee802154_hw {
 	/* filled by the driver */
 	int	extra_tx_headroom;
@@ -62,6 +69,7 @@ struct ieee802154_hw {
 	struct	ieee802154_hw_addr_filt hw_filt;
 	void	*priv;
 	struct	wpan_phy *phy;
+	size_t vif_data_size;
 };
 
 /* Checksum is in hardware and is omitted from a packet
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index 748dc5afe36..931f8516cee 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -79,7 +79,6 @@ struct ieee802154_sub_if_data {
 	struct ieee802154_local *local;
 	struct net_device *dev;
 
-	int type;
 	unsigned long state;
 	char name[IFNAMSIZ];
 
@@ -103,6 +102,8 @@ struct ieee802154_sub_if_data {
 	struct mutex sec_mtx;
 
 	struct mac802154_llsec sec;
+	/* must be last, dynamically sized area in this! */
+	struct ieee802154_vif vif;
 };
 
 #define MAC802154_CHAN_NONE		0xff /* No channel is assigned */
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index 2e2638e72ae..764ce496fdc 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -136,10 +136,11 @@ static int mac802154_slave_open(struct net_device *dev)
 
 	ASSERT_RTNL();
 
-	if (sdata->type == IEEE802154_DEV_WPAN) {
+	if (sdata->vif.type == IEEE802154_DEV_WPAN) {
 		mutex_lock(&sdata->local->iflist_mtx);
 		list_for_each_entry(subif, &sdata->local->interfaces, list) {
-			if (subif != sdata && subif->type == sdata->type &&
+			if (subif != sdata &&
+			    subif->vif.type == sdata->vif.type &&
 			    ieee802154_sdata_running(subif)) {
 				mutex_unlock(&sdata->local->iflist_mtx);
 				return -EBUSY;
@@ -397,7 +398,7 @@ static int
 ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, int type)
 {
 	/* set some type-dependent values */
-	sdata->type = type;
+	sdata->vif.type = type;
 
 	get_random_bytes(&sdata->bsn, 1);
 	get_random_bytes(&sdata->dsn, 1);
@@ -447,8 +448,8 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name,
 
 	ASSERT_RTNL();
 
-	ndev = alloc_netdev(sizeof(*sdata), name, NET_NAME_UNKNOWN,
-			    ieee802154_if_setup);
+	ndev = alloc_netdev(sizeof(*sdata) + local->hw.vif_data_size, name,
+			    NET_NAME_UNKNOWN, ieee802154_if_setup);
 	if (!ndev)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index 95961cccc25..4b54cf33e56 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -208,7 +208,7 @@ __ieee802154_rx_handle_packet(struct ieee802154_local *local,
 	}
 
 	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
-		if (sdata->type != IEEE802154_DEV_WPAN ||
+		if (sdata->vif.type != IEEE802154_DEV_WPAN ||
 		    !netif_running(sdata->dev))
 			continue;
 
@@ -233,7 +233,7 @@ ieee802154_monitors_rx(struct ieee802154_local *local, struct sk_buff *skb)
 	skb->protocol = htons(ETH_P_IEEE802154);
 
 	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
-		if (sdata->type != IEEE802154_DEV_MONITOR)
+		if (sdata->vif.type != IEEE802154_DEV_MONITOR)
 			continue;
 
 		if (!ieee802154_sdata_running(sdata))
-- 
cgit v1.2.3-70-g09d2


From 1906bbbddbe085b19be2c21cd132335260f551c3 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 5 Nov 2014 20:51:21 +0100
Subject: ieee802154: add IEEE802154_EXTENDED_ADDR_LEN

This patch adds a new define for getting the length of an extended
address.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/ieee802154.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index 4c032863cd7..a907fe59b1d 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -29,6 +29,8 @@
 #define IEEE802154_MTU			127
 #define IEEE802154_MIN_PSDU_LEN		5
 
+#define IEEE802154_EXTENDED_ADDR_LEN	8
+
 #define IEEE802154_FC_TYPE_BEACON	0x0	/* Frame is beacon */
 #define	IEEE802154_FC_TYPE_DATA		0x1	/* Frame is data */
 #define IEEE802154_FC_TYPE_ACK		0x2	/* Frame is acknowledgment */
-- 
cgit v1.2.3-70-g09d2


From 35d5a374a559a1ba9c6810739cf3ad1d672c2de2 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 5 Nov 2014 20:51:22 +0100
Subject: ieee802154: add ieee802154_random_extended_addr

This patch adds a new function to generate a random IEEE 802.15.4
extended address.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/ieee802154.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index a907fe59b1d..d043449a079 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -24,6 +24,7 @@
 #define LINUX_IEEE802154_H
 
 #include <linux/types.h>
+#include <linux/random.h>
 #include <asm/byteorder.h>
 
 #define IEEE802154_MTU			127
@@ -215,4 +216,17 @@ static inline bool ieee802154_is_valid_extended_addr(const __le64 addr)
 		(addr != cpu_to_le64(0xffffffffffffffffULL)));
 }
 
+/**
+ * ieee802154_random_extended_addr - generates a random extended address
+ * @addr: extended addr pointer to place the random address
+ */
+static inline void ieee802154_random_extended_addr(__le64 *addr)
+{
+	get_random_bytes(addr, IEEE802154_EXTENDED_ADDR_LEN);
+
+	/* toggle some bit if we hit an invalid extended addr */
+	if (!ieee802154_is_valid_extended_addr(*addr))
+		((u8 *)addr)[IEEE802154_EXTENDED_ADDR_LEN - 1] ^= 0x01;
+}
+
 #endif /* LINUX_IEEE802154_H */
-- 
cgit v1.2.3-70-g09d2


From 239a84a9a0bcbc7214eb93fb3ba76962de846239 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 5 Nov 2014 20:51:23 +0100
Subject: mac802154: add ieee802154_le64_to_be64

This patch adds a new function to convert a le64 to a be64. This is
useful to translate an extended address to a netdev dev_addr.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/mac802154.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 10711a6409f..cc188cb4f94 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -17,6 +17,7 @@
 #define NET_MAC802154_H
 
 #include <net/af_ieee802154.h>
+#include <linux/ieee802154.h>
 #include <linux/skbuff.h>
 
 /* General MAC frame format:
@@ -231,6 +232,18 @@ static inline __le64 ieee802154_netdev_to_extended_addr(const void *dev_addr)
 	return (__force __le64)swab64p(dev_addr);
 }
 
+/**
+ * ieee802154_le64_to_be64 - copies and convert le64 to be64
+ * @be64_dst: be64 destination pointer
+ * @le64_src: le64 source pointer
+ */
+static inline void ieee802154_le64_to_be64(void *be64_dst, const void *le64_src)
+{
+	__be64 tmp = (__force __be64)swab64p(le64_src);
+
+	memcpy(be64_dst, &tmp, IEEE802154_EXTENDED_ADDR_LEN);
+}
+
 /* Basic interface to register ieee802154 hwice */
 struct ieee802154_hw *
 ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops);
-- 
cgit v1.2.3-70-g09d2


From 705cbbbe9ccca260658f971a4369c22f5704db75 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 5 Nov 2014 20:51:24 +0100
Subject: mac802154: cleanup ieee802154_netdev_to_extended_addr

This patch cleanups the ieee802154_be64_to_le64 to have a similar
function like ieee802154_le64_to_be64 only with switched source and
destionation types.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/mac802154.h | 11 +++++++----
 net/mac802154/iface.c   |  2 +-
 2 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index cc188cb4f94..632f6566adb 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -224,12 +224,15 @@ struct ieee802154_ops {
 };
 
 /**
- * ieee802154_netdev_to_extended_addr - convert big endian 64 byte void pointer to __le64
- * @dev_addr: big endian address pointer like netdevice dev_addr attribute
+ * ieee802154_be64_to_le64 - copies and convert be64 to le64
+ * @le64_dst: le64 destination pointer
+ * @be64_src: be64 source pointer
  */
-static inline __le64 ieee802154_netdev_to_extended_addr(const void *dev_addr)
+static inline void ieee802154_be64_to_le64(void *le64_dst, const void *be64_src)
 {
-	return (__force __le64)swab64p(dev_addr);
+	__le64 tmp = (__force __le64)swab64p(be64_src);
+
+	memcpy(le64_dst, &tmp, IEEE802154_EXTENDED_ADDR_LEN);
 }
 
 /**
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index 764ce496fdc..a1aa09b03d1 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -117,7 +117,7 @@ static int mac802154_wpan_mac_addr(struct net_device *dev, void *p)
 	if (netif_running(dev))
 		return -EBUSY;
 
-	extended_addr = ieee802154_netdev_to_extended_addr(addr->sa_data);
+	ieee802154_be64_to_le64(&extended_addr, addr->sa_data);
 	if (!ieee802154_is_valid_extended_addr(extended_addr))
 		return -EINVAL;
 
-- 
cgit v1.2.3-70-g09d2


From dee56d14779b1e01706adafb9e020303318e22e3 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 5 Nov 2014 20:51:25 +0100
Subject: mac802154: add support for perm_extended_addr

This patch adding support for a perm extended address. This is useful
when a device supports an eeprom with a programmed static extended address.
If a device doesn't support such eeprom or serial registers then the
driver should generate a random extended address.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h | 2 ++
 net/mac802154/iface.c   | 4 ++++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 57333f1ee75..9d99b965576 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -57,6 +57,8 @@ struct wpan_phy {
 	u8 csma_retries;
 	s8 frame_retries;
 
+	__le64 perm_extended_addr;
+
 	bool lbt;
 	s32 cca_ed_level;
 
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index a1aa09b03d1..97e5bed9f91 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -410,6 +410,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, int type)
 	/* for compatibility, actual default is 3 */
 	sdata->mac_params.frame_retries = -1;
 
+	ieee802154_be64_to_le64(&sdata->extended_addr, sdata->dev->dev_addr);
 	sdata->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
 	sdata->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
 
@@ -471,6 +472,9 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name,
 		goto err;
 	}
 
+	ieee802154_le64_to_be64(ndev->perm_addr,
+				&local->hw.phy->perm_extended_addr);
+	memcpy(ndev->dev_addr, ndev->perm_addr, IEEE802154_EXTENDED_ADDR_LEN);
 	/* TODO check this */
 	SET_NETDEV_DEV(ndev, &local->phy->dev);
 	sdata = netdev_priv(ndev);
-- 
cgit v1.2.3-70-g09d2


From 63487babf08d6d67483c67ed21d8cea6674a44ec Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Tue, 4 Nov 2014 09:06:51 -0800
Subject: net: Move fou_build_header into fou.c and refactor

Move fou_build_header out of ip_tunnel.c and into fou.c splitting
it up into fou_build_header, gue_build_header, and fou_build_udp.
This allows for other users for TX of FOU or GUE. Change ip_tunnel_encap
to call fou_build_header or gue_build_header based on the tunnel
encapsulation type. Similarly, added fou_encap_hlen and gue_encap_hlen
functions which are called by ip_encap_hlen. New net/fou.h has
prototypes and defines for this.

Added NET_FOU_IP_TUNNELS configuration. When this is set, IP tunnels
can use FOU/GUE and fou module is also selected.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/fou.h    | 26 +++++++++++++++++++
 net/ipv4/Kconfig     |  9 +++++++
 net/ipv4/fou.c       | 73 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 net/ipv4/ip_tunnel.c | 61 +++++++++----------------------------------
 4 files changed, 120 insertions(+), 49 deletions(-)
 create mode 100644 include/net/fou.h

(limited to 'include')

diff --git a/include/net/fou.h b/include/net/fou.h
new file mode 100644
index 00000000000..cf4ce8874f9
--- /dev/null
+++ b/include/net/fou.h
@@ -0,0 +1,26 @@
+#ifndef __NET_FOU_H
+#define __NET_FOU_H
+
+#include <linux/skbuff.h>
+
+#include <net/flow.h>
+#include <net/gue.h>
+#include <net/ip_tunnels.h>
+#include <net/udp.h>
+
+int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+		     u8 *protocol, struct flowi4 *fl4);
+int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+		     u8 *protocol, struct flowi4 *fl4);
+
+static size_t fou_encap_hlen(struct ip_tunnel_encap *e)
+{
+	return sizeof(struct udphdr);
+}
+
+static size_t gue_encap_hlen(struct ip_tunnel_encap *e)
+{
+	return sizeof(struct udphdr) + sizeof(struct guehdr);
+}
+
+#endif
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index e682b48e070..bd290160484 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -322,6 +322,15 @@ config NET_FOU
 	  network mechanisms and optimizations for UDP (such as ECMP
 	  and RSS) can be leveraged to provide better service.
 
+config NET_FOU_IP_TUNNELS
+	bool "IP: FOU encapsulation of IP tunnels"
+	depends on NET_IPIP || NET_IPGRE || IPV6_SIT
+	select NET_FOU
+	---help---
+	  Allow configuration of FOU or GUE encapsulation for IP tunnels.
+	  When this option is enabled IP tunnels can be configured to use
+	  FOU or GUE encapsulation.
+
 config GENEVE
 	tristate "Generic Network Virtualization Encapsulation (Geneve)"
 	depends on INET
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 32e78924e24..5446c1c8c26 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -487,6 +487,79 @@ static const struct genl_ops fou_nl_ops[] = {
 	},
 };
 
+static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e,
+			  struct flowi4 *fl4, u8 *protocol, __be16 sport)
+{
+	struct udphdr *uh;
+
+	skb_push(skb, sizeof(struct udphdr));
+	skb_reset_transport_header(skb);
+
+	uh = udp_hdr(skb);
+
+	uh->dest = e->dport;
+	uh->source = sport;
+	uh->len = htons(skb->len);
+	uh->check = 0;
+	udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb,
+		     fl4->saddr, fl4->daddr, skb->len);
+
+	*protocol = IPPROTO_UDP;
+}
+
+int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+		     u8 *protocol, struct flowi4 *fl4)
+{
+	bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM);
+	int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+	__be16 sport;
+
+	skb = iptunnel_handle_offloads(skb, csum, type);
+
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
+					       skb, 0, 0, false);
+	fou_build_udp(skb, e, fl4, protocol, sport);
+
+	return 0;
+}
+EXPORT_SYMBOL(fou_build_header);
+
+int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+		     u8 *protocol, struct flowi4 *fl4)
+{
+	bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM);
+	int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+	struct guehdr *guehdr;
+	size_t hdr_len = sizeof(struct guehdr);
+	__be16 sport;
+
+	skb = iptunnel_handle_offloads(skb, csum, type);
+
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	/* Get source port (based on flow hash) before skb_push */
+	sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
+					       skb, 0, 0, false);
+
+	skb_push(skb, hdr_len);
+
+	guehdr = (struct guehdr *)skb->data;
+
+	guehdr->version = 0;
+	guehdr->hlen = 0;
+	guehdr->flags = 0;
+	guehdr->next_hdr = *protocol;
+
+	fou_build_udp(skb, e, fl4, protocol, sport);
+
+	return 0;
+}
+EXPORT_SYMBOL(gue_build_header);
+
 static int __init fou_init(void)
 {
 	int ret;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 0bb8e141eac..c3587e1c8b8 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -56,7 +56,10 @@
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
 #include <net/udp.h>
-#include <net/gue.h>
+
+#if IS_ENABLED(CONFIG_NET_FOU)
+#include <net/fou.h>
+#endif
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
@@ -494,10 +497,12 @@ static int ip_encap_hlen(struct ip_tunnel_encap *e)
 	switch (e->type) {
 	case TUNNEL_ENCAP_NONE:
 		return 0;
+#if IS_ENABLED(CONFIG_NET_FOU)
 	case TUNNEL_ENCAP_FOU:
-		return sizeof(struct udphdr);
+		return fou_encap_hlen(e);
 	case TUNNEL_ENCAP_GUE:
-		return sizeof(struct udphdr) + sizeof(struct guehdr);
+		return gue_encap_hlen(e);
+#endif
 	default:
 		return -EINVAL;
 	}
@@ -526,60 +531,18 @@ int ip_tunnel_encap_setup(struct ip_tunnel *t,
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_encap_setup);
 
-static int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
-			    size_t hdr_len, u8 *protocol, struct flowi4 *fl4)
-{
-	struct udphdr *uh;
-	__be16 sport;
-	bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM);
-	int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
-
-	skb = iptunnel_handle_offloads(skb, csum, type);
-
-	if (IS_ERR(skb))
-		return PTR_ERR(skb);
-
-	/* Get length and hash before making space in skb */
-
-	sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
-					       skb, 0, 0, false);
-
-	skb_push(skb, hdr_len);
-
-	skb_reset_transport_header(skb);
-	uh = udp_hdr(skb);
-
-	if (e->type == TUNNEL_ENCAP_GUE) {
-		struct guehdr *guehdr = (struct guehdr *)&uh[1];
-
-		guehdr->version = 0;
-		guehdr->hlen = 0;
-		guehdr->flags = 0;
-		guehdr->next_hdr = *protocol;
-	}
-
-	uh->dest = e->dport;
-	uh->source = sport;
-	uh->len = htons(skb->len);
-	uh->check = 0;
-	udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb,
-		     fl4->saddr, fl4->daddr, skb->len);
-
-	*protocol = IPPROTO_UDP;
-
-	return 0;
-}
-
 int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
 		    u8 *protocol, struct flowi4 *fl4)
 {
 	switch (t->encap.type) {
 	case TUNNEL_ENCAP_NONE:
 		return 0;
+#if IS_ENABLED(CONFIG_NET_FOU)
 	case TUNNEL_ENCAP_FOU:
+		return fou_build_header(skb, &t->encap, protocol, fl4);
 	case TUNNEL_ENCAP_GUE:
-		return fou_build_header(skb, &t->encap, t->encap_hlen,
-					protocol, fl4);
+		return gue_build_header(skb, &t->encap, protocol, fl4);
+#endif
 	default:
 		return -EINVAL;
 	}
-- 
cgit v1.2.3-70-g09d2


From 5024c33ac354577635c5671498891eb197f3ec4d Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Tue, 4 Nov 2014 09:06:53 -0800
Subject: gue: Add infrastructure for flags and options

Add functions and basic definitions for processing standard flags,
private flags, and control messages. This includes definitions
to compute length of optional fields corresponding to a set of flags.
Flag validation is in validate_gue_flags function. This checks for
unknown flags, and that length of optional fields is <= length
in guehdr hlen.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gue.h | 100 ++++++++++++++++++++++++++++++++++++--
 net/ipv4/fou.c    | 142 ++++++++++++++++++++++++++++++++++++------------------
 2 files changed, 189 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/include/net/gue.h b/include/net/gue.h
index b6c33278808..cb68ae843c7 100644
--- a/include/net/gue.h
+++ b/include/net/gue.h
@@ -1,23 +1,113 @@
 #ifndef __NET_GUE_H
 #define __NET_GUE_H
 
+/* Definitions for the GUE header, standard and private flags, lengths
+ * of optional fields are below.
+ *
+ * Diagram of GUE header:
+ *
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |Ver|C|  Hlen   | Proto/ctype   |        Standard flags       |P|
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                                                               |
+ * ~                      Fields (optional)                        ~
+ * |                                                               |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |            Private flags (optional, P bit is set)             |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                                                               |
+ * ~                   Private fields (optional)                   ~
+ * |                                                               |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * C bit indicates contol message when set, data message when unset.
+ * For a control message, proto/ctype is interpreted as a type of
+ * control message. For data messages, proto/ctype is the IP protocol
+ * of the next header.
+ *
+ * P bit indicates private flags field is present. The private flags
+ * may refer to options placed after this field.
+ */
+
 struct guehdr {
 	union {
 		struct {
 #if defined(__LITTLE_ENDIAN_BITFIELD)
-			__u8	hlen:4,
-			version:4;
+			__u8	hlen:5,
+				control:1,
+				version:2;
 #elif defined (__BIG_ENDIAN_BITFIELD)
-			__u8	version:4,
-				hlen:4;
+			__u8	version:2,
+				control:1,
+				hlen:5;
 #else
 #error  "Please fix <asm/byteorder.h>"
 #endif
-			__u8    next_hdr;
+			__u8    proto_ctype;
 			__u16   flags;
 		};
 		__u32 word;
 	};
 };
 
+/* Standard flags in GUE header */
+
+#define GUE_FLAG_PRIV	htons(1<<0)	/* Private flags are in options */
+#define GUE_LEN_PRIV	4
+
+#define GUE_FLAGS_ALL	(GUE_FLAG_PRIV)
+
+/* Private flags in the private option extension */
+
+#define GUE_PFLAGS_ALL	(0)
+
+/* Functions to compute options length corresponding to flags.
+ * If we ever have a lot of flags this can be potentially be
+ * converted to a more optimized algorithm (table lookup
+ * for instance).
+ */
+static inline size_t guehdr_flags_len(__be16 flags)
+{
+	return ((flags & GUE_FLAG_PRIV) ? GUE_LEN_PRIV : 0);
+}
+
+static inline size_t guehdr_priv_flags_len(__be32 flags)
+{
+	return 0;
+}
+
+/* Validate standard and private flags. Returns non-zero (meaning invalid)
+ * if there is an unknown standard or private flags, or the options length for
+ * the flags exceeds the options length specific in hlen of the GUE header.
+ */
+static inline int validate_gue_flags(struct guehdr *guehdr,
+				     size_t optlen)
+{
+	size_t len;
+	__be32 flags = guehdr->flags;
+
+	if (flags & ~GUE_FLAGS_ALL)
+		return 1;
+
+	len = guehdr_flags_len(flags);
+	if (len > optlen)
+		return 1;
+
+	if (flags & GUE_FLAG_PRIV) {
+		/* Private flags are last four bytes accounted in
+		 * guehdr_flags_len
+		 */
+		flags = *(__be32 *)((void *)&guehdr[1] + len - GUE_LEN_PRIV);
+
+		if (flags & ~GUE_PFLAGS_ALL)
+			return 1;
+
+		len += guehdr_priv_flags_len(flags);
+		if (len > optlen)
+			return 1;
+	}
+
+	return 0;
+}
+
 #endif
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 5446c1c8c26..a3b8c5b3630 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -38,21 +38,17 @@ static inline struct fou *fou_from_sock(struct sock *sk)
 	return sk->sk_user_data;
 }
 
-static int fou_udp_encap_recv_deliver(struct sk_buff *skb,
-				      u8 protocol, size_t len)
+static void fou_recv_pull(struct sk_buff *skb, size_t len)
 {
 	struct iphdr *iph = ip_hdr(skb);
 
 	/* Remove 'len' bytes from the packet (UDP header and
-	 * FOU header if present), modify the protocol to the one
-	 * we found, and then call rcv_encap.
+	 * FOU header if present).
 	 */
 	iph->tot_len = htons(ntohs(iph->tot_len) - len);
 	__skb_pull(skb, len);
 	skb_postpull_rcsum(skb, udp_hdr(skb), len);
 	skb_reset_transport_header(skb);
-
-	return -protocol;
 }
 
 static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
@@ -62,16 +58,24 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
 	if (!fou)
 		return 1;
 
-	return fou_udp_encap_recv_deliver(skb, fou->protocol,
-					  sizeof(struct udphdr));
+	fou_recv_pull(skb, sizeof(struct udphdr));
+
+	return -fou->protocol;
+}
+
+static int gue_control_message(struct sk_buff *skb, struct guehdr *guehdr)
+{
+	/* No support yet */
+	kfree_skb(skb);
+	return 0;
 }
 
 static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct fou *fou = fou_from_sock(sk);
-	size_t len;
+	size_t len, optlen, hdrlen;
 	struct guehdr *guehdr;
-	struct udphdr *uh;
+	void *data;
 
 	if (!fou)
 		return 1;
@@ -80,25 +84,38 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	if (!pskb_may_pull(skb, len))
 		goto drop;
 
-	uh = udp_hdr(skb);
-	guehdr = (struct guehdr *)&uh[1];
+	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
+
+	optlen = guehdr->hlen << 2;
+	len += optlen;
 
-	len += guehdr->hlen << 2;
 	if (!pskb_may_pull(skb, len))
 		goto drop;
 
-	uh = udp_hdr(skb);
-	guehdr = (struct guehdr *)&uh[1];
+	/* guehdr may change after pull */
+	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
 
-	if (guehdr->version != 0)
-		goto drop;
+	hdrlen = sizeof(struct guehdr) + optlen;
 
-	if (guehdr->flags) {
-		/* No support yet */
+	if (guehdr->version != 0 || validate_gue_flags(guehdr, optlen))
 		goto drop;
+
+	/* Pull UDP and GUE headers */
+	fou_recv_pull(skb, len);
+
+	data = &guehdr[1];
+
+	if (guehdr->flags & GUE_FLAG_PRIV) {
+		data += GUE_LEN_PRIV;
+
+		/* Process private flags */
 	}
 
-	return fou_udp_encap_recv_deliver(skb, guehdr->next_hdr, len);
+	if (unlikely(guehdr->control))
+		return gue_control_message(skb, guehdr);
+
+	return -guehdr->proto_ctype;
+
 drop:
 	kfree_skb(skb);
 	return 0;
@@ -154,36 +171,47 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 	const struct net_offload *ops;
 	struct sk_buff **pp = NULL;
 	struct sk_buff *p;
-	u8 proto;
 	struct guehdr *guehdr;
-	unsigned int hlen, guehlen;
-	unsigned int off;
+	size_t len, optlen, hdrlen, off;
+	void *data;
 	int flush = 1;
 
 	off = skb_gro_offset(skb);
-	hlen = off + sizeof(*guehdr);
+	len = off + sizeof(*guehdr);
+
 	guehdr = skb_gro_header_fast(skb, off);
-	if (skb_gro_header_hard(skb, hlen)) {
-		guehdr = skb_gro_header_slow(skb, hlen, off);
+	if (skb_gro_header_hard(skb, len)) {
+		guehdr = skb_gro_header_slow(skb, len, off);
 		if (unlikely(!guehdr))
 			goto out;
 	}
 
-	proto = guehdr->next_hdr;
+	optlen = guehdr->hlen << 2;
+	len += optlen;
 
-	rcu_read_lock();
-	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
-	ops = rcu_dereference(offloads[proto]);
-	if (WARN_ON(!ops || !ops->callbacks.gro_receive))
-		goto out_unlock;
+	if (skb_gro_header_hard(skb, len)) {
+		guehdr = skb_gro_header_slow(skb, len, off);
+		if (unlikely(!guehdr))
+			goto out;
+	}
 
-	guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);
+	if (unlikely(guehdr->control) || guehdr->version != 0 ||
+	    validate_gue_flags(guehdr, optlen))
+		goto out;
 
-	hlen = off + guehlen;
-	if (skb_gro_header_hard(skb, hlen)) {
-		guehdr = skb_gro_header_slow(skb, hlen, off);
-		if (unlikely(!guehdr))
-			goto out_unlock;
+	hdrlen = sizeof(*guehdr) + optlen;
+
+	skb_gro_pull(skb, hdrlen);
+
+	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
+	skb_gro_postpull_rcsum(skb, guehdr, hdrlen);
+
+	data = &guehdr[1];
+
+	if (guehdr->flags & GUE_FLAG_PRIV) {
+		data += GUE_LEN_PRIV;
+
+		/* Process private flags */
 	}
 
 	flush = 0;
@@ -197,7 +225,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 		guehdr2 = (struct guehdr *)(p->data + off);
 
 		/* Compare base GUE header to be equal (covers
-		 * hlen, version, next_hdr, and flags.
+		 * hlen, version, proto_ctype, and flags.
 		 */
 		if (guehdr->word != guehdr2->word) {
 			NAPI_GRO_CB(p)->same_flow = 0;
@@ -212,10 +240,11 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 		}
 	}
 
-	skb_gro_pull(skb, guehlen);
-
-	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
-	skb_gro_postpull_rcsum(skb, guehdr, guehlen);
+	rcu_read_lock();
+	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
+	ops = rcu_dereference(offloads[guehdr->proto_ctype]);
+	if (WARN_ON(!ops || !ops->callbacks.gro_receive))
+		goto out_unlock;
 
 	pp = ops->callbacks.gro_receive(head, skb);
 
@@ -236,7 +265,7 @@ static int gue_gro_complete(struct sk_buff *skb, int nhoff)
 	u8 proto;
 	int err = -ENOENT;
 
-	proto = guehdr->next_hdr;
+	proto = guehdr->proto_ctype;
 
 	guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);
 
@@ -533,8 +562,12 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 	bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM);
 	int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
 	struct guehdr *guehdr;
-	size_t hdr_len = sizeof(struct guehdr);
+	size_t optlen = 0;
 	__be16 sport;
+	void *data;
+	bool need_priv = false;
+
+	optlen += need_priv ? GUE_LEN_PRIV : 0;
 
 	skb = iptunnel_handle_offloads(skb, csum, type);
 
@@ -545,14 +578,27 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 	sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
 					       skb, 0, 0, false);
 
-	skb_push(skb, hdr_len);
+	skb_push(skb, sizeof(struct guehdr) + optlen);
 
 	guehdr = (struct guehdr *)skb->data;
 
+	guehdr->control = 0;
 	guehdr->version = 0;
-	guehdr->hlen = 0;
+	guehdr->hlen = optlen >> 2;
 	guehdr->flags = 0;
-	guehdr->next_hdr = *protocol;
+	guehdr->proto_ctype = *protocol;
+
+	data = &guehdr[1];
+
+	if (need_priv) {
+		__be32 *flags = data;
+
+		guehdr->flags |= GUE_FLAG_PRIV;
+		*flags = 0;
+		data += GUE_LEN_PRIV;
+
+		/* Add private flags */
+	}
 
 	fou_build_udp(skb, e, fl4, protocol, sport);
 
-- 
cgit v1.2.3-70-g09d2


From e585f23636370320bc2071ca5ba2744ae37c3e51 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Tue, 4 Nov 2014 09:06:54 -0800
Subject: udp: Changes to udp_offload to support remote checksum offload

Add a new GSO type, SKB_GSO_TUNNEL_REMCSUM, which indicates remote
checksum offload being done (in this case inner checksum must not
be offloaded to the NIC).

Added logic in __skb_udp_tunnel_segment to handle remote checksum
offload case.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdev_features.h |  4 +++-
 include/linux/netdevice.h       |  1 +
 include/linux/skbuff.h          |  4 +++-
 net/core/skbuff.c               |  4 ++--
 net/ipv4/af_inet.c              |  1 +
 net/ipv4/tcp_offload.c          |  1 +
 net/ipv4/udp_offload.c          | 18 ++++++++++++++++--
 net/ipv6/ip6_offload.c          |  1 +
 net/ipv6/udp_offload.c          |  1 +
 9 files changed, 29 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index dcfdecbfa0b..8c94b07e654 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -48,8 +48,9 @@ enum {
 	NETIF_F_GSO_UDP_TUNNEL_BIT,	/* ... UDP TUNNEL with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT,/* ... UDP TUNNEL with TSO & CSUM */
 	NETIF_F_GSO_MPLS_BIT,		/* ... MPLS segmentation */
+	NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
-		NETIF_F_GSO_MPLS_BIT,
+		NETIF_F_GSO_TUNNEL_REMCSUM_BIT,
 
 	NETIF_F_FCOE_CRC_BIT,		/* FCoE CRC32 */
 	NETIF_F_SCTP_CSUM_BIT,		/* SCTP checksum offload */
@@ -119,6 +120,7 @@ enum {
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
 #define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM)
 #define NETIF_F_GSO_MPLS	__NETIF_F(GSO_MPLS)
+#define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
 #define NETIF_F_HW_VLAN_STAG_TX	__NETIF_F(HW_VLAN_STAG_TX)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5ed05bd764d..4767f546d7c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3584,6 +3584,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_MPLS    != (NETIF_F_GSO_MPLS >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5ad9675b6fe..74ed3441396 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -373,6 +373,7 @@ enum {
 
 	SKB_GSO_MPLS = 1 << 12,
 
+	SKB_GSO_TUNNEL_REMCSUM = 1 << 13,
 };
 
 #if BITS_PER_LONG > 32
@@ -603,7 +604,8 @@ struct sk_buff {
 #endif
 	__u8			ipvs_property:1;
 	__u8			inner_protocol_type:1;
-	/* 4 or 6 bit hole */
+	__u8			remcsum_offload:1;
+	/* 3 or 5 bit hole */
 
 #ifdef CONFIG_NET_SCHED
 	__u16			tc_index;	/* traffic control index */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e48e5c02e87..700189604f3 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3013,7 +3013,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 		if (nskb->len == len + doffset)
 			goto perform_csum_check;
 
-		if (!sg) {
+		if (!sg && !nskb->remcsum_offload) {
 			nskb->ip_summed = CHECKSUM_NONE;
 			nskb->csum = skb_copy_and_csum_bits(head_skb, offset,
 							    skb_put(nskb, len),
@@ -3085,7 +3085,7 @@ skip_fraglist:
 		nskb->truesize += nskb->data_len;
 
 perform_csum_check:
-		if (!csum) {
+		if (!csum && !nskb->remcsum_offload) {
 			nskb->csum = skb_checksum(nskb, doffset,
 						  nskb->len - doffset, 0);
 			nskb->ip_summed = CHECKSUM_NONE;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8b7fe5b0390..ed2c672c5b0 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1222,6 +1222,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_TCPV6 |
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_UDP_TUNNEL_CSUM |
+		       SKB_GSO_TUNNEL_REMCSUM |
 		       SKB_GSO_MPLS |
 		       0)))
 		goto out;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 5b90f2f447a..a1b2a5624f9 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -97,6 +97,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			       SKB_GSO_MPLS |
 			       SKB_GSO_UDP_TUNNEL |
 			       SKB_GSO_UDP_TUNNEL_CSUM |
+			       SKB_GSO_TUNNEL_REMCSUM |
 			       0) ||
 			     !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
 			goto out;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index a774711a88b..0a5a70d0e84 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -41,7 +41,8 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	unsigned int oldlen;
 	bool need_csum = !!(skb_shinfo(skb)->gso_type &
 			    SKB_GSO_UDP_TUNNEL_CSUM);
-	bool offload_csum = false, dont_encap = need_csum;
+	bool remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM);
+	bool offload_csum = false, dont_encap = (need_csum || remcsum);
 
 	oldlen = (u16)~skb->len;
 
@@ -55,6 +56,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	skb->mac_len = skb_inner_network_offset(skb);
 	skb->protocol = new_protocol;
 	skb->encap_hdr_csum = need_csum;
+	skb->remcsum_offload = remcsum;
 
 	/* Try to offload checksum if possible */
 	offload_csum = !!(need_csum &&
@@ -108,11 +110,22 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 		uh->check = ~csum_fold((__force __wsum)
 				       ((__force u32)uh->check +
 					(__force u32)delta));
-
 		if (offload_csum) {
 			skb->ip_summed = CHECKSUM_PARTIAL;
 			skb->csum_start = skb_transport_header(skb) - skb->head;
 			skb->csum_offset = offsetof(struct udphdr, check);
+		} else if (remcsum) {
+			/* Need to calculate checksum from scratch,
+			 * inner checksums are never when doing
+			 * remote_checksum_offload.
+			 */
+
+			skb->csum = skb_checksum(skb, udp_offset,
+						 skb->len - udp_offset,
+						 0);
+			uh->check = csum_fold(skb->csum);
+			if (uh->check == 0)
+				uh->check = CSUM_MANGLED_0;
 		} else {
 			uh->check = gso_make_checksum(skb, ~uh->check);
 
@@ -192,6 +205,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 		if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
 				      SKB_GSO_UDP_TUNNEL |
 				      SKB_GSO_UDP_TUNNEL_CSUM |
+				      SKB_GSO_TUNNEL_REMCSUM |
 				      SKB_GSO_IPIP |
 				      SKB_GSO_GRE | SKB_GSO_GRE_CSUM |
 				      SKB_GSO_MPLS) ||
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index a071563a7e6..e9767079a36 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -78,6 +78,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_SIT |
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_UDP_TUNNEL_CSUM |
+		       SKB_GSO_TUNNEL_REMCSUM |
 		       SKB_GSO_MPLS |
 		       SKB_GSO_TCPV6 |
 		       0)))
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 6b8f543f6ac..637ba2e438b 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -42,6 +42,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 				      SKB_GSO_DODGY |
 				      SKB_GSO_UDP_TUNNEL |
 				      SKB_GSO_UDP_TUNNEL_CSUM |
+				      SKB_GSO_TUNNEL_REMCSUM |
 				      SKB_GSO_GRE |
 				      SKB_GSO_GRE_CSUM |
 				      SKB_GSO_IPIP |
-- 
cgit v1.2.3-70-g09d2


From c1aa8347e73e4092411fbd96cc59531fb7e76d04 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Tue, 4 Nov 2014 09:06:55 -0800
Subject: gue: Protocol constants for remote checksum offload

Define a private flag for remote checksun offload as well as a length
for the option.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gue.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/gue.h b/include/net/gue.h
index cb68ae843c7..3f28ec7f1c7 100644
--- a/include/net/gue.h
+++ b/include/net/gue.h
@@ -59,7 +59,10 @@ struct guehdr {
 
 /* Private flags in the private option extension */
 
-#define GUE_PFLAGS_ALL	(0)
+#define GUE_PFLAG_REMCSUM	htonl(1 << 31)
+#define GUE_PLEN_REMCSUM	4
+
+#define GUE_PFLAGS_ALL	(GUE_PFLAG_REMCSUM)
 
 /* Functions to compute options length corresponding to flags.
  * If we ever have a lot of flags this can be potentially be
-- 
cgit v1.2.3-70-g09d2


From b17f709a24013fcbb257f6f89b4d81ac9fdf0d18 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Tue, 4 Nov 2014 09:06:56 -0800
Subject: gue: TX support for using remote checksum offload option

Add if_tunnel flag TUNNEL_ENCAP_FLAG_REMCSUM to configure
remote checksum offload on an IP tunnel. Add logic in gue_build_header
to insert remote checksum offload option.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/fou.h              | 14 +++++++++++++-
 include/uapi/linux/if_tunnel.h |  1 +
 net/ipv4/fou.c                 | 35 ++++++++++++++++++++++++++++++++---
 3 files changed, 46 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/fou.h b/include/net/fou.h
index cf4ce8874f9..25b26ffcf1d 100644
--- a/include/net/fou.h
+++ b/include/net/fou.h
@@ -20,7 +20,19 @@ static size_t fou_encap_hlen(struct ip_tunnel_encap *e)
 
 static size_t gue_encap_hlen(struct ip_tunnel_encap *e)
 {
-	return sizeof(struct udphdr) + sizeof(struct guehdr);
+	size_t len;
+	bool need_priv = false;
+
+	len = sizeof(struct udphdr) + sizeof(struct guehdr);
+
+	if (e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) {
+		len += GUE_PLEN_REMCSUM;
+		need_priv = true;
+	}
+
+	len += need_priv ? GUE_LEN_PRIV : 0;
+
+	return len;
 }
 
 #endif
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 280d9e09228..bd3cc11a431 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -69,6 +69,7 @@ enum tunnel_encap_types {
 
 #define TUNNEL_ENCAP_FLAG_CSUM		(1<<0)
 #define TUNNEL_ENCAP_FLAG_CSUM6		(1<<1)
+#define TUNNEL_ENCAP_FLAG_REMCSUM	(1<<2)
 
 /* SIT-mode i_flags */
 #define	SIT_ISATAP	0x0001
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index a3b8c5b3630..fb0db99adf9 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -562,11 +562,19 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 	bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM);
 	int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
 	struct guehdr *guehdr;
-	size_t optlen = 0;
+	size_t hdrlen, optlen = 0;
 	__be16 sport;
 	void *data;
 	bool need_priv = false;
 
+	if ((e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) &&
+	    skb->ip_summed == CHECKSUM_PARTIAL) {
+		csum = false;
+		optlen += GUE_PLEN_REMCSUM;
+		type |= SKB_GSO_TUNNEL_REMCSUM;
+		need_priv = true;
+	}
+
 	optlen += need_priv ? GUE_LEN_PRIV : 0;
 
 	skb = iptunnel_handle_offloads(skb, csum, type);
@@ -578,7 +586,9 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 	sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
 					       skb, 0, 0, false);
 
-	skb_push(skb, sizeof(struct guehdr) + optlen);
+	hdrlen = sizeof(struct guehdr) + optlen;
+
+	skb_push(skb, hdrlen);
 
 	guehdr = (struct guehdr *)skb->data;
 
@@ -597,7 +607,26 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 		*flags = 0;
 		data += GUE_LEN_PRIV;
 
-		/* Add private flags */
+		if (type & SKB_GSO_TUNNEL_REMCSUM) {
+			u16 csum_start = skb_checksum_start_offset(skb);
+			__be16 *pd = data;
+
+			if (csum_start < hdrlen)
+				return -EINVAL;
+
+			csum_start -= hdrlen;
+			pd[0] = htons(csum_start);
+			pd[1] = htons(csum_start + skb->csum_offset);
+
+			if (!skb_is_gso(skb)) {
+				skb->ip_summed = CHECKSUM_NONE;
+				skb->encapsulation = 0;
+			}
+
+			*flags |= GUE_PFLAG_REMCSUM;
+			data += GUE_PLEN_REMCSUM;
+		}
+
 	}
 
 	fou_build_udp(skb, e, fl4, protocol, sport);
-- 
cgit v1.2.3-70-g09d2


From 51f3d02b980a338cd291d2bc7629cdfb2568424b Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 5 Nov 2014 16:46:40 -0500
Subject: net: Add and use skb_copy_datagram_msg() helper.

This encapsulates all of the skb_copy_datagram_iovec() callers
with call argument signature "skb, offset, msghdr->msg_iov, length".

When we move to iov_iters in the networking, the iov_iter object will
sit in the msghdr.

Having a helper like this means there will be less places to touch
during that transformation.

Based upon descriptions and patch from Al Viro.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/mISDN/socket.c    | 2 +-
 drivers/net/ppp/pppoe.c        | 2 +-
 include/linux/skbuff.h         | 6 ++++++
 net/appletalk/ddp.c            | 2 +-
 net/atm/common.c               | 2 +-
 net/ax25/af_ax25.c             | 2 +-
 net/bluetooth/af_bluetooth.c   | 4 ++--
 net/bluetooth/hci_sock.c       | 2 +-
 net/caif/caif_socket.c         | 2 +-
 net/core/sock.c                | 2 +-
 net/dccp/proto.c               | 2 +-
 net/ieee802154/dgram.c         | 2 +-
 net/ieee802154/raw.c           | 2 +-
 net/ipv4/ip_sockglue.c         | 2 +-
 net/ipv4/ping.c                | 2 +-
 net/ipv4/raw.c                 | 2 +-
 net/ipv4/tcp.c                 | 5 ++---
 net/ipv4/udp.c                 | 4 ++--
 net/ipv6/datagram.c            | 4 ++--
 net/ipv6/raw.c                 | 4 ++--
 net/ipv6/udp.c                 | 4 ++--
 net/ipx/af_ipx.c               | 3 +--
 net/irda/af_irda.c             | 2 +-
 net/iucv/af_iucv.c             | 2 +-
 net/key/af_key.c               | 2 +-
 net/l2tp/l2tp_ip.c             | 2 +-
 net/l2tp/l2tp_ip6.c            | 2 +-
 net/l2tp/l2tp_ppp.c            | 2 +-
 net/llc/af_llc.c               | 3 +--
 net/netlink/af_netlink.c       | 2 +-
 net/netrom/af_netrom.c         | 2 +-
 net/nfc/llcp_sock.c            | 2 +-
 net/nfc/rawsock.c              | 2 +-
 net/packet/af_packet.c         | 2 +-
 net/phonet/datagram.c          | 2 +-
 net/phonet/pep.c               | 2 +-
 net/rose/af_rose.c             | 2 +-
 net/rxrpc/ar-recvmsg.c         | 2 +-
 net/sctp/socket.c              | 2 +-
 net/tipc/socket.c              | 7 +++----
 net/unix/af_unix.c             | 6 +++---
 net/vmw_vsock/vmci_transport.c | 3 +--
 net/x25/af_x25.c               | 2 +-
 43 files changed, 58 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index 1be82284cf9..dcbd8589f0c 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -163,7 +163,7 @@ mISDN_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	memcpy(skb_push(skb, MISDN_HEADER_LEN), mISDN_HEAD_P(skb),
 	       MISDN_HEADER_LEN);
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 
 	mISDN_sock_cmsg(sk, msg, skb);
 
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 6c9c16d7693..443cbbf5c55 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -981,7 +981,7 @@ static int pppoe_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	if (skb) {
 		total_len = min_t(size_t, total_len, skb->len);
-		error = skb_copy_datagram_iovec(skb, 0, m->msg_iov, total_len);
+		error = skb_copy_datagram_msg(skb, 0, m, total_len);
 		if (error == 0) {
 			consume_skb(skb);
 			return total_len;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 74ed3441396..39ec7530ae2 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -21,6 +21,7 @@
 #include <linux/bug.h>
 #include <linux/cache.h>
 #include <linux/rbtree.h>
+#include <linux/socket.h>
 
 #include <linux/atomic.h>
 #include <asm/types.h>
@@ -2639,6 +2640,11 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
 			   struct poll_table_struct *wait);
 int skb_copy_datagram_iovec(const struct sk_buff *from, int offset,
 			    struct iovec *to, int size);
+static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
+					struct msghdr *msg, int size)
+{
+	return skb_copy_datagram_iovec(from, offset, msg->msg_iov, size);
+}
 int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, int hlen,
 				     struct iovec *iov);
 int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index c00897f65a3..425942db17f 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1758,7 +1758,7 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 		copied = size;
 		msg->msg_flags |= MSG_TRUNC;
 	}
-	err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, offset, msg, copied);
 
 	if (!err && msg->msg_name) {
 		DECLARE_SOCKADDR(struct sockaddr_at *, sat, msg->msg_name);
diff --git a/net/atm/common.c b/net/atm/common.c
index 6a765156a3f..9cd1ccae9a1 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -554,7 +554,7 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	error = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	error = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (error)
 		return error;
 	sock_recv_ts_and_drops(msg, sk, skb);
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index c35c3f48fc0..f4f835e1937 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1634,7 +1634,7 @@ static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock,
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	skb_copy_datagram_msg(skb, 0, msg, copied);
 
 	if (msg->msg_name) {
 		ax25_digi digi;
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 339c74ad455..0a7cc565f93 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -237,7 +237,7 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	}
 
 	skb_reset_transport_header(skb);
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err == 0) {
 		sock_recv_ts_and_drops(msg, sk, skb);
 
@@ -328,7 +328,7 @@ int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		}
 
 		chunk = min_t(unsigned int, skb->len, size);
-		if (skb_copy_datagram_iovec(skb, 0, msg->msg_iov, chunk)) {
+		if (skb_copy_datagram_msg(skb, 0, msg, chunk)) {
 			skb_queue_head(&sk->sk_receive_queue, skb);
 			if (!copied)
 				copied = -EFAULT;
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 115f149362b..29e1ec7189b 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -878,7 +878,7 @@ static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	}
 
 	skb_reset_transport_header(skb);
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 
 	switch (hci_pi(sk)->channel) {
 	case HCI_CHANNEL_RAW:
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 43f750e88e1..fbcd156099f 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -293,7 +293,7 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock,
 		copylen = len;
 	}
 
-	ret = skb_copy_datagram_iovec(skb, 0, m->msg_iov, copylen);
+	ret = skb_copy_datagram_msg(skb, 0, m, copylen);
 	if (ret)
 		goto out_free;
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 15e0c67b106..ac56dd06c30 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2457,7 +2457,7 @@ int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
 		msg->msg_flags |= MSG_TRUNC;
 		copied = len;
 	}
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free_skb;
 
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 5ab6627cf37..8e6ae9422a7 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -896,7 +896,7 @@ verify_sock_status:
 		else if (len < skb->len)
 			msg->msg_flags |= MSG_TRUNC;
 
-		if (skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len)) {
+		if (skb_copy_datagram_msg(skb, 0, msg, len)) {
 			/* Exception. Bailout! */
 			len = -EFAULT;
 			break;
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
index ef2ad8aaef1..fc9193eabd4 100644
--- a/net/ieee802154/dgram.c
+++ b/net/ieee802154/dgram.c
@@ -324,7 +324,7 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk,
 	}
 
 	/* FIXME: skip headers if necessary ?! */
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto done;
 
diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c
index 9d1f64806f0..73a4d53463d 100644
--- a/net/ieee802154/raw.c
+++ b/net/ieee802154/raw.c
@@ -195,7 +195,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		copied = len;
 	}
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto done;
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index c373a9ad455..21894df6626 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -424,7 +424,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 		msg->msg_flags |= MSG_TRUNC;
 		copied = len;
 	}
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free_skb;
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 57f7c980413..736236c3e55 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -875,7 +875,7 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	}
 
 	/* Don't bother checking the checksum */
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto done;
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 739db3100c2..ee8fa4bf3b7 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -718,7 +718,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		copied = len;
 	}
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto done;
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 39ec0c37954..c239f4740d1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1377,7 +1377,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
 	/* XXX -- need to support SO_PEEK_OFF */
 
 	skb_queue_walk(&sk->sk_write_queue, skb) {
-		err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, skb->len);
+		err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
 		if (err)
 			break;
 
@@ -1833,8 +1833,7 @@ do_prequeue:
 		}
 
 		if (!(flags & MSG_TRUNC)) {
-			err = skb_copy_datagram_iovec(skb, offset,
-						      msg->msg_iov, used);
+			err = skb_copy_datagram_msg(skb, offset, msg, used);
 			if (err) {
 				/* Exception. Bailout! */
 				if (!copied)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 3f001db7235..df19027f44f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1281,8 +1281,8 @@ try_again:
 	}
 
 	if (skb_csum_unnecessary(skb))
-		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
-					      msg->msg_iov, copied);
+		err = skb_copy_datagram_msg(skb, sizeof(struct udphdr),
+					    msg, copied);
 	else {
 		err = skb_copy_and_csum_datagram_iovec(skb,
 						       sizeof(struct udphdr),
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 2cdc38338be..5c6996e44b1 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -351,7 +351,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 		msg->msg_flags |= MSG_TRUNC;
 		copied = len;
 	}
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free_skb;
 
@@ -445,7 +445,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
 		msg->msg_flags |= MSG_TRUNC;
 		copied = len;
 	}
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free_skb;
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 075a0fb400e..0cbcf98f2ca 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -486,11 +486,11 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	}
 
 	if (skb_csum_unnecessary(skb)) {
-		err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+		err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	} else if (msg->msg_flags&MSG_TRUNC) {
 		if (__skb_checksum_complete(skb))
 			goto csum_copy_err;
-		err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+		err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	} else {
 		err = skb_copy_and_csum_datagram_iovec(skb, 0, msg->msg_iov);
 		if (err == -EINVAL)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index f6ba535b6fe..9b6809232b1 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -424,8 +424,8 @@ try_again:
 	}
 
 	if (skb_csum_unnecessary(skb))
-		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
-					      msg->msg_iov, copied);
+		err = skb_copy_datagram_msg(skb, sizeof(struct udphdr),
+					    msg, copied);
 	else {
 		err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov);
 		if (err == -EINVAL)
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 313ef464406..a0c75366c93 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1805,8 +1805,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	rc = skb_copy_datagram_iovec(skb, sizeof(struct ipxhdr), msg->msg_iov,
-				     copied);
+	rc = skb_copy_datagram_msg(skb, sizeof(struct ipxhdr), msg, copied);
 	if (rc)
 		goto out_free;
 	if (skb->tstamp.tv64)
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 92fafd485de..980bc2670a1 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1396,7 +1396,7 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock,
 		copied = size;
 		msg->msg_flags |= MSG_TRUNC;
 	}
-	skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	skb_copy_datagram_msg(skb, 0, msg, copied);
 
 	skb_free_datagram(sk, skb);
 
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index a089b6b9165..057b5647ef9 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1355,7 +1355,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 		sk->sk_shutdown = sk->sk_shutdown | RCV_SHUTDOWN;
 
 	cskb = skb;
-	if (skb_copy_datagram_iovec(cskb, offset, msg->msg_iov, copied)) {
+	if (skb_copy_datagram_msg(cskb, offset, msg, copied)) {
 		if (!(flags & MSG_PEEK))
 			skb_queue_head(&sk->sk_receive_queue, skb);
 		return -EFAULT;
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 1847ec4e393..e5883091a8c 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3654,7 +3654,7 @@ static int pfkey_recvmsg(struct kiocb *kiocb,
 	}
 
 	skb_reset_transport_header(skb);
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free;
 
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 369a9822488..a6cc1fed2b5 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -528,7 +528,7 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 		copied = len;
 	}
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto done;
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 0edb263cc00..2177b960da8 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -672,7 +672,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk,
 		copied = len;
 	}
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto done;
 
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index b704a935620..c559bcdf467 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -208,7 +208,7 @@ static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock,
 	else if (len < skb->len)
 		msg->msg_flags |= MSG_TRUNC;
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len);
+	err = skb_copy_datagram_msg(skb, 0, msg, len);
 	if (likely(err == 0))
 		err = len;
 
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index bb9cbc17d92..af662669f95 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -819,8 +819,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 			used = len;
 
 		if (!(flags & MSG_TRUNC)) {
-			int rc = skb_copy_datagram_iovec(skb, offset,
-							 msg->msg_iov, used);
+			int rc = skb_copy_datagram_msg(skb, offset, msg, used);
 			if (rc) {
 				/* Exception. Bailout! */
 				if (!copied)
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index f1de72de273..580b79452be 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2401,7 +2401,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	}
 
 	skb_reset_transport_header(data_skb);
-	err = skb_copy_datagram_iovec(data_skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(data_skb, 0, msg, copied);
 
 	if (msg->msg_name) {
 		DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 1b06a1fcf3e..7e13f6afcd1 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1167,7 +1167,7 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock,
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	er = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	er = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (er < 0) {
 		skb_free_datagram(sk, skb);
 		release_sock(sk);
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 51f077a92fa..83bc785d585 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -832,7 +832,7 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	copied = min_t(unsigned int, rlen, len);
 
 	cskb = skb;
-	if (skb_copy_datagram_iovec(cskb, 0, msg->msg_iov, copied)) {
+	if (skb_copy_datagram_msg(cskb, 0, msg, copied)) {
 		if (!(flags & MSG_PEEK))
 			skb_queue_head(&sk->sk_receive_queue, skb);
 		return -EFAULT;
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index 11c3544ea54..9d7d2b7ba5e 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -269,7 +269,7 @@ static int rawsock_recvmsg(struct kiocb *iocb, struct socket *sock,
 		copied = len;
 	}
 
-	rc = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	rc = skb_copy_datagram_msg(skb, 0, msg, copied);
 
 	skb_free_datagram(sk, skb);
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 87d20f48ff0..4cd13d8de44 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2953,7 +2953,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free;
 
diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c
index 290352c0e6b..0918bc21eae 100644
--- a/net/phonet/datagram.c
+++ b/net/phonet/datagram.c
@@ -150,7 +150,7 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk,
 		copylen = len;
 	}
 
-	rval = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copylen);
+	rval = skb_copy_datagram_msg(skb, 0, msg, copylen);
 	if (rval) {
 		rval = -EFAULT;
 		goto out;
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 70a547ea517..44b2123e22b 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -1296,7 +1296,7 @@ copy:
 	else
 		len = skb->len;
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len);
+	err = skb_copy_datagram_msg(skb, 0, msg, len);
 	if (!err)
 		err = (flags & MSG_TRUNC) ? skb->len : len;
 
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index a85c1a086ae..9b600c20a7a 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1249,7 +1249,7 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	skb_copy_datagram_msg(skb, 0, msg, copied);
 
 	if (msg->msg_name) {
 		struct sockaddr_rose *srose;
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index e9aaa65c077..4575485ad1b 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -180,7 +180,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
 		if (copy > len - copied)
 			copy = len - copied;
 
-		ret = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copy);
+		ret = skb_copy_datagram_msg(skb, offset, msg, copy);
 
 		if (ret < 0)
 			goto copy_error;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 634a2abb5f3..2120292c842 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2095,7 +2095,7 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk,
 	if (copied > len)
 		copied = len;
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 
 	event = sctp_skb2event(skb);
 
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index ad8a1a1e227..591bbfa082a 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1372,8 +1372,7 @@ restart:
 			sz = buf_len;
 			m->msg_flags |= MSG_TRUNC;
 		}
-		res = skb_copy_datagram_iovec(buf, msg_hdr_sz(msg),
-					      m->msg_iov, sz);
+		res = skb_copy_datagram_msg(buf, msg_hdr_sz(msg), m, sz);
 		if (res)
 			goto exit;
 		res = sz;
@@ -1473,8 +1472,8 @@ restart:
 		needed = (buf_len - sz_copied);
 		sz_to_copy = (sz <= needed) ? sz : needed;
 
-		res = skb_copy_datagram_iovec(buf, msg_hdr_sz(msg) + offset,
-					      m->msg_iov, sz_to_copy);
+		res = skb_copy_datagram_msg(buf, msg_hdr_sz(msg) + offset,
+					    m, sz_to_copy);
 		if (res)
 			goto exit;
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e9688438073..5eee625d113 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1825,7 +1825,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 	else if (size < skb->len - skip)
 		msg->msg_flags |= MSG_TRUNC;
 
-	err = skb_copy_datagram_iovec(skb, skip, msg->msg_iov, size);
+	err = skb_copy_datagram_msg(skb, skip, msg, size);
 	if (err)
 		goto out_free;
 
@@ -2030,8 +2030,8 @@ again:
 		}
 
 		chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size);
-		if (skb_copy_datagram_iovec(skb, UNIXCB(skb).consumed + skip,
-					    msg->msg_iov, chunk)) {
+		if (skb_copy_datagram_msg(skb, UNIXCB(skb).consumed + skip,
+					  msg, chunk)) {
 			if (copied == 0)
 				copied = -EFAULT;
 			break;
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 9bb63ffec4f..a57ddef7d5a 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1773,8 +1773,7 @@ static int vmci_transport_dgram_dequeue(struct kiocb *kiocb,
 	}
 
 	/* Place the datagram payload in the user's iovec. */
-	err = skb_copy_datagram_iovec(skb, sizeof(*dg), msg->msg_iov,
-		payload_len);
+	err = skb_copy_datagram_msg(skb, sizeof(*dg), msg, payload_len);
 	if (err)
 		goto out;
 
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 5ad4418ef09..59e785bfde6 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1335,7 +1335,7 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock,
 	/* Currently, each datagram always contains a complete record */
 	msg->msg_flags |= MSG_EOR;
 
-	rc = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	rc = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (rc)
 		goto out_free_dgram;
 
-- 
cgit v1.2.3-70-g09d2


From 25de4668d094f00e44a8f2428dd3c1a4ecfa0053 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 4 Nov 2014 10:59:47 -0800
Subject: ipv6: move INET6_MATCH() to include/net/inet6_hashtables.h

It is only used in net/ipv6/inet6_hashtables.c.

Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h           | 10 ----------
 include/net/inet6_hashtables.h | 10 ++++++++++
 2 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 7121a2e97ce..c694e7baa62 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -317,14 +317,4 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 #define tcp_twsk_ipv6only(__sk)		0
 #define inet_v6_ipv6only(__sk)		0
 #endif /* IS_ENABLED(CONFIG_IPV6) */
-
-#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif)	\
-	(((__sk)->sk_portpair == (__ports))			&&	\
-	 ((__sk)->sk_family == AF_INET6)			&&	\
-	 ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr))		&&	\
-	 ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr))	&&	\
-	 (!(__sk)->sk_bound_dev_if	||				\
-	   ((__sk)->sk_bound_dev_if == (__dif))) 		&&	\
-	 net_eq(sock_net(__sk), (__net)))
-
 #endif /* _IPV6_H */
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index d1d272843b3..9201afe083f 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -99,4 +99,14 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
 			  const struct in6_addr *daddr, const __be16 dport,
 			  const int dif);
 #endif /* IS_ENABLED(CONFIG_IPV6) */
+
+#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif)	\
+	(((__sk)->sk_portpair == (__ports))			&&	\
+	 ((__sk)->sk_family == AF_INET6)			&&	\
+	 ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr))		&&	\
+	 ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr))	&&	\
+	 (!(__sk)->sk_bound_dev_if	||				\
+	   ((__sk)->sk_bound_dev_if == (__dif))) 		&&	\
+	 net_eq(sock_net(__sk), (__net)))
+
 #endif /* _INET6_HASHTABLES_H */
-- 
cgit v1.2.3-70-g09d2


From 096916610f415e07cfe71d71a391011c617be5ed Mon Sep 17 00:00:00 2001
From: Aaron Sierra <asierra@xes-inc.com>
Date: Tue, 26 Aug 2014 18:18:33 -0500
Subject: fsl_ifc: Support all 8 IFC chip selects

Freescale's QorIQ T Series processors support 8 IFC chip selects
within a memory map backward compatible with previous P Series
processors which supported only 4 chip selects.

Signed-off-by: Aaron Sierra <asierra@xes-inc.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/memory/fsl_ifc.c        | 13 +++++++++++--
 drivers/mtd/nand/fsl_ifc_nand.c | 10 ++++------
 include/linux/fsl_ifc.h         | 21 ++++++++++++++++-----
 3 files changed, 31 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/memory/fsl_ifc.c b/drivers/memory/fsl_ifc.c
index 3d5d792d5cb..410c3974987 100644
--- a/drivers/memory/fsl_ifc.c
+++ b/drivers/memory/fsl_ifc.c
@@ -61,7 +61,7 @@ int fsl_ifc_find(phys_addr_t addr_base)
 	if (!fsl_ifc_ctrl_dev || !fsl_ifc_ctrl_dev->regs)
 		return -ENODEV;
 
-	for (i = 0; i < ARRAY_SIZE(fsl_ifc_ctrl_dev->regs->cspr_cs); i++) {
+	for (i = 0; i < fsl_ifc_ctrl_dev->banks; i++) {
 		u32 cspr = in_be32(&fsl_ifc_ctrl_dev->regs->cspr_cs[i].cspr);
 		if (cspr & CSPR_V && (cspr & CSPR_BA) ==
 				convert_ifc_address(addr_base))
@@ -213,7 +213,7 @@ static irqreturn_t fsl_ifc_ctrl_irq(int irqno, void *data)
 static int fsl_ifc_ctrl_probe(struct platform_device *dev)
 {
 	int ret = 0;
-
+	int version, banks;
 
 	dev_info(&dev->dev, "Freescale Integrated Flash Controller\n");
 
@@ -231,6 +231,15 @@ static int fsl_ifc_ctrl_probe(struct platform_device *dev)
 		goto err;
 	}
 
+	version = ioread32be(&fsl_ifc_ctrl_dev->regs->ifc_rev) &
+			FSL_IFC_VERSION_MASK;
+	banks = (version == FSL_IFC_VERSION_1_0_0) ? 4 : 8;
+	dev_info(&dev->dev, "IFC version %d.%d, %d banks\n",
+		version >> 24, (version >> 16) & 0xf, banks);
+
+	fsl_ifc_ctrl_dev->version = version;
+	fsl_ifc_ctrl_dev->banks = banks;
+
 	/* get the Controller level irq */
 	fsl_ifc_ctrl_dev->irq = irq_of_parse_and_map(dev->dev.of_node, 0);
 	if (fsl_ifc_ctrl_dev->irq == NO_IRQ) {
diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c
index 2338124dd05..4d40fdb2418 100644
--- a/drivers/mtd/nand/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/fsl_ifc_nand.c
@@ -31,7 +31,6 @@
 #include <linux/mtd/nand_ecc.h>
 #include <linux/fsl_ifc.h>
 
-#define FSL_IFC_V1_1_0	0x01010000
 #define ERR_BYTE		0xFF /* Value returned for read
 					bytes when read failed	*/
 #define IFC_TIMEOUT_MSECS	500  /* Maximum number of mSecs to wait
@@ -877,7 +876,7 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
 	struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
 	struct nand_chip *chip = &priv->chip;
 	struct nand_ecclayout *layout;
-	u32 csor, ver;
+	u32 csor;
 
 	/* Fill in fsl_ifc_mtd structure */
 	priv->mtd.priv = chip;
@@ -984,8 +983,7 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
 		chip->ecc.mode = NAND_ECC_SOFT;
 	}
 
-	ver = ioread32be(&ifc->ifc_rev);
-	if (ver == FSL_IFC_V1_1_0)
+	if (ctrl->version == FSL_IFC_VERSION_1_1_0)
 		fsl_ifc_sram_init(priv);
 
 	return 0;
@@ -1045,12 +1043,12 @@ static int fsl_ifc_nand_probe(struct platform_device *dev)
 	}
 
 	/* find which chip select it is connected to */
-	for (bank = 0; bank < FSL_IFC_BANK_COUNT; bank++) {
+	for (bank = 0; bank < fsl_ifc_ctrl_dev->banks; bank++) {
 		if (match_bank(ifc, bank, res.start))
 			break;
 	}
 
-	if (bank >= FSL_IFC_BANK_COUNT) {
+	if (bank >= fsl_ifc_ctrl_dev->banks) {
 		dev_err(&dev->dev, "%s: address did not match any chip selects\n",
 			__func__);
 		return -ENODEV;
diff --git a/include/linux/fsl_ifc.h b/include/linux/fsl_ifc.h
index 84d60cb841b..bf0321eabbd 100644
--- a/include/linux/fsl_ifc.h
+++ b/include/linux/fsl_ifc.h
@@ -29,7 +29,16 @@
 #include <linux/of_platform.h>
 #include <linux/interrupt.h>
 
-#define FSL_IFC_BANK_COUNT 4
+/*
+ * The actual number of banks implemented depends on the IFC version
+ *    - IFC version 1.0 implements 4 banks.
+ *    - IFC version 1.1 onward implements 8 banks.
+ */
+#define FSL_IFC_BANK_COUNT 8
+
+#define FSL_IFC_VERSION_MASK	0x0F0F0000
+#define FSL_IFC_VERSION_1_0_0	0x01000000
+#define FSL_IFC_VERSION_1_1_0	0x01010000
 
 /*
  * CSPR - Chip Select Property Register
@@ -776,23 +785,23 @@ struct fsl_ifc_regs {
 		__be32 cspr;
 		u32 res2;
 	} cspr_cs[FSL_IFC_BANK_COUNT];
-	u32 res3[0x19];
+	u32 res3[0xd];
 	struct {
 		__be32 amask;
 		u32 res4[0x2];
 	} amask_cs[FSL_IFC_BANK_COUNT];
-	u32 res5[0x18];
+	u32 res5[0xc];
 	struct {
 		__be32 csor;
 		__be32 csor_ext;
 		u32 res6;
 	} csor_cs[FSL_IFC_BANK_COUNT];
-	u32 res7[0x18];
+	u32 res7[0xc];
 	struct {
 		__be32 ftim[4];
 		u32 res8[0x8];
 	} ftim_cs[FSL_IFC_BANK_COUNT];
-	u32 res9[0x60];
+	u32 res9[0x30];
 	__be32 rb_stat;
 	u32 res10[0x2];
 	__be32 ifc_gcr;
@@ -827,6 +836,8 @@ struct fsl_ifc_ctrl {
 	int				nand_irq;
 	spinlock_t			lock;
 	void				*nand;
+	int				version;
+	int				banks;
 
 	u32 nand_stat;
 	wait_queue_head_t nand_wait;
-- 
cgit v1.2.3-70-g09d2


From d4260b51699082c7dea257bea002d79394e876e0 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Thu, 16 Oct 2014 14:19:47 -0400
Subject: serial: Fix upstat_t sparse warnings

Commit 299245a145b2ad4cfb4c5432eb1264299f55e7e0,
serial: core: Privatize modem status enable flags, introduced
the upstat_t type and matching bit definitions. The purpose is to
produce sparse warnings if the wrong bit definitions are used
(by warning of implicit integer conversions).

Fix implicit conversion to integer return type from uart_cts_enabled()
and uart_dcd_enabled().

Fixes the following sparse warnings:
drivers/tty/serial/serial_core.c:63:30: warning: incorrect type in return expression (different base types)
drivers/tty/serial/serial_core.c:63:30:    expected int
drivers/tty/serial/serial_core.c:63:30:    got restricted upstat_t
include/linux/serial_core.h:364:30: warning: incorrect type in return expression (different base types)
include/linux/serial_core.h:364:30:    expected bool
include/linux/serial_core.h:364:30:    got restricted upstat_t
include/linux/serial_core.h:364:30: warning: incorrect type in return expression (different base types)
include/linux/serial_core.h:364:30:    expected bool
include/linux/serial_core.h:364:30:    got restricted upstat_t

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 2 +-
 include/linux/serial_core.h      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index df3a8c74358..971103714dd 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -61,7 +61,7 @@ static void uart_port_shutdown(struct tty_port *port);
 
 static int uart_dcd_enabled(struct uart_port *uport)
 {
-	return uport->status & UPSTAT_DCD_ENABLE;
+	return !!(uport->status & UPSTAT_DCD_ENABLE);
 }
 
 /*
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 21c2e05c1bc..bccf4bac22f 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -367,7 +367,7 @@ static inline int uart_tx_stopped(struct uart_port *port)
 
 static inline bool uart_cts_enabled(struct uart_port *uport)
 {
-	return uport->status & UPSTAT_CTS_ENABLE;
+	return !!(uport->status & UPSTAT_CTS_ENABLE);
 }
 
 /*
-- 
cgit v1.2.3-70-g09d2


From 8f166e00196fcb16364c9c39dab6fe7b72e63f18 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Thu, 16 Oct 2014 14:59:41 -0400
Subject: tty: Remove tty_pair_get_tty()/tty_pair_get_pty() api

tty_pair_get_pty() has no in-tree users and tty_pair_get_tty()
has only one file-local user. Remove the external declarations,
the export declarations, and declare tty_pair_get_tty() static.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Reviewed-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c | 16 +++++-----------
 include/linux/tty.h  |  3 ---
 2 files changed, 5 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index c322e7af737..d3e71331641 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2703,23 +2703,17 @@ static int tty_tiocgicount(struct tty_struct *tty, void __user *arg)
 	return 0;
 }
 
-struct tty_struct *tty_pair_get_tty(struct tty_struct *tty)
+/*
+ * if pty, return the slave side (real_tty)
+ * otherwise, return self
+ */
+static struct tty_struct *tty_pair_get_tty(struct tty_struct *tty)
 {
 	if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
 	    tty->driver->subtype == PTY_TYPE_MASTER)
 		tty = tty->link;
 	return tty;
 }
-EXPORT_SYMBOL(tty_pair_get_tty);
-
-struct tty_struct *tty_pair_get_pty(struct tty_struct *tty)
-{
-	if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
-	    tty->driver->subtype == PTY_TYPE_MASTER)
-	    return tty;
-	return tty->link;
-}
-EXPORT_SYMBOL(tty_pair_get_pty);
 
 /*
  * Split this up, as gcc can choke on it otherwise..
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 5171ef8f7b8..b36b0b445c1 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -498,9 +498,6 @@ extern int tty_init_termios(struct tty_struct *tty);
 extern int tty_standard_install(struct tty_driver *driver,
 		struct tty_struct *tty);
 
-extern struct tty_struct *tty_pair_get_tty(struct tty_struct *tty);
-extern struct tty_struct *tty_pair_get_pty(struct tty_struct *tty);
-
 extern struct mutex tty_mutex;
 extern spinlock_t tty_files_lock;
 
-- 
cgit v1.2.3-70-g09d2


From e1c2296c3485158304bfad5a80e89078463d70c8 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Thu, 16 Oct 2014 14:59:48 -0400
Subject: tty: Move session_of_pgrp() and make static

tiocspgrp() is the lone caller of session_of_pgrp(); relocate and
limit to file scope.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Reviewed-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c   | 21 +++++++++++++++++++++
 include/linux/kernel.h |  3 ---
 kernel/exit.c          | 21 ---------------------
 3 files changed, 21 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 114854c5554..ae8f53c7972 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2515,6 +2515,27 @@ struct pid *tty_get_pgrp(struct tty_struct *tty)
 }
 EXPORT_SYMBOL_GPL(tty_get_pgrp);
 
+/*
+ * This checks not only the pgrp, but falls back on the pid if no
+ * satisfactory pgrp is found. I dunno - gdb doesn't work correctly
+ * without this...
+ *
+ * The caller must hold rcu lock or the tasklist lock.
+ */
+static struct pid *session_of_pgrp(struct pid *pgrp)
+{
+	struct task_struct *p;
+	struct pid *sid = NULL;
+
+	p = pid_task(pgrp, PIDTYPE_PGID);
+	if (p == NULL)
+		p = pid_task(pgrp, PIDTYPE_PID);
+	if (p != NULL)
+		sid = task_session(p);
+
+	return sid;
+}
+
 /**
  *	tiocgpgrp		-	get process group
  *	@tty: tty passed by user
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 3d770f5564b..01bc530fbfc 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -411,9 +411,6 @@ extern int __kernel_text_address(unsigned long addr);
 extern int kernel_text_address(unsigned long addr);
 extern int func_ptr_is_kernel_text(void *ptr);
 
-struct pid;
-extern struct pid *session_of_pgrp(struct pid *pgrp);
-
 unsigned long int_sqrt(unsigned long);
 
 extern void bust_spinlocks(int yes);
diff --git a/kernel/exit.c b/kernel/exit.c
index 5d30019ff95..6a3e2e5004b 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -214,27 +214,6 @@ repeat:
 		goto repeat;
 }
 
-/*
- * This checks not only the pgrp, but falls back on the pid if no
- * satisfactory pgrp is found. I dunno - gdb doesn't work correctly
- * without this...
- *
- * The caller must hold rcu lock or the tasklist lock.
- */
-struct pid *session_of_pgrp(struct pid *pgrp)
-{
-	struct task_struct *p;
-	struct pid *sid = NULL;
-
-	p = pid_task(pgrp, PIDTYPE_PGID);
-	if (p == NULL)
-		p = pid_task(pgrp, PIDTYPE_PID);
-	if (p != NULL)
-		sid = task_session(p);
-
-	return sid;
-}
-
 /*
  * Determine if a process group is "orphaned", according to the POSIX
  * definition in 2.2.2.52.  Orphaned process groups are not to be affected
-- 
cgit v1.2.3-70-g09d2


From 3ff51a199f9e85aed843471bc10dae9e94dbb0fc Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 5 Nov 2014 12:12:46 -0500
Subject: tty: Remove TTY_HUPPING

Now that tty_ldisc_hangup() does not drop the tty lock, it is no
longer possible to observe TTY_HUPPING while holding the tty lock
on another cpu.

Remove TTY_HUPPING bit definition.

Reviewed-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c    | 12 +-----------
 drivers/tty/tty_ldisc.c |  3 +--
 include/linux/tty.h     |  1 -
 3 files changed, 2 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 9d1e247ee33..873793c426d 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -690,9 +690,6 @@ static void __tty_hangup(struct tty_struct *tty, int exit_session)
 		return;
 	}
 
-	/* some functions below drop BTM, so we need this bit */
-	set_bit(TTY_HUPPING, &tty->flags);
-
 	/* inuse_filps is protected by the single tty lock,
 	   this really needs to change if we want to flush the
 	   workqueue with the lock held */
@@ -717,10 +714,6 @@ static void __tty_hangup(struct tty_struct *tty, int exit_session)
 	while (refs--)
 		tty_kref_put(tty);
 
-	/*
-	 * it drops BTM and thus races with reopen
-	 * we protect the race by TTY_HUPPING
-	 */
 	tty_ldisc_hangup(tty);
 
 	spin_lock_irq(&tty->ctrl_lock);
@@ -752,8 +745,6 @@ static void __tty_hangup(struct tty_struct *tty, int exit_session)
 	 * can't yet guarantee all that.
 	 */
 	set_bit(TTY_HUPPED, &tty->flags);
-	clear_bit(TTY_HUPPING, &tty->flags);
-
 	tty_unlock(tty);
 
 	if (f)
@@ -1461,8 +1452,7 @@ static int tty_reopen(struct tty_struct *tty)
 {
 	struct tty_driver *driver = tty->driver;
 
-	if (test_bit(TTY_CLOSING, &tty->flags) ||
-			test_bit(TTY_HUPPING, &tty->flags))
+	if (test_bit(TTY_CLOSING, &tty->flags))
 		return -EIO;
 
 	if (driver->type == TTY_DRIVER_TYPE_PTY &&
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 28858ebe291..49001fa2ea2 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -544,8 +544,7 @@ int tty_set_ldisc(struct tty_struct *tty, int ldisc)
 
 	old_ldisc = tty->ldisc;
 
-	if (test_bit(TTY_HUPPING, &tty->flags) ||
-	    test_bit(TTY_HUPPED, &tty->flags)) {
+	if (test_bit(TTY_HUPPED, &tty->flags)) {
 		/* We were raced by the hangup method. It will have stomped
 		   the ldisc data and closed the ldisc down */
 		tty_ldisc_enable_pair(tty, o_tty);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index b36b0b445c1..ff0dd7aeaf3 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -321,7 +321,6 @@ struct tty_file_private {
 #define TTY_PTY_LOCK 		16	/* pty private */
 #define TTY_NO_WRITE_SPLIT 	17	/* Preserve write boundaries to driver */
 #define TTY_HUPPED 		18	/* Post driver->hangup() */
-#define TTY_HUPPING 		21	/* ->hangup() in progress */
 #define TTY_LDISC_HALTED	22	/* Line discipline is halted */
 
 #define TTY_WRITE_FLUSH(tty) tty_write_flush((tty))
-- 
cgit v1.2.3-70-g09d2


From 04980706c8febe41ec598116b174bd3a2dc82355 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 5 Nov 2014 12:12:52 -0500
Subject: tty: Remove TTY_CLOSING

Now that re-open is not permitted for a legacy BSD pty master,
using TTY_CLOSING to indicate when a tty can be torn-down is
no longer necessary.

Reviewed-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c | 14 ++------------
 include/linux/tty.h  |  1 -
 2 files changed, 2 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 66d6bcc24c7..ea8c6cae8d1 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1197,7 +1197,7 @@ void tty_write_message(struct tty_struct *tty, char *msg)
 	if (tty) {
 		mutex_lock(&tty->atomic_write_lock);
 		tty_lock(tty);
-		if (tty->ops->write && !test_bit(TTY_CLOSING, &tty->flags)) {
+		if (tty->ops->write && tty->count > 0) {
 			tty_unlock(tty);
 			tty->ops->write(tty, msg, strlen(msg));
 		} else
@@ -1879,16 +1879,6 @@ int tty_release(struct inode *inode, struct file *filp)
 	/*
 	 * Perform some housekeeping before deciding whether to return.
 	 *
-	 * Set the TTY_CLOSING flag if this was the last open.  In the
-	 * case of a pty we may have to wait around for the other side
-	 * to close, and TTY_CLOSING makes sure we can't be reopened.
-	 */
-	if (tty_closing)
-		set_bit(TTY_CLOSING, &tty->flags);
-	if (o_tty_closing)
-		set_bit(TTY_CLOSING, &o_tty->flags);
-
-	/*
 	 * If _either_ side is closing, make sure there aren't any
 	 * processes that still think tty or o_tty is their controlling
 	 * tty.
@@ -1903,7 +1893,7 @@ int tty_release(struct inode *inode, struct file *filp)
 
 	mutex_unlock(&tty_mutex);
 	tty_unlock_pair(tty, o_tty);
-	/* At this point the TTY_CLOSING flag should ensure a dead tty
+	/* At this point, the tty->count == 0 should ensure a dead tty
 	   cannot be re-opened by a racing opener */
 
 	/* check whether both sides are closing ... */
diff --git a/include/linux/tty.h b/include/linux/tty.h
index ff0dd7aeaf3..35b29f0750f 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -316,7 +316,6 @@ struct tty_file_private {
 #define TTY_EXCLUSIVE 		3	/* Exclusive open mode */
 #define TTY_DEBUG 		4	/* Debugging */
 #define TTY_DO_WRITE_WAKEUP 	5	/* Call write_wakeup after queuing new */
-#define TTY_CLOSING 		7	/* ->close() in progress */
 #define TTY_LDISC_OPEN	 	11	/* Line discipline is open */
 #define TTY_PTY_LOCK 		16	/* pty private */
 #define TTY_NO_WRITE_SPLIT 	17	/* Preserve write boundaries to driver */
-- 
cgit v1.2.3-70-g09d2


From 62462aefeb5aff092fc97037d9c12a4afe95a3ff Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 5 Nov 2014 12:12:58 -0500
Subject: tty: Simplify tty_ldisc_release() interface

Passing the 'other' tty to tty_ldisc_release() only makes sense
for a pty pair; make o_tty function local instead.

Reviewed-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c    |  2 +-
 drivers/tty/tty_ldisc.c | 15 +++++++--------
 include/linux/tty.h     |  2 +-
 3 files changed, 9 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index f5b62b99489..cd9550820a5 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1892,7 +1892,7 @@ int tty_release(struct inode *inode, struct file *filp)
 	/*
 	 * Ask the line discipline code to release its structures
 	 */
-	tty_ldisc_release(tty, o_tty);
+	tty_ldisc_release(tty);
 
 	/* Wait for pending work before tty destruction commmences */
 	tty_flush_works(tty);
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 49001fa2ea2..1c4d7b6d8a7 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -756,18 +756,17 @@ static void tty_ldisc_kill(struct tty_struct *tty)
 
 /**
  *	tty_ldisc_release		-	release line discipline
- *	@tty: tty being shut down
- *	@o_tty: pair tty for pty/tty pairs
- *
- *	Called during the final close of a tty/pty pair in order to shut down
- *	the line discpline layer. On exit the ldisc assigned is N_TTY and the
- *	ldisc has not been opened.
+ *	@tty: tty being shut down (or one end of pty pair)
  *
- *	Holding ldisc_sem write lock serializes tty->ldisc changes.
+ *	Called during the final close of a tty or a pty pair in order to shut
+ *	down the line discpline layer. On exit, each ldisc assigned is N_TTY and
+ *	each ldisc has not been opened.
  */
 
-void tty_ldisc_release(struct tty_struct *tty, struct tty_struct *o_tty)
+void tty_ldisc_release(struct tty_struct *tty)
 {
+	struct tty_struct *o_tty = tty->link;
+
 	/*
 	 * Shutdown this line discipline. As this is the final close,
 	 * it does not race with the set_ldisc code path.
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 35b29f0750f..af1a7f3e4e4 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -557,7 +557,7 @@ extern int tty_register_ldisc(int disc, struct tty_ldisc_ops *new_ldisc);
 extern int tty_unregister_ldisc(int disc);
 extern int tty_set_ldisc(struct tty_struct *tty, int ldisc);
 extern int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty);
-extern void tty_ldisc_release(struct tty_struct *tty, struct tty_struct *o_tty);
+extern void tty_ldisc_release(struct tty_struct *tty);
 extern void tty_ldisc_init(struct tty_struct *tty);
 extern void tty_ldisc_deinit(struct tty_struct *tty);
 extern void tty_ldisc_begin(void);
-- 
cgit v1.2.3-70-g09d2


From 2aff5e2bc62db43e05c814461a08aff0fc2b7fe5 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 5 Nov 2014 12:13:01 -0500
Subject: tty: Change tty lock order to master->slave

When releasing the master pty, the slave pty also needs to be locked
to prevent concurrent tty count changes for the slave pty and to
ensure that only one parallel master and slave release observe the
final close, and proceed to destruct the pty pair. Conversely, when
releasing the slave pty, locking the master pty is not necessary
(since the master's state can be inferred by the slave tty count).

Introduce tty_lock_slave()/tty_unlock_slave() which acquires/releases
the tty lock of the slave pty. Remove tty_lock_pair()/tty_unlock_pair().

Dropping the tty_lock is no longer required to re-establish a stable
lock order.

Reviewed-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c    | 10 ++++++----
 drivers/tty/tty_mutex.c | 32 +++++++++++++-------------------
 include/linux/tty.h     |  7 ++-----
 3 files changed, 21 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index bd7cde3c56e..4ecee2856ec 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1790,7 +1790,9 @@ int tty_release(struct inode *inode, struct file *filp)
 	if (tty->ops->close)
 		tty->ops->close(tty, filp);
 
-	tty_unlock(tty);
+	/* If tty is pty master, lock the slave pty (stable lock order) */
+	tty_lock_slave(o_tty);
+
 	/*
 	 * Sanity check: if tty->count is going to zero, there shouldn't be
 	 * any waiters on tty->read_wait or tty->write_wait.  We test the
@@ -1804,8 +1806,6 @@ int tty_release(struct inode *inode, struct file *filp)
 	 * Thus this test wouldn't be triggered at the time the slave closed,
 	 * so we do it now.
 	 */
-	tty_lock_pair(tty, o_tty);
-
 	while (1) {
 		do_sleep = 0;
 
@@ -1879,7 +1879,9 @@ int tty_release(struct inode *inode, struct file *filp)
 	/* check whether both sides are closing ... */
 	final = !tty->count && !(o_tty && o_tty->count);
 
-	tty_unlock_pair(tty, o_tty);
+	tty_unlock_slave(o_tty);
+	tty_unlock(tty);
+
 	/* At this point, the tty->count == 0 should ensure a dead tty
 	   cannot be re-opened by a racing opener */
 
diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c
index 2e41abebbcb..f43e995c7a0 100644
--- a/drivers/tty/tty_mutex.c
+++ b/drivers/tty/tty_mutex.c
@@ -4,6 +4,11 @@
 #include <linux/semaphore.h>
 #include <linux/sched.h>
 
+/*
+ * Nested tty locks are necessary for releasing pty pairs.
+ * The stable lock order is master pty first, then slave pty.
+ */
+
 /* Legacy tty mutex glue */
 
 enum {
@@ -45,29 +50,18 @@ void __lockfunc tty_unlock(struct tty_struct *tty)
 }
 EXPORT_SYMBOL(tty_unlock);
 
-/*
- * Getting the big tty mutex for a pair of ttys with lock ordering
- * On a non pty/tty pair tty2 can be NULL which is just fine.
- */
-void __lockfunc tty_lock_pair(struct tty_struct *tty,
-					struct tty_struct *tty2)
+void __lockfunc tty_lock_slave(struct tty_struct *tty)
 {
-	if (tty < tty2) {
-		tty_lock(tty);
-		tty_lock_nested(tty2, TTY_MUTEX_NESTED);
-	} else {
-		if (tty2 && tty2 != tty)
-			tty_lock(tty2);
+	if (tty && tty != tty->link) {
+		WARN_ON(!mutex_is_locked(&tty->link->legacy_mutex) ||
+			!tty->driver->type == TTY_DRIVER_TYPE_PTY ||
+			!tty->driver->type == PTY_TYPE_SLAVE);
 		tty_lock_nested(tty, TTY_MUTEX_NESTED);
 	}
 }
-EXPORT_SYMBOL(tty_lock_pair);
 
-void __lockfunc tty_unlock_pair(struct tty_struct *tty,
-						struct tty_struct *tty2)
+void __lockfunc tty_unlock_slave(struct tty_struct *tty)
 {
-	tty_unlock(tty);
-	if (tty2 && tty2 != tty)
-		tty_unlock(tty2);
+	if (tty && tty != tty->link)
+		tty_unlock(tty);
 }
-EXPORT_SYMBOL(tty_unlock_pair);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index af1a7f3e4e4..a07b4b415db 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -638,11 +638,8 @@ extern long vt_compat_ioctl(struct tty_struct *tty,
 /* functions for preparation of BKL removal */
 extern void __lockfunc tty_lock(struct tty_struct *tty);
 extern void __lockfunc tty_unlock(struct tty_struct *tty);
-extern void __lockfunc tty_lock_pair(struct tty_struct *tty,
-				struct tty_struct *tty2);
-extern void __lockfunc tty_unlock_pair(struct tty_struct *tty,
-				struct tty_struct *tty2);
-
+extern void __lockfunc tty_lock_slave(struct tty_struct *tty);
+extern void __lockfunc tty_unlock_slave(struct tty_struct *tty);
 /*
  * this shall be called only from where BTM is held (like close)
  *
-- 
cgit v1.2.3-70-g09d2


From 2febdb632bb96235b94b8fccaf882a78f8f4b2bb Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 5 Nov 2014 12:13:02 -0500
Subject: tty: Preset lock subclass for nested tty locks

Eliminate the requirement of specifying the tty lock nesting at
lock time; instead, set the lock subclass for slave ptys at pty
install (normal ttys and master ptys use subclass 0).

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/pty.c       |  2 ++
 drivers/tty/tty_mutex.c | 19 +++++++++----------
 include/linux/tty.h     |  1 +
 3 files changed, 12 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index bdb8fd1a202..11db7dc8676 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -399,6 +399,8 @@ static int pty_common_install(struct tty_driver *driver, struct tty_struct *tty,
 	if (!o_tty)
 		goto err_put_module;
 
+	tty_set_lock_subclass(o_tty);
+
 	if (legacy) {
 		/* We always use new tty termios data so we can do this
 		   the easy way .. */
diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c
index f43e995c7a0..4486741190c 100644
--- a/drivers/tty/tty_mutex.c
+++ b/drivers/tty/tty_mutex.c
@@ -13,15 +13,14 @@
 
 enum {
 	TTY_MUTEX_NORMAL,
-	TTY_MUTEX_NESTED,
+	TTY_MUTEX_SLAVE,
 };
 
 /*
  * Getting the big tty mutex.
  */
 
-static void __lockfunc tty_lock_nested(struct tty_struct *tty,
-				       unsigned int subclass)
+void __lockfunc tty_lock(struct tty_struct *tty)
 {
 	if (tty->magic != TTY_MAGIC) {
 		pr_err("L Bad %p\n", tty);
@@ -29,12 +28,7 @@ static void __lockfunc tty_lock_nested(struct tty_struct *tty,
 		return;
 	}
 	tty_kref_get(tty);
-	mutex_lock_nested(&tty->legacy_mutex, subclass);
-}
-
-void __lockfunc tty_lock(struct tty_struct *tty)
-{
-	return tty_lock_nested(tty, TTY_MUTEX_NORMAL);
+	mutex_lock(&tty->legacy_mutex);
 }
 EXPORT_SYMBOL(tty_lock);
 
@@ -56,7 +50,7 @@ void __lockfunc tty_lock_slave(struct tty_struct *tty)
 		WARN_ON(!mutex_is_locked(&tty->link->legacy_mutex) ||
 			!tty->driver->type == TTY_DRIVER_TYPE_PTY ||
 			!tty->driver->type == PTY_TYPE_SLAVE);
-		tty_lock_nested(tty, TTY_MUTEX_NESTED);
+		tty_lock(tty);
 	}
 }
 
@@ -65,3 +59,8 @@ void __lockfunc tty_unlock_slave(struct tty_struct *tty)
 	if (tty && tty != tty->link)
 		tty_unlock(tty);
 }
+
+void tty_set_lock_subclass(struct tty_struct *tty)
+{
+	lockdep_set_subclass(&tty->legacy_mutex, TTY_MUTEX_SLAVE);
+}
diff --git a/include/linux/tty.h b/include/linux/tty.h
index a07b4b415db..196c352a5ce 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -640,6 +640,7 @@ extern void __lockfunc tty_lock(struct tty_struct *tty);
 extern void __lockfunc tty_unlock(struct tty_struct *tty);
 extern void __lockfunc tty_lock_slave(struct tty_struct *tty);
 extern void __lockfunc tty_unlock_slave(struct tty_struct *tty);
+extern void tty_set_lock_subclass(struct tty_struct *tty);
 /*
  * this shall be called only from where BTM is held (like close)
  *
-- 
cgit v1.2.3-70-g09d2


From 35af935ee47eb4548e0052733e9d75328e260fa1 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 5 Nov 2014 12:13:03 -0500
Subject: tty: Remove tty_unhangup() declaration

The tty_unhangup() function is not defined.

Reviewed-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 196c352a5ce..e33ea1a0c2d 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -435,7 +435,6 @@ extern int is_ignored(int sig);
 extern int tty_signal(int sig, struct tty_struct *tty);
 extern void tty_hangup(struct tty_struct *tty);
 extern void tty_vhangup(struct tty_struct *tty);
-extern void tty_unhangup(struct file *filp);
 extern int tty_hung_up_p(struct file *filp);
 extern void do_SAK(struct tty_struct *tty);
 extern void __do_SAK(struct tty_struct *tty);
-- 
cgit v1.2.3-70-g09d2


From 86c80a8e2ab443e9c4261b3499de4ce808399104 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 5 Nov 2014 12:13:09 -0500
Subject: tty: Flush ldisc buffer atomically with tty flip buffers

tty_ldisc_flush() first clears the line discipline input buffer,
then clears the tty flip buffers. However, this allows for existing
data in the tty flip buffers to be added after the ldisc input
buffer has been cleared, but before the flip buffers have been cleared.

Add an optional ldisc parameter to tty_buffer_flush() to allow
tty_ldisc_flush() to pass the ldisc to clear.

NB: Initially, the plan was to do this automatically in
tty_buffer_flush(). However, an audit of the behavior of existing
line disciplines showed that performing a ldisc buffer flush on
ioctl(TCFLSH) was not always the outcome. For example, some line
disciplines have flush_buffer() methods but not ioctl() methods,
so a ->flush_buffer() command would be unexpected.

Reviewed-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_buffer.c | 10 ++++++++--
 drivers/tty/tty_io.c     |  2 +-
 drivers/tty/tty_ldisc.c  | 12 +++++-------
 include/linux/tty.h      |  2 +-
 4 files changed, 15 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index 143deb62467..3605103fc1a 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -202,14 +202,16 @@ static void tty_buffer_free(struct tty_port *port, struct tty_buffer *b)
 /**
  *	tty_buffer_flush		-	flush full tty buffers
  *	@tty: tty to flush
+ *	@ld:  optional ldisc ptr (must be referenced)
  *
- *	flush all the buffers containing receive data.
+ *	flush all the buffers containing receive data. If ld != NULL,
+ *	flush the ldisc input buffer.
  *
  *	Locking: takes buffer lock to ensure single-threaded flip buffer
  *		 'consumer'
  */
 
-void tty_buffer_flush(struct tty_struct *tty)
+void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld)
 {
 	struct tty_port *port = tty->port;
 	struct tty_bufhead *buf = &port->buf;
@@ -223,6 +225,10 @@ void tty_buffer_flush(struct tty_struct *tty)
 		buf->head = next;
 	}
 	buf->head->read = buf->head->commit;
+
+	if (ld && ld->ops->flush_buffer)
+		ld->ops->flush_buffer(tty);
+
 	atomic_dec(&buf->priority);
 	mutex_unlock(&buf->lock);
 }
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 4ecee2856ec..aa83cd1bf07 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2890,7 +2890,7 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		case TCIFLUSH:
 		case TCIOFLUSH:
 		/* flush tty buffer and allow ldisc to process ioctl */
-			tty_buffer_flush(tty);
+			tty_buffer_flush(tty, NULL);
 			break;
 		}
 		break;
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 6368dd95e13..b66a81d0549 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -397,19 +397,17 @@ static void __lockfunc tty_ldisc_unlock_pair(struct tty_struct *tty,
  *	tty_ldisc_flush	-	flush line discipline queue
  *	@tty: tty
  *
- *	Flush the line discipline queue (if any) for this tty. If there
- *	is no line discipline active this is a no-op.
+ *	Flush the line discipline queue (if any) and the tty flip buffers
+ *	for this tty.
  */
 
 void tty_ldisc_flush(struct tty_struct *tty)
 {
 	struct tty_ldisc *ld = tty_ldisc_ref(tty);
-	if (ld) {
-		if (ld->ops->flush_buffer)
-			ld->ops->flush_buffer(tty);
+
+	tty_buffer_flush(tty, ld);
+	if (ld)
 		tty_ldisc_deref(ld);
-	}
-	tty_buffer_flush(tty);
 }
 EXPORT_SYMBOL_GPL(tty_ldisc_flush);
 
diff --git a/include/linux/tty.h b/include/linux/tty.h
index e33ea1a0c2d..f6835ea1079 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -441,7 +441,7 @@ extern void __do_SAK(struct tty_struct *tty);
 extern void no_tty(void);
 extern void tty_flush_to_ldisc(struct tty_struct *tty);
 extern void tty_buffer_free_all(struct tty_port *port);
-extern void tty_buffer_flush(struct tty_struct *tty);
+extern void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld);
 extern void tty_buffer_init(struct tty_port *port);
 extern speed_t tty_termios_baud_rate(struct ktermios *termios);
 extern speed_t tty_termios_input_baud_rate(struct ktermios *termios);
-- 
cgit v1.2.3-70-g09d2


From 904326ecac022ebaeb39cdfb206fd3b6551cdfca Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Thu, 16 Oct 2014 16:54:21 -0400
Subject: tty,serial: Unify UPF_* and ASYNC_* flag definitions

The userspace-defined ASYNC_* flags in include/uapi/linux/tty_flags.h
are the authoritative bit definitions for the serial_struct flags,
and thus for any derivative values or fields.

Although the serial core provides the TIOCSSERIAL and TIOCGSERIAL
ioctls to set and retrieve these flags from userspace, it defines these
bits independently, as UPF_* macros.

Define the UPF_* macros which are userspace-modifiable directly from
the ASYNC_* symbolic constants. Add compile-time test to ensure the
bits changeable by TIOCSSERIAL match the defined range in the uapi
header.

Add ASYNCB_MAGIC_MULTIPLIER to the uapi header since this bit is
programmable by userspace.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/serial_core.h    | 47 ++++++++++++++++++++++++++++--------------
 include/uapi/linux/tty_flags.h |  6 +++++-
 2 files changed, 37 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index bccf4bac22f..ad9329669ab 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -160,21 +160,33 @@ struct uart_port {
 	/* flags must be updated while holding port mutex */
 	upf_t			flags;
 
-#define UPF_FOURPORT		((__force upf_t) (1 << 1))
-#define UPF_SAK			((__force upf_t) (1 << 2))
-#define UPF_SPD_MASK		((__force upf_t) (0x1030))
-#define UPF_SPD_HI		((__force upf_t) (0x0010))
-#define UPF_SPD_VHI		((__force upf_t) (0x0020))
-#define UPF_SPD_CUST		((__force upf_t) (0x0030))
-#define UPF_SPD_SHI		((__force upf_t) (0x1000))
-#define UPF_SPD_WARP		((__force upf_t) (0x1010))
-#define UPF_SKIP_TEST		((__force upf_t) (1 << 6))
-#define UPF_AUTO_IRQ		((__force upf_t) (1 << 7))
-#define UPF_HARDPPS_CD		((__force upf_t) (1 << 11))
-#define UPF_LOW_LATENCY		((__force upf_t) (1 << 13))
-#define UPF_BUGGY_UART		((__force upf_t) (1 << 14))
+	/*
+	 * These flags must be equivalent to the flags defined in
+	 * include/uapi/linux/tty_flags.h which are the userspace definitions
+	 * assigned from the serial_struct flags in uart_set_info()
+	 * [for bit definitions in the UPF_CHANGE_MASK]
+	 *
+	 * Bits [0..UPF_LAST_USER] are userspace defined/visible/changeable
+	 * except bit 15 (UPF_NO_TXEN_TEST) which is masked off.
+	 * The remaining bits are serial-core specific and not modifiable by
+	 * userspace.
+	 */
+#define UPF_FOURPORT		((__force upf_t) ASYNC_FOURPORT       /* 1  */ )
+#define UPF_SAK			((__force upf_t) ASYNC_SAK            /* 2  */ )
+#define UPF_SPD_HI		((__force upf_t) ASYNC_SPD_HI         /* 4  */ )
+#define UPF_SPD_VHI		((__force upf_t) ASYNC_SPD_VHI        /* 5  */ )
+#define UPF_SPD_CUST		((__force upf_t) ASYNC_SPD_CUST   /* 0x0030 */ )
+#define UPF_SPD_WARP		((__force upf_t) ASYNC_SPD_WARP   /* 0x1010 */ )
+#define UPF_SPD_MASK		((__force upf_t) ASYNC_SPD_MASK   /* 0x1030 */ )
+#define UPF_SKIP_TEST		((__force upf_t) ASYNC_SKIP_TEST      /* 6  */ )
+#define UPF_AUTO_IRQ		((__force upf_t) ASYNC_AUTO_IRQ       /* 7  */ )
+#define UPF_HARDPPS_CD		((__force upf_t) ASYNC_HARDPPS_CD     /* 11 */ )
+#define UPF_SPD_SHI		((__force upf_t) ASYNC_SPD_SHI        /* 12 */ )
+#define UPF_LOW_LATENCY		((__force upf_t) ASYNC_LOW_LATENCY    /* 13 */ )
+#define UPF_BUGGY_UART		((__force upf_t) ASYNC_BUGGY_UART     /* 14 */ )
 #define UPF_NO_TXEN_TEST	((__force upf_t) (1 << 15))
-#define UPF_MAGIC_MULTIPLIER	((__force upf_t) (1 << 16))
+#define UPF_MAGIC_MULTIPLIER	((__force upf_t) ASYNC_MAGIC_MULTIPLIER /* 16 */ )
+
 /* Port has hardware-assisted h/w flow control (iow, auto-RTS *not* auto-CTS) */
 #define UPF_HARD_FLOW		((__force upf_t) (1 << 21))
 /* Port has hardware-assisted s/w flow control */
@@ -190,9 +202,14 @@ struct uart_port {
 #define UPF_DEAD		((__force upf_t) (1 << 30))
 #define UPF_IOREMAP		((__force upf_t) (1 << 31))
 
-#define UPF_CHANGE_MASK		((__force upf_t) (0x17fff))
+#define __UPF_CHANGE_MASK	0x17fff
+#define UPF_CHANGE_MASK		((__force upf_t) __UPF_CHANGE_MASK)
 #define UPF_USR_MASK		((__force upf_t) (UPF_SPD_MASK|UPF_LOW_LATENCY))
 
+#if __UPF_CHANGE_MASK > ASYNC_FLAGS
+#error Change mask not equivalent to userspace-visible bit defines
+#endif
+
 	/* status must be updated while holding port lock */
 	upstat_t		status;
 
diff --git a/include/uapi/linux/tty_flags.h b/include/uapi/linux/tty_flags.h
index eefcb483a2c..7b516f7ee7e 100644
--- a/include/uapi/linux/tty_flags.h
+++ b/include/uapi/linux/tty_flags.h
@@ -6,6 +6,8 @@
  * shared by the tty_port flags structures.
  *
  * Define ASYNCB_* for convenient use with {test,set,clear}_bit.
+ *
+ * Bits [0..ASYNCB_LAST_USER] are userspace defined/visible/changeable
  */
 #define ASYNCB_HUP_NOTIFY	 0 /* Notify getty on hangups and closes
 				    * on the callout port */
@@ -26,7 +28,8 @@
 #define ASYNCB_BUGGY_UART	14 /* This is a buggy UART, skip some safety
 				    * checks.  Note: can be dangerous! */
 #define ASYNCB_AUTOPROBE	15 /* Port was autoprobed by PCI or PNP code */
-#define ASYNCB_LAST_USER	15
+#define ASYNCB_MAGIC_MULTIPLIER	16 /* Use special CLK or divisor */
+#define ASYNCB_LAST_USER	16
 
 /* Internal flags used only by kernel */
 #define ASYNCB_INITIALIZED	31 /* Serial port was initialized */
@@ -57,6 +60,7 @@
 #define ASYNC_LOW_LATENCY	(1U << ASYNCB_LOW_LATENCY)
 #define ASYNC_BUGGY_UART	(1U << ASYNCB_BUGGY_UART)
 #define ASYNC_AUTOPROBE		(1U << ASYNCB_AUTOPROBE)
+#define ASYNC_MAGIC_MULTIPLIER	(1U << ASYNCB_MAGIC_MULTIPLIER)
 
 #define ASYNC_FLAGS		((1U << (ASYNCB_LAST_USER + 1)) - 1)
 #define ASYNC_USR_MASK		(ASYNC_SPD_MASK|ASYNC_CALLOUT_NOHUP| \
-- 
cgit v1.2.3-70-g09d2


From 352f86187e1d3e9e27d3be237103dc83a48f882c Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Thu, 16 Oct 2014 16:54:22 -0400
Subject: tty: Document defunct ASYNC_* bits in uapi header

Note the serial_struct flags for which the kernel ignores and performs
no action. The flags cannot be removed since they form part of the
userspace interface via the TIOCSSERIAL/TIOCGSERIAL ioctls.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/tty_flags.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/tty_flags.h b/include/uapi/linux/tty_flags.h
index 7b516f7ee7e..4e021e31c21 100644
--- a/include/uapi/linux/tty_flags.h
+++ b/include/uapi/linux/tty_flags.h
@@ -8,6 +8,7 @@
  * Define ASYNCB_* for convenient use with {test,set,clear}_bit.
  *
  * Bits [0..ASYNCB_LAST_USER] are userspace defined/visible/changeable
+ * [x] in the bit comments indicates the flag is defunct and no longer used.
  */
 #define ASYNCB_HUP_NOTIFY	 0 /* Notify getty on hangups and closes
 				    * on the callout port */
@@ -19,15 +20,15 @@
 #define ASYNCB_SKIP_TEST	 6 /* Skip UART test during autoconfiguration */
 #define ASYNCB_AUTO_IRQ		 7 /* Do automatic IRQ during
 				    * autoconfiguration */
-#define ASYNCB_SESSION_LOCKOUT	 8 /* Lock out cua opens based on session */
-#define ASYNCB_PGRP_LOCKOUT	 9 /* Lock out cua opens based on pgrp */
-#define ASYNCB_CALLOUT_NOHUP	10 /* Don't do hangups for cua device */
+#define ASYNCB_SESSION_LOCKOUT	 8 /* [x] Lock out cua opens based on session */
+#define ASYNCB_PGRP_LOCKOUT	 9 /* [x] Lock out cua opens based on pgrp */
+#define ASYNCB_CALLOUT_NOHUP	10 /* [x] Don't do hangups for cua device */
 #define ASYNCB_HARDPPS_CD	11 /* Call hardpps when CD goes high  */
 #define ASYNCB_SPD_SHI		12 /* Use 230400 instead of 38400 bps */
 #define ASYNCB_LOW_LATENCY	13 /* Request low latency behaviour */
 #define ASYNCB_BUGGY_UART	14 /* This is a buggy UART, skip some safety
 				    * checks.  Note: can be dangerous! */
-#define ASYNCB_AUTOPROBE	15 /* Port was autoprobed by PCI or PNP code */
+#define ASYNCB_AUTOPROBE	15 /* [x] Port was autoprobed by PCI/PNP code */
 #define ASYNCB_MAGIC_MULTIPLIER	16 /* Use special CLK or divisor */
 #define ASYNCB_LAST_USER	16
 
-- 
cgit v1.2.3-70-g09d2


From e5a2c899957659cd1a9f789bc462f9c0b35f5150 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Wed, 5 Nov 2014 00:23:04 +0100
Subject: fast_hash: avoid indirect function calls

By default the arch_fast_hash hashing function pointers are initialized
to jhash(2). If during boot-up a CPU with SSE4.2 is detected they get
updated to the CRC32 ones. This dispatching scheme incurs a function
pointer lookup and indirect call for every hashing operation.

rhashtable as a user of arch_fast_hash e.g. stores pointers to hashing
functions in its structure, too, causing two indirect branches per
hashing operation.

Using alternative_call we can get away with one of those indirect branches.

Acked-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/include/asm/hash.h | 51 ++++++++++++++++++++++++++++++++++++++++-----
 arch/x86/lib/hash.c         | 29 +++++++++++++++-----------
 include/asm-generic/hash.h  | 36 ++++++++++++++++++++++++++++++--
 include/linux/hash.h        | 34 ------------------------------
 lib/Makefile                |  2 +-
 lib/hash.c                  | 39 ----------------------------------
 6 files changed, 98 insertions(+), 93 deletions(-)
 delete mode 100644 lib/hash.c

(limited to 'include')

diff --git a/arch/x86/include/asm/hash.h b/arch/x86/include/asm/hash.h
index e8c58f88b1d..a881d784f04 100644
--- a/arch/x86/include/asm/hash.h
+++ b/arch/x86/include/asm/hash.h
@@ -1,7 +1,48 @@
-#ifndef _ASM_X86_HASH_H
-#define _ASM_X86_HASH_H
+#ifndef __ASM_X86_HASH_H
+#define __ASM_X86_HASH_H
 
-struct fast_hash_ops;
-extern void setup_arch_fast_hash(struct fast_hash_ops *ops);
+#include <linux/cpufeature.h>
+#include <asm/alternative.h>
 
-#endif /* _ASM_X86_HASH_H */
+u32 __intel_crc4_2_hash(const void *data, u32 len, u32 seed);
+u32 __intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed);
+
+/*
+ * non-inline versions of jhash so gcc does not need to generate
+ * duplicate code in every object file
+ */
+u32 __jhash(const void *data, u32 len, u32 seed);
+u32 __jhash2(const u32 *data, u32 len, u32 seed);
+
+/*
+ * for documentation of these functions please look into
+ * <include/asm-generic/hash.h>
+ */
+
+static inline u32 arch_fast_hash(const void *data, u32 len, u32 seed)
+{
+	u32 hash;
+
+	alternative_call(__jhash, __intel_crc4_2_hash, X86_FEATURE_XMM4_2,
+#ifdef CONFIG_X86_64
+			 "=a" (hash), "D" (data), "S" (len), "d" (seed));
+#else
+			 "=a" (hash), "a" (data), "d" (len), "c" (seed));
+#endif
+	return hash;
+}
+
+static inline u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed)
+{
+	u32 hash;
+
+	alternative_call(__jhash2, __intel_crc4_2_hash2, X86_FEATURE_XMM4_2,
+#ifdef CONFIG_X86_64
+			 "=a" (hash), "D" (data), "S" (len), "d" (seed));
+#else
+			 "=a" (hash), "a" (data), "d" (len), "c" (seed));
+#endif
+	return hash;
+}
+
+#endif /* __ASM_X86_HASH_H */
diff --git a/arch/x86/lib/hash.c b/arch/x86/lib/hash.c
index ff4fa51a5b1..e1432719883 100644
--- a/arch/x86/lib/hash.c
+++ b/arch/x86/lib/hash.c
@@ -31,13 +31,13 @@
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-#include <linux/hash.h>
-#include <linux/init.h>
-
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
 #include <asm/hash.h>
 
+#include <linux/hash.h>
+#include <linux/jhash.h>
+
 static inline u32 crc32_u32(u32 crc, u32 val)
 {
 #ifdef CONFIG_AS_CRC32
@@ -48,7 +48,7 @@ static inline u32 crc32_u32(u32 crc, u32 val)
 	return crc;
 }
 
-static u32 intel_crc4_2_hash(const void *data, u32 len, u32 seed)
+u32 __intel_crc4_2_hash(const void *data, u32 len, u32 seed)
 {
 	const u32 *p32 = (const u32 *) data;
 	u32 i, tmp = 0;
@@ -71,22 +71,27 @@ static u32 intel_crc4_2_hash(const void *data, u32 len, u32 seed)
 
 	return seed;
 }
+EXPORT_SYMBOL(__intel_crc4_2_hash);
 
-static u32 intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed)
+u32 __intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed)
 {
-	const u32 *p32 = (const u32 *) data;
 	u32 i;
 
 	for (i = 0; i < len; i++)
-		seed = crc32_u32(seed, *p32++);
+		seed = crc32_u32(seed, *data++);
 
 	return seed;
 }
+EXPORT_SYMBOL(__intel_crc4_2_hash2);
 
-void __init setup_arch_fast_hash(struct fast_hash_ops *ops)
+u32 __jhash(const void *data, u32 len, u32 seed)
 {
-	if (cpu_has_xmm4_2) {
-		ops->hash  = intel_crc4_2_hash;
-		ops->hash2 = intel_crc4_2_hash2;
-	}
+	return jhash(data, len, seed);
+}
+EXPORT_SYMBOL(__jhash);
+
+u32 __jhash2(const u32 *data, u32 len, u32 seed)
+{
+	return jhash2(data, len, seed);
 }
+EXPORT_SYMBOL(__jhash2);
diff --git a/include/asm-generic/hash.h b/include/asm-generic/hash.h
index b6312843dbd..3c82760ff2a 100644
--- a/include/asm-generic/hash.h
+++ b/include/asm-generic/hash.h
@@ -1,9 +1,41 @@
 #ifndef __ASM_GENERIC_HASH_H
 #define __ASM_GENERIC_HASH_H
 
-struct fast_hash_ops;
-static inline void setup_arch_fast_hash(struct fast_hash_ops *ops)
+#include <linux/jhash.h>
+
+/**
+ *	arch_fast_hash - Caclulates a hash over a given buffer that can have
+ *			 arbitrary size. This function will eventually use an
+ *			 architecture-optimized hashing implementation if
+ *			 available, and trades off distribution for speed.
+ *
+ *	@data: buffer to hash
+ *	@len: length of buffer in bytes
+ *	@seed: start seed
+ *
+ *	Returns 32bit hash.
+ */
+static inline u32 arch_fast_hash(const void *data, u32 len, u32 seed)
+{
+	return jhash(data, len, seed);
+}
+
+/**
+ *	arch_fast_hash2 - Caclulates a hash over a given buffer that has a
+ *			  size that is of a multiple of 32bit words. This
+ *			  function will eventually use an architecture-
+ *			  optimized hashing implementation if available,
+ *			  and trades off distribution for speed.
+ *
+ *	@data: buffer to hash (must be 32bit padded)
+ *	@len: number of 32bit words
+ *	@seed: start seed
+ *
+ *	Returns 32bit hash.
+ */
+static inline u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed)
 {
+	return jhash2(data, len, seed);
 }
 
 #endif /* __ASM_GENERIC_HASH_H */
diff --git a/include/linux/hash.h b/include/linux/hash.h
index d0494c39939..6e8fb028848 100644
--- a/include/linux/hash.h
+++ b/include/linux/hash.h
@@ -84,38 +84,4 @@ static inline u32 hash32_ptr(const void *ptr)
 	return (u32)val;
 }
 
-struct fast_hash_ops {
-	u32 (*hash)(const void *data, u32 len, u32 seed);
-	u32 (*hash2)(const u32 *data, u32 len, u32 seed);
-};
-
-/**
- *	arch_fast_hash - Caclulates a hash over a given buffer that can have
- *			 arbitrary size. This function will eventually use an
- *			 architecture-optimized hashing implementation if
- *			 available, and trades off distribution for speed.
- *
- *	@data: buffer to hash
- *	@len: length of buffer in bytes
- *	@seed: start seed
- *
- *	Returns 32bit hash.
- */
-extern u32 arch_fast_hash(const void *data, u32 len, u32 seed);
-
-/**
- *	arch_fast_hash2 - Caclulates a hash over a given buffer that has a
- *			  size that is of a multiple of 32bit words. This
- *			  function will eventually use an architecture-
- *			  optimized hashing implementation if available,
- *			  and trades off distribution for speed.
- *
- *	@data: buffer to hash (must be 32bit padded)
- *	@len: number of 32bit words
- *	@seed: start seed
- *
- *	Returns 32bit hash.
- */
-extern u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed);
-
 #endif /* _LINUX_HASH_H */
diff --git a/lib/Makefile b/lib/Makefile
index 7512dc978f1..04e53dd1607 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -26,7 +26,7 @@ obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
 	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
 	 gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \
 	 bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
-	 percpu-refcount.o percpu_ida.o hash.o rhashtable.o
+	 percpu-refcount.o percpu_ida.o rhashtable.o
 obj-y += string_helpers.o
 obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
 obj-y += kstrtox.o
diff --git a/lib/hash.c b/lib/hash.c
deleted file mode 100644
index fea973f4bd5..00000000000
--- a/lib/hash.c
+++ /dev/null
@@ -1,39 +0,0 @@
-/* General purpose hashing library
- *
- * That's a start of a kernel hashing library, which can be extended
- * with further algorithms in future. arch_fast_hash{2,}() will
- * eventually resolve to an architecture optimized implementation.
- *
- * Copyright 2013 Francesco Fusco <ffusco@redhat.com>
- * Copyright 2013 Daniel Borkmann <dborkman@redhat.com>
- * Copyright 2013 Thomas Graf <tgraf@redhat.com>
- * Licensed under the GNU General Public License, version 2.0 (GPLv2)
- */
-
-#include <linux/jhash.h>
-#include <linux/hash.h>
-#include <linux/cache.h>
-
-static struct fast_hash_ops arch_hash_ops __read_mostly = {
-	.hash  = jhash,
-	.hash2 = jhash2,
-};
-
-u32 arch_fast_hash(const void *data, u32 len, u32 seed)
-{
-	return arch_hash_ops.hash(data, len, seed);
-}
-EXPORT_SYMBOL_GPL(arch_fast_hash);
-
-u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed)
-{
-	return arch_hash_ops.hash2(data, len, seed);
-}
-EXPORT_SYMBOL_GPL(arch_fast_hash2);
-
-static int __init hashlib_init(void)
-{
-	setup_arch_fast_hash(&arch_hash_ops);
-	return 0;
-}
-early_initcall(hashlib_init);
-- 
cgit v1.2.3-70-g09d2


From 31a171328e870c9f65d01191e51a75cde5f78ffd Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 29 Sep 2014 20:06:43 +0200
Subject: tty: serial: 8250_omap: add custom DMA-TX callback

This patch provides mostly a copy of serial8250_tx_dma() +
__dma_tx_complete() with the following extensions:

- DMA bug
  At least on AM335x the following problem exists: Even if the TX FIFO is
  empty and a TX transfer is programmed (and started) the UART does not
  trigger the DMA transfer.
  After $TRESHOLD number of bytes have been written to the FIFO manually the
  UART reevaluates the whole situation and decides that now there is enough
  room in the FIFO and so the transfer begins.
  This problem has not been seen on DRA7 or beagle board xm (OMAP3). I am not
  sure if this is UART-IP core specific or DMA engine.

  The workaround is to use a threshold of one byte, program the DMA
  transfer minus one byte and then to put the first byte into the FIFO to
  kick start the transfer.

- support for runtime PM
  RPM is enabled on start_tx(). We can't disable RPM on DMA complete callback
  because there is still data in the FIFO which is being sent. We have to wait
  until the FIFO is empty before we disable it.
  For this to happen we fake a TX sent error and enable THRI. Once the
  FIFO is empty we receive an interrupt and since the TTY-buffer is still
  empty we "put RPM" via __stop_tx(). Should it been filed then in the
  start_tx() path we should program the DMA transfer and remove the error
  flag and the THRI bit.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_omap.c | 144 ++++++++++++++++++++++++++++++++++++
 include/uapi/linux/serial_reg.h     |   1 +
 2 files changed, 145 insertions(+)

(limited to 'include')

diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index 2f653c48639..5f183d197df 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -22,6 +22,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/console.h>
 #include <linux/pm_qos.h>
+#include <linux/dma-mapping.h>
 
 #include "8250.h"
 
@@ -29,6 +30,7 @@
 
 #define UART_ERRATA_i202_MDR1_ACCESS	(1 << 0)
 #define OMAP_UART_WER_HAS_TX_WAKEUP	(1 << 1)
+#define OMAP_DMA_TX_KICK		(1 << 2)
 
 #define OMAP_UART_FCR_RX_TRIG		6
 #define OMAP_UART_FCR_TX_TRIG		4
@@ -616,6 +618,148 @@ static void omap_8250_unthrottle(struct uart_port *port)
 	pm_runtime_put_autosuspend(port->dev);
 }
 
+#ifdef CONFIG_SERIAL_8250_DMA
+static int omap_8250_tx_dma(struct uart_8250_port *p);
+
+static void omap_8250_dma_tx_complete(void *param)
+{
+	struct uart_8250_port	*p = param;
+	struct uart_8250_dma	*dma = p->dma;
+	struct circ_buf		*xmit = &p->port.state->xmit;
+	unsigned long		flags;
+	bool			en_thri = false;
+
+	dma_sync_single_for_cpu(dma->txchan->device->dev, dma->tx_addr,
+				UART_XMIT_SIZE, DMA_TO_DEVICE);
+
+	spin_lock_irqsave(&p->port.lock, flags);
+
+	dma->tx_running = 0;
+
+	xmit->tail += dma->tx_size;
+	xmit->tail &= UART_XMIT_SIZE - 1;
+	p->port.icount.tx += dma->tx_size;
+
+	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
+		uart_write_wakeup(&p->port);
+
+	if (!uart_circ_empty(xmit) && !uart_tx_stopped(&p->port)) {
+		int ret;
+
+		ret = omap_8250_tx_dma(p);
+		if (ret)
+			en_thri = true;
+
+	} else if (p->capabilities & UART_CAP_RPM) {
+		en_thri = true;
+	}
+
+	if (en_thri) {
+		dma->tx_err = 1;
+		p->ier |= UART_IER_THRI;
+		serial_port_out(&p->port, UART_IER, p->ier);
+	}
+
+	spin_unlock_irqrestore(&p->port.lock, flags);
+}
+
+static int omap_8250_tx_dma(struct uart_8250_port *p)
+{
+	struct uart_8250_dma		*dma = p->dma;
+	struct omap8250_priv		*priv = p->port.private_data;
+	struct circ_buf			*xmit = &p->port.state->xmit;
+	struct dma_async_tx_descriptor	*desc;
+	unsigned int	skip_byte = 0;
+	int ret;
+
+	if (dma->tx_running)
+		return 0;
+	if (uart_tx_stopped(&p->port) || uart_circ_empty(xmit)) {
+
+		/*
+		 * Even if no data, we need to return an error for the two cases
+		 * below so serial8250_tx_chars() is invoked and properly clears
+		 * THRI and/or runtime suspend.
+		 */
+		if (dma->tx_err || p->capabilities & UART_CAP_RPM) {
+			ret = -EBUSY;
+			goto err;
+		}
+		if (p->ier & UART_IER_THRI) {
+			p->ier &= ~UART_IER_THRI;
+			serial_out(p, UART_IER, p->ier);
+		}
+		return 0;
+	}
+
+	dma->tx_size = CIRC_CNT_TO_END(xmit->head, xmit->tail, UART_XMIT_SIZE);
+	if (priv->habit & OMAP_DMA_TX_KICK) {
+		u8 tx_lvl;
+
+		/*
+		 * We need to put the first byte into the FIFO in order to start
+		 * the DMA transfer. For transfers smaller than four bytes we
+		 * don't bother doing DMA at all. It seem not matter if there
+		 * are still bytes in the FIFO from the last transfer (in case
+		 * we got here directly from omap_8250_dma_tx_complete()). Bytes
+		 * leaving the FIFO seem not to trigger the DMA transfer. It is
+		 * really the byte that we put into the FIFO.
+		 * If the FIFO is already full then we most likely got here from
+		 * omap_8250_dma_tx_complete(). And this means the DMA engine
+		 * just completed its work. We don't have to wait the complete
+		 * 86us at 115200,8n1 but around 60us (not to mention lower
+		 * baudrates). So in that case we take the interrupt and try
+		 * again with an empty FIFO.
+		 */
+		tx_lvl = serial_in(p, UART_OMAP_TX_LVL);
+		if (tx_lvl == p->tx_loadsz) {
+			ret = -EBUSY;
+			goto err;
+		}
+		if (dma->tx_size < 4) {
+			ret = -EINVAL;
+			goto err;
+		}
+		skip_byte = 1;
+	}
+
+	desc = dmaengine_prep_slave_single(dma->txchan,
+			dma->tx_addr + xmit->tail + skip_byte,
+			dma->tx_size - skip_byte, DMA_MEM_TO_DEV,
+			DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!desc) {
+		ret = -EBUSY;
+		goto err;
+	}
+
+	dma->tx_running = 1;
+
+	desc->callback = omap_8250_dma_tx_complete;
+	desc->callback_param = p;
+
+	dma->tx_cookie = dmaengine_submit(desc);
+
+	dma_sync_single_for_device(dma->txchan->device->dev, dma->tx_addr,
+				   UART_XMIT_SIZE, DMA_TO_DEVICE);
+
+	dma_async_issue_pending(dma->txchan);
+	if (dma->tx_err)
+		dma->tx_err = 0;
+
+	if (p->ier & UART_IER_THRI) {
+		p->ier &= ~UART_IER_THRI;
+		serial_out(p, UART_IER, p->ier);
+	}
+	if (skip_byte)
+		serial_out(p, UART_TX, xmit->buf[xmit->tail]);
+	return 0;
+err:
+	dma->tx_err = 1;
+	return ret;
+}
+
+#endif
+
 static int omap8250_probe(struct platform_device *pdev)
 {
 	struct resource *regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/include/uapi/linux/serial_reg.h b/include/uapi/linux/serial_reg.h
index df6c9ab6b0c..53af3b79012 100644
--- a/include/uapi/linux/serial_reg.h
+++ b/include/uapi/linux/serial_reg.h
@@ -359,6 +359,7 @@
 #define UART_OMAP_SYSC		0x15	/* System configuration register */
 #define UART_OMAP_SYSS		0x16	/* System status register */
 #define UART_OMAP_WER		0x17	/* Wake-up enable register */
+#define UART_OMAP_TX_LVL	0x1a	/* TX FIFO level register */
 
 /*
  * These are the definitions for the MDR1 register
-- 
cgit v1.2.3-70-g09d2


From 1d597e7c266658697843352c5c030e20f48c6230 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 5 Nov 2014 12:26:26 -0500
Subject: tty: Remove defunct pcxe_open() declaration

pcxe_open() has no definition in mainline; remove declaration.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index f6835ea1079..97cfb3108e2 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -621,10 +621,6 @@ extern long n_tty_compat_ioctl_helper(struct tty_struct *tty, struct file *file,
 
 extern void serial_console_init(void);
 
-/* pcxx.c */
-
-extern int pcxe_open(struct tty_struct *tty, struct file *filp);
-
 /* vt.c */
 
 extern int vt_ioctl(struct tty_struct *tty,
-- 
cgit v1.2.3-70-g09d2


From b9104f5cec3b7d8fb4068bce5ddc8240dc7b81f7 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 5 Nov 2014 12:26:27 -0500
Subject: tty: Remove defunct serial_console_init() declaration

serial_console_init() is not defined by the tty core; remove
declaration.

Note that the powerpc arch boot code contains a serial_console_init()
declaration in arch/powerpc/boot/ops.h which is restricted to
the powerpc arch boot.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 97cfb3108e2..c52a689e09a 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -617,10 +617,6 @@ extern int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file,
 extern long n_tty_compat_ioctl_helper(struct tty_struct *tty, struct file *file,
 		       unsigned int cmd, unsigned long arg);
 
-/* serial.c */
-
-extern void serial_console_init(void);
-
 /* vt.c */
 
 extern int vt_ioctl(struct tty_struct *tty,
-- 
cgit v1.2.3-70-g09d2


From 5ac9c05d789044d30735402f387355a394ec8e18 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 5 Nov 2014 12:26:30 -0500
Subject: tty: Document defunct ASYNC_SPLIT_TERMIOS flag in uapi header

The last vestige of ASYNC_SPLIT_TERMIOS was removed by commit
'cris: Remove obsolete ASYNC_SPLIT_TERMIOS behavior'. Mark the flag
as defunct in the uapi header.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/tty_flags.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/tty_flags.h b/include/uapi/linux/tty_flags.h
index 4e021e31c21..d2bc4ff94f4 100644
--- a/include/uapi/linux/tty_flags.h
+++ b/include/uapi/linux/tty_flags.h
@@ -14,7 +14,7 @@
 				    * on the callout port */
 #define ASYNCB_FOURPORT		 1 /* Set OU1, OUT2 per AST Fourport settings */
 #define ASYNCB_SAK		 2 /* Secure Attention Key (Orange book) */
-#define ASYNCB_SPLIT_TERMIOS	 3 /* Separate termios for dialin/callout */
+#define ASYNCB_SPLIT_TERMIOS	 3 /* [x] Separate termios for dialin/callout */
 #define ASYNCB_SPD_HI		 4 /* Use 56000 instead of 38400 bps */
 #define ASYNCB_SPD_VHI		 5 /* Use 115200 instead of 38400 bps */
 #define ASYNCB_SKIP_TEST	 6 /* Skip UART test during autoconfiguration */
-- 
cgit v1.2.3-70-g09d2


From 68952076e9226cc23ebce66d3fc2fdb8b6c04c30 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 5 Nov 2014 12:26:31 -0500
Subject: vt: Remove vt_get_kmsg_redirect() from uapi header

vt_get_kmsg_redirect() only has meaning to the console driver as
an alias for calling vt_kmsg_redirect(). Move the macro definition
to the only source file which uses it; remove from uapi/linux/vt.h

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/vt.c     | 2 ++
 include/uapi/linux/vt.h | 3 ---
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index b33b00b386d..3dc5d56261a 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -2509,6 +2509,8 @@ int vt_kmsg_redirect(int new)
 		return kmsg_con;
 }
 
+#define vt_get_kmsg_redirect() vt_kmsg_redirect(-1)
+
 /*
  *	Console on virtual terminal
  *
diff --git a/include/uapi/linux/vt.h b/include/uapi/linux/vt.h
index 4b59a26799a..978578bd189 100644
--- a/include/uapi/linux/vt.h
+++ b/include/uapi/linux/vt.h
@@ -84,7 +84,4 @@ struct vt_setactivate {
 
 #define VT_SETACTIVATE	0x560F	/* Activate and set the mode of a console */
 
-
-#define vt_get_kmsg_redirect() vt_kmsg_redirect(-1)
-
 #endif /* _UAPI_LINUX_VT_H */
-- 
cgit v1.2.3-70-g09d2


From e1f7c9eee70730d7e6ec77f7ecc76f936e262cf0 Mon Sep 17 00:00:00 2001
From: Ludovic Desroches <ludovic.desroches@atmel.com>
Date: Wed, 22 Oct 2014 17:22:18 +0200
Subject: dmaengine: at_xdmac: creation of the atmel eXtended DMA Controller
 driver

New atmel DMA controller known as XDMAC, introduced with SAMA5D4
devices.

Signed-off-by: Ludovic Desroches <ludovic.desroches@atmel.com>
Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 drivers/dma/Kconfig            |    7 +
 drivers/dma/Makefile           |    1 +
 drivers/dma/at_xdmac.c         | 1510 ++++++++++++++++++++++++++++++++++++++++
 include/dt-bindings/dma/at91.h |   25 +
 4 files changed, 1543 insertions(+)
 create mode 100644 drivers/dma/at_xdmac.c

(limited to 'include')

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index de469821bc1..607271a999a 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -107,6 +107,13 @@ config AT_HDMAC
 	help
 	  Support the Atmel AHB DMA controller.
 
+config AT_XDMAC
+	tristate "Atmel XDMA support"
+	depends on (ARCH_AT91 || COMPILE_TEST)
+	select DMA_ENGINE
+	help
+	  Support the Atmel XDMA controller.
+
 config FSL_DMA
 	tristate "Freescale Elo series DMA support"
 	depends on FSL_SOC
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index cb626c17991..2022b545137 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_PPC_BESTCOMM) += bestcomm/
 obj-$(CONFIG_MV_XOR) += mv_xor.o
 obj-$(CONFIG_DW_DMAC_CORE) += dw/
 obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
+obj-$(CONFIG_AT_XDMAC) += at_xdmac.o
 obj-$(CONFIG_MX3_IPU) += ipu/
 obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
 obj-$(CONFIG_SH_DMAE_BASE) += sh/
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
new file mode 100644
index 00000000000..4e9b023990a
--- /dev/null
+++ b/drivers/dma/at_xdmac.c
@@ -0,0 +1,1510 @@
+/*
+ * Driver for the Atmel Extensible DMA Controller (aka XDMAC on AT91 systems)
+ *
+ * Copyright (C) 2014 Atmel Corporation
+ *
+ * Author: Ludovic Desroches <ludovic.desroches@atmel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <asm/barrier.h>
+#include <dt-bindings/dma/at91.h>
+#include <linux/clk.h>
+#include <linux/dmaengine.h>
+#include <linux/dmapool.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/of_dma.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+
+#include "dmaengine.h"
+
+/* Global registers */
+#define AT_XDMAC_GTYPE		0x00	/* Global Type Register */
+#define		AT_XDMAC_NB_CH(i)	(((i) & 0x1F) + 1)		/* Number of Channels Minus One */
+#define		AT_XDMAC_FIFO_SZ(i)	(((i) >> 5) & 0x7FF)		/* Number of Bytes */
+#define		AT_XDMAC_NB_REQ(i)	((((i) >> 16) & 0x3F) + 1)	/* Number of Peripheral Requests Minus One */
+#define AT_XDMAC_GCFG		0x04	/* Global Configuration Register */
+#define AT_XDMAC_GWAC		0x08	/* Global Weighted Arbiter Configuration Register */
+#define AT_XDMAC_GIE		0x0C	/* Global Interrupt Enable Register */
+#define AT_XDMAC_GID		0x10	/* Global Interrupt Disable Register */
+#define AT_XDMAC_GIM		0x14	/* Global Interrupt Mask Register */
+#define AT_XDMAC_GIS		0x18	/* Global Interrupt Status Register */
+#define AT_XDMAC_GE		0x1C	/* Global Channel Enable Register */
+#define AT_XDMAC_GD		0x20	/* Global Channel Disable Register */
+#define AT_XDMAC_GS		0x24	/* Global Channel Status Register */
+#define AT_XDMAC_GRS		0x28	/* Global Channel Read Suspend Register */
+#define AT_XDMAC_GWS		0x2C	/* Global Write Suspend Register */
+#define AT_XDMAC_GRWS		0x30	/* Global Channel Read Write Suspend Register */
+#define AT_XDMAC_GRWR		0x34	/* Global Channel Read Write Resume Register */
+#define AT_XDMAC_GSWR		0x38	/* Global Channel Software Request Register */
+#define AT_XDMAC_GSWS		0x3C	/* Global channel Software Request Status Register */
+#define AT_XDMAC_GSWF		0x40	/* Global Channel Software Flush Request Register */
+#define AT_XDMAC_VERSION	0xFFC	/* XDMAC Version Register */
+
+/* Channel relative registers offsets */
+#define AT_XDMAC_CIE		0x00	/* Channel Interrupt Enable Register */
+#define		AT_XDMAC_CIE_BIE	BIT(0)	/* End of Block Interrupt Enable Bit */
+#define		AT_XDMAC_CIE_LIE	BIT(1)	/* End of Linked List Interrupt Enable Bit */
+#define		AT_XDMAC_CIE_DIE	BIT(2)	/* End of Disable Interrupt Enable Bit */
+#define		AT_XDMAC_CIE_FIE	BIT(3)	/* End of Flush Interrupt Enable Bit */
+#define		AT_XDMAC_CIE_RBEIE	BIT(4)	/* Read Bus Error Interrupt Enable Bit */
+#define		AT_XDMAC_CIE_WBEIE	BIT(5)	/* Write Bus Error Interrupt Enable Bit */
+#define		AT_XDMAC_CIE_ROIE	BIT(6)	/* Request Overflow Interrupt Enable Bit */
+#define AT_XDMAC_CID		0x04	/* Channel Interrupt Disable Register */
+#define		AT_XDMAC_CID_BID	BIT(0)	/* End of Block Interrupt Disable Bit */
+#define		AT_XDMAC_CID_LID	BIT(1)	/* End of Linked List Interrupt Disable Bit */
+#define		AT_XDMAC_CID_DID	BIT(2)	/* End of Disable Interrupt Disable Bit */
+#define		AT_XDMAC_CID_FID	BIT(3)	/* End of Flush Interrupt Disable Bit */
+#define		AT_XDMAC_CID_RBEID	BIT(4)	/* Read Bus Error Interrupt Disable Bit */
+#define		AT_XDMAC_CID_WBEID	BIT(5)	/* Write Bus Error Interrupt Disable Bit */
+#define		AT_XDMAC_CID_ROID	BIT(6)	/* Request Overflow Interrupt Disable Bit */
+#define AT_XDMAC_CIM		0x08	/* Channel Interrupt Mask Register */
+#define		AT_XDMAC_CIM_BIM	BIT(0)	/* End of Block Interrupt Mask Bit */
+#define		AT_XDMAC_CIM_LIM	BIT(1)	/* End of Linked List Interrupt Mask Bit */
+#define		AT_XDMAC_CIM_DIM	BIT(2)	/* End of Disable Interrupt Mask Bit */
+#define		AT_XDMAC_CIM_FIM	BIT(3)	/* End of Flush Interrupt Mask Bit */
+#define		AT_XDMAC_CIM_RBEIM	BIT(4)	/* Read Bus Error Interrupt Mask Bit */
+#define		AT_XDMAC_CIM_WBEIM	BIT(5)	/* Write Bus Error Interrupt Mask Bit */
+#define		AT_XDMAC_CIM_ROIM	BIT(6)	/* Request Overflow Interrupt Mask Bit */
+#define AT_XDMAC_CIS		0x0C	/* Channel Interrupt Status Register */
+#define		AT_XDMAC_CIS_BIS	BIT(0)	/* End of Block Interrupt Status Bit */
+#define		AT_XDMAC_CIS_LIS	BIT(1)	/* End of Linked List Interrupt Status Bit */
+#define		AT_XDMAC_CIS_DIS	BIT(2)	/* End of Disable Interrupt Status Bit */
+#define		AT_XDMAC_CIS_FIS	BIT(3)	/* End of Flush Interrupt Status Bit */
+#define		AT_XDMAC_CIS_RBEIS	BIT(4)	/* Read Bus Error Interrupt Status Bit */
+#define		AT_XDMAC_CIS_WBEIS	BIT(5)	/* Write Bus Error Interrupt Status Bit */
+#define		AT_XDMAC_CIS_ROIS	BIT(6)	/* Request Overflow Interrupt Status Bit */
+#define AT_XDMAC_CSA		0x10	/* Channel Source Address Register */
+#define AT_XDMAC_CDA		0x14	/* Channel Destination Address Register */
+#define AT_XDMAC_CNDA		0x18	/* Channel Next Descriptor Address Register */
+#define		AT_XDMAC_CNDA_NDAIF(i)	((i) & 0x1)			/* Channel x Next Descriptor Interface */
+#define		AT_XDMAC_CNDA_NDA(i)	((i) & 0xfffffffc)		/* Channel x Next Descriptor Address */
+#define AT_XDMAC_CNDC		0x1C	/* Channel Next Descriptor Control Register */
+#define		AT_XDMAC_CNDC_NDE		(0x1 << 0)		/* Channel x Next Descriptor Enable */
+#define		AT_XDMAC_CNDC_NDSUP		(0x1 << 1)		/* Channel x Next Descriptor Source Update */
+#define		AT_XDMAC_CNDC_NDDUP		(0x1 << 2)		/* Channel x Next Descriptor Destination Update */
+#define		AT_XDMAC_CNDC_NDVIEW_NDV0	(0x0 << 3)		/* Channel x Next Descriptor View 0 */
+#define		AT_XDMAC_CNDC_NDVIEW_NDV1	(0x1 << 3)		/* Channel x Next Descriptor View 1 */
+#define		AT_XDMAC_CNDC_NDVIEW_NDV2	(0x2 << 3)		/* Channel x Next Descriptor View 2 */
+#define		AT_XDMAC_CNDC_NDVIEW_NDV3	(0x3 << 3)		/* Channel x Next Descriptor View 3 */
+#define AT_XDMAC_CUBC		0x20	/* Channel Microblock Control Register */
+#define AT_XDMAC_CBC		0x24	/* Channel Block Control Register */
+#define AT_XDMAC_CC		0x28	/* Channel Configuration Register */
+#define		AT_XDMAC_CC_TYPE	(0x1 << 0)	/* Channel Transfer Type */
+#define			AT_XDMAC_CC_TYPE_MEM_TRAN	(0x0 << 0)	/* Memory to Memory Transfer */
+#define			AT_XDMAC_CC_TYPE_PER_TRAN	(0x1 << 0)	/* Peripheral to Memory or Memory to Peripheral Transfer */
+#define		AT_XDMAC_CC_MBSIZE_MASK	(0x3 << 1)
+#define			AT_XDMAC_CC_MBSIZE_SINGLE	(0x0 << 1)
+#define			AT_XDMAC_CC_MBSIZE_FOUR		(0x1 << 1)
+#define			AT_XDMAC_CC_MBSIZE_EIGHT	(0x2 << 1)
+#define			AT_XDMAC_CC_MBSIZE_SIXTEEN	(0x3 << 1)
+#define		AT_XDMAC_CC_DSYNC	(0x1 << 4)	/* Channel Synchronization */
+#define			AT_XDMAC_CC_DSYNC_PER2MEM	(0x0 << 4)
+#define			AT_XDMAC_CC_DSYNC_MEM2PER	(0x1 << 4)
+#define		AT_XDMAC_CC_PROT	(0x1 << 5)	/* Channel Protection */
+#define			AT_XDMAC_CC_PROT_SEC		(0x0 << 5)
+#define			AT_XDMAC_CC_PROT_UNSEC		(0x1 << 5)
+#define		AT_XDMAC_CC_SWREQ	(0x1 << 6)	/* Channel Software Request Trigger */
+#define			AT_XDMAC_CC_SWREQ_HWR_CONNECTED	(0x0 << 6)
+#define			AT_XDMAC_CC_SWREQ_SWR_CONNECTED	(0x1 << 6)
+#define		AT_XDMAC_CC_MEMSET	(0x1 << 7)	/* Channel Fill Block of memory */
+#define			AT_XDMAC_CC_MEMSET_NORMAL_MODE	(0x0 << 7)
+#define			AT_XDMAC_CC_MEMSET_HW_MODE	(0x1 << 7)
+#define		AT_XDMAC_CC_CSIZE(i)	((0x7 & (i)) << 8)	/* Channel Chunk Size */
+#define		AT_XDMAC_CC_DWIDTH_OFFSET	11
+#define		AT_XDMAC_CC_DWIDTH_MASK	(0x3 << AT_XDMAC_CC_DWIDTH_OFFSET)
+#define		AT_XDMAC_CC_DWIDTH(i)	((0x3 & (i)) << AT_XDMAC_CC_DWIDTH_OFFSET)	/* Channel Data Width */
+#define			AT_XDMAC_CC_DWIDTH_BYTE		0x0
+#define			AT_XDMAC_CC_DWIDTH_HALFWORD	0x1
+#define			AT_XDMAC_CC_DWIDTH_WORD		0x2
+#define			AT_XDMAC_CC_DWIDTH_DWORD	0x3
+#define		AT_XDMAC_CC_SIF(i)	((0x1 & (i)) << 13)	/* Channel Source Interface Identifier */
+#define		AT_XDMAC_CC_DIF(i)	((0x1 & (i)) << 14)	/* Channel Destination Interface Identifier */
+#define		AT_XDMAC_CC_SAM_MASK	(0x3 << 16)	/* Channel Source Addressing Mode */
+#define			AT_XDMAC_CC_SAM_FIXED_AM	(0x0 << 16)
+#define			AT_XDMAC_CC_SAM_INCREMENTED_AM	(0x1 << 16)
+#define			AT_XDMAC_CC_SAM_UBS_AM		(0x2 << 16)
+#define			AT_XDMAC_CC_SAM_UBS_DS_AM	(0x3 << 16)
+#define		AT_XDMAC_CC_DAM_MASK	(0x3 << 18)	/* Channel Source Addressing Mode */
+#define			AT_XDMAC_CC_DAM_FIXED_AM	(0x0 << 18)
+#define			AT_XDMAC_CC_DAM_INCREMENTED_AM	(0x1 << 18)
+#define			AT_XDMAC_CC_DAM_UBS_AM		(0x2 << 18)
+#define			AT_XDMAC_CC_DAM_UBS_DS_AM	(0x3 << 18)
+#define		AT_XDMAC_CC_INITD	(0x1 << 21)	/* Channel Initialization Terminated (read only) */
+#define			AT_XDMAC_CC_INITD_TERMINATED	(0x0 << 21)
+#define			AT_XDMAC_CC_INITD_IN_PROGRESS	(0x1 << 21)
+#define		AT_XDMAC_CC_RDIP	(0x1 << 22)	/* Read in Progress (read only) */
+#define			AT_XDMAC_CC_RDIP_DONE		(0x0 << 22)
+#define			AT_XDMAC_CC_RDIP_IN_PROGRESS	(0x1 << 22)
+#define		AT_XDMAC_CC_WRIP	(0x1 << 23)	/* Write in Progress (read only) */
+#define			AT_XDMAC_CC_WRIP_DONE		(0x0 << 23)
+#define			AT_XDMAC_CC_WRIP_IN_PROGRESS	(0x1 << 23)
+#define		AT_XDMAC_CC_PERID(i)	(0x7f & (h) << 24)	/* Channel Peripheral Identifier */
+#define AT_XDMAC_CDS_MSP	0x2C	/* Channel Data Stride Memory Set Pattern */
+#define AT_XDMAC_CSUS		0x30	/* Channel Source Microblock Stride */
+#define AT_XDMAC_CDUS		0x34	/* Channel Destination Microblock Stride */
+
+#define AT_XDMAC_CHAN_REG_BASE	0x50	/* Channel registers base address */
+
+/* Microblock control members */
+#define AT_XDMAC_MBR_UBC_UBLEN_MAX	0xFFFFFFUL	/* Maximum Microblock Length */
+#define AT_XDMAC_MBR_UBC_NDE		(0x1 << 24)	/* Next Descriptor Enable */
+#define AT_XDMAC_MBR_UBC_NSEN		(0x1 << 25)	/* Next Descriptor Source Update */
+#define AT_XDMAC_MBR_UBC_NDEN		(0x1 << 26)	/* Next Descriptor Destination Update */
+#define AT_XDMAC_MBR_UBC_NDV0		(0x0 << 27)	/* Next Descriptor View 0 */
+#define AT_XDMAC_MBR_UBC_NDV1		(0x1 << 27)	/* Next Descriptor View 1 */
+#define AT_XDMAC_MBR_UBC_NDV2		(0x2 << 27)	/* Next Descriptor View 2 */
+#define AT_XDMAC_MBR_UBC_NDV3		(0x3 << 27)	/* Next Descriptor View 3 */
+
+#define AT_XDMAC_MAX_CHAN	0x20
+
+enum atc_status {
+	AT_XDMAC_CHAN_IS_CYCLIC = 0,
+	AT_XDMAC_CHAN_IS_PAUSED,
+};
+
+/* ----- Channels ----- */
+struct at_xdmac_chan {
+	struct dma_chan			chan;
+	void __iomem			*ch_regs;
+	u32				mask;		/* Channel Mask */
+	u32				cfg[3];		/* Channel Configuration Register */
+	#define	AT_XDMAC_CUR_CFG	0		/* Current channel conf */
+	#define	AT_XDMAC_DEV_TO_MEM_CFG	1		/* Predifined dev to mem channel conf */
+	#define	AT_XDMAC_MEM_TO_DEV_CFG	2		/* Predifined mem to dev channel conf */
+	u8				perid;		/* Peripheral ID */
+	u8				perif;		/* Peripheral Interface */
+	u8				memif;		/* Memory Interface */
+	u32				per_src_addr;
+	u32				per_dst_addr;
+	u32				save_cim;
+	u32				save_cnda;
+	u32				save_cndc;
+	unsigned long			status;
+	struct tasklet_struct		tasklet;
+
+	spinlock_t			lock;
+
+	struct list_head		xfers_list;
+	struct list_head		free_descs_list;
+};
+
+
+/* ----- Controller ----- */
+struct at_xdmac {
+	struct dma_device	dma;
+	void __iomem		*regs;
+	int			irq;
+	struct clk		*clk;
+	u32			save_gim;
+	u32			save_gs;
+	struct dma_pool		*at_xdmac_desc_pool;
+	struct at_xdmac_chan	chan[0];
+};
+
+
+/* ----- Descriptors ----- */
+
+/* Linked List Descriptor */
+struct at_xdmac_lld {
+	dma_addr_t	mbr_nda;	/* Next Descriptor Member */
+	u32		mbr_ubc;	/* Microblock Control Member */
+	dma_addr_t	mbr_sa;		/* Source Address Member */
+	dma_addr_t	mbr_da;		/* Destination Address Member */
+	u32		mbr_cfg;	/* Configuration Register */
+};
+
+
+struct at_xdmac_desc {
+	struct at_xdmac_lld		lld;
+	enum dma_transfer_direction	direction;
+	struct dma_async_tx_descriptor	tx_dma_desc;
+	struct list_head		desc_node;
+	/* Following members are only used by the first descriptor */
+	bool				active_xfer;
+	unsigned int			xfer_size;
+	struct list_head		descs_list;
+	struct list_head		xfer_node;
+};
+
+static inline void __iomem *at_xdmac_chan_reg_base(struct at_xdmac *atxdmac, unsigned int chan_nb)
+{
+	return atxdmac->regs + (AT_XDMAC_CHAN_REG_BASE + chan_nb * 0x40);
+}
+
+#define at_xdmac_read(atxdmac, reg) readl_relaxed((atxdmac)->regs + (reg))
+#define at_xdmac_write(atxdmac, reg, value) \
+	writel_relaxed((value), (atxdmac)->regs + (reg))
+
+#define at_xdmac_chan_read(atchan, reg) readl_relaxed((atchan)->ch_regs + (reg))
+#define at_xdmac_chan_write(atchan, reg, value) writel_relaxed((value), (atchan)->ch_regs + (reg))
+
+static inline struct at_xdmac_chan *to_at_xdmac_chan(struct dma_chan *dchan)
+{
+	return container_of(dchan, struct at_xdmac_chan, chan);
+}
+
+static struct device *chan2dev(struct dma_chan *chan)
+{
+	return &chan->dev->device;
+}
+
+static inline struct at_xdmac *to_at_xdmac(struct dma_device *ddev)
+{
+	return container_of(ddev, struct at_xdmac, dma);
+}
+
+static inline struct at_xdmac_desc *txd_to_at_desc(struct dma_async_tx_descriptor *txd)
+{
+	return container_of(txd, struct at_xdmac_desc, tx_dma_desc);
+}
+
+static inline int at_xdmac_chan_is_cyclic(struct at_xdmac_chan *atchan)
+{
+	return test_bit(AT_XDMAC_CHAN_IS_CYCLIC, &atchan->status);
+}
+
+static inline int at_xdmac_chan_is_paused(struct at_xdmac_chan *atchan)
+{
+	return test_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status);
+}
+
+static inline int at_xdmac_csize(u32 maxburst)
+{
+	int csize;
+
+	csize = ffs(maxburst) - 1;
+	if (csize > 4)
+		csize = -EINVAL;
+
+	return csize;
+};
+
+static inline u8 at_xdmac_get_dwidth(u32 cfg)
+{
+	return (cfg & AT_XDMAC_CC_DWIDTH_MASK) >> AT_XDMAC_CC_DWIDTH_OFFSET;
+};
+
+static unsigned int init_nr_desc_per_channel = 64;
+module_param(init_nr_desc_per_channel, uint, 0644);
+MODULE_PARM_DESC(init_nr_desc_per_channel,
+		 "initial descriptors per channel (default: 64)");
+
+
+static bool at_xdmac_chan_is_enabled(struct at_xdmac_chan *atchan)
+{
+	return at_xdmac_chan_read(atchan, AT_XDMAC_GS) & atchan->mask;
+}
+
+static void at_xdmac_off(struct at_xdmac *atxdmac)
+{
+	at_xdmac_write(atxdmac, AT_XDMAC_GD, -1L);
+
+	/* Wait that all chans are disabled. */
+	while (at_xdmac_read(atxdmac, AT_XDMAC_GS))
+		cpu_relax();
+
+	at_xdmac_write(atxdmac, AT_XDMAC_GID, -1L);
+}
+
+/* Call with lock hold. */
+static void at_xdmac_start_xfer(struct at_xdmac_chan *atchan,
+				struct at_xdmac_desc *first)
+{
+	struct at_xdmac	*atxdmac = to_at_xdmac(atchan->chan.device);
+	u32		reg;
+
+	dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, first);
+
+	if (at_xdmac_chan_is_enabled(atchan))
+		return;
+
+	/* Set transfer as active to not try to start it again. */
+	first->active_xfer = true;
+
+	/* Tell xdmac where to get the first descriptor. */
+	reg = AT_XDMAC_CNDA_NDA(first->tx_dma_desc.phys)
+	      | AT_XDMAC_CNDA_NDAIF(atchan->memif);
+	at_xdmac_chan_write(atchan, AT_XDMAC_CNDA, reg);
+
+	/*
+	 * When doing memory to memory transfer we need to use the next
+	 * descriptor view 2 since some fields of the configuration register
+	 * depend on transfer size and src/dest addresses.
+	 */
+	if (is_slave_direction(first->direction)) {
+		reg = AT_XDMAC_CNDC_NDVIEW_NDV1;
+		if (first->direction == DMA_MEM_TO_DEV)
+			atchan->cfg[AT_XDMAC_CUR_CFG] =
+				atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG];
+		else
+			atchan->cfg[AT_XDMAC_CUR_CFG] =
+				atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG];
+		at_xdmac_chan_write(atchan, AT_XDMAC_CC,
+				    atchan->cfg[AT_XDMAC_CUR_CFG]);
+	} else {
+		/*
+		 * No need to write AT_XDMAC_CC reg, it will be done when the
+		 * descriptor is fecthed.
+		 */
+		reg = AT_XDMAC_CNDC_NDVIEW_NDV2;
+	}
+
+	reg |= AT_XDMAC_CNDC_NDDUP
+	       | AT_XDMAC_CNDC_NDSUP
+	       | AT_XDMAC_CNDC_NDE;
+	at_xdmac_chan_write(atchan, AT_XDMAC_CNDC, reg);
+
+	dev_vdbg(chan2dev(&atchan->chan),
+		 "%s: CC=0x%08x CNDA=0x%08x, CNDC=0x%08x, CSA=0x%08x, CDA=0x%08x, CUBC=0x%08x\n",
+		 __func__, at_xdmac_chan_read(atchan, AT_XDMAC_CC),
+		 at_xdmac_chan_read(atchan, AT_XDMAC_CNDA),
+		 at_xdmac_chan_read(atchan, AT_XDMAC_CNDC),
+		 at_xdmac_chan_read(atchan, AT_XDMAC_CSA),
+		 at_xdmac_chan_read(atchan, AT_XDMAC_CDA),
+		 at_xdmac_chan_read(atchan, AT_XDMAC_CUBC));
+
+	at_xdmac_chan_write(atchan, AT_XDMAC_CID, 0xffffffff);
+	reg = AT_XDMAC_CIE_RBEIE | AT_XDMAC_CIE_WBEIE | AT_XDMAC_CIE_ROIE;
+	/*
+	 * There is no end of list when doing cyclic dma, we need to get
+	 * an interrupt after each periods.
+	 */
+	if (at_xdmac_chan_is_cyclic(atchan))
+		at_xdmac_chan_write(atchan, AT_XDMAC_CIE,
+				    reg | AT_XDMAC_CIE_BIE);
+	else
+		at_xdmac_chan_write(atchan, AT_XDMAC_CIE,
+				    reg | AT_XDMAC_CIE_LIE);
+	at_xdmac_write(atxdmac, AT_XDMAC_GIE, atchan->mask);
+	dev_vdbg(chan2dev(&atchan->chan),
+		 "%s: enable channel (0x%08x)\n", __func__, atchan->mask);
+	wmb();
+	at_xdmac_write(atxdmac, AT_XDMAC_GE, atchan->mask);
+
+	dev_vdbg(chan2dev(&atchan->chan),
+		 "%s: CC=0x%08x CNDA=0x%08x, CNDC=0x%08x, CSA=0x%08x, CDA=0x%08x, CUBC=0x%08x\n",
+		 __func__, at_xdmac_chan_read(atchan, AT_XDMAC_CC),
+		 at_xdmac_chan_read(atchan, AT_XDMAC_CNDA),
+		 at_xdmac_chan_read(atchan, AT_XDMAC_CNDC),
+		 at_xdmac_chan_read(atchan, AT_XDMAC_CSA),
+		 at_xdmac_chan_read(atchan, AT_XDMAC_CDA),
+		 at_xdmac_chan_read(atchan, AT_XDMAC_CUBC));
+
+}
+
+static dma_cookie_t at_xdmac_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct at_xdmac_desc	*desc = txd_to_at_desc(tx);
+	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(tx->chan);
+	dma_cookie_t		cookie;
+
+	spin_lock_bh(&atchan->lock);
+	cookie = dma_cookie_assign(tx);
+
+	dev_vdbg(chan2dev(tx->chan), "%s: atchan 0x%p, add desc 0x%p to xfers_list\n",
+		 __func__, atchan, desc);
+	list_add_tail(&desc->xfer_node, &atchan->xfers_list);
+	if (list_is_singular(&atchan->xfers_list))
+		at_xdmac_start_xfer(atchan, desc);
+
+	spin_unlock_bh(&atchan->lock);
+	return cookie;
+}
+
+static struct at_xdmac_desc *at_xdmac_alloc_desc(struct dma_chan *chan,
+						 gfp_t gfp_flags)
+{
+	struct at_xdmac_desc	*desc;
+	struct at_xdmac		*atxdmac = to_at_xdmac(chan->device);
+	dma_addr_t		phys;
+
+	desc = dma_pool_alloc(atxdmac->at_xdmac_desc_pool, gfp_flags, &phys);
+	if (desc) {
+		memset(desc, 0, sizeof(*desc));
+		INIT_LIST_HEAD(&desc->descs_list);
+		dma_async_tx_descriptor_init(&desc->tx_dma_desc, chan);
+		desc->tx_dma_desc.tx_submit = at_xdmac_tx_submit;
+		desc->tx_dma_desc.phys = phys;
+	}
+
+	return desc;
+}
+
+/* Call must be protected by lock. */
+static struct at_xdmac_desc *at_xdmac_get_desc(struct at_xdmac_chan *atchan)
+{
+	struct at_xdmac_desc *desc;
+
+	if (list_empty(&atchan->free_descs_list)) {
+		desc = at_xdmac_alloc_desc(&atchan->chan, GFP_NOWAIT);
+	} else {
+		desc = list_first_entry(&atchan->free_descs_list,
+					struct at_xdmac_desc, desc_node);
+		list_del(&desc->desc_node);
+		desc->active_xfer = false;
+	}
+
+	return desc;
+}
+
+static struct dma_chan *at_xdmac_xlate(struct of_phandle_args *dma_spec,
+				       struct of_dma *of_dma)
+{
+	struct at_xdmac		*atxdmac = of_dma->of_dma_data;
+	struct at_xdmac_chan	*atchan;
+	struct dma_chan		*chan;
+	struct device		*dev = atxdmac->dma.dev;
+
+	if (dma_spec->args_count != 1) {
+		dev_err(dev, "dma phandler args: bad number of args\n");
+		return NULL;
+	}
+
+	chan = dma_get_any_slave_channel(&atxdmac->dma);
+	if (!chan) {
+		dev_err(dev, "can't get a dma channel\n");
+		return NULL;
+	}
+
+	atchan = to_at_xdmac_chan(chan);
+	atchan->memif = AT91_XDMAC_DT_GET_MEM_IF(dma_spec->args[0]);
+	atchan->perif = AT91_XDMAC_DT_GET_PER_IF(dma_spec->args[0]);
+	atchan->perid = AT91_XDMAC_DT_GET_PERID(dma_spec->args[0]);
+	dev_dbg(dev, "chan dt cfg: memif=%u perif=%u perid=%u\n",
+		 atchan->memif, atchan->perif, atchan->perid);
+
+	return chan;
+}
+
+static int at_xdmac_set_slave_config(struct dma_chan *chan,
+				      struct dma_slave_config *sconfig)
+{
+	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
+	u8 dwidth;
+	int csize;
+
+	atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG] =
+		AT91_XDMAC_DT_PERID(atchan->perid)
+		| AT_XDMAC_CC_DAM_INCREMENTED_AM
+		| AT_XDMAC_CC_SAM_FIXED_AM
+		| AT_XDMAC_CC_DIF(atchan->memif)
+		| AT_XDMAC_CC_SIF(atchan->perif)
+		| AT_XDMAC_CC_SWREQ_HWR_CONNECTED
+		| AT_XDMAC_CC_DSYNC_PER2MEM
+		| AT_XDMAC_CC_MBSIZE_SIXTEEN
+		| AT_XDMAC_CC_TYPE_PER_TRAN;
+	csize = at_xdmac_csize(sconfig->src_maxburst);
+	if (csize < 0) {
+		dev_err(chan2dev(chan), "invalid src maxburst value\n");
+		return -EINVAL;
+	}
+	atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG] |= AT_XDMAC_CC_CSIZE(csize);
+	dwidth = ffs(sconfig->src_addr_width) - 1;
+	atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG] |= AT_XDMAC_CC_DWIDTH(dwidth);
+
+
+	atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG] =
+		AT91_XDMAC_DT_PERID(atchan->perid)
+		| AT_XDMAC_CC_DAM_FIXED_AM
+		| AT_XDMAC_CC_SAM_INCREMENTED_AM
+		| AT_XDMAC_CC_DIF(atchan->perif)
+		| AT_XDMAC_CC_SIF(atchan->memif)
+		| AT_XDMAC_CC_SWREQ_HWR_CONNECTED
+		| AT_XDMAC_CC_DSYNC_MEM2PER
+		| AT_XDMAC_CC_MBSIZE_SIXTEEN
+		| AT_XDMAC_CC_TYPE_PER_TRAN;
+	csize = at_xdmac_csize(sconfig->dst_maxburst);
+	if (csize < 0) {
+		dev_err(chan2dev(chan), "invalid src maxburst value\n");
+		return -EINVAL;
+	}
+	atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG] |= AT_XDMAC_CC_CSIZE(csize);
+	dwidth = ffs(sconfig->dst_addr_width) - 1;
+	atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG] |= AT_XDMAC_CC_DWIDTH(dwidth);
+
+	/* Src and dst addr are needed to configure the link list descriptor. */
+	atchan->per_src_addr = sconfig->src_addr;
+	atchan->per_dst_addr = sconfig->dst_addr;
+
+	dev_dbg(chan2dev(chan),
+		"%s: cfg[dev2mem]=0x%08x, cfg[mem2dev]=0x%08x, per_src_addr=0x%08x, per_dst_addr=0x%08x\n",
+		__func__, atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG],
+		atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG],
+		atchan->per_src_addr, atchan->per_dst_addr);
+
+	return 0;
+}
+
+static struct dma_async_tx_descriptor *
+at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+		       unsigned int sg_len, enum dma_transfer_direction direction,
+		       unsigned long flags, void *context)
+{
+	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
+	struct at_xdmac_desc	*first = NULL, *prev = NULL;
+	struct scatterlist	*sg;
+	int			i;
+	u32			cfg;
+
+	if (!sgl)
+		return NULL;
+
+	if (!is_slave_direction(direction)) {
+		dev_err(chan2dev(chan), "invalid DMA direction\n");
+		return NULL;
+	}
+
+	dev_dbg(chan2dev(chan), "%s: sg_len=%d, dir=%s, flags=0x%lx\n",
+		 __func__, sg_len,
+		 direction == DMA_MEM_TO_DEV ? "to device" : "from device",
+		 flags);
+
+	/* Protect dma_sconfig field that can be modified by set_slave_conf. */
+	spin_lock_bh(&atchan->lock);
+
+	/* Prepare descriptors. */
+	for_each_sg(sgl, sg, sg_len, i) {
+		struct at_xdmac_desc	*desc = NULL;
+		u32			len, mem;
+
+		len = sg_dma_len(sg);
+		mem = sg_dma_address(sg);
+		if (unlikely(!len)) {
+			dev_err(chan2dev(chan), "sg data length is zero\n");
+			spin_unlock_bh(&atchan->lock);
+			return NULL;
+		}
+		dev_dbg(chan2dev(chan), "%s: * sg%d len=%u, mem=0x%08x\n",
+			 __func__, i, len, mem);
+
+		desc = at_xdmac_get_desc(atchan);
+		if (!desc) {
+			dev_err(chan2dev(chan), "can't get descriptor\n");
+			if (first)
+				list_splice_init(&first->descs_list, &atchan->free_descs_list);
+			spin_unlock_bh(&atchan->lock);
+			return NULL;
+		}
+
+		/* Linked list descriptor setup. */
+		if (direction == DMA_DEV_TO_MEM) {
+			desc->lld.mbr_sa = atchan->per_src_addr;
+			desc->lld.mbr_da = mem;
+			cfg = atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG];
+		} else {
+			desc->lld.mbr_sa = mem;
+			desc->lld.mbr_da = atchan->per_dst_addr;
+			cfg = atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG];
+		}
+		desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV1		/* next descriptor view */
+			| AT_XDMAC_MBR_UBC_NDEN				/* next descriptor dst parameter update */
+			| AT_XDMAC_MBR_UBC_NSEN				/* next descriptor src parameter update */
+			| (i == sg_len - 1 ? 0 : AT_XDMAC_MBR_UBC_NDE)	/* descriptor fetch */
+			| len / (1 << at_xdmac_get_dwidth(cfg));	/* microblock length */
+		dev_dbg(chan2dev(chan),
+			 "%s: lld: mbr_sa=0x%08x, mbr_da=0x%08x, mbr_ubc=0x%08x\n",
+			 __func__, desc->lld.mbr_sa, desc->lld.mbr_da, desc->lld.mbr_ubc);
+
+		/* Chain lld. */
+		if (prev) {
+			prev->lld.mbr_nda = desc->tx_dma_desc.phys;
+			dev_dbg(chan2dev(chan),
+				 "%s: chain lld: prev=0x%p, mbr_nda=0x%08x\n",
+				 __func__, prev, prev->lld.mbr_nda);
+		}
+
+		prev = desc;
+		if (!first)
+			first = desc;
+
+		dev_dbg(chan2dev(chan), "%s: add desc 0x%p to descs_list 0x%p\n",
+			 __func__, desc, first);
+		list_add_tail(&desc->desc_node, &first->descs_list);
+	}
+
+	spin_unlock_bh(&atchan->lock);
+
+	first->tx_dma_desc.flags = flags;
+	first->xfer_size = sg_len;
+	first->direction = direction;
+
+	return &first->tx_dma_desc;
+}
+
+static struct dma_async_tx_descriptor *
+at_xdmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
+			 size_t buf_len, size_t period_len,
+			 enum dma_transfer_direction direction,
+			 unsigned long flags)
+{
+	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
+	struct at_xdmac_desc	*first = NULL, *prev = NULL;
+	unsigned int		periods = buf_len / period_len;
+	int			i;
+	u32			cfg;
+
+	dev_dbg(chan2dev(chan), "%s: buf_addr=0x%08x, buf_len=%d, period_len=%d, dir=%s, flags=0x%lx\n",
+		__func__, buf_addr, buf_len, period_len,
+		direction == DMA_MEM_TO_DEV ? "mem2per" : "per2mem", flags);
+
+	if (!is_slave_direction(direction)) {
+		dev_err(chan2dev(chan), "invalid DMA direction\n");
+		return NULL;
+	}
+
+	if (test_and_set_bit(AT_XDMAC_CHAN_IS_CYCLIC, &atchan->status)) {
+		dev_err(chan2dev(chan), "channel currently used\n");
+		return NULL;
+	}
+
+	for (i = 0; i < periods; i++) {
+		struct at_xdmac_desc	*desc = NULL;
+
+		spin_lock_bh(&atchan->lock);
+		desc = at_xdmac_get_desc(atchan);
+		if (!desc) {
+			dev_err(chan2dev(chan), "can't get descriptor\n");
+			if (first)
+				list_splice_init(&first->descs_list, &atchan->free_descs_list);
+			spin_unlock_bh(&atchan->lock);
+			return NULL;
+		}
+		spin_unlock_bh(&atchan->lock);
+		dev_dbg(chan2dev(chan),
+			"%s: desc=0x%p, tx_dma_desc.phys=0x%08x\n",
+			__func__, desc, desc->tx_dma_desc.phys);
+
+		if (direction == DMA_DEV_TO_MEM) {
+			desc->lld.mbr_sa = atchan->per_src_addr;
+			desc->lld.mbr_da = buf_addr + i * period_len;
+			cfg = atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG];
+		} else {
+			desc->lld.mbr_sa = buf_addr + i * period_len;
+			desc->lld.mbr_da = atchan->per_dst_addr;
+			cfg = atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG];
+		};
+		desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV1
+			| AT_XDMAC_MBR_UBC_NDEN
+			| AT_XDMAC_MBR_UBC_NSEN
+			| AT_XDMAC_MBR_UBC_NDE
+			| period_len >> at_xdmac_get_dwidth(cfg);
+
+		dev_dbg(chan2dev(chan),
+			 "%s: lld: mbr_sa=0x%08x, mbr_da=0x%08x, mbr_ubc=0x%08x\n",
+			 __func__, desc->lld.mbr_sa, desc->lld.mbr_da, desc->lld.mbr_ubc);
+
+		/* Chain lld. */
+		if (prev) {
+			prev->lld.mbr_nda = desc->tx_dma_desc.phys;
+			dev_dbg(chan2dev(chan),
+				 "%s: chain lld: prev=0x%p, mbr_nda=0x%08x\n",
+				 __func__, prev, prev->lld.mbr_nda);
+		}
+
+		prev = desc;
+		if (!first)
+			first = desc;
+
+		dev_dbg(chan2dev(chan), "%s: add desc 0x%p to descs_list 0x%p\n",
+			 __func__, desc, first);
+		list_add_tail(&desc->desc_node, &first->descs_list);
+	}
+
+	prev->lld.mbr_nda = first->tx_dma_desc.phys;
+	dev_dbg(chan2dev(chan),
+		"%s: chain lld: prev=0x%p, mbr_nda=0x%08x\n",
+		__func__, prev, prev->lld.mbr_nda);
+	first->tx_dma_desc.flags = flags;
+	first->xfer_size = buf_len;
+	first->direction = direction;
+
+	return &first->tx_dma_desc;
+}
+
+static struct dma_async_tx_descriptor *
+at_xdmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
+			 size_t len, unsigned long flags)
+{
+	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
+	struct at_xdmac_desc	*first = NULL, *prev = NULL;
+	size_t			remaining_size = len, xfer_size = 0, ublen;
+	dma_addr_t		src_addr = src, dst_addr = dest;
+	u32			dwidth;
+	/*
+	 * WARNING: We don't know the direction, it involves we can't
+	 * dynamically set the source and dest interface so we have to use the
+	 * same one. Only interface 0 allows EBI access. Hopefully we can
+	 * access DDR through both ports (at least on SAMA5D4x), so we can use
+	 * the same interface for source and dest, that solves the fact we
+	 * don't know the direction.
+	 */
+	u32			chan_cc = AT_XDMAC_CC_DAM_INCREMENTED_AM
+					| AT_XDMAC_CC_SAM_INCREMENTED_AM
+					| AT_XDMAC_CC_DIF(0)
+					| AT_XDMAC_CC_SIF(0)
+					| AT_XDMAC_CC_MBSIZE_SIXTEEN
+					| AT_XDMAC_CC_TYPE_MEM_TRAN;
+
+	dev_dbg(chan2dev(chan), "%s: src=0x%08x, dest=0x%08x, len=%d, flags=0x%lx\n",
+		__func__, src, dest, len, flags);
+
+	if (unlikely(!len))
+		return NULL;
+
+	/*
+	 * Check address alignment to select the greater data width we can use.
+	 * Some XDMAC implementations don't provide dword transfer, in this
+	 * case selecting dword has the same behavior as selecting word transfers.
+	 */
+	if (!((src_addr | dst_addr) & 7)) {
+		dwidth = AT_XDMAC_CC_DWIDTH_DWORD;
+		dev_dbg(chan2dev(chan), "%s: dwidth: double word\n", __func__);
+	} else if (!((src_addr | dst_addr)  & 3)) {
+		dwidth = AT_XDMAC_CC_DWIDTH_WORD;
+		dev_dbg(chan2dev(chan), "%s: dwidth: word\n", __func__);
+	} else if (!((src_addr | dst_addr) & 1)) {
+		dwidth = AT_XDMAC_CC_DWIDTH_HALFWORD;
+		dev_dbg(chan2dev(chan), "%s: dwidth: half word\n", __func__);
+	} else {
+		dwidth = AT_XDMAC_CC_DWIDTH_BYTE;
+		dev_dbg(chan2dev(chan), "%s: dwidth: byte\n", __func__);
+	}
+
+	/* Prepare descriptors. */
+	while (remaining_size) {
+		struct at_xdmac_desc	*desc = NULL;
+
+		dev_dbg(chan2dev(chan), "%s: remaining_size=%u\n", __func__, remaining_size);
+
+		spin_lock_bh(&atchan->lock);
+		desc = at_xdmac_get_desc(atchan);
+		spin_unlock_bh(&atchan->lock);
+		if (!desc) {
+			dev_err(chan2dev(chan), "can't get descriptor\n");
+			if (first)
+				list_splice_init(&first->descs_list, &atchan->free_descs_list);
+			return NULL;
+		}
+
+		/* Update src and dest addresses. */
+		src_addr += xfer_size;
+		dst_addr += xfer_size;
+
+		if (remaining_size >= AT_XDMAC_MBR_UBC_UBLEN_MAX << dwidth)
+			xfer_size = AT_XDMAC_MBR_UBC_UBLEN_MAX << dwidth;
+		else
+			xfer_size = remaining_size;
+
+		dev_dbg(chan2dev(chan), "%s: xfer_size=%u\n", __func__, xfer_size);
+
+		/* Check remaining length and change data width if needed. */
+		if (!((src_addr | dst_addr | xfer_size) & 7)) {
+			dwidth = AT_XDMAC_CC_DWIDTH_DWORD;
+			dev_dbg(chan2dev(chan), "%s: dwidth: double word\n", __func__);
+		} else if (!((src_addr | dst_addr | xfer_size)  & 3)) {
+			dwidth = AT_XDMAC_CC_DWIDTH_WORD;
+			dev_dbg(chan2dev(chan), "%s: dwidth: word\n", __func__);
+		} else if (!((src_addr | dst_addr | xfer_size) & 1)) {
+			dwidth = AT_XDMAC_CC_DWIDTH_HALFWORD;
+			dev_dbg(chan2dev(chan), "%s: dwidth: half word\n", __func__);
+		} else if ((src_addr | dst_addr | xfer_size) & 1) {
+			dwidth = AT_XDMAC_CC_DWIDTH_BYTE;
+			dev_dbg(chan2dev(chan), "%s: dwidth: byte\n", __func__);
+		}
+		chan_cc |= AT_XDMAC_CC_DWIDTH(dwidth);
+
+		ublen = xfer_size >> dwidth;
+		remaining_size -= xfer_size;
+
+		desc->lld.mbr_sa = src_addr;
+		desc->lld.mbr_da = dst_addr;
+		desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV2
+			| AT_XDMAC_MBR_UBC_NDEN
+			| AT_XDMAC_MBR_UBC_NSEN
+			| (remaining_size ? AT_XDMAC_MBR_UBC_NDE : 0)
+			| ublen;
+		desc->lld.mbr_cfg = chan_cc;
+
+		dev_dbg(chan2dev(chan),
+			 "%s: lld: mbr_sa=0x%08x, mbr_da=0x%08x, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
+			 __func__, desc->lld.mbr_sa, desc->lld.mbr_da, desc->lld.mbr_ubc, desc->lld.mbr_cfg);
+
+		/* Chain lld. */
+		if (prev) {
+			prev->lld.mbr_nda = desc->tx_dma_desc.phys;
+			dev_dbg(chan2dev(chan),
+				 "%s: chain lld: prev=0x%p, mbr_nda=0x%08x\n",
+				 __func__, prev, prev->lld.mbr_nda);
+		}
+
+		prev = desc;
+		if (!first)
+			first = desc;
+
+		dev_dbg(chan2dev(chan), "%s: add desc 0x%p to descs_list 0x%p\n",
+			 __func__, desc, first);
+		list_add_tail(&desc->desc_node, &first->descs_list);
+	}
+
+	first->tx_dma_desc.flags = flags;
+	first->xfer_size = len;
+
+	return &first->tx_dma_desc;
+}
+
+static enum dma_status
+at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
+		struct dma_tx_state *txstate)
+{
+	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
+	struct at_xdmac		*atxdmac = to_at_xdmac(atchan->chan.device);
+	struct at_xdmac_desc	*desc, *_desc;
+	struct list_head	*descs_list;
+	enum dma_status		ret;
+	int			residue;
+	u32			cur_nda;
+	u8			dwidth = at_xdmac_get_dwidth(atchan->cfg[AT_XDMAC_CUR_CFG]);
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_COMPLETE)
+		return ret;
+
+	if (!txstate)
+		return ret;
+
+	spin_lock_bh(&atchan->lock);
+
+	desc = list_first_entry(&atchan->xfers_list, struct at_xdmac_desc, xfer_node);
+
+	/*
+	 * If the transfer has not been started yet, don't need to compute the
+	 * residue, it's the transfer length.
+	 */
+	if (!desc->active_xfer) {
+		dma_set_residue(txstate, desc->xfer_size);
+		return ret;
+	}
+
+	residue = desc->xfer_size;
+	/* Flush FIFO. */
+	at_xdmac_write(atxdmac, AT_XDMAC_GSWF, atchan->mask);
+	while (!(at_xdmac_chan_read(atchan, AT_XDMAC_CIS) & AT_XDMAC_CIS_FIS))
+		cpu_relax();
+
+	cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+	/*
+	 * Remove size of all microblocks already transferred and the current
+	 * one. Then add the remaining size to transfer of the current
+	 * microblock.
+	 */
+	descs_list = &desc->descs_list;
+	list_for_each_entry_safe(desc, _desc, descs_list, desc_node) {
+		residue -= (desc->lld.mbr_ubc & 0xffffff) << dwidth;
+		if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda)
+			break;
+	}
+	residue += at_xdmac_chan_read(atchan, AT_XDMAC_CUBC) << dwidth;
+
+	spin_unlock_bh(&atchan->lock);
+
+	dma_set_residue(txstate, residue);
+
+	dev_dbg(chan2dev(chan),
+		 "%s: desc=0x%p, tx_dma_desc.phys=0x%08x, tx_status=%d, cookie=%d, residue=%d\n",
+		 __func__, desc, desc->tx_dma_desc.phys, ret, cookie, residue);
+
+	return ret;
+}
+
+/* Call must be protected by lock. */
+static void at_xdmac_remove_xfer(struct at_xdmac_chan *atchan,
+				    struct at_xdmac_desc *desc)
+{
+	dev_dbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc);
+
+	/*
+	 * Remove the transfer from the transfer list then move the transfer
+	 * descriptors into the free descriptors list.
+	 */
+	list_del(&desc->xfer_node);
+	list_splice_init(&desc->descs_list, &atchan->free_descs_list);
+}
+
+static void at_xdmac_advance_work(struct at_xdmac_chan *atchan)
+{
+	struct at_xdmac_desc	*desc;
+
+	spin_lock_bh(&atchan->lock);
+
+	/*
+	 * If channel is enabled, do nothing, advance_work will be triggered
+	 * after the interruption.
+	 */
+	if (!at_xdmac_chan_is_enabled(atchan) && !list_empty(&atchan->xfers_list)) {
+		desc = list_first_entry(&atchan->xfers_list,
+					struct at_xdmac_desc,
+					xfer_node);
+		dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc);
+		if (!desc->active_xfer)
+			at_xdmac_start_xfer(atchan, desc);
+	}
+
+	spin_unlock_bh(&atchan->lock);
+}
+
+static void at_xdmac_handle_cyclic(struct at_xdmac_chan *atchan)
+{
+	struct at_xdmac_desc		*desc;
+	struct dma_async_tx_descriptor	*txd;
+
+	desc = list_first_entry(&atchan->xfers_list, struct at_xdmac_desc, xfer_node);
+	txd = &desc->tx_dma_desc;
+
+	if (txd->callback && (txd->flags & DMA_PREP_INTERRUPT))
+		txd->callback(txd->callback_param);
+}
+
+static void at_xdmac_tasklet(unsigned long data)
+{
+	struct at_xdmac_chan	*atchan = (struct at_xdmac_chan *)data;
+	struct at_xdmac_desc	*desc;
+	u32			error_mask;
+
+	dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08lx\n",
+		 __func__, atchan->status);
+
+	error_mask = AT_XDMAC_CIS_RBEIS
+		     | AT_XDMAC_CIS_WBEIS
+		     | AT_XDMAC_CIS_ROIS;
+
+	if (at_xdmac_chan_is_cyclic(atchan)) {
+		at_xdmac_handle_cyclic(atchan);
+	} else if ((atchan->status & AT_XDMAC_CIS_LIS)
+		   || (atchan->status & error_mask)) {
+		struct dma_async_tx_descriptor  *txd;
+
+		if (atchan->status & AT_XDMAC_CIS_RBEIS)
+			dev_err(chan2dev(&atchan->chan), "read bus error!!!");
+		if (atchan->status & AT_XDMAC_CIS_WBEIS)
+			dev_err(chan2dev(&atchan->chan), "write bus error!!!");
+		if (atchan->status & AT_XDMAC_CIS_ROIS)
+			dev_err(chan2dev(&atchan->chan), "request overflow error!!!");
+
+		spin_lock_bh(&atchan->lock);
+		desc = list_first_entry(&atchan->xfers_list,
+					struct at_xdmac_desc,
+					xfer_node);
+		dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc);
+		BUG_ON(!desc->active_xfer);
+
+		txd = &desc->tx_dma_desc;
+
+		at_xdmac_remove_xfer(atchan, desc);
+		spin_unlock_bh(&atchan->lock);
+
+		if (!at_xdmac_chan_is_cyclic(atchan)) {
+			dma_cookie_complete(txd);
+			if (txd->callback && (txd->flags & DMA_PREP_INTERRUPT))
+				txd->callback(txd->callback_param);
+		}
+
+		dma_run_dependencies(txd);
+
+		at_xdmac_advance_work(atchan);
+	}
+}
+
+static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id)
+{
+	struct at_xdmac		*atxdmac = (struct at_xdmac *)dev_id;
+	struct at_xdmac_chan	*atchan;
+	u32			imr, status, pending;
+	u32			chan_imr, chan_status;
+	int			i, ret = IRQ_NONE;
+
+	do {
+		imr = at_xdmac_read(atxdmac, AT_XDMAC_GIM);
+		status = at_xdmac_read(atxdmac, AT_XDMAC_GIS);
+		pending = status & imr;
+
+		dev_vdbg(atxdmac->dma.dev,
+			 "%s: status=0x%08x, imr=0x%08x, pending=0x%08x\n",
+			 __func__, status, imr, pending);
+
+		if (!pending)
+			break;
+
+		/* We have to find which channel has generated the interrupt. */
+		for (i = 0; i < atxdmac->dma.chancnt; i++) {
+			if (!((1 << i) & pending))
+				continue;
+
+			atchan = &atxdmac->chan[i];
+			chan_imr = at_xdmac_chan_read(atchan, AT_XDMAC_CIM);
+			chan_status = at_xdmac_chan_read(atchan, AT_XDMAC_CIS);
+			atchan->status = chan_status & chan_imr;
+			dev_vdbg(atxdmac->dma.dev,
+				 "%s: chan%d: imr=0x%x, status=0x%x\n",
+				 __func__, i, chan_imr, chan_status);
+			dev_vdbg(chan2dev(&atchan->chan),
+				 "%s: CC=0x%08x CNDA=0x%08x, CNDC=0x%08x, CSA=0x%08x, CDA=0x%08x, CUBC=0x%08x\n",
+				 __func__,
+				 at_xdmac_chan_read(atchan, AT_XDMAC_CC),
+				 at_xdmac_chan_read(atchan, AT_XDMAC_CNDA),
+				 at_xdmac_chan_read(atchan, AT_XDMAC_CNDC),
+				 at_xdmac_chan_read(atchan, AT_XDMAC_CSA),
+				 at_xdmac_chan_read(atchan, AT_XDMAC_CDA),
+				 at_xdmac_chan_read(atchan, AT_XDMAC_CUBC));
+
+			if (atchan->status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS))
+				at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask);
+
+			tasklet_schedule(&atchan->tasklet);
+			ret = IRQ_HANDLED;
+		}
+
+	} while (pending);
+
+	return ret;
+}
+
+static void at_xdmac_issue_pending(struct dma_chan *chan)
+{
+	struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan);
+
+	dev_dbg(chan2dev(&atchan->chan), "%s\n", __func__);
+
+	if (!at_xdmac_chan_is_cyclic(atchan))
+		at_xdmac_advance_work(atchan);
+
+	return;
+}
+
+static int at_xdmac_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+			    unsigned long arg)
+{
+	struct at_xdmac_desc	*desc, *_desc;
+	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
+	struct at_xdmac		*atxdmac = to_at_xdmac(atchan->chan.device);
+	int			ret = 0;
+
+	dev_dbg(chan2dev(chan), "%s: cmd=%d\n", __func__, cmd);
+
+	spin_lock_bh(&atchan->lock);
+
+	switch (cmd) {
+	case DMA_PAUSE:
+		at_xdmac_write(atxdmac, AT_XDMAC_GRWS, atchan->mask);
+		set_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status);
+		break;
+
+	case DMA_RESUME:
+		if (!at_xdmac_chan_is_paused(atchan))
+			break;
+
+		at_xdmac_write(atxdmac, AT_XDMAC_GRWR, atchan->mask);
+		clear_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status);
+		break;
+
+	case DMA_TERMINATE_ALL:
+		at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask);
+		while (at_xdmac_read(atxdmac, AT_XDMAC_GS) & atchan->mask)
+			cpu_relax();
+
+		/* Cancel all pending transfers. */
+		list_for_each_entry_safe(desc, _desc, &atchan->xfers_list, xfer_node)
+			at_xdmac_remove_xfer(atchan, desc);
+
+		clear_bit(AT_XDMAC_CHAN_IS_CYCLIC, &atchan->status);
+		break;
+
+	case DMA_SLAVE_CONFIG:
+		ret = at_xdmac_set_slave_config(chan,
+				(struct dma_slave_config *)arg);
+		break;
+
+	default:
+		dev_err(chan2dev(chan),
+			"unmanaged or unknown dma control cmd: %d\n", cmd);
+		ret = -ENXIO;
+	}
+
+	spin_unlock_bh(&atchan->lock);
+
+	return ret;
+}
+
+static int at_xdmac_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
+	struct at_xdmac_desc	*desc;
+	int			i;
+
+	spin_lock_bh(&atchan->lock);
+
+	if (at_xdmac_chan_is_enabled(atchan)) {
+		dev_err(chan2dev(chan),
+			"can't allocate channel resources (channel enabled)\n");
+		i = -EIO;
+		goto spin_unlock;
+	}
+
+	if (!list_empty(&atchan->free_descs_list)) {
+		dev_err(chan2dev(chan),
+			"can't allocate channel resources (channel not free from a previous use)\n");
+		i = -EIO;
+		goto spin_unlock;
+	}
+
+	for (i = 0; i < init_nr_desc_per_channel; i++) {
+		desc = at_xdmac_alloc_desc(chan, GFP_ATOMIC);
+		if (!desc) {
+			dev_warn(chan2dev(chan),
+				"only %d descriptors have been allocated\n", i);
+			break;
+		}
+		list_add_tail(&desc->desc_node, &atchan->free_descs_list);
+	}
+
+	dma_cookie_init(chan);
+
+	dev_dbg(chan2dev(chan), "%s: allocated %d descriptors\n", __func__, i);
+
+spin_unlock:
+	spin_unlock_bh(&atchan->lock);
+	return i;
+}
+
+static void at_xdmac_free_chan_resources(struct dma_chan *chan)
+{
+	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
+	struct at_xdmac		*atxdmac = to_at_xdmac(chan->device);
+	struct at_xdmac_desc	*desc, *_desc;
+
+	list_for_each_entry_safe(desc, _desc, &atchan->free_descs_list, desc_node) {
+		dev_dbg(chan2dev(chan), "%s: freeing descriptor %p\n", __func__, desc);
+		list_del(&desc->desc_node);
+		dma_pool_free(atxdmac->at_xdmac_desc_pool, desc, desc->tx_dma_desc.phys);
+	}
+
+	return;
+}
+
+#define AT_XDMAC_DMA_BUSWIDTHS\
+	(BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\
+	BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) |\
+	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |\
+	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) |\
+	BIT(DMA_SLAVE_BUSWIDTH_8_BYTES))
+
+static int at_xdmac_device_slave_caps(struct dma_chan *dchan,
+				      struct dma_slave_caps *caps)
+{
+
+	caps->src_addr_widths = AT_XDMAC_DMA_BUSWIDTHS;
+	caps->dstn_addr_widths = AT_XDMAC_DMA_BUSWIDTHS;
+	caps->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	caps->cmd_pause = true;
+	caps->cmd_terminate = true;
+	caps->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int atmel_xdmac_prepare(struct device *dev)
+{
+	struct platform_device	*pdev = to_platform_device(dev);
+	struct at_xdmac		*atxdmac = platform_get_drvdata(pdev);
+	struct dma_chan		*chan, *_chan;
+
+	list_for_each_entry_safe(chan, _chan, &atxdmac->dma.channels, device_node) {
+		struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
+
+		/* Wait for transfer completion, except in cyclic case. */
+		if (at_xdmac_chan_is_enabled(atchan) && !at_xdmac_chan_is_cyclic(atchan))
+			return -EAGAIN;
+	}
+	return 0;
+}
+#else
+#	define atmel_xdmac_prepare NULL
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+static int atmel_xdmac_suspend(struct device *dev)
+{
+	struct platform_device	*pdev = to_platform_device(dev);
+	struct at_xdmac		*atxdmac = platform_get_drvdata(pdev);
+	struct dma_chan		*chan, *_chan;
+
+	list_for_each_entry_safe(chan, _chan, &atxdmac->dma.channels, device_node) {
+		struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
+
+		if (at_xdmac_chan_is_cyclic(atchan)) {
+			if (!at_xdmac_chan_is_paused(atchan))
+				at_xdmac_control(chan, DMA_PAUSE, 0);
+			atchan->save_cim = at_xdmac_chan_read(atchan, AT_XDMAC_CIM);
+			atchan->save_cnda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA);
+			atchan->save_cndc = at_xdmac_chan_read(atchan, AT_XDMAC_CNDC);
+		}
+	}
+	atxdmac->save_gim = at_xdmac_read(atxdmac, AT_XDMAC_GIM);
+
+	at_xdmac_off(atxdmac);
+	clk_disable_unprepare(atxdmac->clk);
+	return 0;
+}
+
+static int atmel_xdmac_resume(struct device *dev)
+{
+	struct platform_device	*pdev = to_platform_device(dev);
+	struct at_xdmac		*atxdmac = platform_get_drvdata(pdev);
+	struct at_xdmac_chan	*atchan;
+	struct dma_chan		*chan, *_chan;
+	int			i;
+	u32			cfg;
+
+	clk_prepare_enable(atxdmac->clk);
+
+	/* Clear pending interrupts. */
+	for (i = 0; i < atxdmac->dma.chancnt; i++) {
+		atchan = &atxdmac->chan[i];
+		while (at_xdmac_chan_read(atchan, AT_XDMAC_CIS))
+			cpu_relax();
+	}
+
+	at_xdmac_write(atxdmac, AT_XDMAC_GIE, atxdmac->save_gim);
+	at_xdmac_write(atxdmac, AT_XDMAC_GE, atxdmac->save_gs);
+	list_for_each_entry_safe(chan, _chan, &atxdmac->dma.channels, device_node) {
+		atchan = to_at_xdmac_chan(chan);
+		cfg = atchan->cfg[AT_XDMAC_CUR_CFG];
+		at_xdmac_chan_write(atchan, AT_XDMAC_CC, cfg);
+		if (at_xdmac_chan_is_cyclic(atchan)) {
+			at_xdmac_chan_write(atchan, AT_XDMAC_CNDA, atchan->save_cnda);
+			at_xdmac_chan_write(atchan, AT_XDMAC_CNDC, atchan->save_cndc);
+			at_xdmac_chan_write(atchan, AT_XDMAC_CIE, atchan->save_cim);
+			wmb();
+			at_xdmac_write(atxdmac, AT_XDMAC_GE, atchan->mask);
+		}
+	}
+	return 0;
+}
+#endif /* CONFIG_PM_SLEEP */
+
+static int at_xdmac_probe(struct platform_device *pdev)
+{
+	struct resource	*res;
+	struct at_xdmac	*atxdmac;
+	int		irq, size, nr_channels, i, ret;
+	void __iomem	*base;
+	u32		reg;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	/*
+	 * Read number of xdmac channels, read helper function can't be used
+	 * since atxdmac is not yet allocated and we need to know the number
+	 * of channels to do the allocation.
+	 */
+	reg = readl_relaxed(base + AT_XDMAC_GTYPE);
+	nr_channels = AT_XDMAC_NB_CH(reg);
+	if (nr_channels > AT_XDMAC_MAX_CHAN) {
+		dev_err(&pdev->dev, "invalid number of channels (%u)\n",
+			nr_channels);
+		return -EINVAL;
+	}
+
+	size = sizeof(*atxdmac);
+	size += nr_channels * sizeof(struct at_xdmac_chan);
+	atxdmac = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
+	if (!atxdmac) {
+		dev_err(&pdev->dev, "can't allocate at_xdmac structure\n");
+		return -ENOMEM;
+	}
+
+	atxdmac->regs = base;
+	atxdmac->irq = irq;
+
+	atxdmac->clk = devm_clk_get(&pdev->dev, "dma_clk");
+	if (IS_ERR(atxdmac->clk)) {
+		dev_err(&pdev->dev, "can't get dma_clk\n");
+		return PTR_ERR(atxdmac->clk);
+	}
+
+	/* Do not use dev res to prevent races with tasklet */
+	ret = request_irq(atxdmac->irq, at_xdmac_interrupt, 0, "at_xdmac", atxdmac);
+	if (ret) {
+		dev_err(&pdev->dev, "can't request irq\n");
+		return ret;
+	}
+
+	ret = clk_prepare_enable(atxdmac->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "can't prepare or enable clock\n");
+		goto err_free_irq;
+	}
+
+	atxdmac->at_xdmac_desc_pool =
+		dmam_pool_create(dev_name(&pdev->dev), &pdev->dev,
+				sizeof(struct at_xdmac_desc), 4, 0);
+	if (!atxdmac->at_xdmac_desc_pool) {
+		dev_err(&pdev->dev, "no memory for descriptors dma pool\n");
+		ret = -ENOMEM;
+		goto err_clk_disable;
+	}
+
+	dma_cap_set(DMA_CYCLIC, atxdmac->dma.cap_mask);
+	dma_cap_set(DMA_MEMCPY, atxdmac->dma.cap_mask);
+	dma_cap_set(DMA_SLAVE, atxdmac->dma.cap_mask);
+	atxdmac->dma.dev				= &pdev->dev;
+	atxdmac->dma.device_alloc_chan_resources	= at_xdmac_alloc_chan_resources;
+	atxdmac->dma.device_free_chan_resources		= at_xdmac_free_chan_resources;
+	atxdmac->dma.device_tx_status			= at_xdmac_tx_status;
+	atxdmac->dma.device_issue_pending		= at_xdmac_issue_pending;
+	atxdmac->dma.device_prep_dma_cyclic		= at_xdmac_prep_dma_cyclic;
+	atxdmac->dma.device_prep_dma_memcpy		= at_xdmac_prep_dma_memcpy;
+	atxdmac->dma.device_prep_slave_sg		= at_xdmac_prep_slave_sg;
+	atxdmac->dma.device_control			= at_xdmac_control;
+	atxdmac->dma.chancnt				= nr_channels;
+	atxdmac->dma.device_slave_caps			= at_xdmac_device_slave_caps;
+
+	/* Disable all chans and interrupts. */
+	at_xdmac_off(atxdmac);
+
+	/* Init channels. */
+	INIT_LIST_HEAD(&atxdmac->dma.channels);
+	for (i = 0; i < nr_channels; i++) {
+		struct at_xdmac_chan *atchan = &atxdmac->chan[i];
+
+		atchan->chan.device = &atxdmac->dma;
+		list_add_tail(&atchan->chan.device_node,
+			      &atxdmac->dma.channels);
+
+		atchan->ch_regs = at_xdmac_chan_reg_base(atxdmac, i);
+		atchan->mask = 1 << i;
+
+		spin_lock_init(&atchan->lock);
+		INIT_LIST_HEAD(&atchan->xfers_list);
+		INIT_LIST_HEAD(&atchan->free_descs_list);
+		tasklet_init(&atchan->tasklet, at_xdmac_tasklet,
+			     (unsigned long)atchan);
+
+		/* Clear pending interrupts. */
+		while (at_xdmac_chan_read(atchan, AT_XDMAC_CIS))
+			cpu_relax();
+	}
+	platform_set_drvdata(pdev, atxdmac);
+
+	ret = dma_async_device_register(&atxdmac->dma);
+	if (ret) {
+		dev_err(&pdev->dev, "fail to register DMA engine device\n");
+		goto err_clk_disable;
+	}
+
+	ret = of_dma_controller_register(pdev->dev.of_node,
+					 at_xdmac_xlate, atxdmac);
+	if (ret) {
+		dev_err(&pdev->dev, "could not register of dma controller\n");
+		goto err_dma_unregister;
+	}
+
+	dev_info(&pdev->dev, "%d channels, mapped at 0x%p\n",
+		 nr_channels, atxdmac->regs);
+
+	return 0;
+
+err_dma_unregister:
+	dma_async_device_unregister(&atxdmac->dma);
+err_clk_disable:
+	clk_disable_unprepare(atxdmac->clk);
+err_free_irq:
+	free_irq(atxdmac->irq, atxdmac->dma.dev);
+	return ret;
+}
+
+static int at_xdmac_remove(struct platform_device *pdev)
+{
+	struct at_xdmac	*atxdmac = (struct at_xdmac *)platform_get_drvdata(pdev);
+	int		i;
+
+	at_xdmac_off(atxdmac);
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&atxdmac->dma);
+	clk_disable_unprepare(atxdmac->clk);
+
+	synchronize_irq(atxdmac->irq);
+
+	free_irq(atxdmac->irq, atxdmac->dma.dev);
+
+	for (i = 0; i < atxdmac->dma.chancnt; i++) {
+		struct at_xdmac_chan *atchan = &atxdmac->chan[i];
+
+		tasklet_kill(&atchan->tasklet);
+		at_xdmac_free_chan_resources(&atchan->chan);
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops atmel_xdmac_dev_pm_ops = {
+	.prepare	= atmel_xdmac_prepare,
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(atmel_xdmac_suspend, atmel_xdmac_resume)
+};
+
+static const struct of_device_id atmel_xdmac_dt_ids[] = {
+	{
+		.compatible = "atmel,sama5d4-dma",
+	}, {
+		/* sentinel */
+	}
+};
+MODULE_DEVICE_TABLE(of, atmel_xdmac_dt_ids);
+
+static struct platform_driver at_xdmac_driver = {
+	.probe		= at_xdmac_probe,
+	.remove		= at_xdmac_remove,
+	.driver = {
+		.name		= "at_xdmac",
+		.owner		= THIS_MODULE,
+		.of_match_table	= of_match_ptr(atmel_xdmac_dt_ids),
+		.pm		= &atmel_xdmac_dev_pm_ops,
+	}
+};
+
+static int __init at_xdmac_init(void)
+{
+	return platform_driver_probe(&at_xdmac_driver, at_xdmac_probe);
+}
+subsys_initcall(at_xdmac_init);
+
+MODULE_DESCRIPTION("Atmel Extended DMA Controller driver");
+MODULE_AUTHOR("Ludovic Desroches <ludovic.desroches@atmel.com>");
+MODULE_LICENSE("GPL");
diff --git a/include/dt-bindings/dma/at91.h b/include/dt-bindings/dma/at91.h
index e835037a77b..ab6cbba4540 100644
--- a/include/dt-bindings/dma/at91.h
+++ b/include/dt-bindings/dma/at91.h
@@ -9,6 +9,8 @@
 #ifndef __DT_BINDINGS_AT91_DMA_H__
 #define __DT_BINDINGS_AT91_DMA_H__
 
+/* ---------- HDMAC ---------- */
+
 /*
  * Source and/or destination peripheral ID
  */
@@ -24,4 +26,27 @@
 #define AT91_DMA_CFG_FIFOCFG_ALAP	(0x1 << AT91_DMA_CFG_FIFOCFG_OFFSET)	/* largest defined AHB burst */
 #define AT91_DMA_CFG_FIFOCFG_ASAP	(0x2 << AT91_DMA_CFG_FIFOCFG_OFFSET)	/* single AHB access */
 
+
+/* ---------- XDMAC ---------- */
+#define AT91_XDMAC_DT_MEM_IF_MASK	(0x1)
+#define AT91_XDMAC_DT_MEM_IF_OFFSET	(13)
+#define AT91_XDMAC_DT_MEM_IF(mem_if)	(((mem_if) & AT91_XDMAC_DT_MEM_IF_MASK) \
+					<< AT91_XDMAC_DT_MEM_IF_OFFSET)
+#define AT91_XDMAC_DT_GET_MEM_IF(cfg)	(((cfg) >> AT91_XDMAC_DT_MEM_IF_OFFSET) \
+					& AT91_XDMAC_DT_MEM_IF_MASK)
+
+#define AT91_XDMAC_DT_PER_IF_MASK	(0x1)
+#define AT91_XDMAC_DT_PER_IF_OFFSET	(14)
+#define AT91_XDMAC_DT_PER_IF(per_if)	(((per_if) & AT91_XDMAC_DT_PER_IF_MASK) \
+					<< AT91_XDMAC_DT_PER_IF_OFFSET)
+#define AT91_XDMAC_DT_GET_PER_IF(cfg)	(((cfg) >> AT91_XDMAC_DT_PER_IF_OFFSET) \
+					& AT91_XDMAC_DT_PER_IF_MASK)
+
+#define AT91_XDMAC_DT_PERID_MASK	(0x7f)
+#define AT91_XDMAC_DT_PERID_OFFSET	(24)
+#define AT91_XDMAC_DT_PERID(perid)	(((perid) & AT91_XDMAC_DT_PERID_MASK) \
+					<< AT91_XDMAC_DT_PERID_OFFSET)
+#define AT91_XDMAC_DT_GET_PERID(cfg)	(((cfg) >> AT91_XDMAC_DT_PERID_OFFSET) \
+					& AT91_XDMAC_DT_PERID_MASK)
+
 #endif /* __DT_BINDINGS_AT91_DMA_H__ */
-- 
cgit v1.2.3-70-g09d2


From 59b93b41e7fa71138734a911b11b044340dd16bd Mon Sep 17 00:00:00 2001
From: Pravin B Shelar <pshelar@nicira.com>
Date: Wed, 5 Nov 2014 15:27:48 -0800
Subject: net: Remove MPLS GSO feature.

Device can export MPLS GSO support in dev->mpls_features same way
it export vlan features in dev->vlan_features. So it is safe to
remove NETIF_F_GSO_MPLS redundant flag.

Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
---
 include/linux/netdev_features.h | 5 +----
 include/linux/netdevice.h       | 1 -
 include/linux/skbuff.h          | 4 +---
 net/core/ethtool.c              | 1 -
 net/ipv4/af_inet.c              | 1 -
 net/ipv4/tcp_offload.c          | 1 -
 net/ipv4/udp_offload.c          | 3 +--
 net/ipv6/ip6_offload.c          | 1 -
 net/ipv6/udp_offload.c          | 3 +--
 net/mpls/mpls_gso.c             | 3 +--
 10 files changed, 5 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 8c94b07e654..8e30685affe 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -47,7 +47,6 @@ enum {
 	NETIF_F_GSO_SIT_BIT,		/* ... SIT tunnel with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_BIT,	/* ... UDP TUNNEL with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT,/* ... UDP TUNNEL with TSO & CSUM */
-	NETIF_F_GSO_MPLS_BIT,		/* ... MPLS segmentation */
 	NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
 		NETIF_F_GSO_TUNNEL_REMCSUM_BIT,
@@ -119,7 +118,6 @@ enum {
 #define NETIF_F_GSO_SIT		__NETIF_F(GSO_SIT)
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
 #define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM)
-#define NETIF_F_GSO_MPLS	__NETIF_F(GSO_MPLS)
 #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
@@ -183,7 +181,6 @@ enum {
 				 NETIF_F_GSO_IPIP |			\
 				 NETIF_F_GSO_SIT |			\
 				 NETIF_F_GSO_UDP_TUNNEL |		\
-				 NETIF_F_GSO_UDP_TUNNEL_CSUM |		\
-				 NETIF_F_GSO_MPLS)
+				 NETIF_F_GSO_UDP_TUNNEL_CSUM)
 
 #endif	/* _LINUX_NETDEV_FEATURES_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4767f546d7c..90ac95900a1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3583,7 +3583,6 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_SIT     != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
-	BUILD_BUG_ON(SKB_GSO_MPLS    != (NETIF_F_GSO_MPLS >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 39ec7530ae2..53f4f6c9335 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -372,9 +372,7 @@ enum {
 
 	SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11,
 
-	SKB_GSO_MPLS = 1 << 12,
-
-	SKB_GSO_TUNNEL_REMCSUM = 1 << 13,
+	SKB_GSO_TUNNEL_REMCSUM = 1 << 12,
 };
 
 #if BITS_PER_LONG > 32
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 06dfb293e5a..b0f84f5ddda 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -84,7 +84,6 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_GSO_IPIP_BIT] =	 "tx-ipip-segmentation",
 	[NETIF_F_GSO_SIT_BIT] =		 "tx-sit-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
-	[NETIF_F_GSO_MPLS_BIT] =	 "tx-mpls-segmentation",
 
 	[NETIF_F_FCOE_CRC_BIT] =         "tx-checksum-fcoe-crc",
 	[NETIF_F_SCTP_CSUM_BIT] =        "tx-checksum-sctp",
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ed2c672c5b0..3a096bb2d59 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1223,7 +1223,6 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_UDP_TUNNEL_CSUM |
 		       SKB_GSO_TUNNEL_REMCSUM |
-		       SKB_GSO_MPLS |
 		       0)))
 		goto out;
 
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index a1b2a5624f9..9d7930ba8e0 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -94,7 +94,6 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			       SKB_GSO_GRE_CSUM |
 			       SKB_GSO_IPIP |
 			       SKB_GSO_SIT |
-			       SKB_GSO_MPLS |
 			       SKB_GSO_UDP_TUNNEL |
 			       SKB_GSO_UDP_TUNNEL_CSUM |
 			       SKB_GSO_TUNNEL_REMCSUM |
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 0a5a70d0e84..d3e537ef6b7 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -207,8 +207,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 				      SKB_GSO_UDP_TUNNEL_CSUM |
 				      SKB_GSO_TUNNEL_REMCSUM |
 				      SKB_GSO_IPIP |
-				      SKB_GSO_GRE | SKB_GSO_GRE_CSUM |
-				      SKB_GSO_MPLS) ||
+				      SKB_GSO_GRE | SKB_GSO_GRE_CSUM) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
 
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index e9767079a36..fd76ce938c3 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -79,7 +79,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_UDP_TUNNEL_CSUM |
 		       SKB_GSO_TUNNEL_REMCSUM |
-		       SKB_GSO_MPLS |
 		       SKB_GSO_TCPV6 |
 		       0)))
 		goto out;
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 637ba2e438b..b6aa8ed1825 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -46,8 +46,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 				      SKB_GSO_GRE |
 				      SKB_GSO_GRE_CSUM |
 				      SKB_GSO_IPIP |
-				      SKB_GSO_SIT |
-				      SKB_GSO_MPLS) ||
+				      SKB_GSO_SIT) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
 
diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index e3545f21a09..ca27837974f 100644
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -34,8 +34,7 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_TCP_ECN |
 				  SKB_GSO_GRE |
 				  SKB_GSO_GRE_CSUM |
-				  SKB_GSO_IPIP |
-				  SKB_GSO_MPLS)))
+				  SKB_GSO_IPIP)))
 		goto out;
 
 	/* Setup inner SKB. */
-- 
cgit v1.2.3-70-g09d2


From 25cd9ba0abc0749e5cb78e6493c6f6b3311ec6c5 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Mon, 6 Oct 2014 05:05:13 -0700
Subject: openvswitch: Add basic MPLS support to kernel

Allow datapath to recognize and extract MPLS labels into flow keys
and execute actions which push, pop, and set labels on packets.

Based heavily on work by Leo Alterman, Ravi K, Isaku Yamahata and Joe Stringer.

Cc: Ravi K <rkerur@gmail.com>
Cc: Leo Alterman <lalterman@nicira.com>
Cc: Isaku Yamahata <yamahata@valinux.co.jp>
Cc: Joe Stringer <joe@wand.net.nz>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
---
 include/net/mpls.h               |  39 +++++++++++
 include/uapi/linux/openvswitch.h |  32 +++++++++
 net/core/dev.c                   |   3 +-
 net/openvswitch/Kconfig          |   1 +
 net/openvswitch/actions.c        | 106 ++++++++++++++++++++++++++++-
 net/openvswitch/datapath.c       |   6 +-
 net/openvswitch/flow.c           |  30 +++++++++
 net/openvswitch/flow.h           |  17 +++--
 net/openvswitch/flow_netlink.c   | 139 ++++++++++++++++++++++++++++++++++-----
 net/openvswitch/flow_netlink.h   |   2 +-
 10 files changed, 345 insertions(+), 30 deletions(-)
 create mode 100644 include/net/mpls.h

(limited to 'include')

diff --git a/include/net/mpls.h b/include/net/mpls.h
new file mode 100644
index 00000000000..5b3b5addfb0
--- /dev/null
+++ b/include/net/mpls.h
@@ -0,0 +1,39 @@
+/*
+ * Copyright (c) 2014 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _NET_MPLS_H
+#define _NET_MPLS_H 1
+
+#include <linux/if_ether.h>
+#include <linux/netdevice.h>
+
+#define MPLS_HLEN 4
+
+static inline bool eth_p_mpls(__be16 eth_type)
+{
+	return eth_type == htons(ETH_P_MPLS_UC) ||
+		eth_type == htons(ETH_P_MPLS_MC);
+}
+
+/*
+ * For non-MPLS skbs this will correspond to the network header.
+ * For MPLS skbs it will be before the network_header as the MPLS
+ * label stack lies between the end of the mac header and the network
+ * header. That is, for MPLS skbs the end of the mac header
+ * is the top of the MPLS label stack.
+ */
+static inline unsigned char *skb_mpls_header(struct sk_buff *skb)
+{
+	return skb_mac_header(skb) + skb->mac_len;
+}
+#endif
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 435eabc5ffa..631056b66f8 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -293,6 +293,9 @@ enum ovs_key_attr {
 	OVS_KEY_ATTR_DP_HASH,      /* u32 hash value. Value 0 indicates the hash
 				   is not computed by the datapath. */
 	OVS_KEY_ATTR_RECIRC_ID, /* u32 recirc id */
+	OVS_KEY_ATTR_MPLS,      /* array of struct ovs_key_mpls.
+				 * The implementation may restrict
+				 * the accepted length of the array. */
 
 #ifdef __KERNEL__
 	OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ovs_tunnel_info */
@@ -340,6 +343,10 @@ struct ovs_key_ethernet {
 	__u8	 eth_dst[ETH_ALEN];
 };
 
+struct ovs_key_mpls {
+	__be32 mpls_lse;
+};
+
 struct ovs_key_ipv4 {
 	__be32 ipv4_src;
 	__be32 ipv4_dst;
@@ -483,6 +490,19 @@ enum ovs_userspace_attr {
 
 #define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1)
 
+/**
+ * struct ovs_action_push_mpls - %OVS_ACTION_ATTR_PUSH_MPLS action argument.
+ * @mpls_lse: MPLS label stack entry to push.
+ * @mpls_ethertype: Ethertype to set in the encapsulating ethernet frame.
+ *
+ * The only values @mpls_ethertype should ever be given are %ETH_P_MPLS_UC and
+ * %ETH_P_MPLS_MC, indicating MPLS unicast or multicast. Other are rejected.
+ */
+struct ovs_action_push_mpls {
+	__be32 mpls_lse;
+	__be16 mpls_ethertype; /* Either %ETH_P_MPLS_UC or %ETH_P_MPLS_MC */
+};
+
 /**
  * struct ovs_action_push_vlan - %OVS_ACTION_ATTR_PUSH_VLAN action argument.
  * @vlan_tpid: Tag protocol identifier (TPID) to push.
@@ -534,6 +554,15 @@ struct ovs_action_hash {
  * @OVS_ACTION_ATTR_POP_VLAN: Pop the outermost 802.1Q header off the packet.
  * @OVS_ACTION_ATTR_SAMPLE: Probabilitically executes actions, as specified in
  * the nested %OVS_SAMPLE_ATTR_* attributes.
+ * @OVS_ACTION_ATTR_PUSH_MPLS: Push a new MPLS label stack entry onto the
+ * top of the packets MPLS label stack.  Set the ethertype of the
+ * encapsulating frame to either %ETH_P_MPLS_UC or %ETH_P_MPLS_MC to
+ * indicate the new packet contents.
+ * @OVS_ACTION_ATTR_POP_MPLS: Pop an MPLS label stack entry off of the
+ * packet's MPLS label stack.  Set the encapsulating frame's ethertype to
+ * indicate the new packet contents. This could potentially still be
+ * %ETH_P_MPLS if the resulting MPLS label stack is not empty.  If there
+ * is no MPLS label stack, as determined by ethertype, no action is taken.
  *
  * Only a single header can be set with a single %OVS_ACTION_ATTR_SET.  Not all
  * fields within a header are modifiable, e.g. the IPv4 protocol and fragment
@@ -550,6 +579,9 @@ enum ovs_action_attr {
 	OVS_ACTION_ATTR_SAMPLE,       /* Nested OVS_SAMPLE_ATTR_*. */
 	OVS_ACTION_ATTR_RECIRC,       /* u32 recirc_id. */
 	OVS_ACTION_ATTR_HASH,	      /* struct ovs_action_hash. */
+	OVS_ACTION_ATTR_PUSH_MPLS,    /* struct ovs_action_push_mpls. */
+	OVS_ACTION_ATTR_POP_MPLS,     /* __be16 ethertype. */
+
 	__OVS_ACTION_ATTR_MAX
 };
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 40be481268d..70bb609c283 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -118,6 +118,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <net/ip.h>
+#include <net/mpls.h>
 #include <linux/ipv6.h>
 #include <linux/in.h>
 #include <linux/jhash.h>
@@ -2530,7 +2531,7 @@ static netdev_features_t net_mpls_features(struct sk_buff *skb,
 					   netdev_features_t features,
 					   __be16 type)
 {
-	if (type == htons(ETH_P_MPLS_UC) || type == htons(ETH_P_MPLS_MC))
+	if (eth_p_mpls(type))
 		features &= skb->dev->mpls_features;
 
 	return features;
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
index 2a9673e39ca..454ce12efbb 100644
--- a/net/openvswitch/Kconfig
+++ b/net/openvswitch/Kconfig
@@ -30,6 +30,7 @@ config OPENVSWITCH
 
 config OPENVSWITCH_GRE
 	tristate "Open vSwitch GRE tunneling support"
+	select NET_MPLS_GSO
 	depends on INET
 	depends on OPENVSWITCH
 	depends on NET_IPGRE_DEMUX
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 922c133b193..930b1b6e4ce 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -28,10 +28,12 @@
 #include <linux/in6.h>
 #include <linux/if_arp.h>
 #include <linux/if_vlan.h>
+
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/checksum.h>
 #include <net/dsfield.h>
+#include <net/mpls.h>
 #include <net/sctp/checksum.h>
 
 #include "datapath.h"
@@ -118,6 +120,92 @@ static int make_writable(struct sk_buff *skb, int write_len)
 	return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
 }
 
+static int push_mpls(struct sk_buff *skb,
+		     const struct ovs_action_push_mpls *mpls)
+{
+	__be32 *new_mpls_lse;
+	struct ethhdr *hdr;
+
+	/* Networking stack do not allow simultaneous Tunnel and MPLS GSO. */
+	if (skb->encapsulation)
+		return -ENOTSUPP;
+
+	if (skb_cow_head(skb, MPLS_HLEN) < 0)
+		return -ENOMEM;
+
+	skb_push(skb, MPLS_HLEN);
+	memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
+		skb->mac_len);
+	skb_reset_mac_header(skb);
+
+	new_mpls_lse = (__be32 *)skb_mpls_header(skb);
+	*new_mpls_lse = mpls->mpls_lse;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(skb->csum, csum_partial(new_mpls_lse,
+							     MPLS_HLEN, 0));
+
+	hdr = eth_hdr(skb);
+	hdr->h_proto = mpls->mpls_ethertype;
+
+	skb_set_inner_protocol(skb, skb->protocol);
+	skb->protocol = mpls->mpls_ethertype;
+
+	return 0;
+}
+
+static int pop_mpls(struct sk_buff *skb, const __be16 ethertype)
+{
+	struct ethhdr *hdr;
+	int err;
+
+	err = make_writable(skb, skb->mac_len + MPLS_HLEN);
+	if (unlikely(err))
+		return err;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_sub(skb->csum,
+				     csum_partial(skb_mpls_header(skb),
+						  MPLS_HLEN, 0));
+
+	memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
+		skb->mac_len);
+
+	__skb_pull(skb, MPLS_HLEN);
+	skb_reset_mac_header(skb);
+
+	/* skb_mpls_header() is used to locate the ethertype
+	 * field correctly in the presence of VLAN tags.
+	 */
+	hdr = (struct ethhdr *)(skb_mpls_header(skb) - ETH_HLEN);
+	hdr->h_proto = ethertype;
+	if (eth_p_mpls(skb->protocol))
+		skb->protocol = ethertype;
+	return 0;
+}
+
+static int set_mpls(struct sk_buff *skb, const __be32 *mpls_lse)
+{
+	__be32 *stack;
+	int err;
+
+	err = make_writable(skb, skb->mac_len + MPLS_HLEN);
+	if (unlikely(err))
+		return err;
+
+	stack = (__be32 *)skb_mpls_header(skb);
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		__be32 diff[] = { ~(*stack), *mpls_lse };
+
+		skb->csum = ~csum_partial((char *)diff, sizeof(diff),
+					  ~skb->csum);
+	}
+
+	*stack = *mpls_lse;
+
+	return 0;
+}
+
 /* remove VLAN header from packet and update csum accordingly. */
 static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
 {
@@ -140,10 +228,12 @@ static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
 
 	vlan_set_encap_proto(skb, vhdr);
 	skb->mac_header += VLAN_HLEN;
+
 	if (skb_network_offset(skb) < ETH_HLEN)
 		skb_set_network_header(skb, ETH_HLEN);
-	skb_reset_mac_len(skb);
 
+	/* Update mac_len for subsequent MPLS actions */
+	skb_reset_mac_len(skb);
 	return 0;
 }
 
@@ -186,6 +276,8 @@ static int push_vlan(struct sk_buff *skb, const struct ovs_action_push_vlan *vla
 
 		if (!__vlan_put_tag(skb, skb->vlan_proto, current_tag))
 			return -ENOMEM;
+		/* Update mac_len for subsequent MPLS actions */
+		skb->mac_len += VLAN_HLEN;
 
 		if (skb->ip_summed == CHECKSUM_COMPLETE)
 			skb->csum = csum_add(skb->csum, csum_partial(skb->data
@@ -612,6 +704,10 @@ static int execute_set_action(struct sk_buff *skb,
 	case OVS_KEY_ATTR_SCTP:
 		err = set_sctp(skb, nla_data(nested_attr));
 		break;
+
+	case OVS_KEY_ATTR_MPLS:
+		err = set_mpls(skb, nla_data(nested_attr));
+		break;
 	}
 
 	return err;
@@ -690,6 +786,14 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			execute_hash(skb, key, a);
 			break;
 
+		case OVS_ACTION_ATTR_PUSH_MPLS:
+			err = push_mpls(skb, nla_data(a));
+			break;
+
+		case OVS_ACTION_ATTR_POP_MPLS:
+			err = pop_mpls(skb, nla_get_be16(a));
+			break;
+
 		case OVS_ACTION_ATTR_PUSH_VLAN:
 			err = push_vlan(skb, nla_data(a));
 			if (unlikely(err)) /* skb already freed. */
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index f18302f3204..688cb9bc0ef 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -560,7 +560,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 		goto err_flow_free;
 
 	err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS],
-				   &flow->key, 0, &acts);
+				   &flow->key, &acts);
 	if (err)
 		goto err_flow_free;
 
@@ -846,7 +846,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		goto err_kfree_flow;
 
 	error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key,
-				     0, &acts);
+				     &acts);
 	if (error) {
 		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
 		goto err_kfree_acts;
@@ -953,7 +953,7 @@ static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
 		return acts;
 
 	ovs_flow_mask_key(&masked_key, key, mask);
-	error = ovs_nla_copy_actions(a, &masked_key, 0, &acts);
+	error = ovs_nla_copy_actions(a, &masked_key, &acts);
 	if (error) {
 		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
 		kfree(acts);
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 2b78789ea7c..90a21010fc8 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -32,6 +32,7 @@
 #include <linux/if_arp.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/mpls.h>
 #include <linux/sctp.h>
 #include <linux/smp.h>
 #include <linux/tcp.h>
@@ -42,6 +43,7 @@
 #include <net/ip.h>
 #include <net/ip_tunnels.h>
 #include <net/ipv6.h>
+#include <net/mpls.h>
 #include <net/ndisc.h>
 
 #include "datapath.h"
@@ -480,6 +482,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 		return -ENOMEM;
 
 	skb_reset_network_header(skb);
+	skb_reset_mac_len(skb);
 	__skb_push(skb, skb->data - skb_mac_header(skb));
 
 	/* Network layer. */
@@ -584,6 +587,33 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 			memset(&key->ip, 0, sizeof(key->ip));
 			memset(&key->ipv4, 0, sizeof(key->ipv4));
 		}
+	} else if (eth_p_mpls(key->eth.type)) {
+		size_t stack_len = MPLS_HLEN;
+
+		/* In the presence of an MPLS label stack the end of the L2
+		 * header and the beginning of the L3 header differ.
+		 *
+		 * Advance network_header to the beginning of the L3
+		 * header. mac_len corresponds to the end of the L2 header.
+		 */
+		while (1) {
+			__be32 lse;
+
+			error = check_header(skb, skb->mac_len + stack_len);
+			if (unlikely(error))
+				return 0;
+
+			memcpy(&lse, skb_network_header(skb), MPLS_HLEN);
+
+			if (stack_len == MPLS_HLEN)
+				memcpy(&key->mpls.top_lse, &lse, MPLS_HLEN);
+
+			skb_set_network_header(skb, skb->mac_len + stack_len);
+			if (lse & htonl(MPLS_LS_S_MASK))
+				break;
+
+			stack_len += MPLS_HLEN;
+		}
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
 		int nh_len;             /* IPv6 Header + Extensions */
 
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 71813318c8c..4962bee81a1 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -102,12 +102,17 @@ struct sw_flow_key {
 		__be16 tci;		/* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */
 		__be16 type;		/* Ethernet frame type. */
 	} eth;
-	struct {
-		u8     proto;		/* IP protocol or lower 8 bits of ARP opcode. */
-		u8     tos;		/* IP ToS. */
-		u8     ttl;		/* IP TTL/hop limit. */
-		u8     frag;		/* One of OVS_FRAG_TYPE_*. */
-	} ip;
+	union {
+		struct {
+			__be32 top_lse;	/* top label stack entry */
+		} mpls;
+		struct {
+			u8     proto;	/* IP protocol or lower 8 bits of ARP opcode. */
+			u8     tos;	    /* IP ToS. */
+			u8     ttl;	    /* IP TTL/hop limit. */
+			u8     frag;	/* One of OVS_FRAG_TYPE_*. */
+		} ip;
+	};
 	struct {
 		__be16 src;		/* TCP/UDP/SCTP source port. */
 		__be16 dst;		/* TCP/UDP/SCTP destination port. */
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 939bcb32100..569309c49cc 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -46,6 +46,7 @@
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/ndisc.h>
+#include <net/mpls.h>
 
 #include "flow_netlink.h"
 
@@ -134,7 +135,8 @@ static bool match_validate(const struct sw_flow_match *match,
 			| (1 << OVS_KEY_ATTR_ICMP)
 			| (1 << OVS_KEY_ATTR_ICMPV6)
 			| (1 << OVS_KEY_ATTR_ARP)
-			| (1 << OVS_KEY_ATTR_ND));
+			| (1 << OVS_KEY_ATTR_ND)
+			| (1 << OVS_KEY_ATTR_MPLS));
 
 	/* Always allowed mask fields. */
 	mask_allowed |= ((1 << OVS_KEY_ATTR_TUNNEL)
@@ -149,6 +151,12 @@ static bool match_validate(const struct sw_flow_match *match,
 			mask_allowed |= 1 << OVS_KEY_ATTR_ARP;
 	}
 
+	if (eth_p_mpls(match->key->eth.type)) {
+		key_expected |= 1 << OVS_KEY_ATTR_MPLS;
+		if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
+			mask_allowed |= 1 << OVS_KEY_ATTR_MPLS;
+	}
+
 	if (match->key->eth.type == htons(ETH_P_IP)) {
 		key_expected |= 1 << OVS_KEY_ATTR_IPV4;
 		if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
@@ -266,6 +274,7 @@ static const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
 	[OVS_KEY_ATTR_RECIRC_ID] = sizeof(u32),
 	[OVS_KEY_ATTR_DP_HASH] = sizeof(u32),
 	[OVS_KEY_ATTR_TUNNEL] = -1,
+	[OVS_KEY_ATTR_MPLS] = sizeof(struct ovs_key_mpls),
 };
 
 static bool is_all_zero(const u8 *fp, size_t size)
@@ -735,6 +744,16 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 		attrs &= ~(1 << OVS_KEY_ATTR_ARP);
 	}
 
+	if (attrs & (1 << OVS_KEY_ATTR_MPLS)) {
+		const struct ovs_key_mpls *mpls_key;
+
+		mpls_key = nla_data(a[OVS_KEY_ATTR_MPLS]);
+		SW_FLOW_KEY_PUT(match, mpls.top_lse,
+				mpls_key->mpls_lse, is_mask);
+
+		attrs &= ~(1 << OVS_KEY_ATTR_MPLS);
+	 }
+
 	if (attrs & (1 << OVS_KEY_ATTR_TCP)) {
 		const struct ovs_key_tcp *tcp_key;
 
@@ -1140,6 +1159,14 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 		arp_key->arp_op = htons(output->ip.proto);
 		ether_addr_copy(arp_key->arp_sha, output->ipv4.arp.sha);
 		ether_addr_copy(arp_key->arp_tha, output->ipv4.arp.tha);
+	} else if (eth_p_mpls(swkey->eth.type)) {
+		struct ovs_key_mpls *mpls_key;
+
+		nla = nla_reserve(skb, OVS_KEY_ATTR_MPLS, sizeof(*mpls_key));
+		if (!nla)
+			goto nla_put_failure;
+		mpls_key = nla_data(nla);
+		mpls_key->mpls_lse = output->mpls.top_lse;
 	}
 
 	if ((swkey->eth.type == htons(ETH_P_IP) ||
@@ -1336,9 +1363,15 @@ static inline void add_nested_action_end(struct sw_flow_actions *sfa,
 	a->nla_len = sfa->actions_len - st_offset;
 }
 
+static int ovs_nla_copy_actions__(const struct nlattr *attr,
+				  const struct sw_flow_key *key,
+				  int depth, struct sw_flow_actions **sfa,
+				  __be16 eth_type, __be16 vlan_tci);
+
 static int validate_and_copy_sample(const struct nlattr *attr,
 				    const struct sw_flow_key *key, int depth,
-				    struct sw_flow_actions **sfa)
+				    struct sw_flow_actions **sfa,
+				    __be16 eth_type, __be16 vlan_tci)
 {
 	const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
 	const struct nlattr *probability, *actions;
@@ -1375,7 +1408,8 @@ static int validate_and_copy_sample(const struct nlattr *attr,
 	if (st_acts < 0)
 		return st_acts;
 
-	err = ovs_nla_copy_actions(actions, key, depth + 1, sfa);
+	err = ovs_nla_copy_actions__(actions, key, depth + 1, sfa,
+				     eth_type, vlan_tci);
 	if (err)
 		return err;
 
@@ -1385,10 +1419,10 @@ static int validate_and_copy_sample(const struct nlattr *attr,
 	return 0;
 }
 
-static int validate_tp_port(const struct sw_flow_key *flow_key)
+static int validate_tp_port(const struct sw_flow_key *flow_key,
+			    __be16 eth_type)
 {
-	if ((flow_key->eth.type == htons(ETH_P_IP) ||
-	     flow_key->eth.type == htons(ETH_P_IPV6)) &&
+	if ((eth_type == htons(ETH_P_IP) || eth_type == htons(ETH_P_IPV6)) &&
 	    (flow_key->tp.src || flow_key->tp.dst))
 		return 0;
 
@@ -1483,7 +1517,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 static int validate_set(const struct nlattr *a,
 			const struct sw_flow_key *flow_key,
 			struct sw_flow_actions **sfa,
-			bool *set_tun)
+			bool *set_tun, __be16 eth_type)
 {
 	const struct nlattr *ovs_key = nla_data(a);
 	int key_type = nla_type(ovs_key);
@@ -1508,6 +1542,9 @@ static int validate_set(const struct nlattr *a,
 		break;
 
 	case OVS_KEY_ATTR_TUNNEL:
+		if (eth_p_mpls(eth_type))
+			return -EINVAL;
+
 		*set_tun = true;
 		err = validate_and_copy_set_tun(a, sfa);
 		if (err)
@@ -1515,7 +1552,7 @@ static int validate_set(const struct nlattr *a,
 		break;
 
 	case OVS_KEY_ATTR_IPV4:
-		if (flow_key->eth.type != htons(ETH_P_IP))
+		if (eth_type != htons(ETH_P_IP))
 			return -EINVAL;
 
 		if (!flow_key->ip.proto)
@@ -1531,7 +1568,7 @@ static int validate_set(const struct nlattr *a,
 		break;
 
 	case OVS_KEY_ATTR_IPV6:
-		if (flow_key->eth.type != htons(ETH_P_IPV6))
+		if (eth_type != htons(ETH_P_IPV6))
 			return -EINVAL;
 
 		if (!flow_key->ip.proto)
@@ -1553,19 +1590,24 @@ static int validate_set(const struct nlattr *a,
 		if (flow_key->ip.proto != IPPROTO_TCP)
 			return -EINVAL;
 
-		return validate_tp_port(flow_key);
+		return validate_tp_port(flow_key, eth_type);
 
 	case OVS_KEY_ATTR_UDP:
 		if (flow_key->ip.proto != IPPROTO_UDP)
 			return -EINVAL;
 
-		return validate_tp_port(flow_key);
+		return validate_tp_port(flow_key, eth_type);
+
+	case OVS_KEY_ATTR_MPLS:
+		if (!eth_p_mpls(eth_type))
+			return -EINVAL;
+		break;
 
 	case OVS_KEY_ATTR_SCTP:
 		if (flow_key->ip.proto != IPPROTO_SCTP)
 			return -EINVAL;
 
-		return validate_tp_port(flow_key);
+		return validate_tp_port(flow_key, eth_type);
 
 	default:
 		return -EINVAL;
@@ -1609,12 +1651,13 @@ static int copy_action(const struct nlattr *from,
 	return 0;
 }
 
-int ovs_nla_copy_actions(const struct nlattr *attr,
-			 const struct sw_flow_key *key,
-			 int depth,
-			 struct sw_flow_actions **sfa)
+static int ovs_nla_copy_actions__(const struct nlattr *attr,
+				  const struct sw_flow_key *key,
+				  int depth, struct sw_flow_actions **sfa,
+				  __be16 eth_type, __be16 vlan_tci)
 {
 	const struct nlattr *a;
+	bool out_tnl_port = false;
 	int rem, err;
 
 	if (depth >= SAMPLE_ACTION_DEPTH)
@@ -1626,6 +1669,8 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 			[OVS_ACTION_ATTR_OUTPUT] = sizeof(u32),
 			[OVS_ACTION_ATTR_RECIRC] = sizeof(u32),
 			[OVS_ACTION_ATTR_USERSPACE] = (u32)-1,
+			[OVS_ACTION_ATTR_PUSH_MPLS] = sizeof(struct ovs_action_push_mpls),
+			[OVS_ACTION_ATTR_POP_MPLS] = sizeof(__be16),
 			[OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
 			[OVS_ACTION_ATTR_POP_VLAN] = 0,
 			[OVS_ACTION_ATTR_SET] = (u32)-1,
@@ -1655,6 +1700,8 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 		case OVS_ACTION_ATTR_OUTPUT:
 			if (nla_get_u32(a) >= DP_MAX_PORTS)
 				return -EINVAL;
+			out_tnl_port = false;
+
 			break;
 
 		case OVS_ACTION_ATTR_HASH: {
@@ -1671,6 +1718,7 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 		}
 
 		case OVS_ACTION_ATTR_POP_VLAN:
+			vlan_tci = htons(0);
 			break;
 
 		case OVS_ACTION_ATTR_PUSH_VLAN:
@@ -1679,19 +1727,66 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 				return -EINVAL;
 			if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT)))
 				return -EINVAL;
+			vlan_tci = vlan->vlan_tci;
 			break;
 
 		case OVS_ACTION_ATTR_RECIRC:
 			break;
 
+		case OVS_ACTION_ATTR_PUSH_MPLS: {
+			const struct ovs_action_push_mpls *mpls = nla_data(a);
+
+			/* Networking stack do not allow simultaneous Tunnel
+			 * and MPLS GSO.
+			 */
+			if (out_tnl_port)
+				return -EINVAL;
+
+			if (!eth_p_mpls(mpls->mpls_ethertype))
+				return -EINVAL;
+			/* Prohibit push MPLS other than to a white list
+			 * for packets that have a known tag order.
+			 */
+			if (vlan_tci & htons(VLAN_TAG_PRESENT) ||
+			    (eth_type != htons(ETH_P_IP) &&
+			     eth_type != htons(ETH_P_IPV6) &&
+			     eth_type != htons(ETH_P_ARP) &&
+			     eth_type != htons(ETH_P_RARP) &&
+			     !eth_p_mpls(eth_type)))
+				return -EINVAL;
+			eth_type = mpls->mpls_ethertype;
+			break;
+		}
+
+		case OVS_ACTION_ATTR_POP_MPLS:
+			if (vlan_tci & htons(VLAN_TAG_PRESENT) ||
+			    !eth_p_mpls(eth_type))
+				return -EINVAL;
+
+			/* Disallow subsequent L2.5+ set and mpls_pop actions
+			 * as there is no check here to ensure that the new
+			 * eth_type is valid and thus set actions could
+			 * write off the end of the packet or otherwise
+			 * corrupt it.
+			 *
+			 * Support for these actions is planned using packet
+			 * recirculation.
+			 */
+			eth_type = htons(0);
+			break;
+
 		case OVS_ACTION_ATTR_SET:
-			err = validate_set(a, key, sfa, &skip_copy);
+			err = validate_set(a, key, sfa,
+					   &out_tnl_port, eth_type);
 			if (err)
 				return err;
+
+			skip_copy = out_tnl_port;
 			break;
 
 		case OVS_ACTION_ATTR_SAMPLE:
-			err = validate_and_copy_sample(a, key, depth, sfa);
+			err = validate_and_copy_sample(a, key, depth, sfa,
+						       eth_type, vlan_tci);
 			if (err)
 				return err;
 			skip_copy = true;
@@ -1713,6 +1808,14 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 	return 0;
 }
 
+int ovs_nla_copy_actions(const struct nlattr *attr,
+			 const struct sw_flow_key *key,
+			 struct sw_flow_actions **sfa)
+{
+	return ovs_nla_copy_actions__(attr, key, 0, sfa, key->eth.type,
+				      key->eth.tci);
+}
+
 static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb)
 {
 	const struct nlattr *a;
diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h
index 206e45add88..6355b1d0132 100644
--- a/net/openvswitch/flow_netlink.h
+++ b/net/openvswitch/flow_netlink.h
@@ -49,7 +49,7 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 		      const struct nlattr *);
 
 int ovs_nla_copy_actions(const struct nlattr *attr,
-			 const struct sw_flow_key *key, int depth,
+			 const struct sw_flow_key *key,
 			 struct sw_flow_actions **sfa);
 int ovs_nla_put_actions(const struct nlattr *attr,
 			int len, struct sk_buff *skb);
-- 
cgit v1.2.3-70-g09d2


From 1a4e96a0e989200f7180264e27b22e9a85f3fcc8 Mon Sep 17 00:00:00 2001
From: Jarno Rajahalme <jrajahalme@nicira.com>
Date: Tue, 30 Sep 2014 10:52:32 -0700
Subject: openvswitch: Fix the type of struct ovs_key_nd nd_target field.

Should be the same as other IPv6 address fields.

Current master produces sparse warnings without this change.

Signed-off-by: Jarno Rajahalme <jrajahalme@nicira.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
---
 include/uapi/linux/openvswitch.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 631056b66f8..26c36c4cf7e 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -400,9 +400,9 @@ struct ovs_key_arp {
 };
 
 struct ovs_key_nd {
-	__u32 nd_target[4];
-	__u8  nd_sll[ETH_ALEN];
-	__u8  nd_tll[ETH_ALEN];
+	__be32	nd_target[4];
+	__u8	nd_sll[ETH_ALEN];
+	__u8	nd_tll[ETH_ALEN];
 };
 
 /**
-- 
cgit v1.2.3-70-g09d2


From bb656add19764c7a3cf28b2b330ec0a189fe4f48 Mon Sep 17 00:00:00 2001
From: Bard Liao <bardliao@realtek.com>
Date: Wed, 5 Nov 2014 15:02:08 +0800
Subject: ASoC: rt5645: Add JD function support

rt5645 codec support jack detection function. The patch will set
related registers if JD function is used.

Signed-off-by: Bard Liao <bardliao@realtek.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/rt5645.h    |  3 +++
 sound/soc/codecs/rt5645.c | 20 ++++++++++++++++++++
 sound/soc/codecs/rt5645.h |  5 +++++
 3 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/include/sound/rt5645.h b/include/sound/rt5645.h
index a5352712194..937f421bc66 100644
--- a/include/sound/rt5645.h
+++ b/include/sound/rt5645.h
@@ -23,6 +23,9 @@ struct rt5645_platform_data {
 
 	unsigned int hp_det_gpio;
 	bool gpio_hp_det_active_high;
+
+	/* true if codec's jd function is used */
+	bool en_jd_func;
 };
 
 #endif
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 1423cb283f1..286438d6916 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -2203,6 +2203,13 @@ static int rt5645_probe(struct snd_soc_codec *codec)
 
 	snd_soc_update_bits(codec, RT5645_CHARGE_PUMP, 0x0300, 0x0200);
 
+	/* for JD function */
+	if (rt5645->pdata.en_jd_func) {
+		snd_soc_dapm_force_enable_pin(&codec->dapm, "JD Power");
+		snd_soc_dapm_force_enable_pin(&codec->dapm, "LDO2");
+		snd_soc_dapm_sync(&codec->dapm);
+	}
+
 	return 0;
 }
 
@@ -2436,6 +2443,19 @@ static int rt5645_i2c_probe(struct i2c_client *i2c,
 
 	}
 
+	if (rt5645->pdata.en_jd_func) {
+		regmap_update_bits(rt5645->regmap, RT5645_GEN_CTRL3,
+			RT5645_IRQ_CLK_GATE_CTRL | RT5645_MICINDET_MANU,
+			RT5645_IRQ_CLK_GATE_CTRL | RT5645_MICINDET_MANU);
+		regmap_update_bits(rt5645->regmap, RT5645_IN1_CTRL1,
+			RT5645_CBJ_BST1_EN, RT5645_CBJ_BST1_EN);
+		regmap_update_bits(rt5645->regmap, RT5645_JD_CTRL3,
+			RT5645_JD_CBJ_EN | RT5645_JD_CBJ_POL,
+			RT5645_JD_CBJ_EN | RT5645_JD_CBJ_POL);
+		regmap_update_bits(rt5645->regmap, RT5645_MICBIAS,
+			RT5645_IRQ_CLK_INT, RT5645_IRQ_CLK_INT);
+	}
+
 	if (rt5645->i2c->irq) {
 		ret = request_threaded_irq(rt5645->i2c->irq, NULL, rt5645_irq,
 			IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
diff --git a/sound/soc/codecs/rt5645.h b/sound/soc/codecs/rt5645.h
index 5ec2520614d..82f681b0294 100644
--- a/sound/soc/codecs/rt5645.h
+++ b/sound/soc/codecs/rt5645.h
@@ -1348,6 +1348,8 @@
 #define RT5645_PWR_CLK25M_SFT			4
 #define RT5645_PWR_CLK25M_PD			(0x0 << 4)
 #define RT5645_PWR_CLK25M_PU			(0x1 << 4)
+#define RT5645_IRQ_CLK_MCLK			(0x0 << 3)
+#define RT5645_IRQ_CLK_INT			(0x1 << 3)
 
 /* VAD Control 4 (0x9d) */
 #define RT5645_VAD_SEL_MASK			(0x3 << 8)
@@ -2116,6 +2118,9 @@ enum {
 #define RT5645_RXDP2_SEL_ADC			(0x1 << 3)
 #define RT5645_RXDP2_SEL_SFT			(3)
 
+/* General Control3 (0xfc) */
+#define RT5645_IRQ_CLK_GATE_CTRL		(0x1 << 11)
+#define RT5645_MICINDET_MANU			(0x1 << 7)
 
 /* Vendor ID (0xfd) */
 #define RT5645_VER_C				0x2
-- 
cgit v1.2.3-70-g09d2


From d50051407f136028108cfda068d55ef053a54fe1 Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Wed, 5 Nov 2014 08:02:48 +0100
Subject: ipv6: Allow sending packets through tunnels with wildcard endpoints

Currently we need the IP6_TNL_F_CAP_XMIT capabiltiy to transmit
packets through an ipv6 tunnel. This capability is set when the
tunnel gets configured, based on the tunnel endpoint addresses.

On tunnels with wildcard tunnel endpoints, we need to do the
capabiltiy checking on a per packet basis like it is done in
the receive path.

This patch extends ip6_tnl_xmit_ctl() to take local and remote
addresses as parameters to allow for per packet capabiltiy
checking.

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_tunnel.h |  3 ++-
 net/ipv6/ip6_gre.c       |  2 +-
 net/ipv6/ip6_tunnel.c    | 23 +++++++++++++++--------
 net/ipv6/ip6_vti.c       | 10 ++++++++--
 4 files changed, 26 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index a5593dab6af..9326c41c2d7 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -65,7 +65,8 @@ void ip6_tnl_dst_reset(struct ip6_tnl *t);
 void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst);
 int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
 		const struct in6_addr *raddr);
-int ip6_tnl_xmit_ctl(struct ip6_tnl *t);
+int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
+		     const struct in6_addr *raddr);
 __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw);
 __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr,
 			     const struct in6_addr *raddr);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 12c3c8ef384..1fcf62ea5eb 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -902,7 +902,7 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb,
 	struct net_device_stats *stats = &t->dev->stats;
 	int ret;
 
-	if (!ip6_tnl_xmit_ctl(t))
+	if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr))
 		goto tx_err;
 
 	switch (skb->protocol) {
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 8c97cd1048c..a8f94ff9c60 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -909,24 +909,28 @@ ip6_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr)
 	return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr);
 }
 
-int ip6_tnl_xmit_ctl(struct ip6_tnl *t)
+int ip6_tnl_xmit_ctl(struct ip6_tnl *t,
+		     const struct in6_addr *laddr,
+		     const struct in6_addr *raddr)
 {
 	struct __ip6_tnl_parm *p = &t->parms;
 	int ret = 0;
 	struct net *net = t->net;
 
-	if (p->flags & IP6_TNL_F_CAP_XMIT) {
+	if ((p->flags & IP6_TNL_F_CAP_XMIT) ||
+	    ((p->flags & IP6_TNL_F_CAP_PER_PACKET) &&
+	     (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_XMIT))) {
 		struct net_device *ldev = NULL;
 
 		rcu_read_lock();
 		if (p->link)
 			ldev = dev_get_by_index_rcu(net, p->link);
 
-		if (unlikely(!ipv6_chk_addr(net, &p->laddr, ldev, 0)))
+		if (unlikely(!ipv6_chk_addr(net, laddr, ldev, 0)))
 			pr_warn("%s xmit: Local address not yet configured!\n",
 				p->name);
-		else if (!ipv6_addr_is_multicast(&p->raddr) &&
-			 unlikely(ipv6_chk_addr(net, &p->raddr, NULL, 0)))
+		else if (!ipv6_addr_is_multicast(raddr) &&
+			 unlikely(ipv6_chk_addr(net, raddr, NULL, 0)))
 			pr_warn("%s xmit: Routing loop! Remote address found on this node!\n",
 				p->name);
 		else
@@ -977,6 +981,10 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 
 	if (!fl6->flowi6_mark)
 		dst = ip6_tnl_dst_check(t);
+
+	if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr))
+		goto tx_err_link_failure;
+
 	if (!dst) {
 		ndst = ip6_route_output(net, NULL, fl6);
 
@@ -1086,8 +1094,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	int err;
 
 	tproto = ACCESS_ONCE(t->parms.proto);
-	if ((tproto != IPPROTO_IPIP && tproto != 0) ||
-	    !ip6_tnl_xmit_ctl(t))
+	if (tproto != IPPROTO_IPIP && tproto != 0)
 		return -1;
 
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
@@ -1131,7 +1138,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	tproto = ACCESS_ONCE(t->parms.proto);
 	if ((tproto != IPPROTO_IPV6 && tproto != 0) ||
-	    !ip6_tnl_xmit_ctl(t) || ip6_tnl_addr_conflict(t, ipv6h))
+	    ip6_tnl_addr_conflict(t, ipv6h))
 		return -1;
 
 	offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index d440bb58552..0e8e97e0d38 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -416,6 +416,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	struct net_device_stats *stats = &t->dev->stats;
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;
+	struct xfrm_state *x;
 	int err = -1;
 
 	if (!dst)
@@ -429,7 +430,12 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 		goto tx_err_link_failure;
 	}
 
-	if (!vti6_state_check(dst->xfrm, &t->parms.raddr, &t->parms.laddr))
+	x = dst->xfrm;
+	if (!vti6_state_check(x, &t->parms.raddr, &t->parms.laddr))
+		goto tx_err_link_failure;
+
+	if (!ip6_tnl_xmit_ctl(t, (const struct in6_addr *)&x->props.saddr,
+			      (const struct in6_addr *)&x->id.daddr))
 		goto tx_err_link_failure;
 
 	tdev = dst->dev;
@@ -484,7 +490,7 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		ipv6h = ipv6_hdr(skb);
 
 		if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
-		    !ip6_tnl_xmit_ctl(t) || vti6_addr_conflict(t, ipv6h))
+		    vti6_addr_conflict(t, ipv6h))
 			goto tx_err;
 
 		xfrm_decode_session(skb, &fl, AF_INET6);
-- 
cgit v1.2.3-70-g09d2


From 926c512685ddd8f26f1c789218391530ccd54a35 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 5 Nov 2014 15:42:09 -0800
Subject: sock.h: Remove unused NETDEBUG macro

It's unused now, just delete it.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 7db3db112ba..6767d75ecb1 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2280,9 +2280,6 @@ bool sk_net_capable(const struct sock *sk, int cap);
  *	Enable debug/info messages
  */
 extern int net_msg_warn;
-#define NETDEBUG(fmt, args...) \
-	do { if (net_msg_warn) printk(fmt,##args); } while (0)
-
 #define LIMIT_NETDEBUG(fmt, args...) \
 	do { if (net_msg_warn && net_ratelimit()) printk(fmt,##args); } while(0)
 
-- 
cgit v1.2.3-70-g09d2


From 9b8777e3473e31b2aabd669e5f34866d4a3afb6a Mon Sep 17 00:00:00 2001
From: John Crispin <blogic@openwrt.org>
Date: Thu, 16 Oct 2014 21:48:21 +0200
Subject: serial: of: add a PORT_RT2880 definition

The Ralink RT2880 SoC and its successors have an internal 8250 core. This core
needs the same quirks applied as the AMD AU1xxx uart. In addition to these
quirks, the ports memory region is only 0x100 unlike the AU1xxx which has a
size of 0x1000.

Signed-off-by: John Crispin <blogic@openwrt.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_core.c |  5 ++++-
 drivers/tty/serial/of_serial.c      | 10 +++++++++-
 include/uapi/linux/serial_core.h    |  3 ++-
 3 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 7e78f3077b5..223503299e9 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -2640,8 +2640,11 @@ serial8250_pm(struct uart_port *port, unsigned int state,
 
 static unsigned int serial8250_port_size(struct uart_8250_port *pt)
 {
-	if (pt->port.iotype == UPIO_AU)
+	if (pt->port.iotype == UPIO_AU) {
+		if (pt->port.type == PORT_RT2880)
+			return 0x100;
 		return 0x1000;
+	}
 	if (is_omap1_8250(pt))
 		return 0x16 << pt->port.regshift;
 
diff --git a/drivers/tty/serial/of_serial.c b/drivers/tty/serial/of_serial.c
index 9c64ad2ac1a..8749fb84980 100644
--- a/drivers/tty/serial/of_serial.c
+++ b/drivers/tty/serial/of_serial.c
@@ -130,8 +130,15 @@ static int of_platform_serial_setup(struct platform_device *ofdev,
 
 	port->dev = &ofdev->dev;
 
-	if (type == PORT_TEGRA)
+	switch (type) {
+	case PORT_TEGRA:
 		port->handle_break = tegra_serial_handle_break;
+		break;
+
+	case PORT_RT2880:
+		port->iotype = UPIO_AU;
+		break;
+	}
 
 	return 0;
 out:
@@ -317,6 +324,7 @@ static struct of_device_id of_platform_serial_table[] = {
 	{ .compatible = "ns16850",  .data = (void *)PORT_16850, },
 	{ .compatible = "nvidia,tegra20-uart", .data = (void *)PORT_TEGRA, },
 	{ .compatible = "nxp,lpc3220-uart", .data = (void *)PORT_LPC3220, },
+	{ .compatible = "ralink,rt2880-uart", .data = (void *)PORT_RT2880, },
 	{ .compatible = "altr,16550-FIFO32",
 		.data = (void *)PORT_ALTR_16550_F32, },
 	{ .compatible = "altr,16550-FIFO64",
diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h
index 16ad8521af6..c17218094f1 100644
--- a/include/uapi/linux/serial_core.h
+++ b/include/uapi/linux/serial_core.h
@@ -54,7 +54,8 @@
 #define PORT_ALTR_16550_F32 26	/* Altera 16550 UART with 32 FIFOs */
 #define PORT_ALTR_16550_F64 27	/* Altera 16550 UART with 64 FIFOs */
 #define PORT_ALTR_16550_F128 28 /* Altera 16550 UART with 128 FIFOs */
-#define PORT_MAX_8250	28	/* max port ID */
+#define PORT_RT2880	29	/* Ralink RT2880 internal UART */
+#define PORT_MAX_8250	29	/* max port ID */
 
 /*
  * ARM specific type numbers.  These are not currently guaranteed
-- 
cgit v1.2.3-70-g09d2


From e979f3b712c8b8ae44bab591427f1647dd25aa0d Mon Sep 17 00:00:00 2001
From: Kevin Cernekee <cernekee@gmail.com>
Date: Tue, 21 Oct 2014 15:23:03 -0700
Subject: tty: serial: bcm63xx: Eliminate unnecessary request/release functions

We don't really need to perform the ioremap "on demand" so it's simpler
just to do it from the probe function.  This also lets us eliminate the
UART_REG_SIZE constant and rely on the resource information passed in
from the DT or platform code.

Signed-off-by: Kevin Cernekee <cernekee@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/bcm63xx_uart.c | 30 ++++++++++--------------------
 include/linux/serial_bcm63xx.h    |  2 --
 2 files changed, 10 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c
index 109dea71131..e04e5805ae6 100644
--- a/drivers/tty/serial/bcm63xx_uart.c
+++ b/drivers/tty/serial/bcm63xx_uart.c
@@ -588,20 +588,7 @@ static void bcm_uart_set_termios(struct uart_port *port,
  */
 static int bcm_uart_request_port(struct uart_port *port)
 {
-	unsigned int size;
-
-	size = UART_REG_SIZE;
-	if (!request_mem_region(port->mapbase, size, "bcm63xx")) {
-		dev_err(port->dev, "Memory region busy\n");
-		return -EBUSY;
-	}
-
-	port->membase = ioremap(port->mapbase, size);
-	if (!port->membase) {
-		dev_err(port->dev, "Unable to map registers\n");
-		release_mem_region(port->mapbase, size);
-		return -EBUSY;
-	}
+	/* UARTs always present */
 	return 0;
 }
 
@@ -610,8 +597,7 @@ static int bcm_uart_request_port(struct uart_port *port)
  */
 static void bcm_uart_release_port(struct uart_port *port)
 {
-	release_mem_region(port->mapbase, UART_REG_SIZE);
-	iounmap(port->membase);
+	/* Nothing to release ... */
 }
 
 /*
@@ -833,13 +819,20 @@ static int bcm_uart_probe(struct platform_device *pdev)
 	if (pdev->id < 0 || pdev->id >= BCM63XX_NR_UARTS)
 		return -EINVAL;
 
-	if (ports[pdev->id].membase)
+	port = &ports[pdev->id];
+	if (port->membase)
 		return -EBUSY;
+	memset(port, 0, sizeof(*port));
 
 	res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res_mem)
 		return -ENODEV;
 
+	port->mapbase = res_mem->start;
+	port->membase = devm_ioremap_resource(&pdev->dev, res_mem);
+	if (IS_ERR(port->membase))
+		return PTR_ERR(port->membase);
+
 	res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (!res_irq)
 		return -ENODEV;
@@ -849,10 +842,7 @@ static int bcm_uart_probe(struct platform_device *pdev)
 	if (IS_ERR(clk))
 		return -ENODEV;
 
-	port = &ports[pdev->id];
-	memset(port, 0, sizeof(*port));
 	port->iotype = UPIO_MEM;
-	port->mapbase = res_mem->start;
 	port->irq = res_irq->start;
 	port->ops = &bcm_uart_ops;
 	port->flags = UPF_BOOT_AUTOCONF;
diff --git a/include/linux/serial_bcm63xx.h b/include/linux/serial_bcm63xx.h
index a80aa1a5bee..570e964dc89 100644
--- a/include/linux/serial_bcm63xx.h
+++ b/include/linux/serial_bcm63xx.h
@@ -116,6 +116,4 @@
 					UART_FIFO_PARERR_MASK |		\
 					UART_FIFO_BRKDET_MASK)
 
-#define UART_REG_SIZE			24
-
 #endif /* _LINUX_SERIAL_BCM63XX_H */
-- 
cgit v1.2.3-70-g09d2


From 413ba6385382bc80e4bf2f58efa900e82e810b11 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 5 Nov 2014 12:40:04 -0500
Subject: tty: Convert tty->closing to int

tty->closing is a bitfield member; prevent corruption from non-atomic
update by assigning a unique memory location.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index c52a689e09a..7d66ae508e5 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -284,7 +284,7 @@ struct tty_struct {
 
 #define N_TTY_BUF_SIZE 4096
 
-	unsigned char closing:1;
+	int closing;
 	unsigned char *write_buf;
 	int write_cnt;
 	/* If the tty has a pending do_SAK, queue it here - akpm */
-- 
cgit v1.2.3-70-g09d2


From 732a84a037a4de29b54e0b4e6cb6f9b3813e29e5 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 5 Nov 2014 13:11:43 -0500
Subject: serial: core: Pass termios to set_ldisc() notifications

UART drivers which enable modem status interrupts when switching
to N_PPS line discipline need to determine if modem status
interrupts should be disabled when switching from N_PPS.
Specifically, the set_ldisc() notification needs to evaluate
UART_ENABLE_MS() which requires termios->c_cflag.

Convert in-tree UART drivers to new interface.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_core.c | 4 ++--
 drivers/tty/serial/amba-pl010.c     | 4 ++--
 drivers/tty/serial/atmel_serial.c   | 4 ++--
 drivers/tty/serial/bfin_uart.c      | 5 +++--
 drivers/tty/serial/clps711x.c       | 5 +++--
 drivers/tty/serial/serial_core.c    | 2 +-
 include/linux/serial_core.h         | 2 +-
 7 files changed, 14 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 223503299e9..116b5a75f1a 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -2609,9 +2609,9 @@ serial8250_set_termios(struct uart_port *port, struct ktermios *termios,
 }
 
 static void
-serial8250_set_ldisc(struct uart_port *port, int new)
+serial8250_set_ldisc(struct uart_port *port, struct ktermios *termios)
 {
-	if (new == N_PPS) {
+	if (termios->c_line == N_PPS) {
 		port->flags |= UPF_HARDPPS_CD;
 		serial8250_enable_ms(port);
 	} else
diff --git a/drivers/tty/serial/amba-pl010.c b/drivers/tty/serial/amba-pl010.c
index 00ae8dcabc9..230bc7a290d 100644
--- a/drivers/tty/serial/amba-pl010.c
+++ b/drivers/tty/serial/amba-pl010.c
@@ -479,9 +479,9 @@ pl010_set_termios(struct uart_port *port, struct ktermios *termios,
 	spin_unlock_irqrestore(&uap->port.lock, flags);
 }
 
-static void pl010_set_ldisc(struct uart_port *port, int new)
+static void pl010_set_ldisc(struct uart_port *port, struct ktermios *termios)
 {
-	if (new == N_PPS) {
+	if (termios->c_line == N_PPS) {
 		port->flags |= UPF_HARDPPS_CD;
 		pl010_enable_ms(port);
 	} else
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index b9987109b2d..6a1d960e2e8 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -2056,9 +2056,9 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios,
 	spin_unlock_irqrestore(&port->lock, flags);
 }
 
-static void atmel_set_ldisc(struct uart_port *port, int new)
+static void atmel_set_ldisc(struct uart_port *port, struct ktermios *termios)
 {
-	if (new == N_PPS) {
+	if (termios->c_line == N_PPS) {
 		port->flags |= UPF_HARDPPS_CD;
 		atmel_enable_ms(port);
 	} else {
diff --git a/drivers/tty/serial/bfin_uart.c b/drivers/tty/serial/bfin_uart.c
index 7da9911e95f..44b27ec3234 100644
--- a/drivers/tty/serial/bfin_uart.c
+++ b/drivers/tty/serial/bfin_uart.c
@@ -944,12 +944,13 @@ bfin_serial_verify_port(struct uart_port *port, struct serial_struct *ser)
  * Enable the IrDA function if tty->ldisc.num is N_IRDA.
  * In other cases, disable IrDA function.
  */
-static void bfin_serial_set_ldisc(struct uart_port *port, int ld)
+static void bfin_serial_set_ldisc(struct uart_port *port,
+				  struct ktermios *termios)
 {
 	struct bfin_serial_port *uart = (struct bfin_serial_port *)port;
 	unsigned int val;
 
-	switch (ld) {
+	switch (termios->c_line) {
 	case N_IRDA:
 		val = UART_GET_GCTL(uart);
 		val |= (UMOD_IRDA | RPOLC);
diff --git a/drivers/tty/serial/clps711x.c b/drivers/tty/serial/clps711x.c
index acfe3177364..f963c4c4808 100644
--- a/drivers/tty/serial/clps711x.c
+++ b/drivers/tty/serial/clps711x.c
@@ -225,13 +225,14 @@ static void uart_clps711x_break_ctl(struct uart_port *port, int break_state)
 	writel(ubrlcr, port->membase + UBRLCR_OFFSET);
 }
 
-static void uart_clps711x_set_ldisc(struct uart_port *port, int ld)
+static void uart_clps711x_set_ldisc(struct uart_port *port,
+				    struct ktermios *termios)
 {
 	if (!port->line) {
 		struct clps711x_port *s = dev_get_drvdata(port->dev);
 
 		regmap_update_bits(s->syscon, SYSCON_OFFSET, SYSCON1_SIREN,
-				   (ld == N_IRDA) ? SYSCON1_SIREN : 0);
+				   (termios->c_line == N_IRDA) ? SYSCON1_SIREN : 0);
 	}
 }
 
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 5209eaaa722..c5fb08cfbdb 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1247,7 +1247,7 @@ static void uart_set_ldisc(struct tty_struct *tty)
 
 	if (uport->ops->set_ldisc) {
 		mutex_lock(&state->port.mutex);
-		uport->ops->set_ldisc(uport, tty->termios.c_line);
+		uport->ops->set_ldisc(uport, &tty->termios);
 		mutex_unlock(&state->port.mutex);
 	}
 }
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index ad9329669ab..40b4cc4f8e1 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -63,7 +63,7 @@ struct uart_ops {
 	void		(*flush_buffer)(struct uart_port *);
 	void		(*set_termios)(struct uart_port *, struct ktermios *new,
 				       struct ktermios *old);
-	void		(*set_ldisc)(struct uart_port *, int new);
+	void		(*set_ldisc)(struct uart_port *, struct ktermios *);
 	void		(*pm)(struct uart_port *, unsigned int state,
 			      unsigned int oldstate);
 
-- 
cgit v1.2.3-70-g09d2


From a5f276f10ff70da89b349df445e944c8cd87956c Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Date: Thu, 6 Nov 2014 22:46:13 +0100
Subject: serial_core: Handle TIOC[GS]RS485 ioctls.

The following drivers: 8250_core, atmel_serial, max310x, mcf, omap-serial
and sci16is7xx implement code to handle RS485 ioctls.

In order to avoid code duplication, we implement a simple ioctl handler
on the serial_core layer.

This handler can be used by all the other drivers instead of duplicating
code.

Until this is the only RS485 ioctl handler, it will try first the
rs485_config callback and if it is not present it will call the driver
specific ioctl.

Reviewed-by: Alan Cox <alan@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 45 ++++++++++++++++++++++++++++++++++++++++
 include/linux/serial_core.h      |  3 +++
 2 files changed, 48 insertions(+)

(limited to 'include')

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index c5fb08cfbdb..ab4db1dcc47 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1152,6 +1152,39 @@ static int uart_get_icount(struct tty_struct *tty,
 	return 0;
 }
 
+static int uart_get_rs485_config(struct uart_port *port,
+			 struct serial_rs485 __user *rs485)
+{
+	if (!port->rs485_config)
+		return -ENOIOCTLCMD;
+
+	if (copy_to_user(rs485, &port->rs485, sizeof(port->rs485)))
+		return -EFAULT;
+	return 0;
+}
+
+static int uart_set_rs485_config(struct uart_port *port,
+			 struct serial_rs485 __user *rs485_user)
+{
+	struct serial_rs485 rs485;
+	int ret;
+
+	if (!port->rs485_config)
+		return -ENOIOCTLCMD;
+
+	if (copy_from_user(&rs485, rs485_user, sizeof(*rs485_user)))
+		return -EFAULT;
+
+	ret = port->rs485_config(port, &rs485);
+	if (ret)
+		return ret;
+
+	if (copy_to_user(rs485_user, &port->rs485, sizeof(port->rs485)))
+		return -EFAULT;
+
+	return 0;
+}
+
 /*
  * Called via sys_ioctl.  We can use spin_lock_irq() here.
  */
@@ -1223,6 +1256,18 @@ uart_ioctl(struct tty_struct *tty, unsigned int cmd,
 	 * protected against the tty being hung up.
 	 */
 	switch (cmd) {
+	case TIOCGRS485:
+		ret = uart_get_rs485_config(state->uart_port, uarg);
+		break;
+
+	case TIOCSRS485:
+		ret = uart_set_rs485_config(state->uart_port, uarg);
+		break;
+	}
+	if (ret != -ENOIOCTLCMD)
+		goto out;
+
+	switch (cmd) {
 	case TIOCSERGETLSR: /* Get line status register */
 		ret = uart_get_lsr_info(tty, state, uarg);
 		break;
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 40b4cc4f8e1..3231a43f6ac 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -131,6 +131,8 @@ struct uart_port {
 	void			(*pm)(struct uart_port *, unsigned int state,
 				      unsigned int old);
 	void			(*handle_break)(struct uart_port *);
+	int			(*rs485_config)(struct uart_port *,
+						struct serial_rs485 *rs485);
 	unsigned int		irq;			/* irq number */
 	unsigned long		irqflags;		/* irq flags  */
 	unsigned int		uartclk;		/* base uart clock */
@@ -231,6 +233,7 @@ struct uart_port {
 	unsigned char		unused[2];
 	struct attribute_group	*attr_group;		/* port specific attributes */
 	const struct attribute_group **tty_groups;	/* all attributes (serial core use only) */
+	struct serial_rs485     rs485;
 	void			*private_data;		/* generic platform data pointer */
 };
 
-- 
cgit v1.2.3-70-g09d2


From 039ec1f010e6b058f497381d5a6bb840e160b4ac Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Date: Thu, 6 Nov 2014 09:22:53 +0100
Subject: serial/8250: Remove obsolete handling of rs485 ioctls

There is no more users for this functions. All the 8250 drivers are
using the rs485 handler on serial_core instead.

Reviewed-by: Alan Cox <alan@linux.intel.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Alan Cox <alan@linux.intel.com>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: Yoshihiro YUNOMAE <yoshihiro.yunomae.ez@hitachi.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_core.c | 39 -------------------------------------
 include/linux/serial_8250.h         |  3 ---
 2 files changed, 42 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 3f2c6576ab4..30522d68001 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -3005,42 +3005,6 @@ serial8250_verify_port(struct uart_port *port, struct serial_struct *ser)
 	return 0;
 }
 
-static int serial8250_ioctl(struct uart_port *port, unsigned int cmd,
-			   unsigned long arg)
-{
-	struct uart_8250_port *up =
-		container_of(port, struct uart_8250_port, port);
-	int ret;
-	struct serial_rs485 rs485_config;
-
-	if (!up->rs485_config)
-		return -ENOIOCTLCMD;
-
-	switch (cmd) {
-	case TIOCSRS485:
-		if (copy_from_user(&rs485_config, (void __user *)arg,
-				   sizeof(rs485_config)))
-			return -EFAULT;
-
-		ret = up->rs485_config(up, &rs485_config);
-		if (ret)
-			return ret;
-
-		memcpy(&up->rs485, &rs485_config, sizeof(rs485_config));
-
-		return 0;
-	case TIOCGRS485:
-		if (copy_to_user((void __user *)arg, &up->rs485,
-				 sizeof(up->rs485)))
-			return -EFAULT;
-		return 0;
-	default:
-		break;
-	}
-
-	return -ENOIOCTLCMD;
-}
-
 static const char *
 serial8250_type(struct uart_port *port)
 {
@@ -3072,7 +3036,6 @@ static struct uart_ops serial8250_pops = {
 	.request_port	= serial8250_request_port,
 	.config_port	= serial8250_config_port,
 	.verify_port	= serial8250_verify_port,
-	.ioctl		= serial8250_ioctl,
 #ifdef CONFIG_CONSOLE_POLL
 	.poll_get_char = serial8250_get_poll_char,
 	.poll_put_char = serial8250_put_poll_char,
@@ -3615,8 +3578,6 @@ int serial8250_register_8250_port(struct uart_8250_port *up)
 		uart->port.fifosize	= up->port.fifosize;
 		uart->tx_loadsz		= up->tx_loadsz;
 		uart->capabilities	= up->capabilities;
-		uart->rs485_config	= up->rs485_config;
-		uart->rs485		= up->rs485;
 		uart->port.throttle	= up->port.throttle;
 		uart->port.unthrottle	= up->port.unthrottle;
 		uart->port.rs485_config	= up->port.rs485_config;
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index 3df10d5f154..e02acf0a0ec 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -97,13 +97,10 @@ struct uart_8250_port {
 	unsigned char		msr_saved_flags;
 
 	struct uart_8250_dma	*dma;
-	struct serial_rs485     rs485;
 
 	/* 8250 specific callbacks */
 	int			(*dl_read)(struct uart_8250_port *);
 	void			(*dl_write)(struct uart_8250_port *, int);
-	int			(*rs485_config)(struct uart_8250_port *,
-						struct serial_rs485 *rs485);
 };
 
 static inline struct uart_8250_port *up_to_u8250p(struct uart_port *up)
-- 
cgit v1.2.3-70-g09d2


From 8a8ae62f8296760a2a1eee7009a1444c327603e0 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Thu, 6 Nov 2014 16:56:33 +0100
Subject: tty: warn on deprecated serial flags

When somebody calls TIOCSSERIAL ioctl with serial flags to set one of
* ASYNC_SESSION_LOCKOUT
* ASYNC_PGRP_LOCKOUT
* ASYNC_CALLOUT_NOHUP
* ASYNC_AUTOPROBE
nothing happens. We actually ignore the flags for over a decade at
least (I checked 2.6.0).

So start yelling at users who use those flags, that they shouldn't.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c           | 21 +++++++++++++++++++++
 include/uapi/linux/tty_flags.h |  2 ++
 2 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 01d45fd7d35..705885891b8 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2760,6 +2760,24 @@ static int tty_tiocgicount(struct tty_struct *tty, void __user *arg)
 	return 0;
 }
 
+static void tty_warn_deprecated_flags(struct serial_struct __user *ss)
+{
+	static DEFINE_RATELIMIT_STATE(depr_flags,
+			DEFAULT_RATELIMIT_INTERVAL,
+			DEFAULT_RATELIMIT_BURST);
+	char comm[TASK_COMM_LEN];
+	int flags;
+
+	if (get_user(flags, &ss->flags))
+		return;
+
+	flags &= ASYNC_DEPRECATED;
+
+	if (flags && __ratelimit(&depr_flags))
+		pr_warning("%s: '%s' is using deprecated serial flags (with no effect): %.8x\n",
+				__func__, get_task_comm(comm, current), flags);
+}
+
 /*
  * if pty, return the slave side (real_tty)
  * otherwise, return self
@@ -2903,6 +2921,9 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			break;
 		}
 		break;
+	case TIOCSSERIAL:
+		tty_warn_deprecated_flags(p);
+		break;
 	}
 	if (tty->ops->ioctl) {
 		retval = tty->ops->ioctl(tty, cmd, arg);
diff --git a/include/uapi/linux/tty_flags.h b/include/uapi/linux/tty_flags.h
index d2bc4ff94f4..fae4864737f 100644
--- a/include/uapi/linux/tty_flags.h
+++ b/include/uapi/linux/tty_flags.h
@@ -64,6 +64,8 @@
 #define ASYNC_MAGIC_MULTIPLIER	(1U << ASYNCB_MAGIC_MULTIPLIER)
 
 #define ASYNC_FLAGS		((1U << (ASYNCB_LAST_USER + 1)) - 1)
+#define ASYNC_DEPRECATED	(ASYNC_SESSION_LOCKOUT | ASYNC_PGRP_LOCKOUT | \
+		ASYNC_CALLOUT_NOHUP | ASYNC_AUTOPROBE)
 #define ASYNC_USR_MASK		(ASYNC_SPD_MASK|ASYNC_CALLOUT_NOHUP| \
 		ASYNC_LOW_LATENCY)
 #define ASYNC_SPD_CUST		(ASYNC_SPD_HI|ASYNC_SPD_VHI)
-- 
cgit v1.2.3-70-g09d2


From c3b50dc219e1437e4dcb6a1639b004648dc29faa Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Tue, 28 Oct 2014 17:40:41 +0100
Subject: core: platform: let platform_driver_probe initialize module owner

Since commit 9447057eaff8 ("platform_device: use a macro instead of
platform_driver_register"), platform_driver_register() always overwrites
the .owner field of a platform_driver with THIS_MODULE. This breaks
platform_driver_probe() which uses it from within the platform core
instead of the module init. Fix it by using a similar #define construct
to obtain THIS_MODULE and pass it on later.

Reported-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/platform.c         | 11 ++++++-----
 include/linux/platform_device.h |  6 ++++--
 2 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index b2afc29403f..c87a6332687 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -580,9 +580,10 @@ void platform_driver_unregister(struct platform_driver *drv)
 EXPORT_SYMBOL_GPL(platform_driver_unregister);
 
 /**
- * platform_driver_probe - register driver for non-hotpluggable device
+ * __platform_driver_probe - register driver for non-hotpluggable device
  * @drv: platform driver structure
  * @probe: the driver probe routine, probably from an __init section
+ * @module: module which will be the owner of the driver
  *
  * Use this instead of platform_driver_register() when you know the device
  * is not hotpluggable and has already been registered, and you want to
@@ -598,8 +599,8 @@ EXPORT_SYMBOL_GPL(platform_driver_unregister);
  * Returns zero if the driver registered and bound to a device, else returns
  * a negative error code and with the driver not registered.
  */
-int __init_or_module platform_driver_probe(struct platform_driver *drv,
-		int (*probe)(struct platform_device *))
+int __init_or_module __platform_driver_probe(struct platform_driver *drv,
+		int (*probe)(struct platform_device *), struct module *module)
 {
 	int retval, code;
 
@@ -614,7 +615,7 @@ int __init_or_module platform_driver_probe(struct platform_driver *drv,
 
 	/* temporary section violation during probe() */
 	drv->probe = probe;
-	retval = code = platform_driver_register(drv);
+	retval = code = __platform_driver_register(drv, module);
 
 	/*
 	 * Fixup that section violation, being paranoid about code scanning
@@ -633,7 +634,7 @@ int __init_or_module platform_driver_probe(struct platform_driver *drv,
 		platform_driver_unregister(drv);
 	return retval;
 }
-EXPORT_SYMBOL_GPL(platform_driver_probe);
+EXPORT_SYMBOL_GPL(__platform_driver_probe);
 
 /**
  * platform_create_bundle - register driver and create corresponding device
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 153d303af7e..c8d95c60da1 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -197,8 +197,10 @@ extern void platform_driver_unregister(struct platform_driver *);
 /* non-hotpluggable platform devices may use this so that probe() and
  * its support may live in __init sections, conserving runtime memory.
  */
-extern int platform_driver_probe(struct platform_driver *driver,
-		int (*probe)(struct platform_device *));
+#define platform_driver_probe(drv, probe) \
+	__platform_driver_probe(drv, probe, THIS_MODULE)
+extern int __platform_driver_probe(struct platform_driver *driver,
+		int (*probe)(struct platform_device *), struct module *module);
 
 static inline void *platform_get_drvdata(const struct platform_device *pdev)
 {
-- 
cgit v1.2.3-70-g09d2


From 291f653a140ad880426125e5e9dbb70f4c184683 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Tue, 28 Oct 2014 17:40:42 +0100
Subject: core: platform: let platform_create_bundle initialize module owner

Since commit 9447057eaff8 ("platform_device: use a macro instead of
platform_driver_register"), platform_driver_register() always overwrites
the .owner field of a platform_driver with THIS_MODULE. This breaks
platform_create_bundle() which uses it via platform_driver_probe() from
within the platform core instead of the module init. Fix it by using a
similar #define construct to obtain THIS_MODULE and pass it on later.

Reported-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/platform.c         | 11 ++++++-----
 include/linux/platform_device.h |  6 ++++--
 2 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index c87a6332687..cdb6c076c3f 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -637,24 +637,25 @@ int __init_or_module __platform_driver_probe(struct platform_driver *drv,
 EXPORT_SYMBOL_GPL(__platform_driver_probe);
 
 /**
- * platform_create_bundle - register driver and create corresponding device
+ * __platform_create_bundle - register driver and create corresponding device
  * @driver: platform driver structure
  * @probe: the driver probe routine, probably from an __init section
  * @res: set of resources that needs to be allocated for the device
  * @n_res: number of resources
  * @data: platform specific data for this platform device
  * @size: size of platform specific data
+ * @module: module which will be the owner of the driver
  *
  * Use this in legacy-style modules that probe hardware directly and
  * register a single platform device and corresponding platform driver.
  *
  * Returns &struct platform_device pointer on success, or ERR_PTR() on error.
  */
-struct platform_device * __init_or_module platform_create_bundle(
+struct platform_device * __init_or_module __platform_create_bundle(
 			struct platform_driver *driver,
 			int (*probe)(struct platform_device *),
 			struct resource *res, unsigned int n_res,
-			const void *data, size_t size)
+			const void *data, size_t size, struct module *module)
 {
 	struct platform_device *pdev;
 	int error;
@@ -677,7 +678,7 @@ struct platform_device * __init_or_module platform_create_bundle(
 	if (error)
 		goto err_pdev_put;
 
-	error = platform_driver_probe(driver, probe);
+	error = __platform_driver_probe(driver, probe, module);
 	if (error)
 		goto err_pdev_del;
 
@@ -690,7 +691,7 @@ err_pdev_put:
 err_out:
 	return ERR_PTR(error);
 }
-EXPORT_SYMBOL_GPL(platform_create_bundle);
+EXPORT_SYMBOL_GPL(__platform_create_bundle);
 
 /* modalias support enables more hands-off userspace setup:
  * (a) environment variable lets new-style hotplug events work once system is
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index c8d95c60da1..ae4882ca4a6 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -240,10 +240,12 @@ static void __exit __platform_driver##_exit(void) \
 } \
 module_exit(__platform_driver##_exit);
 
-extern struct platform_device *platform_create_bundle(
+#define platform_create_bundle(driver, probe, res, n_res, data, size) \
+	__platform_create_bundle(driver, probe, res, n_res, data, size, THIS_MODULE)
+extern struct platform_device *__platform_create_bundle(
 	struct platform_driver *driver, int (*probe)(struct platform_device *),
 	struct resource *res, unsigned int n_res,
-	const void *data, size_t size);
+	const void *data, size_t size, struct module *module);
 
 /* early platform driver interface */
 struct early_platform_driver {
-- 
cgit v1.2.3-70-g09d2


From 38737d82f9f0168955f9944c3f8bd3bb262c7e88 Mon Sep 17 00:00:00 2001
From: Yijing Wang <wangyijing@huawei.com>
Date: Mon, 27 Oct 2014 10:44:36 +0800
Subject: PCI/MSI: Add pci_msi_ignore_mask to prevent writes to MSI/MSI-X Mask
 Bits

MSI-X vector Mask Bits are in MSI-X Tables in PCI memory space.  Xen PV
guests can't write to those tables.  MSI vector Mask Bits are in PCI
configuration space.  Xen PV guests can write to config space, but those
writes are ignored.

Commit 0e4ccb1505a9 ("PCI: Add x86_msi.msi_mask_irq() and
msix_mask_irq()") added a way to override default_mask_msi_irqs() and
default_mask_msix_irqs() so they can be no-ops in Xen guests, but this is
more complicated than necessary.

Add "pci_msi_ignore_mask" in the core PCI MSI code.  If set,
default_mask_msi_irqs() and default_mask_msix_irqs() return without doing
anything.  This is less flexible, but much simpler.

[bhelgaas: changelog]
Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
CC: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
CC: xen-devel@lists.xenproject.org
---
 arch/x86/pci/xen.c  | 2 ++
 drivers/pci/msi.c   | 7 ++++++-
 include/linux/msi.h | 1 +
 3 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 093f5f4272d..5ef62ed20ba 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -427,6 +427,7 @@ int __init pci_xen_init(void)
 	x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs;
 	x86_msi.msi_mask_irq = xen_nop_msi_mask_irq;
 	x86_msi.msix_mask_irq = xen_nop_msix_mask_irq;
+	pci_msi_ignore_mask = 1;
 #endif
 	return 0;
 }
@@ -508,6 +509,7 @@ int __init pci_xen_initial_domain(void)
 	x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs;
 	x86_msi.msi_mask_irq = xen_nop_msi_mask_irq;
 	x86_msi.msix_mask_irq = xen_nop_msix_mask_irq;
+	pci_msi_ignore_mask = 1;
 #endif
 	xen_setup_acpi_sci();
 	__acpi_register_gsi = acpi_register_gsi_xen;
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 9fab30af0e7..066c2fb9763 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -23,6 +23,7 @@
 #include "pci.h"
 
 static int pci_msi_enable = 1;
+int pci_msi_ignore_mask;
 
 #define msix_table_size(flags)	((flags & PCI_MSIX_FLAGS_QSIZE) + 1)
 
@@ -167,7 +168,7 @@ u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 {
 	u32 mask_bits = desc->masked;
 
-	if (!desc->msi_attrib.maskbit)
+	if (pci_msi_ignore_mask || !desc->msi_attrib.maskbit)
 		return 0;
 
 	mask_bits &= ~mask;
@@ -199,6 +200,10 @@ u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag)
 	u32 mask_bits = desc->masked;
 	unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
 						PCI_MSIX_ENTRY_VECTOR_CTRL;
+
+	if (pci_msi_ignore_mask)
+		return 0;
+
 	mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
 	if (flag)
 		mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 44f4746d033..86dc501a153 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -10,6 +10,7 @@ struct msi_msg {
 	u32	data;		/* 16 bits of msi message data */
 };
 
+extern int pci_msi_ignore_mask;
 /* Helper functions */
 struct irq_data;
 struct msi_desc;
-- 
cgit v1.2.3-70-g09d2


From 245bd6f6af8a62a2e2e14976e5ef3dc2b82ec153 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 6 Nov 2014 15:51:00 +0200
Subject: PM / clock_ops: Add pm_clk_add_clk()

The existing pm_clk_add() allows to pass a clock by con_id. However,
when referring to a specific clock from DT, no con_id is available.

Add pm_clk_add_clk(), which allows to specify the struct clk * directly.
The will will increment refcount on clock pointer, so the caller has
to use clk_put() on clock pointer when done.

Reviewed-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Reviewed-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Reviewed-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/clock_ops.c | 47 +++++++++++++++++++++++++++++++++---------
 include/linux/pm_clock.h       |  8 +++++++
 2 files changed, 45 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index 78369305e06..f061eaa48bb 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -12,6 +12,7 @@
 #include <linux/pm.h>
 #include <linux/pm_clock.h>
 #include <linux/clk.h>
+#include <linux/clkdev.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 
@@ -53,7 +54,8 @@ static inline int __pm_clk_enable(struct device *dev, struct clk *clk)
  */
 static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce)
 {
-	ce->clk = clk_get(dev, ce->con_id);
+	if (!ce->clk)
+		ce->clk = clk_get(dev, ce->con_id);
 	if (IS_ERR(ce->clk)) {
 		ce->status = PCE_STATUS_ERROR;
 	} else {
@@ -63,15 +65,8 @@ static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce)
 	}
 }
 
-/**
- * pm_clk_add - Start using a device clock for power management.
- * @dev: Device whose clock is going to be used for power management.
- * @con_id: Connection ID of the clock.
- *
- * Add the clock represented by @con_id to the list of clocks used for
- * the power management of @dev.
- */
-int pm_clk_add(struct device *dev, const char *con_id)
+static int __pm_clk_add(struct device *dev, const char *con_id,
+			struct clk *clk)
 {
 	struct pm_subsys_data *psd = dev_to_psd(dev);
 	struct pm_clock_entry *ce;
@@ -93,6 +88,12 @@ int pm_clk_add(struct device *dev, const char *con_id)
 			kfree(ce);
 			return -ENOMEM;
 		}
+	} else {
+		if (IS_ERR(ce->clk) || !__clk_get(clk)) {
+			kfree(ce);
+			return -ENOENT;
+		}
+		ce->clk = clk;
 	}
 
 	pm_clk_acquire(dev, ce);
@@ -103,6 +104,32 @@ int pm_clk_add(struct device *dev, const char *con_id)
 	return 0;
 }
 
+/**
+ * pm_clk_add - Start using a device clock for power management.
+ * @dev: Device whose clock is going to be used for power management.
+ * @con_id: Connection ID of the clock.
+ *
+ * Add the clock represented by @con_id to the list of clocks used for
+ * the power management of @dev.
+ */
+int pm_clk_add(struct device *dev, const char *con_id)
+{
+	return __pm_clk_add(dev, con_id, NULL);
+}
+
+/**
+ * pm_clk_add_clk - Start using a device clock for power management.
+ * @dev: Device whose clock is going to be used for power management.
+ * @clk: Clock pointer
+ *
+ * Add the clock to the list of clocks used for the power management of @dev.
+ * It will increment refcount on clock pointer, use clk_put() on it when done.
+ */
+int pm_clk_add_clk(struct device *dev, struct clk *clk)
+{
+	return __pm_clk_add(dev, NULL, clk);
+}
+
 /**
  * __pm_clk_remove - Destroy PM clock entry.
  * @ce: PM clock entry to destroy.
diff --git a/include/linux/pm_clock.h b/include/linux/pm_clock.h
index 8348866e7b0..0b003963441 100644
--- a/include/linux/pm_clock.h
+++ b/include/linux/pm_clock.h
@@ -18,6 +18,8 @@ struct pm_clk_notifier_block {
 	char *con_ids[];
 };
 
+struct clk;
+
 #ifdef CONFIG_PM_CLK
 static inline bool pm_clk_no_clocks(struct device *dev)
 {
@@ -29,6 +31,7 @@ extern void pm_clk_init(struct device *dev);
 extern int pm_clk_create(struct device *dev);
 extern void pm_clk_destroy(struct device *dev);
 extern int pm_clk_add(struct device *dev, const char *con_id);
+extern int pm_clk_add_clk(struct device *dev, struct clk *clk);
 extern void pm_clk_remove(struct device *dev, const char *con_id);
 extern int pm_clk_suspend(struct device *dev);
 extern int pm_clk_resume(struct device *dev);
@@ -51,6 +54,11 @@ static inline int pm_clk_add(struct device *dev, const char *con_id)
 {
 	return -EINVAL;
 }
+
+static inline int pm_clk_add_clk(struct device *dev, struct clk *clk)
+{
+	return -EINVAL;
+}
 static inline void pm_clk_remove(struct device *dev, const char *con_id)
 {
 }
-- 
cgit v1.2.3-70-g09d2


From b07597367001c2c4f36a97863530f71b84060d3d Mon Sep 17 00:00:00 2001
From: Padmavathi Venna <padma.v@samsung.com>
Date: Fri, 7 Nov 2014 12:24:39 +0530
Subject: ASoC: Samsung: Add quirk for internal DMA

Internal DMA is available only on some of Samsung platforms.
So added a quirk for the same and made it optional.

Signed-off-by: Padmavathi Venna <padma.v@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/platform_data/asoc-s3c.h |  1 +
 sound/soc/samsung/i2s.c                | 12 ++++++------
 2 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/platform_data/asoc-s3c.h b/include/linux/platform_data/asoc-s3c.h
index a6591c693eb..5e0bc779e6c 100644
--- a/include/linux/platform_data/asoc-s3c.h
+++ b/include/linux/platform_data/asoc-s3c.h
@@ -27,6 +27,7 @@ struct samsung_i2s {
 #define QUIRK_NO_MUXPSR		(1 << 2)
 #define QUIRK_NEED_RSTCLR	(1 << 3)
 #define QUIRK_SUPPORTS_TDM	(1 << 4)
+#define QUIRK_SUPPORTS_IDMA	(1 << 5)
 	/* Quirks of the I2S controller */
 	u32 quirks;
 	dma_addr_t idma_addr;
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 9d513473b30..38b9a524cc9 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -987,7 +987,7 @@ static int samsung_i2s_dai_probe(struct snd_soc_dai *dai)
 	if (i2s->quirks & QUIRK_NEED_RSTCLR)
 		writel(CON_RSTCLR, i2s->addr + I2SCON);
 
-	if (i2s->quirks & QUIRK_SEC_DAI)
+	if (i2s->quirks & QUIRK_SUPPORTS_IDMA)
 		idma_reg_addr_init(i2s->addr,
 					i2s->sec_dai->idma_playback.dma_addr);
 
@@ -1199,10 +1199,9 @@ static int samsung_i2s_probe(struct platform_device *pdev)
 		quirks = i2s_dai_data->quirks;
 		if (of_property_read_u32(np, "samsung,idma-addr",
 					 &idma_addr)) {
-			if (quirks & QUIRK_SEC_DAI) {
-				dev_err(&pdev->dev, "idma address is not"\
+			if (quirks & QUIRK_SUPPORTS_IDMA) {
+				dev_info(&pdev->dev, "idma address is not"\
 						"specified");
-				return -EINVAL;
 			}
 		}
 	}
@@ -1309,13 +1308,14 @@ static const struct samsung_i2s_dai_data i2sv3_dai_type = {
 
 static const struct samsung_i2s_dai_data i2sv5_dai_type = {
 	.dai_type = TYPE_PRI,
-	.quirks = QUIRK_PRI_6CHAN | QUIRK_SEC_DAI | QUIRK_NEED_RSTCLR,
+	.quirks = QUIRK_PRI_6CHAN | QUIRK_SEC_DAI | QUIRK_NEED_RSTCLR |
+			QUIRK_SUPPORTS_IDMA,
 };
 
 static const struct samsung_i2s_dai_data i2sv6_dai_type = {
 	.dai_type = TYPE_PRI,
 	.quirks = QUIRK_PRI_6CHAN | QUIRK_SEC_DAI | QUIRK_NEED_RSTCLR |
-			QUIRK_SUPPORTS_TDM,
+			QUIRK_SUPPORTS_TDM | QUIRK_SUPPORTS_IDMA,
 };
 
 static const struct samsung_i2s_dai_data samsung_dai_type_pri = {
-- 
cgit v1.2.3-70-g09d2


From b9ec1c9da64f0c1d130beb125a916d0725363ec9 Mon Sep 17 00:00:00 2001
From: Chris Rorvick <chris@rorvick.com>
Date: Tue, 4 Nov 2014 19:18:45 -0600
Subject: usb: Create separate header for ehci-dbgp

The FUSBH200 and FOTG210 controllers implement sufficiently EHCI-
compatible debug ports to leverage ehci-dbgp from their respective
drivers.  Rather than including <linux/usb/ehci_def.h> header, though,
they replicate the necessary declarations in their own headers.  Move
the ehci-dbgp stuff into its own header as a first step towards removing
this redundancy.

Signed-off-by: Chris Rorvick <chris@rorvick.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/ehci-dbgp.h | 84 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/usb/ehci_def.h  | 65 ++-------------------------------
 2 files changed, 86 insertions(+), 63 deletions(-)
 create mode 100644 include/linux/usb/ehci-dbgp.h

(limited to 'include')

diff --git a/include/linux/usb/ehci-dbgp.h b/include/linux/usb/ehci-dbgp.h
new file mode 100644
index 00000000000..796c1cd6f26
--- /dev/null
+++ b/include/linux/usb/ehci-dbgp.h
@@ -0,0 +1,84 @@
+/*
+ * Standalone EHCI usb debug driver
+ *
+ * Originally written by:
+ *  Eric W. Biederman" <ebiederm@xmission.com> and
+ *  Yinghai Lu <yhlu.kernel@gmail.com>
+ *
+ * Changes for early/late printk and HW errata:
+ *  Jason Wessel <jason.wessel@windriver.com>
+ *  Copyright (C) 2009 Wind River Systems, Inc.
+ *
+ */
+
+#ifndef __LINUX_USB_EHCI_DBGP_H
+#define __LINUX_USB_EHCI_DBGP_H
+
+#include <linux/console.h>
+#include <linux/types.h>
+
+/* Appendix C, Debug port ... intended for use with special "debug devices"
+ * that can help if there's no serial console.  (nonstandard enumeration.)
+ */
+struct ehci_dbg_port {
+	u32	control;
+#define DBGP_OWNER	(1<<30)
+#define DBGP_ENABLED	(1<<28)
+#define DBGP_DONE	(1<<16)
+#define DBGP_INUSE	(1<<10)
+#define DBGP_ERRCODE(x)	(((x)>>7)&0x07)
+#	define DBGP_ERR_BAD	1
+#	define DBGP_ERR_SIGNAL	2
+#define DBGP_ERROR	(1<<6)
+#define DBGP_GO		(1<<5)
+#define DBGP_OUT	(1<<4)
+#define DBGP_LEN(x)	(((x)>>0)&0x0f)
+	u32	pids;
+#define DBGP_PID_GET(x)		(((x)>>16)&0xff)
+#define DBGP_PID_SET(data, tok)	(((data)<<8)|(tok))
+	u32	data03;
+	u32	data47;
+	u32	address;
+#define DBGP_EPADDR(dev, ep)	(((dev)<<8)|(ep))
+};
+
+#ifdef CONFIG_EARLY_PRINTK_DBGP
+#include <linux/init.h>
+extern int __init early_dbgp_init(char *s);
+extern struct console early_dbgp_console;
+#endif /* CONFIG_EARLY_PRINTK_DBGP */
+
+struct usb_hcd;
+
+#ifdef CONFIG_XEN_DOM0
+extern int xen_dbgp_reset_prep(struct usb_hcd *);
+extern int xen_dbgp_external_startup(struct usb_hcd *);
+#else
+static inline int xen_dbgp_reset_prep(struct usb_hcd *hcd)
+{
+	return 1; /* Shouldn't this be 0? */
+}
+
+static inline int xen_dbgp_external_startup(struct usb_hcd *hcd)
+{
+	return -1;
+}
+#endif
+
+#ifdef CONFIG_EARLY_PRINTK_DBGP
+/* Call backs from ehci host driver to ehci debug driver */
+extern int dbgp_external_startup(struct usb_hcd *);
+extern int dbgp_reset_prep(struct usb_hcd *);
+#else
+static inline int dbgp_reset_prep(struct usb_hcd *hcd)
+{
+	return xen_dbgp_reset_prep(hcd);
+}
+
+static inline int dbgp_external_startup(struct usb_hcd *hcd)
+{
+	return xen_dbgp_external_startup(hcd);
+}
+#endif
+
+#endif /* __LINUX_USB_EHCI_DBGP_H */
diff --git a/include/linux/usb/ehci_def.h b/include/linux/usb/ehci_def.h
index daec99af5d5..966889a20ea 100644
--- a/include/linux/usb/ehci_def.h
+++ b/include/linux/usb/ehci_def.h
@@ -19,6 +19,8 @@
 #ifndef __LINUX_USB_EHCI_DEF_H
 #define __LINUX_USB_EHCI_DEF_H
 
+#include <linux/usb/ehci-dbgp.h>
+
 /* EHCI register interface, corresponds to EHCI Revision 0.95 specification */
 
 /* Section 2.2 Host Controller Capability Registers */
@@ -190,67 +192,4 @@ struct ehci_regs {
 #define USBMODE_EX_HC	(3<<0)		/* host controller mode */
 };
 
-/* Appendix C, Debug port ... intended for use with special "debug devices"
- * that can help if there's no serial console.  (nonstandard enumeration.)
- */
-struct ehci_dbg_port {
-	u32	control;
-#define DBGP_OWNER	(1<<30)
-#define DBGP_ENABLED	(1<<28)
-#define DBGP_DONE	(1<<16)
-#define DBGP_INUSE	(1<<10)
-#define DBGP_ERRCODE(x)	(((x)>>7)&0x07)
-#	define DBGP_ERR_BAD	1
-#	define DBGP_ERR_SIGNAL	2
-#define DBGP_ERROR	(1<<6)
-#define DBGP_GO		(1<<5)
-#define DBGP_OUT	(1<<4)
-#define DBGP_LEN(x)	(((x)>>0)&0x0f)
-	u32	pids;
-#define DBGP_PID_GET(x)		(((x)>>16)&0xff)
-#define DBGP_PID_SET(data, tok)	(((data)<<8)|(tok))
-	u32	data03;
-	u32	data47;
-	u32	address;
-#define DBGP_EPADDR(dev, ep)	(((dev)<<8)|(ep))
-};
-
-#ifdef CONFIG_EARLY_PRINTK_DBGP
-#include <linux/init.h>
-extern int __init early_dbgp_init(char *s);
-extern struct console early_dbgp_console;
-#endif /* CONFIG_EARLY_PRINTK_DBGP */
-
-struct usb_hcd;
-
-#ifdef CONFIG_XEN_DOM0
-extern int xen_dbgp_reset_prep(struct usb_hcd *);
-extern int xen_dbgp_external_startup(struct usb_hcd *);
-#else
-static inline int xen_dbgp_reset_prep(struct usb_hcd *hcd)
-{
-	return 1; /* Shouldn't this be 0? */
-}
-
-static inline int xen_dbgp_external_startup(struct usb_hcd *hcd)
-{
-	return -1;
-}
-#endif
-
-#ifdef CONFIG_EARLY_PRINTK_DBGP
-/* Call backs from ehci host driver to ehci debug driver */
-extern int dbgp_external_startup(struct usb_hcd *);
-extern int dbgp_reset_prep(struct usb_hcd *hcd);
-#else
-static inline int dbgp_reset_prep(struct usb_hcd *hcd)
-{
-	return xen_dbgp_reset_prep(hcd);
-}
-static inline int dbgp_external_startup(struct usb_hcd *hcd)
-{
-	return xen_dbgp_external_startup(hcd);
-}
-#endif
-
 #endif /* __LINUX_USB_EHCI_DEF_H */
-- 
cgit v1.2.3-70-g09d2


From 35a27eab6f94e15fa30f7662af00fbec50526f4a Mon Sep 17 00:00:00 2001
From: Chris Rorvick <chris@rorvick.com>
Date: Tue, 4 Nov 2014 19:18:54 -0600
Subject: usb: Remove __init from early_dbgp_init() prototype

Specifying these attributes in both the prototype and the function
definition is unnecessary and could cause confusion or bugs if they are
inconsistent.  As such, __init should only be specified at the function
definition.

Keith Owens suggested this as a janitorial task on LKML several years
ago:

  https://lkml.org/lkml/2006/1/14/305

Signed-off-by: Chris Rorvick <chris@rorvick.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/ehci-dbgp.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/usb/ehci-dbgp.h b/include/linux/usb/ehci-dbgp.h
index 796c1cd6f26..7344d9e591c 100644
--- a/include/linux/usb/ehci-dbgp.h
+++ b/include/linux/usb/ehci-dbgp.h
@@ -43,8 +43,7 @@ struct ehci_dbg_port {
 };
 
 #ifdef CONFIG_EARLY_PRINTK_DBGP
-#include <linux/init.h>
-extern int __init early_dbgp_init(char *s);
+extern int early_dbgp_init(char *s);
 extern struct console early_dbgp_console;
 #endif /* CONFIG_EARLY_PRINTK_DBGP */
 
-- 
cgit v1.2.3-70-g09d2


From a8f820aa4066d2c97e75ecd1bbca8a7920b66f2c Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Fri, 7 Nov 2014 21:22:22 +0800
Subject: inet: Add skb_copy_datagram_iter

This patch adds skb_copy_datagram_iter, which is identical to
skb_copy_datagram_iovec except that it operates on iov_iter
instead of iovec.

Eventually all users of skb_copy_datagram_iovec should switch
over to iov_iter and then we can remove skb_copy_datagram_iovec.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  3 ++
 net/core/datagram.c    | 87 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 90 insertions(+)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 53f4f6c9335..933cfce7fcd 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -150,6 +150,7 @@
 struct net_device;
 struct scatterlist;
 struct pipe_inode_info;
+struct iov_iter;
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 struct nf_conntrack {
@@ -2653,6 +2654,8 @@ int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *frm,
 int skb_copy_datagram_const_iovec(const struct sk_buff *from, int offset,
 				  const struct iovec *to, int to_offset,
 				  int size);
+int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
+			   struct iov_iter *to, int size);
 void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
 void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb);
 int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index fdbc9a81d4c..84d90d087a3 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -49,6 +49,7 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/pagemap.h>
+#include <linux/uio.h>
 
 #include <net/protocol.h>
 #include <linux/skbuff.h>
@@ -481,6 +482,92 @@ fault:
 }
 EXPORT_SYMBOL(skb_copy_datagram_const_iovec);
 
+/**
+ *	skb_copy_datagram_iter - Copy a datagram to an iovec iterator.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying from
+ *	@to: iovec iterator to copy to
+ *	@len: amount of data to copy from buffer to iovec
+ */
+int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
+			   struct iov_iter *to, int len)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+	struct sk_buff *frag_iter;
+
+	trace_skb_copy_datagram_iovec(skb, len);
+
+	/* Copy header. */
+	if (copy > 0) {
+		if (copy > len)
+			copy = len;
+		if (copy_to_iter(skb->data + offset, copy, to) != copy)
+			goto short_copy;
+		if ((len -= copy) == 0)
+			return 0;
+		offset += copy;
+	}
+
+	/* Copy paged appendix. Hmm... why does this look so complicated? */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_frag_size(frag);
+		if ((copy = end - offset) > 0) {
+			if (copy > len)
+				copy = len;
+			if (copy_page_to_iter(skb_frag_page(frag),
+					      frag->page_offset + offset -
+					      start, copy, to) != copy)
+				goto short_copy;
+			if (!(len -= copy))
+				return 0;
+			offset += copy;
+		}
+		start = end;
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		if ((copy = end - offset) > 0) {
+			if (copy > len)
+				copy = len;
+			if (skb_copy_datagram_iter(frag_iter, offset - start,
+						   to, copy))
+				goto fault;
+			if ((len -= copy) == 0)
+				return 0;
+			offset += copy;
+		}
+		start = end;
+	}
+	if (!len)
+		return 0;
+
+	/* This is not really a user copy fault, but rather someone
+	 * gave us a bogus length on the skb.  We should probably
+	 * print a warning here as it may indicate a kernel bug.
+	 */
+
+fault:
+	return -EFAULT;
+
+short_copy:
+	if (iov_iter_count(to))
+		goto fault;
+
+	return 0;
+}
+EXPORT_SYMBOL(skb_copy_datagram_iter);
+
 /**
  *	skb_copy_datagram_from_iovec - Copy a datagram from an iovec.
  *	@skb: buffer to copy
-- 
cgit v1.2.3-70-g09d2


From bfe1be38fcee0e13ad53175d0b530707c20f93ec Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Fri, 7 Nov 2014 21:22:26 +0800
Subject: net: Kill skb_copy_datagram_const_iovec

Now that both macvtap and tun are using skb_copy_datagram_iter, we
can kill the abomination that is skb_copy_datagram_const_iovec.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  3 --
 net/core/datagram.c    | 89 --------------------------------------------------
 2 files changed, 92 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 933cfce7fcd..103fbe8113f 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2651,9 +2651,6 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
 				 int len);
 int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *frm,
 			   int offset, size_t count);
-int skb_copy_datagram_const_iovec(const struct sk_buff *from, int offset,
-				  const struct iovec *to, int to_offset,
-				  int size);
 int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
 			   struct iov_iter *to, int size);
 void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 84d90d087a3..26391a3fe3e 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -393,95 +393,6 @@ fault:
 }
 EXPORT_SYMBOL(skb_copy_datagram_iovec);
 
-/**
- *	skb_copy_datagram_const_iovec - Copy a datagram to an iovec.
- *	@skb: buffer to copy
- *	@offset: offset in the buffer to start copying from
- *	@to: io vector to copy to
- *	@to_offset: offset in the io vector to start copying to
- *	@len: amount of data to copy from buffer to iovec
- *
- *	Returns 0 or -EFAULT.
- *	Note: the iovec is not modified during the copy.
- */
-int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset,
-				  const struct iovec *to, int to_offset,
-				  int len)
-{
-	int start = skb_headlen(skb);
-	int i, copy = start - offset;
-	struct sk_buff *frag_iter;
-
-	/* Copy header. */
-	if (copy > 0) {
-		if (copy > len)
-			copy = len;
-		if (memcpy_toiovecend(to, skb->data + offset, to_offset, copy))
-			goto fault;
-		if ((len -= copy) == 0)
-			return 0;
-		offset += copy;
-		to_offset += copy;
-	}
-
-	/* Copy paged appendix. Hmm... why does this look so complicated? */
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		int end;
-		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
-		WARN_ON(start > offset + len);
-
-		end = start + skb_frag_size(frag);
-		if ((copy = end - offset) > 0) {
-			int err;
-			u8  *vaddr;
-			struct page *page = skb_frag_page(frag);
-
-			if (copy > len)
-				copy = len;
-			vaddr = kmap(page);
-			err = memcpy_toiovecend(to, vaddr + frag->page_offset +
-						offset - start, to_offset, copy);
-			kunmap(page);
-			if (err)
-				goto fault;
-			if (!(len -= copy))
-				return 0;
-			offset += copy;
-			to_offset += copy;
-		}
-		start = end;
-	}
-
-	skb_walk_frags(skb, frag_iter) {
-		int end;
-
-		WARN_ON(start > offset + len);
-
-		end = start + frag_iter->len;
-		if ((copy = end - offset) > 0) {
-			if (copy > len)
-				copy = len;
-			if (skb_copy_datagram_const_iovec(frag_iter,
-							  offset - start,
-							  to, to_offset,
-							  copy))
-				goto fault;
-			if ((len -= copy) == 0)
-				return 0;
-			offset += copy;
-			to_offset += copy;
-		}
-		start = end;
-	}
-	if (!len)
-		return 0;
-
-fault:
-	return -EFAULT;
-}
-EXPORT_SYMBOL(skb_copy_datagram_const_iovec);
-
 /**
  *	skb_copy_datagram_iter - Copy a datagram to an iovec iterator.
  *	@skb: buffer to copy
-- 
cgit v1.2.3-70-g09d2


From 5559b7bc42f1ff85759246e40ef73abf3171d8d9 Mon Sep 17 00:00:00 2001
From: Cristian Stoica <cristian.stoica@freescale.com>
Date: Tue, 7 Oct 2014 18:25:43 +0300
Subject: devres: support sizes greater than an unsigned long

As in 4f452e8aa492c0b8028ca9b4bdb4d018ba28c6c7, use resource_size_t
to accomodate sizes greater than the size of an unsigned long int on
platforms that have more than 32 bit physical addresses.

Signed-off-by: Cristian Stoica <cristian.stoica@freescale.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/io.h | 4 ++--
 lib/devres.c       | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/io.h b/include/linux/io.h
index d5fc9b8d8b0..fa02e55e5a2 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -61,9 +61,9 @@ static inline void devm_ioport_unmap(struct device *dev, void __iomem *addr)
 #define IOMEM_ERR_PTR(err) (__force void __iomem *)ERR_PTR(err)
 
 void __iomem *devm_ioremap(struct device *dev, resource_size_t offset,
-			    unsigned long size);
+			   resource_size_t size);
 void __iomem *devm_ioremap_nocache(struct device *dev, resource_size_t offset,
-				    unsigned long size);
+				   resource_size_t size);
 void devm_iounmap(struct device *dev, void __iomem *addr);
 int check_signature(const volatile void __iomem *io_addr,
 			const unsigned char *signature, int length);
diff --git a/lib/devres.c b/lib/devres.c
index f4a195a6efe..0f1dd2e9d2c 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -23,7 +23,7 @@ static int devm_ioremap_match(struct device *dev, void *res, void *match_data)
  * Managed ioremap().  Map is automatically unmapped on driver detach.
  */
 void __iomem *devm_ioremap(struct device *dev, resource_size_t offset,
-			   unsigned long size)
+			   resource_size_t size)
 {
 	void __iomem **ptr, *addr;
 
@@ -52,7 +52,7 @@ EXPORT_SYMBOL(devm_ioremap);
  * detach.
  */
 void __iomem *devm_ioremap_nocache(struct device *dev, resource_size_t offset,
-				   unsigned long size)
+				   resource_size_t size)
 {
 	void __iomem **ptr, *addr;
 
-- 
cgit v1.2.3-70-g09d2


From e0f1147cc9512d3610d2f2a0f069690661444703 Mon Sep 17 00:00:00 2001
From: Cristian Stoica <cristian.stoica@freescale.com>
Date: Thu, 9 Oct 2014 15:00:27 +0300
Subject: uio: support memory sizes larger than 32 bits

This is a completion to 27a90700a4275c5178b883b65927affdafa5185c
The size field is also increased to allow values larger than 32 bits
on platforms that have more than 32 bit physical addresses.

Signed-off-by: Cristian Stoica <cristian.stoica@freescale.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/DocBook/uio-howto.tmpl | 2 +-
 drivers/uio/uio.c                    | 4 ++--
 include/linux/uio_driver.h           | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/Documentation/DocBook/uio-howto.tmpl b/Documentation/DocBook/uio-howto.tmpl
index bbe9c1fd5ce..1fdc246e425 100644
--- a/Documentation/DocBook/uio-howto.tmpl
+++ b/Documentation/DocBook/uio-howto.tmpl
@@ -540,7 +540,7 @@ appears in sysfs.
 </para></listitem>
 
 <listitem><para>
-<varname>unsigned long size</varname>: Fill in the size of the
+<varname>resource_size_t size</varname>: Fill in the size of the
 memory block that <varname>addr</varname> points to. If <varname>size</varname>
 is zero, the mapping is considered unused. Note that you
 <emphasis>must</emphasis> initialize <varname>size</varname> with zero for
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index 60fa6278fbc..6276f13e9e1 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -56,12 +56,12 @@ static ssize_t map_name_show(struct uio_mem *mem, char *buf)
 
 static ssize_t map_addr_show(struct uio_mem *mem, char *buf)
 {
-	return sprintf(buf, "0x%llx\n", (unsigned long long)mem->addr);
+	return sprintf(buf, "%pa\n", &mem->addr);
 }
 
 static ssize_t map_size_show(struct uio_mem *mem, char *buf)
 {
-	return sprintf(buf, "0x%lx\n", mem->size);
+	return sprintf(buf, "%pa\n", &mem->size);
 }
 
 static ssize_t map_offset_show(struct uio_mem *mem, char *buf)
diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h
index baa81718d98..32c0e83d623 100644
--- a/include/linux/uio_driver.h
+++ b/include/linux/uio_driver.h
@@ -35,7 +35,7 @@ struct uio_map;
 struct uio_mem {
 	const char		*name;
 	phys_addr_t		addr;
-	unsigned long		size;
+	resource_size_t		size;
 	int			memtype;
 	void __iomem		*internal_addr;
 	struct uio_map		*map;
-- 
cgit v1.2.3-70-g09d2


From 31d4ea1a093fcf668d5f95af44b8d41488bdb7ec Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Fri, 24 Oct 2014 12:20:27 +0200
Subject: Drivers: hv: util: make struct hv_do_fcopy match Hyper-V host
 messages

An attempt to fix fcopy on i586 (bc5a5b0 Drivers: hv: util: Properly pack the data
for file copy functionality) led to a regression on x86_64 (and actually didn't fix
i586 breakage). Fcopy messages from Hyper-V host come in the following format:

struct do_fcopy_hdr   |   36 bytes
0000                  |    4 bytes
offset                |    8 bytes
size                  |    4 bytes
data                  | 6144 bytes

On x86_64 struct hv_do_fcopy matched this format without ' __attribute__((packed))'
and on i586 adding ' __attribute__((packed))' to it doesn't change anything. Keep
the structure packed and add padding to match re reality. Tested both i586 and x86_64
on Hyper-V Server 2012 R2.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/hyperv.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h
index 0a8e6badb29..bb1cb73c927 100644
--- a/include/uapi/linux/hyperv.h
+++ b/include/uapi/linux/hyperv.h
@@ -134,6 +134,7 @@ struct hv_start_fcopy {
 
 struct hv_do_fcopy {
 	struct hv_fcopy_hdr hdr;
+	__u32   pad;
 	__u64	offset;
 	__u32	size;
 	__u8	data[DATA_FRAGMENT];
-- 
cgit v1.2.3-70-g09d2


From 2b75869bba676c248d8d25ae6d2bd9221dfffdb6 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 13 Oct 2014 16:41:28 +1100
Subject: sysfs/kernfs: allow attributes to request write buffer be
 pre-allocated.

md/raid allows metadata management to be performed in user-space.
A various times, particularly on device failure, the metadata needs
to be updated before further writes can be permitted.
This means that the user-space program which updates metadata much
not block on writeout, and so must not allocate memory.

mlockall(MCL_CURRENT|MCL_FUTURE) and pre-allocation can avoid all
memory allocation issues for user-memory, but that does not help
kernel memory.
Several kernel objects can be pre-allocated.  e.g. files opened before
any writes to the array are permitted.
However some kernel allocation happens in places that cannot be
pre-allocated.
In particular, writes to sysfs files (to tell md that it can now
allow writes to the array) allocate a buffer using GFP_KERNEL.

This patch allows attributes to be marked as "PREALLOC".  In that case
the maximal buffer is allocated when the file is opened, and then used
on each write instead of allocating a new buffer.

As the same buffer is now shared for all writes on the same file
description, the mutex is extended to cover full use of the buffer
including the copy_from_user().

The new __ATTR_PREALLOC() 'or's a new flag in to the 'mode', which is
inspected by sysfs_add_file_mode_ns() to determine if the file should be
marked as requiring prealloc.

Despite the comment, we *do* use ->seq_show together with ->prealloc
in this patch.  The next patch fixes that.

Signed-off-by: NeilBrown  <neilb@suse.de>
Reviewed-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/file.c       | 45 ++++++++++++++++++++++++++++++---------------
 fs/sysfs/file.c        | 31 ++++++++++++++++++++++++-------
 include/linux/kernfs.h |  8 ++++++++
 include/linux/sysfs.h  |  9 +++++++++
 4 files changed, 71 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 4429d6d9217..70186e2e692 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -106,7 +106,7 @@ static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos)
 	const struct kernfs_ops *ops;
 
 	/*
-	 * @of->mutex nests outside active ref and is just to ensure that
+	 * @of->mutex nests outside active ref and is primarily to ensure that
 	 * the ops aren't called concurrently for the same open file.
 	 */
 	mutex_lock(&of->mutex);
@@ -194,7 +194,7 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
 		return -ENOMEM;
 
 	/*
-	 * @of->mutex nests outside active ref and is just to ensure that
+	 * @of->mutex nests outside active ref and is primarily to ensure that
 	 * the ops aren't called concurrently for the same open file.
 	 */
 	mutex_lock(&of->mutex);
@@ -278,19 +278,16 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
 		len = min_t(size_t, count, PAGE_SIZE);
 	}
 
-	buf = kmalloc(len + 1, GFP_KERNEL);
+	buf = of->prealloc_buf;
+	if (!buf)
+		buf = kmalloc(len + 1, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	if (copy_from_user(buf, user_buf, len)) {
-		len = -EFAULT;
-		goto out_free;
-	}
-	buf[len] = '\0';	/* guarantee string termination */
-
 	/*
-	 * @of->mutex nests outside active ref and is just to ensure that
-	 * the ops aren't called concurrently for the same open file.
+	 * @of->mutex nests outside active ref and is used both to ensure that
+	 * the ops aren't called concurrently for the same open file, and
+	 * to provide exclusive access to ->prealloc_buf (when that exists).
 	 */
 	mutex_lock(&of->mutex);
 	if (!kernfs_get_active(of->kn)) {
@@ -299,19 +296,27 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
 		goto out_free;
 	}
 
+	if (copy_from_user(buf, user_buf, len)) {
+		len = -EFAULT;
+		goto out_unlock;
+	}
+	buf[len] = '\0';	/* guarantee string termination */
+
 	ops = kernfs_ops(of->kn);
 	if (ops->write)
 		len = ops->write(of, buf, len, *ppos);
 	else
 		len = -EINVAL;
 
-	kernfs_put_active(of->kn);
-	mutex_unlock(&of->mutex);
-
 	if (len > 0)
 		*ppos += len;
+
+out_unlock:
+	kernfs_put_active(of->kn);
+	mutex_unlock(&of->mutex);
 out_free:
-	kfree(buf);
+	if (buf != of->prealloc_buf)
+		kfree(buf);
 	return len;
 }
 
@@ -685,6 +690,14 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
 	 */
 	of->atomic_write_len = ops->atomic_write_len;
 
+	if (ops->prealloc) {
+		int len = of->atomic_write_len ?: PAGE_SIZE;
+		of->prealloc_buf = kmalloc(len + 1, GFP_KERNEL);
+		error = -ENOMEM;
+		if (!of->prealloc_buf)
+			goto err_free;
+	}
+
 	/*
 	 * Always instantiate seq_file even if read access doesn't use
 	 * seq_file or is not requested.  This unifies private data access
@@ -715,6 +728,7 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
 err_close:
 	seq_release(inode, file);
 err_free:
+	kfree(of->prealloc_buf);
 	kfree(of);
 err_out:
 	kernfs_put_active(kn);
@@ -728,6 +742,7 @@ static int kernfs_fop_release(struct inode *inode, struct file *filp)
 
 	kernfs_put_open_node(kn, of);
 	seq_release(inode, filp);
+	kfree(of->prealloc_buf);
 	kfree(of);
 
 	return 0;
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 589abee16a3..4ad3721a991 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -184,6 +184,17 @@ static const struct kernfs_ops sysfs_file_kfops_rw = {
 	.write		= sysfs_kf_write,
 };
 
+static const struct kernfs_ops sysfs_prealloc_kfops_wo = {
+	.write		= sysfs_kf_write,
+	.prealloc	= true,
+};
+
+static const struct kernfs_ops sysfs_prealloc_kfops_rw = {
+	.seq_show	= sysfs_kf_seq_show,
+	.write		= sysfs_kf_write,
+	.prealloc	= true,
+};
+
 static const struct kernfs_ops sysfs_bin_kfops_ro = {
 	.read		= sysfs_kf_bin_read,
 };
@@ -222,13 +233,19 @@ int sysfs_add_file_mode_ns(struct kernfs_node *parent,
 			 kobject_name(kobj)))
 			return -EINVAL;
 
-		if (sysfs_ops->show && sysfs_ops->store)
-			ops = &sysfs_file_kfops_rw;
-		else if (sysfs_ops->show)
+		if (sysfs_ops->show && sysfs_ops->store) {
+			if (mode & SYSFS_PREALLOC)
+				ops = &sysfs_prealloc_kfops_rw;
+			else
+				ops = &sysfs_file_kfops_rw;
+		} else if (sysfs_ops->show)
 			ops = &sysfs_file_kfops_ro;
-		else if (sysfs_ops->store)
-			ops = &sysfs_file_kfops_wo;
-		else
+		else if (sysfs_ops->store) {
+			if (mode & SYSFS_PREALLOC)
+				ops = &sysfs_prealloc_kfops_wo;
+			else
+				ops = &sysfs_file_kfops_wo;
+		} else
 			ops = &sysfs_file_kfops_empty;
 
 		size = PAGE_SIZE;
@@ -253,7 +270,7 @@ int sysfs_add_file_mode_ns(struct kernfs_node *parent,
 	if (!attr->ignore_lockdep)
 		key = attr->key ?: (struct lock_class_key *)&attr->skey;
 #endif
-	kn = __kernfs_create_file(parent, attr->name, mode, size, ops,
+	kn = __kernfs_create_file(parent, attr->name, mode & 0777, size, ops,
 				  (void *)attr, ns, true, key);
 	if (IS_ERR(kn)) {
 		if (PTR_ERR(kn) == -EEXIST)
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 30faf797c2c..d4e01b35834 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -179,6 +179,7 @@ struct kernfs_open_file {
 	struct mutex		mutex;
 	int			event;
 	struct list_head	list;
+	char			*prealloc_buf;
 
 	size_t			atomic_write_len;
 	bool			mmapped;
@@ -214,6 +215,13 @@ struct kernfs_ops {
 	 * larger ones are rejected with -E2BIG.
 	 */
 	size_t atomic_write_len;
+	/*
+	 * "prealloc" causes a buffer to be allocated at open for
+	 * all read/write requests.  As ->seq_show uses seq_read()
+	 * which does its own allocation, it is incompatible with
+	 * ->prealloc.  Provide ->read and ->write with ->prealloc.
+	 */
+	bool prealloc;
 	ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes,
 			 loff_t off);
 
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index f97d0dbb59f..ddad16148bd 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -70,6 +70,8 @@ struct attribute_group {
  * for examples..
  */
 
+#define SYSFS_PREALLOC 010000
+
 #define __ATTR(_name, _mode, _show, _store) {				\
 	.attr = {.name = __stringify(_name),				\
 		 .mode = VERIFY_OCTAL_PERMISSIONS(_mode) },		\
@@ -77,6 +79,13 @@ struct attribute_group {
 	.store	= _store,						\
 }
 
+#define __ATTR_PREALLOC(_name, _mode, _show, _store) {			\
+	.attr = {.name = __stringify(_name),				\
+		 .mode = SYSFS_PREALLOC | VERIFY_OCTAL_PERMISSIONS(_mode) },\
+	.show	= _show,						\
+	.store	= _store,						\
+}
+
 #define __ATTR_RO(_name) {						\
 	.attr	= { .name = __stringify(_name), .mode = S_IRUGO },	\
 	.show	= _name##_show,						\
-- 
cgit v1.2.3-70-g09d2


From 5aaba36318e5995e8c95d077a46d9a4d00fcc1cd Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Tue, 30 Sep 2014 14:48:22 +0100
Subject: cpumask: factor out show_cpumap into separate helper function

Many sysfs *_show function use cpu{list,mask}_scnprintf to copy cpumap
to the buffer aligned to PAGE_SIZE, append '\n' and '\0' to return null
terminated buffer with newline.

This patch creates a new helper function cpumap_print_to_pagebuf in
cpumask.h using newly added bitmap_print_to_pagebuf and consolidates
most of those sysfs functions using the new helper function.

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Suggested-by: Stephen Boyd <sboyd@codeaurora.org>
Tested-by: Stephen Boyd <sboyd@codeaurora.org>
Acked-by: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: x86@kernel.org
Cc: linux-acpi@vger.kernel.org
Cc: linux-pci@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/kernel/cpu/perf_event_amd_iommu.c    |  5 +---
 arch/x86/kernel/cpu/perf_event_amd_uncore.c   |  6 +----
 arch/x86/kernel/cpu/perf_event_intel_rapl.c   |  6 +----
 arch/x86/kernel/cpu/perf_event_intel_uncore.c |  6 +----
 drivers/acpi/acpi_pad.c                       |  8 +++---
 drivers/base/cpu.c                            |  5 +---
 drivers/base/node.c                           | 14 +++-------
 drivers/base/topology.c                       | 22 ++-------------
 drivers/pci/pci-sysfs.c                       | 39 +++++++--------------------
 include/linux/bitmap.h                        |  3 +++
 include/linux/cpumask.h                       | 17 ++++++++++++
 lib/bitmap.c                                  | 29 ++++++++++++++++++++
 12 files changed, 73 insertions(+), 87 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.c b/arch/x86/kernel/cpu/perf_event_amd_iommu.c
index 639d1289b1b..97242a9242b 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_iommu.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_iommu.c
@@ -130,10 +130,7 @@ static ssize_t _iommu_cpumask_show(struct device *dev,
 				   struct device_attribute *attr,
 				   char *buf)
 {
-	int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &iommu_cpumask);
-	buf[n++] = '\n';
-	buf[n] = '\0';
-	return n;
+	return cpumap_print_to_pagebuf(true, buf, &iommu_cpumask);
 }
 static DEVICE_ATTR(cpumask, S_IRUGO, _iommu_cpumask_show, NULL);
 
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
index 30790d798e6..cc6cedb8f25 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -219,7 +219,6 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
 					    struct device_attribute *attr,
 					    char *buf)
 {
-	int n;
 	cpumask_t *active_mask;
 	struct pmu *pmu = dev_get_drvdata(dev);
 
@@ -230,10 +229,7 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
 	else
 		return 0;
 
-	n = cpulist_scnprintf(buf, PAGE_SIZE - 2, active_mask);
-	buf[n++] = '\n';
-	buf[n] = '\0';
-	return n;
+	return cpumap_print_to_pagebuf(true, buf, active_mask);
 }
 static DEVICE_ATTR(cpumask, S_IRUGO, amd_uncore_attr_show_cpumask, NULL);
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index d64f275fe27..673f930c700 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -365,11 +365,7 @@ static void rapl_pmu_event_read(struct perf_event *event)
 static ssize_t rapl_get_attr_cpumask(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &rapl_cpu_mask);
-
-	buf[n++] = '\n';
-	buf[n] = '\0';
-	return n;
+	return cpumap_print_to_pagebuf(true, buf, &rapl_cpu_mask);
 }
 
 static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 9762dbd9f3f..08f3fed2b0f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -647,11 +647,7 @@ static int uncore_pmu_event_init(struct perf_event *event)
 static ssize_t uncore_get_attr_cpumask(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &uncore_cpu_mask);
-
-	buf[n++] = '\n';
-	buf[n] = '\0';
-	return n;
+	return cpumap_print_to_pagebuf(true, buf, &uncore_cpu_mask);
 }
 
 static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL);
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index f148a0580e0..c7b105c0e1d 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -350,12 +350,10 @@ static ssize_t acpi_pad_idlecpus_store(struct device *dev,
 static ssize_t acpi_pad_idlecpus_show(struct device *dev,
 	struct device_attribute *attr, char *buf)
 {
-	int n = 0;
-	n = cpumask_scnprintf(buf, PAGE_SIZE-2, to_cpumask(pad_busy_cpus_bits));
-	buf[n++] = '\n';
-	buf[n] = '\0';
-	return n;
+	return cpumap_print_to_pagebuf(false, buf,
+				       to_cpumask(pad_busy_cpus_bits));
 }
+
 static DEVICE_ATTR(idlecpus, S_IRUGO|S_IWUSR,
 	acpi_pad_idlecpus_show,
 	acpi_pad_idlecpus_store);
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 006b1bc5297..4d8a56406fb 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -207,11 +207,8 @@ static ssize_t show_cpus_attr(struct device *dev,
 			      char *buf)
 {
 	struct cpu_attr *ca = container_of(attr, struct cpu_attr, attr);
-	int n = cpulist_scnprintf(buf, PAGE_SIZE-2, *(ca->map));
 
-	buf[n++] = '\n';
-	buf[n] = '\0';
-	return n;
+	return cpumap_print_to_pagebuf(true, buf, *ca->map);
 }
 
 #define _CPU_ATTR(name, map) \
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 472168cd0c9..a3b82e9c7f2 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -25,32 +25,26 @@ static struct bus_type node_subsys = {
 };
 
 
-static ssize_t node_read_cpumap(struct device *dev, int type, char *buf)
+static ssize_t node_read_cpumap(struct device *dev, bool list, char *buf)
 {
 	struct node *node_dev = to_node(dev);
 	const struct cpumask *mask = cpumask_of_node(node_dev->dev.id);
-	int len;
 
 	/* 2008/04/07: buf currently PAGE_SIZE, need 9 chars per 32 bits. */
 	BUILD_BUG_ON((NR_CPUS/32 * 9) > (PAGE_SIZE-1));
 
-	len = type?
-		cpulist_scnprintf(buf, PAGE_SIZE-2, mask) :
-		cpumask_scnprintf(buf, PAGE_SIZE-2, mask);
- 	buf[len++] = '\n';
- 	buf[len] = '\0';
-	return len;
+	return cpumap_print_to_pagebuf(list, buf, mask);
 }
 
 static inline ssize_t node_read_cpumask(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	return node_read_cpumap(dev, 0, buf);
+	return node_read_cpumap(dev, false, buf);
 }
 static inline ssize_t node_read_cpulist(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	return node_read_cpumap(dev, 1, buf);
+	return node_read_cpumap(dev, true, buf);
 }
 
 static DEVICE_ATTR(cpumap,  S_IRUGO, node_read_cpumask, NULL);
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index be7c1fb7c0c..f7c353843dd 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -42,29 +42,11 @@ static ssize_t show_##name(struct device *dev,			\
 	return sprintf(buf, "%d\n", topology_##name(dev->id));	\
 }
 
-#if defined(topology_thread_cpumask) || defined(topology_core_cpumask) || \
-    defined(topology_book_cpumask)
-static ssize_t show_cpumap(int type, const struct cpumask *mask, char *buf)
-{
-	ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
-	int n = 0;
-
-	if (len > 1) {
-		n = type?
-			cpulist_scnprintf(buf, len-2, mask) :
-			cpumask_scnprintf(buf, len-2, mask);
-		buf[n++] = '\n';
-		buf[n] = '\0';
-	}
-	return n;
-}
-#endif
-
 #define define_siblings_show_map(name)					\
 static ssize_t show_##name(struct device *dev,				\
 			   struct device_attribute *attr, char *buf)	\
 {									\
-	return show_cpumap(0, topology_##name(dev->id), buf);		\
+	return cpumap_print_to_pagebuf(false, buf, topology_##name(dev->id));\
 }
 
 #define define_siblings_show_list(name)					\
@@ -72,7 +54,7 @@ static ssize_t show_##name##_list(struct device *dev,			\
 				  struct device_attribute *attr,	\
 				  char *buf)				\
 {									\
-	return show_cpumap(1, topology_##name(dev->id), buf);		\
+	return cpumap_print_to_pagebuf(true, buf, topology_##name(dev->id));\
 }
 
 #define define_siblings_show_func(name)		\
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 2c6643fdc0c..368bdac4260 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -77,11 +77,10 @@ static ssize_t broken_parity_status_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(broken_parity_status);
 
-static ssize_t pci_dev_show_local_cpu(struct device *dev, int type,
+static ssize_t pci_dev_show_local_cpu(struct device *dev, bool list,
 				      struct device_attribute *attr, char *buf)
 {
 	const struct cpumask *mask;
-	int len;
 
 #ifdef CONFIG_NUMA
 	mask = (dev_to_node(dev) == -1) ? cpu_online_mask :
@@ -89,59 +88,41 @@ static ssize_t pci_dev_show_local_cpu(struct device *dev, int type,
 #else
 	mask = cpumask_of_pcibus(to_pci_dev(dev)->bus);
 #endif
-	len = type ?
-		cpumask_scnprintf(buf, PAGE_SIZE-2, mask) :
-		cpulist_scnprintf(buf, PAGE_SIZE-2, mask);
-
-	buf[len++] = '\n';
-	buf[len] = '\0';
-	return len;
+	return cpumap_print_to_pagebuf(list, buf, mask);
 }
 
 static ssize_t local_cpus_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
-	return pci_dev_show_local_cpu(dev, 1, attr, buf);
+	return pci_dev_show_local_cpu(dev, false, attr, buf);
 }
 static DEVICE_ATTR_RO(local_cpus);
 
 static ssize_t local_cpulist_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
-	return pci_dev_show_local_cpu(dev, 0, attr, buf);
+	return pci_dev_show_local_cpu(dev, true, attr, buf);
 }
 static DEVICE_ATTR_RO(local_cpulist);
 
 /*
  * PCI Bus Class Devices
  */
-static ssize_t pci_bus_show_cpuaffinity(struct device *dev, int type,
-					struct device_attribute *attr,
-					char *buf)
-{
-	int ret;
-	const struct cpumask *cpumask;
-
-	cpumask = cpumask_of_pcibus(to_pci_bus(dev));
-	ret = type ?
-		cpulist_scnprintf(buf, PAGE_SIZE-2, cpumask) :
-		cpumask_scnprintf(buf, PAGE_SIZE-2, cpumask);
-	buf[ret++] = '\n';
-	buf[ret] = '\0';
-	return ret;
-}
-
 static ssize_t cpuaffinity_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	return pci_bus_show_cpuaffinity(dev, 0, attr, buf);
+	const struct cpumask *cpumask = cpumask_of_pcibus(to_pci_bus(dev));
+
+	return cpumap_print_to_pagebuf(false, buf, cpumask);
 }
 static DEVICE_ATTR_RO(cpuaffinity);
 
 static ssize_t cpulistaffinity_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
-	return pci_bus_show_cpuaffinity(dev, 1, attr, buf);
+	const struct cpumask *cpumask = cpumask_of_pcibus(to_pci_bus(dev));
+
+	return cpumap_print_to_pagebuf(true, buf, cpumask);
 }
 static DEVICE_ATTR_RO(cpulistaffinity);
 
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index e1c8d080c42..9d5c3224a1e 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -60,6 +60,7 @@
  * bitmap_find_free_region(bitmap, bits, order)	Find and allocate bit region
  * bitmap_release_region(bitmap, pos, order)	Free specified bit region
  * bitmap_allocate_region(bitmap, pos, order)	Allocate specified bit region
+ * bitmap_print_to_pagebuf(list, buf, mask, nbits) Print bitmap src as list/hex
  */
 
 /*
@@ -145,6 +146,8 @@ extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int o
 extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order);
 extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits);
 extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits);
+extern int bitmap_print_to_pagebuf(bool list, char *buf,
+				   const unsigned long *maskp, int nmaskbits);
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) % BITS_PER_LONG))
 #define BITMAP_LAST_WORD_MASK(nbits)					\
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 0a9a6da21e7..b950e9d6008 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -803,6 +803,23 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
 }
 #endif /* NR_CPUS > BITS_PER_LONG */
 
+/**
+ * cpumap_print_to_pagebuf  - copies the cpumask into the buffer either
+ *	as comma-separated list of cpus or hex values of cpumask
+ * @list: indicates whether the cpumap must be list
+ * @mask: the cpumask to copy
+ * @buf: the buffer to copy into
+ *
+ * Returns the length of the (null-terminated) @buf string, zero if
+ * nothing is copied.
+ */
+static inline ssize_t
+cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
+{
+	return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask),
+				      nr_cpumask_bits);
+}
+
 /*
  *
  * From here down, all obsolete.  Use cpumask_ variants!
diff --git a/lib/bitmap.c b/lib/bitmap.c
index b499ab6ada2..5bc7a1128fe 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -12,6 +12,8 @@
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
 #include <linux/bug.h>
+
+#include <asm/page.h>
 #include <asm/uaccess.h>
 
 /*
@@ -583,6 +585,33 @@ int bitmap_scnlistprintf(char *buf, unsigned int buflen,
 }
 EXPORT_SYMBOL(bitmap_scnlistprintf);
 
+/**
+ * bitmap_print_to_pagebuf - convert bitmap to list or hex format ASCII string
+ * @list: indicates whether the bitmap must be list
+ * @buf: page aligned buffer into which string is placed
+ * @maskp: pointer to bitmap to convert
+ * @nmaskbits: size of bitmap, in bits
+ *
+ * Output format is a comma-separated list of decimal numbers and
+ * ranges if list is specified or hex digits grouped into comma-separated
+ * sets of 8 digits/set. Returns the number of characters written to buf.
+ */
+int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp,
+			    int nmaskbits)
+{
+	ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf - 2;
+	int n = 0;
+
+	if (len > 1) {
+		n = list ? bitmap_scnlistprintf(buf, len, maskp, nmaskbits) :
+			   bitmap_scnprintf(buf, len, maskp, nmaskbits);
+		buf[n++] = '\n';
+		buf[n] = '\0';
+	}
+	return n;
+}
+EXPORT_SYMBOL(bitmap_print_to_pagebuf);
+
 /**
  * __bitmap_parselist - convert list format ASCII string to bitmap
  * @buf: read nul-terminated user string from this buffer
-- 
cgit v1.2.3-70-g09d2


From 3d52943b3a51497a777e6d7d840a38596a92cee9 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Tue, 30 Sep 2014 14:48:24 +0100
Subject: drivers: base: add cpu_device_create to support per-cpu devices

This patch adds a new function to create per-cpu devices.
This helps in:
1. reusing the device infrastructure to create any cpu related
   attributes and corresponding sysfs instead of creating and
   dealing with raw kobjects directly
2. retaining the legacy path(/sys/devices/system/cpu/..) to support
   existing sysfs ABI
3. avoiding to create links in the bus directory pointing to the
   device as there would be per-cpu instance of these devices with
   the same name since dev->bus is not populated to cpu_sysbus on
   purpose

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Tested-by: Stephen Boyd <sboyd@codeaurora.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: David Herrmann <dh.herrmann@gmail.com>
Cc: Kay Sievers <kay@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/cpu.c  | 54 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/cpu.h |  4 ++++
 2 files changed, 58 insertions(+)

(limited to 'include')

diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 4d8a56406fb..f829a4c7174 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -363,6 +363,60 @@ struct device *get_cpu_device(unsigned cpu)
 }
 EXPORT_SYMBOL_GPL(get_cpu_device);
 
+static void device_create_release(struct device *dev)
+{
+	kfree(dev);
+}
+
+static struct device *
+__cpu_device_create(struct device *parent, void *drvdata,
+		    const struct attribute_group **groups,
+		    const char *fmt, va_list args)
+{
+	struct device *dev = NULL;
+	int retval = -ENODEV;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev) {
+		retval = -ENOMEM;
+		goto error;
+	}
+
+	device_initialize(dev);
+	dev->parent = parent;
+	dev->groups = groups;
+	dev->release = device_create_release;
+	dev_set_drvdata(dev, drvdata);
+
+	retval = kobject_set_name_vargs(&dev->kobj, fmt, args);
+	if (retval)
+		goto error;
+
+	retval = device_add(dev);
+	if (retval)
+		goto error;
+
+	return dev;
+
+error:
+	put_device(dev);
+	return ERR_PTR(retval);
+}
+
+struct device *cpu_device_create(struct device *parent, void *drvdata,
+				 const struct attribute_group **groups,
+				 const char *fmt, ...)
+{
+	va_list vargs;
+	struct device *dev;
+
+	va_start(vargs, fmt);
+	dev = __cpu_device_create(parent, drvdata, groups, fmt, vargs);
+	va_end(vargs);
+	return dev;
+}
+EXPORT_SYMBOL_GPL(cpu_device_create);
+
 #ifdef CONFIG_GENERIC_CPU_AUTOPROBE
 static DEVICE_ATTR(modalias, 0444, print_cpu_modalias, NULL);
 #endif
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index b2d9a43012b..4260e8594bd 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -19,6 +19,7 @@
 
 struct device;
 struct device_node;
+struct attribute_group;
 
 struct cpu {
 	int node_id;		/* The node which contains the CPU */
@@ -39,6 +40,9 @@ extern void cpu_remove_dev_attr(struct device_attribute *attr);
 extern int cpu_add_dev_attr_group(struct attribute_group *attrs);
 extern void cpu_remove_dev_attr_group(struct attribute_group *attrs);
 
+extern struct device *cpu_device_create(struct device *parent, void *drvdata,
+					const struct attribute_group **groups,
+					const char *fmt, ...);
 #ifdef CONFIG_HOTPLUG_CPU
 extern void unregister_cpu(struct cpu *cpu);
 extern ssize_t arch_cpu_probe(const char *, size_t);
-- 
cgit v1.2.3-70-g09d2


From 246246cbde5e840012f853e27630ebb59f409486 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Tue, 30 Sep 2014 14:48:25 +0100
Subject: drivers: base: support cpu cache information interface to userspace
 via sysfs

This patch adds initial support for providing processor cache information
to userspace through sysfs interface. This is based on already existing
implementations(x86, ia64, s390 and powerpc) and hence the interface is
intended to be fully compatible.

The main purpose of this generic support is to avoid further code
duplication to support new architectures and also to unify all the existing
different implementations.

This implementation maintains the hierarchy of cache objects which reflects
the system's cache topology. Cache devices are instantiated as needed as
CPUs come online. The cache information is replicated per-cpu even if they are
shared. A per-cpu array of cache information maintained is used mainly for
sysfs-related book keeping.

It also implements the shared_cpu_map attribute, which is essential for
enabling both kernel and user-space to discover the system's overall cache
topology.

This patch also add the missing ABI documentation for the cacheinfo sysfs
interface already, which is well defined and widely used.

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Tested-by: Stephen Boyd <sboyd@codeaurora.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-api@vger.kernel.org
Cc: linux390@de.ibm.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-ia64@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Cc: x86@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/ABI/testing/sysfs-devices-system-cpu |  47 ++
 drivers/base/Makefile                              |   2 +-
 drivers/base/cacheinfo.c                           | 541 +++++++++++++++++++++
 include/linux/cacheinfo.h                          | 100 ++++
 4 files changed, 689 insertions(+), 1 deletion(-)
 create mode 100644 drivers/base/cacheinfo.c
 create mode 100644 include/linux/cacheinfo.h

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index acb9bfc89b4..99983e67c13 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -224,3 +224,50 @@ Description:	Parameters for the Intel P-state driver
 		frequency range.
 
 		More details can be found in Documentation/cpu-freq/intel-pstate.txt
+
+What:		/sys/devices/system/cpu/cpu*/cache/index*/<set_of_attributes_mentioned_below>
+Date:		July 2014(documented, existed before August 2008)
+Contact:	Sudeep Holla <sudeep.holla@arm.com>
+		Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Parameters for the CPU cache attributes
+
+		allocation_policy:
+			- WriteAllocate: allocate a memory location to a cache line
+					 on a cache miss because of a write
+			- ReadAllocate: allocate a memory location to a cache line
+					on a cache miss because of a read
+			- ReadWriteAllocate: both writeallocate and readallocate
+
+		attributes: LEGACY used only on IA64 and is same as write_policy
+
+		coherency_line_size: the minimum amount of data in bytes that gets
+				     transferred from memory to cache
+
+		level: the cache hierarcy in the multi-level cache configuration
+
+		number_of_sets: total number of sets in the cache, a set is a
+				collection of cache lines with the same cache index
+
+		physical_line_partition: number of physical cache line per cache tag
+
+		shared_cpu_list: the list of logical cpus sharing the cache
+
+		shared_cpu_map: logical cpu mask containing the list of cpus sharing
+				the cache
+
+		size: the total cache size in kB
+
+		type:
+			- Instruction: cache that only holds instructions
+			- Data: cache that only caches data
+			- Unified: cache that holds both data and instructions
+
+		ways_of_associativity: degree of freedom in placing a particular block
+					of memory in the cache
+
+		write_policy:
+			- WriteThrough: data is written to both the cache line
+					and to the block in the lower-level memory
+			- WriteBack: data is written only to the cache line and
+				     the modified cache line is written to main
+				     memory only when it is replaced
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 6922cd6850a..e81a55ca513 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -4,7 +4,7 @@ obj-y			:= component.o core.o bus.o dd.o syscore.o \
 			   driver.o class.o platform.o \
 			   cpu.o firmware.o init.o map.o devres.o \
 			   attribute_container.o transport_class.o \
-			   topology.o container.o
+			   topology.o container.o cacheinfo.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
 obj-$(CONFIG_DMA_CMA) += dma-contiguous.o
 obj-y			+= power/
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
new file mode 100644
index 00000000000..8ed4ea1f371
--- /dev/null
+++ b/drivers/base/cacheinfo.c
@@ -0,0 +1,541 @@
+/*
+ * cacheinfo support - processor cache information via sysfs
+ *
+ * Based on arch/x86/kernel/cpu/intel_cacheinfo.c
+ * Author: Sudeep Holla <sudeep.holla@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/bitops.h>
+#include <linux/cacheinfo.h>
+#include <linux/compiler.h>
+#include <linux/cpu.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+
+/* pointer to per cpu cacheinfo */
+static DEFINE_PER_CPU(struct cpu_cacheinfo, ci_cpu_cacheinfo);
+#define ci_cacheinfo(cpu)	(&per_cpu(ci_cpu_cacheinfo, cpu))
+#define cache_leaves(cpu)	(ci_cacheinfo(cpu)->num_leaves)
+#define per_cpu_cacheinfo(cpu)	(ci_cacheinfo(cpu)->info_list)
+
+struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu)
+{
+	return ci_cacheinfo(cpu);
+}
+
+#ifdef CONFIG_OF
+static int cache_setup_of_node(unsigned int cpu)
+{
+	struct device_node *np;
+	struct cacheinfo *this_leaf;
+	struct device *cpu_dev = get_cpu_device(cpu);
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	unsigned int index = 0;
+
+	/* skip if of_node is already populated */
+	if (this_cpu_ci->info_list->of_node)
+		return 0;
+
+	if (!cpu_dev) {
+		pr_err("No cpu device for CPU %d\n", cpu);
+		return -ENODEV;
+	}
+	np = cpu_dev->of_node;
+	if (!np) {
+		pr_err("Failed to find cpu%d device node\n", cpu);
+		return -ENOENT;
+	}
+
+	while (np && index < cache_leaves(cpu)) {
+		this_leaf = this_cpu_ci->info_list + index;
+		if (this_leaf->level != 1)
+			np = of_find_next_cache_node(np);
+		else
+			np = of_node_get(np);/* cpu node itself */
+		this_leaf->of_node = np;
+		index++;
+	}
+	return 0;
+}
+
+static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf,
+					   struct cacheinfo *sib_leaf)
+{
+	return sib_leaf->of_node == this_leaf->of_node;
+}
+#else
+static inline int cache_setup_of_node(unsigned int cpu) { return 0; }
+static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf,
+					   struct cacheinfo *sib_leaf)
+{
+	/*
+	 * For non-DT systems, assume unique level 1 cache, system-wide
+	 * shared caches for all other levels. This will be used only if
+	 * arch specific code has not populated shared_cpu_map
+	 */
+	return !(this_leaf->level == 1);
+}
+#endif
+
+static int cache_shared_cpu_map_setup(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf, *sib_leaf;
+	unsigned int index;
+	int ret;
+
+	ret = cache_setup_of_node(cpu);
+	if (ret)
+		return ret;
+
+	for (index = 0; index < cache_leaves(cpu); index++) {
+		unsigned int i;
+
+		this_leaf = this_cpu_ci->info_list + index;
+		/* skip if shared_cpu_map is already populated */
+		if (!cpumask_empty(&this_leaf->shared_cpu_map))
+			continue;
+
+		cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
+		for_each_online_cpu(i) {
+			struct cpu_cacheinfo *sib_cpu_ci = get_cpu_cacheinfo(i);
+
+			if (i == cpu || !sib_cpu_ci->info_list)
+				continue;/* skip if itself or no cacheinfo */
+			sib_leaf = sib_cpu_ci->info_list + index;
+			if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
+				cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
+				cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
+			}
+		}
+	}
+
+	return 0;
+}
+
+static void cache_shared_cpu_map_remove(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf, *sib_leaf;
+	unsigned int sibling, index;
+
+	for (index = 0; index < cache_leaves(cpu); index++) {
+		this_leaf = this_cpu_ci->info_list + index;
+		for_each_cpu(sibling, &this_leaf->shared_cpu_map) {
+			struct cpu_cacheinfo *sib_cpu_ci;
+
+			if (sibling == cpu) /* skip itself */
+				continue;
+			sib_cpu_ci = get_cpu_cacheinfo(sibling);
+			sib_leaf = sib_cpu_ci->info_list + index;
+			cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
+			cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
+		}
+		of_node_put(this_leaf->of_node);
+	}
+}
+
+static void free_cache_attributes(unsigned int cpu)
+{
+	cache_shared_cpu_map_remove(cpu);
+
+	kfree(per_cpu_cacheinfo(cpu));
+	per_cpu_cacheinfo(cpu) = NULL;
+}
+
+int __weak init_cache_level(unsigned int cpu)
+{
+	return -ENOENT;
+}
+
+int __weak populate_cache_leaves(unsigned int cpu)
+{
+	return -ENOENT;
+}
+
+static int detect_cache_attributes(unsigned int cpu)
+{
+	int ret;
+
+	if (init_cache_level(cpu))
+		return -ENOENT;
+
+	per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu),
+					 sizeof(struct cacheinfo), GFP_KERNEL);
+	if (per_cpu_cacheinfo(cpu) == NULL)
+		return -ENOMEM;
+
+	ret = populate_cache_leaves(cpu);
+	if (ret)
+		goto free_ci;
+	/*
+	 * For systems using DT for cache hierarcy, of_node and shared_cpu_map
+	 * will be set up here only if they are not populated already
+	 */
+	ret = cache_shared_cpu_map_setup(cpu);
+	if (ret)
+		goto free_ci;
+	return 0;
+
+free_ci:
+	free_cache_attributes(cpu);
+	return ret;
+}
+
+/* pointer to cpuX/cache device */
+static DEFINE_PER_CPU(struct device *, ci_cache_dev);
+#define per_cpu_cache_dev(cpu)	(per_cpu(ci_cache_dev, cpu))
+
+static cpumask_t cache_dev_map;
+
+/* pointer to array of devices for cpuX/cache/indexY */
+static DEFINE_PER_CPU(struct device **, ci_index_dev);
+#define per_cpu_index_dev(cpu)	(per_cpu(ci_index_dev, cpu))
+#define per_cache_index_dev(cpu, idx)	((per_cpu_index_dev(cpu))[idx])
+
+#define show_one(file_name, object)				\
+static ssize_t file_name##_show(struct device *dev,		\
+		struct device_attribute *attr, char *buf)	\
+{								\
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);	\
+	return sprintf(buf, "%u\n", this_leaf->object);		\
+}
+
+show_one(level, level);
+show_one(coherency_line_size, coherency_line_size);
+show_one(number_of_sets, number_of_sets);
+show_one(physical_line_partition, physical_line_partition);
+show_one(ways_of_associativity, ways_of_associativity);
+
+static ssize_t size_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%uK\n", this_leaf->size >> 10);
+}
+
+static ssize_t shared_cpumap_show_func(struct device *dev, bool list, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+	const struct cpumask *mask = &this_leaf->shared_cpu_map;
+
+	return cpumap_print_to_pagebuf(list, buf, mask);
+}
+
+static ssize_t shared_cpu_map_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	return shared_cpumap_show_func(dev, false, buf);
+}
+
+static ssize_t shared_cpu_list_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	return shared_cpumap_show_func(dev, true, buf);
+}
+
+static ssize_t type_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+
+	switch (this_leaf->type) {
+	case CACHE_TYPE_DATA:
+		return sprintf(buf, "Data\n");
+	case CACHE_TYPE_INST:
+		return sprintf(buf, "Instruction\n");
+	case CACHE_TYPE_UNIFIED:
+		return sprintf(buf, "Unified\n");
+	default:
+		return -EINVAL;
+	}
+}
+
+static ssize_t allocation_policy_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+	unsigned int ci_attr = this_leaf->attributes;
+	int n = 0;
+
+	if ((ci_attr & CACHE_READ_ALLOCATE) && (ci_attr & CACHE_WRITE_ALLOCATE))
+		n = sprintf(buf, "ReadWriteAllocate\n");
+	else if (ci_attr & CACHE_READ_ALLOCATE)
+		n = sprintf(buf, "ReadAllocate\n");
+	else if (ci_attr & CACHE_WRITE_ALLOCATE)
+		n = sprintf(buf, "WriteAllocate\n");
+	return n;
+}
+
+static ssize_t write_policy_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+	unsigned int ci_attr = this_leaf->attributes;
+	int n = 0;
+
+	if (ci_attr & CACHE_WRITE_THROUGH)
+		n = sprintf(buf, "WriteThrough\n");
+	else if (ci_attr & CACHE_WRITE_BACK)
+		n = sprintf(buf, "WriteBack\n");
+	return n;
+}
+
+static DEVICE_ATTR_RO(level);
+static DEVICE_ATTR_RO(type);
+static DEVICE_ATTR_RO(coherency_line_size);
+static DEVICE_ATTR_RO(ways_of_associativity);
+static DEVICE_ATTR_RO(number_of_sets);
+static DEVICE_ATTR_RO(size);
+static DEVICE_ATTR_RO(allocation_policy);
+static DEVICE_ATTR_RO(write_policy);
+static DEVICE_ATTR_RO(shared_cpu_map);
+static DEVICE_ATTR_RO(shared_cpu_list);
+static DEVICE_ATTR_RO(physical_line_partition);
+
+static struct attribute *cache_default_attrs[] = {
+	&dev_attr_type.attr,
+	&dev_attr_level.attr,
+	&dev_attr_shared_cpu_map.attr,
+	&dev_attr_shared_cpu_list.attr,
+	&dev_attr_coherency_line_size.attr,
+	&dev_attr_ways_of_associativity.attr,
+	&dev_attr_number_of_sets.attr,
+	&dev_attr_size.attr,
+	&dev_attr_allocation_policy.attr,
+	&dev_attr_write_policy.attr,
+	&dev_attr_physical_line_partition.attr,
+	NULL
+};
+
+static umode_t
+cache_default_attrs_is_visible(struct kobject *kobj,
+			       struct attribute *attr, int unused)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+	const struct cpumask *mask = &this_leaf->shared_cpu_map;
+	umode_t mode = attr->mode;
+
+	if ((attr == &dev_attr_type.attr) && this_leaf->type)
+		return mode;
+	if ((attr == &dev_attr_level.attr) && this_leaf->level)
+		return mode;
+	if ((attr == &dev_attr_shared_cpu_map.attr) && !cpumask_empty(mask))
+		return mode;
+	if ((attr == &dev_attr_shared_cpu_list.attr) && !cpumask_empty(mask))
+		return mode;
+	if ((attr == &dev_attr_coherency_line_size.attr) &&
+	    this_leaf->coherency_line_size)
+		return mode;
+	if ((attr == &dev_attr_ways_of_associativity.attr) &&
+	    this_leaf->size) /* allow 0 = full associativity */
+		return mode;
+	if ((attr == &dev_attr_number_of_sets.attr) &&
+	    this_leaf->number_of_sets)
+		return mode;
+	if ((attr == &dev_attr_size.attr) && this_leaf->size)
+		return mode;
+	if ((attr == &dev_attr_write_policy.attr) &&
+	    (this_leaf->attributes & CACHE_WRITE_POLICY_MASK))
+		return mode;
+	if ((attr == &dev_attr_allocation_policy.attr) &&
+	    (this_leaf->attributes & CACHE_ALLOCATE_POLICY_MASK))
+		return mode;
+	if ((attr == &dev_attr_physical_line_partition.attr) &&
+	    this_leaf->physical_line_partition)
+		return mode;
+
+	return 0;
+}
+
+static const struct attribute_group cache_default_group = {
+	.attrs = cache_default_attrs,
+	.is_visible = cache_default_attrs_is_visible,
+};
+
+static const struct attribute_group *cache_default_groups[] = {
+	&cache_default_group,
+	NULL,
+};
+
+static const struct attribute_group *cache_private_groups[] = {
+	&cache_default_group,
+	NULL, /* Place holder for private group */
+	NULL,
+};
+
+const struct attribute_group *
+__weak cache_get_priv_group(struct cacheinfo *this_leaf)
+{
+	return NULL;
+}
+
+static const struct attribute_group **
+cache_get_attribute_groups(struct cacheinfo *this_leaf)
+{
+	const struct attribute_group *priv_group =
+			cache_get_priv_group(this_leaf);
+
+	if (!priv_group)
+		return cache_default_groups;
+
+	if (!cache_private_groups[1])
+		cache_private_groups[1] = priv_group;
+
+	return cache_private_groups;
+}
+
+/* Add/Remove cache interface for CPU device */
+static void cpu_cache_sysfs_exit(unsigned int cpu)
+{
+	int i;
+	struct device *ci_dev;
+
+	if (per_cpu_index_dev(cpu)) {
+		for (i = 0; i < cache_leaves(cpu); i++) {
+			ci_dev = per_cache_index_dev(cpu, i);
+			if (!ci_dev)
+				continue;
+			device_unregister(ci_dev);
+		}
+		kfree(per_cpu_index_dev(cpu));
+		per_cpu_index_dev(cpu) = NULL;
+	}
+	device_unregister(per_cpu_cache_dev(cpu));
+	per_cpu_cache_dev(cpu) = NULL;
+}
+
+static int cpu_cache_sysfs_init(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	if (per_cpu_cacheinfo(cpu) == NULL)
+		return -ENOENT;
+
+	per_cpu_cache_dev(cpu) = cpu_device_create(dev, NULL, NULL, "cache");
+	if (IS_ERR(per_cpu_cache_dev(cpu)))
+		return PTR_ERR(per_cpu_cache_dev(cpu));
+
+	/* Allocate all required memory */
+	per_cpu_index_dev(cpu) = kcalloc(cache_leaves(cpu),
+					 sizeof(struct device *), GFP_KERNEL);
+	if (unlikely(per_cpu_index_dev(cpu) == NULL))
+		goto err_out;
+
+	return 0;
+
+err_out:
+	cpu_cache_sysfs_exit(cpu);
+	return -ENOMEM;
+}
+
+static int cache_add_dev(unsigned int cpu)
+{
+	unsigned int i;
+	int rc;
+	struct device *ci_dev, *parent;
+	struct cacheinfo *this_leaf;
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	const struct attribute_group **cache_groups;
+
+	rc = cpu_cache_sysfs_init(cpu);
+	if (unlikely(rc < 0))
+		return rc;
+
+	parent = per_cpu_cache_dev(cpu);
+	for (i = 0; i < cache_leaves(cpu); i++) {
+		this_leaf = this_cpu_ci->info_list + i;
+		if (this_leaf->disable_sysfs)
+			continue;
+		cache_groups = cache_get_attribute_groups(this_leaf);
+		ci_dev = cpu_device_create(parent, this_leaf, cache_groups,
+					   "index%1u", i);
+		if (IS_ERR(ci_dev)) {
+			rc = PTR_ERR(ci_dev);
+			goto err;
+		}
+		per_cache_index_dev(cpu, i) = ci_dev;
+	}
+	cpumask_set_cpu(cpu, &cache_dev_map);
+
+	return 0;
+err:
+	cpu_cache_sysfs_exit(cpu);
+	return rc;
+}
+
+static void cache_remove_dev(unsigned int cpu)
+{
+	if (!cpumask_test_cpu(cpu, &cache_dev_map))
+		return;
+	cpumask_clear_cpu(cpu, &cache_dev_map);
+
+	cpu_cache_sysfs_exit(cpu);
+}
+
+static int cacheinfo_cpu_callback(struct notifier_block *nfb,
+				  unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+	int rc = 0;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+		rc = detect_cache_attributes(cpu);
+		if (!rc)
+			rc = cache_add_dev(cpu);
+		break;
+	case CPU_DEAD:
+		cache_remove_dev(cpu);
+		if (per_cpu_cacheinfo(cpu))
+			free_cache_attributes(cpu);
+		break;
+	}
+	return notifier_from_errno(rc);
+}
+
+static int __init cacheinfo_sysfs_init(void)
+{
+	int cpu, rc = 0;
+
+	cpu_notifier_register_begin();
+
+	for_each_online_cpu(cpu) {
+		rc = detect_cache_attributes(cpu);
+		if (rc) {
+			pr_err("error detecting cacheinfo..cpu%d\n", cpu);
+			goto out;
+		}
+		rc = cache_add_dev(cpu);
+		if (rc) {
+			free_cache_attributes(cpu);
+			pr_err("error populating cacheinfo..cpu%d\n", cpu);
+			goto out;
+		}
+	}
+	__hotcpu_notifier(cacheinfo_cpu_callback, 0);
+
+out:
+	cpu_notifier_register_done();
+	return rc;
+}
+
+device_initcall(cacheinfo_sysfs_init);
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
new file mode 100644
index 00000000000..3daf5ed392c
--- /dev/null
+++ b/include/linux/cacheinfo.h
@@ -0,0 +1,100 @@
+#ifndef _LINUX_CACHEINFO_H
+#define _LINUX_CACHEINFO_H
+
+#include <linux/bitops.h>
+#include <linux/cpumask.h>
+#include <linux/smp.h>
+
+struct device_node;
+struct attribute;
+
+enum cache_type {
+	CACHE_TYPE_NOCACHE = 0,
+	CACHE_TYPE_INST = BIT(0),
+	CACHE_TYPE_DATA = BIT(1),
+	CACHE_TYPE_SEPARATE = CACHE_TYPE_INST | CACHE_TYPE_DATA,
+	CACHE_TYPE_UNIFIED = BIT(2),
+};
+
+/**
+ * struct cacheinfo - represent a cache leaf node
+ * @type: type of the cache - data, inst or unified
+ * @level: represents the hierarcy in the multi-level cache
+ * @coherency_line_size: size of each cache line usually representing
+ *	the minimum amount of data that gets transferred from memory
+ * @number_of_sets: total number of sets, a set is a collection of cache
+ *	lines sharing the same index
+ * @ways_of_associativity: number of ways in which a particular memory
+ *	block can be placed in the cache
+ * @physical_line_partition: number of physical cache lines sharing the
+ *	same cachetag
+ * @size: Total size of the cache
+ * @shared_cpu_map: logical cpumask representing all the cpus sharing
+ *	this cache node
+ * @attributes: bitfield representing various cache attributes
+ * @of_node: if devicetree is used, this represents either the cpu node in
+ *	case there's no explicit cache node or the cache node itself in the
+ *	device tree
+ * @disable_sysfs: indicates whether this node is visible to the user via
+ *	sysfs or not
+ * @priv: pointer to any private data structure specific to particular
+ *	cache design
+ *
+ * While @of_node, @disable_sysfs and @priv are used for internal book
+ * keeping, the remaining members form the core properties of the cache
+ */
+struct cacheinfo {
+	enum cache_type type;
+	unsigned int level;
+	unsigned int coherency_line_size;
+	unsigned int number_of_sets;
+	unsigned int ways_of_associativity;
+	unsigned int physical_line_partition;
+	unsigned int size;
+	cpumask_t shared_cpu_map;
+	unsigned int attributes;
+#define CACHE_WRITE_THROUGH	BIT(0)
+#define CACHE_WRITE_BACK	BIT(1)
+#define CACHE_WRITE_POLICY_MASK		\
+	(CACHE_WRITE_THROUGH | CACHE_WRITE_BACK)
+#define CACHE_READ_ALLOCATE	BIT(2)
+#define CACHE_WRITE_ALLOCATE	BIT(3)
+#define CACHE_ALLOCATE_POLICY_MASK	\
+	(CACHE_READ_ALLOCATE | CACHE_WRITE_ALLOCATE)
+
+	struct device_node *of_node;
+	bool disable_sysfs;
+	void *priv;
+};
+
+struct cpu_cacheinfo {
+	struct cacheinfo *info_list;
+	unsigned int num_levels;
+	unsigned int num_leaves;
+};
+
+/*
+ * Helpers to make sure "func" is executed on the cpu whose cache
+ * attributes are being detected
+ */
+#define DEFINE_SMP_CALL_CACHE_FUNCTION(func)			\
+static inline void _##func(void *ret)				\
+{								\
+	int cpu = smp_processor_id();				\
+	*(int *)ret = __##func(cpu);				\
+}								\
+								\
+int func(unsigned int cpu)					\
+{								\
+	int ret;						\
+	smp_call_function_single(cpu, _##func, &ret, true);	\
+	return ret;						\
+}
+
+struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu);
+int init_cache_level(unsigned int cpu);
+int populate_cache_leaves(unsigned int cpu);
+
+const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf);
+
+#endif /* _LINUX_CACHEINFO_H */
-- 
cgit v1.2.3-70-g09d2


From df32dd2054b6edcbdfd3a31aec24e7fd0edba2ac Mon Sep 17 00:00:00 2001
From: stephen hemminger <stephen@networkplumber.org>
Date: Mon, 3 Nov 2014 12:42:34 -0800
Subject: uapi: resort Kbuild entries

The entries in the Kbuild files are incorrectly sorted.
Matters for aesthetics only.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/Kbuild | 88 +++++++++++++++++++++++------------------------
 1 file changed, 44 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 4c94f31a8c9..72298b6887a 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -37,27 +37,27 @@ header-y += aio_abi.h
 header-y += apm_bios.h
 header-y += arcfb.h
 header-y += atalk.h
-header-y += atm.h
-header-y += atm_eni.h
-header-y += atm_he.h
-header-y += atm_idt77105.h
-header-y += atm_nicstar.h
-header-y += atm_tcp.h
-header-y += atm_zatm.h
 header-y += atmapi.h
 header-y += atmarp.h
 header-y += atmbr2684.h
 header-y += atmclip.h
 header-y += atmdev.h
+header-y += atm_eni.h
+header-y += atm.h
+header-y += atm_he.h
+header-y += atm_idt77105.h
 header-y += atmioc.h
 header-y += atmlec.h
 header-y += atmmpc.h
+header-y += atm_nicstar.h
 header-y += atmppp.h
 header-y += atmsap.h
 header-y += atmsvc.h
+header-y += atm_tcp.h
+header-y += atm_zatm.h
 header-y += audit.h
-header-y += auto_fs.h
 header-y += auto_fs4.h
+header-y += auto_fs.h
 header-y += auxvec.h
 header-y += ax25.h
 header-y += b1lli.h
@@ -67,8 +67,8 @@ header-y += bfs_fs.h
 header-y += binfmts.h
 header-y += blkpg.h
 header-y += blktrace_api.h
-header-y += bpf.h
 header-y += bpf_common.h
+header-y += bpf.h
 header-y += bpqether.h
 header-y += bsg.h
 header-y += btrfs.h
@@ -93,21 +93,21 @@ header-y += cyclades.h
 header-y += cycx_cfm.h
 header-y += dcbnl.h
 header-y += dccp.h
-header-y += dlm.h
+header-y += dlmconstants.h
 header-y += dlm_device.h
+header-y += dlm.h
 header-y += dlm_netlink.h
 header-y += dlm_plock.h
-header-y += dlmconstants.h
 header-y += dm-ioctl.h
 header-y += dm-log-userspace.h
 header-y += dn.h
 header-y += dqblk_xfs.h
 header-y += edd.h
 header-y += efs_fs_sb.h
+header-y += elfcore.h
 header-y += elf-em.h
 header-y += elf-fdpic.h
 header-y += elf.h
-header-y += elfcore.h
 header-y += errno.h
 header-y += errqueue.h
 header-y += ethtool.h
@@ -131,15 +131,15 @@ header-y += fsl_hypervisor.h
 header-y += fuse.h
 header-y += futex.h
 header-y += gameport.h
-header-y += gen_stats.h
 header-y += genetlink.h
+header-y += gen_stats.h
 header-y += gfs2_ondisk.h
 header-y += gigaset_dev.h
-header-y += hdlc.h
 header-y += hdlcdrv.h
+header-y += hdlc.h
 header-y += hdreg.h
-header-y += hid.h
 header-y += hiddev.h
+header-y += hid.h
 header-y += hidraw.h
 header-y += hpet.h
 header-y += hsr_netlink.h
@@ -151,7 +151,6 @@ header-y += i2o-dev.h
 header-y += i8k.h
 header-y += icmp.h
 header-y += icmpv6.h
-header-y += if.h
 header-y += if_addr.h
 header-y += if_addrlabel.h
 header-y += if_alg.h
@@ -165,6 +164,7 @@ header-y += if_ether.h
 header-y += if_fc.h
 header-y += if_fddi.h
 header-y += if_frad.h
+header-y += if.h
 header-y += if_hippi.h
 header-y += if_infiniband.h
 header-y += if_link.h
@@ -182,40 +182,40 @@ header-y += if_tunnel.h
 header-y += if_vlan.h
 header-y += if_x25.h
 header-y += igmp.h
-header-y += in.h
 header-y += in6.h
-header-y += in_route.h
 header-y += inet_diag.h
+header-y += in.h
 header-y += inotify.h
 header-y += input.h
+header-y += in_route.h
 header-y += ioctl.h
-header-y += ip.h
 header-y += ip6_tunnel.h
-header-y += ip_vs.h
 header-y += ipc.h
+header-y += ip.h
 header-y += ipmi.h
 header-y += ipmi_msgdefs.h
 header-y += ipsec.h
 header-y += ipv6.h
 header-y += ipv6_route.h
+header-y += ip_vs.h
 header-y += ipx.h
 header-y += irda.h
 header-y += irqnr.h
-header-y += isdn.h
 header-y += isdn_divertif.h
-header-y += isdn_ppp.h
+header-y += isdn.h
 header-y += isdnif.h
+header-y += isdn_ppp.h
 header-y += iso_fs.h
-header-y += ivtv.h
 header-y += ivtvfb.h
+header-y += ivtv.h
 header-y += ixjuser.h
 header-y += jffs2.h
 header-y += joystick.h
-header-y += kd.h
 header-y += kdev_t.h
-header-y += kernel-page-flags.h
-header-y += kernel.h
+header-y += kd.h
 header-y += kernelcapi.h
+header-y += kernel.h
+header-y += kernel-page-flags.h
 header-y += kexec.h
 header-y += keyboard.h
 header-y += keyctl.h
@@ -231,6 +231,7 @@ ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/kvm_para.h \
 header-y += kvm_para.h
 endif
 
+header-y += hw_breakpoint.h
 header-y += l2tp.h
 header-y += libc-compat.h
 header-y += limits.h
@@ -255,43 +256,43 @@ header-y += mman.h
 header-y += mmtimer.h
 header-y += mpls.h
 header-y += mqueue.h
-header-y += mroute.h
 header-y += mroute6.h
+header-y += mroute.h
 header-y += msdos_fs.h
 header-y += msg.h
 header-y += mtio.h
-header-y += n_r3964.h
 header-y += nbd.h
-header-y += ncp.h
 header-y += ncp_fs.h
+header-y += ncp.h
 header-y += ncp_mount.h
 header-y += ncp_no.h
 header-y += neighbour.h
-header-y += net.h
-header-y += net_dropmon.h
-header-y += net_tstamp.h
 header-y += netconf.h
 header-y += netdevice.h
-header-y += netlink_diag.h
-header-y += netfilter.h
+header-y += net_dropmon.h
 header-y += netfilter_arp.h
 header-y += netfilter_bridge.h
 header-y += netfilter_decnet.h
+header-y += netfilter.h
 header-y += netfilter_ipv4.h
 header-y += netfilter_ipv6.h
+header-y += net.h
+header-y += netlink_diag.h
 header-y += netlink.h
 header-y += netrom.h
+header-y += net_tstamp.h
 header-y += nfc.h
-header-y += nfs.h
 header-y += nfs2.h
 header-y += nfs3.h
 header-y += nfs4.h
 header-y += nfs4_mount.h
+header-y += nfsacl.h
 header-y += nfs_fs.h
+header-y += nfs.h
 header-y += nfs_idmap.h
 header-y += nfs_mount.h
-header-y += nfsacl.h
 header-y += nl80211.h
+header-y += n_r3964.h
 header-y += nubus.h
 header-y += nvme.h
 header-y += nvram.h
@@ -311,16 +312,16 @@ header-y += pfkeyv2.h
 header-y += pg.h
 header-y += phantom.h
 header-y += phonet.h
+header-y += pktcdvd.h
 header-y += pkt_cls.h
 header-y += pkt_sched.h
-header-y += pktcdvd.h
 header-y += pmu.h
 header-y += poll.h
 header-y += posix_types.h
 header-y += ppdev.h
 header-y += ppp-comp.h
-header-y += ppp-ioctl.h
 header-y += ppp_defs.h
+header-y += ppp-ioctl.h
 header-y += pps.h
 header-y += prctl.h
 header-y += psci.h
@@ -352,13 +353,13 @@ header-y += seccomp.h
 header-y += securebits.h
 header-y += selinux_netlink.h
 header-y += sem.h
-header-y += serial.h
 header-y += serial_core.h
+header-y += serial.h
 header-y += serial_reg.h
 header-y += serio.h
 header-y += shm.h
-header-y += signal.h
 header-y += signalfd.h
+header-y += signal.h
 header-y += smiapp.h
 header-y += snmp.h
 header-y += sock_diag.h
@@ -367,8 +368,8 @@ header-y += sockios.h
 header-y += som.h
 header-y += sonet.h
 header-y += sonypi.h
-header-y += sound.h
 header-y += soundcard.h
+header-y += sound.h
 header-y += stat.h
 header-y += stddef.h
 header-y += string.h
@@ -387,11 +388,11 @@ header-y += time.h
 header-y += times.h
 header-y += timex.h
 header-y += tiocl.h
-header-y += tipc.h
 header-y += tipc_config.h
+header-y += tipc.h
 header-y += toshiba.h
-header-y += tty.h
 header-y += tty_flags.h
+header-y += tty.h
 header-y += types.h
 header-y += udf_fs_i.h
 header-y += udp.h
@@ -437,6 +438,5 @@ header-y += wireless.h
 header-y += x25.h
 header-y += xattr.h
 header-y += xfrm.h
-header-y += hw_breakpoint.h
 header-y += zorro.h
 header-y += zorro_ids.h
-- 
cgit v1.2.3-70-g09d2


From 36cbb2452cbafca64dcdd3578047433787900cf0 Mon Sep 17 00:00:00 2001
From: Rick Jones <rick.jones2@hp.com>
Date: Thu, 6 Nov 2014 10:37:54 -0800
Subject: udp: Increment UDP_MIB_IGNOREDMULTI for arriving unmatched multicasts

As NIC multicast filtering isn't perfect, and some platforms are
quite content to spew broadcasts, we should not trigger an event
for skb:kfree_skb when we do not have a match for such an incoming
datagram.  We do though want to avoid sweeping the matter under the
rug entirely, so increment a suitable statistic.

This incorporates feedback from David L. Stevens, Karl Neiss and Eric
Dumazet.

V3 - use bool per David Miller

Signed-off-by: Rick Jones <rick.jones2@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/snmp.h |  1 +
 net/ipv4/proc.c           |  1 +
 net/ipv4/udp.c            | 12 +++++++++---
 net/ipv6/proc.c           |  1 +
 net/ipv6/udp.c            | 11 ++++++++---
 5 files changed, 20 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index df40137f33d..30f541b3289 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -156,6 +156,7 @@ enum
 	UDP_MIB_RCVBUFERRORS,			/* RcvbufErrors */
 	UDP_MIB_SNDBUFERRORS,			/* SndbufErrors */
 	UDP_MIB_CSUMERRORS,			/* InCsumErrors */
+	UDP_MIB_IGNOREDMULTI,			/* IgnoredMulti */
 	__UDP_MIB_MAX
 };
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index f0d4eb8b99b..6513ade8d6d 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -181,6 +181,7 @@ static const struct snmp_mib snmp4_udp_list[] = {
 	SNMP_MIB_ITEM("RcvbufErrors", UDP_MIB_RCVBUFERRORS),
 	SNMP_MIB_ITEM("SndbufErrors", UDP_MIB_SNDBUFERRORS),
 	SNMP_MIB_ITEM("InCsumErrors", UDP_MIB_CSUMERRORS),
+	SNMP_MIB_ITEM("IgnoredMulti", UDP_MIB_IGNOREDMULTI),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index df19027f44f..5d0fdca8e96 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1647,7 +1647,8 @@ static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 				    struct udphdr  *uh,
 				    __be32 saddr, __be32 daddr,
-				    struct udp_table *udptable)
+				    struct udp_table *udptable,
+				    int proto)
 {
 	struct sock *sk, *stack[256 / sizeof(struct sock *)];
 	struct hlist_nulls_node *node;
@@ -1656,6 +1657,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 	int dif = skb->dev->ifindex;
 	unsigned int count = 0, offset = offsetof(typeof(*sk), sk_nulls_node);
 	unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
+	bool inner_flushed = false;
 
 	if (use_hash2) {
 		hash2_any = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum) &
@@ -1674,6 +1676,7 @@ start_lookup:
 					dif, hnum)) {
 			if (unlikely(count == ARRAY_SIZE(stack))) {
 				flush_stack(stack, count, skb, ~0);
+				inner_flushed = true;
 				count = 0;
 			}
 			stack[count++] = sk;
@@ -1695,7 +1698,10 @@ start_lookup:
 	if (count) {
 		flush_stack(stack, count, skb, count - 1);
 	} else {
-		kfree_skb(skb);
+		if (!inner_flushed)
+			UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
+					 proto == IPPROTO_UDPLITE);
+		consume_skb(skb);
 	}
 	return 0;
 }
@@ -1781,7 +1787,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 
 	if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
 		return __udp4_lib_mcast_deliver(net, skb, uh,
-				saddr, daddr, udptable);
+						saddr, daddr, udptable, proto);
 
 	sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
 	if (sk != NULL) {
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 1752cd0b488..679253d0af8 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -136,6 +136,7 @@ static const struct snmp_mib snmp6_udp6_list[] = {
 	SNMP_MIB_ITEM("Udp6RcvbufErrors", UDP_MIB_RCVBUFERRORS),
 	SNMP_MIB_ITEM("Udp6SndbufErrors", UDP_MIB_SNDBUFERRORS),
 	SNMP_MIB_ITEM("Udp6InCsumErrors", UDP_MIB_CSUMERRORS),
+	SNMP_MIB_ITEM("Udp6IgnoredMulti", UDP_MIB_IGNOREDMULTI),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 9b6809232b1..b756355e973 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -771,7 +771,7 @@ static void udp6_csum_zero_error(struct sk_buff *skb)
  */
 static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 		const struct in6_addr *saddr, const struct in6_addr *daddr,
-		struct udp_table *udptable)
+		struct udp_table *udptable, int proto)
 {
 	struct sock *sk, *stack[256 / sizeof(struct sock *)];
 	const struct udphdr *uh = udp_hdr(skb);
@@ -781,6 +781,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 	int dif = inet6_iif(skb);
 	unsigned int count = 0, offset = offsetof(typeof(*sk), sk_nulls_node);
 	unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
+	bool inner_flushed = false;
 
 	if (use_hash2) {
 		hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) &
@@ -803,6 +804,7 @@ start_lookup:
 		    (uh->check || udp_sk(sk)->no_check6_rx)) {
 			if (unlikely(count == ARRAY_SIZE(stack))) {
 				flush_stack(stack, count, skb, ~0);
+				inner_flushed = true;
 				count = 0;
 			}
 			stack[count++] = sk;
@@ -821,7 +823,10 @@ start_lookup:
 	if (count) {
 		flush_stack(stack, count, skb, count - 1);
 	} else {
-		kfree_skb(skb);
+		if (!inner_flushed)
+			UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
+					 proto == IPPROTO_UDPLITE);
+		consume_skb(skb);
 	}
 	return 0;
 }
@@ -873,7 +878,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	 */
 	if (ipv6_addr_is_multicast(daddr))
 		return __udp6_lib_mcast_deliver(net, skb,
-				saddr, daddr, udptable);
+				saddr, daddr, udptable, proto);
 
 	/* Unicast */
 
-- 
cgit v1.2.3-70-g09d2


From 72c72bdf7bf53353d2d8e055194d27f0128be92b Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@netapp.com>
Date: Fri, 7 Nov 2014 14:44:25 -0500
Subject: VFS: Rename do_fallocate() to vfs_fallocate()

This function needs to be exported so it can be used by the NFSD module
when responding to the new ALLOCATE and DEALLOCATE operations in NFS
v4.2.  Christoph Hellwig suggested renaming the function to stay
consistent with how other vfs functions are named.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 drivers/staging/android/ashmem.c | 2 +-
 fs/ioctl.c                       | 2 +-
 fs/open.c                        | 5 +++--
 include/linux/fs.h               | 2 +-
 mm/madvise.c                     | 2 +-
 5 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index ad4f5790a76..27eecfe1c41 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -446,7 +446,7 @@ ashmem_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 		loff_t start = range->pgstart * PAGE_SIZE;
 		loff_t end = (range->pgend + 1) * PAGE_SIZE;
 
-		do_fallocate(range->asma->file,
+		vfs_fallocate(range->asma->file,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				start, end - start);
 		range->purged = ASHMEM_WAS_PURGED;
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 8ac3fad3619..0bd6142183e 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -443,7 +443,7 @@ int ioctl_preallocate(struct file *filp, void __user *argp)
 		return -EINVAL;
 	}
 
-	return do_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len);
+	return vfs_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len);
 }
 
 static int file_ioctl(struct file *filp, unsigned int cmd,
diff --git a/fs/open.c b/fs/open.c
index d6fd3acde13..c94449b2e58 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -222,7 +222,7 @@ SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length)
 #endif /* BITS_PER_LONG == 32 */
 
 
-int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
+int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(file);
 	long ret;
@@ -298,6 +298,7 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	sb_end_write(inode->i_sb);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(vfs_fallocate);
 
 SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len)
 {
@@ -305,7 +306,7 @@ SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len)
 	int error = -EBADF;
 
 	if (f.file) {
-		error = do_fallocate(f.file, mode, offset, len);
+		error = vfs_fallocate(f.file, mode, offset, len);
 		fdput(f);
 	}
 	return error;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a957d4366c2..a8871867757 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2032,7 +2032,7 @@ struct filename {
 extern long vfs_truncate(struct path *, loff_t);
 extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
 		       struct file *filp);
-extern int do_fallocate(struct file *file, int mode, loff_t offset,
+extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
 			loff_t len);
 extern long do_sys_open(int dfd, const char __user *filename, int flags,
 			umode_t mode);
diff --git a/mm/madvise.c b/mm/madvise.c
index 0938b30da4a..a271adc9328 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -326,7 +326,7 @@ static long madvise_remove(struct vm_area_struct *vma,
 	 */
 	get_file(f);
 	up_read(&current->mm->mmap_sem);
-	error = do_fallocate(f,
+	error = vfs_fallocate(f,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				offset, end - start);
 	fput(f);
-- 
cgit v1.2.3-70-g09d2


From a06ae8609b3dd06b957a6e4e965772a8a14d3af5 Mon Sep 17 00:00:00 2001
From: Pratik Patel <pratikp@codeaurora.org>
Date: Mon, 3 Nov 2014 11:07:35 -0700
Subject: coresight: add CoreSight core layer framework

CoreSight components are compliant with the ARM CoreSight
architecture specification and can be connected in various
topologies to suit a particular SoC tracing needs. These trace
components can generally be classified as sources, links and
sinks. Trace data produced by one or more sources flows through
the intermediate links connecting the source to the currently
selected sink.

The CoreSight framework provides an interface for the CoreSight trace
drivers to register themselves with. It's intended to build up a
topological view of the CoreSight components and configure the
correct serie of components on user input via sysfs.

For eg., when enabling a source, the framework builds up a path
consisting of all the components connecting the source to the
currently selected sink(s) and enables all of them.

The framework also supports switching between available sinks
and provides status information to user space applications
through the debugfs interface.

Signed-off-by: Pratik Patel <pratikp@codeaurora.org>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS                        |   8 +
 arch/arm/Kconfig.debug             |   9 +
 drivers/Makefile                   |   1 +
 drivers/amba/bus.c                 |   2 +-
 drivers/coresight/Makefile         |   5 +
 drivers/coresight/coresight-priv.h |  63 ++++
 drivers/coresight/coresight.c      | 717 +++++++++++++++++++++++++++++++++++++
 drivers/coresight/of_coresight.c   | 204 +++++++++++
 include/linux/amba/bus.h           |   1 +
 include/linux/coresight.h          | 263 ++++++++++++++
 10 files changed, 1272 insertions(+), 1 deletion(-)
 create mode 100644 drivers/coresight/Makefile
 create mode 100644 drivers/coresight/coresight-priv.h
 create mode 100644 drivers/coresight/coresight.c
 create mode 100644 drivers/coresight/of_coresight.c
 create mode 100644 include/linux/coresight.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 3c6427190be..39952634be8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -918,6 +918,14 @@ M:	Hubert Feurstein <hubert.feurstein@contec.at>
 S:	Maintained
 F:	arch/arm/mach-ep93xx/micro9.c
 
+ARM/CORESIGHT FRAMEWORK AND DRIVERS
+M:	Mathieu Poirier <mathieu.poirier@linaro.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	drivers/coresight/*
+F:	Documentation/trace/coresight.txt
+F:	Documentation/devicetree/bindings/arm/coresight.txt
+
 ARM/CORGI MACHINE SUPPORT
 M:	Richard Purdie <rpurdie@rpsys.net>
 S:	Maintained
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 03dc4c1a873..cd3890e3110 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -1331,4 +1331,13 @@ config DEBUG_SET_MODULE_RONX
 	  against certain classes of kernel exploits.
 	  If in doubt, say "N".
 
+menuconfig CORESIGHT
+	bool "CoreSight Tracing Support"
+	select ARM_AMBA
+	help
+	  This framework provides a kernel interface for the CoreSight debug
+	  and trace drivers to register themselves with. It's intended to build
+	  a topological view of the CoreSight components based on a DT
+	  specification and configure the right serie of components when a
+	  trace source gets enabled.
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index ebee55537a0..628b512b625 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -161,3 +161,4 @@ obj-$(CONFIG_POWERCAP)		+= powercap/
 obj-$(CONFIG_MCB)		+= mcb/
 obj-$(CONFIG_RAS)		+= ras/
 obj-$(CONFIG_THUNDERBOLT)	+= thunderbolt/
+obj-$(CONFIG_CORESIGHT)		+= coresight/
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 47bbdc1b5be..a4ac490dd78 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -336,7 +336,7 @@ int amba_device_add(struct amba_device *dev, struct resource *parent)
 
 		amba_put_disable_pclk(dev);
 
-		if (cid == AMBA_CID)
+		if (cid == AMBA_CID || cid == CORESIGHT_CID)
 			dev->periphid = pid;
 
 		if (!dev->periphid)
diff --git a/drivers/coresight/Makefile b/drivers/coresight/Makefile
new file mode 100644
index 00000000000..218e3b589f9
--- /dev/null
+++ b/drivers/coresight/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for CoreSight drivers.
+#
+obj-$(CONFIG_CORESIGHT) += coresight.o
+obj-$(CONFIG_OF) += of_coresight.o
diff --git a/drivers/coresight/coresight-priv.h b/drivers/coresight/coresight-priv.h
new file mode 100644
index 00000000000..8d1180c47c0
--- /dev/null
+++ b/drivers/coresight/coresight-priv.h
@@ -0,0 +1,63 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CORESIGHT_PRIV_H
+#define _CORESIGHT_PRIV_H
+
+#include <linux/bitops.h>
+#include <linux/io.h>
+#include <linux/coresight.h>
+
+/*
+ * Coresight management registers (0xf00-0xfcc)
+ * 0xfa0 - 0xfa4: Management	registers in PFTv1.0
+ *		  Trace		registers in PFTv1.1
+ */
+#define CORESIGHT_ITCTRL	0xf00
+#define CORESIGHT_CLAIMSET	0xfa0
+#define CORESIGHT_CLAIMCLR	0xfa4
+#define CORESIGHT_LAR		0xfb0
+#define CORESIGHT_LSR		0xfb4
+#define CORESIGHT_AUTHSTATUS	0xfb8
+#define CORESIGHT_DEVID		0xfc8
+#define CORESIGHT_DEVTYPE	0xfcc
+
+#define TIMEOUT_US		100
+#define BMVAL(val, lsb, msb)	((val & GENMASK(msb, lsb)) >> lsb)
+
+static inline void CS_LOCK(void __iomem *addr)
+{
+	do {
+		/* Wait for things to settle */
+		mb();
+		writel_relaxed(0x0, addr + CORESIGHT_LAR);
+	} while (0);
+}
+
+static inline void CS_UNLOCK(void __iomem *addr)
+{
+	do {
+		writel_relaxed(CORESIGHT_UNLOCK, addr + CORESIGHT_LAR);
+		/* Make sure eveyone has seen this */
+		mb();
+	} while (0);
+}
+
+#ifdef CONFIG_CORESIGHT_SOURCE_ETM3X
+extern int etm_readl_cp14(u32 off, unsigned int *val);
+extern int etm_writel_cp14(u32 off, u32 val);
+#else
+static inline int etm_readl_cp14(u32 off, unsigned int *val) { return 0; }
+static inline int etm_writel_cp14(u32 val, u32 off) { return 0; }
+#endif
+
+#endif
diff --git a/drivers/coresight/coresight.c b/drivers/coresight/coresight.c
new file mode 100644
index 00000000000..6e0181f8442
--- /dev/null
+++ b/drivers/coresight/coresight.c
@@ -0,0 +1,717 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/clk.h>
+#include <linux/coresight.h>
+#include <linux/of_platform.h>
+#include <linux/delay.h>
+
+#include "coresight-priv.h"
+
+static DEFINE_MUTEX(coresight_mutex);
+
+static int coresight_id_match(struct device *dev, void *data)
+{
+	int trace_id, i_trace_id;
+	struct coresight_device *csdev, *i_csdev;
+
+	csdev = data;
+	i_csdev = to_coresight_device(dev);
+
+	/*
+	 * No need to care about oneself and components that are not
+	 * sources or not enabled
+	 */
+	if (i_csdev == csdev || !i_csdev->enable ||
+	    i_csdev->type != CORESIGHT_DEV_TYPE_SOURCE)
+		return 0;
+
+	/* Get the source ID for both compoment */
+	trace_id = source_ops(csdev)->trace_id(csdev);
+	i_trace_id = source_ops(i_csdev)->trace_id(i_csdev);
+
+	/* All you need is one */
+	if (trace_id == i_trace_id)
+		return 1;
+
+	return 0;
+}
+
+static int coresight_source_is_unique(struct coresight_device *csdev)
+{
+	int trace_id = source_ops(csdev)->trace_id(csdev);
+
+	/* this shouldn't happen */
+	if (trace_id < 0)
+		return 0;
+
+	return !bus_for_each_dev(&coresight_bustype, NULL,
+				 csdev, coresight_id_match);
+}
+
+static int coresight_find_link_inport(struct coresight_device *csdev)
+{
+	int i;
+	struct coresight_device *parent;
+	struct coresight_connection *conn;
+
+	parent = container_of(csdev->path_link.next,
+			      struct coresight_device, path_link);
+
+	for (i = 0; i < parent->nr_outport; i++) {
+		conn = &parent->conns[i];
+		if (conn->child_dev == csdev)
+			return conn->child_port;
+	}
+
+	dev_err(&csdev->dev, "couldn't find inport, parent: %s, child: %s\n",
+		dev_name(&parent->dev), dev_name(&csdev->dev));
+
+	return 0;
+}
+
+static int coresight_find_link_outport(struct coresight_device *csdev)
+{
+	int i;
+	struct coresight_device *child;
+	struct coresight_connection *conn;
+
+	child = container_of(csdev->path_link.prev,
+			     struct coresight_device, path_link);
+
+	for (i = 0; i < csdev->nr_outport; i++) {
+		conn = &csdev->conns[i];
+		if (conn->child_dev == child)
+			return conn->outport;
+	}
+
+	dev_err(&csdev->dev, "couldn't find outport, parent: %s, child: %s\n",
+		dev_name(&csdev->dev), dev_name(&child->dev));
+
+	return 0;
+}
+
+static int coresight_enable_sink(struct coresight_device *csdev)
+{
+	int ret;
+
+	if (!csdev->enable) {
+		if (sink_ops(csdev)->enable) {
+			ret = sink_ops(csdev)->enable(csdev);
+			if (ret)
+				return ret;
+		}
+		csdev->enable = true;
+	}
+
+	atomic_inc(csdev->refcnt);
+
+	return 0;
+}
+
+static void coresight_disable_sink(struct coresight_device *csdev)
+{
+	if (atomic_dec_return(csdev->refcnt) == 0) {
+		if (sink_ops(csdev)->disable) {
+			sink_ops(csdev)->disable(csdev);
+			csdev->enable = false;
+		}
+	}
+}
+
+static int coresight_enable_link(struct coresight_device *csdev)
+{
+	int ret;
+	int link_subtype;
+	int refport, inport, outport;
+
+	inport = coresight_find_link_inport(csdev);
+	outport = coresight_find_link_outport(csdev);
+	link_subtype = csdev->subtype.link_subtype;
+
+	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG)
+		refport = inport;
+	else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT)
+		refport = outport;
+	else
+		refport = 0;
+
+	if (atomic_inc_return(&csdev->refcnt[refport]) == 1) {
+		if (link_ops(csdev)->enable) {
+			ret = link_ops(csdev)->enable(csdev, inport, outport);
+			if (ret)
+				return ret;
+		}
+	}
+
+	csdev->enable = true;
+
+	return 0;
+}
+
+static void coresight_disable_link(struct coresight_device *csdev)
+{
+	int i, nr_conns;
+	int link_subtype;
+	int refport, inport, outport;
+
+	inport = coresight_find_link_inport(csdev);
+	outport = coresight_find_link_outport(csdev);
+	link_subtype = csdev->subtype.link_subtype;
+
+	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) {
+		refport = inport;
+		nr_conns = csdev->nr_inport;
+	} else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) {
+		refport = outport;
+		nr_conns = csdev->nr_outport;
+	} else {
+		refport = 0;
+		nr_conns = 1;
+	}
+
+	if (atomic_dec_return(&csdev->refcnt[refport]) == 0) {
+		if (link_ops(csdev)->disable)
+			link_ops(csdev)->disable(csdev, inport, outport);
+	}
+
+	for (i = 0; i < nr_conns; i++)
+		if (atomic_read(&csdev->refcnt[i]) != 0)
+			return;
+
+	csdev->enable = false;
+}
+
+static int coresight_enable_source(struct coresight_device *csdev)
+{
+	int ret;
+
+	if (!coresight_source_is_unique(csdev)) {
+		dev_warn(&csdev->dev, "traceID %d not unique\n",
+			 source_ops(csdev)->trace_id(csdev));
+		return -EINVAL;
+	}
+
+	if (!csdev->enable) {
+		if (source_ops(csdev)->enable) {
+			ret = source_ops(csdev)->enable(csdev);
+			if (ret)
+				return ret;
+		}
+		csdev->enable = true;
+	}
+
+	atomic_inc(csdev->refcnt);
+
+	return 0;
+}
+
+static void coresight_disable_source(struct coresight_device *csdev)
+{
+	if (atomic_dec_return(csdev->refcnt) == 0) {
+		if (source_ops(csdev)->disable) {
+			source_ops(csdev)->disable(csdev);
+			csdev->enable = false;
+		}
+	}
+}
+
+static int coresight_enable_path(struct list_head *path)
+{
+	int ret = 0;
+	struct coresight_device *cd;
+
+	list_for_each_entry(cd, path, path_link) {
+		if (cd == list_first_entry(path, struct coresight_device,
+					   path_link)) {
+			ret = coresight_enable_sink(cd);
+		} else if (list_is_last(&cd->path_link, path)) {
+			/*
+			 * Don't enable the source just yet - this needs to
+			 * happen at the very end when all links and sink
+			 * along the path have been configured properly.
+			 */
+			;
+		} else {
+			ret = coresight_enable_link(cd);
+		}
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+err:
+	list_for_each_entry_continue_reverse(cd, path, path_link) {
+		if (cd == list_first_entry(path, struct coresight_device,
+					   path_link)) {
+			coresight_disable_sink(cd);
+		} else if (list_is_last(&cd->path_link, path)) {
+			;
+		} else {
+			coresight_disable_link(cd);
+		}
+	}
+
+	return ret;
+}
+
+static int coresight_disable_path(struct list_head *path)
+{
+	struct coresight_device *cd;
+
+	list_for_each_entry_reverse(cd, path, path_link) {
+		if (cd == list_first_entry(path, struct coresight_device,
+					   path_link)) {
+			coresight_disable_sink(cd);
+		} else if (list_is_last(&cd->path_link, path)) {
+			/*
+			 * The source has already been stopped, no need
+			 * to do it again here.
+			 */
+			;
+		} else {
+			coresight_disable_link(cd);
+		}
+	}
+
+	return 0;
+}
+
+static int coresight_build_paths(struct coresight_device *csdev,
+				 struct list_head *path,
+				 bool enable)
+{
+	int i, ret = -EINVAL;
+	struct coresight_connection *conn;
+
+	list_add(&csdev->path_link, path);
+
+	if (csdev->type == CORESIGHT_DEV_TYPE_SINK && csdev->activated) {
+		if (enable)
+			ret = coresight_enable_path(path);
+		else
+			ret = coresight_disable_path(path);
+	} else {
+		for (i = 0; i < csdev->nr_outport; i++) {
+			conn = &csdev->conns[i];
+			if (coresight_build_paths(conn->child_dev,
+						    path, enable) == 0)
+				ret = 0;
+		}
+	}
+
+	if (list_first_entry(path, struct coresight_device, path_link) != csdev)
+		dev_err(&csdev->dev, "wrong device in %s\n", __func__);
+
+	list_del(&csdev->path_link);
+
+	return ret;
+}
+
+int coresight_enable(struct coresight_device *csdev)
+{
+	int ret = 0;
+	LIST_HEAD(path);
+
+	mutex_lock(&coresight_mutex);
+	if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) {
+		ret = -EINVAL;
+		dev_err(&csdev->dev, "wrong device type in %s\n", __func__);
+		goto out;
+	}
+	if (csdev->enable)
+		goto out;
+
+	if (coresight_build_paths(csdev, &path, true)) {
+		dev_err(&csdev->dev, "building path(s) failed\n");
+		goto out;
+	}
+
+	if (coresight_enable_source(csdev))
+		dev_err(&csdev->dev, "source enable failed\n");
+out:
+	mutex_unlock(&coresight_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(coresight_enable);
+
+void coresight_disable(struct coresight_device *csdev)
+{
+	LIST_HEAD(path);
+
+	mutex_lock(&coresight_mutex);
+	if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) {
+		dev_err(&csdev->dev, "wrong device type in %s\n", __func__);
+		goto out;
+	}
+	if (!csdev->enable)
+		goto out;
+
+	coresight_disable_source(csdev);
+	if (coresight_build_paths(csdev, &path, false))
+		dev_err(&csdev->dev, "releasing path(s) failed\n");
+
+out:
+	mutex_unlock(&coresight_mutex);
+}
+EXPORT_SYMBOL_GPL(coresight_disable);
+
+static ssize_t enable_sink_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", (unsigned)csdev->activated);
+}
+
+static ssize_t enable_sink_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	if (val)
+		csdev->activated = true;
+	else
+		csdev->activated = false;
+
+	return size;
+
+}
+static DEVICE_ATTR_RW(enable_sink);
+
+static ssize_t enable_source_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", (unsigned)csdev->enable);
+}
+
+static ssize_t enable_source_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t size)
+{
+	int ret = 0;
+	unsigned long val;
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	if (val) {
+		ret = coresight_enable(csdev);
+		if (ret)
+			return ret;
+	} else {
+		coresight_disable(csdev);
+	}
+
+	return size;
+}
+static DEVICE_ATTR_RW(enable_source);
+
+static struct attribute *coresight_sink_attrs[] = {
+	&dev_attr_enable_sink.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_sink);
+
+static struct attribute *coresight_source_attrs[] = {
+	&dev_attr_enable_source.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_source);
+
+static struct device_type coresight_dev_type[] = {
+	{
+		.name = "none",
+	},
+	{
+		.name = "sink",
+		.groups = coresight_sink_groups,
+	},
+	{
+		.name = "link",
+	},
+	{
+		.name = "linksink",
+		.groups = coresight_sink_groups,
+	},
+	{
+		.name = "source",
+		.groups = coresight_source_groups,
+	},
+};
+
+static void coresight_device_release(struct device *dev)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	kfree(csdev);
+}
+
+static int coresight_orphan_match(struct device *dev, void *data)
+{
+	int i;
+	bool still_orphan = false;
+	struct coresight_device *csdev, *i_csdev;
+	struct coresight_connection *conn;
+
+	csdev = data;
+	i_csdev = to_coresight_device(dev);
+
+	/* No need to check oneself */
+	if (csdev == i_csdev)
+		return 0;
+
+	/* Move on to another component if no connection is orphan */
+	if (!i_csdev->orphan)
+		return 0;
+	/*
+	 * Circle throuch all the connection of that component.  If we find
+	 * an orphan connection whose name matches @csdev, link it.
+	 */
+	for (i = 0; i < i_csdev->nr_outport; i++)	{
+		conn = &i_csdev->conns[i];
+
+		/* We have found at least one orphan connection */
+		if (conn->child_dev == NULL) {
+			/* Does it match this newly added device? */
+			if (!strcmp(dev_name(&csdev->dev), conn->child_name))
+				conn->child_dev = csdev;
+		} else {
+			/* Too bad, this component still has an orphan */
+			still_orphan = true;
+		}
+	}
+
+	i_csdev->orphan = still_orphan;
+
+	/*
+	 * Returning '0' ensures that all known component on the
+	 * bus will be checked.
+	 */
+	return 0;
+}
+
+static void coresight_fixup_orphan_conns(struct coresight_device *csdev)
+{
+	/*
+	 * No need to check for a return value as orphan connection(s)
+	 * are hooked-up with each newly added component.
+	 */
+	bus_for_each_dev(&coresight_bustype, NULL,
+				 csdev, coresight_orphan_match);
+}
+
+
+static int coresight_name_match(struct device *dev, void *data)
+{
+	char *to_match;
+	struct coresight_device *i_csdev;
+
+	to_match = data;
+	i_csdev = to_coresight_device(dev);
+
+	if (!strcmp(to_match, dev_name(&i_csdev->dev)))
+		return 1;
+
+	return 0;
+}
+
+static void coresight_fixup_device_conns(struct coresight_device *csdev)
+{
+	int i;
+	struct device *dev = NULL;
+	struct coresight_connection *conn;
+
+	for (i = 0; i < csdev->nr_outport; i++) {
+		conn = &csdev->conns[i];
+		dev = bus_find_device(&coresight_bustype, NULL,
+				      (void *)conn->child_name,
+				      coresight_name_match);
+
+		if (dev) {
+			conn->child_dev = to_coresight_device(dev);
+		} else {
+			csdev->orphan = true;
+			conn->child_dev = NULL;
+		}
+	}
+}
+
+/**
+ * coresight_timeout - loop until a bit has changed to a specific state.
+ * @addr: base address of the area of interest.
+ * @offset: address of a register, starting from @addr.
+ * @position: the position of the bit of interest.
+ * @value: the value the bit should have.
+ *
+ * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if
+ * TIMEOUT_US has elapsed, which ever happens first.
+ */
+
+int coresight_timeout(void __iomem *addr, u32 offset, int position, int value)
+{
+	int i;
+	u32 val;
+
+	for (i = TIMEOUT_US; i > 0; i--) {
+		val = __raw_readl(addr + offset);
+		/* waiting on the bit to go from 0 to 1 */
+		if (value) {
+			if (val & BIT(position))
+				return 0;
+		/* waiting on the bit to go from 1 to 0 */
+		} else {
+			if (!(val & BIT(position)))
+				return 0;
+		}
+
+		/*
+		 * Delay is arbitrary - the specification doesn't say how long
+		 * we are expected to wait.  Extra check required to make sure
+		 * we don't wait needlessly on the last iteration.
+		 */
+		if (i - 1)
+			udelay(1);
+	}
+
+	return -EAGAIN;
+}
+
+struct bus_type coresight_bustype = {
+	.name	= "coresight",
+};
+
+static int __init coresight_init(void)
+{
+	return bus_register(&coresight_bustype);
+}
+postcore_initcall(coresight_init);
+
+struct coresight_device *coresight_register(struct coresight_desc *desc)
+{
+	int i;
+	int ret;
+	int link_subtype;
+	int nr_refcnts = 1;
+	atomic_t *refcnts = NULL;
+	struct coresight_device *csdev;
+	struct coresight_connection *conns;
+
+	csdev = kzalloc(sizeof(*csdev), GFP_KERNEL);
+	if (!csdev) {
+		ret = -ENOMEM;
+		goto err_kzalloc_csdev;
+	}
+
+	if (desc->type == CORESIGHT_DEV_TYPE_LINK ||
+	    desc->type == CORESIGHT_DEV_TYPE_LINKSINK) {
+		link_subtype = desc->subtype.link_subtype;
+
+		if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG)
+			nr_refcnts = desc->pdata->nr_inport;
+		else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT)
+			nr_refcnts = desc->pdata->nr_outport;
+	}
+
+	refcnts = kcalloc(nr_refcnts, sizeof(*refcnts), GFP_KERNEL);
+	if (!refcnts) {
+		ret = -ENOMEM;
+		goto err_kzalloc_refcnts;
+	}
+
+	csdev->refcnt = refcnts;
+
+	csdev->nr_inport = desc->pdata->nr_inport;
+	csdev->nr_outport = desc->pdata->nr_outport;
+	conns = kcalloc(csdev->nr_outport, sizeof(*conns), GFP_KERNEL);
+	if (!conns) {
+		ret = -ENOMEM;
+		goto err_kzalloc_conns;
+	}
+
+	for (i = 0; i < csdev->nr_outport; i++) {
+		conns[i].outport = desc->pdata->outports[i];
+		conns[i].child_name = desc->pdata->child_names[i];
+		conns[i].child_port = desc->pdata->child_ports[i];
+	}
+
+	csdev->conns = conns;
+
+	csdev->type = desc->type;
+	csdev->subtype = desc->subtype;
+	csdev->ops = desc->ops;
+	csdev->orphan = false;
+
+	csdev->dev.type = &coresight_dev_type[desc->type];
+	csdev->dev.groups = desc->groups;
+	csdev->dev.parent = desc->dev;
+	csdev->dev.release = coresight_device_release;
+	csdev->dev.bus = &coresight_bustype;
+	dev_set_name(&csdev->dev, "%s", desc->pdata->name);
+
+	ret = device_register(&csdev->dev);
+	if (ret)
+		goto err_device_register;
+
+	mutex_lock(&coresight_mutex);
+
+	coresight_fixup_device_conns(csdev);
+	coresight_fixup_orphan_conns(csdev);
+
+	mutex_unlock(&coresight_mutex);
+
+	return csdev;
+
+err_device_register:
+	kfree(conns);
+err_kzalloc_conns:
+	kfree(refcnts);
+err_kzalloc_refcnts:
+	kfree(csdev);
+err_kzalloc_csdev:
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(coresight_register);
+
+void coresight_unregister(struct coresight_device *csdev)
+{
+	mutex_lock(&coresight_mutex);
+
+	kfree(csdev->conns);
+	device_unregister(&csdev->dev);
+
+	mutex_unlock(&coresight_mutex);
+}
+EXPORT_SYMBOL_GPL(coresight_unregister);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/coresight/of_coresight.c b/drivers/coresight/of_coresight.c
new file mode 100644
index 00000000000..5030c073450
--- /dev/null
+++ b/drivers/coresight/of_coresight.c
@@ -0,0 +1,204 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_graph.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/amba/bus.h>
+#include <linux/coresight.h>
+#include <asm/smp_plat.h>
+
+
+static int of_dev_node_match(struct device *dev, void *data)
+{
+	return dev->of_node == data;
+}
+
+static struct device *
+of_coresight_get_endpoint_device(struct device_node *endpoint)
+{
+	struct device *dev = NULL;
+
+	/*
+	 * If we have a non-configuable replicator, it will be found on the
+	 * platform bus.
+	 */
+	dev = bus_find_device(&platform_bus_type, NULL,
+			      endpoint, of_dev_node_match);
+	if (dev)
+		return dev;
+
+	/*
+	 * We have a configurable component - circle through the AMBA bus
+	 * looking for the device that matches the endpoint node.
+	 */
+	return bus_find_device(&amba_bustype, NULL,
+			       endpoint, of_dev_node_match);
+}
+
+static struct device_node *of_get_coresight_endpoint(
+		const struct device_node *parent, struct device_node *prev)
+{
+	struct device_node *node = of_graph_get_next_endpoint(parent, prev);
+
+	of_node_put(prev);
+	return node;
+}
+
+static void of_coresight_get_ports(struct device_node *node,
+				   int *nr_inport, int *nr_outport)
+{
+	struct device_node *ep = NULL;
+	int in = 0, out = 0;
+
+	do {
+		ep = of_get_coresight_endpoint(node, ep);
+		if (!ep)
+			break;
+
+		if (of_property_read_bool(ep, "slave-mode"))
+			in++;
+		else
+			out++;
+
+	} while (ep);
+
+	*nr_inport = in;
+	*nr_outport = out;
+}
+
+static int of_coresight_alloc_memory(struct device *dev,
+			struct coresight_platform_data *pdata)
+{
+	/* List of output port on this component */
+	pdata->outports = devm_kzalloc(dev, pdata->nr_outport *
+				       sizeof(*pdata->outports),
+				       GFP_KERNEL);
+	if (!pdata->outports)
+		return -ENOMEM;
+
+	/* Children connected to this component via @outport */
+	 pdata->child_names = devm_kzalloc(dev, pdata->nr_outport *
+					  sizeof(*pdata->child_names),
+					  GFP_KERNEL);
+	if (!pdata->child_names)
+		return -ENOMEM;
+
+	/* Port number on the child this component is connected to */
+	pdata->child_ports = devm_kzalloc(dev, pdata->nr_outport *
+					  sizeof(*pdata->child_ports),
+					  GFP_KERNEL);
+	if (!pdata->child_ports)
+		return -ENOMEM;
+
+	return 0;
+}
+
+struct coresight_platform_data *of_get_coresight_platform_data(
+				struct device *dev, struct device_node *node)
+{
+	int i = 0, ret = 0;
+	struct coresight_platform_data *pdata;
+	struct of_endpoint endpoint, rendpoint;
+	struct device *rdev;
+	struct device_node *cpu;
+	struct device_node *ep = NULL;
+	struct device_node *rparent = NULL;
+	struct device_node *rport = NULL;
+
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+
+	/* Use device name as debugfs handle */
+	pdata->name = dev_name(dev);
+
+	/* Get the number of input and output port for this component */
+	of_coresight_get_ports(node, &pdata->nr_inport, &pdata->nr_outport);
+
+	if (pdata->nr_outport) {
+		ret = of_coresight_alloc_memory(dev, pdata);
+		if (ret)
+			return ERR_PTR(ret);
+
+		/* Iterate through each port to discover topology */
+		do {
+			/* Get a handle on a port */
+			ep = of_get_coresight_endpoint(node, ep);
+			if (!ep)
+				break;
+
+			/*
+			 * No need to deal with input ports, processing for as
+			 * processing for output ports will deal with them.
+			 */
+			if (of_find_property(ep, "slave-mode", NULL))
+				continue;
+
+			/* Get a handle on the local endpoint */
+			ret = of_graph_parse_endpoint(ep, &endpoint);
+
+			if (ret)
+				continue;
+
+			/* The local out port number */
+			pdata->outports[i] = endpoint.id;
+
+			/*
+			 * Get a handle on the remote port and parent
+			 * attached to it.
+			 */
+			rparent = of_graph_get_remote_port_parent(ep);
+			rport = of_graph_get_remote_port(ep);
+
+			if (!rparent || !rport)
+				continue;
+
+			if (of_graph_parse_endpoint(rport, &rendpoint))
+				continue;
+
+			rdev = of_coresight_get_endpoint_device(rparent);
+			if (!dev)
+				continue;
+
+			pdata->child_names[i] = dev_name(rdev);
+			pdata->child_ports[i] = rendpoint.id;
+
+			i++;
+		} while (ep);
+	}
+
+	/* Affinity defaults to CPU0 */
+	pdata->cpu = 0;
+	cpu = of_parse_phandle(node, "cpu", 0);
+	if (cpu) {
+		const u32 *mpidr;
+		int len, index;
+
+		mpidr = of_get_property(cpu, "reg", &len);
+		if (mpidr && len == 4) {
+			index = get_logical_index(be32_to_cpup(mpidr));
+			if (index != -EINVAL)
+				pdata->cpu = index;
+		}
+	}
+
+	return pdata;
+}
+EXPORT_SYMBOL_GPL(of_get_coresight_platform_data);
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index c324f5700d1..d024bd9c9d9 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -23,6 +23,7 @@
 
 #define AMBA_NR_IRQS	9
 #define AMBA_CID	0xb105f00d
+#define CORESIGHT_CID	0xb105900d
 
 struct clk;
 
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
new file mode 100644
index 00000000000..bdde4199c74
--- /dev/null
+++ b/include/linux/coresight.h
@@ -0,0 +1,263 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _LINUX_CORESIGHT_H
+#define _LINUX_CORESIGHT_H
+
+#include <linux/device.h>
+
+/* Peripheral id registers (0xFD0-0xFEC) */
+#define CORESIGHT_PERIPHIDR4	0xfd0
+#define CORESIGHT_PERIPHIDR5	0xfd4
+#define CORESIGHT_PERIPHIDR6	0xfd8
+#define CORESIGHT_PERIPHIDR7	0xfdC
+#define CORESIGHT_PERIPHIDR0	0xfe0
+#define CORESIGHT_PERIPHIDR1	0xfe4
+#define CORESIGHT_PERIPHIDR2	0xfe8
+#define CORESIGHT_PERIPHIDR3	0xfeC
+/* Component id registers (0xFF0-0xFFC) */
+#define CORESIGHT_COMPIDR0	0xff0
+#define CORESIGHT_COMPIDR1	0xff4
+#define CORESIGHT_COMPIDR2	0xff8
+#define CORESIGHT_COMPIDR3	0xffC
+
+#define ETM_ARCH_V3_3		0x23
+#define ETM_ARCH_V3_5		0x25
+#define PFT_ARCH_V1_0		0x30
+#define PFT_ARCH_V1_1		0x31
+
+#define CORESIGHT_UNLOCK	0xc5acce55
+
+extern struct bus_type coresight_bustype;
+
+enum coresight_dev_type {
+	CORESIGHT_DEV_TYPE_NONE,
+	CORESIGHT_DEV_TYPE_SINK,
+	CORESIGHT_DEV_TYPE_LINK,
+	CORESIGHT_DEV_TYPE_LINKSINK,
+	CORESIGHT_DEV_TYPE_SOURCE,
+};
+
+enum coresight_dev_subtype_sink {
+	CORESIGHT_DEV_SUBTYPE_SINK_NONE,
+	CORESIGHT_DEV_SUBTYPE_SINK_PORT,
+	CORESIGHT_DEV_SUBTYPE_SINK_BUFFER,
+};
+
+enum coresight_dev_subtype_link {
+	CORESIGHT_DEV_SUBTYPE_LINK_NONE,
+	CORESIGHT_DEV_SUBTYPE_LINK_MERG,
+	CORESIGHT_DEV_SUBTYPE_LINK_SPLIT,
+	CORESIGHT_DEV_SUBTYPE_LINK_FIFO,
+};
+
+enum coresight_dev_subtype_source {
+	CORESIGHT_DEV_SUBTYPE_SOURCE_NONE,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_PROC,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_BUS,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE,
+};
+
+/**
+ * struct coresight_dev_subtype - further characterisation of a type
+ * @sink_subtype:	type of sink this component is, as defined
+			by @coresight_dev_subtype_sink.
+ * @link_subtype:	type of link this component is, as defined
+			by @coresight_dev_subtype_link.
+ * @source_subtype:	type of source this component is, as defined
+			by @coresight_dev_subtype_source.
+ */
+struct coresight_dev_subtype {
+	enum coresight_dev_subtype_sink sink_subtype;
+	enum coresight_dev_subtype_link link_subtype;
+	enum coresight_dev_subtype_source source_subtype;
+};
+
+/**
+ * struct coresight_platform_data - data harvested from the DT specification
+ * @cpu:	the CPU a source belongs to. Only applicable for ETM/PTMs.
+ * @name:	name of the component as shown under sysfs.
+ * @nr_inport:	number of input ports for this component.
+ * @outports:	list of remote enpoint port number.
+ * @child_names:name of all child components connected to this device.
+ * @child_ports:child component port number the current component is
+		connected  to.
+ * @nr_outport:	number of output ports for this component.
+ * @clk:	The clock this component is associated to.
+ */
+struct coresight_platform_data {
+	int cpu;
+	const char *name;
+	int nr_inport;
+	int *outports;
+	const char **child_names;
+	int *child_ports;
+	int nr_outport;
+	struct clk *clk;
+};
+
+/**
+ * struct coresight_desc - description of a component required from drivers
+ * @type:	as defined by @coresight_dev_type.
+ * @subtype:	as defined by @coresight_dev_subtype.
+ * @ops:	generic operations for this component, as defined
+		by @coresight_ops.
+ * @pdata:	platform data collected from DT.
+ * @dev:	The device entity associated to this component.
+ * @groups	:operations specific to this component. These will end up
+		in the component's sysfs sub-directory.
+ */
+struct coresight_desc {
+	enum coresight_dev_type type;
+	struct coresight_dev_subtype subtype;
+	const struct coresight_ops *ops;
+	struct coresight_platform_data *pdata;
+	struct device *dev;
+	const struct attribute_group **groups;
+};
+
+/**
+ * struct coresight_connection - representation of a single connection
+ * @ref_count:	keeping count a port' references.
+ * @outport:	a connection's output port number.
+ * @chid_name:	remote component's name.
+ * @child_port:	remote component's port number @output is connected to.
+ * @child_dev:	a @coresight_device representation of the component
+		connected to @outport.
+ */
+struct coresight_connection {
+	int outport;
+	const char *child_name;
+	int child_port;
+	struct coresight_device *child_dev;
+};
+
+/**
+ * struct coresight_device - representation of a device as used by the framework
+ * @nr_inport:	number of input port associated to this component.
+ * @nr_outport:	number of output port associated to this component.
+ * @type:	as defined by @coresight_dev_type.
+ * @subtype:	as defined by @coresight_dev_subtype.
+ * @ops:	generic operations for this component, as defined
+		by @coresight_ops.
+ * @dev:	The device entity associated to this component.
+ * @refcnt:	keep track of what is in use.
+ * @path_link:	link of current component into the path being enabled.
+ * @orphan:	true if the component has connections that haven't been linked.
+ * @enable:	'true' if component is currently part of an active path.
+ * @activated:	'true' only if a _sink_ has been activated.  A sink can be
+		activated but not yet enabled.  Enabling for a _sink_
+		happens when a source has been selected for that it.
+ */
+struct coresight_device {
+	struct coresight_connection *conns;
+	int nr_inport;
+	int nr_outport;
+	enum coresight_dev_type type;
+	struct coresight_dev_subtype subtype;
+	const struct coresight_ops *ops;
+	struct device dev;
+	atomic_t *refcnt;
+	struct list_head path_link;
+	bool orphan;
+	bool enable;	/* true only if configured as part of a path */
+	bool activated;	/* true only if a sink is part of a path */
+};
+
+#define to_coresight_device(d) container_of(d, struct coresight_device, dev)
+
+#define source_ops(csdev)	csdev->ops->source_ops
+#define sink_ops(csdev)		csdev->ops->sink_ops
+#define link_ops(csdev)		csdev->ops->link_ops
+
+#define CORESIGHT_DEBUGFS_ENTRY(__name, __entry_name,			\
+				 __mode, __get, __set, __fmt)		\
+DEFINE_SIMPLE_ATTRIBUTE(__name ## _ops, __get, __set, __fmt);		\
+static const struct coresight_ops_entry __name ## _entry = {		\
+	.name = __entry_name,						\
+	.mode = __mode,							\
+	.ops  = &__name ## _ops						\
+}
+
+/**
+ * struct coresight_ops_sink - basic operations for a sink
+ * Operations available for sinks
+ * @enable:	enables the sink.
+ * @disable:	disables the sink.
+ */
+struct coresight_ops_sink {
+	int (*enable)(struct coresight_device *csdev);
+	void (*disable)(struct coresight_device *csdev);
+};
+
+/**
+ * struct coresight_ops_link - basic operations for a link
+ * Operations available for links.
+ * @enable:	enables flow between iport and oport.
+ * @disable:	disables flow between iport and oport.
+ */
+struct coresight_ops_link {
+	int (*enable)(struct coresight_device *csdev, int iport, int oport);
+	void (*disable)(struct coresight_device *csdev, int iport, int oport);
+};
+
+/**
+ * struct coresight_ops_source - basic operations for a source
+ * Operations available for sources.
+ * @trace_id:	returns the value of the component's trace ID as known
+		to the HW.
+ * @enable:	enables tracing from a source.
+ * @disable:	disables tracing for a source.
+ */
+struct coresight_ops_source {
+	int (*trace_id)(struct coresight_device *csdev);
+	int (*enable)(struct coresight_device *csdev);
+	void (*disable)(struct coresight_device *csdev);
+};
+
+struct coresight_ops {
+	const struct coresight_ops_sink *sink_ops;
+	const struct coresight_ops_link *link_ops;
+	const struct coresight_ops_source *source_ops;
+};
+
+#ifdef CONFIG_CORESIGHT
+extern struct coresight_device *
+coresight_register(struct coresight_desc *desc);
+extern void coresight_unregister(struct coresight_device *csdev);
+extern int coresight_enable(struct coresight_device *csdev);
+extern void coresight_disable(struct coresight_device *csdev);
+extern int coresight_is_bit_set(u32 val, int position, int value);
+extern int coresight_timeout(void __iomem *addr, u32 offset,
+			     int position, int value);
+#ifdef CONFIG_OF
+extern struct coresight_platform_data *of_get_coresight_platform_data(
+				struct device *dev, struct device_node *node);
+#endif
+#else
+static inline struct coresight_device *
+coresight_register(struct coresight_desc *desc) { return NULL; }
+static inline void coresight_unregister(struct coresight_device *csdev) {}
+static inline int
+coresight_enable(struct coresight_device *csdev) { return -ENOSYS; }
+static inline void coresight_disable(struct coresight_device *csdev) {}
+static inline int coresight_is_bit_set(u32 val, int position, int value)
+					 { return 0; }
+static inline int coresight_timeout(void __iomem *addr, u32 offset,
+				     int position, int value) { return 1; }
+#ifdef CONFIG_OF
+static inline struct coresight_platform_data *of_get_coresight_platform_data(
+	struct device *dev, struct device_node *node) { return NULL; }
+#endif
+#endif
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From 332fd7c4fef5f3b166e93decb07fd69eb24f7998 Mon Sep 17 00:00:00 2001
From: Kevin Cernekee <cernekee@gmail.com>
Date: Thu, 6 Nov 2014 22:44:17 -0800
Subject: genirq: Generic chip: Change irq_reg_{readl,writel} arguments

Pass in the irq_chip_generic struct so we can use different readl/writel
settings for each irqchip driver, when appropriate.  Compute
(gc->reg_base + reg_offset) in the helper function because this is pretty
much what all callers want to do anyway.

Compile-tested using the following configurations:

    at91_dt_defconfig (CONFIG_ATMEL_AIC_IRQ=y)
    sama5_defconfig (CONFIG_ATMEL_AIC5_IRQ=y)
    sunxi_defconfig (CONFIG_ARCH_SUNXI=y)

tb10x (ARC) is untested.

Signed-off-by: Kevin Cernekee <cernekee@gmail.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lkml.kernel.org/r/1415342669-30640-3-git-send-email-cernekee@gmail.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
---
 drivers/irqchip/irq-atmel-aic.c  | 40 ++++++++++++-------------
 drivers/irqchip/irq-atmel-aic5.c | 65 +++++++++++++++++++---------------------
 drivers/irqchip/irq-sunxi-nmi.c  |  4 +--
 drivers/irqchip/irq-tb10x.c      |  4 +--
 include/linux/irq.h              | 20 ++++++++-----
 kernel/irq/generic-chip.c        | 20 ++++++-------
 6 files changed, 78 insertions(+), 75 deletions(-)

(limited to 'include')

diff --git a/drivers/irqchip/irq-atmel-aic.c b/drivers/irqchip/irq-atmel-aic.c
index 9a2cf3c1a3a..27fdd8c3e7b 100644
--- a/drivers/irqchip/irq-atmel-aic.c
+++ b/drivers/irqchip/irq-atmel-aic.c
@@ -65,11 +65,11 @@ aic_handle(struct pt_regs *regs)
 	u32 irqnr;
 	u32 irqstat;
 
-	irqnr = irq_reg_readl(gc->reg_base + AT91_AIC_IVR);
-	irqstat = irq_reg_readl(gc->reg_base + AT91_AIC_ISR);
+	irqnr = irq_reg_readl(gc, AT91_AIC_IVR);
+	irqstat = irq_reg_readl(gc, AT91_AIC_ISR);
 
 	if (!irqstat)
-		irq_reg_writel(0, gc->reg_base + AT91_AIC_EOICR);
+		irq_reg_writel(gc, 0, AT91_AIC_EOICR);
 	else
 		handle_domain_irq(aic_domain, irqnr, regs);
 }
@@ -80,7 +80,7 @@ static int aic_retrigger(struct irq_data *d)
 
 	/* Enable interrupt on AIC5 */
 	irq_gc_lock(gc);
-	irq_reg_writel(d->mask, gc->reg_base + AT91_AIC_ISCR);
+	irq_reg_writel(gc, d->mask, AT91_AIC_ISCR);
 	irq_gc_unlock(gc);
 
 	return 0;
@@ -92,12 +92,12 @@ static int aic_set_type(struct irq_data *d, unsigned type)
 	unsigned int smr;
 	int ret;
 
-	smr = irq_reg_readl(gc->reg_base + AT91_AIC_SMR(d->hwirq));
+	smr = irq_reg_readl(gc, AT91_AIC_SMR(d->hwirq));
 	ret = aic_common_set_type(d, type, &smr);
 	if (ret)
 		return ret;
 
-	irq_reg_writel(smr, gc->reg_base + AT91_AIC_SMR(d->hwirq));
+	irq_reg_writel(gc, smr, AT91_AIC_SMR(d->hwirq));
 
 	return 0;
 }
@@ -108,8 +108,8 @@ static void aic_suspend(struct irq_data *d)
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 
 	irq_gc_lock(gc);
-	irq_reg_writel(gc->mask_cache, gc->reg_base + AT91_AIC_IDCR);
-	irq_reg_writel(gc->wake_active, gc->reg_base + AT91_AIC_IECR);
+	irq_reg_writel(gc, gc->mask_cache, AT91_AIC_IDCR);
+	irq_reg_writel(gc, gc->wake_active, AT91_AIC_IECR);
 	irq_gc_unlock(gc);
 }
 
@@ -118,8 +118,8 @@ static void aic_resume(struct irq_data *d)
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 
 	irq_gc_lock(gc);
-	irq_reg_writel(gc->wake_active, gc->reg_base + AT91_AIC_IDCR);
-	irq_reg_writel(gc->mask_cache, gc->reg_base + AT91_AIC_IECR);
+	irq_reg_writel(gc, gc->wake_active, AT91_AIC_IDCR);
+	irq_reg_writel(gc, gc->mask_cache, AT91_AIC_IECR);
 	irq_gc_unlock(gc);
 }
 
@@ -128,8 +128,8 @@ static void aic_pm_shutdown(struct irq_data *d)
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 
 	irq_gc_lock(gc);
-	irq_reg_writel(0xffffffff, gc->reg_base + AT91_AIC_IDCR);
-	irq_reg_writel(0xffffffff, gc->reg_base + AT91_AIC_ICCR);
+	irq_reg_writel(gc, 0xffffffff, AT91_AIC_IDCR);
+	irq_reg_writel(gc, 0xffffffff, AT91_AIC_ICCR);
 	irq_gc_unlock(gc);
 }
 #else
@@ -148,24 +148,24 @@ static void __init aic_hw_init(struct irq_domain *domain)
 	 * will not Lock out nIRQ
 	 */
 	for (i = 0; i < 8; i++)
-		irq_reg_writel(0, gc->reg_base + AT91_AIC_EOICR);
+		irq_reg_writel(gc, 0, AT91_AIC_EOICR);
 
 	/*
 	 * Spurious Interrupt ID in Spurious Vector Register.
 	 * When there is no current interrupt, the IRQ Vector Register
 	 * reads the value stored in AIC_SPU
 	 */
-	irq_reg_writel(0xffffffff, gc->reg_base + AT91_AIC_SPU);
+	irq_reg_writel(gc, 0xffffffff, AT91_AIC_SPU);
 
 	/* No debugging in AIC: Debug (Protect) Control Register */
-	irq_reg_writel(0, gc->reg_base + AT91_AIC_DCR);
+	irq_reg_writel(gc, 0, AT91_AIC_DCR);
 
 	/* Disable and clear all interrupts initially */
-	irq_reg_writel(0xffffffff, gc->reg_base + AT91_AIC_IDCR);
-	irq_reg_writel(0xffffffff, gc->reg_base + AT91_AIC_ICCR);
+	irq_reg_writel(gc, 0xffffffff, AT91_AIC_IDCR);
+	irq_reg_writel(gc, 0xffffffff, AT91_AIC_ICCR);
 
 	for (i = 0; i < 32; i++)
-		irq_reg_writel(i, gc->reg_base + AT91_AIC_SVR(i));
+		irq_reg_writel(gc, i, AT91_AIC_SVR(i));
 }
 
 static int aic_irq_domain_xlate(struct irq_domain *d,
@@ -195,10 +195,10 @@ static int aic_irq_domain_xlate(struct irq_domain *d,
 	gc = dgc->gc[idx];
 
 	irq_gc_lock(gc);
-	smr = irq_reg_readl(gc->reg_base + AT91_AIC_SMR(*out_hwirq));
+	smr = irq_reg_readl(gc, AT91_AIC_SMR(*out_hwirq));
 	ret = aic_common_set_priority(intspec[2], &smr);
 	if (!ret)
-		irq_reg_writel(smr, gc->reg_base + AT91_AIC_SMR(*out_hwirq));
+		irq_reg_writel(gc, smr, AT91_AIC_SMR(*out_hwirq));
 	irq_gc_unlock(gc);
 
 	return ret;
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index a11aae8fb00..a2e8c3f876c 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -75,11 +75,11 @@ aic5_handle(struct pt_regs *regs)
 	u32 irqnr;
 	u32 irqstat;
 
-	irqnr = irq_reg_readl(gc->reg_base + AT91_AIC5_IVR);
-	irqstat = irq_reg_readl(gc->reg_base + AT91_AIC5_ISR);
+	irqnr = irq_reg_readl(gc, AT91_AIC5_IVR);
+	irqstat = irq_reg_readl(gc, AT91_AIC5_ISR);
 
 	if (!irqstat)
-		irq_reg_writel(0, gc->reg_base + AT91_AIC5_EOICR);
+		irq_reg_writel(gc, 0, AT91_AIC5_EOICR);
 	else
 		handle_domain_irq(aic5_domain, irqnr, regs);
 }
@@ -92,8 +92,8 @@ static void aic5_mask(struct irq_data *d)
 
 	/* Disable interrupt on AIC5 */
 	irq_gc_lock(gc);
-	irq_reg_writel(d->hwirq, gc->reg_base + AT91_AIC5_SSR);
-	irq_reg_writel(1, gc->reg_base + AT91_AIC5_IDCR);
+	irq_reg_writel(gc, d->hwirq, AT91_AIC5_SSR);
+	irq_reg_writel(gc, 1, AT91_AIC5_IDCR);
 	gc->mask_cache &= ~d->mask;
 	irq_gc_unlock(gc);
 }
@@ -106,8 +106,8 @@ static void aic5_unmask(struct irq_data *d)
 
 	/* Enable interrupt on AIC5 */
 	irq_gc_lock(gc);
-	irq_reg_writel(d->hwirq, gc->reg_base + AT91_AIC5_SSR);
-	irq_reg_writel(1, gc->reg_base + AT91_AIC5_IECR);
+	irq_reg_writel(gc, d->hwirq, AT91_AIC5_SSR);
+	irq_reg_writel(gc, 1, AT91_AIC5_IECR);
 	gc->mask_cache |= d->mask;
 	irq_gc_unlock(gc);
 }
@@ -120,8 +120,8 @@ static int aic5_retrigger(struct irq_data *d)
 
 	/* Enable interrupt on AIC5 */
 	irq_gc_lock(gc);
-	irq_reg_writel(d->hwirq, gc->reg_base + AT91_AIC5_SSR);
-	irq_reg_writel(1, gc->reg_base + AT91_AIC5_ISCR);
+	irq_reg_writel(gc, d->hwirq, AT91_AIC5_SSR);
+	irq_reg_writel(gc, 1, AT91_AIC5_ISCR);
 	irq_gc_unlock(gc);
 
 	return 0;
@@ -136,11 +136,11 @@ static int aic5_set_type(struct irq_data *d, unsigned type)
 	int ret;
 
 	irq_gc_lock(gc);
-	irq_reg_writel(d->hwirq, gc->reg_base + AT91_AIC5_SSR);
-	smr = irq_reg_readl(gc->reg_base + AT91_AIC5_SMR);
+	irq_reg_writel(gc, d->hwirq, AT91_AIC5_SSR);
+	smr = irq_reg_readl(gc, AT91_AIC5_SMR);
 	ret = aic_common_set_type(d, type, &smr);
 	if (!ret)
-		irq_reg_writel(smr, gc->reg_base + AT91_AIC5_SMR);
+		irq_reg_writel(gc, smr, AT91_AIC5_SMR);
 	irq_gc_unlock(gc);
 
 	return ret;
@@ -162,12 +162,11 @@ static void aic5_suspend(struct irq_data *d)
 		if ((mask & gc->mask_cache) == (mask & gc->wake_active))
 			continue;
 
-		irq_reg_writel(i + gc->irq_base,
-			       bgc->reg_base + AT91_AIC5_SSR);
+		irq_reg_writel(bgc, i + gc->irq_base, AT91_AIC5_SSR);
 		if (mask & gc->wake_active)
-			irq_reg_writel(1, bgc->reg_base + AT91_AIC5_IECR);
+			irq_reg_writel(bgc, 1, AT91_AIC5_IECR);
 		else
-			irq_reg_writel(1, bgc->reg_base + AT91_AIC5_IDCR);
+			irq_reg_writel(bgc, 1, AT91_AIC5_IDCR);
 	}
 	irq_gc_unlock(bgc);
 }
@@ -187,12 +186,11 @@ static void aic5_resume(struct irq_data *d)
 		if ((mask & gc->mask_cache) == (mask & gc->wake_active))
 			continue;
 
-		irq_reg_writel(i + gc->irq_base,
-			       bgc->reg_base + AT91_AIC5_SSR);
+		irq_reg_writel(bgc, i + gc->irq_base, AT91_AIC5_SSR);
 		if (mask & gc->mask_cache)
-			irq_reg_writel(1, bgc->reg_base + AT91_AIC5_IECR);
+			irq_reg_writel(bgc, 1, AT91_AIC5_IECR);
 		else
-			irq_reg_writel(1, bgc->reg_base + AT91_AIC5_IDCR);
+			irq_reg_writel(bgc, 1, AT91_AIC5_IDCR);
 	}
 	irq_gc_unlock(bgc);
 }
@@ -207,10 +205,9 @@ static void aic5_pm_shutdown(struct irq_data *d)
 
 	irq_gc_lock(bgc);
 	for (i = 0; i < dgc->irqs_per_chip; i++) {
-		irq_reg_writel(i + gc->irq_base,
-			       bgc->reg_base + AT91_AIC5_SSR);
-		irq_reg_writel(1, bgc->reg_base + AT91_AIC5_IDCR);
-		irq_reg_writel(1, bgc->reg_base + AT91_AIC5_ICCR);
+		irq_reg_writel(bgc, i + gc->irq_base, AT91_AIC5_SSR);
+		irq_reg_writel(bgc, 1, AT91_AIC5_IDCR);
+		irq_reg_writel(bgc, 1, AT91_AIC5_ICCR);
 	}
 	irq_gc_unlock(bgc);
 }
@@ -230,24 +227,24 @@ static void __init aic5_hw_init(struct irq_domain *domain)
 	 * will not Lock out nIRQ
 	 */
 	for (i = 0; i < 8; i++)
-		irq_reg_writel(0, gc->reg_base + AT91_AIC5_EOICR);
+		irq_reg_writel(gc, 0, AT91_AIC5_EOICR);
 
 	/*
 	 * Spurious Interrupt ID in Spurious Vector Register.
 	 * When there is no current interrupt, the IRQ Vector Register
 	 * reads the value stored in AIC_SPU
 	 */
-	irq_reg_writel(0xffffffff, gc->reg_base + AT91_AIC5_SPU);
+	irq_reg_writel(gc, 0xffffffff, AT91_AIC5_SPU);
 
 	/* No debugging in AIC: Debug (Protect) Control Register */
-	irq_reg_writel(0, gc->reg_base + AT91_AIC5_DCR);
+	irq_reg_writel(gc, 0, AT91_AIC5_DCR);
 
 	/* Disable and clear all interrupts initially */
 	for (i = 0; i < domain->revmap_size; i++) {
-		irq_reg_writel(i, gc->reg_base + AT91_AIC5_SSR);
-		irq_reg_writel(i, gc->reg_base + AT91_AIC5_SVR);
-		irq_reg_writel(1, gc->reg_base + AT91_AIC5_IDCR);
-		irq_reg_writel(1, gc->reg_base + AT91_AIC5_ICCR);
+		irq_reg_writel(gc, i, AT91_AIC5_SSR);
+		irq_reg_writel(gc, i, AT91_AIC5_SVR);
+		irq_reg_writel(gc, 1, AT91_AIC5_IDCR);
+		irq_reg_writel(gc, 1, AT91_AIC5_ICCR);
 	}
 }
 
@@ -273,11 +270,11 @@ static int aic5_irq_domain_xlate(struct irq_domain *d,
 	gc = dgc->gc[0];
 
 	irq_gc_lock(gc);
-	irq_reg_writel(*out_hwirq, gc->reg_base + AT91_AIC5_SSR);
-	smr = irq_reg_readl(gc->reg_base + AT91_AIC5_SMR);
+	irq_reg_writel(gc, *out_hwirq, AT91_AIC5_SSR);
+	smr = irq_reg_readl(gc, AT91_AIC5_SMR);
 	ret = aic_common_set_priority(intspec[2], &smr);
 	if (!ret)
-		irq_reg_writel(intspec[2] | smr, gc->reg_base + AT91_AIC5_SMR);
+		irq_reg_writel(gc, intspec[2] | smr, AT91_AIC5_SMR);
 	irq_gc_unlock(gc);
 
 	return ret;
diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c
index 12f547a44ae..4a9ce5b50c5 100644
--- a/drivers/irqchip/irq-sunxi-nmi.c
+++ b/drivers/irqchip/irq-sunxi-nmi.c
@@ -50,12 +50,12 @@ static struct sunxi_sc_nmi_reg_offs sun6i_reg_offs = {
 static inline void sunxi_sc_nmi_write(struct irq_chip_generic *gc, u32 off,
 				      u32 val)
 {
-	irq_reg_writel(val, gc->reg_base + off);
+	irq_reg_writel(gc, val, off);
 }
 
 static inline u32 sunxi_sc_nmi_read(struct irq_chip_generic *gc, u32 off)
 {
-	return irq_reg_readl(gc->reg_base + off);
+	return irq_reg_readl(gc, off);
 }
 
 static void sunxi_sc_nmi_handle_irq(unsigned int irq, struct irq_desc *desc)
diff --git a/drivers/irqchip/irq-tb10x.c b/drivers/irqchip/irq-tb10x.c
index 7c44c99bf1f..accc20036a3 100644
--- a/drivers/irqchip/irq-tb10x.c
+++ b/drivers/irqchip/irq-tb10x.c
@@ -43,12 +43,12 @@
 static inline void ab_irqctl_writereg(struct irq_chip_generic *gc, u32 reg,
 	u32 val)
 {
-	irq_reg_writel(val, gc->reg_base + reg);
+	irq_reg_writel(gc, val, reg);
 }
 
 static inline u32 ab_irqctl_readreg(struct irq_chip_generic *gc, u32 reg)
 {
-	return irq_reg_readl(gc->reg_base + reg);
+	return irq_reg_readl(gc, reg);
 }
 
 static int tb10x_irq_set_type(struct irq_data *data, unsigned int flow_type)
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 03f48d936f6..ed1135d32d8 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -20,6 +20,7 @@
 #include <linux/errno.h>
 #include <linux/topology.h>
 #include <linux/wait.h>
+#include <linux/io.h>
 
 #include <asm/irq.h>
 #include <asm/ptrace.h>
@@ -639,13 +640,6 @@ void arch_teardown_hwirq(unsigned int irq);
 void irq_init_desc(unsigned int irq);
 #endif
 
-#ifndef irq_reg_writel
-# define irq_reg_writel(val, addr)	writel(val, addr)
-#endif
-#ifndef irq_reg_readl
-# define irq_reg_readl(addr)		readl(addr)
-#endif
-
 /**
  * struct irq_chip_regs - register offsets for struct irq_gci
  * @enable:	Enable register offset to reg_base
@@ -821,4 +815,16 @@ static inline void irq_gc_lock(struct irq_chip_generic *gc) { }
 static inline void irq_gc_unlock(struct irq_chip_generic *gc) { }
 #endif
 
+static inline void irq_reg_writel(struct irq_chip_generic *gc,
+				  u32 val, int reg_offset)
+{
+	writel(val, gc->reg_base + reg_offset);
+}
+
+static inline u32 irq_reg_readl(struct irq_chip_generic *gc,
+				int reg_offset)
+{
+	return readl(gc->reg_base + reg_offset);
+}
+
 #endif /* _LINUX_IRQ_H */
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index cf80e7b0dda..db458c68e39 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -39,7 +39,7 @@ void irq_gc_mask_disable_reg(struct irq_data *d)
 	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
-	irq_reg_writel(mask, gc->reg_base + ct->regs.disable);
+	irq_reg_writel(gc, mask, ct->regs.disable);
 	*ct->mask_cache &= ~mask;
 	irq_gc_unlock(gc);
 }
@@ -59,7 +59,7 @@ void irq_gc_mask_set_bit(struct irq_data *d)
 
 	irq_gc_lock(gc);
 	*ct->mask_cache |= mask;
-	irq_reg_writel(*ct->mask_cache, gc->reg_base + ct->regs.mask);
+	irq_reg_writel(gc, *ct->mask_cache, ct->regs.mask);
 	irq_gc_unlock(gc);
 }
 EXPORT_SYMBOL_GPL(irq_gc_mask_set_bit);
@@ -79,7 +79,7 @@ void irq_gc_mask_clr_bit(struct irq_data *d)
 
 	irq_gc_lock(gc);
 	*ct->mask_cache &= ~mask;
-	irq_reg_writel(*ct->mask_cache, gc->reg_base + ct->regs.mask);
+	irq_reg_writel(gc, *ct->mask_cache, ct->regs.mask);
 	irq_gc_unlock(gc);
 }
 EXPORT_SYMBOL_GPL(irq_gc_mask_clr_bit);
@@ -98,7 +98,7 @@ void irq_gc_unmask_enable_reg(struct irq_data *d)
 	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
-	irq_reg_writel(mask, gc->reg_base + ct->regs.enable);
+	irq_reg_writel(gc, mask, ct->regs.enable);
 	*ct->mask_cache |= mask;
 	irq_gc_unlock(gc);
 }
@@ -114,7 +114,7 @@ void irq_gc_ack_set_bit(struct irq_data *d)
 	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
-	irq_reg_writel(mask, gc->reg_base + ct->regs.ack);
+	irq_reg_writel(gc, mask, ct->regs.ack);
 	irq_gc_unlock(gc);
 }
 EXPORT_SYMBOL_GPL(irq_gc_ack_set_bit);
@@ -130,7 +130,7 @@ void irq_gc_ack_clr_bit(struct irq_data *d)
 	u32 mask = ~d->mask;
 
 	irq_gc_lock(gc);
-	irq_reg_writel(mask, gc->reg_base + ct->regs.ack);
+	irq_reg_writel(gc, mask, ct->regs.ack);
 	irq_gc_unlock(gc);
 }
 
@@ -145,8 +145,8 @@ void irq_gc_mask_disable_reg_and_ack(struct irq_data *d)
 	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
-	irq_reg_writel(mask, gc->reg_base + ct->regs.mask);
-	irq_reg_writel(mask, gc->reg_base + ct->regs.ack);
+	irq_reg_writel(gc, mask, ct->regs.mask);
+	irq_reg_writel(gc, mask, ct->regs.ack);
 	irq_gc_unlock(gc);
 }
 
@@ -161,7 +161,7 @@ void irq_gc_eoi(struct irq_data *d)
 	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
-	irq_reg_writel(mask, gc->reg_base + ct->regs.eoi);
+	irq_reg_writel(gc, mask, ct->regs.eoi);
 	irq_gc_unlock(gc);
 }
 
@@ -245,7 +245,7 @@ irq_gc_init_mask_cache(struct irq_chip_generic *gc, enum irq_gc_flags flags)
 		}
 		ct[i].mask_cache = mskptr;
 		if (flags & IRQ_GC_INIT_MASK_CACHE)
-			*mskptr = irq_reg_readl(gc->reg_base + mskreg);
+			*mskptr = irq_reg_readl(gc, mskreg);
 	}
 }
 
-- 
cgit v1.2.3-70-g09d2


From 2b28037632b1e62b92c0616f08652d806008c80d Mon Sep 17 00:00:00 2001
From: Kevin Cernekee <cernekee@gmail.com>
Date: Thu, 6 Nov 2014 22:44:18 -0800
Subject: genirq: Generic chip: Allow irqchip drivers to override
 irq_reg_{readl,writel}

Currently, these I/O accessors always assume little endian 32-bit
registers (readl/writel).  On some systems the IRQ registers need to be
accessed in BE mode or using 16-bit loads/stores, so we will provide a
way to override the default behavior.

Signed-off-by: Kevin Cernekee <cernekee@gmail.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lkml.kernel.org/r/1415342669-30640-4-git-send-email-cernekee@gmail.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
---
 include/linux/irq.h | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index ed1135d32d8..0fecd95ba27 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -686,6 +686,8 @@ struct irq_chip_type {
  * struct irq_chip_generic - Generic irq chip data structure
  * @lock:		Lock to protect register and cache data access
  * @reg_base:		Register base address (virtual)
+ * @reg_readl:		Alternate I/O accessor (defaults to readl if NULL)
+ * @reg_writel:		Alternate I/O accessor (defaults to writel if NULL)
  * @irq_base:		Interrupt base nr for this chip
  * @irq_cnt:		Number of interrupts handled by this chip
  * @mask_cache:		Cached mask register shared between all chip types
@@ -710,6 +712,8 @@ struct irq_chip_type {
 struct irq_chip_generic {
 	raw_spinlock_t		lock;
 	void __iomem		*reg_base;
+	u32			(*reg_readl)(void __iomem *addr);
+	void			(*reg_writel)(u32 val, void __iomem *addr);
 	unsigned int		irq_base;
 	unsigned int		irq_cnt;
 	u32			mask_cache;
@@ -818,13 +822,19 @@ static inline void irq_gc_unlock(struct irq_chip_generic *gc) { }
 static inline void irq_reg_writel(struct irq_chip_generic *gc,
 				  u32 val, int reg_offset)
 {
-	writel(val, gc->reg_base + reg_offset);
+	if (gc->reg_writel)
+		gc->reg_writel(val, gc->reg_base + reg_offset);
+	else
+		writel(val, gc->reg_base + reg_offset);
 }
 
 static inline u32 irq_reg_readl(struct irq_chip_generic *gc,
 				int reg_offset)
 {
-	return readl(gc->reg_base + reg_offset);
+	if (gc->reg_readl)
+		return gc->reg_readl(gc->reg_base + reg_offset);
+	else
+		return readl(gc->reg_base + reg_offset);
 }
 
 #endif /* _LINUX_IRQ_H */
-- 
cgit v1.2.3-70-g09d2


From b79055952badbd73710685643bab44104f2509ea Mon Sep 17 00:00:00 2001
From: Kevin Cernekee <cernekee@gmail.com>
Date: Thu, 6 Nov 2014 22:44:19 -0800
Subject: genirq: Generic chip: Add big endian I/O accessors

Use io{read,write}32be if the caller specified IRQ_GC_BE_IO when creating
the irqchip.

Signed-off-by: Kevin Cernekee <cernekee@gmail.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lkml.kernel.org/r/1415342669-30640-5-git-send-email-cernekee@gmail.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
---
 include/linux/irq.h       |  2 ++
 kernel/irq/generic-chip.c | 16 ++++++++++++++++
 2 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 0fecd95ba27..8588e5efe57 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -738,12 +738,14 @@ struct irq_chip_generic {
  *				the parent irq. Usually GPIO implementations
  * @IRQ_GC_MASK_CACHE_PER_TYPE:	Mask cache is chip type private
  * @IRQ_GC_NO_MASK:		Do not calculate irq_data->mask
+ * @IRQ_GC_BE_IO:		Use big-endian register accesses (default: LE)
  */
 enum irq_gc_flags {
 	IRQ_GC_INIT_MASK_CACHE		= 1 << 0,
 	IRQ_GC_INIT_NESTED_LOCK		= 1 << 1,
 	IRQ_GC_MASK_CACHE_PER_TYPE	= 1 << 2,
 	IRQ_GC_NO_MASK			= 1 << 3,
+	IRQ_GC_BE_IO			= 1 << 4,
 };
 
 /*
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index db458c68e39..61024e8abde 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -191,6 +191,16 @@ int irq_gc_set_wake(struct irq_data *d, unsigned int on)
 	return 0;
 }
 
+static u32 irq_readl_be(void __iomem *addr)
+{
+	return ioread32be(addr);
+}
+
+static void irq_writel_be(u32 val, void __iomem *addr)
+{
+	iowrite32be(val, addr);
+}
+
 static void
 irq_init_generic_chip(struct irq_chip_generic *gc, const char *name,
 		      int num_ct, unsigned int irq_base,
@@ -300,7 +310,13 @@ int irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip,
 		dgc->gc[i] = gc = tmp;
 		irq_init_generic_chip(gc, name, num_ct, i * irqs_per_chip,
 				      NULL, handler);
+
 		gc->domain = d;
+		if (gcflags & IRQ_GC_BE_IO) {
+			gc->reg_readl = &irq_readl_be;
+			gc->reg_writel = &irq_writel_be;
+		}
+
 		raw_spin_lock_irqsave(&gc_lock, flags);
 		list_add_tail(&gc->list, &gc_list);
 		raw_spin_unlock_irqrestore(&gc_lock, flags);
-- 
cgit v1.2.3-70-g09d2


From 427d204c86e095bb91eb8af381bd90a48376a860 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sat, 8 Nov 2014 16:38:07 +0100
Subject: ASoC: Remove snd_soc_cache_sync() implementation

This function has no more non regmap user, which means we can remove the
implementation of the function and associated functions and structure
fields.

For convenience we keep a static inline version of the function that
forwards calls to regcache_sync() unconditionally.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h         |  19 ++++--
 include/trace/events/asoc.h |  25 --------
 sound/soc/soc-cache.c       | 152 --------------------------------------------
 sound/soc/soc-core.c        |   4 --
 4 files changed, 12 insertions(+), 188 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 7ba7130037a..fadcb351f3e 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -409,13 +409,9 @@ int devm_snd_soc_register_component(struct device *dev,
 			 const struct snd_soc_component_driver *cmpnt_drv,
 			 struct snd_soc_dai_driver *dai_drv, int num_dai);
 void snd_soc_unregister_component(struct device *dev);
-int snd_soc_cache_sync(struct snd_soc_codec *codec);
 int snd_soc_cache_init(struct snd_soc_codec *codec);
 int snd_soc_cache_exit(struct snd_soc_codec *codec);
-int snd_soc_cache_write(struct snd_soc_codec *codec,
-			unsigned int reg, unsigned int value);
-int snd_soc_cache_read(struct snd_soc_codec *codec,
-		       unsigned int reg, unsigned int *value);
+
 int snd_soc_platform_read(struct snd_soc_platform *platform,
 					unsigned int reg);
 int snd_soc_platform_write(struct snd_soc_platform *platform,
@@ -791,13 +787,11 @@ struct snd_soc_codec {
 	unsigned int ac97_registered:1; /* Codec has been AC97 registered */
 	unsigned int ac97_created:1; /* Codec has been created by SoC */
 	unsigned int cache_init:1; /* codec cache has been initialized */
-	u32 cache_sync; /* Cache needs to be synced to hardware */
 
 	/* codec IO */
 	void *control_data; /* codec control (i2c/3wire) data */
 	hw_write_t hw_write;
 	void *reg_cache;
-	struct mutex cache_rw_mutex;
 
 	/* component */
 	struct snd_soc_component component;
@@ -1264,6 +1258,17 @@ unsigned int snd_soc_read(struct snd_soc_codec *codec, unsigned int reg);
 int snd_soc_write(struct snd_soc_codec *codec, unsigned int reg,
 	unsigned int val);
 
+/**
+ * snd_soc_cache_sync() - Sync the register cache with the hardware
+ * @codec: CODEC to sync
+ *
+ * Note: This function will call regcache_sync()
+ */
+static inline int snd_soc_cache_sync(struct snd_soc_codec *codec)
+{
+	return regcache_sync(codec->component.regmap);
+}
+
 /* component IO */
 int snd_soc_component_read(struct snd_soc_component *component,
 	unsigned int reg, unsigned int *val);
diff --git a/include/trace/events/asoc.h b/include/trace/events/asoc.h
index b04ee7e5a46..88cf39d96d0 100644
--- a/include/trace/events/asoc.h
+++ b/include/trace/events/asoc.h
@@ -288,31 +288,6 @@ TRACE_EVENT(snd_soc_jack_notify,
 	TP_printk("jack=%s %x", __get_str(name), (int)__entry->val)
 );
 
-TRACE_EVENT(snd_soc_cache_sync,
-
-	TP_PROTO(struct snd_soc_codec *codec, const char *type,
-		 const char *status),
-
-	TP_ARGS(codec, type, status),
-
-	TP_STRUCT__entry(
-		__string(	name,		codec->component.name)
-		__string(	status,		status		)
-		__string(	type,		type		)
-		__field(	int,		id		)
-	),
-
-	TP_fast_assign(
-		__assign_str(name, codec->component.name);
-		__assign_str(status, status);
-		__assign_str(type, type);
-		__entry->id = codec->component.id;
-	),
-
-	TP_printk("codec=%s.%d type=%s status=%s", __get_str(name),
-		  (int)__entry->id, __get_str(type), __get_str(status))
-);
-
 #endif /* _TRACE_ASOC_H */
 
 /* This part must be outside protection */
diff --git a/sound/soc/soc-cache.c b/sound/soc/soc-cache.c
index 6dab81799b9..07f43356f96 100644
--- a/sound/soc/soc-cache.c
+++ b/sound/soc/soc-cache.c
@@ -15,56 +15,6 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 
-#include <trace/events/asoc.h>
-
-static bool snd_soc_set_cache_val(void *base, unsigned int idx,
-				  unsigned int val, unsigned int word_size)
-{
-	switch (word_size) {
-	case 1: {
-		u8 *cache = base;
-		if (cache[idx] == val)
-			return true;
-		cache[idx] = val;
-		break;
-	}
-	case 2: {
-		u16 *cache = base;
-		if (cache[idx] == val)
-			return true;
-		cache[idx] = val;
-		break;
-	}
-	default:
-		WARN(1, "Invalid word_size %d\n", word_size);
-		break;
-	}
-	return false;
-}
-
-static unsigned int snd_soc_get_cache_val(const void *base, unsigned int idx,
-		unsigned int word_size)
-{
-	if (!base)
-		return -1;
-
-	switch (word_size) {
-	case 1: {
-		const u8 *cache = base;
-		return cache[idx];
-	}
-	case 2: {
-		const u16 *cache = base;
-		return cache[idx];
-	}
-	default:
-		WARN(1, "Invalid word_size %d\n", word_size);
-		break;
-	}
-	/* unreachable */
-	return -1;
-}
-
 int snd_soc_cache_init(struct snd_soc_codec *codec)
 {
 	const struct snd_soc_codec_driver *codec_drv = codec->driver;
@@ -75,8 +25,6 @@ int snd_soc_cache_init(struct snd_soc_codec *codec)
 	if (!reg_size)
 		return 0;
 
-	mutex_init(&codec->cache_rw_mutex);
-
 	dev_dbg(codec->dev, "ASoC: Initializing cache for %s codec\n",
 				codec->component.name);
 
@@ -103,103 +51,3 @@ int snd_soc_cache_exit(struct snd_soc_codec *codec)
 	codec->reg_cache = NULL;
 	return 0;
 }
-
-/**
- * snd_soc_cache_read: Fetch the value of a given register from the cache.
- *
- * @codec: CODEC to configure.
- * @reg: The register index.
- * @value: The value to be returned.
- */
-int snd_soc_cache_read(struct snd_soc_codec *codec,
-		       unsigned int reg, unsigned int *value)
-{
-	if (!value)
-		return -EINVAL;
-
-	mutex_lock(&codec->cache_rw_mutex);
-	if (!ZERO_OR_NULL_PTR(codec->reg_cache))
-		*value = snd_soc_get_cache_val(codec->reg_cache, reg,
-					       codec->driver->reg_word_size);
-	mutex_unlock(&codec->cache_rw_mutex);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_soc_cache_read);
-
-/**
- * snd_soc_cache_write: Set the value of a given register in the cache.
- *
- * @codec: CODEC to configure.
- * @reg: The register index.
- * @value: The new register value.
- */
-int snd_soc_cache_write(struct snd_soc_codec *codec,
-			unsigned int reg, unsigned int value)
-{
-	mutex_lock(&codec->cache_rw_mutex);
-	if (!ZERO_OR_NULL_PTR(codec->reg_cache))
-		snd_soc_set_cache_val(codec->reg_cache, reg, value,
-				      codec->driver->reg_word_size);
-	mutex_unlock(&codec->cache_rw_mutex);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_soc_cache_write);
-
-static int snd_soc_flat_cache_sync(struct snd_soc_codec *codec)
-{
-	int i;
-	int ret;
-	const struct snd_soc_codec_driver *codec_drv;
-	unsigned int val;
-
-	codec_drv = codec->driver;
-	for (i = 0; i < codec_drv->reg_cache_size; ++i) {
-		ret = snd_soc_cache_read(codec, i, &val);
-		if (ret)
-			return ret;
-		if (codec_drv->reg_cache_default)
-			if (snd_soc_get_cache_val(codec_drv->reg_cache_default,
-						  i, codec_drv->reg_word_size) == val)
-				continue;
-
-		ret = snd_soc_write(codec, i, val);
-		if (ret)
-			return ret;
-		dev_dbg(codec->dev, "ASoC: Synced register %#x, value = %#x\n",
-			i, val);
-	}
-	return 0;
-}
-
-/**
- * snd_soc_cache_sync: Sync the register cache with the hardware.
- *
- * @codec: CODEC to configure.
- *
- * Any registers that should not be synced should be marked as
- * volatile.  In general drivers can choose not to use the provided
- * syncing functionality if they so require.
- */
-int snd_soc_cache_sync(struct snd_soc_codec *codec)
-{
-	const char *name = "flat";
-	int ret;
-
-	if (codec->component.regmap)
-		return regcache_sync(codec->component.regmap);
-
-	if (!codec->cache_sync)
-		return 0;
-
-	dev_dbg(codec->dev, "ASoC: Syncing cache for %s codec\n",
-		codec->component.name);
-	trace_snd_soc_cache_sync(codec, name, "start");
-	ret = snd_soc_flat_cache_sync(codec);
-	if (!ret)
-		codec->cache_sync = 0;
-	trace_snd_soc_cache_sync(codec, name, "end");
-	return ret;
-}
-EXPORT_SYMBOL_GPL(snd_soc_cache_sync);
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 4c8f8a23a0e..4e0e32bb991 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -309,9 +309,6 @@ static void soc_init_codec_debugfs(struct snd_soc_component *component)
 {
 	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
 
-	debugfs_create_bool("cache_sync", 0444, codec->component.debugfs_root,
-			    &codec->cache_sync);
-
 	codec->debugfs_reg = debugfs_create_file("codec_reg", 0644,
 						 codec->component.debugfs_root,
 						 codec, &codec_reg_fops);
@@ -656,7 +653,6 @@ int snd_soc_suspend(struct device *dev)
 				if (codec->driver->suspend)
 					codec->driver->suspend(codec);
 				codec->suspended = 1;
-				codec->cache_sync = 1;
 				if (codec->component.regmap)
 					regcache_mark_dirty(codec->component.regmap);
 				/* deactivate pins to sleep state */
-- 
cgit v1.2.3-70-g09d2


From ce674173e9f4ef7fd0dc04ea0773cdedfbf8e366 Mon Sep 17 00:00:00 2001
From: Ana Rey <anarey@gmail.com>
Date: Mon, 3 Nov 2014 18:10:50 +0100
Subject: netfilter: nft_meta: add cgroup support

This allows you to filter traffic by process control group (cgroup).

Signed-off-by: Ana Rey <anarey@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h | 2 ++
 net/netfilter/nft_meta.c                 | 7 +++++++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 16f62a5cf04..832bc46db78 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -579,6 +579,7 @@ enum nft_exthdr_attributes {
  * @NFT_META_CPU: cpu id through smp_processor_id()
  * @NFT_META_IIFGROUP: packet input interface group
  * @NFT_META_OIFGROUP: packet output interface group
+ * @NFT_META_CGROUP: socket control group (skb->sk->sk_classid)
  */
 enum nft_meta_keys {
 	NFT_META_LEN,
@@ -604,6 +605,7 @@ enum nft_meta_keys {
 	NFT_META_CPU,
 	NFT_META_IIFGROUP,
 	NFT_META_OIFGROUP,
+	NFT_META_CGROUP,
 };
 
 /**
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 1e7c076ca63..e99911eda91 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -165,6 +165,12 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 			goto err;
 		dest->data[0] = out->group;
 		break;
+	case NFT_META_CGROUP:
+		if (skb->sk == NULL)
+			break;
+
+		dest->data[0] = skb->sk->sk_classid;
+		break;
 	default:
 		WARN_ON(1);
 		goto err;
@@ -240,6 +246,7 @@ int nft_meta_get_init(const struct nft_ctx *ctx,
 	case NFT_META_CPU:
 	case NFT_META_IIFGROUP:
 	case NFT_META_OIFGROUP:
+	case NFT_META_CGROUP:
 		break;
 	default:
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3-70-g09d2


From 1fb8510cdb5b7befe8a59f533c7fc12ef0dac73e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 7 Nov 2014 17:08:28 +0100
Subject: ALSA: pcm: Add snd_pcm_stop_xrun() helper

Add a new helper function snd_pcm_stop_xrun() to the standard sequnce
lock/snd_pcm_stop(XRUN)/unlock by a single call, and replace the
existing open codes with this helper.

The function checks the PCM running state to prevent setting the wrong
state, too, for more safety.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 drivers/media/pci/saa7134/saa7134-alsa.c |  4 +---
 include/sound/pcm.h                      |  1 +
 sound/arm/pxa2xx-pcm-lib.c               |  4 +---
 sound/core/pcm_native.c                  | 23 +++++++++++++++++++++++
 sound/firewire/amdtp.c                   |  8 ++------
 sound/firewire/isight.c                  | 10 ++--------
 sound/pci/asihpi/asihpi.c                |  5 +----
 sound/pci/atiixp.c                       |  4 +---
 sound/pci/atiixp_modem.c                 |  4 +---
 sound/soc/atmel/atmel-pcm-dma.c          |  4 +---
 sound/soc/fsl/fsl_dma.c                  |  9 +--------
 sound/usb/6fire/pcm.c                    | 17 ++++-------------
 sound/usb/endpoint.c                     |  4 +---
 sound/usb/misc/ua101.c                   | 18 ++++--------------
 sound/usb/usx2y/usbusx2yaudio.c          |  9 ++-------
 15 files changed, 46 insertions(+), 78 deletions(-)

(limited to 'include')

diff --git a/drivers/media/pci/saa7134/saa7134-alsa.c b/drivers/media/pci/saa7134/saa7134-alsa.c
index 40569894c1c..ac3cd74e824 100644
--- a/drivers/media/pci/saa7134/saa7134-alsa.c
+++ b/drivers/media/pci/saa7134/saa7134-alsa.c
@@ -173,9 +173,7 @@ static void saa7134_irq_alsa_done(struct saa7134_dev *dev,
 		dprintk("irq: overrun [full=%d/%d] - Blocks in %d\n",dev->dmasound.read_count,
 			dev->dmasound.bufsize, dev->dmasound.blocks);
 		spin_unlock(&dev->slock);
-		snd_pcm_stream_lock(dev->dmasound.substream);
-		snd_pcm_stop(dev->dmasound.substream,SNDRV_PCM_STATE_XRUN);
-		snd_pcm_stream_unlock(dev->dmasound.substream);
+		snd_pcm_stop_xrun(dev->dmasound.substream);
 		return;
 	}
 
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 0b8daeed0a3..40289ec2451 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -506,6 +506,7 @@ int snd_pcm_status(struct snd_pcm_substream *substream,
 int snd_pcm_start(struct snd_pcm_substream *substream);
 int snd_pcm_stop(struct snd_pcm_substream *substream, snd_pcm_state_t status);
 int snd_pcm_drain_done(struct snd_pcm_substream *substream);
+int snd_pcm_stop_xrun(struct snd_pcm_substream *substream);
 #ifdef CONFIG_PM
 int snd_pcm_suspend(struct snd_pcm_substream *substream);
 int snd_pcm_suspend_all(struct snd_pcm *pcm);
diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c
index a61d7a9a995..01f8fdc42b1 100644
--- a/sound/arm/pxa2xx-pcm-lib.c
+++ b/sound/arm/pxa2xx-pcm-lib.c
@@ -200,9 +200,7 @@ void pxa2xx_pcm_dma_irq(int dma_ch, void *dev_id)
 	} else {
 		printk(KERN_ERR "DMA error on channel %d (DCSR=%#x)\n",
 			dma_ch, dcsr);
-		snd_pcm_stream_lock(substream);
-		snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
-		snd_pcm_stream_unlock(substream);
+		snd_pcm_stop_xrun(substream);
 	}
 }
 EXPORT_SYMBOL(pxa2xx_pcm_dma_irq);
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index dfb5031969f..a3d12210970 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -1098,6 +1098,29 @@ int snd_pcm_drain_done(struct snd_pcm_substream *substream)
 				     SNDRV_PCM_STATE_SETUP);
 }
 
+/**
+ * snd_pcm_stop_xrun - stop the running streams as XRUN
+ * @substream: the PCM substream instance
+ * @state: PCM state after stopping the stream
+ *
+ * This stops the given running substream (and all linked substreams) as XRUN.
+ * Unlike snd_pcm_stop(), this function takes the substream lock by itself.
+ *
+ * Return: Zero if successful, or a negative error code.
+ */
+int snd_pcm_stop_xrun(struct snd_pcm_substream *substream)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	snd_pcm_stream_lock_irqsave(substream, flags);
+	if (snd_pcm_running(substream))
+		ret = snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
+	snd_pcm_stream_unlock_irqrestore(substream, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(snd_pcm_stop_xrun);
+
 /*
  * pause callbacks
  */
diff --git a/sound/firewire/amdtp.c b/sound/firewire/amdtp.c
index 95fc2eaf11d..3badc70124a 100644
--- a/sound/firewire/amdtp.c
+++ b/sound/firewire/amdtp.c
@@ -1006,11 +1006,7 @@ void amdtp_stream_pcm_abort(struct amdtp_stream *s)
 	struct snd_pcm_substream *pcm;
 
 	pcm = ACCESS_ONCE(s->pcm);
-	if (pcm) {
-		snd_pcm_stream_lock_irq(pcm);
-		if (snd_pcm_running(pcm))
-			snd_pcm_stop(pcm, SNDRV_PCM_STATE_XRUN);
-		snd_pcm_stream_unlock_irq(pcm);
-	}
+	if (pcm)
+		snd_pcm_stop_xrun(pcm);
 }
 EXPORT_SYMBOL(amdtp_stream_pcm_abort);
diff --git a/sound/firewire/isight.c b/sound/firewire/isight.c
index 7ac94439e75..48d6dca471c 100644
--- a/sound/firewire/isight.c
+++ b/sound/firewire/isight.c
@@ -131,14 +131,8 @@ static void isight_samples(struct isight *isight,
 
 static void isight_pcm_abort(struct isight *isight)
 {
-	unsigned long flags;
-
-	if (ACCESS_ONCE(isight->pcm_active)) {
-		snd_pcm_stream_lock_irqsave(isight->pcm, flags);
-		if (snd_pcm_running(isight->pcm))
-			snd_pcm_stop(isight->pcm, SNDRV_PCM_STATE_XRUN);
-		snd_pcm_stream_unlock_irqrestore(isight->pcm, flags);
-	}
+	if (ACCESS_ONCE(isight->pcm_active))
+		snd_pcm_stop_xrun(isight->pcm);
 }
 
 static void isight_dropped_samples(struct isight *isight, unsigned int total)
diff --git a/sound/pci/asihpi/asihpi.c b/sound/pci/asihpi/asihpi.c
index ac66b3228a3..ff9f9f1c039 100644
--- a/sound/pci/asihpi/asihpi.c
+++ b/sound/pci/asihpi/asihpi.c
@@ -769,10 +769,7 @@ static void snd_card_asihpi_timer_function(unsigned long data)
 						s->number);
 				ds->drained_count++;
 				if (ds->drained_count > 20) {
-					unsigned long flags;
-					snd_pcm_stream_lock_irqsave(s, flags);
-					snd_pcm_stop(s, SNDRV_PCM_STATE_XRUN);
-					snd_pcm_stream_unlock_irqrestore(s, flags);
+					snd_pcm_stop_xrun(s);
 					continue;
 				}
 			} else {
diff --git a/sound/pci/atiixp.c b/sound/pci/atiixp.c
index 7895c5d300c..9c1c4452a8e 100644
--- a/sound/pci/atiixp.c
+++ b/sound/pci/atiixp.c
@@ -688,9 +688,7 @@ static void snd_atiixp_xrun_dma(struct atiixp *chip, struct atiixp_dma *dma)
 	if (! dma->substream || ! dma->running)
 		return;
 	dev_dbg(chip->card->dev, "XRUN detected (DMA %d)\n", dma->ops->type);
-	snd_pcm_stream_lock(dma->substream);
-	snd_pcm_stop(dma->substream, SNDRV_PCM_STATE_XRUN);
-	snd_pcm_stream_unlock(dma->substream);
+	snd_pcm_stop_xrun(dma->substream);
 }
 
 /*
diff --git a/sound/pci/atiixp_modem.c b/sound/pci/atiixp_modem.c
index 3c3241309a3..b2f63e0727d 100644
--- a/sound/pci/atiixp_modem.c
+++ b/sound/pci/atiixp_modem.c
@@ -638,9 +638,7 @@ static void snd_atiixp_xrun_dma(struct atiixp_modem *chip,
 	if (! dma->substream || ! dma->running)
 		return;
 	dev_dbg(chip->card->dev, "XRUN detected (DMA %d)\n", dma->ops->type);
-	snd_pcm_stream_lock(dma->substream);
-	snd_pcm_stop(dma->substream, SNDRV_PCM_STATE_XRUN);
-	snd_pcm_stream_unlock(dma->substream);
+	snd_pcm_stop_xrun(dma->substream);
 }
 
 /*
diff --git a/sound/soc/atmel/atmel-pcm-dma.c b/sound/soc/atmel/atmel-pcm-dma.c
index b79a2a86451..33fb3bb133d 100644
--- a/sound/soc/atmel/atmel-pcm-dma.c
+++ b/sound/soc/atmel/atmel-pcm-dma.c
@@ -80,9 +80,7 @@ static void atmel_pcm_dma_irq(u32 ssc_sr,
 
 		/* stop RX and capture: will be enabled again at restart */
 		ssc_writex(prtd->ssc->regs, SSC_CR, prtd->mask->ssc_disable);
-		snd_pcm_stream_lock(substream);
-		snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
-		snd_pcm_stream_unlock(substream);
+		snd_pcm_stop_xrun(substream);
 
 		/* now drain RHR and read status to remove xrun condition */
 		ssc_readx(prtd->ssc->regs, SSC_RHR);
diff --git a/sound/soc/fsl/fsl_dma.c b/sound/soc/fsl/fsl_dma.c
index a609aafc994..b2b108805b2 100644
--- a/sound/soc/fsl/fsl_dma.c
+++ b/sound/soc/fsl/fsl_dma.c
@@ -151,14 +151,7 @@ static const struct snd_pcm_hardware fsl_dma_hardware = {
  */
 static void fsl_dma_abort_stream(struct snd_pcm_substream *substream)
 {
-	unsigned long flags;
-
-	snd_pcm_stream_lock_irqsave(substream, flags);
-
-	if (snd_pcm_running(substream))
-		snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
-
-	snd_pcm_stream_unlock_irqrestore(substream, flags);
+	snd_pcm_stop_xrun(substream);
 }
 
 /**
diff --git a/sound/usb/6fire/pcm.c b/sound/usb/6fire/pcm.c
index ba40489b2de..36f4115eb1c 100644
--- a/sound/usb/6fire/pcm.c
+++ b/sound/usb/6fire/pcm.c
@@ -679,25 +679,16 @@ int usb6fire_pcm_init(struct sfire_chip *chip)
 void usb6fire_pcm_abort(struct sfire_chip *chip)
 {
 	struct pcm_runtime *rt = chip->pcm;
-	unsigned long flags;
 	int i;
 
 	if (rt) {
 		rt->panic = true;
 
-		if (rt->playback.instance) {
-			snd_pcm_stream_lock_irqsave(rt->playback.instance, flags);
-			snd_pcm_stop(rt->playback.instance,
-					SNDRV_PCM_STATE_XRUN);
-			snd_pcm_stream_unlock_irqrestore(rt->playback.instance, flags);
-		}
+		if (rt->playback.instance)
+			snd_pcm_stop_xrun(rt->playback.instance);
 
-		if (rt->capture.instance) {
-			snd_pcm_stream_lock_irqsave(rt->capture.instance, flags);
-			snd_pcm_stop(rt->capture.instance,
-					SNDRV_PCM_STATE_XRUN);
-			snd_pcm_stream_unlock_irqrestore(rt->capture.instance, flags);
-		}
+		if (rt->capture.instance)
+			snd_pcm_stop_xrun(rt->capture.instance);
 
 		for (i = 0; i < PCM_N_URBS; i++) {
 			usb_poison_urb(&rt->in_urbs[i].instance);
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index a4679913b0a..03b07441996 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -391,9 +391,7 @@ static void snd_complete_urb(struct urb *urb)
 	usb_audio_err(ep->chip, "cannot submit urb (err = %d)\n", err);
 	if (ep->data_subs && ep->data_subs->pcm_substream) {
 		substream = ep->data_subs->pcm_substream;
-		snd_pcm_stream_lock_irqsave(substream, flags);
-		snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
-		snd_pcm_stream_unlock_irqrestore(substream, flags);
+		snd_pcm_stop_xrun(substream);
 	}
 
 exit_clear:
diff --git a/sound/usb/misc/ua101.c b/sound/usb/misc/ua101.c
index a1bab149df4..9581089c28c 100644
--- a/sound/usb/misc/ua101.c
+++ b/sound/usb/misc/ua101.c
@@ -613,24 +613,14 @@ static int start_usb_playback(struct ua101 *ua)
 
 static void abort_alsa_capture(struct ua101 *ua)
 {
-	unsigned long flags;
-
-	if (test_bit(ALSA_CAPTURE_RUNNING, &ua->states)) {
-		snd_pcm_stream_lock_irqsave(ua->capture.substream, flags);
-		snd_pcm_stop(ua->capture.substream, SNDRV_PCM_STATE_XRUN);
-		snd_pcm_stream_unlock_irqrestore(ua->capture.substream, flags);
-	}
+	if (test_bit(ALSA_CAPTURE_RUNNING, &ua->states))
+		snd_pcm_stop_xrun(ua->capture.substream);
 }
 
 static void abort_alsa_playback(struct ua101 *ua)
 {
-	unsigned long flags;
-
-	if (test_bit(ALSA_PLAYBACK_RUNNING, &ua->states)) {
-		snd_pcm_stream_lock_irqsave(ua->playback.substream, flags);
-		snd_pcm_stop(ua->playback.substream, SNDRV_PCM_STATE_XRUN);
-		snd_pcm_stream_unlock_irqrestore(ua->playback.substream, flags);
-	}
+	if (test_bit(ALSA_PLAYBACK_RUNNING, &ua->states))
+		snd_pcm_stop_xrun(ua->playback.substream);
 }
 
 static int set_stream_hw(struct ua101 *ua, struct snd_pcm_substream *substream,
diff --git a/sound/usb/usx2y/usbusx2yaudio.c b/sound/usb/usx2y/usbusx2yaudio.c
index a63330dd140..61d5dc2a342 100644
--- a/sound/usb/usx2y/usbusx2yaudio.c
+++ b/sound/usb/usx2y/usbusx2yaudio.c
@@ -272,13 +272,8 @@ static void usX2Y_clients_stop(struct usX2Ydev *usX2Y)
 	for (s = 0; s < 4; s++) {
 		struct snd_usX2Y_substream *subs = usX2Y->subs[s];
 		if (subs) {
-			if (atomic_read(&subs->state) >= state_PRERUNNING) {
-				unsigned long flags;
-
-				snd_pcm_stream_lock_irqsave(subs->pcm_substream, flags);
-				snd_pcm_stop(subs->pcm_substream, SNDRV_PCM_STATE_XRUN);
-				snd_pcm_stream_unlock_irqrestore(subs->pcm_substream, flags);
-			}
+			if (atomic_read(&subs->state) >= state_PRERUNNING)
+				snd_pcm_stop_xrun(subs->pcm_substream);
 			for (u = 0; u < NRURBS; u++) {
 				struct urb *urb = subs->urb[u];
 				if (NULL != urb)
-- 
cgit v1.2.3-70-g09d2


From 863e88f255dac0657e57d5f1a1f95ee8733f8c13 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 9 Nov 2014 08:36:45 +0100
Subject: mac802154: move mac pib attributes into wpan_dev

This patch moves all mac pib attributes into the wpan_dev struct.
Furthermore we can easier access these attributes over the netdev
802154_ptr pointer. Currently this is only possible over a complicated
callback structure in mac802154 because subif data structure is
accessable inside mac802154 only.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h      | 24 +++++++++++++++----
 net/mac802154/ieee802154_i.h | 10 --------
 net/mac802154/iface.c        | 55 +++++++++++++++++++++++++-------------------
 net/mac802154/mib.c          | 10 ++++----
 net/mac802154/rx.c           |  7 +++---
 5 files changed, 59 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 9d99b965576..ac8dd3b8669 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -52,14 +52,9 @@ struct wpan_phy {
 	u32 channels_supported[32];
 	s8 transmit_power;
 	u8 cca_mode;
-	u8 min_be;
-	u8 max_be;
-	u8 csma_retries;
-	s8 frame_retries;
 
 	__le64 perm_extended_addr;
 
-	bool lbt;
 	s32 cca_ed_level;
 
 	struct device dev;
@@ -69,6 +64,25 @@ struct wpan_phy {
 
 struct wpan_dev {
 	struct wpan_phy *wpan_phy;
+
+	/* MAC PIB */
+	__le16 pan_id;
+	__le16 short_addr;
+	__le64 extended_addr;
+
+	/* MAC BSN field */
+	u8 bsn;
+	/* MAC DSN field */
+	u8 dsn;
+
+	u8 min_be;
+	u8 max_be;
+	u8 csma_retries;
+	s8 frame_retries;
+
+	bool lbt;
+
+	bool promiscuous_mode;
 };
 
 #define to_phy(_dev)	container_of(_dev, struct wpan_phy, dev)
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index 4acacea0d37..803f529e2c4 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -84,18 +84,8 @@ struct ieee802154_sub_if_data {
 
 	spinlock_t mib_lock;
 
-	__le16 pan_id;
-	__le16 short_addr;
-	__le64 extended_addr;
-	bool promiscuous_mode;
-
 	struct ieee802154_mac_params mac_params;
 
-	/* MAC BSN field */
-	u8 bsn;
-	/* MAC DSN field */
-	u8 dsn;
-
 	/* protects sec from concurrent access by netlink. access by
 	 * encrypt/decrypt/header_create safe without additional protection.
 	 */
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index 384f4bb3c99..6669da7446f 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -35,16 +35,17 @@ static int mac802154_wpan_update_llsec(struct net_device *dev)
 {
 	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
 	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
 	int rc = 0;
 
 	if (ops->llsec) {
 		struct ieee802154_llsec_params params;
 		int changed = 0;
 
-		params.pan_id = sdata->pan_id;
+		params.pan_id = wpan_dev->pan_id;
 		changed |= IEEE802154_LLSEC_PARAM_PAN_ID;
 
-		params.hwaddr = sdata->extended_addr;
+		params.hwaddr = wpan_dev->extended_addr;
 		changed |= IEEE802154_LLSEC_PARAM_HWADDR;
 
 		rc = ops->llsec->set_params(dev, &params, changed);
@@ -57,6 +58,7 @@ static int
 mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
 	struct sockaddr_ieee802154 *sa =
 		(struct sockaddr_ieee802154 *)&ifr->ifr_addr;
 	int err = -ENOIOCTLCMD;
@@ -68,8 +70,8 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	{
 		u16 pan_id, short_addr;
 
-		pan_id = le16_to_cpu(sdata->pan_id);
-		short_addr = le16_to_cpu(sdata->short_addr);
+		pan_id = le16_to_cpu(wpan_dev->pan_id);
+		short_addr = le16_to_cpu(wpan_dev->short_addr);
 		if (pan_id == IEEE802154_PANID_BROADCAST ||
 		    short_addr == IEEE802154_ADDR_BROADCAST) {
 			err = -EADDRNOTAVAIL;
@@ -96,8 +98,8 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			break;
 		}
 
-		sdata->pan_id = cpu_to_le16(sa->addr.pan_id);
-		sdata->short_addr = cpu_to_le16(sa->addr.short_addr);
+		wpan_dev->pan_id = cpu_to_le16(sa->addr.pan_id);
+		wpan_dev->short_addr = cpu_to_le16(sa->addr.short_addr);
 
 		err = mac802154_wpan_update_llsec(dev);
 		break;
@@ -121,7 +123,7 @@ static int mac802154_wpan_mac_addr(struct net_device *dev, void *p)
 		return -EINVAL;
 
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
-	sdata->extended_addr = extended_addr;
+	sdata->wpan_dev.extended_addr = extended_addr;
 
 	return mac802154_wpan_update_llsec(dev);
 }
@@ -172,6 +174,7 @@ static int mac802154_wpan_open(struct net_device *dev)
 	int rc;
 	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
 	struct ieee802154_local *local = sdata->local;
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
 	struct wpan_phy *phy = sdata->local->phy;
 
 	rc = mac802154_slave_open(dev);
@@ -181,21 +184,22 @@ static int mac802154_wpan_open(struct net_device *dev)
 	mutex_lock(&phy->pib_lock);
 
 	if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) {
-		rc = drv_set_promiscuous_mode(local, sdata->promiscuous_mode);
+		rc = drv_set_promiscuous_mode(local,
+					      wpan_dev->promiscuous_mode);
 		if (rc < 0)
 			goto out;
 	}
 
 	if (local->hw.flags & IEEE802154_HW_AFILT) {
-		rc = drv_set_pan_id(local, sdata->pan_id);
+		rc = drv_set_pan_id(local, wpan_dev->pan_id);
 		if (rc < 0)
 			goto out;
 
-		rc = drv_set_extended_addr(local, sdata->extended_addr);
+		rc = drv_set_extended_addr(local, wpan_dev->extended_addr);
 		if (rc < 0)
 			goto out;
 
-		rc = drv_set_short_addr(local, sdata->short_addr);
+		rc = drv_set_short_addr(local, wpan_dev->short_addr);
 		if (rc < 0)
 			goto out;
 	}
@@ -288,6 +292,7 @@ static int mac802154_header_create(struct sk_buff *skb,
 {
 	struct ieee802154_hdr hdr;
 	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
 	struct ieee802154_mac_cb *cb = mac_cb(skb);
 	int hlen;
 
@@ -306,17 +311,17 @@ static int mac802154_header_create(struct sk_buff *skb,
 	if (!saddr) {
 		spin_lock_bh(&sdata->mib_lock);
 
-		if (sdata->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST) ||
-		    sdata->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) ||
-		    sdata->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST)) {
+		if (wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST) ||
+		    wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) ||
+		    wpan_dev->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST)) {
 			hdr.source.mode = IEEE802154_ADDR_LONG;
-			hdr.source.extended_addr = sdata->extended_addr;
+			hdr.source.extended_addr = wpan_dev->extended_addr;
 		} else {
 			hdr.source.mode = IEEE802154_ADDR_SHORT;
-			hdr.source.short_addr = sdata->short_addr;
+			hdr.source.short_addr = wpan_dev->short_addr;
 		}
 
-		hdr.source.pan_id = sdata->pan_id;
+		hdr.source.pan_id = wpan_dev->pan_id;
 
 		spin_unlock_bh(&sdata->mib_lock);
 	} else {
@@ -396,11 +401,13 @@ static void ieee802154_if_setup(struct net_device *dev)
 static int
 ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, int type)
 {
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+
 	/* set some type-dependent values */
 	sdata->vif.type = type;
 
-	get_random_bytes(&sdata->bsn, 1);
-	get_random_bytes(&sdata->dsn, 1);
+	get_random_bytes(&wpan_dev->bsn, 1);
+	get_random_bytes(&wpan_dev->dsn, 1);
 
 	/* defaults per 802.15.4-2011 */
 	sdata->mac_params.min_be = 3;
@@ -409,9 +416,9 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, int type)
 	/* for compatibility, actual default is 3 */
 	sdata->mac_params.frame_retries = -1;
 
-	ieee802154_be64_to_le64(&sdata->extended_addr, sdata->dev->dev_addr);
-	sdata->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
-	sdata->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
+	ieee802154_be64_to_le64(&wpan_dev->extended_addr, sdata->dev->dev_addr);
+	wpan_dev->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
+	wpan_dev->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
 
 	switch (type) {
 	case IEEE802154_DEV_WPAN:
@@ -419,7 +426,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, int type)
 		sdata->dev->destructor = mac802154_wpan_free;
 		sdata->dev->netdev_ops = &mac802154_wpan_ops;
 		sdata->dev->ml_priv = &mac802154_mlme_wpan;
-		sdata->promiscuous_mode = false;
+		wpan_dev->promiscuous_mode = false;
 
 		spin_lock_init(&sdata->mib_lock);
 		mutex_init(&sdata->sec_mtx);
@@ -429,7 +436,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, int type)
 	case IEEE802154_DEV_MONITOR:
 		sdata->dev->destructor = free_netdev;
 		sdata->dev->netdev_ops = &mac802154_monitor_ops;
-		sdata->promiscuous_mode = true;
+		wpan_dev->promiscuous_mode = true;
 		break;
 	default:
 		BUG();
diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c
index 6fa749154ba..3596b29ead6 100644
--- a/net/mac802154/mib.c
+++ b/net/mac802154/mib.c
@@ -33,7 +33,7 @@ void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val)
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
 	spin_lock_bh(&sdata->mib_lock);
-	sdata->short_addr = val;
+	sdata->wpan_dev.short_addr = val;
 	spin_unlock_bh(&sdata->mib_lock);
 }
 
@@ -45,7 +45,7 @@ __le16 mac802154_dev_get_short_addr(const struct net_device *dev)
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
 	spin_lock_bh(&sdata->mib_lock);
-	ret = sdata->short_addr;
+	ret = sdata->wpan_dev.short_addr;
 	spin_unlock_bh(&sdata->mib_lock);
 
 	return ret;
@@ -59,7 +59,7 @@ __le16 mac802154_dev_get_pan_id(const struct net_device *dev)
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
 	spin_lock_bh(&sdata->mib_lock);
-	ret = sdata->pan_id;
+	ret = sdata->wpan_dev.pan_id;
 	spin_unlock_bh(&sdata->mib_lock);
 
 	return ret;
@@ -72,7 +72,7 @@ void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val)
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
 	spin_lock_bh(&sdata->mib_lock);
-	sdata->pan_id = val;
+	sdata->wpan_dev.pan_id = val;
 	spin_unlock_bh(&sdata->mib_lock);
 }
 
@@ -82,7 +82,7 @@ u8 mac802154_dev_get_dsn(const struct net_device *dev)
 
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
-	return sdata->dsn++;
+	return sdata->wpan_dev.dsn++;
 }
 
 void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan)
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index 4b54cf33e56..b18e755c38c 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -42,6 +42,7 @@ static int
 ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata,
 		       struct sk_buff *skb, const struct ieee802154_hdr *hdr)
 {
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
 	__le16 span, sshort;
 	int rc;
 
@@ -49,8 +50,8 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata,
 
 	spin_lock_bh(&sdata->mib_lock);
 
-	span = sdata->pan_id;
-	sshort = sdata->short_addr;
+	span = wpan_dev->pan_id;
+	sshort = wpan_dev->short_addr;
 
 	switch (mac_cb(skb)->dest.mode) {
 	case IEEE802154_ADDR_NONE:
@@ -65,7 +66,7 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata,
 		if (mac_cb(skb)->dest.pan_id != span &&
 		    mac_cb(skb)->dest.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST))
 			skb->pkt_type = PACKET_OTHERHOST;
-		else if (mac_cb(skb)->dest.extended_addr == sdata->extended_addr)
+		else if (mac_cb(skb)->dest.extended_addr == wpan_dev->extended_addr)
 			skb->pkt_type = PACKET_HOST;
 		else
 			skb->pkt_type = PACKET_OTHERHOST;
-- 
cgit v1.2.3-70-g09d2


From f601379fa113906b8bf4389a62002def283519c9 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 9 Nov 2014 08:36:47 +0100
Subject: ieee802154: rename wpan_phy_alloc

This patch renames the wpan_phy_alloc function to wpan_phy_new. This
naming convention is like wireless and "wiphy_new" function.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h | 2 +-
 net/ieee802154/core.c   | 4 ++--
 net/mac802154/main.c    | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index ac8dd3b8669..72c4723a120 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -88,7 +88,7 @@ struct wpan_dev {
 #define to_phy(_dev)	container_of(_dev, struct wpan_phy, dev)
 
 struct wpan_phy *
-wpan_phy_alloc(const struct cfg802154_ops *ops, size_t priv_size);
+wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size);
 static inline void wpan_phy_set_dev(struct wpan_phy *phy, struct device *dev)
 {
 	phy->dev.parent = dev;
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index d1cd0edfb14..a3aa23f8c36 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -70,7 +70,7 @@ int wpan_phy_for_each(int (*fn)(struct wpan_phy *phy, void *data),
 EXPORT_SYMBOL(wpan_phy_for_each);
 
 struct wpan_phy *
-wpan_phy_alloc(const struct cfg802154_ops *ops, size_t priv_size)
+wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size)
 {
 	static atomic_t wpan_phy_counter = ATOMIC_INIT(0);
 	struct cfg802154_registered_device *rdev;
@@ -105,7 +105,7 @@ wpan_phy_alloc(const struct cfg802154_ops *ops, size_t priv_size)
 
 	return &rdev->wpan_phy;
 }
-EXPORT_SYMBOL(wpan_phy_alloc);
+EXPORT_SYMBOL(wpan_phy_new);
 
 int wpan_phy_register(struct wpan_phy *phy)
 {
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 7d0ff7fd2cd..234084d2690 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -86,7 +86,7 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops)
 
 	priv_size = ALIGN(sizeof(*local), NETDEV_ALIGN) + priv_data_len;
 
-	phy = wpan_phy_alloc(&mac802154_config_ops, priv_size);
+	phy = wpan_phy_new(&mac802154_config_ops, priv_size);
 	if (!phy) {
 		pr_err("failure to allocate master IEEE802.15.4 device\n");
 		return NULL;
-- 
cgit v1.2.3-70-g09d2


From 190ac1ca33442dc25a172ece0f34746a7e1514f3 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 9 Nov 2014 08:36:49 +0100
Subject: ieee802154: add iftype to wpan_dev

This patch adds an iftype argument to the wpan_dev. This is needed to
get the interface type from netdev ieee802154_ptr. The subif data struct
can only accessible in mac802154 branch.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h | 1 +
 net/mac802154/iface.c   | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 72c4723a120..7e1bc21423b 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -64,6 +64,7 @@ struct wpan_phy {
 
 struct wpan_dev {
 	struct wpan_phy *wpan_phy;
+	int iftype;
 
 	/* MAC PIB */
 	__le16 pan_id;
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index c0b96cf525d..4630ceb25ad 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -404,6 +404,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, int type)
 
 	/* set some type-dependent values */
 	sdata->vif.type = type;
+	sdata->wpan_dev.iftype = type;
 
 	get_random_bytes(&wpan_dev->bsn, 1);
 	get_random_bytes(&wpan_dev->dsn, 1);
-- 
cgit v1.2.3-70-g09d2


From fcf39e6e88e9492f6688ec8ba4e1be622b904232 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 9 Nov 2014 08:36:50 +0100
Subject: ieee802154: add wpan_dev_list

This patch adds a wpan_dev_list list into cfg802154_registered_device
struct. Also adding new wpan_dev into this list while
cfg802154_netdev_notifier_call. This behaviour is mostly grab from
wireless core.c implementation and is needed for preparing nl802154
framework.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h |  6 ++++
 net/ieee802154/core.c   | 95 +++++++++++++++++++++++++++++++++++++++++++++++--
 net/ieee802154/core.h   | 11 ++++++
 3 files changed, 109 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 7e1bc21423b..e5570e01111 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -66,6 +66,12 @@ struct wpan_dev {
 	struct wpan_phy *wpan_phy;
 	int iftype;
 
+	/* the remainder of this struct should be private to cfg802154 */
+	struct list_head list;
+	struct net_device *netdev;
+
+	u32 identifier;
+
 	/* MAC PIB */
 	__le16 pan_id;
 	__le16 short_addr;
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index 11a1d2ed5b2..3ee00bf0e51 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -102,12 +102,15 @@ wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size)
 
 	mutex_init(&rdev->wpan_phy.pib_lock);
 
+	INIT_LIST_HEAD(&rdev->wpan_dev_list);
 	device_initialize(&rdev->wpan_phy.dev);
 	dev_set_name(&rdev->wpan_phy.dev, "wpan-phy%d", rdev->wpan_phy_idx);
 
 	rdev->wpan_phy.dev.class = &wpan_phy_class;
 	rdev->wpan_phy.dev.platform_data = rdev;
 
+	init_waitqueue_head(&rdev->dev_wait);
+
 	return &rdev->wpan_phy;
 }
 EXPORT_SYMBOL(wpan_phy_new);
@@ -140,13 +143,18 @@ void wpan_phy_unregister(struct wpan_phy *phy)
 {
 	struct cfg802154_registered_device *rdev = wpan_phy_to_rdev(phy);
 
-	/* TODO open count */
+	wait_event(rdev->dev_wait, ({
+		int __count;
+		rtnl_lock();
+		__count = rdev->opencount;
+		rtnl_unlock();
+		__count == 0; }));
 
 	rtnl_lock();
 	/* TODO nl802154 phy notify */
 	/* TODO phy registered lock */
 
-	/* TODO WARN_ON wpan_dev_list */
+	WARN_ON(!list_empty(&rdev->wpan_dev_list));
 
 	/* First remove the hardware from everywhere, this makes
 	 * it impossible to find from userspace.
@@ -173,6 +181,79 @@ void cfg802154_dev_free(struct cfg802154_registered_device *rdev)
 	kfree(rdev);
 }
 
+static void
+cfg802154_update_iface_num(struct cfg802154_registered_device *rdev,
+			   int iftype, int num)
+{
+	ASSERT_RTNL();
+
+	rdev->num_running_ifaces += num;
+}
+
+static int cfg802154_netdev_notifier_call(struct notifier_block *nb,
+					  unsigned long state, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	struct cfg802154_registered_device *rdev;
+
+	if (!wpan_dev)
+		return NOTIFY_DONE;
+
+	rdev = wpan_phy_to_rdev(wpan_dev->wpan_phy);
+
+	/* TODO WARN_ON unspec type */
+
+	switch (state) {
+		/* TODO NETDEV_DEVTYPE */
+	case NETDEV_REGISTER:
+		wpan_dev->identifier = ++rdev->wpan_dev_id;
+		list_add_rcu(&wpan_dev->list, &rdev->wpan_dev_list);
+		rdev->devlist_generation++;
+
+		wpan_dev->netdev = dev;
+		break;
+	case NETDEV_DOWN:
+		cfg802154_update_iface_num(rdev, wpan_dev->iftype, -1);
+
+		rdev->opencount--;
+		wake_up(&rdev->dev_wait);
+		break;
+	case NETDEV_UP:
+		cfg802154_update_iface_num(rdev, wpan_dev->iftype, 1);
+
+		rdev->opencount++;
+		break;
+	case NETDEV_UNREGISTER:
+		/* It is possible to get NETDEV_UNREGISTER
+		 * multiple times. To detect that, check
+		 * that the interface is still on the list
+		 * of registered interfaces, and only then
+		 * remove and clean it up.
+		 */
+		if (!list_empty(&wpan_dev->list)) {
+			list_del_rcu(&wpan_dev->list);
+			rdev->devlist_generation++;
+		}
+		/* synchronize (so that we won't find this netdev
+		 * from other code any more) and then clear the list
+		 * head so that the above code can safely check for
+		 * !list_empty() to avoid double-cleanup.
+		 */
+		synchronize_rcu();
+		INIT_LIST_HEAD(&wpan_dev->list);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block cfg802154_netdev_notifier = {
+	.notifier_call = cfg802154_netdev_notifier_call,
+};
+
 static int __init wpan_phy_class_init(void)
 {
 	int rc;
@@ -181,11 +262,18 @@ static int __init wpan_phy_class_init(void)
 	if (rc)
 		goto err;
 
-	rc = ieee802154_nl_init();
+	rc = register_netdevice_notifier(&cfg802154_netdev_notifier);
 	if (rc)
 		goto err_nl;
 
+	rc = ieee802154_nl_init();
+	if (rc)
+		goto err_notifier;
+
 	return 0;
+
+err_notifier:
+	unregister_netdevice_notifier(&cfg802154_netdev_notifier);
 err_nl:
 	wpan_phy_sysfs_exit();
 err:
@@ -196,6 +284,7 @@ subsys_initcall(wpan_phy_class_init);
 static void __exit wpan_phy_class_exit(void)
 {
 	ieee802154_nl_exit();
+	unregister_netdevice_notifier(&cfg802154_netdev_notifier);
 	wpan_phy_sysfs_exit();
 }
 module_exit(wpan_phy_class_exit);
diff --git a/net/ieee802154/core.h b/net/ieee802154/core.h
index 38887cb2eaf..e708d9d5878 100644
--- a/net/ieee802154/core.h
+++ b/net/ieee802154/core.h
@@ -10,6 +10,17 @@ struct cfg802154_registered_device {
 	/* wpan_phy index, internal only */
 	int wpan_phy_idx;
 
+	/* also protected by devlist_mtx */
+	int opencount;
+	wait_queue_head_t dev_wait;
+
+	/* protected by RTNL only */
+	int num_running_ifaces;
+
+	/* associated wpan interfaces, protected by rtnl or RCU */
+	struct list_head wpan_dev_list;
+	int devlist_generation, wpan_dev_id;
+
 	/* must be last because of the way we do wpan_phy_priv(),
 	 * and it should at least be aligned to NETDEV_ALIGN
 	 */
-- 
cgit v1.2.3-70-g09d2


From 3ae75e02c34b5b8d521b0470522e540512ce24e3 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Sun, 9 Nov 2014 08:36:52 +0100
Subject: ieee802154: add new nl802154 header

This patch adds the new userspace header for nl802154. We don't place
this header in include/uapi now. This header could be modified in the
next time.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 MAINTAINERS            |   1 +
 include/net/nl802154.h | 122 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 123 insertions(+)
 create mode 100644 include/net/nl802154.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index b42eb50b742..7ec37a396ff 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4699,6 +4699,7 @@ F:	net/mac802154/
 F:	drivers/net/ieee802154/
 F:	include/linux/nl802154.h
 F:	include/linux/ieee802154.h
+F:	include/net/nl802154.h
 F:	include/net/mac802154.h
 F:	include/net/af_ieee802154.h
 F:	include/net/cfg802154.h
diff --git a/include/net/nl802154.h b/include/net/nl802154.h
new file mode 100644
index 00000000000..6dbd406ca41
--- /dev/null
+++ b/include/net/nl802154.h
@@ -0,0 +1,122 @@
+#ifndef __NL802154_H
+#define __NL802154_H
+/*
+ * 802.15.4 netlink interface public header
+ *
+ * Copyright 2014 Alexander Aring <aar@pengutronix.de>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ *
+ */
+
+#define NL802154_GENL_NAME "nl802154"
+
+enum nl802154_commands {
+/* don't change the order or add anything between, this is ABI! */
+/* currently we don't shipping this file via uapi, ignore the above one */
+	NL802154_CMD_UNSPEC,
+
+	NL802154_CMD_GET_WPAN_PHY,		/* can dump */
+	NL802154_CMD_SET_WPAN_PHY,
+	NL802154_CMD_NEW_WPAN_PHY,
+	NL802154_CMD_DEL_WPAN_PHY,
+
+	NL802154_CMD_GET_INTERFACE,		/* can dump */
+	NL802154_CMD_SET_INTERFACE,
+	NL802154_CMD_NEW_INTERFACE,
+	NL802154_CMD_DEL_INTERFACE,
+
+	NL802154_CMD_SET_CHANNEL,
+
+	NL802154_CMD_SET_PAN_ID,
+	NL802154_CMD_SET_SHORT_ADDR,
+
+	NL802154_CMD_SET_TX_POWER,
+	NL802154_CMD_SET_CCA_MODE,
+	NL802154_CMD_SET_CCA_ED_LEVEL,
+
+	NL802154_CMD_SET_MAX_FRAME_RETRIES,
+
+	NL802154_CMD_SET_BACKOFF_EXPONENT,
+	NL802154_CMD_SET_MAX_CSMA_BACKOFFS,
+
+	NL802154_CMD_SET_LBT_MODE,
+
+	/* add new commands above here */
+
+	/* used to define NL802154_CMD_MAX below */
+	__NL802154_CMD_AFTER_LAST,
+	NL802154_CMD_MAX = __NL802154_CMD_AFTER_LAST - 1
+};
+
+enum nl802154_attrs {
+/* don't change the order or add anything between, this is ABI! */
+/* currently we don't shipping this file via uapi, ignore the above one */
+	NL802154_ATTR_UNSPEC,
+
+	NL802154_ATTR_WPAN_PHY,
+	NL802154_ATTR_WPAN_PHY_NAME,
+
+	NL802154_ATTR_IFINDEX,
+	NL802154_ATTR_IFNAME,
+	NL802154_ATTR_IFTYPE,
+
+	NL802154_ATTR_WPAN_DEV,
+
+	NL802154_ATTR_PAGE,
+	NL802154_ATTR_CHANNEL,
+
+	NL802154_ATTR_PAN_ID,
+	NL802154_ATTR_SHORT_ADDR,
+
+	NL802154_ATTR_TX_POWER,
+
+	NL802154_ATTR_CCA_MODE,
+	NL802154_ATTR_CCA_MODE3_AND,
+	NL802154_ATTR_CCA_ED_LEVEL,
+
+	NL802154_ATTR_MAX_FRAME_RETRIES,
+
+	NL802154_ATTR_MAX_BE,
+	NL802154_ATTR_MIN_BE,
+	NL802154_ATTR_MAX_CSMA_BACKOFFS,
+
+	NL802154_ATTR_LBT_MODE,
+
+	NL802154_ATTR_GENERATION,
+
+	NL802154_ATTR_CHANNELS_SUPPORTED,
+	NL802154_ATTR_SUPPORTED_CHANNEL,
+
+	NL802154_ATTR_EXTENDED_ADDR,
+
+	/* add attributes here, update the policy in nl802154.c */
+
+	__NL802154_ATTR_AFTER_LAST,
+	NL802154_ATTR_MAX = __NL802154_ATTR_AFTER_LAST - 1
+};
+
+enum nl802154_iftype {
+	/* for backwards compatibility TODO */
+	NL802154_IFTYPE_UNSPEC = -1,
+
+	NL802154_IFTYPE_NODE,
+	NL802154_IFTYPE_MONITOR,
+	NL802154_IFTYPE_COORD,
+
+	/* keep last */
+	NUM_NL802154_IFTYPES,
+	NL802154_IFTYPE_MAX = NUM_NL802154_IFTYPES - 1
+};
+
+#endif /* __NL802154_H */
-- 
cgit v1.2.3-70-g09d2


From ba3240beae340bc84dad16f2b67590f32d25d5a6 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 3 Nov 2014 17:44:51 -0800
Subject: ARM: shmobile: r8a7790: Add Audio DMAC devices to DT

Instantiate the two Audio DMA controllers in the r8a7790 device tree.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
[geert: corrected spelling of audmac1]
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 arch/arm/boot/dts/r8a7790.dtsi            | 64 +++++++++++++++++++++++++++++--
 include/dt-bindings/clock/r8a7790-clock.h |  2 +
 2 files changed, 63 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index 52c21569e35..2e01d4950b5 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -312,6 +312,63 @@
 		#dma-cells = <1>;
 		dma-channels = <15>;
 	};
+
+	audma0: dma-controller@ec700000 {
+		compatible = "renesas,rcar-dmac";
+		reg = <0 0xec700000 0 0x10000>;
+		interrupts =	<0 346 IRQ_TYPE_LEVEL_HIGH
+				 0 320 IRQ_TYPE_LEVEL_HIGH
+				 0 321 IRQ_TYPE_LEVEL_HIGH
+				 0 322 IRQ_TYPE_LEVEL_HIGH
+				 0 323 IRQ_TYPE_LEVEL_HIGH
+				 0 324 IRQ_TYPE_LEVEL_HIGH
+				 0 325 IRQ_TYPE_LEVEL_HIGH
+				 0 326 IRQ_TYPE_LEVEL_HIGH
+				 0 327 IRQ_TYPE_LEVEL_HIGH
+				 0 328 IRQ_TYPE_LEVEL_HIGH
+				 0 329 IRQ_TYPE_LEVEL_HIGH
+				 0 330 IRQ_TYPE_LEVEL_HIGH
+				 0 331 IRQ_TYPE_LEVEL_HIGH
+				 0 332 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "error",
+				"ch0", "ch1", "ch2", "ch3",
+				"ch4", "ch5", "ch6", "ch7",
+				"ch8", "ch9", "ch10", "ch11",
+				"ch12";
+		clocks = <&mstp5_clks R8A7790_CLK_AUDIO_DMAC0>;
+		clock-names = "fck";
+		#dma-cells = <1>;
+		dma-channels = <13>;
+	};
+
+	audma1: dma-controller@ec720000 {
+		compatible = "renesas,rcar-dmac";
+		reg = <0 0xec720000 0 0x10000>;
+		interrupts =	<0 347 IRQ_TYPE_LEVEL_HIGH
+				 0 333 IRQ_TYPE_LEVEL_HIGH
+				 0 334 IRQ_TYPE_LEVEL_HIGH
+				 0 335 IRQ_TYPE_LEVEL_HIGH
+				 0 336 IRQ_TYPE_LEVEL_HIGH
+				 0 337 IRQ_TYPE_LEVEL_HIGH
+				 0 338 IRQ_TYPE_LEVEL_HIGH
+				 0 339 IRQ_TYPE_LEVEL_HIGH
+				 0 340 IRQ_TYPE_LEVEL_HIGH
+				 0 341 IRQ_TYPE_LEVEL_HIGH
+				 0 342 IRQ_TYPE_LEVEL_HIGH
+				 0 343 IRQ_TYPE_LEVEL_HIGH
+				 0 344 IRQ_TYPE_LEVEL_HIGH
+				 0 345 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "error",
+				"ch0", "ch1", "ch2", "ch3",
+				"ch4", "ch5", "ch6", "ch7",
+				"ch8", "ch9", "ch10", "ch11",
+				"ch12";
+		clocks = <&mstp5_clks R8A7790_CLK_AUDIO_DMAC1>;
+		clock-names = "fck";
+		#dma-cells = <1>;
+		dma-channels = <13>;
+	};
+
 	i2c0: i2c@e6508000 {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -1050,10 +1107,11 @@
 		mstp5_clks: mstp5_clks@e6150144 {
 			compatible = "renesas,r8a7790-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150144 0 4>, <0 0xe615003c 0 4>;
-			clocks = <&extal_clk>, <&p_clk>;
+			clocks = <&hp_clk>, <&hp_clk>, <&extal_clk>, <&p_clk>;
 			#clock-cells = <1>;
-			renesas,clock-indices = <R8A7790_CLK_THERMAL R8A7790_CLK_PWM>;
-			clock-output-names = "thermal", "pwm";
+			renesas,clock-indices = <R8A7790_CLK_AUDIO_DMAC0 R8A7790_CLK_AUDIO_DMAC1
+						 R8A7790_CLK_THERMAL R8A7790_CLK_PWM>;
+			clock-output-names = "audmac0", "audmac1", "thermal", "pwm";
 		};
 		mstp7_clks: mstp7_clks@e615014c {
 			compatible = "renesas,r8a7790-mstp-clocks", "renesas,cpg-mstp-clocks";
diff --git a/include/dt-bindings/clock/r8a7790-clock.h b/include/dt-bindings/clock/r8a7790-clock.h
index e3a3fb80feb..c27b3b5133b 100644
--- a/include/dt-bindings/clock/r8a7790-clock.h
+++ b/include/dt-bindings/clock/r8a7790-clock.h
@@ -78,6 +78,8 @@
 #define R8A7790_CLK_USBDMAC1		31
 
 /* MSTP5 */
+#define R8A7790_CLK_AUDIO_DMAC1		1
+#define R8A7790_CLK_AUDIO_DMAC0		2
 #define R8A7790_CLK_THERMAL		22
 #define R8A7790_CLK_PWM			23
 
-- 
cgit v1.2.3-70-g09d2


From 8994fff677610e2e0aacb25c39b49739444844b0 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 3 Nov 2014 17:45:37 -0800
Subject: ARM: shmobile: r8a7791: Add Audio DMAC devices to DT

Instantiate the two Audio DMA controllers in the r8a7791 device tree.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
[geert: corrected spelling of audmac1]
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 arch/arm/boot/dts/r8a7791.dtsi            | 63 +++++++++++++++++++++++++++++--
 include/dt-bindings/clock/r8a7791-clock.h |  2 +
 2 files changed, 62 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index a862243f043..b54af745141 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -301,6 +301,62 @@
 		dma-channels = <15>;
 	};
 
+	audma0: dma-controller@ec700000 {
+		compatible = "renesas,rcar-dmac";
+		reg = <0 0xec700000 0 0x10000>;
+		interrupts =	<0 346 IRQ_TYPE_LEVEL_HIGH
+				 0 320 IRQ_TYPE_LEVEL_HIGH
+				 0 321 IRQ_TYPE_LEVEL_HIGH
+				 0 322 IRQ_TYPE_LEVEL_HIGH
+				 0 323 IRQ_TYPE_LEVEL_HIGH
+				 0 324 IRQ_TYPE_LEVEL_HIGH
+				 0 325 IRQ_TYPE_LEVEL_HIGH
+				 0 326 IRQ_TYPE_LEVEL_HIGH
+				 0 327 IRQ_TYPE_LEVEL_HIGH
+				 0 328 IRQ_TYPE_LEVEL_HIGH
+				 0 329 IRQ_TYPE_LEVEL_HIGH
+				 0 330 IRQ_TYPE_LEVEL_HIGH
+				 0 331 IRQ_TYPE_LEVEL_HIGH
+				 0 332 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "error",
+				"ch0", "ch1", "ch2", "ch3",
+				"ch4", "ch5", "ch6", "ch7",
+				"ch8", "ch9", "ch10", "ch11",
+				"ch12";
+		clocks = <&mstp5_clks R8A7791_CLK_AUDIO_DMAC0>;
+		clock-names = "fck";
+		#dma-cells = <1>;
+		dma-channels = <13>;
+	};
+
+	audma1: dma-controller@ec720000 {
+		compatible = "renesas,rcar-dmac";
+		reg = <0 0xec720000 0 0x10000>;
+		interrupts =	<0 347 IRQ_TYPE_LEVEL_HIGH
+				 0 333 IRQ_TYPE_LEVEL_HIGH
+				 0 334 IRQ_TYPE_LEVEL_HIGH
+				 0 335 IRQ_TYPE_LEVEL_HIGH
+				 0 336 IRQ_TYPE_LEVEL_HIGH
+				 0 337 IRQ_TYPE_LEVEL_HIGH
+				 0 338 IRQ_TYPE_LEVEL_HIGH
+				 0 339 IRQ_TYPE_LEVEL_HIGH
+				 0 340 IRQ_TYPE_LEVEL_HIGH
+				 0 341 IRQ_TYPE_LEVEL_HIGH
+				 0 342 IRQ_TYPE_LEVEL_HIGH
+				 0 343 IRQ_TYPE_LEVEL_HIGH
+				 0 344 IRQ_TYPE_LEVEL_HIGH
+				 0 345 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "error",
+				"ch0", "ch1", "ch2", "ch3",
+				"ch4", "ch5", "ch6", "ch7",
+				"ch8", "ch9", "ch10", "ch11",
+				"ch12";
+		clocks = <&mstp5_clks R8A7791_CLK_AUDIO_DMAC1>;
+		clock-names = "fck";
+		#dma-cells = <1>;
+		dma-channels = <13>;
+	};
+
 	/* The memory map in the User's Manual maps the cores to bus numbers */
 	i2c0: i2c@e6508000 {
 		#address-cells = <1>;
@@ -1053,10 +1109,11 @@
 		mstp5_clks: mstp5_clks@e6150144 {
 			compatible = "renesas,r8a7791-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150144 0 4>, <0 0xe615003c 0 4>;
-			clocks = <&extal_clk>, <&p_clk>;
+			clocks = <&hp_clk>, <&hp_clk>, <&extal_clk>, <&p_clk>;
 			#clock-cells = <1>;
-			renesas,clock-indices = <R8A7791_CLK_THERMAL R8A7791_CLK_PWM>;
-			clock-output-names = "thermal", "pwm";
+			renesas,clock-indices = <R8A7791_CLK_AUDIO_DMAC0 R8A7791_CLK_AUDIO_DMAC1
+						 R8A7791_CLK_THERMAL R8A7791_CLK_PWM>;
+			clock-output-names = "audmac0", "audmac1", "thermal", "pwm";
 		};
 		mstp7_clks: mstp7_clks@e615014c {
 			compatible = "renesas,r8a7791-mstp-clocks", "renesas,cpg-mstp-clocks";
diff --git a/include/dt-bindings/clock/r8a7791-clock.h b/include/dt-bindings/clock/r8a7791-clock.h
index dcececd9f4d..3ea2bbc0da3 100644
--- a/include/dt-bindings/clock/r8a7791-clock.h
+++ b/include/dt-bindings/clock/r8a7791-clock.h
@@ -69,6 +69,8 @@
 #define R8A7791_CLK_USBDMAC1		31
 
 /* MSTP5 */
+#define R8A7791_CLK_AUDIO_DMAC1		1
+#define R8A7791_CLK_AUDIO_DMAC0		2
 #define R8A7791_CLK_THERMAL		22
 #define R8A7791_CLK_PWM			23
 
-- 
cgit v1.2.3-70-g09d2


From 8f0aad6f35f7e8b3118b7b8a65e8e76b135cc4cb Mon Sep 17 00:00:00 2001
From: Wenyu Zhang <wenyuz@vmware.com>
Date: Thu, 6 Nov 2014 06:51:24 -0800
Subject: openvswitch: Extend packet attribute for egress tunnel info

OVS vswitch has extended IPFIX exporter to export tunnel headers
to improve network visibility.
To export this information userspace needs to know egress tunnel
for given packet. By extending packet attributes datapath can
export egress tunnel info for given packet. So that userspace
can ask for egress tunnel info in userspace action. This
information is used to build IPFIX data for given flow.

Signed-off-by: Wenyu Zhang <wenyuz@vmware.com>
Acked-by: Romain Lenglet <rlenglet@vmware.com>
Acked-by: Ben Pfaff <blp@nicira.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
---
 include/uapi/linux/openvswitch.h | 13 +++++++++
 net/openvswitch/actions.c        | 19 ++++++++++++
 net/openvswitch/datapath.c       | 21 +++++++++++---
 net/openvswitch/datapath.h       |  2 ++
 net/openvswitch/flow.h           | 62 +++++++++++++++++++++++++++++++---------
 net/openvswitch/flow_netlink.c   | 54 +++++++++++++++++++++++++++-------
 net/openvswitch/flow_netlink.h   |  3 ++
 net/openvswitch/vport-geneve.c   | 21 +++++++++++++-
 net/openvswitch/vport-gre.c      | 12 +++++++-
 net/openvswitch/vport-vxlan.c    | 24 +++++++++++++++-
 net/openvswitch/vport.c          | 61 +++++++++++++++++++++++++++++++++++++++
 net/openvswitch/vport.h          | 14 +++++++++
 12 files changed, 275 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 26c36c4cf7e..cf8185661e5 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -157,6 +157,11 @@ enum ovs_packet_cmd {
  * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an
  * %OVS_USERSPACE_ATTR_USERDATA attribute, with the same length and content
  * specified there.
+ * @OVS_PACKET_ATTR_EGRESS_TUN_KEY: Present for an %OVS_PACKET_CMD_ACTION
+ * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an
+ * %OVS_USERSPACE_ATTR_EGRESS_TUN_PORT attribute, which is sent only if the
+ * output port is actually a tunnel port. Contains the output tunnel key
+ * extracted from the packet as nested %OVS_TUNNEL_KEY_ATTR_* attributes.
  *
  * These attributes follow the &struct ovs_header within the Generic Netlink
  * payload for %OVS_PACKET_* commands.
@@ -167,6 +172,8 @@ enum ovs_packet_attr {
 	OVS_PACKET_ATTR_KEY,         /* Nested OVS_KEY_ATTR_* attributes. */
 	OVS_PACKET_ATTR_ACTIONS,     /* Nested OVS_ACTION_ATTR_* attributes. */
 	OVS_PACKET_ATTR_USERDATA,    /* OVS_ACTION_ATTR_USERSPACE arg. */
+	OVS_PACKET_ATTR_EGRESS_TUN_KEY,  /* Nested OVS_TUNNEL_KEY_ATTR_*
+					    attributes. */
 	__OVS_PACKET_ATTR_MAX
 };
 
@@ -315,6 +322,8 @@ enum ovs_tunnel_key_attr {
 	OVS_TUNNEL_KEY_ATTR_CSUM,               /* No argument. CSUM packet. */
 	OVS_TUNNEL_KEY_ATTR_OAM,                /* No argument. OAM frame.  */
 	OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,        /* Array of Geneve options. */
+	OVS_TUNNEL_KEY_ATTR_TP_SRC,		/* be16 src Transport Port. */
+	OVS_TUNNEL_KEY_ATTR_TP_DST,		/* be16 dst Transport Port. */
 	__OVS_TUNNEL_KEY_ATTR_MAX
 };
 
@@ -480,11 +489,15 @@ enum ovs_sample_attr {
  * message should be sent.  Required.
  * @OVS_USERSPACE_ATTR_USERDATA: If present, its variable-length argument is
  * copied to the %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA.
+ * @OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: If present, u32 output port to get
+ * tunnel info.
  */
 enum ovs_userspace_attr {
 	OVS_USERSPACE_ATTR_UNSPEC,
 	OVS_USERSPACE_ATTR_PID,	      /* u32 Netlink PID to receive upcalls. */
 	OVS_USERSPACE_ATTR_USERDATA,  /* Optional user-specified cookie. */
+	OVS_USERSPACE_ATTR_EGRESS_TUN_PORT,  /* Optional, u32 output port
+					      * to get tunnel info. */
 	__OVS_USERSPACE_ATTR_MAX
 };
 
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index f7e589159e4..ceb618cf129 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -564,6 +564,7 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
 static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 			    struct sw_flow_key *key, const struct nlattr *attr)
 {
+	struct ovs_tunnel_info info;
 	struct dp_upcall_info upcall;
 	const struct nlattr *a;
 	int rem;
@@ -572,6 +573,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 	upcall.key = key;
 	upcall.userdata = NULL;
 	upcall.portid = 0;
+	upcall.egress_tun_info = NULL;
 
 	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
 		 a = nla_next(a, &rem)) {
@@ -583,7 +585,24 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 		case OVS_USERSPACE_ATTR_PID:
 			upcall.portid = nla_get_u32(a);
 			break;
+
+		case OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: {
+			/* Get out tunnel info. */
+			struct vport *vport;
+
+			vport = ovs_vport_rcu(dp, nla_get_u32(a));
+			if (vport) {
+				int err;
+
+				err = ovs_vport_get_egress_tun_info(vport, skb,
+								    &info);
+				if (!err)
+					upcall.egress_tun_info = &info;
+			}
+			break;
 		}
+
+		} /* End of switch. */
 	}
 
 	return ovs_dp_upcall(dp, skb, &upcall);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6cfb44f3a7f..c2ac340e19f 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -274,6 +274,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 		upcall.key = key;
 		upcall.userdata = NULL;
 		upcall.portid = ovs_vport_find_upcall_portid(p, skb);
+		upcall.egress_tun_info = NULL;
 		error = ovs_dp_upcall(dp, skb, &upcall);
 		if (unlikely(error))
 			kfree_skb(skb);
@@ -375,7 +376,7 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	return err;
 }
 
-static size_t upcall_msg_size(const struct nlattr *userdata,
+static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
 			      unsigned int hdrlen)
 {
 	size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
@@ -383,8 +384,12 @@ static size_t upcall_msg_size(const struct nlattr *userdata,
 		+ nla_total_size(ovs_key_attr_size()); /* OVS_PACKET_ATTR_KEY */
 
 	/* OVS_PACKET_ATTR_USERDATA */
-	if (userdata)
-		size += NLA_ALIGN(userdata->nla_len);
+	if (upcall_info->userdata)
+		size += NLA_ALIGN(upcall_info->userdata->nla_len);
+
+	/* OVS_PACKET_ATTR_EGRESS_TUN_KEY */
+	if (upcall_info->egress_tun_info)
+		size += nla_total_size(ovs_tun_key_attr_size());
 
 	return size;
 }
@@ -440,7 +445,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	else
 		hlen = skb->len;
 
-	len = upcall_msg_size(upcall_info->userdata, hlen);
+	len = upcall_msg_size(upcall_info, hlen);
 	user_skb = genlmsg_new_unicast(len, &info, GFP_ATOMIC);
 	if (!user_skb) {
 		err = -ENOMEM;
@@ -461,6 +466,14 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 			  nla_len(upcall_info->userdata),
 			  nla_data(upcall_info->userdata));
 
+	if (upcall_info->egress_tun_info) {
+		nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY);
+		err = ovs_nla_put_egress_tunnel_key(user_skb,
+						    upcall_info->egress_tun_info);
+		BUG_ON(err);
+		nla_nest_end(user_skb, nla);
+	}
+
 	/* Only reserve room for attribute header, packet data is added
 	 * in skb_zerocopy() */
 	if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 1c56a80d667..2bc577bf9b3 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -114,12 +114,14 @@ struct ovs_skb_cb {
  * @pid: Netlink PID to which packet should be sent.  If @pid is 0 then no
  * packet is sent and the packet is accounted in the datapath's @n_lost
  * counter.
+ * @egress_tun_info: If nonnull, becomes %OVS_PACKET_ATTR_EGRESS_TUN_KEY.
  */
 struct dp_upcall_info {
 	u8 cmd;
 	const struct sw_flow_key *key;
 	const struct nlattr *userdata;
 	u32 portid;
+	const struct ovs_tunnel_info *egress_tun_info;
 };
 
 /**
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 4962bee81a1..543b358ee57 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -37,8 +37,8 @@ struct sk_buff;
 
 /* Used to memset ovs_key_ipv4_tunnel padding. */
 #define OVS_TUNNEL_KEY_SIZE					\
-	(offsetof(struct ovs_key_ipv4_tunnel, ipv4_ttl) +	\
-	FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, ipv4_ttl))
+	(offsetof(struct ovs_key_ipv4_tunnel, tp_dst) +		\
+	 FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, tp_dst))
 
 struct ovs_key_ipv4_tunnel {
 	__be64 tun_id;
@@ -47,6 +47,8 @@ struct ovs_key_ipv4_tunnel {
 	__be16 tun_flags;
 	u8   ipv4_tos;
 	u8   ipv4_ttl;
+	__be16 tp_src;
+	__be16 tp_dst;
 } __packed __aligned(4); /* Minimize padding. */
 
 struct ovs_tunnel_info {
@@ -64,27 +66,59 @@ struct ovs_tunnel_info {
 			       FIELD_SIZEOF(struct sw_flow_key, tun_opts) - \
 			       opt_len))
 
-static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
-					  const struct iphdr *iph,
-					  __be64 tun_id, __be16 tun_flags,
-					  struct geneve_opt *opts,
-					  u8 opts_len)
+static inline void __ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+					    __be32 saddr, __be32 daddr,
+					    u8 tos, u8 ttl,
+					    __be16 tp_src,
+					    __be16 tp_dst,
+					    __be64 tun_id,
+					    __be16 tun_flags,
+					    struct geneve_opt *opts,
+					    u8 opts_len)
 {
 	tun_info->tunnel.tun_id = tun_id;
-	tun_info->tunnel.ipv4_src = iph->saddr;
-	tun_info->tunnel.ipv4_dst = iph->daddr;
-	tun_info->tunnel.ipv4_tos = iph->tos;
-	tun_info->tunnel.ipv4_ttl = iph->ttl;
+	tun_info->tunnel.ipv4_src = saddr;
+	tun_info->tunnel.ipv4_dst = daddr;
+	tun_info->tunnel.ipv4_tos = tos;
+	tun_info->tunnel.ipv4_ttl = ttl;
 	tun_info->tunnel.tun_flags = tun_flags;
 
-	/* clear struct padding. */
-	memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, 0,
-	       sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
+	/* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
+	 * the upper tunnel are used.
+	 * E.g: GRE over IPSEC, the tp_src and tp_port are zero.
+	 */
+	tun_info->tunnel.tp_src = tp_src;
+	tun_info->tunnel.tp_dst = tp_dst;
+
+	/* Clear struct padding. */
+	if (sizeof(tun_info->tunnel) != OVS_TUNNEL_KEY_SIZE)
+		memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE,
+		       0, sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
 
 	tun_info->options = opts;
 	tun_info->options_len = opts_len;
 }
 
+static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+					  const struct iphdr *iph,
+					  __be16 tp_src,
+					  __be16 tp_dst,
+					  __be64 tun_id,
+					  __be16 tun_flags,
+					  struct geneve_opt *opts,
+					  u8 opts_len)
+{
+	__ovs_flow_tun_info_init(tun_info, iph->saddr, iph->daddr,
+				 iph->tos, iph->ttl,
+				 tp_src, tp_dst,
+				 tun_id, tun_flags,
+				 opts, opts_len);
+}
+
+#define OVS_SW_FLOW_KEY_METADATA_SIZE			\
+	(offsetof(struct sw_flow_key, recirc_id) +	\
+	FIELD_SIZEOF(struct sw_flow_key, recirc_id))
+
 struct sw_flow_key {
 	u8 tun_opts[255];
 	u8 tun_opts_len;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index ed310976182..98a3e96b7d9 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -245,6 +245,24 @@ static bool match_validate(const struct sw_flow_match *match,
 	return true;
 }
 
+size_t ovs_tun_key_attr_size(void)
+{
+	/* Whenever adding new OVS_TUNNEL_KEY_ FIELDS, we should consider
+	 * updating this function.
+	 */
+	return    nla_total_size(8)    /* OVS_TUNNEL_KEY_ATTR_ID */
+		+ nla_total_size(4)    /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */
+		+ nla_total_size(4)    /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */
+		+ nla_total_size(1)    /* OVS_TUNNEL_KEY_ATTR_TOS */
+		+ nla_total_size(1)    /* OVS_TUNNEL_KEY_ATTR_TTL */
+		+ nla_total_size(0)    /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
+		+ nla_total_size(0)    /* OVS_TUNNEL_KEY_ATTR_CSUM */
+		+ nla_total_size(0)    /* OVS_TUNNEL_KEY_ATTR_OAM */
+		+ nla_total_size(256)  /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
+		+ nla_total_size(2)    /* OVS_TUNNEL_KEY_ATTR_TP_SRC */
+		+ nla_total_size(2);   /* OVS_TUNNEL_KEY_ATTR_TP_DST */
+}
+
 size_t ovs_key_attr_size(void)
 {
 	/* Whenever adding new OVS_KEY_ FIELDS, we should consider
@@ -254,15 +272,7 @@ size_t ovs_key_attr_size(void)
 
 	return    nla_total_size(4)   /* OVS_KEY_ATTR_PRIORITY */
 		+ nla_total_size(0)   /* OVS_KEY_ATTR_TUNNEL */
-		  + nla_total_size(8)   /* OVS_TUNNEL_KEY_ATTR_ID */
-		  + nla_total_size(4)   /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */
-		  + nla_total_size(4)   /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */
-		  + nla_total_size(1)   /* OVS_TUNNEL_KEY_ATTR_TOS */
-		  + nla_total_size(1)   /* OVS_TUNNEL_KEY_ATTR_TTL */
-		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
-		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_CSUM */
-		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_OAM */
-		  + nla_total_size(256) /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
+		  + ovs_tun_key_attr_size()
 		+ nla_total_size(4)   /* OVS_KEY_ATTR_IN_PORT */
 		+ nla_total_size(4)   /* OVS_KEY_ATTR_SKB_MARK */
 		+ nla_total_size(4)   /* OVS_KEY_ATTR_DP_HASH */
@@ -393,6 +403,8 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 			[OVS_TUNNEL_KEY_ATTR_TTL] = 1,
 			[OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0,
 			[OVS_TUNNEL_KEY_ATTR_CSUM] = 0,
+			[OVS_TUNNEL_KEY_ATTR_TP_SRC] = sizeof(u16),
+			[OVS_TUNNEL_KEY_ATTR_TP_DST] = sizeof(u16),
 			[OVS_TUNNEL_KEY_ATTR_OAM] = 0,
 			[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = -1,
 		};
@@ -440,6 +452,14 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 		case OVS_TUNNEL_KEY_ATTR_CSUM:
 			tun_flags |= TUNNEL_CSUM;
 			break;
+		case OVS_TUNNEL_KEY_ATTR_TP_SRC:
+			SW_FLOW_KEY_PUT(match, tun_key.tp_src,
+					nla_get_be16(a), is_mask);
+			break;
+		case OVS_TUNNEL_KEY_ATTR_TP_DST:
+			SW_FLOW_KEY_PUT(match, tun_key.tp_dst,
+					nla_get_be16(a), is_mask);
+			break;
 		case OVS_TUNNEL_KEY_ATTR_OAM:
 			tun_flags |= TUNNEL_OAM;
 			break;
@@ -548,6 +568,12 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
 	if ((output->tun_flags & TUNNEL_CSUM) &&
 	    nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM))
 		return -EMSGSIZE;
+	if (output->tp_src &&
+	    nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_SRC, output->tp_src))
+		return -EMSGSIZE;
+	if (output->tp_dst &&
+	    nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_DST, output->tp_dst))
+		return -EMSGSIZE;
 	if ((output->tun_flags & TUNNEL_OAM) &&
 	    nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
 		return -EMSGSIZE;
@@ -559,7 +585,6 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
 	return 0;
 }
 
-
 static int ipv4_tun_to_nlattr(struct sk_buff *skb,
 			      const struct ovs_key_ipv4_tunnel *output,
 			      const struct geneve_opt *tun_opts,
@@ -580,6 +605,14 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb,
 	return 0;
 }
 
+int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb,
+				  const struct ovs_tunnel_info *egress_tun_info)
+{
+	return __ipv4_tun_to_nlattr(skb, &egress_tun_info->tunnel,
+				    egress_tun_info->options,
+				    egress_tun_info->options_len);
+}
+
 static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
 				 const struct nlattr **a, bool is_mask)
 {
@@ -1653,6 +1686,7 @@ static int validate_userspace(const struct nlattr *attr)
 	static const struct nla_policy userspace_policy[OVS_USERSPACE_ATTR_MAX + 1] = {
 		[OVS_USERSPACE_ATTR_PID] = {.type = NLA_U32 },
 		[OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_UNSPEC },
+		[OVS_USERSPACE_ATTR_EGRESS_TUN_PORT] = {.type = NLA_U32 },
 	};
 	struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
 	int error;
diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h
index eb0b177300a..90bbe378550 100644
--- a/net/openvswitch/flow_netlink.h
+++ b/net/openvswitch/flow_netlink.h
@@ -37,6 +37,7 @@
 
 #include "flow.h"
 
+size_t ovs_tun_key_attr_size(void);
 size_t ovs_key_attr_size(void);
 
 void ovs_match_init(struct sw_flow_match *match,
@@ -49,6 +50,8 @@ int ovs_nla_get_flow_metadata(const struct nlattr *, struct sw_flow_key *);
 int ovs_nla_get_match(struct sw_flow_match *match,
 		      const struct nlattr *,
 		      const struct nlattr *);
+int ovs_nla_put_egress_tunnel_key(struct sk_buff *,
+				  const struct ovs_tunnel_info *);
 
 int ovs_nla_copy_actions(const struct nlattr *attr,
 			 const struct sw_flow_key *key,
diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c
index 70c9765011f..e31f19c922e 100644
--- a/net/openvswitch/vport-geneve.c
+++ b/net/openvswitch/vport-geneve.c
@@ -97,7 +97,9 @@ static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb)
 
 	key = vni_to_tunnel_id(geneveh->vni);
 
-	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key, flags,
+	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb),
+			       udp_hdr(skb)->source, udp_hdr(skb)->dest,
+			       key, flags,
 			       geneveh->options, opts_len);
 
 	ovs_vport_receive(vport, skb, &tun_info);
@@ -228,6 +230,22 @@ static const char *geneve_get_name(const struct vport *vport)
 	return geneve_port->name;
 }
 
+static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				      struct ovs_tunnel_info *egress_tun_info)
+{
+	struct geneve_port *geneve_port = geneve_vport(vport);
+	struct net *net = ovs_dp_get_net(vport->dp);
+	__be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport;
+	__be16 sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true);
+
+	/* Get tp_src and tp_dst, refert to geneve_build_header().
+	 */
+	return ovs_tunnel_get_egress_info(egress_tun_info,
+					  ovs_dp_get_net(vport->dp),
+					  OVS_CB(skb)->egress_tun_info,
+					  IPPROTO_UDP, skb->mark, sport, dport);
+}
+
 static struct vport_ops ovs_geneve_vport_ops = {
 	.type		= OVS_VPORT_TYPE_GENEVE,
 	.create		= geneve_tnl_create,
@@ -236,6 +254,7 @@ static struct vport_ops ovs_geneve_vport_ops = {
 	.get_options	= geneve_get_options,
 	.send		= geneve_tnl_send,
 	.owner          = THIS_MODULE,
+	.get_egress_tun_info	= geneve_get_egress_tun_info,
 };
 
 static int __init ovs_geneve_tnl_init(void)
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index 00270b60884..8e61a5c6ae7 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -108,7 +108,7 @@ static int gre_rcv(struct sk_buff *skb,
 		return PACKET_REJECT;
 
 	key = key_to_tunnel_id(tpi->key, tpi->seq);
-	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key,
+	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), 0, 0, key,
 			       filter_tnl_flags(tpi->flags), NULL, 0);
 
 	ovs_vport_receive(vport, skb, &tun_info);
@@ -284,12 +284,22 @@ static void gre_tnl_destroy(struct vport *vport)
 	gre_exit();
 }
 
+static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				   struct ovs_tunnel_info *egress_tun_info)
+{
+	return ovs_tunnel_get_egress_info(egress_tun_info,
+					  ovs_dp_get_net(vport->dp),
+					  OVS_CB(skb)->egress_tun_info,
+					  IPPROTO_GRE, skb->mark, 0, 0);
+}
+
 static struct vport_ops ovs_gre_vport_ops = {
 	.type		= OVS_VPORT_TYPE_GRE,
 	.create		= gre_create,
 	.destroy	= gre_tnl_destroy,
 	.get_name	= gre_get_name,
 	.send		= gre_tnl_send,
+	.get_egress_tun_info	= gre_get_egress_tun_info,
 	.owner		= THIS_MODULE,
 };
 
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 965e7500c5a..38f95a52241 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -69,7 +69,9 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
 	/* Save outer tunnel values */
 	iph = ip_hdr(skb);
 	key = cpu_to_be64(ntohl(vx_vni) >> 8);
-	ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY, NULL, 0);
+	ovs_flow_tun_info_init(&tun_info, iph,
+			       udp_hdr(skb)->source, udp_hdr(skb)->dest,
+			       key, TUNNEL_KEY, NULL, 0);
 
 	ovs_vport_receive(vport, skb, &tun_info);
 }
@@ -189,6 +191,25 @@ error:
 	return err;
 }
 
+static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				     struct ovs_tunnel_info *egress_tun_info)
+{
+	struct net *net = ovs_dp_get_net(vport->dp);
+	struct vxlan_port *vxlan_port = vxlan_vport(vport);
+	__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
+	__be16 src_port;
+	int port_min;
+	int port_max;
+
+	inet_get_local_port_range(net, &port_min, &port_max);
+	src_port = udp_flow_src_port(net, skb, 0, 0, true);
+
+	return ovs_tunnel_get_egress_info(egress_tun_info, net,
+					  OVS_CB(skb)->egress_tun_info,
+					  IPPROTO_UDP, skb->mark,
+					  src_port, dst_port);
+}
+
 static const char *vxlan_get_name(const struct vport *vport)
 {
 	struct vxlan_port *vxlan_port = vxlan_vport(vport);
@@ -202,6 +223,7 @@ static struct vport_ops ovs_vxlan_vport_ops = {
 	.get_name	= vxlan_get_name,
 	.get_options	= vxlan_get_options,
 	.send		= vxlan_tnl_send,
+	.get_egress_tun_info	= vxlan_get_egress_tun_info,
 	.owner		= THIS_MODULE,
 };
 
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 4b5dd18953a..630e81984b6 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -573,3 +573,64 @@ void ovs_vport_deferred_free(struct vport *vport)
 	call_rcu(&vport->rcu, free_vport_rcu);
 }
 EXPORT_SYMBOL_GPL(ovs_vport_deferred_free);
+
+int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
+			       struct net *net,
+			       const struct ovs_tunnel_info *tun_info,
+			       u8 ipproto,
+			       u32 skb_mark,
+			       __be16 tp_src,
+			       __be16 tp_dst)
+{
+	const struct ovs_key_ipv4_tunnel *tun_key;
+	struct rtable *rt;
+	struct flowi4 fl;
+
+	if (unlikely(!tun_info))
+		return -EINVAL;
+
+	tun_key = &tun_info->tunnel;
+
+	/* Route lookup to get srouce IP address.
+	 * The process may need to be changed if the corresponding process
+	 * in vports ops changed.
+	 */
+	memset(&fl, 0, sizeof(fl));
+	fl.daddr = tun_key->ipv4_dst;
+	fl.saddr = tun_key->ipv4_src;
+	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
+	fl.flowi4_mark = skb_mark;
+	fl.flowi4_proto = IPPROTO_GRE;
+
+	rt = ip_route_output_key(net, &fl);
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
+
+	ip_rt_put(rt);
+
+	/* Generate egress_tun_info based on tun_info,
+	 * saddr, tp_src and tp_dst
+	 */
+	__ovs_flow_tun_info_init(egress_tun_info,
+				 fl.saddr, tun_key->ipv4_dst,
+				 tun_key->ipv4_tos,
+				 tun_key->ipv4_ttl,
+				 tp_src, tp_dst,
+				 tun_key->tun_id,
+				 tun_key->tun_flags,
+				 tun_info->options,
+				 tun_info->options_len);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info);
+
+int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				  struct ovs_tunnel_info *info)
+{
+	/* get_egress_tun_info() is only implemented on tunnel ports. */
+	if (unlikely(!vport->ops->get_egress_tun_info))
+		return -EINVAL;
+
+	return vport->ops->get_egress_tun_info(vport, skb, info);
+}
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index e41c3facf79..0635d1d761e 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -58,6 +58,16 @@ u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *);
 
 int ovs_vport_send(struct vport *, struct sk_buff *);
 
+int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
+			       struct net *net,
+			       const struct ovs_tunnel_info *tun_info,
+			       u8 ipproto,
+			       u32 skb_mark,
+			       __be16 tp_src,
+			       __be16 tp_dst);
+int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				  struct ovs_tunnel_info *info);
+
 /* The following definitions are for implementers of vport devices: */
 
 struct vport_err_stats {
@@ -146,6 +156,8 @@ struct vport_parms {
  * @get_name: Get the device's name.
  * @send: Send a packet on the device.  Returns the length of the packet sent,
  * zero for dropped packets or negative for error.
+ * @get_egress_tun_info: Get the egress tunnel 5-tuple and other info for
+ * a packet.
  */
 struct vport_ops {
 	enum ovs_vport_type type;
@@ -161,6 +173,8 @@ struct vport_ops {
 	const char *(*get_name)(const struct vport *);
 
 	int (*send)(struct vport *, struct sk_buff *);
+	int (*get_egress_tun_info)(struct vport *, struct sk_buff *,
+				   struct ovs_tunnel_info *);
 
 	struct module *owner;
 	struct list_head list;
-- 
cgit v1.2.3-70-g09d2


From 05da5898a96c05e32aa9850c9cd89eef29471b13 Mon Sep 17 00:00:00 2001
From: Jarno Rajahalme <jrajahalme@nicira.com>
Date: Thu, 6 Nov 2014 07:03:05 -0800
Subject: openvswitch: Add support for OVS_FLOW_ATTR_PROBE.

This new flag is useful for suppressing error logging while probing
for datapath features using flow commands.  For backwards
compatibility reasons the commands are executed normally, but error
logging is suppressed.

Signed-off-by: Jarno Rajahalme <jrajahalme@nicira.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
---
 include/uapi/linux/openvswitch.h |   2 +
 net/openvswitch/datapath.c       |  49 ++++---
 net/openvswitch/datapath.h       |   6 +-
 net/openvswitch/flow.c           |   4 +-
 net/openvswitch/flow.h           |   2 +-
 net/openvswitch/flow_netlink.c   | 303 +++++++++++++++++++++------------------
 net/openvswitch/flow_netlink.h   |  10 +-
 7 files changed, 208 insertions(+), 168 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index cf8185661e5..3a6dcaa359b 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -457,6 +457,8 @@ enum ovs_flow_attr {
 	OVS_FLOW_ATTR_USED,      /* u64 msecs last used in monotonic time. */
 	OVS_FLOW_ATTR_CLEAR,     /* Flag to clear stats, tcp_flags, used. */
 	OVS_FLOW_ATTR_MASK,      /* Sequence of OVS_KEY_ATTR_* attributes. */
+	OVS_FLOW_ATTR_PROBE,     /* Flow operation is a feature probe, error
+				  * logging should be suppressed. */
 	__OVS_FLOW_ATTR_MAX
 };
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 65561ebb489..ab141d49bb9 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -526,6 +526,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 	struct vport *input_vport;
 	int len;
 	int err;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	err = -EINVAL;
 	if (!a[OVS_PACKET_ATTR_PACKET] || !a[OVS_PACKET_ATTR_KEY] ||
@@ -559,12 +560,12 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 		goto err_kfree_skb;
 
 	err = ovs_flow_key_extract_userspace(a[OVS_PACKET_ATTR_KEY], packet,
-					     &flow->key);
+					     &flow->key, log);
 	if (err)
 		goto err_flow_free;
 
 	err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS],
-				   &flow->key, &acts);
+				   &flow->key, &acts, log);
 	if (err)
 		goto err_flow_free;
 
@@ -855,15 +856,16 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	struct sw_flow_actions *acts;
 	struct sw_flow_match match;
 	int error;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	/* Must have key and actions. */
 	error = -EINVAL;
 	if (!a[OVS_FLOW_ATTR_KEY]) {
-		OVS_NLERR("Flow key attribute not present in new flow.\n");
+		OVS_NLERR(log, "Flow key attr not present in new flow.");
 		goto error;
 	}
 	if (!a[OVS_FLOW_ATTR_ACTIONS]) {
-		OVS_NLERR("Flow actions attribute not present in new flow.\n");
+		OVS_NLERR(log, "Flow actions attr not present in new flow.");
 		goto error;
 	}
 
@@ -878,8 +880,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 
 	/* Extract key. */
 	ovs_match_init(&match, &new_flow->unmasked_key, &mask);
-	error = ovs_nla_get_match(&match,
-				  a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]);
+	error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY],
+				  a[OVS_FLOW_ATTR_MASK], log);
 	if (error)
 		goto err_kfree_flow;
 
@@ -887,9 +889,9 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 
 	/* Validate actions. */
 	error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key,
-				     &acts);
+				     &acts, log);
 	if (error) {
-		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
+		OVS_NLERR(log, "Flow actions may not be safe on all matching packets.");
 		goto err_kfree_flow;
 	}
 
@@ -942,6 +944,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		}
 		/* The unmasked key has to be the same for flow updates. */
 		if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) {
+			/* Look for any overlapping flow. */
 			flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
 			if (!flow) {
 				error = -ENOENT;
@@ -984,16 +987,18 @@ error:
 /* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */
 static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
 						const struct sw_flow_key *key,
-						const struct sw_flow_mask *mask)
+						const struct sw_flow_mask *mask,
+						bool log)
 {
 	struct sw_flow_actions *acts;
 	struct sw_flow_key masked_key;
 	int error;
 
 	ovs_flow_mask_key(&masked_key, key, mask);
-	error = ovs_nla_copy_actions(a, &masked_key, &acts);
+	error = ovs_nla_copy_actions(a, &masked_key, &acts, log);
 	if (error) {
-		OVS_NLERR("Actions may not be safe on all matching packets.\n");
+		OVS_NLERR(log,
+			  "Actions may not be safe on all matching packets");
 		return ERR_PTR(error);
 	}
 
@@ -1012,23 +1017,25 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	struct sw_flow_actions *old_acts = NULL, *acts = NULL;
 	struct sw_flow_match match;
 	int error;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	/* Extract key. */
 	error = -EINVAL;
 	if (!a[OVS_FLOW_ATTR_KEY]) {
-		OVS_NLERR("Flow key attribute not present in set flow.\n");
+		OVS_NLERR(log, "Flow key attribute not present in set flow.");
 		goto error;
 	}
 
 	ovs_match_init(&match, &key, &mask);
-	error = ovs_nla_get_match(&match,
-				  a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]);
+	error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY],
+				  a[OVS_FLOW_ATTR_MASK], log);
 	if (error)
 		goto error;
 
 	/* Validate actions. */
 	if (a[OVS_FLOW_ATTR_ACTIONS]) {
-		acts = get_flow_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, &mask);
+		acts = get_flow_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, &mask,
+					log);
 		if (IS_ERR(acts)) {
 			error = PTR_ERR(acts);
 			goto error;
@@ -1109,14 +1116,16 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	struct sw_flow_match match;
 	int err;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	if (!a[OVS_FLOW_ATTR_KEY]) {
-		OVS_NLERR("Flow get message rejected, Key attribute missing.\n");
+		OVS_NLERR(log,
+			  "Flow get message rejected, Key attribute missing.");
 		return -EINVAL;
 	}
 
 	ovs_match_init(&match, &key, NULL);
-	err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
+	err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL, log);
 	if (err)
 		return err;
 
@@ -1157,10 +1166,12 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	struct sw_flow_match match;
 	int err;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	if (likely(a[OVS_FLOW_ATTR_KEY])) {
 		ovs_match_init(&match, &key, NULL);
-		err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
+		err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL,
+					log);
 		if (unlikely(err))
 			return err;
 	}
@@ -1250,8 +1261,10 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
 	[OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED },
+	[OVS_FLOW_ATTR_MASK] = { .type = NLA_NESTED },
 	[OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
 	[OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
+	[OVS_FLOW_ATTR_PROBE] = { .type = NLA_FLAG },
 };
 
 static const struct genl_ops dp_flow_genl_ops[] = {
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 8389c1d68e5..3ece9456307 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -199,9 +199,9 @@ void ovs_dp_notify_wq(struct work_struct *work);
 int action_fifos_init(void);
 void action_fifos_exit(void);
 
-#define OVS_NLERR(fmt, ...)					\
+#define OVS_NLERR(logging_allowed, fmt, ...)			\
 do {								\
-	if (net_ratelimit())					\
-		pr_info("netlink: " fmt, ##__VA_ARGS__);	\
+	if (logging_allowed && net_ratelimit())			\
+		pr_info("netlink: " fmt "\n", ##__VA_ARGS__);	\
 } while (0)
 #endif /* datapath.h */
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 25e9abcd51f..70bef2ab7f2 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -712,12 +712,12 @@ int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info,
 
 int ovs_flow_key_extract_userspace(const struct nlattr *attr,
 				   struct sk_buff *skb,
-				   struct sw_flow_key *key)
+				   struct sw_flow_key *key, bool log)
 {
 	int err;
 
 	/* Extract metadata from netlink attributes. */
-	err = ovs_nla_get_flow_metadata(attr, key);
+	err = ovs_nla_get_flow_metadata(attr, key, log);
 	if (err)
 		return err;
 
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 9e0a787c862..a8b30f33438 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -257,6 +257,6 @@ int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info,
 /* Extract key from packet coming from userspace. */
 int ovs_flow_key_extract_userspace(const struct nlattr *attr,
 				   struct sk_buff *skb,
-				   struct sw_flow_key *key);
+				   struct sw_flow_key *key, bool log);
 
 #endif /* flow.h */
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 98a3e96b7d9..c0d066def22 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -112,7 +112,7 @@ static void update_range(struct sw_flow_match *match,
 	} while (0)
 
 static bool match_validate(const struct sw_flow_match *match,
-			   u64 key_attrs, u64 mask_attrs)
+			   u64 key_attrs, u64 mask_attrs, bool log)
 {
 	u64 key_expected = 1 << OVS_KEY_ATTR_ETHERNET;
 	u64 mask_allowed = key_attrs;  /* At most allow all key attributes */
@@ -230,15 +230,17 @@ static bool match_validate(const struct sw_flow_match *match,
 
 	if ((key_attrs & key_expected) != key_expected) {
 		/* Key attributes check failed. */
-		OVS_NLERR("Missing expected key attributes (key_attrs=%llx, expected=%llx).\n",
-				(unsigned long long)key_attrs, (unsigned long long)key_expected);
+		OVS_NLERR(log, "Missing key (keys=%llx, expected=%llx)",
+			  (unsigned long long)key_attrs,
+			  (unsigned long long)key_expected);
 		return false;
 	}
 
 	if ((mask_attrs & mask_allowed) != mask_attrs) {
 		/* Mask attributes check failed. */
-		OVS_NLERR("Contain more than allowed mask fields (mask_attrs=%llx, mask_allowed=%llx).\n",
-				(unsigned long long)mask_attrs, (unsigned long long)mask_allowed);
+		OVS_NLERR(log, "Unexpected mask (mask=%llx, allowed=%llx)",
+			  (unsigned long long)mask_attrs,
+			  (unsigned long long)mask_allowed);
 		return false;
 	}
 
@@ -328,7 +330,7 @@ static bool is_all_zero(const u8 *fp, size_t size)
 
 static int __parse_flow_nlattrs(const struct nlattr *attr,
 				const struct nlattr *a[],
-				u64 *attrsp, bool nz)
+				u64 *attrsp, bool log, bool nz)
 {
 	const struct nlattr *nla;
 	u64 attrs;
@@ -340,21 +342,20 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
 		int expected_len;
 
 		if (type > OVS_KEY_ATTR_MAX) {
-			OVS_NLERR("Unknown key attribute (type=%d, max=%d).\n",
+			OVS_NLERR(log, "Key type %d is out of range max %d",
 				  type, OVS_KEY_ATTR_MAX);
 			return -EINVAL;
 		}
 
 		if (attrs & (1 << type)) {
-			OVS_NLERR("Duplicate key attribute (type %d).\n", type);
+			OVS_NLERR(log, "Duplicate key (type %d).", type);
 			return -EINVAL;
 		}
 
 		expected_len = ovs_key_lens[type];
 		if (nla_len(nla) != expected_len && expected_len != -1) {
-			OVS_NLERR("Key attribute has unexpected length (type=%d"
-				  ", length=%d, expected=%d).\n", type,
-				  nla_len(nla), expected_len);
+			OVS_NLERR(log, "Key %d has unexpected len %d expected %d",
+				  type, nla_len(nla), expected_len);
 			return -EINVAL;
 		}
 
@@ -364,7 +365,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
 		}
 	}
 	if (rem) {
-		OVS_NLERR("Message has %d unknown bytes.\n", rem);
+		OVS_NLERR(log, "Message has %d unknown bytes.", rem);
 		return -EINVAL;
 	}
 
@@ -373,28 +374,84 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
 }
 
 static int parse_flow_mask_nlattrs(const struct nlattr *attr,
-				   const struct nlattr *a[], u64 *attrsp)
+				   const struct nlattr *a[], u64 *attrsp,
+				   bool log)
 {
-	return __parse_flow_nlattrs(attr, a, attrsp, true);
+	return __parse_flow_nlattrs(attr, a, attrsp, log, true);
 }
 
 static int parse_flow_nlattrs(const struct nlattr *attr,
-			      const struct nlattr *a[], u64 *attrsp)
+			      const struct nlattr *a[], u64 *attrsp,
+			      bool log)
 {
-	return __parse_flow_nlattrs(attr, a, attrsp, false);
+	return __parse_flow_nlattrs(attr, a, attrsp, log, false);
+}
+
+static int genev_tun_opt_from_nlattr(const struct nlattr *a,
+				     struct sw_flow_match *match, bool is_mask,
+				     bool log)
+{
+	unsigned long opt_key_offset;
+
+	if (nla_len(a) > sizeof(match->key->tun_opts)) {
+		OVS_NLERR(log, "Geneve option length err (len %d, max %zu).",
+			  nla_len(a), sizeof(match->key->tun_opts));
+		return -EINVAL;
+	}
+
+	if (nla_len(a) % 4 != 0) {
+		OVS_NLERR(log, "Geneve opt len %d is not a multiple of 4.",
+			  nla_len(a));
+		return -EINVAL;
+	}
+
+	/* We need to record the length of the options passed
+	 * down, otherwise packets with the same format but
+	 * additional options will be silently matched.
+	 */
+	if (!is_mask) {
+		SW_FLOW_KEY_PUT(match, tun_opts_len, nla_len(a),
+				false);
+	} else {
+		/* This is somewhat unusual because it looks at
+		 * both the key and mask while parsing the
+		 * attributes (and by extension assumes the key
+		 * is parsed first). Normally, we would verify
+		 * that each is the correct length and that the
+		 * attributes line up in the validate function.
+		 * However, that is difficult because this is
+		 * variable length and we won't have the
+		 * information later.
+		 */
+		if (match->key->tun_opts_len != nla_len(a)) {
+			OVS_NLERR(log, "Geneve option len %d != mask len %d",
+				  match->key->tun_opts_len, nla_len(a));
+			return -EINVAL;
+		}
+
+		SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true);
+	}
+
+	opt_key_offset = (unsigned long)GENEVE_OPTS((struct sw_flow_key *)0,
+						    nla_len(a));
+	SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, nla_data(a),
+				  nla_len(a), is_mask);
+	return 0;
 }
 
 static int ipv4_tun_from_nlattr(const struct nlattr *attr,
-				struct sw_flow_match *match, bool is_mask)
+				struct sw_flow_match *match, bool is_mask,
+				bool log)
 {
 	struct nlattr *a;
 	int rem;
 	bool ttl = false;
 	__be16 tun_flags = 0;
-	unsigned long opt_key_offset;
 
 	nla_for_each_nested(a, attr, rem) {
 		int type = nla_type(a);
+		int err;
+
 		static const u32 ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = {
 			[OVS_TUNNEL_KEY_ATTR_ID] = sizeof(u64),
 			[OVS_TUNNEL_KEY_ATTR_IPV4_SRC] = sizeof(u32),
@@ -410,15 +467,14 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 		};
 
 		if (type > OVS_TUNNEL_KEY_ATTR_MAX) {
-			OVS_NLERR("Unknown IPv4 tunnel attribute (type=%d, max=%d).\n",
-			type, OVS_TUNNEL_KEY_ATTR_MAX);
+			OVS_NLERR(log, "Tunnel attr %d out of range max %d",
+				  type, OVS_TUNNEL_KEY_ATTR_MAX);
 			return -EINVAL;
 		}
 
 		if (ovs_tunnel_key_lens[type] != nla_len(a) &&
 		    ovs_tunnel_key_lens[type] != -1) {
-			OVS_NLERR("IPv4 tunnel attribute type has unexpected "
-				  " length (type=%d, length=%d, expected=%d).\n",
+			OVS_NLERR(log, "Tunnel attr %d has unexpected len %d expected %d",
 				  type, nla_len(a), ovs_tunnel_key_lens[type]);
 			return -EINVAL;
 		}
@@ -464,58 +520,14 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 			tun_flags |= TUNNEL_OAM;
 			break;
 		case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS:
-			tun_flags |= TUNNEL_OPTIONS_PRESENT;
-			if (nla_len(a) > sizeof(match->key->tun_opts)) {
-				OVS_NLERR("Geneve option length exceeds maximum size (len %d, max %zu).\n",
-					  nla_len(a),
-					  sizeof(match->key->tun_opts));
-				return -EINVAL;
-			}
-
-			if (nla_len(a) % 4 != 0) {
-				OVS_NLERR("Geneve option length is not a multiple of 4 (len %d).\n",
-					  nla_len(a));
-				return -EINVAL;
-			}
-
-			/* We need to record the length of the options passed
-			 * down, otherwise packets with the same format but
-			 * additional options will be silently matched.
-			 */
-			if (!is_mask) {
-				SW_FLOW_KEY_PUT(match, tun_opts_len, nla_len(a),
-						false);
-			} else {
-				/* This is somewhat unusual because it looks at
-				 * both the key and mask while parsing the
-				 * attributes (and by extension assumes the key
-				 * is parsed first). Normally, we would verify
-				 * that each is the correct length and that the
-				 * attributes line up in the validate function.
-				 * However, that is difficult because this is
-				 * variable length and we won't have the
-				 * information later.
-				 */
-				if (match->key->tun_opts_len != nla_len(a)) {
-					OVS_NLERR("Geneve option key length (%d) is different from mask length (%d).",
-						  match->key->tun_opts_len,
-						  nla_len(a));
-					return -EINVAL;
-				}
-
-				SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff,
-						true);
-			}
+			err = genev_tun_opt_from_nlattr(a, match, is_mask, log);
+			if (err)
+				return err;
 
-			opt_key_offset = (unsigned long)GENEVE_OPTS(
-					  (struct sw_flow_key *)0,
-					  nla_len(a));
-			SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset,
-						  nla_data(a), nla_len(a),
-						  is_mask);
+			tun_flags |= TUNNEL_OPTIONS_PRESENT;
 			break;
 		default:
-			OVS_NLERR("Unknown IPv4 tunnel attribute (%d).\n",
+			OVS_NLERR(log, "Unknown IPv4 tunnel attribute %d",
 				  type);
 			return -EINVAL;
 		}
@@ -524,18 +536,19 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 	SW_FLOW_KEY_PUT(match, tun_key.tun_flags, tun_flags, is_mask);
 
 	if (rem > 0) {
-		OVS_NLERR("IPv4 tunnel attribute has %d unknown bytes.\n", rem);
+		OVS_NLERR(log, "IPv4 tunnel attribute has %d unknown bytes.",
+			  rem);
 		return -EINVAL;
 	}
 
 	if (!is_mask) {
 		if (!match->key->tun_key.ipv4_dst) {
-			OVS_NLERR("IPv4 tunnel destination address is zero.\n");
+			OVS_NLERR(log, "IPv4 tunnel dst address is zero");
 			return -EINVAL;
 		}
 
 		if (!ttl) {
-			OVS_NLERR("IPv4 tunnel TTL not specified.\n");
+			OVS_NLERR(log, "IPv4 tunnel TTL not specified.");
 			return -EINVAL;
 		}
 	}
@@ -614,7 +627,8 @@ int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb,
 }
 
 static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
-				 const struct nlattr **a, bool is_mask)
+				 const struct nlattr **a, bool is_mask,
+				 bool log)
 {
 	if (*attrs & (1 << OVS_KEY_ATTR_DP_HASH)) {
 		u32 hash_val = nla_get_u32(a[OVS_KEY_ATTR_DP_HASH]);
@@ -642,7 +656,7 @@ static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
 		if (is_mask) {
 			in_port = 0xffffffff; /* Always exact match in_port. */
 		} else if (in_port >= DP_MAX_PORTS) {
-			OVS_NLERR("Port (%d) exceeds maximum allowable (%d).\n",
+			OVS_NLERR(log, "Port %d exceeds max allowable %d",
 				  in_port, DP_MAX_PORTS);
 			return -EINVAL;
 		}
@@ -661,7 +675,7 @@ static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
 	}
 	if (*attrs & (1 << OVS_KEY_ATTR_TUNNEL)) {
 		if (ipv4_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match,
-					 is_mask))
+					 is_mask, log))
 			return -EINVAL;
 		*attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL);
 	}
@@ -669,11 +683,12 @@ static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
 }
 
 static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
-				const struct nlattr **a, bool is_mask)
+				const struct nlattr **a, bool is_mask,
+				bool log)
 {
 	int err;
 
-	err = metadata_from_nlattrs(match, &attrs, a, is_mask);
+	err = metadata_from_nlattrs(match, &attrs, a, is_mask, log);
 	if (err)
 		return err;
 
@@ -694,9 +709,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 		tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
 		if (!(tci & htons(VLAN_TAG_PRESENT))) {
 			if (is_mask)
-				OVS_NLERR("VLAN TCI mask does not have exact match for VLAN_TAG_PRESENT bit.\n");
+				OVS_NLERR(log, "VLAN TCI mask does not have exact match for VLAN_TAG_PRESENT bit.");
 			else
-				OVS_NLERR("VLAN TCI does not have VLAN_TAG_PRESENT bit set.\n");
+				OVS_NLERR(log, "VLAN TCI does not have VLAN_TAG_PRESENT bit set.");
 
 			return -EINVAL;
 		}
@@ -713,8 +728,8 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 			/* Always exact match EtherType. */
 			eth_type = htons(0xffff);
 		} else if (ntohs(eth_type) < ETH_P_802_3_MIN) {
-			OVS_NLERR("EtherType is less than minimum (type=%x, min=%x).\n",
-					ntohs(eth_type), ETH_P_802_3_MIN);
+			OVS_NLERR(log, "EtherType %x is less than min %x",
+				  ntohs(eth_type), ETH_P_802_3_MIN);
 			return -EINVAL;
 		}
 
@@ -729,8 +744,8 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 
 		ipv4_key = nla_data(a[OVS_KEY_ATTR_IPV4]);
 		if (!is_mask && ipv4_key->ipv4_frag > OVS_FRAG_TYPE_MAX) {
-			OVS_NLERR("Unknown IPv4 fragment type (value=%d, max=%d).\n",
-				ipv4_key->ipv4_frag, OVS_FRAG_TYPE_MAX);
+			OVS_NLERR(log, "IPv4 frag type %d is out of range max %d",
+				  ipv4_key->ipv4_frag, OVS_FRAG_TYPE_MAX);
 			return -EINVAL;
 		}
 		SW_FLOW_KEY_PUT(match, ip.proto,
@@ -753,8 +768,8 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 
 		ipv6_key = nla_data(a[OVS_KEY_ATTR_IPV6]);
 		if (!is_mask && ipv6_key->ipv6_frag > OVS_FRAG_TYPE_MAX) {
-			OVS_NLERR("Unknown IPv6 fragment type (value=%d, max=%d).\n",
-				ipv6_key->ipv6_frag, OVS_FRAG_TYPE_MAX);
+			OVS_NLERR(log, "IPv6 frag type %d is out of range max %d",
+				  ipv6_key->ipv6_frag, OVS_FRAG_TYPE_MAX);
 			return -EINVAL;
 		}
 		SW_FLOW_KEY_PUT(match, ipv6.label,
@@ -784,7 +799,7 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 
 		arp_key = nla_data(a[OVS_KEY_ATTR_ARP]);
 		if (!is_mask && (arp_key->arp_op & htons(0xff00))) {
-			OVS_NLERR("Unknown ARP opcode (opcode=%d).\n",
+			OVS_NLERR(log, "Unknown ARP opcode (opcode=%d).",
 				  arp_key->arp_op);
 			return -EINVAL;
 		}
@@ -885,7 +900,7 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 	}
 
 	if (attrs != 0) {
-		OVS_NLERR("Unknown key attributes (%llx).\n",
+		OVS_NLERR(log, "Unknown key attributes %llx",
 			  (unsigned long long)attrs);
 		return -EINVAL;
 	}
@@ -926,10 +941,14 @@ static void mask_set_nlattr(struct nlattr *attr, u8 val)
  * of this flow.
  * @mask: Optional. Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink
  * attribute specifies the mask field of the wildcarded flow.
+ * @log: Boolean to allow kernel error logging.  Normally true, but when
+ * probing for feature compatibility this should be passed in as false to
+ * suppress unnecessary error logging.
  */
 int ovs_nla_get_match(struct sw_flow_match *match,
 		      const struct nlattr *nla_key,
-		      const struct nlattr *nla_mask)
+		      const struct nlattr *nla_mask,
+		      bool log)
 {
 	const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
 	const struct nlattr *encap;
@@ -939,7 +958,7 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 	bool encap_valid = false;
 	int err;
 
-	err = parse_flow_nlattrs(nla_key, a, &key_attrs);
+	err = parse_flow_nlattrs(nla_key, a, &key_attrs, log);
 	if (err)
 		return err;
 
@@ -950,7 +969,7 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 
 		if (!((key_attrs & (1 << OVS_KEY_ATTR_VLAN)) &&
 		      (key_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) {
-			OVS_NLERR("Invalid Vlan frame.\n");
+			OVS_NLERR(log, "Invalid Vlan frame.");
 			return -EINVAL;
 		}
 
@@ -961,22 +980,22 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 		encap_valid = true;
 
 		if (tci & htons(VLAN_TAG_PRESENT)) {
-			err = parse_flow_nlattrs(encap, a, &key_attrs);
+			err = parse_flow_nlattrs(encap, a, &key_attrs, log);
 			if (err)
 				return err;
 		} else if (!tci) {
 			/* Corner case for truncated 802.1Q header. */
 			if (nla_len(encap)) {
-				OVS_NLERR("Truncated 802.1Q header has non-zero encap attribute.\n");
+				OVS_NLERR(log, "Truncated 802.1Q header has non-zero encap attribute.");
 				return -EINVAL;
 			}
 		} else {
-			OVS_NLERR("Encap attribute is set for a non-VLAN frame.\n");
+			OVS_NLERR(log, "Encap attr is set for non-VLAN frame");
 			return  -EINVAL;
 		}
 	}
 
-	err = ovs_key_from_nlattrs(match, key_attrs, a, false);
+	err = ovs_key_from_nlattrs(match, key_attrs, a, false, log);
 	if (err)
 		return err;
 
@@ -1010,7 +1029,7 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 			nla_mask = newmask;
 		}
 
-		err = parse_flow_mask_nlattrs(nla_mask, a, &mask_attrs);
+		err = parse_flow_mask_nlattrs(nla_mask, a, &mask_attrs, log);
 		if (err)
 			goto free_newmask;
 
@@ -1022,7 +1041,7 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 			__be16 tci = 0;
 
 			if (!encap_valid) {
-				OVS_NLERR("Encap mask attribute is set for non-VLAN frame.\n");
+				OVS_NLERR(log, "Encap mask attribute is set for non-VLAN frame.");
 				err = -EINVAL;
 				goto free_newmask;
 			}
@@ -1034,12 +1053,13 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 			if (eth_type == htons(0xffff)) {
 				mask_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
 				encap = a[OVS_KEY_ATTR_ENCAP];
-				err = parse_flow_mask_nlattrs(encap, a, &mask_attrs);
+				err = parse_flow_mask_nlattrs(encap, a,
+							      &mask_attrs, log);
 				if (err)
 					goto free_newmask;
 			} else {
-				OVS_NLERR("VLAN frames must have an exact match on the TPID (mask=%x).\n",
-						ntohs(eth_type));
+				OVS_NLERR(log, "VLAN frames must have an exact match on the TPID (mask=%x).",
+					  ntohs(eth_type));
 				err = -EINVAL;
 				goto free_newmask;
 			}
@@ -1048,18 +1068,19 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 				tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
 
 			if (!(tci & htons(VLAN_TAG_PRESENT))) {
-				OVS_NLERR("VLAN tag present bit must have an exact match (tci_mask=%x).\n", ntohs(tci));
+				OVS_NLERR(log, "VLAN tag present bit must have an exact match (tci_mask=%x).",
+					  ntohs(tci));
 				err = -EINVAL;
 				goto free_newmask;
 			}
 		}
 
-		err = ovs_key_from_nlattrs(match, mask_attrs, a, true);
+		err = ovs_key_from_nlattrs(match, mask_attrs, a, true, log);
 		if (err)
 			goto free_newmask;
 	}
 
-	if (!match_validate(match, key_attrs, mask_attrs))
+	if (!match_validate(match, key_attrs, mask_attrs, log))
 		err = -EINVAL;
 
 free_newmask:
@@ -1072,6 +1093,9 @@ free_newmask:
  * @key: Receives extracted in_port, priority, tun_key and skb_mark.
  * @attr: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
  * sequence.
+ * @log: Boolean to allow kernel error logging.  Normally true, but when
+ * probing for feature compatibility this should be passed in as false to
+ * suppress unnecessary error logging.
  *
  * This parses a series of Netlink attributes that form a flow key, which must
  * take the same form accepted by flow_from_nlattrs(), but only enough of it to
@@ -1080,14 +1104,15 @@ free_newmask:
  */
 
 int ovs_nla_get_flow_metadata(const struct nlattr *attr,
-			      struct sw_flow_key *key)
+			      struct sw_flow_key *key,
+			      bool log)
 {
 	const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
 	struct sw_flow_match match;
 	u64 attrs = 0;
 	int err;
 
-	err = parse_flow_nlattrs(attr, a, &attrs);
+	err = parse_flow_nlattrs(attr, a, &attrs, log);
 	if (err)
 		return -EINVAL;
 
@@ -1096,7 +1121,7 @@ int ovs_nla_get_flow_metadata(const struct nlattr *attr,
 
 	key->phy.in_port = DP_MAX_PORTS;
 
-	return metadata_from_nlattrs(&match, &attrs, a, false);
+	return metadata_from_nlattrs(&match, &attrs, a, false, log);
 }
 
 int ovs_nla_put_flow(const struct sw_flow_key *swkey,
@@ -1316,12 +1341,12 @@ nla_put_failure:
 
 #define MAX_ACTIONS_BUFSIZE	(32 * 1024)
 
-static struct sw_flow_actions *nla_alloc_flow_actions(int size)
+static struct sw_flow_actions *nla_alloc_flow_actions(int size, bool log)
 {
 	struct sw_flow_actions *sfa;
 
 	if (size > MAX_ACTIONS_BUFSIZE) {
-		OVS_NLERR("Flow action size (%u bytes) exceeds maximum", size);
+		OVS_NLERR(log, "Flow action size %u bytes exceeds max", size);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -1341,7 +1366,7 @@ void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
 }
 
 static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
-				       int attr_len)
+				       int attr_len, bool log)
 {
 
 	struct sw_flow_actions *acts;
@@ -1361,7 +1386,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
 		new_acts_size = MAX_ACTIONS_BUFSIZE;
 	}
 
-	acts = nla_alloc_flow_actions(new_acts_size);
+	acts = nla_alloc_flow_actions(new_acts_size, log);
 	if (IS_ERR(acts))
 		return (void *)acts;
 
@@ -1376,11 +1401,11 @@ out:
 }
 
 static struct nlattr *__add_action(struct sw_flow_actions **sfa,
-				   int attrtype, void *data, int len)
+				   int attrtype, void *data, int len, bool log)
 {
 	struct nlattr *a;
 
-	a = reserve_sfa_size(sfa, nla_attr_size(len));
+	a = reserve_sfa_size(sfa, nla_attr_size(len), log);
 	if (IS_ERR(a))
 		return a;
 
@@ -1395,11 +1420,11 @@ static struct nlattr *__add_action(struct sw_flow_actions **sfa,
 }
 
 static int add_action(struct sw_flow_actions **sfa, int attrtype,
-		      void *data, int len)
+		      void *data, int len, bool log)
 {
 	struct nlattr *a;
 
-	a = __add_action(sfa, attrtype, data, len);
+	a = __add_action(sfa, attrtype, data, len, log);
 	if (IS_ERR(a))
 		return PTR_ERR(a);
 
@@ -1407,12 +1432,12 @@ static int add_action(struct sw_flow_actions **sfa, int attrtype,
 }
 
 static inline int add_nested_action_start(struct sw_flow_actions **sfa,
-					  int attrtype)
+					  int attrtype, bool log)
 {
 	int used = (*sfa)->actions_len;
 	int err;
 
-	err = add_action(sfa, attrtype, NULL, 0);
+	err = add_action(sfa, attrtype, NULL, 0, log);
 	if (err)
 		return err;
 
@@ -1431,12 +1456,12 @@ static inline void add_nested_action_end(struct sw_flow_actions *sfa,
 static int __ovs_nla_copy_actions(const struct nlattr *attr,
 				  const struct sw_flow_key *key,
 				  int depth, struct sw_flow_actions **sfa,
-				  __be16 eth_type, __be16 vlan_tci);
+				  __be16 eth_type, __be16 vlan_tci, bool log);
 
 static int validate_and_copy_sample(const struct nlattr *attr,
 				    const struct sw_flow_key *key, int depth,
 				    struct sw_flow_actions **sfa,
-				    __be16 eth_type, __be16 vlan_tci)
+				    __be16 eth_type, __be16 vlan_tci, bool log)
 {
 	const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
 	const struct nlattr *probability, *actions;
@@ -1462,19 +1487,19 @@ static int validate_and_copy_sample(const struct nlattr *attr,
 		return -EINVAL;
 
 	/* validation done, copy sample action. */
-	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE);
+	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE, log);
 	if (start < 0)
 		return start;
 	err = add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY,
-			 nla_data(probability), sizeof(u32));
+			 nla_data(probability), sizeof(u32), log);
 	if (err)
 		return err;
-	st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS);
+	st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS, log);
 	if (st_acts < 0)
 		return st_acts;
 
 	err = __ovs_nla_copy_actions(actions, key, depth + 1, sfa,
-				     eth_type, vlan_tci);
+				     eth_type, vlan_tci, log);
 	if (err)
 		return err;
 
@@ -1511,7 +1536,7 @@ void ovs_match_init(struct sw_flow_match *match,
 }
 
 static int validate_and_copy_set_tun(const struct nlattr *attr,
-				     struct sw_flow_actions **sfa)
+				     struct sw_flow_actions **sfa, bool log)
 {
 	struct sw_flow_match match;
 	struct sw_flow_key key;
@@ -1520,7 +1545,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	int err, start;
 
 	ovs_match_init(&match, &key, NULL);
-	err = ipv4_tun_from_nlattr(nla_data(attr), &match, false);
+	err = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log);
 	if (err)
 		return err;
 
@@ -1549,12 +1574,12 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 		key.tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0;
 	};
 
-	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET);
+	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET, log);
 	if (start < 0)
 		return start;
 
 	a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL,
-			 sizeof(*tun_info) + key.tun_opts_len);
+			 sizeof(*tun_info) + key.tun_opts_len, log);
 	if (IS_ERR(a))
 		return PTR_ERR(a);
 
@@ -1582,7 +1607,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 static int validate_set(const struct nlattr *a,
 			const struct sw_flow_key *flow_key,
 			struct sw_flow_actions **sfa,
-			bool *set_tun, __be16 eth_type)
+			bool *set_tun, __be16 eth_type, bool log)
 {
 	const struct nlattr *ovs_key = nla_data(a);
 	int key_type = nla_type(ovs_key);
@@ -1611,7 +1636,7 @@ static int validate_set(const struct nlattr *a,
 			return -EINVAL;
 
 		*set_tun = true;
-		err = validate_and_copy_set_tun(a, sfa);
+		err = validate_and_copy_set_tun(a, sfa, log);
 		if (err)
 			return err;
 		break;
@@ -1704,12 +1729,12 @@ static int validate_userspace(const struct nlattr *attr)
 }
 
 static int copy_action(const struct nlattr *from,
-		       struct sw_flow_actions **sfa)
+		       struct sw_flow_actions **sfa, bool log)
 {
 	int totlen = NLA_ALIGN(from->nla_len);
 	struct nlattr *to;
 
-	to = reserve_sfa_size(sfa, from->nla_len);
+	to = reserve_sfa_size(sfa, from->nla_len, log);
 	if (IS_ERR(to))
 		return PTR_ERR(to);
 
@@ -1720,7 +1745,7 @@ static int copy_action(const struct nlattr *from,
 static int __ovs_nla_copy_actions(const struct nlattr *attr,
 				  const struct sw_flow_key *key,
 				  int depth, struct sw_flow_actions **sfa,
-				  __be16 eth_type, __be16 vlan_tci)
+				  __be16 eth_type, __be16 vlan_tci, bool log)
 {
 	const struct nlattr *a;
 	bool out_tnl_port = false;
@@ -1843,7 +1868,7 @@ static int __ovs_nla_copy_actions(const struct nlattr *attr,
 
 		case OVS_ACTION_ATTR_SET:
 			err = validate_set(a, key, sfa,
-					   &out_tnl_port, eth_type);
+					   &out_tnl_port, eth_type, log);
 			if (err)
 				return err;
 
@@ -1852,18 +1877,18 @@ static int __ovs_nla_copy_actions(const struct nlattr *attr,
 
 		case OVS_ACTION_ATTR_SAMPLE:
 			err = validate_and_copy_sample(a, key, depth, sfa,
-						       eth_type, vlan_tci);
+						       eth_type, vlan_tci, log);
 			if (err)
 				return err;
 			skip_copy = true;
 			break;
 
 		default:
-			OVS_NLERR("Unknown tunnel attribute (%d).\n", type);
+			OVS_NLERR(log, "Unknown Action type %d", type);
 			return -EINVAL;
 		}
 		if (!skip_copy) {
-			err = copy_action(a, sfa);
+			err = copy_action(a, sfa, log);
 			if (err)
 				return err;
 		}
@@ -1877,16 +1902,16 @@ static int __ovs_nla_copy_actions(const struct nlattr *attr,
 
 int ovs_nla_copy_actions(const struct nlattr *attr,
 			 const struct sw_flow_key *key,
-			 struct sw_flow_actions **sfa)
+			 struct sw_flow_actions **sfa, bool log)
 {
 	int err;
 
-	*sfa = nla_alloc_flow_actions(nla_len(attr));
+	*sfa = nla_alloc_flow_actions(nla_len(attr), log);
 	if (IS_ERR(*sfa))
 		return PTR_ERR(*sfa);
 
 	err = __ovs_nla_copy_actions(attr, key, 0, sfa, key->eth.type,
-				     key->eth.tci);
+				     key->eth.tci, log);
 	if (err)
 		kfree(*sfa);
 
diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h
index 90bbe378550..577f12be345 100644
--- a/net/openvswitch/flow_netlink.h
+++ b/net/openvswitch/flow_netlink.h
@@ -45,17 +45,17 @@ void ovs_match_init(struct sw_flow_match *match,
 
 int ovs_nla_put_flow(const struct sw_flow_key *,
 		     const struct sw_flow_key *, struct sk_buff *);
-int ovs_nla_get_flow_metadata(const struct nlattr *, struct sw_flow_key *);
+int ovs_nla_get_flow_metadata(const struct nlattr *, struct sw_flow_key *,
+			      bool log);
 
-int ovs_nla_get_match(struct sw_flow_match *match,
-		      const struct nlattr *,
-		      const struct nlattr *);
+int ovs_nla_get_match(struct sw_flow_match *, const struct nlattr *key,
+		      const struct nlattr *mask, bool log);
 int ovs_nla_put_egress_tunnel_key(struct sk_buff *,
 				  const struct ovs_tunnel_info *);
 
 int ovs_nla_copy_actions(const struct nlattr *attr,
 			 const struct sw_flow_key *key,
-			 struct sw_flow_actions **sfa);
+			 struct sw_flow_actions **sfa, bool log);
 int ovs_nla_put_actions(const struct nlattr *attr,
 			int len, struct sk_buff *skb);
 
-- 
cgit v1.2.3-70-g09d2


From 6bab3596bbede980c067eaeaf6a470c262888dac Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 20 Oct 2014 16:01:33 +0200
Subject: quota: Remove const from function declarations

We don't use const through VFS too much so just remove it from quota
function declarations.

Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/quota/dquot.c         | 4 ++--
 include/linux/quotaops.h | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index a180b1d1a6c..b1910c915c9 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1643,7 +1643,7 @@ EXPORT_SYMBOL(__dquot_alloc_space);
 /*
  * This operation can block, but only after everything is updated
  */
-int dquot_alloc_inode(const struct inode *inode)
+int dquot_alloc_inode(struct inode *inode)
 {
 	int cnt, ret = 0, index;
 	struct dquot_warn warn[MAXQUOTAS];
@@ -1784,7 +1784,7 @@ EXPORT_SYMBOL(__dquot_free_space);
 /*
  * This operation can block, but only after everything is updated
  */
-void dquot_free_inode(const struct inode *inode)
+void dquot_free_inode(struct inode *inode)
 {
 	unsigned int cnt;
 	struct dquot_warn warn[MAXQUOTAS];
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 1d3eee594cd..f23538a6e41 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -64,10 +64,10 @@ void dquot_destroy(struct dquot *dquot);
 int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags);
 void __dquot_free_space(struct inode *inode, qsize_t number, int flags);
 
-int dquot_alloc_inode(const struct inode *inode);
+int dquot_alloc_inode(struct inode *inode);
 
 int dquot_claim_space_nodirty(struct inode *inode, qsize_t number);
-void dquot_free_inode(const struct inode *inode);
+void dquot_free_inode(struct inode *inode);
 void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number);
 
 int dquot_disable(struct super_block *sb, int type, unsigned int flags);
@@ -213,12 +213,12 @@ static inline void dquot_drop(struct inode *inode)
 {
 }
 
-static inline int dquot_alloc_inode(const struct inode *inode)
+static inline int dquot_alloc_inode(struct inode *inode)
 {
 	return 0;
 }
 
-static inline void dquot_free_inode(const struct inode *inode)
+static inline void dquot_free_inode(struct inode *inode)
 {
 }
 
-- 
cgit v1.2.3-70-g09d2


From 2c5f648aa24a7c8f0668d8ce5722d69da5bef739 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 30 Sep 2014 10:43:09 +0200
Subject: quota: Allow each filesystem to specify which quota types it supports

Currently all filesystems supporting VFS quota support user and group
quotas. With introduction of project quotas this is going to change so
make sure filesystem isn't called for quota type it doesn't support by
introduction of a bitmask determining which quota types each filesystem
supports.

Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/quota/quota.c      | 13 +++++++++++--
 fs/super.c            |  6 ++++++
 include/linux/fs.h    |  1 +
 include/linux/quota.h |  5 +++++
 4 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 75621649dbd..2aa4151f99d 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -47,8 +47,11 @@ static int check_quotactl_permission(struct super_block *sb, int type, int cmd,
 
 static void quota_sync_one(struct super_block *sb, void *arg)
 {
-	if (sb->s_qcop && sb->s_qcop->quota_sync)
-		sb->s_qcop->quota_sync(sb, *(int *)arg);
+	int type = *(int *)arg;
+
+	if (sb->s_qcop && sb->s_qcop->quota_sync &&
+	    (sb->s_quota_types & (1 << type)))
+		sb->s_qcop->quota_sync(sb, type);
 }
 
 static int quota_sync_all(int type)
@@ -297,8 +300,14 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 
 	if (type >= (XQM_COMMAND(cmd) ? XQM_MAXQUOTAS : MAXQUOTAS))
 		return -EINVAL;
+	/*
+	 * Quota not supported on this fs? Check this before s_quota_types
+	 * since they needn't be set if quota is not supported at all.
+	 */
 	if (!sb->s_qcop)
 		return -ENOSYS;
+	if (!(sb->s_quota_types & (1 << type)))
+		return -EINVAL;
 
 	ret = check_quotactl_permission(sb, type, cmd, id);
 	if (ret < 0)
diff --git a/fs/super.c b/fs/super.c
index eae088f6aaa..4512281df8f 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -218,6 +218,12 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	atomic_set(&s->s_active, 1);
 	mutex_init(&s->s_vfs_rename_mutex);
 	lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key);
+	/*
+	 * For now MAXQUOTAS check in do_quotactl() will limit quota type
+	 * appropriately. When each fs sets allowed_types, we can remove the
+	 * line below
+	 */
+	s->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
 	mutex_init(&s->s_dquot.dqio_mutex);
 	mutex_init(&s->s_dquot.dqonoff_mutex);
 	s->s_maxbytes = MAX_NON_LFS;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9ab779e8a63..cf55a5483d4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1224,6 +1224,7 @@ struct super_block {
 	struct backing_dev_info *s_bdi;
 	struct mtd_info		*s_mtd;
 	struct hlist_node	s_instances;
+	unsigned int		s_quota_types;	/* Bitmask of supported quota types */
 	struct quota_info	s_dquot;	/* Diskquota specific options */
 
 	struct sb_writers	s_writers;
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 80d345a3524..50978b781a1 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -56,6 +56,11 @@ enum quota_type {
 	PRJQUOTA = 2,		/* element used for project quotas */
 };
 
+/* Masks for quota types when used as a bitmask */
+#define QTYPE_MASK_USR (1 << USRQUOTA)
+#define QTYPE_MASK_GRP (1 << GRPQUOTA)
+#define QTYPE_MASK_PRJ (1 << PRJQUOTA)
+
 typedef __kernel_uid32_t qid_t; /* Type in which we store ids in memory */
 typedef long long qsize_t;	/* Type in which we store sizes */
 
-- 
cgit v1.2.3-70-g09d2


From 2d0fa467915ed0c5957c992011b7f142a7dedf8e Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 25 Sep 2014 16:36:14 +0200
Subject: quota: Use function to provide i_dquot pointers

i_dquot array is used by relatively few filesystems (ext?, ocfs2, jfs,
reiserfs) so it is beneficial to move this array to fs-private part of
the inode. We cannot just pass quota pointers from filesystems to quota
functions because during quotaon and quotaoff we have to traverse list
of all inodes and manipulate i_dquot pointers for each inode. So we
provide a function which generic quota code can use to get pointer to
the i_dquot array from the filesystem.

Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/quota/dquot.c   | 54 +++++++++++++++++++++++++++++++-----------------------
 include/linux/fs.h |  1 +
 2 files changed, 32 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index b1910c915c9..b80d1fe56f8 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -893,6 +893,14 @@ out:
 }
 EXPORT_SYMBOL(dqget);
 
+static inline struct dquot **i_dquot(struct inode *inode)
+{
+	/* Temporary workaround until all filesystems are converted. */
+	if (!inode->i_sb->s_op->get_dquots)
+		return inode->i_dquot;
+	return inode->i_sb->s_op->get_dquots(inode);
+}
+
 static int dqinit_needed(struct inode *inode, int type)
 {
 	int cnt;
@@ -900,9 +908,9 @@ static int dqinit_needed(struct inode *inode, int type)
 	if (IS_NOQUOTA(inode))
 		return 0;
 	if (type != -1)
-		return !inode->i_dquot[type];
+		return !i_dquot(inode)[type];
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
-		if (!inode->i_dquot[cnt])
+		if (!i_dquot(inode)[cnt])
 			return 1;
 	return 0;
 }
@@ -965,9 +973,9 @@ static void add_dquot_ref(struct super_block *sb, int type)
 static void remove_inode_dquot_ref(struct inode *inode, int type,
 				   struct list_head *tofree_head)
 {
-	struct dquot *dquot = inode->i_dquot[type];
+	struct dquot *dquot = i_dquot(inode)[type];
 
-	inode->i_dquot[type] = NULL;
+	i_dquot(inode)[type] = NULL;
 	if (!dquot)
 		return;
 
@@ -1402,7 +1410,7 @@ static void __dquot_initialize(struct inode *inode, int type)
 		 * we check it without locking here to avoid unnecessary
 		 * dqget()/dqput() calls.
 		 */
-		if (inode->i_dquot[cnt])
+		if (i_dquot(inode)[cnt])
 			continue;
 		init_needed = 1;
 
@@ -1433,8 +1441,8 @@ static void __dquot_initialize(struct inode *inode, int type)
 		/* We could race with quotaon or dqget() could have failed */
 		if (!got[cnt])
 			continue;
-		if (!inode->i_dquot[cnt]) {
-			inode->i_dquot[cnt] = got[cnt];
+		if (!i_dquot(inode)[cnt]) {
+			i_dquot(inode)[cnt] = got[cnt];
 			got[cnt] = NULL;
 			/*
 			 * Make quota reservation system happy if someone
@@ -1442,7 +1450,7 @@ static void __dquot_initialize(struct inode *inode, int type)
 			 */
 			rsv = inode_get_rsv_space(inode);
 			if (unlikely(rsv))
-				dquot_resv_space(inode->i_dquot[cnt], rsv);
+				dquot_resv_space(i_dquot(inode)[cnt], rsv);
 		}
 	}
 out_err:
@@ -1472,8 +1480,8 @@ static void __dquot_drop(struct inode *inode)
 
 	spin_lock(&dq_data_lock);
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		put[cnt] = inode->i_dquot[cnt];
-		inode->i_dquot[cnt] = NULL;
+		put[cnt] = i_dquot(inode)[cnt];
+		i_dquot(inode)[cnt] = NULL;
 	}
 	spin_unlock(&dq_data_lock);
 	dqput_all(put);
@@ -1494,7 +1502,7 @@ void dquot_drop(struct inode *inode)
 	 * add quota pointers back anyway.
 	 */
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (inode->i_dquot[cnt])
+		if (i_dquot(inode)[cnt])
 			break;
 	}
 
@@ -1595,7 +1603,7 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
 {
 	int cnt, ret = 0, index;
 	struct dquot_warn warn[MAXQUOTAS];
-	struct dquot **dquots = inode->i_dquot;
+	struct dquot **dquots = i_dquot(inode);
 	int reserve = flags & DQUOT_SPACE_RESERVE;
 
 	if (!dquot_active(inode)) {
@@ -1647,7 +1655,7 @@ int dquot_alloc_inode(struct inode *inode)
 {
 	int cnt, ret = 0, index;
 	struct dquot_warn warn[MAXQUOTAS];
-	struct dquot * const *dquots = inode->i_dquot;
+	struct dquot * const *dquots = i_dquot(inode);
 
 	if (!dquot_active(inode))
 		return 0;
@@ -1696,14 +1704,14 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
 	spin_lock(&dq_data_lock);
 	/* Claim reserved quotas to allocated quotas */
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (inode->i_dquot[cnt])
-			dquot_claim_reserved_space(inode->i_dquot[cnt],
+		if (i_dquot(inode)[cnt])
+			dquot_claim_reserved_space(i_dquot(inode)[cnt],
 							number);
 	}
 	/* Update inode bytes */
 	inode_claim_rsv_space(inode, number);
 	spin_unlock(&dq_data_lock);
-	mark_all_dquot_dirty(inode->i_dquot);
+	mark_all_dquot_dirty(i_dquot(inode));
 	srcu_read_unlock(&dquot_srcu, index);
 	return 0;
 }
@@ -1725,14 +1733,14 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number)
 	spin_lock(&dq_data_lock);
 	/* Claim reserved quotas to allocated quotas */
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (inode->i_dquot[cnt])
-			dquot_reclaim_reserved_space(inode->i_dquot[cnt],
+		if (i_dquot(inode)[cnt])
+			dquot_reclaim_reserved_space(i_dquot(inode)[cnt],
 						     number);
 	}
 	/* Update inode bytes */
 	inode_reclaim_rsv_space(inode, number);
 	spin_unlock(&dq_data_lock);
-	mark_all_dquot_dirty(inode->i_dquot);
+	mark_all_dquot_dirty(i_dquot(inode));
 	srcu_read_unlock(&dquot_srcu, index);
 	return;
 }
@@ -1745,7 +1753,7 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
 {
 	unsigned int cnt;
 	struct dquot_warn warn[MAXQUOTAS];
-	struct dquot **dquots = inode->i_dquot;
+	struct dquot **dquots = i_dquot(inode);
 	int reserve = flags & DQUOT_SPACE_RESERVE, index;
 
 	if (!dquot_active(inode)) {
@@ -1788,7 +1796,7 @@ void dquot_free_inode(struct inode *inode)
 {
 	unsigned int cnt;
 	struct dquot_warn warn[MAXQUOTAS];
-	struct dquot * const *dquots = inode->i_dquot;
+	struct dquot * const *dquots = i_dquot(inode);
 	int index;
 
 	if (!dquot_active(inode))
@@ -1865,7 +1873,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 		if (!sb_has_quota_active(inode->i_sb, cnt))
 			continue;
 		is_valid[cnt] = 1;
-		transfer_from[cnt] = inode->i_dquot[cnt];
+		transfer_from[cnt] = i_dquot(inode)[cnt];
 		ret = check_idq(transfer_to[cnt], 1, &warn_to[cnt]);
 		if (ret)
 			goto over_quota;
@@ -1901,7 +1909,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 		dquot_incr_space(transfer_to[cnt], cur_space);
 		dquot_resv_space(transfer_to[cnt], rsv_space);
 
-		inode->i_dquot[cnt] = transfer_to[cnt];
+		i_dquot(inode)[cnt] = transfer_to[cnt];
 	}
 	spin_unlock(&dq_data_lock);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index cf55a5483d4..8c093ad4952 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1591,6 +1591,7 @@ struct super_operations {
 #ifdef CONFIG_QUOTA
 	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
 	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
+	struct dquot **(*get_dquots)(struct inode *);
 #endif
 	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
 	long (*nr_cached_objects)(struct super_block *, int);
-- 
cgit v1.2.3-70-g09d2


From 75cbe701a4251fcd8b846d52ae42f88c9a8e5e93 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 29 Sep 2014 15:10:26 +0200
Subject: vfs: Remove i_dquot field from inode

All filesystems using VFS quotas are now converted to use their private
i_dquot fields. Remove the i_dquot field from generic inode structure.

Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/inode.c         | 3 ---
 fs/quota/dquot.c   | 3 ---
 fs/super.c         | 6 ------
 include/linux/fs.h | 3 ---
 4 files changed, 15 deletions(-)

(limited to 'include')

diff --git a/fs/inode.c b/fs/inode.c
index 26753ba7b6d..2ed95f7caa4 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -143,9 +143,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_blocks = 0;
 	inode->i_bytes = 0;
 	inode->i_generation = 0;
-#ifdef CONFIG_QUOTA
-	memset(&inode->i_dquot, 0, sizeof(inode->i_dquot));
-#endif
 	inode->i_pipe = NULL;
 	inode->i_bdev = NULL;
 	inode->i_cdev = NULL;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index b80d1fe56f8..8f0acef3d18 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -895,9 +895,6 @@ EXPORT_SYMBOL(dqget);
 
 static inline struct dquot **i_dquot(struct inode *inode)
 {
-	/* Temporary workaround until all filesystems are converted. */
-	if (!inode->i_sb->s_op->get_dquots)
-		return inode->i_dquot;
 	return inode->i_sb->s_op->get_dquots(inode);
 }
 
diff --git a/fs/super.c b/fs/super.c
index 4512281df8f..eae088f6aaa 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -218,12 +218,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	atomic_set(&s->s_active, 1);
 	mutex_init(&s->s_vfs_rename_mutex);
 	lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key);
-	/*
-	 * For now MAXQUOTAS check in do_quotactl() will limit quota type
-	 * appropriately. When each fs sets allowed_types, we can remove the
-	 * line below
-	 */
-	s->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
 	mutex_init(&s->s_dquot.dqio_mutex);
 	mutex_init(&s->s_dquot.dqonoff_mutex);
 	s->s_maxbytes = MAX_NON_LFS;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8c093ad4952..6eb5337688b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -606,9 +606,6 @@ struct inode {
 	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
 	struct file_lock	*i_flock;
 	struct address_space	i_data;
-#ifdef CONFIG_QUOTA
-	struct dquot		*i_dquot[MAXQUOTAS];
-#endif
 	struct list_head	i_devices;
 	union {
 		struct pipe_inode_info	*i_pipe;
-- 
cgit v1.2.3-70-g09d2


From f8d7552e945d38bd8d2e9c23aebf98042ce12302 Mon Sep 17 00:00:00 2001
From: Luciano Coelho <luciano.coelho@intel.com>
Date: Fri, 7 Nov 2014 14:31:35 +0200
Subject: cfg80211: add channel switch started notification

Add a new NL80211_CH_SWITCH_STARTED_NOTIFY message that can be sent to
the userspace when a channel switch process has started.  This allows
userspace to take action, for instance, by requesting other interfaces
to switch channel as necessary.

This patch introduces a function that allows the drivers to send this
notification.  It should be used when the driver starts processing a
channel switch initiated by a remote device (eg. when a STA receives a
CSA from the AP) and when it successfully starts a userspace-triggered
channel switch (eg. when hostapd triggers a channel swith in the AP).

Signed-off-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 14 ++++++++++++++
 include/uapi/linux/nl80211.h | 11 +++++++++++
 net/wireless/nl80211.c       | 28 +++++++++++++++++++++++++---
 net/wireless/trace.h         | 16 ++++++++++++++++
 4 files changed, 66 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 5c3acd07acd..220d5f5f1ac 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4719,6 +4719,20 @@ bool cfg80211_reg_can_beacon(struct wiphy *wiphy,
 void cfg80211_ch_switch_notify(struct net_device *dev,
 			       struct cfg80211_chan_def *chandef);
 
+/*
+ * cfg80211_ch_switch_started_notify - notify channel switch start
+ * @dev: the device on which the channel switch started
+ * @chandef: the future channel definition
+ * @count: the number of TBTTs until the channel switch happens
+ *
+ * Inform the userspace about the channel switch that has just
+ * started, so that it can take appropriate actions (eg. starting
+ * channel switch on other vifs), if necessary.
+ */
+void cfg80211_ch_switch_started_notify(struct net_device *dev,
+				       struct cfg80211_chan_def *chandef,
+				       u8 count);
+
 /**
  * ieee80211_operating_class_to_band - convert operating class to band
  *
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 9b3025e4377..35416343335 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -645,6 +645,15 @@
  *	%NL80211_ATTR_IFINDEX is now on %NL80211_ATTR_WIPHY_FREQ and the
  *	attributes determining channel width.
  *
+ * @NL80211_CMD_CH_SWITCH_STARTED_NOTIFY: Notify that a channel switch
+ *	has been started on an interface, regardless of the initiator
+ *	(ie. whether it was requested from a remote device or
+ *	initiated on our own).  It indicates that
+ *	%NL80211_ATTR_IFINDEX will be on %NL80211_ATTR_WIPHY_FREQ
+ *	after %NL80211_ATTR_CH_SWITCH_COUNT TBTT's.  The userspace may
+ *	decide to react to this indication by requesting other
+ *	interfaces to change channel as well.
+ *
  * @NL80211_CMD_START_P2P_DEVICE: Start the given P2P Device, identified by
  *	its %NL80211_ATTR_WDEV identifier. It must have been created with
  *	%NL80211_CMD_NEW_INTERFACE previously. After it has been started, the
@@ -930,6 +939,8 @@ enum nl80211_commands {
 	NL80211_CMD_JOIN_OCB,
 	NL80211_CMD_LEAVE_OCB,
 
+	NL80211_CMD_CH_SWITCH_STARTED_NOTIFY,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 24549cbe0b5..24fd2925b28 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -11653,7 +11653,9 @@ EXPORT_SYMBOL(cfg80211_pmksa_candidate_notify);
 static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev,
 				     struct net_device *netdev,
 				     struct cfg80211_chan_def *chandef,
-				     gfp_t gfp)
+				     gfp_t gfp,
+				     enum nl80211_commands notif,
+				     u8 count)
 {
 	struct sk_buff *msg;
 	void *hdr;
@@ -11662,7 +11664,7 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev,
 	if (!msg)
 		return;
 
-	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_CH_SWITCH_NOTIFY);
+	hdr = nl80211hdr_put(msg, 0, 0, 0, notif);
 	if (!hdr) {
 		nlmsg_free(msg);
 		return;
@@ -11674,6 +11676,10 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev,
 	if (nl80211_send_chandef(msg, chandef))
 		goto nla_put_failure;
 
+	if ((notif == NL80211_CMD_CH_SWITCH_STARTED_NOTIFY) &&
+	    (nla_put_u32(msg, NL80211_ATTR_CH_SWITCH_COUNT, count)))
+			goto nla_put_failure;
+
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
@@ -11704,10 +11710,26 @@ void cfg80211_ch_switch_notify(struct net_device *dev,
 
 	wdev->chandef = *chandef;
 	wdev->preset_chandef = *chandef;
-	nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL);
+	nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL,
+				 NL80211_CMD_CH_SWITCH_NOTIFY, 0);
 }
 EXPORT_SYMBOL(cfg80211_ch_switch_notify);
 
+void cfg80211_ch_switch_started_notify(struct net_device *dev,
+				       struct cfg80211_chan_def *chandef,
+				       u8 count)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct wiphy *wiphy = wdev->wiphy;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+
+	trace_cfg80211_ch_switch_started_notify(dev, chandef);
+
+	nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL,
+				 NL80211_CMD_CH_SWITCH_STARTED_NOTIFY, count);
+}
+EXPORT_SYMBOL(cfg80211_ch_switch_started_notify);
+
 void cfg80211_cqm_txe_notify(struct net_device *dev,
 			     const u8 *peer, u32 num_packets,
 			     u32 rate, u32 intvl, gfp_t gfp)
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 277a85df910..6e25370d3ce 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -2355,6 +2355,22 @@ TRACE_EVENT(cfg80211_ch_switch_notify,
 		  NETDEV_PR_ARG, CHAN_DEF_PR_ARG)
 );
 
+TRACE_EVENT(cfg80211_ch_switch_started_notify,
+	TP_PROTO(struct net_device *netdev,
+		 struct cfg80211_chan_def *chandef),
+	TP_ARGS(netdev, chandef),
+	TP_STRUCT__entry(
+		NETDEV_ENTRY
+		CHAN_DEF_ENTRY
+	),
+	TP_fast_assign(
+		NETDEV_ASSIGN;
+		CHAN_DEF_ASSIGN(chandef);
+	),
+	TP_printk(NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT,
+		  NETDEV_PR_ARG, CHAN_DEF_PR_ARG)
+);
+
 TRACE_EVENT(cfg80211_radar_event,
 	TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef),
 	TP_ARGS(wiphy, chandef),
-- 
cgit v1.2.3-70-g09d2


From d04b5ac9e70b2056a8a12f768f4b46773576025e Mon Sep 17 00:00:00 2001
From: Luciano Coelho <luciano.coelho@intel.com>
Date: Fri, 7 Nov 2014 14:31:37 +0200
Subject: cfg80211/mac80211: allow any interface to send channel switch
 notifications

For multi-vif channel switches, we want to send
NL80211_CMD_CH_SWITCH_NOTIFY to the userspace to let it decide whether
other interfaces need to be moved as well.  This is needed when we
want a P2P GO interface to follow the channel of a station, for
example.

Modify the code so that all interfaces can send CSA notifications.
Additionally, send notifications for STA CSA as well.

Signed-off-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 4 +++-
 net/mac80211/mlme.c          | 2 ++
 net/wireless/nl80211.c       | 6 ------
 3 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 35416343335..a552736c3e5 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -643,7 +643,9 @@
  * @NL80211_CMD_CH_SWITCH_NOTIFY: An AP or GO may decide to switch channels
  *	independently of the userspace SME, send this event indicating
  *	%NL80211_ATTR_IFINDEX is now on %NL80211_ATTR_WIPHY_FREQ and the
- *	attributes determining channel width.
+ *	attributes determining channel width.  This indication may also be
+ *	sent when a remotely-initiated switch (e.g., when a STA receives a CSA
+ *	from the remote AP) is completed;
  *
  * @NL80211_CMD_CH_SWITCH_STARTED_NOTIFY: Notify that a channel switch
  *	has been started on an interface, regardless of the initiator
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 94725007761..24353987899 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1049,6 +1049,8 @@ static void ieee80211_chswitch_post_beacon(struct ieee80211_sub_if_data *sdata)
 		sdata->csa_block_tx = false;
 	}
 
+	cfg80211_ch_switch_notify(sdata->dev, &sdata->reserved_chandef);
+
 	sdata->vif.csa_active = false;
 	ifmgd->csa_waiting_bcn = false;
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 24fd2925b28..d0a8361b339 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -11702,12 +11702,6 @@ void cfg80211_ch_switch_notify(struct net_device *dev,
 
 	trace_cfg80211_ch_switch_notify(dev, chandef);
 
-	if (WARN_ON(wdev->iftype != NL80211_IFTYPE_AP &&
-		    wdev->iftype != NL80211_IFTYPE_P2P_GO &&
-		    wdev->iftype != NL80211_IFTYPE_ADHOC &&
-		    wdev->iftype != NL80211_IFTYPE_MESH_POINT))
-		return;
-
 	wdev->chandef = *chandef;
 	wdev->preset_chandef = *chandef;
 	nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL,
-- 
cgit v1.2.3-70-g09d2


From 1f7bba79af57ceecf25c2b7d3e6a484efefe340f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 6 Nov 2014 22:56:36 +0100
Subject: mac80211: add back support for radiotap vendor namespace data

Radiotap vendor namespace data might still be useful, but we
reverted it because it used too much space in the RX status.
Put it back, but address the space problem by using a single
bit only and putting everything else into the skb->data.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c |  50 +++++++++++++++++
 include/net/mac80211.h                |  37 +++++++++++++
 net/mac80211/rx.c                     | 100 ++++++++++++++++++++++++++++------
 3 files changed, 169 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 209db62ee62..58f11bb0896 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -984,6 +984,53 @@ static void mac80211_hwsim_tx_iter(void *_data, u8 *addr,
 	data->receive = true;
 }
 
+static void mac80211_hwsim_add_vendor_rtap(struct sk_buff *skb)
+{
+	/*
+	 * To enable this code, #define the HWSIM_RADIOTAP_OUI,
+	 * e.g. like this:
+	 * #define HWSIM_RADIOTAP_OUI "\x02\x00\x00"
+	 * (but you should use a valid OUI, not that)
+	 *
+	 * If anyone wants to 'donate' a radiotap OUI/subns code
+	 * please send a patch removing this #ifdef and changing
+	 * the values accordingly.
+	 */
+#ifdef HWSIM_RADIOTAP_OUI
+	struct ieee80211_vendor_radiotap *rtap;
+
+	/*
+	 * Note that this code requires the headroom in the SKB
+	 * that was allocated earlier.
+	 */
+	rtap = (void *)skb_push(skb, sizeof(*rtap) + 8 + 4);
+	rtap->oui[0] = HWSIM_RADIOTAP_OUI[0];
+	rtap->oui[1] = HWSIM_RADIOTAP_OUI[1];
+	rtap->oui[2] = HWSIM_RADIOTAP_OUI[2];
+	rtap->subns = 127;
+
+	/*
+	 * Radiotap vendor namespaces can (and should) also be
+	 * split into fields by using the standard radiotap
+	 * presence bitmap mechanism. Use just BIT(0) here for
+	 * the presence bitmap.
+	 */
+	rtap->present = BIT(0);
+	/* We have 8 bytes of (dummy) data */
+	rtap->len = 8;
+	/* For testing, also require it to be aligned */
+	rtap->align = 8;
+	/* And also test that padding works, 4 bytes */
+	rtap->pad = 4;
+	/* push the data */
+	memcpy(rtap->data, "ABCDEFGH", 8);
+	/* make sure to clear padding, mac80211 doesn't */
+	memset(rtap->data + 8, 0, 4);
+
+	IEEE80211_SKB_RXCB(skb)->flag |= RX_FLAG_RADIOTAP_VENDOR_DATA;
+#endif
+}
+
 static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw,
 					  struct sk_buff *skb,
 					  struct ieee80211_channel *chan)
@@ -1098,6 +1145,9 @@ static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw,
 		rx_status.mactime = now + data2->tsf_offset;
 
 		memcpy(IEEE80211_SKB_RXCB(nskb), &rx_status, sizeof(rx_status));
+
+		mac80211_hwsim_add_vendor_rtap(nskb);
+
 		data2->rx_pkts++;
 		data2->rx_bytes += nskb->len;
 		ieee80211_rx_irqsafe(data2->hw, nskb);
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 5f203a6a5e7..83232aa2f07 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -882,6 +882,9 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  *	subframes share the same sequence number. Reported subframes can be
  *	either regular MSDU or singly A-MSDUs. Subframes must not be
  *	interleaved with other frames.
+ * @RX_FLAG_RADIOTAP_VENDOR_DATA: This frame contains vendor-specific
+ *	radiotap data in the skb->data (before the frame) as described by
+ *	the &struct ieee80211_vendor_radiotap.
  */
 enum mac80211_rx_flags {
 	RX_FLAG_MMIC_ERROR		= BIT(0),
@@ -911,6 +914,7 @@ enum mac80211_rx_flags {
 	RX_FLAG_10MHZ			= BIT(28),
 	RX_FLAG_5MHZ			= BIT(29),
 	RX_FLAG_AMSDU_MORE		= BIT(30),
+	RX_FLAG_RADIOTAP_VENDOR_DATA	= BIT(31),
 };
 
 #define RX_FLAG_STBC_SHIFT		26
@@ -981,6 +985,39 @@ struct ieee80211_rx_status {
 	u8 ampdu_delimiter_crc;
 };
 
+/**
+ * struct ieee80211_vendor_radiotap - vendor radiotap data information
+ * @present: presence bitmap for this vendor namespace
+ *	(this could be extended in the future if any vendor needs more
+ *	 bits, the radiotap spec does allow for that)
+ * @align: radiotap vendor namespace alignment. This defines the needed
+ *	alignment for the @data field below, not for the vendor namespace
+ *	description itself (which has a fixed 2-byte alignment)
+ *	Must be a power of two, and be set to at least 1!
+ * @oui: radiotap vendor namespace OUI
+ * @subns: radiotap vendor sub namespace
+ * @len: radiotap vendor sub namespace skip length, if alignment is done
+ *	then that's added to this, i.e. this is only the length of the
+ *	@data field.
+ * @pad: number of bytes of padding after the @data, this exists so that
+ *	the skb data alignment can be preserved even if the data has odd
+ *	length
+ * @data: the actual vendor namespace data
+ *
+ * This struct, including the vendor data, goes into the skb->data before
+ * the 802.11 header. It's split up in mac80211 using the align/oui/subns
+ * data.
+ */
+struct ieee80211_vendor_radiotap {
+	u32 present;
+	u8 align;
+	u8 oui[3];
+	u8 subns;
+	u8 pad;
+	u16 len;
+	u8 data[];
+} __packed;
+
 /**
  * enum ieee80211_conf_flags - configuration flags
  *
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index bc63aa0c540..f57af5c7c12 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -39,7 +39,8 @@
  * only useful for monitoring.
  */
 static struct sk_buff *remove_monitor_info(struct ieee80211_local *local,
-					   struct sk_buff *skb)
+					   struct sk_buff *skb,
+					   unsigned int rtap_vendor_space)
 {
 	if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS) {
 		if (likely(skb->len > FCS_LEN))
@@ -52,20 +53,25 @@ static struct sk_buff *remove_monitor_info(struct ieee80211_local *local,
 		}
 	}
 
+	__pskb_pull(skb, rtap_vendor_space);
+
 	return skb;
 }
 
-static inline bool should_drop_frame(struct sk_buff *skb, int present_fcs_len)
+static inline bool should_drop_frame(struct sk_buff *skb, int present_fcs_len,
+				     unsigned int rtap_vendor_space)
 {
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
-	struct ieee80211_hdr *hdr = (void *)skb->data;
+	struct ieee80211_hdr *hdr;
+
+	hdr = (void *)(skb->data + rtap_vendor_space);
 
 	if (status->flag & (RX_FLAG_FAILED_FCS_CRC |
 			    RX_FLAG_FAILED_PLCP_CRC |
 			    RX_FLAG_AMPDU_IS_ZEROLEN))
 		return true;
 
-	if (unlikely(skb->len < 16 + present_fcs_len))
+	if (unlikely(skb->len < 16 + present_fcs_len + rtap_vendor_space))
 		return true;
 
 	if (ieee80211_is_ctl(hdr->frame_control) &&
@@ -77,8 +83,9 @@ static inline bool should_drop_frame(struct sk_buff *skb, int present_fcs_len)
 }
 
 static int
-ieee80211_rx_radiotap_space(struct ieee80211_local *local,
-			    struct ieee80211_rx_status *status)
+ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local,
+			     struct ieee80211_rx_status *status,
+			     struct sk_buff *skb)
 {
 	int len;
 
@@ -121,6 +128,21 @@ ieee80211_rx_radiotap_space(struct ieee80211_local *local,
 		len += 2 * hweight8(status->chains);
 	}
 
+	if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) {
+		struct ieee80211_vendor_radiotap *rtap = (void *)skb->data;
+
+		/* vendor presence bitmap */
+		len += 4;
+		/* alignment for fixed 6-byte vendor data header */
+		len = ALIGN(len, 2);
+		/* vendor data header */
+		len += 6;
+		if (WARN_ON(rtap->align == 0))
+			rtap->align = 1;
+		len = ALIGN(len, rtap->align);
+		len += rtap->len + rtap->pad;
+	}
+
 	return len;
 }
 
@@ -144,13 +166,20 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	u16 channel_flags = 0;
 	int mpdulen, chain;
 	unsigned long chains = status->chains;
+	struct ieee80211_vendor_radiotap rtap = {};
+
+	if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) {
+		rtap = *(struct ieee80211_vendor_radiotap *)skb->data;
+		/* rtap.len and rtap.pad are undone immediately */
+		skb_pull(skb, sizeof(rtap) + rtap.len + rtap.pad);
+	}
 
 	mpdulen = skb->len;
 	if (!(has_fcs && (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS)))
 		mpdulen += FCS_LEN;
 
 	rthdr = (struct ieee80211_radiotap_header *)skb_push(skb, rtap_len);
-	memset(rthdr, 0, rtap_len);
+	memset(rthdr, 0, rtap_len - rtap.len - rtap.pad);
 	it_present = &rthdr->it_present;
 
 	/* radiotap header, set always present flags */
@@ -172,6 +201,14 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 				 BIT(IEEE80211_RADIOTAP_DBM_ANTSIGNAL);
 	}
 
+	if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) {
+		it_present_val |= BIT(IEEE80211_RADIOTAP_VENDOR_NAMESPACE) |
+				  BIT(IEEE80211_RADIOTAP_EXT);
+		put_unaligned_le32(it_present_val, it_present);
+		it_present++;
+		it_present_val = rtap.present;
+	}
+
 	put_unaligned_le32(it_present_val, it_present);
 
 	pos = (void *)(it_present + 1);
@@ -366,6 +403,22 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		*pos++ = status->chain_signal[chain];
 		*pos++ = chain;
 	}
+
+	if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) {
+		/* ensure 2 byte alignment for the vendor field as required */
+		if ((pos - (u8 *)rthdr) & 1)
+			*pos++ = 0;
+		*pos++ = rtap.oui[0];
+		*pos++ = rtap.oui[1];
+		*pos++ = rtap.oui[2];
+		*pos++ = rtap.subns;
+		put_unaligned_le16(rtap.len, pos);
+		pos += 2;
+		/* align the actual payload as requested */
+		while ((pos - (u8 *)rthdr) & (rtap.align - 1))
+			*pos++ = 0;
+		/* data (and possible padding) already follows */
+	}
 }
 
 /*
@@ -379,10 +432,17 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 {
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(origskb);
 	struct ieee80211_sub_if_data *sdata;
-	int needed_headroom;
+	int rt_hdrlen, needed_headroom;
 	struct sk_buff *skb, *skb2;
 	struct net_device *prev_dev = NULL;
 	int present_fcs_len = 0;
+	unsigned int rtap_vendor_space = 0;
+
+	if (unlikely(status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA)) {
+		struct ieee80211_vendor_radiotap *rtap = (void *)origskb->data;
+
+		rtap_vendor_space = sizeof(*rtap) + rtap->len + rtap->pad;
+	}
 
 	/*
 	 * First, we may need to make a copy of the skb because
@@ -396,25 +456,27 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 	if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS)
 		present_fcs_len = FCS_LEN;
 
-	/* ensure hdr->frame_control is in skb head */
-	if (!pskb_may_pull(origskb, 2)) {
+	/* ensure hdr->frame_control and vendor radiotap data are in skb head */
+	if (!pskb_may_pull(origskb, 2 + rtap_vendor_space)) {
 		dev_kfree_skb(origskb);
 		return NULL;
 	}
 
 	if (!local->monitors) {
-		if (should_drop_frame(origskb, present_fcs_len)) {
+		if (should_drop_frame(origskb, present_fcs_len,
+				      rtap_vendor_space)) {
 			dev_kfree_skb(origskb);
 			return NULL;
 		}
 
-		return remove_monitor_info(local, origskb);
+		return remove_monitor_info(local, origskb, rtap_vendor_space);
 	}
 
 	/* room for the radiotap header based on driver features */
-	needed_headroom = ieee80211_rx_radiotap_space(local, status);
+	rt_hdrlen = ieee80211_rx_radiotap_hdrlen(local, status, origskb);
+	needed_headroom = rt_hdrlen - rtap_vendor_space;
 
-	if (should_drop_frame(origskb, present_fcs_len)) {
+	if (should_drop_frame(origskb, present_fcs_len, rtap_vendor_space)) {
 		/* only need to expand headroom if necessary */
 		skb = origskb;
 		origskb = NULL;
@@ -438,15 +500,15 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 		 */
 		skb = skb_copy_expand(origskb, needed_headroom, 0, GFP_ATOMIC);
 
-		origskb = remove_monitor_info(local, origskb);
+		origskb = remove_monitor_info(local, origskb,
+					      rtap_vendor_space);
 
 		if (!skb)
 			return origskb;
 	}
 
 	/* prepend radiotap information */
-	ieee80211_add_rx_radiotap_header(local, skb, rate, needed_headroom,
-					 true);
+	ieee80211_add_rx_radiotap_header(local, skb, rate, rt_hdrlen, true);
 
 	skb_reset_mac_header(skb);
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -2892,8 +2954,10 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx,
 	if (!local->cooked_mntrs)
 		goto out_free_skb;
 
+	/* vendor data is long removed here */
+	status->flag &= ~RX_FLAG_RADIOTAP_VENDOR_DATA;
 	/* room for the radiotap header based on driver features */
-	needed_headroom = ieee80211_rx_radiotap_space(local, status);
+	needed_headroom = ieee80211_rx_radiotap_hdrlen(local, status, skb);
 
 	if (skb_headroom(skb) < needed_headroom &&
 	    pskb_expand_head(skb, needed_headroom, 0, GFP_ATOMIC))
-- 
cgit v1.2.3-70-g09d2


From a6d4a534e15f0e1b13b518c31219f9fb7166412a Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Thu, 23 Oct 2014 09:37:33 +0300
Subject: cfg80211: introduce regulatory flags controlling bw

Allow setting bandwidth related regulatory flags. These flags are mapped
to the corresponding channel flags in the specified range.
Make sure the new flags are consulted when calculating the maximum
bandwidth allowed by a regulatory-rule.

Also allow propagating the GO_CONCURRENT modifier from a reg-rule to a
channel.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Reviewed-by: Luis R. Rodriguez <mcgrof@suse.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 12 ++++++++++++
 net/wireless/reg.c           | 36 ++++++++++++++++++++++++++++++++++--
 2 files changed, 46 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index a552736c3e5..442369f69b4 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2665,6 +2665,11 @@ enum nl80211_sched_scan_match_attr {
  * @NL80211_RRF_AUTO_BW: maximum available bandwidth should be calculated
  *	base on contiguous rules and wider channels will be allowed to cross
  *	multiple contiguous/overlapping frequency ranges.
+ * @NL80211_RRF_GO_CONCURRENT: See &NL80211_FREQUENCY_ATTR_GO_CONCURRENT
+ * @NL80211_RRF_NO_HT40MINUS: channels can't be used in HT40- operation
+ * @NL80211_RRF_NO_HT40PLUS: channels can't be used in HT40+ operation
+ * @NL80211_RRF_NO_80MHZ: 80MHz operation not allowed
+ * @NL80211_RRF_NO_160MHZ: 160MHz operation not allowed
  */
 enum nl80211_reg_rule_flags {
 	NL80211_RRF_NO_OFDM		= 1<<0,
@@ -2677,11 +2682,18 @@ enum nl80211_reg_rule_flags {
 	NL80211_RRF_NO_IR		= 1<<7,
 	__NL80211_RRF_NO_IBSS		= 1<<8,
 	NL80211_RRF_AUTO_BW		= 1<<11,
+	NL80211_RRF_GO_CONCURRENT	= 1<<12,
+	NL80211_RRF_NO_HT40MINUS	= 1<<13,
+	NL80211_RRF_NO_HT40PLUS		= 1<<14,
+	NL80211_RRF_NO_80MHZ		= 1<<15,
+	NL80211_RRF_NO_160MHZ		= 1<<16,
 };
 
 #define NL80211_RRF_PASSIVE_SCAN	NL80211_RRF_NO_IR
 #define NL80211_RRF_NO_IBSS		NL80211_RRF_NO_IR
 #define NL80211_RRF_NO_IR		NL80211_RRF_NO_IR
+#define NL80211_RRF_NO_HT40		(NL80211_RRF_NO_HT40MINUS |\
+					 NL80211_RRF_NO_HT40PLUS)
 
 /* For backport compatibility with older userspace */
 #define NL80211_RRF_NO_IR_ALL		(NL80211_RRF_NO_IR | __NL80211_RRF_NO_IBSS)
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index b725a31a475..7449a8c0f9f 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -573,8 +573,9 @@ static const struct ieee80211_regdomain *reg_get_regdomain(struct wiphy *wiphy)
 	return get_cfg80211_regdom();
 }
 
-unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd,
-				   const struct ieee80211_reg_rule *rule)
+static unsigned int
+reg_get_max_bandwidth_from_range(const struct ieee80211_regdomain *rd,
+				 const struct ieee80211_reg_rule *rule)
 {
 	const struct ieee80211_freq_range *freq_range = &rule->freq_range;
 	const struct ieee80211_freq_range *freq_range_tmp;
@@ -622,6 +623,27 @@ unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd,
 	return end_freq - start_freq;
 }
 
+unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd,
+				   const struct ieee80211_reg_rule *rule)
+{
+	unsigned int bw = reg_get_max_bandwidth_from_range(rd, rule);
+
+	if (rule->flags & NL80211_RRF_NO_160MHZ)
+		bw = min_t(unsigned int, bw, MHZ_TO_KHZ(80));
+	if (rule->flags & NL80211_RRF_NO_80MHZ)
+		bw = min_t(unsigned int, bw, MHZ_TO_KHZ(40));
+
+	/*
+	 * HT40+/HT40- limits are handled per-channel. Only limit BW if both
+	 * are not allowed.
+	 */
+	if (rule->flags & NL80211_RRF_NO_HT40MINUS &&
+	    rule->flags & NL80211_RRF_NO_HT40PLUS)
+		bw = min_t(unsigned int, bw, MHZ_TO_KHZ(20));
+
+	return bw;
+}
+
 /* Sanity check on a regulatory rule */
 static bool is_valid_reg_rule(const struct ieee80211_reg_rule *rule)
 {
@@ -946,6 +968,16 @@ static u32 map_regdom_flags(u32 rd_flags)
 		channel_flags |= IEEE80211_CHAN_NO_OFDM;
 	if (rd_flags & NL80211_RRF_NO_OUTDOOR)
 		channel_flags |= IEEE80211_CHAN_INDOOR_ONLY;
+	if (rd_flags & NL80211_RRF_GO_CONCURRENT)
+		channel_flags |= IEEE80211_CHAN_GO_CONCURRENT;
+	if (rd_flags & NL80211_RRF_NO_HT40MINUS)
+		channel_flags |= IEEE80211_CHAN_NO_HT40MINUS;
+	if (rd_flags & NL80211_RRF_NO_HT40PLUS)
+		channel_flags |= IEEE80211_CHAN_NO_HT40PLUS;
+	if (rd_flags & NL80211_RRF_NO_80MHZ)
+		channel_flags |= IEEE80211_CHAN_NO_80MHZ;
+	if (rd_flags & NL80211_RRF_NO_160MHZ)
+		channel_flags |= IEEE80211_CHAN_NO_160MHZ;
 	return channel_flags;
 }
 
-- 
cgit v1.2.3-70-g09d2


From cc9571e85808dfc121e4fda5c75c9a3c3c75e514 Mon Sep 17 00:00:00 2001
From: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Date: Tue, 21 Oct 2014 11:22:35 +0200
Subject: mmc: sdhci-pxav3: Move private driver data to driver source

struct sdhci_pxa is only used in sdhci_pxa driver itself, so move it
there.

Signed-off-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci-pxav3.c          | 5 +++++
 include/linux/platform_data/pxa_sdhci.h | 5 -----
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index b55c807982f..48bc8179c8f 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -58,6 +58,11 @@
 #define SDCE_MISC_INT		(1<<2)
 #define SDCE_MISC_INT_EN	(1<<1)
 
+struct sdhci_pxa {
+	u8	clk_enable;
+	u8	power_mode;
+};
+
 /*
  * These registers are relative to the second register region, for the
  * MBus bridge.
diff --git a/include/linux/platform_data/pxa_sdhci.h b/include/linux/platform_data/pxa_sdhci.h
index 27d3156d093..9e20c2fb4ff 100644
--- a/include/linux/platform_data/pxa_sdhci.h
+++ b/include/linux/platform_data/pxa_sdhci.h
@@ -55,9 +55,4 @@ struct sdhci_pxa_platdata {
 	unsigned int	quirks2;
 	unsigned int	pm_caps;
 };
-
-struct sdhci_pxa {
-	u8	clk_enable;
-	u8	power_mode;
-};
 #endif /* _PXA_SDHCI_H_ */
-- 
cgit v1.2.3-70-g09d2


From 433b7b1210a4ece4f2b4f1b04f31a2f0928c8aa8 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 6 Oct 2014 11:00:15 +0200
Subject: mmc: core: Don't export the to_sdio_driver macro

The macro is only used by the mmc core, so let's move it in there.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/sdio_bus.c   | 2 ++
 include/linux/mmc/sdio_func.h | 2 --
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index f09040bf548..51e23f50210 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -26,6 +26,8 @@
 #include "sdio_cis.h"
 #include "sdio_bus.h"
 
+#define to_sdio_driver(d)	container_of(d, struct sdio_driver, drv)
+
 /* show configuration fields */
 #define sdio_config_attr(field, format_string)				\
 static ssize_t								\
diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h
index 50f0bc95232..aab032a6ae6 100644
--- a/include/linux/mmc/sdio_func.h
+++ b/include/linux/mmc/sdio_func.h
@@ -84,8 +84,6 @@ struct sdio_driver {
 	struct device_driver drv;
 };
 
-#define to_sdio_driver(d)	container_of(d, struct sdio_driver, drv)
-
 /**
  * SDIO_DEVICE - macro used to describe a specific SDIO device
  * @vend: the 16 bit manufacturer code
-- 
cgit v1.2.3-70-g09d2


From 6685ac62b2f08fcff77dc35c6b8bff1b74aaa408 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 6 Oct 2014 13:51:40 +0200
Subject: mmc: core: Convert mmc_driver to device_driver

The struct mmc_driver adds an extra layer on top of the struct
device_driver. That would be fine, if there were a good reason, but
that's not the case.

Let's simplify code by converting to the common struct device_driver
instead and thus also removing superfluous overhead.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/card/block.c    | 26 ++++++++++++++------------
 drivers/mmc/card/mmc_test.c | 18 +++++++++++-------
 drivers/mmc/core/bus.c      | 41 ++++++++---------------------------------
 include/linux/mmc/card.h    | 16 ++--------------
 4 files changed, 35 insertions(+), 66 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index dfbdfb995dd..70569d9b5c7 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -2425,8 +2425,9 @@ static const struct mmc_fixup blk_fixups[] =
 	END_FIXUP
 };
 
-static int mmc_blk_probe(struct mmc_card *card)
+static int mmc_blk_probe(struct device *dev)
 {
+	struct mmc_card *card = mmc_dev_to_card(dev);
 	struct mmc_blk_data *md, *part_md;
 	char cap_str[10];
 
@@ -2481,8 +2482,9 @@ static int mmc_blk_probe(struct mmc_card *card)
 	return 0;
 }
 
-static void mmc_blk_remove(struct mmc_card *card)
+static int mmc_blk_remove(struct device *dev)
 {
+	struct mmc_card *card = mmc_dev_to_card(dev);
 	struct mmc_blk_data *md = mmc_get_drvdata(card);
 
 	mmc_blk_remove_parts(card, md);
@@ -2495,11 +2497,14 @@ static void mmc_blk_remove(struct mmc_card *card)
 	pm_runtime_put_noidle(&card->dev);
 	mmc_blk_remove_req(md);
 	mmc_set_drvdata(card, NULL);
+
+	return 0;
 }
 
-static int _mmc_blk_suspend(struct mmc_card *card)
+static int _mmc_blk_suspend(struct device *dev)
 {
 	struct mmc_blk_data *part_md;
+	struct mmc_card *card = mmc_dev_to_card(dev);
 	struct mmc_blk_data *md = mmc_get_drvdata(card);
 
 	if (md) {
@@ -2511,16 +2516,15 @@ static int _mmc_blk_suspend(struct mmc_card *card)
 	return 0;
 }
 
-static void mmc_blk_shutdown(struct mmc_card *card)
+static void mmc_blk_shutdown(struct device *dev)
 {
-	_mmc_blk_suspend(card);
+	_mmc_blk_suspend(dev);
 }
 
 #ifdef CONFIG_PM_SLEEP
 static int mmc_blk_suspend(struct device *dev)
 {
-	struct mmc_card *card = mmc_dev_to_card(dev);
-	return _mmc_blk_suspend(card);
+	return _mmc_blk_suspend(dev);
 }
 
 static int mmc_blk_resume(struct device *dev)
@@ -2546,11 +2550,9 @@ static int mmc_blk_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(mmc_blk_pm_ops, mmc_blk_suspend, mmc_blk_resume);
 
-static struct mmc_driver mmc_driver = {
-	.drv		= {
-		.name	= "mmcblk",
-		.pm	= &mmc_blk_pm_ops,
-	},
+static struct device_driver mmc_driver = {
+	.name		= "mmcblk",
+	.pm		= &mmc_blk_pm_ops,
 	.probe		= mmc_blk_probe,
 	.remove		= mmc_blk_remove,
 	.shutdown	= mmc_blk_shutdown,
diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c
index 0c0fc52d42c..b0643432d6d 100644
--- a/drivers/mmc/card/mmc_test.c
+++ b/drivers/mmc/card/mmc_test.c
@@ -14,6 +14,7 @@
 #include <linux/mmc/host.h>
 #include <linux/mmc/mmc.h>
 #include <linux/slab.h>
+#include <linux/device.h>
 
 #include <linux/scatterlist.h>
 #include <linux/swap.h>		/* For nr_free_buffer_pages() */
@@ -2997,8 +2998,9 @@ err:
 	return ret;
 }
 
-static int mmc_test_probe(struct mmc_card *card)
+static int mmc_test_probe(struct device *dev)
 {
+	struct mmc_card *card = mmc_dev_to_card(dev);
 	int ret;
 
 	if (!mmc_card_mmc(card) && !mmc_card_sd(card))
@@ -3013,20 +3015,22 @@ static int mmc_test_probe(struct mmc_card *card)
 	return 0;
 }
 
-static void mmc_test_remove(struct mmc_card *card)
+static int mmc_test_remove(struct device *dev)
 {
+	struct mmc_card *card = mmc_dev_to_card(dev);
+
 	mmc_test_free_result(card);
 	mmc_test_free_dbgfs_file(card);
+
+	return 0;
 }
 
-static void mmc_test_shutdown(struct mmc_card *card)
+static void mmc_test_shutdown(struct device *dev)
 {
 }
 
-static struct mmc_driver mmc_driver = {
-	.drv		= {
-		.name	= "mmc_test",
-	},
+static struct device_driver mmc_driver = {
+	.name	= "mmc_test",
 	.probe		= mmc_test_probe,
 	.remove		= mmc_test_remove,
 	.shutdown	= mmc_test_shutdown,
diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c
index 2f375283c42..5ca562ccfcf 100644
--- a/drivers/mmc/core/bus.c
+++ b/drivers/mmc/core/bus.c
@@ -25,8 +25,6 @@
 #include "sdio_cis.h"
 #include "bus.h"
 
-#define to_mmc_driver(d)	container_of(d, struct mmc_driver, drv)
-
 static ssize_t type_show(struct device *dev,
 	struct device_attribute *attr, char *buf)
 {
@@ -106,33 +104,14 @@ mmc_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
 	return retval;
 }
 
-static int mmc_bus_probe(struct device *dev)
-{
-	struct mmc_driver *drv = to_mmc_driver(dev->driver);
-	struct mmc_card *card = mmc_dev_to_card(dev);
-
-	return drv->probe(card);
-}
-
-static int mmc_bus_remove(struct device *dev)
-{
-	struct mmc_driver *drv = to_mmc_driver(dev->driver);
-	struct mmc_card *card = mmc_dev_to_card(dev);
-
-	drv->remove(card);
-
-	return 0;
-}
-
 static void mmc_bus_shutdown(struct device *dev)
 {
-	struct mmc_driver *drv = to_mmc_driver(dev->driver);
 	struct mmc_card *card = mmc_dev_to_card(dev);
 	struct mmc_host *host = card->host;
 	int ret;
 
-	if (dev->driver && drv->shutdown)
-		drv->shutdown(card);
+	if (dev->driver && dev->driver->shutdown)
+		dev->driver->shutdown(dev);
 
 	if (host->bus_ops->shutdown) {
 		ret = host->bus_ops->shutdown(host);
@@ -201,8 +180,6 @@ static struct bus_type mmc_bus_type = {
 	.dev_groups	= mmc_dev_groups,
 	.match		= mmc_bus_match,
 	.uevent		= mmc_bus_uevent,
-	.probe		= mmc_bus_probe,
-	.remove		= mmc_bus_remove,
 	.shutdown	= mmc_bus_shutdown,
 	.pm		= &mmc_bus_pm_ops,
 };
@@ -221,24 +198,22 @@ void mmc_unregister_bus(void)
  *	mmc_register_driver - register a media driver
  *	@drv: MMC media driver
  */
-int mmc_register_driver(struct mmc_driver *drv)
+int mmc_register_driver(struct device_driver *drv)
 {
-	drv->drv.bus = &mmc_bus_type;
-	return driver_register(&drv->drv);
+	drv->bus = &mmc_bus_type;
+	return driver_register(drv);
 }
-
 EXPORT_SYMBOL(mmc_register_driver);
 
 /**
  *	mmc_unregister_driver - unregister a media driver
  *	@drv: MMC media driver
  */
-void mmc_unregister_driver(struct mmc_driver *drv)
+void mmc_unregister_driver(struct device_driver *drv)
 {
-	drv->drv.bus = &mmc_bus_type;
-	driver_unregister(&drv->drv);
+	drv->bus = &mmc_bus_type;
+	driver_unregister(drv);
 }
-
 EXPORT_SYMBOL(mmc_unregister_driver);
 
 static void mmc_release_card(struct device *dev)
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index b0692d28f8e..cf54afe5d86 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -513,20 +513,8 @@ static inline int mmc_card_broken_irq_polling(const struct mmc_card *c)
 #define mmc_get_drvdata(c)	dev_get_drvdata(&(c)->dev)
 #define mmc_set_drvdata(c,d)	dev_set_drvdata(&(c)->dev, d)
 
-/*
- * MMC device driver (e.g., Flash card, I/O card...)
- */
-struct mmc_driver {
-	struct device_driver drv;
-	int (*probe)(struct mmc_card *);
-	void (*remove)(struct mmc_card *);
-	int (*suspend)(struct mmc_card *);
-	int (*resume)(struct mmc_card *);
-	void (*shutdown)(struct mmc_card *);
-};
-
-extern int mmc_register_driver(struct mmc_driver *);
-extern void mmc_unregister_driver(struct mmc_driver *);
+extern int mmc_register_driver(struct device_driver *);
+extern void mmc_unregister_driver(struct device_driver *);
 
 extern void mmc_fixup_device(struct mmc_card *card,
 			     const struct mmc_fixup *table);
-- 
cgit v1.2.3-70-g09d2


From fc95e30ba33b9f4faa8630d0762af2548031dc00 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 6 Oct 2014 14:34:09 +0200
Subject: mmc: block: Use dev_set|get_drvdata()

In most of the cases mmc_get|set_drvdata() didn't simplify code, which
should be the primary reason for such macros.

Let's remove them and convert to the common device_driver macros,
dev_set|get_drvdata() instead.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/card/block.c | 21 ++++++++++-----------
 include/linux/mmc/card.h |  2 --
 2 files changed, 10 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 70569d9b5c7..f45f7e3870b 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -112,7 +112,7 @@ struct mmc_blk_data {
 
 	/*
 	 * Only set in main mmc_blk_data associated
-	 * with mmc_card with mmc_set_drvdata, and keeps
+	 * with mmc_card with dev_set_drvdata, and keeps
 	 * track of the current selected device partition.
 	 */
 	unsigned int	part_curr;
@@ -642,7 +642,7 @@ static inline int mmc_blk_part_switch(struct mmc_card *card,
 				      struct mmc_blk_data *md)
 {
 	int ret;
-	struct mmc_blk_data *main_md = mmc_get_drvdata(card);
+	struct mmc_blk_data *main_md = dev_get_drvdata(&card->dev);
 
 	if (main_md->part_curr == md->part_type)
 		return 0;
@@ -1004,7 +1004,8 @@ static int mmc_blk_reset(struct mmc_blk_data *md, struct mmc_host *host,
 	err = mmc_hw_reset(host);
 	/* Ensure we switch back to the correct partition */
 	if (err != -EOPNOTSUPP) {
-		struct mmc_blk_data *main_md = mmc_get_drvdata(host->card);
+		struct mmc_blk_data *main_md =
+			dev_get_drvdata(&host->card->dev);
 		int part_err;
 
 		main_md->part_curr = main_md->part_type;
@@ -2093,7 +2094,7 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 
 	/*
 	 * !subname implies we are creating main mmc_blk_data that will be
-	 * associated with mmc_card with mmc_set_drvdata. Due to device
+	 * associated with mmc_card with dev_set_drvdata. Due to device
 	 * partitions, devidx will not coincide with a per-physical card
 	 * index anymore so we keep track of a name index.
 	 */
@@ -2452,7 +2453,7 @@ static int mmc_blk_probe(struct device *dev)
 	if (mmc_blk_alloc_parts(card, md))
 		goto out;
 
-	mmc_set_drvdata(card, md);
+	dev_set_drvdata(dev, md);
 
 	if (mmc_add_disk(md))
 		goto out;
@@ -2485,7 +2486,7 @@ static int mmc_blk_probe(struct device *dev)
 static int mmc_blk_remove(struct device *dev)
 {
 	struct mmc_card *card = mmc_dev_to_card(dev);
-	struct mmc_blk_data *md = mmc_get_drvdata(card);
+	struct mmc_blk_data *md = dev_get_drvdata(dev);
 
 	mmc_blk_remove_parts(card, md);
 	pm_runtime_get_sync(&card->dev);
@@ -2496,7 +2497,7 @@ static int mmc_blk_remove(struct device *dev)
 		pm_runtime_disable(&card->dev);
 	pm_runtime_put_noidle(&card->dev);
 	mmc_blk_remove_req(md);
-	mmc_set_drvdata(card, NULL);
+	dev_set_drvdata(dev, NULL);
 
 	return 0;
 }
@@ -2504,8 +2505,7 @@ static int mmc_blk_remove(struct device *dev)
 static int _mmc_blk_suspend(struct device *dev)
 {
 	struct mmc_blk_data *part_md;
-	struct mmc_card *card = mmc_dev_to_card(dev);
-	struct mmc_blk_data *md = mmc_get_drvdata(card);
+	struct mmc_blk_data *md = dev_get_drvdata(dev);
 
 	if (md) {
 		mmc_queue_suspend(&md->queue);
@@ -2530,8 +2530,7 @@ static int mmc_blk_suspend(struct device *dev)
 static int mmc_blk_resume(struct device *dev)
 {
 	struct mmc_blk_data *part_md;
-	struct mmc_card *card = mmc_dev_to_card(dev);
-	struct mmc_blk_data *md = mmc_get_drvdata(card);
+	struct mmc_blk_data *md = dev_get_drvdata(dev);
 
 	if (md) {
 		/*
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index cf54afe5d86..64f41367641 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -510,8 +510,6 @@ static inline int mmc_card_broken_irq_polling(const struct mmc_card *c)
 #define mmc_dev_to_card(d)	container_of(d, struct mmc_card, dev)
 
 #define mmc_list_to_card(l)	container_of(l, struct mmc_card, node)
-#define mmc_get_drvdata(c)	dev_get_drvdata(&(c)->dev)
-#define mmc_set_drvdata(c,d)	dev_set_drvdata(&(c)->dev, d)
 
 extern int mmc_register_driver(struct device_driver *);
 extern void mmc_unregister_driver(struct device_driver *);
-- 
cgit v1.2.3-70-g09d2


From 390e316c606de2f839389698f4531004cfe1bafd Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 6 Oct 2014 14:39:03 +0200
Subject: mmc: core: Remove unused mmc_list_to_card() macro

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 include/linux/mmc/card.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 64f41367641..0ba8f251f8e 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -509,8 +509,6 @@ static inline int mmc_card_broken_irq_polling(const struct mmc_card *c)
 
 #define mmc_dev_to_card(d)	container_of(d, struct mmc_card, dev)
 
-#define mmc_list_to_card(l)	container_of(l, struct mmc_card, node)
-
 extern int mmc_register_driver(struct device_driver *);
 extern void mmc_unregister_driver(struct device_driver *);
 
-- 
cgit v1.2.3-70-g09d2


From 0f762426769a517d5b278e4e5d579fcea6801734 Mon Sep 17 00:00:00 2001
From: Gwendal Grignou <gwendal@chromium.org>
Date: Thu, 16 Oct 2014 11:27:16 -0700
Subject: mmc: core: Report firmware version for eMMC 5.0 devices.

For eMMC 5.0 compliant device, firmware version is stored in ext_csd.
Report firmware as a 64bit hexa decimal. Vendor can use hexa or ascii
string to report firmware version.
Also add FFU related EXT_CSD register and note if the device is FFU capable.

Signed-off-by: Gwendal Grignou <gwendal@chromium.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/mmc.c   | 27 ++++++++++++++++++++++++++-
 include/linux/mmc/card.h |  3 +++
 include/linux/mmc/mmc.h  |  3 +++
 3 files changed, 32 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index bcde451f6d9..a5e05ceb554 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -628,6 +628,14 @@ static int mmc_read_ext_csd(struct mmc_card *card, u8 *ext_csd)
 		card->ext_csd.data_sector_size = 512;
 	}
 
+	/* eMMC v5 or later */
+	if (card->ext_csd.rev >= 7) {
+		memcpy(card->ext_csd.fwrev, &ext_csd[EXT_CSD_FIRMWARE_VERSION],
+		       MMC_FIRMWARE_LEN);
+		card->ext_csd.ffu_capable =
+			(ext_csd[EXT_CSD_SUPPORTED_MODE] & 0x1) &&
+			!(ext_csd[EXT_CSD_FW_CONFIG] & 0x1);
+	}
 out:
 	return err;
 }
@@ -722,7 +730,7 @@ MMC_DEV_ATTR(csd, "%08x%08x%08x%08x\n", card->raw_csd[0], card->raw_csd[1],
 MMC_DEV_ATTR(date, "%02d/%04d\n", card->cid.month, card->cid.year);
 MMC_DEV_ATTR(erase_size, "%u\n", card->erase_size << 9);
 MMC_DEV_ATTR(preferred_erase_size, "%u\n", card->pref_erase << 9);
-MMC_DEV_ATTR(fwrev, "0x%x\n", card->cid.fwrev);
+MMC_DEV_ATTR(ffu_capable, "%d\n", card->ext_csd.ffu_capable);
 MMC_DEV_ATTR(hwrev, "0x%x\n", card->cid.hwrev);
 MMC_DEV_ATTR(manfid, "0x%06x\n", card->cid.manfid);
 MMC_DEV_ATTR(name, "%s\n", card->cid.prod_name);
@@ -735,6 +743,22 @@ MMC_DEV_ATTR(enhanced_area_size, "%u\n", card->ext_csd.enhanced_area_size);
 MMC_DEV_ATTR(raw_rpmb_size_mult, "%#x\n", card->ext_csd.raw_rpmb_size_mult);
 MMC_DEV_ATTR(rel_sectors, "%#x\n", card->ext_csd.rel_sectors);
 
+static ssize_t mmc_fwrev_show(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct mmc_card *card = mmc_dev_to_card(dev);
+
+	if (card->ext_csd.rev < 7) {
+		return sprintf(buf, "0x%x\n", card->cid.fwrev);
+	} else {
+		return sprintf(buf, "0x%*phN\n", MMC_FIRMWARE_LEN,
+			       card->ext_csd.fwrev);
+	}
+}
+
+static DEVICE_ATTR(fwrev, S_IRUGO, mmc_fwrev_show, NULL);
+
 static struct attribute *mmc_std_attrs[] = {
 	&dev_attr_cid.attr,
 	&dev_attr_csd.attr,
@@ -742,6 +766,7 @@ static struct attribute *mmc_std_attrs[] = {
 	&dev_attr_erase_size.attr,
 	&dev_attr_preferred_erase_size.attr,
 	&dev_attr_fwrev.attr,
+	&dev_attr_ffu_capable.attr,
 	&dev_attr_hwrev.attr,
 	&dev_attr_manfid.attr,
 	&dev_attr_name.attr,
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 0ba8f251f8e..4d69c00497b 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -88,6 +88,9 @@ struct mmc_ext_csd {
 	unsigned int            data_tag_unit_size;     /* DATA TAG UNIT size */
 	unsigned int		boot_ro_lock;		/* ro lock support */
 	bool			boot_ro_lockable;
+	bool			ffu_capable;	/* Firmware upgrade support */
+#define MMC_FIRMWARE_LEN 8
+	u8			fwrev[MMC_FIRMWARE_LEN];  /* FW version */
 	u8			raw_exception_status;	/* 54 */
 	u8			raw_partition_support;	/* 160 */
 	u8			raw_rpmb_size_mult;	/* 168 */
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index 1cd00b3a75b..49ad7a94363 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -296,6 +296,7 @@ struct _mmc_csd {
 #define EXT_CSD_SANITIZE_START		165     /* W */
 #define EXT_CSD_WR_REL_PARAM		166	/* RO */
 #define EXT_CSD_RPMB_MULT		168	/* RO */
+#define EXT_CSD_FW_CONFIG		169	/* R/W */
 #define EXT_CSD_BOOT_WP			173	/* R/W */
 #define EXT_CSD_ERASE_GROUP_DEF		175	/* R/W */
 #define EXT_CSD_PART_CONFIG		179	/* R/W */
@@ -332,6 +333,8 @@ struct _mmc_csd {
 #define EXT_CSD_GENERIC_CMD6_TIME	248	/* RO */
 #define EXT_CSD_CACHE_SIZE		249	/* RO, 4 bytes */
 #define EXT_CSD_PWR_CL_DDR_200_360	253	/* RO */
+#define EXT_CSD_FIRMWARE_VERSION	254	/* RO, 8 bytes */
+#define EXT_CSD_SUPPORTED_MODE		493	/* RO */
 #define EXT_CSD_TAG_UNIT_SIZE		498	/* RO */
 #define EXT_CSD_DATA_TAG_SUPPORT	499	/* RO */
 #define EXT_CSD_MAX_PACKED_WRITES	500	/* RO */
-- 
cgit v1.2.3-70-g09d2


From 9cbef73cb657ff795c130cccfed251f0ae923abb Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Date: Fri, 17 Oct 2014 10:26:36 +0200
Subject: mmc: atmel-mci: move mach header to platform_data

Move the mach header that can come either from arm/mach-at91 or avr32 to
platform_data to be able to switch the AT91 platforms to multiplatform.

Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Ludovic Desroches <ludovic.desroches@atmel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
[Ulf: Fixed compile error]
---
 drivers/mmc/host/atmel-mci.c                |  2 +-
 include/linux/platform_data/mmc-atmel-mci.h | 22 ++++++++++++++++++++++
 2 files changed, 23 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/platform_data/mmc-atmel-mci.h

(limited to 'include')

diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index 77250d4b197..0b9ddf8aed0 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -30,11 +30,11 @@
 #include <linux/stat.h>
 #include <linux/types.h>
 #include <linux/platform_data/atmel.h>
+#include <linux/platform_data/mmc-atmel-mci.h>
 
 #include <linux/mmc/host.h>
 #include <linux/mmc/sdio.h>
 
-#include <mach/atmel-mci.h>
 #include <linux/atmel-mci.h>
 #include <linux/atmel_pdc.h>
 
diff --git a/include/linux/platform_data/mmc-atmel-mci.h b/include/linux/platform_data/mmc-atmel-mci.h
new file mode 100644
index 00000000000..399a2d5a14b
--- /dev/null
+++ b/include/linux/platform_data/mmc-atmel-mci.h
@@ -0,0 +1,22 @@
+#ifndef __MMC_ATMEL_MCI_H
+#define __MMC_ATMEL_MCI_H
+
+#include <linux/platform_data/dma-atmel.h>
+#include <linux/platform_data/dma-dw.h>
+
+/**
+ * struct mci_dma_data - DMA data for MCI interface
+ */
+struct mci_dma_data {
+#ifdef CONFIG_ARM
+	struct at_dma_slave     sdata;
+#else
+	struct dw_dma_slave     sdata;
+#endif
+};
+
+/* accessor macros */
+#define	slave_data_ptr(s)	(&(s)->sdata)
+#define find_slave_dev(s)	((s)->sdata.dma_dev)
+
+#endif /* __MMC_ATMEL_MCI_H */
-- 
cgit v1.2.3-70-g09d2


From 6130e7a9c34d01afbd4e7e215846d1f2d70333bb Mon Sep 17 00:00:00 2001
From: Doug Anderson <dianders@chromium.org>
Date: Tue, 14 Oct 2014 09:33:09 -0700
Subject: mmc: dw_mmc: Remove old card detect infrastructure

The dw_mmc driver had a bunch of code that ran whenever a card was
ejected and inserted.  However, this code was old and crufty and
should be removed.  Some evidence that it's really not needed:

1. Is is supposed to be legal to use 'cd-gpio' on dw_mmc instead of
   using the built-in card detect mechanism.  The 'cd-gpio' code
   doesn't run any of the crufty old code but yet still works.

2. While looking at this, I realized that my old change (369ac86 mmc:
   dw_mmc: don't queue up a card detect at slot startup) actually
   castrated the old code a little bit already and nobody noticed.
   Specifically "last_detect_state" was left as 0 at bootup.  That
   means that on the first card removal none of the crufty code ran.

3. I can run "while true; do dd if=/dev/mmcblk1 of=/dev/null; done"
   while ejecting and inserting an SD Card and the world doesn't
   explode.

If some of the crufty old code is actually needed, we should justify
it and also put it in some place where it will be run even with
"cd-gpio".

Note that in my case I'm using the "cd-gpio" mechanism but for various
reasons the hardware triggers a dw_mmc "card detect" at bootup.  That
was actually causing a real bug.  The card detect workqueue was
running while the system was trying to enumerate the card.  The
"present != slot->last_detect_state" triggered and we were doing all
kinds of crazy stuff and messing up enumeration.  The new mechanism of
just asking the core to check the card is much safer and then the
bogus interrupt doesn't hurt.

Signed-off-by: Doug Anderson <dianders@chromium.org>
Tested-by: Jaehoon Chung <jh80.chung@samsung.com>
Acked-by: Jaehoon Chung <jh80.chung@samsung.com>
Tested-by: alim.akhtar <alim.akhtar@samsung.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/dw_mmc.c  | 121 ++++++++-------------------------------------
 drivers/mmc/host/dw_mmc.h  |   2 -
 include/linux/mmc/dw_mmc.h |   2 -
 3 files changed, 20 insertions(+), 105 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 545f62191af..bb46b1b8d16 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -34,7 +34,6 @@
 #include <linux/mmc/dw_mmc.h>
 #include <linux/bitops.h>
 #include <linux/regulator/consumer.h>
-#include <linux/workqueue.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 #include <linux/mmc/slot-gpio.h>
@@ -1959,6 +1958,23 @@ static void dw_mci_cmd_interrupt(struct dw_mci *host, u32 status)
 	tasklet_schedule(&host->tasklet);
 }
 
+static void dw_mci_handle_cd(struct dw_mci *host)
+{
+	int i;
+
+	for (i = 0; i < host->num_slots; i++) {
+		struct dw_mci_slot *slot = host->slot[i];
+
+		if (!slot)
+			continue;
+
+		if (slot->mmc->ops->card_event)
+			slot->mmc->ops->card_event(slot->mmc);
+		mmc_detect_change(slot->mmc,
+			msecs_to_jiffies(host->pdata->detect_delay_ms));
+	}
+}
+
 static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 {
 	struct dw_mci *host = dev_id;
@@ -2034,7 +2050,7 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 
 		if (pending & SDMMC_INT_CD) {
 			mci_writel(host, RINTSTS, SDMMC_INT_CD);
-			queue_work(host->card_workqueue, &host->card_work);
+			dw_mci_handle_cd(host);
 		}
 
 		/* Handle SDIO Interrupts */
@@ -2061,88 +2077,6 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static void dw_mci_work_routine_card(struct work_struct *work)
-{
-	struct dw_mci *host = container_of(work, struct dw_mci, card_work);
-	int i;
-
-	for (i = 0; i < host->num_slots; i++) {
-		struct dw_mci_slot *slot = host->slot[i];
-		struct mmc_host *mmc = slot->mmc;
-		struct mmc_request *mrq;
-		int present;
-
-		present = dw_mci_get_cd(mmc);
-		while (present != slot->last_detect_state) {
-			dev_dbg(&slot->mmc->class_dev, "card %s\n",
-				present ? "inserted" : "removed");
-
-			spin_lock_bh(&host->lock);
-
-			/* Card change detected */
-			slot->last_detect_state = present;
-
-			/* Clean up queue if present */
-			mrq = slot->mrq;
-			if (mrq) {
-				if (mrq == host->mrq) {
-					host->data = NULL;
-					host->cmd = NULL;
-
-					switch (host->state) {
-					case STATE_IDLE:
-					case STATE_WAITING_CMD11_DONE:
-						break;
-					case STATE_SENDING_CMD11:
-					case STATE_SENDING_CMD:
-						mrq->cmd->error = -ENOMEDIUM;
-						if (!mrq->data)
-							break;
-						/* fall through */
-					case STATE_SENDING_DATA:
-						mrq->data->error = -ENOMEDIUM;
-						dw_mci_stop_dma(host);
-						break;
-					case STATE_DATA_BUSY:
-					case STATE_DATA_ERROR:
-						if (mrq->data->error == -EINPROGRESS)
-							mrq->data->error = -ENOMEDIUM;
-						/* fall through */
-					case STATE_SENDING_STOP:
-						if (mrq->stop)
-							mrq->stop->error = -ENOMEDIUM;
-						break;
-					}
-
-					dw_mci_request_end(host, mrq);
-				} else {
-					list_del(&slot->queue_node);
-					mrq->cmd->error = -ENOMEDIUM;
-					if (mrq->data)
-						mrq->data->error = -ENOMEDIUM;
-					if (mrq->stop)
-						mrq->stop->error = -ENOMEDIUM;
-
-					spin_unlock(&host->lock);
-					mmc_request_done(slot->mmc, mrq);
-					spin_lock(&host->lock);
-				}
-			}
-
-			/* Power down slot */
-			if (present == 0)
-				dw_mci_reset(host);
-
-			spin_unlock_bh(&host->lock);
-
-			present = dw_mci_get_cd(mmc);
-		}
-
-		mmc_detect_change(slot->mmc,
-			msecs_to_jiffies(host->pdata->detect_delay_ms));
-	}
-}
-
 #ifdef CONFIG_OF
 /* given a slot id, find out the device node representing that slot */
 static struct device_node *dw_mci_of_find_slot_node(struct device *dev, u8 slot)
@@ -2294,9 +2228,6 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	dw_mci_init_debugfs(slot);
 #endif
 
-	/* Card initially undetected */
-	slot->last_detect_state = 0;
-
 	return 0;
 
 err_host_allocated:
@@ -2677,17 +2608,10 @@ int dw_mci_probe(struct dw_mci *host)
 		host->data_offset = DATA_240A_OFFSET;
 
 	tasklet_init(&host->tasklet, dw_mci_tasklet_func, (unsigned long)host);
-	host->card_workqueue = alloc_workqueue("dw-mci-card",
-			WQ_MEM_RECLAIM, 1);
-	if (!host->card_workqueue) {
-		ret = -ENOMEM;
-		goto err_dmaunmap;
-	}
-	INIT_WORK(&host->card_work, dw_mci_work_routine_card);
 	ret = devm_request_irq(host->dev, host->irq, dw_mci_interrupt,
 			       host->irq_flags, "dw-mci", host);
 	if (ret)
-		goto err_workqueue;
+		goto err_dmaunmap;
 
 	if (host->pdata->num_slots)
 		host->num_slots = host->pdata->num_slots;
@@ -2723,7 +2647,7 @@ int dw_mci_probe(struct dw_mci *host)
 	} else {
 		dev_dbg(host->dev, "attempted to initialize %d slots, "
 					"but failed on all\n", host->num_slots);
-		goto err_workqueue;
+		goto err_dmaunmap;
 	}
 
 	if (host->quirks & DW_MCI_QUIRK_IDMAC_DTO)
@@ -2731,9 +2655,6 @@ int dw_mci_probe(struct dw_mci *host)
 
 	return 0;
 
-err_workqueue:
-	destroy_workqueue(host->card_workqueue);
-
 err_dmaunmap:
 	if (host->use_dma && host->dma_ops->exit)
 		host->dma_ops->exit(host);
@@ -2767,8 +2688,6 @@ void dw_mci_remove(struct dw_mci *host)
 	mci_writel(host, CLKENA, 0);
 	mci_writel(host, CLKSRC, 0);
 
-	destroy_workqueue(host->card_workqueue);
-
 	if (host->use_dma && host->dma_ops->exit)
 		host->dma_ops->exit(host);
 
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index 01b99e8a919..71d499557ed 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -214,7 +214,6 @@ extern int dw_mci_resume(struct dw_mci *host);
  *	with CONFIG_MMC_CLKGATE.
  * @flags: Random state bits associated with the slot.
  * @id: Number of this slot.
- * @last_detect_state: Most recently observed card detect state.
  */
 struct dw_mci_slot {
 	struct mmc_host		*mmc;
@@ -234,7 +233,6 @@ struct dw_mci_slot {
 #define DW_MMC_CARD_PRESENT	0
 #define DW_MMC_CARD_NEED_INIT	1
 	int			id;
-	int			last_detect_state;
 };
 
 struct dw_mci_tuning_data {
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index 001366927cf..69d08144cfa 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -135,7 +135,6 @@ struct dw_mci {
 	struct mmc_command	stop_abort;
 	unsigned int		prev_blksz;
 	unsigned char		timing;
-	struct workqueue_struct	*card_workqueue;
 
 	/* DMA interface members*/
 	int			use_dma;
@@ -154,7 +153,6 @@ struct dw_mci {
 	u32			stop_cmdr;
 	u32			dir_status;
 	struct tasklet_struct	tasklet;
-	struct work_struct	card_work;
 	unsigned long		pending_events;
 	unsigned long		completed_events;
 	enum dw_mci_state	state;
-- 
cgit v1.2.3-70-g09d2


From e21aa519ee3667d0fabda5d806cc68826e9899e0 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 17 Oct 2014 11:32:32 +0200
Subject: mmc: core: Export mmc_get_ext_csd()

Callers of mmc_send_ext_csd() will be able to decrease code duplication
by using mmc_get_ext_csd() instead. Let's make it available.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/mmc.c     | 31 -------------------------------
 drivers/mmc/core/mmc_ops.c | 29 +++++++++++++++++++++++++++++
 include/linux/mmc/core.h   |  1 +
 3 files changed, 30 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index efaa9f8f07b..02ad79229f6 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -177,37 +177,6 @@ static int mmc_decode_csd(struct mmc_card *card)
 	return 0;
 }
 
-/*
- * Read extended CSD.
- */
-static int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd)
-{
-	int err;
-	u8 *ext_csd;
-
-	if (!card || !new_ext_csd)
-		return -EINVAL;
-
-	if (!mmc_can_ext_csd(card))
-		return -EOPNOTSUPP;
-
-	/*
-	 * As the ext_csd is so large and mostly unused, we don't store the
-	 * raw block in mmc_card.
-	 */
-	ext_csd = kmalloc(512, GFP_KERNEL);
-	if (!ext_csd)
-		return -ENOMEM;
-
-	err = mmc_send_ext_csd(card, ext_csd);
-	if (err)
-		kfree(ext_csd);
-	else
-		*new_ext_csd = ext_csd;
-
-	return err;
-}
-
 static void mmc_select_card_type(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 1db60be43c3..72e1f9b3ed0 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -385,6 +385,35 @@ int mmc_send_ext_csd(struct mmc_card *card, u8 *ext_csd)
 }
 EXPORT_SYMBOL_GPL(mmc_send_ext_csd);
 
+int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd)
+{
+	int err;
+	u8 *ext_csd;
+
+	if (!card || !new_ext_csd)
+		return -EINVAL;
+
+	if (!mmc_can_ext_csd(card))
+		return -EOPNOTSUPP;
+
+	/*
+	 * As the ext_csd is so large and mostly unused, we don't store the
+	 * raw block in mmc_card.
+	 */
+	ext_csd = kmalloc(512, GFP_KERNEL);
+	if (!ext_csd)
+		return -ENOMEM;
+
+	err = mmc_send_ext_csd(card, ext_csd);
+	if (err)
+		kfree(ext_csd);
+	else
+		*new_ext_csd = ext_csd;
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mmc_get_ext_csd);
+
 int mmc_spi_read_ocr(struct mmc_host *host, int highcap, u32 *ocrp)
 {
 	struct mmc_command cmd = {0};
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index f206e29f94d..0a77d3567c2 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -155,6 +155,7 @@ extern int __mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int, bool,
 			bool, bool);
 extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int);
 extern int mmc_send_ext_csd(struct mmc_card *card, u8 *ext_csd);
+extern int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd);
 
 #define MMC_ERASE_ARG		0x00000000
 #define MMC_SECURE_ERASE_ARG	0x80000000
-- 
cgit v1.2.3-70-g09d2


From 2fc91e8b0e1cd89094677d1c9dfba1b26979e48b Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 17 Oct 2014 11:54:22 +0200
Subject: mmc: core: Remove the redundant mmc_send_ext_csd() API

Previous patches has replaced the calls to mmc_send_ext_csd() into
mmc_get_ext_csd(), thus mmc_send_ext_csd() has become redundant. Let's
remove it.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/mmc_ops.c | 10 ++--------
 include/linux/mmc/core.h   |  1 -
 2 files changed, 2 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 72e1f9b3ed0..9a6181bf0c0 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -378,13 +378,6 @@ err:
 	return ret;
 }
 
-int mmc_send_ext_csd(struct mmc_card *card, u8 *ext_csd)
-{
-	return mmc_send_cxd_data(card, card->host, MMC_SEND_EXT_CSD,
-			ext_csd, 512);
-}
-EXPORT_SYMBOL_GPL(mmc_send_ext_csd);
-
 int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd)
 {
 	int err;
@@ -404,7 +397,8 @@ int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd)
 	if (!ext_csd)
 		return -ENOMEM;
 
-	err = mmc_send_ext_csd(card, ext_csd);
+	err = mmc_send_cxd_data(card, card->host, MMC_SEND_EXT_CSD, ext_csd,
+				512);
 	if (err)
 		kfree(ext_csd);
 	else
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index 0a77d3567c2..b11e43c1063 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -154,7 +154,6 @@ extern void mmc_start_bkops(struct mmc_card *card, bool from_exception);
 extern int __mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int, bool,
 			bool, bool);
 extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int);
-extern int mmc_send_ext_csd(struct mmc_card *card, u8 *ext_csd);
 extern int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd);
 
 #define MMC_ERASE_ARG		0x00000000
-- 
cgit v1.2.3-70-g09d2


From 76d5556428fbbdf411504895b516272cad27127d Mon Sep 17 00:00:00 2001
From: Timo Kokkonen <timo.kokkonen@offcode.fi>
Date: Mon, 3 Nov 2014 13:12:59 +0200
Subject: mmc: host: atmel-mci: Add support for non-removable slots

Add support for non-removable slots which have no card detection GPIO
and which should not be polled for a card change.

Signed-off-by: Timo Kokkonen <timo.kokkonen@offcode.fi>
Acked-by: Ludovic Desroches <ludovic.desroches@atmel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/atmel-mci.c | 11 +++++++++--
 include/linux/atmel-mci.h    |  2 ++
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index 0b9ddf8aed0..d9646e5ae2c 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -560,6 +560,9 @@ atmci_of_init(struct platform_device *pdev)
 		pdata->slot[slot_id].detect_is_active_high =
 			of_property_read_bool(cnp, "cd-inverted");
 
+		pdata->slot[slot_id].non_removable =
+			of_property_read_bool(cnp, "non-removable");
+
 		pdata->slot[slot_id].wp_pin =
 			of_get_named_gpio(cnp, "wp-gpios", 0);
 	}
@@ -2206,8 +2209,12 @@ static int __init atmci_init_slot(struct atmel_mci *host,
 		}
 	}
 
-	if (!gpio_is_valid(slot->detect_pin))
-		mmc->caps |= MMC_CAP_NEEDS_POLL;
+	if (!gpio_is_valid(slot->detect_pin)) {
+		if (slot_data->non_removable)
+			mmc->caps |= MMC_CAP_NONREMOVABLE;
+		else
+			mmc->caps |= MMC_CAP_NEEDS_POLL;
+	}
 
 	if (gpio_is_valid(slot->wp_pin)) {
 		if (devm_gpio_request(&host->pdev->dev, slot->wp_pin,
diff --git a/include/linux/atmel-mci.h b/include/linux/atmel-mci.h
index 91b77f8d495..9177947bf03 100644
--- a/include/linux/atmel-mci.h
+++ b/include/linux/atmel-mci.h
@@ -11,6 +11,7 @@
  * @detect_pin: GPIO pin wired to the card detect switch
  * @wp_pin: GPIO pin wired to the write protect sensor
  * @detect_is_active_high: The state of the detect pin when it is active
+ * @non_removable: The slot is not removable, only detect once
  *
  * If a given slot is not present on the board, @bus_width should be
  * set to 0. The other fields are ignored in this case.
@@ -26,6 +27,7 @@ struct mci_slot_pdata {
 	int			detect_pin;
 	int			wp_pin;
 	bool			detect_is_active_high;
+	bool			non_removable;
 };
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 4efaa6fbe1fd5e86ab2fee4cdcfc6873dab60716 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 4 Nov 2014 12:42:39 +0200
Subject: mmc: sdhci: Rename adma_desc to adma_table

In preparation for 64-bit ADMA, rename adma_desc to
adma_table.  That is because members will be added
for descriptor size and table size, so using adma_desc
(which is the table) is confusing.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.c  | 31 ++++++++++++++++---------------
 include/linux/mmc/sdhci.h |  2 +-
 2 files changed, 17 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index e40414ab7ef..f2062b073e0 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -505,7 +505,7 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 	if (host->sg_count == 0)
 		goto unmap_align;
 
-	desc = host->adma_desc;
+	desc = host->adma_table;
 	align = host->align_buffer;
 
 	align_addr = host->align_addr;
@@ -555,14 +555,14 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 		 * If this triggers then we have a calculation bug
 		 * somewhere. :/
 		 */
-		WARN_ON((desc - host->adma_desc) >= ADMA_SIZE);
+		WARN_ON((desc - host->adma_table) >= ADMA_SIZE);
 	}
 
 	if (host->quirks & SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC) {
 		/*
 		* Mark the last descriptor as the terminating descriptor
 		*/
-		if (desc != host->adma_desc) {
+		if (desc != host->adma_table) {
 			desc -= 8;
 			desc[0] |= 0x2; /* end */
 		}
@@ -2294,7 +2294,7 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *mask)
 static void sdhci_adma_show_error(struct sdhci_host *host)
 {
 	const char *name = mmc_hostname(host->mmc);
-	u8 *desc = host->adma_desc;
+	u8 *desc = host->adma_table;
 	__le32 *dma;
 	__le16 *len;
 	u8 attr;
@@ -2875,27 +2875,28 @@ int sdhci_add_host(struct sdhci_host *host)
 		 * (128) and potentially one alignment transfer for
 		 * each of those entries.
 		 */
-		host->adma_desc = dma_alloc_coherent(mmc_dev(mmc),
-						     ADMA_SIZE, &host->adma_addr,
-						     GFP_KERNEL);
+		host->adma_table = dma_alloc_coherent(mmc_dev(mmc),
+						      ADMA_SIZE,
+						      &host->adma_addr,
+						      GFP_KERNEL);
 		host->align_buffer = kmalloc(128 * 4, GFP_KERNEL);
-		if (!host->adma_desc || !host->align_buffer) {
+		if (!host->adma_table || !host->align_buffer) {
 			dma_free_coherent(mmc_dev(mmc), ADMA_SIZE,
-					  host->adma_desc, host->adma_addr);
+					  host->adma_table, host->adma_addr);
 			kfree(host->align_buffer);
 			pr_warn("%s: Unable to allocate ADMA buffers - falling back to standard DMA\n",
 				mmc_hostname(mmc));
 			host->flags &= ~SDHCI_USE_ADMA;
-			host->adma_desc = NULL;
+			host->adma_table = NULL;
 			host->align_buffer = NULL;
 		} else if (host->adma_addr & 3) {
 			pr_warn("%s: unable to allocate aligned ADMA descriptor\n",
 				mmc_hostname(mmc));
 			host->flags &= ~SDHCI_USE_ADMA;
 			dma_free_coherent(mmc_dev(mmc), ADMA_SIZE,
-					  host->adma_desc, host->adma_addr);
+					  host->adma_table, host->adma_addr);
 			kfree(host->align_buffer);
-			host->adma_desc = NULL;
+			host->adma_table = NULL;
 			host->align_buffer = NULL;
 		}
 	}
@@ -3351,12 +3352,12 @@ void sdhci_remove_host(struct sdhci_host *host, int dead)
 	if (!IS_ERR(mmc->supply.vqmmc))
 		regulator_disable(mmc->supply.vqmmc);
 
-	if (host->adma_desc)
+	if (host->adma_table)
 		dma_free_coherent(mmc_dev(mmc), ADMA_SIZE,
-				  host->adma_desc, host->adma_addr);
+				  host->adma_table, host->adma_addr);
 	kfree(host->align_buffer);
 
-	host->adma_desc = NULL;
+	host->adma_table = NULL;
 	host->align_buffer = NULL;
 }
 
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index dba793e3a33..76e04324cc3 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -155,7 +155,7 @@ struct sdhci_host {
 
 	int sg_count;		/* Mapped sg entries */
 
-	u8 *adma_desc;		/* ADMA descriptor table */
+	u8 *adma_table;		/* ADMA descriptor table */
 	u8 *align_buffer;	/* Bounce buffer */
 
 	dma_addr_t adma_addr;	/* Mapped ADMA descr. table */
-- 
cgit v1.2.3-70-g09d2


From 1c3d5f6ddcb915c0e702cf513bad4a3b1583f48f Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 4 Nov 2014 12:42:41 +0200
Subject: mmc: sdhci: Use 'void *' for not 'u8 *' for ADMA data

It is kernel-style to use 'void *' for anonymous data.
This is being applied to the ADMA bounce buffer which
contains unaligned bytes, and to the ADMA descriptor
table which will contain 32-bit ADMA descriptors
or 64-bit ADMA descriptors when support is added.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.c  | 12 ++++++------
 include/linux/mmc/sdhci.h |  4 ++--
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 19f31ea9973..20e8a2d0d51 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -454,7 +454,7 @@ static void sdhci_kunmap_atomic(void *buffer, unsigned long *flags)
 	local_irq_restore(*flags);
 }
 
-static void sdhci_adma_write_desc(u8 *desc, u32 addr, int len, unsigned cmd)
+static void sdhci_adma_write_desc(void *desc, u32 addr, int len, unsigned cmd)
 {
 	__le32 *dataddr = (__le32 __force *)(desc + 4);
 	__le16 *cmdlen = (__le16 __force *)desc;
@@ -480,8 +480,8 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 {
 	int direction;
 
-	u8 *desc;
-	u8 *align;
+	void *desc;
+	void *align;
 	dma_addr_t addr;
 	dma_addr_t align_addr;
 	int len, offset;
@@ -606,7 +606,7 @@ static void sdhci_adma_table_post(struct sdhci_host *host,
 
 	struct scatterlist *sg;
 	int i, size;
-	u8 *align;
+	void *align;
 	char *buffer;
 	unsigned long flags;
 	bool has_unaligned;
@@ -2301,7 +2301,7 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *mask)
 static void sdhci_adma_show_error(struct sdhci_host *host)
 {
 	const char *name = mmc_hostname(host->mmc);
-	u8 *desc = host->adma_table;
+	void *desc = host->adma_table;
 	__le32 *dma;
 	__le16 *len;
 	u8 attr;
@@ -2311,7 +2311,7 @@ static void sdhci_adma_show_error(struct sdhci_host *host)
 	while (true) {
 		dma = (__le32 *)(desc + 4);
 		len = (__le16 *)(desc + 2);
-		attr = *desc;
+		attr = *(u8 *)desc;
 
 		DBG("%s: %p: DMA 0x%08x, LEN 0x%04x, Attr=0x%02x\n",
 		    name, desc, le32_to_cpu(*dma), le16_to_cpu(*len), attr);
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index 76e04324cc3..933dbbb5074 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -155,8 +155,8 @@ struct sdhci_host {
 
 	int sg_count;		/* Mapped sg entries */
 
-	u8 *adma_table;		/* ADMA descriptor table */
-	u8 *align_buffer;	/* Bounce buffer */
+	void *adma_table;	/* ADMA descriptor table */
+	void *align_buffer;	/* Bounce buffer */
 
 	dma_addr_t adma_addr;	/* Mapped ADMA descr. table */
 	dma_addr_t align_addr;	/* Mapped bounce buffer */
-- 
cgit v1.2.3-70-g09d2


From 76fe379acaeb857f91705f3bd5c6f69ec13872a9 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 4 Nov 2014 12:42:42 +0200
Subject: mmc: sdhci: Parameterize ADMA sizes and alignment

In preparation for 64-bit ADMA, parameterize ADMA sizes
and alignment.  64-bit ADMA has a larger descriptor
because it contains a 64-bit address instead of a 32-bit
address.  Also data must be 8-byte aligned instead
of 4-byte aligned.  Consequently, sdhci_host members
are added for descriptor, table, and buffer sizes
and alignment.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.c  | 68 +++++++++++++++++++++++------------------------
 include/linux/mmc/sdhci.h |  7 +++++
 2 files changed, 41 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 20e8a2d0d51..053b55df9df 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -44,14 +44,6 @@
 
 #define MAX_TUNING_LOOP 40
 
-/*
- * The ADMA2 descriptor table size is calculated as the maximum number of
- * segments (128), times 2 to allow for an alignment descriptor for each
- * segment, plus 1 for a nop end descriptor, all multipled by the 32-bit
- * descriptor size (8).
- */
-#define ADMA_SIZE	((128 * 2 + 1) * 8)
-
 static unsigned int debug_quirks = 0;
 static unsigned int debug_quirks2;
 
@@ -502,10 +494,10 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 		direction = DMA_TO_DEVICE;
 
 	host->align_addr = dma_map_single(mmc_dev(host->mmc),
-		host->align_buffer, 128 * 4, direction);
+		host->align_buffer, host->align_buffer_sz, direction);
 	if (dma_mapping_error(mmc_dev(host->mmc), host->align_addr))
 		goto fail;
-	BUG_ON(host->align_addr & 0x3);
+	BUG_ON(host->align_addr & host->align_mask);
 
 	host->sg_count = dma_map_sg(mmc_dev(host->mmc),
 		data->sg, data->sg_len, direction);
@@ -528,7 +520,8 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 		 * the (up to three) bytes that screw up the
 		 * alignment.
 		 */
-		offset = (4 - (addr & 0x3)) & 0x3;
+		offset = (host->align_sz - (addr & host->align_mask)) &
+			 host->align_mask;
 		if (offset) {
 			if (data->flags & MMC_DATA_WRITE) {
 				buffer = sdhci_kmap_atomic(sg, &flags);
@@ -543,10 +536,10 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 
 			BUG_ON(offset > 65536);
 
-			align += 4;
-			align_addr += 4;
+			align += host->align_sz;
+			align_addr += host->align_sz;
 
-			desc += 8;
+			desc += host->desc_sz;
 
 			addr += offset;
 			len -= offset;
@@ -556,13 +549,13 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 
 		/* tran, valid */
 		sdhci_adma_write_desc(desc, addr, len, 0x21);
-		desc += 8;
+		desc += host->desc_sz;
 
 		/*
 		 * If this triggers then we have a calculation bug
 		 * somewhere. :/
 		 */
-		WARN_ON((desc - host->adma_table) >= ADMA_SIZE);
+		WARN_ON((desc - host->adma_table) >= host->adma_table_sz);
 	}
 
 	if (host->quirks & SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC) {
@@ -570,7 +563,7 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 		* Mark the last descriptor as the terminating descriptor
 		*/
 		if (desc != host->adma_table) {
-			desc -= 8;
+			desc -= host->desc_sz;
 			sdhci_adma_mark_end(desc);
 		}
 	} else {
@@ -587,14 +580,14 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 	 */
 	if (data->flags & MMC_DATA_WRITE) {
 		dma_sync_single_for_device(mmc_dev(host->mmc),
-			host->align_addr, 128 * 4, direction);
+			host->align_addr, host->align_buffer_sz, direction);
 	}
 
 	return 0;
 
 unmap_align:
 	dma_unmap_single(mmc_dev(host->mmc), host->align_addr,
-		128 * 4, direction);
+		host->align_buffer_sz, direction);
 fail:
 	return -EINVAL;
 }
@@ -617,12 +610,12 @@ static void sdhci_adma_table_post(struct sdhci_host *host,
 		direction = DMA_TO_DEVICE;
 
 	dma_unmap_single(mmc_dev(host->mmc), host->align_addr,
-		128 * 4, direction);
+		host->align_buffer_sz, direction);
 
 	/* Do a quick scan of the SG list for any unaligned mappings */
 	has_unaligned = false;
 	for_each_sg(data->sg, sg, host->sg_count, i)
-		if (sg_dma_address(sg) & 3) {
+		if (sg_dma_address(sg) & host->align_mask) {
 			has_unaligned = true;
 			break;
 		}
@@ -634,8 +627,9 @@ static void sdhci_adma_table_post(struct sdhci_host *host,
 		align = host->align_buffer;
 
 		for_each_sg(data->sg, sg, host->sg_count, i) {
-			if (sg_dma_address(sg) & 0x3) {
-				size = 4 - (sg_dma_address(sg) & 0x3);
+			if (sg_dma_address(sg) & host->align_mask) {
+				size = host->align_sz -
+				       (sg_dma_address(sg) & host->align_mask);
 
 				buffer = sdhci_kmap_atomic(sg, &flags);
 				WARN_ON(((long)buffer & (PAGE_SIZE - 1)) >
@@ -643,7 +637,7 @@ static void sdhci_adma_table_post(struct sdhci_host *host,
 				memcpy(buffer, align, size);
 				sdhci_kunmap_atomic(buffer, &flags);
 
-				align += 4;
+				align += host->align_sz;
 			}
 		}
 	}
@@ -2316,7 +2310,7 @@ static void sdhci_adma_show_error(struct sdhci_host *host)
 		DBG("%s: %p: DMA 0x%08x, LEN 0x%04x, Attr=0x%02x\n",
 		    name, desc, le32_to_cpu(*dma), le16_to_cpu(*len), attr);
 
-		desc += 8;
+		desc += host->desc_sz;
 
 		if (attr & 2)
 			break;
@@ -2878,17 +2872,23 @@ int sdhci_add_host(struct sdhci_host *host)
 
 	if (host->flags & SDHCI_USE_ADMA) {
 		/*
-		 * We need to allocate descriptors for all sg entries
-		 * (128) and potentially one alignment transfer for
-		 * each of those entries.
+		 * The DMA descriptor table size is calculated as the maximum
+		 * number of segments times 2, to allow for an alignment
+		 * descriptor for each segment, plus 1 for a nop end descriptor,
+		 * all multipled by the descriptor size.
 		 */
+		host->adma_table_sz = (128 * 2 + 1) * 8;
+		host->align_buffer_sz = 128 * 4;
+		host->desc_sz = 8;
+		host->align_sz = 4;
+		host->align_mask = 3;
 		host->adma_table = dma_alloc_coherent(mmc_dev(mmc),
-						      ADMA_SIZE,
+						      host->adma_table_sz,
 						      &host->adma_addr,
 						      GFP_KERNEL);
-		host->align_buffer = kmalloc(128 * 4, GFP_KERNEL);
+		host->align_buffer = kmalloc(host->align_buffer_sz, GFP_KERNEL);
 		if (!host->adma_table || !host->align_buffer) {
-			dma_free_coherent(mmc_dev(mmc), ADMA_SIZE,
+			dma_free_coherent(mmc_dev(mmc), host->adma_table_sz,
 					  host->adma_table, host->adma_addr);
 			kfree(host->align_buffer);
 			pr_warn("%s: Unable to allocate ADMA buffers - falling back to standard DMA\n",
@@ -2896,11 +2896,11 @@ int sdhci_add_host(struct sdhci_host *host)
 			host->flags &= ~SDHCI_USE_ADMA;
 			host->adma_table = NULL;
 			host->align_buffer = NULL;
-		} else if (host->adma_addr & 3) {
+		} else if (host->adma_addr & host->align_mask) {
 			pr_warn("%s: unable to allocate aligned ADMA descriptor\n",
 				mmc_hostname(mmc));
 			host->flags &= ~SDHCI_USE_ADMA;
-			dma_free_coherent(mmc_dev(mmc), ADMA_SIZE,
+			dma_free_coherent(mmc_dev(mmc), host->adma_table_sz,
 					  host->adma_table, host->adma_addr);
 			kfree(host->align_buffer);
 			host->adma_table = NULL;
@@ -3360,7 +3360,7 @@ void sdhci_remove_host(struct sdhci_host *host, int dead)
 		regulator_disable(mmc->supply.vqmmc);
 
 	if (host->adma_table)
-		dma_free_coherent(mmc_dev(mmc), ADMA_SIZE,
+		dma_free_coherent(mmc_dev(mmc), host->adma_table_sz,
 				  host->adma_table, host->adma_addr);
 	kfree(host->align_buffer);
 
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index 933dbbb5074..2a72e951083 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -158,9 +158,16 @@ struct sdhci_host {
 	void *adma_table;	/* ADMA descriptor table */
 	void *align_buffer;	/* Bounce buffer */
 
+	size_t adma_table_sz;	/* ADMA descriptor table size */
+	size_t align_buffer_sz;	/* Bounce buffer size */
+
 	dma_addr_t adma_addr;	/* Mapped ADMA descr. table */
 	dma_addr_t align_addr;	/* Mapped bounce buffer */
 
+	unsigned int desc_sz;	/* ADMA descriptor size */
+	unsigned int align_sz;	/* ADMA alignment */
+	unsigned int align_mask;	/* ADMA alignment mask */
+
 	struct tasklet_struct finish_tasklet;	/* Tasklet structures */
 
 	struct timer_list timer;	/* Timer for timeouts */
-- 
cgit v1.2.3-70-g09d2


From e57a5f61eae7e145aeeda18ccb22576822f534bf Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 4 Nov 2014 12:42:46 +0200
Subject: mmc: sdhci: Add 64-bit ADMA support

Add 64-bit ADMA support including:
	- add 64-bit ADMA descriptor
	- add SDHCI_USE_64_BIT_DMA flag
	- set upper 32-bits of DMA addresses
	- ability to select 64-bit ADMA
	- ability to use 64-bit ADMA sizes and alignment
	- display "ADMA 64-bit" when host is added

It is assumed that a 64-bit capable device has set a 64-bit DMA mask
and *must* do 64-bit DMA.  A driver has the opportunity to change
that during the first call to ->enable_dma().  Similarly
SDHCI_QUIRK2_BROKEN_64_BIT_DMA must be left to the drivers to
implement.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.c  | 109 ++++++++++++++++++++++++++++++++++------------
 drivers/mmc/host/sdhci.h  |  18 ++++++++
 include/linux/mmc/sdhci.h |   3 ++
 3 files changed, 102 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index ec093490a24..f895ab07fcc 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -117,10 +117,17 @@ static void sdhci_dumpregs(struct sdhci_host *host)
 	pr_debug(DRIVER_NAME ": Host ctl2: 0x%08x\n",
 		sdhci_readw(host, SDHCI_HOST_CONTROL2));
 
-	if (host->flags & SDHCI_USE_ADMA)
-		pr_debug(DRIVER_NAME ": ADMA Err: 0x%08x | ADMA Ptr: 0x%08x\n",
-		       readl(host->ioaddr + SDHCI_ADMA_ERROR),
-		       readl(host->ioaddr + SDHCI_ADMA_ADDRESS));
+	if (host->flags & SDHCI_USE_ADMA) {
+		if (host->flags & SDHCI_USE_64_BIT_DMA)
+			pr_debug(DRIVER_NAME ": ADMA Err: 0x%08x | ADMA Ptr: 0x%08x%08x\n",
+				 readl(host->ioaddr + SDHCI_ADMA_ERROR),
+				 readl(host->ioaddr + SDHCI_ADMA_ADDRESS_HI),
+				 readl(host->ioaddr + SDHCI_ADMA_ADDRESS));
+		else
+			pr_debug(DRIVER_NAME ": ADMA Err: 0x%08x | ADMA Ptr: 0x%08x\n",
+				 readl(host->ioaddr + SDHCI_ADMA_ERROR),
+				 readl(host->ioaddr + SDHCI_ADMA_ADDRESS));
+	}
 
 	pr_debug(DRIVER_NAME ": ===========================================\n");
 }
@@ -446,19 +453,25 @@ static void sdhci_kunmap_atomic(void *buffer, unsigned long *flags)
 	local_irq_restore(*flags);
 }
 
-static void sdhci_adma_write_desc(void *desc, u32 addr, int len, unsigned cmd)
+static void sdhci_adma_write_desc(struct sdhci_host *host, void *desc,
+				  dma_addr_t addr, int len, unsigned cmd)
 {
-	struct sdhci_adma2_32_desc *dma_desc = desc;
+	struct sdhci_adma2_64_desc *dma_desc = desc;
 
+	/* 32-bit and 64-bit descriptors have these members in same position */
 	dma_desc->cmd = cpu_to_le16(cmd);
 	dma_desc->len = cpu_to_le16(len);
-	dma_desc->addr = cpu_to_le32(addr);
+	dma_desc->addr_lo = cpu_to_le32((u32)addr);
+
+	if (host->flags & SDHCI_USE_64_BIT_DMA)
+		dma_desc->addr_hi = cpu_to_le32((u64)addr >> 32);
 }
 
 static void sdhci_adma_mark_end(void *desc)
 {
-	struct sdhci_adma2_32_desc *dma_desc = desc;
+	struct sdhci_adma2_64_desc *dma_desc = desc;
 
+	/* 32-bit and 64-bit descriptors have 'cmd' in same position */
 	dma_desc->cmd |= cpu_to_le16(ADMA2_END);
 }
 
@@ -527,7 +540,7 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 			}
 
 			/* tran, valid */
-			sdhci_adma_write_desc(desc, align_addr, offset,
+			sdhci_adma_write_desc(host, desc, align_addr, offset,
 					      ADMA2_TRAN_VALID);
 
 			BUG_ON(offset > 65536);
@@ -544,7 +557,7 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 		BUG_ON(len > 65536);
 
 		/* tran, valid */
-		sdhci_adma_write_desc(desc, addr, len, ADMA2_TRAN_VALID);
+		sdhci_adma_write_desc(host, desc, addr, len, ADMA2_TRAN_VALID);
 		desc += host->desc_sz;
 
 		/*
@@ -568,7 +581,7 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 		*/
 
 		/* nop, end, valid */
-		sdhci_adma_write_desc(desc, 0, 0, ADMA2_NOP_END_VALID);
+		sdhci_adma_write_desc(host, desc, 0, 0, ADMA2_NOP_END_VALID);
 	}
 
 	/*
@@ -827,6 +840,10 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
 			} else {
 				sdhci_writel(host, host->adma_addr,
 					SDHCI_ADMA_ADDRESS);
+				if (host->flags & SDHCI_USE_64_BIT_DMA)
+					sdhci_writel(host,
+						     (u64)host->adma_addr >> 32,
+						     SDHCI_ADMA_ADDRESS_HI);
 			}
 		} else {
 			int sg_cnt;
@@ -860,10 +877,14 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
 		ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
 		ctrl &= ~SDHCI_CTRL_DMA_MASK;
 		if ((host->flags & SDHCI_REQ_USE_DMA) &&
-			(host->flags & SDHCI_USE_ADMA))
-			ctrl |= SDHCI_CTRL_ADMA32;
-		else
+			(host->flags & SDHCI_USE_ADMA)) {
+			if (host->flags & SDHCI_USE_64_BIT_DMA)
+				ctrl |= SDHCI_CTRL_ADMA64;
+			else
+				ctrl |= SDHCI_CTRL_ADMA32;
+		} else {
 			ctrl |= SDHCI_CTRL_SDMA;
+		}
 		sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
 	}
 
@@ -2296,12 +2317,19 @@ static void sdhci_adma_show_error(struct sdhci_host *host)
 	sdhci_dumpregs(host);
 
 	while (true) {
-		struct sdhci_adma2_32_desc *dma_desc = desc;
-
-		DBG("%s: %p: DMA 0x%08x, LEN 0x%04x, Attr=0x%02x\n",
-		    name, desc, le32_to_cpu(dma_desc->addr),
-		    le16_to_cpu(dma_desc->len),
-		    le16_to_cpu(dma_desc->cmd));
+		struct sdhci_adma2_64_desc *dma_desc = desc;
+
+		if (host->flags & SDHCI_USE_64_BIT_DMA)
+			DBG("%s: %p: DMA 0x%08x%08x, LEN 0x%04x, Attr=0x%02x\n",
+			    name, desc, le32_to_cpu(dma_desc->addr_hi),
+			    le32_to_cpu(dma_desc->addr_lo),
+			    le16_to_cpu(dma_desc->len),
+			    le16_to_cpu(dma_desc->cmd));
+		else
+			DBG("%s: %p: DMA 0x%08x, LEN 0x%04x, Attr=0x%02x\n",
+			    name, desc, le32_to_cpu(dma_desc->addr_lo),
+			    le16_to_cpu(dma_desc->len),
+			    le16_to_cpu(dma_desc->cmd));
 
 		desc += host->desc_sz;
 
@@ -2852,6 +2880,16 @@ int sdhci_add_host(struct sdhci_host *host)
 		host->flags &= ~SDHCI_USE_ADMA;
 	}
 
+	/*
+	 * It is assumed that a 64-bit capable device has set a 64-bit DMA mask
+	 * and *must* do 64-bit DMA.  A driver has the opportunity to change
+	 * that during the first call to ->enable_dma().  Similarly
+	 * SDHCI_QUIRK2_BROKEN_64_BIT_DMA must be left to the drivers to
+	 * implement.
+	 */
+	if (sdhci_readl(host, SDHCI_CAPABILITIES) & SDHCI_CAN_64BIT)
+		host->flags |= SDHCI_USE_64_BIT_DMA;
+
 	if (host->flags & (SDHCI_USE_SDMA | SDHCI_USE_ADMA)) {
 		if (host->ops->enable_dma) {
 			if (host->ops->enable_dma(host)) {
@@ -2863,6 +2901,10 @@ int sdhci_add_host(struct sdhci_host *host)
 		}
 	}
 
+	/* SDMA does not support 64-bit DMA */
+	if (host->flags & SDHCI_USE_64_BIT_DMA)
+		host->flags &= ~SDHCI_USE_SDMA;
+
 	if (host->flags & SDHCI_USE_ADMA) {
 		/*
 		 * The DMA descriptor table size is calculated as the maximum
@@ -2870,13 +2912,23 @@ int sdhci_add_host(struct sdhci_host *host)
 		 * descriptor for each segment, plus 1 for a nop end descriptor,
 		 * all multipled by the descriptor size.
 		 */
-		host->adma_table_sz = (SDHCI_MAX_SEGS * 2 + 1) *
-				      SDHCI_ADMA2_32_DESC_SZ;
-		host->align_buffer_sz = SDHCI_MAX_SEGS *
-					SDHCI_ADMA2_32_ALIGN;
-		host->desc_sz = SDHCI_ADMA2_32_DESC_SZ;
-		host->align_sz = SDHCI_ADMA2_32_ALIGN;
-		host->align_mask = SDHCI_ADMA2_32_ALIGN - 1;
+		if (host->flags & SDHCI_USE_64_BIT_DMA) {
+			host->adma_table_sz = (SDHCI_MAX_SEGS * 2 + 1) *
+					      SDHCI_ADMA2_64_DESC_SZ;
+			host->align_buffer_sz = SDHCI_MAX_SEGS *
+						SDHCI_ADMA2_64_ALIGN;
+			host->desc_sz = SDHCI_ADMA2_64_DESC_SZ;
+			host->align_sz = SDHCI_ADMA2_64_ALIGN;
+			host->align_mask = SDHCI_ADMA2_64_ALIGN - 1;
+		} else {
+			host->adma_table_sz = (SDHCI_MAX_SEGS * 2 + 1) *
+					      SDHCI_ADMA2_32_DESC_SZ;
+			host->align_buffer_sz = SDHCI_MAX_SEGS *
+						SDHCI_ADMA2_32_ALIGN;
+			host->desc_sz = SDHCI_ADMA2_32_DESC_SZ;
+			host->align_sz = SDHCI_ADMA2_32_ALIGN;
+			host->align_mask = SDHCI_ADMA2_32_ALIGN - 1;
+		}
 		host->adma_table = dma_alloc_coherent(mmc_dev(mmc),
 						      host->adma_table_sz,
 						      &host->adma_addr,
@@ -3289,7 +3341,8 @@ int sdhci_add_host(struct sdhci_host *host)
 
 	pr_info("%s: SDHCI controller on %s [%s] using %s\n",
 		mmc_hostname(mmc), host->hw_name, dev_name(mmc_dev(mmc)),
-		(host->flags & SDHCI_USE_ADMA) ? "ADMA" :
+		(host->flags & SDHCI_USE_ADMA) ?
+		(host->flags & SDHCI_USE_64_BIT_DMA) ? "ADMA 64-bit" : "ADMA" :
 		(host->flags & SDHCI_USE_SDMA) ? "DMA" : "PIO");
 
 	sdhci_enable_card_detection(host);
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 14c8b6773db..c2ec7fcd8a1 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -227,6 +227,7 @@
 /* 55-57 reserved */
 
 #define SDHCI_ADMA_ADDRESS	0x58
+#define SDHCI_ADMA_ADDRESS_HI	0x5C
 
 /* 60-FB reserved */
 
@@ -279,6 +280,23 @@ struct sdhci_adma2_32_desc {
 	__le32	addr;
 }  __packed __aligned(SDHCI_ADMA2_32_ALIGN);
 
+/* ADMA2 64-bit DMA descriptor size */
+#define SDHCI_ADMA2_64_DESC_SZ	12
+
+/* ADMA2 64-bit DMA alignment */
+#define SDHCI_ADMA2_64_ALIGN	8
+
+/*
+ * ADMA2 64-bit descriptor. Note 12-byte descriptor can't always be 8-byte
+ * aligned.
+ */
+struct sdhci_adma2_64_desc {
+	__le16	cmd;
+	__le16	len;
+	__le32	addr_lo;
+	__le32	addr_hi;
+}  __packed __aligned(4);
+
 #define ADMA2_TRAN_VALID	0x21
 #define ADMA2_NOP_END_VALID	0x3
 #define ADMA2_END		0x2
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index 2a72e951083..931ac5e0545 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -100,6 +100,8 @@ struct sdhci_host {
 #define SDHCI_QUIRK2_BROKEN_DDR50			(1<<7)
 /* Stop command (CMD12) can set Transfer Complete when not using MMC_RSP_BUSY */
 #define SDHCI_QUIRK2_STOP_WITH_TC			(1<<8)
+/* Controller does not support 64-bit DMA */
+#define SDHCI_QUIRK2_BROKEN_64_BIT_DMA			(1<<9)
 
 	int irq;		/* Device IRQ */
 	void __iomem *ioaddr;	/* Mapped address */
@@ -130,6 +132,7 @@ struct sdhci_host {
 #define SDHCI_SDIO_IRQ_ENABLED	(1<<9)	/* SDIO irq enabled */
 #define SDHCI_SDR104_NEEDS_TUNING (1<<10)	/* SDR104/HS200 needs tuning */
 #define SDHCI_USING_RETUNING_TIMER (1<<11)	/* Host is using a retuning timer for the card */
+#define SDHCI_USE_64_BIT_DMA	(1<<12)	/* Use 64-bit DMA */
 
 	unsigned int version;	/* SDHCI spec. version */
 
-- 
cgit v1.2.3-70-g09d2


From 9216efafc52ff99e9351ef60de5fcafc2bc8adb6 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Wed, 1 Oct 2014 15:20:33 +0200
Subject: asm-generic/io.h: Reconcile I/O accessor overrides

Overriding I/O accessors and helpers is currently very inconsistent.
This commit introduces a homogeneous way to override functions by
checking for the existence of a macro with the same of the function.
Architectures can provide their own implementations and communicate this
to the generic header by defining the appropriate macro. Doing this will
also help prevent the implementations from being subsequently
overridden.

While at it, also turn a lot of macros into static inline functions for
better type checking and to provide a canonical signature for overriding
architectures to copy. Also reorder functions by logical groups.

Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 include/asm-generic/io.h | 445 +++++++++++++++++++++++++++++++++++++----------
 1 file changed, 350 insertions(+), 95 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index b8fdc57a733..fb62c621acf 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -12,6 +12,7 @@
 #define __ASM_GENERIC_IO_H
 
 #include <asm/page.h> /* I/O is all done through memory accesses */
+#include <linux/string.h> /* for memset() and memcpy() */
 #include <linux/types.h>
 
 #ifdef CONFIG_GENERIC_IOMAP
@@ -24,142 +25,154 @@
 #define mmiowb() do {} while (0)
 #endif
 
-/*****************************************************************************/
 /*
- * readX/writeX() are used to access memory mapped devices. On some
- * architectures the memory mapped IO stuff needs to be accessed
- * differently. On the simple architectures, we just read/write the
- * memory location directly.
+ * __raw_{read,write}{b,w,l,q}() access memory in native endianness.
+ *
+ * On some architectures memory mapped IO needs to be accessed differently.
+ * On the simple architectures, we just read/write the memory location
+ * directly.
  */
+
 #ifndef __raw_readb
+#define __raw_readb __raw_readb
 static inline u8 __raw_readb(const volatile void __iomem *addr)
 {
-	return *(const volatile u8 __force *) addr;
+	return *(const volatile u8 __force *)addr;
 }
 #endif
 
 #ifndef __raw_readw
+#define __raw_readw __raw_readw
 static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
-	return *(const volatile u16 __force *) addr;
+	return *(const volatile u16 __force *)addr;
 }
 #endif
 
 #ifndef __raw_readl
+#define __raw_readl __raw_readl
 static inline u32 __raw_readl(const volatile void __iomem *addr)
 {
-	return *(const volatile u32 __force *) addr;
+	return *(const volatile u32 __force *)addr;
 }
 #endif
 
-#define readb __raw_readb
-
-#define readw readw
-static inline u16 readw(const volatile void __iomem *addr)
-{
-	return __le16_to_cpu(__raw_readw(addr));
-}
-
-#define readl readl
-static inline u32 readl(const volatile void __iomem *addr)
+#ifdef CONFIG_64BIT
+#ifndef __raw_readq
+#define __raw_readq __raw_readq
+static inline u64 __raw_readq(const volatile void __iomem *addr)
 {
-	return __le32_to_cpu(__raw_readl(addr));
+	return *(const volatile u64 __force *)addr;
 }
+#endif
+#endif /* CONFIG_64BIT */
 
 #ifndef __raw_writeb
-static inline void __raw_writeb(u8 b, volatile void __iomem *addr)
+#define __raw_writeb __raw_writeb
+static inline void __raw_writeb(u8 value, volatile void __iomem *addr)
 {
-	*(volatile u8 __force *) addr = b;
+	*(volatile u8 __force *)addr = value;
 }
 #endif
 
 #ifndef __raw_writew
-static inline void __raw_writew(u16 b, volatile void __iomem *addr)
+#define __raw_writew __raw_writew
+static inline void __raw_writew(u16 value, volatile void __iomem *addr)
 {
-	*(volatile u16 __force *) addr = b;
+	*(volatile u16 __force *)addr = value;
 }
 #endif
 
 #ifndef __raw_writel
-static inline void __raw_writel(u32 b, volatile void __iomem *addr)
+#define __raw_writel __raw_writel
+static inline void __raw_writel(u32 value, volatile void __iomem *addr)
 {
-	*(volatile u32 __force *) addr = b;
+	*(volatile u32 __force *)addr = value;
 }
 #endif
 
-#define writeb __raw_writeb
-#define writew(b,addr) __raw_writew(__cpu_to_le16(b),addr)
-#define writel(b,addr) __raw_writel(__cpu_to_le32(b),addr)
-
 #ifdef CONFIG_64BIT
-#ifndef __raw_readq
-static inline u64 __raw_readq(const volatile void __iomem *addr)
+#ifndef __raw_writeq
+#define __raw_writeq __raw_writeq
+static inline void __raw_writeq(u64 value, volatile void __iomem *addr)
 {
-	return *(const volatile u64 __force *) addr;
+	*(volatile u64 __force *)addr = value;
 }
 #endif
+#endif /* CONFIG_64BIT */
 
-#define readq readq
-static inline u64 readq(const volatile void __iomem *addr)
-{
-	return __le64_to_cpu(__raw_readq(addr));
-}
+/*
+ * {read,write}{b,w,l,q}() access little endian memory and return result in
+ * native endianness.
+ */
 
-#ifndef __raw_writeq
-static inline void __raw_writeq(u64 b, volatile void __iomem *addr)
+#ifndef readb
+#define readb readb
+static inline u8 readb(const volatile void __iomem *addr)
 {
-	*(volatile u64 __force *) addr = b;
+	return __raw_readb(addr);
 }
 #endif
 
-#define writeq(b, addr) __raw_writeq(__cpu_to_le64(b), addr)
-#endif /* CONFIG_64BIT */
-
-#ifndef PCI_IOBASE
-#define PCI_IOBASE ((void __iomem *) 0)
+#ifndef readw
+#define readw readw
+static inline u16 readw(const volatile void __iomem *addr)
+{
+	return __le16_to_cpu(__raw_readw(addr));
+}
 #endif
 
-/*****************************************************************************/
-/*
- * traditional input/output functions
- */
-
-static inline u8 inb(unsigned long addr)
+#ifndef readl
+#define readl readl
+static inline u32 readl(const volatile void __iomem *addr)
 {
-	return readb(addr + PCI_IOBASE);
+	return __le32_to_cpu(__raw_readl(addr));
 }
+#endif
 
-static inline u16 inw(unsigned long addr)
+#ifdef CONFIG_64BIT
+#ifndef readq
+#define readq readq
+static inline u64 readq(const volatile void __iomem *addr)
 {
-	return readw(addr + PCI_IOBASE);
+	return __le64_to_cpu(__raw_readq(addr));
 }
+#endif
+#endif /* CONFIG_64BIT */
 
-static inline u32 inl(unsigned long addr)
+#ifndef writeb
+#define writeb writeb
+static inline void writeb(u8 value, volatile void __iomem *addr)
 {
-	return readl(addr + PCI_IOBASE);
+	__raw_writeb(value, addr);
 }
+#endif
 
-static inline void outb(u8 b, unsigned long addr)
+#ifndef writew
+#define writew writew
+static inline void writew(u16 value, volatile void __iomem *addr)
 {
-	writeb(b, addr + PCI_IOBASE);
+	__raw_writew(cpu_to_le16(value), addr);
 }
+#endif
 
-static inline void outw(u16 b, unsigned long addr)
+#ifndef writel
+#define writel writel
+static inline void writel(u32 value, volatile void __iomem *addr)
 {
-	writew(b, addr + PCI_IOBASE);
+	__raw_writel(__cpu_to_le32(value), addr);
 }
+#endif
 
-static inline void outl(u32 b, unsigned long addr)
+#ifdef CONFIG_64BIT
+#ifndef writeq
+#define writeq writeq
+static inline void writeq(u64 value, volatile void __iomem *addr)
 {
-	writel(b, addr + PCI_IOBASE);
+	__raw_writeq(__cpu_to_le64(value), addr);
 }
-
-#define inb_p(addr)	inb(addr)
-#define inw_p(addr)	inw(addr)
-#define inl_p(addr)	inl(addr)
-#define outb_p(x, addr)	outb((x), (addr))
-#define outw_p(x, addr)	outw((x), (addr))
-#define outl_p(x, addr)	outl((x), (addr))
+#endif
+#endif /* CONFIG_64BIT */
 
 #ifndef insb
 static inline void insb(unsigned long addr, void *buffer, int count)
@@ -237,18 +250,6 @@ static inline void outsl(unsigned long addr, const void *buffer, int count)
 #endif
 
 #ifndef CONFIG_GENERIC_IOMAP
-#define ioread8(addr)		readb(addr)
-#define ioread16(addr)		readw(addr)
-#define ioread16be(addr)	__be16_to_cpu(__raw_readw(addr))
-#define ioread32(addr)		readl(addr)
-#define ioread32be(addr)	__be32_to_cpu(__raw_readl(addr))
-
-#define iowrite8(v, addr)	writeb((v), (addr))
-#define iowrite16(v, addr)	writew((v), (addr))
-#define iowrite16be(v, addr)	__raw_writew(__cpu_to_be16(v), addr)
-#define iowrite32(v, addr)	writel((v), (addr))
-#define iowrite32be(v, addr)	__raw_writel(__cpu_to_be32(v), addr)
-
 #define ioread8_rep(p, dst, count) \
 	insb((unsigned long) (p), (dst), (count))
 #define ioread16_rep(p, dst, count) \
@@ -264,20 +265,209 @@ static inline void outsl(unsigned long addr, const void *buffer, int count)
 	outsl((unsigned long) (p), (src), (count))
 #endif /* CONFIG_GENERIC_IOMAP */
 
+#ifndef PCI_IOBASE
+#define PCI_IOBASE ((void __iomem *)0)
+#endif
+
 #ifndef IO_SPACE_LIMIT
 #define IO_SPACE_LIMIT 0xffff
 #endif
 
+/*
+ * {in,out}{b,w,l}() access little endian I/O. {in,out}{b,w,l}_p() can be
+ * implemented on hardware that needs an additional delay for I/O accesses to
+ * take effect.
+ */
+
+#ifndef inb
+#define inb inb
+static inline u8 inb(unsigned long addr)
+{
+	return readb(PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef inw
+#define inw inw
+static inline u16 inw(unsigned long addr)
+{
+	return readw(PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef inl
+#define inl inl
+static inline u32 inl(unsigned long addr)
+{
+	return readl(PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef outb
+#define outb outb
+static inline void outb(u8 value, unsigned long addr)
+{
+	writeb(value, PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef outw
+#define outw outw
+static inline void outw(u16 value, unsigned long addr)
+{
+	writew(value, PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef outl
+#define outl outl
+static inline void outl(u32 value, unsigned long addr)
+{
+	writel(value, PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef inb_p
+#define inb_p inb_p
+static inline u8 inb_p(unsigned long addr)
+{
+	return inb(addr);
+}
+#endif
+
+#ifndef inw_p
+#define inw_p inw_p
+static inline u16 inw_p(unsigned long addr)
+{
+	return inw(addr);
+}
+#endif
+
+#ifndef inl_p
+#define inl_p inl_p
+static inline u32 inl_p(unsigned long addr)
+{
+	return inl(addr);
+}
+#endif
+
+#ifndef outb_p
+#define outb_p outb_p
+static inline void outb_p(u8 value, unsigned long addr)
+{
+	outb(value, addr);
+}
+#endif
+
+#ifndef outw_p
+#define outw_p outw_p
+static inline void outw_p(u16 value, unsigned long addr)
+{
+	outw(value, addr);
+}
+#endif
+
+#ifndef outl_p
+#define outl_p outl_p
+static inline void outl_p(u32 value, unsigned long addr)
+{
+	outl(value, addr);
+}
+#endif
+
+#ifndef CONFIG_GENERIC_IOMAP
+#ifndef ioread8
+#define ioread8 ioread8
+static inline u8 ioread8(const volatile void __iomem *addr)
+{
+	return readb(addr);
+}
+#endif
+
+#ifndef ioread16
+#define ioread16 ioread16
+static inline u16 ioread16(const volatile void __iomem *addr)
+{
+	return readw(addr);
+}
+#endif
+
+#ifndef ioread32
+#define ioread32 ioread32
+static inline u32 ioread32(const volatile void __iomem *addr)
+{
+	return readl(addr);
+}
+#endif
+
+#ifndef iowrite8
+#define iowrite8 iowrite8
+static inline void iowrite8(u8 value, volatile void __iomem *addr)
+{
+	writeb(value, addr);
+}
+#endif
+
+#ifndef iowrite16
+#define iowrite16 iowrite16
+static inline void iowrite16(u16 value, volatile void __iomem *addr)
+{
+	writew(value, addr);
+}
+#endif
+
+#ifndef iowrite32
+#define iowrite32 iowrite32
+static inline void iowrite32(u32 value, volatile void __iomem *addr)
+{
+	writel(value, addr);
+}
+#endif
+
+#ifndef ioread16be
+#define ioread16be ioread16be
+static inline u16 ioread16be(const volatile void __iomem *addr)
+{
+	return __be16_to_cpu(__raw_readw(addr));
+}
+#endif
+
+#ifndef ioread32be
+#define ioread32be ioread32be
+static inline u32 ioread32be(const volatile void __iomem *addr)
+{
+	return __be32_to_cpu(__raw_readl(addr));
+}
+#endif
+
+#ifndef iowrite16be
+#define iowrite16be iowrite16be
+static inline void iowrite16be(u16 value, void volatile __iomem *addr)
+{
+	__raw_writew(__cpu_to_be16(value), addr);
+}
+#endif
+
+#ifndef iowrite32be
+#define iowrite32be iowrite32be
+static inline void iowrite32be(u32 value, volatile void __iomem *addr)
+{
+	__raw_writel(__cpu_to_be32(value), addr);
+}
+#endif
+#endif /* CONFIG_GENERIC_IOMAP */
+
 #ifdef __KERNEL__
 
 #include <linux/vmalloc.h>
-#define __io_virt(x) ((void __force *) (x))
+#define __io_virt(x) ((void __force *)(x))
 
 #ifndef CONFIG_GENERIC_IOMAP
 struct pci_dev;
 extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
 
 #ifndef pci_iounmap
+#define pci_iounmap pci_iounmap
 static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
 {
 }
@@ -289,11 +479,15 @@ static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
  * These are pretty trivial
  */
 #ifndef virt_to_phys
+#define virt_to_phys virt_to_phys
 static inline unsigned long virt_to_phys(volatile void *address)
 {
 	return __pa((unsigned long)address);
 }
+#endif
 
+#ifndef phys_to_virt
+#define phys_to_virt phys_to_virt
 static inline void *phys_to_virt(unsigned long address)
 {
 	return __va(address);
@@ -306,37 +500,65 @@ static inline void *phys_to_virt(unsigned long address)
  * This implementation is for the no-MMU case only... if you have an MMU
  * you'll need to provide your own definitions.
  */
+
 #ifndef CONFIG_MMU
-static inline void __iomem *ioremap(phys_addr_t offset, unsigned long size)
+#ifndef ioremap
+#define ioremap ioremap
+static inline void __iomem *ioremap(phys_addr_t offset, size_t size)
 {
-	return (void __iomem*) (unsigned long)offset;
+	return (void __iomem *)(unsigned long)offset;
 }
+#endif
 
-#define __ioremap(offset, size, flags)	ioremap(offset, size)
+#ifndef __ioremap
+#define __ioremap __ioremap
+static inline void __iomem *__ioremap(phys_addr_t offset, size_t size,
+				      unsigned long flags)
+{
+	return ioremap(offset, size);
+}
+#endif
 
 #ifndef ioremap_nocache
-#define ioremap_nocache ioremap
+#define ioremap_nocache ioremap_nocache
+static inline void __iomem *ioremap_nocache(phys_addr_t offset, size_t size)
+{
+	return ioremap(offset, size);
+}
 #endif
 
 #ifndef ioremap_wc
-#define ioremap_wc ioremap_nocache
+#define ioremap_wc ioremap_wc
+static inline void __iomem *ioremap_wc(phys_addr_t offset, size_t size)
+{
+	return ioremap_nocache(offset, size);
+}
 #endif
 
+#ifndef iounmap
+#define iounmap iounmap
 static inline void iounmap(void __iomem *addr)
 {
 }
+#endif
 #endif /* CONFIG_MMU */
 
 #ifdef CONFIG_HAS_IOPORT_MAP
 #ifndef CONFIG_GENERIC_IOMAP
+#ifndef ioport_map
+#define ioport_map ioport_map
 static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
 {
 	return PCI_IOBASE + (port & IO_SPACE_LIMIT);
 }
+#endif
 
+#ifndef ioport_unmap
+#define ioport_unmap ioport_unmap
 static inline void ioport_unmap(void __iomem *p)
 {
 }
+#endif
 #else /* CONFIG_GENERIC_IOMAP */
 extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
 extern void ioport_unmap(void __iomem *p);
@@ -344,35 +566,68 @@ extern void ioport_unmap(void __iomem *p);
 #endif /* CONFIG_HAS_IOPORT_MAP */
 
 #ifndef xlate_dev_kmem_ptr
-#define xlate_dev_kmem_ptr(p)	p
+#define xlate_dev_kmem_ptr xlate_dev_kmem_ptr
+static inline void *xlate_dev_kmem_ptr(void *addr)
+{
+	return addr;
+}
 #endif
+
 #ifndef xlate_dev_mem_ptr
-#define xlate_dev_mem_ptr(p)	__va(p)
+#define xlate_dev_mem_ptr xlate_dev_mem_ptr
+static inline void *xlate_dev_mem_ptr(phys_addr_t addr)
+{
+	return __va(addr);
+}
+#endif
+
+#ifndef unxlate_dev_mem_ptr
+#define unxlate_dev_mem_ptr unxlate_dev_mem_ptr
+static inline void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
+{
+}
 #endif
 
 #ifdef CONFIG_VIRT_TO_BUS
 #ifndef virt_to_bus
-static inline unsigned long virt_to_bus(volatile void *address)
+static inline unsigned long virt_to_bus(void *address)
 {
-	return ((unsigned long) address);
+	return (unsigned long)address;
 }
 
 static inline void *bus_to_virt(unsigned long address)
 {
-	return (void *) address;
+	return (void *)address;
 }
 #endif
 #endif
 
 #ifndef memset_io
-#define memset_io(a, b, c)	memset(__io_virt(a), (b), (c))
+#define memset_io memset_io
+static inline void memset_io(volatile void __iomem *addr, int value,
+			     size_t size)
+{
+	memset(__io_virt(addr), value, size);
+}
 #endif
 
 #ifndef memcpy_fromio
-#define memcpy_fromio(a, b, c)	memcpy((a), __io_virt(b), (c))
+#define memcpy_fromio memcpy_fromio
+static inline void memcpy_fromio(void *buffer,
+				 const volatile void __iomem *addr,
+				 size_t size)
+{
+	memcpy(buffer, __io_virt(addr), size);
+}
 #endif
+
 #ifndef memcpy_toio
-#define memcpy_toio(a, b, c)	memcpy(__io_virt(a), (b), (c))
+#define memcpy_toio memcpy_toio
+static inline void memcpy_toio(volatile void __iomem *addr, const void *buffer,
+			       size_t size)
+{
+	memcpy(__io_virt(addr), buffer, size);
+}
 #endif
 
 #endif /* __KERNEL__ */
-- 
cgit v1.2.3-70-g09d2


From 9ab3a7a0d2b417773e8e8a880fc3a69f7fc1f57a Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Fri, 4 Jul 2014 13:07:57 +0200
Subject: asm-generic/io.h: Implement generic {read,write}s*()

Currently driver writers need to use io{read,write}{8,16,32}_rep() when
accessing FIFO registers portably. This is bad for two reasons: it is
inconsistent with how other registers are accessed using the standard
{read,write}{b,w,l}() functions, which can lead to confusion. On some
architectures the io{read,write}*() functions also need to perform some
extra checks to determine whether an address is memory-mapped or refers
to I/O space. Drivers which can be expected to never use I/O can safely
use the {read,write}s{b,w,l,q}(), just like they use their non-string
variants and there's no need for these extra checks.

This patch implements generic versions of readsb(), readsw(), readsl(),
readsq(), writesb(), writesw(), writesl() and writesq(). Variants of
these string functions for I/O accesses (ins*() and outs*() as well as
ioread*_rep() and iowrite*_rep()) are now implemented in terms of the
new functions.

Going forward, {read,write}{,s}{b,w,l,q}() should be used consistently
by drivers for devices that will only ever be memory-mapped and hence
don't need to access I/O space, whereas io{read,write}{8,16,32}_rep()
should be used by drivers for devices that can be either memory-mapped
or I/O-mapped.

Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 include/asm-generic/io.h | 271 +++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 238 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index fb62c621acf..00483d769d8 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -174,96 +174,137 @@ static inline void writeq(u64 value, volatile void __iomem *addr)
 #endif
 #endif /* CONFIG_64BIT */
 
-#ifndef insb
-static inline void insb(unsigned long addr, void *buffer, int count)
+/*
+ * {read,write}s{b,w,l,q}() repeatedly access the same memory address in
+ * native endianness in 8-, 16-, 32- or 64-bit chunks (@count times).
+ */
+#ifndef readsb
+#define readsb readsb
+static inline void readsb(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
 {
 	if (count) {
 		u8 *buf = buffer;
+
 		do {
-			u8 x = __raw_readb(addr + PCI_IOBASE);
+			u8 x = __raw_readb(addr);
 			*buf++ = x;
 		} while (--count);
 	}
 }
 #endif
 
-#ifndef insw
-static inline void insw(unsigned long addr, void *buffer, int count)
+#ifndef readsw
+#define readsw readsw
+static inline void readsw(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
 {
 	if (count) {
 		u16 *buf = buffer;
+
 		do {
-			u16 x = __raw_readw(addr + PCI_IOBASE);
+			u16 x = __raw_readw(addr);
 			*buf++ = x;
 		} while (--count);
 	}
 }
 #endif
 
-#ifndef insl
-static inline void insl(unsigned long addr, void *buffer, int count)
+#ifndef readsl
+#define readsl readsl
+static inline void readsl(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
 {
 	if (count) {
 		u32 *buf = buffer;
+
 		do {
-			u32 x = __raw_readl(addr + PCI_IOBASE);
+			u32 x = __raw_readl(addr);
 			*buf++ = x;
 		} while (--count);
 	}
 }
 #endif
 
-#ifndef outsb
-static inline void outsb(unsigned long addr, const void *buffer, int count)
+#ifdef CONFIG_64BIT
+#ifndef readsq
+#define readsq readsq
+static inline void readsq(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
+{
+	if (count) {
+		u64 *buf = buffer;
+
+		do {
+			u64 x = __raw_readq(addr);
+			*buf++ = x;
+		} while (--count);
+	}
+}
+#endif
+#endif /* CONFIG_64BIT */
+
+#ifndef writesb
+#define writesb writesb
+static inline void writesb(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
 {
 	if (count) {
 		const u8 *buf = buffer;
+
 		do {
-			__raw_writeb(*buf++, addr + PCI_IOBASE);
+			__raw_writeb(*buf++, addr);
 		} while (--count);
 	}
 }
 #endif
 
-#ifndef outsw
-static inline void outsw(unsigned long addr, const void *buffer, int count)
+#ifndef writesw
+#define writesw writesw
+static inline void writesw(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
 {
 	if (count) {
 		const u16 *buf = buffer;
+
 		do {
-			__raw_writew(*buf++, addr + PCI_IOBASE);
+			__raw_writew(*buf++, addr);
 		} while (--count);
 	}
 }
 #endif
 
-#ifndef outsl
-static inline void outsl(unsigned long addr, const void *buffer, int count)
+#ifndef writesl
+#define writesl writesl
+static inline void writesl(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
 {
 	if (count) {
 		const u32 *buf = buffer;
+
 		do {
-			__raw_writel(*buf++, addr + PCI_IOBASE);
+			__raw_writel(*buf++, addr);
 		} while (--count);
 	}
 }
 #endif
 
-#ifndef CONFIG_GENERIC_IOMAP
-#define ioread8_rep(p, dst, count) \
-	insb((unsigned long) (p), (dst), (count))
-#define ioread16_rep(p, dst, count) \
-	insw((unsigned long) (p), (dst), (count))
-#define ioread32_rep(p, dst, count) \
-	insl((unsigned long) (p), (dst), (count))
-
-#define iowrite8_rep(p, src, count) \
-	outsb((unsigned long) (p), (src), (count))
-#define iowrite16_rep(p, src, count) \
-	outsw((unsigned long) (p), (src), (count))
-#define iowrite32_rep(p, src, count) \
-	outsl((unsigned long) (p), (src), (count))
-#endif /* CONFIG_GENERIC_IOMAP */
+#ifdef CONFIG_64BIT
+#ifndef writesq
+#define writesq writesq
+static inline void writesq(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
+{
+	if (count) {
+		const u64 *buf = buffer;
+
+		do {
+			__raw_writeq(*buf++, addr);
+		} while (--count);
+	}
+}
+#endif
+#endif /* CONFIG_64BIT */
 
 #ifndef PCI_IOBASE
 #define PCI_IOBASE ((void __iomem *)0)
@@ -375,6 +416,113 @@ static inline void outl_p(u32 value, unsigned long addr)
 }
 #endif
 
+/*
+ * {in,out}s{b,w,l}{,_p}() are variants of the above that repeatedly access a
+ * single I/O port multiple times.
+ */
+
+#ifndef insb
+#define insb insb
+static inline void insb(unsigned long addr, void *buffer, unsigned int count)
+{
+	readsb(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef insw
+#define insw insw
+static inline void insw(unsigned long addr, void *buffer, unsigned int count)
+{
+	readsw(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef insl
+#define insl insl
+static inline void insl(unsigned long addr, void *buffer, unsigned int count)
+{
+	readsl(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef outsb
+#define outsb outsb
+static inline void outsb(unsigned long addr, const void *buffer,
+			 unsigned int count)
+{
+	writesb(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef outsw
+#define outsw outsw
+static inline void outsw(unsigned long addr, const void *buffer,
+			 unsigned int count)
+{
+	writesw(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef outsl
+#define outsl outsl
+static inline void outsl(unsigned long addr, const void *buffer,
+			 unsigned int count)
+{
+	writesl(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef insb_p
+#define insb_p insb_p
+static inline void insb_p(unsigned long addr, void *buffer, unsigned int count)
+{
+	insb(addr, buffer, count);
+}
+#endif
+
+#ifndef insw_p
+#define insw_p insw_p
+static inline void insw_p(unsigned long addr, void *buffer, unsigned int count)
+{
+	insw(addr, buffer, count);
+}
+#endif
+
+#ifndef insl_p
+#define insl_p insl_p
+static inline void insl_p(unsigned long addr, void *buffer, unsigned int count)
+{
+	insl(addr, buffer, count);
+}
+#endif
+
+#ifndef outsb_p
+#define outsb_p outsb_p
+static inline void outsb_p(unsigned long addr, const void *buffer,
+			   unsigned int count)
+{
+	outsb(addr, buffer, count);
+}
+#endif
+
+#ifndef outsw_p
+#define outsw_p outsw_p
+static inline void outsw_p(unsigned long addr, const void *buffer,
+			   unsigned int count)
+{
+	outsw(addr, buffer, count);
+}
+#endif
+
+#ifndef outsl_p
+#define outsl_p outsl_p
+static inline void outsl_p(unsigned long addr, const void *buffer,
+			   unsigned int count)
+{
+	outsl(addr, buffer, count);
+}
+#endif
+
 #ifndef CONFIG_GENERIC_IOMAP
 #ifndef ioread8
 #define ioread8 ioread8
@@ -455,6 +603,63 @@ static inline void iowrite32be(u32 value, volatile void __iomem *addr)
 	__raw_writel(__cpu_to_be32(value), addr);
 }
 #endif
+
+#ifndef ioread8_rep
+#define ioread8_rep ioread8_rep
+static inline void ioread8_rep(const volatile void __iomem *addr, void *buffer,
+			       unsigned int count)
+{
+	readsb(addr, buffer, count);
+}
+#endif
+
+#ifndef ioread16_rep
+#define ioread16_rep ioread16_rep
+static inline void ioread16_rep(const volatile void __iomem *addr,
+				void *buffer, unsigned int count)
+{
+	readsw(addr, buffer, count);
+}
+#endif
+
+#ifndef ioread32_rep
+#define ioread32_rep ioread32_rep
+static inline void ioread32_rep(const volatile void __iomem *addr,
+				void *buffer, unsigned int count)
+{
+	readsl(addr, buffer, count);
+}
+#endif
+
+#ifndef iowrite8_rep
+#define iowrite8_rep iowrite8_rep
+static inline void iowrite8_rep(volatile void __iomem *addr,
+				const void *buffer,
+				unsigned int count)
+{
+	writesb(addr, buffer, count);
+}
+#endif
+
+#ifndef iowrite16_rep
+#define iowrite16_rep iowrite16_rep
+static inline void iowrite16_rep(volatile void __iomem *addr,
+				 const void *buffer,
+				 unsigned int count)
+{
+	writesw(addr, buffer, count);
+}
+#endif
+
+#ifndef iowrite32_rep
+#define iowrite32_rep iowrite32_rep
+static inline void iowrite32_rep(volatile void __iomem *addr,
+				 const void *buffer,
+				 unsigned int count)
+{
+	writesl(addr, buffer, count);
+}
+#endif
 #endif /* CONFIG_GENERIC_IOMAP */
 
 #ifdef __KERNEL__
-- 
cgit v1.2.3-70-g09d2


From 179e20b8df97e0c7541a1bae30cad53ecc7a5e86 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruen@linbit.com>
Date: Mon, 10 Nov 2014 17:21:09 +0100
Subject: drbd: Minor cleanups

 . Update comments
 . drbd_set_{in,out_of}_sync(): Remove unused parameters
 . Move common code into adm_del_resource()
 . Redefine ERR_MINOR_EXISTS -> ERR_MINOR_OR_VOLUME_EXISTS

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/block/drbd/drbd_actlog.c |  3 +-
 drivers/block/drbd/drbd_int.h    |  9 +++---
 drivers/block/drbd/drbd_main.c   |  6 ++--
 drivers/block/drbd/drbd_nl.c     | 60 +++++++++++++++++-----------------------
 include/linux/drbd.h             |  2 +-
 5 files changed, 35 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index a2dfa169237..1318e3217cb 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -827,8 +827,7 @@ static int update_sync_bits(struct drbd_device *device,
  *
  */
 int __drbd_change_sync(struct drbd_device *device, sector_t sector, int size,
-		enum update_sync_bits_mode mode,
-		const char *file, const unsigned int line)
+		enum update_sync_bits_mode mode)
 {
 	/* Is called from worker and receiver context _only_ */
 	unsigned long sbnr, ebnr, lbnr;
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 9b22f8f01b5..c14b718c2fa 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1662,14 +1662,13 @@ extern void drbd_advance_rs_marks(struct drbd_device *device, unsigned long stil
 
 enum update_sync_bits_mode { RECORD_RS_FAILED, SET_OUT_OF_SYNC, SET_IN_SYNC };
 extern int __drbd_change_sync(struct drbd_device *device, sector_t sector, int size,
-		enum update_sync_bits_mode mode,
-		const char *file, const unsigned int line);
+		enum update_sync_bits_mode mode);
 #define drbd_set_in_sync(device, sector, size) \
-	__drbd_change_sync(device, sector, size, SET_IN_SYNC, __FILE__, __LINE__)
+	__drbd_change_sync(device, sector, size, SET_IN_SYNC)
 #define drbd_set_out_of_sync(device, sector, size) \
-	__drbd_change_sync(device, sector, size, SET_OUT_OF_SYNC, __FILE__, __LINE__)
+	__drbd_change_sync(device, sector, size, SET_OUT_OF_SYNC)
 #define drbd_rs_failed_io(device, sector, size) \
-	__drbd_change_sync(device, sector, size, RECORD_RS_FAILED, __FILE__, __LINE__)
+	__drbd_change_sync(device, sector, size, RECORD_RS_FAILED)
 extern void drbd_al_shrink(struct drbd_device *device);
 extern int drbd_initialize_al(struct drbd_device *, void *);
 
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 973c185c9cf..cce25a5eb15 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2731,7 +2731,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	device = minor_to_device(minor);
 	if (device)
-		return ERR_MINOR_EXISTS;
+		return ERR_MINOR_OR_VOLUME_EXISTS;
 
 	/* GFP_KERNEL, we are outside of all write-out paths */
 	device = kzalloc(sizeof(struct drbd_device), GFP_KERNEL);
@@ -2794,7 +2794,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	id = idr_alloc(&drbd_devices, device, minor, minor + 1, GFP_KERNEL);
 	if (id < 0) {
 		if (id == -ENOSPC) {
-			err = ERR_MINOR_EXISTS;
+			err = ERR_MINOR_OR_VOLUME_EXISTS;
 			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
 		}
 		goto out_no_minor_idr;
@@ -2804,7 +2804,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	id = idr_alloc(&resource->devices, device, vnr, vnr + 1, GFP_KERNEL);
 	if (id < 0) {
 		if (id == -ENOSPC) {
-			err = ERR_MINOR_EXISTS;
+			err = ERR_MINOR_OR_VOLUME_EXISTS;
 			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
 		}
 		goto out_idr_remove_minor;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 1cd47df44bd..c145619f1cc 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2052,7 +2052,7 @@ check_net_options(struct drbd_connection *connection, struct net_conf *new_net_c
 	rv = _check_net_options(connection, rcu_dereference(connection->net_conf), new_net_conf);
 	rcu_read_unlock();
 
-	/* connection->volumes protected by genl_lock() here */
+	/* connection->peer_devices protected by genl_lock() here */
 	idr_for_each_entry(&connection->peer_devices, peer_device, i) {
 		struct drbd_device *device = peer_device->device;
 		if (!device->bitmap) {
@@ -3483,7 +3483,7 @@ int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info)
 	 * that first_peer_device(device)->connection and device->vnr match the request. */
 	if (adm_ctx.device) {
 		if (info->nlhdr->nlmsg_flags & NLM_F_EXCL)
-			retcode = ERR_MINOR_EXISTS;
+			retcode = ERR_MINOR_OR_VOLUME_EXISTS;
 		/* else: still NO_ERROR */
 		goto out;
 	}
@@ -3530,6 +3530,27 @@ out:
 	return 0;
 }
 
+static int adm_del_resource(struct drbd_resource *resource)
+{
+	struct drbd_connection *connection;
+
+	for_each_connection(connection, resource) {
+		if (connection->cstate > C_STANDALONE)
+			return ERR_NET_CONFIGURED;
+	}
+	if (!idr_is_empty(&resource->devices))
+		return ERR_RES_IN_USE;
+
+	list_del_rcu(&resource->resources);
+	/* Make sure all threads have actually stopped: state handling only
+	 * does drbd_thread_stop_nowait(). */
+	list_for_each_entry(connection, &resource->connections, connections)
+		drbd_thread_stop(&connection->worker);
+	synchronize_rcu();
+	drbd_free_resource(resource);
+	return NO_ERROR;
+}
+
 int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_config_context adm_ctx;
@@ -3575,14 +3596,6 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	/* If we reach this, all volumes (of this connection) are Secondary,
-	 * Disconnected, Diskless, aka Unconfigured. Make sure all threads have
-	 * actually stopped, state handling only does drbd_thread_stop_nowait(). */
-	for_each_connection(connection, resource)
-		drbd_thread_stop(&connection->worker);
-
-	/* Now, nothing can fail anymore */
-
 	/* delete volumes */
 	idr_for_each_entry(&resource->devices, device, i) {
 		retcode = adm_del_minor(device);
@@ -3593,10 +3606,7 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	list_del_rcu(&resource->resources);
-	synchronize_rcu();
-	drbd_free_resource(resource);
-	retcode = NO_ERROR;
+	retcode = adm_del_resource(resource);
 out:
 	mutex_unlock(&resource->adm_mutex);
 finish:
@@ -3608,7 +3618,6 @@ int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_config_context adm_ctx;
 	struct drbd_resource *resource;
-	struct drbd_connection *connection;
 	enum drbd_ret_code retcode;
 
 	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE);
@@ -3616,27 +3625,10 @@ int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto finish;
-
 	resource = adm_ctx.resource;
-	mutex_lock(&resource->adm_mutex);
-	for_each_connection(connection, resource) {
-		if (connection->cstate > C_STANDALONE) {
-			retcode = ERR_NET_CONFIGURED;
-			goto out;
-		}
-	}
-	if (!idr_is_empty(&resource->devices)) {
-		retcode = ERR_RES_IN_USE;
-		goto out;
-	}
 
-	list_del_rcu(&resource->resources);
-	for_each_connection(connection, resource)
-		drbd_thread_stop(&connection->worker);
-	synchronize_rcu();
-	drbd_free_resource(resource);
-	retcode = NO_ERROR;
-out:
+	mutex_lock(&resource->adm_mutex);
+	retcode = adm_del_resource(resource);
 	mutex_unlock(&resource->adm_mutex);
 finish:
 	drbd_adm_finish(&adm_ctx, info, retcode);
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index debb70d4054..8723f2a99e1 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -172,7 +172,7 @@ enum drbd_ret_code {
 	ERR_RES_NOT_KNOWN	= 158,
 	ERR_RES_IN_USE		= 159,
 	ERR_MINOR_CONFIGURED    = 160,
-	ERR_MINOR_EXISTS	= 161,
+	ERR_MINOR_OR_VOLUME_EXISTS = 161,
 	ERR_INVALID_REQUEST	= 162,
 	ERR_NEED_APV_100	= 163,
 	ERR_NEED_ALLOW_TWO_PRI  = 164,
-- 
cgit v1.2.3-70-g09d2


From a7975473cc41773d9f6d8ea72b48c7656e6cd0f6 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Fri, 26 Sep 2014 12:55:30 +0200
Subject: mfd: core: Add helper function to register hotplug devices

Hot-pluggable multi-function devices should always be registered with
PLATFORM_DEVID_AUTO to avoid name collisions on the platform bus. This
helper also hides the memory map and irq parameters, which aren't used
by hot-pluggable (e.g. USB-based) devices.

Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/core.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h
index 73e1709d4c0..a76bc100bf9 100644
--- a/include/linux/mfd/core.h
+++ b/include/linux/mfd/core.h
@@ -111,6 +111,13 @@ extern int mfd_add_devices(struct device *parent, int id,
 			   struct resource *mem_base,
 			   int irq_base, struct irq_domain *irq_domain);
 
+static inline int mfd_add_hotplug_devices(struct device *parent,
+		const struct mfd_cell *cells, int n_devs)
+{
+	return mfd_add_devices(parent, PLATFORM_DEVID_AUTO, cells, n_devs,
+			NULL, 0, NULL);
+}
+
 extern void mfd_remove_devices(struct device *parent);
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From 338a128142975439a19ab3c91480bc9d5a71f033 Mon Sep 17 00:00:00 2001
From: Octavian Purdila <octavian.purdila@intel.com>
Date: Thu, 6 Nov 2014 15:48:03 +0200
Subject: mfd: Add support for Diolan DLN-2 devices

This patch implements the USB part of the Diolan USB-I2C/SPI/GPIO
Master Adapter DLN-2. Details about the device can be found here:

https://www.diolan.com/i2c/i2c_interface.html.

Information about the USB protocol can be found in the Programmer's
Reference Manual [1], see section 1.7.

Because the hardware has a single transmit endpoint and a single
receive endpoint the communication between the various DLN2 drivers
and the hardware will be muxed/demuxed by this driver.

Each DLN2 module will be identified by the handle field within the DLN2
message header. If a DLN2 module issues multiple commands in parallel
they will be identified by the echo counter field in the message header.

The DLN2 modules can use the dln2_transfer() function to issue a
command and wait for its response. They can also register a callback
that is going to be called when a specific event id is generated by
the device (e.g. GPIO interrupts). The device uses handle 0 for
sending events.

[1] https://www.diolan.com/downloads/dln-api-manual.pdf

Signed-off-by: Octavian Purdila <octavian.purdila@intel.com>
Reviewed-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/Kconfig      |  10 +
 drivers/mfd/Makefile     |   1 +
 drivers/mfd/dln2.c       | 763 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/dln2.h | 103 +++++++
 4 files changed, 877 insertions(+)
 create mode 100644 drivers/mfd/dln2.c
 create mode 100644 include/linux/mfd/dln2.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 1456ea70bbc..c1acc76a519 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -183,6 +183,16 @@ config MFD_DA9063
 	  Additional drivers must be enabled in order to use the functionality
 	  of the device.
 
+config MFD_DLN2
+	tristate "Diolan DLN2 support"
+	select MFD_CORE
+	depends on USB
+	help
+	  This adds support for Diolan USB-I2C/SPI/GPIO Master Adapter
+	  DLN-2. Additional drivers such as I2C_DLN2, GPIO_DLN2,
+	  etc. must be enabled in order to use the functionality of
+	  the device.
+
 config MFD_MC13XXX
 	tristate
 	depends on (SPI_MASTER || I2C)
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 8bd54b1253a..10bbd0b9096 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -174,6 +174,7 @@ obj-$(CONFIG_MFD_STW481X)	+= stw481x.o
 obj-$(CONFIG_MFD_IPAQ_MICRO)	+= ipaq-micro.o
 obj-$(CONFIG_MFD_MENF21BMC)	+= menf21bmc.o
 obj-$(CONFIG_MFD_HI6421_PMIC)	+= hi6421-pmic-core.o
+obj-$(CONFIG_MFD_DLN2)		+= dln2.o
 
 intel-soc-pmic-objs		:= intel_soc_pmic_core.o intel_soc_pmic_crc.o
 obj-$(CONFIG_INTEL_SOC_PMIC)	+= intel-soc-pmic.o
diff --git a/drivers/mfd/dln2.c b/drivers/mfd/dln2.c
new file mode 100644
index 00000000000..9765a174d2c
--- /dev/null
+++ b/drivers/mfd/dln2.c
@@ -0,0 +1,763 @@
+/*
+ * Driver for the Diolan DLN-2 USB adapter
+ *
+ * Copyright (c) 2014 Intel Corporation
+ *
+ * Derived from:
+ *  i2c-diolan-u2c.c
+ *  Copyright (c) 2010-2011 Ericsson AB
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/usb.h>
+#include <linux/i2c.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/dln2.h>
+#include <linux/rculist.h>
+
+struct dln2_header {
+	__le16 size;
+	__le16 id;
+	__le16 echo;
+	__le16 handle;
+};
+
+struct dln2_response {
+	struct dln2_header hdr;
+	__le16 result;
+};
+
+#define DLN2_GENERIC_MODULE_ID		0x00
+#define DLN2_GENERIC_CMD(cmd)		DLN2_CMD(cmd, DLN2_GENERIC_MODULE_ID)
+#define CMD_GET_DEVICE_VER		DLN2_GENERIC_CMD(0x30)
+#define CMD_GET_DEVICE_SN		DLN2_GENERIC_CMD(0x31)
+
+#define DLN2_HW_ID			0x200
+#define DLN2_USB_TIMEOUT		200	/* in ms */
+#define DLN2_MAX_RX_SLOTS		16
+#define DLN2_MAX_URBS			16
+#define DLN2_RX_BUF_SIZE		512
+
+enum dln2_handle {
+	DLN2_HANDLE_EVENT = 0,		/* don't change, hardware defined */
+	DLN2_HANDLE_CTRL,
+	DLN2_HANDLE_GPIO,
+	DLN2_HANDLE_I2C,
+	DLN2_HANDLES
+};
+
+/*
+ * Receive context used between the receive demultiplexer and the transfer
+ * routine. While sending a request the transfer routine will look for a free
+ * receive context and use it to wait for a response and to receive the URB and
+ * thus the response data.
+ */
+struct dln2_rx_context {
+	/* completion used to wait for a response */
+	struct completion done;
+
+	/* if non-NULL the URB contains the response */
+	struct urb *urb;
+
+	/* if true then this context is used to wait for a response */
+	bool in_use;
+};
+
+/*
+ * Receive contexts for a particular DLN2 module (i2c, gpio, etc.). We use the
+ * handle header field to identify the module in dln2_dev.mod_rx_slots and then
+ * the echo header field to index the slots field and find the receive context
+ * for a particular request.
+ */
+struct dln2_mod_rx_slots {
+	/* RX slots bitmap */
+	DECLARE_BITMAP(bmap, DLN2_MAX_RX_SLOTS);
+
+	/* used to wait for a free RX slot */
+	wait_queue_head_t wq;
+
+	/* used to wait for an RX operation to complete */
+	struct dln2_rx_context slots[DLN2_MAX_RX_SLOTS];
+
+	/* avoid races between alloc/free_rx_slot and dln2_rx_transfer */
+	spinlock_t lock;
+};
+
+struct dln2_dev {
+	struct usb_device *usb_dev;
+	struct usb_interface *interface;
+	u8 ep_in;
+	u8 ep_out;
+
+	struct urb *rx_urb[DLN2_MAX_URBS];
+	void *rx_buf[DLN2_MAX_URBS];
+
+	struct dln2_mod_rx_slots mod_rx_slots[DLN2_HANDLES];
+
+	struct list_head event_cb_list;
+	spinlock_t event_cb_lock;
+
+	bool disconnect;
+	int active_transfers;
+	wait_queue_head_t disconnect_wq;
+	spinlock_t disconnect_lock;
+};
+
+struct dln2_event_cb_entry {
+	struct list_head list;
+	u16 id;
+	struct platform_device *pdev;
+	dln2_event_cb_t callback;
+};
+
+int dln2_register_event_cb(struct platform_device *pdev, u16 id,
+			   dln2_event_cb_t event_cb)
+{
+	struct dln2_dev *dln2 = dev_get_drvdata(pdev->dev.parent);
+	struct dln2_event_cb_entry *i, *entry;
+	unsigned long flags;
+	int ret = 0;
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->id = id;
+	entry->callback = event_cb;
+	entry->pdev = pdev;
+
+	spin_lock_irqsave(&dln2->event_cb_lock, flags);
+
+	list_for_each_entry(i, &dln2->event_cb_list, list) {
+		if (i->id == id) {
+			ret = -EBUSY;
+			break;
+		}
+	}
+
+	if (!ret)
+		list_add_rcu(&entry->list, &dln2->event_cb_list);
+
+	spin_unlock_irqrestore(&dln2->event_cb_lock, flags);
+
+	if (ret)
+		kfree(entry);
+
+	return ret;
+}
+EXPORT_SYMBOL(dln2_register_event_cb);
+
+void dln2_unregister_event_cb(struct platform_device *pdev, u16 id)
+{
+	struct dln2_dev *dln2 = dev_get_drvdata(pdev->dev.parent);
+	struct dln2_event_cb_entry *i;
+	unsigned long flags;
+	bool found = false;
+
+	spin_lock_irqsave(&dln2->event_cb_lock, flags);
+
+	list_for_each_entry(i, &dln2->event_cb_list, list) {
+		if (i->id == id) {
+			list_del_rcu(&i->list);
+			found = true;
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&dln2->event_cb_lock, flags);
+
+	if (found) {
+		synchronize_rcu();
+		kfree(i);
+	}
+}
+EXPORT_SYMBOL(dln2_unregister_event_cb);
+
+/*
+ * Returns true if a valid transfer slot is found. In this case the URB must not
+ * be resubmitted immediately in dln2_rx as we need the data when dln2_transfer
+ * is woke up. It will be resubmitted there.
+ */
+static bool dln2_transfer_complete(struct dln2_dev *dln2, struct urb *urb,
+				   u16 handle, u16 rx_slot)
+{
+	struct device *dev = &dln2->interface->dev;
+	struct dln2_mod_rx_slots *rxs = &dln2->mod_rx_slots[handle];
+	struct dln2_rx_context *rxc;
+	bool valid_slot = false;
+
+	rxc = &rxs->slots[rx_slot];
+
+	/*
+	 * No need to disable interrupts as this lock is not taken in interrupt
+	 * context elsewhere in this driver. This function (or its callers) are
+	 * also not exported to other modules.
+	 */
+	spin_lock(&rxs->lock);
+	if (rxc->in_use && !rxc->urb) {
+		rxc->urb = urb;
+		complete(&rxc->done);
+		valid_slot = true;
+	}
+	spin_unlock(&rxs->lock);
+
+	if (!valid_slot)
+		dev_warn(dev, "bad/late response %d/%d\n", handle, rx_slot);
+
+	return valid_slot;
+}
+
+static void dln2_run_event_callbacks(struct dln2_dev *dln2, u16 id, u16 echo,
+				     void *data, int len)
+{
+	struct dln2_event_cb_entry *i;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(i, &dln2->event_cb_list, list) {
+		if (i->id == id) {
+			i->callback(i->pdev, echo, data, len);
+			break;
+		}
+	}
+
+	rcu_read_unlock();
+}
+
+static void dln2_rx(struct urb *urb)
+{
+	struct dln2_dev *dln2 = urb->context;
+	struct dln2_header *hdr = urb->transfer_buffer;
+	struct device *dev = &dln2->interface->dev;
+	u16 id, echo, handle, size;
+	u8 *data;
+	int len;
+	int err;
+
+	switch (urb->status) {
+	case 0:
+		/* success */
+		break;
+	case -ECONNRESET:
+	case -ENOENT:
+	case -ESHUTDOWN:
+	case -EPIPE:
+		/* this urb is terminated, clean up */
+		dev_dbg(dev, "urb shutting down with status %d\n", urb->status);
+		return;
+	default:
+		dev_dbg(dev, "nonzero urb status received %d\n", urb->status);
+		goto out;
+	}
+
+	if (urb->actual_length < sizeof(struct dln2_header)) {
+		dev_err(dev, "short response: %d\n", urb->actual_length);
+		goto out;
+	}
+
+	handle = le16_to_cpu(hdr->handle);
+	id = le16_to_cpu(hdr->id);
+	echo = le16_to_cpu(hdr->echo);
+	size = le16_to_cpu(hdr->size);
+
+	if (size != urb->actual_length) {
+		dev_err(dev, "size mismatch: handle %x cmd %x echo %x size %d actual %d\n",
+			handle, id, echo, size, urb->actual_length);
+		goto out;
+	}
+
+	if (handle >= DLN2_HANDLES) {
+		dev_warn(dev, "invalid handle %d\n", handle);
+		goto out;
+	}
+
+	data = urb->transfer_buffer + sizeof(struct dln2_header);
+	len = urb->actual_length - sizeof(struct dln2_header);
+
+	if (handle == DLN2_HANDLE_EVENT) {
+		dln2_run_event_callbacks(dln2, id, echo, data, len);
+	} else {
+		/* URB will be re-submitted in _dln2_transfer (free_rx_slot) */
+		if (dln2_transfer_complete(dln2, urb, handle, echo))
+			return;
+	}
+
+out:
+	err = usb_submit_urb(urb, GFP_ATOMIC);
+	if (err < 0)
+		dev_err(dev, "failed to resubmit RX URB: %d\n", err);
+}
+
+static void *dln2_prep_buf(u16 handle, u16 cmd, u16 echo, const void *obuf,
+			   int *obuf_len, gfp_t gfp)
+{
+	int len;
+	void *buf;
+	struct dln2_header *hdr;
+
+	len = *obuf_len + sizeof(*hdr);
+	buf = kmalloc(len, gfp);
+	if (!buf)
+		return NULL;
+
+	hdr = (struct dln2_header *)buf;
+	hdr->id = cpu_to_le16(cmd);
+	hdr->size = cpu_to_le16(len);
+	hdr->echo = cpu_to_le16(echo);
+	hdr->handle = cpu_to_le16(handle);
+
+	memcpy(buf + sizeof(*hdr), obuf, *obuf_len);
+
+	*obuf_len = len;
+
+	return buf;
+}
+
+static int dln2_send_wait(struct dln2_dev *dln2, u16 handle, u16 cmd, u16 echo,
+			  const void *obuf, int obuf_len)
+{
+	int ret = 0;
+	int len = obuf_len;
+	void *buf;
+	int actual;
+
+	buf = dln2_prep_buf(handle, cmd, echo, obuf, &len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = usb_bulk_msg(dln2->usb_dev,
+			   usb_sndbulkpipe(dln2->usb_dev, dln2->ep_out),
+			   buf, len, &actual, DLN2_USB_TIMEOUT);
+
+	kfree(buf);
+
+	return ret;
+}
+
+static bool find_free_slot(struct dln2_dev *dln2, u16 handle, int *slot)
+{
+	struct dln2_mod_rx_slots *rxs;
+	unsigned long flags;
+
+	if (dln2->disconnect) {
+		*slot = -ENODEV;
+		return true;
+	}
+
+	rxs = &dln2->mod_rx_slots[handle];
+
+	spin_lock_irqsave(&rxs->lock, flags);
+
+	*slot = find_first_zero_bit(rxs->bmap, DLN2_MAX_RX_SLOTS);
+
+	if (*slot < DLN2_MAX_RX_SLOTS) {
+		struct dln2_rx_context *rxc = &rxs->slots[*slot];
+
+		set_bit(*slot, rxs->bmap);
+		rxc->in_use = true;
+	}
+
+	spin_unlock_irqrestore(&rxs->lock, flags);
+
+	return *slot < DLN2_MAX_RX_SLOTS;
+}
+
+static int alloc_rx_slot(struct dln2_dev *dln2, u16 handle)
+{
+	int ret;
+	int slot;
+
+	/*
+	 * No need to timeout here, the wait is bounded by the timeout in
+	 * _dln2_transfer.
+	 */
+	ret = wait_event_interruptible(dln2->mod_rx_slots[handle].wq,
+				       find_free_slot(dln2, handle, &slot));
+	if (ret < 0)
+		return ret;
+
+	return slot;
+}
+
+static void free_rx_slot(struct dln2_dev *dln2, u16 handle, int slot)
+{
+	struct dln2_mod_rx_slots *rxs;
+	struct urb *urb = NULL;
+	unsigned long flags;
+	struct dln2_rx_context *rxc;
+
+	rxs = &dln2->mod_rx_slots[handle];
+
+	spin_lock_irqsave(&rxs->lock, flags);
+
+	clear_bit(slot, rxs->bmap);
+
+	rxc = &rxs->slots[slot];
+	rxc->in_use = false;
+	urb = rxc->urb;
+	rxc->urb = NULL;
+	reinit_completion(&rxc->done);
+
+	spin_unlock_irqrestore(&rxs->lock, flags);
+
+	if (urb) {
+		int err;
+		struct device *dev = &dln2->interface->dev;
+
+		err = usb_submit_urb(urb, GFP_KERNEL);
+		if (err < 0)
+			dev_err(dev, "failed to resubmit RX URB: %d\n", err);
+	}
+
+	wake_up_interruptible(&rxs->wq);
+}
+
+static int _dln2_transfer(struct dln2_dev *dln2, u16 handle, u16 cmd,
+			  const void *obuf, unsigned obuf_len,
+			  void *ibuf, unsigned *ibuf_len)
+{
+	int ret = 0;
+	int rx_slot;
+	struct dln2_response *rsp;
+	struct dln2_rx_context *rxc;
+	struct device *dev = &dln2->interface->dev;
+	const unsigned long timeout = DLN2_USB_TIMEOUT * HZ / 1000;
+	struct dln2_mod_rx_slots *rxs = &dln2->mod_rx_slots[handle];
+
+	spin_lock(&dln2->disconnect_lock);
+	if (!dln2->disconnect)
+		dln2->active_transfers++;
+	else
+		ret = -ENODEV;
+	spin_unlock(&dln2->disconnect_lock);
+
+	if (ret)
+		return ret;
+
+	rx_slot = alloc_rx_slot(dln2, handle);
+	if (rx_slot < 0) {
+		ret = rx_slot;
+		goto out_decr;
+	}
+
+	ret = dln2_send_wait(dln2, handle, cmd, rx_slot, obuf, obuf_len);
+	if (ret < 0) {
+		dev_err(dev, "USB write failed: %d\n", ret);
+		goto out_free_rx_slot;
+	}
+
+	rxc = &rxs->slots[rx_slot];
+
+	ret = wait_for_completion_interruptible_timeout(&rxc->done, timeout);
+	if (ret <= 0) {
+		if (!ret)
+			ret = -ETIMEDOUT;
+		goto out_free_rx_slot;
+	}
+
+	if (dln2->disconnect) {
+		ret = -ENODEV;
+		goto out_free_rx_slot;
+	}
+
+	/* if we got here we know that the response header has been checked */
+	rsp = rxc->urb->transfer_buffer;
+
+	if (rsp->hdr.size < sizeof(*rsp)) {
+		ret = -EPROTO;
+		goto out_free_rx_slot;
+	}
+
+	if (le16_to_cpu(rsp->result) > 0x80) {
+		dev_dbg(dev, "%d received response with error %d\n",
+			handle, le16_to_cpu(rsp->result));
+		ret = -EREMOTEIO;
+		goto out_free_rx_slot;
+	}
+
+	if (!ibuf) {
+		ret = 0;
+		goto out_free_rx_slot;
+	}
+
+	if (*ibuf_len > rsp->hdr.size - sizeof(*rsp))
+		*ibuf_len = rsp->hdr.size - sizeof(*rsp);
+
+	memcpy(ibuf, rsp + 1, *ibuf_len);
+
+out_free_rx_slot:
+	free_rx_slot(dln2, handle, rx_slot);
+out_decr:
+	spin_lock(&dln2->disconnect_lock);
+	dln2->active_transfers--;
+	spin_unlock(&dln2->disconnect_lock);
+	if (dln2->disconnect)
+		wake_up(&dln2->disconnect_wq);
+
+	return ret;
+}
+
+int dln2_transfer(struct platform_device *pdev, u16 cmd,
+		  const void *obuf, unsigned obuf_len,
+		  void *ibuf, unsigned *ibuf_len)
+{
+	struct dln2_platform_data *dln2_pdata;
+	struct dln2_dev *dln2;
+	u16 handle;
+
+	dln2 = dev_get_drvdata(pdev->dev.parent);
+	dln2_pdata = dev_get_platdata(&pdev->dev);
+	handle = dln2_pdata->handle;
+
+	return _dln2_transfer(dln2, handle, cmd, obuf, obuf_len, ibuf,
+			      ibuf_len);
+}
+EXPORT_SYMBOL(dln2_transfer);
+
+static int dln2_check_hw(struct dln2_dev *dln2)
+{
+	int ret;
+	__le32 hw_type;
+	int len = sizeof(hw_type);
+
+	ret = _dln2_transfer(dln2, DLN2_HANDLE_CTRL, CMD_GET_DEVICE_VER,
+			     NULL, 0, &hw_type, &len);
+	if (ret < 0)
+		return ret;
+	if (len < sizeof(hw_type))
+		return -EREMOTEIO;
+
+	if (le32_to_cpu(hw_type) != DLN2_HW_ID) {
+		dev_err(&dln2->interface->dev, "Device ID 0x%x not supported\n",
+			le32_to_cpu(hw_type));
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int dln2_print_serialno(struct dln2_dev *dln2)
+{
+	int ret;
+	__le32 serial_no;
+	int len = sizeof(serial_no);
+	struct device *dev = &dln2->interface->dev;
+
+	ret = _dln2_transfer(dln2, DLN2_HANDLE_CTRL, CMD_GET_DEVICE_SN, NULL, 0,
+			     &serial_no, &len);
+	if (ret < 0)
+		return ret;
+	if (len < sizeof(serial_no))
+		return -EREMOTEIO;
+
+	dev_info(dev, "Diolan DLN2 serial %u\n", le32_to_cpu(serial_no));
+
+	return 0;
+}
+
+static int dln2_hw_init(struct dln2_dev *dln2)
+{
+	int ret;
+
+	ret = dln2_check_hw(dln2);
+	if (ret < 0)
+		return ret;
+
+	return dln2_print_serialno(dln2);
+}
+
+static void dln2_free_rx_urbs(struct dln2_dev *dln2)
+{
+	int i;
+
+	for (i = 0; i < DLN2_MAX_URBS; i++) {
+		usb_kill_urb(dln2->rx_urb[i]);
+		usb_free_urb(dln2->rx_urb[i]);
+		kfree(dln2->rx_buf[i]);
+	}
+}
+
+static void dln2_free(struct dln2_dev *dln2)
+{
+	dln2_free_rx_urbs(dln2);
+	usb_put_dev(dln2->usb_dev);
+	kfree(dln2);
+}
+
+static int dln2_setup_rx_urbs(struct dln2_dev *dln2,
+			      struct usb_host_interface *hostif)
+{
+	int i;
+	int ret;
+	const int rx_max_size = DLN2_RX_BUF_SIZE;
+	struct device *dev = &dln2->interface->dev;
+
+	for (i = 0; i < DLN2_MAX_URBS; i++) {
+		dln2->rx_buf[i] = kmalloc(rx_max_size, GFP_KERNEL);
+		if (!dln2->rx_buf[i])
+			return -ENOMEM;
+
+		dln2->rx_urb[i] = usb_alloc_urb(0, GFP_KERNEL);
+		if (!dln2->rx_urb[i])
+			return -ENOMEM;
+
+		usb_fill_bulk_urb(dln2->rx_urb[i], dln2->usb_dev,
+				  usb_rcvbulkpipe(dln2->usb_dev, dln2->ep_in),
+				  dln2->rx_buf[i], rx_max_size, dln2_rx, dln2);
+
+		ret = usb_submit_urb(dln2->rx_urb[i], GFP_KERNEL);
+		if (ret < 0) {
+			dev_err(dev, "failed to submit RX URB: %d\n", ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static struct dln2_platform_data dln2_pdata_gpio = {
+	.handle = DLN2_HANDLE_GPIO,
+};
+
+/* Only one I2C port seems to be supported on current hardware */
+static struct dln2_platform_data dln2_pdata_i2c = {
+	.handle = DLN2_HANDLE_I2C,
+	.port = 0,
+};
+
+static const struct mfd_cell dln2_devs[] = {
+	{
+		.name = "dln2-gpio",
+		.platform_data = &dln2_pdata_gpio,
+		.pdata_size = sizeof(struct dln2_platform_data),
+	},
+	{
+		.name = "dln2-i2c",
+		.platform_data = &dln2_pdata_i2c,
+		.pdata_size = sizeof(struct dln2_platform_data),
+	},
+};
+
+static void dln2_disconnect(struct usb_interface *interface)
+{
+	struct dln2_dev *dln2 = usb_get_intfdata(interface);
+	int i, j;
+
+	/* don't allow starting new transfers */
+	spin_lock(&dln2->disconnect_lock);
+	dln2->disconnect = true;
+	spin_unlock(&dln2->disconnect_lock);
+
+	/* cancel in progress transfers */
+	for (i = 0; i < DLN2_HANDLES; i++) {
+		struct dln2_mod_rx_slots *rxs = &dln2->mod_rx_slots[i];
+		unsigned long flags;
+
+		spin_lock_irqsave(&rxs->lock, flags);
+
+		/* cancel all response waiters */
+		for (j = 0; j < DLN2_MAX_RX_SLOTS; j++) {
+			struct dln2_rx_context *rxc = &rxs->slots[j];
+
+			if (rxc->in_use)
+				complete(&rxc->done);
+		}
+
+		spin_unlock_irqrestore(&rxs->lock, flags);
+	}
+
+	/* wait for transfers to end */
+	wait_event(dln2->disconnect_wq, !dln2->active_transfers);
+
+	mfd_remove_devices(&interface->dev);
+
+	dln2_free(dln2);
+}
+
+static int dln2_probe(struct usb_interface *interface,
+		      const struct usb_device_id *usb_id)
+{
+	struct usb_host_interface *hostif = interface->cur_altsetting;
+	struct device *dev = &interface->dev;
+	struct dln2_dev *dln2;
+	int ret;
+	int i, j;
+
+	if (hostif->desc.bInterfaceNumber != 0 ||
+	    hostif->desc.bNumEndpoints < 2)
+		return -ENODEV;
+
+	dln2 = kzalloc(sizeof(*dln2), GFP_KERNEL);
+	if (!dln2)
+		return -ENOMEM;
+
+	dln2->ep_out = hostif->endpoint[0].desc.bEndpointAddress;
+	dln2->ep_in = hostif->endpoint[1].desc.bEndpointAddress;
+	dln2->usb_dev = usb_get_dev(interface_to_usbdev(interface));
+	dln2->interface = interface;
+	usb_set_intfdata(interface, dln2);
+	init_waitqueue_head(&dln2->disconnect_wq);
+
+	for (i = 0; i < DLN2_HANDLES; i++) {
+		init_waitqueue_head(&dln2->mod_rx_slots[i].wq);
+		spin_lock_init(&dln2->mod_rx_slots[i].lock);
+		for (j = 0; j < DLN2_MAX_RX_SLOTS; j++)
+			init_completion(&dln2->mod_rx_slots[i].slots[j].done);
+	}
+
+	spin_lock_init(&dln2->event_cb_lock);
+	spin_lock_init(&dln2->disconnect_lock);
+	INIT_LIST_HEAD(&dln2->event_cb_list);
+
+	ret = dln2_setup_rx_urbs(dln2, hostif);
+	if (ret)
+		goto out_cleanup;
+
+	ret = dln2_hw_init(dln2);
+	if (ret < 0) {
+		dev_err(dev, "failed to initialize hardware\n");
+		goto out_cleanup;
+	}
+
+	ret = mfd_add_hotplug_devices(dev, dln2_devs, ARRAY_SIZE(dln2_devs));
+	if (ret != 0) {
+		dev_err(dev, "failed to add mfd devices to core\n");
+		goto out_cleanup;
+	}
+
+	return 0;
+
+out_cleanup:
+	dln2_free(dln2);
+
+	return ret;
+}
+
+static const struct usb_device_id dln2_table[] = {
+	{ USB_DEVICE(0xa257, 0x2013) },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(usb, dln2_table);
+
+static struct usb_driver dln2_driver = {
+	.name = "dln2",
+	.probe = dln2_probe,
+	.disconnect = dln2_disconnect,
+	.id_table = dln2_table,
+};
+
+module_usb_driver(dln2_driver);
+
+MODULE_AUTHOR("Octavian Purdila <octavian.purdila@intel.com>");
+MODULE_DESCRIPTION("Core driver for the Diolan DLN2 interface adapter");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mfd/dln2.h b/include/linux/mfd/dln2.h
new file mode 100644
index 00000000000..004b24576da
--- /dev/null
+++ b/include/linux/mfd/dln2.h
@@ -0,0 +1,103 @@
+#ifndef __LINUX_USB_DLN2_H
+#define __LINUX_USB_DLN2_H
+
+#define DLN2_CMD(cmd, id)		((cmd) | ((id) << 8))
+
+struct dln2_platform_data {
+	u16 handle;		/* sub-driver handle (internally used only) */
+	u8 port;		/* I2C/SPI port */
+};
+
+/**
+ * dln2_event_cb_t - event callback function signature
+ *
+ * @pdev - the sub-device that registered this callback
+ * @echo - the echo header field received in the message
+ * @data - the data payload
+ * @len  - the data payload length
+ *
+ * The callback function is called in interrupt context and the data payload is
+ * only valid during the call. If the user needs later access of the data, it
+ * must copy it.
+ */
+
+typedef void (*dln2_event_cb_t)(struct platform_device *pdev, u16 echo,
+				const void *data, int len);
+
+/**
+ * dl2n_register_event_cb - register a callback function for an event
+ *
+ * @pdev - the sub-device that registers the callback
+ * @event - the event for which to register a callback
+ * @event_cb - the callback function
+ *
+ * @return 0 in case of success, negative value in case of error
+ */
+int dln2_register_event_cb(struct platform_device *pdev, u16 event,
+			   dln2_event_cb_t event_cb);
+
+/**
+ * dln2_unregister_event_cb - unregister the callback function for an event
+ *
+ * @pdev - the sub-device that registered the callback
+ * @event - the event for which to register a callback
+ */
+void dln2_unregister_event_cb(struct platform_device *pdev, u16 event);
+
+/**
+ * dln2_transfer - issue a DLN2 command and wait for a response and the
+ * associated data
+ *
+ * @pdev - the sub-device which is issuing this transfer
+ * @cmd - the command to be sent to the device
+ * @obuf - the buffer to be sent to the device; it can be NULL if the user
+ *	doesn't need to transmit data with this command
+ * @obuf_len - the size of the buffer to be sent to the device
+ * @ibuf - any data associated with the response will be copied here; it can be
+ *	NULL if the user doesn't need the response data
+ * @ibuf_len - must be initialized to the input buffer size; it will be modified
+ *	to indicate the actual data transferred;
+ *
+ * @return 0 for success, negative value for errors
+ */
+int dln2_transfer(struct platform_device *pdev, u16 cmd,
+		  const void *obuf, unsigned obuf_len,
+		  void *ibuf, unsigned *ibuf_len);
+
+/**
+ * dln2_transfer_rx - variant of @dln2_transfer() where TX buffer is not needed
+ *
+ * @pdev - the sub-device which is issuing this transfer
+ * @cmd - the command to be sent to the device
+ * @ibuf - any data associated with the response will be copied here; it can be
+ *	NULL if the user doesn't need the response data
+ * @ibuf_len - must be initialized to the input buffer size; it will be modified
+ *	to indicate the actual data transferred;
+ *
+ * @return 0 for success, negative value for errors
+ */
+
+static inline int dln2_transfer_rx(struct platform_device *pdev, u16 cmd,
+				   void *ibuf, unsigned *ibuf_len)
+{
+	return dln2_transfer(pdev, cmd, NULL, 0, ibuf, ibuf_len);
+}
+
+/**
+ * dln2_transfer_tx - variant of @dln2_transfer() where RX buffer is not needed
+ *
+ * @pdev - the sub-device which is issuing this transfer
+ * @cmd - the command to be sent to the device
+ * @obuf - the buffer to be sent to the device; it can be NULL if the
+ *	user doesn't need to transmit data with this command
+ * @obuf_len - the size of the buffer to be sent to the device
+ *
+ * @return 0 for success, negative value for errors
+ */
+static inline int dln2_transfer_tx(struct platform_device *pdev, u16 cmd,
+				   const void *obuf, unsigned obuf_len)
+{
+	return dln2_transfer(pdev, cmd, obuf, obuf_len, NULL, NULL);
+}
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From be955b2984822e2a66176bccb3e0dbaf9cd569b6 Mon Sep 17 00:00:00 2001
From: Dave Taht <dave.taht@bufferbloat.net>
Date: Thu, 6 Nov 2014 08:10:14 -0800
Subject: rtnetlink: add babel protocol recognition

Babel uses rt_proto 42. Add to userspace visible header file.

Signed-off-by: Dave Taht <dave.taht@bufferbloat.net>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/rtnetlink.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index eb0f1a554d7..9c9b8b4480c 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -235,6 +235,7 @@ enum {
 #define RTPROT_NTK	15	/* Netsukuku */
 #define RTPROT_DHCP	16      /* DHCP client */
 #define RTPROT_MROUTED	17      /* Multicast daemon */
+#define RTPROT_BABEL	42      /* Babel daemon */
 
 /* rtm_scope
 
-- 
cgit v1.2.3-70-g09d2


From 3b47d30396bae4f0bd1ff0dbcd7c4f5077e7df4e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 6 Nov 2014 21:09:44 -0800
Subject: net: gro: add a per device gro flush timer

Tuning coalescing parameters on NIC can be really hard.

Servers can handle both bulk and RPC like traffic, with conflicting
goals : bulk flows want as big GRO packets as possible, RPC want minimal
latencies.

To reach big GRO packets on 10Gbe NIC, one can use :

ethtool -C eth0 rx-usecs 4 rx-frames 44

But this penalizes rpc sessions, with an increase of latencies, up to
50% in some cases, as NICs generally do not force an interrupt when
a packet with TCP Push flag is received.

Some NICs do not have an absolute timer, only a timer rearmed for every
incoming packet.

This patch uses a different strategy : Let GRO stack decides what do do,
based on traffic pattern.

Packets with Push flag wont be delayed.
Packets without Push flag might be held in GRO engine, if we keep
receiving data.

This new mechanism is off by default, and shall be enabled by setting
/sys/class/net/ethX/gro_flush_timeout to a value in nanosecond.

To fully enable this mechanism, drivers should use napi_complete_done()
instead of napi_complete().

Tested:
 Ran 200 netperf TCP_STREAM from A to B (10Gbe mlx4 link, 8 RX queues)

Without this feature, we send back about 305,000 ACK per second.

GRO aggregation ratio is low (811/305 = 2.65 segments per GRO packet)

Setting a timer of 2000 nsec is enough to increase GRO packet sizes
and reduce number of ACK packets. (811/19.2 = 42)

Receiver performs less calls to upper stacks, less wakes up.
This also reduces cpu usage on the sender, as it receives less ACK
packets.

Note that reducing number of wakes up increases cpu efficiency, but can
decrease QPS, as applications wont have the chance to warmup cpu caches
doing a partial read of RPC requests/answers if they fit in one skb.

B:~# sar -n DEV 1 10 | grep eth0 | tail -1
Average:         eth0 811269.80 305732.30 1199462.57  19705.72      0.00
0.00      0.50

B:~# echo 2000 >/sys/class/net/eth0/gro_flush_timeout

B:~# sar -n DEV 1 10 | grep eth0 | tail -1
Average:         eth0 811577.30  19230.80 1199916.51   1239.80      0.00
0.00      0.50

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 20 ++++++++++----------
 net/core/dev.c            | 45 +++++++++++++++++++++++++++++++++++++++++----
 net/core/net-sysfs.c      | 18 ++++++++++++++++++
 3 files changed, 69 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 90ac95900a1..888d5513fa4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -314,6 +314,7 @@ struct napi_struct {
 	struct net_device	*dev;
 	struct sk_buff		*gro_list;
 	struct sk_buff		*skb;
+	struct hrtimer		timer;
 	struct list_head	dev_list;
 	struct hlist_node	napi_hash_node;
 	unsigned int		napi_id;
@@ -443,14 +444,19 @@ static inline bool napi_reschedule(struct napi_struct *napi)
 	return false;
 }
 
+void __napi_complete(struct napi_struct *n);
+void napi_complete_done(struct napi_struct *n, int work_done);
 /**
  *	napi_complete - NAPI processing complete
  *	@n: napi context
  *
  * Mark NAPI processing as complete.
+ * Consider using napi_complete_done() instead.
  */
-void __napi_complete(struct napi_struct *n);
-void napi_complete(struct napi_struct *n);
+static inline void napi_complete(struct napi_struct *n)
+{
+	return napi_complete_done(n, 0);
+}
 
 /**
  *	napi_by_id - lookup a NAPI by napi_id
@@ -485,14 +491,7 @@ void napi_hash_del(struct napi_struct *napi);
  * Stop NAPI from being scheduled on this context.
  * Waits till any outstanding processing completes.
  */
-static inline void napi_disable(struct napi_struct *n)
-{
-	might_sleep();
-	set_bit(NAPI_STATE_DISABLE, &n->state);
-	while (test_and_set_bit(NAPI_STATE_SCHED, &n->state))
-		msleep(1);
-	clear_bit(NAPI_STATE_DISABLE, &n->state);
-}
+void napi_disable(struct napi_struct *n);
 
 /**
  *	napi_enable - enable NAPI scheduling
@@ -1603,6 +1602,7 @@ struct net_device {
 
 #endif
 
+	unsigned long		gro_flush_timeout;
 	rx_handler_func_t __rcu	*rx_handler;
 	void __rcu		*rx_handler_data;
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 70bb609c283..bb09b036461 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -134,6 +134,7 @@
 #include <linux/vmalloc.h>
 #include <linux/if_macvlan.h>
 #include <linux/errqueue.h>
+#include <linux/hrtimer.h>
 
 #include "net-sysfs.h"
 
@@ -4412,7 +4413,6 @@ EXPORT_SYMBOL(__napi_schedule_irqoff);
 void __napi_complete(struct napi_struct *n)
 {
 	BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
-	BUG_ON(n->gro_list);
 
 	list_del_init(&n->poll_list);
 	smp_mb__before_atomic();
@@ -4420,7 +4420,7 @@ void __napi_complete(struct napi_struct *n)
 }
 EXPORT_SYMBOL(__napi_complete);
 
-void napi_complete(struct napi_struct *n)
+void napi_complete_done(struct napi_struct *n, int work_done)
 {
 	unsigned long flags;
 
@@ -4431,8 +4431,18 @@ void napi_complete(struct napi_struct *n)
 	if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
 		return;
 
-	napi_gro_flush(n, false);
+	if (n->gro_list) {
+		unsigned long timeout = 0;
 
+		if (work_done)
+			timeout = n->dev->gro_flush_timeout;
+
+		if (timeout)
+			hrtimer_start(&n->timer, ns_to_ktime(timeout),
+				      HRTIMER_MODE_REL_PINNED);
+		else
+			napi_gro_flush(n, false);
+	}
 	if (likely(list_empty(&n->poll_list))) {
 		WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state));
 	} else {
@@ -4442,7 +4452,7 @@ void napi_complete(struct napi_struct *n)
 		local_irq_restore(flags);
 	}
 }
-EXPORT_SYMBOL(napi_complete);
+EXPORT_SYMBOL(napi_complete_done);
 
 /* must be called under rcu_read_lock(), as we dont take a reference */
 struct napi_struct *napi_by_id(unsigned int napi_id)
@@ -4496,10 +4506,23 @@ void napi_hash_del(struct napi_struct *napi)
 }
 EXPORT_SYMBOL_GPL(napi_hash_del);
 
+static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
+{
+	struct napi_struct *napi;
+
+	napi = container_of(timer, struct napi_struct, timer);
+	if (napi->gro_list)
+		napi_schedule(napi);
+
+	return HRTIMER_NORESTART;
+}
+
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight)
 {
 	INIT_LIST_HEAD(&napi->poll_list);
+	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
+	napi->timer.function = napi_watchdog;
 	napi->gro_count = 0;
 	napi->gro_list = NULL;
 	napi->skb = NULL;
@@ -4518,6 +4541,20 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 }
 EXPORT_SYMBOL(netif_napi_add);
 
+void napi_disable(struct napi_struct *n)
+{
+	might_sleep();
+	set_bit(NAPI_STATE_DISABLE, &n->state);
+
+	while (test_and_set_bit(NAPI_STATE_SCHED, &n->state))
+		msleep(1);
+
+	hrtimer_cancel(&n->timer);
+
+	clear_bit(NAPI_STATE_DISABLE, &n->state);
+}
+EXPORT_SYMBOL(napi_disable);
+
 void netif_napi_del(struct napi_struct *napi)
 {
 	list_del_init(&napi->dev_list);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 9dd06699b09..1a24602cd54 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -325,6 +325,23 @@ static ssize_t tx_queue_len_store(struct device *dev,
 }
 NETDEVICE_SHOW_RW(tx_queue_len, fmt_ulong);
 
+static int change_gro_flush_timeout(struct net_device *dev, unsigned long val)
+{
+	dev->gro_flush_timeout = val;
+	return 0;
+}
+
+static ssize_t gro_flush_timeout_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t len)
+{
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	return netdev_store(dev, attr, buf, len, change_gro_flush_timeout);
+}
+NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong);
+
 static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
 			     const char *buf, size_t len)
 {
@@ -422,6 +439,7 @@ static struct attribute *net_class_attrs[] = {
 	&dev_attr_mtu.attr,
 	&dev_attr_flags.attr,
 	&dev_attr_tx_queue_len.attr,
+	&dev_attr_gro_flush_timeout.attr,
 	&dev_attr_phys_port_id.attr,
 	NULL,
 };
-- 
cgit v1.2.3-70-g09d2


From 7aff221c5dbe4f88930a64531df2236f303e1851 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Sat, 8 Nov 2014 10:42:46 +1100
Subject: ARM: OMAP: serial: remove last vestige of DTR_gpio support.

These fields were added by:
commit 9574f36fb801035f6ab0fbb1b53ce2c12c17d100
    OMAP/serial: Add support for driving a GPIO as DTR.

but not removed by

commit 985bfd54c826c0ba873ca0adfd5589263e0c6ee2
    tty: serial: omap: remove some dead code

which reverted most of that commit.
Time to revert the rest.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/serial.c              | 3 ---
 include/linux/platform_data/serial-omap.h | 3 ---
 2 files changed, 6 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/serial.c b/arch/arm/mach-omap2/serial.c
index a388f8c1bcb..57dee0c7cd2 100644
--- a/arch/arm/mach-omap2/serial.c
+++ b/arch/arm/mach-omap2/serial.c
@@ -263,9 +263,6 @@ void __init omap_serial_init_port(struct omap_board_data *bdata,
 	omap_up.dma_rx_timeout = info->dma_rx_timeout;
 	omap_up.dma_rx_poll_rate = info->dma_rx_poll_rate;
 	omap_up.autosuspend_timeout = info->autosuspend_timeout;
-	omap_up.DTR_gpio = info->DTR_gpio;
-	omap_up.DTR_inverted = info->DTR_inverted;
-	omap_up.DTR_present = info->DTR_present;
 
 	pdata = &omap_up;
 	pdata_size = sizeof(struct omap_uart_port_info);
diff --git a/include/linux/platform_data/serial-omap.h b/include/linux/platform_data/serial-omap.h
index c860c1b314c..d09275f3cde 100644
--- a/include/linux/platform_data/serial-omap.h
+++ b/include/linux/platform_data/serial-omap.h
@@ -38,9 +38,6 @@ struct omap_uart_port_info {
 	unsigned int		dma_rx_timeout;
 	unsigned int		autosuspend_timeout;
 	unsigned int		dma_rx_poll_rate;
-	int			DTR_gpio;
-	int			DTR_inverted;
-	int			DTR_present;
 
 	int (*get_context_loss_count)(struct device *);
 	void (*enable_wakeup)(struct device *, bool);
-- 
cgit v1.2.3-70-g09d2


From 1ef8019be8799c39f316a772ffdd705c46029752 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 10 Nov 2014 13:27:49 -0500
Subject: net: Move bonding headers under include/net

This ways drivers like cxgb4 don't need to do ugly relative includes.

Reported-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_3ad.c                  |   4 +-
 drivers/net/bonding/bond_3ad.h                  | 283 ----------
 drivers/net/bonding/bond_alb.c                  |   4 +-
 drivers/net/bonding/bond_alb.h                  | 181 -------
 drivers/net/bonding/bond_debugfs.c              |   4 +-
 drivers/net/bonding/bond_main.c                 |   6 +-
 drivers/net/bonding/bond_netlink.c              |   2 +-
 drivers/net/bonding/bond_options.c              |   2 +-
 drivers/net/bonding/bond_options.h              | 130 -----
 drivers/net/bonding/bond_procfs.c               |   2 +-
 drivers/net/bonding/bond_sysfs.c                |   2 +-
 drivers/net/bonding/bond_sysfs_slave.c          |   2 +-
 drivers/net/bonding/bonding.h                   | 654 ------------------------
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c |   3 +-
 include/net/bond_3ad.h                          | 283 ++++++++++
 include/net/bond_alb.h                          | 181 +++++++
 include/net/bond_options.h                      | 130 +++++
 include/net/bonding.h                           | 654 ++++++++++++++++++++++++
 18 files changed, 1263 insertions(+), 1264 deletions(-)
 delete mode 100644 drivers/net/bonding/bond_3ad.h
 delete mode 100644 drivers/net/bonding/bond_alb.h
 delete mode 100644 drivers/net/bonding/bond_options.h
 delete mode 100644 drivers/net/bonding/bonding.h
 create mode 100644 include/net/bond_3ad.h
 create mode 100644 include/net/bond_alb.h
 create mode 100644 include/net/bond_options.h
 create mode 100644 include/net/bonding.h

(limited to 'include')

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 2110215f352..0a32143af12 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -29,8 +29,8 @@
 #include <linux/if_bonding.h>
 #include <linux/pkt_sched.h>
 #include <net/net_namespace.h>
-#include "bonding.h"
-#include "bond_3ad.h"
+#include <net/bonding.h>
+#include <net/bond_3ad.h>
 
 /* General definitions */
 #define AD_SHORT_TIMEOUT           1
diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h
deleted file mode 100644
index c5f14ac63f3..00000000000
--- a/drivers/net/bonding/bond_3ad.h
+++ /dev/null
@@ -1,283 +0,0 @@
-/*
- * Copyright(c) 1999 - 2004 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
- * The full GNU General Public License is included in this distribution in the
- * file called LICENSE.
- *
- */
-
-#ifndef __BOND_3AD_H__
-#define __BOND_3AD_H__
-
-#include <asm/byteorder.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <linux/if_ether.h>
-
-/* General definitions */
-#define PKT_TYPE_LACPDU         cpu_to_be16(ETH_P_SLOW)
-#define AD_TIMER_INTERVAL       100 /*msec*/
-
-#define MULTICAST_LACPDU_ADDR    {0x01, 0x80, 0xC2, 0x00, 0x00, 0x02}
-
-#define AD_LACP_SLOW 0
-#define AD_LACP_FAST 1
-
-typedef struct mac_addr {
-	u8 mac_addr_value[ETH_ALEN];
-} __packed mac_addr_t;
-
-enum {
-	BOND_AD_STABLE = 0,
-	BOND_AD_BANDWIDTH = 1,
-	BOND_AD_COUNT = 2,
-};
-
-/* rx machine states(43.4.11 in the 802.3ad standard) */
-typedef enum {
-	AD_RX_DUMMY,
-	AD_RX_INITIALIZE,	/* rx Machine */
-	AD_RX_PORT_DISABLED,	/* rx Machine */
-	AD_RX_LACP_DISABLED,	/* rx Machine */
-	AD_RX_EXPIRED,		/* rx Machine */
-	AD_RX_DEFAULTED,	/* rx Machine */
-	AD_RX_CURRENT		/* rx Machine */
-} rx_states_t;
-
-/* periodic machine states(43.4.12 in the 802.3ad standard) */
-typedef enum {
-	AD_PERIODIC_DUMMY,
-	AD_NO_PERIODIC,		/* periodic machine */
-	AD_FAST_PERIODIC,	/* periodic machine */
-	AD_SLOW_PERIODIC,	/* periodic machine */
-	AD_PERIODIC_TX		/* periodic machine */
-} periodic_states_t;
-
-/* mux machine states(43.4.13 in the 802.3ad standard) */
-typedef enum {
-	AD_MUX_DUMMY,
-	AD_MUX_DETACHED,	/* mux machine */
-	AD_MUX_WAITING,		/* mux machine */
-	AD_MUX_ATTACHED,	/* mux machine */
-	AD_MUX_COLLECTING_DISTRIBUTING	/* mux machine */
-} mux_states_t;
-
-/* tx machine states(43.4.15 in the 802.3ad standard) */
-typedef enum {
-	AD_TX_DUMMY,
-	AD_TRANSMIT		/* tx Machine */
-} tx_states_t;
-
-/* rx indication types */
-typedef enum {
-	AD_TYPE_LACPDU = 1,	/* type lacpdu */
-	AD_TYPE_MARKER		/* type marker */
-} pdu_type_t;
-
-/* rx marker indication types */
-typedef enum {
-	AD_MARKER_INFORMATION_SUBTYPE = 1,	/* marker imformation subtype */
-	AD_MARKER_RESPONSE_SUBTYPE		/* marker response subtype */
-} bond_marker_subtype_t;
-
-/* timers types(43.4.9 in the 802.3ad standard) */
-typedef enum {
-	AD_CURRENT_WHILE_TIMER,
-	AD_ACTOR_CHURN_TIMER,
-	AD_PERIODIC_TIMER,
-	AD_PARTNER_CHURN_TIMER,
-	AD_WAIT_WHILE_TIMER
-} ad_timers_t;
-
-#pragma pack(1)
-
-/* Link Aggregation Control Protocol(LACP) data unit structure(43.4.2.2 in the 802.3ad standard) */
-typedef struct lacpdu {
-	u8 subtype;		/* = LACP(= 0x01) */
-	u8 version_number;
-	u8 tlv_type_actor_info;	/* = actor information(type/length/value) */
-	u8 actor_information_length;	/* = 20 */
-	__be16 actor_system_priority;
-	struct mac_addr actor_system;
-	__be16 actor_key;
-	__be16 actor_port_priority;
-	__be16 actor_port;
-	u8 actor_state;
-	u8 reserved_3_1[3];		/* = 0 */
-	u8 tlv_type_partner_info;	/* = partner information */
-	u8 partner_information_length;	/* = 20 */
-	__be16 partner_system_priority;
-	struct mac_addr partner_system;
-	__be16 partner_key;
-	__be16 partner_port_priority;
-	__be16 partner_port;
-	u8 partner_state;
-	u8 reserved_3_2[3];		/* = 0 */
-	u8 tlv_type_collector_info;	/* = collector information */
-	u8 collector_information_length;/* = 16 */
-	__be16 collector_max_delay;
-	u8 reserved_12[12];
-	u8 tlv_type_terminator;		/* = terminator */
-	u8 terminator_length;		/* = 0 */
-	u8 reserved_50[50];		/* = 0 */
-} __packed lacpdu_t;
-
-typedef struct lacpdu_header {
-	struct ethhdr hdr;
-	struct lacpdu lacpdu;
-} __packed lacpdu_header_t;
-
-/* Marker Protocol Data Unit(PDU) structure(43.5.3.2 in the 802.3ad standard) */
-typedef struct bond_marker {
-	u8 subtype;		/* = 0x02  (marker PDU) */
-	u8 version_number;	/* = 0x01 */
-	u8 tlv_type;		/* = 0x01  (marker information) */
-	/* = 0x02  (marker response information) */
-	u8 marker_length;	/* = 0x16 */
-	u16 requester_port;	/* The number assigned to the port by the requester */
-	struct mac_addr requester_system;	/* The requester's system id */
-	u32 requester_transaction_id;		/* The transaction id allocated by the requester, */
-	u16 pad;		/* = 0 */
-	u8 tlv_type_terminator;	/* = 0x00 */
-	u8 terminator_length;	/* = 0x00 */
-	u8 reserved_90[90];	/* = 0 */
-} __packed bond_marker_t;
-
-typedef struct bond_marker_header {
-	struct ethhdr hdr;
-	struct bond_marker marker;
-} __packed bond_marker_header_t;
-
-#pragma pack()
-
-struct slave;
-struct bonding;
-struct ad_info;
-struct port;
-
-#ifdef __ia64__
-#pragma pack(8)
-#endif
-
-/* aggregator structure(43.4.5 in the 802.3ad standard) */
-typedef struct aggregator {
-	struct mac_addr aggregator_mac_address;
-	u16 aggregator_identifier;
-	bool is_individual;
-	u16 actor_admin_aggregator_key;
-	u16 actor_oper_aggregator_key;
-	struct mac_addr partner_system;
-	u16 partner_system_priority;
-	u16 partner_oper_aggregator_key;
-	u16 receive_state;	/* BOOLEAN */
-	u16 transmit_state;	/* BOOLEAN */
-	struct port *lag_ports;
-	/* ****** PRIVATE PARAMETERS ****** */
-	struct slave *slave;	/* pointer to the bond slave that this aggregator belongs to */
-	u16 is_active;		/* BOOLEAN. Indicates if this aggregator is active */
-	u16 num_of_ports;
-} aggregator_t;
-
-struct port_params {
-	struct mac_addr system;
-	u16 system_priority;
-	u16 key;
-	u16 port_number;
-	u16 port_priority;
-	u16 port_state;
-};
-
-/* port structure(43.4.6 in the 802.3ad standard) */
-typedef struct port {
-	u16 actor_port_number;
-	u16 actor_port_priority;
-	struct mac_addr actor_system;	/* This parameter is added here although it is not specified in the standard, just for simplification */
-	u16 actor_system_priority;	/* This parameter is added here although it is not specified in the standard, just for simplification */
-	u16 actor_port_aggregator_identifier;
-	bool ntt;
-	u16 actor_admin_port_key;
-	u16 actor_oper_port_key;
-	u8 actor_admin_port_state;
-	u8 actor_oper_port_state;
-
-	struct port_params partner_admin;
-	struct port_params partner_oper;
-
-	bool is_enabled;
-
-	/* ****** PRIVATE PARAMETERS ****** */
-	u16 sm_vars;		/* all state machines variables for this port */
-	rx_states_t sm_rx_state;	/* state machine rx state */
-	u16 sm_rx_timer_counter;	/* state machine rx timer counter */
-	periodic_states_t sm_periodic_state;	/* state machine periodic state */
-	u16 sm_periodic_timer_counter;	/* state machine periodic timer counter */
-	mux_states_t sm_mux_state;	/* state machine mux state */
-	u16 sm_mux_timer_counter;	/* state machine mux timer counter */
-	tx_states_t sm_tx_state;	/* state machine tx state */
-	u16 sm_tx_timer_counter;	/* state machine tx timer counter(allways on - enter to transmit state 3 time per second) */
-	struct slave *slave;		/* pointer to the bond slave that this port belongs to */
-	struct aggregator *aggregator;	/* pointer to an aggregator that this port related to */
-	struct port *next_port_in_aggregator;	/* Next port on the linked list of the parent aggregator */
-	u32 transaction_id;		/* continuous number for identification of Marker PDU's; */
-	struct lacpdu lacpdu;		/* the lacpdu that will be sent for this port */
-} port_t;
-
-/* system structure */
-struct ad_system {
-	u16 sys_priority;
-	struct mac_addr sys_mac_addr;
-};
-
-#ifdef __ia64__
-#pragma pack()
-#endif
-
-/* ========== AD Exported structures to the main bonding code ========== */
-#define BOND_AD_INFO(bond)   ((bond)->ad_info)
-#define SLAVE_AD_INFO(slave) ((slave)->ad_info)
-
-struct ad_bond_info {
-	struct ad_system system;	/* 802.3ad system structure */
-	u32 agg_select_timer;		/* Timer to select aggregator after all adapter's hand shakes */
-	u16 aggregator_identifier;
-};
-
-struct ad_slave_info {
-	struct aggregator aggregator;	/* 802.3ad aggregator structure */
-	struct port port;		/* 802.3ad port structure */
-	u16 id;
-};
-
-/* ========== AD Exported functions to the main bonding code ========== */
-void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution);
-void bond_3ad_bind_slave(struct slave *slave);
-void bond_3ad_unbind_slave(struct slave *slave);
-void bond_3ad_state_machine_handler(struct work_struct *);
-void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout);
-void bond_3ad_adapter_speed_changed(struct slave *slave);
-void bond_3ad_adapter_duplex_changed(struct slave *slave);
-void bond_3ad_handle_link_change(struct slave *slave, char link);
-int  bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info);
-int  __bond_3ad_get_active_agg_info(struct bonding *bond,
-				    struct ad_info *ad_info);
-int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev);
-int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
-			 struct slave *slave);
-int bond_3ad_set_carrier(struct bonding *bond);
-void bond_3ad_update_lacp_rate(struct bonding *bond);
-#endif /* __BOND_3AD_H__ */
-
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index baa58e79256..e1f1a006af8 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -37,8 +37,8 @@
 #include <net/arp.h>
 #include <net/ipv6.h>
 #include <asm/byteorder.h>
-#include "bonding.h"
-#include "bond_alb.h"
+#include <net/bonding.h>
+#include <net/bond_alb.h>
 
 
 
diff --git a/drivers/net/bonding/bond_alb.h b/drivers/net/bonding/bond_alb.h
deleted file mode 100644
index 1ad473b4ade..00000000000
--- a/drivers/net/bonding/bond_alb.h
+++ /dev/null
@@ -1,181 +0,0 @@
-/*
- * Copyright(c) 1999 - 2004 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
- * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in the
- * file called LICENSE.
- *
- */
-
-#ifndef __BOND_ALB_H__
-#define __BOND_ALB_H__
-
-#include <linux/if_ether.h>
-
-struct bonding;
-struct slave;
-
-#define BOND_ALB_INFO(bond)   ((bond)->alb_info)
-#define SLAVE_TLB_INFO(slave) ((slave)->tlb_info)
-
-#define ALB_TIMER_TICKS_PER_SEC	    10	/* should be a divisor of HZ */
-#define BOND_TLB_REBALANCE_INTERVAL 10	/* In seconds, periodic re-balancing.
-					 * Used for division - never set
-					 * to zero !!!
-					 */
-#define BOND_ALB_DEFAULT_LP_INTERVAL 1
-#define BOND_ALB_LP_INTERVAL(bond) (bond->params.lp_interval)	/* In seconds, periodic send of
-								 * learning packets to the switch
-								 */
-
-#define BOND_TLB_REBALANCE_TICKS (BOND_TLB_REBALANCE_INTERVAL \
-				  * ALB_TIMER_TICKS_PER_SEC)
-
-#define BOND_ALB_LP_TICKS(bond) (BOND_ALB_LP_INTERVAL(bond) \
-			   * ALB_TIMER_TICKS_PER_SEC)
-
-#define TLB_HASH_TABLE_SIZE 256	/* The size of the clients hash table.
-				 * Note that this value MUST NOT be smaller
-				 * because the key hash table is BYTE wide !
-				 */
-
-
-#define TLB_NULL_INDEX		0xffffffff
-
-/* rlb defs */
-#define RLB_HASH_TABLE_SIZE	256
-#define RLB_NULL_INDEX		0xffffffff
-#define RLB_UPDATE_DELAY	(2*ALB_TIMER_TICKS_PER_SEC) /* 2 seconds */
-#define RLB_ARP_BURST_SIZE	2
-#define RLB_UPDATE_RETRY	3 /* 3-ticks - must be smaller than the rlb
-				   * rebalance interval (5 min).
-				   */
-/* RLB_PROMISC_TIMEOUT = 10 sec equals the time that the current slave is
- * promiscuous after failover
- */
-#define RLB_PROMISC_TIMEOUT	(10*ALB_TIMER_TICKS_PER_SEC)
-
-
-struct tlb_client_info {
-	struct slave *tx_slave;	/* A pointer to slave used for transmiting
-				 * packets to a Client that the Hash function
-				 * gave this entry index.
-				 */
-	u32 tx_bytes;		/* Each Client accumulates the BytesTx that
-				 * were transmitted to it, and after each
-				 * CallBack the LoadHistory is divided
-				 * by the balance interval
-				 */
-	u32 load_history;	/* This field contains the amount of Bytes
-				 * that were transmitted to this client by
-				 * the server on the previous balance
-				 * interval in Bps.
-				 */
-	u32 next;		/* The next Hash table entry index, assigned
-				 * to use the same adapter for transmit.
-				 */
-	u32 prev;		/* The previous Hash table entry index,
-				 * assigned to use the same
-				 */
-};
-
-/* -------------------------------------------------------------------------
- * struct rlb_client_info contains all info related to a specific rx client
- * connection. This is the Clients Hash Table entry struct.
- * Note that this is not a proper hash table; if a new client's IP address
- * hash collides with an existing client entry, the old entry is replaced.
- *
- * There is a linked list (linked by the used_next and used_prev members)
- * linking all the used entries of the hash table. This allows updating
- * all the clients without walking over all the unused elements of the table.
- *
- * There are also linked lists of entries with identical hash(ip_src). These
- * allow cleaning up the table from ip_src<->mac_src associations that have
- * become outdated and would cause sending out invalid ARP updates to the
- * network. These are linked by the (src_next and src_prev members).
- * -------------------------------------------------------------------------
- */
-struct rlb_client_info {
-	__be32 ip_src;		/* the server IP address */
-	__be32 ip_dst;		/* the client IP address */
-	u8  mac_src[ETH_ALEN];	/* the server MAC address */
-	u8  mac_dst[ETH_ALEN];	/* the client MAC address */
-
-	/* list of used hash table entries, starting at rx_hashtbl_used_head */
-	u32 used_next;
-	u32 used_prev;
-
-	/* ip_src based hashing */
-	u32 src_next;	/* next entry with same hash(ip_src) */
-	u32 src_prev;	/* prev entry with same hash(ip_src) */
-	u32 src_first;	/* first entry with hash(ip_src) == this entry's index */
-
-	u8  assigned;		/* checking whether this entry is assigned */
-	u8  ntt;		/* flag - need to transmit client info */
-	struct slave *slave;	/* the slave assigned to this client */
-	unsigned short vlan_id;	/* VLAN tag associated with IP address */
-};
-
-struct tlb_slave_info {
-	u32 head;	/* Index to the head of the bi-directional clients
-			 * hash table entries list. The entries in the list
-			 * are the entries that were assigned to use this
-			 * slave for transmit.
-			 */
-	u32 load;	/* Each slave sums the loadHistory of all clients
-			 * assigned to it
-			 */
-};
-
-struct alb_bond_info {
-	struct tlb_client_info	*tx_hashtbl; /* Dynamically allocated */
-	u32			unbalanced_load;
-	int			tx_rebalance_counter;
-	int			lp_counter;
-	/* -------- rlb parameters -------- */
-	int rlb_enabled;
-	struct rlb_client_info	*rx_hashtbl;	/* Receive hash table */
-	u32			rx_hashtbl_used_head;
-	u8			rx_ntt;	/* flag - need to transmit
-					 * to all rx clients
-					 */
-	struct slave		*rx_slave;/* last slave to xmit from */
-	u8			primary_is_promisc;	   /* boolean */
-	u32			rlb_promisc_timeout_counter;/* counts primary
-							     * promiscuity time
-							     */
-	u32			rlb_update_delay_counter;
-	u32			rlb_update_retry_counter;/* counter of retries
-							  * of client update
-							  */
-	u8			rlb_rebalance;	/* flag - indicates that the
-						 * rx traffic should be
-						 * rebalanced
-						 */
-};
-
-int bond_alb_initialize(struct bonding *bond, int rlb_enabled);
-void bond_alb_deinitialize(struct bonding *bond);
-int bond_alb_init_slave(struct bonding *bond, struct slave *slave);
-void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave);
-void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char link);
-void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave);
-int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev);
-int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev);
-void bond_alb_monitor(struct work_struct *);
-int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr);
-void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id);
-#endif /* __BOND_ALB_H__ */
-
diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c
index 8f99082f90e..e52e25a977f 100644
--- a/drivers/net/bonding/bond_debugfs.c
+++ b/drivers/net/bonding/bond_debugfs.c
@@ -3,8 +3,8 @@
 #include <linux/device.h>
 #include <linux/netdevice.h>
 
-#include "bonding.h"
-#include "bond_alb.h"
+#include <net/bonding.h>
+#include <net/bond_alb.h>
 
 #if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_NET_NS)
 
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index c7520082fb0..b9b34566b9b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -77,9 +77,9 @@
 #include <net/pkt_sched.h>
 #include <linux/rculist.h>
 #include <net/flow_keys.h>
-#include "bonding.h"
-#include "bond_3ad.h"
-#include "bond_alb.h"
+#include <net/bonding.h>
+#include <net/bond_3ad.h>
+#include <net/bond_alb.h>
 
 /*---------------------------- Module parameters ----------------------------*/
 
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index c13d83e15ac..3e6eebd5be5 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -17,7 +17,7 @@
 #include <linux/if_ether.h>
 #include <net/netlink.h>
 #include <net/rtnetlink.h>
-#include "bonding.h"
+#include <net/bonding.h>
 
 static size_t bond_get_slave_size(const struct net_device *bond_dev,
 				  const struct net_device *slave_dev)
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index b62697f4a3d..1a61cc9b340 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -16,7 +16,7 @@
 #include <linux/rcupdate.h>
 #include <linux/ctype.h>
 #include <linux/inet.h>
-#include "bonding.h"
+#include <net/bonding.h>
 
 static int bond_option_active_slave_set(struct bonding *bond,
 					const struct bond_opt_value *newval);
diff --git a/drivers/net/bonding/bond_options.h b/drivers/net/bonding/bond_options.h
deleted file mode 100644
index 17ded5b2917..00000000000
--- a/drivers/net/bonding/bond_options.h
+++ /dev/null
@@ -1,130 +0,0 @@
-/*
- * drivers/net/bond/bond_options.h - bonding options
- * Copyright (c) 2013 Nikolay Aleksandrov <nikolay@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef _BOND_OPTIONS_H
-#define _BOND_OPTIONS_H
-
-#define BOND_OPT_MAX_NAMELEN 32
-#define BOND_OPT_VALID(opt) ((opt) < BOND_OPT_LAST)
-#define BOND_MODE_ALL_EX(x) (~(x))
-
-/* Option flags:
- * BOND_OPTFLAG_NOSLAVES - check if the bond device is empty before setting
- * BOND_OPTFLAG_IFDOWN - check if the bond device is down before setting
- * BOND_OPTFLAG_RAWVAL - the option parses the value itself
- */
-enum {
-	BOND_OPTFLAG_NOSLAVES	= BIT(0),
-	BOND_OPTFLAG_IFDOWN	= BIT(1),
-	BOND_OPTFLAG_RAWVAL	= BIT(2)
-};
-
-/* Value type flags:
- * BOND_VALFLAG_DEFAULT - mark the value as default
- * BOND_VALFLAG_(MIN|MAX) - mark the value as min/max
- */
-enum {
-	BOND_VALFLAG_DEFAULT	= BIT(0),
-	BOND_VALFLAG_MIN	= BIT(1),
-	BOND_VALFLAG_MAX	= BIT(2)
-};
-
-/* Option IDs, their bit positions correspond to their IDs */
-enum {
-	BOND_OPT_MODE,
-	BOND_OPT_PACKETS_PER_SLAVE,
-	BOND_OPT_XMIT_HASH,
-	BOND_OPT_ARP_VALIDATE,
-	BOND_OPT_ARP_ALL_TARGETS,
-	BOND_OPT_FAIL_OVER_MAC,
-	BOND_OPT_ARP_INTERVAL,
-	BOND_OPT_ARP_TARGETS,
-	BOND_OPT_DOWNDELAY,
-	BOND_OPT_UPDELAY,
-	BOND_OPT_LACP_RATE,
-	BOND_OPT_MINLINKS,
-	BOND_OPT_AD_SELECT,
-	BOND_OPT_NUM_PEER_NOTIF,
-	BOND_OPT_MIIMON,
-	BOND_OPT_PRIMARY,
-	BOND_OPT_PRIMARY_RESELECT,
-	BOND_OPT_USE_CARRIER,
-	BOND_OPT_ACTIVE_SLAVE,
-	BOND_OPT_QUEUE_ID,
-	BOND_OPT_ALL_SLAVES_ACTIVE,
-	BOND_OPT_RESEND_IGMP,
-	BOND_OPT_LP_INTERVAL,
-	BOND_OPT_SLAVES,
-	BOND_OPT_TLB_DYNAMIC_LB,
-	BOND_OPT_LAST
-};
-
-/* This structure is used for storing option values and for passing option
- * values when changing an option. The logic when used as an arg is as follows:
- * - if string != NULL -> parse it, if the opt is RAW type then return it, else
- *   return the parse result
- * - if string == NULL -> parse value
- */
-struct bond_opt_value {
-	char *string;
-	u64 value;
-	u32 flags;
-};
-
-struct bonding;
-
-struct bond_option {
-	int id;
-	const char *name;
-	const char *desc;
-	u32 flags;
-
-	/* unsuppmodes is used to denote modes in which the option isn't
-	 * supported.
-	 */
-	unsigned long unsuppmodes;
-	/* supported values which this option can have, can be a subset of
-	 * BOND_OPTVAL_RANGE's value range
-	 */
-	const struct bond_opt_value *values;
-
-	int (*set)(struct bonding *bond, const struct bond_opt_value *val);
-};
-
-int __bond_opt_set(struct bonding *bond, unsigned int option,
-		   struct bond_opt_value *val);
-int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf);
-
-const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt,
-					    struct bond_opt_value *val);
-const struct bond_option *bond_opt_get(unsigned int option);
-const struct bond_option *bond_opt_get_by_name(const char *name);
-const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val);
-
-/* This helper is used to initialize a bond_opt_value structure for parameter
- * passing. There should be either a valid string or value, but not both.
- * When value is ULLONG_MAX then string will be used.
- */
-static inline void __bond_opt_init(struct bond_opt_value *optval,
-				   char *string, u64 value)
-{
-	memset(optval, 0, sizeof(*optval));
-	optval->value = ULLONG_MAX;
-	if (value == ULLONG_MAX)
-		optval->string = string;
-	else
-		optval->value = value;
-}
-#define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value)
-#define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX)
-
-void bond_option_arp_ip_targets_clear(struct bonding *bond);
-
-#endif /* _BOND_OPTIONS_H */
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index a3948f8d1e5..976f5ad2a0f 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -2,7 +2,7 @@
 #include <linux/export.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
-#include "bonding.h"
+#include <net/bonding.h>
 
 
 static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 8ffbafd500f..7e9e151d4d6 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -40,7 +40,7 @@
 #include <net/netns/generic.h>
 #include <linux/nsproxy.h>
 
-#include "bonding.h"
+#include <net/bonding.h>
 
 #define to_dev(obj)	container_of(obj, struct device, kobj)
 #define to_bond(cd)	((struct bonding *)(netdev_priv(to_net_dev(cd))))
diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c
index b01b0ce4d1b..23618a83161 100644
--- a/drivers/net/bonding/bond_sysfs_slave.c
+++ b/drivers/net/bonding/bond_sysfs_slave.c
@@ -12,7 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
 
-#include "bonding.h"
+#include <net/bonding.h>
 
 struct slave_attribute {
 	struct attribute attr;
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
deleted file mode 100644
index bfb0b51c081..00000000000
--- a/drivers/net/bonding/bonding.h
+++ /dev/null
@@ -1,654 +0,0 @@
-/*
- * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'.
- *
- * Portions are (c) Copyright 1995 Simon "Guru Aleph-Null" Janes
- * NCM: Network and Communications Management, Inc.
- *
- * BUT, I'm the one who modified it for ethernet, so:
- * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov
- *
- *	This software may be used and distributed according to the terms
- *	of the GNU Public License, incorporated herein by reference.
- *
- */
-
-#ifndef _LINUX_BONDING_H
-#define _LINUX_BONDING_H
-
-#include <linux/timer.h>
-#include <linux/proc_fs.h>
-#include <linux/if_bonding.h>
-#include <linux/cpumask.h>
-#include <linux/in6.h>
-#include <linux/netpoll.h>
-#include <linux/inetdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/reciprocal_div.h>
-#include <linux/if_link.h>
-
-#include "bond_3ad.h"
-#include "bond_alb.h"
-#include "bond_options.h"
-
-#define DRV_VERSION	"3.7.1"
-#define DRV_RELDATE	"April 27, 2011"
-#define DRV_NAME	"bonding"
-#define DRV_DESCRIPTION	"Ethernet Channel Bonding Driver"
-
-#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n"
-
-#define BOND_MAX_ARP_TARGETS	16
-
-#define BOND_DEFAULT_MIIMON	100
-
-/*
- * Less bad way to call ioctl from within the kernel; this needs to be
- * done some other way to get the call out of interrupt context.
- * Needs "ioctl" variable to be supplied by calling context.
- */
-#define IOCTL(dev, arg, cmd) ({		\
-	int res = 0;			\
-	mm_segment_t fs = get_fs();	\
-	set_fs(get_ds());		\
-	res = ioctl(dev, arg, cmd);	\
-	set_fs(fs);			\
-	res; })
-
-#define BOND_MODE(bond) ((bond)->params.mode)
-
-/* slave list primitives */
-#define bond_slave_list(bond) (&(bond)->dev->adj_list.lower)
-
-#define bond_has_slaves(bond) !list_empty(bond_slave_list(bond))
-
-/* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */
-#define bond_first_slave(bond) \
-	(bond_has_slaves(bond) ? \
-		netdev_adjacent_get_private(bond_slave_list(bond)->next) : \
-		NULL)
-#define bond_last_slave(bond) \
-	(bond_has_slaves(bond) ? \
-		netdev_adjacent_get_private(bond_slave_list(bond)->prev) : \
-		NULL)
-
-/* Caller must have rcu_read_lock */
-#define bond_first_slave_rcu(bond) \
-	netdev_lower_get_first_private_rcu(bond->dev)
-
-#define bond_is_first_slave(bond, pos) (pos == bond_first_slave(bond))
-#define bond_is_last_slave(bond, pos) (pos == bond_last_slave(bond))
-
-/**
- * bond_for_each_slave - iterate over all slaves
- * @bond:	the bond holding this list
- * @pos:	current slave
- * @iter:	list_head * iterator
- *
- * Caller must hold RTNL
- */
-#define bond_for_each_slave(bond, pos, iter) \
-	netdev_for_each_lower_private((bond)->dev, pos, iter)
-
-/* Caller must have rcu_read_lock */
-#define bond_for_each_slave_rcu(bond, pos, iter) \
-	netdev_for_each_lower_private_rcu((bond)->dev, pos, iter)
-
-#ifdef CONFIG_NET_POLL_CONTROLLER
-extern atomic_t netpoll_block_tx;
-
-static inline void block_netpoll_tx(void)
-{
-	atomic_inc(&netpoll_block_tx);
-}
-
-static inline void unblock_netpoll_tx(void)
-{
-	atomic_dec(&netpoll_block_tx);
-}
-
-static inline int is_netpoll_tx_blocked(struct net_device *dev)
-{
-	if (unlikely(netpoll_tx_running(dev)))
-		return atomic_read(&netpoll_block_tx);
-	return 0;
-}
-#else
-#define block_netpoll_tx()
-#define unblock_netpoll_tx()
-#define is_netpoll_tx_blocked(dev) (0)
-#endif
-
-struct bond_params {
-	int mode;
-	int xmit_policy;
-	int miimon;
-	u8 num_peer_notif;
-	int arp_interval;
-	int arp_validate;
-	int arp_all_targets;
-	int use_carrier;
-	int fail_over_mac;
-	int updelay;
-	int downdelay;
-	int lacp_fast;
-	unsigned int min_links;
-	int ad_select;
-	char primary[IFNAMSIZ];
-	int primary_reselect;
-	__be32 arp_targets[BOND_MAX_ARP_TARGETS];
-	int tx_queues;
-	int all_slaves_active;
-	int resend_igmp;
-	int lp_interval;
-	int packets_per_slave;
-	int tlb_dynamic_lb;
-	struct reciprocal_value reciprocal_packets_per_slave;
-};
-
-struct bond_parm_tbl {
-	char *modename;
-	int mode;
-};
-
-struct slave {
-	struct net_device *dev; /* first - useful for panic debug */
-	struct bonding *bond; /* our master */
-	int    delay;
-	/* all three in jiffies */
-	unsigned long last_link_up;
-	unsigned long last_rx;
-	unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS];
-	s8     link;    /* one of BOND_LINK_XXXX */
-	s8     new_link;
-	u8     backup:1,   /* indicates backup slave. Value corresponds with
-			      BOND_STATE_ACTIVE and BOND_STATE_BACKUP */
-	       inactive:1, /* indicates inactive slave */
-	       should_notify:1; /* indicateds whether the state changed */
-	u8     duplex;
-	u32    original_mtu;
-	u32    link_failure_count;
-	u32    speed;
-	u16    queue_id;
-	u8     perm_hwaddr[ETH_ALEN];
-	struct ad_slave_info *ad_info;
-	struct tlb_slave_info tlb_info;
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	struct netpoll *np;
-#endif
-	struct kobject kobj;
-	struct rtnl_link_stats64 slave_stats;
-};
-
-struct bond_up_slave {
-	unsigned int	count;
-	struct rcu_head rcu;
-	struct slave	*arr[0];
-};
-
-/*
- * Link pseudo-state only used internally by monitors
- */
-#define BOND_LINK_NOCHANGE -1
-
-/*
- * Here are the locking policies for the two bonding locks:
- * Get rcu_read_lock when reading or RTNL when writing slave list.
- */
-struct bonding {
-	struct   net_device *dev; /* first - useful for panic debug */
-	struct   slave __rcu *curr_active_slave;
-	struct   slave __rcu *current_arp_slave;
-	struct   slave __rcu *primary_slave;
-	struct   bond_up_slave __rcu *slave_arr; /* Array of usable slaves */
-	bool     force_primary;
-	s32      slave_cnt; /* never change this value outside the attach/detach wrappers */
-	int     (*recv_probe)(const struct sk_buff *, struct bonding *,
-			      struct slave *);
-	/* mode_lock is used for mode-specific locking needs, currently used by:
-	 * 3ad mode (4) - protect against running bond_3ad_unbind_slave() and
-	 *                bond_3ad_state_machine_handler() concurrently and also
-	 *                the access to the state machine shared variables.
-	 * TLB mode (5) - to sync the use and modifications of its hash table
-	 * ALB mode (6) - to sync the use and modifications of its hash table
-	 */
-	spinlock_t mode_lock;
-	u8	 send_peer_notif;
-	u8       igmp_retrans;
-#ifdef CONFIG_PROC_FS
-	struct   proc_dir_entry *proc_entry;
-	char     proc_file_name[IFNAMSIZ];
-#endif /* CONFIG_PROC_FS */
-	struct   list_head bond_list;
-	u32      rr_tx_counter;
-	struct   ad_bond_info ad_info;
-	struct   alb_bond_info alb_info;
-	struct   bond_params params;
-	struct   workqueue_struct *wq;
-	struct   delayed_work mii_work;
-	struct   delayed_work arp_work;
-	struct   delayed_work alb_work;
-	struct   delayed_work ad_work;
-	struct   delayed_work mcast_work;
-	struct   delayed_work slave_arr_work;
-#ifdef CONFIG_DEBUG_FS
-	/* debugging support via debugfs */
-	struct	 dentry *debug_dir;
-#endif /* CONFIG_DEBUG_FS */
-	struct rtnl_link_stats64 bond_stats;
-};
-
-#define bond_slave_get_rcu(dev) \
-	((struct slave *) rcu_dereference(dev->rx_handler_data))
-
-#define bond_slave_get_rtnl(dev) \
-	((struct slave *) rtnl_dereference(dev->rx_handler_data))
-
-struct bond_vlan_tag {
-	__be16		vlan_proto;
-	unsigned short	vlan_id;
-};
-
-/**
- * Returns NULL if the net_device does not belong to any of the bond's slaves
- *
- * Caller must hold bond lock for read
- */
-static inline struct slave *bond_get_slave_by_dev(struct bonding *bond,
-						  struct net_device *slave_dev)
-{
-	return netdev_lower_dev_get_private(bond->dev, slave_dev);
-}
-
-static inline struct bonding *bond_get_bond_by_slave(struct slave *slave)
-{
-	return slave->bond;
-}
-
-static inline bool bond_should_override_tx_queue(struct bonding *bond)
-{
-	return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP ||
-	       BOND_MODE(bond) == BOND_MODE_ROUNDROBIN;
-}
-
-static inline bool bond_is_lb(const struct bonding *bond)
-{
-	return BOND_MODE(bond) == BOND_MODE_TLB ||
-	       BOND_MODE(bond) == BOND_MODE_ALB;
-}
-
-static inline bool bond_is_nondyn_tlb(const struct bonding *bond)
-{
-	return (BOND_MODE(bond) == BOND_MODE_TLB)  &&
-	       (bond->params.tlb_dynamic_lb == 0);
-}
-
-static inline bool bond_mode_uses_xmit_hash(const struct bonding *bond)
-{
-	return (BOND_MODE(bond) == BOND_MODE_8023AD ||
-		BOND_MODE(bond) == BOND_MODE_XOR ||
-		bond_is_nondyn_tlb(bond));
-}
-
-static inline bool bond_mode_uses_arp(int mode)
-{
-	return mode != BOND_MODE_8023AD && mode != BOND_MODE_TLB &&
-	       mode != BOND_MODE_ALB;
-}
-
-static inline bool bond_mode_uses_primary(int mode)
-{
-	return mode == BOND_MODE_ACTIVEBACKUP || mode == BOND_MODE_TLB ||
-	       mode == BOND_MODE_ALB;
-}
-
-static inline bool bond_uses_primary(struct bonding *bond)
-{
-	return bond_mode_uses_primary(BOND_MODE(bond));
-}
-
-static inline bool bond_slave_is_up(struct slave *slave)
-{
-	return netif_running(slave->dev) && netif_carrier_ok(slave->dev);
-}
-
-static inline void bond_set_active_slave(struct slave *slave)
-{
-	if (slave->backup) {
-		slave->backup = 0;
-		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
-	}
-}
-
-static inline void bond_set_backup_slave(struct slave *slave)
-{
-	if (!slave->backup) {
-		slave->backup = 1;
-		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
-	}
-}
-
-static inline void bond_set_slave_state(struct slave *slave,
-					int slave_state, bool notify)
-{
-	if (slave->backup == slave_state)
-		return;
-
-	slave->backup = slave_state;
-	if (notify) {
-		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
-		slave->should_notify = 0;
-	} else {
-		if (slave->should_notify)
-			slave->should_notify = 0;
-		else
-			slave->should_notify = 1;
-	}
-}
-
-static inline void bond_slave_state_change(struct bonding *bond)
-{
-	struct list_head *iter;
-	struct slave *tmp;
-
-	bond_for_each_slave(bond, tmp, iter) {
-		if (tmp->link == BOND_LINK_UP)
-			bond_set_active_slave(tmp);
-		else if (tmp->link == BOND_LINK_DOWN)
-			bond_set_backup_slave(tmp);
-	}
-}
-
-static inline void bond_slave_state_notify(struct bonding *bond)
-{
-	struct list_head *iter;
-	struct slave *tmp;
-
-	bond_for_each_slave(bond, tmp, iter) {
-		if (tmp->should_notify) {
-			rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_ATOMIC);
-			tmp->should_notify = 0;
-		}
-	}
-}
-
-static inline int bond_slave_state(struct slave *slave)
-{
-	return slave->backup;
-}
-
-static inline bool bond_is_active_slave(struct slave *slave)
-{
-	return !bond_slave_state(slave);
-}
-
-static inline bool bond_slave_can_tx(struct slave *slave)
-{
-	return bond_slave_is_up(slave) && slave->link == BOND_LINK_UP &&
-	       bond_is_active_slave(slave);
-}
-
-#define BOND_PRI_RESELECT_ALWAYS	0
-#define BOND_PRI_RESELECT_BETTER	1
-#define BOND_PRI_RESELECT_FAILURE	2
-
-#define BOND_FOM_NONE			0
-#define BOND_FOM_ACTIVE			1
-#define BOND_FOM_FOLLOW			2
-
-#define BOND_ARP_TARGETS_ANY		0
-#define BOND_ARP_TARGETS_ALL		1
-
-#define BOND_ARP_VALIDATE_NONE		0
-#define BOND_ARP_VALIDATE_ACTIVE	(1 << BOND_STATE_ACTIVE)
-#define BOND_ARP_VALIDATE_BACKUP	(1 << BOND_STATE_BACKUP)
-#define BOND_ARP_VALIDATE_ALL		(BOND_ARP_VALIDATE_ACTIVE | \
-					 BOND_ARP_VALIDATE_BACKUP)
-#define BOND_ARP_FILTER			(BOND_ARP_VALIDATE_ALL + 1)
-#define BOND_ARP_FILTER_ACTIVE		(BOND_ARP_VALIDATE_ACTIVE | \
-					 BOND_ARP_FILTER)
-#define BOND_ARP_FILTER_BACKUP		(BOND_ARP_VALIDATE_BACKUP | \
-					 BOND_ARP_FILTER)
-
-#define BOND_SLAVE_NOTIFY_NOW		true
-#define BOND_SLAVE_NOTIFY_LATER		false
-
-static inline int slave_do_arp_validate(struct bonding *bond,
-					struct slave *slave)
-{
-	return bond->params.arp_validate & (1 << bond_slave_state(slave));
-}
-
-static inline int slave_do_arp_validate_only(struct bonding *bond)
-{
-	return bond->params.arp_validate & BOND_ARP_FILTER;
-}
-
-static inline int bond_is_ip_target_ok(__be32 addr)
-{
-	return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr);
-}
-
-/* Get the oldest arp which we've received on this slave for bond's
- * arp_targets.
- */
-static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond,
-						       struct slave *slave)
-{
-	int i = 1;
-	unsigned long ret = slave->target_last_arp_rx[0];
-
-	for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++)
-		if (time_before(slave->target_last_arp_rx[i], ret))
-			ret = slave->target_last_arp_rx[i];
-
-	return ret;
-}
-
-static inline unsigned long slave_last_rx(struct bonding *bond,
-					struct slave *slave)
-{
-	if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL)
-		return slave_oldest_target_arp_rx(bond, slave);
-
-	return slave->last_rx;
-}
-
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static inline void bond_netpoll_send_skb(const struct slave *slave,
-					 struct sk_buff *skb)
-{
-	struct netpoll *np = slave->np;
-
-	if (np)
-		netpoll_send_skb(np, skb);
-}
-#else
-static inline void bond_netpoll_send_skb(const struct slave *slave,
-					 struct sk_buff *skb)
-{
-}
-#endif
-
-static inline void bond_set_slave_inactive_flags(struct slave *slave,
-						 bool notify)
-{
-	if (!bond_is_lb(slave->bond))
-		bond_set_slave_state(slave, BOND_STATE_BACKUP, notify);
-	if (!slave->bond->params.all_slaves_active)
-		slave->inactive = 1;
-}
-
-static inline void bond_set_slave_active_flags(struct slave *slave,
-					       bool notify)
-{
-	bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify);
-	slave->inactive = 0;
-}
-
-static inline bool bond_is_slave_inactive(struct slave *slave)
-{
-	return slave->inactive;
-}
-
-static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local)
-{
-	struct in_device *in_dev;
-	__be32 addr = 0;
-
-	rcu_read_lock();
-	in_dev = __in_dev_get_rcu(dev);
-
-	if (in_dev)
-		addr = inet_confirm_addr(dev_net(dev), in_dev, dst, local,
-					 RT_SCOPE_HOST);
-	rcu_read_unlock();
-	return addr;
-}
-
-struct bond_net {
-	struct net		*net;	/* Associated network namespace */
-	struct list_head	dev_list;
-#ifdef CONFIG_PROC_FS
-	struct proc_dir_entry	*proc_dir;
-#endif
-	struct class_attribute	class_attr_bonding_masters;
-};
-
-int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave);
-void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev);
-int bond_create(struct net *net, const char *name);
-int bond_create_sysfs(struct bond_net *net);
-void bond_destroy_sysfs(struct bond_net *net);
-void bond_prepare_sysfs_group(struct bonding *bond);
-int bond_sysfs_slave_add(struct slave *slave);
-void bond_sysfs_slave_del(struct slave *slave);
-int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev);
-int bond_release(struct net_device *bond_dev, struct net_device *slave_dev);
-u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb);
-void bond_select_active_slave(struct bonding *bond);
-void bond_change_active_slave(struct bonding *bond, struct slave *new_active);
-void bond_create_debugfs(void);
-void bond_destroy_debugfs(void);
-void bond_debug_register(struct bonding *bond);
-void bond_debug_unregister(struct bonding *bond);
-void bond_debug_reregister(struct bonding *bond);
-const char *bond_mode_name(int mode);
-void bond_setup(struct net_device *bond_dev);
-unsigned int bond_get_num_tx_queues(void);
-int bond_netlink_init(void);
-void bond_netlink_fini(void);
-struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
-const char *bond_slave_link_status(s8 link);
-struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev,
-					      struct net_device *end_dev,
-					      int level);
-int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave);
-void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay);
-
-#ifdef CONFIG_PROC_FS
-void bond_create_proc_entry(struct bonding *bond);
-void bond_remove_proc_entry(struct bonding *bond);
-void bond_create_proc_dir(struct bond_net *bn);
-void bond_destroy_proc_dir(struct bond_net *bn);
-#else
-static inline void bond_create_proc_entry(struct bonding *bond)
-{
-}
-
-static inline void bond_remove_proc_entry(struct bonding *bond)
-{
-}
-
-static inline void bond_create_proc_dir(struct bond_net *bn)
-{
-}
-
-static inline void bond_destroy_proc_dir(struct bond_net *bn)
-{
-}
-#endif
-
-static inline struct slave *bond_slave_has_mac(struct bonding *bond,
-					       const u8 *mac)
-{
-	struct list_head *iter;
-	struct slave *tmp;
-
-	bond_for_each_slave(bond, tmp, iter)
-		if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr))
-			return tmp;
-
-	return NULL;
-}
-
-/* Caller must hold rcu_read_lock() for read */
-static inline struct slave *bond_slave_has_mac_rcu(struct bonding *bond,
-					       const u8 *mac)
-{
-	struct list_head *iter;
-	struct slave *tmp;
-
-	bond_for_each_slave_rcu(bond, tmp, iter)
-		if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr))
-			return tmp;
-
-	return NULL;
-}
-
-/* Caller must hold rcu_read_lock() for read */
-static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac)
-{
-	struct list_head *iter;
-	struct slave *tmp;
-	struct netdev_hw_addr *ha;
-
-	bond_for_each_slave_rcu(bond, tmp, iter)
-		if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr))
-			return true;
-
-	if (netdev_uc_empty(bond->dev))
-		return false;
-
-	netdev_for_each_uc_addr(ha, bond->dev)
-		if (ether_addr_equal_64bits(mac, ha->addr))
-			return true;
-
-	return false;
-}
-
-/* Check if the ip is present in arp ip list, or first free slot if ip == 0
- * Returns -1 if not found, index if found
- */
-static inline int bond_get_targets_ip(__be32 *targets, __be32 ip)
-{
-	int i;
-
-	for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
-		if (targets[i] == ip)
-			return i;
-		else if (targets[i] == 0)
-			break;
-
-	return -1;
-}
-
-/* exported from bond_main.c */
-extern int bond_net_id;
-extern const struct bond_parm_tbl bond_lacp_tbl[];
-extern const struct bond_parm_tbl xmit_hashtype_tbl[];
-extern const struct bond_parm_tbl arp_validate_tbl[];
-extern const struct bond_parm_tbl arp_all_targets_tbl[];
-extern const struct bond_parm_tbl fail_over_mac_tbl[];
-extern const struct bond_parm_tbl pri_reselect_tbl[];
-extern struct bond_parm_tbl ad_select_tbl[];
-
-/* exported from bond_netlink.c */
-extern struct rtnl_link_ops bond_link_ops;
-
-static inline void bond_tx_drop(struct net_device *dev, struct sk_buff *skb)
-{
-	atomic_long_inc(&dev->tx_dropped);
-	dev_kfree_skb_any(skb);
-}
-
-#endif /* _LINUX_BONDING_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index a9c117fdf77..d13d36abe55 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -61,6 +61,7 @@
 #include <net/neighbour.h>
 #include <net/netevent.h>
 #include <net/addrconf.h>
+#include <net/bonding.h>
 #include <asm/uaccess.h>
 
 #include "cxgb4.h"
@@ -71,8 +72,6 @@
 #include "cxgb4_debugfs.h"
 #include "l2t.h"
 
-#include <../drivers/net/bonding/bonding.h>
-
 #ifdef DRV_VERSION
 #undef DRV_VERSION
 #endif
diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h
new file mode 100644
index 00000000000..e01d903633e
--- /dev/null
+++ b/include/net/bond_3ad.h
@@ -0,0 +1,283 @@
+/*
+ * Copyright(c) 1999 - 2004 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ *
+ * The full GNU General Public License is included in this distribution in the
+ * file called LICENSE.
+ *
+ */
+
+#ifndef _NET_BOND_3AD_H
+#define _NET_BOND_3AD_H
+
+#include <asm/byteorder.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/if_ether.h>
+
+/* General definitions */
+#define PKT_TYPE_LACPDU         cpu_to_be16(ETH_P_SLOW)
+#define AD_TIMER_INTERVAL       100 /*msec*/
+
+#define MULTICAST_LACPDU_ADDR    {0x01, 0x80, 0xC2, 0x00, 0x00, 0x02}
+
+#define AD_LACP_SLOW 0
+#define AD_LACP_FAST 1
+
+typedef struct mac_addr {
+	u8 mac_addr_value[ETH_ALEN];
+} __packed mac_addr_t;
+
+enum {
+	BOND_AD_STABLE = 0,
+	BOND_AD_BANDWIDTH = 1,
+	BOND_AD_COUNT = 2,
+};
+
+/* rx machine states(43.4.11 in the 802.3ad standard) */
+typedef enum {
+	AD_RX_DUMMY,
+	AD_RX_INITIALIZE,	/* rx Machine */
+	AD_RX_PORT_DISABLED,	/* rx Machine */
+	AD_RX_LACP_DISABLED,	/* rx Machine */
+	AD_RX_EXPIRED,		/* rx Machine */
+	AD_RX_DEFAULTED,	/* rx Machine */
+	AD_RX_CURRENT		/* rx Machine */
+} rx_states_t;
+
+/* periodic machine states(43.4.12 in the 802.3ad standard) */
+typedef enum {
+	AD_PERIODIC_DUMMY,
+	AD_NO_PERIODIC,		/* periodic machine */
+	AD_FAST_PERIODIC,	/* periodic machine */
+	AD_SLOW_PERIODIC,	/* periodic machine */
+	AD_PERIODIC_TX		/* periodic machine */
+} periodic_states_t;
+
+/* mux machine states(43.4.13 in the 802.3ad standard) */
+typedef enum {
+	AD_MUX_DUMMY,
+	AD_MUX_DETACHED,	/* mux machine */
+	AD_MUX_WAITING,		/* mux machine */
+	AD_MUX_ATTACHED,	/* mux machine */
+	AD_MUX_COLLECTING_DISTRIBUTING	/* mux machine */
+} mux_states_t;
+
+/* tx machine states(43.4.15 in the 802.3ad standard) */
+typedef enum {
+	AD_TX_DUMMY,
+	AD_TRANSMIT		/* tx Machine */
+} tx_states_t;
+
+/* rx indication types */
+typedef enum {
+	AD_TYPE_LACPDU = 1,	/* type lacpdu */
+	AD_TYPE_MARKER		/* type marker */
+} pdu_type_t;
+
+/* rx marker indication types */
+typedef enum {
+	AD_MARKER_INFORMATION_SUBTYPE = 1,	/* marker imformation subtype */
+	AD_MARKER_RESPONSE_SUBTYPE		/* marker response subtype */
+} bond_marker_subtype_t;
+
+/* timers types(43.4.9 in the 802.3ad standard) */
+typedef enum {
+	AD_CURRENT_WHILE_TIMER,
+	AD_ACTOR_CHURN_TIMER,
+	AD_PERIODIC_TIMER,
+	AD_PARTNER_CHURN_TIMER,
+	AD_WAIT_WHILE_TIMER
+} ad_timers_t;
+
+#pragma pack(1)
+
+/* Link Aggregation Control Protocol(LACP) data unit structure(43.4.2.2 in the 802.3ad standard) */
+typedef struct lacpdu {
+	u8 subtype;		/* = LACP(= 0x01) */
+	u8 version_number;
+	u8 tlv_type_actor_info;	/* = actor information(type/length/value) */
+	u8 actor_information_length;	/* = 20 */
+	__be16 actor_system_priority;
+	struct mac_addr actor_system;
+	__be16 actor_key;
+	__be16 actor_port_priority;
+	__be16 actor_port;
+	u8 actor_state;
+	u8 reserved_3_1[3];		/* = 0 */
+	u8 tlv_type_partner_info;	/* = partner information */
+	u8 partner_information_length;	/* = 20 */
+	__be16 partner_system_priority;
+	struct mac_addr partner_system;
+	__be16 partner_key;
+	__be16 partner_port_priority;
+	__be16 partner_port;
+	u8 partner_state;
+	u8 reserved_3_2[3];		/* = 0 */
+	u8 tlv_type_collector_info;	/* = collector information */
+	u8 collector_information_length;/* = 16 */
+	__be16 collector_max_delay;
+	u8 reserved_12[12];
+	u8 tlv_type_terminator;		/* = terminator */
+	u8 terminator_length;		/* = 0 */
+	u8 reserved_50[50];		/* = 0 */
+} __packed lacpdu_t;
+
+typedef struct lacpdu_header {
+	struct ethhdr hdr;
+	struct lacpdu lacpdu;
+} __packed lacpdu_header_t;
+
+/* Marker Protocol Data Unit(PDU) structure(43.5.3.2 in the 802.3ad standard) */
+typedef struct bond_marker {
+	u8 subtype;		/* = 0x02  (marker PDU) */
+	u8 version_number;	/* = 0x01 */
+	u8 tlv_type;		/* = 0x01  (marker information) */
+	/* = 0x02  (marker response information) */
+	u8 marker_length;	/* = 0x16 */
+	u16 requester_port;	/* The number assigned to the port by the requester */
+	struct mac_addr requester_system;	/* The requester's system id */
+	u32 requester_transaction_id;		/* The transaction id allocated by the requester, */
+	u16 pad;		/* = 0 */
+	u8 tlv_type_terminator;	/* = 0x00 */
+	u8 terminator_length;	/* = 0x00 */
+	u8 reserved_90[90];	/* = 0 */
+} __packed bond_marker_t;
+
+typedef struct bond_marker_header {
+	struct ethhdr hdr;
+	struct bond_marker marker;
+} __packed bond_marker_header_t;
+
+#pragma pack()
+
+struct slave;
+struct bonding;
+struct ad_info;
+struct port;
+
+#ifdef __ia64__
+#pragma pack(8)
+#endif
+
+/* aggregator structure(43.4.5 in the 802.3ad standard) */
+typedef struct aggregator {
+	struct mac_addr aggregator_mac_address;
+	u16 aggregator_identifier;
+	bool is_individual;
+	u16 actor_admin_aggregator_key;
+	u16 actor_oper_aggregator_key;
+	struct mac_addr partner_system;
+	u16 partner_system_priority;
+	u16 partner_oper_aggregator_key;
+	u16 receive_state;	/* BOOLEAN */
+	u16 transmit_state;	/* BOOLEAN */
+	struct port *lag_ports;
+	/* ****** PRIVATE PARAMETERS ****** */
+	struct slave *slave;	/* pointer to the bond slave that this aggregator belongs to */
+	u16 is_active;		/* BOOLEAN. Indicates if this aggregator is active */
+	u16 num_of_ports;
+} aggregator_t;
+
+struct port_params {
+	struct mac_addr system;
+	u16 system_priority;
+	u16 key;
+	u16 port_number;
+	u16 port_priority;
+	u16 port_state;
+};
+
+/* port structure(43.4.6 in the 802.3ad standard) */
+typedef struct port {
+	u16 actor_port_number;
+	u16 actor_port_priority;
+	struct mac_addr actor_system;	/* This parameter is added here although it is not specified in the standard, just for simplification */
+	u16 actor_system_priority;	/* This parameter is added here although it is not specified in the standard, just for simplification */
+	u16 actor_port_aggregator_identifier;
+	bool ntt;
+	u16 actor_admin_port_key;
+	u16 actor_oper_port_key;
+	u8 actor_admin_port_state;
+	u8 actor_oper_port_state;
+
+	struct port_params partner_admin;
+	struct port_params partner_oper;
+
+	bool is_enabled;
+
+	/* ****** PRIVATE PARAMETERS ****** */
+	u16 sm_vars;		/* all state machines variables for this port */
+	rx_states_t sm_rx_state;	/* state machine rx state */
+	u16 sm_rx_timer_counter;	/* state machine rx timer counter */
+	periodic_states_t sm_periodic_state;	/* state machine periodic state */
+	u16 sm_periodic_timer_counter;	/* state machine periodic timer counter */
+	mux_states_t sm_mux_state;	/* state machine mux state */
+	u16 sm_mux_timer_counter;	/* state machine mux timer counter */
+	tx_states_t sm_tx_state;	/* state machine tx state */
+	u16 sm_tx_timer_counter;	/* state machine tx timer counter(allways on - enter to transmit state 3 time per second) */
+	struct slave *slave;		/* pointer to the bond slave that this port belongs to */
+	struct aggregator *aggregator;	/* pointer to an aggregator that this port related to */
+	struct port *next_port_in_aggregator;	/* Next port on the linked list of the parent aggregator */
+	u32 transaction_id;		/* continuous number for identification of Marker PDU's; */
+	struct lacpdu lacpdu;		/* the lacpdu that will be sent for this port */
+} port_t;
+
+/* system structure */
+struct ad_system {
+	u16 sys_priority;
+	struct mac_addr sys_mac_addr;
+};
+
+#ifdef __ia64__
+#pragma pack()
+#endif
+
+/* ========== AD Exported structures to the main bonding code ========== */
+#define BOND_AD_INFO(bond)   ((bond)->ad_info)
+#define SLAVE_AD_INFO(slave) ((slave)->ad_info)
+
+struct ad_bond_info {
+	struct ad_system system;	/* 802.3ad system structure */
+	u32 agg_select_timer;		/* Timer to select aggregator after all adapter's hand shakes */
+	u16 aggregator_identifier;
+};
+
+struct ad_slave_info {
+	struct aggregator aggregator;	/* 802.3ad aggregator structure */
+	struct port port;		/* 802.3ad port structure */
+	u16 id;
+};
+
+/* ========== AD Exported functions to the main bonding code ========== */
+void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution);
+void bond_3ad_bind_slave(struct slave *slave);
+void bond_3ad_unbind_slave(struct slave *slave);
+void bond_3ad_state_machine_handler(struct work_struct *);
+void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout);
+void bond_3ad_adapter_speed_changed(struct slave *slave);
+void bond_3ad_adapter_duplex_changed(struct slave *slave);
+void bond_3ad_handle_link_change(struct slave *slave, char link);
+int  bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info);
+int  __bond_3ad_get_active_agg_info(struct bonding *bond,
+				    struct ad_info *ad_info);
+int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev);
+int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
+			 struct slave *slave);
+int bond_3ad_set_carrier(struct bonding *bond);
+void bond_3ad_update_lacp_rate(struct bonding *bond);
+#endif /* _NET_BOND_3AD_H */
+
diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h
new file mode 100644
index 00000000000..313a8d3b306
--- /dev/null
+++ b/include/net/bond_alb.h
@@ -0,0 +1,181 @@
+/*
+ * Copyright(c) 1999 - 2004 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in the
+ * file called LICENSE.
+ *
+ */
+
+#ifndef _NET_BOND_ALB_H
+#define _NET_BOND_ALB_H
+
+#include <linux/if_ether.h>
+
+struct bonding;
+struct slave;
+
+#define BOND_ALB_INFO(bond)   ((bond)->alb_info)
+#define SLAVE_TLB_INFO(slave) ((slave)->tlb_info)
+
+#define ALB_TIMER_TICKS_PER_SEC	    10	/* should be a divisor of HZ */
+#define BOND_TLB_REBALANCE_INTERVAL 10	/* In seconds, periodic re-balancing.
+					 * Used for division - never set
+					 * to zero !!!
+					 */
+#define BOND_ALB_DEFAULT_LP_INTERVAL 1
+#define BOND_ALB_LP_INTERVAL(bond) (bond->params.lp_interval)	/* In seconds, periodic send of
+								 * learning packets to the switch
+								 */
+
+#define BOND_TLB_REBALANCE_TICKS (BOND_TLB_REBALANCE_INTERVAL \
+				  * ALB_TIMER_TICKS_PER_SEC)
+
+#define BOND_ALB_LP_TICKS(bond) (BOND_ALB_LP_INTERVAL(bond) \
+			   * ALB_TIMER_TICKS_PER_SEC)
+
+#define TLB_HASH_TABLE_SIZE 256	/* The size of the clients hash table.
+				 * Note that this value MUST NOT be smaller
+				 * because the key hash table is BYTE wide !
+				 */
+
+
+#define TLB_NULL_INDEX		0xffffffff
+
+/* rlb defs */
+#define RLB_HASH_TABLE_SIZE	256
+#define RLB_NULL_INDEX		0xffffffff
+#define RLB_UPDATE_DELAY	(2*ALB_TIMER_TICKS_PER_SEC) /* 2 seconds */
+#define RLB_ARP_BURST_SIZE	2
+#define RLB_UPDATE_RETRY	3 /* 3-ticks - must be smaller than the rlb
+				   * rebalance interval (5 min).
+				   */
+/* RLB_PROMISC_TIMEOUT = 10 sec equals the time that the current slave is
+ * promiscuous after failover
+ */
+#define RLB_PROMISC_TIMEOUT	(10*ALB_TIMER_TICKS_PER_SEC)
+
+
+struct tlb_client_info {
+	struct slave *tx_slave;	/* A pointer to slave used for transmiting
+				 * packets to a Client that the Hash function
+				 * gave this entry index.
+				 */
+	u32 tx_bytes;		/* Each Client accumulates the BytesTx that
+				 * were transmitted to it, and after each
+				 * CallBack the LoadHistory is divided
+				 * by the balance interval
+				 */
+	u32 load_history;	/* This field contains the amount of Bytes
+				 * that were transmitted to this client by
+				 * the server on the previous balance
+				 * interval in Bps.
+				 */
+	u32 next;		/* The next Hash table entry index, assigned
+				 * to use the same adapter for transmit.
+				 */
+	u32 prev;		/* The previous Hash table entry index,
+				 * assigned to use the same
+				 */
+};
+
+/* -------------------------------------------------------------------------
+ * struct rlb_client_info contains all info related to a specific rx client
+ * connection. This is the Clients Hash Table entry struct.
+ * Note that this is not a proper hash table; if a new client's IP address
+ * hash collides with an existing client entry, the old entry is replaced.
+ *
+ * There is a linked list (linked by the used_next and used_prev members)
+ * linking all the used entries of the hash table. This allows updating
+ * all the clients without walking over all the unused elements of the table.
+ *
+ * There are also linked lists of entries with identical hash(ip_src). These
+ * allow cleaning up the table from ip_src<->mac_src associations that have
+ * become outdated and would cause sending out invalid ARP updates to the
+ * network. These are linked by the (src_next and src_prev members).
+ * -------------------------------------------------------------------------
+ */
+struct rlb_client_info {
+	__be32 ip_src;		/* the server IP address */
+	__be32 ip_dst;		/* the client IP address */
+	u8  mac_src[ETH_ALEN];	/* the server MAC address */
+	u8  mac_dst[ETH_ALEN];	/* the client MAC address */
+
+	/* list of used hash table entries, starting at rx_hashtbl_used_head */
+	u32 used_next;
+	u32 used_prev;
+
+	/* ip_src based hashing */
+	u32 src_next;	/* next entry with same hash(ip_src) */
+	u32 src_prev;	/* prev entry with same hash(ip_src) */
+	u32 src_first;	/* first entry with hash(ip_src) == this entry's index */
+
+	u8  assigned;		/* checking whether this entry is assigned */
+	u8  ntt;		/* flag - need to transmit client info */
+	struct slave *slave;	/* the slave assigned to this client */
+	unsigned short vlan_id;	/* VLAN tag associated with IP address */
+};
+
+struct tlb_slave_info {
+	u32 head;	/* Index to the head of the bi-directional clients
+			 * hash table entries list. The entries in the list
+			 * are the entries that were assigned to use this
+			 * slave for transmit.
+			 */
+	u32 load;	/* Each slave sums the loadHistory of all clients
+			 * assigned to it
+			 */
+};
+
+struct alb_bond_info {
+	struct tlb_client_info	*tx_hashtbl; /* Dynamically allocated */
+	u32			unbalanced_load;
+	int			tx_rebalance_counter;
+	int			lp_counter;
+	/* -------- rlb parameters -------- */
+	int rlb_enabled;
+	struct rlb_client_info	*rx_hashtbl;	/* Receive hash table */
+	u32			rx_hashtbl_used_head;
+	u8			rx_ntt;	/* flag - need to transmit
+					 * to all rx clients
+					 */
+	struct slave		*rx_slave;/* last slave to xmit from */
+	u8			primary_is_promisc;	   /* boolean */
+	u32			rlb_promisc_timeout_counter;/* counts primary
+							     * promiscuity time
+							     */
+	u32			rlb_update_delay_counter;
+	u32			rlb_update_retry_counter;/* counter of retries
+							  * of client update
+							  */
+	u8			rlb_rebalance;	/* flag - indicates that the
+						 * rx traffic should be
+						 * rebalanced
+						 */
+};
+
+int bond_alb_initialize(struct bonding *bond, int rlb_enabled);
+void bond_alb_deinitialize(struct bonding *bond);
+int bond_alb_init_slave(struct bonding *bond, struct slave *slave);
+void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave);
+void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char link);
+void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave);
+int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev);
+int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev);
+void bond_alb_monitor(struct work_struct *);
+int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr);
+void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id);
+#endif /* _NET_BOND_ALB_H */
+
diff --git a/include/net/bond_options.h b/include/net/bond_options.h
new file mode 100644
index 00000000000..ea6546d2c94
--- /dev/null
+++ b/include/net/bond_options.h
@@ -0,0 +1,130 @@
+/*
+ * drivers/net/bond/bond_options.h - bonding options
+ * Copyright (c) 2013 Nikolay Aleksandrov <nikolay@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _NET_BOND_OPTIONS_H
+#define _NET_BOND_OPTIONS_H
+
+#define BOND_OPT_MAX_NAMELEN 32
+#define BOND_OPT_VALID(opt) ((opt) < BOND_OPT_LAST)
+#define BOND_MODE_ALL_EX(x) (~(x))
+
+/* Option flags:
+ * BOND_OPTFLAG_NOSLAVES - check if the bond device is empty before setting
+ * BOND_OPTFLAG_IFDOWN - check if the bond device is down before setting
+ * BOND_OPTFLAG_RAWVAL - the option parses the value itself
+ */
+enum {
+	BOND_OPTFLAG_NOSLAVES	= BIT(0),
+	BOND_OPTFLAG_IFDOWN	= BIT(1),
+	BOND_OPTFLAG_RAWVAL	= BIT(2)
+};
+
+/* Value type flags:
+ * BOND_VALFLAG_DEFAULT - mark the value as default
+ * BOND_VALFLAG_(MIN|MAX) - mark the value as min/max
+ */
+enum {
+	BOND_VALFLAG_DEFAULT	= BIT(0),
+	BOND_VALFLAG_MIN	= BIT(1),
+	BOND_VALFLAG_MAX	= BIT(2)
+};
+
+/* Option IDs, their bit positions correspond to their IDs */
+enum {
+	BOND_OPT_MODE,
+	BOND_OPT_PACKETS_PER_SLAVE,
+	BOND_OPT_XMIT_HASH,
+	BOND_OPT_ARP_VALIDATE,
+	BOND_OPT_ARP_ALL_TARGETS,
+	BOND_OPT_FAIL_OVER_MAC,
+	BOND_OPT_ARP_INTERVAL,
+	BOND_OPT_ARP_TARGETS,
+	BOND_OPT_DOWNDELAY,
+	BOND_OPT_UPDELAY,
+	BOND_OPT_LACP_RATE,
+	BOND_OPT_MINLINKS,
+	BOND_OPT_AD_SELECT,
+	BOND_OPT_NUM_PEER_NOTIF,
+	BOND_OPT_MIIMON,
+	BOND_OPT_PRIMARY,
+	BOND_OPT_PRIMARY_RESELECT,
+	BOND_OPT_USE_CARRIER,
+	BOND_OPT_ACTIVE_SLAVE,
+	BOND_OPT_QUEUE_ID,
+	BOND_OPT_ALL_SLAVES_ACTIVE,
+	BOND_OPT_RESEND_IGMP,
+	BOND_OPT_LP_INTERVAL,
+	BOND_OPT_SLAVES,
+	BOND_OPT_TLB_DYNAMIC_LB,
+	BOND_OPT_LAST
+};
+
+/* This structure is used for storing option values and for passing option
+ * values when changing an option. The logic when used as an arg is as follows:
+ * - if string != NULL -> parse it, if the opt is RAW type then return it, else
+ *   return the parse result
+ * - if string == NULL -> parse value
+ */
+struct bond_opt_value {
+	char *string;
+	u64 value;
+	u32 flags;
+};
+
+struct bonding;
+
+struct bond_option {
+	int id;
+	const char *name;
+	const char *desc;
+	u32 flags;
+
+	/* unsuppmodes is used to denote modes in which the option isn't
+	 * supported.
+	 */
+	unsigned long unsuppmodes;
+	/* supported values which this option can have, can be a subset of
+	 * BOND_OPTVAL_RANGE's value range
+	 */
+	const struct bond_opt_value *values;
+
+	int (*set)(struct bonding *bond, const struct bond_opt_value *val);
+};
+
+int __bond_opt_set(struct bonding *bond, unsigned int option,
+		   struct bond_opt_value *val);
+int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf);
+
+const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt,
+					    struct bond_opt_value *val);
+const struct bond_option *bond_opt_get(unsigned int option);
+const struct bond_option *bond_opt_get_by_name(const char *name);
+const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val);
+
+/* This helper is used to initialize a bond_opt_value structure for parameter
+ * passing. There should be either a valid string or value, but not both.
+ * When value is ULLONG_MAX then string will be used.
+ */
+static inline void __bond_opt_init(struct bond_opt_value *optval,
+				   char *string, u64 value)
+{
+	memset(optval, 0, sizeof(*optval));
+	optval->value = ULLONG_MAX;
+	if (value == ULLONG_MAX)
+		optval->string = string;
+	else
+		optval->value = value;
+}
+#define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value)
+#define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX)
+
+void bond_option_arp_ip_targets_clear(struct bonding *bond);
+
+#endif /* _NET_BOND_OPTIONS_H */
diff --git a/include/net/bonding.h b/include/net/bonding.h
new file mode 100644
index 00000000000..983a94b86b9
--- /dev/null
+++ b/include/net/bonding.h
@@ -0,0 +1,654 @@
+/*
+ * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'.
+ *
+ * Portions are (c) Copyright 1995 Simon "Guru Aleph-Null" Janes
+ * NCM: Network and Communications Management, Inc.
+ *
+ * BUT, I'm the one who modified it for ethernet, so:
+ * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov
+ *
+ *	This software may be used and distributed according to the terms
+ *	of the GNU Public License, incorporated herein by reference.
+ *
+ */
+
+#ifndef _NET_BONDING_H
+#define _NET_BONDING_H
+
+#include <linux/timer.h>
+#include <linux/proc_fs.h>
+#include <linux/if_bonding.h>
+#include <linux/cpumask.h>
+#include <linux/in6.h>
+#include <linux/netpoll.h>
+#include <linux/inetdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/reciprocal_div.h>
+#include <linux/if_link.h>
+
+#include <net/bond_3ad.h>
+#include <net/bond_alb.h>
+#include <net/bond_options.h>
+
+#define DRV_VERSION	"3.7.1"
+#define DRV_RELDATE	"April 27, 2011"
+#define DRV_NAME	"bonding"
+#define DRV_DESCRIPTION	"Ethernet Channel Bonding Driver"
+
+#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n"
+
+#define BOND_MAX_ARP_TARGETS	16
+
+#define BOND_DEFAULT_MIIMON	100
+
+/*
+ * Less bad way to call ioctl from within the kernel; this needs to be
+ * done some other way to get the call out of interrupt context.
+ * Needs "ioctl" variable to be supplied by calling context.
+ */
+#define IOCTL(dev, arg, cmd) ({		\
+	int res = 0;			\
+	mm_segment_t fs = get_fs();	\
+	set_fs(get_ds());		\
+	res = ioctl(dev, arg, cmd);	\
+	set_fs(fs);			\
+	res; })
+
+#define BOND_MODE(bond) ((bond)->params.mode)
+
+/* slave list primitives */
+#define bond_slave_list(bond) (&(bond)->dev->adj_list.lower)
+
+#define bond_has_slaves(bond) !list_empty(bond_slave_list(bond))
+
+/* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */
+#define bond_first_slave(bond) \
+	(bond_has_slaves(bond) ? \
+		netdev_adjacent_get_private(bond_slave_list(bond)->next) : \
+		NULL)
+#define bond_last_slave(bond) \
+	(bond_has_slaves(bond) ? \
+		netdev_adjacent_get_private(bond_slave_list(bond)->prev) : \
+		NULL)
+
+/* Caller must have rcu_read_lock */
+#define bond_first_slave_rcu(bond) \
+	netdev_lower_get_first_private_rcu(bond->dev)
+
+#define bond_is_first_slave(bond, pos) (pos == bond_first_slave(bond))
+#define bond_is_last_slave(bond, pos) (pos == bond_last_slave(bond))
+
+/**
+ * bond_for_each_slave - iterate over all slaves
+ * @bond:	the bond holding this list
+ * @pos:	current slave
+ * @iter:	list_head * iterator
+ *
+ * Caller must hold RTNL
+ */
+#define bond_for_each_slave(bond, pos, iter) \
+	netdev_for_each_lower_private((bond)->dev, pos, iter)
+
+/* Caller must have rcu_read_lock */
+#define bond_for_each_slave_rcu(bond, pos, iter) \
+	netdev_for_each_lower_private_rcu((bond)->dev, pos, iter)
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+extern atomic_t netpoll_block_tx;
+
+static inline void block_netpoll_tx(void)
+{
+	atomic_inc(&netpoll_block_tx);
+}
+
+static inline void unblock_netpoll_tx(void)
+{
+	atomic_dec(&netpoll_block_tx);
+}
+
+static inline int is_netpoll_tx_blocked(struct net_device *dev)
+{
+	if (unlikely(netpoll_tx_running(dev)))
+		return atomic_read(&netpoll_block_tx);
+	return 0;
+}
+#else
+#define block_netpoll_tx()
+#define unblock_netpoll_tx()
+#define is_netpoll_tx_blocked(dev) (0)
+#endif
+
+struct bond_params {
+	int mode;
+	int xmit_policy;
+	int miimon;
+	u8 num_peer_notif;
+	int arp_interval;
+	int arp_validate;
+	int arp_all_targets;
+	int use_carrier;
+	int fail_over_mac;
+	int updelay;
+	int downdelay;
+	int lacp_fast;
+	unsigned int min_links;
+	int ad_select;
+	char primary[IFNAMSIZ];
+	int primary_reselect;
+	__be32 arp_targets[BOND_MAX_ARP_TARGETS];
+	int tx_queues;
+	int all_slaves_active;
+	int resend_igmp;
+	int lp_interval;
+	int packets_per_slave;
+	int tlb_dynamic_lb;
+	struct reciprocal_value reciprocal_packets_per_slave;
+};
+
+struct bond_parm_tbl {
+	char *modename;
+	int mode;
+};
+
+struct slave {
+	struct net_device *dev; /* first - useful for panic debug */
+	struct bonding *bond; /* our master */
+	int    delay;
+	/* all three in jiffies */
+	unsigned long last_link_up;
+	unsigned long last_rx;
+	unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS];
+	s8     link;    /* one of BOND_LINK_XXXX */
+	s8     new_link;
+	u8     backup:1,   /* indicates backup slave. Value corresponds with
+			      BOND_STATE_ACTIVE and BOND_STATE_BACKUP */
+	       inactive:1, /* indicates inactive slave */
+	       should_notify:1; /* indicateds whether the state changed */
+	u8     duplex;
+	u32    original_mtu;
+	u32    link_failure_count;
+	u32    speed;
+	u16    queue_id;
+	u8     perm_hwaddr[ETH_ALEN];
+	struct ad_slave_info *ad_info;
+	struct tlb_slave_info tlb_info;
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	struct netpoll *np;
+#endif
+	struct kobject kobj;
+	struct rtnl_link_stats64 slave_stats;
+};
+
+struct bond_up_slave {
+	unsigned int	count;
+	struct rcu_head rcu;
+	struct slave	*arr[0];
+};
+
+/*
+ * Link pseudo-state only used internally by monitors
+ */
+#define BOND_LINK_NOCHANGE -1
+
+/*
+ * Here are the locking policies for the two bonding locks:
+ * Get rcu_read_lock when reading or RTNL when writing slave list.
+ */
+struct bonding {
+	struct   net_device *dev; /* first - useful for panic debug */
+	struct   slave __rcu *curr_active_slave;
+	struct   slave __rcu *current_arp_slave;
+	struct   slave __rcu *primary_slave;
+	struct   bond_up_slave __rcu *slave_arr; /* Array of usable slaves */
+	bool     force_primary;
+	s32      slave_cnt; /* never change this value outside the attach/detach wrappers */
+	int     (*recv_probe)(const struct sk_buff *, struct bonding *,
+			      struct slave *);
+	/* mode_lock is used for mode-specific locking needs, currently used by:
+	 * 3ad mode (4) - protect against running bond_3ad_unbind_slave() and
+	 *                bond_3ad_state_machine_handler() concurrently and also
+	 *                the access to the state machine shared variables.
+	 * TLB mode (5) - to sync the use and modifications of its hash table
+	 * ALB mode (6) - to sync the use and modifications of its hash table
+	 */
+	spinlock_t mode_lock;
+	u8	 send_peer_notif;
+	u8       igmp_retrans;
+#ifdef CONFIG_PROC_FS
+	struct   proc_dir_entry *proc_entry;
+	char     proc_file_name[IFNAMSIZ];
+#endif /* CONFIG_PROC_FS */
+	struct   list_head bond_list;
+	u32      rr_tx_counter;
+	struct   ad_bond_info ad_info;
+	struct   alb_bond_info alb_info;
+	struct   bond_params params;
+	struct   workqueue_struct *wq;
+	struct   delayed_work mii_work;
+	struct   delayed_work arp_work;
+	struct   delayed_work alb_work;
+	struct   delayed_work ad_work;
+	struct   delayed_work mcast_work;
+	struct   delayed_work slave_arr_work;
+#ifdef CONFIG_DEBUG_FS
+	/* debugging support via debugfs */
+	struct	 dentry *debug_dir;
+#endif /* CONFIG_DEBUG_FS */
+	struct rtnl_link_stats64 bond_stats;
+};
+
+#define bond_slave_get_rcu(dev) \
+	((struct slave *) rcu_dereference(dev->rx_handler_data))
+
+#define bond_slave_get_rtnl(dev) \
+	((struct slave *) rtnl_dereference(dev->rx_handler_data))
+
+struct bond_vlan_tag {
+	__be16		vlan_proto;
+	unsigned short	vlan_id;
+};
+
+/**
+ * Returns NULL if the net_device does not belong to any of the bond's slaves
+ *
+ * Caller must hold bond lock for read
+ */
+static inline struct slave *bond_get_slave_by_dev(struct bonding *bond,
+						  struct net_device *slave_dev)
+{
+	return netdev_lower_dev_get_private(bond->dev, slave_dev);
+}
+
+static inline struct bonding *bond_get_bond_by_slave(struct slave *slave)
+{
+	return slave->bond;
+}
+
+static inline bool bond_should_override_tx_queue(struct bonding *bond)
+{
+	return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP ||
+	       BOND_MODE(bond) == BOND_MODE_ROUNDROBIN;
+}
+
+static inline bool bond_is_lb(const struct bonding *bond)
+{
+	return BOND_MODE(bond) == BOND_MODE_TLB ||
+	       BOND_MODE(bond) == BOND_MODE_ALB;
+}
+
+static inline bool bond_is_nondyn_tlb(const struct bonding *bond)
+{
+	return (BOND_MODE(bond) == BOND_MODE_TLB)  &&
+	       (bond->params.tlb_dynamic_lb == 0);
+}
+
+static inline bool bond_mode_uses_xmit_hash(const struct bonding *bond)
+{
+	return (BOND_MODE(bond) == BOND_MODE_8023AD ||
+		BOND_MODE(bond) == BOND_MODE_XOR ||
+		bond_is_nondyn_tlb(bond));
+}
+
+static inline bool bond_mode_uses_arp(int mode)
+{
+	return mode != BOND_MODE_8023AD && mode != BOND_MODE_TLB &&
+	       mode != BOND_MODE_ALB;
+}
+
+static inline bool bond_mode_uses_primary(int mode)
+{
+	return mode == BOND_MODE_ACTIVEBACKUP || mode == BOND_MODE_TLB ||
+	       mode == BOND_MODE_ALB;
+}
+
+static inline bool bond_uses_primary(struct bonding *bond)
+{
+	return bond_mode_uses_primary(BOND_MODE(bond));
+}
+
+static inline bool bond_slave_is_up(struct slave *slave)
+{
+	return netif_running(slave->dev) && netif_carrier_ok(slave->dev);
+}
+
+static inline void bond_set_active_slave(struct slave *slave)
+{
+	if (slave->backup) {
+		slave->backup = 0;
+		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
+	}
+}
+
+static inline void bond_set_backup_slave(struct slave *slave)
+{
+	if (!slave->backup) {
+		slave->backup = 1;
+		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
+	}
+}
+
+static inline void bond_set_slave_state(struct slave *slave,
+					int slave_state, bool notify)
+{
+	if (slave->backup == slave_state)
+		return;
+
+	slave->backup = slave_state;
+	if (notify) {
+		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
+		slave->should_notify = 0;
+	} else {
+		if (slave->should_notify)
+			slave->should_notify = 0;
+		else
+			slave->should_notify = 1;
+	}
+}
+
+static inline void bond_slave_state_change(struct bonding *bond)
+{
+	struct list_head *iter;
+	struct slave *tmp;
+
+	bond_for_each_slave(bond, tmp, iter) {
+		if (tmp->link == BOND_LINK_UP)
+			bond_set_active_slave(tmp);
+		else if (tmp->link == BOND_LINK_DOWN)
+			bond_set_backup_slave(tmp);
+	}
+}
+
+static inline void bond_slave_state_notify(struct bonding *bond)
+{
+	struct list_head *iter;
+	struct slave *tmp;
+
+	bond_for_each_slave(bond, tmp, iter) {
+		if (tmp->should_notify) {
+			rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_ATOMIC);
+			tmp->should_notify = 0;
+		}
+	}
+}
+
+static inline int bond_slave_state(struct slave *slave)
+{
+	return slave->backup;
+}
+
+static inline bool bond_is_active_slave(struct slave *slave)
+{
+	return !bond_slave_state(slave);
+}
+
+static inline bool bond_slave_can_tx(struct slave *slave)
+{
+	return bond_slave_is_up(slave) && slave->link == BOND_LINK_UP &&
+	       bond_is_active_slave(slave);
+}
+
+#define BOND_PRI_RESELECT_ALWAYS	0
+#define BOND_PRI_RESELECT_BETTER	1
+#define BOND_PRI_RESELECT_FAILURE	2
+
+#define BOND_FOM_NONE			0
+#define BOND_FOM_ACTIVE			1
+#define BOND_FOM_FOLLOW			2
+
+#define BOND_ARP_TARGETS_ANY		0
+#define BOND_ARP_TARGETS_ALL		1
+
+#define BOND_ARP_VALIDATE_NONE		0
+#define BOND_ARP_VALIDATE_ACTIVE	(1 << BOND_STATE_ACTIVE)
+#define BOND_ARP_VALIDATE_BACKUP	(1 << BOND_STATE_BACKUP)
+#define BOND_ARP_VALIDATE_ALL		(BOND_ARP_VALIDATE_ACTIVE | \
+					 BOND_ARP_VALIDATE_BACKUP)
+#define BOND_ARP_FILTER			(BOND_ARP_VALIDATE_ALL + 1)
+#define BOND_ARP_FILTER_ACTIVE		(BOND_ARP_VALIDATE_ACTIVE | \
+					 BOND_ARP_FILTER)
+#define BOND_ARP_FILTER_BACKUP		(BOND_ARP_VALIDATE_BACKUP | \
+					 BOND_ARP_FILTER)
+
+#define BOND_SLAVE_NOTIFY_NOW		true
+#define BOND_SLAVE_NOTIFY_LATER		false
+
+static inline int slave_do_arp_validate(struct bonding *bond,
+					struct slave *slave)
+{
+	return bond->params.arp_validate & (1 << bond_slave_state(slave));
+}
+
+static inline int slave_do_arp_validate_only(struct bonding *bond)
+{
+	return bond->params.arp_validate & BOND_ARP_FILTER;
+}
+
+static inline int bond_is_ip_target_ok(__be32 addr)
+{
+	return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr);
+}
+
+/* Get the oldest arp which we've received on this slave for bond's
+ * arp_targets.
+ */
+static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond,
+						       struct slave *slave)
+{
+	int i = 1;
+	unsigned long ret = slave->target_last_arp_rx[0];
+
+	for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++)
+		if (time_before(slave->target_last_arp_rx[i], ret))
+			ret = slave->target_last_arp_rx[i];
+
+	return ret;
+}
+
+static inline unsigned long slave_last_rx(struct bonding *bond,
+					struct slave *slave)
+{
+	if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL)
+		return slave_oldest_target_arp_rx(bond, slave);
+
+	return slave->last_rx;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static inline void bond_netpoll_send_skb(const struct slave *slave,
+					 struct sk_buff *skb)
+{
+	struct netpoll *np = slave->np;
+
+	if (np)
+		netpoll_send_skb(np, skb);
+}
+#else
+static inline void bond_netpoll_send_skb(const struct slave *slave,
+					 struct sk_buff *skb)
+{
+}
+#endif
+
+static inline void bond_set_slave_inactive_flags(struct slave *slave,
+						 bool notify)
+{
+	if (!bond_is_lb(slave->bond))
+		bond_set_slave_state(slave, BOND_STATE_BACKUP, notify);
+	if (!slave->bond->params.all_slaves_active)
+		slave->inactive = 1;
+}
+
+static inline void bond_set_slave_active_flags(struct slave *slave,
+					       bool notify)
+{
+	bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify);
+	slave->inactive = 0;
+}
+
+static inline bool bond_is_slave_inactive(struct slave *slave)
+{
+	return slave->inactive;
+}
+
+static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local)
+{
+	struct in_device *in_dev;
+	__be32 addr = 0;
+
+	rcu_read_lock();
+	in_dev = __in_dev_get_rcu(dev);
+
+	if (in_dev)
+		addr = inet_confirm_addr(dev_net(dev), in_dev, dst, local,
+					 RT_SCOPE_HOST);
+	rcu_read_unlock();
+	return addr;
+}
+
+struct bond_net {
+	struct net		*net;	/* Associated network namespace */
+	struct list_head	dev_list;
+#ifdef CONFIG_PROC_FS
+	struct proc_dir_entry	*proc_dir;
+#endif
+	struct class_attribute	class_attr_bonding_masters;
+};
+
+int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave);
+void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev);
+int bond_create(struct net *net, const char *name);
+int bond_create_sysfs(struct bond_net *net);
+void bond_destroy_sysfs(struct bond_net *net);
+void bond_prepare_sysfs_group(struct bonding *bond);
+int bond_sysfs_slave_add(struct slave *slave);
+void bond_sysfs_slave_del(struct slave *slave);
+int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev);
+int bond_release(struct net_device *bond_dev, struct net_device *slave_dev);
+u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb);
+void bond_select_active_slave(struct bonding *bond);
+void bond_change_active_slave(struct bonding *bond, struct slave *new_active);
+void bond_create_debugfs(void);
+void bond_destroy_debugfs(void);
+void bond_debug_register(struct bonding *bond);
+void bond_debug_unregister(struct bonding *bond);
+void bond_debug_reregister(struct bonding *bond);
+const char *bond_mode_name(int mode);
+void bond_setup(struct net_device *bond_dev);
+unsigned int bond_get_num_tx_queues(void);
+int bond_netlink_init(void);
+void bond_netlink_fini(void);
+struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
+const char *bond_slave_link_status(s8 link);
+struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev,
+					      struct net_device *end_dev,
+					      int level);
+int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave);
+void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay);
+
+#ifdef CONFIG_PROC_FS
+void bond_create_proc_entry(struct bonding *bond);
+void bond_remove_proc_entry(struct bonding *bond);
+void bond_create_proc_dir(struct bond_net *bn);
+void bond_destroy_proc_dir(struct bond_net *bn);
+#else
+static inline void bond_create_proc_entry(struct bonding *bond)
+{
+}
+
+static inline void bond_remove_proc_entry(struct bonding *bond)
+{
+}
+
+static inline void bond_create_proc_dir(struct bond_net *bn)
+{
+}
+
+static inline void bond_destroy_proc_dir(struct bond_net *bn)
+{
+}
+#endif
+
+static inline struct slave *bond_slave_has_mac(struct bonding *bond,
+					       const u8 *mac)
+{
+	struct list_head *iter;
+	struct slave *tmp;
+
+	bond_for_each_slave(bond, tmp, iter)
+		if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr))
+			return tmp;
+
+	return NULL;
+}
+
+/* Caller must hold rcu_read_lock() for read */
+static inline struct slave *bond_slave_has_mac_rcu(struct bonding *bond,
+					       const u8 *mac)
+{
+	struct list_head *iter;
+	struct slave *tmp;
+
+	bond_for_each_slave_rcu(bond, tmp, iter)
+		if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr))
+			return tmp;
+
+	return NULL;
+}
+
+/* Caller must hold rcu_read_lock() for read */
+static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac)
+{
+	struct list_head *iter;
+	struct slave *tmp;
+	struct netdev_hw_addr *ha;
+
+	bond_for_each_slave_rcu(bond, tmp, iter)
+		if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr))
+			return true;
+
+	if (netdev_uc_empty(bond->dev))
+		return false;
+
+	netdev_for_each_uc_addr(ha, bond->dev)
+		if (ether_addr_equal_64bits(mac, ha->addr))
+			return true;
+
+	return false;
+}
+
+/* Check if the ip is present in arp ip list, or first free slot if ip == 0
+ * Returns -1 if not found, index if found
+ */
+static inline int bond_get_targets_ip(__be32 *targets, __be32 ip)
+{
+	int i;
+
+	for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
+		if (targets[i] == ip)
+			return i;
+		else if (targets[i] == 0)
+			break;
+
+	return -1;
+}
+
+/* exported from bond_main.c */
+extern int bond_net_id;
+extern const struct bond_parm_tbl bond_lacp_tbl[];
+extern const struct bond_parm_tbl xmit_hashtype_tbl[];
+extern const struct bond_parm_tbl arp_validate_tbl[];
+extern const struct bond_parm_tbl arp_all_targets_tbl[];
+extern const struct bond_parm_tbl fail_over_mac_tbl[];
+extern const struct bond_parm_tbl pri_reselect_tbl[];
+extern struct bond_parm_tbl ad_select_tbl[];
+
+/* exported from bond_netlink.c */
+extern struct rtnl_link_ops bond_link_ops;
+
+static inline void bond_tx_drop(struct net_device *dev, struct sk_buff *skb)
+{
+	atomic_long_inc(&dev->tx_dropped);
+	dev_kfree_skb_any(skb);
+}
+
+#endif /* _NET_BONDING_H */
-- 
cgit v1.2.3-70-g09d2


From d74bcaaeb66826192c9e361cbfe8fd1ffaccf74e Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sun, 9 Nov 2014 17:00:59 +0100
Subject: ASoC: wm5102: Move ultrasonic response settings lock to the driver
 level

The wm5102 driver currently uses the snd_soc_codec mutex to protect its
ultrasonic response settings from concurrent access. This patch moves this
lock to the driver level. This will allow us to eventually remove the
snd_soc_codec mutex.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/mfd/arizona/core.h |  1 +
 sound/soc/codecs/arizona.c       |  4 ++--
 sound/soc/codecs/wm5102.c        | 16 ++++++++--------
 3 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/mfd/arizona/core.h b/include/linux/mfd/arizona/core.h
index f34723f7663..910e3aa1e96 100644
--- a/include/linux/mfd/arizona/core.h
+++ b/include/linux/mfd/arizona/core.h
@@ -141,6 +141,7 @@ struct arizona {
 
 	uint16_t dac_comp_coeff;
 	uint8_t dac_comp_enabled;
+	struct mutex dac_comp_lock;
 };
 
 int arizona_clk32k_enable(struct arizona *arizona);
diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c
index 0c05e7a7945..730636c14f2 100644
--- a/sound/soc/codecs/arizona.c
+++ b/sound/soc/codecs/arizona.c
@@ -1164,13 +1164,13 @@ static void arizona_wm5102_set_dac_comp(struct snd_soc_codec *codec,
 		{ 0x80, 0x0 },
 	};
 
-	mutex_lock(&codec->mutex);
+	mutex_lock(&arizona->dac_comp_lock);
 
 	dac_comp[1].def = arizona->dac_comp_coeff;
 	if (rate >= 176400)
 		dac_comp[2].def = arizona->dac_comp_enabled;
 
-	mutex_unlock(&codec->mutex);
+	mutex_unlock(&arizona->dac_comp_lock);
 
 	regmap_multi_reg_write(arizona->regmap,
 			       dac_comp,
diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c
index f6023496252..1f755349266 100644
--- a/sound/soc/codecs/wm5102.c
+++ b/sound/soc/codecs/wm5102.c
@@ -619,10 +619,10 @@ static int wm5102_out_comp_coeff_get(struct snd_kcontrol *kcontrol,
 	struct arizona *arizona = dev_get_drvdata(codec->dev->parent);
 	uint16_t data;
 
-	mutex_lock(&codec->mutex);
+	mutex_lock(&arizona->dac_comp_lock);
 	data = cpu_to_be16(arizona->dac_comp_coeff);
 	memcpy(ucontrol->value.bytes.data, &data, sizeof(data));
-	mutex_unlock(&codec->mutex);
+	mutex_unlock(&arizona->dac_comp_lock);
 
 	return 0;
 }
@@ -633,11 +633,11 @@ static int wm5102_out_comp_coeff_put(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct arizona *arizona = dev_get_drvdata(codec->dev->parent);
 
-	mutex_lock(&codec->mutex);
+	mutex_lock(&arizona->dac_comp_lock);
 	memcpy(&arizona->dac_comp_coeff, ucontrol->value.bytes.data,
 	       sizeof(arizona->dac_comp_coeff));
 	arizona->dac_comp_coeff = be16_to_cpu(arizona->dac_comp_coeff);
-	mutex_unlock(&codec->mutex);
+	mutex_unlock(&arizona->dac_comp_lock);
 
 	return 0;
 }
@@ -648,9 +648,9 @@ static int wm5102_out_comp_switch_get(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct arizona *arizona = dev_get_drvdata(codec->dev->parent);
 
-	mutex_lock(&codec->mutex);
+	mutex_lock(&arizona->dac_comp_lock);
 	ucontrol->value.integer.value[0] = arizona->dac_comp_enabled;
-	mutex_unlock(&codec->mutex);
+	mutex_unlock(&arizona->dac_comp_lock);
 
 	return 0;
 }
@@ -661,9 +661,9 @@ static int wm5102_out_comp_switch_put(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct arizona *arizona = dev_get_drvdata(codec->dev->parent);
 
-	mutex_lock(&codec->mutex);
+	mutex_lock(&arizona->dac_comp_lock);
 	arizona->dac_comp_enabled = ucontrol->value.integer.value[0];
-	mutex_unlock(&codec->mutex);
+	mutex_unlock(&arizona->dac_comp_lock);
 
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From bd6b87c104bae49816808fde5f55a262093e85ed Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sun, 9 Nov 2014 17:01:04 +0100
Subject: ASoC: Remove CODEC mutex

The CODEC mutex is now unused and can be removed.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  | 1 -
 sound/soc/soc-core.c | 1 -
 2 files changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 7ba7130037a..5c91b06864c 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -780,7 +780,6 @@ struct snd_soc_codec {
 	struct device *dev;
 	const struct snd_soc_codec_driver *driver;
 
-	struct mutex mutex;
 	struct list_head list;
 	struct list_head card_list;
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 4c8f8a23a0e..cc7bb7ad967 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -4362,7 +4362,6 @@ int snd_soc_register_codec(struct device *dev,
 	codec->dev = dev;
 	codec->driver = codec_drv;
 	codec->component.val_bytes = codec_drv->reg_word_size;
-	mutex_init(&codec->mutex);
 
 #ifdef CONFIG_DEBUG_FS
 	codec->component.init_debugfs = soc_init_codec_debugfs;
-- 
cgit v1.2.3-70-g09d2


From 2f35c41f58a978dfa44ffa102249d556caa99eeb Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Date: Mon, 10 Nov 2014 09:29:29 +1030
Subject: module: Replace module_ref with atomic_t refcnt

Replace module_ref per-cpu complex reference counter with
an atomic_t simple refcnt. This is for code simplification.

Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/module.h        | 16 +---------------
 include/trace/events/module.h |  2 +-
 kernel/module.c               | 39 +++++----------------------------------
 3 files changed, 7 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/include/linux/module.h b/include/linux/module.h
index 71f282a4e30..ebfb0e153c6 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -210,20 +210,6 @@ enum module_state {
 	MODULE_STATE_UNFORMED,	/* Still setting it up. */
 };
 
-/**
- * struct module_ref - per cpu module reference counts
- * @incs: number of module get on this cpu
- * @decs: number of module put on this cpu
- *
- * We force an alignment on 8 or 16 bytes, so that alloc_percpu()
- * put @incs/@decs in same cache line, with no extra memory cost,
- * since alloc_percpu() is fine grained.
- */
-struct module_ref {
-	unsigned long incs;
-	unsigned long decs;
-} __attribute((aligned(2 * sizeof(unsigned long))));
-
 struct module {
 	enum module_state state;
 
@@ -367,7 +353,7 @@ struct module {
 	/* Destruction function. */
 	void (*exit)(void);
 
-	struct module_ref __percpu *refptr;
+	atomic_t refcnt;
 #endif
 
 #ifdef CONFIG_CONSTRUCTORS
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index 7c5cbfe3fc4..81c4c183d34 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -80,7 +80,7 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
 	TP_fast_assign(
 		__entry->ip	= ip;
-		__entry->refcnt	= __this_cpu_read(mod->refptr->incs) - __this_cpu_read(mod->refptr->decs);
+		__entry->refcnt	= atomic_read(&mod->refcnt);
 		__assign_str(name, mod->name);
 	),
 
diff --git a/kernel/module.c b/kernel/module.c
index d596a306b0a..b1d485df5ac 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -631,15 +631,11 @@ EXPORT_TRACEPOINT_SYMBOL(module_get);
 /* Init the unload section of the module. */
 static int module_unload_init(struct module *mod)
 {
-	mod->refptr = alloc_percpu(struct module_ref);
-	if (!mod->refptr)
-		return -ENOMEM;
-
 	INIT_LIST_HEAD(&mod->source_list);
 	INIT_LIST_HEAD(&mod->target_list);
 
 	/* Hold reference count during initialization. */
-	raw_cpu_write(mod->refptr->incs, 1);
+	atomic_set(&mod->refcnt, 1);
 
 	return 0;
 }
@@ -721,8 +717,6 @@ static void module_unload_free(struct module *mod)
 		kfree(use);
 	}
 	mutex_unlock(&module_mutex);
-
-	free_percpu(mod->refptr);
 }
 
 #ifdef CONFIG_MODULE_FORCE_UNLOAD
@@ -772,28 +766,7 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
 
 unsigned long module_refcount(struct module *mod)
 {
-	unsigned long incs = 0, decs = 0;
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		decs += per_cpu_ptr(mod->refptr, cpu)->decs;
-	/*
-	 * ensure the incs are added up after the decs.
-	 * module_put ensures incs are visible before decs with smp_wmb.
-	 *
-	 * This 2-count scheme avoids the situation where the refcount
-	 * for CPU0 is read, then CPU0 increments the module refcount,
-	 * then CPU1 drops that refcount, then the refcount for CPU1 is
-	 * read. We would record a decrement but not its corresponding
-	 * increment so we would see a low count (disaster).
-	 *
-	 * Rare situation? But module_refcount can be preempted, and we
-	 * might be tallying up 4096+ CPUs. So it is not impossible.
-	 */
-	smp_rmb();
-	for_each_possible_cpu(cpu)
-		incs += per_cpu_ptr(mod->refptr, cpu)->incs;
-	return incs - decs;
+	return (unsigned long)atomic_read(&mod->refcnt);
 }
 EXPORT_SYMBOL(module_refcount);
 
@@ -935,7 +908,7 @@ void __module_get(struct module *module)
 {
 	if (module) {
 		preempt_disable();
-		__this_cpu_inc(module->refptr->incs);
+		atomic_inc(&module->refcnt);
 		trace_module_get(module, _RET_IP_);
 		preempt_enable();
 	}
@@ -950,7 +923,7 @@ bool try_module_get(struct module *module)
 		preempt_disable();
 
 		if (likely(module_is_live(module))) {
-			__this_cpu_inc(module->refptr->incs);
+			atomic_inc(&module->refcnt);
 			trace_module_get(module, _RET_IP_);
 		} else
 			ret = false;
@@ -965,9 +938,7 @@ void module_put(struct module *module)
 {
 	if (module) {
 		preempt_disable();
-		smp_wmb(); /* see comment in module_refcount */
-		__this_cpu_inc(module->refptr->decs);
-
+		atomic_dec(&module->refcnt);
 		trace_module_put(module, _RET_IP_);
 		preempt_enable();
 	}
-- 
cgit v1.2.3-70-g09d2


From cbd7f8d6825c6900daa9d6f1b363b592ea9ee1fa Mon Sep 17 00:00:00 2001
From: Paul Bolle <pebolle@tiscali.nl>
Date: Mon, 10 Nov 2014 09:33:29 +1030
Subject: virtio: Fix comment typo 'CONFIG_S_FAILED'

Without the VIRTIO_ prefix CONFIG_S_FAILED looks like a Kconfig macro.
So use that prefix here too.

Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/virtio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 65261a7244f..abafae78305 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -78,7 +78,7 @@ bool virtqueue_is_broken(struct virtqueue *vq);
 /**
  * virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus
- * @failed: saved value for CONFIG_S_FAILED bit (for restore)
+ * @failed: saved value for VIRTIO_CONFIG_S_FAILED bit (for restore)
  * @config_enabled: configuration change reporting enabled
  * @config_change_pending: configuration change reported while disabled
  * @config_lock: protects configuration change reporting
-- 
cgit v1.2.3-70-g09d2


From 5a10b7dbf904bfe01bb9fcc6298f7df09eed77d5 Mon Sep 17 00:00:00 2001
From: Raushaniya Maksudova <rmaksudova@parallels.com>
Date: Mon, 10 Nov 2014 09:36:29 +1030
Subject: virtio_balloon: free some memory from balloon on OOM

Excessive virtio_balloon inflation can cause invocation of OOM-killer,
when Linux is under severe memory pressure. Various mechanisms are
responsible for correct virtio_balloon memory management. Nevertheless
it is often the case that these control tools does not have enough time
to react on fast changing memory load. As a result OS runs out of memory
and invokes OOM-killer. The balancing of memory by use of the virtio
balloon should not cause the termination of processes while there are
pages in the balloon. Now there is no way for virtio balloon driver to
free some memory at the last moment before some process will be get
killed by OOM-killer.

This does not provide a security breach as balloon itself is running
inside guest OS and is working in the cooperation with the host. Thus
some improvements from guest side should be considered as normal.

To solve the problem, introduce a virtio_balloon callback which is
expected to be called from the oom notifier call chain in out_of_memory()
function. If virtio balloon could release some memory, it will make
the system to return and retry the allocation that forced the out of
memory killer to run.

Allocate virtio  feature bit for this: it is not set by default,
the the guest will not deflate virtio balloon on OOM without explicit
permission from host.

Signed-off-by: Raushaniya Maksudova <rmaksudova@parallels.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 drivers/virtio/virtio_balloon.c     | 52 +++++++++++++++++++++++++++++++++++++
 include/uapi/linux/virtio_balloon.h |  1 +
 2 files changed, 53 insertions(+)

(limited to 'include')

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index ff71fdcf334..50c5f42d7a9 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/balloon_compaction.h>
+#include <linux/oom.h>
 
 /*
  * Balloon device works in 4K page units.  So each page is pointed to by
@@ -36,6 +37,12 @@
  */
 #define VIRTIO_BALLOON_PAGES_PER_PAGE (unsigned)(PAGE_SIZE >> VIRTIO_BALLOON_PFN_SHIFT)
 #define VIRTIO_BALLOON_ARRAY_PFNS_MAX 256
+#define OOM_VBALLOON_DEFAULT_PAGES 256
+#define VIRTBALLOON_OOM_NOTIFY_PRIORITY 80
+
+static int oom_pages = OOM_VBALLOON_DEFAULT_PAGES;
+module_param(oom_pages, int, S_IRUSR | S_IWUSR);
+MODULE_PARM_DESC(oom_pages, "pages to free on OOM");
 
 struct virtio_balloon
 {
@@ -71,6 +78,9 @@ struct virtio_balloon
 	/* Memory statistics */
 	int need_stats_update;
 	struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
+
+	/* To register callback in oom notifier call chain */
+	struct notifier_block nb;
 };
 
 static struct virtio_device_id id_table[] = {
@@ -290,6 +300,38 @@ static void update_balloon_size(struct virtio_balloon *vb)
 		      &actual);
 }
 
+/*
+ * virtballoon_oom_notify - release pages when system is under severe
+ *			    memory pressure (called from out_of_memory())
+ * @self : notifier block struct
+ * @dummy: not used
+ * @parm : returned - number of freed pages
+ *
+ * The balancing of memory by use of the virtio balloon should not cause
+ * the termination of processes while there are pages in the balloon.
+ * If virtio balloon manages to release some memory, it will make the
+ * system return and retry the allocation that forced the OOM killer
+ * to run.
+ */
+static int virtballoon_oom_notify(struct notifier_block *self,
+				  unsigned long dummy, void *parm)
+{
+	struct virtio_balloon *vb;
+	unsigned long *freed;
+	unsigned num_freed_pages;
+
+	vb = container_of(self, struct virtio_balloon, nb);
+	if (!virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
+		return NOTIFY_OK;
+
+	freed = parm;
+	num_freed_pages = leak_balloon(vb, oom_pages);
+	update_balloon_size(vb);
+	*freed += num_freed_pages;
+
+	return NOTIFY_OK;
+}
+
 static int balloon(void *_vballoon)
 {
 	struct virtio_balloon *vb = _vballoon;
@@ -446,6 +488,12 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	if (err)
 		goto out_free_vb;
 
+	vb->nb.notifier_call = virtballoon_oom_notify;
+	vb->nb.priority = VIRTBALLOON_OOM_NOTIFY_PRIORITY;
+	err = register_oom_notifier(&vb->nb);
+	if (err < 0)
+		goto out_oom_notify;
+
 	vb->thread = kthread_run(balloon, vb, "vballoon");
 	if (IS_ERR(vb->thread)) {
 		err = PTR_ERR(vb->thread);
@@ -455,6 +503,8 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	return 0;
 
 out_del_vqs:
+	unregister_oom_notifier(&vb->nb);
+out_oom_notify:
 	vdev->config->del_vqs(vdev);
 out_free_vb:
 	kfree(vb);
@@ -479,6 +529,7 @@ static void virtballoon_remove(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb = vdev->priv;
 
+	unregister_oom_notifier(&vb->nb);
 	kthread_stop(vb->thread);
 	remove_common(vb);
 	kfree(vb);
@@ -518,6 +569,7 @@ static int virtballoon_restore(struct virtio_device *vdev)
 static unsigned int features[] = {
 	VIRTIO_BALLOON_F_MUST_TELL_HOST,
 	VIRTIO_BALLOON_F_STATS_VQ,
+	VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
 };
 
 static struct virtio_driver virtio_balloon_driver = {
diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
index 5e26f61b5df..be40f7059e9 100644
--- a/include/uapi/linux/virtio_balloon.h
+++ b/include/uapi/linux/virtio_balloon.h
@@ -31,6 +31,7 @@
 /* The feature bitmap for virtio balloon */
 #define VIRTIO_BALLOON_F_MUST_TELL_HOST	0 /* Tell before reclaiming pages */
 #define VIRTIO_BALLOON_F_STATS_VQ	1 /* Memory Stats virtqueue */
+#define VIRTIO_BALLOON_F_DEFLATE_ON_OOM	2 /* Deflate balloon on OOM */
 
 /* Size of a PFN in the balloon interface. */
 #define VIRTIO_BALLOON_PFN_SHIFT 12
-- 
cgit v1.2.3-70-g09d2


From ddcecf6b6ae7b91c8735e52f50cd403ee9cbe298 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 10 Nov 2014 17:24:26 +0100
Subject: ALSA: Fix invalid kerneldoc markers

They are no real kerneldoc comments, so drop such markers.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/uapi/sound/hdspm.h   | 12 +++++------
 sound/pci/emu10k1/emu10k1x.c |  2 +-
 sound/pci/lx6464es/lx_defs.h |  2 +-
 sound/pci/rme9652/hdspm.c    | 48 ++++++++++++++++++++++----------------------
 4 files changed, 32 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/uapi/sound/hdspm.h b/include/uapi/sound/hdspm.h
index d956c3593f6..b357f1a5e29 100644
--- a/include/uapi/sound/hdspm.h
+++ b/include/uapi/sound/hdspm.h
@@ -74,14 +74,14 @@ struct hdspm_config {
 #define SNDRV_HDSPM_IOCTL_GET_CONFIG \
 	_IOR('H', 0x41, struct hdspm_config)
 
-/**
+/*
  * If there's a TCO (TimeCode Option) board installed,
  * there are further options and status data available.
  * The hdspm_ltc structure contains the current SMPTE
  * timecode and some status information and can be
  * obtained via SNDRV_HDSPM_IOCTL_GET_LTC or in the
  * hdspm_status struct.
- **/
+ */
 
 enum hdspm_ltc_format {
 	format_invalid,
@@ -113,11 +113,11 @@ struct hdspm_ltc {
 
 #define SNDRV_HDSPM_IOCTL_GET_LTC _IOR('H', 0x46, struct hdspm_ltc)
 
-/**
+/*
  * The status data reflects the device's current state
  * as determined by the card's configuration and
  * connection status.
- **/
+ */
 
 enum hdspm_sync {
 	hdspm_sync_no_lock = 0,
@@ -171,9 +171,9 @@ struct hdspm_status {
 #define SNDRV_HDSPM_IOCTL_GET_STATUS \
 	_IOR('H', 0x47, struct hdspm_status)
 
-/**
+/*
  * Get information about the card and its add-ons.
- **/
+ */
 
 #define HDSPM_ADDON_TCO 1
 
diff --git a/sound/pci/emu10k1/emu10k1x.c b/sound/pci/emu10k1/emu10k1x.c
index e223de1408c..15933f92f63 100644
--- a/sound/pci/emu10k1/emu10k1x.c
+++ b/sound/pci/emu10k1/emu10k1x.c
@@ -180,7 +180,7 @@ MODULE_PARM_DESC(enable, "Enable the EMU10K1X soundcard.");
 
 /* From 0x50 - 0x5f, last samples captured */
 
-/**
+/*
  * The hardware has 3 channels for playback and 1 for capture.
  *  - channel 0 is the front channel
  *  - channel 1 is the rear channel
diff --git a/sound/pci/lx6464es/lx_defs.h b/sound/pci/lx6464es/lx_defs.h
index 49d36bdd512..469bcc685ed 100644
--- a/sound/pci/lx6464es/lx_defs.h
+++ b/sound/pci/lx6464es/lx_defs.h
@@ -175,7 +175,7 @@ enum buffer_flags {
 	BF_ZERO		= 0x00,	/* no flags (init).*/
 };
 
-/**
+/*
 *	Stream Flags definitions
 */
 enum stream_flags {
diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index e09348c156d..3342705a571 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -2201,10 +2201,10 @@ static inline int hdspm_get_pll_freq(struct hdspm *hdspm)
 	return rate;
 }
 
-/**
+/*
  * Calculate the real sample rate from the
  * current DDS value.
- **/
+ */
 static int hdspm_get_system_sample_rate(struct hdspm *hdspm)
 {
 	unsigned int rate;
@@ -2270,9 +2270,9 @@ static int snd_hdspm_put_system_sample_rate(struct snd_kcontrol *kcontrol,
 }
 
 
-/**
+/*
  * Returns the WordClock sample rate class for the given card.
- **/
+ */
 static int hdspm_get_wc_sample_rate(struct hdspm *hdspm)
 {
 	int status;
@@ -2295,9 +2295,9 @@ static int hdspm_get_wc_sample_rate(struct hdspm *hdspm)
 }
 
 
-/**
+/*
  * Returns the TCO sample rate class for the given card.
- **/
+ */
 static int hdspm_get_tco_sample_rate(struct hdspm *hdspm)
 {
 	int status;
@@ -2321,9 +2321,9 @@ static int hdspm_get_tco_sample_rate(struct hdspm *hdspm)
 }
 
 
-/**
+/*
  * Returns the SYNC_IN sample rate class for the given card.
- **/
+ */
 static int hdspm_get_sync_in_sample_rate(struct hdspm *hdspm)
 {
 	int status;
@@ -2343,9 +2343,9 @@ static int hdspm_get_sync_in_sample_rate(struct hdspm *hdspm)
 	return 0;
 }
 
-/**
+/*
  * Returns the AES sample rate class for the given card.
- **/
+ */
 static int hdspm_get_aes_sample_rate(struct hdspm *hdspm, int index)
 {
 	int timecode;
@@ -2361,10 +2361,10 @@ static int hdspm_get_aes_sample_rate(struct hdspm *hdspm, int index)
 	return 0;
 }
 
-/**
+/*
  * Returns the sample rate class for input source <idx> for
  * 'new style' cards like the AIO and RayDAT.
- **/
+ */
 static int hdspm_get_s1_sample_rate(struct hdspm *hdspm, unsigned int idx)
 {
 	int status = hdspm_read(hdspm, HDSPM_RD_STATUS_2);
@@ -2512,10 +2512,10 @@ static int snd_hdspm_get_autosync_sample_rate(struct snd_kcontrol *kcontrol,
 }
 
 
-/**
+/*
  * Returns the system clock mode for the given card.
  * @returns 0 - master, 1 - slave
- **/
+ */
 static int hdspm_system_clock_mode(struct hdspm *hdspm)
 {
 	switch (hdspm->io_type) {
@@ -2534,10 +2534,10 @@ static int hdspm_system_clock_mode(struct hdspm *hdspm)
 }
 
 
-/**
+/*
  * Sets the system clock mode.
  * @param mode 0 - master, 1 - slave
- **/
+ */
 static void hdspm_set_system_clock_mode(struct hdspm *hdspm, int mode)
 {
 	hdspm_set_toggle_setting(hdspm,
@@ -2692,11 +2692,11 @@ static int snd_hdspm_put_clock_source(struct snd_kcontrol *kcontrol,
 }
 
 
-/**
+/*
  * Returns the current preferred sync reference setting.
  * The semantics of the return value are depending on the
  * card, please see the comments for clarification.
- **/
+ */
 static int hdspm_pref_sync_ref(struct hdspm * hdspm)
 {
 	switch (hdspm->io_type) {
@@ -2795,11 +2795,11 @@ static int hdspm_pref_sync_ref(struct hdspm * hdspm)
 }
 
 
-/**
+/*
  * Set the preferred sync reference to <pref>. The semantics
  * of <pref> are depending on the card type, see the comments
  * for clarification.
- **/
+ */
 static int hdspm_set_pref_sync_ref(struct hdspm * hdspm, int pref)
 {
 	int p = 0;
@@ -4101,9 +4101,9 @@ static int snd_hdspm_get_sync_check(struct snd_kcontrol *kcontrol,
 
 
 
-/**
+/*
  * TCO controls
- **/
+ */
 static void hdspm_tco_write(struct hdspm *hdspm)
 {
 	unsigned int tc[4] = { 0, 0, 0, 0};
@@ -5403,7 +5403,7 @@ static irqreturn_t snd_hdspm_interrupt(int irq, void *dev_id)
 			HDSPM_midi2IRQPending | HDSPM_midi3IRQPending);
 
 	/* now = get_cycles(); */
-	/**
+	/*
 	 *   LAT_2..LAT_0 period  counter (win)  counter (mac)
 	 *          6       4096   ~256053425     ~514672358
 	 *          5       2048   ~128024983     ~257373821
@@ -5412,7 +5412,7 @@ static irqreturn_t snd_hdspm_interrupt(int irq, void *dev_id)
 	 *          2        256    ~16003039      ~32260176
 	 *          1        128     ~7998738      ~16194507
 	 *          0         64     ~3998231       ~8191558
-	 **/
+	 */
 	/*
 	  dev_info(hdspm->card->dev, "snd_hdspm_interrupt %llu @ %llx\n",
 	   now-hdspm->last_interrupt, status & 0xFFC0);
-- 
cgit v1.2.3-70-g09d2


From 2fbbc96d16009276153fd33823616877dcca30d8 Mon Sep 17 00:00:00 2001
From: Gabriel FERNANDEZ <gabriel.fernandez@st.com>
Date: Tue, 4 Nov 2014 11:51:18 +0100
Subject: phy: Add PHY header file for DT x Driver defines

This provides the shared header file which will be reference from both
PHY driver and its associated Device Tree node(s).

Signed-off-by: Gabriel Fernandez <gabriel.fernandez@linaro.org>
---
 include/dt-bindings/phy/phy.h | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
 create mode 100644 include/dt-bindings/phy/phy.h

(limited to 'include')

diff --git a/include/dt-bindings/phy/phy.h b/include/dt-bindings/phy/phy.h
new file mode 100644
index 00000000000..e8c6a3f04b8
--- /dev/null
+++ b/include/dt-bindings/phy/phy.h
@@ -0,0 +1,18 @@
+/*
+ *
+ * This header provides constants for the phy framework
+ *
+ * Copyright (C) 2014 STMicroelectronics
+ * Author: Gabriel Fernandez <gabriel.fernandez@st.com>
+ * License terms:  GNU General Public License (GPL), version 2
+ */
+
+#ifndef _DT_BINDINGS_PHY
+#define _DT_BINDINGS_PHY
+
+#define PHY_TYPE_SATA		1
+#define PHY_TYPE_PCIE		2
+#define PHY_TYPE_USB2		3
+#define PHY_TYPE_USB3		4
+
+#endif /* _DT_BINDINGS_PHY */
-- 
cgit v1.2.3-70-g09d2


From 7041bc997db6a29af74499938987160bbe6654ef Mon Sep 17 00:00:00 2001
From: Prabhakar Lad <prabhakar.csengg@gmail.com>
Date: Wed, 22 Oct 2014 18:42:01 -0300
Subject: [media] media: davinci: vpbe: add support for VIDIOC_CREATE_BUFS

this patch adds support for vidioc_create_bufs. Along side
remove unneeded member numbuffers.

Signed-off-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/platform/davinci/vpbe_display.c | 10 +++++++---
 include/media/davinci/vpbe_display.h          |  2 --
 2 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/media/platform/davinci/vpbe_display.c b/drivers/media/platform/davinci/vpbe_display.c
index 3b607498bb4..78b9ffebc94 100644
--- a/drivers/media/platform/davinci/vpbe_display.c
+++ b/drivers/media/platform/davinci/vpbe_display.c
@@ -244,12 +244,15 @@ vpbe_buffer_queue_setup(struct vb2_queue *vq, const struct v4l2_format *fmt,
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "vpbe_buffer_setup\n");
 
+	if (fmt && fmt->fmt.pix.sizeimage < layer->pix_fmt.sizeimage)
+		return -EINVAL;
+
 	/* Store number of buffers allocated in numbuffer member */
-	if (*nbuffers < VPBE_DEFAULT_NUM_BUFS)
-		*nbuffers = layer->numbuffers = VPBE_DEFAULT_NUM_BUFS;
+	if (vq->num_buffers + *nbuffers < VPBE_DEFAULT_NUM_BUFS)
+		*nbuffers = VPBE_DEFAULT_NUM_BUFS - vq->num_buffers;
 
 	*nplanes = 1;
-	sizes[0] = layer->pix_fmt.sizeimage;
+	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : layer->pix_fmt.sizeimage;
 	alloc_ctxs[0] = layer->alloc_ctx;
 
 	return 0;
@@ -1241,6 +1244,7 @@ static const struct v4l2_ioctl_ops vpbe_ioctl_ops = {
 	.vidioc_try_fmt_vid_out  = vpbe_display_try_fmt,
 
 	.vidioc_reqbufs		 = vb2_ioctl_reqbufs,
+	.vidioc_create_bufs	 = vb2_ioctl_create_bufs,
 	.vidioc_querybuf	 = vb2_ioctl_querybuf,
 	.vidioc_qbuf		 = vb2_ioctl_qbuf,
 	.vidioc_dqbuf		 = vb2_ioctl_dqbuf,
diff --git a/include/media/davinci/vpbe_display.h b/include/media/davinci/vpbe_display.h
index 163a02b92c0..fa0247ad815 100644
--- a/include/media/davinci/vpbe_display.h
+++ b/include/media/davinci/vpbe_display.h
@@ -70,8 +70,6 @@ struct vpbe_disp_buffer {
 
 /* vpbe display object structure */
 struct vpbe_layer {
-	/* number of buffers in fbuffers */
-	unsigned int numbuffers;
 	/* Pointer to the vpbe_display */
 	struct vpbe_display *disp_dev;
 	/* Pointer pointing to current v4l2_buffer */
-- 
cgit v1.2.3-70-g09d2


From 15a42a9bc9ffcff4315a7154313db08c6bf9ef11 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <anton.vorontsov@linaro.org>
Date: Thu, 6 Nov 2014 14:36:41 +0000
Subject: kdb: Rename kdb_repeat_t to kdb_cmdflags_t, cmd_repeat to cmd_flags

We're about to add more options for command behaviour, so let's expand
the meaning of kdb_repeat_t.

So far we just do various renames, there should be no functional changes.

Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
---
 include/linux/kdb.h            | 6 +++---
 kernel/debug/kdb/kdb_main.c    | 6 +++---
 kernel/debug/kdb/kdb_private.h | 2 +-
 3 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index 290db1269c4..e650f79aa41 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -17,7 +17,7 @@ typedef enum {
 	KDB_REPEAT_NONE = 0,	/* Do not repeat this command */
 	KDB_REPEAT_NO_ARGS,	/* Repeat the command without arguments */
 	KDB_REPEAT_WITH_ARGS,	/* Repeat the command including its arguments */
-} kdb_repeat_t;
+} kdb_cmdflags_t;
 
 typedef int (*kdb_func_t)(int, const char **);
 
@@ -147,7 +147,7 @@ static inline const char *kdb_walk_kallsyms(loff_t *pos)
 /* Dynamic kdb shell command registration */
 extern int kdb_register(char *, kdb_func_t, char *, char *, short);
 extern int kdb_register_repeat(char *, kdb_func_t, char *, char *,
-			       short, kdb_repeat_t);
+			       short, kdb_cmdflags_t);
 extern int kdb_unregister(char *);
 #else /* ! CONFIG_KGDB_KDB */
 static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; }
@@ -156,7 +156,7 @@ static inline int kdb_register(char *cmd, kdb_func_t func, char *usage,
 			       char *help, short minlen) { return 0; }
 static inline int kdb_register_repeat(char *cmd, kdb_func_t func, char *usage,
 				      char *help, short minlen,
-				      kdb_repeat_t repeat) { return 0; }
+				      kdb_cmdflags_t flags) { return 0; }
 static inline int kdb_unregister(char *cmd) { return 0; }
 #endif	/* CONFIG_KGDB_KDB */
 enum {
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index cc02aa20566..41966b5f86b 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1008,7 +1008,7 @@ int kdb_parse(const char *cmdstr)
 		if (result && ignore_errors && result > KDB_CMD_GO)
 			result = 0;
 		KDB_STATE_CLEAR(CMD);
-		switch (tp->cmd_repeat) {
+		switch (tp->cmd_flags) {
 		case KDB_REPEAT_NONE:
 			argc = 0;
 			if (argv[0])
@@ -2646,7 +2646,7 @@ int kdb_register_repeat(char *cmd,
 			char *usage,
 			char *help,
 			short minlen,
-			kdb_repeat_t repeat)
+			kdb_cmdflags_t flags)
 {
 	int i;
 	kdbtab_t *kp;
@@ -2695,7 +2695,7 @@ int kdb_register_repeat(char *cmd,
 	kp->cmd_usage  = usage;
 	kp->cmd_help   = help;
 	kp->cmd_minlen = minlen;
-	kp->cmd_repeat = repeat;
+	kp->cmd_flags  = flags;
 
 	return 0;
 }
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index c4c46c7b26f..eaacd169395 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -174,7 +174,7 @@ typedef struct _kdbtab {
 	char    *cmd_help;		/* Help message for this command */
 	short    cmd_minlen;		/* Minimum legal # command
 					 * chars required */
-	kdb_repeat_t cmd_repeat;	/* Does command auto repeat on enter? */
+	kdb_cmdflags_t cmd_flags;	/* Command behaviour flags */
 } kdbtab_t;
 
 extern int kdb_bt(int, const char **);	/* KDB display back trace */
-- 
cgit v1.2.3-70-g09d2


From 42c884c10b775ce04f8aabe488820134625c893e Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <anton.vorontsov@linaro.org>
Date: Thu, 6 Nov 2014 14:36:42 +0000
Subject: kdb: Rename kdb_register_repeat() to kdb_register_flags()

We're about to add more options for commands behaviour, so let's give
a more generic name to the low-level kdb command registration function.

There are just various renames, no functional changes.

Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
---
 include/linux/kdb.h         | 10 +++---
 kernel/debug/kdb/kdb_bp.c   | 14 ++++----
 kernel/debug/kdb/kdb_main.c | 86 ++++++++++++++++++++++-----------------------
 kernel/trace/trace_kdb.c    |  2 +-
 4 files changed, 56 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index e650f79aa41..32d2f407981 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -146,17 +146,17 @@ static inline const char *kdb_walk_kallsyms(loff_t *pos)
 
 /* Dynamic kdb shell command registration */
 extern int kdb_register(char *, kdb_func_t, char *, char *, short);
-extern int kdb_register_repeat(char *, kdb_func_t, char *, char *,
-			       short, kdb_cmdflags_t);
+extern int kdb_register_flags(char *, kdb_func_t, char *, char *,
+			      short, kdb_cmdflags_t);
 extern int kdb_unregister(char *);
 #else /* ! CONFIG_KGDB_KDB */
 static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; }
 static inline void kdb_init(int level) {}
 static inline int kdb_register(char *cmd, kdb_func_t func, char *usage,
 			       char *help, short minlen) { return 0; }
-static inline int kdb_register_repeat(char *cmd, kdb_func_t func, char *usage,
-				      char *help, short minlen,
-				      kdb_cmdflags_t flags) { return 0; }
+static inline int kdb_register_flags(char *cmd, kdb_func_t func, char *usage,
+				     char *help, short minlen,
+				     kdb_cmdflags_t flags) { return 0; }
 static inline int kdb_unregister(char *cmd) { return 0; }
 #endif	/* CONFIG_KGDB_KDB */
 enum {
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
index b20d544f20c..59536661c7b 100644
--- a/kernel/debug/kdb/kdb_bp.c
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -531,21 +531,21 @@ void __init kdb_initbptab(void)
 	for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; i++, bp++)
 		bp->bp_free = 1;
 
-	kdb_register_repeat("bp", kdb_bp, "[<vaddr>]",
+	kdb_register_flags("bp", kdb_bp, "[<vaddr>]",
 		"Set/Display breakpoints", 0, KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("bl", kdb_bp, "[<vaddr>]",
+	kdb_register_flags("bl", kdb_bp, "[<vaddr>]",
 		"Display breakpoints", 0, KDB_REPEAT_NO_ARGS);
 	if (arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT)
-		kdb_register_repeat("bph", kdb_bp, "[<vaddr>]",
+		kdb_register_flags("bph", kdb_bp, "[<vaddr>]",
 		"[datar [length]|dataw [length]]   Set hw brk", 0, KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("bc", kdb_bc, "<bpnum>",
+	kdb_register_flags("bc", kdb_bc, "<bpnum>",
 		"Clear Breakpoint", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("be", kdb_bc, "<bpnum>",
+	kdb_register_flags("be", kdb_bc, "<bpnum>",
 		"Enable Breakpoint", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("bd", kdb_bc, "<bpnum>",
+	kdb_register_flags("bd", kdb_bc, "<bpnum>",
 		"Disable Breakpoint", 0, KDB_REPEAT_NONE);
 
-	kdb_register_repeat("ss", kdb_ss, "",
+	kdb_register_flags("ss", kdb_ss, "",
 		"Single Step", 1, KDB_REPEAT_NO_ARGS);
 	/*
 	 * Architecture dependent initialization.
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 41966b5f86b..070f1ff358d 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -2629,7 +2629,7 @@ static int kdb_grep_help(int argc, const char **argv)
 }
 
 /*
- * kdb_register_repeat - This function is used to register a kernel
+ * kdb_register_flags - This function is used to register a kernel
  * 	debugger command.
  * Inputs:
  *	cmd	Command name
@@ -2641,12 +2641,12 @@ static int kdb_grep_help(int argc, const char **argv)
  *	zero for success, one if a duplicate command.
  */
 #define kdb_command_extend 50	/* arbitrary */
-int kdb_register_repeat(char *cmd,
-			kdb_func_t func,
-			char *usage,
-			char *help,
-			short minlen,
-			kdb_cmdflags_t flags)
+int kdb_register_flags(char *cmd,
+		       kdb_func_t func,
+		       char *usage,
+		       char *help,
+		       short minlen,
+		       kdb_cmdflags_t flags)
 {
 	int i;
 	kdbtab_t *kp;
@@ -2699,13 +2699,13 @@ int kdb_register_repeat(char *cmd,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(kdb_register_repeat);
+EXPORT_SYMBOL_GPL(kdb_register_flags);
 
 
 /*
  * kdb_register - Compatibility register function for commands that do
  *	not need to specify a repeat state.  Equivalent to
- *	kdb_register_repeat with KDB_REPEAT_NONE.
+ *	kdb_register_flags with KDB_REPEAT_NONE.
  * Inputs:
  *	cmd	Command name
  *	func	Function to execute the command
@@ -2720,8 +2720,8 @@ int kdb_register(char *cmd,
 	     char *help,
 	     short minlen)
 {
-	return kdb_register_repeat(cmd, func, usage, help, minlen,
-				   KDB_REPEAT_NONE);
+	return kdb_register_flags(cmd, func, usage, help, minlen,
+				  KDB_REPEAT_NONE);
 }
 EXPORT_SYMBOL_GPL(kdb_register);
 
@@ -2763,79 +2763,79 @@ static void __init kdb_inittab(void)
 	for_each_kdbcmd(kp, i)
 		kp->cmd_name = NULL;
 
-	kdb_register_repeat("md", kdb_md, "<vaddr>",
+	kdb_register_flags("md", kdb_md, "<vaddr>",
 	  "Display Memory Contents, also mdWcN, e.g. md8c1", 1,
 			    KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("mdr", kdb_md, "<vaddr> <bytes>",
+	kdb_register_flags("mdr", kdb_md, "<vaddr> <bytes>",
 	  "Display Raw Memory", 0, KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("mdp", kdb_md, "<paddr> <bytes>",
+	kdb_register_flags("mdp", kdb_md, "<paddr> <bytes>",
 	  "Display Physical Memory", 0, KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("mds", kdb_md, "<vaddr>",
+	kdb_register_flags("mds", kdb_md, "<vaddr>",
 	  "Display Memory Symbolically", 0, KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("mm", kdb_mm, "<vaddr> <contents>",
+	kdb_register_flags("mm", kdb_mm, "<vaddr> <contents>",
 	  "Modify Memory Contents", 0, KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("go", kdb_go, "[<vaddr>]",
+	kdb_register_flags("go", kdb_go, "[<vaddr>]",
 	  "Continue Execution", 1, KDB_REPEAT_NONE);
-	kdb_register_repeat("rd", kdb_rd, "",
+	kdb_register_flags("rd", kdb_rd, "",
 	  "Display Registers", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("rm", kdb_rm, "<reg> <contents>",
+	kdb_register_flags("rm", kdb_rm, "<reg> <contents>",
 	  "Modify Registers", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("ef", kdb_ef, "<vaddr>",
+	kdb_register_flags("ef", kdb_ef, "<vaddr>",
 	  "Display exception frame", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("bt", kdb_bt, "[<vaddr>]",
+	kdb_register_flags("bt", kdb_bt, "[<vaddr>]",
 	  "Stack traceback", 1, KDB_REPEAT_NONE);
-	kdb_register_repeat("btp", kdb_bt, "<pid>",
+	kdb_register_flags("btp", kdb_bt, "<pid>",
 	  "Display stack for process <pid>", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("bta", kdb_bt, "[D|R|S|T|C|Z|E|U|I|M|A]",
+	kdb_register_flags("bta", kdb_bt, "[D|R|S|T|C|Z|E|U|I|M|A]",
 	  "Backtrace all processes matching state flag", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("btc", kdb_bt, "",
+	kdb_register_flags("btc", kdb_bt, "",
 	  "Backtrace current process on each cpu", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("btt", kdb_bt, "<vaddr>",
+	kdb_register_flags("btt", kdb_bt, "<vaddr>",
 	  "Backtrace process given its struct task address", 0,
 			    KDB_REPEAT_NONE);
-	kdb_register_repeat("env", kdb_env, "",
+	kdb_register_flags("env", kdb_env, "",
 	  "Show environment variables", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("set", kdb_set, "",
+	kdb_register_flags("set", kdb_set, "",
 	  "Set environment variables", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("help", kdb_help, "",
+	kdb_register_flags("help", kdb_help, "",
 	  "Display Help Message", 1, KDB_REPEAT_NONE);
-	kdb_register_repeat("?", kdb_help, "",
+	kdb_register_flags("?", kdb_help, "",
 	  "Display Help Message", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("cpu", kdb_cpu, "<cpunum>",
+	kdb_register_flags("cpu", kdb_cpu, "<cpunum>",
 	  "Switch to new cpu", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("kgdb", kdb_kgdb, "",
+	kdb_register_flags("kgdb", kdb_kgdb, "",
 	  "Enter kgdb mode", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("ps", kdb_ps, "[<flags>|A]",
+	kdb_register_flags("ps", kdb_ps, "[<flags>|A]",
 	  "Display active task list", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("pid", kdb_pid, "<pidnum>",
+	kdb_register_flags("pid", kdb_pid, "<pidnum>",
 	  "Switch to another task", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("reboot", kdb_reboot, "",
+	kdb_register_flags("reboot", kdb_reboot, "",
 	  "Reboot the machine immediately", 0, KDB_REPEAT_NONE);
 #if defined(CONFIG_MODULES)
-	kdb_register_repeat("lsmod", kdb_lsmod, "",
+	kdb_register_flags("lsmod", kdb_lsmod, "",
 	  "List loaded kernel modules", 0, KDB_REPEAT_NONE);
 #endif
 #if defined(CONFIG_MAGIC_SYSRQ)
-	kdb_register_repeat("sr", kdb_sr, "<key>",
+	kdb_register_flags("sr", kdb_sr, "<key>",
 	  "Magic SysRq key", 0, KDB_REPEAT_NONE);
 #endif
 #if defined(CONFIG_PRINTK)
-	kdb_register_repeat("dmesg", kdb_dmesg, "[lines]",
+	kdb_register_flags("dmesg", kdb_dmesg, "[lines]",
 	  "Display syslog buffer", 0, KDB_REPEAT_NONE);
 #endif
 	if (arch_kgdb_ops.enable_nmi) {
-		kdb_register_repeat("disable_nmi", kdb_disable_nmi, "",
+		kdb_register_flags("disable_nmi", kdb_disable_nmi, "",
 		  "Disable NMI entry to KDB", 0, KDB_REPEAT_NONE);
 	}
-	kdb_register_repeat("defcmd", kdb_defcmd, "name \"usage\" \"help\"",
+	kdb_register_flags("defcmd", kdb_defcmd, "name \"usage\" \"help\"",
 	  "Define a set of commands, down to endefcmd", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("kill", kdb_kill, "<-signal> <pid>",
+	kdb_register_flags("kill", kdb_kill, "<-signal> <pid>",
 	  "Send a signal to a process", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("summary", kdb_summary, "",
+	kdb_register_flags("summary", kdb_summary, "",
 	  "Summarize the system", 4, KDB_REPEAT_NONE);
-	kdb_register_repeat("per_cpu", kdb_per_cpu, "<sym> [<bytes>] [<cpu>]",
+	kdb_register_flags("per_cpu", kdb_per_cpu, "<sym> [<bytes>] [<cpu>]",
 	  "Display per_cpu variables", 3, KDB_REPEAT_NONE);
-	kdb_register_repeat("grephelp", kdb_grep_help, "",
+	kdb_register_flags("grephelp", kdb_grep_help, "",
 	  "Display help on | grep", 0, KDB_REPEAT_NONE);
 }
 
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index bd90e1b0608..1e3b36c7504 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -127,7 +127,7 @@ static int kdb_ftdump(int argc, const char **argv)
 
 static __init int kdb_ftrace_register(void)
 {
-	kdb_register_repeat("ftdump", kdb_ftdump, "[skip_#lines] [cpu]",
+	kdb_register_flags("ftdump", kdb_ftdump, "[skip_#lines] [cpu]",
 			    "Dump ftrace log", 0, KDB_REPEAT_NONE);
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From 04bb171e7aa99dee0c92e772e4f66f8d5c1b4081 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <anton.vorontsov@linaro.org>
Date: Thu, 6 Nov 2014 14:36:43 +0000
Subject: kdb: Use KDB_REPEAT_* values as flags

The actual values of KDB_REPEAT_* enum values and overall logic stayed
the same, but we now treat the values as flags.

This makes it possible to add other flags and combine them, plus makes
the code a lot simpler and shorter. But functionality-wise, there should
be no changes.

Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
---
 include/linux/kdb.h         |  4 ++--
 kernel/debug/kdb/kdb_main.c | 21 +++++++--------------
 2 files changed, 9 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index 32d2f407981..90aed7c31f0 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -15,8 +15,8 @@
 
 typedef enum {
 	KDB_REPEAT_NONE = 0,	/* Do not repeat this command */
-	KDB_REPEAT_NO_ARGS,	/* Repeat the command without arguments */
-	KDB_REPEAT_WITH_ARGS,	/* Repeat the command including its arguments */
+	KDB_REPEAT_NO_ARGS	= 0x1, /* Repeat the command w/o arguments */
+	KDB_REPEAT_WITH_ARGS	= 0x2, /* Repeat the command w/ its arguments */
 } kdb_cmdflags_t;
 
 typedef int (*kdb_func_t)(int, const char **);
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 070f1ff358d..cbacae24a55 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1008,20 +1008,13 @@ int kdb_parse(const char *cmdstr)
 		if (result && ignore_errors && result > KDB_CMD_GO)
 			result = 0;
 		KDB_STATE_CLEAR(CMD);
-		switch (tp->cmd_flags) {
-		case KDB_REPEAT_NONE:
-			argc = 0;
-			if (argv[0])
-				*(argv[0]) = '\0';
-			break;
-		case KDB_REPEAT_NO_ARGS:
-			argc = 1;
-			if (argv[1])
-				*(argv[1]) = '\0';
-			break;
-		case KDB_REPEAT_WITH_ARGS:
-			break;
-		}
+
+		if (tp->cmd_flags & KDB_REPEAT_WITH_ARGS)
+			return result;
+
+		argc = tp->cmd_flags & KDB_REPEAT_NO_ARGS ? 1 : 0;
+		if (argv[argc])
+			*(argv[argc]) = '\0';
 		return result;
 	}
 
-- 
cgit v1.2.3-70-g09d2


From e8ab24d9b0173ada3eeed31d7d7f982228efc2c5 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <anton.vorontsov@linaro.org>
Date: Thu, 6 Nov 2014 14:36:44 +0000
Subject: kdb: Remove KDB_REPEAT_NONE flag

Since we now treat KDB_REPEAT_* as flags, there is no need to
pass KDB_REPEAT_NONE. It's just the default behaviour when no
flags are specified.

Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
---
 include/linux/kdb.h         |  1 -
 kernel/debug/kdb/kdb_bp.c   |  6 ++---
 kernel/debug/kdb/kdb_main.c | 59 ++++++++++++++++++++++-----------------------
 kernel/trace/trace_kdb.c    |  2 +-
 4 files changed, 33 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index 90aed7c31f0..39b44b37c8d 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -14,7 +14,6 @@
  */
 
 typedef enum {
-	KDB_REPEAT_NONE = 0,	/* Do not repeat this command */
 	KDB_REPEAT_NO_ARGS	= 0x1, /* Repeat the command w/o arguments */
 	KDB_REPEAT_WITH_ARGS	= 0x2, /* Repeat the command w/ its arguments */
 } kdb_cmdflags_t;
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
index 59536661c7b..f8844fb5531 100644
--- a/kernel/debug/kdb/kdb_bp.c
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -539,11 +539,11 @@ void __init kdb_initbptab(void)
 		kdb_register_flags("bph", kdb_bp, "[<vaddr>]",
 		"[datar [length]|dataw [length]]   Set hw brk", 0, KDB_REPEAT_NO_ARGS);
 	kdb_register_flags("bc", kdb_bc, "<bpnum>",
-		"Clear Breakpoint", 0, KDB_REPEAT_NONE);
+		"Clear Breakpoint", 0, 0);
 	kdb_register_flags("be", kdb_bc, "<bpnum>",
-		"Enable Breakpoint", 0, KDB_REPEAT_NONE);
+		"Enable Breakpoint", 0, 0);
 	kdb_register_flags("bd", kdb_bc, "<bpnum>",
-		"Disable Breakpoint", 0, KDB_REPEAT_NONE);
+		"Disable Breakpoint", 0, 0);
 
 	kdb_register_flags("ss", kdb_ss, "",
 		"Single Step", 1, KDB_REPEAT_NO_ARGS);
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index cbacae24a55..538bf1dce26 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -2698,7 +2698,7 @@ EXPORT_SYMBOL_GPL(kdb_register_flags);
 /*
  * kdb_register - Compatibility register function for commands that do
  *	not need to specify a repeat state.  Equivalent to
- *	kdb_register_flags with KDB_REPEAT_NONE.
+ *	kdb_register_flags with flags set to 0.
  * Inputs:
  *	cmd	Command name
  *	func	Function to execute the command
@@ -2713,8 +2713,7 @@ int kdb_register(char *cmd,
 	     char *help,
 	     short minlen)
 {
-	return kdb_register_flags(cmd, func, usage, help, minlen,
-				  KDB_REPEAT_NONE);
+	return kdb_register_flags(cmd, func, usage, help, minlen, 0);
 }
 EXPORT_SYMBOL_GPL(kdb_register);
 
@@ -2768,68 +2767,68 @@ static void __init kdb_inittab(void)
 	kdb_register_flags("mm", kdb_mm, "<vaddr> <contents>",
 	  "Modify Memory Contents", 0, KDB_REPEAT_NO_ARGS);
 	kdb_register_flags("go", kdb_go, "[<vaddr>]",
-	  "Continue Execution", 1, KDB_REPEAT_NONE);
+	  "Continue Execution", 1, 0);
 	kdb_register_flags("rd", kdb_rd, "",
-	  "Display Registers", 0, KDB_REPEAT_NONE);
+	  "Display Registers", 0, 0);
 	kdb_register_flags("rm", kdb_rm, "<reg> <contents>",
-	  "Modify Registers", 0, KDB_REPEAT_NONE);
+	  "Modify Registers", 0, 0);
 	kdb_register_flags("ef", kdb_ef, "<vaddr>",
-	  "Display exception frame", 0, KDB_REPEAT_NONE);
+	  "Display exception frame", 0, 0);
 	kdb_register_flags("bt", kdb_bt, "[<vaddr>]",
-	  "Stack traceback", 1, KDB_REPEAT_NONE);
+	  "Stack traceback", 1, 0);
 	kdb_register_flags("btp", kdb_bt, "<pid>",
-	  "Display stack for process <pid>", 0, KDB_REPEAT_NONE);
+	  "Display stack for process <pid>", 0, 0);
 	kdb_register_flags("bta", kdb_bt, "[D|R|S|T|C|Z|E|U|I|M|A]",
-	  "Backtrace all processes matching state flag", 0, KDB_REPEAT_NONE);
+	  "Backtrace all processes matching state flag", 0, 0);
 	kdb_register_flags("btc", kdb_bt, "",
-	  "Backtrace current process on each cpu", 0, KDB_REPEAT_NONE);
+	  "Backtrace current process on each cpu", 0, 0);
 	kdb_register_flags("btt", kdb_bt, "<vaddr>",
 	  "Backtrace process given its struct task address", 0,
-			    KDB_REPEAT_NONE);
+			    0);
 	kdb_register_flags("env", kdb_env, "",
-	  "Show environment variables", 0, KDB_REPEAT_NONE);
+	  "Show environment variables", 0, 0);
 	kdb_register_flags("set", kdb_set, "",
-	  "Set environment variables", 0, KDB_REPEAT_NONE);
+	  "Set environment variables", 0, 0);
 	kdb_register_flags("help", kdb_help, "",
-	  "Display Help Message", 1, KDB_REPEAT_NONE);
+	  "Display Help Message", 1, 0);
 	kdb_register_flags("?", kdb_help, "",
-	  "Display Help Message", 0, KDB_REPEAT_NONE);
+	  "Display Help Message", 0, 0);
 	kdb_register_flags("cpu", kdb_cpu, "<cpunum>",
-	  "Switch to new cpu", 0, KDB_REPEAT_NONE);
+	  "Switch to new cpu", 0, 0);
 	kdb_register_flags("kgdb", kdb_kgdb, "",
-	  "Enter kgdb mode", 0, KDB_REPEAT_NONE);
+	  "Enter kgdb mode", 0, 0);
 	kdb_register_flags("ps", kdb_ps, "[<flags>|A]",
-	  "Display active task list", 0, KDB_REPEAT_NONE);
+	  "Display active task list", 0, 0);
 	kdb_register_flags("pid", kdb_pid, "<pidnum>",
-	  "Switch to another task", 0, KDB_REPEAT_NONE);
+	  "Switch to another task", 0, 0);
 	kdb_register_flags("reboot", kdb_reboot, "",
-	  "Reboot the machine immediately", 0, KDB_REPEAT_NONE);
+	  "Reboot the machine immediately", 0, 0);
 #if defined(CONFIG_MODULES)
 	kdb_register_flags("lsmod", kdb_lsmod, "",
-	  "List loaded kernel modules", 0, KDB_REPEAT_NONE);
+	  "List loaded kernel modules", 0, 0);
 #endif
 #if defined(CONFIG_MAGIC_SYSRQ)
 	kdb_register_flags("sr", kdb_sr, "<key>",
-	  "Magic SysRq key", 0, KDB_REPEAT_NONE);
+	  "Magic SysRq key", 0, 0);
 #endif
 #if defined(CONFIG_PRINTK)
 	kdb_register_flags("dmesg", kdb_dmesg, "[lines]",
-	  "Display syslog buffer", 0, KDB_REPEAT_NONE);
+	  "Display syslog buffer", 0, 0);
 #endif
 	if (arch_kgdb_ops.enable_nmi) {
 		kdb_register_flags("disable_nmi", kdb_disable_nmi, "",
-		  "Disable NMI entry to KDB", 0, KDB_REPEAT_NONE);
+		  "Disable NMI entry to KDB", 0, 0);
 	}
 	kdb_register_flags("defcmd", kdb_defcmd, "name \"usage\" \"help\"",
-	  "Define a set of commands, down to endefcmd", 0, KDB_REPEAT_NONE);
+	  "Define a set of commands, down to endefcmd", 0, 0);
 	kdb_register_flags("kill", kdb_kill, "<-signal> <pid>",
-	  "Send a signal to a process", 0, KDB_REPEAT_NONE);
+	  "Send a signal to a process", 0, 0);
 	kdb_register_flags("summary", kdb_summary, "",
-	  "Summarize the system", 4, KDB_REPEAT_NONE);
+	  "Summarize the system", 4, 0);
 	kdb_register_flags("per_cpu", kdb_per_cpu, "<sym> [<bytes>] [<cpu>]",
-	  "Display per_cpu variables", 3, KDB_REPEAT_NONE);
+	  "Display per_cpu variables", 3, 0);
 	kdb_register_flags("grephelp", kdb_grep_help, "",
-	  "Display help on | grep", 0, KDB_REPEAT_NONE);
+	  "Display help on | grep", 0, 0);
 }
 
 /* Execute any commands defined in kdb_cmds.  */
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index 1e3b36c7504..3da7e304359 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -128,7 +128,7 @@ static int kdb_ftdump(int argc, const char **argv)
 static __init int kdb_ftrace_register(void)
 {
 	kdb_register_flags("ftdump", kdb_ftdump, "[skip_#lines] [cpu]",
-			    "Dump ftrace log", 0, KDB_REPEAT_NONE);
+			    "Dump ftrace log", 0, 0);
 	return 0;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 9452e977ac17caf9f98a91b33d5e3c3357258c64 Mon Sep 17 00:00:00 2001
From: Daniel Thompson <daniel.thompson@linaro.org>
Date: Thu, 6 Nov 2014 14:36:45 +0000
Subject: kdb: Categorize kdb commands (similar to SysRq categorization)

This patch introduces several new flags to collect kdb commands into
groups (later allowing them to be optionally disabled).

This follows similar prior art to enable/disable magic sysrq
commands.

The commands have been categorized as follows:

Always on:  go (w/o args), env, set, help, ?, cpu (w/o args), sr,
            dmesg, disable_nmi, defcmd, summary, grephelp
Mem read:   md, mdr, mdp, mds, ef, bt (with args), per_cpu
Mem write:  mm
Reg read:   rd
Reg write:  go (with args), rm
Inspect:    bt (w/o args), btp, bta, btc, btt, ps, pid, lsmod
Flow ctrl:  bp, bl, bph, bc, be, bd, ss
Signal:     kill
Reboot:     reboot
All:        cpu, kgdb, (and all of the above), nmi_console

Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
---
 include/linux/kdb.h         |  48 +++++++++++++++++-
 kernel/debug/kdb/kdb_bp.c   |  21 +++++---
 kernel/debug/kdb/kdb_main.c | 120 ++++++++++++++++++++++++++++++++------------
 kernel/trace/trace_kdb.c    |   2 +-
 4 files changed, 148 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index 39b44b37c8d..f1fe36185c1 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -13,9 +13,53 @@
  * Copyright (C) 2009 Jason Wessel <jason.wessel@windriver.com>
  */
 
+/* Shifted versions of the command enable bits are be used if the command
+ * has no arguments (see kdb_check_flags). This allows commands, such as
+ * go, to have different permissions depending upon whether it is called
+ * with an argument.
+ */
+#define KDB_ENABLE_NO_ARGS_SHIFT 10
+
 typedef enum {
-	KDB_REPEAT_NO_ARGS	= 0x1, /* Repeat the command w/o arguments */
-	KDB_REPEAT_WITH_ARGS	= 0x2, /* Repeat the command w/ its arguments */
+	KDB_ENABLE_ALL = (1 << 0), /* Enable everything */
+	KDB_ENABLE_MEM_READ = (1 << 1),
+	KDB_ENABLE_MEM_WRITE = (1 << 2),
+	KDB_ENABLE_REG_READ = (1 << 3),
+	KDB_ENABLE_REG_WRITE = (1 << 4),
+	KDB_ENABLE_INSPECT = (1 << 5),
+	KDB_ENABLE_FLOW_CTRL = (1 << 6),
+	KDB_ENABLE_SIGNAL = (1 << 7),
+	KDB_ENABLE_REBOOT = (1 << 8),
+	/* User exposed values stop here, all remaining flags are
+	 * exclusively used to describe a commands behaviour.
+	 */
+
+	KDB_ENABLE_ALWAYS_SAFE = (1 << 9),
+	KDB_ENABLE_MASK = (1 << KDB_ENABLE_NO_ARGS_SHIFT) - 1,
+
+	KDB_ENABLE_ALL_NO_ARGS = KDB_ENABLE_ALL << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_MEM_READ_NO_ARGS = KDB_ENABLE_MEM_READ
+				      << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_MEM_WRITE_NO_ARGS = KDB_ENABLE_MEM_WRITE
+				       << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_REG_READ_NO_ARGS = KDB_ENABLE_REG_READ
+				      << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_REG_WRITE_NO_ARGS = KDB_ENABLE_REG_WRITE
+				       << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_INSPECT_NO_ARGS = KDB_ENABLE_INSPECT
+				     << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_FLOW_CTRL_NO_ARGS = KDB_ENABLE_FLOW_CTRL
+				       << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_SIGNAL_NO_ARGS = KDB_ENABLE_SIGNAL
+				    << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_REBOOT_NO_ARGS = KDB_ENABLE_REBOOT
+				    << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_ALWAYS_SAFE_NO_ARGS = KDB_ENABLE_ALWAYS_SAFE
+					 << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_MASK_NO_ARGS = KDB_ENABLE_MASK << KDB_ENABLE_NO_ARGS_SHIFT,
+
+	KDB_REPEAT_NO_ARGS = 0x40000000, /* Repeat the command w/o arguments */
+	KDB_REPEAT_WITH_ARGS = 0x80000000, /* Repeat the command with args */
 } kdb_cmdflags_t;
 
 typedef int (*kdb_func_t)(int, const char **);
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
index f8844fb5531..e1dbf4a2c69 100644
--- a/kernel/debug/kdb/kdb_bp.c
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -532,21 +532,28 @@ void __init kdb_initbptab(void)
 		bp->bp_free = 1;
 
 	kdb_register_flags("bp", kdb_bp, "[<vaddr>]",
-		"Set/Display breakpoints", 0, KDB_REPEAT_NO_ARGS);
+		"Set/Display breakpoints", 0,
+		KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS);
 	kdb_register_flags("bl", kdb_bp, "[<vaddr>]",
-		"Display breakpoints", 0, KDB_REPEAT_NO_ARGS);
+		"Display breakpoints", 0,
+		KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS);
 	if (arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT)
 		kdb_register_flags("bph", kdb_bp, "[<vaddr>]",
-		"[datar [length]|dataw [length]]   Set hw brk", 0, KDB_REPEAT_NO_ARGS);
+		"[datar [length]|dataw [length]]   Set hw brk", 0,
+		KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS);
 	kdb_register_flags("bc", kdb_bc, "<bpnum>",
-		"Clear Breakpoint", 0, 0);
+		"Clear Breakpoint", 0,
+		KDB_ENABLE_FLOW_CTRL);
 	kdb_register_flags("be", kdb_bc, "<bpnum>",
-		"Enable Breakpoint", 0, 0);
+		"Enable Breakpoint", 0,
+		KDB_ENABLE_FLOW_CTRL);
 	kdb_register_flags("bd", kdb_bc, "<bpnum>",
-		"Disable Breakpoint", 0, 0);
+		"Disable Breakpoint", 0,
+		KDB_ENABLE_FLOW_CTRL);
 
 	kdb_register_flags("ss", kdb_ss, "",
-		"Single Step", 1, KDB_REPEAT_NO_ARGS);
+		"Single Step", 1,
+		KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS);
 	/*
 	 * Architecture dependent initialization.
 	 */
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 538bf1dce26..fae1fc3962f 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -187,6 +187,26 @@ struct task_struct *kdb_curr_task(int cpu)
 	return p;
 }
 
+/*
+ * Check whether the flags of the current command and the permissions
+ * of the kdb console has allow a command to be run.
+ */
+static inline bool kdb_check_flags(kdb_cmdflags_t flags, int permissions,
+				   bool no_args)
+{
+	/* permissions comes from userspace so needs massaging slightly */
+	permissions &= KDB_ENABLE_MASK;
+	permissions |= KDB_ENABLE_ALWAYS_SAFE;
+
+	/* some commands change group when launched with no arguments */
+	if (no_args)
+		permissions |= permissions << KDB_ENABLE_NO_ARGS_SHIFT;
+
+	flags |= KDB_ENABLE_ALL;
+
+	return permissions & flags;
+}
+
 /*
  * kdbgetenv - This function will return the character string value of
  *	an environment variable.
@@ -641,8 +661,13 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0)
 		if (!s->count)
 			s->usable = 0;
 		if (s->usable)
-			kdb_register(s->name, kdb_exec_defcmd,
-				     s->usage, s->help, 0);
+			/* macros are always safe because when executed each
+			 * internal command re-enters kdb_parse() and is
+			 * safety checked individually.
+			 */
+			kdb_register_flags(s->name, kdb_exec_defcmd, s->usage,
+					   s->help, 0,
+					   KDB_ENABLE_ALWAYS_SAFE);
 		return 0;
 	}
 	if (!s->usable)
@@ -2757,78 +2782,107 @@ static void __init kdb_inittab(void)
 
 	kdb_register_flags("md", kdb_md, "<vaddr>",
 	  "Display Memory Contents, also mdWcN, e.g. md8c1", 1,
-			    KDB_REPEAT_NO_ARGS);
+	  KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS);
 	kdb_register_flags("mdr", kdb_md, "<vaddr> <bytes>",
-	  "Display Raw Memory", 0, KDB_REPEAT_NO_ARGS);
+	  "Display Raw Memory", 0,
+	  KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS);
 	kdb_register_flags("mdp", kdb_md, "<paddr> <bytes>",
-	  "Display Physical Memory", 0, KDB_REPEAT_NO_ARGS);
+	  "Display Physical Memory", 0,
+	  KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS);
 	kdb_register_flags("mds", kdb_md, "<vaddr>",
-	  "Display Memory Symbolically", 0, KDB_REPEAT_NO_ARGS);
+	  "Display Memory Symbolically", 0,
+	  KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS);
 	kdb_register_flags("mm", kdb_mm, "<vaddr> <contents>",
-	  "Modify Memory Contents", 0, KDB_REPEAT_NO_ARGS);
+	  "Modify Memory Contents", 0,
+	  KDB_ENABLE_MEM_WRITE | KDB_REPEAT_NO_ARGS);
 	kdb_register_flags("go", kdb_go, "[<vaddr>]",
-	  "Continue Execution", 1, 0);
+	  "Continue Execution", 1,
+	  KDB_ENABLE_REG_WRITE | KDB_ENABLE_ALWAYS_SAFE_NO_ARGS);
 	kdb_register_flags("rd", kdb_rd, "",
-	  "Display Registers", 0, 0);
+	  "Display Registers", 0,
+	  KDB_ENABLE_REG_READ);
 	kdb_register_flags("rm", kdb_rm, "<reg> <contents>",
-	  "Modify Registers", 0, 0);
+	  "Modify Registers", 0,
+	  KDB_ENABLE_REG_WRITE);
 	kdb_register_flags("ef", kdb_ef, "<vaddr>",
-	  "Display exception frame", 0, 0);
+	  "Display exception frame", 0,
+	  KDB_ENABLE_MEM_READ);
 	kdb_register_flags("bt", kdb_bt, "[<vaddr>]",
-	  "Stack traceback", 1, 0);
+	  "Stack traceback", 1,
+	  KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS);
 	kdb_register_flags("btp", kdb_bt, "<pid>",
-	  "Display stack for process <pid>", 0, 0);
+	  "Display stack for process <pid>", 0,
+	  KDB_ENABLE_INSPECT);
 	kdb_register_flags("bta", kdb_bt, "[D|R|S|T|C|Z|E|U|I|M|A]",
-	  "Backtrace all processes matching state flag", 0, 0);
+	  "Backtrace all processes matching state flag", 0,
+	  KDB_ENABLE_INSPECT);
 	kdb_register_flags("btc", kdb_bt, "",
-	  "Backtrace current process on each cpu", 0, 0);
+	  "Backtrace current process on each cpu", 0,
+	  KDB_ENABLE_INSPECT);
 	kdb_register_flags("btt", kdb_bt, "<vaddr>",
 	  "Backtrace process given its struct task address", 0,
-			    0);
+	  KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS);
 	kdb_register_flags("env", kdb_env, "",
-	  "Show environment variables", 0, 0);
+	  "Show environment variables", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
 	kdb_register_flags("set", kdb_set, "",
-	  "Set environment variables", 0, 0);
+	  "Set environment variables", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
 	kdb_register_flags("help", kdb_help, "",
-	  "Display Help Message", 1, 0);
+	  "Display Help Message", 1,
+	  KDB_ENABLE_ALWAYS_SAFE);
 	kdb_register_flags("?", kdb_help, "",
-	  "Display Help Message", 0, 0);
+	  "Display Help Message", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
 	kdb_register_flags("cpu", kdb_cpu, "<cpunum>",
-	  "Switch to new cpu", 0, 0);
+	  "Switch to new cpu", 0,
+	  KDB_ENABLE_ALWAYS_SAFE_NO_ARGS);
 	kdb_register_flags("kgdb", kdb_kgdb, "",
 	  "Enter kgdb mode", 0, 0);
 	kdb_register_flags("ps", kdb_ps, "[<flags>|A]",
-	  "Display active task list", 0, 0);
+	  "Display active task list", 0,
+	  KDB_ENABLE_INSPECT);
 	kdb_register_flags("pid", kdb_pid, "<pidnum>",
-	  "Switch to another task", 0, 0);
+	  "Switch to another task", 0,
+	  KDB_ENABLE_INSPECT);
 	kdb_register_flags("reboot", kdb_reboot, "",
-	  "Reboot the machine immediately", 0, 0);
+	  "Reboot the machine immediately", 0,
+	  KDB_ENABLE_REBOOT);
 #if defined(CONFIG_MODULES)
 	kdb_register_flags("lsmod", kdb_lsmod, "",
-	  "List loaded kernel modules", 0, 0);
+	  "List loaded kernel modules", 0,
+	  KDB_ENABLE_INSPECT);
 #endif
 #if defined(CONFIG_MAGIC_SYSRQ)
 	kdb_register_flags("sr", kdb_sr, "<key>",
-	  "Magic SysRq key", 0, 0);
+	  "Magic SysRq key", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
 #endif
 #if defined(CONFIG_PRINTK)
 	kdb_register_flags("dmesg", kdb_dmesg, "[lines]",
-	  "Display syslog buffer", 0, 0);
+	  "Display syslog buffer", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
 #endif
 	if (arch_kgdb_ops.enable_nmi) {
 		kdb_register_flags("disable_nmi", kdb_disable_nmi, "",
-		  "Disable NMI entry to KDB", 0, 0);
+		  "Disable NMI entry to KDB", 0,
+		  KDB_ENABLE_ALWAYS_SAFE);
 	}
 	kdb_register_flags("defcmd", kdb_defcmd, "name \"usage\" \"help\"",
-	  "Define a set of commands, down to endefcmd", 0, 0);
+	  "Define a set of commands, down to endefcmd", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
 	kdb_register_flags("kill", kdb_kill, "<-signal> <pid>",
-	  "Send a signal to a process", 0, 0);
+	  "Send a signal to a process", 0,
+	  KDB_ENABLE_SIGNAL);
 	kdb_register_flags("summary", kdb_summary, "",
-	  "Summarize the system", 4, 0);
+	  "Summarize the system", 4,
+	  KDB_ENABLE_ALWAYS_SAFE);
 	kdb_register_flags("per_cpu", kdb_per_cpu, "<sym> [<bytes>] [<cpu>]",
-	  "Display per_cpu variables", 3, 0);
+	  "Display per_cpu variables", 3,
+	  KDB_ENABLE_MEM_READ);
 	kdb_register_flags("grephelp", kdb_grep_help, "",
-	  "Display help on | grep", 0, 0);
+	  "Display help on | grep", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
 }
 
 /* Execute any commands defined in kdb_cmds.  */
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index 3da7e304359..1058f6bd839 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -128,7 +128,7 @@ static int kdb_ftdump(int argc, const char **argv)
 static __init int kdb_ftrace_register(void)
 {
 	kdb_register_flags("ftdump", kdb_ftdump, "[skip_#lines] [cpu]",
-			    "Dump ftrace log", 0, 0);
+			    "Dump ftrace log", 0, KDB_ENABLE_ALWAYS_SAFE);
 	return 0;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 420c2b1b0df84f5956036b5185cc1e11d247817d Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <anton.vorontsov@linaro.org>
Date: Thu, 6 Nov 2014 14:36:46 +0000
Subject: kdb: Add enable mask for groups of commands

Currently all kdb commands are enabled whenever kdb is deployed. This
makes it difficult to deploy kdb to help debug certain types of
systems.

Android phones provide one example; the FIQ debugger found on some
Android devices has a deliberately weak set of commands to allow the
debugger to enabled very late in the production cycle.

Certain kiosk environments offer another interesting case where an
engineer might wish to probe the system state using passive inspection
commands without providing sufficient power for a passer by to root it.

Without any restrictions, obtaining the root rights via KDB is a matter of
a few commands, and works everywhere. For example, log in as a normal
user:

cbou:~$ id
uid=1001(cbou) gid=1001(cbou) groups=1001(cbou)

Now enter KDB (for example via sysrq):

Entering kdb (current=0xffff8800065bc740, pid 920) due to Keyboard Entry
kdb> ps
23 sleeping system daemon (state M) processes suppressed,
use 'ps A' to see all.
Task Addr               Pid   Parent [*] cpu State Thread             Command
0xffff8800065bc740      920      919  1    0   R  0xffff8800065bca20 *bash

0xffff880007078000        1        0  0    0   S  0xffff8800070782e0  init
[...snip...]
0xffff8800065be3c0      918        1  0    0   S  0xffff8800065be6a0  getty
0xffff8800065b9c80      919        1  0    0   S  0xffff8800065b9f60  login
0xffff8800065bc740      920      919  1    0   R  0xffff8800065bca20 *bash

All we need is the offset of cred pointers. We can look up the offset in
the distro's kernel source, but it is unnecessary. We can just start
dumping init's task_struct, until we see the process name:

kdb> md 0xffff880007078000
0xffff880007078000 0000000000000001 ffff88000703c000   ................
0xffff880007078010 0040210000000002 0000000000000000   .....!@.........
[...snip...]
0xffff8800070782b0 ffff8800073e0580 ffff8800073e0580   ..>.......>.....
0xffff8800070782c0 0000000074696e69 0000000000000000   init............

^ Here, 'init'. Creds are just above it, so the offset is 0x02b0.

Now we set up init's creds for our non-privileged shell:

kdb> mm 0xffff8800065bc740+0x02b0 0xffff8800073e0580
0xffff8800065bc9f0 = 0xffff8800073e0580
kdb> mm 0xffff8800065bc740+0x02b8 0xffff8800073e0580
0xffff8800065bc9f8 = 0xffff8800073e0580

And thus gaining the root:

kdb> go
cbou:~$ id
uid=0(root) gid=0(root) groups=0(root)
cbou:~$ bash
root:~#

p.s. No distro enables kdb by default (although, with a nice KDB-over-KMS
feature availability, I would expect at least some would enable it), so
it's not actually some kind of a major issue.

Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
---
 include/linux/kdb.h         |  1 +
 kernel/debug/kdb/kdb_main.c | 30 +++++++++++++++++++++++++++++-
 2 files changed, 30 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index f1fe36185c1..75ae2e2631f 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -105,6 +105,7 @@ extern atomic_t kdb_event;
 #define KDB_BADLENGTH	(-19)
 #define KDB_NOBP	(-20)
 #define KDB_BADADDR	(-21)
+#define KDB_NOPERM	(-22)
 
 /*
  * kdb_diemsg
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index fae1fc3962f..fe1ac56b62e 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/ctype.h>
+#include <linux/types.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/kmsg_dump.h>
@@ -23,6 +24,7 @@
 #include <linux/vmalloc.h>
 #include <linux/atomic.h>
 #include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/kallsyms.h>
@@ -42,6 +44,12 @@
 #include <linux/slab.h>
 #include "kdb_private.h"
 
+#undef	MODULE_PARAM_PREFIX
+#define	MODULE_PARAM_PREFIX "kdb."
+
+static int kdb_cmd_enabled;
+module_param_named(cmd_enable, kdb_cmd_enabled, int, 0600);
+
 #define GREP_LEN 256
 char kdb_grep_string[GREP_LEN];
 int kdb_grepping_flag;
@@ -121,6 +129,7 @@ static kdbmsg_t kdbmsgs[] = {
 	KDBMSG(BADLENGTH, "Invalid length field"),
 	KDBMSG(NOBP, "No Breakpoint exists"),
 	KDBMSG(BADADDR, "Invalid address"),
+	KDBMSG(NOPERM, "Permission denied"),
 };
 #undef KDBMSG
 
@@ -495,6 +504,15 @@ int kdbgetaddrarg(int argc, const char **argv, int *nextarg,
 	char *cp;
 	kdb_symtab_t symtab;
 
+	/*
+	 * If the enable flags prohibit both arbitrary memory access
+	 * and flow control then there are no reasonable grounds to
+	 * provide symbol lookup.
+	 */
+	if (!kdb_check_flags(KDB_ENABLE_MEM_READ | KDB_ENABLE_FLOW_CTRL,
+			     kdb_cmd_enabled, false))
+		return KDB_NOPERM;
+
 	/*
 	 * Process arguments which follow the following syntax:
 	 *
@@ -1028,6 +1046,10 @@ int kdb_parse(const char *cmdstr)
 
 	if (i < kdb_max_commands) {
 		int result;
+
+		if (!kdb_check_flags(tp->cmd_flags, kdb_cmd_enabled, argc <= 1))
+			return KDB_NOPERM;
+
 		KDB_STATE_SET(CMD);
 		result = (*tp->cmd_func)(argc-1, (const char **)argv);
 		if (result && ignore_errors && result > KDB_CMD_GO)
@@ -1939,10 +1961,14 @@ static int kdb_rm(int argc, const char **argv)
  */
 static int kdb_sr(int argc, const char **argv)
 {
+	bool check_mask =
+	    !kdb_check_flags(KDB_ENABLE_ALL, kdb_cmd_enabled, false);
+
 	if (argc != 1)
 		return KDB_ARGCOUNT;
+
 	kdb_trap_printk++;
-	__handle_sysrq(*argv[1], false);
+	__handle_sysrq(*argv[1], check_mask);
 	kdb_trap_printk--;
 
 	return 0;
@@ -2393,6 +2419,8 @@ static int kdb_help(int argc, const char **argv)
 			return 0;
 		if (!kt->cmd_name)
 			continue;
+		if (!kdb_check_flags(kt->cmd_flags, kdb_cmd_enabled, true))
+			continue;
 		if (strlen(kt->cmd_usage) > 20)
 			space = "\n                                    ";
 		kdb_printf("%-15.15s %-20s%s%s\n", kt->cmd_name,
-- 
cgit v1.2.3-70-g09d2


From 4fd3279b48605ae3ea509b9b2c02e46aa0975930 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 24 Oct 2014 17:56:04 -0400
Subject: ftrace: Add more information to ftrace_bug() output

With the introduction of the dynamic trampolines, it is useful that if
things go wrong that ftrace_bug() produces more information about what
the current state is. This can help debug issues that may arise.

Ftrace has lots of checks to make sure that the state of the system it
touchs is exactly what it expects it to be. When it detects an abnormality
it calls ftrace_bug() and disables itself to prevent any further damage.
It is crucial that ftrace_bug() produces sufficient information that
can be used to debug the situation.

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Borislav Petkov <bp@suse.de>
Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/powerpc/kernel/ftrace.c |  2 +-
 arch/x86/kernel/ftrace.c     |  2 +-
 include/linux/ftrace.h       |  4 +++-
 kernel/trace/ftrace.c        | 38 +++++++++++++++++++++++++++++---------
 4 files changed, 34 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 390311c0f03..e66af6d265e 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -449,7 +449,7 @@ void ftrace_replace_code(int enable)
 		rec = ftrace_rec_iter_record(iter);
 		ret = __ftrace_replace_code(rec, enable);
 		if (ret) {
-			ftrace_bug(ret, rec->ip);
+			ftrace_bug(ret, rec);
 			return;
 		}
 	}
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 4cfeca6ffe1..1aea94d336c 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -583,7 +583,7 @@ void ftrace_replace_code(int enable)
 
  remove_breakpoints:
 	pr_warn("Failed on %s (%d):\n", report, count);
-	ftrace_bug(ret, rec ? rec->ip : 0);
+	ftrace_bug(ret, rec);
 	for_ftrace_rec_iter(iter) {
 		rec = ftrace_rec_iter_record(iter);
 		/*
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 06e3ca5a508..619e37cc17f 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -263,7 +263,9 @@ struct ftrace_func_command {
 int ftrace_arch_code_modify_prepare(void);
 int ftrace_arch_code_modify_post_process(void);
 
-void ftrace_bug(int err, unsigned long ip);
+struct dyn_ftrace;
+
+void ftrace_bug(int err, struct dyn_ftrace *rec);
 
 struct seq_file;
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index eab3123a1fb..4043332f672 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1738,10 +1738,13 @@ static void print_ip_ins(const char *fmt, unsigned char *p)
 		printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]);
 }
 
+static struct ftrace_ops *
+ftrace_find_tramp_ops_any(struct dyn_ftrace *rec);
+
 /**
  * ftrace_bug - report and shutdown function tracer
  * @failed: The failed type (EFAULT, EINVAL, EPERM)
- * @ip: The address that failed
+ * @rec: The record that failed
  *
  * The arch code that enables or disables the function tracing
  * can call ftrace_bug() when it has detected a problem in
@@ -1750,8 +1753,10 @@ static void print_ip_ins(const char *fmt, unsigned char *p)
  * EINVAL - if what is read at @ip is not what was expected
  * EPERM - if the problem happens on writting to the @ip address
  */
-void ftrace_bug(int failed, unsigned long ip)
+void ftrace_bug(int failed, struct dyn_ftrace *rec)
 {
+	unsigned long ip = rec ? rec->ip : 0;
+
 	switch (failed) {
 	case -EFAULT:
 		FTRACE_WARN_ON_ONCE(1);
@@ -1763,7 +1768,7 @@ void ftrace_bug(int failed, unsigned long ip)
 		pr_info("ftrace failed to modify ");
 		print_ip_sym(ip);
 		print_ip_ins(" actual: ", (unsigned char *)ip);
-		printk(KERN_CONT "\n");
+		pr_cont("\n");
 		break;
 	case -EPERM:
 		FTRACE_WARN_ON_ONCE(1);
@@ -1775,6 +1780,24 @@ void ftrace_bug(int failed, unsigned long ip)
 		pr_info("ftrace faulted on unknown error ");
 		print_ip_sym(ip);
 	}
+	if (rec) {
+		struct ftrace_ops *ops = NULL;
+
+		pr_info("ftrace record flags: %lx\n", rec->flags);
+		pr_cont(" (%ld)%s", ftrace_rec_count(rec),
+			rec->flags & FTRACE_FL_REGS ? " R" : "  ");
+		if (rec->flags & FTRACE_FL_TRAMP_EN) {
+			ops = ftrace_find_tramp_ops_any(rec);
+			if (ops)
+				pr_cont("\ttramp: %pS",
+					(void *)ops->trampoline);
+			else
+				pr_cont("\ttramp: ERROR!");
+
+		}
+		ip = ftrace_get_addr_curr(rec);
+		pr_cont(" expected tramp: %lx\n", ip);
+	}
 }
 
 static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
@@ -2097,7 +2120,7 @@ void __weak ftrace_replace_code(int enable)
 	do_for_each_ftrace_rec(pg, rec) {
 		failed = __ftrace_replace_code(rec, enable);
 		if (failed) {
-			ftrace_bug(failed, rec->ip);
+			ftrace_bug(failed, rec);
 			/* Stop processing */
 			return;
 		}
@@ -2179,17 +2202,14 @@ struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter)
 static int
 ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec)
 {
-	unsigned long ip;
 	int ret;
 
-	ip = rec->ip;
-
 	if (unlikely(ftrace_disabled))
 		return 0;
 
 	ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR);
 	if (ret) {
-		ftrace_bug(ret, ip);
+		ftrace_bug(ret, rec);
 		return 0;
 	}
 	return 1;
@@ -2633,7 +2653,7 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
 			if (ftrace_start_up && cnt) {
 				int failed = __ftrace_replace_code(p, 1);
 				if (failed)
-					ftrace_bug(failed, p->ip);
+					ftrace_bug(failed, p);
 			}
 		}
 	}
-- 
cgit v1.2.3-70-g09d2


From 2c8c56e15df3d4c2af3d656e44feb18789f75837 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 11 Nov 2014 05:54:28 -0800
Subject: net: introduce SO_INCOMING_CPU

Alternative to RPS/RFS is to use hardware support for multiple
queues.

Then split a set of million of sockets into worker threads, each
one using epoll() to manage events on its own socket pool.

Ideally, we want one thread per RX/TX queue/cpu, but we have no way to
know after accept() or connect() on which queue/cpu a socket is managed.

We normally use one cpu per RX queue (IRQ smp_affinity being properly
set), so remembering on socket structure which cpu delivered last packet
is enough to solve the problem.

After accept(), connect(), or even file descriptor passing around
processes, applications can use :

 int cpu;
 socklen_t len = sizeof(cpu);

 getsockopt(fd, SOL_SOCKET, SO_INCOMING_CPU, &cpu, &len);

And use this information to put the socket into the right silo
for optimal performance, as all networking stack should run
on the appropriate cpu, without need to send IPI (RPS/RFS).

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/alpha/include/uapi/asm/socket.h   |  2 ++
 arch/avr32/include/uapi/asm/socket.h   |  2 ++
 arch/cris/include/uapi/asm/socket.h    |  2 ++
 arch/frv/include/uapi/asm/socket.h     |  2 ++
 arch/ia64/include/uapi/asm/socket.h    |  2 ++
 arch/m32r/include/uapi/asm/socket.h    |  2 ++
 arch/mips/include/uapi/asm/socket.h    |  2 ++
 arch/mn10300/include/uapi/asm/socket.h |  2 ++
 arch/parisc/include/uapi/asm/socket.h  |  2 ++
 arch/powerpc/include/uapi/asm/socket.h |  2 ++
 arch/s390/include/uapi/asm/socket.h    |  2 ++
 arch/sparc/include/uapi/asm/socket.h   |  2 ++
 arch/xtensa/include/uapi/asm/socket.h  |  2 ++
 include/net/sock.h                     | 12 ++++++++++++
 include/uapi/asm-generic/socket.h      |  2 ++
 net/core/sock.c                        |  5 +++++
 net/ipv4/tcp_ipv4.c                    |  1 +
 net/ipv4/udp.c                         |  1 +
 net/ipv6/tcp_ipv6.c                    |  1 +
 net/ipv6/udp.c                         |  1 +
 net/sctp/ulpqueue.c                    |  5 +++--
 21 files changed, 52 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 3de1394bcab..e2fe0700b3b 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -87,4 +87,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h
index 6e6cd159924..92121b0f5b9 100644
--- a/arch/avr32/include/uapi/asm/socket.h
+++ b/arch/avr32/include/uapi/asm/socket.h
@@ -80,4 +80,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _UAPI__ASM_AVR32_SOCKET_H */
diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h
index ed94e5ed0a2..60f60f5b9b3 100644
--- a/arch/cris/include/uapi/asm/socket.h
+++ b/arch/cris/include/uapi/asm/socket.h
@@ -82,6 +82,8 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _ASM_SOCKET_H */
 
 
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index ca2c6e6f31c..2c6890209ea 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -80,5 +80,7 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _ASM_SOCKET_H */
 
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index a1b49bac795..09a93fb566f 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -89,4 +89,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index 6c9a24b3aef..e8589819c27 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -80,4 +80,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index a14baa218c7..2e9ee8c55a1 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -98,4 +98,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index 6aa3ce1854a..f3492e8c9f7 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -80,4 +80,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index fe35ceacf0e..7984a1cab3d 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -79,4 +79,6 @@
 
 #define SO_BPF_EXTENSIONS	0x4029
 
+#define SO_INCOMING_CPU		0x402A
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index a9c3e2e18c0..3474e4ef166 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -87,4 +87,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif	/* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index e031332096d..8457636c33e 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -86,4 +86,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 54d9608681b..4a8003a9416 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -76,6 +76,8 @@
 
 #define SO_BPF_EXTENSIONS	0x0032
 
+#define SO_INCOMING_CPU		0x0033
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index 39acec0cf0b..c46f6a69684 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -91,4 +91,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif	/* _XTENSA_SOCKET_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 6767d75ecb1..7789b59c0c4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -273,6 +273,7 @@ struct cg_proto;
   *	@sk_rcvtimeo: %SO_RCVTIMEO setting
   *	@sk_sndtimeo: %SO_SNDTIMEO setting
   *	@sk_rxhash: flow hash received from netif layer
+  *	@sk_incoming_cpu: record cpu processing incoming packets
   *	@sk_txhash: computed flow hash for use on transmit
   *	@sk_filter: socket filtering instructions
   *	@sk_protinfo: private area, net family specific, when not using slab
@@ -350,6 +351,12 @@ struct sock {
 #ifdef CONFIG_RPS
 	__u32			sk_rxhash;
 #endif
+	u16			sk_incoming_cpu;
+	/* 16bit hole
+	 * Warned : sk_incoming_cpu can be set from softirq,
+	 * Do not use this hole without fully understanding possible issues.
+	 */
+
 	__u32			sk_txhash;
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	unsigned int		sk_napi_id;
@@ -833,6 +840,11 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 	return sk->sk_backlog_rcv(sk, skb);
 }
 
+static inline void sk_incoming_cpu_update(struct sock *sk)
+{
+	sk->sk_incoming_cpu = raw_smp_processor_id();
+}
+
 static inline void sock_rps_record_flow_hash(__u32 hash)
 {
 #ifdef CONFIG_RPS
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index ea0796bdcf8..f541ccefd4a 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -82,4 +82,6 @@
 
 #define SO_BPF_EXTENSIONS	48
 
+#define SO_INCOMING_CPU		49
+
 #endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/net/core/sock.c b/net/core/sock.c
index ac56dd06c30..0725cf0cb68 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1213,6 +1213,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = sk->sk_max_pacing_rate;
 		break;
 
+	case SO_INCOMING_CPU:
+		v.val = sk->sk_incoming_cpu;
+		break;
+
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -1517,6 +1521,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 
 		newsk->sk_err	   = 0;
 		newsk->sk_priority = 0;
+		newsk->sk_incoming_cpu = raw_smp_processor_id();
 		/*
 		 * Before updating sk_refcnt, we must commit prior changes to memory
 		 * (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8893598a412..2c6a955fd5c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1663,6 +1663,7 @@ process:
 	if (sk_filter(sk, skb))
 		goto discard_and_relse;
 
+	sk_incoming_cpu_update(sk);
 	skb->dev = NULL;
 
 	bh_lock_sock_nested(sk);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5d0fdca8e96..d13751685f4 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1445,6 +1445,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if (inet_sk(sk)->inet_daddr) {
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
+		sk_incoming_cpu_update(sk);
 	}
 
 	rc = sock_queue_rcv_skb(sk, skb);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index fd8e50b380e..1985b4933a6 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1456,6 +1456,7 @@ process:
 	if (sk_filter(sk, skb))
 		goto discard_and_relse;
 
+	sk_incoming_cpu_update(sk);
 	skb->dev = NULL;
 
 	bh_lock_sock_nested(sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index b756355e973..d1fe3627490 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -577,6 +577,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
+		sk_incoming_cpu_update(sk);
 	}
 
 	rc = sock_queue_rcv_skb(sk, skb);
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index d49dc2ed30a..ce469d648ff 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -205,9 +205,10 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 	if (sock_flag(sk, SOCK_DEAD) || (sk->sk_shutdown & RCV_SHUTDOWN))
 		goto out_free;
 
-	if (!sctp_ulpevent_is_notification(event))
+	if (!sctp_ulpevent_is_notification(event)) {
 		sk_mark_napi_id(sk, skb);
-
+		sk_incoming_cpu_update(sk);
+	}
 	/* Check if the user wishes to receive this event.  */
 	if (!sctp_ulpevent_is_enabled(event, &sctp_sk(sk)->subscribe))
 		goto out_free;
-- 
cgit v1.2.3-70-g09d2


From f8c6455bb04b944edb69e9b074e28efee2c56bdd Mon Sep 17 00:00:00 2001
From: Shani Michaeli <shanim@mellanox.com>
Date: Sun, 9 Nov 2014 13:51:53 +0200
Subject: net/mlx4_en: Extend checksum offloading by CHECKSUM COMPLETE

When processing received traffic, pass CHECKSUM_COMPLETE status to the
stack, with calculated checksum for non TCP/UDP packets (such
as GRE or ICMP).

Although the stack expects checksum which doesn't include the pseudo
header, the HW adds it. To address that, we are subtracting the pseudo
header checksum from the checksum value provided by the HW.

In the IPv6 case, we also compute/add the IP header checksum which
is not added by the HW for such packets.

Cc: Jerry Chu <hkchu@google.com>
Signed-off-by: Shani Michaeli <shanim@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c |   2 +-
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c  |   5 +
 drivers/net/ethernet/mellanox/mlx4/en_port.c    |   2 +
 drivers/net/ethernet/mellanox/mlx4/en_rx.c      | 126 ++++++++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx4/main.c       |   9 ++
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h    |   5 +-
 include/linux/mlx4/device.h                     |   1 +
 7 files changed, 142 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 8ea4d5be737..6c643230a5e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -115,7 +115,7 @@ static const char main_strings[][ETH_GSTRING_LEN] = {
 	"tso_packets",
 	"xmit_more",
 	"queue_stopped", "wake_queue", "tx_timeout", "rx_alloc_failed",
-	"rx_csum_good", "rx_csum_none", "tx_chksum_offload",
+	"rx_csum_good", "rx_csum_none", "rx_csum_complete", "tx_chksum_offload",
 
 	/* packet statistics */
 	"broadcast", "rx_prio_0", "rx_prio_1", "rx_prio_2", "rx_prio_3",
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 0efbae90f1b..d1eb25dbff5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1893,6 +1893,7 @@ static void mlx4_en_clear_stats(struct net_device *dev)
 		priv->rx_ring[i]->packets = 0;
 		priv->rx_ring[i]->csum_ok = 0;
 		priv->rx_ring[i]->csum_none = 0;
+		priv->rx_ring[i]->csum_complete = 0;
 	}
 }
 
@@ -2503,6 +2504,10 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	/* Query for default mac and max mtu */
 	priv->max_mtu = mdev->dev->caps.eth_mtu_cap[priv->port];
 
+	if (mdev->dev->caps.rx_checksum_flags_port[priv->port] &
+	    MLX4_RX_CSUM_MODE_VAL_NON_TCP_UDP)
+		priv->flags |= MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP;
+
 	/* Set default MAC */
 	dev->addr_len = ETH_ALEN;
 	mlx4_en_u64_to_mac(dev->dev_addr, mdev->dev->caps.def_mac[priv->port]);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 134b12e17da..6cb80072af6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -155,11 +155,13 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	stats->rx_bytes = 0;
 	priv->port_stats.rx_chksum_good = 0;
 	priv->port_stats.rx_chksum_none = 0;
+	priv->port_stats.rx_chksum_complete = 0;
 	for (i = 0; i < priv->rx_ring_num; i++) {
 		stats->rx_packets += priv->rx_ring[i]->packets;
 		stats->rx_bytes += priv->rx_ring[i]->bytes;
 		priv->port_stats.rx_chksum_good += priv->rx_ring[i]->csum_ok;
 		priv->port_stats.rx_chksum_none += priv->rx_ring[i]->csum_none;
+		priv->port_stats.rx_chksum_complete += priv->rx_ring[i]->csum_complete;
 	}
 	stats->tx_packets = 0;
 	stats->tx_bytes = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index df6d352c4e5..ccd95177ea7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -42,6 +42,10 @@
 #include <linux/vmalloc.h>
 #include <linux/irq.h>
 
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ip6_checksum.h>
+#endif
+
 #include "mlx4_en.h"
 
 static int mlx4_alloc_pages(struct mlx4_en_priv *priv,
@@ -643,6 +647,86 @@ static void mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv,
 	}
 }
 
+/* When hardware doesn't strip the vlan, we need to calculate the checksum
+ * over it and add it to the hardware's checksum calculation
+ */
+static inline __wsum get_fixed_vlan_csum(__wsum hw_checksum,
+					 struct vlan_hdr *vlanh)
+{
+	return csum_add(hw_checksum, *(__wsum *)vlanh);
+}
+
+/* Although the stack expects checksum which doesn't include the pseudo
+ * header, the HW adds it. To address that, we are subtracting the pseudo
+ * header checksum from the checksum value provided by the HW.
+ */
+static void get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb,
+				struct iphdr *iph)
+{
+	__u16 length_for_csum = 0;
+	__wsum csum_pseudo_header = 0;
+
+	length_for_csum = (be16_to_cpu(iph->tot_len) - (iph->ihl << 2));
+	csum_pseudo_header = csum_tcpudp_nofold(iph->saddr, iph->daddr,
+						length_for_csum, iph->protocol, 0);
+	skb->csum = csum_sub(hw_checksum, csum_pseudo_header);
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+/* In IPv6 packets, besides subtracting the pseudo header checksum,
+ * we also compute/add the IP header checksum which
+ * is not added by the HW.
+ */
+static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
+			       struct ipv6hdr *ipv6h)
+{
+	__wsum csum_pseudo_hdr = 0;
+
+	if (ipv6h->nexthdr == IPPROTO_FRAGMENT || ipv6h->nexthdr == IPPROTO_HOPOPTS)
+		return -1;
+	hw_checksum = csum_add(hw_checksum, (__force __wsum)(ipv6h->nexthdr << 8));
+
+	csum_pseudo_hdr = csum_partial(&ipv6h->saddr,
+				       sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0);
+	csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ipv6h->payload_len);
+	csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ntohs(ipv6h->nexthdr));
+
+	skb->csum = csum_sub(hw_checksum, csum_pseudo_hdr);
+	skb->csum = csum_add(skb->csum, csum_partial(ipv6h, sizeof(struct ipv6hdr), 0));
+	return 0;
+}
+#endif
+static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
+		      int hwtstamp_rx_filter)
+{
+	__wsum hw_checksum = 0;
+
+	void *hdr = (u8 *)va + sizeof(struct ethhdr);
+
+	hw_checksum = csum_unfold((__force __sum16)cqe->checksum);
+
+	if (((struct ethhdr *)va)->h_proto == htons(ETH_P_8021Q) &&
+	    hwtstamp_rx_filter != HWTSTAMP_FILTER_NONE) {
+		/* next protocol non IPv4 or IPv6 */
+		if (((struct vlan_hdr *)hdr)->h_vlan_encapsulated_proto
+		    != htons(ETH_P_IP) &&
+		    ((struct vlan_hdr *)hdr)->h_vlan_encapsulated_proto
+		    != htons(ETH_P_IPV6))
+			return -1;
+		hw_checksum = get_fixed_vlan_csum(hw_checksum, hdr);
+		hdr += sizeof(struct vlan_hdr);
+	}
+
+	if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4))
+		get_fixed_ipv4_csum(hw_checksum, skb, hdr);
+#if IS_ENABLED(CONFIG_IPV6)
+	else if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6))
+		if (get_fixed_ipv6_csum(hw_checksum, skb, hdr))
+			return -1;
+#endif
+	return 0;
+}
+
 int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int budget)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -744,13 +828,26 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
 
 		if (likely(dev->features & NETIF_F_RXCSUM)) {
-			if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
-			    (cqe->checksum == cpu_to_be16(0xffff))) {
-				ring->csum_ok++;
-				ip_summed = CHECKSUM_UNNECESSARY;
+			if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
+						      MLX4_CQE_STATUS_UDP)) {
+				if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
+				    cqe->checksum == cpu_to_be16(0xffff)) {
+					ip_summed = CHECKSUM_UNNECESSARY;
+					ring->csum_ok++;
+				} else {
+					ip_summed = CHECKSUM_NONE;
+					ring->csum_none++;
+				}
 			} else {
-				ip_summed = CHECKSUM_NONE;
-				ring->csum_none++;
+				if (priv->flags & MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP &&
+				    (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 |
+							       MLX4_CQE_STATUS_IPV6))) {
+					ip_summed = CHECKSUM_COMPLETE;
+					ring->csum_complete++;
+				} else {
+					ip_summed = CHECKSUM_NONE;
+					ring->csum_none++;
+				}
 			}
 		} else {
 			ip_summed = CHECKSUM_NONE;
@@ -776,6 +873,15 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			if (!nr)
 				goto next;
 
+			if (ip_summed == CHECKSUM_COMPLETE) {
+				void *va = skb_frag_address(skb_shinfo(gro_skb)->frags);
+				if (check_csum(cqe, gro_skb, va, ring->hwtstamp_rx_filter)) {
+					ip_summed = CHECKSUM_NONE;
+					ring->csum_none++;
+					ring->csum_complete--;
+				}
+			}
+
 			skb_shinfo(gro_skb)->nr_frags = nr;
 			gro_skb->len = length;
 			gro_skb->data_len = length;
@@ -822,6 +928,14 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			goto next;
 		}
 
+		if (ip_summed == CHECKSUM_COMPLETE) {
+			if (check_csum(cqe, skb, skb->data, ring->hwtstamp_rx_filter)) {
+				ip_summed = CHECKSUM_NONE;
+				ring->csum_complete--;
+				ring->csum_none++;
+			}
+		}
+
 		skb->ip_summed = ip_summed;
 		skb->protocol = eth_type_trans(skb, dev);
 		skb_record_rx_queue(skb, cq->ring);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 9f821964a1b..2f6ba420ac0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1629,6 +1629,7 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 	struct mlx4_init_hca_param init_hca;
 	u64 icm_size;
 	int err;
+	struct mlx4_config_dev_params params;
 
 	if (!mlx4_is_slave(dev)) {
 		err = mlx4_QUERY_FW(dev);
@@ -1762,6 +1763,14 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 		goto unmap_bf;
 	}
 
+	/* Query CONFIG_DEV parameters */
+	err = mlx4_config_dev_retrieval(dev, &params);
+	if (err && err != -ENOTSUPP) {
+		mlx4_err(dev, "Failed to query CONFIG_DEV parameters\n");
+	} else if (!err) {
+		dev->caps.rx_checksum_flags_port[1] = params.rx_csum_flags_port_1;
+		dev->caps.rx_checksum_flags_port[2] = params.rx_csum_flags_port_2;
+	}
 	priv->eq_table.inta_pin = adapter.inta_pin;
 	memcpy(dev->board_id, adapter.board_id, sizeof dev->board_id);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index ef83d127f40..de456749ffa 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -326,6 +326,7 @@ struct mlx4_en_rx_ring {
 #endif
 	unsigned long csum_ok;
 	unsigned long csum_none;
+	unsigned long csum_complete;
 	int hwtstamp_rx_filter;
 	cpumask_var_t affinity_mask;
 };
@@ -449,6 +450,7 @@ struct mlx4_en_port_stats {
 	unsigned long rx_alloc_failed;
 	unsigned long rx_chksum_good;
 	unsigned long rx_chksum_none;
+	unsigned long rx_chksum_complete;
 	unsigned long tx_chksum_offload;
 #define NUM_PORT_STATS		9
 };
@@ -507,7 +509,8 @@ enum {
 	MLX4_EN_FLAG_ENABLE_HW_LOOPBACK	= (1 << 2),
 	/* whether we need to drop packets that hardware loopback-ed */
 	MLX4_EN_FLAG_RX_FILTER_NEEDED	= (1 << 3),
-	MLX4_EN_FLAG_FORCE_PROMISC	= (1 << 4)
+	MLX4_EN_FLAG_FORCE_PROMISC	= (1 << 4),
+	MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP	= (1 << 5),
 };
 
 #define MLX4_EN_MAC_HASH_SIZE (1 << BITS_PER_BYTE)
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 5cc5eac47d1..3d9bff00f24 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -497,6 +497,7 @@ struct mlx4_caps {
 	u16			hca_core_clock;
 	u64			phys_port_id[MLX4_MAX_PORTS + 1];
 	int			tunnel_offload_mode;
+	u8			rx_checksum_flags_port[MLX4_MAX_PORTS + 1];
 };
 
 struct mlx4_buf_list {
-- 
cgit v1.2.3-70-g09d2


From ba7a46f16dd29f93303daeb1fee8af316c5a07f4 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 11 Nov 2014 10:59:17 -0800
Subject: net: Convert LIMIT_NETDEBUG to net_dbg_ratelimited

Use the more common dynamic_debug capable net_dbg_ratelimited
and remove the LIMIT_NETDEBUG macro.

All messages are still ratelimited.

Some KERN_<LEVEL> uses are changed to KERN_DEBUG.

This may have some negative impact on messages that were
emitted at KERN_INFO that are not not enabled at all unless
DEBUG is defined or dynamic_debug is enabled.  Even so,
these messages are now _not_ emitted by default.

This also eliminates the use of the net_msg_warn sysctl
"/proc/sys/net/core/warnings".  For backward compatibility,
the sysctl is not removed, but it has no function.  The extern
declaration of net_msg_warn is removed from sock.h and made
static in net/core/sysctl_net_core.c

Miscellanea:

o Update the sysctl documentation
o Remove the embedded uses of pr_fmt
o Coalesce format fragments
o Realign arguments

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/sysctl/net.txt | 12 ++++++++----
 include/net/sock.h           |  7 -------
 include/net/udplite.h        |  6 +++---
 net/core/sysctl_net_core.c   |  2 ++
 net/core/utils.c             |  3 ---
 net/ipv4/icmp.c              |  8 ++++----
 net/ipv4/inet_fragment.c     |  2 +-
 net/ipv4/ip_fragment.c       |  3 +--
 net/ipv4/tcp_input.c         |  8 ++++----
 net/ipv4/tcp_timer.c         | 18 ++++++++++--------
 net/ipv4/udp.c               | 30 +++++++++++++++---------------
 net/ipv6/addrconf.c          |  6 ++----
 net/ipv6/ah6.c               |  7 +++----
 net/ipv6/datagram.c          |  4 ++--
 net/ipv6/esp6.c              |  4 ++--
 net/ipv6/exthdrs.c           | 18 +++++++++---------
 net/ipv6/icmp.c              | 15 +++++++--------
 net/ipv6/mip6.c              | 11 ++++++-----
 net/ipv6/netfilter.c         |  2 +-
 net/ipv6/udp.c               | 31 +++++++++++++------------------
 net/phonet/af_phonet.c       |  9 +++++----
 net/phonet/pep-gprs.c        |  3 +--
 net/phonet/pep.c             | 12 ++++++------
 23 files changed, 105 insertions(+), 116 deletions(-)

(limited to 'include')

diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index 04892b82115..e26c607468a 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -120,10 +120,14 @@ seconds.
 warnings
 --------
 
-This controls console messages from the networking stack that can occur because
-of problems on the network like duplicate address or bad checksums. Normally,
-this should be enabled, but if the problem persists the messages can be
-disabled.
+This sysctl is now unused.
+
+This was used to control console messages from the networking stack that
+occur because of problems on the network like duplicate address or bad
+checksums.
+
+These messages are now emitted at KERN_DEBUG and can generally be enabled
+and controlled by the dynamic_debug facility.
 
 netdev_budget
 -------------
diff --git a/include/net/sock.h b/include/net/sock.h
index 7789b59c0c4..83a669f83ba 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2288,13 +2288,6 @@ bool sk_ns_capable(const struct sock *sk,
 bool sk_capable(const struct sock *sk, int cap);
 bool sk_net_capable(const struct sock *sk, int cap);
 
-/*
- *	Enable debug/info messages
- */
-extern int net_msg_warn;
-#define LIMIT_NETDEBUG(fmt, args...) \
-	do { if (net_msg_warn && net_ratelimit()) printk(fmt,##args); } while(0)
-
 extern __u32 sysctl_wmem_max;
 extern __u32 sysctl_rmem_max;
 
diff --git a/include/net/udplite.h b/include/net/udplite.h
index 2caadabcd07..9a28a517940 100644
--- a/include/net/udplite.h
+++ b/include/net/udplite.h
@@ -40,7 +40,7 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh)
          * checksum. UDP-Lite (like IPv6) mandates checksums, hence packets
          * with a zero checksum field are illegal.                            */
 	if (uh->check == 0) {
-		LIMIT_NETDEBUG(KERN_DEBUG "UDPLite: zeroed checksum field\n");
+		net_dbg_ratelimited("UDPLite: zeroed checksum field\n");
 		return 1;
 	}
 
@@ -52,8 +52,8 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh)
 		/*
 		 * Coverage length violates RFC 3828: log and discard silently.
 		 */
-		LIMIT_NETDEBUG(KERN_DEBUG "UDPLite: bad csum coverage %d/%d\n",
-			       cscov, skb->len);
+		net_dbg_ratelimited("UDPLite: bad csum coverage %d/%d\n",
+				    cscov, skb->len);
 		return 1;
 
 	} else if (cscov < skb->len) {
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index cf9cd13509a..f93f092fe22 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -26,6 +26,8 @@ static int zero = 0;
 static int one = 1;
 static int ushort_max = USHRT_MAX;
 
+static int net_msg_warn;	/* Unused, but still a sysctl */
+
 #ifdef CONFIG_RPS
 static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
 				void __user *buffer, size_t *lenp, loff_t *ppos)
diff --git a/net/core/utils.c b/net/core/utils.c
index efc76dd9dcd..7b803884c16 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -33,9 +33,6 @@
 #include <asm/byteorder.h>
 #include <asm/uaccess.h>
 
-int net_msg_warn __read_mostly = 1;
-EXPORT_SYMBOL(net_msg_warn);
-
 DEFINE_RATELIMIT_STATE(net_ratelimit_state, 5 * HZ, 10);
 /*
  * All net warning printk()s should be guarded by this function.
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 5882f584910..36b7bfa609d 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -784,8 +784,8 @@ static void icmp_unreach(struct sk_buff *skb)
 			 */
 			switch (net->ipv4.sysctl_ip_no_pmtu_disc) {
 			default:
-				LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: fragmentation needed and DF set\n"),
-					       &iph->daddr);
+				net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n",
+						    &iph->daddr);
 				break;
 			case 2:
 				goto out;
@@ -798,8 +798,8 @@ static void icmp_unreach(struct sk_buff *skb)
 			}
 			break;
 		case ICMP_SR_FAILED:
-			LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: Source Route Failed\n"),
-				       &iph->daddr);
+			net_dbg_ratelimited("%pI4: Source Route Failed\n",
+					    &iph->daddr);
 			break;
 		default:
 			break;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 19419b60cb3..e7920352646 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -458,6 +458,6 @@ void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
 		". Dropping fragment.\n";
 
 	if (PTR_ERR(q) == -ENOBUFS)
-		LIMIT_NETDEBUG(KERN_WARNING "%s%s", prefix, msg);
+		net_dbg_ratelimited("%s%s", prefix, msg);
 }
 EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 4d964dadd65..e5b6d0ddcb5 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -618,8 +618,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 	return 0;
 
 out_nomem:
-	LIMIT_NETDEBUG(KERN_ERR pr_fmt("queue_glue: no memory for gluing queue %p\n"),
-		       qp);
+	net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp);
 	err = -ENOMEM;
 	goto out_fail;
 out_oversize:
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5f979c7f513..d91436ba17e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5854,12 +5854,12 @@ static inline void pr_drop_req(struct request_sock *req, __u16 port, int family)
 	struct inet_request_sock *ireq = inet_rsk(req);
 
 	if (family == AF_INET)
-		LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI4/%u\n"),
-			       &ireq->ir_rmt_addr, port);
+		net_dbg_ratelimited("drop open request from %pI4/%u\n",
+				    &ireq->ir_rmt_addr, port);
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (family == AF_INET6)
-		LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI6/%u\n"),
-			       &ireq->ir_v6_rmt_addr, port);
+		net_dbg_ratelimited("drop open request from %pI6/%u\n",
+				    &ireq->ir_v6_rmt_addr, port);
 #endif
 }
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 9b21ae8b2e3..1829c7fbc77 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -374,17 +374,19 @@ void tcp_retransmit_timer(struct sock *sk)
 		 */
 		struct inet_sock *inet = inet_sk(sk);
 		if (sk->sk_family == AF_INET) {
-			LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"),
-				       &inet->inet_daddr,
-				       ntohs(inet->inet_dport), inet->inet_num,
-				       tp->snd_una, tp->snd_nxt);
+			net_dbg_ratelimited("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
+					    &inet->inet_daddr,
+					    ntohs(inet->inet_dport),
+					    inet->inet_num,
+					    tp->snd_una, tp->snd_nxt);
 		}
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (sk->sk_family == AF_INET6) {
-			LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"),
-				       &sk->sk_v6_daddr,
-				       ntohs(inet->inet_dport), inet->inet_num,
-				       tp->snd_una, tp->snd_nxt);
+			net_dbg_ratelimited("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
+					    &sk->sk_v6_daddr,
+					    ntohs(inet->inet_dport),
+					    inet->inet_num,
+					    tp->snd_una, tp->snd_nxt);
 		}
 #endif
 		if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d13751685f4..1b6e9d5fade 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1051,7 +1051,7 @@ back_from_confirm:
 		/* ... which is an evident application bug. --ANK */
 		release_sock(sk);
 
-		LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("cork app bug 2\n"));
+		net_dbg_ratelimited("cork app bug 2\n");
 		err = -EINVAL;
 		goto out;
 	}
@@ -1133,7 +1133,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
 	if (unlikely(!up->pending)) {
 		release_sock(sk);
 
-		LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("udp cork app bug 3\n"));
+		net_dbg_ratelimited("udp cork app bug 3\n");
 		return -EINVAL;
 	}
 
@@ -1547,8 +1547,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		 * provided by the application."
 		 */
 		if (up->pcrlen == 0) {          /* full coverage was set  */
-			LIMIT_NETDEBUG(KERN_WARNING "UDPLite: partial coverage %d while full coverage %d requested\n",
-				       UDP_SKB_CB(skb)->cscov, skb->len);
+			net_dbg_ratelimited("UDPLite: partial coverage %d while full coverage %d requested\n",
+					    UDP_SKB_CB(skb)->cscov, skb->len);
 			goto drop;
 		}
 		/* The next case involves violating the min. coverage requested
@@ -1558,8 +1558,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		 * Therefore the above ...()->partial_cov statement is essential.
 		 */
 		if (UDP_SKB_CB(skb)->cscov  <  up->pcrlen) {
-			LIMIT_NETDEBUG(KERN_WARNING "UDPLite: coverage %d too small, need min %d\n",
-				       UDP_SKB_CB(skb)->cscov, up->pcrlen);
+			net_dbg_ratelimited("UDPLite: coverage %d too small, need min %d\n",
+					    UDP_SKB_CB(skb)->cscov, up->pcrlen);
 			goto drop;
 		}
 	}
@@ -1828,11 +1828,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	return 0;
 
 short_packet:
-	LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n",
-		       proto == IPPROTO_UDPLITE ? "Lite" : "",
-		       &saddr, ntohs(uh->source),
-		       ulen, skb->len,
-		       &daddr, ntohs(uh->dest));
+	net_dbg_ratelimited("UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n",
+			    proto == IPPROTO_UDPLITE ? "Lite" : "",
+			    &saddr, ntohs(uh->source),
+			    ulen, skb->len,
+			    &daddr, ntohs(uh->dest));
 	goto drop;
 
 csum_error:
@@ -1840,10 +1840,10 @@ csum_error:
 	 * RFC1122: OK.  Discards the bad packet silently (as far as
 	 * the network is concerned, anyway) as per 4.1.3.4 (MUST).
 	 */
-	LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n",
-		       proto == IPPROTO_UDPLITE ? "Lite" : "",
-		       &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest),
-		       ulen);
+	net_dbg_ratelimited("UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n",
+			    proto == IPPROTO_UDPLITE ? "Lite" : "",
+			    &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest),
+			    ulen);
 	UDP_INC_STATS_BH(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
 drop:
 	UDP_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 06e897832a7..251fcb48b21 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1411,10 +1411,8 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 
 			if (unlikely(score->addr_type == IPV6_ADDR_ANY ||
 				     score->addr_type & IPV6_ADDR_MULTICAST)) {
-				LIMIT_NETDEBUG(KERN_DEBUG
-					       "ADDRCONF: unspecified / multicast address "
-					       "assigned as unicast address on %s",
-					       dev->name);
+				net_dbg_ratelimited("ADDRCONF: unspecified / multicast address assigned as unicast address on %s",
+						    dev->name);
 				continue;
 			}
 
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 6d16eb0e0c7..8ab1989198f 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -272,10 +272,9 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir)
 				ipv6_rearrange_destopt(iph, exthdr.opth);
 		case NEXTHDR_HOP:
 			if (!zero_out_mutable_opts(exthdr.opth)) {
-				LIMIT_NETDEBUG(
-					KERN_WARNING "overrun %sopts\n",
-					nexthdr == NEXTHDR_HOP ?
-						"hop" : "dest");
+				net_dbg_ratelimited("overrun %sopts\n",
+						    nexthdr == NEXTHDR_HOP ?
+						    "hop" : "dest");
 				return -EINVAL;
 			}
 			break;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 5c6996e44b1..cc1139687fd 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -893,8 +893,8 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 			break;
 		    }
 		default:
-			LIMIT_NETDEBUG(KERN_DEBUG "invalid cmsg type: %d\n",
-				       cmsg->cmsg_type);
+			net_dbg_ratelimited("invalid cmsg type: %d\n",
+					    cmsg->cmsg_type);
 			err = -EINVAL;
 			goto exit_f;
 		}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index d21d7b22eeb..d2c2d749b6d 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -286,8 +286,8 @@ static int esp_input_done2(struct sk_buff *skb, int err)
 	err = -EINVAL;
 	padlen = nexthdr[0];
 	if (padlen + 2 + alen >= elen) {
-		LIMIT_NETDEBUG(KERN_WARNING "ipsec esp packet is garbage "
-			       "padlen=%d, elen=%d\n", padlen + 2, elen - alen);
+		net_dbg_ratelimited("ipsec esp packet is garbage padlen=%d, elen=%d\n",
+				    padlen + 2, elen - alen);
 		goto out;
 	}
 
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 601d896f22d..a7bbbe45570 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -184,7 +184,7 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
 	int ret;
 
 	if (opt->dsthao) {
-		LIMIT_NETDEBUG(KERN_DEBUG "hao duplicated\n");
+		net_dbg_ratelimited("hao duplicated\n");
 		goto discard;
 	}
 	opt->dsthao = opt->dst1;
@@ -193,14 +193,14 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
 	hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + optoff);
 
 	if (hao->length != 16) {
-		LIMIT_NETDEBUG(
-			KERN_DEBUG "hao invalid option length = %d\n", hao->length);
+		net_dbg_ratelimited("hao invalid option length = %d\n",
+				    hao->length);
 		goto discard;
 	}
 
 	if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) {
-		LIMIT_NETDEBUG(
-			KERN_DEBUG "hao is not an unicast addr: %pI6\n", &hao->addr);
+		net_dbg_ratelimited("hao is not an unicast addr: %pI6\n",
+				    &hao->addr);
 		goto discard;
 	}
 
@@ -551,8 +551,8 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff)
 		memcpy(&IP6CB(skb)->ra, nh + optoff + 2, sizeof(IP6CB(skb)->ra));
 		return true;
 	}
-	LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_ra: wrong RA length %d\n",
-		       nh[optoff + 1]);
+	net_dbg_ratelimited("ipv6_hop_ra: wrong RA length %d\n",
+			    nh[optoff + 1]);
 	kfree_skb(skb);
 	return false;
 }
@@ -566,8 +566,8 @@ static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff)
 	u32 pkt_len;
 
 	if (nh[optoff + 1] != 4 || (optoff & 3) != 2) {
-		LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n",
-			       nh[optoff+1]);
+		net_dbg_ratelimited("ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n",
+				    nh[optoff+1]);
 		IP6_INC_STATS_BH(net, ipv6_skb_idev(skb),
 				 IPSTATS_MIB_INHDRERRORS);
 		goto drop;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 62c1037d9e8..09293403207 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -338,7 +338,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net,
 	 * anycast.
 	 */
 	if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) {
-		LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: acast source\n");
+		net_dbg_ratelimited("icmp6_send: acast source\n");
 		dst_release(dst);
 		return ERR_PTR(-EINVAL);
 	}
@@ -452,7 +452,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	 *	and anycast addresses will be checked later.
 	 */
 	if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
-		LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: addr_any/mcast source\n");
+		net_dbg_ratelimited("icmp6_send: addr_any/mcast source\n");
 		return;
 	}
 
@@ -460,7 +460,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	 *	Never answer to a ICMP packet.
 	 */
 	if (is_ineligible(skb)) {
-		LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: no reply to icmp error\n");
+		net_dbg_ratelimited("icmp6_send: no reply to icmp error\n");
 		return;
 	}
 
@@ -509,7 +509,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	len = skb->len - msg.offset;
 	len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr));
 	if (len < 0) {
-		LIMIT_NETDEBUG(KERN_DEBUG "icmp: len problem\n");
+		net_dbg_ratelimited("icmp: len problem\n");
 		goto out_dst_release;
 	}
 
@@ -706,9 +706,8 @@ static int icmpv6_rcv(struct sk_buff *skb)
 	daddr = &ipv6_hdr(skb)->daddr;
 
 	if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) {
-		LIMIT_NETDEBUG(KERN_DEBUG
-			       "ICMPv6 checksum failed [%pI6c > %pI6c]\n",
-			       saddr, daddr);
+		net_dbg_ratelimited("ICMPv6 checksum failed [%pI6c > %pI6c]\n",
+				    saddr, daddr);
 		goto csum_error;
 	}
 
@@ -781,7 +780,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		if (type & ICMPV6_INFOMSG_MASK)
 			break;
 
-		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6: msg of unknown type\n");
+		net_dbg_ratelimited("icmpv6: msg of unknown type\n");
 
 		/*
 		 * error of unknown type.
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index f61429d391d..b9779d441b1 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -97,16 +97,17 @@ static int mip6_mh_filter(struct sock *sk, struct sk_buff *skb)
 		return -1;
 
 	if (mh->ip6mh_hdrlen < mip6_mh_len(mh->ip6mh_type)) {
-		LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH message too short: %d vs >=%d\n",
-			       mh->ip6mh_hdrlen, mip6_mh_len(mh->ip6mh_type));
+		net_dbg_ratelimited("mip6: MH message too short: %d vs >=%d\n",
+				    mh->ip6mh_hdrlen,
+				    mip6_mh_len(mh->ip6mh_type));
 		mip6_param_prob(skb, 0, offsetof(struct ip6_mh, ip6mh_hdrlen) +
 				skb_network_header_len(skb));
 		return -1;
 	}
 
 	if (mh->ip6mh_proto != IPPROTO_NONE) {
-		LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH invalid payload proto = %d\n",
-			       mh->ip6mh_proto);
+		net_dbg_ratelimited("mip6: MH invalid payload proto = %d\n",
+				    mh->ip6mh_proto);
 		mip6_param_prob(skb, 0, offsetof(struct ip6_mh, ip6mh_proto) +
 				skb_network_header_len(skb));
 		return -1;
@@ -288,7 +289,7 @@ static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb,
 			 * XXX: packet if HAO exists.
 			 */
 			if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) {
-				LIMIT_NETDEBUG(KERN_WARNING "mip6: hao exists already, override\n");
+				net_dbg_ratelimited("mip6: hao exists already, override\n");
 				return offset;
 			}
 
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index d38e6a8d8b9..398377a9d01 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -36,7 +36,7 @@ int ip6_route_me_harder(struct sk_buff *skb)
 	err = dst->error;
 	if (err) {
 		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
-		LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
+		net_dbg_ratelimited("ip6_route_me_harder: No more route\n");
 		dst_release(dst);
 		return err;
 	}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d1fe3627490..0ba3de4f236 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -660,15 +660,13 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if ((is_udplite & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
 
 		if (up->pcrlen == 0) {          /* full coverage was set  */
-			LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: partial coverage"
-				" %d while full coverage %d requested\n",
-				UDP_SKB_CB(skb)->cscov, skb->len);
+			net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n",
+					    UDP_SKB_CB(skb)->cscov, skb->len);
 			goto drop;
 		}
 		if (UDP_SKB_CB(skb)->cscov  <  up->pcrlen) {
-			LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: coverage %d "
-						    "too small, need min %d\n",
-				       UDP_SKB_CB(skb)->cscov, up->pcrlen);
+			net_dbg_ratelimited("UDPLITE6: coverage %d too small, need min %d\n",
+					    UDP_SKB_CB(skb)->cscov, up->pcrlen);
 			goto drop;
 		}
 	}
@@ -761,9 +759,9 @@ static void udp6_csum_zero_error(struct sk_buff *skb)
 	/* RFC 2460 section 8.1 says that we SHOULD log
 	 * this error. Well, it is reasonable.
 	 */
-	LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n",
-		       &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source),
-		       &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest));
+	net_dbg_ratelimited("IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n",
+			    &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source),
+			    &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest));
 }
 
 /*
@@ -931,14 +929,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	return 0;
 
 short_packet:
-	LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n",
-		       proto == IPPROTO_UDPLITE ? "-Lite" : "",
-		       saddr,
-		       ntohs(uh->source),
-		       ulen,
-		       skb->len,
-		       daddr,
-		       ntohs(uh->dest));
+	net_dbg_ratelimited("UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n",
+			    proto == IPPROTO_UDPLITE ? "-Lite" : "",
+			    saddr, ntohs(uh->source),
+			    ulen, skb->len,
+			    daddr, ntohs(uh->dest));
 	goto discard;
 csum_error:
 	UDP6_INC_STATS_BH(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
@@ -1290,7 +1285,7 @@ back_from_confirm:
 		/* ... which is an evident application bug. --ANK */
 		release_sock(sk);
 
-		LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n");
+		net_dbg_ratelimited("udp cork app bug 2\n");
 		err = -EINVAL;
 		goto out;
 	}
diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c
index 5a940dbd74a..32ab87d3482 100644
--- a/net/phonet/af_phonet.c
+++ b/net/phonet/af_phonet.c
@@ -426,16 +426,17 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev,
 
 		out_dev = phonet_route_output(net, pn_sockaddr_get_addr(&sa));
 		if (!out_dev) {
-			LIMIT_NETDEBUG(KERN_WARNING"No Phonet route to %02X\n",
-					pn_sockaddr_get_addr(&sa));
+			net_dbg_ratelimited("No Phonet route to %02X\n",
+					    pn_sockaddr_get_addr(&sa));
 			goto out;
 		}
 
 		__skb_push(skb, sizeof(struct phonethdr));
 		skb->dev = out_dev;
 		if (out_dev == dev) {
-			LIMIT_NETDEBUG(KERN_ERR"Phonet loop to %02X on %s\n",
-					pn_sockaddr_get_addr(&sa), dev->name);
+			net_dbg_ratelimited("Phonet loop to %02X on %s\n",
+					    pn_sockaddr_get_addr(&sa),
+					    dev->name);
 			goto out_dev;
 		}
 		/* Some drivers (e.g. TUN) do not allocate HW header space */
diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c
index e9a83a63718..fa8237fdc57 100644
--- a/net/phonet/pep-gprs.c
+++ b/net/phonet/pep-gprs.c
@@ -203,8 +203,7 @@ static netdev_tx_t gprs_xmit(struct sk_buff *skb, struct net_device *dev)
 	len = skb->len;
 	err = pep_write(sk, skb);
 	if (err) {
-		LIMIT_NETDEBUG(KERN_WARNING"%s: TX error (%d)\n",
-				dev->name, err);
+		net_dbg_ratelimited("%s: TX error (%d)\n", dev->name, err);
 		dev->stats.tx_aborted_errors++;
 		dev->stats.tx_errors++;
 	} else {
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 44b2123e22b..9cd069dfaf6 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -272,8 +272,8 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb)
 
 	hdr = pnp_hdr(skb);
 	if (hdr->data[0] != PN_PEP_TYPE_COMMON) {
-		LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP type: %u\n",
-				(unsigned int)hdr->data[0]);
+		net_dbg_ratelimited("Phonet unknown PEP type: %u\n",
+				    (unsigned int)hdr->data[0]);
 		return -EOPNOTSUPP;
 	}
 
@@ -304,8 +304,8 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb)
 		break;
 
 	default:
-		LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP indication: %u\n",
-				(unsigned int)hdr->data[1]);
+		net_dbg_ratelimited("Phonet unknown PEP indication: %u\n",
+				    (unsigned int)hdr->data[1]);
 		return -EOPNOTSUPP;
 	}
 	if (wake)
@@ -451,8 +451,8 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb)
 		break;
 
 	default:
-		LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP message: %u\n",
-				hdr->message_id);
+		net_dbg_ratelimited("Phonet unknown PEP message: %u\n",
+				    hdr->message_id);
 		err = -EINVAL;
 	}
 out:
-- 
cgit v1.2.3-70-g09d2


From d7480fd3b1738a8eae6a76098b17af318cf9b9cc Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 10 Nov 2014 15:59:36 -0800
Subject: neigh: remove dynamic neigh table registration support

Currently there are only three neigh tables in the whole kernel:
arp table, ndisc table and decnet neigh table. What's more,
we don't support registering multiple tables per family.
Therefore we can just make these tables statically built-in.

Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h |  11 ++-
 net/core/neighbour.c    | 247 ++++++++++++++++++++++--------------------------
 net/decnet/dn_neigh.c   |   4 +-
 net/ipv4/arp.c          |   2 +-
 net/ipv6/ndisc.c        |   4 +-
 5 files changed, 126 insertions(+), 142 deletions(-)

(limited to 'include')

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index dedfb188b1a..eb070b3674a 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -220,6 +220,13 @@ struct neigh_table {
 	struct pneigh_entry	**phash_buckets;
 };
 
+enum {
+	NEIGH_ARP_TABLE = 0,
+	NEIGH_ND_TABLE = 1,
+	NEIGH_DN_TABLE = 2,
+	NEIGH_NR_TABLES,
+};
+
 static inline int neigh_parms_family(struct neigh_parms *p)
 {
 	return p->tbl->family;
@@ -240,8 +247,8 @@ static inline void *neighbour_priv(const struct neighbour *n)
 #define NEIGH_UPDATE_F_ISROUTER			0x40000000
 #define NEIGH_UPDATE_F_ADMIN			0x80000000
 
-void neigh_table_init(struct neigh_table *tbl);
-int neigh_table_clear(struct neigh_table *tbl);
+void neigh_table_init(int index, struct neigh_table *tbl);
+int neigh_table_clear(int index, struct neigh_table *tbl);
 struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey,
 			       struct net_device *dev);
 struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net,
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index edd04116ecb..8e38f17288d 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -56,7 +56,6 @@ static void __neigh_notify(struct neighbour *n, int type, int flags);
 static void neigh_update_notify(struct neighbour *neigh);
 static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
 
-static struct neigh_table *neigh_tables;
 #ifdef CONFIG_PROC_FS
 static const struct file_operations neigh_stat_seq_fops;
 #endif
@@ -87,13 +86,8 @@ static const struct file_operations neigh_stat_seq_fops;
    the most complicated procedure, which we allow is dev->hard_header.
    It is supposed, that dev->hard_header is simplistic and does
    not make callbacks to neighbour tables.
-
-   The last lock is neigh_tbl_lock. It is pure SMP lock, protecting
-   list of neighbour tables. This list is used only in process context,
  */
 
-static DEFINE_RWLOCK(neigh_tbl_lock);
-
 static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb)
 {
 	kfree_skb(skb);
@@ -1520,7 +1514,9 @@ static void neigh_parms_destroy(struct neigh_parms *parms)
 
 static struct lock_class_key neigh_table_proxy_queue_class;
 
-static void neigh_table_init_no_netlink(struct neigh_table *tbl)
+static struct neigh_table *neigh_tables[NEIGH_NR_TABLES] __read_mostly;
+
+void neigh_table_init(int index, struct neigh_table *tbl)
 {
 	unsigned long now = jiffies;
 	unsigned long phsize;
@@ -1566,34 +1562,14 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl)
 
 	tbl->last_flush = now;
 	tbl->last_rand	= now + tbl->parms.reachable_time * 20;
-}
-
-void neigh_table_init(struct neigh_table *tbl)
-{
-	struct neigh_table *tmp;
 
-	neigh_table_init_no_netlink(tbl);
-	write_lock(&neigh_tbl_lock);
-	for (tmp = neigh_tables; tmp; tmp = tmp->next) {
-		if (tmp->family == tbl->family)
-			break;
-	}
-	tbl->next	= neigh_tables;
-	neigh_tables	= tbl;
-	write_unlock(&neigh_tbl_lock);
-
-	if (unlikely(tmp)) {
-		pr_err("Registering multiple tables for family %d\n",
-		       tbl->family);
-		dump_stack();
-	}
+	neigh_tables[index] = tbl;
 }
 EXPORT_SYMBOL(neigh_table_init);
 
-int neigh_table_clear(struct neigh_table *tbl)
+int neigh_table_clear(int index, struct neigh_table *tbl)
 {
-	struct neigh_table **tp;
-
+	neigh_tables[index] = NULL;
 	/* It is not clean... Fix it to unload IPv6 module safely */
 	cancel_delayed_work_sync(&tbl->gc_work);
 	del_timer_sync(&tbl->proxy_timer);
@@ -1601,14 +1577,6 @@ int neigh_table_clear(struct neigh_table *tbl)
 	neigh_ifdown(tbl, NULL);
 	if (atomic_read(&tbl->entries))
 		pr_crit("neighbour leakage\n");
-	write_lock(&neigh_tbl_lock);
-	for (tp = &neigh_tables; *tp; tp = &(*tp)->next) {
-		if (*tp == tbl) {
-			*tp = tbl->next;
-			break;
-		}
-	}
-	write_unlock(&neigh_tbl_lock);
 
 	call_rcu(&rcu_dereference_protected(tbl->nht, 1)->rcu,
 		 neigh_hash_free_rcu);
@@ -1626,12 +1594,32 @@ int neigh_table_clear(struct neigh_table *tbl)
 }
 EXPORT_SYMBOL(neigh_table_clear);
 
+static struct neigh_table *neigh_find_table(int family)
+{
+	struct neigh_table *tbl = NULL;
+
+	switch (family) {
+	case AF_INET:
+		tbl = neigh_tables[NEIGH_ARP_TABLE];
+		break;
+	case AF_INET6:
+		tbl = neigh_tables[NEIGH_ND_TABLE];
+		break;
+	case AF_DECnet:
+		tbl = neigh_tables[NEIGH_DN_TABLE];
+		break;
+	}
+
+	return tbl;
+}
+
 static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
 	struct nlattr *dst_attr;
 	struct neigh_table *tbl;
+	struct neighbour *neigh;
 	struct net_device *dev = NULL;
 	int err = -EINVAL;
 
@@ -1652,39 +1640,31 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
 		}
 	}
 
-	read_lock(&neigh_tbl_lock);
-	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
-		struct neighbour *neigh;
-
-		if (tbl->family != ndm->ndm_family)
-			continue;
-		read_unlock(&neigh_tbl_lock);
-
-		if (nla_len(dst_attr) < tbl->key_len)
-			goto out;
+	tbl = neigh_find_table(ndm->ndm_family);
+	if (tbl == NULL)
+		return -EAFNOSUPPORT;
 
-		if (ndm->ndm_flags & NTF_PROXY) {
-			err = pneigh_delete(tbl, net, nla_data(dst_attr), dev);
-			goto out;
-		}
+	if (nla_len(dst_attr) < tbl->key_len)
+		goto out;
 
-		if (dev == NULL)
-			goto out;
+	if (ndm->ndm_flags & NTF_PROXY) {
+		err = pneigh_delete(tbl, net, nla_data(dst_attr), dev);
+		goto out;
+	}
 
-		neigh = neigh_lookup(tbl, nla_data(dst_attr), dev);
-		if (neigh == NULL) {
-			err = -ENOENT;
-			goto out;
-		}
+	if (dev == NULL)
+		goto out;
 
-		err = neigh_update(neigh, NULL, NUD_FAILED,
-				   NEIGH_UPDATE_F_OVERRIDE |
-				   NEIGH_UPDATE_F_ADMIN);
-		neigh_release(neigh);
+	neigh = neigh_lookup(tbl, nla_data(dst_attr), dev);
+	if (neigh == NULL) {
+		err = -ENOENT;
 		goto out;
 	}
-	read_unlock(&neigh_tbl_lock);
-	err = -EAFNOSUPPORT;
+
+	err = neigh_update(neigh, NULL, NUD_FAILED,
+			   NEIGH_UPDATE_F_OVERRIDE |
+			   NEIGH_UPDATE_F_ADMIN);
+	neigh_release(neigh);
 
 out:
 	return err;
@@ -1692,11 +1672,14 @@ out:
 
 static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
+	int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE;
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
 	struct nlattr *tb[NDA_MAX+1];
 	struct neigh_table *tbl;
 	struct net_device *dev = NULL;
+	struct neighbour *neigh;
+	void *dst, *lladdr;
 	int err;
 
 	ASSERT_RTNL();
@@ -1720,70 +1703,60 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 			goto out;
 	}
 
-	read_lock(&neigh_tbl_lock);
-	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
-		int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE;
-		struct neighbour *neigh;
-		void *dst, *lladdr;
+	tbl = neigh_find_table(ndm->ndm_family);
+	if (tbl == NULL)
+		return -EAFNOSUPPORT;
 
-		if (tbl->family != ndm->ndm_family)
-			continue;
-		read_unlock(&neigh_tbl_lock);
+	if (nla_len(tb[NDA_DST]) < tbl->key_len)
+		goto out;
+	dst = nla_data(tb[NDA_DST]);
+	lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
 
-		if (nla_len(tb[NDA_DST]) < tbl->key_len)
-			goto out;
-		dst = nla_data(tb[NDA_DST]);
-		lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
+	if (ndm->ndm_flags & NTF_PROXY) {
+		struct pneigh_entry *pn;
+
+		err = -ENOBUFS;
+		pn = pneigh_lookup(tbl, net, dst, dev, 1);
+		if (pn) {
+			pn->flags = ndm->ndm_flags;
+			err = 0;
+		}
+		goto out;
+	}
 
-		if (ndm->ndm_flags & NTF_PROXY) {
-			struct pneigh_entry *pn;
+	if (dev == NULL)
+		goto out;
 
-			err = -ENOBUFS;
-			pn = pneigh_lookup(tbl, net, dst, dev, 1);
-			if (pn) {
-				pn->flags = ndm->ndm_flags;
-				err = 0;
-			}
+	neigh = neigh_lookup(tbl, dst, dev);
+	if (neigh == NULL) {
+		if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
+			err = -ENOENT;
 			goto out;
 		}
 
-		if (dev == NULL)
+		neigh = __neigh_lookup_errno(tbl, dst, dev);
+		if (IS_ERR(neigh)) {
+			err = PTR_ERR(neigh);
+			goto out;
+		}
+	} else {
+		if (nlh->nlmsg_flags & NLM_F_EXCL) {
+			err = -EEXIST;
+			neigh_release(neigh);
 			goto out;
-
-		neigh = neigh_lookup(tbl, dst, dev);
-		if (neigh == NULL) {
-			if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
-				err = -ENOENT;
-				goto out;
-			}
-
-			neigh = __neigh_lookup_errno(tbl, dst, dev);
-			if (IS_ERR(neigh)) {
-				err = PTR_ERR(neigh);
-				goto out;
-			}
-		} else {
-			if (nlh->nlmsg_flags & NLM_F_EXCL) {
-				err = -EEXIST;
-				neigh_release(neigh);
-				goto out;
-			}
-
-			if (!(nlh->nlmsg_flags & NLM_F_REPLACE))
-				flags &= ~NEIGH_UPDATE_F_OVERRIDE;
 		}
 
-		if (ndm->ndm_flags & NTF_USE) {
-			neigh_event_send(neigh, NULL);
-			err = 0;
-		} else
-			err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
-		neigh_release(neigh);
-		goto out;
+		if (!(nlh->nlmsg_flags & NLM_F_REPLACE))
+			flags &= ~NEIGH_UPDATE_F_OVERRIDE;
 	}
 
-	read_unlock(&neigh_tbl_lock);
-	err = -EAFNOSUPPORT;
+	if (ndm->ndm_flags & NTF_USE) {
+		neigh_event_send(neigh, NULL);
+		err = 0;
+	} else
+		err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
+	neigh_release(neigh);
+
 out:
 	return err;
 }
@@ -1982,7 +1955,8 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct neigh_table *tbl;
 	struct ndtmsg *ndtmsg;
 	struct nlattr *tb[NDTA_MAX+1];
-	int err;
+	bool found = false;
+	int err, tidx;
 
 	err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX,
 			  nl_neightbl_policy);
@@ -1995,19 +1969,21 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 	}
 
 	ndtmsg = nlmsg_data(nlh);
-	read_lock(&neigh_tbl_lock);
-	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
+
+	for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) {
+		tbl = neigh_tables[tidx];
+		if (!tbl)
+			continue;
 		if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family)
 			continue;
-
-		if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0)
+		if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0) {
+			found = true;
 			break;
+		}
 	}
 
-	if (tbl == NULL) {
-		err = -ENOENT;
-		goto errout_locked;
-	}
+	if (!found)
+		return -ENOENT;
 
 	/*
 	 * We acquire tbl->lock to be nice to the periodic timers and
@@ -2118,8 +2094,6 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 errout_tbl_lock:
 	write_unlock_bh(&tbl->lock);
-errout_locked:
-	read_unlock(&neigh_tbl_lock);
 errout:
 	return err;
 }
@@ -2134,10 +2108,13 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 
 	family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
 
-	read_lock(&neigh_tbl_lock);
-	for (tbl = neigh_tables, tidx = 0; tbl; tbl = tbl->next, tidx++) {
+	for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) {
 		struct neigh_parms *p;
 
+		tbl = neigh_tables[tidx];
+		if (!tbl)
+			continue;
+
 		if (tidx < tbl_skip || (family && tbl->family != family))
 			continue;
 
@@ -2168,7 +2145,6 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 		neigh_skip = 0;
 	}
 out:
-	read_unlock(&neigh_tbl_lock);
 	cb->args[0] = tidx;
 	cb->args[1] = nidx;
 
@@ -2351,7 +2327,6 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 	int proxy = 0;
 	int err;
 
-	read_lock(&neigh_tbl_lock);
 	family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
 
 	/* check for full ndmsg structure presence, family member is
@@ -2363,8 +2338,11 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 
 	s_t = cb->args[0];
 
-	for (tbl = neigh_tables, t = 0; tbl;
-	     tbl = tbl->next, t++) {
+	for (t = 0; t < NEIGH_NR_TABLES; t++) {
+		tbl = neigh_tables[t];
+
+		if (!tbl)
+			continue;
 		if (t < s_t || (family && tbl->family != family))
 			continue;
 		if (t > s_t)
@@ -2377,7 +2355,6 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 		if (err < 0)
 			break;
 	}
-	read_unlock(&neigh_tbl_lock);
 
 	cb->args[0] = t;
 	return skb->len;
diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c
index c8121ceddb9..7ca7c3143da 100644
--- a/net/decnet/dn_neigh.c
+++ b/net/decnet/dn_neigh.c
@@ -591,7 +591,7 @@ static const struct file_operations dn_neigh_seq_fops = {
 
 void __init dn_neigh_init(void)
 {
-	neigh_table_init(&dn_neigh_table);
+	neigh_table_init(NEIGH_DN_TABLE, &dn_neigh_table);
 	proc_create("decnet_neigh", S_IRUGO, init_net.proc_net,
 		    &dn_neigh_seq_fops);
 }
@@ -599,5 +599,5 @@ void __init dn_neigh_init(void)
 void __exit dn_neigh_cleanup(void)
 {
 	remove_proc_entry("decnet_neigh", init_net.proc_net);
-	neigh_table_clear(&dn_neigh_table);
+	neigh_table_clear(NEIGH_DN_TABLE, &dn_neigh_table);
 }
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 16acb59d665..205e1472aa7 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1292,7 +1292,7 @@ static int arp_proc_init(void);
 
 void __init arp_init(void)
 {
-	neigh_table_init(&arp_tbl);
+	neigh_table_init(NEIGH_ARP_TABLE, &arp_tbl);
 
 	dev_add_pack(&arp_packet_type);
 	arp_proc_init();
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 4cb45c1079a..2c9f6bf5732 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1763,7 +1763,7 @@ int __init ndisc_init(void)
 	/*
 	 * Initialize the neighbour table
 	 */
-	neigh_table_init(&nd_tbl);
+	neigh_table_init(NEIGH_ND_TABLE, &nd_tbl);
 
 #ifdef CONFIG_SYSCTL
 	err = neigh_sysctl_register(NULL, &nd_tbl.parms,
@@ -1796,6 +1796,6 @@ void ndisc_cleanup(void)
 #ifdef CONFIG_SYSCTL
 	neigh_sysctl_unregister(&nd_tbl.parms);
 #endif
-	neigh_table_clear(&nd_tbl);
+	neigh_table_clear(NEIGH_ND_TABLE, &nd_tbl);
 	unregister_pernet_subsys(&ndisc_net_ops);
 }
-- 
cgit v1.2.3-70-g09d2


From d65c4e4e0aeb699e984bd4b382efffab418aa359 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 11 Nov 2014 13:13:41 -0800
Subject: irda: Simplify IRDA logging macros

These are the same as net_<level>_ratelimited, so
use the more common style in the macro definition.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/irda/irda.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/irda/irda.h b/include/net/irda/irda.h
index a059465101f..42aa054aa67 100644
--- a/include/net/irda/irda.h
+++ b/include/net/irda/irda.h
@@ -77,9 +77,9 @@ do { if(!(expr)) { \
 #define IRDA_ASSERT_LABEL(label)
 #endif /* CONFIG_IRDA_DEBUG */
 
-#define IRDA_WARNING(args...) do { if (net_ratelimit()) printk(KERN_WARNING args); } while (0)
-#define IRDA_MESSAGE(args...) do { if (net_ratelimit()) printk(KERN_INFO args); } while (0)
-#define IRDA_ERROR(args...)   do { if (net_ratelimit()) printk(KERN_ERR args); } while (0)
+#define IRDA_ERROR		net_err_ratelimited
+#define IRDA_WARNING		net_warn_ratelimited
+#define IRDA_MESSAGE		net_info_ratelimited
 
 /*
  *  Magic numbers used by Linux-IrDA. Random numbers which must be unique to 
-- 
cgit v1.2.3-70-g09d2


From 09626e9d153326ca82568e4e27f2daa53713992e Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 11 Nov 2014 13:29:42 -0800
Subject: net: kill netif_copy_real_num_queues()

vlan was the only user of netif_copy_real_num_queues(),
but it no longer calls it after
commit 4af429d29b341bb1735f04c2fb960178 ("vlan: lockless transmit path").
So we can just remove it.

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 17 -----------------
 1 file changed, 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 888d5513fa4..4a6f770377d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2762,23 +2762,6 @@ static inline int netif_set_real_num_rx_queues(struct net_device *dev,
 }
 #endif
 
-static inline int netif_copy_real_num_queues(struct net_device *to_dev,
-					     const struct net_device *from_dev)
-{
-	int err;
-
-	err = netif_set_real_num_tx_queues(to_dev,
-					   from_dev->real_num_tx_queues);
-	if (err)
-		return err;
-#ifdef CONFIG_SYSFS
-	return netif_set_real_num_rx_queues(to_dev,
-					    from_dev->real_num_rx_queues);
-#else
-	return 0;
-#endif
-}
-
 #ifdef CONFIG_SYSFS
 static inline unsigned int get_netdev_rx_queue_index(
 		struct netdev_rx_queue *queue)
-- 
cgit v1.2.3-70-g09d2


From 85eb92e81801d64686eb78928d500a4c83ee9623 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Sat, 1 Nov 2014 16:54:55 +0100
Subject: bcma: make it possible to specify a IRQ num in bcma_core_irq()

This moves bcma_core_irq() to main.c and add a extra parameter with a
number so that we can return different irq number for devices with more
than one.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/bcma/driver_chipcommon.c      |  2 +-
 drivers/bcma/driver_gpio.c            |  4 ++--
 drivers/bcma/driver_mips.c            | 11 ++---------
 drivers/bcma/driver_pci_host.c        |  4 ++--
 drivers/bcma/main.c                   | 22 ++++++++++++++++++++++
 include/linux/bcma/bcma.h             |  2 ++
 include/linux/bcma/bcma_driver_mips.h |  4 ++--
 7 files changed, 33 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/bcma/driver_chipcommon.c b/drivers/bcma/driver_chipcommon.c
index b068f98920a..19f679667ca 100644
--- a/drivers/bcma/driver_chipcommon.c
+++ b/drivers/bcma/driver_chipcommon.c
@@ -339,7 +339,7 @@ void bcma_chipco_serial_init(struct bcma_drv_cc *cc)
 		return;
 	}
 
-	irq = bcma_core_irq(cc->core);
+	irq = bcma_core_irq(cc->core, 0);
 
 	/* Determine the registers of the UARTs */
 	cc->nr_serial_ports = (cc->capabilities & BCMA_CC_CAP_NRUART);
diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c
index 706b9ae0dcf..598a6cd9028 100644
--- a/drivers/bcma/driver_gpio.c
+++ b/drivers/bcma/driver_gpio.c
@@ -152,7 +152,7 @@ static int bcma_gpio_irq_domain_init(struct bcma_drv_cc *cc)
 					 handle_simple_irq);
 	}
 
-	hwirq = bcma_core_irq(cc->core);
+	hwirq = bcma_core_irq(cc->core, 0);
 	err = request_irq(hwirq, bcma_gpio_irq_handler, IRQF_SHARED, "gpio",
 			  cc);
 	if (err)
@@ -183,7 +183,7 @@ static void bcma_gpio_irq_domain_exit(struct bcma_drv_cc *cc)
 		return;
 
 	bcma_cc_mask32(cc, BCMA_CC_IRQMASK, ~BCMA_CC_IRQ_GPIO);
-	free_irq(bcma_core_irq(cc->core), cc);
+	free_irq(bcma_core_irq(cc->core, 0), cc);
 	for (gpio = 0; gpio < chip->ngpio; gpio++) {
 		int irq = irq_find_mapping(cc->irq_domain, gpio);
 
diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c
index 004d6aa671c..5ec69c3d409 100644
--- a/drivers/bcma/driver_mips.c
+++ b/drivers/bcma/driver_mips.c
@@ -115,7 +115,7 @@ static u32 bcma_core_mips_irqflag(struct bcma_device *dev)
  * If disabled, 5 is returned.
  * If not supported, 6 is returned.
  */
-static unsigned int bcma_core_mips_irq(struct bcma_device *dev)
+unsigned int bcma_core_mips_irq(struct bcma_device *dev)
 {
 	struct bcma_device *mdev = dev->bus->drv_mips.core;
 	u32 irqflag;
@@ -133,13 +133,6 @@ static unsigned int bcma_core_mips_irq(struct bcma_device *dev)
 	return 5;
 }
 
-unsigned int bcma_core_irq(struct bcma_device *dev)
-{
-	unsigned int mips_irq = bcma_core_mips_irq(dev);
-	return mips_irq <= 4 ? mips_irq + 2 : 0;
-}
-EXPORT_SYMBOL(bcma_core_irq);
-
 static void bcma_core_mips_set_irq(struct bcma_device *dev, unsigned int irq)
 {
 	unsigned int oldirq = bcma_core_mips_irq(dev);
@@ -423,7 +416,7 @@ void bcma_core_mips_init(struct bcma_drv_mips *mcore)
 		break;
 	default:
 		list_for_each_entry(core, &bus->cores, list) {
-			core->irq = bcma_core_irq(core);
+			core->irq = bcma_core_irq(core, 0);
 		}
 		bcma_err(bus,
 			 "Unknown device (0x%x) found, can not configure IRQs\n",
diff --git a/drivers/bcma/driver_pci_host.c b/drivers/bcma/driver_pci_host.c
index c3d7b03c2fd..c8a6b741967 100644
--- a/drivers/bcma/driver_pci_host.c
+++ b/drivers/bcma/driver_pci_host.c
@@ -593,7 +593,7 @@ int bcma_core_pci_plat_dev_init(struct pci_dev *dev)
 	pr_info("PCI: Fixing up device %s\n", pci_name(dev));
 
 	/* Fix up interrupt lines */
-	dev->irq = bcma_core_irq(pc_host->pdev->core);
+	dev->irq = bcma_core_irq(pc_host->pdev->core, 0);
 	pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq);
 
 	readrq = pcie_get_readrq(dev);
@@ -617,6 +617,6 @@ int bcma_core_pci_pcibios_map_irq(const struct pci_dev *dev)
 
 	pc_host = container_of(dev->bus->ops, struct bcma_drv_pci_host,
 			       pci_ops);
-	return bcma_core_irq(pc_host->pdev->core);
+	return bcma_core_irq(pc_host->pdev->core, 0);
 }
 EXPORT_SYMBOL(bcma_core_pci_pcibios_map_irq);
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index 9b229c9c35e..6d1cf570145 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -169,6 +169,28 @@ static void bcma_of_fill_device(struct platform_device *parent,
 }
 #endif /* CONFIG_OF */
 
+unsigned int bcma_core_irq(struct bcma_device *core, int num)
+{
+	struct bcma_bus *bus = core->bus;
+	unsigned int mips_irq;
+
+	switch (bus->hosttype) {
+	case BCMA_HOSTTYPE_PCI:
+		return bus->host_pci->irq;
+	case BCMA_HOSTTYPE_SOC:
+		if (bus->drv_mips.core && num == 0) {
+			mips_irq = bcma_core_mips_irq(core);
+			return mips_irq <= 4 ? mips_irq + 2 : 0;
+		}
+		break;
+	case BCMA_HOSTTYPE_SDIO:
+		return 0;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(bcma_core_irq);
+
 void bcma_prepare_core(struct bcma_bus *bus, struct bcma_device *core)
 {
 	core->dev.release = bcma_release_core_dev;
diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h
index 729f48e6b20..eb1c6a47b67 100644
--- a/include/linux/bcma/bcma.h
+++ b/include/linux/bcma/bcma.h
@@ -447,4 +447,6 @@ extern u32 bcma_chipco_pll_read(struct bcma_drv_cc *cc, u32 offset);
 #define  BCMA_DMA_TRANSLATION_DMA64_CMT	0x80000000 /* Client Mode Translation for 64-bit DMA */
 extern u32 bcma_core_dma_translation(struct bcma_device *core);
 
+extern unsigned int bcma_core_irq(struct bcma_device *core, int num);
+
 #endif /* LINUX_BCMA_H_ */
diff --git a/include/linux/bcma/bcma_driver_mips.h b/include/linux/bcma/bcma_driver_mips.h
index fb61f3fb4dd..0b3b32aeeb8 100644
--- a/include/linux/bcma/bcma_driver_mips.h
+++ b/include/linux/bcma/bcma_driver_mips.h
@@ -43,12 +43,12 @@ struct bcma_drv_mips {
 extern void bcma_core_mips_init(struct bcma_drv_mips *mcore);
 extern void bcma_core_mips_early_init(struct bcma_drv_mips *mcore);
 
-extern unsigned int bcma_core_irq(struct bcma_device *core);
+extern unsigned int bcma_core_mips_irq(struct bcma_device *dev);
 #else
 static inline void bcma_core_mips_init(struct bcma_drv_mips *mcore) { }
 static inline void bcma_core_mips_early_init(struct bcma_drv_mips *mcore) { }
 
-static inline unsigned int bcma_core_irq(struct bcma_device *core)
+static inline unsigned int bcma_core_mips_irq(struct bcma_device *dev)
 {
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From 03f56e42d03eb7d0a47e40e9ae72a3ac0afeff08 Mon Sep 17 00:00:00 2001
From: Yijing Wang <wangyijing@huawei.com>
Date: Mon, 27 Oct 2014 10:44:37 +0800
Subject: Revert "PCI: Add x86_msi.msi_mask_irq() and msix_mask_irq()"

The problem fixed by 0e4ccb1505a9 ("PCI: Add x86_msi.msi_mask_irq() and
msix_mask_irq()") has been fixed in a simpler way by a previous commit
("PCI/MSI: Add pci_msi_ignore_mask to prevent writes to MSI/MSI-X Mask
Bits").

The msi_mask_irq() and msix_mask_irq() x86_msi_ops added by 0e4ccb1505a9
are no longer needed, so revert the commit.

default_msi_mask_irq() and default_msix_mask_irq() were added by
0e4ccb1505a9 and are still used by s390, so keep them for now.

[bhelgaas: changelog]
Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: David Vrabel <david.vrabel@citrix.com>
CC: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
CC: xen-devel@lists.xenproject.org
---
 arch/x86/include/asm/x86_init.h |  3 ---
 arch/x86/kernel/x86_init.c      | 10 ----------
 arch/x86/pci/xen.c              | 13 +------------
 drivers/pci/msi.c               | 22 ++++++----------------
 include/linux/msi.h             |  6 ++++--
 5 files changed, 11 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index e45e4da96bf..f58a9c7a3c8 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -172,7 +172,6 @@ struct x86_platform_ops {
 
 struct pci_dev;
 struct msi_msg;
-struct msi_desc;
 
 struct x86_msi_ops {
 	int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
@@ -183,8 +182,6 @@ struct x86_msi_ops {
 	void (*teardown_msi_irqs)(struct pci_dev *dev);
 	void (*restore_msi_irqs)(struct pci_dev *dev);
 	int  (*setup_hpet_msi)(unsigned int irq, unsigned int id);
-	u32 (*msi_mask_irq)(struct msi_desc *desc, u32 mask, u32 flag);
-	u32 (*msix_mask_irq)(struct msi_desc *desc, u32 flag);
 };
 
 struct IO_APIC_route_entry;
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index e48b674639c..234b0722de5 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -116,8 +116,6 @@ struct x86_msi_ops x86_msi = {
 	.teardown_msi_irqs	= default_teardown_msi_irqs,
 	.restore_msi_irqs	= default_restore_msi_irqs,
 	.setup_hpet_msi		= default_setup_hpet_msi,
-	.msi_mask_irq		= default_msi_mask_irq,
-	.msix_mask_irq		= default_msix_mask_irq,
 };
 
 /* MSI arch specific hooks */
@@ -140,14 +138,6 @@ void arch_restore_msi_irqs(struct pci_dev *dev)
 {
 	x86_msi.restore_msi_irqs(dev);
 }
-u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
-{
-	return x86_msi.msi_mask_irq(desc, mask, flag);
-}
-u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag)
-{
-	return x86_msi.msix_mask_irq(desc, flag);
-}
 #endif
 
 struct x86_io_apic_ops x86_io_apic_ops = {
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 5ef62ed20ba..466b978e13a 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -394,14 +394,7 @@ static void xen_teardown_msi_irq(unsigned int irq)
 {
 	xen_destroy_irq(irq);
 }
-static u32 xen_nop_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
-{
-	return 0;
-}
-static u32 xen_nop_msix_mask_irq(struct msi_desc *desc, u32 flag)
-{
-	return 0;
-}
+
 #endif
 
 int __init pci_xen_init(void)
@@ -425,8 +418,6 @@ int __init pci_xen_init(void)
 	x86_msi.setup_msi_irqs = xen_setup_msi_irqs;
 	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
 	x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs;
-	x86_msi.msi_mask_irq = xen_nop_msi_mask_irq;
-	x86_msi.msix_mask_irq = xen_nop_msix_mask_irq;
 	pci_msi_ignore_mask = 1;
 #endif
 	return 0;
@@ -507,8 +498,6 @@ int __init pci_xen_initial_domain(void)
 	x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs;
 	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
 	x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs;
-	x86_msi.msi_mask_irq = xen_nop_msi_mask_irq;
-	x86_msi.msix_mask_irq = xen_nop_msix_mask_irq;
 	pci_msi_ignore_mask = 1;
 #endif
 	xen_setup_acpi_sci();
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 066c2fb9763..d9a92cf6a6d 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -164,7 +164,7 @@ static inline __attribute_const__ u32 msi_mask(unsigned x)
  * reliably as devices without an INTx disable bit will then generate a
  * level IRQ which will never be cleared.
  */
-u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 {
 	u32 mask_bits = desc->masked;
 
@@ -178,14 +178,9 @@ u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 	return mask_bits;
 }
 
-__weak u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
-{
-	return default_msi_mask_irq(desc, mask, flag);
-}
-
 static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 {
-	desc->masked = arch_msi_mask_irq(desc, mask, flag);
+	desc->masked = __msi_mask_irq(desc, mask, flag);
 }
 
 /*
@@ -195,7 +190,7 @@ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
  * file.  This saves a few milliseconds when initialising devices with lots
  * of MSI-X interrupts.
  */
-u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag)
+u32 __msix_mask_irq(struct msi_desc *desc, u32 flag)
 {
 	u32 mask_bits = desc->masked;
 	unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
@@ -212,14 +207,9 @@ u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag)
 	return mask_bits;
 }
 
-__weak u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag)
-{
-	return default_msix_mask_irq(desc, flag);
-}
-
 static void msix_mask_irq(struct msi_desc *desc, u32 flag)
 {
-	desc->masked = arch_msix_mask_irq(desc, flag);
+	desc->masked = __msix_mask_irq(desc, flag);
 }
 
 static void msi_set_mask_bit(struct irq_data *data, u32 flag)
@@ -874,7 +864,7 @@ void pci_msi_shutdown(struct pci_dev *dev)
 	/* Return the device with MSI unmasked as initial states */
 	mask = msi_mask(desc->msi_attrib.multi_cap);
 	/* Keep cached state to be restored */
-	arch_msi_mask_irq(desc, mask, ~mask);
+	__msi_mask_irq(desc, mask, ~mask);
 
 	/* Restore dev->irq to its default pin-assertion irq */
 	dev->irq = desc->msi_attrib.default_irq;
@@ -972,7 +962,7 @@ void pci_msix_shutdown(struct pci_dev *dev)
 	/* Return the device with MSI-X masked as initial states */
 	list_for_each_entry(entry, &dev->msi_list, list) {
 		/* Keep cached states to be restored */
-		arch_msix_mask_irq(entry, 1);
+		__msix_mask_irq(entry, 1);
 	}
 
 	msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 86dc501a153..f6630a53be7 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -22,6 +22,8 @@ void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void read_msi_msg(unsigned int irq, struct msi_msg *msg);
 void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg);
 void write_msi_msg(unsigned int irq, struct msi_msg *msg);
+u32 __msix_mask_irq(struct msi_desc *desc, u32 flag);
+u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag);
 
 struct msi_desc {
 	struct {
@@ -62,8 +64,8 @@ void arch_restore_msi_irqs(struct pci_dev *dev);
 
 void default_teardown_msi_irqs(struct pci_dev *dev);
 void default_restore_msi_irqs(struct pci_dev *dev);
-u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag);
-u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag);
+#define default_msi_mask_irq  __msi_mask_irq
+#define default_msix_mask_irq  __msix_mask_irq
 
 struct msi_chip {
 	struct module *owner;
-- 
cgit v1.2.3-70-g09d2


From f8338694270224970cbaae7e404517ec39f9c753 Mon Sep 17 00:00:00 2001
From: Yijing Wang <wangyijing@huawei.com>
Date: Mon, 27 Oct 2014 10:44:38 +0800
Subject: s390/MSI: Use __msi_mask_irq() instead of default_msi_mask_irq()

Now only s390/MSI use default_msi_mask_irq() and default_msix_mask_irq(),
replace them with the common MSI mask IRQ functions __msi_mask_irq() and
__msix_mask_irq().  Remove default_msi_mask_irq() and
default_msix_mask_irq().

Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
CC: linux-s390@vger.kernel.org
---
 arch/s390/pci/pci.c | 4 ++--
 include/linux/msi.h | 2 --
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 2fa7b14b9c0..552b9908aa7 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -448,9 +448,9 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
 	/* Release MSI interrupts */
 	list_for_each_entry(msi, &pdev->msi_list, list) {
 		if (msi->msi_attrib.is_msix)
-			default_msix_mask_irq(msi, 1);
+			__msix_mask_irq(msi, 1);
 		else
-			default_msi_mask_irq(msi, 1, 1);
+			__msi_mask_irq(msi, 1, 1);
 		irq_set_msi_desc(msi->irq, NULL);
 		irq_free_desc(msi->irq);
 		msi->msg.address_lo = 0;
diff --git a/include/linux/msi.h b/include/linux/msi.h
index f6630a53be7..efad12742e4 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -64,8 +64,6 @@ void arch_restore_msi_irqs(struct pci_dev *dev);
 
 void default_teardown_msi_irqs(struct pci_dev *dev);
 void default_restore_msi_irqs(struct pci_dev *dev);
-#define default_msi_mask_irq  __msi_mask_irq
-#define default_msix_mask_irq  __msix_mask_irq
 
 struct msi_chip {
 	struct module *owner;
-- 
cgit v1.2.3-70-g09d2


From 24119a8829cdaf299294095ec568bf49e863c5a5 Mon Sep 17 00:00:00 2001
From: Hanjun Guo <hanjun.guo@linaro.org>
Date: Thu, 30 Oct 2014 17:52:58 +0800
Subject: ACPI / processor: Update the comments in processor.h

In commit 46ba51e (ACPI / processor: Introduce ARCH_MIGHT_HAVE_ACPI_PDC),
acpi_processor_set_pdc() was moved to processor_pdc.c, so update
the comments accordingly.

Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/processor.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 9b9b6f29bbf..cbb6cd3a98d 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -313,11 +313,13 @@ static inline int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
 #endif				/* CONFIG_CPU_FREQ */
 
 /* in processor_core.c */
-void acpi_processor_set_pdc(acpi_handle handle);
 int acpi_get_apicid(acpi_handle, int type, u32 acpi_id);
 int acpi_map_cpuid(int apic_id, u32 acpi_id);
 int acpi_get_cpuid(acpi_handle, int type, u32 acpi_id);
 
+/* in processor_pdc.c */
+void acpi_processor_set_pdc(acpi_handle handle);
+
 /* in processor_throttling.c */
 int acpi_processor_tstate_has_changed(struct acpi_processor *pr);
 int acpi_processor_get_throttling_info(struct acpi_processor *pr);
-- 
cgit v1.2.3-70-g09d2


From 6c91023dc35c88d5e6aebe4bfe6f1ed5ec2b84be Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 11 Nov 2014 13:37:30 -0800
Subject: irda: Remove IRDA_<TYPE> logging macros

And use the more common mechanisms directly.

Other miscellanea:

o Coalesce formats
o Add missing newlines
o Realign arguments
o Remove unnecessary OOM message logging as
  there's a generic stack dump already on OOM.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/irda/act200l-sir.c      |   3 +-
 drivers/net/irda/ali-ircc.c         |  57 ++++++++--------
 drivers/net/irda/girbil-sir.c       |   6 +-
 drivers/net/irda/irda-usb.c         |  47 +++++++------
 drivers/net/irda/irtty-sir.c        |  10 +--
 drivers/net/irda/ma600-sir.c        |   6 +-
 drivers/net/irda/mcp2120-sir.c      |   6 +-
 drivers/net/irda/mcs7780.c          |  45 +++++++------
 drivers/net/irda/nsc-ircc.c         |  66 +++++++++---------
 drivers/net/irda/sir_dev.c          |  35 +++++-----
 drivers/net/irda/smsc-ircc2.c       | 130 +++++++++++++++++++-----------------
 drivers/net/irda/tekram-sir.c       |   3 +-
 drivers/net/irda/via-ircc.c         |  21 +++---
 drivers/net/irda/vlsi_ir.c          | 118 +++++++++++++++++---------------
 drivers/net/irda/vlsi_ir.h          |   3 +-
 drivers/net/irda/w83977af_ir.c      |   9 +--
 include/net/irda/irda.h             |   4 --
 net/irda/af_irda.c                  |  34 +++++-----
 net/irda/ircomm/ircomm_core.c       |   5 +-
 net/irda/ircomm/ircomm_lmp.c        |   2 +-
 net/irda/ircomm/ircomm_param.c      |   3 +-
 net/irda/ircomm/ircomm_ttp.c        |  10 +--
 net/irda/ircomm/ircomm_tty.c        |  21 +++---
 net/irda/ircomm/ircomm_tty_attach.c |  12 ++--
 net/irda/ircomm/ircomm_tty_ioctl.c  |   3 +-
 net/irda/irda_device.c              |  18 ++---
 net/irda/iriap.c                    |  24 +++----
 net/irda/iriap_event.c              |   4 +-
 net/irda/irias_object.c             |  64 ++++++++----------
 net/irda/irlan/irlan_client.c       |  22 +++---
 net/irda/irlan/irlan_client_event.c |   4 +-
 net/irda/irlan/irlan_common.c       |   3 +-
 net/irda/irlan/irlan_eth.c          |   2 +-
 net/irda/irlap.c                    |  15 +++--
 net/irda/irlap_event.c              |   5 +-
 net/irda/irlap_frame.c              |  30 ++++-----
 net/irda/irlmp.c                    |  19 +++---
 net/irda/irlmp_event.c              |   8 +--
 net/irda/irttp.c                    |  31 ++++-----
 net/irda/parameters.c               |  39 +++++------
 net/irda/qos.c                      |  12 ++--
 net/irda/wrapper.c                  |   6 +-
 42 files changed, 486 insertions(+), 479 deletions(-)

(limited to 'include')

diff --git a/drivers/net/irda/act200l-sir.c b/drivers/net/irda/act200l-sir.c
index 8ff084f1d23..a9116456bc9 100644
--- a/drivers/net/irda/act200l-sir.c
+++ b/drivers/net/irda/act200l-sir.c
@@ -240,7 +240,8 @@ static int act200l_reset(struct sir_dev *dev)
 		dev->speed = 9600;
 		break;
 	default:
-		IRDA_ERROR("%s(), unknown state %d\n", __func__, state);
+		net_err_ratelimited("%s(), unknown state %d\n",
+				    __func__, state);
 		ret = -1;
 		break;
 	}
diff --git a/drivers/net/irda/ali-ircc.c b/drivers/net/irda/ali-ircc.c
index befa45f809c..7f23e5ff099 100644
--- a/drivers/net/irda/ali-ircc.c
+++ b/drivers/net/irda/ali-ircc.c
@@ -158,8 +158,8 @@ static int __init ali_ircc_init(void)
 
 	ret = platform_driver_register(&ali_ircc_driver);
         if (ret) {
-                IRDA_ERROR("%s, Can't register driver!\n",
-			   ALI_IRCC_DRIVER_NAME);
+		net_err_ratelimited("%s, Can't register driver!\n",
+				    ALI_IRCC_DRIVER_NAME);
                 return ret;
         }
 
@@ -292,8 +292,8 @@ static int ali_ircc_open(int i, chipio_t *info)
 	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__);
 
 	if (i >= ARRAY_SIZE(dev_self)) {
-		IRDA_ERROR("%s(), maximum number of supported chips reached!\n",
-			   __func__);
+		net_err_ratelimited("%s(), maximum number of supported chips reached!\n",
+				    __func__);
 		return -ENOMEM;
 	}
 	
@@ -303,8 +303,8 @@ static int ali_ircc_open(int i, chipio_t *info)
 		
 	dev = alloc_irdadev(sizeof(*self));
 	if (dev == NULL) {
-		IRDA_ERROR("%s(), can't allocate memory for control block!\n",
-			   __func__);
+		net_err_ratelimited("%s(), can't allocate memory for control block!\n",
+				    __func__);
 		return -ENOMEM;
 	}
 
@@ -328,8 +328,8 @@ static int ali_ircc_open(int i, chipio_t *info)
 	/* Reserve the ioports that we need */
 	if (!request_region(self->io.fir_base, self->io.fir_ext,
 			    ALI_IRCC_DRIVER_NAME)) {
-		IRDA_WARNING("%s(), can't get iobase of 0x%03x\n", __func__,
-			self->io.fir_base);
+		net_warn_ratelimited("%s(), can't get iobase of 0x%03x\n",
+				     __func__, self->io.fir_base);
 		err = -ENODEV;
 		goto err_out1;
 	}
@@ -380,15 +380,17 @@ static int ali_ircc_open(int i, chipio_t *info)
 
 	err = register_netdev(dev);
 	if (err) {
-		IRDA_ERROR("%s(), register_netdev() failed!\n", __func__);
+		net_err_ratelimited("%s(), register_netdev() failed!\n",
+				    __func__);
 		goto err_out4;
 	}
-	IRDA_MESSAGE("IrDA: Registered device %s\n", dev->name);
+	net_info_ratelimited("IrDA: Registered device %s\n", dev->name);
 
 	/* Check dongle id */
 	dongle_id = ali_ircc_read_dongle_id(i, info);
-	IRDA_MESSAGE("%s(), %s, Found dongle: %s\n", __func__,
-		     ALI_IRCC_DRIVER_NAME, dongle_types[dongle_id]);
+	net_info_ratelimited("%s(), %s, Found dongle: %s\n",
+			     __func__, ALI_IRCC_DRIVER_NAME,
+			     dongle_types[dongle_id]);
 		
 	self->io.dongle_id = dongle_id;
 
@@ -521,7 +523,8 @@ static int ali_ircc_probe_53(ali_chip_t *chip, chipio_t *info)
 	info->dma = reg & 0x07;
 	
 	if(info->dma == 0x04)
-		IRDA_WARNING("%s(), No DMA channel assigned !\n", __func__);
+		net_warn_ratelimited("%s(), No DMA channel assigned !\n",
+				     __func__);
 	else
 		IRDA_DEBUG(2, "%s(), probing dma=%d\n", __func__, info->dma);
 	
@@ -578,8 +581,8 @@ static int ali_ircc_setup(chipio_t *info)
 	/* Should be 0x00 in the M1535/M1535D */
 	if(version != 0x00)
 	{
-		IRDA_ERROR("%s, Wrong chip version %02x\n",
-			   ALI_IRCC_DRIVER_NAME, version);
+		net_err_ratelimited("%s, Wrong chip version %02x\n",
+				    ALI_IRCC_DRIVER_NAME, version);
 		return -1;
 	}
 	
@@ -612,8 +615,8 @@ static int ali_ircc_setup(chipio_t *info)
 	/* Switch to SIR space */
 	FIR2SIR(iobase);
 	
-	IRDA_MESSAGE("%s, driver loaded (Benjamin Kong)\n",
-		     ALI_IRCC_DRIVER_NAME);
+	net_info_ratelimited("%s, driver loaded (Benjamin Kong)\n",
+			     ALI_IRCC_DRIVER_NAME);
 	
 	/* Enable receive interrupts */ 
 	// outb(UART_IER_RDI, iobase+UART_IER); //benjamin 2000/11/23 01:25PM
@@ -1352,9 +1355,8 @@ static int ali_ircc_net_open(struct net_device *dev)
 	/* Request IRQ and install Interrupt Handler */
 	if (request_irq(self->io.irq, ali_ircc_interrupt, 0, dev->name, dev)) 
 	{
-		IRDA_WARNING("%s, unable to allocate irq=%d\n",
-			     ALI_IRCC_DRIVER_NAME,
-			     self->io.irq);
+		net_warn_ratelimited("%s, unable to allocate irq=%d\n",
+				     ALI_IRCC_DRIVER_NAME, self->io.irq);
 		return -EAGAIN;
 	}
 	
@@ -1363,9 +1365,8 @@ static int ali_ircc_net_open(struct net_device *dev)
 	 * failure.
 	 */
 	if (request_dma(self->io.dma, dev->name)) {
-		IRDA_WARNING("%s, unable to allocate dma=%d\n",
-			     ALI_IRCC_DRIVER_NAME,
-			     self->io.dma);
+		net_warn_ratelimited("%s, unable to allocate dma=%d\n",
+				     ALI_IRCC_DRIVER_NAME, self->io.dma);
 		free_irq(self->io.irq, dev);
 		return -EAGAIN;
 	}
@@ -1671,7 +1672,8 @@ static int  ali_ircc_dma_xmit_complete(struct ali_ircc_cb *self)
 	if((inb(iobase+FIR_LSR) & LSR_FRAME_ABORT) == LSR_FRAME_ABORT)
 	
 	{
-		IRDA_ERROR("%s(), ********* LSR_FRAME_ABORT *********\n", __func__);
+		net_err_ratelimited("%s(), ********* LSR_FRAME_ABORT *********\n",
+				    __func__);
 		self->netdev->stats.tx_errors++;
 		self->netdev->stats.tx_fifo_errors++;
 	}
@@ -1918,9 +1920,6 @@ static int  ali_ircc_dma_receive_complete(struct ali_ircc_cb *self)
 			skb = dev_alloc_skb(len+1);
 			if (skb == NULL)  
 			{
-				IRDA_WARNING("%s(), memory squeeze, "
-					     "dropping frame.\n",
-					     __func__);
 				self->netdev->stats.rx_dropped++;
 
 				return FALSE;
@@ -2127,7 +2126,7 @@ static int ali_ircc_suspend(struct platform_device *dev, pm_message_t state)
 {
 	struct ali_ircc_cb *self = platform_get_drvdata(dev);
 	
-	IRDA_MESSAGE("%s, Suspending\n", ALI_IRCC_DRIVER_NAME);
+	net_info_ratelimited("%s, Suspending\n", ALI_IRCC_DRIVER_NAME);
 
 	if (self->io.suspended)
 		return 0;
@@ -2148,7 +2147,7 @@ static int ali_ircc_resume(struct platform_device *dev)
 	
 	ali_ircc_net_open(self->netdev);
 	
-	IRDA_MESSAGE("%s, Waking up\n", ALI_IRCC_DRIVER_NAME);
+	net_info_ratelimited("%s, Waking up\n", ALI_IRCC_DRIVER_NAME);
 
 	self->io.suspended = 0;
 
diff --git a/drivers/net/irda/girbil-sir.c b/drivers/net/irda/girbil-sir.c
index 96cdecff349..f0512ad7dae 100644
--- a/drivers/net/irda/girbil-sir.c
+++ b/drivers/net/irda/girbil-sir.c
@@ -179,7 +179,8 @@ static int girbil_change_speed(struct sir_dev *dev, unsigned speed)
 		break;
 
 	default:
-		IRDA_ERROR("%s - undefined state %d\n", __func__, state);
+		net_err_ratelimited("%s - undefined state %d\n",
+				    __func__, state);
 		ret = -EINVAL;
 		break;
 	}
@@ -241,7 +242,8 @@ static int girbil_reset(struct sir_dev *dev)
 		break;
 
 	default:
-		IRDA_ERROR("%s(), undefined state %d\n", __func__, state);
+		net_err_ratelimited("%s(), undefined state %d\n",
+				    __func__, state);
 		ret = -1;
 		break;
 	}
diff --git a/drivers/net/irda/irda-usb.c b/drivers/net/irda/irda-usb.c
index 925b78cc979..e9aedbe3fc9 100644
--- a/drivers/net/irda/irda-usb.c
+++ b/drivers/net/irda/irda-usb.c
@@ -307,7 +307,7 @@ static void irda_usb_change_speed_xbofs(struct irda_usb_cb *self)
 	/* Grab the speed URB */
 	urb = self->speed_urb;
 	if (urb->status != 0) {
-		IRDA_WARNING("%s(), URB still in use!\n", __func__);
+		net_warn_ratelimited("%s(), URB still in use!\n", __func__);
 		return;
 	}
 
@@ -333,7 +333,7 @@ static void irda_usb_change_speed_xbofs(struct irda_usb_cb *self)
 
 	/* Irq disabled -> GFP_ATOMIC */
 	if ((ret = usb_submit_urb(urb, GFP_ATOMIC))) {
-		IRDA_WARNING("%s(), failed Speed URB\n", __func__);
+		net_warn_ratelimited("%s(), failed Speed URB\n", __func__);
 	}
 }
 
@@ -435,7 +435,7 @@ static netdev_tx_t irda_usb_hard_xmit(struct sk_buff *skb,
 	}
 
 	if (urb->status != 0) {
-		IRDA_WARNING("%s(), URB still in use!\n", __func__);
+		net_warn_ratelimited("%s(), URB still in use!\n", __func__);
 		goto drop;
 	}
 
@@ -522,7 +522,7 @@ static netdev_tx_t irda_usb_hard_xmit(struct sk_buff *skb,
 	
 	/* Ask USB to send the packet - Irq disabled -> GFP_ATOMIC */
 	if ((res = usb_submit_urb(urb, GFP_ATOMIC))) {
-		IRDA_WARNING("%s(), failed Tx URB\n", __func__);
+		net_warn_ratelimited("%s(), failed Tx URB\n", __func__);
 		netdev->stats.tx_errors++;
 		/* Let USB recover : We will catch that in the watchdog */
 		/*netif_start_queue(netdev);*/
@@ -638,7 +638,7 @@ static void irda_usb_net_timeout(struct net_device *netdev)
 
 	/* self->present *MUST* be read under spinlock */
 	if (!self->present) {
-		IRDA_WARNING("%s(), device not present!\n", __func__);
+		net_warn_ratelimited("%s(), device not present!\n", __func__);
 		netif_stop_queue(netdev);
 		spin_unlock_irqrestore(&self->lock, flags);
 		return;
@@ -783,8 +783,8 @@ static void irda_usb_submit(struct irda_usb_cb *self, struct sk_buff *skb, struc
 	if (ret) {
 		/* If this ever happen, we are in deep s***.
 		 * Basically, the Rx path will stop... */
-		IRDA_WARNING("%s(), Failed to submit Rx URB %d\n",
-			     __func__, ret);
+		net_warn_ratelimited("%s(), Failed to submit Rx URB %d\n",
+				     __func__, ret);
 	}
 }
 
@@ -859,7 +859,7 @@ static void irda_usb_receive(struct urb *urb)
 	
 	/* Check for empty frames */
 	if (urb->actual_length <= self->header_length) {
-		IRDA_WARNING("%s(), empty frame!\n", __func__);
+		net_warn_ratelimited("%s(), empty frame!\n", __func__);
 		goto done;
 	}
 
@@ -1088,8 +1088,8 @@ static int stir421x_patch_device(struct irda_usb_cb *self)
                 return ret;
 
         /* We get a patch from userspace */
-        IRDA_MESSAGE("%s(): Received firmware %s (%zu bytes)\n",
-                     __func__, stir421x_fw_name, fw->size);
+	net_info_ratelimited("%s(): Received firmware %s (%zu bytes)\n",
+			     __func__, stir421x_fw_name, fw->size);
 
         ret = -EINVAL;
 
@@ -1179,13 +1179,13 @@ static int irda_usb_net_open(struct net_device *netdev)
 	/* Can only open the device if it's there */
 	if(!self->present) {
 		spin_unlock_irqrestore(&self->lock, flags);
-		IRDA_WARNING("%s(), device not present!\n", __func__);
+		net_warn_ratelimited("%s(), device not present!\n", __func__);
 		return -1;
 	}
 
 	if(self->needspatch) {
 		spin_unlock_irqrestore(&self->lock, flags);
-		IRDA_WARNING("%s(), device needs patch\n", __func__) ;
+		net_warn_ratelimited("%s(), device needs patch\n", __func__);
 		return -EIO ;
 	}
 
@@ -1227,8 +1227,6 @@ static int irda_usb_net_open(struct net_device *netdev)
 		if (!skb) {
 			/* If this ever happen, we are in deep s***.
 			 * Basically, we can't start the Rx path... */
-			IRDA_WARNING("%s(), Failed to allocate Rx skb\n",
-				     __func__);
 			return -1;
 		}
 		//skb_reserve(newskb, USB_IRDA_HEADER - 1);
@@ -1505,7 +1503,8 @@ static inline int irda_usb_parse_endpoints(struct irda_usb_cb *self, struct usb_
 				/* This is our interrupt endpoint */
 				self->bulk_int_ep = ep;
 			} else {
-				IRDA_ERROR("%s(), Unrecognised endpoint %02X.\n", __func__, ep);
+				net_err_ratelimited("%s(), Unrecognised endpoint %02X\n",
+						    __func__, ep);
 			}
 		}
 	}
@@ -1575,11 +1574,11 @@ static inline struct irda_class_desc *irda_usb_find_class_desc(struct usb_interf
 	
 	IRDA_DEBUG(1, "%s(), ret=%d\n", __func__, ret);
 	if (ret < sizeof(*desc)) {
-		IRDA_WARNING("usb-irda: class_descriptor read %s (%d)\n",
-			     (ret<0) ? "failed" : "too short", ret);
+		net_warn_ratelimited("usb-irda: class_descriptor read %s (%d)\n",
+				     ret < 0 ? "failed" : "too short", ret);
 	}
 	else if (desc->bDescriptorType != USB_DT_IRDA) {
-		IRDA_WARNING("usb-irda: bad class_descriptor type\n");
+		net_warn_ratelimited("usb-irda: bad class_descriptor type\n");
 	}
 	else {
 #ifdef IU_DUMP_CLASS_DESC
@@ -1622,9 +1621,9 @@ static int irda_usb_probe(struct usb_interface *intf,
 	 * don't need to check if the dongle is really ours.
 	 * Jean II */
 
-	IRDA_MESSAGE("IRDA-USB found at address %d, Vendor: %x, Product: %x\n",
-		     dev->devnum, le16_to_cpu(dev->descriptor.idVendor),
-		     le16_to_cpu(dev->descriptor.idProduct));
+	net_info_ratelimited("IRDA-USB found at address %d, Vendor: %x, Product: %x\n",
+			     dev->devnum, le16_to_cpu(dev->descriptor.idVendor),
+			     le16_to_cpu(dev->descriptor.idProduct));
 
 	net = alloc_irdadev(sizeof(*self));
 	if (!net) 
@@ -1700,7 +1699,7 @@ static int irda_usb_probe(struct usb_interface *intf,
 	interface = intf->cur_altsetting;
 	if(!irda_usb_parse_endpoints(self, interface->endpoint,
 				     interface->desc.bNumEndpoints)) {
-		IRDA_ERROR("%s(), Bogus endpoints...\n", __func__);
+		net_err_ratelimited("%s(), Bogus endpoints...\n", __func__);
 		ret = -EIO;
 		goto err_out_3;
 	}
@@ -1746,7 +1745,7 @@ static int irda_usb_probe(struct usb_interface *intf,
 	if (ret) 
 		goto err_out_5;
 
-	IRDA_MESSAGE("IrDA: Registered device %s\n", net->name);
+	net_info_ratelimited("IrDA: Registered device %s\n", net->name);
 	usb_set_intfdata(intf, self);
 
 	if (self->needspatch) {
@@ -1754,7 +1753,7 @@ static int irda_usb_probe(struct usb_interface *intf,
 		ret = stir421x_patch_device(self);
 		self->needspatch = (ret < 0);
 		if (self->needspatch) {
-			IRDA_ERROR("STIR421X: Couldn't upload patch\n");
+			net_err_ratelimited("STIR421X: Couldn't upload patch\n");
 			goto err_out_6;
 		}
 
diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c
index 24b6dddd7f2..abbb654c066 100644
--- a/drivers/net/irda/irtty-sir.c
+++ b/drivers/net/irda/irtty-sir.c
@@ -231,7 +231,7 @@ static void irtty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
 
 	dev = priv->dev;
 	if (!dev) {
-		IRDA_WARNING("%s(), not ready yet!\n", __func__);
+		net_warn_ratelimited("%s(), not ready yet!\n", __func__);
 		return;
 	}
 
@@ -555,8 +555,8 @@ static int __init irtty_sir_init(void)
 	int err;
 
 	if ((err = tty_register_ldisc(N_IRDA, &irda_ldisc)) != 0)
-		IRDA_ERROR("IrDA: can't register line discipline (err = %d)\n",
-			   err);
+		net_err_ratelimited("IrDA: can't register line discipline (err = %d)\n",
+				    err);
 	return err;
 }
 
@@ -565,8 +565,8 @@ static void __exit irtty_sir_cleanup(void)
 	int err;
 
 	if ((err = tty_unregister_ldisc(N_IRDA))) {
-		IRDA_ERROR("%s(), can't unregister line discipline (err = %d)\n",
-			   __func__, err);
+		net_err_ratelimited("%s(), can't unregister line discipline (err = %d)\n",
+				    __func__, err);
 	}
 }
 
diff --git a/drivers/net/irda/ma600-sir.c b/drivers/net/irda/ma600-sir.c
index a9a81358477..944d044510e 100644
--- a/drivers/net/irda/ma600-sir.c
+++ b/drivers/net/irda/ma600-sir.c
@@ -198,9 +198,9 @@ static int ma600_change_speed(struct sir_dev *dev, unsigned speed)
 
 	sirdev_raw_read(dev, &byte, sizeof(byte));
 	if (byte != get_control_byte(speed))  {
-		IRDA_WARNING("%s(): bad control byte read-back %02x != %02x\n",
-			     __func__, (unsigned) byte,
-			     (unsigned) get_control_byte(speed));
+		net_warn_ratelimited("%s(): bad control byte read-back %02x != %02x\n",
+				     __func__, (unsigned)byte,
+				     (unsigned)get_control_byte(speed));
 		return -1;
 	}
 	else
diff --git a/drivers/net/irda/mcp2120-sir.c b/drivers/net/irda/mcp2120-sir.c
index 5e2f4859cee..97674695211 100644
--- a/drivers/net/irda/mcp2120-sir.c
+++ b/drivers/net/irda/mcp2120-sir.c
@@ -155,7 +155,8 @@ static int mcp2120_change_speed(struct sir_dev *dev, unsigned speed)
 		break;
 
 	default:
-		IRDA_ERROR("%s(), undefine state %d\n", __func__, state);
+		net_err_ratelimited("%s(), undefine state %d\n",
+				    __func__, state);
 		ret = -EINVAL;
 		break;
 	}
@@ -213,7 +214,8 @@ static int mcp2120_reset(struct sir_dev *dev)
 		break;
 
 	default:
-		IRDA_ERROR("%s(), undefined state %d\n", __func__, state);
+		net_err_ratelimited("%s(), undefined state %d\n",
+				    __func__, state);
 		ret = -EINVAL;
 		break;
 	}
diff --git a/drivers/net/irda/mcs7780.c b/drivers/net/irda/mcs7780.c
index 16f8ffb50e0..6cbd29dcf2d 100644
--- a/drivers/net/irda/mcs7780.c
+++ b/drivers/net/irda/mcs7780.c
@@ -197,14 +197,14 @@ error:
 /* Setup a communication between mcs7780 and agilent chip. */
 static inline int mcs_setup_transceiver_agilent(struct mcs_cb *mcs)
 {
-	IRDA_WARNING("This transceiver type is not supported yet.\n");
+	net_warn_ratelimited("This transceiver type is not supported yet\n");
 	return 1;
 }
 
 /* Setup a communication between mcs7780 and sharp chip. */
 static inline int mcs_setup_transceiver_sharp(struct mcs_cb *mcs)
 {
-	IRDA_WARNING("This transceiver type is not supported yet.\n");
+	net_warn_ratelimited("This transceiver type is not supported yet\n");
 	return 1;
 }
 
@@ -213,9 +213,9 @@ static inline int mcs_setup_transceiver(struct mcs_cb *mcs)
 {
 	int ret = 0;
 	__u16 rval;
-	char *msg;
+	const char *msg;
 
-	msg = "Basic transceiver setup error.";
+	msg = "Basic transceiver setup error";
 
 	/* read value of MODE Register, set the DRIVER and RESET bits
 	* and write value back out to MODE Register
@@ -261,7 +261,7 @@ static inline int mcs_setup_transceiver(struct mcs_cb *mcs)
 	if(unlikely(ret))
 		goto error;
 
-	msg = "transceiver model specific setup error.";
+	msg = "transceiver model specific setup error";
 	switch (mcs->transceiver_type) {
 	case MCS_TSC_VISHAY:
 		ret = mcs_setup_transceiver_vishay(mcs);
@@ -276,8 +276,8 @@ static inline int mcs_setup_transceiver(struct mcs_cb *mcs)
 		break;
 
 	default:
-		IRDA_WARNING("Unknown transceiver type: %d\n",
-			     mcs->transceiver_type);
+		net_warn_ratelimited("Unknown transceiver type: %d\n",
+				     mcs->transceiver_type);
 		ret = 1;
 	}
 	if (unlikely(ret))
@@ -300,7 +300,7 @@ static inline int mcs_setup_transceiver(struct mcs_cb *mcs)
 			goto error;
 	}
 
-	msg = "transceiver reset.";
+	msg = "transceiver reset";
 
 	ret = mcs_get_reg(mcs, MCS_MODE_REG, &rval);
 	if (unlikely(ret != 2))
@@ -315,7 +315,7 @@ static inline int mcs_setup_transceiver(struct mcs_cb *mcs)
 		return ret;
 
 error:
-	IRDA_ERROR("%s\n", msg);
+	net_err_ratelimited("%s\n", msg);
 	return ret;
 }
 
@@ -399,8 +399,8 @@ static void mcs_unwrap_mir(struct mcs_cb *mcs, __u8 *buf, int len)
 
 	new_len = len - 2;
 	if(unlikely(new_len <= 0)) {
-		IRDA_ERROR("%s short frame length %d\n",
-			     mcs->netdev->name, new_len);
+		net_err_ratelimited("%s short frame length %d\n",
+				    mcs->netdev->name, new_len);
 		++mcs->netdev->stats.rx_errors;
 		++mcs->netdev->stats.rx_length_errors;
 		return;
@@ -409,8 +409,8 @@ static void mcs_unwrap_mir(struct mcs_cb *mcs, __u8 *buf, int len)
 	fcs = irda_calc_crc16(~fcs, buf, len);
 
 	if(fcs != GOOD_FCS) {
-		IRDA_ERROR("crc error calc 0x%x len %d\n",
-			   fcs, new_len);
+		net_err_ratelimited("crc error calc 0x%x len %d\n",
+				    fcs, new_len);
 		mcs->netdev->stats.rx_errors++;
 		mcs->netdev->stats.rx_crc_errors++;
 		return;
@@ -452,8 +452,8 @@ static void mcs_unwrap_fir(struct mcs_cb *mcs, __u8 *buf, int len)
 
 	new_len = len - 4;
 	if(unlikely(new_len <= 0)) {
-		IRDA_ERROR("%s short frame length %d\n",
-			   mcs->netdev->name, new_len);
+		net_err_ratelimited("%s short frame length %d\n",
+				    mcs->netdev->name, new_len);
 		++mcs->netdev->stats.rx_errors;
 		++mcs->netdev->stats.rx_length_errors;
 		return;
@@ -461,7 +461,8 @@ static void mcs_unwrap_fir(struct mcs_cb *mcs, __u8 *buf, int len)
 
 	fcs = ~(crc32_le(~0, buf, new_len));
 	if(fcs != get_unaligned_le32(buf + new_len)) {
-		IRDA_ERROR("crc error calc 0x%x len %d\n", fcs, new_len);
+		net_err_ratelimited("crc error calc 0x%x len %d\n",
+				    fcs, new_len);
 		mcs->netdev->stats.rx_errors++;
 		mcs->netdev->stats.rx_crc_errors++;
 		return;
@@ -583,7 +584,7 @@ static int mcs_speed_change(struct mcs_cb *mcs)
 	} while(cnt++ < 100 && (rval & MCS_IRINTX));
 
 	if (cnt > 100) {
-		IRDA_ERROR("unable to change speed\n");
+		net_err_ratelimited("unable to change speed\n");
 		ret = -EIO;
 		goto error;
 	}
@@ -634,8 +635,8 @@ static int mcs_speed_change(struct mcs_cb *mcs)
 
 		default:
 			ret = 1;
-			IRDA_WARNING("Unknown transceiver type: %d\n",
-				     mcs->transceiver_type);
+			net_warn_ratelimited("Unknown transceiver type: %d\n",
+					     mcs->transceiver_type);
 		}
 	if (unlikely(ret))
 		goto error;
@@ -731,7 +732,7 @@ static int mcs_net_open(struct net_device *netdev)
 	sprintf(hwname, "usb#%d", mcs->usbdev->devnum);
 	mcs->irlap = irlap_open(netdev, &mcs->qos, hwname);
 	if (!mcs->irlap) {
-		IRDA_ERROR("mcs7780: irlap_open failed\n");
+		net_err_ratelimited("mcs7780: irlap_open failed\n");
 		goto error2;
 	}
 
@@ -851,7 +852,7 @@ static netdev_tx_t mcs_hard_xmit(struct sk_buff *skb,
 			  mcs->out_buf, wraplen, mcs_send_irq, mcs);
 
 	if ((ret = usb_submit_urb(mcs->tx_urb, GFP_ATOMIC))) {
-		IRDA_ERROR("failed tx_urb: %d\n", ret);
+		net_err_ratelimited("failed tx_urb: %d\n", ret);
 		switch (ret) {
 		case -ENODEV:
 		case -EPIPE:
@@ -899,7 +900,7 @@ static int mcs_probe(struct usb_interface *intf,
 
 	ret = usb_reset_configuration(udev);
 	if (ret != 0) {
-		IRDA_ERROR("mcs7780: usb reset configuration failed\n");
+		net_err_ratelimited("mcs7780: usb reset configuration failed\n");
 		goto error2;
 	}
 
diff --git a/drivers/net/irda/nsc-ircc.c b/drivers/net/irda/nsc-ircc.c
index 66bc03bdb13..c0a179098ea 100644
--- a/drivers/net/irda/nsc-ircc.c
+++ b/drivers/net/irda/nsc-ircc.c
@@ -211,7 +211,8 @@ static int __init nsc_ircc_init(void)
 
 	ret = platform_driver_register(&nsc_ircc_driver);
         if (ret) {
-                IRDA_ERROR("%s, Can't register driver!\n", driver_name);
+		net_err_ratelimited("%s, Can't register driver!\n",
+				    driver_name);
                 return ret;
         }
 
@@ -260,7 +261,8 @@ static int __init nsc_ircc_init(void)
 					info.irq = pnp_info.irq;
 
 					if (info.fir_base < 0x2000) {
-						IRDA_MESSAGE("%s, chip->init\n", driver_name);
+						net_info_ratelimited("%s, chip->init\n",
+								     driver_name);
 						chip->init(chip, &info);
 					} else
 						chip->probe(chip, &info);
@@ -370,22 +372,23 @@ static int __init nsc_ircc_open(chipio_t *info)
 	}
 
 	if (chip_index == ARRAY_SIZE(dev_self)) {
-		IRDA_ERROR("%s(), maximum number of supported chips reached!\n", __func__);
+		net_err_ratelimited("%s(), maximum number of supported chips reached!\n",
+				    __func__);
 		return -ENOMEM;
 	}
 
-	IRDA_MESSAGE("%s, Found chip at base=0x%03x\n", driver_name,
-		     info->cfg_base);
+	net_info_ratelimited("%s, Found chip at base=0x%03x\n",
+			     driver_name, info->cfg_base);
 
 	if ((nsc_ircc_setup(info)) == -1)
 		return -1;
 
-	IRDA_MESSAGE("%s, driver loaded (Dag Brattli)\n", driver_name);
+	net_info_ratelimited("%s, driver loaded (Dag Brattli)\n", driver_name);
 
 	dev = alloc_irdadev(sizeof(struct nsc_ircc_cb));
 	if (dev == NULL) {
-		IRDA_ERROR("%s(), can't allocate memory for "
-			   "control block!\n", __func__);
+		net_err_ratelimited("%s(), can't allocate memory for control block!\n",
+				    __func__);
 		return -ENOMEM;
 	}
 
@@ -408,8 +411,8 @@ static int __init nsc_ircc_open(chipio_t *info)
 	/* Reserve the ioports that we need */
 	ret = request_region(self->io.fir_base, self->io.fir_ext, driver_name);
 	if (!ret) {
-		IRDA_WARNING("%s(), can't get iobase of 0x%03x\n",
-			     __func__, self->io.fir_base);
+		net_warn_ratelimited("%s(), can't get iobase of 0x%03x\n",
+				     __func__, self->io.fir_base);
 		err = -ENODEV;
 		goto out1;
 	}
@@ -460,21 +463,22 @@ static int __init nsc_ircc_open(chipio_t *info)
 
 	err = register_netdev(dev);
 	if (err) {
-		IRDA_ERROR("%s(), register_netdev() failed!\n", __func__);
+		net_err_ratelimited("%s(), register_netdev() failed!\n",
+				    __func__);
 		goto out4;
 	}
-	IRDA_MESSAGE("IrDA: Registered device %s\n", dev->name);
+	net_info_ratelimited("IrDA: Registered device %s\n", dev->name);
 
 	/* Check if user has supplied a valid dongle id or not */
 	if ((dongle_id <= 0) ||
 	    (dongle_id >= ARRAY_SIZE(dongle_types))) {
 		dongle_id = nsc_ircc_read_dongle_id(self->io.fir_base);
 		
-		IRDA_MESSAGE("%s, Found dongle: %s\n", driver_name,
-			     dongle_types[dongle_id]);
+		net_info_ratelimited("%s, Found dongle: %s\n",
+				     driver_name, dongle_types[dongle_id]);
 	} else {
-		IRDA_MESSAGE("%s, Using dongle: %s\n", driver_name,
-			     dongle_types[dongle_id]);
+		net_info_ratelimited("%s, Using dongle: %s\n",
+				     driver_name, dongle_types[dongle_id]);
 	}
 	
 	self->io.dongle_id = dongle_id;
@@ -567,7 +571,7 @@ static int nsc_ircc_init_108(nsc_chip_t *chip, chipio_t *info)
 	case 0x2e8: outb(0x15, cfg_base+1); break;
 	case 0x3f8: outb(0x16, cfg_base+1); break;
 	case 0x2f8: outb(0x17, cfg_base+1); break;
-	default: IRDA_ERROR("%s(), invalid base_address", __func__);
+	default: net_err_ratelimited("%s(), invalid base_address\n", __func__);
 	}
 	
 	/* Control Signal Routing Register (CSRT) */
@@ -579,7 +583,7 @@ static int nsc_ircc_init_108(nsc_chip_t *chip, chipio_t *info)
 	case 9:  temp = 0x05; break;
 	case 11: temp = 0x06; break;
 	case 15: temp = 0x07; break;
-	default: IRDA_ERROR("%s(), invalid irq", __func__);
+	default: net_err_ratelimited("%s(), invalid irq\n", __func__);
 	}
 	outb(CFG_108_CSRT, cfg_base);
 	
@@ -587,7 +591,7 @@ static int nsc_ircc_init_108(nsc_chip_t *chip, chipio_t *info)
 	case 0: outb(0x08+temp, cfg_base+1); break;
 	case 1: outb(0x10+temp, cfg_base+1); break;
 	case 3: outb(0x18+temp, cfg_base+1); break;
-	default: IRDA_ERROR("%s(), invalid dma", __func__);
+	default: net_err_ratelimited("%s(), invalid dma\n", __func__);
 	}
 	
 	outb(CFG_108_MCTL, cfg_base);      /* Mode Control Register (MCTL) */
@@ -993,8 +997,8 @@ static int nsc_ircc_setup(chipio_t *info)
 
 	/* Should be 0x2? */
 	if (0x20 != (version & 0xf0)) {
-		IRDA_ERROR("%s, Wrong chip version %02x\n",
-			   driver_name, version);
+		net_err_ratelimited("%s, Wrong chip version %02x\n",
+				    driver_name, version);
 		return -1;
 	}
 
@@ -1872,9 +1876,6 @@ static int nsc_ircc_dma_receive_complete(struct nsc_ircc_cb *self, int iobase)
 
 			skb = dev_alloc_skb(len+1);
 			if (skb == NULL)  {
-				IRDA_WARNING("%s(), memory squeeze, "
-					     "dropping frame.\n",
-					     __func__);
 				self->netdev->stats.rx_dropped++;
 
 				/* Restore bank register */
@@ -2063,9 +2064,8 @@ static void nsc_ircc_fir_interrupt(struct nsc_ircc_cb *self, int iobase,
 					nsc_ircc_dma_receive(self);
 					self->ier = IER_SFIF_IE;
 				} else
-					IRDA_WARNING("%s(), potential "
-						     "Tx queue lockup !\n",
-						     __func__);
+					net_warn_ratelimited("%s(), potential Tx queue lockup !\n",
+							     __func__);
 			}
 		} else {
 			/*  Not finished yet, so interrupt on DMA again */
@@ -2184,8 +2184,8 @@ static int nsc_ircc_net_open(struct net_device *dev)
 	iobase = self->io.fir_base;
 	
 	if (request_irq(self->io.irq, nsc_ircc_interrupt, 0, dev->name, dev)) {
-		IRDA_WARNING("%s, unable to allocate irq=%d\n",
-			     driver_name, self->io.irq);
+		net_warn_ratelimited("%s, unable to allocate irq=%d\n",
+				     driver_name, self->io.irq);
 		return -EAGAIN;
 	}
 	/*
@@ -2193,8 +2193,8 @@ static int nsc_ircc_net_open(struct net_device *dev)
 	 * failure.
 	 */
 	if (request_dma(self->io.dma, dev->name)) {
-		IRDA_WARNING("%s, unable to allocate dma=%d\n",
-			     driver_name, self->io.dma);
+		net_warn_ratelimited("%s, unable to allocate dma=%d\n",
+				     driver_name, self->io.dma);
 		free_irq(self->io.irq, dev);
 		return -EAGAIN;
 	}
@@ -2372,8 +2372,8 @@ static int nsc_ircc_resume(struct platform_device *dev)
 	if (netif_running(self->netdev)) {
 		if (request_irq(self->io.irq, nsc_ircc_interrupt, 0,
 				self->netdev->name, self->netdev)) {
- 		    	IRDA_WARNING("%s, unable to allocate irq=%d\n",
-				     driver_name, self->io.irq);
+			net_warn_ratelimited("%s, unable to allocate irq=%d\n",
+					     driver_name, self->io.irq);
 
 			/*
 			 * Don't fail resume process, just kill this
diff --git a/drivers/net/irda/sir_dev.c b/drivers/net/irda/sir_dev.c
index 43e9ab4f4d7..5bfcd25923b 100644
--- a/drivers/net/irda/sir_dev.c
+++ b/drivers/net/irda/sir_dev.c
@@ -82,7 +82,7 @@ static int sirdev_tx_complete_fsm(struct sir_dev *dev)
 			return 0;
 
 		default:
-			IRDA_ERROR("%s - undefined state\n", __func__);
+			net_err_ratelimited("%s - undefined state\n", __func__);
 			return -EINVAL;
 		}
 		fsm->substate = next_state;
@@ -251,12 +251,13 @@ static void sirdev_config_fsm(struct work_struct *work)
 			break;
 
 		default:
-			IRDA_ERROR("%s - undefined state\n", __func__);
+			net_err_ratelimited("%s - undefined state\n", __func__);
 			fsm->result = -EINVAL;
 			/* fall thru */
 
 		case SIRDEV_STATE_ERROR:
-			IRDA_ERROR("%s - error: %d\n", __func__, fsm->result);
+			net_err_ratelimited("%s - error: %d\n",
+					    __func__, fsm->result);
 
 #if 0	/* don't enable this before we have netdev->tx_timeout to recover */
 			netif_stop_queue(dev->netdev);
@@ -299,7 +300,7 @@ int sirdev_schedule_request(struct sir_dev *dev, int initial_state, unsigned par
 
 	if (fsm->state == SIRDEV_STATE_DEAD) {
 		/* race with sirdev_close should never happen */
-		IRDA_ERROR("%s(), instance staled!\n", __func__);
+		net_err_ratelimited("%s(), instance staled!\n", __func__);
 		up(&fsm->sem);
 		return -ESTALE;		/* or better EPIPE? */
 	}
@@ -452,8 +453,8 @@ void sirdev_write_complete(struct sir_dev *dev)
 		}
 		else if (unlikely(actual<0)) {
 			/* could be dropped later when we have tx_timeout to recover */
-			IRDA_ERROR("%s: drv->do_write failed (%d)\n",
-				   __func__, actual);
+			net_err_ratelimited("%s: drv->do_write failed (%d)\n",
+					    __func__, actual);
 			if ((skb=dev->tx_skb) != NULL) {
 				dev->tx_skb = NULL;
 				dev_kfree_skb_any(skb);
@@ -507,8 +508,8 @@ void sirdev_write_complete(struct sir_dev *dev)
 			/* should never happen
 			 * forget the speed change and hope the stack recovers
 			 */
-			IRDA_ERROR("%s - schedule speed change failed: %d\n",
-				   __func__, err);
+			net_err_ratelimited("%s - schedule speed change failed: %d\n",
+					    __func__, err);
 			netif_wake_queue(dev->netdev);
 		}
 		/* else: success
@@ -535,13 +536,13 @@ EXPORT_SYMBOL(sirdev_write_complete);
 int sirdev_receive(struct sir_dev *dev, const unsigned char *cp, size_t count) 
 {
 	if (!dev || !dev->netdev) {
-		IRDA_WARNING("%s(), not ready yet!\n", __func__);
+		net_warn_ratelimited("%s(), not ready yet!\n", __func__);
 		return -1;
 	}
 
 	if (!dev->irlap) {
-		IRDA_WARNING("%s - too early: %p / %zd!\n",
-			     __func__, cp, count);
+		net_warn_ratelimited("%s - too early: %p / %zd!\n",
+				     __func__, cp, count);
 		return -1;
 	}
 
@@ -661,8 +662,8 @@ static netdev_tx_t sirdev_hard_xmit(struct sk_buff *skb,
 	}
 	else if (unlikely(actual < 0)) {
 		/* could be dropped later when we have tx_timeout to recover */
-		IRDA_ERROR("%s: drv->do_write failed (%d)\n",
-			   __func__, actual);
+		net_err_ratelimited("%s: drv->do_write failed (%d)\n",
+				    __func__, actual);
 		dev_kfree_skb_any(skb);
 		dev->netdev->stats.tx_errors++;
 		dev->netdev->stats.tx_dropped++;
@@ -894,7 +895,8 @@ struct sir_dev * sirdev_get_instance(const struct sir_driver *drv, const char *n
 	 */
 	ndev = alloc_irdadev(sizeof(*dev));
 	if (ndev == NULL) {
-		IRDA_ERROR("%s - Can't allocate memory for IrDA control block!\n", __func__);
+		net_err_ratelimited("%s - Can't allocate memory for IrDA control block!\n",
+				    __func__);
 		goto out;
 	}
 	dev = netdev_priv(ndev);
@@ -919,7 +921,8 @@ struct sir_dev * sirdev_get_instance(const struct sir_driver *drv, const char *n
 	ndev->netdev_ops = &sirdev_ops;
 
 	if (register_netdev(ndev)) {
-		IRDA_ERROR("%s(), register_netdev() failed!\n", __func__);
+		net_err_ratelimited("%s(), register_netdev() failed!\n",
+				    __func__);
 		goto out_freenetdev;
 	}
 
@@ -946,7 +949,7 @@ int sirdev_put_instance(struct sir_dev *dev)
 	if (dev->dongle_drv)
 		err = sirdev_schedule_dongle_close(dev);
 	if (err)
-		IRDA_ERROR("%s - error %d\n", __func__, err);
+		net_err_ratelimited("%s - error %d\n", __func__, err);
 
 	sirdev_close(dev->netdev);
 
diff --git a/drivers/net/irda/smsc-ircc2.c b/drivers/net/irda/smsc-ircc2.c
index 282120430f1..a7f0f5214ad 100644
--- a/drivers/net/irda/smsc-ircc2.c
+++ b/drivers/net/irda/smsc-ircc2.c
@@ -419,13 +419,16 @@ static int __init smsc_ircc_legacy_probe(void)
 #ifdef CONFIG_PCI
 	if (smsc_ircc_preconfigure_subsystems(ircc_cfg, ircc_fir, ircc_sir, ircc_dma, ircc_irq) < 0) {
 		/* Ignore errors from preconfiguration */
-		IRDA_ERROR("%s, Preconfiguration failed !\n", driver_name);
+		net_err_ratelimited("%s, Preconfiguration failed !\n",
+				    driver_name);
 	}
 #endif
 
 	if (ircc_fir > 0 && ircc_sir > 0) {
-		IRDA_MESSAGE(" Overriding FIR address 0x%04x\n", ircc_fir);
-		IRDA_MESSAGE(" Overriding SIR address 0x%04x\n", ircc_sir);
+		net_info_ratelimited(" Overriding FIR address 0x%04x\n",
+				     ircc_fir);
+		net_info_ratelimited(" Overriding SIR address 0x%04x\n",
+				     ircc_sir);
 
 		if (smsc_ircc_open(ircc_fir, ircc_sir, ircc_dma, ircc_irq))
 			ret = -ENODEV;
@@ -434,8 +437,8 @@ static int __init smsc_ircc_legacy_probe(void)
 
 		/* try user provided configuration register base address */
 		if (ircc_cfg > 0) {
-			IRDA_MESSAGE(" Overriding configuration address "
-				     "0x%04x\n", ircc_cfg);
+			net_info_ratelimited(" Overriding configuration address 0x%04x\n",
+					     ircc_cfg);
 			if (!smsc_superio_fdc(ircc_cfg))
 				ret = 0;
 			if (!smsc_superio_lpc(ircc_cfg))
@@ -462,7 +465,8 @@ static int __init smsc_ircc_init(void)
 
 	ret = platform_driver_register(&smsc_ircc_driver);
 	if (ret) {
-		IRDA_ERROR("%s, Can't register driver!\n", driver_name);
+		net_err_ratelimited("%s, Can't register driver!\n",
+				    driver_name);
 		return ret;
 	}
 
@@ -527,7 +531,7 @@ static int smsc_ircc_open(unsigned int fir_base, unsigned int sir_base, u8 dma,
 
 	err = -ENOMEM;
 	if (dev_count >= ARRAY_SIZE(dev_self)) {
-	        IRDA_WARNING("%s(), too many devices!\n", __func__);
+		net_warn_ratelimited("%s(), too many devices!\n", __func__);
 		goto err_out1;
 	}
 
@@ -536,7 +540,8 @@ static int smsc_ircc_open(unsigned int fir_base, unsigned int sir_base, u8 dma,
 	 */
 	dev = alloc_irdadev(sizeof(struct smsc_ircc_cb));
 	if (!dev) {
-		IRDA_WARNING("%s() can't allocate net device\n", __func__);
+		net_warn_ratelimited("%s() can't allocate net device\n",
+				     __func__);
 		goto err_out1;
 	}
 
@@ -588,8 +593,8 @@ static int smsc_ircc_open(unsigned int fir_base, unsigned int sir_base, u8 dma,
 
 	err = register_netdev(self->netdev);
 	if (err) {
-		IRDA_ERROR("%s, Network device registration failed!\n",
-			   driver_name);
+		net_err_ratelimited("%s, Network device registration failed!\n",
+				    driver_name);
 		goto err_out4;
 	}
 
@@ -601,7 +606,7 @@ static int smsc_ircc_open(unsigned int fir_base, unsigned int sir_base, u8 dma,
 	}
 	platform_set_drvdata(self->pldev, self);
 
-	IRDA_MESSAGE("IrDA: Registered device %s\n", dev->name);
+	net_info_ratelimited("IrDA: Registered device %s\n", dev->name);
 	dev_count++;
 
 	return 0;
@@ -637,15 +642,15 @@ static int smsc_ircc_present(unsigned int fir_base, unsigned int sir_base)
 
 	if (!request_region(fir_base, SMSC_IRCC2_FIR_CHIP_IO_EXTENT,
 			    driver_name)) {
-		IRDA_WARNING("%s: can't get fir_base of 0x%03x\n",
-			     __func__, fir_base);
+		net_warn_ratelimited("%s: can't get fir_base of 0x%03x\n",
+				     __func__, fir_base);
 		goto out1;
 	}
 
 	if (!request_region(sir_base, SMSC_IRCC2_SIR_CHIP_IO_EXTENT,
 			    driver_name)) {
-		IRDA_WARNING("%s: can't get sir_base of 0x%03x\n",
-			     __func__, sir_base);
+		net_warn_ratelimited("%s: can't get sir_base of 0x%03x\n",
+				     __func__, sir_base);
 		goto out2;
 	}
 
@@ -660,13 +665,13 @@ static int smsc_ircc_present(unsigned int fir_base, unsigned int sir_base)
 	irq     = (config & IRCC_INTERFACE_IRQ_MASK) >> 4;
 
 	if (high != 0x10 || low != 0xb8 || (chip != 0xf1 && chip != 0xf2)) {
-		IRDA_WARNING("%s(), addr 0x%04x - no device found!\n",
-			     __func__, fir_base);
+		net_warn_ratelimited("%s(), addr 0x%04x - no device found!\n",
+				     __func__, fir_base);
 		goto out3;
 	}
-	IRDA_MESSAGE("SMsC IrDA Controller found\n IrCC version %d.%d, "
-		     "firport 0x%03x, sirport 0x%03x dma=%d, irq=%d\n",
-		     chip & 0x0f, version, fir_base, sir_base, dma, irq);
+	net_info_ratelimited("SMsC IrDA Controller found\n IrCC version %d.%d, firport 0x%03x, sirport 0x%03x dma=%d, irq=%d\n",
+			     chip & 0x0f, version,
+			     fir_base, sir_base, dma, irq);
 
 	return 0;
 
@@ -704,16 +709,16 @@ static void smsc_ircc_setup_io(struct smsc_ircc_cb *self,
 
 	if (irq != IRQ_INVAL) {
 		if (irq != chip_irq)
-			IRDA_MESSAGE("%s, Overriding IRQ - chip says %d, using %d\n",
-				     driver_name, chip_irq, irq);
+			net_info_ratelimited("%s, Overriding IRQ - chip says %d, using %d\n",
+					     driver_name, chip_irq, irq);
 		self->io.irq = irq;
 	} else
 		self->io.irq = chip_irq;
 
 	if (dma != DMA_INVAL) {
 		if (dma != chip_dma)
-			IRDA_MESSAGE("%s, Overriding DMA - chip says %d, using %d\n",
-				     driver_name, chip_dma, dma);
+			net_info_ratelimited("%s, Overriding DMA - chip says %d, using %d\n",
+					     driver_name, chip_dma, dma);
 		self->io.dma = dma;
 	} else
 		self->io.dma = chip_dma;
@@ -852,8 +857,8 @@ static void smsc_ircc_timeout(struct net_device *dev)
 	struct smsc_ircc_cb *self = netdev_priv(dev);
 	unsigned long flags;
 
-	IRDA_WARNING("%s: transmit timed out, changing speed to: %d\n",
-		     dev->name, self->io.speed);
+	net_warn_ratelimited("%s: transmit timed out, changing speed to: %d\n",
+			     dev->name, self->io.speed);
 	spin_lock_irqsave(&self->lock, flags);
 	smsc_ircc_sir_start(self);
 	smsc_ircc_change_speed(self, self->io.speed);
@@ -1442,17 +1447,15 @@ static void smsc_ircc_dma_receive_complete(struct smsc_ircc_cb *self)
 	len -= self->io.speed < 4000000 ? 2 : 4;
 
 	if (len < 2 || len > 2050) {
-		IRDA_WARNING("%s(), bogus len=%d\n", __func__, len);
+		net_warn_ratelimited("%s(), bogus len=%d\n", __func__, len);
 		return;
 	}
 	IRDA_DEBUG(2, "%s: msgcnt = %d, len=%d\n", __func__, msgcnt, len);
 
 	skb = dev_alloc_skb(len + 1);
-	if (!skb) {
-		IRDA_WARNING("%s(), memory squeeze, dropping frame.\n",
-			     __func__);
+	if (!skb)
 		return;
-	}
+
 	/* Make sure IP header gets aligned */
 	skb_reserve(skb, 1);
 
@@ -1730,8 +1733,8 @@ static int smsc_ircc_net_open(struct net_device *dev)
 	if (request_dma(self->io.dma, dev->name)) {
 		smsc_ircc_net_close(dev);
 
-		IRDA_WARNING("%s(), unable to allocate DMA=%d\n",
-			     __func__, self->io.dma);
+		net_warn_ratelimited("%s(), unable to allocate DMA=%d\n",
+				     __func__, self->io.dma);
 		return -EAGAIN;
 	}
 
@@ -2019,7 +2022,8 @@ static int smsc_ircc_sir_write(int iobase, int fifo_size, __u8 *buf, int len)
 
 	/* Tx FIFO should be empty! */
 	if (!(inb(iobase + UART_LSR) & UART_LSR_THRE)) {
-		IRDA_WARNING("%s(), failed, fifo not empty!\n", __func__);
+		net_warn_ratelimited("%s(), failed, fifo not empty!\n",
+				     __func__);
 		return 0;
 	}
 
@@ -2058,14 +2062,14 @@ static void smsc_ircc_probe_transceiver(struct smsc_ircc_cb *self)
 
 	for (i = 0; smsc_transceivers[i].name != NULL; i++)
 		if (smsc_transceivers[i].probe(self->io.fir_base)) {
-			IRDA_MESSAGE(" %s transceiver found\n",
-				     smsc_transceivers[i].name);
+			net_info_ratelimited(" %s transceiver found\n",
+					     smsc_transceivers[i].name);
 			self->transceiver= i + 1;
 			return;
 		}
 
-	IRDA_MESSAGE("No transceiver found. Defaulting to %s\n",
-		     smsc_transceivers[SMSC_IRCC2_C_DEFAULT_TRANSCEIVER].name);
+	net_info_ratelimited("No transceiver found. Defaulting to %s\n",
+			     smsc_transceivers[SMSC_IRCC2_C_DEFAULT_TRANSCEIVER].name);
 
 	self->transceiver = SMSC_IRCC2_C_DEFAULT_TRANSCEIVER;
 }
@@ -2191,7 +2195,7 @@ static int __init smsc_superio_flat(const struct smsc_chip *chips, unsigned shor
 	/*printk(KERN_WARNING "%s(): mode: 0x%02x\n", __func__, mode);*/
 
 	if (!(mode & SMSCSIOFLAT_UART2MODE_VAL_IRDA))
-		IRDA_WARNING("%s(): IrDA not enabled\n", __func__);
+		net_warn_ratelimited("%s(): IrDA not enabled\n", __func__);
 
 	outb(SMSCSIOFLAT_UART2BASEADDR_REG, cfgbase);
 	sirbase = inb(cfgbase + 1) << 2;
@@ -2208,7 +2212,8 @@ static int __init smsc_superio_flat(const struct smsc_chip *chips, unsigned shor
 	outb(SMSCSIOFLAT_UARTIRQSELECT_REG, cfgbase);
 	irq = inb(cfgbase + 1) & SMSCSIOFLAT_UART2IRQSELECT_MASK;
 
-	IRDA_MESSAGE("%s(): fir: 0x%02x, sir: 0x%02x, dma: %02d, irq: %d, mode: 0x%02x\n", __func__, firbase, sirbase, dma, irq, mode);
+	net_info_ratelimited("%s(): fir: 0x%02x, sir: 0x%02x, dma: %02d, irq: %d, mode: 0x%02x\n",
+			     __func__, firbase, sirbase, dma, irq, mode);
 
 	if (firbase && smsc_ircc_open(firbase, sirbase, dma, irq) == 0)
 		ret = 0;
@@ -2329,16 +2334,16 @@ static const struct smsc_chip * __init smsc_ircc_probe(unsigned short cfg_base,
 			return NULL;
 	}
 
-	IRDA_MESSAGE("found SMC SuperIO Chip (devid=0x%02x rev=%02X base=0x%04x): %s%s\n",
-		     devid, rev, cfg_base, type, chip->name);
+	net_info_ratelimited("found SMC SuperIO Chip (devid=0x%02x rev=%02X base=0x%04x): %s%s\n",
+			     devid, rev, cfg_base, type, chip->name);
 
 	if (chip->rev > rev) {
-		IRDA_MESSAGE("Revision higher than expected\n");
+		net_info_ratelimited("Revision higher than expected\n");
 		return NULL;
 	}
 
 	if (chip->flags & NoIRDA)
-		IRDA_MESSAGE("chipset does not support IRDA\n");
+		net_info_ratelimited("chipset does not support IRDA\n");
 
 	return chip;
 }
@@ -2348,8 +2353,8 @@ static int __init smsc_superio_fdc(unsigned short cfg_base)
 	int ret = -1;
 
 	if (!request_region(cfg_base, 2, driver_name)) {
-		IRDA_WARNING("%s: can't get cfg_base of 0x%03x\n",
-			     __func__, cfg_base);
+		net_warn_ratelimited("%s: can't get cfg_base of 0x%03x\n",
+				     __func__, cfg_base);
 	} else {
 		if (!smsc_superio_flat(fdc_chips_flat, cfg_base, "FDC") ||
 		    !smsc_superio_paged(fdc_chips_paged, cfg_base, "FDC"))
@@ -2366,8 +2371,8 @@ static int __init smsc_superio_lpc(unsigned short cfg_base)
 	int ret = -1;
 
 	if (!request_region(cfg_base, 2, driver_name)) {
-		IRDA_WARNING("%s: can't get cfg_base of 0x%03x\n",
-			     __func__, cfg_base);
+		net_warn_ratelimited("%s: can't get cfg_base of 0x%03x\n",
+				     __func__, cfg_base);
 	} else {
 		if (!smsc_superio_flat(lpc_chips_flat, cfg_base, "LPC") ||
 		    !smsc_superio_paged(lpc_chips_paged, cfg_base, "LPC"))
@@ -2540,8 +2545,8 @@ static int __init preconfigure_smsc_chip(struct
 	outb( (conf->sir_io >> 2), iobase + 1); // bits 2-9 of 0x3f8
 	tmpbyte = inb(iobase + 1);
 	if (tmpbyte != (conf->sir_io >> 2) ) {
-		IRDA_WARNING("ERROR: could not configure SIR ioport.\n");
-		IRDA_WARNING("Try to supply ircc_cfg argument.\n");
+		net_warn_ratelimited("ERROR: could not configure SIR ioport\n");
+		net_warn_ratelimited("Try to supply ircc_cfg argument\n");
 		return -ENXIO;
 	}
 
@@ -2553,7 +2558,7 @@ static int __init preconfigure_smsc_chip(struct
 	outb(tmpbyte, iobase + 1);
 	tmpbyte = inb(iobase + 1) & SMSCSIOFLAT_UART2IRQSELECT_MASK;
 	if (tmpbyte != conf->fir_irq) {
-		IRDA_WARNING("ERROR: could not configure FIR IRQ channel.\n");
+		net_warn_ratelimited("ERROR: could not configure FIR IRQ channel\n");
 		return -ENXIO;
 	}
 
@@ -2562,7 +2567,7 @@ static int __init preconfigure_smsc_chip(struct
 	outb((conf->fir_io >> 3), iobase + 1);
 	tmpbyte = inb(iobase + 1);
 	if (tmpbyte != (conf->fir_io >> 3) ) {
-		IRDA_WARNING("ERROR: could not configure FIR I/O port.\n");
+		net_warn_ratelimited("ERROR: could not configure FIR I/O port\n");
 		return -ENXIO;
 	}
 
@@ -2571,7 +2576,7 @@ static int __init preconfigure_smsc_chip(struct
 	outb((conf->fir_dma & LPC47N227_FIRDMASELECT_MASK), iobase + 1); // DMA
 	tmpbyte = inb(iobase + 1) & LPC47N227_FIRDMASELECT_MASK;
 	if (tmpbyte != (conf->fir_dma & LPC47N227_FIRDMASELECT_MASK)) {
-		IRDA_WARNING("ERROR: could not configure FIR DMA channel.\n");
+		net_warn_ratelimited("ERROR: could not configure FIR DMA channel\n");
 		return -ENXIO;
 	}
 
@@ -2628,7 +2633,7 @@ static int __init preconfigure_through_82801(struct pci_dev *dev,
 	unsigned short tmpword;
 	unsigned char tmpbyte;
 
-	IRDA_MESSAGE("Setting up Intel 82801 controller and SMSC device\n");
+	net_info_ratelimited("Setting up Intel 82801 controller and SMSC device\n");
 	/*
 	 * Select the range for the COMA COM port (SIR)
 	 * Register COM_DEC:
@@ -2699,8 +2704,8 @@ static int __init preconfigure_through_82801(struct pci_dev *dev,
 		tmpword |= 0x0400;
 		break;
 	default:
-		IRDA_WARNING("Uncommon I/O base address: 0x%04x\n",
-			     conf->cfg_base);
+		net_warn_ratelimited("Uncommon I/O base address: 0x%04x\n",
+				     conf->cfg_base);
 		break;
 	}
 	tmpword &= 0xfffd; /* disable LPC COMB */
@@ -2800,7 +2805,8 @@ static void __init preconfigure_ali_port(struct pci_dev *dev,
 		mask = 0x08;
 		break;
 	default:
-		IRDA_ERROR("Failed to configure unsupported port on ALi 1533 bridge: 0x%04x\n", port);
+		net_err_ratelimited("Failed to configure unsupported port on ALi 1533 bridge: 0x%04x\n",
+				    port);
 		return;
 	}
 
@@ -2808,7 +2814,8 @@ static void __init preconfigure_ali_port(struct pci_dev *dev,
 	/* Turn on the right bits */
 	tmpbyte |= mask;
 	pci_write_config_byte(dev, reg, tmpbyte);
-	IRDA_MESSAGE("Activated ALi 1533 ISA bridge port 0x%04x.\n", port);
+	net_info_ratelimited("Activated ALi 1533 ISA bridge port 0x%04x\n",
+			     port);
 }
 
 static int __init preconfigure_through_ali(struct pci_dev *dev,
@@ -2877,7 +2884,8 @@ static int __init smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
 				if (ircc_irq != IRQ_INVAL)
 					tmpconf.fir_irq = ircc_irq;
 
-				IRDA_MESSAGE("Detected unconfigured %s SMSC IrDA chip, pre-configuring device.\n", conf->name);
+				net_info_ratelimited("Detected unconfigured %s SMSC IrDA chip, pre-configuring device\n",
+						     conf->name);
 				if (conf->preconfigure)
 					ret = conf->preconfigure(dev, &tmpconf);
 				else
@@ -2922,8 +2930,8 @@ static void smsc_ircc_set_transceiver_smsc_ircc_atc(int fir_base, u32 speed)
 		/* empty */;
 
 	if (val)
-		IRDA_WARNING("%s(): ATC: 0x%02x\n", __func__,
-			     inb(fir_base + IRCC_ATC));
+		net_warn_ratelimited("%s(): ATC: 0x%02x\n",
+				     __func__, inb(fir_base + IRCC_ATC));
 }
 
 /*
diff --git a/drivers/net/irda/tekram-sir.c b/drivers/net/irda/tekram-sir.c
index 048a1542284..04db4eac9dc 100644
--- a/drivers/net/irda/tekram-sir.c
+++ b/drivers/net/irda/tekram-sir.c
@@ -179,7 +179,8 @@ static int tekram_change_speed(struct sir_dev *dev, unsigned speed)
 		break;
 
 	default:
-		IRDA_ERROR("%s - undefined state %d\n", __func__, state);
+		net_err_ratelimited("%s - undefined state %d\n",
+				    __func__, state);
 		ret = -EINVAL;
 		break;
 	}
diff --git a/drivers/net/irda/via-ircc.c b/drivers/net/irda/via-ircc.c
index 36e004288ea..b07b4ccddca 100644
--- a/drivers/net/irda/via-ircc.c
+++ b/drivers/net/irda/via-ircc.c
@@ -391,7 +391,8 @@ static int via_ircc_open(struct pci_dev *pdev, chipio_t *info, unsigned int id)
 	if (err)
 		goto err_out4;
 
-	IRDA_MESSAGE("IrDA: Registered device %s (via-ircc)\n", dev->name);
+	net_info_ratelimited("IrDA: Registered device %s (via-ircc)\n",
+			     dev->name);
 
 	/* Initialise the hardware..
 	*/
@@ -510,7 +511,7 @@ static void via_hw_init(struct via_ircc_cb *self)
  */
 static int via_ircc_read_dongle_id(int iobase)
 {
-	IRDA_ERROR("via-ircc: dongle probing not supported, please specify dongle_id module parameter.\n");
+	net_err_ratelimited("via-ircc: dongle probing not supported, please specify dongle_id module parameter\n");
 	return 9;	/* Default to IBM */
 }
 
@@ -652,8 +653,8 @@ static void via_ircc_change_dongle_speed(int iobase, int speed,
 		break;
 
 	default:
-		IRDA_ERROR("%s: Error: dongle_id %d unsupported !\n",
-			   __func__, dongle_id);
+		net_err_ratelimited("%s: Error: dongle_id %d unsupported !\n",
+				    __func__, dongle_id);
 	}
 }
 
@@ -1473,8 +1474,8 @@ static int via_ircc_net_open(struct net_device *dev)
 	IRDA_ASSERT(self != NULL, return 0;);
 	iobase = self->io.fir_base;
 	if (request_irq(self->io.irq, via_ircc_interrupt, 0, dev->name, dev)) {
-		IRDA_WARNING("%s, unable to allocate irq=%d\n", driver_name,
-			     self->io.irq);
+		net_warn_ratelimited("%s, unable to allocate irq=%d\n",
+				     driver_name, self->io.irq);
 		return -EAGAIN;
 	}
 	/*
@@ -1482,15 +1483,15 @@ static int via_ircc_net_open(struct net_device *dev)
 	 * failure.
 	 */
 	if (request_dma(self->io.dma, dev->name)) {
-		IRDA_WARNING("%s, unable to allocate dma=%d\n", driver_name,
-			     self->io.dma);
+		net_warn_ratelimited("%s, unable to allocate dma=%d\n",
+				     driver_name, self->io.dma);
 		free_irq(self->io.irq, dev);
 		return -EAGAIN;
 	}
 	if (self->io.dma2 != self->io.dma) {
 		if (request_dma(self->io.dma2, dev->name)) {
-			IRDA_WARNING("%s, unable to allocate dma2=%d\n",
-				     driver_name, self->io.dma2);
+			net_warn_ratelimited("%s, unable to allocate dma2=%d\n",
+					     driver_name, self->io.dma2);
 			free_irq(self->io.irq, dev);
 			free_dma(self->io.dma);
 			return -EAGAIN;
diff --git a/drivers/net/irda/vlsi_ir.c b/drivers/net/irda/vlsi_ir.c
index a2e55616828..fd4dedea8e0 100644
--- a/drivers/net/irda/vlsi_ir.c
+++ b/drivers/net/irda/vlsi_ir.c
@@ -429,8 +429,8 @@ static struct vlsi_ring *vlsi_alloc_ring(struct pci_dev *pdev, struct ring_descr
 		if (rd->buf == NULL ||
 		    !(busaddr = pci_map_single(pdev, rd->buf, len, dir))) {
 			if (rd->buf) {
-				IRDA_ERROR("%s: failed to create PCI-MAP for %p",
-					   __func__, rd->buf);
+				net_err_ratelimited("%s: failed to create PCI-MAP for %p\n",
+						    __func__, rd->buf);
 				kfree(rd->buf);
 				rd->buf = NULL;
 			}
@@ -483,11 +483,8 @@ static int vlsi_create_hwif(vlsi_irda_dev_t *idev)
 
 	ringarea = pci_zalloc_consistent(idev->pdev, HW_RING_AREA_SIZE,
 					 &idev->busaddr);
-	if (!ringarea) {
-		IRDA_ERROR("%s: insufficient memory for descriptor rings\n",
-			   __func__);
+	if (!ringarea)
 		goto out;
-	}
 
 	hwmap = (struct ring_descr_hw *)ringarea;
 	idev->rx_ring = vlsi_alloc_ring(idev->pdev, hwmap, ringsize[1],
@@ -581,7 +578,7 @@ static int vlsi_process_rx(struct vlsi_ring *r, struct ring_descr *rd)
 	}
 
 	if (!rd->skb) {
-		IRDA_WARNING("%s: rx packet lost\n", __func__);
+		net_warn_ratelimited("%s: rx packet lost\n", __func__);
 		ret |= VLSI_RX_DROP;
 		goto done;
 	}
@@ -610,8 +607,8 @@ static void vlsi_fill_rx(struct vlsi_ring *r)
 
 	for (rd = ring_last(r); rd != NULL; rd = ring_put(r)) {
 		if (rd_is_active(rd)) {
-			IRDA_WARNING("%s: driver bug: rx descr race with hw\n",
-				     __func__);
+			net_warn_ratelimited("%s: driver bug: rx descr race with hw\n",
+					     __func__);
 			vlsi_ring_debug(r);
 			break;
 		}
@@ -670,7 +667,7 @@ static void vlsi_rx_interrupt(struct net_device *ndev)
 
 	if (ring_first(r) == NULL) {
 		/* we are in big trouble, if this should ever happen */
-		IRDA_ERROR("%s: rx ring exhausted!\n", __func__);
+		net_err_ratelimited("%s: rx ring exhausted!\n", __func__);
 		vlsi_ring_debug(r);
 	}
 	else
@@ -783,8 +780,8 @@ static int vlsi_set_baud(vlsi_irda_dev_t *idev, unsigned iobase)
 		config = IRCFG_SIR | IRCFG_SIRFILT  | IRCFG_RXANY;
 		switch(baudrate) {
 			default:
-				IRDA_WARNING("%s: undefined baudrate %d - fallback to 9600!\n",
-					     __func__, baudrate);
+				net_warn_ratelimited("%s: undefined baudrate %d - fallback to 9600!\n",
+						     __func__, baudrate);
 				baudrate = 9600;
 				/* fallthru */
 			case 2400:
@@ -825,14 +822,16 @@ static int vlsi_set_baud(vlsi_irda_dev_t *idev, unsigned iobase)
 		config ^= IRENABLE_SIR_ON;
 
 	if (config != (IRENABLE_PHYANDCLOCK|IRENABLE_ENRXST)) {
-		IRDA_WARNING("%s: failed to set %s mode!\n", __func__,
-			(mode==IFF_SIR)?"SIR":((mode==IFF_MIR)?"MIR":"FIR"));
+		net_warn_ratelimited("%s: failed to set %s mode!\n",
+				     __func__,
+				     mode == IFF_SIR ? "SIR" :
+				     mode == IFF_MIR ? "MIR" : "FIR");
 		ret = -1;
 	}
 	else {
 		if (inw(iobase+VLSI_PIO_PHYCTL) != nphyctl) {
-			IRDA_WARNING("%s: failed to apply baudrate %d\n",
-				     __func__, baudrate);
+			net_warn_ratelimited("%s: failed to apply baudrate %d\n",
+					     __func__, baudrate);
 			ret = -1;
 		}
 		else {
@@ -977,8 +976,8 @@ static netdev_tx_t vlsi_hard_start_xmit(struct sk_buff *skb,
 		 */
 
 		if (len >= r->len-5)
-			 IRDA_WARNING("%s: possible buffer overflow with SIR wrapping!\n",
-				      __func__);
+			net_warn_ratelimited("%s: possible buffer overflow with SIR wrapping!\n",
+					     __func__);
 	}
 	else {
 		/* hw deals with MIR/FIR mode wrapping */
@@ -1044,7 +1043,7 @@ static netdev_tx_t vlsi_hard_start_xmit(struct sk_buff *skb,
 drop_unlock:
 	spin_unlock_irqrestore(&idev->lock, flags);
 drop:
-	IRDA_WARNING("%s: dropping packet - %s\n", __func__, msg);
+	net_warn_ratelimited("%s: dropping packet - %s\n", __func__, msg);
 	dev_kfree_skb_any(skb);
 	ndev->stats.tx_errors++;
 	ndev->stats.tx_dropped++;
@@ -1183,8 +1182,8 @@ static int vlsi_start_clock(struct pci_dev *pdev)
 		}
 		if (count < 3) {
 			if (clksrc == 1) { /* explicitly asked for PLL hence bail out */
-				IRDA_ERROR("%s: no PLL or failed to lock!\n",
-					   __func__);
+				net_err_ratelimited("%s: no PLL or failed to lock!\n",
+						    __func__);
 				clkctl = CLKCTL_CLKSTP;
 				pci_write_config_byte(pdev, VLSI_PCI_CLKCTL, clkctl);
 				return -1;
@@ -1265,7 +1264,7 @@ static int vlsi_init_chip(struct pci_dev *pdev)
 	/* start the clock and clean the registers */
 
 	if (vlsi_start_clock(pdev)) {
-		IRDA_ERROR("%s: no valid clock source\n", __func__);
+		net_err_ratelimited("%s: no valid clock source\n", __func__);
 		return -1;
 	}
 	iobase = ndev->base_addr;
@@ -1389,8 +1388,8 @@ static void vlsi_tx_timeout(struct net_device *ndev)
 		idev->new_baud = idev->baud;		/* keep current baudrate */
 
 	if (vlsi_start_hw(idev))
-		IRDA_ERROR("%s: failed to restart hw - %s(%s) unusable!\n",
-			   __func__, pci_name(idev->pdev), ndev->name);
+		net_err_ratelimited("%s: failed to restart hw - %s(%s) unusable!\n",
+				    __func__, pci_name(idev->pdev), ndev->name);
 	else
 		netif_start_queue(ndev);
 }
@@ -1434,8 +1433,8 @@ static int vlsi_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
 			irq->ifr_receiving = (fifocnt!=0) ? 1 : 0;
 			break;
 		default:
-			IRDA_WARNING("%s: notsupp - cmd=%04x\n",
-				     __func__, cmd);
+			net_warn_ratelimited("%s: notsupp - cmd=%04x\n",
+					     __func__, cmd);
 			ret = -EOPNOTSUPP;
 	}	
 	
@@ -1479,8 +1478,8 @@ static irqreturn_t vlsi_interrupt(int irq, void *dev_instance)
 	spin_unlock_irqrestore(&idev->lock,flags);
 
 	if (boguscount <= 0)
-		IRDA_MESSAGE("%s: too much work in interrupt!\n",
-			     __func__);
+		net_info_ratelimited("%s: too much work in interrupt!\n",
+				     __func__);
 	return IRQ_RETVAL(handled);
 }
 
@@ -1493,7 +1492,7 @@ static int vlsi_open(struct net_device *ndev)
 	char	hwname[32];
 
 	if (pci_request_regions(idev->pdev, drivername)) {
-		IRDA_WARNING("%s: io resource busy\n", __func__);
+		net_warn_ratelimited("%s: io resource busy\n", __func__);
 		goto errout;
 	}
 	ndev->base_addr = pci_resource_start(idev->pdev,0);
@@ -1507,8 +1506,8 @@ static int vlsi_open(struct net_device *ndev)
 
 	if (request_irq(ndev->irq, vlsi_interrupt, IRQF_SHARED,
 			drivername, ndev)) {
-		IRDA_WARNING("%s: couldn't get IRQ: %d\n",
-			     __func__, ndev->irq);
+		net_warn_ratelimited("%s: couldn't get IRQ: %d\n",
+				     __func__, ndev->irq);
 		goto errout_io;
 	}
 
@@ -1529,7 +1528,8 @@ static int vlsi_open(struct net_device *ndev)
 
 	netif_start_queue(ndev);
 
-	IRDA_MESSAGE("%s: device %s operational\n", __func__, ndev->name);
+	net_info_ratelimited("%s: device %s operational\n",
+			     __func__, ndev->name);
 
 	return 0;
 
@@ -1563,7 +1563,7 @@ static int vlsi_close(struct net_device *ndev)
 
 	pci_release_regions(idev->pdev);
 
-	IRDA_MESSAGE("%s: device %s stopped\n", __func__, ndev->name);
+	net_info_ratelimited("%s: device %s stopped\n", __func__, ndev->name);
 
 	return 0;
 }
@@ -1590,7 +1590,8 @@ static int vlsi_irda_init(struct net_device *ndev)
 
 	if (pci_set_dma_mask(pdev,DMA_MASK_USED_BY_HW) ||
 	    pci_set_dma_mask(pdev,DMA_MASK_MSTRPAGE)) {
-		IRDA_ERROR("%s: aborting due to PCI BM-DMA address limitations\n", __func__);
+		net_err_ratelimited("%s: aborting due to PCI BM-DMA address limitations\n",
+				    __func__);
 		return -1;
 	}
 
@@ -1632,19 +1633,19 @@ vlsi_irda_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	else
 		pdev->current_state = 0; /* hw must be running now */
 
-	IRDA_MESSAGE("%s: IrDA PCI controller %s detected\n",
-		     drivername, pci_name(pdev));
+	net_info_ratelimited("%s: IrDA PCI controller %s detected\n",
+			     drivername, pci_name(pdev));
 
 	if ( !pci_resource_start(pdev,0) ||
 	     !(pci_resource_flags(pdev,0) & IORESOURCE_IO) ) {
-		IRDA_ERROR("%s: bar 0 invalid", __func__);
+		net_err_ratelimited("%s: bar 0 invalid", __func__);
 		goto out_disable;
 	}
 
 	ndev = alloc_irdadev(sizeof(*idev));
 	if (ndev==NULL) {
-		IRDA_ERROR("%s: Unable to allocate device memory.\n",
-			   __func__);
+		net_err_ratelimited("%s: Unable to allocate device memory.\n",
+				    __func__);
 		goto out_disable;
 	}
 
@@ -1659,7 +1660,7 @@ vlsi_irda_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto out_freedev;
 
 	if (register_netdev(ndev) < 0) {
-		IRDA_ERROR("%s: register_netdev failed\n", __func__);
+		net_err_ratelimited("%s: register_netdev failed\n", __func__);
 		goto out_freedev;
 	}
 
@@ -1669,14 +1670,15 @@ vlsi_irda_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		ent = proc_create_data(ndev->name, S_IFREG|S_IRUGO,
 				       vlsi_proc_root, VLSI_PROC_FOPS, ndev);
 		if (!ent) {
-			IRDA_WARNING("%s: failed to create proc entry\n",
-				     __func__);
+			net_warn_ratelimited("%s: failed to create proc entry\n",
+					     __func__);
 		} else {
 			proc_set_size(ent, 0);
 		}
 		idev->proc_entry = ent;
 	}
-	IRDA_MESSAGE("%s: registered device %s\n", drivername, ndev->name);
+	net_info_ratelimited("%s: registered device %s\n",
+			     drivername, ndev->name);
 
 	pci_set_drvdata(pdev, ndev);
 	mutex_unlock(&idev->mtx);
@@ -1698,7 +1700,7 @@ static void vlsi_irda_remove(struct pci_dev *pdev)
 	vlsi_irda_dev_t *idev;
 
 	if (!ndev) {
-		IRDA_ERROR("%s: lost netdevice?\n", drivername);
+		net_err_ratelimited("%s: lost netdevice?\n", drivername);
 		return;
 	}
 
@@ -1714,7 +1716,7 @@ static void vlsi_irda_remove(struct pci_dev *pdev)
 
 	free_netdev(ndev);
 
-	IRDA_MESSAGE("%s: %s removed\n", drivername, pci_name(pdev));
+	net_info_ratelimited("%s: %s removed\n", drivername, pci_name(pdev));
 }
 
 #ifdef CONFIG_PM
@@ -1733,8 +1735,8 @@ static int vlsi_irda_suspend(struct pci_dev *pdev, pm_message_t state)
 	vlsi_irda_dev_t *idev;
 
 	if (!ndev) {
-		IRDA_ERROR("%s - %s: no netdevice\n",
-			   __func__, pci_name(pdev));
+		net_err_ratelimited("%s - %s: no netdevice\n",
+				    __func__, pci_name(pdev));
 		return 0;
 	}
 	idev = netdev_priv(ndev);
@@ -1745,7 +1747,9 @@ static int vlsi_irda_suspend(struct pci_dev *pdev, pm_message_t state)
 			pdev->current_state = state.event;
 		}
 		else
-			IRDA_ERROR("%s - %s: invalid suspend request %u -> %u\n", __func__, pci_name(pdev), pdev->current_state, state.event);
+			net_err_ratelimited("%s - %s: invalid suspend request %u -> %u\n",
+					    __func__, pci_name(pdev),
+					    pdev->current_state, state.event);
 		mutex_unlock(&idev->mtx);
 		return 0;
 	}
@@ -1772,16 +1776,16 @@ static int vlsi_irda_resume(struct pci_dev *pdev)
 	vlsi_irda_dev_t	*idev;
 
 	if (!ndev) {
-		IRDA_ERROR("%s - %s: no netdevice\n",
-			   __func__, pci_name(pdev));
+		net_err_ratelimited("%s - %s: no netdevice\n",
+				    __func__, pci_name(pdev));
 		return 0;
 	}
 	idev = netdev_priv(ndev);
 	mutex_lock(&idev->mtx);
 	if (pdev->current_state == 0) {
 		mutex_unlock(&idev->mtx);
-		IRDA_WARNING("%s - %s: already resumed\n",
-			     __func__, pci_name(pdev));
+		net_warn_ratelimited("%s - %s: already resumed\n",
+				     __func__, pci_name(pdev));
 		return 0;
 	}
 	
@@ -1800,7 +1804,7 @@ static int vlsi_irda_resume(struct pci_dev *pdev)
 		 * now we explicitly set pdev->current_state = 0 after enabling the
 		 * device and independently resume_ok should catch any garbage config.
 		 */
-		IRDA_WARNING("%s - hm, nothing to resume?\n", __func__);
+		net_warn_ratelimited("%s - hm, nothing to resume?\n", __func__);
 		mutex_unlock(&idev->mtx);
 		return 0;
 	}
@@ -1837,7 +1841,8 @@ static int __init vlsi_mod_init(void)
 	int	i, ret;
 
 	if (clksrc < 0  ||  clksrc > 3) {
-		IRDA_ERROR("%s: invalid clksrc=%d\n", drivername, clksrc);
+		net_err_ratelimited("%s: invalid clksrc=%d\n",
+				    drivername, clksrc);
 		return -1;
 	}
 
@@ -1850,7 +1855,10 @@ static int __init vlsi_mod_init(void)
 			case 64:
 				break;
 			default:
-				IRDA_WARNING("%s: invalid %s ringsize %d, using default=8", drivername, (i)?"rx":"tx", ringsize[i]);
+				net_warn_ratelimited("%s: invalid %s ringsize %d, using default=8\n",
+						     drivername,
+						     i ? "rx" : "tx",
+						     ringsize[i]);
 				ringsize[i] = 8;
 				break;
 		}
diff --git a/drivers/net/irda/vlsi_ir.h b/drivers/net/irda/vlsi_ir.h
index 56399204e68..f9119c6d2a0 100644
--- a/drivers/net/irda/vlsi_ir.h
+++ b/drivers/net/irda/vlsi_ir.h
@@ -615,7 +615,8 @@ static inline void rd_set_addr_status(struct ring_descr *rd, dma_addr_t a, u8 s)
 	 */
 
 	if ((a & ~DMA_MASK_MSTRPAGE)>>24 != MSTRPAGE_VALUE) {
-		IRDA_ERROR("%s: pci busaddr inconsistency!\n", __func__);
+		net_err_ratelimited("%s: pci busaddr inconsistency!\n",
+				    __func__);
 		dump_stack();
 		return;
 	}
diff --git a/drivers/net/irda/w83977af_ir.c b/drivers/net/irda/w83977af_ir.c
index 11dbdf36d9c..86ca123887d 100644
--- a/drivers/net/irda/w83977af_ir.c
+++ b/drivers/net/irda/w83977af_ir.c
@@ -236,10 +236,11 @@ static int w83977af_open(int i, unsigned int iobase, unsigned int irq,
 
 	err = register_netdev(dev);
 	if (err) {
-		IRDA_ERROR("%s(), register_netdevice() failed!\n", __func__);
+		net_err_ratelimited("%s(), register_netdevice() failed!\n",
+				    __func__);
 		goto err_out3;
 	}
-	IRDA_MESSAGE("IrDA: Registered device %s\n", dev->name);
+	net_info_ratelimited("IrDA: Registered device %s\n", dev->name);
 
 	/* Need to store self somewhere */
 	dev_self[i] = self;
@@ -392,8 +393,8 @@ static int w83977af_probe(int iobase, int irq, int dma)
 			switch_bank(iobase, SET7);
 			outb(0x40, iobase+7);
 			
-			IRDA_MESSAGE("W83977AF (IR) driver loaded. "
-				     "Version: 0x%02x\n", version);
+			net_info_ratelimited("W83977AF (IR) driver loaded. Version: 0x%02x\n",
+					     version);
 			
 			return 0;
 		} else {
diff --git a/include/net/irda/irda.h b/include/net/irda/irda.h
index 42aa054aa67..4ff18bdc63d 100644
--- a/include/net/irda/irda.h
+++ b/include/net/irda/irda.h
@@ -77,10 +77,6 @@ do { if(!(expr)) { \
 #define IRDA_ASSERT_LABEL(label)
 #endif /* CONFIG_IRDA_DEBUG */
 
-#define IRDA_ERROR		net_err_ratelimited
-#define IRDA_WARNING		net_warn_ratelimited
-#define IRDA_MESSAGE		net_info_ratelimited
-
 /*
  *  Magic numbers used by Linux-IrDA. Random numbers which must be unique to 
  *  give the best protection
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 980bc2670a1..4b04ae06b28 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -201,16 +201,16 @@ static void irda_connect_confirm(void *instance, void *sap,
 	switch (sk->sk_type) {
 	case SOCK_STREAM:
 		if (max_sdu_size != 0) {
-			IRDA_ERROR("%s: max_sdu_size must be 0\n",
-				   __func__);
+			net_err_ratelimited("%s: max_sdu_size must be 0\n",
+					    __func__);
 			return;
 		}
 		self->max_data_size = irttp_get_max_seg_size(self->tsap);
 		break;
 	case SOCK_SEQPACKET:
 		if (max_sdu_size == 0) {
-			IRDA_ERROR("%s: max_sdu_size cannot be 0\n",
-				   __func__);
+			net_err_ratelimited("%s: max_sdu_size cannot be 0\n",
+					    __func__);
 			return;
 		}
 		self->max_data_size = max_sdu_size;
@@ -262,8 +262,8 @@ static void irda_connect_indication(void *instance, void *sap,
 	switch (sk->sk_type) {
 	case SOCK_STREAM:
 		if (max_sdu_size != 0) {
-			IRDA_ERROR("%s: max_sdu_size must be 0\n",
-				   __func__);
+			net_err_ratelimited("%s: max_sdu_size must be 0\n",
+					    __func__);
 			kfree_skb(skb);
 			return;
 		}
@@ -271,8 +271,8 @@ static void irda_connect_indication(void *instance, void *sap,
 		break;
 	case SOCK_SEQPACKET:
 		if (max_sdu_size == 0) {
-			IRDA_ERROR("%s: max_sdu_size cannot be 0\n",
-				   __func__);
+			net_err_ratelimited("%s: max_sdu_size cannot be 0\n",
+					    __func__);
 			kfree_skb(skb);
 			return;
 		}
@@ -368,7 +368,7 @@ static void irda_getvalue_confirm(int result, __u16 obj_id,
 
 	self = priv;
 	if (!self) {
-		IRDA_WARNING("%s: lost myself!\n", __func__);
+		net_warn_ratelimited("%s: lost myself!\n", __func__);
 		return;
 	}
 
@@ -417,7 +417,7 @@ static void irda_selective_discovery_indication(discinfo_t *discovery,
 
 	self = priv;
 	if (!self) {
-		IRDA_WARNING("%s: lost myself!\n", __func__);
+		net_warn_ratelimited("%s: lost myself!\n", __func__);
 		return;
 	}
 
@@ -505,7 +505,7 @@ static int irda_open_lsap(struct irda_sock *self, int pid)
 	notify_t notify;
 
 	if (self->lsap) {
-		IRDA_WARNING("%s(), busy!\n", __func__);
+		net_warn_ratelimited("%s(), busy!\n", __func__);
 		return -EBUSY;
 	}
 
@@ -541,8 +541,8 @@ static int irda_find_lsap_sel(struct irda_sock *self, char *name)
 	IRDA_DEBUG(2, "%s(%p, %s)\n", __func__, self, name);
 
 	if (self->iriap) {
-		IRDA_WARNING("%s(): busy with a previous query\n",
-			     __func__);
+		net_warn_ratelimited("%s(): busy with a previous query\n",
+				     __func__);
 		return -EBUSY;
 	}
 
@@ -2129,8 +2129,8 @@ static int irda_setsockopt(struct socket *sock, int level, int optname,
 				   __func__, opt);
 			self->max_sdu_size_rx = opt;
 		} else {
-			IRDA_WARNING("%s: not allowed to set MAXSDUSIZE for this socket type!\n",
-				     __func__);
+			net_warn_ratelimited("%s: not allowed to set MAXSDUSIZE for this socket type!\n",
+					     __func__);
 			err = -ENOPROTOOPT;
 			goto out;
 		}
@@ -2441,8 +2441,8 @@ bed:
 
 		/* Check that we can proceed with IAP */
 		if (self->iriap) {
-			IRDA_WARNING("%s: busy with a previous query\n",
-				     __func__);
+			net_warn_ratelimited("%s: busy with a previous query\n",
+					     __func__);
 			kfree(ias_opt);
 			err = -EBUSY;
 			goto out;
diff --git a/net/irda/ircomm/ircomm_core.c b/net/irda/ircomm/ircomm_core.c
index 4490a675b1b..b77fe8c8623 100644
--- a/net/irda/ircomm/ircomm_core.c
+++ b/net/irda/ircomm/ircomm_core.c
@@ -69,7 +69,8 @@ static int __init ircomm_init(void)
 {
 	ircomm = hashbin_new(HB_LOCK);
 	if (ircomm == NULL) {
-		IRDA_ERROR("%s(), can't allocate hashbin!\n", __func__);
+		net_err_ratelimited("%s(), can't allocate hashbin!\n",
+				    __func__);
 		return -ENOMEM;
 	}
 
@@ -83,7 +84,7 @@ static int __init ircomm_init(void)
 	}
 #endif /* CONFIG_PROC_FS */
 
-	IRDA_MESSAGE("IrCOMM protocol (Dag Brattli)\n");
+	net_info_ratelimited("IrCOMM protocol (Dag Brattli)\n");
 
 	return 0;
 }
diff --git a/net/irda/ircomm/ircomm_lmp.c b/net/irda/ircomm/ircomm_lmp.c
index 6536114adf3..05767e3ef0d 100644
--- a/net/irda/ircomm/ircomm_lmp.c
+++ b/net/irda/ircomm/ircomm_lmp.c
@@ -204,7 +204,7 @@ static int ircomm_lmp_data_request(struct ircomm_cb *self,
 	}
 	ret = irlmp_data_request(self->lsap, skb);
 	if (ret) {
-		IRDA_ERROR("%s(), failed\n", __func__);
+		net_err_ratelimited("%s(), failed\n", __func__);
 		/* irlmp_data_request already free the packet */
 	}
 
diff --git a/net/irda/ircomm/ircomm_param.c b/net/irda/ircomm/ircomm_param.c
index f80b1a6a244..c203fbb8cdd 100644
--- a/net/irda/ircomm/ircomm_param.c
+++ b/net/irda/ircomm/ircomm_param.c
@@ -130,7 +130,8 @@ int ircomm_param_request(struct ircomm_tty_cb *self, __u8 pi, int flush)
 	count = irda_param_insert(self, pi, skb_tail_pointer(skb),
 				  skb_tailroom(skb), &ircomm_param_info);
 	if (count < 0) {
-		IRDA_WARNING("%s(), no room for parameter!\n", __func__);
+		net_warn_ratelimited("%s(), no room for parameter!\n",
+				     __func__);
 		spin_unlock_irqrestore(&self->spinlock, flags);
 		return -1;
 	}
diff --git a/net/irda/ircomm/ircomm_ttp.c b/net/irda/ircomm/ircomm_ttp.c
index d362d711b79..abe9a5ab8d3 100644
--- a/net/irda/ircomm/ircomm_ttp.c
+++ b/net/irda/ircomm/ircomm_ttp.c
@@ -188,7 +188,7 @@ static int ircomm_ttp_data_request(struct ircomm_cb *self,
 
 	ret = irttp_data_request(self->tsap, skb);
 	if (ret) {
-		IRDA_ERROR("%s(), failed\n", __func__);
+		net_err_ratelimited("%s(), failed\n", __func__);
 		/* irttp_data_request already free the packet */
 	}
 
@@ -237,8 +237,8 @@ static void ircomm_ttp_connect_confirm(void *instance, void *sap,
 	IRDA_ASSERT(qos != NULL, goto out;);
 
 	if (max_sdu_size != TTP_SAR_DISABLE) {
-		IRDA_ERROR("%s(), SAR not allowed for IrCOMM!\n",
-			   __func__);
+		net_err_ratelimited("%s(), SAR not allowed for IrCOMM!\n",
+				    __func__);
 		goto out;
 	}
 
@@ -278,8 +278,8 @@ static void ircomm_ttp_connect_indication(void *instance, void *sap,
 	IRDA_ASSERT(qos != NULL, goto out;);
 
 	if (max_sdu_size != TTP_SAR_DISABLE) {
-		IRDA_ERROR("%s(), SAR not allowed for IrCOMM!\n",
-			   __func__);
+		net_err_ratelimited("%s(), SAR not allowed for IrCOMM!\n",
+				    __func__);
 		goto out;
 	}
 
diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c
index 61ceb4cdb4a..11b0a5ed025 100644
--- a/net/irda/ircomm/ircomm_tty.c
+++ b/net/irda/ircomm/ircomm_tty.c
@@ -147,7 +147,8 @@ static int __init ircomm_tty_init(void)
 		return -ENOMEM;
 	ircomm_tty = hashbin_new(HB_LOCK);
 	if (ircomm_tty == NULL) {
-		IRDA_ERROR("%s(), can't allocate hashbin!\n", __func__);
+		net_err_ratelimited("%s(), can't allocate hashbin!\n",
+				    __func__);
 		put_tty_driver(driver);
 		return -ENOMEM;
 	}
@@ -163,8 +164,8 @@ static int __init ircomm_tty_init(void)
 	driver->flags           = TTY_DRIVER_REAL_RAW;
 	tty_set_operations(driver, &ops);
 	if (tty_register_driver(driver)) {
-		IRDA_ERROR("%s(): Couldn't register serial driver\n",
-			   __func__);
+		net_err_ratelimited("%s(): Couldn't register serial driver\n",
+				    __func__);
 		put_tty_driver(driver);
 		return -1;
 	}
@@ -199,8 +200,8 @@ static void __exit ircomm_tty_cleanup(void)
 
 	ret = tty_unregister_driver(driver);
 	if (ret) {
-		IRDA_ERROR("%s(), failed to unregister driver\n",
-			   __func__);
+		net_err_ratelimited("%s(), failed to unregister driver\n",
+				    __func__);
 		return;
 	}
 
@@ -256,7 +257,7 @@ static int ircomm_tty_startup(struct ircomm_tty_cb *self)
 	/* Connect IrCOMM link with remote device */
 	ret = ircomm_tty_attach_cable(self);
 	if (ret < 0) {
-		IRDA_ERROR("%s(), error attaching cable!\n", __func__);
+		net_err_ratelimited("%s(), error attaching cable!\n", __func__);
 		goto err;
 	}
 
@@ -389,10 +390,8 @@ static int ircomm_tty_install(struct tty_driver *driver, struct tty_struct *tty)
 	if (!self) {
 		/* No, so make new instance */
 		self = kzalloc(sizeof(struct ircomm_tty_cb), GFP_KERNEL);
-		if (self == NULL) {
-			IRDA_ERROR("%s(), kmalloc failed!\n", __func__);
+		if (self == NULL)
 			return -ENOMEM;
-		}
 
 		tty_port_init(&self->port);
 		self->port.ops = &ircomm_port_ops;
@@ -469,8 +468,8 @@ static int ircomm_tty_open(struct tty_struct *tty, struct file *filp)
 
 		if (wait_event_interruptible(self->port.close_wait,
 				!test_bit(ASYNCB_CLOSING, &self->port.flags))) {
-			IRDA_WARNING("%s - got signal while blocking on ASYNC_CLOSING!\n",
-				     __func__);
+			net_warn_ratelimited("%s - got signal while blocking on ASYNC_CLOSING!\n",
+					     __func__);
 			return -ERESTARTSYS;
 		}
 
diff --git a/net/irda/ircomm/ircomm_tty_attach.c b/net/irda/ircomm/ircomm_tty_attach.c
index 2ee87bf387c..211904419f6 100644
--- a/net/irda/ircomm/ircomm_tty_attach.c
+++ b/net/irda/ircomm/ircomm_tty_attach.c
@@ -694,8 +694,8 @@ static int ircomm_tty_state_idle(struct ircomm_tty_cb *self,
 		self->saddr = info->saddr;
 
 		if (self->iriap) {
-			IRDA_WARNING("%s(), busy with a previous query\n",
-				     __func__);
+			net_warn_ratelimited("%s(), busy with a previous query\n",
+					     __func__);
 			return -EBUSY;
 		}
 
@@ -752,8 +752,8 @@ static int ircomm_tty_state_search(struct ircomm_tty_cb *self,
 		self->saddr = info->saddr;
 
 		if (self->iriap) {
-			IRDA_WARNING("%s(), busy with a previous query\n",
-				     __func__);
+			net_warn_ratelimited("%s(), busy with a previous query\n",
+					     __func__);
 			return -EBUSY;
 		}
 
@@ -822,8 +822,8 @@ static int ircomm_tty_state_query_parameters(struct ircomm_tty_cb *self,
 	switch (event) {
 	case IRCOMM_TTY_GOT_PARAMETERS:
 		if (self->iriap) {
-			IRDA_WARNING("%s(), busy with a previous query\n",
-				     __func__);
+			net_warn_ratelimited("%s(), busy with a previous query\n",
+					     __func__);
 			return -EBUSY;
 		}
 
diff --git a/net/irda/ircomm/ircomm_tty_ioctl.c b/net/irda/ircomm/ircomm_tty_ioctl.c
index ce943853c38..7eb06e08f8e 100644
--- a/net/irda/ircomm/ircomm_tty_ioctl.c
+++ b/net/irda/ircomm/ircomm_tty_ioctl.c
@@ -93,7 +93,8 @@ static void ircomm_tty_change_speed(struct ircomm_tty_cb *self,
 		self->settings.flow_control |= IRCOMM_RTS_CTS_IN;
 		/* This got me. Bummer. Jean II */
 		if (self->service_type == IRCOMM_3_WIRE_RAW)
-			IRDA_WARNING("%s(), enabling RTS/CTS on link that doesn't support it (3-wire-raw)\n", __func__);
+			net_warn_ratelimited("%s(), enabling RTS/CTS on link that doesn't support it (3-wire-raw)\n",
+					     __func__);
 	} else {
 		self->port.flags &= ~ASYNC_CTS_FLOW;
 		self->settings.flow_control &= ~IRCOMM_RTS_CTS_IN;
diff --git a/net/irda/irda_device.c b/net/irda/irda_device.c
index 9e0d909390f..96788db1dc3 100644
--- a/net/irda/irda_device.c
+++ b/net/irda/irda_device.c
@@ -63,14 +63,14 @@ int __init irda_device_init( void)
 {
 	dongles = hashbin_new(HB_NOLOCK);
 	if (dongles == NULL) {
-		IRDA_WARNING("IrDA: Can't allocate dongles hashbin!\n");
+		net_warn_ratelimited("IrDA: Can't allocate dongles hashbin!\n");
 		return -ENOMEM;
 	}
 	spin_lock_init(&dongles->hb_spinlock);
 
 	tasks = hashbin_new(HB_LOCK);
 	if (tasks == NULL) {
-		IRDA_WARNING("IrDA: Can't allocate tasks hashbin!\n");
+		net_warn_ratelimited("IrDA: Can't allocate tasks hashbin!\n");
 		hashbin_delete(dongles, NULL);
 		return -ENOMEM;
 	}
@@ -84,8 +84,8 @@ int __init irda_device_init( void)
 static void leftover_dongle(void *arg)
 {
 	struct dongle_reg *reg = arg;
-	IRDA_WARNING("IrDA: Dongle type %x not unregistered\n",
-		     reg->type);
+	net_warn_ratelimited("IrDA: Dongle type %x not unregistered\n",
+			     reg->type);
 }
 
 void irda_device_cleanup(void)
@@ -150,8 +150,8 @@ int irda_device_is_receiving(struct net_device *dev)
 	IRDA_DEBUG(2, "%s()\n", __func__);
 
 	if (!dev->netdev_ops->ndo_do_ioctl) {
-		IRDA_ERROR("%s: do_ioctl not impl. by device driver\n",
-			   __func__);
+		net_err_ratelimited("%s: do_ioctl not impl. by device driver\n",
+				    __func__);
 		return -1;
 	}
 
@@ -201,15 +201,15 @@ static int irda_task_kick(struct irda_task *task)
 	do {
 		timeout = task->function(task);
 		if (count++ > 100) {
-			IRDA_ERROR("%s: error in task handler!\n",
-				   __func__);
+			net_err_ratelimited("%s: error in task handler!\n",
+					    __func__);
 			irda_task_delete(task);
 			return TRUE;
 		}
 	} while ((timeout == 0) && (task->state != IRDA_TASK_DONE));
 
 	if (timeout < 0) {
-		IRDA_ERROR("%s: Error executing task!\n", __func__);
+		net_err_ratelimited("%s: Error executing task!\n", __func__);
 		irda_task_delete(task);
 		return TRUE;
 	}
diff --git a/net/irda/iriap.c b/net/irda/iriap.c
index e1b37f5a269..c2ea3443f66 100644
--- a/net/irda/iriap.c
+++ b/net/irda/iriap.c
@@ -110,8 +110,8 @@ int __init iriap_init(void)
 	/* Object repository - defined in irias_object.c */
 	irias_objects = hashbin_new(HB_LOCK);
 	if (!irias_objects) {
-		IRDA_WARNING("%s: Can't allocate irias_objects hashbin!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Can't allocate irias_objects hashbin!\n",
+				     __func__);
 		hashbin_delete(iriap, NULL);
 		return -ENOMEM;
 	}
@@ -180,10 +180,8 @@ struct iriap_cb *iriap_open(__u8 slsap_sel, int mode, void *priv,
 	IRDA_DEBUG(2, "%s()\n", __func__);
 
 	self = kzalloc(sizeof(*self), GFP_ATOMIC);
-	if (!self) {
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+	if (!self)
 		return NULL;
-	}
 
 	/*
 	 *  Initialize instance
@@ -283,7 +281,8 @@ static int iriap_register_lsap(struct iriap_cb *self, __u8 slsap_sel, int mode)
 
 	self->lsap = irlmp_open_lsap(slsap_sel, &notify, 0);
 	if (self->lsap == NULL) {
-		IRDA_ERROR("%s: Unable to allocated LSAP!\n", __func__);
+		net_err_ratelimited("%s: Unable to allocated LSAP!\n",
+				    __func__);
 		return -1;
 	}
 	self->slsap_sel = self->lsap->slsap_sel;
@@ -859,9 +858,8 @@ static int iriap_data_indication(void *instance, void *sap,
 	}
 	opcode = frame[0];
 	if (~opcode & IAP_LST) {
-		IRDA_WARNING("%s:, IrIAS multiframe commands or "
-			     "results is not implemented yet!\n",
-			     __func__);
+		net_warn_ratelimited("%s:, IrIAS multiframe commands or results is not implemented yet!\n",
+				     __func__);
 		goto out;
 	}
 
@@ -945,16 +943,16 @@ void iriap_call_indication(struct iriap_cb *self, struct sk_buff *skb)
 
 	opcode = fp[0];
 	if (~opcode & 0x80) {
-		IRDA_WARNING("%s: IrIAS multiframe commands or results "
-			     "is not implemented yet!\n", __func__);
+		net_warn_ratelimited("%s: IrIAS multiframe commands or results is not implemented yet!\n",
+				     __func__);
 		return;
 	}
 	opcode &= 0x7f; /* Mask away LST bit */
 
 	switch (opcode) {
 	case GET_INFO_BASE:
-		IRDA_WARNING("%s: GetInfoBaseDetails not implemented yet!\n",
-			     __func__);
+		net_warn_ratelimited("%s: GetInfoBaseDetails not implemented yet!\n",
+				     __func__);
 		break;
 	case GET_VALUE_BY_CLASS:
 		iriap_getvaluebyclass_indication(self, skb);
diff --git a/net/irda/iriap_event.c b/net/irda/iriap_event.c
index 703774e29e3..09de4efc73a 100644
--- a/net/irda/iriap_event.c
+++ b/net/irda/iriap_event.c
@@ -368,10 +368,8 @@ static void state_r_disconnect(struct iriap_cb *self, IRIAP_EVENT event,
 	switch (event) {
 	case IAP_LM_CONNECT_INDICATION:
 		tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC);
-		if (tx_skb == NULL) {
-			IRDA_WARNING("%s: unable to malloc!\n", __func__);
+		if (tx_skb == NULL)
 			return;
-		}
 
 		/* Reserve space for MUX_CONTROL and LAP header */
 		skb_reserve(tx_skb, LMP_MAX_HEADER);
diff --git a/net/irda/irias_object.c b/net/irda/irias_object.c
index f07ed9fd579..cd53692fe8c 100644
--- a/net/irda/irias_object.c
+++ b/net/irda/irias_object.c
@@ -52,16 +52,16 @@ struct ias_object *irias_new_object( char *name, int id)
 
 	obj = kzalloc(sizeof(struct ias_object), GFP_ATOMIC);
 	if (obj == NULL) {
-		IRDA_WARNING("%s(), Unable to allocate object!\n",
-			     __func__);
+		net_warn_ratelimited("%s(), Unable to allocate object!\n",
+				     __func__);
 		return NULL;
 	}
 
 	obj->magic = IAS_OBJECT_MAGIC;
 	obj->name = kstrndup(name, IAS_MAX_CLASSNAME, GFP_ATOMIC);
 	if (!obj->name) {
-		IRDA_WARNING("%s(), Unable to allocate name!\n",
-			     __func__);
+		net_warn_ratelimited("%s(), Unable to allocate name!\n",
+				     __func__);
 		kfree(obj);
 		return NULL;
 	}
@@ -73,8 +73,8 @@ struct ias_object *irias_new_object( char *name, int id)
 	obj->attribs = hashbin_new(HB_LOCK);
 
 	if (obj->attribs == NULL) {
-		IRDA_WARNING("%s(), Unable to allocate attribs!\n",
-			     __func__);
+		net_warn_ratelimited("%s(), Unable to allocate attribs!\n",
+				     __func__);
 		kfree(obj->name);
 		kfree(obj);
 		return NULL;
@@ -269,8 +269,8 @@ int irias_object_change_attribute(char *obj_name, char *attrib_name,
 	/* Find object */
 	obj = hashbin_lock_find(irias_objects, 0, obj_name);
 	if (obj == NULL) {
-		IRDA_WARNING("%s: Unable to find object: %s\n", __func__,
-			     obj_name);
+		net_warn_ratelimited("%s: Unable to find object: %s\n",
+				     __func__, obj_name);
 		return -1;
 	}
 
@@ -280,8 +280,8 @@ int irias_object_change_attribute(char *obj_name, char *attrib_name,
 	/* Find attribute */
 	attrib = hashbin_find(obj->attribs, 0, attrib_name);
 	if (attrib == NULL) {
-		IRDA_WARNING("%s: Unable to find attribute: %s\n",
-			     __func__, attrib_name);
+		net_warn_ratelimited("%s: Unable to find attribute: %s\n",
+				     __func__, attrib_name);
 		spin_unlock_irqrestore(&obj->attribs->hb_spinlock, flags);
 		return -1;
 	}
@@ -322,8 +322,8 @@ void irias_add_integer_attrib(struct ias_object *obj, char *name, int value,
 
 	attrib = kzalloc(sizeof(struct ias_attrib), GFP_ATOMIC);
 	if (attrib == NULL) {
-		IRDA_WARNING("%s: Unable to allocate attribute!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Unable to allocate attribute!\n",
+				     __func__);
 		return;
 	}
 
@@ -333,8 +333,8 @@ void irias_add_integer_attrib(struct ias_object *obj, char *name, int value,
 	/* Insert value */
 	attrib->value = irias_new_integer_value(value);
 	if (!attrib->name || !attrib->value) {
-		IRDA_WARNING("%s: Unable to allocate attribute!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Unable to allocate attribute!\n",
+				     __func__);
 		if (attrib->value)
 			irias_delete_value(attrib->value);
 		kfree(attrib->name);
@@ -366,8 +366,8 @@ void irias_add_octseq_attrib(struct ias_object *obj, char *name, __u8 *octets,
 
 	attrib = kzalloc(sizeof(struct ias_attrib), GFP_ATOMIC);
 	if (attrib == NULL) {
-		IRDA_WARNING("%s: Unable to allocate attribute!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Unable to allocate attribute!\n",
+				     __func__);
 		return;
 	}
 
@@ -376,8 +376,8 @@ void irias_add_octseq_attrib(struct ias_object *obj, char *name, __u8 *octets,
 
 	attrib->value = irias_new_octseq_value( octets, len);
 	if (!attrib->name || !attrib->value) {
-		IRDA_WARNING("%s: Unable to allocate attribute!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Unable to allocate attribute!\n",
+				     __func__);
 		if (attrib->value)
 			irias_delete_value(attrib->value);
 		kfree(attrib->name);
@@ -408,8 +408,8 @@ void irias_add_string_attrib(struct ias_object *obj, char *name, char *value,
 
 	attrib = kzalloc(sizeof( struct ias_attrib), GFP_ATOMIC);
 	if (attrib == NULL) {
-		IRDA_WARNING("%s: Unable to allocate attribute!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Unable to allocate attribute!\n",
+				     __func__);
 		return;
 	}
 
@@ -418,8 +418,8 @@ void irias_add_string_attrib(struct ias_object *obj, char *name, char *value,
 
 	attrib->value = irias_new_string_value(value);
 	if (!attrib->name || !attrib->value) {
-		IRDA_WARNING("%s: Unable to allocate attribute!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Unable to allocate attribute!\n",
+				     __func__);
 		if (attrib->value)
 			irias_delete_value(attrib->value);
 		kfree(attrib->name);
@@ -442,10 +442,8 @@ struct ias_value *irias_new_integer_value(int integer)
 	struct ias_value *value;
 
 	value = kzalloc(sizeof(struct ias_value), GFP_ATOMIC);
-	if (value == NULL) {
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+	if (value == NULL)
 		return NULL;
-	}
 
 	value->type = IAS_INTEGER;
 	value->len = 4;
@@ -467,16 +465,14 @@ struct ias_value *irias_new_string_value(char *string)
 	struct ias_value *value;
 
 	value = kzalloc(sizeof(struct ias_value), GFP_ATOMIC);
-	if (value == NULL) {
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+	if (value == NULL)
 		return NULL;
-	}
 
 	value->type = IAS_STRING;
 	value->charset = CS_ASCII;
 	value->t.string = kstrndup(string, IAS_MAX_STRING, GFP_ATOMIC);
 	if (!value->t.string) {
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+		net_warn_ratelimited("%s: Unable to kmalloc!\n", __func__);
 		kfree(value);
 		return NULL;
 	}
@@ -498,10 +494,8 @@ struct ias_value *irias_new_octseq_value(__u8 *octseq , int len)
 	struct ias_value *value;
 
 	value = kzalloc(sizeof(struct ias_value), GFP_ATOMIC);
-	if (value == NULL) {
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+	if (value == NULL)
 		return NULL;
-	}
 
 	value->type = IAS_OCT_SEQ;
 	/* Check length */
@@ -511,7 +505,7 @@ struct ias_value *irias_new_octseq_value(__u8 *octseq , int len)
 
 	value->t.oct_seq = kmemdup(octseq, len, GFP_ATOMIC);
 	if (value->t.oct_seq == NULL){
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+		net_warn_ratelimited("%s: Unable to kmalloc!\n", __func__);
 		kfree(value);
 		return NULL;
 	}
@@ -523,10 +517,8 @@ struct ias_value *irias_new_missing_value(void)
 	struct ias_value *value;
 
 	value = kzalloc(sizeof(struct ias_value), GFP_ATOMIC);
-	if (value == NULL) {
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+	if (value == NULL)
 		return NULL;
-	}
 
 	value->type = IAS_MISSING;
 
diff --git a/net/irda/irlan/irlan_client.c b/net/irda/irlan/irlan_client.c
index 42cf1390ce9..f8eea02843f 100644
--- a/net/irda/irlan/irlan_client.c
+++ b/net/irda/irlan/irlan_client.c
@@ -323,34 +323,34 @@ static void print_ret_code(__u8 code)
 		printk(KERN_INFO "Success\n");
 		break;
 	case 1:
-		IRDA_WARNING("IrLAN: Insufficient resources\n");
+		net_warn_ratelimited("IrLAN: Insufficient resources\n");
 		break;
 	case 2:
-		IRDA_WARNING("IrLAN: Invalid command format\n");
+		net_warn_ratelimited("IrLAN: Invalid command format\n");
 		break;
 	case 3:
-		IRDA_WARNING("IrLAN: Command not supported\n");
+		net_warn_ratelimited("IrLAN: Command not supported\n");
 		break;
 	case 4:
-		IRDA_WARNING("IrLAN: Parameter not supported\n");
+		net_warn_ratelimited("IrLAN: Parameter not supported\n");
 		break;
 	case 5:
-		IRDA_WARNING("IrLAN: Value not supported\n");
+		net_warn_ratelimited("IrLAN: Value not supported\n");
 		break;
 	case 6:
-		IRDA_WARNING("IrLAN: Not open\n");
+		net_warn_ratelimited("IrLAN: Not open\n");
 		break;
 	case 7:
-		IRDA_WARNING("IrLAN: Authentication required\n");
+		net_warn_ratelimited("IrLAN: Authentication required\n");
 		break;
 	case 8:
-		IRDA_WARNING("IrLAN: Invalid password\n");
+		net_warn_ratelimited("IrLAN: Invalid password\n");
 		break;
 	case 9:
-		IRDA_WARNING("IrLAN: Protocol error\n");
+		net_warn_ratelimited("IrLAN: Protocol error\n");
 		break;
 	case 255:
-		IRDA_WARNING("IrLAN: Asynchronous status\n");
+		net_warn_ratelimited("IrLAN: Asynchronous status\n");
 		break;
 	}
 }
@@ -380,7 +380,7 @@ void irlan_client_parse_response(struct irlan_cb *self, struct sk_buff *skb)
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
 	if (!skb) {
-		IRDA_ERROR("%s(), Got NULL skb!\n", __func__);
+		net_err_ratelimited("%s(), Got NULL skb!\n", __func__);
 		return;
 	}
 	frame = skb->data;
diff --git a/net/irda/irlan/irlan_client_event.c b/net/irda/irlan/irlan_client_event.c
index 8d5a8ebc444..f9d11bf3815 100644
--- a/net/irda/irlan/irlan_client_event.c
+++ b/net/irda/irlan/irlan_client_event.c
@@ -100,8 +100,8 @@ static int irlan_client_state_idle(struct irlan_cb *self, IRLAN_EVENT event,
 	switch (event) {
 	case IRLAN_DISCOVERY_INDICATION:
 		if (self->client.iriap) {
-			IRDA_WARNING("%s(), busy with a previous query\n",
-				     __func__);
+			net_warn_ratelimited("%s(), busy with a previous query\n",
+					     __func__);
 			return -EBUSY;
 		}
 
diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c
index 5a2d0a69552..cc60b4a282a 100644
--- a/net/irda/irlan/irlan_common.c
+++ b/net/irda/irlan/irlan_common.c
@@ -437,7 +437,8 @@ static void irlan_disconnect_indication(void *instance,
 		IRDA_DEBUG(2, "%s(), IrLMP connect failed\n", __func__ );
 		break;
 	default:
-		IRDA_ERROR("%s(), Unknown disconnect reason\n", __func__);
+		net_err_ratelimited("%s(), Unknown disconnect reason\n",
+				    __func__);
 		break;
 	}
 
diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c
index dc13f1a45f2..94b948ef36f 100644
--- a/net/irda/irlan/irlan_eth.c
+++ b/net/irda/irlan/irlan_eth.c
@@ -320,7 +320,7 @@ static void irlan_eth_set_multicast_list(struct net_device *dev)
 
 	if (dev->flags & IFF_PROMISC) {
 		/* Enable promiscuous mode */
-		IRDA_WARNING("Promiscuous mode not implemented by IrLAN!\n");
+		net_warn_ratelimited("Promiscuous mode not implemented by IrLAN!\n");
 	} else if ((dev->flags & IFF_ALLMULTI) ||
 		 netdev_mc_count(dev) > HW_MAX_ADDRS) {
 		/* Disable promiscuous mode, use normal mode. */
diff --git a/net/irda/irlap.c b/net/irda/irlap.c
index a778df55f5d..2e3bc6ccf4b 100644
--- a/net/irda/irlap.c
+++ b/net/irda/irlap.c
@@ -85,8 +85,8 @@ int __init irlap_init(void)
 	/* Allocate master array */
 	irlap = hashbin_new(HB_LOCK);
 	if (irlap == NULL) {
-		IRDA_ERROR("%s: can't allocate irlap hashbin!\n",
-			   __func__);
+		net_err_ratelimited("%s: can't allocate irlap hashbin!\n",
+				    __func__);
 		return -ENOMEM;
 	}
 
@@ -491,7 +491,8 @@ void irlap_disconnect_indication(struct irlap_cb *self, LAP_REASON reason)
 						 reason, NULL);
 		break;
 	default:
-		IRDA_ERROR("%s: Unknown reason %d\n", __func__, reason);
+		net_err_ratelimited("%s: Unknown reason %d\n",
+				    __func__, reason);
 	}
 }
 
@@ -540,8 +541,8 @@ void irlap_discovery_request(struct irlap_cb *self, discovery_t *discovery)
 	self->discovery_log = hashbin_new(HB_NOLOCK);
 
 	if (self->discovery_log == NULL) {
-		IRDA_WARNING("%s(), Unable to allocate discovery log!\n",
-			     __func__);
+		net_warn_ratelimited("%s(), Unable to allocate discovery log!\n",
+				     __func__);
 		return;
 	}
 
@@ -625,10 +626,10 @@ void irlap_status_indication(struct irlap_cb *self, int quality_of_link)
 {
 	switch (quality_of_link) {
 	case STATUS_NO_ACTIVITY:
-		IRDA_MESSAGE("IrLAP, no activity on link!\n");
+		net_info_ratelimited("IrLAP, no activity on link!\n");
 		break;
 	case STATUS_NOISY:
-		IRDA_MESSAGE("IrLAP, noisy link!\n");
+		net_info_ratelimited("IrLAP, noisy link!\n");
 		break;
 	default:
 		break;
diff --git a/net/irda/irlap_event.c b/net/irda/irlap_event.c
index ccd214f9d19..5f4a84eb35c 100644
--- a/net/irda/irlap_event.c
+++ b/net/irda/irlap_event.c
@@ -572,9 +572,8 @@ static int irlap_state_query(struct irlap_cb *self, IRLAP_EVENT event,
 			   info->discovery->data.daddr);
 
 		if (!self->discovery_log) {
-			IRDA_WARNING("%s: discovery log is gone! "
-				     "maybe the discovery timeout has been set"
-				     " too short?\n", __func__);
+			net_warn_ratelimited("%s: discovery log is gone! maybe the discovery timeout has been set too short?\n",
+					     __func__);
 			break;
 		}
 		hashbin_insert(self->discovery_log,
diff --git a/net/irda/irlap_frame.c b/net/irda/irlap_frame.c
index a37998c6273..90ef03658a7 100644
--- a/net/irda/irlap_frame.c
+++ b/net/irda/irlap_frame.c
@@ -421,7 +421,7 @@ static void irlap_recv_discovery_xid_rsp(struct irlap_cb *self,
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
 	if (!pskb_may_pull(skb, sizeof(struct xid_frame))) {
-		IRDA_ERROR("%s: frame too short!\n", __func__);
+		net_err_ratelimited("%s: frame too short!\n", __func__);
 		return;
 	}
 
@@ -438,7 +438,7 @@ static void irlap_recv_discovery_xid_rsp(struct irlap_cb *self,
 	}
 
 	if ((discovery = kzalloc(sizeof(discovery_t), GFP_ATOMIC)) == NULL) {
-		IRDA_WARNING("%s: kmalloc failed!\n", __func__);
+		net_warn_ratelimited("%s: kmalloc failed!\n", __func__);
 		return;
 	}
 
@@ -492,7 +492,7 @@ static void irlap_recv_discovery_xid_cmd(struct irlap_cb *self,
 	char *text;
 
 	if (!pskb_may_pull(skb, sizeof(struct xid_frame))) {
-		IRDA_ERROR("%s: frame too short!\n", __func__);
+		net_err_ratelimited("%s: frame too short!\n", __func__);
 		return;
 	}
 
@@ -536,8 +536,8 @@ static void irlap_recv_discovery_xid_cmd(struct irlap_cb *self,
 		/* Check if things are sane at this point... */
 		if((discovery_info == NULL) ||
 		   !pskb_may_pull(skb, 3)) {
-			IRDA_ERROR("%s: discovery frame too short!\n",
-				   __func__);
+			net_err_ratelimited("%s: discovery frame too short!\n",
+					    __func__);
 			return;
 		}
 
@@ -545,10 +545,8 @@ static void irlap_recv_discovery_xid_cmd(struct irlap_cb *self,
 		 *  We now have some discovery info to deliver!
 		 */
 		discovery = kzalloc(sizeof(discovery_t), GFP_ATOMIC);
-		if (!discovery) {
-			IRDA_WARNING("%s: unable to malloc!\n", __func__);
+		if (!discovery)
 			return;
-		}
 
 		discovery->data.daddr = info->daddr;
 		discovery->data.saddr = self->saddr;
@@ -1170,7 +1168,7 @@ static void irlap_recv_frmr_frame(struct irlap_cb *self, struct sk_buff *skb,
 	IRDA_ASSERT(info != NULL, return;);
 
 	if (!pskb_may_pull(skb, 4)) {
-		IRDA_ERROR("%s: frame too short!\n", __func__);
+		net_err_ratelimited("%s: frame too short!\n", __func__);
 		return;
 	}
 
@@ -1259,7 +1257,7 @@ static void irlap_recv_test_frame(struct irlap_cb *self, struct sk_buff *skb,
 	IRDA_DEBUG(2, "%s()\n", __func__);
 
 	if (!pskb_may_pull(skb, sizeof(*frame))) {
-		IRDA_ERROR("%s: frame too short!\n", __func__);
+		net_err_ratelimited("%s: frame too short!\n", __func__);
 		return;
 	}
 	frame = (struct test_frame *) skb->data;
@@ -1328,13 +1326,13 @@ int irlap_driver_rcv(struct sk_buff *skb, struct net_device *dev,
 	 * share and non linear skbs. This should never happen, so
 	 * we don't need to be clever about it. Jean II */
 	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
-		IRDA_ERROR("%s: can't clone shared skb!\n", __func__);
+		net_err_ratelimited("%s: can't clone shared skb!\n", __func__);
 		goto err;
 	}
 
 	/* Check if frame is large enough for parsing */
 	if (!pskb_may_pull(skb, 2)) {
-		IRDA_ERROR("%s: frame too short!\n", __func__);
+		net_err_ratelimited("%s: frame too short!\n", __func__);
 		goto err;
 	}
 
@@ -1383,8 +1381,8 @@ int irlap_driver_rcv(struct sk_buff *skb, struct net_device *dev,
 			irlap_recv_srej_frame(self, skb, &info, command);
 			break;
 		default:
-			IRDA_WARNING("%s: Unknown S-frame %02x received!\n",
-				__func__, info.control);
+			net_warn_ratelimited("%s: Unknown S-frame %02x received!\n",
+					     __func__, info.control);
 			break;
 		}
 		goto out;
@@ -1421,8 +1419,8 @@ int irlap_driver_rcv(struct sk_buff *skb, struct net_device *dev,
 		irlap_recv_ui_frame(self, skb, &info);
 		break;
 	default:
-		IRDA_WARNING("%s: Unknown frame %02x received!\n",
-				__func__, info.control);
+		net_warn_ratelimited("%s: Unknown frame %02x received!\n",
+				     __func__, info.control);
 		break;
 	}
 out:
diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c
index a5f28d421ea..6178e71f3a5 100644
--- a/net/irda/irlmp.c
+++ b/net/irda/irlmp.c
@@ -170,10 +170,8 @@ struct lsap_cb *irlmp_open_lsap(__u8 slsap_sel, notify_t *notify, __u8 pid)
 
 	/* Allocate new instance of a LSAP connection */
 	self = kzalloc(sizeof(struct lsap_cb), GFP_ATOMIC);
-	if (self == NULL) {
-		IRDA_ERROR("%s: can't allocate memory\n", __func__);
+	if (self == NULL)
 		return NULL;
-	}
 
 	self->magic = LMP_LSAP_MAGIC;
 	self->slsap_sel = slsap_sel;
@@ -297,10 +295,8 @@ void irlmp_register_link(struct irlap_cb *irlap, __u32 saddr, notify_t *notify)
 	 *  Allocate new instance of a LSAP connection
 	 */
 	lap = kzalloc(sizeof(struct lap_cb), GFP_KERNEL);
-	if (lap == NULL) {
-		IRDA_ERROR("%s: unable to kmalloc\n", __func__);
+	if (lap == NULL)
 		return;
-	}
 
 	lap->irlap = irlap;
 	lap->magic = LMP_LAP_MAGIC;
@@ -311,7 +307,8 @@ void irlmp_register_link(struct irlap_cb *irlap, __u32 saddr, notify_t *notify)
 #endif
 	lap->lsaps = hashbin_new(HB_LOCK);
 	if (lap->lsaps == NULL) {
-		IRDA_WARNING("%s(), unable to kmalloc lsaps\n", __func__);
+		net_warn_ratelimited("%s(), unable to kmalloc lsaps\n",
+				     __func__);
 		kfree(lap);
 		return;
 	}
@@ -852,8 +849,8 @@ void irlmp_do_discovery(int nslots)
 
 	/* Make sure the value is sane */
 	if ((nslots != 1) && (nslots != 6) && (nslots != 8) && (nslots != 16)){
-		IRDA_WARNING("%s: invalid value for number of slots!\n",
-			     __func__);
+		net_warn_ratelimited("%s: invalid value for number of slots!\n",
+				     __func__);
 		nslots = sysctl_discovery_slots = 8;
 	}
 
@@ -1799,8 +1796,8 @@ static __u8 irlmp_find_free_slsap(void)
 
 			/* Make sure we terminate the loop */
 			if (wrapped++) {
-				IRDA_ERROR("%s: no more free LSAPs !\n",
-					   __func__);
+				net_err_ratelimited("%s: no more free LSAPs !\n",
+						    __func__);
 				return 0;
 			}
 		}
diff --git a/net/irda/irlmp_event.c b/net/irda/irlmp_event.c
index 9505a7d06f1..30e51f9f4ba 100644
--- a/net/irda/irlmp_event.c
+++ b/net/irda/irlmp_event.c
@@ -508,8 +508,8 @@ static int irlmp_state_disconnected(struct lsap_cb *self, IRLMP_EVENT event,
 		IRDA_DEBUG(4, "%s(), LM_CONNECT_REQUEST\n", __func__);
 
 		if (self->conn_skb) {
-			IRDA_WARNING("%s: busy with another request!\n",
-				     __func__);
+			net_warn_ratelimited("%s: busy with another request!\n",
+					     __func__);
 			return -EBUSY;
 		}
 		/* Don't forget to refcount it (see irlmp_connect_request()) */
@@ -525,8 +525,8 @@ static int irlmp_state_disconnected(struct lsap_cb *self, IRLMP_EVENT event,
 		break;
 	case LM_CONNECT_INDICATION:
 		if (self->conn_skb) {
-			IRDA_WARNING("%s: busy with another request!\n",
-				     __func__);
+			net_warn_ratelimited("%s: busy with another request!\n",
+					     __func__);
 			return -EBUSY;
 		}
 		/* Don't forget to refcount it (see irlap_driver_rcv()) */
diff --git a/net/irda/irttp.c b/net/irda/irttp.c
index 85372cfa7b9..e0b2b0d9af1 100644
--- a/net/irda/irttp.c
+++ b/net/irda/irttp.c
@@ -96,8 +96,8 @@ int __init irttp_init(void)
 
 	irttp->tsaps = hashbin_new(HB_LOCK);
 	if (!irttp->tsaps) {
-		IRDA_ERROR("%s: can't allocate IrTTP hashbin!\n",
-			   __func__);
+		net_err_ratelimited("%s: can't allocate IrTTP hashbin!\n",
+				    __func__);
 		kfree(irttp);
 		return -ENOMEM;
 	}
@@ -518,8 +518,8 @@ int irttp_close_tsap(struct tsap_cb *self)
 	if (self->connected) {
 		/* Check if disconnect is not pending */
 		if (!test_bit(0, &self->disconnect_pend)) {
-			IRDA_WARNING("%s: TSAP still connected!\n",
-				     __func__);
+			net_warn_ratelimited("%s: TSAP still connected!\n",
+					     __func__);
 			irttp_disconnect_request(self, NULL, P_NORMAL);
 		}
 		self->close_pend = TRUE;
@@ -568,13 +568,14 @@ int irttp_udata_request(struct tsap_cb *self, struct sk_buff *skb)
 
 	/* Check that nothing bad happens */
 	if (!self->connected) {
-		IRDA_WARNING("%s(), Not connected\n", __func__);
+		net_warn_ratelimited("%s(), Not connected\n", __func__);
 		ret = -ENOTCONN;
 		goto err;
 	}
 
 	if (skb->len > self->max_seg_size) {
-		IRDA_ERROR("%s(), UData is too large for IrLAP!\n", __func__);
+		net_err_ratelimited("%s(), UData is too large for IrLAP!\n",
+				    __func__);
 		ret = -EMSGSIZE;
 		goto err;
 	}
@@ -617,7 +618,7 @@ int irttp_data_request(struct tsap_cb *self, struct sk_buff *skb)
 
 	/* Check that nothing bad happens */
 	if (!self->connected) {
-		IRDA_WARNING("%s: Not connected\n", __func__);
+		net_warn_ratelimited("%s: Not connected\n", __func__);
 		ret = -ENOTCONN;
 		goto err;
 	}
@@ -627,8 +628,8 @@ int irttp_data_request(struct tsap_cb *self, struct sk_buff *skb)
 	 *  inside an IrLAP frame
 	 */
 	if ((self->tx_max_sdu_size == 0) && (skb->len > self->max_seg_size)) {
-		IRDA_ERROR("%s: SAR disabled, and data is too large for IrLAP!\n",
-			   __func__);
+		net_err_ratelimited("%s: SAR disabled, and data is too large for IrLAP!\n",
+				    __func__);
 		ret = -EMSGSIZE;
 		goto err;
 	}
@@ -640,8 +641,8 @@ int irttp_data_request(struct tsap_cb *self, struct sk_buff *skb)
 	if ((self->tx_max_sdu_size != 0) &&
 	    (self->tx_max_sdu_size != TTP_SAR_UNBOUND) &&
 	    (skb->len > self->tx_max_sdu_size)) {
-		IRDA_ERROR("%s: SAR enabled, but data is larger than TxMaxSduSize!\n",
-			   __func__);
+		net_err_ratelimited("%s: SAR enabled, but data is larger than TxMaxSduSize!\n",
+				    __func__);
 		ret = -EMSGSIZE;
 		goto err;
 	}
@@ -1249,8 +1250,8 @@ static void irttp_connect_confirm(void *instance, void *sap,
 
 		/* Any errors in the parameter list? */
 		if (ret < 0) {
-			IRDA_WARNING("%s: error extracting parameters\n",
-				     __func__);
+			net_warn_ratelimited("%s: error extracting parameters\n",
+					     __func__);
 			dev_kfree_skb(skb);
 
 			/* Do not accept this connection attempt */
@@ -1326,8 +1327,8 @@ static void irttp_connect_indication(void *instance, void *sap,
 
 		/* Any errors in the parameter list? */
 		if (ret < 0) {
-			IRDA_WARNING("%s: error extracting parameters\n",
-				     __func__);
+			net_warn_ratelimited("%s: error extracting parameters\n",
+					     __func__);
 			dev_kfree_skb(skb);
 
 			/* Do not accept this connection attempt */
diff --git a/net/irda/parameters.c b/net/irda/parameters.c
index 6d0869716bf..d7a5778262e 100644
--- a/net/irda/parameters.c
+++ b/net/irda/parameters.c
@@ -158,8 +158,8 @@ static int irda_insert_integer(void *self, __u8 *buf, int len, __u8 pi,
 	}
 	/* Check if buffer is long enough for insertion */
 	if (len < (2+p.pl)) {
-		IRDA_WARNING("%s: buffer too short for insertion!\n",
-			     __func__);
+		net_warn_ratelimited("%s: buffer too short for insertion!\n",
+				     __func__);
 		return -1;
 	}
 	IRDA_DEBUG(2, "%s(), pi=%#x, pl=%d, pi=%d\n", __func__,
@@ -184,8 +184,8 @@ static int irda_insert_integer(void *self, __u8 *buf, int len, __u8 pi,
 
 		break;
 	default:
-		IRDA_WARNING("%s: length %d not supported\n",
-			     __func__, p.pl);
+		net_warn_ratelimited("%s: length %d not supported\n",
+				     __func__, p.pl);
 		/* Skip parameter */
 		return -1;
 	}
@@ -214,9 +214,8 @@ static int irda_extract_integer(void *self, __u8 *buf, int len, __u8 pi,
 
 	/* Check if buffer is long enough for parsing */
 	if (len < (2+p.pl)) {
-		IRDA_WARNING("%s: buffer too short for parsing! "
-			     "Need %d bytes, but len is only %d\n",
-			     __func__, p.pl, len);
+		net_warn_ratelimited("%s: buffer too short for parsing! Need %d bytes, but len is only %d\n",
+				     __func__, p.pl, len);
 		return -1;
 	}
 
@@ -226,9 +225,8 @@ static int irda_extract_integer(void *self, __u8 *buf, int len, __u8 pi,
 	 * PV_INTEGER means that the handler is flexible.
 	 */
 	if (((type & PV_MASK) != PV_INTEGER) && ((type & PV_MASK) != p.pl)) {
-		IRDA_ERROR("%s: invalid parameter length! "
-			   "Expected %d bytes, but value had %d bytes!\n",
-			   __func__, type & PV_MASK, p.pl);
+		net_err_ratelimited("%s: invalid parameter length! Expected %d bytes, but value had %d bytes!\n",
+				    __func__, type & PV_MASK, p.pl);
 
 		/* Most parameters are bit/byte fields or little endian,
 		 * so it's ok to only extract a subset of it (the subset
@@ -265,8 +263,8 @@ static int irda_extract_integer(void *self, __u8 *buf, int len, __u8 pi,
 			le32_to_cpus(&p.pv.i);
 		break;
 	default:
-		IRDA_WARNING("%s: length %d not supported\n",
-			     __func__, p.pl);
+		net_warn_ratelimited("%s: length %d not supported\n",
+				     __func__, p.pl);
 
 		/* Skip parameter */
 		return p.pl+2;
@@ -304,9 +302,8 @@ static int irda_extract_string(void *self, __u8 *buf, int len, __u8 pi,
 
 	/* Check if buffer is long enough for parsing */
 	if (len < (2+p.pl)) {
-		IRDA_WARNING("%s: buffer too short for parsing! "
-			     "Need %d bytes, but len is only %d\n",
-			     __func__, p.pl, len);
+		net_warn_ratelimited("%s: buffer too short for parsing! Need %d bytes, but len is only %d\n",
+				     __func__, p.pl, len);
 		return -1;
 	}
 
@@ -343,9 +340,8 @@ static int irda_extract_octseq(void *self, __u8 *buf, int len, __u8 pi,
 
 	/* Check if buffer is long enough for parsing */
 	if (len < (2+p.pl)) {
-		IRDA_WARNING("%s: buffer too short for parsing! "
-			     "Need %d bytes, but len is only %d\n",
-			     __func__, p.pl, len);
+		net_warn_ratelimited("%s: buffer too short for parsing! Need %d bytes, but len is only %d\n",
+				     __func__, p.pl, len);
 		return -1;
 	}
 
@@ -487,7 +483,8 @@ int irda_param_insert(void *self, __u8 pi, __u8 *buf, int len,
 
 	/*  Check if handler has been implemented */
 	if (!pi_minor_info->func) {
-		IRDA_MESSAGE("%s: no handler for pi=%#x\n", __func__, pi);
+		net_info_ratelimited("%s: no handler for pi=%#x\n",
+				     __func__, pi);
 		/* Skip this parameter */
 		return -1;
 	}
@@ -544,8 +541,8 @@ static int irda_param_extract(void *self, __u8 *buf, int len,
 
 	/*  Check if handler has been implemented */
 	if (!pi_minor_info->func) {
-		IRDA_MESSAGE("%s: no handler for pi=%#x\n",
-			     __func__, buf[n]);
+		net_info_ratelimited("%s: no handler for pi=%#x\n",
+				     __func__, buf[n]);
 		/* Skip this parameter */
 		return 2 + buf[n + 1]; /* Continue */
 	}
diff --git a/net/irda/qos.c b/net/irda/qos.c
index 11a7cc0cbc2..f3b588c17d3 100644
--- a/net/irda/qos.c
+++ b/net/irda/qos.c
@@ -200,8 +200,8 @@ static int msb_index (__u16 word)
 	 * able to check precisely what's going on. If a end user sees this,
 	 * it's very likely the peer. - Jean II */
 	if (word == 0) {
-		IRDA_WARNING("%s(), Detected buggy peer, adjust null PV to 0x1!\n",
-			 __func__);
+		net_warn_ratelimited("%s(), Detected buggy peer, adjust null PV to 0x1!\n",
+				     __func__);
 		/* The only safe choice (we don't know the array size) */
 		word = 0x1;
 	}
@@ -351,8 +351,8 @@ static void irlap_adjust_qos_settings(struct qos_info *qos)
 	if (sysctl_min_tx_turn_time > qos->min_turn_time.value) {
 		int i;
 
-		IRDA_WARNING("%s(), Detected buggy peer, adjust mtt to %dus!\n",
-			 __func__, sysctl_min_tx_turn_time);
+		net_warn_ratelimited("%s(), Detected buggy peer, adjust mtt to %dus!\n",
+				     __func__, sysctl_min_tx_turn_time);
 
 		/* We don't really need bits, but easier this way */
 		i = value_highest_bit(sysctl_min_tx_turn_time, min_turn_times,
@@ -402,8 +402,8 @@ static void irlap_adjust_qos_settings(struct qos_info *qos)
 			IRDA_DEBUG(2, "%s(), reducing data size to %d\n",
 				   __func__, qos->data_size.value);
 		} else {
-			IRDA_WARNING("%s(), nothing more we can do!\n",
-				     __func__);
+			net_warn_ratelimited("%s(), nothing more we can do!\n",
+					     __func__);
 		}
 	}
 #endif /* CONFIG_IRDA_DYNAMIC_WINDOW */
diff --git a/net/irda/wrapper.c b/net/irda/wrapper.c
index fd0995b1323..9efffeb8d0f 100644
--- a/net/irda/wrapper.c
+++ b/net/irda/wrapper.c
@@ -134,8 +134,8 @@ int async_wrap_skb(struct sk_buff *skb, __u8 *tx_buff, int buffsize)
 		 *  transmitted after this point is 5.
 		 */
 		if(n >= (buffsize-5)) {
-			IRDA_ERROR("%s(), tx buffer overflow (n=%d)\n",
-				   __func__, n);
+			net_err_ratelimited("%s(), tx buffer overflow (n=%d)\n",
+					    __func__, n);
 			return n;
 		}
 
@@ -386,7 +386,7 @@ async_unwrap_ce(struct net_device *dev,
 		break;
 
 	case LINK_ESCAPE:
-		IRDA_WARNING("%s: state not defined\n", __func__);
+		net_warn_ratelimited("%s: state not defined\n", __func__);
 		break;
 
 	case BEGIN_FRAME:
-- 
cgit v1.2.3-70-g09d2


From 6322d50d879c7ad150164cedc64015a7817f7b28 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 12 Nov 2014 03:36:51 +0100
Subject: mac802154: add wpan_phy priv id

This patch adds an unique id for an wpan_phy. This behaviour is mostly
grabbed from wireless stack. This is needed for upcomming patches which
identify the wpan netdev while NETDEV_CHANGENAME in netdev notify function.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h      | 8 ++++++++
 net/mac802154/ieee802154_i.h | 3 +++
 net/mac802154/main.c         | 2 ++
 net/mac802154/util.c         | 3 +++
 4 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index e5570e01111..36951523130 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -42,6 +42,14 @@ struct cfg802154_ops {
 struct wpan_phy {
 	struct mutex pib_lock;
 
+	/* If multiple wpan_phys are registered and you're handed e.g.
+	 * a regular netdev with assigned ieee802154_ptr, you won't
+	 * know whether it points to a wpan_phy your driver has registered
+	 * or not. Assign this to something global to your driver to
+	 * help determine whether you own this wpan_phy or not.
+	 */
+	const void *privid;
+
 	/*
 	 * This is a PIB according to 802.15.4-2011.
 	 * We do not provide timing-related variables, as they
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index abb19701d49..4be5e23c7e8 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -96,6 +96,9 @@ struct ieee802154_sub_if_data {
 
 #define MAC802154_CHAN_NONE		0xff /* No channel is assigned */
 
+/* utility functions/constants */
+extern const void *const mac802154_wpan_phy_privid; /*  for wpan_phy privid */
+
 static inline struct ieee802154_local *
 hw_to_local(struct ieee802154_hw *hw)
 {
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 709dcc5f7f1..24e8ca6a669 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -92,6 +92,8 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops)
 		return NULL;
 	}
 
+	phy->privid = mac802154_wpan_phy_privid;
+
 	local = wpan_phy_priv(phy);
 	local->phy = phy;
 	local->hw.phy = local->phy;
diff --git a/net/mac802154/util.c b/net/mac802154/util.c
index 117e4eff4ca..9a04e4a8e50 100644
--- a/net/mac802154/util.c
+++ b/net/mac802154/util.c
@@ -15,6 +15,9 @@
 
 #include "ieee802154_i.h"
 
+/* privid for wpan_phys to determine whether they belong to us or not */
+const void *const mac802154_wpan_phy_privid = &mac802154_wpan_phy_privid;
+
 void ieee802154_wake_queue(struct ieee802154_hw *hw)
 {
 	struct ieee802154_local *local = hw_to_local(hw);
-- 
cgit v1.2.3-70-g09d2


From 9d30a8cf98b2dd132d6e4503718df78ffc1b7f53 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 12 Nov 2014 03:36:54 +0100
Subject: ieee802154: cleanup cfg802154 intendation

This is patch is cleanup to have a similar indentation like cfg80211
implementation.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 36951523130..8a3edc5edad 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -35,8 +35,8 @@ struct cfg802154_ops {
 	struct net_device * (*add_virtual_intf_deprecated)(struct wpan_phy *wpan_phy,
 							   const char *name,
 							   int type);
-	void (*del_virtual_intf_deprecated)(struct wpan_phy *wpan_phy,
-					    struct net_device *dev);
+	void	(*del_virtual_intf_deprecated)(struct wpan_phy *wpan_phy,
+					       struct net_device *dev);
 };
 
 struct wpan_phy {
-- 
cgit v1.2.3-70-g09d2


From ab0bd561724bf3c09aa80e76ca0a187c6880bc5c Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 12 Nov 2014 03:36:55 +0100
Subject: ieee820154: add channel set support

This patch adds page and channel setting support to nl802154 framework.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h   |  1 +
 net/ieee802154/nl802154.c | 28 ++++++++++++++++++++++++++++
 net/ieee802154/rdev-ops.h |  7 +++++++
 net/mac802154/cfg.c       | 24 ++++++++++++++++++++++++
 4 files changed, 60 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 8a3edc5edad..391fdb37208 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -37,6 +37,7 @@ struct cfg802154_ops {
 							   int type);
 	void	(*del_virtual_intf_deprecated)(struct wpan_phy *wpan_phy,
 					       struct net_device *dev);
+	int	(*set_channel)(struct wpan_phy *wpan_phy, u8 page, u8 channel);
 };
 
 struct wpan_phy {
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 46df7dca92d..d8ef2c8a182 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -23,6 +23,7 @@
 #include <net/sock.h>
 
 #include "nl802154.h"
+#include "rdev-ops.h"
 #include "core.h"
 
 static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
@@ -550,6 +551,25 @@ static int nl802154_get_interface(struct sk_buff *skb, struct genl_info *info)
 	return genlmsg_reply(msg, info);
 }
 
+static int nl802154_set_channel(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	u8 channel, page;
+
+	if (!info->attrs[NL802154_ATTR_PAGE] ||
+	    !info->attrs[NL802154_ATTR_CHANNEL])
+		return -EINVAL;
+
+	page = nla_get_u8(info->attrs[NL802154_ATTR_PAGE]);
+	channel = nla_get_u8(info->attrs[NL802154_ATTR_CHANNEL]);
+
+	/* check 802.15.4 constraints */
+	if (page >= WPAN_NUM_PAGES || channel >= WPAN_NUM_CHANNELS)
+		return -EINVAL;
+
+	return rdev_set_channel(rdev, page, channel);
+}
+
 #define NL802154_FLAG_NEED_WPAN_PHY	0x01
 #define NL802154_FLAG_NEED_NETDEV	0x02
 #define NL802154_FLAG_NEED_RTNL		0x04
@@ -660,6 +680,14 @@ static const struct genl_ops nl802154_ops[] = {
 		.internal_flags = NL802154_FLAG_NEED_WPAN_DEV |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_SET_CHANNEL,
+		.doit = nl802154_set_channel,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
+				  NL802154_FLAG_NEED_RTNL,
+	},
 };
 
 /* initialisation/exit functions */
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index ac8824ec168..8a3b0eb4e02 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -20,4 +20,11 @@ rdev_del_virtual_intf_deprecated(struct cfg802154_registered_device *rdev,
 	rdev->ops->del_virtual_intf_deprecated(&rdev->wpan_phy, dev);
 }
 
+static inline int
+rdev_set_channel(struct cfg802154_registered_device *rdev, const u8 page,
+		 const u8 channel)
+{
+	return rdev->ops->set_channel(&rdev->wpan_phy, page, channel);
+}
+
 #endif /* __CFG802154_RDEV_OPS */
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index d2c4e8f8972..9d5b1895c75 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -17,6 +17,7 @@
 #include <net/cfg802154.h>
 
 #include "ieee802154_i.h"
+#include "driver-ops.h"
 #include "cfg.h"
 
 static struct net_device *
@@ -41,7 +42,30 @@ static void ieee802154_del_iface_deprecated(struct wpan_phy *wpan_phy,
 	ieee802154_if_remove(sdata);
 }
 
+static int
+ieee802154_set_channel(struct wpan_phy *wpan_phy, const u8 page,
+		       const u8 channel)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+	int ret;
+
+	ASSERT_RTNL();
+
+	/* check if phy support this setting */
+	if (!(wpan_phy->channels_supported[page] & BIT(channel)))
+		return -EINVAL;
+
+	ret = drv_set_channel(local, page, channel);
+	if (!ret) {
+		wpan_phy->current_page = page;
+		wpan_phy->current_channel = channel;
+	}
+
+	return ret;
+}
+
 const struct cfg802154_ops mac802154_config_ops = {
 	.add_virtual_intf_deprecated = ieee802154_add_iface_deprecated,
 	.del_virtual_intf_deprecated = ieee802154_del_iface_deprecated,
+	.set_channel = ieee802154_set_channel,
 };
-- 
cgit v1.2.3-70-g09d2


From 702bf371282f5912fe53f0b247fa2d7df9d7951f Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 12 Nov 2014 03:36:57 +0100
Subject: ieee820154: add pan_id setting support

This patch adds support for setting pan_id via nl802154 framework.
Adding a comment because setting 0xffff as pan_id seems to be valid
setting. The pan_id 0xffff as source pan is invalid. I am not sure now
about this setting but for the current netlink interface this is an
invalid setting, so we do the same now. Maybe we need to change that
when we have coordinator support and association support.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/ieee802154.h |  2 ++
 include/net/cfg802154.h    |  2 ++
 net/ieee802154/nl802154.c  | 31 +++++++++++++++++++++++++++++++
 net/ieee802154/rdev-ops.h  |  7 +++++++
 net/mac802154/cfg.c        | 20 ++++++++++++++++++++
 5 files changed, 62 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index d043449a079..d40379876b8 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -30,6 +30,8 @@
 #define IEEE802154_MTU			127
 #define IEEE802154_MIN_PSDU_LEN		5
 
+#define IEEE802154_PAN_ID_BROADCAST	0xffff
+
 #define IEEE802154_EXTENDED_ADDR_LEN	8
 
 #define IEEE802154_FC_TYPE_BEACON	0x0	/* Frame is beacon */
diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 391fdb37208..d07b0726b28 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -38,6 +38,8 @@ struct cfg802154_ops {
 	void	(*del_virtual_intf_deprecated)(struct wpan_phy *wpan_phy,
 					       struct net_device *dev);
 	int	(*set_channel)(struct wpan_phy *wpan_phy, u8 page, u8 channel);
+	int	(*set_pan_id)(struct wpan_phy *wpan_phy,
+			      struct wpan_dev *wpan_dev, u16 pan_id);
 };
 
 struct wpan_phy {
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index d8ef2c8a182..88cd1293283 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -570,6 +570,29 @@ static int nl802154_set_channel(struct sk_buff *skb, struct genl_info *info)
 	return rdev_set_channel(rdev, page, channel);
 }
 
+static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	u16 pan_id;
+
+	/* conflict here while tx/rx calls */
+	if (netif_running(dev))
+		return -EBUSY;
+
+	/* don't change address fields on monitor */
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		return -EINVAL;
+
+	if (!info->attrs[NL802154_ATTR_PAN_ID])
+		return -EINVAL;
+
+	pan_id = nla_get_u16(info->attrs[NL802154_ATTR_PAN_ID]);
+
+	return rdev_set_pan_id(rdev, wpan_dev, pan_id);
+}
+
 #define NL802154_FLAG_NEED_WPAN_PHY	0x01
 #define NL802154_FLAG_NEED_NETDEV	0x02
 #define NL802154_FLAG_NEED_RTNL		0x04
@@ -688,6 +711,14 @@ static const struct genl_ops nl802154_ops[] = {
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_SET_PAN_ID,
+		.doit = nl802154_set_pan_id,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
 };
 
 /* initialisation/exit functions */
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index 8a3b0eb4e02..4115ea264fd 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -27,4 +27,11 @@ rdev_set_channel(struct cfg802154_registered_device *rdev, const u8 page,
 	return rdev->ops->set_channel(&rdev->wpan_phy, page, channel);
 }
 
+static inline int
+rdev_set_pan_id(struct cfg802154_registered_device *rdev,
+		struct wpan_dev *wpan_dev, u16 pan_id)
+{
+	return rdev->ops->set_pan_id(&rdev->wpan_phy, wpan_dev, pan_id);
+}
+
 #endif /* __CFG802154_RDEV_OPS */
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index 9d5b1895c75..db6e5e981a8 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -64,8 +64,28 @@ ieee802154_set_channel(struct wpan_phy *wpan_phy, const u8 page,
 	return ret;
 }
 
+static int ieee802154_set_pan_id(struct wpan_phy *wpan_phy,
+				 struct wpan_dev *wpan_dev, const u16 pan_id)
+{
+	ASSERT_RTNL();
+
+	/* TODO
+	 * I am not sure about to check here on broadcast pan_id.
+	 * Broadcast is a valid setting, comment from 802.15.4:
+	 * If this value is 0xffff, the device is not associated.
+	 *
+	 * This could useful to simple deassociate an device.
+	 */
+	if (pan_id == IEEE802154_PAN_ID_BROADCAST)
+		return -EINVAL;
+
+	wpan_dev->pan_id = cpu_to_le16(pan_id);
+	return 0;
+}
+
 const struct cfg802154_ops mac802154_config_ops = {
 	.add_virtual_intf_deprecated = ieee802154_add_iface_deprecated,
 	.del_virtual_intf_deprecated = ieee802154_del_iface_deprecated,
 	.set_channel = ieee802154_set_channel,
+	.set_pan_id = ieee802154_set_pan_id,
 };
-- 
cgit v1.2.3-70-g09d2


From 9830c62a0b3d57d9d00880989cfe987f581bc03f Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 12 Nov 2014 03:36:58 +0100
Subject: ieee820154: add short_addr setting support

This patch adds support for setting short address via nl802154 framework.
Also added a comment because a 0xffff seems to be valid address that we
don't have a short address. This is a valid setting but we need
more checks in upper layers to don't allow this address as source address.
Also the current netlink interface doesn't allow to set the short_addr
to 0xffff. Same for the 0xfffe short address which describes a not
allocated short address.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/ieee802154.h |  2 ++
 include/net/cfg802154.h    |  2 ++
 net/ieee802154/nl802154.c  | 31 +++++++++++++++++++++++++++++++
 net/ieee802154/rdev-ops.h  |  7 +++++++
 net/mac802154/cfg.c        | 26 ++++++++++++++++++++++++++
 5 files changed, 68 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index d40379876b8..ce0f96a5597 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -31,6 +31,8 @@
 #define IEEE802154_MIN_PSDU_LEN		5
 
 #define IEEE802154_PAN_ID_BROADCAST	0xffff
+#define IEEE802154_ADDR_SHORT_BROADCAST	0xffff
+#define IEEE802154_ADDR_SHORT_UNSPEC	0xfffe
 
 #define IEEE802154_EXTENDED_ADDR_LEN	8
 
diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index d07b0726b28..e8a4c2b7072 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -40,6 +40,8 @@ struct cfg802154_ops {
 	int	(*set_channel)(struct wpan_phy *wpan_phy, u8 page, u8 channel);
 	int	(*set_pan_id)(struct wpan_phy *wpan_phy,
 			      struct wpan_dev *wpan_dev, u16 pan_id);
+	int	(*set_short_addr)(struct wpan_phy *wpan_phy,
+				  struct wpan_dev *wpan_dev, u16 short_addr);
 };
 
 struct wpan_phy {
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 88cd1293283..2978c1a7801 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -593,6 +593,29 @@ static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info)
 	return rdev_set_pan_id(rdev, wpan_dev, pan_id);
 }
 
+static int nl802154_set_short_addr(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	u16 short_addr;
+
+	/* conflict here while tx/rx calls */
+	if (netif_running(dev))
+		return -EBUSY;
+
+	/* don't change address fields on monitor */
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		return -EINVAL;
+
+	if (!info->attrs[NL802154_ATTR_SHORT_ADDR])
+		return -EINVAL;
+
+	short_addr = nla_get_u16(info->attrs[NL802154_ATTR_SHORT_ADDR]);
+
+	return rdev_set_short_addr(rdev, wpan_dev, short_addr);
+}
+
 #define NL802154_FLAG_NEED_WPAN_PHY	0x01
 #define NL802154_FLAG_NEED_NETDEV	0x02
 #define NL802154_FLAG_NEED_RTNL		0x04
@@ -719,6 +742,14 @@ static const struct genl_ops nl802154_ops[] = {
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_SET_SHORT_ADDR,
+		.doit = nl802154_set_short_addr,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
 };
 
 /* initialisation/exit functions */
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index 4115ea264fd..16b0de06c3a 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -34,4 +34,11 @@ rdev_set_pan_id(struct cfg802154_registered_device *rdev,
 	return rdev->ops->set_pan_id(&rdev->wpan_phy, wpan_dev, pan_id);
 }
 
+static inline int
+rdev_set_short_addr(struct cfg802154_registered_device *rdev,
+		    struct wpan_dev *wpan_dev, u16 short_addr)
+{
+	return rdev->ops->set_short_addr(&rdev->wpan_phy, wpan_dev, short_addr);
+}
+
 #endif /* __CFG802154_RDEV_OPS */
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index db6e5e981a8..df29976d132 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -83,9 +83,35 @@ static int ieee802154_set_pan_id(struct wpan_phy *wpan_phy,
 	return 0;
 }
 
+static int
+ieee802154_set_short_addr(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+			  const u16 short_addr)
+{
+	ASSERT_RTNL();
+
+	/* TODO
+	 * I am not sure about to check here on broadcast short_addr.
+	 * Broadcast is a valid setting, comment from 802.15.4:
+	 * A value of 0xfffe indicates that the device has
+	 * associated but has not been allocated an address. A
+	 * value of 0xffff indicates that the device does not
+	 * have a short address.
+	 *
+	 * I think we should allow to set these settings but
+	 * don't allow to allow socket communication with it.
+	 */
+	if (short_addr == IEEE802154_ADDR_SHORT_UNSPEC ||
+	    short_addr == IEEE802154_ADDR_SHORT_BROADCAST)
+		return -EINVAL;
+
+	wpan_dev->short_addr = cpu_to_le16(short_addr);
+	return 0;
+}
+
 const struct cfg802154_ops mac802154_config_ops = {
 	.add_virtual_intf_deprecated = ieee802154_add_iface_deprecated,
 	.del_virtual_intf_deprecated = ieee802154_del_iface_deprecated,
 	.set_channel = ieee802154_set_channel,
 	.set_pan_id = ieee802154_set_pan_id,
+	.set_short_addr = ieee802154_set_short_addr,
 };
-- 
cgit v1.2.3-70-g09d2


From 656a999e8701c1e3d17040f051d3a080ec6c710c Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 12 Nov 2014 03:36:59 +0100
Subject: ieee820154: add backoff exponent setting support

This patch adds support for setting backoff exponents via nl802154
framework.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h   |  3 +++
 net/ieee802154/nl802154.c | 34 ++++++++++++++++++++++++++++++++++
 net/ieee802154/rdev-ops.h |  9 +++++++++
 net/mac802154/cfg.c       | 18 ++++++++++++++++++
 4 files changed, 64 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index e8a4c2b7072..27e98d10fb2 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -42,6 +42,9 @@ struct cfg802154_ops {
 			      struct wpan_dev *wpan_dev, u16 pan_id);
 	int	(*set_short_addr)(struct wpan_phy *wpan_phy,
 				  struct wpan_dev *wpan_dev, u16 short_addr);
+	int	(*set_backoff_exponent)(struct wpan_phy *wpan_phy,
+					struct wpan_dev *wpan_dev, u8 min_be,
+					u8 max_be);
 };
 
 struct wpan_phy {
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 2978c1a7801..d1cf3021ff3 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -616,6 +616,32 @@ static int nl802154_set_short_addr(struct sk_buff *skb, struct genl_info *info)
 	return rdev_set_short_addr(rdev, wpan_dev, short_addr);
 }
 
+static int
+nl802154_set_backoff_exponent(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	u8 min_be, max_be;
+
+	/* should be set on netif open inside phy settings */
+	if (netif_running(dev))
+		return -EBUSY;
+
+	if (!info->attrs[NL802154_ATTR_MIN_BE] ||
+	    !info->attrs[NL802154_ATTR_MAX_BE])
+		return -EINVAL;
+
+	min_be = nla_get_u8(info->attrs[NL802154_ATTR_MIN_BE]);
+	max_be = nla_get_u8(info->attrs[NL802154_ATTR_MAX_BE]);
+
+	/* check 802.15.4 constraints */
+	if (max_be < 3 || max_be > 8 || min_be > max_be)
+		return -EINVAL;
+
+	return rdev_set_backoff_exponent(rdev, wpan_dev, min_be, max_be);
+}
+
 #define NL802154_FLAG_NEED_WPAN_PHY	0x01
 #define NL802154_FLAG_NEED_NETDEV	0x02
 #define NL802154_FLAG_NEED_RTNL		0x04
@@ -750,6 +776,14 @@ static const struct genl_ops nl802154_ops[] = {
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_SET_BACKOFF_EXPONENT,
+		.doit = nl802154_set_backoff_exponent,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
 };
 
 /* initialisation/exit functions */
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index 16b0de06c3a..dbccfa9383f 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -41,4 +41,13 @@ rdev_set_short_addr(struct cfg802154_registered_device *rdev,
 	return rdev->ops->set_short_addr(&rdev->wpan_phy, wpan_dev, short_addr);
 }
 
+static inline int
+rdev_set_backoff_exponent(struct cfg802154_registered_device *rdev,
+			  struct wpan_dev *wpan_dev, const u8 min_be,
+			  const u8 max_be)
+{
+	return rdev->ops->set_backoff_exponent(&rdev->wpan_phy, wpan_dev,
+					       min_be, max_be);
+}
+
 #endif /* __CFG802154_RDEV_OPS */
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index df29976d132..67c96f98169 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -83,6 +83,23 @@ static int ieee802154_set_pan_id(struct wpan_phy *wpan_phy,
 	return 0;
 }
 
+static int
+ieee802154_set_backoff_exponent(struct wpan_phy *wpan_phy,
+				struct wpan_dev *wpan_dev,
+				const u8 min_be, const u8 max_be)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+
+	ASSERT_RTNL();
+
+	if (!(local->hw.flags & IEEE802154_HW_CSMA_PARAMS))
+		return -EOPNOTSUPP;
+
+	wpan_dev->min_be = min_be;
+	wpan_dev->max_be = max_be;
+	return 0;
+}
+
 static int
 ieee802154_set_short_addr(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
 			  const u16 short_addr)
@@ -114,4 +131,5 @@ const struct cfg802154_ops mac802154_config_ops = {
 	.set_channel = ieee802154_set_channel,
 	.set_pan_id = ieee802154_set_pan_id,
 	.set_short_addr = ieee802154_set_short_addr,
+	.set_backoff_exponent = ieee802154_set_backoff_exponent,
 };
-- 
cgit v1.2.3-70-g09d2


From a01ba7652cda5602b248efff168450ec658640b8 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 12 Nov 2014 03:37:01 +0100
Subject: ieee820154: add max csma backoffs setting support

This patch add support for max csma backoffs setting via nl802154
framework.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h   |  3 +++
 net/ieee802154/nl802154.c | 33 +++++++++++++++++++++++++++++++++
 net/ieee802154/rdev-ops.h |  9 +++++++++
 net/mac802154/cfg.c       | 16 ++++++++++++++++
 4 files changed, 61 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 27e98d10fb2..79b9ae0abb3 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -45,6 +45,9 @@ struct cfg802154_ops {
 	int	(*set_backoff_exponent)(struct wpan_phy *wpan_phy,
 					struct wpan_dev *wpan_dev, u8 min_be,
 					u8 max_be);
+	int	(*set_max_csma_backoffs)(struct wpan_phy *wpan_phy,
+					 struct wpan_dev *wpan_dev,
+					 u8 max_csma_backoffs);
 };
 
 struct wpan_phy {
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index d1cf3021ff3..af383553bdd 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -642,6 +642,31 @@ nl802154_set_backoff_exponent(struct sk_buff *skb, struct genl_info *info)
 	return rdev_set_backoff_exponent(rdev, wpan_dev, min_be, max_be);
 }
 
+static int
+nl802154_set_max_csma_backoffs(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	u8 max_csma_backoffs;
+
+	/* conflict here while other running iface settings */
+	if (netif_running(dev))
+		return -EBUSY;
+
+	if (!info->attrs[NL802154_ATTR_MAX_CSMA_BACKOFFS])
+		return -EINVAL;
+
+	max_csma_backoffs = nla_get_u8(
+			info->attrs[NL802154_ATTR_MAX_CSMA_BACKOFFS]);
+
+	/* check 802.15.4 constraints */
+	if (max_csma_backoffs > 5)
+		return -EINVAL;
+
+	return rdev_set_max_csma_backoffs(rdev, wpan_dev, max_csma_backoffs);
+}
+
 #define NL802154_FLAG_NEED_WPAN_PHY	0x01
 #define NL802154_FLAG_NEED_NETDEV	0x02
 #define NL802154_FLAG_NEED_RTNL		0x04
@@ -784,6 +809,14 @@ static const struct genl_ops nl802154_ops[] = {
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_SET_MAX_CSMA_BACKOFFS,
+		.doit = nl802154_set_max_csma_backoffs,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
 };
 
 /* initialisation/exit functions */
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index dbccfa9383f..263095c8686 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -50,4 +50,13 @@ rdev_set_backoff_exponent(struct cfg802154_registered_device *rdev,
 					       min_be, max_be);
 }
 
+static inline int
+rdev_set_max_csma_backoffs(struct cfg802154_registered_device *rdev,
+			   struct wpan_dev *wpan_dev,
+			   const u8 max_csma_backoffs)
+{
+	return rdev->ops->set_max_csma_backoffs(&rdev->wpan_phy, wpan_dev,
+						max_csma_backoffs);
+}
+
 #endif /* __CFG802154_RDEV_OPS */
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index 67c96f98169..d72feebb939 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -125,6 +125,21 @@ ieee802154_set_short_addr(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
 	return 0;
 }
 
+static int ieee802154_set_max_csma_backoffs(struct wpan_phy *wpan_phy,
+					    struct wpan_dev *wpan_dev,
+					    const u8 max_csma_backoffs)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+
+	ASSERT_RTNL();
+
+	if (!(local->hw.flags & IEEE802154_HW_CSMA_PARAMS))
+		return -EOPNOTSUPP;
+
+	wpan_dev->csma_retries = max_csma_backoffs;
+	return 0;
+}
+
 const struct cfg802154_ops mac802154_config_ops = {
 	.add_virtual_intf_deprecated = ieee802154_add_iface_deprecated,
 	.del_virtual_intf_deprecated = ieee802154_del_iface_deprecated,
@@ -132,4 +147,5 @@ const struct cfg802154_ops mac802154_config_ops = {
 	.set_pan_id = ieee802154_set_pan_id,
 	.set_short_addr = ieee802154_set_short_addr,
 	.set_backoff_exponent = ieee802154_set_backoff_exponent,
+	.set_max_csma_backoffs = ieee802154_set_max_csma_backoffs,
 };
-- 
cgit v1.2.3-70-g09d2


From 17a3a46bfbf1c2b944812a81b11ffe255a55e9ca Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 12 Nov 2014 03:37:03 +0100
Subject: ieee820154: add max frame retries setting support

This patch add support for setting mac frame retries setting via
nl802154 framework.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h   |  3 +++
 net/ieee802154/nl802154.c | 32 ++++++++++++++++++++++++++++++++
 net/ieee802154/rdev-ops.h |  9 +++++++++
 net/mac802154/cfg.c       | 16 ++++++++++++++++
 4 files changed, 60 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 79b9ae0abb3..5c3bc12706c 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -48,6 +48,9 @@ struct cfg802154_ops {
 	int	(*set_max_csma_backoffs)(struct wpan_phy *wpan_phy,
 					 struct wpan_dev *wpan_dev,
 					 u8 max_csma_backoffs);
+	int	(*set_max_frame_retries)(struct wpan_phy *wpan_phy,
+					 struct wpan_dev *wpan_dev,
+					 s8 max_frame_retries);
 };
 
 struct wpan_phy {
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index af383553bdd..0e272c67c49 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -667,6 +667,30 @@ nl802154_set_max_csma_backoffs(struct sk_buff *skb, struct genl_info *info)
 	return rdev_set_max_csma_backoffs(rdev, wpan_dev, max_csma_backoffs);
 }
 
+static int
+nl802154_set_max_frame_retries(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	s8 max_frame_retries;
+
+	if (netif_running(dev))
+		return -EBUSY;
+
+	if (!info->attrs[NL802154_ATTR_MAX_FRAME_RETRIES])
+		return -EINVAL;
+
+	max_frame_retries = nla_get_s8(
+			info->attrs[NL802154_ATTR_MAX_FRAME_RETRIES]);
+
+	/* check 802.15.4 constraints */
+	if (max_frame_retries < -1 || max_frame_retries > 7)
+		return -EINVAL;
+
+	return rdev_set_max_frame_retries(rdev, wpan_dev, max_frame_retries);
+}
+
 #define NL802154_FLAG_NEED_WPAN_PHY	0x01
 #define NL802154_FLAG_NEED_NETDEV	0x02
 #define NL802154_FLAG_NEED_RTNL		0x04
@@ -817,6 +841,14 @@ static const struct genl_ops nl802154_ops[] = {
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_SET_MAX_FRAME_RETRIES,
+		.doit = nl802154_set_max_frame_retries,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
 };
 
 /* initialisation/exit functions */
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index 263095c8686..f9171aaf985 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -59,4 +59,13 @@ rdev_set_max_csma_backoffs(struct cfg802154_registered_device *rdev,
 						max_csma_backoffs);
 }
 
+static inline int
+rdev_set_max_frame_retries(struct cfg802154_registered_device *rdev,
+			   struct wpan_dev *wpan_dev,
+			   const s8 max_frame_retries)
+{
+	return rdev->ops->set_max_frame_retries(&rdev->wpan_phy, wpan_dev,
+						max_frame_retries);
+}
+
 #endif /* __CFG802154_RDEV_OPS */
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index d72feebb939..a8f6eaa76d4 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -140,6 +140,21 @@ static int ieee802154_set_max_csma_backoffs(struct wpan_phy *wpan_phy,
 	return 0;
 }
 
+static int ieee802154_set_max_frame_retries(struct wpan_phy *wpan_phy,
+					    struct wpan_dev *wpan_dev,
+					    const s8 max_frame_retries)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+
+	ASSERT_RTNL();
+
+	if (!(local->hw.flags & IEEE802154_HW_FRAME_RETRIES))
+		return -EOPNOTSUPP;
+
+	wpan_dev->frame_retries = max_frame_retries;
+	return 0;
+}
+
 const struct cfg802154_ops mac802154_config_ops = {
 	.add_virtual_intf_deprecated = ieee802154_add_iface_deprecated,
 	.del_virtual_intf_deprecated = ieee802154_del_iface_deprecated,
@@ -148,4 +163,5 @@ const struct cfg802154_ops mac802154_config_ops = {
 	.set_short_addr = ieee802154_set_short_addr,
 	.set_backoff_exponent = ieee802154_set_backoff_exponent,
 	.set_max_csma_backoffs = ieee802154_set_max_csma_backoffs,
+	.set_max_frame_retries = ieee802154_set_max_frame_retries,
 };
-- 
cgit v1.2.3-70-g09d2


From c8937a1d112b1a948454f4fa2f9b747fee2a3f66 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 12 Nov 2014 03:37:05 +0100
Subject: ieee820154: add lbt setting support

This patch adds support for setting listen before transmit mode via
nl802154 framework.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h   |  2 ++
 net/ieee802154/nl802154.c | 25 +++++++++++++++++++++++++
 net/ieee802154/rdev-ops.h |  7 +++++++
 net/mac802154/cfg.c       | 16 ++++++++++++++++
 4 files changed, 50 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 5c3bc12706c..fa0a9e51952 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -51,6 +51,8 @@ struct cfg802154_ops {
 	int	(*set_max_frame_retries)(struct wpan_phy *wpan_phy,
 					 struct wpan_dev *wpan_dev,
 					 s8 max_frame_retries);
+	int	(*set_lbt_mode)(struct wpan_phy *wpan_phy,
+				struct wpan_dev *wpan_dev, bool mode);
 };
 
 struct wpan_phy {
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 0e272c67c49..ccdf33ecee0 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -691,6 +691,23 @@ nl802154_set_max_frame_retries(struct sk_buff *skb, struct genl_info *info)
 	return rdev_set_max_frame_retries(rdev, wpan_dev, max_frame_retries);
 }
 
+static int nl802154_set_lbt_mode(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	bool mode;
+
+	if (netif_running(dev))
+		return -EBUSY;
+
+	if (!info->attrs[NL802154_ATTR_LBT_MODE])
+		return -EINVAL;
+
+	mode = !!nla_get_u8(info->attrs[NL802154_ATTR_LBT_MODE]);
+	return rdev_set_lbt_mode(rdev, wpan_dev, mode);
+}
+
 #define NL802154_FLAG_NEED_WPAN_PHY	0x01
 #define NL802154_FLAG_NEED_NETDEV	0x02
 #define NL802154_FLAG_NEED_RTNL		0x04
@@ -849,6 +866,14 @@ static const struct genl_ops nl802154_ops[] = {
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_SET_LBT_MODE,
+		.doit = nl802154_set_lbt_mode,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
 };
 
 /* initialisation/exit functions */
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index f9171aaf985..a78f700bc82 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -68,4 +68,11 @@ rdev_set_max_frame_retries(struct cfg802154_registered_device *rdev,
 						max_frame_retries);
 }
 
+static inline int
+rdev_set_lbt_mode(struct cfg802154_registered_device *rdev,
+		  struct wpan_dev *wpan_dev, const bool mode)
+{
+	return rdev->ops->set_lbt_mode(&rdev->wpan_phy, wpan_dev, mode);
+}
+
 #endif /* __CFG802154_RDEV_OPS */
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index a8f6eaa76d4..5d669d87dd7 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -155,6 +155,21 @@ static int ieee802154_set_max_frame_retries(struct wpan_phy *wpan_phy,
 	return 0;
 }
 
+static int ieee802154_set_lbt_mode(struct wpan_phy *wpan_phy,
+				   struct wpan_dev *wpan_dev,
+				   const bool mode)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+
+	ASSERT_RTNL();
+
+	if (!(local->hw.flags & IEEE802154_HW_LBT))
+		return -EOPNOTSUPP;
+
+	wpan_dev->lbt = mode;
+	return 0;
+}
+
 const struct cfg802154_ops mac802154_config_ops = {
 	.add_virtual_intf_deprecated = ieee802154_add_iface_deprecated,
 	.del_virtual_intf_deprecated = ieee802154_del_iface_deprecated,
@@ -164,4 +179,5 @@ const struct cfg802154_ops mac802154_config_ops = {
 	.set_backoff_exponent = ieee802154_set_backoff_exponent,
 	.set_max_csma_backoffs = ieee802154_set_max_csma_backoffs,
 	.set_max_frame_retries = ieee802154_set_max_frame_retries,
+	.set_lbt_mode = ieee802154_set_lbt_mode,
 };
-- 
cgit v1.2.3-70-g09d2


From 71dfda58aaaf4bf6b1bc59f9d8afa635fa1337d4 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@redhat.com>
Date: Tue, 11 Nov 2014 09:26:34 -0800
Subject: net: Add device Rx page allocation function

This patch implements __dev_alloc_pages and __dev_alloc_page.  These are
meant to replace the __skb_alloc_pages and __skb_alloc_page functions.  The
reason for doing this is that it occurred to me that __skb_alloc_page is
supposed to be passed an sk_buff pointer, but it is NULL in all cases where
it is used.  Worse is that in the case of ixgbe it is passed NULL via the
sk_buff pointer in the rx_buffer info structure which means the compiler is
not correctly stripping it out.

The naming for these functions is based on dev_alloc_skb and __dev_alloc_skb.
There was originally a netdev_alloc_page, however that was passed a
net_device pointer and this function is not so I thought it best to follow
that naming scheme since that is the same difference between dev_alloc_skb
and netdev_alloc_skb.

In the case of anything greater than order 0 it is assumed that we want a
compound page so __GFP_COMP is set for all allocations as we expect a
compound page when assigning a page frag.

The other change in this patch is to exploit the behaviors of the page
allocator in how it handles flags.  So for example we can always set
__GFP_COMP and __GFP_MEMALLOC since they are ignored if they are not
applicable or are overridden by another flag.

Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 103fbe8113f..2e5221f1ec7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2184,6 +2184,54 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
 	return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC);
 }
 
+/**
+ * __dev_alloc_pages - allocate page for network Rx
+ * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx
+ * @order: size of the allocation
+ *
+ * Allocate a new page.
+ *
+ * %NULL is returned if there is no free memory.
+*/
+static inline struct page *__dev_alloc_pages(gfp_t gfp_mask,
+					     unsigned int order)
+{
+	/* This piece of code contains several assumptions.
+	 * 1.  This is for device Rx, therefor a cold page is preferred.
+	 * 2.  The expectation is the user wants a compound page.
+	 * 3.  If requesting a order 0 page it will not be compound
+	 *     due to the check to see if order has a value in prep_new_page
+	 * 4.  __GFP_MEMALLOC is ignored if __GFP_NOMEMALLOC is set due to
+	 *     code in gfp_to_alloc_flags that should be enforcing this.
+	 */
+	gfp_mask |= __GFP_COLD | __GFP_COMP | __GFP_MEMALLOC;
+
+	return alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
+}
+
+static inline struct page *dev_alloc_pages(unsigned int order)
+{
+	return __dev_alloc_pages(GFP_ATOMIC, order);
+}
+
+/**
+ * __dev_alloc_page - allocate a page for network Rx
+ * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx
+ *
+ * Allocate a new page.
+ *
+ * %NULL is returned if there is no free memory.
+ */
+static inline struct page *__dev_alloc_page(gfp_t gfp_mask)
+{
+	return __dev_alloc_pages(gfp_mask, 0);
+}
+
+static inline struct page *dev_alloc_page(void)
+{
+	return __dev_alloc_page(GFP_ATOMIC);
+}
+
 /**
  *	__skb_alloc_pages - allocate pages for ps-rx on a skb and preserve pfmemalloc data
  *	@gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX
-- 
cgit v1.2.3-70-g09d2


From 160d2aba550b23c6a538158511d5adccc400f04c Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@redhat.com>
Date: Tue, 11 Nov 2014 09:27:05 -0800
Subject: net: Remove __skb_alloc_page and __skb_alloc_pages

Remove the two functions which are now dead code.

Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 43 -------------------------------------------
 1 file changed, 43 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2e5221f1ec7..73c370e615d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2232,49 +2232,6 @@ static inline struct page *dev_alloc_page(void)
 	return __dev_alloc_page(GFP_ATOMIC);
 }
 
-/**
- *	__skb_alloc_pages - allocate pages for ps-rx on a skb and preserve pfmemalloc data
- *	@gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX
- *	@skb: skb to set pfmemalloc on if __GFP_MEMALLOC is used
- *	@order: size of the allocation
- *
- * 	Allocate a new page.
- *
- * 	%NULL is returned if there is no free memory.
-*/
-static inline struct page *__skb_alloc_pages(gfp_t gfp_mask,
-					      struct sk_buff *skb,
-					      unsigned int order)
-{
-	struct page *page;
-
-	gfp_mask |= __GFP_COLD;
-
-	if (!(gfp_mask & __GFP_NOMEMALLOC))
-		gfp_mask |= __GFP_MEMALLOC;
-
-	page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
-	if (skb && page && page->pfmemalloc)
-		skb->pfmemalloc = true;
-
-	return page;
-}
-
-/**
- *	__skb_alloc_page - allocate a page for ps-rx for a given skb and preserve pfmemalloc data
- *	@gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX
- *	@skb: skb to set pfmemalloc on if __GFP_MEMALLOC is used
- *
- * 	Allocate a new page.
- *
- * 	%NULL is returned if there is no free memory.
- */
-static inline struct page *__skb_alloc_page(gfp_t gfp_mask,
-					     struct sk_buff *skb)
-{
-	return __skb_alloc_pages(gfp_mask, skb, 0);
-}
-
 /**
  *	skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page
  *	@page: The page that was allocated from skb_alloc_page
-- 
cgit v1.2.3-70-g09d2


From 26cf591e6dfc0d07495b7bcf20a557b316811f00 Mon Sep 17 00:00:00 2001
From: Douglas Gilbert <dgilbert@interlog.com>
Date: Sat, 18 Oct 2014 22:11:21 +0200
Subject: scsi: add SG_SCSI_RESET_NO_ESCALATE flag to SG_SCSI_RESET ioctl

Further to a January 2013 thread titled: "[PATCH] SG_SCSI_RESET ioctl
should only perform requested operation" by Jeremy Linton a patch (v3)
is presented that expands the existing ioctl to include "no_escalate"
versions to the existing resets. This requires no changes to SCSI low
level drivers (LLDs); it adds several more finely tuned reset options
to the user space. For example:

   /* This call remains the same, with the same escalating semantics
    * if the device (LU) reset fail. That is: on failure to try a
    * target reset and if that fails, try a bus reset, and if that fails
    * try a host (i.e. LLD) reset. */
   val = SG_SCSI_RESET_DEVICE;
   res = ioctl(<sg_or_block_fd>, SG_SCSI_RESET, &val);

   /* What follows is a new option introduced by this patch series. Only
    * a device reset is attempted. If that fails then an appropriate
    * error code is provided. N.B. There is no reset escalation. */
   val = SG_SCSI_RESET_DEVICE | SG_SCSI_RESET_NO_ESCALATE;
   res = ioctl(<sg_or_block_fd>, SG_SCSI_RESET, &val);

Signed-off-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Jeremy Linton <jlinton@tributary.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/scsi_error.c | 10 ++++++++++
 drivers/scsi/scsi_ioctl.c | 20 +++++++++++++-------
 drivers/scsi/sg.c         | 17 +++++++++++------
 include/scsi/scsi_eh.h    |  5 +++++
 include/scsi/sg.h         |  5 ++++-
 5 files changed, 43 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index bc5ff6ff9c7..0ed666112b4 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -2366,8 +2366,18 @@ scsi_reset_provider(struct scsi_device *dev, int flag)
 			break;
 		/* FALLTHROUGH */
 	case SCSI_TRY_RESET_HOST:
+	case SCSI_TRY_RESET_HOST | SCSI_TRY_RESET_NO_ESCALATE:
 		rtn = scsi_try_host_reset(scmd);
 		break;
+	case SCSI_TRY_RESET_DEVICE | SCSI_TRY_RESET_NO_ESCALATE:
+		rtn = scsi_try_bus_device_reset(scmd);
+		break;
+	case SCSI_TRY_RESET_TARGET | SCSI_TRY_RESET_NO_ESCALATE:
+		rtn = scsi_try_target_reset(scmd);
+		break;
+	case SCSI_TRY_RESET_BUS | SCSI_TRY_RESET_NO_ESCALATE:
+		rtn = scsi_try_bus_reset(scmd);
+		break;
 	default:
 		rtn = FAILED;
 	}
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 1aaaf43c680..12fe676d134 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -285,13 +285,14 @@ EXPORT_SYMBOL(scsi_ioctl);
  * scsi_nonblockable_ioctl() - Handle SG_SCSI_RESET
  * @sdev: scsi device receiving ioctl
  * @cmd: Must be SC_SCSI_RESET
- * @arg: pointer to int containing SG_SCSI_RESET_{DEVICE,BUS,HOST}
+ * @arg: pointer to int containing SG_SCSI_RESET_{DEVICE,TARGET,BUS,HOST}
+ *       possibly OR-ed with SG_SCSI_RESET_NO_ESCALATE
  * @ndelay: file mode O_NDELAY flag
  */
 int scsi_nonblockable_ioctl(struct scsi_device *sdev, int cmd,
 			    void __user *arg, int ndelay)
 {
-	int val, result;
+	int val, val2, result;
 
 	/* The first set of iocts may be executed even if we're doing
 	 * error processing, as long as the device was opened
@@ -307,27 +308,32 @@ int scsi_nonblockable_ioctl(struct scsi_device *sdev, int cmd,
 		result = get_user(val, (int __user *)arg);
 		if (result)
 			return result;
+		if (val & SG_SCSI_RESET_NO_ESCALATE) {
+			val &= ~SG_SCSI_RESET_NO_ESCALATE;
+			val2 = SCSI_TRY_RESET_NO_ESCALATE;
+		} else
+			val2 = 0;
 		if (val == SG_SCSI_RESET_NOTHING)
 			return 0;
 		switch (val) {
 		case SG_SCSI_RESET_DEVICE:
-			val = SCSI_TRY_RESET_DEVICE;
+			val2 |= SCSI_TRY_RESET_DEVICE;
 			break;
 		case SG_SCSI_RESET_TARGET:
-			val = SCSI_TRY_RESET_TARGET;
+			val2 |= SCSI_TRY_RESET_TARGET;
 			break;
 		case SG_SCSI_RESET_BUS:
-			val = SCSI_TRY_RESET_BUS;
+			val2 |= SCSI_TRY_RESET_BUS;
 			break;
 		case SG_SCSI_RESET_HOST:
-			val = SCSI_TRY_RESET_HOST;
+			val2 |= SCSI_TRY_RESET_HOST;
 			break;
 		default:
 			return -EINVAL;
 		}
 		if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
 			return -EACCES;
-		return (scsi_reset_provider(sdev, val) ==
+		return (scsi_reset_provider(sdev, val2) ==
 			SUCCESS) ? 0 : -EIO;
 	}
 	return -ENODEV;
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 60354449d9e..fe44c14f551 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -847,7 +847,7 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 {
 	void __user *p = (void __user *)arg;
 	int __user *ip = p;
-	int result, val, read_only;
+	int result, val, val2, read_only;
 	Sg_device *sdp;
 	Sg_fd *sfp;
 	Sg_request *srp;
@@ -1082,27 +1082,32 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 		result = get_user(val, ip);
 		if (result)
 			return result;
+		if (val & SG_SCSI_RESET_NO_ESCALATE) {
+			val &= ~SG_SCSI_RESET_NO_ESCALATE;
+			val2 = SCSI_TRY_RESET_NO_ESCALATE;
+		} else
+			val2 = 0;
 		if (SG_SCSI_RESET_NOTHING == val)
 			return 0;
 		switch (val) {
 		case SG_SCSI_RESET_DEVICE:
-			val = SCSI_TRY_RESET_DEVICE;
+			val2 |= SCSI_TRY_RESET_DEVICE;
 			break;
 		case SG_SCSI_RESET_TARGET:
-			val = SCSI_TRY_RESET_TARGET;
+			val2 |= SCSI_TRY_RESET_TARGET;
 			break;
 		case SG_SCSI_RESET_BUS:
-			val = SCSI_TRY_RESET_BUS;
+			val2 |= SCSI_TRY_RESET_BUS;
 			break;
 		case SG_SCSI_RESET_HOST:
-			val = SCSI_TRY_RESET_HOST;
+			val2 |= SCSI_TRY_RESET_HOST;
 			break;
 		default:
 			return -EINVAL;
 		}
 		if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
 			return -EACCES;
-		return (scsi_reset_provider(sdp->device, val) ==
+		return (scsi_reset_provider(sdp->device, val2) ==
 			SUCCESS) ? 0 : -EIO;
 	case SCSI_IOCTL_SEND_COMMAND:
 		if (atomic_read(&sdp->detaching))
diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h
index 06a8790893e..49af14ad528 100644
--- a/include/scsi/scsi_eh.h
+++ b/include/scsi/scsi_eh.h
@@ -62,11 +62,16 @@ extern void scsi_build_sense_buffer(int desc, u8 *buf, u8 key, u8 asc, u8 ascq);
 
 /*
  * Reset request from external source
+ * Note: if SCSI_TRY_RESET_DEVICE fails then it will escalate to
+ * SCSI_TRY_RESET_TARGET which if it fails will escalate to
+ * SCSI_TRY_RESET_BUS which if it fails will escalate to SCSI_TRY_RESET_HOST.
+ * To prevent escalation OR with SCSI_TRY_RESET_NO_ESCALATE.
  */
 #define SCSI_TRY_RESET_DEVICE	1
 #define SCSI_TRY_RESET_BUS	2
 #define SCSI_TRY_RESET_HOST	3
 #define SCSI_TRY_RESET_TARGET	4
+#define SCSI_TRY_RESET_NO_ESCALATE	0x100	/* OR-ed to prior defines */
 
 extern int scsi_reset_provider(struct scsi_device *, int);
 
diff --git a/include/scsi/sg.h b/include/scsi/sg.h
index 750e5db7c6b..3afec703244 100644
--- a/include/scsi/sg.h
+++ b/include/scsi/sg.h
@@ -164,12 +164,15 @@ typedef struct sg_req_info { /* used by SG_GET_REQUEST_TABLE ioctl() */
 
 /* Returns -EBUSY if occupied. 3rd argument pointer to int (see next) */
 #define SG_SCSI_RESET 0x2284
-/* Associated values that can be given to SG_SCSI_RESET follow */
+/* Associated values that can be given to SG_SCSI_RESET follow.
+ * SG_SCSI_RESET_NO_ESCALATE may be OR-ed to the _DEVICE, _TARGET, _BUS
+ * or _HOST reset value so only that action is attempted. */
 #define		SG_SCSI_RESET_NOTHING	0
 #define		SG_SCSI_RESET_DEVICE	1
 #define		SG_SCSI_RESET_BUS	2
 #define		SG_SCSI_RESET_HOST	3
 #define		SG_SCSI_RESET_TARGET	4
+#define		SG_SCSI_RESET_NO_ESCALATE	0x100
 
 /* synchronous SCSI command ioctl, (only in version 3 interface) */
 #define SG_IO 0x2285   /* similar effect as write() followed by read() */
-- 
cgit v1.2.3-70-g09d2


From 639ae4d0337ce5bc6f5f6921ecb144841b617c26 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 24 Oct 2014 14:26:41 +0200
Subject: scsi: remove scsi_cmd_print_sense_hdr()

Unused.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/constants.c | 14 --------------
 include/scsi/scsi_dbg.h  |  2 --
 2 files changed, 16 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index d35a5d6c8d7..2f447075adb 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -1428,20 +1428,6 @@ scsi_print_sense_hdr(const char *name, struct scsi_sense_hdr *sshdr)
 }
 EXPORT_SYMBOL(scsi_print_sense_hdr);
 
-/*
- * Print normalized SCSI sense header with device information and a prefix.
- */
-void
-scsi_cmd_print_sense_hdr(struct scsi_cmnd *scmd, const char *desc,
-			  struct scsi_sense_hdr *sshdr)
-{
-	scmd_printk(KERN_INFO, scmd, "%s: ", desc);
-	scsi_show_sense_hdr(sshdr);
-	scmd_printk(KERN_INFO, scmd, "%s: ", desc);
-	scsi_show_extd_sense(sshdr->asc, sshdr->ascq);
-}
-EXPORT_SYMBOL(scsi_cmd_print_sense_hdr);
-
 static void
 scsi_decode_sense_buffer(const unsigned char *sense_buffer, int sense_len,
 		       struct scsi_sense_hdr *sshdr)
diff --git a/include/scsi/scsi_dbg.h b/include/scsi/scsi_dbg.h
index e89844cc2cd..5a43a4cd96c 100644
--- a/include/scsi/scsi_dbg.h
+++ b/include/scsi/scsi_dbg.h
@@ -9,8 +9,6 @@ extern void __scsi_print_command(unsigned char *);
 extern void scsi_show_extd_sense(unsigned char, unsigned char);
 extern void scsi_show_sense_hdr(struct scsi_sense_hdr *);
 extern void scsi_print_sense_hdr(const char *, struct scsi_sense_hdr *);
-extern void scsi_cmd_print_sense_hdr(struct scsi_cmnd *, const char *,
-				     struct scsi_sense_hdr *);
 extern void scsi_print_sense(char *, struct scsi_cmnd *);
 extern void __scsi_print_sense(const char *name,
 			       const unsigned char *sense_buffer,
-- 
cgit v1.2.3-70-g09d2


From 22e0d994151c3eac183625f8c1400c0c83ac414f Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 24 Oct 2014 14:26:44 +0200
Subject: scsi: introduce sdev_prefix_printk()

Like scmd_printk(), but the device name is passed in as
a string. Can be used by eg ULDs which do not have access
to the scsi_cmnd structure.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/ch.c          | 3 +--
 drivers/scsi/sd.h          | 6 +++---
 drivers/scsi/sg.c          | 4 ++--
 drivers/scsi/sr.h          | 3 +--
 drivers/scsi/st.c          | 3 +--
 include/scsi/scsi_device.h | 9 +++++++++
 6 files changed, 17 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index ef5ae0d0361..52060e72b75 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -85,8 +85,7 @@ static const char * vendor_labels[CH_TYPES-4] = {
 // module_param_string_array(vendor_labels, NULL, 0444);
 
 #define ch_printk(prefix, ch, fmt, a...) \
-	sdev_printk(prefix, (ch)->device, "[%s] " fmt, \
-		    (ch)->name, ##a)
+	sdev_prefix_printk(prefix, (ch)->device, (ch)->name, fmt, ##a)
 
 #define DPRINTK(fmt, arg...)						\
 do {									\
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 467377884b6..63ba5ca7f9a 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -103,9 +103,9 @@ static inline struct scsi_disk *scsi_disk(struct gendisk *disk)
 
 #define sd_printk(prefix, sdsk, fmt, a...)				\
         (sdsk)->disk ?							\
-	sdev_printk(prefix, (sdsk)->device, "[%s] " fmt,		\
-		    (sdsk)->disk->disk_name, ##a) :			\
-	sdev_printk(prefix, (sdsk)->device, fmt, ##a)
+	      sdev_prefix_printk(prefix, (sdsk)->device,		\
+				 (sdsk)->disk->disk_name, fmt, ##a) :	\
+	      sdev_printk(prefix, (sdsk)->device, fmt, ##a)
 
 #define sd_first_printk(prefix, sdsk, fmt, a...)			\
 	do {								\
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index fe44c14f551..55cbc6689d2 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -219,8 +219,8 @@ static void sg_device_destroy(struct kref *kref);
 #define SZ_SG_REQ_INFO sizeof(sg_req_info_t)
 
 #define sg_printk(prefix, sdp, fmt, a...) \
-	sdev_printk(prefix, (sdp)->device, "[%s] " fmt, \
-		    (sdp)->disk->disk_name, ##a)
+	sdev_prefix_printk(prefix, (sdp)->device,		\
+			   (sdp)->disk->disk_name, fmt, ##a)
 
 static int sg_allow_access(struct file *filp, unsigned char *cmd)
 {
diff --git a/drivers/scsi/sr.h b/drivers/scsi/sr.h
index 1d1f6f416c5..1de33719ad8 100644
--- a/drivers/scsi/sr.h
+++ b/drivers/scsi/sr.h
@@ -57,8 +57,7 @@ typedef struct scsi_cd {
 } Scsi_CD;
 
 #define sr_printk(prefix, cd, fmt, a...) \
-	sdev_printk(prefix, (cd)->device, "[%s] " fmt, \
-		    (cd)->cdi.name, ##a)
+	sdev_prefix_printk(prefix, (cd)->device, (cd)->cdi.name, fmt, ##a)
 
 int sr_do_ioctl(Scsi_CD *, struct packet_command *);
 
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 8d5f8b4f9a2..36ab023793c 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -314,8 +314,7 @@ static inline char *tape_name(struct scsi_tape *tape)
 }
 
 #define st_printk(prefix, t, fmt, a...) \
-	sdev_printk(prefix, (t)->device, "%s: " fmt, \
-		    tape_name(t), ##a)
+	sdev_prefix_printk(prefix, (t)->device, tape_name(t), fmt, ##a)
 #ifdef DEBUG
 #define DEBC_printk(t, fmt, a...) \
 	if (debugging) { st_printk(ST_DEB_MSG, t, fmt, ##a ); }
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 27ecee73bd7..0b18a097c1b 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -244,6 +244,15 @@ struct scsi_dh_data {
 #define sdev_dbg(sdev, fmt, a...) \
 	dev_dbg(&(sdev)->sdev_gendev, fmt, ##a)
 
+/*
+ * like scmd_printk, but the device name is passed in
+ * as a string pointer
+ */
+#define sdev_prefix_printk(l, sdev, p, fmt, a...)			\
+	(p) ?								\
+	sdev_printk(l, sdev, "[%s] " fmt, p, ##a) :			\
+	sdev_printk(l, sdev, fmt, ##a)
+
 #define scmd_printk(prefix, scmd, fmt, a...)				\
         (scmd)->request->rq_disk ?					\
 	sdev_printk(prefix, (scmd)->device, "[%s] " fmt,		\
-- 
cgit v1.2.3-70-g09d2


From d811b848ebb78a1135658aa20a80e31994df47f7 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 24 Oct 2014 14:26:45 +0200
Subject: scsi: use sdev as argument for sense code printing

We should be using the standard dev_printk() variants for
sense code printing.

[hch: remove __scsi_print_sense call in xen-scsiback, Acked by Juergen]
[hch: folded bracing fix from Dan Carpenter]
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/53c700.c       |   2 +-
 drivers/scsi/ch.c           |   2 +-
 drivers/scsi/constants.c    | 120 ++++++++++++++++++++++----------------------
 drivers/scsi/osst.c         |   8 +--
 drivers/scsi/scsi.c         |   2 +-
 drivers/scsi/scsi_error.c   |   2 +-
 drivers/scsi/scsi_ioctl.c   |   2 +-
 drivers/scsi/scsi_lib.c     |   4 +-
 drivers/scsi/sd.c           |   9 ++--
 drivers/scsi/sg.c           |   2 +-
 drivers/scsi/sr_ioctl.c     |   6 +--
 drivers/scsi/st.c           |   6 ++-
 drivers/scsi/storvsc_drv.c  |   3 +-
 drivers/scsi/ufs/ufshcd.c   |   4 +-
 drivers/usb/storage/debug.c |  10 ++--
 drivers/xen/xen-scsiback.c  |   4 --
 include/scsi/scsi_dbg.h     |  17 ++++---
 include/scsi/scsi_eh.h      |   2 +-
 18 files changed, 107 insertions(+), 98 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index fabd4be2c98..68bf423008a 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -602,7 +602,7 @@ NCR_700_scsi_done(struct NCR_700_Host_Parameters *hostdata,
 #ifdef NCR_700_DEBUG
 			printk(" ORIGINAL CMD %p RETURNED %d, new return is %d sense is\n",
 			       SCp, SCp->cmnd[7], result);
-			scsi_print_sense("53c700", SCp);
+			scsi_print_sense(SCp);
 
 #endif
 			dma_unmap_single(hostdata->dev, slot->dma_handle,
diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index 52060e72b75..53621a34c5f 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -206,7 +206,7 @@ ch_do_scsi(scsi_changer *ch, unsigned char *cmd,
 	DPRINTK("result: 0x%x\n",result);
 	if (driver_byte(result) & DRIVER_SENSE) {
 		if (debug)
-			scsi_print_sense_hdr(ch->name, &sshdr);
+			scsi_print_sense_hdr(ch->device, ch->name, &sshdr);
 		errno = ch_find_errno(&sshdr);
 
 		switch(sshdr.sense_key) {
diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index 2f447075adb..9065b6f8f51 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -1292,18 +1292,19 @@ static const struct error_info additional[] =
 
 struct error_info2 {
 	unsigned char code1, code2_min, code2_max;
+	const char * str;
 	const char * fmt;
 };
 
 static const struct error_info2 additional2[] =
 {
-	{0x40, 0x00, 0x7f, "Ram failure (%x)"},
-	{0x40, 0x80, 0xff, "Diagnostic failure on component (%x)"},
-	{0x41, 0x00, 0xff, "Data path failure (%x)"},
-	{0x42, 0x00, 0xff, "Power-on or self-test failure (%x)"},
-	{0x4D, 0x00, 0xff, "Tagged overlapped commands (task tag %x)"},
-	{0x70, 0x00, 0xff, "Decompression exception short algorithm id of %x"},
-	{0, 0, 0, NULL}
+	{0x40, 0x00, 0x7f, "Ram failure", ""},
+	{0x40, 0x80, 0xff, "Diagnostic failure on component", ""},
+	{0x41, 0x00, 0xff, "Data path failure", ""},
+	{0x42, 0x00, 0xff, "Power-on or self-test failure", ""},
+	{0x4D, 0x00, 0xff, "Tagged overlapped commands", "task tag "},
+	{0x70, 0x00, 0xff, "Decompression exception", "short algorithm id of "},
+	{0, 0, 0, NULL, NULL}
 };
 
 /* description of the sense key values */
@@ -1349,7 +1350,8 @@ EXPORT_SYMBOL(scsi_sense_key_string);
  * This string may contain a "%x" and should be printed with ascq as arg.
  */
 const char *
-scsi_extd_sense_format(unsigned char asc, unsigned char ascq) {
+scsi_extd_sense_format(unsigned char asc, unsigned char ascq, const char **fmt)
+{
 #ifdef CONFIG_SCSI_CONSTANTS
 	int i;
 	unsigned short code = ((asc << 8) | ascq);
@@ -1360,8 +1362,10 @@ scsi_extd_sense_format(unsigned char asc, unsigned char ascq) {
 	for (i = 0; additional2[i].fmt; i++) {
 		if (additional2[i].code1 == asc &&
 		    ascq >= additional2[i].code2_min &&
-		    ascq <= additional2[i].code2_max)
-			return additional2[i].fmt;
+		    ascq <= additional2[i].code2_max) {
+			*fmt = additional2[i].fmt;
+			return additional2[i].str;
+		}
 	}
 #endif
 	return NULL;
@@ -1369,49 +1373,53 @@ scsi_extd_sense_format(unsigned char asc, unsigned char ascq) {
 EXPORT_SYMBOL(scsi_extd_sense_format);
 
 void
-scsi_show_extd_sense(unsigned char asc, unsigned char ascq)
+scsi_show_extd_sense(const struct scsi_device *sdev, const char *name,
+		     unsigned char asc, unsigned char ascq)
 {
-        const char *extd_sense_fmt = scsi_extd_sense_format(asc, ascq);
+	const char *extd_sense_fmt = NULL;
+	const char *extd_sense_str = scsi_extd_sense_format(asc, ascq,
+							    &extd_sense_fmt);
+
+	if (extd_sense_str) {
+		if (extd_sense_fmt)
+			sdev_prefix_printk(KERN_INFO, sdev, name,
+					   "Add. Sense: %s (%s%x)",
+					   extd_sense_str, extd_sense_fmt,
+					   ascq);
+		else
+			sdev_prefix_printk(KERN_INFO, sdev, name,
+					   "Add. Sense: %s", extd_sense_str);
 
-	if (extd_sense_fmt) {
-		if (strstr(extd_sense_fmt, "%x")) {
-			printk("Add. Sense: ");
-			printk(extd_sense_fmt, ascq);
-		} else
-			printk("Add. Sense: %s", extd_sense_fmt);
 	} else {
-		if (asc >= 0x80)
-			printk("<<vendor>> ASC=0x%x ASCQ=0x%x", asc,
-			       ascq);
-		if (ascq >= 0x80)
-			printk("ASC=0x%x <<vendor>> ASCQ=0x%x", asc,
-			       ascq);
-		else
-			printk("ASC=0x%x ASCQ=0x%x", asc, ascq);
+		sdev_prefix_printk(KERN_INFO, sdev, name,
+				   "%sASC=0x%x %sASCQ=0x%x\n",
+				   asc >= 0x80 ? "<<vendor>> " : "", asc,
+				   ascq >= 0x80 ? "<<vendor>> " : "", ascq);
 	}
-
-	printk("\n");
 }
 EXPORT_SYMBOL(scsi_show_extd_sense);
 
 void
-scsi_show_sense_hdr(struct scsi_sense_hdr *sshdr)
+scsi_show_sense_hdr(const struct scsi_device *sdev, const char *name,
+		    const struct scsi_sense_hdr *sshdr)
 {
 	const char *sense_txt;
 
 	sense_txt = scsi_sense_key_string(sshdr->sense_key);
 	if (sense_txt)
-		printk("Sense Key : %s ", sense_txt);
+		sdev_prefix_printk(KERN_INFO, sdev, name,
+				   "Sense Key : %s [%s]%s\n", sense_txt,
+				   scsi_sense_is_deferred(sshdr) ?
+				   "deferred" : "current",
+				   sshdr->response_code >= 0x72 ?
+				   " [descriptor]" : "");
 	else
-		printk("Sense Key : 0x%x ", sshdr->sense_key);
-
-	printk("%s", scsi_sense_is_deferred(sshdr) ? "[deferred] " :
-	       "[current] ");
-
-	if (sshdr->response_code >= 0x72)
-		printk("[descriptor]");
-
-	printk("\n");
+		sdev_prefix_printk(KERN_INFO, sdev, name,
+				   "Sense Key : 0x%x [%s]%s", sshdr->sense_key,
+				   scsi_sense_is_deferred(sshdr) ?
+				   "deferred" : "current",
+				   sshdr->response_code >= 0x72 ?
+				   " [descriptor]" : "");
 }
 EXPORT_SYMBOL(scsi_show_sense_hdr);
 
@@ -1419,12 +1427,11 @@ EXPORT_SYMBOL(scsi_show_sense_hdr);
  * Print normalized SCSI sense header with a prefix.
  */
 void
-scsi_print_sense_hdr(const char *name, struct scsi_sense_hdr *sshdr)
+scsi_print_sense_hdr(const struct scsi_device *sdev, const char *name,
+		     const struct scsi_sense_hdr *sshdr)
 {
-	printk(KERN_INFO "%s: ", name);
-	scsi_show_sense_hdr(sshdr);
-	printk(KERN_INFO "%s: ", name);
-	scsi_show_extd_sense(sshdr->asc, sshdr->ascq);
+	scsi_show_sense_hdr(sdev, name, sshdr);
+	scsi_show_extd_sense(sdev, name, sshdr->asc, sshdr->ascq);
 }
 EXPORT_SYMBOL(scsi_print_sense_hdr);
 
@@ -1513,33 +1520,26 @@ scsi_decode_sense_extras(const unsigned char *sense_buffer, int sense_len,
 }
 
 /* Normalize and print sense buffer with name prefix */
-void __scsi_print_sense(const char *name, const unsigned char *sense_buffer,
-			int sense_len)
+void __scsi_print_sense(const struct scsi_device *sdev, const char *name,
+			const unsigned char *sense_buffer, int sense_len)
 {
 	struct scsi_sense_hdr sshdr;
 
-	printk(KERN_INFO "%s: ", name);
 	scsi_decode_sense_buffer(sense_buffer, sense_len, &sshdr);
-	scsi_show_sense_hdr(&sshdr);
+	scsi_show_sense_hdr(sdev, name, &sshdr);
 	scsi_decode_sense_extras(sense_buffer, sense_len, &sshdr);
-	printk(KERN_INFO "%s: ", name);
-	scsi_show_extd_sense(sshdr.asc, sshdr.ascq);
+	scsi_show_extd_sense(sdev, name, sshdr.asc, sshdr.ascq);
 }
 EXPORT_SYMBOL(__scsi_print_sense);
 
 /* Normalize and print sense buffer in SCSI command */
-void scsi_print_sense(char *name, struct scsi_cmnd *cmd)
+void scsi_print_sense(const struct scsi_cmnd *cmd)
 {
-	struct scsi_sense_hdr sshdr;
+	struct gendisk *disk = cmd->request->rq_disk;
+	const char *disk_name = disk ? disk->disk_name : NULL;
 
-	scmd_printk(KERN_INFO, cmd, " ");
-	scsi_decode_sense_buffer(cmd->sense_buffer, SCSI_SENSE_BUFFERSIZE,
-				 &sshdr);
-	scsi_show_sense_hdr(&sshdr);
-	scsi_decode_sense_extras(cmd->sense_buffer, SCSI_SENSE_BUFFERSIZE,
-				 &sshdr);
-	scmd_printk(KERN_INFO, cmd, " ");
-	scsi_show_extd_sense(sshdr.asc, sshdr.ascq);
+	__scsi_print_sense(cmd->device, disk_name, cmd->sense_buffer,
+			   SCSI_SENSE_BUFFERSIZE);
 }
 EXPORT_SYMBOL(scsi_print_sense);
 
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index dff37a250d7..3d0d13c4da1 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -259,9 +259,10 @@ static int osst_chk_result(struct osst_tape * STp, struct osst_request * SRpnt)
 		   SRpnt->cmd[0], SRpnt->cmd[1], SRpnt->cmd[2],
 		   SRpnt->cmd[3], SRpnt->cmd[4], SRpnt->cmd[5]);
 		if (scode) printk(OSST_DEB_MSG "%s:D: Sense: %02x, ASC: %02x, ASCQ: %02x\n",
-			       	name, scode, sense[12], sense[13]);
+				  name, scode, sense[12], sense[13]);
 		if (cmdstatp->have_sense)
-			__scsi_print_sense("osst ", SRpnt->sense, SCSI_SENSE_BUFFERSIZE);
+			__scsi_print_sense(STp->device, name,
+					   SRpnt->sense, SCSI_SENSE_BUFFERSIZE);
 	}
 	else
 #endif
@@ -275,7 +276,8 @@ static int osst_chk_result(struct osst_tape * STp, struct osst_request * SRpnt)
 		 SRpnt->cmd[0] != TEST_UNIT_READY)) { /* Abnormal conditions for tape */
 		if (cmdstatp->have_sense) {
 			printk(KERN_WARNING "%s:W: Command with sense data:\n", name);
-			__scsi_print_sense("osst ", SRpnt->sense, SCSI_SENSE_BUFFERSIZE);
+			__scsi_print_sense(STp->device, name,
+					   SRpnt->sense, SCSI_SENSE_BUFFERSIZE);
 		}
 		else {
 			static	int	notyetprinted = 1;
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 79c77b485a6..32eaac03cf4 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -606,7 +606,7 @@ void scsi_log_completion(struct scsi_cmnd *cmd, int disposition)
 			scsi_print_result(cmd);
 			scsi_print_command(cmd);
 			if (status_byte(cmd->result) & CHECK_CONDITION)
-				scsi_print_sense("", cmd);
+				scsi_print_sense(cmd);
 			if (level > 3)
 				scmd_printk(KERN_INFO, cmd,
 					    "scsi host busy %d failed %d\n",
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 0ed666112b4..0084f0b21a9 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1180,7 +1180,7 @@ int scsi_eh_get_sense(struct list_head *work_q,
 		SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd,
 			"sense requested for %p result %x\n",
 			scmd, scmd->result));
-		SCSI_LOG_ERROR_RECOVERY(3, scsi_print_sense("bh", scmd));
+		SCSI_LOG_ERROR_RECOVERY(3, scsi_print_sense(scmd));
 
 		rtn = scsi_decide_disposition(scmd);
 
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 12fe676d134..5207274574f 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -126,7 +126,7 @@ static int ioctl_internal_command(struct scsi_device *sdev, char *cmd,
 			sdev_printk(KERN_INFO, sdev,
 				    "ioctl_internal_command return code = %x\n",
 				    result);
-			scsi_print_sense_hdr("   ", &sshdr);
+			scsi_print_sense_hdr(sdev, NULL, &sshdr);
 			break;
 		}
 	}
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 389bc6fd19a..3c96e392352 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -912,7 +912,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d))
 			;
 		else if (!(req->cmd_flags & REQ_QUIET))
-			scsi_print_sense("", cmd);
+			scsi_print_sense(cmd);
 		result = 0;
 		/* BLOCK_PC may have set error */
 		error = 0;
@@ -1041,7 +1041,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		if (!(req->cmd_flags & REQ_QUIET)) {
 			scsi_print_result(cmd);
 			if (driver_byte(result) & DRIVER_SENSE)
-				scsi_print_sense("", cmd);
+				scsi_print_sense(cmd);
 			scsi_print_command(cmd);
 		}
 		if (!scsi_end_request(req, error, blk_rq_err_bytes(req), 0))
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 52b40b1e8c4..3ae75402809 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3336,10 +3336,11 @@ module_exit(exit_sd);
 static void sd_print_sense_hdr(struct scsi_disk *sdkp,
 			       struct scsi_sense_hdr *sshdr)
 {
-	sd_printk(KERN_INFO, sdkp, " ");
-	scsi_show_sense_hdr(sshdr);
-	sd_printk(KERN_INFO, sdkp, " ");
-	scsi_show_extd_sense(sshdr->asc, sshdr->ascq);
+	scsi_show_sense_hdr(sdkp->device,
+			    sdkp->disk ? sdkp->disk->disk_name : NULL, sshdr);
+	scsi_show_extd_sense(sdkp->device,
+			     sdkp->disk ? sdkp->disk->disk_name : NULL,
+			     sshdr->asc, sshdr->ascq);
 }
 
 static void sd_print_result(struct scsi_disk *sdkp, int result)
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 55cbc6689d2..2fe2701d86d 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1365,7 +1365,7 @@ sg_rq_end_io(struct request *rq, int uptodate)
 		if ((sdp->sgdebug > 0) &&
 		    ((CHECK_CONDITION == srp->header.masked_status) ||
 		     (COMMAND_TERMINATED == srp->header.masked_status)))
-			__scsi_print_sense(__func__, sense,
+			__scsi_print_sense(sdp->device, __func__, sense,
 					   SCSI_SENSE_BUFFERSIZE);
 
 		/* Following if statement is a patch supplied by Eric Youngdale */
diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
index 6389fcff12e..17e0c2b28a9 100644
--- a/drivers/scsi/sr_ioctl.c
+++ b/drivers/scsi/sr_ioctl.c
@@ -246,7 +246,7 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 					  "CDROM not ready.  Make sure there "
 					  "is a disc in the drive.\n");
 #ifdef DEBUG
-			scsi_print_sense_hdr("sr", &sshdr);
+			scsi_print_sense_hdr(cd->device, cd->cdi.name, &sshdr);
 #endif
 			err = -ENOMEDIUM;
 			break;
@@ -258,14 +258,14 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 				err = -EDRIVE_CANT_DO_THIS;
 #ifdef DEBUG
 			__scsi_print_command(cgc->cmd);
-			scsi_print_sense_hdr("sr", &sshdr);
+			scsi_print_sense_hdr(cd->device, cd->cdi.name, &sshdr);
 #endif
 			break;
 		default:
 			sr_printk(KERN_ERR, cd,
 				  "CDROM (ioctl) error, command: ");
 			__scsi_print_command(cgc->cmd);
-			scsi_print_sense_hdr("sr", &sshdr);
+			scsi_print_sense_hdr(cd->device, cd->cdi.name, &sshdr);
 			err = -EIO;
 		}
 	}
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 36ab023793c..63c35ed3c88 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -381,7 +381,8 @@ static int st_chk_result(struct scsi_tape *STp, struct st_request * SRpnt)
 			    SRpnt->cmd[0], SRpnt->cmd[1], SRpnt->cmd[2],
 			    SRpnt->cmd[3], SRpnt->cmd[4], SRpnt->cmd[5]);
 		if (cmdstatp->have_sense)
-			 __scsi_print_sense(name, SRpnt->sense, SCSI_SENSE_BUFFERSIZE);
+			__scsi_print_sense(STp->device, name,
+					   SRpnt->sense, SCSI_SENSE_BUFFERSIZE);
 	} ) /* end DEB */
 	if (!debugging) { /* Abnormal conditions for tape */
 		if (!cmdstatp->have_sense)
@@ -397,7 +398,8 @@ static int st_chk_result(struct scsi_tape *STp, struct st_request * SRpnt)
 			 SRpnt->cmd[0] != MODE_SENSE &&
 			 SRpnt->cmd[0] != TEST_UNIT_READY) {
 
-			__scsi_print_sense(name, SRpnt->sense, SCSI_SENSE_BUFFERSIZE);
+			__scsi_print_sense(STp->device, name,
+					   SRpnt->sense, SCSI_SENSE_BUFFERSIZE);
 		}
 	}
 
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 733e5f75951..37f5fd8ed76 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1097,7 +1097,8 @@ static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request)
 	if (scmnd->result) {
 		if (scsi_normalize_sense(scmnd->sense_buffer,
 				SCSI_SENSE_BUFFERSIZE, &sense_hdr))
-			scsi_print_sense_hdr("storvsc", &sense_hdr);
+			scsi_print_sense_hdr(scmnd->device, "storvsc",
+					     &sense_hdr);
 	}
 
 	if (vm_srb->srb_status != SRB_STATUS_SUCCESS)
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 497c38a4a86..eb3997ed8e7 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -4710,8 +4710,8 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 			  "START_STOP failed for power mode: %d\n", pwr_mode);
 		scsi_show_result(ret);
 		if (driver_byte(ret) & DRIVER_SENSE) {
-			scsi_show_sense_hdr(&sshdr);
-			scsi_show_extd_sense(sshdr.asc, sshdr.ascq);
+			scsi_show_sense_hdr(sdp, NULL, &sshdr);
+			scsi_show_extd_sense(sdp, NULL, sshdr.asc, sshdr.ascq);
 		}
 	}
 
diff --git a/drivers/usb/storage/debug.c b/drivers/usb/storage/debug.c
index e08f64780e3..66a684a2993 100644
--- a/drivers/usb/storage/debug.c
+++ b/drivers/usb/storage/debug.c
@@ -164,10 +164,10 @@ void usb_stor_show_sense(const struct us_data *us,
 			 unsigned char asc,
 			 unsigned char ascq)
 {
-	const char *what, *keystr;
+	const char *what, *keystr, *fmt;
 
 	keystr = scsi_sense_key_string(key);
-	what = scsi_extd_sense_format(asc, ascq);
+	what = scsi_extd_sense_format(asc, ascq, &fmt);
 
 	if (keystr == NULL)
 		keystr = "(Unknown Key)";
@@ -175,8 +175,10 @@ void usb_stor_show_sense(const struct us_data *us,
 		what = "(unknown ASC/ASCQ)";
 
 	usb_stor_dbg(us, "%s: ", keystr);
-	US_DEBUGPX(what, ascq);
-	US_DEBUGPX("\n");
+	if (fmt)
+		US_DEBUGPX("%s (%s%x)\n", what, fmt, ascq);
+	else
+		US_DEBUGPX("%s\n", what);
 }
 
 int usb_stor_dbg(const struct us_data *us, const char *fmt, ...)
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 3e32146472a..50610a6acf3 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -274,10 +274,6 @@ static void scsiback_print_status(char *sense_buffer, int errors,
 	       tpg->tport->tport_name, pending_req->v2p->lun,
 	       pending_req->cmnd[0], status_byte(errors), msg_byte(errors),
 	       host_byte(errors), driver_byte(errors));
-
-	if (CHECK_CONDITION & status_byte(errors))
-		__scsi_print_sense("xen-pvscsi", sense_buffer,
-				   SCSI_SENSE_BUFFERSIZE);
 }
 
 static void scsiback_fast_flush_area(struct vscsibk_pend *req)
diff --git a/include/scsi/scsi_dbg.h b/include/scsi/scsi_dbg.h
index 5a43a4cd96c..6cbd179a17c 100644
--- a/include/scsi/scsi_dbg.h
+++ b/include/scsi/scsi_dbg.h
@@ -2,21 +2,26 @@
 #define _SCSI_SCSI_DBG_H
 
 struct scsi_cmnd;
+struct scsi_device;
 struct scsi_sense_hdr;
 
 extern void scsi_print_command(struct scsi_cmnd *);
 extern void __scsi_print_command(unsigned char *);
-extern void scsi_show_extd_sense(unsigned char, unsigned char);
-extern void scsi_show_sense_hdr(struct scsi_sense_hdr *);
-extern void scsi_print_sense_hdr(const char *, struct scsi_sense_hdr *);
-extern void scsi_print_sense(char *, struct scsi_cmnd *);
-extern void __scsi_print_sense(const char *name,
+extern void scsi_show_extd_sense(const struct scsi_device *, const char *,
+				 unsigned char, unsigned char);
+extern void scsi_show_sense_hdr(const struct scsi_device *, const char *,
+				const struct scsi_sense_hdr *);
+extern void scsi_print_sense_hdr(const struct scsi_device *, const char *,
+				 const struct scsi_sense_hdr *);
+extern void scsi_print_sense(const struct scsi_cmnd *);
+extern void __scsi_print_sense(const struct scsi_device *, const char *name,
 			       const unsigned char *sense_buffer,
 			       int sense_len);
 extern void scsi_show_result(int);
 extern void scsi_print_result(struct scsi_cmnd *);
 extern void scsi_print_status(unsigned char);
 extern const char *scsi_sense_key_string(unsigned char);
-extern const char *scsi_extd_sense_format(unsigned char, unsigned char);
+extern const char *scsi_extd_sense_format(unsigned char, unsigned char,
+					  const char **);
 
 #endif /* _SCSI_SCSI_DBG_H */
diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h
index 49af14ad528..5e598f01143 100644
--- a/include/scsi/scsi_eh.h
+++ b/include/scsi/scsi_eh.h
@@ -47,7 +47,7 @@ extern int scsi_normalize_sense(const u8 *sense_buffer, int sb_len,
 extern int scsi_command_normalize_sense(struct scsi_cmnd *cmd,
 		struct scsi_sense_hdr *sshdr);
 
-static inline int scsi_sense_is_deferred(struct scsi_sense_hdr *sshdr)
+static inline int scsi_sense_is_deferred(const struct scsi_sense_hdr *sshdr)
 {
 	return ((sshdr->response_code >= 0x70) && (sshdr->response_code & 1));
 }
-- 
cgit v1.2.3-70-g09d2


From 4753cbc0a1286a60d2f859a7056f8e4873f494c8 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 24 Oct 2014 14:26:52 +0200
Subject: scsi: use 'bool' as return value for scsi_normalize_sense()

Convert scsi_normalize_sense() and friends to return 'bool'
instead of an integer.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Yoshihiro Yunomae <yoshihiro.yunomae.ez@hitachi.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/scsi_error.c | 16 ++++++++--------
 drivers/scsi/scsi_lib.c   |  2 +-
 include/scsi/scsi_eh.h    | 14 +++++++-------
 3 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 0084f0b21a9..ab570f5cb6b 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -2422,20 +2422,20 @@ EXPORT_SYMBOL(scsi_reset_provider);
  *	responded to a SCSI command with the CHECK_CONDITION status.
  *
  * Return value:
- *	1 if valid sense data information found, else 0;
+ *	true if valid sense data information found, else false;
  */
-int scsi_normalize_sense(const u8 *sense_buffer, int sb_len,
-                         struct scsi_sense_hdr *sshdr)
+bool scsi_normalize_sense(const u8 *sense_buffer, int sb_len,
+			  struct scsi_sense_hdr *sshdr)
 {
 	if (!sense_buffer || !sb_len)
-		return 0;
+		return false;
 
 	memset(sshdr, 0, sizeof(struct scsi_sense_hdr));
 
 	sshdr->response_code = (sense_buffer[0] & 0x7f);
 
 	if (!scsi_sense_valid(sshdr))
-		return 0;
+		return false;
 
 	if (sshdr->response_code >= 0x72) {
 		/*
@@ -2465,12 +2465,12 @@ int scsi_normalize_sense(const u8 *sense_buffer, int sb_len,
 		}
 	}
 
-	return 1;
+	return true;
 }
 EXPORT_SYMBOL(scsi_normalize_sense);
 
-int scsi_command_normalize_sense(struct scsi_cmnd *cmd,
-				 struct scsi_sense_hdr *sshdr)
+bool scsi_command_normalize_sense(const struct scsi_cmnd *cmd,
+				  struct scsi_sense_hdr *sshdr)
 {
 	return scsi_normalize_sense(cmd->sense_buffer,
 			SCSI_SENSE_BUFFERSIZE, sshdr);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 3c96e392352..30f51c11a27 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -831,7 +831,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	struct request *req = cmd->request;
 	int error = 0;
 	struct scsi_sense_hdr sshdr;
-	int sense_valid = 0;
+	bool sense_valid = false;
 	int sense_deferred = 0;
 	enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY,
 	      ACTION_DELAYED_RETRY} action;
diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h
index 5e598f01143..25624814132 100644
--- a/include/scsi/scsi_eh.h
+++ b/include/scsi/scsi_eh.h
@@ -27,10 +27,10 @@ struct scsi_sense_hdr {		/* See SPC-3 section 4.5 */
 	u8 additional_length;	/* always 0 for fixed sense format */
 };
 
-static inline int scsi_sense_valid(struct scsi_sense_hdr *sshdr)
+static inline bool scsi_sense_valid(const struct scsi_sense_hdr *sshdr)
 {
 	if (!sshdr)
-		return 0;
+		return false;
 
 	return (sshdr->response_code & 0x70) == 0x70;
 }
@@ -42,12 +42,12 @@ extern void scsi_eh_flush_done_q(struct list_head *done_q);
 extern void scsi_report_bus_reset(struct Scsi_Host *, int);
 extern void scsi_report_device_reset(struct Scsi_Host *, int, int);
 extern int scsi_block_when_processing_errors(struct scsi_device *);
-extern int scsi_normalize_sense(const u8 *sense_buffer, int sb_len,
-		struct scsi_sense_hdr *sshdr);
-extern int scsi_command_normalize_sense(struct scsi_cmnd *cmd,
-		struct scsi_sense_hdr *sshdr);
+extern bool scsi_normalize_sense(const u8 *sense_buffer, int sb_len,
+				 struct scsi_sense_hdr *sshdr);
+extern bool scsi_command_normalize_sense(const struct scsi_cmnd *cmd,
+					 struct scsi_sense_hdr *sshdr);
 
-static inline int scsi_sense_is_deferred(const struct scsi_sense_hdr *sshdr)
+static inline bool scsi_sense_is_deferred(const struct scsi_sense_hdr *sshdr)
 {
 	return ((sshdr->response_code >= 0x70) && (sshdr->response_code & 1));
 }
-- 
cgit v1.2.3-70-g09d2


From 7ac7076344d90b27e0b6dcbe1380b0841f70859b Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 24 Oct 2014 14:26:53 +0200
Subject: scsi: remove scsi_print_status()

Last caller is gone, so we can remove it.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/constants.c | 35 -----------------------------------
 include/scsi/scsi_dbg.h  |  1 -
 2 files changed, 36 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index 94c0642e287..885c559164d 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -433,41 +433,6 @@ void scsi_print_command(struct scsi_cmnd *cmd)
 }
 EXPORT_SYMBOL(scsi_print_command);
 
-/**
- *	scsi_print_status - print scsi status description
- *	@scsi_status: scsi status value
- *
- *	If the status is recognized, the description is printed.
- *	Otherwise "Unknown status" is output. No trailing space.
- *	If CONFIG_SCSI_CONSTANTS is not set, then print status in hex
- *	(e.g. "0x2" for Check Condition).
- **/
-void
-scsi_print_status(unsigned char scsi_status) {
-#ifdef CONFIG_SCSI_CONSTANTS
-	const char * ccp;
-
-	switch (scsi_status) {
-	case 0:    ccp = "Good"; break;
-	case 0x2:  ccp = "Check Condition"; break;
-	case 0x4:  ccp = "Condition Met"; break;
-	case 0x8:  ccp = "Busy"; break;
-	case 0x10: ccp = "Intermediate"; break;
-	case 0x14: ccp = "Intermediate-Condition Met"; break;
-	case 0x18: ccp = "Reservation Conflict"; break;
-	case 0x22: ccp = "Command Terminated"; break;	/* obsolete */
-	case 0x28: ccp = "Task set Full"; break;	/* was: Queue Full */
-	case 0x30: ccp = "ACA Active"; break;
-	case 0x40: ccp = "Task Aborted"; break;
-	default:   ccp = "Unknown status";
-	}
-	printk(KERN_INFO "%s", ccp);
-#else
-	printk(KERN_INFO "0x%0x", scsi_status);
-#endif
-}
-EXPORT_SYMBOL(scsi_print_status);
-
 #ifdef CONFIG_SCSI_CONSTANTS
 
 struct error_info {
diff --git a/include/scsi/scsi_dbg.h b/include/scsi/scsi_dbg.h
index 6cbd179a17c..386474ee53a 100644
--- a/include/scsi/scsi_dbg.h
+++ b/include/scsi/scsi_dbg.h
@@ -19,7 +19,6 @@ extern void __scsi_print_sense(const struct scsi_device *, const char *name,
 			       int sense_len);
 extern void scsi_show_result(int);
 extern void scsi_print_result(struct scsi_cmnd *);
-extern void scsi_print_status(unsigned char);
 extern const char *scsi_sense_key_string(unsigned char);
 extern const char *scsi_extd_sense_format(unsigned char, unsigned char,
 					  const char **);
-- 
cgit v1.2.3-70-g09d2


From a9a47bf58ac1d5525ae99922e055d8de87eeae78 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 24 Oct 2014 14:26:57 +0200
Subject: scsi: repurpose the last argument from print_opcode_name()

print_opcode_name() was only ever called with a '0' argument
from LLDDs and ULDs which were _not_ supporting variable length
CDBs, so the 'if' clause was never triggered.
Instead we should be using the last argument to specify
the cdb length to avoid accidental overflow when reading
the cdb buffer.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/arm/fas216.c |  2 +-
 drivers/scsi/ch.c         | 24 +++++++++++++-----------
 drivers/scsi/constants.c  | 25 ++++++++++---------------
 drivers/scsi/sr_ioctl.c   |  4 ++--
 include/scsi/scsi_dbg.h   |  2 +-
 5 files changed, 27 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/arm/fas216.c b/drivers/scsi/arm/fas216.c
index cea34633b90..d2581cb41ec 100644
--- a/drivers/scsi/arm/fas216.c
+++ b/drivers/scsi/arm/fas216.c
@@ -2424,7 +2424,7 @@ int fas216_eh_abort(struct scsi_cmnd *SCpnt)
 	info->stats.aborts += 1;
 
 	printk(KERN_WARNING "scsi%d: abort command ", info->host->host_no);
-	__scsi_print_command(SCpnt->cmnd);
+	__scsi_print_command(SCpnt->cmnd, SCpnt->cmd_len);
 
 	print_debug_list();
 	fas216_dumpstate(info);
diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index 53621a34c5f..226ef771eff 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -182,7 +182,7 @@ static int ch_find_errno(struct scsi_sense_hdr *sshdr)
 }
 
 static int
-ch_do_scsi(scsi_changer *ch, unsigned char *cmd,
+ch_do_scsi(scsi_changer *ch, unsigned char *cmd, int cmd_len,
 	   void *buffer, unsigned buflength,
 	   enum dma_data_direction direction)
 {
@@ -196,7 +196,7 @@ ch_do_scsi(scsi_changer *ch, unsigned char *cmd,
 	errno = 0;
 	if (debug) {
 		DPRINTK("command: ");
-		__scsi_print_command(cmd);
+		__scsi_print_command(cmd, cmd_len);
 	}
 
 	result = scsi_execute_req(ch->device, cmd, direction, buffer,
@@ -257,7 +257,8 @@ ch_read_element_status(scsi_changer *ch, u_int elem, char *data)
 	cmd[3] = elem        & 0xff;
 	cmd[5] = 1;
 	cmd[9] = 255;
-	if (0 == (result = ch_do_scsi(ch, cmd, buffer, 256, DMA_FROM_DEVICE))) {
+	if (0 == (result = ch_do_scsi(ch, cmd, 12,
+				      buffer, 256, DMA_FROM_DEVICE))) {
 		if (((buffer[16] << 8) | buffer[17]) != elem) {
 			DPRINTK("asked for element 0x%02x, got 0x%02x\n",
 				elem,(buffer[16] << 8) | buffer[17]);
@@ -287,7 +288,7 @@ ch_init_elem(scsi_changer *ch)
 	memset(cmd,0,sizeof(cmd));
 	cmd[0] = INITIALIZE_ELEMENT_STATUS;
 	cmd[1] = (ch->device->lun & 0x7) << 5;
-	err = ch_do_scsi(ch, cmd, NULL, 0, DMA_NONE);
+	err = ch_do_scsi(ch, cmd, 6, NULL, 0, DMA_NONE);
 	VPRINTK(KERN_INFO, "... finished\n");
 	return err;
 }
@@ -309,10 +310,10 @@ ch_readconfig(scsi_changer *ch)
 	cmd[1] = (ch->device->lun & 0x7) << 5;
 	cmd[2] = 0x1d;
 	cmd[4] = 255;
-	result = ch_do_scsi(ch, cmd, buffer, 255, DMA_FROM_DEVICE);
+	result = ch_do_scsi(ch, cmd, 10, buffer, 255, DMA_FROM_DEVICE);
 	if (0 != result) {
 		cmd[1] |= (1<<3);
-		result  = ch_do_scsi(ch, cmd, buffer, 255, DMA_FROM_DEVICE);
+		result  = ch_do_scsi(ch, cmd, 10, buffer, 255, DMA_FROM_DEVICE);
 	}
 	if (0 == result) {
 		ch->firsts[CHET_MT] =
@@ -437,7 +438,7 @@ ch_position(scsi_changer *ch, u_int trans, u_int elem, int rotate)
 	cmd[4]  = (elem  >> 8) & 0xff;
 	cmd[5]  =  elem        & 0xff;
 	cmd[8]  = rotate ? 1 : 0;
-	return ch_do_scsi(ch, cmd, NULL, 0, DMA_NONE);
+	return ch_do_scsi(ch, cmd, 10, NULL, 0, DMA_NONE);
 }
 
 static int
@@ -458,7 +459,7 @@ ch_move(scsi_changer *ch, u_int trans, u_int src, u_int dest, int rotate)
 	cmd[6]  = (dest  >> 8) & 0xff;
 	cmd[7]  =  dest        & 0xff;
 	cmd[10] = rotate ? 1 : 0;
-	return ch_do_scsi(ch, cmd, NULL,0, DMA_NONE);
+	return ch_do_scsi(ch, cmd, 12, NULL,0, DMA_NONE);
 }
 
 static int
@@ -484,7 +485,7 @@ ch_exchange(scsi_changer *ch, u_int trans, u_int src,
 	cmd[9]  =  dest2       & 0xff;
 	cmd[10] = (rotate1 ? 1 : 0) | (rotate2 ? 2 : 0);
 
-	return ch_do_scsi(ch, cmd, NULL,0, DMA_NONE);
+	return ch_do_scsi(ch, cmd, 12, NULL, 0, DMA_NONE);
 }
 
 static void
@@ -534,7 +535,7 @@ ch_set_voltag(scsi_changer *ch, u_int elem,
 	memcpy(buffer,tag,32);
 	ch_check_voltag(buffer);
 
-	result = ch_do_scsi(ch, cmd, buffer, 256, DMA_TO_DEVICE);
+	result = ch_do_scsi(ch, cmd, 12, buffer, 256, DMA_TO_DEVICE);
 	kfree(buffer);
 	return result;
 }
@@ -765,7 +766,8 @@ static long ch_ioctl(struct file *file,
 		ch_cmd[5] = 1;
 		ch_cmd[9] = 255;
 
-		result = ch_do_scsi(ch, ch_cmd, buffer, 256, DMA_FROM_DEVICE);
+		result = ch_do_scsi(ch, ch_cmd, 12,
+				    buffer, 256, DMA_FROM_DEVICE);
 		if (!result) {
 			cge.cge_status = buffer[18];
 			cge.cge_flags = 0;
diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index dc1b18c821e..a84ced0de02 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -320,25 +320,21 @@ static bool scsi_opcode_sa_name(int opcode, int service_action,
 	return true;
 }
 
-/* attempt to guess cdb length if cdb_len==0 . No trailing linefeed. */
-static void print_opcode_name(unsigned char * cdbp, int cdb_len)
+static void print_opcode_name(const unsigned char *cdbp, size_t cdb_len)
 {
-	int sa, len, cdb0;
+	int sa, cdb0;
 	const char *cdb_name = NULL, *sa_name = NULL;
 
 	cdb0 = cdbp[0];
 	if (cdb0 == VARIABLE_LENGTH_CMD) {
-		len = scsi_varlen_cdb_length(cdbp);
-		if (len < 10) {
-			printk("short variable length command, "
-			       "len=%d ext_len=%d", len, cdb_len);
+		if (cdb_len < 10) {
+			printk("short variable length command, len=%zu",
+			       cdb_len);
 			return;
 		}
 		sa = (cdbp[8] << 8) + cdbp[9];
-	} else {
+	} else
 		sa = cdbp[1] & 0x1f;
-		len = cdb_len;
-	}
 
 	if (!scsi_opcode_sa_name(cdb0, sa, &cdb_name, &sa_name)) {
 		if (cdb_name)
@@ -356,18 +352,17 @@ static void print_opcode_name(unsigned char * cdbp, int cdb_len)
 			printk("%s, sa=0x%x", cdb_name, sa);
 		else
 			printk("cdb[0]=0x%x, sa=0x%x", cdb0, sa);
-
-		if (cdb_len > 0 && len != cdb_len)
-			printk(", in_cdb_len=%d, ext_len=%d", len, cdb_len);
 	}
 }
 
-void __scsi_print_command(unsigned char *cdb)
+void __scsi_print_command(const unsigned char *cdb, size_t cdb_len)
 {
 	int k, len;
 
-	print_opcode_name(cdb, 0);
+	print_opcode_name(cdb, cdb_len);
 	len = scsi_command_size(cdb);
+	if (cdb_len < len)
+		len = cdb_len;
 	/* print out all bytes in cdb */
 	for (k = 0; k < len; ++k)
 		printk(" %02x", cdb[k]);
diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
index 17e0c2b28a9..fb929fac22b 100644
--- a/drivers/scsi/sr_ioctl.c
+++ b/drivers/scsi/sr_ioctl.c
@@ -257,14 +257,14 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 				/* sense: Invalid command operation code */
 				err = -EDRIVE_CANT_DO_THIS;
 #ifdef DEBUG
-			__scsi_print_command(cgc->cmd);
+			__scsi_print_command(cgc->cmd, CDROM_PACKET_SIZE);
 			scsi_print_sense_hdr(cd->device, cd->cdi.name, &sshdr);
 #endif
 			break;
 		default:
 			sr_printk(KERN_ERR, cd,
 				  "CDROM (ioctl) error, command: ");
-			__scsi_print_command(cgc->cmd);
+			__scsi_print_command(cgc->cmd, CDROM_PACKET_SIZE);
 			scsi_print_sense_hdr(cd->device, cd->cdi.name, &sshdr);
 			err = -EIO;
 		}
diff --git a/include/scsi/scsi_dbg.h b/include/scsi/scsi_dbg.h
index 386474ee53a..81d04182222 100644
--- a/include/scsi/scsi_dbg.h
+++ b/include/scsi/scsi_dbg.h
@@ -6,7 +6,7 @@ struct scsi_device;
 struct scsi_sense_hdr;
 
 extern void scsi_print_command(struct scsi_cmnd *);
-extern void __scsi_print_command(unsigned char *);
+extern void __scsi_print_command(const unsigned char *, size_t);
 extern void scsi_show_extd_sense(const struct scsi_device *, const char *,
 				 unsigned char, unsigned char);
 extern void scsi_show_sense_hdr(const struct scsi_device *, const char *,
-- 
cgit v1.2.3-70-g09d2


From 3cc958cc19278de5fa090f3f7f1ed48b0170980a Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 24 Oct 2014 14:26:59 +0200
Subject: scsi: separate out scsi_(host|driver)byte_string()

Export functions for later use.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/constants.c | 58 ++++++++++++++++++++++++++++++++++++------------
 include/scsi/scsi_dbg.h  |  2 ++
 2 files changed, 46 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index a84ced0de02..541a8620929 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -1407,38 +1407,68 @@ static const char * const hostbyte_table[]={
 "DID_PASSTHROUGH", "DID_SOFT_ERROR", "DID_IMM_RETRY", "DID_REQUEUE",
 "DID_TRANSPORT_DISRUPTED", "DID_TRANSPORT_FAILFAST", "DID_TARGET_FAILURE",
 "DID_NEXUS_FAILURE" };
-#define NUM_HOSTBYTE_STRS ARRAY_SIZE(hostbyte_table)
 
 static const char * const driverbyte_table[]={
 "DRIVER_OK", "DRIVER_BUSY", "DRIVER_SOFT",  "DRIVER_MEDIA", "DRIVER_ERROR",
 "DRIVER_INVALID", "DRIVER_TIMEOUT", "DRIVER_HARD", "DRIVER_SENSE"};
-#define NUM_DRIVERBYTE_STRS ARRAY_SIZE(driverbyte_table)
 
-void scsi_show_result(int result)
+#endif
+
+const char *scsi_hostbyte_string(int result)
 {
+	const char *hb_string = NULL;
+#ifdef CONFIG_SCSI_CONSTANTS
 	int hb = host_byte(result);
-	int db = driver_byte(result);
 
-	printk("Result: hostbyte=%s driverbyte=%s\n",
-	       (hb < NUM_HOSTBYTE_STRS ? hostbyte_table[hb]     : "invalid"),
-	       (db < NUM_DRIVERBYTE_STRS ? driverbyte_table[db] : "invalid"));
+	if (hb < ARRAY_SIZE(hostbyte_table))
+		hb_string = hostbyte_table[hb];
+#endif
+	return hb_string;
 }
+EXPORT_SYMBOL(scsi_hostbyte_string);
 
-#else
+const char *scsi_driverbyte_string(int result)
+{
+	const char *db_string = NULL;
+#ifdef CONFIG_SCSI_CONSTANTS
+	int db = driver_byte(result);
+
+	if (db < ARRAY_SIZE(driverbyte_table))
+		db_string = driverbyte_table[db];
+#endif
+	return db_string;
+}
+EXPORT_SYMBOL(scsi_driverbyte_string);
 
 void scsi_show_result(int result)
 {
-	printk("Result: hostbyte=0x%02x driverbyte=0x%02x\n",
-	       host_byte(result), driver_byte(result));
-}
+	const char *hb_string = scsi_hostbyte_string(result);
+	const char *db_string = scsi_driverbyte_string(result);
 
-#endif
+	if (hb_string || db_string)
+		printk("Result: hostbyte=%s driverbyte=%s\n",
+		       hb_string ? hb_string : "invalid",
+		       db_string ? db_string : "invalid");
+	else
+		printk("Result: hostbyte=0x%02x driverbyte=0x%02x\n",
+		       host_byte(result), driver_byte(result));
+}
 EXPORT_SYMBOL(scsi_show_result);
 
 
 void scsi_print_result(struct scsi_cmnd *cmd)
 {
-	scmd_printk(KERN_INFO, cmd, " ");
-	scsi_show_result(cmd->result);
+	const char *hb_string = scsi_hostbyte_string(cmd->result);
+	const char *db_string = scsi_driverbyte_string(cmd->result);
+
+	if (hb_string || db_string)
+		scmd_printk(KERN_INFO, cmd,
+			    "Result: hostbyte=%s driverbyte=%s",
+			    hb_string ? hb_string : "invalid",
+			    db_string ? db_string : "invalid");
+	else
+		scmd_printk(KERN_INFO, cmd,
+			    "Result: hostbyte=0x%02x driverbyte=0x%02x",
+			    host_byte(cmd->result), driver_byte(cmd->result));
 }
 EXPORT_SYMBOL(scsi_print_result);
diff --git a/include/scsi/scsi_dbg.h b/include/scsi/scsi_dbg.h
index 81d04182222..50f4d8542ec 100644
--- a/include/scsi/scsi_dbg.h
+++ b/include/scsi/scsi_dbg.h
@@ -19,6 +19,8 @@ extern void __scsi_print_sense(const struct scsi_device *, const char *name,
 			       int sense_len);
 extern void scsi_show_result(int);
 extern void scsi_print_result(struct scsi_cmnd *);
+extern const char *scsi_hostbyte_string(int);
+extern const char *scsi_driverbyte_string(int);
 extern const char *scsi_sense_key_string(unsigned char);
 extern const char *scsi_extd_sense_format(unsigned char, unsigned char,
 					  const char **);
-- 
cgit v1.2.3-70-g09d2


From ef61329db7b8b4326b1c4e603806b2754fd2a692 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 24 Oct 2014 14:27:00 +0200
Subject: scsi: remove scsi_show_result()

Open-code scsi_print_result in sd.c, and cleanup logging to
not print duplicate informations.
Also remove the call to scsi_show_result() in ufshcd.c
to be consistent with other callers of scsi_execute().

With that we can remove scsi_show_result in constants.c

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/constants.c  | 16 ---------------
 drivers/scsi/sd.c         | 50 ++++++++++++++++++++++++-----------------------
 drivers/scsi/ufs/ufshcd.c |  4 ++--
 include/scsi/scsi_dbg.h   |  1 -
 4 files changed, 28 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index 541a8620929..2893464129b 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -1440,22 +1440,6 @@ const char *scsi_driverbyte_string(int result)
 }
 EXPORT_SYMBOL(scsi_driverbyte_string);
 
-void scsi_show_result(int result)
-{
-	const char *hb_string = scsi_hostbyte_string(result);
-	const char *db_string = scsi_driverbyte_string(result);
-
-	if (hb_string || db_string)
-		printk("Result: hostbyte=%s driverbyte=%s\n",
-		       hb_string ? hb_string : "invalid",
-		       db_string ? db_string : "invalid");
-	else
-		printk("Result: hostbyte=0x%02x driverbyte=0x%02x\n",
-		       host_byte(result), driver_byte(result));
-}
-EXPORT_SYMBOL(scsi_show_result);
-
-
 void scsi_print_result(struct scsi_cmnd *cmd)
 {
 	const char *hb_string = scsi_hostbyte_string(cmd->result);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 3ae75402809..242f9b17728 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -116,7 +116,7 @@ static int sd_eh_action(struct scsi_cmnd *, int);
 static void sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer);
 static void scsi_disk_release(struct device *cdev);
 static void sd_print_sense_hdr(struct scsi_disk *, struct scsi_sense_hdr *);
-static void sd_print_result(struct scsi_disk *, int);
+static void sd_print_result(const struct scsi_disk *, const char *, int);
 
 static DEFINE_SPINLOCK(sd_index_lock);
 static DEFINE_IDA(sd_index_ida);
@@ -1492,7 +1492,7 @@ static int sd_sync_cache(struct scsi_disk *sdkp)
 	}
 
 	if (res) {
-		sd_print_result(sdkp, res);
+		sd_print_result(sdkp, "Synchronize Cache(10) failed", res);
 
 		if (driver_byte(res) & DRIVER_SENSE)
 			sd_print_sense_hdr(sdkp, &sshdr);
@@ -1713,17 +1713,6 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 		if (sense_valid)
 			sense_deferred = scsi_sense_is_deferred(&sshdr);
 	}
-#ifdef CONFIG_SCSI_LOGGING
-	SCSI_LOG_HLCOMPLETE(1, scsi_print_result(SCpnt));
-	if (sense_valid) {
-		SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, SCpnt,
-						   "sd_done: sb[respc,sk,asc,"
-						   "ascq]=%x,%x,%x,%x\n",
-						   sshdr.response_code,
-						   sshdr.sense_key, sshdr.asc,
-						   sshdr.ascq));
-	}
-#endif
 	sdkp->medium_access_timed_out = 0;
 
 	if (driver_byte(result) != DRIVER_SENSE &&
@@ -1778,6 +1767,10 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 		break;
 	}
  out:
+	SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, SCpnt,
+					   "sd_done: completed %d of %d bytes\n",
+					   good_bytes, scsi_bufflen(SCpnt)));
+
 	if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt))
 		sd_dif_complete(SCpnt, good_bytes);
 
@@ -1833,12 +1826,12 @@ sd_spinup_disk(struct scsi_disk *sdkp)
 			/* no sense, TUR either succeeded or failed
 			 * with a status error */
 			if(!spintime && !scsi_status_is_good(the_result)) {
-				sd_printk(KERN_NOTICE, sdkp, "Unit Not Ready\n");
-				sd_print_result(sdkp, the_result);
+				sd_print_result(sdkp, "Test Unit Ready failed",
+						the_result);
 			}
 			break;
 		}
-					
+
 		/*
 		 * The device does not want the automatic start to be issued.
 		 */
@@ -1954,7 +1947,6 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp,
 			struct scsi_sense_hdr *sshdr, int sense_valid,
 			int the_result)
 {
-	sd_print_result(sdkp, the_result);
 	if (driver_byte(the_result) & DRIVER_SENSE)
 		sd_print_sense_hdr(sdkp, sshdr);
 	else
@@ -2035,7 +2027,7 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
 	} while (the_result && retries);
 
 	if (the_result) {
-		sd_printk(KERN_NOTICE, sdkp, "READ CAPACITY(16) failed\n");
+		sd_print_result(sdkp, "Read Capacity(16) failed", the_result);
 		read_capacity_error(sdkp, sdp, &sshdr, sense_valid, the_result);
 		return -EINVAL;
 	}
@@ -2117,7 +2109,7 @@ static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp,
 	} while (the_result && retries);
 
 	if (the_result) {
-		sd_printk(KERN_NOTICE, sdkp, "READ CAPACITY failed\n");
+		sd_print_result(sdkp, "Read Capacity(10) failed", the_result);
 		read_capacity_error(sdkp, sdp, &sshdr, sense_valid, the_result);
 		return -EINVAL;
 	}
@@ -3141,8 +3133,7 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start)
 	res = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0, &sshdr,
 			       SD_TIMEOUT, SD_MAX_RETRIES, NULL, REQ_PM);
 	if (res) {
-		sd_printk(KERN_WARNING, sdkp, "START_STOP FAILED\n");
-		sd_print_result(sdkp, res);
+		sd_print_result(sdkp, "Start/Stop Unit failed", res);
 		if (driver_byte(res) & DRIVER_SENSE)
 			sd_print_sense_hdr(sdkp, &sshdr);
 		if (scsi_sense_valid(&sshdr) &&
@@ -3343,9 +3334,20 @@ static void sd_print_sense_hdr(struct scsi_disk *sdkp,
 			     sshdr->asc, sshdr->ascq);
 }
 
-static void sd_print_result(struct scsi_disk *sdkp, int result)
+static void sd_print_result(const struct scsi_disk *sdkp, const char *msg,
+			    int result)
 {
-	sd_printk(KERN_INFO, sdkp, " ");
-	scsi_show_result(result);
+	const char *hb_string = scsi_hostbyte_string(result);
+	const char *db_string = scsi_driverbyte_string(result);
+
+	if (hb_string || db_string)
+		sd_printk(KERN_INFO, sdkp,
+			  "%s: Result: hostbyte=%s driverbyte=%s\n", msg,
+			  hb_string ? hb_string : "invalid",
+			  db_string ? db_string : "invalid");
+	else
+		sd_printk(KERN_INFO, sdkp,
+			  "%s: Result: hostbyte=0x%02x driverbyte=0x%02x\n",
+			  msg, host_byte(result), driver_byte(result));
 }
 
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index eb3997ed8e7..9da319130da 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -4707,8 +4707,8 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 				     START_STOP_TIMEOUT, 0, NULL, REQ_PM);
 	if (ret) {
 		sdev_printk(KERN_WARNING, sdp,
-			  "START_STOP failed for power mode: %d\n", pwr_mode);
-		scsi_show_result(ret);
+			    "START_STOP failed for power mode: %d, result %x\n",
+			    pwr_mode, ret);
 		if (driver_byte(ret) & DRIVER_SENSE) {
 			scsi_show_sense_hdr(sdp, NULL, &sshdr);
 			scsi_show_extd_sense(sdp, NULL, sshdr.asc, sshdr.ascq);
diff --git a/include/scsi/scsi_dbg.h b/include/scsi/scsi_dbg.h
index 50f4d8542ec..f41a86bc1a8 100644
--- a/include/scsi/scsi_dbg.h
+++ b/include/scsi/scsi_dbg.h
@@ -17,7 +17,6 @@ extern void scsi_print_sense(const struct scsi_cmnd *);
 extern void __scsi_print_sense(const struct scsi_device *, const char *name,
 			       const unsigned char *sense_buffer,
 			       int sense_len);
-extern void scsi_show_result(int);
 extern void scsi_print_result(struct scsi_cmnd *);
 extern const char *scsi_hostbyte_string(int);
 extern const char *scsi_driverbyte_string(int);
-- 
cgit v1.2.3-70-g09d2


From c11c004b1c052fae77d3d0d14462d1f3a4e88d06 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Fri, 24 Oct 2014 14:27:01 +0200
Subject: scsi: simplify scsi_log_(send|completion)

Simplify scsi_log_(send|completion) by externalizing
scsi_mlreturn_string() and always print the command address.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/constants.c    | 41 ++++++++++++++++++++++++++++++++++++++---
 drivers/scsi/scsi.c         | 43 ++++++-------------------------------------
 drivers/scsi/scsi_lib.c     | 13 ++++++++++---
 drivers/scsi/scsi_logging.h |  1 +
 include/scsi/scsi_dbg.h     |  3 ++-
 5 files changed, 57 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index 2893464129b..0cf43f6e464 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -1440,19 +1440,54 @@ const char *scsi_driverbyte_string(int result)
 }
 EXPORT_SYMBOL(scsi_driverbyte_string);
 
-void scsi_print_result(struct scsi_cmnd *cmd)
+#ifdef CONFIG_SCSI_CONSTANTS
+#define scsi_mlreturn_name(result)	{ result, #result }
+static const struct value_name_pair scsi_mlreturn_arr[] = {
+	scsi_mlreturn_name(NEEDS_RETRY),
+	scsi_mlreturn_name(SUCCESS),
+	scsi_mlreturn_name(FAILED),
+	scsi_mlreturn_name(QUEUED),
+	scsi_mlreturn_name(SOFT_ERROR),
+	scsi_mlreturn_name(ADD_TO_MLQUEUE),
+	scsi_mlreturn_name(TIMEOUT_ERROR),
+	scsi_mlreturn_name(SCSI_RETURN_NOT_HANDLED),
+	scsi_mlreturn_name(FAST_IO_FAIL)
+};
+#endif
+
+const char *scsi_mlreturn_string(int result)
+{
+#ifdef CONFIG_SCSI_CONSTANTS
+	const struct value_name_pair *arr = scsi_mlreturn_arr;
+	int k;
+
+	for (k = 0; k < ARRAY_SIZE(scsi_mlreturn_arr); ++k, ++arr) {
+		if (result == arr->value)
+			return arr->name;
+	}
+#endif
+	return NULL;
+}
+EXPORT_SYMBOL(scsi_mlreturn_string);
+
+void scsi_print_result(struct scsi_cmnd *cmd, const char *msg, int disposition)
 {
+	const char *mlret_string = scsi_mlreturn_string(disposition);
 	const char *hb_string = scsi_hostbyte_string(cmd->result);
 	const char *db_string = scsi_driverbyte_string(cmd->result);
 
 	if (hb_string || db_string)
 		scmd_printk(KERN_INFO, cmd,
-			    "Result: hostbyte=%s driverbyte=%s",
+			    "%s%s Result: hostbyte=%s driverbyte=%s",
+			    msg ? msg : "",
+			    mlret_string ? mlret_string : "UNKNOWN",
 			    hb_string ? hb_string : "invalid",
 			    db_string ? db_string : "invalid");
 	else
 		scmd_printk(KERN_INFO, cmd,
-			    "Result: hostbyte=0x%02x driverbyte=0x%02x",
+			    "%s%s Result: hostbyte=0x%02x driverbyte=0x%02x",
+			    msg ? msg : "",
+			    mlret_string ? mlret_string : "UNKNOWN",
 			    host_byte(cmd->result), driver_byte(cmd->result));
 }
 EXPORT_SYMBOL(scsi_print_result);
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 32eaac03cf4..bc52bbd9738 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -527,9 +527,9 @@ void scsi_log_send(struct scsi_cmnd *cmd)
 	 *
 	 * 1: nothing (match completion)
 	 *
-	 * 2: log opcode + command of all commands
+	 * 2: log opcode + command of all commands + cmd address
 	 *
-	 * 3: same as 2 plus dump cmd address
+	 * 3: same as 2
 	 *
 	 * 4: same as 3 plus dump extra junk
 	 */
@@ -537,10 +537,8 @@ void scsi_log_send(struct scsi_cmnd *cmd)
 		level = SCSI_LOG_LEVEL(SCSI_LOG_MLQUEUE_SHIFT,
 				       SCSI_LOG_MLQUEUE_BITS);
 		if (level > 1) {
-			scmd_printk(KERN_INFO, cmd, "Send: ");
-			if (level > 2)
-				printk("0x%p ", cmd);
-			printk("\n");
+			scmd_printk(KERN_INFO, cmd,
+				    "Send: scmd 0x%p\n", cmd);
 			scsi_print_command(cmd);
 			if (level > 3) {
 				printk(KERN_INFO "buffer = 0x%p, bufflen = %d,"
@@ -565,7 +563,7 @@ void scsi_log_completion(struct scsi_cmnd *cmd, int disposition)
 	 *
 	 * 2: same as 1 but for all command completions.
 	 *
-	 * 3: same as 2 plus dump cmd address
+	 * 3: same as 2
 	 *
 	 * 4: same as 3 plus dump extra junk
 	 */
@@ -574,36 +572,7 @@ void scsi_log_completion(struct scsi_cmnd *cmd, int disposition)
 				       SCSI_LOG_MLCOMPLETE_BITS);
 		if (((level > 0) && (cmd->result || disposition != SUCCESS)) ||
 		    (level > 1)) {
-			scmd_printk(KERN_INFO, cmd, "Done: ");
-			if (level > 2)
-				printk("0x%p ", cmd);
-			/*
-			 * Dump truncated values, so we usually fit within
-			 * 80 chars.
-			 */
-			switch (disposition) {
-			case SUCCESS:
-				printk("SUCCESS\n");
-				break;
-			case NEEDS_RETRY:
-				printk("RETRY\n");
-				break;
-			case ADD_TO_MLQUEUE:
-				printk("MLQUEUE\n");
-				break;
-			case FAILED:
-				printk("FAILED\n");
-				break;
-			case TIMEOUT_ERROR:
-				/* 
-				 * If called via scsi_times_out.
-				 */
-				printk("TIMEOUT\n");
-				break;
-			default:
-				printk("UNKNOWN\n");
-			}
-			scsi_print_result(cmd);
+			scsi_print_result(cmd, "Done: ", disposition);
 			scsi_print_command(cmd);
 			if (status_byte(cmd->result) & CHECK_CONDITION)
 				scsi_print_sense(cmd);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 30f51c11a27..26a57faf885 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -832,7 +832,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	int error = 0;
 	struct scsi_sense_hdr sshdr;
 	bool sense_valid = false;
-	int sense_deferred = 0;
+	int sense_deferred = 0, level = 0;
 	enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY,
 	      ACTION_DELAYED_RETRY} action;
 	unsigned long wait_for = (cmd->allowed + 1) * req->timeout;
@@ -1038,8 +1038,15 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	switch (action) {
 	case ACTION_FAIL:
 		/* Give up and fail the remainder of the request */
-		if (!(req->cmd_flags & REQ_QUIET)) {
-			scsi_print_result(cmd);
+		if (unlikely(scsi_logging_level))
+			level = SCSI_LOG_LEVEL(SCSI_LOG_MLQUEUE_SHIFT,
+					       SCSI_LOG_MLQUEUE_BITS);
+		/*
+		 * if logging is enabled the failure will be printed
+		 * in scsi_log_completion(), so avoid duplicate messages
+		 */
+		if (!level && !(req->cmd_flags & REQ_QUIET)) {
+			scsi_print_result(cmd, NULL, FAILED);
 			if (driver_byte(result) & DRIVER_SENSE)
 				scsi_print_sense(cmd);
 			scsi_print_command(cmd);
diff --git a/drivers/scsi/scsi_logging.h b/drivers/scsi/scsi_logging.h
index 1f65139e14f..7fe64a84714 100644
--- a/drivers/scsi/scsi_logging.h
+++ b/drivers/scsi/scsi_logging.h
@@ -51,6 +51,7 @@ do {								\
 		} while (0);					\
 } while (0)
 #else
+#define SCSI_LOG_LEVEL(SHIFT, BITS) 0
 #define SCSI_CHECK_LOGGING(SHIFT, BITS, LEVEL, CMD)
 #endif /* CONFIG_SCSI_LOGGING */
 
diff --git a/include/scsi/scsi_dbg.h b/include/scsi/scsi_dbg.h
index f41a86bc1a8..7982795df59 100644
--- a/include/scsi/scsi_dbg.h
+++ b/include/scsi/scsi_dbg.h
@@ -17,9 +17,10 @@ extern void scsi_print_sense(const struct scsi_cmnd *);
 extern void __scsi_print_sense(const struct scsi_device *, const char *name,
 			       const unsigned char *sense_buffer,
 			       int sense_len);
-extern void scsi_print_result(struct scsi_cmnd *);
+extern void scsi_print_result(struct scsi_cmnd *, const char *, int);
 extern const char *scsi_hostbyte_string(int);
 extern const char *scsi_driverbyte_string(int);
+extern const char *scsi_mlreturn_string(int);
 extern const char *scsi_sense_key_string(unsigned char);
 extern const char *scsi_extd_sense_format(unsigned char, unsigned char,
 					  const char **);
-- 
cgit v1.2.3-70-g09d2


From 205fb5f5ba1d8edcf18009998ed05b80b7d186af Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Thu, 30 Oct 2014 14:45:11 +0100
Subject: blk-mq: add blk_mq_unique_tag()

The queuecommand() callback functions in SCSI low-level drivers
need to know which hardware context has been selected by the
block layer. Since this information is not available in the
request structure, and since passing the hctx pointer directly to
the queuecommand callback function would require modification of
all SCSI LLDs, add a function to the block layer that allows to
query the hardware context index.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 block/blk-mq-tag.c     | 28 ++++++++++++++++++++++++++++
 block/blk-mq.c         |  2 ++
 include/linux/blk-mq.h | 17 +++++++++++++++++
 3 files changed, 47 insertions(+)

(limited to 'include')

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 8317175a300..728b9a4d5f5 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -584,6 +584,34 @@ int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int tdepth)
 	return 0;
 }
 
+/**
+ * blk_mq_unique_tag() - return a tag that is unique queue-wide
+ * @rq: request for which to compute a unique tag
+ *
+ * The tag field in struct request is unique per hardware queue but not over
+ * all hardware queues. Hence this function that returns a tag with the
+ * hardware context index in the upper bits and the per hardware queue tag in
+ * the lower bits.
+ *
+ * Note: When called for a request that is queued on a non-multiqueue request
+ * queue, the hardware context index is set to zero.
+ */
+u32 blk_mq_unique_tag(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct blk_mq_hw_ctx *hctx;
+	int hwq = 0;
+
+	if (q->mq_ops) {
+		hctx = q->mq_ops->map_queue(q, rq->mq_ctx->cpu);
+		hwq = hctx->queue_num;
+	}
+
+	return (hwq << BLK_MQ_UNIQUE_TAG_BITS) |
+		(rq->tag & BLK_MQ_UNIQUE_TAG_MASK);
+}
+EXPORT_SYMBOL(blk_mq_unique_tag);
+
 ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page)
 {
 	char *orig_page = page;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 68929bad9a6..b5896d436fc 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2024,6 +2024,8 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
  */
 int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 {
+	BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS);
+
 	if (!set->nr_hw_queues)
 		return -EINVAL;
 	if (!set->queue_depth)
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index c9be1589415..15f7034aa37 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -167,6 +167,23 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		gfp_t gfp, bool reserved);
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
 
+enum {
+	BLK_MQ_UNIQUE_TAG_BITS = 16,
+	BLK_MQ_UNIQUE_TAG_MASK = (1 << BLK_MQ_UNIQUE_TAG_BITS) - 1,
+};
+
+u32 blk_mq_unique_tag(struct request *rq);
+
+static inline u16 blk_mq_unique_tag_to_hwq(u32 unique_tag)
+{
+	return unique_tag >> BLK_MQ_UNIQUE_TAG_BITS;
+}
+
+static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
+{
+	return unique_tag & BLK_MQ_UNIQUE_TAG_MASK;
+}
+
 struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
 struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int);
 
-- 
cgit v1.2.3-70-g09d2


From efec4b90f1a9b4c80827e4b8c0863334e13b0bf1 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Thu, 30 Oct 2014 14:45:36 +0100
Subject: scsi: add support for multiple hardware queues

Allow a SCSI LLD to declare how many hardware queues it supports
by setting Scsi_Host.nr_hw_queues before calling scsi_add_host().

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/scsi_lib.c  | 2 +-
 include/scsi/scsi_host.h | 8 ++++++++
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index fc0a8a0c0a3..38f8c85957b 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2106,7 +2106,7 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
 
 	memset(&shost->tag_set, 0, sizeof(shost->tag_set));
 	shost->tag_set.ops = &scsi_mq_ops;
-	shost->tag_set.nr_hw_queues = 1;
+	shost->tag_set.nr_hw_queues = shost->nr_hw_queues ? : 1;
 	shost->tag_set.queue_depth = shost->can_queue;
 	shost->tag_set.cmd_size = cmd_size;
 	shost->tag_set.numa_node = NUMA_NO_NODE;
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 5e362489ee8..bb9e27815be 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -638,6 +638,14 @@ struct Scsi_Host {
 	short unsigned int sg_prot_tablesize;
 	unsigned int max_sectors;
 	unsigned long dma_boundary;
+	/*
+	 * In scsi-mq mode, the number of hardware queues supported by the LLD.
+	 *
+	 * Note: it is assumed that each hardware queue has a queue depth of
+	 * can_queue. In other words, the total queue depth per host
+	 * is nr_hw_queues * can_queue.
+	 */
+	unsigned nr_hw_queues;
 	/* 
 	 * Used to assign serial numbers to the cmds.
 	 * Protected by the host lock.
-- 
cgit v1.2.3-70-g09d2


From 1ee8e889d946b3b1c2cc8b99e29eac47d1581dfd Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Thu, 30 Oct 2014 14:46:00 +0100
Subject: scsi: add support for multiple hardware queues in
 scsi_(host_)find_tag

Modify scsi_find_tag() and scsi_host_find_tag() such that these
functions can translate a tag generated by blk_mq_unique_tag().

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/scsi/scsi_tcq.h | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index 56ed843969c..7529c6acc23 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -111,18 +111,21 @@ static inline int scsi_populate_tag_msg(struct scsi_cmnd *cmd, char *msg)
 }
 
 static inline struct scsi_cmnd *scsi_mq_find_tag(struct Scsi_Host *shost,
-		unsigned int hw_ctx, int tag)
+						 int unique_tag)
 {
-	struct request *req;
+	u16 hwq = blk_mq_unique_tag_to_hwq(unique_tag);
+	struct request *req = NULL;
 
-	req = blk_mq_tag_to_rq(shost->tag_set.tags[hw_ctx], tag);
+	if (hwq < shost->tag_set.nr_hw_queues)
+		req = blk_mq_tag_to_rq(shost->tag_set.tags[hwq],
+				       blk_mq_unique_tag_to_tag(unique_tag));
 	return req ? (struct scsi_cmnd *)req->special : NULL;
 }
 
 /**
  * scsi_find_tag - find a tagged command by device
  * @SDpnt:	pointer to the ScSI device
- * @tag:	the tag number
+ * @tag:	tag generated by blk_mq_unique_tag()
  *
  * Notes:
  *	Only works with tags allocated by the generic blk layer.
@@ -133,9 +136,9 @@ static inline struct scsi_cmnd *scsi_find_tag(struct scsi_device *sdev, int tag)
 
         if (tag != SCSI_NO_TAG) {
 		if (shost_use_blk_mq(sdev->host))
-			return scsi_mq_find_tag(sdev->host, 0, tag);
+			return scsi_mq_find_tag(sdev->host, tag);
 
-        	req = blk_queue_find_tag(sdev->request_queue, tag);
+		req = blk_queue_find_tag(sdev->request_queue, tag);
 	        return req ? (struct scsi_cmnd *)req->special : NULL;
 	}
 
@@ -174,7 +177,7 @@ static inline int scsi_init_shared_tag_map(struct Scsi_Host *shost, int depth)
 /**
  * scsi_host_find_tag - find the tagged command by host
  * @shost:	pointer to scsi_host
- * @tag:	tag of the scsi_cmnd
+ * @tag:	tag generated by blk_mq_unique_tag()
  *
  * Notes:
  *	Only works with tags allocated by the generic blk layer.
@@ -186,7 +189,7 @@ static inline struct scsi_cmnd *scsi_host_find_tag(struct Scsi_Host *shost,
 
 	if (tag != SCSI_NO_TAG) {
 		if (shost_use_blk_mq(shost))
-			return scsi_mq_find_tag(shost, 0, tag);
+			return scsi_mq_find_tag(shost, tag);
 		req = blk_map_queue_find_tag(shost->bqt, tag);
 		return req ? (struct scsi_cmnd *)req->special : NULL;
 	}
-- 
cgit v1.2.3-70-g09d2


From 176aa9d6ee2db582e7e856dbe1983004a82869b4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 11 Oct 2014 12:06:47 +0200
Subject: scsi: refactor scsi_reset_provider handling

Pull the common code from the two callers into the function,
and rename it to scsi_ioctl_reset.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/scsi/scsi_error.c | 76 ++++++++++++++++++++++-------------------------
 drivers/scsi/scsi_ioctl.c | 33 +-------------------
 drivers/scsi/sg.c         | 34 ++-------------------
 include/scsi/scsi_eh.h    | 15 +---------
 4 files changed, 41 insertions(+), 117 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 95c9abb6418..a6f6b9222b5 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -36,6 +36,7 @@
 #include <scsi/scsi_transport.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_ioctl.h>
+#include <scsi/sg.h>
 
 #include "scsi_priv.h"
 #include "scsi_logging.h"
@@ -2311,39 +2312,36 @@ scsi_reset_provider_done_command(struct scsi_cmnd *scmd)
 {
 }
 
-/*
- * Function:	scsi_reset_provider
- *
- * Purpose:	Send requested reset to a bus or device at any phase.
- *
- * Arguments:	device	- device to send reset to
- *		flag - reset type (see scsi.h)
- *
- * Returns:	SUCCESS/FAILURE.
- *
- * Notes:	This is used by the SCSI Generic driver to provide
- *		Bus/Device reset capability.
+/**
+ * scsi_ioctl_reset: explicitly reset a host/bus/target/device
+ * @dev:	scsi_device to operate on
+ * @arg:	reset type (see sg.h)
  */
 int
-scsi_reset_provider(struct scsi_device *dev, int flag)
+scsi_ioctl_reset(struct scsi_device *dev, int __user *arg)
 {
 	struct scsi_cmnd *scmd;
 	struct Scsi_Host *shost = dev->host;
 	struct request req;
 	unsigned long flags;
-	int rtn;
+	int error = 0, rtn, val;
+
+	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
+		return -EACCES;
+
+	error = get_user(val, arg);
+	if (error)
+		return error;
 
 	if (scsi_autopm_get_host(shost) < 0)
-		return FAILED;
+		return -EIO;
 
-	if (!get_device(&dev->sdev_gendev)) {
-		rtn = FAILED;
+	error = -EIO;
+	if (!get_device(&dev->sdev_gendev))
 		goto out_put_autopm_host;
-	}
 
 	scmd = scsi_get_command(dev, GFP_KERNEL);
 	if (!scmd) {
-		rtn = FAILED;
 		put_device(&dev->sdev_gendev);
 		goto out_put_autopm_host;
 	}
@@ -2364,39 +2362,37 @@ scsi_reset_provider(struct scsi_device *dev, int flag)
 	shost->tmf_in_progress = 1;
 	spin_unlock_irqrestore(shost->host_lock, flags);
 
-	switch (flag) {
-	case SCSI_TRY_RESET_DEVICE:
+	switch (val & ~SG_SCSI_RESET_NO_ESCALATE) {
+	case SG_SCSI_RESET_NOTHING:
+		rtn = SUCCESS;
+		break;
+	case SG_SCSI_RESET_DEVICE:
 		rtn = scsi_try_bus_device_reset(scmd);
-		if (rtn == SUCCESS)
+		if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE))
 			break;
 		/* FALLTHROUGH */
-	case SCSI_TRY_RESET_TARGET:
+	case SG_SCSI_RESET_TARGET:
 		rtn = scsi_try_target_reset(scmd);
-		if (rtn == SUCCESS)
+		if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE))
 			break;
 		/* FALLTHROUGH */
-	case SCSI_TRY_RESET_BUS:
+	case SG_SCSI_RESET_BUS:
 		rtn = scsi_try_bus_reset(scmd);
-		if (rtn == SUCCESS)
+		if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE))
 			break;
 		/* FALLTHROUGH */
-	case SCSI_TRY_RESET_HOST:
-	case SCSI_TRY_RESET_HOST | SCSI_TRY_RESET_NO_ESCALATE:
+	case SG_SCSI_RESET_HOST:
 		rtn = scsi_try_host_reset(scmd);
-		break;
-	case SCSI_TRY_RESET_DEVICE | SCSI_TRY_RESET_NO_ESCALATE:
-		rtn = scsi_try_bus_device_reset(scmd);
-		break;
-	case SCSI_TRY_RESET_TARGET | SCSI_TRY_RESET_NO_ESCALATE:
-		rtn = scsi_try_target_reset(scmd);
-		break;
-	case SCSI_TRY_RESET_BUS | SCSI_TRY_RESET_NO_ESCALATE:
-		rtn = scsi_try_bus_reset(scmd);
-		break;
+		if (rtn == SUCCESS)
+			break;
 	default:
+		/* FALLTHROUGH */
 		rtn = FAILED;
+		break;
 	}
 
+	error = (rtn == SUCCESS) ? 0 : -EIO;
+
 	spin_lock_irqsave(shost->host_lock, flags);
 	shost->tmf_in_progress = 0;
 	spin_unlock_irqrestore(shost->host_lock, flags);
@@ -2416,9 +2412,9 @@ scsi_reset_provider(struct scsi_device *dev, int flag)
 	scsi_next_command(scmd);
 out_put_autopm_host:
 	scsi_autopm_put_host(shost);
-	return rtn;
+	return error;
 }
-EXPORT_SYMBOL(scsi_reset_provider);
+EXPORT_SYMBOL(scsi_ioctl_reset);
 
 /**
  * scsi_normalize_sense - normalize main elements from either fixed or
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 5207274574f..5ddc08f3998 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -292,8 +292,6 @@ EXPORT_SYMBOL(scsi_ioctl);
 int scsi_nonblockable_ioctl(struct scsi_device *sdev, int cmd,
 			    void __user *arg, int ndelay)
 {
-	int val, val2, result;
-
 	/* The first set of iocts may be executed even if we're doing
 	 * error processing, as long as the device was opened
 	 * non-blocking */
@@ -305,36 +303,7 @@ int scsi_nonblockable_ioctl(struct scsi_device *sdev, int cmd,
 
 	switch (cmd) {
 	case SG_SCSI_RESET:
-		result = get_user(val, (int __user *)arg);
-		if (result)
-			return result;
-		if (val & SG_SCSI_RESET_NO_ESCALATE) {
-			val &= ~SG_SCSI_RESET_NO_ESCALATE;
-			val2 = SCSI_TRY_RESET_NO_ESCALATE;
-		} else
-			val2 = 0;
-		if (val == SG_SCSI_RESET_NOTHING)
-			return 0;
-		switch (val) {
-		case SG_SCSI_RESET_DEVICE:
-			val2 |= SCSI_TRY_RESET_DEVICE;
-			break;
-		case SG_SCSI_RESET_TARGET:
-			val2 |= SCSI_TRY_RESET_TARGET;
-			break;
-		case SG_SCSI_RESET_BUS:
-			val2 |= SCSI_TRY_RESET_BUS;
-			break;
-		case SG_SCSI_RESET_HOST:
-			val2 |= SCSI_TRY_RESET_HOST;
-			break;
-		default:
-			return -EINVAL;
-		}
-		if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
-			return -EACCES;
-		return (scsi_reset_provider(sdev, val2) ==
-			SUCCESS) ? 0 : -EIO;
+		return scsi_ioctl_reset(sdev, arg);
 	}
 	return -ENODEV;
 }
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 2fe2701d86d..7c55cacceb7 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -847,7 +847,7 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 {
 	void __user *p = (void __user *)arg;
 	int __user *ip = p;
-	int result, val, val2, read_only;
+	int result, val, read_only;
 	Sg_device *sdp;
 	Sg_fd *sfp;
 	Sg_request *srp;
@@ -1079,36 +1079,8 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 				return -EBUSY;
 		} else if (!scsi_block_when_processing_errors(sdp->device))
 			return -EBUSY;
-		result = get_user(val, ip);
-		if (result)
-			return result;
-		if (val & SG_SCSI_RESET_NO_ESCALATE) {
-			val &= ~SG_SCSI_RESET_NO_ESCALATE;
-			val2 = SCSI_TRY_RESET_NO_ESCALATE;
-		} else
-			val2 = 0;
-		if (SG_SCSI_RESET_NOTHING == val)
-			return 0;
-		switch (val) {
-		case SG_SCSI_RESET_DEVICE:
-			val2 |= SCSI_TRY_RESET_DEVICE;
-			break;
-		case SG_SCSI_RESET_TARGET:
-			val2 |= SCSI_TRY_RESET_TARGET;
-			break;
-		case SG_SCSI_RESET_BUS:
-			val2 |= SCSI_TRY_RESET_BUS;
-			break;
-		case SG_SCSI_RESET_HOST:
-			val2 |= SCSI_TRY_RESET_HOST;
-			break;
-		default:
-			return -EINVAL;
-		}
-		if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
-			return -EACCES;
-		return (scsi_reset_provider(sdp->device, val2) ==
-			SUCCESS) ? 0 : -EIO;
+
+		return scsi_ioctl_reset(sdp->device, ip);
 	case SCSI_IOCTL_SEND_COMMAND:
 		if (atomic_read(&sdp->detaching))
 			return -ENODEV;
diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h
index 25624814132..1e1421b0656 100644
--- a/include/scsi/scsi_eh.h
+++ b/include/scsi/scsi_eh.h
@@ -60,20 +60,7 @@ extern int scsi_get_sense_info_fld(const u8 * sense_buffer, int sb_len,
 
 extern void scsi_build_sense_buffer(int desc, u8 *buf, u8 key, u8 asc, u8 ascq);
 
-/*
- * Reset request from external source
- * Note: if SCSI_TRY_RESET_DEVICE fails then it will escalate to
- * SCSI_TRY_RESET_TARGET which if it fails will escalate to
- * SCSI_TRY_RESET_BUS which if it fails will escalate to SCSI_TRY_RESET_HOST.
- * To prevent escalation OR with SCSI_TRY_RESET_NO_ESCALATE.
- */
-#define SCSI_TRY_RESET_DEVICE	1
-#define SCSI_TRY_RESET_BUS	2
-#define SCSI_TRY_RESET_HOST	3
-#define SCSI_TRY_RESET_TARGET	4
-#define SCSI_TRY_RESET_NO_ESCALATE	0x100	/* OR-ed to prior defines */
-
-extern int scsi_reset_provider(struct scsi_device *, int);
+extern int scsi_ioctl_reset(struct scsi_device *, int __user *);
 
 struct scsi_eh_save {
 	/* saved state */
-- 
cgit v1.2.3-70-g09d2


From 906d15fbd23c1267addab361063c1c8119992215 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 11 Oct 2014 16:25:31 +0200
Subject: scsi: split scsi_nonblockable_ioctl

The calling conventions for this function are bad as it could return
-ENODEV both for a device not currently online and a not recognized ioctl.

Add a new scsi_ioctl_block_when_processing_errors function that wraps
scsi_block_when_processing_errors with the a special case for the
SG_SCSI_RESET ioctl command, and handle the SG_SCSI_RESET case itself
in scsi_ioctl.  All callers of scsi_ioctl now must call the above helper
to check for the EH state, so that the ioctl handler itself doesn't
have to.

Reported-by: Robert Elliott <Elliott@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/scsi/ch.c         |  5 +++++
 drivers/scsi/osst.c       |  6 +++---
 drivers/scsi/scsi_ioctl.c | 47 +++++++++++++----------------------------------
 drivers/scsi/sd.c         |  6 +++---
 drivers/scsi/sg.c         | 33 +++++++++++++++------------------
 drivers/scsi/sr.c         | 15 +++++----------
 drivers/scsi/st.c         |  7 +++----
 include/scsi/scsi_ioctl.h |  4 ++--
 8 files changed, 49 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index 226ef771eff..4f502f95f3b 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -616,6 +616,11 @@ static long ch_ioctl(struct file *file,
 	int retval;
 	void __user *argp = (void __user *)arg;
 
+	retval = scsi_ioctl_block_when_processing_errors(ch->device, cmd,
+			file->f_flags & O_NDELAY);
+	if (retval)
+		return retval;
+
 	switch (cmd) {
 	case CHIOGPARAMS:
 	{
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index 3d0d13c4da1..b6d63d63669 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -4969,10 +4969,10 @@ static long osst_ioctl(struct file * file,
 	 * may try and take the device offline, in which case all further
 	 * access to the device is prohibited.
 	 */
-	if( !scsi_block_when_processing_errors(STp->device) ) {
-		retval = (-ENXIO);
+	retval = scsi_ioctl_block_when_processing_errors(STp->device, cmd_in,
+			file->f_flags & O_NDELAY);
+	if (retval)
 		goto out;
-	}
 
 	cmd_type = _IOC_TYPE(cmd_in);
 	cmd_nr   = _IOC_NR(cmd_in);
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 5ddc08f3998..712f159ebb6 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -200,19 +200,6 @@ int scsi_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 {
 	char scsi_cmd[MAX_COMMAND_SIZE];
 
-	/* No idea how this happens.... */
-	if (!sdev)
-		return -ENXIO;
-
-	/*
-	 * If we are in the middle of error recovery, don't let anyone
-	 * else try and use this device.  Also, if error recovery fails, it
-	 * may try and take the device offline, in which case all further
-	 * access to the device is prohibited.
-	 */
-	if (!scsi_block_when_processing_errors(sdev))
-		return -ENODEV;
-
 	/* Check for deprecated ioctls ... all the ioctls which don't
 	 * follow the new unique numbering scheme are deprecated */
 	switch (cmd) {
@@ -273,6 +260,8 @@ int scsi_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 				     START_STOP_TIMEOUT, NORMAL_RETRIES);
         case SCSI_IOCTL_GET_PCI:
                 return scsi_ioctl_get_pci(sdev, arg);
+	case SG_SCSI_RESET:
+		return scsi_ioctl_reset(sdev, arg);
 	default:
 		if (sdev->host->hostt->ioctl)
 			return sdev->host->hostt->ioctl(sdev, cmd, arg);
@@ -281,30 +270,20 @@ int scsi_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 }
 EXPORT_SYMBOL(scsi_ioctl);
 
-/**
- * scsi_nonblockable_ioctl() - Handle SG_SCSI_RESET
- * @sdev: scsi device receiving ioctl
- * @cmd: Must be SC_SCSI_RESET
- * @arg: pointer to int containing SG_SCSI_RESET_{DEVICE,TARGET,BUS,HOST}
- *       possibly OR-ed with SG_SCSI_RESET_NO_ESCALATE
- * @ndelay: file mode O_NDELAY flag
+/*
+ * We can process a reset even when a device isn't fully operable.
  */
-int scsi_nonblockable_ioctl(struct scsi_device *sdev, int cmd,
-			    void __user *arg, int ndelay)
+int scsi_ioctl_block_when_processing_errors(struct scsi_device *sdev, int cmd,
+		bool ndelay)
 {
-	/* The first set of iocts may be executed even if we're doing
-	 * error processing, as long as the device was opened
-	 * non-blocking */
-	if (ndelay) {
+	if (cmd == SG_SCSI_RESET && ndelay) {
 		if (scsi_host_in_recovery(sdev->host))
 			return -ENODEV;
-	} else if (!scsi_block_when_processing_errors(sdev))
-		return -ENODEV;
-
-	switch (cmd) {
-	case SG_SCSI_RESET:
-		return scsi_ioctl_reset(sdev, arg);
+	} else {
+		if (!scsi_block_when_processing_errors(sdev))
+			return -ENODEV;
 	}
-	return -ENODEV;
+
+	return 0;
 }
-EXPORT_SYMBOL(scsi_nonblockable_ioctl);
+EXPORT_SYMBOL_GPL(scsi_ioctl_block_when_processing_errors);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 242f9b17728..ddf763ad3b8 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1334,9 +1334,9 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode,
 	 * may try and take the device offline, in which case all further
 	 * access to the device is prohibited.
 	 */
-	error = scsi_nonblockable_ioctl(sdp, cmd, p,
-					(mode & FMODE_NDELAY) != 0);
-	if (!scsi_block_when_processing_errors(sdp) || !error)
+	error = scsi_ioctl_block_when_processing_errors(sdp, cmd,
+			(mode & FMODE_NDELAY) != 0);
+	if (error)
 		goto out;
 
 	/*
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 7c55cacceb7..b14f64cb972 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1071,16 +1071,6 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 		if (atomic_read(&sdp->detaching))
 			return -ENODEV;
 		return put_user(sdp->device->host->hostt->emulated, ip);
-	case SG_SCSI_RESET:
-		if (atomic_read(&sdp->detaching))
-			return -ENODEV;
-		if (filp->f_flags & O_NONBLOCK) {
-			if (scsi_host_in_recovery(sdp->device->host))
-				return -EBUSY;
-		} else if (!scsi_block_when_processing_errors(sdp->device))
-			return -EBUSY;
-
-		return scsi_ioctl_reset(sdp->device, ip);
 	case SCSI_IOCTL_SEND_COMMAND:
 		if (atomic_read(&sdp->detaching))
 			return -ENODEV;
@@ -1100,13 +1090,6 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 			return result;
 		sdp->sgdebug = (char) val;
 		return 0;
-	case SCSI_IOCTL_GET_IDLUN:
-	case SCSI_IOCTL_GET_BUS_NUMBER:
-	case SCSI_IOCTL_PROBE_HOST:
-	case SG_GET_TRANSFORM:
-		if (atomic_read(&sdp->detaching))
-			return -ENODEV;
-		return scsi_ioctl(sdp->device, cmd_in, p);
 	case BLKSECTGET:
 		return put_user(max_sectors_bytes(sdp->device->request_queue),
 				ip);
@@ -1122,11 +1105,25 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 		return blk_trace_startstop(sdp->device->request_queue, 0);
 	case BLKTRACETEARDOWN:
 		return blk_trace_remove(sdp->device->request_queue);
+	case SCSI_IOCTL_GET_IDLUN:
+	case SCSI_IOCTL_GET_BUS_NUMBER:
+	case SCSI_IOCTL_PROBE_HOST:
+	case SG_GET_TRANSFORM:
+	case SG_SCSI_RESET:
+		if (atomic_read(&sdp->detaching))
+			return -ENODEV;
+		break;
 	default:
 		if (read_only)
 			return -EPERM;	/* don't know so take safe approach */
-		return scsi_ioctl(sdp->device, cmd_in, p);
+		break;
 	}
+
+	result = scsi_ioctl_block_when_processing_errors(sdp->device,
+			cmd_in, filp->f_flags & O_NDELAY);
+	if (result)
+		return result;
+	return scsi_ioctl(sdp->device, cmd_in, p);
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 2de44cc58b1..3d5399e341a 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -549,6 +549,11 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 
 	mutex_lock(&sr_mutex);
 
+	ret = scsi_ioctl_block_when_processing_errors(sdev, cmd,
+			(mode & FMODE_NDELAY) != 0);
+	if (ret)
+		goto out;
+
 	/*
 	 * Send SCSI addressing ioctls directly to mid level, send other
 	 * ioctls to cdrom/block level.
@@ -564,16 +569,6 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	if (ret != -ENOSYS)
 		goto out;
 
-	/*
-	 * ENODEV means that we didn't recognise the ioctl, or that we
-	 * cannot execute it in the current device state.  In either
-	 * case fall through to scsi_ioctl, which will return ENDOEV again
-	 * if it doesn't recognise the ioctl
-	 */
-	ret = scsi_nonblockable_ioctl(sdev, cmd, argp,
-					(mode & FMODE_NDELAY) != 0);
-	if (ret != -ENODEV)
-		goto out;
 	ret = scsi_ioctl(sdev, cmd, argp);
 
 out:
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 63c35ed3c88..7d2e036c75c 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -3376,11 +3376,10 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 	 * may try and take the device offline, in which case all further
 	 * access to the device is prohibited.
 	 */
-	retval = scsi_nonblockable_ioctl(STp->device, cmd_in, p,
-					file->f_flags & O_NDELAY);
-	if (!scsi_block_when_processing_errors(STp->device) || retval != -ENODEV)
+	retval = scsi_ioctl_block_when_processing_errors(STp->device, cmd_in,
+			file->f_flags & O_NDELAY);
+	if (retval)
 		goto out;
-	retval = 0;
 
 	cmd_type = _IOC_TYPE(cmd_in);
 	cmd_nr = _IOC_NR(cmd_in);
diff --git a/include/scsi/scsi_ioctl.h b/include/scsi/scsi_ioctl.h
index b9006848b81..8d19d1d233c 100644
--- a/include/scsi/scsi_ioctl.h
+++ b/include/scsi/scsi_ioctl.h
@@ -40,9 +40,9 @@ typedef struct scsi_fctargaddress {
 	unsigned char host_wwn[8]; // include NULL term.
 } Scsi_FCTargAddress;
 
+int scsi_ioctl_block_when_processing_errors(struct scsi_device *sdev,
+		int cmd, bool ndelay);
 extern int scsi_ioctl(struct scsi_device *, int, void __user *);
-extern int scsi_nonblockable_ioctl(struct scsi_device *sdev, int cmd,
-				   void __user *arg, int ndelay);
 
 #endif /* __KERNEL__ */
 #endif /* _SCSI_IOCTL_H */
-- 
cgit v1.2.3-70-g09d2


From cd37743fc978a14fee75a4e662582e15d16038a3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 13 Sep 2014 19:59:51 -0700
Subject: scsi: use container_of to get at device handler private data

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/scsi/device_handler/scsi_dh_alua.c  | 25 +++++++++----------------
 drivers/scsi/device_handler/scsi_dh_emc.c   | 24 ++++++++++--------------
 drivers/scsi/device_handler/scsi_dh_hp_sw.c | 23 +++++++++--------------
 drivers/scsi/device_handler/scsi_dh_rdac.c  | 25 +++++++++----------------
 include/scsi/scsi_device.h                  |  1 -
 5 files changed, 37 insertions(+), 61 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 9115c31f26e..d9781045c4e 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -62,6 +62,7 @@
 #define ALUA_OPTIMIZE_STPG		1
 
 struct alua_dh_data {
+	struct scsi_dh_data	dh_data;
 	int			group_id;
 	int			rel_port;
 	int			tpgs;
@@ -87,9 +88,7 @@ static int alua_check_sense(struct scsi_device *, struct scsi_sense_hdr *);
 
 static inline struct alua_dh_data *get_alua_data(struct scsi_device *sdev)
 {
-	struct scsi_dh_data *scsi_dh_data = sdev->scsi_dh_data;
-	BUG_ON(scsi_dh_data == NULL);
-	return ((struct alua_dh_data *) scsi_dh_data->buf);
+	return container_of(sdev->scsi_dh_data, struct alua_dh_data, dh_data);
 }
 
 static int realloc_buffer(struct alua_dh_data *h, unsigned len)
@@ -846,21 +845,18 @@ static struct scsi_device_handler alua_dh = {
  */
 static int alua_bus_attach(struct scsi_device *sdev)
 {
-	struct scsi_dh_data *scsi_dh_data;
 	struct alua_dh_data *h;
 	unsigned long flags;
 	int err = SCSI_DH_OK;
 
-	scsi_dh_data = kzalloc(sizeof(*scsi_dh_data)
-			       + sizeof(*h) , GFP_KERNEL);
-	if (!scsi_dh_data) {
+	h = kzalloc(sizeof(*h) , GFP_KERNEL);
+	if (!h) {
 		sdev_printk(KERN_ERR, sdev, "%s: Attach failed\n",
 			    ALUA_DH_NAME);
 		return -ENOMEM;
 	}
 
-	scsi_dh_data->scsi_dh = &alua_dh;
-	h = (struct alua_dh_data *) scsi_dh_data->buf;
+	h->dh_data.scsi_dh = &alua_dh;
 	h->tpgs = TPGS_MODE_UNINITIALIZED;
 	h->state = TPGS_STATE_OPTIMIZED;
 	h->group_id = -1;
@@ -874,14 +870,14 @@ static int alua_bus_attach(struct scsi_device *sdev)
 		goto failed;
 
 	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	sdev->scsi_dh_data = scsi_dh_data;
+	sdev->scsi_dh_data = &h->dh_data;
 	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
 	sdev_printk(KERN_NOTICE, sdev, "%s: Attached\n", ALUA_DH_NAME);
 
 	return 0;
 
 failed:
-	kfree(scsi_dh_data);
+	kfree(h);
 	sdev_printk(KERN_ERR, sdev, "%s: not attached\n", ALUA_DH_NAME);
 	return -EINVAL;
 }
@@ -892,19 +888,16 @@ failed:
  */
 static void alua_bus_detach(struct scsi_device *sdev)
 {
-	struct scsi_dh_data *scsi_dh_data;
-	struct alua_dh_data *h;
+	struct alua_dh_data *h = get_alua_data(sdev);
 	unsigned long flags;
 
 	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	scsi_dh_data = sdev->scsi_dh_data;
 	sdev->scsi_dh_data = NULL;
 	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
 
-	h = (struct alua_dh_data *) scsi_dh_data->buf;
 	if (h->buff && h->inq != h->buff)
 		kfree(h->buff);
-	kfree(scsi_dh_data);
+	kfree(h);
 	sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n", ALUA_DH_NAME);
 }
 
diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c
index 153b4c3547a..c2e26cdef21 100644
--- a/drivers/scsi/device_handler/scsi_dh_emc.c
+++ b/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -72,6 +72,7 @@ static const char * lun_state[] =
 };
 
 struct clariion_dh_data {
+	struct scsi_dh_data dh_data;
 	/*
 	 * Flags:
 	 *  CLARIION_SHORT_TRESPASS
@@ -116,9 +117,8 @@ struct clariion_dh_data {
 static inline struct clariion_dh_data
 			*get_clariion_data(struct scsi_device *sdev)
 {
-	struct scsi_dh_data *scsi_dh_data = sdev->scsi_dh_data;
-	BUG_ON(scsi_dh_data == NULL);
-	return ((struct clariion_dh_data *) scsi_dh_data->buf);
+	return container_of(sdev->scsi_dh_data, struct clariion_dh_data,
+			dh_data);
 }
 
 /*
@@ -665,21 +665,18 @@ static struct scsi_device_handler clariion_dh = {
 
 static int clariion_bus_attach(struct scsi_device *sdev)
 {
-	struct scsi_dh_data *scsi_dh_data;
 	struct clariion_dh_data *h;
 	unsigned long flags;
 	int err;
 
-	scsi_dh_data = kzalloc(sizeof(*scsi_dh_data)
-			       + sizeof(*h) , GFP_KERNEL);
-	if (!scsi_dh_data) {
+	h = kzalloc(sizeof(*h) , GFP_KERNEL);
+	if (!h) {
 		sdev_printk(KERN_ERR, sdev, "%s: Attach failed\n",
 			    CLARIION_NAME);
 		return -ENOMEM;
 	}
 
-	scsi_dh_data->scsi_dh = &clariion_dh;
-	h = (struct clariion_dh_data *) scsi_dh_data->buf;
+	h->dh_data.scsi_dh = &clariion_dh;
 	h->lun_state = CLARIION_LUN_UNINITIALIZED;
 	h->default_sp = CLARIION_UNBOUND_LU;
 	h->current_sp = CLARIION_UNBOUND_LU;
@@ -693,7 +690,7 @@ static int clariion_bus_attach(struct scsi_device *sdev)
 		goto failed;
 
 	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	sdev->scsi_dh_data = scsi_dh_data;
+	sdev->scsi_dh_data = &h->dh_data;
 	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
 
 	sdev_printk(KERN_INFO, sdev,
@@ -705,7 +702,7 @@ static int clariion_bus_attach(struct scsi_device *sdev)
 	return 0;
 
 failed:
-	kfree(scsi_dh_data);
+	kfree(h);
 	sdev_printk(KERN_ERR, sdev, "%s: not attached\n",
 		    CLARIION_NAME);
 	return -EINVAL;
@@ -713,18 +710,17 @@ failed:
 
 static void clariion_bus_detach(struct scsi_device *sdev)
 {
-	struct scsi_dh_data *scsi_dh_data;
+	struct clariion_dh_data *h = get_clariion_data(sdev);
 	unsigned long flags;
 
 	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	scsi_dh_data = sdev->scsi_dh_data;
 	sdev->scsi_dh_data = NULL;
 	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
 
 	sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n",
 		    CLARIION_NAME);
 
-	kfree(scsi_dh_data);
+	kfree(h);
 }
 
 static int __init clariion_init(void)
diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
index cf36557a1d4..37dedcae0aa 100644
--- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c
+++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
@@ -38,6 +38,7 @@
 #define HP_SW_PATH_PASSIVE		1
 
 struct hp_sw_dh_data {
+	struct scsi_dh_data dh_data;
 	unsigned char sense[SCSI_SENSE_BUFFERSIZE];
 	int path_state;
 	int retries;
@@ -51,9 +52,7 @@ static int hp_sw_start_stop(struct hp_sw_dh_data *);
 
 static inline struct hp_sw_dh_data *get_hp_sw_data(struct scsi_device *sdev)
 {
-	struct scsi_dh_data *scsi_dh_data = sdev->scsi_dh_data;
-	BUG_ON(scsi_dh_data == NULL);
-	return ((struct hp_sw_dh_data *) scsi_dh_data->buf);
+	return container_of(sdev->scsi_dh_data, struct hp_sw_dh_data, dh_data);
 }
 
 /*
@@ -354,21 +353,18 @@ static struct scsi_device_handler hp_sw_dh = {
 
 static int hp_sw_bus_attach(struct scsi_device *sdev)
 {
-	struct scsi_dh_data *scsi_dh_data;
 	struct hp_sw_dh_data *h;
 	unsigned long flags;
 	int ret;
 
-	scsi_dh_data = kzalloc(sizeof(*scsi_dh_data)
-			       + sizeof(*h) , GFP_KERNEL);
-	if (!scsi_dh_data) {
+	h = kzalloc(sizeof(*h), GFP_KERNEL);
+	if (!h) {
 		sdev_printk(KERN_ERR, sdev, "%s: Attach Failed\n",
 			    HP_SW_NAME);
 		return -ENOMEM;
 	}
 
-	scsi_dh_data->scsi_dh = &hp_sw_dh;
-	h = (struct hp_sw_dh_data *) scsi_dh_data->buf;
+	h->dh_data.scsi_dh = &hp_sw_dh;
 	h->path_state = HP_SW_PATH_UNINITIALIZED;
 	h->retries = HP_SW_RETRIES;
 	h->sdev = sdev;
@@ -378,7 +374,7 @@ static int hp_sw_bus_attach(struct scsi_device *sdev)
 		goto failed;
 
 	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	sdev->scsi_dh_data = scsi_dh_data;
+	sdev->scsi_dh_data = &h->dh_data;
 	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
 
 	sdev_printk(KERN_INFO, sdev, "%s: attached to %s path\n",
@@ -388,7 +384,7 @@ static int hp_sw_bus_attach(struct scsi_device *sdev)
 	return 0;
 
 failed:
-	kfree(scsi_dh_data);
+	kfree(h);
 	sdev_printk(KERN_ERR, sdev, "%s: not attached\n",
 		    HP_SW_NAME);
 	return -EINVAL;
@@ -396,17 +392,16 @@ failed:
 
 static void hp_sw_bus_detach( struct scsi_device *sdev )
 {
-	struct scsi_dh_data *scsi_dh_data;
+	struct hp_sw_dh_data *h = get_hp_sw_data(sdev);
 	unsigned long flags;
 
 	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	scsi_dh_data = sdev->scsi_dh_data;
 	sdev->scsi_dh_data = NULL;
 	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
 
 	sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n", HP_SW_NAME);
 
-	kfree(scsi_dh_data);
+	kfree(h);
 }
 
 static int __init hp_sw_init(void)
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index b850954c4e2..ef8caaaad76 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -181,6 +181,7 @@ struct c2_inquiry {
 };
 
 struct rdac_dh_data {
+	struct scsi_dh_data	dh_data;
 	struct rdac_controller	*ctlr;
 #define UNINITIALIZED_LUN	(1 << 8)
 	unsigned		lun;
@@ -261,9 +262,7 @@ do { \
 
 static inline struct rdac_dh_data *get_rdac_data(struct scsi_device *sdev)
 {
-	struct scsi_dh_data *scsi_dh_data = sdev->scsi_dh_data;
-	BUG_ON(scsi_dh_data == NULL);
-	return ((struct rdac_dh_data *) scsi_dh_data->buf);
+	return container_of(sdev->scsi_dh_data, struct rdac_dh_data, dh_data);
 }
 
 static struct request *get_rdac_req(struct scsi_device *sdev,
@@ -842,23 +841,20 @@ static struct scsi_device_handler rdac_dh = {
 
 static int rdac_bus_attach(struct scsi_device *sdev)
 {
-	struct scsi_dh_data *scsi_dh_data;
 	struct rdac_dh_data *h;
 	unsigned long flags;
 	int err;
 	char array_name[ARRAY_LABEL_LEN];
 	char array_id[UNIQUE_ID_LEN];
 
-	scsi_dh_data = kzalloc(sizeof(*scsi_dh_data)
-			       + sizeof(*h) , GFP_KERNEL);
-	if (!scsi_dh_data) {
+	h = kzalloc(sizeof(*h) , GFP_KERNEL);
+	if (!h) {
 		sdev_printk(KERN_ERR, sdev, "%s: Attach failed\n",
 			    RDAC_NAME);
 		return -ENOMEM;
 	}
 
-	scsi_dh_data->scsi_dh = &rdac_dh;
-	h = (struct rdac_dh_data *) scsi_dh_data->buf;
+	h->dh_data.scsi_dh = &rdac_dh;
 	h->lun = UNINITIALIZED_LUN;
 	h->state = RDAC_STATE_ACTIVE;
 
@@ -879,7 +875,7 @@ static int rdac_bus_attach(struct scsi_device *sdev)
 		goto clean_ctlr;
 
 	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	sdev->scsi_dh_data = scsi_dh_data;
+	sdev->scsi_dh_data = &h->dh_data;
 	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
 
 	sdev_printk(KERN_NOTICE, sdev,
@@ -895,7 +891,7 @@ clean_ctlr:
 	spin_unlock(&list_lock);
 
 failed:
-	kfree(scsi_dh_data);
+	kfree(h);
 	sdev_printk(KERN_ERR, sdev, "%s: not attached\n",
 		    RDAC_NAME);
 	return -EINVAL;
@@ -903,12 +899,9 @@ failed:
 
 static void rdac_bus_detach( struct scsi_device *sdev )
 {
-	struct scsi_dh_data *scsi_dh_data;
-	struct rdac_dh_data *h;
+	struct rdac_dh_data *h = get_rdac_data(sdev);
 	unsigned long flags;
 
-	scsi_dh_data = sdev->scsi_dh_data;
-	h = (struct rdac_dh_data *) scsi_dh_data->buf;
 	if (h->ctlr && h->ctlr->ms_queued)
 		flush_workqueue(kmpath_rdacd);
 
@@ -920,7 +913,7 @@ static void rdac_bus_detach( struct scsi_device *sdev )
 	if (h->ctlr)
 		kref_put(&h->ctlr->kref, release_controller);
 	spin_unlock(&list_lock);
-	kfree(scsi_dh_data);
+	kfree(h);
 	sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n", RDAC_NAME);
 }
 
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 0b18a097c1b..04cd5ad8289 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -228,7 +228,6 @@ struct scsi_dh_data {
 	struct scsi_device_handler *scsi_dh;
 	struct scsi_device *sdev;
 	struct kref kref;
-	char buf[0];
 };
 
 #define	to_scsi_device(d)	\
-- 
cgit v1.2.3-70-g09d2


From a64d01dcf8440846f3077a436344f99313c1396c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 13 Sep 2014 20:05:04 -0700
Subject: scsi: remove struct scsi_dh_devlist

All drivers now do their own matching, so there is no more need to expose
a device list as part of the interface.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/scsi/device_handler/scsi_dh_emc.c   | 6 ++++--
 drivers/scsi/device_handler/scsi_dh_hp_sw.c | 6 ++++--
 drivers/scsi/device_handler/scsi_dh_rdac.c  | 6 ++++--
 include/scsi/scsi_device.h                  | 6 ------
 4 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c
index c2e26cdef21..800deb75a11 100644
--- a/drivers/scsi/device_handler/scsi_dh_emc.c
+++ b/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -622,7 +622,10 @@ done:
 	return result;
 }
 
-static const struct scsi_dh_devlist clariion_dev_list[] = {
+static const struct {
+	char *vendor;
+	char *model;
+} clariion_dev_list[] = {
 	{"DGC", "RAID"},
 	{"DGC", "DISK"},
 	{"DGC", "VRAID"},
@@ -653,7 +656,6 @@ static void clariion_bus_detach(struct scsi_device *sdev);
 static struct scsi_device_handler clariion_dh = {
 	.name		= CLARIION_NAME,
 	.module		= THIS_MODULE,
-	.devlist	= clariion_dev_list,
 	.attach		= clariion_bus_attach,
 	.detach		= clariion_bus_detach,
 	.check_sense	= clariion_check_sense,
diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
index 37dedcae0aa..471ffd19f2c 100644
--- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c
+++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
@@ -311,7 +311,10 @@ static int hp_sw_activate(struct scsi_device *sdev,
 	return 0;
 }
 
-static const struct scsi_dh_devlist hp_sw_dh_data_list[] = {
+static const struct {
+	char *vendor;
+	char *model;
+} hp_sw_dh_data_list[] = {
 	{"COMPAQ", "MSA1000 VOLUME"},
 	{"COMPAQ", "HSV110"},
 	{"HP", "HSV100"},
@@ -343,7 +346,6 @@ static void hp_sw_bus_detach(struct scsi_device *sdev);
 static struct scsi_device_handler hp_sw_dh = {
 	.name		= HP_SW_NAME,
 	.module		= THIS_MODULE,
-	.devlist	= hp_sw_dh_data_list,
 	.attach		= hp_sw_bus_attach,
 	.detach		= hp_sw_bus_detach,
 	.activate	= hp_sw_activate,
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index ef8caaaad76..8b09528613d 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -778,7 +778,10 @@ static int rdac_check_sense(struct scsi_device *sdev,
 	return SCSI_RETURN_NOT_HANDLED;
 }
 
-static const struct scsi_dh_devlist rdac_dev_list[] = {
+static const struct {
+	char *vendor;
+	char *model;
+} rdac_dev_list[] = {
 	{"IBM", "1722"},
 	{"IBM", "1724"},
 	{"IBM", "1726"},
@@ -830,7 +833,6 @@ static void rdac_bus_detach(struct scsi_device *sdev);
 static struct scsi_device_handler rdac_dh = {
 	.name = RDAC_NAME,
 	.module = THIS_MODULE,
-	.devlist = rdac_dev_list,
 	.prep_fn = rdac_prep_fn,
 	.check_sense = rdac_check_sense,
 	.attach = rdac_bus_attach,
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 04cd5ad8289..2601c97fd8b 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -201,11 +201,6 @@ struct scsi_device {
 	unsigned long		sdev_data[0];
 } __attribute__((aligned(sizeof(unsigned long))));
 
-struct scsi_dh_devlist {
-	char *vendor;
-	char *model;
-};
-
 typedef void (*activate_complete)(void *, int);
 struct scsi_device_handler {
 	/* Used by the infrastructure */
@@ -214,7 +209,6 @@ struct scsi_device_handler {
 	/* Filled by the hardware handler */
 	struct module *module;
 	const char *name;
-	const struct scsi_dh_devlist *devlist;
 	int (*check_sense)(struct scsi_device *, struct scsi_sense_hdr *);
 	int (*attach)(struct scsi_device *);
 	void (*detach)(struct scsi_device *);
-- 
cgit v1.2.3-70-g09d2


From 1d5203284d8acbdfdf9b478d434450b34f338f28 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 14 Sep 2014 11:08:21 -0700
Subject: scsi: handle more device handler setup/teardown in common code

Move all code to set up and tear down sdev->scsi_dh_data to common code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/scsi/device_handler/scsi_dh.c       | 29 ++++++++++----
 drivers/scsi/device_handler/scsi_dh_alua.c  | 59 ++++++++++-------------------
 drivers/scsi/device_handler/scsi_dh_emc.c   | 58 +++++++++-------------------
 drivers/scsi/device_handler/scsi_dh_hp_sw.c | 54 ++++++++------------------
 drivers/scsi/device_handler/scsi_dh_rdac.c  | 53 ++++++++------------------
 include/scsi/scsi_device.h                  |  2 +-
 6 files changed, 88 insertions(+), 167 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/device_handler/scsi_dh.c b/drivers/scsi/device_handler/scsi_dh.c
index d8a8aac2c3d..1dba62c5cf6 100644
--- a/drivers/scsi/device_handler/scsi_dh.c
+++ b/drivers/scsi/device_handler/scsi_dh.c
@@ -98,7 +98,7 @@ device_handler_match(struct scsi_device_handler *scsi_dh,
 static int scsi_dh_handler_attach(struct scsi_device *sdev,
 				  struct scsi_device_handler *scsi_dh)
 {
-	int err = 0;
+	struct scsi_dh_data *d;
 
 	if (sdev->scsi_dh_data) {
 		if (sdev->scsi_dh_data->scsi_dh != scsi_dh)
@@ -111,15 +111,22 @@ static int scsi_dh_handler_attach(struct scsi_device *sdev,
 	if (!try_module_get(scsi_dh->module))
 		return -EINVAL;
 
-	err = scsi_dh->attach(sdev);
-	if (err) {
+	d = scsi_dh->attach(sdev);
+	if (IS_ERR(d)) {
+		sdev_printk(KERN_ERR, sdev, "%s: Attach failed (%ld)\n",
+			    scsi_dh->name, PTR_ERR(d));
 		module_put(scsi_dh->module);
-		return err;
+		return PTR_ERR(d);
 	}
 
-	kref_init(&sdev->scsi_dh_data->kref);
-	sdev->scsi_dh_data->sdev = sdev;
-	return err;
+	d->scsi_dh = scsi_dh;
+	kref_init(&d->kref);
+	d->sdev = sdev;
+
+	spin_lock_irq(sdev->request_queue->queue_lock);
+	sdev->scsi_dh_data = d;
+	spin_unlock_irq(sdev->request_queue->queue_lock);
+	return 0;
 }
 
 static void __detach_handler (struct kref *kref)
@@ -127,8 +134,14 @@ static void __detach_handler (struct kref *kref)
 	struct scsi_dh_data *scsi_dh_data =
 		container_of(kref, struct scsi_dh_data, kref);
 	struct scsi_device_handler *scsi_dh = scsi_dh_data->scsi_dh;
+	struct scsi_device *sdev = scsi_dh_data->sdev;
+
+	spin_lock_irq(sdev->request_queue->queue_lock);
+	sdev->scsi_dh_data = NULL;
+	spin_unlock_irq(sdev->request_queue->queue_lock);
 
-	scsi_dh->detach(scsi_dh_data->sdev);
+	scsi_dh->detach(sdev);
+	sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n", scsi_dh->name);
 	module_put(scsi_dh->module);
 }
 
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index d9781045c4e..854b568b993 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -824,39 +824,18 @@ static bool alua_match(struct scsi_device *sdev)
 	return (scsi_device_tpgs(sdev) != 0);
 }
 
-static int alua_bus_attach(struct scsi_device *sdev);
-static void alua_bus_detach(struct scsi_device *sdev);
-
-static struct scsi_device_handler alua_dh = {
-	.name = ALUA_DH_NAME,
-	.module = THIS_MODULE,
-	.attach = alua_bus_attach,
-	.detach = alua_bus_detach,
-	.prep_fn = alua_prep_fn,
-	.check_sense = alua_check_sense,
-	.activate = alua_activate,
-	.set_params = alua_set_params,
-	.match = alua_match,
-};
-
 /*
  * alua_bus_attach - Attach device handler
  * @sdev: device to be attached to
  */
-static int alua_bus_attach(struct scsi_device *sdev)
+static struct scsi_dh_data *alua_bus_attach(struct scsi_device *sdev)
 {
 	struct alua_dh_data *h;
-	unsigned long flags;
-	int err = SCSI_DH_OK;
+	int err;
 
 	h = kzalloc(sizeof(*h) , GFP_KERNEL);
-	if (!h) {
-		sdev_printk(KERN_ERR, sdev, "%s: Attach failed\n",
-			    ALUA_DH_NAME);
-		return -ENOMEM;
-	}
-
-	h->dh_data.scsi_dh = &alua_dh;
+	if (!h)
+		return ERR_PTR(-ENOMEM);
 	h->tpgs = TPGS_MODE_UNINITIALIZED;
 	h->state = TPGS_STATE_OPTIMIZED;
 	h->group_id = -1;
@@ -866,20 +845,14 @@ static int alua_bus_attach(struct scsi_device *sdev)
 	h->sdev = sdev;
 
 	err = alua_initialize(sdev, h);
-	if ((err != SCSI_DH_OK) && (err != SCSI_DH_DEV_OFFLINED))
+	if (err != SCSI_DH_OK && err != SCSI_DH_DEV_OFFLINED)
 		goto failed;
 
-	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	sdev->scsi_dh_data = &h->dh_data;
-	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
 	sdev_printk(KERN_NOTICE, sdev, "%s: Attached\n", ALUA_DH_NAME);
-
-	return 0;
-
+	return &h->dh_data;
 failed:
 	kfree(h);
-	sdev_printk(KERN_ERR, sdev, "%s: not attached\n", ALUA_DH_NAME);
-	return -EINVAL;
+	return ERR_PTR(-EINVAL);
 }
 
 /*
@@ -889,18 +862,24 @@ failed:
 static void alua_bus_detach(struct scsi_device *sdev)
 {
 	struct alua_dh_data *h = get_alua_data(sdev);
-	unsigned long flags;
-
-	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	sdev->scsi_dh_data = NULL;
-	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
 
 	if (h->buff && h->inq != h->buff)
 		kfree(h->buff);
 	kfree(h);
-	sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n", ALUA_DH_NAME);
 }
 
+static struct scsi_device_handler alua_dh = {
+	.name = ALUA_DH_NAME,
+	.module = THIS_MODULE,
+	.attach = alua_bus_attach,
+	.detach = alua_bus_detach,
+	.prep_fn = alua_prep_fn,
+	.check_sense = alua_check_sense,
+	.activate = alua_activate,
+	.set_params = alua_set_params,
+	.match = alua_match,
+};
+
 static int __init alua_init(void)
 {
 	int r;
diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c
index 800deb75a11..6ed1caadbc6 100644
--- a/drivers/scsi/device_handler/scsi_dh_emc.c
+++ b/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -650,35 +650,14 @@ static bool clariion_match(struct scsi_device *sdev)
 	return false;
 }
 
-static int clariion_bus_attach(struct scsi_device *sdev);
-static void clariion_bus_detach(struct scsi_device *sdev);
-
-static struct scsi_device_handler clariion_dh = {
-	.name		= CLARIION_NAME,
-	.module		= THIS_MODULE,
-	.attach		= clariion_bus_attach,
-	.detach		= clariion_bus_detach,
-	.check_sense	= clariion_check_sense,
-	.activate	= clariion_activate,
-	.prep_fn	= clariion_prep_fn,
-	.set_params	= clariion_set_params,
-	.match		= clariion_match,
-};
-
-static int clariion_bus_attach(struct scsi_device *sdev)
+static struct scsi_dh_data *clariion_bus_attach(struct scsi_device *sdev)
 {
 	struct clariion_dh_data *h;
-	unsigned long flags;
 	int err;
 
 	h = kzalloc(sizeof(*h) , GFP_KERNEL);
-	if (!h) {
-		sdev_printk(KERN_ERR, sdev, "%s: Attach failed\n",
-			    CLARIION_NAME);
-		return -ENOMEM;
-	}
-
-	h->dh_data.scsi_dh = &clariion_dh;
+	if (!h)
+		return ERR_PTR(-ENOMEM);
 	h->lun_state = CLARIION_LUN_UNINITIALIZED;
 	h->default_sp = CLARIION_UNBOUND_LU;
 	h->current_sp = CLARIION_UNBOUND_LU;
@@ -691,40 +670,37 @@ static int clariion_bus_attach(struct scsi_device *sdev)
 	if (err != SCSI_DH_OK)
 		goto failed;
 
-	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	sdev->scsi_dh_data = &h->dh_data;
-	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
-
 	sdev_printk(KERN_INFO, sdev,
 		    "%s: connected to SP %c Port %d (%s, default SP %c)\n",
 		    CLARIION_NAME, h->current_sp + 'A',
 		    h->port, lun_state[h->lun_state],
 		    h->default_sp + 'A');
-
-	return 0;
+	return &h->dh_data;
 
 failed:
 	kfree(h);
-	sdev_printk(KERN_ERR, sdev, "%s: not attached\n",
-		    CLARIION_NAME);
-	return -EINVAL;
+	return ERR_PTR(-EINVAL);
 }
 
 static void clariion_bus_detach(struct scsi_device *sdev)
 {
 	struct clariion_dh_data *h = get_clariion_data(sdev);
-	unsigned long flags;
-
-	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	sdev->scsi_dh_data = NULL;
-	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
-
-	sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n",
-		    CLARIION_NAME);
 
 	kfree(h);
 }
 
+static struct scsi_device_handler clariion_dh = {
+	.name		= CLARIION_NAME,
+	.module		= THIS_MODULE,
+	.attach		= clariion_bus_attach,
+	.detach		= clariion_bus_detach,
+	.check_sense	= clariion_check_sense,
+	.activate	= clariion_activate,
+	.prep_fn	= clariion_prep_fn,
+	.set_params	= clariion_set_params,
+	.match		= clariion_match,
+};
+
 static int __init clariion_init(void)
 {
 	int r;
diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
index 471ffd19f2c..485d99544a1 100644
--- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c
+++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
@@ -340,33 +340,14 @@ static bool hp_sw_match(struct scsi_device *sdev)
 	return false;
 }
 
-static int hp_sw_bus_attach(struct scsi_device *sdev);
-static void hp_sw_bus_detach(struct scsi_device *sdev);
-
-static struct scsi_device_handler hp_sw_dh = {
-	.name		= HP_SW_NAME,
-	.module		= THIS_MODULE,
-	.attach		= hp_sw_bus_attach,
-	.detach		= hp_sw_bus_detach,
-	.activate	= hp_sw_activate,
-	.prep_fn	= hp_sw_prep_fn,
-	.match		= hp_sw_match,
-};
-
-static int hp_sw_bus_attach(struct scsi_device *sdev)
+static struct scsi_dh_data *hp_sw_bus_attach(struct scsi_device *sdev)
 {
 	struct hp_sw_dh_data *h;
-	unsigned long flags;
 	int ret;
 
 	h = kzalloc(sizeof(*h), GFP_KERNEL);
-	if (!h) {
-		sdev_printk(KERN_ERR, sdev, "%s: Attach Failed\n",
-			    HP_SW_NAME);
-		return -ENOMEM;
-	}
-
-	h->dh_data.scsi_dh = &hp_sw_dh;
+	if (!h)
+		return ERR_PTR(-ENOMEM);
 	h->path_state = HP_SW_PATH_UNINITIALIZED;
 	h->retries = HP_SW_RETRIES;
 	h->sdev = sdev;
@@ -375,37 +356,32 @@ static int hp_sw_bus_attach(struct scsi_device *sdev)
 	if (ret != SCSI_DH_OK || h->path_state == HP_SW_PATH_UNINITIALIZED)
 		goto failed;
 
-	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	sdev->scsi_dh_data = &h->dh_data;
-	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
-
 	sdev_printk(KERN_INFO, sdev, "%s: attached to %s path\n",
 		    HP_SW_NAME, h->path_state == HP_SW_PATH_ACTIVE?
 		    "active":"passive");
-
-	return 0;
-
+	return &h->dh_data;
 failed:
 	kfree(h);
-	sdev_printk(KERN_ERR, sdev, "%s: not attached\n",
-		    HP_SW_NAME);
-	return -EINVAL;
+	return ERR_PTR(-EINVAL);
 }
 
 static void hp_sw_bus_detach( struct scsi_device *sdev )
 {
 	struct hp_sw_dh_data *h = get_hp_sw_data(sdev);
-	unsigned long flags;
-
-	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	sdev->scsi_dh_data = NULL;
-	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
-
-	sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n", HP_SW_NAME);
 
 	kfree(h);
 }
 
+static struct scsi_device_handler hp_sw_dh = {
+	.name		= HP_SW_NAME,
+	.module		= THIS_MODULE,
+	.attach		= hp_sw_bus_attach,
+	.detach		= hp_sw_bus_detach,
+	.activate	= hp_sw_activate,
+	.prep_fn	= hp_sw_prep_fn,
+	.match		= hp_sw_match,
+};
+
 static int __init hp_sw_init(void)
 {
 	return scsi_register_device_handler(&hp_sw_dh);
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index 8b09528613d..b46ace3d4bf 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -827,36 +827,16 @@ static bool rdac_match(struct scsi_device *sdev)
 	return false;
 }
 
-static int rdac_bus_attach(struct scsi_device *sdev);
-static void rdac_bus_detach(struct scsi_device *sdev);
-
-static struct scsi_device_handler rdac_dh = {
-	.name = RDAC_NAME,
-	.module = THIS_MODULE,
-	.prep_fn = rdac_prep_fn,
-	.check_sense = rdac_check_sense,
-	.attach = rdac_bus_attach,
-	.detach = rdac_bus_detach,
-	.activate = rdac_activate,
-	.match = rdac_match,
-};
-
-static int rdac_bus_attach(struct scsi_device *sdev)
+static struct scsi_dh_data *rdac_bus_attach(struct scsi_device *sdev)
 {
 	struct rdac_dh_data *h;
-	unsigned long flags;
 	int err;
 	char array_name[ARRAY_LABEL_LEN];
 	char array_id[UNIQUE_ID_LEN];
 
 	h = kzalloc(sizeof(*h) , GFP_KERNEL);
-	if (!h) {
-		sdev_printk(KERN_ERR, sdev, "%s: Attach failed\n",
-			    RDAC_NAME);
-		return -ENOMEM;
-	}
-
-	h->dh_data.scsi_dh = &rdac_dh;
+	if (!h)
+		return ERR_PTR(-ENOMEM);
 	h->lun = UNINITIALIZED_LUN;
 	h->state = RDAC_STATE_ACTIVE;
 
@@ -876,16 +856,12 @@ static int rdac_bus_attach(struct scsi_device *sdev)
 	if (err != SCSI_DH_OK)
 		goto clean_ctlr;
 
-	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	sdev->scsi_dh_data = &h->dh_data;
-	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
-
 	sdev_printk(KERN_NOTICE, sdev,
 		    "%s: LUN %d (%s) (%s)\n",
 		    RDAC_NAME, h->lun, mode[(int)h->mode],
 		    lun_state[(int)h->lun_state]);
 
-	return 0;
+	return &h->dh_data;
 
 clean_ctlr:
 	spin_lock(&list_lock);
@@ -894,32 +870,33 @@ clean_ctlr:
 
 failed:
 	kfree(h);
-	sdev_printk(KERN_ERR, sdev, "%s: not attached\n",
-		    RDAC_NAME);
-	return -EINVAL;
+	return ERR_PTR(-EINVAL);
 }
 
 static void rdac_bus_detach( struct scsi_device *sdev )
 {
 	struct rdac_dh_data *h = get_rdac_data(sdev);
-	unsigned long flags;
 
 	if (h->ctlr && h->ctlr->ms_queued)
 		flush_workqueue(kmpath_rdacd);
 
-	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	sdev->scsi_dh_data = NULL;
-	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
-
 	spin_lock(&list_lock);
 	if (h->ctlr)
 		kref_put(&h->ctlr->kref, release_controller);
 	spin_unlock(&list_lock);
 	kfree(h);
-	sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n", RDAC_NAME);
 }
 
-
+static struct scsi_device_handler rdac_dh = {
+	.name = RDAC_NAME,
+	.module = THIS_MODULE,
+	.prep_fn = rdac_prep_fn,
+	.check_sense = rdac_check_sense,
+	.attach = rdac_bus_attach,
+	.detach = rdac_bus_detach,
+	.activate = rdac_activate,
+	.match = rdac_match,
+};
 
 static int __init rdac_init(void)
 {
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 2601c97fd8b..50d47e6e89d 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -210,7 +210,7 @@ struct scsi_device_handler {
 	struct module *module;
 	const char *name;
 	int (*check_sense)(struct scsi_device *, struct scsi_sense_hdr *);
-	int (*attach)(struct scsi_device *);
+	struct scsi_dh_data *(*attach)(struct scsi_device *);
 	void (*detach)(struct scsi_device *);
 	int (*activate)(struct scsi_device *, activate_complete, void *);
 	int (*prep_fn)(struct scsi_device *, struct request *);
-- 
cgit v1.2.3-70-g09d2


From a62182f338b39a22035531c6afc0a8d2928b1df2 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 2 Oct 2014 14:39:55 +0200
Subject: scsi: provide a generic change_queue_type method

Most drivers use exactly the same implementation, so provide it as a
library function.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/infiniband/ulp/srp/ib_srp.c  | 24 +-----------------------
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c    |  2 +-
 drivers/scsi/esas2r/esas2r.h         |  1 -
 drivers/scsi/esas2r/esas2r_main.c    | 20 +-------------------
 drivers/scsi/fcoe/fcoe.c             |  2 +-
 drivers/scsi/fnic/fnic_main.c        |  2 +-
 drivers/scsi/ibmvscsi/ibmvfc.c       | 25 +------------------------
 drivers/scsi/ipr.c                   | 20 +++-----------------
 drivers/scsi/libfc/fc_fcp.c          | 20 --------------------
 drivers/scsi/lpfc/lpfc_scsi.c        | 24 ++----------------------
 drivers/scsi/mpt2sas/mpt2sas_scsih.c | 24 +-----------------------
 drivers/scsi/mpt3sas/mpt3sas_scsih.c | 25 +------------------------
 drivers/scsi/pmcraid.c               | 14 ++++----------
 drivers/scsi/qla2xxx/qla_os.c        | 18 +-----------------
 drivers/scsi/scsi.c                  | 20 ++++++++++++++++++++
 drivers/scsi/scsi_debug.c            |  9 +--------
 drivers/target/loopback/tcm_loop.c   | 17 +----------------
 include/scsi/libfc.h                 |  1 -
 include/scsi/scsi_tcq.h              |  2 ++
 19 files changed, 42 insertions(+), 228 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 62d2a18e1b4..51670d75ab7 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -2258,28 +2258,6 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event)
 	return 0;
 }
 
-/**
- * srp_change_queue_type - changing device queue tag type
- * @sdev: scsi device struct
- * @tag_type: requested tag type
- *
- * Returns queue tag type.
- */
-static int
-srp_change_queue_type(struct scsi_device *sdev, int tag_type)
-{
-	if (sdev->tagged_supported) {
-		scsi_set_tag_type(sdev, tag_type);
-		if (tag_type)
-			scsi_activate_tcq(sdev, sdev->queue_depth);
-		else
-			scsi_deactivate_tcq(sdev, sdev->queue_depth);
-	} else
-		tag_type = 0;
-
-	return tag_type;
-}
-
 /**
  * srp_change_queue_depth - setting device queue depth
  * @sdev: scsi device struct
@@ -2600,7 +2578,7 @@ static struct scsi_host_template srp_template = {
 	.info				= srp_target_info,
 	.queuecommand			= srp_queuecommand,
 	.change_queue_depth             = srp_change_queue_depth,
-	.change_queue_type              = srp_change_queue_type,
+	.change_queue_type              = scsi_change_queue_type,
 	.eh_abort_handler		= srp_abort,
 	.eh_device_reset_handler	= srp_reset_device,
 	.eh_host_reset_handler		= srp_reset_host,
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 79e5c94107a..3c6dc8abc77 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -2784,7 +2784,7 @@ static struct scsi_host_template bnx2fc_shost_template = {
 	.eh_host_reset_handler	= fc_eh_host_reset,
 	.slave_alloc		= fc_slave_alloc,
 	.change_queue_depth	= fc_change_queue_depth,
-	.change_queue_type	= fc_change_queue_type,
+	.change_queue_type	= scsi_change_queue_type,
 	.this_id		= -1,
 	.cmd_per_lun		= 3,
 	.use_clustering		= ENABLE_CLUSTERING,
diff --git a/drivers/scsi/esas2r/esas2r.h b/drivers/scsi/esas2r/esas2r.h
index 3fd305d6b67..20ab211983f 100644
--- a/drivers/scsi/esas2r/esas2r.h
+++ b/drivers/scsi/esas2r/esas2r.h
@@ -976,7 +976,6 @@ int esas2r_slave_alloc(struct scsi_device *dev);
 int esas2r_slave_configure(struct scsi_device *dev);
 void esas2r_slave_destroy(struct scsi_device *dev);
 int esas2r_change_queue_depth(struct scsi_device *dev, int depth, int reason);
-int esas2r_change_queue_type(struct scsi_device *dev, int type);
 long esas2r_proc_ioctl(struct file *fp, unsigned int cmd, unsigned long arg);
 
 /* SCSI error handler (eh) functions */
diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c
index 45aa684f8b7..be09c628d03 100644
--- a/drivers/scsi/esas2r/esas2r_main.c
+++ b/drivers/scsi/esas2r/esas2r_main.c
@@ -258,7 +258,7 @@ static struct scsi_host_template driver_template = {
 	.slave_alloc			= esas2r_slave_alloc,
 	.slave_destroy			= esas2r_slave_destroy,
 	.change_queue_depth		= esas2r_change_queue_depth,
-	.change_queue_type		= esas2r_change_queue_type,
+	.change_queue_type		= scsi_change_queue_type,
 	.max_sectors			= 0xFFFF,
 };
 
@@ -1268,24 +1268,6 @@ int esas2r_change_queue_depth(struct scsi_device *dev, int depth, int reason)
 	return dev->queue_depth;
 }
 
-int esas2r_change_queue_type(struct scsi_device *dev, int type)
-{
-	esas2r_log(ESAS2R_LOG_INFO, "change_queue_type %p, %d", dev, type);
-
-	if (dev->tagged_supported) {
-		scsi_set_tag_type(dev, type);
-
-		if (type)
-			scsi_activate_tcq(dev, dev->queue_depth);
-		else
-			scsi_deactivate_tcq(dev, dev->queue_depth);
-	} else {
-		type = 0;
-	}
-
-	return type;
-}
-
 int esas2r_slave_alloc(struct scsi_device *dev)
 {
 	return 0;
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 4a8ac7d8c76..86956cc3448 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -281,7 +281,7 @@ static struct scsi_host_template fcoe_shost_template = {
 	.eh_host_reset_handler = fc_eh_host_reset,
 	.slave_alloc = fc_slave_alloc,
 	.change_queue_depth = fc_change_queue_depth,
-	.change_queue_type = fc_change_queue_type,
+	.change_queue_type = scsi_change_queue_type,
 	.this_id = -1,
 	.cmd_per_lun = 3,
 	.can_queue = FCOE_MAX_OUTSTANDING_COMMANDS,
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index 8c56fdc3a45..8581ce662cf 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -113,7 +113,7 @@ static struct scsi_host_template fnic_host_template = {
 	.eh_host_reset_handler = fnic_host_reset,
 	.slave_alloc = fnic_slave_alloc,
 	.change_queue_depth = fc_change_queue_depth,
-	.change_queue_type = fc_change_queue_type,
+	.change_queue_type = scsi_change_queue_type,
 	.this_id = -1,
 	.cmd_per_lun = 3,
 	.can_queue = FNIC_DFLT_IO_REQ,
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 598c42cba5a..48d19a3256c 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -2929,29 +2929,6 @@ static int ibmvfc_change_queue_depth(struct scsi_device *sdev, int qdepth,
 	return sdev->queue_depth;
 }
 
-/**
- * ibmvfc_change_queue_type - Change the device's queue type
- * @sdev:		scsi device struct
- * @tag_type:	type of tags to use
- *
- * Return value:
- * 	actual queue type set
- **/
-static int ibmvfc_change_queue_type(struct scsi_device *sdev, int tag_type)
-{
-	if (sdev->tagged_supported) {
-		scsi_set_tag_type(sdev, tag_type);
-
-		if (tag_type)
-			scsi_activate_tcq(sdev, sdev->queue_depth);
-		else
-			scsi_deactivate_tcq(sdev, sdev->queue_depth);
-	} else
-		tag_type = 0;
-
-	return tag_type;
-}
-
 static ssize_t ibmvfc_show_host_partition_name(struct device *dev,
 						 struct device_attribute *attr, char *buf)
 {
@@ -3133,7 +3110,7 @@ static struct scsi_host_template driver_template = {
 	.target_alloc = ibmvfc_target_alloc,
 	.scan_finished = ibmvfc_scan_finished,
 	.change_queue_depth = ibmvfc_change_queue_depth,
-	.change_queue_type = ibmvfc_change_queue_type,
+	.change_queue_type = scsi_change_queue_type,
 	.cmd_per_lun = 16,
 	.can_queue = IBMVFC_MAX_REQUESTS_DEFAULT,
 	.this_id = -1,
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 2a9578c116b..3d689f6023e 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -4364,24 +4364,10 @@ static int ipr_change_queue_type(struct scsi_device *sdev, int tag_type)
 
 	spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
 	res = (struct ipr_resource_entry *)sdev->hostdata;
-
-	if (res) {
-		if (ipr_is_gscsi(res) && sdev->tagged_supported) {
-			/*
-			 * We don't bother quiescing the device here since the
-			 * adapter firmware does it for us.
-			 */
-			scsi_set_tag_type(sdev, tag_type);
-
-			if (tag_type)
-				scsi_activate_tcq(sdev, sdev->queue_depth);
-			else
-				scsi_deactivate_tcq(sdev, sdev->queue_depth);
-		} else
-			tag_type = 0;
-	} else
+	if (res && ipr_is_gscsi(res))
+		tag_type = scsi_change_queue_type(sdev, tag_type);
+	else
 		tag_type = 0;
-
 	spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
 	return tag_type;
 }
diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index 1d7e76e8b44..f3043ad1f35 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -2195,26 +2195,6 @@ int fc_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 }
 EXPORT_SYMBOL(fc_change_queue_depth);
 
-/**
- * fc_change_queue_type() - Change a device's queue type
- * @sdev:     The SCSI device whose queue depth is to change
- * @tag_type: Identifier for queue type
- */
-int fc_change_queue_type(struct scsi_device *sdev, int tag_type)
-{
-	if (sdev->tagged_supported) {
-		scsi_set_tag_type(sdev, tag_type);
-		if (tag_type)
-			scsi_activate_tcq(sdev, sdev->queue_depth);
-		else
-			scsi_deactivate_tcq(sdev, sdev->queue_depth);
-	} else
-		tag_type = 0;
-
-	return tag_type;
-}
-EXPORT_SYMBOL(fc_change_queue_type);
-
 /**
  * fc_fcp_destory() - Tear down the FCP layer for a given local port
  * @lport: The local port that no longer needs the FCP layer
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index b99399fe254..2896e52ac6c 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -344,26 +344,6 @@ lpfc_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 	return sdev->queue_depth;
 }
 
-/**
- * lpfc_change_queue_type() - Change a device's scsi tag queuing type
- * @sdev: Pointer the scsi device whose queue depth is to change
- * @tag_type: Identifier for queue tag type
- */
-static int
-lpfc_change_queue_type(struct scsi_device *sdev, int tag_type)
-{
-	if (sdev->tagged_supported) {
-		scsi_set_tag_type(sdev, tag_type);
-		if (tag_type)
-			scsi_activate_tcq(sdev, sdev->queue_depth);
-		else
-			scsi_deactivate_tcq(sdev, sdev->queue_depth);
-	} else
-		tag_type = 0;
-
-	return tag_type;
-}
-
 /**
  * lpfc_rampdown_queue_depth - Post RAMP_DOWN_QUEUE event to worker thread
  * @phba: The Hba for which this call is being executed.
@@ -6019,7 +5999,7 @@ struct scsi_host_template lpfc_template = {
 	.max_sectors		= 0xFFFF,
 	.vendor_id		= LPFC_NL_VENDOR_ID,
 	.change_queue_depth	= lpfc_change_queue_depth,
-	.change_queue_type	= lpfc_change_queue_type,
+	.change_queue_type	= scsi_change_queue_type,
 };
 
 struct scsi_host_template lpfc_vport_template = {
@@ -6042,5 +6022,5 @@ struct scsi_host_template lpfc_vport_template = {
 	.shost_attrs		= lpfc_vport_attrs,
 	.max_sectors		= 0xFFFF,
 	.change_queue_depth	= lpfc_change_queue_depth,
-	.change_queue_type	= lpfc_change_queue_type,
+	.change_queue_type	= scsi_change_queue_type,
 };
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index c80ed048264..ec36b91c880 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -1254,28 +1254,6 @@ _scsih_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 	return sdev->queue_depth;
 }
 
-/**
- * _scsih_change_queue_type - changing device queue tag type
- * @sdev: scsi device struct
- * @tag_type: requested tag type
- *
- * Returns queue tag type.
- */
-static int
-_scsih_change_queue_type(struct scsi_device *sdev, int tag_type)
-{
-	if (sdev->tagged_supported) {
-		scsi_set_tag_type(sdev, tag_type);
-		if (tag_type)
-			scsi_activate_tcq(sdev, sdev->queue_depth);
-		else
-			scsi_deactivate_tcq(sdev, sdev->queue_depth);
-	} else
-		tag_type = 0;
-
-	return tag_type;
-}
-
 /**
  * _scsih_target_alloc - target add routine
  * @starget: scsi target struct
@@ -7653,7 +7631,7 @@ static struct scsi_host_template scsih_driver_template = {
 	.scan_finished			= _scsih_scan_finished,
 	.scan_start			= _scsih_scan_start,
 	.change_queue_depth 		= _scsih_change_queue_depth,
-	.change_queue_type		= _scsih_change_queue_type,
+	.change_queue_type		= scsi_change_queue_type,
 	.eh_abort_handler		= _scsih_abort,
 	.eh_device_reset_handler	= _scsih_dev_reset,
 	.eh_target_reset_handler	= _scsih_target_reset,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 857276b8880..52464ace282 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -1122,29 +1122,6 @@ _scsih_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 	return sdev->queue_depth;
 }
 
-/**
- * _scsih_change_queue_type - changing device queue tag type
- * @sdev: scsi device struct
- * @tag_type: requested tag type
- *
- * Returns queue tag type.
- */
-static int
-_scsih_change_queue_type(struct scsi_device *sdev, int tag_type)
-{
-	if (sdev->tagged_supported) {
-		scsi_set_tag_type(sdev, tag_type);
-		if (tag_type)
-			scsi_activate_tcq(sdev, sdev->queue_depth);
-		else
-			scsi_deactivate_tcq(sdev, sdev->queue_depth);
-	} else
-		tag_type = 0;
-
-	return tag_type;
-}
-
-
 /**
  * _scsih_target_alloc - target add routine
  * @starget: scsi target struct
@@ -7284,7 +7261,7 @@ static struct scsi_host_template scsih_driver_template = {
 	.scan_finished			= _scsih_scan_finished,
 	.scan_start			= _scsih_scan_start,
 	.change_queue_depth		= _scsih_change_queue_depth,
-	.change_queue_type		= _scsih_change_queue_type,
+	.change_queue_type		= scsi_change_queue_type,
 	.eh_abort_handler		= _scsih_abort,
 	.eh_device_reset_handler	= _scsih_dev_reset,
 	.eh_target_reset_handler	= _scsih_target_reset,
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index bcb64eb1387..2233ed6b89e 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -321,16 +321,10 @@ static int pmcraid_change_queue_type(struct scsi_device *scsi_dev, int tag)
 	struct pmcraid_resource_entry *res;
 
 	res = (struct pmcraid_resource_entry *)scsi_dev->hostdata;
-
-	if ((res) && scsi_dev->tagged_supported &&
-	    (RES_IS_GSCSI(res->cfg_entry) || RES_IS_VSET(res->cfg_entry))) {
-		scsi_set_tag_type(scsi_dev, tag);
-
-		if (tag)
-			scsi_activate_tcq(scsi_dev, scsi_dev->queue_depth);
-		else
-			scsi_deactivate_tcq(scsi_dev, scsi_dev->queue_depth);
-	} else
+	if (res && scsi_dev->tagged_supported &&
+	    (RES_IS_GSCSI(res->cfg_entry) || RES_IS_VSET(res->cfg_entry)))
+	    	tag = scsi_change_queue_type(scsi_dev, tag);
+	else
 		tag = 0;
 
 	return tag;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index db3dbd999cb..5e755747e07 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -237,7 +237,6 @@ static int qla2xxx_eh_bus_reset(struct scsi_cmnd *);
 static int qla2xxx_eh_host_reset(struct scsi_cmnd *);
 
 static int qla2x00_change_queue_depth(struct scsi_device *, int, int);
-static int qla2x00_change_queue_type(struct scsi_device *, int);
 static void qla2x00_clear_drv_active(struct qla_hw_data *);
 static void qla2x00_free_device(scsi_qla_host_t *);
 static void qla83xx_disable_laser(scsi_qla_host_t *vha);
@@ -260,7 +259,7 @@ struct scsi_host_template qla2xxx_driver_template = {
 	.scan_finished		= qla2xxx_scan_finished,
 	.scan_start		= qla2xxx_scan_start,
 	.change_queue_depth	= qla2x00_change_queue_depth,
-	.change_queue_type	= qla2x00_change_queue_type,
+	.change_queue_type	= scsi_change_queue_type,
 	.this_id		= -1,
 	.cmd_per_lun		= 3,
 	.use_clustering		= ENABLE_CLUSTERING,
@@ -1473,21 +1472,6 @@ qla2x00_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 	return sdev->queue_depth;
 }
 
-static int
-qla2x00_change_queue_type(struct scsi_device *sdev, int tag_type)
-{
-	if (sdev->tagged_supported) {
-		scsi_set_tag_type(sdev, tag_type);
-		if (tag_type)
-			scsi_activate_tcq(sdev, sdev->queue_depth);
-		else
-			scsi_deactivate_tcq(sdev, sdev->queue_depth);
-	} else
-		tag_type = 0;
-
-	return tag_type;
-}
-
 /**
  * qla2x00_config_dma_addressing() - Configure OS DMA addressing method.
  * @ha: HA context
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index bc52bbd9738..9baeff03dd9 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -866,6 +866,26 @@ int scsi_track_queue_full(struct scsi_device *sdev, int depth)
 }
 EXPORT_SYMBOL(scsi_track_queue_full);
 
+/**
+ * scsi_change_queue_type() - Change a device's queue type
+ * @sdev:     The SCSI device whose queue depth is to change
+ * @tag_type: Identifier for queue type
+ */
+int scsi_change_queue_type(struct scsi_device *sdev, int tag_type)
+{
+	if (sdev->tagged_supported) {
+		scsi_set_tag_type(sdev, tag_type);
+		if (tag_type)
+			scsi_activate_tcq(sdev, sdev->queue_depth);
+		else
+			scsi_deactivate_tcq(sdev, sdev->queue_depth);
+	} else
+		tag_type = 0;
+
+	return tag_type;
+}
+EXPORT_SYMBOL(scsi_change_queue_type);
+
 /**
  * scsi_vpd_inquiry - Request a device provide us with a VPD page
  * @sdev: The device to ask
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 238e06f13b8..7bcace2cdd5 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -4532,14 +4532,7 @@ sdebug_change_qdepth(struct scsi_device *sdev, int qdepth, int reason)
 static int
 sdebug_change_qtype(struct scsi_device *sdev, int qtype)
 {
-	if (sdev->tagged_supported) {
-		scsi_set_tag_type(sdev, qtype);
-		if (qtype)
-			scsi_activate_tcq(sdev, sdev->queue_depth);
-		else
-			scsi_deactivate_tcq(sdev, sdev->queue_depth);
-	} else
-		qtype = 0;
+	qtype = scsi_change_queue_type(sdev, qtype);
 	if (SCSI_DEBUG_OPT_Q_NOISE & scsi_debug_opts) {
 		const char *cp;
 
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index ab3ab27d49b..3b9c76835b4 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -135,21 +135,6 @@ static int tcm_loop_change_queue_depth(
 	return sdev->queue_depth;
 }
 
-static int tcm_loop_change_queue_type(struct scsi_device *sdev, int tag)
-{
-	if (sdev->tagged_supported) {
-		scsi_set_tag_type(sdev, tag);
-
-		if (tag)
-			scsi_activate_tcq(sdev, sdev->queue_depth);
-		else
-			scsi_deactivate_tcq(sdev, sdev->queue_depth);
-	} else
-		tag = 0;
-
-	return tag;
-}
-
 /*
  * Locate the SAM Task Attr from struct scsi_cmnd *
  */
@@ -451,7 +436,7 @@ static struct scsi_host_template tcm_loop_driver_template = {
 	.name			= "TCM_Loopback",
 	.queuecommand		= tcm_loop_queuecommand,
 	.change_queue_depth	= tcm_loop_change_queue_depth,
-	.change_queue_type	= tcm_loop_change_queue_type,
+	.change_queue_type	= scsi_change_queue_type,
 	.eh_abort_handler = tcm_loop_abort_task,
 	.eh_device_reset_handler = tcm_loop_device_reset,
 	.eh_target_reset_handler = tcm_loop_target_reset,
diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h
index 52beadf9a29..2e0cf568a9c 100644
--- a/include/scsi/libfc.h
+++ b/include/scsi/libfc.h
@@ -1106,7 +1106,6 @@ int fc_eh_device_reset(struct scsi_cmnd *);
 int fc_eh_host_reset(struct scsi_cmnd *);
 int fc_slave_alloc(struct scsi_device *);
 int fc_change_queue_depth(struct scsi_device *, int qdepth, int reason);
-int fc_change_queue_type(struct scsi_device *, int tag_type);
 
 /*
  * ELS/CT interface
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index 7529c6acc23..1712dab6e00 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -16,6 +16,8 @@
 
 #ifdef CONFIG_BLOCK
 
+int scsi_change_queue_type(struct scsi_device *sdev, int tag_type);
+
 /**
  * scsi_get_tag_type - get the type of tag the device supports
  * @sdev:	the scsi device
-- 
cgit v1.2.3-70-g09d2


From 125c99bc8b6b108d251169a86324a7ed3c6f3cce Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 3 Nov 2014 12:47:47 +0100
Subject: scsi: add new scsi-command flag for tagged commands

Currently scsi piggy backs on the block layer to define the concept
of a tagged command.  But we want to be able to have block-level host-wide
tags assigned even for untagged commands like the initial INQUIRY, so add
a new SCSI-level flag for commands that are tagged at the scsi level, so
that even commands without that set can have tags assigned to them.  Note
that this alredy is the case for the blk-mq code path, and this just lets
the old path catch up with it.

We also set this flag based upon sdev->simple_tags instead of the block
queue flag, so that it is entirely independent of the block layer tagging,
and thus always correct even if a driver doesn't use block level tagging
yet.

Also remove the old blk_rq_tagged; it was only used by SCSI drivers, and
removing it forces them to look for the proper replacement.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 Documentation/block/biodoc.txt     |  4 ----
 block/blk-core.c                   |  4 ++--
 drivers/scsi/53c700.c              |  6 +++---
 drivers/scsi/aic7xxx/aic7xxx_osm.c |  2 +-
 drivers/scsi/scsi_lib.c            | 13 +++++++++----
 drivers/usb/storage/uas.c          |  2 +-
 include/linux/blkdev.h             |  1 -
 include/scsi/scsi_cmnd.h           |  4 ++++
 include/scsi/scsi_tcq.h            |  6 ++----
 9 files changed, 22 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index 2101e718670..6b972b28779 100644
--- a/Documentation/block/biodoc.txt
+++ b/Documentation/block/biodoc.txt
@@ -827,10 +827,6 @@ but in the event of any barrier requests in the tag queue we need to ensure
 that requests are restarted in the order they were queue. This may happen
 if the driver needs to use blk_queue_invalidate_tags().
 
-Tagging also defines a new request flag, REQ_QUEUED. This is set whenever
-a request is currently tagged. You should not use this flag directly,
-blk_rq_tagged(rq) is the portable way to do so.
-
 3.3 I/O Submission
 
 The routine submit_bio() is used to submit a single io. Higher level i/o
diff --git a/block/blk-core.c b/block/blk-core.c
index 0421b53e643..2e7424b4294 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1266,7 +1266,7 @@ void blk_requeue_request(struct request_queue *q, struct request *rq)
 	blk_clear_rq_complete(rq);
 	trace_block_rq_requeue(q, rq);
 
-	if (blk_rq_tagged(rq))
+	if (rq->cmd_flags & REQ_QUEUED)
 		blk_queue_end_tag(q, rq);
 
 	BUG_ON(blk_queued_rq(rq));
@@ -2554,7 +2554,7 @@ EXPORT_SYMBOL_GPL(blk_unprep_request);
  */
 void blk_finish_request(struct request *req, int error)
 {
-	if (blk_rq_tagged(req))
+	if (req->cmd_flags & REQ_QUEUED)
 		blk_queue_end_tag(req->q, req);
 
 	BUG_ON(blk_queued_rq(req));
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index 474cc6dc98e..5143d3213e8 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -1767,7 +1767,7 @@ NCR_700_queuecommand_lck(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *)
 	 */
 	if(NCR_700_get_depth(SCp->device) != 0
 	   && (!(hostdata->tag_negotiated & (1<<scmd_id(SCp)))
-	       || !blk_rq_tagged(SCp->request))) {
+	       || !(SCp->flags & SCMD_TAGGED))) {
 		CDEBUG(KERN_ERR, SCp, "has non zero depth %d\n",
 		       NCR_700_get_depth(SCp->device));
 		return SCSI_MLQUEUE_DEVICE_BUSY;
@@ -1795,7 +1795,7 @@ NCR_700_queuecommand_lck(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *)
 	printk("53c700: scsi%d, command ", SCp->device->host->host_no);
 	scsi_print_command(SCp);
 #endif
-	if(blk_rq_tagged(SCp->request)
+	if ((SCp->flags & SCMD_TAGGED)
 	   && (hostdata->tag_negotiated &(1<<scmd_id(SCp))) == 0
 	   && NCR_700_get_tag_neg_state(SCp->device) == NCR_700_START_TAG_NEGOTIATION) {
 		scmd_printk(KERN_ERR, SCp, "Enabling Tag Command Queuing\n");
@@ -1809,7 +1809,7 @@ NCR_700_queuecommand_lck(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *)
 	 *
 	 * FIXME: This will royally screw up on multiple LUN devices
 	 * */
-	if(!blk_rq_tagged(SCp->request)
+	if (!(SCp->flags & SCMD_TAGGED)
 	   && (hostdata->tag_negotiated &(1<<scmd_id(SCp)))) {
 		scmd_printk(KERN_INFO, SCp, "Disabling Tag Command Queuing\n");
 		hostdata->tag_negotiated &= ~(1<<scmd_id(SCp));
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c
index d2c9bf39033..63bae7c65c9 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c
@@ -1447,7 +1447,7 @@ ahc_linux_run_command(struct ahc_softc *ahc, struct ahc_linux_device *dev,
 	 * we are storing a full busy target *lun*
 	 * table in SCB space.
 	 */
-	if (!blk_rq_tagged(cmd->request)
+	if (!(cmd->flags & SCMD_TAGGED)
 	    && (ahc->features & AHC_SCB_BTT) == 0) {
 		int target_offset;
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 38f8c85957b..994eb083fff 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1740,7 +1740,7 @@ static void scsi_request_fn(struct request_queue *q)
 		 * we add the dev to the starved list so it eventually gets
 		 * a run when a tag is freed.
 		 */
-		if (blk_queue_tagged(q) && !blk_rq_tagged(req)) {
+		if (blk_queue_tagged(q) && !(req->cmd_flags & REQ_QUEUED)) {
 			spin_lock_irq(shost->host_lock);
 			if (list_empty(&sdev->starved_entry))
 				list_add_tail(&sdev->starved_entry,
@@ -1754,6 +1754,11 @@ static void scsi_request_fn(struct request_queue *q)
 
 		if (!scsi_host_queue_ready(q, shost, sdev))
 			goto host_not_ready;
+	
+		if (sdev->simple_tags)
+			cmd->flags |= SCMD_TAGGED;
+		else
+			cmd->flags &= ~SCMD_TAGGED;
 
 		/*
 		 * Finally, initialize any error handling parameters, and set up
@@ -1908,10 +1913,10 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
 		blk_mq_start_request(req);
 	}
 
-	if (blk_queue_tagged(q))
-		req->cmd_flags |= REQ_QUEUED;
+	if (sdev->simple_tags)
+		cmd->flags |= SCMD_TAGGED;
 	else
-		req->cmd_flags &= ~REQ_QUEUED;
+		cmd->flags &= ~SCMD_TAGGED;
 
 	scsi_init_cmd_errh(cmd);
 	cmd->scsi_done = scsi_mq_done;
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 89b24349269..b38bc1318a6 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -181,7 +181,7 @@ static int uas_get_tag(struct scsi_cmnd *cmnd)
 {
 	int tag;
 
-	if (blk_rq_tagged(cmnd->request))
+	if (cmnd->flags & SCMD_TAGGED)
 		tag = cmnd->request->tag + 2;
 	else
 		tag = 1;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index aac0f9ea952..6d76b8b4aa2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1136,7 +1136,6 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk)
 /*
  * tag stuff
  */
-#define blk_rq_tagged(rq)		((rq)->cmd_flags & REQ_QUEUED)
 extern int blk_queue_start_tag(struct request_queue *, struct request *);
 extern struct request *blk_queue_find_tag(struct request_queue *, int);
 extern void blk_queue_end_tag(struct request_queue *, struct request *);
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 522a5f27f55..e119142e565 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -53,6 +53,9 @@ struct scsi_pointer {
 	volatile int phase;
 };
 
+/* for scmd->flags */
+#define SCMD_TAGGED		(1 << 0)
+
 struct scsi_cmnd {
 	struct scsi_device *device;
 	struct list_head list;  /* scsi_cmnd participates in queue lists */
@@ -132,6 +135,7 @@ struct scsi_cmnd {
 					 * to be at an address < 16Mb). */
 
 	int result;		/* Status code from lower level driver */
+	int flags;		/* Command flags */
 
 	unsigned char tag;	/* SCSI-II queued command tag */
 };
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index 1712dab6e00..032df74b66d 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -101,11 +101,9 @@ static inline void scsi_deactivate_tcq(struct scsi_device *sdev, int depth)
  **/
 static inline int scsi_populate_tag_msg(struct scsi_cmnd *cmd, char *msg)
 {
-        struct request *req = cmd->request;
-
-        if (blk_rq_tagged(req)) {
+        if (cmd->flags & SCMD_TAGGED) {
 		*msg++ = MSG_SIMPLE_TAG;
-        	*msg++ = req->tag;
+        	*msg++ = cmd->request->tag;
         	return 2;
 	}
 
-- 
cgit v1.2.3-70-g09d2


From 609aa22f3be76d470a334f39cc2197112dc91bd7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 30 Oct 2014 11:54:58 +0100
Subject: scsi: remove ordered_tags scsi_device field

Remove the ordered_tags field, we haven't been issuing ordered tags based
on it since the big barrier rework in 2010.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/message/fusion/mptscsih.c    |  5 ++---
 drivers/scsi/bfa/bfad_im.c           | 11 +++--------
 drivers/scsi/mpt2sas/mpt2sas_scsih.c | 16 ++++------------
 drivers/scsi/mpt3sas/mpt3sas_scsih.c | 15 +++------------
 drivers/scsi/qla2xxx/qla_os.c        |  5 +----
 drivers/scsi/scsi.c                  | 13 ++-----------
 drivers/scsi/scsi_sysfs.c            | 13 +++++++------
 drivers/scsi/vmw_pvscsi.c            |  4 ++--
 drivers/target/loopback/tcm_loop.c   | 14 +-------------
 include/scsi/scsi_device.h           |  1 -
 include/scsi/scsi_tcq.h              |  9 ---------
 11 files changed, 25 insertions(+), 81 deletions(-)

(limited to 'include')

diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c
index e7dcb258336..00bd13dc3dc 100644
--- a/drivers/message/fusion/mptscsih.c
+++ b/drivers/message/fusion/mptscsih.c
@@ -2400,9 +2400,8 @@ mptscsih_slave_configure(struct scsi_device *sdev)
 	mptscsih_change_queue_depth(sdev, MPT_SCSI_CMD_PER_DEV_HIGH,
 				    SCSI_QDEPTH_DEFAULT);
 	dsprintk(ioc, printk(MYIOC_s_DEBUG_FMT
-		"tagged %d, simple %d, ordered %d\n",
-		ioc->name,sdev->tagged_supported, sdev->simple_tags,
-		sdev->ordered_tags));
+		"tagged %d, simple %d\n",
+		ioc->name,sdev->tagged_supported, sdev->simple_tags));
 
 	blk_queue_dma_alignment (sdev->request_queue, 512 - 1);
 
diff --git a/drivers/scsi/bfa/bfad_im.c b/drivers/scsi/bfa/bfad_im.c
index f067332bf76..99280e89c28 100644
--- a/drivers/scsi/bfa/bfad_im.c
+++ b/drivers/scsi/bfa/bfad_im.c
@@ -868,14 +868,9 @@ bfad_ramp_up_qdepth(struct bfad_itnim_s *itnim, struct scsi_device *sdev)
 			if (bfa_lun_queue_depth > tmp_sdev->queue_depth) {
 				if (tmp_sdev->id != sdev->id)
 					continue;
-				if (tmp_sdev->ordered_tags)
-					scsi_adjust_queue_depth(tmp_sdev,
-						MSG_ORDERED_TAG,
-						tmp_sdev->queue_depth + 1);
-				else
-					scsi_adjust_queue_depth(tmp_sdev,
-						MSG_SIMPLE_TAG,
-						tmp_sdev->queue_depth + 1);
+				scsi_adjust_queue_depth(tmp_sdev,
+					MSG_SIMPLE_TAG,
+					tmp_sdev->queue_depth + 1);
 
 				itnim->last_ramp_up_time = jiffies;
 			}
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index ec36b91c880..69dc166b52b 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -1246,9 +1246,9 @@ _scsih_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 
 	if (sdev->inquiry_len > 7)
 		sdev_printk(KERN_INFO, sdev, "qdepth(%d), tagged(%d), "
-		"simple(%d), ordered(%d), scsi_level(%d), cmd_que(%d)\n",
+		"simple(%d), scsi_level(%d), cmd_que(%d)\n",
 		sdev->queue_depth, sdev->tagged_supported, sdev->simple_tags,
-		sdev->ordered_tags, sdev->scsi_level,
+		sdev->scsi_level,
 		(sdev->inquiry[7] & 2) >> 1);
 
 	return sdev->queue_depth;
@@ -3944,16 +3944,8 @@ _scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 		mpi_control = MPI2_SCSIIO_CONTROL_NODATATRANSFER;
 
 	/* set tags */
-	if (!(sas_device_priv_data->flags & MPT_DEVICE_FLAGS_INIT)) {
-		if (scmd->device->tagged_supported) {
-			if (scmd->device->ordered_tags)
-				mpi_control |= MPI2_SCSIIO_CONTROL_ORDEREDQ;
-			else
-				mpi_control |= MPI2_SCSIIO_CONTROL_SIMPLEQ;
-		} else
-			mpi_control |= MPI2_SCSIIO_CONTROL_SIMPLEQ;
-	} else
-		mpi_control |= MPI2_SCSIIO_CONTROL_SIMPLEQ;
+	mpi_control |= MPI2_SCSIIO_CONTROL_SIMPLEQ;
+
 	/* Make sure Device is not raid volume.
 	 * We do not expose raid functionality to upper layer for warpdrive.
 	 */
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 52464ace282..d3abf254341 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -1114,9 +1114,9 @@ _scsih_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 
 	if (sdev->inquiry_len > 7)
 		sdev_printk(KERN_INFO, sdev, "qdepth(%d), tagged(%d), " \
-		"simple(%d), ordered(%d), scsi_level(%d), cmd_que(%d)\n",
+		"simple(%d), scsi_level(%d), cmd_que(%d)\n",
 		sdev->queue_depth, sdev->tagged_supported, sdev->simple_tags,
-		sdev->ordered_tags, sdev->scsi_level,
+		sdev->scsi_level,
 		(sdev->inquiry[7] & 2) >> 1);
 
 	return sdev->queue_depth;
@@ -3563,16 +3563,7 @@ _scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 		mpi_control = MPI2_SCSIIO_CONTROL_NODATATRANSFER;
 
 	/* set tags */
-	if (!(sas_device_priv_data->flags & MPT_DEVICE_FLAGS_INIT)) {
-		if (scmd->device->tagged_supported) {
-			if (scmd->device->ordered_tags)
-				mpi_control |= MPI2_SCSIIO_CONTROL_ORDEREDQ;
-			else
-				mpi_control |= MPI2_SCSIIO_CONTROL_SIMPLEQ;
-		} else
-			mpi_control |= MPI2_SCSIIO_CONTROL_SIMPLEQ;
-	} else
-		mpi_control |= MPI2_SCSIIO_CONTROL_SIMPLEQ;
+	mpi_control |= MPI2_SCSIIO_CONTROL_SIMPLEQ;
 
 	if ((sas_device_priv_data->flags & MPT_DEVICE_TLR_ON) &&
 	    scmd->cmd_len != 32)
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 5e755747e07..1e34fcf68e7 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1442,10 +1442,7 @@ static void qla2x00_adjust_sdev_qdepth_up(struct scsi_device *sdev, int qdepth)
 	if (req->max_q_depth <= sdev->queue_depth || req->max_q_depth < qdepth)
 		return;
 
-	if (sdev->ordered_tags)
-		scsi_adjust_queue_depth(sdev, MSG_ORDERED_TAG, qdepth);
-	else
-		scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, qdepth);
+	scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, qdepth);
 
 	ql_dbg(ql_dbg_io, vha, 0x302a,
 	    "Queue depth adjusted-up to %d for nexus=%ld:%d:%llu.\n",
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 9baeff03dd9..22c449e926f 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -789,19 +789,13 @@ void scsi_adjust_queue_depth(struct scsi_device *sdev, int tagged, int tags)
 	sdev->queue_depth = tags;
 	switch (tagged) {
 		case 0:
-			sdev->ordered_tags = 0;
 			sdev->simple_tags = 0;
 			break;
 		case MSG_ORDERED_TAG:
-			sdev->ordered_tags = 1;
-			sdev->simple_tags = 1;
-			break;
 		case MSG_SIMPLE_TAG:
-			sdev->ordered_tags = 0;
 			sdev->simple_tags = 1;
 			break;
 		default:
-			sdev->ordered_tags = 0;
 			sdev->simple_tags = 0;
 			sdev_printk(KERN_WARNING, sdev,
 				    "scsi_adjust_queue_depth, bad queue type, "
@@ -857,11 +851,8 @@ int scsi_track_queue_full(struct scsi_device *sdev, int depth)
 		scsi_adjust_queue_depth(sdev, 0, sdev->host->cmd_per_lun);
 		return -1;
 	}
-	
-	if (sdev->ordered_tags)
-		scsi_adjust_queue_depth(sdev, MSG_ORDERED_TAG, depth);
-	else
-		scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, depth);
+
+	scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, depth);
 	return depth;
 }
 EXPORT_SYMBOL(scsi_track_queue_full);
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index f4cb7b3e9e2..35d93b0af82 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -727,9 +727,7 @@ show_queue_type_field(struct device *dev, struct device_attribute *attr,
 	struct scsi_device *sdev = to_scsi_device(dev);
 	const char *name = "none";
 
-	if (sdev->ordered_tags)
-		name = "ordered";
-	else if (sdev->simple_tags)
+	if (sdev->simple_tags)
 		name = "simple";
 
 	return snprintf(buf, 20, "%s\n", name);
@@ -747,9 +745,12 @@ store_queue_type_field(struct device *dev, struct device_attribute *attr,
 	if (!sdev->tagged_supported || !sht->change_queue_type)
 		return -EINVAL;
 
-	if (strncmp(buf, "ordered", 7) == 0)
-		tag_type = MSG_ORDERED_TAG;
-	else if (strncmp(buf, "simple", 6) == 0)
+	/*
+	 * We're never issueing order tags these days, but allow the value
+	 * for backwards compatibility.
+	 */
+	if (strncmp(buf, "ordered", 7) == 0 ||
+	    strncmp(buf, "simple", 6) == 0)
 		tag_type = MSG_SIMPLE_TAG;
 	else if (strncmp(buf, "none", 4) != 0)
 		return -EINVAL;
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 598f65efaae..53a3eb6c063 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -526,9 +526,9 @@ static int pvscsi_change_queue_depth(struct scsi_device *sdev,
 
 	if (sdev->inquiry_len > 7)
 		sdev_printk(KERN_INFO, sdev,
-			    "qdepth(%d), tagged(%d), simple(%d), ordered(%d), scsi_level(%d), cmd_que(%d)\n",
+			    "qdepth(%d), tagged(%d), simple(%d), scsi_level(%d), cmd_que(%d)\n",
 			    sdev->queue_depth, sdev->tagged_supported,
-			    sdev->simple_tags, sdev->ordered_tags,
+			    sdev->simple_tags,
 			    sdev->scsi_level, (sdev->inquiry[7] & 2) >> 1);
 	return sdev->queue_depth;
 }
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 3b9c76835b4..e30932f989a 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -135,18 +135,6 @@ static int tcm_loop_change_queue_depth(
 	return sdev->queue_depth;
 }
 
-/*
- * Locate the SAM Task Attr from struct scsi_cmnd *
- */
-static int tcm_loop_sam_attr(struct scsi_cmnd *sc, int tag)
-{
-	if (sc->device->tagged_supported &&
-	    sc->device->ordered_tags && tag >= 0)
-		return MSG_ORDERED_TAG;
-
-	return MSG_SIMPLE_TAG;
-}
-
 static void tcm_loop_submission_work(struct work_struct *work)
 {
 	struct tcm_loop_cmd *tl_cmd =
@@ -205,7 +193,7 @@ static void tcm_loop_submission_work(struct work_struct *work)
 
 	rc = target_submit_cmd_map_sgls(se_cmd, tl_nexus->se_sess, sc->cmnd,
 			&tl_cmd->tl_sense_buf[0], tl_cmd->sc->device->lun,
-			transfer_length, tcm_loop_sam_attr(sc, tl_cmd->sc_cmd_tag),
+			transfer_length, MSG_SIMPLE_TAG,
 			sc->sc_data_direction, 0,
 			scsi_sglist(sc), scsi_sg_count(sc),
 			sgl_bidi, sgl_bidi_count,
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 50d47e6e89d..e8fecb5ea79 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -141,7 +141,6 @@ struct scsi_device {
 	unsigned ppr:1;		/* Device supports PPR messages */
 	unsigned tagged_supported:1;	/* Supports SCSI-II tagged queuing */
 	unsigned simple_tags:1;	/* simple queue tag messages are enabled */
-	unsigned ordered_tags:1;/* ordered queue tag messages are enabled */
 	unsigned was_reset:1;	/* There was a bus reset on the bus for 
 				 * this device */
 	unsigned expecting_cc_ua:1; /* Expecting a CHECK_CONDITION/UNIT_ATTN
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index 032df74b66d..342f38c5b06 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -21,17 +21,11 @@ int scsi_change_queue_type(struct scsi_device *sdev, int tag_type);
 /**
  * scsi_get_tag_type - get the type of tag the device supports
  * @sdev:	the scsi device
- *
- * Notes:
- *	If the drive only supports simple tags, returns MSG_SIMPLE_TAG
- *	if it supports all tag types, returns MSG_ORDERED_TAG.
  */
 static inline int scsi_get_tag_type(struct scsi_device *sdev)
 {
 	if (!sdev->tagged_supported)
 		return 0;
-	if (sdev->ordered_tags)
-		return MSG_ORDERED_TAG;
 	if (sdev->simple_tags)
 		return MSG_SIMPLE_TAG;
 	return 0;
@@ -41,15 +35,12 @@ static inline void scsi_set_tag_type(struct scsi_device *sdev, int tag)
 {
 	switch (tag) {
 	case MSG_ORDERED_TAG:
-		sdev->ordered_tags = 1;
-		/* fall through */
 	case MSG_SIMPLE_TAG:
 		sdev->simple_tags = 1;
 		break;
 	case 0:
 		/* fall through */
 	default:
-		sdev->ordered_tags = 0;
 		sdev->simple_tags = 0;
 		break;
 	}
-- 
cgit v1.2.3-70-g09d2


From abd0c533e37789ef56a73562d6d06d39897bd801 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 3 Nov 2014 14:47:07 +0100
Subject: scsi: remove ordered_tag host template field

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/scsi/hosts.c      |  1 -
 drivers/usb/storage/uas.c |  1 -
 include/scsi/scsi_host.h  | 10 ----------
 3 files changed, 12 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 06030e1ad69..8bb173e0108 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -418,7 +418,6 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	shost->cmd_per_lun = sht->cmd_per_lun;
 	shost->unchecked_isa_dma = sht->unchecked_isa_dma;
 	shost->use_clustering = sht->use_clustering;
-	shost->ordered_tag = sht->ordered_tag;
 	shost->no_write_same = sht->no_write_same;
 
 	if (shost_eh_deadline == -1 || !sht->eh_host_reset_handler)
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index b38bc1318a6..1bc5df4200a 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -817,7 +817,6 @@ static struct scsi_host_template uas_host_template = {
 	.sg_tablesize = SG_NONE,
 	.cmd_per_lun = 1,	/* until we override it */
 	.skip_settle_delay = 1,
-	.ordered_tag = 1,
 
 	/*
 	 * The uas drivers expects tags not to be bigger than the maximum
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index bb9e27815be..5b03ba9d739 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -451,11 +451,6 @@ struct scsi_host_template {
 	 */
 	unsigned skip_settle_delay:1;
 
-	/*
-	 * True if we are using ordered write support.
-	 */
-	unsigned ordered_tag:1;
-
 	/* True if the controller does not support WRITE SAME */
 	unsigned no_write_same:1;
 
@@ -670,11 +665,6 @@ struct Scsi_Host {
 	 */
 	unsigned reverse_ordering:1;
 
-	/*
-	 * Ordered write support
-	 */
-	unsigned ordered_tag:1;
-
 	/* Task mgmt function in progress */
 	unsigned tmf_in_progress:1;
 
-- 
cgit v1.2.3-70-g09d2


From 5066863337afdb0ad7323f424f7959d9f9f066da Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 30 Oct 2014 14:30:06 +0100
Subject: scsi: remove abuses of scsi_populate_tag

Unless we want to build a SPI tag message we should just check SCMD_TAGGED
instead of reverse engineering a tag type through the use of
scsi_populate_tag_msg.

Also rename the function to spi_populate_tag_msg, make it behave like the
other spi message helpers, and move it to the spi transport class.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/s390/scsi/zfcp_fc.h        | 14 +-----
 drivers/scsi/53c700.c              |  2 +-
 drivers/scsi/aic7xxx/aic79xx_osm.c |  9 ----
 drivers/scsi/aic7xxx/aic7xxx_osm.c | 10 +----
 drivers/scsi/bnx2fc/bnx2fc_io.c    | 18 ++------
 drivers/scsi/csiostor/csio_scsi.c  | 29 ++----------
 drivers/scsi/esp_scsi.c            |  2 +-
 drivers/scsi/fnic/fnic_scsi.c      | 11 +----
 drivers/scsi/ibmvscsi/ibmvfc.c     | 16 ++-----
 drivers/scsi/ipr.c                 | 34 ++------------
 drivers/scsi/lpfc/lpfc_scsi.c      | 16 +------
 drivers/scsi/pmcraid.c             | 34 ++------------
 drivers/scsi/qla2xxx/qla_iocb.c    | 92 ++------------------------------------
 drivers/scsi/qla2xxx/qla_mr.c      | 13 ------
 drivers/scsi/qla4xxx/ql4_iocb.c    | 10 -----
 drivers/scsi/scsi_transport_spi.c  | 23 ++++++++++
 drivers/scsi/tmscsim.c             | 12 +++--
 include/scsi/scsi_tcq.h            | 21 ---------
 include/scsi/scsi_transport_spi.h  |  1 +
 19 files changed, 56 insertions(+), 311 deletions(-)

(limited to 'include')

diff --git a/drivers/s390/scsi/zfcp_fc.h b/drivers/s390/scsi/zfcp_fc.h
index b1d2024ed51..df2b541c828 100644
--- a/drivers/s390/scsi/zfcp_fc.h
+++ b/drivers/s390/scsi/zfcp_fc.h
@@ -212,8 +212,6 @@ static inline
 void zfcp_fc_scsi_to_fcp(struct fcp_cmnd *fcp, struct scsi_cmnd *scsi,
 			 u8 tm_flags)
 {
-	char tag[2];
-
 	int_to_scsilun(scsi->device->lun, (struct scsi_lun *) &fcp->fc_lun);
 
 	if (unlikely(tm_flags)) {
@@ -221,17 +219,7 @@ void zfcp_fc_scsi_to_fcp(struct fcp_cmnd *fcp, struct scsi_cmnd *scsi,
 		return;
 	}
 
-	if (scsi_populate_tag_msg(scsi, tag)) {
-		switch (tag[0]) {
-		case MSG_ORDERED_TAG:
-			fcp->fc_pri_ta |= FCP_PTA_ORDERED;
-			break;
-		case MSG_SIMPLE_TAG:
-			fcp->fc_pri_ta |= FCP_PTA_SIMPLE;
-			break;
-		};
-	} else
-		fcp->fc_pri_ta = FCP_PTA_SIMPLE;
+	fcp->fc_pri_ta = FCP_PTA_SIMPLE;
 
 	if (scsi->sc_data_direction == DMA_FROM_DEVICE)
 		fcp->fc_flags |= FCP_CFL_RDDATA;
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index 5143d3213e8..1b36fd3a6e6 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -1427,7 +1427,7 @@ NCR_700_start_command(struct scsi_cmnd *SCp)
 	if((hostdata->tag_negotiated & (1<<scmd_id(SCp)))
 	   && (slot->tag != SCSI_NO_TAG && SCp->cmnd[0] != REQUEST_SENSE &&
 	       slot->flags != NCR_700_FLAG_AUTOSENSE)) {
-		count += scsi_populate_tag_msg(SCp, &hostdata->msgout[count]);
+		count += spi_populate_tag_msg(&hostdata->msgout[count], SCp);
 	}
 
 	if(hostdata->fast &&
diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c
index ed333669a7d..d3b6d68107e 100644
--- a/drivers/scsi/aic7xxx/aic79xx_osm.c
+++ b/drivers/scsi/aic7xxx/aic79xx_osm.c
@@ -1619,15 +1619,6 @@ ahd_linux_run_command(struct ahd_softc *ahd, struct ahd_linux_device *dev,
 	}
 
 	if ((dev->flags & (AHD_DEV_Q_TAGGED|AHD_DEV_Q_BASIC)) != 0) {
-		int	msg_bytes;
-		uint8_t tag_msgs[2];
-
-		msg_bytes = scsi_populate_tag_msg(cmd, tag_msgs);
-		if (msg_bytes && tag_msgs[0] != MSG_SIMPLE_TASK) {
-			hscb->control |= tag_msgs[0];
-			if (tag_msgs[0] == MSG_ORDERED_TASK)
-				dev->commands_since_idle_or_otag = 0;
-		} else
 		if (dev->commands_since_idle_or_otag == AHD_OTAG_THRESH
 		 && (dev->flags & AHD_DEV_Q_TAGGED) != 0) {
 			hscb->control |= MSG_ORDERED_TASK;
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c
index 63bae7c65c9..33a5f959e86 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c
@@ -1501,15 +1501,7 @@ ahc_linux_run_command(struct ahc_softc *ahc, struct ahc_linux_device *dev,
 	}
 
 	if ((dev->flags & (AHC_DEV_Q_TAGGED|AHC_DEV_Q_BASIC)) != 0) {
-		int	msg_bytes;
-		uint8_t tag_msgs[2];
-		
-		msg_bytes = scsi_populate_tag_msg(cmd, tag_msgs);
-		if (msg_bytes && tag_msgs[0] != MSG_SIMPLE_TASK) {
-			hscb->control |= tag_msgs[0];
-			if (tag_msgs[0] == MSG_ORDERED_TASK)
-				dev->commands_since_idle_or_otag = 0;
-		} else if (dev->commands_since_idle_or_otag == AHC_OTAG_THRESH
+		if (dev->commands_since_idle_or_otag == AHC_OTAG_THRESH
 				&& (dev->flags & AHC_DEV_Q_TAGGED) != 0) {
 			hscb->control |= MSG_ORDERED_TASK;
 			dev->commands_since_idle_or_otag = 0;
diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c
index 5b99844ef6b..4b56858c1df 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_io.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_io.c
@@ -1725,7 +1725,6 @@ void bnx2fc_build_fcp_cmnd(struct bnx2fc_cmd *io_req,
 				  struct fcp_cmnd *fcp_cmnd)
 {
 	struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
-	char tag[2];
 
 	memset(fcp_cmnd, 0, sizeof(struct fcp_cmnd));
 
@@ -1739,21 +1738,10 @@ void bnx2fc_build_fcp_cmnd(struct bnx2fc_cmd *io_req,
 	fcp_cmnd->fc_tm_flags = io_req->mp_req.tm_flags;
 	fcp_cmnd->fc_flags = io_req->io_req_flags;
 
-	if (scsi_populate_tag_msg(sc_cmd, tag)) {
-		switch (tag[0]) {
-		case HEAD_OF_QUEUE_TAG:
-			fcp_cmnd->fc_pri_ta = FCP_PTA_HEADQ;
-			break;
-		case ORDERED_QUEUE_TAG:
-			fcp_cmnd->fc_pri_ta = FCP_PTA_ORDERED;
-			break;
-		default:
-			fcp_cmnd->fc_pri_ta = FCP_PTA_SIMPLE;
-			break;
-		}
-	} else {
+	if (sc_cmd->flags & SCMD_TAGGED)
+		fcp_cmnd->fc_pri_ta = FCP_PTA_SIMPLE;
+	else
 		fcp_cmnd->fc_pri_ta = 0;
-	}
 }
 
 static void bnx2fc_parse_fcp_rsp(struct bnx2fc_cmd *io_req,
diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c
index 86103c8475d..8231505cce0 100644
--- a/drivers/scsi/csiostor/csio_scsi.c
+++ b/drivers/scsi/csiostor/csio_scsi.c
@@ -152,28 +152,6 @@ csio_scsi_itnexus_loss_error(uint16_t error)
 	return 0;
 }
 
-static inline void
-csio_scsi_tag(struct scsi_cmnd *scmnd, uint8_t *tag, uint8_t hq,
-	      uint8_t oq, uint8_t sq)
-{
-	char stag[2];
-
-	if (scsi_populate_tag_msg(scmnd, stag)) {
-		switch (stag[0]) {
-		case HEAD_OF_QUEUE_TAG:
-			*tag = hq;
-			break;
-		case ORDERED_QUEUE_TAG:
-			*tag = oq;
-			break;
-		default:
-			*tag = sq;
-			break;
-		}
-	} else
-		*tag = 0;
-}
-
 /*
  * csio_scsi_fcp_cmnd - Frame the SCSI FCP command paylod.
  * @req: IO req structure.
@@ -192,11 +170,12 @@ csio_scsi_fcp_cmnd(struct csio_ioreq *req, void *addr)
 		int_to_scsilun(scmnd->device->lun, &fcp_cmnd->fc_lun);
 		fcp_cmnd->fc_tm_flags = 0;
 		fcp_cmnd->fc_cmdref = 0;
-		fcp_cmnd->fc_pri_ta = 0;
 
 		memcpy(fcp_cmnd->fc_cdb, scmnd->cmnd, 16);
-		csio_scsi_tag(scmnd, &fcp_cmnd->fc_pri_ta,
-			      FCP_PTA_HEADQ, FCP_PTA_ORDERED, FCP_PTA_SIMPLE);
+		if (scmnd->flags & SCMD_TAGGED)
+			fcp_cmnd->fc_pri_ta = FCP_PTA_SIMPLE;
+		else
+			fcp_cmnd->fc_pri_ta = 0;
 		fcp_cmnd->fc_dl = cpu_to_be32(scsi_bufflen(scmnd));
 
 		if (req->nsge)
diff --git a/drivers/scsi/esp_scsi.c b/drivers/scsi/esp_scsi.c
index 55548dc5cec..b23101b28bf 100644
--- a/drivers/scsi/esp_scsi.c
+++ b/drivers/scsi/esp_scsi.c
@@ -663,7 +663,7 @@ static struct esp_cmd_entry *find_and_prep_issuable_command(struct esp *esp)
 			return ent;
 		}
 
-		if (!scsi_populate_tag_msg(cmd, &ent->tag[0])) {
+		if (!spi_populate_tag_msg(&ent->tag[0], cmd)) {
 			ent->tag[0] = 0;
 			ent->tag[1] = 0;
 		}
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 961bdf5d31c..10d5c6bbc9e 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -325,13 +325,11 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic,
 	struct fc_rport_libfc_priv *rp = rport->dd_data;
 	struct host_sg_desc *desc;
 	struct misc_stats *misc_stats = &fnic->fnic_stats.misc_stats;
-	u8 pri_tag = 0;
 	unsigned int i;
 	unsigned long intr_flags;
 	int flags;
 	u8 exch_flags;
 	struct scsi_lun fc_lun;
-	char msg[2];
 
 	if (sg_count) {
 		/* For each SGE, create a device desc entry */
@@ -357,12 +355,6 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic,
 
 	int_to_scsilun(sc->device->lun, &fc_lun);
 
-	pri_tag = FCPIO_ICMND_PTA_SIMPLE;
-	msg[0] = MSG_SIMPLE_TAG;
-	scsi_populate_tag_msg(sc, msg);
-	if (msg[0] == MSG_ORDERED_TAG)
-		pri_tag = FCPIO_ICMND_PTA_ORDERED;
-
 	/* Enqueue the descriptor in the Copy WQ */
 	spin_lock_irqsave(&fnic->wq_copy_lock[0], intr_flags);
 
@@ -394,7 +386,8 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic,
 					 io_req->sgl_list_pa,
 					 io_req->sense_buf_pa,
 					 0, /* scsi cmd ref, always 0 */
-					 pri_tag, /* scsi pri and tag */
+					 FCPIO_ICMND_PTA_SIMPLE,
+					 	/* scsi pri and tag */
 					 flags,	/* command flags */
 					 sc->cmnd, sc->cmd_len,
 					 scsi_bufflen(sc),
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 48d19a3256c..a964f8c8583 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -1643,19 +1643,9 @@ static int ibmvfc_queuecommand_lck(struct scsi_cmnd *cmnd,
 	int_to_scsilun(cmnd->device->lun, &vfc_cmd->iu.lun);
 	memcpy(vfc_cmd->iu.cdb, cmnd->cmnd, cmnd->cmd_len);
 
-	if (scsi_populate_tag_msg(cmnd, tag)) {
-		vfc_cmd->task_tag = cpu_to_be64(tag[1]);
-		switch (tag[0]) {
-		case MSG_SIMPLE_TAG:
-			vfc_cmd->iu.pri_task_attr = IBMVFC_SIMPLE_TASK;
-			break;
-		case MSG_HEAD_TAG:
-			vfc_cmd->iu.pri_task_attr = IBMVFC_HEAD_OF_QUEUE;
-			break;
-		case MSG_ORDERED_TAG:
-			vfc_cmd->iu.pri_task_attr = IBMVFC_ORDERED_TASK;
-			break;
-		};
+	if (cmnd->flags & SCMD_TAGGED) {
+		vfc_cmd->task_tag = cpu_to_be64(cmnd->tag);
+		vfc_cmd->iu.pri_task_attr = IBMVFC_SIMPLE_TASK;
 	}
 
 	if (likely(!(rc = ibmvfc_map_sg_data(cmnd, evt, vfc_cmd, vhost->dev))))
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 3d689f6023e..6b52feafa92 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -5658,35 +5658,6 @@ static int ipr_build_ioadl(struct ipr_ioa_cfg *ioa_cfg,
 	return 0;
 }
 
-/**
- * ipr_get_task_attributes - Translate SPI Q-Tag to task attributes
- * @scsi_cmd:	scsi command struct
- *
- * Return value:
- * 	task attributes
- **/
-static u8 ipr_get_task_attributes(struct scsi_cmnd *scsi_cmd)
-{
-	u8 tag[2];
-	u8 rc = IPR_FLAGS_LO_UNTAGGED_TASK;
-
-	if (scsi_populate_tag_msg(scsi_cmd, tag)) {
-		switch (tag[0]) {
-		case MSG_SIMPLE_TAG:
-			rc = IPR_FLAGS_LO_SIMPLE_TASK;
-			break;
-		case MSG_HEAD_TAG:
-			rc = IPR_FLAGS_LO_HEAD_OF_Q_TASK;
-			break;
-		case MSG_ORDERED_TAG:
-			rc = IPR_FLAGS_LO_ORDERED_TASK;
-			break;
-		};
-	}
-
-	return rc;
-}
-
 /**
  * ipr_erp_done - Process completion of ERP for a device
  * @ipr_cmd:		ipr command struct
@@ -6222,7 +6193,10 @@ static int ipr_queuecommand(struct Scsi_Host *shost,
 			ioarcb->cmd_pkt.flags_lo |= IPR_FLAGS_LO_DELAY_AFTER_RST;
 		}
 		ioarcb->cmd_pkt.flags_lo |= IPR_FLAGS_LO_ALIGNED_BFR;
-		ioarcb->cmd_pkt.flags_lo |= ipr_get_task_attributes(scsi_cmd);
+		if (scsi_cmd->flags & SCMD_TAGGED)
+			ioarcb->cmd_pkt.flags_lo |= IPR_FLAGS_LO_SIMPLE_TASK;
+		else
+			ioarcb->cmd_pkt.flags_lo |= IPR_FLAGS_LO_UNTAGGED_TASK;
 	}
 
 	if (scsi_cmd->cmnd[0] >= 0xC0 &&
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 2896e52ac6c..4a150063fb4 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -4266,7 +4266,6 @@ lpfc_scsi_prep_cmnd(struct lpfc_vport *vport, struct lpfc_scsi_buf *lpfc_cmd,
 	IOCB_t *iocb_cmd = &lpfc_cmd->cur_iocbq.iocb;
 	struct lpfc_iocbq *piocbq = &(lpfc_cmd->cur_iocbq);
 	int datadir = scsi_cmnd->sc_data_direction;
-	char tag[2];
 	uint8_t *ptr;
 	bool sli4;
 	uint32_t fcpdl;
@@ -4288,20 +4287,7 @@ lpfc_scsi_prep_cmnd(struct lpfc_vport *vport, struct lpfc_scsi_buf *lpfc_cmd,
 		memset(ptr, 0, (LPFC_FCP_CDB_LEN - scsi_cmnd->cmd_len));
 	}
 
-	if (scsi_populate_tag_msg(scsi_cmnd, tag)) {
-		switch (tag[0]) {
-		case HEAD_OF_QUEUE_TAG:
-			fcp_cmnd->fcpCntl1 = HEAD_OF_Q;
-			break;
-		case ORDERED_QUEUE_TAG:
-			fcp_cmnd->fcpCntl1 = ORDERED_Q;
-			break;
-		default:
-			fcp_cmnd->fcpCntl1 = SIMPLE_Q;
-			break;
-		}
-	} else
-		fcp_cmnd->fcpCntl1 = SIMPLE_Q;
+	fcp_cmnd->fcpCntl1 = SIMPLE_Q;
 
 	sli4 = (phba->sli_rev == LPFC_SLI_REV4);
 	piocbq->iocb.un.fcpi.fcpi_XRdy = 0;
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index 2233ed6b89e..d5fb31fa388 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -3168,36 +3168,6 @@ static int pmcraid_eh_host_reset_handler(struct scsi_cmnd *scmd)
 	return pmcraid_reset_bringup(pinstance) == 0 ? SUCCESS : FAILED;
 }
 
-/**
- * pmcraid_task_attributes - Translate SPI Q-Tags to task attributes
- * @scsi_cmd:   scsi command struct
- *
- * Return value
- *	  number of tags or 0 if the task is not tagged
- */
-static u8 pmcraid_task_attributes(struct scsi_cmnd *scsi_cmd)
-{
-	char tag[2];
-	u8 rc = 0;
-
-	if (scsi_populate_tag_msg(scsi_cmd, tag)) {
-		switch (tag[0]) {
-		case MSG_SIMPLE_TAG:
-			rc = TASK_TAG_SIMPLE;
-			break;
-		case MSG_HEAD_TAG:
-			rc = TASK_TAG_QUEUE_HEAD;
-			break;
-		case MSG_ORDERED_TAG:
-			rc = TASK_TAG_ORDERED;
-			break;
-		};
-	}
-
-	return rc;
-}
-
-
 /**
  * pmcraid_init_ioadls - initializes IOADL related fields in IOARCB
  * @cmd: pmcraid command struct
@@ -3553,7 +3523,9 @@ static int pmcraid_queuecommand_lck(
 		}
 
 		ioarcb->request_flags0 |= NO_LINK_DESCS;
-		ioarcb->request_flags1 |= pmcraid_task_attributes(scsi_cmd);
+
+		if (scsi_cmd->flags & SCMD_TAGGED)
+			ioarcb->request_flags1 |= TASK_TAG_SIMPLE;
 
 		if (RES_IS_GSCSI(res->cfg_entry))
 			ioarcb->request_flags1 |= DELAY_AFTER_RESET;
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index f0edb07f319..a1ab25fca87 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -325,7 +325,6 @@ qla2x00_start_scsi(srb_t *sp)
 	struct qla_hw_data *ha;
 	struct req_que *req;
 	struct rsp_que *rsp;
-	char		tag[2];
 
 	/* Setup device pointers. */
 	ret = 0;
@@ -404,26 +403,7 @@ qla2x00_start_scsi(srb_t *sp)
 	/* Set target ID and LUN number*/
 	SET_TARGET_ID(ha, cmd_pkt->target, sp->fcport->loop_id);
 	cmd_pkt->lun = cpu_to_le16(cmd->device->lun);
-
-	/* Update tagged queuing modifier */
-	if (scsi_populate_tag_msg(cmd, tag)) {
-		switch (tag[0]) {
-		case HEAD_OF_QUEUE_TAG:
-			cmd_pkt->control_flags =
-			    __constant_cpu_to_le16(CF_HEAD_TAG);
-			break;
-		case ORDERED_QUEUE_TAG:
-			cmd_pkt->control_flags =
-			    __constant_cpu_to_le16(CF_ORDERED_TAG);
-			break;
-		default:
-			cmd_pkt->control_flags =
-			    __constant_cpu_to_le16(CF_SIMPLE_TAG);
-			break;
-		}
-	} else {
-		cmd_pkt->control_flags = __constant_cpu_to_le16(CF_SIMPLE_TAG);
-	}
+	cmd_pkt->control_flags = __constant_cpu_to_le16(CF_SIMPLE_TAG);
 
 	/* Load SCSI command packet. */
 	memcpy(cmd_pkt->scsi_cdb, cmd->cmnd, cmd->cmd_len);
@@ -1264,7 +1244,6 @@ qla24xx_build_scsi_crc_2_iocbs(srb_t *sp, struct cmd_type_crc_2 *cmd_pkt,
 	uint16_t		fcp_cmnd_len;
 	struct fcp_cmnd		*fcp_cmnd;
 	dma_addr_t		crc_ctx_dma;
-	char			tag[2];
 
 	cmd = GET_CMD_SP(sp);
 
@@ -1356,25 +1335,7 @@ qla24xx_build_scsi_crc_2_iocbs(srb_t *sp, struct cmd_type_crc_2 *cmd_pkt,
 	cmd_pkt->fcp_cmnd_dseg_address[1] = cpu_to_le32(
 	    MSD(crc_ctx_dma + CRC_CONTEXT_FCPCMND_OFF));
 	fcp_cmnd->task_management = 0;
-
-	/*
-	 * Update tagged queuing modifier if using command tag queuing
-	 */
-	if (scsi_populate_tag_msg(cmd, tag)) {
-		switch (tag[0]) {
-		case HEAD_OF_QUEUE_TAG:
-		    fcp_cmnd->task_attribute = TSK_HEAD_OF_QUEUE;
-		    break;
-		case ORDERED_QUEUE_TAG:
-		    fcp_cmnd->task_attribute = TSK_ORDERED;
-		    break;
-		default:
-		    fcp_cmnd->task_attribute = TSK_SIMPLE;
-		    break;
-		}
-	} else {
-		fcp_cmnd->task_attribute = TSK_SIMPLE;
-	}
+	fcp_cmnd->task_attribute = TSK_SIMPLE;
 
 	cmd_pkt->fcp_rsp_dseg_len = 0; /* Let response come in status iocb */
 
@@ -1495,7 +1456,6 @@ qla24xx_start_scsi(srb_t *sp)
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
 	struct scsi_qla_host *vha = sp->fcport->vha;
 	struct qla_hw_data *ha = vha->hw;
-	char		tag[2];
 
 	/* Setup device pointers. */
 	ret = 0;
@@ -1578,22 +1538,7 @@ qla24xx_start_scsi(srb_t *sp)
 	int_to_scsilun(cmd->device->lun, &cmd_pkt->lun);
 	host_to_fcp_swap((uint8_t *)&cmd_pkt->lun, sizeof(cmd_pkt->lun));
 
-	/* Update tagged queuing modifier -- default is TSK_SIMPLE (0). */
-	if (scsi_populate_tag_msg(cmd, tag)) {
-		switch (tag[0]) {
-		case HEAD_OF_QUEUE_TAG:
-			cmd_pkt->task = TSK_HEAD_OF_QUEUE;
-			break;
-		case ORDERED_QUEUE_TAG:
-			cmd_pkt->task = TSK_ORDERED;
-			break;
-		default:
-		    cmd_pkt->task = TSK_SIMPLE;
-		    break;
-		}
-	} else {
-		cmd_pkt->task = TSK_SIMPLE;
-	}
+	cmd_pkt->task = TSK_SIMPLE;
 
 	/* Load SCSI command packet. */
 	memcpy(cmd_pkt->fcp_cdb, cmd->cmnd, cmd->cmd_len);
@@ -2310,7 +2255,6 @@ qla82xx_start_scsi(srb_t *sp)
 	struct qla_hw_data *ha = vha->hw;
 	struct req_que *req = NULL;
 	struct rsp_que *rsp = NULL;
-	char tag[2];
 
 	/* Setup device pointers. */
 	ret = 0;
@@ -2489,22 +2433,6 @@ sufficient_dsds:
 		else if (cmd->sc_data_direction == DMA_FROM_DEVICE)
 			ctx->fcp_cmnd->additional_cdb_len |= 2;
 
-		/*
-		 * Update tagged queuing modifier -- default is TSK_SIMPLE (0).
-		 */
-		if (scsi_populate_tag_msg(cmd, tag)) {
-			switch (tag[0]) {
-			case HEAD_OF_QUEUE_TAG:
-				ctx->fcp_cmnd->task_attribute =
-				    TSK_HEAD_OF_QUEUE;
-				break;
-			case ORDERED_QUEUE_TAG:
-				ctx->fcp_cmnd->task_attribute =
-				    TSK_ORDERED;
-				break;
-			}
-		}
-
 		/* Populate the FCP_PRIO. */
 		if (ha->flags.fcp_prio_enabled)
 			ctx->fcp_cmnd->task_attribute |=
@@ -2565,20 +2493,6 @@ sufficient_dsds:
 		host_to_fcp_swap((uint8_t *)&cmd_pkt->lun,
 		    sizeof(cmd_pkt->lun));
 
-		/*
-		 * Update tagged queuing modifier -- default is TSK_SIMPLE (0).
-		 */
-		if (scsi_populate_tag_msg(cmd, tag)) {
-			switch (tag[0]) {
-			case HEAD_OF_QUEUE_TAG:
-				cmd_pkt->task = TSK_HEAD_OF_QUEUE;
-				break;
-			case ORDERED_QUEUE_TAG:
-				cmd_pkt->task = TSK_ORDERED;
-				break;
-			}
-		}
-
 		/* Populate the FCP_PRIO. */
 		if (ha->flags.fcp_prio_enabled)
 			cmd_pkt->task |= sp->fcport->fcp_prio << 3;
diff --git a/drivers/scsi/qla2xxx/qla_mr.c b/drivers/scsi/qla2xxx/qla_mr.c
index 80867599527..6d190b4b82a 100644
--- a/drivers/scsi/qla2xxx/qla_mr.c
+++ b/drivers/scsi/qla2xxx/qla_mr.c
@@ -3086,7 +3086,6 @@ qlafx00_start_scsi(srb_t *sp)
 	struct cmd_type_7_fx00 *cmd_pkt;
 	struct cmd_type_7_fx00 lcmd_pkt;
 	struct scsi_lun llun;
-	char		tag[2];
 
 	/* Setup device pointers. */
 	ret = 0;
@@ -3157,18 +3156,6 @@ qlafx00_start_scsi(srb_t *sp)
 	host_to_adap((uint8_t *)&llun, (uint8_t *)&lcmd_pkt.lun,
 	    sizeof(lcmd_pkt.lun));
 
-	/* Update tagged queuing modifier -- default is TSK_SIMPLE (0). */
-	if (scsi_populate_tag_msg(cmd, tag)) {
-		switch (tag[0]) {
-		case HEAD_OF_QUEUE_TAG:
-			lcmd_pkt.task = TSK_HEAD_OF_QUEUE;
-			break;
-		case ORDERED_QUEUE_TAG:
-			lcmd_pkt.task = TSK_ORDERED;
-			break;
-		}
-	}
-
 	/* Load SCSI command packet. */
 	host_to_adap(cmd->cmnd, lcmd_pkt.fcp_cdb, sizeof(lcmd_pkt.fcp_cdb));
 	lcmd_pkt.byte_count = cpu_to_le32((uint32_t)scsi_bufflen(cmd));
diff --git a/drivers/scsi/qla4xxx/ql4_iocb.c b/drivers/scsi/qla4xxx/ql4_iocb.c
index 08ab6dac226..17222eb4976 100644
--- a/drivers/scsi/qla4xxx/ql4_iocb.c
+++ b/drivers/scsi/qla4xxx/ql4_iocb.c
@@ -280,7 +280,6 @@ int qla4xxx_send_command_to_isp(struct scsi_qla_host *ha, struct srb * srb)
 	uint16_t req_cnt;
 	unsigned long flags;
 	uint32_t index;
-	char tag[2];
 
 	/* Get real lun and adapter */
 	ddb_entry = srb->ddb;
@@ -352,15 +351,6 @@ int qla4xxx_send_command_to_isp(struct scsi_qla_host *ha, struct srb * srb)
 
 	/* Set tagged queueing control flags */
 	cmd_entry->control_flags |= CF_SIMPLE_TAG;
-	if (scsi_populate_tag_msg(cmd, tag))
-		switch (tag[0]) {
-		case MSG_HEAD_TAG:
-			cmd_entry->control_flags |= CF_HEAD_TAG;
-			break;
-		case MSG_ORDERED_TAG:
-			cmd_entry->control_flags |= CF_ORDERED_TAG;
-			break;
-		}
 
 	qla4xxx_advance_req_ring_ptr(ha);
 	qla4xxx_build_scsi_iocbs(srb, cmd_entry, tot_dsds);
diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c
index cf08071a9b6..fa2aece76cc 100644
--- a/drivers/scsi/scsi_transport_spi.c
+++ b/drivers/scsi/scsi_transport_spi.c
@@ -32,6 +32,7 @@
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_eh.h>
+#include <scsi/scsi_tcq.h>
 #include <scsi/scsi_transport.h>
 #include <scsi/scsi_transport_spi.h>
 
@@ -1207,6 +1208,28 @@ int spi_populate_ppr_msg(unsigned char *msg, int period, int offset,
 }
 EXPORT_SYMBOL_GPL(spi_populate_ppr_msg);
 
+/**
+ * spi_populate_tag_msg - place a tag message in a buffer
+ * @msg:	pointer to the area to place the tag
+ * @cmd:	pointer to the scsi command for the tag
+ *
+ * Notes:
+ *	designed to create the correct type of tag message for the 
+ *	particular request.  Returns the size of the tag message.
+ *	May return 0 if TCQ is disabled for this device.
+ **/
+int spi_populate_tag_msg(unsigned char *msg, struct scsi_cmnd *cmd)
+{
+        if (cmd->flags & SCMD_TAGGED) {
+		*msg++ = MSG_SIMPLE_TAG;
+        	*msg++ = cmd->request->tag;
+        	return 2;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(spi_populate_tag_msg);
+
 #ifdef CONFIG_SCSI_CONSTANTS
 static const char * const one_byte_msgs[] = {
 /* 0x00 */ "Task Complete", NULL /* Extended Message */, "Save Pointers",
diff --git a/drivers/scsi/tmscsim.c b/drivers/scsi/tmscsim.c
index 764575726c8..547812437a7 100644
--- a/drivers/scsi/tmscsim.c
+++ b/drivers/scsi/tmscsim.c
@@ -243,7 +243,6 @@
 #include <scsi/scsicam.h>
 #include <scsi/scsi_tcq.h>
 
-
 #define DC390_BANNER "Tekram DC390/AM53C974"
 #define DC390_VERSION "2.1d 2004-05-27"
 
@@ -508,7 +507,6 @@ dc390_StartSCSI( struct dc390_acb* pACB, struct dc390_dcb* pDCB, struct dc390_sr
     struct scsi_cmnd *scmd = pSRB->pcmd;
     struct scsi_device *sdev = scmd->device;
     u8 cmd, disc_allowed, try_sync_nego;
-    char tag[2];
 
     pSRB->ScsiPhase = SCSI_NOP0;
 
@@ -560,11 +558,11 @@ dc390_StartSCSI( struct dc390_acb* pACB, struct dc390_dcb* pDCB, struct dc390_sr
     cmd = SEL_W_ATN;
     DC390_write8 (ScsiFifo, IDENTIFY(disc_allowed, pDCB->TargetLUN));
     /* Change 99/05/31: Don't use tags when not disconnecting (BUSY) */
-    if ((pDCB->SyncMode & EN_TAG_QUEUEING) && disc_allowed && scsi_populate_tag_msg(scmd, tag)) {
-	DC390_write8(ScsiFifo, tag[0]);
-	pDCB->TagMask |= 1 << tag[1];
-	pSRB->TagNumber = tag[1];
-	DC390_write8(ScsiFifo, tag[1]);
+    if ((pDCB->SyncMode & EN_TAG_QUEUEING) && disc_allowed && (scmd->flags & SCMD_TAGGED)) {
+	DC390_write8(ScsiFifo, MSG_SIMPLE_TAG);
+	pDCB->TagMask |= 1 << scmd->request->tag;
+	pSRB->TagNumber = scmd->request->tag;
+	DC390_write8(ScsiFifo, scmd->request->tag);
 	DEBUG1(printk(KERN_INFO "DC390: Select w/DisCn for SRB %p, block tag %02x\n", pSRB, tag[1]));
 	cmd = SEL_W_ATN3;
     } else {
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index 342f38c5b06..005f68da5ad 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -80,27 +80,6 @@ static inline void scsi_deactivate_tcq(struct scsi_device *sdev, int depth)
 	scsi_adjust_queue_depth(sdev, 0, depth);
 }
 
-/**
- * scsi_populate_tag_msg - place a tag message in a buffer
- * @SCpnt:	pointer to the Scsi_Cmnd for the tag
- * @msg:	pointer to the area to place the tag
- *
- * Notes:
- *	designed to create the correct type of tag message for the 
- *	particular request.  Returns the size of the tag message.
- *	May return 0 if TCQ is disabled for this device.
- **/
-static inline int scsi_populate_tag_msg(struct scsi_cmnd *cmd, char *msg)
-{
-        if (cmd->flags & SCMD_TAGGED) {
-		*msg++ = MSG_SIMPLE_TAG;
-        	*msg++ = cmd->request->tag;
-        	return 2;
-	}
-
-	return 0;
-}
-
 static inline struct scsi_cmnd *scsi_mq_find_tag(struct Scsi_Host *shost,
 						 int unique_tag)
 {
diff --git a/include/scsi/scsi_transport_spi.h b/include/scsi/scsi_transport_spi.h
index 7497a383b1a..a4fa52b4d5c 100644
--- a/include/scsi/scsi_transport_spi.h
+++ b/include/scsi/scsi_transport_spi.h
@@ -157,5 +157,6 @@ int spi_populate_width_msg(unsigned char *msg, int width);
 int spi_populate_sync_msg(unsigned char *msg, int period, int offset);
 int spi_populate_ppr_msg(unsigned char *msg, int period, int offset, int width,
 		int options);
+int spi_populate_tag_msg(unsigned char *msg, struct scsi_cmnd *cmd);
 
 #endif /* SCSI_TRANSPORT_SPI_H */
-- 
cgit v1.2.3-70-g09d2


From e2eddf4d530df745019fded0fedfb78f6d3e33ca Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 4 Nov 2014 07:58:28 +0100
Subject: scsi: remove use_blk_tcq Scsi_Host field

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 include/scsi/scsi_host.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 5b03ba9d739..d6bd6529400 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -650,7 +650,6 @@ struct Scsi_Host {
 	unsigned active_mode:2;
 	unsigned unchecked_isa_dma:1;
 	unsigned use_clustering:1;
-	unsigned use_blk_tcq:1;
 
 	/*
 	 * Host has requested that no further requests come through for the
-- 
cgit v1.2.3-70-g09d2


From 2ecb204d07ac8debe3893c362415919bc78bebd6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 3 Nov 2014 14:09:02 +0100
Subject: scsi: always assign block layer tags if enabled

Allow a driver to ask for block layer tags by setting .use_blk_tags in the
host template, in which case it will always see a valid value in
request->tag, similar to the behavior when using blk-mq.  This means even
SCSI "untagged" commands will now have a tag, which is especially useful
when using a host-wide tag map.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 Documentation/scsi/scsi_mid_low_api.txt | 38 +--------------------------------
 drivers/message/fusion/mptsas.c         |  1 +
 drivers/scsi/53c700.c                   | 12 +++++------
 drivers/scsi/aic7xxx/aic79xx_osm.c      | 11 +++++-----
 drivers/scsi/aic7xxx/aic7xxx_osm.c      | 11 +++++-----
 drivers/scsi/aic94xx/aic94xx_init.c     |  1 +
 drivers/scsi/bfa/bfad_im.c              |  8 +++----
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c       |  1 +
 drivers/scsi/csiostor/csio_scsi.c       |  8 +++----
 drivers/scsi/esas2r/esas2r_main.c       | 12 +++++------
 drivers/scsi/esp_scsi.c                 |  6 +++---
 drivers/scsi/fcoe/fcoe.c                |  1 +
 drivers/scsi/fnic/fnic_main.c           |  3 ++-
 drivers/scsi/ibmvscsi/ibmvfc.c          | 11 +++++-----
 drivers/scsi/ipr.c                      |  1 +
 drivers/scsi/isci/init.c                |  1 +
 drivers/scsi/libfc/fc_fcp.c             |  7 +-----
 drivers/scsi/libsas/sas_scsi_host.c     | 11 +++-------
 drivers/scsi/lpfc/lpfc_scsi.c           |  7 +++---
 drivers/scsi/mvsas/mv_init.c            |  1 +
 drivers/scsi/pm8001/pm8001_init.c       |  1 +
 drivers/scsi/pmcraid.c                  |  4 ++--
 drivers/scsi/qla2xxx/qla_os.c           |  6 ++----
 drivers/scsi/qla4xxx/ql4_os.c           | 10 ++-------
 drivers/scsi/scsi.c                     | 12 ++++-------
 drivers/scsi/scsi_scan.c                |  6 ++++++
 drivers/scsi/stex.c                     | 10 ++-------
 drivers/scsi/tmscsim.c                  |  3 ++-
 drivers/scsi/ufs/ufshcd.c               |  5 +++--
 drivers/target/loopback/tcm_loop.c      |  2 +-
 drivers/usb/storage/uas.c               |  4 ++--
 include/scsi/scsi_host.h                |  5 +++++
 include/scsi/scsi_tcq.h                 | 34 -----------------------------
 33 files changed, 86 insertions(+), 168 deletions(-)

(limited to 'include')

diff --git a/Documentation/scsi/scsi_mid_low_api.txt b/Documentation/scsi/scsi_mid_low_api.txt
index d6a9bdeee7f..a6719420958 100644
--- a/Documentation/scsi/scsi_mid_low_api.txt
+++ b/Documentation/scsi/scsi_mid_low_api.txt
@@ -366,13 +366,11 @@ is initialized. The functions below are listed alphabetically and their
 names all start with "scsi_".
 
 Summary:
-   scsi_activate_tcq - turn on tag command queueing
    scsi_add_device - creates new scsi device (lu) instance
    scsi_add_host - perform sysfs registration and set up transport class
    scsi_adjust_queue_depth - change the queue depth on a SCSI device
    scsi_bios_ptable - return copy of block device's partition table
    scsi_block_requests - prevent further commands being queued to given host
-   scsi_deactivate_tcq - turn off tag command queueing
    scsi_host_alloc - return a new scsi_host instance whose refcount==1
    scsi_host_get - increments Scsi_Host instance's refcount
    scsi_host_put - decrements Scsi_Host instance's refcount (free if 0)
@@ -389,24 +387,6 @@ Summary:
 
 Details:
 
-/**
- * scsi_activate_tcq - turn on tag command queueing ("ordered" task attribute)
- * @sdev:       device to turn on TCQ for
- * @depth:      queue depth
- *
- *      Returns nothing
- *
- *      Might block: no
- *
- *      Notes: Eventually, it is hoped depth would be the maximum depth
- *      the device could cope with and the real queue depth
- *      would be adjustable from 0 to depth.
- *
- *      Defined (inline) in: include/scsi/scsi_tcq.h
- **/
-void scsi_activate_tcq(struct scsi_device *sdev, int depth)
-
-
 /**
  * scsi_add_device - creates new scsi device (lu) instance
  * @shost:   pointer to scsi host instance
@@ -471,9 +451,7 @@ int scsi_add_host(struct Scsi_Host *shost, struct device * dev)
  *
  *      Notes: Can be invoked any time on a SCSI device controlled by this
  *      LLD. [Specifically during and after slave_configure() and prior to
- *      slave_destroy().] Can safely be invoked from interrupt code. Actual
- *      queue depth change may be delayed until the next command is being
- *      processed. See also scsi_activate_tcq() and scsi_deactivate_tcq().
+ *      slave_destroy().] Can safely be invoked from interrupt code.
  *
  *      Defined in: drivers/scsi/scsi.c [see source code for more notes]
  *
@@ -514,20 +492,6 @@ unsigned char *scsi_bios_ptable(struct block_device *dev)
 void scsi_block_requests(struct Scsi_Host * shost)
 
 
-/**
- * scsi_deactivate_tcq - turn off tag command queueing
- * @sdev:       device to turn off TCQ for
- * @depth:      queue depth (stored in sdev)
- *
- *      Returns nothing
- *
- *      Might block: no
- *
- *      Defined (inline) in: include/scsi/scsi_tcq.h
- **/
-void scsi_deactivate_tcq(struct scsi_device *sdev, int depth)
-
-
 /**
  * scsi_host_alloc - create a scsi host adapter instance and perform basic
  *                   initialization.
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index 0707fa2c701..5bdaae15a74 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -1994,6 +1994,7 @@ static struct scsi_host_template mptsas_driver_template = {
 	.cmd_per_lun			= 7,
 	.use_clustering			= ENABLE_CLUSTERING,
 	.shost_attrs			= mptscsih_host_attrs,
+	.use_blk_tags			= 1,
 };
 
 static int mptsas_get_linkerrors(struct sas_phy *phy)
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index 1b36fd3a6e6..497cbb1efd4 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -327,6 +327,7 @@ NCR_700_detect(struct scsi_host_template *tpnt,
 	tpnt->slave_alloc = NCR_700_slave_alloc;
 	tpnt->change_queue_depth = NCR_700_change_queue_depth;
 	tpnt->change_queue_type = NCR_700_change_queue_type;
+	tpnt->use_blk_tags = 1;
 
 	if(tpnt->name == NULL)
 		tpnt->name = "53c700";
@@ -902,7 +903,7 @@ process_message(struct Scsi_Host *host,	struct NCR_700_Host_Parameters *hostdata
 			NCR_700_set_tag_neg_state(SCp->device, NCR_700_FINISHED_TAG_NEGOTIATION);
 			hostdata->tag_negotiated &= ~(1<<scmd_id(SCp));
 			SCp->device->tagged_supported = 0;
-			scsi_deactivate_tcq(SCp->device, host->cmd_per_lun);
+			scsi_adjust_queue_depth(SCp->device, 0, host->cmd_per_lun);
 		} else {
 			shost_printk(KERN_WARNING, host,
 				"(%d:%d) Unexpected REJECT Message %s\n",
@@ -2049,8 +2050,7 @@ NCR_700_slave_configure(struct scsi_device *SDp)
 
 	/* to do here: allocate memory; build a queue_full list */
 	if(SDp->tagged_supported) {
-		scsi_set_tag_type(SDp, MSG_ORDERED_TAG);
-		scsi_activate_tcq(SDp, NCR_700_DEFAULT_TAGS);
+		scsi_adjust_queue_depth(SDp, MSG_ORDERED_TAG, NCR_700_DEFAULT_TAGS);
 		NCR_700_set_tag_neg_state(SDp, NCR_700_START_TAG_NEGOTIATION);
 	} else {
 		/* initialise to default depth */
@@ -2094,8 +2094,6 @@ static int NCR_700_change_queue_type(struct scsi_device *SDp, int tag_type)
 	struct NCR_700_Host_Parameters *hostdata = 
 		(struct NCR_700_Host_Parameters *)SDp->host->hostdata[0];
 
-	scsi_set_tag_type(SDp, tag_type);
-
 	/* We have a global (per target) flag to track whether TCQ is
 	 * enabled, so we'll be turning it off for the entire target here.
 	 * our tag algorithm will fail if we mix tagged and untagged commands,
@@ -2106,12 +2104,12 @@ static int NCR_700_change_queue_type(struct scsi_device *SDp, int tag_type)
 	if (!tag_type) {
 		/* shift back to the default unqueued number of commands
 		 * (the user can still raise this) */
-		scsi_deactivate_tcq(SDp, SDp->host->cmd_per_lun);
+		scsi_adjust_queue_depth(SDp, 0, SDp->host->cmd_per_lun);
 		hostdata->tag_negotiated &= ~(1 << sdev_id(SDp));
 	} else {
 		/* Here, we cleared the negotiation flag above, so this
 		 * will force the driver to renegotiate */
-		scsi_activate_tcq(SDp, SDp->queue_depth);
+		scsi_adjust_queue_depth(SDp, tag_type, SDp->queue_depth);
 		if (change_tag)
 			NCR_700_set_tag_neg_state(SDp, NCR_700_START_TAG_NEGOTIATION);
 	}
diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c
index d3b6d68107e..9fd6b5618b2 100644
--- a/drivers/scsi/aic7xxx/aic79xx_osm.c
+++ b/drivers/scsi/aic7xxx/aic79xx_osm.c
@@ -925,6 +925,7 @@ struct scsi_host_template aic79xx_driver_template = {
 	.slave_configure	= ahd_linux_slave_configure,
 	.target_alloc		= ahd_linux_target_alloc,
 	.target_destroy		= ahd_linux_target_destroy,
+	.use_blk_tags		= 1,
 };
 
 /******************************** Bus DMA *************************************/
@@ -1468,12 +1469,12 @@ ahd_platform_set_tags(struct ahd_softc *ahd, struct scsi_device *sdev,
 
 	switch ((dev->flags & (AHD_DEV_Q_BASIC|AHD_DEV_Q_TAGGED))) {
 	case AHD_DEV_Q_BASIC:
-		scsi_set_tag_type(sdev, MSG_SIMPLE_TASK);
-		scsi_activate_tcq(sdev, dev->openings + dev->active);
+		scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TASK,
+				dev->openings + dev->active);
 		break;
 	case AHD_DEV_Q_TAGGED:
-		scsi_set_tag_type(sdev, MSG_ORDERED_TASK);
-		scsi_activate_tcq(sdev, dev->openings + dev->active);
+		scsi_adjust_queue_depth(sdev, MSG_ORDERED_TASK,
+				dev->openings + dev->active);
 		break;
 	default:
 		/*
@@ -1482,7 +1483,7 @@ ahd_platform_set_tags(struct ahd_softc *ahd, struct scsi_device *sdev,
 		 * serially on the controller/device.  This should
 		 * remove some latency.
 		 */
-		scsi_deactivate_tcq(sdev, 1);
+		scsi_adjust_queue_depth(sdev, 0, 1);
 		break;
 	}
 }
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c
index 33a5f959e86..f18b6d69d3f 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c
@@ -812,6 +812,7 @@ struct scsi_host_template aic7xxx_driver_template = {
 	.slave_configure	= ahc_linux_slave_configure,
 	.target_alloc		= ahc_linux_target_alloc,
 	.target_destroy		= ahc_linux_target_destroy,
+	.use_blk_tags		= 1,
 };
 
 /**************************** Tasklet Handler *********************************/
@@ -1334,12 +1335,12 @@ ahc_platform_set_tags(struct ahc_softc *ahc, struct scsi_device *sdev,
 	}
 	switch ((dev->flags & (AHC_DEV_Q_BASIC|AHC_DEV_Q_TAGGED))) {
 	case AHC_DEV_Q_BASIC:
-		scsi_set_tag_type(sdev, MSG_SIMPLE_TAG);
-		scsi_activate_tcq(sdev, dev->openings + dev->active);
+		scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TASK,
+				dev->openings + dev->active);
 		break;
 	case AHC_DEV_Q_TAGGED:
-		scsi_set_tag_type(sdev, MSG_ORDERED_TAG);
-		scsi_activate_tcq(sdev, dev->openings + dev->active);
+		scsi_adjust_queue_depth(sdev, MSG_ORDERED_TASK,
+				dev->openings + dev->active);
 		break;
 	default:
 		/*
@@ -1348,7 +1349,7 @@ ahc_platform_set_tags(struct ahc_softc *ahc, struct scsi_device *sdev,
 		 * serially on the controller/device.  This should
 		 * remove some latency.
 		 */
-		scsi_deactivate_tcq(sdev, 2);
+		scsi_adjust_queue_depth(sdev, 0, 2);
 		break;
 	}
 }
diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c
index c56741fc4b9..579dc2f460c 100644
--- a/drivers/scsi/aic94xx/aic94xx_init.c
+++ b/drivers/scsi/aic94xx/aic94xx_init.c
@@ -83,6 +83,7 @@ static struct scsi_host_template aic94xx_sht = {
 	.eh_bus_reset_handler	= sas_eh_bus_reset_handler,
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
+	.use_blk_tags		= 1,
 };
 
 static int asd_map_memio(struct asd_ha_struct *asd_ha)
diff --git a/drivers/scsi/bfa/bfad_im.c b/drivers/scsi/bfa/bfad_im.c
index 99280e89c28..d8e43c81d19 100644
--- a/drivers/scsi/bfa/bfad_im.c
+++ b/drivers/scsi/bfa/bfad_im.c
@@ -776,11 +776,7 @@ bfad_thread_workq(struct bfad_s *bfad)
 static int
 bfad_im_slave_configure(struct scsi_device *sdev)
 {
-	if (sdev->tagged_supported)
-		scsi_activate_tcq(sdev, bfa_lun_queue_depth);
-	else
-		scsi_deactivate_tcq(sdev, bfa_lun_queue_depth);
-
+	scsi_adjust_queue_depth(sdev, 0, bfa_lun_queue_depth);
 	return 0;
 }
 
@@ -804,6 +800,7 @@ struct scsi_host_template bfad_im_scsi_host_template = {
 	.shost_attrs = bfad_im_host_attrs,
 	.max_sectors = BFAD_MAX_SECTORS,
 	.vendor_id = BFA_PCI_VENDOR_ID_BROCADE,
+	.use_blk_tags = 1,
 };
 
 struct scsi_host_template bfad_im_vport_template = {
@@ -825,6 +822,7 @@ struct scsi_host_template bfad_im_vport_template = {
 	.use_clustering = ENABLE_CLUSTERING,
 	.shost_attrs = bfad_im_vport_attrs,
 	.max_sectors = BFAD_MAX_SECTORS,
+	.use_blk_tags = 1,
 };
 
 bfa_status_t
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 3c6dc8abc77..cd2e6102592 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -2790,6 +2790,7 @@ static struct scsi_host_template bnx2fc_shost_template = {
 	.use_clustering		= ENABLE_CLUSTERING,
 	.sg_tablesize		= BNX2FC_MAX_BDS_PER_CMD,
 	.max_sectors		= 1024,
+	.use_blk_tags		= 1,
 };
 
 static struct libfc_function_template bnx2fc_libfc_fcn_templ = {
diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c
index 8231505cce0..f73155db80a 100644
--- a/drivers/scsi/csiostor/csio_scsi.c
+++ b/drivers/scsi/csiostor/csio_scsi.c
@@ -2241,11 +2241,7 @@ csio_slave_alloc(struct scsi_device *sdev)
 static int
 csio_slave_configure(struct scsi_device *sdev)
 {
-	if (sdev->tagged_supported)
-		scsi_activate_tcq(sdev, csio_lun_qdepth);
-	else
-		scsi_deactivate_tcq(sdev, csio_lun_qdepth);
-
+	scsi_adjust_queue_depth(sdev, 0, csio_lun_qdepth);
 	return 0;
 }
 
@@ -2290,6 +2286,7 @@ struct scsi_host_template csio_fcoe_shost_template = {
 	.use_clustering		= ENABLE_CLUSTERING,
 	.shost_attrs		= csio_fcoe_lport_attrs,
 	.max_sectors		= CSIO_MAX_SECTOR_SIZE,
+	.use_blk_tags		= 1,
 };
 
 struct scsi_host_template csio_fcoe_shost_vport_template = {
@@ -2309,6 +2306,7 @@ struct scsi_host_template csio_fcoe_shost_vport_template = {
 	.use_clustering		= ENABLE_CLUSTERING,
 	.shost_attrs		= csio_fcoe_vport_attrs,
 	.max_sectors		= CSIO_MAX_SECTOR_SIZE,
+	.use_blk_tags		= 1,
 };
 
 /*
diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c
index be09c628d03..a020b09ba34 100644
--- a/drivers/scsi/esas2r/esas2r_main.c
+++ b/drivers/scsi/esas2r/esas2r_main.c
@@ -260,6 +260,7 @@ static struct scsi_host_template driver_template = {
 	.change_queue_depth		= esas2r_change_queue_depth,
 	.change_queue_type		= scsi_change_queue_type,
 	.max_sectors			= 0xFFFF,
+	.use_blk_tags			= 1,
 };
 
 int sgl_page_size = 512;
@@ -1278,13 +1279,10 @@ int esas2r_slave_configure(struct scsi_device *dev)
 	esas2r_log_dev(ESAS2R_LOG_INFO, &(dev->sdev_gendev),
 		       "esas2r_slave_configure()");
 
-	if (dev->tagged_supported) {
-		scsi_set_tag_type(dev, MSG_SIMPLE_TAG);
-		scsi_activate_tcq(dev, cmd_per_lun);
-	} else {
-		scsi_set_tag_type(dev, 0);
-		scsi_deactivate_tcq(dev, cmd_per_lun);
-	}
+	if (dev->tagged_supported)
+		scsi_adjust_queue_depth(dev, MSG_SIMPLE_TAG, cmd_per_lun);
+	else
+		scsi_adjust_queue_depth(dev, 0, cmd_per_lun);
 
 	return 0;
 }
diff --git a/drivers/scsi/esp_scsi.c b/drivers/scsi/esp_scsi.c
index b23101b28bf..66b6ce10b25 100644
--- a/drivers/scsi/esp_scsi.c
+++ b/drivers/scsi/esp_scsi.c
@@ -2419,10 +2419,9 @@ static int esp_slave_configure(struct scsi_device *dev)
 		queue_depth = dev->host->cmd_per_lun;
 
 	if (goal_tags) {
-		scsi_set_tag_type(dev, MSG_ORDERED_TAG);
-		scsi_activate_tcq(dev, queue_depth);
+		scsi_adjust_queue_depth(dev, MSG_ORDERED_TAG, queue_depth);
 	} else {
-		scsi_deactivate_tcq(dev, queue_depth);
+		scsi_adjust_queue_depth(dev, 0, queue_depth);
 	}
 	tp->flags |= ESP_TGT_DISCONNECT;
 
@@ -2631,6 +2630,7 @@ struct scsi_host_template scsi_esp_template = {
 	.use_clustering		= ENABLE_CLUSTERING,
 	.max_sectors		= 0xffff,
 	.skip_settle_delay	= 1,
+	.use_blk_tags		= 1,
 };
 EXPORT_SYMBOL(scsi_esp_template);
 
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 86956cc3448..a3eeb684249 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -288,6 +288,7 @@ static struct scsi_host_template fcoe_shost_template = {
 	.use_clustering = ENABLE_CLUSTERING,
 	.sg_tablesize = SG_ALL,
 	.max_sectors = 0xffff,
+	.use_blk_tags = 1,
 };
 
 /**
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index 8581ce662cf..2a6c98b7d4d 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -100,7 +100,7 @@ static int fnic_slave_alloc(struct scsi_device *sdev)
 	if (!rport || fc_remote_port_chkready(rport))
 		return -ENXIO;
 
-	scsi_activate_tcq(sdev, fnic_max_qdepth);
+	scsi_adjust_queue_depth(sdev, 0, fnic_max_qdepth);
 	return 0;
 }
 
@@ -121,6 +121,7 @@ static struct scsi_host_template fnic_host_template = {
 	.sg_tablesize = FNIC_MAX_SG_DESC_CNT,
 	.max_sectors = 0xffff,
 	.shost_attrs = fnic_attrs,
+	.use_blk_tags = 1,
 };
 
 static void
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index a964f8c8583..4723d89df5a 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -2888,11 +2888,11 @@ static int ibmvfc_slave_configure(struct scsi_device *sdev)
 	if (sdev->type == TYPE_DISK)
 		sdev->allow_restart = 1;
 
-	if (sdev->tagged_supported) {
-		scsi_set_tag_type(sdev, MSG_SIMPLE_TAG);
-		scsi_activate_tcq(sdev, sdev->queue_depth);
-	} else
-		scsi_deactivate_tcq(sdev, sdev->queue_depth);
+	if (sdev->tagged_supported)
+		scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG,
+				sdev->queue_depth);
+	else
+		scsi_adjust_queue_depth(sdev, 0, sdev->queue_depth);
 	spin_unlock_irqrestore(shost->host_lock, flags);
 	return 0;
 }
@@ -3108,6 +3108,7 @@ static struct scsi_host_template driver_template = {
 	.max_sectors = IBMVFC_MAX_SECTORS,
 	.use_clustering = ENABLE_CLUSTERING,
 	.shost_attrs = ibmvfc_attrs,
+	.use_blk_tags = 1,
 };
 
 /**
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 6b52feafa92..f84fcb9a6ed 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -6317,6 +6317,7 @@ static struct scsi_host_template driver_template = {
 	.sdev_attrs = ipr_dev_attrs,
 	.proc_name = IPR_NAME,
 	.no_write_same = 1,
+	.use_blk_tags = 1,
 };
 
 /**
diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c
index 2e890b1e252..89756205601 100644
--- a/drivers/scsi/isci/init.c
+++ b/drivers/scsi/isci/init.c
@@ -172,6 +172,7 @@ static struct scsi_host_template isci_sht = {
 	.target_destroy			= sas_target_destroy,
 	.ioctl				= sas_ioctl,
 	.shost_attrs			= isci_host_attrs,
+	.use_blk_tags			= 1,
 };
 
 static struct sas_domain_function_template isci_transport_ops  = {
diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index f3043ad1f35..d4bb642f268 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -2160,12 +2160,7 @@ int fc_slave_alloc(struct scsi_device *sdev)
 	if (!rport || fc_remote_port_chkready(rport))
 		return -ENXIO;
 
-	if (sdev->tagged_supported)
-		scsi_activate_tcq(sdev, FC_FCP_DFLT_QUEUE_DEPTH);
-	else
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev),
-					FC_FCP_DFLT_QUEUE_DEPTH);
-
+	scsi_adjust_queue_depth(sdev, 0, FC_FCP_DFLT_QUEUE_DEPTH);
 	return 0;
 }
 EXPORT_SYMBOL(fc_slave_alloc);
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 24e477d2ea7..eee21a060d9 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -940,15 +940,13 @@ int sas_slave_configure(struct scsi_device *scsi_dev)
 	sas_read_port_mode_page(scsi_dev);
 
 	if (scsi_dev->tagged_supported) {
-		scsi_set_tag_type(scsi_dev, MSG_SIMPLE_TAG);
-		scsi_activate_tcq(scsi_dev, SAS_DEF_QD);
+		scsi_adjust_queue_depth(scsi_dev, MSG_SIMPLE_TAG, SAS_DEF_QD);
 	} else {
 		SAS_DPRINTK("device %llx, LUN %llx doesn't support "
 			    "TCQ\n", SAS_ADDR(dev->sas_addr),
 			    scsi_dev->lun);
 		scsi_dev->tagged_supported = 0;
-		scsi_set_tag_type(scsi_dev, 0);
-		scsi_deactivate_tcq(scsi_dev, 1);
+		scsi_adjust_queue_depth(scsi_dev, 0, 1);
 	}
 
 	scsi_dev->allow_restart = 1;
@@ -991,10 +989,7 @@ int sas_change_queue_type(struct scsi_device *scsi_dev, int qt)
 	if (!scsi_dev->tagged_supported)
 		return 0;
 
-	scsi_deactivate_tcq(scsi_dev, 1);
-
-	scsi_set_tag_type(scsi_dev, qt);
-	scsi_activate_tcq(scsi_dev, scsi_dev->queue_depth);
+	scsi_adjust_queue_depth(scsi_dev, qt, scsi_dev->queue_depth);
 
 	return qt;
 }
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 4a150063fb4..a24106a7096 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -5598,10 +5598,7 @@ lpfc_slave_configure(struct scsi_device *sdev)
 	struct lpfc_vport *vport = (struct lpfc_vport *) sdev->host->hostdata;
 	struct lpfc_hba   *phba = vport->phba;
 
-	if (sdev->tagged_supported)
-		scsi_activate_tcq(sdev, vport->cfg_lun_queue_depth);
-	else
-		scsi_deactivate_tcq(sdev, vport->cfg_lun_queue_depth);
+	scsi_adjust_queue_depth(sdev, 0, vport->cfg_lun_queue_depth);
 
 	if (phba->cfg_poll & ENABLE_FCP_RING_POLLING) {
 		lpfc_sli_handle_fast_ring_event(phba,
@@ -5986,6 +5983,7 @@ struct scsi_host_template lpfc_template = {
 	.vendor_id		= LPFC_NL_VENDOR_ID,
 	.change_queue_depth	= lpfc_change_queue_depth,
 	.change_queue_type	= scsi_change_queue_type,
+	.use_blk_tags		= 1,
 };
 
 struct scsi_host_template lpfc_vport_template = {
@@ -6009,4 +6007,5 @@ struct scsi_host_template lpfc_vport_template = {
 	.max_sectors		= 0xFFFF,
 	.change_queue_depth	= lpfc_change_queue_depth,
 	.change_queue_type	= scsi_change_queue_type,
+	.use_blk_tags		= 1,
 };
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index eacee48a955..d3c1fa5e76f 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -76,6 +76,7 @@ static struct scsi_host_template mvs_sht = {
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
 	.shost_attrs		= mvst_host_attrs,
+	.use_blk_tags		= 1,
 };
 
 static struct sas_domain_function_template mvs_transport_ops = {
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index 666bf5af06e..3ff759a3b74 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -89,6 +89,7 @@ static struct scsi_host_template pm8001_sht = {
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
 	.shost_attrs		= pm8001_host_attrs,
+	.use_blk_tags		= 1,
 };
 
 /**
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index d5fb31fa388..71f9f59b13c 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -251,7 +251,6 @@ static int pmcraid_slave_configure(struct scsi_device *scsi_dev)
 
 	if (scsi_dev->tagged_supported &&
 	    (RES_IS_GSCSI(res->cfg_entry) || RES_IS_VSET(res->cfg_entry))) {
-		scsi_activate_tcq(scsi_dev, scsi_dev->queue_depth);
 		scsi_adjust_queue_depth(scsi_dev, MSG_SIMPLE_TAG,
 					scsi_dev->host->cmd_per_lun);
 	} else {
@@ -4295,7 +4294,8 @@ static struct scsi_host_template pmcraid_host_template = {
 	.cmd_per_lun = PMCRAID_MAX_CMD_PER_LUN,
 	.use_clustering = ENABLE_CLUSTERING,
 	.shost_attrs = pmcraid_host_attrs,
-	.proc_name = PMCRAID_DRIVER_NAME
+	.proc_name = PMCRAID_DRIVER_NAME,
+	.use_blk_tags = 1,
 };
 
 /*
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 1e34fcf68e7..eb0465305f8 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -269,6 +269,7 @@ struct scsi_host_template qla2xxx_driver_template = {
 	.shost_attrs		= qla2x00_host_attrs,
 
 	.supported_mode		= MODE_INITIATOR,
+	.use_blk_tags		= 1,
 };
 
 static struct scsi_transport_template *qla2xxx_transport_template = NULL;
@@ -1404,10 +1405,7 @@ qla2xxx_slave_configure(struct scsi_device *sdev)
 	if (IS_T10_PI_CAPABLE(vha->hw))
 		blk_queue_update_dma_alignment(sdev->request_queue, 0x7);
 
-	if (sdev->tagged_supported)
-		scsi_activate_tcq(sdev, req->max_q_depth);
-	else
-		scsi_deactivate_tcq(sdev, req->max_q_depth);
+	scsi_adjust_queue_depth(sdev, 0, req->max_q_depth);
 	return 0;
 }
 
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 199fcf79a05..f3119c144e2 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -163,7 +163,6 @@ static int qla4xxx_eh_target_reset(struct scsi_cmnd *cmd);
 static int qla4xxx_eh_host_reset(struct scsi_cmnd *cmd);
 static int qla4xxx_slave_alloc(struct scsi_device *device);
 static int qla4xxx_slave_configure(struct scsi_device *device);
-static void qla4xxx_slave_destroy(struct scsi_device *sdev);
 static umode_t qla4_attr_is_visible(int param_type, int param);
 static int qla4xxx_host_reset(struct Scsi_Host *shost, int reset_type);
 static int qla4xxx_change_queue_depth(struct scsi_device *sdev, int qdepth,
@@ -206,7 +205,6 @@ static struct scsi_host_template qla4xxx_driver_template = {
 
 	.slave_configure	= qla4xxx_slave_configure,
 	.slave_alloc		= qla4xxx_slave_alloc,
-	.slave_destroy		= qla4xxx_slave_destroy,
 	.change_queue_depth	= qla4xxx_change_queue_depth,
 
 	.this_id		= -1,
@@ -218,6 +216,7 @@ static struct scsi_host_template qla4xxx_driver_template = {
 	.shost_attrs		= qla4xxx_host_attrs,
 	.host_reset		= qla4xxx_host_reset,
 	.vendor_id		= SCSI_NL_VID_TYPE_PCI | PCI_VENDOR_ID_QLOGIC,
+	.use_blk_tags		= 1,
 };
 
 static struct iscsi_transport qla4xxx_iscsi_transport = {
@@ -9065,7 +9064,7 @@ static int qla4xxx_slave_alloc(struct scsi_device *sdev)
 	if (ql4xmaxqdepth != 0 && ql4xmaxqdepth <= 0xffffU)
 		queue_depth = ql4xmaxqdepth;
 
-	scsi_activate_tcq(sdev, queue_depth);
+	scsi_adjust_queue_depth(sdev, 0, queue_depth);
 	return 0;
 }
 
@@ -9075,11 +9074,6 @@ static int qla4xxx_slave_configure(struct scsi_device *sdev)
 	return 0;
 }
 
-static void qla4xxx_slave_destroy(struct scsi_device *sdev)
-{
-	scsi_deactivate_tcq(sdev, 1);
-}
-
 static int qla4xxx_change_queue_depth(struct scsi_device *sdev, int qdepth,
 				      int reason)
 {
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 22c449e926f..a3426f1bf0d 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -864,16 +864,12 @@ EXPORT_SYMBOL(scsi_track_queue_full);
  */
 int scsi_change_queue_type(struct scsi_device *sdev, int tag_type)
 {
-	if (sdev->tagged_supported) {
-		scsi_set_tag_type(sdev, tag_type);
-		if (tag_type)
-			scsi_activate_tcq(sdev, sdev->queue_depth);
-		else
-			scsi_deactivate_tcq(sdev, sdev->queue_depth);
-	} else
-		tag_type = 0;
+	if (!sdev->tagged_supported)
+		return 0;
 
+	scsi_adjust_queue_depth(sdev, tag_type, sdev->queue_depth);
 	return tag_type;
+
 }
 EXPORT_SYMBOL(scsi_change_queue_type);
 
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index b1aa1646012..408891cb14f 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -286,6 +286,12 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	}
 	WARN_ON_ONCE(!blk_get_queue(sdev->request_queue));
 	sdev->request_queue->queuedata = sdev;
+
+	if (!shost_use_blk_mq(sdev->host) &&
+	    (shost->bqt || shost->hostt->use_blk_tags)) {
+		blk_queue_init_tags(sdev->request_queue,
+				    sdev->host->cmd_per_lun, shost->bqt);
+	}
 	scsi_adjust_queue_depth(sdev, 0, sdev->host->cmd_per_lun);
 
 	scsi_sysfs_device_initialize(sdev);
diff --git a/drivers/scsi/stex.c b/drivers/scsi/stex.c
index 713af13b858..b5eae4f6ba4 100644
--- a/drivers/scsi/stex.c
+++ b/drivers/scsi/stex.c
@@ -549,7 +549,7 @@ stex_slave_alloc(struct scsi_device *sdev)
 	/* Cheat: usually extracted from Inquiry data */
 	sdev->tagged_supported = 1;
 
-	scsi_activate_tcq(sdev, sdev->host->can_queue);
+	scsi_adjust_queue_depth(sdev, 0, sdev->host->can_queue);
 
 	return 0;
 }
@@ -565,12 +565,6 @@ stex_slave_config(struct scsi_device *sdev)
 	return 0;
 }
 
-static void
-stex_slave_destroy(struct scsi_device *sdev)
-{
-	scsi_deactivate_tcq(sdev, 1);
-}
-
 static int
 stex_queuecommand_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
 {
@@ -1390,10 +1384,10 @@ static struct scsi_host_template driver_template = {
 	.queuecommand			= stex_queuecommand,
 	.slave_alloc			= stex_slave_alloc,
 	.slave_configure		= stex_slave_config,
-	.slave_destroy			= stex_slave_destroy,
 	.eh_abort_handler		= stex_abort,
 	.eh_host_reset_handler		= stex_reset,
 	.this_id			= -1,
+	.use_blk_tags			= 1,
 };
 
 static struct pci_device_id stex_pci_tbl[] = {
diff --git a/drivers/scsi/tmscsim.c b/drivers/scsi/tmscsim.c
index 547812437a7..6369f9a282f 100644
--- a/drivers/scsi/tmscsim.c
+++ b/drivers/scsi/tmscsim.c
@@ -2187,7 +2187,7 @@ static int dc390_slave_configure(struct scsi_device *sdev)
 	acb->scan_devices = 0;
 	if (sdev->tagged_supported && (dcb->DevMode & TAG_QUEUEING_)) {
 		dcb->SyncMode |= EN_TAG_QUEUEING;
-		scsi_activate_tcq(sdev, acb->TagMaxNum);
+		scsi_adjust_queue_depth(sdev, 0, acb->TagMaxNum);
 	}
 
 	return 0;
@@ -2209,6 +2209,7 @@ static struct scsi_host_template driver_template = {
 	.cmd_per_lun		= 1,
 	.use_clustering		= ENABLE_CLUSTERING,
 	.max_sectors		= 0x4000, /* 8MiB = 16 * 1024 * 512 */
+	.use_blk_tags		= 1,
 };
 
 /***********************************************************************
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 9da319130da..48c7f9e8f25 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -2695,7 +2695,8 @@ static void ufshcd_set_queue_depth(struct scsi_device *sdev)
 
 	dev_dbg(hba->dev, "%s: activate tcq with queue depth %d\n",
 			__func__, lun_qdepth);
-	scsi_activate_tcq(sdev, lun_qdepth);
+	if (sdev->tagged_supported)
+		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), lun_qdepth);
 }
 
 /*
@@ -2842,7 +2843,6 @@ static void ufshcd_slave_destroy(struct scsi_device *sdev)
 	struct ufs_hba *hba;
 
 	hba = shost_priv(sdev->host);
-	scsi_deactivate_tcq(sdev, hba->nutrs);
 	/* Drop the reference as it won't be needed anymore */
 	if (ufshcd_scsi_to_upiu_lun(sdev->lun) == UFS_UPIU_UFS_DEVICE_WLUN)
 		hba->sdev_ufs_device = NULL;
@@ -4235,6 +4235,7 @@ static struct scsi_host_template ufshcd_driver_template = {
 	.cmd_per_lun		= UFSHCD_CMD_PER_LUN,
 	.can_queue		= UFSHCD_CAN_QUEUE,
 	.max_host_blocked	= 1,
+	.use_blk_tags		= 1,
 };
 
 static int ufshcd_config_vreg_load(struct device *dev, struct ufs_vreg *vreg,
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index e30932f989a..120a851df0d 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -407,7 +407,6 @@ static int tcm_loop_slave_alloc(struct scsi_device *sd)
 static int tcm_loop_slave_configure(struct scsi_device *sd)
 {
 	if (sd->tagged_supported) {
-		scsi_activate_tcq(sd, sd->queue_depth);
 		scsi_adjust_queue_depth(sd, MSG_SIMPLE_TAG,
 					sd->host->cmd_per_lun);
 	} else {
@@ -437,6 +436,7 @@ static struct scsi_host_template tcm_loop_driver_template = {
 	.slave_alloc		= tcm_loop_slave_alloc,
 	.slave_configure	= tcm_loop_slave_configure,
 	.module			= THIS_MODULE,
+	.use_blk_tags		= 1,
 };
 
 static int tcm_loop_driver_probe(struct device *dev)
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 1bc5df4200a..ee69b82fc7d 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -799,8 +799,7 @@ static int uas_slave_configure(struct scsi_device *sdev)
 	if (devinfo->flags & US_FL_NO_REPORT_OPCODES)
 		sdev->no_report_opcodes = 1;
 
-	scsi_set_tag_type(sdev, MSG_ORDERED_TAG);
-	scsi_activate_tcq(sdev, devinfo->qdepth - 2);
+	scsi_adjust_queue_depth(sdev, MSG_ORDERED_TAG, devinfo->qdepth - 2);
 	return 0;
 }
 
@@ -824,6 +823,7 @@ static struct scsi_host_template uas_host_template = {
 	 * allocator.
 	 */
 	.disable_blk_mq = true,
+	.use_blk_tags = 1,
 };
 
 #define UNUSUAL_DEV(id_vendor, id_product, bcdDeviceMin, bcdDeviceMax, \
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index d6bd6529400..61a81bf77e2 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -421,6 +421,11 @@ struct scsi_host_template {
 	 */
 	unsigned char present;
 
+	/*
+	 * Let the block layer assigns tags to all commands.
+	 */
+	unsigned use_blk_tags:1;
+
 	/*
 	 * This specifies the mode that a LLD supports.
 	 */
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index 005f68da5ad..fe4a7029941 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -45,40 +45,6 @@ static inline void scsi_set_tag_type(struct scsi_device *sdev, int tag)
 		break;
 	}
 }
-/**
- * scsi_activate_tcq - turn on tag command queueing
- * @SDpnt:	device to turn on TCQ for
- * @depth:	queue depth
- *
- * Notes:
- *	Eventually, I hope depth would be the maximum depth
- *	the device could cope with and the real queue depth
- *	would be adjustable from 0 to depth.
- **/
-static inline void scsi_activate_tcq(struct scsi_device *sdev, int depth)
-{
-	if (!sdev->tagged_supported)
-		return;
-
-	if (shost_use_blk_mq(sdev->host))
-		queue_flag_set_unlocked(QUEUE_FLAG_QUEUED, sdev->request_queue);
-	else if (!blk_queue_tagged(sdev->request_queue))
-		blk_queue_init_tags(sdev->request_queue, depth,
-				    sdev->host->bqt);
-
-	scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), depth);
-}
-
-/**
- * scsi_deactivate_tcq - turn off tag command queueing
- * @SDpnt:	device to turn off TCQ for
- **/
-static inline void scsi_deactivate_tcq(struct scsi_device *sdev, int depth)
-{
-	if (blk_queue_tagged(sdev->request_queue))
-		blk_queue_free_tags(sdev->request_queue);
-	scsi_adjust_queue_depth(sdev, 0, depth);
-}
 
 static inline struct scsi_cmnd *scsi_mq_find_tag(struct Scsi_Host *shost,
 						 int unique_tag)
-- 
cgit v1.2.3-70-g09d2


From c8b09f6fb67df7fc1b51ced1037fa9b677428149 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 3 Nov 2014 20:15:14 +0100
Subject: scsi: don't set tagging state from scsi_adjust_queue_depth

Remove the tagged argument from scsi_adjust_queue_depth, and just let it
handle the queue depth.  For most drivers those two are fairly separate,
given that most modern drivers don't care about the SCSI "tagged" status
of a command at all, and many old drivers allow queuing of multiple
untagged commands in the driver.

Instead we start out with the ->simple_tags flag set before calling
->slave_configure, which is how all drivers actually looking at
->simple_tags except for one worke anyway.  The one other case looks
broken, but I've kept the behavior as-is for now.

Except for that we only change ->simple_tags from the ->change_queue_type,
and when rejecting a tag message in a single driver, so keeping this
churn out of scsi_adjust_queue_depth is a clear win.

Now that the usage of scsi_adjust_queue_depth is more obvious we can
also remove all the trivial instances in ->slave_alloc or ->slave_configure
that just set it to the cmd_per_lun default.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 Documentation/scsi/scsi_mid_low_api.txt   | 12 ++++------
 drivers/ata/libata-scsi.c                 |  4 ++--
 drivers/infiniband/ulp/srp/ib_srp.c       |  2 +-
 drivers/message/fusion/mptscsih.c         |  2 +-
 drivers/s390/scsi/zfcp_scsi.c             |  8 +++----
 drivers/scsi/3w-9xxx.c                    |  2 +-
 drivers/scsi/3w-sas.c                     |  2 +-
 drivers/scsi/3w-xxxx.c                    |  2 +-
 drivers/scsi/53c700.c                     | 17 ++++++-------
 drivers/scsi/BusLogic.c                   |  4 ++--
 drivers/scsi/aacraid/linit.c              |  8 +++----
 drivers/scsi/advansys.c                   |  7 ++----
 drivers/scsi/aic7xxx/aic79xx_osm.c        |  7 ++----
 drivers/scsi/aic7xxx/aic7xxx_osm.c        |  8 ++-----
 drivers/scsi/arcmsr/arcmsr_hba.c          |  2 +-
 drivers/scsi/bfa/bfad_im.c                |  3 +--
 drivers/scsi/csiostor/csio_scsi.c         |  2 +-
 drivers/scsi/dpt_i2o.c                    |  4 +---
 drivers/scsi/eata.c                       |  8 +++----
 drivers/scsi/esas2r/esas2r.h              |  3 ---
 drivers/scsi/esas2r/esas2r_main.c         | 29 +---------------------
 drivers/scsi/esp_scsi.c                   | 17 ++-----------
 drivers/scsi/fnic/fnic_main.c             |  2 +-
 drivers/scsi/gdth.c                       |  1 -
 drivers/scsi/hpsa.c                       |  2 +-
 drivers/scsi/hptiop.c                     |  2 +-
 drivers/scsi/ibmvscsi/ibmvfc.c            |  8 +------
 drivers/scsi/ibmvscsi/ibmvscsi.c          |  3 +--
 drivers/scsi/ipr.c                        |  8 +++----
 drivers/scsi/ips.c                        |  2 +-
 drivers/scsi/libfc/fc_fcp.c               |  6 ++---
 drivers/scsi/libiscsi.c                   |  4 ++--
 drivers/scsi/libsas/sas_scsi_host.c       | 20 +++++-----------
 drivers/scsi/lpfc/lpfc_scsi.c             |  4 ++--
 drivers/scsi/megaraid/megaraid_mbox.c     |  2 +-
 drivers/scsi/megaraid/megaraid_sas_base.c |  3 +--
 drivers/scsi/mpt2sas/mpt2sas_scsih.c      |  2 +-
 drivers/scsi/mpt3sas/mpt3sas_scsih.c      |  2 +-
 drivers/scsi/ncr53c8xx.c                  |  5 +---
 drivers/scsi/pmcraid.c                    | 40 ++++++-------------------------
 drivers/scsi/qla1280.c                    |  5 ++--
 drivers/scsi/qla2xxx/qla_os.c             |  6 ++---
 drivers/scsi/qla4xxx/ql4_os.c             |  2 +-
 drivers/scsi/scsi.c                       | 25 ++++---------------
 drivers/scsi/scsi_debug.c                 |  7 ++----
 drivers/scsi/scsi_scan.c                  |  6 +++--
 drivers/scsi/stex.c                       |  2 --
 drivers/scsi/storvsc_drv.c                |  3 +--
 drivers/scsi/sym53c8xx_2/sym_glue.c       |  4 +---
 drivers/scsi/tmscsim.c                    |  9 ++++++-
 drivers/scsi/u14-34f.c                    | 10 ++++----
 drivers/scsi/ufs/ufshcd.c                 |  4 ++--
 drivers/scsi/virtio_scsi.c                |  4 +---
 drivers/scsi/vmw_pvscsi.c                 |  2 +-
 drivers/target/loopback/tcm_loop.c        | 18 ++------------
 drivers/usb/storage/uas.c                 |  2 +-
 include/scsi/scsi_device.h                |  2 +-
 57 files changed, 120 insertions(+), 260 deletions(-)

(limited to 'include')

diff --git a/Documentation/scsi/scsi_mid_low_api.txt b/Documentation/scsi/scsi_mid_low_api.txt
index a6719420958..bee7d86b9dc 100644
--- a/Documentation/scsi/scsi_mid_low_api.txt
+++ b/Documentation/scsi/scsi_mid_low_api.txt
@@ -271,9 +271,9 @@ init_this_scsi_driver() ----+
                       slave_destroy() ***
 ------------------------------------------------------------
 
-The mid level invokes scsi_adjust_queue_depth() with tagged queuing off and
-"cmd_per_lun" for that host as the queue length. These settings can be
-overridden by a slave_configure() supplied by the LLD.
+The mid level invokes scsi_adjust_queue_depth() with "cmd_per_lun" for that
+host as the queue length. These settings can be overridden by a
+slave_configure() supplied by the LLD.
 
 *** For scsi devices that the mid level tries to scan but do not
     respond, a slave_alloc(), slave_destroy() pair is called.
@@ -438,9 +438,6 @@ int scsi_add_host(struct Scsi_Host *shost, struct device * dev)
 /**
  * scsi_adjust_queue_depth - allow LLD to change queue depth on a SCSI device
  * @sdev:       pointer to SCSI device to change queue depth on
- * @tagged:     0 - no tagged queuing
- *              MSG_SIMPLE_TAG - simple tagged queuing
- *              MSG_ORDERED_TAG - ordered tagged queuing
  * @tags        Number of tags allowed if tagged queuing enabled,
  *              or number of commands the LLD can queue up
  *              in non-tagged mode (as per cmd_per_lun).
@@ -456,8 +453,7 @@ int scsi_add_host(struct Scsi_Host *shost, struct device * dev)
  *      Defined in: drivers/scsi/scsi.c [see source code for more notes]
  *
  **/
-void scsi_adjust_queue_depth(struct scsi_device * sdev, int tagged, 
-                             int tags)
+void scsi_adjust_queue_depth(struct scsi_device *sdev, int tags)
 
 
 /**
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 0586f66d70f..c8bb6abbf12 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1164,7 +1164,7 @@ static int ata_scsi_dev_config(struct scsi_device *sdev,
 
 		depth = min(sdev->host->can_queue, ata_id_queue_depth(dev->id));
 		depth = min(ATA_MAX_QUEUE - 1, depth);
-		scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, depth);
+		scsi_adjust_queue_depth(sdev, depth);
 	}
 
 	blk_queue_flush_queueable(q, false);
@@ -1282,7 +1282,7 @@ int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev,
 	if (sdev->queue_depth == queue_depth)
 		return -EINVAL;
 
-	scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, queue_depth);
+	scsi_adjust_queue_depth(sdev, queue_depth);
 	return queue_depth;
 }
 
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 51670d75ab7..023a66f5ca1 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -2278,7 +2278,7 @@ srp_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 			max_depth = 1;
 		if (qdepth > max_depth)
 			qdepth = max_depth;
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), qdepth);
+		scsi_adjust_queue_depth(sdev, qdepth);
 	} else if (reason == SCSI_QDEPTH_QFULL)
 		scsi_track_queue_full(sdev, qdepth);
 	else
diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c
index c0d84a09db9..dee06d6f0b6 100644
--- a/drivers/message/fusion/mptscsih.c
+++ b/drivers/message/fusion/mptscsih.c
@@ -2347,7 +2347,7 @@ mptscsih_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 	if (qdepth > max_depth)
 		qdepth = max_depth;
 
-	scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), qdepth);
+	scsi_adjust_queue_depth(sdev, qdepth);
 	return sdev->queue_depth;
 }
 
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index 7b353647cb9..b5dfa51f396 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -37,13 +37,13 @@ static int zfcp_scsi_change_queue_depth(struct scsi_device *sdev, int depth,
 {
 	switch (reason) {
 	case SCSI_QDEPTH_DEFAULT:
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), depth);
+		scsi_adjust_queue_depth(sdev, depth);
 		break;
 	case SCSI_QDEPTH_QFULL:
 		scsi_track_queue_full(sdev, depth);
 		break;
 	case SCSI_QDEPTH_RAMP_UP:
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), depth);
+		scsi_adjust_queue_depth(sdev, depth);
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -66,9 +66,7 @@ static void zfcp_scsi_slave_destroy(struct scsi_device *sdev)
 static int zfcp_scsi_slave_configure(struct scsi_device *sdp)
 {
 	if (sdp->tagged_supported)
-		scsi_adjust_queue_depth(sdp, MSG_SIMPLE_TAG, default_depth);
-	else
-		scsi_adjust_queue_depth(sdp, 0, 1);
+		scsi_adjust_queue_depth(sdp, default_depth);
 	return 0;
 }
 
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index 0a7325361d2..02021f5ca86 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -198,7 +198,7 @@ static int twa_change_queue_depth(struct scsi_device *sdev, int queue_depth,
 
 	if (queue_depth > TW_Q_LENGTH-2)
 		queue_depth = TW_Q_LENGTH-2;
-	scsi_adjust_queue_depth(sdev, MSG_ORDERED_TAG, queue_depth);
+	scsi_adjust_queue_depth(sdev, queue_depth);
 	return queue_depth;
 } /* End twa_change_queue_depth() */
 
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index 6da6cec9a65..ac0c2544a47 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -200,7 +200,7 @@ static int twl_change_queue_depth(struct scsi_device *sdev, int queue_depth,
 
 	if (queue_depth > TW_Q_LENGTH-2)
 		queue_depth = TW_Q_LENGTH-2;
-	scsi_adjust_queue_depth(sdev, MSG_ORDERED_TAG, queue_depth);
+	scsi_adjust_queue_depth(sdev, queue_depth);
 	return queue_depth;
 } /* End twl_change_queue_depth() */
 
diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index 752624e6bc0..1ec9ad92b6c 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -532,7 +532,7 @@ static int tw_change_queue_depth(struct scsi_device *sdev, int queue_depth,
 
 	if (queue_depth > TW_Q_LENGTH-2)
 		queue_depth = TW_Q_LENGTH-2;
-	scsi_adjust_queue_depth(sdev, MSG_ORDERED_TAG, queue_depth);
+	scsi_adjust_queue_depth(sdev, queue_depth);
 	return queue_depth;
 } /* End tw_change_queue_depth() */
 
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index 497cbb1efd4..d7557b93211 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -902,8 +902,10 @@ process_message(struct Scsi_Host *host,	struct NCR_700_Host_Parameters *hostdata
 			/* we're done negotiating */
 			NCR_700_set_tag_neg_state(SCp->device, NCR_700_FINISHED_TAG_NEGOTIATION);
 			hostdata->tag_negotiated &= ~(1<<scmd_id(SCp));
+
 			SCp->device->tagged_supported = 0;
-			scsi_adjust_queue_depth(SCp->device, 0, host->cmd_per_lun);
+			scsi_adjust_queue_depth(SCp->device, host->cmd_per_lun);
+			scsi_set_tag_type(SCp->device, 0);
 		} else {
 			shost_printk(KERN_WARNING, host,
 				"(%d:%d) Unexpected REJECT Message %s\n",
@@ -2050,12 +2052,10 @@ NCR_700_slave_configure(struct scsi_device *SDp)
 
 	/* to do here: allocate memory; build a queue_full list */
 	if(SDp->tagged_supported) {
-		scsi_adjust_queue_depth(SDp, MSG_ORDERED_TAG, NCR_700_DEFAULT_TAGS);
+		scsi_adjust_queue_depth(SDp, NCR_700_DEFAULT_TAGS);
 		NCR_700_set_tag_neg_state(SDp, NCR_700_START_TAG_NEGOTIATION);
-	} else {
-		/* initialise to default depth */
-		scsi_adjust_queue_depth(SDp, 0, SDp->host->cmd_per_lun);
 	}
+
 	if(hostdata->fast) {
 		/* Find the correct offset and period via domain validation */
 		if (!spi_initial_dv(SDp->sdev_target))
@@ -2083,7 +2083,7 @@ NCR_700_change_queue_depth(struct scsi_device *SDp, int depth, int reason)
 	if (depth > NCR_700_MAX_TAGS)
 		depth = NCR_700_MAX_TAGS;
 
-	scsi_adjust_queue_depth(SDp, scsi_get_tag_type(SDp), depth);
+	scsi_adjust_queue_depth(SDp, depth);
 	return depth;
 }
 
@@ -2101,15 +2101,16 @@ static int NCR_700_change_queue_type(struct scsi_device *SDp, int tag_type)
 	if (change_tag)
 		scsi_target_quiesce(SDp->sdev_target);
 
+	scsi_set_tag_type(SDp, tag_type);
 	if (!tag_type) {
 		/* shift back to the default unqueued number of commands
 		 * (the user can still raise this) */
-		scsi_adjust_queue_depth(SDp, 0, SDp->host->cmd_per_lun);
+		scsi_adjust_queue_depth(SDp, SDp->host->cmd_per_lun);
 		hostdata->tag_negotiated &= ~(1 << sdev_id(SDp));
 	} else {
 		/* Here, we cleared the negotiation flag above, so this
 		 * will force the driver to renegotiate */
-		scsi_adjust_queue_depth(SDp, tag_type, SDp->queue_depth);
+		scsi_adjust_queue_depth(SDp, SDp->queue_depth);
 		if (change_tag)
 			NCR_700_set_tag_neg_state(SDp, NCR_700_START_TAG_NEGOTIATION);
 	}
diff --git a/drivers/scsi/BusLogic.c b/drivers/scsi/BusLogic.c
index 64c75143c89..5aa476b6b8a 100644
--- a/drivers/scsi/BusLogic.c
+++ b/drivers/scsi/BusLogic.c
@@ -2327,12 +2327,12 @@ static int blogic_slaveconfig(struct scsi_device *dev)
 		if (qdepth == 0)
 			qdepth = BLOGIC_MAX_AUTO_TAG_DEPTH;
 		adapter->qdepth[tgt_id] = qdepth;
-		scsi_adjust_queue_depth(dev, MSG_SIMPLE_TAG, qdepth);
+		scsi_adjust_queue_depth(dev, qdepth);
 	} else {
 		adapter->tagq_ok &= ~(1 << tgt_id);
 		qdepth = adapter->untag_qdepth;
 		adapter->qdepth[tgt_id] = qdepth;
-		scsi_adjust_queue_depth(dev, 0, qdepth);
+		scsi_adjust_queue_depth(dev, qdepth);
 	}
 	qdepth = 0;
 	for (tgt_id = 0; tgt_id < adapter->maxdev; tgt_id++)
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index a759cb2d4b1..41b9c68bca6 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -462,9 +462,9 @@ static int aac_slave_configure(struct scsi_device *sdev)
 			depth = 256;
 		else if (depth < 2)
 			depth = 2;
-		scsi_adjust_queue_depth(sdev, MSG_ORDERED_TAG, depth);
+		scsi_adjust_queue_depth(sdev, depth);
 	} else
-		scsi_adjust_queue_depth(sdev, 0, 1);
+		scsi_adjust_queue_depth(sdev, 1);
 
 	return 0;
 }
@@ -504,9 +504,9 @@ static int aac_change_queue_depth(struct scsi_device *sdev, int depth,
 			depth = 256;
 		else if (depth < 2)
 			depth = 2;
-		scsi_adjust_queue_depth(sdev, MSG_ORDERED_TAG, depth);
+		scsi_adjust_queue_depth(sdev, depth);
 	} else
-		scsi_adjust_queue_depth(sdev, 0, 1);
+		scsi_adjust_queue_depth(sdev, 1);
 	return sdev->queue_depth;
 }
 
diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
index 43761c1c46f..ae4840e4c1c 100644
--- a/drivers/scsi/advansys.c
+++ b/drivers/scsi/advansys.c
@@ -7706,7 +7706,7 @@ advansys_narrow_slave_configure(struct scsi_device *sdev, ASC_DVC_VAR *asc_dvc)
 				asc_dvc->cfg->can_tagged_qng |= tid_bit;
 				asc_dvc->use_tagged_qng |= tid_bit;
 			}
-			scsi_adjust_queue_depth(sdev, MSG_ORDERED_TAG,
+			scsi_adjust_queue_depth(sdev, 
 						asc_dvc->max_dvc_qng[sdev->id]);
 		}
 	} else {
@@ -7714,7 +7714,6 @@ advansys_narrow_slave_configure(struct scsi_device *sdev, ASC_DVC_VAR *asc_dvc)
 			asc_dvc->cfg->can_tagged_qng &= ~tid_bit;
 			asc_dvc->use_tagged_qng &= ~tid_bit;
 		}
-		scsi_adjust_queue_depth(sdev, 0, sdev->host->cmd_per_lun);
 	}
 
 	if ((sdev->lun == 0) &&
@@ -7849,10 +7848,8 @@ advansys_wide_slave_configure(struct scsi_device *sdev, ADV_DVC_VAR *adv_dvc)
 	}
 
 	if ((adv_dvc->tagqng_able & tidmask) && sdev->tagged_supported) {
-		scsi_adjust_queue_depth(sdev, MSG_ORDERED_TAG,
+		scsi_adjust_queue_depth(sdev,
 					adv_dvc->max_dvc_qng);
-	} else {
-		scsi_adjust_queue_depth(sdev, 0, sdev->host->cmd_per_lun);
 	}
 }
 
diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c
index 9fd6b5618b2..80cb4fd7caa 100644
--- a/drivers/scsi/aic7xxx/aic79xx_osm.c
+++ b/drivers/scsi/aic7xxx/aic79xx_osm.c
@@ -1469,11 +1469,8 @@ ahd_platform_set_tags(struct ahd_softc *ahd, struct scsi_device *sdev,
 
 	switch ((dev->flags & (AHD_DEV_Q_BASIC|AHD_DEV_Q_TAGGED))) {
 	case AHD_DEV_Q_BASIC:
-		scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TASK,
-				dev->openings + dev->active);
-		break;
 	case AHD_DEV_Q_TAGGED:
-		scsi_adjust_queue_depth(sdev, MSG_ORDERED_TASK,
+		scsi_adjust_queue_depth(sdev,
 				dev->openings + dev->active);
 		break;
 	default:
@@ -1483,7 +1480,7 @@ ahd_platform_set_tags(struct ahd_softc *ahd, struct scsi_device *sdev,
 		 * serially on the controller/device.  This should
 		 * remove some latency.
 		 */
-		scsi_adjust_queue_depth(sdev, 0, 1);
+		scsi_adjust_queue_depth(sdev, 1);
 		break;
 	}
 }
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c
index f18b6d69d3f..a6a27d5398d 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c
@@ -1335,13 +1335,9 @@ ahc_platform_set_tags(struct ahc_softc *ahc, struct scsi_device *sdev,
 	}
 	switch ((dev->flags & (AHC_DEV_Q_BASIC|AHC_DEV_Q_TAGGED))) {
 	case AHC_DEV_Q_BASIC:
-		scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TASK,
-				dev->openings + dev->active);
-		break;
 	case AHC_DEV_Q_TAGGED:
-		scsi_adjust_queue_depth(sdev, MSG_ORDERED_TASK,
+		scsi_adjust_queue_depth(sdev,
 				dev->openings + dev->active);
-		break;
 	default:
 		/*
 		 * We allow the OS to queue 2 untagged transactions to
@@ -1349,7 +1345,7 @@ ahc_platform_set_tags(struct ahc_softc *ahc, struct scsi_device *sdev,
 		 * serially on the controller/device.  This should
 		 * remove some latency.
 		 */
-		scsi_adjust_queue_depth(sdev, 0, 2);
+		scsi_adjust_queue_depth(sdev, 2);
 		break;
 	}
 }
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 0b44fb5ee48..209f77162d0 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -122,7 +122,7 @@ static int arcmsr_adjust_disk_queue_depth(struct scsi_device *sdev,
 
 	if (queue_depth > ARCMSR_MAX_CMD_PERLUN)
 		queue_depth = ARCMSR_MAX_CMD_PERLUN;
-	scsi_adjust_queue_depth(sdev, MSG_ORDERED_TAG, queue_depth);
+	scsi_adjust_queue_depth(sdev, queue_depth);
 	return queue_depth;
 }
 
diff --git a/drivers/scsi/bfa/bfad_im.c b/drivers/scsi/bfa/bfad_im.c
index d8e43c81d19..87b09cd232c 100644
--- a/drivers/scsi/bfa/bfad_im.c
+++ b/drivers/scsi/bfa/bfad_im.c
@@ -776,7 +776,7 @@ bfad_thread_workq(struct bfad_s *bfad)
 static int
 bfad_im_slave_configure(struct scsi_device *sdev)
 {
-	scsi_adjust_queue_depth(sdev, 0, bfa_lun_queue_depth);
+	scsi_adjust_queue_depth(sdev, bfa_lun_queue_depth);
 	return 0;
 }
 
@@ -867,7 +867,6 @@ bfad_ramp_up_qdepth(struct bfad_itnim_s *itnim, struct scsi_device *sdev)
 				if (tmp_sdev->id != sdev->id)
 					continue;
 				scsi_adjust_queue_depth(tmp_sdev,
-					MSG_SIMPLE_TAG,
 					tmp_sdev->queue_depth + 1);
 
 				itnim->last_ramp_up_time = jiffies;
diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c
index f73155db80a..44a8cc51428 100644
--- a/drivers/scsi/csiostor/csio_scsi.c
+++ b/drivers/scsi/csiostor/csio_scsi.c
@@ -2241,7 +2241,7 @@ csio_slave_alloc(struct scsi_device *sdev)
 static int
 csio_slave_configure(struct scsi_device *sdev)
 {
-	scsi_adjust_queue_depth(sdev, 0, csio_lun_qdepth);
+	scsi_adjust_queue_depth(sdev, csio_lun_qdepth);
 	return 0;
 }
 
diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c
index 072f0ec2851..1af8d54bcde 100644
--- a/drivers/scsi/dpt_i2o.c
+++ b/drivers/scsi/dpt_i2o.c
@@ -415,10 +415,8 @@ static int adpt_slave_configure(struct scsi_device * device)
 	pHba = (adpt_hba *) host->hostdata[0];
 
 	if (host->can_queue && device->tagged_supported) {
-		scsi_adjust_queue_depth(device, MSG_SIMPLE_TAG,
+		scsi_adjust_queue_depth(device,
 				host->can_queue - 1);
-	} else {
-		scsi_adjust_queue_depth(device, 0, 1);
 	}
 	return 0;
 }
diff --git a/drivers/scsi/eata.c b/drivers/scsi/eata.c
index 943ad3a1966..bc0f918f172 100644
--- a/drivers/scsi/eata.c
+++ b/drivers/scsi/eata.c
@@ -946,20 +946,18 @@ static int eata2x_slave_configure(struct scsi_device *dev)
 
 	if (TLDEV(dev->type) && dev->tagged_supported) {
 		if (tag_mode == TAG_SIMPLE) {
-			scsi_adjust_queue_depth(dev, MSG_SIMPLE_TAG, tqd);
 			tag_suffix = ", simple tags";
 		} else if (tag_mode == TAG_ORDERED) {
-			scsi_adjust_queue_depth(dev, MSG_ORDERED_TAG, tqd);
 			tag_suffix = ", ordered tags";
 		} else {
-			scsi_adjust_queue_depth(dev, 0, tqd);
 			tag_suffix = ", no tags";
 		}
+		scsi_adjust_queue_depth(dev, tqd);
 	} else if (TLDEV(dev->type) && linked_comm) {
-		scsi_adjust_queue_depth(dev, 0, tqd);
+		scsi_adjust_queue_depth(dev, tqd);
 		tag_suffix = ", untagged";
 	} else {
-		scsi_adjust_queue_depth(dev, 0, utqd);
+		scsi_adjust_queue_depth(dev, utqd);
 		tag_suffix = "";
 	}
 
diff --git a/drivers/scsi/esas2r/esas2r.h b/drivers/scsi/esas2r/esas2r.h
index 20ab211983f..1941d837f6f 100644
--- a/drivers/scsi/esas2r/esas2r.h
+++ b/drivers/scsi/esas2r/esas2r.h
@@ -972,9 +972,6 @@ u8 handle_hba_ioctl(struct esas2r_adapter *a,
 		    struct atto_ioctl *ioctl_hba);
 int esas2r_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd);
 int esas2r_show_info(struct seq_file *m, struct Scsi_Host *sh);
-int esas2r_slave_alloc(struct scsi_device *dev);
-int esas2r_slave_configure(struct scsi_device *dev);
-void esas2r_slave_destroy(struct scsi_device *dev);
 int esas2r_change_queue_depth(struct scsi_device *dev, int depth, int reason);
 long esas2r_proc_ioctl(struct file *fp, unsigned int cmd, unsigned long arg);
 
diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c
index a020b09ba34..30fce64faf7 100644
--- a/drivers/scsi/esas2r/esas2r_main.c
+++ b/drivers/scsi/esas2r/esas2r_main.c
@@ -254,9 +254,6 @@ static struct scsi_host_template driver_template = {
 	.use_clustering			= ENABLE_CLUSTERING,
 	.emulated			= 0,
 	.proc_name			= ESAS2R_DRVR_NAME,
-	.slave_configure		= esas2r_slave_configure,
-	.slave_alloc			= esas2r_slave_alloc,
-	.slave_destroy			= esas2r_slave_destroy,
 	.change_queue_depth		= esas2r_change_queue_depth,
 	.change_queue_type		= scsi_change_queue_type,
 	.max_sectors			= 0xFFFF,
@@ -1264,35 +1261,11 @@ int esas2r_change_queue_depth(struct scsi_device *dev, int depth, int reason)
 {
 	esas2r_log(ESAS2R_LOG_INFO, "change_queue_depth %p, %d", dev, depth);
 
-	scsi_adjust_queue_depth(dev, scsi_get_tag_type(dev), depth);
+	scsi_adjust_queue_depth(dev, depth);
 
 	return dev->queue_depth;
 }
 
-int esas2r_slave_alloc(struct scsi_device *dev)
-{
-	return 0;
-}
-
-int esas2r_slave_configure(struct scsi_device *dev)
-{
-	esas2r_log_dev(ESAS2R_LOG_INFO, &(dev->sdev_gendev),
-		       "esas2r_slave_configure()");
-
-	if (dev->tagged_supported)
-		scsi_adjust_queue_depth(dev, MSG_SIMPLE_TAG, cmd_per_lun);
-	else
-		scsi_adjust_queue_depth(dev, 0, cmd_per_lun);
-
-	return 0;
-}
-
-void esas2r_slave_destroy(struct scsi_device *dev)
-{
-	esas2r_log_dev(ESAS2R_LOG_INFO, &(dev->sdev_gendev),
-		       "esas2r_slave_destroy()");
-}
-
 void esas2r_log_request_failure(struct esas2r_adapter *a,
 				struct esas2r_request *rq)
 {
diff --git a/drivers/scsi/esp_scsi.c b/drivers/scsi/esp_scsi.c
index 66b6ce10b25..38c23e0b73a 100644
--- a/drivers/scsi/esp_scsi.c
+++ b/drivers/scsi/esp_scsi.c
@@ -2402,27 +2402,14 @@ static int esp_slave_configure(struct scsi_device *dev)
 {
 	struct esp *esp = shost_priv(dev->host);
 	struct esp_target_data *tp = &esp->target[dev->id];
-	int goal_tags, queue_depth;
-
-	goal_tags = 0;
 
 	if (dev->tagged_supported) {
 		/* XXX make this configurable somehow XXX */
-		goal_tags = ESP_DEFAULT_TAGS;
+		int goal_tags = min(ESP_DEFAULT_TAGS, ESP_MAX_TAG);
 
-		if (goal_tags > ESP_MAX_TAG)
-			goal_tags = ESP_MAX_TAG;
+		scsi_adjust_queue_depth(dev, goal_tags);
 	}
 
-	queue_depth = goal_tags;
-	if (queue_depth < dev->host->cmd_per_lun)
-		queue_depth = dev->host->cmd_per_lun;
-
-	if (goal_tags) {
-		scsi_adjust_queue_depth(dev, MSG_ORDERED_TAG, queue_depth);
-	} else {
-		scsi_adjust_queue_depth(dev, 0, queue_depth);
-	}
 	tp->flags |= ESP_TGT_DISCONNECT;
 
 	if (!spi_initial_dv(dev->sdev_target))
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index 2a6c98b7d4d..0f29e3f89b2 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -100,7 +100,7 @@ static int fnic_slave_alloc(struct scsi_device *sdev)
 	if (!rport || fc_remote_port_chkready(rport))
 		return -ENXIO;
 
-	scsi_adjust_queue_depth(sdev, 0, fnic_max_qdepth);
+	scsi_adjust_queue_depth(sdev, fnic_max_qdepth);
 	return 0;
 }
 
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index 0f1ae13ce7c..4ebbeae161e 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -4661,7 +4661,6 @@ static void gdth_flush(gdth_ha_str *ha)
 /* configure lun */
 static int gdth_slave_configure(struct scsi_device *sdev)
 {
-    scsi_adjust_queue_depth(sdev, 0, sdev->host->cmd_per_lun);
     sdev->skip_ms_page_3f = 1;
     sdev->skip_ms_page_8 = 1;
     return 0;
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index cef5d49b59c..18ea2e16e34 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -4165,7 +4165,7 @@ static int hpsa_change_queue_depth(struct scsi_device *sdev,
 	else
 		if (qdepth > h->nr_cmds)
 			qdepth = h->nr_cmds;
-	scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), qdepth);
+	scsi_adjust_queue_depth(sdev, qdepth);
 	return sdev->queue_depth;
 }
 
diff --git a/drivers/scsi/hptiop.c b/drivers/scsi/hptiop.c
index dedb62c21b2..151893148ab 100644
--- a/drivers/scsi/hptiop.c
+++ b/drivers/scsi/hptiop.c
@@ -1127,7 +1127,7 @@ static int hptiop_adjust_disk_queue_depth(struct scsi_device *sdev,
 
 	if (queue_depth > hba->max_requests)
 		queue_depth = hba->max_requests;
-	scsi_adjust_queue_depth(sdev, MSG_ORDERED_TAG, queue_depth);
+	scsi_adjust_queue_depth(sdev, queue_depth);
 	return queue_depth;
 }
 
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 4723d89df5a..147b80e07b0 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -2887,12 +2887,6 @@ static int ibmvfc_slave_configure(struct scsi_device *sdev)
 	spin_lock_irqsave(shost->host_lock, flags);
 	if (sdev->type == TYPE_DISK)
 		sdev->allow_restart = 1;
-
-	if (sdev->tagged_supported)
-		scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG,
-				sdev->queue_depth);
-	else
-		scsi_adjust_queue_depth(sdev, 0, sdev->queue_depth);
 	spin_unlock_irqrestore(shost->host_lock, flags);
 	return 0;
 }
@@ -2915,7 +2909,7 @@ static int ibmvfc_change_queue_depth(struct scsi_device *sdev, int qdepth,
 	if (qdepth > IBMVFC_MAX_CMDS_PER_LUN)
 		qdepth = IBMVFC_MAX_CMDS_PER_LUN;
 
-	scsi_adjust_queue_depth(sdev, 0, qdepth);
+	scsi_adjust_queue_depth(sdev, qdepth);
 	return sdev->queue_depth;
 }
 
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 7b23f21f22f..e8c3cdf0d03 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -1929,7 +1929,6 @@ static int ibmvscsi_slave_configure(struct scsi_device *sdev)
 		blk_queue_rq_timeout(sdev->request_queue, 120 * HZ);
 	}
 	spin_unlock_irqrestore(shost->host_lock, lock_flags);
-	scsi_adjust_queue_depth(sdev, 0, shost->cmd_per_lun);
 	return 0;
 }
 
@@ -1951,7 +1950,7 @@ static int ibmvscsi_change_queue_depth(struct scsi_device *sdev, int qdepth,
 	if (qdepth > IBMVSCSI_MAX_CMDS_PER_LUN)
 		qdepth = IBMVSCSI_MAX_CMDS_PER_LUN;
 
-	scsi_adjust_queue_depth(sdev, 0, qdepth);
+	scsi_adjust_queue_depth(sdev, qdepth);
 	return sdev->queue_depth;
 }
 
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index f84fcb9a6ed..256ef98f5c2 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -4344,7 +4344,7 @@ static int ipr_change_queue_depth(struct scsi_device *sdev, int qdepth,
 		qdepth = IPR_MAX_CMD_PER_ATA_LUN;
 	spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
 
-	scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), qdepth);
+	scsi_adjust_queue_depth(sdev, qdepth);
 	return sdev->queue_depth;
 }
 
@@ -4751,10 +4751,10 @@ static int ipr_slave_configure(struct scsi_device *sdev)
 		spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
 
 		if (ap) {
-			scsi_adjust_queue_depth(sdev, 0, IPR_MAX_CMD_PER_ATA_LUN);
+			scsi_adjust_queue_depth(sdev, IPR_MAX_CMD_PER_ATA_LUN);
 			ata_sas_slave_configure(sdev, ap);
-		} else
-			scsi_adjust_queue_depth(sdev, 0, sdev->host->cmd_per_lun);
+		}
+
 		if (ioa_cfg->sis64)
 			sdev_printk(KERN_INFO, sdev, "Resource path: %s\n",
 				    ipr_format_res_path(ioa_cfg,
diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c
index e5afc3884d7..454741a8da4 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -1210,7 +1210,7 @@ ips_slave_configure(struct scsi_device * SDptr)
 		min = ha->max_cmds / 2;
 		if (ha->enq->ucLogDriveCount <= 2)
 			min = ha->max_cmds - 1;
-		scsi_adjust_queue_depth(SDptr, MSG_ORDERED_TAG, min);
+		scsi_adjust_queue_depth(SDptr, min);
 	}
 
 	SDptr->skip_ms_page_8 = 1;
diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index d4bb642f268..bf954ee050f 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -2160,7 +2160,7 @@ int fc_slave_alloc(struct scsi_device *sdev)
 	if (!rport || fc_remote_port_chkready(rport))
 		return -ENXIO;
 
-	scsi_adjust_queue_depth(sdev, 0, FC_FCP_DFLT_QUEUE_DEPTH);
+	scsi_adjust_queue_depth(sdev, FC_FCP_DFLT_QUEUE_DEPTH);
 	return 0;
 }
 EXPORT_SYMBOL(fc_slave_alloc);
@@ -2175,13 +2175,13 @@ int fc_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 {
 	switch (reason) {
 	case SCSI_QDEPTH_DEFAULT:
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), qdepth);
+		scsi_adjust_queue_depth(sdev, qdepth);
 		break;
 	case SCSI_QDEPTH_QFULL:
 		scsi_track_queue_full(sdev, qdepth);
 		break;
 	case SCSI_QDEPTH_RAMP_UP:
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), qdepth);
+		scsi_adjust_queue_depth(sdev, qdepth);
 		break;
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 0d8bc6c6665..d521624dedf 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1775,13 +1775,13 @@ int iscsi_change_queue_depth(struct scsi_device *sdev, int depth, int reason)
 {
 	switch (reason) {
 	case SCSI_QDEPTH_DEFAULT:
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), depth);
+		scsi_adjust_queue_depth(sdev, depth);
 		break;
 	case SCSI_QDEPTH_QFULL:
 		scsi_track_queue_full(sdev, depth);
 		break;
 	case SCSI_QDEPTH_RAMP_UP:
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), depth);
+		scsi_adjust_queue_depth(sdev, depth);
 		break;
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index eee21a060d9..56d698af073 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -940,13 +940,13 @@ int sas_slave_configure(struct scsi_device *scsi_dev)
 	sas_read_port_mode_page(scsi_dev);
 
 	if (scsi_dev->tagged_supported) {
-		scsi_adjust_queue_depth(scsi_dev, MSG_SIMPLE_TAG, SAS_DEF_QD);
+		scsi_adjust_queue_depth(scsi_dev, SAS_DEF_QD);
 	} else {
 		SAS_DPRINTK("device %llx, LUN %llx doesn't support "
 			    "TCQ\n", SAS_ADDR(dev->sas_addr),
 			    scsi_dev->lun);
 		scsi_dev->tagged_supported = 0;
-		scsi_adjust_queue_depth(scsi_dev, 0, 1);
+		scsi_adjust_queue_depth(scsi_dev, 1);
 	}
 
 	scsi_dev->allow_restart = 1;
@@ -967,7 +967,7 @@ int sas_change_queue_depth(struct scsi_device *sdev, int depth, int reason)
 	case SCSI_QDEPTH_RAMP_UP:
 		if (!sdev->tagged_supported)
 			depth = 1;
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), depth);
+		scsi_adjust_queue_depth(sdev, depth);
 		break;
 	case SCSI_QDEPTH_QFULL:
 		scsi_track_queue_full(sdev, depth);
@@ -979,19 +979,11 @@ int sas_change_queue_depth(struct scsi_device *sdev, int depth, int reason)
 	return depth;
 }
 
-int sas_change_queue_type(struct scsi_device *scsi_dev, int qt)
+int sas_change_queue_type(struct scsi_device *scsi_dev, int type)
 {
-	struct domain_device *dev = sdev_to_domain_dev(scsi_dev);
-
-	if (dev_is_sata(dev))
+	if (dev_is_sata(sdev_to_domain_dev(scsi_dev)))
 		return -EINVAL;
-
-	if (!scsi_dev->tagged_supported)
-		return 0;
-
-	scsi_adjust_queue_depth(scsi_dev, qt, scsi_dev->queue_depth);
-
-	return qt;
+	return scsi_change_queue_type(scsi_dev, type);
 }
 
 int sas_bios_param(struct scsi_device *scsi_dev,
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index a24106a7096..8533ee9b818 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -320,7 +320,7 @@ lpfc_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 	case SCSI_QDEPTH_DEFAULT:
 		/* change request from sysfs, fall through */
 	case SCSI_QDEPTH_RAMP_UP:
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), qdepth);
+		scsi_adjust_queue_depth(sdev, qdepth);
 		break;
 	case SCSI_QDEPTH_QFULL:
 		if (scsi_track_queue_full(sdev, qdepth) == 0)
@@ -5598,7 +5598,7 @@ lpfc_slave_configure(struct scsi_device *sdev)
 	struct lpfc_vport *vport = (struct lpfc_vport *) sdev->host->hostdata;
 	struct lpfc_hba   *phba = vport->phba;
 
-	scsi_adjust_queue_depth(sdev, 0, vport->cfg_lun_queue_depth);
+	scsi_adjust_queue_depth(sdev, vport->cfg_lun_queue_depth);
 
 	if (phba->cfg_poll & ENABLE_FCP_RING_POLLING) {
 		lpfc_sli_handle_fast_ring_event(phba,
diff --git a/drivers/scsi/megaraid/megaraid_mbox.c b/drivers/scsi/megaraid/megaraid_mbox.c
index 531dce419c1..6b077d839f2 100644
--- a/drivers/scsi/megaraid/megaraid_mbox.c
+++ b/drivers/scsi/megaraid/megaraid_mbox.c
@@ -349,7 +349,7 @@ static int megaraid_change_queue_depth(struct scsi_device *sdev, int qdepth,
 
 	if (qdepth > MBOX_MAX_SCSI_CMDS)
 		qdepth = MBOX_MAX_SCSI_CMDS;
-	scsi_adjust_queue_depth(sdev, 0, qdepth);
+	scsi_adjust_queue_depth(sdev, qdepth);
 	return sdev->queue_depth;
 }
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 5640ad1c821..107244cebd2 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -2594,8 +2594,7 @@ static int megasas_change_queue_depth(struct scsi_device *sdev,
 
 	if (queue_depth > sdev->host->can_queue)
 		queue_depth = sdev->host->can_queue;
-	scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev),
-				queue_depth);
+	scsi_adjust_queue_depth(sdev, queue_depth);
 
 	return queue_depth;
 }
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index 69dc166b52b..42fef914d44 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -1222,7 +1222,7 @@ _scsih_adjust_queue_depth(struct scsi_device *sdev, int qdepth)
 		max_depth = 1;
 	if (qdepth > max_depth)
 		qdepth = max_depth;
-	scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), qdepth);
+	scsi_adjust_queue_depth(sdev, qdepth);
 }
 
 /**
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index d3abf254341..b23c2e7588e 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -1090,7 +1090,7 @@ _scsih_adjust_queue_depth(struct scsi_device *sdev, int qdepth)
 		max_depth = 1;
 	if (qdepth > max_depth)
 		qdepth = max_depth;
-	scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), qdepth);
+	scsi_adjust_queue_depth(sdev, qdepth);
 }
 
 /**
diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c
index a7305ffc359..9c331b7bfdc 100644
--- a/drivers/scsi/ncr53c8xx.c
+++ b/drivers/scsi/ncr53c8xx.c
@@ -7997,10 +7997,7 @@ static int ncr53c8xx_slave_configure(struct scsi_device *device)
 	if (depth_to_use > MAX_TAGS)
 		depth_to_use = MAX_TAGS;
 
-	scsi_adjust_queue_depth(device,
-				(device->tagged_supported ?
-				 MSG_SIMPLE_TAG : 0),
-				depth_to_use);
+	scsi_adjust_queue_depth(device, depth_to_use);
 
 	/*
 	**	Since the queue depth is not tunable under Linux,
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index 71f9f59b13c..d8b9ba251fb 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -249,14 +249,11 @@ static int pmcraid_slave_configure(struct scsi_device *scsi_dev)
 				      PMCRAID_VSET_MAX_SECTORS);
 	}
 
-	if (scsi_dev->tagged_supported &&
-	    (RES_IS_GSCSI(res->cfg_entry) || RES_IS_VSET(res->cfg_entry))) {
-		scsi_adjust_queue_depth(scsi_dev, MSG_SIMPLE_TAG,
-					scsi_dev->host->cmd_per_lun);
-	} else {
-		scsi_adjust_queue_depth(scsi_dev, 0,
-					scsi_dev->host->cmd_per_lun);
-	}
+	/*
+	 * We never want to report TCQ support for these types of devices.
+	 */
+	if (!RES_IS_GSCSI(res->cfg_entry) && !RES_IS_VSET(res->cfg_entry))
+		scsi_dev->tagged_supported = 0;
 
 	return 0;
 }
@@ -302,34 +299,11 @@ static int pmcraid_change_queue_depth(struct scsi_device *scsi_dev, int depth,
 	if (depth > PMCRAID_MAX_CMD_PER_LUN)
 		depth = PMCRAID_MAX_CMD_PER_LUN;
 
-	scsi_adjust_queue_depth(scsi_dev, scsi_get_tag_type(scsi_dev), depth);
+	scsi_adjust_queue_depth(scsi_dev, depth);
 
 	return scsi_dev->queue_depth;
 }
 
-/**
- * pmcraid_change_queue_type - Change the device's queue type
- * @scsi_dev: scsi device struct
- * @tag: type of tags to use
- *
- * Return value:
- *	actual queue type set
- */
-static int pmcraid_change_queue_type(struct scsi_device *scsi_dev, int tag)
-{
-	struct pmcraid_resource_entry *res;
-
-	res = (struct pmcraid_resource_entry *)scsi_dev->hostdata;
-	if (res && scsi_dev->tagged_supported &&
-	    (RES_IS_GSCSI(res->cfg_entry) || RES_IS_VSET(res->cfg_entry)))
-	    	tag = scsi_change_queue_type(scsi_dev, tag);
-	else
-		tag = 0;
-
-	return tag;
-}
-
-
 /**
  * pmcraid_init_cmdblk - initializes a command block
  *
@@ -4285,7 +4259,7 @@ static struct scsi_host_template pmcraid_host_template = {
 	.slave_configure = pmcraid_slave_configure,
 	.slave_destroy = pmcraid_slave_destroy,
 	.change_queue_depth = pmcraid_change_queue_depth,
-	.change_queue_type  = pmcraid_change_queue_type,
+	.change_queue_type  = scsi_change_queue_type,
 	.can_queue = PMCRAID_MAX_IO_CMD,
 	.this_id = -1,
 	.sg_tablesize = PMCRAID_MAX_IOADLS,
diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c
index 158020522df..adedb6ef8ee 100644
--- a/drivers/scsi/qla1280.c
+++ b/drivers/scsi/qla1280.c
@@ -1224,10 +1224,9 @@ qla1280_slave_configure(struct scsi_device *device)
 
 	if (device->tagged_supported &&
 	    (ha->bus_settings[bus].qtag_enables & (BIT_0 << target))) {
-		scsi_adjust_queue_depth(device, MSG_ORDERED_TAG,
-					ha->bus_settings[bus].hiwat);
+		scsi_adjust_queue_depth(device, ha->bus_settings[bus].hiwat);
 	} else {
-		scsi_adjust_queue_depth(device, 0, default_depth);
+		scsi_adjust_queue_depth(device, default_depth);
 	}
 
 	nv->bus[bus].target[target].parameter.enable_sync = device->sdtr;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index eb0465305f8..33166ebec7d 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1405,7 +1405,7 @@ qla2xxx_slave_configure(struct scsi_device *sdev)
 	if (IS_T10_PI_CAPABLE(vha->hw))
 		blk_queue_update_dma_alignment(sdev->request_queue, 0x7);
 
-	scsi_adjust_queue_depth(sdev, 0, req->max_q_depth);
+	scsi_adjust_queue_depth(sdev, req->max_q_depth);
 	return 0;
 }
 
@@ -1440,7 +1440,7 @@ static void qla2x00_adjust_sdev_qdepth_up(struct scsi_device *sdev, int qdepth)
 	if (req->max_q_depth <= sdev->queue_depth || req->max_q_depth < qdepth)
 		return;
 
-	scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, qdepth);
+	scsi_adjust_queue_depth(sdev, qdepth);
 
 	ql_dbg(ql_dbg_io, vha, 0x302a,
 	    "Queue depth adjusted-up to %d for nexus=%ld:%d:%llu.\n",
@@ -1452,7 +1452,7 @@ qla2x00_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 {
 	switch (reason) {
 	case SCSI_QDEPTH_DEFAULT:
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), qdepth);
+		scsi_adjust_queue_depth(sdev, qdepth);
 		break;
 	case SCSI_QDEPTH_QFULL:
 		qla2x00_handle_queue_full(sdev, qdepth);
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index f3119c144e2..784f59e5551 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -9064,7 +9064,7 @@ static int qla4xxx_slave_alloc(struct scsi_device *sdev)
 	if (ql4xmaxqdepth != 0 && ql4xmaxqdepth <= 0xffffU)
 		queue_depth = ql4xmaxqdepth;
 
-	scsi_adjust_queue_depth(sdev, 0, queue_depth);
+	scsi_adjust_queue_depth(sdev, queue_depth);
 	return 0;
 }
 
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index a3426f1bf0d..106fa2f886d 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -744,8 +744,6 @@ void scsi_finish_command(struct scsi_cmnd *cmd)
 /**
  * scsi_adjust_queue_depth - Let low level drivers change a device's queue depth
  * @sdev: SCSI Device in question
- * @tagged: Do we use tagged queueing (non-0) or do we treat
- *          this device as an untagged device (0)
  * @tags: Number of tags allowed if tagged queueing enabled,
  *        or number of commands the low level driver can
  *        queue up in non-tagged mode (as per cmd_per_lun).
@@ -759,7 +757,7 @@ void scsi_finish_command(struct scsi_cmnd *cmd)
  * 		currently active and whether or not it even has the
  * 		command blocks built yet.
  */
-void scsi_adjust_queue_depth(struct scsi_device *sdev, int tagged, int tags)
+void scsi_adjust_queue_depth(struct scsi_device *sdev, int tags)
 {
 	unsigned long flags;
 
@@ -787,20 +785,6 @@ void scsi_adjust_queue_depth(struct scsi_device *sdev, int tagged, int tags)
 	}
 
 	sdev->queue_depth = tags;
-	switch (tagged) {
-		case 0:
-			sdev->simple_tags = 0;
-			break;
-		case MSG_ORDERED_TAG:
-		case MSG_SIMPLE_TAG:
-			sdev->simple_tags = 1;
-			break;
-		default:
-			sdev->simple_tags = 0;
-			sdev_printk(KERN_WARNING, sdev,
-				    "scsi_adjust_queue_depth, bad queue type, "
-				    "disabled\n");
-	}
  out:
 	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
 }
@@ -848,11 +832,12 @@ int scsi_track_queue_full(struct scsi_device *sdev, int depth)
 		return 0;
 	if (sdev->last_queue_full_depth < 8) {
 		/* Drop back to untagged */
-		scsi_adjust_queue_depth(sdev, 0, sdev->host->cmd_per_lun);
+		scsi_set_tag_type(sdev, 0);
+		scsi_adjust_queue_depth(sdev, sdev->host->cmd_per_lun);
 		return -1;
 	}
 
-	scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, depth);
+	scsi_adjust_queue_depth(sdev, depth);
 	return depth;
 }
 EXPORT_SYMBOL(scsi_track_queue_full);
@@ -867,7 +852,7 @@ int scsi_change_queue_type(struct scsi_device *sdev, int tag_type)
 	if (!sdev->tagged_supported)
 		return 0;
 
-	scsi_adjust_queue_depth(sdev, tag_type, sdev->queue_depth);
+	scsi_set_tag_type(sdev, tag_type);
 	return tag_type;
 
 }
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 7bcace2cdd5..fce4e47becc 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -2700,11 +2700,8 @@ static int scsi_debug_slave_configure(struct scsi_device *sdp)
 	devip = devInfoReg(sdp);
 	if (NULL == devip)
 		return 1;	/* no resources, will be marked offline */
-	sdp->hostdata = devip;
 	sdp->tagged_supported = 1;
-	if (sdp->host->cmd_per_lun)
-		scsi_adjust_queue_depth(sdp, DEF_TAGGED_QUEUING,
-					DEF_CMD_PER_LUN);
+	sdp->hostdata = devip;
 	blk_queue_max_segment_size(sdp->request_queue, -1U);
 	if (scsi_debug_no_uld)
 		sdp->no_uld_attach = 1;
@@ -4494,7 +4491,7 @@ sdebug_change_qdepth(struct scsi_device *sdev, int qdepth, int reason)
 		/* allow to exceed max host queued_arr elements for testing */
 		if (qdepth > SCSI_DEBUG_CANQUEUE + 10)
 			qdepth = SCSI_DEBUG_CANQUEUE + 10;
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), qdepth);
+		scsi_adjust_queue_depth(sdev, qdepth);
 	} else if (reason == SCSI_QDEPTH_QFULL)
 		scsi_track_queue_full(sdev, qdepth);
 	else
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 408891cb14f..d97597e6337 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -292,7 +292,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 		blk_queue_init_tags(sdev->request_queue,
 				    sdev->host->cmd_per_lun, shost->bqt);
 	}
-	scsi_adjust_queue_depth(sdev, 0, sdev->host->cmd_per_lun);
+	scsi_adjust_queue_depth(sdev, sdev->host->cmd_per_lun);
 
 	scsi_sysfs_device_initialize(sdev);
 
@@ -880,8 +880,10 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,
 			(inq_result[3] & 0x0f) == 1 ? " CCS" : "");
 
 	if ((sdev->scsi_level >= SCSI_2) && (inq_result[7] & 2) &&
-	    !(*bflags & BLIST_NOTQ))
+	    !(*bflags & BLIST_NOTQ)) {
 		sdev->tagged_supported = 1;
+		sdev->simple_tags = 1;
+	}
 
 	/*
 	 * Some devices (Texel CD ROM drives) have handshaking problems
diff --git a/drivers/scsi/stex.c b/drivers/scsi/stex.c
index b5eae4f6ba4..2bb8a9e74da 100644
--- a/drivers/scsi/stex.c
+++ b/drivers/scsi/stex.c
@@ -549,8 +549,6 @@ stex_slave_alloc(struct scsi_device *sdev)
 	/* Cheat: usually extracted from Inquiry data */
 	sdev->tagged_supported = 1;
 
-	scsi_adjust_queue_depth(sdev, 0, sdev->host->can_queue);
-
 	return 0;
 }
 
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 37f5fd8ed76..ff8befbdf17 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1429,8 +1429,7 @@ static void storvsc_device_destroy(struct scsi_device *sdevice)
 
 static int storvsc_device_configure(struct scsi_device *sdevice)
 {
-	scsi_adjust_queue_depth(sdevice, MSG_SIMPLE_TAG,
-				STORVSC_MAX_IO_REQUESTS);
+	scsi_adjust_queue_depth(sdevice, STORVSC_MAX_IO_REQUESTS);
 
 	blk_queue_max_segment_size(sdevice->request_queue, PAGE_SIZE);
 
diff --git a/drivers/scsi/sym53c8xx_2/sym_glue.c b/drivers/scsi/sym53c8xx_2/sym_glue.c
index e59e6f96b72..3557b385251 100644
--- a/drivers/scsi/sym53c8xx_2/sym_glue.c
+++ b/drivers/scsi/sym53c8xx_2/sym_glue.c
@@ -820,9 +820,7 @@ static int sym53c8xx_slave_configure(struct scsi_device *sdev)
 	if (reqtags > SYM_CONF_MAX_TAG)
 		reqtags = SYM_CONF_MAX_TAG;
 	depth_to_use = reqtags ? reqtags : 1;
-	scsi_adjust_queue_depth(sdev,
-				sdev->tagged_supported ? MSG_SIMPLE_TAG : 0,
-				depth_to_use);
+	scsi_adjust_queue_depth(sdev, depth_to_use);
 	lp->s.scdev_depth = depth_to_use;
 	sym_tune_dev_queuing(tp, sdev->lun, reqtags);
 
diff --git a/drivers/scsi/tmscsim.c b/drivers/scsi/tmscsim.c
index 6369f9a282f..844c9a048c0 100644
--- a/drivers/scsi/tmscsim.c
+++ b/drivers/scsi/tmscsim.c
@@ -2185,9 +2185,16 @@ static int dc390_slave_configure(struct scsi_device *sdev)
 	struct dc390_dcb *dcb = (struct dc390_dcb *)sdev->hostdata;
 
 	acb->scan_devices = 0;
+
+	/*
+	 * XXX: Note that while this driver used to called scsi_activate_tcq,
+	 * it never actually set a tag type, so emulate the old behavior.
+	 */
+	scsi_set_tag_type(sdev, 0);
+
 	if (sdev->tagged_supported && (dcb->DevMode & TAG_QUEUEING_)) {
 		dcb->SyncMode |= EN_TAG_QUEUEING;
-		scsi_adjust_queue_depth(sdev, 0, acb->TagMaxNum);
+		scsi_adjust_queue_depth(sdev, acb->TagMaxNum);
 	}
 
 	return 0;
diff --git a/drivers/scsi/u14-34f.c b/drivers/scsi/u14-34f.c
index d8dcf36aed1..aa0f4035afa 100644
--- a/drivers/scsi/u14-34f.c
+++ b/drivers/scsi/u14-34f.c
@@ -696,25 +696,25 @@ static int u14_34f_slave_configure(struct scsi_device *dev) {
    if (TLDEV(dev->type) && dev->tagged_supported)
 
       if (tag_mode == TAG_SIMPLE) {
-         scsi_adjust_queue_depth(dev, MSG_SIMPLE_TAG, tqd);
+         scsi_adjust_queue_depth(dev, tqd);
          tag_suffix = ", simple tags";
          }
       else if (tag_mode == TAG_ORDERED) {
-         scsi_adjust_queue_depth(dev, MSG_ORDERED_TAG, tqd);
+         scsi_adjust_queue_depth(dev, tqd);
          tag_suffix = ", ordered tags";
          }
       else {
-         scsi_adjust_queue_depth(dev, 0, tqd);
+         scsi_adjust_queue_depth(dev, tqd);
          tag_suffix = ", no tags";
          }
 
    else if (TLDEV(dev->type) && linked_comm) {
-      scsi_adjust_queue_depth(dev, 0, tqd);
+      scsi_adjust_queue_depth(dev, tqd);
       tag_suffix = ", untagged";
       }
 
    else {
-      scsi_adjust_queue_depth(dev, 0, utqd);
+      scsi_adjust_queue_depth(dev, utqd);
       tag_suffix = "";
       }
 
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 48c7f9e8f25..5eb4931e2ad 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -2696,7 +2696,7 @@ static void ufshcd_set_queue_depth(struct scsi_device *sdev)
 	dev_dbg(hba->dev, "%s: activate tcq with queue depth %d\n",
 			__func__, lun_qdepth);
 	if (sdev->tagged_supported)
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), lun_qdepth);
+		scsi_adjust_queue_depth(sdev, lun_qdepth);
 }
 
 /*
@@ -2808,7 +2808,7 @@ static int ufshcd_change_queue_depth(struct scsi_device *sdev,
 	case SCSI_QDEPTH_RAMP_UP:
 		if (!sdev->tagged_supported)
 			depth = 1;
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), depth);
+		scsi_adjust_queue_depth(sdev, depth);
 		break;
 	case SCSI_QDEPTH_QFULL:
 		scsi_track_queue_full(sdev, depth);
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index b83846fc785..355afbc7fde 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -683,9 +683,7 @@ static int virtscsi_change_queue_depth(struct scsi_device *sdev,
 		break;
 	case SCSI_QDEPTH_RAMP_UP: /* Raise qdepth after BUSY state resolved */
 	case SCSI_QDEPTH_DEFAULT: /* Manual change via sysfs */
-		scsi_adjust_queue_depth(sdev,
-					scsi_get_tag_type(sdev),
-					min(max_depth, qdepth));
+		scsi_adjust_queue_depth(sdev, min(max_depth, qdepth));
 		break;
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 53a3eb6c063..c3b4f8b3a3a 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -522,7 +522,7 @@ static int pvscsi_change_queue_depth(struct scsi_device *sdev,
 		max_depth = 1;
 	if (qdepth > max_depth)
 		qdepth = max_depth;
-	scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), qdepth);
+	scsi_adjust_queue_depth(sdev, qdepth);
 
 	if (sdev->inquiry_len > 7)
 		sdev_printk(KERN_INFO, sdev,
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 120a851df0d..0ed96644ec9 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -121,13 +121,13 @@ static int tcm_loop_change_queue_depth(
 {
 	switch (reason) {
 	case SCSI_QDEPTH_DEFAULT:
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), depth);
+		scsi_adjust_queue_depth(sdev, depth);
 		break;
 	case SCSI_QDEPTH_QFULL:
 		scsi_track_queue_full(sdev, depth);
 		break;
 	case SCSI_QDEPTH_RAMP_UP:
-		scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), depth);
+		scsi_adjust_queue_depth(sdev, depth);
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -404,19 +404,6 @@ static int tcm_loop_slave_alloc(struct scsi_device *sd)
 	return 0;
 }
 
-static int tcm_loop_slave_configure(struct scsi_device *sd)
-{
-	if (sd->tagged_supported) {
-		scsi_adjust_queue_depth(sd, MSG_SIMPLE_TAG,
-					sd->host->cmd_per_lun);
-	} else {
-		scsi_adjust_queue_depth(sd, 0,
-					sd->host->cmd_per_lun);
-	}
-
-	return 0;
-}
-
 static struct scsi_host_template tcm_loop_driver_template = {
 	.show_info		= tcm_loop_show_info,
 	.proc_name		= "tcm_loopback",
@@ -434,7 +421,6 @@ static struct scsi_host_template tcm_loop_driver_template = {
 	.max_sectors		= 0xFFFF,
 	.use_clustering		= DISABLE_CLUSTERING,
 	.slave_alloc		= tcm_loop_slave_alloc,
-	.slave_configure	= tcm_loop_slave_configure,
 	.module			= THIS_MODULE,
 	.use_blk_tags		= 1,
 };
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index ee69b82fc7d..33f211b56a4 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -799,7 +799,7 @@ static int uas_slave_configure(struct scsi_device *sdev)
 	if (devinfo->flags & US_FL_NO_REPORT_OPCODES)
 		sdev->no_report_opcodes = 1;
 
-	scsi_adjust_queue_depth(sdev, MSG_ORDERED_TAG, devinfo->qdepth - 2);
+	scsi_adjust_queue_depth(sdev, devinfo->qdepth - 2);
 	return 0;
 }
 
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index e8fecb5ea79..0aeaa003c3c 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -380,7 +380,7 @@ extern struct scsi_device *__scsi_iterate_devices(struct Scsi_Host *,
 #define __shost_for_each_device(sdev, shost) \
 	list_for_each_entry((sdev), &((shost)->__devices), siblings)
 
-extern void scsi_adjust_queue_depth(struct scsi_device *, int, int);
+extern void scsi_adjust_queue_depth(struct scsi_device *, int);
 extern int scsi_track_queue_full(struct scsi_device *, int);
 
 extern int scsi_set_medium_removal(struct scsi_device *, char);
-- 
cgit v1.2.3-70-g09d2


From ef691ff48bc838e9fca54b58dccac0a7c36a3130 Mon Sep 17 00:00:00 2001
From: Archit Taneja <archit@ti.com>
Date: Tue, 22 Apr 2014 17:43:48 +0530
Subject: OMAPDSS: DT: Get source endpoint by matching reg-id

In omapdss_of_find_source_for_first_ep, we retrieve a source endpoint's DT node,
and then see what omapdss output has the matching device_node pointer in
omap_dss_find_output_by_node.

For all DPI and SDI outputs, the device_node pointer is set as the parent's DSS
device_node pointer. If the source is one of these outputs, the above method
won't work.

To get the correct output for ports within DSS(and in other cases in the future,
where multiple ports might be under one device), we require additional
information which is exclusive to the output port.

We create a new field in omap_dss_device called 'port_num', this provides port
number of the output port corresponding to this device. When searching for the
source endpoint in DT, we extract the 'reg' property from the port corresponding
to the endpoint source. From the list of registered outputs, we pick out that
output which has both dev->of_node and port_num matching with the device_node
pointer and 'reg' of the source endpoint node from DT.

For encoder blocks(the ones which have both an input and output port), we need
to set the port_num as the 'reg' property for the output port as defined in the
DT bindings. We set port_num to 1 in the tfp410 and tpd12s015 encoder drivers.

Signed-off-by: Archit Taneja <archit@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 .../fbdev/omap2/displays-new/encoder-tfp410.c      |  1 +
 .../fbdev/omap2/displays-new/encoder-tpd12s015.c   |  1 +
 drivers/video/fbdev/omap2/dss/dss-of.c             | 58 +++++++++++++++-------
 drivers/video/fbdev/omap2/dss/dss.h                |  4 ++
 drivers/video/fbdev/omap2/dss/output.c             | 19 +++++--
 include/video/omapdss.h                            |  5 +-
 6 files changed, 66 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/video/fbdev/omap2/displays-new/encoder-tfp410.c b/drivers/video/fbdev/omap2/displays-new/encoder-tfp410.c
index 47ee7cdee1c..e349064ed61 100644
--- a/drivers/video/fbdev/omap2/displays-new/encoder-tfp410.c
+++ b/drivers/video/fbdev/omap2/displays-new/encoder-tfp410.c
@@ -249,6 +249,7 @@ static int tfp410_probe(struct platform_device *pdev)
 	dssdev->output_type = OMAP_DISPLAY_TYPE_DVI;
 	dssdev->owner = THIS_MODULE;
 	dssdev->phy.dpi.data_lines = ddata->data_lines;
+	dssdev->port_num = 1;
 
 	r = omapdss_register_output(dssdev);
 	if (r) {
diff --git a/drivers/video/fbdev/omap2/displays-new/encoder-tpd12s015.c b/drivers/video/fbdev/omap2/displays-new/encoder-tpd12s015.c
index c4abd56dd84..1891967b650 100644
--- a/drivers/video/fbdev/omap2/displays-new/encoder-tpd12s015.c
+++ b/drivers/video/fbdev/omap2/displays-new/encoder-tpd12s015.c
@@ -409,6 +409,7 @@ static int tpd_probe(struct platform_device *pdev)
 	dssdev->type = OMAP_DISPLAY_TYPE_HDMI;
 	dssdev->output_type = OMAP_DISPLAY_TYPE_HDMI;
 	dssdev->owner = THIS_MODULE;
+	dssdev->port_num = 1;
 
 	in = ddata->in;
 
diff --git a/drivers/video/fbdev/omap2/dss/dss-of.c b/drivers/video/fbdev/omap2/dss/dss-of.c
index a4b20aaf614..928ee639c0c 100644
--- a/drivers/video/fbdev/omap2/dss/dss-of.c
+++ b/drivers/video/fbdev/omap2/dss/dss-of.c
@@ -20,6 +20,8 @@
 
 #include <video/omapdss.h>
 
+#include "dss.h"
+
 struct device_node *
 omapdss_of_get_next_port(const struct device_node *parent,
 			 struct device_node *prev)
@@ -84,20 +86,17 @@ omapdss_of_get_next_endpoint(const struct device_node *parent,
 }
 EXPORT_SYMBOL_GPL(omapdss_of_get_next_endpoint);
 
-static struct device_node *
-omapdss_of_get_remote_device_node(const struct device_node *node)
+struct device_node *dss_of_port_get_parent_device(struct device_node *port)
 {
 	struct device_node *np;
 	int i;
 
-	np = of_parse_phandle(node, "remote-endpoint", 0);
-
-	if (!np)
+	if (!port)
 		return NULL;
 
-	np = of_get_next_parent(np);
+	np = of_get_next_parent(port);
 
-	for (i = 0; i < 3 && np; ++i) {
+	for (i = 0; i < 2 && np; ++i) {
 		struct property *prop;
 
 		prop = of_find_property(np, "compatible", NULL);
@@ -111,6 +110,31 @@ omapdss_of_get_remote_device_node(const struct device_node *node)
 	return NULL;
 }
 
+u32 dss_of_port_get_port_number(struct device_node *port)
+{
+	int r;
+	u32 reg;
+
+	r = of_property_read_u32(port, "reg", &reg);
+	if (r)
+		reg = 0;
+
+	return reg;
+}
+
+static struct device_node *omapdss_of_get_remote_port(const struct device_node *node)
+{
+	struct device_node *np;
+
+	np = of_parse_phandle(node, "remote-endpoint", 0);
+	if (!np)
+		return NULL;
+
+	np = of_get_next_parent(np);
+
+	return np;
+}
+
 struct device_node *
 omapdss_of_get_first_endpoint(const struct device_node *parent)
 {
@@ -133,27 +157,25 @@ struct omap_dss_device *
 omapdss_of_find_source_for_first_ep(struct device_node *node)
 {
 	struct device_node *ep;
-	struct device_node *src_node;
+	struct device_node *src_port;
 	struct omap_dss_device *src;
 
 	ep = omapdss_of_get_first_endpoint(node);
 	if (!ep)
 		return ERR_PTR(-EINVAL);
 
-	src_node = omapdss_of_get_remote_device_node(ep);
-
-	of_node_put(ep);
-
-	if (!src_node)
+	src_port = omapdss_of_get_remote_port(ep);
+	if (!src_port) {
+		of_node_put(ep);
 		return ERR_PTR(-EINVAL);
+	}
 
-	src = omap_dss_find_output_by_node(src_node);
+	of_node_put(ep);
 
-	of_node_put(src_node);
+	src = omap_dss_find_output_by_port_node(src_port);
 
-	if (!src)
-		return ERR_PTR(-EPROBE_DEFER);
+	of_node_put(src_port);
 
-	return src;
+	return src ? src : ERR_PTR(-EPROBE_DEFER);
 }
 EXPORT_SYMBOL_GPL(omapdss_of_find_source_for_first_ep);
diff --git a/drivers/video/fbdev/omap2/dss/dss.h b/drivers/video/fbdev/omap2/dss/dss.h
index da4de14aaf1..6f346bf518b 100644
--- a/drivers/video/fbdev/omap2/dss/dss.h
+++ b/drivers/video/fbdev/omap2/dss/dss.h
@@ -215,6 +215,10 @@ enum dss_hdmi_venc_clk_source_select dss_get_hdmi_venc_clk_source(void);
 const char *dss_get_generic_clk_source_name(enum omap_dss_clk_source clk_src);
 void dss_dump_clocks(struct seq_file *s);
 
+/* dss-of */
+struct device_node *dss_of_port_get_parent_device(struct device_node *port);
+u32 dss_of_port_get_port_number(struct device_node *port);
+
 #if defined(CONFIG_OMAP2_DSS_DEBUGFS)
 void dss_debug_dump_clocks(struct seq_file *s);
 #endif
diff --git a/drivers/video/fbdev/omap2/dss/output.c b/drivers/video/fbdev/omap2/dss/output.c
index 2ab3afa615e..16072159bd2 100644
--- a/drivers/video/fbdev/omap2/dss/output.c
+++ b/drivers/video/fbdev/omap2/dss/output.c
@@ -19,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/of.h>
 
 #include <video/omapdss.h>
 
@@ -131,18 +132,30 @@ struct omap_dss_device *omap_dss_find_output(const char *name)
 }
 EXPORT_SYMBOL(omap_dss_find_output);
 
-struct omap_dss_device *omap_dss_find_output_by_node(struct device_node *node)
+struct omap_dss_device *omap_dss_find_output_by_port_node(struct device_node *port)
 {
+	struct device_node *src_node;
 	struct omap_dss_device *out;
+	u32 reg;
+
+	src_node = dss_of_port_get_parent_device(port);
+	if (!src_node)
+		return NULL;
+
+	reg = dss_of_port_get_port_number(port);
 
 	list_for_each_entry(out, &output_list, list) {
-		if (out->dev->of_node == node)
+		if (out->dev->of_node == src_node && out->port_num == reg) {
+			of_node_put(src_node);
 			return omap_dss_get_device(out);
+		}
 	}
 
+	of_node_put(src_node);
+
 	return NULL;
 }
-EXPORT_SYMBOL(omap_dss_find_output_by_node);
+EXPORT_SYMBOL(omap_dss_find_output_by_port_node);
 
 struct omap_dss_device *omapdss_find_output_from_display(struct omap_dss_device *dssdev)
 {
diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index 069dfca9549..1db32023396 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -795,6 +795,9 @@ struct omap_dss_device {
 	/* output instance */
 	enum omap_dss_output_id id;
 
+	/* the port number in the DT node */
+	int port_num;
+
 	/* dynamic fields */
 	struct omap_overlay_manager *manager;
 
@@ -918,7 +921,7 @@ int omapdss_register_output(struct omap_dss_device *output);
 void omapdss_unregister_output(struct omap_dss_device *output);
 struct omap_dss_device *omap_dss_get_output(enum omap_dss_output_id id);
 struct omap_dss_device *omap_dss_find_output(const char *name);
-struct omap_dss_device *omap_dss_find_output_by_node(struct device_node *node);
+struct omap_dss_device *omap_dss_find_output_by_port_node(struct device_node *port);
 int omapdss_output_set_device(struct omap_dss_device *out,
 		struct omap_dss_device *dssdev);
 int omapdss_output_unset_device(struct omap_dss_device *out);
-- 
cgit v1.2.3-70-g09d2


From c2791b806988100cc1c047e2b0b5c5d0914aa3b6 Mon Sep 17 00:00:00 2001
From: Yijing Wang <wangyijing@huawei.com>
Date: Tue, 11 Nov 2014 17:45:45 -0700
Subject: PCI/MSI: Rename "struct msi_chip" to "struct msi_controller"

"msi_chip" isn't very descriptive, so rename it to "msi_controller".  That
tells a little more about what it does and is already used in device tree
bindings.

No functional change.

[bhelgaas: changelog, change *only* the struct name so it's reviewable]
Suggested-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/irqchip/irq-armada-370-xp.c |  6 +++---
 drivers/of/of_pci.c                 |  8 ++++----
 drivers/pci/host/pci-keystone-dw.c  |  2 +-
 drivers/pci/host/pci-keystone.h     |  2 +-
 drivers/pci/host/pci-mvebu.c        |  2 +-
 drivers/pci/host/pci-tegra.c        | 11 ++++++-----
 drivers/pci/host/pcie-designware.c  |  6 +++---
 drivers/pci/host/pcie-designware.h  |  2 +-
 drivers/pci/host/pcie-rcar.c        |  8 ++++----
 drivers/pci/host/pcie-xilinx.c      |  7 ++++---
 drivers/pci/msi.c                   |  4 ++--
 include/linux/msi.h                 |  6 +++---
 include/linux/of_pci.h              | 12 ++++++------
 include/linux/pci.h                 |  2 +-
 14 files changed, 40 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 3e238cd049e..4e202375e02 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -129,7 +129,7 @@ static void armada_370_xp_free_msi(int hwirq)
 	mutex_unlock(&msi_used_lock);
 }
 
-static int armada_370_xp_setup_msi_irq(struct msi_chip *chip,
+static int armada_370_xp_setup_msi_irq(struct msi_controller *chip,
 				       struct pci_dev *pdev,
 				       struct msi_desc *desc)
 {
@@ -160,7 +160,7 @@ static int armada_370_xp_setup_msi_irq(struct msi_chip *chip,
 	return 0;
 }
 
-static void armada_370_xp_teardown_msi_irq(struct msi_chip *chip,
+static void armada_370_xp_teardown_msi_irq(struct msi_controller *chip,
 					   unsigned int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
@@ -195,7 +195,7 @@ static const struct irq_domain_ops armada_370_xp_msi_irq_ops = {
 static int armada_370_xp_msi_init(struct device_node *node,
 				  phys_addr_t main_int_phys_base)
 {
-	struct msi_chip *msi_chip;
+	struct msi_controller *msi_chip;
 	u32 reg;
 	int ret;
 
diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c
index 8882b467be9..88471d3d98c 100644
--- a/drivers/of/of_pci.c
+++ b/drivers/of/of_pci.c
@@ -236,7 +236,7 @@ EXPORT_SYMBOL_GPL(of_pci_get_host_bridge_resources);
 static LIST_HEAD(of_pci_msi_chip_list);
 static DEFINE_MUTEX(of_pci_msi_chip_mutex);
 
-int of_pci_msi_chip_add(struct msi_chip *chip)
+int of_pci_msi_chip_add(struct msi_controller *chip)
 {
 	if (!of_property_read_bool(chip->of_node, "msi-controller"))
 		return -EINVAL;
@@ -249,7 +249,7 @@ int of_pci_msi_chip_add(struct msi_chip *chip)
 }
 EXPORT_SYMBOL_GPL(of_pci_msi_chip_add);
 
-void of_pci_msi_chip_remove(struct msi_chip *chip)
+void of_pci_msi_chip_remove(struct msi_controller *chip)
 {
 	mutex_lock(&of_pci_msi_chip_mutex);
 	list_del(&chip->list);
@@ -257,9 +257,9 @@ void of_pci_msi_chip_remove(struct msi_chip *chip)
 }
 EXPORT_SYMBOL_GPL(of_pci_msi_chip_remove);
 
-struct msi_chip *of_pci_find_msi_chip_by_node(struct device_node *of_node)
+struct msi_controller *of_pci_find_msi_chip_by_node(struct device_node *of_node)
 {
-	struct msi_chip *c;
+	struct msi_controller *c;
 
 	mutex_lock(&of_pci_msi_chip_mutex);
 	list_for_each_entry(c, &of_pci_msi_chip_list, list) {
diff --git a/drivers/pci/host/pci-keystone-dw.c b/drivers/pci/host/pci-keystone-dw.c
index 34086ce88e8..ac3d08c4277 100644
--- a/drivers/pci/host/pci-keystone-dw.c
+++ b/drivers/pci/host/pci-keystone-dw.c
@@ -205,7 +205,7 @@ const struct irq_domain_ops ks_dw_pcie_msi_domain_ops = {
 	.map = ks_dw_pcie_msi_map,
 };
 
-int ks_dw_pcie_msi_host_init(struct pcie_port *pp, struct msi_chip *chip)
+int ks_dw_pcie_msi_host_init(struct pcie_port *pp, struct msi_controller *chip)
 {
 	struct keystone_pcie *ks_pcie = to_keystone_pcie(pp);
 	int i;
diff --git a/drivers/pci/host/pci-keystone.h b/drivers/pci/host/pci-keystone.h
index 1fc1fceede9..478d932b602 100644
--- a/drivers/pci/host/pci-keystone.h
+++ b/drivers/pci/host/pci-keystone.h
@@ -55,4 +55,4 @@ void ks_dw_pcie_msi_set_irq(struct pcie_port *pp, int irq);
 void ks_dw_pcie_msi_clear_irq(struct pcie_port *pp, int irq);
 void ks_dw_pcie_v3_65_scan_bus(struct pcie_port *pp);
 int ks_dw_pcie_msi_host_init(struct pcie_port *pp,
-		struct msi_chip *chip);
+		struct msi_controller *chip);
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index b1315e197ff..cf907fec065 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -99,7 +99,7 @@ struct mvebu_pcie_port;
 struct mvebu_pcie {
 	struct platform_device *pdev;
 	struct mvebu_pcie_port *ports;
-	struct msi_chip *msi;
+	struct msi_controller *msi;
 	struct resource io;
 	char io_name[30];
 	struct resource realio;
diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c
index 3d43874319b..5529de7328b 100644
--- a/drivers/pci/host/pci-tegra.c
+++ b/drivers/pci/host/pci-tegra.c
@@ -238,7 +238,7 @@
 	)
 
 struct tegra_msi {
-	struct msi_chip chip;
+	struct msi_controller chip;
 	DECLARE_BITMAP(used, INT_PCI_MSI_NR);
 	struct irq_domain *domain;
 	unsigned long pages;
@@ -259,7 +259,7 @@ struct tegra_pcie_soc_data {
 	bool has_gen2;
 };
 
-static inline struct tegra_msi *to_tegra_msi(struct msi_chip *chip)
+static inline struct tegra_msi *to_tegra_msi(struct msi_controller *chip)
 {
 	return container_of(chip, struct tegra_msi, chip);
 }
@@ -1283,8 +1283,8 @@ static irqreturn_t tegra_pcie_msi_irq(int irq, void *data)
 	return processed > 0 ? IRQ_HANDLED : IRQ_NONE;
 }
 
-static int tegra_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev,
-			       struct msi_desc *desc)
+static int tegra_msi_setup_irq(struct msi_controller *chip,
+			       struct pci_dev *pdev, struct msi_desc *desc)
 {
 	struct tegra_msi *msi = to_tegra_msi(chip);
 	struct msi_msg msg;
@@ -1313,7 +1313,8 @@ static int tegra_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev,
 	return 0;
 }
 
-static void tegra_msi_teardown_irq(struct msi_chip *chip, unsigned int irq)
+static void tegra_msi_teardown_irq(struct msi_controller *chip,
+				   unsigned int irq)
 {
 	struct tegra_msi *msi = to_tegra_msi(chip);
 	struct irq_data *d = irq_get_irq_data(irq);
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index dfed00aa3ac..f4decad80ee 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -276,7 +276,7 @@ no_valid_irq:
 	return -ENOSPC;
 }
 
-static int dw_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev,
+static int dw_msi_setup_irq(struct msi_controller *chip, struct pci_dev *pdev,
 			struct msi_desc *desc)
 {
 	int irq, pos;
@@ -303,7 +303,7 @@ static int dw_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev,
 	return 0;
 }
 
-static void dw_msi_teardown_irq(struct msi_chip *chip, unsigned int irq)
+static void dw_msi_teardown_irq(struct msi_controller *chip, unsigned int irq)
 {
 	struct irq_data *data = irq_get_irq_data(irq);
 	struct msi_desc *msi = irq_data_get_msi(data);
@@ -312,7 +312,7 @@ static void dw_msi_teardown_irq(struct msi_chip *chip, unsigned int irq)
 	clear_irq_range(pp, irq, 1, data->hwirq);
 }
 
-static struct msi_chip dw_pcie_msi_chip = {
+static struct msi_controller dw_pcie_msi_chip = {
 	.setup_irq = dw_msi_setup_irq,
 	.teardown_irq = dw_msi_teardown_irq,
 };
diff --git a/drivers/pci/host/pcie-designware.h b/drivers/pci/host/pcie-designware.h
index c6256751daf..d0bbd276840 100644
--- a/drivers/pci/host/pcie-designware.h
+++ b/drivers/pci/host/pcie-designware.h
@@ -73,7 +73,7 @@ struct pcie_host_ops {
 	u32 (*get_msi_addr)(struct pcie_port *pp);
 	u32 (*get_msi_data)(struct pcie_port *pp, int pos);
 	void (*scan_bus)(struct pcie_port *pp);
-	int (*msi_host_init)(struct pcie_port *pp, struct msi_chip *chip);
+	int (*msi_host_init)(struct pcie_port *pp, struct msi_controller *chip);
 };
 
 int dw_pcie_cfg_read(void __iomem *addr, int where, int size, u32 *val);
diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c
index 61158e03ab5..b986c51d4df 100644
--- a/drivers/pci/host/pcie-rcar.c
+++ b/drivers/pci/host/pcie-rcar.c
@@ -111,14 +111,14 @@
 struct rcar_msi {
 	DECLARE_BITMAP(used, INT_PCI_MSI_NR);
 	struct irq_domain *domain;
-	struct msi_chip chip;
+	struct msi_controller chip;
 	unsigned long pages;
 	struct mutex lock;
 	int irq1;
 	int irq2;
 };
 
-static inline struct rcar_msi *to_rcar_msi(struct msi_chip *chip)
+static inline struct rcar_msi *to_rcar_msi(struct msi_controller *chip)
 {
 	return container_of(chip, struct rcar_msi, chip);
 }
@@ -622,7 +622,7 @@ static irqreturn_t rcar_pcie_msi_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int rcar_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev,
+static int rcar_msi_setup_irq(struct msi_controller *chip, struct pci_dev *pdev,
 			      struct msi_desc *desc)
 {
 	struct rcar_msi *msi = to_rcar_msi(chip);
@@ -652,7 +652,7 @@ static int rcar_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev,
 	return 0;
 }
 
-static void rcar_msi_teardown_irq(struct msi_chip *chip, unsigned int irq)
+static void rcar_msi_teardown_irq(struct msi_controller *chip, unsigned int irq)
 {
 	struct rcar_msi *msi = to_rcar_msi(chip);
 	struct irq_data *d = irq_get_irq_data(irq);
diff --git a/drivers/pci/host/pcie-xilinx.c b/drivers/pci/host/pcie-xilinx.c
index ccc496b33a9..f41bc601b7b 100644
--- a/drivers/pci/host/pcie-xilinx.c
+++ b/drivers/pci/host/pcie-xilinx.c
@@ -335,7 +335,8 @@ static int xilinx_pcie_assign_msi(struct xilinx_pcie_port *port)
  * @chip: MSI Chip descriptor
  * @irq: MSI IRQ to destroy
  */
-static void xilinx_msi_teardown_irq(struct msi_chip *chip, unsigned int irq)
+static void xilinx_msi_teardown_irq(struct msi_controller *chip,
+				    unsigned int irq)
 {
 	xilinx_pcie_destroy_msi(irq);
 }
@@ -348,7 +349,7 @@ static void xilinx_msi_teardown_irq(struct msi_chip *chip, unsigned int irq)
  *
  * Return: '0' on success and error value on failure
  */
-static int xilinx_pcie_msi_setup_irq(struct msi_chip *chip,
+static int xilinx_pcie_msi_setup_irq(struct msi_controller *chip,
 				     struct pci_dev *pdev,
 				     struct msi_desc *desc)
 {
@@ -380,7 +381,7 @@ static int xilinx_pcie_msi_setup_irq(struct msi_chip *chip,
 }
 
 /* MSI Chip Descriptor */
-static struct msi_chip xilinx_pcie_msi_chip = {
+static struct msi_controller xilinx_pcie_msi_chip = {
 	.setup_irq = xilinx_pcie_msi_setup_irq,
 	.teardown_irq = xilinx_msi_teardown_irq,
 };
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index d9a92cf6a6d..0260f393321 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -32,7 +32,7 @@ int pci_msi_ignore_mask;
 
 int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
 {
-	struct msi_chip *chip = dev->bus->msi;
+	struct msi_controller *chip = dev->bus->msi;
 	int err;
 
 	if (!chip || !chip->setup_irq)
@@ -49,7 +49,7 @@ int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
 
 void __weak arch_teardown_msi_irq(unsigned int irq)
 {
-	struct msi_chip *chip = irq_get_chip_data(irq);
+	struct msi_controller *chip = irq_get_chip_data(irq);
 
 	if (!chip || !chip->teardown_irq)
 		return;
diff --git a/include/linux/msi.h b/include/linux/msi.h
index efad12742e4..6704991b017 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -65,15 +65,15 @@ void arch_restore_msi_irqs(struct pci_dev *dev);
 void default_teardown_msi_irqs(struct pci_dev *dev);
 void default_restore_msi_irqs(struct pci_dev *dev);
 
-struct msi_chip {
+struct msi_controller {
 	struct module *owner;
 	struct device *dev;
 	struct device_node *of_node;
 	struct list_head list;
 
-	int (*setup_irq)(struct msi_chip *chip, struct pci_dev *dev,
+	int (*setup_irq)(struct msi_controller *chip, struct pci_dev *dev,
 			 struct msi_desc *desc);
-	void (*teardown_irq)(struct msi_chip *chip, unsigned int irq);
+	void (*teardown_irq)(struct msi_controller *chip, unsigned int irq);
 };
 
 #endif /* LINUX_MSI_H */
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
index 1fd207e7a84..ce0e5abeb45 100644
--- a/include/linux/of_pci.h
+++ b/include/linux/of_pci.h
@@ -59,13 +59,13 @@ int of_pci_get_host_bridge_resources(struct device_node *dev,
 #endif
 
 #if defined(CONFIG_OF) && defined(CONFIG_PCI_MSI)
-int of_pci_msi_chip_add(struct msi_chip *chip);
-void of_pci_msi_chip_remove(struct msi_chip *chip);
-struct msi_chip *of_pci_find_msi_chip_by_node(struct device_node *of_node);
+int of_pci_msi_chip_add(struct msi_controller *chip);
+void of_pci_msi_chip_remove(struct msi_controller *chip);
+struct msi_controller *of_pci_find_msi_chip_by_node(struct device_node *of_node);
 #else
-static inline int of_pci_msi_chip_add(struct msi_chip *chip) { return -EINVAL; }
-static inline void of_pci_msi_chip_remove(struct msi_chip *chip) { }
-static inline struct msi_chip *
+static inline int of_pci_msi_chip_add(struct msi_controller *chip) { return -EINVAL; }
+static inline void of_pci_msi_chip_remove(struct msi_controller *chip) { }
+static inline struct msi_controller *
 of_pci_find_msi_chip_by_node(struct device_node *of_node) { return NULL; }
 #endif
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 5be8db45e36..90a5fdec6b9 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -449,7 +449,7 @@ struct pci_bus {
 	struct resource busn_res;	/* bus numbers routed to this bus */
 
 	struct pci_ops	*ops;		/* configuration access functions */
-	struct msi_chip	*msi;		/* MSI controller */
+	struct msi_controller *msi;	/* MSI controller */
 	void		*sysdata;	/* hook for sys-specific extension */
 	struct proc_dir_entry *procdir;	/* directory entry in /proc/bus/pci */
 
-- 
cgit v1.2.3-70-g09d2


From d3cf6a4b01894e69e9e800ef76f34eaa13357ff1 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Mon, 10 Nov 2014 20:02:47 +0900
Subject: usb: renesas_usbhs: expand USB-DMAC channels for R-Car Gen2

This patch expands USB-DMAC channels for R-Car Gen2 SoCs. The SoCs
have 4 channels. If d{2,3}_{t,x}x_id are not set, this driver never
uses the expanded USB-DMAC channels.

Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/renesas_usbhs/common.h | 4 ++++
 drivers/usb/renesas_usbhs/fifo.c   | 2 ++
 drivers/usb/renesas_usbhs/fifo.h   | 2 +-
 include/linux/usb/renesas_usbhs.h  | 4 ++++
 4 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/usb/renesas_usbhs/common.h b/drivers/usb/renesas_usbhs/common.h
index c45667f942b..0427cdd1a48 100644
--- a/drivers/usb/renesas_usbhs/common.h
+++ b/drivers/usb/renesas_usbhs/common.h
@@ -102,6 +102,10 @@ struct usbhs_priv;
 #define DEVADD8		0x00E0
 #define DEVADD9		0x00E2
 #define DEVADDA		0x00E4
+#define D2FIFOSEL	0x00F0	/* for R-Car Gen2 */
+#define D2FIFOCTR	0x00F2	/* for R-Car Gen2 */
+#define D3FIFOSEL	0x00F4	/* for R-Car Gen2 */
+#define D3FIFOCTR	0x00F6	/* for R-Car Gen2 */
 
 /* SYSCFG */
 #define SCKE	(1 << 10)	/* USB Module Clock Enable */
diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c
index bc9a0506b54..f46271ce1b1 100644
--- a/drivers/usb/renesas_usbhs/fifo.c
+++ b/drivers/usb/renesas_usbhs/fifo.c
@@ -1234,6 +1234,8 @@ int usbhs_fifo_probe(struct usbhs_priv *priv)
 	/* DFIFO */
 	USBHS_DFIFO_INIT(priv, fifo, 0);
 	USBHS_DFIFO_INIT(priv, fifo, 1);
+	USBHS_DFIFO_INIT_NO_PORT(priv, fifo, 2);
+	USBHS_DFIFO_INIT_NO_PORT(priv, fifo, 3);
 
 	return 0;
 }
diff --git a/drivers/usb/renesas_usbhs/fifo.h b/drivers/usb/renesas_usbhs/fifo.h
index 899729ac085..f07037c1185 100644
--- a/drivers/usb/renesas_usbhs/fifo.h
+++ b/drivers/usb/renesas_usbhs/fifo.h
@@ -38,7 +38,7 @@ struct usbhs_fifo {
 	struct sh_dmae_slave	rx_slave;
 };
 
-#define USBHS_MAX_NUM_DFIFO	2
+#define USBHS_MAX_NUM_DFIFO	4
 struct usbhs_fifo_info {
 	struct usbhs_fifo cfifo;
 	struct usbhs_fifo dfifo[USBHS_MAX_NUM_DFIFO];
diff --git a/include/linux/usb/renesas_usbhs.h b/include/linux/usb/renesas_usbhs.h
index d5952bb6675..9fd9e481ea9 100644
--- a/include/linux/usb/renesas_usbhs.h
+++ b/include/linux/usb/renesas_usbhs.h
@@ -145,6 +145,10 @@ struct renesas_usbhs_driver_param {
 	int d0_rx_id;
 	int d1_tx_id;
 	int d1_rx_id;
+	int d2_tx_id;
+	int d2_rx_id;
+	int d3_tx_id;
+	int d3_rx_id;
 
 	/*
 	 * option:
-- 
cgit v1.2.3-70-g09d2


From c31accd159a6477b91de61ae237dce38e3f3ee4d Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 11 Nov 2014 19:45:57 +0100
Subject: net: phy: add module_phy_driver macro

Add helper macro for PHY drivers which do not do anything special in
module init/exit. This will allow us to eliminate a lot of boilerplate
code.

Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phy.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'include')

diff --git a/include/linux/phy.h b/include/linux/phy.h
index d090cfcaa16..07794e72013 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -772,4 +772,28 @@ int __init mdio_bus_init(void);
 void mdio_bus_exit(void);
 
 extern struct bus_type mdio_bus_type;
+
+/**
+ * module_phy_driver() - Helper macro for registering PHY drivers
+ * @__phy_drivers: array of PHY drivers to register
+ *
+ * Helper macro for PHY drivers which do not do anything special in module
+ * init/exit. Each module may only use this macro once, and calling it
+ * replaces module_init() and module_exit().
+ */
+#define phy_module_driver(__phy_drivers, __count)			\
+static int __init phy_module_init(void)					\
+{									\
+	return phy_drivers_register(__phy_drivers, __count);		\
+}									\
+module_init(phy_module_init);						\
+static void __exit phy_module_exit(void)				\
+{									\
+	phy_drivers_unregister(__phy_drivers, __count);			\
+}									\
+module_exit(phy_module_exit)
+
+#define module_phy_driver(__phy_drivers)				\
+	phy_module_driver(__phy_drivers, ARRAY_SIZE(__phy_drivers))
+
 #endif /* __PHY_H */
-- 
cgit v1.2.3-70-g09d2


From 955a9d202f470019f42979f0d1caec98843e39ce Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 11 Nov 2014 14:44:57 -0800
Subject: irda: Convert IRDA_DEBUG to pr_debug

Use the normal kernel debugging mechanism which also
enables dynamic_debug at the same time.

Other miscellanea:

o Remove sysctl for irda_debug
o Remove function tracing like uses (use ftrace instead)
o Coalesce formats
o Realign arguments
o Remove unnecessary OOM messages

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/irda/act200l-sir.c        |   8 --
 drivers/net/irda/actisys-sir.c        |   3 +-
 drivers/net/irda/ali-ircc.c           | 206 +++++++++++++------------------
 drivers/net/irda/donauboe.c           |  96 ++++++---------
 drivers/net/irda/girbil-sir.c         |   8 --
 drivers/net/irda/irda-usb.c           |  95 +++++++-------
 drivers/net/irda/irtty-sir.c          |   8 +-
 drivers/net/irda/litelink-sir.c       |   8 --
 drivers/net/irda/ma600-sir.c          |  14 +--
 drivers/net/irda/mcp2120-sir.c        |   8 --
 drivers/net/irda/mcs7780.c            |   8 +-
 drivers/net/irda/nsc-ircc.c           | 163 ++++++++++++------------
 drivers/net/irda/old_belkin-sir.c     |   8 --
 drivers/net/irda/sir_dev.c            |  44 ++++---
 drivers/net/irda/sir_dongle.c         |   4 +-
 drivers/net/irda/smsc-ircc2.c         | 125 ++++++++++---------
 drivers/net/irda/tekram-sir.c         |  12 +-
 drivers/net/irda/toim3232-sir.c       |  12 +-
 drivers/net/irda/via-ircc.c           | 154 ++++++++++-------------
 drivers/net/irda/vlsi_ir.c            |  27 ++--
 drivers/net/irda/w83977af_ir.c        |  68 ++++------
 include/net/irda/irda.h               |  11 --
 include/net/irda/irlap.h              |   2 +-
 net/irda/af_irda.c                    | 209 ++++++++++++++-----------------
 net/irda/discovery.c                  |  12 +-
 net/irda/ircomm/ircomm_core.c         |  50 ++------
 net/irda/ircomm/ircomm_event.c        |  24 ++--
 net/irda/ircomm/ircomm_lmp.c          |  28 +----
 net/irda/ircomm/ircomm_param.c        |  41 +++----
 net/irda/ircomm/ircomm_ttp.c          |  20 +--
 net/irda/ircomm/ircomm_tty.c          |  95 +++++---------
 net/irda/ircomm/ircomm_tty_attach.c   | 106 +++++++---------
 net/irda/ircomm/ircomm_tty_ioctl.c    |  18 +--
 net/irda/irda_device.c                |  16 +--
 net/irda/iriap.c                      |  91 +++++---------
 net/irda/iriap_event.c                |  38 +++---
 net/irda/irias_object.c               |  14 +--
 net/irda/irlan/irlan_client.c         |  64 ++++------
 net/irda/irlan/irlan_client_event.c   |  62 +++-------
 net/irda/irlan/irlan_common.c         |  77 +++---------
 net/irda/irlan/irlan_eth.c            |  24 ++--
 net/irda/irlan/irlan_event.c          |   4 +-
 net/irda/irlan/irlan_filter.c         |  23 ++--
 net/irda/irlan/irlan_provider.c       |  42 +++----
 net/irda/irlan/irlan_provider_event.c |  16 +--
 net/irda/irlap.c                      |  55 ++-------
 net/irda/irlap_event.c                | 225 ++++++++++++++++------------------
 net/irda/irlap_frame.c                |  87 +++++--------
 net/irda/irlmp.c                      | 167 ++++++++++---------------
 net/irda/irlmp_event.c                | 121 ++++++++----------
 net/irda/irlmp_frame.c                |  56 ++++-----
 net/irda/irmod.c                      |  12 --
 net/irda/irnetlink.c                  |   4 +-
 net/irda/irqueue.c                    |  14 +--
 net/irda/irsysctl.c                   |   9 --
 net/irda/irttp.c                      | 127 ++++++++-----------
 net/irda/parameters.c                 |  38 +++---
 net/irda/qos.c                        |  71 +++++------
 net/irda/wrapper.c                    |  22 ++--
 59 files changed, 1244 insertions(+), 1930 deletions(-)

(limited to 'include')

diff --git a/drivers/net/irda/act200l-sir.c b/drivers/net/irda/act200l-sir.c
index a9116456bc9..e8917511e1a 100644
--- a/drivers/net/irda/act200l-sir.c
+++ b/drivers/net/irda/act200l-sir.c
@@ -107,8 +107,6 @@ static int act200l_open(struct sir_dev *dev)
 {
 	struct qos_info *qos = &dev->qos;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* Power on the dongle */
 	sirdev_set_dtr_rts(dev, TRUE, TRUE);
 
@@ -124,8 +122,6 @@ static int act200l_open(struct sir_dev *dev)
 
 static int act200l_close(struct sir_dev *dev)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* Power off the dongle */
 	sirdev_set_dtr_rts(dev, FALSE, FALSE);
 
@@ -143,8 +139,6 @@ static int act200l_change_speed(struct sir_dev *dev, unsigned speed)
 	u8 control[3];
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* Clear DTR and set RTS to enter command mode */
 	sirdev_set_dtr_rts(dev, FALSE, TRUE);
 
@@ -212,8 +206,6 @@ static int act200l_reset(struct sir_dev *dev)
 	};
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	switch (state) {
 	case SIRDEV_STATE_DONGLE_RESET:
 		/* Reset the dongle : set RTS low for 25 ms */
diff --git a/drivers/net/irda/actisys-sir.c b/drivers/net/irda/actisys-sir.c
index 50b2141a610..e224b8b9951 100644
--- a/drivers/net/irda/actisys-sir.c
+++ b/drivers/net/irda/actisys-sir.c
@@ -165,8 +165,7 @@ static int actisys_change_speed(struct sir_dev *dev, unsigned speed)
 	int ret = 0;
 	int i = 0;
 
-        IRDA_DEBUG(4, "%s(), speed=%d (was %d)\n", __func__,
-        	speed, dev->speed);
+	pr_debug("%s(), speed=%d (was %d)\n", __func__, speed, dev->speed);
 
 	/* dongle was already resetted from irda_request state machine,
 	 * we are in known state (dongle default)
diff --git a/drivers/net/irda/ali-ircc.c b/drivers/net/irda/ali-ircc.c
index 7f23e5ff099..588680a72fa 100644
--- a/drivers/net/irda/ali-ircc.c
+++ b/drivers/net/irda/ali-ircc.c
@@ -154,8 +154,6 @@ static int __init ali_ircc_init(void)
 	int reg, revision;
 	int i = 0;
 	
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__);
-
 	ret = platform_driver_register(&ali_ircc_driver);
         if (ret) {
 		net_err_ratelimited("%s, Can't register driver!\n",
@@ -168,7 +166,7 @@ static int __init ali_ircc_init(void)
 	/* Probe for all the ALi chipsets we know about */
 	for (chip= chips; chip->name; chip++, i++) 
 	{
-		IRDA_DEBUG(2, "%s(), Probing for %s ...\n", __func__, chip->name);
+		pr_debug("%s(), Probing for %s ...\n", __func__, chip->name);
 				
 		/* Try all config registers for this chip */
 		for (cfg=0; cfg<2; cfg++)
@@ -198,12 +196,13 @@ static int __init ali_ircc_init(void)
 				
 			if (reg == chip->cid_value)
 			{
-				IRDA_DEBUG(2, "%s(), Chip found at 0x%03x\n", __func__, cfg_base);
+				pr_debug("%s(), Chip found at 0x%03x\n",
+					 __func__, cfg_base);
 					   
 				outb(0x1F, cfg_base);
 				revision = inb(cfg_base+1);
-				IRDA_DEBUG(2, "%s(), Found %s chip, revision=%d\n", __func__,
-					   chip->name, revision);					
+				pr_debug("%s(), Found %s chip, revision=%d\n",
+					 __func__, chip->name, revision);
 				
 				/* 
 				 * If the user supplies the base address, then
@@ -225,15 +224,14 @@ static int __init ali_ircc_init(void)
 			}
 			else
 			{
-				IRDA_DEBUG(2, "%s(), No %s chip at 0x%03x\n", __func__, chip->name, cfg_base);
+				pr_debug("%s(), No %s chip at 0x%03x\n",
+					 __func__, chip->name, cfg_base);
 			}
 			/* Exit configuration */
 			outb(0xbb, cfg_base);
 		}
 	}		
 		
-	IRDA_DEBUG(2, "%s(), ----------------- End -----------------\n", __func__);
-
 	if (ret)
 		platform_driver_unregister(&ali_ircc_driver);
 
@@ -250,8 +248,6 @@ static void __exit ali_ircc_cleanup(void)
 {
 	int i;
 
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__);
-
 	for (i=0; i < ARRAY_SIZE(dev_self); i++) {
 		if (dev_self[i])
 			ali_ircc_close(dev_self[i]);
@@ -259,7 +255,6 @@ static void __exit ali_ircc_cleanup(void)
 	
 	platform_driver_unregister(&ali_ircc_driver);
 
-	IRDA_DEBUG(2, "%s(), ----------------- End -----------------\n", __func__);
 }
 
 static const struct net_device_ops ali_ircc_sir_ops = {
@@ -289,8 +284,6 @@ static int ali_ircc_open(int i, chipio_t *info)
 	int dongle_id;
 	int err;
 			
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__);
-
 	if (i >= ARRAY_SIZE(dev_self)) {
 		net_err_ratelimited("%s(), maximum number of supported chips reached!\n",
 				    __func__);
@@ -394,7 +387,6 @@ static int ali_ircc_open(int i, chipio_t *info)
 		
 	self->io.dongle_id = dongle_id;
 
-	IRDA_DEBUG(2, "%s(), ----------------- End -----------------\n", __func__);
 	
 	return 0;
 
@@ -423,8 +415,6 @@ static int __exit ali_ircc_close(struct ali_ircc_cb *self)
 {
 	int iobase;
 
-	IRDA_DEBUG(4, "%s(), ---------------- Start ----------------\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
         iobase = self->io.fir_base;
@@ -433,7 +423,7 @@ static int __exit ali_ircc_close(struct ali_ircc_cb *self)
 	unregister_netdev(self->netdev);
 
 	/* Release the PORT that this driver is using */
-	IRDA_DEBUG(4, "%s(), Releasing Region %03x\n", __func__, self->io.fir_base);
+	pr_debug("%s(), Releasing Region %03x\n", __func__, self->io.fir_base);
 	release_region(self->io.fir_base, self->io.fir_ext);
 
 	if (self->tx_buff.head)
@@ -447,7 +437,6 @@ static int __exit ali_ircc_close(struct ali_ircc_cb *self)
 	dev_self[self->index] = NULL;
 	free_netdev(self->netdev);
 	
-	IRDA_DEBUG(2, "%s(), ----------------- End -----------------\n", __func__);
 	
 	return 0;
 }
@@ -490,7 +479,6 @@ static int ali_ircc_probe_53(ali_chip_t *chip, chipio_t *info)
 	int cfg_base = info->cfg_base;
 	int hi, low, reg;
 	
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__);
 	
 	/* Enter Configuration */
 	outb(chip->entr1, cfg_base);
@@ -509,13 +497,13 @@ static int ali_ircc_probe_53(ali_chip_t *chip, chipio_t *info)
 	
 	info->sir_base = info->fir_base;
 	
-	IRDA_DEBUG(2, "%s(), probing fir_base=0x%03x\n", __func__, info->fir_base);
+	pr_debug("%s(), probing fir_base=0x%03x\n", __func__, info->fir_base);
 		
 	/* Read IRQ control register */
 	outb(0x70, cfg_base);
 	reg = inb(cfg_base+1);
 	info->irq = reg & 0x0f;
-	IRDA_DEBUG(2, "%s(), probing irq=%d\n", __func__, info->irq);
+	pr_debug("%s(), probing irq=%d\n", __func__, info->irq);
 	
 	/* Read DMA channel */
 	outb(0x74, cfg_base);
@@ -526,24 +514,23 @@ static int ali_ircc_probe_53(ali_chip_t *chip, chipio_t *info)
 		net_warn_ratelimited("%s(), No DMA channel assigned !\n",
 				     __func__);
 	else
-		IRDA_DEBUG(2, "%s(), probing dma=%d\n", __func__, info->dma);
+		pr_debug("%s(), probing dma=%d\n", __func__, info->dma);
 	
 	/* Read Enabled Status */
 	outb(0x30, cfg_base);
 	reg = inb(cfg_base+1);
 	info->enabled = (reg & 0x80) && (reg & 0x01);
-	IRDA_DEBUG(2, "%s(), probing enabled=%d\n", __func__, info->enabled);
+	pr_debug("%s(), probing enabled=%d\n", __func__, info->enabled);
 	
 	/* Read Power Status */
 	outb(0x22, cfg_base);
 	reg = inb(cfg_base+1);
 	info->suspended = (reg & 0x20);
-	IRDA_DEBUG(2, "%s(), probing suspended=%d\n", __func__, info->suspended);
+	pr_debug("%s(), probing suspended=%d\n", __func__, info->suspended);
 	
 	/* Exit configuration */
 	outb(0xbb, cfg_base);
 		
-	IRDA_DEBUG(2, "%s(), ----------------- End -----------------\n", __func__);
 	
 	return 0;	
 }
@@ -561,7 +548,6 @@ static int ali_ircc_setup(chipio_t *info)
 	int version;
 	int iobase = info->fir_base;
 	
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__);
 	
 	/* Locking comments :
 	 * Most operations here need to be protected. We are called before
@@ -622,7 +608,6 @@ static int ali_ircc_setup(chipio_t *info)
 	// outb(UART_IER_RDI, iobase+UART_IER); //benjamin 2000/11/23 01:25PM
 	// Turn on the interrupts in ali_ircc_net_open
 	
-	IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__);
 	
 	return 0;
 }
@@ -639,7 +624,6 @@ static int ali_ircc_read_dongle_id (int i, chipio_t *info)
 	int dongle_id, reg;
 	int cfg_base = info->cfg_base;
 	
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__);
 		
 	/* Enter Configuration */
 	outb(chips[i].entr1, cfg_base);
@@ -653,13 +637,12 @@ static int ali_ircc_read_dongle_id (int i, chipio_t *info)
 	outb(0xf0, cfg_base);
 	reg = inb(cfg_base+1);	
 	dongle_id = ((reg>>6)&0x02) | ((reg>>5)&0x01);
-	IRDA_DEBUG(2, "%s(), probing dongle_id=%d, dongle_types=%s\n", __func__,
-		dongle_id, dongle_types[dongle_id]);
+	pr_debug("%s(), probing dongle_id=%d, dongle_types=%s\n",
+		 __func__, dongle_id, dongle_types[dongle_id]);
 	
 	/* Exit configuration */
 	outb(0xbb, cfg_base);
 			
-	IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__);
 	
 	return dongle_id;
 }
@@ -676,7 +659,6 @@ static irqreturn_t ali_ircc_interrupt(int irq, void *dev_id)
 	struct ali_ircc_cb *self;
 	int ret;
 		
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__);
 		
 	self = netdev_priv(dev);
 	
@@ -690,7 +672,6 @@ static irqreturn_t ali_ircc_interrupt(int irq, void *dev_id)
 		
 	spin_unlock(&self->lock);
 	
-	IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__);
 	return ret;
 }
 /*
@@ -704,7 +685,6 @@ static irqreturn_t ali_ircc_fir_interrupt(struct ali_ircc_cb *self)
 	__u8 eir, OldMessageCount;
 	int iobase, tmp;
 	
-	IRDA_DEBUG(1, "%s(), ---------------- Start ----------------\n", __func__);
 	
 	iobase = self->io.fir_base;
 	
@@ -717,10 +697,10 @@ static irqreturn_t ali_ircc_fir_interrupt(struct ali_ircc_cb *self)
 	//self->ier = inb(iobase+FIR_IER); 		2000/12/1 04:32PM
 	eir = self->InterruptID & self->ier; /* Mask out the interesting ones */ 
 	
-	IRDA_DEBUG(1, "%s(), self->InterruptID = %x\n", __func__,self->InterruptID);
-	IRDA_DEBUG(1, "%s(), self->LineStatus = %x\n", __func__,self->LineStatus);
-	IRDA_DEBUG(1, "%s(), self->ier = %x\n", __func__,self->ier);
-	IRDA_DEBUG(1, "%s(), eir = %x\n", __func__,eir);
+	pr_debug("%s(), self->InterruptID = %x\n", __func__, self->InterruptID);
+	pr_debug("%s(), self->LineStatus = %x\n", __func__, self->LineStatus);
+	pr_debug("%s(), self->ier = %x\n", __func__, self->ier);
+	pr_debug("%s(), eir = %x\n", __func__, eir);
 	
 	/* Disable interrupts */
 	 SetCOMInterrupts(self, FALSE);
@@ -731,7 +711,8 @@ static irqreturn_t ali_ircc_fir_interrupt(struct ali_ircc_cb *self)
 	{		
 		if (self->io.direction == IO_XMIT) /* TX */
 		{
-			IRDA_DEBUG(1, "%s(), ******* IIR_EOM (Tx) *******\n", __func__);
+			pr_debug("%s(), ******* IIR_EOM (Tx) *******\n",
+				 __func__);
 			
 			if(ali_ircc_dma_xmit_complete(self))
 			{
@@ -750,23 +731,27 @@ static irqreturn_t ali_ircc_fir_interrupt(struct ali_ircc_cb *self)
 		}	
 		else /* RX */
 		{
-			IRDA_DEBUG(1, "%s(), ******* IIR_EOM (Rx) *******\n", __func__);
+			pr_debug("%s(), ******* IIR_EOM (Rx) *******\n",
+				 __func__);
 			
 			if(OldMessageCount > ((self->LineStatus+1) & 0x07))
 			{
 				self->rcvFramesOverflow = TRUE;	
-				IRDA_DEBUG(1, "%s(), ******* self->rcvFramesOverflow = TRUE ********\n", __func__);
+				pr_debug("%s(), ******* self->rcvFramesOverflow = TRUE ********\n",
+					 __func__);
 			}
 						
 			if (ali_ircc_dma_receive_complete(self))
 			{
-				IRDA_DEBUG(1, "%s(), ******* receive complete ********\n", __func__);
+				pr_debug("%s(), ******* receive complete ********\n",
+					 __func__);
 				
 				self->ier = IER_EOM;				
 			}
 			else
 			{
-				IRDA_DEBUG(1, "%s(), ******* Not receive complete ********\n", __func__);
+				pr_debug("%s(), ******* Not receive complete ********\n",
+					 __func__);
 				
 				self->ier = IER_EOM | IER_TIMER;								
 			}	
@@ -779,7 +764,8 @@ static irqreturn_t ali_ircc_fir_interrupt(struct ali_ircc_cb *self)
 		if(OldMessageCount > ((self->LineStatus+1) & 0x07))
 		{
 			self->rcvFramesOverflow = TRUE;	
-			IRDA_DEBUG(1, "%s(), ******* self->rcvFramesOverflow = TRUE *******\n", __func__);
+			pr_debug("%s(), ******* self->rcvFramesOverflow = TRUE *******\n",
+				 __func__);
 		}
 		/* Disable Timer */
 		switch_bank(iobase, BANK1);
@@ -811,7 +797,6 @@ static irqreturn_t ali_ircc_fir_interrupt(struct ali_ircc_cb *self)
 	/* Restore Interrupt */	
 	SetCOMInterrupts(self, TRUE);	
 		
-	IRDA_DEBUG(1, "%s(), ----------------- End ---------------\n", __func__);
 	return IRQ_RETVAL(eir);
 }
 
@@ -826,7 +811,6 @@ static irqreturn_t ali_ircc_sir_interrupt(struct ali_ircc_cb *self)
 	int iobase;
 	int iir, lsr;
 	
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__);
 	
 	iobase = self->io.sir_base;
 
@@ -835,13 +819,13 @@ static irqreturn_t ali_ircc_sir_interrupt(struct ali_ircc_cb *self)
 		/* Clear interrupt */
 		lsr = inb(iobase+UART_LSR);
 
-		IRDA_DEBUG(4, "%s(), iir=%02x, lsr=%02x, iobase=%#x\n", __func__,
-			   iir, lsr, iobase);
+		pr_debug("%s(), iir=%02x, lsr=%02x, iobase=%#x\n",
+			 __func__, iir, lsr, iobase);
 
 		switch (iir) 
 		{
 			case UART_IIR_RLSI:
-				IRDA_DEBUG(2, "%s(), RLSI\n", __func__);
+				pr_debug("%s(), RLSI\n", __func__);
 				break;
 			case UART_IIR_RDI:
 				/* Receive interrupt */
@@ -855,15 +839,14 @@ static irqreturn_t ali_ircc_sir_interrupt(struct ali_ircc_cb *self)
 				}				
 				break;
 			default:
-				IRDA_DEBUG(0, "%s(), unhandled IIR=%#x\n", __func__, iir);
+				pr_debug("%s(), unhandled IIR=%#x\n",
+					 __func__, iir);
 				break;
 		} 
 		
 	}
 	
 	
-	IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__);
-
 	return IRQ_RETVAL(iir);
 }
 
@@ -879,7 +862,6 @@ static void ali_ircc_sir_receive(struct ali_ircc_cb *self)
 	int boguscount = 0;
 	int iobase;
 	
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__);
 	IRDA_ASSERT(self != NULL, return;);
 
 	iobase = self->io.sir_base;
@@ -894,12 +876,11 @@ static void ali_ircc_sir_receive(struct ali_ircc_cb *self)
 
 		/* Make sure we don't stay here too long */
 		if (boguscount++ > 32) {
-			IRDA_DEBUG(2,"%s(), breaking!\n", __func__);
+			pr_debug("%s(), breaking!\n", __func__);
 			break;
 		}
 	} while (inb(iobase+UART_LSR) & UART_LSR_DR);	
 	
-	IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__ );
 }
 
 /*
@@ -916,7 +897,6 @@ static void ali_ircc_sir_write_wakeup(struct ali_ircc_cb *self)
 
 	IRDA_ASSERT(self != NULL, return;);
 
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__ );
 	
 	iobase = self->io.sir_base;
 
@@ -935,16 +915,18 @@ static void ali_ircc_sir_write_wakeup(struct ali_ircc_cb *self)
 		{
 			/* We must wait until all data are gone */
 			while(!(inb(iobase+UART_LSR) & UART_LSR_TEMT))
-				IRDA_DEBUG(1, "%s(), UART_LSR_THRE\n", __func__ );
+				pr_debug("%s(), UART_LSR_THRE\n", __func__);
 			
-			IRDA_DEBUG(1, "%s(), Changing speed! self->new_speed = %d\n", __func__ , self->new_speed);
+			pr_debug("%s(), Changing speed! self->new_speed = %d\n",
+				 __func__, self->new_speed);
 			ali_ircc_change_speed(self, self->new_speed);
 			self->new_speed = 0;			
 			
 			// benjamin 2000/11/10 06:32PM
 			if (self->io.speed > 115200)
 			{
-				IRDA_DEBUG(2, "%s(), ali_ircc_change_speed from UART_LSR_TEMT\n", __func__ );
+				pr_debug("%s(), ali_ircc_change_speed from UART_LSR_TEMT\n",
+					 __func__);
 					
 				self->ier = IER_EOM;
 				// SetCOMInterrupts(self, TRUE);							
@@ -962,7 +944,6 @@ static void ali_ircc_sir_write_wakeup(struct ali_ircc_cb *self)
 		outb(UART_IER_RDI, iobase+UART_IER);
 	}
 		
-	IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__ );
 }
 
 static void ali_ircc_change_speed(struct ali_ircc_cb *self, __u32 baud)
@@ -970,9 +951,8 @@ static void ali_ircc_change_speed(struct ali_ircc_cb *self, __u32 baud)
 	struct net_device *dev = self->netdev;
 	int iobase;
 	
-	IRDA_DEBUG(1, "%s(), ---------------- Start ----------------\n", __func__ );
 	
-	IRDA_DEBUG(2, "%s(), setting speed = %d\n", __func__ , baud);
+	pr_debug("%s(), setting speed = %d\n", __func__, baud);
 	
 	/* This function *must* be called with irq off and spin-lock.
 	 * - Jean II */
@@ -1011,7 +991,6 @@ static void ali_ircc_change_speed(struct ali_ircc_cb *self, __u32 baud)
 		
 	netif_wake_queue(self->netdev);	
 	
-	IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__ );
 }
 
 static void ali_ircc_fir_change_speed(struct ali_ircc_cb *priv, __u32 baud)
@@ -1021,14 +1000,14 @@ static void ali_ircc_fir_change_speed(struct ali_ircc_cb *priv, __u32 baud)
 	struct ali_ircc_cb *self = priv;
 	struct net_device *dev;
 
-	IRDA_DEBUG(1, "%s(), ---------------- Start ----------------\n", __func__ );
 		
 	IRDA_ASSERT(self != NULL, return;);
 
 	dev = self->netdev;
 	iobase = self->io.fir_base;
 	
-	IRDA_DEBUG(1, "%s(), self->io.speed = %d, change to speed = %d\n", __func__ ,self->io.speed,baud);
+	pr_debug("%s(), self->io.speed = %d, change to speed = %d\n",
+		 __func__, self->io.speed, baud);
 	
 	/* Come from SIR speed */
 	if(self->io.speed <=115200)
@@ -1042,7 +1021,6 @@ static void ali_ircc_fir_change_speed(struct ali_ircc_cb *priv, __u32 baud)
 	// Set Dongle Speed mode
 	ali_ircc_change_dongle_speed(self, baud);
 		
-	IRDA_DEBUG(1, "%s(), ----------------- End ------------------\n", __func__ );
 }
 
 /*
@@ -1060,9 +1038,8 @@ static void ali_ircc_sir_change_speed(struct ali_ircc_cb *priv, __u32 speed)
 	int lcr;    /* Line control reg */
 	int divisor;
 
-	IRDA_DEBUG(1, "%s(), ---------------- Start ----------------\n", __func__ );
 	
-	IRDA_DEBUG(1, "%s(), Setting speed to: %d\n", __func__ , speed);
+	pr_debug("%s(), Setting speed to: %d\n", __func__, speed);
 
 	IRDA_ASSERT(self != NULL, return;);
 
@@ -1116,7 +1093,6 @@ static void ali_ircc_sir_change_speed(struct ali_ircc_cb *priv, __u32 speed)
 	
 	spin_unlock_irqrestore(&self->lock, flags);
 	
-	IRDA_DEBUG(1, "%s(), ----------------- End ------------------\n", __func__ );
 }
 
 static void ali_ircc_change_dongle_speed(struct ali_ircc_cb *priv, int speed)
@@ -1126,14 +1102,14 @@ static void ali_ircc_change_dongle_speed(struct ali_ircc_cb *priv, int speed)
 	int iobase,dongle_id;
 	int tmp = 0;
 			
-	IRDA_DEBUG(1, "%s(), ---------------- Start ----------------\n", __func__ );
 	
 	iobase = self->io.fir_base; 	/* or iobase = self->io.sir_base; */
 	dongle_id = self->io.dongle_id;
 	
 	/* We are already locked, no need to do it again */
 		
-	IRDA_DEBUG(1, "%s(), Set Speed for %s , Speed = %d\n", __func__ , dongle_types[dongle_id], speed);
+	pr_debug("%s(), Set Speed for %s , Speed = %d\n",
+		 __func__, dongle_types[dongle_id], speed);
 	
 	switch_bank(iobase, BANK2);
 	tmp = inb(iobase+FIR_IRDA_CR);
@@ -1297,7 +1273,6 @@ static void ali_ircc_change_dongle_speed(struct ali_ircc_cb *priv, int speed)
 			
 	switch_bank(iobase, BANK0);
 	
-	IRDA_DEBUG(1, "%s(), ----------------- End ------------------\n", __func__ );
 }
 
 /*
@@ -1310,11 +1285,10 @@ static int ali_ircc_sir_write(int iobase, int fifo_size, __u8 *buf, int len)
 {
 	int actual = 0;
 	
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__ );
 		
 	/* Tx FIFO should be empty! */
 	if (!(inb(iobase+UART_LSR) & UART_LSR_THRE)) {
-		IRDA_DEBUG(0, "%s(), failed, fifo not empty!\n", __func__ );
+		pr_debug("%s(), failed, fifo not empty!\n", __func__);
 		return 0;
 	}
         
@@ -1326,7 +1300,6 @@ static int ali_ircc_sir_write(int iobase, int fifo_size, __u8 *buf, int len)
 		actual++;
 	}
 	
-        IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__ );
 	return actual;
 }
 
@@ -1342,7 +1315,6 @@ static int ali_ircc_net_open(struct net_device *dev)
 	int iobase;
 	char hwname[32];
 		
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__ );
 	
 	IRDA_ASSERT(dev != NULL, return -1;);
 	
@@ -1386,7 +1358,6 @@ static int ali_ircc_net_open(struct net_device *dev)
 	 */
 	self->irlap = irlap_open(dev, &self->qos, hwname);
 		
-	IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__ );
 	
 	return 0;
 }
@@ -1403,7 +1374,6 @@ static int ali_ircc_net_close(struct net_device *dev)
 	struct ali_ircc_cb *self;
 	//int iobase;
 			
-	IRDA_DEBUG(4, "%s(), ---------------- Start ----------------\n", __func__ );
 		
 	IRDA_ASSERT(dev != NULL, return -1;);
 
@@ -1426,7 +1396,6 @@ static int ali_ircc_net_close(struct net_device *dev)
 	free_irq(self->io.irq, dev);
 	free_dma(self->io.dma);
 
-	IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__ );
 	
 	return 0;
 }
@@ -1446,7 +1415,6 @@ static netdev_tx_t ali_ircc_fir_hard_xmit(struct sk_buff *skb,
 	__u32 speed;
 	int mtt, diff;
 	
-	IRDA_DEBUG(1, "%s(), ---------------- Start -----------------\n", __func__ );
 	
 	self = netdev_priv(dev);
 	iobase = self->io.fir_base;
@@ -1500,7 +1468,8 @@ static netdev_tx_t ali_ircc_fir_hard_xmit(struct sk_buff *skb,
 			diff = self->now.tv_usec - self->stamp.tv_usec;
 			/* self->stamp is set from ali_ircc_dma_receive_complete() */
 							
-			IRDA_DEBUG(1, "%s(), ******* diff = %d *******\n", __func__ , diff);
+			pr_debug("%s(), ******* diff = %d *******\n",
+				 __func__, diff);
 			
 			if (diff < 0) 
 				diff += 1000000;
@@ -1522,7 +1491,8 @@ static netdev_tx_t ali_ircc_fir_hard_xmit(struct sk_buff *skb,
 					/* Adjust for timer resolution */
 					mtt = (mtt+250) / 500; 	/* 4 discard, 5 get advanced, Let's round off */
 					
-					IRDA_DEBUG(1, "%s(), ************** mtt = %d ***********\n", __func__ , mtt);
+					pr_debug("%s(), ************** mtt = %d ***********\n",
+						 __func__, mtt);
 					
 					/* Setup timer */
 					if (mtt == 1) /* 500 us */
@@ -1579,7 +1549,6 @@ static netdev_tx_t ali_ircc_fir_hard_xmit(struct sk_buff *skb,
 	spin_unlock_irqrestore(&self->lock, flags);
 	dev_kfree_skb(skb);
 
-	IRDA_DEBUG(1, "%s(), ----------------- End ------------------\n", __func__ );
 	return NETDEV_TX_OK;	
 }
 
@@ -1590,7 +1559,6 @@ static void ali_ircc_dma_xmit(struct ali_ircc_cb *self)
 	unsigned char FIFO_OPTI, Hi, Lo;
 	
 	
-	IRDA_DEBUG(1, "%s(), ---------------- Start -----------------\n", __func__ );
 	
 	iobase = self->io.fir_base;
 	
@@ -1641,7 +1609,8 @@ static void ali_ircc_dma_xmit(struct ali_ircc_cb *self)
 	tmp = inb(iobase+FIR_LCR_B);
 	tmp &= ~0x20; // Disable SIP
 	outb(((unsigned char)(tmp & 0x3f) | LCR_B_TX_MODE) & ~LCR_B_BW, iobase+FIR_LCR_B);
-	IRDA_DEBUG(1, "%s(), *** Change to TX mode: FIR_LCR_B = 0x%x ***\n", __func__ , inb(iobase+FIR_LCR_B));
+	pr_debug("%s(), *** Change to TX mode: FIR_LCR_B = 0x%x ***\n",
+		 __func__, inb(iobase + FIR_LCR_B));
 	
 	outb(0, iobase+FIR_LSR);
 			
@@ -1651,7 +1620,6 @@ static void ali_ircc_dma_xmit(struct ali_ircc_cb *self)
 	
 	switch_bank(iobase, BANK0); 
 	
-	IRDA_DEBUG(1, "%s(), ----------------- End ------------------\n", __func__ );
 }
 
 static int  ali_ircc_dma_xmit_complete(struct ali_ircc_cb *self)
@@ -1659,7 +1627,6 @@ static int  ali_ircc_dma_xmit_complete(struct ali_ircc_cb *self)
 	int iobase;
 	int ret = TRUE;
 	
-	IRDA_DEBUG(1, "%s(), ---------------- Start -----------------\n", __func__ );
 	
 	iobase = self->io.fir_base;
 	
@@ -1716,7 +1683,6 @@ static int  ali_ircc_dma_xmit_complete(struct ali_ircc_cb *self)
 		
 	switch_bank(iobase, BANK0); 
 	
-	IRDA_DEBUG(1, "%s(), ----------------- End ------------------\n", __func__ );
 	return ret;
 }
 
@@ -1731,7 +1697,6 @@ static int ali_ircc_dma_receive(struct ali_ircc_cb *self)
 {
 	int iobase, tmp;
 	
-	IRDA_DEBUG(1, "%s(), ---------------- Start -----------------\n", __func__ );
 	
 	iobase = self->io.fir_base;
 	
@@ -1769,7 +1734,8 @@ static int ali_ircc_dma_receive(struct ali_ircc_cb *self)
 	//switch_bank(iobase, BANK0);
 	tmp = inb(iobase+FIR_LCR_B);
 	outb((unsigned char)(tmp &0x3f) | LCR_B_RX_MODE | LCR_B_BW , iobase + FIR_LCR_B); // 2000/12/1 05:16PM
-	IRDA_DEBUG(1, "%s(), *** Change To RX mode: FIR_LCR_B = 0x%x ***\n", __func__ , inb(iobase+FIR_LCR_B));
+	pr_debug("%s(), *** Change To RX mode: FIR_LCR_B = 0x%x ***\n",
+		 __func__, inb(iobase + FIR_LCR_B));
 			
 	/* Set Rx Threshold */
 	switch_bank(iobase, BANK1);
@@ -1781,7 +1747,6 @@ static int ali_ircc_dma_receive(struct ali_ircc_cb *self)
 	outb(CR_DMA_EN | CR_DMA_BURST, iobase+FIR_CR);
 				
 	switch_bank(iobase, BANK0); 
-	IRDA_DEBUG(1, "%s(), ----------------- End ------------------\n", __func__ );
 	return 0;
 }
 
@@ -1792,8 +1757,6 @@ static int  ali_ircc_dma_receive_complete(struct ali_ircc_cb *self)
 	__u8 status, MessageCount;
 	int len, i, iobase, val;	
 
-	IRDA_DEBUG(1, "%s(), ---------------- Start -----------------\n", __func__ );
-
 	st_fifo = &self->st_fifo;		
 	iobase = self->io.fir_base;	
 		
@@ -1801,7 +1764,7 @@ static int  ali_ircc_dma_receive_complete(struct ali_ircc_cb *self)
 	MessageCount = inb(iobase+ FIR_LSR)&0x07;
 	
 	if (MessageCount > 0)	
-		IRDA_DEBUG(0, "%s(), Message count = %d,\n", __func__ , MessageCount);
+		pr_debug("%s(), Message count = %d\n", __func__, MessageCount);
 		
 	for (i=0; i<=MessageCount; i++)
 	{
@@ -1814,11 +1777,11 @@ static int  ali_ircc_dma_receive_complete(struct ali_ircc_cb *self)
 		len = len << 8; 
 		len |= inb(iobase+FIR_RX_DSR_LO);
 		
-		IRDA_DEBUG(1, "%s(), RX Length = 0x%.2x,\n", __func__ , len);
-		IRDA_DEBUG(1, "%s(), RX Status = 0x%.2x,\n", __func__ , status);
+		pr_debug("%s(), RX Length = 0x%.2x,\n", __func__ , len);
+		pr_debug("%s(), RX Status = 0x%.2x,\n", __func__ , status);
 		
 		if (st_fifo->tail >= MAX_RX_WINDOW) {
-			IRDA_DEBUG(0, "%s(), window is full!\n", __func__ );
+			pr_debug("%s(), window is full!\n", __func__);
 			continue;
 		}
 			
@@ -1841,7 +1804,8 @@ static int  ali_ircc_dma_receive_complete(struct ali_ircc_cb *self)
 		/* Check for errors */
 		if ((status & 0xd8) || self->rcvFramesOverflow || (len==0)) 		
 		{
-			IRDA_DEBUG(0,"%s(), ************* RX Errors ************\n", __func__ );
+			pr_debug("%s(), ************* RX Errors ************\n",
+				 __func__);
 			
 			/* Skip frame */
 			self->netdev->stats.rx_errors++;
@@ -1851,29 +1815,34 @@ static int  ali_ircc_dma_receive_complete(struct ali_ircc_cb *self)
 			if (status & LSR_FIFO_UR) 
 			{
 				self->netdev->stats.rx_frame_errors++;
-				IRDA_DEBUG(0,"%s(), ************* FIFO Errors ************\n", __func__ );
+				pr_debug("%s(), ************* FIFO Errors ************\n",
+					 __func__);
 			}	
 			if (status & LSR_FRAME_ERROR)
 			{
 				self->netdev->stats.rx_frame_errors++;
-				IRDA_DEBUG(0,"%s(), ************* FRAME Errors ************\n", __func__ );
+				pr_debug("%s(), ************* FRAME Errors ************\n",
+					 __func__);
 			}
 							
 			if (status & LSR_CRC_ERROR) 
 			{
 				self->netdev->stats.rx_crc_errors++;
-				IRDA_DEBUG(0,"%s(), ************* CRC Errors ************\n", __func__ );
+				pr_debug("%s(), ************* CRC Errors ************\n",
+					 __func__);
 			}
 			
 			if(self->rcvFramesOverflow)
 			{
 				self->netdev->stats.rx_frame_errors++;
-				IRDA_DEBUG(0,"%s(), ************* Overran DMA buffer ************\n", __func__ );
+				pr_debug("%s(), ************* Overran DMA buffer ************\n",
+					 __func__);
 			}
 			if(len == 0)
 			{
 				self->netdev->stats.rx_frame_errors++;
-				IRDA_DEBUG(0,"%s(), ********** Receive Frame Size = 0 *********\n", __func__ );
+				pr_debug("%s(), ********** Receive Frame Size = 0 *********\n",
+					 __func__);
 			}
 		}	 
 		else 
@@ -1885,7 +1854,8 @@ static int  ali_ircc_dma_receive_complete(struct ali_ircc_cb *self)
 				val = inb(iobase+FIR_BSR);	
 				if ((val& BSR_FIFO_NOT_EMPTY)== 0x80) 
 				{
-					IRDA_DEBUG(0, "%s(), ************* BSR_FIFO_NOT_EMPTY ************\n", __func__ );
+					pr_debug("%s(), ************* BSR_FIFO_NOT_EMPTY ************\n",
+						 __func__);
 					
 					/* Put this entry back in fifo */
 					st_fifo->head--;
@@ -1946,7 +1916,6 @@ static int  ali_ircc_dma_receive_complete(struct ali_ircc_cb *self)
 	
 	switch_bank(iobase, BANK0);	
 		
-	IRDA_DEBUG(1, "%s(), ----------------- End ------------------\n", __func__ );
 	return TRUE;
 }
 
@@ -1966,7 +1935,6 @@ static netdev_tx_t ali_ircc_sir_hard_xmit(struct sk_buff *skb,
 	int iobase;
 	__u32 speed;
 	
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__ );
 	
 	IRDA_ASSERT(dev != NULL, return NETDEV_TX_OK;);
 	
@@ -2015,7 +1983,6 @@ static netdev_tx_t ali_ircc_sir_hard_xmit(struct sk_buff *skb,
 
 	dev_kfree_skb(skb);
 	
-	IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__ );
 	
 	return NETDEV_TX_OK;	
 }
@@ -2034,7 +2001,6 @@ static int ali_ircc_net_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	unsigned long flags;
 	int ret = 0;
 	
-	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __func__ );
 	
 	IRDA_ASSERT(dev != NULL, return -1;);
 
@@ -2042,11 +2008,11 @@ static int ali_ircc_net_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 
 	IRDA_ASSERT(self != NULL, return -1;);
 
-	IRDA_DEBUG(2, "%s(), %s, (cmd=0x%X)\n", __func__ , dev->name, cmd);
+	pr_debug("%s(), %s, (cmd=0x%X)\n", __func__ , dev->name, cmd);
 	
 	switch (cmd) {
 	case SIOCSBANDWIDTH: /* Set bandwidth */
-		IRDA_DEBUG(1, "%s(), SIOCSBANDWIDTH\n", __func__ );
+		pr_debug("%s(), SIOCSBANDWIDTH\n", __func__);
 		/*
 		 * This function will also be used by IrLAP to change the
 		 * speed, so we still must allow for speed change within
@@ -2060,13 +2026,13 @@ static int ali_ircc_net_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		spin_unlock_irqrestore(&self->lock, flags);
 		break;
 	case SIOCSMEDIABUSY: /* Set media busy */
-		IRDA_DEBUG(1, "%s(), SIOCSMEDIABUSY\n", __func__ );
+		pr_debug("%s(), SIOCSMEDIABUSY\n", __func__);
 		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
 		irda_device_set_media_busy(self->netdev, TRUE);
 		break;
 	case SIOCGRECEIVING: /* Check if we are receiving right now */
-		IRDA_DEBUG(2, "%s(), SIOCGRECEIVING\n", __func__ );
+		pr_debug("%s(), SIOCGRECEIVING\n", __func__);
 		/* This is protected */
 		irq->ifr_receiving = ali_ircc_is_receiving(self);
 		break;
@@ -2074,7 +2040,6 @@ static int ali_ircc_net_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		ret = -EOPNOTSUPP;
 	}
 	
-	IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__ );
 	
 	return ret;
 }
@@ -2091,7 +2056,6 @@ static int ali_ircc_is_receiving(struct ali_ircc_cb *self)
 	int status = FALSE;
 	int iobase;		
 	
-	IRDA_DEBUG(2, "%s(), ---------------- Start -----------------\n", __func__ );
 	
 	IRDA_ASSERT(self != NULL, return FALSE;);
 
@@ -2105,7 +2069,8 @@ static int ali_ircc_is_receiving(struct ali_ircc_cb *self)
 		if((inb(iobase+FIR_FIFO_FR) & 0x3f) != 0) 		
 		{
 			/* We are receiving something */
-			IRDA_DEBUG(1, "%s(), We are receiving something\n", __func__ );
+			pr_debug("%s(), We are receiving something\n",
+				 __func__);
 			status = TRUE;
 		}
 		switch_bank(iobase, BANK0);		
@@ -2117,7 +2082,6 @@ static int ali_ircc_is_receiving(struct ali_ircc_cb *self)
 	
 	spin_unlock_irqrestore(&self->lock, flags);
 	
-	IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__ );
 	
 	return status;
 }
@@ -2163,7 +2127,8 @@ static void SetCOMInterrupts(struct ali_ircc_cb *self , unsigned char enable)
 	
 	int iobase = self->io.fir_base; /* or sir_base */
 
-	IRDA_DEBUG(2, "%s(), -------- Start -------- ( Enable = %d )\n", __func__ , enable);
+	pr_debug("%s(), -------- Start -------- ( Enable = %d )\n",
+		 __func__, enable);
 	
 	/* Enable the interrupt which we wish to */
 	if (enable){
@@ -2204,14 +2169,12 @@ static void SetCOMInterrupts(struct ali_ircc_cb *self , unsigned char enable)
 	else
 		outb(newMask, iobase+UART_IER);
 		
-	IRDA_DEBUG(2, "%s(), ----------------- End ------------------\n", __func__ );
 }
 
 static void SIR2FIR(int iobase)
 {
 	//unsigned char tmp;
 		
-	IRDA_DEBUG(1, "%s(), ---------------- Start ----------------\n", __func__ );
 	
 	/* Already protected (change_speed() or setup()), no need to lock.
 	 * Jean II */
@@ -2227,14 +2190,12 @@ static void SIR2FIR(int iobase)
 	//tmp |= 0x20;
 	//outb(tmp, iobase+FIR_LCR_B);	
 	
-	IRDA_DEBUG(1, "%s(), ----------------- End ------------------\n", __func__ );
 }
 
 static void FIR2SIR(int iobase)
 {
 	unsigned char val;
 	
-	IRDA_DEBUG(1, "%s(), ---------------- Start ----------------\n", __func__ );
 	
 	/* Already protected (change_speed() or setup()), no need to lock.
 	 * Jean II */
@@ -2250,7 +2211,6 @@ static void FIR2SIR(int iobase)
 	val = inb(iobase+UART_LSR);
 	val = inb(iobase+UART_MSR);
 	
-	IRDA_DEBUG(1, "%s(), ----------------- End ------------------\n", __func__ );
 }
 
 MODULE_AUTHOR("Benjamin Kong <benjamin_kong@ali.com.tw>");
diff --git a/drivers/net/irda/donauboe.c b/drivers/net/irda/donauboe.c
index a87a82ca111..b337e6d23a8 100644
--- a/drivers/net/irda/donauboe.c
+++ b/drivers/net/irda/donauboe.c
@@ -232,7 +232,7 @@ char head=tete;
 for (i=0;i<len;i+=16) {
     for (j=0;j<16 && i+j<len;j++) { sprintf(&dump[3*j],"%02x.",data[i+j]); }
     dump [3*j]=0;
-    IRDA_DEBUG (2, "%c%s\n",head , dump);
+    pr_debug("%c%s\n", head, dump);
     head='+';
     }
 }
@@ -245,8 +245,6 @@ toshoboe_dumpregs (struct toshoboe_cb *self)
 {
   __u32 ringbase;
 
-  IRDA_DEBUG (4, "%s()\n", __func__);
-
   ringbase = INB (OBOE_RING_BASE0) << 10;
   ringbase |= INB (OBOE_RING_BASE1) << 18;
   ringbase |= INB (OBOE_RING_BASE2) << 26;
@@ -293,8 +291,6 @@ static void
 toshoboe_disablebm (struct toshoboe_cb *self)
 {
   __u8 command;
-  IRDA_DEBUG (4, "%s()\n", __func__);
-
   pci_read_config_byte (self->pdev, PCI_COMMAND, &command);
   command &= ~PCI_COMMAND_MASTER;
   pci_write_config_byte (self->pdev, PCI_COMMAND, command);
@@ -305,8 +301,6 @@ toshoboe_disablebm (struct toshoboe_cb *self)
 static void
 toshoboe_stopchip (struct toshoboe_cb *self)
 {
-  IRDA_DEBUG (4, "%s()\n", __func__);
-
   /*Disable interrupts */
   OUTB (0x0, OBOE_IER);
   /*Disable DMA, Disable Rx, Disable Tx */
@@ -350,7 +344,7 @@ toshoboe_setbaud (struct toshoboe_cb *self)
   __u16 pconfig = 0;
   __u8 config0l = 0;
 
-  IRDA_DEBUG (2, "%s(%d/%d)\n", __func__, self->speed, self->io.speed);
+  pr_debug("%s(%d/%d)\n", __func__, self->speed, self->io.speed);
 
   switch (self->speed)
     {
@@ -482,7 +476,6 @@ toshoboe_setbaud (struct toshoboe_cb *self)
 static void
 toshoboe_enablebm (struct toshoboe_cb *self)
 {
-  IRDA_DEBUG (4, "%s()\n", __func__);
   pci_set_master (self->pdev);
 }
 
@@ -492,8 +485,6 @@ toshoboe_initring (struct toshoboe_cb *self)
 {
   int i;
 
-  IRDA_DEBUG (4, "%s()\n", __func__);
-
   for (i = 0; i < TX_SLOTS; ++i)
     {
       self->ring->tx[i].len = 0;
@@ -550,8 +541,6 @@ toshoboe_startchip (struct toshoboe_cb *self)
 {
   __u32 physaddr;
 
-  IRDA_DEBUG (4, "%s()\n", __func__);
-
   toshoboe_initring (self);
   toshoboe_enablebm (self);
   OUTBP (OBOE_CONFIG1_RESET, OBOE_CONFIG1);
@@ -636,9 +625,8 @@ toshoboe_makemttpacket (struct toshoboe_cb *self, void *buf, int mtt)
   xbofs=xbofs/80000; /*Eight bits per byte, and mtt is in us*/
   xbofs++;
 
-  IRDA_DEBUG (2, DRIVER_NAME
-      ": generated mtt of %d bytes for %d us at %d baud\n"
-	  , xbofs,mtt,self->speed);
+  pr_debug(DRIVER_NAME ": generated mtt of %d bytes for %d us at %d baud\n",
+	   xbofs, mtt, self->speed);
 
   if (xbofs > TX_LEN)
     {
@@ -824,8 +812,6 @@ toshoboe_probe (struct toshoboe_cb *self)
 #endif
   unsigned long flags;
 
-  IRDA_DEBUG (4, "%s()\n", __func__);
-
   if (request_irq (self->io.irq, toshoboe_probeinterrupt,
                    self->io.irqflags, "toshoboe", (void *) self))
     {
@@ -983,10 +969,10 @@ toshoboe_hard_xmit (struct sk_buff *skb, struct net_device *dev)
 
   IRDA_ASSERT (self != NULL, return NETDEV_TX_OK; );
 
-  IRDA_DEBUG (1, "%s.tx:%x(%x)%x\n", __func__
-      ,skb->len,self->txpending,INB (OBOE_ENABLEH));
+  pr_debug("%s.tx:%x(%x)%x\n",
+	   __func__, skb->len, self->txpending, INB(OBOE_ENABLEH));
   if (!cb->magic) {
-      IRDA_DEBUG (2, "%s.Not IrLAP:%x\n", __func__, cb->magic);
+	  pr_debug("%s.Not IrLAP:%x\n", __func__, cb->magic);
 #ifdef DUMP_PACKETS
       _dumpbufs(skb->data,skb->len,'>');
 #endif
@@ -1012,8 +998,8 @@ toshoboe_hard_xmit (struct sk_buff *skb, struct net_device *dev)
       if (self->txpending || skb->len)
         {
           self->new_speed = speed;
-          IRDA_DEBUG (1, "%s: Queued TxDone scheduled speed change %d\n" ,
-		      __func__, speed);
+	  pr_debug("%s: Queued TxDone scheduled speed change %d\n" ,
+		   __func__, speed);
           /* if no data, that's all! */
           if (!skb->len)
             {
@@ -1055,8 +1041,7 @@ toshoboe_hard_xmit (struct sk_buff *skb, struct net_device *dev)
       /* which we will add a wrong checksum to */
 
       mtt = toshoboe_makemttpacket (self, self->tx_bufs[self->txs], mtt);
-      IRDA_DEBUG (1, "%s.mtt:%x(%x)%d\n", __func__
-          ,skb->len,mtt,self->txpending);
+      pr_debug("%s.mtt:%x(%x)%d\n", __func__, skb->len, mtt, self->txpending);
       if (mtt)
         {
           self->ring->tx[self->txs].len = mtt & 0xfff;
@@ -1099,8 +1084,9 @@ dumpbufs(skb->data,skb->len,'>');
 
   if (self->ring->tx[self->txs].control & OBOE_CTL_TX_HW_OWNS)
     {
-      IRDA_DEBUG (0, "%s.ful:%x(%x)%x\n", __func__
-          ,skb->len, self->ring->tx[self->txs].control, self->txpending);
+	    pr_debug("%s.ful:%x(%x)%x\n",
+		     __func__, skb->len, self->ring->tx[self->txs].control,
+		     self->txpending);
       toshoboe_start_DMA(self, OBOE_CONFIG0H_ENTX);
       spin_unlock_irqrestore(&self->spinlock, flags);
       return NETDEV_TX_BUSY;
@@ -1177,8 +1163,7 @@ toshoboe_interrupt (int irq, void *dev_id)
           if (self->ring->tx[i].control & OBOE_CTL_TX_HW_OWNS)
               self->txpending++;
         }
-      IRDA_DEBUG (1, "%s.txd(%x)%x/%x\n", __func__
-          ,irqstat,txp,self->txpending);
+      pr_debug("%s.txd(%x)%x/%x\n", __func__, irqstat, txp, self->txpending);
 
       txp = INB (OBOE_TXSLOT) & OBOE_SLOT_MASK;
 
@@ -1206,8 +1191,8 @@ toshoboe_interrupt (int irq, void *dev_id)
       if ((!self->txpending) && (self->new_speed))
         {
           self->speed = self->new_speed;
-          IRDA_DEBUG (1, "%s: Executed TxDone scheduled speed change %d\n",
-		      __func__, self->speed);
+	  pr_debug("%s: Executed TxDone scheduled speed change %d\n",
+		   __func__, self->speed);
           toshoboe_setbaud (self);
         }
 
@@ -1222,8 +1207,8 @@ toshoboe_interrupt (int irq, void *dev_id)
         {
           int len = self->ring->rx[self->rxs].len;
           skb = NULL;
-          IRDA_DEBUG (3, "%s.rcv:%x(%x)\n", __func__
-		      ,len,self->ring->rx[self->rxs].control);
+	  pr_debug("%s.rcv:%x(%x)\n", __func__
+		   , len, self->ring->rx[self->rxs].control);
 
 #ifdef DUMP_PACKETS
 dumpbufs(self->rx_bufs[self->rxs],len,'<');
@@ -1244,7 +1229,7 @@ dumpbufs(self->rx_bufs[self->rxs],len,'<');
                       len -= 2;
                   else
                       len = 0;
-                  IRDA_DEBUG (1, "%s.SIR:%x(%x)\n", __func__, len,enable);
+                  pr_debug("%s.SIR:%x(%x)\n", __func__, len, enable);
                 }
 
 #ifdef USE_MIR
@@ -1254,7 +1239,7 @@ dumpbufs(self->rx_bufs[self->rxs],len,'<');
                       len -= 2;
                   else
                       len = 0;
-                  IRDA_DEBUG (2, "%s.MIR:%x(%x)\n", __func__, len,enable);
+                  pr_debug("%s.MIR:%x(%x)\n", __func__, len, enable);
                 }
 #endif
               else if (enable & OBOE_ENABLEH_FIRON)
@@ -1263,10 +1248,10 @@ dumpbufs(self->rx_bufs[self->rxs],len,'<');
                       len -= 4;   /*FIXME: check this */
                   else
                       len = 0;
-                  IRDA_DEBUG (1, "%s.FIR:%x(%x)\n", __func__, len,enable);
+                  pr_debug("%s.FIR:%x(%x)\n", __func__, len, enable);
                 }
               else
-                  IRDA_DEBUG (0, "%s.?IR:%x(%x)\n", __func__, len,enable);
+		      pr_debug("%s.?IR:%x(%x)\n", __func__, len, enable);
 
               if (len)
                 {
@@ -1299,8 +1284,8 @@ dumpbufs(self->rx_bufs[self->rxs],len,'<');
             /* (SIR) data is splitted in several slots. */
             /* we have to join all the received buffers received */
             /*in a large buffer before checking CRC. */
-            IRDA_DEBUG (0, "%s.err:%x(%x)\n", __func__
-                ,len,self->ring->rx[self->rxs].control);
+		    pr_debug("%s.err:%x(%x)\n", __func__
+			     , len, self->ring->rx[self->rxs].control);
             }
 
           self->ring->rx[self->rxs].len = 0x0;
@@ -1327,8 +1312,8 @@ dumpbufs(self->rx_bufs[self->rxs],len,'<');
   if (irqstat & OBOE_INT_SIP)
     {
       self->int_sip++;
-      IRDA_DEBUG (1, "%s.sip:%x(%x)%x\n", __func__
-	      ,self->int_sip,irqstat,self->txpending);
+      pr_debug("%s.sip:%x(%x)%x\n",
+	       __func__, self->int_sip, irqstat, self->txpending);
     }
   return IRQ_HANDLED;
 }
@@ -1341,8 +1326,6 @@ toshoboe_net_open (struct net_device *dev)
   unsigned long flags;
   int rc;
 
-  IRDA_DEBUG (4, "%s()\n", __func__);
-
   self = netdev_priv(dev);
 
   if (self->async)
@@ -1379,8 +1362,6 @@ toshoboe_net_close (struct net_device *dev)
 {
   struct toshoboe_cb *self;
 
-  IRDA_DEBUG (4, "%s()\n", __func__);
-
   IRDA_ASSERT (dev != NULL, return -1; );
   self = netdev_priv(dev);
 
@@ -1424,7 +1405,7 @@ toshoboe_net_ioctl (struct net_device *dev, struct ifreq *rq, int cmd)
 
   IRDA_ASSERT (self != NULL, return -1; );
 
-  IRDA_DEBUG (5, "%s(), %s, (cmd=0x%X)\n", __func__, dev->name, cmd);
+  pr_debug("%s(), %s, (cmd=0x%X)\n", __func__, dev->name, cmd);
 
   /* Disable interrupts & save flags */
   spin_lock_irqsave(&self->spinlock, flags);
@@ -1436,8 +1417,8 @@ toshoboe_net_ioctl (struct net_device *dev, struct ifreq *rq, int cmd)
        * speed, so we still must allow for speed change within
        * interrupt context.
        */
-      IRDA_DEBUG (1, "%s(BANDWIDTH), %s, (%X/%ld\n", __func__
-          ,dev->name, INB (OBOE_STATUS), irq->ifr_baudrate );
+	    pr_debug("%s(BANDWIDTH), %s, (%X/%ld\n",
+		     __func__, dev->name, INB(OBOE_STATUS), irq->ifr_baudrate);
       if (!in_interrupt () && !capable (CAP_NET_ADMIN)) {
 	ret = -EPERM;
 	goto out;
@@ -1449,8 +1430,9 @@ toshoboe_net_ioctl (struct net_device *dev, struct ifreq *rq, int cmd)
       self->new_speed = irq->ifr_baudrate;
       break;
     case SIOCSMEDIABUSY:       /* Set media busy */
-      IRDA_DEBUG (1, "%s(MEDIABUSY), %s, (%X/%x)\n", __func__
-          ,dev->name, INB (OBOE_STATUS), capable (CAP_NET_ADMIN) );
+	    pr_debug("%s(MEDIABUSY), %s, (%X/%x)\n",
+		     __func__, dev->name,
+		     INB(OBOE_STATUS), capable(CAP_NET_ADMIN));
       if (!capable (CAP_NET_ADMIN)) {
 	ret = -EPERM;
 	goto out;
@@ -1459,11 +1441,11 @@ toshoboe_net_ioctl (struct net_device *dev, struct ifreq *rq, int cmd)
       break;
     case SIOCGRECEIVING:       /* Check if we are receiving right now */
       irq->ifr_receiving = (INB (OBOE_STATUS) & OBOE_STATUS_RXBUSY) ? 1 : 0;
-      IRDA_DEBUG (3, "%s(RECEIVING), %s, (%X/%x)\n", __func__
-          ,dev->name, INB (OBOE_STATUS), irq->ifr_receiving );
+	    pr_debug("%s(RECEIVING), %s, (%X/%x)\n",
+		     __func__, dev->name, INB(OBOE_STATUS), irq->ifr_receiving);
       break;
     default:
-      IRDA_DEBUG (1, "%s(?), %s, (cmd=0x%X)\n", __func__, dev->name, cmd);
+	    pr_debug("%s(?), %s, (cmd=0x%X)\n", __func__, dev->name, cmd);
       ret = -EOPNOTSUPP;
     }
 out:
@@ -1490,8 +1472,6 @@ toshoboe_close (struct pci_dev *pci_dev)
   int i;
   struct toshoboe_cb *self = pci_get_drvdata(pci_dev);
 
-  IRDA_DEBUG (4, "%s()\n", __func__);
-
   IRDA_ASSERT (self != NULL, return; );
 
   if (!self->stopped)
@@ -1538,8 +1518,6 @@ toshoboe_open (struct pci_dev *pci_dev, const struct pci_device_id *pdid)
   int ok = 0;
   int err;
 
-  IRDA_DEBUG (4, "%s()\n", __func__);
-
   if ((err=pci_enable_device(pci_dev)))
     return err;
 
@@ -1700,8 +1678,6 @@ toshoboe_gotosleep (struct pci_dev *pci_dev, pm_message_t crap)
   unsigned long flags;
   int i = 10;
 
-  IRDA_DEBUG (4, "%s()\n", __func__);
-
   if (!self || self->stopped)
     return 0;
 
@@ -1728,8 +1704,6 @@ toshoboe_wakeup (struct pci_dev *pci_dev)
   struct toshoboe_cb *self = pci_get_drvdata(pci_dev);
   unsigned long flags;
 
-  IRDA_DEBUG (4, "%s()\n", __func__);
-
   if (!self || !self->stopped)
     return 0;
 
diff --git a/drivers/net/irda/girbil-sir.c b/drivers/net/irda/girbil-sir.c
index f0512ad7dae..7e0a5b8c6d5 100644
--- a/drivers/net/irda/girbil-sir.c
+++ b/drivers/net/irda/girbil-sir.c
@@ -86,8 +86,6 @@ static int girbil_open(struct sir_dev *dev)
 {
 	struct qos_info *qos = &dev->qos;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Power on dongle */
 	sirdev_set_dtr_rts(dev, TRUE, TRUE);
 
@@ -102,8 +100,6 @@ static int girbil_open(struct sir_dev *dev)
 
 static int girbil_close(struct sir_dev *dev)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Power off dongle */
 	sirdev_set_dtr_rts(dev, FALSE, FALSE);
 
@@ -126,8 +122,6 @@ static int girbil_change_speed(struct sir_dev *dev, unsigned speed)
 	u8 control[2];
 	static int ret = 0;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* dongle alread reset - port and dongle at default speed */
 
 	switch(state) {
@@ -210,8 +204,6 @@ static int girbil_reset(struct sir_dev *dev)
 	u8 control = GIRBIL_TXEN | GIRBIL_RXEN;
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	switch (state) {
 	case SIRDEV_STATE_DONGLE_RESET:
 		/* Reset dongle */
diff --git a/drivers/net/irda/irda-usb.c b/drivers/net/irda/irda-usb.c
index e9aedbe3fc9..48b2f9a321b 100644
--- a/drivers/net/irda/irda-usb.c
+++ b/drivers/net/irda/irda-usb.c
@@ -176,12 +176,13 @@ static void irda_usb_build_header(struct irda_usb_cb *self,
 		    (!force) && (self->speed != -1)) {
 			/* No speed and xbofs change here
 			 * (we'll do it later in the write callback) */
-			IRDA_DEBUG(2, "%s(), not changing speed yet\n", __func__);
+			pr_debug("%s(), not changing speed yet\n", __func__);
 			*header = 0;
 			return;
 		}
 
-		IRDA_DEBUG(2, "%s(), changing speed to %d\n", __func__, self->new_speed);
+		pr_debug("%s(), changing speed to %d\n",
+			 __func__, self->new_speed);
 		self->speed = self->new_speed;
 		/* We will do ` self->new_speed = -1; ' in the completion
 		 * handler just in case the current URB fail - Jean II */
@@ -227,7 +228,8 @@ static void irda_usb_build_header(struct irda_usb_cb *self,
 	
 	/* Set the negotiated additional XBOFS */
 	if (self->new_xbofs != -1) {
-		IRDA_DEBUG(2, "%s(), changing xbofs to %d\n", __func__, self->new_xbofs);
+		pr_debug("%s(), changing xbofs to %d\n",
+			 __func__, self->new_xbofs);
 		self->xbofs = self->new_xbofs;
 		/* We will do ` self->new_xbofs = -1; ' in the completion
 		 * handler just in case the current URB fail - Jean II */
@@ -301,8 +303,8 @@ static void irda_usb_change_speed_xbofs(struct irda_usb_cb *self)
 	struct urb *urb;
 	int ret;
 
-	IRDA_DEBUG(2, "%s(), speed=%d, xbofs=%d\n", __func__,
-		   self->new_speed, self->new_xbofs);
+	pr_debug("%s(), speed=%d, xbofs=%d\n", __func__,
+		 self->new_speed, self->new_xbofs);
 
 	/* Grab the speed URB */
 	urb = self->speed_urb;
@@ -346,8 +348,6 @@ static void speed_bulk_callback(struct urb *urb)
 {
 	struct irda_usb_cb *self = urb->context;
 	
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* We should always have a context */
 	IRDA_ASSERT(self != NULL, return;);
 	/* We should always be called for the speed URB */
@@ -356,7 +356,8 @@ static void speed_bulk_callback(struct urb *urb)
 	/* Check for timeout and other USB nasties */
 	if (urb->status != 0) {
 		/* I get a lot of -ECONNABORTED = -103 here - Jean II */
-		IRDA_DEBUG(0, "%s(), URB complete status %d, transfer_flags 0x%04X\n", __func__, urb->status, urb->transfer_flags);
+		pr_debug("%s(), URB complete status %d, transfer_flags 0x%04X\n",
+			 __func__, urb->status, urb->transfer_flags);
 
 		/* Don't do anything here, that might confuse the USB layer.
 		 * Instead, we will wait for irda_usb_net_timeout(), the
@@ -391,7 +392,7 @@ static netdev_tx_t irda_usb_hard_xmit(struct sk_buff *skb,
 	s16 xbofs;
 	int res, mtt;
 
-	IRDA_DEBUG(4, "%s() on %s\n", __func__, netdev->name);
+	pr_debug("%s() on %s\n", __func__, netdev->name);
 
 	netif_stop_queue(netdev);
 
@@ -402,7 +403,7 @@ static netdev_tx_t irda_usb_hard_xmit(struct sk_buff *skb,
 	 * We need to check self->present under the spinlock because
 	 * of irda_usb_disconnect() is synchronous - Jean II */
 	if (!self->present) {
-		IRDA_DEBUG(0, "%s(), Device is gone...\n", __func__);
+		pr_debug("%s(), Device is gone...\n", __func__);
 		goto drop;
 	}
 
@@ -554,8 +555,6 @@ static void write_bulk_callback(struct urb *urb)
 	struct sk_buff *skb = urb->context;
 	struct irda_usb_cb *self = ((struct irda_skb_cb *) skb->cb)->context;
 	
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* We should always have a context */
 	IRDA_ASSERT(self != NULL, return;);
 	/* We should always be called for the speed URB */
@@ -568,7 +567,8 @@ static void write_bulk_callback(struct urb *urb)
 	/* Check for timeout and other USB nasties */
 	if (urb->status != 0) {
 		/* I get a lot of -ECONNABORTED = -103 here - Jean II */
-		IRDA_DEBUG(0, "%s(), URB complete status %d, transfer_flags 0x%04X\n", __func__, urb->status, urb->transfer_flags);
+		pr_debug("%s(), URB complete status %d, transfer_flags 0x%04X\n",
+			 __func__, urb->status, urb->transfer_flags);
 
 		/* Don't do anything here, that might confuse the USB layer,
 		 * and we could go in recursion and blow the kernel stack...
@@ -587,7 +587,7 @@ static void write_bulk_callback(struct urb *urb)
 
 	/* If the network is closed, stop everything */
 	if ((!self->netopen) || (!self->present)) {
-		IRDA_DEBUG(0, "%s(), Network is gone...\n", __func__);
+		pr_debug("%s(), Network is gone...\n", __func__);
 		spin_unlock_irqrestore(&self->lock, flags);
 		return;
 	}
@@ -598,7 +598,7 @@ static void write_bulk_callback(struct urb *urb)
 		    (self->new_xbofs != self->xbofs)) {
 			/* We haven't changed speed yet (because of
 			 * IUC_SPEED_BUG), so do it now - Jean II */
-			IRDA_DEBUG(1, "%s(), Changing speed now...\n", __func__);
+			pr_debug("%s(), Changing speed now...\n", __func__);
 			irda_usb_change_speed_xbofs(self);
 		} else {
 			/* New speed and xbof is now committed in hardware */
@@ -630,7 +630,7 @@ static void irda_usb_net_timeout(struct net_device *netdev)
 	struct urb *urb;
 	int	done = 0;	/* If we have made any progress */
 
-	IRDA_DEBUG(0, "%s(), Network layer thinks we timed out!\n", __func__);
+	pr_debug("%s(), Network layer thinks we timed out!\n", __func__);
 	IRDA_ASSERT(self != NULL, return;);
 
 	/* Protect us from USB callbacks, net Tx and else. */
@@ -647,7 +647,8 @@ static void irda_usb_net_timeout(struct net_device *netdev)
 	/* Check speed URB */
 	urb = self->speed_urb;
 	if (urb->status != 0) {
-		IRDA_DEBUG(0, "%s: Speed change timed out, urb->status=%d, urb->transfer_flags=0x%04X\n", netdev->name, urb->status, urb->transfer_flags);
+		pr_debug("%s: Speed change timed out, urb->status=%d, urb->transfer_flags=0x%04X\n",
+			 netdev->name, urb->status, urb->transfer_flags);
 
 		switch (urb->status) {
 		case -EINPROGRESS:
@@ -672,7 +673,8 @@ static void irda_usb_net_timeout(struct net_device *netdev)
 	if (urb->status != 0) {
 		struct sk_buff *skb = urb->context;
 
-		IRDA_DEBUG(0, "%s: Tx timed out, urb->status=%d, urb->transfer_flags=0x%04X\n", netdev->name, urb->status, urb->transfer_flags);
+		pr_debug("%s: Tx timed out, urb->status=%d, urb->transfer_flags=0x%04X\n",
+			 netdev->name, urb->status, urb->transfer_flags);
 
 		/* Increase error count */
 		netdev->stats.tx_errors++;
@@ -761,8 +763,6 @@ static void irda_usb_submit(struct irda_usb_cb *self, struct sk_buff *skb, struc
 	struct irda_skb_cb *cb;
 	int ret;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* This should never happen */
 	IRDA_ASSERT(skb != NULL, return;);
 	IRDA_ASSERT(urb != NULL, return;);
@@ -805,7 +805,7 @@ static void irda_usb_receive(struct urb *urb)
 	struct urb *next_urb;
 	unsigned int len, docopy;
 
-	IRDA_DEBUG(2, "%s(), len=%d\n", __func__, urb->actual_length);
+	pr_debug("%s(), len=%d\n", __func__, urb->actual_length);
 	
 	/* Find ourselves */
 	cb = (struct irda_skb_cb *) skb->cb;
@@ -815,7 +815,7 @@ static void irda_usb_receive(struct urb *urb)
 
 	/* If the network is closed or the device gone, stop everything */
 	if ((!self->netopen) || (!self->present)) {
-		IRDA_DEBUG(0, "%s(), Network is gone!\n", __func__);
+		pr_debug("%s(), Network is gone!\n", __func__);
 		/* Don't re-submit the URB : will stall the Rx path */
 		return;
 	}
@@ -838,7 +838,8 @@ static void irda_usb_receive(struct urb *urb)
 			/* Usually precursor to a hot-unplug on OHCI. */
 		default:
 			self->netdev->stats.rx_errors++;
-			IRDA_DEBUG(0, "%s(), RX status %d, transfer_flags 0x%04X\n", __func__, urb->status, urb->transfer_flags);
+			pr_debug("%s(), RX status %d, transfer_flags 0x%04X\n",
+				 __func__, urb->status, urb->transfer_flags);
 			break;
 		}
 		/* If we received an error, we don't want to resubmit the
@@ -964,8 +965,6 @@ static void irda_usb_rx_defer_expired(unsigned long data)
 	struct irda_skb_cb *cb;
 	struct urb *next_urb;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Find ourselves */
 	cb = (struct irda_skb_cb *) skb->cb;
 	IRDA_ASSERT(cb != NULL, return;);
@@ -1049,8 +1048,8 @@ static int stir421x_fw_upload(struct irda_usb_cb *self,
 						   self->bulk_out_ep),
 				   patch_block, block_size,
 				   &actual_len, msecs_to_jiffies(500));
-		IRDA_DEBUG(3,"%s(): Bulk send %u bytes, ret=%d\n",
-			   __func__, actual_len, ret);
+		pr_debug("%s(): Bulk send %u bytes, ret=%d\n",
+			 __func__, actual_len, ret);
 
 		if (ret < 0)
 			break;
@@ -1112,8 +1111,8 @@ static int stir421x_patch_device(struct irda_usb_cb *self)
 				+ ((build / 10) << 4)
 				+ (build % 10);
 
-			IRDA_DEBUG(3, "%s(): Firmware Product version %ld\n",
-                                   __func__, fw_version);
+			pr_debug("%s(): Firmware Product version %ld\n",
+				 __func__, fw_version);
                 }
         }
 
@@ -1169,8 +1168,6 @@ static int irda_usb_net_open(struct net_device *netdev)
 	char	hwname[16];
 	int i;
 	
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	IRDA_ASSERT(netdev != NULL, return -1;);
 	self = netdev_priv(netdev);
 	IRDA_ASSERT(self != NULL, return -1;);
@@ -1249,8 +1246,6 @@ static int irda_usb_net_close(struct net_device *netdev)
 	struct irda_usb_cb *self;
 	int	i;
 
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	IRDA_ASSERT(netdev != NULL, return -1;);
 	self = netdev_priv(netdev);
 	IRDA_ASSERT(self != NULL, return -1;);
@@ -1304,7 +1299,7 @@ static int irda_usb_net_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	self = netdev_priv(dev);
 	IRDA_ASSERT(self != NULL, return -1;);
 
-	IRDA_DEBUG(2, "%s(), %s, (cmd=0x%X)\n", __func__, dev->name, cmd);
+	pr_debug("%s(), %s, (cmd=0x%X)\n", __func__, dev->name, cmd);
 
 	switch (cmd) {
 	case SIOCSBANDWIDTH: /* Set bandwidth */
@@ -1354,7 +1349,6 @@ static inline void irda_usb_init_qos(struct irda_usb_cb *self)
 {
 	struct irda_class_desc *desc;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
 	
 	desc = self->irda_desc;
 	
@@ -1370,8 +1364,10 @@ static inline void irda_usb_init_qos(struct irda_usb_cb *self)
 	self->qos.window_size.bits     = desc->bmWindowSize;
 	self->qos.data_size.bits       = desc->bmDataSize;
 
-	IRDA_DEBUG(0, "%s(), dongle says speed=0x%X, size=0x%X, window=0x%X, bofs=0x%X, turn=0x%X\n", 
-		__func__, self->qos.baud_rate.bits, self->qos.data_size.bits, self->qos.window_size.bits, self->qos.additional_bofs.bits, self->qos.min_turn_time.bits);
+	pr_debug("%s(), dongle says speed=0x%X, size=0x%X, window=0x%X, bofs=0x%X, turn=0x%X\n",
+		 __func__, self->qos.baud_rate.bits, self->qos.data_size.bits,
+		 self->qos.window_size.bits, self->qos.additional_bofs.bits,
+		 self->qos.min_turn_time.bits);
 
 	/* Don't always trust what the dongle tell us */
 	if(self->capability & IUC_SIR_ONLY)
@@ -1414,8 +1410,6 @@ static inline int irda_usb_open(struct irda_usb_cb *self)
 {
 	struct net_device *netdev = self->netdev;
 
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	netdev->netdev_ops = &irda_usb_netdev_ops;
 
 	irda_usb_init_qos(self);
@@ -1430,8 +1424,6 @@ static inline int irda_usb_open(struct irda_usb_cb *self)
  */
 static inline void irda_usb_close(struct irda_usb_cb *self)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	/* Remove netdevice */
 	unregister_netdev(self->netdev);
 
@@ -1509,8 +1501,9 @@ static inline int irda_usb_parse_endpoints(struct irda_usb_cb *self, struct usb_
 		}
 	}
 
-	IRDA_DEBUG(0, "%s(), And our endpoints are : in=%02X, out=%02X (%d), int=%02X\n",
-		__func__, self->bulk_in_ep, self->bulk_out_ep, self->bulk_out_mtu, self->bulk_int_ep);
+	pr_debug("%s(), And our endpoints are : in=%02X, out=%02X (%d), int=%02X\n",
+		 __func__, self->bulk_in_ep, self->bulk_out_ep,
+		 self->bulk_out_mtu, self->bulk_int_ep);
 
 	return (self->bulk_in_ep != 0) && (self->bulk_out_ep != 0);
 }
@@ -1572,7 +1565,7 @@ static inline struct irda_class_desc *irda_usb_find_class_desc(struct usb_interf
 		0, intf->altsetting->desc.bInterfaceNumber, desc,
 		sizeof(*desc), 500);
 	
-	IRDA_DEBUG(1, "%s(), ret=%d\n", __func__, ret);
+	pr_debug("%s(), ret=%d\n", __func__, ret);
 	if (ret < sizeof(*desc)) {
 		net_warn_ratelimited("usb-irda: class_descriptor read %s (%d)\n",
 				     ret < 0 ? "failed" : "too short", ret);
@@ -1679,7 +1672,8 @@ static int irda_usb_probe(struct usb_interface *intf,
 	 * specify an alternate, but very few driver do like this.
 	 * Jean II */
 	ret = usb_set_interface(dev, intf->altsetting->desc.bInterfaceNumber, 0);
-	IRDA_DEBUG(1, "usb-irda: set interface %d result %d\n", intf->altsetting->desc.bInterfaceNumber, ret);
+	pr_debug("usb-irda: set interface %d result %d\n",
+		 intf->altsetting->desc.bInterfaceNumber, ret);
 	switch (ret) {
 		case 0:
 			break;
@@ -1687,10 +1681,11 @@ static int irda_usb_probe(struct usb_interface *intf,
 			/* Martin Diehl says if we get a -EPIPE we should
 			 * be fine and we don't need to do a usb_clear_halt().
 			 * - Jean II */
-			IRDA_DEBUG(0, "%s(), Received -EPIPE, ignoring...\n", __func__);
+			pr_debug("%s(), Received -EPIPE, ignoring...\n",
+				 __func__);
 			break;
 		default:
-			IRDA_DEBUG(0, "%s(), Unknown error %d\n", __func__, ret);
+			pr_debug("%s(), Unknown error %d\n", __func__, ret);
 			ret = -EIO;
 			goto err_out_3;
 	}
@@ -1716,7 +1711,7 @@ static int irda_usb_probe(struct usb_interface *intf,
 		ret = usb_control_msg (self->usbdev, usb_sndctrlpipe (self->usbdev, 0),
 				       0x02, 0x40, 0, 0, NULL, 0, 500);
 		if (ret < 0) {
-			IRDA_DEBUG (0, "usb_control_msg failed %d\n", ret);
+			pr_debug("usb_control_msg failed %d\n", ret);
 			goto err_out_3;
 		} else {
 			mdelay(10);
@@ -1808,8 +1803,6 @@ static void irda_usb_disconnect(struct usb_interface *intf)
 	struct irda_usb_cb *self = usb_get_intfdata(intf);
 	int i;
 
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	usb_set_intfdata(intf, NULL);
 	if (!self)
 		return;
@@ -1858,7 +1851,7 @@ static void irda_usb_disconnect(struct usb_interface *intf)
 
 	/* Free self and network device */
 	free_netdev(self->netdev);
-	IRDA_DEBUG(0, "%s(), USB IrDA Disconnected\n", __func__);
+	pr_debug("%s(), USB IrDA Disconnected\n", __func__);
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c
index abbb654c066..696852eb23c 100644
--- a/drivers/net/irda/irtty-sir.c
+++ b/drivers/net/irda/irtty-sir.c
@@ -240,7 +240,7 @@ static void irtty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
 		 *  Characters received with a parity error, etc?
 		 */
  		if (fp && *fp++) { 
-			IRDA_DEBUG(0, "Framing or parity error!\n");
+			pr_debug("Framing or parity error!\n");
 			sirdev_receive(dev, NULL, 0);	/* notify sir_dev (updating stats) */
 			return;
  		}
@@ -387,7 +387,7 @@ static int irtty_ioctl(struct tty_struct *tty, struct file *file, unsigned int c
 	IRDA_ASSERT(priv != NULL, return -ENODEV;);
 	IRDA_ASSERT(priv->magic == IRTTY_MAGIC, return -EBADR;);
 
-	IRDA_DEBUG(3, "%s(cmd=0x%X)\n", __func__, cmd);
+	pr_debug("%s(cmd=0x%X)\n", __func__, cmd);
 
 	dev = priv->dev;
 	IRDA_ASSERT(dev != NULL, return -1;);
@@ -477,7 +477,7 @@ static int irtty_open(struct tty_struct *tty)
 
 	mutex_unlock(&irtty_mutex);
 
-	IRDA_DEBUG(0, "%s - %s: irda line discipline opened\n", __func__, tty->name);
+	pr_debug("%s - %s: irda line discipline opened\n", __func__, tty->name);
 
 	return 0;
 
@@ -528,7 +528,7 @@ static void irtty_close(struct tty_struct *tty)
 
 	kfree(priv);
 
-	IRDA_DEBUG(0, "%s - %s: irda line discipline closed\n", __func__, tty->name);
+	pr_debug("%s - %s: irda line discipline closed\n", __func__, tty->name);
 }
 
 /* ------------------------------------------------------- */
diff --git a/drivers/net/irda/litelink-sir.c b/drivers/net/irda/litelink-sir.c
index 6827777cbee..8eefcb44bac 100644
--- a/drivers/net/irda/litelink-sir.c
+++ b/drivers/net/irda/litelink-sir.c
@@ -76,8 +76,6 @@ static int litelink_open(struct sir_dev *dev)
 {
 	struct qos_info *qos = &dev->qos;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Power up dongle */
 	sirdev_set_dtr_rts(dev, TRUE, TRUE);
 
@@ -93,8 +91,6 @@ static int litelink_open(struct sir_dev *dev)
 
 static int litelink_close(struct sir_dev *dev)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Power off dongle */
 	sirdev_set_dtr_rts(dev, FALSE, FALSE);
 
@@ -111,8 +107,6 @@ static int litelink_change_speed(struct sir_dev *dev, unsigned speed)
 {
         int i;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* dongle already reset by irda-thread - current speed (dongle and
 	 * port) is the default speed (115200 for litelink!)
 	 */
@@ -154,8 +148,6 @@ static int litelink_change_speed(struct sir_dev *dev, unsigned speed)
  */
 static int litelink_reset(struct sir_dev *dev)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* probably the power-up can be dropped here, but with only
 	 * 15 usec delay it's not worth the risk unless somebody with
 	 * the hardware confirms it doesn't break anything...
diff --git a/drivers/net/irda/ma600-sir.c b/drivers/net/irda/ma600-sir.c
index 944d044510e..a764817b47f 100644
--- a/drivers/net/irda/ma600-sir.c
+++ b/drivers/net/irda/ma600-sir.c
@@ -65,13 +65,11 @@ static struct dongle_driver ma600 = {
 
 static int __init ma600_sir_init(void)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
 	return irda_register_dongle(&ma600);
 }
 
 static void __exit ma600_sir_cleanup(void)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
 	irda_unregister_dongle(&ma600);
 }
 
@@ -86,8 +84,6 @@ static int ma600_open(struct sir_dev *dev)
 {
 	struct qos_info *qos = &dev->qos;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	sirdev_set_dtr_rts(dev, TRUE, TRUE);
 
 	/* Explicitly set the speeds we can accept */
@@ -104,8 +100,6 @@ static int ma600_open(struct sir_dev *dev)
 
 static int ma600_close(struct sir_dev *dev)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Power off dongle */
 	sirdev_set_dtr_rts(dev, FALSE, FALSE);
 
@@ -174,8 +168,8 @@ static int ma600_change_speed(struct sir_dev *dev, unsigned speed)
 {
 	u8	byte;
 	
-	IRDA_DEBUG(2, "%s(), speed=%d (was %d)\n", __func__,
-		speed, dev->speed);
+	pr_debug("%s(), speed=%d (was %d)\n", __func__,
+		 speed, dev->speed);
 
 	/* dongle already reset, dongle and port at default speed (9600) */
 
@@ -204,7 +198,7 @@ static int ma600_change_speed(struct sir_dev *dev, unsigned speed)
 		return -1;
 	}
 	else
-		IRDA_DEBUG(2, "%s() control byte write read OK\n", __func__);
+		pr_debug("%s() control byte write read OK\n", __func__);
 #endif
 
 	/* Set DTR, Set RTS */
@@ -236,8 +230,6 @@ static int ma600_change_speed(struct sir_dev *dev, unsigned speed)
 
 static int ma600_reset(struct sir_dev *dev)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Reset the dongle : set DTR low for 10 ms */
 	sirdev_set_dtr_rts(dev, FALSE, TRUE);
 	msleep(10);
diff --git a/drivers/net/irda/mcp2120-sir.c b/drivers/net/irda/mcp2120-sir.c
index 97674695211..2e33f91bfe8 100644
--- a/drivers/net/irda/mcp2120-sir.c
+++ b/drivers/net/irda/mcp2120-sir.c
@@ -63,8 +63,6 @@ static int mcp2120_open(struct sir_dev *dev)
 {
 	struct qos_info *qos = &dev->qos;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* seems no explicit power-on required here and reset switching it on anyway */
 
 	qos->baud_rate.bits &= IR_9600|IR_19200|IR_38400|IR_57600|IR_115200;
@@ -76,8 +74,6 @@ static int mcp2120_open(struct sir_dev *dev)
 
 static int mcp2120_close(struct sir_dev *dev)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Power off dongle */
         /* reset and inhibit mcp2120 */
 	sirdev_set_dtr_rts(dev, TRUE, TRUE);
@@ -102,8 +98,6 @@ static int mcp2120_change_speed(struct sir_dev *dev, unsigned speed)
 	u8 control[2];
 	static int ret = 0;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	switch (state) {
 	case SIRDEV_STATE_DONGLE_SPEED:
 		/* Set DTR to enter command mode */
@@ -188,8 +182,6 @@ static int mcp2120_reset(struct sir_dev *dev)
 	unsigned delay = 0;
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	switch (state) {
 	case SIRDEV_STATE_DONGLE_RESET:
                 //printk("mcp2120_reset: dongle_reset\n");
diff --git a/drivers/net/irda/mcs7780.c b/drivers/net/irda/mcs7780.c
index 6cbd29dcf2d..e4d678fbeb2 100644
--- a/drivers/net/irda/mcs7780.c
+++ b/drivers/net/irda/mcs7780.c
@@ -894,7 +894,7 @@ static int mcs_probe(struct usb_interface *intf,
 	if (!ndev)
 		goto error1;
 
-	IRDA_DEBUG(1, "MCS7780 USB-IrDA bridge found at %d.\n", udev->devnum);
+	pr_debug("MCS7780 USB-IrDA bridge found at %d.\n", udev->devnum);
 
 	SET_NETDEV_DEV(ndev, &intf->dev);
 
@@ -942,8 +942,8 @@ static int mcs_probe(struct usb_interface *intf,
 	if (ret != 0)
 		goto error2;
 
-	IRDA_DEBUG(1, "IrDA: Registered MosChip MCS7780 device as %s\n",
-		   ndev->name);
+	pr_debug("IrDA: Registered MosChip MCS7780 device as %s\n",
+		 ndev->name);
 
 	mcs->transceiver_type = transceiver_type;
 	mcs->sir_tweak = sir_tweak;
@@ -973,7 +973,7 @@ static void mcs_disconnect(struct usb_interface *intf)
 	free_netdev(mcs->netdev);
 
 	usb_set_intfdata(intf, NULL);
-	IRDA_DEBUG(0, "MCS7780 now disconnected.\n");
+	pr_debug("MCS7780 now disconnected.\n");
 }
 
 module_usb_driver(mcs_driver);
diff --git a/drivers/net/irda/nsc-ircc.c b/drivers/net/irda/nsc-ircc.c
index c0a179098ea..e7317b104bf 100644
--- a/drivers/net/irda/nsc-ircc.c
+++ b/drivers/net/irda/nsc-ircc.c
@@ -226,8 +226,8 @@ static int __init nsc_ircc_init(void)
 
 	/* Probe for all the NSC chipsets we know about */
 	for (chip = chips; chip->name ; chip++) {
-		IRDA_DEBUG(2, "%s(), Probing for %s ...\n", __func__,
-			   chip->name);
+		pr_debug("%s(), Probing for %s ...\n", __func__,
+			 chip->name);
 		
 		/* Try all config registers for this chip */
 		for (cfg = 0; cfg < ARRAY_SIZE(chip->cfg); cfg++) {
@@ -238,7 +238,8 @@ static int __init nsc_ircc_init(void)
 			/* Read index register */
 			reg = inb(cfg_base);
 			if (reg == 0xff) {
-				IRDA_DEBUG(2, "%s() no chip at 0x%03x\n", __func__, cfg_base);
+				pr_debug("%s() no chip at 0x%03x\n",
+					 __func__, cfg_base);
 				continue;
 			}
 			
@@ -246,8 +247,9 @@ static int __init nsc_ircc_init(void)
 			outb(chip->cid_index, cfg_base);
 			id = inb(cfg_base+1);
 			if ((id & chip->cid_mask) == chip->cid_value) {
-				IRDA_DEBUG(2, "%s() Found %s chip, revision=%d\n",
-					   __func__, chip->name, id & ~chip->cid_mask);
+				pr_debug("%s() Found %s chip, revision=%d\n",
+					 __func__, chip->name,
+					 id & ~chip->cid_mask);
 
 				/*
 				 * If we found a correct PnP setting,
@@ -277,7 +279,8 @@ static int __init nsc_ircc_init(void)
 				 * the chip.
 				 */
 				if (ret) {
-					IRDA_DEBUG(2, "%s, PnP init failed\n", driver_name);
+					pr_debug("%s, PnP init failed\n",
+						 driver_name);
 					memset(&info, 0, sizeof(chipio_t));
 					info.cfg_base = cfg_base;
 					info.fir_base = io[i];
@@ -299,7 +302,8 @@ static int __init nsc_ircc_init(void)
 				}
 				i++;
 			} else {
-				IRDA_DEBUG(2, "%s(), Wrong chip id=0x%02x\n", __func__, id);
+				pr_debug("%s(), Wrong chip id=0x%02x\n",
+					 __func__, id);
 			}
 		} 
 	}
@@ -363,9 +367,6 @@ static int __init nsc_ircc_open(chipio_t *info)
 	void *ret;
 	int err, chip_index;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
-
  	for (chip_index = 0; chip_index < ARRAY_SIZE(dev_self); chip_index++) {
 		if (!dev_self[chip_index])
 			break;
@@ -520,8 +521,6 @@ static int __exit nsc_ircc_close(struct nsc_ircc_cb *self)
 {
 	int iobase;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
         iobase = self->io.fir_base;
@@ -532,8 +531,8 @@ static int __exit nsc_ircc_close(struct nsc_ircc_cb *self)
 	unregister_netdev(self->netdev);
 
 	/* Release the PORT that this driver is using */
-	IRDA_DEBUG(4, "%s(), Releasing Region %03x\n", 
-		   __func__, self->io.fir_base);
+	pr_debug("%s(), Releasing Region %03x\n",
+		 __func__, self->io.fir_base);
 	release_region(self->io.fir_base, self->io.fir_ext);
 
 	if (self->tx_buff.head)
@@ -630,8 +629,8 @@ static int nsc_ircc_probe_108(nsc_chip_t *chip, chipio_t *info)
 		break;
 	}
 	info->sir_base = info->fir_base;
-	IRDA_DEBUG(2, "%s(), probing fir_base=0x%03x\n", __func__,
-		   info->fir_base);
+	pr_debug("%s(), probing fir_base=0x%03x\n", __func__,
+		 info->fir_base);
 
 	/* Read control signals routing register (CSRT) */
 	outb(CFG_108_CSRT, cfg_base);
@@ -663,7 +662,7 @@ static int nsc_ircc_probe_108(nsc_chip_t *chip, chipio_t *info)
 		info->irq = 15;
 		break;
 	}
-	IRDA_DEBUG(2, "%s(), probing irq=%d\n", __func__, info->irq);
+	pr_debug("%s(), probing irq=%d\n", __func__, info->irq);
 
 	/* Currently we only read Rx DMA but it will also be used for Tx */
 	switch ((reg >> 3) & 0x03) {
@@ -680,7 +679,7 @@ static int nsc_ircc_probe_108(nsc_chip_t *chip, chipio_t *info)
 		info->dma = 3;
 		break;
 	}
-	IRDA_DEBUG(2, "%s(), probing dma=%d\n", __func__, info->dma);
+	pr_debug("%s(), probing dma=%d\n", __func__, info->dma);
 
 	/* Read mode control register (MCTL) */
 	outb(CFG_108_MCTL, cfg_base);
@@ -731,7 +730,7 @@ static int nsc_ircc_probe_338(nsc_chip_t *chip, chipio_t *info)
 	
 	pnp = (reg >> 3) & 0x01;
 	if (pnp) {
-		IRDA_DEBUG(2, "(), Chip is in PnP mode\n");
+		pr_debug("(), Chip is in PnP mode\n");
 		outb(0x46, cfg_base);
 		reg = (inb(cfg_base+1) & 0xfe) << 2;
 
@@ -835,9 +834,8 @@ static int nsc_ircc_init_39x(nsc_chip_t *chip, chipio_t *info)
 	int enabled;
 
 	/* User is sure about his config... accept it. */
-	IRDA_DEBUG(2, "%s(): nsc_ircc_init_39x (user settings): "
-		   "io=0x%04x, irq=%d, dma=%d\n", 
-		   __func__, info->fir_base, info->irq, info->dma);
+	pr_debug("%s(): nsc_ircc_init_39x (user settings): io=0x%04x, irq=%d, dma=%d\n",
+		 __func__, info->fir_base, info->irq, info->dma);
 
 	/* Access bank for SP2 */
 	outb(CFG_39X_LDN, cfg_base);
@@ -877,8 +875,8 @@ static int nsc_ircc_probe_39x(nsc_chip_t *chip, chipio_t *info)
 	int reg1, reg2, irq, irqt, dma1, dma2;
 	int enabled, susp;
 
-	IRDA_DEBUG(2, "%s(), nsc_ircc_probe_39x, base=%d\n",
-		   __func__, cfg_base);
+	pr_debug("%s(), nsc_ircc_probe_39x, base=%d\n",
+		 __func__, cfg_base);
 
 	/* This function should be executed with irq off to avoid
 	 * another driver messing with the Super I/O bank - Jean II */
@@ -912,7 +910,8 @@ static int nsc_ircc_probe_39x(nsc_chip_t *chip, chipio_t *info)
 	outb(CFG_39X_SPC, cfg_base);
 	susp = 1 - ((inb(cfg_base+1) & 0x02) >> 1);
 
-	IRDA_DEBUG(2, "%s(): io=0x%02x%02x, irq=%d (type %d), rxdma=%d, txdma=%d, enabled=%d (suspended=%d)\n", __func__, reg1,reg2,irq,irqt,dma1,dma2,enabled,susp);
+	pr_debug("%s(): io=0x%02x%02x, irq=%d (type %d), rxdma=%d, txdma=%d, enabled=%d (suspended=%d)\n",
+		 __func__, reg1, reg2, irq, irqt, dma1, dma2, enabled, susp);
 
 	/* Configure SP2 */
 
@@ -963,8 +962,8 @@ static int nsc_ircc_pnp_probe(struct pnp_dev *dev, const struct pnp_device_id *i
 		!(pnp_dma_flags(dev, 0) & IORESOURCE_DISABLED))
 		pnp_info.dma = pnp_dma(dev, 0);
 
-	IRDA_DEBUG(0, "%s() : From PnP, found firbase 0x%03X ; irq %d ; dma %d.\n",
-		   __func__, pnp_info.fir_base, pnp_info.irq, pnp_info.dma);
+	pr_debug("%s() : From PnP, found firbase 0x%03X ; irq %d ; dma %d.\n",
+		 __func__, pnp_info.fir_base, pnp_info.irq, pnp_info.dma);
 
 	if((pnp_info.fir_base == 0) ||
 	   (pnp_info.irq == -1) || (pnp_info.dma == -1)) {
@@ -992,8 +991,8 @@ static int nsc_ircc_setup(chipio_t *info)
 	switch_bank(iobase, BANK3);
 	version = inb(iobase+MID);
 
-	IRDA_DEBUG(2, "%s() Driver %s Found chip version %02x\n",
-		   __func__, driver_name, version);
+	pr_debug("%s() Driver %s Found chip version %02x\n",
+		 __func__, driver_name, version);
 
 	/* Should be 0x2? */
 	if (0x20 != (version & 0xf0)) {
@@ -1096,39 +1095,39 @@ static void nsc_ircc_init_dongle_interface (int iobase, int dongle_id)
 	switch (dongle_id) {
 	case 0x00: /* same as */
 	case 0x01: /* Differential serial interface */
-		IRDA_DEBUG(0, "%s(), %s not defined by irda yet\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s not defined by irda yet\n",
+			 __func__, dongle_types[dongle_id]);
 		break;
 	case 0x02: /* same as */
 	case 0x03: /* Reserved */
-		IRDA_DEBUG(0, "%s(), %s not defined by irda yet\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s not defined by irda yet\n",
+			 __func__, dongle_types[dongle_id]);
 		break;
 	case 0x04: /* Sharp RY5HD01 */
 		break;
 	case 0x05: /* Reserved, but this is what the Thinkpad reports */
-		IRDA_DEBUG(0, "%s(), %s not defined by irda yet\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s not defined by irda yet\n",
+			 __func__, dongle_types[dongle_id]);
 		break;
 	case 0x06: /* Single-ended serial interface */
-		IRDA_DEBUG(0, "%s(), %s not defined by irda yet\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s not defined by irda yet\n",
+			 __func__, dongle_types[dongle_id]);
 		break;
 	case 0x07: /* Consumer-IR only */
-		IRDA_DEBUG(0, "%s(), %s is not for IrDA mode\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s is not for IrDA mode\n",
+			 __func__, dongle_types[dongle_id]);
 		break;
 	case 0x08: /* HP HSDL-2300, HP HSDL-3600/HSDL-3610 */
-		IRDA_DEBUG(0, "%s(), %s\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s\n",
+			 __func__, dongle_types[dongle_id]);
 		break;
 	case 0x09: /* IBM31T1100 or Temic TFDS6000/TFDS6500 */
 		outb(0x28, iobase+7); /* Set irsl[0-2] as output */
 		break;
 	case 0x0A: /* same as */
 	case 0x0B: /* Reserved */
-		IRDA_DEBUG(0, "%s(), %s not defined by irda yet\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s not defined by irda yet\n",
+			 __func__, dongle_types[dongle_id]);
 		break;
 	case 0x0C: /* same as */
 	case 0x0D: /* HP HSDL-1100/HSDL-2100 */
@@ -1142,15 +1141,15 @@ static void nsc_ircc_init_dongle_interface (int iobase, int dongle_id)
 		outb(0x28, iobase+7); /* Set irsl[0-2] as output */
 		break;
 	case 0x0F: /* No dongle connected */
-		IRDA_DEBUG(0, "%s(), %s\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s\n",
+			 __func__, dongle_types[dongle_id]);
 
 		switch_bank(iobase, BANK0);
 		outb(0x62, iobase+MCR);
 		break;
 	default: 
-		IRDA_DEBUG(0, "%s(), invalid dongle_id %#x", 
-			   __func__, dongle_id);
+		pr_debug("%s(), invalid dongle_id %#x",
+			 __func__, dongle_id);
 	}
 	
 	/* IRCFG1: IRSL1 and 2 are set to IrDA mode */
@@ -1181,31 +1180,31 @@ static void nsc_ircc_change_dongle_speed(int iobase, int speed, int dongle_id)
 	switch (dongle_id) {
 	case 0x00: /* same as */
 	case 0x01: /* Differential serial interface */
-		IRDA_DEBUG(0, "%s(), %s not defined by irda yet\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s not defined by irda yet\n",
+			 __func__, dongle_types[dongle_id]);
 		break;
 	case 0x02: /* same as */
 	case 0x03: /* Reserved */
-		IRDA_DEBUG(0, "%s(), %s not defined by irda yet\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s not defined by irda yet\n",
+			 __func__, dongle_types[dongle_id]);
 		break;
 	case 0x04: /* Sharp RY5HD01 */
 		break;
 	case 0x05: /* Reserved */
-		IRDA_DEBUG(0, "%s(), %s not defined by irda yet\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s not defined by irda yet\n",
+			 __func__, dongle_types[dongle_id]);
 		break;
 	case 0x06: /* Single-ended serial interface */
-		IRDA_DEBUG(0, "%s(), %s not defined by irda yet\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s not defined by irda yet\n",
+			 __func__, dongle_types[dongle_id]);
 		break;
 	case 0x07: /* Consumer-IR only */
-		IRDA_DEBUG(0, "%s(), %s is not for IrDA mode\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s is not for IrDA mode\n",
+			 __func__, dongle_types[dongle_id]);
 		break;
 	case 0x08: /* HP HSDL-2300, HP HSDL-3600/HSDL-3610 */
-		IRDA_DEBUG(0, "%s(), %s\n", 
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s\n",
+			 __func__, dongle_types[dongle_id]);
 		outb(0x00, iobase+4);
 		if (speed > 115200)
 			outb(0x01, iobase+4);
@@ -1223,8 +1222,8 @@ static void nsc_ircc_change_dongle_speed(int iobase, int speed, int dongle_id)
 		break;
 	case 0x0A: /* same as */
 	case 0x0B: /* Reserved */
-		IRDA_DEBUG(0, "%s(), %s not defined by irda yet\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s not defined by irda yet\n",
+			 __func__, dongle_types[dongle_id]);
 		break;
 	case 0x0C: /* same as */
 	case 0x0D: /* HP HSDL-1100/HSDL-2100 */
@@ -1232,14 +1231,14 @@ static void nsc_ircc_change_dongle_speed(int iobase, int speed, int dongle_id)
 	case 0x0E: /* Supports SIR Mode only */
 		break;
 	case 0x0F: /* No dongle connected */
-		IRDA_DEBUG(0, "%s(), %s is not for IrDA mode\n",
-			   __func__, dongle_types[dongle_id]);
+		pr_debug("%s(), %s is not for IrDA mode\n",
+			 __func__, dongle_types[dongle_id]);
 
 		switch_bank(iobase, BANK0); 
 		outb(0x62, iobase+MCR);
 		break;
 	default: 
-		IRDA_DEBUG(0, "%s(), invalid data_rate\n", __func__);
+		pr_debug("%s(), invalid data_rate\n", __func__);
 	}
 	/* Restore bank register */
 	outb(bank, iobase+BSR);
@@ -1260,7 +1259,7 @@ static __u8 nsc_ircc_change_speed(struct nsc_ircc_cb *self, __u32 speed)
 	__u8 bank;
 	__u8 ier;                  /* Interrupt enable register */
 
-	IRDA_DEBUG(2, "%s(), speed=%d\n", __func__, speed);
+	pr_debug("%s(), speed=%d\n", __func__, speed);
 
 	IRDA_ASSERT(self != NULL, return 0;);
 
@@ -1293,20 +1292,20 @@ static __u8 nsc_ircc_change_speed(struct nsc_ircc_cb *self, __u32 speed)
 		outb(inb(iobase+4) | 0x04, iobase+4);
 	       
 		mcr = MCR_MIR;
-		IRDA_DEBUG(0, "%s(), handling baud of 576000\n", __func__);
+		pr_debug("%s(), handling baud of 576000\n", __func__);
 		break;
 	case 1152000:
 		mcr = MCR_MIR;
-		IRDA_DEBUG(0, "%s(), handling baud of 1152000\n", __func__);
+		pr_debug("%s(), handling baud of 1152000\n", __func__);
 		break;
 	case 4000000:
 		mcr = MCR_FIR;
-		IRDA_DEBUG(0, "%s(), handling baud of 4000000\n", __func__);
+		pr_debug("%s(), handling baud of 4000000\n", __func__);
 		break;
 	default:
 		mcr = MCR_FIR;
-		IRDA_DEBUG(0, "%s(), unknown baud rate of %d\n", 
-			   __func__, speed);
+		pr_debug("%s(), unknown baud rate of %d\n",
+			 __func__, speed);
 		break;
 	}
 
@@ -1613,15 +1612,13 @@ static int nsc_ircc_pio_write(int iobase, __u8 *buf, int len, int fifo_size)
 	int actual = 0;
 	__u8 bank;
 	
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	/* Save current bank */
 	bank = inb(iobase+BSR);
 
 	switch_bank(iobase, BANK0);
 	if (!(inb_p(iobase+LSR) & LSR_TXEMP)) {
-		IRDA_DEBUG(4, "%s(), warning, FIFO not empty yet!\n",
-			   __func__);
+		pr_debug("%s(), warning, FIFO not empty yet!\n",
+			 __func__);
 
 		/* FIFO may still be filled to the Tx interrupt threshold */
 		fifo_size -= 17;
@@ -1633,8 +1630,8 @@ static int nsc_ircc_pio_write(int iobase, __u8 *buf, int len, int fifo_size)
 		outb(buf[actual++], iobase+TXD);
 	}
         
-	IRDA_DEBUG(4, "%s(), fifo_size %d ; %d sent of %d\n", 
-		   __func__, fifo_size, actual, len);
+	pr_debug("%s(), fifo_size %d ; %d sent of %d\n",
+		 __func__, fifo_size, actual, len);
 	
 	/* Restore bank */
 	outb(bank, iobase+BSR);
@@ -1655,8 +1652,6 @@ static int nsc_ircc_dma_xmit_complete(struct nsc_ircc_cb *self)
 	__u8 bank;
 	int ret = TRUE;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	iobase = self->io.fir_base;
 
 	/* Save current bank */
@@ -1786,7 +1781,7 @@ static int nsc_ircc_dma_receive_complete(struct nsc_ircc_cb *self, int iobase)
 		len = inb(iobase+RFLFL) | ((inb(iobase+RFLFH) & 0x1f) << 8);
 
 		if (st_fifo->tail >= MAX_RX_WINDOW) {
-			IRDA_DEBUG(0, "%s(), window is full!\n", __func__);
+			pr_debug("%s(), window is full!\n", __func__);
 			continue;
 		}
 			
@@ -1980,7 +1975,7 @@ static void nsc_ircc_sir_interrupt(struct nsc_ircc_cb *self, int eir)
 		 * Need to be after self->io.direction to avoid race with
 		 * nsc_ircc_hard_xmit_sir() - Jean II */
 		if (self->new_speed) {
-			IRDA_DEBUG(2, "%s(), Changing speed!\n", __func__);
+			pr_debug("%s(), Changing speed!\n", __func__);
 			self->ier = nsc_ircc_change_speed(self,
 							  self->new_speed);
 			self->new_speed = 0;
@@ -2174,7 +2169,6 @@ static int nsc_ircc_net_open(struct net_device *dev)
 	char hwname[32];
 	__u8 bank;
 	
-	IRDA_DEBUG(4, "%s()\n", __func__);
 	
 	IRDA_ASSERT(dev != NULL, return -1;);
 	self = netdev_priv(dev);
@@ -2236,7 +2230,6 @@ static int nsc_ircc_net_close(struct net_device *dev)
 	int iobase;
 	__u8 bank;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
 	
 	IRDA_ASSERT(dev != NULL, return -1;);
 
@@ -2290,7 +2283,7 @@ static int nsc_ircc_net_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 
 	IRDA_ASSERT(self != NULL, return -1;);
 
-	IRDA_DEBUG(2, "%s(), %s, (cmd=0x%X)\n", __func__, dev->name, cmd);
+	pr_debug("%s(), %s, (cmd=0x%X)\n", __func__, dev->name, cmd);
 	
 	switch (cmd) {
 	case SIOCSBANDWIDTH: /* Set bandwidth */
@@ -2329,7 +2322,7 @@ static int nsc_ircc_suspend(struct platform_device *dev, pm_message_t state)
 	if (self->io.suspended)
 		return 0;
 
-	IRDA_DEBUG(1, "%s, Suspending\n", driver_name);
+	pr_debug("%s, Suspending\n", driver_name);
 
 	rtnl_lock();
 	if (netif_running(self->netdev)) {
@@ -2363,7 +2356,7 @@ static int nsc_ircc_resume(struct platform_device *dev)
 	if (!self->io.suspended)
 		return 0;
 
-	IRDA_DEBUG(1, "%s, Waking up\n", driver_name);
+	pr_debug("%s, Waking up\n", driver_name);
 
 	rtnl_lock();
 	nsc_ircc_setup(&self->io);
diff --git a/drivers/net/irda/old_belkin-sir.c b/drivers/net/irda/old_belkin-sir.c
index f237136f382..a7c2e990ae6 100644
--- a/drivers/net/irda/old_belkin-sir.c
+++ b/drivers/net/irda/old_belkin-sir.c
@@ -90,8 +90,6 @@ static int old_belkin_open(struct sir_dev *dev)
 {
 	struct qos_info *qos = &dev->qos;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Power on dongle */
 	sirdev_set_dtr_rts(dev, TRUE, TRUE);
 
@@ -108,8 +106,6 @@ static int old_belkin_open(struct sir_dev *dev)
 
 static int old_belkin_close(struct sir_dev *dev)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Power off dongle */
 	sirdev_set_dtr_rts(dev, FALSE, FALSE);
 
@@ -123,8 +119,6 @@ static int old_belkin_close(struct sir_dev *dev)
  */
 static int old_belkin_change_speed(struct sir_dev *dev, unsigned speed)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	dev->speed = 9600;
 	return (speed==dev->speed) ? 0 : -EINVAL;
 }
@@ -137,8 +131,6 @@ static int old_belkin_change_speed(struct sir_dev *dev, unsigned speed)
  */
 static int old_belkin_reset(struct sir_dev *dev)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* This dongles speed "defaults" to 9600 bps ;-) */
 	dev->speed = 9600;
 
diff --git a/drivers/net/irda/sir_dev.c b/drivers/net/irda/sir_dev.c
index 5bfcd25923b..6af26a7d787 100644
--- a/drivers/net/irda/sir_dev.c
+++ b/drivers/net/irda/sir_dev.c
@@ -109,11 +109,11 @@ static void sirdev_config_fsm(struct work_struct *work)
 	int ret = -1;
 	unsigned delay;
 
-	IRDA_DEBUG(2, "%s(), <%ld>\n", __func__, jiffies);
+	pr_debug("%s(), <%ld>\n", __func__, jiffies);
 
 	do {
-		IRDA_DEBUG(3, "%s - state=0x%04x / substate=0x%04x\n",
-			__func__, fsm->state, fsm->substate);
+		pr_debug("%s - state=0x%04x / substate=0x%04x\n",
+			 __func__, fsm->state, fsm->substate);
 
 		next_state = fsm->state;
 		delay = 0;
@@ -287,12 +287,12 @@ int sirdev_schedule_request(struct sir_dev *dev, int initial_state, unsigned par
 {
 	struct sir_fsm *fsm = &dev->fsm;
 
-	IRDA_DEBUG(2, "%s - state=0x%04x / param=%u\n", __func__,
-			initial_state, param);
+	pr_debug("%s - state=0x%04x / param=%u\n", __func__,
+		 initial_state, param);
 
 	if (down_trylock(&fsm->sem)) {
 		if (in_interrupt()  ||  in_atomic()  ||  irqs_disabled()) {
-			IRDA_DEBUG(1, "%s(), state machine busy!\n", __func__);
+			pr_debug("%s(), state machine busy!\n", __func__);
 			return -EWOULDBLOCK;
 		} else
 			down(&fsm->sem);
@@ -345,7 +345,7 @@ int sirdev_set_dongle(struct sir_dev *dev, IRDA_DONGLE type)
 {
 	int err;
 
-	IRDA_DEBUG(3, "%s : requesting dongle %d.\n", __func__, type);
+	pr_debug("%s : requesting dongle %d.\n", __func__, type);
 
 	err = sirdev_schedule_dongle_open(dev, type);
 	if (unlikely(err))
@@ -380,7 +380,7 @@ int sirdev_raw_write(struct sir_dev *dev, const char *buf, int len)
 
 	ret = dev->drv->do_write(dev, dev->tx_buff.data, dev->tx_buff.len);
 	if (ret > 0) {
-		IRDA_DEBUG(3, "%s(), raw-tx started\n", __func__);
+		pr_debug("%s(), raw-tx started\n", __func__);
 
 		dev->tx_buff.data += ret;
 		dev->tx_buff.len -= ret;
@@ -440,8 +440,8 @@ void sirdev_write_complete(struct sir_dev *dev)
 	
 	spin_lock_irqsave(&dev->tx_lock, flags);
 
-	IRDA_DEBUG(3, "%s() - dev->tx_buff.len = %d\n",
-		   __func__, dev->tx_buff.len);
+	pr_debug("%s() - dev->tx_buff.len = %d\n",
+		 __func__, dev->tx_buff.len);
 
 	if (likely(dev->tx_buff.len > 0))  {
 		/* Write data left in transmit buffer */
@@ -475,7 +475,7 @@ void sirdev_write_complete(struct sir_dev *dev)
 		 * restarted when the irda-thread has completed the request.
 		 */
 
-		IRDA_DEBUG(3, "%s(), raw-tx done\n", __func__);
+		pr_debug("%s(), raw-tx done\n", __func__);
 		dev->raw_tx = 0;
 		goto done;	/* no post-frame handling in raw mode */
 	}
@@ -492,7 +492,7 @@ void sirdev_write_complete(struct sir_dev *dev)
 	 * re-activated.
 	 */
 
-	IRDA_DEBUG(5, "%s(), finished with frame!\n", __func__);
+	pr_debug("%s(), finished with frame!\n", __func__);
 		
 	if ((skb=dev->tx_skb) != NULL) {
 		dev->tx_skb = NULL;
@@ -502,7 +502,7 @@ void sirdev_write_complete(struct sir_dev *dev)
 	}
 
 	if (unlikely(dev->new_speed > 0)) {
-		IRDA_DEBUG(5, "%s(), Changing speed!\n", __func__);
+		pr_debug("%s(), Changing speed!\n", __func__);
 		err = sirdev_schedule_speed(dev, dev->new_speed);
 		if (unlikely(err)) {
 			/* should never happen
@@ -552,7 +552,7 @@ int sirdev_receive(struct sir_dev *dev, const unsigned char *cp, size_t count)
 		 */
 		irda_device_set_media_busy(dev->netdev, TRUE);
 		dev->netdev->stats.rx_dropped++;
-		IRDA_DEBUG(0, "%s; rx-drop: %zd\n", __func__, count);
+		pr_debug("%s; rx-drop: %zd\n", __func__, count);
 		return 0;
 	}
 
@@ -598,7 +598,7 @@ static netdev_tx_t sirdev_hard_xmit(struct sk_buff *skb,
 
 	netif_stop_queue(ndev);
 
-	IRDA_DEBUG(3, "%s(), skb->len = %d\n", __func__, skb->len);
+	pr_debug("%s(), skb->len = %d\n", __func__, skb->len);
 
 	speed = irda_get_next_speed(skb);
 	if ((speed != dev->speed) && (speed != -1)) {
@@ -635,7 +635,7 @@ static netdev_tx_t sirdev_hard_xmit(struct sk_buff *skb,
 
 	/* Check problems */
 	if(spin_is_locked(&dev->tx_lock)) {
-		IRDA_DEBUG(3, "%s(), write not completed\n", __func__);
+		pr_debug("%s(), write not completed\n", __func__);
 	}
 
 	/* serialize with write completion */
@@ -684,7 +684,7 @@ static int sirdev_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
 
 	IRDA_ASSERT(dev != NULL, return -1;);
 
-	IRDA_DEBUG(3, "%s(), %s, (cmd=0x%X)\n", __func__, ndev->name, cmd);
+	pr_debug("%s(), %s, (cmd=0x%X)\n", __func__, ndev->name, cmd);
 	
 	switch (cmd) {
 	case SIOCSBANDWIDTH: /* Set bandwidth */
@@ -801,8 +801,6 @@ static int sirdev_open(struct net_device *ndev)
 	if (!try_module_get(drv->owner))
 		return -ESTALE;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	if (sirdev_alloc_buffers(dev))
 		goto errout_dec;
 
@@ -819,7 +817,7 @@ static int sirdev_open(struct net_device *ndev)
 
 	netif_wake_queue(ndev);
 
-	IRDA_DEBUG(2, "%s - done, speed = %d\n", __func__, dev->speed);
+	pr_debug("%s - done, speed = %d\n", __func__, dev->speed);
 
 	return 0;
 
@@ -839,7 +837,7 @@ static int sirdev_close(struct net_device *ndev)
 	struct sir_dev *dev = netdev_priv(ndev);
 	const struct sir_driver *drv;
 
-//	IRDA_DEBUG(0, "%s\n", __func__);
+/* pr_debug("%s\n", __func__); */
 
 	netif_stop_queue(ndev);
 
@@ -881,7 +879,7 @@ struct sir_dev * sirdev_get_instance(const struct sir_driver *drv, const char *n
 	struct net_device *ndev;
 	struct sir_dev *dev;
 
-	IRDA_DEBUG(0, "%s - %s\n", __func__, name);
+	pr_debug("%s - %s\n", __func__, name);
 
 	/* instead of adding tests to protect against drv->do_write==NULL
 	 * at several places we refuse to create a sir_dev instance for
@@ -939,7 +937,7 @@ int sirdev_put_instance(struct sir_dev *dev)
 {
 	int err = 0;
 
-	IRDA_DEBUG(0, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	atomic_set(&dev->enable_rx, 0);
 
diff --git a/drivers/net/irda/sir_dongle.c b/drivers/net/irda/sir_dongle.c
index cfbabb63f5c..7436f73ff1b 100644
--- a/drivers/net/irda/sir_dongle.c
+++ b/drivers/net/irda/sir_dongle.c
@@ -34,8 +34,8 @@ int irda_register_dongle(struct dongle_driver *new)
 	struct list_head *entry;
 	struct dongle_driver *drv;
 
-	IRDA_DEBUG(0, "%s : registering dongle \"%s\" (%d).\n",
-		   __func__, new->driver_name, new->type);
+	pr_debug("%s : registering dongle \"%s\" (%d).\n",
+		 __func__, new->driver_name, new->type);
 
 	mutex_lock(&dongle_list_lock);
 	list_for_each(entry, &dongle_list) {
diff --git a/drivers/net/irda/smsc-ircc2.c b/drivers/net/irda/smsc-ircc2.c
index a7f0f5214ad..b455ffe8850 100644
--- a/drivers/net/irda/smsc-ircc2.c
+++ b/drivers/net/irda/smsc-ircc2.c
@@ -461,7 +461,7 @@ static int __init smsc_ircc_init(void)
 {
 	int ret;
 
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	ret = platform_driver_register(&smsc_ircc_driver);
 	if (ret) {
@@ -523,7 +523,7 @@ static int smsc_ircc_open(unsigned int fir_base, unsigned int sir_base, u8 dma,
 	struct net_device *dev;
 	int err;
 
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	err = smsc_ircc_present(fir_base, sir_base);
 	if (err)
@@ -803,7 +803,7 @@ static int smsc_ircc_net_ioctl(struct net_device *dev, struct ifreq *rq, int cmd
 
 	IRDA_ASSERT(self != NULL, return -1;);
 
-	IRDA_DEBUG(2, "%s(), %s, (cmd=0x%X)\n", __func__, dev->name, cmd);
+	pr_debug("%s(), %s, (cmd=0x%X)\n", __func__, dev->name, cmd);
 
 	switch (cmd) {
 	case SIOCSBANDWIDTH: /* Set bandwidth */
@@ -882,7 +882,7 @@ static netdev_tx_t smsc_ircc_hard_xmit_sir(struct sk_buff *skb,
 	unsigned long flags;
 	s32 speed;
 
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	IRDA_ASSERT(dev != NULL, return NETDEV_TX_OK;);
 
@@ -957,21 +957,21 @@ static void smsc_ircc_set_fir_speed(struct smsc_ircc_cb *self, u32 speed)
 		ir_mode = IRCC_CFGA_IRDA_HDLC;
 		ctrl = IRCC_CRC;
 		fast = 0;
-		IRDA_DEBUG(0, "%s(), handling baud of 576000\n", __func__);
+		pr_debug("%s(), handling baud of 576000\n", __func__);
 		break;
 	case 1152000:
 		ir_mode = IRCC_CFGA_IRDA_HDLC;
 		ctrl = IRCC_1152 | IRCC_CRC;
 		fast = IRCC_LCR_A_FAST | IRCC_LCR_A_GP_DATA;
-		IRDA_DEBUG(0, "%s(), handling baud of 1152000\n",
-			   __func__);
+		pr_debug("%s(), handling baud of 1152000\n",
+			 __func__);
 		break;
 	case 4000000:
 		ir_mode = IRCC_CFGA_IRDA_4PPM;
 		ctrl = IRCC_CRC;
 		fast = IRCC_LCR_A_FAST;
-		IRDA_DEBUG(0, "%s(), handling baud of 4000000\n",
-			   __func__);
+		pr_debug("%s(), handling baud of 4000000\n",
+			 __func__);
 		break;
 	}
 	#if 0
@@ -999,7 +999,7 @@ static void smsc_ircc_fir_start(struct smsc_ircc_cb *self)
 	struct net_device *dev;
 	int fir_base;
 
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	IRDA_ASSERT(self != NULL, return;);
 	dev = self->netdev;
@@ -1044,7 +1044,7 @@ static void smsc_ircc_fir_stop(struct smsc_ircc_cb *self)
 {
 	int fir_base;
 
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	IRDA_ASSERT(self != NULL, return;);
 
@@ -1068,7 +1068,7 @@ static void smsc_ircc_change_speed(struct smsc_ircc_cb *self, u32 speed)
 	struct net_device *dev;
 	int last_speed_was_sir;
 
-	IRDA_DEBUG(0, "%s() changing speed to: %d\n", __func__, speed);
+	pr_debug("%s() changing speed to: %d\n", __func__, speed);
 
 	IRDA_ASSERT(self != NULL, return;);
 	dev = self->netdev;
@@ -1136,7 +1136,7 @@ static void smsc_ircc_set_sir_speed(struct smsc_ircc_cb *self, __u32 speed)
 	int lcr;    /* Line control reg */
 	int divisor;
 
-	IRDA_DEBUG(0, "%s(), Setting speed to: %d\n", __func__, speed);
+	pr_debug("%s(), Setting speed to: %d\n", __func__, speed);
 
 	IRDA_ASSERT(self != NULL, return;);
 	iobase = self->io.sir_base;
@@ -1171,7 +1171,7 @@ static void smsc_ircc_set_sir_speed(struct smsc_ircc_cb *self, __u32 speed)
 	/* Turn on interrups */
 	outb(UART_IER_RLSI | UART_IER_RDI | UART_IER_THRI, iobase + UART_IER);
 
-	IRDA_DEBUG(2, "%s() speed changed to: %d\n", __func__, speed);
+	pr_debug("%s() speed changed to: %d\n", __func__, speed);
 }
 
 
@@ -1255,7 +1255,7 @@ static void smsc_ircc_dma_xmit(struct smsc_ircc_cb *self, int bofs)
 	int iobase = self->io.fir_base;
 	u8 ctrl;
 
-	IRDA_DEBUG(3, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 #if 1
 	/* Disable Rx */
 	register_bank(iobase, 0);
@@ -1309,7 +1309,7 @@ static void smsc_ircc_dma_xmit_complete(struct smsc_ircc_cb *self)
 {
 	int iobase = self->io.fir_base;
 
-	IRDA_DEBUG(3, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 #if 0
 	/* Disable Tx */
 	register_bank(iobase, 0);
@@ -1413,7 +1413,7 @@ static void smsc_ircc_dma_receive_complete(struct smsc_ircc_cb *self)
 
 	register_bank(iobase, 0);
 
-	IRDA_DEBUG(3, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 #if 0
 	/* Disable Rx */
 	register_bank(iobase, 0);
@@ -1424,8 +1424,8 @@ static void smsc_ircc_dma_receive_complete(struct smsc_ircc_cb *self)
 	lsr= inb(iobase + IRCC_LSR);
 	msgcnt = inb(iobase + IRCC_LCR_B) & 0x08;
 
-	IRDA_DEBUG(2, "%s: dma count = %d\n", __func__,
-		   get_dma_residue(self->io.dma));
+	pr_debug("%s: dma count = %d\n", __func__,
+		 get_dma_residue(self->io.dma));
 
 	len = self->rx_buff.truesize - get_dma_residue(self->io.dma);
 
@@ -1450,7 +1450,7 @@ static void smsc_ircc_dma_receive_complete(struct smsc_ircc_cb *self)
 		net_warn_ratelimited("%s(), bogus len=%d\n", __func__, len);
 		return;
 	}
-	IRDA_DEBUG(2, "%s: msgcnt = %d, len=%d\n", __func__, msgcnt, len);
+	pr_debug("%s: msgcnt = %d, len=%d\n", __func__, msgcnt, len);
 
 	skb = dev_alloc_skb(len + 1);
 	if (!skb)
@@ -1494,7 +1494,7 @@ static void smsc_ircc_sir_receive(struct smsc_ircc_cb *self)
 
 		/* Make sure we don't stay here to long */
 		if (boguscount++ > 32) {
-			IRDA_DEBUG(2, "%s(), breaking!\n", __func__);
+			pr_debug("%s(), breaking!\n", __func__);
 			break;
 		}
 	} while (inb(iobase + UART_LSR) & UART_LSR_DR);
@@ -1536,7 +1536,7 @@ static irqreturn_t smsc_ircc_interrupt(int dummy, void *dev_id)
 	lcra = inb(iobase + IRCC_LCR_A);
 	lsr = inb(iobase + IRCC_LSR);
 
-	IRDA_DEBUG(2, "%s(), iir = 0x%02x\n", __func__, iir);
+	pr_debug("%s(), iir = 0x%02x\n", __func__, iir);
 
 	if (iir & IRCC_IIR_EOM) {
 		if (self->io.direction == IO_RECV)
@@ -1586,12 +1586,12 @@ static irqreturn_t smsc_ircc_interrupt_sir(struct net_device *dev)
 		/* Clear interrupt */
 		lsr = inb(iobase + UART_LSR);
 
-		IRDA_DEBUG(4, "%s(), iir=%02x, lsr=%02x, iobase=%#x\n",
-			    __func__, iir, lsr, iobase);
+		pr_debug("%s(), iir=%02x, lsr=%02x, iobase=%#x\n",
+			 __func__, iir, lsr, iobase);
 
 		switch (iir) {
 		case UART_IIR_RLSI:
-			IRDA_DEBUG(2, "%s(), RLSI\n", __func__);
+			pr_debug("%s(), RLSI\n", __func__);
 			break;
 		case UART_IIR_RDI:
 			/* Receive interrupt */
@@ -1603,8 +1603,8 @@ static irqreturn_t smsc_ircc_interrupt_sir(struct net_device *dev)
 				smsc_ircc_sir_write_wakeup(self);
 			break;
 		default:
-			IRDA_DEBUG(0, "%s(), unhandled IIR=%#x\n",
-				   __func__, iir);
+			pr_debug("%s(), unhandled IIR=%#x\n",
+				 __func__, iir);
 			break;
 		}
 
@@ -1631,12 +1631,12 @@ static int ircc_is_receiving(struct smsc_ircc_cb *self)
 	int status = FALSE;
 	/* int iobase; */
 
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	IRDA_ASSERT(self != NULL, return FALSE;);
 
-	IRDA_DEBUG(0, "%s: dma count = %d\n", __func__,
-		   get_dma_residue(self->io.dma));
+	pr_debug("%s: dma count = %d\n", __func__,
+		 get_dma_residue(self->io.dma));
 
 	status = (self->rx_buff.state != OUTSIDE_FRAME);
 
@@ -1651,8 +1651,8 @@ static int smsc_ircc_request_irq(struct smsc_ircc_cb *self)
 	error = request_irq(self->io.irq, smsc_ircc_interrupt, 0,
 			    self->netdev->name, self->netdev);
 	if (error)
-		IRDA_DEBUG(0, "%s(), unable to allocate irq=%d, err=%d\n",
-			   __func__, self->io.irq, error);
+		pr_debug("%s(), unable to allocate irq=%d, err=%d\n",
+			 __func__, self->io.irq, error);
 
 	return error;
 }
@@ -1696,21 +1696,21 @@ static int smsc_ircc_net_open(struct net_device *dev)
 	struct smsc_ircc_cb *self;
 	char hwname[16];
 
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	IRDA_ASSERT(dev != NULL, return -1;);
 	self = netdev_priv(dev);
 	IRDA_ASSERT(self != NULL, return 0;);
 
 	if (self->io.suspended) {
-		IRDA_DEBUG(0, "%s(), device is suspended\n", __func__);
+		pr_debug("%s(), device is suspended\n", __func__);
 		return -EAGAIN;
 	}
 
 	if (request_irq(self->io.irq, smsc_ircc_interrupt, 0, dev->name,
 			(void *) dev)) {
-		IRDA_DEBUG(0, "%s(), unable to allocate irq=%d\n",
-			   __func__, self->io.irq);
+		pr_debug("%s(), unable to allocate irq=%d\n",
+			 __func__, self->io.irq);
 		return -EAGAIN;
 	}
 
@@ -1753,7 +1753,7 @@ static int smsc_ircc_net_close(struct net_device *dev)
 {
 	struct smsc_ircc_cb *self;
 
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	IRDA_ASSERT(dev != NULL, return -1;);
 	self = netdev_priv(dev);
@@ -1784,7 +1784,7 @@ static int smsc_ircc_suspend(struct platform_device *dev, pm_message_t state)
 	struct smsc_ircc_cb *self = platform_get_drvdata(dev);
 
 	if (!self->io.suspended) {
-		IRDA_DEBUG(1, "%s, Suspending\n", driver_name);
+		pr_debug("%s, Suspending\n", driver_name);
 
 		rtnl_lock();
 		if (netif_running(self->netdev)) {
@@ -1805,7 +1805,7 @@ static int smsc_ircc_resume(struct platform_device *dev)
 	struct smsc_ircc_cb *self = platform_get_drvdata(dev);
 
 	if (self->io.suspended) {
-		IRDA_DEBUG(1, "%s, Waking up\n", driver_name);
+		pr_debug("%s, Waking up\n", driver_name);
 
 		rtnl_lock();
 		smsc_ircc_init_chip(self);
@@ -1836,7 +1836,7 @@ static int smsc_ircc_resume(struct platform_device *dev)
  */
 static int __exit smsc_ircc_close(struct smsc_ircc_cb *self)
 {
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	IRDA_ASSERT(self != NULL, return -1;);
 
@@ -1848,13 +1848,13 @@ static int __exit smsc_ircc_close(struct smsc_ircc_cb *self)
 	smsc_ircc_stop_interrupts(self);
 
 	/* Release the PORTS that this driver is using */
-	IRDA_DEBUG(0, "%s(), releasing 0x%03x\n",  __func__,
-		   self->io.fir_base);
+	pr_debug("%s(), releasing 0x%03x\n",  __func__,
+		 self->io.fir_base);
 
 	release_region(self->io.fir_base, self->io.fir_ext);
 
-	IRDA_DEBUG(0, "%s(), releasing 0x%03x\n", __func__,
-		   self->io.sir_base);
+	pr_debug("%s(), releasing 0x%03x\n", __func__,
+		 self->io.sir_base);
 
 	release_region(self->io.sir_base, self->io.sir_ext);
 
@@ -1875,7 +1875,7 @@ static void __exit smsc_ircc_cleanup(void)
 {
 	int i;
 
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	for (i = 0; i < 2; i++) {
 		if (dev_self[i])
@@ -1899,7 +1899,7 @@ static void smsc_ircc_sir_start(struct smsc_ircc_cb *self)
 	struct net_device *dev;
 	int fir_base, sir_base;
 
-	IRDA_DEBUG(3, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	IRDA_ASSERT(self != NULL, return;);
 	dev = self->netdev;
@@ -1925,7 +1925,7 @@ static void smsc_ircc_sir_start(struct smsc_ircc_cb *self)
 	/* Turn on interrups */
 	outb(UART_IER_RLSI | UART_IER_RDI |UART_IER_THRI, sir_base + UART_IER);
 
-	IRDA_DEBUG(3, "%s() - exit\n", __func__);
+	pr_debug("%s() - exit\n", __func__);
 
 	outb(0x00, fir_base + IRCC_MASTER);
 }
@@ -1935,7 +1935,7 @@ void smsc_ircc_sir_stop(struct smsc_ircc_cb *self)
 {
 	int iobase;
 
-	IRDA_DEBUG(3, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 	iobase = self->io.sir_base;
 
 	/* Reset UART */
@@ -1961,7 +1961,7 @@ static void smsc_ircc_sir_write_wakeup(struct smsc_ircc_cb *self)
 
 	IRDA_ASSERT(self != NULL, return;);
 
-	IRDA_DEBUG(4, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	iobase = self->io.sir_base;
 
@@ -1982,8 +1982,8 @@ static void smsc_ircc_sir_write_wakeup(struct smsc_ircc_cb *self)
 		 *  if we need to change the speed of the hardware
 		 */
 		if (self->new_speed) {
-			IRDA_DEBUG(5, "%s(), Changing speed to %d.\n",
-				   __func__, self->new_speed);
+			pr_debug("%s(), Changing speed to %d.\n",
+				 __func__, self->new_speed);
 			smsc_ircc_sir_wait_hw_transmitter_finish(self);
 			smsc_ircc_change_speed(self, self->new_speed);
 			self->new_speed = 0;
@@ -2123,7 +2123,7 @@ static void smsc_ircc_sir_wait_hw_transmitter_finish(struct smsc_ircc_cb *self)
 		udelay(1);
 
 	if (count < 0)
-		IRDA_DEBUG(0, "%s(): stuck transmitter\n", __func__);
+		pr_debug("%s(): stuck transmitter\n", __func__);
 }
 
 
@@ -2184,7 +2184,7 @@ static int __init smsc_superio_flat(const struct smsc_chip *chips, unsigned shor
 	u8 mode, dma, irq;
 	int ret = -ENODEV;
 
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	if (smsc_ircc_probe(cfgbase, SMSCSIOFLAT_DEVICEID_REG, chips, type) == NULL)
 		return ret;
@@ -2235,7 +2235,7 @@ static int __init smsc_superio_paged(const struct smsc_chip *chips, unsigned sho
 	unsigned short fir_io, sir_io;
 	int ret = -ENODEV;
 
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	if (smsc_ircc_probe(cfg_base, 0x20, chips, type) == NULL)
 		return ret;
@@ -2269,7 +2269,7 @@ static int __init smsc_superio_paged(const struct smsc_chip *chips, unsigned sho
 
 static int __init smsc_access(unsigned short cfg_base, unsigned char reg)
 {
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	outb(reg, cfg_base);
 	return inb(cfg_base) != reg ? -1 : 0;
@@ -2279,7 +2279,7 @@ static const struct smsc_chip * __init smsc_ircc_probe(unsigned short cfg_base,
 {
 	u8 devid, xdevid, rev;
 
-	IRDA_DEBUG(1, "%s\n", __func__);
+	pr_debug("%s\n", __func__);
 
 	/* Leave configuration */
 
@@ -2534,9 +2534,8 @@ static int __init preconfigure_smsc_chip(struct
 	outb(LPC47N227_CFGACCESSKEY, iobase); // enter configuration state
 	outb(SMSCSIOFLAT_DEVICEID_REG, iobase); // set for device ID
 	tmpbyte = inb(iobase +1); // Read device ID
-	IRDA_DEBUG(0,
-		   "Detected Chip id: 0x%02x, setting up registers...\n",
-		   tmpbyte);
+	pr_debug("Detected Chip id: 0x%02x, setting up registers...\n",
+		 tmpbyte);
 
 	/* Disable UART1 and set up SIR I/O port */
 	outb(0x24, iobase);  // select CR24 - UART1 base addr
@@ -2682,7 +2681,7 @@ static int __init preconfigure_through_82801(struct pci_dev *dev,
 	default:
 		tmpbyte |= 0x01; /* COM2 default */
 	}
-	IRDA_DEBUG(1, "COM_DEC (write): 0x%02x\n", tmpbyte);
+	pr_debug("COM_DEC (write): 0x%02x\n", tmpbyte);
 	pci_write_config_byte(dev, COM_DEC, tmpbyte);
 
 	/* Enable Low Pin Count interface */
@@ -2710,7 +2709,7 @@ static int __init preconfigure_through_82801(struct pci_dev *dev,
 	}
 	tmpword &= 0xfffd; /* disable LPC COMB */
 	tmpword |= 0x0001; /* set bit 0 : enable LPC COMA addr range (GEN2) */
-	IRDA_DEBUG(1, "LPC_EN (write): 0x%04x\n", tmpword);
+	pr_debug("LPC_EN (write): 0x%04x\n", tmpword);
 	pci_write_config_word(dev, LPC_EN, tmpword);
 
 	/*
@@ -2755,7 +2754,7 @@ static int __init preconfigure_through_82801(struct pci_dev *dev,
 	default:
 		break; /* do not change settings */
 	}
-	IRDA_DEBUG(1, "PCI_DMA_C (write): 0x%04x\n", tmpword);
+	pr_debug("PCI_DMA_C (write): 0x%04x\n", tmpword);
 	pci_write_config_word(dev, PCI_DMA_C, tmpword);
 
 	/*
@@ -2766,7 +2765,7 @@ static int __init preconfigure_through_82801(struct pci_dev *dev,
 	 */
 	tmpword = conf->fir_io & 0xfff8;
 	tmpword |= 0x0001;
-	IRDA_DEBUG(1, "GEN2_DEC (write): 0x%04x\n", tmpword);
+	pr_debug("GEN2_DEC (write): 0x%04x\n", tmpword);
 	pci_write_config_word(dev, GEN2_DEC, tmpword);
 
 	/* Pre-configure chip */
diff --git a/drivers/net/irda/tekram-sir.c b/drivers/net/irda/tekram-sir.c
index 04db4eac9dc..9dcf0c103b9 100644
--- a/drivers/net/irda/tekram-sir.c
+++ b/drivers/net/irda/tekram-sir.c
@@ -63,8 +63,8 @@ static int __init tekram_sir_init(void)
 {
 	if (tekram_delay < 1  ||  tekram_delay > 500)
 		tekram_delay = 200;
-	IRDA_DEBUG(1, "%s - using %d ms delay\n",
-		tekram.driver_name, tekram_delay);
+	pr_debug("%s - using %d ms delay\n",
+		 tekram.driver_name, tekram_delay);
 	return irda_register_dongle(&tekram);
 }
 
@@ -77,8 +77,6 @@ static int tekram_open(struct sir_dev *dev)
 {
 	struct qos_info *qos = &dev->qos;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	sirdev_set_dtr_rts(dev, TRUE, TRUE);
 
 	qos->baud_rate.bits &= IR_9600|IR_19200|IR_38400|IR_57600|IR_115200;
@@ -92,8 +90,6 @@ static int tekram_open(struct sir_dev *dev)
 
 static int tekram_close(struct sir_dev *dev)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Power off dongle */
 	sirdev_set_dtr_rts(dev, FALSE, FALSE);
 
@@ -130,8 +126,6 @@ static int tekram_change_speed(struct sir_dev *dev, unsigned speed)
 	u8 byte;
 	static int ret = 0;
 	
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	switch(state) {
 	case SIRDEV_STATE_DONGLE_SPEED:
 
@@ -205,8 +199,6 @@ static int tekram_change_speed(struct sir_dev *dev, unsigned speed)
 
 static int tekram_reset(struct sir_dev *dev)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Clear DTR, Set RTS */
 	sirdev_set_dtr_rts(dev, FALSE, TRUE); 
 
diff --git a/drivers/net/irda/toim3232-sir.c b/drivers/net/irda/toim3232-sir.c
index 19ad4606b79..6d2f55959c4 100644
--- a/drivers/net/irda/toim3232-sir.c
+++ b/drivers/net/irda/toim3232-sir.c
@@ -168,8 +168,8 @@ static int __init toim3232_sir_init(void)
 {
 	if (toim3232delay < 1  ||  toim3232delay > 500)
 		toim3232delay = 200;
-	IRDA_DEBUG(1, "%s - using %d ms delay\n",
-		toim3232.driver_name, toim3232delay);
+	pr_debug("%s - using %d ms delay\n",
+		 toim3232.driver_name, toim3232delay);
 	return irda_register_dongle(&toim3232);
 }
 
@@ -182,8 +182,6 @@ static int toim3232_open(struct sir_dev *dev)
 {
 	struct qos_info *qos = &dev->qos;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Pull the lines high to start with.
 	 *
 	 * For the IR320ST-2, we need to charge the main supply capacitor to
@@ -210,8 +208,6 @@ static int toim3232_open(struct sir_dev *dev)
 
 static int toim3232_close(struct sir_dev *dev)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Power off dongle */
 	sirdev_set_dtr_rts(dev, FALSE, FALSE);
 
@@ -242,8 +238,6 @@ static int toim3232_change_speed(struct sir_dev *dev, unsigned speed)
 	u8 byte;
 	static int ret = 0;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	switch(state) {
 	case SIRDEV_STATE_DONGLE_SPEED:
 
@@ -345,8 +339,6 @@ static int toim3232_change_speed(struct sir_dev *dev, unsigned speed)
 
 static int toim3232_reset(struct sir_dev *dev)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Switch off both DTR and RTS to switch off dongle */
 	sirdev_set_dtr_rts(dev, FALSE, FALSE);
 
diff --git a/drivers/net/irda/via-ircc.c b/drivers/net/irda/via-ircc.c
index b07b4ccddca..6960d4cd3ca 100644
--- a/drivers/net/irda/via-ircc.c
+++ b/drivers/net/irda/via-ircc.c
@@ -144,12 +144,10 @@ static int __init via_ircc_init(void)
 {
 	int rc;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	rc = pci_register_driver(&via_driver);
 	if (rc < 0) {
-		IRDA_DEBUG(0, "%s(): error rc = %d, returning  -ENODEV...\n",
-			   __func__, rc);
+		pr_debug("%s(): error rc = %d, returning  -ENODEV...\n",
+			 __func__, rc);
 		return -ENODEV;
 	}
 	return 0;
@@ -162,11 +160,11 @@ static int via_init_one(struct pci_dev *pcidev, const struct pci_device_id *id)
 	u16 Chipset,FirDRQ1,FirDRQ0,FirIRQ,FirIOBase;
 	chipio_t info;
 
-	IRDA_DEBUG(2, "%s(): Device ID=(0X%X)\n", __func__, id->device);
+	pr_debug("%s(): Device ID=(0X%X)\n", __func__, id->device);
 
 	rc = pci_enable_device (pcidev);
 	if (rc) {
-		IRDA_DEBUG(0, "%s(): error rc = %d\n", __func__, rc);
+		pr_debug("%s(): error rc = %d\n", __func__, rc);
 		return -ENODEV;
 	}
 
@@ -177,7 +175,7 @@ static int via_init_one(struct pci_dev *pcidev, const struct pci_device_id *id)
 		Chipset=0x3076;
 
 	if (Chipset==0x3076) {
-		IRDA_DEBUG(2, "%s(): Chipset = 3076\n", __func__);
+		pr_debug("%s(): Chipset = 3076\n", __func__);
 
 		WriteLPCReg(7,0x0c );
 		temp=ReadLPCReg(0x30);//check if BIOS Enable Fir
@@ -213,7 +211,7 @@ static int via_init_one(struct pci_dev *pcidev, const struct pci_device_id *id)
 		} else
 			rc = -ENODEV; //IR not turn on	 
 	} else { //Not VT1211
-		IRDA_DEBUG(2, "%s(): Chipset = 3096\n", __func__);
+		pr_debug("%s(): Chipset = 3096\n", __func__);
 
 		pci_read_config_byte(pcidev,0x67,&bTmp);//check if BIOS Enable Fir
 		if((bTmp&0x01)==1) {  // BIOS enable FIR
@@ -252,14 +250,12 @@ static int via_init_one(struct pci_dev *pcidev, const struct pci_device_id *id)
 			rc = -ENODEV; //IR not turn on !!!!!
 	}//Not VT1211
 
-	IRDA_DEBUG(2, "%s(): End - rc = %d\n", __func__, rc);
+	pr_debug("%s(): End - rc = %d\n", __func__, rc);
 	return rc;
 }
 
 static void __exit via_ircc_cleanup(void)
 {
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	/* Cleanup all instances of the driver */
 	pci_unregister_driver (&via_driver); 
 }
@@ -289,8 +285,6 @@ static int via_ircc_open(struct pci_dev *pdev, chipio_t *info, unsigned int id)
 	struct via_ircc_cb *self;
 	int err;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	/* Allocate new instance of the driver */
 	dev = alloc_irdadev(sizeof(struct via_ircc_cb));
 	if (dev == NULL) 
@@ -316,8 +310,8 @@ static int via_ircc_open(struct pci_dev *pdev, chipio_t *info, unsigned int id)
 
 	/* Reserve the ioports that we need */
 	if (!request_region(self->io.fir_base, self->io.fir_ext, driver_name)) {
-		IRDA_DEBUG(0, "%s(), can't get iobase of 0x%03x\n",
-			   __func__, self->io.fir_base);
+		pr_debug("%s(), can't get iobase of 0x%03x\n",
+			 __func__, self->io.fir_base);
 		err = -ENODEV;
 		goto err_out1;
 	}
@@ -423,8 +417,6 @@ static void via_remove_one(struct pci_dev *pdev)
 	struct via_ircc_cb *self = pci_get_drvdata(pdev);
 	int iobase;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	iobase = self->io.fir_base;
 
 	ResetChip(iobase, 5);	//hardware reset.
@@ -432,8 +424,8 @@ static void via_remove_one(struct pci_dev *pdev)
 	unregister_netdev(self->netdev);
 
 	/* Release the PORT that this driver is using */
-	IRDA_DEBUG(2, "%s(), Releasing Region %03x\n",
-		   __func__, self->io.fir_base);
+	pr_debug("%s(), Releasing Region %03x\n",
+		 __func__, self->io.fir_base);
 	release_region(self->io.fir_base, self->io.fir_ext);
 	if (self->tx_buff.head)
 		dma_free_coherent(&pdev->dev, self->tx_buff.truesize,
@@ -458,8 +450,6 @@ static void via_hw_init(struct via_ircc_cb *self)
 {
 	int iobase = self->io.fir_base;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	SetMaxRxPacketSize(iobase, 0x0fff);	//set to max:4095
 	// FIFO Init
 	EnRXFIFOReadyInt(iobase, OFF);
@@ -528,8 +518,8 @@ static void via_ircc_change_dongle_speed(int iobase, int speed,
 	/* speed is unused, as we use IsSIROn()/IsMIROn() */
 	speed = speed;
 
-	IRDA_DEBUG(1, "%s(): change_dongle_speed to %d for 0x%x, %d\n",
-		   __func__, speed, iobase, dongle_id);
+	pr_debug("%s(): change_dongle_speed to %d for 0x%x, %d\n",
+		 __func__, speed, iobase, dongle_id);
 
 	switch (dongle_id) {
 
@@ -618,7 +608,8 @@ static void via_ircc_change_dongle_speed(int iobase, int speed,
 
 	case 0x11:		/* Temic TFDS4500 */
 
-		IRDA_DEBUG(2, "%s: Temic TFDS4500: One RX pin, TX normal, RX inverted.\n", __func__);
+		pr_debug("%s: Temic TFDS4500: One RX pin, TX normal, RX inverted\n",
+			 __func__);
 
 		UseOneRX(iobase, ON);	//use ONE RX....RX1
 		InvertTX(iobase, OFF);
@@ -636,7 +627,8 @@ static void via_ircc_change_dongle_speed(int iobase, int speed,
 			SlowIRRXLowActive(iobase, OFF);
 
 		} else{
-			IRDA_DEBUG(0, "%s: Warning: TFDS4500 not running in SIR mode !\n", __func__);
+			pr_debug("%s: Warning: TFDS4500 not running in SIR mode !\n",
+				 __func__);
 		}
 		break;
 
@@ -673,7 +665,7 @@ static void via_ircc_change_speed(struct via_ircc_cb *self, __u32 speed)
 	iobase = self->io.fir_base;
 	/* Update accounting for new speed */
 	self->io.speed = speed;
-	IRDA_DEBUG(1, "%s: change_speed to %d bps.\n", __func__, speed);
+	pr_debug("%s: change_speed to %d bps.\n", __func__, speed);
 
 	WriteReg(iobase, I_ST_CT_0, 0x0);
 
@@ -903,10 +895,10 @@ static int via_ircc_dma_xmit(struct via_ircc_cb *self, u16 iobase)
 		       ((u8 *)self->tx_fifo.queue[self->tx_fifo.ptr].start -
 			self->tx_buff.head) + self->tx_buff_dma,
 		       self->tx_fifo.queue[self->tx_fifo.ptr].len, DMA_TX_MODE);
-	IRDA_DEBUG(1, "%s: tx_fifo.ptr=%x,len=%x,tx_fifo.len=%x..\n",
-		   __func__, self->tx_fifo.ptr,
-		   self->tx_fifo.queue[self->tx_fifo.ptr].len,
-		   self->tx_fifo.len);
+	pr_debug("%s: tx_fifo.ptr=%x,len=%x,tx_fifo.len=%x..\n",
+		 __func__, self->tx_fifo.ptr,
+		 self->tx_fifo.queue[self->tx_fifo.ptr].len,
+		 self->tx_fifo.len);
 
 	SetSendByte(iobase, self->tx_fifo.queue[self->tx_fifo.ptr].len);
 	RXStart(iobase, OFF);
@@ -927,8 +919,6 @@ static int via_ircc_dma_xmit_complete(struct via_ircc_cb *self)
 	int iobase;
 	u8 Tx_status;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	iobase = self->io.fir_base;
 	/* Disable DMA */
 //      DisableDmaChannel(self->io.dma);
@@ -958,10 +948,9 @@ static int via_ircc_dma_xmit_complete(struct via_ircc_cb *self)
 			self->tx_fifo.ptr++;
 		}
 	}
-	IRDA_DEBUG(1,
-		   "%s: tx_fifo.len=%x ,tx_fifo.ptr=%x,tx_fifo.free=%x...\n",
-		   __func__,
-		   self->tx_fifo.len, self->tx_fifo.ptr, self->tx_fifo.free);
+	pr_debug("%s: tx_fifo.len=%x ,tx_fifo.ptr=%x,tx_fifo.free=%x...\n",
+		 __func__,
+		 self->tx_fifo.len, self->tx_fifo.ptr, self->tx_fifo.free);
 /* F01_S
 	// Any frames to be sent back-to-back? 
 	if (self->tx_fifo.len) {
@@ -996,8 +985,6 @@ static int via_ircc_dma_receive(struct via_ircc_cb *self)
 
 	iobase = self->io.fir_base;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	self->tx_fifo.len = self->tx_fifo.ptr = self->tx_fifo.free = 0;
 	self->tx_fifo.tail = self->tx_buff.head;
 	self->RxDataReady = 0;
@@ -1079,15 +1066,15 @@ static int via_ircc_dma_receive_complete(struct via_ircc_cb *self,
 		if (len == 0)
 			return TRUE;	//interrupt only, data maybe move by RxT  
 		if (((len - 4) < 2) || ((len - 4) > 2048)) {
-			IRDA_DEBUG(1, "%s(): Trouble:len=%x,CurCount=%x,LastCount=%x..\n",
-				   __func__, len, RxCurCount(iobase, self),
-				   self->RxLastCount);
+			pr_debug("%s(): Trouble:len=%x,CurCount=%x,LastCount=%x\n",
+				 __func__, len, RxCurCount(iobase, self),
+				 self->RxLastCount);
 			hwreset(self);
 			return FALSE;
 		}
-		IRDA_DEBUG(2, "%s(): fifo.len=%x,len=%x,CurCount=%x..\n",
-			   __func__,
-			   st_fifo->len, len - 4, RxCurCount(iobase, self));
+		pr_debug("%s(): fifo.len=%x,len=%x,CurCount=%x..\n",
+			 __func__,
+			 st_fifo->len, len - 4, RxCurCount(iobase, self));
 
 		st_fifo->entries[st_fifo->tail].status = status;
 		st_fifo->entries[st_fifo->tail].len = len;
@@ -1134,8 +1121,8 @@ F01_E */
 		skb_put(skb, len - 4);
 
 		skb_copy_to_linear_data(skb, self->rx_buff.data, len - 4);
-		IRDA_DEBUG(2, "%s(): len=%x.rx_buff=%p\n", __func__,
-			   len - 4, self->rx_buff.data);
+		pr_debug("%s(): len=%x.rx_buff=%p\n", __func__,
+			 len - 4, self->rx_buff.data);
 
 		// Move to next frame 
 		self->rx_buff.data += len;
@@ -1164,7 +1151,7 @@ static int upload_rxdata(struct via_ircc_cb *self, int iobase)
 
 	len = GetRecvByte(iobase, self);
 
-	IRDA_DEBUG(2, "%s(): len=%x\n", __func__, len);
+	pr_debug("%s(): len=%x\n", __func__, len);
 
 	if ((len - 4) < 2) {
 		self->netdev->stats.rx_dropped++;
@@ -1249,8 +1236,8 @@ static int RxTimerHandler(struct via_ircc_cb *self, int iobase)
 			skb_put(skb, len - 4);
 			skb_copy_to_linear_data(skb, self->rx_buff.data, len - 4);
 
-			IRDA_DEBUG(2, "%s(): len=%x.head=%x\n", __func__,
-				   len - 4, st_fifo->head);
+			pr_debug("%s(): len=%x.head=%x\n", __func__,
+				 len - 4, st_fifo->head);
 
 			// Move to next frame 
 			self->rx_buff.data += len;
@@ -1263,10 +1250,8 @@ static int RxTimerHandler(struct via_ircc_cb *self, int iobase)
 		}		//while
 		self->RetryCount = 0;
 
-		IRDA_DEBUG(2,
-			   "%s(): End of upload HostStatus=%x,RxStatus=%x\n",
-			   __func__,
-			   GetHostStatus(iobase), GetRXStatus(iobase));
+		pr_debug("%s(): End of upload HostStatus=%x,RxStatus=%x\n",
+			 __func__, GetHostStatus(iobase), GetRXStatus(iobase));
 
 		/*
 		 * if frame is receive complete at this routine ,then upload
@@ -1304,12 +1289,12 @@ static irqreturn_t via_ircc_interrupt(int dummy, void *dev_id)
 	spin_lock(&self->lock);
 	iHostIntType = GetHostStatus(iobase);
 
-	IRDA_DEBUG(4, "%s(): iHostIntType %02x:  %s %s %s  %02x\n",
-		   __func__, iHostIntType,
-		   (iHostIntType & 0x40) ? "Timer" : "",
-		   (iHostIntType & 0x20) ? "Tx" : "",
-		   (iHostIntType & 0x10) ? "Rx" : "",
-		   (iHostIntType & 0x0e) >> 1);
+	pr_debug("%s(): iHostIntType %02x:  %s %s %s  %02x\n",
+		 __func__, iHostIntType,
+		 (iHostIntType & 0x40) ? "Timer" : "",
+		 (iHostIntType & 0x20) ? "Tx" : "",
+		 (iHostIntType & 0x10) ? "Rx" : "",
+		 (iHostIntType & 0x0e) >> 1);
 
 	if ((iHostIntType & 0x40) != 0) {	//Timer Event
 		self->EventFlag.TimeOut++;
@@ -1334,12 +1319,12 @@ static irqreturn_t via_ircc_interrupt(int dummy, void *dev_id)
 	if ((iHostIntType & 0x20) != 0) {	//Tx Event
 		iTxIntType = GetTXStatus(iobase);
 
-		IRDA_DEBUG(4, "%s(): iTxIntType %02x:  %s %s %s %s\n",
-			   __func__, iTxIntType,
-			   (iTxIntType & 0x08) ? "FIFO underr." : "",
-			   (iTxIntType & 0x04) ? "EOM" : "",
-			   (iTxIntType & 0x02) ? "FIFO ready" : "",
-			   (iTxIntType & 0x01) ? "Early EOM" : "");
+		pr_debug("%s(): iTxIntType %02x:  %s %s %s %s\n",
+			 __func__, iTxIntType,
+			 (iTxIntType & 0x08) ? "FIFO underr." : "",
+			 (iTxIntType & 0x04) ? "EOM" : "",
+			 (iTxIntType & 0x02) ? "FIFO ready" : "",
+			 (iTxIntType & 0x01) ? "Early EOM" : "");
 
 		if (iTxIntType & 0x4) {
 			self->EventFlag.EOMessage++;	// read and will auto clean
@@ -1358,17 +1343,17 @@ static irqreturn_t via_ircc_interrupt(int dummy, void *dev_id)
 		/* Check if DMA has finished */
 		iRxIntType = GetRXStatus(iobase);
 
-		IRDA_DEBUG(4, "%s(): iRxIntType %02x:  %s %s %s %s %s %s %s\n",
-			   __func__, iRxIntType,
-			   (iRxIntType & 0x80) ? "PHY err."	: "",
-			   (iRxIntType & 0x40) ? "CRC err"	: "",
-			   (iRxIntType & 0x20) ? "FIFO overr."	: "",
-			   (iRxIntType & 0x10) ? "EOF"		: "",
-			   (iRxIntType & 0x08) ? "RxData"	: "",
-			   (iRxIntType & 0x02) ? "RxMaxLen"	: "",
-			   (iRxIntType & 0x01) ? "SIR bad"	: "");
+		pr_debug("%s(): iRxIntType %02x:  %s %s %s %s %s %s %s\n",
+			 __func__, iRxIntType,
+			 (iRxIntType & 0x80) ? "PHY err."	: "",
+			 (iRxIntType & 0x40) ? "CRC err"	: "",
+			 (iRxIntType & 0x20) ? "FIFO overr."	: "",
+			 (iRxIntType & 0x10) ? "EOF"		: "",
+			 (iRxIntType & 0x08) ? "RxData"		: "",
+			 (iRxIntType & 0x02) ? "RxMaxLen"	: "",
+			 (iRxIntType & 0x01) ? "SIR bad"	: "");
 		if (!iRxIntType)
-			IRDA_DEBUG(3, "%s(): RxIRQ =0\n", __func__);
+			pr_debug("%s(): RxIRQ =0\n", __func__);
 
 		if (iRxIntType & 0x10) {
 			if (via_ircc_dma_receive_complete(self, iobase)) {
@@ -1377,10 +1362,9 @@ static irqreturn_t via_ircc_interrupt(int dummy, void *dev_id)
 			}
 		}		// No ERR     
 		else {		//ERR
-			IRDA_DEBUG(4, "%s(): RxIRQ ERR:iRxIntType=%x,HostIntType=%x,CurCount=%x,RxLastCount=%x_____\n",
-				   __func__, iRxIntType, iHostIntType,
-				   RxCurCount(iobase, self),
-				   self->RxLastCount);
+			pr_debug("%s(): RxIRQ ERR:iRxIntType=%x,HostIntType=%x,CurCount=%x,RxLastCount=%x_____\n",
+				 __func__, iRxIntType, iHostIntType,
+				 RxCurCount(iobase, self), self->RxLastCount);
 
 			if (iRxIntType & 0x20) {	//FIFO OverRun ERR
 				ResetChip(iobase, 0);
@@ -1403,8 +1387,6 @@ static void hwreset(struct via_ircc_cb *self)
 	int iobase;
 	iobase = self->io.fir_base;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	ResetChip(iobase, 5);
 	EnableDMA(iobase, OFF);
 	EnableTX(iobase, OFF);
@@ -1448,7 +1430,7 @@ static int via_ircc_is_receiving(struct via_ircc_cb *self)
 	if (CkRxRecv(iobase, self))
 		status = TRUE;
 
-	IRDA_DEBUG(2, "%s(): status=%x....\n", __func__, status);
+	pr_debug("%s(): status=%x....\n", __func__, status);
 
 	return status;
 }
@@ -1466,8 +1448,6 @@ static int via_ircc_net_open(struct net_device *dev)
 	int iobase;
 	char hwname[32];
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(dev != NULL, return -1;);
 	self = netdev_priv(dev);
 	dev->stats.rx_packets = 0;
@@ -1533,8 +1513,6 @@ static int via_ircc_net_close(struct net_device *dev)
 	struct via_ircc_cb *self;
 	int iobase;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(dev != NULL, return -1;);
 	self = netdev_priv(dev);
 	IRDA_ASSERT(self != NULL, return 0;);
@@ -1577,8 +1555,8 @@ static int via_ircc_net_ioctl(struct net_device *dev, struct ifreq *rq,
 	IRDA_ASSERT(dev != NULL, return -1;);
 	self = netdev_priv(dev);
 	IRDA_ASSERT(self != NULL, return -1;);
-	IRDA_DEBUG(1, "%s(), %s, (cmd=0x%X)\n", __func__, dev->name,
-		   cmd);
+	pr_debug("%s(), %s, (cmd=0x%X)\n", __func__, dev->name,
+		 cmd);
 	/* Disable interrupts & save flags */
 	spin_lock_irqsave(&self->lock, flags);
 	switch (cmd) {
diff --git a/drivers/net/irda/vlsi_ir.c b/drivers/net/irda/vlsi_ir.c
index fd4dedea8e0..ac39d9f33d5 100644
--- a/drivers/net/irda/vlsi_ir.c
+++ b/drivers/net/irda/vlsi_ir.c
@@ -556,7 +556,7 @@ static int vlsi_process_rx(struct vlsi_ring *r, struct ring_descr *rd)
 	crclen = (idev->mode==IFF_FIR) ? sizeof(u32) : sizeof(u16);
 	len -= crclen;		/* remove trailing CRC */
 	if (len <= 0) {
-		IRDA_DEBUG(0, "%s: strange frame (len=%d)\n", __func__, len);
+		pr_debug("%s: strange frame (len=%d)\n", __func__, len);
 		ret |= VLSI_RX_DROP;
 		goto done;
 	}
@@ -571,7 +571,7 @@ static int vlsi_process_rx(struct vlsi_ring *r, struct ring_descr *rd)
 		 */
 		le16_to_cpus(rd->buf+len);
 		if (irda_calc_crc16(INIT_FCS,rd->buf,len+crclen) != GOOD_FCS) {
-			IRDA_DEBUG(0, "%s: crc error\n", __func__);
+			pr_debug("%s: crc error\n", __func__);
 			ret |= VLSI_RX_CRC;
 			goto done;
 		}
@@ -689,7 +689,7 @@ static void vlsi_unarm_rx(vlsi_irda_dev_t *idev)
 		if (rd_is_active(rd)) {
 			rd_set_status(rd, 0);
 			if (rd_get_count(rd)) {
-				IRDA_DEBUG(0, "%s - dropping rx packet\n", __func__);
+				pr_debug("%s - dropping rx packet\n", __func__);
 				ret = -VLSI_RX_DROP;
 			}
 			rd_set_count(rd, 0);
@@ -764,7 +764,7 @@ static int vlsi_set_baud(vlsi_irda_dev_t *idev, unsigned iobase)
 	int	fifocnt;
 
 	baudrate = idev->new_baud;
-	IRDA_DEBUG(2, "%s: %d -> %d\n", __func__, idev->baud, idev->new_baud);
+	pr_debug("%s: %d -> %d\n", __func__, idev->baud, idev->new_baud);
 	if (baudrate == 4000000) {
 		mode = IFF_FIR;
 		config = IRCFG_FIR;
@@ -798,7 +798,7 @@ static int vlsi_set_baud(vlsi_irda_dev_t *idev, unsigned iobase)
 
 	fifocnt = inw(iobase+VLSI_PIO_RCVBCNT) & RCVBCNT_MASK;
 	if (fifocnt != 0) {
-		IRDA_DEBUG(0, "%s: rx fifo not empty(%d)\n", __func__, fifocnt);
+		pr_debug("%s: rx fifo not empty(%d)\n", __func__, fifocnt);
 	}
 
 	outw(0, iobase+VLSI_PIO_IRENABLE);
@@ -1022,7 +1022,8 @@ static netdev_tx_t vlsi_hard_start_xmit(struct sk_buff *skb,
 
 		fifocnt = inw(ndev->base_addr+VLSI_PIO_RCVBCNT) & RCVBCNT_MASK;
 		if (fifocnt != 0) {
-			IRDA_DEBUG(0, "%s: rx fifo not empty(%d)\n", __func__, fifocnt);
+			pr_debug("%s: rx fifo not empty(%d)\n",
+				 __func__, fifocnt);
 		}
 
 		config = inw(iobase+VLSI_PIO_IRCFG);
@@ -1034,7 +1035,7 @@ static netdev_tx_t vlsi_hard_start_xmit(struct sk_buff *skb,
 
 	if (ring_put(r) == NULL) {
 		netif_stop_queue(ndev);
-		IRDA_DEBUG(3, "%s: tx ring full - queue stopped\n", __func__);
+		pr_debug("%s: tx ring full - queue stopped\n", __func__);
 	}
 	spin_unlock_irqrestore(&idev->lock, flags);
 
@@ -1099,8 +1100,8 @@ static void vlsi_tx_interrupt(struct net_device *ndev)
 
 		fifocnt = inw(iobase+VLSI_PIO_RCVBCNT) & RCVBCNT_MASK;
 		if (fifocnt != 0) {
-			IRDA_DEBUG(0, "%s: rx fifo not empty(%d)\n",
-				__func__, fifocnt);
+			pr_debug("%s: rx fifo not empty(%d)\n",
+				 __func__, fifocnt);
 		}
 		outw(config | IRCFG_ENTX, iobase+VLSI_PIO_IRCFG);
 	}
@@ -1109,7 +1110,7 @@ static void vlsi_tx_interrupt(struct net_device *ndev)
 
 	if (netif_queue_stopped(ndev)  &&  !idev->new_baud) {
 		netif_wake_queue(ndev);
-		IRDA_DEBUG(3, "%s: queue awoken\n", __func__);
+		pr_debug("%s: queue awoken\n", __func__);
 	}
 }
 
@@ -1133,7 +1134,7 @@ static void vlsi_unarm_tx(vlsi_irda_dev_t *idev)
 				dev_kfree_skb_any(rd->skb);
 				rd->skb = NULL;
 			}
-			IRDA_DEBUG(0, "%s - dropping tx packet\n", __func__);
+			pr_debug("%s - dropping tx packet\n", __func__);
 			ret = -VLSI_TX_DROP;
 		}
 		else
@@ -1191,8 +1192,8 @@ static int vlsi_start_clock(struct pci_dev *pdev)
 			else			/* was: clksrc=0(auto) */
 				clksrc = 3;	/* fallback to 40MHz XCLK (OB800) */
 
-			IRDA_DEBUG(0, "%s: PLL not locked, fallback to clksrc=%d\n",
-				__func__, clksrc);
+			pr_debug("%s: PLL not locked, fallback to clksrc=%d\n",
+				 __func__, clksrc);
 		}
 		else
 			clksrc = 1;	/* got successful PLL lock */
diff --git a/drivers/net/irda/w83977af_ir.c b/drivers/net/irda/w83977af_ir.c
index 86ca123887d..4e3d2e7c697 100644
--- a/drivers/net/irda/w83977af_ir.c
+++ b/drivers/net/irda/w83977af_ir.c
@@ -110,8 +110,6 @@ static int __init w83977af_init(void)
 {
         int i;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	for (i=0; i < ARRAY_SIZE(dev_self) && io[i] < 2000; i++) {
 		if (w83977af_open(i, io[i], irq[i], dma[i]) == 0)
 			return 0;
@@ -129,8 +127,6 @@ static void __exit w83977af_cleanup(void)
 {
 	int i;
 
-        IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	for (i=0; i < ARRAY_SIZE(dev_self); i++) {
 		if (dev_self[i])
 			w83977af_close(dev_self[i]);
@@ -157,12 +153,10 @@ static int w83977af_open(int i, unsigned int iobase, unsigned int irq,
         struct w83977af_ir *self;
 	int err;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	/* Lock the port that we need */
 	if (!request_region(iobase, CHIP_IO_EXTENT, driver_name)) {
-		IRDA_DEBUG(0, "%s(), can't get iobase of 0x%03x\n",
-		      __func__ , iobase);
+		pr_debug("%s(), can't get iobase of 0x%03x\n",
+			 __func__ , iobase);
 		return -ENODEV;
 	}
 
@@ -269,8 +263,6 @@ static int w83977af_close(struct w83977af_ir *self)
 {
 	int iobase;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
         iobase = self->io.fir_base;
 
 #ifdef CONFIG_USE_W977_PNP
@@ -289,8 +281,8 @@ static int w83977af_close(struct w83977af_ir *self)
 	unregister_netdev(self->netdev);
 
 	/* Release the PORT that this driver is using */
-	IRDA_DEBUG(0 , "%s(), Releasing Region %03x\n", 
-	      __func__ , self->io.fir_base);
+	pr_debug("%s(), Releasing Region %03x\n",
+		 __func__ , self->io.fir_base);
 	release_region(self->io.fir_base, self->io.fir_ext);
 
 	if (self->tx_buff.head)
@@ -312,7 +304,6 @@ static int w83977af_probe(int iobase, int irq, int dma)
 	int i;
   	
  	for (i=0; i < 2; i++) {
-		IRDA_DEBUG( 0, "%s()\n", __func__ );
 #ifdef CONFIG_USE_W977_PNP
  		/* Enter PnP configuration mode */
 		w977_efm_enter(efbase[i]);
@@ -399,7 +390,7 @@ static int w83977af_probe(int iobase, int irq, int dma)
 			return 0;
 		} else {
 			/* Try next extented function register address */
-			IRDA_DEBUG( 0, "%s(), Wrong chip version", __func__ );
+			pr_debug("%s(), Wrong chip version", __func__);
 		}
   	}   	
 	return -1;
@@ -435,19 +426,19 @@ static void w83977af_change_speed(struct w83977af_ir *self, __u32 speed)
 	case 115200: outb(0x01, iobase+ABLL); break;
 	case 576000:
 		ir_mode = HCR_MIR_576;
-		IRDA_DEBUG(0, "%s(), handling baud of 576000\n", __func__ );
+		pr_debug("%s(), handling baud of 576000\n", __func__);
 		break;
 	case 1152000:
 		ir_mode = HCR_MIR_1152;
-		IRDA_DEBUG(0, "%s(), handling baud of 1152000\n", __func__ );
+		pr_debug("%s(), handling baud of 1152000\n", __func__);
 		break;
 	case 4000000:
 		ir_mode = HCR_FIR;
-		IRDA_DEBUG(0, "%s(), handling baud of 4000000\n", __func__ );
+		pr_debug("%s(), handling baud of 4000000\n", __func__);
 		break;
 	default:
 		ir_mode = HCR_FIR;
-		IRDA_DEBUG(0, "%s(), unknown baud rate of %d\n", __func__ , speed);
+		pr_debug("%s(), unknown baud rate of %d\n", __func__ , speed);
 		break;
 	}
 
@@ -498,8 +489,8 @@ static netdev_tx_t w83977af_hard_xmit(struct sk_buff *skb,
 
 	iobase = self->io.fir_base;
 
-	IRDA_DEBUG(4, "%s(%ld), skb->len=%d\n", __func__ , jiffies,
-		   (int) skb->len);
+	pr_debug("%s(%ld), skb->len=%d\n", __func__ , jiffies,
+		 (int)skb->len);
 	
 	/* Lock transmit buffer */
 	netif_stop_queue(dev);
@@ -526,7 +517,7 @@ static netdev_tx_t w83977af_hard_xmit(struct sk_buff *skb,
 		self->tx_buff.len = skb->len;
 		
 		mtt = irda_get_mtt(skb);
-			IRDA_DEBUG(4, "%s(%ld), mtt=%d\n", __func__ , jiffies, mtt);
+		pr_debug("%s(%ld), mtt=%d\n", __func__ , jiffies, mtt);
 			if (mtt)
 				udelay(mtt);
 
@@ -560,7 +551,7 @@ static netdev_tx_t w83977af_hard_xmit(struct sk_buff *skb,
 static void w83977af_dma_write(struct w83977af_ir *self, int iobase)
 {
 	__u8 set;
-        IRDA_DEBUG(4, "%s(), len=%d\n", __func__ , self->tx_buff.len);
+	pr_debug("%s(), len=%d\n", __func__ , self->tx_buff.len);
 
 	/* Save current set */
 	set = inb(iobase+SSR);
@@ -595,19 +586,16 @@ static int w83977af_pio_write(int iobase, __u8 *buf, int len, int fifo_size)
 	int actual = 0;
 	__u8 set;
 	
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	/* Save current bank */
 	set = inb(iobase+SSR);
 
 	switch_bank(iobase, SET0);
 	if (!(inb_p(iobase+USR) & USR_TSRE)) {
-		IRDA_DEBUG(4,
-			   "%s(), warning, FIFO not empty yet!\n", __func__  );
+		pr_debug("%s(), warning, FIFO not empty yet!\n", __func__);
 
 		fifo_size -= 17;
-		IRDA_DEBUG(4, "%s(), %d bytes left in tx fifo\n", 
-			   __func__ , fifo_size);
+		pr_debug("%s(), %d bytes left in tx fifo\n",
+			 __func__ , fifo_size);
 	}
 
 	/* Fill FIFO with current frame */
@@ -616,8 +604,8 @@ static int w83977af_pio_write(int iobase, __u8 *buf, int len, int fifo_size)
 		outb(buf[actual++], iobase+TBR);
 	}
         
-	IRDA_DEBUG(4, "%s(), fifo_size %d ; %d sent of %d\n", 
-		   __func__ , fifo_size, actual, len);
+	pr_debug("%s(), fifo_size %d ; %d sent of %d\n",
+		 __func__ , fifo_size, actual, len);
 
 	/* Restore bank */
 	outb(set, iobase+SSR);
@@ -637,7 +625,7 @@ static void w83977af_dma_xmit_complete(struct w83977af_ir *self)
 	int iobase;
 	__u8 set;
 
-	IRDA_DEBUG(4, "%s(%ld)\n", __func__ , jiffies);
+	pr_debug("%s(%ld)\n", __func__ , jiffies);
 
 	IRDA_ASSERT(self != NULL, return;);
 
@@ -652,7 +640,7 @@ static void w83977af_dma_xmit_complete(struct w83977af_ir *self)
 	
 	/* Check for underrun! */
 	if (inb(iobase+AUDR) & AUDR_UNDR) {
-		IRDA_DEBUG(0, "%s(), Transmit underrun!\n", __func__ );
+		pr_debug("%s(), Transmit underrun!\n", __func__);
 		
 		self->netdev->stats.tx_errors++;
 		self->netdev->stats.tx_fifo_errors++;
@@ -693,7 +681,7 @@ static int w83977af_dma_receive(struct w83977af_ir *self)
 #endif
 	IRDA_ASSERT(self != NULL, return -1;);
 
-	IRDA_DEBUG(4, "%s\n", __func__ );
+	pr_debug("%s\n", __func__);
 
 	iobase= self->io.fir_base;
 
@@ -764,7 +752,7 @@ static int w83977af_dma_receive_complete(struct w83977af_ir *self)
 	__u8 set;
 	__u8 status;
 
-	IRDA_DEBUG(4, "%s\n", __func__ );
+	pr_debug("%s\n", __func__);
 
 	st_fifo = &self->st_fifo;
 
@@ -881,8 +869,6 @@ static void w83977af_pio_receive(struct w83977af_ir *self)
 	__u8 byte = 0x00;
 	int iobase;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	
 	iobase = self->io.fir_base;
@@ -908,7 +894,7 @@ static __u8 w83977af_sir_interrupt(struct w83977af_ir *self, int isr)
 	__u8 set;
 	int iobase;
 
-	IRDA_DEBUG(4, "%s(), isr=%#x\n", __func__ , isr);
+	pr_debug("%s(), isr=%#x\n", __func__ , isr);
 	
 	iobase = self->io.fir_base;
 	/* Transmit FIFO low on data */
@@ -944,8 +930,7 @@ static __u8 w83977af_sir_interrupt(struct w83977af_ir *self, int isr)
 	if (isr & ISR_TXEMP_I) {		
 		/* Check if we need to change the speed? */
 		if (self->new_speed) {
-			IRDA_DEBUG(2,
-				   "%s(), Changing speed!\n", __func__ );
+			pr_debug("%s(), Changing speed!\n", __func__);
 			w83977af_change_speed(self, self->new_speed);
 			self->new_speed = 0;
 		}
@@ -1127,7 +1112,6 @@ static int w83977af_net_open(struct net_device *dev)
 	char hwname[32];
 	__u8 set;
 	
-	IRDA_DEBUG(0, "%s()\n", __func__ );
 	
 	IRDA_ASSERT(dev != NULL, return -1;);
 	self = netdev_priv(dev);
@@ -1190,8 +1174,6 @@ static int w83977af_net_close(struct net_device *dev)
 	int iobase;
 	__u8 set;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(dev != NULL, return -1;);
 	
 	self = netdev_priv(dev);
@@ -1245,7 +1227,7 @@ static int w83977af_net_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 
 	IRDA_ASSERT(self != NULL, return -1;);
 
-	IRDA_DEBUG(2, "%s(), %s, (cmd=0x%X)\n", __func__ , dev->name, cmd);
+	pr_debug("%s(), %s, (cmd=0x%X)\n", __func__ , dev->name, cmd);
 	
 	spin_lock_irqsave(&self->lock, flags);
 
diff --git a/include/net/irda/irda.h b/include/net/irda/irda.h
index 4ff18bdc63d..92c8fb57521 100644
--- a/include/net/irda/irda.h
+++ b/include/net/irda/irda.h
@@ -55,16 +55,6 @@ typedef __u32 magic_t;
 #endif
 
 #ifdef CONFIG_IRDA_DEBUG
-
-extern unsigned int irda_debug;
-
-/* use 0 for production, 1 for verification, >2 for debug */
-#define IRDA_DEBUG_LEVEL 0
-
-#define IRDA_DEBUG(n, args...) \
-do {	if (irda_debug >= (n)) \
-		printk(KERN_DEBUG args); \
-} while (0)
 #define IRDA_ASSERT(expr, func) \
 do { if(!(expr)) { \
 	printk( "Assertion failed! %s:%s:%d %s\n", \
@@ -72,7 +62,6 @@ do { if(!(expr)) { \
 	func } } while (0)
 #define IRDA_ASSERT_LABEL(label)	label
 #else
-#define IRDA_DEBUG(n, args...) do { } while (0)
 #define IRDA_ASSERT(expr, func) do { (void)(expr); } while (0)
 #define IRDA_ASSERT_LABEL(label)
 #endif /* CONFIG_IRDA_DEBUG */
diff --git a/include/net/irda/irlap.h b/include/net/irda/irlap.h
index fb4b76d5d7f..6f23e820618 100644
--- a/include/net/irda/irlap.h
+++ b/include/net/irda/irlap.h
@@ -303,7 +303,7 @@ static inline void irlap_next_state(struct irlap_cb *self, IRLAP_STATE state)
 	if (!self || self->magic != LAP_MAGIC)
 		return;
 
-	IRDA_DEBUG(4, "next LAP state = %s\n", irlap_state[state]);
+		pr_debug("next LAP state = %s\n", irlap_state[state]);
 	*/
 	self->state = state;
 }
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 4b04ae06b28..31f70a8c781 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -84,14 +84,12 @@ static int irda_data_indication(void *instance, void *sap, struct sk_buff *skb)
 	struct sock *sk;
 	int err;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	self = instance;
 	sk = instance;
 
 	err = sock_queue_rcv_skb(sk, skb);
 	if (err) {
-		IRDA_DEBUG(1, "%s(), error: no more mem!\n", __func__);
+		pr_debug("%s(), error: no more mem!\n", __func__);
 		self->rx_flow = FLOW_STOP;
 
 		/* When we return error, TTP will need to requeue the skb */
@@ -115,7 +113,7 @@ static void irda_disconnect_indication(void *instance, void *sap,
 
 	self = instance;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	/* Don't care about it, but let's not leak it */
 	if(skb)
@@ -123,8 +121,8 @@ static void irda_disconnect_indication(void *instance, void *sap,
 
 	sk = instance;
 	if (sk == NULL) {
-		IRDA_DEBUG(0, "%s(%p) : BUG : sk is NULL\n",
-			   __func__, self);
+		pr_debug("%s(%p) : BUG : sk is NULL\n",
+			 __func__, self);
 		return;
 	}
 
@@ -180,7 +178,7 @@ static void irda_connect_confirm(void *instance, void *sap,
 
 	self = instance;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	sk = instance;
 	if (sk == NULL) {
@@ -219,8 +217,8 @@ static void irda_connect_confirm(void *instance, void *sap,
 		self->max_data_size = irttp_get_max_seg_size(self->tsap);
 	}
 
-	IRDA_DEBUG(2, "%s(), max_data_size=%d\n", __func__,
-		   self->max_data_size);
+	pr_debug("%s(), max_data_size=%d\n", __func__,
+		 self->max_data_size);
 
 	memcpy(&self->qos_tx, qos, sizeof(struct qos_info));
 
@@ -244,7 +242,7 @@ static void irda_connect_indication(void *instance, void *sap,
 
 	self = instance;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	sk = instance;
 	if (sk == NULL) {
@@ -282,8 +280,8 @@ static void irda_connect_indication(void *instance, void *sap,
 		self->max_data_size = irttp_get_max_seg_size(self->tsap);
 	}
 
-	IRDA_DEBUG(2, "%s(), max_data_size=%d\n", __func__,
-		   self->max_data_size);
+	pr_debug("%s(), max_data_size=%d\n", __func__,
+		 self->max_data_size);
 
 	memcpy(&self->qos_tx, qos, sizeof(struct qos_info));
 
@@ -301,12 +299,10 @@ static void irda_connect_response(struct irda_sock *self)
 {
 	struct sk_buff *skb;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	skb = alloc_skb(TTP_MAX_HEADER + TTP_SAR_HEADER, GFP_KERNEL);
 	if (skb == NULL) {
-		IRDA_DEBUG(0, "%s() Unable to allocate sk_buff!\n",
-			   __func__);
+		pr_debug("%s() Unable to allocate sk_buff!\n",
+			 __func__);
 		return;
 	}
 
@@ -327,26 +323,24 @@ static void irda_flow_indication(void *instance, void *sap, LOCAL_FLOW flow)
 	struct irda_sock *self;
 	struct sock *sk;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	self = instance;
 	sk = instance;
 	BUG_ON(sk == NULL);
 
 	switch (flow) {
 	case FLOW_STOP:
-		IRDA_DEBUG(1, "%s(), IrTTP wants us to slow down\n",
-			   __func__);
+		pr_debug("%s(), IrTTP wants us to slow down\n",
+			 __func__);
 		self->tx_flow = flow;
 		break;
 	case FLOW_START:
 		self->tx_flow = flow;
-		IRDA_DEBUG(1, "%s(), IrTTP wants us to start again\n",
-			   __func__);
+		pr_debug("%s(), IrTTP wants us to start again\n",
+			 __func__);
 		wake_up_interruptible(sk_sleep(sk));
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown flow command!\n", __func__);
+		pr_debug("%s(), Unknown flow command!\n", __func__);
 		/* Unknown flow command, better stop */
 		self->tx_flow = flow;
 		break;
@@ -372,7 +366,7 @@ static void irda_getvalue_confirm(int result, __u16 obj_id,
 		return;
 	}
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	/* We probably don't need to make any more queries */
 	iriap_close(self->iriap);
@@ -380,8 +374,8 @@ static void irda_getvalue_confirm(int result, __u16 obj_id,
 
 	/* Check if request succeeded */
 	if (result != IAS_SUCCESS) {
-		IRDA_DEBUG(1, "%s(), IAS query failed! (%d)\n", __func__,
-			   result);
+		pr_debug("%s(), IAS query failed! (%d)\n", __func__,
+			 result);
 
 		self->errno = result;	/* We really need it later */
 
@@ -413,8 +407,6 @@ static void irda_selective_discovery_indication(discinfo_t *discovery,
 {
 	struct irda_sock *self;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	self = priv;
 	if (!self) {
 		net_warn_ratelimited("%s: lost myself!\n", __func__);
@@ -440,8 +432,6 @@ static void irda_discovery_timeout(u_long priv)
 {
 	struct irda_sock *self;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	self = (struct irda_sock *) priv;
 	BUG_ON(self == NULL);
 
@@ -465,7 +455,7 @@ static int irda_open_tsap(struct irda_sock *self, __u8 tsap_sel, char *name)
 	notify_t notify;
 
 	if (self->tsap) {
-		IRDA_DEBUG(0, "%s: busy!\n", __func__);
+		pr_debug("%s: busy!\n", __func__);
 		return -EBUSY;
 	}
 
@@ -483,8 +473,8 @@ static int irda_open_tsap(struct irda_sock *self, __u8 tsap_sel, char *name)
 	self->tsap = irttp_open_tsap(tsap_sel, DEFAULT_INITIAL_CREDIT,
 				     &notify);
 	if (self->tsap == NULL) {
-		IRDA_DEBUG(0, "%s(), Unable to allocate TSAP!\n",
-			   __func__);
+		pr_debug("%s(), Unable to allocate TSAP!\n",
+			 __func__);
 		return -ENOMEM;
 	}
 	/* Remember which TSAP selector we actually got */
@@ -517,7 +507,7 @@ static int irda_open_lsap(struct irda_sock *self, int pid)
 
 	self->lsap = irlmp_open_lsap(LSAP_CONNLESS, &notify, pid);
 	if (self->lsap == NULL) {
-		IRDA_DEBUG( 0, "%s(), Unable to allocate LSAP!\n", __func__);
+		pr_debug("%s(), Unable to allocate LSAP!\n", __func__);
 		return -ENOMEM;
 	}
 
@@ -538,7 +528,7 @@ static int irda_open_lsap(struct irda_sock *self, int pid)
  */
 static int irda_find_lsap_sel(struct irda_sock *self, char *name)
 {
-	IRDA_DEBUG(2, "%s(%p, %s)\n", __func__, self, name);
+	pr_debug("%s(%p, %s)\n", __func__, self, name);
 
 	if (self->iriap) {
 		net_warn_ratelimited("%s(): busy with a previous query\n",
@@ -577,8 +567,8 @@ static int irda_find_lsap_sel(struct irda_sock *self, char *name)
 	/* Get the remote TSAP selector */
 	switch (self->ias_result->type) {
 	case IAS_INTEGER:
-		IRDA_DEBUG(4, "%s() int=%d\n",
-			   __func__, self->ias_result->t.integer);
+		pr_debug("%s() int=%d\n",
+			 __func__, self->ias_result->t.integer);
 
 		if (self->ias_result->t.integer != -1)
 			self->dtsap_sel = self->ias_result->t.integer;
@@ -587,7 +577,7 @@ static int irda_find_lsap_sel(struct irda_sock *self, char *name)
 		break;
 	default:
 		self->dtsap_sel = 0;
-		IRDA_DEBUG(0, "%s(), bad type!\n", __func__);
+		pr_debug("%s(), bad type!\n", __func__);
 		break;
 	}
 	if (self->ias_result)
@@ -625,7 +615,7 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name)
 	__u32	daddr = DEV_ADDR_ANY;	/* Address we found the service on */
 	__u8	dtsap_sel = 0x0;	/* TSAP associated with it */
 
-	IRDA_DEBUG(2, "%s(), name=%s\n", __func__, name);
+	pr_debug("%s(), name=%s\n", __func__, name);
 
 	/* Ask lmp for the current discovery log
 	 * Note : we have to use irlmp_get_discoveries(), as opposed
@@ -646,8 +636,8 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name)
 		/* Try the address in the log */
 		self->daddr = discoveries[i].daddr;
 		self->saddr = 0x0;
-		IRDA_DEBUG(1, "%s(), trying daddr = %08x\n",
-			   __func__, self->daddr);
+		pr_debug("%s(), trying daddr = %08x\n",
+			 __func__, self->daddr);
 
 		/* Query remote LM-IAS for this service */
 		err = irda_find_lsap_sel(self, name);
@@ -655,8 +645,8 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name)
 		case 0:
 			/* We found the requested service */
 			if(daddr != DEV_ADDR_ANY) {
-				IRDA_DEBUG(1, "%s(), discovered service ''%s'' in two different devices !!!\n",
-					   __func__, name);
+				pr_debug("%s(), discovered service ''%s'' in two different devices !!!\n",
+					 __func__, name);
 				self->daddr = DEV_ADDR_ANY;
 				kfree(discoveries);
 				return -ENOTUNIQ;
@@ -670,7 +660,8 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name)
 			break;
 		default:
 			/* Something bad did happen :-( */
-			IRDA_DEBUG(0, "%s(), unexpected IAS query failure\n", __func__);
+			pr_debug("%s(), unexpected IAS query failure\n",
+				 __func__);
 			self->daddr = DEV_ADDR_ANY;
 			kfree(discoveries);
 			return -EHOSTUNREACH;
@@ -681,8 +672,8 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name)
 
 	/* Check out what we found */
 	if(daddr == DEV_ADDR_ANY) {
-		IRDA_DEBUG(1, "%s(), cannot discover service ''%s'' in any device !!!\n",
-			   __func__, name);
+		pr_debug("%s(), cannot discover service ''%s'' in any device !!!\n",
+			 __func__, name);
 		self->daddr = DEV_ADDR_ANY;
 		return -EADDRNOTAVAIL;
 	}
@@ -692,8 +683,8 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name)
 	self->saddr = 0x0;
 	self->dtsap_sel = dtsap_sel;
 
-	IRDA_DEBUG(1, "%s(), discovered requested service ''%s'' at address %08x\n",
-		   __func__, name, self->daddr);
+	pr_debug("%s(), discovered requested service ''%s'' at address %08x\n",
+		 __func__, name, self->daddr);
 
 	return 0;
 }
@@ -725,8 +716,8 @@ static int irda_getname(struct socket *sock, struct sockaddr *uaddr,
 		saddr.sir_addr = self->saddr;
 	}
 
-	IRDA_DEBUG(1, "%s(), tsap_sel = %#x\n", __func__, saddr.sir_lsap_sel);
-	IRDA_DEBUG(1, "%s(), addr = %08x\n", __func__, saddr.sir_addr);
+	pr_debug("%s(), tsap_sel = %#x\n", __func__, saddr.sir_lsap_sel);
+	pr_debug("%s(), addr = %08x\n", __func__, saddr.sir_addr);
 
 	/* uaddr_len come to us uninitialised */
 	*uaddr_len = sizeof (struct sockaddr_irda);
@@ -746,8 +737,6 @@ static int irda_listen(struct socket *sock, int backlog)
 	struct sock *sk = sock->sk;
 	int err = -EOPNOTSUPP;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	lock_sock(sk);
 
 	if ((sk->sk_type != SOCK_STREAM) && (sk->sk_type != SOCK_SEQPACKET) &&
@@ -779,7 +768,7 @@ static int irda_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct irda_sock *self = irda_sk(sk);
 	int err;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	if (addr_len != sizeof(struct sockaddr_irda))
 		return -EINVAL;
@@ -792,7 +781,8 @@ static int irda_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		self->pid = addr->sir_lsap_sel;
 		err = -EOPNOTSUPP;
 		if (self->pid & 0x80) {
-			IRDA_DEBUG(0, "%s(), extension in PID not supp!\n", __func__);
+			pr_debug("%s(), extension in PID not supp!\n",
+				 __func__);
 			goto out;
 		}
 		err = irda_open_lsap(self, self->pid);
@@ -845,8 +835,6 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
 	struct sk_buff *skb;
 	int err;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0);
 	if (err)
 		return err;
@@ -911,7 +899,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
 	new->tsap = irttp_dup(self->tsap, new);
 	err = -EPERM; /* value does not seem to make sense. -arnd */
 	if (!new->tsap) {
-		IRDA_DEBUG(0, "%s(), dup failed!\n", __func__);
+		pr_debug("%s(), dup failed!\n", __func__);
 		kfree_skb(skb);
 		goto out;
 	}
@@ -971,7 +959,7 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
 	struct irda_sock *self = irda_sk(sk);
 	int err;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	lock_sock(sk);
 	/* Don't allow connect for Ultra sockets */
@@ -1007,13 +995,13 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
 		/* Try to find one suitable */
 		err = irda_discover_daddr_and_lsap_sel(self, addr->sir_name);
 		if (err) {
-			IRDA_DEBUG(0, "%s(), auto-connect failed!\n", __func__);
+			pr_debug("%s(), auto-connect failed!\n", __func__);
 			goto out;
 		}
 	} else {
 		/* Use the one provided by the user */
 		self->daddr = addr->sir_addr;
-		IRDA_DEBUG(1, "%s(), daddr = %08x\n", __func__, self->daddr);
+		pr_debug("%s(), daddr = %08x\n", __func__, self->daddr);
 
 		/* If we don't have a valid service name, we assume the
 		 * user want to connect on a specific LSAP. Prevent
@@ -1023,7 +1011,7 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
 			/* Query remote LM-IAS using service name */
 			err = irda_find_lsap_sel(self, addr->sir_name);
 			if (err) {
-				IRDA_DEBUG(0, "%s(), connect failed!\n", __func__);
+				pr_debug("%s(), connect failed!\n", __func__);
 				goto out;
 			}
 		} else {
@@ -1048,7 +1036,7 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
 				    self->saddr, self->daddr, NULL,
 				    self->max_sdu_size_rx, NULL);
 	if (err) {
-		IRDA_DEBUG(0, "%s(), connect failed!\n", __func__);
+		pr_debug("%s(), connect failed!\n", __func__);
 		goto out;
 	}
 
@@ -1100,8 +1088,6 @@ static int irda_create(struct net *net, struct socket *sock, int protocol,
 	struct sock *sk;
 	struct irda_sock *self;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	if (net != &init_net)
 		return -EAFNOSUPPORT;
 
@@ -1121,7 +1107,7 @@ static int irda_create(struct net *net, struct socket *sock, int protocol,
 		return -ENOMEM;
 
 	self = irda_sk(sk);
-	IRDA_DEBUG(2, "%s() : self is %p\n", __func__, self);
+	pr_debug("%s() : self is %p\n", __func__, self);
 
 	init_waitqueue_head(&self->query_wait);
 
@@ -1183,7 +1169,7 @@ static int irda_create(struct net *net, struct socket *sock, int protocol,
  */
 static void irda_destroy_socket(struct irda_sock *self)
 {
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	/* Unregister with IrLMP */
 	irlmp_unregister_client(self->ckey);
@@ -1220,8 +1206,6 @@ static int irda_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	if (sk == NULL)
 		return 0;
 
@@ -1288,7 +1272,7 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock,
 	struct sk_buff *skb;
 	int err = -EPIPE;
 
-	IRDA_DEBUG(4, "%s(), len=%zd\n", __func__, len);
+	pr_debug("%s(), len=%zd\n", __func__, len);
 
 	/* Note : socket.c set MSG_EOR on SEQPACKET sockets */
 	if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_EOR | MSG_CMSG_COMPAT |
@@ -1324,8 +1308,8 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 	/* Check that we don't send out too big frames */
 	if (len > self->max_data_size) {
-		IRDA_DEBUG(2, "%s(), Chopping frame from %zd to %d bytes!\n",
-			   __func__, len, self->max_data_size);
+		pr_debug("%s(), Chopping frame from %zd to %d bytes!\n",
+			 __func__, len, self->max_data_size);
 		len = self->max_data_size;
 	}
 
@@ -1349,7 +1333,7 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock,
 	 */
 	err = irttp_data_request(self->tsap, skb);
 	if (err) {
-		IRDA_DEBUG(0, "%s(), err=%d\n", __func__, err);
+		pr_debug("%s(), err=%d\n", __func__, err);
 		goto out_err;
 	}
 
@@ -1380,8 +1364,6 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock,
 	size_t copied;
 	int err;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 				flags & MSG_DONTWAIT, &err);
 	if (!skb)
@@ -1391,8 +1373,8 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock,
 	copied = skb->len;
 
 	if (copied > size) {
-		IRDA_DEBUG(2, "%s(), Received truncated frame (%zd < %zd)!\n",
-			   __func__, copied, size);
+		pr_debug("%s(), Received truncated frame (%zd < %zd)!\n",
+			 __func__, copied, size);
 		copied = size;
 		msg->msg_flags |= MSG_TRUNC;
 	}
@@ -1408,7 +1390,7 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock,
 	 */
 	if (self->rx_flow == FLOW_STOP) {
 		if ((atomic_read(&sk->sk_rmem_alloc) << 2) <= sk->sk_rcvbuf) {
-			IRDA_DEBUG(2, "%s(), Starting IrTTP\n", __func__);
+			pr_debug("%s(), Starting IrTTP\n", __func__);
 			self->rx_flow = FLOW_START;
 			irttp_flow_request(self->tsap, FLOW_START);
 		}
@@ -1430,8 +1412,6 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
 	int target, err;
 	long timeo;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	if ((err = sock_error(sk)) < 0)
 		return err;
 
@@ -1503,15 +1483,15 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
 
 			/* put the skb back if we didn't use it up.. */
 			if (skb->len) {
-				IRDA_DEBUG(1, "%s(), back on q!\n",
-					   __func__);
+				pr_debug("%s(), back on q!\n",
+					 __func__);
 				skb_queue_head(&sk->sk_receive_queue, skb);
 				break;
 			}
 
 			kfree_skb(skb);
 		} else {
-			IRDA_DEBUG(0, "%s() questionable!?\n", __func__);
+			pr_debug("%s() questionable!?\n", __func__);
 
 			/* put message back and return */
 			skb_queue_head(&sk->sk_receive_queue, skb);
@@ -1527,7 +1507,7 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
 	 */
 	if (self->rx_flow == FLOW_STOP) {
 		if ((atomic_read(&sk->sk_rmem_alloc) << 2) <= sk->sk_rcvbuf) {
-			IRDA_DEBUG(2, "%s(), Starting IrTTP\n", __func__);
+			pr_debug("%s(), Starting IrTTP\n", __func__);
 			self->rx_flow = FLOW_START;
 			irttp_flow_request(self->tsap, FLOW_START);
 		}
@@ -1551,7 +1531,7 @@ static int irda_sendmsg_dgram(struct kiocb *iocb, struct socket *sock,
 	struct sk_buff *skb;
 	int err;
 
-	IRDA_DEBUG(4, "%s(), len=%zd\n", __func__, len);
+	pr_debug("%s(), len=%zd\n", __func__, len);
 
 	if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_CMSG_COMPAT))
 		return -EINVAL;
@@ -1575,9 +1555,8 @@ static int irda_sendmsg_dgram(struct kiocb *iocb, struct socket *sock,
 	 * service, so we have no fragmentation and no coalescence
 	 */
 	if (len > self->max_data_size) {
-		IRDA_DEBUG(0, "%s(), Warning to much data! "
-			   "Chopping frame from %zd to %d bytes!\n",
-			   __func__, len, self->max_data_size);
+		pr_debug("%s(), Warning too much data! Chopping frame from %zd to %d bytes!\n",
+			 __func__, len, self->max_data_size);
 		len = self->max_data_size;
 	}
 
@@ -1590,7 +1569,7 @@ static int irda_sendmsg_dgram(struct kiocb *iocb, struct socket *sock,
 	skb_reserve(skb, self->max_header_size);
 	skb_reset_transport_header(skb);
 
-	IRDA_DEBUG(4, "%s(), appending user data\n", __func__);
+	pr_debug("%s(), appending user data\n", __func__);
 	skb_put(skb, len);
 	err = memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len);
 	if (err) {
@@ -1604,7 +1583,7 @@ static int irda_sendmsg_dgram(struct kiocb *iocb, struct socket *sock,
 	 */
 	err = irttp_udata_request(self->tsap, skb);
 	if (err) {
-		IRDA_DEBUG(0, "%s(), err=%d\n", __func__, err);
+		pr_debug("%s(), err=%d\n", __func__, err);
 		goto out;
 	}
 
@@ -1633,7 +1612,7 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 	struct sk_buff *skb;
 	int err;
 
-	IRDA_DEBUG(4, "%s(), len=%zd\n", __func__, len);
+	pr_debug("%s(), len=%zd\n", __func__, len);
 
 	err = -EINVAL;
 	if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_CMSG_COMPAT))
@@ -1661,7 +1640,8 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 
 		pid = addr->sir_lsap_sel;
 		if (pid & 0x80) {
-			IRDA_DEBUG(0, "%s(), extension in PID not supp!\n", __func__);
+			pr_debug("%s(), extension in PID not supp!\n",
+				 __func__);
 			err = -EOPNOTSUPP;
 			goto out;
 		}
@@ -1670,8 +1650,8 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 		 * port. Jean II */
 		if ((self->lsap == NULL) ||
 		    (sk->sk_state != TCP_ESTABLISHED)) {
-			IRDA_DEBUG(0, "%s(), socket not bound to Ultra PID.\n",
-				   __func__);
+			pr_debug("%s(), socket not bound to Ultra PID.\n",
+				 __func__);
 			err = -ENOTCONN;
 			goto out;
 		}
@@ -1684,9 +1664,8 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 	 * service, so we have no fragmentation and no coalescence
 	 */
 	if (len > self->max_data_size) {
-		IRDA_DEBUG(0, "%s(), Warning to much data! "
-			   "Chopping frame from %zd to %d bytes!\n",
-			   __func__, len, self->max_data_size);
+		pr_debug("%s(), Warning too much data! Chopping frame from %zd to %d bytes!\n",
+			 __func__, len, self->max_data_size);
 		len = self->max_data_size;
 	}
 
@@ -1699,7 +1678,7 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 	skb_reserve(skb, self->max_header_size);
 	skb_reset_transport_header(skb);
 
-	IRDA_DEBUG(4, "%s(), appending user data\n", __func__);
+	pr_debug("%s(), appending user data\n", __func__);
 	skb_put(skb, len);
 	err = memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len);
 	if (err) {
@@ -1710,7 +1689,7 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 	err = irlmp_connless_data_request((bound ? self->lsap : NULL),
 					  skb, pid);
 	if (err)
-		IRDA_DEBUG(0, "%s(), err=%d\n", __func__, err);
+		pr_debug("%s(), err=%d\n", __func__, err);
 out:
 	release_sock(sk);
 	return err ? : len;
@@ -1725,7 +1704,7 @@ static int irda_shutdown(struct socket *sock, int how)
 	struct sock *sk = sock->sk;
 	struct irda_sock *self = irda_sk(sk);
 
-	IRDA_DEBUG(1, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	lock_sock(sk);
 
@@ -1764,8 +1743,6 @@ static unsigned int irda_poll(struct file * file, struct socket *sock,
 	struct irda_sock *self = irda_sk(sk);
 	unsigned int mask;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	poll_wait(file, sk_sleep(sk), wait);
 	mask = 0;
 
@@ -1773,13 +1750,13 @@ static unsigned int irda_poll(struct file * file, struct socket *sock,
 	if (sk->sk_err)
 		mask |= POLLERR;
 	if (sk->sk_shutdown & RCV_SHUTDOWN) {
-		IRDA_DEBUG(0, "%s(), POLLHUP\n", __func__);
+		pr_debug("%s(), POLLHUP\n", __func__);
 		mask |= POLLHUP;
 	}
 
 	/* Readable? */
 	if (!skb_queue_empty(&sk->sk_receive_queue)) {
-		IRDA_DEBUG(4, "Socket is readable\n");
+		pr_debug("Socket is readable\n");
 		mask |= POLLIN | POLLRDNORM;
 	}
 
@@ -1787,7 +1764,7 @@ static unsigned int irda_poll(struct file * file, struct socket *sock,
 	switch (sk->sk_type) {
 	case SOCK_STREAM:
 		if (sk->sk_state == TCP_CLOSE) {
-			IRDA_DEBUG(0, "%s(), POLLHUP\n", __func__);
+			pr_debug("%s(), POLLHUP\n", __func__);
 			mask |= POLLHUP;
 		}
 
@@ -1825,7 +1802,7 @@ static int irda_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	struct sock *sk = sock->sk;
 	int err;
 
-	IRDA_DEBUG(4, "%s(), cmd=%#x\n", __func__, cmd);
+	pr_debug("%s(), cmd=%#x\n", __func__, cmd);
 
 	err = -EINVAL;
 	switch (cmd) {
@@ -1866,7 +1843,7 @@ static int irda_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	case SIOCSIFMETRIC:
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), doing device ioctl!\n", __func__);
+		pr_debug("%s(), doing device ioctl!\n", __func__);
 		err = -ENOIOCTLCMD;
 	}
 
@@ -1902,7 +1879,7 @@ static int irda_setsockopt(struct socket *sock, int level, int optname,
 	struct ias_attrib *	ias_attr;	/* Attribute in IAS object */
 	int opt, free_ias = 0, err = 0;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	if (level != SOL_IRLMP)
 		return -ENOPROTOOPT;
@@ -2102,7 +2079,8 @@ static int irda_setsockopt(struct socket *sock, int level, int optname,
 
 		/* Check is the user space own the object */
 		if(ias_attr->value->owner != IAS_USER_ATTR) {
-			IRDA_DEBUG(1, "%s(), attempting to delete a kernel attribute\n", __func__);
+			pr_debug("%s(), attempting to delete a kernel attribute\n",
+				 __func__);
 			kfree(ias_opt);
 			err = -EPERM;
 			goto out;
@@ -2125,8 +2103,8 @@ static int irda_setsockopt(struct socket *sock, int level, int optname,
 
 		/* Only possible for a seqpacket service (TTP with SAR) */
 		if (sk->sk_type != SOCK_SEQPACKET) {
-			IRDA_DEBUG(2, "%s(), setting max_sdu_size = %d\n",
-				   __func__, opt);
+			pr_debug("%s(), setting max_sdu_size = %d\n",
+				 __func__, opt);
 			self->max_sdu_size_rx = opt;
 		} else {
 			net_warn_ratelimited("%s: not allowed to set MAXSDUSIZE for this socket type!\n",
@@ -2258,7 +2236,7 @@ static int irda_getsockopt(struct socket *sock, int level, int optname,
 	int err = 0;
 	int offset, total;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	if (level != SOL_IRLMP)
 		return -ENOPROTOOPT;
@@ -2546,7 +2524,8 @@ bed:
 
 		/* Wait until a node is discovered */
 		if (!self->cachedaddr) {
-			IRDA_DEBUG(1, "%s(), nothing discovered yet, going to sleep...\n", __func__);
+			pr_debug("%s(), nothing discovered yet, going to sleep...\n",
+				 __func__);
 
 			/* Set watchdog timer to expire in <val> ms. */
 			self->errno = 0;
@@ -2562,14 +2541,14 @@ bed:
 			/* If watchdog is still activated, kill it! */
 			del_timer(&(self->watchdog));
 
-			IRDA_DEBUG(1, "%s(), ...waking up !\n", __func__);
+			pr_debug("%s(), ...waking up !\n", __func__);
 
 			if (err != 0)
 				goto out;
 		}
 		else
-			IRDA_DEBUG(1, "%s(), found immediately !\n",
-				   __func__);
+			pr_debug("%s(), found immediately !\n",
+				 __func__);
 
 		/* Tell IrLMP that we have been notified */
 		irlmp_update_client(self->ckey, self->mask.word,
diff --git a/net/irda/discovery.c b/net/irda/discovery.c
index 6786e7f193d..364d70aed06 100644
--- a/net/irda/discovery.c
+++ b/net/irda/discovery.c
@@ -112,8 +112,6 @@ void irlmp_add_discovery_log(hashbin_t *cachelog, hashbin_t *log)
 {
 	discovery_t *discovery;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	/*
 	 *  If log is missing this means that IrLAP was unable to perform the
 	 *  discovery, so restart discovery again with just the half timeout
@@ -159,8 +157,6 @@ void irlmp_expire_discoveries(hashbin_t *log, __u32 saddr, int force)
 	int			i = 0;		/* How many we expired */
 
 	IRDA_ASSERT(log != NULL, return;);
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	spin_lock_irqsave(&log->hb_spinlock, flags);
 
 	discovery = (discovery_t *) hashbin_get_first(log);
@@ -232,10 +228,10 @@ void irlmp_dump_discoveries(hashbin_t *log)
 
 	discovery = (discovery_t *) hashbin_get_first(log);
 	while (discovery != NULL) {
-		IRDA_DEBUG(0, "Discovery:\n");
-		IRDA_DEBUG(0, "  daddr=%08x\n", discovery->data.daddr);
-		IRDA_DEBUG(0, "  saddr=%08x\n", discovery->data.saddr);
-		IRDA_DEBUG(0, "  nickname=%s\n", discovery->data.info);
+		pr_debug("Discovery:\n");
+		pr_debug("  daddr=%08x\n", discovery->data.daddr);
+		pr_debug("  saddr=%08x\n", discovery->data.saddr);
+		pr_debug("  nickname=%s\n", discovery->data.info);
 
 		discovery = (discovery_t *) hashbin_get_next(log);
 	}
diff --git a/net/irda/ircomm/ircomm_core.c b/net/irda/ircomm/ircomm_core.c
index b77fe8c8623..3af219545f6 100644
--- a/net/irda/ircomm/ircomm_core.c
+++ b/net/irda/ircomm/ircomm_core.c
@@ -91,8 +91,6 @@ static int __init ircomm_init(void)
 
 static void __exit ircomm_cleanup(void)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	hashbin_delete(ircomm, (FREE_FUNC) __ircomm_close);
 
 #ifdef CONFIG_PROC_FS
@@ -111,8 +109,8 @@ struct ircomm_cb *ircomm_open(notify_t *notify, __u8 service_type, int line)
 	struct ircomm_cb *self = NULL;
 	int ret;
 
-	IRDA_DEBUG(2, "%s(), service_type=0x%02x\n", __func__ ,
-		   service_type);
+	pr_debug("%s(), service_type=0x%02x\n", __func__ ,
+		 service_type);
 
 	IRDA_ASSERT(ircomm != NULL, return NULL;);
 
@@ -155,8 +153,6 @@ EXPORT_SYMBOL(ircomm_open);
  */
 static int __ircomm_close(struct ircomm_cb *self)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* Disconnect link if any */
 	ircomm_do_event(self, IRCOMM_DISCONNECT_REQUEST, NULL, NULL);
 
@@ -191,8 +187,6 @@ int ircomm_close(struct ircomm_cb *self)
 	IRDA_ASSERT(self != NULL, return -EIO;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -EIO;);
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	entry = hashbin_remove(ircomm, self->line, NULL);
 
 	IRDA_ASSERT(entry == self, return -1;);
@@ -216,8 +210,6 @@ int ircomm_connect_request(struct ircomm_cb *self, __u8 dlsap_sel,
 	struct ircomm_info info;
 	int ret;
 
-	IRDA_DEBUG(2 , "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -1;);
 
@@ -243,8 +235,6 @@ EXPORT_SYMBOL(ircomm_connect_request);
 void ircomm_connect_indication(struct ircomm_cb *self, struct sk_buff *skb,
 			       struct ircomm_info *info)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/*
 	 * If there are any data hiding in the control channel, we must
 	 * deliver it first. The side effect is that the control channel
@@ -255,7 +245,7 @@ void ircomm_connect_indication(struct ircomm_cb *self, struct sk_buff *skb,
 						info->qos, info->max_data_size,
 						info->max_header_size, skb);
 	else {
-		IRDA_DEBUG(0, "%s(), missing handler\n", __func__ );
+		pr_debug("%s(), missing handler\n", __func__);
 	}
 }
 
@@ -272,8 +262,6 @@ int ircomm_connect_response(struct ircomm_cb *self, struct sk_buff *userdata)
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -1;);
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	ret = ircomm_do_event(self, IRCOMM_CONNECT_RESPONSE, userdata, NULL);
 
 	return ret;
@@ -290,15 +278,13 @@ EXPORT_SYMBOL(ircomm_connect_response);
 void ircomm_connect_confirm(struct ircomm_cb *self, struct sk_buff *skb,
 			    struct ircomm_info *info)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	if (self->notify.connect_confirm )
 		self->notify.connect_confirm(self->notify.instance,
 					     self, info->qos,
 					     info->max_data_size,
 					     info->max_header_size, skb);
 	else {
-		IRDA_DEBUG(0, "%s(), missing handler\n", __func__ );
+		pr_debug("%s(), missing handler\n", __func__);
 	}
 }
 
@@ -312,8 +298,6 @@ int ircomm_data_request(struct ircomm_cb *self, struct sk_buff *skb)
 {
 	int ret;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -EFAULT;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -EFAULT;);
 	IRDA_ASSERT(skb != NULL, return -EFAULT;);
@@ -333,14 +317,12 @@ EXPORT_SYMBOL(ircomm_data_request);
  */
 void ircomm_data_indication(struct ircomm_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(skb->len > 0, return;);
 
 	if (self->notify.data_indication)
 		self->notify.data_indication(self->notify.instance, self, skb);
 	else {
-		IRDA_DEBUG(0, "%s(), missing handler\n", __func__ );
+		pr_debug("%s(), missing handler\n", __func__);
 	}
 }
 
@@ -365,8 +347,8 @@ void ircomm_process_data(struct ircomm_cb *self, struct sk_buff *skb)
 	 * fine
 	 */
 	if (unlikely(skb->len < (clen + 1))) {
-		IRDA_DEBUG(2, "%s() throwing away illegal frame\n",
-			   __func__ );
+		pr_debug("%s() throwing away illegal frame\n",
+			 __func__);
 		return;
 	}
 
@@ -384,8 +366,8 @@ void ircomm_process_data(struct ircomm_cb *self, struct sk_buff *skb)
 	if (skb->len)
 		ircomm_data_indication(self, skb);
 	else {
-		IRDA_DEBUG(4, "%s(), data was control info only!\n",
-			   __func__ );
+		pr_debug("%s(), data was control info only!\n",
+			 __func__);
 	}
 }
 
@@ -399,8 +381,6 @@ int ircomm_control_request(struct ircomm_cb *self, struct sk_buff *skb)
 {
 	int ret;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -EFAULT;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -EFAULT;);
 	IRDA_ASSERT(skb != NULL, return -EFAULT;);
@@ -421,8 +401,6 @@ EXPORT_SYMBOL(ircomm_control_request);
 static void ircomm_control_indication(struct ircomm_cb *self,
 				      struct sk_buff *skb, int clen)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* Use udata for delivering data on the control channel */
 	if (self->notify.udata_indication) {
 		struct sk_buff *ctrl_skb;
@@ -442,7 +420,7 @@ static void ircomm_control_indication(struct ircomm_cb *self,
 		 * see ircomm_tty_control_indication(). */
 		dev_kfree_skb(ctrl_skb);
 	} else {
-		IRDA_DEBUG(0, "%s(), missing handler\n", __func__ );
+		pr_debug("%s(), missing handler\n", __func__);
 	}
 }
 
@@ -457,8 +435,6 @@ int ircomm_disconnect_request(struct ircomm_cb *self, struct sk_buff *userdata)
 	struct ircomm_info info;
 	int ret;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -1;);
 
@@ -478,15 +454,13 @@ EXPORT_SYMBOL(ircomm_disconnect_request);
 void ircomm_disconnect_indication(struct ircomm_cb *self, struct sk_buff *skb,
 				  struct ircomm_info *info)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(info != NULL, return;);
 
 	if (self->notify.disconnect_indication) {
 		self->notify.disconnect_indication(self->notify.instance, self,
 						   info->reason, skb);
 	} else {
-		IRDA_DEBUG(0, "%s(), missing handler\n", __func__ );
+		pr_debug("%s(), missing handler\n", __func__);
 	}
 }
 
@@ -498,8 +472,6 @@ void ircomm_disconnect_indication(struct ircomm_cb *self, struct sk_buff *skb,
  */
 void ircomm_flow_request(struct ircomm_cb *self, LOCAL_FLOW flow)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 
diff --git a/net/irda/ircomm/ircomm_event.c b/net/irda/ircomm/ircomm_event.c
index b172c652232..0476da24848 100644
--- a/net/irda/ircomm/ircomm_event.c
+++ b/net/irda/ircomm/ircomm_event.c
@@ -106,8 +106,8 @@ static int ircomm_state_idle(struct ircomm_cb *self, IRCOMM_EVENT event,
 		ircomm_connect_indication(self, skb, info);
 		break;
 	default:
-		IRDA_DEBUG(4, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -136,8 +136,8 @@ static int ircomm_state_waiti(struct ircomm_cb *self, IRCOMM_EVENT event,
 		ircomm_disconnect_indication(self, skb, info);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -169,8 +169,8 @@ static int ircomm_state_waitr(struct ircomm_cb *self, IRCOMM_EVENT event,
 		ircomm_disconnect_indication(self, skb, info);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event = %s\n", __func__ ,
-			   ircomm_event[event]);
+		pr_debug("%s(), unknown event = %s\n", __func__ ,
+			 ircomm_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -211,8 +211,8 @@ static int ircomm_state_conn(struct ircomm_cb *self, IRCOMM_EVENT event,
 		ret = self->issue.disconnect_request(self, skb, info);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event = %s\n", __func__ ,
-			   ircomm_event[event]);
+		pr_debug("%s(), unknown event = %s\n", __func__ ,
+			 ircomm_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -227,8 +227,8 @@ static int ircomm_state_conn(struct ircomm_cb *self, IRCOMM_EVENT event,
 int ircomm_do_event(struct ircomm_cb *self, IRCOMM_EVENT event,
 		    struct sk_buff *skb, struct ircomm_info *info)
 {
-	IRDA_DEBUG(4, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_state[self->state], ircomm_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_state[self->state], ircomm_event[event]);
 
 	return (*state[self->state])(self, event, skb, info);
 }
@@ -243,6 +243,6 @@ void ircomm_next_state(struct ircomm_cb *self, IRCOMM_STATE state)
 {
 	self->state = state;
 
-	IRDA_DEBUG(4, "%s: next state=%s, service type=%d\n", __func__ ,
-		   ircomm_state[self->state], self->service_type);
+	pr_debug("%s: next state=%s, service type=%d\n", __func__ ,
+		 ircomm_state[self->state], self->service_type);
 }
diff --git a/net/irda/ircomm/ircomm_lmp.c b/net/irda/ircomm/ircomm_lmp.c
index 05767e3ef0d..e4cc847bb93 100644
--- a/net/irda/ircomm/ircomm_lmp.c
+++ b/net/irda/ircomm/ircomm_lmp.c
@@ -52,8 +52,6 @@ static int ircomm_lmp_connect_request(struct ircomm_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	/* Don't forget to refcount it - should be NULL anyway */
 	if(userdata)
 		skb_get(userdata);
@@ -74,8 +72,6 @@ static int ircomm_lmp_connect_response(struct ircomm_cb *self,
 {
 	struct sk_buff *tx_skb;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	/* Any userdata supplied? */
 	if (userdata == NULL) {
 		tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC);
@@ -107,8 +103,6 @@ static int ircomm_lmp_disconnect_request(struct ircomm_cb *self,
 	struct sk_buff *tx_skb;
 	int ret;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	if (!userdata) {
 		tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC);
 		if (!tx_skb)
@@ -144,13 +138,11 @@ static void ircomm_lmp_flow_control(struct sk_buff *skb)
 
 	cb = (struct irda_skb_cb *) skb->cb;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	line = cb->line;
 
 	self = (struct ircomm_cb *) hashbin_lock_find(ircomm, line, NULL);
 	if (!self) {
-		IRDA_DEBUG(2, "%s(), didn't find myself\n", __func__ );
+		pr_debug("%s(), didn't find myself\n", __func__);
 		return;
 	}
 
@@ -160,7 +152,7 @@ static void ircomm_lmp_flow_control(struct sk_buff *skb)
 	self->pkt_count--;
 
 	if ((self->pkt_count < 2) && (self->flow_status == FLOW_STOP)) {
-		IRDA_DEBUG(2, "%s(), asking TTY to start again!\n", __func__ );
+		pr_debug("%s(), asking TTY to start again!\n", __func__);
 		self->flow_status = FLOW_START;
 		if (self->notify.flow_indication)
 			self->notify.flow_indication(self->notify.instance,
@@ -187,7 +179,7 @@ static int ircomm_lmp_data_request(struct ircomm_cb *self,
 
 	cb->line = self->line;
 
-	IRDA_DEBUG(4, "%s(), sending frame\n", __func__ );
+	pr_debug("%s(), sending frame\n", __func__);
 
 	/* Don't forget to refcount it - see ircomm_tty_do_softint() */
 	skb_get(skb);
@@ -196,7 +188,7 @@ static int ircomm_lmp_data_request(struct ircomm_cb *self,
 	skb->destructor = ircomm_lmp_flow_control;
 
 	if ((self->pkt_count++ > 7) && (self->flow_status == FLOW_START)) {
-		IRDA_DEBUG(2, "%s(), asking TTY to slow down!\n", __func__ );
+		pr_debug("%s(), asking TTY to slow down!\n", __func__);
 		self->flow_status = FLOW_STOP;
 		if (self->notify.flow_indication)
 			self->notify.flow_indication(self->notify.instance,
@@ -222,8 +214,6 @@ static int ircomm_lmp_data_indication(void *instance, void *sap,
 {
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -1;);
 	IRDA_ASSERT(skb != NULL, return -1;);
@@ -252,8 +242,6 @@ static void ircomm_lmp_connect_confirm(void *instance, void *sap,
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 	struct ircomm_info info;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -285,8 +273,6 @@ static void ircomm_lmp_connect_indication(void *instance, void *sap,
 	struct ircomm_cb *self = (struct ircomm_cb *)instance;
 	struct ircomm_info info;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -315,8 +301,6 @@ static void ircomm_lmp_disconnect_indication(void *instance, void *sap,
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 	struct ircomm_info info;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 
@@ -338,8 +322,6 @@ int ircomm_open_lsap(struct ircomm_cb *self)
 {
 	notify_t notify;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	/* Register callbacks */
 	irda_notify_init(&notify);
 	notify.data_indication       = ircomm_lmp_data_indication;
@@ -351,7 +333,7 @@ int ircomm_open_lsap(struct ircomm_cb *self)
 
 	self->lsap = irlmp_open_lsap(LSAP_ANY, &notify, 0);
 	if (!self->lsap) {
-		IRDA_DEBUG(0,"%sfailed to allocate tsap\n", __func__ );
+		pr_debug("%sfailed to allocate tsap\n", __func__);
 		return -1;
 	}
 	self->slsap_sel = self->lsap->slsap_sel;
diff --git a/net/irda/ircomm/ircomm_param.c b/net/irda/ircomm/ircomm_param.c
index c203fbb8cdd..27be782be7e 100644
--- a/net/irda/ircomm/ircomm_param.c
+++ b/net/irda/ircomm/ircomm_param.c
@@ -101,8 +101,6 @@ int ircomm_param_request(struct ircomm_tty_cb *self, __u8 pi, int flush)
 	struct sk_buff *skb;
 	int count;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 
@@ -139,7 +137,7 @@ int ircomm_param_request(struct ircomm_tty_cb *self, __u8 pi, int flush)
 
 	spin_unlock_irqrestore(&self->spinlock, flags);
 
-	IRDA_DEBUG(2, "%s(), skb->len=%d\n", __func__ , skb->len);
+	pr_debug("%s(), skb->len=%d\n", __func__ , skb->len);
 
 	if (flush) {
 		/* ircomm_tty_do_softint will take care of the rest */
@@ -173,12 +171,11 @@ static int ircomm_param_service_type(void *instance, irda_param_t *param,
 	/* Find all common service types */
 	service_type &= self->service_type;
 	if (!service_type) {
-		IRDA_DEBUG(2,
-			   "%s(), No common service type to use!\n", __func__ );
+		pr_debug("%s(), No common service type to use!\n", __func__);
 		return -1;
 	}
-	IRDA_DEBUG(0, "%s(), services in common=%02x\n", __func__ ,
-		   service_type);
+	pr_debug("%s(), services in common=%02x\n", __func__ ,
+		 service_type);
 
 	/*
 	 * Now choose a preferred service type of those available
@@ -192,8 +189,8 @@ static int ircomm_param_service_type(void *instance, irda_param_t *param,
 	else if (service_type & IRCOMM_3_WIRE_RAW)
 		self->settings.service_type = IRCOMM_3_WIRE_RAW;
 
-	IRDA_DEBUG(0, "%s(), resulting service type=0x%02x\n", __func__ ,
-		   self->settings.service_type);
+	pr_debug("%s(), resulting service type=0x%02x\n", __func__ ,
+		 self->settings.service_type);
 
 	/*
 	 * Now the line is ready for some communication. Check if we are a
@@ -235,8 +232,8 @@ static int ircomm_param_port_type(void *instance, irda_param_t *param, int get)
 	else {
 		self->settings.port_type = (__u8) param->pv.i;
 
-		IRDA_DEBUG(0, "%s(), port type=%d\n", __func__ ,
-			   self->settings.port_type);
+		pr_debug("%s(), port type=%d\n", __func__ ,
+			 self->settings.port_type);
 	}
 	return 0;
 }
@@ -255,9 +252,9 @@ static int ircomm_param_port_name(void *instance, irda_param_t *param, int get)
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 
 	if (get) {
-		IRDA_DEBUG(0, "%s(), not imp!\n", __func__ );
+		pr_debug("%s(), not imp!\n", __func__);
 	} else {
-		IRDA_DEBUG(0, "%s(), port-name=%s\n", __func__ , param->pv.c);
+		pr_debug("%s(), port-name=%s\n", __func__ , param->pv.c);
 		strncpy(self->settings.port_name, param->pv.c, 32);
 	}
 
@@ -282,7 +279,7 @@ static int ircomm_param_data_rate(void *instance, irda_param_t *param, int get)
 	else
 		self->settings.data_rate = param->pv.i;
 
-	IRDA_DEBUG(2, "%s(), data rate = %d\n", __func__ , param->pv.i);
+	pr_debug("%s(), data rate = %d\n", __func__ , param->pv.i);
 
 	return 0;
 }
@@ -328,7 +325,7 @@ static int ircomm_param_flow_control(void *instance, irda_param_t *param,
 	else
 		self->settings.flow_control = (__u8) param->pv.i;
 
-	IRDA_DEBUG(1, "%s(), flow control = 0x%02x\n", __func__ , (__u8) param->pv.i);
+	pr_debug("%s(), flow control = 0x%02x\n", __func__ , (__u8)param->pv.i);
 
 	return 0;
 }
@@ -354,8 +351,8 @@ static int ircomm_param_xon_xoff(void *instance, irda_param_t *param, int get)
 		self->settings.xonxoff[1] = (__u16) param->pv.i >> 8;
 	}
 
-	IRDA_DEBUG(0, "%s(), XON/XOFF = 0x%02x,0x%02x\n", __func__ ,
-		   param->pv.i & 0xff, param->pv.i >> 8);
+	pr_debug("%s(), XON/XOFF = 0x%02x,0x%02x\n", __func__ ,
+		 param->pv.i & 0xff, param->pv.i >> 8);
 
 	return 0;
 }
@@ -381,8 +378,8 @@ static int ircomm_param_enq_ack(void *instance, irda_param_t *param, int get)
 		self->settings.enqack[1] = (__u16) param->pv.i >> 8;
 	}
 
-	IRDA_DEBUG(0, "%s(), ENQ/ACK = 0x%02x,0x%02x\n", __func__ ,
-		   param->pv.i & 0xff, param->pv.i >> 8);
+	pr_debug("%s(), ENQ/ACK = 0x%02x,0x%02x\n", __func__ ,
+		 param->pv.i & 0xff, param->pv.i >> 8);
 
 	return 0;
 }
@@ -396,7 +393,7 @@ static int ircomm_param_enq_ack(void *instance, irda_param_t *param, int get)
 static int ircomm_param_line_status(void *instance, irda_param_t *param,
 				    int get)
 {
-	IRDA_DEBUG(2, "%s(), not impl.\n", __func__ );
+	pr_debug("%s(), not impl.\n", __func__);
 
 	return 0;
 }
@@ -457,7 +454,7 @@ static int ircomm_param_dce(void *instance, irda_param_t *param, int get)
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) instance;
 	__u8 dce;
 
-	IRDA_DEBUG(1, "%s(), dce = 0x%02x\n", __func__ , (__u8) param->pv.i);
+	pr_debug("%s(), dce = 0x%02x\n", __func__ , (__u8)param->pv.i);
 
 	dce = (__u8) param->pv.i;
 
@@ -469,7 +466,7 @@ static int ircomm_param_dce(void *instance, irda_param_t *param, int get)
 	/* Check if any of the settings have changed */
 	if (dce & 0x0f) {
 		if (dce & IRCOMM_DELTA_CTS) {
-			IRDA_DEBUG(2, "%s(), CTS\n", __func__ );
+			pr_debug("%s(), CTS\n", __func__);
 		}
 	}
 
diff --git a/net/irda/ircomm/ircomm_ttp.c b/net/irda/ircomm/ircomm_ttp.c
index abe9a5ab8d3..4b81e093477 100644
--- a/net/irda/ircomm/ircomm_ttp.c
+++ b/net/irda/ircomm/ircomm_ttp.c
@@ -76,8 +76,6 @@ int ircomm_open_tsap(struct ircomm_cb *self)
 {
 	notify_t notify;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	/* Register callbacks */
 	irda_notify_init(&notify);
 	notify.data_indication       = ircomm_ttp_data_indication;
@@ -91,7 +89,7 @@ int ircomm_open_tsap(struct ircomm_cb *self)
 	self->tsap = irttp_open_tsap(LSAP_ANY, DEFAULT_INITIAL_CREDIT,
 				     &notify);
 	if (!self->tsap) {
-		IRDA_DEBUG(0, "%sfailed to allocate tsap\n", __func__ );
+		pr_debug("%sfailed to allocate tsap\n", __func__);
 		return -1;
 	}
 	self->slsap_sel = self->tsap->stsap_sel;
@@ -119,8 +117,6 @@ static int ircomm_ttp_connect_request(struct ircomm_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	/* Don't forget to refcount it - should be NULL anyway */
 	if(userdata)
 		skb_get(userdata);
@@ -143,8 +139,6 @@ static int ircomm_ttp_connect_response(struct ircomm_cb *self,
 {
 	int ret;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	/* Don't forget to refcount it - should be NULL anyway */
 	if(userdata)
 		skb_get(userdata);
@@ -171,7 +165,7 @@ static int ircomm_ttp_data_request(struct ircomm_cb *self,
 
 	IRDA_ASSERT(skb != NULL, return -1;);
 
-	IRDA_DEBUG(2, "%s(), clen=%d\n", __func__ , clen);
+	pr_debug("%s(), clen=%d\n", __func__ , clen);
 
 	/*
 	 * Insert clen field, currently we either send data only, or control
@@ -206,8 +200,6 @@ static int ircomm_ttp_data_indication(void *instance, void *sap,
 {
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -1;);
 	IRDA_ASSERT(skb != NULL, return -1;);
@@ -229,8 +221,6 @@ static void ircomm_ttp_connect_confirm(void *instance, void *sap,
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 	struct ircomm_info info;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -270,8 +260,6 @@ static void ircomm_ttp_connect_indication(void *instance, void *sap,
 	struct ircomm_cb *self = (struct ircomm_cb *)instance;
 	struct ircomm_info info;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -329,8 +317,6 @@ static void ircomm_ttp_disconnect_indication(void *instance, void *sap,
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 	struct ircomm_info info;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 
@@ -354,8 +340,6 @@ static void ircomm_ttp_flow_indication(void *instance, void *sap,
 {
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 
diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c
index 11b0a5ed025..40695b9751c 100644
--- a/net/irda/ircomm/ircomm_tty.c
+++ b/net/irda/ircomm/ircomm_tty.c
@@ -174,8 +174,6 @@ static int __init ircomm_tty_init(void)
 
 static void __exit __ircomm_tty_cleanup(struct ircomm_tty_cb *self)
 {
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -196,8 +194,6 @@ static void __exit ircomm_tty_cleanup(void)
 {
 	int ret;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	ret = tty_unregister_driver(driver);
 	if (ret) {
 		net_err_ratelimited("%s(), failed to unregister driver\n",
@@ -220,14 +216,12 @@ static int ircomm_tty_startup(struct ircomm_tty_cb *self)
 	notify_t notify;
 	int ret = -ENODEV;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 
 	/* Check if already open */
 	if (test_and_set_bit(ASYNCB_INITIALIZED, &self->port.flags)) {
-		IRDA_DEBUG(2, "%s(), already open so break out!\n", __func__ );
+		pr_debug("%s(), already open so break out!\n", __func__);
 		return 0;
 	}
 
@@ -282,8 +276,6 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self,
 	int		do_clocal = 0;
 	unsigned long	flags;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/*
 	 * If non-blocking mode is set, or the port is not enabled,
 	 * then make the check up front and then exit.
@@ -298,12 +290,12 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self,
 		if (tty->termios.c_cflag & CBAUD)
 			tty_port_raise_dtr_rts(port);
 		port->flags |= ASYNC_NORMAL_ACTIVE;
-		IRDA_DEBUG(1, "%s(), O_NONBLOCK requested!\n", __func__ );
+		pr_debug("%s(), O_NONBLOCK requested!\n", __func__);
 		return 0;
 	}
 
 	if (tty->termios.c_cflag & CLOCAL) {
-		IRDA_DEBUG(1, "%s(), doing CLOCAL!\n", __func__ );
+		pr_debug("%s(), doing CLOCAL!\n", __func__);
 		do_clocal = 1;
 	}
 
@@ -317,8 +309,8 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self,
 	retval = 0;
 	add_wait_queue(&port->open_wait, &wait);
 
-	IRDA_DEBUG(2, "%s(%d):block_til_ready before block on %s open_count=%d\n",
-	      __FILE__, __LINE__, tty->driver->name, port->count);
+	pr_debug("%s(%d):block_til_ready before block on %s open_count=%d\n",
+		 __FILE__, __LINE__, tty->driver->name, port->count);
 
 	spin_lock_irqsave(&port->lock, flags);
 	port->count--;
@@ -355,8 +347,8 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self,
 			break;
 		}
 
-		IRDA_DEBUG(1, "%s(%d):block_til_ready blocking on %s open_count=%d\n",
-		      __FILE__, __LINE__, tty->driver->name, port->count);
+		pr_debug("%s(%d):block_til_ready blocking on %s open_count=%d\n",
+			 __FILE__, __LINE__, tty->driver->name, port->count);
 
 		schedule();
 	}
@@ -370,8 +362,8 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self,
 	port->blocked_open--;
 	spin_unlock_irqrestore(&port->lock, flags);
 
-	IRDA_DEBUG(1, "%s(%d):block_til_ready after blocking on %s open_count=%d\n",
-	      __FILE__, __LINE__, tty->driver->name, port->count);
+	pr_debug("%s(%d):block_til_ready after blocking on %s open_count=%d\n",
+		 __FILE__, __LINE__, tty->driver->name, port->count);
 
 	if (!retval)
 		port->flags |= ASYNC_NORMAL_ACTIVE;
@@ -439,16 +431,14 @@ static int ircomm_tty_open(struct tty_struct *tty, struct file *filp)
 	unsigned long	flags;
 	int ret;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* ++ is not atomic, so this should be protected - Jean II */
 	spin_lock_irqsave(&self->port.lock, flags);
 	self->port.count++;
 	spin_unlock_irqrestore(&self->port.lock, flags);
 	tty_port_tty_set(&self->port, tty);
 
-	IRDA_DEBUG(1, "%s(), %s%d, count = %d\n", __func__ , tty->driver->name,
-		   self->line, self->port.count);
+	pr_debug("%s(), %s%d, count = %d\n", __func__ , tty->driver->name,
+		 self->line, self->port.count);
 
 	/* Not really used by us, but lets do it anyway */
 	self->port.low_latency = (self->port.flags & ASYNC_LOW_LATENCY) ? 1 : 0;
@@ -487,9 +477,9 @@ static int ircomm_tty_open(struct tty_struct *tty, struct file *filp)
 		self->settings.service_type = IRCOMM_9_WIRE; /* 9 wire as default */
 		/* Jan Kiszka -> add DSR/RI -> Conform to IrCOMM spec */
 		self->settings.dce = IRCOMM_CTS | IRCOMM_CD | IRCOMM_DSR | IRCOMM_RI; /* Default line settings */
-		IRDA_DEBUG(2, "%s(), IrCOMM device\n", __func__ );
+		pr_debug("%s(), IrCOMM device\n", __func__);
 	} else {
-		IRDA_DEBUG(2, "%s(), IrLPT device\n", __func__ );
+		pr_debug("%s(), IrLPT device\n", __func__);
 		self->service_type = IRCOMM_3_WIRE_RAW;
 		self->settings.service_type = IRCOMM_3_WIRE_RAW; /* Default */
 	}
@@ -500,9 +490,8 @@ static int ircomm_tty_open(struct tty_struct *tty, struct file *filp)
 
 	ret = ircomm_tty_block_til_ready(self, tty, filp);
 	if (ret) {
-		IRDA_DEBUG(2,
-		      "%s(), returning after block_til_ready with %d\n", __func__ ,
-		      ret);
+		pr_debug("%s(), returning after block_til_ready with %d\n",
+			 __func__, ret);
 
 		return ret;
 	}
@@ -520,8 +509,6 @@ static void ircomm_tty_close(struct tty_struct *tty, struct file *filp)
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 	struct tty_port *port = &self->port;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -571,8 +558,6 @@ static void ircomm_tty_do_softint(struct work_struct *work)
 	unsigned long flags;
 	struct sk_buff *skb, *ctrl_skb;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (!self || self->magic != IRCOMM_TTY_MAGIC)
 		return;
 
@@ -638,8 +623,8 @@ static int ircomm_tty_write(struct tty_struct *tty,
 	int len = 0;
 	int size;
 
-	IRDA_DEBUG(2, "%s(), count=%d, hw_stopped=%d\n", __func__ , count,
-		   tty->hw_stopped);
+	pr_debug("%s(), count=%d, hw_stopped=%d\n", __func__ , count,
+		 tty->hw_stopped);
 
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
@@ -661,7 +646,7 @@ static int ircomm_tty_write(struct tty_struct *tty,
 	 * we don't mess up the original "safe skb" (see tx_data_size).
 	 * Jean II */
 	if (self->max_header_size == IRCOMM_TTY_HDR_UNINITIALISED) {
-		IRDA_DEBUG(1, "%s() : not initialised\n", __func__);
+		pr_debug("%s() : not initialised\n", __func__);
 #ifdef IRCOMM_NO_TX_BEFORE_INIT
 		/* We didn't consume anything, TTY will retry */
 		return 0;
@@ -790,7 +775,7 @@ static int ircomm_tty_write_room(struct tty_struct *tty)
 			ret = self->max_data_size;
 		spin_unlock_irqrestore(&self->spinlock, flags);
 	}
-	IRDA_DEBUG(2, "%s(), ret=%d\n", __func__ , ret);
+	pr_debug("%s(), ret=%d\n", __func__ , ret);
 
 	return ret;
 }
@@ -807,8 +792,6 @@ static void ircomm_tty_wait_until_sent(struct tty_struct *tty, int timeout)
 	unsigned long orig_jiffies, poll_time;
 	unsigned long flags;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -842,8 +825,6 @@ static void ircomm_tty_throttle(struct tty_struct *tty)
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -873,8 +854,6 @@ static void ircomm_tty_unthrottle(struct tty_struct *tty)
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -888,7 +867,7 @@ static void ircomm_tty_unthrottle(struct tty_struct *tty)
 		self->settings.dte |= (IRCOMM_RTS|IRCOMM_DELTA_RTS);
 
 		ircomm_param_request(self, IRCOMM_DTE, TRUE);
-		IRDA_DEBUG(1, "%s(), FLOW_START\n", __func__ );
+		pr_debug("%s(), FLOW_START\n", __func__);
 	}
 	ircomm_flow_request(self->ircomm, FLOW_START);
 }
@@ -925,8 +904,6 @@ static void ircomm_tty_shutdown(struct ircomm_tty_cb *self)
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	if (!test_and_clear_bit(ASYNCB_INITIALIZED, &self->port.flags))
 		return;
 
@@ -969,8 +946,6 @@ static void ircomm_tty_hangup(struct tty_struct *tty)
 	struct tty_port *port = &self->port;
 	unsigned long	flags;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -998,7 +973,7 @@ static void ircomm_tty_hangup(struct tty_struct *tty)
  */
 static void ircomm_tty_send_xchar(struct tty_struct *tty, char ch)
 {
-	IRDA_DEBUG(0, "%s(), not impl\n", __func__ );
+	pr_debug("%s(), not impl\n", __func__);
 }
 
 /*
@@ -1042,8 +1017,6 @@ void ircomm_tty_check_modem_status(struct ircomm_tty_cb *self)
 	struct tty_struct *tty;
 	int status;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -1055,15 +1028,13 @@ void ircomm_tty_check_modem_status(struct ircomm_tty_cb *self)
 		/*wake_up_interruptible(&self->delta_msr_wait);*/
 	}
 	if ((self->port.flags & ASYNC_CHECK_CD) && (status & IRCOMM_DELTA_CD)) {
-		IRDA_DEBUG(2,
-			   "%s(), ircomm%d CD now %s...\n", __func__ , self->line,
-			   (status & IRCOMM_CD) ? "on" : "off");
+		pr_debug("%s(), ircomm%d CD now %s...\n", __func__ , self->line,
+			 (status & IRCOMM_CD) ? "on" : "off");
 
 		if (status & IRCOMM_CD) {
 			wake_up_interruptible(&self->port.open_wait);
 		} else {
-			IRDA_DEBUG(2,
-				   "%s(), Doing serial hangup..\n", __func__ );
+			pr_debug("%s(), Doing serial hangup..\n", __func__);
 			if (tty)
 				tty_hangup(tty);
 
@@ -1074,8 +1045,7 @@ void ircomm_tty_check_modem_status(struct ircomm_tty_cb *self)
 	if (tty && tty_port_cts_enabled(&self->port)) {
 		if (tty->hw_stopped) {
 			if (status & IRCOMM_CTS) {
-				IRDA_DEBUG(2,
-					   "%s(), CTS tx start...\n", __func__ );
+				pr_debug("%s(), CTS tx start...\n", __func__);
 				tty->hw_stopped = 0;
 
 				/* Wake up processes blocked on open */
@@ -1086,8 +1056,7 @@ void ircomm_tty_check_modem_status(struct ircomm_tty_cb *self)
 			}
 		} else {
 			if (!(status & IRCOMM_CTS)) {
-				IRDA_DEBUG(2,
-					   "%s(), CTS tx stop...\n", __func__ );
+				pr_debug("%s(), CTS tx stop...\n", __func__);
 				tty->hw_stopped = 1;
 			}
 		}
@@ -1108,15 +1077,13 @@ static int ircomm_tty_data_indication(void *instance, void *sap,
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) instance;
 	struct tty_struct *tty;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 	IRDA_ASSERT(skb != NULL, return -1;);
 
 	tty = tty_port_tty_get(&self->port);
 	if (!tty) {
-		IRDA_DEBUG(0, "%s(), no tty!\n", __func__ );
+		pr_debug("%s(), no tty!\n", __func__);
 		return 0;
 	}
 
@@ -1127,7 +1094,7 @@ static int ircomm_tty_data_indication(void *instance, void *sap,
 	 * params, we can just as well declare the hardware for running.
 	 */
 	if (tty->hw_stopped && (self->flow == FLOW_START)) {
-		IRDA_DEBUG(0, "%s(), polling for line settings!\n", __func__ );
+		pr_debug("%s(), polling for line settings!\n", __func__);
 		ircomm_param_request(self, IRCOMM_POLL, TRUE);
 
 		/* We can just as well declare the hardware for running */
@@ -1160,8 +1127,6 @@ static int ircomm_tty_control_indication(void *instance, void *sap,
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) instance;
 	int clen;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 	IRDA_ASSERT(skb != NULL, return -1;);
@@ -1196,7 +1161,7 @@ static void ircomm_tty_flow_indication(void *instance, void *sap,
 
 	switch (cmd) {
 	case FLOW_START:
-		IRDA_DEBUG(2, "%s(), hw start!\n", __func__ );
+		pr_debug("%s(), hw start!\n", __func__);
 		if (tty)
 			tty->hw_stopped = 0;
 
@@ -1205,7 +1170,7 @@ static void ircomm_tty_flow_indication(void *instance, void *sap,
 		break;
 	default:  /* If we get here, something is very wrong, better stop */
 	case FLOW_STOP:
-		IRDA_DEBUG(2, "%s(), hw stopped!\n", __func__ );
+		pr_debug("%s(), hw stopped!\n", __func__);
 		if (tty)
 			tty->hw_stopped = 1;
 		break;
diff --git a/net/irda/ircomm/ircomm_tty_attach.c b/net/irda/ircomm/ircomm_tty_attach.c
index 211904419f6..549ca143f0a 100644
--- a/net/irda/ircomm/ircomm_tty_attach.c
+++ b/net/irda/ircomm/ircomm_tty_attach.c
@@ -130,14 +130,12 @@ int ircomm_tty_attach_cable(struct ircomm_tty_cb *self)
 {
 	struct tty_struct *tty;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 
 	/* Check if somebody has already connected to us */
 	if (ircomm_is_connected(self->ircomm)) {
-		IRDA_DEBUG(0, "%s(), already connected!\n", __func__ );
+		pr_debug("%s(), already connected!\n", __func__);
 		return 0;
 	}
 
@@ -163,8 +161,6 @@ int ircomm_tty_attach_cable(struct ircomm_tty_cb *self)
  */
 void ircomm_tty_detach_cable(struct ircomm_tty_cb *self)
 {
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -212,8 +208,6 @@ static void ircomm_tty_ias_register(struct ircomm_tty_cb *self)
 	__u8 oct_seq[6];
 	__u16 hints;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -313,17 +307,17 @@ int ircomm_tty_send_initial_parameters(struct ircomm_tty_cb *self)
 	 * Set default values, but only if the application for some reason
 	 * haven't set them already
 	 */
-	IRDA_DEBUG(2, "%s(), data-rate = %d\n", __func__ ,
-		   self->settings.data_rate);
+	pr_debug("%s(), data-rate = %d\n", __func__ ,
+		 self->settings.data_rate);
 	if (!self->settings.data_rate)
 		self->settings.data_rate = 9600;
-	IRDA_DEBUG(2, "%s(), data-format = %d\n", __func__ ,
-		   self->settings.data_format);
+	pr_debug("%s(), data-format = %d\n", __func__ ,
+		 self->settings.data_format);
 	if (!self->settings.data_format)
 		self->settings.data_format = IRCOMM_WSIZE_8;  /* 8N1 */
 
-	IRDA_DEBUG(2, "%s(), flow-control = %d\n", __func__ ,
-		   self->settings.flow_control);
+	pr_debug("%s(), flow-control = %d\n", __func__ ,
+		 self->settings.flow_control);
 	/*self->settings.flow_control = IRCOMM_RTS_CTS_IN|IRCOMM_RTS_CTS_OUT;*/
 
 	/* Do not set delta values for the initial parameters */
@@ -367,8 +361,6 @@ static void ircomm_tty_discovery_indication(discinfo_t *discovery,
 	struct ircomm_tty_cb *self;
 	struct ircomm_tty_info info;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* Important note :
 	 * We need to drop all passive discoveries.
 	 * The LSAP management of IrComm is deficient and doesn't deal
@@ -404,8 +396,6 @@ void ircomm_tty_disconnect_indication(void *instance, void *sap,
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) instance;
 	struct tty_struct *tty;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -436,8 +426,6 @@ static void ircomm_tty_getvalue_confirm(int result, __u16 obj_id,
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) priv;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -447,13 +435,13 @@ static void ircomm_tty_getvalue_confirm(int result, __u16 obj_id,
 
 	/* Check if request succeeded */
 	if (result != IAS_SUCCESS) {
-		IRDA_DEBUG(4, "%s(), got NULL value!\n", __func__ );
+		pr_debug("%s(), got NULL value!\n", __func__);
 		return;
 	}
 
 	switch (value->type) {
 	case IAS_OCT_SEQ:
-		IRDA_DEBUG(2, "%s(), got octet sequence\n", __func__ );
+		pr_debug("%s(), got octet sequence\n", __func__);
 
 		irda_param_extract_all(self, value->t.oct_seq, value->len,
 				       &ircomm_param_info);
@@ -463,21 +451,21 @@ static void ircomm_tty_getvalue_confirm(int result, __u16 obj_id,
 		break;
 	case IAS_INTEGER:
 		/* Got LSAP selector */
-		IRDA_DEBUG(2, "%s(), got lsapsel = %d\n", __func__ ,
-			   value->t.integer);
+		pr_debug("%s(), got lsapsel = %d\n", __func__ ,
+			 value->t.integer);
 
 		if (value->t.integer == -1) {
-			IRDA_DEBUG(0, "%s(), invalid value!\n", __func__ );
+			pr_debug("%s(), invalid value!\n", __func__);
 		} else
 			self->dlsap_sel = value->t.integer;
 
 		ircomm_tty_do_event(self, IRCOMM_TTY_GOT_LSAPSEL, NULL, NULL);
 		break;
 	case IAS_MISSING:
-		IRDA_DEBUG(0, "%s(), got IAS_MISSING\n", __func__ );
+		pr_debug("%s(), got IAS_MISSING\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), got unknown type!\n", __func__ );
+		pr_debug("%s(), got unknown type!\n", __func__);
 		break;
 	}
 	irias_delete_value(value);
@@ -497,8 +485,6 @@ void ircomm_tty_connect_confirm(void *instance, void *sap,
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) instance;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -528,8 +514,6 @@ void ircomm_tty_connect_indication(void *instance, void *sap,
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) instance;
 	int clen;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -559,8 +543,6 @@ void ircomm_tty_link_established(struct ircomm_tty_cb *self)
 {
 	struct tty_struct *tty;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -578,10 +560,10 @@ void ircomm_tty_link_established(struct ircomm_tty_cb *self)
 	 */
 	if (tty_port_cts_enabled(&self->port) &&
 			((self->settings.dce & IRCOMM_CTS) == 0)) {
-		IRDA_DEBUG(0, "%s(), waiting for CTS ...\n", __func__ );
+		pr_debug("%s(), waiting for CTS ...\n", __func__);
 		goto put;
 	} else {
-		IRDA_DEBUG(1, "%s(), starting hardware!\n", __func__ );
+		pr_debug("%s(), starting hardware!\n", __func__);
 
 		tty->hw_stopped = 0;
 
@@ -621,8 +603,6 @@ static void ircomm_tty_watchdog_timer_expired(void *data)
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -642,8 +622,8 @@ int ircomm_tty_do_event(struct ircomm_tty_cb *self, IRCOMM_TTY_EVENT event,
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 
-	IRDA_DEBUG(2, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_tty_state[self->state], ircomm_tty_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_tty_state[self->state], ircomm_tty_event[event]);
 
 	return (*state[self->state])(self, event, skb, info);
 }
@@ -660,8 +640,8 @@ static inline void ircomm_tty_next_state(struct ircomm_tty_cb *self, IRCOMM_TTY_
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
-	IRDA_DEBUG(2, "%s: next state=%s, service type=%d\n", __func__ ,
-		   ircomm_tty_state[self->state], self->service_type);
+	pr_debug("%s: next state=%s, service type=%d\n", __func__ ,
+	ircomm_tty_state[self->state], self->service_type);
 	*/
 	self->state = state;
 }
@@ -679,8 +659,8 @@ static int ircomm_tty_state_idle(struct ircomm_tty_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_tty_state[self->state], ircomm_tty_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_tty_state[self->state], ircomm_tty_event[event]);
 	switch (event) {
 	case IRCOMM_TTY_ATTACH_CABLE:
 		/* Try to discover any remote devices */
@@ -723,8 +703,8 @@ static int ircomm_tty_state_idle(struct ircomm_tty_cb *self,
 		ircomm_tty_next_state(self, IRCOMM_TTY_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_tty_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_tty_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -743,8 +723,8 @@ static int ircomm_tty_state_search(struct ircomm_tty_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_tty_state[self->state], ircomm_tty_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_tty_state[self->state], ircomm_tty_event[event]);
 
 	switch (event) {
 	case IRCOMM_TTY_DISCOVERY_INDICATION:
@@ -796,8 +776,8 @@ static int ircomm_tty_state_search(struct ircomm_tty_cb *self,
 		ircomm_tty_next_state(self, IRCOMM_TTY_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_tty_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_tty_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -816,8 +796,8 @@ static int ircomm_tty_state_query_parameters(struct ircomm_tty_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_tty_state[self->state], ircomm_tty_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_tty_state[self->state], ircomm_tty_event[event]);
 
 	switch (event) {
 	case IRCOMM_TTY_GOT_PARAMETERS:
@@ -854,8 +834,8 @@ static int ircomm_tty_state_query_parameters(struct ircomm_tty_cb *self,
 		ircomm_tty_next_state(self, IRCOMM_TTY_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_tty_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_tty_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -874,8 +854,8 @@ static int ircomm_tty_state_query_lsap_sel(struct ircomm_tty_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_tty_state[self->state], ircomm_tty_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_tty_state[self->state], ircomm_tty_event[event]);
 
 	switch (event) {
 	case IRCOMM_TTY_GOT_LSAPSEL:
@@ -903,8 +883,8 @@ static int ircomm_tty_state_query_lsap_sel(struct ircomm_tty_cb *self,
 		ircomm_tty_next_state(self, IRCOMM_TTY_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_tty_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_tty_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -923,8 +903,8 @@ static int ircomm_tty_state_setup(struct ircomm_tty_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_tty_state[self->state], ircomm_tty_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_tty_state[self->state], ircomm_tty_event[event]);
 
 	switch (event) {
 	case IRCOMM_TTY_CONNECT_CONFIRM:
@@ -957,8 +937,8 @@ static int ircomm_tty_state_setup(struct ircomm_tty_cb *self,
 		ircomm_tty_next_state(self, IRCOMM_TTY_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_tty_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_tty_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -995,13 +975,13 @@ static int ircomm_tty_state_ready(struct ircomm_tty_cb *self,
 			self->settings.dce = IRCOMM_DELTA_CD;
 			ircomm_tty_check_modem_status(self);
 		} else {
-			IRDA_DEBUG(0, "%s(), hanging up!\n", __func__ );
+			pr_debug("%s(), hanging up!\n", __func__);
 			tty_port_tty_hangup(&self->port, false);
 		}
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_tty_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_tty_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
diff --git a/net/irda/ircomm/ircomm_tty_ioctl.c b/net/irda/ircomm/ircomm_tty_ioctl.c
index 7eb06e08f8e..75ccdbd0728 100644
--- a/net/irda/ircomm/ircomm_tty_ioctl.c
+++ b/net/irda/ircomm/ircomm_tty_ioctl.c
@@ -56,8 +56,6 @@ static void ircomm_tty_change_speed(struct ircomm_tty_cb *self,
 	unsigned int cflag, cval;
 	int baud;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (!self->ircomm)
 		return;
 
@@ -150,8 +148,6 @@ void ircomm_tty_set_termios(struct tty_struct *tty,
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 	unsigned int cflag = tty->termios.c_cflag;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if ((cflag == old_termios->c_cflag) &&
 	    (RELEVANT_IFLAG(tty->termios.c_iflag) ==
 	     RELEVANT_IFLAG(old_termios->c_iflag)))
@@ -199,8 +195,6 @@ int ircomm_tty_tiocmget(struct tty_struct *tty)
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 	unsigned int result;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (tty->flags & (1 << TTY_IO_ERROR))
 		return -EIO;
 
@@ -224,8 +218,6 @@ int ircomm_tty_tiocmset(struct tty_struct *tty,
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (tty->flags & (1 << TTY_IO_ERROR))
 		return -EIO;
 
@@ -266,8 +258,6 @@ static int ircomm_tty_get_serial_info(struct ircomm_tty_cb *self,
 	if (!retinfo)
 		return -EFAULT;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	memset(&info, 0, sizeof(info));
 	info.line = self->line;
 	info.flags = self->port.flags;
@@ -302,8 +292,6 @@ static int ircomm_tty_set_serial_info(struct ircomm_tty_cb *self,
 	struct serial_struct new_serial;
 	struct ircomm_tty_cb old_state, *state;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	if (copy_from_user(&new_serial,new_info,sizeof(new_serial)))
 		return -EFAULT;
 
@@ -376,8 +364,6 @@ int ircomm_tty_ioctl(struct tty_struct *tty,
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if ((cmd != TIOCGSERIAL) && (cmd != TIOCSSERIAL) &&
 	    (cmd != TIOCSERCONFIG) && (cmd != TIOCSERGSTRUCT) &&
 	    (cmd != TIOCMIWAIT) && (cmd != TIOCGICOUNT)) {
@@ -393,11 +379,11 @@ int ircomm_tty_ioctl(struct tty_struct *tty,
 		ret = ircomm_tty_set_serial_info(self, (struct serial_struct __user *) arg);
 		break;
 	case TIOCMIWAIT:
-		IRDA_DEBUG(0, "(), TIOCMIWAIT, not impl!\n");
+		pr_debug("(), TIOCMIWAIT, not impl!\n");
 		break;
 
 	case TIOCGICOUNT:
-		IRDA_DEBUG(0, "%s(), TIOCGICOUNT not impl!\n", __func__ );
+		pr_debug("%s(), TIOCGICOUNT not impl!\n", __func__);
 #if 0
 		save_flags(flags); cli();
 		cnow = driver->icount;
diff --git a/net/irda/irda_device.c b/net/irda/irda_device.c
index 96788db1dc3..856736656a3 100644
--- a/net/irda/irda_device.c
+++ b/net/irda/irda_device.c
@@ -90,8 +90,6 @@ static void leftover_dongle(void *arg)
 
 void irda_device_cleanup(void)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	hashbin_delete(tasks, (FREE_FUNC) __irda_task_delete);
 
 	hashbin_delete(dongles, leftover_dongle);
@@ -107,7 +105,7 @@ void irda_device_set_media_busy(struct net_device *dev, int status)
 {
 	struct irlap_cb *self;
 
-	IRDA_DEBUG(4, "%s(%s)\n", __func__, status ? "TRUE" : "FALSE");
+	pr_debug("%s(%s)\n", __func__, status ? "TRUE" : "FALSE");
 
 	self = (struct irlap_cb *) dev->atalk_ptr;
 
@@ -127,7 +125,7 @@ void irda_device_set_media_busy(struct net_device *dev, int status)
 			irlap_start_mbusy_timer(self, SMALLBUSY_TIMEOUT);
 		else
 			irlap_start_mbusy_timer(self, MEDIABUSY_TIMEOUT);
-		IRDA_DEBUG( 4, "Media busy!\n");
+		pr_debug("Media busy!\n");
 	} else {
 		self->media_busy = FALSE;
 		irlap_stop_mbusy_timer(self);
@@ -147,8 +145,6 @@ int irda_device_is_receiving(struct net_device *dev)
 	struct if_irda_req req;
 	int ret;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	if (!dev->netdev_ops->ndo_do_ioctl) {
 		net_err_ratelimited("%s: do_ioctl not impl. by device driver\n",
 				    __func__);
@@ -192,8 +188,6 @@ static int irda_task_kick(struct irda_task *task)
 	int count = 0;
 	int timeout;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(task != NULL, return -1;);
 	IRDA_ASSERT(task->magic == IRDA_TASK_MAGIC, return -1;);
 
@@ -241,8 +235,8 @@ static int irda_task_kick(struct irda_task *task)
 				 irda_task_timer_expired);
 		finished = FALSE;
 	} else {
-		IRDA_DEBUG(0, "%s(), not finished, and no timeout!\n",
-			   __func__);
+		pr_debug("%s(), not finished, and no timeout!\n",
+			 __func__);
 		finished = FALSE;
 	}
 
@@ -259,8 +253,6 @@ static void irda_task_timer_expired(void *data)
 {
 	struct irda_task *task;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	task = data;
 
 	irda_task_kick(task);
diff --git a/net/irda/iriap.c b/net/irda/iriap.c
index c2ea3443f66..7a93cdd1ac3 100644
--- a/net/irda/iriap.c
+++ b/net/irda/iriap.c
@@ -145,7 +145,7 @@ int __init iriap_init(void)
 	 */
 	server = iriap_open(LSAP_IAS, IAS_SERVER, NULL, NULL);
 	if (!server) {
-		IRDA_DEBUG(0, "%s(), unable to open server\n", __func__);
+		pr_debug("%s(), unable to open server\n", __func__);
 		return -1;
 	}
 	iriap_register_lsap(server, LSAP_IAS, IAS_SERVER);
@@ -177,8 +177,6 @@ struct iriap_cb *iriap_open(__u8 slsap_sel, int mode, void *priv,
 {
 	struct iriap_cb *self;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	self = kzalloc(sizeof(*self), GFP_ATOMIC);
 	if (!self)
 		return NULL;
@@ -221,8 +219,6 @@ EXPORT_SYMBOL(iriap_open);
  */
 static void __iriap_close(struct iriap_cb *self)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 
@@ -245,8 +241,6 @@ void iriap_close(struct iriap_cb *self)
 {
 	struct iriap_cb *entry;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 
@@ -266,8 +260,6 @@ static int iriap_register_lsap(struct iriap_cb *self, __u8 slsap_sel, int mode)
 {
 	notify_t notify;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	irda_notify_init(&notify);
 	notify.connect_confirm       = iriap_connect_confirm;
 	notify.connect_indication    = iriap_connect_indication;
@@ -302,8 +294,8 @@ static void iriap_disconnect_indication(void *instance, void *sap,
 {
 	struct iriap_cb *self;
 
-	IRDA_DEBUG(4, "%s(), reason=%s [%d]\n", __func__,
-		   irlmp_reason_str(reason), reason);
+	pr_debug("%s(), reason=%s [%d]\n", __func__,
+		 irlmp_reason_str(reason), reason);
 
 	self = instance;
 
@@ -319,7 +311,7 @@ static void iriap_disconnect_indication(void *instance, void *sap,
 		dev_kfree_skb(skb);
 
 	if (self->mode == IAS_CLIENT) {
-		IRDA_DEBUG(4, "%s(), disconnect as client\n", __func__);
+		pr_debug("%s(), disconnect as client\n", __func__);
 
 
 		iriap_do_client_event(self, IAP_LM_DISCONNECT_INDICATION,
@@ -332,7 +324,7 @@ static void iriap_disconnect_indication(void *instance, void *sap,
 		if (self->confirm)
 			self->confirm(IAS_DISCONNECT, 0, NULL, self->priv);
 	} else {
-		IRDA_DEBUG(4, "%s(), disconnect as server\n", __func__);
+		pr_debug("%s(), disconnect as server\n", __func__);
 		iriap_do_server_event(self, IAP_LM_DISCONNECT_INDICATION,
 				      NULL);
 		iriap_close(self);
@@ -346,16 +338,13 @@ static void iriap_disconnect_request(struct iriap_cb *self)
 {
 	struct sk_buff *tx_skb;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 
 	tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC);
 	if (tx_skb == NULL) {
-		IRDA_DEBUG(0,
-			   "%s(), Could not allocate an sk_buff of length %d\n",
-			   __func__, LMP_MAX_HEADER);
+		pr_debug("%s(), Could not allocate an sk_buff of length %d\n",
+			 __func__, LMP_MAX_HEADER);
 		return;
 	}
 
@@ -460,14 +449,14 @@ static void iriap_getvaluebyclass_confirm(struct iriap_cb *self,
 	len = get_unaligned_be16(fp + n);
 	n += 2;
 
-	IRDA_DEBUG(4, "%s(), len=%d\n", __func__, len);
+	pr_debug("%s(), len=%d\n", __func__, len);
 
 	/* Get object ID, MSB first */
 	obj_id = get_unaligned_be16(fp + n);
 	n += 2;
 
 	type = fp[n++];
-	IRDA_DEBUG(4, "%s(), Value type = %d\n", __func__, type);
+	pr_debug("%s(), Value type = %d\n", __func__, type);
 
 	switch (type) {
 	case IAS_INTEGER:
@@ -476,7 +465,7 @@ static void iriap_getvaluebyclass_confirm(struct iriap_cb *self,
 		value = irias_new_integer_value(tmp_cpu32);
 
 		/*  Legal values restricted to 0x01-0x6f, page 15 irttp */
-		IRDA_DEBUG(4, "%s(), lsap=%d\n", __func__, value->t.integer);
+		pr_debug("%s(), lsap=%d\n", __func__, value->t.integer);
 		break;
 	case IAS_STRING:
 		charset = fp[n++];
@@ -495,11 +484,11 @@ static void iriap_getvaluebyclass_confirm(struct iriap_cb *self,
 /*		case CS_ISO_8859_9: */
 /*		case CS_UNICODE: */
 		default:
-			IRDA_DEBUG(0, "%s(), charset [%d] %s, not supported\n",
-				   __func__, charset,
-				   charset < ARRAY_SIZE(ias_charset_types) ?
-					ias_charset_types[charset] :
-					"(unknown)");
+			pr_debug("%s(), charset [%d] %s, not supported\n",
+				 __func__, charset,
+				 charset < ARRAY_SIZE(ias_charset_types) ?
+				 ias_charset_types[charset] :
+				 "(unknown)");
 
 			/* Aborting, close connection! */
 			iriap_disconnect_request(self);
@@ -507,12 +496,12 @@ static void iriap_getvaluebyclass_confirm(struct iriap_cb *self,
 			/* break; */
 		}
 		value_len = fp[n++];
-		IRDA_DEBUG(4, "%s(), strlen=%d\n", __func__, value_len);
+		pr_debug("%s(), strlen=%d\n", __func__, value_len);
 
 		/* Make sure the string is null-terminated */
 		if (n + value_len < skb->len)
 			fp[n + value_len] = 0x00;
-		IRDA_DEBUG(4, "Got string %s\n", fp+n);
+		pr_debug("Got string %s\n", fp+n);
 
 		/* Will truncate to IAS_MAX_STRING bytes */
 		value = irias_new_string_value(fp+n);
@@ -538,7 +527,7 @@ static void iriap_getvaluebyclass_confirm(struct iriap_cb *self,
 	if (self->confirm)
 		self->confirm(IAS_SUCCESS, obj_id, value, self->priv);
 	else {
-		IRDA_DEBUG(0, "%s(), missing handler!\n", __func__);
+		pr_debug("%s(), missing handler!\n", __func__);
 		irias_delete_value(value);
 	}
 }
@@ -560,8 +549,6 @@ static void iriap_getvaluebyclass_response(struct iriap_cb *self,
 	__be16 tmp_be16;
 	__u8 *fp;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 	IRDA_ASSERT(value != NULL, return;);
@@ -622,12 +609,12 @@ static void iriap_getvaluebyclass_response(struct iriap_cb *self,
 		memcpy(fp+n, value->t.oct_seq, value->len); n+=value->len;
 		break;
 	case IAS_MISSING:
-		IRDA_DEBUG( 3, "%s: sending IAS_MISSING\n", __func__);
+		pr_debug("%s: sending IAS_MISSING\n", __func__);
 		skb_put(tx_skb, 1);
 		fp[n++] = value->type;
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), type not implemented!\n", __func__);
+		pr_debug("%s(), type not implemented!\n", __func__);
 		break;
 	}
 	iriap_do_r_connect_event(self, IAP_CALL_RESPONSE, tx_skb);
@@ -654,8 +641,6 @@ static void iriap_getvaluebyclass_indication(struct iriap_cb *self,
 	__u8 *fp;
 	int n;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -677,20 +662,20 @@ static void iriap_getvaluebyclass_indication(struct iriap_cb *self,
 	memcpy(attr, fp+n, attr_len); n+=attr_len;
 	attr[attr_len] = '\0';
 
-	IRDA_DEBUG(4, "LM-IAS: Looking up %s: %s\n", name, attr);
+	pr_debug("LM-IAS: Looking up %s: %s\n", name, attr);
 	obj = irias_find_object(name);
 
 	if (obj == NULL) {
-		IRDA_DEBUG(2, "LM-IAS: Object %s not found\n", name);
+		pr_debug("LM-IAS: Object %s not found\n", name);
 		iriap_getvaluebyclass_response(self, 0x1235, IAS_CLASS_UNKNOWN,
 					       &irias_missing);
 		return;
 	}
-	IRDA_DEBUG(4, "LM-IAS: found %s, id=%d\n", obj->name, obj->id);
+	pr_debug("LM-IAS: found %s, id=%d\n", obj->name, obj->id);
 
 	attrib = irias_find_attrib(obj, attr);
 	if (attrib == NULL) {
-		IRDA_DEBUG(2, "LM-IAS: Attribute %s not found\n", attr);
+		pr_debug("LM-IAS: Attribute %s not found\n", attr);
 		iriap_getvaluebyclass_response(self, obj->id,
 					       IAS_ATTRIB_UNKNOWN,
 					       &irias_missing);
@@ -713,8 +698,6 @@ void iriap_send_ack(struct iriap_cb *self)
 	struct sk_buff *tx_skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 
@@ -744,7 +727,7 @@ void iriap_connect_request(struct iriap_cb *self)
 				    self->saddr, self->daddr,
 				    NULL, NULL);
 	if (ret < 0) {
-		IRDA_DEBUG(0, "%s(), connect failed!\n", __func__);
+		pr_debug("%s(), connect failed!\n", __func__);
 		self->confirm(IAS_DISCONNECT, 0, NULL, self->priv);
 	}
 }
@@ -792,8 +775,6 @@ static void iriap_connect_indication(void *instance, void *sap,
 {
 	struct iriap_cb *self, *new;
 
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	self = instance;
 
 	IRDA_ASSERT(skb != NULL, return;);
@@ -803,14 +784,14 @@ static void iriap_connect_indication(void *instance, void *sap,
 	/* Start new server */
 	new = iriap_open(LSAP_IAS, IAS_SERVER, NULL, NULL);
 	if (!new) {
-		IRDA_DEBUG(0, "%s(), open failed\n", __func__);
+		pr_debug("%s(), open failed\n", __func__);
 		goto out;
 	}
 
 	/* Now attach up the new "socket" */
 	new->lsap = irlmp_dup(self->lsap, new);
 	if (!new->lsap) {
-		IRDA_DEBUG(0, "%s(), dup failed!\n", __func__);
+		pr_debug("%s(), dup failed!\n", __func__);
 		goto out;
 	}
 
@@ -840,8 +821,6 @@ static int iriap_data_indication(void *instance, void *sap,
 	__u8  *frame;
 	__u8  opcode;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	self = instance;
 
 	IRDA_ASSERT(skb != NULL, return 0;);
@@ -852,7 +831,7 @@ static int iriap_data_indication(void *instance, void *sap,
 
 	if (self->mode == IAS_SERVER) {
 		/* Call server */
-		IRDA_DEBUG(4, "%s(), Calling server!\n", __func__);
+		pr_debug("%s(), Calling server!\n", __func__);
 		iriap_do_r_connect_event(self, IAP_RECV_F_LST, skb);
 		goto out;
 	}
@@ -865,7 +844,7 @@ static int iriap_data_indication(void *instance, void *sap,
 
 	/* Check for ack frames since they don't contain any data */
 	if (opcode & IAP_ACK) {
-		IRDA_DEBUG(0, "%s() Got ack frame!\n", __func__);
+		pr_debug("%s() Got ack frame!\n", __func__);
 		goto out;
 	}
 
@@ -873,7 +852,7 @@ static int iriap_data_indication(void *instance, void *sap,
 
 	switch (opcode) {
 	case GET_INFO_BASE:
-		IRDA_DEBUG(0, "IrLMP GetInfoBaseDetails not implemented!\n");
+		pr_debug("IrLMP GetInfoBaseDetails not implemented!\n");
 		break;
 	case GET_VALUE_BY_CLASS:
 		iriap_do_call_event(self, IAP_RECV_F_LST, NULL);
@@ -883,7 +862,7 @@ static int iriap_data_indication(void *instance, void *sap,
 			iriap_getvaluebyclass_confirm(self, skb);
 			break;
 		case IAS_CLASS_UNKNOWN:
-			IRDA_DEBUG(1, "%s(), No such class!\n", __func__);
+			pr_debug("%s(), No such class!\n", __func__);
 			/* Finished, close connection! */
 			iriap_disconnect_request(self);
 
@@ -896,7 +875,7 @@ static int iriap_data_indication(void *instance, void *sap,
 					      self->priv);
 			break;
 		case IAS_ATTRIB_UNKNOWN:
-			IRDA_DEBUG(1, "%s(), No such attribute!\n", __func__);
+			pr_debug("%s(), No such attribute!\n", __func__);
 			/* Finished, close connection! */
 			iriap_disconnect_request(self);
 
@@ -911,8 +890,8 @@ static int iriap_data_indication(void *instance, void *sap,
 		}
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown op-code: %02x\n", __func__,
-			   opcode);
+		pr_debug("%s(), Unknown op-code: %02x\n", __func__,
+			 opcode);
 		break;
 	}
 
@@ -933,8 +912,6 @@ void iriap_call_indication(struct iriap_cb *self, struct sk_buff *skb)
 	__u8 *fp;
 	__u8 opcode;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
diff --git a/net/irda/iriap_event.c b/net/irda/iriap_event.c
index 09de4efc73a..e6098b2e048 100644
--- a/net/irda/iriap_event.c
+++ b/net/irda/iriap_event.c
@@ -187,7 +187,7 @@ static void state_s_disconnect(struct iriap_cb *self, IRIAP_EVENT event,
 	case IAP_LM_DISCONNECT_INDICATION:
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %d\n", __func__, event);
+		pr_debug("%s(), Unknown event %d\n", __func__, event);
 		break;
 	}
 }
@@ -219,7 +219,7 @@ static void state_s_connecting(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_next_client_state(self, S_DISCONNECT);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %d\n", __func__, event);
+		pr_debug("%s(), Unknown event %d\n", __func__, event);
 		break;
 	}
 }
@@ -243,7 +243,7 @@ static void state_s_call(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_next_client_state(self, S_DISCONNECT);
 		break;
 	default:
-		IRDA_DEBUG(0, "state_s_call: Unknown event %d\n", event);
+		pr_debug("state_s_call: Unknown event %d\n", event);
 		break;
 	}
 }
@@ -271,7 +271,7 @@ static void state_s_make_call(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_next_call_state(self, S_OUTSTANDING);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %d\n", __func__, event);
+		pr_debug("%s(), Unknown event %d\n", __func__, event);
 		break;
 	}
 }
@@ -285,7 +285,7 @@ static void state_s_make_call(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_s_calling(struct iriap_cb *self, IRIAP_EVENT event,
 			    struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), Not implemented\n", __func__);
+	pr_debug("%s(), Not implemented\n", __func__);
 }
 
 /*
@@ -307,7 +307,7 @@ static void state_s_outstanding(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_next_call_state(self, S_WAIT_FOR_CALL);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %d\n", __func__, event);
+		pr_debug("%s(), Unknown event %d\n", __func__, event);
 		break;
 	}
 }
@@ -320,7 +320,7 @@ static void state_s_outstanding(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_s_replying(struct iriap_cb *self, IRIAP_EVENT event,
 			     struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), Not implemented\n", __func__);
+	pr_debug("%s(), Not implemented\n", __func__);
 }
 
 /*
@@ -332,7 +332,7 @@ static void state_s_replying(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_s_wait_for_call(struct iriap_cb *self, IRIAP_EVENT event,
 				  struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), Not implemented\n", __func__);
+	pr_debug("%s(), Not implemented\n", __func__);
 }
 
 
@@ -345,7 +345,7 @@ static void state_s_wait_for_call(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_s_wait_active(struct iriap_cb *self, IRIAP_EVENT event,
 				struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), Not implemented\n", __func__);
+	pr_debug("%s(), Not implemented\n", __func__);
 }
 
 /**************************************************************************
@@ -386,7 +386,7 @@ static void state_r_disconnect(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_next_r_connect_state(self, R_RECEIVING);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event %d\n", __func__, event);
+		pr_debug("%s(), unknown event %d\n", __func__, event);
 		break;
 	}
 }
@@ -397,8 +397,6 @@ static void state_r_disconnect(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_r_call(struct iriap_cb *self, IRIAP_EVENT event,
 			 struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	switch (event) {
 	case IAP_LM_DISCONNECT_INDICATION:
 		/* Abort call */
@@ -406,7 +404,7 @@ static void state_r_call(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_next_r_connect_state(self, R_WAITING);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event!\n", __func__);
+		pr_debug("%s(), unknown event!\n", __func__);
 		break;
 	}
 }
@@ -421,13 +419,13 @@ static void state_r_call(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_r_waiting(struct iriap_cb *self, IRIAP_EVENT event,
 			    struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), Not implemented\n", __func__);
+	pr_debug("%s(), Not implemented\n", __func__);
 }
 
 static void state_r_wait_active(struct iriap_cb *self, IRIAP_EVENT event,
 				struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), Not implemented\n", __func__);
+	pr_debug("%s(), Not implemented\n", __func__);
 }
 
 /*
@@ -439,8 +437,6 @@ static void state_r_wait_active(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_r_receiving(struct iriap_cb *self, IRIAP_EVENT event,
 			      struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	switch (event) {
 	case IAP_RECV_F_LST:
 		iriap_next_r_connect_state(self, R_EXECUTE);
@@ -448,7 +444,7 @@ static void state_r_receiving(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_call_indication(self, skb);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event!\n", __func__);
+		pr_debug("%s(), unknown event!\n", __func__);
 		break;
 	}
 }
@@ -462,8 +458,6 @@ static void state_r_receiving(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_r_execute(struct iriap_cb *self, IRIAP_EVENT event,
 			    struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(skb != NULL, return;);
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
@@ -483,7 +477,7 @@ static void state_r_execute(struct iriap_cb *self, IRIAP_EVENT event,
 		irlmp_data_request(self->lsap, skb);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event!\n", __func__);
+		pr_debug("%s(), unknown event!\n", __func__);
 		break;
 	}
 }
@@ -491,7 +485,7 @@ static void state_r_execute(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_r_returning(struct iriap_cb *self, IRIAP_EVENT event,
 			      struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), event=%d\n", __func__, event);
+	pr_debug("%s(), event=%d\n", __func__, event);
 
 	switch (event) {
 	case IAP_RECV_F_LST:
diff --git a/net/irda/irias_object.c b/net/irda/irias_object.c
index cd53692fe8c..53b86d0e163 100644
--- a/net/irda/irias_object.c
+++ b/net/irda/irias_object.c
@@ -48,8 +48,6 @@ struct ias_object *irias_new_object( char *name, int id)
 {
 	struct ias_object *obj;
 
-	IRDA_DEBUG( 4, "%s()\n", __func__);
-
 	obj = kzalloc(sizeof(struct ias_object), GFP_ATOMIC);
 	if (obj == NULL) {
 		net_warn_ratelimited("%s(), Unable to allocate object!\n",
@@ -134,8 +132,8 @@ int irias_delete_object(struct ias_object *obj)
 	/* Remove from list */
 	node = hashbin_remove_this(irias_objects, (irda_queue_t *) obj);
 	if (!node)
-		IRDA_DEBUG( 0, "%s(), object already removed!\n",
-			    __func__);
+		pr_debug("%s(), object already removed!\n",
+			 __func__);
 
 	/* Destroy */
 	__irias_delete_object(obj);
@@ -287,8 +285,8 @@ int irias_object_change_attribute(char *obj_name, char *attrib_name,
 	}
 
 	if ( attrib->value->type != new_value->type) {
-		IRDA_DEBUG( 0, "%s(), changing value type not allowed!\n",
-			    __func__);
+		pr_debug("%s(), changing value type not allowed!\n",
+			 __func__);
 		spin_unlock_irqrestore(&obj->attribs->hb_spinlock, flags);
 		return -1;
 	}
@@ -533,8 +531,6 @@ struct ias_value *irias_new_missing_value(void)
  */
 void irias_delete_value(struct ias_value *value)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(value != NULL, return;);
 
 	switch (value->type) {
@@ -551,7 +547,7 @@ void irias_delete_value(struct ias_value *value)
 		 kfree(value->t.oct_seq);
 		 break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown value type!\n", __func__);
+		pr_debug("%s(), Unknown value type!\n", __func__);
 		break;
 	}
 	kfree(value);
diff --git a/net/irda/irlan/irlan_client.c b/net/irda/irlan/irlan_client.c
index f8eea02843f..c5837a40c78 100644
--- a/net/irda/irlan/irlan_client.c
+++ b/net/irda/irlan/irlan_client.c
@@ -72,8 +72,6 @@ static void irlan_client_kick_timer_expired(void *data)
 {
 	struct irlan_cb *self = (struct irlan_cb *) data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -91,8 +89,6 @@ static void irlan_client_kick_timer_expired(void *data)
 
 static void irlan_client_start_kick_timer(struct irlan_cb *self, int timeout)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	irda_start_timer(&self->client.kick_timer, timeout, (void *) self,
 			 irlan_client_kick_timer_expired);
 }
@@ -105,8 +101,6 @@ static void irlan_client_start_kick_timer(struct irlan_cb *self, int timeout)
  */
 void irlan_client_wakeup(struct irlan_cb *self, __u32 saddr, __u32 daddr)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -117,7 +111,7 @@ void irlan_client_wakeup(struct irlan_cb *self, __u32 saddr, __u32 daddr)
 	if ((self->client.state != IRLAN_IDLE) ||
 	    (self->provider.access_type == ACCESS_DIRECT))
 	{
-			IRDA_DEBUG(0, "%s(), already awake!\n", __func__ );
+		pr_debug("%s(), already awake!\n", __func__);
 			return;
 	}
 
@@ -126,7 +120,7 @@ void irlan_client_wakeup(struct irlan_cb *self, __u32 saddr, __u32 daddr)
 	self->daddr = daddr;
 
 	if (self->disconnect_reason == LM_USER_REQUEST) {
-			IRDA_DEBUG(0, "%s(), still stopped by user\n", __func__ );
+		pr_debug("%s(), still stopped by user\n", __func__);
 			return;
 	}
 
@@ -153,8 +147,6 @@ void irlan_client_discovery_indication(discinfo_t *discovery,
 	struct irlan_cb *self;
 	__u32 saddr, daddr;
 
-	IRDA_DEBUG(1, "%s()\n", __func__ );
-
 	IRDA_ASSERT(discovery != NULL, return;);
 
 	/*
@@ -175,8 +167,8 @@ void irlan_client_discovery_indication(discinfo_t *discovery,
 	if (self) {
 		IRDA_ASSERT(self->magic == IRLAN_MAGIC, goto out;);
 
-		IRDA_DEBUG(1, "%s(), Found instance (%08x)!\n", __func__ ,
-		      daddr);
+		pr_debug("%s(), Found instance (%08x)!\n", __func__ ,
+			 daddr);
 
 		irlan_client_wakeup(self, saddr, daddr);
 	}
@@ -195,8 +187,6 @@ static int irlan_client_ctrl_data_indication(void *instance, void *sap,
 {
 	struct irlan_cb *self;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return -1;);
@@ -206,7 +196,7 @@ static int irlan_client_ctrl_data_indication(void *instance, void *sap,
 	irlan_do_client_event(self, IRLAN_DATA_INDICATION, skb);
 
 	/* Ready for a new command */
-	IRDA_DEBUG(2, "%s(), clearing tx_busy\n", __func__ );
+	pr_debug("%s(), clearing tx_busy\n", __func__);
 	self->client.tx_busy = FALSE;
 
 	/* Check if we have some queued commands waiting to be sent */
@@ -223,7 +213,7 @@ static void irlan_client_ctrl_disconnect_indication(void *instance, void *sap,
 	struct tsap_cb *tsap;
 	struct sk_buff *skb;
 
-	IRDA_DEBUG(4, "%s(), reason=%d\n", __func__ , reason);
+	pr_debug("%s(), reason=%d\n", __func__ , reason);
 
 	self = instance;
 	tsap = sap;
@@ -255,8 +245,6 @@ static void irlan_client_open_ctrl_tsap(struct irlan_cb *self)
 	struct tsap_cb *tsap;
 	notify_t notify;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -275,7 +263,7 @@ static void irlan_client_open_ctrl_tsap(struct irlan_cb *self)
 
 	tsap = irttp_open_tsap(LSAP_ANY, DEFAULT_INITIAL_CREDIT, &notify);
 	if (!tsap) {
-		IRDA_DEBUG(2, "%s(), Got no tsap!\n", __func__ );
+		pr_debug("%s(), Got no tsap!\n", __func__);
 		return;
 	}
 	self->client.tsap_ctrl = tsap;
@@ -295,8 +283,6 @@ static void irlan_client_ctrl_connect_confirm(void *instance, void *sap,
 {
 	struct irlan_cb *self;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return;);
@@ -374,7 +360,7 @@ void irlan_client_parse_response(struct irlan_cb *self, struct sk_buff *skb)
 
 	IRDA_ASSERT(skb != NULL, return;);
 
-	IRDA_DEBUG(4, "%s() skb->len=%d\n", __func__ , (int) skb->len);
+	pr_debug("%s() skb->len=%d\n", __func__ , (int)skb->len);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
@@ -405,7 +391,7 @@ void irlan_client_parse_response(struct irlan_cb *self, struct sk_buff *skb)
 	/* How many parameters? */
 	count = frame[1];
 
-	IRDA_DEBUG(4, "%s(), got %d parameters\n", __func__ , count);
+	pr_debug("%s(), got %d parameters\n", __func__ , count);
 
 	ptr = frame+2;
 
@@ -413,7 +399,7 @@ void irlan_client_parse_response(struct irlan_cb *self, struct sk_buff *skb)
 	for (i=0; i<count;i++) {
 		ret = irlan_extract_param(ptr, name, value, &val_len);
 		if (ret < 0) {
-			IRDA_DEBUG(2, "%s(), IrLAN, Error!\n", __func__ );
+			pr_debug("%s(), IrLAN, Error!\n", __func__);
 			break;
 		}
 		ptr += ret;
@@ -437,7 +423,7 @@ static void irlan_check_response_param(struct irlan_cb *self, char *param,
 	__u8 *bytes;
 	int i;
 
-	IRDA_DEBUG(4, "%s(), parm=%s\n", __func__ , param);
+	pr_debug("%s(), parm=%s\n", __func__ , param);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
@@ -475,13 +461,13 @@ static void irlan_check_response_param(struct irlan_cb *self, char *param,
 		else if (strcmp(value, "HOSTED") == 0)
 			self->client.access_type = ACCESS_HOSTED;
 		else {
-			IRDA_DEBUG(2, "%s(), unknown access type!\n", __func__ );
+			pr_debug("%s(), unknown access type!\n", __func__);
 		}
 	}
 	/* IRLAN version */
 	if (strcmp(param, "IRLAN_VER") == 0) {
-		IRDA_DEBUG(4, "IrLAN version %d.%d\n", (__u8) value[0],
-		      (__u8) value[1]);
+		pr_debug("IrLAN version %d.%d\n", (__u8)value[0],
+			 (__u8)value[1]);
 
 		self->version[0] = value[0];
 		self->version[1] = value[1];
@@ -490,37 +476,37 @@ static void irlan_check_response_param(struct irlan_cb *self, char *param,
 	/* Which remote TSAP to use for data channel */
 	if (strcmp(param, "DATA_CHAN") == 0) {
 		self->dtsap_sel_data = value[0];
-		IRDA_DEBUG(4, "Data TSAP = %02x\n", self->dtsap_sel_data);
+		pr_debug("Data TSAP = %02x\n", self->dtsap_sel_data);
 		return;
 	}
 	if (strcmp(param, "CON_ARB") == 0) {
 		memcpy(&tmp_cpu, value, 2); /* Align value */
 		le16_to_cpus(&tmp_cpu);     /* Convert to host order */
 		self->client.recv_arb_val = tmp_cpu;
-		IRDA_DEBUG(2, "%s(), receive arb val=%d\n", __func__ ,
-			   self->client.recv_arb_val);
+		pr_debug("%s(), receive arb val=%d\n", __func__ ,
+			 self->client.recv_arb_val);
 	}
 	if (strcmp(param, "MAX_FRAME") == 0) {
 		memcpy(&tmp_cpu, value, 2); /* Align value */
 		le16_to_cpus(&tmp_cpu);     /* Convert to host order */
 		self->client.max_frame = tmp_cpu;
-		IRDA_DEBUG(4, "%s(), max frame=%d\n", __func__ ,
-			   self->client.max_frame);
+		pr_debug("%s(), max frame=%d\n", __func__ ,
+			 self->client.max_frame);
 	}
 
 	/* RECONNECT_KEY, in case the link goes down! */
 	if (strcmp(param, "RECONNECT_KEY") == 0) {
-		IRDA_DEBUG(4, "Got reconnect key: ");
+		pr_debug("Got reconnect key: ");
 		/* for (i = 0; i < val_len; i++) */
 /* 			printk("%02x", value[i]); */
 		memcpy(self->client.reconnect_key, value, val_len);
 		self->client.key_len = val_len;
-		IRDA_DEBUG(4, "\n");
+		pr_debug("\n");
 	}
 	/* FILTER_ENTRY, have we got an ethernet address? */
 	if (strcmp(param, "FILTER_ENTRY") == 0) {
 		bytes = value;
-		IRDA_DEBUG(4, "Ethernet address = %pM\n", bytes);
+		pr_debug("Ethernet address = %pM\n", bytes);
 		for (i = 0; i < 6; i++)
 			self->dev->dev_addr[i] = bytes[i];
 	}
@@ -537,8 +523,6 @@ void irlan_client_get_value_confirm(int result, __u16 obj_id,
 {
 	struct irlan_cb *self;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(priv != NULL, return;);
 
 	self = priv;
@@ -550,7 +534,7 @@ void irlan_client_get_value_confirm(int result, __u16 obj_id,
 
 	/* Check if request succeeded */
 	if (result != IAS_SUCCESS) {
-		IRDA_DEBUG(2, "%s(), got NULL value!\n", __func__ );
+		pr_debug("%s(), got NULL value!\n", __func__);
 		irlan_do_client_event(self, IRLAN_IAS_PROVIDER_NOT_AVAIL,
 				      NULL);
 		return;
@@ -568,7 +552,7 @@ void irlan_client_get_value_confirm(int result, __u16 obj_id,
 		irias_delete_value(value);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown type!\n", __func__ );
+		pr_debug("%s(), unknown type!\n", __func__);
 		break;
 	}
 	irlan_do_client_event(self, IRLAN_IAS_PROVIDER_NOT_AVAIL, NULL);
diff --git a/net/irda/irlan/irlan_client_event.c b/net/irda/irlan/irlan_client_event.c
index f9d11bf3815..cc93fabbbb1 100644
--- a/net/irda/irlan/irlan_client_event.c
+++ b/net/irda/irlan/irlan_client_event.c
@@ -92,8 +92,6 @@ void irlan_do_client_event(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_idle(struct irlan_cb *self, IRLAN_EVENT event,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -1;);
 
@@ -114,10 +112,10 @@ static int irlan_client_state_idle(struct irlan_cb *self, IRLAN_EVENT event,
 					      "IrLAN", "IrDA:TinyTP:LsapSel");
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(4, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -136,8 +134,6 @@ static int irlan_client_state_idle(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_query(struct irlan_cb *self, IRLAN_EVENT event,
 				    struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -1;);
 
@@ -154,7 +150,7 @@ static int irlan_client_state_query(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_CONN);
 		break;
 	case IRLAN_IAS_PROVIDER_NOT_AVAIL:
-		IRDA_DEBUG(2, "%s(), IAS_PROVIDER_NOT_AVAIL\n", __func__ );
+		pr_debug("%s(), IAS_PROVIDER_NOT_AVAIL\n", __func__);
 		irlan_next_client_state(self, IRLAN_IDLE);
 
 		/* Give the client a kick! */
@@ -167,10 +163,10 @@ static int irlan_client_state_query(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -189,8 +185,6 @@ static int irlan_client_state_query(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_conn(struct irlan_cb *self, IRLAN_EVENT event,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch (event) {
@@ -204,10 +198,10 @@ static int irlan_client_state_conn(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -224,8 +218,6 @@ static int irlan_client_state_conn(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_info(struct irlan_cb *self, IRLAN_EVENT event,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch (event) {
@@ -244,10 +236,10 @@ static int irlan_client_state_info(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -266,8 +258,6 @@ static int irlan_client_state_info(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_media(struct irlan_cb *self, IRLAN_EVENT event,
 				    struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -281,10 +271,10 @@ static int irlan_client_state_media(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -305,8 +295,6 @@ static int irlan_client_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 {
 	struct qos_info qos;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -344,7 +332,7 @@ static int irlan_client_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 			irlan_next_client_state(self, IRLAN_DATA);
 			break;
 		default:
-			IRDA_DEBUG(2, "%s(), unknown access type!\n", __func__ );
+			pr_debug("%s(), unknown access type!\n", __func__);
 			break;
 		}
 		break;
@@ -353,10 +341,10 @@ static int irlan_client_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 
@@ -376,8 +364,6 @@ static int irlan_client_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_wait(struct irlan_cb *self, IRLAN_EVENT event,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -390,10 +376,10 @@ static int irlan_client_state_wait(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -407,8 +393,6 @@ static int irlan_client_state_arb(struct irlan_cb *self, IRLAN_EVENT event,
 {
 	struct qos_info qos;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -429,7 +413,7 @@ static int irlan_client_state_arb(struct irlan_cb *self, IRLAN_EVENT event,
 		} else if (self->client.recv_arb_val >
 			   self->provider.send_arb_val)
 		{
-			IRDA_DEBUG(2, "%s(), lost the battle :-(\n", __func__ );
+			pr_debug("%s(), lost the battle :-(\n", __func__);
 		}
 		break;
 	case IRLAN_DATA_CONNECT_INDICATION:
@@ -440,10 +424,10 @@ static int irlan_client_state_arb(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -462,8 +446,6 @@ static int irlan_client_state_arb(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_data(struct irlan_cb *self, IRLAN_EVENT event,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -1;);
 
@@ -476,7 +458,7 @@ static int irlan_client_state_data(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -494,8 +476,6 @@ static int irlan_client_state_data(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_close(struct irlan_cb *self, IRLAN_EVENT event,
 				    struct sk_buff *skb)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (skb)
 		dev_kfree_skb(skb);
 
@@ -511,8 +491,6 @@ static int irlan_client_state_close(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_sync(struct irlan_cb *self, IRLAN_EVENT event,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (skb)
 		dev_kfree_skb(skb);
 
diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c
index cc60b4a282a..481bbc2a434 100644
--- a/net/irda/irlan/irlan_common.c
+++ b/net/irda/irlan/irlan_common.c
@@ -118,8 +118,6 @@ static int __init irlan_init(void)
 	struct irlan_cb *new;
 	__u16 hints;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 #ifdef CONFIG_PROC_FS
 	{ struct proc_dir_entry *proc;
 	proc = proc_create("irlan", 0, proc_irda, &irlan_fops);
@@ -130,7 +128,6 @@ static int __init irlan_init(void)
 	}
 #endif /* CONFIG_PROC_FS */
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
 	hints = irlmp_service_to_hint(S_LAN);
 
 	/* Register with IrLMP as a client */
@@ -173,8 +170,6 @@ static void __exit irlan_cleanup(void)
 {
 	struct irlan_cb *self, *next;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	irlmp_unregister_client(ckey);
 	irlmp_unregister_service(skey);
 
@@ -201,8 +196,6 @@ static struct irlan_cb __init *irlan_open(__u32 saddr, __u32 daddr)
 	struct net_device *dev;
 	struct irlan_cb *self;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* Create network device with irlan */
 	dev = alloc_irlandev(eth ? "eth%d" : "irlan%d");
 	if (!dev)
@@ -245,8 +238,8 @@ static struct irlan_cb __init *irlan_open(__u32 saddr, __u32 daddr)
 	irlan_next_provider_state(self, IRLAN_IDLE);
 
 	if (register_netdev(dev)) {
-		IRDA_DEBUG(2, "%s(), register_netdev() failed!\n",
-			   __func__ );
+		pr_debug("%s(), register_netdev() failed!\n",
+			 __func__);
 		self = NULL;
 		free_netdev(dev);
 	} else {
@@ -266,8 +259,6 @@ static struct irlan_cb __init *irlan_open(__u32 saddr, __u32 daddr)
  */
 static void __irlan_close(struct irlan_cb *self)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	ASSERT_RTNL();
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
@@ -314,8 +305,6 @@ static void irlan_connect_indication(void *instance, void *sap,
 	struct irlan_cb *self;
 	struct tsap_cb *tsap;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	self = instance;
 	tsap = sap;
 
@@ -326,7 +315,7 @@ static void irlan_connect_indication(void *instance, void *sap,
 	self->max_sdu_size = max_sdu_size;
 	self->max_header_size = max_header_size;
 
-	IRDA_DEBUG(0, "%s: We are now connected!\n", __func__);
+	pr_debug("%s: We are now connected!\n", __func__);
 
 	del_timer(&self->watchdog_timer);
 
@@ -370,7 +359,7 @@ static void irlan_connect_confirm(void *instance, void *sap,
 
 	/* TODO: we could set the MTU depending on the max_sdu_size */
 
-	IRDA_DEBUG(0, "%s: We are now connected!\n", __func__);
+	pr_debug("%s: We are now connected!\n", __func__);
 	del_timer(&self->watchdog_timer);
 
 	/*
@@ -403,7 +392,7 @@ static void irlan_disconnect_indication(void *instance,
 	struct irlan_cb *self;
 	struct tsap_cb *tsap;
 
-	IRDA_DEBUG(0, "%s(), reason=%d\n", __func__ , reason);
+	pr_debug("%s(), reason=%d\n", __func__ , reason);
 
 	self = instance;
 	tsap = sap;
@@ -415,26 +404,26 @@ static void irlan_disconnect_indication(void *instance,
 
 	IRDA_ASSERT(tsap == self->tsap_data, return;);
 
-	IRDA_DEBUG(2, "IrLAN, data channel disconnected by peer!\n");
+	pr_debug("IrLAN, data channel disconnected by peer!\n");
 
 	/* Save reason so we know if we should try to reconnect or not */
 	self->disconnect_reason = reason;
 
 	switch (reason) {
 	case LM_USER_REQUEST: /* User request */
-		IRDA_DEBUG(2, "%s(), User requested\n", __func__ );
+		pr_debug("%s(), User requested\n", __func__);
 		break;
 	case LM_LAP_DISCONNECT: /* Unexpected IrLAP disconnect */
-		IRDA_DEBUG(2, "%s(), Unexpected IrLAP disconnect\n", __func__ );
+		pr_debug("%s(), Unexpected IrLAP disconnect\n", __func__);
 		break;
 	case LM_CONNECT_FAILURE: /* Failed to establish IrLAP connection */
-		IRDA_DEBUG(2, "%s(), IrLAP connect failed\n", __func__ );
+		pr_debug("%s(), IrLAP connect failed\n", __func__);
 		break;
 	case LM_LAP_RESET:  /* IrLAP reset */
-		IRDA_DEBUG(2, "%s(), IrLAP reset\n", __func__ );
+		pr_debug("%s(), IrLAP reset\n", __func__);
 		break;
 	case LM_INIT_DISCONNECT:
-		IRDA_DEBUG(2, "%s(), IrLMP connect failed\n", __func__ );
+		pr_debug("%s(), IrLMP connect failed\n", __func__);
 		break;
 	default:
 		net_err_ratelimited("%s(), Unknown disconnect reason\n",
@@ -460,8 +449,6 @@ void irlan_open_data_tsap(struct irlan_cb *self)
 	struct tsap_cb *tsap;
 	notify_t notify;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -482,7 +469,7 @@ void irlan_open_data_tsap(struct irlan_cb *self)
 
 	tsap = irttp_open_tsap(LSAP_ANY, DEFAULT_INITIAL_CREDIT, &notify);
 	if (!tsap) {
-		IRDA_DEBUG(2, "%s(), Got no tsap!\n", __func__ );
+		pr_debug("%s(), Got no tsap!\n", __func__);
 		return;
 	}
 	self->tsap_data = tsap;
@@ -496,8 +483,6 @@ void irlan_open_data_tsap(struct irlan_cb *self)
 
 void irlan_close_tsaps(struct irlan_cb *self)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -586,8 +571,6 @@ int irlan_run_ctrl_tx_queue(struct irlan_cb *self)
 {
 	struct sk_buff *skb;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (irda_lock(&self->client.tx_busy) == FALSE)
 		return -EBUSY;
 
@@ -605,7 +588,7 @@ int irlan_run_ctrl_tx_queue(struct irlan_cb *self)
 		dev_kfree_skb(skb);
 		return -1;
 	}
-	IRDA_DEBUG(2, "%s(), sending ...\n", __func__ );
+	pr_debug("%s(), sending ...\n", __func__);
 
 	return irttp_data_request(self->client.tsap_ctrl, skb);
 }
@@ -618,8 +601,6 @@ int irlan_run_ctrl_tx_queue(struct irlan_cb *self)
  */
 static void irlan_ctrl_data_request(struct irlan_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* Queue command */
 	skb_queue_tail(&self->client.txq, skb);
 
@@ -638,8 +619,6 @@ void irlan_get_provider_info(struct irlan_cb *self)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -671,8 +650,6 @@ void irlan_open_data_channel(struct irlan_cb *self)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -706,8 +683,6 @@ void irlan_close_data_channel(struct irlan_cb *self)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -747,8 +722,6 @@ static void irlan_open_unicast_addr(struct irlan_cb *self)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -789,8 +762,6 @@ void irlan_set_broadcast_filter(struct irlan_cb *self, int status)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -833,8 +804,6 @@ void irlan_set_multicast_filter(struct irlan_cb *self, int status)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -878,8 +847,6 @@ static void irlan_get_unicast_addr(struct irlan_cb *self)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -918,8 +885,6 @@ void irlan_get_media_char(struct irlan_cb *self)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -1006,7 +971,7 @@ static int __irlan_insert_param(struct sk_buff *skb, char *param, int type,
 	int n=0;
 
 	if (skb == NULL) {
-		IRDA_DEBUG(2, "%s(), Got NULL skb\n", __func__ );
+		pr_debug("%s(), Got NULL skb\n", __func__);
 		return 0;
 	}
 
@@ -1023,7 +988,7 @@ static int __irlan_insert_param(struct sk_buff *skb, char *param, int type,
 		IRDA_ASSERT(value_len > 0, return 0;);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown parameter type!\n", __func__ );
+		pr_debug("%s(), Unknown parameter type!\n", __func__);
 		return 0;
 	}
 
@@ -1032,7 +997,7 @@ static int __irlan_insert_param(struct sk_buff *skb, char *param, int type,
 
 	/* Make space for data */
 	if (skb_tailroom(skb) < (param_len+value_len+3)) {
-		IRDA_DEBUG(2, "%s(), No more space at end of skb\n", __func__ );
+		pr_debug("%s(), No more space at end of skb\n", __func__);
 		return 0;
 	}
 	skb_put(skb, param_len+value_len+3);
@@ -1079,13 +1044,11 @@ int irlan_extract_param(__u8 *buf, char *name, char *value, __u16 *len)
 	__u16 val_len;
 	int n=0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	/* get length of parameter name (1 byte) */
 	name_len = buf[n++];
 
 	if (name_len > 254) {
-		IRDA_DEBUG(2, "%s(), name_len > 254\n", __func__ );
+		pr_debug("%s(), name_len > 254\n", __func__);
 		return -RSP_INVALID_COMMAND_FORMAT;
 	}
 
@@ -1102,7 +1065,7 @@ int irlan_extract_param(__u8 *buf, char *name, char *value, __u16 *len)
 	le16_to_cpus(&val_len); n+=2;
 
 	if (val_len >= 1016) {
-		IRDA_DEBUG(2, "%s(), parameter length to long\n", __func__ );
+		pr_debug("%s(), parameter length to long\n", __func__);
 		return -RSP_INVALID_COMMAND_FORMAT;
 	}
 	*len = val_len;
@@ -1112,8 +1075,8 @@ int irlan_extract_param(__u8 *buf, char *name, char *value, __u16 *len)
 	value[val_len] = '\0';
 	n+=val_len;
 
-	IRDA_DEBUG(4, "Parameter: %s ", name);
-	IRDA_DEBUG(4, "Value: %s\n", value);
+	pr_debug("Parameter: %s ", name);
+	pr_debug("Value: %s\n", value);
 
 	return n;
 }
diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c
index 94b948ef36f..fcfbe579434 100644
--- a/net/irda/irlan/irlan_eth.c
+++ b/net/irda/irlan/irlan_eth.c
@@ -110,8 +110,6 @@ static int irlan_eth_open(struct net_device *dev)
 {
 	struct irlan_cb *self = netdev_priv(dev);
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Ready to play! */
 	netif_stop_queue(dev); /* Wait until data link is ready */
 
@@ -137,8 +135,6 @@ static int irlan_eth_close(struct net_device *dev)
 {
 	struct irlan_cb *self = netdev_priv(dev);
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Stop device */
 	netif_stop_queue(dev);
 
@@ -231,8 +227,8 @@ int irlan_eth_receive(void *instance, void *sap, struct sk_buff *skb)
 		return 0;
 	}
 	if (skb->len < ETH_HLEN) {
-		IRDA_DEBUG(0, "%s() : IrLAN frame too short (%d)\n",
-			   __func__, skb->len);
+		pr_debug("%s() : IrLAN frame too short (%d)\n",
+			 __func__, skb->len);
 		dev->stats.rx_dropped++;
 		dev_kfree_skb(skb);
 		return 0;
@@ -281,9 +277,9 @@ void irlan_eth_flow_indication(void *instance, void *sap, LOCAL_FLOW flow)
 
 	IRDA_ASSERT(dev != NULL, return;);
 
-	IRDA_DEBUG(0, "%s() : flow %s ; running %d\n", __func__,
-		   flow == FLOW_STOP ? "FLOW_STOP" : "FLOW_START",
-		   netif_running(dev));
+	pr_debug("%s() : flow %s ; running %d\n", __func__,
+		 flow == FLOW_STOP ? "FLOW_STOP" : "FLOW_START",
+		 netif_running(dev));
 
 	switch (flow) {
 	case FLOW_STOP:
@@ -310,11 +306,9 @@ static void irlan_eth_set_multicast_list(struct net_device *dev)
 {
 	struct irlan_cb *self = netdev_priv(dev);
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Check if data channel has been connected yet */
 	if (self->client.state != IRLAN_DATA) {
-		IRDA_DEBUG(1, "%s(), delaying!\n", __func__);
+		pr_debug("%s(), delaying!\n", __func__);
 		return;
 	}
 
@@ -324,18 +318,18 @@ static void irlan_eth_set_multicast_list(struct net_device *dev)
 	} else if ((dev->flags & IFF_ALLMULTI) ||
 		 netdev_mc_count(dev) > HW_MAX_ADDRS) {
 		/* Disable promiscuous mode, use normal mode. */
-		IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__);
+		pr_debug("%s(), Setting multicast filter\n", __func__);
 		/* hardware_set_filter(NULL); */
 
 		irlan_set_multicast_filter(self, TRUE);
 	} else if (!netdev_mc_empty(dev)) {
-		IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__);
+		pr_debug("%s(), Setting multicast filter\n", __func__);
 		/* Walk the address list, and load the filter */
 		/* hardware_set_filter(dev->mc_list); */
 
 		irlan_set_multicast_filter(self, TRUE);
 	} else {
-		IRDA_DEBUG(4, "%s(), Clearing multicast filter\n", __func__);
+		pr_debug("%s(), Clearing multicast filter\n", __func__);
 		irlan_set_multicast_filter(self, FALSE);
 	}
 
diff --git a/net/irda/irlan/irlan_event.c b/net/irda/irlan/irlan_event.c
index 43f16040a6f..9a1cc11c16f 100644
--- a/net/irda/irlan/irlan_event.c
+++ b/net/irda/irlan/irlan_event.c
@@ -40,7 +40,7 @@ const char * const irlan_state[] = {
 
 void irlan_next_client_state(struct irlan_cb *self, IRLAN_STATE state)
 {
-	IRDA_DEBUG(2, "%s(), %s\n", __func__ , irlan_state[state]);
+	pr_debug("%s(), %s\n", __func__ , irlan_state[state]);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
@@ -50,7 +50,7 @@ void irlan_next_client_state(struct irlan_cb *self, IRLAN_STATE state)
 
 void irlan_next_provider_state(struct irlan_cb *self, IRLAN_STATE state)
 {
-	IRDA_DEBUG(2, "%s(), %s\n", __func__ , irlan_state[state]);
+	pr_debug("%s(), %s\n", __func__ , irlan_state[state]);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
diff --git a/net/irda/irlan/irlan_filter.c b/net/irda/irlan/irlan_filter.c
index 7977be7caf0..e755e90b2f2 100644
--- a/net/irda/irlan/irlan_filter.c
+++ b/net/irda/irlan/irlan_filter.c
@@ -43,7 +43,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_DIRECTED) &&
 	    (self->provider.filter_operation == DYNAMIC))
 	{
-		IRDA_DEBUG(0, "Giving peer a dynamic Ethernet address\n");
+		pr_debug("Giving peer a dynamic Ethernet address\n");
 		self->provider.mac_address[0] = 0x40;
 		self->provider.mac_address[1] = 0x00;
 		self->provider.mac_address[2] = 0x00;
@@ -73,7 +73,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_DIRECTED) &&
 	    (self->provider.filter_mode == FILTER))
 	{
-		IRDA_DEBUG(0, "Directed filter on\n");
+		pr_debug("Directed filter on\n");
 		skb->data[0] = 0x00; /* Success */
 		skb->data[1] = 0x00;
 		return;
@@ -81,7 +81,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_DIRECTED) &&
 	    (self->provider.filter_mode == NONE))
 	{
-		IRDA_DEBUG(0, "Directed filter off\n");
+		pr_debug("Directed filter off\n");
 		skb->data[0] = 0x00; /* Success */
 		skb->data[1] = 0x00;
 		return;
@@ -90,7 +90,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_BROADCAST) &&
 	    (self->provider.filter_mode == FILTER))
 	{
-		IRDA_DEBUG(0, "Broadcast filter on\n");
+		pr_debug("Broadcast filter on\n");
 		skb->data[0] = 0x00; /* Success */
 		skb->data[1] = 0x00;
 		return;
@@ -98,7 +98,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_BROADCAST) &&
 	    (self->provider.filter_mode == NONE))
 	{
-		IRDA_DEBUG(0, "Broadcast filter off\n");
+		pr_debug("Broadcast filter off\n");
 		skb->data[0] = 0x00; /* Success */
 		skb->data[1] = 0x00;
 		return;
@@ -106,7 +106,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_MULTICAST) &&
 	    (self->provider.filter_mode == FILTER))
 	{
-		IRDA_DEBUG(0, "Multicast filter on\n");
+		pr_debug("Multicast filter on\n");
 		skb->data[0] = 0x00; /* Success */
 		skb->data[1] = 0x00;
 		return;
@@ -114,7 +114,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_MULTICAST) &&
 	    (self->provider.filter_mode == NONE))
 	{
-		IRDA_DEBUG(0, "Multicast filter off\n");
+		pr_debug("Multicast filter off\n");
 		skb->data[0] = 0x00; /* Success */
 		skb->data[1] = 0x00;
 		return;
@@ -122,7 +122,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_MULTICAST) &&
 	    (self->provider.filter_operation == GET))
 	{
-		IRDA_DEBUG(0, "Multicast filter get\n");
+		pr_debug("Multicast filter get\n");
 		skb->data[0] = 0x00; /* Success? */
 		skb->data[1] = 0x02;
 		irlan_insert_string_param(skb, "FILTER_MODE", "NONE");
@@ -132,7 +132,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	skb->data[0] = 0x00; /* Command not supported */
 	skb->data[1] = 0x00;
 
-	IRDA_DEBUG(0, "Not implemented!\n");
+	pr_debug("Not implemented!\n");
 }
 
 /*
@@ -143,18 +143,15 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
  */
 void irlan_check_command_param(struct irlan_cb *self, char *param, char *value)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
-	IRDA_DEBUG(4, "%s, %s\n", param, value);
+	pr_debug("%s, %s\n", param, value);
 
 	/*
 	 *  This is experimental!! DB.
 	 */
 	 if (strcmp(param, "MODE") == 0) {
-		IRDA_DEBUG(0, "%s()\n", __func__ );
 		self->use_udata = TRUE;
 		return;
 	}
diff --git a/net/irda/irlan/irlan_provider.c b/net/irda/irlan/irlan_provider.c
index 4664855222f..15c292cf264 100644
--- a/net/irda/irlan/irlan_provider.c
+++ b/net/irda/irlan/irlan_provider.c
@@ -70,8 +70,6 @@ static int irlan_provider_data_indication(void *instance, void *sap,
 	struct irlan_cb *self;
 	__u8 code;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return -1;);
@@ -82,32 +80,32 @@ static int irlan_provider_data_indication(void *instance, void *sap,
 	code = skb->data[0];
 	switch(code) {
 	case CMD_GET_PROVIDER_INFO:
-		IRDA_DEBUG(4, "Got GET_PROVIDER_INFO command!\n");
+		pr_debug("Got GET_PROVIDER_INFO command!\n");
 		irlan_do_provider_event(self, IRLAN_GET_INFO_CMD, skb);
 		break;
 
 	case CMD_GET_MEDIA_CHAR:
-		IRDA_DEBUG(4, "Got GET_MEDIA_CHAR command!\n");
+		pr_debug("Got GET_MEDIA_CHAR command!\n");
 		irlan_do_provider_event(self, IRLAN_GET_MEDIA_CMD, skb);
 		break;
 	case CMD_OPEN_DATA_CHANNEL:
-		IRDA_DEBUG(4, "Got OPEN_DATA_CHANNEL command!\n");
+		pr_debug("Got OPEN_DATA_CHANNEL command!\n");
 		irlan_do_provider_event(self, IRLAN_OPEN_DATA_CMD, skb);
 		break;
 	case CMD_FILTER_OPERATION:
-		IRDA_DEBUG(4, "Got FILTER_OPERATION command!\n");
+		pr_debug("Got FILTER_OPERATION command!\n");
 		irlan_do_provider_event(self, IRLAN_FILTER_CONFIG_CMD, skb);
 		break;
 	case CMD_RECONNECT_DATA_CHAN:
-		IRDA_DEBUG(2, "%s(), Got RECONNECT_DATA_CHAN command\n", __func__ );
-		IRDA_DEBUG(2, "%s(), NOT IMPLEMENTED\n", __func__ );
+		pr_debug("%s(), Got RECONNECT_DATA_CHAN command\n", __func__);
+		pr_debug("%s(), NOT IMPLEMENTED\n", __func__);
 		break;
 	case CMD_CLOSE_DATA_CHAN:
-		IRDA_DEBUG(2, "Got CLOSE_DATA_CHAN command!\n");
-		IRDA_DEBUG(2, "%s(), NOT IMPLEMENTED\n", __func__ );
+		pr_debug("Got CLOSE_DATA_CHAN command!\n");
+		pr_debug("%s(), NOT IMPLEMENTED\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown command!\n", __func__ );
+		pr_debug("%s(), Unknown command!\n", __func__);
 		break;
 	}
 	return 0;
@@ -128,8 +126,6 @@ static void irlan_provider_connect_indication(void *instance, void *sap,
 	struct irlan_cb *self;
 	struct tsap_cb *tsap;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	self = instance;
 	tsap = sap;
 
@@ -179,7 +175,7 @@ static void irlan_provider_disconnect_indication(void *instance, void *sap,
 	struct irlan_cb *self;
 	struct tsap_cb *tsap;
 
-	IRDA_DEBUG(4, "%s(), reason=%d\n", __func__ , reason);
+	pr_debug("%s(), reason=%d\n", __func__ , reason);
 
 	self = instance;
 	tsap = sap;
@@ -233,7 +229,7 @@ int irlan_provider_parse_command(struct irlan_cb *self, int cmd,
 
 	IRDA_ASSERT(skb != NULL, return -RSP_PROTOCOL_ERROR;);
 
-	IRDA_DEBUG(4, "%s(), skb->len=%d\n", __func__ , (int)skb->len);
+	pr_debug("%s(), skb->len=%d\n", __func__ , (int)skb->len);
 
 	IRDA_ASSERT(self != NULL, return -RSP_PROTOCOL_ERROR;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -RSP_PROTOCOL_ERROR;);
@@ -255,7 +251,7 @@ int irlan_provider_parse_command(struct irlan_cb *self, int cmd,
 	/* How many parameters? */
 	count = frame[1];
 
-	IRDA_DEBUG(4, "Got %d parameters\n", count);
+	pr_debug("Got %d parameters\n", count);
 
 	ptr = frame+2;
 
@@ -263,7 +259,7 @@ int irlan_provider_parse_command(struct irlan_cb *self, int cmd,
 	for (i=0; i<count;i++) {
 		ret = irlan_extract_param(ptr, name, value, &val_len);
 		if (ret < 0) {
-			IRDA_DEBUG(2, "%s(), IrLAN, Error!\n", __func__ );
+			pr_debug("%s(), IrLAN, Error!\n", __func__);
 			break;
 		}
 		ptr+=ret;
@@ -288,8 +284,6 @@ void irlan_provider_send_reply(struct irlan_cb *self, int command,
 {
 	struct sk_buff *skb;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -320,7 +314,7 @@ void irlan_provider_send_reply(struct irlan_cb *self, int command,
 			irlan_insert_string_param(skb, "MEDIA", "802.5");
 			break;
 		default:
-			IRDA_DEBUG(2, "%s(), unknown media type!\n", __func__ );
+			pr_debug("%s(), unknown media type!\n", __func__);
 			break;
 		}
 		irlan_insert_short_param(skb, "IRLAN_VER", 0x0101);
@@ -344,7 +338,7 @@ void irlan_provider_send_reply(struct irlan_cb *self, int command,
 			irlan_insert_string_param(skb, "ACCESS_TYPE", "HOSTED");
 			break;
 		default:
-			IRDA_DEBUG(2, "%s(), Unknown access type\n", __func__ );
+			pr_debug("%s(), Unknown access type\n", __func__);
 			break;
 		}
 		irlan_insert_short_param(skb, "MAX_FRAME", 0x05ee);
@@ -364,7 +358,7 @@ void irlan_provider_send_reply(struct irlan_cb *self, int command,
 		irlan_filter_request(self, skb);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown command!\n", __func__ );
+		pr_debug("%s(), Unknown command!\n", __func__);
 		break;
 	}
 
@@ -382,8 +376,6 @@ int irlan_provider_open_ctrl_tsap(struct irlan_cb *self)
 	struct tsap_cb *tsap;
 	notify_t notify;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -1;);
 
@@ -403,7 +395,7 @@ int irlan_provider_open_ctrl_tsap(struct irlan_cb *self)
 
 	tsap = irttp_open_tsap(LSAP_ANY, 1, &notify);
 	if (!tsap) {
-		IRDA_DEBUG(2, "%s(), Got no tsap!\n", __func__ );
+		pr_debug("%s(), Got no tsap!\n", __func__);
 		return -1;
 	}
 	self->provider.tsap_ctrl = tsap;
diff --git a/net/irda/irlan/irlan_provider_event.c b/net/irda/irlan/irlan_provider_event.c
index 01a9d7c993e..9c4f7f51d6b 100644
--- a/net/irda/irlan/irlan_provider_event.c
+++ b/net/irda/irlan/irlan_provider_event.c
@@ -72,8 +72,6 @@ void irlan_do_provider_event(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_provider_state_idle(struct irlan_cb *self, IRLAN_EVENT event,
 				     struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -82,7 +80,7 @@ static int irlan_provider_state_idle(struct irlan_cb *self, IRLAN_EVENT event,
 	     irlan_next_provider_state( self, IRLAN_INFO);
 	     break;
 	default:
-		IRDA_DEBUG(4, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -101,8 +99,6 @@ static int irlan_provider_state_info(struct irlan_cb *self, IRLAN_EVENT event,
 {
 	int ret;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -147,7 +143,7 @@ static int irlan_provider_state_info(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_provider_state(self, IRLAN_IDLE);
 		break;
 	default:
-		IRDA_DEBUG( 0, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -166,8 +162,6 @@ static int irlan_provider_state_info(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_provider_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 				     struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -186,7 +180,7 @@ static int irlan_provider_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_provider_state(self, IRLAN_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -205,8 +199,6 @@ static int irlan_provider_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_provider_state_data(struct irlan_cb *self, IRLAN_EVENT event,
 				     struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -1;);
 
@@ -221,7 +213,7 @@ static int irlan_provider_state_data(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_provider_state(self, IRLAN_IDLE);
 		break;
 	default:
-		IRDA_DEBUG( 0, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
diff --git a/net/irda/irlap.c b/net/irda/irlap.c
index 2e3bc6ccf4b..4b011b7aac8 100644
--- a/net/irda/irlap.c
+++ b/net/irda/irlap.c
@@ -111,8 +111,6 @@ struct irlap_cb *irlap_open(struct net_device *dev, struct qos_info *qos,
 {
 	struct irlap_cb *self;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	/* Initialize the irlap structure. */
 	self = kzalloc(sizeof(struct irlap_cb), GFP_KERNEL);
 	if (self == NULL)
@@ -213,8 +211,6 @@ void irlap_close(struct irlap_cb *self)
 {
 	struct irlap_cb *lap;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -229,7 +225,7 @@ void irlap_close(struct irlap_cb *self)
 	/* Be sure that we manage to remove ourself from the hash */
 	lap = hashbin_remove(irlap, self->saddr, NULL);
 	if (!lap) {
-		IRDA_DEBUG(1, "%s(), Didn't find myself!\n", __func__);
+		pr_debug("%s(), Didn't find myself!\n", __func__);
 		return;
 	}
 	__irlap_close(lap);
@@ -244,8 +240,6 @@ EXPORT_SYMBOL(irlap_close);
  */
 void irlap_connect_indication(struct irlap_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -263,8 +257,6 @@ void irlap_connect_indication(struct irlap_cb *self, struct sk_buff *skb)
  */
 void irlap_connect_response(struct irlap_cb *self, struct sk_buff *userdata)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	irlap_do_event(self, CONNECT_RESPONSE, userdata, NULL);
 }
 
@@ -278,7 +270,7 @@ void irlap_connect_response(struct irlap_cb *self, struct sk_buff *userdata)
 void irlap_connect_request(struct irlap_cb *self, __u32 daddr,
 			   struct qos_info *qos_user, int sniff)
 {
-	IRDA_DEBUG(3, "%s(), daddr=0x%08x\n", __func__, daddr);
+	pr_debug("%s(), daddr=0x%08x\n", __func__, daddr);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -305,8 +297,6 @@ void irlap_connect_request(struct irlap_cb *self, __u32 daddr,
  */
 void irlap_connect_confirm(struct irlap_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -342,8 +332,6 @@ void irlap_data_request(struct irlap_cb *self, struct sk_buff *skb,
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(skb_headroom(skb) >= (LAP_ADDR_HEADER+LAP_CTRL_HEADER),
 		    return;);
 	skb_push(skb, LAP_ADDR_HEADER+LAP_CTRL_HEADER);
@@ -389,8 +377,6 @@ void irlap_unitdata_request(struct irlap_cb *self, struct sk_buff *skb)
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(skb_headroom(skb) >= (LAP_ADDR_HEADER+LAP_CTRL_HEADER),
 	       return;);
 	skb_push(skb, LAP_ADDR_HEADER+LAP_CTRL_HEADER);
@@ -415,8 +401,6 @@ void irlap_unitdata_request(struct irlap_cb *self, struct sk_buff *skb)
 #ifdef CONFIG_IRDA_ULTRA
 void irlap_unitdata_indication(struct irlap_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -435,8 +419,6 @@ void irlap_unitdata_indication(struct irlap_cb *self, struct sk_buff *skb)
  */
 void irlap_disconnect_request(struct irlap_cb *self)
 {
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -456,7 +438,7 @@ void irlap_disconnect_request(struct irlap_cb *self)
 		irlap_do_event(self, DISCONNECT_REQUEST, NULL, NULL);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), disconnect pending!\n", __func__);
+		pr_debug("%s(), disconnect pending!\n", __func__);
 		self->disconnect_pending = TRUE;
 		break;
 	}
@@ -470,7 +452,7 @@ void irlap_disconnect_request(struct irlap_cb *self)
  */
 void irlap_disconnect_indication(struct irlap_cb *self, LAP_REASON reason)
 {
-	IRDA_DEBUG(1, "%s(), reason=%s\n", __func__, lap_reasons[reason]);
+	pr_debug("%s(), reason=%s\n", __func__, lap_reasons[reason]);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -480,7 +462,7 @@ void irlap_disconnect_indication(struct irlap_cb *self, LAP_REASON reason)
 
 	switch (reason) {
 	case LAP_RESET_INDICATION:
-		IRDA_DEBUG(1, "%s(), Sending reset request!\n", __func__);
+		pr_debug("%s(), Sending reset request!\n", __func__);
 		irlap_do_event(self, RESET_REQUEST, NULL, NULL);
 		break;
 	case LAP_NO_RESPONSE:	   /* FALLTHROUGH */
@@ -510,7 +492,7 @@ void irlap_discovery_request(struct irlap_cb *self, discovery_t *discovery)
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 	IRDA_ASSERT(discovery != NULL, return;);
 
-	IRDA_DEBUG(4, "%s(), nslots = %d\n", __func__, discovery->nslots);
+	pr_debug("%s(), nslots = %d\n", __func__, discovery->nslots);
 
 	IRDA_ASSERT((discovery->nslots == 1) || (discovery->nslots == 6) ||
 		    (discovery->nslots == 8) || (discovery->nslots == 16),
@@ -518,8 +500,8 @@ void irlap_discovery_request(struct irlap_cb *self, discovery_t *discovery)
 
 	/* Discovery is only possible in NDM mode */
 	if (self->state != LAP_NDM) {
-		IRDA_DEBUG(4, "%s(), discovery only possible in NDM mode\n",
-			   __func__);
+		pr_debug("%s(), discovery only possible in NDM mode\n",
+			 __func__);
 		irlap_discovery_confirm(self, NULL);
 		/* Note : in theory, if we are not in NDM, we could postpone
 		 * the discovery like we do for connection request.
@@ -597,8 +579,6 @@ void irlap_discovery_confirm(struct irlap_cb *self, hashbin_t *discovery_log)
  */
 void irlap_discovery_indication(struct irlap_cb *self, discovery_t *discovery)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 	IRDA_ASSERT(discovery != NULL, return;);
@@ -643,8 +623,6 @@ void irlap_status_indication(struct irlap_cb *self, int quality_of_link)
  */
 void irlap_reset_indication(struct irlap_cb *self)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -659,7 +637,6 @@ void irlap_reset_indication(struct irlap_cb *self)
  */
 void irlap_reset_confirm(void)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__);
 }
 
 /*
@@ -759,7 +736,7 @@ int irlap_validate_nr_received(struct irlap_cb *self, int nr)
 {
 	/*  nr as expected?  */
 	if (nr == self->vs) {
-		IRDA_DEBUG(4, "%s(), expected!\n", __func__);
+		pr_debug("%s(), expected!\n", __func__);
 		return NR_EXPECTED;
 	}
 
@@ -787,8 +764,6 @@ int irlap_validate_nr_received(struct irlap_cb *self, int nr)
  */
 void irlap_initiate_connection_state(struct irlap_cb *self)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -870,7 +845,7 @@ static void irlap_change_speed(struct irlap_cb *self, __u32 speed, int now)
 {
 	struct sk_buff *skb;
 
-	IRDA_DEBUG(0, "%s(), setting speed to %d\n", __func__, speed);
+	pr_debug("%s(), setting speed to %d\n", __func__, speed);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -913,7 +888,7 @@ static void irlap_init_qos_capabilities(struct irlap_cb *self,
 	 *  user may not have set all of them.
 	 */
 	if (qos_user) {
-		IRDA_DEBUG(1, "%s(), Found user specified QoS!\n", __func__);
+		pr_debug("%s(), Found user specified QoS!\n", __func__);
 
 		if (qos_user->baud_rate.bits)
 			self->qos_rx.baud_rate.bits &= qos_user->baud_rate.bits;
@@ -943,8 +918,6 @@ static void irlap_init_qos_capabilities(struct irlap_cb *self,
  */
 void irlap_apply_default_connection_parameters(struct irlap_cb *self)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -1006,8 +979,6 @@ void irlap_apply_default_connection_parameters(struct irlap_cb *self)
  */
 void irlap_apply_connection_parameters(struct irlap_cb *self, int now)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -1086,12 +1057,12 @@ void irlap_apply_connection_parameters(struct irlap_cb *self, int now)
 		self->N1 = sysctl_warn_noreply_time * 1000 /
 		  self->qos_rx.max_turn_time.value;
 
-	IRDA_DEBUG(4, "Setting N1 = %d\n", self->N1);
+	pr_debug("Setting N1 = %d\n", self->N1);
 
 	/* Set N2 to match our own disconnect time */
 	self->N2 = self->qos_tx.link_disc_time.value * 1000 /
 		self->qos_rx.max_turn_time.value;
-	IRDA_DEBUG(4, "Setting N2 = %d\n", self->N2);
+	pr_debug("Setting N2 = %d\n", self->N2);
 }
 
 #ifdef CONFIG_PROC_FS
diff --git a/net/irda/irlap_event.c b/net/irda/irlap_event.c
index 5f4a84eb35c..245d87b4202 100644
--- a/net/irda/irlap_event.c
+++ b/net/irda/irlap_event.c
@@ -218,7 +218,7 @@ static void irlap_start_poll_timer(struct irlap_cb *self, int timeout)
 	} else
 		self->fast_RR = FALSE;
 
-	IRDA_DEBUG(3, "%s(), timeout=%d (%ld)\n", __func__, timeout, jiffies);
+	pr_debug("%s(), timeout=%d (%ld)\n", __func__, timeout, jiffies);
 #endif /* CONFIG_IRDA_FAST_RR */
 
 	if (timeout == 0)
@@ -242,8 +242,8 @@ void irlap_do_event(struct irlap_cb *self, IRLAP_EVENT event,
 	if (!self || self->magic != LAP_MAGIC)
 		return;
 
-	IRDA_DEBUG(3, "%s(), event = %s, state = %s\n", __func__,
-		   irlap_event[event], irlap_state[self->state]);
+	pr_debug("%s(), event = %s, state = %s\n", __func__,
+		 irlap_event[event], irlap_state[self->state]);
 
 	ret = (*state[self->state])(self, event, skb, info);
 
@@ -260,8 +260,8 @@ void irlap_do_event(struct irlap_cb *self, IRLAP_EVENT event,
 		 * try to disconnect link if we send any data frames, since
 		 * that will change the state away form XMIT
 		 */
-		IRDA_DEBUG(2, "%s() : queue len = %d\n", __func__,
-			   skb_queue_len(&self->txq));
+		pr_debug("%s() : queue len = %d\n", __func__,
+			 skb_queue_len(&self->txq));
 
 		if (!skb_queue_empty(&self->txq)) {
 			/* Prevent race conditions with irlap_data_request() */
@@ -340,8 +340,8 @@ static int irlap_state_ndm(struct irlap_cb *self, IRLAP_EVENT event,
 			/* Note : this will never happen, because we test
 			 * media busy in irlap_connect_request() and
 			 * postpone the event... - Jean II */
-			IRDA_DEBUG(0, "%s(), CONNECT_REQUEST: media busy!\n",
-				   __func__);
+			pr_debug("%s(), CONNECT_REQUEST: media busy!\n",
+				 __func__);
 
 			/* Always switch state before calling upper layers */
 			irlap_next_state(self, LAP_NDM);
@@ -367,16 +367,16 @@ static int irlap_state_ndm(struct irlap_cb *self, IRLAP_EVENT event,
 
 			irlap_connect_indication(self, skb);
 		} else {
-			IRDA_DEBUG(0, "%s(), SNRM frame does not "
-				   "contain an I field!\n", __func__);
+			pr_debug("%s(), SNRM frame does not contain an I field!\n",
+				 __func__);
 		}
 		break;
 	case DISCOVERY_REQUEST:
 		IRDA_ASSERT(info != NULL, return -1;);
 
 		if (self->media_busy) {
-			IRDA_DEBUG(1, "%s(), DISCOVERY_REQUEST: media busy!\n",
-				   __func__);
+			pr_debug("%s(), DISCOVERY_REQUEST: media busy!\n",
+				 __func__);
 			/* irlap->log.condition = MEDIA_BUSY; */
 
 			/* This will make IrLMP try again */
@@ -442,7 +442,8 @@ static int irlap_state_ndm(struct irlap_cb *self, IRLAP_EVENT event,
 		 * those cases...
 		 * Jean II
 		 */
-			IRDA_DEBUG(1, "%s(), Receiving final discovery request, missed the discovery slots :-(\n", __func__);
+			pr_debug("%s(), Receiving final discovery request, missed the discovery slots :-(\n",
+				 __func__);
 
 			/* Last discovery request -> in the log */
 			irlap_discovery_indication(self, info->discovery);
@@ -520,8 +521,8 @@ static int irlap_state_ndm(struct irlap_cb *self, IRLAP_EVENT event,
 	case RECV_UI_FRAME:
 		/* Only accept broadcast frames in NDM mode */
 		if (info->caddr != CBROADCAST) {
-			IRDA_DEBUG(0, "%s(), not a broadcast frame!\n",
-				   __func__);
+			pr_debug("%s(), not a broadcast frame!\n",
+				 __func__);
 		} else
 			irlap_unitdata_indication(self, skb);
 		break;
@@ -537,11 +538,11 @@ static int irlap_state_ndm(struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_send_test_frame(self, CBROADCAST, info->daddr, skb);
 		break;
 	case RECV_TEST_RSP:
-		IRDA_DEBUG(0, "%s() not implemented!\n", __func__);
+		pr_debug("%s() not implemented!\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %s\n", __func__,
-			   irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n", __func__,
+			 irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -568,8 +569,8 @@ static int irlap_state_query(struct irlap_cb *self, IRLAP_EVENT event,
 		IRDA_ASSERT(info != NULL, return -1;);
 		IRDA_ASSERT(info->discovery != NULL, return -1;);
 
-		IRDA_DEBUG(4, "%s(), daddr=%08x\n", __func__,
-			   info->discovery->data.daddr);
+		pr_debug("%s(), daddr=%08x\n", __func__,
+			 info->discovery->data.daddr);
 
 		if (!self->discovery_log) {
 			net_warn_ratelimited("%s: discovery log is gone! maybe the discovery timeout has been set too short?\n",
@@ -598,7 +599,8 @@ static int irlap_state_query(struct irlap_cb *self, IRLAP_EVENT event,
 
 		IRDA_ASSERT(info != NULL, return -1;);
 
-		IRDA_DEBUG(1, "%s(), Receiving discovery request (s = %d) while performing discovery :-(\n", __func__, info->s);
+		pr_debug("%s(), Receiving discovery request (s = %d) while performing discovery :-(\n",
+			 __func__, info->s);
 
 		/* Last discovery request ? */
 		if (info->s == 0xff)
@@ -612,8 +614,8 @@ static int irlap_state_query(struct irlap_cb *self, IRLAP_EVENT event,
 		 * timing requirements.
 		 */
 		if (irda_device_is_receiving(self->netdev) && !self->add_wait) {
-			IRDA_DEBUG(2, "%s(), device is slow to answer, "
-				   "waiting some more!\n", __func__);
+			pr_debug("%s(), device is slow to answer, waiting some more!\n",
+				 __func__);
 			irlap_start_slot_timer(self, msecs_to_jiffies(10));
 			self->add_wait = TRUE;
 			return ret;
@@ -649,8 +651,8 @@ static int irlap_state_query(struct irlap_cb *self, IRLAP_EVENT event,
 		}
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %s\n", __func__,
-			   irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n", __func__,
+			 irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -671,15 +673,13 @@ static int irlap_state_reply(struct irlap_cb *self, IRLAP_EVENT event,
 	discovery_t *discovery_rsp;
 	int ret=0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
 
 	switch (event) {
 	case QUERY_TIMER_EXPIRED:
-		IRDA_DEBUG(0, "%s(), QUERY_TIMER_EXPIRED <%ld>\n",
-			   __func__, jiffies);
+		pr_debug("%s(), QUERY_TIMER_EXPIRED <%ld>\n",
+			 __func__, jiffies);
 		irlap_next_state(self, LAP_NDM);
 		break;
 	case RECV_DISCOVERY_XID_CMD:
@@ -717,8 +717,8 @@ static int irlap_state_reply(struct irlap_cb *self, IRLAP_EVENT event,
 		}
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %d, %s\n", __func__,
-			   event, irlap_event[event]);
+		pr_debug("%s(), Unknown event %d, %s\n", __func__,
+			 event, irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -738,7 +738,7 @@ static int irlap_state_conn(struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s(), event=%s\n", __func__, irlap_event[ event]);
+	pr_debug("%s(), event=%s\n", __func__, irlap_event[event]);
 
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
@@ -798,20 +798,20 @@ static int irlap_state_conn(struct irlap_cb *self, IRLAP_EVENT event,
 
 		break;
 	case RECV_DISCOVERY_XID_CMD:
-		IRDA_DEBUG(3, "%s(), event RECV_DISCOVER_XID_CMD!\n",
-			   __func__);
+		pr_debug("%s(), event RECV_DISCOVER_XID_CMD!\n",
+			 __func__);
 		irlap_next_state(self, LAP_NDM);
 
 		break;
 	case DISCONNECT_REQUEST:
-		IRDA_DEBUG(0, "%s(), Disconnect request!\n", __func__);
+		pr_debug("%s(), Disconnect request!\n", __func__);
 		irlap_send_dm_frame(self);
 		irlap_next_state( self, LAP_NDM);
 		irlap_disconnect_indication(self, LAP_DISC_INDICATION);
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %d, %s\n", __func__,
-			   event, irlap_event[event]);
+		pr_debug("%s(), Unknown event %d, %s\n", __func__,
+			 event, irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -832,8 +832,6 @@ static int irlap_state_setup(struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
 
@@ -861,7 +859,7 @@ static int irlap_state_setup(struct irlap_cb *self, IRLAP_EVENT event,
 		self->retry_count++;
 		break;
 	case RECV_SNRM_CMD:
-		IRDA_DEBUG(4, "%s(), SNRM battle!\n", __func__);
+		pr_debug("%s(), SNRM battle!\n", __func__);
 
 		IRDA_ASSERT(skb != NULL, return 0;);
 		IRDA_ASSERT(info != NULL, return 0;);
@@ -948,8 +946,8 @@ static int irlap_state_setup(struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_disconnect_indication(self, LAP_DISC_INDICATION);
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %d, %s\n", __func__,
-			   event, irlap_event[event]);
+		pr_debug("%s(), Unknown event %d, %s\n", __func__,
+			 event, irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -966,7 +964,7 @@ static int irlap_state_setup(struct irlap_cb *self, IRLAP_EVENT event,
 static int irlap_state_offline(struct irlap_cb *self, IRLAP_EVENT event,
 			       struct sk_buff *skb, struct irlap_info *info)
 {
-	IRDA_DEBUG( 0, "%s(), Unknown event\n", __func__);
+	pr_debug("%s(), Unknown event\n", __func__);
 
 	return -1;
 }
@@ -1029,8 +1027,8 @@ static int irlap_state_xmit_p(struct irlap_cb *self, IRLAP_EVENT event,
 			 *  speed and turn-around-time.
 			 */
 			if((!nextfit) && (skb->len > self->bytes_left)) {
-				IRDA_DEBUG(0, "%s(), Not allowed to transmit"
-					   " more bytes!\n", __func__);
+				pr_debug("%s(), Not allowed to transmit more bytes!\n",
+					 __func__);
 				/* Requeue the skb */
 				skb_queue_head(&self->txq, skb_get(skb));
 				/*
@@ -1081,8 +1079,8 @@ static int irlap_state_xmit_p(struct irlap_cb *self, IRLAP_EVENT event,
 			self->fast_RR = FALSE;
 #endif /* CONFIG_IRDA_FAST_RR */
 		} else {
-			IRDA_DEBUG(4, "%s(), Unable to send! remote busy?\n",
-				   __func__);
+			pr_debug("%s(), Unable to send! remote busy?\n",
+				 __func__);
 			skb_queue_head(&self->txq, skb_get(skb));
 
 			/*
@@ -1093,8 +1091,8 @@ static int irlap_state_xmit_p(struct irlap_cb *self, IRLAP_EVENT event,
 		}
 		break;
 	case POLL_TIMER_EXPIRED:
-		IRDA_DEBUG(3, "%s(), POLL_TIMER_EXPIRED <%ld>\n",
-			    __func__, jiffies);
+		pr_debug("%s(), POLL_TIMER_EXPIRED <%ld>\n",
+			 __func__, jiffies);
 		irlap_send_rr_frame(self, CMD_FRAME);
 		/* Return to NRM properly - Jean II  */
 		self->window = self->window_size;
@@ -1119,8 +1117,8 @@ static int irlap_state_xmit_p(struct irlap_cb *self, IRLAP_EVENT event,
 		 * when we return... - Jean II */
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s\n",
-			   __func__, irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n",
+			 __func__, irlap_event[event]);
 
 		ret = -EINVAL;
 		break;
@@ -1138,8 +1136,6 @@ static int irlap_state_pclose(struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
 
@@ -1173,7 +1169,7 @@ static int irlap_state_pclose(struct irlap_cb *self, IRLAP_EVENT event,
 		}
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %d\n", __func__, event);
+		pr_debug("%s(), Unknown event %d\n", __func__, event);
 
 		ret = -1;
 		break;
@@ -1295,9 +1291,8 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 				/* Keep state */
 				irlap_next_state(self, LAP_NRM_P);
 			} else {
-				IRDA_DEBUG(4,
-				       "%s(), missing or duplicate frame!\n",
-					   __func__);
+				pr_debug("%s(), missing or duplicate frame!\n",
+					 __func__);
 
 				/* Update Nr received */
 				irlap_update_nr_received(self, info->nr);
@@ -1366,8 +1361,8 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 		if ((ns_status == NS_UNEXPECTED) &&
 		    (nr_status == NR_UNEXPECTED))
 		{
-			IRDA_DEBUG(4, "%s(), unexpected nr and ns!\n",
-				   __func__);
+			pr_debug("%s(), unexpected nr and ns!\n",
+				 __func__);
 			if (info->pf) {
 				/* Resend rejected frames */
 				irlap_resend_rejected_frames(self, CMD_FRAME);
@@ -1407,9 +1402,9 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 			}
 			break;
 		}
-		IRDA_DEBUG(1, "%s(), Not implemented!\n", __func__);
-		IRDA_DEBUG(1, "%s(), event=%s, ns_status=%d, nr_status=%d\n",
-		       __func__, irlap_event[event], ns_status, nr_status);
+		pr_debug("%s(), Not implemented!\n", __func__);
+		pr_debug("%s(), event=%s, ns_status=%d, nr_status=%d\n",
+			 __func__, irlap_event[event], ns_status, nr_status);
 		break;
 	case RECV_UI_FRAME:
 		/* Poll bit cleared? */
@@ -1420,7 +1415,8 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 			del_timer(&self->final_timer);
 			irlap_data_indication(self, skb, TRUE);
 			irlap_next_state(self, LAP_XMIT_P);
-			IRDA_DEBUG(1, "%s: RECV_UI_FRAME: next state %s\n", __func__, irlap_state[self->state]);
+			pr_debug("%s: RECV_UI_FRAME: next state %s\n",
+				 __func__, irlap_state[self->state]);
 			irlap_start_poll_timer(self, self->poll_timeout);
 		}
 		break;
@@ -1463,10 +1459,9 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 			/* Update Nr received */
 			irlap_update_nr_received(self, info->nr);
 
-			IRDA_DEBUG(4, "RECV_RR_FRAME: Retrans:%d, nr=%d, va=%d, "
-			      "vs=%d, vr=%d\n",
-			      self->retry_count, info->nr, self->va,
-			      self->vs, self->vr);
+			pr_debug("RECV_RR_FRAME: Retrans:%d, nr=%d, va=%d, vs=%d, vr=%d\n",
+				 self->retry_count, info->nr, self->va,
+				 self->vs, self->vr);
 
 			/* Resend rejected frames */
 			irlap_resend_rejected_frames(self, CMD_FRAME);
@@ -1474,8 +1469,8 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 
 			irlap_next_state(self, LAP_NRM_P);
 		} else if (ret == NR_INVALID) {
-			IRDA_DEBUG(1, "%s(), Received RR with "
-				   "invalid nr !\n", __func__);
+			pr_debug("%s(), Received RR with invalid nr !\n",
+				 __func__);
 
 			irlap_next_state(self, LAP_RESET_WAIT);
 
@@ -1511,8 +1506,7 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 		 *  we only do this once for each frame.
 		 */
 		if (irda_device_is_receiving(self->netdev) && !self->add_wait) {
-			IRDA_DEBUG(1, "FINAL_TIMER_EXPIRED when receiving a "
-			      "frame! Waiting a little bit more!\n");
+			pr_debug("FINAL_TIMER_EXPIRED when receiving a frame! Waiting a little bit more!\n");
 			irlap_start_final_timer(self, msecs_to_jiffies(300));
 
 			/*
@@ -1529,18 +1523,18 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 		if (self->retry_count < self->N2) {
 			if (skb_peek(&self->wx_list) == NULL) {
 				/* Retry sending the pf bit to the secondary */
-				IRDA_DEBUG(4, "nrm_p: resending rr");
+				pr_debug("nrm_p: resending rr");
 				irlap_wait_min_turn_around(self, &self->qos_tx);
 				irlap_send_rr_frame(self, CMD_FRAME);
 			} else {
-				IRDA_DEBUG(4, "nrm_p: resend frames");
+				pr_debug("nrm_p: resend frames");
 				irlap_resend_rejected_frames(self, CMD_FRAME);
 			}
 
 			irlap_start_final_timer(self, self->final_timeout);
 			self->retry_count++;
-			IRDA_DEBUG(4, "irlap_state_nrm_p: FINAL_TIMER_EXPIRED:"
-				   " retry_count=%d\n", self->retry_count);
+			pr_debug("irlap_state_nrm_p: FINAL_TIMER_EXPIRED: retry_count=%d\n",
+				 self->retry_count);
 
 			/* Early warning event. I'm using a pretty liberal
 			 * interpretation of the spec and generate an event
@@ -1580,7 +1574,7 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_start_final_timer(self, 2 * self->final_timeout);
 		break;
 	case RECV_RD_RSP:
-		IRDA_DEBUG(1, "%s(), RECV_RD_RSP\n", __func__);
+		pr_debug("%s(), RECV_RD_RSP\n", __func__);
 
 		irlap_flush_all_queues(self);
 		irlap_next_state(self, LAP_XMIT_P);
@@ -1588,8 +1582,8 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_disconnect_request(self);
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %s\n",
-			    __func__, irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n",
+			 __func__, irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -1609,7 +1603,7 @@ static int irlap_state_reset_wait(struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(3, "%s(), event = %s\n", __func__, irlap_event[event]);
+	pr_debug("%s(), event = %s\n", __func__, irlap_event[event]);
 
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
@@ -1635,8 +1629,8 @@ static int irlap_state_reset_wait(struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_next_state( self, LAP_PCLOSE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %s\n", __func__,
-			   irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n", __func__,
+			 irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -1656,7 +1650,7 @@ static int irlap_state_reset(struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(3, "%s(), event = %s\n", __func__, irlap_event[event]);
+	pr_debug("%s(), event = %s\n", __func__, irlap_event[event]);
 
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
@@ -1714,7 +1708,7 @@ static int irlap_state_reset(struct irlap_cb *self, IRLAP_EVENT event,
 		 * state
 		 */
 		if (!info) {
-			IRDA_DEBUG(3, "%s(), RECV_SNRM_CMD\n", __func__);
+			pr_debug("%s(), RECV_SNRM_CMD\n", __func__);
 			irlap_initiate_connection_state(self);
 			irlap_wait_min_turn_around(self, &self->qos_tx);
 			irlap_send_ua_response_frame(self, &self->qos_rx);
@@ -1722,14 +1716,13 @@ static int irlap_state_reset(struct irlap_cb *self, IRLAP_EVENT event,
 			irlap_start_wd_timer(self, self->wd_timeout);
 			irlap_next_state(self, LAP_NDM);
 		} else {
-			IRDA_DEBUG(0,
-				   "%s(), SNRM frame contained an I field!\n",
-				   __func__);
+			pr_debug("%s(), SNRM frame contained an I field!\n",
+				 __func__);
 		}
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %s\n",
-			   __func__, irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n",
+			 __func__, irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -1749,7 +1742,7 @@ static int irlap_state_xmit_s(struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s(), event=%s\n", __func__, irlap_event[event]);
+	pr_debug("%s(), event=%s\n", __func__, irlap_event[event]);
 
 	IRDA_ASSERT(self != NULL, return -ENODEV;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -EBADR;);
@@ -1785,8 +1778,8 @@ static int irlap_state_xmit_s(struct irlap_cb *self, IRLAP_EVENT event,
 			 *  speed and turn-around-time.
 			 */
 			if((!nextfit) && (skb->len > self->bytes_left)) {
-				IRDA_DEBUG(0, "%s(), Not allowed to transmit"
-					   " more bytes!\n", __func__);
+				pr_debug("%s(), Not allowed to transmit more bytes!\n",
+					 __func__);
 				/* Requeue the skb */
 				skb_queue_head(&self->txq, skb_get(skb));
 
@@ -1832,7 +1825,7 @@ static int irlap_state_xmit_s(struct irlap_cb *self, IRLAP_EVENT event,
 				ret = -EPROTO;
 			}
 		} else {
-			IRDA_DEBUG(2, "%s(), Unable to send!\n", __func__);
+			pr_debug("%s(), Unable to send!\n", __func__);
 			skb_queue_head(&self->txq, skb_get(skb));
 			ret = -EPROTO;
 		}
@@ -1848,8 +1841,8 @@ static int irlap_state_xmit_s(struct irlap_cb *self, IRLAP_EVENT event,
 		 * when we return... - Jean II */
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %s\n", __func__,
-			   irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n", __func__,
+			 irlap_event[event]);
 
 		ret = -EINVAL;
 		break;
@@ -1871,7 +1864,7 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 	int nr_status;
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s(), event=%s\n", __func__, irlap_event[ event]);
+	pr_debug("%s(), event=%s\n", __func__, irlap_event[event]);
 
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
@@ -1879,10 +1872,9 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 	switch (event) {
 	case RECV_I_CMD: /* Optimize for the common case */
 		/* FIXME: must check for remote_busy below */
-		IRDA_DEBUG(4, "%s(), event=%s nr=%d, vs=%d, ns=%d, "
-			   "vr=%d, pf=%d\n", __func__,
-			   irlap_event[event], info->nr,
-			   self->vs, info->ns, self->vr, info->pf);
+		pr_debug("%s(), event=%s nr=%d, vs=%d, ns=%d, vr=%d, pf=%d\n",
+			 __func__, irlap_event[event], info->nr,
+			 self->vs, info->ns, self->vr, info->pf);
 
 		self->retry_count = 0;
 
@@ -1982,7 +1974,7 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 		if ((ns_status == NS_EXPECTED) && (nr_status == NR_UNEXPECTED))
 		{
 			if (info->pf) {
-				IRDA_DEBUG(4, "RECV_I_RSP: frame(s) lost\n");
+				pr_debug("RECV_I_RSP: frame(s) lost\n");
 
 				self->vr = (self->vr + 1) % 8;
 
@@ -2019,10 +2011,10 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 		}
 
 		if (ret == NR_INVALID) {
-			IRDA_DEBUG(0, "NRM_S, NR_INVALID not implemented!\n");
+			pr_debug("NRM_S, NR_INVALID not implemented!\n");
 		}
 		if (ret == NS_INVALID) {
-			IRDA_DEBUG(0, "NRM_S, NS_INVALID not implemented!\n");
+			pr_debug("NRM_S, NS_INVALID not implemented!\n");
 		}
 		break;
 	case RECV_UI_FRAME:
@@ -2111,22 +2103,21 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 			/* Keep state */
 			irlap_next_state(self, LAP_NRM_S);
 		} else {
-			IRDA_DEBUG(1, "%s(), invalid nr not implemented!\n",
-				   __func__);
+			pr_debug("%s(), invalid nr not implemented!\n",
+				 __func__);
 		}
 		break;
 	case RECV_SNRM_CMD:
 		/* SNRM frame is not allowed to contain an I-field */
 		if (!info) {
 			del_timer(&self->wd_timer);
-			IRDA_DEBUG(1, "%s(), received SNRM cmd\n", __func__);
+			pr_debug("%s(), received SNRM cmd\n", __func__);
 			irlap_next_state(self, LAP_RESET_CHECK);
 
 			irlap_reset_indication(self);
 		} else {
-			IRDA_DEBUG(0,
-				   "%s(), SNRM frame contained an I-field!\n",
-				   __func__);
+			pr_debug("%s(), SNRM frame contained an I-field!\n",
+				 __func__);
 
 		}
 		break;
@@ -2158,8 +2149,8 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 		 *   which explain why we use (self->N2 / 2) here !!!
 		 * Jean II
 		 */
-		IRDA_DEBUG(1, "%s(), retry_count = %d\n", __func__,
-			   self->retry_count);
+		pr_debug("%s(), retry_count = %d\n", __func__,
+			 self->retry_count);
 
 		if (self->retry_count < (self->N2 / 2)) {
 			/* No retry, just wait for primary */
@@ -2211,8 +2202,8 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_send_test_frame(self, self->caddr, info->daddr, skb);
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %d, (%s)\n", __func__,
-			   event, irlap_event[event]);
+		pr_debug("%s(), Unknown event %d, (%s)\n", __func__,
+			 event, irlap_event[event]);
 
 		ret = -EINVAL;
 		break;
@@ -2226,8 +2217,6 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 static int irlap_state_sclose(struct irlap_cb *self, IRLAP_EVENT event,
 			      struct sk_buff *skb, struct irlap_info *info)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -ENODEV;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -EBADR;);
 
@@ -2283,8 +2272,8 @@ static int irlap_state_sclose(struct irlap_cb *self, IRLAP_EVENT event,
 			break;		/* stay in SCLOSE */
 		}
 
-		IRDA_DEBUG(1, "%s(), Unknown event %d, (%s)\n", __func__,
-			   event, irlap_event[event]);
+		pr_debug("%s(), Unknown event %d, (%s)\n", __func__,
+			 event, irlap_event[event]);
 
 		break;
 	}
@@ -2298,7 +2287,7 @@ static int irlap_state_reset_check( struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(1, "%s(), event=%s\n", __func__, irlap_event[event]);
+	pr_debug("%s(), event=%s\n", __func__, irlap_event[event]);
 
 	IRDA_ASSERT(self != NULL, return -ENODEV;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -EBADR;);
@@ -2319,8 +2308,8 @@ static int irlap_state_reset_check( struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_next_state(self, LAP_SCLOSE);
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %d, (%s)\n", __func__,
-			   event, irlap_event[event]);
+		pr_debug("%s(), Unknown event %d, (%s)\n", __func__,
+			 event, irlap_event[event]);
 
 		ret = -EINVAL;
 		break;
diff --git a/net/irda/irlap_frame.c b/net/irda/irlap_frame.c
index 90ef03658a7..b936b1251a6 100644
--- a/net/irda/irlap_frame.c
+++ b/net/irda/irlap_frame.c
@@ -103,8 +103,8 @@ void irlap_queue_xmit(struct irlap_cb *self, struct sk_buff *skb)
 	irlap_insert_info(self, skb);
 
 	if (unlikely(self->mode & IRDA_MODE_MONITOR)) {
-		IRDA_DEBUG(3, "%s(): %s is in monitor mode\n", __func__,
-			   self->netdev->name);
+		pr_debug("%s(): %s is in monitor mode\n", __func__,
+			 self->netdev->name);
 		dev_kfree_skb(skb);
 		return;
 	}
@@ -182,8 +182,8 @@ static void irlap_recv_snrm_cmd(struct irlap_cb *self, struct sk_buff *skb,
 
 		/* Check if the new connection address is valid */
 		if ((info->caddr == 0x00) || (info->caddr == 0xfe)) {
-			IRDA_DEBUG(3, "%s(), invalid connection address!\n",
-				   __func__);
+			pr_debug("%s(), invalid connection address!\n",
+				 __func__);
 			return;
 		}
 
@@ -193,8 +193,8 @@ static void irlap_recv_snrm_cmd(struct irlap_cb *self, struct sk_buff *skb,
 
 		/* Only accept if addressed directly to us */
 		if (info->saddr != self->saddr) {
-			IRDA_DEBUG(2, "%s(), not addressed to us!\n",
-				   __func__);
+			pr_debug("%s(), not addressed to us!\n",
+				 __func__);
 			return;
 		}
 		irlap_do_event(self, RECV_SNRM_CMD, skb, info);
@@ -216,7 +216,7 @@ void irlap_send_ua_response_frame(struct irlap_cb *self, struct qos_info *qos)
 	struct ua_frame *frame;
 	int ret;
 
-	IRDA_DEBUG(2, "%s() <%ld>\n", __func__, jiffies);
+	pr_debug("%s() <%ld>\n", __func__, jiffies);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -291,8 +291,6 @@ void irlap_send_disc_frame(struct irlap_cb *self)
 	struct sk_buff *tx_skb = NULL;
 	struct disc_frame *frame;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -322,8 +320,8 @@ void irlap_send_discovery_xid_frame(struct irlap_cb *self, int S, __u8 s,
 	__u32 bcast = BROADCAST;
 	__u8 *info;
 
-	IRDA_DEBUG(4, "%s(), s=%d, S=%d, command=%d\n", __func__,
-		   s, S, command);
+	pr_debug("%s(), s=%d, S=%d, command=%d\n", __func__,
+		 s, S, command);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -415,8 +413,6 @@ static void irlap_recv_discovery_xid_rsp(struct irlap_cb *self,
 	__u8 *discovery_info;
 	char *text;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -432,8 +428,8 @@ static void irlap_recv_discovery_xid_rsp(struct irlap_cb *self,
 
 	/* Make sure frame is addressed to us */
 	if ((info->saddr != self->saddr) && (info->saddr != BROADCAST)) {
-		IRDA_DEBUG(0, "%s(), frame is not addressed to us!\n",
-			   __func__);
+		pr_debug("%s(), frame is not addressed to us!\n",
+			 __func__);
 		return;
 	}
 
@@ -446,15 +442,15 @@ static void irlap_recv_discovery_xid_rsp(struct irlap_cb *self,
 	discovery->data.saddr = self->saddr;
 	discovery->timestamp = jiffies;
 
-	IRDA_DEBUG(4, "%s(), daddr=%08x\n", __func__,
-		   discovery->data.daddr);
+	pr_debug("%s(), daddr=%08x\n", __func__,
+		 discovery->data.daddr);
 
 	discovery_info = skb_pull(skb, sizeof(struct xid_frame));
 
 	/* Get info returned from peer */
 	discovery->data.hints[0] = discovery_info[0];
 	if (discovery_info[0] & HINT_EXTENSION) {
-		IRDA_DEBUG(4, "EXTENSION\n");
+		pr_debug("EXTENSION\n");
 		discovery->data.hints[1] = discovery_info[1];
 		discovery->data.charset = discovery_info[2];
 		text = (char *) &discovery_info[3];
@@ -503,8 +499,8 @@ static void irlap_recv_discovery_xid_cmd(struct irlap_cb *self,
 
 	/* Make sure frame is addressed to us */
 	if ((info->saddr != self->saddr) && (info->saddr != BROADCAST)) {
-		IRDA_DEBUG(0, "%s(), frame is not addressed to us!\n",
-			   __func__);
+		pr_debug("%s(), frame is not addressed to us!\n",
+			 __func__);
 		return;
 	}
 
@@ -656,7 +652,7 @@ static void irlap_recv_rnr_frame(struct irlap_cb *self, struct sk_buff *skb,
 {
 	info->nr = skb->data[1] >> 5;
 
-	IRDA_DEBUG(4, "%s(), nr=%d, %ld\n", __func__, info->nr, jiffies);
+	pr_debug("%s(), nr=%d, %ld\n", __func__, info->nr, jiffies);
 
 	if (command)
 		irlap_do_event(self, RECV_RNR_CMD, skb, info);
@@ -667,8 +663,6 @@ static void irlap_recv_rnr_frame(struct irlap_cb *self, struct sk_buff *skb,
 static void irlap_recv_rej_frame(struct irlap_cb *self, struct sk_buff *skb,
 				 struct irlap_info *info, int command)
 {
-	IRDA_DEBUG(0, "%s()\n", __func__);
-
 	info->nr = skb->data[1] >> 5;
 
 	/* Check if this is a command or a response frame */
@@ -681,8 +675,6 @@ static void irlap_recv_rej_frame(struct irlap_cb *self, struct sk_buff *skb,
 static void irlap_recv_srej_frame(struct irlap_cb *self, struct sk_buff *skb,
 				  struct irlap_info *info, int command)
 {
-	IRDA_DEBUG(0, "%s()\n", __func__);
-
 	info->nr = skb->data[1] >> 5;
 
 	/* Check if this is a command or a response frame */
@@ -695,8 +687,6 @@ static void irlap_recv_srej_frame(struct irlap_cb *self, struct sk_buff *skb,
 static void irlap_recv_disc_frame(struct irlap_cb *self, struct sk_buff *skb,
 				  struct irlap_info *info, int command)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Check if this is a command or a response frame */
 	if (command)
 		irlap_do_event(self, RECV_DISC_CMD, skb, info);
@@ -754,7 +744,7 @@ void irlap_send_data_primary(struct irlap_cb *self, struct sk_buff *skb)
 
 		irlap_send_i_frame( self, tx_skb, CMD_FRAME);
 	} else {
-		IRDA_DEBUG(4, "%s(), sending unreliable frame\n", __func__);
+		pr_debug("%s(), sending unreliable frame\n", __func__);
 		irlap_send_ui_frame(self, skb_get(skb), self->caddr, CMD_FRAME);
 		self->window -= 1;
 	}
@@ -807,7 +797,7 @@ void irlap_send_data_primary_poll(struct irlap_cb *self, struct sk_buff *skb)
 		irlap_next_state(self, LAP_NRM_P);
 		irlap_send_i_frame(self, tx_skb, CMD_FRAME);
 	} else {
-		IRDA_DEBUG(4, "%s(), sending unreliable frame\n", __func__);
+		pr_debug("%s(), sending unreliable frame\n", __func__);
 
 		if (self->ack_required) {
 			irlap_send_ui_frame(self, skb_get(skb), self->caddr, CMD_FRAME);
@@ -834,7 +824,9 @@ void irlap_send_data_primary_poll(struct irlap_cb *self, struct sk_buff *skb)
 	 * See max_line_capacities[][] in qos.c for details. Jean II */
 	transmission_time -= (self->final_timeout * self->bytes_left
 			      / self->line_capacity);
-	IRDA_DEBUG(4, "%s() adjusting transmission_time : ft=%d, bl=%d, lc=%d -> tt=%d\n", __func__, self->final_timeout, self->bytes_left, self->line_capacity, transmission_time);
+	pr_debug("%s() adjusting transmission_time : ft=%d, bl=%d, lc=%d -> tt=%d\n",
+		 __func__, self->final_timeout, self->bytes_left,
+		 self->line_capacity, transmission_time);
 
 	/* We are allowed to transmit a maximum number of bytes again. */
 	self->bytes_left = self->line_capacity;
@@ -995,7 +987,7 @@ void irlap_resend_rejected_frames(struct irlap_cb *self, int command)
 		/* tx_skb = skb_clone( skb, GFP_ATOMIC); */
 		tx_skb = skb_copy(skb, GFP_ATOMIC);
 		if (!tx_skb) {
-			IRDA_DEBUG(0, "%s(), unable to copy\n", __func__);
+			pr_debug("%s(), unable to copy\n", __func__);
 			return;
 		}
 
@@ -1018,7 +1010,7 @@ void irlap_resend_rejected_frames(struct irlap_cb *self, int command)
 	 */
 	while (!skb_queue_empty(&self->txq)) {
 
-		IRDA_DEBUG(0, "%s(), sending additional frames!\n", __func__);
+		pr_debug("%s(), sending additional frames!\n", __func__);
 		if (self->window > 0) {
 			skb = skb_dequeue( &self->txq);
 			IRDA_ASSERT(skb != NULL, return;);
@@ -1058,7 +1050,7 @@ void irlap_resend_rejected_frame(struct irlap_cb *self, int command)
 		/* tx_skb = skb_clone( skb, GFP_ATOMIC); */
 		tx_skb = skb_copy(skb, GFP_ATOMIC);
 		if (!tx_skb) {
-			IRDA_DEBUG(0, "%s(), unable to copy\n", __func__);
+			pr_debug("%s(), unable to copy\n", __func__);
 			return;
 		}
 
@@ -1081,8 +1073,6 @@ void irlap_resend_rejected_frame(struct irlap_cb *self, int command)
 void irlap_send_ui_frame(struct irlap_cb *self, struct sk_buff *skb,
 			 __u8 caddr, int command)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -1141,8 +1131,6 @@ static inline void irlap_recv_i_frame(struct irlap_cb *self,
 static void irlap_recv_ui_frame(struct irlap_cb *self, struct sk_buff *skb,
 				struct irlap_info *info)
 {
-	IRDA_DEBUG( 4, "%s()\n", __func__);
-
 	info->pf = skb->data[1] & PF_BIT;      /* Final bit */
 
 	irlap_do_event(self, RECV_UI_FRAME, skb, info);
@@ -1160,8 +1148,6 @@ static void irlap_recv_frmr_frame(struct irlap_cb *self, struct sk_buff *skb,
 	__u8 *frame;
 	int w, x, y, z;
 
-	IRDA_DEBUG(0, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -1184,21 +1170,16 @@ static void irlap_recv_frmr_frame(struct irlap_cb *self, struct sk_buff *skb,
 	z = frame[3] & 0x08;
 
 	if (w) {
-		IRDA_DEBUG(0, "Rejected control field is undefined or not "
-		      "implemented.\n");
+		pr_debug("Rejected control field is undefined or not implemented\n");
 	}
 	if (x) {
-		IRDA_DEBUG(0, "Rejected control field was invalid because it "
-		      "contained a non permitted I field.\n");
+		pr_debug("Rejected control field was invalid because it contained a non permitted I field\n");
 	}
 	if (y) {
-		IRDA_DEBUG(0, "Received I field exceeded the maximum negotiated "
-		      "for the existing connection or exceeded the maximum "
-		      "this station supports if no connection exists.\n");
+		pr_debug("Received I field exceeded the maximum negotiated for the existing connection or exceeded the maximum this station supports if no connection exists\n");
 	}
 	if (z) {
-		IRDA_DEBUG(0, "Rejected control field control field contained an "
-		      "invalid Nr count.\n");
+		pr_debug("Rejected control field control field contained an invalid Nr count\n");
 	}
 	irlap_do_event(self, RECV_FRMR_RSP, skb, info);
 }
@@ -1254,8 +1235,6 @@ static void irlap_recv_test_frame(struct irlap_cb *self, struct sk_buff *skb,
 {
 	struct test_frame *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	if (!pskb_may_pull(skb, sizeof(*frame))) {
 		net_err_ratelimited("%s: frame too short!\n", __func__);
 		return;
@@ -1265,8 +1244,8 @@ static void irlap_recv_test_frame(struct irlap_cb *self, struct sk_buff *skb,
 	/* Broadcast frames must carry saddr and daddr fields */
 	if (info->caddr == CBROADCAST) {
 		if (skb->len < sizeof(struct test_frame)) {
-			IRDA_DEBUG(0, "%s() test frame too short!\n",
-				   __func__);
+			pr_debug("%s() test frame too short!\n",
+				 __func__);
 			return;
 		}
 
@@ -1346,8 +1325,8 @@ int irlap_driver_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	/*  First we check if this frame has a valid connection address */
 	if ((info.caddr != self->caddr) && (info.caddr != CBROADCAST)) {
-		IRDA_DEBUG(0, "%s(), wrong connection address!\n",
-			   __func__);
+		pr_debug("%s(), wrong connection address!\n",
+			 __func__);
 		goto out;
 	}
 	/*
diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c
index 6178e71f3a5..a26c401ef4a 100644
--- a/net/irda/irlmp.c
+++ b/net/irda/irlmp.c
@@ -83,7 +83,6 @@ const char *irlmp_reason_str(LM_REASON reason)
  */
 int __init irlmp_init(void)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__);
 	/* Initialize the irlmp structure. */
 	irlmp = kzalloc( sizeof(struct irlmp_cb), GFP_KERNEL);
 	if (irlmp == NULL)
@@ -207,8 +206,6 @@ EXPORT_SYMBOL(irlmp_open_lsap);
  */
 static void __irlmp_close_lsap(struct lsap_cb *self)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
 
@@ -267,9 +264,8 @@ void irlmp_close_lsap(struct lsap_cb *self)
 				      NULL);
 	}
 	if (!lsap) {
-		IRDA_DEBUG(0,
-		     "%s(), Looks like somebody has removed me already!\n",
-			   __func__);
+		pr_debug("%s(), Looks like somebody has removed me already!\n",
+			 __func__);
 		return;
 	}
 	__irlmp_close_lsap(self);
@@ -340,8 +336,6 @@ void irlmp_unregister_link(__u32 saddr)
 {
 	struct lap_cb *link;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	/* We must remove ourselves from the hashbin *first*. This ensure
 	 * that no more LSAPs will be open on this link and no discovery
 	 * will be triggered anymore. Jean II */
@@ -383,9 +377,8 @@ int irlmp_connect_request(struct lsap_cb *self, __u8 dlsap_sel,
 	IRDA_ASSERT(self != NULL, return -EBADR;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -EBADR;);
 
-	IRDA_DEBUG(2,
-	      "%s(), slsap_sel=%02x, dlsap_sel=%02x, saddr=%08x, daddr=%08x\n",
-	      __func__, self->slsap_sel, dlsap_sel, saddr, daddr);
+	pr_debug("%s(), slsap_sel=%02x, dlsap_sel=%02x, saddr=%08x, daddr=%08x\n",
+		 __func__, self->slsap_sel, dlsap_sel, saddr, daddr);
 
 	if (test_bit(0, &self->connected)) {
 		ret = -EISCONN;
@@ -429,7 +422,7 @@ int irlmp_connect_request(struct lsap_cb *self, __u8 dlsap_sel,
 		if (daddr != DEV_ADDR_ANY)
 			discovery = hashbin_find(irlmp->cachelog, daddr, NULL);
 		else {
-			IRDA_DEBUG(2, "%s(), no daddr\n", __func__);
+			pr_debug("%s(), no daddr\n", __func__);
 			discovery = (discovery_t *)
 				hashbin_get_first(irlmp->cachelog);
 		}
@@ -442,7 +435,7 @@ int irlmp_connect_request(struct lsap_cb *self, __u8 dlsap_sel,
 	}
 	lap = hashbin_lock_find(irlmp->links, saddr, NULL);
 	if (lap == NULL) {
-		IRDA_DEBUG(1, "%s(), Unable to find a usable link!\n", __func__);
+		pr_debug("%s(), Unable to find a usable link!\n", __func__);
 		ret = -EHOSTUNREACH;
 		goto err;
 	}
@@ -457,14 +450,15 @@ int irlmp_connect_request(struct lsap_cb *self, __u8 dlsap_sel,
 			 * disconnected yet (waiting for timeout in LAP).
 			 * Maybe we could give LAP a bit of help in this case.
 			 */
-			IRDA_DEBUG(0, "%s(), sorry, but I'm waiting for LAP to timeout!\n", __func__);
+			pr_debug("%s(), sorry, but I'm waiting for LAP to timeout!\n",
+				 __func__);
 			ret = -EAGAIN;
 			goto err;
 		}
 
 		/* LAP is already connected to a different node, and LAP
 		 * can only talk to one node at a time */
-		IRDA_DEBUG(0, "%s(), sorry, but link is busy!\n", __func__);
+		pr_debug("%s(), sorry, but link is busy!\n", __func__);
 		ret = -EBUSY;
 		goto err;
 	}
@@ -525,8 +519,8 @@ void irlmp_connect_indication(struct lsap_cb *self, struct sk_buff *skb)
 	IRDA_ASSERT(skb != NULL, return;);
 	IRDA_ASSERT(self->lap != NULL, return;);
 
-	IRDA_DEBUG(2, "%s(), slsap_sel=%02x, dlsap_sel=%02x\n",
-		   __func__, self->slsap_sel, self->dlsap_sel);
+	pr_debug("%s(), slsap_sel=%02x, dlsap_sel=%02x\n",
+		 __func__, self->slsap_sel, self->dlsap_sel);
 
 	/* Note : self->lap is set in irlmp_link_data_indication(),
 	 * (case CONNECT_CMD:) because we have no way to set it here.
@@ -566,8 +560,8 @@ int irlmp_connect_response(struct lsap_cb *self, struct sk_buff *userdata)
 	/* We set the connected bit and move the lsap to the connected list
 	 * in the state machine itself. Jean II */
 
-	IRDA_DEBUG(2, "%s(), slsap_sel=%02x, dlsap_sel=%02x\n",
-		   __func__, self->slsap_sel, self->dlsap_sel);
+	pr_debug("%s(), slsap_sel=%02x, dlsap_sel=%02x\n",
+		 __func__, self->slsap_sel, self->dlsap_sel);
 
 	/* Make room for MUX control header (3 bytes) */
 	IRDA_ASSERT(skb_headroom(userdata) >= LMP_CONTROL_HEADER, return -1;);
@@ -593,8 +587,6 @@ void irlmp_connect_confirm(struct lsap_cb *self, struct sk_buff *skb)
 	int lap_header_size;
 	int max_seg_size;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(skb != NULL, return;);
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
@@ -606,8 +598,8 @@ void irlmp_connect_confirm(struct lsap_cb *self, struct sk_buff *skb)
 	lap_header_size = IRLAP_GET_HEADER_SIZE(self->lap->irlap);
 	max_header_size = LMP_HEADER + lap_header_size;
 
-	IRDA_DEBUG(2, "%s(), max_header_size=%d\n",
-		   __func__, max_header_size);
+	pr_debug("%s(), max_header_size=%d\n",
+		 __func__, max_header_size);
 
 	/* Hide LMP_CONTROL_HEADER header from layer above */
 	skb_pull(skb, LMP_CONTROL_HEADER);
@@ -633,16 +625,14 @@ struct lsap_cb *irlmp_dup(struct lsap_cb *orig, void *instance)
 	struct lsap_cb *new;
 	unsigned long flags;
 
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	spin_lock_irqsave(&irlmp->unconnected_lsaps->hb_spinlock, flags);
 
 	/* Only allowed to duplicate unconnected LSAP's, and only LSAPs
 	 * that have received a connect indication. Jean II */
 	if ((!hashbin_find(irlmp->unconnected_lsaps, (long) orig, NULL)) ||
 	    (orig->lap == NULL)) {
-		IRDA_DEBUG(0, "%s(), invalid LSAP (wrong state)\n",
-			   __func__);
+		pr_debug("%s(), invalid LSAP (wrong state)\n",
+			 __func__);
 		spin_unlock_irqrestore(&irlmp->unconnected_lsaps->hb_spinlock,
 				       flags);
 		return NULL;
@@ -651,7 +641,7 @@ struct lsap_cb *irlmp_dup(struct lsap_cb *orig, void *instance)
 	/* Allocate a new instance */
 	new = kmemdup(orig, sizeof(*new), GFP_ATOMIC);
 	if (!new)  {
-		IRDA_DEBUG(0, "%s(), unable to kmalloc\n", __func__);
+		pr_debug("%s(), unable to kmalloc\n", __func__);
 		spin_unlock_irqrestore(&irlmp->unconnected_lsaps->hb_spinlock,
 				       flags);
 		return NULL;
@@ -697,7 +687,7 @@ int irlmp_disconnect_request(struct lsap_cb *self, struct sk_buff *userdata)
 	 * and us that might mess up the hashbins below. This fixes it.
 	 * Jean II */
 	if (! test_and_clear_bit(0, &self->connected)) {
-		IRDA_DEBUG(0, "%s(), already disconnected!\n", __func__);
+		pr_debug("%s(), already disconnected!\n", __func__);
 		dev_kfree_skb(userdata);
 		return -1;
 	}
@@ -751,20 +741,20 @@ void irlmp_disconnect_indication(struct lsap_cb *self, LM_REASON reason,
 {
 	struct lsap_cb *lsap;
 
-	IRDA_DEBUG(1, "%s(), reason=%s [%d]\n", __func__,
-		   irlmp_reason_str(reason), reason);
+	pr_debug("%s(), reason=%s [%d]\n", __func__,
+		 irlmp_reason_str(reason), reason);
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
 
-	IRDA_DEBUG(3, "%s(), slsap_sel=%02x, dlsap_sel=%02x\n",
-		   __func__, self->slsap_sel, self->dlsap_sel);
+	pr_debug("%s(), slsap_sel=%02x, dlsap_sel=%02x\n",
+		 __func__, self->slsap_sel, self->dlsap_sel);
 
 	/* Already disconnected ?
 	 * There is a race condition between irlmp_disconnect_request()
 	 * and us that might mess up the hashbins below. This fixes it.
 	 * Jean II */
 	if (! test_and_clear_bit(0, &self->connected)) {
-		IRDA_DEBUG(0, "%s(), already disconnected!\n", __func__);
+		pr_debug("%s(), already disconnected!\n", __func__);
 		return;
 	}
 
@@ -797,7 +787,7 @@ void irlmp_disconnect_indication(struct lsap_cb *self, LM_REASON reason,
 		self->notify.disconnect_indication(self->notify.instance,
 						   self, reason, skb);
 	} else {
-		IRDA_DEBUG(0, "%s(), no handler\n", __func__);
+		pr_debug("%s(), no handler\n", __func__);
 	}
 }
 
@@ -968,8 +958,6 @@ irlmp_notify_client(irlmp_client_t *client,
 	int	number;			/* Number of nodes in the log */
 	int	i;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	/* Check if client wants or not partial/selective log (optimisation) */
 	if (!client->disco_callback)
 		return;
@@ -1019,8 +1007,6 @@ void irlmp_discovery_confirm(hashbin_t *log, DISCOVERY_MODE mode)
 	irlmp_client_t *client;
 	irlmp_client_t *client_next;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(log != NULL, return;);
 
 	if (!(HASHBIN_GET_SIZE(log)))
@@ -1054,8 +1040,6 @@ void irlmp_discovery_expiry(discinfo_t *expiries, int number)
 	irlmp_client_t *client_next;
 	int		i;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(expiries != NULL, return;);
 
 	/* For each client - notify callback may touch client list */
@@ -1088,8 +1072,6 @@ void irlmp_discovery_expiry(discinfo_t *expiries, int number)
  */
 discovery_t *irlmp_get_discovery_response(void)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(irlmp != NULL, return NULL;);
 
 	put_unaligned(irlmp->hints.word, (__u16 *)irlmp->discovery_rsp.data.hints);
@@ -1166,8 +1148,6 @@ int irlmp_udata_request(struct lsap_cb *self, struct sk_buff *userdata)
 {
 	int	ret;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(userdata != NULL, return -1;);
 
 	/* Make room for MUX header */
@@ -1190,8 +1170,6 @@ int irlmp_udata_request(struct lsap_cb *self, struct sk_buff *userdata)
  */
 void irlmp_udata_indication(struct lsap_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -1217,8 +1195,6 @@ int irlmp_connless_data_request(struct lsap_cb *self, struct sk_buff *userdata,
 	struct sk_buff *clone_skb;
 	struct lap_cb *lap;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(userdata != NULL, return -1;);
 
 	/* Make room for MUX and PID header */
@@ -1268,8 +1244,6 @@ int irlmp_connless_data_request(struct lsap_cb *self, struct sk_buff *userdata,
 #ifdef CONFIG_IRDA_ULTRA
 void irlmp_connless_data_indication(struct lsap_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -1311,7 +1285,7 @@ void irlmp_status_indication(struct lap_cb *self,
 			curr->notify.status_indication(curr->notify.instance,
 						       link, lock);
 		else
-			IRDA_DEBUG(2, "%s(), no handler\n", __func__);
+			pr_debug("%s(), no handler\n", __func__);
 
 		curr = next;
 	}
@@ -1339,7 +1313,7 @@ void irlmp_flow_indication(struct lap_cb *self, LOCAL_FLOW flow)
 	/* Get the number of lsap. That's the only safe way to know
 	 * that we have looped around... - Jean II */
 	lsap_todo = HASHBIN_GET_SIZE(self->lsaps);
-	IRDA_DEBUG(4, "%s() : %d lsaps to scan\n", __func__, lsap_todo);
+	pr_debug("%s() : %d lsaps to scan\n", __func__, lsap_todo);
 
 	/* Poll lsap in order until the queue is full or until we
 	 * tried them all.
@@ -1358,14 +1332,16 @@ void irlmp_flow_indication(struct lap_cb *self, LOCAL_FLOW flow)
 		/* Uh-oh... Paranoia */
 		if(curr == NULL)
 			break;
-		IRDA_DEBUG(4, "%s() : curr is %p, next was %p and is now %p, still %d to go - queue len = %d\n", __func__, curr, next, self->flow_next, lsap_todo, IRLAP_GET_TX_QUEUE_LEN(self->irlap));
+		pr_debug("%s() : curr is %p, next was %p and is now %p, still %d to go - queue len = %d\n",
+			 __func__, curr, next, self->flow_next, lsap_todo,
+			 IRLAP_GET_TX_QUEUE_LEN(self->irlap));
 
 		/* Inform lsap user that it can send one more packet. */
 		if (curr->notify.flow_indication != NULL)
 			curr->notify.flow_indication(curr->notify.instance,
 						     curr, flow);
 		else
-			IRDA_DEBUG(1, "%s(), no handler\n", __func__);
+			pr_debug("%s(), no handler\n", __func__);
 	}
 }
 
@@ -1386,32 +1362,30 @@ __u8 *irlmp_hint_to_service(__u8 *hint)
 	 * since we currently only support 2 hint bytes
 	 */
 	service = kmalloc(16, GFP_ATOMIC);
-	if (!service) {
-		IRDA_DEBUG(1, "%s(), Unable to kmalloc!\n", __func__);
+	if (!service)
 		return NULL;
-	}
 
 	if (!hint[0]) {
-		IRDA_DEBUG(1, "<None>\n");
+		pr_debug("<None>\n");
 		kfree(service);
 		return NULL;
 	}
 	if (hint[0] & HINT_PNP)
-		IRDA_DEBUG(1, "PnP Compatible ");
+		pr_debug("PnP Compatible ");
 	if (hint[0] & HINT_PDA)
-		IRDA_DEBUG(1, "PDA/Palmtop ");
+		pr_debug("PDA/Palmtop ");
 	if (hint[0] & HINT_COMPUTER)
-		IRDA_DEBUG(1, "Computer ");
+		pr_debug("Computer ");
 	if (hint[0] & HINT_PRINTER) {
-		IRDA_DEBUG(1, "Printer ");
+		pr_debug("Printer ");
 		service[i++] = S_PRINTER;
 	}
 	if (hint[0] & HINT_MODEM)
-		IRDA_DEBUG(1, "Modem ");
+		pr_debug("Modem ");
 	if (hint[0] & HINT_FAX)
-		IRDA_DEBUG(1, "Fax ");
+		pr_debug("Fax ");
 	if (hint[0] & HINT_LAN) {
-		IRDA_DEBUG(1, "LAN Access ");
+		pr_debug("LAN Access ");
 		service[i++] = S_LAN;
 	}
 	/*
@@ -1421,22 +1395,22 @@ __u8 *irlmp_hint_to_service(__u8 *hint)
 	 */
 	if (hint[0] & HINT_EXTENSION) {
 		if (hint[1] & HINT_TELEPHONY) {
-			IRDA_DEBUG(1, "Telephony ");
+			pr_debug("Telephony ");
 			service[i++] = S_TELEPHONY;
 		}
 		if (hint[1] & HINT_FILE_SERVER)
-			IRDA_DEBUG(1, "File Server ");
+			pr_debug("File Server ");
 
 		if (hint[1] & HINT_COMM) {
-			IRDA_DEBUG(1, "IrCOMM ");
+			pr_debug("IrCOMM ");
 			service[i++] = S_COMM;
 		}
 		if (hint[1] & HINT_OBEX) {
-			IRDA_DEBUG(1, "IrOBEX ");
+			pr_debug("IrOBEX ");
 			service[i++] = S_OBEX;
 		}
 	}
-	IRDA_DEBUG(1, "\n");
+	pr_debug("\n");
 
 	/* So that client can be notified about any discovery */
 	service[i++] = S_ANY;
@@ -1489,14 +1463,13 @@ void *irlmp_register_service(__u16 hints)
 {
 	irlmp_service_t *service;
 
-	IRDA_DEBUG(4, "%s(), hints = %04x\n", __func__, hints);
+	pr_debug("%s(), hints = %04x\n", __func__, hints);
 
 	/* Make a new registration */
 	service = kmalloc(sizeof(irlmp_service_t), GFP_ATOMIC);
-	if (!service) {
-		IRDA_DEBUG(1, "%s(), Unable to kmalloc!\n", __func__);
+	if (!service)
 		return NULL;
-	}
+
 	service->hints.word = hints;
 	hashbin_insert(irlmp->services, (irda_queue_t *) service,
 		       (long) service, NULL);
@@ -1519,15 +1492,13 @@ int irlmp_unregister_service(void *handle)
 	irlmp_service_t *service;
 	unsigned long flags;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	if (!handle)
 		return -1;
 
 	/* Caller may call with invalid handle (it's legal) - Jean II */
 	service = hashbin_lock_find(irlmp->services, (long) handle, NULL);
 	if (!service) {
-		IRDA_DEBUG(1, "%s(), Unknown service!\n", __func__);
+		pr_debug("%s(), Unknown service!\n", __func__);
 		return -1;
 	}
 
@@ -1564,15 +1535,12 @@ void *irlmp_register_client(__u16 hint_mask, DISCOVERY_CALLBACK1 disco_clb,
 {
 	irlmp_client_t *client;
 
-	IRDA_DEBUG(1, "%s()\n", __func__);
 	IRDA_ASSERT(irlmp != NULL, return NULL;);
 
 	/* Make a new registration */
 	client = kmalloc(sizeof(irlmp_client_t), GFP_ATOMIC);
-	if (!client) {
-		IRDA_DEBUG( 1, "%s(), Unable to kmalloc!\n", __func__);
+	if (!client)
 		return NULL;
-	}
 
 	/* Register the details */
 	client->hint_mask.word = hint_mask;
@@ -1606,7 +1574,7 @@ int irlmp_update_client(void *handle, __u16 hint_mask,
 
 	client = hashbin_lock_find(irlmp->clients, (long) handle, NULL);
 	if (!client) {
-		IRDA_DEBUG(1, "%s(), Unknown client!\n", __func__);
+		pr_debug("%s(), Unknown client!\n", __func__);
 		return -1;
 	}
 
@@ -1629,19 +1597,17 @@ int irlmp_unregister_client(void *handle)
 {
 	struct irlmp_client *client;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	if (!handle)
 		return -1;
 
 	/* Caller may call with invalid handle (it's legal) - Jean II */
 	client = hashbin_lock_find(irlmp->clients, (long) handle, NULL);
 	if (!client) {
-		IRDA_DEBUG(1, "%s(), Unknown client!\n", __func__);
+		pr_debug("%s(), Unknown client!\n", __func__);
 		return -1;
 	}
 
-	IRDA_DEBUG(4, "%s(), removing client!\n", __func__);
+	pr_debug("%s(), removing client!\n", __func__);
 	hashbin_remove_this(irlmp->clients, (irda_queue_t *) client);
 	kfree(client);
 
@@ -1670,8 +1636,6 @@ static int irlmp_slsap_inuse(__u8 slsap_sel)
 	IRDA_ASSERT(irlmp->magic == LMP_MAGIC, return TRUE;);
 	IRDA_ASSERT(slsap_sel != LSAP_ANY, return TRUE;);
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 #ifdef CONFIG_IRDA_ULTRA
 	/* Accept all bindings to the connectionless LSAP */
 	if (slsap_sel == LSAP_CONNLESS)
@@ -1705,8 +1669,8 @@ static int irlmp_slsap_inuse(__u8 slsap_sel)
 				    goto errlsap;);
 
 			if ((self->slsap_sel == slsap_sel)) {
-				IRDA_DEBUG(4, "Source LSAP selector=%02x in use\n",
-					   self->slsap_sel);
+				pr_debug("Source LSAP selector=%02x in use\n",
+					 self->slsap_sel);
 				goto errlsap;
 			}
 			self = (struct lsap_cb*) hashbin_get_next(lap->lsaps);
@@ -1730,8 +1694,8 @@ static int irlmp_slsap_inuse(__u8 slsap_sel)
 	while (self != NULL) {
 		IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, goto erruncon;);
 		if ((self->slsap_sel == slsap_sel)) {
-			IRDA_DEBUG(4, "Source LSAP selector=%02x in use (unconnected)\n",
-				   self->slsap_sel);
+			pr_debug("Source LSAP selector=%02x in use (unconnected)\n",
+				 self->slsap_sel);
 			goto erruncon;
 		}
 		self = (struct lsap_cb*) hashbin_get_next(irlmp->unconnected_lsaps);
@@ -1811,8 +1775,8 @@ static __u8 irlmp_find_free_slsap(void)
 
 	/* Got it ! */
 	lsap_sel = irlmp->last_lsap_sel;
-	IRDA_DEBUG(4, "%s(), found free lsap_sel=%02x\n",
-		   __func__, lsap_sel);
+	pr_debug("%s(), found free lsap_sel=%02x\n",
+		 __func__, lsap_sel);
 
 	return lsap_sel;
 }
@@ -1830,26 +1794,27 @@ LM_REASON irlmp_convert_lap_reason( LAP_REASON lap_reason)
 
 	switch (lap_reason) {
 	case LAP_DISC_INDICATION: /* Received a disconnect request from peer */
-		IRDA_DEBUG( 1, "%s(), LAP_DISC_INDICATION\n", __func__);
+		pr_debug("%s(), LAP_DISC_INDICATION\n", __func__);
 		reason = LM_USER_REQUEST;
 		break;
 	case LAP_NO_RESPONSE:    /* To many retransmits without response */
-		IRDA_DEBUG( 1, "%s(), LAP_NO_RESPONSE\n", __func__);
+		pr_debug("%s(), LAP_NO_RESPONSE\n", __func__);
 		reason = LM_LAP_DISCONNECT;
 		break;
 	case LAP_RESET_INDICATION:
-		IRDA_DEBUG( 1, "%s(), LAP_RESET_INDICATION\n", __func__);
+		pr_debug("%s(), LAP_RESET_INDICATION\n", __func__);
 		reason = LM_LAP_RESET;
 		break;
 	case LAP_FOUND_NONE:
 	case LAP_MEDIA_BUSY:
 	case LAP_PRIMARY_CONFLICT:
-		IRDA_DEBUG(1, "%s(), LAP_FOUND_NONE, LAP_MEDIA_BUSY or LAP_PRIMARY_CONFLICT\n", __func__);
+		pr_debug("%s(), LAP_FOUND_NONE, LAP_MEDIA_BUSY or LAP_PRIMARY_CONFLICT\n",
+			 __func__);
 		reason = LM_CONNECT_FAILURE;
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown IrLAP disconnect reason %d!\n",
-			   __func__, lap_reason);
+		pr_debug("%s(), Unknown IrLAP disconnect reason %d!\n",
+			 __func__, lap_reason);
 		reason = LM_LAP_DISCONNECT;
 		break;
 	}
diff --git a/net/irda/irlmp_event.c b/net/irda/irlmp_event.c
index 30e51f9f4ba..22c019ccd4a 100644
--- a/net/irda/irlmp_event.c
+++ b/net/irda/irlmp_event.c
@@ -120,7 +120,7 @@ static inline void irlmp_next_lap_state(struct lap_cb *self,
 					IRLMP_STATE state)
 {
 	/*
-	IRDA_DEBUG(4, "%s(), LMP LAP = %s\n", __func__, irlmp_state[state]);
+	  pr_debug("%s(), LMP LAP = %s\n", __func__, irlmp_state[state]);
 	*/
 	self->lap_state = state;
 }
@@ -130,7 +130,7 @@ static inline void irlmp_next_lsap_state(struct lsap_cb *self,
 {
 	/*
 	IRDA_ASSERT(self != NULL, return;);
-	IRDA_DEBUG(4, "%s(), LMP LSAP = %s\n", __func__, irlsap_state[state]);
+	pr_debug("%s(), LMP LSAP = %s\n", __func__, irlsap_state[state]);
 	*/
 	self->lsap_state = state;
 }
@@ -142,8 +142,8 @@ int irlmp_do_lsap_event(struct lsap_cb *self, IRLMP_EVENT event,
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -1;);
 
-	IRDA_DEBUG(4, "%s(), EVENT = %s, STATE = %s\n",
-		__func__, irlmp_event[event], irlsap_state[ self->lsap_state]);
+	pr_debug("%s(), EVENT = %s, STATE = %s\n",
+		 __func__, irlmp_event[event], irlsap_state[self->lsap_state]);
 
 	return (*lsap_state[self->lsap_state]) (self, event, skb);
 }
@@ -160,17 +160,15 @@ void irlmp_do_lap_event(struct lap_cb *self, IRLMP_EVENT event,
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 
-	IRDA_DEBUG(4, "%s(), EVENT = %s, STATE = %s\n", __func__,
-		   irlmp_event[event],
-		   irlmp_state[self->lap_state]);
+	pr_debug("%s(), EVENT = %s, STATE = %s\n", __func__,
+		 irlmp_event[event],
+		 irlmp_state[self->lap_state]);
 
 	(*lap_state[self->lap_state]) (self, event, skb);
 }
 
 void irlmp_discovery_timer_expired(void *data)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	/* We always cleanup the log (active & passive discovery) */
 	irlmp_do_expiry();
 
@@ -184,8 +182,6 @@ void irlmp_watchdog_timer_expired(void *data)
 {
 	struct lsap_cb *self = (struct lsap_cb *) data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
 
@@ -196,8 +192,6 @@ void irlmp_idle_timer_expired(void *data)
 {
 	struct lap_cb *self = (struct lap_cb *) data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 
@@ -256,7 +250,6 @@ irlmp_do_all_lsap_event(hashbin_t *	lsap_hashbin,
 static void irlmp_state_standby(struct lap_cb *self, IRLMP_EVENT event,
 				struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
 	IRDA_ASSERT(self->irlap != NULL, return;);
 
 	switch (event) {
@@ -276,7 +269,7 @@ static void irlmp_state_standby(struct lap_cb *self, IRLMP_EVENT event,
 		irlap_connect_response(self->irlap, skb);
 		break;
 	case LM_LAP_CONNECT_REQUEST:
-		IRDA_DEBUG(4, "%s() LS_CONNECT_REQUEST\n", __func__);
+		pr_debug("%s() LS_CONNECT_REQUEST\n", __func__);
 
 		irlmp_next_lap_state(self, LAP_U_CONNECT);
 
@@ -284,14 +277,14 @@ static void irlmp_state_standby(struct lap_cb *self, IRLMP_EVENT event,
 		irlap_connect_request(self->irlap, self->daddr, NULL, 0);
 		break;
 	case LM_LAP_DISCONNECT_INDICATION:
-		IRDA_DEBUG(4, "%s(), Error LM_LAP_DISCONNECT_INDICATION\n",
-			   __func__);
+		pr_debug("%s(), Error LM_LAP_DISCONNECT_INDICATION\n",
+			 __func__);
 
 		irlmp_next_lap_state(self, LAP_STANDBY);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s\n",
-			   __func__, irlmp_event[event]);
+		pr_debug("%s(), Unknown event %s\n",
+			 __func__, irlmp_event[event]);
 		break;
 	}
 }
@@ -306,7 +299,7 @@ static void irlmp_state_standby(struct lap_cb *self, IRLMP_EVENT event,
 static void irlmp_state_u_connect(struct lap_cb *self, IRLMP_EVENT event,
 				  struct sk_buff *skb)
 {
-	IRDA_DEBUG(2, "%s(), event=%s\n", __func__, irlmp_event[event]);
+	pr_debug("%s(), event=%s\n", __func__, irlmp_event[event]);
 
 	switch (event) {
 	case LM_LAP_CONNECT_INDICATION:
@@ -326,7 +319,7 @@ static void irlmp_state_u_connect(struct lap_cb *self, IRLMP_EVENT event,
 		 * the lsaps may already have gone. This avoid getting stuck
 		 * forever in LAP_ACTIVE state - Jean II */
 		if (HASHBIN_GET_SIZE(self->lsaps) == 0) {
-			IRDA_DEBUG(0, "%s() NO LSAPs !\n",  __func__);
+			pr_debug("%s() NO LSAPs !\n",  __func__);
 			irlmp_start_idle_timer(self, LM_IDLE_TIMEOUT);
 		}
 		break;
@@ -344,12 +337,12 @@ static void irlmp_state_u_connect(struct lap_cb *self, IRLMP_EVENT event,
 		 * the lsaps may already have gone. This avoid getting stuck
 		 * forever in LAP_ACTIVE state - Jean II */
 		if (HASHBIN_GET_SIZE(self->lsaps) == 0) {
-			IRDA_DEBUG(0, "%s() NO LSAPs !\n",  __func__);
+			pr_debug("%s() NO LSAPs !\n",  __func__);
 			irlmp_start_idle_timer(self, LM_IDLE_TIMEOUT);
 		}
 		break;
 	case LM_LAP_DISCONNECT_INDICATION:
-		IRDA_DEBUG(4, "%s(), LM_LAP_DISCONNECT_INDICATION\n",  __func__);
+		pr_debug("%s(), LM_LAP_DISCONNECT_INDICATION\n",  __func__);
 		irlmp_next_lap_state(self, LAP_STANDBY);
 
 		/* Send disconnect event to all LSAPs using this link */
@@ -357,7 +350,7 @@ static void irlmp_state_u_connect(struct lap_cb *self, IRLMP_EVENT event,
 					LM_LAP_DISCONNECT_INDICATION);
 		break;
 	case LM_LAP_DISCONNECT_REQUEST:
-		IRDA_DEBUG(4, "%s(), LM_LAP_DISCONNECT_REQUEST\n",  __func__);
+		pr_debug("%s(), LM_LAP_DISCONNECT_REQUEST\n",  __func__);
 
 		/* One of the LSAP did timeout or was closed, if it was
 		 * the last one, try to get out of here - Jean II */
@@ -366,7 +359,7 @@ static void irlmp_state_u_connect(struct lap_cb *self, IRLMP_EVENT event,
 		}
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s\n",
+		pr_debug("%s(), Unknown event %s\n",
 			 __func__, irlmp_event[event]);
 		break;
 	}
@@ -381,11 +374,9 @@ static void irlmp_state_u_connect(struct lap_cb *self, IRLMP_EVENT event,
 static void irlmp_state_active(struct lap_cb *self, IRLMP_EVENT event,
 			       struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	switch (event) {
 	case LM_LAP_CONNECT_REQUEST:
-		IRDA_DEBUG(4, "%s(), LS_CONNECT_REQUEST\n", __func__);
+		pr_debug("%s(), LS_CONNECT_REQUEST\n", __func__);
 
 		/*
 		 * IrLAP may have a pending disconnect. We tried to close
@@ -467,7 +458,7 @@ static void irlmp_state_active(struct lap_cb *self, IRLMP_EVENT event,
 		irlmp_do_expiry();
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s\n",
+		pr_debug("%s(), Unknown event %s\n",
 			 __func__, irlmp_event[event]);
 		break;
 	}
@@ -490,8 +481,6 @@ static int irlmp_state_disconnected(struct lsap_cb *self, IRLMP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -1;);
 
@@ -505,7 +494,7 @@ static int irlmp_state_disconnected(struct lsap_cb *self, IRLMP_EVENT event,
 		break;
 #endif /* CONFIG_IRDA_ULTRA */
 	case LM_CONNECT_REQUEST:
-		IRDA_DEBUG(4, "%s(), LM_CONNECT_REQUEST\n", __func__);
+		pr_debug("%s(), LM_CONNECT_REQUEST\n", __func__);
 
 		if (self->conn_skb) {
 			net_warn_ratelimited("%s: busy with another request!\n",
@@ -551,8 +540,8 @@ static int irlmp_state_disconnected(struct lsap_cb *self, IRLMP_EVENT event,
 		irlmp_do_lap_event(self->lap, LM_LAP_CONNECT_REQUEST, NULL);
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %s on LSAP %#02x\n",
-			   __func__, irlmp_event[event], self->slsap_sel);
+		pr_debug("%s(), Unknown event %s on LSAP %#02x\n",
+			 __func__, irlmp_event[event], self->slsap_sel);
 		break;
 	}
 	return ret;
@@ -570,8 +559,6 @@ static int irlmp_state_connect(struct lsap_cb *self, IRLMP_EVENT event,
 	struct lsap_cb *lsap;
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -1;);
 
@@ -603,7 +590,7 @@ static int irlmp_state_connect(struct lsap_cb *self, IRLMP_EVENT event,
 	case LM_WATCHDOG_TIMEOUT:
 		/* May happen, who knows...
 		 * Jean II */
-		IRDA_DEBUG(0, "%s() WATCHDOG_TIMEOUT!\n",  __func__);
+		pr_debug("%s() WATCHDOG_TIMEOUT!\n",  __func__);
 
 		/* Disconnect, get out... - Jean II */
 		self->lap = NULL;
@@ -613,8 +600,8 @@ static int irlmp_state_connect(struct lsap_cb *self, IRLMP_EVENT event,
 	default:
 		/* LM_LAP_DISCONNECT_INDICATION : Should never happen, we
 		 * are *not* yet bound to the IrLAP link. Jean II */
-		IRDA_DEBUG(0, "%s(), Unknown event %s on LSAP %#02x\n",
-			   __func__, irlmp_event[event], self->slsap_sel);
+		pr_debug("%s(), Unknown event %s on LSAP %#02x\n",
+			 __func__, irlmp_event[event], self->slsap_sel);
 		break;
 	}
 	return ret;
@@ -632,8 +619,6 @@ static int irlmp_state_connect_pend(struct lsap_cb *self, IRLMP_EVENT event,
 	struct sk_buff *tx_skb;
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -1;);
 
@@ -642,17 +627,17 @@ static int irlmp_state_connect_pend(struct lsap_cb *self, IRLMP_EVENT event,
 		/* Keep state */
 		break;
 	case LM_CONNECT_RESPONSE:
-		IRDA_DEBUG(0, "%s(), LM_CONNECT_RESPONSE, "
-			   "no indication issued yet\n",  __func__);
+		pr_debug("%s(), LM_CONNECT_RESPONSE, no indication issued yet\n",
+			 __func__);
 		/* Keep state */
 		break;
 	case LM_DISCONNECT_REQUEST:
-		IRDA_DEBUG(0, "%s(), LM_DISCONNECT_REQUEST, "
-			   "not yet bound to IrLAP connection\n",  __func__);
+		pr_debug("%s(), LM_DISCONNECT_REQUEST, not yet bound to IrLAP connection\n",
+			 __func__);
 		/* Keep state */
 		break;
 	case LM_LAP_CONNECT_CONFIRM:
-		IRDA_DEBUG(4, "%s(), LS_CONNECT_CONFIRM\n",  __func__);
+		pr_debug("%s(), LS_CONNECT_CONFIRM\n",  __func__);
 		irlmp_next_lsap_state(self, LSAP_CONNECT);
 
 		tx_skb = self->conn_skb;
@@ -666,7 +651,7 @@ static int irlmp_state_connect_pend(struct lsap_cb *self, IRLMP_EVENT event,
 		/* Will happen in some rare cases because of a race condition.
 		 * Just make sure we don't stay there forever...
 		 * Jean II */
-		IRDA_DEBUG(0, "%s() WATCHDOG_TIMEOUT!\n",  __func__);
+		pr_debug("%s() WATCHDOG_TIMEOUT!\n",  __func__);
 
 		/* Go back to disconnected mode, keep the socket waiting */
 		self->lap = NULL;
@@ -679,8 +664,8 @@ static int irlmp_state_connect_pend(struct lsap_cb *self, IRLMP_EVENT event,
 	default:
 		/* LM_LAP_DISCONNECT_INDICATION : Should never happen, we
 		 * are *not* yet bound to the IrLAP link. Jean II */
-		IRDA_DEBUG(0, "%s(), Unknown event %s on LSAP %#02x\n",
-			   __func__, irlmp_event[event], self->slsap_sel);
+		pr_debug("%s(), Unknown event %s on LSAP %#02x\n",
+			 __func__, irlmp_event[event], self->slsap_sel);
 		break;
 	}
 	return ret;
@@ -698,8 +683,6 @@ static int irlmp_state_dtr(struct lsap_cb *self, IRLMP_EVENT event,
 	LM_REASON reason;
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -1;);
 	IRDA_ASSERT(self->lap != NULL, return -1;);
@@ -721,13 +704,13 @@ static int irlmp_state_dtr(struct lsap_cb *self, IRLMP_EVENT event,
 		irlmp_udata_indication(self, skb);
 		break;
 	case LM_CONNECT_REQUEST:
-		IRDA_DEBUG(0, "%s(), LM_CONNECT_REQUEST, "
-			   "error, LSAP already connected\n", __func__);
+		pr_debug("%s(), LM_CONNECT_REQUEST, error, LSAP already connected\n",
+			 __func__);
 		/* Keep state */
 		break;
 	case LM_CONNECT_RESPONSE:
-		IRDA_DEBUG(0, "%s(), LM_CONNECT_RESPONSE, "
-			   "error, LSAP already connected\n", __func__);
+		pr_debug("%s(), LM_CONNECT_RESPONSE, error, LSAP already connected\n",
+			 __func__);
 		/* Keep state */
 		break;
 	case LM_DISCONNECT_REQUEST:
@@ -739,8 +722,8 @@ static int irlmp_state_dtr(struct lsap_cb *self, IRLMP_EVENT event,
 
 		/* Try to close the LAP connection if its still there */
 		if (self->lap) {
-			IRDA_DEBUG(4, "%s(), trying to close IrLAP\n",
-				   __func__);
+			pr_debug("%s(), trying to close IrLAP\n",
+				 __func__);
 			irlmp_do_lap_event(self->lap,
 					   LM_LAP_DISCONNECT_REQUEST,
 					   NULL);
@@ -764,14 +747,14 @@ static int irlmp_state_dtr(struct lsap_cb *self, IRLMP_EVENT event,
 		reason = skb->data[3];
 
 		 /* Try to close the LAP connection */
-		IRDA_DEBUG(4, "%s(), trying to close IrLAP\n", __func__);
+		pr_debug("%s(), trying to close IrLAP\n", __func__);
 		irlmp_do_lap_event(self->lap, LM_LAP_DISCONNECT_REQUEST, NULL);
 
 		irlmp_disconnect_indication(self, reason, skb);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s on LSAP %#02x\n",
-			   __func__, irlmp_event[event], self->slsap_sel);
+		pr_debug("%s(), Unknown event %s on LSAP %#02x\n",
+			 __func__, irlmp_event[event], self->slsap_sel);
 		break;
 	}
 	return ret;
@@ -793,8 +776,6 @@ static int irlmp_state_setup(struct lsap_cb *self, IRLMP_EVENT event,
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -1;);
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	switch (event) {
 	case LM_CONNECT_CONFIRM:
 		irlmp_next_lsap_state(self, LSAP_DATA_TRANSFER_READY);
@@ -814,7 +795,7 @@ static int irlmp_state_setup(struct lsap_cb *self, IRLMP_EVENT event,
 		reason = skb->data[3];
 
 		 /* Try to close the LAP connection */
-		IRDA_DEBUG(4, "%s(), trying to close IrLAP\n",  __func__);
+		pr_debug("%s(), trying to close IrLAP\n",  __func__);
 		irlmp_do_lap_event(self->lap, LM_LAP_DISCONNECT_REQUEST, NULL);
 
 		irlmp_disconnect_indication(self, reason, skb);
@@ -832,7 +813,7 @@ static int irlmp_state_setup(struct lsap_cb *self, IRLMP_EVENT event,
 		irlmp_disconnect_indication(self, reason, skb);
 		break;
 	case LM_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(0, "%s() WATCHDOG_TIMEOUT!\n", __func__);
+		pr_debug("%s() WATCHDOG_TIMEOUT!\n", __func__);
 
 		IRDA_ASSERT(self->lap != NULL, return -1;);
 		irlmp_do_lap_event(self->lap, LM_LAP_DISCONNECT_REQUEST, NULL);
@@ -841,8 +822,8 @@ static int irlmp_state_setup(struct lsap_cb *self, IRLMP_EVENT event,
 		irlmp_disconnect_indication(self, LM_CONNECT_FAILURE, NULL);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s on LSAP %#02x\n",
-			   __func__, irlmp_event[event], self->slsap_sel);
+		pr_debug("%s(), Unknown event %s on LSAP %#02x\n",
+			 __func__, irlmp_event[event], self->slsap_sel);
 		break;
 	}
 	return ret;
@@ -863,8 +844,6 @@ static int irlmp_state_setup_pend(struct lsap_cb *self, IRLMP_EVENT event,
 	LM_REASON reason;
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(irlmp != NULL, return -1;);
 
@@ -883,7 +862,7 @@ static int irlmp_state_setup_pend(struct lsap_cb *self, IRLMP_EVENT event,
 		irlmp_next_lsap_state(self, LSAP_SETUP);
 		break;
 	case LM_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(0, "%s() : WATCHDOG_TIMEOUT !\n",  __func__);
+		pr_debug("%s() : WATCHDOG_TIMEOUT !\n",  __func__);
 
 		IRDA_ASSERT(self->lap != NULL, return -1;);
 		irlmp_do_lap_event(self->lap, LM_LAP_DISCONNECT_REQUEST, NULL);
@@ -901,8 +880,8 @@ static int irlmp_state_setup_pend(struct lsap_cb *self, IRLMP_EVENT event,
 		irlmp_disconnect_indication(self, reason, NULL);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s on LSAP %#02x\n",
-			   __func__, irlmp_event[event], self->slsap_sel);
+		pr_debug("%s(), Unknown event %s on LSAP %#02x\n",
+			 __func__, irlmp_event[event], self->slsap_sel);
 		break;
 	}
 	return ret;
diff --git a/net/irda/irlmp_frame.c b/net/irda/irlmp_frame.c
index 062e63b1c5c..38b0f994bc7 100644
--- a/net/irda/irlmp_frame.c
+++ b/net/irda/irlmp_frame.c
@@ -44,7 +44,7 @@ inline void irlmp_send_data_pdu(struct lap_cb *self, __u8 dlsap, __u8 slsap,
 	skb->data[1] = slsap;
 
 	if (expedited) {
-		IRDA_DEBUG(4, "%s(), sending expedited data\n", __func__);
+		pr_debug("%s(), sending expedited data\n", __func__);
 		irlap_data_request(self->irlap, skb, TRUE);
 	} else
 		irlap_data_request(self->irlap, skb, FALSE);
@@ -60,8 +60,6 @@ void irlmp_send_lcf_pdu(struct lap_cb *self, __u8 dlsap, __u8 slsap,
 {
 	__u8 *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -95,8 +93,6 @@ void irlmp_link_data_indication(struct lap_cb *self, struct sk_buff *skb,
 	__u8   dlsap_sel;   /* Destination LSAP address */
 	__u8   *fp;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 	IRDA_ASSERT(skb->len > 2, return;);
@@ -115,9 +111,8 @@ void irlmp_link_data_indication(struct lap_cb *self, struct sk_buff *skb,
 	 *  it in a different way than other established connections.
 	 */
 	if ((fp[0] & CONTROL_BIT) && (fp[2] == CONNECT_CMD)) {
-		IRDA_DEBUG(3, "%s(), incoming connection, "
-			   "source LSAP=%d, dest LSAP=%d\n",
-			   __func__, slsap_sel, dlsap_sel);
+		pr_debug("%s(), incoming connection, source LSAP=%d, dest LSAP=%d\n",
+			 __func__, slsap_sel, dlsap_sel);
 
 		/* Try to find LSAP among the unconnected LSAPs */
 		lsap = irlmp_find_lsap(self, dlsap_sel, slsap_sel, CONNECT_CMD,
@@ -125,7 +120,8 @@ void irlmp_link_data_indication(struct lap_cb *self, struct sk_buff *skb,
 
 		/* Maybe LSAP was already connected, so try one more time */
 		if (!lsap) {
-			IRDA_DEBUG(1, "%s(), incoming connection for LSAP already connected\n", __func__);
+			pr_debug("%s(), incoming connection for LSAP already connected\n",
+				 __func__);
 			lsap = irlmp_find_lsap(self, dlsap_sel, slsap_sel, 0,
 					       self->lsaps);
 		}
@@ -134,14 +130,14 @@ void irlmp_link_data_indication(struct lap_cb *self, struct sk_buff *skb,
 				       self->lsaps);
 
 	if (lsap == NULL) {
-		IRDA_DEBUG(2, "IrLMP, Sorry, no LSAP for received frame!\n");
-		IRDA_DEBUG(2, "%s(), slsap_sel = %02x, dlsap_sel = %02x\n",
-			   __func__, slsap_sel, dlsap_sel);
+		pr_debug("IrLMP, Sorry, no LSAP for received frame!\n");
+		pr_debug("%s(), slsap_sel = %02x, dlsap_sel = %02x\n",
+			 __func__, slsap_sel, dlsap_sel);
 		if (fp[0] & CONTROL_BIT) {
-			IRDA_DEBUG(2, "%s(), received control frame %02x\n",
-				   __func__, fp[2]);
+			pr_debug("%s(), received control frame %02x\n",
+				 __func__, fp[2]);
 		} else {
-			IRDA_DEBUG(2, "%s(), received data frame\n", __func__);
+			pr_debug("%s(), received data frame\n", __func__);
 		}
 		return;
 	}
@@ -159,20 +155,20 @@ void irlmp_link_data_indication(struct lap_cb *self, struct sk_buff *skb,
 			irlmp_do_lsap_event(lsap, LM_CONNECT_CONFIRM, skb);
 			break;
 		case DISCONNECT:
-			IRDA_DEBUG(4, "%s(), Disconnect indication!\n",
-				   __func__);
+			pr_debug("%s(), Disconnect indication!\n",
+				 __func__);
 			irlmp_do_lsap_event(lsap, LM_DISCONNECT_INDICATION,
 					    skb);
 			break;
 		case ACCESSMODE_CMD:
-			IRDA_DEBUG(0, "Access mode cmd not implemented!\n");
+			pr_debug("Access mode cmd not implemented!\n");
 			break;
 		case ACCESSMODE_CNF:
-			IRDA_DEBUG(0, "Access mode cnf not implemented!\n");
+			pr_debug("Access mode cnf not implemented!\n");
 			break;
 		default:
-			IRDA_DEBUG(0, "%s(), Unknown control frame %02x\n",
-				   __func__, fp[2]);
+			pr_debug("%s(), Unknown control frame %02x\n",
+				 __func__, fp[2]);
 			break;
 		}
 	} else if (unreliable) {
@@ -206,8 +202,6 @@ void irlmp_link_unitdata_indication(struct lap_cb *self, struct sk_buff *skb)
 	__u8   *fp;
 	unsigned long flags;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 	IRDA_ASSERT(skb->len > 2, return;);
@@ -223,14 +217,14 @@ void irlmp_link_unitdata_indication(struct lap_cb *self, struct sk_buff *skb)
 	pid       = fp[2];
 
 	if (pid & 0x80) {
-		IRDA_DEBUG(0, "%s(), extension in PID not supp!\n",
-			   __func__);
+		pr_debug("%s(), extension in PID not supp!\n",
+			 __func__);
 		return;
 	}
 
 	/* Check if frame is addressed to the connectionless LSAP */
 	if ((slsap_sel != LSAP_CONNLESS) || (dlsap_sel != LSAP_CONNLESS)) {
-		IRDA_DEBUG(0, "%s(), dropping frame!\n", __func__);
+		pr_debug("%s(), dropping frame!\n", __func__);
 		return;
 	}
 
@@ -254,7 +248,7 @@ void irlmp_link_unitdata_indication(struct lap_cb *self, struct sk_buff *skb)
 	if (lsap)
 		irlmp_connless_data_indication(lsap, skb);
 	else {
-		IRDA_DEBUG(0, "%s(), found no matching LSAP!\n", __func__);
+		pr_debug("%s(), found no matching LSAP!\n", __func__);
 	}
 }
 #endif /* CONFIG_IRDA_ULTRA */
@@ -270,8 +264,6 @@ void irlmp_link_disconnect_indication(struct lap_cb *lap,
 				      LAP_REASON reason,
 				      struct sk_buff *skb)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(lap != NULL, return;);
 	IRDA_ASSERT(lap->magic == LMP_LAP_MAGIC, return;);
 
@@ -296,8 +288,6 @@ void irlmp_link_connect_indication(struct lap_cb *self, __u32 saddr,
 				   __u32 daddr, struct qos_info *qos,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	/* Copy QoS settings for this session */
 	self->qos = qos;
 
@@ -317,8 +307,6 @@ void irlmp_link_connect_indication(struct lap_cb *self, __u32 saddr,
 void irlmp_link_connect_confirm(struct lap_cb *self, struct qos_info *qos,
 				struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 	IRDA_ASSERT(qos != NULL, return;);
@@ -383,8 +371,6 @@ void irlmp_link_discovery_indication(struct lap_cb *self,
  */
 void irlmp_link_discovery_confirm(struct lap_cb *self, hashbin_t *log)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 
diff --git a/net/irda/irmod.c b/net/irda/irmod.c
index 303a68d9273..c5e35b85c47 100644
--- a/net/irda/irmod.c
+++ b/net/irda/irmod.c
@@ -42,16 +42,6 @@
 #include <net/irda/irttp.h>		/* irttp_init */
 #include <net/irda/irda_device.h>	/* irda_device_init */
 
-/*
- * Module parameters
- */
-#ifdef CONFIG_IRDA_DEBUG
-unsigned int irda_debug = IRDA_DEBUG_LEVEL;
-module_param_named(debug, irda_debug, uint, 0);
-MODULE_PARM_DESC(debug, "IRDA debugging level");
-EXPORT_SYMBOL(irda_debug);
-#endif
-
 /* Packet type handler.
  * Tell the kernel how IrDA packets should be handled.
  */
@@ -90,8 +80,6 @@ static int __init irda_init(void)
 {
 	int ret = 0;
 
-	IRDA_DEBUG(0, "%s()\n", __func__);
-
 	/* Lower layer of the stack */
 	irlmp_init();
 	irlap_init();
diff --git a/net/irda/irnetlink.c b/net/irda/irnetlink.c
index a37b81fe047..e15c40e8666 100644
--- a/net/irda/irnetlink.c
+++ b/net/irda/irnetlink.c
@@ -41,7 +41,7 @@ static struct net_device * ifname_to_netdev(struct net *net, struct genl_info *i
 
 	ifname = nla_data(info->attrs[IRDA_NL_ATTR_IFNAME]);
 
-	IRDA_DEBUG(5, "%s(): Looking for %s\n", __func__, ifname);
+	pr_debug("%s(): Looking for %s\n", __func__, ifname);
 
 	return dev_get_by_name(net, ifname);
 }
@@ -57,7 +57,7 @@ static int irda_nl_set_mode(struct sk_buff *skb, struct genl_info *info)
 
 	mode = nla_get_u32(info->attrs[IRDA_NL_ATTR_MODE]);
 
-	IRDA_DEBUG(5, "%s(): Switching to mode: %d\n", __func__, mode);
+	pr_debug("%s(): Switching to mode: %d\n", __func__, mode);
 
 	dev = ifname_to_netdev(&init_net, info);
 	if (!dev)
diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c
index 7152624ed5f..acbe61c7e68 100644
--- a/net/irda/irqueue.c
+++ b/net/irda/irqueue.c
@@ -233,8 +233,6 @@ static __u32 hash( const char* name)
 static void enqueue_first(irda_queue_t **queue, irda_queue_t* element)
 {
 
-	IRDA_DEBUG( 4, "%s()\n", __func__);
-
 	/*
 	 * Check if queue is empty.
 	 */
@@ -267,7 +265,7 @@ static irda_queue_t *dequeue_first(irda_queue_t **queue)
 {
 	irda_queue_t *ret;
 
-	IRDA_DEBUG( 4, "dequeue_first()\n");
+	pr_debug("dequeue_first()\n");
 
 	/*
 	 * Set return value
@@ -308,7 +306,7 @@ static irda_queue_t *dequeue_general(irda_queue_t **queue, irda_queue_t* element
 {
 	irda_queue_t *ret;
 
-	IRDA_DEBUG( 4, "dequeue_general()\n");
+	pr_debug("dequeue_general()\n");
 
 	/*
 	 * Set return value
@@ -452,8 +450,6 @@ void hashbin_insert(hashbin_t* hashbin, irda_queue_t* entry, long hashv,
 	unsigned long flags = 0;
 	int bin;
 
-	IRDA_DEBUG( 4, "%s()\n", __func__);
-
 	IRDA_ASSERT( hashbin != NULL, return;);
 	IRDA_ASSERT( hashbin->magic == HB_MAGIC, return;);
 
@@ -565,8 +561,6 @@ void* hashbin_remove( hashbin_t* hashbin, long hashv, const char* name)
 	unsigned long flags = 0;
 	irda_queue_t* entry;
 
-	IRDA_DEBUG( 4, "%s()\n", __func__);
-
 	IRDA_ASSERT( hashbin != NULL, return NULL;);
 	IRDA_ASSERT( hashbin->magic == HB_MAGIC, return NULL;);
 
@@ -658,8 +652,6 @@ void* hashbin_remove_this( hashbin_t* hashbin, irda_queue_t* entry)
 	int	bin;
 	long	hashv;
 
-	IRDA_DEBUG( 4, "%s()\n", __func__);
-
 	IRDA_ASSERT( hashbin != NULL, return NULL;);
 	IRDA_ASSERT( hashbin->magic == HB_MAGIC, return NULL;);
 	IRDA_ASSERT( entry != NULL, return NULL;);
@@ -719,7 +711,7 @@ void* hashbin_find( hashbin_t* hashbin, long hashv, const char* name )
 	int bin;
 	irda_queue_t* entry;
 
-	IRDA_DEBUG( 4, "hashbin_find()\n");
+	pr_debug("hashbin_find()\n");
 
 	IRDA_ASSERT( hashbin != NULL, return NULL;);
 	IRDA_ASSERT( hashbin->magic == HB_MAGIC, return NULL;);
diff --git a/net/irda/irsysctl.c b/net/irda/irsysctl.c
index d6a59651767..873da5e7d42 100644
--- a/net/irda/irsysctl.c
+++ b/net/irda/irsysctl.c
@@ -126,15 +126,6 @@ static struct ctl_table irda_table[] = {
 		.mode		= 0644,
 		.proc_handler	= do_devname,
 	},
-#ifdef CONFIG_IRDA_DEBUG
-	{
-		.procname	= "debug",
-		.data		= &irda_debug,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-#endif
 #ifdef CONFIG_IRDA_FAST_RR
 	{
 		.procname	= "fast_poll_increase",
diff --git a/net/irda/irttp.c b/net/irda/irttp.c
index e0b2b0d9af1..3ef0b08b6bf 100644
--- a/net/irda/irttp.c
+++ b/net/irda/irttp.c
@@ -166,7 +166,7 @@ static void irttp_todo_expired(unsigned long data)
 	if (!self || self->magic != TTP_TSAP_MAGIC)
 		return;
 
-	IRDA_DEBUG(4, "%s(instance=%p)\n", __func__, self);
+	pr_debug("%s(instance=%p)\n", __func__, self);
 
 	/* Try to make some progress, especially on Tx side - Jean II */
 	irttp_run_rx_queue(self);
@@ -207,8 +207,6 @@ static void irttp_flush_queues(struct tsap_cb *self)
 {
 	struct sk_buff *skb;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;);
 
@@ -240,8 +238,8 @@ static struct sk_buff *irttp_reassemble_skb(struct tsap_cb *self)
 	IRDA_ASSERT(self != NULL, return NULL;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return NULL;);
 
-	IRDA_DEBUG(2, "%s(), self->rx_sdu_size=%d\n", __func__,
-		   self->rx_sdu_size);
+	pr_debug("%s(), self->rx_sdu_size=%d\n", __func__,
+		 self->rx_sdu_size);
 
 	skb = dev_alloc_skb(TTP_HEADER + self->rx_sdu_size);
 	if (!skb)
@@ -264,9 +262,8 @@ static struct sk_buff *irttp_reassemble_skb(struct tsap_cb *self)
 		dev_kfree_skb(frag);
 	}
 
-	IRDA_DEBUG(2,
-		   "%s(), frame len=%d, rx_sdu_size=%d, rx_max_sdu_size=%d\n",
-		   __func__, n, self->rx_sdu_size, self->rx_max_sdu_size);
+	pr_debug("%s(), frame len=%d, rx_sdu_size=%d, rx_max_sdu_size=%d\n",
+		 __func__, n, self->rx_sdu_size, self->rx_max_sdu_size);
 	/* Note : irttp_run_rx_queue() calculate self->rx_sdu_size
 	 * by summing the size of all fragments, so we should always
 	 * have n == self->rx_sdu_size, except in cases where we
@@ -295,8 +292,6 @@ static inline void irttp_fragment_skb(struct tsap_cb *self,
 	struct sk_buff *frag;
 	__u8 *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -305,7 +300,7 @@ static inline void irttp_fragment_skb(struct tsap_cb *self,
 	 *  Split frame into a number of segments
 	 */
 	while (skb->len > self->max_seg_size) {
-		IRDA_DEBUG(2, "%s(), fragmenting ...\n", __func__);
+		pr_debug("%s(), fragmenting ...\n", __func__);
 
 		/* Make new segment */
 		frag = alloc_skb(self->max_seg_size+self->max_header_size,
@@ -330,7 +325,7 @@ static inline void irttp_fragment_skb(struct tsap_cb *self,
 		skb_queue_tail(&self->tx_queue, frag);
 	}
 	/* Queue what is left of the original skb */
-	IRDA_DEBUG(2, "%s(), queuing last segment\n", __func__);
+	pr_debug("%s(), queuing last segment\n", __func__);
 
 	frame = skb_push(skb, TTP_HEADER);
 	frame[0] = 0x00; /* Clear more bit */
@@ -361,7 +356,7 @@ static int irttp_param_max_sdu_size(void *instance, irda_param_t *param,
 	else
 		self->tx_max_sdu_size = param->pv.i;
 
-	IRDA_DEBUG(1, "%s(), MaxSduSize=%d\n", __func__, param->pv.i);
+	pr_debug("%s(), MaxSduSize=%d\n", __func__, param->pv.i);
 
 	return 0;
 }
@@ -402,15 +397,13 @@ struct tsap_cb *irttp_open_tsap(__u8 stsap_sel, int credit, notify_t *notify)
 	 * JeanII */
 	if ((stsap_sel != LSAP_ANY) &&
 	   ((stsap_sel < 0x01) || (stsap_sel >= 0x70))) {
-		IRDA_DEBUG(0, "%s(), invalid tsap!\n", __func__);
+		pr_debug("%s(), invalid tsap!\n", __func__);
 		return NULL;
 	}
 
 	self = kzalloc(sizeof(struct tsap_cb), GFP_ATOMIC);
-	if (self == NULL) {
-		IRDA_DEBUG(0, "%s(), unable to kmalloc!\n", __func__);
+	if (self == NULL)
 		return NULL;
-	}
 
 	/* Initialize internal objects */
 	irttp_init_tsap(self);
@@ -440,7 +433,7 @@ struct tsap_cb *irttp_open_tsap(__u8 stsap_sel, int credit, notify_t *notify)
 	 */
 	lsap = irlmp_open_lsap(stsap_sel, &ttp_notify, 0);
 	if (lsap == NULL) {
-		IRDA_DEBUG(0, "%s: unable to allocate LSAP!!\n", __func__);
+		pr_debug("%s: unable to allocate LSAP!!\n", __func__);
 		__irttp_close_tsap(self);
 		return NULL;
 	}
@@ -451,7 +444,7 @@ struct tsap_cb *irttp_open_tsap(__u8 stsap_sel, int credit, notify_t *notify)
 	 *  the stsap_sel we have might not be valid anymore
 	 */
 	self->stsap_sel = lsap->slsap_sel;
-	IRDA_DEBUG(4, "%s(), stsap_sel=%02x\n", __func__, self->stsap_sel);
+	pr_debug("%s(), stsap_sel=%02x\n", __func__, self->stsap_sel);
 
 	self->notify = *notify;
 	self->lsap = lsap;
@@ -509,8 +502,6 @@ int irttp_close_tsap(struct tsap_cb *self)
 {
 	struct tsap_cb *tsap;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -1;);
 
@@ -558,8 +549,6 @@ int irttp_udata_request(struct tsap_cb *self, struct sk_buff *skb)
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -1;);
 	IRDA_ASSERT(skb != NULL, return -1;);
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	/* Take shortcut on zero byte packets */
 	if (skb->len == 0) {
 		ret = 0;
@@ -607,8 +596,8 @@ int irttp_data_request(struct tsap_cb *self, struct sk_buff *skb)
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -1;);
 	IRDA_ASSERT(skb != NULL, return -1;);
 
-	IRDA_DEBUG(2, "%s() : queue len = %d\n", __func__,
-		   skb_queue_len(&self->tx_queue));
+	pr_debug("%s() : queue len = %d\n", __func__,
+		 skb_queue_len(&self->tx_queue));
 
 	/* Take shortcut on zero byte packets */
 	if (skb->len == 0) {
@@ -720,9 +709,9 @@ static void irttp_run_tx_queue(struct tsap_cb *self)
 	unsigned long flags;
 	int n;
 
-	IRDA_DEBUG(2, "%s() : send_credit = %d, queue_len = %d\n",
-		   __func__,
-		   self->send_credit, skb_queue_len(&self->tx_queue));
+	pr_debug("%s() : send_credit = %d, queue_len = %d\n",
+		 __func__,
+		 self->send_credit, skb_queue_len(&self->tx_queue));
 
 	/* Get exclusive access to the tx queue, otherwise don't touch it */
 	if (irda_lock(&self->tx_queue_lock) == FALSE)
@@ -827,9 +816,9 @@ static inline void irttp_give_credit(struct tsap_cb *self)
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;);
 
-	IRDA_DEBUG(4, "%s() send=%d,avail=%d,remote=%d\n",
-		   __func__,
-		   self->send_credit, self->avail_credit, self->remote_credit);
+	pr_debug("%s() send=%d,avail=%d,remote=%d\n",
+		 __func__,
+		 self->send_credit, self->avail_credit, self->remote_credit);
 
 	/* Give credit to peer */
 	tx_skb = alloc_skb(TTP_MAX_HEADER, GFP_ATOMIC);
@@ -877,8 +866,6 @@ static int irttp_udata_indication(void *instance, void *sap,
 	struct tsap_cb *self;
 	int err;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return -1;);
@@ -994,8 +981,6 @@ static void irttp_status_indication(void *instance,
 {
 	struct tsap_cb *self;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return;);
@@ -1012,7 +997,7 @@ static void irttp_status_indication(void *instance,
 		self->notify.status_indication(self->notify.instance,
 					       link, lock);
 	else
-		IRDA_DEBUG(2, "%s(), no handler\n", __func__);
+		pr_debug("%s(), no handler\n", __func__);
 }
 
 /*
@@ -1030,7 +1015,7 @@ static void irttp_flow_indication(void *instance, void *sap, LOCAL_FLOW flow)
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;);
 
-	IRDA_DEBUG(4, "%s(instance=%p)\n", __func__, self);
+	pr_debug("%s(instance=%p)\n", __func__, self);
 
 	/* We are "polled" directly from LAP, and the LAP want to fill
 	 * its Tx window. We want to do our best to send it data, so that
@@ -1068,18 +1053,16 @@ static void irttp_flow_indication(void *instance, void *sap, LOCAL_FLOW flow)
  */
 void irttp_flow_request(struct tsap_cb *self, LOCAL_FLOW flow)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;);
 
 	switch (flow) {
 	case FLOW_STOP:
-		IRDA_DEBUG(1, "%s(), flow stop\n", __func__);
+		pr_debug("%s(), flow stop\n", __func__);
 		self->rx_sdu_busy = TRUE;
 		break;
 	case FLOW_START:
-		IRDA_DEBUG(1, "%s(), flow start\n", __func__);
+		pr_debug("%s(), flow start\n", __func__);
 		self->rx_sdu_busy = FALSE;
 
 		/* Client say he can accept more data, try to free our
@@ -1088,7 +1071,7 @@ void irttp_flow_request(struct tsap_cb *self, LOCAL_FLOW flow)
 
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown flow command!\n", __func__);
+		pr_debug("%s(), Unknown flow command!\n", __func__);
 	}
 }
 EXPORT_SYMBOL(irttp_flow_request);
@@ -1108,7 +1091,7 @@ int irttp_connect_request(struct tsap_cb *self, __u8 dtsap_sel,
 	__u8 *frame;
 	__u8 n;
 
-	IRDA_DEBUG(4, "%s(), max_sdu_size=%d\n", __func__, max_sdu_size);
+	pr_debug("%s(), max_sdu_size=%d\n", __func__, max_sdu_size);
 
 	IRDA_ASSERT(self != NULL, return -EBADR;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -EBADR;);
@@ -1206,8 +1189,6 @@ static void irttp_connect_confirm(void *instance, void *sap,
 	__u8 plen;
 	__u8 n;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return;);
@@ -1222,15 +1203,15 @@ static void irttp_connect_confirm(void *instance, void *sap,
 	 *  negotiated QoS for the link.
 	 */
 	if (qos) {
-		IRDA_DEBUG(4, "IrTTP, Negotiated BAUD_RATE: %02x\n",
-		       qos->baud_rate.bits);
-		IRDA_DEBUG(4, "IrTTP, Negotiated BAUD_RATE: %d bps.\n",
-		       qos->baud_rate.value);
+		pr_debug("IrTTP, Negotiated BAUD_RATE: %02x\n",
+			 qos->baud_rate.bits);
+		pr_debug("IrTTP, Negotiated BAUD_RATE: %d bps.\n",
+			 qos->baud_rate.value);
 	}
 
 	n = skb->data[0] & 0x7f;
 
-	IRDA_DEBUG(4, "%s(), Initial send_credit=%d\n", __func__, n);
+	pr_debug("%s(), Initial send_credit=%d\n", __func__, n);
 
 	self->send_credit = n;
 	self->tx_max_sdu_size = 0;
@@ -1261,11 +1242,11 @@ static void irttp_connect_confirm(void *instance, void *sap,
 		skb_pull(skb, IRDA_MIN(skb->len, plen+1));
 	}
 
-	IRDA_DEBUG(4, "%s() send=%d,avail=%d,remote=%d\n", __func__,
-	      self->send_credit, self->avail_credit, self->remote_credit);
+	pr_debug("%s() send=%d,avail=%d,remote=%d\n", __func__,
+		 self->send_credit, self->avail_credit, self->remote_credit);
 
-	IRDA_DEBUG(2, "%s(), MaxSduSize=%d\n", __func__,
-		   self->tx_max_sdu_size);
+	pr_debug("%s(), MaxSduSize=%d\n", __func__,
+		 self->tx_max_sdu_size);
 
 	if (self->notify.connect_confirm) {
 		self->notify.connect_confirm(self->notify.instance, self, qos,
@@ -1303,7 +1284,7 @@ static void irttp_connect_indication(void *instance, void *sap,
 	self->max_seg_size = max_seg_size - TTP_HEADER;
 	self->max_header_size = max_header_size+TTP_HEADER;
 
-	IRDA_DEBUG(4, "%s(), TSAP sel=%02x\n", __func__, self->stsap_sel);
+	pr_debug("%s(), TSAP sel=%02x\n", __func__, self->stsap_sel);
 
 	/* Need to update dtsap_sel if its equal to LSAP_ANY */
 	self->dtsap_sel = lsap->dlsap_sel;
@@ -1365,8 +1346,8 @@ int irttp_connect_response(struct tsap_cb *self, __u32 max_sdu_size,
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -1;);
 
-	IRDA_DEBUG(4, "%s(), Source TSAP selector=%02x\n", __func__,
-		   self->stsap_sel);
+	pr_debug("%s(), Source TSAP selector=%02x\n", __func__,
+		 self->stsap_sel);
 
 	/* Any userdata supplied? */
 	if (userdata == NULL) {
@@ -1447,14 +1428,12 @@ struct tsap_cb *irttp_dup(struct tsap_cb *orig, void *instance)
 	struct tsap_cb *new;
 	unsigned long flags;
 
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	/* Protect our access to the old tsap instance */
 	spin_lock_irqsave(&irttp->tsaps->hb_spinlock, flags);
 
 	/* Find the old instance */
 	if (!hashbin_find(irttp->tsaps, (long) orig, NULL)) {
-		IRDA_DEBUG(0, "%s(), unable to find TSAP\n", __func__);
+		pr_debug("%s(), unable to find TSAP\n", __func__);
 		spin_unlock_irqrestore(&irttp->tsaps->hb_spinlock, flags);
 		return NULL;
 	}
@@ -1462,7 +1441,7 @@ struct tsap_cb *irttp_dup(struct tsap_cb *orig, void *instance)
 	/* Allocate a new instance */
 	new = kmemdup(orig, sizeof(struct tsap_cb), GFP_ATOMIC);
 	if (!new) {
-		IRDA_DEBUG(0, "%s(), unable to kmalloc\n", __func__);
+		pr_debug("%s(), unable to kmalloc\n", __func__);
 		spin_unlock_irqrestore(&irttp->tsaps->hb_spinlock, flags);
 		return NULL;
 	}
@@ -1474,7 +1453,7 @@ struct tsap_cb *irttp_dup(struct tsap_cb *orig, void *instance)
 	/* Try to dup the LSAP (may fail if we were too slow) */
 	new->lsap = irlmp_dup(orig->lsap, new);
 	if (!new->lsap) {
-		IRDA_DEBUG(0, "%s(), dup failed!\n", __func__);
+		pr_debug("%s(), dup failed!\n", __func__);
 		kfree(new);
 		return NULL;
 	}
@@ -1509,7 +1488,7 @@ int irttp_disconnect_request(struct tsap_cb *self, struct sk_buff *userdata,
 
 	/* Already disconnected? */
 	if (!self->connected) {
-		IRDA_DEBUG(4, "%s(), already disconnected!\n", __func__);
+		pr_debug("%s(), already disconnected!\n", __func__);
 		if (userdata)
 			dev_kfree_skb(userdata);
 		return -1;
@@ -1521,8 +1500,8 @@ int irttp_disconnect_request(struct tsap_cb *self, struct sk_buff *userdata,
 	 * for following a disconnect_indication() (i.e. net_bh).
 	 * Jean II */
 	if (test_and_set_bit(0, &self->disconnect_pend)) {
-		IRDA_DEBUG(0, "%s(), disconnect already pending\n",
-			   __func__);
+		pr_debug("%s(), disconnect already pending\n",
+			 __func__);
 		if (userdata)
 			dev_kfree_skb(userdata);
 
@@ -1541,7 +1520,7 @@ int irttp_disconnect_request(struct tsap_cb *self, struct sk_buff *userdata,
 			 *  disconnecting right now since the data will
 			 *  not have any usable connection to be sent on
 			 */
-			IRDA_DEBUG(1, "%s(): High priority!!()\n", __func__);
+			pr_debug("%s(): High priority!!()\n", __func__);
 			irttp_flush_queues(self);
 		} else if (priority == P_NORMAL) {
 			/*
@@ -1562,7 +1541,7 @@ int irttp_disconnect_request(struct tsap_cb *self, struct sk_buff *userdata,
 	 * be sent at the LMP level (so even if the peer has its Tx queue
 	 * full of data). - Jean II */
 
-	IRDA_DEBUG(1, "%s(), Disconnecting ...\n", __func__);
+	pr_debug("%s(), Disconnecting ...\n", __func__);
 	self->connected = FALSE;
 
 	if (!userdata) {
@@ -1598,8 +1577,6 @@ static void irttp_disconnect_indication(void *instance, void *sap,
 {
 	struct tsap_cb *self;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return;);
@@ -1658,7 +1635,7 @@ static void irttp_do_data_indication(struct tsap_cb *self, struct sk_buff *skb)
 	 * give an error back
 	 */
 	if (err) {
-		IRDA_DEBUG(0, "%s() requeueing skb!\n", __func__);
+		pr_debug("%s() requeueing skb!\n", __func__);
 
 		/* Make sure we take a break */
 		self->rx_sdu_busy = TRUE;
@@ -1683,8 +1660,8 @@ static void irttp_run_rx_queue(struct tsap_cb *self)
 	struct sk_buff *skb;
 	int more = 0;
 
-	IRDA_DEBUG(2, "%s() send=%d,avail=%d,remote=%d\n", __func__,
-		   self->send_credit, self->avail_credit, self->remote_credit);
+	pr_debug("%s() send=%d,avail=%d,remote=%d\n", __func__,
+		 self->send_credit, self->avail_credit, self->remote_credit);
 
 	/* Get exclusive access to the rx queue, otherwise don't touch it */
 	if (irda_lock(&self->rx_queue_lock) == FALSE)
@@ -1723,8 +1700,8 @@ static void irttp_run_rx_queue(struct tsap_cb *self)
 			 *  limits of the maximum size of the rx_sdu
 			 */
 			if (self->rx_sdu_size <= self->rx_max_sdu_size) {
-				IRDA_DEBUG(4, "%s(), queueing frag\n",
-					   __func__);
+				pr_debug("%s(), queueing frag\n",
+					 __func__);
 				skb_queue_tail(&self->rx_fragments, skb);
 			} else {
 				/* Free the part of the SDU that is too big */
@@ -1753,7 +1730,7 @@ static void irttp_run_rx_queue(struct tsap_cb *self)
 			/* Now we can deliver the reassembled skb */
 			irttp_do_data_indication(self, skb);
 		} else {
-			IRDA_DEBUG(1, "%s(), Truncated frame\n", __func__);
+			pr_debug("%s(), Truncated frame\n", __func__);
 
 			/* Free the part of the SDU that is too big */
 			dev_kfree_skb(skb);
diff --git a/net/irda/parameters.c b/net/irda/parameters.c
index d7a5778262e..006786bfdd6 100644
--- a/net/irda/parameters.c
+++ b/net/irda/parameters.c
@@ -146,13 +146,13 @@ static int irda_insert_integer(void *self, __u8 *buf, int len, __u8 pi,
 	 */
 	if (p.pl == 0) {
 		if (p.pv.i < 0xff) {
-			IRDA_DEBUG(2, "%s(), using 1 byte\n", __func__);
+			pr_debug("%s(), using 1 byte\n", __func__);
 			p.pl = 1;
 		} else if (p.pv.i < 0xffff) {
-			IRDA_DEBUG(2, "%s(), using 2 bytes\n", __func__);
+			pr_debug("%s(), using 2 bytes\n", __func__);
 			p.pl = 2;
 		} else {
-			IRDA_DEBUG(2, "%s(), using 4 bytes\n", __func__);
+			pr_debug("%s(), using 4 bytes\n", __func__);
 			p.pl = 4; /* Default length */
 		}
 	}
@@ -162,8 +162,8 @@ static int irda_insert_integer(void *self, __u8 *buf, int len, __u8 pi,
 				     __func__);
 		return -1;
 	}
-	IRDA_DEBUG(2, "%s(), pi=%#x, pl=%d, pi=%d\n", __func__,
-		   p.pi, p.pl, p.pv.i);
+	pr_debug("%s(), pi=%#x, pl=%d, pi=%d\n", __func__,
+		 p.pi, p.pl, p.pv.i);
 	switch (p.pl) {
 	case 1:
 		n += irda_param_pack(buf, "bbb", p.pi, p.pl, (__u8) p.pv.i);
@@ -270,8 +270,8 @@ static int irda_extract_integer(void *self, __u8 *buf, int len, __u8 pi,
 		return p.pl+2;
 	}
 
-	IRDA_DEBUG(2, "%s(), pi=%#x, pl=%d, pi=%d\n", __func__,
-		   p.pi, p.pl, p.pv.i);
+	pr_debug("%s(), pi=%#x, pl=%d, pi=%d\n", __func__,
+		 p.pi, p.pl, p.pv.i);
 	/* Call handler for this parameter */
 	err = (*func)(self, &p, PV_PUT);
 	if (err < 0)
@@ -290,15 +290,13 @@ static int irda_extract_string(void *self, __u8 *buf, int len, __u8 pi,
 	irda_param_t p;
 	int err;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	p.pi = pi;     /* In case handler needs to know */
 	p.pl = buf[1]; /* Extract length of value */
 	if (p.pl > 32)
 		p.pl = 32;
 
-	IRDA_DEBUG(2, "%s(), pi=%#x, pl=%d\n", __func__,
-		   p.pi, p.pl);
+	pr_debug("%s(), pi=%#x, pl=%d\n", __func__,
+		 p.pi, p.pl);
 
 	/* Check if buffer is long enough for parsing */
 	if (len < (2+p.pl)) {
@@ -311,8 +309,8 @@ static int irda_extract_string(void *self, __u8 *buf, int len, __u8 pi,
 	 * checked that the buffer is long enough */
 	strncpy(str, buf+2, p.pl);
 
-	IRDA_DEBUG(2, "%s(), str=0x%02x 0x%02x\n", __func__,
-		   (__u8) str[0], (__u8) str[1]);
+	pr_debug("%s(), str=0x%02x 0x%02x\n",
+		 __func__, (__u8)str[0], (__u8)str[1]);
 
 	/* Null terminate string */
 	str[p.pl] = '\0';
@@ -345,7 +343,7 @@ static int irda_extract_octseq(void *self, __u8 *buf, int len, __u8 pi,
 		return -1;
 	}
 
-	IRDA_DEBUG(0, "%s(), not impl\n", __func__);
+	pr_debug("%s(), not impl\n", __func__);
 
 	return p.pl+2; /* Extracted pl+2 bytes */
 }
@@ -468,8 +466,8 @@ int irda_param_insert(void *self, __u8 pi, __u8 *buf, int len,
 	if ((pi_major > info->len-1) ||
 	    (pi_minor > info->tables[pi_major].len-1))
 	{
-		IRDA_DEBUG(0, "%s(), no handler for parameter=0x%02x\n",
-			   __func__, pi);
+		pr_debug("%s(), no handler for parameter=0x%02x\n",
+			 __func__, pi);
 
 		/* Skip this parameter */
 		return -1;
@@ -523,8 +521,8 @@ static int irda_param_extract(void *self, __u8 *buf, int len,
 	if ((pi_major > info->len-1) ||
 	    (pi_minor > info->tables[pi_major].len-1))
 	{
-		IRDA_DEBUG(0, "%s(), no handler for parameter=0x%02x\n",
-			   __func__, buf[0]);
+		pr_debug("%s(), no handler for parameter=0x%02x\n",
+			 __func__, buf[0]);
 
 		/* Skip this parameter */
 		return 2 + buf[n + 1];  /* Continue */
@@ -536,8 +534,8 @@ static int irda_param_extract(void *self, __u8 *buf, int len,
 	/* Find expected data type for this parameter identifier (pi)*/
 	type = pi_minor_info->type;
 
-	IRDA_DEBUG(3, "%s(), pi=[%d,%d], type=%d\n", __func__,
-		   pi_major, pi_minor, type);
+	pr_debug("%s(), pi=[%d,%d], type=%d\n", __func__,
+		 pi_major, pi_minor, type);
 
 	/*  Check if handler has been implemented */
 	if (!pi_minor_info->func) {
diff --git a/net/irda/qos.c b/net/irda/qos.c
index f3b588c17d3..5ed6c9a7bae 100644
--- a/net/irda/qos.c
+++ b/net/irda/qos.c
@@ -342,8 +342,6 @@ static void irlap_adjust_qos_settings(struct qos_info *qos)
 	__u32 line_capacity;
 	int index;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/*
 	 * Make sure the mintt is sensible.
 	 * Main culprit : Ericsson T39. - Jean II
@@ -368,9 +366,8 @@ static void irlap_adjust_qos_settings(struct qos_info *qos)
 	if ((qos->baud_rate.value < 115200) &&
 	    (qos->max_turn_time.value < 500))
 	{
-		IRDA_DEBUG(0,
-			   "%s(), adjusting max turn time from %d to 500 ms\n",
-			   __func__, qos->max_turn_time.value);
+		pr_debug("%s(), adjusting max turn time from %d to 500 ms\n",
+			 __func__, qos->max_turn_time.value);
 		qos->max_turn_time.value = 500;
 	}
 
@@ -385,8 +382,8 @@ static void irlap_adjust_qos_settings(struct qos_info *qos)
 #ifdef CONFIG_IRDA_DYNAMIC_WINDOW
 	while ((qos->data_size.value > line_capacity) && (index > 0)) {
 		qos->data_size.value = data_sizes[index--];
-		IRDA_DEBUG(2, "%s(), reducing data size to %d\n",
-			   __func__, qos->data_size.value);
+		pr_debug("%s(), reducing data size to %d\n",
+			 __func__, qos->data_size.value);
 	}
 #else /* Use method described in section 6.6.11 of IrLAP */
 	while (irlap_requested_line_capacity(qos) > line_capacity) {
@@ -395,12 +392,12 @@ static void irlap_adjust_qos_settings(struct qos_info *qos)
 		/* Must be able to send at least one frame */
 		if (qos->window_size.value > 1) {
 			qos->window_size.value--;
-			IRDA_DEBUG(2, "%s(), reducing window size to %d\n",
-				   __func__, qos->window_size.value);
+			pr_debug("%s(), reducing window size to %d\n",
+				 __func__, qos->window_size.value);
 		} else if (index > 1) {
 			qos->data_size.value = data_sizes[index--];
-			IRDA_DEBUG(2, "%s(), reducing data size to %d\n",
-				   __func__, qos->data_size.value);
+			pr_debug("%s(), reducing data size to %d\n",
+				 __func__, qos->data_size.value);
 		} else {
 			net_warn_ratelimited("%s(), nothing more we can do!\n",
 					     __func__);
@@ -440,20 +437,20 @@ int irlap_qos_negotiate(struct irlap_cb *self, struct sk_buff *skb)
 
 	irlap_adjust_qos_settings(&self->qos_tx);
 
-	IRDA_DEBUG(2, "Setting BAUD_RATE to %d bps.\n",
-		   self->qos_tx.baud_rate.value);
-	IRDA_DEBUG(2, "Setting DATA_SIZE to %d bytes\n",
-		   self->qos_tx.data_size.value);
-	IRDA_DEBUG(2, "Setting WINDOW_SIZE to %d\n",
-		   self->qos_tx.window_size.value);
-	IRDA_DEBUG(2, "Setting XBOFS to %d\n",
-		   self->qos_tx.additional_bofs.value);
-	IRDA_DEBUG(2, "Setting MAX_TURN_TIME to %d ms.\n",
-		   self->qos_tx.max_turn_time.value);
-	IRDA_DEBUG(2, "Setting MIN_TURN_TIME to %d usecs.\n",
-		   self->qos_tx.min_turn_time.value);
-	IRDA_DEBUG(2, "Setting LINK_DISC to %d secs.\n",
-		   self->qos_tx.link_disc_time.value);
+	pr_debug("Setting BAUD_RATE to %d bps.\n",
+		 self->qos_tx.baud_rate.value);
+	pr_debug("Setting DATA_SIZE to %d bytes\n",
+		 self->qos_tx.data_size.value);
+	pr_debug("Setting WINDOW_SIZE to %d\n",
+		 self->qos_tx.window_size.value);
+	pr_debug("Setting XBOFS to %d\n",
+		 self->qos_tx.additional_bofs.value);
+	pr_debug("Setting MAX_TURN_TIME to %d ms.\n",
+		 self->qos_tx.max_turn_time.value);
+	pr_debug("Setting MIN_TURN_TIME to %d usecs.\n",
+		 self->qos_tx.min_turn_time.value);
+	pr_debug("Setting LINK_DISC to %d secs.\n",
+		 self->qos_tx.link_disc_time.value);
 	return ret;
 }
 
@@ -537,17 +534,17 @@ static int irlap_param_baud_rate(void *instance, irda_param_t *param, int get)
 
 	if (get) {
 		param->pv.i = self->qos_rx.baud_rate.bits;
-		IRDA_DEBUG(2, "%s(), baud rate = 0x%02x\n",
-			   __func__, param->pv.i);
+		pr_debug("%s(), baud rate = 0x%02x\n",
+			 __func__, param->pv.i);
 	} else {
 		/*
 		 *  Stations must agree on baud rate, so calculate
 		 *  intersection
 		 */
-		IRDA_DEBUG(2, "Requested BAUD_RATE: 0x%04x\n", (__u16) param->pv.i);
+		pr_debug("Requested BAUD_RATE: 0x%04x\n", (__u16)param->pv.i);
 		final = (__u16) param->pv.i & self->qos_rx.baud_rate.bits;
 
-		IRDA_DEBUG(2, "Final BAUD_RATE: 0x%04x\n", final);
+		pr_debug("Final BAUD_RATE: 0x%04x\n", final);
 		self->qos_tx.baud_rate.bits = final;
 		self->qos_rx.baud_rate.bits = final;
 	}
@@ -578,10 +575,10 @@ static int irlap_param_link_disconnect(void *instance, irda_param_t *param,
 		 *  Stations must agree on link disconnect/threshold
 		 *  time.
 		 */
-		IRDA_DEBUG(2, "LINK_DISC: %02x\n", (__u8) param->pv.i);
+		pr_debug("LINK_DISC: %02x\n", (__u8)param->pv.i);
 		final = (__u8) param->pv.i & self->qos_rx.link_disc_time.bits;
 
-		IRDA_DEBUG(2, "Final LINK_DISC: %02x\n", final);
+		pr_debug("Final LINK_DISC: %02x\n", final);
 		self->qos_tx.link_disc_time.bits = final;
 		self->qos_rx.link_disc_time.bits = final;
 	}
@@ -710,8 +707,8 @@ __u32 irlap_max_line_capacity(__u32 speed, __u32 max_turn_time)
 	__u32 line_capacity;
 	int i,j;
 
-	IRDA_DEBUG(2, "%s(), speed=%d, max_turn_time=%d\n",
-		   __func__, speed, max_turn_time);
+	pr_debug("%s(), speed=%d, max_turn_time=%d\n",
+		 __func__, speed, max_turn_time);
 
 	i = value_index(speed, baud_rates, 10);
 	j = value_index(max_turn_time, max_turn_times, 4);
@@ -721,8 +718,8 @@ __u32 irlap_max_line_capacity(__u32 speed, __u32 max_turn_time)
 
 	line_capacity = max_line_capacities[i][j];
 
-	IRDA_DEBUG(2, "%s(), line capacity=%d bytes\n",
-		   __func__, line_capacity);
+	pr_debug("%s(), line capacity=%d bytes\n",
+		 __func__, line_capacity);
 
 	return line_capacity;
 }
@@ -737,8 +734,8 @@ static __u32 irlap_requested_line_capacity(struct qos_info *qos)
 		irlap_min_turn_time_in_bytes(qos->baud_rate.value,
 					     qos->min_turn_time.value);
 
-	IRDA_DEBUG(2, "%s(), requested line capacity=%d\n",
-		   __func__, line_capacity);
+	pr_debug("%s(), requested line capacity=%d\n",
+		 __func__, line_capacity);
 
 	return line_capacity;
 }
diff --git a/net/irda/wrapper.c b/net/irda/wrapper.c
index 9efffeb8d0f..40a0f993bf1 100644
--- a/net/irda/wrapper.c
+++ b/net/irda/wrapper.c
@@ -106,17 +106,17 @@ int async_wrap_skb(struct sk_buff *skb, __u8 *tx_buff, int buffsize)
 		 * Nothing to worry about, but we set the default number of
 		 * BOF's
 		 */
-		IRDA_DEBUG(1, "%s(), wrong magic in skb!\n", __func__);
+		pr_debug("%s(), wrong magic in skb!\n", __func__);
 		xbofs = 10;
 	} else
 		xbofs = cb->xbofs + cb->xbofs_delay;
 
-	IRDA_DEBUG(4, "%s(), xbofs=%d\n", __func__, xbofs);
+	pr_debug("%s(), xbofs=%d\n", __func__, xbofs);
 
 	/* Check that we never use more than 115 + 48 xbofs */
 	if (xbofs > 163) {
-		IRDA_DEBUG(0, "%s(), too many xbofs (%d)\n", __func__,
-			   xbofs);
+		pr_debug("%s(), too many xbofs (%d)\n", __func__,
+			 xbofs);
 		xbofs = 163;
 	}
 
@@ -286,8 +286,8 @@ async_unwrap_bof(struct net_device *dev,
 	case INSIDE_FRAME:
 		/* Not supposed to happen, the previous frame is not
 		 * finished - Jean II */
-		IRDA_DEBUG(1, "%s(), Discarding incomplete frame\n",
-			   __func__);
+		pr_debug("%s(), Discarding incomplete frame\n",
+			 __func__);
 		stats->rx_errors++;
 		stats->rx_missed_errors++;
 		irda_device_set_media_busy(dev, TRUE);
@@ -360,7 +360,7 @@ async_unwrap_eof(struct net_device *dev,
 			/* Wrong CRC, discard frame!  */
 			irda_device_set_media_busy(dev, TRUE);
 
-			IRDA_DEBUG(1, "%s(), crc error\n", __func__);
+			pr_debug("%s(), crc error\n", __func__);
 			stats->rx_errors++;
 			stats->rx_crc_errors++;
 		}
@@ -420,8 +420,8 @@ async_unwrap_other(struct net_device *dev,
 			rx_buff->fcs = irda_fcs(rx_buff->fcs, byte);
 #endif
 		} else {
-			IRDA_DEBUG(1, "%s(), Rx buffer overflow, aborting\n",
-				   __func__);
+			pr_debug("%s(), Rx buffer overflow, aborting\n",
+				 __func__);
 			rx_buff->state = OUTSIDE_FRAME;
 		}
 		break;
@@ -439,8 +439,8 @@ async_unwrap_other(struct net_device *dev,
 #endif
 			rx_buff->state = INSIDE_FRAME;
 		} else {
-			IRDA_DEBUG(1, "%s(), Rx buffer overflow, aborting\n",
-				   __func__);
+			pr_debug("%s(), Rx buffer overflow, aborting\n",
+				 __func__);
 			rx_buff->state = OUTSIDE_FRAME;
 		}
 		break;
-- 
cgit v1.2.3-70-g09d2


From a8c5f90fb59a2d3bff0bd29adbb3e39fe0dd52f8 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Wed, 12 Nov 2014 11:54:09 -0800
Subject: ip_tunnel: Ops registration for secondary encap (fou, gue)

Instead of calling fou and gue functions directly from ip_tunnel
use ops for these that were previously registered. This patch adds the
logic to add and remove encapsulation operations for ip_tunnel,
and modified fou (and gue) to register with ip_tunnels.

This patch also addresses a circular dependency between ip_tunnel
and fou that was causing link errors when CONFIG_NET_IP_TUNNEL=y
and CONFIG_NET_FOU=m. References to fou an gue have been removed from
ip_tunnel.c

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/fou.h        | 25 ++------------
 include/net/ip_tunnels.h | 16 +++++++++
 net/ipv4/fou.c           | 85 ++++++++++++++++++++++++++++++++++++++++++++++++
 net/ipv4/ip_tunnel.c     | 78 ++++++++++++++++++++++++++++++--------------
 4 files changed, 157 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/include/net/fou.h b/include/net/fou.h
index 25b26ffcf1d..19b8a0c62a9 100644
--- a/include/net/fou.h
+++ b/include/net/fou.h
@@ -8,31 +8,12 @@
 #include <net/ip_tunnels.h>
 #include <net/udp.h>
 
+size_t fou_encap_hlen(struct ip_tunnel_encap *e);
+static size_t gue_encap_hlen(struct ip_tunnel_encap *e);
+
 int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 		     u8 *protocol, struct flowi4 *fl4);
 int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 		     u8 *protocol, struct flowi4 *fl4);
 
-static size_t fou_encap_hlen(struct ip_tunnel_encap *e)
-{
-	return sizeof(struct udphdr);
-}
-
-static size_t gue_encap_hlen(struct ip_tunnel_encap *e)
-{
-	size_t len;
-	bool need_priv = false;
-
-	len = sizeof(struct udphdr) + sizeof(struct guehdr);
-
-	if (e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) {
-		len += GUE_PLEN_REMCSUM;
-		need_priv = true;
-	}
-
-	len += need_priv ? GUE_LEN_PRIV : 0;
-
-	return len;
-}
-
 #endif
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 5bc6edeb714..25a59eb388a 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -117,6 +117,22 @@ struct ip_tunnel_net {
 	struct hlist_head tunnels[IP_TNL_HASH_SIZE];
 };
 
+struct ip_tunnel_encap_ops {
+	size_t (*encap_hlen)(struct ip_tunnel_encap *e);
+	int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
+			    u8 *protocol, struct flowi4 *fl4);
+};
+
+#define MAX_IPTUN_ENCAP_OPS 8
+
+extern const struct ip_tunnel_encap_ops __rcu *
+		iptun_encaps[MAX_IPTUN_ENCAP_OPS];
+
+int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op,
+			    unsigned int num);
+int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
+			    unsigned int num);
+
 #ifdef CONFIG_INET
 
 int ip_tunnel_init(struct net_device *dev);
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 740ae099a0d..fe0907774ce 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -668,6 +668,30 @@ static const struct genl_ops fou_nl_ops[] = {
 	},
 };
 
+size_t fou_encap_hlen(struct ip_tunnel_encap *e)
+{
+	return sizeof(struct udphdr);
+}
+EXPORT_SYMBOL(fou_encap_hlen);
+
+size_t gue_encap_hlen(struct ip_tunnel_encap *e)
+{
+	size_t len;
+	bool need_priv = false;
+
+	len = sizeof(struct udphdr) + sizeof(struct guehdr);
+
+	if (e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) {
+		len += GUE_PLEN_REMCSUM;
+		need_priv = true;
+	}
+
+	len += need_priv ? GUE_LEN_PRIV : 0;
+
+	return len;
+}
+EXPORT_SYMBOL(gue_encap_hlen);
+
 static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e,
 			  struct flowi4 *fl4, u8 *protocol, __be16 sport)
 {
@@ -787,6 +811,57 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 }
 EXPORT_SYMBOL(gue_build_header);
 
+#ifdef CONFIG_NET_FOU_IP_TUNNELS
+
+static const struct ip_tunnel_encap_ops __read_mostly fou_iptun_ops = {
+	.encap_hlen = fou_encap_hlen,
+	.build_header = fou_build_header,
+};
+
+static const struct ip_tunnel_encap_ops __read_mostly gue_iptun_ops = {
+	.encap_hlen = gue_encap_hlen,
+	.build_header = gue_build_header,
+};
+
+static int ip_tunnel_encap_add_fou_ops(void)
+{
+	int ret;
+
+	ret = ip_tunnel_encap_add_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU);
+	if (ret < 0) {
+		pr_err("can't add fou ops\n");
+		return ret;
+	}
+
+	ret = ip_tunnel_encap_add_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE);
+	if (ret < 0) {
+		pr_err("can't add gue ops\n");
+		ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void ip_tunnel_encap_del_fou_ops(void)
+{
+	ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU);
+	ip_tunnel_encap_del_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE);
+}
+
+#else
+
+static int ip_tunnel_encap_add_fou_ops(void)
+{
+	return 0;
+}
+
+static int ip_tunnel_encap_del_fou_ops(void)
+{
+}
+
+#endif
+
 static int __init fou_init(void)
 {
 	int ret;
@@ -794,6 +869,14 @@ static int __init fou_init(void)
 	ret = genl_register_family_with_ops(&fou_nl_family,
 					    fou_nl_ops);
 
+	if (ret < 0)
+		goto exit;
+
+	ret = ip_tunnel_encap_add_fou_ops();
+	if (ret < 0)
+		genl_unregister_family(&fou_nl_family);
+
+exit:
 	return ret;
 }
 
@@ -801,6 +884,8 @@ static void __exit fou_fini(void)
 {
 	struct fou *fou, *next;
 
+	ip_tunnel_encap_del_fou_ops();
+
 	genl_unregister_family(&fou_nl_family);
 
 	/* Close all the FOU sockets */
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index c3587e1c8b8..63e745aadab 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -57,10 +57,6 @@
 #include <net/rtnetlink.h>
 #include <net/udp.h>
 
-#if IS_ENABLED(CONFIG_NET_FOU)
-#include <net/fou.h>
-#endif
-
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
 #include <net/ip6_fib.h>
@@ -494,19 +490,50 @@ EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
 
 static int ip_encap_hlen(struct ip_tunnel_encap *e)
 {
-	switch (e->type) {
-	case TUNNEL_ENCAP_NONE:
+	const struct ip_tunnel_encap_ops *ops;
+	int hlen = -EINVAL;
+
+	if (e->type == TUNNEL_ENCAP_NONE)
 		return 0;
-#if IS_ENABLED(CONFIG_NET_FOU)
-	case TUNNEL_ENCAP_FOU:
-		return fou_encap_hlen(e);
-	case TUNNEL_ENCAP_GUE:
-		return gue_encap_hlen(e);
-#endif
-	default:
+
+	if (e->type >= MAX_IPTUN_ENCAP_OPS)
 		return -EINVAL;
-	}
+
+	rcu_read_lock();
+	ops = rcu_dereference(iptun_encaps[e->type]);
+	if (likely(ops && ops->encap_hlen))
+		hlen = ops->encap_hlen(e);
+	rcu_read_unlock();
+
+	return hlen;
+}
+
+const struct ip_tunnel_encap_ops __rcu *
+		iptun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
+
+int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *ops,
+			    unsigned int num)
+{
+	return !cmpxchg((const struct ip_tunnel_encap_ops **)
+			&iptun_encaps[num],
+			NULL, ops) ? 0 : -1;
 }
+EXPORT_SYMBOL(ip_tunnel_encap_add_ops);
+
+int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *ops,
+			    unsigned int num)
+{
+	int ret;
+
+	ret = (cmpxchg((const struct ip_tunnel_encap_ops **)
+		       &iptun_encaps[num],
+		       ops, NULL) == ops) ? 0 : -1;
+
+	synchronize_net();
+
+	return ret;
+}
+EXPORT_SYMBOL(ip_tunnel_encap_del_ops);
 
 int ip_tunnel_encap_setup(struct ip_tunnel *t,
 			  struct ip_tunnel_encap *ipencap)
@@ -534,18 +561,19 @@ EXPORT_SYMBOL_GPL(ip_tunnel_encap_setup);
 int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
 		    u8 *protocol, struct flowi4 *fl4)
 {
-	switch (t->encap.type) {
-	case TUNNEL_ENCAP_NONE:
+	const struct ip_tunnel_encap_ops *ops;
+	int ret = -EINVAL;
+
+	if (t->encap.type == TUNNEL_ENCAP_NONE)
 		return 0;
-#if IS_ENABLED(CONFIG_NET_FOU)
-	case TUNNEL_ENCAP_FOU:
-		return fou_build_header(skb, &t->encap, protocol, fl4);
-	case TUNNEL_ENCAP_GUE:
-		return gue_build_header(skb, &t->encap, protocol, fl4);
-#endif
-	default:
-		return -EINVAL;
-	}
+
+	rcu_read_lock();
+	ops = rcu_dereference(iptun_encaps[t->encap.type]);
+	if (likely(ops && ops->build_header))
+		ret = ops->build_header(skb, &t->encap, protocol, fl4);
+	rcu_read_unlock();
+
+	return ret;
 }
 EXPORT_SYMBOL(ip_tunnel_encap);
 
-- 
cgit v1.2.3-70-g09d2


From b82b6cca488074da3852e8a54fde1d9f74bf1557 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Wed, 12 Nov 2014 16:03:50 +0100
Subject: cpuidle: Invert CPUIDLE_FLAG_TIME_VALID logic

The only place where the time is invalid is when the ACPI_CSTATE_FFH entry
method is not set. Otherwise for all the drivers, the time can be correctly
measured.

Instead of duplicating the CPUIDLE_FLAG_TIME_VALID flag in all the drivers
for all the states, just invert the logic by replacing it by the flag
CPUIDLE_FLAG_TIME_INVALID, hence we can set this flag only for the acpi idle
driver, remove the former flag from all the drivers and invert the logic with
this flag in the different governor.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/arm/include/asm/cpuidle.h         |   1 -
 arch/arm/mach-davinci/cpuidle.c        |   1 -
 arch/arm/mach-imx/cpuidle-imx5.c       |   1 -
 arch/arm/mach-imx/cpuidle-imx6q.c      |   3 +-
 arch/arm/mach-imx/cpuidle-imx6sl.c     |   3 +-
 arch/arm/mach-omap2/cpuidle34xx.c      |   7 ---
 arch/arm/mach-omap2/cpuidle44xx.c      |   5 +-
 arch/arm/mach-s3c64xx/cpuidle.c        |   1 -
 arch/arm/mach-shmobile/pm-sh7372.c     |   4 --
 arch/arm/mach-tegra/cpuidle-tegra114.c |   1 -
 arch/arm/mach-tegra/cpuidle-tegra20.c  |   3 +-
 arch/arm/mach-tegra/cpuidle-tegra30.c  |   1 -
 arch/mips/include/asm/idle.h           |   1 -
 arch/sh/kernel/cpu/shmobile/cpuidle.c  |   3 -
 arch/x86/kernel/apm_32.c               |   1 -
 drivers/acpi/processor_idle.c          |   6 +-
 drivers/cpuidle/cpuidle-arm64.c        |   1 -
 drivers/cpuidle/cpuidle-at91.c         |   1 -
 drivers/cpuidle/cpuidle-big_little.c   |   6 +-
 drivers/cpuidle/cpuidle-calxeda.c      |   1 -
 drivers/cpuidle/cpuidle-cps.c          |   7 +--
 drivers/cpuidle/cpuidle-exynos.c       |   1 -
 drivers/cpuidle/cpuidle-kirkwood.c     |   1 -
 drivers/cpuidle/cpuidle-mvebu-v7.c     |   8 +--
 drivers/cpuidle/cpuidle-powernv.c      |   6 +-
 drivers/cpuidle/cpuidle-pseries.c      |   3 -
 drivers/cpuidle/cpuidle-ux500.c        |   3 +-
 drivers/cpuidle/cpuidle-zynq.c         |   1 -
 drivers/cpuidle/driver.c               |   1 -
 drivers/cpuidle/dt_idle_states.c       |   2 +-
 drivers/cpuidle/governors/ladder.c     |   2 +-
 drivers/cpuidle/governors/menu.c       |   2 +-
 drivers/idle/intel_idle.c              | 108 ++++++++++++++++-----------------
 include/linux/cpuidle.h                |   4 +-
 34 files changed, 75 insertions(+), 125 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/cpuidle.h b/arch/arm/include/asm/cpuidle.h
index 2fca60ab513..af319ac4960 100644
--- a/arch/arm/include/asm/cpuidle.h
+++ b/arch/arm/include/asm/cpuidle.h
@@ -15,7 +15,6 @@ static inline int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
 	.exit_latency           = 1,\
 	.target_residency       = 1,\
 	.power_usage		= p,\
-	.flags                  = CPUIDLE_FLAG_TIME_VALID,\
 	.name                   = "WFI",\
 	.desc                   = "ARM WFI",\
 }
diff --git a/arch/arm/mach-davinci/cpuidle.c b/arch/arm/mach-davinci/cpuidle.c
index f1ac1c94ac0..b4675fc28f8 100644
--- a/arch/arm/mach-davinci/cpuidle.c
+++ b/arch/arm/mach-davinci/cpuidle.c
@@ -66,7 +66,6 @@ static struct cpuidle_driver davinci_idle_driver = {
 		.enter			= davinci_enter_idle,
 		.exit_latency		= 10,
 		.target_residency	= 10000,
-		.flags			= CPUIDLE_FLAG_TIME_VALID,
 		.name			= "DDR SR",
 		.desc			= "WFI and DDR Self Refresh",
 	},
diff --git a/arch/arm/mach-imx/cpuidle-imx5.c b/arch/arm/mach-imx/cpuidle-imx5.c
index 5a47e3c6172..3feca526d16 100644
--- a/arch/arm/mach-imx/cpuidle-imx5.c
+++ b/arch/arm/mach-imx/cpuidle-imx5.c
@@ -24,7 +24,6 @@ static struct cpuidle_driver imx5_cpuidle_driver = {
 		.enter            = imx5_cpuidle_enter,
 		.exit_latency     = 2,
 		.target_residency = 1,
-		.flags            = CPUIDLE_FLAG_TIME_VALID,
 		.name             = "IMX5 SRPG",
 		.desc             = "CPU state retained,powered off",
 	},
diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c
index aa935787b74..d76d08623f9 100644
--- a/arch/arm/mach-imx/cpuidle-imx6q.c
+++ b/arch/arm/mach-imx/cpuidle-imx6q.c
@@ -53,8 +53,7 @@ static struct cpuidle_driver imx6q_cpuidle_driver = {
 		{
 			.exit_latency = 50,
 			.target_residency = 75,
-			.flags = CPUIDLE_FLAG_TIME_VALID |
-			         CPUIDLE_FLAG_TIMER_STOP,
+			.flags = CPUIDLE_FLAG_TIMER_STOP,
 			.enter = imx6q_enter_wait,
 			.name = "WAIT",
 			.desc = "Clock off",
diff --git a/arch/arm/mach-imx/cpuidle-imx6sl.c b/arch/arm/mach-imx/cpuidle-imx6sl.c
index d4b6b8171fa..7d92e658455 100644
--- a/arch/arm/mach-imx/cpuidle-imx6sl.c
+++ b/arch/arm/mach-imx/cpuidle-imx6sl.c
@@ -40,8 +40,7 @@ static struct cpuidle_driver imx6sl_cpuidle_driver = {
 		{
 			.exit_latency = 50,
 			.target_residency = 75,
-			.flags = CPUIDLE_FLAG_TIME_VALID |
-				CPUIDLE_FLAG_TIMER_STOP,
+			.flags = CPUIDLE_FLAG_TIMER_STOP,
 			.enter = imx6sl_enter_wait,
 			.name = "WAIT",
 			.desc = "Clock off",
diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c
index e18709d3b95..aa7b379e266 100644
--- a/arch/arm/mach-omap2/cpuidle34xx.c
+++ b/arch/arm/mach-omap2/cpuidle34xx.c
@@ -265,7 +265,6 @@ static struct cpuidle_driver omap3_idle_driver = {
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 2 + 2,
 			.target_residency = 5,
-			.flags		  = CPUIDLE_FLAG_TIME_VALID,
 			.name		  = "C1",
 			.desc		  = "MPU ON + CORE ON",
 		},
@@ -273,7 +272,6 @@ static struct cpuidle_driver omap3_idle_driver = {
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 10 + 10,
 			.target_residency = 30,
-			.flags		  = CPUIDLE_FLAG_TIME_VALID,
 			.name		  = "C2",
 			.desc		  = "MPU ON + CORE ON",
 		},
@@ -281,7 +279,6 @@ static struct cpuidle_driver omap3_idle_driver = {
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 50 + 50,
 			.target_residency = 300,
-			.flags		  = CPUIDLE_FLAG_TIME_VALID,
 			.name		  = "C3",
 			.desc		  = "MPU RET + CORE ON",
 		},
@@ -289,7 +286,6 @@ static struct cpuidle_driver omap3_idle_driver = {
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 1500 + 1800,
 			.target_residency = 4000,
-			.flags		  = CPUIDLE_FLAG_TIME_VALID,
 			.name		  = "C4",
 			.desc		  = "MPU OFF + CORE ON",
 		},
@@ -297,7 +293,6 @@ static struct cpuidle_driver omap3_idle_driver = {
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 2500 + 7500,
 			.target_residency = 12000,
-			.flags		  = CPUIDLE_FLAG_TIME_VALID,
 			.name		  = "C5",
 			.desc		  = "MPU RET + CORE RET",
 		},
@@ -305,7 +300,6 @@ static struct cpuidle_driver omap3_idle_driver = {
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 3000 + 8500,
 			.target_residency = 15000,
-			.flags		  = CPUIDLE_FLAG_TIME_VALID,
 			.name		  = "C6",
 			.desc		  = "MPU OFF + CORE RET",
 		},
@@ -313,7 +307,6 @@ static struct cpuidle_driver omap3_idle_driver = {
 			.enter		  = omap3_enter_idle_bm,
 			.exit_latency	  = 10000 + 30000,
 			.target_residency = 30000,
-			.flags		  = CPUIDLE_FLAG_TIME_VALID,
 			.name		  = "C7",
 			.desc		  = "MPU OFF + CORE OFF",
 		},
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index 2498ab025fa..01e398a868b 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -196,7 +196,6 @@ static struct cpuidle_driver omap4_idle_driver = {
 			/* C1 - CPU0 ON + CPU1 ON + MPU ON */
 			.exit_latency = 2 + 2,
 			.target_residency = 5,
-			.flags = CPUIDLE_FLAG_TIME_VALID,
 			.enter = omap_enter_idle_simple,
 			.name = "C1",
 			.desc = "CPUx ON, MPUSS ON"
@@ -205,7 +204,7 @@ static struct cpuidle_driver omap4_idle_driver = {
 			/* C2 - CPU0 OFF + CPU1 OFF + MPU CSWR */
 			.exit_latency = 328 + 440,
 			.target_residency = 960,
-			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED,
+			.flags = CPUIDLE_FLAG_COUPLED,
 			.enter = omap_enter_idle_coupled,
 			.name = "C2",
 			.desc = "CPUx OFF, MPUSS CSWR",
@@ -214,7 +213,7 @@ static struct cpuidle_driver omap4_idle_driver = {
 			/* C3 - CPU0 OFF + CPU1 OFF + MPU OSWR */
 			.exit_latency = 460 + 518,
 			.target_residency = 1100,
-			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED,
+			.flags = CPUIDLE_FLAG_COUPLED,
 			.enter = omap_enter_idle_coupled,
 			.name = "C3",
 			.desc = "CPUx OFF, MPUSS OSWR",
diff --git a/arch/arm/mach-s3c64xx/cpuidle.c b/arch/arm/mach-s3c64xx/cpuidle.c
index 3c8ab07c201..2eb072440df 100644
--- a/arch/arm/mach-s3c64xx/cpuidle.c
+++ b/arch/arm/mach-s3c64xx/cpuidle.c
@@ -48,7 +48,6 @@ static struct cpuidle_driver s3c64xx_cpuidle_driver = {
 			.enter            = s3c64xx_enter_idle,
 			.exit_latency     = 1,
 			.target_residency = 1,
-			.flags            = CPUIDLE_FLAG_TIME_VALID,
 			.name             = "IDLE",
 			.desc             = "System active, ARM gated",
 		},
diff --git a/arch/arm/mach-shmobile/pm-sh7372.c b/arch/arm/mach-shmobile/pm-sh7372.c
index 7e5c2676c48..0e37da654ed 100644
--- a/arch/arm/mach-shmobile/pm-sh7372.c
+++ b/arch/arm/mach-shmobile/pm-sh7372.c
@@ -423,7 +423,6 @@ static struct cpuidle_driver sh7372_cpuidle_driver = {
 		.desc = "Core Standby Mode",
 		.exit_latency = 10,
 		.target_residency = 20 + 10,
-		.flags = CPUIDLE_FLAG_TIME_VALID,
 		.enter = sh7372_enter_core_standby,
 	},
 	.states[2] = {
@@ -431,7 +430,6 @@ static struct cpuidle_driver sh7372_cpuidle_driver = {
 		.desc = "A3SM PLL ON",
 		.exit_latency = 20,
 		.target_residency = 30 + 20,
-		.flags = CPUIDLE_FLAG_TIME_VALID,
 		.enter = sh7372_enter_a3sm_pll_on,
 	},
 	.states[3] = {
@@ -439,7 +437,6 @@ static struct cpuidle_driver sh7372_cpuidle_driver = {
 		.desc = "A3SM PLL OFF",
 		.exit_latency = 120,
 		.target_residency = 30 + 120,
-		.flags = CPUIDLE_FLAG_TIME_VALID,
 		.enter = sh7372_enter_a3sm_pll_off,
 	},
 	.states[4] = {
@@ -447,7 +444,6 @@ static struct cpuidle_driver sh7372_cpuidle_driver = {
 		.desc = "A4S PLL OFF",
 		.exit_latency = 240,
 		.target_residency = 30 + 240,
-		.flags = CPUIDLE_FLAG_TIME_VALID,
 		.enter = sh7372_enter_a4s,
 		.disabled = true,
 	},
diff --git a/arch/arm/mach-tegra/cpuidle-tegra114.c b/arch/arm/mach-tegra/cpuidle-tegra114.c
index e3ebdce3e71..b30908235d5 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra114.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra114.c
@@ -75,7 +75,6 @@ static struct cpuidle_driver tegra_idle_driver = {
 			.exit_latency		= 500,
 			.target_residency	= 1000,
 			.power_usage		= 0,
-			.flags			= CPUIDLE_FLAG_TIME_VALID,
 			.name			= "powered-down",
 			.desc			= "CPU power gated",
 		},
diff --git a/arch/arm/mach-tegra/cpuidle-tegra20.c b/arch/arm/mach-tegra/cpuidle-tegra20.c
index b30bf5cba65..4f25a7c7ca0 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra20.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra20.c
@@ -59,8 +59,7 @@ static struct cpuidle_driver tegra_idle_driver = {
 			.exit_latency     = 5000,
 			.target_residency = 10000,
 			.power_usage      = 0,
-			.flags            = CPUIDLE_FLAG_TIME_VALID |
-			CPUIDLE_FLAG_COUPLED,
+			.flags            = CPUIDLE_FLAG_COUPLED,
 			.name             = "powered-down",
 			.desc             = "CPU power gated",
 		},
diff --git a/arch/arm/mach-tegra/cpuidle-tegra30.c b/arch/arm/mach-tegra/cpuidle-tegra30.c
index 35561274f6c..f8815ed65d9 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra30.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra30.c
@@ -56,7 +56,6 @@ static struct cpuidle_driver tegra_idle_driver = {
 			.exit_latency		= 2000,
 			.target_residency	= 2200,
 			.power_usage		= 0,
-			.flags			= CPUIDLE_FLAG_TIME_VALID,
 			.name			= "powered-down",
 			.desc			= "CPU power gated",
 		},
diff --git a/arch/mips/include/asm/idle.h b/arch/mips/include/asm/idle.h
index 1c967abd545..a2d18ab57ac 100644
--- a/arch/mips/include/asm/idle.h
+++ b/arch/mips/include/asm/idle.h
@@ -22,7 +22,6 @@ extern int mips_cpuidle_wait_enter(struct cpuidle_device *dev,
 	.exit_latency		= 1,\
 	.target_residency	= 1,\
 	.power_usage		= UINT_MAX,\
-	.flags			= CPUIDLE_FLAG_TIME_VALID,\
 	.name			= "wait",\
 	.desc			= "MIPS wait",\
 }
diff --git a/arch/sh/kernel/cpu/shmobile/cpuidle.c b/arch/sh/kernel/cpu/shmobile/cpuidle.c
index e3abfd4277e..53b8eeb1db2 100644
--- a/arch/sh/kernel/cpu/shmobile/cpuidle.c
+++ b/arch/sh/kernel/cpu/shmobile/cpuidle.c
@@ -59,7 +59,6 @@ static struct cpuidle_driver cpuidle_driver = {
 			.exit_latency = 1,
 			.target_residency = 1 * 2,
 			.power_usage = 3,
-			.flags = CPUIDLE_FLAG_TIME_VALID,
 			.enter = cpuidle_sleep_enter,
 			.name = "C1",
 			.desc = "SuperH Sleep Mode",
@@ -68,7 +67,6 @@ static struct cpuidle_driver cpuidle_driver = {
 			.exit_latency = 100,
 			.target_residency = 1 * 2,
 			.power_usage = 1,
-			.flags = CPUIDLE_FLAG_TIME_VALID,
 			.enter = cpuidle_sleep_enter,
 			.name = "C2",
 			.desc = "SuperH Sleep Mode [SF]",
@@ -78,7 +76,6 @@ static struct cpuidle_driver cpuidle_driver = {
 			.exit_latency = 2300,
 			.target_residency = 1 * 2,
 			.power_usage = 1,
-			.flags = CPUIDLE_FLAG_TIME_VALID,
 			.enter = cpuidle_sleep_enter,
 			.name = "C3",
 			.desc = "SuperH Mobile Standby Mode [SF]",
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 58487445141..927ec923594 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -378,7 +378,6 @@ static struct cpuidle_driver apm_idle_driver = {
 		{ /* entry 1 is for APM idle */
 			.name = "APM",
 			.desc = "APM idle",
-			.flags = CPUIDLE_FLAG_TIME_VALID,
 			.exit_latency = 250,	/* WAG */
 			.target_residency = 500,	/* WAG */
 			.enter = &apm_cpu_idle
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 17f9ec50197..380b4b43f36 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -985,8 +985,8 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr)
 		state->flags = 0;
 		switch (cx->type) {
 			case ACPI_STATE_C1:
-			if (cx->entry_method == ACPI_CSTATE_FFH)
-				state->flags |= CPUIDLE_FLAG_TIME_VALID;
+			if (cx->entry_method != ACPI_CSTATE_FFH)
+				state->flags |= CPUIDLE_FLAG_TIME_INVALID;
 
 			state->enter = acpi_idle_enter_c1;
 			state->enter_dead = acpi_idle_play_dead;
@@ -994,14 +994,12 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr)
 			break;
 
 			case ACPI_STATE_C2:
-			state->flags |= CPUIDLE_FLAG_TIME_VALID;
 			state->enter = acpi_idle_enter_simple;
 			state->enter_dead = acpi_idle_play_dead;
 			drv->safe_state_index = count;
 			break;
 
 			case ACPI_STATE_C3:
-			state->flags |= CPUIDLE_FLAG_TIME_VALID;
 			state->enter = pr->flags.bm_check ?
 					acpi_idle_enter_bm :
 					acpi_idle_enter_simple;
diff --git a/drivers/cpuidle/cpuidle-arm64.c b/drivers/cpuidle/cpuidle-arm64.c
index 50997ea942f..87320e62c72 100644
--- a/drivers/cpuidle/cpuidle-arm64.c
+++ b/drivers/cpuidle/cpuidle-arm64.c
@@ -73,7 +73,6 @@ static struct cpuidle_driver arm64_idle_driver = {
 		.exit_latency           = 1,
 		.target_residency       = 1,
 		.power_usage		= UINT_MAX,
-		.flags                  = CPUIDLE_FLAG_TIME_VALID,
 		.name                   = "WFI",
 		.desc                   = "ARM64 WFI",
 	}
diff --git a/drivers/cpuidle/cpuidle-at91.c b/drivers/cpuidle/cpuidle-at91.c
index a0774370c6b..1964ff07117 100644
--- a/drivers/cpuidle/cpuidle-at91.c
+++ b/drivers/cpuidle/cpuidle-at91.c
@@ -43,7 +43,6 @@ static struct cpuidle_driver at91_idle_driver = {
 		.enter			= at91_enter_idle,
 		.exit_latency		= 10,
 		.target_residency	= 10000,
-		.flags			= CPUIDLE_FLAG_TIME_VALID,
 		.name			= "RAM_SR",
 		.desc			= "WFI and DDR Self Refresh",
 	},
diff --git a/drivers/cpuidle/cpuidle-big_little.c b/drivers/cpuidle/cpuidle-big_little.c
index fbc00a1d3c4..e3e225fe6b4 100644
--- a/drivers/cpuidle/cpuidle-big_little.c
+++ b/drivers/cpuidle/cpuidle-big_little.c
@@ -67,8 +67,7 @@ static struct cpuidle_driver bl_idle_little_driver = {
 		.enter			= bl_enter_powerdown,
 		.exit_latency		= 700,
 		.target_residency	= 2500,
-		.flags			= CPUIDLE_FLAG_TIME_VALID |
-					  CPUIDLE_FLAG_TIMER_STOP,
+		.flags			= CPUIDLE_FLAG_TIMER_STOP,
 		.name			= "C1",
 		.desc			= "ARM little-cluster power down",
 	},
@@ -89,8 +88,7 @@ static struct cpuidle_driver bl_idle_big_driver = {
 		.enter			= bl_enter_powerdown,
 		.exit_latency		= 500,
 		.target_residency	= 2000,
-		.flags			= CPUIDLE_FLAG_TIME_VALID |
-					  CPUIDLE_FLAG_TIMER_STOP,
+		.flags			= CPUIDLE_FLAG_TIMER_STOP,
 		.name			= "C1",
 		.desc			= "ARM big-cluster power down",
 	},
diff --git a/drivers/cpuidle/cpuidle-calxeda.c b/drivers/cpuidle/cpuidle-calxeda.c
index 6e51114057d..6541b0bfdfa 100644
--- a/drivers/cpuidle/cpuidle-calxeda.c
+++ b/drivers/cpuidle/cpuidle-calxeda.c
@@ -55,7 +55,6 @@ static struct cpuidle_driver calxeda_idle_driver = {
 		{
 			.name = "PG",
 			.desc = "Power Gate",
-			.flags = CPUIDLE_FLAG_TIME_VALID,
 			.exit_latency = 30,
 			.power_usage = 50,
 			.target_residency = 200,
diff --git a/drivers/cpuidle/cpuidle-cps.c b/drivers/cpuidle/cpuidle-cps.c
index fc7b62720de..1adb6980b70 100644
--- a/drivers/cpuidle/cpuidle-cps.c
+++ b/drivers/cpuidle/cpuidle-cps.c
@@ -79,7 +79,6 @@ static struct cpuidle_driver cps_driver = {
 			.enter	= cps_nc_enter,
 			.exit_latency		= 200,
 			.target_residency	= 450,
-			.flags	= CPUIDLE_FLAG_TIME_VALID,
 			.name	= "nc-wait",
 			.desc	= "non-coherent MIPS wait",
 		},
@@ -87,8 +86,7 @@ static struct cpuidle_driver cps_driver = {
 			.enter	= cps_nc_enter,
 			.exit_latency		= 300,
 			.target_residency	= 700,
-			.flags	= CPUIDLE_FLAG_TIME_VALID |
-				  CPUIDLE_FLAG_TIMER_STOP,
+			.flags	= CPUIDLE_FLAG_TIMER_STOP,
 			.name	= "clock-gated",
 			.desc	= "core clock gated",
 		},
@@ -96,8 +94,7 @@ static struct cpuidle_driver cps_driver = {
 			.enter	= cps_nc_enter,
 			.exit_latency		= 600,
 			.target_residency	= 1000,
-			.flags	= CPUIDLE_FLAG_TIME_VALID |
-				  CPUIDLE_FLAG_TIMER_STOP,
+			.flags	= CPUIDLE_FLAG_TIMER_STOP,
 			.name	= "power-gated",
 			.desc	= "core power gated",
 		},
diff --git a/drivers/cpuidle/cpuidle-exynos.c b/drivers/cpuidle/cpuidle-exynos.c
index ba9b34b579f..64d12a855ec 100644
--- a/drivers/cpuidle/cpuidle-exynos.c
+++ b/drivers/cpuidle/cpuidle-exynos.c
@@ -47,7 +47,6 @@ static struct cpuidle_driver exynos_idle_driver = {
 			.enter			= exynos_enter_lowpower,
 			.exit_latency		= 300,
 			.target_residency	= 100000,
-			.flags			= CPUIDLE_FLAG_TIME_VALID,
 			.name			= "C1",
 			.desc			= "ARM power down",
 		},
diff --git a/drivers/cpuidle/cpuidle-kirkwood.c b/drivers/cpuidle/cpuidle-kirkwood.c
index 41ba843251b..d88f8d7c214 100644
--- a/drivers/cpuidle/cpuidle-kirkwood.c
+++ b/drivers/cpuidle/cpuidle-kirkwood.c
@@ -47,7 +47,6 @@ static struct cpuidle_driver kirkwood_idle_driver = {
 		.enter			= kirkwood_enter_idle,
 		.exit_latency		= 10,
 		.target_residency	= 100000,
-		.flags			= CPUIDLE_FLAG_TIME_VALID,
 		.name			= "DDR SR",
 		.desc			= "WFI and DDR Self Refresh",
 	},
diff --git a/drivers/cpuidle/cpuidle-mvebu-v7.c b/drivers/cpuidle/cpuidle-mvebu-v7.c
index 45371bb1621..dd4c176df2a 100644
--- a/drivers/cpuidle/cpuidle-mvebu-v7.c
+++ b/drivers/cpuidle/cpuidle-mvebu-v7.c
@@ -53,7 +53,6 @@ static struct cpuidle_driver armadaxp_idle_driver = {
 		.exit_latency		= 10,
 		.power_usage		= 50,
 		.target_residency	= 100,
-		.flags			= CPUIDLE_FLAG_TIME_VALID,
 		.name			= "MV CPU IDLE",
 		.desc			= "CPU power down",
 	},
@@ -62,8 +61,7 @@ static struct cpuidle_driver armadaxp_idle_driver = {
 		.exit_latency		= 100,
 		.power_usage		= 5,
 		.target_residency	= 1000,
-		.flags			= CPUIDLE_FLAG_TIME_VALID |
-						MVEBU_V7_FLAG_DEEP_IDLE,
+		.flags			= MVEBU_V7_FLAG_DEEP_IDLE,
 		.name			= "MV CPU DEEP IDLE",
 		.desc			= "CPU and L2 Fabric power down",
 	},
@@ -78,8 +76,7 @@ static struct cpuidle_driver armada370_idle_driver = {
 		.exit_latency		= 100,
 		.power_usage		= 5,
 		.target_residency	= 1000,
-		.flags			= (CPUIDLE_FLAG_TIME_VALID |
-					   MVEBU_V7_FLAG_DEEP_IDLE),
+		.flags			= MVEBU_V7_FLAG_DEEP_IDLE,
 		.name			= "Deep Idle",
 		.desc			= "CPU and L2 Fabric power down",
 	},
@@ -94,7 +91,6 @@ static struct cpuidle_driver armada38x_idle_driver = {
 		.exit_latency		= 10,
 		.power_usage		= 5,
 		.target_residency	= 100,
-		.flags			= CPUIDLE_FLAG_TIME_VALID,
 		.name			= "Idle",
 		.desc			= "CPU and SCU power down",
 	},
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 7d3a3497dd4..e9248bb9173 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -93,7 +93,6 @@ static struct cpuidle_state powernv_states[MAX_POWERNV_IDLE_STATES] = {
 	{ /* Snooze */
 		.name = "snooze",
 		.desc = "snooze",
-		.flags = CPUIDLE_FLAG_TIME_VALID,
 		.exit_latency = 0,
 		.target_residency = 0,
 		.enter = &snooze_loop },
@@ -202,7 +201,7 @@ static int powernv_add_idle_states(void)
 			/* Add NAP state */
 			strcpy(powernv_states[nr_idle_states].name, "Nap");
 			strcpy(powernv_states[nr_idle_states].desc, "Nap");
-			powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIME_VALID;
+			powernv_states[nr_idle_states].flags = 0;
 			powernv_states[nr_idle_states].exit_latency =
 					((unsigned int)latency_ns) / 1000;
 			powernv_states[nr_idle_states].target_residency =
@@ -215,8 +214,7 @@ static int powernv_add_idle_states(void)
 			/* Add FASTSLEEP state */
 			strcpy(powernv_states[nr_idle_states].name, "FastSleep");
 			strcpy(powernv_states[nr_idle_states].desc, "FastSleep");
-			powernv_states[nr_idle_states].flags =
-				CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TIMER_STOP;
+			powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIMER_STOP;
 			powernv_states[nr_idle_states].exit_latency =
 					((unsigned int)latency_ns) / 1000;
 			powernv_states[nr_idle_states].target_residency =
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 6f7b0195688..bb9e2b6f3ec 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -142,14 +142,12 @@ static struct cpuidle_state dedicated_states[] = {
 	{ /* Snooze */
 		.name = "snooze",
 		.desc = "snooze",
-		.flags = CPUIDLE_FLAG_TIME_VALID,
 		.exit_latency = 0,
 		.target_residency = 0,
 		.enter = &snooze_loop },
 	{ /* CEDE */
 		.name = "CEDE",
 		.desc = "CEDE",
-		.flags = CPUIDLE_FLAG_TIME_VALID,
 		.exit_latency = 10,
 		.target_residency = 100,
 		.enter = &dedicated_cede_loop },
@@ -162,7 +160,6 @@ static struct cpuidle_state shared_states[] = {
 	{ /* Shared Cede */
 		.name = "Shared Cede",
 		.desc = "Shared Cede",
-		.flags = CPUIDLE_FLAG_TIME_VALID,
 		.exit_latency = 0,
 		.target_residency = 0,
 		.enter = &shared_cede_loop },
diff --git a/drivers/cpuidle/cpuidle-ux500.c b/drivers/cpuidle/cpuidle-ux500.c
index 5e35804b1a9..292e65a9030 100644
--- a/drivers/cpuidle/cpuidle-ux500.c
+++ b/drivers/cpuidle/cpuidle-ux500.c
@@ -101,8 +101,7 @@ static struct cpuidle_driver ux500_idle_driver = {
 			.enter		  = ux500_enter_idle,
 			.exit_latency	  = 70,
 			.target_residency = 260,
-			.flags		  = CPUIDLE_FLAG_TIME_VALID |
-			                    CPUIDLE_FLAG_TIMER_STOP,
+			.flags		  = CPUIDLE_FLAG_TIMER_STOP,
 			.name		  = "ApIdle",
 			.desc		  = "ARM Retention",
 		},
diff --git a/drivers/cpuidle/cpuidle-zynq.c b/drivers/cpuidle/cpuidle-zynq.c
index c61b8b2a7c7..022dec86de8 100644
--- a/drivers/cpuidle/cpuidle-zynq.c
+++ b/drivers/cpuidle/cpuidle-zynq.c
@@ -52,7 +52,6 @@ static struct cpuidle_driver zynq_idle_driver = {
 			.enter			= zynq_enter_idle,
 			.exit_latency		= 10,
 			.target_residency	= 10000,
-			.flags			= CPUIDLE_FLAG_TIME_VALID,
 			.name			= "RAM_SR",
 			.desc			= "WFI and RAM Self Refresh",
 		},
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index e431d11abf8..2697e87d5b3 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -201,7 +201,6 @@ static void poll_idle_init(struct cpuidle_driver *drv)
 	state->exit_latency = 0;
 	state->target_residency = 0;
 	state->power_usage = -1;
-	state->flags = CPUIDLE_FLAG_TIME_VALID;
 	state->enter = poll_idle;
 	state->disabled = false;
 }
diff --git a/drivers/cpuidle/dt_idle_states.c b/drivers/cpuidle/dt_idle_states.c
index 52f4d11bbf3..6e6f0b27283 100644
--- a/drivers/cpuidle/dt_idle_states.c
+++ b/drivers/cpuidle/dt_idle_states.c
@@ -73,7 +73,7 @@ static int init_state_node(struct cpuidle_state *idle_state,
 		return -EINVAL;
 	}
 
-	idle_state->flags = CPUIDLE_FLAG_TIME_VALID;
+	idle_state->flags = 0;
 	if (of_property_read_bool(state_node, "local-timer-stop"))
 		idle_state->flags |= CPUIDLE_FLAG_TIMER_STOP;
 	/*
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index 06b57c4c4d8..37263d9a105 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -79,7 +79,7 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 
 	last_state = &ldev->states[last_idx];
 
-	if (drv->states[last_idx].flags & CPUIDLE_FLAG_TIME_VALID) {
+	if (!(drv->states[last_idx].flags & CPUIDLE_FLAG_TIME_INVALID)) {
 		last_residency = cpuidle_get_last_residency(dev) - \
 					 drv->states[last_idx].exit_latency;
 	}
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 710a233b9b0..659d7b0c9eb 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -405,7 +405,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * the measured amount of time is less than the exit latency,
 	 * assume the state was never reached and the exit latency is 0.
 	 */
-	if (unlikely(!(target->flags & CPUIDLE_FLAG_TIME_VALID))) {
+	if (unlikely(target->flags & CPUIDLE_FLAG_TIME_INVALID)) {
 		/* Use timer value as is */
 		measured_us = data->next_timer_us;
 
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 9b7ee7e427d..9cceacb92f9 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -128,28 +128,28 @@ static struct cpuidle_state nehalem_cstates[] = {
 	{
 		.name = "C1-NHM",
 		.desc = "MWAIT 0x00",
-		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x00),
 		.exit_latency = 3,
 		.target_residency = 6,
 		.enter = &intel_idle },
 	{
 		.name = "C1E-NHM",
 		.desc = "MWAIT 0x01",
-		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
 		.target_residency = 20,
 		.enter = &intel_idle },
 	{
 		.name = "C3-NHM",
 		.desc = "MWAIT 0x10",
-		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 20,
 		.target_residency = 80,
 		.enter = &intel_idle },
 	{
 		.name = "C6-NHM",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 200,
 		.target_residency = 800,
 		.enter = &intel_idle },
@@ -161,35 +161,35 @@ static struct cpuidle_state snb_cstates[] = {
 	{
 		.name = "C1-SNB",
 		.desc = "MWAIT 0x00",
-		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x00),
 		.exit_latency = 2,
 		.target_residency = 2,
 		.enter = &intel_idle },
 	{
 		.name = "C1E-SNB",
 		.desc = "MWAIT 0x01",
-		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
 		.target_residency = 20,
 		.enter = &intel_idle },
 	{
 		.name = "C3-SNB",
 		.desc = "MWAIT 0x10",
-		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 80,
 		.target_residency = 211,
 		.enter = &intel_idle },
 	{
 		.name = "C6-SNB",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 104,
 		.target_residency = 345,
 		.enter = &intel_idle },
 	{
 		.name = "C7-SNB",
 		.desc = "MWAIT 0x30",
-		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 109,
 		.target_residency = 345,
 		.enter = &intel_idle },
@@ -201,42 +201,42 @@ static struct cpuidle_state byt_cstates[] = {
 	{
 		.name = "C1-BYT",
 		.desc = "MWAIT 0x00",
-		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x00),
 		.exit_latency = 1,
 		.target_residency = 1,
 		.enter = &intel_idle },
 	{
 		.name = "C1E-BYT",
 		.desc = "MWAIT 0x01",
-		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x01),
 		.exit_latency = 15,
 		.target_residency = 30,
 		.enter = &intel_idle },
 	{
 		.name = "C6N-BYT",
 		.desc = "MWAIT 0x58",
-		.flags = MWAIT2flg(0x58) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x58) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 40,
 		.target_residency = 275,
 		.enter = &intel_idle },
 	{
 		.name = "C6S-BYT",
 		.desc = "MWAIT 0x52",
-		.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 140,
 		.target_residency = 560,
 		.enter = &intel_idle },
 	{
 		.name = "C7-BYT",
 		.desc = "MWAIT 0x60",
-		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 1200,
 		.target_residency = 1500,
 		.enter = &intel_idle },
 	{
 		.name = "C7S-BYT",
 		.desc = "MWAIT 0x64",
-		.flags = MWAIT2flg(0x64) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x64) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 10000,
 		.target_residency = 20000,
 		.enter = &intel_idle },
@@ -248,35 +248,35 @@ static struct cpuidle_state ivb_cstates[] = {
 	{
 		.name = "C1-IVB",
 		.desc = "MWAIT 0x00",
-		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x00),
 		.exit_latency = 1,
 		.target_residency = 1,
 		.enter = &intel_idle },
 	{
 		.name = "C1E-IVB",
 		.desc = "MWAIT 0x01",
-		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
 		.target_residency = 20,
 		.enter = &intel_idle },
 	{
 		.name = "C3-IVB",
 		.desc = "MWAIT 0x10",
-		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 59,
 		.target_residency = 156,
 		.enter = &intel_idle },
 	{
 		.name = "C6-IVB",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 80,
 		.target_residency = 300,
 		.enter = &intel_idle },
 	{
 		.name = "C7-IVB",
 		.desc = "MWAIT 0x30",
-		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 87,
 		.target_residency = 300,
 		.enter = &intel_idle },
@@ -288,28 +288,28 @@ static struct cpuidle_state ivt_cstates[] = {
 	{
 		.name = "C1-IVT",
 		.desc = "MWAIT 0x00",
-		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x00),
 		.exit_latency = 1,
 		.target_residency = 1,
 		.enter = &intel_idle },
 	{
 		.name = "C1E-IVT",
 		.desc = "MWAIT 0x01",
-		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
 		.target_residency = 80,
 		.enter = &intel_idle },
 	{
 		.name = "C3-IVT",
 		.desc = "MWAIT 0x10",
-		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 59,
 		.target_residency = 156,
 		.enter = &intel_idle },
 	{
 		.name = "C6-IVT",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 82,
 		.target_residency = 300,
 		.enter = &intel_idle },
@@ -321,28 +321,28 @@ static struct cpuidle_state ivt_cstates_4s[] = {
 	{
 		.name = "C1-IVT-4S",
 		.desc = "MWAIT 0x00",
-		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x00),
 		.exit_latency = 1,
 		.target_residency = 1,
 		.enter = &intel_idle },
 	{
 		.name = "C1E-IVT-4S",
 		.desc = "MWAIT 0x01",
-		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
 		.target_residency = 250,
 		.enter = &intel_idle },
 	{
 		.name = "C3-IVT-4S",
 		.desc = "MWAIT 0x10",
-		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 59,
 		.target_residency = 300,
 		.enter = &intel_idle },
 	{
 		.name = "C6-IVT-4S",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 84,
 		.target_residency = 400,
 		.enter = &intel_idle },
@@ -354,28 +354,28 @@ static struct cpuidle_state ivt_cstates_8s[] = {
 	{
 		.name = "C1-IVT-8S",
 		.desc = "MWAIT 0x00",
-		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x00),
 		.exit_latency = 1,
 		.target_residency = 1,
 		.enter = &intel_idle },
 	{
 		.name = "C1E-IVT-8S",
 		.desc = "MWAIT 0x01",
-		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
 		.target_residency = 500,
 		.enter = &intel_idle },
 	{
 		.name = "C3-IVT-8S",
 		.desc = "MWAIT 0x10",
-		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 59,
 		.target_residency = 600,
 		.enter = &intel_idle },
 	{
 		.name = "C6-IVT-8S",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 88,
 		.target_residency = 700,
 		.enter = &intel_idle },
@@ -387,56 +387,56 @@ static struct cpuidle_state hsw_cstates[] = {
 	{
 		.name = "C1-HSW",
 		.desc = "MWAIT 0x00",
-		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x00),
 		.exit_latency = 2,
 		.target_residency = 2,
 		.enter = &intel_idle },
 	{
 		.name = "C1E-HSW",
 		.desc = "MWAIT 0x01",
-		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
 		.target_residency = 20,
 		.enter = &intel_idle },
 	{
 		.name = "C3-HSW",
 		.desc = "MWAIT 0x10",
-		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 33,
 		.target_residency = 100,
 		.enter = &intel_idle },
 	{
 		.name = "C6-HSW",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 133,
 		.target_residency = 400,
 		.enter = &intel_idle },
 	{
 		.name = "C7s-HSW",
 		.desc = "MWAIT 0x32",
-		.flags = MWAIT2flg(0x32) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x32) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 166,
 		.target_residency = 500,
 		.enter = &intel_idle },
 	{
 		.name = "C8-HSW",
 		.desc = "MWAIT 0x40",
-		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 300,
 		.target_residency = 900,
 		.enter = &intel_idle },
 	{
 		.name = "C9-HSW",
 		.desc = "MWAIT 0x50",
-		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 600,
 		.target_residency = 1800,
 		.enter = &intel_idle },
 	{
 		.name = "C10-HSW",
 		.desc = "MWAIT 0x60",
-		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 2600,
 		.target_residency = 7700,
 		.enter = &intel_idle },
@@ -447,56 +447,56 @@ static struct cpuidle_state bdw_cstates[] = {
 	{
 		.name = "C1-BDW",
 		.desc = "MWAIT 0x00",
-		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x00),
 		.exit_latency = 2,
 		.target_residency = 2,
 		.enter = &intel_idle },
 	{
 		.name = "C1E-BDW",
 		.desc = "MWAIT 0x01",
-		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x01),
 		.exit_latency = 10,
 		.target_residency = 20,
 		.enter = &intel_idle },
 	{
 		.name = "C3-BDW",
 		.desc = "MWAIT 0x10",
-		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 40,
 		.target_residency = 100,
 		.enter = &intel_idle },
 	{
 		.name = "C6-BDW",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 133,
 		.target_residency = 400,
 		.enter = &intel_idle },
 	{
 		.name = "C7s-BDW",
 		.desc = "MWAIT 0x32",
-		.flags = MWAIT2flg(0x32) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x32) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 166,
 		.target_residency = 500,
 		.enter = &intel_idle },
 	{
 		.name = "C8-BDW",
 		.desc = "MWAIT 0x40",
-		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 300,
 		.target_residency = 900,
 		.enter = &intel_idle },
 	{
 		.name = "C9-BDW",
 		.desc = "MWAIT 0x50",
-		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 600,
 		.target_residency = 1800,
 		.enter = &intel_idle },
 	{
 		.name = "C10-BDW",
 		.desc = "MWAIT 0x60",
-		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 2600,
 		.target_residency = 7700,
 		.enter = &intel_idle },
@@ -508,28 +508,28 @@ static struct cpuidle_state atom_cstates[] = {
 	{
 		.name = "C1E-ATM",
 		.desc = "MWAIT 0x00",
-		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x00),
 		.exit_latency = 10,
 		.target_residency = 20,
 		.enter = &intel_idle },
 	{
 		.name = "C2-ATM",
 		.desc = "MWAIT 0x10",
-		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x10),
 		.exit_latency = 20,
 		.target_residency = 80,
 		.enter = &intel_idle },
 	{
 		.name = "C4-ATM",
 		.desc = "MWAIT 0x30",
-		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 100,
 		.target_residency = 400,
 		.enter = &intel_idle },
 	{
 		.name = "C6-ATM",
 		.desc = "MWAIT 0x52",
-		.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 140,
 		.target_residency = 560,
 		.enter = &intel_idle },
@@ -540,14 +540,14 @@ static struct cpuidle_state avn_cstates[] = {
 	{
 		.name = "C1-AVN",
 		.desc = "MWAIT 0x00",
-		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+		.flags = MWAIT2flg(0x00),
 		.exit_latency = 2,
 		.target_residency = 2,
 		.enter = &intel_idle },
 	{
 		.name = "C6-AVN",
 		.desc = "MWAIT 0x51",
-		.flags = MWAIT2flg(0x51) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x51) | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 15,
 		.target_residency = 45,
 		.enter = &intel_idle },
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 25e0df6155a..a07e087f54b 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -53,7 +53,7 @@ struct cpuidle_state {
 };
 
 /* Idle State Flags */
-#define CPUIDLE_FLAG_TIME_VALID	(0x01) /* is residency time measurable? */
+#define CPUIDLE_FLAG_TIME_INVALID	(0x01) /* is residency time measurable? */
 #define CPUIDLE_FLAG_COUPLED	(0x02) /* state applies to multiple cpus */
 #define CPUIDLE_FLAG_TIMER_STOP (0x04)  /* timer is stopped on this state */
 
@@ -90,7 +90,7 @@ DECLARE_PER_CPU(struct cpuidle_device, cpuidle_dev);
  * cpuidle_get_last_residency - retrieves the last state's residency time
  * @dev: the target CPU
  *
- * NOTE: this value is invalid if CPUIDLE_FLAG_TIME_VALID isn't set
+ * NOTE: this value is invalid if CPUIDLE_FLAG_TIME_INVALID is set
  */
 static inline int cpuidle_get_last_residency(struct cpuidle_device *dev)
 {
-- 
cgit v1.2.3-70-g09d2


From ab08aefcd12d4e21abb28264ca77a430dcce7ebd Mon Sep 17 00:00:00 2001
From: Chao Xie <chao.xie@marvell.com>
Date: Fri, 31 Oct 2014 10:13:49 +0800
Subject: clk: mmp: add pxa168 DT support for clock driver

It adds the DT support for pxa168 clock subsystem.

Signed-off-by: Chao Xie <chao.xie@marvell.com>
Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com>
Signed-off-by: Michael Turquette <mturquette@linaro.org>
---
 .../devicetree/bindings/clock/marvell,pxa168.txt   |  21 ++
 drivers/clk/mmp/Makefile                           |   2 +
 drivers/clk/mmp/clk-of-pxa168.c                    | 279 +++++++++++++++++++++
 include/dt-bindings/clock/marvell,pxa168.h         |  57 +++++
 4 files changed, 359 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/marvell,pxa168.txt
 create mode 100644 drivers/clk/mmp/clk-of-pxa168.c
 create mode 100644 include/dt-bindings/clock/marvell,pxa168.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/marvell,pxa168.txt b/Documentation/devicetree/bindings/clock/marvell,pxa168.txt
new file mode 100644
index 00000000000..c62eb1d173a
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/marvell,pxa168.txt
@@ -0,0 +1,21 @@
+* Marvell PXA168 Clock Controller
+
+The PXA168 clock subsystem generates and supplies clock to various
+controllers within the PXA168 SoC.
+
+Required Properties:
+
+- compatible: should be one of the following.
+  - "marvell,pxa168-clock" - controller compatible with PXA168 SoC.
+
+- reg: physical base address of the clock subsystem and length of memory mapped
+  region. There are 3 places in SOC has clock control logic:
+  "mpmu", "apmu", "apbc". So three reg spaces need to be defined.
+
+- #clock-cells: should be 1.
+- #reset-cells: should be 1.
+
+Each clock is assigned an identifier and client nodes use this identifier
+to specify the clock which they consume.
+
+All these identifier could be found in <dt-bindings/clock/marvell,pxa168.h>.
diff --git a/drivers/clk/mmp/Makefile b/drivers/clk/mmp/Makefile
index 2573d7c6198..733acc7aa48 100644
--- a/drivers/clk/mmp/Makefile
+++ b/drivers/clk/mmp/Makefile
@@ -6,6 +6,8 @@ obj-y += clk-apbc.o clk-apmu.o clk-frac.o clk-mix.o clk-gate.o clk.o
 
 obj-$(CONFIG_RESET_CONTROLLER) += reset.o
 
+obj-$(CONFIG_MACH_MMP_DT) += clk-of-pxa168.o
+
 obj-$(CONFIG_CPU_PXA168) += clk-pxa168.o
 obj-$(CONFIG_CPU_PXA910) += clk-pxa910.o
 obj-$(CONFIG_CPU_MMP2) += clk-mmp2.o
diff --git a/drivers/clk/mmp/clk-of-pxa168.c b/drivers/clk/mmp/clk-of-pxa168.c
new file mode 100644
index 00000000000..5b1810dc4bd
--- /dev/null
+++ b/drivers/clk/mmp/clk-of-pxa168.c
@@ -0,0 +1,279 @@
+/*
+ * pxa168 clock framework source file
+ *
+ * Copyright (C) 2012 Marvell
+ * Chao Xie <xiechao.mail@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/of_address.h>
+
+#include <dt-bindings/clock/marvell,pxa168.h>
+
+#include "clk.h"
+#include "reset.h"
+
+#define APBC_RTC	0x28
+#define APBC_TWSI0	0x2c
+#define APBC_KPC	0x30
+#define APBC_UART0	0x0
+#define APBC_UART1	0x4
+#define APBC_GPIO	0x8
+#define APBC_PWM0	0xc
+#define APBC_PWM1	0x10
+#define APBC_PWM2	0x14
+#define APBC_PWM3	0x18
+#define APBC_SSP0	0x81c
+#define APBC_SSP1	0x820
+#define APBC_SSP2	0x84c
+#define APBC_SSP3	0x858
+#define APBC_SSP4	0x85c
+#define APBC_TWSI1	0x6c
+#define APBC_UART2	0x70
+#define APMU_SDH0	0x54
+#define APMU_SDH1	0x58
+#define APMU_USB	0x5c
+#define APMU_DISP0	0x4c
+#define APMU_CCIC0	0x50
+#define APMU_DFC	0x60
+#define MPMU_UART_PLL	0x14
+
+struct pxa168_clk_unit {
+	struct mmp_clk_unit unit;
+	void __iomem *mpmu_base;
+	void __iomem *apmu_base;
+	void __iomem *apbc_base;
+};
+
+static struct mmp_param_fixed_rate_clk fixed_rate_clks[] = {
+	{PXA168_CLK_CLK32, "clk32", NULL, CLK_IS_ROOT, 32768},
+	{PXA168_CLK_VCTCXO, "vctcxo", NULL, CLK_IS_ROOT, 26000000},
+	{PXA168_CLK_PLL1, "pll1", NULL, CLK_IS_ROOT, 624000000},
+};
+
+static struct mmp_param_fixed_factor_clk fixed_factor_clks[] = {
+	{PXA168_CLK_PLL1_2, "pll1_2", "pll1", 1, 2, 0},
+	{PXA168_CLK_PLL1_4, "pll1_4", "pll1_2", 1, 2, 0},
+	{PXA168_CLK_PLL1_8, "pll1_8", "pll1_4", 1, 2, 0},
+	{PXA168_CLK_PLL1_16, "pll1_16", "pll1_8", 1, 2, 0},
+	{PXA168_CLK_PLL1_6, "pll1_6", "pll1_2", 1, 3, 0},
+	{PXA168_CLK_PLL1_12, "pll1_12", "pll1_6", 1, 2, 0},
+	{PXA168_CLK_PLL1_24, "pll1_24", "pll1_12", 1, 2, 0},
+	{PXA168_CLK_PLL1_48, "pll1_48", "pll1_24", 1, 2, 0},
+	{PXA168_CLK_PLL1_96, "pll1_96", "pll1_48", 1, 2, 0},
+	{PXA168_CLK_PLL1_13, "pll1_13", "pll1", 1, 13, 0},
+	{PXA168_CLK_PLL1_13_1_5, "pll1_13_1_5", "pll1_13", 2, 3, 0},
+	{PXA168_CLK_PLL1_2_1_5, "pll1_2_1_5", "pll1_2", 2, 3, 0},
+	{PXA168_CLK_PLL1_3_16, "pll1_3_16", "pll1", 3, 16, 0},
+};
+
+static struct mmp_clk_factor_masks uart_factor_masks = {
+	.factor = 2,
+	.num_mask = 0x1fff,
+	.den_mask = 0x1fff,
+	.num_shift = 16,
+	.den_shift = 0,
+};
+
+static struct mmp_clk_factor_tbl uart_factor_tbl[] = {
+	{.num = 8125, .den = 1536},	/*14.745MHZ */
+};
+
+static void pxa168_pll_init(struct pxa168_clk_unit *pxa_unit)
+{
+	struct clk *clk;
+	struct mmp_clk_unit *unit = &pxa_unit->unit;
+
+	mmp_register_fixed_rate_clks(unit, fixed_rate_clks,
+					ARRAY_SIZE(fixed_rate_clks));
+
+	mmp_register_fixed_factor_clks(unit, fixed_factor_clks,
+					ARRAY_SIZE(fixed_factor_clks));
+
+	clk = mmp_clk_register_factor("uart_pll", "pll1_4",
+				CLK_SET_RATE_PARENT,
+				pxa_unit->mpmu_base + MPMU_UART_PLL,
+				&uart_factor_masks, uart_factor_tbl,
+				ARRAY_SIZE(uart_factor_tbl), NULL);
+	mmp_clk_add(unit, PXA168_CLK_UART_PLL, clk);
+}
+
+static DEFINE_SPINLOCK(uart0_lock);
+static DEFINE_SPINLOCK(uart1_lock);
+static DEFINE_SPINLOCK(uart2_lock);
+static const char *uart_parent_names[] = {"pll1_3_16", "uart_pll"};
+
+static DEFINE_SPINLOCK(ssp0_lock);
+static DEFINE_SPINLOCK(ssp1_lock);
+static DEFINE_SPINLOCK(ssp2_lock);
+static DEFINE_SPINLOCK(ssp3_lock);
+static DEFINE_SPINLOCK(ssp4_lock);
+static const char *ssp_parent_names[] = {"pll1_96", "pll1_48", "pll1_24", "pll1_12"};
+
+static DEFINE_SPINLOCK(reset_lock);
+
+static struct mmp_param_mux_clk apbc_mux_clks[] = {
+	{0, "uart0_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, APBC_UART0, 4, 3, 0, &uart0_lock},
+	{0, "uart1_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, APBC_UART1, 4, 3, 0, &uart1_lock},
+	{0, "uart2_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, APBC_UART2, 4, 3, 0, &uart2_lock},
+	{0, "ssp0_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP0, 4, 3, 0, &ssp0_lock},
+	{0, "ssp1_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP1, 4, 3, 0, &ssp1_lock},
+	{0, "ssp2_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP2, 4, 3, 0, &ssp2_lock},
+	{0, "ssp3_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP3, 4, 3, 0, &ssp3_lock},
+	{0, "ssp4_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP4, 4, 3, 0, &ssp4_lock},
+};
+
+static struct mmp_param_gate_clk apbc_gate_clks[] = {
+	{PXA168_CLK_TWSI0, "twsi0_clk", "pll1_13_1_5", CLK_SET_RATE_PARENT, APBC_TWSI0, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA168_CLK_TWSI1, "twsi1_clk", "pll1_13_1_5", CLK_SET_RATE_PARENT, APBC_TWSI1, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA168_CLK_GPIO, "gpio_clk", "vctcxo", CLK_SET_RATE_PARENT, APBC_GPIO, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA168_CLK_KPC, "kpc_clk", "clk32", CLK_SET_RATE_PARENT, APBC_KPC, 0x3, 0x3, 0x0, MMP_CLK_GATE_NEED_DELAY, NULL},
+	{PXA168_CLK_RTC, "rtc_clk", "clk32", CLK_SET_RATE_PARENT, APBC_RTC, 0x83, 0x83, 0x0, MMP_CLK_GATE_NEED_DELAY, NULL},
+	{PXA168_CLK_PWM0, "pwm0_clk", "pll1_48", CLK_SET_RATE_PARENT, APBC_PWM0, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA168_CLK_PWM1, "pwm1_clk", "pll1_48", CLK_SET_RATE_PARENT, APBC_PWM1, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA168_CLK_PWM2, "pwm2_clk", "pll1_48", CLK_SET_RATE_PARENT, APBC_PWM2, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA168_CLK_PWM3, "pwm3_clk", "pll1_48", CLK_SET_RATE_PARENT, APBC_PWM3, 0x3, 0x3, 0x0, 0, &reset_lock},
+	/* The gate clocks has mux parent. */
+	{PXA168_CLK_UART0, "uart0_clk", "uart0_mux", CLK_SET_RATE_PARENT, APBC_UART0, 0x3, 0x3, 0x0, 0, &uart0_lock},
+	{PXA168_CLK_UART1, "uart1_clk", "uart1_mux", CLK_SET_RATE_PARENT, APBC_UART1, 0x3, 0x3, 0x0, 0, &uart1_lock},
+	{PXA168_CLK_UART2, "uart2_clk", "uart2_mux", CLK_SET_RATE_PARENT, APBC_UART2, 0x3, 0x3, 0x0, 0, &uart2_lock},
+	{PXA168_CLK_SSP0, "ssp0_clk", "ssp0_mux", CLK_SET_RATE_PARENT, APBC_SSP0, 0x3, 0x3, 0x0, 0, &ssp0_lock},
+	{PXA168_CLK_SSP1, "ssp1_clk", "ssp1_mux", CLK_SET_RATE_PARENT, APBC_SSP1, 0x3, 0x3, 0x0, 0, &ssp1_lock},
+	{PXA168_CLK_SSP2, "ssp2_clk", "ssp2_mux", CLK_SET_RATE_PARENT, APBC_SSP2, 0x3, 0x3, 0x0, 0, &ssp2_lock},
+	{PXA168_CLK_SSP3, "ssp3_clk", "ssp3_mux", CLK_SET_RATE_PARENT, APBC_SSP3, 0x3, 0x3, 0x0, 0, &ssp3_lock},
+	{PXA168_CLK_SSP4, "ssp4_clk", "ssp4_mux", CLK_SET_RATE_PARENT, APBC_SSP4, 0x3, 0x3, 0x0, 0, &ssp4_lock},
+};
+
+static void pxa168_apb_periph_clk_init(struct pxa168_clk_unit *pxa_unit)
+{
+	struct mmp_clk_unit *unit = &pxa_unit->unit;
+
+	mmp_register_mux_clks(unit, apbc_mux_clks, pxa_unit->apbc_base,
+				ARRAY_SIZE(apbc_mux_clks));
+
+	mmp_register_gate_clks(unit, apbc_gate_clks, pxa_unit->apbc_base,
+				ARRAY_SIZE(apbc_gate_clks));
+
+}
+
+static DEFINE_SPINLOCK(sdh0_lock);
+static DEFINE_SPINLOCK(sdh1_lock);
+static const char *sdh_parent_names[] = {"pll1_12", "pll1_13"};
+
+static DEFINE_SPINLOCK(usb_lock);
+
+static DEFINE_SPINLOCK(disp0_lock);
+static const char *disp_parent_names[] = {"pll1_2", "pll1_12"};
+
+static DEFINE_SPINLOCK(ccic0_lock);
+static const char *ccic_parent_names[] = {"pll1_2", "pll1_12"};
+static const char *ccic_phy_parent_names[] = {"pll1_6", "pll1_12"};
+
+static struct mmp_param_mux_clk apmu_mux_clks[] = {
+	{0, "sdh0_mux", sdh_parent_names, ARRAY_SIZE(sdh_parent_names), CLK_SET_RATE_PARENT, APMU_SDH0, 6, 1, 0, &sdh0_lock},
+	{0, "sdh1_mux", sdh_parent_names, ARRAY_SIZE(sdh_parent_names), CLK_SET_RATE_PARENT, APMU_SDH1, 6, 1, 0, &sdh1_lock},
+	{0, "disp0_mux", disp_parent_names, ARRAY_SIZE(disp_parent_names), CLK_SET_RATE_PARENT, APMU_DISP0, 6, 1, 0, &disp0_lock},
+	{0, "ccic0_mux", ccic_parent_names, ARRAY_SIZE(ccic_parent_names), CLK_SET_RATE_PARENT, APMU_CCIC0, 6, 1, 0, &ccic0_lock},
+	{0, "ccic0_phy_mux", ccic_phy_parent_names, ARRAY_SIZE(ccic_phy_parent_names), CLK_SET_RATE_PARENT, APMU_CCIC0, 7, 1, 0, &ccic0_lock},
+};
+
+static struct mmp_param_div_clk apmu_div_clks[] = {
+	{0, "ccic0_sphy_div", "ccic0_mux", CLK_SET_RATE_PARENT, APMU_CCIC0, 10, 5, 0, &ccic0_lock},
+};
+
+static struct mmp_param_gate_clk apmu_gate_clks[] = {
+	{PXA168_CLK_DFC, "dfc_clk", "pll1_4", CLK_SET_RATE_PARENT, APMU_DFC, 0x19b, 0x19b, 0x0, 0, NULL},
+	{PXA168_CLK_USB, "usb_clk", "usb_pll", 0, APMU_USB, 0x9, 0x9, 0x0, 0, &usb_lock},
+	{PXA168_CLK_SPH, "sph_clk", "usb_pll", 0, APMU_USB, 0x12, 0x12, 0x0, 0, &usb_lock},
+	/* The gate clocks has mux parent. */
+	{PXA168_CLK_SDH0, "sdh0_clk", "sdh0_mux", CLK_SET_RATE_PARENT, APMU_SDH0, 0x1b, 0x1b, 0x0, 0, &sdh0_lock},
+	{PXA168_CLK_SDH1, "sdh1_clk", "sdh1_mux", CLK_SET_RATE_PARENT, APMU_SDH1, 0x1b, 0x1b, 0x0, 0, &sdh1_lock},
+	{PXA168_CLK_DISP0, "disp0_clk", "disp0_mux", CLK_SET_RATE_PARENT, APMU_DISP0, 0x1b, 0x1b, 0x0, 0, &disp0_lock},
+	{PXA168_CLK_CCIC0, "ccic0_clk", "ccic0_mux", CLK_SET_RATE_PARENT, APMU_CCIC0, 0x1b, 0x1b, 0x0, 0, &ccic0_lock},
+	{PXA168_CLK_CCIC0_PHY, "ccic0_phy_clk", "ccic0_phy_mux", CLK_SET_RATE_PARENT, APMU_CCIC0, 0x24, 0x24, 0x0, 0, &ccic0_lock},
+	{PXA168_CLK_CCIC0_SPHY, "ccic0_sphy_clk", "ccic0_sphy_div", CLK_SET_RATE_PARENT, APMU_CCIC0, 0x300, 0x300, 0x0, 0, &ccic0_lock},
+};
+
+static void pxa168_axi_periph_clk_init(struct pxa168_clk_unit *pxa_unit)
+{
+	struct mmp_clk_unit *unit = &pxa_unit->unit;
+
+	mmp_register_mux_clks(unit, apmu_mux_clks, pxa_unit->apmu_base,
+				ARRAY_SIZE(apmu_mux_clks));
+
+	mmp_register_div_clks(unit, apmu_div_clks, pxa_unit->apmu_base,
+				ARRAY_SIZE(apmu_div_clks));
+
+	mmp_register_gate_clks(unit, apmu_gate_clks, pxa_unit->apmu_base,
+				ARRAY_SIZE(apmu_gate_clks));
+}
+
+static void pxa168_clk_reset_init(struct device_node *np,
+				struct pxa168_clk_unit *pxa_unit)
+{
+	struct mmp_clk_reset_cell *cells;
+	int i, nr_resets;
+
+	nr_resets = ARRAY_SIZE(apbc_gate_clks);
+	cells = kcalloc(nr_resets, sizeof(*cells), GFP_KERNEL);
+	if (!cells)
+		return;
+
+	for (i = 0; i < nr_resets; i++) {
+		cells[i].clk_id = apbc_gate_clks[i].id;
+		cells[i].reg = pxa_unit->apbc_base + apbc_gate_clks[i].offset;
+		cells[i].flags = 0;
+		cells[i].lock = apbc_gate_clks[i].lock;
+		cells[i].bits = 0x4;
+	}
+
+	mmp_clk_reset_register(np, cells, nr_resets);
+}
+
+static void __init pxa168_clk_init(struct device_node *np)
+{
+	struct pxa168_clk_unit *pxa_unit;
+
+	pxa_unit = kzalloc(sizeof(*pxa_unit), GFP_KERNEL);
+	if (!pxa_unit)
+		return;
+
+	pxa_unit->mpmu_base = of_iomap(np, 0);
+	if (!pxa_unit->mpmu_base) {
+		pr_err("failed to map mpmu registers\n");
+		return;
+	}
+
+	pxa_unit->apmu_base = of_iomap(np, 1);
+	if (!pxa_unit->mpmu_base) {
+		pr_err("failed to map apmu registers\n");
+		return;
+	}
+
+	pxa_unit->apbc_base = of_iomap(np, 2);
+	if (!pxa_unit->apbc_base) {
+		pr_err("failed to map apbc registers\n");
+		return;
+	}
+
+	mmp_clk_init(np, &pxa_unit->unit, PXA168_NR_CLKS);
+
+	pxa168_pll_init(pxa_unit);
+
+	pxa168_apb_periph_clk_init(pxa_unit);
+
+	pxa168_axi_periph_clk_init(pxa_unit);
+
+	pxa168_clk_reset_init(np, pxa_unit);
+}
+
+CLK_OF_DECLARE(pxa168_clk, "marvell,pxa168-clock", pxa168_clk_init);
diff --git a/include/dt-bindings/clock/marvell,pxa168.h b/include/dt-bindings/clock/marvell,pxa168.h
new file mode 100644
index 00000000000..79630b9d74b
--- /dev/null
+++ b/include/dt-bindings/clock/marvell,pxa168.h
@@ -0,0 +1,57 @@
+#ifndef __DTS_MARVELL_PXA168_CLOCK_H
+#define __DTS_MARVELL_PXA168_CLOCK_H
+
+/* fixed clocks and plls */
+#define PXA168_CLK_CLK32		1
+#define PXA168_CLK_VCTCXO		2
+#define PXA168_CLK_PLL1			3
+#define PXA168_CLK_PLL1_2		8
+#define PXA168_CLK_PLL1_4		9
+#define PXA168_CLK_PLL1_8		10
+#define PXA168_CLK_PLL1_16		11
+#define PXA168_CLK_PLL1_6		12
+#define PXA168_CLK_PLL1_12		13
+#define PXA168_CLK_PLL1_24		14
+#define PXA168_CLK_PLL1_48		15
+#define PXA168_CLK_PLL1_96		16
+#define PXA168_CLK_PLL1_13		17
+#define PXA168_CLK_PLL1_13_1_5		18
+#define PXA168_CLK_PLL1_2_1_5		19
+#define PXA168_CLK_PLL1_3_16		20
+#define PXA168_CLK_UART_PLL		27
+
+/* apb periphrals */
+#define PXA168_CLK_TWSI0		60
+#define PXA168_CLK_TWSI1		61
+#define PXA168_CLK_TWSI2		62
+#define PXA168_CLK_TWSI3		63
+#define PXA168_CLK_GPIO			64
+#define PXA168_CLK_KPC			65
+#define PXA168_CLK_RTC			66
+#define PXA168_CLK_PWM0			67
+#define PXA168_CLK_PWM1			68
+#define PXA168_CLK_PWM2			69
+#define PXA168_CLK_PWM3			70
+#define PXA168_CLK_UART0		71
+#define PXA168_CLK_UART1		72
+#define PXA168_CLK_UART2		73
+#define PXA168_CLK_SSP0			74
+#define PXA168_CLK_SSP1			75
+#define PXA168_CLK_SSP2			76
+#define PXA168_CLK_SSP3			77
+#define PXA168_CLK_SSP4			78
+
+/* axi periphrals */
+#define PXA168_CLK_DFC			100
+#define PXA168_CLK_SDH0			101
+#define PXA168_CLK_SDH1			102
+#define PXA168_CLK_SDH2			103
+#define PXA168_CLK_USB			104
+#define PXA168_CLK_SPH			105
+#define PXA168_CLK_DISP0		106
+#define PXA168_CLK_CCIC0		107
+#define PXA168_CLK_CCIC0_PHY		108
+#define PXA168_CLK_CCIC0_SPHY		109
+
+#define PXA168_NR_CLKS			200
+#endif
-- 
cgit v1.2.3-70-g09d2


From 2bc61da9f7ff422117a68bef0d309a29affd023a Mon Sep 17 00:00:00 2001
From: Chao Xie <chao.xie@marvell.com>
Date: Fri, 31 Oct 2014 10:13:50 +0800
Subject: clk: mmp: add pxa910 DT support for clock driver

It adds the DT support for pxa910 clock subsystem.

Signed-off-by: Chao Xie <chao.xie@marvell.com>
Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com>
Signed-off-by: Michael Turquette <mturquette@linaro.org>
---
 .../devicetree/bindings/clock/marvell,pxa910.txt   |  21 ++
 drivers/clk/mmp/Makefile                           |   2 +-
 drivers/clk/mmp/clk-of-pxa910.c                    | 301 +++++++++++++++++++++
 include/dt-bindings/clock/marvell,pxa910.h         |  54 ++++
 4 files changed, 377 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/devicetree/bindings/clock/marvell,pxa910.txt
 create mode 100644 drivers/clk/mmp/clk-of-pxa910.c
 create mode 100644 include/dt-bindings/clock/marvell,pxa910.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/marvell,pxa910.txt b/Documentation/devicetree/bindings/clock/marvell,pxa910.txt
new file mode 100644
index 00000000000..d9f41f3c03a
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/marvell,pxa910.txt
@@ -0,0 +1,21 @@
+* Marvell PXA910 Clock Controller
+
+The PXA910 clock subsystem generates and supplies clock to various
+controllers within the PXA910 SoC.
+
+Required Properties:
+
+- compatible: should be one of the following.
+  - "marvell,pxa910-clock" - controller compatible with PXA910 SoC.
+
+- reg: physical base address of the clock subsystem and length of memory mapped
+  region. There are 4 places in SOC has clock control logic:
+  "mpmu", "apmu", "apbc", "apbcp". So four reg spaces need to be defined.
+
+- #clock-cells: should be 1.
+- #reset-cells: should be 1.
+
+Each clock is assigned an identifier and client nodes use this identifier
+to specify the clock which they consume.
+
+All these identifier could be found in <dt-bindings/clock/marvell-pxa910.h>.
diff --git a/drivers/clk/mmp/Makefile b/drivers/clk/mmp/Makefile
index 733acc7aa48..947cd74a82a 100644
--- a/drivers/clk/mmp/Makefile
+++ b/drivers/clk/mmp/Makefile
@@ -6,7 +6,7 @@ obj-y += clk-apbc.o clk-apmu.o clk-frac.o clk-mix.o clk-gate.o clk.o
 
 obj-$(CONFIG_RESET_CONTROLLER) += reset.o
 
-obj-$(CONFIG_MACH_MMP_DT) += clk-of-pxa168.o
+obj-$(CONFIG_MACH_MMP_DT) += clk-of-pxa168.o clk-of-pxa910.o
 
 obj-$(CONFIG_CPU_PXA168) += clk-pxa168.o
 obj-$(CONFIG_CPU_PXA910) += clk-pxa910.o
diff --git a/drivers/clk/mmp/clk-of-pxa910.c b/drivers/clk/mmp/clk-of-pxa910.c
new file mode 100644
index 00000000000..5e3c80dad33
--- /dev/null
+++ b/drivers/clk/mmp/clk-of-pxa910.c
@@ -0,0 +1,301 @@
+/*
+ * pxa910 clock framework source file
+ *
+ * Copyright (C) 2012 Marvell
+ * Chao Xie <xiechao.mail@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/of_address.h>
+
+#include <dt-bindings/clock/marvell,pxa910.h>
+
+#include "clk.h"
+#include "reset.h"
+
+#define APBC_RTC	0x28
+#define APBC_TWSI0	0x2c
+#define APBC_KPC	0x18
+#define APBC_UART0	0x0
+#define APBC_UART1	0x4
+#define APBC_GPIO	0x8
+#define APBC_PWM0	0xc
+#define APBC_PWM1	0x10
+#define APBC_PWM2	0x14
+#define APBC_PWM3	0x18
+#define APBC_SSP0	0x1c
+#define APBC_SSP1	0x20
+#define APBC_SSP2	0x4c
+#define APBCP_TWSI1	0x28
+#define APBCP_UART2	0x1c
+#define APMU_SDH0	0x54
+#define APMU_SDH1	0x58
+#define APMU_USB	0x5c
+#define APMU_DISP0	0x4c
+#define APMU_CCIC0	0x50
+#define APMU_DFC	0x60
+#define MPMU_UART_PLL	0x14
+
+struct pxa910_clk_unit {
+	struct mmp_clk_unit unit;
+	void __iomem *mpmu_base;
+	void __iomem *apmu_base;
+	void __iomem *apbc_base;
+	void __iomem *apbcp_base;
+};
+
+static struct mmp_param_fixed_rate_clk fixed_rate_clks[] = {
+	{PXA910_CLK_CLK32, "clk32", NULL, CLK_IS_ROOT, 32768},
+	{PXA910_CLK_VCTCXO, "vctcxo", NULL, CLK_IS_ROOT, 26000000},
+	{PXA910_CLK_PLL1, "pll1", NULL, CLK_IS_ROOT, 624000000},
+};
+
+static struct mmp_param_fixed_factor_clk fixed_factor_clks[] = {
+	{PXA910_CLK_PLL1_2, "pll1_2", "pll1", 1, 2, 0},
+	{PXA910_CLK_PLL1_4, "pll1_4", "pll1_2", 1, 2, 0},
+	{PXA910_CLK_PLL1_8, "pll1_8", "pll1_4", 1, 2, 0},
+	{PXA910_CLK_PLL1_16, "pll1_16", "pll1_8", 1, 2, 0},
+	{PXA910_CLK_PLL1_6, "pll1_6", "pll1_2", 1, 3, 0},
+	{PXA910_CLK_PLL1_12, "pll1_12", "pll1_6", 1, 2, 0},
+	{PXA910_CLK_PLL1_24, "pll1_24", "pll1_12", 1, 2, 0},
+	{PXA910_CLK_PLL1_48, "pll1_48", "pll1_24", 1, 2, 0},
+	{PXA910_CLK_PLL1_96, "pll1_96", "pll1_48", 1, 2, 0},
+	{PXA910_CLK_PLL1_13, "pll1_13", "pll1", 1, 13, 0},
+	{PXA910_CLK_PLL1_13_1_5, "pll1_13_1_5", "pll1_13", 2, 3, 0},
+	{PXA910_CLK_PLL1_2_1_5, "pll1_2_1_5", "pll1_2", 2, 3, 0},
+	{PXA910_CLK_PLL1_3_16, "pll1_3_16", "pll1", 3, 16, 0},
+};
+
+static struct mmp_clk_factor_masks uart_factor_masks = {
+	.factor = 2,
+	.num_mask = 0x1fff,
+	.den_mask = 0x1fff,
+	.num_shift = 16,
+	.den_shift = 0,
+};
+
+static struct mmp_clk_factor_tbl uart_factor_tbl[] = {
+	{.num = 8125, .den = 1536},	/*14.745MHZ */
+};
+
+static void pxa910_pll_init(struct pxa910_clk_unit *pxa_unit)
+{
+	struct clk *clk;
+	struct mmp_clk_unit *unit = &pxa_unit->unit;
+
+	mmp_register_fixed_rate_clks(unit, fixed_rate_clks,
+					ARRAY_SIZE(fixed_rate_clks));
+
+	mmp_register_fixed_factor_clks(unit, fixed_factor_clks,
+					ARRAY_SIZE(fixed_factor_clks));
+
+	clk = mmp_clk_register_factor("uart_pll", "pll1_4",
+				CLK_SET_RATE_PARENT,
+				pxa_unit->mpmu_base + MPMU_UART_PLL,
+				&uart_factor_masks, uart_factor_tbl,
+				ARRAY_SIZE(uart_factor_tbl), NULL);
+	mmp_clk_add(unit, PXA910_CLK_UART_PLL, clk);
+}
+
+static DEFINE_SPINLOCK(uart0_lock);
+static DEFINE_SPINLOCK(uart1_lock);
+static DEFINE_SPINLOCK(uart2_lock);
+static const char *uart_parent_names[] = {"pll1_3_16", "uart_pll"};
+
+static DEFINE_SPINLOCK(ssp0_lock);
+static DEFINE_SPINLOCK(ssp1_lock);
+static const char *ssp_parent_names[] = {"pll1_96", "pll1_48", "pll1_24", "pll1_12"};
+
+static DEFINE_SPINLOCK(reset_lock);
+
+static struct mmp_param_mux_clk apbc_mux_clks[] = {
+	{0, "uart0_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, APBC_UART0, 4, 3, 0, &uart0_lock},
+	{0, "uart1_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, APBC_UART1, 4, 3, 0, &uart1_lock},
+	{0, "ssp0_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP0, 4, 3, 0, &ssp0_lock},
+	{0, "ssp1_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP1, 4, 3, 0, &ssp1_lock},
+};
+
+static struct mmp_param_mux_clk apbcp_mux_clks[] = {
+	{0, "uart2_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, APBCP_UART2, 4, 3, 0, &uart2_lock},
+};
+
+static struct mmp_param_gate_clk apbc_gate_clks[] = {
+	{PXA910_CLK_TWSI0, "twsi0_clk", "pll1_13_1_5", CLK_SET_RATE_PARENT, APBC_TWSI0, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA910_CLK_GPIO, "gpio_clk", "vctcxo", CLK_SET_RATE_PARENT, APBC_GPIO, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA910_CLK_KPC, "kpc_clk", "clk32", CLK_SET_RATE_PARENT, APBC_KPC, 0x3, 0x3, 0x0, MMP_CLK_GATE_NEED_DELAY, NULL},
+	{PXA910_CLK_RTC, "rtc_clk", "clk32", CLK_SET_RATE_PARENT, APBC_RTC, 0x83, 0x83, 0x0, MMP_CLK_GATE_NEED_DELAY, NULL},
+	{PXA910_CLK_PWM0, "pwm0_clk", "pll1_48", CLK_SET_RATE_PARENT, APBC_PWM0, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA910_CLK_PWM1, "pwm1_clk", "pll1_48", CLK_SET_RATE_PARENT, APBC_PWM1, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA910_CLK_PWM2, "pwm2_clk", "pll1_48", CLK_SET_RATE_PARENT, APBC_PWM2, 0x3, 0x3, 0x0, 0, &reset_lock},
+	{PXA910_CLK_PWM3, "pwm3_clk", "pll1_48", CLK_SET_RATE_PARENT, APBC_PWM3, 0x3, 0x3, 0x0, 0, &reset_lock},
+	/* The gate clocks has mux parent. */
+	{PXA910_CLK_UART0, "uart0_clk", "uart0_mux", CLK_SET_RATE_PARENT, APBC_UART0, 0x3, 0x3, 0x0, 0, &uart0_lock},
+	{PXA910_CLK_UART1, "uart1_clk", "uart1_mux", CLK_SET_RATE_PARENT, APBC_UART1, 0x3, 0x3, 0x0, 0, &uart1_lock},
+	{PXA910_CLK_SSP0, "ssp0_clk", "ssp0_mux", CLK_SET_RATE_PARENT, APBC_SSP0, 0x3, 0x3, 0x0, 0, &ssp0_lock},
+	{PXA910_CLK_SSP1, "ssp1_clk", "ssp1_mux", CLK_SET_RATE_PARENT, APBC_SSP1, 0x3, 0x3, 0x0, 0, &ssp1_lock},
+};
+
+static struct mmp_param_gate_clk apbcp_gate_clks[] = {
+	{PXA910_CLK_TWSI1, "twsi1_clk", "pll1_13_1_5", CLK_SET_RATE_PARENT, APBCP_TWSI1, 0x3, 0x3, 0x0, 0, &reset_lock},
+	/* The gate clocks has mux parent. */
+	{PXA910_CLK_UART2, "uart2_clk", "uart2_mux", CLK_SET_RATE_PARENT, APBCP_UART2, 0x3, 0x3, 0x0, 0, &uart2_lock},
+};
+
+static void pxa910_apb_periph_clk_init(struct pxa910_clk_unit *pxa_unit)
+{
+	struct mmp_clk_unit *unit = &pxa_unit->unit;
+
+	mmp_register_mux_clks(unit, apbc_mux_clks, pxa_unit->apbc_base,
+				ARRAY_SIZE(apbc_mux_clks));
+
+	mmp_register_mux_clks(unit, apbcp_mux_clks, pxa_unit->apbcp_base,
+				ARRAY_SIZE(apbcp_mux_clks));
+
+	mmp_register_gate_clks(unit, apbc_gate_clks, pxa_unit->apbc_base,
+				ARRAY_SIZE(apbc_gate_clks));
+
+	mmp_register_gate_clks(unit, apbcp_gate_clks, pxa_unit->apbcp_base,
+				ARRAY_SIZE(apbcp_gate_clks));
+}
+
+static DEFINE_SPINLOCK(sdh0_lock);
+static DEFINE_SPINLOCK(sdh1_lock);
+static const char *sdh_parent_names[] = {"pll1_12", "pll1_13"};
+
+static DEFINE_SPINLOCK(usb_lock);
+
+static DEFINE_SPINLOCK(disp0_lock);
+static const char *disp_parent_names[] = {"pll1_2", "pll1_12"};
+
+static DEFINE_SPINLOCK(ccic0_lock);
+static const char *ccic_parent_names[] = {"pll1_2", "pll1_12"};
+static const char *ccic_phy_parent_names[] = {"pll1_6", "pll1_12"};
+
+static struct mmp_param_mux_clk apmu_mux_clks[] = {
+	{0, "sdh0_mux", sdh_parent_names, ARRAY_SIZE(sdh_parent_names), CLK_SET_RATE_PARENT, APMU_SDH0, 6, 1, 0, &sdh0_lock},
+	{0, "sdh1_mux", sdh_parent_names, ARRAY_SIZE(sdh_parent_names), CLK_SET_RATE_PARENT, APMU_SDH1, 6, 1, 0, &sdh1_lock},
+	{0, "disp0_mux", disp_parent_names, ARRAY_SIZE(disp_parent_names), CLK_SET_RATE_PARENT, APMU_DISP0, 6, 1, 0, &disp0_lock},
+	{0, "ccic0_mux", ccic_parent_names, ARRAY_SIZE(ccic_parent_names), CLK_SET_RATE_PARENT, APMU_CCIC0, 6, 1, 0, &ccic0_lock},
+	{0, "ccic0_phy_mux", ccic_phy_parent_names, ARRAY_SIZE(ccic_phy_parent_names), CLK_SET_RATE_PARENT, APMU_CCIC0, 7, 1, 0, &ccic0_lock},
+};
+
+static struct mmp_param_div_clk apmu_div_clks[] = {
+	{0, "ccic0_sphy_div", "ccic0_mux", CLK_SET_RATE_PARENT, APMU_CCIC0, 10, 5, 0, &ccic0_lock},
+};
+
+static struct mmp_param_gate_clk apmu_gate_clks[] = {
+	{PXA910_CLK_DFC, "dfc_clk", "pll1_4", CLK_SET_RATE_PARENT, APMU_DFC, 0x19b, 0x19b, 0x0, 0, NULL},
+	{PXA910_CLK_USB, "usb_clk", "usb_pll", 0, APMU_USB, 0x9, 0x9, 0x0, 0, &usb_lock},
+	{PXA910_CLK_SPH, "sph_clk", "usb_pll", 0, APMU_USB, 0x12, 0x12, 0x0, 0, &usb_lock},
+	/* The gate clocks has mux parent. */
+	{PXA910_CLK_SDH0, "sdh0_clk", "sdh0_mux", CLK_SET_RATE_PARENT, APMU_SDH0, 0x1b, 0x1b, 0x0, 0, &sdh0_lock},
+	{PXA910_CLK_SDH1, "sdh1_clk", "sdh1_mux", CLK_SET_RATE_PARENT, APMU_SDH1, 0x1b, 0x1b, 0x0, 0, &sdh1_lock},
+	{PXA910_CLK_DISP0, "disp0_clk", "disp0_mux", CLK_SET_RATE_PARENT, APMU_DISP0, 0x1b, 0x1b, 0x0, 0, &disp0_lock},
+	{PXA910_CLK_CCIC0, "ccic0_clk", "ccic0_mux", CLK_SET_RATE_PARENT, APMU_CCIC0, 0x1b, 0x1b, 0x0, 0, &ccic0_lock},
+	{PXA910_CLK_CCIC0_PHY, "ccic0_phy_clk", "ccic0_phy_mux", CLK_SET_RATE_PARENT, APMU_CCIC0, 0x24, 0x24, 0x0, 0, &ccic0_lock},
+	{PXA910_CLK_CCIC0_SPHY, "ccic0_sphy_clk", "ccic0_sphy_div", CLK_SET_RATE_PARENT, APMU_CCIC0, 0x300, 0x300, 0x0, 0, &ccic0_lock},
+};
+
+static void pxa910_axi_periph_clk_init(struct pxa910_clk_unit *pxa_unit)
+{
+	struct mmp_clk_unit *unit = &pxa_unit->unit;
+
+	mmp_register_mux_clks(unit, apmu_mux_clks, pxa_unit->apmu_base,
+				ARRAY_SIZE(apmu_mux_clks));
+
+	mmp_register_div_clks(unit, apmu_div_clks, pxa_unit->apmu_base,
+				ARRAY_SIZE(apmu_div_clks));
+
+	mmp_register_gate_clks(unit, apmu_gate_clks, pxa_unit->apmu_base,
+				ARRAY_SIZE(apmu_gate_clks));
+}
+
+static void pxa910_clk_reset_init(struct device_node *np,
+				struct pxa910_clk_unit *pxa_unit)
+{
+	struct mmp_clk_reset_cell *cells;
+	int i, base, nr_resets_apbc, nr_resets_apbcp, nr_resets;
+
+	nr_resets_apbc = ARRAY_SIZE(apbc_gate_clks);
+	nr_resets_apbcp = ARRAY_SIZE(apbcp_gate_clks);
+	nr_resets = nr_resets_apbc + nr_resets_apbcp;
+	cells = kcalloc(nr_resets, sizeof(*cells), GFP_KERNEL);
+	if (!cells)
+		return;
+
+	base = 0;
+	for (i = 0; i < nr_resets_apbc; i++) {
+		cells[base + i].clk_id = apbc_gate_clks[i].id;
+		cells[base + i].reg =
+			pxa_unit->apbc_base + apbc_gate_clks[i].offset;
+		cells[base + i].flags = 0;
+		cells[base + i].lock = apbc_gate_clks[i].lock;
+		cells[base + i].bits = 0x4;
+	}
+
+	base = nr_resets_apbc;
+	for (i = 0; i < nr_resets_apbcp; i++) {
+		cells[base + i].clk_id = apbcp_gate_clks[i].id;
+		cells[base + i].reg =
+			pxa_unit->apbc_base + apbc_gate_clks[i].offset;
+		cells[base + i].flags = 0;
+		cells[base + i].lock = apbc_gate_clks[i].lock;
+		cells[base + i].bits = 0x4;
+	}
+
+	mmp_clk_reset_register(np, cells, nr_resets);
+}
+
+static void __init pxa910_clk_init(struct device_node *np)
+{
+	struct pxa910_clk_unit *pxa_unit;
+
+	pxa_unit = kzalloc(sizeof(*pxa_unit), GFP_KERNEL);
+	if (!pxa_unit)
+		return;
+
+	pxa_unit->mpmu_base = of_iomap(np, 0);
+	if (!pxa_unit->mpmu_base) {
+		pr_err("failed to map mpmu registers\n");
+		return;
+	}
+
+	pxa_unit->apmu_base = of_iomap(np, 1);
+	if (!pxa_unit->mpmu_base) {
+		pr_err("failed to map apmu registers\n");
+		return;
+	}
+
+	pxa_unit->apbc_base = of_iomap(np, 2);
+	if (!pxa_unit->apbc_base) {
+		pr_err("failed to map apbc registers\n");
+		return;
+	}
+
+	pxa_unit->apbcp_base = of_iomap(np, 3);
+	if (!pxa_unit->mpmu_base) {
+		pr_err("failed to map apbcp registers\n");
+		return;
+	}
+
+	mmp_clk_init(np, &pxa_unit->unit, PXA910_NR_CLKS);
+
+	pxa910_pll_init(pxa_unit);
+
+	pxa910_apb_periph_clk_init(pxa_unit);
+
+	pxa910_axi_periph_clk_init(pxa_unit);
+
+	pxa910_clk_reset_init(np, pxa_unit);
+}
+
+CLK_OF_DECLARE(pxa910_clk, "marvell,pxa910-clock", pxa910_clk_init);
diff --git a/include/dt-bindings/clock/marvell,pxa910.h b/include/dt-bindings/clock/marvell,pxa910.h
new file mode 100644
index 00000000000..719cffb2bea
--- /dev/null
+++ b/include/dt-bindings/clock/marvell,pxa910.h
@@ -0,0 +1,54 @@
+#ifndef __DTS_MARVELL_PXA910_CLOCK_H
+#define __DTS_MARVELL_PXA910_CLOCK_H
+
+/* fixed clocks and plls */
+#define PXA910_CLK_CLK32		1
+#define PXA910_CLK_VCTCXO		2
+#define PXA910_CLK_PLL1			3
+#define PXA910_CLK_PLL1_2		8
+#define PXA910_CLK_PLL1_4		9
+#define PXA910_CLK_PLL1_8		10
+#define PXA910_CLK_PLL1_16		11
+#define PXA910_CLK_PLL1_6		12
+#define PXA910_CLK_PLL1_12		13
+#define PXA910_CLK_PLL1_24		14
+#define PXA910_CLK_PLL1_48		15
+#define PXA910_CLK_PLL1_96		16
+#define PXA910_CLK_PLL1_13		17
+#define PXA910_CLK_PLL1_13_1_5		18
+#define PXA910_CLK_PLL1_2_1_5		19
+#define PXA910_CLK_PLL1_3_16		20
+#define PXA910_CLK_UART_PLL		27
+
+/* apb periphrals */
+#define PXA910_CLK_TWSI0		60
+#define PXA910_CLK_TWSI1		61
+#define PXA910_CLK_TWSI2		62
+#define PXA910_CLK_TWSI3		63
+#define PXA910_CLK_GPIO			64
+#define PXA910_CLK_KPC			65
+#define PXA910_CLK_RTC			66
+#define PXA910_CLK_PWM0			67
+#define PXA910_CLK_PWM1			68
+#define PXA910_CLK_PWM2			69
+#define PXA910_CLK_PWM3			70
+#define PXA910_CLK_UART0		71
+#define PXA910_CLK_UART1		72
+#define PXA910_CLK_UART2		73
+#define PXA910_CLK_SSP0			74
+#define PXA910_CLK_SSP1			75
+
+/* axi periphrals */
+#define PXA910_CLK_DFC			100
+#define PXA910_CLK_SDH0			101
+#define PXA910_CLK_SDH1			102
+#define PXA910_CLK_SDH2			103
+#define PXA910_CLK_USB			104
+#define PXA910_CLK_SPH			105
+#define PXA910_CLK_DISP0		106
+#define PXA910_CLK_CCIC0		107
+#define PXA910_CLK_CCIC0_PHY		108
+#define PXA910_CLK_CCIC0_SPHY		109
+
+#define PXA910_NR_CLKS			200
+#endif
-- 
cgit v1.2.3-70-g09d2


From 1ec770d92a62582ac1f7e0969d6a0ddc54d5f49e Mon Sep 17 00:00:00 2001
From: Chao Xie <chao.xie@marvell.com>
Date: Fri, 31 Oct 2014 10:13:51 +0800
Subject: clk: mmp: add mmp2 DT support for clock driver

It adds the DT support for mmp2 clock subsystem.

Signed-off-by: Chao Xie <chao.xie@marvell.com>
Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com>
Signed-off-by: Michael Turquette <mturquette@linaro.org>
---
 .../devicetree/bindings/clock/marvell,mmp2.txt     |  21 ++
 drivers/clk/mmp/Makefile                           |   1 +
 drivers/clk/mmp/clk-of-mmp2.c                      | 334 +++++++++++++++++++++
 include/dt-bindings/clock/marvell,mmp2.h           |  74 +++++
 4 files changed, 430 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/marvell,mmp2.txt
 create mode 100644 drivers/clk/mmp/clk-of-mmp2.c
 create mode 100644 include/dt-bindings/clock/marvell,mmp2.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/marvell,mmp2.txt b/Documentation/devicetree/bindings/clock/marvell,mmp2.txt
new file mode 100644
index 00000000000..af376a01f2b
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/marvell,mmp2.txt
@@ -0,0 +1,21 @@
+* Marvell MMP2 Clock Controller
+
+The MMP2 clock subsystem generates and supplies clock to various
+controllers within the MMP2 SoC.
+
+Required Properties:
+
+- compatible: should be one of the following.
+  - "marvell,mmp2-clock" - controller compatible with MMP2 SoC.
+
+- reg: physical base address of the clock subsystem and length of memory mapped
+  region. There are 3 places in SOC has clock control logic:
+  "mpmu", "apmu", "apbc". So three reg spaces need to be defined.
+
+- #clock-cells: should be 1.
+- #reset-cells: should be 1.
+
+Each clock is assigned an identifier and client nodes use this identifier
+to specify the clock which they consume.
+
+All these identifier could be found in <dt-bindings/clock/marvell-mmp2.h>.
diff --git a/drivers/clk/mmp/Makefile b/drivers/clk/mmp/Makefile
index 947cd74a82a..3caaf7cc169 100644
--- a/drivers/clk/mmp/Makefile
+++ b/drivers/clk/mmp/Makefile
@@ -7,6 +7,7 @@ obj-y += clk-apbc.o clk-apmu.o clk-frac.o clk-mix.o clk-gate.o clk.o
 obj-$(CONFIG_RESET_CONTROLLER) += reset.o
 
 obj-$(CONFIG_MACH_MMP_DT) += clk-of-pxa168.o clk-of-pxa910.o
+obj-$(CONFIG_MACH_MMP2_DT) += clk-of-mmp2.o
 
 obj-$(CONFIG_CPU_PXA168) += clk-pxa168.o
 obj-$(CONFIG_CPU_PXA910) += clk-pxa910.o
diff --git a/drivers/clk/mmp/clk-of-mmp2.c b/drivers/clk/mmp/clk-of-mmp2.c
new file mode 100644
index 00000000000..2cbc2b43ae5
--- /dev/null
+++ b/drivers/clk/mmp/clk-of-mmp2.c
@@ -0,0 +1,334 @@
+/*
+ * mmp2 clock framework source file
+ *
+ * Copyright (C) 2012 Marvell
+ * Chao Xie <xiechao.mail@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/of_address.h>
+
+#include <dt-bindings/clock/marvell,mmp2.h>
+
+#include "clk.h"
+#include "reset.h"
+
+#define APBC_RTC	0x0
+#define APBC_TWSI0	0x4
+#define APBC_TWSI1	0x8
+#define APBC_TWSI2	0xc
+#define APBC_TWSI3	0x10
+#define APBC_TWSI4	0x7c
+#define APBC_TWSI5	0x80
+#define APBC_KPC	0x18
+#define APBC_UART0	0x2c
+#define APBC_UART1	0x30
+#define APBC_UART2	0x34
+#define APBC_UART3	0x88
+#define APBC_GPIO	0x38
+#define APBC_PWM0	0x3c
+#define APBC_PWM1	0x40
+#define APBC_PWM2	0x44
+#define APBC_PWM3	0x48
+#define APBC_SSP0	0x50
+#define APBC_SSP1	0x54
+#define APBC_SSP2	0x58
+#define APBC_SSP3	0x5c
+#define APMU_SDH0	0x54
+#define APMU_SDH1	0x58
+#define APMU_SDH2	0xe8
+#define APMU_SDH3	0xec
+#define APMU_USB	0x5c
+#define APMU_DISP0	0x4c
+#define APMU_DISP1	0x110
+#define APMU_CCIC0	0x50
+#define APMU_CCIC1	0xf4
+#define MPMU_UART_PLL	0x14
+
+struct mmp2_clk_unit {
+	struct mmp_clk_unit unit;
+	void __iomem *mpmu_base;
+	void __iomem *apmu_base;
+	void __iomem *apbc_base;
+};
+
+static struct mmp_param_fixed_rate_clk fixed_rate_clks[] = {
+	{MMP2_CLK_CLK32, "clk32", NULL, CLK_IS_ROOT, 32768},
+	{MMP2_CLK_VCTCXO, "vctcxo", NULL, CLK_IS_ROOT, 26000000},
+	{MMP2_CLK_PLL1, "pll1", NULL, CLK_IS_ROOT, 800000000},
+	{MMP2_CLK_PLL2, "pll2", NULL, CLK_IS_ROOT, 960000000},
+	{MMP2_CLK_USB_PLL, "usb_pll", NULL, CLK_IS_ROOT, 480000000},
+};
+
+static struct mmp_param_fixed_factor_clk fixed_factor_clks[] = {
+	{MMP2_CLK_PLL1_2, "pll1_2", "pll1", 1, 2, 0},
+	{MMP2_CLK_PLL1_4, "pll1_4", "pll1_2", 1, 2, 0},
+	{MMP2_CLK_PLL1_8, "pll1_8", "pll1_4", 1, 2, 0},
+	{MMP2_CLK_PLL1_16, "pll1_16", "pll1_8", 1, 2, 0},
+	{MMP2_CLK_PLL1_20, "pll1_20", "pll1_4", 1, 5, 0},
+	{MMP2_CLK_PLL1_3, "pll1_3", "pll1", 1, 3, 0},
+	{MMP2_CLK_PLL1_6, "pll1_6", "pll1_3", 1, 2, 0},
+	{MMP2_CLK_PLL1_12, "pll1_12", "pll1_6", 1, 2, 0},
+	{MMP2_CLK_PLL2_2, "pll2_2", "pll2", 1, 2, 0},
+	{MMP2_CLK_PLL2_4, "pll2_4", "pll2_2", 1, 2, 0},
+	{MMP2_CLK_PLL2_8, "pll2_8", "pll2_4", 1, 2, 0},
+	{MMP2_CLK_PLL2_16, "pll2_16", "pll2_8", 1, 2, 0},
+	{MMP2_CLK_PLL2_3, "pll2_3", "pll2", 1, 3, 0},
+	{MMP2_CLK_PLL2_6, "pll2_6", "pll2_3", 1, 2, 0},
+	{MMP2_CLK_PLL2_12, "pll2_12", "pll2_6", 1, 2, 0},
+	{MMP2_CLK_VCTCXO_2, "vctcxo_2", "vctcxo", 1, 2, 0},
+	{MMP2_CLK_VCTCXO_4, "vctcxo_4", "vctcxo_2", 1, 2, 0},
+};
+
+static struct mmp_clk_factor_masks uart_factor_masks = {
+	.factor = 2,
+	.num_mask = 0x1fff,
+	.den_mask = 0x1fff,
+	.num_shift = 16,
+	.den_shift = 0,
+};
+
+static struct mmp_clk_factor_tbl uart_factor_tbl[] = {
+	{.num = 14634, .den = 2165},	/*14.745MHZ */
+	{.num = 3521, .den = 689},	/*19.23MHZ */
+	{.num = 9679, .den = 5728},	/*58.9824MHZ */
+	{.num = 15850, .den = 9451},	/*59.429MHZ */
+};
+
+static void mmp2_pll_init(struct mmp2_clk_unit *pxa_unit)
+{
+	struct clk *clk;
+	struct mmp_clk_unit *unit = &pxa_unit->unit;
+
+	mmp_register_fixed_rate_clks(unit, fixed_rate_clks,
+					ARRAY_SIZE(fixed_rate_clks));
+
+	mmp_register_fixed_factor_clks(unit, fixed_factor_clks,
+					ARRAY_SIZE(fixed_factor_clks));
+
+	clk = mmp_clk_register_factor("uart_pll", "pll1_4",
+				CLK_SET_RATE_PARENT,
+				pxa_unit->mpmu_base + MPMU_UART_PLL,
+				&uart_factor_masks, uart_factor_tbl,
+				ARRAY_SIZE(uart_factor_tbl), NULL);
+	mmp_clk_add(unit, MMP2_CLK_UART_PLL, clk);
+}
+
+static DEFINE_SPINLOCK(uart0_lock);
+static DEFINE_SPINLOCK(uart1_lock);
+static DEFINE_SPINLOCK(uart2_lock);
+static const char *uart_parent_names[] = {"uart_pll", "vctcxo"};
+
+static DEFINE_SPINLOCK(ssp0_lock);
+static DEFINE_SPINLOCK(ssp1_lock);
+static DEFINE_SPINLOCK(ssp2_lock);
+static DEFINE_SPINLOCK(ssp3_lock);
+static const char *ssp_parent_names[] = {"vctcxo_4", "vctcxo_2", "vctcxo", "pll1_16"};
+
+static DEFINE_SPINLOCK(reset_lock);
+
+static struct mmp_param_mux_clk apbc_mux_clks[] = {
+	{0, "uart0_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, APBC_UART0, 4, 3, 0, &uart0_lock},
+	{0, "uart1_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, APBC_UART1, 4, 3, 0, &uart1_lock},
+	{0, "uart2_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, APBC_UART2, 4, 3, 0, &uart2_lock},
+	{0, "uart3_mux", uart_parent_names, ARRAY_SIZE(uart_parent_names), CLK_SET_RATE_PARENT, APBC_UART3, 4, 3, 0, &uart2_lock},
+	{0, "ssp0_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP0, 4, 3, 0, &ssp0_lock},
+	{0, "ssp1_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP1, 4, 3, 0, &ssp1_lock},
+	{0, "ssp2_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP2, 4, 3, 0, &ssp2_lock},
+	{0, "ssp3_mux", ssp_parent_names, ARRAY_SIZE(ssp_parent_names), CLK_SET_RATE_PARENT, APBC_SSP3, 4, 3, 0, &ssp3_lock},
+};
+
+static struct mmp_param_gate_clk apbc_gate_clks[] = {
+	{MMP2_CLK_TWSI0, "twsi0_clk", "vctcxo", CLK_SET_RATE_PARENT, APBC_TWSI0, 0x7, 0x3, 0x0, 0, &reset_lock},
+	{MMP2_CLK_TWSI1, "twsi1_clk", "vctcxo", CLK_SET_RATE_PARENT, APBC_TWSI1, 0x7, 0x3, 0x0, 0, &reset_lock},
+	{MMP2_CLK_TWSI2, "twsi2_clk", "vctcxo", CLK_SET_RATE_PARENT, APBC_TWSI2, 0x7, 0x3, 0x0, 0, &reset_lock},
+	{MMP2_CLK_TWSI3, "twsi3_clk", "vctcxo", CLK_SET_RATE_PARENT, APBC_TWSI3, 0x7, 0x3, 0x0, 0, &reset_lock},
+	{MMP2_CLK_TWSI4, "twsi4_clk", "vctcxo", CLK_SET_RATE_PARENT, APBC_TWSI4, 0x7, 0x3, 0x0, 0, &reset_lock},
+	{MMP2_CLK_TWSI5, "twsi5_clk", "vctcxo", CLK_SET_RATE_PARENT, APBC_TWSI5, 0x7, 0x3, 0x0, 0, &reset_lock},
+	{MMP2_CLK_GPIO, "gpio_clk", "vctcxo", CLK_SET_RATE_PARENT, APBC_GPIO, 0x7, 0x3, 0x0, 0, &reset_lock},
+	{MMP2_CLK_KPC, "kpc_clk", "clk32", CLK_SET_RATE_PARENT, APBC_KPC, 0x7, 0x3, 0x0, MMP_CLK_GATE_NEED_DELAY, &reset_lock},
+	{MMP2_CLK_RTC, "rtc_clk", "clk32", CLK_SET_RATE_PARENT, APBC_RTC, 0x87, 0x83, 0x0, MMP_CLK_GATE_NEED_DELAY, &reset_lock},
+	{MMP2_CLK_PWM0, "pwm0_clk", "pll1_48", CLK_SET_RATE_PARENT, APBC_PWM0, 0x7, 0x3, 0x0, 0, &reset_lock},
+	{MMP2_CLK_PWM1, "pwm1_clk", "pll1_48", CLK_SET_RATE_PARENT, APBC_PWM1, 0x7, 0x3, 0x0, 0, &reset_lock},
+	{MMP2_CLK_PWM2, "pwm2_clk", "pll1_48", CLK_SET_RATE_PARENT, APBC_PWM2, 0x7, 0x3, 0x0, 0, &reset_lock},
+	{MMP2_CLK_PWM3, "pwm3_clk", "pll1_48", CLK_SET_RATE_PARENT, APBC_PWM3, 0x7, 0x3, 0x0, 0, &reset_lock},
+	/* The gate clocks has mux parent. */
+	{MMP2_CLK_UART0, "uart0_clk", "uart0_mux", CLK_SET_RATE_PARENT, APBC_UART0, 0x7, 0x3, 0x0, 0, &uart0_lock},
+	{MMP2_CLK_UART1, "uart1_clk", "uart1_mux", CLK_SET_RATE_PARENT, APBC_UART1, 0x7, 0x3, 0x0, 0, &uart1_lock},
+	{MMP2_CLK_UART2, "uart2_clk", "uart2_mux", CLK_SET_RATE_PARENT, APBC_UART2, 0x7, 0x3, 0x0, 0, &uart2_lock},
+	{MMP2_CLK_UART3, "uart3_clk", "uart3_mux", CLK_SET_RATE_PARENT, APBC_UART3, 0x7, 0x3, 0x0, 0, &uart2_lock},
+	{MMP2_CLK_SSP0, "ssp0_clk", "ssp0_mux", CLK_SET_RATE_PARENT, APBC_SSP0, 0x7, 0x3, 0x0, 0, &ssp0_lock},
+	{MMP2_CLK_SSP1, "ssp1_clk", "ssp1_mux", CLK_SET_RATE_PARENT, APBC_SSP1, 0x7, 0x3, 0x0, 0, &ssp1_lock},
+	{MMP2_CLK_SSP2, "ssp2_clk", "ssp2_mux", CLK_SET_RATE_PARENT, APBC_SSP2, 0x7, 0x3, 0x0, 0, &ssp2_lock},
+	{MMP2_CLK_SSP3, "ssp3_clk", "ssp3_mux", CLK_SET_RATE_PARENT, APBC_SSP3, 0x7, 0x3, 0x0, 0, &ssp3_lock},
+};
+
+static void mmp2_apb_periph_clk_init(struct mmp2_clk_unit *pxa_unit)
+{
+	struct mmp_clk_unit *unit = &pxa_unit->unit;
+
+	mmp_register_mux_clks(unit, apbc_mux_clks, pxa_unit->apbc_base,
+				ARRAY_SIZE(apbc_mux_clks));
+
+	mmp_register_gate_clks(unit, apbc_gate_clks, pxa_unit->apbc_base,
+				ARRAY_SIZE(apbc_gate_clks));
+}
+
+static DEFINE_SPINLOCK(sdh_lock);
+static const char *sdh_parent_names[] = {"pll1_4", "pll2", "usb_pll", "pll1"};
+static struct mmp_clk_mix_config sdh_mix_config = {
+	.reg_info = DEFINE_MIX_REG_INFO(4, 10, 2, 8, 32),
+};
+
+static DEFINE_SPINLOCK(usb_lock);
+
+static DEFINE_SPINLOCK(disp0_lock);
+static DEFINE_SPINLOCK(disp1_lock);
+static const char *disp_parent_names[] = {"pll1", "pll1_16", "pll2", "vctcxo"};
+
+static DEFINE_SPINLOCK(ccic0_lock);
+static DEFINE_SPINLOCK(ccic1_lock);
+static const char *ccic_parent_names[] = {"pll1_2", "pll1_16", "vctcxo"};
+static struct mmp_clk_mix_config ccic0_mix_config = {
+	.reg_info = DEFINE_MIX_REG_INFO(4, 17, 2, 6, 32),
+};
+static struct mmp_clk_mix_config ccic1_mix_config = {
+	.reg_info = DEFINE_MIX_REG_INFO(4, 16, 2, 6, 32),
+};
+
+static struct mmp_param_mux_clk apmu_mux_clks[] = {
+	{MMP2_CLK_DISP0_MUX, "disp0_mux", disp_parent_names, ARRAY_SIZE(disp_parent_names), CLK_SET_RATE_PARENT, APMU_DISP0, 6, 2, 0, &disp0_lock},
+	{MMP2_CLK_DISP1_MUX, "disp1_mux", disp_parent_names, ARRAY_SIZE(disp_parent_names), CLK_SET_RATE_PARENT, APMU_DISP1, 6, 2, 0, &disp1_lock},
+};
+
+static struct mmp_param_div_clk apmu_div_clks[] = {
+	{0, "disp0_div", "disp0_mux", CLK_SET_RATE_PARENT, APMU_DISP0, 8, 4, 0, &disp0_lock},
+	{0, "disp0_sphy_div", "disp0_mux", CLK_SET_RATE_PARENT, APMU_DISP0, 15, 5, 0, &disp0_lock},
+	{0, "disp1_div", "disp1_mux", CLK_SET_RATE_PARENT, APMU_DISP1, 8, 4, 0, &disp1_lock},
+	{0, "ccic0_sphy_div", "ccic0_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC0, 10, 5, 0, &ccic0_lock},
+	{0, "ccic1_sphy_div", "ccic1_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC1, 10, 5, 0, &ccic1_lock},
+};
+
+static struct mmp_param_gate_clk apmu_gate_clks[] = {
+	{MMP2_CLK_USB, "usb_clk", "usb_pll", 0, APMU_USB, 0x9, 0x9, 0x0, 0, &usb_lock},
+	/* The gate clocks has mux parent. */
+	{MMP2_CLK_SDH0, "sdh0_clk", "sdh_mix_clk", CLK_SET_RATE_PARENT, APMU_SDH0, 0x1b, 0x1b, 0x0, 0, &sdh_lock},
+	{MMP2_CLK_SDH1, "sdh1_clk", "sdh_mix_clk", CLK_SET_RATE_PARENT, APMU_SDH1, 0x1b, 0x1b, 0x0, 0, &sdh_lock},
+	{MMP2_CLK_SDH1, "sdh2_clk", "sdh_mix_clk", CLK_SET_RATE_PARENT, APMU_SDH2, 0x1b, 0x1b, 0x0, 0, &sdh_lock},
+	{MMP2_CLK_SDH1, "sdh3_clk", "sdh_mix_clk", CLK_SET_RATE_PARENT, APMU_SDH3, 0x1b, 0x1b, 0x0, 0, &sdh_lock},
+	{MMP2_CLK_DISP0, "disp0_clk", "disp0_div", CLK_SET_RATE_PARENT, APMU_DISP0, 0x1b, 0x1b, 0x0, 0, &disp0_lock},
+	{MMP2_CLK_DISP0_SPHY, "disp0_sphy_clk", "disp0_sphy_div", CLK_SET_RATE_PARENT, APMU_DISP0, 0x1024, 0x1024, 0x0, 0, &disp0_lock},
+	{MMP2_CLK_DISP1, "disp1_clk", "disp1_div", CLK_SET_RATE_PARENT, APMU_DISP1, 0x1b, 0x1b, 0x0, 0, &disp1_lock},
+	{MMP2_CLK_CCIC_ARBITER, "ccic_arbiter", "vctcxo", CLK_SET_RATE_PARENT, APMU_CCIC0, 0x1800, 0x1800, 0x0, 0, &ccic0_lock},
+	{MMP2_CLK_CCIC0, "ccic0_clk", "ccic0_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC0, 0x1b, 0x1b, 0x0, 0, &ccic0_lock},
+	{MMP2_CLK_CCIC0_PHY, "ccic0_phy_clk", "ccic0_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC0, 0x24, 0x24, 0x0, 0, &ccic0_lock},
+	{MMP2_CLK_CCIC0_SPHY, "ccic0_sphy_clk", "ccic0_sphy_div", CLK_SET_RATE_PARENT, APMU_CCIC0, 0x300, 0x300, 0x0, 0, &ccic0_lock},
+	{MMP2_CLK_CCIC1, "ccic1_clk", "ccic1_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x1b, 0x1b, 0x0, 0, &ccic1_lock},
+	{MMP2_CLK_CCIC1_PHY, "ccic1_phy_clk", "ccic1_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x24, 0x24, 0x0, 0, &ccic1_lock},
+	{MMP2_CLK_CCIC1_SPHY, "ccic1_sphy_clk", "ccic1_sphy_div", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x300, 0x300, 0x0, 0, &ccic1_lock},
+};
+
+static void mmp2_axi_periph_clk_init(struct mmp2_clk_unit *pxa_unit)
+{
+	struct clk *clk;
+	struct mmp_clk_unit *unit = &pxa_unit->unit;
+
+	sdh_mix_config.reg_info.reg_clk_ctrl = pxa_unit->apmu_base + APMU_SDH0;
+	clk = mmp_clk_register_mix(NULL, "sdh_mix_clk", sdh_parent_names,
+					ARRAY_SIZE(sdh_parent_names),
+					CLK_SET_RATE_PARENT,
+					&sdh_mix_config, &sdh_lock);
+
+	ccic0_mix_config.reg_info.reg_clk_ctrl = pxa_unit->apmu_base + APMU_CCIC0;
+	clk = mmp_clk_register_mix(NULL, "ccic0_mix_clk", ccic_parent_names,
+					ARRAY_SIZE(ccic_parent_names),
+					CLK_SET_RATE_PARENT,
+					&ccic0_mix_config, &ccic0_lock);
+	mmp_clk_add(unit, MMP2_CLK_CCIC0_MIX, clk);
+
+	ccic1_mix_config.reg_info.reg_clk_ctrl = pxa_unit->apmu_base + APMU_CCIC1;
+	clk = mmp_clk_register_mix(NULL, "ccic1_mix_clk", ccic_parent_names,
+					ARRAY_SIZE(ccic_parent_names),
+					CLK_SET_RATE_PARENT,
+					&ccic1_mix_config, &ccic1_lock);
+	mmp_clk_add(unit, MMP2_CLK_CCIC1_MIX, clk);
+
+	mmp_register_mux_clks(unit, apmu_mux_clks, pxa_unit->apmu_base,
+				ARRAY_SIZE(apmu_mux_clks));
+
+	mmp_register_div_clks(unit, apmu_div_clks, pxa_unit->apmu_base,
+				ARRAY_SIZE(apmu_div_clks));
+
+	mmp_register_gate_clks(unit, apmu_gate_clks, pxa_unit->apmu_base,
+				ARRAY_SIZE(apmu_gate_clks));
+}
+
+static void mmp2_clk_reset_init(struct device_node *np,
+				struct mmp2_clk_unit *pxa_unit)
+{
+	struct mmp_clk_reset_cell *cells;
+	int i, nr_resets;
+
+	nr_resets = ARRAY_SIZE(apbc_gate_clks);
+	cells = kcalloc(nr_resets, sizeof(*cells), GFP_KERNEL);
+	if (!cells)
+		return;
+
+	for (i = 0; i < nr_resets; i++) {
+		cells[i].clk_id = apbc_gate_clks[i].id;
+		cells[i].reg = pxa_unit->apbc_base + apbc_gate_clks[i].offset;
+		cells[i].flags = 0;
+		cells[i].lock = apbc_gate_clks[i].lock;
+		cells[i].bits = 0x4;
+	}
+
+	mmp_clk_reset_register(np, cells, nr_resets);
+}
+
+static void __init mmp2_clk_init(struct device_node *np)
+{
+	struct mmp2_clk_unit *pxa_unit;
+
+	pxa_unit = kzalloc(sizeof(*pxa_unit), GFP_KERNEL);
+	if (!pxa_unit)
+		return;
+
+	pxa_unit->mpmu_base = of_iomap(np, 0);
+	if (!pxa_unit->mpmu_base) {
+		pr_err("failed to map mpmu registers\n");
+		return;
+	}
+
+	pxa_unit->apmu_base = of_iomap(np, 1);
+	if (!pxa_unit->mpmu_base) {
+		pr_err("failed to map apmu registers\n");
+		return;
+	}
+
+	pxa_unit->apbc_base = of_iomap(np, 2);
+	if (!pxa_unit->apbc_base) {
+		pr_err("failed to map apbc registers\n");
+		return;
+	}
+
+	mmp_clk_init(np, &pxa_unit->unit, MMP2_NR_CLKS);
+
+	mmp2_pll_init(pxa_unit);
+
+	mmp2_apb_periph_clk_init(pxa_unit);
+
+	mmp2_axi_periph_clk_init(pxa_unit);
+
+	mmp2_clk_reset_init(np, pxa_unit);
+}
+
+CLK_OF_DECLARE(mmp2_clk, "marvell,mmp2-clock", mmp2_clk_init);
diff --git a/include/dt-bindings/clock/marvell,mmp2.h b/include/dt-bindings/clock/marvell,mmp2.h
new file mode 100644
index 00000000000..591f7fba89e
--- /dev/null
+++ b/include/dt-bindings/clock/marvell,mmp2.h
@@ -0,0 +1,74 @@
+#ifndef __DTS_MARVELL_MMP2_CLOCK_H
+#define __DTS_MARVELL_MMP2_CLOCK_H
+
+/* fixed clocks and plls */
+#define MMP2_CLK_CLK32			1
+#define MMP2_CLK_VCTCXO			2
+#define MMP2_CLK_PLL1			3
+#define MMP2_CLK_PLL1_2			8
+#define MMP2_CLK_PLL1_4			9
+#define MMP2_CLK_PLL1_8			10
+#define MMP2_CLK_PLL1_16		11
+#define MMP2_CLK_PLL1_3			12
+#define MMP2_CLK_PLL1_6			13
+#define MMP2_CLK_PLL1_12		14
+#define MMP2_CLK_PLL1_20		15
+#define MMP2_CLK_PLL2			16
+#define MMP2_CLK_PLL2_2			17
+#define MMP2_CLK_PLL2_4			18
+#define MMP2_CLK_PLL2_8			19
+#define MMP2_CLK_PLL2_16		20
+#define MMP2_CLK_PLL2_3			21
+#define MMP2_CLK_PLL2_6			22
+#define MMP2_CLK_PLL2_12		23
+#define MMP2_CLK_VCTCXO_2		24
+#define MMP2_CLK_VCTCXO_4		25
+#define MMP2_CLK_UART_PLL		26
+#define MMP2_CLK_USB_PLL		27
+
+/* apb periphrals */
+#define MMP2_CLK_TWSI0			60
+#define MMP2_CLK_TWSI1			61
+#define MMP2_CLK_TWSI2			62
+#define MMP2_CLK_TWSI3			63
+#define MMP2_CLK_TWSI4			64
+#define MMP2_CLK_TWSI5			65
+#define MMP2_CLK_GPIO			66
+#define MMP2_CLK_KPC			67
+#define MMP2_CLK_RTC			68
+#define MMP2_CLK_PWM0			69
+#define MMP2_CLK_PWM1			70
+#define MMP2_CLK_PWM2			71
+#define MMP2_CLK_PWM3			72
+#define MMP2_CLK_UART0			73
+#define MMP2_CLK_UART1			74
+#define MMP2_CLK_UART2			75
+#define MMP2_CLK_UART3			76
+#define MMP2_CLK_SSP0			77
+#define MMP2_CLK_SSP1			78
+#define MMP2_CLK_SSP2			79
+#define MMP2_CLK_SSP3			80
+
+/* axi periphrals */
+#define MMP2_CLK_SDH0			101
+#define MMP2_CLK_SDH1			102
+#define MMP2_CLK_SDH2			103
+#define MMP2_CLK_SDH3			104
+#define MMP2_CLK_USB			105
+#define MMP2_CLK_DISP0			106
+#define MMP2_CLK_DISP0_MUX		107
+#define MMP2_CLK_DISP0_SPHY		108
+#define MMP2_CLK_DISP1			109
+#define MMP2_CLK_DISP1_MUX		110
+#define MMP2_CLK_CCIC_ARBITER		111
+#define MMP2_CLK_CCIC0			112
+#define MMP2_CLK_CCIC0_MIX		113
+#define MMP2_CLK_CCIC0_PHY		114
+#define MMP2_CLK_CCIC0_SPHY		115
+#define MMP2_CLK_CCIC1			116
+#define MMP2_CLK_CCIC1_MIX		117
+#define MMP2_CLK_CCIC1_PHY		118
+#define MMP2_CLK_CCIC1_SPHY		119
+
+#define MMP2_NR_CLKS			200
+#endif
-- 
cgit v1.2.3-70-g09d2


From 61f2dcba9a03d4fd9342f0d6821af0a46c7098e9 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 12 Nov 2014 19:51:56 +0100
Subject: mac802154: add interframe spacing time handling

This patch adds a new interframe spacing time handling into mac802154
layer. Interframe spacing time is a time period between each transmit.
This patch adds a high resolution timer into mac802154 and starts on
xmit complete with corresponding interframe spacing expire time if
ifs_handling is true. We make it variable because it depends if
interframe spacing time is handled by transceiver or mac802154. At the
timer complete function we wake the netdev queue again. This avoids
new frame transmit in range of interframe spacing time.

For synced driver we add no handling of interframe spacing time. This
is currently a lack of support in all synced xmit drivers. I suppose
it's working because the latency of workqueue which is needed to call
spi_sync.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/net/ieee802154/at86rf230.c |  2 +-
 include/linux/ieee802154.h         |  3 +++
 include/net/cfg802154.h            |  8 ++++++++
 include/net/mac802154.h            |  3 ++-
 net/mac802154/ieee802154_i.h       |  4 ++++
 net/mac802154/iface.c              |  2 ++
 net/mac802154/main.c               | 17 +++++++++++++++++
 net/mac802154/tx.c                 |  2 +-
 net/mac802154/util.c               | 32 +++++++++++++++++++++++++++++---
 9 files changed, 67 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 31d62f9c6ce..46e50295710 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -731,7 +731,7 @@ at86rf230_tx_complete(void *context)
 			udelay(lp->data->t_sifs);
 	}
 
-	ieee802154_xmit_complete(lp->hw, skb);
+	ieee802154_xmit_complete(lp->hw, skb, false);
 }
 
 static void
diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index ce0f96a5597..5a40c041843 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -36,6 +36,9 @@
 
 #define IEEE802154_EXTENDED_ADDR_LEN	8
 
+#define IEEE802154_LIFS_PERIOD		40
+#define IEEE802154_SIFS_PERIOD		12
+
 #define IEEE802154_FC_TYPE_BEACON	0x0	/* Frame is beacon */
 #define	IEEE802154_FC_TYPE_DATA		0x1	/* Frame is data */
 #define IEEE802154_FC_TYPE_ACK		0x2	/* Frame is acknowledgment */
diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index fa0a9e51952..17b4fc0705b 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -81,6 +81,14 @@ struct wpan_phy {
 
 	s32 cca_ed_level;
 
+	/* PHY depended MAC PIB values */
+
+	/* 802.15.4 acronym: Tdsym in usec */
+	u8 symbol_duration;
+	/* lifs and sifs periods timing */
+	u16 lifs_period;
+	u16 sifs_period;
+
 	struct device dev;
 
 	char priv[0] __aligned(NETDEV_ALIGN);
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 632f6566adb..c823d910b46 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -260,6 +260,7 @@ void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb,
 
 void ieee802154_wake_queue(struct ieee802154_hw *hw);
 void ieee802154_stop_queue(struct ieee802154_hw *hw);
-void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb);
+void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb,
+			      bool ifs_handling);
 
 #endif /* NET_MAC802154_H */
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index 69cb585e162..c5b231047b6 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -20,6 +20,7 @@
 #define __IEEE802154_I_H
 
 #include <linux/mutex.h>
+#include <linux/hrtimer.h>
 #include <net/cfg802154.h>
 #include <net/mac802154.h>
 #include <net/ieee802154_netdev.h>
@@ -51,6 +52,8 @@ struct ieee802154_local {
 	 */
 	struct workqueue_struct	*workqueue;
 
+	struct hrtimer ifs_timer;
+
 	bool started;
 
 	struct tasklet_struct tasklet;
@@ -127,6 +130,7 @@ ieee802154_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev);
 void mac802154_wpan_setup(struct net_device *dev);
 netdev_tx_t
 ieee802154_subif_start_xmit(struct sk_buff *skb, struct net_device *dev);
+enum hrtimer_restart ieee802154_xmit_ifs_timer(struct hrtimer *timer);
 
 /* MIB callbacks */
 void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val);
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index ec92b48d1b0..feb064715d1 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -246,6 +246,8 @@ static int mac802154_slave_close(struct net_device *dev)
 
 	ASSERT_RTNL();
 
+	hrtimer_cancel(&local->ifs_timer);
+
 	netif_stop_queue(dev);
 	local->open_count--;
 
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 46c76e00544..0af1be64e8a 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -125,6 +125,18 @@ void ieee802154_free_hw(struct ieee802154_hw *hw)
 }
 EXPORT_SYMBOL(ieee802154_free_hw);
 
+static void ieee802154_setup_wpan_phy_pib(struct wpan_phy *wpan_phy)
+{
+	/* TODO warn on empty symbol_duration
+	 * Should be done when all drivers sets this value.
+	 */
+
+	wpan_phy->lifs_period = IEEE802154_LIFS_PERIOD *
+				wpan_phy->symbol_duration;
+	wpan_phy->sifs_period = IEEE802154_SIFS_PERIOD *
+				wpan_phy->symbol_duration;
+}
+
 int ieee802154_register_hw(struct ieee802154_hw *hw)
 {
 	struct ieee802154_local *local = hw_to_local(hw);
@@ -138,8 +150,13 @@ int ieee802154_register_hw(struct ieee802154_hw *hw)
 		goto out;
 	}
 
+	hrtimer_init(&local->ifs_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	local->ifs_timer.function = ieee802154_xmit_ifs_timer;
+
 	wpan_phy_set_dev(local->phy, local->hw.parent);
 
+	ieee802154_setup_wpan_phy_pib(local->phy);
+
 	rc = wpan_phy_register(local->phy);
 	if (rc < 0)
 		goto out_wq;
diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c
index cc37b77f263..c62e95695c7 100644
--- a/net/mac802154/tx.c
+++ b/net/mac802154/tx.c
@@ -60,7 +60,7 @@ static void ieee802154_xmit_worker(struct work_struct *work)
 	if (res)
 		goto err_tx;
 
-	ieee802154_xmit_complete(&local->hw, skb);
+	ieee802154_xmit_complete(&local->hw, skb, false);
 
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
diff --git a/net/mac802154/util.c b/net/mac802154/util.c
index 9a04e4a8e50..5fc97902791 100644
--- a/net/mac802154/util.c
+++ b/net/mac802154/util.c
@@ -50,9 +50,35 @@ void ieee802154_stop_queue(struct ieee802154_hw *hw)
 }
 EXPORT_SYMBOL(ieee802154_stop_queue);
 
-void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb)
+enum hrtimer_restart ieee802154_xmit_ifs_timer(struct hrtimer *timer)
 {
-	ieee802154_wake_queue(hw);
-	consume_skb(skb);
+	struct ieee802154_local *local =
+		container_of(timer, struct ieee802154_local, ifs_timer);
+
+	ieee802154_wake_queue(&local->hw);
+
+	return HRTIMER_NORESTART;
+}
+
+void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb,
+			      bool ifs_handling)
+{
+	if (ifs_handling) {
+		struct ieee802154_local *local = hw_to_local(hw);
+
+		if (skb->len > 18)
+			hrtimer_start(&local->ifs_timer,
+				      ktime_set(0, hw->phy->lifs_period * NSEC_PER_USEC),
+				      HRTIMER_MODE_REL);
+		else
+			hrtimer_start(&local->ifs_timer,
+				      ktime_set(0, hw->phy->sifs_period * NSEC_PER_USEC),
+				      HRTIMER_MODE_REL);
+
+		consume_skb(skb);
+	} else {
+		ieee802154_wake_queue(hw);
+		consume_skb(skb);
+	}
 }
 EXPORT_SYMBOL(ieee802154_xmit_complete);
-- 
cgit v1.2.3-70-g09d2


From abe84903a8efc6b83fa92161429e0e3a28bde15c Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Wed, 12 Nov 2014 22:22:21 +0200
Subject: Bluetooth: Use proper nesting annotation for l2cap_chan lock

By default lockdep considers all L2CAP channels equal. This would mean
that we get warnings if a channel is locked when another one's lock is
tried to be acquired in the same thread. This kind of inter-channel
locking dependencies exist in the form of parent-child channels as well
as any channel wishing to elevate the security by requesting procedures
on the SMP channel.

To eliminate the chance for these lockdep warnings we introduce a
nesting level for each channel and use that when acquiring the channel
lock. For now there exists the earlier mentioned three identified
categories: SMP, "normal" channels and parent channels (i.e. those in
BT_LISTEN state). The nesting level is defined as atomic_t since we need
access to it before the lock is actually acquired.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h | 15 ++++++++++++++-
 net/bluetooth/l2cap_sock.c    |  9 +++++++++
 net/bluetooth/smp.c           | 10 ++++++++++
 3 files changed, 33 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index ead99f032f7..061e648052c 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -28,6 +28,7 @@
 #define __L2CAP_H
 
 #include <asm/unaligned.h>
+#include <linux/atomic.h>
 
 /* L2CAP defaults */
 #define L2CAP_DEFAULT_MTU		672
@@ -481,6 +482,7 @@ struct l2cap_chan {
 	struct hci_conn		*hs_hcon;
 	struct hci_chan		*hs_hchan;
 	struct kref	kref;
+	atomic_t	nesting;
 
 	__u8		state;
 
@@ -713,6 +715,17 @@ enum {
 	FLAG_HOLD_HCI_CONN,
 };
 
+/* Lock nesting levels for L2CAP channels. We need these because lockdep
+ * otherwise considers all channels equal and will e.g. complain about a
+ * connection oriented channel triggering SMP procedures or a listening
+ * channel creating and locking a child channel.
+ */
+enum {
+	L2CAP_NESTING_SMP,
+	L2CAP_NESTING_NORMAL,
+	L2CAP_NESTING_PARENT,
+};
+
 enum {
 	L2CAP_TX_STATE_XMIT,
 	L2CAP_TX_STATE_WAIT_F,
@@ -778,7 +791,7 @@ void l2cap_chan_put(struct l2cap_chan *c);
 
 static inline void l2cap_chan_lock(struct l2cap_chan *chan)
 {
-	mutex_lock(&chan->lock);
+	mutex_lock_nested(&chan->lock, atomic_read(&chan->nesting));
 }
 
 static inline void l2cap_chan_unlock(struct l2cap_chan *chan)
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index ad1cf82fee0..f1a51564b8f 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -285,6 +285,12 @@ static int l2cap_sock_listen(struct socket *sock, int backlog)
 	sk->sk_max_ack_backlog = backlog;
 	sk->sk_ack_backlog = 0;
 
+	/* Listening channels need to use nested locking in order not to
+	 * cause lockdep warnings when the created child channels end up
+	 * being locked in the same thread as the parent channel.
+	 */
+	atomic_set(&chan->nesting, L2CAP_NESTING_PARENT);
+
 	chan->state = BT_LISTEN;
 	sk->sk_state = BT_LISTEN;
 
@@ -1497,6 +1503,9 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent)
 		l2cap_chan_set_defaults(chan);
 	}
 
+	/* Set default lock nesting level */
+	atomic_set(&chan->nesting, L2CAP_NESTING_NORMAL);
+
 	/* Default config options */
 	chan->flush_to = L2CAP_DEFAULT_FLUSH_TO;
 
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 3d38553eb52..3b63c7f09dd 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -1658,6 +1658,13 @@ static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan)
 	chan->omtu	= pchan->omtu;
 	chan->mode	= pchan->mode;
 
+	/* Other L2CAP channels may request SMP routines in order to
+	 * change the security level. This means that the SMP channel
+	 * lock must be considered in its own category to avoid lockdep
+	 * warnings.
+	 */
+	atomic_set(&chan->nesting, L2CAP_NESTING_SMP);
+
 	BT_DBG("created chan %p", chan);
 
 	return chan;
@@ -1715,6 +1722,9 @@ int smp_register(struct hci_dev *hdev)
 	chan->imtu = L2CAP_DEFAULT_MTU;
 	chan->ops = &smp_root_chan_ops;
 
+	/* Set correct nesting level for a parent/listening channel */
+	atomic_set(&chan->nesting, L2CAP_NESTING_PARENT);
+
 	hdev->smp_data = chan;
 
 	return 0;
-- 
cgit v1.2.3-70-g09d2


From 53c2e285f9703001e1bb48d04696c5f9d8f3aef7 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 13 Nov 2014 17:09:49 +0800
Subject: xfrm: Do not hash socket policies

Back in 2003 when I added policy expiration, I half-heartedly
did a clean-up and renamed xfrm_sk_policy_link/xfrm_sk_policy_unlink
to __xfrm_policy_link/__xfrm_policy_unlink, because the latter
could be reused for all policies.  I never actually got around
to using __xfrm_policy_link for non-socket policies.

Later on hashing was added to all xfrm policies, including socket
policies.  In fact, we don't need hashing on socket policies at
all since they're always looked up via a linked list.

This patch restores xfrm_sk_policy_link/xfrm_sk_policy_unlink
as wrappers around __xfrm_policy_link/__xfrm_policy_unlink so
that it's obvious we're dealing with socket policies.

This patch also removes hashing from __xfrm_policy_link as for
now it's only used by socket policies which do not need to be
hashed.  Ironically this will in fact allow us to use this helper
for non-socket policies which I shall do later.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/netns/xfrm.h |  4 ++--
 net/xfrm/xfrm_policy.c   | 44 ++++++++++++++++++++++++++------------------
 2 files changed, 28 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 9da798256f0..730d82ad6ee 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -50,8 +50,8 @@ struct netns_xfrm {
 	struct list_head	policy_all;
 	struct hlist_head	*policy_byidx;
 	unsigned int		policy_idx_hmask;
-	struct hlist_head	policy_inexact[XFRM_POLICY_MAX * 2];
-	struct xfrm_policy_hash	policy_bydst[XFRM_POLICY_MAX * 2];
+	struct hlist_head	policy_inexact[XFRM_POLICY_MAX];
+	struct xfrm_policy_hash	policy_bydst[XFRM_POLICY_MAX];
 	unsigned int		policy_count[XFRM_POLICY_MAX * 2];
 	struct work_struct	policy_hash_work;
 	struct xfrm_policy_hthresh policy_hthresh;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index dc653249e84..f4d3a125e49 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -561,7 +561,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 	mutex_lock(&hash_resize_mutex);
 
 	total = 0;
-	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 		if (xfrm_bydst_should_resize(net, dir, &total))
 			xfrm_bydst_resize(net, dir);
 	}
@@ -601,7 +601,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 
 	/* reset the bydst and inexact table in all directions */
-	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 		INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
 		hmask = net->xfrm.policy_bydst[dir].hmask;
 		odst = net->xfrm.policy_bydst[dir].table;
@@ -1247,17 +1247,10 @@ out:
 static void __xfrm_policy_link(struct xfrm_policy *pol, int dir)
 {
 	struct net *net = xp_net(pol);
-	struct hlist_head *chain = policy_hash_bysel(net, &pol->selector,
-						     pol->family, dir);
 
 	list_add(&pol->walk.all, &net->xfrm.policy_all);
-	hlist_add_head(&pol->bydst, chain);
-	hlist_add_head(&pol->byidx, net->xfrm.policy_byidx+idx_hash(net, pol->index));
 	net->xfrm.policy_count[dir]++;
 	xfrm_pol_hold(pol);
-
-	if (xfrm_bydst_should_resize(net, dir, NULL))
-		schedule_work(&net->xfrm.policy_hash_work);
 }
 
 static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
@@ -1265,17 +1258,31 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 {
 	struct net *net = xp_net(pol);
 
-	if (hlist_unhashed(&pol->bydst))
+	if (list_empty(&pol->walk.all))
 		return NULL;
 
-	hlist_del_init(&pol->bydst);
-	hlist_del(&pol->byidx);
-	list_del(&pol->walk.all);
+	/* Socket policies are not hashed. */
+	if (!hlist_unhashed(&pol->bydst)) {
+		hlist_del(&pol->bydst);
+		hlist_del(&pol->byidx);
+	}
+
+	list_del_init(&pol->walk.all);
 	net->xfrm.policy_count[dir]--;
 
 	return pol;
 }
 
+static void xfrm_sk_policy_link(struct xfrm_policy *pol, int dir)
+{
+	__xfrm_policy_link(pol, XFRM_POLICY_MAX + dir);
+}
+
+static void xfrm_sk_policy_unlink(struct xfrm_policy *pol, int dir)
+{
+	__xfrm_policy_unlink(pol, XFRM_POLICY_MAX + dir);
+}
+
 int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
 {
 	struct net *net = xp_net(pol);
@@ -1307,7 +1314,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 	if (pol) {
 		pol->curlft.add_time = get_seconds();
 		pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0);
-		__xfrm_policy_link(pol, XFRM_POLICY_MAX+dir);
+		xfrm_sk_policy_link(pol, dir);
 	}
 	if (old_pol) {
 		if (pol)
@@ -1316,7 +1323,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 		/* Unlinking succeeds always. This is the only function
 		 * allowed to delete or replace socket policy.
 		 */
-		__xfrm_policy_unlink(old_pol, XFRM_POLICY_MAX+dir);
+		xfrm_sk_policy_unlink(old_pol, dir);
 	}
 	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
@@ -1349,7 +1356,7 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
 		memcpy(newp->xfrm_vec, old->xfrm_vec,
 		       newp->xfrm_nr*sizeof(struct xfrm_tmpl));
 		write_lock_bh(&net->xfrm.xfrm_policy_lock);
-		__xfrm_policy_link(newp, XFRM_POLICY_MAX+dir);
+		xfrm_sk_policy_link(newp, dir);
 		write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 		xfrm_pol_put(newp);
 	}
@@ -2965,10 +2972,11 @@ static int __net_init xfrm_policy_init(struct net *net)
 		goto out_byidx;
 	net->xfrm.policy_idx_hmask = hmask;
 
-	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 		struct xfrm_policy_hash *htab;
 
 		net->xfrm.policy_count[dir] = 0;
+		net->xfrm.policy_count[XFRM_POLICY_MAX + dir] = 0;
 		INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
 
 		htab = &net->xfrm.policy_bydst[dir];
@@ -3020,7 +3028,7 @@ static void xfrm_policy_fini(struct net *net)
 
 	WARN_ON(!list_empty(&net->xfrm.policy_all));
 
-	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 		struct xfrm_policy_hash *htab;
 
 		WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir]));
-- 
cgit v1.2.3-70-g09d2


From f0a0a58e6f46c2dded813ee860b9cbd795b4e571 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Date: Fri, 7 Nov 2014 21:58:21 +0100
Subject: ARM: at91: move sdramc/ddrsdr header to include/soc/at91

Move the (DDR) SDRAM controller headers to include/soc/at91 to remove the
dependency on mach/ headers from the at91-reset driver.

Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
---
 MAINTAINERS                                        |   1 +
 arch/arm/mach-at91/include/mach/at91_ramc.h        |   6 +-
 .../arm/mach-at91/include/mach/at91rm9200_sdramc.h |  63 -----------
 arch/arm/mach-at91/include/mach/at91sam9_ddrsdr.h  | 124 ---------------------
 arch/arm/mach-at91/include/mach/at91sam9_sdramc.h  |  85 --------------
 arch/arm/mach-at91/pm.h                            |   1 -
 drivers/power/reset/at91-reset.c                   |   4 +-
 include/soc/at91/at91rm9200_sdramc.h               |  63 +++++++++++
 include/soc/at91/at91sam9_ddrsdr.h                 | 124 +++++++++++++++++++++
 include/soc/at91/at91sam9_sdramc.h                 |  85 ++++++++++++++
 10 files changed, 278 insertions(+), 278 deletions(-)
 delete mode 100644 arch/arm/mach-at91/include/mach/at91rm9200_sdramc.h
 delete mode 100644 arch/arm/mach-at91/include/mach/at91sam9_ddrsdr.h
 delete mode 100644 arch/arm/mach-at91/include/mach/at91sam9_sdramc.h
 create mode 100644 include/soc/at91/at91rm9200_sdramc.h
 create mode 100644 include/soc/at91/at91sam9_ddrsdr.h
 create mode 100644 include/soc/at91/at91sam9_sdramc.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index dab92a78d1d..9b604e7cc86 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -861,6 +861,7 @@ W:	http://maxim.org.za/at91_26.html
 W:	http://www.linux4sam.org
 S:	Supported
 F:	arch/arm/mach-at91/
+F:	include/soc/at91/
 F:	arch/arm/boot/dts/at91*.dts
 F:	arch/arm/boot/dts/at91*.dtsi
 F:	arch/arm/boot/dts/sama*.dts
diff --git a/arch/arm/mach-at91/include/mach/at91_ramc.h b/arch/arm/mach-at91/include/mach/at91_ramc.h
index d8aeb278614..e4492b151fe 100644
--- a/arch/arm/mach-at91/include/mach/at91_ramc.h
+++ b/arch/arm/mach-at91/include/mach/at91_ramc.h
@@ -25,8 +25,8 @@ extern void __iomem *at91_ramc_base[];
 #define AT91_MEMCTRL_SDRAMC	1
 #define AT91_MEMCTRL_DDRSDR	2
 
-#include <mach/at91rm9200_sdramc.h>
-#include <mach/at91sam9_ddrsdr.h>
-#include <mach/at91sam9_sdramc.h>
+#include <soc/at91/at91rm9200_sdramc.h>
+#include <soc/at91/at91sam9_ddrsdr.h>
+#include <soc/at91/at91sam9_sdramc.h>
 
 #endif /* __AT91_RAMC_H__ */
diff --git a/arch/arm/mach-at91/include/mach/at91rm9200_sdramc.h b/arch/arm/mach-at91/include/mach/at91rm9200_sdramc.h
deleted file mode 100644
index aa047f458f1..00000000000
--- a/arch/arm/mach-at91/include/mach/at91rm9200_sdramc.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * arch/arm/mach-at91/include/mach/at91rm9200_sdramc.h
- *
- * Copyright (C) 2005 Ivan Kokshaysky
- * Copyright (C) SAN People
- *
- * Memory Controllers (SDRAMC only) - System peripherals registers.
- * Based on AT91RM9200 datasheet revision E.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef AT91RM9200_SDRAMC_H
-#define AT91RM9200_SDRAMC_H
-
-/* SDRAM Controller registers */
-#define AT91RM9200_SDRAMC_MR		0x90			/* Mode Register */
-#define		AT91RM9200_SDRAMC_MODE	(0xf << 0)		/* Command Mode */
-#define			AT91RM9200_SDRAMC_MODE_NORMAL		(0 << 0)
-#define			AT91RM9200_SDRAMC_MODE_NOP		(1 << 0)
-#define			AT91RM9200_SDRAMC_MODE_PRECHARGE	(2 << 0)
-#define			AT91RM9200_SDRAMC_MODE_LMR		(3 << 0)
-#define			AT91RM9200_SDRAMC_MODE_REFRESH	(4 << 0)
-#define		AT91RM9200_SDRAMC_DBW		(1   << 4)		/* Data Bus Width */
-#define			AT91RM9200_SDRAMC_DBW_32	(0 << 4)
-#define			AT91RM9200_SDRAMC_DBW_16	(1 << 4)
-
-#define AT91RM9200_SDRAMC_TR		0x94			/* Refresh Timer Register */
-#define		AT91RM9200_SDRAMC_COUNT	(0xfff << 0)		/* Refresh Timer Count */
-
-#define AT91RM9200_SDRAMC_CR		0x98			/* Configuration Register */
-#define		AT91RM9200_SDRAMC_NC		(3   <<  0)		/* Number of Column Bits */
-#define			AT91RM9200_SDRAMC_NC_8	(0 << 0)
-#define			AT91RM9200_SDRAMC_NC_9	(1 << 0)
-#define			AT91RM9200_SDRAMC_NC_10	(2 << 0)
-#define			AT91RM9200_SDRAMC_NC_11	(3 << 0)
-#define		AT91RM9200_SDRAMC_NR		(3   <<  2)		/* Number of Row Bits */
-#define			AT91RM9200_SDRAMC_NR_11	(0 << 2)
-#define			AT91RM9200_SDRAMC_NR_12	(1 << 2)
-#define			AT91RM9200_SDRAMC_NR_13	(2 << 2)
-#define		AT91RM9200_SDRAMC_NB		(1   <<  4)		/* Number of Banks */
-#define			AT91RM9200_SDRAMC_NB_2	(0 << 4)
-#define			AT91RM9200_SDRAMC_NB_4	(1 << 4)
-#define		AT91RM9200_SDRAMC_CAS		(3   <<  5)		/* CAS Latency */
-#define			AT91RM9200_SDRAMC_CAS_2	(2 << 5)
-#define		AT91RM9200_SDRAMC_TWR		(0xf <<  7)		/* Write Recovery Delay */
-#define		AT91RM9200_SDRAMC_TRC		(0xf << 11)		/* Row Cycle Delay */
-#define		AT91RM9200_SDRAMC_TRP		(0xf << 15)		/* Row Precharge Delay */
-#define		AT91RM9200_SDRAMC_TRCD	(0xf << 19)		/* Row to Column Delay */
-#define		AT91RM9200_SDRAMC_TRAS	(0xf << 23)		/* Active to Precharge Delay */
-#define		AT91RM9200_SDRAMC_TXSR	(0xf << 27)		/* Exit Self Refresh to Active Delay */
-
-#define AT91RM9200_SDRAMC_SRR		0x9c			/* Self Refresh Register */
-#define AT91RM9200_SDRAMC_LPR		0xa0			/* Low Power Register */
-#define AT91RM9200_SDRAMC_IER		0xa4			/* Interrupt Enable Register */
-#define AT91RM9200_SDRAMC_IDR		0xa8			/* Interrupt Disable Register */
-#define AT91RM9200_SDRAMC_IMR		0xac			/* Interrupt Mask Register */
-#define AT91RM9200_SDRAMC_ISR		0xb0			/* Interrupt Status Register */
-
-#endif
diff --git a/arch/arm/mach-at91/include/mach/at91sam9_ddrsdr.h b/arch/arm/mach-at91/include/mach/at91sam9_ddrsdr.h
deleted file mode 100644
index 0210797abf2..00000000000
--- a/arch/arm/mach-at91/include/mach/at91sam9_ddrsdr.h
+++ /dev/null
@@ -1,124 +0,0 @@
-/*
- * Header file for the Atmel DDR/SDR SDRAM Controller
- *
- * Copyright (C) 2010 Atmel Corporation
- *	Nicolas Ferre <nicolas.ferre@atmel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-#ifndef AT91SAM9_DDRSDR_H
-#define AT91SAM9_DDRSDR_H
-
-#define AT91_DDRSDRC_MR		0x00	/* Mode Register */
-#define		AT91_DDRSDRC_MODE	(0x7 << 0)		/* Command Mode */
-#define			AT91_DDRSDRC_MODE_NORMAL	0
-#define			AT91_DDRSDRC_MODE_NOP		1
-#define			AT91_DDRSDRC_MODE_PRECHARGE	2
-#define			AT91_DDRSDRC_MODE_LMR		3
-#define			AT91_DDRSDRC_MODE_REFRESH	4
-#define			AT91_DDRSDRC_MODE_EXT_LMR	5
-#define			AT91_DDRSDRC_MODE_DEEP		6
-
-#define AT91_DDRSDRC_RTR	0x04	/* Refresh Timer Register */
-#define		AT91_DDRSDRC_COUNT	(0xfff << 0)		/* Refresh Timer Counter */
-
-#define AT91_DDRSDRC_CR		0x08	/* Configuration Register */
-#define		AT91_DDRSDRC_NC		(3 << 0)		/* Number of Column Bits */
-#define			AT91_DDRSDRC_NC_SDR8	(0 << 0)
-#define			AT91_DDRSDRC_NC_SDR9	(1 << 0)
-#define			AT91_DDRSDRC_NC_SDR10	(2 << 0)
-#define			AT91_DDRSDRC_NC_SDR11	(3 << 0)
-#define			AT91_DDRSDRC_NC_DDR9	(0 << 0)
-#define			AT91_DDRSDRC_NC_DDR10	(1 << 0)
-#define			AT91_DDRSDRC_NC_DDR11	(2 << 0)
-#define			AT91_DDRSDRC_NC_DDR12	(3 << 0)
-#define		AT91_DDRSDRC_NR		(3 << 2)		/* Number of Row Bits */
-#define			AT91_DDRSDRC_NR_11	(0 << 2)
-#define			AT91_DDRSDRC_NR_12	(1 << 2)
-#define			AT91_DDRSDRC_NR_13	(2 << 2)
-#define			AT91_DDRSDRC_NR_14	(3 << 2)
-#define		AT91_DDRSDRC_CAS	(7 << 4)		/* CAS Latency */
-#define			AT91_DDRSDRC_CAS_2	(2 << 4)
-#define			AT91_DDRSDRC_CAS_3	(3 << 4)
-#define			AT91_DDRSDRC_CAS_25	(6 << 4)
-#define		AT91_DDRSDRC_RST_DLL	(1 << 7)		/* Reset DLL */
-#define		AT91_DDRSDRC_DICDS	(1 << 8)		/* Output impedance control */
-#define		AT91_DDRSDRC_DIS_DLL	(1 << 9)		/* Disable DLL [SAM9 Only] */
-#define		AT91_DDRSDRC_OCD	(1 << 12)		/* Off-Chip Driver [SAM9 Only] */
-#define		AT91_DDRSDRC_DQMS	(1 << 16)		/* Mask Data is Shared [SAM9 Only] */
-#define		AT91_DDRSDRC_ACTBST	(1 << 18)		/* Active Bank X to Burst Stop Read Access Bank Y [SAM9 Only] */
-
-#define AT91_DDRSDRC_T0PR	0x0C	/* Timing 0 Register */
-#define		AT91_DDRSDRC_TRAS	(0xf <<  0)		/* Active to Precharge delay */
-#define		AT91_DDRSDRC_TRCD	(0xf <<  4)		/* Row to Column delay */
-#define		AT91_DDRSDRC_TWR	(0xf <<  8)		/* Write recovery delay */
-#define		AT91_DDRSDRC_TRC	(0xf << 12)		/* Row cycle delay */
-#define		AT91_DDRSDRC_TRP	(0xf << 16)		/* Row precharge delay */
-#define		AT91_DDRSDRC_TRRD	(0xf << 20)		/* Active BankA to BankB */
-#define		AT91_DDRSDRC_TWTR	(0x7 << 24)		/* Internal Write to Read delay */
-#define		AT91_DDRSDRC_RED_WRRD	(0x1 << 27)		/* Reduce Write to Read Delay [SAM9 Only] */
-#define		AT91_DDRSDRC_TMRD	(0xf << 28)		/* Load mode to active/refresh delay */
-
-#define AT91_DDRSDRC_T1PR	0x10	/* Timing 1 Register */
-#define		AT91_DDRSDRC_TRFC	(0x1f << 0)		/* Row Cycle Delay */
-#define		AT91_DDRSDRC_TXSNR	(0xff << 8)		/* Exit self-refresh to non-read */
-#define		AT91_DDRSDRC_TXSRD	(0xff << 16)		/* Exit self-refresh to read */
-#define		AT91_DDRSDRC_TXP	(0xf  << 24)		/* Exit power-down delay */
-
-#define AT91_DDRSDRC_T2PR	0x14	/* Timing 2 Register [SAM9 Only] */
-#define		AT91_DDRSDRC_TXARD	(0xf  << 0)		/* Exit active power down delay to read command in mode "Fast Exit" */
-#define		AT91_DDRSDRC_TXARDS	(0xf  << 4)		/* Exit active power down delay to read command in mode "Slow Exit" */
-#define		AT91_DDRSDRC_TRPA	(0xf  << 8)		/* Row Precharge All delay */
-#define		AT91_DDRSDRC_TRTP	(0x7  << 12)		/* Read to Precharge delay */
-
-#define AT91_DDRSDRC_LPR	0x1C	/* Low Power Register */
-#define		AT91_DDRSDRC_LPCB	(3 << 0)		/* Low-power Configurations */
-#define			AT91_DDRSDRC_LPCB_DISABLE		0
-#define			AT91_DDRSDRC_LPCB_SELF_REFRESH		1
-#define			AT91_DDRSDRC_LPCB_POWER_DOWN		2
-#define			AT91_DDRSDRC_LPCB_DEEP_POWER_DOWN	3
-#define		AT91_DDRSDRC_CLKFR	(1 << 2)	/* Clock Frozen */
-#define		AT91_DDRSDRC_PASR	(7 << 4)	/* Partial Array Self Refresh */
-#define		AT91_DDRSDRC_TCSR	(3 << 8)	/* Temperature Compensated Self Refresh */
-#define		AT91_DDRSDRC_DS		(3 << 10)	/* Drive Strength */
-#define		AT91_DDRSDRC_TIMEOUT	(3 << 12)	/* Time to define when Low Power Mode is enabled */
-#define			AT91_DDRSDRC_TIMEOUT_0_CLK_CYCLES	(0 << 12)
-#define			AT91_DDRSDRC_TIMEOUT_64_CLK_CYCLES	(1 << 12)
-#define			AT91_DDRSDRC_TIMEOUT_128_CLK_CYCLES	(2 << 12)
-#define		AT91_DDRSDRC_APDE	(1 << 16)	 /* Active power down exit time */
-#define		AT91_DDRSDRC_UPD_MR	(3 << 20)	 /* Update load mode register and extended mode register */
-
-#define AT91_DDRSDRC_MDR	0x20	/* Memory Device Register */
-#define		AT91_DDRSDRC_MD		(3 << 0)		/* Memory Device Type */
-#define			AT91_DDRSDRC_MD_SDR		0
-#define			AT91_DDRSDRC_MD_LOW_POWER_SDR	1
-#define			AT91_DDRSDRC_MD_LOW_POWER_DDR	3
-#define			AT91_DDRSDRC_MD_DDR2		6	/* [SAM9 Only] */
-#define		AT91_DDRSDRC_DBW	(1 << 4)		/* Data Bus Width */
-#define			AT91_DDRSDRC_DBW_32BITS		(0 <<  4)
-#define			AT91_DDRSDRC_DBW_16BITS		(1 <<  4)
-
-#define AT91_DDRSDRC_DLL	0x24	/* DLL Information Register */
-#define		AT91_DDRSDRC_MDINC	(1 << 0)		/* Master Delay increment */
-#define		AT91_DDRSDRC_MDDEC	(1 << 1)		/* Master Delay decrement */
-#define		AT91_DDRSDRC_MDOVF	(1 << 2)		/* Master Delay Overflow */
-#define		AT91_DDRSDRC_MDVAL	(0xff <<  8)		/* Master Delay value */
-
-#define AT91_DDRSDRC_HS		0x2C	/* High Speed Register [SAM9 Only] */
-#define		AT91_DDRSDRC_DIS_ATCP_RD	(1 << 2)	/* Anticip read access is disabled */
-
-#define AT91_DDRSDRC_DELAY(n)	(0x30 + (0x4 * (n)))	/* Delay I/O Register n */
-
-#define AT91_DDRSDRC_WPMR	0xE4	/* Write Protect Mode Register [SAM9 Only] */
-#define		AT91_DDRSDRC_WP		(1 << 0)		/* Write protect enable */
-#define		AT91_DDRSDRC_WPKEY	(0xffffff << 8)		/* Write protect key */
-#define		AT91_DDRSDRC_KEY	(0x444452 << 8)		/* Write protect key = "DDR" */
-
-#define AT91_DDRSDRC_WPSR	0xE8	/* Write Protect Status Register [SAM9 Only] */
-#define		AT91_DDRSDRC_WPVS	(1 << 0)		/* Write protect violation status */
-#define		AT91_DDRSDRC_WPVSRC	(0xffff << 8)		/* Write protect violation source */
-
-#endif
diff --git a/arch/arm/mach-at91/include/mach/at91sam9_sdramc.h b/arch/arm/mach-at91/include/mach/at91sam9_sdramc.h
deleted file mode 100644
index 3d085a9a745..00000000000
--- a/arch/arm/mach-at91/include/mach/at91sam9_sdramc.h
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- * arch/arm/mach-at91/include/mach/at91sam9_sdramc.h
- *
- * Copyright (C) 2007 Andrew Victor
- * Copyright (C) 2007 Atmel Corporation.
- *
- * SDRAM Controllers (SDRAMC) - System peripherals registers.
- * Based on AT91SAM9261 datasheet revision D.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef AT91SAM9_SDRAMC_H
-#define AT91SAM9_SDRAMC_H
-
-/* SDRAM Controller (SDRAMC) registers */
-#define AT91_SDRAMC_MR		0x00	/* SDRAM Controller Mode Register */
-#define		AT91_SDRAMC_MODE	(0xf << 0)		/* Command Mode */
-#define			AT91_SDRAMC_MODE_NORMAL		0
-#define			AT91_SDRAMC_MODE_NOP		1
-#define			AT91_SDRAMC_MODE_PRECHARGE	2
-#define			AT91_SDRAMC_MODE_LMR		3
-#define			AT91_SDRAMC_MODE_REFRESH	4
-#define			AT91_SDRAMC_MODE_EXT_LMR	5
-#define			AT91_SDRAMC_MODE_DEEP		6
-
-#define AT91_SDRAMC_TR		0x04	/* SDRAM Controller Refresh Timer Register */
-#define		AT91_SDRAMC_COUNT	(0xfff << 0)		/* Refresh Timer Counter */
-
-#define AT91_SDRAMC_CR		0x08	/* SDRAM Controller Configuration Register */
-#define		AT91_SDRAMC_NC		(3 << 0)		/* Number of Column Bits */
-#define			AT91_SDRAMC_NC_8	(0 << 0)
-#define			AT91_SDRAMC_NC_9	(1 << 0)
-#define			AT91_SDRAMC_NC_10	(2 << 0)
-#define			AT91_SDRAMC_NC_11	(3 << 0)
-#define		AT91_SDRAMC_NR		(3 << 2)		/* Number of Row Bits */
-#define			AT91_SDRAMC_NR_11	(0 << 2)
-#define			AT91_SDRAMC_NR_12	(1 << 2)
-#define			AT91_SDRAMC_NR_13	(2 << 2)
-#define		AT91_SDRAMC_NB		(1 << 4)		/* Number of Banks */
-#define			AT91_SDRAMC_NB_2	(0 << 4)
-#define			AT91_SDRAMC_NB_4	(1 << 4)
-#define		AT91_SDRAMC_CAS		(3 << 5)		/* CAS Latency */
-#define			AT91_SDRAMC_CAS_1	(1 << 5)
-#define			AT91_SDRAMC_CAS_2	(2 << 5)
-#define			AT91_SDRAMC_CAS_3	(3 << 5)
-#define		AT91_SDRAMC_DBW		(1 << 7)		/* Data Bus Width */
-#define			AT91_SDRAMC_DBW_32	(0 << 7)
-#define			AT91_SDRAMC_DBW_16	(1 << 7)
-#define		AT91_SDRAMC_TWR		(0xf <<  8)		/* Write Recovery Delay */
-#define		AT91_SDRAMC_TRC		(0xf << 12)		/* Row Cycle Delay */
-#define		AT91_SDRAMC_TRP		(0xf << 16)		/* Row Precharge Delay */
-#define		AT91_SDRAMC_TRCD	(0xf << 20)		/* Row to Column Delay */
-#define		AT91_SDRAMC_TRAS	(0xf << 24)		/* Active to Precharge Delay */
-#define		AT91_SDRAMC_TXSR	(0xf << 28)		/* Exit Self Refresh to Active Delay */
-
-#define AT91_SDRAMC_LPR		0x10	/* SDRAM Controller Low Power Register */
-#define		AT91_SDRAMC_LPCB		(3 << 0)	/* Low-power Configurations */
-#define			AT91_SDRAMC_LPCB_DISABLE		0
-#define			AT91_SDRAMC_LPCB_SELF_REFRESH		1
-#define			AT91_SDRAMC_LPCB_POWER_DOWN		2
-#define			AT91_SDRAMC_LPCB_DEEP_POWER_DOWN	3
-#define		AT91_SDRAMC_PASR		(7 << 4)	/* Partial Array Self Refresh */
-#define		AT91_SDRAMC_TCSR		(3 << 8)	/* Temperature Compensated Self Refresh */
-#define		AT91_SDRAMC_DS			(3 << 10)	/* Drive Strength */
-#define		AT91_SDRAMC_TIMEOUT		(3 << 12)	/* Time to define when Low Power Mode is enabled */
-#define			AT91_SDRAMC_TIMEOUT_0_CLK_CYCLES	(0 << 12)
-#define			AT91_SDRAMC_TIMEOUT_64_CLK_CYCLES	(1 << 12)
-#define			AT91_SDRAMC_TIMEOUT_128_CLK_CYCLES	(2 << 12)
-
-#define AT91_SDRAMC_IER		0x14	/* SDRAM Controller Interrupt Enable Register */
-#define AT91_SDRAMC_IDR		0x18	/* SDRAM Controller Interrupt Disable Register */
-#define AT91_SDRAMC_IMR		0x1C	/* SDRAM Controller Interrupt Mask Register */
-#define AT91_SDRAMC_ISR		0x20	/* SDRAM Controller Interrupt Status Register */
-#define		AT91_SDRAMC_RES		(1 << 0)		/* Refresh Error Status */
-
-#define AT91_SDRAMC_MDR		0x24	/* SDRAM Memory Device Register */
-#define		AT91_SDRAMC_MD		(3 << 0)		/* Memory Device Type */
-#define			AT91_SDRAMC_MD_SDRAM		0
-#define			AT91_SDRAMC_MD_LOW_POWER_SDRAM	1
-
-#endif
diff --git a/arch/arm/mach-at91/pm.h b/arch/arm/mach-at91/pm.h
index c5101dcb4fb..d2c89963af2 100644
--- a/arch/arm/mach-at91/pm.h
+++ b/arch/arm/mach-at91/pm.h
@@ -14,7 +14,6 @@
 #include <asm/proc-fns.h>
 
 #include <mach/at91_ramc.h>
-#include <mach/at91rm9200_sdramc.h>
 
 #ifdef CONFIG_PM
 extern void at91_pm_set_standby(void (*at91_standby)(void));
diff --git a/drivers/power/reset/at91-reset.c b/drivers/power/reset/at91-reset.c
index 3cb36693343..69a75d99ae9 100644
--- a/drivers/power/reset/at91-reset.c
+++ b/drivers/power/reset/at91-reset.c
@@ -19,8 +19,8 @@
 
 #include <asm/system_misc.h>
 
-#include <mach/at91sam9_ddrsdr.h>
-#include <mach/at91sam9_sdramc.h>
+#include <soc/at91/at91sam9_ddrsdr.h>
+#include <soc/at91/at91sam9_sdramc.h>
 
 #define AT91_RSTC_CR	0x00		/* Reset Controller Control Register */
 #define AT91_RSTC_PROCRST	BIT(0)		/* Processor Reset */
diff --git a/include/soc/at91/at91rm9200_sdramc.h b/include/soc/at91/at91rm9200_sdramc.h
new file mode 100644
index 00000000000..aa047f458f1
--- /dev/null
+++ b/include/soc/at91/at91rm9200_sdramc.h
@@ -0,0 +1,63 @@
+/*
+ * arch/arm/mach-at91/include/mach/at91rm9200_sdramc.h
+ *
+ * Copyright (C) 2005 Ivan Kokshaysky
+ * Copyright (C) SAN People
+ *
+ * Memory Controllers (SDRAMC only) - System peripherals registers.
+ * Based on AT91RM9200 datasheet revision E.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef AT91RM9200_SDRAMC_H
+#define AT91RM9200_SDRAMC_H
+
+/* SDRAM Controller registers */
+#define AT91RM9200_SDRAMC_MR		0x90			/* Mode Register */
+#define		AT91RM9200_SDRAMC_MODE	(0xf << 0)		/* Command Mode */
+#define			AT91RM9200_SDRAMC_MODE_NORMAL		(0 << 0)
+#define			AT91RM9200_SDRAMC_MODE_NOP		(1 << 0)
+#define			AT91RM9200_SDRAMC_MODE_PRECHARGE	(2 << 0)
+#define			AT91RM9200_SDRAMC_MODE_LMR		(3 << 0)
+#define			AT91RM9200_SDRAMC_MODE_REFRESH	(4 << 0)
+#define		AT91RM9200_SDRAMC_DBW		(1   << 4)		/* Data Bus Width */
+#define			AT91RM9200_SDRAMC_DBW_32	(0 << 4)
+#define			AT91RM9200_SDRAMC_DBW_16	(1 << 4)
+
+#define AT91RM9200_SDRAMC_TR		0x94			/* Refresh Timer Register */
+#define		AT91RM9200_SDRAMC_COUNT	(0xfff << 0)		/* Refresh Timer Count */
+
+#define AT91RM9200_SDRAMC_CR		0x98			/* Configuration Register */
+#define		AT91RM9200_SDRAMC_NC		(3   <<  0)		/* Number of Column Bits */
+#define			AT91RM9200_SDRAMC_NC_8	(0 << 0)
+#define			AT91RM9200_SDRAMC_NC_9	(1 << 0)
+#define			AT91RM9200_SDRAMC_NC_10	(2 << 0)
+#define			AT91RM9200_SDRAMC_NC_11	(3 << 0)
+#define		AT91RM9200_SDRAMC_NR		(3   <<  2)		/* Number of Row Bits */
+#define			AT91RM9200_SDRAMC_NR_11	(0 << 2)
+#define			AT91RM9200_SDRAMC_NR_12	(1 << 2)
+#define			AT91RM9200_SDRAMC_NR_13	(2 << 2)
+#define		AT91RM9200_SDRAMC_NB		(1   <<  4)		/* Number of Banks */
+#define			AT91RM9200_SDRAMC_NB_2	(0 << 4)
+#define			AT91RM9200_SDRAMC_NB_4	(1 << 4)
+#define		AT91RM9200_SDRAMC_CAS		(3   <<  5)		/* CAS Latency */
+#define			AT91RM9200_SDRAMC_CAS_2	(2 << 5)
+#define		AT91RM9200_SDRAMC_TWR		(0xf <<  7)		/* Write Recovery Delay */
+#define		AT91RM9200_SDRAMC_TRC		(0xf << 11)		/* Row Cycle Delay */
+#define		AT91RM9200_SDRAMC_TRP		(0xf << 15)		/* Row Precharge Delay */
+#define		AT91RM9200_SDRAMC_TRCD	(0xf << 19)		/* Row to Column Delay */
+#define		AT91RM9200_SDRAMC_TRAS	(0xf << 23)		/* Active to Precharge Delay */
+#define		AT91RM9200_SDRAMC_TXSR	(0xf << 27)		/* Exit Self Refresh to Active Delay */
+
+#define AT91RM9200_SDRAMC_SRR		0x9c			/* Self Refresh Register */
+#define AT91RM9200_SDRAMC_LPR		0xa0			/* Low Power Register */
+#define AT91RM9200_SDRAMC_IER		0xa4			/* Interrupt Enable Register */
+#define AT91RM9200_SDRAMC_IDR		0xa8			/* Interrupt Disable Register */
+#define AT91RM9200_SDRAMC_IMR		0xac			/* Interrupt Mask Register */
+#define AT91RM9200_SDRAMC_ISR		0xb0			/* Interrupt Status Register */
+
+#endif
diff --git a/include/soc/at91/at91sam9_ddrsdr.h b/include/soc/at91/at91sam9_ddrsdr.h
new file mode 100644
index 00000000000..0210797abf2
--- /dev/null
+++ b/include/soc/at91/at91sam9_ddrsdr.h
@@ -0,0 +1,124 @@
+/*
+ * Header file for the Atmel DDR/SDR SDRAM Controller
+ *
+ * Copyright (C) 2010 Atmel Corporation
+ *	Nicolas Ferre <nicolas.ferre@atmel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef AT91SAM9_DDRSDR_H
+#define AT91SAM9_DDRSDR_H
+
+#define AT91_DDRSDRC_MR		0x00	/* Mode Register */
+#define		AT91_DDRSDRC_MODE	(0x7 << 0)		/* Command Mode */
+#define			AT91_DDRSDRC_MODE_NORMAL	0
+#define			AT91_DDRSDRC_MODE_NOP		1
+#define			AT91_DDRSDRC_MODE_PRECHARGE	2
+#define			AT91_DDRSDRC_MODE_LMR		3
+#define			AT91_DDRSDRC_MODE_REFRESH	4
+#define			AT91_DDRSDRC_MODE_EXT_LMR	5
+#define			AT91_DDRSDRC_MODE_DEEP		6
+
+#define AT91_DDRSDRC_RTR	0x04	/* Refresh Timer Register */
+#define		AT91_DDRSDRC_COUNT	(0xfff << 0)		/* Refresh Timer Counter */
+
+#define AT91_DDRSDRC_CR		0x08	/* Configuration Register */
+#define		AT91_DDRSDRC_NC		(3 << 0)		/* Number of Column Bits */
+#define			AT91_DDRSDRC_NC_SDR8	(0 << 0)
+#define			AT91_DDRSDRC_NC_SDR9	(1 << 0)
+#define			AT91_DDRSDRC_NC_SDR10	(2 << 0)
+#define			AT91_DDRSDRC_NC_SDR11	(3 << 0)
+#define			AT91_DDRSDRC_NC_DDR9	(0 << 0)
+#define			AT91_DDRSDRC_NC_DDR10	(1 << 0)
+#define			AT91_DDRSDRC_NC_DDR11	(2 << 0)
+#define			AT91_DDRSDRC_NC_DDR12	(3 << 0)
+#define		AT91_DDRSDRC_NR		(3 << 2)		/* Number of Row Bits */
+#define			AT91_DDRSDRC_NR_11	(0 << 2)
+#define			AT91_DDRSDRC_NR_12	(1 << 2)
+#define			AT91_DDRSDRC_NR_13	(2 << 2)
+#define			AT91_DDRSDRC_NR_14	(3 << 2)
+#define		AT91_DDRSDRC_CAS	(7 << 4)		/* CAS Latency */
+#define			AT91_DDRSDRC_CAS_2	(2 << 4)
+#define			AT91_DDRSDRC_CAS_3	(3 << 4)
+#define			AT91_DDRSDRC_CAS_25	(6 << 4)
+#define		AT91_DDRSDRC_RST_DLL	(1 << 7)		/* Reset DLL */
+#define		AT91_DDRSDRC_DICDS	(1 << 8)		/* Output impedance control */
+#define		AT91_DDRSDRC_DIS_DLL	(1 << 9)		/* Disable DLL [SAM9 Only] */
+#define		AT91_DDRSDRC_OCD	(1 << 12)		/* Off-Chip Driver [SAM9 Only] */
+#define		AT91_DDRSDRC_DQMS	(1 << 16)		/* Mask Data is Shared [SAM9 Only] */
+#define		AT91_DDRSDRC_ACTBST	(1 << 18)		/* Active Bank X to Burst Stop Read Access Bank Y [SAM9 Only] */
+
+#define AT91_DDRSDRC_T0PR	0x0C	/* Timing 0 Register */
+#define		AT91_DDRSDRC_TRAS	(0xf <<  0)		/* Active to Precharge delay */
+#define		AT91_DDRSDRC_TRCD	(0xf <<  4)		/* Row to Column delay */
+#define		AT91_DDRSDRC_TWR	(0xf <<  8)		/* Write recovery delay */
+#define		AT91_DDRSDRC_TRC	(0xf << 12)		/* Row cycle delay */
+#define		AT91_DDRSDRC_TRP	(0xf << 16)		/* Row precharge delay */
+#define		AT91_DDRSDRC_TRRD	(0xf << 20)		/* Active BankA to BankB */
+#define		AT91_DDRSDRC_TWTR	(0x7 << 24)		/* Internal Write to Read delay */
+#define		AT91_DDRSDRC_RED_WRRD	(0x1 << 27)		/* Reduce Write to Read Delay [SAM9 Only] */
+#define		AT91_DDRSDRC_TMRD	(0xf << 28)		/* Load mode to active/refresh delay */
+
+#define AT91_DDRSDRC_T1PR	0x10	/* Timing 1 Register */
+#define		AT91_DDRSDRC_TRFC	(0x1f << 0)		/* Row Cycle Delay */
+#define		AT91_DDRSDRC_TXSNR	(0xff << 8)		/* Exit self-refresh to non-read */
+#define		AT91_DDRSDRC_TXSRD	(0xff << 16)		/* Exit self-refresh to read */
+#define		AT91_DDRSDRC_TXP	(0xf  << 24)		/* Exit power-down delay */
+
+#define AT91_DDRSDRC_T2PR	0x14	/* Timing 2 Register [SAM9 Only] */
+#define		AT91_DDRSDRC_TXARD	(0xf  << 0)		/* Exit active power down delay to read command in mode "Fast Exit" */
+#define		AT91_DDRSDRC_TXARDS	(0xf  << 4)		/* Exit active power down delay to read command in mode "Slow Exit" */
+#define		AT91_DDRSDRC_TRPA	(0xf  << 8)		/* Row Precharge All delay */
+#define		AT91_DDRSDRC_TRTP	(0x7  << 12)		/* Read to Precharge delay */
+
+#define AT91_DDRSDRC_LPR	0x1C	/* Low Power Register */
+#define		AT91_DDRSDRC_LPCB	(3 << 0)		/* Low-power Configurations */
+#define			AT91_DDRSDRC_LPCB_DISABLE		0
+#define			AT91_DDRSDRC_LPCB_SELF_REFRESH		1
+#define			AT91_DDRSDRC_LPCB_POWER_DOWN		2
+#define			AT91_DDRSDRC_LPCB_DEEP_POWER_DOWN	3
+#define		AT91_DDRSDRC_CLKFR	(1 << 2)	/* Clock Frozen */
+#define		AT91_DDRSDRC_PASR	(7 << 4)	/* Partial Array Self Refresh */
+#define		AT91_DDRSDRC_TCSR	(3 << 8)	/* Temperature Compensated Self Refresh */
+#define		AT91_DDRSDRC_DS		(3 << 10)	/* Drive Strength */
+#define		AT91_DDRSDRC_TIMEOUT	(3 << 12)	/* Time to define when Low Power Mode is enabled */
+#define			AT91_DDRSDRC_TIMEOUT_0_CLK_CYCLES	(0 << 12)
+#define			AT91_DDRSDRC_TIMEOUT_64_CLK_CYCLES	(1 << 12)
+#define			AT91_DDRSDRC_TIMEOUT_128_CLK_CYCLES	(2 << 12)
+#define		AT91_DDRSDRC_APDE	(1 << 16)	 /* Active power down exit time */
+#define		AT91_DDRSDRC_UPD_MR	(3 << 20)	 /* Update load mode register and extended mode register */
+
+#define AT91_DDRSDRC_MDR	0x20	/* Memory Device Register */
+#define		AT91_DDRSDRC_MD		(3 << 0)		/* Memory Device Type */
+#define			AT91_DDRSDRC_MD_SDR		0
+#define			AT91_DDRSDRC_MD_LOW_POWER_SDR	1
+#define			AT91_DDRSDRC_MD_LOW_POWER_DDR	3
+#define			AT91_DDRSDRC_MD_DDR2		6	/* [SAM9 Only] */
+#define		AT91_DDRSDRC_DBW	(1 << 4)		/* Data Bus Width */
+#define			AT91_DDRSDRC_DBW_32BITS		(0 <<  4)
+#define			AT91_DDRSDRC_DBW_16BITS		(1 <<  4)
+
+#define AT91_DDRSDRC_DLL	0x24	/* DLL Information Register */
+#define		AT91_DDRSDRC_MDINC	(1 << 0)		/* Master Delay increment */
+#define		AT91_DDRSDRC_MDDEC	(1 << 1)		/* Master Delay decrement */
+#define		AT91_DDRSDRC_MDOVF	(1 << 2)		/* Master Delay Overflow */
+#define		AT91_DDRSDRC_MDVAL	(0xff <<  8)		/* Master Delay value */
+
+#define AT91_DDRSDRC_HS		0x2C	/* High Speed Register [SAM9 Only] */
+#define		AT91_DDRSDRC_DIS_ATCP_RD	(1 << 2)	/* Anticip read access is disabled */
+
+#define AT91_DDRSDRC_DELAY(n)	(0x30 + (0x4 * (n)))	/* Delay I/O Register n */
+
+#define AT91_DDRSDRC_WPMR	0xE4	/* Write Protect Mode Register [SAM9 Only] */
+#define		AT91_DDRSDRC_WP		(1 << 0)		/* Write protect enable */
+#define		AT91_DDRSDRC_WPKEY	(0xffffff << 8)		/* Write protect key */
+#define		AT91_DDRSDRC_KEY	(0x444452 << 8)		/* Write protect key = "DDR" */
+
+#define AT91_DDRSDRC_WPSR	0xE8	/* Write Protect Status Register [SAM9 Only] */
+#define		AT91_DDRSDRC_WPVS	(1 << 0)		/* Write protect violation status */
+#define		AT91_DDRSDRC_WPVSRC	(0xffff << 8)		/* Write protect violation source */
+
+#endif
diff --git a/include/soc/at91/at91sam9_sdramc.h b/include/soc/at91/at91sam9_sdramc.h
new file mode 100644
index 00000000000..3d085a9a745
--- /dev/null
+++ b/include/soc/at91/at91sam9_sdramc.h
@@ -0,0 +1,85 @@
+/*
+ * arch/arm/mach-at91/include/mach/at91sam9_sdramc.h
+ *
+ * Copyright (C) 2007 Andrew Victor
+ * Copyright (C) 2007 Atmel Corporation.
+ *
+ * SDRAM Controllers (SDRAMC) - System peripherals registers.
+ * Based on AT91SAM9261 datasheet revision D.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef AT91SAM9_SDRAMC_H
+#define AT91SAM9_SDRAMC_H
+
+/* SDRAM Controller (SDRAMC) registers */
+#define AT91_SDRAMC_MR		0x00	/* SDRAM Controller Mode Register */
+#define		AT91_SDRAMC_MODE	(0xf << 0)		/* Command Mode */
+#define			AT91_SDRAMC_MODE_NORMAL		0
+#define			AT91_SDRAMC_MODE_NOP		1
+#define			AT91_SDRAMC_MODE_PRECHARGE	2
+#define			AT91_SDRAMC_MODE_LMR		3
+#define			AT91_SDRAMC_MODE_REFRESH	4
+#define			AT91_SDRAMC_MODE_EXT_LMR	5
+#define			AT91_SDRAMC_MODE_DEEP		6
+
+#define AT91_SDRAMC_TR		0x04	/* SDRAM Controller Refresh Timer Register */
+#define		AT91_SDRAMC_COUNT	(0xfff << 0)		/* Refresh Timer Counter */
+
+#define AT91_SDRAMC_CR		0x08	/* SDRAM Controller Configuration Register */
+#define		AT91_SDRAMC_NC		(3 << 0)		/* Number of Column Bits */
+#define			AT91_SDRAMC_NC_8	(0 << 0)
+#define			AT91_SDRAMC_NC_9	(1 << 0)
+#define			AT91_SDRAMC_NC_10	(2 << 0)
+#define			AT91_SDRAMC_NC_11	(3 << 0)
+#define		AT91_SDRAMC_NR		(3 << 2)		/* Number of Row Bits */
+#define			AT91_SDRAMC_NR_11	(0 << 2)
+#define			AT91_SDRAMC_NR_12	(1 << 2)
+#define			AT91_SDRAMC_NR_13	(2 << 2)
+#define		AT91_SDRAMC_NB		(1 << 4)		/* Number of Banks */
+#define			AT91_SDRAMC_NB_2	(0 << 4)
+#define			AT91_SDRAMC_NB_4	(1 << 4)
+#define		AT91_SDRAMC_CAS		(3 << 5)		/* CAS Latency */
+#define			AT91_SDRAMC_CAS_1	(1 << 5)
+#define			AT91_SDRAMC_CAS_2	(2 << 5)
+#define			AT91_SDRAMC_CAS_3	(3 << 5)
+#define		AT91_SDRAMC_DBW		(1 << 7)		/* Data Bus Width */
+#define			AT91_SDRAMC_DBW_32	(0 << 7)
+#define			AT91_SDRAMC_DBW_16	(1 << 7)
+#define		AT91_SDRAMC_TWR		(0xf <<  8)		/* Write Recovery Delay */
+#define		AT91_SDRAMC_TRC		(0xf << 12)		/* Row Cycle Delay */
+#define		AT91_SDRAMC_TRP		(0xf << 16)		/* Row Precharge Delay */
+#define		AT91_SDRAMC_TRCD	(0xf << 20)		/* Row to Column Delay */
+#define		AT91_SDRAMC_TRAS	(0xf << 24)		/* Active to Precharge Delay */
+#define		AT91_SDRAMC_TXSR	(0xf << 28)		/* Exit Self Refresh to Active Delay */
+
+#define AT91_SDRAMC_LPR		0x10	/* SDRAM Controller Low Power Register */
+#define		AT91_SDRAMC_LPCB		(3 << 0)	/* Low-power Configurations */
+#define			AT91_SDRAMC_LPCB_DISABLE		0
+#define			AT91_SDRAMC_LPCB_SELF_REFRESH		1
+#define			AT91_SDRAMC_LPCB_POWER_DOWN		2
+#define			AT91_SDRAMC_LPCB_DEEP_POWER_DOWN	3
+#define		AT91_SDRAMC_PASR		(7 << 4)	/* Partial Array Self Refresh */
+#define		AT91_SDRAMC_TCSR		(3 << 8)	/* Temperature Compensated Self Refresh */
+#define		AT91_SDRAMC_DS			(3 << 10)	/* Drive Strength */
+#define		AT91_SDRAMC_TIMEOUT		(3 << 12)	/* Time to define when Low Power Mode is enabled */
+#define			AT91_SDRAMC_TIMEOUT_0_CLK_CYCLES	(0 << 12)
+#define			AT91_SDRAMC_TIMEOUT_64_CLK_CYCLES	(1 << 12)
+#define			AT91_SDRAMC_TIMEOUT_128_CLK_CYCLES	(2 << 12)
+
+#define AT91_SDRAMC_IER		0x14	/* SDRAM Controller Interrupt Enable Register */
+#define AT91_SDRAMC_IDR		0x18	/* SDRAM Controller Interrupt Disable Register */
+#define AT91_SDRAMC_IMR		0x1C	/* SDRAM Controller Interrupt Mask Register */
+#define AT91_SDRAMC_ISR		0x20	/* SDRAM Controller Interrupt Status Register */
+#define		AT91_SDRAMC_RES		(1 << 0)		/* Refresh Error Status */
+
+#define AT91_SDRAMC_MDR		0x24	/* SDRAM Memory Device Register */
+#define		AT91_SDRAMC_MD		(3 << 0)		/* Memory Device Type */
+#define			AT91_SDRAMC_MD_SDRAM		0
+#define			AT91_SDRAMC_MD_LOW_POWER_SDRAM	1
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From aa1b6fbcbeaca21038db3e7a98d739786ae93511 Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 12 Nov 2014 05:25:31 +0100
Subject: crypto: doc - RNG API documentation

The API function calls exported by the kernel crypto API for RNGs to
be used by consumers are documented.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/rng.h | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 80 insertions(+)

(limited to 'include')

diff --git a/include/crypto/rng.h b/include/crypto/rng.h
index c93f9b91792..a16fb10142b 100644
--- a/include/crypto/rng.h
+++ b/include/crypto/rng.h
@@ -20,11 +20,38 @@ extern struct crypto_rng *crypto_default_rng;
 int crypto_get_default_rng(void);
 void crypto_put_default_rng(void);
 
+/**
+ * DOC: Random number generator API
+ *
+ * The random number generator API is used with the ciphers of type
+ * CRYPTO_ALG_TYPE_RNG (listed as type "rng" in /proc/crypto)
+ */
+
 static inline struct crypto_rng *__crypto_rng_cast(struct crypto_tfm *tfm)
 {
 	return (struct crypto_rng *)tfm;
 }
 
+/**
+ * crypto_alloc_rng() -- allocate RNG handle
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	      message digest cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Allocate a cipher handle for a random number generator. The returned struct
+ * crypto_rng is the cipher handle that is required for any subsequent
+ * API invocation for that random number generator.
+ *
+ * For all random number generators, this call creates a new private copy of
+ * the random number generator that does not share a state with other
+ * instances. The only exception is the "krng" random number generator which
+ * is a kernel crypto API use case for the get_random_bytes() function of the
+ * /dev/random driver.
+ *
+ * Return: allocated cipher handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
 static inline struct crypto_rng *crypto_alloc_rng(const char *alg_name,
 						  u32 type, u32 mask)
 {
@@ -40,6 +67,14 @@ static inline struct crypto_tfm *crypto_rng_tfm(struct crypto_rng *tfm)
 	return &tfm->base;
 }
 
+/**
+ * crypto_rng_alg - obtain name of RNG
+ * @tfm: cipher handle
+ *
+ * Return the generic name (cra_name) of the initialized random number generator
+ *
+ * Return: generic name string
+ */
 static inline struct rng_alg *crypto_rng_alg(struct crypto_rng *tfm)
 {
 	return &crypto_rng_tfm(tfm)->__crt_alg->cra_rng;
@@ -50,23 +85,68 @@ static inline struct rng_tfm *crypto_rng_crt(struct crypto_rng *tfm)
 	return &crypto_rng_tfm(tfm)->crt_rng;
 }
 
+/**
+ * crypto_free_rng() - zeroize and free RNG handle
+ * @tfm: cipher handle to be freed
+ */
 static inline void crypto_free_rng(struct crypto_rng *tfm)
 {
 	crypto_free_tfm(crypto_rng_tfm(tfm));
 }
 
+/**
+ * crypto_rng_get_bytes() - get random number
+ * @tfm: cipher handle
+ * @rdata: output buffer holding the random numbers
+ * @dlen: length of the output buffer
+ *
+ * This function fills the caller-allocated buffer with random numbers using the
+ * random number generator referenced by the cipher handle.
+ *
+ * Return: > 0 function was successful and returns the number of generated
+ *	   bytes; < 0 if an error occurred
+ */
 static inline int crypto_rng_get_bytes(struct crypto_rng *tfm,
 				       u8 *rdata, unsigned int dlen)
 {
 	return crypto_rng_crt(tfm)->rng_gen_random(tfm, rdata, dlen);
 }
 
+/**
+ * crypto_rng_reset() - re-initialize the RNG
+ * @tfm: cipher handle
+ * @seed: seed input data
+ * @slen: length of the seed input data
+ *
+ * The reset function completely re-initializes the random number generator
+ * referenced by the cipher handle by clearing the current state. The new state
+ * is initialized with the caller provided seed or automatically, depending
+ * on the random number generator type (the ANSI X9.31 RNG requires
+ * caller-provided seed, the SP800-90A DRBGs perform an automatic seeding).
+ * The seed is provided as a parameter to this function call. The provided seed
+ * should have the length of the seed size defined for the random number
+ * generator as defined by crypto_rng_seedsize.
+ *
+ * Return: 0 if the setting of the key was successful; < 0 if an error occurred
+ */
 static inline int crypto_rng_reset(struct crypto_rng *tfm,
 				   u8 *seed, unsigned int slen)
 {
 	return crypto_rng_crt(tfm)->rng_reset(tfm, seed, slen);
 }
 
+/**
+ * crypto_rng_seedsize() - obtain seed size of RNG
+ * @tfm: cipher handle
+ *
+ * The function returns the seed size for the random number generator
+ * referenced by the cipher handle. This value may be zero if the random
+ * number generator does not implement or require a reseeding. For example,
+ * the SP800-90A DRBGs implement an automated reseeding after reaching a
+ * pre-defined threshold.
+ *
+ * Return: seed size for the random number generator
+ */
 static inline int crypto_rng_seedsize(struct crypto_rng *tfm)
 {
 	return crypto_rng_alg(tfm)->seedsize;
-- 
cgit v1.2.3-70-g09d2


From 5d8c723f61f2e6dacbd02d80a516115993c4f292 Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 12 Nov 2014 05:26:03 +0100
Subject: crypto: doc - hash data structures

The hash data structures needed to be filled in by cipher developers are
documented.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/hash.h | 95 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 95 insertions(+)

(limited to 'include')

diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 74b13ec1ebd..bf458fc272a 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -17,6 +17,28 @@
 
 struct crypto_ahash;
 
+/**
+ * DOC: Message Digest Algorithm Definitions
+ *
+ * These data structures define modular message digest algorithm
+ * implementations, managed via crypto_register_ahash(),
+ * crypto_register_shash(), crypto_unregister_ahash() and
+ * crypto_unregister_shash().
+ */
+
+/**
+ * struct hash_alg_common - define properties of message digest
+ * @digestsize: Size of the result of the transformation. A buffer of this size
+ *	        must be available to the @final and @finup calls, so they can
+ *	        store the resulting hash into it. For various predefined sizes,
+ *	        search include/crypto/ using
+ *	        git grep _DIGEST_SIZE include/crypto.
+ * @statesize: Size of the block for partial state of the transformation. A
+ *	       buffer of this size must be passed to the @export function as it
+ *	       will save the partial state of the transformation into it. On the
+ *	       other side, the @import function will load the state from a
+ *	       buffer of this size as well.
+ */
 struct hash_alg_common {
 	unsigned int digestsize;
 	unsigned int statesize;
@@ -37,6 +59,62 @@ struct ahash_request {
 	void *__ctx[] CRYPTO_MINALIGN_ATTR;
 };
 
+/**
+ * struct ahash_alg - asynchronous message digest definition
+ * @init: Initialize the transformation context. Intended only to initialize the
+ *	  state of the HASH transformation at the begining. This shall fill in
+ *	  the internal structures used during the entire duration of the whole
+ *	  transformation. No data processing happens at this point.
+ * @update: Push a chunk of data into the driver for transformation. This
+ *	   function actually pushes blocks of data from upper layers into the
+ *	   driver, which then passes those to the hardware as seen fit. This
+ *	   function must not finalize the HASH transformation by calculating the
+ *	   final message digest as this only adds more data into the
+ *	   transformation. This function shall not modify the transformation
+ *	   context, as this function may be called in parallel with the same
+ *	   transformation object. Data processing can happen synchronously
+ *	   [SHASH] or asynchronously [AHASH] at this point.
+ * @final: Retrieve result from the driver. This function finalizes the
+ *	   transformation and retrieves the resulting hash from the driver and
+ *	   pushes it back to upper layers. No data processing happens at this
+ *	   point.
+ * @finup: Combination of @update and @final. This function is effectively a
+ *	   combination of @update and @final calls issued in sequence. As some
+ *	   hardware cannot do @update and @final separately, this callback was
+ *	   added to allow such hardware to be used at least by IPsec. Data
+ *	   processing can happen synchronously [SHASH] or asynchronously [AHASH]
+ *	   at this point.
+ * @digest: Combination of @init and @update and @final. This function
+ *	    effectively behaves as the entire chain of operations, @init,
+ *	    @update and @final issued in sequence. Just like @finup, this was
+ *	    added for hardware which cannot do even the @finup, but can only do
+ *	    the whole transformation in one run. Data processing can happen
+ *	    synchronously [SHASH] or asynchronously [AHASH] at this point.
+ * @setkey: Set optional key used by the hashing algorithm. Intended to push
+ *	    optional key used by the hashing algorithm from upper layers into
+ *	    the driver. This function can store the key in the transformation
+ *	    context or can outright program it into the hardware. In the former
+ *	    case, one must be careful to program the key into the hardware at
+ *	    appropriate time and one must be careful that .setkey() can be
+ *	    called multiple times during the existence of the transformation
+ *	    object. Not  all hashing algorithms do implement this function as it
+ *	    is only needed for keyed message digests. SHAx/MDx/CRCx do NOT
+ *	    implement this function. HMAC(MDx)/HMAC(SHAx)/CMAC(AES) do implement
+ *	    this function. This function must be called before any other of the
+ *	    @init, @update, @final, @finup, @digest is called. No data
+ *	    processing happens at this point.
+ * @export: Export partial state of the transformation. This function dumps the
+ *	    entire state of the ongoing transformation into a provided block of
+ *	    data so it can be @import 'ed back later on. This is useful in case
+ *	    you want to save partial result of the transformation after
+ *	    processing certain amount of data and reload this partial result
+ *	    multiple times later on for multiple re-use. No data processing
+ *	    happens at this point.
+ * @import: Import partial state of the transformation. This function loads the
+ *	    entire state of the ongoing transformation from a provided block of
+ *	    data so the transformation can continue from this point onward. No
+ *	    data processing happens at this point.
+ */
 struct ahash_alg {
 	int (*init)(struct ahash_request *req);
 	int (*update)(struct ahash_request *req);
@@ -63,6 +141,23 @@ struct shash_desc {
 		crypto_shash_descsize(ctx)] CRYPTO_MINALIGN_ATTR; \
 	struct shash_desc *shash = (struct shash_desc *)__##shash##_desc
 
+/**
+ * struct shash_alg - synchronous message digest definition
+ * @init: see struct ahash_alg
+ * @update: see struct ahash_alg
+ * @final: see struct ahash_alg
+ * @finup: see struct ahash_alg
+ * @digest: see struct ahash_alg
+ * @export: see struct ahash_alg
+ * @import: see struct ahash_alg
+ * @setkey: see struct ahash_alg
+ * @digestsize: see struct ahash_alg
+ * @statesize: see struct ahash_alg
+ * @dedcsize: Size of the operational state for the message digest. This state
+ * 	      size is the memory size that needs to be allocated for
+ *	      shash_desc.__ctx
+ * @base: internally used
+ */
 struct shash_alg {
 	int (*init)(struct shash_desc *desc);
 	int (*update)(struct shash_desc *desc, const u8 *data,
-- 
cgit v1.2.3-70-g09d2


From 90240ffb127729713cd7d9c1b5c1c0c9451681cd Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 12 Nov 2014 05:26:41 +0100
Subject: crypto: doc - AHASH API documentation

The API function calls exported by the kernel crypto API for AHASHes
to be used by consumers are documented.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/hash.h | 228 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 228 insertions(+)

(limited to 'include')

diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index bf458fc272a..b2c193acc1a 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -202,11 +202,35 @@ struct crypto_shash {
 	struct crypto_tfm base;
 };
 
+/**
+ * DOC: Asynchronous Message Digest API
+ *
+ * The asynchronous message digest API is used with the ciphers of type
+ * CRYPTO_ALG_TYPE_AHASH (listed as type "ahash" in /proc/crypto)
+ *
+ * The asynchronous cipher operation discussion provided for the
+ * CRYPTO_ALG_TYPE_ABLKCIPHER API applies here as well.
+ */
+
 static inline struct crypto_ahash *__crypto_ahash_cast(struct crypto_tfm *tfm)
 {
 	return container_of(tfm, struct crypto_ahash, base);
 }
 
+/**
+ * crypto_alloc_ahash() - allocate ahash cipher handle
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	      ahash cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Allocate a cipher handle for an ahash. The returned struct
+ * crypto_ahash is the cipher handle that is required for any subsequent
+ * API invocation for that ahash.
+ *
+ * Return: allocated cipher handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
 struct crypto_ahash *crypto_alloc_ahash(const char *alg_name, u32 type,
 					u32 mask);
 
@@ -215,6 +239,10 @@ static inline struct crypto_tfm *crypto_ahash_tfm(struct crypto_ahash *tfm)
 	return &tfm->base;
 }
 
+/**
+ * crypto_free_ahash() - zeroize and free the ahash handle
+ * @tfm: cipher handle to be freed
+ */
 static inline void crypto_free_ahash(struct crypto_ahash *tfm)
 {
 	crypto_destroy_tfm(tfm, crypto_ahash_tfm(tfm));
@@ -238,6 +266,16 @@ static inline struct hash_alg_common *crypto_hash_alg_common(
 	return __crypto_hash_alg_common(crypto_ahash_tfm(tfm)->__crt_alg);
 }
 
+/**
+ * crypto_ahash_digestsize() - obtain message digest size
+ * @tfm: cipher handle
+ *
+ * The size for the message digest created by the message digest cipher
+ * referenced with the cipher handle is returned.
+ *
+ *
+ * Return: message digest size of cipher
+ */
 static inline unsigned int crypto_ahash_digestsize(struct crypto_ahash *tfm)
 {
 	return crypto_hash_alg_common(tfm)->digestsize;
@@ -263,12 +301,32 @@ static inline void crypto_ahash_clear_flags(struct crypto_ahash *tfm, u32 flags)
 	crypto_tfm_clear_flags(crypto_ahash_tfm(tfm), flags);
 }
 
+/**
+ * crypto_ahash_reqtfm() - obtain cipher handle from request
+ * @req: asynchronous request handle that contains the reference to the ahash
+ *	 cipher handle
+ *
+ * Return the ahash cipher handle that is registered with the asynchronous
+ * request handle ahash_request.
+ *
+ * Return: ahash cipher handle
+ */
 static inline struct crypto_ahash *crypto_ahash_reqtfm(
 	struct ahash_request *req)
 {
 	return __crypto_ahash_cast(req->base.tfm);
 }
 
+/**
+ * crypto_ahash_reqsize() - obtain size of the request data structure
+ * @tfm: cipher handle
+ *
+ * Return the size of the ahash state size. With the crypto_ahash_export
+ * function, the caller can export the state into a buffer whose size is
+ * defined with this function.
+ *
+ * Return: size of the ahash state
+ */
 static inline unsigned int crypto_ahash_reqsize(struct crypto_ahash *tfm)
 {
 	return tfm->reqsize;
@@ -279,38 +337,166 @@ static inline void *ahash_request_ctx(struct ahash_request *req)
 	return req->__ctx;
 }
 
+/**
+ * crypto_ahash_setkey - set key for cipher handle
+ * @tfm: cipher handle
+ * @key: buffer holding the key
+ * @keylen: length of the key in bytes
+ *
+ * The caller provided key is set for the ahash cipher. The cipher
+ * handle must point to a keyed hash in order for this function to succeed.
+ *
+ * Return: 0 if the setting of the key was successful; < 0 if an error occurred
+ */
 int crypto_ahash_setkey(struct crypto_ahash *tfm, const u8 *key,
 			unsigned int keylen);
+
+/**
+ * crypto_ahash_finup() - update and finalize message digest
+ * @req: reference to the ahash_request handle that holds all information
+ *	 needed to perform the cipher operation
+ *
+ * This function is a "short-hand" for the function calls of
+ * crypto_ahash_update and crypto_shash_final. The parameters have the same
+ * meaning as discussed for those separate functions.
+ *
+ * Return: 0 if the message digest creation was successful; < 0 if an error
+ *	   occurred
+ */
 int crypto_ahash_finup(struct ahash_request *req);
+
+/**
+ * crypto_ahash_final() - calculate message digest
+ * @req: reference to the ahash_request handle that holds all information
+ *	 needed to perform the cipher operation
+ *
+ * Finalize the message digest operation and create the message digest
+ * based on all data added to the cipher handle. The message digest is placed
+ * into the output buffer registered with the ahash_request handle.
+ *
+ * Return: 0 if the message digest creation was successful; < 0 if an error
+ *	   occurred
+ */
 int crypto_ahash_final(struct ahash_request *req);
+
+/**
+ * crypto_ahash_digest() - calculate message digest for a buffer
+ * @req: reference to the ahash_request handle that holds all information
+ *	 needed to perform the cipher operation
+ *
+ * This function is a "short-hand" for the function calls of crypto_ahash_init,
+ * crypto_ahash_update and crypto_ahash_final. The parameters have the same
+ * meaning as discussed for those separate three functions.
+ *
+ * Return: 0 if the message digest creation was successful; < 0 if an error
+ *	   occurred
+ */
 int crypto_ahash_digest(struct ahash_request *req);
 
+/**
+ * crypto_ahash_export() - extract current message digest state
+ * @req: reference to the ahash_request handle whose state is exported
+ * @out: output buffer of sufficient size that can hold the hash state
+ *
+ * This function exports the hash state of the ahash_request handle into the
+ * caller-allocated output buffer out which must have sufficient size (e.g. by
+ * calling crypto_ahash_reqsize).
+ *
+ * Return: 0 if the export was successful; < 0 if an error occurred
+ */
 static inline int crypto_ahash_export(struct ahash_request *req, void *out)
 {
 	return crypto_ahash_reqtfm(req)->export(req, out);
 }
 
+/**
+ * crypto_ahash_import() - import message digest state
+ * @req: reference to ahash_request handle the state is imported into
+ * @in: buffer holding the state
+ *
+ * This function imports the hash state into the ahash_request handle from the
+ * input buffer. That buffer should have been generated with the
+ * crypto_ahash_export function.
+ *
+ * Return: 0 if the import was successful; < 0 if an error occurred
+ */
 static inline int crypto_ahash_import(struct ahash_request *req, const void *in)
 {
 	return crypto_ahash_reqtfm(req)->import(req, in);
 }
 
+/**
+ * crypto_ahash_init() - (re)initialize message digest handle
+ * @req: ahash_request handle that already is initialized with all necessary
+ *	 data using the ahash_request_* API functions
+ *
+ * The call (re-)initializes the message digest referenced by the ahash_request
+ * handle. Any potentially existing state created by previous operations is
+ * discarded.
+ *
+ * Return: 0 if the message digest initialization was successful; < 0 if an
+ *	   error occurred
+ */
 static inline int crypto_ahash_init(struct ahash_request *req)
 {
 	return crypto_ahash_reqtfm(req)->init(req);
 }
 
+/**
+ * crypto_ahash_update() - add data to message digest for processing
+ * @req: ahash_request handle that was previously initialized with the
+ *	 crypto_ahash_init call.
+ *
+ * Updates the message digest state of the &ahash_request handle. The input data
+ * is pointed to by the scatter/gather list registered in the &ahash_request
+ * handle
+ *
+ * Return: 0 if the message digest update was successful; < 0 if an error
+ *	   occurred
+ */
 static inline int crypto_ahash_update(struct ahash_request *req)
 {
 	return crypto_ahash_reqtfm(req)->update(req);
 }
 
+/**
+ * DOC: Asynchronous Hash Request Handle
+ *
+ * The &ahash_request data structure contains all pointers to data
+ * required for the asynchronous cipher operation. This includes the cipher
+ * handle (which can be used by multiple &ahash_request instances), pointer
+ * to plaintext and the message digest output buffer, asynchronous callback
+ * function, etc. It acts as a handle to the ahash_request_* API calls in a
+ * similar way as ahash handle to the crypto_ahash_* API calls.
+ */
+
+/**
+ * ahash_request_set_tfm() - update cipher handle reference in request
+ * @req: request handle to be modified
+ * @tfm: cipher handle that shall be added to the request handle
+ *
+ * Allow the caller to replace the existing ahash handle in the request
+ * data structure with a different one.
+ */
 static inline void ahash_request_set_tfm(struct ahash_request *req,
 					 struct crypto_ahash *tfm)
 {
 	req->base.tfm = crypto_ahash_tfm(tfm);
 }
 
+/**
+ * ahash_request_alloc() - allocate request data structure
+ * @tfm: cipher handle to be registered with the request
+ * @gfp: memory allocation flag that is handed to kmalloc by the API call.
+ *
+ * Allocate the request data structure that must be used with the ahash
+ * message digest API calls. During
+ * the allocation, the provided ahash handle
+ * is registered in the request data structure.
+ *
+ * Return: allocated request handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
 static inline struct ahash_request *ahash_request_alloc(
 	struct crypto_ahash *tfm, gfp_t gfp)
 {
@@ -325,6 +511,10 @@ static inline struct ahash_request *ahash_request_alloc(
 	return req;
 }
 
+/**
+ * ahash_request_free() - zeroize and free the request data structure
+ * @req: request data structure cipher handle to be freed
+ */
 static inline void ahash_request_free(struct ahash_request *req)
 {
 	kzfree(req);
@@ -336,6 +526,31 @@ static inline struct ahash_request *ahash_request_cast(
 	return container_of(req, struct ahash_request, base);
 }
 
+/**
+ * ahash_request_set_callback() - set asynchronous callback function
+ * @req: request handle
+ * @flags: specify zero or an ORing of the flags
+ *	   CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and
+ *	   increase the wait queue beyond the initial maximum size;
+ *	   CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep
+ * @compl: callback function pointer to be registered with the request handle
+ * @data: The data pointer refers to memory that is not used by the kernel
+ *	  crypto API, but provided to the callback function for it to use. Here,
+ *	  the caller can provide a reference to memory the callback function can
+ *	  operate on. As the callback function is invoked asynchronously to the
+ *	  related functionality, it may need to access data structures of the
+ *	  related functionality which can be referenced using this pointer. The
+ *	  callback function can access the memory via the "data" field in the
+ *	  &crypto_async_request data structure provided to the callback function.
+ *
+ * This function allows setting the callback function that is triggered once
+ * the cipher operation completes.
+ *
+ * The callback function is registered with the &ahash_request handle and
+ * must comply with the following template
+ *
+ *	void callback_function(struct crypto_async_request *req, int error)
+ */
 static inline void ahash_request_set_callback(struct ahash_request *req,
 					      u32 flags,
 					      crypto_completion_t compl,
@@ -346,6 +561,19 @@ static inline void ahash_request_set_callback(struct ahash_request *req,
 	req->base.flags = flags;
 }
 
+/**
+ * ahash_request_set_crypt() - set data buffers
+ * @req: ahash_request handle to be updated
+ * @src: source scatter/gather list
+ * @result: buffer that is filled with the message digest -- the caller must
+ *	    ensure that the buffer has sufficient space by, for example, calling
+ *	    crypto_ahash_digestsize()
+ * @nbytes: number of bytes to process from the source scatter/gather list
+ *
+ * By using this call, the caller references the source scatter/gather list.
+ * The source scatter/gather list points to the data the message digest is to
+ * be calculated for.
+ */
 static inline void ahash_request_set_crypt(struct ahash_request *req,
 					   struct scatterlist *src, u8 *result,
 					   unsigned int nbytes)
-- 
cgit v1.2.3-70-g09d2


From 968ab291078006de022b2245702a050ccdc32cd3 Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 12 Nov 2014 05:27:16 +0100
Subject: crypto: doc - SHASH API documentation

The API function calls exported by the kernel crypto API for SHASHes
to be used by consumers are documented.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/hash.h | 164 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 164 insertions(+)

(limited to 'include')

diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index b2c193acc1a..3d66e8bd093 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -583,6 +583,33 @@ static inline void ahash_request_set_crypt(struct ahash_request *req,
 	req->result = result;
 }
 
+/**
+ * DOC: Synchronous Message Digest API
+ *
+ * The synchronous message digest API is used with the ciphers of type
+ * CRYPTO_ALG_TYPE_SHASH (listed as type "shash" in /proc/crypto)
+ *
+ * The message digest API is able to maintain state information for the
+ * caller.
+ *
+ * The synchronous message digest API can store user-related context in in its
+ * shash_desc request data structure.
+ */
+
+/**
+ * crypto_alloc_shash() - allocate message digest handle
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	      message digest cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Allocate a cipher handle for a message digest. The returned &struct
+ * crypto_shash is the cipher handle that is required for any subsequent
+ * API invocation for that message digest.
+ *
+ * Return: allocated cipher handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
 struct crypto_shash *crypto_alloc_shash(const char *alg_name, u32 type,
 					u32 mask);
 
@@ -591,6 +618,10 @@ static inline struct crypto_tfm *crypto_shash_tfm(struct crypto_shash *tfm)
 	return &tfm->base;
 }
 
+/**
+ * crypto_free_shash() - zeroize and free the message digest handle
+ * @tfm: cipher handle to be freed
+ */
 static inline void crypto_free_shash(struct crypto_shash *tfm)
 {
 	crypto_destroy_tfm(tfm, crypto_shash_tfm(tfm));
@@ -602,6 +633,15 @@ static inline unsigned int crypto_shash_alignmask(
 	return crypto_tfm_alg_alignmask(crypto_shash_tfm(tfm));
 }
 
+/**
+ * crypto_shash_blocksize() - obtain block size for cipher
+ * @tfm: cipher handle
+ *
+ * The block size for the message digest cipher referenced with the cipher
+ * handle is returned.
+ *
+ * Return: block size of cipher
+ */
 static inline unsigned int crypto_shash_blocksize(struct crypto_shash *tfm)
 {
 	return crypto_tfm_alg_blocksize(crypto_shash_tfm(tfm));
@@ -617,6 +657,15 @@ static inline struct shash_alg *crypto_shash_alg(struct crypto_shash *tfm)
 	return __crypto_shash_alg(crypto_shash_tfm(tfm)->__crt_alg);
 }
 
+/**
+ * crypto_shash_digestsize() - obtain message digest size
+ * @tfm: cipher handle
+ *
+ * The size for the message digest created by the message digest cipher
+ * referenced with the cipher handle is returned.
+ *
+ * Return: digest size of cipher
+ */
 static inline unsigned int crypto_shash_digestsize(struct crypto_shash *tfm)
 {
 	return crypto_shash_alg(tfm)->digestsize;
@@ -642,6 +691,21 @@ static inline void crypto_shash_clear_flags(struct crypto_shash *tfm, u32 flags)
 	crypto_tfm_clear_flags(crypto_shash_tfm(tfm), flags);
 }
 
+/**
+ * crypto_shash_descsize() - obtain the operational state size
+ * @tfm: cipher handle
+ *
+ * The size of the operational state the cipher needs during operation is
+ * returned for the hash referenced with the cipher handle. This size is
+ * required to calculate the memory requirements to allow the caller allocating
+ * sufficient memory for operational state.
+ *
+ * The operational state is defined with struct shash_desc where the size of
+ * that data structure is to be calculated as
+ * sizeof(struct shash_desc) + crypto_shash_descsize(alg)
+ *
+ * Return: size of the operational state
+ */
 static inline unsigned int crypto_shash_descsize(struct crypto_shash *tfm)
 {
 	return tfm->descsize;
@@ -652,29 +716,129 @@ static inline void *shash_desc_ctx(struct shash_desc *desc)
 	return desc->__ctx;
 }
 
+/**
+ * crypto_shash_setkey() - set key for message digest
+ * @tfm: cipher handle
+ * @key: buffer holding the key
+ * @keylen: length of the key in bytes
+ *
+ * The caller provided key is set for the keyed message digest cipher. The
+ * cipher handle must point to a keyed message digest cipher in order for this
+ * function to succeed.
+ *
+ * Return: 0 if the setting of the key was successful; < 0 if an error occurred
+ */
 int crypto_shash_setkey(struct crypto_shash *tfm, const u8 *key,
 			unsigned int keylen);
+
+/**
+ * crypto_shash_digest() - calculate message digest for buffer
+ * @desc: see crypto_shash_final()
+ * @data: see crypto_shash_update()
+ * @len: see crypto_shash_update()
+ * @out: see crypto_shash_final()
+ *
+ * This function is a "short-hand" for the function calls of crypto_shash_init,
+ * crypto_shash_update and crypto_shash_final. The parameters have the same
+ * meaning as discussed for those separate three functions.
+ *
+ * Return: 0 if the message digest creation was successful; < 0 if an error
+ *	   occurred
+ */
 int crypto_shash_digest(struct shash_desc *desc, const u8 *data,
 			unsigned int len, u8 *out);
 
+/**
+ * crypto_shash_export() - extract operational state for message digest
+ * @desc: reference to the operational state handle whose state is exported
+ * @out: output buffer of sufficient size that can hold the hash state
+ *
+ * This function exports the hash state of the operational state handle into the
+ * caller-allocated output buffer out which must have sufficient size (e.g. by
+ * calling crypto_shash_descsize).
+ *
+ * Return: 0 if the export creation was successful; < 0 if an error occurred
+ */
 static inline int crypto_shash_export(struct shash_desc *desc, void *out)
 {
 	return crypto_shash_alg(desc->tfm)->export(desc, out);
 }
 
+/**
+ * crypto_shash_import() - import operational state
+ * @desc: reference to the operational state handle the state imported into
+ * @in: buffer holding the state
+ *
+ * This function imports the hash state into the operational state handle from
+ * the input buffer. That buffer should have been generated with the
+ * crypto_ahash_export function.
+ *
+ * Return: 0 if the import was successful; < 0 if an error occurred
+ */
 static inline int crypto_shash_import(struct shash_desc *desc, const void *in)
 {
 	return crypto_shash_alg(desc->tfm)->import(desc, in);
 }
 
+/**
+ * crypto_shash_init() - (re)initialize message digest
+ * @desc: operational state handle that is already filled
+ *
+ * The call (re-)initializes the message digest referenced by the
+ * operational state handle. Any potentially existing state created by
+ * previous operations is discarded.
+ *
+ * Return: 0 if the message digest initialization was successful; < 0 if an
+ *	   error occurred
+ */
 static inline int crypto_shash_init(struct shash_desc *desc)
 {
 	return crypto_shash_alg(desc->tfm)->init(desc);
 }
 
+/**
+ * crypto_shash_update() - add data to message digest for processing
+ * @desc: operational state handle that is already initialized
+ * @data: input data to be added to the message digest
+ * @len: length of the input data
+ *
+ * Updates the message digest state of the operational state handle.
+ *
+ * Return: 0 if the message digest update was successful; < 0 if an error
+ *	   occurred
+ */
 int crypto_shash_update(struct shash_desc *desc, const u8 *data,
 			unsigned int len);
+
+/**
+ * crypto_shash_final() - calculate message digest
+ * @desc: operational state handle that is already filled with data
+ * @out: output buffer filled with the message digest
+ *
+ * Finalize the message digest operation and create the message digest
+ * based on all data added to the cipher handle. The message digest is placed
+ * into the output buffer. The caller must ensure that the output buffer is
+ * large enough by using crypto_shash_digestsize.
+ *
+ * Return: 0 if the message digest creation was successful; < 0 if an error
+ *	   occurred
+ */
 int crypto_shash_final(struct shash_desc *desc, u8 *out);
+
+/**
+ * crypto_shash_finup() - calculate message digest of buffer
+ * @desc: see crypto_shash_final()
+ * @data: see crypto_shash_update()
+ * @len: see crypto_shash_update()
+ * @out: see crypto_shash_final()
+ *
+ * This function is a "short-hand" for the function calls of
+ * crypto_shash_update and crypto_shash_final. The parameters have the same
+ * meaning as discussed for those separate functions.
+ *
+ * Return: 0 if the message digest creation was successful; < 0 if an error
+ *	   occurred
+ */
 int crypto_shash_finup(struct shash_desc *desc, const u8 *data,
 		       unsigned int len, u8 *out);
 
-- 
cgit v1.2.3-70-g09d2


From 0d7f488f0305a9caffab0a18a882f9980f8bc936 Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 12 Nov 2014 05:27:49 +0100
Subject: crypto: doc - cipher data structures

The data structure of struct crypto_alg together with various other
data structures needed by cipher developers is documented wit all
parameters that can be set by a developer of a transformation. All
parameters that are internal to the crypto API are marked as such.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/crypto.h | 246 ++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 243 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index d45e949699e..752360e1e8f 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -127,6 +127,13 @@ struct skcipher_givcrypt_request;
 
 typedef void (*crypto_completion_t)(struct crypto_async_request *req, int err);
 
+/**
+ * DOC: Block Cipher Context Data Structures
+ *
+ * These data structures define the operating context for each block cipher
+ * type.
+ */
+
 struct crypto_async_request {
 	struct list_head list;
 	crypto_completion_t complete;
@@ -194,9 +201,63 @@ struct hash_desc {
 	u32 flags;
 };
 
-/*
- * Algorithms: modular crypto algorithm implementations, managed
- * via crypto_register_alg() and crypto_unregister_alg().
+/**
+ * DOC: Block Cipher Algorithm Definitions
+ *
+ * These data structures define modular crypto algorithm implementations,
+ * managed via crypto_register_alg() and crypto_unregister_alg().
+ */
+
+/**
+ * struct ablkcipher_alg - asynchronous block cipher definition
+ * @min_keysize: Minimum key size supported by the transformation. This is the
+ *		 smallest key length supported by this transformation algorithm.
+ *		 This must be set to one of the pre-defined values as this is
+ *		 not hardware specific. Possible values for this field can be
+ *		 found via git grep "_MIN_KEY_SIZE" include/crypto/
+ * @max_keysize: Maximum key size supported by the transformation. This is the
+ *		 largest key length supported by this transformation algorithm.
+ *		 This must be set to one of the pre-defined values as this is
+ *		 not hardware specific. Possible values for this field can be
+ *		 found via git grep "_MAX_KEY_SIZE" include/crypto/
+ * @setkey: Set key for the transformation. This function is used to either
+ *	    program a supplied key into the hardware or store the key in the
+ *	    transformation context for programming it later. Note that this
+ *	    function does modify the transformation context. This function can
+ *	    be called multiple times during the existence of the transformation
+ *	    object, so one must make sure the key is properly reprogrammed into
+ *	    the hardware. This function is also responsible for checking the key
+ *	    length for validity. In case a software fallback was put in place in
+ *	    the @cra_init call, this function might need to use the fallback if
+ *	    the algorithm doesn't support all of the key sizes.
+ * @encrypt: Encrypt a scatterlist of blocks. This function is used to encrypt
+ *	     the supplied scatterlist containing the blocks of data. The crypto
+ *	     API consumer is responsible for aligning the entries of the
+ *	     scatterlist properly and making sure the chunks are correctly
+ *	     sized. In case a software fallback was put in place in the
+ *	     @cra_init call, this function might need to use the fallback if
+ *	     the algorithm doesn't support all of the key sizes. In case the
+ *	     key was stored in transformation context, the key might need to be
+ *	     re-programmed into the hardware in this function. This function
+ *	     shall not modify the transformation context, as this function may
+ *	     be called in parallel with the same transformation object.
+ * @decrypt: Decrypt a single block. This is a reverse counterpart to @encrypt
+ *	     and the conditions are exactly the same.
+ * @givencrypt: Update the IV for encryption. With this function, a cipher
+ *	        implementation may provide the function on how to update the IV
+ *	        for encryption.
+ * @givdecrypt: Update the IV for decryption. This is the reverse of
+ *	        @givencrypt .
+ * @geniv: The transformation implementation may use an "IV generator" provided
+ *	   by the kernel crypto API. Several use cases have a predefined
+ *	   approach how IVs are to be updated. For such use cases, the kernel
+ *	   crypto API provides ready-to-use implementations that can be
+ *	   referenced with this variable.
+ * @ivsize: IV size applicable for transformation. The consumer must provide an
+ *	    IV of exactly that size to perform the encrypt or decrypt operation.
+ *
+ * All fields except @givencrypt , @givdecrypt , @geniv and @ivsize are
+ * mandatory and must be filled.
  */
 struct ablkcipher_alg {
 	int (*setkey)(struct crypto_ablkcipher *tfm, const u8 *key,
@@ -213,6 +274,32 @@ struct ablkcipher_alg {
 	unsigned int ivsize;
 };
 
+/**
+ * struct aead_alg - AEAD cipher definition
+ * @maxauthsize: Set the maximum authentication tag size supported by the
+ *		 transformation. A transformation may support smaller tag sizes.
+ *		 As the authentication tag is a message digest to ensure the
+ *		 integrity of the encrypted data, a consumer typically wants the
+ *		 largest authentication tag possible as defined by this
+ *		 variable.
+ * @setauthsize: Set authentication size for the AEAD transformation. This
+ *		 function is used to specify the consumer requested size of the
+ * 		 authentication tag to be either generated by the transformation
+ *		 during encryption or the size of the authentication tag to be
+ *		 supplied during the decryption operation. This function is also
+ *		 responsible for checking the authentication tag size for
+ *		 validity.
+ * @setkey: see struct ablkcipher_alg
+ * @encrypt: see struct ablkcipher_alg
+ * @decrypt: see struct ablkcipher_alg
+ * @givencrypt: see struct ablkcipher_alg
+ * @givdecrypt: see struct ablkcipher_alg
+ * @geniv: see struct ablkcipher_alg
+ * @ivsize: see struct ablkcipher_alg
+ *
+ * All fields except @givencrypt , @givdecrypt , @geniv and @ivsize are
+ * mandatory and must be filled.
+ */
 struct aead_alg {
 	int (*setkey)(struct crypto_aead *tfm, const u8 *key,
 	              unsigned int keylen);
@@ -228,6 +315,18 @@ struct aead_alg {
 	unsigned int maxauthsize;
 };
 
+/**
+ * struct blkcipher_alg - synchronous block cipher definition
+ * @min_keysize: see struct ablkcipher_alg
+ * @max_keysize: see struct ablkcipher_alg
+ * @setkey: see struct ablkcipher_alg
+ * @encrypt: see struct ablkcipher_alg
+ * @decrypt: see struct ablkcipher_alg
+ * @geniv: see struct ablkcipher_alg
+ * @ivsize: see struct ablkcipher_alg
+ *
+ * All fields except @geniv and @ivsize are mandatory and must be filled.
+ */
 struct blkcipher_alg {
 	int (*setkey)(struct crypto_tfm *tfm, const u8 *key,
 	              unsigned int keylen);
@@ -245,6 +344,53 @@ struct blkcipher_alg {
 	unsigned int ivsize;
 };
 
+/**
+ * struct cipher_alg - single-block symmetric ciphers definition
+ * @cia_min_keysize: Minimum key size supported by the transformation. This is
+ *		     the smallest key length supported by this transformation
+ *		     algorithm. This must be set to one of the pre-defined
+ *		     values as this is not hardware specific. Possible values
+ *		     for this field can be found via git grep "_MIN_KEY_SIZE"
+ *		     include/crypto/
+ * @cia_max_keysize: Maximum key size supported by the transformation. This is
+ *		    the largest key length supported by this transformation
+ *		    algorithm. This must be set to one of the pre-defined values
+ *		    as this is not hardware specific. Possible values for this
+ *		    field can be found via git grep "_MAX_KEY_SIZE"
+ *		    include/crypto/
+ * @cia_setkey: Set key for the transformation. This function is used to either
+ *	        program a supplied key into the hardware or store the key in the
+ *	        transformation context for programming it later. Note that this
+ *	        function does modify the transformation context. This function
+ *	        can be called multiple times during the existence of the
+ *	        transformation object, so one must make sure the key is properly
+ *	        reprogrammed into the hardware. This function is also
+ *	        responsible for checking the key length for validity.
+ * @cia_encrypt: Encrypt a single block. This function is used to encrypt a
+ *		 single block of data, which must be @cra_blocksize big. This
+ *		 always operates on a full @cra_blocksize and it is not possible
+ *		 to encrypt a block of smaller size. The supplied buffers must
+ *		 therefore also be at least of @cra_blocksize size. Both the
+ *		 input and output buffers are always aligned to @cra_alignmask.
+ *		 In case either of the input or output buffer supplied by user
+ *		 of the crypto API is not aligned to @cra_alignmask, the crypto
+ *		 API will re-align the buffers. The re-alignment means that a
+ *		 new buffer will be allocated, the data will be copied into the
+ *		 new buffer, then the processing will happen on the new buffer,
+ *		 then the data will be copied back into the original buffer and
+ *		 finally the new buffer will be freed. In case a software
+ *		 fallback was put in place in the @cra_init call, this function
+ *		 might need to use the fallback if the algorithm doesn't support
+ *		 all of the key sizes. In case the key was stored in
+ *		 transformation context, the key might need to be re-programmed
+ *		 into the hardware in this function. This function shall not
+ *		 modify the transformation context, as this function may be
+ *		 called in parallel with the same transformation object.
+ * @cia_decrypt: Decrypt a single block. This is a reverse counterpart to
+ *		 @cia_encrypt, and the conditions are exactly the same.
+ *
+ * All fields are mandatory and must be filled.
+ */
 struct cipher_alg {
 	unsigned int cia_min_keysize;
 	unsigned int cia_max_keysize;
@@ -261,6 +407,25 @@ struct compress_alg {
 			      unsigned int slen, u8 *dst, unsigned int *dlen);
 };
 
+/**
+ * struct rng_alg - random number generator definition
+ * @rng_make_random: The function defined by this variable obtains a random
+ *		     number. The random number generator transform must generate
+ *		     the random number out of the context provided with this
+ *		     call.
+ * @rng_reset: Reset of the random number generator by clearing the entire state.
+ *	       With the invocation of this function call, the random number
+ *             generator shall completely reinitialize its state. If the random
+ *	       number generator requires a seed for setting up a new state,
+ *	       the seed must be provided by the consumer while invoking this
+ *	       function. The required size of the seed is defined with
+ *	       @seedsize .
+ * @seedsize: The seed size required for a random number generator
+ *	      initialization defined with this variable. Some random number
+ *	      generators like the SP800-90A DRBG does not require a seed as the
+ *	      seeding is implemented internally without the need of support by
+ *	      the consumer. In this case, the seed size is set to zero.
+ */
 struct rng_alg {
 	int (*rng_make_random)(struct crypto_rng *tfm, u8 *rdata,
 			       unsigned int dlen);
@@ -277,6 +442,81 @@ struct rng_alg {
 #define cra_compress	cra_u.compress
 #define cra_rng		cra_u.rng
 
+/**
+ * struct crypto_alg - definition of a cryptograpic cipher algorithm
+ * @cra_flags: Flags describing this transformation. See include/linux/crypto.h
+ *	       CRYPTO_ALG_* flags for the flags which go in here. Those are
+ *	       used for fine-tuning the description of the transformation
+ *	       algorithm.
+ * @cra_blocksize: Minimum block size of this transformation. The size in bytes
+ *		   of the smallest possible unit which can be transformed with
+ *		   this algorithm. The users must respect this value.
+ *		   In case of HASH transformation, it is possible for a smaller
+ *		   block than @cra_blocksize to be passed to the crypto API for
+ *		   transformation, in case of any other transformation type, an
+ * 		   error will be returned upon any attempt to transform smaller
+ *		   than @cra_blocksize chunks.
+ * @cra_ctxsize: Size of the operational context of the transformation. This
+ *		 value informs the kernel crypto API about the memory size
+ *		 needed to be allocated for the transformation context.
+ * @cra_alignmask: Alignment mask for the input and output data buffer. The data
+ *		   buffer containing the input data for the algorithm must be
+ *		   aligned to this alignment mask. The data buffer for the
+ *		   output data must be aligned to this alignment mask. Note that
+ *		   the Crypto API will do the re-alignment in software, but
+ *		   only under special conditions and there is a performance hit.
+ *		   The re-alignment happens at these occasions for different
+ *		   @cra_u types: cipher -- For both input data and output data
+ *		   buffer; ahash -- For output hash destination buf; shash --
+ *		   For output hash destination buf.
+ *		   This is needed on hardware which is flawed by design and
+ *		   cannot pick data from arbitrary addresses.
+ * @cra_priority: Priority of this transformation implementation. In case
+ *		  multiple transformations with same @cra_name are available to
+ *		  the Crypto API, the kernel will use the one with highest
+ *		  @cra_priority.
+ * @cra_name: Generic name (usable by multiple implementations) of the
+ *	      transformation algorithm. This is the name of the transformation
+ *	      itself. This field is used by the kernel when looking up the
+ *	      providers of particular transformation.
+ * @cra_driver_name: Unique name of the transformation provider. This is the
+ *		     name of the provider of the transformation. This can be any
+ *		     arbitrary value, but in the usual case, this contains the
+ *		     name of the chip or provider and the name of the
+ *		     transformation algorithm.
+ * @cra_type: Type of the cryptographic transformation. This is a pointer to
+ *	      struct crypto_type, which implements callbacks common for all
+ *	      trasnformation types. There are multiple options:
+ *	      &crypto_blkcipher_type, &crypto_ablkcipher_type,
+ *	      &crypto_ahash_type, &crypto_aead_type, &crypto_rng_type.
+ *	      This field might be empty. In that case, there are no common
+ *	      callbacks. This is the case for: cipher, compress, shash.
+ * @cra_u: Callbacks implementing the transformation. This is a union of
+ *	   multiple structures. Depending on the type of transformation selected
+ *	   by @cra_type and @cra_flags above, the associated structure must be
+ *	   filled with callbacks. This field might be empty. This is the case
+ *	   for ahash, shash.
+ * @cra_init: Initialize the cryptographic transformation object. This function
+ *	      is used to initialize the cryptographic transformation object.
+ *	      This function is called only once at the instantiation time, right
+ *	      after the transformation context was allocated. In case the
+ *	      cryptographic hardware has some special requirements which need to
+ *	      be handled by software, this function shall check for the precise
+ *	      requirement of the transformation and put any software fallbacks
+ *	      in place.
+ * @cra_exit: Deinitialize the cryptographic transformation object. This is a
+ *	      counterpart to @cra_init, used to remove various changes set in
+ *	      @cra_init.
+ * @cra_module: Owner of this transformation implementation. Set to THIS_MODULE
+ * @cra_list: internally used
+ * @cra_users: internally used
+ * @cra_refcnt: internally used
+ * @cra_destroy: internally used
+ *
+ * The struct crypto_alg describes a generic Crypto API algorithm and is common
+ * for all of the transformations. Any variable not documented here shall not
+ * be used by a cipher implementation as it is internal to the Crypto API.
+ */
 struct crypto_alg {
 	struct list_head cra_list;
 	struct list_head cra_users;
-- 
cgit v1.2.3-70-g09d2


From f13ec330a787c2653d4738be1ee887ead1fb3008 Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 12 Nov 2014 05:28:22 +0100
Subject: crypto: doc - ABLKCIPHER API documentation

The API function calls exported by the kernel crypto API for
asynchronous block ciphers to be used by consumers are documented.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/crypto.h | 206 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 206 insertions(+)

(limited to 'include')

diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 752360e1e8f..39c8fc6d331 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -821,6 +821,50 @@ static inline u32 crypto_skcipher_mask(u32 mask)
 	return mask;
 }
 
+/**
+ * DOC: Asynchronous Block Cipher API
+ *
+ * Asynchronous block cipher API is used with the ciphers of type
+ * CRYPTO_ALG_TYPE_ABLKCIPHER (listed as type "ablkcipher" in /proc/crypto).
+ *
+ * Asynchronous cipher operations imply that the function invocation for a
+ * cipher request returns immediately before the completion of the operation.
+ * The cipher request is scheduled as a separate kernel thread and therefore
+ * load-balanced on the different CPUs via the process scheduler. To allow
+ * the kernel crypto API to inform the caller about the completion of a cipher
+ * request, the caller must provide a callback function. That function is
+ * invoked with the cipher handle when the request completes.
+ *
+ * To support the asynchronous operation, additional information than just the
+ * cipher handle must be supplied to the kernel crypto API. That additional
+ * information is given by filling in the ablkcipher_request data structure.
+ *
+ * For the asynchronous block cipher API, the state is maintained with the tfm
+ * cipher handle. A single tfm can be used across multiple calls and in
+ * parallel. For asynchronous block cipher calls, context data supplied and
+ * only used by the caller can be referenced the request data structure in
+ * addition to the IV used for the cipher request. The maintenance of such
+ * state information would be important for a crypto driver implementer to
+ * have, because when calling the callback function upon completion of the
+ * cipher operation, that callback function may need some information about
+ * which operation just finished if it invoked multiple in parallel. This
+ * state information is unused by the kernel crypto API.
+ */
+
+/**
+ * crypto_alloc_ablkcipher() - allocate asynchronous block cipher handle
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	      ablkcipher cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Allocate a cipher handle for an ablkcipher. The returned struct
+ * crypto_ablkcipher is the cipher handle that is required for any subsequent
+ * API invocation for that ablkcipher.
+ *
+ * Return: allocated cipher handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
 struct crypto_ablkcipher *crypto_alloc_ablkcipher(const char *alg_name,
 						  u32 type, u32 mask);
 
@@ -830,11 +874,25 @@ static inline struct crypto_tfm *crypto_ablkcipher_tfm(
 	return &tfm->base;
 }
 
+/**
+ * crypto_free_ablkcipher() - zeroize and free cipher handle
+ * @tfm: cipher handle to be freed
+ */
 static inline void crypto_free_ablkcipher(struct crypto_ablkcipher *tfm)
 {
 	crypto_free_tfm(crypto_ablkcipher_tfm(tfm));
 }
 
+/**
+ * crypto_has_ablkcipher() - Search for the availability of an ablkcipher.
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	      ablkcipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Return: true when the ablkcipher is known to the kernel crypto API; false
+ *	   otherwise
+ */
 static inline int crypto_has_ablkcipher(const char *alg_name, u32 type,
 					u32 mask)
 {
@@ -848,12 +906,31 @@ static inline struct ablkcipher_tfm *crypto_ablkcipher_crt(
 	return &crypto_ablkcipher_tfm(tfm)->crt_ablkcipher;
 }
 
+/**
+ * crypto_ablkcipher_ivsize() - obtain IV size
+ * @tfm: cipher handle
+ *
+ * The size of the IV for the ablkcipher referenced by the cipher handle is
+ * returned. This IV size may be zero if the cipher does not need an IV.
+ *
+ * Return: IV size in bytes
+ */
 static inline unsigned int crypto_ablkcipher_ivsize(
 	struct crypto_ablkcipher *tfm)
 {
 	return crypto_ablkcipher_crt(tfm)->ivsize;
 }
 
+/**
+ * crypto_ablkcipher_blocksize() - obtain block size of cipher
+ * @tfm: cipher handle
+ *
+ * The block size for the ablkcipher referenced with the cipher handle is
+ * returned. The caller may use that information to allocate appropriate
+ * memory for the data returned by the encryption or decryption operation
+ *
+ * Return: block size of cipher
+ */
 static inline unsigned int crypto_ablkcipher_blocksize(
 	struct crypto_ablkcipher *tfm)
 {
@@ -883,6 +960,22 @@ static inline void crypto_ablkcipher_clear_flags(struct crypto_ablkcipher *tfm,
 	crypto_tfm_clear_flags(crypto_ablkcipher_tfm(tfm), flags);
 }
 
+/**
+ * crypto_ablkcipher_setkey() - set key for cipher
+ * @tfm: cipher handle
+ * @key: buffer holding the key
+ * @keylen: length of the key in bytes
+ *
+ * The caller provided key is set for the ablkcipher referenced by the cipher
+ * handle.
+ *
+ * Note, the key length determines the cipher type. Many block ciphers implement
+ * different cipher modes depending on the key size, such as AES-128 vs AES-192
+ * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128
+ * is performed.
+ *
+ * Return: 0 if the setting of the key was successful; < 0 if an error occurred
+ */
 static inline int crypto_ablkcipher_setkey(struct crypto_ablkcipher *tfm,
 					   const u8 *key, unsigned int keylen)
 {
@@ -891,12 +984,32 @@ static inline int crypto_ablkcipher_setkey(struct crypto_ablkcipher *tfm,
 	return crt->setkey(crt->base, key, keylen);
 }
 
+/**
+ * crypto_ablkcipher_reqtfm() - obtain cipher handle from request
+ * @req: ablkcipher_request out of which the cipher handle is to be obtained
+ *
+ * Return the crypto_ablkcipher handle when furnishing an ablkcipher_request
+ * data structure.
+ *
+ * Return: crypto_ablkcipher handle
+ */
 static inline struct crypto_ablkcipher *crypto_ablkcipher_reqtfm(
 	struct ablkcipher_request *req)
 {
 	return __crypto_ablkcipher_cast(req->base.tfm);
 }
 
+/**
+ * crypto_ablkcipher_encrypt() - encrypt plaintext
+ * @req: reference to the ablkcipher_request handle that holds all information
+ *	 needed to perform the cipher operation
+ *
+ * Encrypt plaintext data using the ablkcipher_request handle. That data
+ * structure and how it is filled with data is discussed with the
+ * ablkcipher_request_* functions.
+ *
+ * Return: 0 if the cipher operation was successful; < 0 if an error occurred
+ */
 static inline int crypto_ablkcipher_encrypt(struct ablkcipher_request *req)
 {
 	struct ablkcipher_tfm *crt =
@@ -904,6 +1017,17 @@ static inline int crypto_ablkcipher_encrypt(struct ablkcipher_request *req)
 	return crt->encrypt(req);
 }
 
+/**
+ * crypto_ablkcipher_decrypt() - decrypt ciphertext
+ * @req: reference to the ablkcipher_request handle that holds all information
+ *	 needed to perform the cipher operation
+ *
+ * Decrypt ciphertext data using the ablkcipher_request handle. That data
+ * structure and how it is filled with data is discussed with the
+ * ablkcipher_request_* functions.
+ *
+ * Return: 0 if the cipher operation was successful; < 0 if an error occurred
+ */
 static inline int crypto_ablkcipher_decrypt(struct ablkcipher_request *req)
 {
 	struct ablkcipher_tfm *crt =
@@ -911,12 +1035,37 @@ static inline int crypto_ablkcipher_decrypt(struct ablkcipher_request *req)
 	return crt->decrypt(req);
 }
 
+/**
+ * DOC: Asynchronous Cipher Request Handle
+ *
+ * The ablkcipher_request data structure contains all pointers to data
+ * required for the asynchronous cipher operation. This includes the cipher
+ * handle (which can be used by multiple ablkcipher_request instances), pointer
+ * to plaintext and ciphertext, asynchronous callback function, etc. It acts
+ * as a handle to the ablkcipher_request_* API calls in a similar way as
+ * ablkcipher handle to the crypto_ablkcipher_* API calls.
+ */
+
+/**
+ * crypto_ablkcipher_reqsize() - obtain size of the request data structure
+ * @tfm: cipher handle
+ *
+ * Return: number of bytes
+ */
 static inline unsigned int crypto_ablkcipher_reqsize(
 	struct crypto_ablkcipher *tfm)
 {
 	return crypto_ablkcipher_crt(tfm)->reqsize;
 }
 
+/**
+ * ablkcipher_request_set_tfm() - update cipher handle reference in request
+ * @req: request handle to be modified
+ * @tfm: cipher handle that shall be added to the request handle
+ *
+ * Allow the caller to replace the existing ablkcipher handle in the request
+ * data structure with a different one.
+ */
 static inline void ablkcipher_request_set_tfm(
 	struct ablkcipher_request *req, struct crypto_ablkcipher *tfm)
 {
@@ -929,6 +1078,18 @@ static inline struct ablkcipher_request *ablkcipher_request_cast(
 	return container_of(req, struct ablkcipher_request, base);
 }
 
+/**
+ * ablkcipher_request_alloc() - allocate request data structure
+ * @tfm: cipher handle to be registered with the request
+ * @gfp: memory allocation flag that is handed to kmalloc by the API call.
+ *
+ * Allocate the request data structure that must be used with the ablkcipher
+ * encrypt and decrypt API calls. During the allocation, the provided ablkcipher
+ * handle is registered in the request data structure.
+ *
+ * Return: allocated request handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
 static inline struct ablkcipher_request *ablkcipher_request_alloc(
 	struct crypto_ablkcipher *tfm, gfp_t gfp)
 {
@@ -943,11 +1104,40 @@ static inline struct ablkcipher_request *ablkcipher_request_alloc(
 	return req;
 }
 
+/**
+ * ablkcipher_request_free() - zeroize and free request data structure
+ * @req: request data structure cipher handle to be freed
+ */
 static inline void ablkcipher_request_free(struct ablkcipher_request *req)
 {
 	kzfree(req);
 }
 
+/**
+ * ablkcipher_request_set_callback() - set asynchronous callback function
+ * @req: request handle
+ * @flags: specify zero or an ORing of the flags
+ *         CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and
+ *	   increase the wait queue beyond the initial maximum size;
+ *	   CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep
+ * @compl: callback function pointer to be registered with the request handle
+ * @data: The data pointer refers to memory that is not used by the kernel
+ *	  crypto API, but provided to the callback function for it to use. Here,
+ *	  the caller can provide a reference to memory the callback function can
+ *	  operate on. As the callback function is invoked asynchronously to the
+ *	  related functionality, it may need to access data structures of the
+ *	  related functionality which can be referenced using this pointer. The
+ *	  callback function can access the memory via the "data" field in the
+ *	  crypto_async_request data structure provided to the callback function.
+ *
+ * This function allows setting the callback function that is triggered once the
+ * cipher operation completes.
+ *
+ * The callback function is registered with the ablkcipher_request handle and
+ * must comply with the following template:
+ *
+ *	void callback_function(struct crypto_async_request *req, int error)
+ */
 static inline void ablkcipher_request_set_callback(
 	struct ablkcipher_request *req,
 	u32 flags, crypto_completion_t compl, void *data)
@@ -957,6 +1147,22 @@ static inline void ablkcipher_request_set_callback(
 	req->base.flags = flags;
 }
 
+/**
+ * ablkcipher_request_set_crypt() - set data buffers
+ * @req: request handle
+ * @src: source scatter / gather list
+ * @dst: destination scatter / gather list
+ * @nbytes: number of bytes to process from @src
+ * @iv: IV for the cipher operation which must comply with the IV size defined
+ *      by crypto_ablkcipher_ivsize
+ *
+ * This function allows setting of the source data and destination data
+ * scatter / gather lists.
+ *
+ * For encryption, the source is treated as the plaintext and the
+ * destination is the ciphertext. For a decryption operation, the use is
+ * reversed: the source is the ciphertext and the destination is the plaintext.
+ */
 static inline void ablkcipher_request_set_crypt(
 	struct ablkcipher_request *req,
 	struct scatterlist *src, struct scatterlist *dst,
-- 
cgit v1.2.3-70-g09d2


From fced7b02623e3ccace714f8adceed735698a9c8b Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 12 Nov 2014 05:29:00 +0100
Subject: crypto: doc - AEAD API documentation

The API function calls exported by the kernel crypto API for AEAD
ciphers to be used by consumers are documented.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/crypto.h | 251 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 251 insertions(+)

(limited to 'include')

diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 39c8fc6d331..4704e71a31f 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -1174,11 +1174,55 @@ static inline void ablkcipher_request_set_crypt(
 	req->info = iv;
 }
 
+/**
+ * DOC: Authenticated Encryption With Associated Data (AEAD) Cipher API
+ *
+ * The AEAD cipher API is used with the ciphers of type CRYPTO_ALG_TYPE_AEAD
+ * (listed as type "aead" in /proc/crypto)
+ *
+ * The most prominent examples for this type of encryption is GCM and CCM.
+ * However, the kernel supports other types of AEAD ciphers which are defined
+ * with the following cipher string:
+ *
+ *	authenc(keyed message digest, block cipher)
+ *
+ * For example: authenc(hmac(sha256), cbc(aes))
+ *
+ * The example code provided for the asynchronous block cipher operation
+ * applies here as well. Naturally all *ablkcipher* symbols must be exchanged
+ * the *aead* pendants discussed in the following. In addtion, for the AEAD
+ * operation, the aead_request_set_assoc function must be used to set the
+ * pointer to the associated data memory location before performing the
+ * encryption or decryption operation. In case of an encryption, the associated
+ * data memory is filled during the encryption operation. For decryption, the
+ * associated data memory must contain data that is used to verify the integrity
+ * of the decrypted data. Another deviation from the asynchronous block cipher
+ * operation is that the caller should explicitly check for -EBADMSG of the
+ * crypto_aead_decrypt. That error indicates an authentication error, i.e.
+ * a breach in the integrity of the message. In essence, that -EBADMSG error
+ * code is the key bonus an AEAD cipher has over "standard" block chaining
+ * modes.
+ */
+
 static inline struct crypto_aead *__crypto_aead_cast(struct crypto_tfm *tfm)
 {
 	return (struct crypto_aead *)tfm;
 }
 
+/**
+ * crypto_alloc_aead() - allocate AEAD cipher handle
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	     AEAD cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Allocate a cipher handle for an AEAD. The returned struct
+ * crypto_aead is the cipher handle that is required for any subsequent
+ * API invocation for that AEAD.
+ *
+ * Return: allocated cipher handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
 struct crypto_aead *crypto_alloc_aead(const char *alg_name, u32 type, u32 mask);
 
 static inline struct crypto_tfm *crypto_aead_tfm(struct crypto_aead *tfm)
@@ -1186,6 +1230,10 @@ static inline struct crypto_tfm *crypto_aead_tfm(struct crypto_aead *tfm)
 	return &tfm->base;
 }
 
+/**
+ * crypto_free_aead() - zeroize and free aead handle
+ * @tfm: cipher handle to be freed
+ */
 static inline void crypto_free_aead(struct crypto_aead *tfm)
 {
 	crypto_free_tfm(crypto_aead_tfm(tfm));
@@ -1196,16 +1244,47 @@ static inline struct aead_tfm *crypto_aead_crt(struct crypto_aead *tfm)
 	return &crypto_aead_tfm(tfm)->crt_aead;
 }
 
+/**
+ * crypto_aead_ivsize() - obtain IV size
+ * @tfm: cipher handle
+ *
+ * The size of the IV for the aead referenced by the cipher handle is
+ * returned. This IV size may be zero if the cipher does not need an IV.
+ *
+ * Return: IV size in bytes
+ */
 static inline unsigned int crypto_aead_ivsize(struct crypto_aead *tfm)
 {
 	return crypto_aead_crt(tfm)->ivsize;
 }
 
+/**
+ * crypto_aead_authsize() - obtain maximum authentication data size
+ * @tfm: cipher handle
+ *
+ * The maximum size of the authentication data for the AEAD cipher referenced
+ * by the AEAD cipher handle is returned. The authentication data size may be
+ * zero if the cipher implements a hard-coded maximum.
+ *
+ * The authentication data may also be known as "tag value".
+ *
+ * Return: authentication data size / tag size in bytes
+ */
 static inline unsigned int crypto_aead_authsize(struct crypto_aead *tfm)
 {
 	return crypto_aead_crt(tfm)->authsize;
 }
 
+/**
+ * crypto_aead_blocksize() - obtain block size of cipher
+ * @tfm: cipher handle
+ *
+ * The block size for the AEAD referenced with the cipher handle is returned.
+ * The caller may use that information to allocate appropriate memory for the
+ * data returned by the encryption or decryption operation
+ *
+ * Return: block size of cipher
+ */
 static inline unsigned int crypto_aead_blocksize(struct crypto_aead *tfm)
 {
 	return crypto_tfm_alg_blocksize(crypto_aead_tfm(tfm));
@@ -1231,6 +1310,22 @@ static inline void crypto_aead_clear_flags(struct crypto_aead *tfm, u32 flags)
 	crypto_tfm_clear_flags(crypto_aead_tfm(tfm), flags);
 }
 
+/**
+ * crypto_aead_setkey() - set key for cipher
+ * @tfm: cipher handle
+ * @key: buffer holding the key
+ * @keylen: length of the key in bytes
+ *
+ * The caller provided key is set for the AEAD referenced by the cipher
+ * handle.
+ *
+ * Note, the key length determines the cipher type. Many block ciphers implement
+ * different cipher modes depending on the key size, such as AES-128 vs AES-192
+ * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128
+ * is performed.
+ *
+ * Return: 0 if the setting of the key was successful; < 0 if an error occurred
+ */
 static inline int crypto_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 				     unsigned int keylen)
 {
@@ -1239,6 +1334,16 @@ static inline int crypto_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 	return crt->setkey(crt->base, key, keylen);
 }
 
+/**
+ * crypto_aead_setauthsize() - set authentication data size
+ * @tfm: cipher handle
+ * @authsize: size of the authentication data / tag in bytes
+ *
+ * Set the authentication data size / tag size. AEAD requires an authentication
+ * tag (or MAC) in addition to the associated data.
+ *
+ * Return: 0 if the setting of the key was successful; < 0 if an error occurred
+ */
 int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize);
 
 static inline struct crypto_aead *crypto_aead_reqtfm(struct aead_request *req)
@@ -1246,27 +1351,105 @@ static inline struct crypto_aead *crypto_aead_reqtfm(struct aead_request *req)
 	return __crypto_aead_cast(req->base.tfm);
 }
 
+/**
+ * crypto_aead_encrypt() - encrypt plaintext
+ * @req: reference to the aead_request handle that holds all information
+ *	 needed to perform the cipher operation
+ *
+ * Encrypt plaintext data using the aead_request handle. That data structure
+ * and how it is filled with data is discussed with the aead_request_*
+ * functions.
+ *
+ * IMPORTANT NOTE The encryption operation creates the authentication data /
+ *		  tag. That data is concatenated with the created ciphertext.
+ *		  The ciphertext memory size is therefore the given number of
+ *		  block cipher blocks + the size defined by the
+ *		  crypto_aead_setauthsize invocation. The caller must ensure
+ *		  that sufficient memory is available for the ciphertext and
+ *		  the authentication tag.
+ *
+ * Return: 0 if the cipher operation was successful; < 0 if an error occurred
+ */
 static inline int crypto_aead_encrypt(struct aead_request *req)
 {
 	return crypto_aead_crt(crypto_aead_reqtfm(req))->encrypt(req);
 }
 
+/**
+ * crypto_aead_decrypt() - decrypt ciphertext
+ * @req: reference to the ablkcipher_request handle that holds all information
+ *	 needed to perform the cipher operation
+ *
+ * Decrypt ciphertext data using the aead_request handle. That data structure
+ * and how it is filled with data is discussed with the aead_request_*
+ * functions.
+ *
+ * IMPORTANT NOTE The caller must concatenate the ciphertext followed by the
+ *		  authentication data / tag. That authentication data / tag
+ *		  must have the size defined by the crypto_aead_setauthsize
+ *		  invocation.
+ *
+ *
+ * Return: 0 if the cipher operation was successful; -EBADMSG: The AEAD
+ *	   cipher operation performs the authentication of the data during the
+ *	   decryption operation. Therefore, the function returns this error if
+ *	   the authentication of the ciphertext was unsuccessful (i.e. the
+ *	   integrity of the ciphertext or the associated data was violated);
+ *	   < 0 if an error occurred.
+ */
 static inline int crypto_aead_decrypt(struct aead_request *req)
 {
 	return crypto_aead_crt(crypto_aead_reqtfm(req))->decrypt(req);
 }
 
+/**
+ * DOC: Asynchronous AEAD Request Handle
+ *
+ * The aead_request data structure contains all pointers to data required for
+ * the AEAD cipher operation. This includes the cipher handle (which can be
+ * used by multiple aead_request instances), pointer to plaintext and
+ * ciphertext, asynchronous callback function, etc. It acts as a handle to the
+ * aead_request_* API calls in a similar way as AEAD handle to the
+ * crypto_aead_* API calls.
+ */
+
+/**
+ * crypto_aead_reqsize() - obtain size of the request data structure
+ * @tfm: cipher handle
+ *
+ * Return: number of bytes
+ */
 static inline unsigned int crypto_aead_reqsize(struct crypto_aead *tfm)
 {
 	return crypto_aead_crt(tfm)->reqsize;
 }
 
+/**
+ * aead_request_set_tfm() - update cipher handle reference in request
+ * @req: request handle to be modified
+ * @tfm: cipher handle that shall be added to the request handle
+ *
+ * Allow the caller to replace the existing aead handle in the request
+ * data structure with a different one.
+ */
 static inline void aead_request_set_tfm(struct aead_request *req,
 					struct crypto_aead *tfm)
 {
 	req->base.tfm = crypto_aead_tfm(crypto_aead_crt(tfm)->base);
 }
 
+/**
+ * aead_request_alloc() - allocate request data structure
+ * @tfm: cipher handle to be registered with the request
+ * @gfp: memory allocation flag that is handed to kmalloc by the API call.
+ *
+ * Allocate the request data structure that must be used with the AEAD
+ * encrypt and decrypt API calls. During the allocation, the provided aead
+ * handle is registered in the request data structure.
+ *
+ * Return: allocated request handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
 static inline struct aead_request *aead_request_alloc(struct crypto_aead *tfm,
 						      gfp_t gfp)
 {
@@ -1280,11 +1463,40 @@ static inline struct aead_request *aead_request_alloc(struct crypto_aead *tfm,
 	return req;
 }
 
+/**
+ * aead_request_free() - zeroize and free request data structure
+ * @req: request data structure cipher handle to be freed
+ */
 static inline void aead_request_free(struct aead_request *req)
 {
 	kzfree(req);
 }
 
+/**
+ * aead_request_set_callback() - set asynchronous callback function
+ * @req: request handle
+ * @flags: specify zero or an ORing of the flags
+ *	   CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and
+ *	   increase the wait queue beyond the initial maximum size;
+ *	   CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep
+ * @compl: callback function pointer to be registered with the request handle
+ * @data: The data pointer refers to memory that is not used by the kernel
+ *	  crypto API, but provided to the callback function for it to use. Here,
+ *	  the caller can provide a reference to memory the callback function can
+ *	  operate on. As the callback function is invoked asynchronously to the
+ *	  related functionality, it may need to access data structures of the
+ *	  related functionality which can be referenced using this pointer. The
+ *	  callback function can access the memory via the "data" field in the
+ *	  crypto_async_request data structure provided to the callback function.
+ *
+ * Setting the callback function that is triggered once the cipher operation
+ * completes
+ *
+ * The callback function is registered with the aead_request handle and
+ * must comply with the following template:
+ *
+ *	void callback_function(struct crypto_async_request *req, int error)
+ */
 static inline void aead_request_set_callback(struct aead_request *req,
 					     u32 flags,
 					     crypto_completion_t compl,
@@ -1295,6 +1507,36 @@ static inline void aead_request_set_callback(struct aead_request *req,
 	req->base.flags = flags;
 }
 
+/**
+ * aead_request_set_crypt - set data buffers
+ * @req: request handle
+ * @src: source scatter / gather list
+ * @dst: destination scatter / gather list
+ * @cryptlen: number of bytes to process from @src
+ * @iv: IV for the cipher operation which must comply with the IV size defined
+ *      by crypto_aead_ivsize()
+ *
+ * Setting the source data and destination data scatter / gather lists.
+ *
+ * For encryption, the source is treated as the plaintext and the
+ * destination is the ciphertext. For a decryption operation, the use is
+ * reversed: the source is the ciphertext and the destination is the plaintext.
+ *
+ * IMPORTANT NOTE AEAD requires an authentication tag (MAC). For decryption,
+ *		  the caller must concatenate the ciphertext followed by the
+ *		  authentication tag and provide the entire data stream to the
+ *		  decryption operation (i.e. the data length used for the
+ *		  initialization of the scatterlist and the data length for the
+ *		  decryption operation is identical). For encryption, however,
+ *		  the authentication tag is created while encrypting the data.
+ *		  The destination buffer must hold sufficient space for the
+ *		  ciphertext and the authentication tag while the encryption
+ *		  invocation must only point to the plaintext data size. The
+ *		  following code snippet illustrates the memory usage
+ *		  buffer = kmalloc(ptbuflen + (enc ? authsize : 0));
+ *		  sg_init_one(&sg, buffer, ptbuflen + (enc ? authsize : 0));
+ *		  aead_request_set_crypt(req, &sg, &sg, ptbuflen, iv);
+ */
 static inline void aead_request_set_crypt(struct aead_request *req,
 					  struct scatterlist *src,
 					  struct scatterlist *dst,
@@ -1306,6 +1548,15 @@ static inline void aead_request_set_crypt(struct aead_request *req,
 	req->iv = iv;
 }
 
+/**
+ * aead_request_set_assoc() - set the associated data scatter / gather list
+ * @req: request handle
+ * @assoc: associated data scatter / gather list
+ * @assoclen: number of bytes to process from @assoc
+ *
+ * For encryption, the memory is filled with the associated data. For
+ * decryption, the memory must point to the associated data.
+ */
 static inline void aead_request_set_assoc(struct aead_request *req,
 					  struct scatterlist *assoc,
 					  unsigned int assoclen)
-- 
cgit v1.2.3-70-g09d2


From 58284f0d6c4a974d2d89446f3b3cbc51420432ea Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 12 Nov 2014 05:29:36 +0100
Subject: crypto: doc - BLKCIPHER API documentation

The API function calls exported by the kernel crypto API for
synchronous block ciphers to be used by consumers are documented.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/crypto.h | 188 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 188 insertions(+)

(limited to 'include')

diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 4704e71a31f..c9ebe456dc9 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -1565,6 +1565,36 @@ static inline void aead_request_set_assoc(struct aead_request *req,
 	req->assoclen = assoclen;
 }
 
+/**
+ * DOC: Synchronous Block Cipher API
+ *
+ * The synchronous block cipher API is used with the ciphers of type
+ * CRYPTO_ALG_TYPE_BLKCIPHER (listed as type "blkcipher" in /proc/crypto)
+ *
+ * Synchronous calls, have a context in the tfm. But since a single tfm can be
+ * used in multiple calls and in parallel, this info should not be changeable
+ * (unless a lock is used). This applies, for example, to the symmetric key.
+ * However, the IV is changeable, so there is an iv field in blkcipher_tfm
+ * structure for synchronous blkcipher api. So, its the only state info that can
+ * be kept for synchronous calls without using a big lock across a tfm.
+ *
+ * The block cipher API allows the use of a complete cipher, i.e. a cipher
+ * consisting of a template (a block chaining mode) and a single block cipher
+ * primitive (e.g. AES).
+ *
+ * The plaintext data buffer and the ciphertext data buffer are pointed to
+ * by using scatter/gather lists. The cipher operation is performed
+ * on all segments of the provided scatter/gather lists.
+ *
+ * The kernel crypto API supports a cipher operation "in-place" which means that
+ * the caller may provide the same scatter/gather list for the plaintext and
+ * cipher text. After the completion of the cipher operation, the plaintext
+ * data is replaced with the ciphertext data in case of an encryption and vice
+ * versa for a decryption. The caller must ensure that the scatter/gather lists
+ * for the output data point to sufficiently large buffers, i.e. multiples of
+ * the block size of the cipher.
+ */
+
 static inline struct crypto_blkcipher *__crypto_blkcipher_cast(
 	struct crypto_tfm *tfm)
 {
@@ -1578,6 +1608,20 @@ static inline struct crypto_blkcipher *crypto_blkcipher_cast(
 	return __crypto_blkcipher_cast(tfm);
 }
 
+/**
+ * crypto_alloc_blkcipher() - allocate synchronous block cipher handle
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	      blkcipher cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Allocate a cipher handle for a block cipher. The returned struct
+ * crypto_blkcipher is the cipher handle that is required for any subsequent
+ * API invocation for that block cipher.
+ *
+ * Return: allocated cipher handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
 static inline struct crypto_blkcipher *crypto_alloc_blkcipher(
 	const char *alg_name, u32 type, u32 mask)
 {
@@ -1594,11 +1638,25 @@ static inline struct crypto_tfm *crypto_blkcipher_tfm(
 	return &tfm->base;
 }
 
+/**
+ * crypto_free_blkcipher() - zeroize and free the block cipher handle
+ * @tfm: cipher handle to be freed
+ */
 static inline void crypto_free_blkcipher(struct crypto_blkcipher *tfm)
 {
 	crypto_free_tfm(crypto_blkcipher_tfm(tfm));
 }
 
+/**
+ * crypto_has_blkcipher() - Search for the availability of a block cipher
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	      block cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Return: true when the block cipher is known to the kernel crypto API; false
+ *	   otherwise
+ */
 static inline int crypto_has_blkcipher(const char *alg_name, u32 type, u32 mask)
 {
 	type &= ~CRYPTO_ALG_TYPE_MASK;
@@ -1608,6 +1666,12 @@ static inline int crypto_has_blkcipher(const char *alg_name, u32 type, u32 mask)
 	return crypto_has_alg(alg_name, type, mask);
 }
 
+/**
+ * crypto_blkcipher_name() - return the name / cra_name from the cipher handle
+ * @tfm: cipher handle
+ *
+ * Return: The character string holding the name of the cipher
+ */
 static inline const char *crypto_blkcipher_name(struct crypto_blkcipher *tfm)
 {
 	return crypto_tfm_alg_name(crypto_blkcipher_tfm(tfm));
@@ -1625,11 +1689,30 @@ static inline struct blkcipher_alg *crypto_blkcipher_alg(
 	return &crypto_blkcipher_tfm(tfm)->__crt_alg->cra_blkcipher;
 }
 
+/**
+ * crypto_blkcipher_ivsize() - obtain IV size
+ * @tfm: cipher handle
+ *
+ * The size of the IV for the block cipher referenced by the cipher handle is
+ * returned. This IV size may be zero if the cipher does not need an IV.
+ *
+ * Return: IV size in bytes
+ */
 static inline unsigned int crypto_blkcipher_ivsize(struct crypto_blkcipher *tfm)
 {
 	return crypto_blkcipher_alg(tfm)->ivsize;
 }
 
+/**
+ * crypto_blkcipher_blocksize() - obtain block size of cipher
+ * @tfm: cipher handle
+ *
+ * The block size for the block cipher referenced with the cipher handle is
+ * returned. The caller may use that information to allocate appropriate
+ * memory for the data returned by the encryption or decryption operation.
+ *
+ * Return: block size of cipher
+ */
 static inline unsigned int crypto_blkcipher_blocksize(
 	struct crypto_blkcipher *tfm)
 {
@@ -1659,6 +1742,22 @@ static inline void crypto_blkcipher_clear_flags(struct crypto_blkcipher *tfm,
 	crypto_tfm_clear_flags(crypto_blkcipher_tfm(tfm), flags);
 }
 
+/**
+ * crypto_blkcipher_setkey() - set key for cipher
+ * @tfm: cipher handle
+ * @key: buffer holding the key
+ * @keylen: length of the key in bytes
+ *
+ * The caller provided key is set for the block cipher referenced by the cipher
+ * handle.
+ *
+ * Note, the key length determines the cipher type. Many block ciphers implement
+ * different cipher modes depending on the key size, such as AES-128 vs AES-192
+ * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128
+ * is performed.
+ *
+ * Return: 0 if the setting of the key was successful; < 0 if an error occurred
+ */
 static inline int crypto_blkcipher_setkey(struct crypto_blkcipher *tfm,
 					  const u8 *key, unsigned int keylen)
 {
@@ -1666,6 +1765,24 @@ static inline int crypto_blkcipher_setkey(struct crypto_blkcipher *tfm,
 						 key, keylen);
 }
 
+/**
+ * crypto_blkcipher_encrypt() - encrypt plaintext
+ * @desc: reference to the block cipher handle with meta data
+ * @dst: scatter/gather list that is filled by the cipher operation with the
+ *	ciphertext
+ * @src: scatter/gather list that holds the plaintext
+ * @nbytes: number of bytes of the plaintext to encrypt.
+ *
+ * Encrypt plaintext data using the IV set by the caller with a preceding
+ * call of crypto_blkcipher_set_iv.
+ *
+ * The blkcipher_desc data structure must be filled by the caller and can
+ * reside on the stack. The caller must fill desc as follows: desc.tfm is filled
+ * with the block cipher handle; desc.flags is filled with either
+ * CRYPTO_TFM_REQ_MAY_SLEEP or 0.
+ *
+ * Return: 0 if the cipher operation was successful; < 0 if an error occurred
+ */
 static inline int crypto_blkcipher_encrypt(struct blkcipher_desc *desc,
 					   struct scatterlist *dst,
 					   struct scatterlist *src,
@@ -1675,6 +1792,25 @@ static inline int crypto_blkcipher_encrypt(struct blkcipher_desc *desc,
 	return crypto_blkcipher_crt(desc->tfm)->encrypt(desc, dst, src, nbytes);
 }
 
+/**
+ * crypto_blkcipher_encrypt_iv() - encrypt plaintext with dedicated IV
+ * @desc: reference to the block cipher handle with meta data
+ * @dst: scatter/gather list that is filled by the cipher operation with the
+ *	ciphertext
+ * @src: scatter/gather list that holds the plaintext
+ * @nbytes: number of bytes of the plaintext to encrypt.
+ *
+ * Encrypt plaintext data with the use of an IV that is solely used for this
+ * cipher operation. Any previously set IV is not used.
+ *
+ * The blkcipher_desc data structure must be filled by the caller and can
+ * reside on the stack. The caller must fill desc as follows: desc.tfm is filled
+ * with the block cipher handle; desc.info is filled with the IV to be used for
+ * the current operation; desc.flags is filled with either
+ * CRYPTO_TFM_REQ_MAY_SLEEP or 0.
+ *
+ * Return: 0 if the cipher operation was successful; < 0 if an error occurred
+ */
 static inline int crypto_blkcipher_encrypt_iv(struct blkcipher_desc *desc,
 					      struct scatterlist *dst,
 					      struct scatterlist *src,
@@ -1683,6 +1819,23 @@ static inline int crypto_blkcipher_encrypt_iv(struct blkcipher_desc *desc,
 	return crypto_blkcipher_crt(desc->tfm)->encrypt(desc, dst, src, nbytes);
 }
 
+/**
+ * crypto_blkcipher_decrypt() - decrypt ciphertext
+ * @desc: reference to the block cipher handle with meta data
+ * @dst: scatter/gather list that is filled by the cipher operation with the
+ *	plaintext
+ * @src: scatter/gather list that holds the ciphertext
+ * @nbytes: number of bytes of the ciphertext to decrypt.
+ *
+ * Decrypt ciphertext data using the IV set by the caller with a preceding
+ * call of crypto_blkcipher_set_iv.
+ *
+ * The blkcipher_desc data structure must be filled by the caller as documented
+ * for the crypto_blkcipher_encrypt call above.
+ *
+ * Return: 0 if the cipher operation was successful; < 0 if an error occurred
+ *
+ */
 static inline int crypto_blkcipher_decrypt(struct blkcipher_desc *desc,
 					   struct scatterlist *dst,
 					   struct scatterlist *src,
@@ -1692,6 +1845,22 @@ static inline int crypto_blkcipher_decrypt(struct blkcipher_desc *desc,
 	return crypto_blkcipher_crt(desc->tfm)->decrypt(desc, dst, src, nbytes);
 }
 
+/**
+ * crypto_blkcipher_decrypt_iv() - decrypt ciphertext with dedicated IV
+ * @desc: reference to the block cipher handle with meta data
+ * @dst: scatter/gather list that is filled by the cipher operation with the
+ *	plaintext
+ * @src: scatter/gather list that holds the ciphertext
+ * @nbytes: number of bytes of the ciphertext to decrypt.
+ *
+ * Decrypt ciphertext data with the use of an IV that is solely used for this
+ * cipher operation. Any previously set IV is not used.
+ *
+ * The blkcipher_desc data structure must be filled by the caller as documented
+ * for the crypto_blkcipher_encrypt_iv call above.
+ *
+ * Return: 0 if the cipher operation was successful; < 0 if an error occurred
+ */
 static inline int crypto_blkcipher_decrypt_iv(struct blkcipher_desc *desc,
 					      struct scatterlist *dst,
 					      struct scatterlist *src,
@@ -1700,12 +1869,31 @@ static inline int crypto_blkcipher_decrypt_iv(struct blkcipher_desc *desc,
 	return crypto_blkcipher_crt(desc->tfm)->decrypt(desc, dst, src, nbytes);
 }
 
+/**
+ * crypto_blkcipher_set_iv() - set IV for cipher
+ * @tfm: cipher handle
+ * @src: buffer holding the IV
+ * @len: length of the IV in bytes
+ *
+ * The caller provided IV is set for the block cipher referenced by the cipher
+ * handle.
+ */
 static inline void crypto_blkcipher_set_iv(struct crypto_blkcipher *tfm,
 					   const u8 *src, unsigned int len)
 {
 	memcpy(crypto_blkcipher_crt(tfm)->iv, src, len);
 }
 
+/**
+ * crypto_blkcipher_get_iv() - obtain IV from cipher
+ * @tfm: cipher handle
+ * @dst: buffer filled with the IV
+ * @len: length of the buffer dst
+ *
+ * The caller can obtain the IV set for the block cipher referenced by the
+ * cipher handle and store it into the user-provided buffer. If the buffer
+ * has an insufficient space, the IV is truncated to fit the buffer.
+ */
 static inline void crypto_blkcipher_get_iv(struct crypto_blkcipher *tfm,
 					   u8 *dst, unsigned int len)
 {
-- 
cgit v1.2.3-70-g09d2


From 16e61030aecb250766cf175141fc91d441361c43 Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 12 Nov 2014 05:30:06 +0100
Subject: crypto: doc - CIPHER API documentation

The API function calls exported by the kernel crypto API for
signle block ciphers to be used by consumers are documented.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/crypto.h | 89 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 89 insertions(+)

(limited to 'include')

diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index c9ebe456dc9..0f95a07aa4d 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -1900,6 +1900,23 @@ static inline void crypto_blkcipher_get_iv(struct crypto_blkcipher *tfm,
 	memcpy(dst, crypto_blkcipher_crt(tfm)->iv, len);
 }
 
+/**
+ * DOC: Single Block Cipher API
+ *
+ * The single block cipher API is used with the ciphers of type
+ * CRYPTO_ALG_TYPE_CIPHER (listed as type "cipher" in /proc/crypto).
+ *
+ * Using the single block cipher API calls, operations with the basic cipher
+ * primitive can be implemented. These cipher primitives exclude any block
+ * chaining operations including IV handling.
+ *
+ * The purpose of this single block cipher API is to support the implementation
+ * of templates or other concepts that only need to perform the cipher operation
+ * on one block at a time. Templates invoke the underlying cipher primitive
+ * block-wise and process either the input or the output data of these cipher
+ * operations.
+ */
+
 static inline struct crypto_cipher *__crypto_cipher_cast(struct crypto_tfm *tfm)
 {
 	return (struct crypto_cipher *)tfm;
@@ -1911,6 +1928,20 @@ static inline struct crypto_cipher *crypto_cipher_cast(struct crypto_tfm *tfm)
 	return __crypto_cipher_cast(tfm);
 }
 
+/**
+ * crypto_alloc_cipher() - allocate single block cipher handle
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	     single block cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Allocate a cipher handle for a single block cipher. The returned struct
+ * crypto_cipher is the cipher handle that is required for any subsequent API
+ * invocation for that single block cipher.
+ *
+ * Return: allocated cipher handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
 static inline struct crypto_cipher *crypto_alloc_cipher(const char *alg_name,
 							u32 type, u32 mask)
 {
@@ -1926,11 +1957,25 @@ static inline struct crypto_tfm *crypto_cipher_tfm(struct crypto_cipher *tfm)
 	return &tfm->base;
 }
 
+/**
+ * crypto_free_cipher() - zeroize and free the single block cipher handle
+ * @tfm: cipher handle to be freed
+ */
 static inline void crypto_free_cipher(struct crypto_cipher *tfm)
 {
 	crypto_free_tfm(crypto_cipher_tfm(tfm));
 }
 
+/**
+ * crypto_has_cipher() - Search for the availability of a single block cipher
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	     single block cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Return: true when the single block cipher is known to the kernel crypto API;
+ *	   false otherwise
+ */
 static inline int crypto_has_cipher(const char *alg_name, u32 type, u32 mask)
 {
 	type &= ~CRYPTO_ALG_TYPE_MASK;
@@ -1945,6 +1990,16 @@ static inline struct cipher_tfm *crypto_cipher_crt(struct crypto_cipher *tfm)
 	return &crypto_cipher_tfm(tfm)->crt_cipher;
 }
 
+/**
+ * crypto_cipher_blocksize() - obtain block size for cipher
+ * @tfm: cipher handle
+ *
+ * The block size for the single block cipher referenced with the cipher handle
+ * tfm is returned. The caller may use that information to allocate appropriate
+ * memory for the data returned by the encryption or decryption operation
+ *
+ * Return: block size of cipher
+ */
 static inline unsigned int crypto_cipher_blocksize(struct crypto_cipher *tfm)
 {
 	return crypto_tfm_alg_blocksize(crypto_cipher_tfm(tfm));
@@ -1972,6 +2027,22 @@ static inline void crypto_cipher_clear_flags(struct crypto_cipher *tfm,
 	crypto_tfm_clear_flags(crypto_cipher_tfm(tfm), flags);
 }
 
+/**
+ * crypto_cipher_setkey() - set key for cipher
+ * @tfm: cipher handle
+ * @key: buffer holding the key
+ * @keylen: length of the key in bytes
+ *
+ * The caller provided key is set for the single block cipher referenced by the
+ * cipher handle.
+ *
+ * Note, the key length determines the cipher type. Many block ciphers implement
+ * different cipher modes depending on the key size, such as AES-128 vs AES-192
+ * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128
+ * is performed.
+ *
+ * Return: 0 if the setting of the key was successful; < 0 if an error occurred
+ */
 static inline int crypto_cipher_setkey(struct crypto_cipher *tfm,
                                        const u8 *key, unsigned int keylen)
 {
@@ -1979,6 +2050,15 @@ static inline int crypto_cipher_setkey(struct crypto_cipher *tfm,
 						  key, keylen);
 }
 
+/**
+ * crypto_cipher_encrypt_one() - encrypt one block of plaintext
+ * @tfm: cipher handle
+ * @dst: points to the buffer that will be filled with the ciphertext
+ * @src: buffer holding the plaintext to be encrypted
+ *
+ * Invoke the encryption operation of one block. The caller must ensure that
+ * the plaintext and ciphertext buffers are at least one block in size.
+ */
 static inline void crypto_cipher_encrypt_one(struct crypto_cipher *tfm,
 					     u8 *dst, const u8 *src)
 {
@@ -1986,6 +2066,15 @@ static inline void crypto_cipher_encrypt_one(struct crypto_cipher *tfm,
 						dst, src);
 }
 
+/**
+ * crypto_cipher_decrypt_one() - decrypt one block of ciphertext
+ * @tfm: cipher handle
+ * @dst: points to the buffer that will be filled with the plaintext
+ * @src: buffer holding the ciphertext to be decrypted
+ *
+ * Invoke the decryption operation of one block. The caller must ensure that
+ * the plaintext and ciphertext buffers are at least one block in size.
+ */
 static inline void crypto_cipher_decrypt_one(struct crypto_cipher *tfm,
 					     u8 *dst, const u8 *src)
 {
-- 
cgit v1.2.3-70-g09d2


From 47ca5be9eb066befe284f4e03fc11f21b8321ddc Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 12 Nov 2014 05:30:42 +0100
Subject: crypto: doc - HASH API documentation

The API function calls exported by the kernel crypto API for
message digests to be used by consumers are documented.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/crypto.h | 119 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 119 insertions(+)

(limited to 'include')

diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 0f95a07aa4d..208a63290b2 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -2082,6 +2082,13 @@ static inline void crypto_cipher_decrypt_one(struct crypto_cipher *tfm,
 						dst, src);
 }
 
+/**
+ * DOC: Synchronous Message Digest API
+ *
+ * The synchronous message digest API is used with the ciphers of type
+ * CRYPTO_ALG_TYPE_HASH (listed as type "hash" in /proc/crypto)
+ */
+
 static inline struct crypto_hash *__crypto_hash_cast(struct crypto_tfm *tfm)
 {
 	return (struct crypto_hash *)tfm;
@@ -2094,6 +2101,20 @@ static inline struct crypto_hash *crypto_hash_cast(struct crypto_tfm *tfm)
 	return __crypto_hash_cast(tfm);
 }
 
+/**
+ * crypto_alloc_hash() - allocate synchronous message digest handle
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	      message digest cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Allocate a cipher handle for a message digest. The returned struct
+ * crypto_hash is the cipher handle that is required for any subsequent
+ * API invocation for that message digest.
+ *
+ * Return: allocated cipher handle in case of success; IS_ERR() is true in case
+ * of an error, PTR_ERR() returns the error code.
+ */
 static inline struct crypto_hash *crypto_alloc_hash(const char *alg_name,
 						    u32 type, u32 mask)
 {
@@ -2110,11 +2131,25 @@ static inline struct crypto_tfm *crypto_hash_tfm(struct crypto_hash *tfm)
 	return &tfm->base;
 }
 
+/**
+ * crypto_free_hash() - zeroize and free message digest handle
+ * @tfm: cipher handle to be freed
+ */
 static inline void crypto_free_hash(struct crypto_hash *tfm)
 {
 	crypto_free_tfm(crypto_hash_tfm(tfm));
 }
 
+/**
+ * crypto_has_hash() - Search for the availability of a message digest
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	      message digest cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Return: true when the message digest cipher is known to the kernel crypto
+ *	   API; false otherwise
+ */
 static inline int crypto_has_hash(const char *alg_name, u32 type, u32 mask)
 {
 	type &= ~CRYPTO_ALG_TYPE_MASK;
@@ -2130,6 +2165,15 @@ static inline struct hash_tfm *crypto_hash_crt(struct crypto_hash *tfm)
 	return &crypto_hash_tfm(tfm)->crt_hash;
 }
 
+/**
+ * crypto_hash_blocksize() - obtain block size for message digest
+ * @tfm: cipher handle
+ *
+ * The block size for the message digest cipher referenced with the cipher
+ * handle is returned.
+ *
+ * Return: block size of cipher
+ */
 static inline unsigned int crypto_hash_blocksize(struct crypto_hash *tfm)
 {
 	return crypto_tfm_alg_blocksize(crypto_hash_tfm(tfm));
@@ -2140,6 +2184,15 @@ static inline unsigned int crypto_hash_alignmask(struct crypto_hash *tfm)
 	return crypto_tfm_alg_alignmask(crypto_hash_tfm(tfm));
 }
 
+/**
+ * crypto_hash_digestsize() - obtain message digest size
+ * @tfm: cipher handle
+ *
+ * The size for the message digest created by the message digest cipher
+ * referenced with the cipher handle is returned.
+ *
+ * Return: message digest size
+ */
 static inline unsigned int crypto_hash_digestsize(struct crypto_hash *tfm)
 {
 	return crypto_hash_crt(tfm)->digestsize;
@@ -2160,11 +2213,38 @@ static inline void crypto_hash_clear_flags(struct crypto_hash *tfm, u32 flags)
 	crypto_tfm_clear_flags(crypto_hash_tfm(tfm), flags);
 }
 
+/**
+ * crypto_hash_init() - (re)initialize message digest handle
+ * @desc: cipher request handle that to be filled by caller --
+ *	  desc.tfm is filled with the hash cipher handle;
+ *	  desc.flags is filled with either CRYPTO_TFM_REQ_MAY_SLEEP or 0.
+ *
+ * The call (re-)initializes the message digest referenced by the hash cipher
+ * request handle. Any potentially existing state created by previous
+ * operations is discarded.
+ *
+ * Return: 0 if the message digest initialization was successful; < 0 if an
+ *	   error occurred
+ */
 static inline int crypto_hash_init(struct hash_desc *desc)
 {
 	return crypto_hash_crt(desc->tfm)->init(desc);
 }
 
+/**
+ * crypto_hash_update() - add data to message digest for processing
+ * @desc: cipher request handle
+ * @sg: scatter / gather list pointing to the data to be added to the message
+ *      digest
+ * @nbytes: number of bytes to be processed from @sg
+ *
+ * Updates the message digest state of the cipher handle pointed to by the
+ * hash cipher request handle with the input data pointed to by the
+ * scatter/gather list.
+ *
+ * Return: 0 if the message digest update was successful; < 0 if an error
+ *	   occurred
+ */
 static inline int crypto_hash_update(struct hash_desc *desc,
 				     struct scatterlist *sg,
 				     unsigned int nbytes)
@@ -2172,11 +2252,39 @@ static inline int crypto_hash_update(struct hash_desc *desc,
 	return crypto_hash_crt(desc->tfm)->update(desc, sg, nbytes);
 }
 
+/**
+ * crypto_hash_final() - calculate message digest
+ * @desc: cipher request handle
+ * @out: message digest output buffer -- The caller must ensure that the out
+ *	 buffer has a sufficient size (e.g. by using the crypto_hash_digestsize
+ *	 function).
+ *
+ * Finalize the message digest operation and create the message digest
+ * based on all data added to the cipher handle. The message digest is placed
+ * into the output buffer.
+ *
+ * Return: 0 if the message digest creation was successful; < 0 if an error
+ *	   occurred
+ */
 static inline int crypto_hash_final(struct hash_desc *desc, u8 *out)
 {
 	return crypto_hash_crt(desc->tfm)->final(desc, out);
 }
 
+/**
+ * crypto_hash_digest() - calculate message digest for a buffer
+ * @desc: see crypto_hash_final()
+ * @sg: see crypto_hash_update()
+ * @nbytes:  see crypto_hash_update()
+ * @out: see crypto_hash_final()
+ *
+ * This function is a "short-hand" for the function calls of crypto_hash_init,
+ * crypto_hash_update and crypto_hash_final. The parameters have the same
+ * meaning as discussed for those separate three functions.
+ *
+ * Return: 0 if the message digest creation was successful; < 0 if an error
+ *	   occurred
+ */
 static inline int crypto_hash_digest(struct hash_desc *desc,
 				     struct scatterlist *sg,
 				     unsigned int nbytes, u8 *out)
@@ -2184,6 +2292,17 @@ static inline int crypto_hash_digest(struct hash_desc *desc,
 	return crypto_hash_crt(desc->tfm)->digest(desc, sg, nbytes, out);
 }
 
+/**
+ * crypto_hash_setkey() - set key for message digest
+ * @hash: cipher handle
+ * @key: buffer holding the key
+ * @keylen: length of the key in bytes
+ *
+ * The caller provided key is set for the message digest cipher. The cipher
+ * handle must point to a keyed hash in order for this function to succeed.
+ *
+ * Return: 0 if the setting of the key was successful; < 0 if an error occurred
+ */
 static inline int crypto_hash_setkey(struct crypto_hash *hash,
 				     const u8 *key, unsigned int keylen)
 {
-- 
cgit v1.2.3-70-g09d2


From d539efa37f1f789339699c941e72e320d12d5f28 Mon Sep 17 00:00:00 2001
From: Tero Kristo <t-kristo@ti.com>
Date: Fri, 3 Oct 2014 16:57:11 +0300
Subject: ARM: OMAP3: clock: add new rate changing logic support for noncore
 DPLLs

Currently, DPLL code hides the re-parenting within its internals, which
is wrong. This needs to be exposed to the common clock code via
determine_rate and set_rate_and_parent APIs. This patch adds support
for these, which will be taken into use in the following patches.

Signed-off-by: Tero Kristo <t-kristo@ti.com>
Signed-off-by: Paul Walmsley <paul@pwsan.com>
---
 arch/arm/mach-omap2/dpll3xxx.c | 147 +++++++++++++++++++++++++++++++++++++++++
 include/linux/clk/ti.h         |   9 +++
 2 files changed, 156 insertions(+)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c
index ac3d789ac3c..cfe7c30235d 100644
--- a/arch/arm/mach-omap2/dpll3xxx.c
+++ b/arch/arm/mach-omap2/dpll3xxx.c
@@ -546,6 +546,153 @@ int omap3_noncore_dpll_set_rate(struct clk_hw *hw, unsigned long rate,
 	return 0;
 }
 
+/**
+ * omap3_noncore_dpll_determine_rate - determine rate for a DPLL
+ * @hw: pointer to the clock to determine rate for
+ * @rate: target rate for the DPLL
+ * @best_parent_rate: pointer for returning best parent rate
+ * @best_parent_clk: pointer for returning best parent clock
+ *
+ * Determines which DPLL mode to use for reaching a desired target rate.
+ * Checks whether the DPLL shall be in bypass or locked mode, and if
+ * locked, calculates the M,N values for the DPLL via round-rate.
+ * Returns a positive clock rate with success, negative error value
+ * in failure.
+ */
+long omap3_noncore_dpll_determine_rate(struct clk_hw *hw, unsigned long rate,
+				       unsigned long *best_parent_rate,
+				       struct clk **best_parent_clk)
+{
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+	struct dpll_data *dd;
+
+	if (!hw || !rate)
+		return -EINVAL;
+
+	dd = clk->dpll_data;
+	if (!dd)
+		return -EINVAL;
+
+	if (__clk_get_rate(dd->clk_bypass) == rate &&
+	    (dd->modes & (1 << DPLL_LOW_POWER_BYPASS))) {
+		*best_parent_clk = dd->clk_bypass;
+	} else {
+		rate = omap2_dpll_round_rate(hw, rate, best_parent_rate);
+		*best_parent_clk = dd->clk_ref;
+	}
+
+	*best_parent_rate = rate;
+
+	return rate;
+}
+
+/**
+ * omap3_noncore_dpll_set_parent - set parent for a DPLL clock
+ * @hw: pointer to the clock to set parent for
+ * @index: parent index to select
+ *
+ * Sets parent for a DPLL clock. This sets the DPLL into bypass or
+ * locked mode. Returns 0 with success, negative error value otherwise.
+ */
+int omap3_noncore_dpll_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+	int ret;
+
+	if (!hw)
+		return -EINVAL;
+
+	if (index)
+		ret = _omap3_noncore_dpll_bypass(clk);
+	else
+		ret = _omap3_noncore_dpll_lock(clk);
+
+	return ret;
+}
+
+/**
+ * omap3_noncore_dpll_set_rate_new - set rate for a DPLL clock
+ * @hw: pointer to the clock to set parent for
+ * @rate: target rate for the clock
+ * @parent_rate: rate of the parent clock
+ *
+ * Sets rate for a DPLL clock. First checks if the clock parent is
+ * reference clock (in bypass mode, the rate of the clock can't be
+ * changed) and proceeds with the rate change operation. Returns 0
+ * with success, negative error value otherwise.
+ */
+static int omap3_noncore_dpll_set_rate_new(struct clk_hw *hw,
+					   unsigned long rate,
+					   unsigned long parent_rate)
+{
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+	struct dpll_data *dd;
+	u16 freqsel = 0;
+	int ret;
+
+	if (!hw || !rate)
+		return -EINVAL;
+
+	dd = clk->dpll_data;
+	if (!dd)
+		return -EINVAL;
+
+	if (__clk_get_parent(hw->clk) != dd->clk_ref)
+		return -EINVAL;
+
+	if (dd->last_rounded_rate == 0)
+		return -EINVAL;
+
+	/* Freqsel is available only on OMAP343X devices */
+	if (ti_clk_features.flags & TI_CLK_DPLL_HAS_FREQSEL) {
+		freqsel = _omap3_dpll_compute_freqsel(clk, dd->last_rounded_n);
+		WARN_ON(!freqsel);
+	}
+
+	pr_debug("%s: %s: set rate: locking rate to %lu.\n", __func__,
+		 __clk_get_name(hw->clk), rate);
+
+	ret = omap3_noncore_dpll_program(clk, freqsel);
+
+	return ret;
+}
+
+/**
+ * omap3_noncore_dpll_set_rate_and_parent - set rate and parent for a DPLL clock
+ * @hw: pointer to the clock to set rate and parent for
+ * @rate: target rate for the DPLL
+ * @parent_rate: clock rate of the DPLL parent
+ * @index: new parent index for the DPLL, 0 - reference, 1 - bypass
+ *
+ * Sets rate and parent for a DPLL clock. If new parent is the bypass
+ * clock, only selects the parent. Otherwise proceeds with a rate
+ * change, as this will effectively also change the parent as the
+ * DPLL is put into locked mode. Returns 0 with success, negative error
+ * value otherwise.
+ */
+int omap3_noncore_dpll_set_rate_and_parent(struct clk_hw *hw,
+					   unsigned long rate,
+					   unsigned long parent_rate,
+					   u8 index)
+{
+	int ret;
+
+	if (!hw || !rate)
+		return -EINVAL;
+
+	/*
+	 * clk-ref at index[0], in which case we only need to set rate,
+	 * the parent will be changed automatically with the lock sequence.
+	 * With clk-bypass case we only need to change parent.
+	 */
+	if (index)
+		ret = omap3_noncore_dpll_set_parent(hw, index);
+	else
+		ret = omap3_noncore_dpll_set_rate_new(hw, rate, parent_rate);
+
+	return ret;
+}
+
 /* DPLL autoidle read/set code */
 
 /**
diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h
index f75acbf70e9..6f9fb77ffdd 100644
--- a/include/linux/clk/ti.h
+++ b/include/linux/clk/ti.h
@@ -254,8 +254,17 @@ extern const struct clk_ops ti_clk_mux_ops;
 void omap2_init_clk_hw_omap_clocks(struct clk *clk);
 int omap3_noncore_dpll_enable(struct clk_hw *hw);
 void omap3_noncore_dpll_disable(struct clk_hw *hw);
+int omap3_noncore_dpll_set_parent(struct clk_hw *hw, u8 index);
 int omap3_noncore_dpll_set_rate(struct clk_hw *hw, unsigned long rate,
 				unsigned long parent_rate);
+int omap3_noncore_dpll_set_rate_and_parent(struct clk_hw *hw,
+					   unsigned long rate,
+					   unsigned long parent_rate,
+					   u8 index);
+long omap3_noncore_dpll_determine_rate(struct clk_hw *hw,
+				       unsigned long rate,
+				       unsigned long *best_parent_rate,
+				       struct clk **best_parent_clk);
 unsigned long omap4_dpll_regm4xen_recalc(struct clk_hw *hw,
 					 unsigned long parent_rate);
 long omap4_dpll_regm4xen_round_rate(struct clk_hw *hw,
-- 
cgit v1.2.3-70-g09d2


From 83501ff0a5032dfbd63ab1ca9d9d25b97ec49fb9 Mon Sep 17 00:00:00 2001
From: Tero Kristo <t-kristo@ti.com>
Date: Fri, 3 Oct 2014 16:57:12 +0300
Subject: ARM: OMAP4: clock: add support for determine_rate for omap4 regm4xen
 DPLL

Similarly to OMAP3 noncore DPLL, the implementation of this DPLL clock
type is wrong. This patch adds basic functionality for determine_rate
for this clock type which will be taken into use in the patches following
later.

Signed-off-by: Tero Kristo <t-kristo@ti.com>
Signed-off-by: Paul Walmsley <paul@pwsan.com>
---
 arch/arm/mach-omap2/dpll44xx.c | 41 +++++++++++++++++++++++++++++++++++++++++
 include/linux/clk/ti.h         |  4 ++++
 2 files changed, 45 insertions(+)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/dpll44xx.c b/arch/arm/mach-omap2/dpll44xx.c
index 4613f1e8698..535822fcf4b 100644
--- a/arch/arm/mach-omap2/dpll44xx.c
+++ b/arch/arm/mach-omap2/dpll44xx.c
@@ -207,3 +207,44 @@ out:
 
 	return dd->last_rounded_rate;
 }
+
+/**
+ * omap4_dpll_regm4xen_determine_rate - determine rate for a DPLL
+ * @hw: pointer to the clock to determine rate for
+ * @rate: target rate for the DPLL
+ * @best_parent_rate: pointer for returning best parent rate
+ * @best_parent_clk: pointer for returning best parent clock
+ *
+ * Determines which DPLL mode to use for reaching a desired rate.
+ * Checks whether the DPLL shall be in bypass or locked mode, and if
+ * locked, calculates the M,N values for the DPLL via round-rate.
+ * Returns a positive clock rate with success, negative error value
+ * in failure.
+ */
+long omap4_dpll_regm4xen_determine_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long *best_parent_rate,
+					struct clk **best_parent_clk)
+{
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+	struct dpll_data *dd;
+
+	if (!hw || !rate)
+		return -EINVAL;
+
+	dd = clk->dpll_data;
+	if (!dd)
+		return -EINVAL;
+
+	if (__clk_get_rate(dd->clk_bypass) == rate &&
+	    (dd->modes & (1 << DPLL_LOW_POWER_BYPASS))) {
+		*best_parent_clk = dd->clk_bypass;
+	} else {
+		rate = omap4_dpll_regm4xen_round_rate(hw, rate,
+						      best_parent_rate);
+		*best_parent_clk = dd->clk_ref;
+	}
+
+	*best_parent_rate = rate;
+
+	return rate;
+}
diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h
index 6f9fb77ffdd..abc702a73ac 100644
--- a/include/linux/clk/ti.h
+++ b/include/linux/clk/ti.h
@@ -270,6 +270,10 @@ unsigned long omap4_dpll_regm4xen_recalc(struct clk_hw *hw,
 long omap4_dpll_regm4xen_round_rate(struct clk_hw *hw,
 				    unsigned long target_rate,
 				    unsigned long *parent_rate);
+long omap4_dpll_regm4xen_determine_rate(struct clk_hw *hw,
+					unsigned long rate,
+					unsigned long *best_parent_rate,
+					struct clk **best_parent_clk);
 u8 omap2_init_dpll_parent(struct clk_hw *hw);
 unsigned long omap3_dpll_recalc(struct clk_hw *hw, unsigned long parent_rate);
 long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate,
-- 
cgit v1.2.3-70-g09d2


From e3ab6013ab06d3a861ed00c1f8d32aa4e6b66ddd Mon Sep 17 00:00:00 2001
From: Tero Kristo <t-kristo@ti.com>
Date: Fri, 3 Oct 2014 16:57:13 +0300
Subject: ARM: OMAP3: clock: add support for dpll4_set_rate_and_parent

Expand the support of omap4 per-dpll to provide set_rate_and_parent.
This is required for proper behavior of clk_change_rate with
determine_rate support.

Signed-off-by: Tero Kristo <t-kristo@ti.com>
Signed-off-by: Paul Walmsley <paul@pwsan.com>
---
 arch/arm/mach-omap2/clock3xxx.c | 36 ++++++++++++++++++++++++++++++++++++
 include/linux/clk/ti.h          |  2 ++
 2 files changed, 38 insertions(+)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/clock3xxx.c b/arch/arm/mach-omap2/clock3xxx.c
index 9a256018190..a9e86db5daf 100644
--- a/arch/arm/mach-omap2/clock3xxx.c
+++ b/arch/arm/mach-omap2/clock3xxx.c
@@ -38,6 +38,18 @@
 
 /* needed by omap3_core_dpll_m2_set_rate() */
 struct clk *sdrc_ick_p, *arm_fck_p;
+
+/**
+ * omap3_dpll4_set_rate - set rate for omap3 per-dpll
+ * @hw: clock to change
+ * @rate: target rate for clock
+ * @parent_rate: rate of the parent clock
+ *
+ * Check if the current SoC supports the per-dpll reprogram operation
+ * or not, and then do the rate change if supported. Returns -EINVAL
+ * if not supported, 0 for success, and potential error codes from the
+ * clock rate change.
+ */
 int omap3_dpll4_set_rate(struct clk_hw *hw, unsigned long rate,
 				unsigned long parent_rate)
 {
@@ -54,6 +66,30 @@ int omap3_dpll4_set_rate(struct clk_hw *hw, unsigned long rate,
 	return omap3_noncore_dpll_set_rate(hw, rate, parent_rate);
 }
 
+/**
+ * omap3_dpll4_set_rate_and_parent - set rate and parent for omap3 per-dpll
+ * @hw: clock to change
+ * @rate: target rate for clock
+ * @parent_rate: rate of the parent clock
+ * @index: parent index, 0 - reference clock, 1 - bypass clock
+ *
+ * Check if the current SoC support the per-dpll reprogram operation
+ * or not, and then do the rate + parent change if supported. Returns
+ * -EINVAL if not supported, 0 for success, and potential error codes
+ * from the clock rate change.
+ */
+int omap3_dpll4_set_rate_and_parent(struct clk_hw *hw, unsigned long rate,
+				    unsigned long parent_rate, u8 index)
+{
+	if (ti_clk_features.flags & TI_CLK_DPLL4_DENY_REPROGRAM) {
+		pr_err("clock: DPLL4 cannot change rate due to silicon 'Limitation 2.5' on 3430ES1.\n");
+		return -EINVAL;
+	}
+
+	return omap3_noncore_dpll_set_rate_and_parent(hw, rate, parent_rate,
+						      index);
+}
+
 void __init omap3_clk_lock_dpll5(void)
 {
 	struct clk *dpll5_clk;
diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h
index abc702a73ac..74e5341463c 100644
--- a/include/linux/clk/ti.h
+++ b/include/linux/clk/ti.h
@@ -291,6 +291,8 @@ int omap2_clk_disable_autoidle_all(void);
 void omap2_clk_enable_init_clocks(const char **clk_names, u8 num_clocks);
 int omap3_dpll4_set_rate(struct clk_hw *clk, unsigned long rate,
 			 unsigned long parent_rate);
+int omap3_dpll4_set_rate_and_parent(struct clk_hw *hw, unsigned long rate,
+				    unsigned long parent_rate, u8 index);
 int omap2_dflt_clk_enable(struct clk_hw *hw);
 void omap2_dflt_clk_disable(struct clk_hw *hw);
 int omap2_dflt_clk_is_enabled(struct clk_hw *hw);
-- 
cgit v1.2.3-70-g09d2


From a4acded086c4320bc58bd59ea746fd19de6dabb0 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Wed, 12 Nov 2014 13:43:52 +1100
Subject: PCI: Remove unused and broken to_hotplug_slot()

to_hotplug_slot() is unused and wouldn't work anyway, because struct
hotplug_slot no longer contains a struct kobject (it was removed by
f46753c5e354 ("PCI: introduce pci_slot")).

Remove to_hotplug_slot().

[bhelgaas: changelog]
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci_hotplug.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h
index 2706ee9a432..8c789506112 100644
--- a/include/linux/pci_hotplug.h
+++ b/include/linux/pci_hotplug.h
@@ -109,7 +109,6 @@ struct hotplug_slot {
 	struct list_head		slot_list;
 	struct pci_slot			*pci_slot;
 };
-#define to_hotplug_slot(n) container_of(n, struct hotplug_slot, kobj)
 
 static inline const char *hotplug_slot_name(const struct hotplug_slot *slot)
 {
-- 
cgit v1.2.3-70-g09d2


From 1a6c9b2675460718f819def9a272cca35575eeb7 Mon Sep 17 00:00:00 2001
From: Pranith Kumar <bobby.prani@gmail.com>
Date: Thu, 25 Sep 2014 14:03:34 -0400
Subject: rcu: Add sparse check for RCU_INIT_POINTER()

Add a sparse check when RCU_INIT_POINTER() is used to assign a non __rcu
annotated pointer.

Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index a4a819ffb2d..a033d8b5577 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -1047,6 +1047,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  */
 #define RCU_INIT_POINTER(p, v) \
 	do { \
+		rcu_dereference_sparse(p, __rcu); \
 		p = RCU_INITIALIZER(v); \
 	} while (0)
 
-- 
cgit v1.2.3-70-g09d2


From b6331ae8afe4118884c4b6e14a213758d88422b2 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 4 Oct 2014 03:43:41 -0700
Subject: rcu: Optimize cond_resched_rcu_qs()

The current implementation of cond_resched_rcu_qs() can invoke
rcu_note_voluntary_context_switch() twice in the should_resched()
case, once via the call to __schedule() and once directly.  However, as
noted by Joe Lawrence in a patch to the team subsystem, cond_resched()
returns an indication as to whether or not the call to __schedule()
actually happened.  This commit therefore changes cond_resched_rcu_qs()
so as to invoke rcu_note_voluntary_context_switch() only when __schedule()
was not called.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index a033d8b5577..36ea3ba5c51 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -348,8 +348,8 @@ extern struct srcu_struct tasks_rcu_exit_srcu;
  */
 #define cond_resched_rcu_qs() \
 do { \
-	rcu_note_voluntary_context_switch(current); \
-	cond_resched(); \
+	if (!cond_resched()) \
+		rcu_note_voluntary_context_switch(current); \
 } while (0)
 
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP)
-- 
cgit v1.2.3-70-g09d2


From ce36f2f3eb6613a73bc6f3a5256bde7dd3f95710 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Sun, 28 Sep 2014 23:44:21 +0200
Subject: rcu: More info about potential deadlocks with rcu_read_unlock()

The comment above rcu_read_unlock() explains the potential deadlock
if the caller holds one of the locks taken by rt_mutex_unlock() paths,
but it is not clear from this documentation that any lock which can
be taken from interrupt can lead to deadlock as well and we need to
take rt_mutex_lock() into account too.

The problem is that rt_mutex_lock() takes wait_lock without disabling
irqs, and thus an interrupt taking some LOCK can obviously race with
rcu_read_unlock_special() called with the same LOCK held.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 36ea3ba5c51..ae6942a84a0 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -887,7 +887,9 @@ static inline void rcu_read_lock(void)
  * Unfortunately, this function acquires the scheduler's runqueue and
  * priority-inheritance spinlocks.  This means that deadlock could result
  * if the caller of rcu_read_unlock() already holds one of these locks or
- * any lock that is ever acquired while holding them.
+ * any lock that is ever acquired while holding them; or any lock which
+ * can be taken from interrupt context because rcu_boost()->rt_mutex_lock()
+ * does not disable irqs while taking ->wait_lock.
  *
  * That said, RCU readers are never priority boosted unless they were
  * preempted.  Therefore, one way to avoid deadlock is to make sure
-- 
cgit v1.2.3-70-g09d2


From 1b2f309d70daf04b6a97b3753e375654532f6207 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 13 Nov 2014 18:11:20 +0800
Subject: rhashtable: Move mutex_is_held under PROVE_LOCKING

The rhashtable function mutex_is_held is only used when PROVE_LOCKING
is enabled.  This patch makes the mutex_is_held field in rhashtable
optional depending on PROVE_LOCKING.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 2 ++
 lib/rhashtable.c           | 8 ++++++++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index fb298e9d6d3..96ce8ceff55 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -65,7 +65,9 @@ struct rhashtable_params {
 						 size_t new_size);
 	bool			(*shrink_decision)(const struct rhashtable *ht,
 						   size_t new_size);
+#ifdef CONFIG_PROVE_LOCKING
 	int			(*mutex_is_held)(void);
+#endif
 };
 
 /**
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 081be3ba9ea..c7654b6f5f6 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -532,7 +532,9 @@ static size_t rounded_hashtable_size(struct rhashtable_params *params)
  *	.key_offset = offsetof(struct test_obj, key),
  *	.key_len = sizeof(int),
  *	.hashfn = arch_fast_hash,
+ * #ifdef CONFIG_PROVE_LOCKING
  *	.mutex_is_held = &my_mutex_is_held,
+ * #endif
  * };
  *
  * Configuration Example 2: Variable length keys
@@ -552,7 +554,9 @@ static size_t rounded_hashtable_size(struct rhashtable_params *params)
  *	.head_offset = offsetof(struct test_obj, node),
  *	.hashfn = arch_fast_hash,
  *	.obj_hashfn = my_hash_fn,
+ * #ifdef CONFIG_PROVE_LOCKING
  *	.mutex_is_held = &my_mutex_is_held,
+ * #endif
  * };
  */
 int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params)
@@ -613,10 +617,12 @@ EXPORT_SYMBOL_GPL(rhashtable_destroy);
 #define TEST_PTR	((void *) 0xdeadbeef)
 #define TEST_NEXPANDS	4
 
+#ifdef CONFIG_PROVE_LOCKING
 static int test_mutex_is_held(void)
 {
 	return 1;
 }
+#endif
 
 struct test_obj {
 	void			*ptr;
@@ -767,7 +773,9 @@ static int __init test_rht_init(void)
 		.key_offset = offsetof(struct test_obj, value),
 		.key_len = sizeof(int),
 		.hashfn = arch_fast_hash,
+#ifdef CONFIG_PROVE_LOCKING
 		.mutex_is_held = &test_mutex_is_held,
+#endif
 		.grow_decision = rht_grow_above_75,
 		.shrink_decision = rht_shrink_below_30,
 	};
-- 
cgit v1.2.3-70-g09d2


From 7b4ce2353467fdab6e003be7a3129fb09b09deac Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 13 Nov 2014 18:11:22 +0800
Subject: rhashtable: Add parent argument to mutex_is_held

Currently mutex_is_held can only test locks in the that are global
since it takes no arguments.  This prevents rhashtable from being
used in places where locks are lock, e.g., per-namespace locks.

This patch adds a parent field to mutex_is_held and rhashtable_params
so that local locks can be used (and tested).

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 3 ++-
 lib/rhashtable.c           | 4 ++--
 net/netfilter/nft_hash.c   | 2 +-
 net/netlink/af_netlink.c   | 2 +-
 4 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 96ce8ceff55..473e26bdb91 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -66,7 +66,8 @@ struct rhashtable_params {
 	bool			(*shrink_decision)(const struct rhashtable *ht,
 						   size_t new_size);
 #ifdef CONFIG_PROVE_LOCKING
-	int			(*mutex_is_held)(void);
+	int			(*mutex_is_held)(void *parent);
+	void			*parent;
 #endif
 };
 
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index c7654b6f5f6..4b4b53bfa08 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -32,7 +32,7 @@
 #ifdef CONFIG_PROVE_LOCKING
 int lockdep_rht_mutex_is_held(const struct rhashtable *ht)
 {
-	return ht->p.mutex_is_held();
+	return ht->p.mutex_is_held(ht->p.parent);
 }
 EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held);
 #endif
@@ -618,7 +618,7 @@ EXPORT_SYMBOL_GPL(rhashtable_destroy);
 #define TEST_NEXPANDS	4
 
 #ifdef CONFIG_PROVE_LOCKING
-static int test_mutex_is_held(void)
+static int test_mutex_is_held(void *parent)
 {
 	return 1;
 }
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index b86305c8604..3f75aaaf9d0 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -154,7 +154,7 @@ static unsigned int nft_hash_privsize(const struct nlattr * const nla[])
 }
 
 #ifdef CONFIG_PROVE_LOCKING
-static int lockdep_nfnl_lock_is_held(void)
+static int lockdep_nfnl_lock_is_held(void *parent)
 {
 	return lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES);
 }
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 53b8ea79319..9e0628cfdf6 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -115,7 +115,7 @@ DEFINE_MUTEX(nl_sk_hash_lock);
 EXPORT_SYMBOL_GPL(nl_sk_hash_lock);
 
 #ifdef CONFIG_PROVE_LOCKING
-static int lockdep_nl_sk_hash_is_held(void)
+static int lockdep_nl_sk_hash_is_held(void *parent)
 {
 	if (debug_locks)
 		return lockdep_is_held(&nl_sk_hash_lock) || lockdep_is_held(&nl_table_lock);
-- 
cgit v1.2.3-70-g09d2


From 7ae0e400cd9396c41fe596d35dcc34feaa89a04f Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 13 Nov 2014 14:45:32 +0200
Subject: net/mlx4_core: Flexible (asymmetric) allocation of EQs and MSI-X
 vectors for PF/VFs

Previously, the driver queried the firmware in order to get the number
of supported EQs. Under SRIOV, since this was done before the driver
notified the firmware how many VFs it actually needs, the firmware had
to take into account a worst case scenario and always allocated four EQs
per VF, where one was used for events while the others were used for completions.

Now, when the firmware supports the asymmetric allocation scheme, denoted
by exposing num_sys_eqs > 0 (--> MLX4_DEV_CAP_FLAG2_SYS_EQS), we use the
QUERY_FUNC command to query the firmware before enabling SRIOV. Thus we
can get more EQs and MSI-X vectors per function.

Moreover, when running in the new firmware/driver mode, the limitation
that the number of EQs should be a power of two is lifted.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c            |   3 +-
 drivers/net/ethernet/mellanox/mlx4/eq.c      |   8 +-
 drivers/net/ethernet/mellanox/mlx4/fw.c      |  52 +++++++---
 drivers/net/ethernet/mellanox/mlx4/fw.h      |   2 +
 drivers/net/ethernet/mellanox/mlx4/main.c    | 144 +++++++++++++++++++++++----
 drivers/net/ethernet/mellanox/mlx4/profile.c |  19 ++--
 include/linux/mlx4/device.h                  |   4 +-
 7 files changed, 190 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 8b72cf392b3..0c3375524a6 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1975,8 +1975,7 @@ static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
 	    dev->caps.num_ports > dev->caps.comp_pool)
 		return;
 
-	eq_per_port = rounddown_pow_of_two(dev->caps.comp_pool/
-					dev->caps.num_ports);
+	eq_per_port = dev->caps.comp_pool / dev->caps.num_ports;
 
 	/* Init eq table */
 	added_eqs = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 49290a40590..d68b264cee4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -1123,8 +1123,12 @@ int mlx4_init_eq_table(struct mlx4_dev *dev)
 		goto err_out_free;
 	}
 
-	err = mlx4_bitmap_init(&priv->eq_table.bitmap, dev->caps.num_eqs,
-			       dev->caps.num_eqs - 1, dev->caps.reserved_eqs, 0);
+	err = mlx4_bitmap_init(&priv->eq_table.bitmap,
+			       roundup_pow_of_two(dev->caps.num_eqs),
+			       dev->caps.num_eqs - 1,
+			       dev->caps.reserved_eqs,
+			       roundup_pow_of_two(dev->caps.num_eqs) -
+			       dev->caps.num_eqs);
 	if (err)
 		goto err_out_free;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index b3bbeb97da1..d2f594fadfb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -142,7 +142,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[13] = "Large cache line (>64B) EQE stride support",
 		[14] = "Ethernet protocol control support",
 		[15] = "Ethernet Backplane autoneg support",
-		[16] = "CONFIG DEV support"
+		[16] = "CONFIG DEV support",
+		[17] = "Asymmetric EQs support"
 	};
 	int i;
 
@@ -200,7 +201,6 @@ int mlx4_QUERY_FUNC(struct mlx4_dev *dev, struct mlx4_func *func, int slave)
 	outbox = mailbox->buf;
 
 	in_modifier = slave;
-	mlx4_dbg(dev, "%s for VF %d\n", __func__, in_modifier);
 
 	err = mlx4_cmd_box(dev, 0, mailbox->dma, in_modifier, 0,
 			   MLX4_CMD_QUERY_FUNC,
@@ -243,6 +243,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 	u8	field, port;
 	u32	size, proxy_qp, qkey;
 	int	err = 0;
+	struct mlx4_func func;
 
 #define QUERY_FUNC_CAP_FLAGS_OFFSET		0x0
 #define QUERY_FUNC_CAP_NUM_PORTS_OFFSET		0x1
@@ -287,6 +288,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 #define QUERY_FUNC_CAP_VF_ENABLE_QP0		0x08
 
 #define QUERY_FUNC_CAP_FLAGS0_FORCE_PHY_WQE_GID 0x80
+#define QUERY_FUNC_CAP_SUPPORTS_NON_POWER_OF_2_NUM_EQS (1 << 31)
 
 	if (vhcr->op_modifier == 1) {
 		struct mlx4_active_ports actv_ports =
@@ -365,11 +367,24 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 		size = dev->caps.num_cqs;
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_CQ_QUOTA_OFFSET_DEP);
 
-		size = dev->caps.num_eqs;
-		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MAX_EQ_OFFSET);
-
-		size = dev->caps.reserved_eqs;
-		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_RESERVED_EQ_OFFSET);
+		if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS) ||
+		    mlx4_QUERY_FUNC(dev, &func, slave)) {
+			size = vhcr->in_modifier &
+				QUERY_FUNC_CAP_SUPPORTS_NON_POWER_OF_2_NUM_EQS ?
+				dev->caps.num_eqs :
+				rounddown_pow_of_two(dev->caps.num_eqs);
+			MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MAX_EQ_OFFSET);
+			size = dev->caps.reserved_eqs;
+			MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_RESERVED_EQ_OFFSET);
+		} else {
+			size = vhcr->in_modifier &
+				QUERY_FUNC_CAP_SUPPORTS_NON_POWER_OF_2_NUM_EQS ?
+				func.max_eq :
+				rounddown_pow_of_two(func.max_eq);
+			MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MAX_EQ_OFFSET);
+			size = func.rsvd_eqs;
+			MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_RESERVED_EQ_OFFSET);
+		}
 
 		size = priv->mfunc.master.res_tracker.res_alloc[RES_MPT].quota[slave];
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MPT_QUOTA_OFFSET);
@@ -399,14 +414,17 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u8 gen_or_port,
 	u8			field, op_modifier;
 	u32			size, qkey;
 	int			err = 0, quotas = 0;
+	u32                     in_modifier;
 
 	op_modifier = !!gen_or_port; /* 0 = general, 1 = logical port */
+	in_modifier = op_modifier ? gen_or_port :
+		QUERY_FUNC_CAP_SUPPORTS_NON_POWER_OF_2_NUM_EQS;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
 		return PTR_ERR(mailbox);
 
-	err = mlx4_cmd_box(dev, 0, mailbox->dma, gen_or_port, op_modifier,
+	err = mlx4_cmd_box(dev, 0, mailbox->dma, in_modifier, op_modifier,
 			   MLX4_CMD_QUERY_FUNC_CAP,
 			   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 	if (err)
@@ -578,6 +596,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_MAX_MRW_SZ_OFFSET		0x21
 #define QUERY_DEV_CAP_RSVD_MRW_OFFSET		0x22
 #define QUERY_DEV_CAP_MAX_MTT_SEG_OFFSET	0x23
+#define QUERY_DEV_CAP_NUM_SYS_EQ_OFFSET		0x26
 #define QUERY_DEV_CAP_MAX_AV_OFFSET		0x27
 #define QUERY_DEV_CAP_MAX_REQ_QP_OFFSET		0x29
 #define QUERY_DEV_CAP_MAX_RES_QP_OFFSET		0x2b
@@ -678,6 +697,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev_cap->reserved_mrws = 1 << (field & 0xf);
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_MTT_SEG_OFFSET);
 	dev_cap->max_mtt_seg = 1 << (field & 0x3f);
+	MLX4_GET(size, outbox, QUERY_DEV_CAP_NUM_SYS_EQ_OFFSET);
+	dev_cap->num_sys_eqs = size & 0xfff;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_REQ_QP_OFFSET);
 	dev_cap->max_requester_per_qp = 1 << (field & 0x3f);
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_RES_QP_OFFSET);
@@ -905,8 +926,11 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	 * we can't use any EQs whose doorbell falls on that page,
 	 * even if the EQ itself isn't reserved.
 	 */
-	dev_cap->reserved_eqs = max(dev_cap->reserved_uars * 4,
-				    dev_cap->reserved_eqs);
+	if (dev_cap->num_sys_eqs == 0)
+		dev_cap->reserved_eqs = max(dev_cap->reserved_uars * 4,
+					    dev_cap->reserved_eqs);
+	else
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_SYS_EQS;
 
 	mlx4_dbg(dev, "Max ICM size %lld MB\n",
 		 (unsigned long long) dev_cap->max_icm_sz >> 20);
@@ -916,8 +940,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		 dev_cap->max_srqs, dev_cap->reserved_srqs, dev_cap->srq_entry_sz);
 	mlx4_dbg(dev, "Max CQs: %d, reserved CQs: %d, entry size: %d\n",
 		 dev_cap->max_cqs, dev_cap->reserved_cqs, dev_cap->cqc_entry_sz);
-	mlx4_dbg(dev, "Max EQs: %d, reserved EQs: %d, entry size: %d\n",
-		 dev_cap->max_eqs, dev_cap->reserved_eqs, dev_cap->eqc_entry_sz);
+	mlx4_dbg(dev, "Num sys EQs: %d, max EQs: %d, reserved EQs: %d, entry size: %d\n",
+		 dev_cap->num_sys_eqs, dev_cap->max_eqs, dev_cap->reserved_eqs,
+		 dev_cap->eqc_entry_sz);
 	mlx4_dbg(dev, "reserved MPTs: %d, reserved MTTs: %d\n",
 		 dev_cap->reserved_mrws, dev_cap->reserved_mtts);
 	mlx4_dbg(dev, "Max PDs: %d, reserved PDs: %d, reserved UARs: %d\n",
@@ -1463,6 +1488,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 #define	 INIT_HCA_AUXC_BASE_OFFSET	 (INIT_HCA_QPC_OFFSET + 0x50)
 #define	 INIT_HCA_EQC_BASE_OFFSET	 (INIT_HCA_QPC_OFFSET + 0x60)
 #define	 INIT_HCA_LOG_EQ_OFFSET		 (INIT_HCA_QPC_OFFSET + 0x67)
+#define	INIT_HCA_NUM_SYS_EQS_OFFSET	(INIT_HCA_QPC_OFFSET + 0x6a)
 #define	 INIT_HCA_RDMARC_BASE_OFFSET	 (INIT_HCA_QPC_OFFSET + 0x70)
 #define	 INIT_HCA_LOG_RD_OFFSET		 (INIT_HCA_QPC_OFFSET + 0x77)
 #define INIT_HCA_MCAST_OFFSET		 0x0c0
@@ -1566,6 +1592,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 	MLX4_PUT(inbox, param->auxc_base,     INIT_HCA_AUXC_BASE_OFFSET);
 	MLX4_PUT(inbox, param->eqc_base,      INIT_HCA_EQC_BASE_OFFSET);
 	MLX4_PUT(inbox, param->log_num_eqs,   INIT_HCA_LOG_EQ_OFFSET);
+	MLX4_PUT(inbox, param->num_sys_eqs,   INIT_HCA_NUM_SYS_EQS_OFFSET);
 	MLX4_PUT(inbox, param->rdmarc_base,   INIT_HCA_RDMARC_BASE_OFFSET);
 	MLX4_PUT(inbox, param->log_rd_per_qp, INIT_HCA_LOG_RD_OFFSET);
 
@@ -1676,6 +1703,7 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	MLX4_GET(param->auxc_base,     outbox, INIT_HCA_AUXC_BASE_OFFSET);
 	MLX4_GET(param->eqc_base,      outbox, INIT_HCA_EQC_BASE_OFFSET);
 	MLX4_GET(param->log_num_eqs,   outbox, INIT_HCA_LOG_EQ_OFFSET);
+	MLX4_GET(param->num_sys_eqs,   outbox, INIT_HCA_NUM_SYS_EQS_OFFSET);
 	MLX4_GET(param->rdmarc_base,   outbox, INIT_HCA_RDMARC_BASE_OFFSET);
 	MLX4_GET(param->log_rd_per_qp, outbox, INIT_HCA_LOG_RD_OFFSET);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 48c11b5e73e..475215ee370 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -56,6 +56,7 @@ struct mlx4_dev_cap {
 	int max_mpts;
 	int reserved_eqs;
 	int max_eqs;
+	int num_sys_eqs;
 	int reserved_mtts;
 	int max_mrw_sz;
 	int reserved_mrws;
@@ -180,6 +181,7 @@ struct mlx4_init_hca_param {
 	u8  log_num_srqs;
 	u8  log_num_cqs;
 	u8  log_num_eqs;
+	u16 num_sys_eqs;
 	u8  log_rd_per_qp;
 	u8  log_mc_table_sz;
 	u8  log_mpt_sz;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 43047b2a2aa..ebb279060a2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -197,6 +197,29 @@ static void mlx4_set_port_mask(struct mlx4_dev *dev)
 		dev->caps.port_mask[i] = dev->caps.port_type[i];
 }
 
+enum {
+	MLX4_QUERY_FUNC_NUM_SYS_EQS = 1 << 0,
+};
+
+static int mlx4_query_func(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
+{
+	int err = 0;
+	struct mlx4_func func;
+
+	if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS) {
+		err = mlx4_QUERY_FUNC(dev, &func, 0);
+		if (err) {
+			mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
+			return err;
+		}
+		dev_cap->max_eqs = func.max_eq;
+		dev_cap->reserved_eqs = func.rsvd_eqs;
+		dev_cap->reserved_uars = func.rsvd_uars;
+		err |= MLX4_QUERY_FUNC_NUM_SYS_EQS;
+	}
+	return err;
+}
+
 static void mlx4_enable_cqe_eqe_stride(struct mlx4_dev *dev)
 {
 	struct mlx4_caps *dev_cap = &dev->caps;
@@ -261,7 +284,10 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	}
 
 	dev->caps.num_ports	     = dev_cap->num_ports;
-	dev->phys_caps.num_phys_eqs  = MLX4_MAX_EQ_NUM;
+	dev->caps.num_sys_eqs = dev_cap->num_sys_eqs;
+	dev->phys_caps.num_phys_eqs = dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS ?
+				      dev->caps.num_sys_eqs :
+				      MLX4_MAX_EQ_NUM;
 	for (i = 1; i <= dev->caps.num_ports; ++i) {
 		dev->caps.vl_cap[i]	    = dev_cap->max_vl[i];
 		dev->caps.ib_mtu_cap[i]	    = dev_cap->ib_mtu[i];
@@ -1130,8 +1156,7 @@ static int mlx4_init_cmpt_table(struct mlx4_dev *dev, u64 cmpt_base,
 	if (err)
 		goto err_srq;
 
-	num_eqs = (mlx4_is_master(dev)) ? dev->phys_caps.num_phys_eqs :
-		  dev->caps.num_eqs;
+	num_eqs = dev->phys_caps.num_phys_eqs;
 	err = mlx4_init_icm_table(dev, &priv->eq_table.cmpt_table,
 				  cmpt_base +
 				  ((u64) (MLX4_CMPT_TYPE_EQ *
@@ -1193,8 +1218,7 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 	}
 
 
-	num_eqs = (mlx4_is_master(dev)) ? dev->phys_caps.num_phys_eqs :
-		   dev->caps.num_eqs;
+	num_eqs = dev->phys_caps.num_phys_eqs;
 	err = mlx4_init_icm_table(dev, &priv->eq_table.table,
 				  init_hca->eqc_base, dev_cap->eqc_entry_sz,
 				  num_eqs, num_eqs, 0, 0);
@@ -1719,6 +1743,19 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 			mlx4_err(dev, "INIT_HCA command failed, aborting\n");
 			goto err_free_icm;
 		}
+
+		if (dev_cap.flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS) {
+			err = mlx4_query_func(dev, &dev_cap);
+			if (err < 0) {
+				mlx4_err(dev, "QUERY_FUNC command failed, aborting.\n");
+				goto err_stop_fw;
+			} else if (err & MLX4_QUERY_FUNC_NUM_SYS_EQS) {
+				dev->caps.num_eqs = dev_cap.max_eqs;
+				dev->caps.reserved_eqs = dev_cap.reserved_eqs;
+				dev->caps.reserved_uars = dev_cap.reserved_uars;
+			}
+		}
+
 		/*
 		 * If TS is supported by FW
 		 * read HCA frequency by QUERY_HCA command
@@ -2085,12 +2122,11 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct msix_entry *entries;
-	int nreq = min_t(int, dev->caps.num_ports *
-			 min_t(int, num_online_cpus() + 1,
-			       MAX_MSIX_P_PORT) + MSIX_LEGACY_SZ, MAX_MSIX);
 	int i;
 
 	if (msi_x) {
+		int nreq = dev->caps.num_ports * num_online_cpus() + MSIX_LEGACY_SZ;
+
 		nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
 			     nreq);
 
@@ -2345,6 +2381,7 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 	int err;
 	int port;
 	int i;
+	struct mlx4_dev_cap *dev_cap = NULL;
 	int existing_vfs = 0;
 
 	dev = &priv->dev;
@@ -2381,15 +2418,6 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 			}
 		}
 
-		if (total_vfs) {
-			existing_vfs = pci_num_vf(pdev);
-			dev->flags = MLX4_FLAG_MASTER;
-			dev->flags = mlx4_enable_sriov(dev, pdev, total_vfs,
-						       existing_vfs);
-			if (!SRIOV_VALID_STATE(dev->flags))
-				goto err_sriov;
-		}
-
 		atomic_set(&priv->opreq_count, 0);
 		INIT_WORK(&priv->opreq_task, mlx4_opreq_action);
 
@@ -2403,6 +2431,12 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 			mlx4_err(dev, "Failed to reset HCA, aborting\n");
 			goto err_sriov;
 		}
+
+		if (total_vfs) {
+			existing_vfs = pci_num_vf(pdev);
+			dev->flags = MLX4_FLAG_MASTER;
+			dev->num_vfs = total_vfs;
+		}
 	}
 
 slave_start:
@@ -2416,9 +2450,10 @@ slave_start:
 	 * before posting commands. Also, init num_slaves before calling
 	 * mlx4_init_hca */
 	if (mlx4_is_mfunc(dev)) {
-		if (mlx4_is_master(dev))
+		if (mlx4_is_master(dev)) {
 			dev->num_slaves = MLX4_MAX_NUM_SLAVES;
-		else {
+
+		} else {
 			dev->num_slaves = 0;
 			err = mlx4_multi_func_init(dev);
 			if (err) {
@@ -2434,6 +2469,52 @@ slave_start:
 		goto err_mfunc;
 	}
 
+	if (mlx4_is_master(dev)) {
+		if (!dev_cap) {
+			dev_cap = kzalloc(sizeof(*dev_cap), GFP_KERNEL);
+
+			if (!dev_cap) {
+				err = -ENOMEM;
+				goto err_fw;
+			}
+
+			err = mlx4_QUERY_DEV_CAP(dev, dev_cap);
+			if (err) {
+				mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
+				goto err_fw;
+			}
+
+			if (!(dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS)) {
+				u64 dev_flags = mlx4_enable_sriov(dev, pdev, total_vfs,
+								  existing_vfs);
+
+				mlx4_cmd_cleanup(dev, MLX4_CMD_CLEANUP_ALL);
+				dev->flags = dev_flags;
+				if (!SRIOV_VALID_STATE(dev->flags)) {
+					mlx4_err(dev, "Invalid SRIOV state\n");
+					goto err_sriov;
+				}
+				err = mlx4_reset(dev);
+				if (err) {
+					mlx4_err(dev, "Failed to reset HCA, aborting.\n");
+					goto err_sriov;
+				}
+				goto slave_start;
+			}
+		} else {
+			/* Legacy mode FW requires SRIOV to be enabled before
+			 * doing QUERY_DEV_CAP, since max_eq's value is different if
+			 * SRIOV is enabled.
+			 */
+			memset(dev_cap, 0, sizeof(*dev_cap));
+			err = mlx4_QUERY_DEV_CAP(dev, dev_cap);
+			if (err) {
+				mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
+				goto err_fw;
+			}
+		}
+	}
+
 	err = mlx4_init_hca(dev);
 	if (err) {
 		if (err == -EACCES) {
@@ -2457,6 +2538,30 @@ slave_start:
 			goto err_fw;
 	}
 
+	if (mlx4_is_master(dev) && (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS)) {
+		u64 dev_flags = mlx4_enable_sriov(dev, pdev, total_vfs, existing_vfs);
+
+		if ((dev->flags ^ dev_flags) & (MLX4_FLAG_MASTER | MLX4_FLAG_SLAVE)) {
+			mlx4_cmd_cleanup(dev, MLX4_CMD_CLEANUP_VHCR);
+			dev->flags = dev_flags;
+			err = mlx4_cmd_init(dev);
+			if (err) {
+				/* Only VHCR is cleaned up, so could still
+				 * send FW commands
+				 */
+				mlx4_err(dev, "Failed to init VHCR command interface, aborting\n");
+				goto err_close;
+			}
+		} else {
+			dev->flags = dev_flags;
+		}
+
+		if (!SRIOV_VALID_STATE(dev->flags)) {
+			mlx4_err(dev, "Invalid SRIOV state\n");
+			goto err_close;
+		}
+	}
+
 	/* check if the device is functioning at its maximum possible speed.
 	 * No return code for this call, just warn the user in case of PCI
 	 * express device capabilities are under-satisfied by the bus.
@@ -2631,6 +2736,7 @@ err_sriov:
 	if (!mlx4_is_slave(dev))
 		mlx4_free_ownership(dev);
 
+	kfree(dev_cap);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c
index 14089d9e166..2bf437aafc5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/profile.c
+++ b/drivers/net/ethernet/mellanox/mlx4/profile.c
@@ -126,8 +126,7 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 	profile[MLX4_RES_AUXC].num    = request->num_qp;
 	profile[MLX4_RES_SRQ].num     = request->num_srq;
 	profile[MLX4_RES_CQ].num      = request->num_cq;
-	profile[MLX4_RES_EQ].num      = mlx4_is_mfunc(dev) ?
-					dev->phys_caps.num_phys_eqs :
+	profile[MLX4_RES_EQ].num = mlx4_is_mfunc(dev) ? dev->phys_caps.num_phys_eqs :
 					min_t(unsigned, dev_cap->max_eqs, MAX_MSIX);
 	profile[MLX4_RES_DMPT].num    = request->num_mpt;
 	profile[MLX4_RES_CMPT].num    = MLX4_NUM_CMPTS;
@@ -216,10 +215,18 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 			init_hca->log_num_cqs = profile[i].log_num;
 			break;
 		case MLX4_RES_EQ:
-			dev->caps.num_eqs     = roundup_pow_of_two(min_t(unsigned, dev_cap->max_eqs,
-									 MAX_MSIX));
-			init_hca->eqc_base    = profile[i].start;
-			init_hca->log_num_eqs = ilog2(dev->caps.num_eqs);
+			if (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS) {
+				init_hca->log_num_eqs = 0x1f;
+				init_hca->eqc_base    = profile[i].start;
+				init_hca->num_sys_eqs = dev_cap->num_sys_eqs;
+			} else {
+				dev->caps.num_eqs     = roundup_pow_of_two(
+								min_t(unsigned,
+								      dev_cap->max_eqs,
+								      MAX_MSIX));
+				init_hca->eqc_base    = profile[i].start;
+				init_hca->log_num_eqs = ilog2(dev->caps.num_eqs);
+			}
 			break;
 		case MLX4_RES_DMPT:
 			dev->caps.num_mpts	= profile[i].num;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 3d9bff00f24..1c560eb870a 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -189,7 +189,8 @@ enum {
 	MLX4_DEV_CAP_FLAG2_EQE_STRIDE		= 1LL <<  13,
 	MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL        = 1LL <<  14,
 	MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP	= 1LL <<  15,
-	MLX4_DEV_CAP_FLAG2_CONFIG_DEV		= 1LL <<  16
+	MLX4_DEV_CAP_FLAG2_CONFIG_DEV		= 1LL <<  16,
+	MLX4_DEV_CAP_FLAG2_SYS_EQS		= 1LL <<  17
 };
 
 enum {
@@ -443,6 +444,7 @@ struct mlx4_caps {
 	int			num_cqs;
 	int			max_cqes;
 	int			reserved_cqs;
+	int			num_sys_eqs;
 	int			num_eqs;
 	int			reserved_eqs;
 	int			num_comp_vectors;
-- 
cgit v1.2.3-70-g09d2


From de966c5928026b100a989c8cef761d306310a184 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 13 Nov 2014 14:45:33 +0200
Subject: net/mlx4_core: Support more than 64 VFs

We now allow up to 126 VFs. Note though that certain firmware
versions only allow up to 80 VFs. Moreover, old HCAs only support 64 VFs.
In these cases, we limit the maximum number of VFs to 64.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/fw.c   |  5 ++++-
 drivers/net/ethernet/mellanox/mlx4/main.c | 24 ++++++++++++++++++++++++
 include/linux/mlx4/device.h               |  5 +++--
 3 files changed, 31 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index d2f594fadfb..4251f81a027 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -143,7 +143,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[14] = "Ethernet protocol control support",
 		[15] = "Ethernet Backplane autoneg support",
 		[16] = "CONFIG DEV support",
-		[17] = "Asymmetric EQs support"
+		[17] = "Asymmetric EQs support",
+		[18] = "More than 80 VFs support"
 	};
 	int i;
 
@@ -860,6 +861,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_VLAN_CONTROL;
 	if (field32 & (1 << 20))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FSM;
+	if (field32 & (1 << 21))
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_80_VFS;
 
 	if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
 		for (i = 1; i <= dev_cap->num_ports; ++i) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index ebb279060a2..3044f9e623c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2373,6 +2373,24 @@ disable_sriov:
 	return dev_flags & ~MLX4_FLAG_MASTER;
 }
 
+enum {
+	MLX4_DEV_CAP_CHECK_NUM_VFS_ABOVE_64 = -1,
+};
+
+static int mlx4_check_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
+			      int *nvfs)
+{
+	int requested_vfs = nvfs[0] + nvfs[1] + nvfs[2];
+	/* Checking for 64 VFs as a limitation of CX2 */
+	if (!(dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_80_VFS) &&
+	    requested_vfs >= 64) {
+		mlx4_err(dev, "Requested %d VFs, but FW does not support more than 64\n",
+			 requested_vfs);
+		return MLX4_DEV_CAP_CHECK_NUM_VFS_ABOVE_64;
+	}
+	return 0;
+}
+
 static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 			 int total_vfs, int *nvfs, struct mlx4_priv *priv)
 {
@@ -2484,6 +2502,9 @@ slave_start:
 				goto err_fw;
 			}
 
+			if (mlx4_check_dev_cap(dev, dev_cap, nvfs))
+				goto err_fw;
+
 			if (!(dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS)) {
 				u64 dev_flags = mlx4_enable_sriov(dev, pdev, total_vfs,
 								  existing_vfs);
@@ -2512,6 +2533,9 @@ slave_start:
 				mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
 				goto err_fw;
 			}
+
+			if (mlx4_check_dev_cap(dev, dev_cap, nvfs))
+				goto err_fw;
 		}
 	}
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 1c560eb870a..cf09e65c290 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -95,7 +95,7 @@ enum {
 
 enum {
 	MLX4_MAX_NUM_PF		= 16,
-	MLX4_MAX_NUM_VF		= 64,
+	MLX4_MAX_NUM_VF		= 126,
 	MLX4_MAX_NUM_VF_P_PORT  = 64,
 	MLX4_MFUNC_MAX		= 80,
 	MLX4_MAX_EQ_NUM		= 1024,
@@ -190,7 +190,8 @@ enum {
 	MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL        = 1LL <<  14,
 	MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP	= 1LL <<  15,
 	MLX4_DEV_CAP_FLAG2_CONFIG_DEV		= 1LL <<  16,
-	MLX4_DEV_CAP_FLAG2_SYS_EQS		= 1LL <<  17
+	MLX4_DEV_CAP_FLAG2_SYS_EQS		= 1LL <<  17,
+	MLX4_DEV_CAP_FLAG2_80_VFS		= 1LL <<  18
 };
 
 enum {
-- 
cgit v1.2.3-70-g09d2


From 6eba82248ef47fd478f940a418429e3ec95cb3db Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Thu, 13 Nov 2014 13:45:46 +0100
Subject: rhashtable: Drop gfp_flags arg in insert/remove functions

Reallocation is only required for shrinking and expanding and both rely
on a mutex for synchronization and callers of rhashtable_init() are in
non atomic context. Therefore, no reason to continue passing allocation
hints through the API.

Instead, use GFP_KERNEL and add __GFP_NOWARN | __GFP_NORETRY to allow
for silent fall back to vzalloc() without the OOM killer jumping in as
pointed out by Eric Dumazet and Eric W. Biederman.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 10 +++++-----
 lib/rhashtable.c           | 41 +++++++++++++++++------------------------
 net/netfilter/nft_hash.c   |  4 ++--
 net/netlink/af_netlink.c   |  4 ++--
 4 files changed, 26 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 473e26bdb91..b93fd89b2e5 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -99,16 +99,16 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params);
 u32 rhashtable_hashfn(const struct rhashtable *ht, const void *key, u32 len);
 u32 rhashtable_obj_hashfn(const struct rhashtable *ht, void *ptr);
 
-void rhashtable_insert(struct rhashtable *ht, struct rhash_head *node, gfp_t);
-bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node, gfp_t);
+void rhashtable_insert(struct rhashtable *ht, struct rhash_head *node);
+bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node);
 void rhashtable_remove_pprev(struct rhashtable *ht, struct rhash_head *obj,
-			     struct rhash_head __rcu **pprev, gfp_t flags);
+			     struct rhash_head __rcu **pprev);
 
 bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size);
 bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size);
 
-int rhashtable_expand(struct rhashtable *ht, gfp_t flags);
-int rhashtable_shrink(struct rhashtable *ht, gfp_t flags);
+int rhashtable_expand(struct rhashtable *ht);
+int rhashtable_shrink(struct rhashtable *ht);
 
 void *rhashtable_lookup(const struct rhashtable *ht, const void *key);
 void *rhashtable_lookup_compare(const struct rhashtable *ht, u32 hash,
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 4b4b53bfa08..25e4c213b08 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -107,13 +107,13 @@ static u32 head_hashfn(const struct rhashtable *ht,
 	return obj_hashfn(ht, rht_obj(ht, he), hsize);
 }
 
-static struct bucket_table *bucket_table_alloc(size_t nbuckets, gfp_t flags)
+static struct bucket_table *bucket_table_alloc(size_t nbuckets)
 {
 	struct bucket_table *tbl;
 	size_t size;
 
 	size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]);
-	tbl = kzalloc(size, flags);
+	tbl = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
 	if (tbl == NULL)
 		tbl = vzalloc(size);
 
@@ -200,7 +200,6 @@ static void hashtable_chain_unzip(const struct rhashtable *ht,
 /**
  * rhashtable_expand - Expand hash table while allowing concurrent lookups
  * @ht:		the hash table to expand
- * @flags:	allocation flags
  *
  * A secondary bucket array is allocated and the hash entries are migrated
  * while keeping them on both lists until the end of the RCU grace period.
@@ -211,7 +210,7 @@ static void hashtable_chain_unzip(const struct rhashtable *ht,
  * The caller must ensure that no concurrent table mutations take place.
  * It is however valid to have concurrent lookups if they are RCU protected.
  */
-int rhashtable_expand(struct rhashtable *ht, gfp_t flags)
+int rhashtable_expand(struct rhashtable *ht)
 {
 	struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht);
 	struct rhash_head *he;
@@ -223,7 +222,7 @@ int rhashtable_expand(struct rhashtable *ht, gfp_t flags)
 	if (ht->p.max_shift && ht->shift >= ht->p.max_shift)
 		return 0;
 
-	new_tbl = bucket_table_alloc(old_tbl->size * 2, flags);
+	new_tbl = bucket_table_alloc(old_tbl->size * 2);
 	if (new_tbl == NULL)
 		return -ENOMEM;
 
@@ -281,7 +280,6 @@ EXPORT_SYMBOL_GPL(rhashtable_expand);
 /**
  * rhashtable_shrink - Shrink hash table while allowing concurrent lookups
  * @ht:		the hash table to shrink
- * @flags:	allocation flags
  *
  * This function may only be called in a context where it is safe to call
  * synchronize_rcu(), e.g. not within a rcu_read_lock() section.
@@ -289,7 +287,7 @@ EXPORT_SYMBOL_GPL(rhashtable_expand);
  * The caller must ensure that no concurrent table mutations take place.
  * It is however valid to have concurrent lookups if they are RCU protected.
  */
-int rhashtable_shrink(struct rhashtable *ht, gfp_t flags)
+int rhashtable_shrink(struct rhashtable *ht)
 {
 	struct bucket_table *ntbl, *tbl = rht_dereference(ht->tbl, ht);
 	struct rhash_head __rcu **pprev;
@@ -300,7 +298,7 @@ int rhashtable_shrink(struct rhashtable *ht, gfp_t flags)
 	if (ht->shift <= ht->p.min_shift)
 		return 0;
 
-	ntbl = bucket_table_alloc(tbl->size / 2, flags);
+	ntbl = bucket_table_alloc(tbl->size / 2);
 	if (ntbl == NULL)
 		return -ENOMEM;
 
@@ -341,7 +339,6 @@ EXPORT_SYMBOL_GPL(rhashtable_shrink);
  * rhashtable_insert - insert object into hash hash table
  * @ht:		hash table
  * @obj:	pointer to hash head inside object
- * @flags:	allocation flags (table expansion)
  *
  * Will automatically grow the table via rhashtable_expand() if the the
  * grow_decision function specified at rhashtable_init() returns true.
@@ -349,8 +346,7 @@ EXPORT_SYMBOL_GPL(rhashtable_shrink);
  * The caller must ensure that no concurrent table mutations occur. It is
  * however valid to have concurrent lookups if they are RCU protected.
  */
-void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj,
-		       gfp_t flags)
+void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj)
 {
 	struct bucket_table *tbl = rht_dereference(ht->tbl, ht);
 	u32 hash;
@@ -363,7 +359,7 @@ void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj,
 	ht->nelems++;
 
 	if (ht->p.grow_decision && ht->p.grow_decision(ht, tbl->size))
-		rhashtable_expand(ht, flags);
+		rhashtable_expand(ht);
 }
 EXPORT_SYMBOL_GPL(rhashtable_insert);
 
@@ -372,14 +368,13 @@ EXPORT_SYMBOL_GPL(rhashtable_insert);
  * @ht:		hash table
  * @obj:	pointer to hash head inside object
  * @pprev:	pointer to previous element
- * @flags:	allocation flags (table expansion)
  *
  * Identical to rhashtable_remove() but caller is alreayd aware of the element
  * in front of the element to be deleted. This is in particular useful for
  * deletion when combined with walking or lookup.
  */
 void rhashtable_remove_pprev(struct rhashtable *ht, struct rhash_head *obj,
-			     struct rhash_head __rcu **pprev, gfp_t flags)
+			     struct rhash_head __rcu **pprev)
 {
 	struct bucket_table *tbl = rht_dereference(ht->tbl, ht);
 
@@ -390,7 +385,7 @@ void rhashtable_remove_pprev(struct rhashtable *ht, struct rhash_head *obj,
 
 	if (ht->p.shrink_decision &&
 	    ht->p.shrink_decision(ht, tbl->size))
-		rhashtable_shrink(ht, flags);
+		rhashtable_shrink(ht);
 }
 EXPORT_SYMBOL_GPL(rhashtable_remove_pprev);
 
@@ -398,7 +393,6 @@ EXPORT_SYMBOL_GPL(rhashtable_remove_pprev);
  * rhashtable_remove - remove object from hash table
  * @ht:		hash table
  * @obj:	pointer to hash head inside object
- * @flags:	allocation flags (table expansion)
  *
  * Since the hash chain is single linked, the removal operation needs to
  * walk the bucket chain upon removal. The removal operation is thus
@@ -410,8 +404,7 @@ EXPORT_SYMBOL_GPL(rhashtable_remove_pprev);
  * The caller must ensure that no concurrent table mutations occur. It is
  * however valid to have concurrent lookups if they are RCU protected.
  */
-bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *obj,
-		       gfp_t flags)
+bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *obj)
 {
 	struct bucket_table *tbl = rht_dereference(ht->tbl, ht);
 	struct rhash_head __rcu **pprev;
@@ -429,7 +422,7 @@ bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *obj,
 			continue;
 		}
 
-		rhashtable_remove_pprev(ht, he, pprev, flags);
+		rhashtable_remove_pprev(ht, he, pprev);
 		return true;
 	}
 
@@ -576,7 +569,7 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params)
 	if (params->nelem_hint)
 		size = rounded_hashtable_size(params);
 
-	tbl = bucket_table_alloc(size, GFP_KERNEL);
+	tbl = bucket_table_alloc(size);
 	if (tbl == NULL)
 		return -ENOMEM;
 
@@ -713,7 +706,7 @@ static int __init test_rhashtable(struct rhashtable *ht)
 		obj->ptr = TEST_PTR;
 		obj->value = i * 2;
 
-		rhashtable_insert(ht, &obj->node, GFP_KERNEL);
+		rhashtable_insert(ht, &obj->node);
 	}
 
 	rcu_read_lock();
@@ -724,7 +717,7 @@ static int __init test_rhashtable(struct rhashtable *ht)
 
 	for (i = 0; i < TEST_NEXPANDS; i++) {
 		pr_info("  Table expansion iteration %u...\n", i);
-		rhashtable_expand(ht, GFP_KERNEL);
+		rhashtable_expand(ht);
 
 		rcu_read_lock();
 		pr_info("  Verifying lookups...\n");
@@ -734,7 +727,7 @@ static int __init test_rhashtable(struct rhashtable *ht)
 
 	for (i = 0; i < TEST_NEXPANDS; i++) {
 		pr_info("  Table shrinkage iteration %u...\n", i);
-		rhashtable_shrink(ht, GFP_KERNEL);
+		rhashtable_shrink(ht);
 
 		rcu_read_lock();
 		pr_info("  Verifying lookups...\n");
@@ -749,7 +742,7 @@ static int __init test_rhashtable(struct rhashtable *ht)
 		obj = rhashtable_lookup(ht, &key);
 		BUG_ON(!obj);
 
-		rhashtable_remove(ht, &obj->node, GFP_KERNEL);
+		rhashtable_remove(ht, &obj->node);
 		kfree(obj);
 	}
 
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 3f75aaaf9d0..1e316ce4cb5 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -65,7 +65,7 @@ static int nft_hash_insert(const struct nft_set *set,
 	if (set->flags & NFT_SET_MAP)
 		nft_data_copy(he->data, &elem->data);
 
-	rhashtable_insert(priv, &he->node, GFP_KERNEL);
+	rhashtable_insert(priv, &he->node);
 
 	return 0;
 }
@@ -88,7 +88,7 @@ static void nft_hash_remove(const struct nft_set *set,
 	pprev = elem->cookie;
 	he = rht_dereference((*pprev), priv);
 
-	rhashtable_remove_pprev(priv, he, pprev, GFP_KERNEL);
+	rhashtable_remove_pprev(priv, he, pprev);
 
 	synchronize_rcu();
 	kfree(he);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 9e0628cfdf6..a491c1a4861 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1092,7 +1092,7 @@ static int netlink_insert(struct sock *sk, struct net *net, u32 portid)
 
 	nlk_sk(sk)->portid = portid;
 	sock_hold(sk);
-	rhashtable_insert(&table->hash, &nlk_sk(sk)->node, GFP_KERNEL);
+	rhashtable_insert(&table->hash, &nlk_sk(sk)->node);
 	err = 0;
 err:
 	mutex_unlock(&nl_sk_hash_lock);
@@ -1105,7 +1105,7 @@ static void netlink_remove(struct sock *sk)
 
 	mutex_lock(&nl_sk_hash_lock);
 	table = &nl_table[sk->sk_protocol];
-	if (rhashtable_remove(&table->hash, &nlk_sk(sk)->node, GFP_KERNEL)) {
+	if (rhashtable_remove(&table->hash, &nlk_sk(sk)->node)) {
 		WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
 		__sock_put(sk);
 	}
-- 
cgit v1.2.3-70-g09d2


From f30c59e921f12b209852e1ddc197dc6a8fb0142b Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Wed, 5 Nov 2014 21:57:40 +0530
Subject: mm: Update generic gup implementation to handle hugepage directory

Update generic gup implementation with powerpc specific details.
On powerpc at pmd level we can have hugepte, normal pmd pointer
or a pointer to the hugepage directory.

Tested-by: Steve Capper <steve.capper@linaro.org>
Acked-by: Steve Capper <steve.capper@linaro.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/page.h |  1 +
 include/linux/hugetlb.h         | 46 +++++++++++++++++++++++
 mm/gup.c                        | 81 +++++++++++++++++++++++++++++++++++++----
 3 files changed, 120 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 26fe1ae1521..f973fce73a4 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -380,6 +380,7 @@ static inline int hugepd_ok(hugepd_t hpd)
 #endif
 
 #define is_hugepd(pdep)               (hugepd_ok(*((hugepd_t *)(pdep))))
+#define pgd_huge pgd_huge
 int pgd_huge(pgd_t pgd);
 #else /* CONFIG_HUGETLB_PAGE */
 #define is_hugepd(pdep)			0
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 6e6d338641f..e6b62f30ab2 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -175,6 +175,52 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
 }
 
 #endif /* !CONFIG_HUGETLB_PAGE */
+/*
+ * hugepages at page global directory. If arch support
+ * hugepages at pgd level, they need to define this.
+ */
+#ifndef pgd_huge
+#define pgd_huge(x)	0
+#endif
+
+#ifndef pgd_write
+static inline int pgd_write(pgd_t pgd)
+{
+	BUG();
+	return 0;
+}
+#endif
+
+#ifndef pud_write
+static inline int pud_write(pud_t pud)
+{
+	BUG();
+	return 0;
+}
+#endif
+
+#ifndef is_hugepd
+/*
+ * Some architectures requires a hugepage directory format that is
+ * required to support multiple hugepage sizes. For example
+ * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
+ * introduced the same on powerpc. This allows for a more flexible hugepage
+ * pagetable layout.
+ */
+typedef struct { unsigned long pd; } hugepd_t;
+#define is_hugepd(hugepd) (0)
+#define __hugepd(x) ((hugepd_t) { (x) })
+static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+			      unsigned pdshift, unsigned long end,
+			      int write, struct page **pages, int *nr)
+{
+	return 0;
+}
+#else
+extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+		       unsigned pdshift, unsigned long end,
+		       int write, struct page **pages, int *nr);
+#endif
 
 #define HUGETLB_ANON_FILE "anon_hugepage"
 
diff --git a/mm/gup.c b/mm/gup.c
index cd62c8c90d4..0ca1df9075a 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -3,7 +3,6 @@
 #include <linux/err.h>
 #include <linux/spinlock.h>
 
-#include <linux/hugetlb.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
@@ -12,6 +11,7 @@
 
 #include <linux/sched.h>
 #include <linux/rwsem.h>
+#include <linux/hugetlb.h>
 #include <asm/pgtable.h>
 
 #include "internal.h"
@@ -875,6 +875,49 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 	return 1;
 }
 
+static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
+			unsigned long end, int write,
+			struct page **pages, int *nr)
+{
+	int refs;
+	struct page *head, *page, *tail;
+
+	if (write && !pgd_write(orig))
+		return 0;
+
+	refs = 0;
+	head = pgd_page(orig);
+	page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
+	tail = page;
+	do {
+		VM_BUG_ON_PAGE(compound_head(page) != head, page);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	if (!page_cache_add_speculative(head, refs)) {
+		*nr -= refs;
+		return 0;
+	}
+
+	if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+
+	while (refs--) {
+		if (PageTail(tail))
+			get_huge_page_tail(tail);
+		tail++;
+	}
+
+	return 1;
+}
+
 static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		int write, struct page **pages, int *nr)
 {
@@ -902,6 +945,14 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 				pages, nr))
 				return 0;
 
+		} else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) {
+			/*
+			 * architecture have different format for hugetlbfs
+			 * pmd format and THP pmd format
+			 */
+			if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr,
+					 PMD_SHIFT, next, write, pages, nr))
+				return 0;
 		} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
 				return 0;
 	} while (pmdp++, addr = next, addr != end);
@@ -909,22 +960,26 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 	return 1;
 }
 
-static int gup_pud_range(pgd_t *pgdp, unsigned long addr, unsigned long end,
-		int write, struct page **pages, int *nr)
+static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+			 int write, struct page **pages, int *nr)
 {
 	unsigned long next;
 	pud_t *pudp;
 
-	pudp = pud_offset(pgdp, addr);
+	pudp = pud_offset(&pgd, addr);
 	do {
 		pud_t pud = ACCESS_ONCE(*pudp);
 
 		next = pud_addr_end(addr, end);
 		if (pud_none(pud))
 			return 0;
-		if (pud_huge(pud)) {
+		if (unlikely(pud_huge(pud))) {
 			if (!gup_huge_pud(pud, pudp, addr, next, write,
-					pages, nr))
+					  pages, nr))
+				return 0;
+		} else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) {
+			if (!gup_huge_pd(__hugepd(pud_val(pud)), addr,
+					 PUD_SHIFT, next, write, pages, nr))
 				return 0;
 		} else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
 			return 0;
@@ -970,10 +1025,20 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	local_irq_save(flags);
 	pgdp = pgd_offset(mm, addr);
 	do {
+		pgd_t pgd = ACCESS_ONCE(*pgdp);
+
 		next = pgd_addr_end(addr, end);
-		if (pgd_none(*pgdp))
+		if (pgd_none(pgd))
 			break;
-		else if (!gup_pud_range(pgdp, addr, next, write, pages, &nr))
+		if (unlikely(pgd_huge(pgd))) {
+			if (!gup_huge_pgd(pgd, pgdp, addr, next, write,
+					  pages, &nr))
+				break;
+		} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
+			if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
+					 PGDIR_SHIFT, next, write, pages, &nr))
+				break;
+		} else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
 			break;
 	} while (pgdp++, addr = next, addr != end);
 	local_irq_restore(flags);
-- 
cgit v1.2.3-70-g09d2


From 6d09dc6b74caaca83e32e67f2454406041d58fb0 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 14 Nov 2014 13:26:52 +0100
Subject: of.h: Keep extern declaration of of_* variables when !CONFIG_OF

Keep the extern declaration of of_allnodes and friends, when building without
of support, this way code using them can be written like this:

	if (IS_ENABLED(CONFIG_OF_PLATFORM) && of_chosen) {
		for_each_child_of_node(of_chosen, np)
			...
	}

And rely on the compiler optimizing it away, avoiding the need for #ifdef-ery.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 include/linux/of.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/of.h b/include/linux/of.h
index 6545e7aec7b..f83ca9dddcb 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -105,8 +105,6 @@ static inline struct device_node *of_node_get(struct device_node *node)
 static inline void of_node_put(struct device_node *node) { }
 #endif /* !CONFIG_OF_DYNAMIC */
 
-#ifdef CONFIG_OF
-
 /* Pointer for first entry in chain of all nodes. */
 extern struct device_node *of_allnodes;
 extern struct device_node *of_chosen;
@@ -114,6 +112,7 @@ extern struct device_node *of_aliases;
 extern struct device_node *of_stdout;
 extern raw_spinlock_t devtree_lock;
 
+#ifdef CONFIG_OF
 static inline bool of_have_populated_dt(void)
 {
 	return of_allnodes != NULL;
-- 
cgit v1.2.3-70-g09d2


From a720b41c41f5a7e4c51558cf087882c57331581f Mon Sep 17 00:00:00 2001
From: Antonios Motakis <a.motakis@virtualopensystems.com>
Date: Mon, 13 Oct 2014 14:06:16 +0100
Subject: iommu/arm-smmu: change IOMMU_EXEC to IOMMU_NOEXEC

Exposing the XN flag of the SMMU driver as IOMMU_NOEXEC instead of
IOMMU_EXEC makes it enforceable, since for IOMMUs that don't support
the XN flag pages will always be executable.

Signed-off-by: Antonios Motakis <a.motakis@virtualopensystems.com>
Acked-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 drivers/iommu/arm-smmu.c | 9 +++++----
 include/linux/iommu.h    | 2 +-
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 60558f79492..566c1769d9b 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1281,7 +1281,7 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
 				   unsigned long pfn, int prot, int stage)
 {
 	pte_t *pte, *start;
-	pteval_t pteval = ARM_SMMU_PTE_PAGE | ARM_SMMU_PTE_AF | ARM_SMMU_PTE_XN;
+	pteval_t pteval = ARM_SMMU_PTE_PAGE | ARM_SMMU_PTE_AF;
 
 	if (pmd_none(*pmd)) {
 		/* Allocate a new set of tables */
@@ -1315,10 +1315,11 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
 			pteval |= ARM_SMMU_PTE_MEMATTR_NC;
 	}
 
+	if (prot & IOMMU_NOEXEC)
+		pteval |= ARM_SMMU_PTE_XN;
+
 	/* If no access, create a faulting entry to avoid TLB fills */
-	if (prot & IOMMU_EXEC)
-		pteval &= ~ARM_SMMU_PTE_XN;
-	else if (!(prot & (IOMMU_READ | IOMMU_WRITE)))
+	if (!(prot & (IOMMU_READ | IOMMU_WRITE)))
 		pteval &= ~ARM_SMMU_PTE_PAGE;
 
 	pteval |= ARM_SMMU_PTE_SH_IS;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index e6a7c9ff72f..f47383a05d3 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -27,7 +27,7 @@
 #define IOMMU_READ	(1 << 0)
 #define IOMMU_WRITE	(1 << 1)
 #define IOMMU_CACHE	(1 << 2) /* DMA cache coherency */
-#define IOMMU_EXEC	(1 << 3)
+#define IOMMU_NOEXEC	(1 << 3)
 
 struct iommu_ops;
 struct iommu_group;
-- 
cgit v1.2.3-70-g09d2


From c49866493b1ffb7c0a7963a1e3c0094e78760184 Mon Sep 17 00:00:00 2001
From: Antonios Motakis <a.motakis@virtualopensystems.com>
Date: Mon, 13 Oct 2014 14:06:17 +0100
Subject: iommu: add capability IOMMU_CAP_NOEXEC

Some IOMMUs accept an IOMMU_NOEXEC protection flag in addition to
IOMMU_READ and IOMMU_WRITE. Expose this as an IOMMU capability.

Signed-off-by: Antonios Motakis <a.motakis@virtualopensystems.com>
Acked-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 include/linux/iommu.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index f47383a05d3..e438b30f062 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -61,6 +61,7 @@ enum iommu_cap {
 	IOMMU_CAP_CACHE_COHERENCY,	/* IOMMU can enforce cache coherent DMA
 					   transactions */
 	IOMMU_CAP_INTR_REMAP,		/* IOMMU supports interrupt isolation */
+	IOMMU_CAP_NOEXEC,		/* IOMMU_NOEXEC flag */
 };
 
 /*
-- 
cgit v1.2.3-70-g09d2


From edcf58bc031e621f519c9dfce3c7e1ea6880c70a Mon Sep 17 00:00:00 2001
From: Boris BREZILLON <boris.brezillon@free-electrons.com>
Date: Mon, 10 Nov 2014 14:28:26 -0300
Subject: [media] Move mediabus format definition to a more standard place

Define MEDIA_BUS_FMT macros (re-using the values defined in the
v4l2_mbus_pixelcode enum) into a separate header file so that they can be
used from the DRM/KMS subsystem without any reference to the V4L2
subsystem.

Then set V4L2_MBUS_FMT definitions to the MEDIA_BUS_FMT values using the
V4L2_MBUS_FROM_MEDIA_BUS_FMT macro.

Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Acked-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/uapi/linux/Kbuild             |   1 +
 include/uapi/linux/media-bus-format.h | 125 +++++++++++++++++++++++
 include/uapi/linux/v4l2-mediabus.h    | 184 +++++++++++++++-------------------
 3 files changed, 206 insertions(+), 104 deletions(-)
 create mode 100644 include/uapi/linux/media-bus-format.h

(limited to 'include')

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index b70237e8bc3..ed39ac84c0f 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -241,6 +241,7 @@ header-y += map_to_7segment.h
 header-y += matroxfb.h
 header-y += mdio.h
 header-y += media.h
+header-y += media-bus-format.h
 header-y += mei.h
 header-y += memfd.h
 header-y += mempolicy.h
diff --git a/include/uapi/linux/media-bus-format.h b/include/uapi/linux/media-bus-format.h
new file mode 100644
index 00000000000..23b40908be3
--- /dev/null
+++ b/include/uapi/linux/media-bus-format.h
@@ -0,0 +1,125 @@
+/*
+ * Media Bus API header
+ *
+ * Copyright (C) 2009, Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_MEDIA_BUS_FORMAT_H
+#define __LINUX_MEDIA_BUS_FORMAT_H
+
+/*
+ * These bus formats uniquely identify data formats on the data bus. Format 0
+ * is reserved, MEDIA_BUS_FMT_FIXED shall be used by host-client pairs, where
+ * the data format is fixed. Additionally, "2X8" means that one pixel is
+ * transferred in two 8-bit samples, "BE" or "LE" specify in which order those
+ * samples are transferred over the bus: "LE" means that the least significant
+ * bits are transferred first, "BE" means that the most significant bits are
+ * transferred first, and "PADHI" and "PADLO" define which bits - low or high,
+ * in the incomplete high byte, are filled with padding bits.
+ *
+ * The bus formats are grouped by type, bus_width, bits per component, samples
+ * per pixel and order of subsamples. Numerical values are sorted using generic
+ * numerical sort order (8 thus comes before 10).
+ *
+ * As their value can't change when a new bus format is inserted in the
+ * enumeration, the bus formats are explicitly given a numerical value. The next
+ * free values for each category are listed below, update them when inserting
+ * new pixel codes.
+ */
+
+#define MEDIA_BUS_FMT_FIXED			0x0001
+
+/* RGB - next is	0x100e */
+#define MEDIA_BUS_FMT_RGB444_2X8_PADHI_BE	0x1001
+#define MEDIA_BUS_FMT_RGB444_2X8_PADHI_LE	0x1002
+#define MEDIA_BUS_FMT_RGB555_2X8_PADHI_BE	0x1003
+#define MEDIA_BUS_FMT_RGB555_2X8_PADHI_LE	0x1004
+#define MEDIA_BUS_FMT_BGR565_2X8_BE		0x1005
+#define MEDIA_BUS_FMT_BGR565_2X8_LE		0x1006
+#define MEDIA_BUS_FMT_RGB565_2X8_BE		0x1007
+#define MEDIA_BUS_FMT_RGB565_2X8_LE		0x1008
+#define MEDIA_BUS_FMT_RGB666_1X18		0x1009
+#define MEDIA_BUS_FMT_RGB888_1X24		0x100a
+#define MEDIA_BUS_FMT_RGB888_2X12_BE		0x100b
+#define MEDIA_BUS_FMT_RGB888_2X12_LE		0x100c
+#define MEDIA_BUS_FMT_ARGB8888_1X32		0x100d
+
+/* YUV (including grey) - next is	0x2024 */
+#define MEDIA_BUS_FMT_Y8_1X8			0x2001
+#define MEDIA_BUS_FMT_UV8_1X8			0x2015
+#define MEDIA_BUS_FMT_UYVY8_1_5X8		0x2002
+#define MEDIA_BUS_FMT_VYUY8_1_5X8		0x2003
+#define MEDIA_BUS_FMT_YUYV8_1_5X8		0x2004
+#define MEDIA_BUS_FMT_YVYU8_1_5X8		0x2005
+#define MEDIA_BUS_FMT_UYVY8_2X8			0x2006
+#define MEDIA_BUS_FMT_VYUY8_2X8			0x2007
+#define MEDIA_BUS_FMT_YUYV8_2X8			0x2008
+#define MEDIA_BUS_FMT_YVYU8_2X8			0x2009
+#define MEDIA_BUS_FMT_Y10_1X10			0x200a
+#define MEDIA_BUS_FMT_UYVY10_2X10		0x2018
+#define MEDIA_BUS_FMT_VYUY10_2X10		0x2019
+#define MEDIA_BUS_FMT_YUYV10_2X10		0x200b
+#define MEDIA_BUS_FMT_YVYU10_2X10		0x200c
+#define MEDIA_BUS_FMT_Y12_1X12			0x2013
+#define MEDIA_BUS_FMT_UYVY8_1X16		0x200f
+#define MEDIA_BUS_FMT_VYUY8_1X16		0x2010
+#define MEDIA_BUS_FMT_YUYV8_1X16		0x2011
+#define MEDIA_BUS_FMT_YVYU8_1X16		0x2012
+#define MEDIA_BUS_FMT_YDYUYDYV8_1X16		0x2014
+#define MEDIA_BUS_FMT_UYVY10_1X20		0x201a
+#define MEDIA_BUS_FMT_VYUY10_1X20		0x201b
+#define MEDIA_BUS_FMT_YUYV10_1X20		0x200d
+#define MEDIA_BUS_FMT_YVYU10_1X20		0x200e
+#define MEDIA_BUS_FMT_YUV10_1X30		0x2016
+#define MEDIA_BUS_FMT_AYUV8_1X32		0x2017
+#define MEDIA_BUS_FMT_UYVY12_2X12		0x201c
+#define MEDIA_BUS_FMT_VYUY12_2X12		0x201d
+#define MEDIA_BUS_FMT_YUYV12_2X12		0x201e
+#define MEDIA_BUS_FMT_YVYU12_2X12		0x201f
+#define MEDIA_BUS_FMT_UYVY12_1X24		0x2020
+#define MEDIA_BUS_FMT_VYUY12_1X24		0x2021
+#define MEDIA_BUS_FMT_YUYV12_1X24		0x2022
+#define MEDIA_BUS_FMT_YVYU12_1X24		0x2023
+
+/* Bayer - next is	0x3019 */
+#define MEDIA_BUS_FMT_SBGGR8_1X8		0x3001
+#define MEDIA_BUS_FMT_SGBRG8_1X8		0x3013
+#define MEDIA_BUS_FMT_SGRBG8_1X8		0x3002
+#define MEDIA_BUS_FMT_SRGGB8_1X8		0x3014
+#define MEDIA_BUS_FMT_SBGGR10_ALAW8_1X8		0x3015
+#define MEDIA_BUS_FMT_SGBRG10_ALAW8_1X8		0x3016
+#define MEDIA_BUS_FMT_SGRBG10_ALAW8_1X8		0x3017
+#define MEDIA_BUS_FMT_SRGGB10_ALAW8_1X8		0x3018
+#define MEDIA_BUS_FMT_SBGGR10_DPCM8_1X8		0x300b
+#define MEDIA_BUS_FMT_SGBRG10_DPCM8_1X8		0x300c
+#define MEDIA_BUS_FMT_SGRBG10_DPCM8_1X8		0x3009
+#define MEDIA_BUS_FMT_SRGGB10_DPCM8_1X8		0x300d
+#define MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_BE	0x3003
+#define MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE	0x3004
+#define MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_BE	0x3005
+#define MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_LE	0x3006
+#define MEDIA_BUS_FMT_SBGGR10_1X10		0x3007
+#define MEDIA_BUS_FMT_SGBRG10_1X10		0x300e
+#define MEDIA_BUS_FMT_SGRBG10_1X10		0x300a
+#define MEDIA_BUS_FMT_SRGGB10_1X10		0x300f
+#define MEDIA_BUS_FMT_SBGGR12_1X12		0x3008
+#define MEDIA_BUS_FMT_SGBRG12_1X12		0x3010
+#define MEDIA_BUS_FMT_SGRBG12_1X12		0x3011
+#define MEDIA_BUS_FMT_SRGGB12_1X12		0x3012
+
+/* JPEG compressed formats - next is	0x4002 */
+#define MEDIA_BUS_FMT_JPEG_1X8			0x4001
+
+/* Vendor specific formats - next is	0x5002 */
+
+/* S5C73M3 sensor specific interleaved UYVY and JPEG */
+#define MEDIA_BUS_FMT_S5C_UYVY_JPEG_1X8		0x5001
+
+/* HSV - next is	0x6002 */
+#define MEDIA_BUS_FMT_AHSV8888_1X32		0x6001
+
+#endif /* __LINUX_MEDIA_BUS_FORMAT_H */
diff --git a/include/uapi/linux/v4l2-mediabus.h b/include/uapi/linux/v4l2-mediabus.h
index 1445e858854..26180844c6b 100644
--- a/include/uapi/linux/v4l2-mediabus.h
+++ b/include/uapi/linux/v4l2-mediabus.h
@@ -11,120 +11,96 @@
 #ifndef __LINUX_V4L2_MEDIABUS_H
 #define __LINUX_V4L2_MEDIABUS_H
 
+#include <linux/media-bus-format.h>
 #include <linux/types.h>
 #include <linux/videodev2.h>
 
-/*
- * These pixel codes uniquely identify data formats on the media bus. Mostly
- * they correspond to similarly named V4L2_PIX_FMT_* formats, format 0 is
- * reserved, V4L2_MBUS_FMT_FIXED shall be used by host-client pairs, where the
- * data format is fixed. Additionally, "2X8" means that one pixel is transferred
- * in two 8-bit samples, "BE" or "LE" specify in which order those samples are
- * transferred over the bus: "LE" means that the least significant bits are
- * transferred first, "BE" means that the most significant bits are transferred
- * first, and "PADHI" and "PADLO" define which bits - low or high, in the
- * incomplete high byte, are filled with padding bits.
- *
- * The pixel codes are grouped by type, bus_width, bits per component, samples
- * per pixel and order of subsamples. Numerical values are sorted using generic
- * numerical sort order (8 thus comes before 10).
- *
- * As their value can't change when a new pixel code is inserted in the
- * enumeration, the pixel codes are explicitly given a numerical value. The next
- * free values for each category are listed below, update them when inserting
- * new pixel codes.
- */
-enum v4l2_mbus_pixelcode {
-	V4L2_MBUS_FMT_FIXED = 0x0001,
+#define V4L2_MBUS_FROM_MEDIA_BUS_FMT(name)	\
+	V4L2_MBUS_FMT_ ## name = MEDIA_BUS_FMT_ ## name
 
-	/* RGB - next is 0x100e */
-	V4L2_MBUS_FMT_RGB444_2X8_PADHI_BE = 0x1001,
-	V4L2_MBUS_FMT_RGB444_2X8_PADHI_LE = 0x1002,
-	V4L2_MBUS_FMT_RGB555_2X8_PADHI_BE = 0x1003,
-	V4L2_MBUS_FMT_RGB555_2X8_PADHI_LE = 0x1004,
-	V4L2_MBUS_FMT_BGR565_2X8_BE = 0x1005,
-	V4L2_MBUS_FMT_BGR565_2X8_LE = 0x1006,
-	V4L2_MBUS_FMT_RGB565_2X8_BE = 0x1007,
-	V4L2_MBUS_FMT_RGB565_2X8_LE = 0x1008,
-	V4L2_MBUS_FMT_RGB666_1X18 = 0x1009,
-	V4L2_MBUS_FMT_RGB888_1X24 = 0x100a,
-	V4L2_MBUS_FMT_RGB888_2X12_BE = 0x100b,
-	V4L2_MBUS_FMT_RGB888_2X12_LE = 0x100c,
-	V4L2_MBUS_FMT_ARGB8888_1X32 = 0x100d,
+enum v4l2_mbus_pixelcode {
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(FIXED),
 
-	/* YUV (including grey) - next is 0x2024 */
-	V4L2_MBUS_FMT_Y8_1X8 = 0x2001,
-	V4L2_MBUS_FMT_UV8_1X8 = 0x2015,
-	V4L2_MBUS_FMT_UYVY8_1_5X8 = 0x2002,
-	V4L2_MBUS_FMT_VYUY8_1_5X8 = 0x2003,
-	V4L2_MBUS_FMT_YUYV8_1_5X8 = 0x2004,
-	V4L2_MBUS_FMT_YVYU8_1_5X8 = 0x2005,
-	V4L2_MBUS_FMT_UYVY8_2X8 = 0x2006,
-	V4L2_MBUS_FMT_VYUY8_2X8 = 0x2007,
-	V4L2_MBUS_FMT_YUYV8_2X8 = 0x2008,
-	V4L2_MBUS_FMT_YVYU8_2X8 = 0x2009,
-	V4L2_MBUS_FMT_Y10_1X10 = 0x200a,
-	V4L2_MBUS_FMT_UYVY10_2X10 = 0x2018,
-	V4L2_MBUS_FMT_VYUY10_2X10 = 0x2019,
-	V4L2_MBUS_FMT_YUYV10_2X10 = 0x200b,
-	V4L2_MBUS_FMT_YVYU10_2X10 = 0x200c,
-	V4L2_MBUS_FMT_Y12_1X12 = 0x2013,
-	V4L2_MBUS_FMT_UYVY8_1X16 = 0x200f,
-	V4L2_MBUS_FMT_VYUY8_1X16 = 0x2010,
-	V4L2_MBUS_FMT_YUYV8_1X16 = 0x2011,
-	V4L2_MBUS_FMT_YVYU8_1X16 = 0x2012,
-	V4L2_MBUS_FMT_YDYUYDYV8_1X16 = 0x2014,
-	V4L2_MBUS_FMT_UYVY10_1X20 = 0x201a,
-	V4L2_MBUS_FMT_VYUY10_1X20 = 0x201b,
-	V4L2_MBUS_FMT_YUYV10_1X20 = 0x200d,
-	V4L2_MBUS_FMT_YVYU10_1X20 = 0x200e,
-	V4L2_MBUS_FMT_YUV10_1X30 = 0x2016,
-	V4L2_MBUS_FMT_AYUV8_1X32 = 0x2017,
-	V4L2_MBUS_FMT_UYVY12_2X12 = 0x201c,
-	V4L2_MBUS_FMT_VYUY12_2X12 = 0x201d,
-	V4L2_MBUS_FMT_YUYV12_2X12 = 0x201e,
-	V4L2_MBUS_FMT_YVYU12_2X12 = 0x201f,
-	V4L2_MBUS_FMT_UYVY12_1X24 = 0x2020,
-	V4L2_MBUS_FMT_VYUY12_1X24 = 0x2021,
-	V4L2_MBUS_FMT_YUYV12_1X24 = 0x2022,
-	V4L2_MBUS_FMT_YVYU12_1X24 = 0x2023,
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(RGB444_2X8_PADHI_BE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(RGB444_2X8_PADHI_LE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(RGB555_2X8_PADHI_BE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(RGB555_2X8_PADHI_LE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(BGR565_2X8_BE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(BGR565_2X8_LE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(RGB565_2X8_BE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(RGB565_2X8_LE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(RGB666_1X18),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(RGB888_1X24),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(RGB888_2X12_BE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(RGB888_2X12_LE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(ARGB8888_1X32),
 
-	/* Bayer - next is 0x3019 */
-	V4L2_MBUS_FMT_SBGGR8_1X8 = 0x3001,
-	V4L2_MBUS_FMT_SGBRG8_1X8 = 0x3013,
-	V4L2_MBUS_FMT_SGRBG8_1X8 = 0x3002,
-	V4L2_MBUS_FMT_SRGGB8_1X8 = 0x3014,
-	V4L2_MBUS_FMT_SBGGR10_ALAW8_1X8 = 0x3015,
-	V4L2_MBUS_FMT_SGBRG10_ALAW8_1X8 = 0x3016,
-	V4L2_MBUS_FMT_SGRBG10_ALAW8_1X8 = 0x3017,
-	V4L2_MBUS_FMT_SRGGB10_ALAW8_1X8 = 0x3018,
-	V4L2_MBUS_FMT_SBGGR10_DPCM8_1X8 = 0x300b,
-	V4L2_MBUS_FMT_SGBRG10_DPCM8_1X8 = 0x300c,
-	V4L2_MBUS_FMT_SGRBG10_DPCM8_1X8 = 0x3009,
-	V4L2_MBUS_FMT_SRGGB10_DPCM8_1X8 = 0x300d,
-	V4L2_MBUS_FMT_SBGGR10_2X8_PADHI_BE = 0x3003,
-	V4L2_MBUS_FMT_SBGGR10_2X8_PADHI_LE = 0x3004,
-	V4L2_MBUS_FMT_SBGGR10_2X8_PADLO_BE = 0x3005,
-	V4L2_MBUS_FMT_SBGGR10_2X8_PADLO_LE = 0x3006,
-	V4L2_MBUS_FMT_SBGGR10_1X10 = 0x3007,
-	V4L2_MBUS_FMT_SGBRG10_1X10 = 0x300e,
-	V4L2_MBUS_FMT_SGRBG10_1X10 = 0x300a,
-	V4L2_MBUS_FMT_SRGGB10_1X10 = 0x300f,
-	V4L2_MBUS_FMT_SBGGR12_1X12 = 0x3008,
-	V4L2_MBUS_FMT_SGBRG12_1X12 = 0x3010,
-	V4L2_MBUS_FMT_SGRBG12_1X12 = 0x3011,
-	V4L2_MBUS_FMT_SRGGB12_1X12 = 0x3012,
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(Y8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(UV8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(UYVY8_1_5X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(VYUY8_1_5X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YUYV8_1_5X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YVYU8_1_5X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(UYVY8_2X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(VYUY8_2X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YUYV8_2X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YVYU8_2X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(Y10_1X10),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(UYVY10_2X10),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(VYUY10_2X10),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YUYV10_2X10),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YVYU10_2X10),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(Y12_1X12),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(UYVY8_1X16),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(VYUY8_1X16),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YUYV8_1X16),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YVYU8_1X16),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YDYUYDYV8_1X16),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(UYVY10_1X20),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(VYUY10_1X20),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YUYV10_1X20),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YVYU10_1X20),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YUV10_1X30),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(AYUV8_1X32),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(UYVY12_2X12),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(VYUY12_2X12),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YUYV12_2X12),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YVYU12_2X12),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(UYVY12_1X24),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(VYUY12_1X24),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YUYV12_1X24),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(YVYU12_1X24),
 
-	/* JPEG compressed formats - next is 0x4002 */
-	V4L2_MBUS_FMT_JPEG_1X8 = 0x4001,
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SBGGR8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SGBRG8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SGRBG8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SRGGB8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SBGGR10_ALAW8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SGBRG10_ALAW8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SGRBG10_ALAW8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SRGGB10_ALAW8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SBGGR10_DPCM8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SGBRG10_DPCM8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SGRBG10_DPCM8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SRGGB10_DPCM8_1X8),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SBGGR10_2X8_PADHI_BE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SBGGR10_2X8_PADHI_LE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SBGGR10_2X8_PADLO_BE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SBGGR10_2X8_PADLO_LE),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SBGGR10_1X10),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SGBRG10_1X10),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SGRBG10_1X10),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SRGGB10_1X10),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SBGGR12_1X12),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SGBRG12_1X12),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SGRBG12_1X12),
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(SRGGB12_1X12),
 
-	/* Vendor specific formats - next is 0x5002 */
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(JPEG_1X8),
 
-	/* S5C73M3 sensor specific interleaved UYVY and JPEG */
-	V4L2_MBUS_FMT_S5C_UYVY_JPEG_1X8 = 0x5001,
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(S5C_UYVY_JPEG_1X8),
 
-	/* HSV - next is 0x6002 */
-	V4L2_MBUS_FMT_AHSV8888_1X32 = 0x6001,
+	V4L2_MBUS_FROM_MEDIA_BUS_FMT(AHSV8888_1X32),
 };
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 32b32ce84a02d5e3538941e71d2792ebbef8f795 Mon Sep 17 00:00:00 2001
From: Boris BREZILLON <boris.brezillon@free-electrons.com>
Date: Mon, 10 Nov 2014 14:28:28 -0300
Subject: [media] Make use of the new media_bus_format definitions

Replace references to the v4l2_mbus_pixelcode enum with the new
media_bus_format enum in all common headers.

Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/v4l2-mediabus.h    | 2 +-
 include/media/v4l2-subdev.h      | 2 +-
 include/uapi/linux/v4l2-subdev.h | 6 +++---
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h
index 395c4a95a42..59d7397fb0e 100644
--- a/include/media/v4l2-mediabus.h
+++ b/include/media/v4l2-mediabus.h
@@ -98,7 +98,7 @@ static inline void v4l2_fill_pix_format(struct v4l2_pix_format *pix_fmt,
 
 static inline void v4l2_fill_mbus_format(struct v4l2_mbus_framefmt *mbus_fmt,
 			   const struct v4l2_pix_format *pix_fmt,
-			   enum v4l2_mbus_pixelcode code)
+			   u32 code)
 {
 	mbus_fmt->width = pix_fmt->width;
 	mbus_fmt->height = pix_fmt->height;
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index d7465725773..5860292d42e 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -341,7 +341,7 @@ struct v4l2_subdev_video_ops {
 	int (*query_dv_timings)(struct v4l2_subdev *sd,
 			struct v4l2_dv_timings *timings);
 	int (*enum_mbus_fmt)(struct v4l2_subdev *sd, unsigned int index,
-			     enum v4l2_mbus_pixelcode *code);
+			     u32 *code);
 	int (*enum_mbus_fsizes)(struct v4l2_subdev *sd,
 			     struct v4l2_frmsizeenum *fsize);
 	int (*g_mbus_fmt)(struct v4l2_subdev *sd,
diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h
index a619cdd300a..e0a7e3da498 100644
--- a/include/uapi/linux/v4l2-subdev.h
+++ b/include/uapi/linux/v4l2-subdev.h
@@ -68,7 +68,7 @@ struct v4l2_subdev_crop {
  * struct v4l2_subdev_mbus_code_enum - Media bus format enumeration
  * @pad: pad number, as reported by the media API
  * @index: format index during enumeration
- * @code: format code (from enum v4l2_mbus_pixelcode)
+ * @code: format code (MEDIA_BUS_FMT_ definitions)
  */
 struct v4l2_subdev_mbus_code_enum {
 	__u32 pad;
@@ -81,7 +81,7 @@ struct v4l2_subdev_mbus_code_enum {
  * struct v4l2_subdev_frame_size_enum - Media bus format enumeration
  * @pad: pad number, as reported by the media API
  * @index: format index during enumeration
- * @code: format code (from enum v4l2_mbus_pixelcode)
+ * @code: format code (MEDIA_BUS_FMT_ definitions)
  */
 struct v4l2_subdev_frame_size_enum {
 	__u32 index;
@@ -109,7 +109,7 @@ struct v4l2_subdev_frame_interval {
  * struct v4l2_subdev_frame_interval_enum - Frame interval enumeration
  * @pad: pad number, as reported by the media API
  * @index: frame interval index during enumeration
- * @code: format code (from enum v4l2_mbus_pixelcode)
+ * @code: format code (MEDIA_BUS_FMT_ definitions)
  * @width: frame width in pixels
  * @height: frame height in pixels
  * @interval: frame interval in seconds
-- 
cgit v1.2.3-70-g09d2


From 27ffaeb0ab160852c87e2dfa505594020e9a3a06 Mon Sep 17 00:00:00 2001
From: Boris BREZILLON <boris.brezillon@free-electrons.com>
Date: Mon, 10 Nov 2014 14:28:31 -0300
Subject: [media] platform: Make use of media_bus_format enum

In order to have subsytem agnostic media bus format definitions we've
moved media bus definition to include/uapi/linux/media-bus-format.h and
prefixed values with MEDIA_BUS_FMT instead of V4L2_MBUS_FMT.

Reference new definitions in all platform drivers.

Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Acked-by: Sekhar Nori <nsekhar@ti.com>
Acked-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 Documentation/video4linux/soc-camera.txt           |   2 +-
 arch/arm/mach-davinci/board-dm355-evm.c            |   2 +-
 arch/arm/mach-davinci/board-dm365-evm.c            |   4 +-
 arch/arm/mach-davinci/dm355.c                      |   7 +-
 arch/arm/mach-davinci/dm365.c                      |   7 +-
 arch/arm/mach-shmobile/board-mackerel.c            |   2 +-
 arch/sh/boards/mach-ap325rxa/setup.c               |   2 +-
 drivers/media/platform/blackfin/bfin_capture.c     |  14 +--
 drivers/media/platform/davinci/vpbe.c              |   2 +-
 drivers/media/platform/davinci/vpfe_capture.c      |   4 +-
 drivers/media/platform/exynos-gsc/gsc-core.c       |   8 +-
 drivers/media/platform/exynos-gsc/gsc-core.h       |   2 +-
 drivers/media/platform/exynos4-is/fimc-capture.c   |   2 +-
 drivers/media/platform/exynos4-is/fimc-core.c      |  14 +--
 drivers/media/platform/exynos4-is/fimc-core.h      |   4 +-
 drivers/media/platform/exynos4-is/fimc-isp.c       |  16 +--
 drivers/media/platform/exynos4-is/fimc-lite-reg.c  |  26 ++---
 drivers/media/platform/exynos4-is/fimc-lite.c      |  14 +--
 drivers/media/platform/exynos4-is/fimc-reg.c       |  14 +--
 drivers/media/platform/exynos4-is/mipi-csis.c      |  14 +--
 drivers/media/platform/marvell-ccic/mcam-core.c    |  21 ++--
 drivers/media/platform/marvell-ccic/mcam-core.h    |   2 +-
 drivers/media/platform/omap3isp/ispccdc.c          | 112 ++++++++++-----------
 drivers/media/platform/omap3isp/ispccp2.c          |  18 ++--
 drivers/media/platform/omap3isp/ispcsi2.c          |  42 ++++----
 drivers/media/platform/omap3isp/isppreview.c       |  60 ++++++-----
 drivers/media/platform/omap3isp/ispresizer.c       |  19 ++--
 drivers/media/platform/omap3isp/ispvideo.c         |  95 +++++++++--------
 drivers/media/platform/omap3isp/ispvideo.h         |  10 +-
 drivers/media/platform/s3c-camif/camif-capture.c   |  10 +-
 drivers/media/platform/s3c-camif/camif-regs.c      |   8 +-
 drivers/media/platform/s5p-tv/hdmi_drv.c           |   2 +-
 drivers/media/platform/s5p-tv/sdo_drv.c            |   2 +-
 drivers/media/platform/sh_vou.c                    |   8 +-
 drivers/media/platform/soc_camera/atmel-isi.c      |  22 ++--
 drivers/media/platform/soc_camera/mx2_camera.c     |  26 +++--
 drivers/media/platform/soc_camera/mx3_camera.c     |   6 +-
 drivers/media/platform/soc_camera/omap1_camera.c   |  36 +++----
 drivers/media/platform/soc_camera/pxa_camera.c     |  16 +--
 drivers/media/platform/soc_camera/rcar_vin.c       |  14 +--
 .../platform/soc_camera/sh_mobile_ceu_camera.c     |  20 ++--
 drivers/media/platform/soc_camera/sh_mobile_csi2.c |  38 +++----
 drivers/media/platform/soc_camera/soc_camera.c     |   2 +-
 .../platform/soc_camera/soc_camera_platform.c      |   2 +-
 drivers/media/platform/soc_camera/soc_mediabus.c   |  78 +++++++-------
 drivers/media/platform/via-camera.c                |   8 +-
 drivers/media/platform/vsp1/vsp1_bru.c             |  14 +--
 drivers/media/platform/vsp1/vsp1_hsit.c            |  12 +--
 drivers/media/platform/vsp1/vsp1_lif.c             |  10 +-
 drivers/media/platform/vsp1/vsp1_lut.c             |  14 +--
 drivers/media/platform/vsp1/vsp1_rwpf.c            |  10 +-
 drivers/media/platform/vsp1/vsp1_sru.c             |  12 +--
 drivers/media/platform/vsp1/vsp1_uds.c             |  10 +-
 drivers/media/platform/vsp1/vsp1_video.c           |  42 ++++----
 include/media/davinci/vpbe.h                       |   2 +-
 include/media/davinci/vpbe_venc.h                  |   5 +-
 include/media/exynos-fimc.h                        |   2 +-
 include/media/soc_camera.h                         |   2 +-
 include/media/soc_mediabus.h                       |   6 +-
 59 files changed, 483 insertions(+), 495 deletions(-)

(limited to 'include')

diff --git a/Documentation/video4linux/soc-camera.txt b/Documentation/video4linux/soc-camera.txt
index daa9e2ac162..84f41cf1f3e 100644
--- a/Documentation/video4linux/soc-camera.txt
+++ b/Documentation/video4linux/soc-camera.txt
@@ -151,7 +151,7 @@ they are transferred over a media bus. Soc-camera provides support to
 conveniently manage these formats. A table of standard transformations is
 maintained by soc-camera core, which describes, what FOURCC pixel format will
 be obtained, if a media-bus pixel format is stored in memory according to
-certain rules. E.g. if V4L2_MBUS_FMT_YUYV8_2X8 data is sampled with 8 bits per
+certain rules. E.g. if MEDIA_BUS_FMT_YUYV8_2X8 data is sampled with 8 bits per
 sample and stored in memory in the little-endian order with no gaps between
 bytes, data in memory will represent the V4L2_PIX_FMT_YUYV FOURCC format. These
 standard transformations will be used by soc-camera or by camera host drivers to
diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c
index 06d63d5651f..b46b4d25f93 100644
--- a/arch/arm/mach-davinci/board-dm355-evm.c
+++ b/arch/arm/mach-davinci/board-dm355-evm.c
@@ -294,7 +294,7 @@ static struct vpbe_output dm355evm_vpbe_outputs[] = {
 		.default_mode	= "ntsc",
 		.num_modes	= ARRAY_SIZE(dm355evm_enc_preset_timing),
 		.modes		= dm355evm_enc_preset_timing,
-		.if_params	= V4L2_MBUS_FMT_FIXED,
+		.if_params	= MEDIA_BUS_FMT_FIXED,
 	},
 };
 
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index e08a8684ead..a756003595e 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -485,7 +485,7 @@ static struct vpbe_output dm365evm_vpbe_outputs[] = {
 		.default_mode	= "ntsc",
 		.num_modes	= ARRAY_SIZE(dm365evm_enc_std_timing),
 		.modes		= dm365evm_enc_std_timing,
-		.if_params	= V4L2_MBUS_FMT_FIXED,
+		.if_params	= MEDIA_BUS_FMT_FIXED,
 	},
 	{
 		.output		= {
@@ -498,7 +498,7 @@ static struct vpbe_output dm365evm_vpbe_outputs[] = {
 		.default_mode	= "480p59_94",
 		.num_modes	= ARRAY_SIZE(dm365evm_enc_preset_timing),
 		.modes		= dm365evm_enc_preset_timing,
-		.if_params	= V4L2_MBUS_FMT_FIXED,
+		.if_params	= MEDIA_BUS_FMT_FIXED,
 	},
 };
 
diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index 2f3ed3a58d5..9cbeda79858 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -785,14 +785,13 @@ static struct resource dm355_v4l2_disp_resources[] = {
 	},
 };
 
-static int dm355_vpbe_setup_pinmux(enum v4l2_mbus_pixelcode if_type,
-			    int field)
+static int dm355_vpbe_setup_pinmux(u32 if_type, int field)
 {
 	switch (if_type) {
-	case V4L2_MBUS_FMT_SGRBG8_1X8:
+	case MEDIA_BUS_FMT_SGRBG8_1X8:
 		davinci_cfg_reg(DM355_VOUT_FIELD_G70);
 		break;
-	case V4L2_MBUS_FMT_YUYV10_1X20:
+	case MEDIA_BUS_FMT_YUYV10_1X20:
 		if (field)
 			davinci_cfg_reg(DM355_VOUT_FIELD);
 		else
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index 0ae8114f5cc..e3a3c54b683 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -1306,16 +1306,15 @@ static struct resource dm365_v4l2_disp_resources[] = {
 	},
 };
 
-static int dm365_vpbe_setup_pinmux(enum v4l2_mbus_pixelcode if_type,
-			    int field)
+static int dm365_vpbe_setup_pinmux(u32 if_type, int field)
 {
 	switch (if_type) {
-	case V4L2_MBUS_FMT_SGRBG8_1X8:
+	case MEDIA_BUS_FMT_SGRBG8_1X8:
 		davinci_cfg_reg(DM365_VOUT_FIELD_G81);
 		davinci_cfg_reg(DM365_VOUT_COUTL_EN);
 		davinci_cfg_reg(DM365_VOUT_COUTH_EN);
 		break;
-	case V4L2_MBUS_FMT_YUYV10_1X20:
+	case MEDIA_BUS_FMT_YUYV10_1X20:
 		if (field)
 			davinci_cfg_reg(DM365_VOUT_FIELD);
 		else
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index ca5d34b92aa..a673624878d 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -1153,7 +1153,7 @@ static struct soc_camera_platform_info camera_info = {
 	.format_name = "UYVY",
 	.format_depth = 16,
 	.format = {
-		.code = V4L2_MBUS_FMT_UYVY8_2X8,
+		.code = MEDIA_BUS_FMT_UYVY8_2X8,
 		.colorspace = V4L2_COLORSPACE_SMPTE170M,
 		.field = V4L2_FIELD_NONE,
 		.width = 640,
diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c
index 5620e33c18a..d4b01d4cc10 100644
--- a/arch/sh/boards/mach-ap325rxa/setup.c
+++ b/arch/sh/boards/mach-ap325rxa/setup.c
@@ -338,7 +338,7 @@ static struct soc_camera_platform_info camera_info = {
 	.format_name = "UYVY",
 	.format_depth = 16,
 	.format = {
-		.code = V4L2_MBUS_FMT_UYVY8_2X8,
+		.code = MEDIA_BUS_FMT_UYVY8_2X8,
 		.colorspace = V4L2_COLORSPACE_SMPTE170M,
 		.field = V4L2_FIELD_NONE,
 		.width = 640,
diff --git a/drivers/media/platform/blackfin/bfin_capture.c b/drivers/media/platform/blackfin/bfin_capture.c
index 9b5daa65841..b3345b37bb1 100644
--- a/drivers/media/platform/blackfin/bfin_capture.c
+++ b/drivers/media/platform/blackfin/bfin_capture.c
@@ -49,7 +49,7 @@
 struct bcap_format {
 	char *desc;
 	u32 pixelformat;
-	enum v4l2_mbus_pixelcode mbus_code;
+	u32 mbus_code;
 	int bpp; /* bits per pixel */
 	int dlen; /* data length for ppi in bits */
 };
@@ -116,35 +116,35 @@ static const struct bcap_format bcap_formats[] = {
 	{
 		.desc        = "YCbCr 4:2:2 Interleaved UYVY",
 		.pixelformat = V4L2_PIX_FMT_UYVY,
-		.mbus_code   = V4L2_MBUS_FMT_UYVY8_2X8,
+		.mbus_code   = MEDIA_BUS_FMT_UYVY8_2X8,
 		.bpp         = 16,
 		.dlen        = 8,
 	},
 	{
 		.desc        = "YCbCr 4:2:2 Interleaved YUYV",
 		.pixelformat = V4L2_PIX_FMT_YUYV,
-		.mbus_code   = V4L2_MBUS_FMT_YUYV8_2X8,
+		.mbus_code   = MEDIA_BUS_FMT_YUYV8_2X8,
 		.bpp         = 16,
 		.dlen        = 8,
 	},
 	{
 		.desc        = "YCbCr 4:2:2 Interleaved UYVY",
 		.pixelformat = V4L2_PIX_FMT_UYVY,
-		.mbus_code   = V4L2_MBUS_FMT_UYVY8_1X16,
+		.mbus_code   = MEDIA_BUS_FMT_UYVY8_1X16,
 		.bpp         = 16,
 		.dlen        = 16,
 	},
 	{
 		.desc        = "RGB 565",
 		.pixelformat = V4L2_PIX_FMT_RGB565,
-		.mbus_code   = V4L2_MBUS_FMT_RGB565_2X8_LE,
+		.mbus_code   = MEDIA_BUS_FMT_RGB565_2X8_LE,
 		.bpp         = 16,
 		.dlen        = 8,
 	},
 	{
 		.desc        = "RGB 444",
 		.pixelformat = V4L2_PIX_FMT_RGB444,
-		.mbus_code   = V4L2_MBUS_FMT_RGB444_2X8_PADHI_LE,
+		.mbus_code   = MEDIA_BUS_FMT_RGB444_2X8_PADHI_LE,
 		.bpp         = 16,
 		.dlen        = 8,
 	},
@@ -161,7 +161,7 @@ static struct bcap_buffer *to_bcap_vb(struct vb2_buffer *vb)
 
 static int bcap_init_sensor_formats(struct bcap_device *bcap_dev)
 {
-	enum v4l2_mbus_pixelcode code;
+	u32 code;
 	struct bcap_format *sf;
 	unsigned int num_formats = 0;
 	int i, j;
diff --git a/drivers/media/platform/davinci/vpbe.c b/drivers/media/platform/davinci/vpbe.c
index e5df9916b2a..244d3d6c244 100644
--- a/drivers/media/platform/davinci/vpbe.c
+++ b/drivers/media/platform/davinci/vpbe.c
@@ -227,7 +227,7 @@ static int vpbe_set_output(struct vpbe_device *vpbe_dev, int index)
 			vpbe_current_encoder_info(vpbe_dev);
 	struct vpbe_config *cfg = vpbe_dev->cfg;
 	struct venc_platform_data *venc_device = vpbe_dev->venc_device;
-	enum v4l2_mbus_pixelcode if_params;
+	u32 if_params;
 	int enc_out_index;
 	int sd_index;
 	int ret = 0;
diff --git a/drivers/media/platform/davinci/vpfe_capture.c b/drivers/media/platform/davinci/vpfe_capture.c
index de55f47a77d..3d0e3ae1795 100644
--- a/drivers/media/platform/davinci/vpfe_capture.c
+++ b/drivers/media/platform/davinci/vpfe_capture.c
@@ -414,13 +414,13 @@ static int vpfe_config_image_format(struct vpfe_device *vpfe_dev,
 		/* assume V4L2_PIX_FMT_UYVY as default */
 		pix->pixelformat = V4L2_PIX_FMT_UYVY;
 		v4l2_fill_mbus_format(&mbus_fmt, pix,
-				V4L2_MBUS_FMT_YUYV10_2X10);
+				MEDIA_BUS_FMT_YUYV10_2X10);
 	} else {
 		pix->field = V4L2_FIELD_NONE;
 		/* assume V4L2_PIX_FMT_SBGGR8 */
 		pix->pixelformat = V4L2_PIX_FMT_SBGGR8;
 		v4l2_fill_mbus_format(&mbus_fmt, pix,
-				V4L2_MBUS_FMT_SBGGR8_1X8);
+				MEDIA_BUS_FMT_SBGGR8_1X8);
 	}
 
 	/* if sub device supports g_mbus_fmt, override the defaults */
diff --git a/drivers/media/platform/exynos-gsc/gsc-core.c b/drivers/media/platform/exynos-gsc/gsc-core.c
index b4c9f1d0896..91d226b8fe5 100644
--- a/drivers/media/platform/exynos-gsc/gsc-core.c
+++ b/drivers/media/platform/exynos-gsc/gsc-core.c
@@ -54,7 +54,7 @@ static const struct gsc_fmt gsc_formats[] = {
 		.corder		= GSC_CBCR,
 		.num_planes	= 1,
 		.num_comp	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_YUYV8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_YUYV8_2X8,
 	}, {
 		.name		= "YUV 4:2:2 packed, CbYCrY",
 		.pixelformat	= V4L2_PIX_FMT_UYVY,
@@ -64,7 +64,7 @@ static const struct gsc_fmt gsc_formats[] = {
 		.corder		= GSC_CBCR,
 		.num_planes	= 1,
 		.num_comp	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_UYVY8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_UYVY8_2X8,
 	}, {
 		.name		= "YUV 4:2:2 packed, CrYCbY",
 		.pixelformat	= V4L2_PIX_FMT_VYUY,
@@ -74,7 +74,7 @@ static const struct gsc_fmt gsc_formats[] = {
 		.corder		= GSC_CRCB,
 		.num_planes	= 1,
 		.num_comp	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_VYUY8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_VYUY8_2X8,
 	}, {
 		.name		= "YUV 4:2:2 packed, YCrYCb",
 		.pixelformat	= V4L2_PIX_FMT_YVYU,
@@ -84,7 +84,7 @@ static const struct gsc_fmt gsc_formats[] = {
 		.corder		= GSC_CRCB,
 		.num_planes	= 1,
 		.num_comp	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_YVYU8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_YVYU8_2X8,
 	}, {
 		.name		= "YUV 4:4:4 planar, YCbYCr",
 		.pixelformat	= V4L2_PIX_FMT_YUV32,
diff --git a/drivers/media/platform/exynos-gsc/gsc-core.h b/drivers/media/platform/exynos-gsc/gsc-core.h
index ef0a6564cef..0abdb17fb19 100644
--- a/drivers/media/platform/exynos-gsc/gsc-core.h
+++ b/drivers/media/platform/exynos-gsc/gsc-core.h
@@ -117,7 +117,7 @@ enum gsc_yuv_fmt {
  * @flags: flags indicating which operation mode format applies to
  */
 struct gsc_fmt {
-	enum v4l2_mbus_pixelcode mbus_code;
+	u32 mbus_code;
 	char	*name;
 	u32	pixelformat;
 	u32	color;
diff --git a/drivers/media/platform/exynos4-is/fimc-capture.c b/drivers/media/platform/exynos4-is/fimc-capture.c
index 3d2babd5067..8a2fd8c33d4 100644
--- a/drivers/media/platform/exynos4-is/fimc-capture.c
+++ b/drivers/media/platform/exynos4-is/fimc-capture.c
@@ -749,7 +749,7 @@ static int fimc_cap_enum_fmt_mplane(struct file *file, void *priv,
 		return -EINVAL;
 	strncpy(f->description, fmt->name, sizeof(f->description) - 1);
 	f->pixelformat = fmt->fourcc;
-	if (fmt->fourcc == V4L2_MBUS_FMT_JPEG_1X8)
+	if (fmt->fourcc == MEDIA_BUS_FMT_JPEG_1X8)
 		f->flags |= V4L2_FMT_FLAG_COMPRESSED;
 	return 0;
 }
diff --git a/drivers/media/platform/exynos4-is/fimc-core.c b/drivers/media/platform/exynos4-is/fimc-core.c
index aee92d908e4..dbd74d8dc2a 100644
--- a/drivers/media/platform/exynos4-is/fimc-core.c
+++ b/drivers/media/platform/exynos4-is/fimc-core.c
@@ -81,7 +81,7 @@ static struct fimc_fmt fimc_formats[] = {
 		.flags		= FMT_FLAGS_M2M_OUT | FMT_HAS_ALPHA,
 	}, {
 		.name		= "YUV 4:4:4",
-		.mbus_code	= V4L2_MBUS_FMT_YUV10_1X30,
+		.mbus_code	= MEDIA_BUS_FMT_YUV10_1X30,
 		.flags		= FMT_FLAGS_WRITEBACK,
 	}, {
 		.name		= "YUV 4:2:2 packed, YCbYCr",
@@ -90,7 +90,7 @@ static struct fimc_fmt fimc_formats[] = {
 		.color		= FIMC_FMT_YCBYCR422,
 		.memplanes	= 1,
 		.colplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_YUYV8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_YUYV8_2X8,
 		.flags		= FMT_FLAGS_M2M | FMT_FLAGS_CAM,
 	}, {
 		.name		= "YUV 4:2:2 packed, CbYCrY",
@@ -99,7 +99,7 @@ static struct fimc_fmt fimc_formats[] = {
 		.color		= FIMC_FMT_CBYCRY422,
 		.memplanes	= 1,
 		.colplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_UYVY8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_UYVY8_2X8,
 		.flags		= FMT_FLAGS_M2M | FMT_FLAGS_CAM,
 	}, {
 		.name		= "YUV 4:2:2 packed, CrYCbY",
@@ -108,7 +108,7 @@ static struct fimc_fmt fimc_formats[] = {
 		.color		= FIMC_FMT_CRYCBY422,
 		.memplanes	= 1,
 		.colplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_VYUY8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_VYUY8_2X8,
 		.flags		= FMT_FLAGS_M2M | FMT_FLAGS_CAM,
 	}, {
 		.name		= "YUV 4:2:2 packed, YCrYCb",
@@ -117,7 +117,7 @@ static struct fimc_fmt fimc_formats[] = {
 		.color		= FIMC_FMT_YCRYCB422,
 		.memplanes	= 1,
 		.colplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_YVYU8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_YVYU8_2X8,
 		.flags		= FMT_FLAGS_M2M | FMT_FLAGS_CAM,
 	}, {
 		.name		= "YUV 4:2:2 planar, Y/Cb/Cr",
@@ -190,7 +190,7 @@ static struct fimc_fmt fimc_formats[] = {
 		.depth		= { 8 },
 		.memplanes	= 1,
 		.colplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_JPEG_1X8,
+		.mbus_code	= MEDIA_BUS_FMT_JPEG_1X8,
 		.flags		= FMT_FLAGS_CAM | FMT_FLAGS_COMPRESSED,
 	}, {
 		.name		= "S5C73MX interleaved UYVY/JPEG",
@@ -200,7 +200,7 @@ static struct fimc_fmt fimc_formats[] = {
 		.memplanes	= 2,
 		.colplanes	= 1,
 		.mdataplanes	= 0x2, /* plane 1 holds frame meta data */
-		.mbus_code	= V4L2_MBUS_FMT_S5C_UYVY_JPEG_1X8,
+		.mbus_code	= MEDIA_BUS_FMT_S5C_UYVY_JPEG_1X8,
 		.flags		= FMT_FLAGS_CAM | FMT_FLAGS_COMPRESSED,
 	},
 };
diff --git a/drivers/media/platform/exynos4-is/fimc-core.h b/drivers/media/platform/exynos4-is/fimc-core.h
index 6c75c6ced1f..7328f084506 100644
--- a/drivers/media/platform/exynos4-is/fimc-core.h
+++ b/drivers/media/platform/exynos4-is/fimc-core.h
@@ -579,8 +579,8 @@ static inline bool fimc_jpeg_fourcc(u32 pixelformat)
 
 static inline bool fimc_user_defined_mbus_fmt(u32 code)
 {
-	return (code == V4L2_MBUS_FMT_JPEG_1X8 ||
-		code == V4L2_MBUS_FMT_S5C_UYVY_JPEG_1X8);
+	return (code == MEDIA_BUS_FMT_JPEG_1X8 ||
+		code == MEDIA_BUS_FMT_S5C_UYVY_JPEG_1X8);
 }
 
 /* Return the alpha component bit mask */
diff --git a/drivers/media/platform/exynos4-is/fimc-isp.c b/drivers/media/platform/exynos4-is/fimc-isp.c
index be62d6b9ac4..60c74491554 100644
--- a/drivers/media/platform/exynos4-is/fimc-isp.c
+++ b/drivers/media/platform/exynos4-is/fimc-isp.c
@@ -41,21 +41,21 @@ static const struct fimc_fmt fimc_isp_formats[FIMC_ISP_NUM_FORMATS] = {
 		.depth		= { 8 },
 		.color		= FIMC_FMT_RAW8,
 		.memplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_SGRBG8_1X8,
+		.mbus_code	= MEDIA_BUS_FMT_SGRBG8_1X8,
 	}, {
 		.name		= "RAW10 (GRBG)",
 		.fourcc		= V4L2_PIX_FMT_SGRBG10,
 		.depth		= { 10 },
 		.color		= FIMC_FMT_RAW10,
 		.memplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_SGRBG10_1X10,
+		.mbus_code	= MEDIA_BUS_FMT_SGRBG10_1X10,
 	}, {
 		.name		= "RAW12 (GRBG)",
 		.fourcc		= V4L2_PIX_FMT_SGRBG12,
 		.depth		= { 12 },
 		.color		= FIMC_FMT_RAW12,
 		.memplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_SGRBG12_1X12,
+		.mbus_code	= MEDIA_BUS_FMT_SGRBG12_1X12,
 	},
 };
 
@@ -149,7 +149,7 @@ static int fimc_isp_subdev_get_fmt(struct v4l2_subdev *sd,
 
 		if (fmt->pad == FIMC_ISP_SD_PAD_SRC_FIFO) {
 			mf->colorspace = V4L2_COLORSPACE_JPEG;
-			mf->code = V4L2_MBUS_FMT_YUV10_1X30;
+			mf->code = MEDIA_BUS_FMT_YUV10_1X30;
 		}
 	}
 
@@ -175,7 +175,7 @@ static void __isp_subdev_try_format(struct fimc_isp *isp,
 				FIMC_ISP_SINK_WIDTH_MAX, 0,
 				&mf->height, FIMC_ISP_SINK_HEIGHT_MIN,
 				FIMC_ISP_SINK_HEIGHT_MAX, 0, 0);
-		mf->code = V4L2_MBUS_FMT_SGRBG10_1X10;
+		mf->code = MEDIA_BUS_FMT_SGRBG10_1X10;
 	} else {
 		if (fmt->which == V4L2_SUBDEV_FORMAT_TRY)
 			format = v4l2_subdev_get_try_format(fh,
@@ -188,7 +188,7 @@ static void __isp_subdev_try_format(struct fimc_isp *isp,
 		mf->height = format->height - FIMC_ISP_CAC_MARGIN_HEIGHT;
 
 		if (fmt->pad == FIMC_ISP_SD_PAD_SRC_FIFO) {
-			mf->code = V4L2_MBUS_FMT_YUV10_1X30;
+			mf->code = MEDIA_BUS_FMT_YUV10_1X30;
 			mf->colorspace = V4L2_COLORSPACE_JPEG;
 		} else {
 			mf->code = format->code;
@@ -680,11 +680,11 @@ static void __isp_subdev_set_default_format(struct fimc_isp *isp)
 				FIMC_ISP_CAC_MARGIN_WIDTH;
 	isp->sink_fmt.height = DEFAULT_PREVIEW_STILL_HEIGHT +
 				FIMC_ISP_CAC_MARGIN_HEIGHT;
-	isp->sink_fmt.code = V4L2_MBUS_FMT_SGRBG10_1X10;
+	isp->sink_fmt.code = MEDIA_BUS_FMT_SGRBG10_1X10;
 
 	isp->src_fmt.width = DEFAULT_PREVIEW_STILL_WIDTH;
 	isp->src_fmt.height = DEFAULT_PREVIEW_STILL_HEIGHT;
-	isp->src_fmt.code = V4L2_MBUS_FMT_SGRBG10_1X10;
+	isp->src_fmt.code = MEDIA_BUS_FMT_SGRBG10_1X10;
 	__is_set_frame_size(is, &isp->src_fmt);
 }
 
diff --git a/drivers/media/platform/exynos4-is/fimc-lite-reg.c b/drivers/media/platform/exynos4-is/fimc-lite-reg.c
index bc3ec7d25a3..0477716a20d 100644
--- a/drivers/media/platform/exynos4-is/fimc-lite-reg.c
+++ b/drivers/media/platform/exynos4-is/fimc-lite-reg.c
@@ -112,24 +112,24 @@ void flite_hw_set_test_pattern(struct fimc_lite *dev, bool on)
 }
 
 static const u32 src_pixfmt_map[8][3] = {
-	{ V4L2_MBUS_FMT_YUYV8_2X8, FLITE_REG_CISRCSIZE_ORDER422_IN_YCBYCR,
+	{ MEDIA_BUS_FMT_YUYV8_2X8, FLITE_REG_CISRCSIZE_ORDER422_IN_YCBYCR,
 	  FLITE_REG_CIGCTRL_YUV422_1P },
-	{ V4L2_MBUS_FMT_YVYU8_2X8, FLITE_REG_CISRCSIZE_ORDER422_IN_YCRYCB,
+	{ MEDIA_BUS_FMT_YVYU8_2X8, FLITE_REG_CISRCSIZE_ORDER422_IN_YCRYCB,
 	  FLITE_REG_CIGCTRL_YUV422_1P },
-	{ V4L2_MBUS_FMT_UYVY8_2X8, FLITE_REG_CISRCSIZE_ORDER422_IN_CBYCRY,
+	{ MEDIA_BUS_FMT_UYVY8_2X8, FLITE_REG_CISRCSIZE_ORDER422_IN_CBYCRY,
 	  FLITE_REG_CIGCTRL_YUV422_1P },
-	{ V4L2_MBUS_FMT_VYUY8_2X8, FLITE_REG_CISRCSIZE_ORDER422_IN_CRYCBY,
+	{ MEDIA_BUS_FMT_VYUY8_2X8, FLITE_REG_CISRCSIZE_ORDER422_IN_CRYCBY,
 	  FLITE_REG_CIGCTRL_YUV422_1P },
-	{ V4L2_MBUS_FMT_SGRBG8_1X8, 0, FLITE_REG_CIGCTRL_RAW8 },
-	{ V4L2_MBUS_FMT_SGRBG10_1X10, 0, FLITE_REG_CIGCTRL_RAW10 },
-	{ V4L2_MBUS_FMT_SGRBG12_1X12, 0, FLITE_REG_CIGCTRL_RAW12 },
-	{ V4L2_MBUS_FMT_JPEG_1X8, 0, FLITE_REG_CIGCTRL_USER(1) },
+	{ MEDIA_BUS_FMT_SGRBG8_1X8, 0, FLITE_REG_CIGCTRL_RAW8 },
+	{ MEDIA_BUS_FMT_SGRBG10_1X10, 0, FLITE_REG_CIGCTRL_RAW10 },
+	{ MEDIA_BUS_FMT_SGRBG12_1X12, 0, FLITE_REG_CIGCTRL_RAW12 },
+	{ MEDIA_BUS_FMT_JPEG_1X8, 0, FLITE_REG_CIGCTRL_USER(1) },
 };
 
 /* Set camera input pixel format and resolution */
 void flite_hw_set_source_format(struct fimc_lite *dev, struct flite_frame *f)
 {
-	enum v4l2_mbus_pixelcode pixelcode = f->fmt->mbus_code;
+	u32 pixelcode = f->fmt->mbus_code;
 	int i = ARRAY_SIZE(src_pixfmt_map);
 	u32 cfg;
 
@@ -232,10 +232,10 @@ static void flite_hw_set_pack12(struct fimc_lite *dev, int on)
 static void flite_hw_set_out_order(struct fimc_lite *dev, struct flite_frame *f)
 {
 	static const u32 pixcode[4][2] = {
-		{ V4L2_MBUS_FMT_YUYV8_2X8, FLITE_REG_CIODMAFMT_YCBYCR },
-		{ V4L2_MBUS_FMT_YVYU8_2X8, FLITE_REG_CIODMAFMT_YCRYCB },
-		{ V4L2_MBUS_FMT_UYVY8_2X8, FLITE_REG_CIODMAFMT_CBYCRY },
-		{ V4L2_MBUS_FMT_VYUY8_2X8, FLITE_REG_CIODMAFMT_CRYCBY },
+		{ MEDIA_BUS_FMT_YUYV8_2X8, FLITE_REG_CIODMAFMT_YCBYCR },
+		{ MEDIA_BUS_FMT_YVYU8_2X8, FLITE_REG_CIODMAFMT_YCRYCB },
+		{ MEDIA_BUS_FMT_UYVY8_2X8, FLITE_REG_CIODMAFMT_CBYCRY },
+		{ MEDIA_BUS_FMT_VYUY8_2X8, FLITE_REG_CIODMAFMT_CRYCBY },
 	};
 	u32 cfg = readl(dev->regs + FLITE_REG_CIODMAFMT);
 	int i = ARRAY_SIZE(pixcode);
diff --git a/drivers/media/platform/exynos4-is/fimc-lite.c b/drivers/media/platform/exynos4-is/fimc-lite.c
index a97d2352f1d..b7dca8b2d45 100644
--- a/drivers/media/platform/exynos4-is/fimc-lite.c
+++ b/drivers/media/platform/exynos4-is/fimc-lite.c
@@ -48,7 +48,7 @@ static const struct fimc_fmt fimc_lite_formats[] = {
 		.depth		= { 16 },
 		.color		= FIMC_FMT_YCBYCR422,
 		.memplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_YUYV8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_YUYV8_2X8,
 		.flags		= FMT_FLAGS_YUV,
 	}, {
 		.name		= "YUV 4:2:2 packed, CbYCrY",
@@ -57,7 +57,7 @@ static const struct fimc_fmt fimc_lite_formats[] = {
 		.depth		= { 16 },
 		.color		= FIMC_FMT_CBYCRY422,
 		.memplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_UYVY8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_UYVY8_2X8,
 		.flags		= FMT_FLAGS_YUV,
 	}, {
 		.name		= "YUV 4:2:2 packed, CrYCbY",
@@ -66,7 +66,7 @@ static const struct fimc_fmt fimc_lite_formats[] = {
 		.depth		= { 16 },
 		.color		= FIMC_FMT_CRYCBY422,
 		.memplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_VYUY8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_VYUY8_2X8,
 		.flags		= FMT_FLAGS_YUV,
 	}, {
 		.name		= "YUV 4:2:2 packed, YCrYCb",
@@ -75,7 +75,7 @@ static const struct fimc_fmt fimc_lite_formats[] = {
 		.depth		= { 16 },
 		.color		= FIMC_FMT_YCRYCB422,
 		.memplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_YVYU8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_YVYU8_2X8,
 		.flags		= FMT_FLAGS_YUV,
 	}, {
 		.name		= "RAW8 (GRBG)",
@@ -84,7 +84,7 @@ static const struct fimc_fmt fimc_lite_formats[] = {
 		.depth		= { 8 },
 		.color		= FIMC_FMT_RAW8,
 		.memplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_SGRBG8_1X8,
+		.mbus_code	= MEDIA_BUS_FMT_SGRBG8_1X8,
 		.flags		= FMT_FLAGS_RAW_BAYER,
 	}, {
 		.name		= "RAW10 (GRBG)",
@@ -93,7 +93,7 @@ static const struct fimc_fmt fimc_lite_formats[] = {
 		.depth		= { 16 },
 		.color		= FIMC_FMT_RAW10,
 		.memplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_SGRBG10_1X10,
+		.mbus_code	= MEDIA_BUS_FMT_SGRBG10_1X10,
 		.flags		= FMT_FLAGS_RAW_BAYER,
 	}, {
 		.name		= "RAW12 (GRBG)",
@@ -102,7 +102,7 @@ static const struct fimc_fmt fimc_lite_formats[] = {
 		.depth		= { 16 },
 		.color		= FIMC_FMT_RAW12,
 		.memplanes	= 1,
-		.mbus_code	= V4L2_MBUS_FMT_SGRBG12_1X12,
+		.mbus_code	= MEDIA_BUS_FMT_SGRBG12_1X12,
 		.flags		= FMT_FLAGS_RAW_BAYER,
 	},
 };
diff --git a/drivers/media/platform/exynos4-is/fimc-reg.c b/drivers/media/platform/exynos4-is/fimc-reg.c
index 2d77fd8f440..df0cbcb69b6 100644
--- a/drivers/media/platform/exynos4-is/fimc-reg.c
+++ b/drivers/media/platform/exynos4-is/fimc-reg.c
@@ -592,10 +592,10 @@ struct mbus_pixfmt_desc {
 };
 
 static const struct mbus_pixfmt_desc pix_desc[] = {
-	{ V4L2_MBUS_FMT_YUYV8_2X8, FIMC_REG_CISRCFMT_ORDER422_YCBYCR, 8 },
-	{ V4L2_MBUS_FMT_YVYU8_2X8, FIMC_REG_CISRCFMT_ORDER422_YCRYCB, 8 },
-	{ V4L2_MBUS_FMT_VYUY8_2X8, FIMC_REG_CISRCFMT_ORDER422_CRYCBY, 8 },
-	{ V4L2_MBUS_FMT_UYVY8_2X8, FIMC_REG_CISRCFMT_ORDER422_CBYCRY, 8 },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, FIMC_REG_CISRCFMT_ORDER422_YCBYCR, 8 },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, FIMC_REG_CISRCFMT_ORDER422_YCRYCB, 8 },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, FIMC_REG_CISRCFMT_ORDER422_CRYCBY, 8 },
+	{ MEDIA_BUS_FMT_UYVY8_2X8, FIMC_REG_CISRCFMT_ORDER422_CBYCRY, 8 },
 };
 
 int fimc_hw_set_camera_source(struct fimc_dev *fimc,
@@ -689,11 +689,11 @@ int fimc_hw_set_camera_type(struct fimc_dev *fimc,
 
 		/* TODO: add remaining supported formats. */
 		switch (vid_cap->ci_fmt.code) {
-		case V4L2_MBUS_FMT_VYUY8_2X8:
+		case MEDIA_BUS_FMT_VYUY8_2X8:
 			tmp = FIMC_REG_CSIIMGFMT_YCBCR422_8BIT;
 			break;
-		case V4L2_MBUS_FMT_JPEG_1X8:
-		case V4L2_MBUS_FMT_S5C_UYVY_JPEG_1X8:
+		case MEDIA_BUS_FMT_JPEG_1X8:
+		case MEDIA_BUS_FMT_S5C_UYVY_JPEG_1X8:
 			tmp = FIMC_REG_CSIIMGFMT_USER(1);
 			cfg |= FIMC_REG_CIGCTRL_CAM_JPEG;
 			break;
diff --git a/drivers/media/platform/exynos4-is/mipi-csis.c b/drivers/media/platform/exynos4-is/mipi-csis.c
index db6fd14d193..2f3fdfba1a4 100644
--- a/drivers/media/platform/exynos4-is/mipi-csis.c
+++ b/drivers/media/platform/exynos4-is/mipi-csis.c
@@ -238,34 +238,34 @@ struct csis_state {
  */
 struct csis_pix_format {
 	unsigned int pix_width_alignment;
-	enum v4l2_mbus_pixelcode code;
+	u32 code;
 	u32 fmt_reg;
 	u8 data_alignment;
 };
 
 static const struct csis_pix_format s5pcsis_formats[] = {
 	{
-		.code = V4L2_MBUS_FMT_VYUY8_2X8,
+		.code = MEDIA_BUS_FMT_VYUY8_2X8,
 		.fmt_reg = S5PCSIS_CFG_FMT_YCBCR422_8BIT,
 		.data_alignment = 32,
 	}, {
-		.code = V4L2_MBUS_FMT_JPEG_1X8,
+		.code = MEDIA_BUS_FMT_JPEG_1X8,
 		.fmt_reg = S5PCSIS_CFG_FMT_USER(1),
 		.data_alignment = 32,
 	}, {
-		.code = V4L2_MBUS_FMT_S5C_UYVY_JPEG_1X8,
+		.code = MEDIA_BUS_FMT_S5C_UYVY_JPEG_1X8,
 		.fmt_reg = S5PCSIS_CFG_FMT_USER(1),
 		.data_alignment = 32,
 	}, {
-		.code = V4L2_MBUS_FMT_SGRBG8_1X8,
+		.code = MEDIA_BUS_FMT_SGRBG8_1X8,
 		.fmt_reg = S5PCSIS_CFG_FMT_RAW8,
 		.data_alignment = 24,
 	}, {
-		.code = V4L2_MBUS_FMT_SGRBG10_1X10,
+		.code = MEDIA_BUS_FMT_SGRBG10_1X10,
 		.fmt_reg = S5PCSIS_CFG_FMT_RAW10,
 		.data_alignment = 24,
 	}, {
-		.code = V4L2_MBUS_FMT_SGRBG12_1X12,
+		.code = MEDIA_BUS_FMT_SGRBG12_1X12,
 		.fmt_reg = S5PCSIS_CFG_FMT_RAW12,
 		.data_alignment = 24,
 	}
diff --git a/drivers/media/platform/marvell-ccic/mcam-core.c b/drivers/media/platform/marvell-ccic/mcam-core.c
index 7a86c77bffa..f0eeb6cd262 100644
--- a/drivers/media/platform/marvell-ccic/mcam-core.c
+++ b/drivers/media/platform/marvell-ccic/mcam-core.c
@@ -106,61 +106,61 @@ static struct mcam_format_struct {
 	__u32 pixelformat;
 	int bpp;   /* Bytes per pixel */
 	bool planar;
-	enum v4l2_mbus_pixelcode mbus_code;
+	u32 mbus_code;
 } mcam_formats[] = {
 	{
 		.desc		= "YUYV 4:2:2",
 		.pixelformat	= V4L2_PIX_FMT_YUYV,
-		.mbus_code	= V4L2_MBUS_FMT_YUYV8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_YUYV8_2X8,
 		.bpp		= 2,
 		.planar		= false,
 	},
 	{
 		.desc		= "UYVY 4:2:2",
 		.pixelformat	= V4L2_PIX_FMT_UYVY,
-		.mbus_code	= V4L2_MBUS_FMT_YUYV8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_YUYV8_2X8,
 		.bpp		= 2,
 		.planar		= false,
 	},
 	{
 		.desc		= "YUV 4:2:2 PLANAR",
 		.pixelformat	= V4L2_PIX_FMT_YUV422P,
-		.mbus_code	= V4L2_MBUS_FMT_YUYV8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_YUYV8_2X8,
 		.bpp		= 2,
 		.planar		= true,
 	},
 	{
 		.desc		= "YUV 4:2:0 PLANAR",
 		.pixelformat	= V4L2_PIX_FMT_YUV420,
-		.mbus_code	= V4L2_MBUS_FMT_YUYV8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_YUYV8_2X8,
 		.bpp		= 2,
 		.planar		= true,
 	},
 	{
 		.desc		= "YVU 4:2:0 PLANAR",
 		.pixelformat	= V4L2_PIX_FMT_YVU420,
-		.mbus_code	= V4L2_MBUS_FMT_YUYV8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_YUYV8_2X8,
 		.bpp		= 2,
 		.planar		= true,
 	},
 	{
 		.desc		= "RGB 444",
 		.pixelformat	= V4L2_PIX_FMT_RGB444,
-		.mbus_code	= V4L2_MBUS_FMT_RGB444_2X8_PADHI_LE,
+		.mbus_code	= MEDIA_BUS_FMT_RGB444_2X8_PADHI_LE,
 		.bpp		= 2,
 		.planar		= false,
 	},
 	{
 		.desc		= "RGB 565",
 		.pixelformat	= V4L2_PIX_FMT_RGB565,
-		.mbus_code	= V4L2_MBUS_FMT_RGB565_2X8_LE,
+		.mbus_code	= MEDIA_BUS_FMT_RGB565_2X8_LE,
 		.bpp		= 2,
 		.planar		= false,
 	},
 	{
 		.desc		= "Raw RGB Bayer",
 		.pixelformat	= V4L2_PIX_FMT_SBGGR8,
-		.mbus_code	= V4L2_MBUS_FMT_SBGGR8_1X8,
+		.mbus_code	= MEDIA_BUS_FMT_SBGGR8_1X8,
 		.bpp		= 1,
 		.planar		= false,
 	},
@@ -190,8 +190,7 @@ static const struct v4l2_pix_format mcam_def_pix_format = {
 	.sizeimage	= VGA_WIDTH*VGA_HEIGHT*2,
 };
 
-static const enum v4l2_mbus_pixelcode mcam_def_mbus_code =
-					V4L2_MBUS_FMT_YUYV8_2X8;
+static const u32 mcam_def_mbus_code = MEDIA_BUS_FMT_YUYV8_2X8;
 
 
 /*
diff --git a/drivers/media/platform/marvell-ccic/mcam-core.h b/drivers/media/platform/marvell-ccic/mcam-core.h
index e0e628cb98f..60a8e1cfeff 100644
--- a/drivers/media/platform/marvell-ccic/mcam-core.h
+++ b/drivers/media/platform/marvell-ccic/mcam-core.h
@@ -183,7 +183,7 @@ struct mcam_camera {
 
 	/* Current operating parameters */
 	struct v4l2_pix_format pix_format;
-	enum v4l2_mbus_pixelcode mbus_code;
+	u32 mbus_code;
 
 	/* Locks */
 	struct mutex s_mutex; /* Access to this structure */
diff --git a/drivers/media/platform/omap3isp/ispccdc.c b/drivers/media/platform/omap3isp/ispccdc.c
index 81a9dc053d5..587489a072d 100644
--- a/drivers/media/platform/omap3isp/ispccdc.c
+++ b/drivers/media/platform/omap3isp/ispccdc.c
@@ -36,23 +36,23 @@ __ccdc_get_format(struct isp_ccdc_device *ccdc, struct v4l2_subdev_fh *fh,
 		  unsigned int pad, enum v4l2_subdev_format_whence which);
 
 static const unsigned int ccdc_fmts[] = {
-	V4L2_MBUS_FMT_Y8_1X8,
-	V4L2_MBUS_FMT_Y10_1X10,
-	V4L2_MBUS_FMT_Y12_1X12,
-	V4L2_MBUS_FMT_SGRBG8_1X8,
-	V4L2_MBUS_FMT_SRGGB8_1X8,
-	V4L2_MBUS_FMT_SBGGR8_1X8,
-	V4L2_MBUS_FMT_SGBRG8_1X8,
-	V4L2_MBUS_FMT_SGRBG10_1X10,
-	V4L2_MBUS_FMT_SRGGB10_1X10,
-	V4L2_MBUS_FMT_SBGGR10_1X10,
-	V4L2_MBUS_FMT_SGBRG10_1X10,
-	V4L2_MBUS_FMT_SGRBG12_1X12,
-	V4L2_MBUS_FMT_SRGGB12_1X12,
-	V4L2_MBUS_FMT_SBGGR12_1X12,
-	V4L2_MBUS_FMT_SGBRG12_1X12,
-	V4L2_MBUS_FMT_YUYV8_2X8,
-	V4L2_MBUS_FMT_UYVY8_2X8,
+	MEDIA_BUS_FMT_Y8_1X8,
+	MEDIA_BUS_FMT_Y10_1X10,
+	MEDIA_BUS_FMT_Y12_1X12,
+	MEDIA_BUS_FMT_SGRBG8_1X8,
+	MEDIA_BUS_FMT_SRGGB8_1X8,
+	MEDIA_BUS_FMT_SBGGR8_1X8,
+	MEDIA_BUS_FMT_SGBRG8_1X8,
+	MEDIA_BUS_FMT_SGRBG10_1X10,
+	MEDIA_BUS_FMT_SRGGB10_1X10,
+	MEDIA_BUS_FMT_SBGGR10_1X10,
+	MEDIA_BUS_FMT_SGBRG10_1X10,
+	MEDIA_BUS_FMT_SGRBG12_1X12,
+	MEDIA_BUS_FMT_SRGGB12_1X12,
+	MEDIA_BUS_FMT_SBGGR12_1X12,
+	MEDIA_BUS_FMT_SGBRG12_1X12,
+	MEDIA_BUS_FMT_YUYV8_2X8,
+	MEDIA_BUS_FMT_UYVY8_2X8,
 };
 
 /*
@@ -266,10 +266,10 @@ static int __ccdc_lsc_enable(struct isp_ccdc_device *ccdc, int enable)
 		__ccdc_get_format(ccdc, NULL, CCDC_PAD_SINK,
 				  V4L2_SUBDEV_FORMAT_ACTIVE);
 
-	if ((format->code != V4L2_MBUS_FMT_SGRBG10_1X10) &&
-	    (format->code != V4L2_MBUS_FMT_SRGGB10_1X10) &&
-	    (format->code != V4L2_MBUS_FMT_SBGGR10_1X10) &&
-	    (format->code != V4L2_MBUS_FMT_SGBRG10_1X10))
+	if ((format->code != MEDIA_BUS_FMT_SGRBG10_1X10) &&
+	    (format->code != MEDIA_BUS_FMT_SRGGB10_1X10) &&
+	    (format->code != MEDIA_BUS_FMT_SBGGR10_1X10) &&
+	    (format->code != MEDIA_BUS_FMT_SGBRG10_1X10))
 		return -EINVAL;
 
 	if (enable)
@@ -971,8 +971,8 @@ static void ccdc_config_sync_if(struct isp_ccdc_device *ccdc,
 
 	format = &ccdc->formats[CCDC_PAD_SINK];
 
-	if (format->code == V4L2_MBUS_FMT_YUYV8_2X8 ||
-	    format->code == V4L2_MBUS_FMT_UYVY8_2X8) {
+	if (format->code == MEDIA_BUS_FMT_YUYV8_2X8 ||
+	    format->code == MEDIA_BUS_FMT_UYVY8_2X8) {
 		/* According to the OMAP3 TRM the input mode only affects SYNC
 		 * mode, enabling BT.656 mode should take precedence. However,
 		 * in practice setting the input mode to YCbCr data on 8 bits
@@ -1020,7 +1020,7 @@ static void ccdc_config_sync_if(struct isp_ccdc_device *ccdc,
 	/* The CCDC_CFG.Y8POS bit is used in YCbCr8 input mode only. The
 	 * hardware seems to ignore it in all other input modes.
 	 */
-	if (format->code == V4L2_MBUS_FMT_UYVY8_2X8)
+	if (format->code == MEDIA_BUS_FMT_UYVY8_2X8)
 		isp_reg_set(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_CFG,
 			    ISPCCDC_CFG_Y8POS);
 	else
@@ -1168,9 +1168,9 @@ static void ccdc_configure(struct isp_ccdc_device *ccdc)
 
 	if (ccdc->bt656)
 		bridge = ISPCTRL_PAR_BRIDGE_DISABLE;
-	else if (fmt_info->code == V4L2_MBUS_FMT_YUYV8_2X8)
+	else if (fmt_info->code == MEDIA_BUS_FMT_YUYV8_2X8)
 		bridge = ISPCTRL_PAR_BRIDGE_LENDIAN;
-	else if (fmt_info->code == V4L2_MBUS_FMT_UYVY8_2X8)
+	else if (fmt_info->code == MEDIA_BUS_FMT_UYVY8_2X8)
 		bridge = ISPCTRL_PAR_BRIDGE_BENDIAN;
 	else
 		bridge = ISPCTRL_PAR_BRIDGE_DISABLE;
@@ -1199,16 +1199,16 @@ static void ccdc_configure(struct isp_ccdc_device *ccdc)
 
 	/* Mosaic filter */
 	switch (format->code) {
-	case V4L2_MBUS_FMT_SRGGB10_1X10:
-	case V4L2_MBUS_FMT_SRGGB12_1X12:
+	case MEDIA_BUS_FMT_SRGGB10_1X10:
+	case MEDIA_BUS_FMT_SRGGB12_1X12:
 		ccdc_pattern = ccdc_srggb_pattern;
 		break;
-	case V4L2_MBUS_FMT_SBGGR10_1X10:
-	case V4L2_MBUS_FMT_SBGGR12_1X12:
+	case MEDIA_BUS_FMT_SBGGR10_1X10:
+	case MEDIA_BUS_FMT_SBGGR12_1X12:
 		ccdc_pattern = ccdc_sbggr_pattern;
 		break;
-	case V4L2_MBUS_FMT_SGBRG10_1X10:
-	case V4L2_MBUS_FMT_SGBRG12_1X12:
+	case MEDIA_BUS_FMT_SGBRG10_1X10:
+	case MEDIA_BUS_FMT_SGBRG12_1X12:
 		ccdc_pattern = ccdc_sgbrg_pattern;
 		break;
 	default:
@@ -1267,7 +1267,7 @@ static void ccdc_configure(struct isp_ccdc_device *ccdc)
 	/* The CCDC outputs data in UYVY order by default. Swap bytes to get
 	 * YUYV.
 	 */
-	if (format->code == V4L2_MBUS_FMT_YUYV8_1X16)
+	if (format->code == MEDIA_BUS_FMT_YUYV8_1X16)
 		isp_reg_set(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_CFG,
 			    ISPCCDC_CFG_BSWD);
 	else
@@ -1967,7 +1967,7 @@ ccdc_try_format(struct isp_ccdc_device *ccdc, struct v4l2_subdev_fh *fh,
 		enum v4l2_subdev_format_whence which)
 {
 	const struct isp_format_info *info;
-	enum v4l2_mbus_pixelcode pixelcode;
+	u32 pixelcode;
 	unsigned int width = fmt->width;
 	unsigned int height = fmt->height;
 	struct v4l2_rect *crop;
@@ -1983,7 +1983,7 @@ ccdc_try_format(struct isp_ccdc_device *ccdc, struct v4l2_subdev_fh *fh,
 
 		/* If not found, use SGRBG10 as default */
 		if (i >= ARRAY_SIZE(ccdc_fmts))
-			fmt->code = V4L2_MBUS_FMT_SGRBG10_1X10;
+			fmt->code = MEDIA_BUS_FMT_SGRBG10_1X10;
 
 		/* Clamp the input size. */
 		fmt->width = clamp_t(u32, width, 32, 4096);
@@ -2007,19 +2007,19 @@ ccdc_try_format(struct isp_ccdc_device *ccdc, struct v4l2_subdev_fh *fh,
 		 * configured to pack bytes in BT.656, hiding the inaccuracy.
 		 * In all cases bytes can be swapped.
 		 */
-		if (fmt->code == V4L2_MBUS_FMT_YUYV8_2X8 ||
-		    fmt->code == V4L2_MBUS_FMT_UYVY8_2X8) {
+		if (fmt->code == MEDIA_BUS_FMT_YUYV8_2X8 ||
+		    fmt->code == MEDIA_BUS_FMT_UYVY8_2X8) {
 			/* Use the user requested format if YUV. */
-			if (pixelcode == V4L2_MBUS_FMT_YUYV8_2X8 ||
-			    pixelcode == V4L2_MBUS_FMT_UYVY8_2X8 ||
-			    pixelcode == V4L2_MBUS_FMT_YUYV8_1X16 ||
-			    pixelcode == V4L2_MBUS_FMT_UYVY8_1X16)
+			if (pixelcode == MEDIA_BUS_FMT_YUYV8_2X8 ||
+			    pixelcode == MEDIA_BUS_FMT_UYVY8_2X8 ||
+			    pixelcode == MEDIA_BUS_FMT_YUYV8_1X16 ||
+			    pixelcode == MEDIA_BUS_FMT_UYVY8_1X16)
 				fmt->code = pixelcode;
 
-			if (fmt->code == V4L2_MBUS_FMT_YUYV8_2X8)
-				fmt->code = V4L2_MBUS_FMT_YUYV8_1X16;
-			else if (fmt->code == V4L2_MBUS_FMT_UYVY8_2X8)
-				fmt->code = V4L2_MBUS_FMT_UYVY8_1X16;
+			if (fmt->code == MEDIA_BUS_FMT_YUYV8_2X8)
+				fmt->code = MEDIA_BUS_FMT_YUYV8_1X16;
+			else if (fmt->code == MEDIA_BUS_FMT_UYVY8_2X8)
+				fmt->code = MEDIA_BUS_FMT_UYVY8_1X16;
 		}
 
 		/* Hardcode the output size to the crop rectangle size. */
@@ -2047,8 +2047,8 @@ ccdc_try_format(struct isp_ccdc_device *ccdc, struct v4l2_subdev_fh *fh,
 		fmt->code = info->truncated;
 
 		/* YUV formats are not supported by the video port. */
-		if (fmt->code == V4L2_MBUS_FMT_YUYV8_2X8 ||
-		    fmt->code == V4L2_MBUS_FMT_UYVY8_2X8)
+		if (fmt->code == MEDIA_BUS_FMT_YUYV8_2X8 ||
+		    fmt->code == MEDIA_BUS_FMT_UYVY8_2X8)
 			fmt->code = 0;
 
 		/* The number of lines that can be clocked out from the video
@@ -2083,7 +2083,7 @@ static void ccdc_try_crop(struct isp_ccdc_device *ccdc,
 	 * to keep the Bayer pattern.
 	 */
 	info = omap3isp_video_format_info(sink->code);
-	if (info->flavor != V4L2_MBUS_FMT_Y8_1X8) {
+	if (info->flavor != MEDIA_BUS_FMT_Y8_1X8) {
 		crop->left &= ~1;
 		crop->top &= ~1;
 	}
@@ -2103,7 +2103,7 @@ static void ccdc_try_crop(struct isp_ccdc_device *ccdc,
 			       sink->height - crop->top);
 
 	/* Odd width/height values don't make sense for Bayer formats. */
-	if (info->flavor != V4L2_MBUS_FMT_Y8_1X8) {
+	if (info->flavor != MEDIA_BUS_FMT_Y8_1X8) {
 		crop->width &= ~1;
 		crop->height &= ~1;
 	}
@@ -2135,13 +2135,13 @@ static int ccdc_enum_mbus_code(struct v4l2_subdev *sd,
 		format = __ccdc_get_format(ccdc, fh, code->pad,
 					   V4L2_SUBDEV_FORMAT_TRY);
 
-		if (format->code == V4L2_MBUS_FMT_YUYV8_2X8 ||
-		    format->code == V4L2_MBUS_FMT_UYVY8_2X8) {
+		if (format->code == MEDIA_BUS_FMT_YUYV8_2X8 ||
+		    format->code == MEDIA_BUS_FMT_UYVY8_2X8) {
 			/* In YUV mode the CCDC can swap bytes. */
 			if (code->index == 0)
-				code->code = V4L2_MBUS_FMT_YUYV8_1X16;
+				code->code = MEDIA_BUS_FMT_YUYV8_1X16;
 			else if (code->index == 1)
-				code->code = V4L2_MBUS_FMT_UYVY8_1X16;
+				code->code = MEDIA_BUS_FMT_UYVY8_1X16;
 			else
 				return -EINVAL;
 		} else {
@@ -2383,9 +2383,7 @@ static int ccdc_set_format(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh,
  * return true if the combination is possible
  * return false otherwise
  */
-static bool ccdc_is_shiftable(enum v4l2_mbus_pixelcode in,
-			      enum v4l2_mbus_pixelcode out,
-			      unsigned int additional_shift)
+static bool ccdc_is_shiftable(u32 in, u32 out, unsigned int additional_shift)
 {
 	const struct isp_format_info *in_info, *out_info;
 
@@ -2452,7 +2450,7 @@ static int ccdc_init_formats(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
 	memset(&format, 0, sizeof(format));
 	format.pad = CCDC_PAD_SINK;
 	format.which = fh ? V4L2_SUBDEV_FORMAT_TRY : V4L2_SUBDEV_FORMAT_ACTIVE;
-	format.format.code = V4L2_MBUS_FMT_SGRBG10_1X10;
+	format.format.code = MEDIA_BUS_FMT_SGRBG10_1X10;
 	format.format.width = 4096;
 	format.format.height = 4096;
 	ccdc_set_format(sd, fh, &format);
diff --git a/drivers/media/platform/omap3isp/ispccp2.c b/drivers/media/platform/omap3isp/ispccp2.c
index 9cb49b3c04b..f4aedb37e41 100644
--- a/drivers/media/platform/omap3isp/ispccp2.c
+++ b/drivers/media/platform/omap3isp/ispccp2.c
@@ -289,10 +289,10 @@ static void ccp2_lcx_config(struct isp_ccp2_device *ccp2,
 	u32 val, format;
 
 	switch (config->format) {
-	case V4L2_MBUS_FMT_SGRBG10_DPCM8_1X8:
+	case MEDIA_BUS_FMT_SGRBG10_DPCM8_1X8:
 		format = ISPCCP2_LCx_CTRL_FORMAT_RAW8_DPCM10_VP;
 		break;
-	case V4L2_MBUS_FMT_SGRBG10_1X10:
+	case MEDIA_BUS_FMT_SGRBG10_1X10:
 	default:
 		format = ISPCCP2_LCx_CTRL_FORMAT_RAW10_VP;	/* RAW10+VP */
 		break;
@@ -438,7 +438,7 @@ static void ccp2_mem_configure(struct isp_ccp2_device *ccp2,
 	u32 val, hwords;
 
 	if (sink_pixcode != source_pixcode &&
-	    sink_pixcode == V4L2_MBUS_FMT_SGRBG10_DPCM8_1X8)
+	    sink_pixcode == MEDIA_BUS_FMT_SGRBG10_DPCM8_1X8)
 		dpcm_decompress = 1;
 
 	ccp2_pwr_cfg(ccp2);
@@ -604,8 +604,8 @@ void omap3isp_ccp2_isr(struct isp_ccp2_device *ccp2)
  */
 
 static const unsigned int ccp2_fmts[] = {
-	V4L2_MBUS_FMT_SGRBG10_1X10,
-	V4L2_MBUS_FMT_SGRBG10_DPCM8_1X8,
+	MEDIA_BUS_FMT_SGRBG10_1X10,
+	MEDIA_BUS_FMT_SGRBG10_DPCM8_1X8,
 };
 
 /*
@@ -643,8 +643,8 @@ static void ccp2_try_format(struct isp_ccp2_device *ccp2,
 
 	switch (pad) {
 	case CCP2_PAD_SINK:
-		if (fmt->code != V4L2_MBUS_FMT_SGRBG10_DPCM8_1X8)
-			fmt->code = V4L2_MBUS_FMT_SGRBG10_1X10;
+		if (fmt->code != MEDIA_BUS_FMT_SGRBG10_DPCM8_1X8)
+			fmt->code = MEDIA_BUS_FMT_SGRBG10_1X10;
 
 		if (ccp2->input == CCP2_INPUT_SENSOR) {
 			fmt->width = clamp_t(u32, fmt->width,
@@ -671,7 +671,7 @@ static void ccp2_try_format(struct isp_ccp2_device *ccp2,
 		 */
 		format = __ccp2_get_format(ccp2, fh, CCP2_PAD_SINK, which);
 		memcpy(fmt, format, sizeof(*fmt));
-		fmt->code = V4L2_MBUS_FMT_SGRBG10_1X10;
+		fmt->code = MEDIA_BUS_FMT_SGRBG10_1X10;
 		break;
 	}
 
@@ -808,7 +808,7 @@ static int ccp2_init_formats(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
 	memset(&format, 0, sizeof(format));
 	format.pad = CCP2_PAD_SINK;
 	format.which = fh ? V4L2_SUBDEV_FORMAT_TRY : V4L2_SUBDEV_FORMAT_ACTIVE;
-	format.format.code = V4L2_MBUS_FMT_SGRBG10_1X10;
+	format.format.code = MEDIA_BUS_FMT_SGRBG10_1X10;
 	format.format.width = 4096;
 	format.format.height = 4096;
 	ccp2_set_format(sd, fh, &format);
diff --git a/drivers/media/platform/omap3isp/ispcsi2.c b/drivers/media/platform/omap3isp/ispcsi2.c
index 6530b255f10..09c686d96ae 100644
--- a/drivers/media/platform/omap3isp/ispcsi2.c
+++ b/drivers/media/platform/omap3isp/ispcsi2.c
@@ -78,15 +78,15 @@ static void csi2_recv_config(struct isp_device *isp,
 }
 
 static const unsigned int csi2_input_fmts[] = {
-	V4L2_MBUS_FMT_SGRBG10_1X10,
-	V4L2_MBUS_FMT_SGRBG10_DPCM8_1X8,
-	V4L2_MBUS_FMT_SRGGB10_1X10,
-	V4L2_MBUS_FMT_SRGGB10_DPCM8_1X8,
-	V4L2_MBUS_FMT_SBGGR10_1X10,
-	V4L2_MBUS_FMT_SBGGR10_DPCM8_1X8,
-	V4L2_MBUS_FMT_SGBRG10_1X10,
-	V4L2_MBUS_FMT_SGBRG10_DPCM8_1X8,
-	V4L2_MBUS_FMT_YUYV8_2X8,
+	MEDIA_BUS_FMT_SGRBG10_1X10,
+	MEDIA_BUS_FMT_SGRBG10_DPCM8_1X8,
+	MEDIA_BUS_FMT_SRGGB10_1X10,
+	MEDIA_BUS_FMT_SRGGB10_DPCM8_1X8,
+	MEDIA_BUS_FMT_SBGGR10_1X10,
+	MEDIA_BUS_FMT_SBGGR10_DPCM8_1X8,
+	MEDIA_BUS_FMT_SGBRG10_1X10,
+	MEDIA_BUS_FMT_SGBRG10_DPCM8_1X8,
+	MEDIA_BUS_FMT_YUYV8_2X8,
 };
 
 /* To set the format on the CSI2 requires a mapping function that takes
@@ -171,19 +171,19 @@ static u16 csi2_ctx_map_format(struct isp_csi2_device *csi2)
 	int fmtidx, destidx, is_3630;
 
 	switch (fmt->code) {
-	case V4L2_MBUS_FMT_SGRBG10_1X10:
-	case V4L2_MBUS_FMT_SRGGB10_1X10:
-	case V4L2_MBUS_FMT_SBGGR10_1X10:
-	case V4L2_MBUS_FMT_SGBRG10_1X10:
+	case MEDIA_BUS_FMT_SGRBG10_1X10:
+	case MEDIA_BUS_FMT_SRGGB10_1X10:
+	case MEDIA_BUS_FMT_SBGGR10_1X10:
+	case MEDIA_BUS_FMT_SGBRG10_1X10:
 		fmtidx = 0;
 		break;
-	case V4L2_MBUS_FMT_SGRBG10_DPCM8_1X8:
-	case V4L2_MBUS_FMT_SRGGB10_DPCM8_1X8:
-	case V4L2_MBUS_FMT_SBGGR10_DPCM8_1X8:
-	case V4L2_MBUS_FMT_SGBRG10_DPCM8_1X8:
+	case MEDIA_BUS_FMT_SGRBG10_DPCM8_1X8:
+	case MEDIA_BUS_FMT_SRGGB10_DPCM8_1X8:
+	case MEDIA_BUS_FMT_SBGGR10_DPCM8_1X8:
+	case MEDIA_BUS_FMT_SGBRG10_DPCM8_1X8:
 		fmtidx = 1;
 		break;
-	case V4L2_MBUS_FMT_YUYV8_2X8:
+	case MEDIA_BUS_FMT_YUYV8_2X8:
 		fmtidx = 2;
 		break;
 	default:
@@ -843,7 +843,7 @@ csi2_try_format(struct isp_csi2_device *csi2, struct v4l2_subdev_fh *fh,
 		unsigned int pad, struct v4l2_mbus_framefmt *fmt,
 		enum v4l2_subdev_format_whence which)
 {
-	enum v4l2_mbus_pixelcode pixelcode;
+	u32 pixelcode;
 	struct v4l2_mbus_framefmt *format;
 	const struct isp_format_info *info;
 	unsigned int i;
@@ -858,7 +858,7 @@ csi2_try_format(struct isp_csi2_device *csi2, struct v4l2_subdev_fh *fh,
 
 		/* If not found, use SGRBG10 as default */
 		if (i >= ARRAY_SIZE(csi2_input_fmts))
-			fmt->code = V4L2_MBUS_FMT_SGRBG10_1X10;
+			fmt->code = MEDIA_BUS_FMT_SGRBG10_1X10;
 
 		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
 		fmt->height = clamp_t(u32, fmt->height, 1, 8191);
@@ -1029,7 +1029,7 @@ static int csi2_init_formats(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
 	memset(&format, 0, sizeof(format));
 	format.pad = CSI2_PAD_SINK;
 	format.which = fh ? V4L2_SUBDEV_FORMAT_TRY : V4L2_SUBDEV_FORMAT_ACTIVE;
-	format.format.code = V4L2_MBUS_FMT_SGRBG10_1X10;
+	format.format.code = MEDIA_BUS_FMT_SGRBG10_1X10;
 	format.format.width = 4096;
 	format.format.height = 4096;
 	csi2_set_format(sd, fh, &format);
diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c
index 605f57ef0a4..dd9eed45d85 100644
--- a/drivers/media/platform/omap3isp/isppreview.c
+++ b/drivers/media/platform/omap3isp/isppreview.c
@@ -964,18 +964,16 @@ static void preview_setup_hw(struct isp_prev_device *prev, u32 update,
  * @prev: pointer to previewer private structure
  * @pixelcode: pixel code
  */
-static void
-preview_config_ycpos(struct isp_prev_device *prev,
-		     enum v4l2_mbus_pixelcode pixelcode)
+static void preview_config_ycpos(struct isp_prev_device *prev, u32 pixelcode)
 {
 	struct isp_device *isp = to_isp_device(prev);
 	enum preview_ycpos_mode mode;
 
 	switch (pixelcode) {
-	case V4L2_MBUS_FMT_YUYV8_1X16:
+	case MEDIA_BUS_FMT_YUYV8_1X16:
 		mode = YCPOS_CrYCbY;
 		break;
-	case V4L2_MBUS_FMT_UYVY8_1X16:
+	case MEDIA_BUS_FMT_UYVY8_1X16:
 		mode = YCPOS_YCrYCb;
 		break;
 	default:
@@ -1028,16 +1026,16 @@ static void preview_config_input_format(struct isp_prev_device *prev,
 			    ISPPRV_PCR_WIDTH);
 
 	switch (info->flavor) {
-	case V4L2_MBUS_FMT_SGRBG8_1X8:
+	case MEDIA_BUS_FMT_SGRBG8_1X8:
 		prev->params.cfa_order = 0;
 		break;
-	case V4L2_MBUS_FMT_SRGGB8_1X8:
+	case MEDIA_BUS_FMT_SRGGB8_1X8:
 		prev->params.cfa_order = 1;
 		break;
-	case V4L2_MBUS_FMT_SBGGR8_1X8:
+	case MEDIA_BUS_FMT_SBGGR8_1X8:
 		prev->params.cfa_order = 2;
 		break;
-	case V4L2_MBUS_FMT_SGBRG8_1X8:
+	case MEDIA_BUS_FMT_SGBRG8_1X8:
 		prev->params.cfa_order = 3;
 		break;
 	default:
@@ -1078,8 +1076,8 @@ static void preview_config_input_size(struct isp_prev_device *prev, u32 active)
 	unsigned int elv = prev->crop.top + prev->crop.height - 1;
 	u32 features;
 
-	if (format->code != V4L2_MBUS_FMT_Y8_1X8 &&
-	    format->code != V4L2_MBUS_FMT_Y10_1X10) {
+	if (format->code != MEDIA_BUS_FMT_Y8_1X8 &&
+	    format->code != MEDIA_BUS_FMT_Y10_1X10) {
 		sph -= 2;
 		eph += 2;
 		slv -= 2;
@@ -1709,21 +1707,21 @@ __preview_get_crop(struct isp_prev_device *prev, struct v4l2_subdev_fh *fh,
 
 /* previewer format descriptions */
 static const unsigned int preview_input_fmts[] = {
-	V4L2_MBUS_FMT_Y8_1X8,
-	V4L2_MBUS_FMT_SGRBG8_1X8,
-	V4L2_MBUS_FMT_SRGGB8_1X8,
-	V4L2_MBUS_FMT_SBGGR8_1X8,
-	V4L2_MBUS_FMT_SGBRG8_1X8,
-	V4L2_MBUS_FMT_Y10_1X10,
-	V4L2_MBUS_FMT_SGRBG10_1X10,
-	V4L2_MBUS_FMT_SRGGB10_1X10,
-	V4L2_MBUS_FMT_SBGGR10_1X10,
-	V4L2_MBUS_FMT_SGBRG10_1X10,
+	MEDIA_BUS_FMT_Y8_1X8,
+	MEDIA_BUS_FMT_SGRBG8_1X8,
+	MEDIA_BUS_FMT_SRGGB8_1X8,
+	MEDIA_BUS_FMT_SBGGR8_1X8,
+	MEDIA_BUS_FMT_SGBRG8_1X8,
+	MEDIA_BUS_FMT_Y10_1X10,
+	MEDIA_BUS_FMT_SGRBG10_1X10,
+	MEDIA_BUS_FMT_SRGGB10_1X10,
+	MEDIA_BUS_FMT_SBGGR10_1X10,
+	MEDIA_BUS_FMT_SGBRG10_1X10,
 };
 
 static const unsigned int preview_output_fmts[] = {
-	V4L2_MBUS_FMT_UYVY8_1X16,
-	V4L2_MBUS_FMT_YUYV8_1X16,
+	MEDIA_BUS_FMT_UYVY8_1X16,
+	MEDIA_BUS_FMT_YUYV8_1X16,
 };
 
 /*
@@ -1742,7 +1740,7 @@ static void preview_try_format(struct isp_prev_device *prev,
 			       struct v4l2_mbus_framefmt *fmt,
 			       enum v4l2_subdev_format_whence which)
 {
-	enum v4l2_mbus_pixelcode pixelcode;
+	u32 pixelcode;
 	struct v4l2_rect *crop;
 	unsigned int i;
 
@@ -1774,7 +1772,7 @@ static void preview_try_format(struct isp_prev_device *prev,
 
 		/* If not found, use SGRBG10 as default */
 		if (i >= ARRAY_SIZE(preview_input_fmts))
-			fmt->code = V4L2_MBUS_FMT_SGRBG10_1X10;
+			fmt->code = MEDIA_BUS_FMT_SGRBG10_1X10;
 		break;
 
 	case PREV_PAD_SOURCE:
@@ -1782,13 +1780,13 @@ static void preview_try_format(struct isp_prev_device *prev,
 		*fmt = *__preview_get_format(prev, fh, PREV_PAD_SINK, which);
 
 		switch (pixelcode) {
-		case V4L2_MBUS_FMT_YUYV8_1X16:
-		case V4L2_MBUS_FMT_UYVY8_1X16:
+		case MEDIA_BUS_FMT_YUYV8_1X16:
+		case MEDIA_BUS_FMT_UYVY8_1X16:
 			fmt->code = pixelcode;
 			break;
 
 		default:
-			fmt->code = V4L2_MBUS_FMT_YUYV8_1X16;
+			fmt->code = MEDIA_BUS_FMT_YUYV8_1X16;
 			break;
 		}
 
@@ -1843,8 +1841,8 @@ static void preview_try_crop(struct isp_prev_device *prev,
 	 * and no columns in other modes. Increase the margins based on the sink
 	 * format.
 	 */
-	if (sink->code != V4L2_MBUS_FMT_Y8_1X8 &&
-	    sink->code != V4L2_MBUS_FMT_Y10_1X10) {
+	if (sink->code != MEDIA_BUS_FMT_Y8_1X8 &&
+	    sink->code != MEDIA_BUS_FMT_Y10_1X10) {
 		left += 2;
 		right -= 2;
 		top += 2;
@@ -2092,7 +2090,7 @@ static int preview_init_formats(struct v4l2_subdev *sd,
 	memset(&format, 0, sizeof(format));
 	format.pad = PREV_PAD_SINK;
 	format.which = fh ? V4L2_SUBDEV_FORMAT_TRY : V4L2_SUBDEV_FORMAT_ACTIVE;
-	format.format.code = V4L2_MBUS_FMT_SGRBG10_1X10;
+	format.format.code = MEDIA_BUS_FMT_SGRBG10_1X10;
 	format.format.width = 4096;
 	format.format.height = 4096;
 	preview_set_format(sd, fh, &format);
diff --git a/drivers/media/platform/omap3isp/ispresizer.c b/drivers/media/platform/omap3isp/ispresizer.c
index 05d1ace5745..2b9bc483987 100644
--- a/drivers/media/platform/omap3isp/ispresizer.c
+++ b/drivers/media/platform/omap3isp/ispresizer.c
@@ -198,17 +198,16 @@ static void resizer_set_bilinear(struct isp_res_device *res,
  * @res: Device context.
  * @pixelcode: pixel code.
  */
-static void resizer_set_ycpos(struct isp_res_device *res,
-			      enum v4l2_mbus_pixelcode pixelcode)
+static void resizer_set_ycpos(struct isp_res_device *res, u32 pixelcode)
 {
 	struct isp_device *isp = to_isp_device(res);
 
 	switch (pixelcode) {
-	case V4L2_MBUS_FMT_YUYV8_1X16:
+	case MEDIA_BUS_FMT_YUYV8_1X16:
 		isp_reg_set(isp, OMAP3_ISP_IOMEM_RESZ, ISPRSZ_CNT,
 			    ISPRSZ_CNT_YCPOS);
 		break;
-	case V4L2_MBUS_FMT_UYVY8_1X16:
+	case MEDIA_BUS_FMT_UYVY8_1X16:
 		isp_reg_clr(isp, OMAP3_ISP_IOMEM_RESZ, ISPRSZ_CNT,
 			    ISPRSZ_CNT_YCPOS);
 		break;
@@ -1348,8 +1347,8 @@ static int resizer_set_selection(struct v4l2_subdev *sd,
 
 /* resizer pixel formats */
 static const unsigned int resizer_formats[] = {
-	V4L2_MBUS_FMT_UYVY8_1X16,
-	V4L2_MBUS_FMT_YUYV8_1X16,
+	MEDIA_BUS_FMT_UYVY8_1X16,
+	MEDIA_BUS_FMT_YUYV8_1X16,
 };
 
 static unsigned int resizer_max_in_width(struct isp_res_device *res)
@@ -1385,9 +1384,9 @@ static void resizer_try_format(struct isp_res_device *res,
 
 	switch (pad) {
 	case RESZ_PAD_SINK:
-		if (fmt->code != V4L2_MBUS_FMT_YUYV8_1X16 &&
-		    fmt->code != V4L2_MBUS_FMT_UYVY8_1X16)
-			fmt->code = V4L2_MBUS_FMT_YUYV8_1X16;
+		if (fmt->code != MEDIA_BUS_FMT_YUYV8_1X16 &&
+		    fmt->code != MEDIA_BUS_FMT_UYVY8_1X16)
+			fmt->code = MEDIA_BUS_FMT_YUYV8_1X16;
 
 		fmt->width = clamp_t(u32, fmt->width, MIN_IN_WIDTH,
 				     resizer_max_in_width(res));
@@ -1571,7 +1570,7 @@ static int resizer_init_formats(struct v4l2_subdev *sd,
 	memset(&format, 0, sizeof(format));
 	format.pad = RESZ_PAD_SINK;
 	format.which = fh ? V4L2_SUBDEV_FORMAT_TRY : V4L2_SUBDEV_FORMAT_ACTIVE;
-	format.format.code = V4L2_MBUS_FMT_YUYV8_1X16;
+	format.format.code = MEDIA_BUS_FMT_YUYV8_1X16;
 	format.format.width = 4096;
 	format.format.height = 4096;
 	resizer_set_format(sd, fh, &format);
diff --git a/drivers/media/platform/omap3isp/ispvideo.c b/drivers/media/platform/omap3isp/ispvideo.c
index bc38c88c7bd..b463fe172d1 100644
--- a/drivers/media/platform/omap3isp/ispvideo.c
+++ b/drivers/media/platform/omap3isp/ispvideo.c
@@ -39,74 +39,74 @@
  * corresponding in-memory formats to the table below!!!
  */
 static struct isp_format_info formats[] = {
-	{ V4L2_MBUS_FMT_Y8_1X8, V4L2_MBUS_FMT_Y8_1X8,
-	  V4L2_MBUS_FMT_Y8_1X8, V4L2_MBUS_FMT_Y8_1X8,
+	{ MEDIA_BUS_FMT_Y8_1X8, MEDIA_BUS_FMT_Y8_1X8,
+	  MEDIA_BUS_FMT_Y8_1X8, MEDIA_BUS_FMT_Y8_1X8,
 	  V4L2_PIX_FMT_GREY, 8, 1, },
-	{ V4L2_MBUS_FMT_Y10_1X10, V4L2_MBUS_FMT_Y10_1X10,
-	  V4L2_MBUS_FMT_Y10_1X10, V4L2_MBUS_FMT_Y8_1X8,
+	{ MEDIA_BUS_FMT_Y10_1X10, MEDIA_BUS_FMT_Y10_1X10,
+	  MEDIA_BUS_FMT_Y10_1X10, MEDIA_BUS_FMT_Y8_1X8,
 	  V4L2_PIX_FMT_Y10, 10, 2, },
-	{ V4L2_MBUS_FMT_Y12_1X12, V4L2_MBUS_FMT_Y10_1X10,
-	  V4L2_MBUS_FMT_Y12_1X12, V4L2_MBUS_FMT_Y8_1X8,
+	{ MEDIA_BUS_FMT_Y12_1X12, MEDIA_BUS_FMT_Y10_1X10,
+	  MEDIA_BUS_FMT_Y12_1X12, MEDIA_BUS_FMT_Y8_1X8,
 	  V4L2_PIX_FMT_Y12, 12, 2, },
-	{ V4L2_MBUS_FMT_SBGGR8_1X8, V4L2_MBUS_FMT_SBGGR8_1X8,
-	  V4L2_MBUS_FMT_SBGGR8_1X8, V4L2_MBUS_FMT_SBGGR8_1X8,
+	{ MEDIA_BUS_FMT_SBGGR8_1X8, MEDIA_BUS_FMT_SBGGR8_1X8,
+	  MEDIA_BUS_FMT_SBGGR8_1X8, MEDIA_BUS_FMT_SBGGR8_1X8,
 	  V4L2_PIX_FMT_SBGGR8, 8, 1, },
-	{ V4L2_MBUS_FMT_SGBRG8_1X8, V4L2_MBUS_FMT_SGBRG8_1X8,
-	  V4L2_MBUS_FMT_SGBRG8_1X8, V4L2_MBUS_FMT_SGBRG8_1X8,
+	{ MEDIA_BUS_FMT_SGBRG8_1X8, MEDIA_BUS_FMT_SGBRG8_1X8,
+	  MEDIA_BUS_FMT_SGBRG8_1X8, MEDIA_BUS_FMT_SGBRG8_1X8,
 	  V4L2_PIX_FMT_SGBRG8, 8, 1, },
-	{ V4L2_MBUS_FMT_SGRBG8_1X8, V4L2_MBUS_FMT_SGRBG8_1X8,
-	  V4L2_MBUS_FMT_SGRBG8_1X8, V4L2_MBUS_FMT_SGRBG8_1X8,
+	{ MEDIA_BUS_FMT_SGRBG8_1X8, MEDIA_BUS_FMT_SGRBG8_1X8,
+	  MEDIA_BUS_FMT_SGRBG8_1X8, MEDIA_BUS_FMT_SGRBG8_1X8,
 	  V4L2_PIX_FMT_SGRBG8, 8, 1, },
-	{ V4L2_MBUS_FMT_SRGGB8_1X8, V4L2_MBUS_FMT_SRGGB8_1X8,
-	  V4L2_MBUS_FMT_SRGGB8_1X8, V4L2_MBUS_FMT_SRGGB8_1X8,
+	{ MEDIA_BUS_FMT_SRGGB8_1X8, MEDIA_BUS_FMT_SRGGB8_1X8,
+	  MEDIA_BUS_FMT_SRGGB8_1X8, MEDIA_BUS_FMT_SRGGB8_1X8,
 	  V4L2_PIX_FMT_SRGGB8, 8, 1, },
-	{ V4L2_MBUS_FMT_SBGGR10_DPCM8_1X8, V4L2_MBUS_FMT_SBGGR10_DPCM8_1X8,
-	  V4L2_MBUS_FMT_SBGGR10_1X10, 0,
+	{ MEDIA_BUS_FMT_SBGGR10_DPCM8_1X8, MEDIA_BUS_FMT_SBGGR10_DPCM8_1X8,
+	  MEDIA_BUS_FMT_SBGGR10_1X10, 0,
 	  V4L2_PIX_FMT_SBGGR10DPCM8, 8, 1, },
-	{ V4L2_MBUS_FMT_SGBRG10_DPCM8_1X8, V4L2_MBUS_FMT_SGBRG10_DPCM8_1X8,
-	  V4L2_MBUS_FMT_SGBRG10_1X10, 0,
+	{ MEDIA_BUS_FMT_SGBRG10_DPCM8_1X8, MEDIA_BUS_FMT_SGBRG10_DPCM8_1X8,
+	  MEDIA_BUS_FMT_SGBRG10_1X10, 0,
 	  V4L2_PIX_FMT_SGBRG10DPCM8, 8, 1, },
-	{ V4L2_MBUS_FMT_SGRBG10_DPCM8_1X8, V4L2_MBUS_FMT_SGRBG10_DPCM8_1X8,
-	  V4L2_MBUS_FMT_SGRBG10_1X10, 0,
+	{ MEDIA_BUS_FMT_SGRBG10_DPCM8_1X8, MEDIA_BUS_FMT_SGRBG10_DPCM8_1X8,
+	  MEDIA_BUS_FMT_SGRBG10_1X10, 0,
 	  V4L2_PIX_FMT_SGRBG10DPCM8, 8, 1, },
-	{ V4L2_MBUS_FMT_SRGGB10_DPCM8_1X8, V4L2_MBUS_FMT_SRGGB10_DPCM8_1X8,
-	  V4L2_MBUS_FMT_SRGGB10_1X10, 0,
+	{ MEDIA_BUS_FMT_SRGGB10_DPCM8_1X8, MEDIA_BUS_FMT_SRGGB10_DPCM8_1X8,
+	  MEDIA_BUS_FMT_SRGGB10_1X10, 0,
 	  V4L2_PIX_FMT_SRGGB10DPCM8, 8, 1, },
-	{ V4L2_MBUS_FMT_SBGGR10_1X10, V4L2_MBUS_FMT_SBGGR10_1X10,
-	  V4L2_MBUS_FMT_SBGGR10_1X10, V4L2_MBUS_FMT_SBGGR8_1X8,
+	{ MEDIA_BUS_FMT_SBGGR10_1X10, MEDIA_BUS_FMT_SBGGR10_1X10,
+	  MEDIA_BUS_FMT_SBGGR10_1X10, MEDIA_BUS_FMT_SBGGR8_1X8,
 	  V4L2_PIX_FMT_SBGGR10, 10, 2, },
-	{ V4L2_MBUS_FMT_SGBRG10_1X10, V4L2_MBUS_FMT_SGBRG10_1X10,
-	  V4L2_MBUS_FMT_SGBRG10_1X10, V4L2_MBUS_FMT_SGBRG8_1X8,
+	{ MEDIA_BUS_FMT_SGBRG10_1X10, MEDIA_BUS_FMT_SGBRG10_1X10,
+	  MEDIA_BUS_FMT_SGBRG10_1X10, MEDIA_BUS_FMT_SGBRG8_1X8,
 	  V4L2_PIX_FMT_SGBRG10, 10, 2, },
-	{ V4L2_MBUS_FMT_SGRBG10_1X10, V4L2_MBUS_FMT_SGRBG10_1X10,
-	  V4L2_MBUS_FMT_SGRBG10_1X10, V4L2_MBUS_FMT_SGRBG8_1X8,
+	{ MEDIA_BUS_FMT_SGRBG10_1X10, MEDIA_BUS_FMT_SGRBG10_1X10,
+	  MEDIA_BUS_FMT_SGRBG10_1X10, MEDIA_BUS_FMT_SGRBG8_1X8,
 	  V4L2_PIX_FMT_SGRBG10, 10, 2, },
-	{ V4L2_MBUS_FMT_SRGGB10_1X10, V4L2_MBUS_FMT_SRGGB10_1X10,
-	  V4L2_MBUS_FMT_SRGGB10_1X10, V4L2_MBUS_FMT_SRGGB8_1X8,
+	{ MEDIA_BUS_FMT_SRGGB10_1X10, MEDIA_BUS_FMT_SRGGB10_1X10,
+	  MEDIA_BUS_FMT_SRGGB10_1X10, MEDIA_BUS_FMT_SRGGB8_1X8,
 	  V4L2_PIX_FMT_SRGGB10, 10, 2, },
-	{ V4L2_MBUS_FMT_SBGGR12_1X12, V4L2_MBUS_FMT_SBGGR10_1X10,
-	  V4L2_MBUS_FMT_SBGGR12_1X12, V4L2_MBUS_FMT_SBGGR8_1X8,
+	{ MEDIA_BUS_FMT_SBGGR12_1X12, MEDIA_BUS_FMT_SBGGR10_1X10,
+	  MEDIA_BUS_FMT_SBGGR12_1X12, MEDIA_BUS_FMT_SBGGR8_1X8,
 	  V4L2_PIX_FMT_SBGGR12, 12, 2, },
-	{ V4L2_MBUS_FMT_SGBRG12_1X12, V4L2_MBUS_FMT_SGBRG10_1X10,
-	  V4L2_MBUS_FMT_SGBRG12_1X12, V4L2_MBUS_FMT_SGBRG8_1X8,
+	{ MEDIA_BUS_FMT_SGBRG12_1X12, MEDIA_BUS_FMT_SGBRG10_1X10,
+	  MEDIA_BUS_FMT_SGBRG12_1X12, MEDIA_BUS_FMT_SGBRG8_1X8,
 	  V4L2_PIX_FMT_SGBRG12, 12, 2, },
-	{ V4L2_MBUS_FMT_SGRBG12_1X12, V4L2_MBUS_FMT_SGRBG10_1X10,
-	  V4L2_MBUS_FMT_SGRBG12_1X12, V4L2_MBUS_FMT_SGRBG8_1X8,
+	{ MEDIA_BUS_FMT_SGRBG12_1X12, MEDIA_BUS_FMT_SGRBG10_1X10,
+	  MEDIA_BUS_FMT_SGRBG12_1X12, MEDIA_BUS_FMT_SGRBG8_1X8,
 	  V4L2_PIX_FMT_SGRBG12, 12, 2, },
-	{ V4L2_MBUS_FMT_SRGGB12_1X12, V4L2_MBUS_FMT_SRGGB10_1X10,
-	  V4L2_MBUS_FMT_SRGGB12_1X12, V4L2_MBUS_FMT_SRGGB8_1X8,
+	{ MEDIA_BUS_FMT_SRGGB12_1X12, MEDIA_BUS_FMT_SRGGB10_1X10,
+	  MEDIA_BUS_FMT_SRGGB12_1X12, MEDIA_BUS_FMT_SRGGB8_1X8,
 	  V4L2_PIX_FMT_SRGGB12, 12, 2, },
-	{ V4L2_MBUS_FMT_UYVY8_1X16, V4L2_MBUS_FMT_UYVY8_1X16,
-	  V4L2_MBUS_FMT_UYVY8_1X16, 0,
+	{ MEDIA_BUS_FMT_UYVY8_1X16, MEDIA_BUS_FMT_UYVY8_1X16,
+	  MEDIA_BUS_FMT_UYVY8_1X16, 0,
 	  V4L2_PIX_FMT_UYVY, 16, 2, },
-	{ V4L2_MBUS_FMT_YUYV8_1X16, V4L2_MBUS_FMT_YUYV8_1X16,
-	  V4L2_MBUS_FMT_YUYV8_1X16, 0,
+	{ MEDIA_BUS_FMT_YUYV8_1X16, MEDIA_BUS_FMT_YUYV8_1X16,
+	  MEDIA_BUS_FMT_YUYV8_1X16, 0,
 	  V4L2_PIX_FMT_YUYV, 16, 2, },
-	{ V4L2_MBUS_FMT_UYVY8_2X8, V4L2_MBUS_FMT_UYVY8_2X8,
-	  V4L2_MBUS_FMT_UYVY8_2X8, 0,
+	{ MEDIA_BUS_FMT_UYVY8_2X8, MEDIA_BUS_FMT_UYVY8_2X8,
+	  MEDIA_BUS_FMT_UYVY8_2X8, 0,
 	  V4L2_PIX_FMT_UYVY, 8, 2, },
-	{ V4L2_MBUS_FMT_YUYV8_2X8, V4L2_MBUS_FMT_YUYV8_2X8,
-	  V4L2_MBUS_FMT_YUYV8_2X8, 0,
+	{ MEDIA_BUS_FMT_YUYV8_2X8, MEDIA_BUS_FMT_YUYV8_2X8,
+	  MEDIA_BUS_FMT_YUYV8_2X8, 0,
 	  V4L2_PIX_FMT_YUYV, 8, 2, },
 	/* Empty entry to catch the unsupported pixel code (0) used by the CCDC
 	 * module and avoid NULL pointer dereferences.
@@ -114,8 +114,7 @@ static struct isp_format_info formats[] = {
 	{ 0, }
 };
 
-const struct isp_format_info *
-omap3isp_video_format_info(enum v4l2_mbus_pixelcode code)
+const struct isp_format_info *omap3isp_video_format_info(u32 code)
 {
 	unsigned int i;
 
diff --git a/drivers/media/platform/omap3isp/ispvideo.h b/drivers/media/platform/omap3isp/ispvideo.h
index 0b7efedc3da..4071dd7060e 100644
--- a/drivers/media/platform/omap3isp/ispvideo.h
+++ b/drivers/media/platform/omap3isp/ispvideo.h
@@ -44,10 +44,10 @@ struct v4l2_pix_format;
  * @bpp: Bytes per pixel (when stored in memory)
  */
 struct isp_format_info {
-	enum v4l2_mbus_pixelcode code;
-	enum v4l2_mbus_pixelcode truncated;
-	enum v4l2_mbus_pixelcode uncompressed;
-	enum v4l2_mbus_pixelcode flavor;
+	u32 code;
+	u32 truncated;
+	u32 uncompressed;
+	u32 flavor;
 	u32 pixelformat;
 	unsigned int width;
 	unsigned int bpp;
@@ -206,6 +206,6 @@ void omap3isp_video_resume(struct isp_video *video, int continuous);
 struct media_pad *omap3isp_video_remote_pad(struct isp_video *video);
 
 const struct isp_format_info *
-omap3isp_video_format_info(enum v4l2_mbus_pixelcode code);
+omap3isp_video_format_info(u32 code);
 
 #endif /* OMAP3_ISP_VIDEO_H */
diff --git a/drivers/media/platform/s3c-camif/camif-capture.c b/drivers/media/platform/s3c-camif/camif-capture.c
index 4f81b4c9d11..aa40c8269ab 100644
--- a/drivers/media/platform/s3c-camif/camif-capture.c
+++ b/drivers/media/platform/s3c-camif/camif-capture.c
@@ -1218,11 +1218,11 @@ void s3c_camif_unregister_video_node(struct camif_dev *camif, int idx)
 }
 
 /* Media bus pixel formats supported at the camif input */
-static const enum v4l2_mbus_pixelcode camif_mbus_formats[] = {
-	V4L2_MBUS_FMT_YUYV8_2X8,
-	V4L2_MBUS_FMT_YVYU8_2X8,
-	V4L2_MBUS_FMT_UYVY8_2X8,
-	V4L2_MBUS_FMT_VYUY8_2X8,
+static const u32 camif_mbus_formats[] = {
+	MEDIA_BUS_FMT_YUYV8_2X8,
+	MEDIA_BUS_FMT_YVYU8_2X8,
+	MEDIA_BUS_FMT_UYVY8_2X8,
+	MEDIA_BUS_FMT_VYUY8_2X8,
 };
 
 /*
diff --git a/drivers/media/platform/s3c-camif/camif-regs.c b/drivers/media/platform/s3c-camif/camif-regs.c
index 6e0c9988a19..812fb3a7c4e 100644
--- a/drivers/media/platform/s3c-camif/camif-regs.c
+++ b/drivers/media/platform/s3c-camif/camif-regs.c
@@ -96,10 +96,10 @@ void camif_hw_set_effect(struct camif_dev *camif, unsigned int effect,
 }
 
 static const u32 src_pixfmt_map[8][2] = {
-	{ V4L2_MBUS_FMT_YUYV8_2X8, CISRCFMT_ORDER422_YCBYCR },
-	{ V4L2_MBUS_FMT_YVYU8_2X8, CISRCFMT_ORDER422_YCRYCB },
-	{ V4L2_MBUS_FMT_UYVY8_2X8, CISRCFMT_ORDER422_CBYCRY },
-	{ V4L2_MBUS_FMT_VYUY8_2X8, CISRCFMT_ORDER422_CRYCBY },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, CISRCFMT_ORDER422_YCBYCR },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, CISRCFMT_ORDER422_YCRYCB },
+	{ MEDIA_BUS_FMT_UYVY8_2X8, CISRCFMT_ORDER422_CBYCRY },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, CISRCFMT_ORDER422_CRYCBY },
 };
 
 /* Set camera input pixel format and resolution */
diff --git a/drivers/media/platform/s5p-tv/hdmi_drv.c b/drivers/media/platform/s5p-tv/hdmi_drv.c
index 37c8bd694c5..1d1ef211e11 100644
--- a/drivers/media/platform/s5p-tv/hdmi_drv.c
+++ b/drivers/media/platform/s5p-tv/hdmi_drv.c
@@ -660,7 +660,7 @@ static int hdmi_g_mbus_fmt(struct v4l2_subdev *sd,
 	memset(fmt, 0, sizeof(*fmt));
 	fmt->width = t->hact.end - t->hact.beg;
 	fmt->height = t->vact[0].end - t->vact[0].beg;
-	fmt->code = V4L2_MBUS_FMT_FIXED; /* means RGB888 */
+	fmt->code = MEDIA_BUS_FMT_FIXED; /* means RGB888 */
 	fmt->colorspace = V4L2_COLORSPACE_SRGB;
 	if (t->interlaced) {
 		fmt->field = V4L2_FIELD_INTERLACED;
diff --git a/drivers/media/platform/s5p-tv/sdo_drv.c b/drivers/media/platform/s5p-tv/sdo_drv.c
index 72cf892dd00..46f4d56aaa1 100644
--- a/drivers/media/platform/s5p-tv/sdo_drv.c
+++ b/drivers/media/platform/s5p-tv/sdo_drv.c
@@ -170,7 +170,7 @@ static int sdo_g_mbus_fmt(struct v4l2_subdev *sd,
 	/* all modes are 720 pixels wide */
 	fmt->width = 720;
 	fmt->height = sdev->fmt->height;
-	fmt->code = V4L2_MBUS_FMT_FIXED;
+	fmt->code = MEDIA_BUS_FMT_FIXED;
 	fmt->field = V4L2_FIELD_INTERLACED;
 	fmt->colorspace = V4L2_COLORSPACE_JPEG;
 	return 0;
diff --git a/drivers/media/platform/sh_vou.c b/drivers/media/platform/sh_vou.c
index e5f1d4c14f2..04766960945 100644
--- a/drivers/media/platform/sh_vou.c
+++ b/drivers/media/platform/sh_vou.c
@@ -680,7 +680,7 @@ static int sh_vou_s_fmt_vid_out(struct file *file, void *priv,
 	struct sh_vou_geometry geo;
 	struct v4l2_mbus_framefmt mbfmt = {
 		/* Revisit: is this the correct code? */
-		.code = V4L2_MBUS_FMT_YUYV8_2X8,
+		.code = MEDIA_BUS_FMT_YUYV8_2X8,
 		.field = V4L2_FIELD_INTERLACED,
 		.colorspace = V4L2_COLORSPACE_SMPTE170M,
 	};
@@ -733,7 +733,7 @@ static int sh_vou_s_fmt_vid_out(struct file *file, void *priv,
 	/* Sanity checks */
 	if ((unsigned)mbfmt.width > VOU_MAX_IMAGE_WIDTH ||
 	    (unsigned)mbfmt.height > img_height_max ||
-	    mbfmt.code != V4L2_MBUS_FMT_YUYV8_2X8)
+	    mbfmt.code != MEDIA_BUS_FMT_YUYV8_2X8)
 		return -EIO;
 
 	if (mbfmt.width != geo.output.width ||
@@ -943,7 +943,7 @@ static int sh_vou_s_crop(struct file *file, void *fh, const struct v4l2_crop *a)
 	struct sh_vou_geometry geo;
 	struct v4l2_mbus_framefmt mbfmt = {
 		/* Revisit: is this the correct code? */
-		.code = V4L2_MBUS_FMT_YUYV8_2X8,
+		.code = MEDIA_BUS_FMT_YUYV8_2X8,
 		.field = V4L2_FIELD_INTERLACED,
 		.colorspace = V4L2_COLORSPACE_SMPTE170M,
 	};
@@ -994,7 +994,7 @@ static int sh_vou_s_crop(struct file *file, void *fh, const struct v4l2_crop *a)
 	/* Sanity checks */
 	if ((unsigned)mbfmt.width > VOU_MAX_IMAGE_WIDTH ||
 	    (unsigned)mbfmt.height > img_height_max ||
-	    mbfmt.code != V4L2_MBUS_FMT_YUYV8_2X8)
+	    mbfmt.code != MEDIA_BUS_FMT_YUYV8_2X8)
 		return -EIO;
 
 	geo.output.width = mbfmt.width;
diff --git a/drivers/media/platform/soc_camera/atmel-isi.c b/drivers/media/platform/soc_camera/atmel-isi.c
index c5291b00105..ee5650f4ea2 100644
--- a/drivers/media/platform/soc_camera/atmel-isi.c
+++ b/drivers/media/platform/soc_camera/atmel-isi.c
@@ -105,25 +105,25 @@ static u32 isi_readl(struct atmel_isi *isi, u32 reg)
 }
 
 static int configure_geometry(struct atmel_isi *isi, u32 width,
-			u32 height, enum v4l2_mbus_pixelcode code)
+			u32 height, u32 code)
 {
 	u32 cfg2, cr;
 
 	switch (code) {
 	/* YUV, including grey */
-	case V4L2_MBUS_FMT_Y8_1X8:
+	case MEDIA_BUS_FMT_Y8_1X8:
 		cr = ISI_CFG2_GRAYSCALE;
 		break;
-	case V4L2_MBUS_FMT_VYUY8_2X8:
+	case MEDIA_BUS_FMT_VYUY8_2X8:
 		cr = ISI_CFG2_YCC_SWAP_MODE_3;
 		break;
-	case V4L2_MBUS_FMT_UYVY8_2X8:
+	case MEDIA_BUS_FMT_UYVY8_2X8:
 		cr = ISI_CFG2_YCC_SWAP_MODE_2;
 		break;
-	case V4L2_MBUS_FMT_YVYU8_2X8:
+	case MEDIA_BUS_FMT_YVYU8_2X8:
 		cr = ISI_CFG2_YCC_SWAP_MODE_1;
 		break;
-	case V4L2_MBUS_FMT_YUYV8_2X8:
+	case MEDIA_BUS_FMT_YUYV8_2X8:
 		cr = ISI_CFG2_YCC_SWAP_DEFAULT;
 		break;
 	/* RGB, TODO */
@@ -645,7 +645,7 @@ static int isi_camera_get_formats(struct soc_camera_device *icd,
 	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
 	int formats = 0, ret;
 	/* sensor format */
-	enum v4l2_mbus_pixelcode code;
+	u32 code;
 	/* soc camera host format */
 	const struct soc_mbus_pixelfmt *fmt;
 
@@ -670,10 +670,10 @@ static int isi_camera_get_formats(struct soc_camera_device *icd,
 	}
 
 	switch (code) {
-	case V4L2_MBUS_FMT_UYVY8_2X8:
-	case V4L2_MBUS_FMT_VYUY8_2X8:
-	case V4L2_MBUS_FMT_YUYV8_2X8:
-	case V4L2_MBUS_FMT_YVYU8_2X8:
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+	case MEDIA_BUS_FMT_YVYU8_2X8:
 		formats++;
 		if (xlate) {
 			xlate->host_fmt	= &isi_camera_formats[0];
diff --git a/drivers/media/platform/soc_camera/mx2_camera.c b/drivers/media/platform/soc_camera/mx2_camera.c
index 2347612a4cc..ce72bd26a6a 100644
--- a/drivers/media/platform/soc_camera/mx2_camera.c
+++ b/drivers/media/platform/soc_camera/mx2_camera.c
@@ -211,7 +211,7 @@ struct emma_prp_resize {
 
 /* prp configuration for a client-host fmt pair */
 struct mx2_fmt_cfg {
-	enum v4l2_mbus_pixelcode	in_fmt;
+	u32	in_fmt;
 	u32				out_fmt;
 	struct mx2_prp_cfg		cfg;
 };
@@ -309,7 +309,7 @@ static struct mx2_fmt_cfg mx27_emma_prp_table[] = {
 		}
 	},
 	{
-		.in_fmt		= V4L2_MBUS_FMT_UYVY8_2X8,
+		.in_fmt		= MEDIA_BUS_FMT_UYVY8_2X8,
 		.out_fmt	= V4L2_PIX_FMT_YUYV,
 		.cfg		= {
 			.channel	= 1,
@@ -323,7 +323,7 @@ static struct mx2_fmt_cfg mx27_emma_prp_table[] = {
 		}
 	},
 	{
-		.in_fmt		= V4L2_MBUS_FMT_YUYV8_2X8,
+		.in_fmt		= MEDIA_BUS_FMT_YUYV8_2X8,
 		.out_fmt	= V4L2_PIX_FMT_YUYV,
 		.cfg		= {
 			.channel	= 1,
@@ -337,7 +337,7 @@ static struct mx2_fmt_cfg mx27_emma_prp_table[] = {
 		}
 	},
 	{
-		.in_fmt		= V4L2_MBUS_FMT_YUYV8_2X8,
+		.in_fmt		= MEDIA_BUS_FMT_YUYV8_2X8,
 		.out_fmt	= V4L2_PIX_FMT_YUV420,
 		.cfg		= {
 			.channel	= 2,
@@ -351,7 +351,7 @@ static struct mx2_fmt_cfg mx27_emma_prp_table[] = {
 		}
 	},
 	{
-		.in_fmt		= V4L2_MBUS_FMT_UYVY8_2X8,
+		.in_fmt		= MEDIA_BUS_FMT_UYVY8_2X8,
 		.out_fmt	= V4L2_PIX_FMT_YUV420,
 		.cfg		= {
 			.channel	= 2,
@@ -366,9 +366,7 @@ static struct mx2_fmt_cfg mx27_emma_prp_table[] = {
 	},
 };
 
-static struct mx2_fmt_cfg *mx27_emma_prp_get_format(
-					enum v4l2_mbus_pixelcode in_fmt,
-					u32 out_fmt)
+static struct mx2_fmt_cfg *mx27_emma_prp_get_format(u32 in_fmt, u32 out_fmt)
 {
 	int i;
 
@@ -945,7 +943,7 @@ static int mx2_camera_get_formats(struct soc_camera_device *icd,
 	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
 	const struct soc_mbus_pixelfmt *fmt;
 	struct device *dev = icd->parent;
-	enum v4l2_mbus_pixelcode code;
+	u32 code;
 	int ret, formats = 0;
 
 	ret = v4l2_subdev_call(sd, video, enum_mbus_fmt, idx, &code);
@@ -959,8 +957,8 @@ static int mx2_camera_get_formats(struct soc_camera_device *icd,
 		return 0;
 	}
 
-	if (code == V4L2_MBUS_FMT_YUYV8_2X8 ||
-	    code == V4L2_MBUS_FMT_UYVY8_2X8) {
+	if (code == MEDIA_BUS_FMT_YUYV8_2X8 ||
+	    code == MEDIA_BUS_FMT_UYVY8_2X8) {
 		formats++;
 		if (xlate) {
 			/*
@@ -968,7 +966,7 @@ static int mx2_camera_get_formats(struct soc_camera_device *icd,
 			 * soc_mediabus.c
 			 */
 			xlate->host_fmt =
-				soc_mbus_get_fmtdesc(V4L2_MBUS_FMT_YUYV8_1_5X8);
+				soc_mbus_get_fmtdesc(MEDIA_BUS_FMT_YUYV8_1_5X8);
 			xlate->code	= code;
 			dev_dbg(dev, "Providing host format %s for sensor code %d\n",
 			       xlate->host_fmt->name, code);
@@ -976,11 +974,11 @@ static int mx2_camera_get_formats(struct soc_camera_device *icd,
 		}
 	}
 
-	if (code == V4L2_MBUS_FMT_UYVY8_2X8) {
+	if (code == MEDIA_BUS_FMT_UYVY8_2X8) {
 		formats++;
 		if (xlate) {
 			xlate->host_fmt =
-				soc_mbus_get_fmtdesc(V4L2_MBUS_FMT_YUYV8_2X8);
+				soc_mbus_get_fmtdesc(MEDIA_BUS_FMT_YUYV8_2X8);
 			xlate->code	= code;
 			dev_dbg(dev, "Providing host format %s for sensor code %d\n",
 				xlate->host_fmt->name, code);
diff --git a/drivers/media/platform/soc_camera/mx3_camera.c b/drivers/media/platform/soc_camera/mx3_camera.c
index 7696a873510..8e52ccce66d 100644
--- a/drivers/media/platform/soc_camera/mx3_camera.c
+++ b/drivers/media/platform/soc_camera/mx3_camera.c
@@ -656,7 +656,7 @@ static int mx3_camera_get_formats(struct soc_camera_device *icd, unsigned int id
 	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
 	struct device *dev = icd->parent;
 	int formats = 0, ret;
-	enum v4l2_mbus_pixelcode code;
+	u32 code;
 	const struct soc_mbus_pixelfmt *fmt;
 
 	ret = v4l2_subdev_call(sd, video, enum_mbus_fmt, idx, &code);
@@ -677,7 +677,7 @@ static int mx3_camera_get_formats(struct soc_camera_device *icd, unsigned int id
 		return 0;
 
 	switch (code) {
-	case V4L2_MBUS_FMT_SBGGR10_1X10:
+	case MEDIA_BUS_FMT_SBGGR10_1X10:
 		formats++;
 		if (xlate) {
 			xlate->host_fmt	= &mx3_camera_formats[0];
@@ -687,7 +687,7 @@ static int mx3_camera_get_formats(struct soc_camera_device *icd, unsigned int id
 				mx3_camera_formats[0].name, code);
 		}
 		break;
-	case V4L2_MBUS_FMT_Y10_1X10:
+	case MEDIA_BUS_FMT_Y10_1X10:
 		formats++;
 		if (xlate) {
 			xlate->host_fmt	= &mx3_camera_formats[1];
diff --git a/drivers/media/platform/soc_camera/omap1_camera.c b/drivers/media/platform/soc_camera/omap1_camera.c
index 74ce8b6b79f..e6b93281f24 100644
--- a/drivers/media/platform/soc_camera/omap1_camera.c
+++ b/drivers/media/platform/soc_camera/omap1_camera.c
@@ -140,7 +140,7 @@
 /* buffer for one video frame */
 struct omap1_cam_buf {
 	struct videobuf_buffer		vb;
-	enum v4l2_mbus_pixelcode	code;
+	u32	code;
 	int				inwork;
 	struct scatterlist		*sgbuf;
 	int				sgcount;
@@ -980,7 +980,7 @@ static void omap1_cam_clock_stop(struct soc_camera_host *ici)
 /* Duplicate standard formats based on host capability of byte swapping */
 static const struct soc_mbus_lookup omap1_cam_formats[] = {
 {
-	.code = V4L2_MBUS_FMT_UYVY8_2X8,
+	.code = MEDIA_BUS_FMT_UYVY8_2X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_YUYV,
 		.name			= "YUYV",
@@ -990,7 +990,7 @@ static const struct soc_mbus_lookup omap1_cam_formats[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_VYUY8_2X8,
+	.code = MEDIA_BUS_FMT_VYUY8_2X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_YVYU,
 		.name			= "YVYU",
@@ -1000,7 +1000,7 @@ static const struct soc_mbus_lookup omap1_cam_formats[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_YUYV8_2X8,
+	.code = MEDIA_BUS_FMT_YUYV8_2X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_UYVY,
 		.name			= "UYVY",
@@ -1010,7 +1010,7 @@ static const struct soc_mbus_lookup omap1_cam_formats[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_YVYU8_2X8,
+	.code = MEDIA_BUS_FMT_YVYU8_2X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_VYUY,
 		.name			= "VYUY",
@@ -1020,7 +1020,7 @@ static const struct soc_mbus_lookup omap1_cam_formats[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_RGB555_2X8_PADHI_BE,
+	.code = MEDIA_BUS_FMT_RGB555_2X8_PADHI_BE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_RGB555,
 		.name			= "RGB555",
@@ -1030,7 +1030,7 @@ static const struct soc_mbus_lookup omap1_cam_formats[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_RGB555_2X8_PADHI_LE,
+	.code = MEDIA_BUS_FMT_RGB555_2X8_PADHI_LE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_RGB555X,
 		.name			= "RGB555X",
@@ -1040,7 +1040,7 @@ static const struct soc_mbus_lookup omap1_cam_formats[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_RGB565_2X8_BE,
+	.code = MEDIA_BUS_FMT_RGB565_2X8_BE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_RGB565,
 		.name			= "RGB565",
@@ -1050,7 +1050,7 @@ static const struct soc_mbus_lookup omap1_cam_formats[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_RGB565_2X8_LE,
+	.code = MEDIA_BUS_FMT_RGB565_2X8_LE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_RGB565X,
 		.name			= "RGB565X",
@@ -1068,7 +1068,7 @@ static int omap1_cam_get_formats(struct soc_camera_device *icd,
 	struct v4l2_subdev *sd = soc_camera_to_subdev(icd);
 	struct device *dev = icd->parent;
 	int formats = 0, ret;
-	enum v4l2_mbus_pixelcode code;
+	u32 code;
 	const struct soc_mbus_pixelfmt *fmt;
 
 	ret = v4l2_subdev_call(sd, video, enum_mbus_fmt, idx, &code);
@@ -1088,14 +1088,14 @@ static int omap1_cam_get_formats(struct soc_camera_device *icd,
 		return 0;
 
 	switch (code) {
-	case V4L2_MBUS_FMT_YUYV8_2X8:
-	case V4L2_MBUS_FMT_YVYU8_2X8:
-	case V4L2_MBUS_FMT_UYVY8_2X8:
-	case V4L2_MBUS_FMT_VYUY8_2X8:
-	case V4L2_MBUS_FMT_RGB555_2X8_PADHI_BE:
-	case V4L2_MBUS_FMT_RGB555_2X8_PADHI_LE:
-	case V4L2_MBUS_FMT_RGB565_2X8_BE:
-	case V4L2_MBUS_FMT_RGB565_2X8_LE:
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+	case MEDIA_BUS_FMT_RGB555_2X8_PADHI_BE:
+	case MEDIA_BUS_FMT_RGB555_2X8_PADHI_LE:
+	case MEDIA_BUS_FMT_RGB565_2X8_BE:
+	case MEDIA_BUS_FMT_RGB565_2X8_LE:
 		formats++;
 		if (xlate) {
 			xlate->host_fmt	= soc_mbus_find_fmtdesc(code,
diff --git a/drivers/media/platform/soc_camera/pxa_camera.c b/drivers/media/platform/soc_camera/pxa_camera.c
index 66178fc9f9e..951226af0eb 100644
--- a/drivers/media/platform/soc_camera/pxa_camera.c
+++ b/drivers/media/platform/soc_camera/pxa_camera.c
@@ -187,7 +187,7 @@ struct pxa_cam_dma {
 struct pxa_buffer {
 	/* common v4l buffer stuff -- must be first */
 	struct videobuf_buffer		vb;
-	enum v4l2_mbus_pixelcode	code;
+	u32	code;
 	/* our descriptor lists for Y, U and V channels */
 	struct pxa_cam_dma		dmas[3];
 	int				inwork;
@@ -1253,7 +1253,7 @@ static int pxa_camera_get_formats(struct soc_camera_device *icd, unsigned int id
 	struct device *dev = icd->parent;
 	int formats = 0, ret;
 	struct pxa_cam *cam;
-	enum v4l2_mbus_pixelcode code;
+	u32 code;
 	const struct soc_mbus_pixelfmt *fmt;
 
 	ret = v4l2_subdev_call(sd, video, enum_mbus_fmt, idx, &code);
@@ -1283,7 +1283,7 @@ static int pxa_camera_get_formats(struct soc_camera_device *icd, unsigned int id
 	}
 
 	switch (code) {
-	case V4L2_MBUS_FMT_UYVY8_2X8:
+	case MEDIA_BUS_FMT_UYVY8_2X8:
 		formats++;
 		if (xlate) {
 			xlate->host_fmt	= &pxa_camera_formats[0];
@@ -1292,11 +1292,11 @@ static int pxa_camera_get_formats(struct soc_camera_device *icd, unsigned int id
 			dev_dbg(dev, "Providing format %s using code %d\n",
 				pxa_camera_formats[0].name, code);
 		}
-	case V4L2_MBUS_FMT_VYUY8_2X8:
-	case V4L2_MBUS_FMT_YUYV8_2X8:
-	case V4L2_MBUS_FMT_YVYU8_2X8:
-	case V4L2_MBUS_FMT_RGB565_2X8_LE:
-	case V4L2_MBUS_FMT_RGB555_2X8_PADHI_LE:
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+	case MEDIA_BUS_FMT_RGB565_2X8_LE:
+	case MEDIA_BUS_FMT_RGB555_2X8_PADHI_LE:
 		if (xlate)
 			dev_dbg(dev, "Providing format %s packed\n",
 				fmt->name);
diff --git a/drivers/media/platform/soc_camera/rcar_vin.c b/drivers/media/platform/soc_camera/rcar_vin.c
index 20defcb8b31..8d8438b10b8 100644
--- a/drivers/media/platform/soc_camera/rcar_vin.c
+++ b/drivers/media/platform/soc_camera/rcar_vin.c
@@ -272,16 +272,16 @@ static int rcar_vin_setup(struct rcar_vin_priv *priv)
 
 	/* input interface */
 	switch (icd->current_fmt->code) {
-	case V4L2_MBUS_FMT_YUYV8_1X16:
+	case MEDIA_BUS_FMT_YUYV8_1X16:
 		/* BT.601/BT.1358 16bit YCbCr422 */
 		vnmc |= VNMC_INF_YUV16;
 		break;
-	case V4L2_MBUS_FMT_YUYV8_2X8:
+	case MEDIA_BUS_FMT_YUYV8_2X8:
 		/* BT.656 8bit YCbCr422 or BT.601 8bit YCbCr422 */
 		vnmc |= priv->pdata_flags & RCAR_VIN_BT656 ?
 			VNMC_INF_YUV8_BT656 : VNMC_INF_YUV8_BT601;
 		break;
-	case V4L2_MBUS_FMT_YUYV10_2X10:
+	case MEDIA_BUS_FMT_YUYV10_2X10:
 		/* BT.656 10bit YCbCr422 or BT.601 10bit YCbCr422 */
 		vnmc |= priv->pdata_flags & RCAR_VIN_BT656 ?
 			VNMC_INF_YUV10_BT656 : VNMC_INF_YUV10_BT601;
@@ -921,7 +921,7 @@ static int rcar_vin_get_formats(struct soc_camera_device *icd, unsigned int idx,
 	int ret, k, n;
 	int formats = 0;
 	struct rcar_vin_cam *cam;
-	enum v4l2_mbus_pixelcode code;
+	u32 code;
 	const struct soc_mbus_pixelfmt *fmt;
 
 	ret = v4l2_subdev_call(sd, video, enum_mbus_fmt, idx, &code);
@@ -1010,9 +1010,9 @@ static int rcar_vin_get_formats(struct soc_camera_device *icd, unsigned int idx,
 		cam->extra_fmt = NULL;
 
 	switch (code) {
-	case V4L2_MBUS_FMT_YUYV8_1X16:
-	case V4L2_MBUS_FMT_YUYV8_2X8:
-	case V4L2_MBUS_FMT_YUYV10_2X10:
+	case MEDIA_BUS_FMT_YUYV8_1X16:
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+	case MEDIA_BUS_FMT_YUYV10_2X10:
 		if (cam->extra_fmt)
 			break;
 
diff --git a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c b/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
index 20ad4a571d3..5f58ed99532 100644
--- a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
+++ b/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
@@ -149,7 +149,7 @@ struct sh_mobile_ceu_cam {
 	/* Camera cropping rectangle */
 	struct v4l2_rect rect;
 	const struct soc_mbus_pixelfmt *extra_fmt;
-	enum v4l2_mbus_pixelcode code;
+	u32 code;
 };
 
 static struct sh_mobile_ceu_buffer *to_ceu_vb(struct vb2_buffer *vb)
@@ -861,16 +861,16 @@ static int sh_mobile_ceu_set_bus_param(struct soc_camera_device *icd)
 	case V4L2_PIX_FMT_NV16:
 	case V4L2_PIX_FMT_NV61:
 		switch (cam->code) {
-		case V4L2_MBUS_FMT_UYVY8_2X8:
+		case MEDIA_BUS_FMT_UYVY8_2X8:
 			value = 0x00000000; /* Cb0, Y0, Cr0, Y1 */
 			break;
-		case V4L2_MBUS_FMT_VYUY8_2X8:
+		case MEDIA_BUS_FMT_VYUY8_2X8:
 			value = 0x00000100; /* Cr0, Y0, Cb0, Y1 */
 			break;
-		case V4L2_MBUS_FMT_YUYV8_2X8:
+		case MEDIA_BUS_FMT_YUYV8_2X8:
 			value = 0x00000200; /* Y0, Cb0, Y1, Cr0 */
 			break;
-		case V4L2_MBUS_FMT_YVYU8_2X8:
+		case MEDIA_BUS_FMT_YVYU8_2X8:
 			value = 0x00000300; /* Y0, Cr0, Y1, Cb0 */
 			break;
 		default:
@@ -1048,7 +1048,7 @@ static int sh_mobile_ceu_get_formats(struct soc_camera_device *icd, unsigned int
 	int ret, k, n;
 	int formats = 0;
 	struct sh_mobile_ceu_cam *cam;
-	enum v4l2_mbus_pixelcode code;
+	u32 code;
 	const struct soc_mbus_pixelfmt *fmt;
 
 	ret = v4l2_subdev_call(sd, video, enum_mbus_fmt, idx, &code);
@@ -1141,10 +1141,10 @@ static int sh_mobile_ceu_get_formats(struct soc_camera_device *icd, unsigned int
 		cam->extra_fmt = NULL;
 
 	switch (code) {
-	case V4L2_MBUS_FMT_UYVY8_2X8:
-	case V4L2_MBUS_FMT_VYUY8_2X8:
-	case V4L2_MBUS_FMT_YUYV8_2X8:
-	case V4L2_MBUS_FMT_YVYU8_2X8:
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+	case MEDIA_BUS_FMT_YVYU8_2X8:
 		if (cam->extra_fmt)
 			break;
 
diff --git a/drivers/media/platform/soc_camera/sh_mobile_csi2.c b/drivers/media/platform/soc_camera/sh_mobile_csi2.c
index 05dd21a35d6..c738e27a75d 100644
--- a/drivers/media/platform/soc_camera/sh_mobile_csi2.c
+++ b/drivers/media/platform/soc_camera/sh_mobile_csi2.c
@@ -59,28 +59,28 @@ static int sh_csi2_try_fmt(struct v4l2_subdev *sd,
 	switch (pdata->type) {
 	case SH_CSI2C:
 		switch (mf->code) {
-		case V4L2_MBUS_FMT_UYVY8_2X8:		/* YUV422 */
-		case V4L2_MBUS_FMT_YUYV8_1_5X8:		/* YUV420 */
-		case V4L2_MBUS_FMT_Y8_1X8:		/* RAW8 */
-		case V4L2_MBUS_FMT_SBGGR8_1X8:
-		case V4L2_MBUS_FMT_SGRBG8_1X8:
+		case MEDIA_BUS_FMT_UYVY8_2X8:		/* YUV422 */
+		case MEDIA_BUS_FMT_YUYV8_1_5X8:		/* YUV420 */
+		case MEDIA_BUS_FMT_Y8_1X8:		/* RAW8 */
+		case MEDIA_BUS_FMT_SBGGR8_1X8:
+		case MEDIA_BUS_FMT_SGRBG8_1X8:
 			break;
 		default:
 			/* All MIPI CSI-2 devices must support one of primary formats */
-			mf->code = V4L2_MBUS_FMT_YUYV8_2X8;
+			mf->code = MEDIA_BUS_FMT_YUYV8_2X8;
 		}
 		break;
 	case SH_CSI2I:
 		switch (mf->code) {
-		case V4L2_MBUS_FMT_Y8_1X8:		/* RAW8 */
-		case V4L2_MBUS_FMT_SBGGR8_1X8:
-		case V4L2_MBUS_FMT_SGRBG8_1X8:
-		case V4L2_MBUS_FMT_SBGGR10_1X10:	/* RAW10 */
-		case V4L2_MBUS_FMT_SBGGR12_1X12:	/* RAW12 */
+		case MEDIA_BUS_FMT_Y8_1X8:		/* RAW8 */
+		case MEDIA_BUS_FMT_SBGGR8_1X8:
+		case MEDIA_BUS_FMT_SGRBG8_1X8:
+		case MEDIA_BUS_FMT_SBGGR10_1X10:	/* RAW10 */
+		case MEDIA_BUS_FMT_SBGGR12_1X12:	/* RAW12 */
 			break;
 		default:
 			/* All MIPI CSI-2 devices must support one of primary formats */
-			mf->code = V4L2_MBUS_FMT_SBGGR8_1X8;
+			mf->code = MEDIA_BUS_FMT_SBGGR8_1X8;
 		}
 		break;
 	}
@@ -104,21 +104,21 @@ static int sh_csi2_s_fmt(struct v4l2_subdev *sd,
 		return -EINVAL;
 
 	switch (mf->code) {
-	case V4L2_MBUS_FMT_UYVY8_2X8:
+	case MEDIA_BUS_FMT_UYVY8_2X8:
 		tmp |= 0x1e;	/* YUV422 8 bit */
 		break;
-	case V4L2_MBUS_FMT_YUYV8_1_5X8:
+	case MEDIA_BUS_FMT_YUYV8_1_5X8:
 		tmp |= 0x18;	/* YUV420 8 bit */
 		break;
-	case V4L2_MBUS_FMT_RGB555_2X8_PADHI_BE:
+	case MEDIA_BUS_FMT_RGB555_2X8_PADHI_BE:
 		tmp |= 0x21;	/* RGB555 */
 		break;
-	case V4L2_MBUS_FMT_RGB565_2X8_BE:
+	case MEDIA_BUS_FMT_RGB565_2X8_BE:
 		tmp |= 0x22;	/* RGB565 */
 		break;
-	case V4L2_MBUS_FMT_Y8_1X8:
-	case V4L2_MBUS_FMT_SBGGR8_1X8:
-	case V4L2_MBUS_FMT_SGRBG8_1X8:
+	case MEDIA_BUS_FMT_Y8_1X8:
+	case MEDIA_BUS_FMT_SBGGR8_1X8:
+	case MEDIA_BUS_FMT_SGRBG8_1X8:
 		tmp |= 0x2a;	/* RAW8 */
 		break;
 	default:
diff --git a/drivers/media/platform/soc_camera/soc_camera.c b/drivers/media/platform/soc_camera/soc_camera.c
index 8e61b976da1..f4be2a1c659 100644
--- a/drivers/media/platform/soc_camera/soc_camera.c
+++ b/drivers/media/platform/soc_camera/soc_camera.c
@@ -460,7 +460,7 @@ static int soc_camera_init_user_formats(struct soc_camera_device *icd)
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	unsigned int i, fmts = 0, raw_fmts = 0;
 	int ret;
-	enum v4l2_mbus_pixelcode code;
+	u32 code;
 
 	while (!v4l2_subdev_call(sd, video, enum_mbus_fmt, raw_fmts, &code))
 		raw_fmts++;
diff --git a/drivers/media/platform/soc_camera/soc_camera_platform.c b/drivers/media/platform/soc_camera/soc_camera_platform.c
index ceaddfb85e4..f2ce1ab06d5 100644
--- a/drivers/media/platform/soc_camera/soc_camera_platform.c
+++ b/drivers/media/platform/soc_camera/soc_camera_platform.c
@@ -62,7 +62,7 @@ static struct v4l2_subdev_core_ops platform_subdev_core_ops = {
 };
 
 static int soc_camera_platform_enum_fmt(struct v4l2_subdev *sd, unsigned int index,
-					enum v4l2_mbus_pixelcode *code)
+					u32 *code)
 {
 	struct soc_camera_platform_info *p = v4l2_get_subdevdata(sd);
 
diff --git a/drivers/media/platform/soc_camera/soc_mediabus.c b/drivers/media/platform/soc_camera/soc_mediabus.c
index dc02deca756..1dbcd426683 100644
--- a/drivers/media/platform/soc_camera/soc_mediabus.c
+++ b/drivers/media/platform/soc_camera/soc_mediabus.c
@@ -17,7 +17,7 @@
 
 static const struct soc_mbus_lookup mbus_fmt[] = {
 {
-	.code = V4L2_MBUS_FMT_YUYV8_2X8,
+	.code = MEDIA_BUS_FMT_YUYV8_2X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_YUYV,
 		.name			= "YUYV",
@@ -27,7 +27,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_YVYU8_2X8,
+	.code = MEDIA_BUS_FMT_YVYU8_2X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_YVYU,
 		.name			= "YVYU",
@@ -37,7 +37,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_UYVY8_2X8,
+	.code = MEDIA_BUS_FMT_UYVY8_2X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_UYVY,
 		.name			= "UYVY",
@@ -47,7 +47,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_VYUY8_2X8,
+	.code = MEDIA_BUS_FMT_VYUY8_2X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_VYUY,
 		.name			= "VYUY",
@@ -57,7 +57,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_RGB555_2X8_PADHI_LE,
+	.code = MEDIA_BUS_FMT_RGB555_2X8_PADHI_LE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_RGB555,
 		.name			= "RGB555",
@@ -67,7 +67,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_RGB555_2X8_PADHI_BE,
+	.code = MEDIA_BUS_FMT_RGB555_2X8_PADHI_BE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_RGB555X,
 		.name			= "RGB555X",
@@ -77,7 +77,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_RGB565_2X8_LE,
+	.code = MEDIA_BUS_FMT_RGB565_2X8_LE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_RGB565,
 		.name			= "RGB565",
@@ -87,7 +87,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_RGB565_2X8_BE,
+	.code = MEDIA_BUS_FMT_RGB565_2X8_BE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_RGB565X,
 		.name			= "RGB565X",
@@ -97,7 +97,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_RGB666_1X18,
+	.code = MEDIA_BUS_FMT_RGB666_1X18,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_RGB32,
 		.name			= "RGB666/32bpp",
@@ -106,7 +106,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.order			= SOC_MBUS_ORDER_LE,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_RGB888_1X24,
+	.code = MEDIA_BUS_FMT_RGB888_1X24,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_RGB32,
 		.name			= "RGB888/32bpp",
@@ -115,7 +115,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.order			= SOC_MBUS_ORDER_LE,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_RGB888_2X12_BE,
+	.code = MEDIA_BUS_FMT_RGB888_2X12_BE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_RGB32,
 		.name			= "RGB888/32bpp",
@@ -124,7 +124,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.order			= SOC_MBUS_ORDER_BE,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_RGB888_2X12_LE,
+	.code = MEDIA_BUS_FMT_RGB888_2X12_LE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_RGB32,
 		.name			= "RGB888/32bpp",
@@ -133,7 +133,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.order			= SOC_MBUS_ORDER_LE,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SBGGR8_1X8,
+	.code = MEDIA_BUS_FMT_SBGGR8_1X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SBGGR8,
 		.name			= "Bayer 8 BGGR",
@@ -143,7 +143,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SBGGR10_1X10,
+	.code = MEDIA_BUS_FMT_SBGGR10_1X10,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SBGGR10,
 		.name			= "Bayer 10 BGGR",
@@ -153,7 +153,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_Y8_1X8,
+	.code = MEDIA_BUS_FMT_Y8_1X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_GREY,
 		.name			= "Grey",
@@ -163,7 +163,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_Y10_1X10,
+	.code = MEDIA_BUS_FMT_Y10_1X10,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_Y10,
 		.name			= "Grey 10bit",
@@ -173,7 +173,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SBGGR10_2X8_PADHI_LE,
+	.code = MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SBGGR10,
 		.name			= "Bayer 10 BGGR",
@@ -183,7 +183,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SBGGR10_2X8_PADLO_LE,
+	.code = MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_LE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SBGGR10,
 		.name			= "Bayer 10 BGGR",
@@ -193,7 +193,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SBGGR10_2X8_PADHI_BE,
+	.code = MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_BE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SBGGR10,
 		.name			= "Bayer 10 BGGR",
@@ -203,7 +203,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SBGGR10_2X8_PADLO_BE,
+	.code = MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_BE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SBGGR10,
 		.name			= "Bayer 10 BGGR",
@@ -213,7 +213,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_JPEG_1X8,
+	.code = MEDIA_BUS_FMT_JPEG_1X8,
 	.fmt = {
 		.fourcc                 = V4L2_PIX_FMT_JPEG,
 		.name                   = "JPEG",
@@ -223,7 +223,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_RGB444_2X8_PADHI_BE,
+	.code = MEDIA_BUS_FMT_RGB444_2X8_PADHI_BE,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_RGB444,
 		.name			= "RGB444",
@@ -233,7 +233,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_YUYV8_1_5X8,
+	.code = MEDIA_BUS_FMT_YUYV8_1_5X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_YUV420,
 		.name			= "YUYV 4:2:0",
@@ -243,7 +243,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_YVYU8_1_5X8,
+	.code = MEDIA_BUS_FMT_YVYU8_1_5X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_YVU420,
 		.name			= "YVYU 4:2:0",
@@ -253,7 +253,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_UYVY8_1X16,
+	.code = MEDIA_BUS_FMT_UYVY8_1X16,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_UYVY,
 		.name			= "UYVY 16bit",
@@ -263,7 +263,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_VYUY8_1X16,
+	.code = MEDIA_BUS_FMT_VYUY8_1X16,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_VYUY,
 		.name			= "VYUY 16bit",
@@ -273,7 +273,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_YUYV8_1X16,
+	.code = MEDIA_BUS_FMT_YUYV8_1X16,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_YUYV,
 		.name			= "YUYV 16bit",
@@ -283,7 +283,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_YVYU8_1X16,
+	.code = MEDIA_BUS_FMT_YVYU8_1X16,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_YVYU,
 		.name			= "YVYU 16bit",
@@ -293,7 +293,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SGRBG8_1X8,
+	.code = MEDIA_BUS_FMT_SGRBG8_1X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SGRBG8,
 		.name			= "Bayer 8 GRBG",
@@ -303,7 +303,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SGRBG10_DPCM8_1X8,
+	.code = MEDIA_BUS_FMT_SGRBG10_DPCM8_1X8,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SGRBG10DPCM8,
 		.name			= "Bayer 10 BGGR DPCM 8",
@@ -313,7 +313,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SGBRG10_1X10,
+	.code = MEDIA_BUS_FMT_SGBRG10_1X10,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SGBRG10,
 		.name			= "Bayer 10 GBRG",
@@ -323,7 +323,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SGRBG10_1X10,
+	.code = MEDIA_BUS_FMT_SGRBG10_1X10,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SGRBG10,
 		.name			= "Bayer 10 GRBG",
@@ -333,7 +333,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SRGGB10_1X10,
+	.code = MEDIA_BUS_FMT_SRGGB10_1X10,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SRGGB10,
 		.name			= "Bayer 10 RGGB",
@@ -343,7 +343,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SBGGR12_1X12,
+	.code = MEDIA_BUS_FMT_SBGGR12_1X12,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SBGGR12,
 		.name			= "Bayer 12 BGGR",
@@ -353,7 +353,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SGBRG12_1X12,
+	.code = MEDIA_BUS_FMT_SGBRG12_1X12,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SGBRG12,
 		.name			= "Bayer 12 GBRG",
@@ -363,7 +363,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SGRBG12_1X12,
+	.code = MEDIA_BUS_FMT_SGRBG12_1X12,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SGRBG12,
 		.name			= "Bayer 12 GRBG",
@@ -373,7 +373,7 @@ static const struct soc_mbus_lookup mbus_fmt[] = {
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
 }, {
-	.code = V4L2_MBUS_FMT_SRGGB12_1X12,
+	.code = MEDIA_BUS_FMT_SRGGB12_1X12,
 	.fmt = {
 		.fourcc			= V4L2_PIX_FMT_SRGGB12,
 		.name			= "Bayer 12 RGGB",
@@ -458,7 +458,7 @@ s32 soc_mbus_image_size(const struct soc_mbus_pixelfmt *mf,
 EXPORT_SYMBOL(soc_mbus_image_size);
 
 const struct soc_mbus_pixelfmt *soc_mbus_find_fmtdesc(
-	enum v4l2_mbus_pixelcode code,
+	u32 code,
 	const struct soc_mbus_lookup *lookup,
 	int n)
 {
@@ -473,7 +473,7 @@ const struct soc_mbus_pixelfmt *soc_mbus_find_fmtdesc(
 EXPORT_SYMBOL(soc_mbus_find_fmtdesc);
 
 const struct soc_mbus_pixelfmt *soc_mbus_get_fmtdesc(
-	enum v4l2_mbus_pixelcode code)
+	u32 code)
 {
 	return soc_mbus_find_fmtdesc(code, mbus_fmt, ARRAY_SIZE(mbus_fmt));
 }
diff --git a/drivers/media/platform/via-camera.c b/drivers/media/platform/via-camera.c
index ae6870cb833..2616483fce0 100644
--- a/drivers/media/platform/via-camera.c
+++ b/drivers/media/platform/via-camera.c
@@ -101,7 +101,7 @@ struct via_camera {
 	 */
 	struct v4l2_pix_format sensor_format;
 	struct v4l2_pix_format user_format;
-	enum v4l2_mbus_pixelcode mbus_code;
+	u32 mbus_code;
 };
 
 /*
@@ -143,12 +143,12 @@ static struct via_format {
 	__u8 *desc;
 	__u32 pixelformat;
 	int bpp;   /* Bytes per pixel */
-	enum v4l2_mbus_pixelcode mbus_code;
+	u32 mbus_code;
 } via_formats[] = {
 	{
 		.desc		= "YUYV 4:2:2",
 		.pixelformat	= V4L2_PIX_FMT_YUYV,
-		.mbus_code	= V4L2_MBUS_FMT_YUYV8_2X8,
+		.mbus_code	= MEDIA_BUS_FMT_YUYV8_2X8,
 		.bpp		= 2,
 	},
 	/* RGB444 and Bayer should be doable, but have never been
@@ -849,7 +849,7 @@ static const struct v4l2_pix_format viacam_def_pix_format = {
 	.sizeimage	= VGA_WIDTH * VGA_HEIGHT * 2,
 };
 
-static const enum v4l2_mbus_pixelcode via_def_mbus_code = V4L2_MBUS_FMT_YUYV8_2X8;
+static const u32 via_def_mbus_code = MEDIA_BUS_FMT_YUYV8_2X8;
 
 static int viacam_enum_fmt_vid_cap(struct file *filp, void *priv,
 		struct v4l2_fmtdesc *fmt)
diff --git a/drivers/media/platform/vsp1/vsp1_bru.c b/drivers/media/platform/vsp1/vsp1_bru.c
index a0c1984c733..b21f381a986 100644
--- a/drivers/media/platform/vsp1/vsp1_bru.c
+++ b/drivers/media/platform/vsp1/vsp1_bru.c
@@ -187,8 +187,8 @@ static int bru_enum_mbus_code(struct v4l2_subdev *subdev,
 			      struct v4l2_subdev_mbus_code_enum *code)
 {
 	static const unsigned int codes[] = {
-		V4L2_MBUS_FMT_ARGB8888_1X32,
-		V4L2_MBUS_FMT_AYUV8_1X32,
+		MEDIA_BUS_FMT_ARGB8888_1X32,
+		MEDIA_BUS_FMT_AYUV8_1X32,
 	};
 	struct v4l2_mbus_framefmt *format;
 
@@ -215,8 +215,8 @@ static int bru_enum_frame_size(struct v4l2_subdev *subdev,
 	if (fse->index)
 		return -EINVAL;
 
-	if (fse->code != V4L2_MBUS_FMT_ARGB8888_1X32 &&
-	    fse->code != V4L2_MBUS_FMT_AYUV8_1X32)
+	if (fse->code != MEDIA_BUS_FMT_ARGB8888_1X32 &&
+	    fse->code != MEDIA_BUS_FMT_AYUV8_1X32)
 		return -EINVAL;
 
 	fse->min_width = BRU_MIN_SIZE;
@@ -261,9 +261,9 @@ static void bru_try_format(struct vsp1_bru *bru, struct v4l2_subdev_fh *fh,
 	switch (pad) {
 	case BRU_PAD_SINK(0):
 		/* Default to YUV if the requested format is not supported. */
-		if (fmt->code != V4L2_MBUS_FMT_ARGB8888_1X32 &&
-		    fmt->code != V4L2_MBUS_FMT_AYUV8_1X32)
-			fmt->code = V4L2_MBUS_FMT_AYUV8_1X32;
+		if (fmt->code != MEDIA_BUS_FMT_ARGB8888_1X32 &&
+		    fmt->code != MEDIA_BUS_FMT_AYUV8_1X32)
+			fmt->code = MEDIA_BUS_FMT_AYUV8_1X32;
 		break;
 
 	default:
diff --git a/drivers/media/platform/vsp1/vsp1_hsit.c b/drivers/media/platform/vsp1/vsp1_hsit.c
index db2950a73c6..80bedc554ee 100644
--- a/drivers/media/platform/vsp1/vsp1_hsit.c
+++ b/drivers/media/platform/vsp1/vsp1_hsit.c
@@ -70,9 +70,9 @@ static int hsit_enum_mbus_code(struct v4l2_subdev *subdev,
 
 	if ((code->pad == HSIT_PAD_SINK && !hsit->inverse) |
 	    (code->pad == HSIT_PAD_SOURCE && hsit->inverse))
-		code->code = V4L2_MBUS_FMT_ARGB8888_1X32;
+		code->code = MEDIA_BUS_FMT_ARGB8888_1X32;
 	else
-		code->code = V4L2_MBUS_FMT_AHSV8888_1X32;
+		code->code = MEDIA_BUS_FMT_AHSV8888_1X32;
 
 	return 0;
 }
@@ -136,8 +136,8 @@ static int hsit_set_format(struct v4l2_subdev *subdev,
 		return 0;
 	}
 
-	format->code = hsit->inverse ? V4L2_MBUS_FMT_AHSV8888_1X32
-		     : V4L2_MBUS_FMT_ARGB8888_1X32;
+	format->code = hsit->inverse ? MEDIA_BUS_FMT_AHSV8888_1X32
+		     : MEDIA_BUS_FMT_ARGB8888_1X32;
 	format->width = clamp_t(unsigned int, fmt->format.width,
 				HSIT_MIN_SIZE, HSIT_MAX_SIZE);
 	format->height = clamp_t(unsigned int, fmt->format.height,
@@ -151,8 +151,8 @@ static int hsit_set_format(struct v4l2_subdev *subdev,
 	format = vsp1_entity_get_pad_format(&hsit->entity, fh, HSIT_PAD_SOURCE,
 					    fmt->which);
 	*format = fmt->format;
-	format->code = hsit->inverse ? V4L2_MBUS_FMT_ARGB8888_1X32
-		     : V4L2_MBUS_FMT_AHSV8888_1X32;
+	format->code = hsit->inverse ? MEDIA_BUS_FMT_ARGB8888_1X32
+		     : MEDIA_BUS_FMT_AHSV8888_1X32;
 
 	return 0;
 }
diff --git a/drivers/media/platform/vsp1/vsp1_lif.c b/drivers/media/platform/vsp1/vsp1_lif.c
index d4fb23e9c4a..17a6ca7dafe 100644
--- a/drivers/media/platform/vsp1/vsp1_lif.c
+++ b/drivers/media/platform/vsp1/vsp1_lif.c
@@ -78,8 +78,8 @@ static int lif_enum_mbus_code(struct v4l2_subdev *subdev,
 			      struct v4l2_subdev_mbus_code_enum *code)
 {
 	static const unsigned int codes[] = {
-		V4L2_MBUS_FMT_ARGB8888_1X32,
-		V4L2_MBUS_FMT_AYUV8_1X32,
+		MEDIA_BUS_FMT_ARGB8888_1X32,
+		MEDIA_BUS_FMT_AYUV8_1X32,
 	};
 
 	if (code->pad == LIF_PAD_SINK) {
@@ -147,9 +147,9 @@ static int lif_set_format(struct v4l2_subdev *subdev, struct v4l2_subdev_fh *fh,
 	struct v4l2_mbus_framefmt *format;
 
 	/* Default to YUV if the requested format is not supported. */
-	if (fmt->format.code != V4L2_MBUS_FMT_ARGB8888_1X32 &&
-	    fmt->format.code != V4L2_MBUS_FMT_AYUV8_1X32)
-		fmt->format.code = V4L2_MBUS_FMT_AYUV8_1X32;
+	if (fmt->format.code != MEDIA_BUS_FMT_ARGB8888_1X32 &&
+	    fmt->format.code != MEDIA_BUS_FMT_AYUV8_1X32)
+		fmt->format.code = MEDIA_BUS_FMT_AYUV8_1X32;
 
 	format = vsp1_entity_get_pad_format(&lif->entity, fh, fmt->pad,
 					    fmt->which);
diff --git a/drivers/media/platform/vsp1/vsp1_lut.c b/drivers/media/platform/vsp1/vsp1_lut.c
index fea36ebe256..6f185c3621f 100644
--- a/drivers/media/platform/vsp1/vsp1_lut.c
+++ b/drivers/media/platform/vsp1/vsp1_lut.c
@@ -86,9 +86,9 @@ static int lut_enum_mbus_code(struct v4l2_subdev *subdev,
 			      struct v4l2_subdev_mbus_code_enum *code)
 {
 	static const unsigned int codes[] = {
-		V4L2_MBUS_FMT_ARGB8888_1X32,
-		V4L2_MBUS_FMT_AHSV8888_1X32,
-		V4L2_MBUS_FMT_AYUV8_1X32,
+		MEDIA_BUS_FMT_ARGB8888_1X32,
+		MEDIA_BUS_FMT_AHSV8888_1X32,
+		MEDIA_BUS_FMT_AYUV8_1X32,
 	};
 	struct v4l2_mbus_framefmt *format;
 
@@ -158,10 +158,10 @@ static int lut_set_format(struct v4l2_subdev *subdev, struct v4l2_subdev_fh *fh,
 	struct v4l2_mbus_framefmt *format;
 
 	/* Default to YUV if the requested format is not supported. */
-	if (fmt->format.code != V4L2_MBUS_FMT_ARGB8888_1X32 &&
-	    fmt->format.code != V4L2_MBUS_FMT_AHSV8888_1X32 &&
-	    fmt->format.code != V4L2_MBUS_FMT_AYUV8_1X32)
-		fmt->format.code = V4L2_MBUS_FMT_AYUV8_1X32;
+	if (fmt->format.code != MEDIA_BUS_FMT_ARGB8888_1X32 &&
+	    fmt->format.code != MEDIA_BUS_FMT_AHSV8888_1X32 &&
+	    fmt->format.code != MEDIA_BUS_FMT_AYUV8_1X32)
+		fmt->format.code = MEDIA_BUS_FMT_AYUV8_1X32;
 
 	format = vsp1_entity_get_pad_format(&lut->entity, fh, fmt->pad,
 					    fmt->which);
diff --git a/drivers/media/platform/vsp1/vsp1_rwpf.c b/drivers/media/platform/vsp1/vsp1_rwpf.c
index ec3dab6a9b9..1f1ba26a834 100644
--- a/drivers/media/platform/vsp1/vsp1_rwpf.c
+++ b/drivers/media/platform/vsp1/vsp1_rwpf.c
@@ -29,8 +29,8 @@ int vsp1_rwpf_enum_mbus_code(struct v4l2_subdev *subdev,
 			     struct v4l2_subdev_mbus_code_enum *code)
 {
 	static const unsigned int codes[] = {
-		V4L2_MBUS_FMT_ARGB8888_1X32,
-		V4L2_MBUS_FMT_AYUV8_1X32,
+		MEDIA_BUS_FMT_ARGB8888_1X32,
+		MEDIA_BUS_FMT_AYUV8_1X32,
 	};
 
 	if (code->index >= ARRAY_SIZE(codes))
@@ -103,9 +103,9 @@ int vsp1_rwpf_set_format(struct v4l2_subdev *subdev, struct v4l2_subdev_fh *fh,
 	struct v4l2_rect *crop;
 
 	/* Default to YUV if the requested format is not supported. */
-	if (fmt->format.code != V4L2_MBUS_FMT_ARGB8888_1X32 &&
-	    fmt->format.code != V4L2_MBUS_FMT_AYUV8_1X32)
-		fmt->format.code = V4L2_MBUS_FMT_AYUV8_1X32;
+	if (fmt->format.code != MEDIA_BUS_FMT_ARGB8888_1X32 &&
+	    fmt->format.code != MEDIA_BUS_FMT_AYUV8_1X32)
+		fmt->format.code = MEDIA_BUS_FMT_AYUV8_1X32;
 
 	format = vsp1_entity_get_pad_format(&rwpf->entity, fh, fmt->pad,
 					    fmt->which);
diff --git a/drivers/media/platform/vsp1/vsp1_sru.c b/drivers/media/platform/vsp1/vsp1_sru.c
index b7d3c8b9f18..1129494c7cf 100644
--- a/drivers/media/platform/vsp1/vsp1_sru.c
+++ b/drivers/media/platform/vsp1/vsp1_sru.c
@@ -139,7 +139,7 @@ static int sru_s_stream(struct v4l2_subdev *subdev, int enable)
 	input = &sru->entity.formats[SRU_PAD_SINK];
 	output = &sru->entity.formats[SRU_PAD_SOURCE];
 
-	if (input->code == V4L2_MBUS_FMT_ARGB8888_1X32)
+	if (input->code == MEDIA_BUS_FMT_ARGB8888_1X32)
 		ctrl0 = VI6_SRU_CTRL0_PARAM2 | VI6_SRU_CTRL0_PARAM3
 		      | VI6_SRU_CTRL0_PARAM4;
 	else
@@ -170,8 +170,8 @@ static int sru_enum_mbus_code(struct v4l2_subdev *subdev,
 			      struct v4l2_subdev_mbus_code_enum *code)
 {
 	static const unsigned int codes[] = {
-		V4L2_MBUS_FMT_ARGB8888_1X32,
-		V4L2_MBUS_FMT_AYUV8_1X32,
+		MEDIA_BUS_FMT_ARGB8888_1X32,
+		MEDIA_BUS_FMT_AYUV8_1X32,
 	};
 	struct v4l2_mbus_framefmt *format;
 
@@ -248,9 +248,9 @@ static void sru_try_format(struct vsp1_sru *sru, struct v4l2_subdev_fh *fh,
 	switch (pad) {
 	case SRU_PAD_SINK:
 		/* Default to YUV if the requested format is not supported. */
-		if (fmt->code != V4L2_MBUS_FMT_ARGB8888_1X32 &&
-		    fmt->code != V4L2_MBUS_FMT_AYUV8_1X32)
-			fmt->code = V4L2_MBUS_FMT_AYUV8_1X32;
+		if (fmt->code != MEDIA_BUS_FMT_ARGB8888_1X32 &&
+		    fmt->code != MEDIA_BUS_FMT_AYUV8_1X32)
+			fmt->code = MEDIA_BUS_FMT_AYUV8_1X32;
 
 		fmt->width = clamp(fmt->width, SRU_MIN_SIZE, SRU_MAX_SIZE);
 		fmt->height = clamp(fmt->height, SRU_MIN_SIZE, SRU_MAX_SIZE);
diff --git a/drivers/media/platform/vsp1/vsp1_uds.c b/drivers/media/platform/vsp1/vsp1_uds.c
index de92ef4944b..a4afec13380 100644
--- a/drivers/media/platform/vsp1/vsp1_uds.c
+++ b/drivers/media/platform/vsp1/vsp1_uds.c
@@ -173,8 +173,8 @@ static int uds_enum_mbus_code(struct v4l2_subdev *subdev,
 			      struct v4l2_subdev_mbus_code_enum *code)
 {
 	static const unsigned int codes[] = {
-		V4L2_MBUS_FMT_ARGB8888_1X32,
-		V4L2_MBUS_FMT_AYUV8_1X32,
+		MEDIA_BUS_FMT_ARGB8888_1X32,
+		MEDIA_BUS_FMT_AYUV8_1X32,
 	};
 
 	if (code->pad == UDS_PAD_SINK) {
@@ -246,9 +246,9 @@ static void uds_try_format(struct vsp1_uds *uds, struct v4l2_subdev_fh *fh,
 	switch (pad) {
 	case UDS_PAD_SINK:
 		/* Default to YUV if the requested format is not supported. */
-		if (fmt->code != V4L2_MBUS_FMT_ARGB8888_1X32 &&
-		    fmt->code != V4L2_MBUS_FMT_AYUV8_1X32)
-			fmt->code = V4L2_MBUS_FMT_AYUV8_1X32;
+		if (fmt->code != MEDIA_BUS_FMT_ARGB8888_1X32 &&
+		    fmt->code != MEDIA_BUS_FMT_AYUV8_1X32)
+			fmt->code = MEDIA_BUS_FMT_AYUV8_1X32;
 
 		fmt->width = clamp(fmt->width, UDS_MIN_SIZE, UDS_MAX_SIZE);
 		fmt->height = clamp(fmt->height, UDS_MIN_SIZE, UDS_MAX_SIZE);
diff --git a/drivers/media/platform/vsp1/vsp1_video.c b/drivers/media/platform/vsp1/vsp1_video.c
index 915a20eb003..d91f19a9e1c 100644
--- a/drivers/media/platform/vsp1/vsp1_video.c
+++ b/drivers/media/platform/vsp1/vsp1_video.c
@@ -48,85 +48,85 @@
  */
 
 static const struct vsp1_format_info vsp1_video_formats[] = {
-	{ V4L2_PIX_FMT_RGB332, V4L2_MBUS_FMT_ARGB8888_1X32,
+	{ V4L2_PIX_FMT_RGB332, MEDIA_BUS_FMT_ARGB8888_1X32,
 	  VI6_FMT_RGB_332, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  1, { 8, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_ARGB444, V4L2_MBUS_FMT_ARGB8888_1X32,
+	{ V4L2_PIX_FMT_ARGB444, MEDIA_BUS_FMT_ARGB8888_1X32,
 	  VI6_FMT_ARGB_4444, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS,
 	  1, { 16, 0, 0 }, false, false, 1, 1, true },
-	{ V4L2_PIX_FMT_XRGB444, V4L2_MBUS_FMT_ARGB8888_1X32,
+	{ V4L2_PIX_FMT_XRGB444, MEDIA_BUS_FMT_ARGB8888_1X32,
 	  VI6_FMT_XRGB_4444, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS,
 	  1, { 16, 0, 0 }, false, false, 1, 1, true },
-	{ V4L2_PIX_FMT_ARGB555, V4L2_MBUS_FMT_ARGB8888_1X32,
+	{ V4L2_PIX_FMT_ARGB555, MEDIA_BUS_FMT_ARGB8888_1X32,
 	  VI6_FMT_ARGB_1555, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS,
 	  1, { 16, 0, 0 }, false, false, 1, 1, true },
-	{ V4L2_PIX_FMT_XRGB555, V4L2_MBUS_FMT_ARGB8888_1X32,
+	{ V4L2_PIX_FMT_XRGB555, MEDIA_BUS_FMT_ARGB8888_1X32,
 	  VI6_FMT_XRGB_1555, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS,
 	  1, { 16, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_RGB565, V4L2_MBUS_FMT_ARGB8888_1X32,
+	{ V4L2_PIX_FMT_RGB565, MEDIA_BUS_FMT_ARGB8888_1X32,
 	  VI6_FMT_RGB_565, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS,
 	  1, { 16, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_BGR24, V4L2_MBUS_FMT_ARGB8888_1X32,
+	{ V4L2_PIX_FMT_BGR24, MEDIA_BUS_FMT_ARGB8888_1X32,
 	  VI6_FMT_BGR_888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  1, { 24, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_RGB24, V4L2_MBUS_FMT_ARGB8888_1X32,
+	{ V4L2_PIX_FMT_RGB24, MEDIA_BUS_FMT_ARGB8888_1X32,
 	  VI6_FMT_RGB_888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  1, { 24, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_ABGR32, V4L2_MBUS_FMT_ARGB8888_1X32,
+	{ V4L2_PIX_FMT_ABGR32, MEDIA_BUS_FMT_ARGB8888_1X32,
 	  VI6_FMT_ARGB_8888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS,
 	  1, { 32, 0, 0 }, false, false, 1, 1, true },
-	{ V4L2_PIX_FMT_XBGR32, V4L2_MBUS_FMT_ARGB8888_1X32,
+	{ V4L2_PIX_FMT_XBGR32, MEDIA_BUS_FMT_ARGB8888_1X32,
 	  VI6_FMT_ARGB_8888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS,
 	  1, { 32, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_ARGB32, V4L2_MBUS_FMT_ARGB8888_1X32,
+	{ V4L2_PIX_FMT_ARGB32, MEDIA_BUS_FMT_ARGB8888_1X32,
 	  VI6_FMT_ARGB_8888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  1, { 32, 0, 0 }, false, false, 1, 1, true },
-	{ V4L2_PIX_FMT_XRGB32, V4L2_MBUS_FMT_ARGB8888_1X32,
+	{ V4L2_PIX_FMT_XRGB32, MEDIA_BUS_FMT_ARGB8888_1X32,
 	  VI6_FMT_ARGB_8888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  1, { 32, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_UYVY, V4L2_MBUS_FMT_AYUV8_1X32,
+	{ V4L2_PIX_FMT_UYVY, MEDIA_BUS_FMT_AYUV8_1X32,
 	  VI6_FMT_YUYV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  1, { 16, 0, 0 }, false, false, 2, 1, false },
-	{ V4L2_PIX_FMT_VYUY, V4L2_MBUS_FMT_AYUV8_1X32,
+	{ V4L2_PIX_FMT_VYUY, MEDIA_BUS_FMT_AYUV8_1X32,
 	  VI6_FMT_YUYV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  1, { 16, 0, 0 }, false, true, 2, 1, false },
-	{ V4L2_PIX_FMT_YUYV, V4L2_MBUS_FMT_AYUV8_1X32,
+	{ V4L2_PIX_FMT_YUYV, MEDIA_BUS_FMT_AYUV8_1X32,
 	  VI6_FMT_YUYV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  1, { 16, 0, 0 }, true, false, 2, 1, false },
-	{ V4L2_PIX_FMT_YVYU, V4L2_MBUS_FMT_AYUV8_1X32,
+	{ V4L2_PIX_FMT_YVYU, MEDIA_BUS_FMT_AYUV8_1X32,
 	  VI6_FMT_YUYV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  1, { 16, 0, 0 }, true, true, 2, 1, false },
-	{ V4L2_PIX_FMT_NV12M, V4L2_MBUS_FMT_AYUV8_1X32,
+	{ V4L2_PIX_FMT_NV12M, MEDIA_BUS_FMT_AYUV8_1X32,
 	  VI6_FMT_Y_UV_420, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  2, { 8, 16, 0 }, false, false, 2, 2, false },
-	{ V4L2_PIX_FMT_NV21M, V4L2_MBUS_FMT_AYUV8_1X32,
+	{ V4L2_PIX_FMT_NV21M, MEDIA_BUS_FMT_AYUV8_1X32,
 	  VI6_FMT_Y_UV_420, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  2, { 8, 16, 0 }, false, true, 2, 2, false },
-	{ V4L2_PIX_FMT_NV16M, V4L2_MBUS_FMT_AYUV8_1X32,
+	{ V4L2_PIX_FMT_NV16M, MEDIA_BUS_FMT_AYUV8_1X32,
 	  VI6_FMT_Y_UV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  2, { 8, 16, 0 }, false, false, 2, 1, false },
-	{ V4L2_PIX_FMT_NV61M, V4L2_MBUS_FMT_AYUV8_1X32,
+	{ V4L2_PIX_FMT_NV61M, MEDIA_BUS_FMT_AYUV8_1X32,
 	  VI6_FMT_Y_UV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  2, { 8, 16, 0 }, false, true, 2, 1, false },
-	{ V4L2_PIX_FMT_YUV420M, V4L2_MBUS_FMT_AYUV8_1X32,
+	{ V4L2_PIX_FMT_YUV420M, MEDIA_BUS_FMT_AYUV8_1X32,
 	  VI6_FMT_Y_U_V_420, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
 	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
 	  3, { 8, 8, 8 }, false, false, 2, 2, false },
diff --git a/include/media/davinci/vpbe.h b/include/media/davinci/vpbe.h
index 57585c7004a..4376beeb28c 100644
--- a/include/media/davinci/vpbe.h
+++ b/include/media/davinci/vpbe.h
@@ -63,7 +63,7 @@ struct vpbe_output {
 	 * output basis. If per mode is needed, we may have to move this to
 	 * mode_info structure
 	 */
-	enum v4l2_mbus_pixelcode if_params;
+	u32 if_params;
 };
 
 /* encoder configuration info */
diff --git a/include/media/davinci/vpbe_venc.h b/include/media/davinci/vpbe_venc.h
index 476fafc2f52..3dbd2002610 100644
--- a/include/media/davinci/vpbe_venc.h
+++ b/include/media/davinci/vpbe_venc.h
@@ -30,11 +30,10 @@
 #define VENC_SECOND_FIELD	BIT(2)
 
 struct venc_platform_data {
-	int (*setup_pinmux)(enum v4l2_mbus_pixelcode if_type,
-			    int field);
+	int (*setup_pinmux)(u32 if_type, int field);
 	int (*setup_clock)(enum vpbe_enc_timings_type type,
 			   unsigned int pixclock);
-	int (*setup_if_config)(enum v4l2_mbus_pixelcode pixcode);
+	int (*setup_if_config)(u32 pixcode);
 	/* Number of LCD outputs supported */
 	int num_lcd_outputs;
 	struct vpbe_if_params *lcd_if_params;
diff --git a/include/media/exynos-fimc.h b/include/media/exynos-fimc.h
index aa44660e204..69bcd2a07d5 100644
--- a/include/media/exynos-fimc.h
+++ b/include/media/exynos-fimc.h
@@ -101,7 +101,7 @@ struct fimc_source_info {
  * @flags: flags indicating which operation mode format applies to
  */
 struct fimc_fmt {
-	enum v4l2_mbus_pixelcode mbus_code;
+	u32 mbus_code;
 	char	*name;
 	u32	fourcc;
 	u32	color;
diff --git a/include/media/soc_camera.h b/include/media/soc_camera.h
index 865246b0012..2f6261f3e57 100644
--- a/include/media/soc_camera.h
+++ b/include/media/soc_camera.h
@@ -296,7 +296,7 @@ const struct soc_camera_format_xlate *soc_camera_xlate_by_fourcc(
  * format setup.
  */
 struct soc_camera_format_xlate {
-	enum v4l2_mbus_pixelcode code;
+	u32 code;
 	const struct soc_mbus_pixelfmt *host_fmt;
 };
 
diff --git a/include/media/soc_mediabus.h b/include/media/soc_mediabus.h
index d33f6d05969..2ff773785fb 100644
--- a/include/media/soc_mediabus.h
+++ b/include/media/soc_mediabus.h
@@ -91,16 +91,16 @@ struct soc_mbus_pixelfmt {
  * @fmt:	pixel format description
  */
 struct soc_mbus_lookup {
-	enum v4l2_mbus_pixelcode	code;
+	u32	code;
 	struct soc_mbus_pixelfmt	fmt;
 };
 
 const struct soc_mbus_pixelfmt *soc_mbus_find_fmtdesc(
-	enum v4l2_mbus_pixelcode code,
+	u32 code,
 	const struct soc_mbus_lookup *lookup,
 	int n);
 const struct soc_mbus_pixelfmt *soc_mbus_get_fmtdesc(
-	enum v4l2_mbus_pixelcode code);
+	u32 code);
 s32 soc_mbus_bytes_per_line(u32 width, const struct soc_mbus_pixelfmt *mf);
 s32 soc_mbus_image_size(const struct soc_mbus_pixelfmt *mf,
 			u32 bytes_per_line, u32 height);
-- 
cgit v1.2.3-70-g09d2


From aa1b4da6af67d5c6a4e933c2d30890c6f282f505 Mon Sep 17 00:00:00 2001
From: Boris BREZILLON <boris.brezillon@free-electrons.com>
Date: Mon, 10 Nov 2014 14:28:35 -0300
Subject: [media] v4l: Forbid usage of V4L2_MBUS_FMT definitions inside the
 kernel

Place v4l2_mbus_pixelcode in a #ifndef __KERNEL__ section so that kernel
users don't have access to these definitions.

We have to keep this definition for user-space users even though they're
encouraged to move to the new media_bus_format enum.

Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/uapi/linux/v4l2-mediabus.h | 45 ++++++++++++++++++++++++--------------
 1 file changed, 28 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/v4l2-mediabus.h b/include/uapi/linux/v4l2-mediabus.h
index 26180844c6b..b1934a3961e 100644
--- a/include/uapi/linux/v4l2-mediabus.h
+++ b/include/uapi/linux/v4l2-mediabus.h
@@ -15,6 +15,33 @@
 #include <linux/types.h>
 #include <linux/videodev2.h>
 
+/**
+ * struct v4l2_mbus_framefmt - frame format on the media bus
+ * @width:	frame width
+ * @height:	frame height
+ * @code:	data format code (from enum v4l2_mbus_pixelcode)
+ * @field:	used interlacing type (from enum v4l2_field)
+ * @colorspace:	colorspace of the data (from enum v4l2_colorspace)
+ */
+struct v4l2_mbus_framefmt {
+	__u32			width;
+	__u32			height;
+	__u32			code;
+	__u32			field;
+	__u32			colorspace;
+	__u32			reserved[7];
+};
+
+#ifndef __KERNEL__
+/*
+ * enum v4l2_mbus_pixelcode and its definitions are now deprecated, and
+ * MEDIA_BUS_FMT_ definitions (defined in media-bus-format.h) should be
+ * used instead.
+ *
+ * New defines should only be added to media-bus-format.h. The
+ * v4l2_mbus_pixelcode enum is frozen.
+ */
+
 #define V4L2_MBUS_FROM_MEDIA_BUS_FMT(name)	\
 	V4L2_MBUS_FMT_ ## name = MEDIA_BUS_FMT_ ## name
 
@@ -102,22 +129,6 @@ enum v4l2_mbus_pixelcode {
 
 	V4L2_MBUS_FROM_MEDIA_BUS_FMT(AHSV8888_1X32),
 };
-
-/**
- * struct v4l2_mbus_framefmt - frame format on the media bus
- * @width:	frame width
- * @height:	frame height
- * @code:	data format code (from enum v4l2_mbus_pixelcode)
- * @field:	used interlacing type (from enum v4l2_field)
- * @colorspace:	colorspace of the data (from enum v4l2_colorspace)
- */
-struct v4l2_mbus_framefmt {
-	__u32			width;
-	__u32			height;
-	__u32			code;
-	__u32			field;
-	__u32			colorspace;
-	__u32			reserved[7];
-};
+#endif /* __KERNEL__ */
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From 98bea620c7ff301f9a7a6c31b2aca30964aa2fab Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sre@kernel.org>
Date: Mon, 10 Nov 2014 17:34:41 -0300
Subject: [media] si4713: add device tree support

Add device tree support by changing the device registration order.
In the device tree the si4713 node is a normal I2C device, which
will be probed as such. Thus the V4L device must be probed from
the I2C device and not the other way around.

Signed-off-by: Sebastian Reichel <sre@kernel.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/radio/si4713/radio-platform-si4713.c | 28 +++++---------------
 drivers/media/radio/si4713/si4713.c                | 28 ++++++++++++++++++++
 drivers/media/radio/si4713/si4713.h                |  6 +++++
 include/media/radio-si4713.h                       | 30 ----------------------
 include/media/si4713.h                             |  1 +
 5 files changed, 41 insertions(+), 52 deletions(-)
 delete mode 100644 include/media/radio-si4713.h

(limited to 'include')

diff --git a/drivers/media/radio/si4713/radio-platform-si4713.c b/drivers/media/radio/si4713/radio-platform-si4713.c
index a47502a330f..2de5439b9c7 100644
--- a/drivers/media/radio/si4713/radio-platform-si4713.c
+++ b/drivers/media/radio/si4713/radio-platform-si4713.c
@@ -34,7 +34,7 @@
 #include <media/v4l2-fh.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-event.h>
-#include <media/radio-si4713.h>
+#include "si4713.h"
 
 /* module parameters */
 static int radio_nr = -1;	/* radio device minor (-1 ==> auto assign) */
@@ -153,7 +153,6 @@ static int radio_si4713_pdriver_probe(struct platform_device *pdev)
 {
 	struct radio_si4713_platform_data *pdata = pdev->dev.platform_data;
 	struct radio_si4713_device *rsdev;
-	struct i2c_adapter *adapter;
 	struct v4l2_subdev *sd;
 	int rval = 0;
 
@@ -177,20 +176,11 @@ static int radio_si4713_pdriver_probe(struct platform_device *pdev)
 		goto exit;
 	}
 
-	adapter = i2c_get_adapter(pdata->i2c_bus);
-	if (!adapter) {
-		dev_err(&pdev->dev, "Cannot get i2c adapter %d\n",
-			pdata->i2c_bus);
-		rval = -ENODEV;
-		goto unregister_v4l2_dev;
-	}
-
-	sd = v4l2_i2c_new_subdev_board(&rsdev->v4l2_dev, adapter,
-				       pdata->subdev_board_info, NULL);
-	if (!sd) {
+	sd = i2c_get_clientdata(pdata->subdev);
+	rval = v4l2_device_register_subdev(&rsdev->v4l2_dev, sd);
+	if (rval) {
 		dev_err(&pdev->dev, "Cannot get v4l2 subdevice\n");
-		rval = -ENODEV;
-		goto put_adapter;
+		goto unregister_v4l2_dev;
 	}
 
 	rsdev->radio_dev = radio_si4713_vdev_template;
@@ -202,14 +192,12 @@ static int radio_si4713_pdriver_probe(struct platform_device *pdev)
 	if (video_register_device(&rsdev->radio_dev, VFL_TYPE_RADIO, radio_nr)) {
 		dev_err(&pdev->dev, "Could not register video device.\n");
 		rval = -EIO;
-		goto put_adapter;
+		goto unregister_v4l2_dev;
 	}
 	dev_info(&pdev->dev, "New device successfully probed\n");
 
 	goto exit;
 
-put_adapter:
-	i2c_put_adapter(adapter);
 unregister_v4l2_dev:
 	v4l2_device_unregister(&rsdev->v4l2_dev);
 exit:
@@ -220,14 +208,10 @@ exit:
 static int radio_si4713_pdriver_remove(struct platform_device *pdev)
 {
 	struct v4l2_device *v4l2_dev = platform_get_drvdata(pdev);
-	struct v4l2_subdev *sd = list_entry(v4l2_dev->subdevs.next,
-					    struct v4l2_subdev, list);
-	struct i2c_client *client = v4l2_get_subdevdata(sd);
 	struct radio_si4713_device *rsdev;
 
 	rsdev = container_of(v4l2_dev, struct radio_si4713_device, v4l2_dev);
 	video_unregister_device(&rsdev->radio_dev);
-	i2c_put_adapter(client->adapter);
 	v4l2_device_unregister(&rsdev->v4l2_dev);
 
 	return 0;
diff --git a/drivers/media/radio/si4713/si4713.c b/drivers/media/radio/si4713/si4713.c
index 449f6cda293..c90004dac17 100644
--- a/drivers/media/radio/si4713/si4713.c
+++ b/drivers/media/radio/si4713/si4713.c
@@ -1447,6 +1447,10 @@ static int si4713_probe(struct i2c_client *client,
 {
 	struct si4713_device *sdev;
 	struct v4l2_ctrl_handler *hdl;
+	struct si4713_platform_data *pdata = client->dev.platform_data;
+	struct device_node *np = client->dev.of_node;
+	struct radio_si4713_platform_data si4713_pdev_pdata;
+	struct platform_device *si4713_pdev;
 	int rval;
 
 	sdev = devm_kzalloc(&client->dev, sizeof(*sdev), GFP_KERNEL);
@@ -1607,8 +1611,30 @@ static int si4713_probe(struct i2c_client *client,
 		goto free_ctrls;
 	}
 
+	if (!np && (!pdata || !pdata->is_platform_device))
+		return 0;
+
+	si4713_pdev = platform_device_alloc("radio-si4713", -1);
+	if (!si4713_pdev)
+		goto put_main_pdev;
+
+	si4713_pdev_pdata.subdev = client;
+	rval = platform_device_add_data(si4713_pdev, &si4713_pdev_pdata,
+					sizeof(si4713_pdev_pdata));
+	if (rval)
+		goto put_main_pdev;
+
+	rval = platform_device_add(si4713_pdev);
+	if (rval)
+		goto put_main_pdev;
+
+	sdev->pd = si4713_pdev;
+
 	return 0;
 
+put_main_pdev:
+	platform_device_put(si4713_pdev);
+	v4l2_device_unregister_subdev(&sdev->sd);
 free_ctrls:
 	v4l2_ctrl_handler_free(hdl);
 exit:
@@ -1621,6 +1647,8 @@ static int si4713_remove(struct i2c_client *client)
 	struct v4l2_subdev *sd = i2c_get_clientdata(client);
 	struct si4713_device *sdev = to_si4713_device(sd);
 
+	platform_device_unregister(sdev->pd);
+
 	if (sdev->power_state)
 		si4713_set_power_state(sdev, POWER_DOWN);
 
diff --git a/drivers/media/radio/si4713/si4713.h b/drivers/media/radio/si4713/si4713.h
index 7c2479f4232..8a376e14218 100644
--- a/drivers/media/radio/si4713/si4713.h
+++ b/drivers/media/radio/si4713/si4713.h
@@ -15,6 +15,7 @@
 #ifndef SI4713_I2C_H
 #define SI4713_I2C_H
 
+#include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
 #include <linux/gpio/consumer.h>
 #include <media/v4l2-subdev.h>
@@ -238,6 +239,7 @@ struct si4713_device {
 	struct regulator *vdd;
 	struct regulator *vio;
 	struct gpio_desc *gpio_reset;
+	struct platform_device *pd;
 	u32 power_state;
 	u32 rds_enabled;
 	u32 frequency;
@@ -245,4 +247,8 @@ struct si4713_device {
 	u32 stereo;
 	u32 tune_rnl;
 };
+
+struct radio_si4713_platform_data {
+	struct i2c_client *subdev;
+};
 #endif /* ifndef SI4713_I2C_H */
diff --git a/include/media/radio-si4713.h b/include/media/radio-si4713.h
deleted file mode 100644
index f6aae29c774..00000000000
--- a/include/media/radio-si4713.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * include/media/radio-si4713.h
- *
- * Board related data definitions for Si4713 radio transmitter chip.
- *
- * Copyright (c) 2009 Nokia Corporation
- * Contact: Eduardo Valentin <eduardo.valentin@nokia.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- *
- */
-
-#ifndef RADIO_SI4713_H
-#define RADIO_SI4713_H
-
-#include <linux/i2c.h>
-
-#define SI4713_NAME "radio-si4713"
-
-/*
- * Platform dependent definition
- */
-struct radio_si4713_platform_data {
-	int i2c_bus;
-	struct i2c_board_info *subdev_board_info;
-};
-
-#endif /* ifndef RADIO_SI4713_H*/
diff --git a/include/media/si4713.h b/include/media/si4713.h
index f98a0a7af61..343b8fb50b9 100644
--- a/include/media/si4713.h
+++ b/include/media/si4713.h
@@ -26,6 +26,7 @@ struct si4713_platform_data {
 	const char * const *supply_names;
 	unsigned supplies;
 	int gpio_reset; /* < 0 if not used */
+	bool is_platform_device;
 };
 
 /*
-- 
cgit v1.2.3-70-g09d2


From bf2b892e661213d4e94e2bff76dd13a23909228b Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sre@kernel.org>
Date: Mon, 10 Nov 2014 17:34:44 -0300
Subject: [media] si4713: cleanup platform data

Remove unreferenced members from the platform
data's structure.

Signed-off-by: Sebastian Reichel <sre@kernel.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/si4713.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/media/si4713.h b/include/media/si4713.h
index 343b8fb50b9..be4f58e2440 100644
--- a/include/media/si4713.h
+++ b/include/media/si4713.h
@@ -23,9 +23,6 @@
  * Platform dependent definition
  */
 struct si4713_platform_data {
-	const char * const *supply_names;
-	unsigned supplies;
-	int gpio_reset; /* < 0 if not used */
 	bool is_platform_device;
 };
 
-- 
cgit v1.2.3-70-g09d2


From a77f9c5dcdf8480a93332792c336fa2bf9d31229 Mon Sep 17 00:00:00 2001
From: Jay Vosburgh <jay.vosburgh@canonical.com>
Date: Fri, 14 Nov 2014 11:05:06 -0800
Subject: Revert "fast_hash: avoid indirect function calls"

This reverts commit e5a2c899957659cd1a9f789bc462f9c0b35f5150.

	Commit e5a2c899 introduced an alternative_call, arch_fast_hash2,
that selects between __jhash2 and __intel_crc4_2_hash based on the
X86_FEATURE_XMM4_2.

	Unfortunately, the alternative_call system does not appear to be
suitable for use with C functions, as register usage is not handled
properly for the called functions.  The __jhash2 function in particular
clobbers registers that are not preserved when called via
alternative_call, resulting in a panic for direct callers of
arch_fast_hash2 on older CPUs lacking sse4_2.  It is possible that
__intel_crc4_2_hash works merely by chance because it uses fewer
registers.

	This commit was suggested as the source of the problem by Jesse
Gross <jesse@nicira.com>.

Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/include/asm/hash.h | 51 +++++----------------------------------------
 arch/x86/lib/hash.c         | 29 +++++++++++---------------
 include/asm-generic/hash.h  | 36 ++------------------------------
 include/linux/hash.h        | 34 ++++++++++++++++++++++++++++++
 lib/Makefile                |  2 +-
 lib/hash.c                  | 39 ++++++++++++++++++++++++++++++++++
 6 files changed, 93 insertions(+), 98 deletions(-)
 create mode 100644 lib/hash.c

(limited to 'include')

diff --git a/arch/x86/include/asm/hash.h b/arch/x86/include/asm/hash.h
index a881d784f04..e8c58f88b1d 100644
--- a/arch/x86/include/asm/hash.h
+++ b/arch/x86/include/asm/hash.h
@@ -1,48 +1,7 @@
-#ifndef __ASM_X86_HASH_H
-#define __ASM_X86_HASH_H
+#ifndef _ASM_X86_HASH_H
+#define _ASM_X86_HASH_H
 
-#include <linux/cpufeature.h>
-#include <asm/alternative.h>
+struct fast_hash_ops;
+extern void setup_arch_fast_hash(struct fast_hash_ops *ops);
 
-u32 __intel_crc4_2_hash(const void *data, u32 len, u32 seed);
-u32 __intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed);
-
-/*
- * non-inline versions of jhash so gcc does not need to generate
- * duplicate code in every object file
- */
-u32 __jhash(const void *data, u32 len, u32 seed);
-u32 __jhash2(const u32 *data, u32 len, u32 seed);
-
-/*
- * for documentation of these functions please look into
- * <include/asm-generic/hash.h>
- */
-
-static inline u32 arch_fast_hash(const void *data, u32 len, u32 seed)
-{
-	u32 hash;
-
-	alternative_call(__jhash, __intel_crc4_2_hash, X86_FEATURE_XMM4_2,
-#ifdef CONFIG_X86_64
-			 "=a" (hash), "D" (data), "S" (len), "d" (seed));
-#else
-			 "=a" (hash), "a" (data), "d" (len), "c" (seed));
-#endif
-	return hash;
-}
-
-static inline u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed)
-{
-	u32 hash;
-
-	alternative_call(__jhash2, __intel_crc4_2_hash2, X86_FEATURE_XMM4_2,
-#ifdef CONFIG_X86_64
-			 "=a" (hash), "D" (data), "S" (len), "d" (seed));
-#else
-			 "=a" (hash), "a" (data), "d" (len), "c" (seed));
-#endif
-	return hash;
-}
-
-#endif /* __ASM_X86_HASH_H */
+#endif /* _ASM_X86_HASH_H */
diff --git a/arch/x86/lib/hash.c b/arch/x86/lib/hash.c
index e1432719883..ff4fa51a5b1 100644
--- a/arch/x86/lib/hash.c
+++ b/arch/x86/lib/hash.c
@@ -31,13 +31,13 @@
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <linux/hash.h>
+#include <linux/init.h>
+
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
 #include <asm/hash.h>
 
-#include <linux/hash.h>
-#include <linux/jhash.h>
-
 static inline u32 crc32_u32(u32 crc, u32 val)
 {
 #ifdef CONFIG_AS_CRC32
@@ -48,7 +48,7 @@ static inline u32 crc32_u32(u32 crc, u32 val)
 	return crc;
 }
 
-u32 __intel_crc4_2_hash(const void *data, u32 len, u32 seed)
+static u32 intel_crc4_2_hash(const void *data, u32 len, u32 seed)
 {
 	const u32 *p32 = (const u32 *) data;
 	u32 i, tmp = 0;
@@ -71,27 +71,22 @@ u32 __intel_crc4_2_hash(const void *data, u32 len, u32 seed)
 
 	return seed;
 }
-EXPORT_SYMBOL(__intel_crc4_2_hash);
 
-u32 __intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed)
+static u32 intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed)
 {
+	const u32 *p32 = (const u32 *) data;
 	u32 i;
 
 	for (i = 0; i < len; i++)
-		seed = crc32_u32(seed, *data++);
+		seed = crc32_u32(seed, *p32++);
 
 	return seed;
 }
-EXPORT_SYMBOL(__intel_crc4_2_hash2);
 
-u32 __jhash(const void *data, u32 len, u32 seed)
+void __init setup_arch_fast_hash(struct fast_hash_ops *ops)
 {
-	return jhash(data, len, seed);
-}
-EXPORT_SYMBOL(__jhash);
-
-u32 __jhash2(const u32 *data, u32 len, u32 seed)
-{
-	return jhash2(data, len, seed);
+	if (cpu_has_xmm4_2) {
+		ops->hash  = intel_crc4_2_hash;
+		ops->hash2 = intel_crc4_2_hash2;
+	}
 }
-EXPORT_SYMBOL(__jhash2);
diff --git a/include/asm-generic/hash.h b/include/asm-generic/hash.h
index 3c82760ff2a..b6312843dbd 100644
--- a/include/asm-generic/hash.h
+++ b/include/asm-generic/hash.h
@@ -1,41 +1,9 @@
 #ifndef __ASM_GENERIC_HASH_H
 #define __ASM_GENERIC_HASH_H
 
-#include <linux/jhash.h>
-
-/**
- *	arch_fast_hash - Caclulates a hash over a given buffer that can have
- *			 arbitrary size. This function will eventually use an
- *			 architecture-optimized hashing implementation if
- *			 available, and trades off distribution for speed.
- *
- *	@data: buffer to hash
- *	@len: length of buffer in bytes
- *	@seed: start seed
- *
- *	Returns 32bit hash.
- */
-static inline u32 arch_fast_hash(const void *data, u32 len, u32 seed)
-{
-	return jhash(data, len, seed);
-}
-
-/**
- *	arch_fast_hash2 - Caclulates a hash over a given buffer that has a
- *			  size that is of a multiple of 32bit words. This
- *			  function will eventually use an architecture-
- *			  optimized hashing implementation if available,
- *			  and trades off distribution for speed.
- *
- *	@data: buffer to hash (must be 32bit padded)
- *	@len: number of 32bit words
- *	@seed: start seed
- *
- *	Returns 32bit hash.
- */
-static inline u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed)
+struct fast_hash_ops;
+static inline void setup_arch_fast_hash(struct fast_hash_ops *ops)
 {
-	return jhash2(data, len, seed);
 }
 
 #endif /* __ASM_GENERIC_HASH_H */
diff --git a/include/linux/hash.h b/include/linux/hash.h
index 6e8fb028848..d0494c39939 100644
--- a/include/linux/hash.h
+++ b/include/linux/hash.h
@@ -84,4 +84,38 @@ static inline u32 hash32_ptr(const void *ptr)
 	return (u32)val;
 }
 
+struct fast_hash_ops {
+	u32 (*hash)(const void *data, u32 len, u32 seed);
+	u32 (*hash2)(const u32 *data, u32 len, u32 seed);
+};
+
+/**
+ *	arch_fast_hash - Caclulates a hash over a given buffer that can have
+ *			 arbitrary size. This function will eventually use an
+ *			 architecture-optimized hashing implementation if
+ *			 available, and trades off distribution for speed.
+ *
+ *	@data: buffer to hash
+ *	@len: length of buffer in bytes
+ *	@seed: start seed
+ *
+ *	Returns 32bit hash.
+ */
+extern u32 arch_fast_hash(const void *data, u32 len, u32 seed);
+
+/**
+ *	arch_fast_hash2 - Caclulates a hash over a given buffer that has a
+ *			  size that is of a multiple of 32bit words. This
+ *			  function will eventually use an architecture-
+ *			  optimized hashing implementation if available,
+ *			  and trades off distribution for speed.
+ *
+ *	@data: buffer to hash (must be 32bit padded)
+ *	@len: number of 32bit words
+ *	@seed: start seed
+ *
+ *	Returns 32bit hash.
+ */
+extern u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed);
+
 #endif /* _LINUX_HASH_H */
diff --git a/lib/Makefile b/lib/Makefile
index 04e53dd1607..7512dc978f1 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -26,7 +26,7 @@ obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
 	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
 	 gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \
 	 bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
-	 percpu-refcount.o percpu_ida.o rhashtable.o
+	 percpu-refcount.o percpu_ida.o hash.o rhashtable.o
 obj-y += string_helpers.o
 obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
 obj-y += kstrtox.o
diff --git a/lib/hash.c b/lib/hash.c
new file mode 100644
index 00000000000..fea973f4bd5
--- /dev/null
+++ b/lib/hash.c
@@ -0,0 +1,39 @@
+/* General purpose hashing library
+ *
+ * That's a start of a kernel hashing library, which can be extended
+ * with further algorithms in future. arch_fast_hash{2,}() will
+ * eventually resolve to an architecture optimized implementation.
+ *
+ * Copyright 2013 Francesco Fusco <ffusco@redhat.com>
+ * Copyright 2013 Daniel Borkmann <dborkman@redhat.com>
+ * Copyright 2013 Thomas Graf <tgraf@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+#include <linux/jhash.h>
+#include <linux/hash.h>
+#include <linux/cache.h>
+
+static struct fast_hash_ops arch_hash_ops __read_mostly = {
+	.hash  = jhash,
+	.hash2 = jhash2,
+};
+
+u32 arch_fast_hash(const void *data, u32 len, u32 seed)
+{
+	return arch_hash_ops.hash(data, len, seed);
+}
+EXPORT_SYMBOL_GPL(arch_fast_hash);
+
+u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed)
+{
+	return arch_hash_ops.hash2(data, len, seed);
+}
+EXPORT_SYMBOL_GPL(arch_fast_hash2);
+
+static int __init hashlib_init(void)
+{
+	setup_arch_fast_hash(&arch_hash_ops);
+	return 0;
+}
+early_initcall(hashlib_init);
-- 
cgit v1.2.3-70-g09d2


From acd899e4f3066b6662f6047da5b795cc762093cb Mon Sep 17 00:00:00 2001
From: Jacek Anaszewski <j.anaszewski@samsung.com>
Date: Mon, 22 Sep 2014 08:21:04 -0700
Subject: leds: implement sysfs interface locking mechanism

Add a mechanism for locking LED subsystem sysfs interface.
This patch prepares ground for addition of LED Flash Class
extension, whose API will be integrated with V4L2 Flash API.
Such a fusion enforces introducing a locking scheme, which
will secure consistent access to the LED Flash Class device.

The mechanism being introduced allows for disabling LED
subsystem sysfs interface by calling led_sysfs_disable function
and enabling it by calling led_sysfs_enable. The functions
alter the LED_SYSFS_DISABLE flag state and must be called
under mutex lock. The state of the lock is checked with use
of led_sysfs_is_disabled function. Such a design allows for
providing immediate feedback to the user space on whether
the LED Flash Class device is available or is under V4L2 Flash
sub-device control.

Signed-off-by: Jacek Anaszewski <j.anaszewski@samsung.com>
Acked-by: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Richard Purdie <rpurdie@rpsys.net>
Signed-off-by: Bryan Wu <cooloney@gmail.com>
---
 drivers/leds/led-class.c    | 19 ++++++++++++++++---
 drivers/leds/led-core.c     | 18 ++++++++++++++++++
 drivers/leds/led-triggers.c | 16 +++++++++++++---
 include/linux/leds.h        | 32 ++++++++++++++++++++++++++++++++
 4 files changed, 79 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 7440c58b8e6..65722deb8d2 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -40,17 +40,27 @@ static ssize_t brightness_store(struct device *dev,
 {
 	struct led_classdev *led_cdev = dev_get_drvdata(dev);
 	unsigned long state;
-	ssize_t ret = -EINVAL;
+	ssize_t ret;
+
+	mutex_lock(&led_cdev->led_access);
+
+	if (led_sysfs_is_disabled(led_cdev)) {
+		ret = -EBUSY;
+		goto unlock;
+	}
 
 	ret = kstrtoul(buf, 10, &state);
 	if (ret)
-		return ret;
+		goto unlock;
 
 	if (state == LED_OFF)
 		led_trigger_remove(led_cdev);
 	__led_set_brightness(led_cdev, state);
 
-	return size;
+	ret = size;
+unlock:
+	mutex_unlock(&led_cdev->led_access);
+	return ret;
 }
 static DEVICE_ATTR_RW(brightness);
 
@@ -214,6 +224,7 @@ int led_classdev_register(struct device *parent, struct led_classdev *led_cdev)
 #ifdef CONFIG_LEDS_TRIGGERS
 	init_rwsem(&led_cdev->trigger_lock);
 #endif
+	mutex_init(&led_cdev->led_access);
 	/* add to the list of leds */
 	down_write(&leds_list_lock);
 	list_add_tail(&led_cdev->node, &leds_list);
@@ -267,6 +278,8 @@ void led_classdev_unregister(struct led_classdev *led_cdev)
 	down_write(&leds_list_lock);
 	list_del(&led_cdev->node);
 	up_write(&leds_list_lock);
+
+	mutex_destroy(&led_cdev->led_access);
 }
 EXPORT_SYMBOL_GPL(led_classdev_unregister);
 
diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c
index aaa8eba9099..be6d9fa5e97 100644
--- a/drivers/leds/led-core.c
+++ b/drivers/leds/led-core.c
@@ -143,3 +143,21 @@ int led_update_brightness(struct led_classdev *led_cdev)
 	return ret;
 }
 EXPORT_SYMBOL(led_update_brightness);
+
+/* Caller must ensure led_cdev->led_access held */
+void led_sysfs_disable(struct led_classdev *led_cdev)
+{
+	lockdep_assert_held(&led_cdev->led_access);
+
+	led_cdev->flags |= LED_SYSFS_DISABLE;
+}
+EXPORT_SYMBOL_GPL(led_sysfs_disable);
+
+/* Caller must ensure led_cdev->led_access held */
+void led_sysfs_enable(struct led_classdev *led_cdev)
+{
+	lockdep_assert_held(&led_cdev->led_access);
+
+	led_cdev->flags &= ~LED_SYSFS_DISABLE;
+}
+EXPORT_SYMBOL_GPL(led_sysfs_enable);
diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index c3734f10fdd..e8b1120f486 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -37,6 +37,14 @@ ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr,
 	char trigger_name[TRIG_NAME_MAX];
 	struct led_trigger *trig;
 	size_t len;
+	int ret = count;
+
+	mutex_lock(&led_cdev->led_access);
+
+	if (led_sysfs_is_disabled(led_cdev)) {
+		ret = -EBUSY;
+		goto unlock;
+	}
 
 	trigger_name[sizeof(trigger_name) - 1] = '\0';
 	strncpy(trigger_name, buf, sizeof(trigger_name) - 1);
@@ -47,7 +55,7 @@ ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr,
 
 	if (!strcmp(trigger_name, "none")) {
 		led_trigger_remove(led_cdev);
-		return count;
+		goto unlock;
 	}
 
 	down_read(&triggers_list_lock);
@@ -58,12 +66,14 @@ ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr,
 			up_write(&led_cdev->trigger_lock);
 
 			up_read(&triggers_list_lock);
-			return count;
+			goto unlock;
 		}
 	}
 	up_read(&triggers_list_lock);
 
-	return -EINVAL;
+unlock:
+	mutex_unlock(&led_cdev->led_access);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(led_trigger_store);
 
diff --git a/include/linux/leds.h b/include/linux/leds.h
index a57611d0c94..737f9b1051f 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -13,6 +13,7 @@
 #define __LINUX_LEDS_H_INCLUDED
 
 #include <linux/list.h>
+#include <linux/mutex.h>
 #include <linux/rwsem.h>
 #include <linux/spinlock.h>
 #include <linux/timer.h>
@@ -42,6 +43,7 @@ struct led_classdev {
 #define LED_BLINK_ONESHOT	(1 << 17)
 #define LED_BLINK_ONESHOT_STOP	(1 << 18)
 #define LED_BLINK_INVERT	(1 << 19)
+#define LED_SYSFS_DISABLE	(1 << 20)
 
 	/* Set LED brightness level */
 	/* Must not sleep, use a workqueue if needed */
@@ -85,6 +87,9 @@ struct led_classdev {
 	/* true if activated - deactivate routine uses it to do cleanup */
 	bool			activated;
 #endif
+
+	/* Ensures consistent access to the LED Flash Class device */
+	struct mutex		led_access;
 };
 
 extern int led_classdev_register(struct device *parent,
@@ -151,6 +156,33 @@ extern void led_set_brightness(struct led_classdev *led_cdev,
  */
 extern int led_update_brightness(struct led_classdev *led_cdev);
 
+/**
+ * led_sysfs_disable - disable LED sysfs interface
+ * @led_cdev: the LED to set
+ *
+ * Disable the led_cdev's sysfs interface.
+ */
+extern void led_sysfs_disable(struct led_classdev *led_cdev);
+
+/**
+ * led_sysfs_enable - enable LED sysfs interface
+ * @led_cdev: the LED to set
+ *
+ * Enable the led_cdev's sysfs interface.
+ */
+extern void led_sysfs_enable(struct led_classdev *led_cdev);
+
+/**
+ * led_sysfs_is_disabled - check if LED sysfs interface is disabled
+ * @led_cdev: the LED to query
+ *
+ * Returns: true if the led_cdev's sysfs interface is disabled.
+ */
+static inline bool led_sysfs_is_disabled(struct led_classdev *led_cdev)
+{
+	return led_cdev->flags & LED_SYSFS_DISABLE;
+}
+
 /*
  * LED Triggers
  */
-- 
cgit v1.2.3-70-g09d2


From 4d71a4a12b130ad033219e6f58c74a64059415eb Mon Sep 17 00:00:00 2001
From: Jacek Anaszewski <j.anaszewski@samsung.com>
Date: Fri, 14 Nov 2014 02:50:18 -0800
Subject: leds: Add support for setting brightness in a synchronous way

There are use cases when setting a LED brightness has to
have immediate effect (e.g. setting a torch LED brightness).
This patch extends LED subsystem to support such operations.
The LED subsystem internal API __led_set_brightness is changed
to led_set_brightness_async and new led_set_brightness_sync API
is added.

Signed-off-by: Jacek Anaszewski <j.anaszewski@samsung.com>
Acked-by: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Richard Purdie <rpurdie@rpsys.net>
Signed-off-by: Bryan Wu <cooloney@gmail.com>
---
 drivers/leds/led-class.c                  | 10 ++++++----
 drivers/leds/led-core.c                   | 18 +++++++++++++++---
 drivers/leds/leds.h                       | 20 ++++++++++++++++----
 drivers/leds/trigger/ledtrig-backlight.c  |  8 ++++----
 drivers/leds/trigger/ledtrig-default-on.c |  2 +-
 drivers/leds/trigger/ledtrig-gpio.c       |  6 +++---
 drivers/leds/trigger/ledtrig-heartbeat.c  |  2 +-
 drivers/leds/trigger/ledtrig-oneshot.c    |  4 ++--
 drivers/leds/trigger/ledtrig-transient.c  | 10 ++++++----
 include/linux/leds.h                      |  8 ++++++++
 10 files changed, 62 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 65722deb8d2..dbeebac38d3 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -55,7 +55,7 @@ static ssize_t brightness_store(struct device *dev,
 
 	if (state == LED_OFF)
 		led_trigger_remove(led_cdev);
-	__led_set_brightness(led_cdev, state);
+	led_set_brightness(led_cdev, state);
 
 	ret = size;
 unlock:
@@ -109,7 +109,7 @@ static void led_timer_function(unsigned long data)
 	unsigned long delay;
 
 	if (!led_cdev->blink_delay_on || !led_cdev->blink_delay_off) {
-		__led_set_brightness(led_cdev, LED_OFF);
+		led_set_brightness_async(led_cdev, LED_OFF);
 		return;
 	}
 
@@ -132,7 +132,7 @@ static void led_timer_function(unsigned long data)
 		delay = led_cdev->blink_delay_off;
 	}
 
-	__led_set_brightness(led_cdev, brightness);
+	led_set_brightness_async(led_cdev, brightness);
 
 	/* Return in next iteration if led is in one-shot mode and we are in
 	 * the final blink state so that the led is toggled each delay_on +
@@ -158,7 +158,7 @@ static void set_brightness_delayed(struct work_struct *ws)
 
 	led_stop_software_blink(led_cdev);
 
-	__led_set_brightness(led_cdev, led_cdev->delayed_set_value);
+	led_set_brightness_async(led_cdev, led_cdev->delayed_set_value);
 }
 
 /**
@@ -233,6 +233,8 @@ int led_classdev_register(struct device *parent, struct led_classdev *led_cdev)
 	if (!led_cdev->max_brightness)
 		led_cdev->max_brightness = LED_FULL;
 
+	led_cdev->flags |= SET_BRIGHTNESS_ASYNC;
+
 	led_update_brightness(led_cdev);
 
 	INIT_WORK(&led_cdev->set_brightness_work, set_brightness_delayed);
diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c
index be6d9fa5e97..9886dace5ad 100644
--- a/drivers/leds/led-core.c
+++ b/drivers/leds/led-core.c
@@ -42,13 +42,13 @@ static void led_set_software_blink(struct led_classdev *led_cdev,
 
 	/* never on - just set to off */
 	if (!delay_on) {
-		__led_set_brightness(led_cdev, LED_OFF);
+		led_set_brightness_async(led_cdev, LED_OFF);
 		return;
 	}
 
 	/* never off - just set to brightness */
 	if (!delay_off) {
-		__led_set_brightness(led_cdev, led_cdev->blink_brightness);
+		led_set_brightness_async(led_cdev, led_cdev->blink_brightness);
 		return;
 	}
 
@@ -117,6 +117,8 @@ EXPORT_SYMBOL_GPL(led_stop_software_blink);
 void led_set_brightness(struct led_classdev *led_cdev,
 			enum led_brightness brightness)
 {
+	int ret = 0;
+
 	/* delay brightness setting if need to stop soft-blink timer */
 	if (led_cdev->blink_delay_on || led_cdev->blink_delay_off) {
 		led_cdev->delayed_set_value = brightness;
@@ -124,7 +126,17 @@ void led_set_brightness(struct led_classdev *led_cdev,
 		return;
 	}
 
-	__led_set_brightness(led_cdev, brightness);
+	if (led_cdev->flags & SET_BRIGHTNESS_ASYNC) {
+		led_set_brightness_async(led_cdev, brightness);
+		return;
+	} else if (led_cdev->flags & SET_BRIGHTNESS_SYNC)
+		ret = led_set_brightness_sync(led_cdev, brightness);
+	else
+		ret = -EINVAL;
+
+	if (ret < 0)
+		dev_dbg(led_cdev->dev, "Setting LED brightness failed (%d)\n",
+			ret);
 }
 EXPORT_SYMBOL(led_set_brightness);
 
diff --git a/drivers/leds/leds.h b/drivers/leds/leds.h
index 4c50365344a..2348dbda526 100644
--- a/drivers/leds/leds.h
+++ b/drivers/leds/leds.h
@@ -17,16 +17,28 @@
 #include <linux/rwsem.h>
 #include <linux/leds.h>
 
-static inline void __led_set_brightness(struct led_classdev *led_cdev,
+static inline void led_set_brightness_async(struct led_classdev *led_cdev,
 					enum led_brightness value)
 {
-	if (value > led_cdev->max_brightness)
-		value = led_cdev->max_brightness;
-	led_cdev->brightness = value;
+	led_cdev->brightness = min(value, led_cdev->max_brightness);
+
 	if (!(led_cdev->flags & LED_SUSPENDED))
 		led_cdev->brightness_set(led_cdev, value);
 }
 
+static inline int led_set_brightness_sync(struct led_classdev *led_cdev,
+					enum led_brightness value)
+{
+	int ret = 0;
+
+	led_cdev->brightness = min(value, led_cdev->max_brightness);
+
+	if (!(led_cdev->flags & LED_SUSPENDED))
+		ret = led_cdev->brightness_set_sync(led_cdev,
+						led_cdev->brightness);
+	return ret;
+}
+
 static inline int led_get_brightness(struct led_classdev *led_cdev)
 {
 	return led_cdev->brightness;
diff --git a/drivers/leds/trigger/ledtrig-backlight.c b/drivers/leds/trigger/ledtrig-backlight.c
index 47e55aa9eef..59eca17d966 100644
--- a/drivers/leds/trigger/ledtrig-backlight.c
+++ b/drivers/leds/trigger/ledtrig-backlight.c
@@ -51,9 +51,9 @@ static int fb_notifier_callback(struct notifier_block *p,
 
 	if ((n->old_status == UNBLANK) ^ n->invert) {
 		n->brightness = led->brightness;
-		__led_set_brightness(led, LED_OFF);
+		led_set_brightness_async(led, LED_OFF);
 	} else {
-		__led_set_brightness(led, n->brightness);
+		led_set_brightness_async(led, n->brightness);
 	}
 
 	n->old_status = new_status;
@@ -89,9 +89,9 @@ static ssize_t bl_trig_invert_store(struct device *dev,
 
 	/* After inverting, we need to update the LED. */
 	if ((n->old_status == BLANK) ^ n->invert)
-		__led_set_brightness(led, LED_OFF);
+		led_set_brightness_async(led, LED_OFF);
 	else
-		__led_set_brightness(led, n->brightness);
+		led_set_brightness_async(led, n->brightness);
 
 	return num;
 }
diff --git a/drivers/leds/trigger/ledtrig-default-on.c b/drivers/leds/trigger/ledtrig-default-on.c
index 81a91be8e18..6f38f883aaf 100644
--- a/drivers/leds/trigger/ledtrig-default-on.c
+++ b/drivers/leds/trigger/ledtrig-default-on.c
@@ -19,7 +19,7 @@
 
 static void defon_trig_activate(struct led_classdev *led_cdev)
 {
-	__led_set_brightness(led_cdev, led_cdev->max_brightness);
+	led_set_brightness_async(led_cdev, led_cdev->max_brightness);
 }
 
 static struct led_trigger defon_led_trigger = {
diff --git a/drivers/leds/trigger/ledtrig-gpio.c b/drivers/leds/trigger/ledtrig-gpio.c
index c86c4182647..4cc7040746c 100644
--- a/drivers/leds/trigger/ledtrig-gpio.c
+++ b/drivers/leds/trigger/ledtrig-gpio.c
@@ -54,12 +54,12 @@ static void gpio_trig_work(struct work_struct *work)
 
 	if (tmp) {
 		if (gpio_data->desired_brightness)
-			__led_set_brightness(gpio_data->led,
+			led_set_brightness_async(gpio_data->led,
 					   gpio_data->desired_brightness);
 		else
-			__led_set_brightness(gpio_data->led, LED_FULL);
+			led_set_brightness_async(gpio_data->led, LED_FULL);
 	} else {
-		__led_set_brightness(gpio_data->led, LED_OFF);
+		led_set_brightness_async(gpio_data->led, LED_OFF);
 	}
 }
 
diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c
index 5c8464a3317..fea6871d260 100644
--- a/drivers/leds/trigger/ledtrig-heartbeat.c
+++ b/drivers/leds/trigger/ledtrig-heartbeat.c
@@ -74,7 +74,7 @@ static void led_heartbeat_function(unsigned long data)
 		break;
 	}
 
-	__led_set_brightness(led_cdev, brightness);
+	led_set_brightness_async(led_cdev, brightness);
 	mod_timer(&heartbeat_data->timer, jiffies + delay);
 }
 
diff --git a/drivers/leds/trigger/ledtrig-oneshot.c b/drivers/leds/trigger/ledtrig-oneshot.c
index cb4c7466692..fbd02cdc3ad 100644
--- a/drivers/leds/trigger/ledtrig-oneshot.c
+++ b/drivers/leds/trigger/ledtrig-oneshot.c
@@ -63,9 +63,9 @@ static ssize_t led_invert_store(struct device *dev,
 	oneshot_data->invert = !!state;
 
 	if (oneshot_data->invert)
-		__led_set_brightness(led_cdev, LED_FULL);
+		led_set_brightness_async(led_cdev, LED_FULL);
 	else
-		__led_set_brightness(led_cdev, LED_OFF);
+		led_set_brightness_async(led_cdev, LED_OFF);
 
 	return size;
 }
diff --git a/drivers/leds/trigger/ledtrig-transient.c b/drivers/leds/trigger/ledtrig-transient.c
index e5abc00bb00..3c34de404d1 100644
--- a/drivers/leds/trigger/ledtrig-transient.c
+++ b/drivers/leds/trigger/ledtrig-transient.c
@@ -41,7 +41,7 @@ static void transient_timer_function(unsigned long data)
 	struct transient_trig_data *transient_data = led_cdev->trigger_data;
 
 	transient_data->activate = 0;
-	__led_set_brightness(led_cdev, transient_data->restore_state);
+	led_set_brightness_async(led_cdev, transient_data->restore_state);
 }
 
 static ssize_t transient_activate_show(struct device *dev,
@@ -72,7 +72,8 @@ static ssize_t transient_activate_store(struct device *dev,
 	if (state == 0 && transient_data->activate == 1) {
 		del_timer(&transient_data->timer);
 		transient_data->activate = state;
-		__led_set_brightness(led_cdev, transient_data->restore_state);
+		led_set_brightness_async(led_cdev,
+					transient_data->restore_state);
 		return size;
 	}
 
@@ -80,7 +81,7 @@ static ssize_t transient_activate_store(struct device *dev,
 	if (state == 1 && transient_data->activate == 0 &&
 	    transient_data->duration != 0) {
 		transient_data->activate = state;
-		__led_set_brightness(led_cdev, transient_data->state);
+		led_set_brightness_async(led_cdev, transient_data->state);
 		transient_data->restore_state =
 		    (transient_data->state == LED_FULL) ? LED_OFF : LED_FULL;
 		mod_timer(&transient_data->timer,
@@ -203,7 +204,8 @@ static void transient_trig_deactivate(struct led_classdev *led_cdev)
 
 	if (led_cdev->activated) {
 		del_timer_sync(&transient_data->timer);
-		__led_set_brightness(led_cdev, transient_data->restore_state);
+		led_set_brightness_async(led_cdev,
+					transient_data->restore_state);
 		device_remove_file(led_cdev->dev, &dev_attr_activate);
 		device_remove_file(led_cdev->dev, &dev_attr_duration);
 		device_remove_file(led_cdev->dev, &dev_attr_state);
diff --git a/include/linux/leds.h b/include/linux/leds.h
index 737f9b1051f..dfe70e928ea 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -44,11 +44,19 @@ struct led_classdev {
 #define LED_BLINK_ONESHOT_STOP	(1 << 18)
 #define LED_BLINK_INVERT	(1 << 19)
 #define LED_SYSFS_DISABLE	(1 << 20)
+#define SET_BRIGHTNESS_ASYNC	(1 << 21)
+#define SET_BRIGHTNESS_SYNC	(1 << 22)
 
 	/* Set LED brightness level */
 	/* Must not sleep, use a workqueue if needed */
 	void		(*brightness_set)(struct led_classdev *led_cdev,
 					  enum led_brightness brightness);
+	/*
+	 * Set LED brightness level immediately - it can block the caller for
+	 * the time required for accessing a LED device register.
+	 */
+	int		(*brightness_set_sync)(struct led_classdev *led_cdev,
+					enum led_brightness brightness);
 	/* Get LED brightness level */
 	enum led_brightness (*brightness_get)(struct led_classdev *led_cdev);
 
-- 
cgit v1.2.3-70-g09d2


From 970d0f1b280372cfd46b6de5529d96f8448de943 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Thu, 13 Nov 2014 14:37:47 +0200
Subject: Bluetooth: Convert LTK list to RCU

This patch set converts the hdev->long_term_keys list to use RCU to
eliminate the need to use hci_dev_lock/unlock.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_core.c         | 42 +++++++++++++++++++++++-----------------
 net/bluetooth/hci_event.c        |  4 ++--
 net/bluetooth/smp.c              | 10 ++++------
 4 files changed, 31 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 4e39a5adfca..a4adef22ad7 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -108,6 +108,7 @@ struct smp_csrk {
 
 struct smp_ltk {
 	struct list_head list;
+	struct rcu_head rcu;
 	bdaddr_t bdaddr;
 	u8 bdaddr_type;
 	u8 authenticated;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 6c162c8809c..c9495fb9f59 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -778,17 +778,15 @@ static const struct file_operations identity_resolving_keys_fops = {
 static int long_term_keys_show(struct seq_file *f, void *ptr)
 {
 	struct hci_dev *hdev = f->private;
-	struct list_head *p, *n;
+	struct smp_ltk *ltk;
 
-	hci_dev_lock(hdev);
-	list_for_each_safe(p, n, &hdev->long_term_keys) {
-		struct smp_ltk *ltk = list_entry(p, struct smp_ltk, list);
+	rcu_read_lock();
+	list_for_each_entry_rcu(ltk, &hdev->long_term_keys, list)
 		seq_printf(f, "%pMR (type %u) %u 0x%02x %u %.4x %.16llx %*phN\n",
 			   &ltk->bdaddr, ltk->bdaddr_type, ltk->authenticated,
 			   ltk->type, ltk->enc_size, __le16_to_cpu(ltk->ediv),
 			   __le64_to_cpu(ltk->rand), 16, ltk->val);
-	}
-	hci_dev_unlock(hdev);
+	rcu_read_unlock();
 
 	return 0;
 }
@@ -3106,11 +3104,11 @@ void hci_link_keys_clear(struct hci_dev *hdev)
 
 void hci_smp_ltks_clear(struct hci_dev *hdev)
 {
-	struct smp_ltk *k, *tmp;
+	struct smp_ltk *k;
 
-	list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) {
-		list_del(&k->list);
-		kfree(k);
+	list_for_each_entry_rcu(k, &hdev->long_term_keys, list) {
+		list_del_rcu(&k->list);
+		kfree_rcu(k, rcu);
 	}
 }
 
@@ -3184,15 +3182,18 @@ struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, __le64 rand,
 {
 	struct smp_ltk *k;
 
-	list_for_each_entry(k, &hdev->long_term_keys, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(k, &hdev->long_term_keys, list) {
 		if (k->ediv != ediv || k->rand != rand)
 			continue;
 
 		if (ltk_role(k->type) != role)
 			continue;
 
+		rcu_read_unlock();
 		return k;
 	}
+	rcu_read_unlock();
 
 	return NULL;
 }
@@ -3202,11 +3203,16 @@ struct smp_ltk *hci_find_ltk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr,
 {
 	struct smp_ltk *k;
 
-	list_for_each_entry(k, &hdev->long_term_keys, list)
+	rcu_read_lock();
+	list_for_each_entry_rcu(k, &hdev->long_term_keys, list) {
 		if (addr_type == k->bdaddr_type &&
 		    bacmp(bdaddr, &k->bdaddr) == 0 &&
-		    ltk_role(k->type) == role)
+		    ltk_role(k->type) == role) {
+			rcu_read_unlock();
 			return k;
+		}
+	}
+	rcu_read_unlock();
 
 	return NULL;
 }
@@ -3309,7 +3315,7 @@ struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr,
 		key = kzalloc(sizeof(*key), GFP_KERNEL);
 		if (!key)
 			return NULL;
-		list_add(&key->list, &hdev->long_term_keys);
+		list_add_rcu(&key->list, &hdev->long_term_keys);
 	}
 
 	bacpy(&key->bdaddr, bdaddr);
@@ -3365,17 +3371,17 @@ int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr)
 
 int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type)
 {
-	struct smp_ltk *k, *tmp;
+	struct smp_ltk *k;
 	int removed = 0;
 
-	list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) {
+	list_for_each_entry_rcu(k, &hdev->long_term_keys, list) {
 		if (bacmp(bdaddr, &k->bdaddr) || k->bdaddr_type != bdaddr_type)
 			continue;
 
 		BT_DBG("%s removing %pMR", hdev->name, bdaddr);
 
-		list_del(&k->list);
-		kfree(k);
+		list_del_rcu(&k->list);
+		kfree_rcu(k, rcu);
 		removed++;
 	}
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index aec3b1dce1c..09d76547d98 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -4578,8 +4578,8 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	 */
 	if (ltk->type == SMP_STK) {
 		set_bit(HCI_CONN_STK_ENCRYPT, &conn->flags);
-		list_del(&ltk->list);
-		kfree(ltk);
+		list_del_rcu(&ltk->list);
+		kfree_rcu(ltk, rcu);
 	} else {
 		clear_bit(HCI_CONN_STK_ENCRYPT, &conn->flags);
 	}
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 3dc5f0e6640..fd2dfe5222b 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -383,13 +383,13 @@ static void smp_chan_destroy(struct l2cap_conn *conn)
 	/* If pairing failed clean up any keys we might have */
 	if (!complete) {
 		if (smp->ltk) {
-			list_del(&smp->ltk->list);
-			kfree(smp->ltk);
+			list_del_rcu(&smp->ltk->list);
+			kfree_rcu(smp->ltk, rcu);
 		}
 
 		if (smp->slave_ltk) {
-			list_del(&smp->slave_ltk->list);
-			kfree(smp->slave_ltk);
+			list_del_rcu(&smp->slave_ltk->list);
+			kfree_rcu(smp->slave_ltk, rcu);
 		}
 
 		if (smp->remote_irk) {
@@ -1321,7 +1321,6 @@ static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb)
 
 	skb_pull(skb, sizeof(*rp));
 
-	hci_dev_lock(hdev);
 	authenticated = (hcon->sec_level == BT_SECURITY_HIGH);
 	ltk = hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, SMP_LTK,
 			  authenticated, smp->tk, smp->enc_key_size,
@@ -1329,7 +1328,6 @@ static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb)
 	smp->ltk = ltk;
 	if (!(smp->remote_key_dist & KEY_DIST_MASK))
 		smp_distribute_keys(smp);
-	hci_dev_unlock(hdev);
 
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From adae20cb2d20e5151b866945f802b0c2312f0f82 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Thu, 13 Nov 2014 14:37:48 +0200
Subject: Bluetooth: Convert IRK list to RCU

This patch set converts the hdev->identity_resolving_keys list to use
RCU to eliminate the need to use hci_dev_lock/unlock.

An additional change that must be done is to remove use of
CRYPTO_ALG_ASYNC for the hdev-specific AES crypto context. The reason is
that this context is used for matching RPAs and the loop that does the
matching is under the RCU read lock, i.e. is an atomic section which
cannot sleep.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_core.c         | 46 +++++++++++++++++++++++-----------------
 net/bluetooth/smp.c              | 10 ++++-----
 3 files changed, 33 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index a4adef22ad7..fe2d5f299e1 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -121,6 +121,7 @@ struct smp_ltk {
 
 struct smp_irk {
 	struct list_head list;
+	struct rcu_head rcu;
 	bdaddr_t rpa;
 	bdaddr_t bdaddr;
 	u8 addr_type;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index c9495fb9f59..90ea0b7670d 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -748,16 +748,15 @@ static const struct file_operations white_list_fops = {
 static int identity_resolving_keys_show(struct seq_file *f, void *ptr)
 {
 	struct hci_dev *hdev = f->private;
-	struct list_head *p, *n;
+	struct smp_irk *irk;
 
-	hci_dev_lock(hdev);
-	list_for_each_safe(p, n, &hdev->identity_resolving_keys) {
-		struct smp_irk *irk = list_entry(p, struct smp_irk, list);
+	rcu_read_lock();
+	list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) {
 		seq_printf(f, "%pMR (type %u) %*phN %pMR\n",
 			   &irk->bdaddr, irk->addr_type,
 			   16, irk->val, &irk->rpa);
 	}
-	hci_dev_unlock(hdev);
+	rcu_read_unlock();
 
 	return 0;
 }
@@ -3114,11 +3113,11 @@ void hci_smp_ltks_clear(struct hci_dev *hdev)
 
 void hci_smp_irks_clear(struct hci_dev *hdev)
 {
-	struct smp_irk *k, *tmp;
+	struct smp_irk *k;
 
-	list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) {
-		list_del(&k->list);
-		kfree(k);
+	list_for_each_entry_rcu(k, &hdev->identity_resolving_keys, list) {
+		list_del_rcu(&k->list);
+		kfree_rcu(k, rcu);
 	}
 }
 
@@ -3221,17 +3220,22 @@ struct smp_irk *hci_find_irk_by_rpa(struct hci_dev *hdev, bdaddr_t *rpa)
 {
 	struct smp_irk *irk;
 
-	list_for_each_entry(irk, &hdev->identity_resolving_keys, list) {
-		if (!bacmp(&irk->rpa, rpa))
+	rcu_read_lock();
+	list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) {
+		if (!bacmp(&irk->rpa, rpa)) {
+			rcu_read_unlock();
 			return irk;
+		}
 	}
 
-	list_for_each_entry(irk, &hdev->identity_resolving_keys, list) {
+	list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) {
 		if (smp_irk_matches(hdev, irk->val, rpa)) {
 			bacpy(&irk->rpa, rpa);
+			rcu_read_unlock();
 			return irk;
 		}
 	}
+	rcu_read_unlock();
 
 	return NULL;
 }
@@ -3245,11 +3249,15 @@ struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	if (addr_type == ADDR_LE_DEV_RANDOM && (bdaddr->b[5] & 0xc0) != 0xc0)
 		return NULL;
 
-	list_for_each_entry(irk, &hdev->identity_resolving_keys, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) {
 		if (addr_type == irk->addr_type &&
-		    bacmp(bdaddr, &irk->bdaddr) == 0)
+		    bacmp(bdaddr, &irk->bdaddr) == 0) {
+			rcu_read_unlock();
 			return irk;
+		}
 	}
+	rcu_read_unlock();
 
 	return NULL;
 }
@@ -3344,7 +3352,7 @@ struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr,
 		bacpy(&irk->bdaddr, bdaddr);
 		irk->addr_type = addr_type;
 
-		list_add(&irk->list, &hdev->identity_resolving_keys);
+		list_add_rcu(&irk->list, &hdev->identity_resolving_keys);
 	}
 
 	memcpy(irk->val, val, 16);
@@ -3390,16 +3398,16 @@ int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type)
 
 void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type)
 {
-	struct smp_irk *k, *tmp;
+	struct smp_irk *k;
 
-	list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) {
+	list_for_each_entry_rcu(k, &hdev->identity_resolving_keys, list) {
 		if (bacmp(bdaddr, &k->bdaddr) || k->addr_type != addr_type)
 			continue;
 
 		BT_DBG("%s removing %pMR", hdev->name, bdaddr);
 
-		list_del(&k->list);
-		kfree(k);
+		list_del_rcu(&k->list);
+		kfree_rcu(k, rcu);
 	}
 }
 
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index fd2dfe5222b..7b610f61525 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -393,8 +393,8 @@ static void smp_chan_destroy(struct l2cap_conn *conn)
 		}
 
 		if (smp->remote_irk) {
-			list_del(&smp->remote_irk->list);
-			kfree(smp->remote_irk);
+			list_del_rcu(&smp->remote_irk->list);
+			kfree_rcu(smp->remote_irk, rcu);
 		}
 	}
 
@@ -655,8 +655,8 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 		 * just remove it.
 		 */
 		if (!bacmp(&smp->remote_irk->rpa, BDADDR_ANY)) {
-			list_del(&smp->remote_irk->list);
-			kfree(smp->remote_irk);
+			list_del_rcu(&smp->remote_irk->list);
+			kfree_rcu(smp->remote_irk, rcu);
 			smp->remote_irk = NULL;
 		}
 	}
@@ -1696,7 +1696,7 @@ int smp_register(struct hci_dev *hdev)
 
 	BT_DBG("%s", hdev->name);
 
-	tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
+	tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, 0);
 	if (IS_ERR(tfm_aes)) {
 		int err = PTR_ERR(tfm_aes);
 		BT_ERR("Unable to create crypto context");
-- 
cgit v1.2.3-70-g09d2


From f622b429dadf83c3cc2d70f57f407ad85684eb36 Mon Sep 17 00:00:00 2001
From: Chen Hanxiao <chenhanxiao@cn.fujitsu.com>
Date: Tue, 4 Nov 2014 16:51:22 +0800
Subject: sched: Update comments about CLONE_NEWUTS and CLONE_NEWIPC

Remove question mark:

 s/New utsname group?/New utsname namespace

Unified style for IPC:

 s/New ipcs/New ipc namespace

Signed-off-by: Chen Hanxiao <chenhanxiao@cn.fujitsu.com>
Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Jiri Kosina <trivial@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-api@vger.kernel.org
Link: http://lkml.kernel.org/r/1415091082-15093-1-git-send-email-chenhanxiao@cn.fujitsu.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/uapi/linux/sched.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index b932be9f5c5..cc89ddefa92 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -23,8 +23,8 @@
 #define CLONE_CHILD_SETTID	0x01000000	/* set the TID in the child */
 /* 0x02000000 was previously the unused CLONE_STOPPED (Start in stopped state)
    and is now available for re-use. */
-#define CLONE_NEWUTS		0x04000000	/* New utsname group? */
-#define CLONE_NEWIPC		0x08000000	/* New ipcs */
+#define CLONE_NEWUTS		0x04000000	/* New utsname namespace */
+#define CLONE_NEWIPC		0x08000000	/* New ipc namespace */
 #define CLONE_NEWUSER		0x10000000	/* New user namespace */
 #define CLONE_NEWPID		0x20000000	/* New pid namespace */
 #define CLONE_NEWNET		0x40000000	/* New network namespace */
-- 
cgit v1.2.3-70-g09d2


From d8b163c4c657478ef33c082cff78d03a4ca07bb2 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@parallels.com>
Date: Tue, 11 Nov 2014 12:46:29 +0300
Subject: sched/numa: Init numa balancing fields of init_task

We do not initialize init_task.numa_preferred_nid,
but this value is inherited by userspace "init"
process:

rest_init()->kernel_thread(kernel_init)->do_fork(CLONE_VM);

__sched_fork()
{
	if (clone_flags & CLONE_VM)
		p->numa_preferred_nid = current->numa_preferred_nid;
	else
		p->numa_preferred_nid = -1;
}

kernel_init() becomes userspace "init" process.

So, we propagate garbage nid to userspace, and it may be used
during numa balancing.

Currently, we do not have reports about this brings a problem,
but it seem we should set it for sure.

Even if init_task.numa_preferred_nid is zero, we may meet a weird
configuration without nid#0. On sparc64, where processors are
numbered physically, I saw a machine without cpu#1, while cpu#2
existed. Possible, something similar may be with numa nodes.
So, let's initialize it and be sure we're safe.

Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Eric Paris <eparis@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Sergey Dyasly <dserrg@gmail.com>
Link: http://lkml.kernel.org/r/1415699189.15631.6.camel@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/init_task.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 77fc43f8fb7..5f30ac8c82b 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -166,6 +166,15 @@ extern struct task_group root_task_group;
 # define INIT_RT_MUTEXES(tsk)
 #endif
 
+#ifdef CONFIG_NUMA_BALANCING
+# define INIT_NUMA_BALANCING(tsk)					\
+	.numa_preferred_nid = -1,					\
+	.numa_group = NULL,						\
+	.numa_faults = NULL,
+#else
+# define INIT_NUMA_BALANCING(tsk)
+#endif
+
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
@@ -237,6 +246,7 @@ extern struct task_group root_task_group;
 	INIT_CPUSET_SEQ(tsk)						\
 	INIT_RT_MUTEXES(tsk)						\
 	INIT_VTIME(tsk)							\
+	INIT_NUMA_BALANCING(tsk)					\
 }
 
 
-- 
cgit v1.2.3-70-g09d2


From 60e2364e60e86e81bc6377f49779779e6120977f Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Wed, 24 Sep 2014 13:48:37 +0200
Subject: perf: Add ability to sample machine state on interrupt

Enable capture of interrupted machine state for each sample.

Registers to sample are passed per event in the sample_regs_intr bitmask.

To sample interrupt machine state, the PERF_SAMPLE_INTR_REGS must be passed in
sample_type.

The list of available registers is arch dependent and provided by asm/perf_regs.h

Registers are laid out as u64 in the order of the bit order of sample_intr_regs.

This patch also adds a new ABI version PERF_ATTR_SIZE_VER4 because we extend
the perf_event_attr struct with a new u64 field.

Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: cebbert.lkml@gmail.com
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-api@vger.kernel.org
Link: http://lkml.kernel.org/r/1411559322-16548-2-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/perf_event.h      |  7 +++++--
 include/uapi/linux/perf_event.h | 15 +++++++++++++-
 kernel/events/core.c            | 46 +++++++++++++++++++++++++++++++++++++++--
 3 files changed, 63 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 893a0d07986..68d46d536e2 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -79,7 +79,7 @@ struct perf_branch_stack {
 	struct perf_branch_entry	entries[0];
 };
 
-struct perf_regs_user {
+struct perf_regs {
 	__u64		abi;
 	struct pt_regs	*regs;
 };
@@ -600,7 +600,8 @@ struct perf_sample_data {
 	struct perf_callchain_entry	*callchain;
 	struct perf_raw_record		*raw;
 	struct perf_branch_stack	*br_stack;
-	struct perf_regs_user		regs_user;
+	struct perf_regs		regs_user;
+	struct perf_regs		regs_intr;
 	u64				stack_user_size;
 	u64				weight;
 	/*
@@ -630,6 +631,8 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->weight = 0;
 	data->data_src.val = PERF_MEM_NA;
 	data->txn = 0;
+	data->regs_intr.abi = PERF_SAMPLE_REGS_ABI_NONE;
+	data->regs_intr.regs = NULL;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 9d845404d87..9b79abbd1ab 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -137,8 +137,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_DATA_SRC			= 1U << 15,
 	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
 	PERF_SAMPLE_TRANSACTION			= 1U << 17,
+	PERF_SAMPLE_REGS_INTR			= 1U << 18,
 
-	PERF_SAMPLE_MAX = 1U << 18,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 19,		/* non-ABI */
 };
 
 /*
@@ -238,6 +239,7 @@ enum perf_event_read_format {
 #define PERF_ATTR_SIZE_VER2	80	/* add: branch_sample_type */
 #define PERF_ATTR_SIZE_VER3	96	/* add: sample_regs_user */
 					/* add: sample_stack_user */
+#define PERF_ATTR_SIZE_VER4	104	/* add: sample_regs_intr */
 
 /*
  * Hardware event_id to monitor via a performance monitoring event:
@@ -334,6 +336,15 @@ struct perf_event_attr {
 
 	/* Align to u64. */
 	__u32	__reserved_2;
+	/*
+	 * Defines set of regs to dump for each sample
+	 * state captured on:
+	 *  - precise = 0: PMU interrupt
+	 *  - precise > 0: sampled instruction
+	 *
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_intr;
 };
 
 #define perf_flags(attr)	(*(&(attr)->read_format + 1))
@@ -686,6 +697,8 @@ enum perf_event_type {
 	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
 	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
 	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
+	 *	{ u64			abi; # enum perf_sample_regs_abi
+	 *	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1cd5eef1fcd..c2be1597ece 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4460,7 +4460,7 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 	}
 }
 
-static void perf_sample_regs_user(struct perf_regs_user *regs_user,
+static void perf_sample_regs_user(struct perf_regs *regs_user,
 				  struct pt_regs *regs)
 {
 	if (!user_mode(regs)) {
@@ -4476,6 +4476,14 @@ static void perf_sample_regs_user(struct perf_regs_user *regs_user,
 	}
 }
 
+static void perf_sample_regs_intr(struct perf_regs *regs_intr,
+				  struct pt_regs *regs)
+{
+	regs_intr->regs = regs;
+	regs_intr->abi  = perf_reg_abi(current);
+}
+
+
 /*
  * Get remaining task size from user stack pointer.
  *
@@ -4857,6 +4865,23 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_TRANSACTION)
 		perf_output_put(handle, data->txn);
 
+	if (sample_type & PERF_SAMPLE_REGS_INTR) {
+		u64 abi = data->regs_intr.abi;
+		/*
+		 * If there are no regs to dump, notice it through
+		 * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE).
+		 */
+		perf_output_put(handle, abi);
+
+		if (abi) {
+			u64 mask = event->attr.sample_regs_intr;
+
+			perf_output_sample_regs(handle,
+						data->regs_intr.regs,
+						mask);
+		}
+	}
+
 	if (!event->attr.watermark) {
 		int wakeup_events = event->attr.wakeup_events;
 
@@ -4943,7 +4968,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 		 * in case new sample type is added, because we could eat
 		 * up the rest of the sample size.
 		 */
-		struct perf_regs_user *uregs = &data->regs_user;
+		struct perf_regs *uregs = &data->regs_user;
 		u16 stack_size = event->attr.sample_stack_user;
 		u16 size = sizeof(u64);
 
@@ -4964,6 +4989,21 @@ void perf_prepare_sample(struct perf_event_header *header,
 		data->stack_user_size = stack_size;
 		header->size += size;
 	}
+
+	if (sample_type & PERF_SAMPLE_REGS_INTR) {
+		/* regs dump ABI info */
+		int size = sizeof(u64);
+
+		perf_sample_regs_intr(&data->regs_intr, regs);
+
+		if (data->regs_intr.regs) {
+			u64 mask = event->attr.sample_regs_intr;
+
+			size += hweight64(mask) * sizeof(u64);
+		}
+
+		header->size += size;
+	}
 }
 
 static void perf_event_output(struct perf_event *event,
@@ -7151,6 +7191,8 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 			ret = -EINVAL;
 	}
 
+	if (attr->sample_type & PERF_SAMPLE_REGS_INTR)
+		ret = perf_reg_validate(attr->sample_regs_intr);
 out:
 	return ret;
 
-- 
cgit v1.2.3-70-g09d2


From 2565711fb7d7c28e0cd93c8971b520d1b10b857c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 24 Sep 2014 13:48:42 +0200
Subject: perf: Improve the perf_sample_data struct layout

This patch reorders fields in the perf_sample_data struct in order to
minimize the number of cachelines touched in perf_sample_data_init().
It also removes some intializations which are redundant with the code
in kernel/events/core.c

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1411559322-16548-7-git-send-email-eranian@google.com
Cc: cebbert.lkml@gmail.com
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: jolsa@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/perf_event.h | 34 +++++++++++++++++-----------------
 kernel/events/core.c       | 16 ++++++++--------
 2 files changed, 25 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 68d46d536e2..486e84ccb1f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -580,35 +580,40 @@ extern u64 perf_event_read_value(struct perf_event *event,
 
 
 struct perf_sample_data {
-	u64				type;
+	/*
+	 * Fields set by perf_sample_data_init(), group so as to
+	 * minimize the cachelines touched.
+	 */
+	u64				addr;
+	struct perf_raw_record		*raw;
+	struct perf_branch_stack	*br_stack;
+	u64				period;
+	u64				weight;
+	u64				txn;
+	union  perf_mem_data_src	data_src;
 
+	/*
+	 * The other fields, optionally {set,used} by
+	 * perf_{prepare,output}_sample().
+	 */
+	u64				type;
 	u64				ip;
 	struct {
 		u32	pid;
 		u32	tid;
 	}				tid_entry;
 	u64				time;
-	u64				addr;
 	u64				id;
 	u64				stream_id;
 	struct {
 		u32	cpu;
 		u32	reserved;
 	}				cpu_entry;
-	u64				period;
-	union  perf_mem_data_src	data_src;
 	struct perf_callchain_entry	*callchain;
-	struct perf_raw_record		*raw;
-	struct perf_branch_stack	*br_stack;
 	struct perf_regs		regs_user;
 	struct perf_regs		regs_intr;
 	u64				stack_user_size;
-	u64				weight;
-	/*
-	 * Transaction flags for abort events:
-	 */
-	u64				txn;
-};
+} ____cacheline_aligned;
 
 /* default value for data source */
 #define PERF_MEM_NA (PERF_MEM_S(OP, NA)   |\
@@ -625,14 +630,9 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->raw  = NULL;
 	data->br_stack = NULL;
 	data->period = period;
-	data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
-	data->regs_user.regs = NULL;
-	data->stack_user_size = 0;
 	data->weight = 0;
 	data->data_src.val = PERF_MEM_NA;
 	data->txn = 0;
-	data->regs_intr.abi = PERF_SAMPLE_REGS_ABI_NONE;
-	data->regs_intr.regs = NULL;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c2be1597ece..3e19d3ebc29 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4471,8 +4471,11 @@ static void perf_sample_regs_user(struct perf_regs *regs_user,
 	}
 
 	if (regs) {
-		regs_user->regs = regs;
 		regs_user->abi  = perf_reg_abi(current);
+		regs_user->regs = regs;
+	} else {
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
+		regs_user->regs = NULL;
 	}
 }
 
@@ -4947,12 +4950,13 @@ void perf_prepare_sample(struct perf_event_header *header,
 		header->size += size;
 	}
 
+	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
+		perf_sample_regs_user(&data->regs_user, regs);
+
 	if (sample_type & PERF_SAMPLE_REGS_USER) {
 		/* regs dump ABI info */
 		int size = sizeof(u64);
 
-		perf_sample_regs_user(&data->regs_user, regs);
-
 		if (data->regs_user.regs) {
 			u64 mask = event->attr.sample_regs_user;
 			size += hweight64(mask) * sizeof(u64);
@@ -4968,15 +4972,11 @@ void perf_prepare_sample(struct perf_event_header *header,
 		 * in case new sample type is added, because we could eat
 		 * up the rest of the sample size.
 		 */
-		struct perf_regs *uregs = &data->regs_user;
 		u16 stack_size = event->attr.sample_stack_user;
 		u16 size = sizeof(u64);
 
-		if (!uregs->abi)
-			perf_sample_regs_user(uregs, regs);
-
 		stack_size = perf_sample_ustack_size(stack_size, header->size,
-						     uregs->regs);
+						     data->regs_user.regs);
 
 		/*
 		 * If there is something to dump, add space for the dump
-- 
cgit v1.2.3-70-g09d2


From 960fb622f85180f36d3aff82af53e2be3db2f888 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 16 Nov 2014 06:23:05 -0800
Subject: net: provide a per host RSS key generic infrastructure

RSS (Receive Side Scaling) typically uses Toeplitz hash and a 40 or 52 bytes
RSS key.

Some drivers use a constant (and well known key), some drivers use a random
key per port, making bonding setups hard to tune. Well known keys increase
attack surface, considering that number of queues is usually a power of two.

This patch provides infrastructure to help drivers doing the right thing.

netdev_rss_key_fill() should be used by drivers to initialize their RSS key,
even if they provide ethtool -X support to let user redefine the key later.

A new /proc/sys/net/core/netdev_rss_key file can be used to get the host
RSS key even for drivers not providing ethtool -x support, in case some
applications want to precisely setup flows to match some RX queues.

Tested:

myhost:~# cat /proc/sys/net/core/netdev_rss_key
11:63:99:bb:79:fb:a5:a7:07:45:b2:20:bf:02:42:2d:08:1a:dd:19:2b:6b:23:ac:56:28:9d:70:c3:ac:e8:16:4b:b7:c1:10:53:a4:78:41:36:40:74:b6:15:ca:27:44:aa:b3:4d:72

myhost:~# ethtool -x eth0
RX flow hash indirection table for eth0 with 8 RX ring(s):
    0:      0     1     2     3     4     5     6     7
RSS hash key:
11:63:99:bb:79:fb:a5:a7:07:45:b2:20:bf:02:42:2d:08:1a:dd:19:2b:6b:23:ac:56:28:9d:70:c3:ac:e8:16:4b:b7:c1:10:53:a4:78:41

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/sysctl/net.txt | 22 ++++++++++++++++++++++
 include/linux/netdevice.h    |  6 ++++++
 net/core/ethtool.c           | 11 +++++++++++
 net/core/sysctl_net_core.c   | 19 +++++++++++++++++++
 4 files changed, 58 insertions(+)

(limited to 'include')

diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index e26c607468a..666594b43cf 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -142,6 +142,28 @@ netdev_max_backlog
 Maximum number  of  packets,  queued  on  the  INPUT  side, when the interface
 receives packets faster than kernel can process them.
 
+netdev_rss_key
+--------------
+
+RSS (Receive Side Scaling) enabled drivers use a 40 bytes host key that is
+randomly generated.
+Some user space might need to gather its content even if drivers do not
+provide ethtool -x support yet.
+
+myhost:~# cat /proc/sys/net/core/netdev_rss_key
+84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8: ... (52 bytes total)
+
+File contains nul bytes if no driver ever called netdev_rss_key_fill() function.
+Note:
+/proc/sys/net/core/netdev_rss_key contains 52 bytes of key,
+but most drivers only use 40 bytes of it.
+
+myhost:~# ethtool -x eth0
+RX flow hash indirection table for eth0 with 8 RX ring(s):
+    0:    0     1     2     3     4     5     6     7
+RSS hash key:
+84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8:43:e3:c9:0c:fd:17:55:c2:3a:4d:69:ed:f1:42:89
+
 netdev_tstamp_prequeue
 ----------------------
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4a6f770377d..db63cf459ba 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3422,6 +3422,12 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
 void *netdev_lower_dev_get_private(struct net_device *dev,
 				   struct net_device *lower_dev);
+
+/* RSS keys are 40 or 52 bytes long */
+#define NETDEV_RSS_KEY_LEN 52
+extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN];
+void netdev_rss_key_fill(void *buffer, size_t len);
+
 int dev_get_nest_level(struct net_device *dev,
 		       bool (*type_check)(struct net_device *dev));
 int skb_checksum_help(struct sk_buff *skb);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index b0f84f5ddda..715f51f321e 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -25,6 +25,7 @@
 #include <linux/slab.h>
 #include <linux/rtnetlink.h>
 #include <linux/sched.h>
+#include <linux/net.h>
 
 /*
  * Some useful ethtool_ops methods that're device independent.
@@ -573,6 +574,16 @@ static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr,
 	return 0;
 }
 
+u8 netdev_rss_key[NETDEV_RSS_KEY_LEN];
+
+void netdev_rss_key_fill(void *buffer, size_t len)
+{
+	BUG_ON(len > sizeof(netdev_rss_key));
+	net_get_random_once(netdev_rss_key, sizeof(netdev_rss_key));
+	memcpy(buffer, netdev_rss_key, len);
+}
+EXPORT_SYMBOL(netdev_rss_key_fill);
+
 static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 						     void __user *useraddr)
 {
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index f93f092fe22..31baba2a71c 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -217,6 +217,18 @@ static int set_default_qdisc(struct ctl_table *table, int write,
 }
 #endif
 
+static int proc_do_rss_key(struct ctl_table *table, int write,
+			   void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table fake_table;
+	char buf[NETDEV_RSS_KEY_LEN * 3];
+
+	snprintf(buf, sizeof(buf), "%*phC", NETDEV_RSS_KEY_LEN, netdev_rss_key);
+	fake_table.data = buf;
+	fake_table.maxlen = sizeof(buf);
+	return proc_dostring(&fake_table, write, buffer, lenp, ppos);
+}
+
 static struct ctl_table net_core_table[] = {
 #ifdef CONFIG_NET
 	{
@@ -265,6 +277,13 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "netdev_rss_key",
+		.data		= &netdev_rss_key,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= proc_do_rss_key,
+	},
 #ifdef CONFIG_BPF_JIT
 	{
 		.procname	= "bpf_jit_enable",
-- 
cgit v1.2.3-70-g09d2


From b9d1ab7eb42ede51ffbb6cafffd0a521b30c12e1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 16 Nov 2014 06:23:16 -0800
Subject: mlx4: use netdev_rss_key_fill() helper

Use of well known RSS key increases attack surface.
Switch to a random one, using generic helper so that all
ports share a common key.

Also provide ethtool -x support to fetch RSS key

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 9 ++++++++-
 drivers/net/ethernet/mellanox/mlx4/en_rx.c      | 6 +-----
 include/linux/mlx4/qp.h                         | 4 +++-
 3 files changed, 12 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 6c643230a5e..710cf309962 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -973,6 +973,11 @@ static u32 mlx4_en_get_rxfh_indir_size(struct net_device *dev)
 	return priv->rx_ring_num;
 }
 
+static u32 mlx4_en_get_rxfh_key_size(struct net_device *netdev)
+{
+	return MLX4_EN_RSS_KEY_SIZE;
+}
+
 static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -988,7 +993,8 @@ static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key)
 		ring_index[n] = rss_map->qps[n % rss_rings].qpn -
 			rss_map->base_qpn;
 	}
-
+	if (key)
+		netdev_rss_key_fill(key, MLX4_EN_RSS_KEY_SIZE);
 	return err;
 }
 
@@ -1799,6 +1805,7 @@ const struct ethtool_ops mlx4_en_ethtool_ops = {
 	.get_rxnfc = mlx4_en_get_rxnfc,
 	.set_rxnfc = mlx4_en_set_rxnfc,
 	.get_rxfh_indir_size = mlx4_en_get_rxfh_indir_size,
+	.get_rxfh_key_size = mlx4_en_get_rxfh_key_size,
 	.get_rxfh = mlx4_en_get_rxfh,
 	.set_rxfh = mlx4_en_set_rxfh,
 	.get_channels = mlx4_en_get_channels,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index ccd95177ea7..b7bda895601 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -1169,9 +1169,6 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 	int i, qpn;
 	int err = 0;
 	int good_qps = 0;
-	static const u32 rsskey[10] = { 0xD181C62C, 0xF7F4DB5B, 0x1983A2FC,
-				0x943E1ADB, 0xD9389E6B, 0xD1039C2C, 0xA74499AD,
-				0x593D56D9, 0xF3253C06, 0x2ADC1FFC};
 
 	en_dbg(DRV, priv, "Configuring rss steering\n");
 	err = mlx4_qp_reserve_range(mdev->dev, priv->rx_ring_num,
@@ -1226,8 +1223,7 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 
 	rss_context->flags = rss_mask;
 	rss_context->hash_fn = MLX4_RSS_HASH_TOP;
-	for (i = 0; i < 10; i++)
-		rss_context->rss_key[i] = cpu_to_be32(rsskey[i]);
+	netdev_rss_key_fill(rss_context->rss_key, MLX4_EN_RSS_KEY_SIZE);
 
 	err = mlx4_qp_to_ready(mdev->dev, &priv->res.mtt, &context,
 			       &rss_map->indir_qp, &rss_map->indir_state);
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 5f4e36cf009..467ccdf94c9 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -120,13 +120,15 @@ enum {
 	MLX4_RSS_QPC_FLAG_OFFSET		= 13,
 };
 
+#define MLX4_EN_RSS_KEY_SIZE 40
+
 struct mlx4_rss_context {
 	__be32			base_qpn;
 	__be32			default_qpn;
 	u16			reserved;
 	u8			hash_fn;
 	u8			flags;
-	__be32			rss_key[10];
+	__be32			rss_key[MLX4_EN_RSS_KEY_SIZE / sizeof(__be32)];
 	__be32			base_qpn_udp;
 };
 
-- 
cgit v1.2.3-70-g09d2


From 29aebfde8802b64a5b505a1d8a6842c188abfdbc Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicoleotsuka@gmail.com>
Date: Fri, 24 Oct 2014 12:37:41 -0700
Subject: dmaengine: imx-sdma: Add a new DMATYPE for SAI

This patch simply adds a new DMATYPE for SAI which's included
in i.MX6 Solo X.

Signed-off-by: Nicolin Chen <nicoleotsuka@gmail.com>
Acked-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt | 1 +
 drivers/dma/imx-sdma.c                                 | 1 +
 include/linux/platform_data/dma-imx.h                  | 1 +
 3 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt b/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
index 4659fd95230..dc8d3aac1aa 100644
--- a/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
+++ b/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
@@ -48,6 +48,7 @@ The full ID of peripheral types can be found below.
 	21	ESAI
 	22	SSI Dual FIFO	(needs firmware ver >= 2)
 	23	Shared ASRC
+	24	SAI
 
 The third cell specifies the transfer priority as below.
 
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 99d8833edbd..5b38f2bbd42 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -729,6 +729,7 @@ static void sdma_get_pc(struct sdma_channel *sdmac,
 	case IMX_DMATYPE_CSPI:
 	case IMX_DMATYPE_EXT:
 	case IMX_DMATYPE_SSI:
+	case IMX_DMATYPE_SAI:
 		per_2_emi = sdma->script_addrs->app_2_mcu_addr;
 		emi_2_per = sdma->script_addrs->mcu_2_app_addr;
 		break;
diff --git a/include/linux/platform_data/dma-imx.h b/include/linux/platform_data/dma-imx.h
index 6a1357d3187..7d964e78729 100644
--- a/include/linux/platform_data/dma-imx.h
+++ b/include/linux/platform_data/dma-imx.h
@@ -41,6 +41,7 @@ enum sdma_peripheral_type {
 	IMX_DMATYPE_ESAI,	/* ESAI */
 	IMX_DMATYPE_SSI_DUAL,	/* SSI Dual FIFO */
 	IMX_DMATYPE_ASRC_SP,	/* Shared ASRC */
+	IMX_DMATYPE_SAI,	/* SAI */
 };
 
 enum imx_dma_prio {
-- 
cgit v1.2.3-70-g09d2


From f3ea5e44231a88eaea69a13410d1b80c19cfa1df Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Mon, 17 Nov 2014 08:20:51 +0100
Subject: ieee802154: add new interface command

This patch adds a new nl802154 command for adding a new interface
according to a wpan phy via nl802154.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h   |  5 +++++
 net/ieee802154/nl802154.c | 34 ++++++++++++++++++++++++++++++++++
 net/ieee802154/rdev-ops.h |  7 +++++++
 net/mac802154/cfg.c       | 15 +++++++++++++++
 4 files changed, 61 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 17b4fc0705b..24c7321f364 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -21,6 +21,8 @@
 #include <linux/mutex.h>
 #include <linux/bug.h>
 
+#include <net/nl802154.h>
+
 /* According to the IEEE 802.15.4 stadard the upper most significant bits of
  * the 32-bit channel bitmaps shall be used as an integer value to specify 32
  * possible channel pages. The lower 27 bits of the channel bit map shall be
@@ -37,6 +39,9 @@ struct cfg802154_ops {
 							   int type);
 	void	(*del_virtual_intf_deprecated)(struct wpan_phy *wpan_phy,
 					       struct net_device *dev);
+	int	(*add_virtual_intf)(struct wpan_phy *wpan_phy,
+				    const char *name,
+				    enum nl802154_iftype type);
 	int	(*set_channel)(struct wpan_phy *wpan_phy, u8 page, u8 channel);
 	int	(*set_pan_id)(struct wpan_phy *wpan_phy,
 			      struct wpan_dev *wpan_dev, u16 pan_id);
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index ccdf33ecee0..e7224f3c158 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -551,6 +551,32 @@ static int nl802154_get_interface(struct sk_buff *skb, struct genl_info *info)
 	return genlmsg_reply(msg, info);
 }
 
+static int nl802154_new_interface(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	enum nl802154_iftype type = NL802154_IFTYPE_UNSPEC;
+
+	/* TODO avoid failing a new interface
+	 * creation due to pending removal?
+	 */
+
+	if (!info->attrs[NL802154_ATTR_IFNAME])
+		return -EINVAL;
+
+	if (info->attrs[NL802154_ATTR_IFTYPE]) {
+		type = nla_get_u32(info->attrs[NL802154_ATTR_IFTYPE]);
+		if (type > NL802154_IFTYPE_MAX)
+			return -EINVAL;
+	}
+
+	if (!rdev->ops->add_virtual_intf)
+		return -EOPNOTSUPP;
+
+	return rdev_add_virtual_intf(rdev,
+				     nla_data(info->attrs[NL802154_ATTR_IFNAME]),
+				     type);
+}
+
 static int nl802154_set_channel(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg802154_registered_device *rdev = info->user_ptr[0];
@@ -818,6 +844,14 @@ static const struct genl_ops nl802154_ops[] = {
 		.internal_flags = NL802154_FLAG_NEED_WPAN_DEV |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_NEW_INTERFACE,
+		.doit = nl802154_new_interface,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
+				  NL802154_FLAG_NEED_RTNL,
+	},
 	{
 		.cmd = NL802154_CMD_SET_CHANNEL,
 		.doit = nl802154_set_channel,
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index 578bc41e92d..d3a4f94c5fd 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -20,6 +20,13 @@ rdev_del_virtual_intf_deprecated(struct cfg802154_registered_device *rdev,
 	rdev->ops->del_virtual_intf_deprecated(&rdev->wpan_phy, dev);
 }
 
+static inline int
+rdev_add_virtual_intf(struct cfg802154_registered_device *rdev, char *name,
+		      enum nl802154_iftype type)
+{
+	return rdev->ops->add_virtual_intf(&rdev->wpan_phy, name, type);
+}
+
 static inline int
 rdev_set_channel(struct cfg802154_registered_device *rdev, u8 page, u8 channel)
 {
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index 2abe7e5f097..ae1a9ef2d42 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -42,6 +42,20 @@ static void ieee802154_del_iface_deprecated(struct wpan_phy *wpan_phy,
 	ieee802154_if_remove(sdata);
 }
 
+static int
+ieee802154_add_iface(struct wpan_phy *phy, const char *name,
+		     enum nl802154_iftype type)
+{
+	struct ieee802154_local *local = wpan_phy_priv(phy);
+	struct net_device *err;
+
+	err = ieee802154_if_add(local, name, type);
+	if (IS_ERR(err))
+		return PTR_ERR(err);
+
+	return 0;
+}
+
 static int
 ieee802154_set_channel(struct wpan_phy *wpan_phy, u8 page, u8 channel)
 {
@@ -175,6 +189,7 @@ ieee802154_set_lbt_mode(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
 const struct cfg802154_ops mac802154_config_ops = {
 	.add_virtual_intf_deprecated = ieee802154_add_iface_deprecated,
 	.del_virtual_intf_deprecated = ieee802154_del_iface_deprecated,
+	.add_virtual_intf = ieee802154_add_iface,
 	.set_channel = ieee802154_set_channel,
 	.set_pan_id = ieee802154_set_pan_id,
 	.set_short_addr = ieee802154_set_short_addr,
-- 
cgit v1.2.3-70-g09d2


From 0e57547eb7f0aa99aba32b50c49dbd722a80d6fb Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Mon, 17 Nov 2014 08:20:52 +0100
Subject: ieee802154: setting extended address while iface add

This patch adds support for setting an extended address while
registration a new interface. If ieee802154_is_valid_extended_addr
getting as parameter and invalid extended address then the perm address
is fallback. This is useful to make some default handling while for
example default registration of a wpan interface while phy registration.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h      |  3 ++-
 net/ieee802154/nl802154.c    |  8 +++++++-
 net/ieee802154/rdev-ops.h    |  5 +++--
 net/mac802154/cfg.c          |  7 ++++---
 net/mac802154/ieee802154_i.h |  2 +-
 net/mac802154/iface.c        | 12 ++++++++----
 net/mac802154/main.c         |  3 ++-
 7 files changed, 27 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 24c7321f364..4a9bb0e3db2 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -41,7 +41,8 @@ struct cfg802154_ops {
 					       struct net_device *dev);
 	int	(*add_virtual_intf)(struct wpan_phy *wpan_phy,
 				    const char *name,
-				    enum nl802154_iftype type);
+				    enum nl802154_iftype type,
+				    __le64 extended_addr);
 	int	(*set_channel)(struct wpan_phy *wpan_phy, u8 page, u8 channel);
 	int	(*set_pan_id)(struct wpan_phy *wpan_phy,
 			      struct wpan_dev *wpan_dev, u16 pan_id);
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index e7224f3c158..49c4d8a5004 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -555,6 +555,7 @@ static int nl802154_new_interface(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg802154_registered_device *rdev = info->user_ptr[0];
 	enum nl802154_iftype type = NL802154_IFTYPE_UNSPEC;
+	__le64 extended_addr = cpu_to_le64(0x0000000000000000ULL);
 
 	/* TODO avoid failing a new interface
 	 * creation due to pending removal?
@@ -569,12 +570,17 @@ static int nl802154_new_interface(struct sk_buff *skb, struct genl_info *info)
 			return -EINVAL;
 	}
 
+	/* TODO add nla_get_le64 to netlink */
+	if (info->attrs[NL802154_ATTR_EXTENDED_ADDR])
+		extended_addr = (__force __le64)nla_get_u64(
+				info->attrs[NL802154_ATTR_EXTENDED_ADDR]);
+
 	if (!rdev->ops->add_virtual_intf)
 		return -EOPNOTSUPP;
 
 	return rdev_add_virtual_intf(rdev,
 				     nla_data(info->attrs[NL802154_ATTR_IFNAME]),
-				     type);
+				     type, extended_addr);
 }
 
 static int nl802154_set_channel(struct sk_buff *skb, struct genl_info *info)
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index d3a4f94c5fd..06e97542daf 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -22,9 +22,10 @@ rdev_del_virtual_intf_deprecated(struct cfg802154_registered_device *rdev,
 
 static inline int
 rdev_add_virtual_intf(struct cfg802154_registered_device *rdev, char *name,
-		      enum nl802154_iftype type)
+		      enum nl802154_iftype type, __le64 extended_addr)
 {
-	return rdev->ops->add_virtual_intf(&rdev->wpan_phy, name, type);
+	return rdev->ops->add_virtual_intf(&rdev->wpan_phy, name, type,
+					   extended_addr);
 }
 
 static inline int
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index ae1a9ef2d42..568d712bfc8 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -28,7 +28,8 @@ ieee802154_add_iface_deprecated(struct wpan_phy *wpan_phy,
 	struct net_device *dev;
 
 	rtnl_lock();
-	dev = ieee802154_if_add(local, name, type);
+	dev = ieee802154_if_add(local, name, type,
+				cpu_to_le64(0x0000000000000000ULL));
 	rtnl_unlock();
 
 	return dev;
@@ -44,12 +45,12 @@ static void ieee802154_del_iface_deprecated(struct wpan_phy *wpan_phy,
 
 static int
 ieee802154_add_iface(struct wpan_phy *phy, const char *name,
-		     enum nl802154_iftype type)
+		     enum nl802154_iftype type, __le64 extended_addr)
 {
 	struct ieee802154_local *local = wpan_phy_priv(phy);
 	struct net_device *err;
 
-	err = ieee802154_if_add(local, name, type);
+	err = ieee802154_if_add(local, name, type, extended_addr);
 	if (IS_ERR(err))
 		return PTR_ERR(err);
 
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index 46553830896..cc691637d24 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -176,7 +176,7 @@ void ieee802154_iface_exit(void);
 void ieee802154_if_remove(struct ieee802154_sub_if_data *sdata);
 struct net_device *
 ieee802154_if_add(struct ieee802154_local *local, const char *name,
-		  enum nl802154_iftype type);
+		  enum nl802154_iftype type, __le64 extended_addr);
 void ieee802154_remove_interfaces(struct ieee802154_local *local);
 
 #endif /* __IEEE802154_I_H */
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index ba63ac93ae9..38dfc72d24b 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -458,7 +458,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata,
 
 struct net_device *
 ieee802154_if_add(struct ieee802154_local *local, const char *name,
-		  enum nl802154_iftype type)
+		  enum nl802154_iftype type, __le64 extended_addr)
 {
 	struct net_device *ndev = NULL;
 	struct ieee802154_sub_if_data *sdata = NULL;
@@ -477,9 +477,16 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name,
 	if (ret < 0)
 		goto err;
 
+	ieee802154_le64_to_be64(ndev->perm_addr,
+				&local->hw.phy->perm_extended_addr);
 	switch (type) {
 	case NL802154_IFTYPE_NODE:
 		ndev->type = ARPHRD_IEEE802154;
+		if (ieee802154_is_valid_extended_addr(extended_addr))
+			ieee802154_le64_to_be64(ndev->dev_addr, &extended_addr);
+		else
+			memcpy(ndev->dev_addr, ndev->perm_addr,
+			       IEEE802154_EXTENDED_ADDR_LEN);
 		break;
 	case NL802154_IFTYPE_MONITOR:
 		ndev->type = ARPHRD_IEEE802154_MONITOR;
@@ -489,9 +496,6 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name,
 		goto err;
 	}
 
-	ieee802154_le64_to_be64(ndev->perm_addr,
-				&local->hw.phy->perm_extended_addr);
-	memcpy(ndev->dev_addr, ndev->perm_addr, IEEE802154_EXTENDED_ADDR_LEN);
 	/* TODO check this */
 	SET_NETDEV_DEV(ndev, &local->phy->dev);
 	sdata = netdev_priv(ndev);
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index bbb19dd585a..8500378c831 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -161,7 +161,8 @@ int ieee802154_register_hw(struct ieee802154_hw *hw)
 
 	rtnl_lock();
 
-	dev = ieee802154_if_add(local, "wpan%d", NL802154_IFTYPE_NODE);
+	dev = ieee802154_if_add(local, "wpan%d", NL802154_IFTYPE_NODE,
+				cpu_to_le64(0x0000000000000000ULL));
 	if (IS_ERR(dev)) {
 		rtnl_unlock();
 		rc = PTR_ERR(dev);
-- 
cgit v1.2.3-70-g09d2


From b821ecd4c8a0b3b1fc1bdd191bb7d555d818cafe Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Mon, 17 Nov 2014 08:20:53 +0100
Subject: ieee802154: add del interface command

This patch adds support for deleting a wpan interface via nl802154.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h      |  2 ++
 net/ieee802154/nl802154.c    | 28 ++++++++++++++++++++++++++++
 net/ieee802154/rdev-ops.h    |  7 +++++++
 net/mac802154/cfg.c          |  9 +++++++++
 net/mac802154/ieee802154_i.h |  6 ++++++
 5 files changed, 52 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 4a9bb0e3db2..507ac9d3d38 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -43,6 +43,8 @@ struct cfg802154_ops {
 				    const char *name,
 				    enum nl802154_iftype type,
 				    __le64 extended_addr);
+	int	(*del_virtual_intf)(struct wpan_phy *wpan_phy,
+				    struct wpan_dev *wpan_dev);
 	int	(*set_channel)(struct wpan_phy *wpan_phy, u8 page, u8 channel);
 	int	(*set_pan_id)(struct wpan_phy *wpan_phy,
 			      struct wpan_dev *wpan_dev, u16 pan_id);
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 49c4d8a5004..6b9bc93944a 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -583,6 +583,26 @@ static int nl802154_new_interface(struct sk_buff *skb, struct genl_info *info)
 				     type, extended_addr);
 }
 
+static int nl802154_del_interface(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct wpan_dev *wpan_dev = info->user_ptr[1];
+
+	if (!rdev->ops->del_virtual_intf)
+		return -EOPNOTSUPP;
+
+	/* If we remove a wpan device without a netdev then clear
+	 * user_ptr[1] so that nl802154_post_doit won't dereference it
+	 * to check if it needs to do dev_put(). Otherwise it crashes
+	 * since the wpan_dev has been freed, unlike with a netdev where
+	 * we need the dev_put() for the netdev to really be freed.
+	 */
+	if (!wpan_dev->netdev)
+		info->user_ptr[1] = NULL;
+
+	return rdev_del_virtual_intf(rdev, wpan_dev);
+}
+
 static int nl802154_set_channel(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg802154_registered_device *rdev = info->user_ptr[0];
@@ -858,6 +878,14 @@ static const struct genl_ops nl802154_ops[] = {
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_DEL_INTERFACE,
+		.doit = nl802154_del_interface,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_WPAN_DEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
 	{
 		.cmd = NL802154_CMD_SET_CHANNEL,
 		.doit = nl802154_set_channel,
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index 06e97542daf..40ffbc0d8b8 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -28,6 +28,13 @@ rdev_add_virtual_intf(struct cfg802154_registered_device *rdev, char *name,
 					   extended_addr);
 }
 
+static inline int
+rdev_del_virtual_intf(struct cfg802154_registered_device *rdev,
+		      struct wpan_dev *wpan_dev)
+{
+	return rdev->ops->del_virtual_intf(&rdev->wpan_phy, wpan_dev);
+}
+
 static inline int
 rdev_set_channel(struct cfg802154_registered_device *rdev, u8 page, u8 channel)
 {
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index 568d712bfc8..7def2625eac 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -57,6 +57,14 @@ ieee802154_add_iface(struct wpan_phy *phy, const char *name,
 	return 0;
 }
 
+static int
+ieee802154_del_iface(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev)
+{
+	ieee802154_if_remove(IEEE802154_WPAN_DEV_TO_SUB_IF(wpan_dev));
+
+	return 0;
+}
+
 static int
 ieee802154_set_channel(struct wpan_phy *wpan_phy, u8 page, u8 channel)
 {
@@ -191,6 +199,7 @@ const struct cfg802154_ops mac802154_config_ops = {
 	.add_virtual_intf_deprecated = ieee802154_add_iface_deprecated,
 	.del_virtual_intf_deprecated = ieee802154_del_iface_deprecated,
 	.add_virtual_intf = ieee802154_add_iface,
+	.del_virtual_intf = ieee802154_del_iface,
 	.set_channel = ieee802154_set_channel,
 	.set_pan_id = ieee802154_set_pan_id,
 	.set_short_addr = ieee802154_set_short_addr,
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index cc691637d24..bebd70ffc7a 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -115,6 +115,12 @@ IEEE802154_DEV_TO_SUB_IF(const struct net_device *dev)
 	return netdev_priv(dev);
 }
 
+static inline struct ieee802154_sub_if_data *
+IEEE802154_WPAN_DEV_TO_SUB_IF(struct wpan_dev *wpan_dev)
+{
+	return container_of(wpan_dev, struct ieee802154_sub_if_data, wpan_dev);
+}
+
 static inline bool
 ieee802154_sdata_running(struct ieee802154_sub_if_data *sdata)
 {
-- 
cgit v1.2.3-70-g09d2


From cb41c8dd01d74d091618f72e28f0282f064a9f0a Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Mon, 17 Nov 2014 08:20:54 +0100
Subject: ieee802154: rename and move WPAN_NUM_ defines

This patch moves the 802.15.4 constraints WPAN_NUM_ defines into
"net/ieee802154.h" which should contain all necessary 802.15.4 related
information. Also rename these defines to a common name which is
IEEE802154_MAX_CHANNEL and IEEE802154_MAX_PAGE.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/ieee802154.h |  3 +++
 include/net/cfg802154.h    | 11 ++---------
 net/ieee802154/nl802154.c  |  4 ++--
 3 files changed, 7 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index 5a40c041843..6e82d888287 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -39,6 +39,9 @@
 #define IEEE802154_LIFS_PERIOD		40
 #define IEEE802154_SIFS_PERIOD		12
 
+#define IEEE802154_MAX_CHANNEL		26
+#define IEEE802154_MAX_PAGE		31
+
 #define IEEE802154_FC_TYPE_BEACON	0x0	/* Frame is beacon */
 #define	IEEE802154_FC_TYPE_DATA		0x1	/* Frame is data */
 #define IEEE802154_FC_TYPE_ACK		0x2	/* Frame is acknowledgment */
diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 507ac9d3d38..228f1f7668f 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -17,20 +17,13 @@
 #ifndef __NET_CFG802154_H
 #define __NET_CFG802154_H
 
+#include <linux/ieee802154.h>
 #include <linux/netdevice.h>
 #include <linux/mutex.h>
 #include <linux/bug.h>
 
 #include <net/nl802154.h>
 
-/* According to the IEEE 802.15.4 stadard the upper most significant bits of
- * the 32-bit channel bitmaps shall be used as an integer value to specify 32
- * possible channel pages. The lower 27 bits of the channel bit map shall be
- * used as a bit mask to specify channel numbers within a channel page.
- */
-#define WPAN_NUM_CHANNELS	27
-#define WPAN_NUM_PAGES		32
-
 struct wpan_phy;
 
 struct cfg802154_ops {
@@ -81,7 +74,7 @@ struct wpan_phy {
 	 */
 	u8 current_channel;
 	u8 current_page;
-	u32 channels_supported[32];
+	u32 channels_supported[IEEE802154_MAX_PAGE + 1];
 	s8 transmit_power;
 	u8 cca_mode;
 
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 6b9bc93944a..b82b01669a6 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -245,7 +245,7 @@ nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev,
 	if (!nl_page)
 		return -ENOBUFS;
 
-	for (page = 0; page < WPAN_NUM_PAGES; page++) {
+	for (page = 0; page <= IEEE802154_MAX_PAGE; page++) {
 		if (nla_put_u32(msg, NL802154_ATTR_SUPPORTED_CHANNEL,
 				rdev->wpan_phy.channels_supported[page]))
 			return -ENOBUFS;
@@ -616,7 +616,7 @@ static int nl802154_set_channel(struct sk_buff *skb, struct genl_info *info)
 	channel = nla_get_u8(info->attrs[NL802154_ATTR_CHANNEL]);
 
 	/* check 802.15.4 constraints */
-	if (page >= WPAN_NUM_PAGES || channel >= WPAN_NUM_CHANNELS)
+	if (page > IEEE802154_MAX_PAGE || channel > IEEE802154_MAX_CHANNEL)
 		return -EINVAL;
 
 	return rdev_set_channel(rdev, page, channel);
-- 
cgit v1.2.3-70-g09d2


From ee7b9053bd69ff43cbc87a9bb987f4d92dc2c29f Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Mon, 17 Nov 2014 08:20:55 +0100
Subject: ieee802154: fix byteorder for short address and panid

This patch changes the byteorder handling for short and panid handling.
We now except to get little endian in nl802154 for these attributes.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h   |  4 ++--
 net/ieee802154/nl802154.c |  8 ++++----
 net/ieee802154/rdev-ops.h |  4 ++--
 net/mac802154/cfg.c       | 14 +++++++-------
 4 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 228f1f7668f..7f713acfa10 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -40,9 +40,9 @@ struct cfg802154_ops {
 				    struct wpan_dev *wpan_dev);
 	int	(*set_channel)(struct wpan_phy *wpan_phy, u8 page, u8 channel);
 	int	(*set_pan_id)(struct wpan_phy *wpan_phy,
-			      struct wpan_dev *wpan_dev, u16 pan_id);
+			      struct wpan_dev *wpan_dev, __le16 pan_id);
 	int	(*set_short_addr)(struct wpan_phy *wpan_phy,
-				  struct wpan_dev *wpan_dev, u16 short_addr);
+				  struct wpan_dev *wpan_dev, __le16 short_addr);
 	int	(*set_backoff_exponent)(struct wpan_phy *wpan_phy,
 					struct wpan_dev *wpan_dev, u8 min_be,
 					u8 max_be);
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index b82b01669a6..88964774469 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -627,7 +627,7 @@ static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info)
 	struct cfg802154_registered_device *rdev = info->user_ptr[0];
 	struct net_device *dev = info->user_ptr[1];
 	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
-	u16 pan_id;
+	__le16 pan_id;
 
 	/* conflict here while tx/rx calls */
 	if (netif_running(dev))
@@ -640,7 +640,7 @@ static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[NL802154_ATTR_PAN_ID])
 		return -EINVAL;
 
-	pan_id = nla_get_u16(info->attrs[NL802154_ATTR_PAN_ID]);
+	pan_id = nla_get_le16(info->attrs[NL802154_ATTR_PAN_ID]);
 
 	return rdev_set_pan_id(rdev, wpan_dev, pan_id);
 }
@@ -650,7 +650,7 @@ static int nl802154_set_short_addr(struct sk_buff *skb, struct genl_info *info)
 	struct cfg802154_registered_device *rdev = info->user_ptr[0];
 	struct net_device *dev = info->user_ptr[1];
 	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
-	u16 short_addr;
+	__le16 short_addr;
 
 	/* conflict here while tx/rx calls */
 	if (netif_running(dev))
@@ -663,7 +663,7 @@ static int nl802154_set_short_addr(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[NL802154_ATTR_SHORT_ADDR])
 		return -EINVAL;
 
-	short_addr = nla_get_u16(info->attrs[NL802154_ATTR_SHORT_ADDR]);
+	short_addr = nla_get_le16(info->attrs[NL802154_ATTR_SHORT_ADDR]);
 
 	return rdev_set_short_addr(rdev, wpan_dev, short_addr);
 }
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index 40ffbc0d8b8..aff54fbd926 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -43,14 +43,14 @@ rdev_set_channel(struct cfg802154_registered_device *rdev, u8 page, u8 channel)
 
 static inline int
 rdev_set_pan_id(struct cfg802154_registered_device *rdev,
-		struct wpan_dev *wpan_dev, u16 pan_id)
+		struct wpan_dev *wpan_dev, __le16 pan_id)
 {
 	return rdev->ops->set_pan_id(&rdev->wpan_phy, wpan_dev, pan_id);
 }
 
 static inline int
 rdev_set_short_addr(struct cfg802154_registered_device *rdev,
-		    struct wpan_dev *wpan_dev, u16 short_addr)
+		    struct wpan_dev *wpan_dev, __le16 short_addr)
 {
 	return rdev->ops->set_short_addr(&rdev->wpan_phy, wpan_dev, short_addr);
 }
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index 7def2625eac..c035708ada1 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -88,7 +88,7 @@ ieee802154_set_channel(struct wpan_phy *wpan_phy, u8 page, u8 channel)
 
 static int
 ieee802154_set_pan_id(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
-		      u16 pan_id)
+		      __le16 pan_id)
 {
 	ASSERT_RTNL();
 
@@ -99,10 +99,10 @@ ieee802154_set_pan_id(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
 	 *
 	 * This could useful to simple deassociate an device.
 	 */
-	if (pan_id == IEEE802154_PAN_ID_BROADCAST)
+	if (pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST))
 		return -EINVAL;
 
-	wpan_dev->pan_id = cpu_to_le16(pan_id);
+	wpan_dev->pan_id = pan_id;
 	return 0;
 }
 
@@ -125,7 +125,7 @@ ieee802154_set_backoff_exponent(struct wpan_phy *wpan_phy,
 
 static int
 ieee802154_set_short_addr(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
-			  u16 short_addr)
+			  __le16 short_addr)
 {
 	ASSERT_RTNL();
 
@@ -140,11 +140,11 @@ ieee802154_set_short_addr(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
 	 * I think we should allow to set these settings but
 	 * don't allow to allow socket communication with it.
 	 */
-	if (short_addr == IEEE802154_ADDR_SHORT_UNSPEC ||
-	    short_addr == IEEE802154_ADDR_SHORT_BROADCAST)
+	if (short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC) ||
+	    short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST))
 		return -EINVAL;
 
-	wpan_dev->short_addr = cpu_to_le16(short_addr);
+	wpan_dev->short_addr = short_addr;
 	return 0;
 }
 
-- 
cgit v1.2.3-70-g09d2


From fb7332a9fedfd62b1ba6530c86f39f0fa38afd49 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Wed, 29 Oct 2014 10:03:09 +0000
Subject: mmu_gather: move minimal range calculations into generic code

On architectures with hardware broadcasting of TLB invalidation messages
, it makes sense to reduce the range of the mmu_gather structure when
unmapping page ranges based on the dirty address information passed to
tlb_remove_tlb_entry.

arm64 already does this by directly manipulating the start/end fields
of the gather structure, but this confuses the generic code which
does not expect these fields to change and can end up calculating
invalid, negative ranges when forcing a flush in zap_pte_range.

This patch moves the minimal range calculation out of the arm64 code
and into the generic implementation, simplifying zap_pte_range in the
process (which no longer needs to care about start/end, since they will
point to the appropriate ranges already). With the range being tracked
by core code, the need_flush flag is dropped in favour of checking that
the end of the range has actually been set.

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King - ARM Linux <linux@arm.linux.org.uk>
Cc: Michal Simek <monstr@monstr.eu>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/tlb.h       | 67 ++------------------------------------
 arch/microblaze/include/asm/tlb.h  |  3 +-
 arch/powerpc/include/asm/pgalloc.h |  3 +-
 arch/powerpc/include/asm/tlb.h     |  1 +
 arch/powerpc/mm/hugetlbpage.c      |  2 --
 include/asm-generic/tlb.h          | 57 ++++++++++++++++++++++++++------
 mm/memory.c                        | 30 +++++------------
 7 files changed, 63 insertions(+), 100 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index a82c0c5c8b5..c028fe37456 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -19,10 +19,6 @@
 #ifndef __ASM_TLB_H
 #define __ASM_TLB_H
 
-#define  __tlb_remove_pmd_tlb_entry __tlb_remove_pmd_tlb_entry
-
-#include <asm-generic/tlb.h>
-
 #include <linux/pagemap.h>
 #include <linux/swap.h>
 
@@ -37,71 +33,22 @@ static inline void __tlb_remove_table(void *_table)
 #define tlb_remove_entry(tlb, entry)	tlb_remove_page(tlb, entry)
 #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 
-/*
- * There's three ways the TLB shootdown code is used:
- *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
- *     tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
- *  2. Unmapping all vmas.  See exit_mmap().
- *     tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
- *     Page tables will be freed.
- *  3. Unmapping argument pages.  See shift_arg_pages().
- *     tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
- */
+#include <asm-generic/tlb.h>
+
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 	if (tlb->fullmm) {
 		flush_tlb_mm(tlb->mm);
-	} else if (tlb->end > 0) {
+	} else {
 		struct vm_area_struct vma = { .vm_mm = tlb->mm, };
 		flush_tlb_range(&vma, tlb->start, tlb->end);
-		tlb->start = TASK_SIZE;
-		tlb->end = 0;
-	}
-}
-
-static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
-{
-	if (!tlb->fullmm) {
-		tlb->start = min(tlb->start, addr);
-		tlb->end = max(tlb->end, addr + PAGE_SIZE);
-	}
-}
-
-/*
- * Memorize the range for the TLB flush.
- */
-static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
-					  unsigned long addr)
-{
-	tlb_add_flush(tlb, addr);
-}
-
-/*
- * In the case of tlb vma handling, we can optimise these away in the
- * case where we're doing a full MM flush.  When we're doing a munmap,
- * the vmas are adjusted to only cover the region to be torn down.
- */
-static inline void tlb_start_vma(struct mmu_gather *tlb,
-				 struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm) {
-		tlb->start = TASK_SIZE;
-		tlb->end = 0;
 	}
 }
 
-static inline void tlb_end_vma(struct mmu_gather *tlb,
-			       struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm)
-		tlb_flush(tlb);
-}
-
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				  unsigned long addr)
 {
 	pgtable_page_dtor(pte);
-	tlb_add_flush(tlb, addr);
 	tlb_remove_entry(tlb, pte);
 }
 
@@ -109,7 +56,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
-	tlb_add_flush(tlb, addr);
 	tlb_remove_entry(tlb, virt_to_page(pmdp));
 }
 #endif
@@ -118,15 +64,8 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 				  unsigned long addr)
 {
-	tlb_add_flush(tlb, addr);
 	tlb_remove_entry(tlb, virt_to_page(pudp));
 }
 #endif
 
-static inline void __tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp,
-						unsigned long address)
-{
-	tlb_add_flush(tlb, address);
-}
-
 #endif
diff --git a/arch/microblaze/include/asm/tlb.h b/arch/microblaze/include/asm/tlb.h
index 8aa97817cc8..99b6ded5484 100644
--- a/arch/microblaze/include/asm/tlb.h
+++ b/arch/microblaze/include/asm/tlb.h
@@ -14,7 +14,6 @@
 #define tlb_flush(tlb)	flush_tlb_mm((tlb)->mm)
 
 #include <linux/pagemap.h>
-#include <asm-generic/tlb.h>
 
 #ifdef CONFIG_MMU
 #define tlb_start_vma(tlb, vma)		do { } while (0)
@@ -22,4 +21,6 @@
 #define __tlb_remove_tlb_entry(tlb, pte, address) do { } while (0)
 #endif
 
+#include <asm-generic/tlb.h>
+
 #endif /* _ASM_MICROBLAZE_TLB_H */
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index e9a9f60e596..fc3ee06eab8 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -3,7 +3,6 @@
 #ifdef __KERNEL__
 
 #include <linux/mm.h>
-#include <asm-generic/tlb.h>
 
 #ifdef CONFIG_PPC_BOOK3E
 extern void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address);
@@ -14,6 +13,8 @@ static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
 }
 #endif /* !CONFIG_PPC_BOOK3E */
 
+extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
+
 #ifdef CONFIG_PPC64
 #include <asm/pgalloc-64.h>
 #else
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index e2b428b0f7b..20733fa518a 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -27,6 +27,7 @@
 
 #define tlb_start_vma(tlb, vma)	do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
+#define __tlb_remove_tlb_entry	__tlb_remove_tlb_entry
 
 extern void tlb_flush(struct mmu_gather *tlb);
 
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 7e70ae968e5..6a4a5fcb973 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -517,8 +517,6 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
 	for (i = 0; i < num_hugepd; i++, hpdp++)
 		hpdp->pd = 0;
 
-	tlb->need_flush = 1;
-
 #ifdef CONFIG_PPC_FSL_BOOK3E
 	hugepd_free(tlb, hugepte);
 #else
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 5672d7ea1fa..08848050922 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -96,10 +96,9 @@ struct mmu_gather {
 #endif
 	unsigned long		start;
 	unsigned long		end;
-	unsigned int		need_flush : 1,	/* Did free PTEs */
 	/* we are in the middle of an operation to clear
 	 * a full mm and can make some optimizations */
-				fullmm : 1,
+	unsigned int		fullmm : 1,
 	/* we have performed an operation which
 	 * requires a complete flush of the tlb */
 				need_flush_all : 1;
@@ -128,16 +127,54 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 		tlb_flush_mmu(tlb);
 }
 
+static inline void __tlb_adjust_range(struct mmu_gather *tlb,
+				      unsigned long address)
+{
+	tlb->start = min(tlb->start, address);
+	tlb->end = max(tlb->end, address + PAGE_SIZE);
+}
+
+static inline void __tlb_reset_range(struct mmu_gather *tlb)
+{
+	tlb->start = TASK_SIZE;
+	tlb->end = 0;
+}
+
+/*
+ * In the case of tlb vma handling, we can optimise these away in the
+ * case where we're doing a full MM flush.  When we're doing a munmap,
+ * the vmas are adjusted to only cover the region to be torn down.
+ */
+#ifndef tlb_start_vma
+#define tlb_start_vma(tlb, vma) do { } while (0)
+#endif
+
+#define __tlb_end_vma(tlb, vma)					\
+	do {							\
+		if (!tlb->fullmm && tlb->end) {			\
+			tlb_flush(tlb);				\
+			__tlb_reset_range(tlb);			\
+		}						\
+	} while (0)
+
+#ifndef tlb_end_vma
+#define tlb_end_vma	__tlb_end_vma
+#endif
+
+#ifndef __tlb_remove_tlb_entry
+#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
+#endif
+
 /**
  * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
  *
- * Record the fact that pte's were really umapped in ->need_flush, so we can
- * later optimise away the tlb invalidate.   This helps when userspace is
- * unmapping already-unmapped pages, which happens quite a lot.
+ * Record the fact that pte's were really unmapped by updating the range,
+ * so we can later optimise away the tlb invalidate.   This helps when
+ * userspace is unmapping already-unmapped pages, which happens quite a lot.
  */
 #define tlb_remove_tlb_entry(tlb, ptep, address)		\
 	do {							\
-		tlb->need_flush = 1;				\
+		__tlb_adjust_range(tlb, address);		\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
@@ -151,27 +188,27 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 
 #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address)		\
 	do {							\
-		tlb->need_flush = 1;				\
+		__tlb_adjust_range(tlb, address);		\
 		__tlb_remove_pmd_tlb_entry(tlb, pmdp, address);	\
 	} while (0)
 
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
-		tlb->need_flush = 1;				\
+		__tlb_adjust_range(tlb, address);		\
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
 
 #ifndef __ARCH_HAS_4LEVEL_HACK
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
-		tlb->need_flush = 1;				\
+		__tlb_adjust_range(tlb, address);		\
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
 
 #define pmd_free_tlb(tlb, pmdp, address)			\
 	do {							\
-		tlb->need_flush = 1;				\
+		__tlb_adjust_range(tlb, address);		\
 		__pmd_free_tlb(tlb, pmdp, address);		\
 	} while (0)
 
diff --git a/mm/memory.c b/mm/memory.c
index 1cc6bfbd872..c71edae9ba4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -220,9 +220,6 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long
 	/* Is it from 0 to ~0? */
 	tlb->fullmm     = !(start | (end+1));
 	tlb->need_flush_all = 0;
-	tlb->start	= start;
-	tlb->end	= end;
-	tlb->need_flush = 0;
 	tlb->local.next = NULL;
 	tlb->local.nr   = 0;
 	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
@@ -232,15 +229,20 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb->batch = NULL;
 #endif
+
+	__tlb_reset_range(tlb);
 }
 
 static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
-	tlb->need_flush = 0;
+	if (!tlb->end)
+		return;
+
 	tlb_flush(tlb);
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb_table_flush(tlb);
 #endif
+	__tlb_reset_range(tlb);
 }
 
 static void tlb_flush_mmu_free(struct mmu_gather *tlb)
@@ -256,8 +258,6 @@ static void tlb_flush_mmu_free(struct mmu_gather *tlb)
 
 void tlb_flush_mmu(struct mmu_gather *tlb)
 {
-	if (!tlb->need_flush)
-		return;
 	tlb_flush_mmu_tlbonly(tlb);
 	tlb_flush_mmu_free(tlb);
 }
@@ -292,7 +292,7 @@ int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
 	struct mmu_gather_batch *batch;
 
-	VM_BUG_ON(!tlb->need_flush);
+	VM_BUG_ON(!tlb->end);
 
 	batch = tlb->active;
 	batch->pages[batch->nr++] = page;
@@ -359,8 +359,6 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 {
 	struct mmu_table_batch **batch = &tlb->batch;
 
-	tlb->need_flush = 1;
-
 	/*
 	 * When there's less then two users of this mm there cannot be a
 	 * concurrent page-table walk.
@@ -1185,20 +1183,8 @@ again:
 	arch_leave_lazy_mmu_mode();
 
 	/* Do the actual TLB flush before dropping ptl */
-	if (force_flush) {
-		unsigned long old_end;
-
-		/*
-		 * Flush the TLB just for the previous segment,
-		 * then update the range to be the remaining
-		 * TLB range.
-		 */
-		old_end = tlb->end;
-		tlb->end = addr;
+	if (force_flush)
 		tlb_flush_mmu_tlbonly(tlb);
-		tlb->start = addr;
-		tlb->end = old_end;
-	}
 	pte_unmap_unlock(start_pte, ptl);
 
 	/*
-- 
cgit v1.2.3-70-g09d2


From 48b6bca6b7b8309697fc8a101793befe92d249d9 Mon Sep 17 00:00:00 2001
From: Benjamin Marzinski <bmarzins@redhat.com>
Date: Thu, 13 Nov 2014 20:42:03 -0600
Subject: fs: add freeze_super/thaw_super fs hooks

Currently, freezing a filesystem involves calling freeze_super, which locks
sb->s_umount and then calls the fs-specific freeze_fs hook. This makes it
hard for gfs2 (and potentially other cluster filesystems) to use the vfs
freezing code to do freezes on all the cluster nodes.

In order to communicate that a freeze has been requested, and to make sure
that only one node is trying to freeze at a time, gfs2 uses a glock
(sd_freeze_gl). The problem is that there is no hook for gfs2 to acquire
this lock before calling freeze_super. This means that two nodes can
attempt to freeze the filesystem by both calling freeze_super, acquiring
the sb->s_umount lock, and then attempting to grab the cluster glock
sd_freeze_gl. Only one will succeed, and the other will be stuck in
freeze_super, making it impossible to finish freezing the node.

To solve this problem, this patch adds the freeze_super and thaw_super
hooks.  If a filesystem implements these hooks, they are called instead of
the vfs freeze_super and thaw_super functions. This means that every
filesystem that implements these hooks must call the vfs freeze_super and
thaw_super functions itself within the hook function to make use of the vfs
freezing code.

Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
---
 fs/block_dev.c     | 10 ++++++++--
 fs/ioctl.c         |  6 +++++-
 include/linux/fs.h |  2 ++
 3 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1d9c9f3754f..b48c41bf0f8 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -235,7 +235,10 @@ struct super_block *freeze_bdev(struct block_device *bdev)
 	sb = get_active_super(bdev);
 	if (!sb)
 		goto out;
-	error = freeze_super(sb);
+	if (sb->s_op->freeze_super)
+		error = sb->s_op->freeze_super(sb);
+	else
+		error = freeze_super(sb);
 	if (error) {
 		deactivate_super(sb);
 		bdev->bd_fsfreeze_count--;
@@ -272,7 +275,10 @@ int thaw_bdev(struct block_device *bdev, struct super_block *sb)
 	if (!sb)
 		goto out;
 
-	error = thaw_super(sb);
+	if (sb->s_op->thaw_super)
+		error = sb->s_op->thaw_super(sb);
+	else
+		error = thaw_super(sb);
 	if (error) {
 		bdev->bd_fsfreeze_count++;
 		mutex_unlock(&bdev->bd_fsfreeze_mutex);
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 8ac3fad3619..77c9a781254 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -518,10 +518,12 @@ static int ioctl_fsfreeze(struct file *filp)
 		return -EPERM;
 
 	/* If filesystem doesn't support freeze feature, return. */
-	if (sb->s_op->freeze_fs == NULL)
+	if (sb->s_op->freeze_fs == NULL && sb->s_op->freeze_super == NULL)
 		return -EOPNOTSUPP;
 
 	/* Freeze */
+	if (sb->s_op->freeze_super)
+		return sb->s_op->freeze_super(sb);
 	return freeze_super(sb);
 }
 
@@ -533,6 +535,8 @@ static int ioctl_fsthaw(struct file *filp)
 		return -EPERM;
 
 	/* Thaw */
+	if (sb->s_op->thaw_super)
+		return sb->s_op->thaw_super(sb);
 	return thaw_super(sb);
 }
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9ab779e8a63..b4a1d73c0d5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1577,7 +1577,9 @@ struct super_operations {
 	void (*evict_inode) (struct inode *);
 	void (*put_super) (struct super_block *);
 	int (*sync_fs)(struct super_block *sb, int wait);
+	int (*freeze_super) (struct super_block *);
 	int (*freeze_fs) (struct super_block *);
+	int (*thaw_super) (struct super_block *);
 	int (*unfreeze_fs) (struct super_block *);
 	int (*statfs) (struct dentry *, struct kstatfs *);
 	int (*remount_fs) (struct super_block *, int *, char *);
-- 
cgit v1.2.3-70-g09d2


From 52744af3af977ccbbf768be34650d7c75cfc1ad6 Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Fri, 14 Nov 2014 05:26:21 +0100
Subject: crypto: doc - document uncovered member variables

Fix documentation typo for shash_alg->descsize.

Add documentation for initially uncovered member variables.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/hash.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 3d66e8bd093..98abda9ed3a 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -38,6 +38,10 @@ struct crypto_ahash;
  *	       will save the partial state of the transformation into it. On the
  *	       other side, the @import function will load the state from a
  *	       buffer of this size as well.
+ * @base: Start of data structure of cipher algorithm. The common data
+ *	  structure of crypto_alg contains information common to all ciphers.
+ *	  The hash_alg_common data structure now adds the hash-specific
+ *	  information.
  */
 struct hash_alg_common {
 	unsigned int digestsize;
@@ -114,6 +118,7 @@ struct ahash_request {
  *	    entire state of the ongoing transformation from a provided block of
  *	    data so the transformation can continue from this point onward. No
  *	    data processing happens at this point.
+ * @halg: see struct hash_alg_common
  */
 struct ahash_alg {
 	int (*init)(struct ahash_request *req);
@@ -153,7 +158,7 @@ struct shash_desc {
  * @setkey: see struct ahash_alg
  * @digestsize: see struct ahash_alg
  * @statesize: see struct ahash_alg
- * @dedcsize: Size of the operational state for the message digest. This state
+ * @descsize: Size of the operational state for the message digest. This state
  * 	      size is the memory size that needs to be allocated for
  *	      shash_desc.__ctx
  * @base: internally used
-- 
cgit v1.2.3-70-g09d2


From 7c7f2f2bc9a63f9605a16eabac59fc655dfe7c9a Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@fb.com>
Date: Mon, 17 Nov 2014 10:41:57 -0700
Subject: blk-mq: add blk_mq_free_hctx_request()

It's silly to use blk_mq_free_request() which in turn maps the
request to the hardware queue, for places where we already know
what the hardware queue is. This saves us an extra mapping of a
hardware queue on request completion, if the caller knows this
information already.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c         | 17 ++++++++++++-----
 include/linux/blk-mq.h |  1 +
 2 files changed, 13 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index fdf12152946..4347aa2be6a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -269,16 +269,23 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
 	blk_mq_queue_exit(q);
 }
 
-void blk_mq_free_request(struct request *rq)
+void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
-	struct blk_mq_hw_ctx *hctx;
-	struct request_queue *q = rq->q;
 
 	ctx->rq_completed[rq_is_sync(rq)]++;
-
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 	__blk_mq_free_request(hctx, ctx, rq);
+
+}
+EXPORT_SYMBOL_GPL(blk_mq_free_hctx_request);
+
+void blk_mq_free_request(struct request *rq)
+{
+	struct blk_mq_hw_ctx *hctx;
+	struct request_queue *q = rq->q;
+
+	hctx = q->mq_ops->map_queue(q, rq->mq_ctx->cpu);
+	blk_mq_free_hctx_request(hctx, rq);
 }
 EXPORT_SYMBOL_GPL(blk_mq_free_request);
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index c3b64ec5321..fb0a4fb3dc2 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -169,6 +169,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 void blk_mq_insert_request(struct request *, bool, bool, bool);
 void blk_mq_run_queues(struct request_queue *q, bool async);
 void blk_mq_free_request(struct request *rq);
+void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *, struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
 struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		gfp_t gfp, bool reserved);
-- 
cgit v1.2.3-70-g09d2


From 069fb0b63722f8c9f8b4bbce236793626c89af33 Mon Sep 17 00:00:00 2001
From: Sebastian Schmidt <yath@yath.de>
Date: Fri, 14 Nov 2014 10:51:45 -0800
Subject: syslog: Provide stub check_syslog_permissions

When building without CONFIG_PRINTK, we need to provide a stub
check_syslog_permissions. As there is no way to turn on the
dmesg_restrict sysctl without CONFIG_PRINTK, return success.

Reported-by: Jim Davis <jim.epost@gmail.com>
Signed-off-by: Sebastian Schmidt <yath@yath.de>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 include/linux/syslog.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/syslog.h b/include/linux/syslog.h
index 9def5297dbb..4b7b875a7ce 100644
--- a/include/linux/syslog.h
+++ b/include/linux/syslog.h
@@ -48,6 +48,14 @@
 #define SYSLOG_FROM_PROC             1
 
 int do_syslog(int type, char __user *buf, int count, bool from_file);
+
+#ifdef CONFIG_PRINTK
 int check_syslog_permissions(int type, bool from_file);
+#else
+static inline int check_syslog_permissions(int type, bool from_file)
+{
+	return 0;
+}
+#endif
 
 #endif /* _LINUX_SYSLOG_H */
-- 
cgit v1.2.3-70-g09d2


From 3fb1581ea1ab0aec6ac5430dc0e257a8c9b71680 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Fri, 14 Nov 2014 09:47:25 +0100
Subject: ARM: 8199/1: PM / Runtime: Add getter for querying the IRQ safe
 option v12

Add a simple getter pm_runtime_is_irq_safe() for querying whether runtime
PM IRQ safe was set or not.

Various bus drivers implementing runtime PM may use choose to suspend
differently based on IRQ safeness status of child driver (e.g. do not
unprepare the clock if IRQ safe is not set).

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Rafael J. Wysocki <rjw@rjwysocki.net>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 Documentation/power/runtime_pm.txt | 4 ++++
 include/linux/pm_runtime.h         | 6 ++++++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index f32ce541957..397b8159314 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -468,6 +468,10 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
     - set the power.irq_safe flag for the device, causing the runtime-PM
       callbacks to be invoked with interrupts off
 
+  bool pm_runtime_is_irq_safe(struct device *dev);
+    - return true if power.irq_safe flag was set for the device, causing
+      the runtime-PM callbacks to be invoked with interrupts off
+
   void pm_runtime_mark_last_busy(struct device *dev);
     - set the power.last_busy field to the current time
 
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 367f49b9a1c..44d74f0f182 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -128,6 +128,11 @@ static inline void pm_runtime_mark_last_busy(struct device *dev)
 	ACCESS_ONCE(dev->power.last_busy) = jiffies;
 }
 
+static inline bool pm_runtime_is_irq_safe(struct device *dev)
+{
+	return dev->power.irq_safe;
+}
+
 #else /* !CONFIG_PM_RUNTIME */
 
 static inline int __pm_runtime_idle(struct device *dev, int rpmflags)
@@ -167,6 +172,7 @@ static inline bool pm_runtime_enabled(struct device *dev) { return false; }
 
 static inline void pm_runtime_no_callbacks(struct device *dev) {}
 static inline void pm_runtime_irq_safe(struct device *dev) {}
+static inline bool pm_runtime_is_irq_safe(struct device *dev) { return false; }
 
 static inline bool pm_runtime_callbacks_present(struct device *dev) { return false; }
 static inline void pm_runtime_mark_last_busy(struct device *dev) {}
-- 
cgit v1.2.3-70-g09d2


From f560e3229564a673603541ebfb36118d7cd98038 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Fri, 14 Nov 2014 09:47:49 +0100
Subject: ARM: 8200/1: amba: Add helpers for (un)preparing AMBA clock v12

Add amba_pclk_prepare() and amba_pclk_unprepare() inline functions for
handling the AMBA bus clock by device drivers.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 include/linux/amba/bus.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index c324f5700d1..ac02f9bd63d 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -97,6 +97,16 @@ void amba_release_regions(struct amba_device *);
 #define amba_pclk_disable(d)	\
 	do { if (!IS_ERR((d)->pclk)) clk_disable((d)->pclk); } while (0)
 
+static inline int amba_pclk_prepare(struct amba_device *dev)
+{
+	return clk_prepare(dev->pclk);
+}
+
+static inline void amba_pclk_unprepare(struct amba_device *dev)
+{
+	clk_unprepare(dev->pclk);
+}
+
 /* Some drivers don't use the struct amba_device */
 #define AMBA_CONFIG_BITS(a) (((a) >> 24) & 0xff)
 #define AMBA_REV_BITS(a) (((a) >> 20) & 0x0f)
-- 
cgit v1.2.3-70-g09d2


From 0288d7183c41c0192d2963d44590f346f4aee917 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Mon, 17 Nov 2014 15:51:01 -0500
Subject: audit: convert status version to a feature bitmap

The version field defined in the audit status structure was found to have
limitations in terms of its expressibility of features supported.  This is
distict from the get/set features call to be able to command those features
that are present.

Converting this field from a version number to a feature bitmap will allow
distributions to selectively backport and support certain features and will
allow upstream to be able to deprecate features in the future.  It will allow
userspace clients to first query the kernel for which features are actually
present and supported.  Currently, EINVAL is returned rather than EOPNOTSUP,
which isn't helpful in determining if there was an error in the command, or if
it simply isn't supported yet.  Past features are not represented by this
bitmap, but their use may be converted to EOPNOTSUP if needed in the future.

Since "version" is too generic to convert with a #define, use a union in the
struct status, introducing the member "feature_bitmap" unionized with
"version".

Convert existing AUDIT_VERSION_* macros over to AUDIT_FEATURE_BITMAP*
counterparts, leaving the former for backwards compatibility.

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
[PM: minor whitespace tweaks]
Signed-off-by: Paul Moore <pmoore@redhat.com>
---
 include/uapi/linux/audit.h | 17 +++++++++++++----
 kernel/audit.c             |  2 +-
 2 files changed, 14 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 4d100c841c8..2ccf19e06e1 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -322,9 +322,15 @@ enum {
 #define AUDIT_STATUS_BACKLOG_LIMIT	0x0010
 #define AUDIT_STATUS_BACKLOG_WAIT_TIME	0x0020
 
-#define AUDIT_VERSION_BACKLOG_LIMIT	1
-#define AUDIT_VERSION_BACKLOG_WAIT_TIME	2
-#define AUDIT_VERSION_LATEST AUDIT_VERSION_BACKLOG_WAIT_TIME
+#define AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT	0x00000001
+#define AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME	0x00000002
+#define AUDIT_FEATURE_BITMAP_ALL (AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT | \
+				  AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME)
+
+/* deprecated: AUDIT_VERSION_* */
+#define AUDIT_VERSION_LATEST 		AUDIT_FEATURE_BITMAP_ALL
+#define AUDIT_VERSION_BACKLOG_LIMIT	AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT
+#define AUDIT_VERSION_BACKLOG_WAIT_TIME	AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME
 
 				/* Failure-to-log actions */
 #define AUDIT_FAIL_SILENT	0
@@ -403,7 +409,10 @@ struct audit_status {
 	__u32		backlog_limit;	/* waiting messages limit */
 	__u32		lost;		/* messages lost */
 	__u32		backlog;	/* messages waiting in queue */
-	__u32		version;	/* audit api version number */
+	union {
+		__u32	version;	/* deprecated: audit api version num */
+		__u32	feature_bitmap;	/* bitmap of kernel audit features */
+	};
 	__u32		backlog_wait_time;/* message queue wait timeout */
 };
 
diff --git a/kernel/audit.c b/kernel/audit.c
index 53bb39bf79e..7b83c557aee 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -842,7 +842,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		s.backlog_limit		= audit_backlog_limit;
 		s.lost			= atomic_read(&audit_lost);
 		s.backlog		= skb_queue_len(&audit_skb_queue);
-		s.version		= AUDIT_VERSION_LATEST;
+		s.feature_bitmap	= AUDIT_FEATURE_BITMAP_ALL;
 		s.backlog_wait_time	= audit_backlog_wait_time;
 		audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s));
 		break;
-- 
cgit v1.2.3-70-g09d2


From ee1b58d36aa1b5a79eaba11f5c3633c88231da83 Mon Sep 17 00:00:00 2001
From: Qiaowei Ren <qiaowei.ren@intel.com>
Date: Fri, 14 Nov 2014 07:18:19 -0800
Subject: mpx: Extend siginfo structure to include bound violation information

This patch adds new fields about bound violation into siginfo
structure. si_lower and si_upper are respectively lower bound
and upper bound when bound violation is caused.

Signed-off-by: Qiaowei Ren <qiaowei.ren@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: linux-mm@kvack.org
Cc: linux-mips@linux-mips.org
Cc: Dave Hansen <dave@sr71.net>
Link: http://lkml.kernel.org/r/20141114151819.1908C900@viggo.jf.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/uapi/asm-generic/siginfo.h | 9 ++++++++-
 kernel/signal.c                    | 4 ++++
 2 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index ba5be7fdbdf..1e3552037a5 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -91,6 +91,10 @@ typedef struct siginfo {
 			int _trapno;	/* TRAP # which caused the signal */
 #endif
 			short _addr_lsb; /* LSB of the reported address */
+			struct {
+				void __user *_lower;
+				void __user *_upper;
+			} _addr_bnd;
 		} _sigfault;
 
 		/* SIGPOLL */
@@ -131,6 +135,8 @@ typedef struct siginfo {
 #define si_trapno	_sifields._sigfault._trapno
 #endif
 #define si_addr_lsb	_sifields._sigfault._addr_lsb
+#define si_lower	_sifields._sigfault._addr_bnd._lower
+#define si_upper	_sifields._sigfault._addr_bnd._upper
 #define si_band		_sifields._sigpoll._band
 #define si_fd		_sifields._sigpoll._fd
 #ifdef __ARCH_SIGSYS
@@ -199,7 +205,8 @@ typedef struct siginfo {
  */
 #define SEGV_MAPERR	(__SI_FAULT|1)	/* address not mapped to object */
 #define SEGV_ACCERR	(__SI_FAULT|2)	/* invalid permissions for mapped object */
-#define NSIGSEGV	2
+#define SEGV_BNDERR	(__SI_FAULT|3)  /* failed address bound checks */
+#define NSIGSEGV	3
 
 /*
  * SIGBUS si_codes
diff --git a/kernel/signal.c b/kernel/signal.c
index 8f0876f9f6d..2c403a4c8be 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2747,6 +2747,10 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
 		 */
 		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
+#endif
+#ifdef SEGV_BNDERR
+		err |= __put_user(from->si_lower, &to->si_lower);
+		err |= __put_user(from->si_upper, &to->si_upper);
 #endif
 		break;
 	case __SI_CHLD:
-- 
cgit v1.2.3-70-g09d2


From 4aae7e436fa51faf4bf5d11b175aea82cfe8224a Mon Sep 17 00:00:00 2001
From: Qiaowei Ren <qiaowei.ren@intel.com>
Date: Fri, 14 Nov 2014 07:18:25 -0800
Subject: x86, mpx: Introduce VM_MPX to indicate that a VMA is MPX specific

MPX-enabled applications using large swaths of memory can
potentially have large numbers of bounds tables in process
address space to save bounds information. These tables can take
up huge swaths of memory (as much as 80% of the memory on the
system) even if we clean them up aggressively. In the worst-case
scenario, the tables can be 4x the size of the data structure
being tracked. IOW, a 1-page structure can require 4 bounds-table
pages.

Being this huge, our expectation is that folks using MPX are
going to be keen on figuring out how much memory is being
dedicated to it. So we need a way to track memory use for MPX.

If we want to specifically track MPX VMAs we need to be able to
distinguish them from normal VMAs, and keep them from getting
merged with normal VMAs. A new VM_ flag set only on MPX VMAs does
both of those things. With this flag, MPX bounds-table VMAs can
be distinguished from other VMAs, and userspace can also walk
/proc/$pid/smaps to get memory usage for MPX.

In addition to this flag, we also introduce a special ->vm_ops
specific to MPX VMAs (see the patch "add MPX specific mmap
interface"), but currently different ->vm_ops do not by
themselves prevent VMA merging, so we still need this flag.

We understand that VM_ flags are scarce and are open to other
options.

Signed-off-by: Qiaowei Ren <qiaowei.ren@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: linux-mm@kvack.org
Cc: linux-mips@linux-mips.org
Cc: Dave Hansen <dave@sr71.net>
Link: http://lkml.kernel.org/r/20141114151825.565625B3@viggo.jf.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 fs/proc/task_mmu.c | 3 +++
 include/linux/mm.h | 6 ++++++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4e0388cffe3..f6734c6b66a 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -552,6 +552,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_GROWSDOWN)]	= "gd",
 		[ilog2(VM_PFNMAP)]	= "pf",
 		[ilog2(VM_DENYWRITE)]	= "dw",
+#ifdef CONFIG_X86_INTEL_MPX
+		[ilog2(VM_MPX)]		= "mp",
+#endif
 		[ilog2(VM_LOCKED)]	= "lo",
 		[ilog2(VM_IO)]		= "io",
 		[ilog2(VM_SEQ_READ)]	= "sr",
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b46461116cd..f7606d3a091 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -128,6 +128,7 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
 #define VM_NONLINEAR	0x00800000	/* Is non-linear (remap_file_pages) */
 #define VM_ARCH_1	0x01000000	/* Architecture-specific flag */
+#define VM_ARCH_2	0x02000000
 #define VM_DONTDUMP	0x04000000	/* Do not include in the core dump */
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
@@ -155,6 +156,11 @@ extern unsigned int kobjsize(const void *objp);
 # define VM_MAPPED_COPY	VM_ARCH_1	/* T if mapped copy of data (nommu mmap) */
 #endif
 
+#if defined(CONFIG_X86)
+/* MPX specific bounds table or bounds directory */
+# define VM_MPX		VM_ARCH_2
+#endif
+
 #ifndef VM_GROWSUP
 # define VM_GROWSUP	VM_NONE
 #endif
-- 
cgit v1.2.3-70-g09d2


From fe3d197f84319d3bce379a9c0dc17b1f48ad358c Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Fri, 14 Nov 2014 07:18:29 -0800
Subject: x86, mpx: On-demand kernel allocation of bounds tables

This is really the meat of the MPX patch set.  If there is one patch to
review in the entire series, this is the one.  There is a new ABI here
and this kernel code also interacts with userspace memory in a
relatively unusual manner.  (small FAQ below).

Long Description:

This patch adds two prctl() commands to provide enable or disable the
management of bounds tables in kernel, including on-demand kernel
allocation (See the patch "on-demand kernel allocation of bounds tables")
and cleanup (See the patch "cleanup unused bound tables"). Applications
do not strictly need the kernel to manage bounds tables and we expect
some applications to use MPX without taking advantage of this kernel
support. This means the kernel can not simply infer whether an application
needs bounds table management from the MPX registers.  The prctl() is an
explicit signal from userspace.

PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to
require kernel's help in managing bounds tables.

PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't
want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel
won't allocate and free bounds tables even if the CPU supports MPX.

PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds
directory out of a userspace register (bndcfgu) and then cache it into
a new field (->bd_addr) in  the 'mm_struct'.  PR_MPX_DISABLE_MANAGEMENT
will set "bd_addr" to an invalid address.  Using this scheme, we can
use "bd_addr" to determine whether the management of bounds tables in
kernel is enabled.

Also, the only way to access that bndcfgu register is via an xsaves,
which can be expensive.  Caching "bd_addr" like this also helps reduce
the cost of those xsaves when doing table cleanup at munmap() time.
Unfortunately, we can not apply this optimization to #BR fault time
because we need an xsave to get the value of BNDSTATUS.

==== Why does the hardware even have these Bounds Tables? ====

MPX only has 4 hardware registers for storing bounds information.
If MPX-enabled code needs more than these 4 registers, it needs to
spill them somewhere. It has two special instructions for this
which allow the bounds to be moved between the bounds registers
and some new "bounds tables".

They are similar conceptually to a page fault and will be raised by
the MPX hardware during both bounds violations or when the tables
are not present. This patch handles those #BR exceptions for
not-present tables by carving the space out of the normal processes
address space (essentially calling the new mmap() interface indroduced
earlier in this patch set.) and then pointing the bounds-directory
over to it.

The tables *need* to be accessed and controlled by userspace because
the instructions for moving bounds in and out of them are extremely
frequent. They potentially happen every time a register pointing to
memory is dereferenced. Any direct kernel involvement (like a syscall)
to access the tables would obviously destroy performance.

==== Why not do this in userspace? ====

This patch is obviously doing this allocation in the kernel.
However, MPX does not strictly *require* anything in the kernel.
It can theoretically be done completely from userspace. Here are
a few ways this *could* be done. I don't think any of them are
practical in the real-world, but here they are.

Q: Can virtual space simply be reserved for the bounds tables so
   that we never have to allocate them?
A: As noted earlier, these tables are *HUGE*. An X-GB virtual
   area needs 4*X GB of virtual space, plus 2GB for the bounds
   directory. If we were to preallocate them for the 128TB of
   user virtual address space, we would need to reserve 512TB+2GB,
   which is larger than the entire virtual address space today.
   This means they can not be reserved ahead of time. Also, a
   single process's pre-popualated bounds directory consumes 2GB
   of virtual *AND* physical memory. IOW, it's completely
   infeasible to prepopulate bounds directories.

Q: Can we preallocate bounds table space at the same time memory
   is allocated which might contain pointers that might eventually
   need bounds tables?
A: This would work if we could hook the site of each and every
   memory allocation syscall. This can be done for small,
   constrained applications. But, it isn't practical at a larger
   scale since a given app has no way of controlling how all the
   parts of the app might allocate memory (think libraries). The
   kernel is really the only place to intercept these calls.

Q: Could a bounds fault be handed to userspace and the tables
   allocated there in a signal handler instead of in the kernel?
A: (thanks to tglx) mmap() is not on the list of safe async
   handler functions and even if mmap() would work it still
   requires locking or nasty tricks to keep track of the
   allocation state there.

Having ruled out all of the userspace-only approaches for managing
bounds tables that we could think of, we create them on demand in
the kernel.

Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: linux-mm@kvack.org
Cc: linux-mips@linux-mips.org
Cc: Dave Hansen <dave@sr71.net>
Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/mmu_context.h |   7 ++
 arch/x86/include/asm/mpx.h         |  41 +++++++
 arch/x86/include/asm/processor.h   |  18 +++
 arch/x86/kernel/setup.c            |   2 +
 arch/x86/kernel/traps.c            |  85 +++++++++++++-
 arch/x86/mm/mpx.c                  | 223 ++++++++++++++++++++++++++++++++++++-
 fs/exec.c                          |   2 +
 include/asm-generic/mmu_context.h  |   5 +
 include/linux/mm_types.h           |   4 +
 include/uapi/linux/prctl.h         |   6 +
 kernel/sys.c                       |  12 ++
 11 files changed, 399 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 166af2a8e86..0b0ba91ff1e 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -10,6 +10,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
+#include <asm/mpx.h>
 #ifndef CONFIG_PARAVIRT
 #include <asm-generic/mm_hooks.h>
 
@@ -102,4 +103,10 @@ do {						\
 } while (0)
 #endif
 
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+		struct vm_area_struct *vma)
+{
+	mpx_mm_init(mm);
+}
+
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h
index 35bcb1cddf4..05eecbf8a48 100644
--- a/arch/x86/include/asm/mpx.h
+++ b/arch/x86/include/asm/mpx.h
@@ -5,6 +5,14 @@
 #include <asm/ptrace.h>
 #include <asm/insn.h>
 
+/*
+ * NULL is theoretically a valid place to put the bounds
+ * directory, so point this at an invalid address.
+ */
+#define MPX_INVALID_BOUNDS_DIR	((void __user *)-1)
+#define MPX_BNDCFG_ENABLE_FLAG	0x1
+#define MPX_BD_ENTRY_VALID_FLAG	0x1
+
 #ifdef CONFIG_X86_64
 
 /* upper 28 bits [47:20] of the virtual address in 64-bit used to
@@ -18,6 +26,7 @@
 #define MPX_BT_ENTRY_OFFSET	17
 #define MPX_BT_ENTRY_SHIFT	5
 #define MPX_IGN_BITS		3
+#define MPX_BD_ENTRY_TAIL	3
 
 #else
 
@@ -26,23 +35,55 @@
 #define MPX_BT_ENTRY_OFFSET	10
 #define MPX_BT_ENTRY_SHIFT	4
 #define MPX_IGN_BITS		2
+#define MPX_BD_ENTRY_TAIL	2
 
 #endif
 
 #define MPX_BD_SIZE_BYTES (1UL<<(MPX_BD_ENTRY_OFFSET+MPX_BD_ENTRY_SHIFT))
 #define MPX_BT_SIZE_BYTES (1UL<<(MPX_BT_ENTRY_OFFSET+MPX_BT_ENTRY_SHIFT))
 
+#define MPX_BNDSTA_TAIL		2
+#define MPX_BNDCFG_TAIL		12
+#define MPX_BNDSTA_ADDR_MASK	(~((1UL<<MPX_BNDSTA_TAIL)-1))
+#define MPX_BNDCFG_ADDR_MASK	(~((1UL<<MPX_BNDCFG_TAIL)-1))
+#define MPX_BT_ADDR_MASK	(~((1UL<<MPX_BD_ENTRY_TAIL)-1))
+
+#define MPX_BNDCFG_ADDR_MASK	(~((1UL<<MPX_BNDCFG_TAIL)-1))
 #define MPX_BNDSTA_ERROR_CODE	0x3
 
 #ifdef CONFIG_X86_INTEL_MPX
 siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 				struct xsave_struct *xsave_buf);
+int mpx_handle_bd_fault(struct xsave_struct *xsave_buf);
+static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
+{
+	return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR);
+}
+static inline void mpx_mm_init(struct mm_struct *mm)
+{
+	/*
+	 * NULL is theoretically a valid place to put the bounds
+	 * directory, so point this at an invalid address.
+	 */
+	mm->bd_addr = MPX_INVALID_BOUNDS_DIR;
+}
 #else
 static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 					      struct xsave_struct *xsave_buf)
 {
 	return NULL;
 }
+static inline int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+{
+	return -EINVAL;
+}
+static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
+{
+	return 0;
+}
+static inline void mpx_mm_init(struct mm_struct *mm)
+{
+}
 #endif /* CONFIG_X86_INTEL_MPX */
 
 #endif /* _ASM_X86_MPX_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6571aaabacb..9617a171681 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -954,6 +954,24 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
 extern int get_tsc_mode(unsigned long adr);
 extern int set_tsc_mode(unsigned int val);
 
+/* Register/unregister a process' MPX related resource */
+#define MPX_ENABLE_MANAGEMENT(tsk)	mpx_enable_management((tsk))
+#define MPX_DISABLE_MANAGEMENT(tsk)	mpx_disable_management((tsk))
+
+#ifdef CONFIG_X86_INTEL_MPX
+extern int mpx_enable_management(struct task_struct *tsk);
+extern int mpx_disable_management(struct task_struct *tsk);
+#else
+static inline int mpx_enable_management(struct task_struct *tsk)
+{
+	return -EINVAL;
+}
+static inline int mpx_disable_management(struct task_struct *tsk)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_X86_INTEL_MPX */
+
 extern u16 amd_get_nb_id(int cpu);
 
 static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ab08aa2276f..214245d6b99 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -960,6 +960,8 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.end_data = (unsigned long) _edata;
 	init_mm.brk = _brk_end;
 
+	mpx_mm_init(&init_mm);
+
 	code_resource.start = __pa_symbol(_text);
 	code_resource.end = __pa_symbol(_etext)-1;
 	data_resource.start = __pa_symbol(_etext);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 0d0e922fafc..651d5d4f755 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -60,6 +60,7 @@
 #include <asm/fixmap.h>
 #include <asm/mach_traps.h>
 #include <asm/alternative.h>
+#include <asm/mpx.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/x86_init.h>
@@ -228,7 +229,6 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
 
 DO_ERROR(X86_TRAP_DE,     SIGFPE,  "divide error",		divide_error)
 DO_ERROR(X86_TRAP_OF,     SIGSEGV, "overflow",			overflow)
-DO_ERROR(X86_TRAP_BR,     SIGSEGV, "bounds",			bounds)
 DO_ERROR(X86_TRAP_UD,     SIGILL,  "invalid opcode",		invalid_op)
 DO_ERROR(X86_TRAP_OLD_MF, SIGFPE,  "coprocessor segment overrun",coprocessor_segment_overrun)
 DO_ERROR(X86_TRAP_TS,     SIGSEGV, "invalid TSS",		invalid_TSS)
@@ -278,6 +278,89 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 }
 #endif
 
+dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
+{
+	struct task_struct *tsk = current;
+	struct xsave_struct *xsave_buf;
+	enum ctx_state prev_state;
+	struct bndcsr *bndcsr;
+	siginfo_t *info;
+
+	prev_state = exception_enter();
+	if (notify_die(DIE_TRAP, "bounds", regs, error_code,
+			X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP)
+		goto exit;
+	conditional_sti(regs);
+
+	if (!user_mode(regs))
+		die("bounds", regs, error_code);
+
+	if (!cpu_feature_enabled(X86_FEATURE_MPX)) {
+		/* The exception is not from Intel MPX */
+		goto exit_trap;
+	}
+
+	/*
+	 * We need to look at BNDSTATUS to resolve this exception.
+	 * It is not directly accessible, though, so we need to
+	 * do an xsave and then pull it out of the xsave buffer.
+	 */
+	fpu_save_init(&tsk->thread.fpu);
+	xsave_buf = &(tsk->thread.fpu.state->xsave);
+	bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+	if (!bndcsr)
+		goto exit_trap;
+
+	/*
+	 * The error code field of the BNDSTATUS register communicates status
+	 * information of a bound range exception #BR or operation involving
+	 * bound directory.
+	 */
+	switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) {
+	case 2:	/* Bound directory has invalid entry. */
+		if (mpx_handle_bd_fault(xsave_buf))
+			goto exit_trap;
+		break; /* Success, it was handled */
+	case 1: /* Bound violation. */
+		info = mpx_generate_siginfo(regs, xsave_buf);
+		if (PTR_ERR(info)) {
+			/*
+			 * We failed to decode the MPX instruction.  Act as if
+			 * the exception was not caused by MPX.
+			 */
+			goto exit_trap;
+		}
+		/*
+		 * Success, we decoded the instruction and retrieved
+		 * an 'info' containing the address being accessed
+		 * which caused the exception.  This information
+		 * allows and application to possibly handle the
+		 * #BR exception itself.
+		 */
+		do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, info);
+		kfree(info);
+		break;
+	case 0: /* No exception caused by Intel MPX operations. */
+		goto exit_trap;
+	default:
+		die("bounds", regs, error_code);
+	}
+
+exit:
+	exception_exit(prev_state);
+	return;
+exit_trap:
+	/*
+	 * This path out is for all the cases where we could not
+	 * handle the exception in some way (like allocating a
+	 * table or telling userspace about it.  We will also end
+	 * up here if the kernel has MPX turned off at compile
+	 * time..
+	 */
+	do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL);
+	exception_exit(prev_state);
+}
+
 dotraplinkage void
 do_general_protection(struct pt_regs *regs, long error_code)
 {
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 9009e094d68..96266375441 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -10,8 +10,12 @@
 #include <linux/syscalls.h>
 #include <linux/sched/sysctl.h>
 
+#include <asm/i387.h>
+#include <asm/insn.h>
 #include <asm/mman.h>
 #include <asm/mpx.h>
+#include <asm/processor.h>
+#include <asm/fpu-internal.h>
 
 static const char *mpx_mapping_name(struct vm_area_struct *vma)
 {
@@ -266,10 +270,11 @@ bad_opcode:
 siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 				struct xsave_struct *xsave_buf)
 {
+	struct bndreg *bndregs, *bndreg;
+	siginfo_t *info = NULL;
 	struct insn insn;
 	uint8_t bndregno;
 	int err;
-	siginfo_t *info;
 
 	err = mpx_insn_decode(&insn, regs);
 	if (err)
@@ -285,6 +290,15 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 		err = -EINVAL;
 		goto err_out;
 	}
+	/* get the bndregs _area_ of the xsave structure */
+	bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS);
+	if (!bndregs) {
+		err = -EINVAL;
+		goto err_out;
+	}
+	/* now go select the individual register in the set of 4 */
+	bndreg = &bndregs[bndregno];
+
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info) {
 		err = -ENOMEM;
@@ -300,10 +314,8 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 	 * complains when casting from integers to different-size
 	 * pointers.
 	 */
-	info->si_lower = (void __user *)(unsigned long)
-		(xsave_buf->bndreg[bndregno].lower_bound);
-	info->si_upper = (void __user *)(unsigned long)
-		(~xsave_buf->bndreg[bndregno].upper_bound);
+	info->si_lower = (void __user *)(unsigned long)bndreg->lower_bound;
+	info->si_upper = (void __user *)(unsigned long)~bndreg->upper_bound;
 	info->si_addr_lsb = 0;
 	info->si_signo = SIGSEGV;
 	info->si_errno = 0;
@@ -319,5 +331,206 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 	}
 	return info;
 err_out:
+	/* info might be NULL, but kfree() handles that */
+	kfree(info);
 	return ERR_PTR(err);
 }
+
+static __user void *task_get_bounds_dir(struct task_struct *tsk)
+{
+	struct bndcsr *bndcsr;
+
+	if (!cpu_feature_enabled(X86_FEATURE_MPX))
+		return MPX_INVALID_BOUNDS_DIR;
+
+	/*
+	 * The bounds directory pointer is stored in a register
+	 * only accessible if we first do an xsave.
+	 */
+	fpu_save_init(&tsk->thread.fpu);
+	bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR);
+	if (!bndcsr)
+		return MPX_INVALID_BOUNDS_DIR;
+
+	/*
+	 * Make sure the register looks valid by checking the
+	 * enable bit.
+	 */
+	if (!(bndcsr->bndcfgu & MPX_BNDCFG_ENABLE_FLAG))
+		return MPX_INVALID_BOUNDS_DIR;
+
+	/*
+	 * Lastly, mask off the low bits used for configuration
+	 * flags, and return the address of the bounds table.
+	 */
+	return (void __user *)(unsigned long)
+		(bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK);
+}
+
+int mpx_enable_management(struct task_struct *tsk)
+{
+	void __user *bd_base = MPX_INVALID_BOUNDS_DIR;
+	struct mm_struct *mm = tsk->mm;
+	int ret = 0;
+
+	/*
+	 * runtime in the userspace will be responsible for allocation of
+	 * the bounds directory. Then, it will save the base of the bounds
+	 * directory into XSAVE/XRSTOR Save Area and enable MPX through
+	 * XRSTOR instruction.
+	 *
+	 * fpu_xsave() is expected to be very expensive. Storing the bounds
+	 * directory here means that we do not have to do xsave in the unmap
+	 * path; we can just use mm->bd_addr instead.
+	 */
+	bd_base = task_get_bounds_dir(tsk);
+	down_write(&mm->mmap_sem);
+	mm->bd_addr = bd_base;
+	if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR)
+		ret = -ENXIO;
+
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+
+int mpx_disable_management(struct task_struct *tsk)
+{
+	struct mm_struct *mm = current->mm;
+
+	if (!cpu_feature_enabled(X86_FEATURE_MPX))
+		return -ENXIO;
+
+	down_write(&mm->mmap_sem);
+	mm->bd_addr = MPX_INVALID_BOUNDS_DIR;
+	up_write(&mm->mmap_sem);
+	return 0;
+}
+
+/*
+ * With 32-bit mode, MPX_BT_SIZE_BYTES is 4MB, and the size of each
+ * bounds table is 16KB. With 64-bit mode, MPX_BT_SIZE_BYTES is 2GB,
+ * and the size of each bounds table is 4MB.
+ */
+static int allocate_bt(long __user *bd_entry)
+{
+	unsigned long expected_old_val = 0;
+	unsigned long actual_old_val = 0;
+	unsigned long bt_addr;
+	int ret = 0;
+
+	/*
+	 * Carve the virtual space out of userspace for the new
+	 * bounds table:
+	 */
+	bt_addr = mpx_mmap(MPX_BT_SIZE_BYTES);
+	if (IS_ERR((void *)bt_addr))
+		return PTR_ERR((void *)bt_addr);
+	/*
+	 * Set the valid flag (kinda like _PAGE_PRESENT in a pte)
+	 */
+	bt_addr = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
+
+	/*
+	 * Go poke the address of the new bounds table in to the
+	 * bounds directory entry out in userspace memory.  Note:
+	 * we may race with another CPU instantiating the same table.
+	 * In that case the cmpxchg will see an unexpected
+	 * 'actual_old_val'.
+	 *
+	 * This can fault, but that's OK because we do not hold
+	 * mmap_sem at this point, unlike some of the other part
+	 * of the MPX code that have to pagefault_disable().
+	 */
+	ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
+					   expected_old_val, bt_addr);
+	if (ret)
+		goto out_unmap;
+
+	/*
+	 * The user_atomic_cmpxchg_inatomic() will only return nonzero
+	 * for faults, *not* if the cmpxchg itself fails.  Now we must
+	 * verify that the cmpxchg itself completed successfully.
+	 */
+	/*
+	 * We expected an empty 'expected_old_val', but instead found
+	 * an apparently valid entry.  Assume we raced with another
+	 * thread to instantiate this table and desclare succecss.
+	 */
+	if (actual_old_val & MPX_BD_ENTRY_VALID_FLAG) {
+		ret = 0;
+		goto out_unmap;
+	}
+	/*
+	 * We found a non-empty bd_entry but it did not have the
+	 * VALID_FLAG set.  Return an error which will result in
+	 * a SEGV since this probably means that somebody scribbled
+	 * some invalid data in to a bounds table.
+	 */
+	if (expected_old_val != actual_old_val) {
+		ret = -EINVAL;
+		goto out_unmap;
+	}
+	return 0;
+out_unmap:
+	vm_munmap(bt_addr & MPX_BT_ADDR_MASK, MPX_BT_SIZE_BYTES);
+	return ret;
+}
+
+/*
+ * When a BNDSTX instruction attempts to save bounds to a bounds
+ * table, it will first attempt to look up the table in the
+ * first-level bounds directory.  If it does not find a table in
+ * the directory, a #BR is generated and we get here in order to
+ * allocate a new table.
+ *
+ * With 32-bit mode, the size of BD is 4MB, and the size of each
+ * bound table is 16KB. With 64-bit mode, the size of BD is 2GB,
+ * and the size of each bound table is 4MB.
+ */
+static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
+{
+	unsigned long bd_entry, bd_base;
+	struct bndcsr *bndcsr;
+
+	bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+	if (!bndcsr)
+		return -EINVAL;
+	/*
+	 * Mask off the preserve and enable bits
+	 */
+	bd_base = bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK;
+	/*
+	 * The hardware provides the address of the missing or invalid
+	 * entry via BNDSTATUS, so we don't have to go look it up.
+	 */
+	bd_entry = bndcsr->bndstatus & MPX_BNDSTA_ADDR_MASK;
+	/*
+	 * Make sure the directory entry is within where we think
+	 * the directory is.
+	 */
+	if ((bd_entry < bd_base) ||
+	    (bd_entry >= bd_base + MPX_BD_SIZE_BYTES))
+		return -EINVAL;
+
+	return allocate_bt((long __user *)bd_entry);
+}
+
+int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+{
+	/*
+	 * Userspace never asked us to manage the bounds tables,
+	 * so refuse to help.
+	 */
+	if (!kernel_managing_mpx_tables(current->mm))
+		return -EINVAL;
+
+	if (do_mpx_bt_fault(xsave_buf)) {
+		force_sig(SIGSEGV, current);
+		/*
+		 * The force_sig() is essentially "handling" this
+		 * exception, so we do not pass up the error
+		 * from do_mpx_bt_fault().
+		 */
+	}
+	return 0;
+}
diff --git a/fs/exec.c b/fs/exec.c
index 7302b75a982..65d4f5c70ef 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -60,6 +60,7 @@
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/tlb.h>
+#include <asm/mpx.h>
 
 #include <trace/events/task.h>
 #include "internal.h"
@@ -277,6 +278,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 		goto err;
 
 	mm->stack_vm = mm->total_vm = 1;
+	arch_bprm_mm_init(mm, vma);
 	up_write(&mm->mmap_sem);
 	bprm->p = vma->vm_end - sizeof(void *);
 	return 0;
diff --git a/include/asm-generic/mmu_context.h b/include/asm-generic/mmu_context.h
index a7eec910ba6..1f2a8f9c926 100644
--- a/include/asm-generic/mmu_context.h
+++ b/include/asm-generic/mmu_context.h
@@ -42,4 +42,9 @@ static inline void activate_mm(struct mm_struct *prev_mm,
 {
 }
 
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+			struct vm_area_struct *vma)
+{
+}
+
 #endif /* __ASM_GENERIC_MMU_CONTEXT_H */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6e0b286649f..004e9d17b47 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -454,6 +454,10 @@ struct mm_struct {
 	bool tlb_flush_pending;
 #endif
 	struct uprobes_state uprobes_state;
+#ifdef CONFIG_X86_INTEL_MPX
+	/* address of the bounds directory */
+	void __user *bd_addr;
+#endif
 };
 
 static inline void mm_init_cpumask(struct mm_struct *mm)
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 513df75d0fc..89f63503f90 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -179,4 +179,10 @@ struct prctl_mm_map {
 #define PR_SET_THP_DISABLE	41
 #define PR_GET_THP_DISABLE	42
 
+/*
+ * Tell the kernel to start/stop helping userspace manage bounds tables.
+ */
+#define PR_MPX_ENABLE_MANAGEMENT  43
+#define PR_MPX_DISABLE_MANAGEMENT 44
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index 1eaa2f0b024..a8c9f5a7dda 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -91,6 +91,12 @@
 #ifndef SET_TSC_CTL
 # define SET_TSC_CTL(a)		(-EINVAL)
 #endif
+#ifndef MPX_ENABLE_MANAGEMENT
+# define MPX_ENABLE_MANAGEMENT(a)	(-EINVAL)
+#endif
+#ifndef MPX_DISABLE_MANAGEMENT
+# define MPX_DISABLE_MANAGEMENT(a)	(-EINVAL)
+#endif
 
 /*
  * this is where the system-wide overflow UID and GID are defined, for
@@ -2203,6 +2209,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			me->mm->def_flags &= ~VM_NOHUGEPAGE;
 		up_write(&me->mm->mmap_sem);
 		break;
+	case PR_MPX_ENABLE_MANAGEMENT:
+		error = MPX_ENABLE_MANAGEMENT(me);
+		break;
+	case PR_MPX_DISABLE_MANAGEMENT:
+		error = MPX_DISABLE_MANAGEMENT(me);
+		break;
 	default:
 		error = -EINVAL;
 		break;
-- 
cgit v1.2.3-70-g09d2


From 1de4fa14ee25a8edf287855513b61c3945c8878a Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Fri, 14 Nov 2014 07:18:31 -0800
Subject: x86, mpx: Cleanup unused bound tables

The previous patch allocates bounds tables on-demand.  As noted in
an earlier description, these can add up to *HUGE* amounts of
memory.  This has caused OOMs in practice when running tests.

This patch adds support for freeing bounds tables when they are no
longer in use.

There are two types of mappings in play when unmapping tables:
 1. The mapping with the actual data, which userspace is
    munmap()ing or brk()ing away, etc...
 2. The mapping for the bounds table *backing* the data
    (is tagged with VM_MPX, see the patch "add MPX specific
    mmap interface").

If userspace use the prctl() indroduced earlier in this patchset
to enable the management of bounds tables in kernel, when it
unmaps the first type of mapping with the actual data, the kernel
needs to free the mapping for the bounds table backing the data.
This patch hooks in at the very end of do_unmap() to do so.
We look at the addresses being unmapped and find the bounds
directory entries and tables which cover those addresses.  If
an entire table is unused, we clear associated directory entry
and free the table.

Once we unmap the bounds table, we would have a bounds directory
entry pointing at empty address space. That address space might
now be allocated for some other (random) use, and the MPX
hardware might now try to walk it as if it were a bounds table.
That would be bad.  So any unmapping of an enture bounds table
has to be accompanied by a corresponding write to the bounds
directory entry to invalidate it.  That write to the bounds
directory can fault, which causes the following problem:

Since we are doing the freeing from munmap() (and other paths
like it), we hold mmap_sem for write. If we fault, the page
fault handler will attempt to acquire mmap_sem for read and
we will deadlock.  To avoid the deadlock, we pagefault_disable()
when touching the bounds directory entry and use a
get_user_pages() to resolve the fault.

The unmapping of bounds tables happends under vm_munmap().  We
also (indirectly) call vm_munmap() to _do_ the unmapping of the
bounds tables.  We avoid unbounded recursion by disallowing
freeing of bounds tables *for* bounds tables.  This would not
occur normally, so should not have any practical impact.  Being
strict about it here helps ensure that we do not have an
exploitable stack overflow.

Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: linux-mm@kvack.org
Cc: linux-mips@linux-mips.org
Cc: Dave Hansen <dave@sr71.net>
Link: http://lkml.kernel.org/r/20141114151831.E4531C4A@viggo.jf.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/mmu_context.h |   6 +
 arch/x86/include/asm/mpx.h         |  14 ++
 arch/x86/mm/mpx.c                  | 393 +++++++++++++++++++++++++++++++++++++
 include/asm-generic/mmu_context.h  |   6 +
 mm/mmap.c                          |   2 +
 5 files changed, 421 insertions(+)

(limited to 'include')

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 0b0ba91ff1e..00d4575d540 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -109,4 +109,10 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 	mpx_mm_init(mm);
 }
 
+static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
+			      unsigned long start, unsigned long end)
+{
+	mpx_notify_unmap(mm, vma, start, end);
+}
+
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h
index 05eecbf8a48..a952a13d59a 100644
--- a/arch/x86/include/asm/mpx.h
+++ b/arch/x86/include/asm/mpx.h
@@ -51,6 +51,13 @@
 #define MPX_BNDCFG_ADDR_MASK	(~((1UL<<MPX_BNDCFG_TAIL)-1))
 #define MPX_BNDSTA_ERROR_CODE	0x3
 
+#define MPX_BD_ENTRY_MASK	((1<<MPX_BD_ENTRY_OFFSET)-1)
+#define MPX_BT_ENTRY_MASK	((1<<MPX_BT_ENTRY_OFFSET)-1)
+#define MPX_GET_BD_ENTRY_OFFSET(addr)	((((addr)>>(MPX_BT_ENTRY_OFFSET+ \
+		MPX_IGN_BITS)) & MPX_BD_ENTRY_MASK) << MPX_BD_ENTRY_SHIFT)
+#define MPX_GET_BT_ENTRY_OFFSET(addr)	((((addr)>>MPX_IGN_BITS) & \
+		MPX_BT_ENTRY_MASK) << MPX_BT_ENTRY_SHIFT)
+
 #ifdef CONFIG_X86_INTEL_MPX
 siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 				struct xsave_struct *xsave_buf);
@@ -67,6 +74,8 @@ static inline void mpx_mm_init(struct mm_struct *mm)
 	 */
 	mm->bd_addr = MPX_INVALID_BOUNDS_DIR;
 }
+void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long start, unsigned long end);
 #else
 static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 					      struct xsave_struct *xsave_buf)
@@ -84,6 +93,11 @@ static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
 static inline void mpx_mm_init(struct mm_struct *mm)
 {
 }
+static inline void mpx_notify_unmap(struct mm_struct *mm,
+				    struct vm_area_struct *vma,
+				    unsigned long start, unsigned long end)
+{
+}
 #endif /* CONFIG_X86_INTEL_MPX */
 
 #endif /* _ASM_X86_MPX_H */
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 96266375441..f30b48e3a99 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -13,6 +13,7 @@
 #include <asm/i387.h>
 #include <asm/insn.h>
 #include <asm/mman.h>
+#include <asm/mmu_context.h>
 #include <asm/mpx.h>
 #include <asm/processor.h>
 #include <asm/fpu-internal.h>
@@ -26,6 +27,11 @@ static struct vm_operations_struct mpx_vma_ops = {
 	.name = mpx_mapping_name,
 };
 
+static int is_mpx_vma(struct vm_area_struct *vma)
+{
+	return (vma->vm_ops == &mpx_vma_ops);
+}
+
 /*
  * This is really a simplified "vm_mmap". it only handles MPX
  * bounds tables (the bounds directory is user-allocated).
@@ -534,3 +540,390 @@ int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
 	}
 	return 0;
 }
+
+/*
+ * A thin wrapper around get_user_pages().  Returns 0 if the
+ * fault was resolved or -errno if not.
+ */
+static int mpx_resolve_fault(long __user *addr, int write)
+{
+	long gup_ret;
+	int nr_pages = 1;
+	int force = 0;
+
+	gup_ret = get_user_pages(current, current->mm, (unsigned long)addr,
+				 nr_pages, write, force, NULL, NULL);
+	/*
+	 * get_user_pages() returns number of pages gotten.
+	 * 0 means we failed to fault in and get anything,
+	 * probably because 'addr' is bad.
+	 */
+	if (!gup_ret)
+		return -EFAULT;
+	/* Other error, return it */
+	if (gup_ret < 0)
+		return gup_ret;
+	/* must have gup'd a page and gup_ret>0, success */
+	return 0;
+}
+
+/*
+ * Get the base of bounds tables pointed by specific bounds
+ * directory entry.
+ */
+static int get_bt_addr(struct mm_struct *mm,
+			long __user *bd_entry, unsigned long *bt_addr)
+{
+	int ret;
+	int valid_bit;
+
+	if (!access_ok(VERIFY_READ, (bd_entry), sizeof(*bd_entry)))
+		return -EFAULT;
+
+	while (1) {
+		int need_write = 0;
+
+		pagefault_disable();
+		ret = get_user(*bt_addr, bd_entry);
+		pagefault_enable();
+		if (!ret)
+			break;
+		if (ret == -EFAULT)
+			ret = mpx_resolve_fault(bd_entry, need_write);
+		/*
+		 * If we could not resolve the fault, consider it
+		 * userspace's fault and error out.
+		 */
+		if (ret)
+			return ret;
+	}
+
+	valid_bit = *bt_addr & MPX_BD_ENTRY_VALID_FLAG;
+	*bt_addr &= MPX_BT_ADDR_MASK;
+
+	/*
+	 * When the kernel is managing bounds tables, a bounds directory
+	 * entry will either have a valid address (plus the valid bit)
+	 * *OR* be completely empty. If we see a !valid entry *and* some
+	 * data in the address field, we know something is wrong. This
+	 * -EINVAL return will cause a SIGSEGV.
+	 */
+	if (!valid_bit && *bt_addr)
+		return -EINVAL;
+	/*
+	 * Do we have an completely zeroed bt entry?  That is OK.  It
+	 * just means there was no bounds table for this memory.  Make
+	 * sure to distinguish this from -EINVAL, which will cause
+	 * a SEGV.
+	 */
+	if (!valid_bit)
+		return -ENOENT;
+
+	return 0;
+}
+
+/*
+ * Free the backing physical pages of bounds table 'bt_addr'.
+ * Assume start...end is within that bounds table.
+ */
+static int zap_bt_entries(struct mm_struct *mm,
+		unsigned long bt_addr,
+		unsigned long start, unsigned long end)
+{
+	struct vm_area_struct *vma;
+	unsigned long addr, len;
+
+	/*
+	 * Find the first overlapping vma. If vma->vm_start > start, there
+	 * will be a hole in the bounds table. This -EINVAL return will
+	 * cause a SIGSEGV.
+	 */
+	vma = find_vma(mm, start);
+	if (!vma || vma->vm_start > start)
+		return -EINVAL;
+
+	/*
+	 * A NUMA policy on a VM_MPX VMA could cause this bouds table to
+	 * be split. So we need to look across the entire 'start -> end'
+	 * range of this bounds table, find all of the VM_MPX VMAs, and
+	 * zap only those.
+	 */
+	addr = start;
+	while (vma && vma->vm_start < end) {
+		/*
+		 * We followed a bounds directory entry down
+		 * here.  If we find a non-MPX VMA, that's bad,
+		 * so stop immediately and return an error.  This
+		 * probably results in a SIGSEGV.
+		 */
+		if (!is_mpx_vma(vma))
+			return -EINVAL;
+
+		len = min(vma->vm_end, end) - addr;
+		zap_page_range(vma, addr, len, NULL);
+
+		vma = vma->vm_next;
+		addr = vma->vm_start;
+	}
+
+	return 0;
+}
+
+static int unmap_single_bt(struct mm_struct *mm,
+		long __user *bd_entry, unsigned long bt_addr)
+{
+	unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
+	unsigned long actual_old_val = 0;
+	int ret;
+
+	while (1) {
+		int need_write = 1;
+
+		pagefault_disable();
+		ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
+						   expected_old_val, 0);
+		pagefault_enable();
+		if (!ret)
+			break;
+		if (ret == -EFAULT)
+			ret = mpx_resolve_fault(bd_entry, need_write);
+		/*
+		 * If we could not resolve the fault, consider it
+		 * userspace's fault and error out.
+		 */
+		if (ret)
+			return ret;
+	}
+	/*
+	 * The cmpxchg was performed, check the results.
+	 */
+	if (actual_old_val != expected_old_val) {
+		/*
+		 * Someone else raced with us to unmap the table.
+		 * There was no bounds table pointed to by the
+		 * directory, so declare success.  Somebody freed
+		 * it.
+		 */
+		if (!actual_old_val)
+			return 0;
+		/*
+		 * Something messed with the bounds directory
+		 * entry.  We hold mmap_sem for read or write
+		 * here, so it could not be a _new_ bounds table
+		 * that someone just allocated.  Something is
+		 * wrong, so pass up the error and SIGSEGV.
+		 */
+		return -EINVAL;
+	}
+
+	/*
+	 * Note, we are likely being called under do_munmap() already. To
+	 * avoid recursion, do_munmap() will check whether it comes
+	 * from one bounds table through VM_MPX flag.
+	 */
+	return do_munmap(mm, bt_addr, MPX_BT_SIZE_BYTES);
+}
+
+/*
+ * If the bounds table pointed by bounds directory 'bd_entry' is
+ * not shared, unmap this whole bounds table. Otherwise, only free
+ * those backing physical pages of bounds table entries covered
+ * in this virtual address region start...end.
+ */
+static int unmap_shared_bt(struct mm_struct *mm,
+		long __user *bd_entry, unsigned long start,
+		unsigned long end, bool prev_shared, bool next_shared)
+{
+	unsigned long bt_addr;
+	int ret;
+
+	ret = get_bt_addr(mm, bd_entry, &bt_addr);
+	/*
+	 * We could see an "error" ret for not-present bounds
+	 * tables (not really an error), or actual errors, but
+	 * stop unmapping either way.
+	 */
+	if (ret)
+		return ret;
+
+	if (prev_shared && next_shared)
+		ret = zap_bt_entries(mm, bt_addr,
+				bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
+				bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
+	else if (prev_shared)
+		ret = zap_bt_entries(mm, bt_addr,
+				bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
+				bt_addr+MPX_BT_SIZE_BYTES);
+	else if (next_shared)
+		ret = zap_bt_entries(mm, bt_addr, bt_addr,
+				bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
+	else
+		ret = unmap_single_bt(mm, bd_entry, bt_addr);
+
+	return ret;
+}
+
+/*
+ * A virtual address region being munmap()ed might share bounds table
+ * with adjacent VMAs. We only need to free the backing physical
+ * memory of these shared bounds tables entries covered in this virtual
+ * address region.
+ */
+static int unmap_edge_bts(struct mm_struct *mm,
+		unsigned long start, unsigned long end)
+{
+	int ret;
+	long __user *bde_start, *bde_end;
+	struct vm_area_struct *prev, *next;
+	bool prev_shared = false, next_shared = false;
+
+	bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
+	bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
+
+	/*
+	 * Check whether bde_start and bde_end are shared with adjacent
+	 * VMAs.
+	 *
+	 * We already unliked the VMAs from the mm's rbtree so 'start'
+	 * is guaranteed to be in a hole. This gets us the first VMA
+	 * before the hole in to 'prev' and the next VMA after the hole
+	 * in to 'next'.
+	 */
+	next = find_vma_prev(mm, start, &prev);
+	if (prev && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(prev->vm_end-1))
+			== bde_start)
+		prev_shared = true;
+	if (next && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(next->vm_start))
+			== bde_end)
+		next_shared = true;
+
+	/*
+	 * This virtual address region being munmap()ed is only
+	 * covered by one bounds table.
+	 *
+	 * In this case, if this table is also shared with adjacent
+	 * VMAs, only part of the backing physical memory of the bounds
+	 * table need be freeed. Otherwise the whole bounds table need
+	 * be unmapped.
+	 */
+	if (bde_start == bde_end) {
+		return unmap_shared_bt(mm, bde_start, start, end,
+				prev_shared, next_shared);
+	}
+
+	/*
+	 * If more than one bounds tables are covered in this virtual
+	 * address region being munmap()ed, we need to separately check
+	 * whether bde_start and bde_end are shared with adjacent VMAs.
+	 */
+	ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false);
+	if (ret)
+		return ret;
+	ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int mpx_unmap_tables(struct mm_struct *mm,
+		unsigned long start, unsigned long end)
+{
+	int ret;
+	long __user *bd_entry, *bde_start, *bde_end;
+	unsigned long bt_addr;
+
+	/*
+	 * "Edge" bounds tables are those which are being used by the region
+	 * (start -> end), but that may be shared with adjacent areas.  If they
+	 * turn out to be completely unshared, they will be freed.  If they are
+	 * shared, we will free the backing store (like an MADV_DONTNEED) for
+	 * areas used by this region.
+	 */
+	ret = unmap_edge_bts(mm, start, end);
+	switch (ret) {
+		/* non-present tables are OK */
+		case 0:
+		case -ENOENT:
+			/* Success, or no tables to unmap */
+			break;
+		case -EINVAL:
+		case -EFAULT:
+		default:
+			return ret;
+	}
+
+	/*
+	 * Only unmap the bounds table that are
+	 *   1. fully covered
+	 *   2. not at the edges of the mapping, even if full aligned
+	 */
+	bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
+	bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
+	for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) {
+		ret = get_bt_addr(mm, bd_entry, &bt_addr);
+		switch (ret) {
+			case 0:
+				break;
+			case -ENOENT:
+				/* No table here, try the next one */
+				continue;
+			case -EINVAL:
+			case -EFAULT:
+			default:
+				/*
+				 * Note: we are being strict here.
+				 * Any time we run in to an issue
+				 * unmapping tables, we stop and
+				 * SIGSEGV.
+				 */
+				return ret;
+		}
+
+		ret = unmap_single_bt(mm, bd_entry, bt_addr);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * Free unused bounds tables covered in a virtual address region being
+ * munmap()ed. Assume end > start.
+ *
+ * This function will be called by do_munmap(), and the VMAs covering
+ * the virtual address region start...end have already been split if
+ * necessary, and the 'vma' is the first vma in this range (start -> end).
+ */
+void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long start, unsigned long end)
+{
+	int ret;
+
+	/*
+	 * Refuse to do anything unless userspace has asked
+	 * the kernel to help manage the bounds tables,
+	 */
+	if (!kernel_managing_mpx_tables(current->mm))
+		return;
+	/*
+	 * This will look across the entire 'start -> end' range,
+	 * and find all of the non-VM_MPX VMAs.
+	 *
+	 * To avoid recursion, if a VM_MPX vma is found in the range
+	 * (start->end), we will not continue follow-up work. This
+	 * recursion represents having bounds tables for bounds tables,
+	 * which should not occur normally. Being strict about it here
+	 * helps ensure that we do not have an exploitable stack overflow.
+	 */
+	do {
+		if (vma->vm_flags & VM_MPX)
+			return;
+		vma = vma->vm_next;
+	} while (vma && vma->vm_start < end);
+
+	ret = mpx_unmap_tables(mm, start, end);
+	if (ret)
+		force_sig(SIGSEGV, current);
+}
diff --git a/include/asm-generic/mmu_context.h b/include/asm-generic/mmu_context.h
index 1f2a8f9c926..aa2d8ba35b2 100644
--- a/include/asm-generic/mmu_context.h
+++ b/include/asm-generic/mmu_context.h
@@ -47,4 +47,10 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 {
 }
 
+static inline void arch_unmap(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+}
+
 #endif /* __ASM_GENERIC_MMU_CONTEXT_H */
diff --git a/mm/mmap.c b/mm/mmap.c
index 87e82b38453..814762c1563 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2597,6 +2597,8 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 	detach_vmas_to_be_unmapped(mm, vma, prev, end);
 	unmap_region(mm, vma, prev, start, end);
 
+	arch_unmap(mm, vma, start, end);
+
 	/* Fix up all other VM information */
 	remove_vma_list(mm, vma);
 
-- 
cgit v1.2.3-70-g09d2


From 00e7c295968d74f4dbb00aef8334fafe788e3c89 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 14 Nov 2014 08:41:32 +0100
Subject: PM / Domains: Move struct pm_domain_data to pm_domain.h

The definition of the struct pm_domain_data better belongs in the
header for the PM domains, let's move it there.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h        | 6 +-----
 include/linux/pm_domain.h | 5 +++++
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index 383fd68aaee..45e3e78c1e3 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -538,11 +538,7 @@ enum rpm_request {
 };
 
 struct wakeup_source;
-
-struct pm_domain_data {
-	struct list_head list_node;
-	struct device *dev;
-};
+struct pm_domain_data;
 
 struct pm_subsys_data {
 	spinlock_t lock;
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 73e938b7e93..86689b59ce5 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -98,6 +98,11 @@ struct gpd_timing_data {
 	bool cached_stop_ok;
 };
 
+struct pm_domain_data {
+	struct list_head list_node;
+	struct device *dev;
+};
+
 struct generic_pm_domain_data {
 	struct pm_domain_data base;
 	struct gpd_timing_data td;
-- 
cgit v1.2.3-70-g09d2


From 38da1703060a520e69b00405f9bdf765d1396cd0 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Mon, 17 Nov 2014 20:52:20 +0200
Subject: Bluetooth: Use shorter "rand" name for "randomizer"

The common short form of "randomizer" is "rand" in many places
(including the Bluetooth specification). The shorter version also makes
for easier to read code with less forced line breaks. This patch renames
all occurences of "randomizer" to "rand" in the Bluetooth subsystem
code.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h      | 12 ++++++------
 include/net/bluetooth/hci_core.h | 14 +++++++-------
 include/net/bluetooth/mgmt.h     | 12 ++++++------
 net/bluetooth/hci_core.c         | 14 +++++++-------
 net/bluetooth/hci_event.c        | 17 +++++++----------
 net/bluetooth/mgmt.c             | 23 +++++++++--------------
 6 files changed, 42 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index d5f85d7746b..e56f9099f8e 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -639,7 +639,7 @@ struct hci_cp_user_passkey_reply {
 struct hci_cp_remote_oob_data_reply {
 	bdaddr_t bdaddr;
 	__u8     hash[16];
-	__u8     randomizer[16];
+	__u8     rand[16];
 } __packed;
 
 #define HCI_OP_REMOTE_OOB_DATA_NEG_REPLY	0x0433
@@ -731,9 +731,9 @@ struct hci_rp_set_csb {
 struct hci_cp_remote_oob_ext_data_reply {
 	bdaddr_t bdaddr;
 	__u8     hash192[16];
-	__u8     randomizer192[16];
+	__u8     rand192[16];
 	__u8     hash256[16];
-	__u8     randomizer256[16];
+	__u8     rand256[16];
 } __packed;
 
 #define HCI_OP_SNIFF_MODE		0x0803
@@ -940,7 +940,7 @@ struct hci_cp_write_ssp_mode {
 struct hci_rp_read_local_oob_data {
 	__u8     status;
 	__u8     hash[16];
-	__u8     randomizer[16];
+	__u8     rand[16];
 } __packed;
 
 #define HCI_OP_READ_INQ_RSP_TX_POWER	0x0c58
@@ -1024,9 +1024,9 @@ struct hci_cp_write_sc_support {
 struct hci_rp_read_local_oob_ext_data {
 	__u8     status;
 	__u8     hash192[16];
-	__u8     randomizer192[16];
+	__u8     rand192[16];
 	__u8     hash256[16];
-	__u8     randomizer256[16];
+	__u8     rand256[16];
 } __packed;
 
 #define HCI_OP_READ_LOCAL_VERSION	0x1001
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index fe2d5f299e1..a805b3d97c0 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -140,9 +140,9 @@ struct oob_data {
 	struct list_head list;
 	bdaddr_t bdaddr;
 	u8 hash192[16];
-	u8 randomizer192[16];
+	u8 rand192[16];
 	u8 hash256[16];
-	u8 randomizer256[16];
+	u8 rand256[16];
 };
 
 #define HCI_MAX_SHORT_NAME_LENGTH	10
@@ -943,10 +943,10 @@ void hci_remote_oob_data_clear(struct hci_dev *hdev);
 struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev,
 					  bdaddr_t *bdaddr);
 int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
-			    u8 *hash, u8 *randomizer);
+			    u8 *hash, u8 *rand);
 int hci_add_remote_oob_ext_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
-				u8 *hash192, u8 *randomizer192,
-				u8 *hash256, u8 *randomizer256);
+				u8 *hash192, u8 *rand192,
+				u8 *hash256, u8 *rand256);
 int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr);
 
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb);
@@ -1374,8 +1374,8 @@ void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
 				    u8 status);
 void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status);
 void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192,
-				       u8 *randomizer192, u8 *hash256,
-				       u8 *randomizer256, u8 status);
+				       u8 *rand192, u8 *hash256, u8 *rand256,
+				       u8 status);
 void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		       u8 addr_type, u8 *dev_class, s8 rssi, u32 flags,
 		       u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len);
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 414cd2f9a43..b391fd66346 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -299,28 +299,28 @@ struct mgmt_cp_user_passkey_neg_reply {
 #define MGMT_READ_LOCAL_OOB_DATA_SIZE	0
 struct mgmt_rp_read_local_oob_data {
 	__u8	hash[16];
-	__u8	randomizer[16];
+	__u8	rand[16];
 } __packed;
 struct mgmt_rp_read_local_oob_ext_data {
 	__u8	hash192[16];
-	__u8	randomizer192[16];
+	__u8	rand192[16];
 	__u8	hash256[16];
-	__u8	randomizer256[16];
+	__u8	rand256[16];
 } __packed;
 
 #define MGMT_OP_ADD_REMOTE_OOB_DATA	0x0021
 struct mgmt_cp_add_remote_oob_data {
 	struct mgmt_addr_info addr;
 	__u8	hash[16];
-	__u8	randomizer[16];
+	__u8	rand[16];
 } __packed;
 #define MGMT_ADD_REMOTE_OOB_DATA_SIZE	(MGMT_ADDR_INFO_SIZE + 32)
 struct mgmt_cp_add_remote_oob_ext_data {
 	struct mgmt_addr_info addr;
 	__u8	hash192[16];
-	__u8	randomizer192[16];
+	__u8	rand192[16];
 	__u8	hash256[16];
-	__u8	randomizer256[16];
+	__u8	rand256[16];
 } __packed;
 #define MGMT_ADD_REMOTE_OOB_EXT_DATA_SIZE (MGMT_ADDR_INFO_SIZE + 64)
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 90ea0b7670d..bbefb4eea36 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3469,7 +3469,7 @@ void hci_remote_oob_data_clear(struct hci_dev *hdev)
 }
 
 int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
-			    u8 *hash, u8 *randomizer)
+			    u8 *hash, u8 *rand)
 {
 	struct oob_data *data;
 
@@ -3484,10 +3484,10 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	}
 
 	memcpy(data->hash192, hash, sizeof(data->hash192));
-	memcpy(data->randomizer192, randomizer, sizeof(data->randomizer192));
+	memcpy(data->rand192, rand, sizeof(data->rand192));
 
 	memset(data->hash256, 0, sizeof(data->hash256));
-	memset(data->randomizer256, 0, sizeof(data->randomizer256));
+	memset(data->rand256, 0, sizeof(data->rand256));
 
 	BT_DBG("%s for %pMR", hdev->name, bdaddr);
 
@@ -3495,8 +3495,8 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
 }
 
 int hci_add_remote_oob_ext_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
-				u8 *hash192, u8 *randomizer192,
-				u8 *hash256, u8 *randomizer256)
+				u8 *hash192, u8 *rand192,
+				u8 *hash256, u8 *rand256)
 {
 	struct oob_data *data;
 
@@ -3511,10 +3511,10 @@ int hci_add_remote_oob_ext_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	}
 
 	memcpy(data->hash192, hash192, sizeof(data->hash192));
-	memcpy(data->randomizer192, randomizer192, sizeof(data->randomizer192));
+	memcpy(data->rand192, rand192, sizeof(data->rand192));
 
 	memcpy(data->hash256, hash256, sizeof(data->hash256));
-	memcpy(data->randomizer256, randomizer256, sizeof(data->randomizer256));
+	memcpy(data->rand256, rand256, sizeof(data->rand256));
 
 	BT_DBG("%s for %pMR", hdev->name, bdaddr);
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 09d76547d98..844f7d1ff1c 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -994,8 +994,8 @@ static void hci_cc_read_local_oob_data(struct hci_dev *hdev,
 	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
 
 	hci_dev_lock(hdev);
-	mgmt_read_local_oob_data_complete(hdev, rp->hash, rp->randomizer,
-					  NULL, NULL, rp->status);
+	mgmt_read_local_oob_data_complete(hdev, rp->hash, rp->rand, NULL, NULL,
+					  rp->status);
 	hci_dev_unlock(hdev);
 }
 
@@ -1007,8 +1007,8 @@ static void hci_cc_read_local_oob_ext_data(struct hci_dev *hdev,
 	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
 
 	hci_dev_lock(hdev);
-	mgmt_read_local_oob_data_complete(hdev, rp->hash192, rp->randomizer192,
-					  rp->hash256, rp->randomizer256,
+	mgmt_read_local_oob_data_complete(hdev, rp->hash192, rp->rand192,
+					  rp->hash256, rp->rand256,
 					  rp->status);
 	hci_dev_unlock(hdev);
 }
@@ -3996,11 +3996,9 @@ static void hci_remote_oob_data_request_evt(struct hci_dev *hdev,
 
 			bacpy(&cp.bdaddr, &ev->bdaddr);
 			memcpy(cp.hash192, data->hash192, sizeof(cp.hash192));
-			memcpy(cp.randomizer192, data->randomizer192,
-			       sizeof(cp.randomizer192));
+			memcpy(cp.rand192, data->rand192, sizeof(cp.rand192));
 			memcpy(cp.hash256, data->hash256, sizeof(cp.hash256));
-			memcpy(cp.randomizer256, data->randomizer256,
-			       sizeof(cp.randomizer256));
+			memcpy(cp.rand256, data->rand256, sizeof(cp.rand256));
 
 			hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_EXT_DATA_REPLY,
 				     sizeof(cp), &cp);
@@ -4009,8 +4007,7 @@ static void hci_remote_oob_data_request_evt(struct hci_dev *hdev,
 
 			bacpy(&cp.bdaddr, &ev->bdaddr);
 			memcpy(cp.hash, data->hash192, sizeof(cp.hash));
-			memcpy(cp.randomizer, data->randomizer192,
-			       sizeof(cp.randomizer));
+			memcpy(cp.rand, data->rand192, sizeof(cp.rand));
 
 			hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_REPLY,
 				     sizeof(cp), &cp);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 258c9826e78..cbeef5f62f3 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3598,7 +3598,7 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
 		}
 
 		err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr,
-					      cp->hash, cp->randomizer);
+					      cp->hash, cp->rand);
 		if (err < 0)
 			status = MGMT_STATUS_FAILED;
 		else
@@ -3619,10 +3619,8 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
 		}
 
 		err = hci_add_remote_oob_ext_data(hdev, &cp->addr.bdaddr,
-						  cp->hash192,
-						  cp->randomizer192,
-						  cp->hash256,
-						  cp->randomizer256);
+						  cp->hash192, cp->rand192,
+						  cp->hash256, cp->rand256);
 		if (err < 0)
 			status = MGMT_STATUS_FAILED;
 		else
@@ -6771,8 +6769,8 @@ void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status)
 }
 
 void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192,
-				       u8 *randomizer192, u8 *hash256,
-				       u8 *randomizer256, u8 status)
+				       u8 *rand192, u8 *hash256, u8 *rand256,
+				       u8 status)
 {
 	struct pending_cmd *cmd;
 
@@ -6787,16 +6785,14 @@ void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192,
 			   mgmt_status(status));
 	} else {
 		if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags) &&
-		    hash256 && randomizer256) {
+		    hash256 && rand256) {
 			struct mgmt_rp_read_local_oob_ext_data rp;
 
 			memcpy(rp.hash192, hash192, sizeof(rp.hash192));
-			memcpy(rp.randomizer192, randomizer192,
-			       sizeof(rp.randomizer192));
+			memcpy(rp.rand192, rand192, sizeof(rp.rand192));
 
 			memcpy(rp.hash256, hash256, sizeof(rp.hash256));
-			memcpy(rp.randomizer256, randomizer256,
-			       sizeof(rp.randomizer256));
+			memcpy(rp.rand256, rand256, sizeof(rp.rand256));
 
 			cmd_complete(cmd->sk, hdev->id,
 				     MGMT_OP_READ_LOCAL_OOB_DATA, 0,
@@ -6805,8 +6801,7 @@ void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192,
 			struct mgmt_rp_read_local_oob_data rp;
 
 			memcpy(rp.hash, hash192, sizeof(rp.hash));
-			memcpy(rp.randomizer, randomizer192,
-			       sizeof(rp.randomizer));
+			memcpy(rp.rand, rand192, sizeof(rp.rand));
 
 			cmd_complete(cmd->sk, hdev->id,
 				     MGMT_OP_READ_LOCAL_OOB_DATA, 0,
-- 
cgit v1.2.3-70-g09d2


From c9cd2ce2bc6313aafa33f8e28d29a8690252f219 Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Wed, 5 Nov 2014 17:01:15 +0200
Subject: integrity: provide a hook to load keys when rootfs is ready

Keys can only be loaded once the rootfs is mounted. Initcalls
are not suitable for that. This patch defines a special hook
to load the x509 public keys onto the IMA keyring, before
attempting to access any file. The keys are required for
verifying the file's signature. The hook is called after the
root filesystem is mounted and before the kernel calls 'init'.

Changes in v3:
* added more explanation to the patch description (Mimi)

Changes in v2:
* Hook renamed as 'integrity_load_keys()' to handle both IMA and EVM
  keys by integrity subsystem.
* Hook patch moved after defining loading functions

Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 include/linux/integrity.h |  6 ++++++
 init/main.c               |  6 +++++-
 security/integrity/iint.c | 11 +++++++++++
 3 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/integrity.h b/include/linux/integrity.h
index 83222cebd47..c2d6082a1a4 100644
--- a/include/linux/integrity.h
+++ b/include/linux/integrity.h
@@ -24,6 +24,7 @@ enum integrity_status {
 #ifdef CONFIG_INTEGRITY
 extern struct integrity_iint_cache *integrity_inode_get(struct inode *inode);
 extern void integrity_inode_free(struct inode *inode);
+extern void __init integrity_load_keys(void);
 
 #else
 static inline struct integrity_iint_cache *
@@ -36,5 +37,10 @@ static inline void integrity_inode_free(struct inode *inode)
 {
 	return;
 }
+
+static inline void integrity_load_keys(void)
+{
+}
 #endif /* CONFIG_INTEGRITY */
+
 #endif /* _LINUX_INTEGRITY_H */
diff --git a/init/main.c b/init/main.c
index e8ae1fef090..2c1928d08b7 100644
--- a/init/main.c
+++ b/init/main.c
@@ -78,6 +78,7 @@
 #include <linux/context_tracking.h>
 #include <linux/random.h>
 #include <linux/list.h>
+#include <linux/integrity.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -1026,8 +1027,11 @@ static noinline void __init kernel_init_freeable(void)
 	 * Ok, we have completed the initial bootup, and
 	 * we're essentially up and running. Get rid of the
 	 * initmem segments and start the user-mode stuff..
+	 *
+	 * rootfs is available now, try loading the public keys
+	 * and default modules
 	 */
 
-	/* rootfs is available now, try loading default modules */
+	integrity_load_keys();
 	load_default_modules();
 }
diff --git a/security/integrity/iint.c b/security/integrity/iint.c
index dbee618526b..df45640fbac 100644
--- a/security/integrity/iint.c
+++ b/security/integrity/iint.c
@@ -245,3 +245,14 @@ out:
 	fput(file);
 	return rc;
 }
+
+/*
+ * integrity_load_keys - load integrity keys hook
+ *
+ * Hooks is called from init/main.c:kernel_init_freeable()
+ * when rootfs is ready
+ */
+void __init integrity_load_keys(void)
+{
+	ima_load_x509();
+}
-- 
cgit v1.2.3-70-g09d2


From 6fb5032ebb1c5b852461d64ee33829081de8ca61 Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Wed, 5 Nov 2014 17:01:17 +0200
Subject: VFS: refactor vfs_read()

integrity_kernel_read() duplicates the file read operations code
in vfs_read(). This patch refactors vfs_read() code creating a
helper function __vfs_read(). It is used by both vfs_read() and
integrity_kernel_read().

Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 fs/read_write.c           | 24 ++++++++++++++++++------
 include/linux/fs.h        |  1 +
 security/integrity/iint.c | 10 +++-------
 3 files changed, 22 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/read_write.c b/fs/read_write.c
index 009d8542a88..f45b2ae5d5f 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -412,6 +412,23 @@ ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *p
 
 EXPORT_SYMBOL(new_sync_read);
 
+ssize_t __vfs_read(struct file *file, char __user *buf, size_t count,
+		   loff_t *pos)
+{
+	ssize_t ret;
+
+	if (file->f_op->read)
+		ret = file->f_op->read(file, buf, count, pos);
+	else if (file->f_op->aio_read)
+		ret = do_sync_read(file, buf, count, pos);
+	else if (file->f_op->read_iter)
+		ret = new_sync_read(file, buf, count, pos);
+	else
+		ret = -EINVAL;
+
+	return ret;
+}
+
 ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
 {
 	ssize_t ret;
@@ -426,12 +443,7 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
 	ret = rw_verify_area(READ, file, pos, count);
 	if (ret >= 0) {
 		count = ret;
-		if (file->f_op->read)
-			ret = file->f_op->read(file, buf, count, pos);
-		else if (file->f_op->aio_read)
-			ret = do_sync_read(file, buf, count, pos);
-		else
-			ret = new_sync_read(file, buf, count, pos);
+		ret = __vfs_read(file, buf, count, pos);
 		if (ret > 0) {
 			fsnotify_access(file);
 			add_rchar(current, ret);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e11d60cc867..ac3a36e05da 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1527,6 +1527,7 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			      struct iovec *fast_pointer,
 			      struct iovec **ret_pointer);
 
+extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
diff --git a/security/integrity/iint.c b/security/integrity/iint.c
index df45640fbac..dbb6d141c3d 100644
--- a/security/integrity/iint.c
+++ b/security/integrity/iint.c
@@ -184,20 +184,16 @@ int integrity_kernel_read(struct file *file, loff_t offset,
 {
 	mm_segment_t old_fs;
 	char __user *buf = (char __user *)addr;
-	ssize_t ret = -EINVAL;
+	ssize_t ret;
 
 	if (!(file->f_mode & FMODE_READ))
 		return -EBADF;
 
 	old_fs = get_fs();
 	set_fs(get_ds());
-	if (file->f_op->read)
-		ret = file->f_op->read(file, buf, count, &offset);
-	else if (file->f_op->aio_read)
-		ret = do_sync_read(file, buf, count, &offset);
-	else if (file->f_op->read_iter)
-		ret = new_sync_read(file, buf, count, &offset);
+	ret = __vfs_read(file, buf, count, &offset);
 	set_fs(old_fs);
+
 	return ret;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 7d172cc89b8589e4173d0c73a1ddaae408f29c9d Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 18 Nov 2014 02:49:51 -0500
Subject: cgroup: add cgroup_subsys->css_released()

Add a new cgroup subsys callback css_released().  This is called when
the reference count of the css (cgroup_subsys_state) reaches zero
before RCU scheduling free.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Zefan Li <lizefan@huawei.com>
---
 include/linux/cgroup.h | 1 +
 kernel/cgroup.c        | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 1d519688904..e717a39f22e 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -612,6 +612,7 @@ struct cgroup_subsys {
 	struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css);
 	int (*css_online)(struct cgroup_subsys_state *css);
 	void (*css_offline)(struct cgroup_subsys_state *css);
+	void (*css_released)(struct cgroup_subsys_state *css);
 	void (*css_free)(struct cgroup_subsys_state *css);
 	void (*css_reset)(struct cgroup_subsys_state *css);
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index dffa54041d4..c8558693102 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4380,6 +4380,8 @@ static void css_release_work_fn(struct work_struct *work)
 	if (ss) {
 		/* css release path */
 		cgroup_idr_remove(&ss->css_idr, css->id);
+		if (ss->css_released)
+			ss->css_released(css);
 	} else {
 		/* cgroup release path */
 		cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
-- 
cgit v1.2.3-70-g09d2


From 56c807ba4e91f0980567b6a69de239677879b17f Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 18 Nov 2014 02:49:51 -0500
Subject: cgroup: add cgroup_subsys->css_e_css_changed()

Add a new cgroup_subsys operatoin ->css_e_css_changed().  This is
invoked if any of the effective csses seen from the css's cgroup may
have changed.  This will be used to implement cgroup writeback
support.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Zefan Li <lizefan@huawei.com>
---
 include/linux/cgroup.h |  1 +
 kernel/cgroup.c        | 18 ++++++++++++++++++
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index e717a39f22e..3a04aeb8b5a 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -615,6 +615,7 @@ struct cgroup_subsys {
 	void (*css_released)(struct cgroup_subsys_state *css);
 	void (*css_free)(struct cgroup_subsys_state *css);
 	void (*css_reset)(struct cgroup_subsys_state *css);
+	void (*css_e_css_changed)(struct cgroup_subsys_state *css);
 
 	int (*can_attach)(struct cgroup_subsys_state *css,
 			  struct cgroup_taskset *tset);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c8558693102..69f033582a1 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2836,6 +2836,24 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
 		}
 	}
 
+	/*
+	 * The effective csses of all the descendants (excluding @cgrp) may
+	 * have changed.  Subsystems can optionally subscribe to this event
+	 * by implementing ->css_e_css_changed() which is invoked if any of
+	 * the effective csses seen from the css's cgroup may have changed.
+	 */
+	for_each_subsys(ss, ssid) {
+		struct cgroup_subsys_state *this_css = cgroup_css(cgrp, ss);
+		struct cgroup_subsys_state *css;
+
+		if (!ss->css_e_css_changed || !this_css)
+			continue;
+
+		css_for_each_descendant_pre(css, this_css)
+			if (css != this_css)
+				ss->css_e_css_changed(css);
+	}
+
 	kernfs_activate(cgrp->kn);
 	ret = 0;
 out_unlock:
-- 
cgit v1.2.3-70-g09d2


From eeecbd1971517103e06f11750dd1a9a1dc37e4e6 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 18 Nov 2014 02:49:52 -0500
Subject: cgroup: implement cgroup_get_e_css()

Implement cgroup_get_e_css() which finds and gets the effective css
for the specified cgroup and subsystem combination.  This function
always returns a valid pinned css.  This will be used by cgroup
writeback support.

While at it, add comment to cgroup_e_css() to explain why that
function is different from cgroup_get_e_css() and has to test
cgrp->child_subsys_mask instead of cgroup_css(cgrp, ss).

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Zefan Li <lizefan@huawei.com>
---
 include/linux/cgroup.h |  2 ++
 kernel/cgroup.c        | 37 +++++++++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 3a04aeb8b5a..9fd99f5e699 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -910,6 +910,8 @@ void css_task_iter_end(struct css_task_iter *it);
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 
+struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup,
+					     struct cgroup_subsys *ss);
 struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 						       struct cgroup_subsys *ss);
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 69f033582a1..bb263d0caab 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -277,6 +277,10 @@ static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
 	if (!(cgrp->root->subsys_mask & (1 << ss->id)))
 		return NULL;
 
+	/*
+	 * This function is used while updating css associations and thus
+	 * can't test the csses directly.  Use ->child_subsys_mask.
+	 */
 	while (cgroup_parent(cgrp) &&
 	       !(cgroup_parent(cgrp)->child_subsys_mask & (1 << ss->id)))
 		cgrp = cgroup_parent(cgrp);
@@ -284,6 +288,39 @@ static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
 	return cgroup_css(cgrp, ss);
 }
 
+/**
+ * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem
+ * @cgrp: the cgroup of interest
+ * @ss: the subsystem of interest
+ *
+ * Find and get the effective css of @cgrp for @ss.  The effective css is
+ * defined as the matching css of the nearest ancestor including self which
+ * has @ss enabled.  If @ss is not mounted on the hierarchy @cgrp is on,
+ * the root css is returned, so this function always returns a valid css.
+ * The returned css must be put using css_put().
+ */
+struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp,
+					     struct cgroup_subsys *ss)
+{
+	struct cgroup_subsys_state *css;
+
+	rcu_read_lock();
+
+	do {
+		css = cgroup_css(cgrp, ss);
+
+		if (css && css_tryget_online(css))
+			goto out_unlock;
+		cgrp = cgroup_parent(cgrp);
+	} while (cgrp);
+
+	css = init_css_set.subsys[ss->id];
+	css_get(css);
+out_unlock:
+	rcu_read_unlock();
+	return css;
+}
+
 /* convenient tests for these bits */
 static inline bool cgroup_is_dead(const struct cgroup *cgrp)
 {
-- 
cgit v1.2.3-70-g09d2


From c2a0b538d2c778aef7bf2fbe7973229192c9a392 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Sun, 9 Nov 2014 22:47:56 +0800
Subject: iommu/vt-d: Introduce helper function dmar_walk_resources()

Introduce helper function dmar_walk_resources to walk resource entries
in DMAR table and ACPI buffer object returned by ACPI _DSM method
for IOMMU hot-plug.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/dmar.c        | 209 +++++++++++++++++++++++---------------------
 drivers/iommu/intel-iommu.c |   4 +-
 include/linux/dmar.h        |  19 ++--
 3 files changed, 122 insertions(+), 110 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index c5c61cabd6e..586dd2aa2ca 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -44,6 +44,14 @@
 
 #include "irq_remapping.h"
 
+typedef int (*dmar_res_handler_t)(struct acpi_dmar_header *, void *);
+struct dmar_res_callback {
+	dmar_res_handler_t	cb[ACPI_DMAR_TYPE_RESERVED];
+	void			*arg[ACPI_DMAR_TYPE_RESERVED];
+	bool			ignore_unhandled;
+	bool			print_entry;
+};
+
 /*
  * Assumptions:
  * 1) The hotplug framework guarentees that DMAR unit will be hot-added
@@ -350,7 +358,7 @@ static struct notifier_block dmar_pci_bus_nb = {
  * present in the platform
  */
 static int __init
-dmar_parse_one_drhd(struct acpi_dmar_header *header)
+dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_hardware_unit *drhd;
 	struct dmar_drhd_unit *dmaru;
@@ -381,6 +389,10 @@ dmar_parse_one_drhd(struct acpi_dmar_header *header)
 		return ret;
 	}
 	dmar_register_drhd_unit(dmaru);
+
+	if (arg)
+		(*(int *)arg)++;
+
 	return 0;
 }
 
@@ -393,7 +405,8 @@ static void dmar_free_drhd(struct dmar_drhd_unit *dmaru)
 	kfree(dmaru);
 }
 
-static int __init dmar_parse_one_andd(struct acpi_dmar_header *header)
+static int __init dmar_parse_one_andd(struct acpi_dmar_header *header,
+				      void *arg)
 {
 	struct acpi_dmar_andd *andd = (void *)header;
 
@@ -415,7 +428,7 @@ static int __init dmar_parse_one_andd(struct acpi_dmar_header *header)
 
 #ifdef CONFIG_ACPI_NUMA
 static int __init
-dmar_parse_one_rhsa(struct acpi_dmar_header *header)
+dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_rhsa *rhsa;
 	struct dmar_drhd_unit *drhd;
@@ -442,6 +455,8 @@ dmar_parse_one_rhsa(struct acpi_dmar_header *header)
 
 	return 0;
 }
+#else
+#define	dmar_parse_one_rhsa		dmar_res_noop
 #endif
 
 static void __init
@@ -503,6 +518,52 @@ static int __init dmar_table_detect(void)
 	return (ACPI_SUCCESS(status) ? 1 : 0);
 }
 
+static int dmar_walk_remapping_entries(struct acpi_dmar_header *start,
+				       size_t len, struct dmar_res_callback *cb)
+{
+	int ret = 0;
+	struct acpi_dmar_header *iter, *next;
+	struct acpi_dmar_header *end = ((void *)start) + len;
+
+	for (iter = start; iter < end && ret == 0; iter = next) {
+		next = (void *)iter + iter->length;
+		if (iter->length == 0) {
+			/* Avoid looping forever on bad ACPI tables */
+			pr_debug(FW_BUG "Invalid 0-length structure\n");
+			break;
+		} else if (next > end) {
+			/* Avoid passing table end */
+			pr_warn(FW_BUG "record passes table end\n");
+			ret = -EINVAL;
+			break;
+		}
+
+		if (cb->print_entry)
+			dmar_table_print_dmar_entry(iter);
+
+		if (iter->type >= ACPI_DMAR_TYPE_RESERVED) {
+			/* continue for forward compatibility */
+			pr_debug("Unknown DMAR structure type %d\n",
+				 iter->type);
+		} else if (cb->cb[iter->type]) {
+			ret = cb->cb[iter->type](iter, cb->arg[iter->type]);
+		} else if (!cb->ignore_unhandled) {
+			pr_warn("No handler for DMAR structure type %d\n",
+				iter->type);
+			ret = -EINVAL;
+		}
+	}
+
+	return ret;
+}
+
+static inline int dmar_walk_dmar_table(struct acpi_table_dmar *dmar,
+				       struct dmar_res_callback *cb)
+{
+	return dmar_walk_remapping_entries((void *)(dmar + 1),
+			dmar->header.length - sizeof(*dmar), cb);
+}
+
 /**
  * parse_dmar_table - parses the DMA reporting table
  */
@@ -510,9 +571,18 @@ static int __init
 parse_dmar_table(void)
 {
 	struct acpi_table_dmar *dmar;
-	struct acpi_dmar_header *entry_header;
 	int ret = 0;
 	int drhd_count = 0;
+	struct dmar_res_callback cb = {
+		.print_entry = true,
+		.ignore_unhandled = true,
+		.arg[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &drhd_count,
+		.cb[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &dmar_parse_one_drhd,
+		.cb[ACPI_DMAR_TYPE_RESERVED_MEMORY] = &dmar_parse_one_rmrr,
+		.cb[ACPI_DMAR_TYPE_ROOT_ATS] = &dmar_parse_one_atsr,
+		.cb[ACPI_DMAR_TYPE_HARDWARE_AFFINITY] = &dmar_parse_one_rhsa,
+		.cb[ACPI_DMAR_TYPE_NAMESPACE] = &dmar_parse_one_andd,
+	};
 
 	/*
 	 * Do it again, earlier dmar_tbl mapping could be mapped with
@@ -536,51 +606,10 @@ parse_dmar_table(void)
 	}
 
 	pr_info("Host address width %d\n", dmar->width + 1);
-
-	entry_header = (struct acpi_dmar_header *)(dmar + 1);
-	while (((unsigned long)entry_header) <
-			(((unsigned long)dmar) + dmar_tbl->length)) {
-		/* Avoid looping forever on bad ACPI tables */
-		if (entry_header->length == 0) {
-			pr_warn("Invalid 0-length structure\n");
-			ret = -EINVAL;
-			break;
-		}
-
-		dmar_table_print_dmar_entry(entry_header);
-
-		switch (entry_header->type) {
-		case ACPI_DMAR_TYPE_HARDWARE_UNIT:
-			drhd_count++;
-			ret = dmar_parse_one_drhd(entry_header);
-			break;
-		case ACPI_DMAR_TYPE_RESERVED_MEMORY:
-			ret = dmar_parse_one_rmrr(entry_header);
-			break;
-		case ACPI_DMAR_TYPE_ROOT_ATS:
-			ret = dmar_parse_one_atsr(entry_header);
-			break;
-		case ACPI_DMAR_TYPE_HARDWARE_AFFINITY:
-#ifdef CONFIG_ACPI_NUMA
-			ret = dmar_parse_one_rhsa(entry_header);
-#endif
-			break;
-		case ACPI_DMAR_TYPE_NAMESPACE:
-			ret = dmar_parse_one_andd(entry_header);
-			break;
-		default:
-			pr_warn("Unknown DMAR structure type %d\n",
-				entry_header->type);
-			ret = 0; /* for forward compatibility */
-			break;
-		}
-		if (ret)
-			break;
-
-		entry_header = ((void *)entry_header + entry_header->length);
-	}
-	if (drhd_count == 0)
+	ret = dmar_walk_dmar_table(dmar, &cb);
+	if (ret == 0 && drhd_count == 0)
 		pr_warn(FW_BUG "No DRHD structure found in DMAR table\n");
+
 	return ret;
 }
 
@@ -778,76 +807,60 @@ static void warn_invalid_dmar(u64 addr, const char *message)
 		dmi_get_system_info(DMI_PRODUCT_VERSION));
 }
 
-static int __init check_zero_address(void)
+static int __ref
+dmar_validate_one_drhd(struct acpi_dmar_header *entry, void *arg)
 {
-	struct acpi_table_dmar *dmar;
-	struct acpi_dmar_header *entry_header;
 	struct acpi_dmar_hardware_unit *drhd;
+	void __iomem *addr;
+	u64 cap, ecap;
 
-	dmar = (struct acpi_table_dmar *)dmar_tbl;
-	entry_header = (struct acpi_dmar_header *)(dmar + 1);
-
-	while (((unsigned long)entry_header) <
-			(((unsigned long)dmar) + dmar_tbl->length)) {
-		/* Avoid looping forever on bad ACPI tables */
-		if (entry_header->length == 0) {
-			pr_warn("Invalid 0-length structure\n");
-			return 0;
-		}
-
-		if (entry_header->type == ACPI_DMAR_TYPE_HARDWARE_UNIT) {
-			void __iomem *addr;
-			u64 cap, ecap;
-
-			drhd = (void *)entry_header;
-			if (!drhd->address) {
-				warn_invalid_dmar(0, "");
-				goto failed;
-			}
+	drhd = (void *)entry;
+	if (!drhd->address) {
+		warn_invalid_dmar(0, "");
+		return -EINVAL;
+	}
 
-			addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
-			if (!addr ) {
-				printk("IOMMU: can't validate: %llx\n", drhd->address);
-				goto failed;
-			}
-			cap = dmar_readq(addr + DMAR_CAP_REG);
-			ecap = dmar_readq(addr + DMAR_ECAP_REG);
-			early_iounmap(addr, VTD_PAGE_SIZE);
-			if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
-				warn_invalid_dmar(drhd->address,
-						  " returns all ones");
-				goto failed;
-			}
-		}
+	addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
+	if (!addr) {
+		pr_warn("IOMMU: can't validate: %llx\n", drhd->address);
+		return -EINVAL;
+	}
+	cap = dmar_readq(addr + DMAR_CAP_REG);
+	ecap = dmar_readq(addr + DMAR_ECAP_REG);
+	early_iounmap(addr, VTD_PAGE_SIZE);
 
-		entry_header = ((void *)entry_header + entry_header->length);
+	if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
+		warn_invalid_dmar(drhd->address, " returns all ones");
+		return -EINVAL;
 	}
-	return 1;
 
-failed:
 	return 0;
 }
 
 int __init detect_intel_iommu(void)
 {
 	int ret;
+	struct dmar_res_callback validate_drhd_cb = {
+		.cb[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &dmar_validate_one_drhd,
+		.ignore_unhandled = true,
+	};
 
 	down_write(&dmar_global_lock);
 	ret = dmar_table_detect();
 	if (ret)
-		ret = check_zero_address();
-	{
-		if (ret && !no_iommu && !iommu_detected && !dmar_disabled) {
-			iommu_detected = 1;
-			/* Make sure ACS will be enabled */
-			pci_request_acs();
-		}
+		ret = !dmar_walk_dmar_table((struct acpi_table_dmar *)dmar_tbl,
+					    &validate_drhd_cb);
+	if (ret && !no_iommu && !iommu_detected && !dmar_disabled) {
+		iommu_detected = 1;
+		/* Make sure ACS will be enabled */
+		pci_request_acs();
+	}
 
 #ifdef CONFIG_X86
-		if (ret)
-			x86_init.iommu.iommu_init = intel_iommu_init;
+	if (ret)
+		x86_init.iommu.iommu_init = intel_iommu_init;
 #endif
-	}
+
 	early_acpi_os_unmap_memory((void __iomem *)dmar_tbl, dmar_tbl_size);
 	dmar_tbl = NULL;
 	up_write(&dmar_global_lock);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index ba0fa2a8d69..b9cc9c2b03f 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3684,7 +3684,7 @@ static inline void init_iommu_pm_ops(void) {}
 #endif	/* CONFIG_PM */
 
 
-int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header)
+int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_reserved_memory *rmrr;
 	struct dmar_rmrr_unit *rmrru;
@@ -3710,7 +3710,7 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header)
 	return 0;
 }
 
-int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr)
+int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr, void *arg)
 {
 	struct acpi_dmar_atsr *atsr;
 	struct dmar_atsr_unit *atsru;
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 593fff99e6b..495df5e48f8 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -121,22 +121,21 @@ extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info,
 extern int detect_intel_iommu(void);
 extern int enable_drhd_fault_handling(void);
 
+static inline int dmar_res_noop(struct acpi_dmar_header *hdr, void *arg)
+{
+	return 0;
+}
+
 #ifdef CONFIG_INTEL_IOMMU
 extern int iommu_detected, no_iommu;
 extern int intel_iommu_init(void);
-extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header);
-extern int dmar_parse_one_atsr(struct acpi_dmar_header *header);
+extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg);
+extern int dmar_parse_one_atsr(struct acpi_dmar_header *header, void *arg);
 extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info);
 #else /* !CONFIG_INTEL_IOMMU: */
 static inline int intel_iommu_init(void) { return -ENODEV; }
-static inline int dmar_parse_one_rmrr(struct acpi_dmar_header *header)
-{
-	return 0;
-}
-static inline int dmar_parse_one_atsr(struct acpi_dmar_header *header)
-{
-	return 0;
-}
+#define	dmar_parse_one_rmrr		dmar_res_noop
+#define	dmar_parse_one_atsr		dmar_res_noop
 static inline int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 {
 	return 0;
-- 
cgit v1.2.3-70-g09d2


From 78d8e7046111425bb688cddc4303d79cb0f0d281 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Sun, 9 Nov 2014 22:47:57 +0800
Subject: iommu/vt-d: Dynamically allocate and free seq_id for DMAR units

Introduce functions to support dynamic IOMMU seq_id allocating and
releasing, which will be used to support DMAR hotplug.

Also rename IOMMU_UNITS_SUPPORTED as DMAR_UNITS_SUPPORTED.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Reviewed-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/dmar.c        | 40 ++++++++++++++++++++++++++++++++++------
 drivers/iommu/intel-iommu.c | 13 +++----------
 include/linux/dmar.h        |  6 ++++++
 3 files changed, 43 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 586dd2aa2ca..78aa1b2af11 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -70,6 +70,7 @@ LIST_HEAD(dmar_drhd_units);
 struct acpi_table_header * __initdata dmar_tbl;
 static acpi_size dmar_tbl_size;
 static int dmar_dev_scope_status = 1;
+static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)];
 
 static int alloc_iommu(struct dmar_drhd_unit *drhd);
 static void free_iommu(struct intel_iommu *iommu);
@@ -944,11 +945,32 @@ out:
 	return err;
 }
 
+static int dmar_alloc_seq_id(struct intel_iommu *iommu)
+{
+	iommu->seq_id = find_first_zero_bit(dmar_seq_ids,
+					    DMAR_UNITS_SUPPORTED);
+	if (iommu->seq_id >= DMAR_UNITS_SUPPORTED) {
+		iommu->seq_id = -1;
+	} else {
+		set_bit(iommu->seq_id, dmar_seq_ids);
+		sprintf(iommu->name, "dmar%d", iommu->seq_id);
+	}
+
+	return iommu->seq_id;
+}
+
+static void dmar_free_seq_id(struct intel_iommu *iommu)
+{
+	if (iommu->seq_id >= 0) {
+		clear_bit(iommu->seq_id, dmar_seq_ids);
+		iommu->seq_id = -1;
+	}
+}
+
 static int alloc_iommu(struct dmar_drhd_unit *drhd)
 {
 	struct intel_iommu *iommu;
 	u32 ver, sts;
-	static int iommu_allocated = 0;
 	int agaw = 0;
 	int msagaw = 0;
 	int err;
@@ -962,13 +984,16 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	if (!iommu)
 		return -ENOMEM;
 
-	iommu->seq_id = iommu_allocated++;
-	sprintf (iommu->name, "dmar%d", iommu->seq_id);
+	if (dmar_alloc_seq_id(iommu) < 0) {
+		pr_err("IOMMU: failed to allocate seq_id\n");
+		err = -ENOSPC;
+		goto error;
+	}
 
 	err = map_iommu(iommu, drhd->reg_base_addr);
 	if (err) {
 		pr_err("IOMMU: failed to map %s\n", iommu->name);
-		goto error;
+		goto error_free_seq_id;
 	}
 
 	err = -EINVAL;
@@ -1018,9 +1043,11 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 
 	return 0;
 
- err_unmap:
+err_unmap:
 	unmap_iommu(iommu);
- error:
+error_free_seq_id:
+	dmar_free_seq_id(iommu);
+error:
 	kfree(iommu);
 	return err;
 }
@@ -1044,6 +1071,7 @@ static void free_iommu(struct intel_iommu *iommu)
 	if (iommu->reg)
 		unmap_iommu(iommu);
 
+	dmar_free_seq_id(iommu);
 	kfree(iommu);
 }
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index b9cc9c2b03f..2779354321f 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -330,17 +330,10 @@ static int hw_pass_through = 1;
 /* si_domain contains mulitple devices */
 #define DOMAIN_FLAG_STATIC_IDENTITY	(1 << 1)
 
-/* define the limit of IOMMUs supported in each domain */
-#ifdef	CONFIG_X86
-# define	IOMMU_UNITS_SUPPORTED	MAX_IO_APICS
-#else
-# define	IOMMU_UNITS_SUPPORTED	64
-#endif
-
 struct dmar_domain {
 	int	id;			/* domain id */
 	int	nid;			/* node id */
-	DECLARE_BITMAP(iommu_bmp, IOMMU_UNITS_SUPPORTED);
+	DECLARE_BITMAP(iommu_bmp, DMAR_UNITS_SUPPORTED);
 					/* bitmap of iommus this domain uses*/
 
 	struct list_head devices; 	/* all devices' list */
@@ -2730,12 +2723,12 @@ static int __init init_dmars(void)
 		 * threaded kernel __init code path all other access are read
 		 * only
 		 */
-		if (g_num_of_iommus < IOMMU_UNITS_SUPPORTED) {
+		if (g_num_of_iommus < DMAR_UNITS_SUPPORTED) {
 			g_num_of_iommus++;
 			continue;
 		}
 		printk_once(KERN_ERR "intel-iommu: exceeded %d IOMMUs\n",
-			  IOMMU_UNITS_SUPPORTED);
+			  DMAR_UNITS_SUPPORTED);
 	}
 
 	g_iommus = kcalloc(g_num_of_iommus, sizeof(struct intel_iommu *),
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 495df5e48f8..725204fc433 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -30,6 +30,12 @@
 
 struct acpi_dmar_header;
 
+#ifdef	CONFIG_X86
+# define	DMAR_UNITS_SUPPORTED	MAX_IO_APICS
+#else
+# define	DMAR_UNITS_SUPPORTED	64
+#endif
+
 /* DMAR Flags */
 #define DMAR_INTR_REMAP		0x1
 #define DMAR_X2APIC_OPT_OUT	0x2
-- 
cgit v1.2.3-70-g09d2


From 6b1972493a84f8fe13ff9d202745590f6c53d670 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Sun, 9 Nov 2014 22:47:58 +0800
Subject: iommu/vt-d: Implement DMAR unit hotplug framework

On Intel platforms, an IO Hub (PCI/PCIe host bridge) may contain DMAR
units, so we need to support DMAR hotplug when supporting PCI host
bridge hotplug on Intel platforms.

According to Section 8.8 "Remapping Hardware Unit Hot Plug" in "Intel
Virtualization Technology for Directed IO Architecture Specification
Rev 2.2", ACPI BIOS should implement ACPI _DSM method under the ACPI
object for the PCI host bridge to support DMAR hotplug.

This patch introduces interfaces to parse ACPI _DSM method for
DMAR unit hotplug. It also implements state machines for DMAR unit
hot-addition and hot-removal.

The PCI host bridge hotplug driver should call dmar_hotplug_hotplug()
before scanning PCI devices connected for hot-addition and after
destroying all PCI devices for hot-removal.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Reviewed-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/dmar.c                | 268 ++++++++++++++++++++++++++++++++++--
 drivers/iommu/intel-iommu.c         |  78 ++++++++++-
 drivers/iommu/intel_irq_remapping.c |   5 +
 include/linux/dmar.h                |  33 +++++
 4 files changed, 370 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 78aa1b2af11..0bd536d769a 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -75,7 +75,7 @@ static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)];
 static int alloc_iommu(struct dmar_drhd_unit *drhd);
 static void free_iommu(struct intel_iommu *iommu);
 
-static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
+static void dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
 {
 	/*
 	 * add INCLUDE_ALL at the tail, so scan the list will find it at
@@ -353,24 +353,45 @@ static struct notifier_block dmar_pci_bus_nb = {
 	.priority = INT_MIN,
 };
 
+static struct dmar_drhd_unit *
+dmar_find_dmaru(struct acpi_dmar_hardware_unit *drhd)
+{
+	struct dmar_drhd_unit *dmaru;
+
+	list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list)
+		if (dmaru->segment == drhd->segment &&
+		    dmaru->reg_base_addr == drhd->address)
+			return dmaru;
+
+	return NULL;
+}
+
 /**
  * dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition
  * structure which uniquely represent one DMA remapping hardware unit
  * present in the platform
  */
-static int __init
-dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg)
+static int dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_hardware_unit *drhd;
 	struct dmar_drhd_unit *dmaru;
 	int ret = 0;
 
 	drhd = (struct acpi_dmar_hardware_unit *)header;
-	dmaru = kzalloc(sizeof(*dmaru), GFP_KERNEL);
+	dmaru = dmar_find_dmaru(drhd);
+	if (dmaru)
+		goto out;
+
+	dmaru = kzalloc(sizeof(*dmaru) + header->length, GFP_KERNEL);
 	if (!dmaru)
 		return -ENOMEM;
 
-	dmaru->hdr = header;
+	/*
+	 * If header is allocated from slab by ACPI _DSM method, we need to
+	 * copy the content because the memory buffer will be freed on return.
+	 */
+	dmaru->hdr = (void *)(dmaru + 1);
+	memcpy(dmaru->hdr, header, header->length);
 	dmaru->reg_base_addr = drhd->address;
 	dmaru->segment = drhd->segment;
 	dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */
@@ -391,6 +412,7 @@ dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg)
 	}
 	dmar_register_drhd_unit(dmaru);
 
+out:
 	if (arg)
 		(*(int *)arg)++;
 
@@ -428,8 +450,7 @@ static int __init dmar_parse_one_andd(struct acpi_dmar_header *header,
 }
 
 #ifdef CONFIG_ACPI_NUMA
-static int __init
-dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
+static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_rhsa *rhsa;
 	struct dmar_drhd_unit *drhd;
@@ -821,14 +842,22 @@ dmar_validate_one_drhd(struct acpi_dmar_header *entry, void *arg)
 		return -EINVAL;
 	}
 
-	addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
+	if (arg)
+		addr = ioremap(drhd->address, VTD_PAGE_SIZE);
+	else
+		addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
 	if (!addr) {
 		pr_warn("IOMMU: can't validate: %llx\n", drhd->address);
 		return -EINVAL;
 	}
+
 	cap = dmar_readq(addr + DMAR_CAP_REG);
 	ecap = dmar_readq(addr + DMAR_ECAP_REG);
-	early_iounmap(addr, VTD_PAGE_SIZE);
+
+	if (arg)
+		iounmap(addr);
+	else
+		early_iounmap(addr, VTD_PAGE_SIZE);
 
 	if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
 		warn_invalid_dmar(drhd->address, " returns all ones");
@@ -1702,12 +1731,17 @@ int __init dmar_ir_support(void)
 	return dmar->flags & 0x1;
 }
 
+/* Check whether DMAR units are in use */
+static inline bool dmar_in_use(void)
+{
+	return irq_remapping_enabled || intel_iommu_enabled;
+}
+
 static int __init dmar_free_unused_resources(void)
 {
 	struct dmar_drhd_unit *dmaru, *dmaru_n;
 
-	/* DMAR units are in use */
-	if (irq_remapping_enabled || intel_iommu_enabled)
+	if (dmar_in_use())
 		return 0;
 
 	if (dmar_dev_scope_status != 1 && !list_empty(&dmar_drhd_units))
@@ -1725,3 +1759,215 @@ static int __init dmar_free_unused_resources(void)
 
 late_initcall(dmar_free_unused_resources);
 IOMMU_INIT_POST(detect_intel_iommu);
+
+/*
+ * DMAR Hotplug Support
+ * For more details, please refer to Intel(R) Virtualization Technology
+ * for Directed-IO Architecture Specifiction, Rev 2.2, Section 8.8
+ * "Remapping Hardware Unit Hot Plug".
+ */
+static u8 dmar_hp_uuid[] = {
+	/* 0000 */    0xA6, 0xA3, 0xC1, 0xD8, 0x9B, 0xBE, 0x9B, 0x4C,
+	/* 0008 */    0x91, 0xBF, 0xC3, 0xCB, 0x81, 0xFC, 0x5D, 0xAF
+};
+
+/*
+ * Currently there's only one revision and BIOS will not check the revision id,
+ * so use 0 for safety.
+ */
+#define	DMAR_DSM_REV_ID			0
+#define	DMAR_DSM_FUNC_DRHD		1
+#define	DMAR_DSM_FUNC_ATSR		2
+#define	DMAR_DSM_FUNC_RHSA		3
+
+static inline bool dmar_detect_dsm(acpi_handle handle, int func)
+{
+	return acpi_check_dsm(handle, dmar_hp_uuid, DMAR_DSM_REV_ID, 1 << func);
+}
+
+static int dmar_walk_dsm_resource(acpi_handle handle, int func,
+				  dmar_res_handler_t handler, void *arg)
+{
+	int ret = -ENODEV;
+	union acpi_object *obj;
+	struct acpi_dmar_header *start;
+	struct dmar_res_callback callback;
+	static int res_type[] = {
+		[DMAR_DSM_FUNC_DRHD] = ACPI_DMAR_TYPE_HARDWARE_UNIT,
+		[DMAR_DSM_FUNC_ATSR] = ACPI_DMAR_TYPE_ROOT_ATS,
+		[DMAR_DSM_FUNC_RHSA] = ACPI_DMAR_TYPE_HARDWARE_AFFINITY,
+	};
+
+	if (!dmar_detect_dsm(handle, func))
+		return 0;
+
+	obj = acpi_evaluate_dsm_typed(handle, dmar_hp_uuid, DMAR_DSM_REV_ID,
+				      func, NULL, ACPI_TYPE_BUFFER);
+	if (!obj)
+		return -ENODEV;
+
+	memset(&callback, 0, sizeof(callback));
+	callback.cb[res_type[func]] = handler;
+	callback.arg[res_type[func]] = arg;
+	start = (struct acpi_dmar_header *)obj->buffer.pointer;
+	ret = dmar_walk_remapping_entries(start, obj->buffer.length, &callback);
+
+	ACPI_FREE(obj);
+
+	return ret;
+}
+
+static int dmar_hp_add_drhd(struct acpi_dmar_header *header, void *arg)
+{
+	int ret;
+	struct dmar_drhd_unit *dmaru;
+
+	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
+	if (!dmaru)
+		return -ENODEV;
+
+	ret = dmar_ir_hotplug(dmaru, true);
+	if (ret == 0)
+		ret = dmar_iommu_hotplug(dmaru, true);
+
+	return ret;
+}
+
+static int dmar_hp_remove_drhd(struct acpi_dmar_header *header, void *arg)
+{
+	int i, ret;
+	struct device *dev;
+	struct dmar_drhd_unit *dmaru;
+
+	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
+	if (!dmaru)
+		return 0;
+
+	/*
+	 * All PCI devices managed by this unit should have been destroyed.
+	 */
+	if (!dmaru->include_all && dmaru->devices && dmaru->devices_cnt)
+		for_each_active_dev_scope(dmaru->devices,
+					  dmaru->devices_cnt, i, dev)
+			return -EBUSY;
+
+	ret = dmar_ir_hotplug(dmaru, false);
+	if (ret == 0)
+		ret = dmar_iommu_hotplug(dmaru, false);
+
+	return ret;
+}
+
+static int dmar_hp_release_drhd(struct acpi_dmar_header *header, void *arg)
+{
+	struct dmar_drhd_unit *dmaru;
+
+	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
+	if (dmaru) {
+		list_del_rcu(&dmaru->list);
+		synchronize_rcu();
+		dmar_free_drhd(dmaru);
+	}
+
+	return 0;
+}
+
+static int dmar_hotplug_insert(acpi_handle handle)
+{
+	int ret;
+	int drhd_count = 0;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_validate_one_drhd, (void *)1);
+	if (ret)
+		goto out;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_parse_one_drhd, (void *)&drhd_count);
+	if (ret == 0 && drhd_count == 0) {
+		pr_warn(FW_BUG "No DRHD structures in buffer returned by _DSM method\n");
+		goto out;
+	} else if (ret) {
+		goto release_drhd;
+	}
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_RHSA,
+				     &dmar_parse_one_rhsa, NULL);
+	if (ret)
+		goto release_drhd;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+				     &dmar_parse_one_atsr, NULL);
+	if (ret)
+		goto release_atsr;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_hp_add_drhd, NULL);
+	if (!ret)
+		return 0;
+
+	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+			       &dmar_hp_remove_drhd, NULL);
+release_atsr:
+	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+			       &dmar_release_one_atsr, NULL);
+release_drhd:
+	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+			       &dmar_hp_release_drhd, NULL);
+out:
+	return ret;
+}
+
+static int dmar_hotplug_remove(acpi_handle handle)
+{
+	int ret;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+				     &dmar_check_one_atsr, NULL);
+	if (ret)
+		return ret;
+
+	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				     &dmar_hp_remove_drhd, NULL);
+	if (ret == 0) {
+		WARN_ON(dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
+					       &dmar_release_one_atsr, NULL));
+		WARN_ON(dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+					       &dmar_hp_release_drhd, NULL));
+	} else {
+		dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
+				       &dmar_hp_add_drhd, NULL);
+	}
+
+	return ret;
+}
+
+static int dmar_device_hotplug(acpi_handle handle, bool insert)
+{
+	int ret;
+
+	if (!dmar_in_use())
+		return 0;
+
+	if (!dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD))
+		return 0;
+
+	down_write(&dmar_global_lock);
+	if (insert)
+		ret = dmar_hotplug_insert(handle);
+	else
+		ret = dmar_hotplug_remove(handle);
+	up_write(&dmar_global_lock);
+
+	return ret;
+}
+
+int dmar_device_add(acpi_handle handle)
+{
+	return dmar_device_hotplug(handle, true);
+}
+
+int dmar_device_remove(acpi_handle handle)
+{
+	return dmar_device_hotplug(handle, false);
+}
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 2779354321f..7c49ab51904 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3703,17 +3703,48 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
 	return 0;
 }
 
-int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr, void *arg)
+static struct dmar_atsr_unit *dmar_find_atsr(struct acpi_dmar_atsr *atsr)
+{
+	struct dmar_atsr_unit *atsru;
+	struct acpi_dmar_atsr *tmp;
+
+	list_for_each_entry_rcu(atsru, &dmar_atsr_units, list) {
+		tmp = (struct acpi_dmar_atsr *)atsru->hdr;
+		if (atsr->segment != tmp->segment)
+			continue;
+		if (atsr->header.length != tmp->header.length)
+			continue;
+		if (memcmp(atsr, tmp, atsr->header.length) == 0)
+			return atsru;
+	}
+
+	return NULL;
+}
+
+int dmar_parse_one_atsr(struct acpi_dmar_header *hdr, void *arg)
 {
 	struct acpi_dmar_atsr *atsr;
 	struct dmar_atsr_unit *atsru;
 
+	if (system_state != SYSTEM_BOOTING && !intel_iommu_enabled)
+		return 0;
+
 	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
-	atsru = kzalloc(sizeof(*atsru), GFP_KERNEL);
+	atsru = dmar_find_atsr(atsr);
+	if (atsru)
+		return 0;
+
+	atsru = kzalloc(sizeof(*atsru) + hdr->length, GFP_KERNEL);
 	if (!atsru)
 		return -ENOMEM;
 
-	atsru->hdr = hdr;
+	/*
+	 * If memory is allocated from slab by ACPI _DSM method, we need to
+	 * copy the memory content because the memory buffer will be freed
+	 * on return.
+	 */
+	atsru->hdr = (void *)(atsru + 1);
+	memcpy(atsru->hdr, hdr, hdr->length);
 	atsru->include_all = atsr->flags & 0x1;
 	if (!atsru->include_all) {
 		atsru->devices = dmar_alloc_dev_scope((void *)(atsr + 1),
@@ -3736,6 +3767,47 @@ static void intel_iommu_free_atsr(struct dmar_atsr_unit *atsru)
 	kfree(atsru);
 }
 
+int dmar_release_one_atsr(struct acpi_dmar_header *hdr, void *arg)
+{
+	struct acpi_dmar_atsr *atsr;
+	struct dmar_atsr_unit *atsru;
+
+	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
+	atsru = dmar_find_atsr(atsr);
+	if (atsru) {
+		list_del_rcu(&atsru->list);
+		synchronize_rcu();
+		intel_iommu_free_atsr(atsru);
+	}
+
+	return 0;
+}
+
+int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg)
+{
+	int i;
+	struct device *dev;
+	struct acpi_dmar_atsr *atsr;
+	struct dmar_atsr_unit *atsru;
+
+	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
+	atsru = dmar_find_atsr(atsr);
+	if (!atsru)
+		return 0;
+
+	if (!atsru->include_all && atsru->devices && atsru->devices_cnt)
+		for_each_active_dev_scope(atsru->devices, atsru->devices_cnt,
+					  i, dev)
+			return -EBUSY;
+
+	return 0;
+}
+
+int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
+{
+	return intel_iommu_enabled ? -ENOSYS : 0;
+}
+
 static void intel_iommu_free_dmars(void)
 {
 	struct dmar_rmrr_unit *rmrru, *rmrr_n;
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 7c80661b35c..1cbdb509bc7 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -1171,3 +1171,8 @@ struct irq_remap_ops intel_irq_remap_ops = {
 	.msi_setup_irq		= intel_msi_setup_irq,
 	.alloc_hpet_msi		= intel_alloc_hpet_msi,
 };
+
+int dmar_ir_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
+{
+	return irq_remapping_enabled ? -ENOSYS : 0;
+}
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 725204fc433..30624954dec 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -126,6 +126,8 @@ extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info,
 /* Intel IOMMU detection */
 extern int detect_intel_iommu(void);
 extern int enable_drhd_fault_handling(void);
+extern int dmar_device_add(acpi_handle handle);
+extern int dmar_device_remove(acpi_handle handle);
 
 static inline int dmar_res_noop(struct acpi_dmar_header *hdr, void *arg)
 {
@@ -137,17 +139,48 @@ extern int iommu_detected, no_iommu;
 extern int intel_iommu_init(void);
 extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg);
 extern int dmar_parse_one_atsr(struct acpi_dmar_header *header, void *arg);
+extern int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg);
+extern int dmar_release_one_atsr(struct acpi_dmar_header *hdr, void *arg);
+extern int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert);
 extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info);
 #else /* !CONFIG_INTEL_IOMMU: */
 static inline int intel_iommu_init(void) { return -ENODEV; }
+
 #define	dmar_parse_one_rmrr		dmar_res_noop
 #define	dmar_parse_one_atsr		dmar_res_noop
+#define	dmar_check_one_atsr		dmar_res_noop
+#define	dmar_release_one_atsr		dmar_res_noop
+
 static inline int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 {
 	return 0;
 }
+
+static inline int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
+{
+	return 0;
+}
 #endif /* CONFIG_INTEL_IOMMU */
 
+#ifdef CONFIG_IRQ_REMAP
+extern int dmar_ir_hotplug(struct dmar_drhd_unit *dmaru, bool insert);
+#else  /* CONFIG_IRQ_REMAP */
+static inline int dmar_ir_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
+{ return 0; }
+#endif /* CONFIG_IRQ_REMAP */
+
+#else /* CONFIG_DMAR_TABLE */
+
+static inline int dmar_device_add(void *handle)
+{
+	return 0;
+}
+
+static inline int dmar_device_remove(void *handle)
+{
+	return 0;
+}
+
 #endif /* CONFIG_DMAR_TABLE */
 
 struct irte {
-- 
cgit v1.2.3-70-g09d2


From cc149f7ae2fa54b3d067527642146dde37977358 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Mon, 17 Nov 2014 17:47:00 +0100
Subject: ARM: STi: DT: STiH410: Add defines for STiH410 DT clocks

Although most clock outputs are the same as stih407 SoC, stih410
also has some additional new clock outputs.

Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Maxime Coquelin <maxime.coquelin@st.com>
---
 include/dt-bindings/clock/stih410-clks.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)
 create mode 100644 include/dt-bindings/clock/stih410-clks.h

(limited to 'include')

diff --git a/include/dt-bindings/clock/stih410-clks.h b/include/dt-bindings/clock/stih410-clks.h
new file mode 100644
index 00000000000..2097a4bbe15
--- /dev/null
+++ b/include/dt-bindings/clock/stih410-clks.h
@@ -0,0 +1,25 @@
+/*
+ * This header provides constants clk index STMicroelectronics
+ * STiH410 SoC.
+ */
+#ifndef _DT_BINDINGS_CLK_STIH410
+#define _DT_BINDINGS_CLK_STIH410
+
+#include "stih407-clks.h"
+
+/* STiH410 introduces new clock outputs compared to STiH407 */
+
+/* CLOCKGEN C0 */
+#define CLK_TX_ICN_HADES	32
+#define CLK_RX_ICN_HADES	33
+#define CLK_ICN_REG_16		34
+#define CLK_PP_HADES		35
+#define CLK_CLUST_HADES		36
+#define CLK_HWPE_HADES		37
+#define CLK_FC_HADES		38
+
+/* CLOCKGEN D0 */
+#define CLK_PCMR10_MASTER	4
+#define CLK_USB2_PHY		5
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From 336b8423e285174ebecf02a743d69913b83bbc48 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 10 Nov 2014 22:41:46 +0100
Subject: ASoC: Move AC'97 support to its own file

Currently the AC'97 support is splattered all throughout soc-core.c. Some
parts are #ifdef'd some parts are not. This patch moves the AC'97 support to
its own file, this should make the code a bit more clearer and also makes it
possible to easily not compile it into the kernel when not needed.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  |  28 +++-
 sound/soc/Makefile   |   4 +
 sound/soc/soc-ac97.c | 382 +++++++++++++++++++++++++++++++++++++++++++++++++++
 sound/soc/soc-core.c | 352 +----------------------------------------------
 4 files changed, 416 insertions(+), 350 deletions(-)
 create mode 100644 sound/soc/soc-ac97.c

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 7ba7130037a..adef34fa520 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -366,8 +366,6 @@ struct snd_soc_jack_gpio;
 
 typedef int (*hw_write_t)(void *,const char* ,int);
 
-extern struct snd_ac97_bus_ops *soc_ac97_ops;
-
 enum snd_soc_pcm_subclass {
 	SND_SOC_PCM_CLASS_PCM	= 0,
 	SND_SOC_PCM_CLASS_BE	= 1,
@@ -500,6 +498,7 @@ int snd_soc_update_bits_locked(struct snd_soc_codec *codec,
 int snd_soc_test_bits(struct snd_soc_codec *codec, unsigned int reg,
 				unsigned int mask, unsigned int value);
 
+#ifdef CONFIG_SND_SOC_AC97_BUS
 int snd_soc_new_ac97_codec(struct snd_soc_codec *codec,
 	struct snd_ac97_bus_ops *ops, int num);
 void snd_soc_free_ac97_codec(struct snd_soc_codec *codec);
@@ -508,6 +507,31 @@ int snd_soc_set_ac97_ops(struct snd_ac97_bus_ops *ops);
 int snd_soc_set_ac97_ops_of_reset(struct snd_ac97_bus_ops *ops,
 		struct platform_device *pdev);
 
+extern struct snd_ac97_bus_ops *soc_ac97_ops;
+
+int snd_soc_ac97_register_dai_links(struct snd_soc_card *card);
+void snd_soc_ac97_add_pdata(struct snd_soc_pcm_runtime *rtd);
+#else
+
+static inline int snd_soc_ac97_register_dai_links(struct snd_soc_card *card)
+{
+	return 0;
+}
+
+static inline void snd_soc_ac97_add_pdata(struct snd_soc_pcm_runtime *rtd) {}
+
+static inline int snd_soc_set_ac97_ops_of_reset(struct snd_ac97_bus_ops *ops,
+	struct platform_device *pdev)
+{
+	return 0;
+}
+
+static inline int snd_soc_set_ac97_ops(struct snd_ac97_bus_ops *ops)
+{
+	return 0;
+}
+#endif
+
 /*
  *Controls
  */
diff --git a/sound/soc/Makefile b/sound/soc/Makefile
index 534714a1ca4..0fded1bb613 100644
--- a/sound/soc/Makefile
+++ b/sound/soc/Makefile
@@ -5,6 +5,10 @@ ifneq ($(CONFIG_SND_SOC_GENERIC_DMAENGINE_PCM),)
 snd-soc-core-objs += soc-generic-dmaengine-pcm.o
 endif
 
+ifneq ($(CONFIG_SND_SOC_AC97_BUS),)
+snd-soc-core-objs += soc-ac97.o
+endif
+
 obj-$(CONFIG_SND_SOC)	+= snd-soc-core.o
 obj-$(CONFIG_SND_SOC)	+= codecs/
 obj-$(CONFIG_SND_SOC)	+= generic/
diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c
new file mode 100644
index 00000000000..da7b031a6ee
--- /dev/null
+++ b/sound/soc/soc-ac97.c
@@ -0,0 +1,382 @@
+/*
+ * soc-ac97.c  --  ALSA SoC Audio Layer AC97 support
+ *
+ * Copyright 2005 Wolfson Microelectronics PLC.
+ * Copyright 2005 Openedhand Ltd.
+ * Copyright (C) 2010 Slimlogic Ltd.
+ * Copyright (C) 2010 Texas Instruments Inc.
+ *
+ * Author: Liam Girdwood <lrg@slimlogic.co.uk>
+ *         with code, comments and ideas from :-
+ *         Richard Purdie <richard@openedhand.com>
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ */
+
+#include <linux/ctype.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/gpio.h>
+#include <linux/init.h>
+#include <linux/of_gpio.h>
+#include <linux/of.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/slab.h>
+#include <sound/ac97_codec.h>
+#include <sound/soc.h>
+
+struct snd_ac97_reset_cfg {
+	struct pinctrl *pctl;
+	struct pinctrl_state *pstate_reset;
+	struct pinctrl_state *pstate_warm_reset;
+	struct pinctrl_state *pstate_run;
+	int gpio_sdata;
+	int gpio_sync;
+	int gpio_reset;
+};
+
+/* unregister ac97 codec */
+static int soc_ac97_dev_unregister(struct snd_soc_codec *codec)
+{
+	if (codec->ac97->dev.bus)
+		device_del(&codec->ac97->dev);
+	return 0;
+}
+
+/* register ac97 codec to bus */
+static int soc_ac97_dev_register(struct snd_soc_codec *codec)
+{
+	int err;
+
+	codec->ac97->dev.bus = &ac97_bus_type;
+	codec->ac97->dev.parent = codec->component.card->dev;
+
+	dev_set_name(&codec->ac97->dev, "%d-%d:%s",
+		     codec->component.card->snd_card->number, 0,
+		     codec->component.name);
+	err = device_add(&codec->ac97->dev);
+	if (err < 0) {
+		dev_err(codec->dev, "ASoC: Can't register ac97 bus\n");
+		codec->ac97->dev.bus = NULL;
+		return err;
+	}
+	return 0;
+}
+
+static int soc_register_ac97_codec(struct snd_soc_codec *codec,
+				   struct snd_soc_dai *codec_dai)
+{
+	int ret;
+
+	/* Only instantiate AC97 if not already done by the adaptor
+	 * for the generic AC97 subsystem.
+	 */
+	if (codec_dai->driver->ac97_control && !codec->ac97_registered) {
+		/*
+		 * It is possible that the AC97 device is already registered to
+		 * the device subsystem. This happens when the device is created
+		 * via snd_ac97_mixer(). Currently only SoC codec that does so
+		 * is the generic AC97 glue but others migh emerge.
+		 *
+		 * In those cases we don't try to register the device again.
+		 */
+		if (!codec->ac97_created)
+			return 0;
+
+		ret = soc_ac97_dev_register(codec);
+		if (ret < 0) {
+			dev_err(codec->dev,
+				"ASoC: AC97 device register failed: %d\n", ret);
+			return ret;
+		}
+
+		codec->ac97_registered = 1;
+	}
+	return 0;
+}
+
+static void soc_unregister_ac97_codec(struct snd_soc_codec *codec)
+{
+	if (codec->ac97_registered) {
+		soc_ac97_dev_unregister(codec);
+		codec->ac97_registered = 0;
+	}
+}
+
+static int soc_register_ac97_dai_link(struct snd_soc_pcm_runtime *rtd)
+{
+	int i, ret;
+
+	for (i = 0; i < rtd->num_codecs; i++) {
+		struct snd_soc_dai *codec_dai = rtd->codec_dais[i];
+
+		ret = soc_register_ac97_codec(codec_dai->codec, codec_dai);
+		if (ret) {
+			while (--i >= 0)
+				soc_unregister_ac97_codec(codec_dai->codec);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void soc_unregister_ac97_dai_link(struct snd_soc_pcm_runtime *rtd)
+{
+	int i;
+
+	for (i = 0; i < rtd->num_codecs; i++)
+		soc_unregister_ac97_codec(rtd->codec_dais[i]->codec);
+}
+
+static void soc_ac97_device_release(struct device *dev)
+{
+	kfree(to_ac97_t(dev));
+}
+
+/**
+ * snd_soc_new_ac97_codec - initailise AC97 device
+ * @codec: audio codec
+ * @ops: AC97 bus operations
+ * @num: AC97 codec number
+ *
+ * Initialises AC97 codec resources for use by ad-hoc devices only.
+ */
+int snd_soc_new_ac97_codec(struct snd_soc_codec *codec,
+	struct snd_ac97_bus_ops *ops, int num)
+{
+	codec->ac97 = kzalloc(sizeof(struct snd_ac97), GFP_KERNEL);
+	if (codec->ac97 == NULL)
+		return -ENOMEM;
+
+	codec->ac97->bus = kzalloc(sizeof(struct snd_ac97_bus), GFP_KERNEL);
+	if (codec->ac97->bus == NULL) {
+		kfree(codec->ac97);
+		codec->ac97 = NULL;
+		return -ENOMEM;
+	}
+
+	codec->ac97->bus->ops = ops;
+	codec->ac97->num = num;
+	codec->ac97->dev.release = soc_ac97_device_release;
+
+	/*
+	 * Mark the AC97 device to be created by us. This way we ensure that the
+	 * device will be registered with the device subsystem later on.
+	 */
+	codec->ac97_created = 1;
+	device_initialize(&codec->ac97->dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_soc_new_ac97_codec);
+
+/**
+ * snd_soc_free_ac97_codec - free AC97 codec device
+ * @codec: audio codec
+ *
+ * Frees AC97 codec device resources.
+ */
+void snd_soc_free_ac97_codec(struct snd_soc_codec *codec)
+{
+	soc_unregister_ac97_codec(codec);
+	kfree(codec->ac97->bus);
+	codec->ac97->bus = NULL;
+	put_device(&codec->ac97->dev);
+	codec->ac97 = NULL;
+	codec->ac97_created = 0;
+}
+EXPORT_SYMBOL_GPL(snd_soc_free_ac97_codec);
+
+static struct snd_ac97_reset_cfg snd_ac97_rst_cfg;
+
+static void snd_soc_ac97_warm_reset(struct snd_ac97 *ac97)
+{
+	struct pinctrl *pctl = snd_ac97_rst_cfg.pctl;
+
+	pinctrl_select_state(pctl, snd_ac97_rst_cfg.pstate_warm_reset);
+
+	gpio_direction_output(snd_ac97_rst_cfg.gpio_sync, 1);
+
+	udelay(10);
+
+	gpio_direction_output(snd_ac97_rst_cfg.gpio_sync, 0);
+
+	pinctrl_select_state(pctl, snd_ac97_rst_cfg.pstate_run);
+	msleep(2);
+}
+
+static void snd_soc_ac97_reset(struct snd_ac97 *ac97)
+{
+	struct pinctrl *pctl = snd_ac97_rst_cfg.pctl;
+
+	pinctrl_select_state(pctl, snd_ac97_rst_cfg.pstate_reset);
+
+	gpio_direction_output(snd_ac97_rst_cfg.gpio_sync, 0);
+	gpio_direction_output(snd_ac97_rst_cfg.gpio_sdata, 0);
+	gpio_direction_output(snd_ac97_rst_cfg.gpio_reset, 0);
+
+	udelay(10);
+
+	gpio_direction_output(snd_ac97_rst_cfg.gpio_reset, 1);
+
+	pinctrl_select_state(pctl, snd_ac97_rst_cfg.pstate_run);
+	msleep(2);
+}
+
+static int snd_soc_ac97_parse_pinctl(struct device *dev,
+		struct snd_ac97_reset_cfg *cfg)
+{
+	struct pinctrl *p;
+	struct pinctrl_state *state;
+	int gpio;
+	int ret;
+
+	p = devm_pinctrl_get(dev);
+	if (IS_ERR(p)) {
+		dev_err(dev, "Failed to get pinctrl\n");
+		return PTR_ERR(p);
+	}
+	cfg->pctl = p;
+
+	state = pinctrl_lookup_state(p, "ac97-reset");
+	if (IS_ERR(state)) {
+		dev_err(dev, "Can't find pinctrl state ac97-reset\n");
+		return PTR_ERR(state);
+	}
+	cfg->pstate_reset = state;
+
+	state = pinctrl_lookup_state(p, "ac97-warm-reset");
+	if (IS_ERR(state)) {
+		dev_err(dev, "Can't find pinctrl state ac97-warm-reset\n");
+		return PTR_ERR(state);
+	}
+	cfg->pstate_warm_reset = state;
+
+	state = pinctrl_lookup_state(p, "ac97-running");
+	if (IS_ERR(state)) {
+		dev_err(dev, "Can't find pinctrl state ac97-running\n");
+		return PTR_ERR(state);
+	}
+	cfg->pstate_run = state;
+
+	gpio = of_get_named_gpio(dev->of_node, "ac97-gpios", 0);
+	if (gpio < 0) {
+		dev_err(dev, "Can't find ac97-sync gpio\n");
+		return gpio;
+	}
+	ret = devm_gpio_request(dev, gpio, "AC97 link sync");
+	if (ret) {
+		dev_err(dev, "Failed requesting ac97-sync gpio\n");
+		return ret;
+	}
+	cfg->gpio_sync = gpio;
+
+	gpio = of_get_named_gpio(dev->of_node, "ac97-gpios", 1);
+	if (gpio < 0) {
+		dev_err(dev, "Can't find ac97-sdata gpio %d\n", gpio);
+		return gpio;
+	}
+	ret = devm_gpio_request(dev, gpio, "AC97 link sdata");
+	if (ret) {
+		dev_err(dev, "Failed requesting ac97-sdata gpio\n");
+		return ret;
+	}
+	cfg->gpio_sdata = gpio;
+
+	gpio = of_get_named_gpio(dev->of_node, "ac97-gpios", 2);
+	if (gpio < 0) {
+		dev_err(dev, "Can't find ac97-reset gpio\n");
+		return gpio;
+	}
+	ret = devm_gpio_request(dev, gpio, "AC97 link reset");
+	if (ret) {
+		dev_err(dev, "Failed requesting ac97-reset gpio\n");
+		return ret;
+	}
+	cfg->gpio_reset = gpio;
+
+	return 0;
+}
+
+struct snd_ac97_bus_ops *soc_ac97_ops;
+EXPORT_SYMBOL_GPL(soc_ac97_ops);
+
+int snd_soc_set_ac97_ops(struct snd_ac97_bus_ops *ops)
+{
+	if (ops == soc_ac97_ops)
+		return 0;
+
+	if (soc_ac97_ops && ops)
+		return -EBUSY;
+
+	soc_ac97_ops = ops;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_soc_set_ac97_ops);
+
+/**
+ * snd_soc_set_ac97_ops_of_reset - Set ac97 ops with generic ac97 reset functions
+ *
+ * This function sets the reset and warm_reset properties of ops and parses
+ * the device node of pdev to get pinctrl states and gpio numbers to use.
+ */
+int snd_soc_set_ac97_ops_of_reset(struct snd_ac97_bus_ops *ops,
+		struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct snd_ac97_reset_cfg cfg;
+	int ret;
+
+	ret = snd_soc_ac97_parse_pinctl(dev, &cfg);
+	if (ret)
+		return ret;
+
+	ret = snd_soc_set_ac97_ops(ops);
+	if (ret)
+		return ret;
+
+	ops->warm_reset = snd_soc_ac97_warm_reset;
+	ops->reset = snd_soc_ac97_reset;
+
+	snd_ac97_rst_cfg = cfg;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_soc_set_ac97_ops_of_reset);
+
+int snd_soc_ac97_register_dai_links(struct snd_soc_card *card)
+{
+	int i;
+	int ret;
+
+	/* register any AC97 codecs */
+	for (i = 0; i < card->num_rtd; i++) {
+		ret = soc_register_ac97_dai_link(&card->rtd[i]);
+		if (ret < 0)
+			goto err;
+	}
+
+	return 0;
+err:
+	dev_err(card->dev,
+		"ASoC: failed to register AC97: %d\n", ret);
+	while (--i >= 0)
+		soc_unregister_ac97_dai_link(&card->rtd[i]);
+	return ret;
+}
+
+void snd_soc_ac97_add_pdata(struct snd_soc_pcm_runtime *rtd)
+{
+	unsigned int i;
+
+	/* add platform data for AC97 devices */
+	for (i = 0; i < rtd->num_codecs; i++) {
+		if (rtd->codec_dais[i]->driver->ac97_control)
+			snd_ac97_dev_add_pdata(rtd->codec_dais[i]->codec->ac97,
+					       rtd->cpu_dai->ac97_pdata);
+	}
+}
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 7084c6f1285..026722f5ebf 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -34,9 +34,6 @@
 #include <linux/ctype.h>
 #include <linux/slab.h>
 #include <linux/of.h>
-#include <linux/gpio.h>
-#include <linux/of_gpio.h>
-#include <sound/ac97_codec.h>
 #include <sound/core.h>
 #include <sound/jack.h>
 #include <sound/pcm.h>
@@ -69,16 +66,6 @@ static int pmdown_time = 5000;
 module_param(pmdown_time, int, 0);
 MODULE_PARM_DESC(pmdown_time, "DAPM stream powerdown time (msecs)");
 
-struct snd_ac97_reset_cfg {
-	struct pinctrl *pctl;
-	struct pinctrl_state *pstate_reset;
-	struct pinctrl_state *pstate_warm_reset;
-	struct pinctrl_state *pstate_run;
-	int gpio_sdata;
-	int gpio_sync;
-	int gpio_reset;
-};
-
 /* returns the minimum number of bytes needed to represent
  * a particular given value */
 static int min_bytes_needed(unsigned long val)
@@ -499,36 +486,6 @@ struct snd_soc_pcm_runtime *snd_soc_get_pcm_runtime(struct snd_soc_card *card,
 }
 EXPORT_SYMBOL_GPL(snd_soc_get_pcm_runtime);
 
-#ifdef CONFIG_SND_SOC_AC97_BUS
-/* unregister ac97 codec */
-static int soc_ac97_dev_unregister(struct snd_soc_codec *codec)
-{
-	if (codec->ac97->dev.bus)
-		device_del(&codec->ac97->dev);
-	return 0;
-}
-
-/* register ac97 codec to bus */
-static int soc_ac97_dev_register(struct snd_soc_codec *codec)
-{
-	int err;
-
-	codec->ac97->dev.bus = &ac97_bus_type;
-	codec->ac97->dev.parent = codec->component.card->dev;
-
-	dev_set_name(&codec->ac97->dev, "%d-%d:%s",
-		     codec->component.card->snd_card->number, 0,
-		     codec->component.name);
-	err = device_add(&codec->ac97->dev);
-	if (err < 0) {
-		dev_err(codec->dev, "ASoC: Can't register ac97 bus\n");
-		codec->ac97->dev.bus = NULL;
-		return err;
-	}
-	return 0;
-}
-#endif
-
 static void codec2codec_close_delayed_work(struct work_struct *work)
 {
 	/* Currently nothing to do for c2c links
@@ -1418,84 +1375,11 @@ static int soc_probe_link_dais(struct snd_soc_card *card, int num, int order)
 		}
 	}
 
-	/* add platform data for AC97 devices */
-	for (i = 0; i < rtd->num_codecs; i++) {
-		if (rtd->codec_dais[i]->driver->ac97_control)
-			snd_ac97_dev_add_pdata(rtd->codec_dais[i]->codec->ac97,
-					       rtd->cpu_dai->ac97_pdata);
-	}
-
-	return 0;
-}
-
-#ifdef CONFIG_SND_SOC_AC97_BUS
-static int soc_register_ac97_codec(struct snd_soc_codec *codec,
-				   struct snd_soc_dai *codec_dai)
-{
-	int ret;
-
-	/* Only instantiate AC97 if not already done by the adaptor
-	 * for the generic AC97 subsystem.
-	 */
-	if (codec_dai->driver->ac97_control && !codec->ac97_registered) {
-		/*
-		 * It is possible that the AC97 device is already registered to
-		 * the device subsystem. This happens when the device is created
-		 * via snd_ac97_mixer(). Currently only SoC codec that does so
-		 * is the generic AC97 glue but others migh emerge.
-		 *
-		 * In those cases we don't try to register the device again.
-		 */
-		if (!codec->ac97_created)
-			return 0;
-
-		ret = soc_ac97_dev_register(codec);
-		if (ret < 0) {
-			dev_err(codec->dev,
-				"ASoC: AC97 device register failed: %d\n", ret);
-			return ret;
-		}
-
-		codec->ac97_registered = 1;
-	}
-	return 0;
-}
-
-static void soc_unregister_ac97_codec(struct snd_soc_codec *codec)
-{
-	if (codec->ac97_registered) {
-		soc_ac97_dev_unregister(codec);
-		codec->ac97_registered = 0;
-	}
-}
-
-static int soc_register_ac97_dai_link(struct snd_soc_pcm_runtime *rtd)
-{
-	int i, ret;
-
-	for (i = 0; i < rtd->num_codecs; i++) {
-		struct snd_soc_dai *codec_dai = rtd->codec_dais[i];
-
-		ret = soc_register_ac97_codec(codec_dai->codec, codec_dai);
-		if (ret) {
-			while (--i >= 0)
-				soc_unregister_ac97_codec(codec_dai->codec);
-			return ret;
-		}
-	}
+	snd_soc_ac97_add_pdata(rtd);
 
 	return 0;
 }
 
-static void soc_unregister_ac97_dai_link(struct snd_soc_pcm_runtime *rtd)
-{
-	int i;
-
-	for (i = 0; i < rtd->num_codecs; i++)
-		soc_unregister_ac97_codec(rtd->codec_dais[i]->codec);
-}
-#endif
-
 static int soc_bind_aux_dev(struct snd_soc_card *card, int num)
 {
 	struct snd_soc_pcm_runtime *rtd = &card->rtd_aux[num];
@@ -1789,19 +1673,9 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 		goto probe_aux_dev_err;
 	}
 
-#ifdef CONFIG_SND_SOC_AC97_BUS
-	/* register any AC97 codecs */
-	for (i = 0; i < card->num_rtd; i++) {
-		ret = soc_register_ac97_dai_link(&card->rtd[i]);
-		if (ret < 0) {
-			dev_err(card->dev,
-				"ASoC: failed to register AC97: %d\n", ret);
-			while (--i >= 0)
-				soc_unregister_ac97_dai_link(&card->rtd[i]);
-			goto probe_aux_dev_err;
-		}
-	}
-#endif
+	ret = snd_soc_ac97_register_dai_links(card);
+	if (ret < 0)
+		goto probe_aux_dev_err;
 
 	card->instantiated = 1;
 	snd_soc_dapm_sync(&card->dapm);
@@ -1944,224 +1818,6 @@ static struct platform_driver soc_driver = {
 	.remove		= soc_remove,
 };
 
-static void soc_ac97_device_release(struct device *dev)
-{
-	kfree(to_ac97_t(dev));
-}
-
-/**
- * snd_soc_new_ac97_codec - initailise AC97 device
- * @codec: audio codec
- * @ops: AC97 bus operations
- * @num: AC97 codec number
- *
- * Initialises AC97 codec resources for use by ad-hoc devices only.
- */
-int snd_soc_new_ac97_codec(struct snd_soc_codec *codec,
-	struct snd_ac97_bus_ops *ops, int num)
-{
-	codec->ac97 = kzalloc(sizeof(struct snd_ac97), GFP_KERNEL);
-	if (codec->ac97 == NULL)
-		return -ENOMEM;
-
-	codec->ac97->bus = kzalloc(sizeof(struct snd_ac97_bus), GFP_KERNEL);
-	if (codec->ac97->bus == NULL) {
-		kfree(codec->ac97);
-		codec->ac97 = NULL;
-		return -ENOMEM;
-	}
-
-	codec->ac97->bus->ops = ops;
-	codec->ac97->num = num;
-	codec->ac97->dev.release = soc_ac97_device_release;
-
-	/*
-	 * Mark the AC97 device to be created by us. This way we ensure that the
-	 * device will be registered with the device subsystem later on.
-	 */
-	codec->ac97_created = 1;
-	device_initialize(&codec->ac97->dev);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_soc_new_ac97_codec);
-
-static struct snd_ac97_reset_cfg snd_ac97_rst_cfg;
-
-static void snd_soc_ac97_warm_reset(struct snd_ac97 *ac97)
-{
-	struct pinctrl *pctl = snd_ac97_rst_cfg.pctl;
-
-	pinctrl_select_state(pctl, snd_ac97_rst_cfg.pstate_warm_reset);
-
-	gpio_direction_output(snd_ac97_rst_cfg.gpio_sync, 1);
-
-	udelay(10);
-
-	gpio_direction_output(snd_ac97_rst_cfg.gpio_sync, 0);
-
-	pinctrl_select_state(pctl, snd_ac97_rst_cfg.pstate_run);
-	msleep(2);
-}
-
-static void snd_soc_ac97_reset(struct snd_ac97 *ac97)
-{
-	struct pinctrl *pctl = snd_ac97_rst_cfg.pctl;
-
-	pinctrl_select_state(pctl, snd_ac97_rst_cfg.pstate_reset);
-
-	gpio_direction_output(snd_ac97_rst_cfg.gpio_sync, 0);
-	gpio_direction_output(snd_ac97_rst_cfg.gpio_sdata, 0);
-	gpio_direction_output(snd_ac97_rst_cfg.gpio_reset, 0);
-
-	udelay(10);
-
-	gpio_direction_output(snd_ac97_rst_cfg.gpio_reset, 1);
-
-	pinctrl_select_state(pctl, snd_ac97_rst_cfg.pstate_run);
-	msleep(2);
-}
-
-static int snd_soc_ac97_parse_pinctl(struct device *dev,
-		struct snd_ac97_reset_cfg *cfg)
-{
-	struct pinctrl *p;
-	struct pinctrl_state *state;
-	int gpio;
-	int ret;
-
-	p = devm_pinctrl_get(dev);
-	if (IS_ERR(p)) {
-		dev_err(dev, "Failed to get pinctrl\n");
-		return PTR_ERR(p);
-	}
-	cfg->pctl = p;
-
-	state = pinctrl_lookup_state(p, "ac97-reset");
-	if (IS_ERR(state)) {
-		dev_err(dev, "Can't find pinctrl state ac97-reset\n");
-		return PTR_ERR(state);
-	}
-	cfg->pstate_reset = state;
-
-	state = pinctrl_lookup_state(p, "ac97-warm-reset");
-	if (IS_ERR(state)) {
-		dev_err(dev, "Can't find pinctrl state ac97-warm-reset\n");
-		return PTR_ERR(state);
-	}
-	cfg->pstate_warm_reset = state;
-
-	state = pinctrl_lookup_state(p, "ac97-running");
-	if (IS_ERR(state)) {
-		dev_err(dev, "Can't find pinctrl state ac97-running\n");
-		return PTR_ERR(state);
-	}
-	cfg->pstate_run = state;
-
-	gpio = of_get_named_gpio(dev->of_node, "ac97-gpios", 0);
-	if (gpio < 0) {
-		dev_err(dev, "Can't find ac97-sync gpio\n");
-		return gpio;
-	}
-	ret = devm_gpio_request(dev, gpio, "AC97 link sync");
-	if (ret) {
-		dev_err(dev, "Failed requesting ac97-sync gpio\n");
-		return ret;
-	}
-	cfg->gpio_sync = gpio;
-
-	gpio = of_get_named_gpio(dev->of_node, "ac97-gpios", 1);
-	if (gpio < 0) {
-		dev_err(dev, "Can't find ac97-sdata gpio %d\n", gpio);
-		return gpio;
-	}
-	ret = devm_gpio_request(dev, gpio, "AC97 link sdata");
-	if (ret) {
-		dev_err(dev, "Failed requesting ac97-sdata gpio\n");
-		return ret;
-	}
-	cfg->gpio_sdata = gpio;
-
-	gpio = of_get_named_gpio(dev->of_node, "ac97-gpios", 2);
-	if (gpio < 0) {
-		dev_err(dev, "Can't find ac97-reset gpio\n");
-		return gpio;
-	}
-	ret = devm_gpio_request(dev, gpio, "AC97 link reset");
-	if (ret) {
-		dev_err(dev, "Failed requesting ac97-reset gpio\n");
-		return ret;
-	}
-	cfg->gpio_reset = gpio;
-
-	return 0;
-}
-
-struct snd_ac97_bus_ops *soc_ac97_ops;
-EXPORT_SYMBOL_GPL(soc_ac97_ops);
-
-int snd_soc_set_ac97_ops(struct snd_ac97_bus_ops *ops)
-{
-	if (ops == soc_ac97_ops)
-		return 0;
-
-	if (soc_ac97_ops && ops)
-		return -EBUSY;
-
-	soc_ac97_ops = ops;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_soc_set_ac97_ops);
-
-/**
- * snd_soc_set_ac97_ops_of_reset - Set ac97 ops with generic ac97 reset functions
- *
- * This function sets the reset and warm_reset properties of ops and parses
- * the device node of pdev to get pinctrl states and gpio numbers to use.
- */
-int snd_soc_set_ac97_ops_of_reset(struct snd_ac97_bus_ops *ops,
-		struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct snd_ac97_reset_cfg cfg;
-	int ret;
-
-	ret = snd_soc_ac97_parse_pinctl(dev, &cfg);
-	if (ret)
-		return ret;
-
-	ret = snd_soc_set_ac97_ops(ops);
-	if (ret)
-		return ret;
-
-	ops->warm_reset = snd_soc_ac97_warm_reset;
-	ops->reset = snd_soc_ac97_reset;
-
-	snd_ac97_rst_cfg = cfg;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_soc_set_ac97_ops_of_reset);
-
-/**
- * snd_soc_free_ac97_codec - free AC97 codec device
- * @codec: audio codec
- *
- * Frees AC97 codec device resources.
- */
-void snd_soc_free_ac97_codec(struct snd_soc_codec *codec)
-{
-#ifdef CONFIG_SND_SOC_AC97_BUS
-	soc_unregister_ac97_codec(codec);
-#endif
-	kfree(codec->ac97->bus);
-	codec->ac97->bus = NULL;
-	put_device(&codec->ac97->dev);
-	codec->ac97 = NULL;
-	codec->ac97_created = 0;
-}
-EXPORT_SYMBOL_GPL(snd_soc_free_ac97_codec);
-
 /**
  * snd_soc_cnew - create new control
  * @_template: control template
-- 
cgit v1.2.3-70-g09d2


From eda1a701fd9589b6ed15b109558bd4f6202e3829 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 10 Nov 2014 22:41:47 +0100
Subject: ASoC: ac97: Use static ac97_bus

We always pass soc_ac97_ops to snd_soc_new_ac97_codec(). So instead of
allocating a snd_ac97_bus in snd_soc_new_ac97_codec() just use a static one
that gets initialized when snd_soc_set_ac97_ops() is called.

Also drop the device number parameter from snd_soc_new_ac97_codec(). We
currently only support one device per bus and all drivers pass 0 for the
device number. And if we should ever support multiple devices per bus it
wouldn't be up to individual AC'97 device drivers to pick their number, but
rather either the AC'97 adapter driver or the core code will assign them.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h         |  3 +--
 sound/soc/codecs/ad1980.c   |  2 +-
 sound/soc/codecs/stac9766.c |  2 +-
 sound/soc/codecs/wm9705.c   |  2 +-
 sound/soc/codecs/wm9712.c   |  2 +-
 sound/soc/codecs/wm9713.c   |  2 +-
 sound/soc/soc-ac97.c        | 22 ++++++++--------------
 7 files changed, 14 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index adef34fa520..44b3ce531fd 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -499,8 +499,7 @@ int snd_soc_test_bits(struct snd_soc_codec *codec, unsigned int reg,
 				unsigned int mask, unsigned int value);
 
 #ifdef CONFIG_SND_SOC_AC97_BUS
-int snd_soc_new_ac97_codec(struct snd_soc_codec *codec,
-	struct snd_ac97_bus_ops *ops, int num);
+int snd_soc_new_ac97_codec(struct snd_soc_codec *codec);
 void snd_soc_free_ac97_codec(struct snd_soc_codec *codec);
 
 int snd_soc_set_ac97_ops(struct snd_ac97_bus_ops *ops);
diff --git a/sound/soc/codecs/ad1980.c b/sound/soc/codecs/ad1980.c
index 9ed4e12c26d..f71cc21e67d 100644
--- a/sound/soc/codecs/ad1980.c
+++ b/sound/soc/codecs/ad1980.c
@@ -220,7 +220,7 @@ static int ad1980_soc_probe(struct snd_soc_codec *codec)
 	u16 vendor_id2;
 	u16 ext_status;
 
-	ret = snd_soc_new_ac97_codec(codec, soc_ac97_ops, 0);
+	ret = snd_soc_new_ac97_codec(codec);
 	if (ret < 0) {
 		dev_err(codec->dev, "Failed to register AC97 codec\n");
 		return ret;
diff --git a/sound/soc/codecs/stac9766.c b/sound/soc/codecs/stac9766.c
index 53b810d23fe..45ac4a71ecf 100644
--- a/sound/soc/codecs/stac9766.c
+++ b/sound/soc/codecs/stac9766.c
@@ -336,7 +336,7 @@ static int stac9766_codec_probe(struct snd_soc_codec *codec)
 {
 	int ret = 0;
 
-	ret = snd_soc_new_ac97_codec(codec, soc_ac97_ops, 0);
+	ret = snd_soc_new_ac97_codec(codec);
 	if (ret < 0)
 		goto codec_err;
 
diff --git a/sound/soc/codecs/wm9705.c b/sound/soc/codecs/wm9705.c
index 1650195f6c8..2cb8a31819f 100644
--- a/sound/soc/codecs/wm9705.c
+++ b/sound/soc/codecs/wm9705.c
@@ -337,7 +337,7 @@ static int wm9705_soc_probe(struct snd_soc_codec *codec)
 {
 	int ret = 0;
 
-	ret = snd_soc_new_ac97_codec(codec, soc_ac97_ops, 0);
+	ret = snd_soc_new_ac97_codec(codec);
 	if (ret < 0) {
 		dev_err(codec->dev, "Failed to register AC97 codec\n");
 		return ret;
diff --git a/sound/soc/codecs/wm9712.c b/sound/soc/codecs/wm9712.c
index 3fad37e0d33..6b36223fd24 100644
--- a/sound/soc/codecs/wm9712.c
+++ b/sound/soc/codecs/wm9712.c
@@ -666,7 +666,7 @@ static int wm9712_soc_probe(struct snd_soc_codec *codec)
 {
 	int ret = 0;
 
-	ret = snd_soc_new_ac97_codec(codec, soc_ac97_ops, 0);
+	ret = snd_soc_new_ac97_codec(codec);
 	if (ret < 0) {
 		dev_err(codec->dev, "Failed to register AC97 codec\n");
 		return ret;
diff --git a/sound/soc/codecs/wm9713.c b/sound/soc/codecs/wm9713.c
index 998e4c7b6b1..2071df707e8 100644
--- a/sound/soc/codecs/wm9713.c
+++ b/sound/soc/codecs/wm9713.c
@@ -1219,7 +1219,7 @@ static int wm9713_soc_probe(struct snd_soc_codec *codec)
 {
 	int ret = 0, reg;
 
-	ret = snd_soc_new_ac97_codec(codec, soc_ac97_ops, 0);
+	ret = snd_soc_new_ac97_codec(codec);
 	if (ret < 0)
 		return ret;
 
diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c
index da7b031a6ee..dbfca7e7ddd 100644
--- a/sound/soc/soc-ac97.c
+++ b/sound/soc/soc-ac97.c
@@ -38,6 +38,10 @@ struct snd_ac97_reset_cfg {
 	int gpio_reset;
 };
 
+static struct snd_ac97_bus soc_ac97_bus = {
+	.ops = NULL, /* Gets initialized in snd_soc_set_ac97_ops() */
+};
+
 /* unregister ac97 codec */
 static int soc_ac97_dev_unregister(struct snd_soc_codec *codec)
 {
@@ -140,27 +144,17 @@ static void soc_ac97_device_release(struct device *dev)
 /**
  * snd_soc_new_ac97_codec - initailise AC97 device
  * @codec: audio codec
- * @ops: AC97 bus operations
- * @num: AC97 codec number
  *
  * Initialises AC97 codec resources for use by ad-hoc devices only.
  */
-int snd_soc_new_ac97_codec(struct snd_soc_codec *codec,
-	struct snd_ac97_bus_ops *ops, int num)
+int snd_soc_new_ac97_codec(struct snd_soc_codec *codec)
 {
 	codec->ac97 = kzalloc(sizeof(struct snd_ac97), GFP_KERNEL);
 	if (codec->ac97 == NULL)
 		return -ENOMEM;
 
-	codec->ac97->bus = kzalloc(sizeof(struct snd_ac97_bus), GFP_KERNEL);
-	if (codec->ac97->bus == NULL) {
-		kfree(codec->ac97);
-		codec->ac97 = NULL;
-		return -ENOMEM;
-	}
-
-	codec->ac97->bus->ops = ops;
-	codec->ac97->num = num;
+	codec->ac97->bus = &soc_ac97_bus;
+	codec->ac97->num = 0;
 	codec->ac97->dev.release = soc_ac97_device_release;
 
 	/*
@@ -183,7 +177,6 @@ EXPORT_SYMBOL_GPL(snd_soc_new_ac97_codec);
 void snd_soc_free_ac97_codec(struct snd_soc_codec *codec)
 {
 	soc_unregister_ac97_codec(codec);
-	kfree(codec->ac97->bus);
 	codec->ac97->bus = NULL;
 	put_device(&codec->ac97->dev);
 	codec->ac97 = NULL;
@@ -314,6 +307,7 @@ int snd_soc_set_ac97_ops(struct snd_ac97_bus_ops *ops)
 		return -EBUSY;
 
 	soc_ac97_ops = ops;
+	soc_ac97_bus.ops = ops;
 
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From ca005f324ee38308b319c693f40523d959027acf Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 10 Nov 2014 22:41:49 +0100
Subject: ASoC: ac97: Drop support for setting platform data via the CPU DAI

This has no users since commit f0fba2ad1b6b ("ASoC: multi-component - ASoC
Multi-Component Support") which was almost 5 years ago. Given that this runs
after CODEC probe functions have been run it also doesn't seem to be that
useful.

So drop it altogether to make the code simpler.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dai.h |  1 -
 include/sound/soc.h     |  3 ---
 sound/soc/soc-ac97.c    | 12 ------------
 sound/soc/soc-core.c    |  2 --
 4 files changed, 18 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index e8b3080d196..c0e04688c6e 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -241,7 +241,6 @@ struct snd_soc_dai {
 	const char *name;
 	int id;
 	struct device *dev;
-	void *ac97_pdata;	/* platform_data for the ac97 codec */
 
 	/* driver ops */
 	struct snd_soc_dai_driver *driver;
diff --git a/include/sound/soc.h b/include/sound/soc.h
index 44b3ce531fd..5b4dec693ca 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -509,7 +509,6 @@ int snd_soc_set_ac97_ops_of_reset(struct snd_ac97_bus_ops *ops,
 extern struct snd_ac97_bus_ops *soc_ac97_ops;
 
 int snd_soc_ac97_register_dai_links(struct snd_soc_card *card);
-void snd_soc_ac97_add_pdata(struct snd_soc_pcm_runtime *rtd);
 #else
 
 static inline int snd_soc_ac97_register_dai_links(struct snd_soc_card *card)
@@ -517,8 +516,6 @@ static inline int snd_soc_ac97_register_dai_links(struct snd_soc_card *card)
 	return 0;
 }
 
-static inline void snd_soc_ac97_add_pdata(struct snd_soc_pcm_runtime *rtd) {}
-
 static inline int snd_soc_set_ac97_ops_of_reset(struct snd_ac97_bus_ops *ops,
 	struct platform_device *pdev)
 {
diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c
index b5d23c97666..f2ed77b5169 100644
--- a/sound/soc/soc-ac97.c
+++ b/sound/soc/soc-ac97.c
@@ -342,15 +342,3 @@ err:
 		soc_unregister_ac97_dai_link(&card->rtd[i]);
 	return ret;
 }
-
-void snd_soc_ac97_add_pdata(struct snd_soc_pcm_runtime *rtd)
-{
-	unsigned int i;
-
-	/* add platform data for AC97 devices */
-	for (i = 0; i < rtd->num_codecs; i++) {
-		if (rtd->codec_dais[i]->driver->ac97_control)
-			snd_ac97_dev_add_pdata(rtd->codec_dais[i]->codec->ac97,
-					       rtd->cpu_dai->ac97_pdata);
-	}
-}
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 026722f5ebf..d883b4ad03a 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1375,8 +1375,6 @@ static int soc_probe_link_dais(struct snd_soc_card *card, int num, int order)
 		}
 	}
 
-	snd_soc_ac97_add_pdata(rtd);
-
 	return 0;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 6794f709b7124ff1e574c4f4c9494418ab56c4b4 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 10 Nov 2014 22:41:50 +0100
Subject: ASoC: ac97: Drop delayed device registration

We have all the information and dependencies we need to initialize and
register the device available in snd_soc_new_ac97_codec(). So there is no
need to delay the device registration until after the card itself as been
registered.

This makes the code significantly simpler and also makes it possible to use
the AC'97 device in the CODECs probe function. The later will be required to
be able to convert the AC'97 CODEC drivers to regmap.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  |  10 -----
 sound/soc/soc-ac97.c | 118 ++++++---------------------------------------------
 sound/soc/soc-core.c |   4 --
 3 files changed, 14 insertions(+), 118 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 5b4dec693ca..206cc8d6eef 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -507,15 +507,7 @@ int snd_soc_set_ac97_ops_of_reset(struct snd_ac97_bus_ops *ops,
 		struct platform_device *pdev);
 
 extern struct snd_ac97_bus_ops *soc_ac97_ops;
-
-int snd_soc_ac97_register_dai_links(struct snd_soc_card *card);
 #else
-
-static inline int snd_soc_ac97_register_dai_links(struct snd_soc_card *card)
-{
-	return 0;
-}
-
 static inline int snd_soc_set_ac97_ops_of_reset(struct snd_ac97_bus_ops *ops,
 	struct platform_device *pdev)
 {
@@ -808,8 +800,6 @@ struct snd_soc_codec {
 	struct snd_ac97 *ac97;  /* for ad-hoc ac97 devices */
 	unsigned int cache_bypass:1; /* Suppress access to the cache */
 	unsigned int suspended:1; /* Codec is in suspend PM state */
-	unsigned int ac97_registered:1; /* Codec has been AC97 registered */
-	unsigned int ac97_created:1; /* Codec has been created by SoC */
 	unsigned int cache_init:1; /* codec cache has been initialized */
 	u32 cache_sync; /* Cache needs to be synced to hardware */
 
diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c
index f2ed77b5169..920d76c4382 100644
--- a/sound/soc/soc-ac97.c
+++ b/sound/soc/soc-ac97.c
@@ -42,80 +42,6 @@ static struct snd_ac97_bus soc_ac97_bus = {
 	.ops = NULL, /* Gets initialized in snd_soc_set_ac97_ops() */
 };
 
-/* register ac97 codec to bus */
-static int soc_register_ac97_codec(struct snd_soc_codec *codec,
-	struct snd_soc_dai *codec_dai)
-{
-	int ret;
-
-	/* Only instantiate AC97 if not already done by the adaptor
-	 * for the generic AC97 subsystem.
-	 */
-	if (!codec_dai->driver->ac97_control || codec->ac97_registered)
-		return 0;
-
-	/*
-	 * It is possible that the AC97 device is already registered to
-	 * the device subsystem. This happens when the device is created
-	 * via snd_ac97_mixer(). Currently only SoC codec that does so
-	 * is the generic AC97 glue but others migh emerge.
-	 *
-	 * In those cases we don't try to register the device again.
-	 */
-	if (!codec->ac97_created)
-		return 0;
-
-	codec->ac97->dev.bus = &ac97_bus_type;
-	codec->ac97->dev.parent = codec->component.card->dev;
-
-	dev_set_name(&codec->ac97->dev, "%d-%d:%s",
-		     codec->component.card->snd_card->number, 0,
-		     codec->component.name);
-	ret = device_add(&codec->ac97->dev);
-	if (ret < 0) {
-		dev_err(codec->dev, "ASoC: AC97 device register failed: %d\n",
-			ret);
-		return ret;
-	}
-	codec->ac97_registered = 1;
-
-	return 0;
-}
-
-static void soc_unregister_ac97_codec(struct snd_soc_codec *codec)
-{
-	if (!codec->ac97_registered)
-		return;
-	device_del(&codec->ac97->dev);
-	codec->ac97_registered = 0;
-}
-
-static int soc_register_ac97_dai_link(struct snd_soc_pcm_runtime *rtd)
-{
-	int i, ret;
-
-	for (i = 0; i < rtd->num_codecs; i++) {
-		struct snd_soc_dai *codec_dai = rtd->codec_dais[i];
-
-		ret = soc_register_ac97_codec(codec_dai->codec, codec_dai);
-		if (ret) {
-			while (--i >= 0)
-				soc_unregister_ac97_codec(codec_dai->codec);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-static void soc_unregister_ac97_dai_link(struct snd_soc_pcm_runtime *rtd)
-{
-	int i;
-
-	for (i = 0; i < rtd->num_codecs; i++)
-		soc_unregister_ac97_codec(rtd->codec_dais[i]->codec);
-}
-
 static void soc_ac97_device_release(struct device *dev)
 {
 	kfree(to_ac97_t(dev));
@@ -129,22 +55,28 @@ static void soc_ac97_device_release(struct device *dev)
  */
 int snd_soc_new_ac97_codec(struct snd_soc_codec *codec)
 {
+	int ret;
+
 	codec->ac97 = kzalloc(sizeof(struct snd_ac97), GFP_KERNEL);
 	if (codec->ac97 == NULL)
 		return -ENOMEM;
 
 	codec->ac97->bus = &soc_ac97_bus;
 	codec->ac97->num = 0;
+
+	codec->ac97->dev.bus = &ac97_bus_type;
+	codec->ac97->dev.parent = codec->component.card->dev;
 	codec->ac97->dev.release = soc_ac97_device_release;
 
-	/*
-	 * Mark the AC97 device to be created by us. This way we ensure that the
-	 * device will be registered with the device subsystem later on.
-	 */
-	codec->ac97_created = 1;
-	device_initialize(&codec->ac97->dev);
+	dev_set_name(&codec->ac97->dev, "%d-%d:%s",
+		     codec->component.card->snd_card->number, 0,
+		     codec->component.name);
+
+	ret = device_register(&codec->ac97->dev);
+	if (ret)
+		put_device(&codec->ac97->dev);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_soc_new_ac97_codec);
 
@@ -156,11 +88,10 @@ EXPORT_SYMBOL_GPL(snd_soc_new_ac97_codec);
  */
 void snd_soc_free_ac97_codec(struct snd_soc_codec *codec)
 {
-	soc_unregister_ac97_codec(codec);
+	device_del(&codec->ac97->dev);
 	codec->ac97->bus = NULL;
 	put_device(&codec->ac97->dev);
 	codec->ac97 = NULL;
-	codec->ac97_created = 0;
 }
 EXPORT_SYMBOL_GPL(snd_soc_free_ac97_codec);
 
@@ -321,24 +252,3 @@ int snd_soc_set_ac97_ops_of_reset(struct snd_ac97_bus_ops *ops,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(snd_soc_set_ac97_ops_of_reset);
-
-int snd_soc_ac97_register_dai_links(struct snd_soc_card *card)
-{
-	int i;
-	int ret;
-
-	/* register any AC97 codecs */
-	for (i = 0; i < card->num_rtd; i++) {
-		ret = soc_register_ac97_dai_link(&card->rtd[i]);
-		if (ret < 0)
-			goto err;
-	}
-
-	return 0;
-err:
-	dev_err(card->dev,
-		"ASoC: failed to register AC97: %d\n", ret);
-	while (--i >= 0)
-		soc_unregister_ac97_dai_link(&card->rtd[i]);
-	return ret;
-}
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index d883b4ad03a..fba6e28e18d 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1671,10 +1671,6 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 		goto probe_aux_dev_err;
 	}
 
-	ret = snd_soc_ac97_register_dai_links(card);
-	if (ret < 0)
-		goto probe_aux_dev_err;
-
 	card->instantiated = 1;
 	snd_soc_dapm_sync(&card->dapm);
 	mutex_unlock(&card->mutex);
-- 
cgit v1.2.3-70-g09d2


From bc2632140435cc84f9817f1c362479b23dbdfebc Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 10 Nov 2014 22:41:52 +0100
Subject: ASoC: Rename snd_soc_dai_driver struct ac97_control field to
 bus_control

Setting the ac97_control field on a CPU DAI tells the ASoC core that this
DAI in addition to audio data also transports control data to the CODEC.
This causes the core to suspend the DAI after the CODEC and resume it before
the CODEC so communication to the CODEC is still possible. This is not
necessarily something that is specific to AC'97 and can be used by other
buses with the same requirement. This patch renames the flag from
ac97_control to bus_control to make this explicit.

While we are at it also change the type from int to bool.

The following semantich patch was used for automatic conversion of the
drivers:
// <smpl>
@@
identifier drv;
@@
struct snd_soc_dai_driver drv = {
-	.ac97_control
+	.bus_control
	=
-	1
+	true
};
// </smpl>

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dai.h          |  3 ++-
 sound/soc/au1x/ac97c.c           |  2 +-
 sound/soc/au1x/psc-ac97.c        |  2 +-
 sound/soc/blackfin/bf5xx-ac97.c  |  2 +-
 sound/soc/cirrus/ep93xx-ac97.c   |  2 +-
 sound/soc/fsl/fsl_ssi.c          |  2 +-
 sound/soc/fsl/imx-ssi.c          |  2 +-
 sound/soc/fsl/mpc5200_psc_ac97.c |  4 ++--
 sound/soc/nuc900/nuc900-ac97.c   |  2 +-
 sound/soc/pxa/pxa2xx-ac97.c      |  6 +++---
 sound/soc/samsung/ac97.c         |  4 ++--
 sound/soc/sh/hac.c               |  2 +-
 sound/soc/soc-core.c             | 26 ++++++++++++++------------
 sound/soc/tegra/tegra20_ac97.c   |  2 +-
 sound/soc/txx9/txx9aclc-ac97.c   |  2 +-
 15 files changed, 33 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index c0e04688c6e..a3738be4556 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -206,7 +206,6 @@ struct snd_soc_dai_driver {
 	/* DAI description */
 	const char *name;
 	unsigned int id;
-	int ac97_control;
 	unsigned int base;
 
 	/* DAI driver callbacks */
@@ -216,6 +215,8 @@ struct snd_soc_dai_driver {
 	int (*resume)(struct snd_soc_dai *dai);
 	/* compress dai */
 	bool compress_dai;
+	/* DAI is also used for the control bus */
+	bool bus_control;
 
 	/* ops */
 	const struct snd_soc_dai_ops *ops;
diff --git a/sound/soc/au1x/ac97c.c b/sound/soc/au1x/ac97c.c
index c8a2de103c5..5159a50a45a 100644
--- a/sound/soc/au1x/ac97c.c
+++ b/sound/soc/au1x/ac97c.c
@@ -205,7 +205,7 @@ static int au1xac97c_dai_probe(struct snd_soc_dai *dai)
 
 static struct snd_soc_dai_driver au1xac97c_dai_driver = {
 	.name			= "alchemy-ac97c",
-	.ac97_control		= 1,
+	.bus_control		= true,
 	.probe			= au1xac97c_dai_probe,
 	.playback = {
 		.rates		= AC97_RATES,
diff --git a/sound/soc/au1x/psc-ac97.c b/sound/soc/au1x/psc-ac97.c
index 84f31e1f9d2..c6daec98ff8 100644
--- a/sound/soc/au1x/psc-ac97.c
+++ b/sound/soc/au1x/psc-ac97.c
@@ -343,7 +343,7 @@ static const struct snd_soc_dai_ops au1xpsc_ac97_dai_ops = {
 };
 
 static const struct snd_soc_dai_driver au1xpsc_ac97_dai_template = {
-	.ac97_control		= 1,
+	.bus_control		= true,
 	.probe			= au1xpsc_ac97_probe,
 	.playback = {
 		.rates		= AC97_RATES,
diff --git a/sound/soc/blackfin/bf5xx-ac97.c b/sound/soc/blackfin/bf5xx-ac97.c
index e82eb373a73..6bf21a6c02e 100644
--- a/sound/soc/blackfin/bf5xx-ac97.c
+++ b/sound/soc/blackfin/bf5xx-ac97.c
@@ -260,7 +260,7 @@ static int bf5xx_ac97_resume(struct snd_soc_dai *dai)
 #endif
 
 static struct snd_soc_dai_driver bfin_ac97_dai = {
-	.ac97_control = 1,
+	.bus_control = true,
 	.suspend = bf5xx_ac97_suspend,
 	.resume = bf5xx_ac97_resume,
 	.playback = {
diff --git a/sound/soc/cirrus/ep93xx-ac97.c b/sound/soc/cirrus/ep93xx-ac97.c
index f30dadf85b9..6b8a366b021 100644
--- a/sound/soc/cirrus/ep93xx-ac97.c
+++ b/sound/soc/cirrus/ep93xx-ac97.c
@@ -338,7 +338,7 @@ static const struct snd_soc_dai_ops ep93xx_ac97_dai_ops = {
 static struct snd_soc_dai_driver ep93xx_ac97_dai = {
 	.name		= "ep93xx-ac97",
 	.id		= 0,
-	.ac97_control	= 1,
+	.bus_control	= true,
 	.probe		= ep93xx_ac97_dai_probe,
 	.playback	= {
 		.stream_name	= "AC97 Playback",
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index e6955170dc4..7fd3cbcd74c 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -1099,7 +1099,7 @@ static const struct snd_soc_component_driver fsl_ssi_component = {
 };
 
 static struct snd_soc_dai_driver fsl_ssi_ac97_dai = {
-	.ac97_control = 1,
+	.bus_control = true,
 	.playback = {
 		.stream_name = "AC97 Playback",
 		.channels_min = 2,
diff --git a/sound/soc/fsl/imx-ssi.c b/sound/soc/fsl/imx-ssi.c
index ab2fdd76b69..60b0a5b1f1f 100644
--- a/sound/soc/fsl/imx-ssi.c
+++ b/sound/soc/fsl/imx-ssi.c
@@ -382,7 +382,7 @@ static struct snd_soc_dai_driver imx_ssi_dai = {
 
 static struct snd_soc_dai_driver imx_ac97_dai = {
 	.probe = imx_ssi_dai_probe,
-	.ac97_control = 1,
+	.bus_control = true,
 	.playback = {
 		.stream_name = "AC97 Playback",
 		.channels_min = 2,
diff --git a/sound/soc/fsl/mpc5200_psc_ac97.c b/sound/soc/fsl/mpc5200_psc_ac97.c
index 640801a60c1..c6ed6ba965a 100644
--- a/sound/soc/fsl/mpc5200_psc_ac97.c
+++ b/sound/soc/fsl/mpc5200_psc_ac97.c
@@ -237,7 +237,7 @@ static const struct snd_soc_dai_ops psc_ac97_digital_ops = {
 static struct snd_soc_dai_driver psc_ac97_dai[] = {
 {
 	.name = "mpc5200-psc-ac97.0",
-	.ac97_control = 1,
+	.bus_control = true,
 	.probe	= psc_ac97_probe,
 	.playback = {
 		.stream_name	= "AC97 Playback",
@@ -257,7 +257,7 @@ static struct snd_soc_dai_driver psc_ac97_dai[] = {
 },
 {
 	.name = "mpc5200-psc-ac97.1",
-	.ac97_control = 1,
+	.bus_control = true,
 	.playback = {
 		.stream_name	= "AC97 SPDIF",
 		.channels_min   = 1,
diff --git a/sound/soc/nuc900/nuc900-ac97.c b/sound/soc/nuc900/nuc900-ac97.c
index f2f67942b22..dff443e4b65 100644
--- a/sound/soc/nuc900/nuc900-ac97.c
+++ b/sound/soc/nuc900/nuc900-ac97.c
@@ -298,7 +298,7 @@ static const struct snd_soc_dai_ops nuc900_ac97_dai_ops = {
 static struct snd_soc_dai_driver nuc900_ac97_dai = {
 	.probe			= nuc900_ac97_probe,
 	.remove			= nuc900_ac97_remove,
-	.ac97_control		= 1,
+	.bus_control		= true,
 	.playback = {
 		.rates		= SNDRV_PCM_RATE_8000_48000,
 		.formats	= SNDRV_PCM_FMTBIT_S16_LE,
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index ae956e3f4b9..73ca2820c08 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -157,7 +157,7 @@ static const struct snd_soc_dai_ops pxa_ac97_mic_dai_ops = {
 static struct snd_soc_dai_driver pxa_ac97_dai_driver[] = {
 {
 	.name = "pxa2xx-ac97",
-	.ac97_control = 1,
+	.bus_control = true,
 	.playback = {
 		.stream_name = "AC97 Playback",
 		.channels_min = 2,
@@ -174,7 +174,7 @@ static struct snd_soc_dai_driver pxa_ac97_dai_driver[] = {
 },
 {
 	.name = "pxa2xx-ac97-aux",
-	.ac97_control = 1,
+	.bus_control = true,
 	.playback = {
 		.stream_name = "AC97 Aux Playback",
 		.channels_min = 1,
@@ -191,7 +191,7 @@ static struct snd_soc_dai_driver pxa_ac97_dai_driver[] = {
 },
 {
 	.name = "pxa2xx-ac97-mic",
-	.ac97_control = 1,
+	.bus_control = true,
 	.capture = {
 		.stream_name = "AC97 Mic Capture",
 		.channels_min = 1,
diff --git a/sound/soc/samsung/ac97.c b/sound/soc/samsung/ac97.c
index e1615113fd8..7952a625669 100644
--- a/sound/soc/samsung/ac97.c
+++ b/sound/soc/samsung/ac97.c
@@ -288,7 +288,7 @@ static int s3c_ac97_mic_dai_probe(struct snd_soc_dai *dai)
 static struct snd_soc_dai_driver s3c_ac97_dai[] = {
 	[S3C_AC97_DAI_PCM] = {
 		.name =	"samsung-ac97",
-		.ac97_control = 1,
+		.bus_control = true,
 		.playback = {
 			.stream_name = "AC97 Playback",
 			.channels_min = 2,
@@ -306,7 +306,7 @@ static struct snd_soc_dai_driver s3c_ac97_dai[] = {
 	},
 	[S3C_AC97_DAI_MIC] = {
 		.name = "samsung-ac97-mic",
-		.ac97_control = 1,
+		.bus_control = true,
 		.capture = {
 			.stream_name = "AC97 Mic Capture",
 			.channels_min = 1,
diff --git a/sound/soc/sh/hac.c b/sound/soc/sh/hac.c
index 0af2e4dfd13..d5f567e085f 100644
--- a/sound/soc/sh/hac.c
+++ b/sound/soc/sh/hac.c
@@ -272,7 +272,7 @@ static const struct snd_soc_dai_ops hac_dai_ops = {
 static struct snd_soc_dai_driver sh4_hac_dai[] = {
 {
 	.name			= "hac-dai.0",
-	.ac97_control		= 1,
+	.bus_control		= true,
 	.playback = {
 		.rates		= AC97_RATES,
 		.formats	= AC97_FMTS,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index fba6e28e18d..f5bebca84b7 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -550,7 +550,7 @@ int snd_soc_suspend(struct device *dev)
 		if (card->rtd[i].dai_link->ignore_suspend)
 			continue;
 
-		if (cpu_dai->driver->suspend && !cpu_dai->driver->ac97_control)
+		if (cpu_dai->driver->suspend && !cpu_dai->driver->bus_control)
 			cpu_dai->driver->suspend(cpu_dai);
 		if (platform->driver->suspend && !platform->suspended) {
 			platform->driver->suspend(cpu_dai);
@@ -629,7 +629,7 @@ int snd_soc_suspend(struct device *dev)
 		if (card->rtd[i].dai_link->ignore_suspend)
 			continue;
 
-		if (cpu_dai->driver->suspend && cpu_dai->driver->ac97_control)
+		if (cpu_dai->driver->suspend && cpu_dai->driver->bus_control)
 			cpu_dai->driver->suspend(cpu_dai);
 
 		/* deactivate pins to sleep state */
@@ -665,14 +665,14 @@ static void soc_resume_deferred(struct work_struct *work)
 	if (card->resume_pre)
 		card->resume_pre(card);
 
-	/* resume AC97 DAIs */
+	/* resume control bus DAIs */
 	for (i = 0; i < card->num_rtd; i++) {
 		struct snd_soc_dai *cpu_dai = card->rtd[i].cpu_dai;
 
 		if (card->rtd[i].dai_link->ignore_suspend)
 			continue;
 
-		if (cpu_dai->driver->resume && cpu_dai->driver->ac97_control)
+		if (cpu_dai->driver->resume && cpu_dai->driver->bus_control)
 			cpu_dai->driver->resume(cpu_dai);
 	}
 
@@ -733,7 +733,7 @@ static void soc_resume_deferred(struct work_struct *work)
 		if (card->rtd[i].dai_link->ignore_suspend)
 			continue;
 
-		if (cpu_dai->driver->resume && !cpu_dai->driver->ac97_control)
+		if (cpu_dai->driver->resume && !cpu_dai->driver->bus_control)
 			cpu_dai->driver->resume(cpu_dai);
 		if (platform->driver->resume && platform->suspended) {
 			platform->driver->resume(cpu_dai);
@@ -758,7 +758,8 @@ static void soc_resume_deferred(struct work_struct *work)
 int snd_soc_resume(struct device *dev)
 {
 	struct snd_soc_card *card = dev_get_drvdata(dev);
-	int i, ac97_control = 0;
+	bool bus_control = false;
+	int i;
 
 	/* If the card is not initialized yet there is nothing to do */
 	if (!card->instantiated)
@@ -781,17 +782,18 @@ int snd_soc_resume(struct device *dev)
 		}
 	}
 
-	/* AC97 devices might have other drivers hanging off them so
-	 * need to resume immediately.  Other drivers don't have that
-	 * problem and may take a substantial amount of time to resume
+	/*
+	 * DAIs that also act as the control bus master might have other drivers
+	 * hanging off them so need to resume immediately. Other drivers don't
+	 * have that problem and may take a substantial amount of time to resume
 	 * due to I/O costs and anti-pop so handle them out of line.
 	 */
 	for (i = 0; i < card->num_rtd; i++) {
 		struct snd_soc_dai *cpu_dai = card->rtd[i].cpu_dai;
-		ac97_control |= cpu_dai->driver->ac97_control;
+		bus_control |= cpu_dai->driver->bus_control;
 	}
-	if (ac97_control) {
-		dev_dbg(dev, "ASoC: Resuming AC97 immediately\n");
+	if (bus_control) {
+		dev_dbg(dev, "ASoC: Resuming control bus master immediately\n");
 		soc_resume_deferred(&card->deferred_resume_work);
 	} else {
 		dev_dbg(dev, "ASoC: Scheduling resume work\n");
diff --git a/sound/soc/tegra/tegra20_ac97.c b/sound/soc/tegra/tegra20_ac97.c
index 3b0fa12dbff..29a9957d335 100644
--- a/sound/soc/tegra/tegra20_ac97.c
+++ b/sound/soc/tegra/tegra20_ac97.c
@@ -228,7 +228,7 @@ static int tegra20_ac97_probe(struct snd_soc_dai *dai)
 
 static struct snd_soc_dai_driver tegra20_ac97_dai = {
 	.name = "tegra-ac97-pcm",
-	.ac97_control = 1,
+	.bus_control = true,
 	.probe = tegra20_ac97_probe,
 	.playback = {
 		.stream_name = "PCM Playback",
diff --git a/sound/soc/txx9/txx9aclc-ac97.c b/sound/soc/txx9/txx9aclc-ac97.c
index 9edd68db9f4..f7135cdaa2c 100644
--- a/sound/soc/txx9/txx9aclc-ac97.c
+++ b/sound/soc/txx9/txx9aclc-ac97.c
@@ -152,7 +152,7 @@ static int txx9aclc_ac97_remove(struct snd_soc_dai *dai)
 }
 
 static struct snd_soc_dai_driver txx9aclc_ac97_dai = {
-	.ac97_control		= 1,
+	.bus_control		= true,
 	.probe			= txx9aclc_ac97_probe,
 	.remove			= txx9aclc_ac97_remove,
 	.playback = {
-- 
cgit v1.2.3-70-g09d2


From 358a8bb5628420529e4f0b77068155ca8fa8973b Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 10 Nov 2014 22:41:53 +0100
Subject: ASoC: ac97: Push snd_ac97 pointer to the driver level

Now that the ASoC core no longer needs a handle to the AC'97 device that is
associated with a CODEC we can remove it from the snd_soc_codec struct and
push it into the individual driver state structs like we do for other
communication buses. Doing so creates a clean separation between the AC'97
bus support and the ASoC core.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h         |  5 ++---
 sound/soc/codecs/ac97.c     | 17 +++++++++++++----
 sound/soc/codecs/ad1980.c   | 27 ++++++++++++++++++---------
 sound/soc/codecs/stac9766.c | 38 ++++++++++++++++++++++++--------------
 sound/soc/codecs/wm9705.c   | 31 ++++++++++++++++++++++---------
 sound/soc/codecs/wm9712.c   | 32 +++++++++++++++++++++-----------
 sound/soc/codecs/wm9713.c   | 31 ++++++++++++++++++++-----------
 sound/soc/soc-ac97.c        | 40 +++++++++++++++++++++-------------------
 8 files changed, 141 insertions(+), 80 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 206cc8d6eef..9e513ae1174 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -499,8 +499,8 @@ int snd_soc_test_bits(struct snd_soc_codec *codec, unsigned int reg,
 				unsigned int mask, unsigned int value);
 
 #ifdef CONFIG_SND_SOC_AC97_BUS
-int snd_soc_new_ac97_codec(struct snd_soc_codec *codec);
-void snd_soc_free_ac97_codec(struct snd_soc_codec *codec);
+struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec);
+void snd_soc_free_ac97_codec(struct snd_ac97 *ac97);
 
 int snd_soc_set_ac97_ops(struct snd_ac97_bus_ops *ops);
 int snd_soc_set_ac97_ops_of_reset(struct snd_ac97_bus_ops *ops,
@@ -797,7 +797,6 @@ struct snd_soc_codec {
 	struct list_head card_list;
 
 	/* runtime */
-	struct snd_ac97 *ac97;  /* for ad-hoc ac97 devices */
 	unsigned int cache_bypass:1; /* Suppress access to the cache */
 	unsigned int suspended:1; /* Codec is in suspend PM state */
 	unsigned int cache_init:1; /* codec cache has been initialized */
diff --git a/sound/soc/codecs/ac97.c b/sound/soc/codecs/ac97.c
index 5d90924e8b9..c6e5a313ebf 100644
--- a/sound/soc/codecs/ac97.c
+++ b/sound/soc/codecs/ac97.c
@@ -37,10 +37,11 @@ static int ac97_prepare(struct snd_pcm_substream *substream,
 			struct snd_soc_dai *dai)
 {
 	struct snd_soc_codec *codec = dai->codec;
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
 
 	int reg = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ?
 		  AC97_PCM_FRONT_DAC_RATE : AC97_PCM_LR_ADC_RATE;
-	return snd_ac97_set_rate(codec->ac97, reg, substream->runtime->rate);
+	return snd_ac97_set_rate(ac97, reg, substream->runtime->rate);
 }
 
 #define STD_AC97_RATES (SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_11025 |\
@@ -70,6 +71,7 @@ static struct snd_soc_dai_driver ac97_dai = {
 
 static int ac97_soc_probe(struct snd_soc_codec *codec)
 {
+	struct snd_ac97 *ac97;
 	struct snd_ac97_bus *ac97_bus;
 	struct snd_ac97_template ac97_template;
 	int ret;
@@ -81,24 +83,31 @@ static int ac97_soc_probe(struct snd_soc_codec *codec)
 		return ret;
 
 	memset(&ac97_template, 0, sizeof(struct snd_ac97_template));
-	ret = snd_ac97_mixer(ac97_bus, &ac97_template, &codec->ac97);
+	ret = snd_ac97_mixer(ac97_bus, &ac97_template, &ac97);
 	if (ret < 0)
 		return ret;
 
+	snd_soc_codec_set_drvdata(codec, ac97);
+
 	return 0;
 }
 
 #ifdef CONFIG_PM
 static int ac97_soc_suspend(struct snd_soc_codec *codec)
 {
-	snd_ac97_suspend(codec->ac97);
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
+
+	snd_ac97_suspend(ac97);
 
 	return 0;
 }
 
 static int ac97_soc_resume(struct snd_soc_codec *codec)
 {
-	snd_ac97_resume(codec->ac97);
+
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
+
+	snd_ac97_resume(ac97);
 
 	return 0;
 }
diff --git a/sound/soc/codecs/ad1980.c b/sound/soc/codecs/ad1980.c
index c6cb101a5b8..93bd47db6d0 100644
--- a/sound/soc/codecs/ad1980.c
+++ b/sound/soc/codecs/ad1980.c
@@ -135,6 +135,7 @@ static const struct snd_soc_dapm_route ad1980_dapm_routes[] = {
 static unsigned int ac97_read(struct snd_soc_codec *codec,
 	unsigned int reg)
 {
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
 	u16 *cache = codec->reg_cache;
 
 	switch (reg) {
@@ -144,7 +145,7 @@ static unsigned int ac97_read(struct snd_soc_codec *codec,
 	case AC97_EXTENDED_STATUS:
 	case AC97_VENDOR_ID1:
 	case AC97_VENDOR_ID2:
-		return soc_ac97_ops->read(codec->ac97, reg);
+		return soc_ac97_ops->read(ac97, reg);
 	default:
 		reg = reg >> 1;
 
@@ -158,9 +159,10 @@ static unsigned int ac97_read(struct snd_soc_codec *codec,
 static int ac97_write(struct snd_soc_codec *codec, unsigned int reg,
 	unsigned int val)
 {
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
 	u16 *cache = codec->reg_cache;
 
-	soc_ac97_ops->write(codec->ac97, reg, val);
+	soc_ac97_ops->write(ac97, reg, val);
 	reg = reg >> 1;
 	if (reg < ARRAY_SIZE(ad1980_reg))
 		cache[reg] = val;
@@ -186,16 +188,17 @@ static struct snd_soc_dai_driver ad1980_dai = {
 
 static int ad1980_reset(struct snd_soc_codec *codec, int try_warm)
 {
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
 	unsigned int retry_cnt = 0;
 
 	do {
 		if (try_warm && soc_ac97_ops->warm_reset) {
-			soc_ac97_ops->warm_reset(codec->ac97);
+			soc_ac97_ops->warm_reset(ac97);
 			if (ac97_read(codec, AC97_RESET) == 0x0090)
 				return 1;
 		}
 
-		soc_ac97_ops->reset(codec->ac97);
+		soc_ac97_ops->reset(ac97);
 		/*
 		 * Set bit 16slot in register 74h, then every slot will has only
 		 * 16 bits. This command is sent out in 20bit mode, in which
@@ -215,16 +218,20 @@ static int ad1980_reset(struct snd_soc_codec *codec, int try_warm)
 
 static int ad1980_soc_probe(struct snd_soc_codec *codec)
 {
+	struct snd_ac97 *ac97;
 	int ret;
 	u16 vendor_id2;
 	u16 ext_status;
 
-	ret = snd_soc_new_ac97_codec(codec);
-	if (ret < 0) {
-		dev_err(codec->dev, "Failed to register AC97 codec\n");
+	ac97 = snd_soc_new_ac97_codec(codec);
+	if (IS_ERR(ac97)) {
+		ret = PTR_ERR(ac97);
+		dev_err(codec->dev, "Failed to register AC97 codec: %d\n", ret);
 		return ret;
 	}
 
+	snd_soc_codec_set_drvdata(codec, ac97);
+
 	ret = ad1980_reset(codec, 0);
 	if (ret < 0)
 		goto reset_err;
@@ -261,13 +268,15 @@ static int ad1980_soc_probe(struct snd_soc_codec *codec)
 	return 0;
 
 reset_err:
-	snd_soc_free_ac97_codec(codec);
+	snd_soc_free_ac97_codec(ac97);
 	return ret;
 }
 
 static int ad1980_soc_remove(struct snd_soc_codec *codec)
 {
-	snd_soc_free_ac97_codec(codec);
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
+
+	snd_soc_free_ac97_codec(ac97);
 	return 0;
 }
 
diff --git a/sound/soc/codecs/stac9766.c b/sound/soc/codecs/stac9766.c
index c0808061b08..f37a79ec45e 100644
--- a/sound/soc/codecs/stac9766.c
+++ b/sound/soc/codecs/stac9766.c
@@ -139,18 +139,19 @@ static const struct snd_kcontrol_new stac9766_snd_ac97_controls[] = {
 static int stac9766_ac97_write(struct snd_soc_codec *codec, unsigned int reg,
 			       unsigned int val)
 {
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
 	u16 *cache = codec->reg_cache;
 
 	if (reg > AC97_STAC_PAGE0) {
 		stac9766_ac97_write(codec, AC97_INT_PAGING, 0);
-		soc_ac97_ops->write(codec->ac97, reg, val);
+		soc_ac97_ops->write(ac97, reg, val);
 		stac9766_ac97_write(codec, AC97_INT_PAGING, 1);
 		return 0;
 	}
 	if (reg / 2 >= ARRAY_SIZE(stac9766_reg))
 		return -EIO;
 
-	soc_ac97_ops->write(codec->ac97, reg, val);
+	soc_ac97_ops->write(ac97, reg, val);
 	cache[reg / 2] = val;
 	return 0;
 }
@@ -158,11 +159,12 @@ static int stac9766_ac97_write(struct snd_soc_codec *codec, unsigned int reg,
 static unsigned int stac9766_ac97_read(struct snd_soc_codec *codec,
 				       unsigned int reg)
 {
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
 	u16 val = 0, *cache = codec->reg_cache;
 
 	if (reg > AC97_STAC_PAGE0) {
 		stac9766_ac97_write(codec, AC97_INT_PAGING, 0);
-		val = soc_ac97_ops->read(codec->ac97, reg - AC97_STAC_PAGE0);
+		val = soc_ac97_ops->read(ac97, reg - AC97_STAC_PAGE0);
 		stac9766_ac97_write(codec, AC97_INT_PAGING, 1);
 		return val;
 	}
@@ -173,7 +175,7 @@ static unsigned int stac9766_ac97_read(struct snd_soc_codec *codec,
 		reg == AC97_INT_PAGING || reg == AC97_VENDOR_ID1 ||
 		reg == AC97_VENDOR_ID2) {
 
-		val = soc_ac97_ops->read(codec->ac97, reg);
+		val = soc_ac97_ops->read(ac97, reg);
 		return val;
 	}
 	return cache[reg / 2];
@@ -240,15 +242,17 @@ static int stac9766_set_bias_level(struct snd_soc_codec *codec,
 
 static int stac9766_reset(struct snd_soc_codec *codec, int try_warm)
 {
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
+
 	if (try_warm && soc_ac97_ops->warm_reset) {
-		soc_ac97_ops->warm_reset(codec->ac97);
+		soc_ac97_ops->warm_reset(ac97);
 		if (stac9766_ac97_read(codec, 0) == stac9766_reg[0])
 			return 1;
 	}
 
-	soc_ac97_ops->reset(codec->ac97);
+	soc_ac97_ops->reset(ac97);
 	if (soc_ac97_ops->warm_reset)
-		soc_ac97_ops->warm_reset(codec->ac97);
+		soc_ac97_ops->warm_reset(ac97);
 	if (stac9766_ac97_read(codec, 0) != stac9766_reg[0])
 		return -EIO;
 	return 0;
@@ -262,6 +266,7 @@ static int stac9766_codec_suspend(struct snd_soc_codec *codec)
 
 static int stac9766_codec_resume(struct snd_soc_codec *codec)
 {
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
 	u16 id, reset;
 
 	reset = 0;
@@ -271,8 +276,8 @@ reset:
 		printk(KERN_ERR "stac9766 failed to resume");
 		return -EIO;
 	}
-	codec->ac97->bus->ops->warm_reset(codec->ac97);
-	id = soc_ac97_ops->read(codec->ac97, AC97_VENDOR_ID2);
+	ac97->bus->ops->warm_reset(ac97);
+	id = soc_ac97_ops->read(ac97, AC97_VENDOR_ID2);
 	if (id != 0x4c13) {
 		stac9766_reset(codec, 0);
 		reset++;
@@ -332,11 +337,14 @@ static struct snd_soc_dai_driver stac9766_dai[] = {
 
 static int stac9766_codec_probe(struct snd_soc_codec *codec)
 {
+	struct snd_ac97 *ac97;
 	int ret = 0;
 
-	ret = snd_soc_new_ac97_codec(codec);
-	if (ret < 0)
-		goto codec_err;
+	ac97 = snd_soc_new_ac97_codec(codec);
+	if (IS_ERR(ac97))
+		return PTR_ERR(ac97);
+
+	snd_soc_codec_set_drvdata(codec, ac97);
 
 	/* do a cold reset for the controller and then try
 	 * a warm reset followed by an optional cold reset for codec */
@@ -355,13 +363,15 @@ static int stac9766_codec_probe(struct snd_soc_codec *codec)
 	return 0;
 
 codec_err:
-	snd_soc_free_ac97_codec(codec);
+	snd_soc_free_ac97_codec(ac97);
 	return ret;
 }
 
 static int stac9766_codec_remove(struct snd_soc_codec *codec)
 {
-	snd_soc_free_ac97_codec(codec);
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
+
+	snd_soc_free_ac97_codec(ac97);
 	return 0;
 }
 
diff --git a/sound/soc/codecs/wm9705.c b/sound/soc/codecs/wm9705.c
index 5b5118ba152..d3a800fa6f0 100644
--- a/sound/soc/codecs/wm9705.c
+++ b/sound/soc/codecs/wm9705.c
@@ -203,13 +203,14 @@ static const struct snd_soc_dapm_route wm9705_audio_map[] = {
 /* We use a register cache to enhance read performance. */
 static unsigned int ac97_read(struct snd_soc_codec *codec, unsigned int reg)
 {
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
 	u16 *cache = codec->reg_cache;
 
 	switch (reg) {
 	case AC97_RESET:
 	case AC97_VENDOR_ID1:
 	case AC97_VENDOR_ID2:
-		return soc_ac97_ops->read(codec->ac97, reg);
+		return soc_ac97_ops->read(ac97, reg);
 	default:
 		reg = reg >> 1;
 
@@ -223,9 +224,10 @@ static unsigned int ac97_read(struct snd_soc_codec *codec, unsigned int reg)
 static int ac97_write(struct snd_soc_codec *codec, unsigned int reg,
 	unsigned int val)
 {
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
 	u16 *cache = codec->reg_cache;
 
-	soc_ac97_ops->write(codec->ac97, reg, val);
+	soc_ac97_ops->write(ac97, reg, val);
 	reg = reg >> 1;
 	if (reg < (ARRAY_SIZE(wm9705_reg)))
 		cache[reg] = val;
@@ -293,8 +295,10 @@ static struct snd_soc_dai_driver wm9705_dai[] = {
 
 static int wm9705_reset(struct snd_soc_codec *codec)
 {
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
+
 	if (soc_ac97_ops->reset) {
-		soc_ac97_ops->reset(codec->ac97);
+		soc_ac97_ops->reset(ac97);
 		if (ac97_read(codec, 0) == wm9705_reg[0])
 			return 0; /* Success */
 	}
@@ -307,13 +311,16 @@ static int wm9705_reset(struct snd_soc_codec *codec)
 #ifdef CONFIG_PM
 static int wm9705_soc_suspend(struct snd_soc_codec *codec)
 {
-	soc_ac97_ops->write(codec->ac97, AC97_POWERDOWN, 0xffff);
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
+
+	soc_ac97_ops->write(ac97, AC97_POWERDOWN, 0xffff);
 
 	return 0;
 }
 
 static int wm9705_soc_resume(struct snd_soc_codec *codec)
 {
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
 	int i, ret;
 	u16 *cache = codec->reg_cache;
 
@@ -322,7 +329,7 @@ static int wm9705_soc_resume(struct snd_soc_codec *codec)
 		return ret;
 
 	for (i = 2; i < ARRAY_SIZE(wm9705_reg) << 1; i += 2) {
-		soc_ac97_ops->write(codec->ac97, i, cache[i>>1]);
+		soc_ac97_ops->write(ac97, i, cache[i>>1]);
 	}
 
 	return 0;
@@ -334,14 +341,18 @@ static int wm9705_soc_resume(struct snd_soc_codec *codec)
 
 static int wm9705_soc_probe(struct snd_soc_codec *codec)
 {
+	struct snd_ac97 *ac97;
 	int ret = 0;
 
-	ret = snd_soc_new_ac97_codec(codec);
-	if (ret < 0) {
+	ac97 = snd_soc_new_ac97_codec(codec);
+	if (IS_ERR(ac97)) {
+		ret = PTR_ERR(ac97);
 		dev_err(codec->dev, "Failed to register AC97 codec\n");
 		return ret;
 	}
 
+	snd_soc_codec_set_drvdata(codec, ac97);
+
 	ret = wm9705_reset(codec);
 	if (ret)
 		goto reset_err;
@@ -349,13 +360,15 @@ static int wm9705_soc_probe(struct snd_soc_codec *codec)
 	return 0;
 
 reset_err:
-	snd_soc_free_ac97_codec(codec);
+	snd_soc_free_ac97_codec(ac97);
 	return ret;
 }
 
 static int wm9705_soc_remove(struct snd_soc_codec *codec)
 {
-	snd_soc_free_ac97_codec(codec);
+	struct snd_ac97 *ac97 = snd_soc_codec_get_drvdata(codec);
+
+	snd_soc_free_ac97_codec(ac97);
 	return 0;
 }
 
diff --git a/sound/soc/codecs/wm9712.c b/sound/soc/codecs/wm9712.c
index 9fa794baa5f..52a211be5b4 100644
--- a/sound/soc/codecs/wm9712.c
+++ b/sound/soc/codecs/wm9712.c
@@ -24,6 +24,7 @@
 #include "wm9712.h"
 
 struct wm9712_priv {
+	struct snd_ac97 *ac97;
 	unsigned int hp_mixer[2];
 	struct mutex lock;
 };
@@ -484,12 +485,13 @@ static const struct snd_soc_dapm_route wm9712_audio_map[] = {
 static unsigned int ac97_read(struct snd_soc_codec *codec,
 	unsigned int reg)
 {
+	struct wm9712_priv *wm9712 = snd_soc_codec_get_drvdata(codec);
 	u16 *cache = codec->reg_cache;
 
 	if (reg == AC97_RESET || reg == AC97_GPIO_STATUS ||
 		reg == AC97_VENDOR_ID1 || reg == AC97_VENDOR_ID2 ||
 		reg == AC97_REC_GAIN)
-		return soc_ac97_ops->read(codec->ac97, reg);
+		return soc_ac97_ops->read(wm9712->ac97, reg);
 	else {
 		reg = reg >> 1;
 
@@ -503,9 +505,10 @@ static unsigned int ac97_read(struct snd_soc_codec *codec,
 static int ac97_write(struct snd_soc_codec *codec, unsigned int reg,
 	unsigned int val)
 {
+	struct wm9712_priv *wm9712 = snd_soc_codec_get_drvdata(codec);
 	u16 *cache = codec->reg_cache;
 
-	soc_ac97_ops->write(codec->ac97, reg, val);
+	soc_ac97_ops->write(wm9712->ac97, reg, val);
 	reg = reg >> 1;
 	if (reg < (ARRAY_SIZE(wm9712_reg)))
 		cache[reg] = val;
@@ -613,15 +616,17 @@ static int wm9712_set_bias_level(struct snd_soc_codec *codec,
 
 static int wm9712_reset(struct snd_soc_codec *codec, int try_warm)
 {
+	struct wm9712_priv *wm9712 = snd_soc_codec_get_drvdata(codec);
+
 	if (try_warm && soc_ac97_ops->warm_reset) {
-		soc_ac97_ops->warm_reset(codec->ac97);
+		soc_ac97_ops->warm_reset(wm9712->ac97);
 		if (ac97_read(codec, 0) == wm9712_reg[0])
 			return 1;
 	}
 
-	soc_ac97_ops->reset(codec->ac97);
+	soc_ac97_ops->reset(wm9712->ac97);
 	if (soc_ac97_ops->warm_reset)
-		soc_ac97_ops->warm_reset(codec->ac97);
+		soc_ac97_ops->warm_reset(wm9712->ac97);
 	if (ac97_read(codec, 0) != wm9712_reg[0])
 		goto err;
 	return 0;
@@ -639,6 +644,7 @@ static int wm9712_soc_suspend(struct snd_soc_codec *codec)
 
 static int wm9712_soc_resume(struct snd_soc_codec *codec)
 {
+	struct wm9712_priv *wm9712 = snd_soc_codec_get_drvdata(codec);
 	int i, ret;
 	u16 *cache = codec->reg_cache;
 
@@ -654,7 +660,7 @@ static int wm9712_soc_resume(struct snd_soc_codec *codec)
 			if (i == AC97_INT_PAGING || i == AC97_POWERDOWN ||
 			    (i > 0x58 && i != 0x5c))
 				continue;
-			soc_ac97_ops->write(codec->ac97, i, cache[i>>1]);
+			soc_ac97_ops->write(wm9712->ac97, i, cache[i>>1]);
 		}
 	}
 
@@ -663,11 +669,13 @@ static int wm9712_soc_resume(struct snd_soc_codec *codec)
 
 static int wm9712_soc_probe(struct snd_soc_codec *codec)
 {
+	struct wm9712_priv *wm9712 = snd_soc_codec_get_drvdata(codec);
 	int ret = 0;
 
-	ret = snd_soc_new_ac97_codec(codec);
-	if (ret < 0) {
-		dev_err(codec->dev, "Failed to register AC97 codec\n");
+	wm9712->ac97 = snd_soc_new_ac97_codec(codec);
+	if (IS_ERR(wm9712->ac97)) {
+		ret = PTR_ERR(wm9712->ac97);
+		dev_err(codec->dev, "Failed to register AC97 codec: %d\n", ret);
 		return ret;
 	}
 
@@ -683,13 +691,15 @@ static int wm9712_soc_probe(struct snd_soc_codec *codec)
 	return 0;
 
 reset_err:
-	snd_soc_free_ac97_codec(codec);
+	snd_soc_free_ac97_codec(wm9712->ac97);
 	return ret;
 }
 
 static int wm9712_soc_remove(struct snd_soc_codec *codec)
 {
-	snd_soc_free_ac97_codec(codec);
+	struct wm9712_priv *wm9712 = snd_soc_codec_get_drvdata(codec);
+
+	snd_soc_free_ac97_codec(wm9712->ac97);
 	return 0;
 }
 
diff --git a/sound/soc/codecs/wm9713.c b/sound/soc/codecs/wm9713.c
index cd1b266d3af..6c95d98b0eb 100644
--- a/sound/soc/codecs/wm9713.c
+++ b/sound/soc/codecs/wm9713.c
@@ -30,6 +30,7 @@
 #include "wm9713.h"
 
 struct wm9713_priv {
+	struct snd_ac97 *ac97;
 	u32 pll_in; /* PLL input frequency */
 	unsigned int hp_mixer[2];
 	struct mutex lock;
@@ -674,12 +675,13 @@ static const struct snd_soc_dapm_route wm9713_audio_map[] = {
 static unsigned int ac97_read(struct snd_soc_codec *codec,
 	unsigned int reg)
 {
+	struct wm9713_priv *wm9713 = snd_soc_codec_get_drvdata(codec);
 	u16 *cache = codec->reg_cache;
 
 	if (reg == AC97_RESET || reg == AC97_GPIO_STATUS ||
 		reg == AC97_VENDOR_ID1 || reg == AC97_VENDOR_ID2 ||
 		reg == AC97_CD)
-		return soc_ac97_ops->read(codec->ac97, reg);
+		return soc_ac97_ops->read(wm9713->ac97, reg);
 	else {
 		reg = reg >> 1;
 
@@ -693,8 +695,10 @@ static unsigned int ac97_read(struct snd_soc_codec *codec,
 static int ac97_write(struct snd_soc_codec *codec, unsigned int reg,
 	unsigned int val)
 {
+	struct wm9713_priv *wm9713 = snd_soc_codec_get_drvdata(codec);
+
 	u16 *cache = codec->reg_cache;
-	soc_ac97_ops->write(codec->ac97, reg, val);
+	soc_ac97_ops->write(wm9713->ac97, reg, val);
 	reg = reg >> 1;
 	if (reg < (ARRAY_SIZE(wm9713_reg)))
 		cache[reg] = val;
@@ -1121,15 +1125,17 @@ static struct snd_soc_dai_driver wm9713_dai[] = {
 
 int wm9713_reset(struct snd_soc_codec *codec, int try_warm)
 {
+	struct wm9713_priv *wm9713 = snd_soc_codec_get_drvdata(codec);
+
 	if (try_warm && soc_ac97_ops->warm_reset) {
-		soc_ac97_ops->warm_reset(codec->ac97);
+		soc_ac97_ops->warm_reset(wm9713->ac97);
 		if (ac97_read(codec, 0) == wm9713_reg[0])
 			return 1;
 	}
 
-	soc_ac97_ops->reset(codec->ac97);
+	soc_ac97_ops->reset(wm9713->ac97);
 	if (soc_ac97_ops->warm_reset)
-		soc_ac97_ops->warm_reset(codec->ac97);
+		soc_ac97_ops->warm_reset(wm9713->ac97);
 	if (ac97_read(codec, 0) != wm9713_reg[0]) {
 		dev_err(codec->dev, "Failed to reset: AC97 link error\n");
 		return -EIO;
@@ -1207,7 +1213,7 @@ static int wm9713_soc_resume(struct snd_soc_codec *codec)
 			if (i == AC97_POWERDOWN || i == AC97_EXTENDED_MID ||
 				i == AC97_EXTENDED_MSTATUS || i > 0x66)
 				continue;
-			soc_ac97_ops->write(codec->ac97, i, cache[i>>1]);
+			soc_ac97_ops->write(wm9713->ac97, i, cache[i>>1]);
 		}
 	}
 
@@ -1216,11 +1222,12 @@ static int wm9713_soc_resume(struct snd_soc_codec *codec)
 
 static int wm9713_soc_probe(struct snd_soc_codec *codec)
 {
+	struct wm9713_priv *wm9713 = snd_soc_codec_get_drvdata(codec);
 	int ret = 0, reg;
 
-	ret = snd_soc_new_ac97_codec(codec);
-	if (ret < 0)
-		return ret;
+	wm9713->ac97 = snd_soc_new_ac97_codec(codec);
+	if (IS_ERR(wm9713->ac97))
+		return PTR_ERR(wm9713->ac97);
 
 	/* do a cold reset for the controller and then try
 	 * a warm reset followed by an optional cold reset for codec */
@@ -1238,13 +1245,15 @@ static int wm9713_soc_probe(struct snd_soc_codec *codec)
 	return 0;
 
 reset_err:
-	snd_soc_free_ac97_codec(codec);
+	snd_soc_free_ac97_codec(wm9713->ac97);
 	return ret;
 }
 
 static int wm9713_soc_remove(struct snd_soc_codec *codec)
 {
-	snd_soc_free_ac97_codec(codec);
+	struct wm9713_priv *wm9713 = snd_soc_codec_get_drvdata(codec);
+
+	snd_soc_free_ac97_codec(wm9713->ac97);
 	return 0;
 }
 
diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c
index 920d76c4382..2e10e9a3837 100644
--- a/sound/soc/soc-ac97.c
+++ b/sound/soc/soc-ac97.c
@@ -53,30 +53,33 @@ static void soc_ac97_device_release(struct device *dev)
  *
  * Initialises AC97 codec resources for use by ad-hoc devices only.
  */
-int snd_soc_new_ac97_codec(struct snd_soc_codec *codec)
+struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec)
 {
+	struct snd_ac97 *ac97;
 	int ret;
 
-	codec->ac97 = kzalloc(sizeof(struct snd_ac97), GFP_KERNEL);
-	if (codec->ac97 == NULL)
-		return -ENOMEM;
+	ac97 = kzalloc(sizeof(struct snd_ac97), GFP_KERNEL);
+	if (ac97 == NULL)
+		return ERR_PTR(-ENOMEM);
 
-	codec->ac97->bus = &soc_ac97_bus;
-	codec->ac97->num = 0;
+	ac97->bus = &soc_ac97_bus;
+	ac97->num = 0;
 
-	codec->ac97->dev.bus = &ac97_bus_type;
-	codec->ac97->dev.parent = codec->component.card->dev;
-	codec->ac97->dev.release = soc_ac97_device_release;
+	ac97->dev.bus = &ac97_bus_type;
+	ac97->dev.parent = codec->component.card->dev;
+	ac97->dev.release = soc_ac97_device_release;
 
-	dev_set_name(&codec->ac97->dev, "%d-%d:%s",
+	dev_set_name(&ac97->dev, "%d-%d:%s",
 		     codec->component.card->snd_card->number, 0,
 		     codec->component.name);
 
-	ret = device_register(&codec->ac97->dev);
-	if (ret)
-		put_device(&codec->ac97->dev);
+	ret = device_register(&ac97->dev);
+	if (ret) {
+		put_device(&ac97->dev);
+		return ERR_PTR(ret);
+	}
 
-	return ret;
+	return ac97;
 }
 EXPORT_SYMBOL_GPL(snd_soc_new_ac97_codec);
 
@@ -86,12 +89,11 @@ EXPORT_SYMBOL_GPL(snd_soc_new_ac97_codec);
  *
  * Frees AC97 codec device resources.
  */
-void snd_soc_free_ac97_codec(struct snd_soc_codec *codec)
+void snd_soc_free_ac97_codec(struct snd_ac97 *ac97)
 {
-	device_del(&codec->ac97->dev);
-	codec->ac97->bus = NULL;
-	put_device(&codec->ac97->dev);
-	codec->ac97 = NULL;
+	device_del(&ac97->dev);
+	ac97->bus = NULL;
+	put_device(&ac97->dev);
 }
 EXPORT_SYMBOL_GPL(snd_soc_free_ac97_codec);
 
-- 
cgit v1.2.3-70-g09d2


From 53a4ab96c61a34d62717b1481f6043e0b4338d74 Mon Sep 17 00:00:00 2001
From: Kevin Cernekee <cernekee@gmail.com>
Date: Wed, 12 Nov 2014 12:54:01 -0800
Subject: of: Change of_device_is_available() to return bool

This function can only return true or false; using a bool makes it more
obvious to the reader.

Signed-off-by: Kevin Cernekee <cernekee@gmail.com>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 drivers/of/base.c  | 22 +++++++++++-----------
 include/linux/of.h |  6 +++---
 2 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/of/base.c b/drivers/of/base.c
index 4627e0acf4a..2d5dfb8b2e6 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -522,27 +522,27 @@ EXPORT_SYMBOL(of_machine_is_compatible);
  *
  *  @device: Node to check for availability, with locks already held
  *
- *  Returns 1 if the status property is absent or set to "okay" or "ok",
- *  0 otherwise
+ *  Returns true if the status property is absent or set to "okay" or "ok",
+ *  false otherwise
  */
-static int __of_device_is_available(const struct device_node *device)
+static bool __of_device_is_available(const struct device_node *device)
 {
 	const char *status;
 	int statlen;
 
 	if (!device)
-		return 0;
+		return false;
 
 	status = __of_get_property(device, "status", &statlen);
 	if (status == NULL)
-		return 1;
+		return true;
 
 	if (statlen > 0) {
 		if (!strcmp(status, "okay") || !strcmp(status, "ok"))
-			return 1;
+			return true;
 	}
 
-	return 0;
+	return false;
 }
 
 /**
@@ -550,13 +550,13 @@ static int __of_device_is_available(const struct device_node *device)
  *
  *  @device: Node to check for availability
  *
- *  Returns 1 if the status property is absent or set to "okay" or "ok",
- *  0 otherwise
+ *  Returns true if the status property is absent or set to "okay" or "ok",
+ *  false otherwise
  */
-int of_device_is_available(const struct device_node *device)
+bool of_device_is_available(const struct device_node *device)
 {
 	unsigned long flags;
-	int res;
+	bool res;
 
 	raw_spin_lock_irqsave(&devtree_lock, flags);
 	res = __of_device_is_available(device);
diff --git a/include/linux/of.h b/include/linux/of.h
index 3c851a8f23e..27635c89d8c 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -276,7 +276,7 @@ extern int of_property_read_string_helper(struct device_node *np,
 					      const char **out_strs, size_t sz, int index);
 extern int of_device_is_compatible(const struct device_node *device,
 				   const char *);
-extern int of_device_is_available(const struct device_node *device);
+extern bool of_device_is_available(const struct device_node *device);
 extern const void *of_get_property(const struct device_node *node,
 				const char *name,
 				int *lenp);
@@ -427,9 +427,9 @@ static inline int of_device_is_compatible(const struct device_node *device,
 	return 0;
 }
 
-static inline int of_device_is_available(const struct device_node *device)
+static inline bool of_device_is_available(const struct device_node *device)
 {
-	return 0;
+	return false;
 }
 
 static inline struct property *of_find_property(const struct device_node *np,
-- 
cgit v1.2.3-70-g09d2


From 3274f52073d88b62f3c5ace82ae9d48546232e72 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Thu, 13 Nov 2014 17:36:44 -0800
Subject: bpf: add 'flags' attribute to BPF_MAP_UPDATE_ELEM command

the current meaning of BPF_MAP_UPDATE_ELEM syscall command is:
either update existing map element or create a new one.
Initially the plan was to add a new command to handle the case of
'create new element if it didn't exist', but 'flags' style looks
cleaner and overall diff is much smaller (more code reused), so add 'flags'
attribute to BPF_MAP_UPDATE_ELEM command with the following meaning:
 #define BPF_ANY	0 /* create new element or update existing */
 #define BPF_NOEXIST	1 /* create new element if it didn't exist */
 #define BPF_EXIST	2 /* update existing element */

bpf_update_elem(fd, key, value, BPF_NOEXIST) call can fail with EEXIST
if element already exists.

bpf_update_elem(fd, key, value, BPF_EXIST) can fail with ENOENT
if element doesn't exist.

Userspace will call it as:
int bpf_update_elem(int fd, void *key, void *value, __u64 flags)
{
    union bpf_attr attr = {
        .map_fd = fd,
        .key = ptr_to_u64(key),
        .value = ptr_to_u64(value),
        .flags = flags;
    };

    return bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
}

First two bits of 'flags' are used to encode style of bpf_update_elem() command.
Bits 2-63 are reserved for future use.

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h      | 2 +-
 include/uapi/linux/bpf.h | 8 +++++++-
 kernel/bpf/syscall.c     | 4 ++--
 3 files changed, 10 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3cf91754a95..51e9242e480 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -22,7 +22,7 @@ struct bpf_map_ops {
 
 	/* funcs callable from userspace and from eBPF programs */
 	void *(*map_lookup_elem)(struct bpf_map *map, void *key);
-	int (*map_update_elem)(struct bpf_map *map, void *key, void *value);
+	int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags);
 	int (*map_delete_elem)(struct bpf_map *map, void *key);
 };
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d18316f9e9c..3e9e1b77f29 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -82,7 +82,7 @@ enum bpf_cmd {
 
 	/* create or update key/value pair in a given map
 	 * err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
-	 * Using attr->map_fd, attr->key, attr->value
+	 * Using attr->map_fd, attr->key, attr->value, attr->flags
 	 * returns zero or negative error
 	 */
 	BPF_MAP_UPDATE_ELEM,
@@ -117,6 +117,11 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_UNSPEC,
 };
 
+/* flags for BPF_MAP_UPDATE_ELEM command */
+#define BPF_ANY		0 /* create new element or update existing */
+#define BPF_NOEXIST	1 /* create new element if it didn't exist */
+#define BPF_EXIST	2 /* update existing element */
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -132,6 +137,7 @@ union bpf_attr {
 			__aligned_u64 value;
 			__aligned_u64 next_key;
 		};
+		__u64		flags;
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_LOAD command */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ba61c8c1603..c0d03bf317a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -190,7 +190,7 @@ err_put:
 	return err;
 }
 
-#define BPF_MAP_UPDATE_ELEM_LAST_FIELD value
+#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
 
 static int map_update_elem(union bpf_attr *attr)
 {
@@ -231,7 +231,7 @@ static int map_update_elem(union bpf_attr *attr)
 	 * therefore all map accessors rely on this fact, so do the same here
 	 */
 	rcu_read_lock();
-	err = map->ops->map_update_elem(map, key, value);
+	err = map->ops->map_update_elem(map, key, value, attr->flags);
 	rcu_read_unlock();
 
 free_value:
-- 
cgit v1.2.3-70-g09d2


From 0f8e4bd8a1fc8c4185f1630061d0a1f2d197a475 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Thu, 13 Nov 2014 17:36:45 -0800
Subject: bpf: add hashtable type of eBPF maps

add new map type BPF_MAP_TYPE_HASH and its implementation

- maps are created/destroyed by userspace. Both userspace and eBPF programs
  can lookup/update/delete elements from the map

- eBPF programs can be called in_irq(), so use spin_lock_irqsave() mechanism
  for concurrent updates

- key/value are opaque range of bytes (aligned to 8 bytes)

- user space provides 3 configuration attributes via BPF syscall:
  key_size, value_size, max_entries

- map takes care of allocating/freeing key/value pairs

- map_update_elem() must fail to insert new element when max_entries
  limit is reached to make sure that eBPF programs cannot exhaust memory

- map_update_elem() replaces elements in an atomic way

- optimized for speed of lookup() which can be called multiple times from
  eBPF program which itself is triggered by high volume of events
  . in the future JIT compiler may recognize lookup() call and optimize it
    further, since key_size is constant for life of eBPF program

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/bpf.h |   1 +
 kernel/bpf/Makefile      |   2 +-
 kernel/bpf/hashtab.c     | 362 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 364 insertions(+), 1 deletion(-)
 create mode 100644 kernel/bpf/hashtab.c

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3e9e1b77f29..03a01fd609a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -111,6 +111,7 @@ enum bpf_cmd {
 
 enum bpf_map_type {
 	BPF_MAP_TYPE_UNSPEC,
+	BPF_MAP_TYPE_HASH,
 };
 
 enum bpf_prog_type {
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 0daf7f6ae7d..2c0ec7f9da7 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,5 +1,5 @@
 obj-y := core.o
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o
 ifdef CONFIG_TEST_BPF
 obj-$(CONFIG_BPF_SYSCALL) += test_stub.o
 endif
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
new file mode 100644
index 00000000000..d234a012f04
--- /dev/null
+++ b/kernel/bpf/hashtab.c
@@ -0,0 +1,362 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/bpf.h>
+#include <linux/jhash.h>
+#include <linux/filter.h>
+#include <linux/vmalloc.h>
+
+struct bpf_htab {
+	struct bpf_map map;
+	struct hlist_head *buckets;
+	spinlock_t lock;
+	u32 count;	/* number of elements in this hashtable */
+	u32 n_buckets;	/* number of hash buckets */
+	u32 elem_size;	/* size of each element in bytes */
+};
+
+/* each htab element is struct htab_elem + key + value */
+struct htab_elem {
+	struct hlist_node hash_node;
+	struct rcu_head rcu;
+	u32 hash;
+	char key[0] __aligned(8);
+};
+
+/* Called from syscall */
+static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_htab *htab;
+	int err, i;
+
+	htab = kzalloc(sizeof(*htab), GFP_USER);
+	if (!htab)
+		return ERR_PTR(-ENOMEM);
+
+	/* mandatory map attributes */
+	htab->map.key_size = attr->key_size;
+	htab->map.value_size = attr->value_size;
+	htab->map.max_entries = attr->max_entries;
+
+	/* check sanity of attributes.
+	 * value_size == 0 may be allowed in the future to use map as a set
+	 */
+	err = -EINVAL;
+	if (htab->map.max_entries == 0 || htab->map.key_size == 0 ||
+	    htab->map.value_size == 0)
+		goto free_htab;
+
+	/* hash table size must be power of 2 */
+	htab->n_buckets = roundup_pow_of_two(htab->map.max_entries);
+
+	err = -E2BIG;
+	if (htab->map.key_size > MAX_BPF_STACK)
+		/* eBPF programs initialize keys on stack, so they cannot be
+		 * larger than max stack size
+		 */
+		goto free_htab;
+
+	err = -ENOMEM;
+	htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct hlist_head),
+				      GFP_USER | __GFP_NOWARN);
+
+	if (!htab->buckets) {
+		htab->buckets = vmalloc(htab->n_buckets * sizeof(struct hlist_head));
+		if (!htab->buckets)
+			goto free_htab;
+	}
+
+	for (i = 0; i < htab->n_buckets; i++)
+		INIT_HLIST_HEAD(&htab->buckets[i]);
+
+	spin_lock_init(&htab->lock);
+	htab->count = 0;
+
+	htab->elem_size = sizeof(struct htab_elem) +
+			  round_up(htab->map.key_size, 8) +
+			  htab->map.value_size;
+	return &htab->map;
+
+free_htab:
+	kfree(htab);
+	return ERR_PTR(err);
+}
+
+static inline u32 htab_map_hash(const void *key, u32 key_len)
+{
+	return jhash(key, key_len, 0);
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+	return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash,
+					 void *key, u32 key_size)
+{
+	struct htab_elem *l;
+
+	hlist_for_each_entry_rcu(l, head, hash_node)
+		if (l->hash == hash && !memcmp(&l->key, key, key_size))
+			return l;
+
+	return NULL;
+}
+
+/* Called from syscall or from eBPF program */
+static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_head *head;
+	struct htab_elem *l;
+	u32 hash, key_size;
+
+	/* Must be called with rcu_read_lock. */
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	key_size = map->key_size;
+
+	hash = htab_map_hash(key, key_size);
+
+	head = select_bucket(htab, hash);
+
+	l = lookup_elem_raw(head, hash, key, key_size);
+
+	if (l)
+		return l->key + round_up(map->key_size, 8);
+
+	return NULL;
+}
+
+/* Called from syscall */
+static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_head *head;
+	struct htab_elem *l, *next_l;
+	u32 hash, key_size;
+	int i;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	key_size = map->key_size;
+
+	hash = htab_map_hash(key, key_size);
+
+	head = select_bucket(htab, hash);
+
+	/* lookup the key */
+	l = lookup_elem_raw(head, hash, key, key_size);
+
+	if (!l) {
+		i = 0;
+		goto find_first_elem;
+	}
+
+	/* key was found, get next key in the same bucket */
+	next_l = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&l->hash_node)),
+				  struct htab_elem, hash_node);
+
+	if (next_l) {
+		/* if next elem in this hash list is non-zero, just return it */
+		memcpy(next_key, next_l->key, key_size);
+		return 0;
+	}
+
+	/* no more elements in this hash list, go to the next bucket */
+	i = hash & (htab->n_buckets - 1);
+	i++;
+
+find_first_elem:
+	/* iterate over buckets */
+	for (; i < htab->n_buckets; i++) {
+		head = select_bucket(htab, i);
+
+		/* pick first element in the bucket */
+		next_l = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),
+					  struct htab_elem, hash_node);
+		if (next_l) {
+			/* if it's not empty, just return it */
+			memcpy(next_key, next_l->key, key_size);
+			return 0;
+		}
+	}
+
+	/* itereated over all buckets and all elements */
+	return -ENOENT;
+}
+
+/* Called from syscall or from eBPF program */
+static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
+				u64 map_flags)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct htab_elem *l_new, *l_old;
+	struct hlist_head *head;
+	unsigned long flags;
+	u32 key_size;
+	int ret;
+
+	if (map_flags > BPF_EXIST)
+		/* unknown flags */
+		return -EINVAL;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	/* allocate new element outside of lock */
+	l_new = kmalloc(htab->elem_size, GFP_ATOMIC);
+	if (!l_new)
+		return -ENOMEM;
+
+	key_size = map->key_size;
+
+	memcpy(l_new->key, key, key_size);
+	memcpy(l_new->key + round_up(key_size, 8), value, map->value_size);
+
+	l_new->hash = htab_map_hash(l_new->key, key_size);
+
+	/* bpf_map_update_elem() can be called in_irq() */
+	spin_lock_irqsave(&htab->lock, flags);
+
+	head = select_bucket(htab, l_new->hash);
+
+	l_old = lookup_elem_raw(head, l_new->hash, key, key_size);
+
+	if (!l_old && unlikely(htab->count >= map->max_entries)) {
+		/* if elem with this 'key' doesn't exist and we've reached
+		 * max_entries limit, fail insertion of new elem
+		 */
+		ret = -E2BIG;
+		goto err;
+	}
+
+	if (l_old && map_flags == BPF_NOEXIST) {
+		/* elem already exists */
+		ret = -EEXIST;
+		goto err;
+	}
+
+	if (!l_old && map_flags == BPF_EXIST) {
+		/* elem doesn't exist, cannot update it */
+		ret = -ENOENT;
+		goto err;
+	}
+
+	/* add new element to the head of the list, so that concurrent
+	 * search will find it before old elem
+	 */
+	hlist_add_head_rcu(&l_new->hash_node, head);
+	if (l_old) {
+		hlist_del_rcu(&l_old->hash_node);
+		kfree_rcu(l_old, rcu);
+	} else {
+		htab->count++;
+	}
+	spin_unlock_irqrestore(&htab->lock, flags);
+
+	return 0;
+err:
+	spin_unlock_irqrestore(&htab->lock, flags);
+	kfree(l_new);
+	return ret;
+}
+
+/* Called from syscall or from eBPF program */
+static int htab_map_delete_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_head *head;
+	struct htab_elem *l;
+	unsigned long flags;
+	u32 hash, key_size;
+	int ret = -ENOENT;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	key_size = map->key_size;
+
+	hash = htab_map_hash(key, key_size);
+
+	spin_lock_irqsave(&htab->lock, flags);
+
+	head = select_bucket(htab, hash);
+
+	l = lookup_elem_raw(head, hash, key, key_size);
+
+	if (l) {
+		hlist_del_rcu(&l->hash_node);
+		htab->count--;
+		kfree_rcu(l, rcu);
+		ret = 0;
+	}
+
+	spin_unlock_irqrestore(&htab->lock, flags);
+	return ret;
+}
+
+static void delete_all_elements(struct bpf_htab *htab)
+{
+	int i;
+
+	for (i = 0; i < htab->n_buckets; i++) {
+		struct hlist_head *head = select_bucket(htab, i);
+		struct hlist_node *n;
+		struct htab_elem *l;
+
+		hlist_for_each_entry_safe(l, n, head, hash_node) {
+			hlist_del_rcu(&l->hash_node);
+			htab->count--;
+			kfree(l);
+		}
+	}
+}
+
+/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
+static void htab_map_free(struct bpf_map *map)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+
+	/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
+	 * so the programs (can be more than one that used this map) were
+	 * disconnected from events. Wait for outstanding critical sections in
+	 * these programs to complete
+	 */
+	synchronize_rcu();
+
+	/* some of kfree_rcu() callbacks for elements of this map may not have
+	 * executed. It's ok. Proceed to free residual elements and map itself
+	 */
+	delete_all_elements(htab);
+	kvfree(htab->buckets);
+	kfree(htab);
+}
+
+static struct bpf_map_ops htab_ops = {
+	.map_alloc = htab_map_alloc,
+	.map_free = htab_map_free,
+	.map_get_next_key = htab_map_get_next_key,
+	.map_lookup_elem = htab_map_lookup_elem,
+	.map_update_elem = htab_map_update_elem,
+	.map_delete_elem = htab_map_delete_elem,
+};
+
+static struct bpf_map_type_list tl = {
+	.ops = &htab_ops,
+	.type = BPF_MAP_TYPE_HASH,
+};
+
+static int __init register_htab_map(void)
+{
+	bpf_register_map_type(&tl);
+	return 0;
+}
+late_initcall(register_htab_map);
-- 
cgit v1.2.3-70-g09d2


From 28fbcfa08d8ed7c5a50d41a0433aad222835e8e3 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Thu, 13 Nov 2014 17:36:46 -0800
Subject: bpf: add array type of eBPF maps

add new map type BPF_MAP_TYPE_ARRAY and its implementation

- optimized for fastest possible lookup()
  . in the future verifier/JIT may recognize lookup() with constant key
    and optimize it into constant pointer. Can optimize non-constant
    key into direct pointer arithmetic as well, since pointers and
    value_size are constant for the life of the eBPF program.
    In other words array_map_lookup_elem() may be 'inlined' by verifier/JIT
    while preserving concurrent access to this map from user space

- two main use cases for array type:
  . 'global' eBPF variables: array of 1 element with key=0 and value is a
    collection of 'global' variables which programs can use to keep the state
    between events
  . aggregation of tracing events into fixed set of buckets

- all array elements pre-allocated and zero initialized at init time

- key as an index in array and can only be 4 byte

- map_delete_elem() returns EINVAL, since elements cannot be deleted

- map_update_elem() replaces elements in an non-atomic way
  (for atomic updates hashtable type should be used instead)

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/bpf.h |   1 +
 kernel/bpf/Makefile      |   2 +-
 kernel/bpf/arraymap.c    | 151 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 153 insertions(+), 1 deletion(-)
 create mode 100644 kernel/bpf/arraymap.c

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 03a01fd609a..0d662fe75df 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -112,6 +112,7 @@ enum bpf_cmd {
 enum bpf_map_type {
 	BPF_MAP_TYPE_UNSPEC,
 	BPF_MAP_TYPE_HASH,
+	BPF_MAP_TYPE_ARRAY,
 };
 
 enum bpf_prog_type {
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 2c0ec7f9da7..72ec98ba2d4 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,5 +1,5 @@
 obj-y := core.o
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o arraymap.o
 ifdef CONFIG_TEST_BPF
 obj-$(CONFIG_BPF_SYSCALL) += test_stub.o
 endif
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
new file mode 100644
index 00000000000..58b80c137af
--- /dev/null
+++ b/kernel/bpf/arraymap.c
@@ -0,0 +1,151 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/bpf.h>
+#include <linux/err.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+
+struct bpf_array {
+	struct bpf_map map;
+	u32 elem_size;
+	char value[0] __aligned(8);
+};
+
+/* Called from syscall */
+static struct bpf_map *array_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_array *array;
+	u32 elem_size;
+
+	/* check sanity of attributes */
+	if (attr->max_entries == 0 || attr->key_size != 4 ||
+	    attr->value_size == 0)
+		return ERR_PTR(-EINVAL);
+
+	elem_size = round_up(attr->value_size, 8);
+
+	/* allocate all map elements and zero-initialize them */
+	array = kzalloc(sizeof(*array) + attr->max_entries * elem_size,
+			GFP_USER | __GFP_NOWARN);
+	if (!array) {
+		array = vzalloc(array->map.max_entries * array->elem_size);
+		if (!array)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	/* copy mandatory map attributes */
+	array->map.key_size = attr->key_size;
+	array->map.value_size = attr->value_size;
+	array->map.max_entries = attr->max_entries;
+
+	array->elem_size = elem_size;
+
+	return &array->map;
+
+}
+
+/* Called from syscall or from eBPF program */
+static void *array_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u32 index = *(u32 *)key;
+
+	if (index >= array->map.max_entries)
+		return NULL;
+
+	return array->value + array->elem_size * index;
+}
+
+/* Called from syscall */
+static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u32 index = *(u32 *)key;
+	u32 *next = (u32 *)next_key;
+
+	if (index >= array->map.max_entries) {
+		*next = 0;
+		return 0;
+	}
+
+	if (index == array->map.max_entries - 1)
+		return -ENOENT;
+
+	*next = index + 1;
+	return 0;
+}
+
+/* Called from syscall or from eBPF program */
+static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
+				 u64 map_flags)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u32 index = *(u32 *)key;
+
+	if (map_flags > BPF_EXIST)
+		/* unknown flags */
+		return -EINVAL;
+
+	if (index >= array->map.max_entries)
+		/* all elements were pre-allocated, cannot insert a new one */
+		return -E2BIG;
+
+	if (map_flags == BPF_NOEXIST)
+		/* all elemenets already exist */
+		return -EEXIST;
+
+	memcpy(array->value + array->elem_size * index, value, array->elem_size);
+	return 0;
+}
+
+/* Called from syscall or from eBPF program */
+static int array_map_delete_elem(struct bpf_map *map, void *key)
+{
+	return -EINVAL;
+}
+
+/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
+static void array_map_free(struct bpf_map *map)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+
+	/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
+	 * so the programs (can be more than one that used this map) were
+	 * disconnected from events. Wait for outstanding programs to complete
+	 * and free the array
+	 */
+	synchronize_rcu();
+
+	kvfree(array);
+}
+
+static struct bpf_map_ops array_ops = {
+	.map_alloc = array_map_alloc,
+	.map_free = array_map_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = array_map_lookup_elem,
+	.map_update_elem = array_map_update_elem,
+	.map_delete_elem = array_map_delete_elem,
+};
+
+static struct bpf_map_type_list tl = {
+	.ops = &array_ops,
+	.type = BPF_MAP_TYPE_ARRAY,
+};
+
+static int __init register_array_map(void)
+{
+	bpf_register_map_type(&tl);
+	return 0;
+}
+late_initcall(register_array_map);
-- 
cgit v1.2.3-70-g09d2


From d0003ec01c667b731c139e23de3306a8b328ccf5 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Thu, 13 Nov 2014 17:36:49 -0800
Subject: bpf: allow eBPF programs to use maps

expose bpf_map_lookup_elem(), bpf_map_update_elem(), bpf_map_delete_elem()
map accessors to eBPF programs

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h      |  5 +++
 include/uapi/linux/bpf.h |  3 ++
 kernel/bpf/Makefile      |  2 +-
 kernel/bpf/helpers.c     | 89 ++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 98 insertions(+), 1 deletion(-)
 create mode 100644 kernel/bpf/helpers.c

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 51e9242e480..75e94eaa228 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -133,4 +133,9 @@ struct bpf_prog *bpf_prog_get(u32 ufd);
 /* verify correctness of eBPF program */
 int bpf_check(struct bpf_prog *fp, union bpf_attr *attr);
 
+/* verifier prototypes for helper functions called from eBPF programs */
+extern struct bpf_func_proto bpf_map_lookup_elem_proto;
+extern struct bpf_func_proto bpf_map_update_elem_proto;
+extern struct bpf_func_proto bpf_map_delete_elem_proto;
+
 #endif /* _LINUX_BPF_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0d662fe75df..4a3d0f84f17 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -158,6 +158,9 @@ union bpf_attr {
  */
 enum bpf_func_id {
 	BPF_FUNC_unspec,
+	BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */
+	BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */
+	BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */
 	__BPF_FUNC_MAX_ID,
 };
 
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 72ec98ba2d4..a5ae60f0b0a 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,5 +1,5 @@
 obj-y := core.o
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o arraymap.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o arraymap.o helpers.o
 ifdef CONFIG_TEST_BPF
 obj-$(CONFIG_BPF_SYSCALL) += test_stub.o
 endif
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
new file mode 100644
index 00000000000..9e3414d8545
--- /dev/null
+++ b/kernel/bpf/helpers.c
@@ -0,0 +1,89 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/bpf.h>
+#include <linux/rcupdate.h>
+
+/* If kernel subsystem is allowing eBPF programs to call this function,
+ * inside its own verifier_ops->get_func_proto() callback it should return
+ * bpf_map_lookup_elem_proto, so that verifier can properly check the arguments
+ *
+ * Different map implementations will rely on rcu in map methods
+ * lookup/update/delete, therefore eBPF programs must run under rcu lock
+ * if program is allowed to access maps, so check rcu_read_lock_held in
+ * all three functions.
+ */
+static u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	/* verifier checked that R1 contains a valid pointer to bpf_map
+	 * and R2 points to a program stack and map->key_size bytes were
+	 * initialized
+	 */
+	struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
+	void *key = (void *) (unsigned long) r2;
+	void *value;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	value = map->ops->map_lookup_elem(map, key);
+
+	/* lookup() returns either pointer to element value or NULL
+	 * which is the meaning of PTR_TO_MAP_VALUE_OR_NULL type
+	 */
+	return (unsigned long) value;
+}
+
+struct bpf_func_proto bpf_map_lookup_elem_proto = {
+	.func = bpf_map_lookup_elem,
+	.gpl_only = false,
+	.ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type = ARG_CONST_MAP_PTR,
+	.arg2_type = ARG_PTR_TO_MAP_KEY,
+};
+
+static u64 bpf_map_update_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
+	void *key = (void *) (unsigned long) r2;
+	void *value = (void *) (unsigned long) r3;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	return map->ops->map_update_elem(map, key, value, r4);
+}
+
+struct bpf_func_proto bpf_map_update_elem_proto = {
+	.func = bpf_map_update_elem,
+	.gpl_only = false,
+	.ret_type = RET_INTEGER,
+	.arg1_type = ARG_CONST_MAP_PTR,
+	.arg2_type = ARG_PTR_TO_MAP_KEY,
+	.arg3_type = ARG_PTR_TO_MAP_VALUE,
+	.arg4_type = ARG_ANYTHING,
+};
+
+static u64 bpf_map_delete_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
+	void *key = (void *) (unsigned long) r2;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	return map->ops->map_delete_elem(map, key);
+}
+
+struct bpf_func_proto bpf_map_delete_elem_proto = {
+	.func = bpf_map_delete_elem,
+	.gpl_only = false,
+	.ret_type = RET_INTEGER,
+	.arg1_type = ARG_CONST_MAP_PTR,
+	.arg2_type = ARG_PTR_TO_MAP_KEY,
+};
-- 
cgit v1.2.3-70-g09d2


From e3e3217029a35c579bf100998b43976d0b1cb8d7 Mon Sep 17 00:00:00 2001
From: Rick Jones <rick.jones2@hp.com>
Date: Mon, 17 Nov 2014 14:04:29 -0800
Subject: icmp: Remove some spurious dropped packet profile hits from the ICMP
 path

If icmp_rcv() has successfully processed the incoming ICMP datagram, we
should use consume_skb() rather than kfree_skb() because a hit on the likes
of perf -e skb:kfree_skb is not called-for.

Signed-off-by: Rick Jones <rick.jones2@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ping.h |  2 +-
 net/ipv4/icmp.c    | 43 ++++++++++++++++++++++++++++---------------
 net/ipv4/ping.c    |  6 +++---
 net/ipv6/icmp.c    | 12 ++++++++++--
 4 files changed, 42 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/net/ping.h b/include/net/ping.h
index 026479b61a2..f074060bc5d 100644
--- a/include/net/ping.h
+++ b/include/net/ping.h
@@ -82,7 +82,7 @@ int  ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
 int  ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		     size_t len);
 int  ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
-void ping_rcv(struct sk_buff *skb);
+bool ping_rcv(struct sk_buff *skb);
 
 #ifdef CONFIG_PROC_FS
 struct ping_seq_afinfo {
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 36b7bfa609d..36f5584d93c 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -190,7 +190,7 @@ EXPORT_SYMBOL(icmp_err_convert);
  */
 
 struct icmp_control {
-	void (*handler)(struct sk_buff *skb);
+	bool (*handler)(struct sk_buff *skb);
 	short   error;		/* This ICMP is classed as an error message */
 };
 
@@ -746,7 +746,7 @@ static bool icmp_tag_validation(int proto)
  *	ICMP_PARAMETERPROB.
  */
 
-static void icmp_unreach(struct sk_buff *skb)
+static bool icmp_unreach(struct sk_buff *skb)
 {
 	const struct iphdr *iph;
 	struct icmphdr *icmph;
@@ -839,10 +839,10 @@ static void icmp_unreach(struct sk_buff *skb)
 	icmp_socket_deliver(skb, info);
 
 out:
-	return;
+	return true;
 out_err:
 	ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
-	goto out;
+	return false;
 }
 
 
@@ -850,17 +850,20 @@ out_err:
  *	Handle ICMP_REDIRECT.
  */
 
-static void icmp_redirect(struct sk_buff *skb)
+static bool icmp_redirect(struct sk_buff *skb)
 {
 	if (skb->len < sizeof(struct iphdr)) {
 		ICMP_INC_STATS_BH(dev_net(skb->dev), ICMP_MIB_INERRORS);
-		return;
+		return false;
 	}
 
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		return;
+	if (!pskb_may_pull(skb, sizeof(struct iphdr))) {
+		/* there aught to be a stat */
+		return false;
+	}
 
 	icmp_socket_deliver(skb, icmp_hdr(skb)->un.gateway);
+	return true;
 }
 
 /*
@@ -875,7 +878,7 @@ static void icmp_redirect(struct sk_buff *skb)
  *	See also WRT handling of options once they are done and working.
  */
 
-static void icmp_echo(struct sk_buff *skb)
+static bool icmp_echo(struct sk_buff *skb)
 {
 	struct net *net;
 
@@ -891,6 +894,8 @@ static void icmp_echo(struct sk_buff *skb)
 		icmp_param.head_len	   = sizeof(struct icmphdr);
 		icmp_reply(&icmp_param, skb);
 	}
+	/* should there be an ICMP stat for ignored echos? */
+	return true;
 }
 
 /*
@@ -900,7 +905,7 @@ static void icmp_echo(struct sk_buff *skb)
  *		  MUST be accurate to a few minutes.
  *		  MUST be updated at least at 15Hz.
  */
-static void icmp_timestamp(struct sk_buff *skb)
+static bool icmp_timestamp(struct sk_buff *skb)
 {
 	struct timespec tv;
 	struct icmp_bxm icmp_param;
@@ -927,15 +932,17 @@ static void icmp_timestamp(struct sk_buff *skb)
 	icmp_param.data_len	   = 0;
 	icmp_param.head_len	   = sizeof(struct icmphdr) + 12;
 	icmp_reply(&icmp_param, skb);
-out:
-	return;
+	return true;
+
 out_err:
 	ICMP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS);
-	goto out;
+	return false;
 }
 
-static void icmp_discard(struct sk_buff *skb)
+static bool icmp_discard(struct sk_buff *skb)
 {
+	/* pretend it was a success */
+	return true;
 }
 
 /*
@@ -946,6 +953,7 @@ int icmp_rcv(struct sk_buff *skb)
 	struct icmphdr *icmph;
 	struct rtable *rt = skb_rtable(skb);
 	struct net *net = dev_net(rt->dst.dev);
+	bool success;
 
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
 		struct sec_path *sp = skb_sec_path(skb);
@@ -1012,7 +1020,12 @@ int icmp_rcv(struct sk_buff *skb)
 		}
 	}
 
-	icmp_pointers[icmph->type].handler(skb);
+	success = icmp_pointers[icmph->type].handler(skb);
+
+	if (success)  {
+		consume_skb(skb);
+		return 0;
+	}
 
 drop:
 	kfree_skb(skb);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 736236c3e55..ce2920f5bef 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -955,7 +955,7 @@ EXPORT_SYMBOL_GPL(ping_queue_rcv_skb);
  *	All we need to do is get the socket.
  */
 
-void ping_rcv(struct sk_buff *skb)
+bool ping_rcv(struct sk_buff *skb)
 {
 	struct sock *sk;
 	struct net *net = dev_net(skb->dev);
@@ -974,11 +974,11 @@ void ping_rcv(struct sk_buff *skb)
 		pr_debug("rcv on socket %p\n", sk);
 		ping_queue_rcv_skb(sk, skb_get(skb));
 		sock_put(sk);
-		return;
+		return true;
 	}
 	pr_debug("no socket, dropping\n");
 
-	/* We're called from icmp_rcv(). kfree_skb() is done there. */
+	return false;
 }
 EXPORT_SYMBOL_GPL(ping_rcv);
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 09293403207..39b3ff97a50 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -679,6 +679,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
 	const struct in6_addr *saddr, *daddr;
 	struct icmp6hdr *hdr;
 	u8 type;
+	bool success = false;
 
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
 		struct sec_path *sp = skb_sec_path(skb);
@@ -726,7 +727,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		break;
 
 	case ICMPV6_ECHO_REPLY:
-		ping_rcv(skb);
+		success = ping_rcv(skb);
 		break;
 
 	case ICMPV6_PKT_TOOBIG:
@@ -790,7 +791,14 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
 	}
 
-	kfree_skb(skb);
+	/* until the v6 path can be better sorted assume failure and
+	 * preserve the status quo behaviour for the rest of the paths to here
+	 */
+	if (success)
+		consume_skb(skb);
+	else
+		kfree_skb(skb);
+
 	return 0;
 
 csum_error:
-- 
cgit v1.2.3-70-g09d2


From 3e58a5424c8325df8b62f1de175dc95c7373bfe1 Mon Sep 17 00:00:00 2001
From: Kouei Abe <kouei.abe.cp@renesas.com>
Date: Wed, 12 Nov 2014 17:55:56 +0900
Subject: ARM: shmobile: r8a7794: Add SGX clock to device tree

Signed-off-by: Kouei Abe <kouei.abe.cp@renesas.com>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 arch/arm/boot/dts/r8a7794.dtsi            | 11 +++++------
 include/dt-bindings/clock/r8a7794-clock.h |  1 +
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/arm/boot/dts/r8a7794.dtsi b/arch/arm/boot/dts/r8a7794.dtsi
index 95f656d22fd..b6f8f451e3b 100644
--- a/arch/arm/boot/dts/r8a7794.dtsi
+++ b/arch/arm/boot/dts/r8a7794.dtsi
@@ -461,16 +461,15 @@
 		mstp1_clks: mstp1_clks@e6150134 {
 			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150134 0 4>, <0 0xe6150038 0 4>;
-			clocks = <&p_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
-				 <&cp_clk>,
-				 <&zs_clk>, <&zs_clk>, <&zs_clk>;
+			clocks = <&p_clk>, <&zg_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
+				 <&cp_clk>, <&zs_clk>, <&zs_clk>, <&zs_clk>;
 			#clock-cells = <1>;
 			renesas,clock-indices = <
-				R8A7794_CLK_TMU1 R8A7794_CLK_TMU3 R8A7794_CLK_TMU2
-				R8A7794_CLK_CMT0 R8A7794_CLK_TMU0
+				R8A7794_CLK_TMU1 R8A7794_CLK_3DG R8A7794_CLK_TMU3
+				R8A7794_CLK_TMU2 R8A7794_CLK_CMT0 R8A7794_CLK_TMU0
 			>;
 			clock-output-names =
-				"tmu1", "tmu3", "tmu2", "cmt0", "tmu0";
+				"tmu1", "3dg", "tmu3", "tmu2", "cmt0", "tmu0";
 		};
 		mstp2_clks: mstp2_clks@e6150138 {
 			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
diff --git a/include/dt-bindings/clock/r8a7794-clock.h b/include/dt-bindings/clock/r8a7794-clock.h
index fd7cdee6a66..9066213f5a9 100644
--- a/include/dt-bindings/clock/r8a7794-clock.h
+++ b/include/dt-bindings/clock/r8a7794-clock.h
@@ -27,6 +27,7 @@
 
 /* MSTP1 */
 #define R8A7794_CLK_TMU1		11
+#define R8A7794_CLK_3DG			12
 #define R8A7794_CLK_TMU3		21
 #define R8A7794_CLK_TMU2		22
 #define R8A7794_CLK_CMT0		24
-- 
cgit v1.2.3-70-g09d2


From dc3cf93d89c525dcaebf4460109196fd9752c706 Mon Sep 17 00:00:00 2001
From: Yoshifumi Hosoya <yoshifumi.hosoya.wj@renesas.com>
Date: Wed, 12 Nov 2014 17:55:57 +0900
Subject: ARM: shmobile: r8a7794: Add MMP and VSP1 clocks to device tree

Signed-off-by: Yoshifumi Hosoya <yoshifumi.hosoya.wj@renesas.com>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 arch/arm/boot/dts/r8a7794.dtsi            | 14 +++++++++-----
 include/dt-bindings/clock/r8a7794-clock.h |  6 ++++++
 2 files changed, 15 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/arm/boot/dts/r8a7794.dtsi b/arch/arm/boot/dts/r8a7794.dtsi
index b6f8f451e3b..19c9de3f2a5 100644
--- a/arch/arm/boot/dts/r8a7794.dtsi
+++ b/arch/arm/boot/dts/r8a7794.dtsi
@@ -461,15 +461,19 @@
 		mstp1_clks: mstp1_clks@e6150134 {
 			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150134 0 4>, <0 0xe6150038 0 4>;
-			clocks = <&p_clk>, <&zg_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
-				 <&cp_clk>, <&zs_clk>, <&zs_clk>, <&zs_clk>;
+			clocks = <&zs_clk>, <&zs_clk>, <&p_clk>, <&zg_clk>, <&zs_clk>,
+				 <&zs_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>, <&cp_clk>,
+				 <&zs_clk>, <&zs_clk>;
 			#clock-cells = <1>;
 			renesas,clock-indices = <
-				R8A7794_CLK_TMU1 R8A7794_CLK_3DG R8A7794_CLK_TMU3
-				R8A7794_CLK_TMU2 R8A7794_CLK_CMT0 R8A7794_CLK_TMU0
+				R8A7794_CLK_VCP0 R8A7794_CLK_VPC0 R8A7794_CLK_TMU1
+				R8A7794_CLK_3DG R8A7794_CLK_2DDMAC R8A7794_CLK_FDP1_0
+				R8A7794_CLK_TMU3 R8A7794_CLK_TMU2 R8A7794_CLK_CMT0
+				R8A7794_CLK_TMU0 R8A7794_CLK_VSP1_DU0 R8A7794_CLK_VSP1_S
 			>;
 			clock-output-names =
-				"tmu1", "3dg", "tmu3", "tmu2", "cmt0", "tmu0";
+				"vcp0", "vpc0", "tmu1", "3dg", "2ddmac", "fdp1-0",
+				"tmu3", "tmu2", "cmt0", "tmu0", "vsp1-du0", "vsps";
 		};
 		mstp2_clks: mstp2_clks@e6150138 {
 			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
diff --git a/include/dt-bindings/clock/r8a7794-clock.h b/include/dt-bindings/clock/r8a7794-clock.h
index 9066213f5a9..aa9c286e60c 100644
--- a/include/dt-bindings/clock/r8a7794-clock.h
+++ b/include/dt-bindings/clock/r8a7794-clock.h
@@ -26,12 +26,18 @@
 #define R8A7794_CLK_MSIOF0		0
 
 /* MSTP1 */
+#define R8A7794_CLK_VCP0		1
+#define R8A7794_CLK_VPC0		3
 #define R8A7794_CLK_TMU1		11
 #define R8A7794_CLK_3DG			12
+#define R8A7794_CLK_2DDMAC		15
+#define R8A7794_CLK_FDP1_0		19
 #define R8A7794_CLK_TMU3		21
 #define R8A7794_CLK_TMU2		22
 #define R8A7794_CLK_CMT0		24
 #define R8A7794_CLK_TMU0		25
+#define R8A7794_CLK_VSP1_DU0		28
+#define R8A7794_CLK_VSP1_S		31
 
 /* MSTP2 */
 #define R8A7794_CLK_SCIFA2		2
-- 
cgit v1.2.3-70-g09d2


From 22853223d15b3a626de62cf9e40ce2d3881bc0a8 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Tue, 18 Nov 2014 19:45:51 +0100
Subject: regmap: ac97: Add generic AC'97 callbacks

Use the recently added support for bus operations to provide a standard
mapping for AC'97 register I/O.

Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
---
 drivers/base/regmap/Kconfig       |   5 +-
 drivers/base/regmap/Makefile      |   1 +
 drivers/base/regmap/regmap-ac97.c | 114 ++++++++++++++++++++++++++++++++++++++
 include/linux/regmap.h            |   7 +++
 4 files changed, 126 insertions(+), 1 deletion(-)
 create mode 100644 drivers/base/regmap/regmap-ac97.c

(limited to 'include')

diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig
index 8a3f51f7b1b..db9d00c36a3 100644
--- a/drivers/base/regmap/Kconfig
+++ b/drivers/base/regmap/Kconfig
@@ -3,12 +3,15 @@
 # subsystems should select the appropriate symbols.
 
 config REGMAP
-	default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_SPMI || REGMAP_MMIO || REGMAP_IRQ)
+	default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_SPMI || REGMAP_AC97 || REGMAP_MMIO || REGMAP_IRQ)
 	select LZO_COMPRESS
 	select LZO_DECOMPRESS
 	select IRQ_DOMAIN if REGMAP_IRQ
 	bool
 
+config REGMAP_AC97
+	tristate
+
 config REGMAP_I2C
 	tristate
 	depends on I2C
diff --git a/drivers/base/regmap/Makefile b/drivers/base/regmap/Makefile
index a7c670b4123..0a533653ef3 100644
--- a/drivers/base/regmap/Makefile
+++ b/drivers/base/regmap/Makefile
@@ -1,6 +1,7 @@
 obj-$(CONFIG_REGMAP) += regmap.o regcache.o
 obj-$(CONFIG_REGMAP) += regcache-rbtree.o regcache-lzo.o regcache-flat.o
 obj-$(CONFIG_DEBUG_FS) += regmap-debugfs.o
+obj-$(CONFIG_REGMAP_AC97) += regmap-ac97.o
 obj-$(CONFIG_REGMAP_I2C) += regmap-i2c.o
 obj-$(CONFIG_REGMAP_SPI) += regmap-spi.o
 obj-$(CONFIG_REGMAP_SPMI) += regmap-spmi.o
diff --git a/drivers/base/regmap/regmap-ac97.c b/drivers/base/regmap/regmap-ac97.c
new file mode 100644
index 00000000000..e4c45d2299c
--- /dev/null
+++ b/drivers/base/regmap/regmap-ac97.c
@@ -0,0 +1,114 @@
+/*
+ * Register map access API - AC'97 support
+ *
+ * Copyright 2013 Linaro Ltd.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#include <sound/ac97_codec.h>
+
+bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case AC97_RESET:
+	case AC97_POWERDOWN:
+	case AC97_INT_PAGING:
+	case AC97_EXTENDED_ID:
+	case AC97_EXTENDED_STATUS:
+	case AC97_EXTENDED_MID:
+	case AC97_EXTENDED_MSTATUS:
+	case AC97_GPIO_STATUS:
+	case AC97_MISC_AFE:
+	case AC97_VENDOR_ID1:
+	case AC97_VENDOR_ID2:
+	case AC97_CODEC_CLASS_REV:
+	case AC97_PCI_SVID:
+	case AC97_PCI_SID:
+	case AC97_FUNC_SELECT:
+	case AC97_FUNC_INFO:
+	case AC97_SENSE_INFO:
+		return true;
+	default:
+		return false;
+	}
+}
+EXPORT_SYMBOL_GPL(regmap_ac97_default_volatile);
+
+static int regmap_ac97_reg_read(void *context, unsigned int reg,
+	unsigned int *val)
+{
+	struct snd_ac97 *ac97 = context;
+
+	*val = ac97->bus->ops->read(ac97, reg);
+
+	return 0;
+}
+
+static int regmap_ac97_reg_write(void *context, unsigned int reg,
+	unsigned int val)
+{
+	struct snd_ac97 *ac97 = context;
+
+	ac97->bus->ops->write(ac97, reg, val);
+
+	return 0;
+}
+
+static const struct regmap_bus ac97_regmap_bus = {
+		.reg_write = regmap_ac97_reg_write,
+		.reg_read = regmap_ac97_reg_read,
+};
+
+/**
+ * regmap_init_ac97(): Initialise AC'97 register map
+ *
+ * @ac97: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer to
+ * a struct regmap.
+ */
+struct regmap *regmap_init_ac97(struct snd_ac97 *ac97,
+				const struct regmap_config *config)
+{
+	return regmap_init(&ac97->dev, &ac97_regmap_bus, ac97, config);
+}
+EXPORT_SYMBOL_GPL(regmap_init_ac97);
+
+/**
+ * devm_regmap_init_ac97(): Initialise AC'97 register map
+ *
+ * @ac97: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap.  The regmap will be automatically freed by the
+ * device management code.
+ */
+struct regmap *devm_regmap_init_ac97(struct snd_ac97 *ac97,
+				     const struct regmap_config *config)
+{
+	return devm_regmap_init(&ac97->dev, &ac97_regmap_bus, ac97, config);
+}
+EXPORT_SYMBOL_GPL(devm_regmap_init_ac97);
+
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index c5ed83f49c4..4419b99d8d6 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -27,6 +27,7 @@ struct spmi_device;
 struct regmap;
 struct regmap_range_cfg;
 struct regmap_field;
+struct snd_ac97;
 
 /* An enum of all the supported cache types */
 enum regcache_type {
@@ -340,6 +341,8 @@ struct regmap *regmap_init_spmi_ext(struct spmi_device *dev,
 struct regmap *regmap_init_mmio_clk(struct device *dev, const char *clk_id,
 				    void __iomem *regs,
 				    const struct regmap_config *config);
+struct regmap *regmap_init_ac97(struct snd_ac97 *ac97,
+				const struct regmap_config *config);
 
 struct regmap *devm_regmap_init(struct device *dev,
 				const struct regmap_bus *bus,
@@ -356,6 +359,10 @@ struct regmap *devm_regmap_init_spmi_ext(struct spmi_device *dev,
 struct regmap *devm_regmap_init_mmio_clk(struct device *dev, const char *clk_id,
 					 void __iomem *regs,
 					 const struct regmap_config *config);
+struct regmap *devm_regmap_init_ac97(struct snd_ac97 *ac97,
+				     const struct regmap_config *config);
+
+bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 
 /**
  * regmap_init_mmio(): Initialise register map
-- 
cgit v1.2.3-70-g09d2


From 20feb881988cdf5f53304c355ae8ee3bf82e80ec Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 18 Nov 2014 19:45:52 +0100
Subject: ASoC: Add helper functions for deferred regmap setup

Some drivers (most notably the AC'97 drivers) do not have access to their
regmap struct when the component/codec is registered. For those drivers the
automatic regmap setup will not work and needs to be done manually,
typically from the component/CODEC drivers probe callback.

This patch adds a set of helper function to handle deferred regmap
initialization as well as early regmap tear-down.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  | 35 +++++++++++++++++++++++++++++++
 sound/soc/soc-core.c | 58 ++++++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 82 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 7ba7130037a..342b43b3799 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1277,6 +1277,41 @@ void snd_soc_component_async_complete(struct snd_soc_component *component);
 int snd_soc_component_test_bits(struct snd_soc_component *component,
 	unsigned int reg, unsigned int mask, unsigned int value);
 
+void snd_soc_component_init_regmap(struct snd_soc_component *component,
+	struct regmap *regmap);
+void snd_soc_component_exit_regmap(struct snd_soc_component *component);
+
+/**
+ * snd_soc_codec_init_regmap() - Initialize regmap instance for the CODEC
+ * @codec: The CODEC for which to initialize the regmap instance
+ * @regmap: The regmap instance that should be used by the CODEC
+ *
+ * This function allows deferred assignment of the regmap instance that is
+ * associated with the CODEC. Only use this if the regmap instance is not yet
+ * ready when the CODEC is registered. The function must also be called before
+ * the first IO attempt of the CODEC.
+ */
+static inline void snd_soc_codec_init_regmap(struct snd_soc_codec *codec,
+	struct regmap *regmap)
+{
+	snd_soc_component_init_regmap(&codec->component, regmap);
+}
+
+/**
+ * snd_soc_codec_exit_regmap() - De-initialize regmap instance for the CODEC
+ * @codec: The CODEC for which to de-initialize the regmap instance
+ *
+ * Calls regmap_exit() on the regmap instance associated to the CODEC and
+ * removes the regmap instance from the CODEC.
+ *
+ * This function should only be used if snd_soc_codec_init_regmap() was used to
+ * initialize the regmap instance.
+ */
+static inline void snd_soc_codec_exit_regmap(struct snd_soc_codec *codec)
+{
+	snd_soc_component_exit_regmap(&codec->component);
+}
+
 /* device driver data */
 
 static inline void snd_soc_card_set_drvdata(struct snd_soc_card *card,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 4c8f8a23a0e..5fd5f08ce24 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -3996,22 +3996,58 @@ static int snd_soc_component_initialize(struct snd_soc_component *component,
 	return 0;
 }
 
-static void snd_soc_component_init_regmap(struct snd_soc_component *component)
+static void snd_soc_component_setup_regmap(struct snd_soc_component *component)
 {
-	if (!component->regmap)
-		component->regmap = dev_get_regmap(component->dev, NULL);
-	if (component->regmap) {
-		int val_bytes = regmap_get_val_bytes(component->regmap);
-		/* Errors are legitimate for non-integer byte multiples */
-		if (val_bytes > 0)
-			component->val_bytes = val_bytes;
-	}
+	int val_bytes = regmap_get_val_bytes(component->regmap);
+
+	/* Errors are legitimate for non-integer byte multiples */
+	if (val_bytes > 0)
+		component->val_bytes = val_bytes;
+}
+
+/**
+ * snd_soc_component_init_regmap() - Initialize regmap instance for the component
+ * @component: The component for which to initialize the regmap instance
+ * @regmap: The regmap instance that should be used by the component
+ *
+ * This function allows deferred assignment of the regmap instance that is
+ * associated with the component. Only use this if the regmap instance is not
+ * yet ready when the component is registered. The function must also be called
+ * before the first IO attempt of the component.
+ */
+void snd_soc_component_init_regmap(struct snd_soc_component *component,
+	struct regmap *regmap)
+{
+	component->regmap = regmap;
+	snd_soc_component_setup_regmap(component);
 }
+EXPORT_SYMBOL_GPL(snd_soc_component_init_regmap);
+
+/**
+ * snd_soc_component_exit_regmap() - De-initialize regmap instance for the component
+ * @component: The component for which to de-initialize the regmap instance
+ *
+ * Calls regmap_exit() on the regmap instance associated to the component and
+ * removes the regmap instance from the component.
+ *
+ * This function should only be used if snd_soc_component_init_regmap() was used
+ * to initialize the regmap instance.
+ */
+void snd_soc_component_exit_regmap(struct snd_soc_component *component)
+{
+	regmap_exit(component->regmap);
+	component->regmap = NULL;
+}
+EXPORT_SYMBOL_GPL(snd_soc_component_exit_regmap);
 
 static void snd_soc_component_add_unlocked(struct snd_soc_component *component)
 {
-	if (!component->write && !component->read)
-		snd_soc_component_init_regmap(component);
+	if (!component->write && !component->read) {
+		if (!component->regmap)
+			component->regmap = dev_get_regmap(component->dev, NULL);
+		if (component->regmap)
+			snd_soc_component_setup_regmap(component);
+	}
 
 	list_add(&component->list, &component_list);
 }
-- 
cgit v1.2.3-70-g09d2


From 62e88b1c00de9cb30d937841ed5debed871070b8 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Tue, 18 Nov 2014 10:23:50 -0800
Subject: mm: Make arch_unmap()/bprm_mm_init() available to all architectures

The x86 MPX patch set calls arch_unmap() and arch_bprm_mm_init()
from fs/exec.c, so we need at least a stub for them in all
architectures.  They are only called under an #ifdef for
CONFIG_MMU=y, so we can at least restict this to architectures
with MMU support.

blackfin/c6x have no MMU support, so do not call arch_unmap().
They also do not include mm_hooks.h or mmu_context.h at all and
do not need to be touched.

s390, um and unicore32 do not use asm-generic/mm_hooks.h, so got
their own arch_unmap() versions.  (I also moved um's
arch_dup_mmap() to be closer to the other mm_hooks.h functions).

xtensa only includes mm_hooks when MMU=y, which should be fine
since arch_unmap() is called only from MMU=y code.

For the rest, we use the stub copies of these functions in
asm-generic/mm_hook.h.

I cross compiled defconfigs for cris (to check NOMMU) and s390
to make sure that this works.  I also checked a 64-bit build
of UML and all my normal x86 builds including PARAVIRT on and
off.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: linux-arch@vger.kernel.org
Cc: x86@kernel.org
Link: http://lkml.kernel.org/r/20141118182350.8B4AA2C2@viggo.jf.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/s390/include/asm/mmu_context.h      | 11 +++++++++++
 arch/um/include/asm/mmu_context.h        | 24 +++++++++++++++++++-----
 arch/unicore32/include/asm/mmu_context.h | 11 +++++++++++
 include/asm-generic/mm_hooks.h           | 17 ++++++++++++++---
 include/asm-generic/mmu_context.h        |  6 ------
 5 files changed, 55 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 3815bfea1b2..f49b7195465 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -120,4 +120,15 @@ static inline void arch_exit_mmap(struct mm_struct *mm)
 {
 }
 
+static inline void arch_unmap(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+				     struct vm_area_struct *vma)
+{
+}
+
 #endif /* __S390_MMU_CONTEXT_H */
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index aa4a743dc4a..941527e507f 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -10,7 +10,26 @@
 #include <asm/mmu.h>
 
 extern void uml_setup_stubs(struct mm_struct *mm);
+/*
+ * Needed since we do not use the asm-generic/mm_hooks.h:
+ */
+static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
+{
+	uml_setup_stubs(mm);
+}
 extern void arch_exit_mmap(struct mm_struct *mm);
+static inline void arch_unmap(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+}
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+				     struct vm_area_struct *vma)
+{
+}
+/*
+ * end asm-generic/mm_hooks.h functions
+ */
 
 #define deactivate_mm(tsk,mm)	do { } while (0)
 
@@ -41,11 +60,6 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	}
 }
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
-{
-	uml_setup_stubs(mm);
-}
-
 static inline void enter_lazy_tlb(struct mm_struct *mm, 
 				  struct task_struct *tsk)
 {
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index ef470a7a3d0..1cb5220afaf 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -86,4 +86,15 @@ static inline void arch_dup_mmap(struct mm_struct *oldmm,
 {
 }
 
+static inline void arch_unmap(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+				     struct vm_area_struct *vma)
+{
+}
+
 #endif
diff --git a/include/asm-generic/mm_hooks.h b/include/asm-generic/mm_hooks.h
index 67dea812368..866aa461efa 100644
--- a/include/asm-generic/mm_hooks.h
+++ b/include/asm-generic/mm_hooks.h
@@ -1,7 +1,7 @@
 /*
- * Define generic no-op hooks for arch_dup_mmap and arch_exit_mmap, to
- * be included in asm-FOO/mmu_context.h for any arch FOO which doesn't
- * need to hook these.
+ * Define generic no-op hooks for arch_dup_mmap, arch_exit_mmap
+ * and arch_unmap to be included in asm-FOO/mmu_context.h for any
+ * arch FOO which doesn't need to hook these.
  */
 #ifndef _ASM_GENERIC_MM_HOOKS_H
 #define _ASM_GENERIC_MM_HOOKS_H
@@ -15,4 +15,15 @@ static inline void arch_exit_mmap(struct mm_struct *mm)
 {
 }
 
+static inline void arch_unmap(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+				     struct vm_area_struct *vma)
+{
+}
+
 #endif	/* _ASM_GENERIC_MM_HOOKS_H */
diff --git a/include/asm-generic/mmu_context.h b/include/asm-generic/mmu_context.h
index aa2d8ba35b2..1f2a8f9c926 100644
--- a/include/asm-generic/mmu_context.h
+++ b/include/asm-generic/mmu_context.h
@@ -47,10 +47,4 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 {
 }
 
-static inline void arch_unmap(struct mm_struct *mm,
-			struct vm_area_struct *vma,
-			unsigned long start, unsigned long end)
-{
-}
-
 #endif /* __ASM_GENERIC_MMU_CONTEXT_H */
-- 
cgit v1.2.3-70-g09d2


From 0378b59770130a994272b176a2a4346dc27361e9 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Wed, 19 Nov 2014 15:22:22 +0200
Subject: Bluetooth: Convert link keys list to use RCU

This patch converts the hdev->link_keys list to be protected through
RCU, thereby eliminating the need to hold the hdev lock while accessing
the list.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_core.c         | 37 ++++++++++++++++++-------------------
 net/bluetooth/hci_event.c        |  4 ++--
 3 files changed, 21 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index a805b3d97c0..396c09840fd 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -130,6 +130,7 @@ struct smp_irk {
 
 struct link_key {
 	struct list_head list;
+	struct rcu_head rcu;
 	bdaddr_t bdaddr;
 	u8 type;
 	u8 val[HCI_LINK_KEY_SIZE];
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index a67a4b8e4e1..5c319a49a5a 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -274,15 +274,13 @@ static const struct file_operations inquiry_cache_fops = {
 static int link_keys_show(struct seq_file *f, void *ptr)
 {
 	struct hci_dev *hdev = f->private;
-	struct list_head *p, *n;
+	struct link_key *key;
 
-	hci_dev_lock(hdev);
-	list_for_each_safe(p, n, &hdev->link_keys) {
-		struct link_key *key = list_entry(p, struct link_key, list);
+	rcu_read_lock();
+	list_for_each_entry_rcu(key, &hdev->link_keys, list)
 		seq_printf(f, "%pMR %u %*phN %u\n", &key->bdaddr, key->type,
 			   HCI_LINK_KEY_SIZE, key->val, key->pin_len);
-	}
-	hci_dev_unlock(hdev);
+	rcu_read_unlock();
 
 	return 0;
 }
@@ -3101,15 +3099,11 @@ void hci_uuids_clear(struct hci_dev *hdev)
 
 void hci_link_keys_clear(struct hci_dev *hdev)
 {
-	struct list_head *p, *n;
-
-	list_for_each_safe(p, n, &hdev->link_keys) {
-		struct link_key *key;
-
-		key = list_entry(p, struct link_key, list);
+	struct link_key *key;
 
-		list_del(p);
-		kfree(key);
+	list_for_each_entry_rcu(key, &hdev->link_keys, list) {
+		list_del_rcu(&key->list);
+		kfree_rcu(key, rcu);
 	}
 }
 
@@ -3137,9 +3131,14 @@ struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr)
 {
 	struct link_key *k;
 
-	list_for_each_entry(k, &hdev->link_keys, list)
-		if (bacmp(bdaddr, &k->bdaddr) == 0)
+	rcu_read_lock();
+	list_for_each_entry_rcu(k, &hdev->link_keys, list) {
+		if (bacmp(bdaddr, &k->bdaddr) == 0) {
+			rcu_read_unlock();
 			return k;
+		}
+	}
+	rcu_read_unlock();
 
 	return NULL;
 }
@@ -3290,7 +3289,7 @@ struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn,
 		key = kzalloc(sizeof(*key), GFP_KERNEL);
 		if (!key)
 			return NULL;
-		list_add(&key->list, &hdev->link_keys);
+		list_add_rcu(&key->list, &hdev->link_keys);
 	}
 
 	BT_DBG("%s key for %pMR type %u", hdev->name, bdaddr, type);
@@ -3383,8 +3382,8 @@ int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr)
 
 	BT_DBG("%s removing %pMR", hdev->name, bdaddr);
 
-	list_del(&key->list);
-	kfree(key);
+	list_del_rcu(&key->list);
+	kfree_rcu(key, rcu);
 
 	return 0;
 }
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 54680fd3960..bd0a8012066 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3324,8 +3324,8 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	 */
 	if (key->type == HCI_LK_DEBUG_COMBINATION &&
 	    !test_bit(HCI_KEEP_DEBUG_KEYS, &hdev->dev_flags)) {
-		list_del(&key->list);
-		kfree(key);
+		list_del_rcu(&key->list);
+		kfree_rcu(key, rcu);
 	} else if (conn) {
 		if (persistent)
 			clear_bit(HCI_CONN_FLUSH_KEY, &conn->flags);
-- 
cgit v1.2.3-70-g09d2


From d67ee213fa5700c7da526fe5bcccd485cfa63d8b Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Tue, 28 Oct 2014 20:13:31 -0400
Subject: dm: add presuspend_undo hook to target_type

The DM thin-pool target now must undo the changes performed during
pool_presuspend() so introduce presuspend_undo hook in target_type.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
---
 drivers/md/dm-table.c         | 36 +++++++++++++++++++++++++++++-------
 drivers/md/dm.c               | 10 ++++++++--
 drivers/md/dm.h               |  1 +
 include/linux/device-mapper.h |  2 ++
 include/uapi/linux/dm-ioctl.h |  4 ++--
 5 files changed, 42 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index b2bd1ebf456..3afae9e062f 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1521,18 +1521,32 @@ fmode_t dm_table_get_mode(struct dm_table *t)
 }
 EXPORT_SYMBOL(dm_table_get_mode);
 
-static void suspend_targets(struct dm_table *t, unsigned postsuspend)
+enum suspend_mode {
+	PRESUSPEND,
+	PRESUSPEND_UNDO,
+	POSTSUSPEND,
+};
+
+static void suspend_targets(struct dm_table *t, enum suspend_mode mode)
 {
 	int i = t->num_targets;
 	struct dm_target *ti = t->targets;
 
 	while (i--) {
-		if (postsuspend) {
+		switch (mode) {
+		case PRESUSPEND:
+			if (ti->type->presuspend)
+				ti->type->presuspend(ti);
+			break;
+		case PRESUSPEND_UNDO:
+			if (ti->type->presuspend_undo)
+				ti->type->presuspend_undo(ti);
+			break;
+		case POSTSUSPEND:
 			if (ti->type->postsuspend)
 				ti->type->postsuspend(ti);
-		} else if (ti->type->presuspend)
-			ti->type->presuspend(ti);
-
+			break;
+		}
 		ti++;
 	}
 }
@@ -1542,7 +1556,15 @@ void dm_table_presuspend_targets(struct dm_table *t)
 	if (!t)
 		return;
 
-	suspend_targets(t, 0);
+	suspend_targets(t, PRESUSPEND);
+}
+
+void dm_table_presuspend_undo_targets(struct dm_table *t)
+{
+	if (!t)
+		return;
+
+	suspend_targets(t, PRESUSPEND_UNDO);
 }
 
 void dm_table_postsuspend_targets(struct dm_table *t)
@@ -1550,7 +1572,7 @@ void dm_table_postsuspend_targets(struct dm_table *t)
 	if (!t)
 		return;
 
-	suspend_targets(t, 1);
+	suspend_targets(t, POSTSUSPEND);
 }
 
 int dm_table_resume_targets(struct dm_table *t)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index f8cdd97c28a..f84de321598 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2756,7 +2756,10 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
 	if (noflush)
 		set_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
 
-	/* This does not get reverted if there's an error later. */
+	/*
+	 * This gets reverted if there's an error later and the targets
+	 * provide the .presuspend_undo hook.
+	 */
 	dm_table_presuspend_targets(map);
 
 	/*
@@ -2767,8 +2770,10 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
 	 */
 	if (!noflush && do_lockfs) {
 		r = lock_fs(md);
-		if (r)
+		if (r) {
+			dm_table_presuspend_undo_targets(map);
 			goto out_unlock;
+		}
 	}
 
 	/*
@@ -2816,6 +2821,7 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
 			start_queue(md->queue);
 
 		unlock_fs(md);
+		dm_table_presuspend_undo_targets(map);
 		goto out_unlock; /* pushback list is already flushed, so skip flush */
 	}
 
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 988c7fb7b14..781994093bf 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -65,6 +65,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			       struct queue_limits *limits);
 struct list_head *dm_table_get_devices(struct dm_table *t);
 void dm_table_presuspend_targets(struct dm_table *t);
+void dm_table_presuspend_undo_targets(struct dm_table *t);
 void dm_table_postsuspend_targets(struct dm_table *t);
 int dm_table_resume_targets(struct dm_table *t);
 int dm_table_any_congested(struct dm_table *t, int bdi_bits);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index e1707de043a..ca6d2acc5eb 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -64,6 +64,7 @@ typedef int (*dm_request_endio_fn) (struct dm_target *ti,
 				    union map_info *map_context);
 
 typedef void (*dm_presuspend_fn) (struct dm_target *ti);
+typedef void (*dm_presuspend_undo_fn) (struct dm_target *ti);
 typedef void (*dm_postsuspend_fn) (struct dm_target *ti);
 typedef int (*dm_preresume_fn) (struct dm_target *ti);
 typedef void (*dm_resume_fn) (struct dm_target *ti);
@@ -145,6 +146,7 @@ struct target_type {
 	dm_endio_fn end_io;
 	dm_request_endio_fn rq_end_io;
 	dm_presuspend_fn presuspend;
+	dm_presuspend_undo_fn presuspend_undo;
 	dm_postsuspend_fn postsuspend;
 	dm_preresume_fn preresume;
 	dm_resume_fn resume;
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index 3315ab21f72..2be66f4be2f 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -267,9 +267,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	28
+#define DM_VERSION_MINOR	29
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2014-09-17)"
+#define DM_VERSION_EXTRA	"-ioctl (2014-10-28)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
-- 
cgit v1.2.3-70-g09d2


From ffcc39364160663cda1a3c358f4537302a92459b Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Tue, 28 Oct 2014 18:34:52 -0400
Subject: dm: enhance internal suspend and resume interface

Rename dm_internal_{suspend,resume} to dm_internal_{suspend,resume}_fast
-- dm-stats will continue using these methods to avoid all the extra
suspend/resume logic that is not needed in order to quickly flush IO.

Introduce dm_internal_suspend_noflush() variant that actually calls the
mapped_device's target callbacks -- otherwise target-specific hooks are
avoided (e.g. dm-thin's thin_presuspend and thin_postsuspend).  Common
code between dm_internal_{suspend_noflush,resume} and
dm_{suspend,resume} was factored out as __dm_{suspend,resume}.

Update dm_internal_{suspend_noflush,resume} to always take and release
the mapped_device's suspend_lock.  Also update dm_{suspend,resume} to be
aware of potential for DM_INTERNAL_SUSPEND_FLAG to be set and respond
accordingly by interruptibly waiting for the DM_INTERNAL_SUSPEND_FLAG to
be cleared.  Add lockdep annotation to dm_suspend() and dm_resume().

The existing DM_SUSPEND_FLAG remains unchanged.
DM_INTERNAL_SUSPEND_FLAG is set by dm_internal_suspend_noflush() and
cleared by dm_internal_resume().

Both DM_SUSPEND_FLAG and DM_INTERNAL_SUSPEND_FLAG may be set if a device
was already suspended when dm_internal_suspend_noflush() was called --
this can be thought of as a "nested suspend".  A "nested suspend" can
occur with legacy userspace dm-thin code that might suspend all active
thin volumes before suspending the pool for resize.

But otherwise, in the normal dm-thin-pool suspend case moving forward:
the thin-pool will have DM_SUSPEND_FLAG set and all active thins from
that thin-pool will have DM_INTERNAL_SUSPEND_FLAG set.

Also add DM_INTERNAL_SUSPEND_FLAG to status report.  This new
DM_INTERNAL_SUSPEND_FLAG state is being reported to assist with
debugging (e.g. 'dmsetup info' will report an internally suspended
device accordingly).

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
---
 drivers/md/dm-ioctl.c         |   5 +-
 drivers/md/dm-stats.c         |   2 +-
 drivers/md/dm.c               | 229 +++++++++++++++++++++++++++++++-----------
 drivers/md/dm.h               |   9 ++
 include/uapi/linux/dm-ioctl.h |   5 +
 5 files changed, 192 insertions(+), 58 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 0be9381365d..73f791bb9ea 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -684,11 +684,14 @@ static void __dev_status(struct mapped_device *md, struct dm_ioctl *param)
 	int srcu_idx;
 
 	param->flags &= ~(DM_SUSPEND_FLAG | DM_READONLY_FLAG |
-			  DM_ACTIVE_PRESENT_FLAG);
+			  DM_ACTIVE_PRESENT_FLAG | DM_INTERNAL_SUSPEND_FLAG);
 
 	if (dm_suspended_md(md))
 		param->flags |= DM_SUSPEND_FLAG;
 
+	if (dm_suspended_internally_md(md))
+		param->flags |= DM_INTERNAL_SUSPEND_FLAG;
+
 	if (dm_test_deferred_remove_flag(md))
 		param->flags |= DM_DEFERRED_REMOVE;
 
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 28a90122a5a..42a057aa381 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -824,7 +824,7 @@ static int message_stats_create(struct mapped_device *md,
 		return 1;
 
 	id = dm_stats_create(dm_get_stats(md), start, end, step, program_id, aux_data,
-			     dm_internal_suspend, dm_internal_resume, md);
+			     dm_internal_suspend_fast, dm_internal_resume_fast, md);
 	if (id < 0)
 		return id;
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index f84de321598..a0ece87ad42 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -19,6 +19,7 @@
 #include <linux/idr.h>
 #include <linux/hdreg.h>
 #include <linux/delay.h>
+#include <linux/wait.h>
 
 #include <trace/events/block.h>
 
@@ -117,6 +118,7 @@ EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo);
 #define DMF_NOFLUSH_SUSPENDING 5
 #define DMF_MERGE_IS_OPTIONAL 6
 #define DMF_DEFERRED_REMOVE 7
+#define DMF_SUSPENDED_INTERNALLY 8
 
 /*
  * A dummy definition to make RCU happy.
@@ -2718,36 +2720,18 @@ static void unlock_fs(struct mapped_device *md)
 }
 
 /*
- * We need to be able to change a mapping table under a mounted
- * filesystem.  For example we might want to move some data in
- * the background.  Before the table can be swapped with
- * dm_bind_table, dm_suspend must be called to flush any in
- * flight bios and ensure that any further io gets deferred.
- */
-/*
- * Suspend mechanism in request-based dm.
- *
- * 1. Flush all I/Os by lock_fs() if needed.
- * 2. Stop dispatching any I/O by stopping the request_queue.
- * 3. Wait for all in-flight I/Os to be completed or requeued.
+ * If __dm_suspend returns 0, the device is completely quiescent
+ * now. There is no request-processing activity. All new requests
+ * are being added to md->deferred list.
  *
- * To abort suspend, start the request_queue.
+ * Caller must hold md->suspend_lock
  */
-int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
+static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
+			unsigned suspend_flags, int interruptible)
 {
-	struct dm_table *map = NULL;
-	int r = 0;
-	int do_lockfs = suspend_flags & DM_SUSPEND_LOCKFS_FLAG ? 1 : 0;
-	int noflush = suspend_flags & DM_SUSPEND_NOFLUSH_FLAG ? 1 : 0;
-
-	mutex_lock(&md->suspend_lock);
-
-	if (dm_suspended_md(md)) {
-		r = -EINVAL;
-		goto out_unlock;
-	}
-
-	map = rcu_dereference(md->map);
+	bool do_lockfs = suspend_flags & DM_SUSPEND_LOCKFS_FLAG;
+	bool noflush = suspend_flags & DM_SUSPEND_NOFLUSH_FLAG;
+	int r;
 
 	/*
 	 * DMF_NOFLUSH_SUSPENDING must be set before presuspend.
@@ -2772,7 +2756,7 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
 		r = lock_fs(md);
 		if (r) {
 			dm_table_presuspend_undo_targets(map);
-			goto out_unlock;
+			return r;
 		}
 	}
 
@@ -2806,7 +2790,7 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
 	 * We call dm_wait_for_completion to wait for all existing requests
 	 * to finish.
 	 */
-	r = dm_wait_for_completion(md, TASK_INTERRUPTIBLE);
+	r = dm_wait_for_completion(md, interruptible);
 
 	if (noflush)
 		clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
@@ -2822,14 +2806,55 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
 
 		unlock_fs(md);
 		dm_table_presuspend_undo_targets(map);
-		goto out_unlock; /* pushback list is already flushed, so skip flush */
+		/* pushback list is already flushed, so skip flush */
 	}
 
-	/*
-	 * If dm_wait_for_completion returned 0, the device is completely
-	 * quiescent now. There is no request-processing activity. All new
-	 * requests are being added to md->deferred list.
-	 */
+	return r;
+}
+
+/*
+ * We need to be able to change a mapping table under a mounted
+ * filesystem.  For example we might want to move some data in
+ * the background.  Before the table can be swapped with
+ * dm_bind_table, dm_suspend must be called to flush any in
+ * flight bios and ensure that any further io gets deferred.
+ */
+/*
+ * Suspend mechanism in request-based dm.
+ *
+ * 1. Flush all I/Os by lock_fs() if needed.
+ * 2. Stop dispatching any I/O by stopping the request_queue.
+ * 3. Wait for all in-flight I/Os to be completed or requeued.
+ *
+ * To abort suspend, start the request_queue.
+ */
+int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
+{
+	struct dm_table *map = NULL;
+	int r = 0;
+
+retry:
+	mutex_lock_nested(&md->suspend_lock, SINGLE_DEPTH_NESTING);
+
+	if (dm_suspended_md(md)) {
+		r = -EINVAL;
+		goto out_unlock;
+	}
+
+	if (dm_suspended_internally_md(md)) {
+		/* already internally suspended, wait for internal resume */
+		mutex_unlock(&md->suspend_lock);
+		r = wait_on_bit(&md->flags, DMF_SUSPENDED_INTERNALLY, TASK_INTERRUPTIBLE);
+		if (r)
+			return r;
+		goto retry;
+	}
+
+	map = rcu_dereference(md->map);
+
+	r = __dm_suspend(md, map, suspend_flags, TASK_INTERRUPTIBLE);
+	if (r)
+		goto out_unlock;
 
 	set_bit(DMF_SUSPENDED, &md->flags);
 
@@ -2840,35 +2865,57 @@ out_unlock:
 	return r;
 }
 
+static int __dm_resume(struct mapped_device *md, struct dm_table *map)
+{
+	if (map) {
+		int r = dm_table_resume_targets(map);
+		if (r)
+			return r;
+	}
+
+	dm_queue_flush(md);
+
+	/*
+	 * Flushing deferred I/Os must be done after targets are resumed
+	 * so that mapping of targets can work correctly.
+	 * Request-based dm is queueing the deferred I/Os in its request_queue.
+	 */
+	if (dm_request_based(md))
+		start_queue(md->queue);
+
+	unlock_fs(md);
+
+	return 0;
+}
+
 int dm_resume(struct mapped_device *md)
 {
 	int r = -EINVAL;
 	struct dm_table *map = NULL;
 
-	mutex_lock(&md->suspend_lock);
+retry:
+	mutex_lock_nested(&md->suspend_lock, SINGLE_DEPTH_NESTING);
+
 	if (!dm_suspended_md(md))
 		goto out;
 
+	if (dm_suspended_internally_md(md)) {
+		/* already internally suspended, wait for internal resume */
+		mutex_unlock(&md->suspend_lock);
+		r = wait_on_bit(&md->flags, DMF_SUSPENDED_INTERNALLY, TASK_INTERRUPTIBLE);
+		if (r)
+			return r;
+		goto retry;
+	}
+
 	map = rcu_dereference(md->map);
 	if (!map || !dm_table_get_size(map))
 		goto out;
 
-	r = dm_table_resume_targets(map);
+	r = __dm_resume(md, map);
 	if (r)
 		goto out;
 
-	dm_queue_flush(md);
-
-	/*
-	 * Flushing deferred I/Os must be done after targets are resumed
-	 * so that mapping of targets can work correctly.
-	 * Request-based dm is queueing the deferred I/Os in its request_queue.
-	 */
-	if (dm_request_based(md))
-		start_queue(md->queue);
-
-	unlock_fs(md);
-
 	clear_bit(DMF_SUSPENDED, &md->flags);
 
 	r = 0;
@@ -2882,15 +2929,80 @@ out:
  * Internal suspend/resume works like userspace-driven suspend. It waits
  * until all bios finish and prevents issuing new bios to the target drivers.
  * It may be used only from the kernel.
- *
- * Internal suspend holds md->suspend_lock, which prevents interaction with
- * userspace-driven suspend.
  */
 
-void dm_internal_suspend(struct mapped_device *md)
+static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_flags)
 {
-	mutex_lock(&md->suspend_lock);
+	struct dm_table *map = NULL;
+
+	if (dm_suspended_internally_md(md))
+		return; /* nested internal suspend */
+
+	if (dm_suspended_md(md)) {
+		set_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
+		return; /* nest suspend */
+	}
+
+	map = rcu_dereference(md->map);
+
+	/*
+	 * Using TASK_UNINTERRUPTIBLE because only NOFLUSH internal suspend is
+	 * supported.  Properly supporting a TASK_INTERRUPTIBLE internal suspend
+	 * would require changing .presuspend to return an error -- avoid this
+	 * until there is a need for more elaborate variants of internal suspend.
+	 */
+	(void) __dm_suspend(md, map, suspend_flags, TASK_UNINTERRUPTIBLE);
+
+	set_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
+
+	dm_table_postsuspend_targets(map);
+}
+
+static void __dm_internal_resume(struct mapped_device *md)
+{
+	if (!dm_suspended_internally_md(md))
+		return; /* resume from nested internal suspend */
+
 	if (dm_suspended_md(md))
+		goto done; /* resume from nested suspend */
+
+	/*
+	 * NOTE: existing callers don't need to call dm_table_resume_targets
+	 * (which may fail -- so best to avoid it for now by passing NULL map)
+	 */
+	(void) __dm_resume(md, NULL);
+
+done:
+	clear_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
+	smp_mb__after_atomic();
+	wake_up_bit(&md->flags, DMF_SUSPENDED_INTERNALLY);
+}
+
+void dm_internal_suspend_noflush(struct mapped_device *md)
+{
+	mutex_lock(&md->suspend_lock);
+	__dm_internal_suspend(md, DM_SUSPEND_NOFLUSH_FLAG);
+	mutex_unlock(&md->suspend_lock);
+}
+EXPORT_SYMBOL_GPL(dm_internal_suspend_noflush);
+
+void dm_internal_resume(struct mapped_device *md)
+{
+	mutex_lock(&md->suspend_lock);
+	__dm_internal_resume(md);
+	mutex_unlock(&md->suspend_lock);
+}
+EXPORT_SYMBOL_GPL(dm_internal_resume);
+
+/*
+ * Fast variants of internal suspend/resume hold md->suspend_lock,
+ * which prevents interaction with userspace-driven suspend.
+ */
+
+void dm_internal_suspend_fast(struct mapped_device *md)
+{
+	mutex_lock(&md->suspend_lock);
+	if (dm_suspended_md(md) || dm_suspended_internally_md(md))
 		return;
 
 	set_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags);
@@ -2899,9 +3011,9 @@ void dm_internal_suspend(struct mapped_device *md)
 	dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
 }
 
-void dm_internal_resume(struct mapped_device *md)
+void dm_internal_resume_fast(struct mapped_device *md)
 {
-	if (dm_suspended_md(md))
+	if (dm_suspended_md(md) || dm_suspended_internally_md(md))
 		goto done;
 
 	dm_queue_flush(md);
@@ -2987,6 +3099,11 @@ int dm_suspended_md(struct mapped_device *md)
 	return test_bit(DMF_SUSPENDED, &md->flags);
 }
 
+int dm_suspended_internally_md(struct mapped_device *md)
+{
+	return test_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
+}
+
 int dm_test_deferred_remove_flag(struct mapped_device *md)
 {
 	return test_bit(DMF_DEFERRED_REMOVE, &md->flags);
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 781994093bf..84b0f9e4ba6 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -129,6 +129,15 @@ int dm_deleting_md(struct mapped_device *md);
  */
 int dm_suspended_md(struct mapped_device *md);
 
+/*
+ * Internal suspend and resume methods.
+ */
+int dm_suspended_internally_md(struct mapped_device *md);
+void dm_internal_suspend_fast(struct mapped_device *md);
+void dm_internal_resume_fast(struct mapped_device *md);
+void dm_internal_suspend_noflush(struct mapped_device *md);
+void dm_internal_resume(struct mapped_device *md);
+
 /*
  * Test if the device is scheduled for deferred remove.
  */
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index 2be66f4be2f..a570d7b5796 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -352,4 +352,9 @@ enum {
  */
 #define DM_DEFERRED_REMOVE		(1 << 17) /* In/Out */
 
+/*
+ * If set, the device is suspended internally.
+ */
+#define DM_INTERNAL_SUSPEND_FLAG	(1 << 18) /* Out */
+
 #endif				/* _LINUX_DM_IOCTL_H */
-- 
cgit v1.2.3-70-g09d2


From 1277b4a9f531e84e26f9e0210c1801b0c0bf81ca Mon Sep 17 00:00:00 2001
From: Liad Kaufman <liad.kaufman@intel.com>
Date: Sun, 9 Nov 2014 18:50:08 +0200
Subject: mac80211: retransmit TDLS teardown packet through AP if not ACKed

Since the TDLS peer station might not receive the teardown
packet (e.g., when in PS), this makes sure the packet is
retransmitted - this time through the AP - if the TDLS peer
didn't ACK the packet.

Signed-off-by: Liad Kaufman <liad.kaufman@intel.com>
Signed-off-by: Arik Nemtsov <arik@wizery.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h  | 25 ++++++++++++++++++++
 net/mac80211/ieee80211_i.h |  4 ++++
 net/mac80211/mlme.c        | 12 ++++++++++
 net/mac80211/status.c      | 55 ++++++++++++++++++++++++++++++++++++++++--
 net/mac80211/tdls.c        | 59 +++++++++++++++++++++++++++++++++++++---------
 5 files changed, 142 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index f65b5446d98..4e2bb910787 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -19,6 +19,7 @@
 #include <linux/types.h>
 #include <linux/if_ether.h>
 #include <asm/byteorder.h>
+#include <asm/unaligned.h>
 
 /*
  * DS bit usage
@@ -2418,6 +2419,30 @@ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim,
 	return !!(tim->virtual_map[index] & mask);
 }
 
+/**
+ * ieee80211_get_tdls_action - get tdls packet action (or -1, if not tdls packet)
+ * @skb: the skb containing the frame, length will not be checked
+ * @hdr_size: the size of the ieee80211_hdr that starts at skb->data
+ *
+ * This function assumes the frame is a data frame, and that the network header
+ * is in the correct place.
+ */
+static inline int ieee80211_get_tdls_action(struct sk_buff *skb, u32 hdr_size)
+{
+	if (!skb_is_nonlinear(skb) &&
+	    skb->len > (skb_network_offset(skb) + 2)) {
+		/* Point to where the indication of TDLS should start */
+		const u8 *tdls_data = skb_network_header(skb) - 2;
+
+		if (get_unaligned_be16(tdls_data) == ETH_P_TDLS &&
+		    tdls_data[2] == WLAN_TDLS_SNAP_RFTYPE &&
+		    tdls_data[3] == WLAN_CATEGORY_TDLS)
+			return tdls_data[4];
+	}
+
+	return -1;
+}
+
 /* convert time units */
 #define TU_TO_JIFFIES(x)	(usecs_to_jiffies((x) * 1024))
 #define TU_TO_EXP_TIME(x)	(jiffies + TU_TO_JIFFIES(x))
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 208953d1d02..bc6f12ff1f6 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -525,8 +525,12 @@ struct ieee80211_if_managed {
 	struct ieee80211_vht_cap vht_capa; /* configured VHT overrides */
 	struct ieee80211_vht_cap vht_capa_mask; /* Valid parts of vht_capa */
 
+	/* TDLS support */
 	u8 tdls_peer[ETH_ALEN] __aligned(2);
 	struct delayed_work tdls_peer_del_work;
+	struct sk_buff *orig_teardown_skb; /* The original teardown skb */
+	struct sk_buff *teardown_skb; /* A copy to send through the AP */
+	spinlock_t teardown_lock; /* To lock changing teardown_skb */
 
 	/* WMM-AC TSPEC support */
 	struct ieee80211_sta_tx_tspec tx_tspec[IEEE80211_NUM_ACS];
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 24353987899..11a937f3fde 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4003,6 +4003,11 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata)
 		ifmgd->req_smps = IEEE80211_SMPS_AUTOMATIC;
 	else
 		ifmgd->req_smps = IEEE80211_SMPS_OFF;
+
+	/* Setup TDLS data */
+	spin_lock_init(&ifmgd->teardown_lock);
+	ifmgd->teardown_skb = NULL;
+	ifmgd->orig_teardown_skb = NULL;
 }
 
 /* scan finished notification */
@@ -4865,6 +4870,13 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata)
 	}
 	if (ifmgd->auth_data)
 		ieee80211_destroy_auth_data(sdata, false);
+	spin_lock_bh(&ifmgd->teardown_lock);
+	if (ifmgd->teardown_skb) {
+		kfree_skb(ifmgd->teardown_skb);
+		ifmgd->teardown_skb = NULL;
+		ifmgd->orig_teardown_skb = NULL;
+	}
+	spin_unlock_bh(&ifmgd->teardown_lock);
 	del_timer_sync(&ifmgd->timer);
 	sdata_unlock(sdata);
 }
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 9612d89fad5..71de2d3866c 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -390,6 +390,46 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local,
 	}
 }
 
+/*
+ * Handles the tx for TDLS teardown frames.
+ * If the frame wasn't ACKed by the peer - it will be re-sent through the AP
+ */
+static void ieee80211_tdls_td_tx_handle(struct ieee80211_local *local,
+					struct ieee80211_sub_if_data *sdata,
+					struct sk_buff *skb, u32 flags)
+{
+	struct sk_buff *teardown_skb;
+	struct sk_buff *orig_teardown_skb;
+	bool is_teardown = false;
+
+	/* Get the teardown data we need and free the lock */
+	spin_lock(&sdata->u.mgd.teardown_lock);
+	teardown_skb = sdata->u.mgd.teardown_skb;
+	orig_teardown_skb = sdata->u.mgd.orig_teardown_skb;
+	if ((skb == orig_teardown_skb) && teardown_skb) {
+		sdata->u.mgd.teardown_skb = NULL;
+		sdata->u.mgd.orig_teardown_skb = NULL;
+		is_teardown = true;
+	}
+	spin_unlock(&sdata->u.mgd.teardown_lock);
+
+	if (is_teardown) {
+		/* This mechanism relies on being able to get ACKs */
+		WARN_ON(!(local->hw.flags &
+			  IEEE80211_HW_REPORTS_TX_ACK_STATUS));
+
+		/* Check if peer has ACKed */
+		if (flags & IEEE80211_TX_STAT_ACK) {
+			dev_kfree_skb_any(teardown_skb);
+		} else {
+			tdls_dbg(sdata,
+				 "TDLS Resending teardown through AP\n");
+
+			ieee80211_subif_start_xmit(teardown_skb, skb->dev);
+		}
+	}
+}
+
 static void ieee80211_report_used_skb(struct ieee80211_local *local,
 				      struct sk_buff *skb, bool dropped)
 {
@@ -426,8 +466,19 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local,
 		if (!sdata) {
 			skb->dev = NULL;
 		} else if (info->flags & IEEE80211_TX_INTFL_MLME_CONN_TX) {
-			ieee80211_mgd_conn_tx_status(sdata, hdr->frame_control,
-						     acked);
+			unsigned int hdr_size =
+				ieee80211_hdrlen(hdr->frame_control);
+
+			/* Check to see if packet is a TDLS teardown packet */
+			if (ieee80211_is_data(hdr->frame_control) &&
+			    (ieee80211_get_tdls_action(skb, hdr_size) ==
+			     WLAN_TDLS_TEARDOWN))
+				ieee80211_tdls_td_tx_handle(local, sdata, skb,
+							    info->flags);
+			else
+				ieee80211_mgd_conn_tx_status(sdata,
+							     hdr->frame_control,
+							     acked);
 		} else if (ieee80211_is_nullfunc(hdr->frame_control) ||
 			   ieee80211_is_qos_nullfunc(hdr->frame_control)) {
 			cfg80211_probe_status(sdata->dev, hdr->addr1,
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index b4f368e2cb3..d4fe091fd98 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -512,20 +512,22 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
 	struct sk_buff *skb = NULL;
+	u32 flags = 0;
 	bool send_direct;
 	struct sta_info *sta;
 	int ret;
 
-	skb = dev_alloc_skb(local->hw.extra_tx_headroom +
-			    max(sizeof(struct ieee80211_mgmt),
-				sizeof(struct ieee80211_tdls_data)) +
-			    50 + /* supported rates */
-			    7 + /* ext capab */
-			    26 + /* max(WMM-info, WMM-param) */
-			    2 + max(sizeof(struct ieee80211_ht_cap),
-				    sizeof(struct ieee80211_ht_operation)) +
-			    extra_ies_len +
-			    sizeof(struct ieee80211_tdls_lnkie));
+	skb = netdev_alloc_skb(dev,
+			       local->hw.extra_tx_headroom +
+			       max(sizeof(struct ieee80211_mgmt),
+				   sizeof(struct ieee80211_tdls_data)) +
+			       50 + /* supported rates */
+			       7 + /* ext capab */
+			       26 + /* max(WMM-info, WMM-param) */
+			       2 + max(sizeof(struct ieee80211_ht_cap),
+				       sizeof(struct ieee80211_ht_operation)) +
+			       extra_ies_len +
+			       sizeof(struct ieee80211_tdls_lnkie));
 	if (!skb)
 		return -ENOMEM;
 
@@ -623,9 +625,44 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 		break;
 	}
 
+	/*
+	 * Set the WLAN_TDLS_TEARDOWN flag to indicate a teardown in progress.
+	 * Later, if no ACK is returned from peer, we will re-send the teardown
+	 * packet through the AP.
+	 */
+	if ((action_code == WLAN_TDLS_TEARDOWN) &&
+	    (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)) {
+		struct sta_info *sta = NULL;
+		bool try_resend; /* Should we keep skb for possible resend */
+
+		/* If not sending directly to peer - no point in keeping skb */
+		rcu_read_lock();
+		sta = sta_info_get(sdata, peer);
+		try_resend = sta && test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH);
+		rcu_read_unlock();
+
+		spin_lock_bh(&sdata->u.mgd.teardown_lock);
+		if (try_resend && !sdata->u.mgd.teardown_skb) {
+			/* Mark it as requiring TX status callback  */
+			flags |= IEEE80211_TX_CTL_REQ_TX_STATUS |
+				 IEEE80211_TX_INTFL_MLME_CONN_TX;
+
+			/*
+			 * skb is copied since mac80211 will later set
+			 * properties that might not be the same as the AP,
+			 * such as encryption, QoS, addresses, etc.
+			 *
+			 * No problem if skb_copy() fails, so no need to check.
+			 */
+			sdata->u.mgd.teardown_skb = skb_copy(skb, GFP_ATOMIC);
+			sdata->u.mgd.orig_teardown_skb = skb;
+		}
+		spin_unlock_bh(&sdata->u.mgd.teardown_lock);
+	}
+
 	/* disable bottom halves when entering the Tx path */
 	local_bh_disable();
-	ret = ieee80211_subif_start_xmit(skb, dev);
+	__ieee80211_subif_start_xmit(skb, dev, flags);
 	local_bh_enable();
 
 	return ret;
-- 
cgit v1.2.3-70-g09d2


From 2cedd87960a809dd9bf683f72123b7dce6736f07 Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Sun, 9 Nov 2014 18:50:13 +0200
Subject: mac80211: add BSS coex IE to TDLS setup frames

Add the BSS coex IE in case we support HT40 channels, as mandated by
section 8.5.13 in IEEE802.11 2012.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Signed-off-by: Arik Nemtsov <arik@wizery.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h |  3 +++
 net/mac80211/tdls.c       | 15 +++++++++++++++
 2 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 4e2bb910787..adac1be6738 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2037,6 +2037,9 @@ enum ieee80211_tdls_actioncode {
 /* TDLS specific payload type in the LLC/SNAP header */
 #define WLAN_TDLS_SNAP_RFTYPE	0x2
 
+/* BSS Coex IE information field bits */
+#define WLAN_BSS_COEX_INFORMATION_REQUEST	BIT(0)
+
 /**
  * enum - mesh synchronization method identifier
  *
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index 8fb314b182e..30a4c100401 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -117,6 +117,16 @@ ieee80211_tdls_add_supp_channels(struct ieee80211_sub_if_data *sdata,
 	*pos = 2 * subband_cnt;
 }
 
+static void ieee80211_tdls_add_bss_coex_ie(struct sk_buff *skb)
+{
+	u8 *pos = (void *)skb_put(skb, 3);
+
+	*pos++ = WLAN_EID_BSS_COEX_2040;
+	*pos++ = 1; /* len */
+
+	*pos++ = WLAN_BSS_COEX_INFORMATION_REQUEST;
+}
+
 static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata,
 					u16 status_code)
 {
@@ -341,6 +351,10 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
 
 	rcu_read_unlock();
 
+	if (ht_cap.ht_supported &&
+	    (ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40))
+		ieee80211_tdls_add_bss_coex_ie(skb);
+
 	/* add any remaining IEs */
 	if (extra_ies_len) {
 		noffset = extra_ies_len;
@@ -597,6 +611,7 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 			       2 + max(sizeof(struct ieee80211_ht_cap),
 				       sizeof(struct ieee80211_ht_operation)) +
 			       50 + /* supported channels */
+			       3 + /* 40/20 BSS coex */
 			       extra_ies_len +
 			       sizeof(struct ieee80211_tdls_lnkie));
 	if (!skb)
-- 
cgit v1.2.3-70-g09d2


From 78632a17eaa7a5abdc22aac8ca5932d6cad59984 Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Sun, 9 Nov 2014 18:50:14 +0200
Subject: cfg/mac80211: define TDLS channel switch feature bit

Define some related TDLS protocol constants and advertise channel switch
support in the extended-capabilities IE when the feature bit is defined.

Actually supporting TDLS channel-switching also requires support for
some new nl80211 commands, to be introduced by future patches.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Signed-off-by: Arik Nemtsov <arik@wizery.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h    | 6 ++++++
 include/uapi/linux/nl80211.h | 3 +++
 net/mac80211/tdls.c          | 9 ++++++---
 3 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index adac1be6738..fbb02d24065 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2019,6 +2019,11 @@ enum ieee80211_tdls_actioncode {
  */
 #define WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING	BIT(2)
 
+/* TDLS capabilities in the the 4th byte of @WLAN_EID_EXT_CAPABILITY */
+#define WLAN_EXT_CAPA4_TDLS_BUFFER_STA		BIT(4)
+#define WLAN_EXT_CAPA4_TDLS_PEER_PSM		BIT(5)
+#define WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH		BIT(6)
+
 /* Interworking capabilities are set in 7th bit of 4th byte of the
  * @WLAN_EID_EXT_CAPABILITY information element
  */
@@ -2030,6 +2035,7 @@ enum ieee80211_tdls_actioncode {
  */
 #define WLAN_EXT_CAPA5_TDLS_ENABLED	BIT(5)
 #define WLAN_EXT_CAPA5_TDLS_PROHIBITED	BIT(6)
+#define WLAN_EXT_CAPA5_TDLS_CH_SW_PROHIBITED	BIT(7)
 
 #define WLAN_EXT_CAPA8_OPMODE_NOTIF	BIT(6)
 #define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED	BIT(7)
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 442369f69b4..ccdeef28d67 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -4095,6 +4095,8 @@ enum nl80211_ap_sme_features {
  * @NL80211_FEATURE_MAC_ON_CREATE: Device supports configuring
  *	the vif's MAC address upon creation.
  *	See 'macaddr' field in the vif_params (cfg80211.h).
+ * @NL80211_FEATURE_TDLS_CHANNEL_SWITCH: Driver supports channel switching when
+ *	operating as a TDLS peer.
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -4125,6 +4127,7 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_DYNAMIC_SMPS			= 1 << 25,
 	NL80211_FEATURE_SUPPORTS_WMM_ADMISSION		= 1 << 26,
 	NL80211_FEATURE_MAC_ON_CREATE			= 1 << 27,
+	NL80211_FEATURE_TDLS_CHANNEL_SWITCH		= 1 << 28,
 };
 
 /**
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index 30a4c100401..4554bdc72c9 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -35,16 +35,19 @@ void ieee80211_tdls_peer_del_work(struct work_struct *wk)
 	mutex_unlock(&local->mtx);
 }
 
-static void ieee80211_tdls_add_ext_capab(struct sk_buff *skb)
+static void ieee80211_tdls_add_ext_capab(struct ieee80211_local *local,
+					 struct sk_buff *skb)
 {
 	u8 *pos = (void *)skb_put(skb, 7);
+	bool chan_switch = local->hw.wiphy->features &
+			   NL80211_FEATURE_TDLS_CHANNEL_SWITCH;
 
 	*pos++ = WLAN_EID_EXT_CAPABILITY;
 	*pos++ = 5; /* len */
 	*pos++ = 0x0;
 	*pos++ = 0x0;
 	*pos++ = 0x0;
-	*pos++ = 0x0;
+	*pos++ = chan_switch ? WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH : 0;
 	*pos++ = WLAN_EXT_CAPA5_TDLS_ENABLED;
 }
 
@@ -289,7 +292,7 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
 		offset = noffset;
 	}
 
-	ieee80211_tdls_add_ext_capab(skb);
+	ieee80211_tdls_add_ext_capab(local, skb);
 
 	/* add the QoS element if we support it */
 	if (local->hw.queues >= IEEE80211_NUM_ACS &&
-- 
cgit v1.2.3-70-g09d2


From 1057d35ede5dbf7ed7842357564fb42c9b54ba50 Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Wed, 19 Nov 2014 12:54:26 +0200
Subject: cfg80211: introduce TDLS channel switch commands

Introduce commands to initiate and cancel TDLS channel-switching. Once
TDLS channel-switching is started, the lower level driver is responsible
for continually initiating channel-switch operations and returning to
the base (AP) channel to listen for beacons from time to time.

Upon cancellation of the channel-switch all communication between the
relevant TDLS peers will continue on the base channel.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  14 ++++++
 include/uapi/linux/nl80211.h |  19 ++++++++
 net/wireless/core.c          |   4 ++
 net/wireless/nl80211.c       | 108 +++++++++++++++++++++++++++++++++++++++++++
 net/wireless/rdev-ops.h      |  24 ++++++++++
 net/wireless/trace.h         |  42 +++++++++++++++++
 6 files changed, 211 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 220d5f5f1ac..8d04dfef32b 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2367,6 +2367,12 @@ struct cfg80211_qos_map {
  *	(invoked with the wireless_dev mutex held)
  * @leave_ocb: leave the current OCB network
  *	(invoked with the wireless_dev mutex held)
+ *
+ * @tdls_channel_switch: Start channel-switching with a TDLS peer. The driver
+ *	is responsible for continually initiating channel-switching operations
+ *	and returning to the base channel for communication with the AP.
+ * @tdls_cancel_channel_switch: Stop channel-switching with a TDLS peer. Both
+ *	peers must be on the base channel when the call completes.
  */
 struct cfg80211_ops {
 	int	(*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -2622,6 +2628,14 @@ struct cfg80211_ops {
 			     u16 admitted_time);
 	int	(*del_tx_ts)(struct wiphy *wiphy, struct net_device *dev,
 			     u8 tsid, const u8 *peer);
+
+	int	(*tdls_channel_switch)(struct wiphy *wiphy,
+				       struct net_device *dev,
+				       const u8 *addr, u8 oper_class,
+				       struct cfg80211_chan_def *chandef);
+	void	(*tdls_cancel_channel_switch)(struct wiphy *wiphy,
+					      struct net_device *dev,
+					      const u8 *addr);
 };
 
 /*
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index ccdeef28d67..365db67ca71 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -762,6 +762,18 @@
  * @NL80211_CMD_LEAVE_OCB: Leave the OCB network -- no special arguments, the
  *	network is determined by the network interface.
  *
+ * @NL80211_CMD_TDLS_CHANNEL_SWITCH: Start channel-switching with a TDLS peer,
+ *	identified by the %NL80211_ATTR_MAC parameter. A target channel is
+ *	provided via %NL80211_ATTR_WIPHY_FREQ and other attributes determining
+ *	channel width/type. The target operating class is given via
+ *	%NL80211_ATTR_OPER_CLASS.
+ *	The driver is responsible for continually initiating channel-switching
+ *	operations and returning to the base channel for communication with the
+ *	AP.
+ * @NL80211_CMD_TDLS_CANCEL_CHANNEL_SWITCH: Stop channel-switching with a TDLS
+ *	peer given by %NL80211_ATTR_MAC. Both peers must be on the base channel
+ *	when this command completes.
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -943,6 +955,9 @@ enum nl80211_commands {
 
 	NL80211_CMD_CH_SWITCH_STARTED_NOTIFY,
 
+	NL80211_CMD_TDLS_CHANNEL_SWITCH,
+	NL80211_CMD_TDLS_CANCEL_CHANNEL_SWITCH,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
@@ -1669,6 +1684,8 @@ enum nl80211_commands {
  * @NL80211_ATTR_SMPS_MODE: SMPS mode to use (ap mode). see
  *	&enum nl80211_smps_mode.
  *
+ * @NL80211_ATTR_OPER_CLASS: operating class
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -2021,6 +2038,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_SMPS_MODE,
 
+	NL80211_ATTR_OPER_CLASS,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/wireless/core.c b/net/wireless/core.c
index a4d27927aba..4c2e501203d 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -541,6 +541,10 @@ int wiphy_register(struct wiphy *wiphy)
 		    !wiphy->wowlan->tcp))
 		return -EINVAL;
 #endif
+	if (WARN_ON((wiphy->features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH) &&
+		    (!rdev->ops->tdls_channel_switch ||
+		     !rdev->ops->tdls_cancel_channel_switch)))
+		return -EINVAL;
 
 	if (WARN_ON(wiphy->coalesce &&
 		    (!wiphy->coalesce->n_rules ||
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d0a8361b339..27666f5e505 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -9658,6 +9658,98 @@ static int nl80211_del_tx_ts(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
+static int nl80211_tdls_channel_switch(struct sk_buff *skb,
+				       struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct cfg80211_chan_def chandef = {};
+	const u8 *addr;
+	u8 oper_class;
+	int err;
+
+	if (!rdev->ops->tdls_channel_switch ||
+	    !(rdev->wiphy.features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH))
+		return -EOPNOTSUPP;
+
+	switch (dev->ieee80211_ptr->iftype) {
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_P2P_CLIENT:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (!info->attrs[NL80211_ATTR_MAC] ||
+	    !info->attrs[NL80211_ATTR_OPER_CLASS])
+		return -EINVAL;
+
+	err = nl80211_parse_chandef(rdev, info, &chandef);
+	if (err)
+		return err;
+
+	/*
+	 * Don't allow wide channels on the 2.4Ghz band, as per IEEE802.11-2012
+	 * section 10.22.6.2.1. Disallow 5/10Mhz channels as well for now, the
+	 * specification is not defined for them.
+	 */
+	if (chandef.chan->band == IEEE80211_BAND_2GHZ &&
+	    chandef.width != NL80211_CHAN_WIDTH_20_NOHT &&
+	    chandef.width != NL80211_CHAN_WIDTH_20)
+		return -EINVAL;
+
+	/* we will be active on the TDLS link */
+	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &chandef, wdev->iftype))
+		return -EINVAL;
+
+	/* don't allow switching to DFS channels */
+	if (cfg80211_chandef_dfs_required(wdev->wiphy, &chandef, wdev->iftype))
+		return -EINVAL;
+
+	addr = nla_data(info->attrs[NL80211_ATTR_MAC]);
+	oper_class = nla_get_u8(info->attrs[NL80211_ATTR_OPER_CLASS]);
+
+	wdev_lock(wdev);
+	err = rdev_tdls_channel_switch(rdev, dev, addr, oper_class, &chandef);
+	wdev_unlock(wdev);
+
+	return err;
+}
+
+static int nl80211_tdls_cancel_channel_switch(struct sk_buff *skb,
+					      struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	const u8 *addr;
+
+	if (!rdev->ops->tdls_channel_switch ||
+	    !rdev->ops->tdls_cancel_channel_switch ||
+	    !(rdev->wiphy.features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH))
+		return -EOPNOTSUPP;
+
+	switch (dev->ieee80211_ptr->iftype) {
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_P2P_CLIENT:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (!info->attrs[NL80211_ATTR_MAC])
+		return -EINVAL;
+
+	addr = nla_data(info->attrs[NL80211_ATTR_MAC]);
+
+	wdev_lock(wdev);
+	rdev_tdls_cancel_channel_switch(rdev, dev, addr);
+	wdev_unlock(wdev);
+
+	return 0;
+}
+
 #define NL80211_FLAG_NEED_WIPHY		0x01
 #define NL80211_FLAG_NEED_NETDEV	0x02
 #define NL80211_FLAG_NEED_RTNL		0x04
@@ -10456,6 +10548,22 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_TDLS_CHANNEL_SWITCH,
+		.doit = nl80211_tdls_channel_switch,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL80211_CMD_TDLS_CANCEL_CHANNEL_SWITCH,
+		.doit = nl80211_tdls_cancel_channel_switch,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 };
 
 /* notification functions */
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 1b3864cd50c..35cfb7134bd 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -993,4 +993,28 @@ rdev_del_tx_ts(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static inline int
+rdev_tdls_channel_switch(struct cfg80211_registered_device *rdev,
+			 struct net_device *dev, const u8 *addr,
+			 u8 oper_class, struct cfg80211_chan_def *chandef)
+{
+	int ret;
+
+	trace_rdev_tdls_channel_switch(&rdev->wiphy, dev, addr, oper_class,
+				       chandef);
+	ret = rdev->ops->tdls_channel_switch(&rdev->wiphy, dev, addr,
+					     oper_class, chandef);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+	return ret;
+}
+
+static inline void
+rdev_tdls_cancel_channel_switch(struct cfg80211_registered_device *rdev,
+				struct net_device *dev, const u8 *addr)
+{
+	trace_rdev_tdls_cancel_channel_switch(&rdev->wiphy, dev, addr);
+	rdev->ops->tdls_cancel_channel_switch(&rdev->wiphy, dev, addr);
+	trace_rdev_return_void(&rdev->wiphy);
+}
+
 #endif /* __CFG80211_RDEV_OPS */
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 6e25370d3ce..ad38910f703 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -2032,6 +2032,48 @@ TRACE_EVENT(rdev_del_tx_ts,
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->tsid)
 );
 
+TRACE_EVENT(rdev_tdls_channel_switch,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 const u8 *addr, u8 oper_class,
+		 struct cfg80211_chan_def *chandef),
+	TP_ARGS(wiphy, netdev, addr, oper_class, chandef),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(addr)
+		__field(u8, oper_class)
+		CHAN_DEF_ENTRY
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(addr, addr);
+		CHAN_DEF_ASSIGN(chandef);
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT
+		  " oper class %d, " CHAN_DEF_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(addr),
+		  __entry->oper_class, CHAN_DEF_PR_ARG)
+);
+
+TRACE_EVENT(rdev_tdls_cancel_channel_switch,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 const u8 *addr),
+	TP_ARGS(wiphy, netdev, addr),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(addr)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(addr, addr);
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(addr))
+);
+
 /*************************************************************
  *	     cfg80211 exported functions traces		     *
  *************************************************************/
-- 
cgit v1.2.3-70-g09d2


From 53837584438f8899e061ada4663ae1d09b49b96a Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Sun, 9 Nov 2014 18:50:18 +0200
Subject: mac80211: add parsing of TDLS specific IEs

These are used in TDLS channel switching code.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Signed-off-by: Arik Nemtsov <arik@wizery.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h  | 15 +++++++++++++++
 net/mac80211/ieee80211_i.h |  2 ++
 net/mac80211/util.c        | 16 ++++++++++++++++
 3 files changed, 33 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index fbb02d24065..4f4eea8a628 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1067,6 +1067,12 @@ struct ieee80211_pspoll {
 
 /* TDLS */
 
+/* Channel switch timing */
+struct ieee80211_ch_switch_timing {
+	__le16 switch_time;
+	__le16 switch_timeout;
+} __packed;
+
 /* Link-id information element */
 struct ieee80211_tdls_lnkie {
 	u8 ie_type; /* Link Identifier IE */
@@ -1108,6 +1114,15 @@ struct ieee80211_tdls_data {
 			u8 dialog_token;
 			u8 variable[0];
 		} __packed discover_req;
+		struct {
+			u8 target_channel;
+			u8 oper_class;
+			u8 variable[0];
+		} __packed chan_switch_req;
+		struct {
+			__le16 status_code;
+			u8 variable[0];
+		} __packed chan_switch_resp;
 	} u;
 } __packed;
 
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 4b3a7e7ec2a..e786ab6bc72 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1400,6 +1400,8 @@ struct ieee802_11_elems {
 	size_t total_len;
 
 	/* pointers to IEs */
+	const struct ieee80211_tdls_lnkie *lnk_id;
+	const struct ieee80211_ch_switch_timing *ch_sw_timing;
 	const u8 *ext_capab;
 	const u8 *ssid;
 	const u8 *supp_rates;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 3ca0c2e725f..9e5bfd61485 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -832,6 +832,8 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 		case WLAN_EID_WIDE_BW_CHANNEL_SWITCH:
 		case WLAN_EID_CHAN_SWITCH_PARAM:
 		case WLAN_EID_EXT_CAPABILITY:
+		case WLAN_EID_CHAN_SWITCH_TIMING:
+		case WLAN_EID_LINK_ID:
 		/*
 		 * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible
 		 * that if the content gets bigger it might be needed more than once
@@ -851,6 +853,20 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 		elem_parse_failed = false;
 
 		switch (id) {
+		case WLAN_EID_LINK_ID:
+			if (elen + 2 != sizeof(struct ieee80211_tdls_lnkie)) {
+				elem_parse_failed = true;
+				break;
+			}
+			elems->lnk_id = (void *)(pos - 2);
+			break;
+		case WLAN_EID_CHAN_SWITCH_TIMING:
+			if (elen != sizeof(struct ieee80211_ch_switch_timing)) {
+				elem_parse_failed = true;
+				break;
+			}
+			elems->ch_sw_timing = (void *)pos;
+			break;
 		case WLAN_EID_EXT_CAPABILITY:
 			elems->ext_capab = pos;
 			elems->ext_capab_len = elen;
-- 
cgit v1.2.3-70-g09d2


From a7a6bdd0670feb8bfc26d41cda32b6064dbca50e Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Sun, 9 Nov 2014 18:50:19 +0200
Subject: mac80211: introduce TDLS channel switch ops

Implement the cfg80211 TDLS channel switch ops and introduce new mac80211
ones for low-level drivers.
Verify low-level driver support for the new ops when using the relevant
wiphy feature bit. Also verify the peer supports channel switching before
passing the command down.

Add a new STA flag to track the off-channel state with the TDLS peer and
make sure to cancel the channel-switch if the peer STA is unexpectedly
removed.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Signed-off-by: Arik Nemtsov <arik@wizery.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |  19 ++++
 net/mac80211/cfg.c         |   2 +
 net/mac80211/debugfs_sta.c |  10 +-
 net/mac80211/driver-ops.h  |  41 ++++++++
 net/mac80211/ieee80211_i.h |   6 ++
 net/mac80211/main.c        |   5 +
 net/mac80211/sta_info.c    |   9 ++
 net/mac80211/sta_info.h    |   3 +
 net/mac80211/tdls.c        | 234 +++++++++++++++++++++++++++++++++++++++++++++
 net/mac80211/trace.h       |  57 +++++++++++
 10 files changed, 381 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 83232aa2f07..fdedceb7adc 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2915,6 +2915,16 @@ enum ieee80211_reconfig_type {
  *
  * @get_txpower: get current maximum tx power (in dBm) based on configuration
  *	and hardware limits.
+ *
+ * @tdls_channel_switch: Start channel-switching with a TDLS peer. The driver
+ *	is responsible for continually initiating channel-switching operations
+ *	and returning to the base channel for communication with the AP. The
+ *	driver receives a channel-switch request template and the location of
+ *	the switch-timing IE within the template as part of the invocation.
+ *	The template is valid only within the call, and the driver can
+ *	optionally copy the skb for further re-use.
+ * @tdls_cancel_channel_switch: Stop channel-switching with a TDLS peer. Both
+ *	peers must be on the base channel when the call completes.
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw,
@@ -3126,6 +3136,15 @@ struct ieee80211_ops {
 	u32 (*get_expected_throughput)(struct ieee80211_sta *sta);
 	int (*get_txpower)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			   int *dbm);
+
+	int (*tdls_channel_switch)(struct ieee80211_hw *hw,
+				   struct ieee80211_vif *vif,
+				   struct ieee80211_sta *sta, u8 oper_class,
+				   struct cfg80211_chan_def *chandef,
+				   struct sk_buff *skb, u32 ch_sw_tm_ie);
+	void (*tdls_cancel_channel_switch)(struct ieee80211_hw *hw,
+					   struct ieee80211_vif *vif,
+					   struct ieee80211_sta *sta);
 };
 
 /**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 8195e65d8a9..e75d5c53e97 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3752,6 +3752,8 @@ const struct cfg80211_ops mac80211_config_ops = {
 	.set_rekey_data = ieee80211_set_rekey_data,
 	.tdls_oper = ieee80211_tdls_oper,
 	.tdls_mgmt = ieee80211_tdls_mgmt,
+	.tdls_channel_switch = ieee80211_tdls_channel_switch,
+	.tdls_cancel_channel_switch = ieee80211_tdls_cancel_channel_switch,
 	.probe_client = ieee80211_probe_client,
 	.set_noack_map = ieee80211_set_noack_map,
 #ifdef CONFIG_PM
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 2ba7f53746d..94c70091bbd 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -74,7 +74,7 @@ static ssize_t sta_flags_read(struct file *file, char __user *userbuf,
 	test_sta_flag(sta, WLAN_STA_##flg) ? #flg "\n" : ""
 
 	int res = scnprintf(buf, sizeof(buf),
-			    "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s",
+			    "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s",
 			    TEST(AUTH), TEST(ASSOC), TEST(PS_STA),
 			    TEST(PS_DRIVER), TEST(AUTHORIZED),
 			    TEST(SHORT_PREAMBLE),
@@ -83,10 +83,10 @@ static ssize_t sta_flags_read(struct file *file, char __user *userbuf,
 			    TEST(MFP), TEST(BLOCK_BA), TEST(PSPOLL),
 			    TEST(UAPSD), TEST(SP), TEST(TDLS_PEER),
 			    TEST(TDLS_PEER_AUTH), TEST(TDLS_INITIATOR),
-			    TEST(TDLS_CHAN_SWITCH), TEST(4ADDR_EVENT),
-			    TEST(INSERTED), TEST(RATE_CONTROL),
-			    TEST(TOFFSET_KNOWN), TEST(MPSP_OWNER),
-			    TEST(MPSP_RECIPIENT));
+			    TEST(TDLS_CHAN_SWITCH), TEST(TDLS_OFF_CHANNEL),
+			    TEST(4ADDR_EVENT), TEST(INSERTED),
+			    TEST(RATE_CONTROL), TEST(TOFFSET_KNOWN),
+			    TEST(MPSP_OWNER), TEST(MPSP_RECIPIENT));
 #undef TEST
 	return simple_read_from_buffer(userbuf, count, ppos, buf, res);
 }
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 9759dd1f073..ec4ae42ac15 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1296,4 +1296,45 @@ static inline int drv_get_txpower(struct ieee80211_local *local,
 	return ret;
 }
 
+static inline int
+drv_tdls_channel_switch(struct ieee80211_local *local,
+			struct ieee80211_sub_if_data *sdata,
+			struct ieee80211_sta *sta, u8 oper_class,
+			struct cfg80211_chan_def *chandef,
+			struct sk_buff *tmpl_skb, u32 ch_sw_tm_ie)
+{
+	int ret;
+
+	might_sleep();
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
+
+	if (!local->ops->tdls_channel_switch)
+		return -EOPNOTSUPP;
+
+	trace_drv_tdls_channel_switch(local, sdata, sta, oper_class, chandef);
+	ret = local->ops->tdls_channel_switch(&local->hw, &sdata->vif, sta,
+					      oper_class, chandef, tmpl_skb,
+					      ch_sw_tm_ie);
+	trace_drv_return_int(local, ret);
+	return ret;
+}
+
+static inline void
+drv_tdls_cancel_channel_switch(struct ieee80211_local *local,
+			       struct ieee80211_sub_if_data *sdata,
+			       struct ieee80211_sta *sta)
+{
+	might_sleep();
+	if (!check_sdata_in_driver(sdata))
+		return;
+
+	if (!local->ops->tdls_cancel_channel_switch)
+		return;
+
+	trace_drv_tdls_cancel_channel_switch(local, sdata, sta);
+	local->ops->tdls_cancel_channel_switch(&local->hw, &sdata->vif, sta);
+	trace_drv_return_void(local);
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index e786ab6bc72..2c7abc077b6 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2007,6 +2007,12 @@ int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
 int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
 			const u8 *peer, enum nl80211_tdls_operation oper);
 void ieee80211_tdls_peer_del_work(struct work_struct *wk);
+int ieee80211_tdls_channel_switch(struct wiphy *wiphy, struct net_device *dev,
+				  const u8 *addr, u8 oper_class,
+				  struct cfg80211_chan_def *chandef);
+void ieee80211_tdls_cancel_channel_switch(struct wiphy *wiphy,
+					  struct net_device *dev,
+					  const u8 *addr);
 
 extern const struct ethtool_ops ieee80211_ethtool_ops;
 
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 282a4f36eb9..774ccb2d9a7 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -764,6 +764,11 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	     local->hw.offchannel_tx_hw_queue >= local->hw.queues))
 		return -EINVAL;
 
+	if ((hw->wiphy->features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH) &&
+	    (!local->ops->tdls_channel_switch ||
+	     !local->ops->tdls_cancel_channel_switch))
+		return -EOPNOTSUPP;
+
 #ifdef CONFIG_PM
 	if (hw->wiphy->wowlan && (!local->ops->suspend || !local->ops->resume))
 		return -EINVAL;
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 97372514f28..86ca6276569 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -847,6 +847,15 @@ static int __must_check __sta_info_destroy_part1(struct sta_info *sta)
 	if (WARN_ON(ret))
 		return ret;
 
+	/*
+	 * for TDLS peers, make sure to return to the base channel before
+	 * removal.
+	 */
+	if (test_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL)) {
+		drv_tdls_cancel_channel_switch(local, sdata, &sta->sta);
+		clear_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL);
+	}
+
 	list_del_rcu(&sta->list);
 
 	drv_sta_pre_rcu_remove(local, sta->sdata, sta);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index b6702c810ad..00f56eb72c6 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -50,6 +50,8 @@
  * @WLAN_STA_TDLS_INITIATOR: We are the initiator of the TDLS link with this
  *	station.
  * @WLAN_STA_TDLS_CHAN_SWITCH: This TDLS peer supports TDLS channel-switching
+ * @WLAN_STA_TDLS_OFF_CHANNEL: The local STA is currently off-channel with this
+ *	TDLS peer
  * @WLAN_STA_UAPSD: Station requested unscheduled SP while driver was
  *	keeping station in power-save mode, reply when the driver
  *	unblocks the station.
@@ -80,6 +82,7 @@ enum ieee80211_sta_info_flags {
 	WLAN_STA_TDLS_PEER_AUTH,
 	WLAN_STA_TDLS_INITIATOR,
 	WLAN_STA_TDLS_CHAN_SWITCH,
+	WLAN_STA_TDLS_OFF_CHANNEL,
 	WLAN_STA_UAPSD,
 	WLAN_STA_SP,
 	WLAN_STA_4ADDR_EVENT,
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index fa141aecd98..358f9a4512a 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -449,6 +449,48 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata,
 	ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
 }
 
+static void
+ieee80211_tdls_add_chan_switch_req_ies(struct ieee80211_sub_if_data *sdata,
+				       struct sk_buff *skb, const u8 *peer,
+				       bool initiator, const u8 *extra_ies,
+				       size_t extra_ies_len, u8 oper_class,
+				       struct cfg80211_chan_def *chandef)
+{
+	struct ieee80211_tdls_data *tf;
+	size_t offset = 0, noffset;
+	u8 *pos;
+
+	if (WARN_ON_ONCE(!chandef))
+		return;
+
+	tf = (void *)skb->data;
+	tf->u.chan_switch_req.target_channel =
+		ieee80211_frequency_to_channel(chandef->chan->center_freq);
+	tf->u.chan_switch_req.oper_class = oper_class;
+
+	if (extra_ies_len) {
+		static const u8 before_lnkie[] = {
+			WLAN_EID_SECONDARY_CHANNEL_OFFSET,
+		};
+		noffset = ieee80211_ie_split(extra_ies, extra_ies_len,
+					     before_lnkie,
+					     ARRAY_SIZE(before_lnkie),
+					     offset);
+		pos = skb_put(skb, noffset - offset);
+		memcpy(pos, extra_ies + offset, noffset - offset);
+		offset = noffset;
+	}
+
+	ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
+
+	/* add any remaining IEs */
+	if (extra_ies_len) {
+		noffset = extra_ies_len;
+		pos = skb_put(skb, noffset - offset);
+		memcpy(pos, extra_ies + offset, noffset - offset);
+	}
+}
+
 static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata,
 				   struct sk_buff *skb, const u8 *peer,
 				   u8 action_code, u16 status_code,
@@ -481,6 +523,12 @@ static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata,
 		if (status_code == 0 || action_code == WLAN_TDLS_TEARDOWN)
 			ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
 		break;
+	case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
+		ieee80211_tdls_add_chan_switch_req_ies(sdata, skb, peer,
+						       initiator, extra_ies,
+						       extra_ies_len,
+						       oper_class, chandef);
+		break;
 	}
 
 }
@@ -547,6 +595,12 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev,
 		skb_put(skb, sizeof(tf->u.discover_req));
 		tf->u.discover_req.dialog_token = dialog_token;
 		break;
+	case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_CHANNEL_SWITCH_REQUEST;
+
+		skb_put(skb, sizeof(tf->u.chan_switch_req));
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -626,6 +680,7 @@ ieee80211_tdls_build_mgmt_packet_data(struct ieee80211_sub_if_data *sdata,
 	case WLAN_TDLS_SETUP_CONFIRM:
 	case WLAN_TDLS_TEARDOWN:
 	case WLAN_TDLS_DISCOVERY_REQUEST:
+	case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
 		ret = ieee80211_prep_tdls_encap_data(local->hw.wiphy,
 						     sdata->dev, peer,
 						     action_code, dialog_token,
@@ -699,6 +754,7 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 		initiator = false;
 		break;
 	case WLAN_TDLS_TEARDOWN:
+	case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
 		/* any value is ok */
 		break;
 	default:
@@ -1046,3 +1102,181 @@ void ieee80211_tdls_oper_request(struct ieee80211_vif *vif, const u8 *peer,
 	cfg80211_tdls_oper_request(sdata->dev, peer, oper, reason_code, gfp);
 }
 EXPORT_SYMBOL(ieee80211_tdls_oper_request);
+
+static void
+iee80211_tdls_add_ch_switch_timing(u8 *buf, u16 switch_time, u16 switch_timeout)
+{
+	struct ieee80211_ch_switch_timing *ch_sw;
+
+	*buf++ = WLAN_EID_CHAN_SWITCH_TIMING;
+	*buf++ = sizeof(struct ieee80211_ch_switch_timing);
+
+	ch_sw = (void *)buf;
+	ch_sw->switch_time = cpu_to_le16(switch_time);
+	ch_sw->switch_timeout = cpu_to_le16(switch_timeout);
+}
+
+/* find switch timing IE in SKB ready for Tx */
+static const u8 *ieee80211_tdls_find_sw_timing_ie(struct sk_buff *skb)
+{
+	struct ieee80211_tdls_data *tf;
+	const u8 *ie_start;
+
+	/*
+	 * Get the offset for the new location of the switch timing IE.
+	 * The SKB network header will now point to the "payload_type"
+	 * element of the TDLS data frame struct.
+	 */
+	tf = container_of(skb->data + skb_network_offset(skb),
+			  struct ieee80211_tdls_data, payload_type);
+	ie_start = tf->u.chan_switch_req.variable;
+	return cfg80211_find_ie(WLAN_EID_CHAN_SWITCH_TIMING, ie_start,
+				skb->len - (ie_start - skb->data));
+}
+
+static struct sk_buff *
+ieee80211_tdls_ch_sw_tmpl_get(struct sta_info *sta, u8 oper_class,
+			      struct cfg80211_chan_def *chandef,
+			      u32 *ch_sw_tm_ie_offset)
+{
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	u8 extra_ies[2 + sizeof(struct ieee80211_sec_chan_offs_ie) +
+		     2 + sizeof(struct ieee80211_ch_switch_timing)];
+	int extra_ies_len = 2 + sizeof(struct ieee80211_ch_switch_timing);
+	u8 *pos = extra_ies;
+	struct sk_buff *skb;
+
+	/*
+	 * if chandef points to a wide channel add a Secondary-Channel
+	 * Offset information element
+	 */
+	if (chandef->width == NL80211_CHAN_WIDTH_40) {
+		struct ieee80211_sec_chan_offs_ie *sec_chan_ie;
+		bool ht40plus;
+
+		*pos++ = WLAN_EID_SECONDARY_CHANNEL_OFFSET;
+		*pos++ = sizeof(*sec_chan_ie);
+		sec_chan_ie = (void *)pos;
+
+		ht40plus = cfg80211_get_chandef_type(chandef) ==
+							NL80211_CHAN_HT40PLUS;
+		sec_chan_ie->sec_chan_offs = ht40plus ?
+					     IEEE80211_HT_PARAM_CHA_SEC_ABOVE :
+					     IEEE80211_HT_PARAM_CHA_SEC_BELOW;
+		pos += sizeof(*sec_chan_ie);
+
+		extra_ies_len += 2 + sizeof(struct ieee80211_sec_chan_offs_ie);
+	}
+
+	/* just set the values to 0, this is a template */
+	iee80211_tdls_add_ch_switch_timing(pos, 0, 0);
+
+	skb = ieee80211_tdls_build_mgmt_packet_data(sdata, sta->sta.addr,
+					      WLAN_TDLS_CHANNEL_SWITCH_REQUEST,
+					      0, 0, !sta->sta.tdls_initiator,
+					      extra_ies, extra_ies_len,
+					      oper_class, chandef);
+	if (!skb)
+		return NULL;
+
+	skb = ieee80211_build_data_template(sdata, skb, 0);
+	if (IS_ERR(skb)) {
+		tdls_dbg(sdata, "Failed building TDLS channel switch frame\n");
+		return NULL;
+	}
+
+	if (ch_sw_tm_ie_offset) {
+		const u8 *tm_ie = ieee80211_tdls_find_sw_timing_ie(skb);
+
+		if (!tm_ie) {
+			tdls_dbg(sdata, "No switch timing IE in TDLS switch\n");
+			dev_kfree_skb_any(skb);
+			return NULL;
+		}
+
+		*ch_sw_tm_ie_offset = tm_ie - skb->data;
+	}
+
+	tdls_dbg(sdata,
+		 "TDLS channel switch request template for %pM ch %d width %d\n",
+		 sta->sta.addr, chandef->chan->center_freq, chandef->width);
+	return skb;
+}
+
+int
+ieee80211_tdls_channel_switch(struct wiphy *wiphy, struct net_device *dev,
+			      const u8 *addr, u8 oper_class,
+			      struct cfg80211_chan_def *chandef)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_local *local = sdata->local;
+	struct sta_info *sta;
+	struct sk_buff *skb = NULL;
+	u32 ch_sw_tm_ie;
+	int ret;
+
+	mutex_lock(&local->sta_mtx);
+	sta = sta_info_get(sdata, addr);
+	if (!sta) {
+		tdls_dbg(sdata,
+			 "Invalid TDLS peer %pM for channel switch request\n",
+			 addr);
+		ret = -ENOENT;
+		goto out;
+	}
+
+	if (!test_sta_flag(sta, WLAN_STA_TDLS_CHAN_SWITCH)) {
+		tdls_dbg(sdata, "TDLS channel switch unsupported by %pM\n",
+			 addr);
+		ret = -ENOTSUPP;
+		goto out;
+	}
+
+	skb = ieee80211_tdls_ch_sw_tmpl_get(sta, oper_class, chandef,
+					    &ch_sw_tm_ie);
+	if (!skb) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	ret = drv_tdls_channel_switch(local, sdata, &sta->sta, oper_class,
+				      chandef, skb, ch_sw_tm_ie);
+	if (!ret)
+		set_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL);
+
+out:
+	mutex_unlock(&local->sta_mtx);
+	dev_kfree_skb_any(skb);
+	return ret;
+}
+
+void
+ieee80211_tdls_cancel_channel_switch(struct wiphy *wiphy,
+				     struct net_device *dev,
+				     const u8 *addr)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_local *local = sdata->local;
+	struct sta_info *sta;
+
+	mutex_lock(&local->sta_mtx);
+	sta = sta_info_get(sdata, addr);
+	if (!sta) {
+		tdls_dbg(sdata,
+			 "Invalid TDLS peer %pM for channel switch cancel\n",
+			 addr);
+		goto out;
+	}
+
+	if (!test_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL)) {
+		tdls_dbg(sdata, "TDLS channel switch not initiated by %pM\n",
+			 addr);
+		goto out;
+	}
+
+	drv_tdls_cancel_channel_switch(local, sdata, &sta->sta);
+	clear_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL);
+
+out:
+	mutex_unlock(&local->sta_mtx);
+}
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 96847e78848..c0c0fcace9d 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -2196,6 +2196,63 @@ TRACE_EVENT(drv_get_txpower,
 	)
 );
 
+TRACE_EVENT(drv_tdls_channel_switch,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_sta *sta, u8 oper_class,
+		 struct cfg80211_chan_def *chandef),
+
+	TP_ARGS(local, sdata, sta, oper_class, chandef),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		STA_ENTRY
+		__field(u8, oper_class)
+		CHANDEF_ENTRY
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		STA_ASSIGN;
+		__entry->oper_class = oper_class;
+		CHANDEF_ASSIGN(chandef)
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT VIF_PR_FMT " tdls channel switch to"
+		CHANDEF_PR_FMT  " oper_class:%d " STA_PR_FMT,
+		LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->oper_class,
+		STA_PR_ARG
+	)
+);
+
+TRACE_EVENT(drv_tdls_cancel_channel_switch,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_sta *sta),
+
+	TP_ARGS(local, sdata, sta),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		STA_ENTRY
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		STA_ASSIGN;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT VIF_PR_FMT
+		" tdls cancel channel switch with " STA_PR_FMT,
+		LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG
+	)
+);
 
 #ifdef CONFIG_MAC80211_MESSAGE_TRACING
 #undef TRACE_SYSTEM
-- 
cgit v1.2.3-70-g09d2


From 8a4d32f30d11d6d8cc29594c7a36b9be6b0edbb5 Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Sun, 9 Nov 2014 18:50:20 +0200
Subject: mac80211: add TDLS channel-switch Rx flow

When receiving a TDLS channel switch request or response, parse the frame
and call a new tdls_recv_channel_switch op in the low level driver with
the parsed data.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Signed-off-by: Arik Nemtsov <arik@wizery.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |  37 ++++-
 net/mac80211/driver-ops.h  |  12 ++
 net/mac80211/ieee80211_i.h |   3 +
 net/mac80211/iface.c       |   2 +
 net/mac80211/main.c        |   3 +-
 net/mac80211/rx.c          |  21 +++
 net/mac80211/tdls.c        | 328 +++++++++++++++++++++++++++++++++++++++++++++
 net/mac80211/trace.h       |  45 +++++++
 8 files changed, 449 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index fdedceb7adc..56b7e211472 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1826,6 +1826,31 @@ struct ieee80211_scan_request {
 	struct cfg80211_scan_request req;
 };
 
+/**
+ * struct ieee80211_tdls_ch_sw_params - TDLS channel switch parameters
+ *
+ * @sta: peer this TDLS channel-switch request/response came from
+ * @chandef: channel referenced in a TDLS channel-switch request
+ * @action_code: see &enum ieee80211_tdls_actioncode
+ * @status: channel-switch response status
+ * @timestamp: time at which the frame was received
+ * @switch_time: switch-timing parameter received in the frame
+ * @switch_timeout: switch-timing parameter received in the frame
+ * @tmpl_skb: TDLS switch-channel response template
+ * @ch_sw_tm_ie: offset of the channel-switch timing IE inside @tmpl_skb
+ */
+struct ieee80211_tdls_ch_sw_params {
+	struct ieee80211_sta *sta;
+	struct cfg80211_chan_def *chandef;
+	u8 action_code;
+	u32 status;
+	u32 timestamp;
+	u16 switch_time;
+	u16 switch_timeout;
+	struct sk_buff *tmpl_skb;
+	u32 ch_sw_tm_ie;
+};
+
 /**
  * wiphy_to_ieee80211_hw - return a mac80211 driver hw struct from a wiphy
  *
@@ -2925,6 +2950,13 @@ enum ieee80211_reconfig_type {
  *	optionally copy the skb for further re-use.
  * @tdls_cancel_channel_switch: Stop channel-switching with a TDLS peer. Both
  *	peers must be on the base channel when the call completes.
+ * @tdls_recv_channel_switch: a TDLS channel-switch related frame (request or
+ *	response) has been received from a remote peer. The driver gets
+ *	parameters parsed from the incoming frame and may use them to continue
+ *	an ongoing channel-switch operation. In addition, a channel-switch
+ *	response template is provided, together with the location of the
+ *	switch-timing IE within the template. The skb can only be used within
+ *	the function call.
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw,
@@ -3141,10 +3173,13 @@ struct ieee80211_ops {
 				   struct ieee80211_vif *vif,
 				   struct ieee80211_sta *sta, u8 oper_class,
 				   struct cfg80211_chan_def *chandef,
-				   struct sk_buff *skb, u32 ch_sw_tm_ie);
+				   struct sk_buff *tmpl_skb, u32 ch_sw_tm_ie);
 	void (*tdls_cancel_channel_switch)(struct ieee80211_hw *hw,
 					   struct ieee80211_vif *vif,
 					   struct ieee80211_sta *sta);
+	void (*tdls_recv_channel_switch)(struct ieee80211_hw *hw,
+					 struct ieee80211_vif *vif,
+					 struct ieee80211_tdls_ch_sw_params *params);
 };
 
 /**
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index ec4ae42ac15..ba0d2cb5df1 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1337,4 +1337,16 @@ drv_tdls_cancel_channel_switch(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
+static inline void
+drv_tdls_recv_channel_switch(struct ieee80211_local *local,
+			     struct ieee80211_sub_if_data *sdata,
+			     struct ieee80211_tdls_ch_sw_params *params)
+{
+	trace_drv_tdls_recv_channel_switch(local, sdata, params);
+	if (local->ops->tdls_recv_channel_switch)
+		local->ops->tdls_recv_channel_switch(&local->hw, &sdata->vif,
+						     params);
+	trace_drv_return_void(local);
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 2c7abc077b6..5de2e5f3a57 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -993,6 +993,7 @@ enum sdata_queue_type {
 	IEEE80211_SDATA_QUEUE_AGG_STOP		= 2,
 	IEEE80211_SDATA_QUEUE_RX_AGG_START	= 3,
 	IEEE80211_SDATA_QUEUE_RX_AGG_STOP	= 4,
+	IEEE80211_SDATA_QUEUE_TDLS_CHSW		= 5,
 };
 
 enum {
@@ -2013,6 +2014,8 @@ int ieee80211_tdls_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 void ieee80211_tdls_cancel_channel_switch(struct wiphy *wiphy,
 					  struct net_device *dev,
 					  const u8 *addr);
+void ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata,
+					   struct sk_buff *skb);
 
 extern const struct ethtool_ops ieee80211_ethtool_ops;
 
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 6b631c049eb..82473d909bb 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1202,6 +1202,8 @@ static void ieee80211_iface_work(struct work_struct *work)
 							WLAN_BACK_RECIPIENT, 0,
 							false);
 			mutex_unlock(&local->sta_mtx);
+		} else if (skb->pkt_type == IEEE80211_SDATA_QUEUE_TDLS_CHSW) {
+			ieee80211_process_tdls_channel_switch(sdata, skb);
 		} else if (ieee80211_is_action(mgmt->frame_control) &&
 			   mgmt->u.action.category == WLAN_CATEGORY_BACK) {
 			int len = skb->len;
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 774ccb2d9a7..6ab99da38db 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -766,7 +766,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 
 	if ((hw->wiphy->features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH) &&
 	    (!local->ops->tdls_channel_switch ||
-	     !local->ops->tdls_cancel_channel_switch))
+	     !local->ops->tdls_cancel_channel_switch ||
+	     !local->ops->tdls_recv_channel_switch))
 		return -EOPNOTSUPP;
 
 #ifdef CONFIG_PM
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 0f4297e2aae..d9bbb73d443 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2333,6 +2333,27 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx)
 	if (!ieee80211_frame_allowed(rx, fc))
 		return RX_DROP_MONITOR;
 
+	/* directly handle TDLS channel switch requests/responses */
+	if (unlikely(((struct ethhdr *)rx->skb->data)->h_proto ==
+						cpu_to_be16(ETH_P_TDLS))) {
+		struct ieee80211_tdls_data *tf = (void *)rx->skb->data;
+
+		if (pskb_may_pull(rx->skb,
+				  offsetof(struct ieee80211_tdls_data, u)) &&
+		    tf->payload_type == WLAN_TDLS_SNAP_RFTYPE &&
+		    tf->category == WLAN_CATEGORY_TDLS &&
+		    (tf->action_code == WLAN_TDLS_CHANNEL_SWITCH_REQUEST ||
+		     tf->action_code == WLAN_TDLS_CHANNEL_SWITCH_RESPONSE)) {
+			rx->skb->pkt_type = IEEE80211_SDATA_QUEUE_TDLS_CHSW;
+			skb_queue_tail(&sdata->skb_queue, rx->skb);
+			ieee80211_queue_work(&rx->local->hw, &sdata->work);
+			if (rx->sta)
+				rx->sta->rx_packets++;
+
+			return RX_QUEUED;
+		}
+	}
+
 	if (rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
 	    unlikely(port_control) && sdata->bss) {
 		sdata = container_of(sdata->bss, struct ieee80211_sub_if_data,
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index 358f9a4512a..55ddd77b865 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -491,6 +491,20 @@ ieee80211_tdls_add_chan_switch_req_ies(struct ieee80211_sub_if_data *sdata,
 	}
 }
 
+static void
+ieee80211_tdls_add_chan_switch_resp_ies(struct ieee80211_sub_if_data *sdata,
+					struct sk_buff *skb, const u8 *peer,
+					u16 status_code, bool initiator,
+					const u8 *extra_ies,
+					size_t extra_ies_len)
+{
+	if (status_code == 0)
+		ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
+
+	if (extra_ies_len)
+		memcpy(skb_put(skb, extra_ies_len), extra_ies, extra_ies_len);
+}
+
 static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata,
 				   struct sk_buff *skb, const u8 *peer,
 				   u8 action_code, u16 status_code,
@@ -529,6 +543,12 @@ static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata,
 						       extra_ies_len,
 						       oper_class, chandef);
 		break;
+	case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE:
+		ieee80211_tdls_add_chan_switch_resp_ies(sdata, skb, peer,
+							status_code,
+							initiator, extra_ies,
+							extra_ies_len);
+		break;
 	}
 
 }
@@ -601,6 +621,13 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev,
 
 		skb_put(skb, sizeof(tf->u.chan_switch_req));
 		break;
+	case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_CHANNEL_SWITCH_RESPONSE;
+
+		skb_put(skb, sizeof(tf->u.chan_switch_resp));
+		tf->u.chan_switch_resp.status_code = cpu_to_le16(status_code);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -681,6 +708,7 @@ ieee80211_tdls_build_mgmt_packet_data(struct ieee80211_sub_if_data *sdata,
 	case WLAN_TDLS_TEARDOWN:
 	case WLAN_TDLS_DISCOVERY_REQUEST:
 	case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
+	case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE:
 		ret = ieee80211_prep_tdls_encap_data(local->hw.wiphy,
 						     sdata->dev, peer,
 						     action_code, dialog_token,
@@ -755,6 +783,7 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 		break;
 	case WLAN_TDLS_TEARDOWN:
 	case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
+	case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE:
 		/* any value is ok */
 		break;
 	default:
@@ -1280,3 +1309,302 @@ ieee80211_tdls_cancel_channel_switch(struct wiphy *wiphy,
 out:
 	mutex_unlock(&local->sta_mtx);
 }
+
+static struct sk_buff *
+ieee80211_tdls_ch_sw_resp_tmpl_get(struct sta_info *sta,
+				   u32 *ch_sw_tm_ie_offset)
+{
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	struct sk_buff *skb;
+	u8 extra_ies[2 + sizeof(struct ieee80211_ch_switch_timing)];
+
+	/* initial timing are always zero in the template */
+	iee80211_tdls_add_ch_switch_timing(extra_ies, 0, 0);
+
+	skb = ieee80211_tdls_build_mgmt_packet_data(sdata, sta->sta.addr,
+					WLAN_TDLS_CHANNEL_SWITCH_RESPONSE,
+					0, 0, !sta->sta.tdls_initiator,
+					extra_ies, sizeof(extra_ies), 0, NULL);
+	if (!skb)
+		return NULL;
+
+	skb = ieee80211_build_data_template(sdata, skb, 0);
+	if (IS_ERR(skb)) {
+		tdls_dbg(sdata,
+			 "Failed building TDLS channel switch resp frame\n");
+		return NULL;
+	}
+
+	if (ch_sw_tm_ie_offset) {
+		const u8 *tm_ie = ieee80211_tdls_find_sw_timing_ie(skb);
+
+		if (!tm_ie) {
+			tdls_dbg(sdata,
+				 "No switch timing IE in TDLS switch resp\n");
+			dev_kfree_skb_any(skb);
+			return NULL;
+		}
+
+		*ch_sw_tm_ie_offset = tm_ie - skb->data;
+	}
+
+	tdls_dbg(sdata, "TDLS get channel switch response template for %pM\n",
+		 sta->sta.addr);
+	return skb;
+}
+
+static int
+ieee80211_process_tdls_channel_switch_resp(struct ieee80211_sub_if_data *sdata,
+					   struct sk_buff *skb)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee802_11_elems elems;
+	struct sta_info *sta;
+	struct ieee80211_tdls_data *tf = (void *)skb->data;
+	bool local_initiator;
+	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
+	int baselen = offsetof(typeof(*tf), u.chan_switch_resp.variable);
+	struct ieee80211_tdls_ch_sw_params params = {};
+	int ret;
+
+	params.action_code = WLAN_TDLS_CHANNEL_SWITCH_RESPONSE;
+	params.timestamp = rx_status->device_timestamp;
+
+	if (skb->len < baselen) {
+		tdls_dbg(sdata, "TDLS channel switch resp too short: %d\n",
+			 skb->len);
+		return -EINVAL;
+	}
+
+	mutex_lock(&local->sta_mtx);
+	sta = sta_info_get(sdata, tf->sa);
+	if (!sta || !test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) {
+		tdls_dbg(sdata, "TDLS chan switch from non-peer sta %pM\n",
+			 tf->sa);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	params.sta = &sta->sta;
+	params.status = le16_to_cpu(tf->u.chan_switch_resp.status_code);
+	if (params.status != 0) {
+		ret = 0;
+		goto call_drv;
+	}
+
+	ieee802_11_parse_elems(tf->u.chan_switch_resp.variable,
+			       skb->len - baselen, false, &elems);
+	if (elems.parse_error) {
+		tdls_dbg(sdata, "Invalid IEs in TDLS channel switch resp\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (!elems.ch_sw_timing || !elems.lnk_id) {
+		tdls_dbg(sdata, "TDLS channel switch resp - missing IEs\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* validate the initiator is set correctly */
+	local_initiator =
+		!memcmp(elems.lnk_id->init_sta, sdata->vif.addr, ETH_ALEN);
+	if (local_initiator == sta->sta.tdls_initiator) {
+		tdls_dbg(sdata, "TDLS chan switch invalid lnk-id initiator\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	params.switch_time = le16_to_cpu(elems.ch_sw_timing->switch_time);
+	params.switch_timeout = le16_to_cpu(elems.ch_sw_timing->switch_timeout);
+
+	params.tmpl_skb =
+		ieee80211_tdls_ch_sw_resp_tmpl_get(sta, &params.ch_sw_tm_ie);
+	if (!params.tmpl_skb) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+call_drv:
+	drv_tdls_recv_channel_switch(sdata->local, sdata, &params);
+
+	tdls_dbg(sdata,
+		 "TDLS channel switch response received from %pM status %d\n",
+		 tf->sa, params.status);
+
+out:
+	mutex_unlock(&local->sta_mtx);
+	dev_kfree_skb_any(params.tmpl_skb);
+	return ret;
+}
+
+static int
+ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata,
+					  struct sk_buff *skb)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee802_11_elems elems;
+	struct cfg80211_chan_def chandef;
+	struct ieee80211_channel *chan;
+	enum nl80211_channel_type chan_type;
+	int freq;
+	u8 target_channel, oper_class;
+	bool local_initiator;
+	struct sta_info *sta;
+	enum ieee80211_band band;
+	struct ieee80211_tdls_data *tf = (void *)skb->data;
+	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
+	int baselen = offsetof(typeof(*tf), u.chan_switch_req.variable);
+	struct ieee80211_tdls_ch_sw_params params = {};
+	int ret = 0;
+
+	params.action_code = WLAN_TDLS_CHANNEL_SWITCH_REQUEST;
+	params.timestamp = rx_status->device_timestamp;
+
+	if (skb->len < baselen) {
+		tdls_dbg(sdata, "TDLS channel switch req too short: %d\n",
+			 skb->len);
+		return -EINVAL;
+	}
+
+	target_channel = tf->u.chan_switch_req.target_channel;
+	oper_class = tf->u.chan_switch_req.oper_class;
+
+	/*
+	 * We can't easily infer the channel band. The operating class is
+	 * ambiguous - there are multiple tables (US/Europe/JP/Global). The
+	 * solution here is to treat channels with number >14 as 5GHz ones,
+	 * and specifically check for the (oper_class, channel) combinations
+	 * where this doesn't hold. These are thankfully unique according to
+	 * IEEE802.11-2012.
+	 * We consider only the 2GHz and 5GHz bands and 20MHz+ channels as
+	 * valid here.
+	 */
+	if ((oper_class == 112 || oper_class == 2 || oper_class == 3 ||
+	     oper_class == 4 || oper_class == 5 || oper_class == 6) &&
+	     target_channel < 14)
+		band = IEEE80211_BAND_5GHZ;
+	else
+		band = target_channel < 14 ? IEEE80211_BAND_2GHZ :
+					     IEEE80211_BAND_5GHZ;
+
+	freq = ieee80211_channel_to_frequency(target_channel, band);
+	if (freq == 0) {
+		tdls_dbg(sdata, "Invalid channel in TDLS chan switch: %d\n",
+			 target_channel);
+		return -EINVAL;
+	}
+
+	chan = ieee80211_get_channel(sdata->local->hw.wiphy, freq);
+	if (!chan) {
+		tdls_dbg(sdata,
+			 "Unsupported channel for TDLS chan switch: %d\n",
+			 target_channel);
+		return -EINVAL;
+	}
+
+	ieee802_11_parse_elems(tf->u.chan_switch_req.variable,
+			       skb->len - baselen, false, &elems);
+	if (elems.parse_error) {
+		tdls_dbg(sdata, "Invalid IEs in TDLS channel switch req\n");
+		return -EINVAL;
+	}
+
+	if (!elems.ch_sw_timing || !elems.lnk_id) {
+		tdls_dbg(sdata, "TDLS channel switch req - missing IEs\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(&local->sta_mtx);
+	sta = sta_info_get(sdata, tf->sa);
+	if (!sta || !test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) {
+		tdls_dbg(sdata, "TDLS chan switch from non-peer sta %pM\n",
+			 tf->sa);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	params.sta = &sta->sta;
+
+	/* validate the initiator is set correctly */
+	local_initiator =
+		!memcmp(elems.lnk_id->init_sta, sdata->vif.addr, ETH_ALEN);
+	if (local_initiator == sta->sta.tdls_initiator) {
+		tdls_dbg(sdata, "TDLS chan switch invalid lnk-id initiator\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (!sta->sta.ht_cap.ht_supported) {
+		chan_type = NL80211_CHAN_NO_HT;
+	} else if (!elems.sec_chan_offs) {
+		chan_type = NL80211_CHAN_HT20;
+	} else {
+		switch (elems.sec_chan_offs->sec_chan_offs) {
+		case IEEE80211_HT_PARAM_CHA_SEC_ABOVE:
+			chan_type = NL80211_CHAN_HT40PLUS;
+			break;
+		case IEEE80211_HT_PARAM_CHA_SEC_BELOW:
+			chan_type = NL80211_CHAN_HT40MINUS;
+			break;
+		default:
+			chan_type = NL80211_CHAN_HT20;
+			break;
+		}
+	}
+
+	cfg80211_chandef_create(&chandef, chan, chan_type);
+	params.chandef = &chandef;
+
+	params.switch_time = le16_to_cpu(elems.ch_sw_timing->switch_time);
+	params.switch_timeout = le16_to_cpu(elems.ch_sw_timing->switch_timeout);
+
+	params.tmpl_skb =
+		ieee80211_tdls_ch_sw_resp_tmpl_get(sta,
+						   &params.ch_sw_tm_ie);
+	if (!params.tmpl_skb) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	drv_tdls_recv_channel_switch(sdata->local, sdata, &params);
+
+	tdls_dbg(sdata,
+		 "TDLS ch switch request received from %pM ch %d width %d\n",
+		 tf->sa, params.chandef->chan->center_freq,
+		 params.chandef->width);
+out:
+	mutex_unlock(&local->sta_mtx);
+	dev_kfree_skb_any(params.tmpl_skb);
+	return ret;
+}
+
+void ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata,
+					   struct sk_buff *skb)
+{
+	struct ieee80211_tdls_data *tf = (void *)skb->data;
+	struct wiphy *wiphy = sdata->local->hw.wiphy;
+
+	/* make sure the driver supports it */
+	if (!(wiphy->features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH))
+		return;
+
+	/* we want to access the entire packet */
+	if (skb_linearize(skb))
+		return;
+	/*
+	 * The packet/size was already validated by mac80211 Rx path, only look
+	 * at the action type.
+	 */
+	switch (tf->action_code) {
+	case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
+		ieee80211_process_tdls_channel_switch_req(sdata, skb);
+		break;
+	case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE:
+		ieee80211_process_tdls_channel_switch_resp(sdata, skb);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return;
+	}
+}
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index c0c0fcace9d..7f76e2f2574 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -16,6 +16,7 @@
 
 #define STA_ENTRY	__array(char, sta_addr, ETH_ALEN)
 #define STA_ASSIGN	(sta ? memcpy(__entry->sta_addr, sta->addr, ETH_ALEN) : memset(__entry->sta_addr, 0, ETH_ALEN))
+#define STA_NAMED_ASSIGN(s)	memcpy(__entry->sta_addr, (s)->addr, ETH_ALEN)
 #define STA_PR_FMT	" sta:%pM"
 #define STA_PR_ARG	__entry->sta_addr
 
@@ -2254,6 +2255,50 @@ TRACE_EVENT(drv_tdls_cancel_channel_switch,
 	)
 );
 
+TRACE_EVENT(drv_tdls_recv_channel_switch,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_tdls_ch_sw_params *params),
+
+	TP_ARGS(local, sdata, params),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		__field(u8, action_code)
+		STA_ENTRY
+		CHANDEF_ENTRY
+		__field(u32, status)
+		__field(bool, peer_initiator)
+		__field(u32, timestamp)
+		__field(u16, switch_time)
+		__field(u16, switch_timeout)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		STA_NAMED_ASSIGN(params->sta);
+		CHANDEF_ASSIGN(params->chandef)
+		__entry->peer_initiator = params->sta->tdls_initiator;
+		__entry->action_code = params->action_code;
+		__entry->status = params->status;
+		__entry->timestamp = params->timestamp;
+		__entry->switch_time = params->switch_time;
+		__entry->switch_timeout = params->switch_timeout;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT VIF_PR_FMT " received tdls channel switch packet"
+		" action:%d status:%d time:%d switch time:%d switch"
+		" timeout:%d initiator: %d chan:" CHANDEF_PR_FMT STA_PR_FMT,
+		LOCAL_PR_ARG, VIF_PR_ARG, __entry->action_code, __entry->status,
+		__entry->timestamp, __entry->switch_time,
+		__entry->switch_timeout, __entry->peer_initiator,
+		CHANDEF_PR_ARG, STA_PR_ARG
+	)
+);
+
 #ifdef CONFIG_MAC80211_MESSAGE_TRACING
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM mac80211_msg
-- 
cgit v1.2.3-70-g09d2


From b6da911b3cf1d342f2f7123c9eb6463d299bca4e Mon Sep 17 00:00:00 2001
From: Liad Kaufman <liad.kaufman@intel.com>
Date: Wed, 19 Nov 2014 13:47:38 +0200
Subject: mac80211: synchronously reserve TID per station

In TDLS (e.g., TDLS off-channel) there is a requirement for
some drivers to supply an unused TID between the AP and the
device to the FW, to allow sending PTI requests and to allow
the FW to aggregate on a specific TID for better throughput.

To ensure that the allocated TID is indeed unused, this patch
introduces an API for blocking the driver from TXing on that
TID.

Signed-off-by: Liad Kaufman <liad.kaufman@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     | 37 +++++++++++++++++++
 net/mac80211/agg-tx.c      |  7 ++++
 net/mac80211/ieee80211_i.h |  1 +
 net/mac80211/sta_info.c    |  3 ++
 net/mac80211/sta_info.h    |  6 +++
 net/mac80211/tx.c          | 91 ++++++++++++++++++++++++++++++++++++++++++++++
 net/mac80211/wme.c         | 39 ++++++++++++++++++++
 7 files changed, 184 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 56b7e211472..59166a115af 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -5070,6 +5070,43 @@ void ieee80211_tdls_oper_request(struct ieee80211_vif *vif, const u8 *peer,
 				 enum nl80211_tdls_operation oper,
 				 u16 reason_code, gfp_t gfp);
 
+/**
+ * ieee80211_reserve_tid - request to reserve a specific TID
+ *
+ * There is sometimes a need (such as in TDLS) for blocking the driver from
+ * using a specific TID so that the FW can use it for certain operations such
+ * as sending PTI requests. To make sure that the driver doesn't use that TID,
+ * this function must be called as it flushes out packets on this TID and marks
+ * it as blocked, so that any transmit for the station on this TID will be
+ * redirected to the alternative TID in the same AC.
+ *
+ * Note that this function blocks and may call back into the driver, so it
+ * should be called without driver locks held. Also note this function should
+ * only be called from the driver's @sta_state callback.
+ *
+ * @sta: the station to reserve the TID for
+ * @tid: the TID to reserve
+ *
+ * Returns: 0 on success, else on failure
+ */
+int ieee80211_reserve_tid(struct ieee80211_sta *sta, u8 tid);
+
+/**
+ * ieee80211_unreserve_tid - request to unreserve a specific TID
+ *
+ * Once there is no longer any need for reserving a certain TID, this function
+ * should be called, and no longer will packets have their TID modified for
+ * preventing use of this TID in the driver.
+ *
+ * Note that this function blocks and acquires a lock, so it should be called
+ * without driver locks held. Also note this function should only be called
+ * from the driver's @sta_state callback.
+ *
+ * @sta: the station
+ * @tid: the TID to unreserve
+ */
+void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid);
+
 /**
  * ieee80211_ie_split - split an IE buffer according to ordering
  *
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 9242c60048c..a360c15cc97 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -509,6 +509,10 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid,
 	struct tid_ampdu_tx *tid_tx;
 	int ret = 0;
 
+	if (WARN(sta->reserved_tid == tid,
+		 "Requested to start BA session on reserved tid=%d", tid))
+		return -EINVAL;
+
 	trace_api_start_tx_ba_session(pubsta, tid);
 
 	if (WARN_ON_ONCE(!local->ops->ampdu_action))
@@ -765,6 +769,9 @@ int ieee80211_stop_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid)
 		goto unlock;
 	}
 
+	WARN(sta->reserved_tid == tid,
+	     "Requested to stop BA session on reserved tid=%d", tid);
+
 	if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) {
 		/* already in progress stopping it */
 		ret = 0;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index a30d40839d4..34168c21bf0 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1011,6 +1011,7 @@ enum queue_stop_reason {
 	IEEE80211_QUEUE_STOP_REASON_OFFCHANNEL,
 	IEEE80211_QUEUE_STOP_REASON_FLUSH,
 	IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN,
+	IEEE80211_QUEUE_STOP_REASON_RESERVE_TID,
 
 	IEEE80211_QUEUE_STOP_REASONS,
 };
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 86ca6276569..a42f5b2b024 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -351,6 +351,9 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 
 	sta->sta_state = IEEE80211_STA_NONE;
 
+	/* Mark TID as unreserved */
+	sta->reserved_tid = IEEE80211_TID_UNRESERVED;
+
 	ktime_get_ts(&uptime);
 	sta->last_connected = uptime.tv_sec;
 	ewma_init(&sta->avg_signal, 1024, 8);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 00f56eb72c6..4f052bb2a5a 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -254,6 +254,9 @@ struct ieee80211_tx_latency_stat {
 	u32 bin_count;
 };
 
+/* Value to indicate no TID reservation */
+#define IEEE80211_TID_UNRESERVED	0xff
+
 /**
  * struct sta_info - STA information
  *
@@ -342,6 +345,7 @@ struct ieee80211_tx_latency_stat {
  *	AP only.
  * @cipher_scheme: optional cipher scheme for this station
  * @last_tdls_pkt_time: holds the time in jiffies of last TDLS pkt ACKed
+ * @reserved_tid: reserved TID (if any, otherwise IEEE80211_TID_UNRESERVED)
  */
 struct sta_info {
 	/* General information, mostly static */
@@ -459,6 +463,8 @@ struct sta_info {
 	/* TDLS timeout data */
 	unsigned long last_tdls_pkt_time;
 
+	u8 reserved_tid;
+
 	/* keep last! */
 	struct ieee80211_sta sta;
 };
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 2dd89670e1c..0cb41d1a1f2 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3107,6 +3107,97 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL(ieee80211_get_buffered_bc);
 
+int ieee80211_reserve_tid(struct ieee80211_sta *pubsta, u8 tid)
+{
+	struct sta_info *sta = container_of(pubsta, struct sta_info, sta);
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	struct ieee80211_local *local = sdata->local;
+	int ret;
+	u32 queues;
+
+	lockdep_assert_held(&local->sta_mtx);
+
+	/* only some cases are supported right now */
+	switch (sdata->vif.type) {
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_AP_VLAN:
+		break;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	if (WARN_ON(tid >= IEEE80211_NUM_UPS))
+		return -EINVAL;
+
+	if (sta->reserved_tid == tid) {
+		ret = 0;
+		goto out;
+	}
+
+	if (sta->reserved_tid != IEEE80211_TID_UNRESERVED) {
+		sdata_err(sdata, "TID reservation already active\n");
+		ret = -EALREADY;
+		goto out;
+	}
+
+	ieee80211_stop_vif_queues(sdata->local, sdata,
+				  IEEE80211_QUEUE_STOP_REASON_RESERVE_TID);
+
+	synchronize_net();
+
+	/* Tear down BA sessions so we stop aggregating on this TID */
+	if (local->hw.flags & IEEE80211_HW_AMPDU_AGGREGATION) {
+		set_sta_flag(sta, WLAN_STA_BLOCK_BA);
+		__ieee80211_stop_tx_ba_session(sta, tid,
+					       AGG_STOP_LOCAL_REQUEST);
+	}
+
+	queues = BIT(sdata->vif.hw_queue[ieee802_1d_to_ac[tid]]);
+	__ieee80211_flush_queues(local, sdata, queues);
+
+	sta->reserved_tid = tid;
+
+	ieee80211_wake_vif_queues(local, sdata,
+				  IEEE80211_QUEUE_STOP_REASON_RESERVE_TID);
+
+	if (local->hw.flags & IEEE80211_HW_AMPDU_AGGREGATION)
+		clear_sta_flag(sta, WLAN_STA_BLOCK_BA);
+
+	ret = 0;
+ out:
+	return ret;
+}
+EXPORT_SYMBOL(ieee80211_reserve_tid);
+
+void ieee80211_unreserve_tid(struct ieee80211_sta *pubsta, u8 tid)
+{
+	struct sta_info *sta = container_of(pubsta, struct sta_info, sta);
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+
+	lockdep_assert_held(&sdata->local->sta_mtx);
+
+	/* only some cases are supported right now */
+	switch (sdata->vif.type) {
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_AP_VLAN:
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	if (tid != sta->reserved_tid) {
+		sdata_err(sdata, "TID to unreserve (%d) isn't reserved\n", tid);
+		return;
+	}
+
+	sta->reserved_tid = IEEE80211_TID_UNRESERVED;
+}
+EXPORT_SYMBOL(ieee80211_unreserve_tid);
+
 void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata,
 				 struct sk_buff *skb, int tid,
 				 enum ieee80211_band band)
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index fdf52db95b3..9eb0aee9105 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -53,6 +53,36 @@ static int wme_downgrade_ac(struct sk_buff *skb)
 	}
 }
 
+/**
+ * ieee80211_fix_reserved_tid - return the TID to use if this one is reserved
+ * @tid: the assumed-reserved TID
+ *
+ * Returns: the alternative TID to use, or 0 on error
+ */
+static inline u8 ieee80211_fix_reserved_tid(u8 tid)
+{
+	switch (tid) {
+	case 0:
+		return 3;
+	case 1:
+		return 2;
+	case 2:
+		return 1;
+	case 3:
+		return 0;
+	case 4:
+		return 5;
+	case 5:
+		return 4;
+	case 6:
+		return 7;
+	case 7:
+		return 6;
+	}
+
+	return 0;
+}
+
 static u16 ieee80211_downgrade_queue(struct ieee80211_sub_if_data *sdata,
 				     struct sta_info *sta, struct sk_buff *skb)
 {
@@ -77,6 +107,10 @@ static u16 ieee80211_downgrade_queue(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
+	/* Check to see if this is a reserved TID */
+	if (sta && sta->reserved_tid == skb->priority)
+		skb->priority = ieee80211_fix_reserved_tid(skb->priority);
+
 	/* look up which queue to use for frames with this 1d tag */
 	return ieee802_1d_to_ac[skb->priority];
 }
@@ -143,6 +177,11 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 		break;
 #endif
 	case NL80211_IFTYPE_STATION:
+		/* might be a TDLS station */
+		sta = sta_info_get(sdata, skb->data);
+		if (sta)
+			qos = sta->sta.wme;
+
 		ra = sdata->u.mgd.bssid;
 		break;
 	case NL80211_IFTYPE_ADHOC:
-- 
cgit v1.2.3-70-g09d2


From 8cd4d4563ef0a518002c4a8f47dd950afe386ea8 Mon Sep 17 00:00:00 2001
From: Luciano Coelho <luciano.coelho@intel.com>
Date: Wed, 17 Sep 2014 11:55:28 +0300
Subject: cfg80211: add wowlan net-detect support

Add a new WoWLAN API to enable net-detect as a wake up trigger.
Net-detect allows the device to scan in the background while the
host is asleep to wake up the host system when a matching network
is found.

Reuse the scheduled scan attributes to specify how the scan is
performed while suspended and the matches that will trigger a
wake event.

Signed-off-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  41 ++++++++++++++++
 include/uapi/linux/nl80211.h |  23 +++++++++
 net/wireless/core.h          |   1 +
 net/wireless/nl80211.c       | 111 ++++++++++++++++++++++++++++++++++++++++++-
 4 files changed, 175 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 8d04dfef32b..05aae22e92a 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1940,6 +1940,7 @@ struct cfg80211_wowlan_tcp {
  * @rfkill_release: wake up when rfkill is released
  * @tcp: TCP connection establishment/wakeup parameters, see nl80211.h.
  *	NULL if not configured.
+ * @nd_config: configuration for the scan to be used for net detect wake.
  */
 struct cfg80211_wowlan {
 	bool any, disconnect, magic_pkt, gtk_rekey_failure,
@@ -1948,6 +1949,7 @@ struct cfg80211_wowlan {
 	struct cfg80211_pkt_pattern *patterns;
 	struct cfg80211_wowlan_tcp *tcp;
 	int n_patterns;
+	struct cfg80211_sched_scan_request *nd_config;
 };
 
 /**
@@ -1979,6 +1981,35 @@ struct cfg80211_coalesce {
 	int n_rules;
 };
 
+/**
+ * struct cfg80211_wowlan_nd_match - information about the match
+ *
+ * @ssid: SSID of the match that triggered the wake up
+ * @n_channels: Number of channels where the match occurred.  This
+ *	value may be zero if the driver can't report the channels.
+ * @channels: center frequencies of the channels where a match
+ *	occurred (in MHz)
+ */
+struct cfg80211_wowlan_nd_match {
+	struct cfg80211_ssid ssid;
+	int n_channels;
+	u32 channels[];
+};
+
+/**
+ * struct cfg80211_wowlan_nd_info - net detect wake up information
+ *
+ * @n_matches: Number of match information instances provided in
+ *	@matches.  This value may be zero if the driver can't provide
+ *	match information.
+ * @matches: Array of pointers to matches containing information about
+ *	the matches that triggered the wake up.
+ */
+struct cfg80211_wowlan_nd_info {
+	int n_matches;
+	struct cfg80211_wowlan_nd_match *matches[];
+};
+
 /**
  * struct cfg80211_wowlan_wakeup - wakeup report
  * @disconnect: woke up by getting disconnected
@@ -1998,6 +2029,7 @@ struct cfg80211_coalesce {
  * @tcp_match: TCP wakeup packet received
  * @tcp_connlost: TCP connection lost or failed to establish
  * @tcp_nomoretokens: TCP data ran out of tokens
+ * @net_detect: if not %NULL, woke up because of net detect
  */
 struct cfg80211_wowlan_wakeup {
 	bool disconnect, magic_pkt, gtk_rekey_failure,
@@ -2007,6 +2039,7 @@ struct cfg80211_wowlan_wakeup {
 	s32 pattern_idx;
 	u32 packet_present_len, packet_len;
 	const void *packet;
+	struct cfg80211_wowlan_nd_info *net_detect;
 };
 
 /**
@@ -2810,6 +2843,7 @@ struct ieee80211_txrx_stypes {
  * @WIPHY_WOWLAN_EAP_IDENTITY_REQ: supports wakeup on EAP identity request
  * @WIPHY_WOWLAN_4WAY_HANDSHAKE: supports wakeup on 4-way handshake failure
  * @WIPHY_WOWLAN_RFKILL_RELEASE: supports wakeup on RF-kill release
+ * @WIPHY_WOWLAN_NET_DETECT: supports wakeup on network detection
  */
 enum wiphy_wowlan_support_flags {
 	WIPHY_WOWLAN_ANY		= BIT(0),
@@ -2820,6 +2854,7 @@ enum wiphy_wowlan_support_flags {
 	WIPHY_WOWLAN_EAP_IDENTITY_REQ	= BIT(5),
 	WIPHY_WOWLAN_4WAY_HANDSHAKE	= BIT(6),
 	WIPHY_WOWLAN_RFKILL_RELEASE	= BIT(7),
+	WIPHY_WOWLAN_NET_DETECT		= BIT(8),
 };
 
 struct wiphy_wowlan_tcp_support {
@@ -2838,6 +2873,11 @@ struct wiphy_wowlan_tcp_support {
  * @pattern_max_len: maximum length of each pattern
  * @pattern_min_len: minimum length of each pattern
  * @max_pkt_offset: maximum Rx packet offset
+ * @max_nd_match_sets: maximum number of matchsets for net-detect,
+ *	similar, but not necessarily identical, to max_match_sets for
+ *	scheduled scans.
+ *	See &struct cfg80211_sched_scan_request.@match_sets for more
+ *	details.
  * @tcp: TCP wakeup support information
  */
 struct wiphy_wowlan_support {
@@ -2846,6 +2886,7 @@ struct wiphy_wowlan_support {
 	int pattern_max_len;
 	int pattern_min_len;
 	int max_pkt_offset;
+	int max_nd_match_sets;
 	const struct wiphy_wowlan_tcp_support *tcp;
 };
 
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 365db67ca71..d23208194e3 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1686,6 +1686,7 @@ enum nl80211_commands {
  *
  * @NL80211_ATTR_OPER_CLASS: operating class
  *
+ * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -2043,6 +2044,7 @@ enum nl80211_attrs {
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
+	NUM_NL80211_ATTR = __NL80211_ATTR_AFTER_LAST,
 	NL80211_ATTR_MAX = __NL80211_ATTR_AFTER_LAST - 1
 };
 
@@ -3610,6 +3612,25 @@ struct nl80211_pattern_support {
  * @NL80211_WOWLAN_TRIG_WAKEUP_TCP_NOMORETOKENS: For wakeup reporting only,
  *	the TCP connection ran out of tokens to use for data to send to the
  *	service
+ * @NL80211_WOWLAN_TRIG_NET_DETECT: wake up when a configured network
+ *	is detected.  This is a nested attribute that contains the
+ *	same attributes used with @NL80211_CMD_START_SCHED_SCAN.  It
+ *	specifies how the scan is performed (e.g. the interval and the
+ *	channels to scan) as well as the scan results that will
+ *	trigger a wake (i.e. the matchsets).
+ * @NL80211_WOWLAN_TRIG_NET_DETECT_RESULTS: nested attribute
+ *	containing an array with information about what triggered the
+ *	wake up.  If no elements are present in the array, it means
+ *	that the information is not available.  If more than one
+ *	element is present, it means that more than one match
+ *	occurred.
+ *	Each element in the array is a nested attribute that contains
+ *	one optional %NL80211_ATTR_SSID attribute and one optional
+ *	%NL80211_ATTR_SCAN_FREQUENCIES attribute.  At least one of
+ *	these attributes must be present.  If
+ *	%NL80211_ATTR_SCAN_FREQUENCIES contains more than one
+ *	frequency, it means that the match occurred in more than one
+ *	channel.
  * @NUM_NL80211_WOWLAN_TRIG: number of wake on wireless triggers
  * @MAX_NL80211_WOWLAN_TRIG: highest wowlan trigger attribute number
  *
@@ -3635,6 +3656,8 @@ enum nl80211_wowlan_triggers {
 	NL80211_WOWLAN_TRIG_WAKEUP_TCP_MATCH,
 	NL80211_WOWLAN_TRIG_WAKEUP_TCP_CONNLOST,
 	NL80211_WOWLAN_TRIG_WAKEUP_TCP_NOMORETOKENS,
+	NL80211_WOWLAN_TRIG_NET_DETECT,
+	NL80211_WOWLAN_TRIG_NET_DETECT_RESULTS,
 
 	/* keep last */
 	NUM_NL80211_WOWLAN_TRIG,
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 61ee664cf2b..faa5b1609aa 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -111,6 +111,7 @@ cfg80211_rdev_free_wowlan(struct cfg80211_registered_device *rdev)
 	    rdev->wiphy.wowlan_config->tcp->sock)
 		sock_release(rdev->wiphy.wowlan_config->tcp->sock);
 	kfree(rdev->wiphy.wowlan_config->tcp);
+	kfree(rdev->wiphy.wowlan_config->nd_config);
 	kfree(rdev->wiphy.wowlan_config);
 #endif
 }
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 03a302b884f..3ec7dc55796 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -209,7 +209,7 @@ cfg80211_get_dev_from_info(struct net *netns, struct genl_info *info)
 }
 
 /* policy for the attributes */
-static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
+static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_WIPHY] = { .type = NLA_U32 },
 	[NL80211_ATTR_WIPHY_NAME] = { .type = NLA_NUL_STRING,
 				      .len = 20-1 },
@@ -428,6 +428,7 @@ nl80211_wowlan_policy[NUM_NL80211_WOWLAN_TRIG] = {
 	[NL80211_WOWLAN_TRIG_4WAY_HANDSHAKE] = { .type = NLA_FLAG },
 	[NL80211_WOWLAN_TRIG_RFKILL_RELEASE] = { .type = NLA_FLAG },
 	[NL80211_WOWLAN_TRIG_TCP_CONNECTION] = { .type = NLA_NESTED },
+	[NL80211_WOWLAN_TRIG_NET_DETECT] = { .type = NLA_NESTED },
 };
 
 static const struct nla_policy
@@ -1088,6 +1089,8 @@ static int nl80211_send_wowlan(struct sk_buff *msg,
 	if (large && nl80211_send_wowlan_tcp_caps(rdev, msg))
 		return -ENOBUFS;
 
+	/* TODO: send wowlan net detect */
+
 	nla_nest_end(msg, nl_wowlan);
 
 	return 0;
@@ -8695,6 +8698,39 @@ static int nl80211_parse_wowlan_tcp(struct cfg80211_registered_device *rdev,
 	return 0;
 }
 
+static int nl80211_parse_wowlan_nd(struct cfg80211_registered_device *rdev,
+				   const struct wiphy_wowlan_support *wowlan,
+				   struct nlattr *attr,
+				   struct cfg80211_wowlan *trig)
+{
+	struct nlattr **tb;
+	int err;
+
+	tb = kzalloc(NUM_NL80211_ATTR * sizeof(*tb), GFP_KERNEL);
+	if (!tb)
+		return -ENOMEM;
+
+	if (!(wowlan->flags & WIPHY_WOWLAN_NET_DETECT)) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	err = nla_parse(tb, NL80211_ATTR_MAX,
+			nla_data(attr), nla_len(attr),
+			nl80211_policy);
+	if (err)
+		goto out;
+
+	trig->nd_config = nl80211_parse_sched_scan(&rdev->wiphy, tb);
+	err = PTR_ERR_OR_ZERO(trig->nd_config);
+	if (err)
+		trig->nd_config = NULL;
+
+out:
+	kfree(tb);
+	return err;
+}
+
 static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -8840,6 +8876,14 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 			goto error;
 	}
 
+	if (tb[NL80211_WOWLAN_TRIG_NET_DETECT]) {
+		err = nl80211_parse_wowlan_nd(
+			rdev, wowlan, tb[NL80211_WOWLAN_TRIG_NET_DETECT],
+			&new_triggers);
+		if (err)
+			goto error;
+	}
+
 	ntrig = kmemdup(&new_triggers, sizeof(new_triggers), GFP_KERNEL);
 	if (!ntrig) {
 		err = -ENOMEM;
@@ -12082,6 +12126,67 @@ void cfg80211_report_obss_beacon(struct wiphy *wiphy,
 EXPORT_SYMBOL(cfg80211_report_obss_beacon);
 
 #ifdef CONFIG_PM
+static int cfg80211_net_detect_results(struct sk_buff *msg,
+				       struct cfg80211_wowlan_wakeup *wakeup)
+{
+	struct cfg80211_wowlan_nd_info *nd = wakeup->net_detect;
+	struct nlattr *nl_results, *nl_match, *nl_freqs;
+	int i, j;
+
+	nl_results = nla_nest_start(
+		msg, NL80211_WOWLAN_TRIG_NET_DETECT_RESULTS);
+	if (!nl_results)
+		return -EMSGSIZE;
+
+	for (i = 0; i < nd->n_matches; i++) {
+		struct cfg80211_wowlan_nd_match *match = nd->matches[i];
+
+		nl_match = nla_nest_start(msg, i);
+		if (!nl_match)
+			break;
+
+		/* The SSID attribute is optional in nl80211, but for
+		 * simplicity reasons it's always present in the
+		 * cfg80211 structure.  If a driver can't pass the
+		 * SSID, that needs to be changed.  A zero length SSID
+		 * is still a valid SSID (wildcard), so it cannot be
+		 * used for this purpose.
+		 */
+		if (nla_put(msg, NL80211_ATTR_SSID, match->ssid.ssid_len,
+			    match->ssid.ssid)) {
+			nla_nest_cancel(msg, nl_match);
+			goto out;
+		}
+
+		if (match->n_channels) {
+			nl_freqs = nla_nest_start(
+				msg, NL80211_ATTR_SCAN_FREQUENCIES);
+			if (!nl_freqs) {
+				nla_nest_cancel(msg, nl_match);
+				goto out;
+			}
+
+			for (j = 0; j < match->n_channels; j++) {
+				if (nla_put_u32(msg,
+						NL80211_ATTR_WIPHY_FREQ,
+						match->channels[j])) {
+					nla_nest_cancel(msg, nl_freqs);
+					nla_nest_cancel(msg, nl_match);
+					goto out;
+				}
+			}
+
+			nla_nest_end(msg, nl_freqs);
+		}
+
+		nla_nest_end(msg, nl_match);
+	}
+
+out:
+	nla_nest_end(msg, nl_results);
+	return 0;
+}
+
 void cfg80211_report_wowlan_wakeup(struct wireless_dev *wdev,
 				   struct cfg80211_wowlan_wakeup *wakeup,
 				   gfp_t gfp)
@@ -12176,6 +12281,10 @@ void cfg80211_report_wowlan_wakeup(struct wireless_dev *wdev,
 				goto free_msg;
 		}
 
+		if (wakeup->net_detect &&
+		    cfg80211_net_detect_results(msg, wakeup))
+				goto free_msg;
+
 		nla_nest_end(msg, reasons);
 	}
 
-- 
cgit v1.2.3-70-g09d2


From ad2b26abc157460ca6fac1a53a2bfeade283adfa Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 12 Jun 2014 21:39:05 +0200
Subject: cfg80211: allow drivers to support random MAC addresses for scan

Add the necessary feature flags and a scan flag to support using
random MAC addresses for scan while unassociated.

The configuration for this supports an arbitrary MAC address
value and mask, so that any kind of configuration (e.g. fixed
OUI or full 46-bit random) can be requested. Full 46-bit random
is the default when no other configuration is passed.

Also add a small helper function to use the addr/mask correctly.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 25 +++++++++++++
 include/uapi/linux/nl80211.h | 29 +++++++++++++++
 net/wireless/nl80211.c       | 86 ++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 137 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 05aae22e92a..bb748c4da5a 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1437,6 +1437,10 @@ struct cfg80211_ssid {
  * @aborted: (internal) scan request was notified as aborted
  * @notified: (internal) scan request was notified as done or aborted
  * @no_cck: used to send probe requests at non CCK rate in 2GHz band
+ * @mac_addr: MAC address used with randomisation
+ * @mac_addr_mask: MAC address mask used with randomisation, bits that
+ *	are 0 in the mask should be randomised, bits that are 1 should
+ *	be taken from the @mac_addr
  */
 struct cfg80211_scan_request {
 	struct cfg80211_ssid *ssids;
@@ -1451,6 +1455,9 @@ struct cfg80211_scan_request {
 
 	struct wireless_dev *wdev;
 
+	u8 mac_addr[ETH_ALEN] __aligned(2);
+	u8 mac_addr_mask[ETH_ALEN] __aligned(2);
+
 	/* internal */
 	struct wiphy *wiphy;
 	unsigned long scan_start;
@@ -1461,6 +1468,17 @@ struct cfg80211_scan_request {
 	struct ieee80211_channel *channels[0];
 };
 
+static inline void get_random_mask_addr(u8 *buf, const u8 *addr, const u8 *mask)
+{
+	int i;
+
+	get_random_bytes(buf, ETH_ALEN);
+	for (i = 0; i < ETH_ALEN; i++) {
+		buf[i] &= ~mask[i];
+		buf[i] |= addr[i] & mask[i];
+	}
+}
+
 /**
  * struct cfg80211_match_set - sets of attributes to match
  *
@@ -1494,6 +1512,10 @@ struct cfg80211_match_set {
  * @channels: channels to scan
  * @min_rssi_thold: for drivers only supporting a single threshold, this
  *	contains the minimum over all matchsets
+ * @mac_addr: MAC address used with randomisation
+ * @mac_addr_mask: MAC address mask used with randomisation, bits that
+ *	are 0 in the mask should be randomised, bits that are 1 should
+ *	be taken from the @mac_addr
  */
 struct cfg80211_sched_scan_request {
 	struct cfg80211_ssid *ssids;
@@ -1508,6 +1530,9 @@ struct cfg80211_sched_scan_request {
 	int n_match_sets;
 	s32 min_rssi_thold;
 
+	u8 mac_addr[ETH_ALEN] __aligned(2);
+	u8 mac_addr_mask[ETH_ALEN] __aligned(2);
+
 	/* internal */
 	struct wiphy *wiphy;
 	struct net_device *dev;
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index d23208194e3..a99081efc2d 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1686,6 +1686,8 @@ enum nl80211_commands {
  *
  * @NL80211_ATTR_OPER_CLASS: operating class
  *
+ * @NL80211_ATTR_MAC_MASK: MAC address mask
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -2041,6 +2043,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_OPER_CLASS,
 
+	NL80211_ATTR_MAC_MASK,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -4139,6 +4143,18 @@ enum nl80211_ap_sme_features {
  *	See 'macaddr' field in the vif_params (cfg80211.h).
  * @NL80211_FEATURE_TDLS_CHANNEL_SWITCH: Driver supports channel switching when
  *	operating as a TDLS peer.
+ * @NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR: This device/driver supports using a
+ *	random MAC address during scan (if the device is unassociated); the
+ *	%NL80211_SCAN_FLAG_RANDOM_ADDR flag may be set for scans and the MAC
+ *	address mask/value will be used.
+ * @NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR: This device/driver supports
+ *	using a random MAC address for every scan iteration during scheduled
+ *	scan (while not associated), the %NL80211_SCAN_FLAG_RANDOM_ADDR may
+ *	be set for scheduled scan and the MAC address mask/value will be used.
+ * @NL80211_FEATURE_ND_RANDOM_MAC_ADDR: This device/driver supports using a
+ *	random MAC address for every scan iteration during "net detect", i.e.
+ *	scan in unassociated WoWLAN, the %NL80211_SCAN_FLAG_RANDOM_ADDR may
+ *	be set for scheduled scan and the MAC address mask/value will be used.
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -4170,6 +4186,9 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_SUPPORTS_WMM_ADMISSION		= 1 << 26,
 	NL80211_FEATURE_MAC_ON_CREATE			= 1 << 27,
 	NL80211_FEATURE_TDLS_CHANNEL_SWITCH		= 1 << 28,
+	NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR		= 1 << 29,
+	NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR	= 1 << 30,
+	NL80211_FEATURE_ND_RANDOM_MAC_ADDR		= 1 << 31,
 };
 
 /**
@@ -4218,11 +4237,21 @@ enum nl80211_connect_failed_reason {
  *	dangerous because will destroy stations performance as a lot of frames
  *	will be lost while scanning off-channel, therefore it must be used only
  *	when really needed
+ * @NL80211_SCAN_FLAG_RANDOM_ADDR: use a random MAC address for this scan (or
+ *	for scheduled scan: a different one for every scan iteration). When the
+ *	flag is set, depending on device capabilities the @NL80211_ATTR_MAC and
+ *	@NL80211_ATTR_MAC_MASK attributes may also be given in which case only
+ *	the masked bits will be preserved from the MAC address and the remainder
+ *	randomised. If the attributes are not given full randomisation (46 bits,
+ *	locally administered 1, multicast 0) is assumed.
+ *	This flag must not be requested when the feature isn't supported, check
+ *	the nl80211 feature flags for the device.
  */
 enum nl80211_scan_flags {
 	NL80211_SCAN_FLAG_LOW_PRIORITY			= 1<<0,
 	NL80211_SCAN_FLAG_FLUSH				= 1<<1,
 	NL80211_SCAN_FLAG_AP				= 1<<2,
+	NL80211_SCAN_FLAG_RANDOM_ADDR			= 1<<3,
 };
 
 /**
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 3ec7dc55796..dd5a827f9cb 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -395,6 +395,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_USER_PRIO] = { .type = NLA_U8 },
 	[NL80211_ATTR_ADMITTED_TIME] = { .type = NLA_U16 },
 	[NL80211_ATTR_SMPS_MODE] = { .type = NLA_U8 },
+	[NL80211_ATTR_MAC_MASK] = { .len = ETH_ALEN },
 };
 
 /* policy for the key attributes */
@@ -5481,6 +5482,43 @@ static int validate_scan_freqs(struct nlattr *freqs)
 	return n_channels;
 }
 
+static int nl80211_parse_random_mac(struct nlattr **attrs,
+				    u8 *mac_addr, u8 *mac_addr_mask)
+{
+	int i;
+
+	if (!attrs[NL80211_ATTR_MAC] && !attrs[NL80211_ATTR_MAC_MASK]) {
+		memset(mac_addr, 0, ETH_ALEN);
+		memset(mac_addr_mask, 0, ETH_ALEN);
+		mac_addr[0] = 0x2;
+		mac_addr_mask[0] = 0x3;
+
+		return 0;
+	}
+
+	/* need both or none */
+	if (!attrs[NL80211_ATTR_MAC] || !attrs[NL80211_ATTR_MAC_MASK])
+		return -EINVAL;
+
+	memcpy(mac_addr, nla_data(attrs[NL80211_ATTR_MAC]), ETH_ALEN);
+	memcpy(mac_addr_mask, nla_data(attrs[NL80211_ATTR_MAC_MASK]), ETH_ALEN);
+
+	/* don't allow or configure an mcast address */
+	if (!is_multicast_ether_addr(mac_addr_mask) ||
+	    is_multicast_ether_addr(mac_addr))
+		return -EINVAL;
+
+	/*
+	 * allow users to pass a MAC address that has bits set outside
+	 * of the mask, but don't bother drivers with having to deal
+	 * with such bits
+	 */
+	for (i = 0; i < ETH_ALEN; i++)
+		mac_addr[i] &= mac_addr_mask[i];
+
+	return 0;
+}
+
 static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -5658,6 +5696,25 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 			err = -EOPNOTSUPP;
 			goto out_free;
 		}
+
+		if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
+			if (!(wiphy->features &
+					NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR)) {
+				err = -EOPNOTSUPP;
+				goto out_free;
+			}
+
+			if (wdev->current_bss) {
+				err = -EOPNOTSUPP;
+				goto out_free;
+			}
+
+			err = nl80211_parse_random_mac(info->attrs,
+						       request->mac_addr,
+						       request->mac_addr_mask);
+			if (err)
+				goto out_free;
+		}
 	}
 
 	request->no_cck =
@@ -5685,7 +5742,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 }
 
 static struct cfg80211_sched_scan_request *
-nl80211_parse_sched_scan(struct wiphy *wiphy,
+nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 			 struct nlattr **attrs)
 {
 	struct cfg80211_sched_scan_request *request;
@@ -5934,6 +5991,28 @@ nl80211_parse_sched_scan(struct wiphy *wiphy,
 			err = -EOPNOTSUPP;
 			goto out_free;
 		}
+
+		if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
+			u32 flg = NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR;
+
+			if (!wdev) /* must be net-detect */
+				flg = NL80211_FEATURE_ND_RANDOM_MAC_ADDR;
+
+			if (!(wiphy->features & flg)) {
+				err = -EOPNOTSUPP;
+				goto out_free;
+			}
+
+			if (wdev && wdev->current_bss) {
+				err = -EOPNOTSUPP;
+				goto out_free;
+			}
+
+			err = nl80211_parse_random_mac(attrs, request->mac_addr,
+						       request->mac_addr_mask);
+			if (err)
+				goto out_free;
+		}
 	}
 
 	request->interval = interval;
@@ -5951,6 +6030,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct net_device *dev = info->user_ptr[1];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	int err;
 
 	if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) ||
@@ -5960,7 +6040,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	if (rdev->sched_scan_req)
 		return -EINPROGRESS;
 
-	rdev->sched_scan_req = nl80211_parse_sched_scan(&rdev->wiphy,
+	rdev->sched_scan_req = nl80211_parse_sched_scan(&rdev->wiphy, wdev,
 							info->attrs);
 	err = PTR_ERR_OR_ZERO(rdev->sched_scan_req);
 	if (err)
@@ -8721,7 +8801,7 @@ static int nl80211_parse_wowlan_nd(struct cfg80211_registered_device *rdev,
 	if (err)
 		goto out;
 
-	trig->nd_config = nl80211_parse_sched_scan(&rdev->wiphy, tb);
+	trig->nd_config = nl80211_parse_sched_scan(&rdev->wiphy, NULL, tb);
 	err = PTR_ERR_OR_ZERO(trig->nd_config);
 	if (err)
 		trig->nd_config = NULL;
-- 
cgit v1.2.3-70-g09d2


From a344d6778a98e4c19ac871f369e399e6356edcb3 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 12 Jun 2014 22:24:31 +0200
Subject: mac80211: allow drivers to support NL80211_SCAN_FLAG_RANDOM_ADDR

Allow drivers to support NL80211_SCAN_FLAG_RANDOM_ADDR with software
based scanning and generate a random MAC address for them for every
scan request with the flag.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath5k/mac80211-ops.c      |  6 ++-
 drivers/net/wireless/ath/ath9k/channel.c           |  2 +-
 drivers/net/wireless/ath/ath9k/htc_drv_main.c      |  7 +++-
 drivers/net/wireless/ath/ath9k/main.c              |  7 +++-
 drivers/net/wireless/ath/wcn36xx/main.c            |  7 +++-
 drivers/net/wireless/b43/main.c                    |  7 +++-
 .../net/wireless/brcm80211/brcmsmac/mac80211_if.c  |  7 +++-
 drivers/net/wireless/cw1200/scan.c                 |  2 +-
 drivers/net/wireless/mac80211_hwsim.c              |  9 ++--
 drivers/net/wireless/mwl8k.c                       |  7 +++-
 drivers/net/wireless/rt2x00/rt2x00.h               |  7 +++-
 drivers/net/wireless/rt2x00/rt2x00mac.c            |  7 +++-
 drivers/net/wireless/rtlwifi/core.c                |  7 +++-
 drivers/net/wireless/ti/wl1251/main.c              |  2 +-
 drivers/net/wireless/ti/wlcore/cmd.c               |  2 +-
 drivers/staging/vt6656/main_usb.c                  |  7 +++-
 include/net/mac80211.h                             | 15 ++++---
 net/mac80211/driver-ops.h                          | 15 ++++---
 net/mac80211/ieee80211_i.h                         |  7 +++-
 net/mac80211/mlme.c                                |  8 ++--
 net/mac80211/scan.c                                | 48 +++++++++++++++++-----
 net/mac80211/trace.h                               | 31 +++++++++++---
 net/mac80211/tx.c                                  |  9 ++--
 net/mac80211/util.c                                | 12 +++---
 24 files changed, 166 insertions(+), 72 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
index ab2709a4376..19eab2a69ad 100644
--- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c
+++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
@@ -547,7 +547,9 @@ ath5k_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 
 
 static void
-ath5k_sw_scan_start(struct ieee80211_hw *hw)
+ath5k_sw_scan_start(struct ieee80211_hw *hw,
+		    struct ieee80211_vif *vif,
+		    const u8 *mac_addr)
 {
 	struct ath5k_hw *ah = hw->priv;
 	if (!ah->assoc)
@@ -556,7 +558,7 @@ ath5k_sw_scan_start(struct ieee80211_hw *hw)
 
 
 static void
-ath5k_sw_scan_complete(struct ieee80211_hw *hw)
+ath5k_sw_scan_complete(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 {
 	struct ath5k_hw *ah = hw->priv;
 	ath5k_hw_set_ledstate(ah, ah->assoc ?
diff --git a/drivers/net/wireless/ath/ath9k/channel.c b/drivers/net/wireless/ath/ath9k/channel.c
index 794d5201643..206665059d6 100644
--- a/drivers/net/wireless/ath/ath9k/channel.c
+++ b/drivers/net/wireless/ath/ath9k/channel.c
@@ -963,7 +963,7 @@ static void ath_scan_send_probe(struct ath_softc *sc,
 	struct ieee80211_tx_info *info;
 	int band = sc->offchannel.chan.chandef.chan->band;
 
-	skb = ieee80211_probereq_get(sc->hw, vif,
+	skb = ieee80211_probereq_get(sc->hw, vif->addr,
 			ssid->ssid, ssid->ssid_len, req->ie_len);
 	if (!skb)
 		return;
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index c7d12efaa86..92d5a6c5a22 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -1691,7 +1691,9 @@ static int ath9k_htc_ampdu_action(struct ieee80211_hw *hw,
 	return ret;
 }
 
-static void ath9k_htc_sw_scan_start(struct ieee80211_hw *hw)
+static void ath9k_htc_sw_scan_start(struct ieee80211_hw *hw,
+				    struct ieee80211_vif *vif,
+				    const u8 *mac_addr)
 {
 	struct ath9k_htc_priv *priv = hw->priv;
 	struct ath_common *common = ath9k_hw_common(priv->ah);
@@ -1705,7 +1707,8 @@ static void ath9k_htc_sw_scan_start(struct ieee80211_hw *hw)
 	mutex_unlock(&priv->mutex);
 }
 
-static void ath9k_htc_sw_scan_complete(struct ieee80211_hw *hw)
+static void ath9k_htc_sw_scan_complete(struct ieee80211_hw *hw,
+				       struct ieee80211_vif *vif)
 {
 	struct ath9k_htc_priv *priv = hw->priv;
 	struct ath_common *common = ath9k_hw_common(priv->ah);
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 5f16630f26c..027ad715ffb 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -2180,14 +2180,17 @@ static int ath9k_get_antenna(struct ieee80211_hw *hw, u32 *tx_ant, u32 *rx_ant)
 	return 0;
 }
 
-static void ath9k_sw_scan_start(struct ieee80211_hw *hw)
+static void ath9k_sw_scan_start(struct ieee80211_hw *hw,
+				struct ieee80211_vif *vif,
+				const u8 *mac_addr)
 {
 	struct ath_softc *sc = hw->priv;
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	set_bit(ATH_OP_SCANNING, &common->op_flags);
 }
 
-static void ath9k_sw_scan_complete(struct ieee80211_hw *hw)
+static void ath9k_sw_scan_complete(struct ieee80211_hw *hw,
+				   struct ieee80211_vif *vif)
 {
 	struct ath_softc *sc = hw->priv;
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index b71d2b33532..267c35d1f69 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -494,7 +494,9 @@ out:
 	return ret;
 }
 
-static void wcn36xx_sw_scan_start(struct ieee80211_hw *hw)
+static void wcn36xx_sw_scan_start(struct ieee80211_hw *hw,
+				  struct ieee80211_vif *vif,
+				  const u8 *mac_addr)
 {
 	struct wcn36xx *wcn = hw->priv;
 
@@ -502,7 +504,8 @@ static void wcn36xx_sw_scan_start(struct ieee80211_hw *hw)
 	wcn36xx_smd_start_scan(wcn);
 }
 
-static void wcn36xx_sw_scan_complete(struct ieee80211_hw *hw)
+static void wcn36xx_sw_scan_complete(struct ieee80211_hw *hw,
+				     struct ieee80211_vif *vif)
 {
 	struct wcn36xx *wcn = hw->priv;
 
diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c
index 5d4173ee55b..47731cb0d81 100644
--- a/drivers/net/wireless/b43/main.c
+++ b/drivers/net/wireless/b43/main.c
@@ -5110,7 +5110,9 @@ static void b43_op_sta_notify(struct ieee80211_hw *hw,
 	B43_WARN_ON(!vif || wl->vif != vif);
 }
 
-static void b43_op_sw_scan_start_notifier(struct ieee80211_hw *hw)
+static void b43_op_sw_scan_start_notifier(struct ieee80211_hw *hw,
+					  struct ieee80211_vif *vif,
+					  const u8 *mac_addr)
 {
 	struct b43_wl *wl = hw_to_b43_wl(hw);
 	struct b43_wldev *dev;
@@ -5124,7 +5126,8 @@ static void b43_op_sw_scan_start_notifier(struct ieee80211_hw *hw)
 	mutex_unlock(&wl->mutex);
 }
 
-static void b43_op_sw_scan_complete_notifier(struct ieee80211_hw *hw)
+static void b43_op_sw_scan_complete_notifier(struct ieee80211_hw *hw,
+					     struct ieee80211_vif *vif)
 {
 	struct b43_wl *wl = hw_to_b43_wl(hw);
 	struct b43_wldev *dev;
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
index 43c71bfaa47..f95b5244228 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
@@ -764,7 +764,9 @@ brcms_ops_configure_filter(struct ieee80211_hw *hw,
 	return;
 }
 
-static void brcms_ops_sw_scan_start(struct ieee80211_hw *hw)
+static void brcms_ops_sw_scan_start(struct ieee80211_hw *hw,
+				    struct ieee80211_vif *vif,
+				    const u8 *mac_addr)
 {
 	struct brcms_info *wl = hw->priv;
 	spin_lock_bh(&wl->lock);
@@ -773,7 +775,8 @@ static void brcms_ops_sw_scan_start(struct ieee80211_hw *hw)
 	return;
 }
 
-static void brcms_ops_sw_scan_complete(struct ieee80211_hw *hw)
+static void brcms_ops_sw_scan_complete(struct ieee80211_hw *hw,
+				       struct ieee80211_vif *vif)
 {
 	struct brcms_info *wl = hw->priv;
 	spin_lock_bh(&wl->lock);
diff --git a/drivers/net/wireless/cw1200/scan.c b/drivers/net/wireless/cw1200/scan.c
index b2fb6c63209..f2e276faca7 100644
--- a/drivers/net/wireless/cw1200/scan.c
+++ b/drivers/net/wireless/cw1200/scan.c
@@ -78,7 +78,7 @@ int cw1200_hw_scan(struct ieee80211_hw *hw,
 	if (req->n_ssids > WSM_SCAN_MAX_NUM_OF_SSIDS)
 		return -EINVAL;
 
-	frame.skb = ieee80211_probereq_get(hw, priv->vif, NULL, 0,
+	frame.skb = ieee80211_probereq_get(hw, priv->vif->addr, NULL, 0,
 		req->ie_len);
 	if (!frame.skb)
 		return -ENOMEM;
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 58f11bb0896..6daaad595ea 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1802,7 +1802,7 @@ static void hw_scan_work(struct work_struct *work)
 			struct sk_buff *probe;
 
 			probe = ieee80211_probereq_get(hwsim->hw,
-						       hwsim->hw_scan_vif,
+						       hwsim->hw_scan_vif->addr,
 						       req->ssids[i].ssid,
 						       req->ssids[i].ssid_len,
 						       req->ie_len);
@@ -1866,7 +1866,9 @@ static void mac80211_hwsim_cancel_hw_scan(struct ieee80211_hw *hw,
 	mutex_unlock(&hwsim->mutex);
 }
 
-static void mac80211_hwsim_sw_scan(struct ieee80211_hw *hw)
+static void mac80211_hwsim_sw_scan(struct ieee80211_hw *hw,
+				   struct ieee80211_vif *vif,
+				   const u8 *mac_addr)
 {
 	struct mac80211_hwsim_data *hwsim = hw->priv;
 
@@ -1884,7 +1886,8 @@ out:
 	mutex_unlock(&hwsim->mutex);
 }
 
-static void mac80211_hwsim_sw_scan_complete(struct ieee80211_hw *hw)
+static void mac80211_hwsim_sw_scan_complete(struct ieee80211_hw *hw,
+					    struct ieee80211_vif *vif)
 {
 	struct mac80211_hwsim_data *hwsim = hw->priv;
 
diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c
index ef1104476bd..b8d1e04aa9b 100644
--- a/drivers/net/wireless/mwl8k.c
+++ b/drivers/net/wireless/mwl8k.c
@@ -5548,7 +5548,9 @@ mwl8k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	return rc;
 }
 
-static void mwl8k_sw_scan_start(struct ieee80211_hw *hw)
+static void mwl8k_sw_scan_start(struct ieee80211_hw *hw,
+				struct ieee80211_vif *vif,
+				const u8 *mac_addr)
 {
 	struct mwl8k_priv *priv = hw->priv;
 	u8 tmp;
@@ -5565,7 +5567,8 @@ static void mwl8k_sw_scan_start(struct ieee80211_hw *hw)
 	priv->sw_scan_start = true;
 }
 
-static void mwl8k_sw_scan_complete(struct ieee80211_hw *hw)
+static void mwl8k_sw_scan_complete(struct ieee80211_hw *hw,
+				   struct ieee80211_vif *vif)
 {
 	struct mwl8k_priv *priv = hw->priv;
 	u8 tmp;
diff --git a/drivers/net/wireless/rt2x00/rt2x00.h b/drivers/net/wireless/rt2x00/rt2x00.h
index d13f25cd70d..1ff81afb672 100644
--- a/drivers/net/wireless/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/rt2x00/rt2x00.h
@@ -1437,8 +1437,11 @@ int rt2x00mac_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		      struct ieee80211_sta *sta);
 int rt2x00mac_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			 struct ieee80211_sta *sta);
-void rt2x00mac_sw_scan_start(struct ieee80211_hw *hw);
-void rt2x00mac_sw_scan_complete(struct ieee80211_hw *hw);
+void rt2x00mac_sw_scan_start(struct ieee80211_hw *hw,
+			     struct ieee80211_vif *vif,
+			     const u8 *mac_addr);
+void rt2x00mac_sw_scan_complete(struct ieee80211_hw *hw,
+				struct ieee80211_vif *vif);
 int rt2x00mac_get_stats(struct ieee80211_hw *hw,
 			struct ieee80211_low_level_stats *stats);
 void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/rt2x00/rt2x00mac.c b/drivers/net/wireless/rt2x00/rt2x00mac.c
index ad6e5a8d1e1..cb40245a069 100644
--- a/drivers/net/wireless/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/rt2x00/rt2x00mac.c
@@ -568,7 +568,9 @@ int rt2x00mac_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 }
 EXPORT_SYMBOL_GPL(rt2x00mac_sta_remove);
 
-void rt2x00mac_sw_scan_start(struct ieee80211_hw *hw)
+void rt2x00mac_sw_scan_start(struct ieee80211_hw *hw,
+			     struct ieee80211_vif *vif,
+			     const u8 *mac_addr)
 {
 	struct rt2x00_dev *rt2x00dev = hw->priv;
 	set_bit(DEVICE_STATE_SCANNING, &rt2x00dev->flags);
@@ -576,7 +578,8 @@ void rt2x00mac_sw_scan_start(struct ieee80211_hw *hw)
 }
 EXPORT_SYMBOL_GPL(rt2x00mac_sw_scan_start);
 
-void rt2x00mac_sw_scan_complete(struct ieee80211_hw *hw)
+void rt2x00mac_sw_scan_complete(struct ieee80211_hw *hw,
+				struct ieee80211_vif *vif)
 {
 	struct rt2x00_dev *rt2x00dev = hw->priv;
 	clear_bit(DEVICE_STATE_SCANNING, &rt2x00dev->flags);
diff --git a/drivers/net/wireless/rtlwifi/core.c b/drivers/net/wireless/rtlwifi/core.c
index f6179bc0608..884d90526f9 100644
--- a/drivers/net/wireless/rtlwifi/core.c
+++ b/drivers/net/wireless/rtlwifi/core.c
@@ -1361,7 +1361,9 @@ static int rtl_op_ampdu_action(struct ieee80211_hw *hw,
 	return 0;
 }
 
-static void rtl_op_sw_scan_start(struct ieee80211_hw *hw)
+static void rtl_op_sw_scan_start(struct ieee80211_hw *hw,
+				 struct ieee80211_vif *vif,
+				 const u8 *mac_addr)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
@@ -1396,7 +1398,8 @@ static void rtl_op_sw_scan_start(struct ieee80211_hw *hw)
 	rtlpriv->cfg->ops->scan_operation_backup(hw, SCAN_OPT_BACKUP_BAND0);
 }
 
-static void rtl_op_sw_scan_complete(struct ieee80211_hw *hw)
+static void rtl_op_sw_scan_complete(struct ieee80211_hw *hw,
+				    struct ieee80211_vif *vif)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
diff --git a/drivers/net/wireless/ti/wl1251/main.c b/drivers/net/wireless/ti/wl1251/main.c
index 38234851457..0b30a7b4d66 100644
--- a/drivers/net/wireless/ti/wl1251/main.c
+++ b/drivers/net/wireless/ti/wl1251/main.c
@@ -1029,7 +1029,7 @@ static int wl1251_op_hw_scan(struct ieee80211_hw *hw,
 			goto out_sleep;
 	}
 
-	skb = ieee80211_probereq_get(wl->hw, wl->vif, ssid, ssid_len,
+	skb = ieee80211_probereq_get(wl->hw, wl->vif->addr, ssid, ssid_len,
 				     req->ie_len);
 	if (!skb) {
 		ret = -ENOMEM;
diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c
index dd2e448c3e2..b82661962d3 100644
--- a/drivers/net/wireless/ti/wlcore/cmd.c
+++ b/drivers/net/wireless/ti/wlcore/cmd.c
@@ -1145,7 +1145,7 @@ int wl12xx_cmd_build_probe_req(struct wl1271 *wl, struct wl12xx_vif *wlvif,
 
 	wl1271_debug(DEBUG_SCAN, "build probe request band %d", band);
 
-	skb = ieee80211_probereq_get(wl->hw, vif, ssid, ssid_len,
+	skb = ieee80211_probereq_get(wl->hw, vif->addr, ssid, ssid_len,
 				     ie0_len + ie1_len);
 	if (!skb) {
 		ret = -ENOMEM;
diff --git a/drivers/staging/vt6656/main_usb.c b/drivers/staging/vt6656/main_usb.c
index 2fbff907ce8..dbc311c3dc3 100644
--- a/drivers/staging/vt6656/main_usb.c
+++ b/drivers/staging/vt6656/main_usb.c
@@ -856,7 +856,9 @@ static int vnt_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	return 0;
 }
 
-static void vnt_sw_scan_start(struct ieee80211_hw *hw)
+static void vnt_sw_scan_start(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      const u8 *addr)
 {
 	struct vnt_private *priv = hw->priv;
 
@@ -865,7 +867,8 @@ static void vnt_sw_scan_start(struct ieee80211_hw *hw)
 	vnt_update_pre_ed_threshold(priv, true);
 }
 
-static void vnt_sw_scan_complete(struct ieee80211_hw *hw)
+static void vnt_sw_scan_complete(struct ieee80211_hw *hw,
+				 struct ieee80211_vif *vif)
 {
 	struct vnt_private *priv = hw->priv;
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 59166a115af..7b889e3a264 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2622,7 +2622,9 @@ enum ieee80211_reconfig_type {
  *
  * @sw_scan_start: Notifier function that is called just before a software scan
  *	is started. Can be NULL, if the driver doesn't need this notification.
- *	The callback can sleep.
+ *	The mac_addr parameter allows supporting NL80211_SCAN_FLAG_RANDOM_ADDR,
+ *	the driver may set the NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR flag if it
+ *	can use this parameter. The callback can sleep.
  *
  * @sw_scan_complete: Notifier function that is called just after a
  *	software scan finished. Can be NULL, if the driver doesn't need
@@ -3016,8 +3018,11 @@ struct ieee80211_ops {
 				struct ieee80211_scan_ies *ies);
 	int (*sched_scan_stop)(struct ieee80211_hw *hw,
 			       struct ieee80211_vif *vif);
-	void (*sw_scan_start)(struct ieee80211_hw *hw);
-	void (*sw_scan_complete)(struct ieee80211_hw *hw);
+	void (*sw_scan_start)(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      const u8 *mac_addr);
+	void (*sw_scan_complete)(struct ieee80211_hw *hw,
+				 struct ieee80211_vif *vif);
 	int (*get_stats)(struct ieee80211_hw *hw,
 			 struct ieee80211_low_level_stats *stats);
 	void (*get_tkip_seq)(struct ieee80211_hw *hw, u8 hw_key_idx,
@@ -3820,7 +3825,7 @@ struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw,
 /**
  * ieee80211_probereq_get - retrieve a Probe Request template
  * @hw: pointer obtained from ieee80211_alloc_hw().
- * @vif: &struct ieee80211_vif pointer from the add_interface callback.
+ * @src_addr: source MAC address
  * @ssid: SSID buffer
  * @ssid_len: length of SSID
  * @tailroom: tailroom to reserve at end of SKB for IEs
@@ -3831,7 +3836,7 @@ struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw,
  * Return: The Probe Request template. %NULL on error.
  */
 struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw,
-				       struct ieee80211_vif *vif,
+				       const u8 *src_addr,
 				       const u8 *ssid, size_t ssid_len,
 				       size_t tailroom);
 
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index ba0d2cb5df1..5f5fc3f3ee7 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -380,23 +380,26 @@ static inline int drv_sched_scan_stop(struct ieee80211_local *local,
 	return ret;
 }
 
-static inline void drv_sw_scan_start(struct ieee80211_local *local)
+static inline void drv_sw_scan_start(struct ieee80211_local *local,
+				     struct ieee80211_sub_if_data *sdata,
+				     const u8 *mac_addr)
 {
 	might_sleep();
 
-	trace_drv_sw_scan_start(local);
+	trace_drv_sw_scan_start(local, sdata, mac_addr);
 	if (local->ops->sw_scan_start)
-		local->ops->sw_scan_start(&local->hw);
+		local->ops->sw_scan_start(&local->hw, &sdata->vif, mac_addr);
 	trace_drv_return_void(local);
 }
 
-static inline void drv_sw_scan_complete(struct ieee80211_local *local)
+static inline void drv_sw_scan_complete(struct ieee80211_local *local,
+					struct ieee80211_sub_if_data *sdata)
 {
 	might_sleep();
 
-	trace_drv_sw_scan_complete(local);
+	trace_drv_sw_scan_complete(local, sdata);
 	if (local->ops->sw_scan_complete)
-		local->ops->sw_scan_complete(&local->hw);
+		local->ops->sw_scan_complete(&local->hw, &sdata->vif);
 	trace_drv_return_void(local);
 }
 
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index dd27180060b..cf95d033bcb 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1249,6 +1249,7 @@ struct ieee80211_local {
 	struct work_struct sched_scan_stopped_work;
 	struct ieee80211_sub_if_data __rcu *sched_scan_sdata;
 	struct cfg80211_sched_scan_request __rcu *sched_scan_req;
+	u8 scan_addr[ETH_ALEN];
 
 	unsigned long leave_oper_channel_time;
 	enum mac80211_scan_state next_scan_state;
@@ -1901,12 +1902,14 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer,
 			     u8 bands_used, u32 *rate_masks,
 			     struct cfg80211_chan_def *chandef);
 struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
-					  u8 *dst, u32 ratemask,
+					  const u8 *src, const u8 *dst,
+					  u32 ratemask,
 					  struct ieee80211_channel *chan,
 					  const u8 *ssid, size_t ssid_len,
 					  const u8 *ie, size_t ie_len,
 					  bool directed);
-void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst,
+void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata,
+			      const u8 *src, const u8 *dst,
 			      const u8 *ssid, size_t ssid_len,
 			      const u8 *ie, size_t ie_len,
 			      u32 ratemask, bool directed, u32 tx_flags,
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 45490a202d9..d29589a0906 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2225,7 +2225,8 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata)
 		else
 			ssid_len = ssid[1];
 
-		ieee80211_send_probe_req(sdata, dst, ssid + 2, ssid_len, NULL,
+		ieee80211_send_probe_req(sdata, sdata->vif.addr, NULL,
+					 ssid + 2, ssid_len, NULL,
 					 0, (u32) -1, true, 0,
 					 ifmgd->associated->channel, false);
 		rcu_read_unlock();
@@ -2328,7 +2329,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw,
 	else
 		ssid_len = ssid[1];
 
-	skb = ieee80211_build_probe_req(sdata, cbss->bssid,
+	skb = ieee80211_build_probe_req(sdata, sdata->vif.addr, cbss->bssid,
 					(u32) -1, cbss->channel,
 					ssid + 2, ssid_len,
 					NULL, 0, true);
@@ -3649,7 +3650,8 @@ static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata)
 		 * Direct probe is sent to broadcast address as some APs
 		 * will not answer to direct packet in unassociated state.
 		 */
-		ieee80211_send_probe_req(sdata, NULL, ssidie + 2, ssidie[1],
+		ieee80211_send_probe_req(sdata, sdata->vif.addr, NULL,
+					 ssidie + 2, ssidie[1],
 					 NULL, 0, (u32) -1, true, 0,
 					 auth_data->bss->channel, false);
 		rcu_read_unlock();
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index e75e64b8042..ae842678b62 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -184,9 +184,21 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 		return;
 
 	if (ieee80211_is_probe_resp(mgmt->frame_control)) {
-		/* ignore ProbeResp to foreign address */
-		if ((!sdata1 || !ether_addr_equal(mgmt->da, sdata1->vif.addr)) &&
-		    (!sdata2 || !ether_addr_equal(mgmt->da, sdata2->vif.addr)))
+		struct cfg80211_scan_request *scan_req;
+		struct cfg80211_sched_scan_request *sched_scan_req;
+
+		scan_req = rcu_dereference(local->scan_req);
+		sched_scan_req = rcu_dereference(local->sched_scan_req);
+
+		/* ignore ProbeResp to foreign address unless scanning
+		 * with randomised address
+		 */
+		if (!(sdata1 &&
+		      (ether_addr_equal(mgmt->da, sdata1->vif.addr) ||
+		       scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)) &&
+		    !(sdata2 &&
+		      (ether_addr_equal(mgmt->da, sdata2->vif.addr) ||
+		       sched_scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)))
 			return;
 
 		elements = mgmt->u.probe_resp.variable;
@@ -284,6 +296,9 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local)
 					 bands_used, req->rates, &chandef);
 	local->hw_scan_req->req.ie_len = ielen;
 	local->hw_scan_req->req.no_cck = req->no_cck;
+	ether_addr_copy(local->hw_scan_req->req.mac_addr, req->mac_addr);
+	ether_addr_copy(local->hw_scan_req->req.mac_addr_mask,
+			req->mac_addr_mask);
 
 	return true;
 }
@@ -294,6 +309,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
 	bool hw_scan = local->ops->hw_scan;
 	bool was_scanning = local->scanning;
 	struct cfg80211_scan_request *scan_req;
+	struct ieee80211_sub_if_data *scan_sdata;
 
 	lockdep_assert_held(&local->mtx);
 
@@ -332,6 +348,9 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
 	if (scan_req != local->int_scan_req)
 		cfg80211_scan_done(scan_req, aborted);
 	RCU_INIT_POINTER(local->scan_req, NULL);
+
+	scan_sdata = rcu_dereference_protected(local->scan_sdata,
+					       lockdep_is_held(&local->mtx));
 	RCU_INIT_POINTER(local->scan_sdata, NULL);
 
 	local->scanning = 0;
@@ -342,7 +361,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
 
 	if (!hw_scan) {
 		ieee80211_configure_filter(local);
-		drv_sw_scan_complete(local);
+		drv_sw_scan_complete(local, scan_sdata);
 		ieee80211_offchannel_return(local);
 	}
 
@@ -368,7 +387,8 @@ void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
 }
 EXPORT_SYMBOL(ieee80211_scan_completed);
 
-static int ieee80211_start_sw_scan(struct ieee80211_local *local)
+static int ieee80211_start_sw_scan(struct ieee80211_local *local,
+				   struct ieee80211_sub_if_data *sdata)
 {
 	/* Software scan is not supported in multi-channel cases */
 	if (local->use_chanctx)
@@ -387,7 +407,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local)
 	 * nullfunc frames and probe requests will be dropped in
 	 * ieee80211_tx_h_check_assoc().
 	 */
-	drv_sw_scan_start(local);
+	drv_sw_scan_start(local, sdata, local->scan_addr);
 
 	local->leave_oper_channel_time = jiffies;
 	local->next_scan_state = SCAN_DECISION;
@@ -463,7 +483,7 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local,
 
 	for (i = 0; i < scan_req->n_ssids; i++)
 		ieee80211_send_probe_req(
-			sdata, NULL,
+			sdata, local->scan_addr, NULL,
 			scan_req->ssids[i].ssid, scan_req->ssids[i].ssid_len,
 			scan_req->ie, scan_req->ie_len,
 			scan_req->rates[band], false,
@@ -543,6 +563,13 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 	rcu_assign_pointer(local->scan_req, req);
 	rcu_assign_pointer(local->scan_sdata, sdata);
 
+	if (req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)
+		get_random_mask_addr(local->scan_addr,
+				     req->mac_addr,
+				     req->mac_addr_mask);
+	else
+		memcpy(local->scan_addr, sdata->vif.addr, ETH_ALEN);
+
 	if (local->ops->hw_scan) {
 		__set_bit(SCAN_HW_SCANNING, &local->scanning);
 	} else if ((req->n_channels == 1) &&
@@ -559,7 +586,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 
 		/* Notify driver scan is starting, keep order of operations
 		 * same as normal software scan, in case that matters. */
-		drv_sw_scan_start(local);
+		drv_sw_scan_start(local, sdata, local->scan_addr);
 
 		ieee80211_configure_filter(local); /* accept probe-responses */
 
@@ -589,8 +616,9 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 	if (local->ops->hw_scan) {
 		WARN_ON(!ieee80211_prep_hw_scan(local));
 		rc = drv_hw_scan(local, sdata, local->hw_scan_req);
-	} else
-		rc = ieee80211_start_sw_scan(local);
+	} else {
+		rc = ieee80211_start_sw_scan(local, sdata);
+	}
 
 	if (rc) {
 		kfree(local->hw_scan_req);
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 7f76e2f2574..eb91505eb43 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -596,14 +596,33 @@ DEFINE_EVENT(local_sdata_evt, drv_sched_scan_stop,
 	TP_ARGS(local, sdata)
 );
 
-DEFINE_EVENT(local_only_evt, drv_sw_scan_start,
-	TP_PROTO(struct ieee80211_local *local),
-	TP_ARGS(local)
+TRACE_EVENT(drv_sw_scan_start,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 const u8 *mac_addr),
+
+	TP_ARGS(local, sdata, mac_addr),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		__array(char, mac_addr, ETH_ALEN)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		memcpy(__entry->mac_addr, mac_addr, ETH_ALEN);
+	),
+
+	TP_printk(LOCAL_PR_FMT ", " VIF_PR_FMT ", addr:%pM",
+		  LOCAL_PR_ARG, VIF_PR_ARG, __entry->mac_addr)
 );
 
-DEFINE_EVENT(local_only_evt, drv_sw_scan_complete,
-	TP_PROTO(struct ieee80211_local *local),
-	TP_ARGS(local)
+DEFINE_EVENT(local_sdata_evt, drv_sw_scan_complete,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata),
+	TP_ARGS(local, sdata)
 );
 
 TRACE_EVENT(drv_get_stats,
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 0cb41d1a1f2..66ddbbeccd2 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -2961,19 +2961,16 @@ struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw,
 EXPORT_SYMBOL(ieee80211_nullfunc_get);
 
 struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw,
-				       struct ieee80211_vif *vif,
+				       const u8 *src_addr,
 				       const u8 *ssid, size_t ssid_len,
 				       size_t tailroom)
 {
-	struct ieee80211_sub_if_data *sdata;
-	struct ieee80211_local *local;
+	struct ieee80211_local *local = hw_to_local(hw);
 	struct ieee80211_hdr_3addr *hdr;
 	struct sk_buff *skb;
 	size_t ie_ssid_len;
 	u8 *pos;
 
-	sdata = vif_to_sdata(vif);
-	local = sdata->local;
 	ie_ssid_len = 2 + ssid_len;
 
 	skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*hdr) +
@@ -2988,7 +2985,7 @@ struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw,
 	hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
 					 IEEE80211_STYPE_PROBE_REQ);
 	eth_broadcast_addr(hdr->addr1);
-	memcpy(hdr->addr2, vif->addr, ETH_ALEN);
+	memcpy(hdr->addr2, src_addr, ETH_ALEN);
 	eth_broadcast_addr(hdr->addr3);
 
 	pos = skb_put(skb, ie_ssid_len);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 0ad534abc00..bb9664cb883 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1523,7 +1523,8 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer,
 };
 
 struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
-					  u8 *dst, u32 ratemask,
+					  const u8 *src, const u8 *dst,
+					  u32 ratemask,
 					  struct ieee80211_channel *chan,
 					  const u8 *ssid, size_t ssid_len,
 					  const u8 *ie, size_t ie_len,
@@ -1548,8 +1549,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 	else
 		chandef.chan = chan;
 
-	skb = ieee80211_probereq_get(&local->hw, &sdata->vif,
-				     ssid, ssid_len, 100 + ie_len);
+	skb = ieee80211_probereq_get(&local->hw, src, ssid, ssid_len,
+				     100 + ie_len);
 	if (!skb)
 		return NULL;
 
@@ -1571,7 +1572,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 	return skb;
 }
 
-void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst,
+void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata,
+			      const u8 *src, const u8 *dst,
 			      const u8 *ssid, size_t ssid_len,
 			      const u8 *ie, size_t ie_len,
 			      u32 ratemask, bool directed, u32 tx_flags,
@@ -1579,7 +1581,7 @@ void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst,
 {
 	struct sk_buff *skb;
 
-	skb = ieee80211_build_probe_req(sdata, dst, ratemask, channel,
+	skb = ieee80211_build_probe_req(sdata, src, dst, ratemask, channel,
 					ssid, ssid_len,
 					ie, ie_len, directed);
 	if (skb) {
-- 
cgit v1.2.3-70-g09d2


From 18e5ca65e55da4cacd9deb4e934eb5429bb4b79d Mon Sep 17 00:00:00 2001
From: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Date: Thu, 13 Nov 2014 17:25:14 +0200
Subject: nl80211: Replace interface socket owner attribute with more generic
 one

Replace NL80211_ATTR_IFACE_SOCKET_OWNER attribute with more generic
NL80211_ATTR_SOCKET_OWNER that can be used with other commands
that interface creation.

Signed-off-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 7 ++++---
 net/wireless/nl80211.c       | 4 ++--
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index a99081efc2d..d7752451043 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1652,9 +1652,9 @@ enum nl80211_commands {
  * @NL80211_ATTR_TDLS_PEER_CAPABILITY: flags for TDLS peer capabilities, u32.
  *	As specified in the &enum nl80211_tdls_peer_capability.
  *
- * @NL80211_ATTR_IFACE_SOCKET_OWNER: flag attribute, if set during interface
+ * @NL80211_ATTR_SOCKET_OWNER: Flag attribute, if set during interface
  *	creation then the new interface will be owned by the netlink socket
- *	that created it and will be destroyed when the socket is closed
+ *	that created it and will be destroyed when the socket is closed.
  *
  * @NL80211_ATTR_TDLS_INITIATOR: flag attribute indicating the current end is
  *	the TDLS link initiator.
@@ -2024,7 +2024,7 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_TDLS_PEER_CAPABILITY,
 
-	NL80211_ATTR_IFACE_SOCKET_OWNER,
+	NL80211_ATTR_SOCKET_OWNER,
 
 	NL80211_ATTR_CSA_C_OFFSETS_TX,
 	NL80211_ATTR_MAX_CSA_COUNTERS,
@@ -2055,6 +2055,7 @@ enum nl80211_attrs {
 /* source-level API compatibility */
 #define NL80211_ATTR_SCAN_GENERATION NL80211_ATTR_GENERATION
 #define	NL80211_ATTR_MESH_PARAMS NL80211_ATTR_MESH_CONFIG
+#define NL80211_ATTR_IFACE_SOCKET_OWNER NL80211_ATTR_SOCKET_OWNER
 
 /*
  * Allow user space programs to use #ifdef on new attributes by defining them
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 5cfd75dfff6..c81491b1f73 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -388,7 +388,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_MAC_HINT] = { .len = ETH_ALEN },
 	[NL80211_ATTR_WIPHY_FREQ_HINT] = { .type = NLA_U32 },
 	[NL80211_ATTR_TDLS_PEER_CAPABILITY] = { .type = NLA_U32 },
-	[NL80211_ATTR_IFACE_SOCKET_OWNER] = { .type = NLA_FLAG },
+	[NL80211_ATTR_SOCKET_OWNER] = { .type = NLA_FLAG },
 	[NL80211_ATTR_CSA_C_OFFSETS_TX] = { .type = NLA_BINARY },
 	[NL80211_ATTR_USE_RRM] = { .type = NLA_FLAG },
 	[NL80211_ATTR_TSID] = { .type = NLA_U8 },
@@ -2653,7 +2653,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 		return PTR_ERR(wdev);
 	}
 
-	if (info->attrs[NL80211_ATTR_IFACE_SOCKET_OWNER])
+	if (info->attrs[NL80211_ATTR_SOCKET_OWNER])
 		wdev->owner_nlportid = info->snd_portid;
 
 	switch (type) {
-- 
cgit v1.2.3-70-g09d2


From b5ae6b15bd73e35b129408755a0804287a87e041 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 12 Oct 2014 22:16:02 -0400
Subject: merge d_materialise_unique() into d_splice_alias()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 143 ++++++++++++-------------------------------------
 include/linux/dcache.h |   2 +-
 2 files changed, 36 insertions(+), 109 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index e605e90d0f0..435991eada1 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2575,11 +2575,11 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
  * Note: If ever the locking in lock_rename() changes, then please
  * remember to update this too...
  */
-static struct dentry *__d_unalias(struct inode *inode,
+static int __d_unalias(struct inode *inode,
 		struct dentry *dentry, struct dentry *alias)
 {
 	struct mutex *m1 = NULL, *m2 = NULL;
-	struct dentry *ret = ERR_PTR(-EBUSY);
+	int ret = -EBUSY;
 
 	/* If alias and dentry share a parent, then no extra locks required */
 	if (alias->d_parent == dentry->d_parent)
@@ -2594,7 +2594,7 @@ static struct dentry *__d_unalias(struct inode *inode,
 	m2 = &alias->d_parent->d_inode->i_mutex;
 out_unalias:
 	__d_move(alias, dentry, false);
-	ret = alias;
+	ret = 0;
 out_err:
 	spin_unlock(&inode->i_lock);
 	if (m2)
@@ -2629,130 +2629,57 @@ out_err:
  */
 struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
 {
-	struct dentry *new = NULL;
-
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
-	if (inode && S_ISDIR(inode->i_mode)) {
-		spin_lock(&inode->i_lock);
-		new = __d_find_any_alias(inode);
-		if (new) {
-			if (!IS_ROOT(new)) {
-				spin_unlock(&inode->i_lock);
-				dput(new);
-				iput(inode);
-				return ERR_PTR(-EIO);
-			}
-			if (d_ancestor(new, dentry)) {
-				spin_unlock(&inode->i_lock);
-				dput(new);
-				iput(inode);
-				return ERR_PTR(-EIO);
-			}
-			write_seqlock(&rename_lock);
-			__d_move(new, dentry, false);
-			write_sequnlock(&rename_lock);
-			spin_unlock(&inode->i_lock);
-			security_d_instantiate(new, inode);
-			iput(inode);
-		} else {
-			/* already taking inode->i_lock, so d_add() by hand */
-			__d_instantiate(dentry, inode);
-			spin_unlock(&inode->i_lock);
-			security_d_instantiate(dentry, inode);
-			d_rehash(dentry);
-		}
-	} else {
-		d_instantiate(dentry, inode);
-		if (d_unhashed(dentry))
-			d_rehash(dentry);
-	}
-	return new;
-}
-EXPORT_SYMBOL(d_splice_alias);
-
-/**
- * d_materialise_unique - introduce an inode into the tree
- * @dentry: candidate dentry
- * @inode: inode to bind to the dentry, to which aliases may be attached
- *
- * Introduces an dentry into the tree, substituting an extant disconnected
- * root directory alias in its place if there is one. Caller must hold the
- * i_mutex of the parent directory.
- */
-struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
-{
-	struct dentry *actual;
-
 	BUG_ON(!d_unhashed(dentry));
 
 	if (!inode) {
-		actual = dentry;
 		__d_instantiate(dentry, NULL);
-		d_rehash(actual);
-		goto out_nolock;
+		goto out;
 	}
-
 	spin_lock(&inode->i_lock);
-
 	if (S_ISDIR(inode->i_mode)) {
-		struct dentry *alias;
-
-		/* Does an aliased dentry already exist? */
-		alias = __d_find_alias(inode);
-		if (alias) {
-			actual = alias;
+		struct dentry *new = __d_find_any_alias(inode);
+		if (unlikely(new)) {
 			write_seqlock(&rename_lock);
-
-			if (d_ancestor(alias, dentry)) {
-				/* Check for loops */
-				actual = ERR_PTR(-ELOOP);
+			if (unlikely(d_ancestor(new, dentry))) {
+				write_sequnlock(&rename_lock);
 				spin_unlock(&inode->i_lock);
-			} else if (IS_ROOT(alias)) {
-				/* Is this an anonymous mountpoint that we
-				 * could splice into our tree? */
-				__d_move(alias, dentry, false);
+				dput(new);
+				new = ERR_PTR(-ELOOP);
+				pr_warn_ratelimited(
+					"VFS: Lookup of '%s' in %s %s"
+					" would have caused loop\n",
+					dentry->d_name.name,
+					inode->i_sb->s_type->name,
+					inode->i_sb->s_id);
+			} else if (!IS_ROOT(new)) {
+				int err = __d_unalias(inode, dentry, new);
 				write_sequnlock(&rename_lock);
-				goto found;
+				if (err) {
+					dput(new);
+					new = ERR_PTR(err);
+				}
 			} else {
-				/* Nope, but we must(!) avoid directory
-				 * aliasing. This drops inode->i_lock */
-				actual = __d_unalias(inode, dentry, alias);
-			}
-			write_sequnlock(&rename_lock);
-			if (IS_ERR(actual)) {
-				if (PTR_ERR(actual) == -ELOOP)
-					pr_warn_ratelimited(
-						"VFS: Lookup of '%s' in %s %s"
-						" would have caused loop\n",
-						dentry->d_name.name,
-						inode->i_sb->s_type->name,
-						inode->i_sb->s_id);
-				dput(alias);
+				__d_move(new, dentry, false);
+				write_sequnlock(&rename_lock);
+				spin_unlock(&inode->i_lock);
+				security_d_instantiate(new, inode);
 			}
-			goto out_nolock;
+			iput(inode);
+			return new;
 		}
 	}
-
-	/* Add a unique reference */
-	actual = __d_instantiate_unique(dentry, inode);
-	if (!actual)
-		actual = dentry;
-
-	d_rehash(actual);
-found:
+	/* already taking inode->i_lock, so d_add() by hand */
+	__d_instantiate(dentry, inode);
 	spin_unlock(&inode->i_lock);
-out_nolock:
-	if (actual == dentry) {
-		security_d_instantiate(dentry, inode);
-		return NULL;
-	}
-
-	iput(inode);
-	return actual;
+out:
+	security_d_instantiate(dentry, inode);
+	d_rehash(dentry);
+	return NULL;
 }
-EXPORT_SYMBOL_GPL(d_materialise_unique);
+EXPORT_SYMBOL(d_splice_alias);
 
 static int prepend(char **buffer, int *buflen, const char *str, int namelen)
 {
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 1c2f1b84468..ee569da27b7 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -230,7 +230,7 @@ extern seqlock_t rename_lock;
  */
 extern void d_instantiate(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
-extern struct dentry * d_materialise_unique(struct dentry *, struct inode *);
+#define d_materialise_unique(d, i) d_splice_alias(i, d)
 extern int d_instantiate_no_diralias(struct dentry *, struct inode *);
 extern void __d_drop(struct dentry *dentry);
 extern void d_drop(struct dentry *dentry);
-- 
cgit v1.2.3-70-g09d2


From 41d28bca2da4bd75a8915c1ccf2cacf7f4a2e531 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 12 Oct 2014 22:24:21 -0400
Subject: switch d_materialise_unique() users to d_splice_alias()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/nfs/Exporting | 23 +++++------------------
 Documentation/filesystems/porting       |  4 ++++
 fs/9p/vfs_inode.c                       |  2 +-
 fs/btrfs/inode.c                        |  2 +-
 fs/ceph/inode.c                         |  2 +-
 fs/cifs/readdir.c                       |  2 +-
 fs/fuse/dir.c                           |  4 ++--
 fs/kernfs/dir.c                         |  2 +-
 fs/nfs/dir.c                            |  4 ++--
 fs/nfs/getroot.c                        |  2 +-
 include/linux/dcache.h                  |  1 -
 11 files changed, 19 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/nfs/Exporting b/Documentation/filesystems/nfs/Exporting
index c8f036a9b13..520a4becb75 100644
--- a/Documentation/filesystems/nfs/Exporting
+++ b/Documentation/filesystems/nfs/Exporting
@@ -72,24 +72,11 @@ c/ Helper routines to allocate anonymous dentries, and to help attach
         DCACHE_DISCONNECTED) dentry is allocated and attached.
       In the case of a directory, care is taken that only one dentry
       can ever be attached.
-    d_splice_alias(inode, dentry) or d_materialise_unique(dentry, inode)
-      will introduce a new dentry into the tree; either the passed-in
-      dentry or a preexisting alias for the given inode (such as an
-      anonymous one created by d_obtain_alias), if appropriate.  The two
-      functions differ in their handling of directories with preexisting
-      aliases:
-        d_splice_alias will use any existing IS_ROOT dentry, but it will
-	  return -EIO rather than try to move a dentry with a different
-	  parent.  This is appropriate for local filesystems, which
-	  should never see such an alias unless the filesystem is
-	  corrupted somehow (for example, if two on-disk directory
-	  entries refer to the same directory.)
-	d_materialise_unique will attempt to move any dentry.  This is
-	  appropriate for distributed filesystems, where finding a
-	  directory other than where we last cached it may be a normal
-	  consequence of concurrent operations on other hosts.
-      Both functions return NULL when the passed-in dentry is used,
-      following the calling convention of ->lookup.
+    d_splice_alias(inode, dentry) will introduce a new dentry into the tree;
+      either the passed-in dentry or a preexisting alias for the given inode
+      (such as an anonymous one created by d_obtain_alias), if appropriate.
+      It returns NULL when the passed-in dentry is used, following the calling
+      convention of ->lookup.
 
  
 Filesystem Issues
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 0f3a1390bf0..b6b55a9cffe 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -463,3 +463,7 @@ in your dentry operations instead.
 	of the in-tree instances did).  inode_hash_lock is still held,
 	of course, so they are still serialized wrt removal from inode hash,
 	as well as wrt set() callback of iget5_locked().
+--
+[mandatory]
+	d_materialise_unique() is gone; d_splice_alias() does everything you
+	need now.  Remember that they have opposite orders of arguments ;-/
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 296482fc77a..9ee5343d488 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -832,7 +832,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	 * moved b under k and client parallely did a lookup for
 	 * k/b.
 	 */
-	res = d_materialise_unique(dentry, inode);
+	res = d_splice_alias(inode, dentry);
 	if (!res)
 		v9fs_fid_add(dentry, fid);
 	else if (!IS_ERR(res))
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d23362f4464..ff0dcc016b7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5303,7 +5303,7 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
 			return ERR_CAST(inode);
 	}
 
-	return d_materialise_unique(dentry, inode);
+	return d_splice_alias(inode, dentry);
 }
 
 unsigned char btrfs_filetype_table[] = {
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 7a1df90c777..90ec8e32c13 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -967,7 +967,7 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
 	/* dn must be unhashed */
 	if (!d_unhashed(dn))
 		d_drop(dn);
-	realdn = d_materialise_unique(dn, in);
+	realdn = d_splice_alias(in, dn);
 	if (IS_ERR(realdn)) {
 		pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
 		       PTR_ERR(realdn), dn, in, ceph_vinop(in));
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 8fd2a95860b..586e3d3b204 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -123,7 +123,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
 	if (!inode)
 		goto out;
 
-	alias = d_materialise_unique(dentry, inode);
+	alias = d_splice_alias(inode, dentry);
 	if (alias && !IS_ERR(alias))
 		dput(alias);
 out:
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index dbab798f5ca..df562cc8776 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -372,7 +372,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 	if (inode && get_node_id(inode) == FUSE_ROOT_ID)
 		goto out_iput;
 
-	newent = d_materialise_unique(entry, inode);
+	newent = d_splice_alias(inode, entry);
 	err = PTR_ERR(newent);
 	if (IS_ERR(newent))
 		goto out_err;
@@ -1320,7 +1320,7 @@ static int fuse_direntplus_link(struct file *file,
 	if (!inode)
 		goto out;
 
-	alias = d_materialise_unique(dentry, inode);
+	alias = d_splice_alias(inode, dentry);
 	err = PTR_ERR(alias);
 	if (IS_ERR(alias))
 		goto out;
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 1c771931bb6..37989f02a22 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -807,7 +807,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir,
 	}
 
 	/* instantiate and hash dentry */
-	ret = d_materialise_unique(dentry, inode);
+	ret = d_splice_alias(inode, dentry);
  out_unlock:
 	mutex_unlock(&kernfs_mutex);
 	return ret;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 06e8cfcbb67..44d7d0c7e37 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -499,7 +499,7 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 	if (IS_ERR(inode))
 		goto out;
 
-	alias = d_materialise_unique(dentry, inode);
+	alias = d_splice_alias(inode, dentry);
 	if (IS_ERR(alias))
 		goto out;
 	else if (alias) {
@@ -1393,7 +1393,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
 	nfs_advise_use_readdirplus(dir);
 
 no_entry:
-	res = d_materialise_unique(dentry, inode);
+	res = d_splice_alias(inode, dentry);
 	if (res != NULL) {
 		if (IS_ERR(res))
 			goto out_unblock_sillyrename;
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index ebc6a0add5a..9ac3846cb59 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -51,7 +51,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i
 		/*
 		 * Ensure that this dentry is invisible to d_find_alias().
 		 * Otherwise, it may be spliced into the tree by
-		 * d_materialise_unique if a parent directory from the same
+		 * d_splice_alias if a parent directory from the same
 		 * filesystem gets mounted at a later time.
 		 * This again causes shrink_dcache_for_umount_subtree() to
 		 * Oops, since the test for IS_ROOT() will fail.
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index ee569da27b7..5a813988e6d 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -230,7 +230,6 @@ extern seqlock_t rename_lock;
  */
 extern void d_instantiate(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
-#define d_materialise_unique(d, i) d_splice_alias(i, d)
 extern int d_instantiate_no_diralias(struct dentry *, struct inode *);
 extern void __d_drop(struct dentry *dentry);
 extern void d_drop(struct dentry *dentry);
-- 
cgit v1.2.3-70-g09d2


From b583043e99bc6d91e98fae32bd9eff6a5958240a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 31 Oct 2014 01:22:04 -0400
Subject: kill f_dentry uses

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/block/drbd/drbd_debugfs.c          |  6 +++---
 drivers/scsi/lpfc/lpfc_debugfs.c           |  4 ++--
 drivers/staging/lustre/lustre/llite/file.c | 12 +++---------
 fs/ceph/dir.c                              |  6 +++---
 fs/ceph/file.c                             |  2 +-
 fs/cifs/readdir.c                          |  2 +-
 fs/ecryptfs/crypto.c                       |  2 +-
 fs/ecryptfs/mmap.c                         |  2 +-
 fs/efivarfs/file.c                         |  4 ++--
 fs/sync.c                                  |  2 +-
 include/linux/cgroup.h                     |  4 ++--
 kernel/auditsc.c                           |  2 +-
 kernel/events/core.c                       |  2 +-
 kernel/taskstats.c                         |  2 +-
 mm/memcontrol.c                            |  4 ++--
 security/commoncap.c                       |  2 +-
 security/integrity/ima/ima_api.c           |  4 ++--
 security/integrity/ima/ima_appraise.c      |  4 ++--
 security/integrity/ima/ima_template_lib.c  |  2 +-
 19 files changed, 31 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c
index 900d4d3272d..9a950022ff8 100644
--- a/drivers/block/drbd/drbd_debugfs.c
+++ b/drivers/block/drbd/drbd_debugfs.c
@@ -419,7 +419,7 @@ static int in_flight_summary_show(struct seq_file *m, void *pos)
 	return 0;
 }
 
-/* simple_positive(file->f_dentry) respectively debugfs_positive(),
+/* simple_positive(file->f_path.dentry) respectively debugfs_positive(),
  * but neither is "reachable" from here.
  * So we have our own inline version of it above.  :-( */
 static inline int debugfs_positive(struct dentry *dentry)
@@ -437,14 +437,14 @@ static int drbd_single_open(struct file *file, int (*show)(struct seq_file *, vo
 
 	/* Are we still linked,
 	 * or has debugfs_remove() already been called? */
-	parent = file->f_dentry->d_parent;
+	parent = file->f_path.dentry->d_parent;
 	/* not sure if this can happen: */
 	if (!parent || !parent->d_inode)
 		goto out;
 	/* serialize with d_delete() */
 	mutex_lock(&parent->d_inode->i_mutex);
 	/* Make sure the object is still alive */
-	if (debugfs_positive(file->f_dentry)
+	if (debugfs_positive(file->f_path.dentry)
 	&& kref_get_unless_zero(kref))
 		ret = 0;
 	mutex_unlock(&parent->d_inode->i_mutex);
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 1311ab15243..5633e7dadc0 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -1011,7 +1011,7 @@ static ssize_t
 lpfc_debugfs_dif_err_read(struct file *file, char __user *buf,
 	size_t nbytes, loff_t *ppos)
 {
-	struct dentry *dent = file->f_dentry;
+	struct dentry *dent = file->f_path.dentry;
 	struct lpfc_hba *phba = file->private_data;
 	char cbuf[32];
 	uint64_t tmp = 0;
@@ -1052,7 +1052,7 @@ static ssize_t
 lpfc_debugfs_dif_err_write(struct file *file, const char __user *buf,
 	size_t nbytes, loff_t *ppos)
 {
-	struct dentry *dent = file->f_dentry;
+	struct dentry *dent = file->f_path.dentry;
 	struct lpfc_hba *phba = file->private_data;
 	char dstbuf[32];
 	uint64_t tmp = 0;
diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c
index c99b7411715..08e77492da8 100644
--- a/drivers/staging/lustre/lustre/llite/file.c
+++ b/drivers/staging/lustre/lustre/llite/file.c
@@ -2092,7 +2092,7 @@ putgl:
 	rc = 0;
 	if (llss->ia2.ia_valid != 0) {
 		mutex_lock(&llss->inode1->i_mutex);
-		rc = ll_setattr(file1->f_dentry, &llss->ia2);
+		rc = ll_setattr(file1->f_path.dentry, &llss->ia2);
 		mutex_unlock(&llss->inode1->i_mutex);
 	}
 
@@ -2100,7 +2100,7 @@ putgl:
 		int rc1;
 
 		mutex_lock(&llss->inode2->i_mutex);
-		rc1 = ll_setattr(file2->f_dentry, &llss->ia1);
+		rc1 = ll_setattr(file2->f_path.dentry, &llss->ia1);
 		mutex_unlock(&llss->inode2->i_mutex);
 		if (rc == 0)
 			rc = rc1;
@@ -2185,7 +2185,7 @@ static int ll_hsm_import(struct inode *inode, struct file *file,
 
 	mutex_lock(&inode->i_mutex);
 
-	rc = ll_setattr_raw(file->f_dentry, attr, true);
+	rc = ll_setattr_raw(file->f_path.dentry, attr, true);
 	if (rc == -ENODATA)
 		rc = 0;
 
@@ -2622,12 +2622,6 @@ int cl_sync_file_range(struct inode *inode, loff_t start, loff_t end,
 	return result;
 }
 
-/*
- * When dentry is provided (the 'else' case), *file->f_dentry may be
- * null and dentry must be used directly rather than pulled from
- * *file->f_dentry as is done otherwise.
- */
-
 int ll_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct dentry *dentry = file->f_dentry;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 766ec35f988..681a8537b64 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -123,7 +123,7 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 			    u32 shared_gen)
 {
 	struct ceph_file_info *fi = file->private_data;
-	struct dentry *parent = file->f_dentry;
+	struct dentry *parent = file->f_path.dentry;
 	struct inode *dir = parent->d_inode;
 	struct list_head *p;
 	struct dentry *dentry, *last;
@@ -274,7 +274,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 		off = 1;
 	}
 	if (ctx->pos == 1) {
-		ino_t ino = parent_ino(file->f_dentry);
+		ino_t ino = parent_ino(file->f_path.dentry);
 		dout("readdir off 1 -> '..'\n");
 		if (!dir_emit(ctx, "..", 2,
 			    ceph_translate_ino(inode->i_sb, ino),
@@ -337,7 +337,7 @@ more:
 		}
 		req->r_inode = inode;
 		ihold(inode);
-		req->r_dentry = dget(file->f_dentry);
+		req->r_dentry = dget(file->f_path.dentry);
 		/* hints to request -> mds selection code */
 		req->r_direct_mode = USE_AUTH_MDS;
 		req->r_direct_hash = ceph_frag_value(frag);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index db2c967950f..9f8e3572040 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -211,7 +211,7 @@ int ceph_open(struct inode *inode, struct file *file)
 
 	req->r_num_caps = 1;
 	if (flags & O_CREAT)
-		parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
+		parent_inode = ceph_get_dentry_parent_inode(file->f_path.dentry);
 	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
 	iput(parent_inode);
 	if (!err)
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index d19f1996a6e..d116ca8ce4c 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -753,7 +753,7 @@ static int cifs_filldir(char *find_entry, struct file *file,
 		 */
 		fattr.cf_flags |= CIFS_FATTR_NEED_REVAL;
 
-	cifs_prime_dcache(file->f_dentry, &name, &fattr);
+	cifs_prime_dcache(file->f_path.dentry, &name, &fattr);
 
 	ino = cifs_uniqueid_to_ino_t(fattr.cf_uniqueid);
 	return !dir_emit(ctx, name.name, name.len, ino, fattr.cf_dtype);
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 2f6735dbf1a..c2d6604667b 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1373,7 +1373,7 @@ out:
 int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode)
 {
 	struct dentry *lower_dentry =
-		ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_dentry;
+		ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_path.dentry;
 	ssize_t size;
 	int rc = 0;
 
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 564a1fa34b9..4626976794e 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -419,7 +419,7 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode)
 	ssize_t size;
 	void *xattr_virt;
 	struct dentry *lower_dentry =
-		ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_dentry;
+		ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_path.dentry;
 	struct inode *lower_inode = lower_dentry->d_inode;
 	int rc;
 
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index cdb2971192a..90001da9abf 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -47,8 +47,8 @@ static ssize_t efivarfs_file_write(struct file *file,
 
 	if (bytes == -ENOENT) {
 		drop_nlink(inode);
-		d_delete(file->f_dentry);
-		dput(file->f_dentry);
+		d_delete(file->f_path.dentry);
+		dput(file->f_path.dentry);
 	} else {
 		mutex_lock(&inode->i_mutex);
 		i_size_write(inode, datasize + sizeof(attributes));
diff --git a/fs/sync.c b/fs/sync.c
index bdc729d80e5..01d9f18a70b 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -154,7 +154,7 @@ SYSCALL_DEFINE1(syncfs, int, fd)
 
 	if (!f.file)
 		return -EBADF;
-	sb = f.file->f_dentry->d_sb;
+	sb = f.file->f_path.dentry->d_sb;
 
 	down_read(&sb->s_umount);
 	ret = sync_filesystem(sb);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 1d519688904..27b0c9105da 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -367,8 +367,8 @@ struct css_set {
  * struct cftype: handler definitions for cgroup control files
  *
  * When reading/writing to a file:
- *	- the cgroup to use is file->f_dentry->d_parent->d_fsdata
- *	- the 'cftype' of the file is file->f_dentry->d_fsdata
+ *	- the cgroup to use is file->f_path.dentry->d_parent->d_fsdata
+ *	- the 'cftype' of the file is file->f_path.dentry->d_fsdata
  */
 
 /* cftype->flags */
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index e420a0c41b5..06820657c8c 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2373,7 +2373,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
 	ax->d.next = context->aux;
 	context->aux = (void *)ax;
 
-	dentry = dget(bprm->file->f_dentry);
+	dentry = dget(bprm->file->f_path.dentry);
 	get_vfs_caps_from_disk(dentry, &vcaps);
 	dput(dentry);
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1425d07018d..446fbeefad1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -614,7 +614,7 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 	if (!f.file)
 		return -EBADF;
 
-	css = css_tryget_online_from_dir(f.file->f_dentry,
+	css = css_tryget_online_from_dir(f.file->f_path.dentry,
 					 &perf_event_cgrp_subsys);
 	if (IS_ERR(css)) {
 		ret = PTR_ERR(css);
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index b312fcc7302..670fff88a96 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -459,7 +459,7 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 	stats = nla_data(na);
 	memset(stats, 0, sizeof(*stats));
 
-	rc = cgroupstats_build(stats, f.file->f_dentry);
+	rc = cgroupstats_build(stats, f.file->f_path.dentry);
 	if (rc < 0) {
 		nlmsg_free(rep_skb);
 		goto err;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 23976fd885f..8c3385181b1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5055,7 +5055,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 	 *
 	 * DO NOT ADD NEW FILES.
 	 */
-	name = cfile.file->f_dentry->d_name.name;
+	name = cfile.file->f_path.dentry->d_name.name;
 
 	if (!strcmp(name, "memory.usage_in_bytes")) {
 		event->register_event = mem_cgroup_usage_register_event;
@@ -5079,7 +5079,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 	 * automatically removed on cgroup destruction but the removal is
 	 * asynchronous, so take an extra ref on @css.
 	 */
-	cfile_css = css_tryget_online_from_dir(cfile.file->f_dentry->d_parent,
+	cfile_css = css_tryget_online_from_dir(cfile.file->f_path.dentry->d_parent,
 					       &memory_cgrp_subsys);
 	ret = -EINVAL;
 	if (IS_ERR(cfile_css))
diff --git a/security/commoncap.c b/security/commoncap.c
index bab0611afc1..2915d850305 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -446,7 +446,7 @@ static int get_file_caps(struct linux_binprm *bprm, bool *effective, bool *has_c
 	if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
 		return 0;
 
-	dentry = dget(bprm->file->f_dentry);
+	dentry = dget(bprm->file->f_path.dentry);
 
 	rc = get_vfs_caps_from_disk(dentry, &vcaps);
 	if (rc < 0) {
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index 86885979918..f92be1b1408 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -196,7 +196,7 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 {
 	const char *audit_cause = "failed";
 	struct inode *inode = file_inode(file);
-	const char *filename = file->f_dentry->d_name.name;
+	const char *filename = file->f_path.dentry->d_name.name;
 	int result = 0;
 	struct {
 		struct ima_digest_data hdr;
@@ -204,7 +204,7 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 	} hash;
 
 	if (xattr_value)
-		*xattr_len = ima_read_xattr(file->f_dentry, xattr_value);
+		*xattr_len = ima_read_xattr(file->f_path.dentry, xattr_value);
 
 	if (!(iint->flags & IMA_COLLECTED)) {
 		u64 i_version = file_inode(file)->i_version;
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 922685483bd..c2f203accbd 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -189,7 +189,7 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 {
 	static const char op[] = "appraise_data";
 	char *cause = "unknown";
-	struct dentry *dentry = file->f_dentry;
+	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	enum integrity_status status = INTEGRITY_UNKNOWN;
 	int rc = xattr_len, hash_start = 0;
@@ -289,7 +289,7 @@ out:
  */
 void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file)
 {
-	struct dentry *dentry = file->f_dentry;
+	struct dentry *dentry = file->f_path.dentry;
 	int rc = 0;
 
 	/* do not collect and update hash for digital signatures */
diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c
index 1506f024857..bcfc36cbde6 100644
--- a/security/integrity/ima/ima_template_lib.c
+++ b/security/integrity/ima/ima_template_lib.c
@@ -284,7 +284,7 @@ static int ima_eventname_init_common(struct integrity_iint_cache *iint,
 	}
 
 	if (file) {
-		cur_filename = file->f_dentry->d_name.name;
+		cur_filename = file->f_path.dentry->d_name.name;
 		cur_filename_len = strlen(cur_filename);
 	} else
 		/*
-- 
cgit v1.2.3-70-g09d2


From 9f45f5bf302daad6835ce64701fb3c286a2cc6af Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 31 Oct 2014 17:44:57 -0400
Subject: new helper: audit_file()

... for situations when we don't have any candidate in pathnames - basically,
in descriptor-based syscalls.

[Folded the build fix for !CONFIG_AUDITSYSCALL configs from Chen Gang]

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/open.c             |  4 ++--
 fs/xattr.c            | 16 ++++++----------
 include/linux/audit.h |  9 +++++++++
 ipc/mqueue.c          |  4 ++--
 kernel/auditsc.c      |  5 +++++
 5 files changed, 24 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/fs/open.c b/fs/open.c
index de92c13b58b..b1bf3d542d5 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -516,7 +516,7 @@ SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
 	int err = -EBADF;
 
 	if (f.file) {
-		audit_inode(NULL, f.file->f_path.dentry, 0);
+		audit_file(f.file);
 		err = chmod_common(&f.file->f_path, mode);
 		fdput(f);
 	}
@@ -642,7 +642,7 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
 	error = mnt_want_write_file(f.file);
 	if (error)
 		goto out_fput;
-	audit_inode(NULL, f.file->f_path.dentry, 0);
+	audit_file(f.file);
 	error = chown_common(&f.file->f_path, user, group);
 	mnt_drop_write_file(f.file);
 out_fput:
diff --git a/fs/xattr.c b/fs/xattr.c
index 64e83efb742..4ef698549e3 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -405,16 +405,14 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
 		const void __user *,value, size_t, size, int, flags)
 {
 	struct fd f = fdget(fd);
-	struct dentry *dentry;
 	int error = -EBADF;
 
 	if (!f.file)
 		return error;
-	dentry = f.file->f_path.dentry;
-	audit_inode(NULL, dentry, 0);
+	audit_file(f.file);
 	error = mnt_want_write_file(f.file);
 	if (!error) {
-		error = setxattr(dentry, name, value, size, flags);
+		error = setxattr(f.file->f_path.dentry, name, value, size, flags);
 		mnt_drop_write_file(f.file);
 	}
 	fdput(f);
@@ -509,7 +507,7 @@ SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name,
 
 	if (!f.file)
 		return error;
-	audit_inode(NULL, f.file->f_path.dentry, 0);
+	audit_file(f.file);
 	error = getxattr(f.file->f_path.dentry, name, value, size);
 	fdput(f);
 	return error;
@@ -590,7 +588,7 @@ SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
 
 	if (!f.file)
 		return error;
-	audit_inode(NULL, f.file->f_path.dentry, 0);
+	audit_file(f.file);
 	error = listxattr(f.file->f_path.dentry, list, size);
 	fdput(f);
 	return error;
@@ -651,16 +649,14 @@ SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
 SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
 {
 	struct fd f = fdget(fd);
-	struct dentry *dentry;
 	int error = -EBADF;
 
 	if (!f.file)
 		return error;
-	dentry = f.file->f_path.dentry;
-	audit_inode(NULL, dentry, 0);
+	audit_file(f.file);
 	error = mnt_want_write_file(f.file);
 	if (!error) {
-		error = removexattr(dentry, name);
+		error = removexattr(f.file->f_path.dentry, name);
 		mnt_drop_write_file(f.file);
 	}
 	fdput(f);
diff --git a/include/linux/audit.h b/include/linux/audit.h
index e58fe7df8b9..0c04917c2f1 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -130,6 +130,7 @@ extern void audit_putname(struct filename *name);
 #define AUDIT_INODE_HIDDEN	2	/* audit record should be hidden */
 extern void __audit_inode(struct filename *name, const struct dentry *dentry,
 				unsigned int flags);
+extern void __audit_file(const struct file *);
 extern void __audit_inode_child(const struct inode *parent,
 				const struct dentry *dentry,
 				const unsigned char type);
@@ -183,6 +184,11 @@ static inline void audit_inode(struct filename *name,
 		__audit_inode(name, dentry, flags);
 	}
 }
+static inline void audit_file(struct file *file)
+{
+	if (unlikely(!audit_dummy_context()))
+		__audit_file(file);
+}
 static inline void audit_inode_parent_hidden(struct filename *name,
 						const struct dentry *dentry)
 {
@@ -357,6 +363,9 @@ static inline void audit_inode(struct filename *name,
 				const struct dentry *dentry,
 				unsigned int parent)
 { }
+static inline void audit_file(struct file *file)
+{
+}
 static inline void audit_inode_parent_hidden(struct filename *name,
 				const struct dentry *dentry)
 { }
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 4fcf39af177..7635a1cf99f 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -990,7 +990,7 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
 		goto out_fput;
 	}
 	info = MQUEUE_I(inode);
-	audit_inode(NULL, f.file->f_path.dentry, 0);
+	audit_file(f.file);
 
 	if (unlikely(!(f.file->f_mode & FMODE_WRITE))) {
 		ret = -EBADF;
@@ -1106,7 +1106,7 @@ SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
 		goto out_fput;
 	}
 	info = MQUEUE_I(inode);
-	audit_inode(NULL, f.file->f_path.dentry, 0);
+	audit_file(f.file);
 
 	if (unlikely(!(f.file->f_mode & FMODE_READ))) {
 		ret = -EBADF;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 06820657c8c..c75522a8367 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1897,6 +1897,11 @@ out:
 	audit_copy_inode(n, dentry, inode);
 }
 
+void __audit_file(const struct file *file)
+{
+	__audit_inode(NULL, file->f_path.dentry, 0);
+}
+
 /**
  * __audit_inode_child - collect inode info for created/removed objects
  * @parent: inode of dentry parent
-- 
cgit v1.2.3-70-g09d2


From 78d28e651f97866d608d9b41f8ad291e65d47dd5 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 31 Oct 2014 01:22:04 -0400
Subject: kill f_dentry macro

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/porting | 4 ++++
 include/linux/fs.h                | 1 -
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index b6b55a9cffe..fa2db081505 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -467,3 +467,7 @@ in your dentry operations instead.
 [mandatory]
 	d_materialise_unique() is gone; d_splice_alias() does everything you
 	need now.  Remember that they have opposite orders of arguments ;-/
+--
+[mandatory]
+	f_dentry is gone; use f_path.dentry, or, better yet, see if you can avoid
+	it entirely.
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1c12c681803..1a8bb3c023a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -789,7 +789,6 @@ struct file {
 		struct rcu_head 	fu_rcuhead;
 	} f_u;
 	struct path		f_path;
-#define f_dentry	f_path.dentry
 	struct inode		*f_inode;	/* cached value */
 	const struct file_operations	*f_op;
 
-- 
cgit v1.2.3-70-g09d2


From f815e2b3c0126c26911cac72b837f03a31c0c2ed Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 19 Nov 2014 00:10:42 +0100
Subject: mac80211: notify drivers on sta rate table changes

This allows drivers with a firmware or chip-based rate lookup table to
use the most recent default rate selection without having to get it from
per-packet data or explicit ieee80211_get_tx_rate calls

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    |  6 ++++++
 net/mac80211/driver-ops.h | 15 +++++++++++++++
 net/mac80211/rate.c       |  3 +++
 net/mac80211/trace.h      |  7 +++++++
 4 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 7b889e3a264..cff3a26a9da 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2695,6 +2695,9 @@ enum ieee80211_reconfig_type {
  *	uses hardware rate control (%IEEE80211_HW_HAS_RATE_CONTROL) since
  *	otherwise the rate control algorithm is notified directly.
  *	Must be atomic.
+ * @sta_rate_tbl_update: Notifies the driver that the rate table changed. This
+ *	is only used if the configured rate control algorithm actually uses
+ *	the new rate table API, and is therefore optional. Must be atomic.
  *
  * @conf_tx: Configure TX queue parameters (EDCF (aifs, cw_min, cw_max),
  *	bursting) for a hardware TX queue.
@@ -3056,6 +3059,9 @@ struct ieee80211_ops {
 			      struct ieee80211_vif *vif,
 			      struct ieee80211_sta *sta,
 			      u32 changed);
+	void (*sta_rate_tbl_update)(struct ieee80211_hw *hw,
+				    struct ieee80211_vif *vif,
+				    struct ieee80211_sta *sta);
 	int (*conf_tx)(struct ieee80211_hw *hw,
 		       struct ieee80211_vif *vif, u16 ac,
 		       const struct ieee80211_tx_queue_params *params);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 5f5fc3f3ee7..2ebc9ead969 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -624,6 +624,21 @@ static inline void drv_sta_rc_update(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
+static inline void drv_sta_rate_tbl_update(struct ieee80211_local *local,
+					   struct ieee80211_sub_if_data *sdata,
+					   struct ieee80211_sta *sta)
+{
+	sdata = get_bss_sdata(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
+
+	trace_drv_sta_rate_tbl_update(local, sdata, sta);
+	if (local->ops->sta_rate_tbl_update)
+		local->ops->sta_rate_tbl_update(&local->hw, &sdata->vif, sta);
+
+	trace_drv_return_void(local);
+}
+
 static inline int drv_conf_tx(struct ieee80211_local *local,
 			      struct ieee80211_sub_if_data *sdata, u16 ac,
 			      const struct ieee80211_tx_queue_params *params)
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index f6fea67fcc5..08ab7d6d151 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -696,6 +696,7 @@ int rate_control_set_rates(struct ieee80211_hw *hw,
 			   struct ieee80211_sta *pubsta,
 			   struct ieee80211_sta_rates *rates)
 {
+	struct sta_info *sta = container_of(pubsta, struct sta_info, sta);
 	struct ieee80211_sta_rates *old;
 
 	/*
@@ -709,6 +710,8 @@ int rate_control_set_rates(struct ieee80211_hw *hw,
 	if (old)
 		kfree_rcu(old, rcu_head);
 
+	drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta);
+
 	return 0;
 }
 EXPORT_SYMBOL(rate_control_set_rates);
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index eb91505eb43..85ccfbe863d 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -846,6 +846,13 @@ DEFINE_EVENT(sta_event, drv_sta_pre_rcu_remove,
 	TP_ARGS(local, sdata, sta)
 );
 
+DEFINE_EVENT(sta_event, drv_sta_rate_tbl_update,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_sta *sta),
+	TP_ARGS(local, sdata, sta)
+);
+
 TRACE_EVENT(drv_conf_tx,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
-- 
cgit v1.2.3-70-g09d2


From aec0be2d6e9f02dbef41ee54854c2e003e55c23e Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 18 Nov 2014 21:14:11 -0500
Subject: ftrace/x86/extable: Add is_ftrace_trampoline() function

Stack traces that happen from function tracing check if the address
on the stack is a __kernel_text_address(). That is, is the address
kernel code. This calls core_kernel_text() which returns true
if the address is part of the builtin kernel code. It also calls
is_module_text_address() which returns true if the address belongs
to module code.

But what is missing is ftrace dynamically allocated trampolines.
These trampolines are allocated for individual ftrace_ops that
call the ftrace_ops callback functions directly. But if they do a
stack trace, the code checking the stack wont detect them as they
are neither core kernel code nor module address space.

Adding another field to ftrace_ops that also stores the size of
the trampoline assigned to it we can create a new function called
is_ftrace_trampoline() that returns true if the address is a
dynamically allocate ftrace trampoline. Note, it ignores trampolines
that are not dynamically allocated as they will return true with
the core_kernel_text() function.

Link: http://lkml.kernel.org/r/20141119034829.497125839@goodmis.org

Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/x86/kernel/ftrace.c |  9 +++++++--
 include/linux/ftrace.h   |  8 ++++++++
 kernel/extable.c         |  7 ++++++-
 kernel/trace/ftrace.c    | 38 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 59 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 1aea94d336c..60881d91943 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -712,7 +712,8 @@ union ftrace_op_code_union {
 	} __attribute__((packed));
 };
 
-static unsigned long create_trampoline(struct ftrace_ops *ops)
+static unsigned long
+create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 {
 	unsigned const char *jmp;
 	unsigned long start_offset;
@@ -749,6 +750,8 @@ static unsigned long create_trampoline(struct ftrace_ops *ops)
 	if (!trampoline)
 		return 0;
 
+	*tramp_size = size + MCOUNT_INSN_SIZE + sizeof(void *);
+
 	/* Copy ftrace_caller onto the trampoline memory */
 	ret = probe_kernel_read(trampoline, (void *)start_offset, size);
 	if (WARN_ON(ret < 0)) {
@@ -819,6 +822,7 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
 	unsigned char *new;
 	unsigned long offset;
 	unsigned long ip;
+	unsigned int size;
 	int ret;
 
 	if (ops->trampoline) {
@@ -829,9 +833,10 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
 		if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
 			return;
 	} else {
-		ops->trampoline = create_trampoline(ops);
+		ops->trampoline = create_trampoline(ops, &size);
 		if (!ops->trampoline)
 			return;
+		ops->trampoline_size = size;
 	}
 
 	offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS);
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 619e37cc17f..7b2616fa247 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -150,6 +150,7 @@ struct ftrace_ops {
 	struct ftrace_ops_hash		*func_hash;
 	struct ftrace_ops_hash		old_hash;
 	unsigned long			trampoline;
+	unsigned long			trampoline_size;
 #endif
 };
 
@@ -297,6 +298,8 @@ extern int ftrace_text_reserved(const void *start, const void *end);
 
 extern int ftrace_nr_registered_ops(void);
 
+bool is_ftrace_trampoline(unsigned long addr);
+
 /*
  * The dyn_ftrace record's flags field is split into two parts.
  * the first part which is '0-FTRACE_REF_MAX' is a counter of
@@ -596,6 +599,11 @@ static inline ssize_t ftrace_notrace_write(struct file *file, const char __user
 			     size_t cnt, loff_t *ppos) { return -ENODEV; }
 static inline int
 ftrace_regex_release(struct inode *inode, struct file *file) { return -ENODEV; }
+
+static inline bool is_ftrace_trampoline(unsigned long addr)
+{
+	return false;
+}
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 /* totally disable ftrace - can not re-enable after this */
diff --git a/kernel/extable.c b/kernel/extable.c
index d8a6446adbc..c98f926277a 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -18,6 +18,7 @@
 #include <linux/ftrace.h>
 #include <linux/memory.h>
 #include <linux/module.h>
+#include <linux/ftrace.h>
 #include <linux/mutex.h>
 #include <linux/init.h>
 
@@ -102,6 +103,8 @@ int __kernel_text_address(unsigned long addr)
 		return 1;
 	if (is_module_text_address(addr))
 		return 1;
+	if (is_ftrace_trampoline(addr))
+		return 1;
 	/*
 	 * There might be init symbols in saved stacktraces.
 	 * Give those symbols a chance to be printed in
@@ -119,7 +122,9 @@ int kernel_text_address(unsigned long addr)
 {
 	if (core_kernel_text(addr))
 		return 1;
-	return is_module_text_address(addr);
+	if (is_module_text_address(addr))
+		return 1;
+	return is_ftrace_trampoline(addr);
 }
 
 /*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6233f910217..fa0f36bb32e 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1117,6 +1117,43 @@ static struct ftrace_ops global_ops = {
 					  FTRACE_OPS_FL_INITIALIZED,
 };
 
+/*
+ * This is used by __kernel_text_address() to return true if the
+ * the address is on a dynamically allocated trampoline that would
+ * not return true for either core_kernel_text() or
+ * is_module_text_address().
+ */
+bool is_ftrace_trampoline(unsigned long addr)
+{
+	struct ftrace_ops *op;
+	bool ret = false;
+
+	/*
+	 * Some of the ops may be dynamically allocated,
+	 * they are freed after a synchronize_sched().
+	 */
+	preempt_disable_notrace();
+
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
+		/*
+		 * This is to check for dynamically allocated trampolines.
+		 * Trampolines that are in kernel text will have
+		 * core_kernel_text() return true.
+		 */
+		if (op->trampoline && op->trampoline_size)
+			if (addr >= op->trampoline &&
+			    addr < op->trampoline + op->trampoline_size) {
+				ret = true;
+				goto out;
+			}
+	} while_for_each_ftrace_op(op);
+
+ out:
+	preempt_enable_notrace();
+
+	return ret;
+}
+
 struct ftrace_page {
 	struct ftrace_page	*next;
 	struct dyn_ftrace	*records;
@@ -5373,6 +5410,7 @@ static struct ftrace_ops graph_ops = {
 				   FTRACE_OPS_FL_STUB,
 #ifdef FTRACE_GRAPH_TRAMP_ADDR
 	.trampoline		= FTRACE_GRAPH_TRAMP_ADDR,
+	/* trampoline_size is only needed for dynamically allocated tramps */
 #endif
 	ASSIGN_OPS_HASH(graph_ops, &global_ops.local_hash)
 };
-- 
cgit v1.2.3-70-g09d2


From 19a7fe206232cc875a3083211e0a21c08edd756e Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 12 Nov 2014 10:29:54 -0500
Subject: tracing: Add trace_seq_has_overflowed() and trace_handle_return()

Adding a trace_seq_has_overflowed() which returns true if the trace_seq
had too much written into it allows us to simplify the code.

Instead of checking the return value of every call to trace_seq_printf()
and friends, they can all be called normally, and at the end we can
return !trace_seq_has_overflowed() instead.

Several functions also return TRACE_TYPE_PARTIAL_LINE when the trace_seq
overflowed and TRACE_TYPE_HANDLED otherwise. Another helper function
was created called trace_handle_return() which takes a trace_seq and
returns these enums. Using this helper function also simplifies the
code.

This change also makes it possible to remove the return values of
trace_seq_printf() and friends. They should instead just be
void functions.

Link: http://lkml.kernel.org/r/20141114011410.365183157@goodmis.org

Reviewed-by: Petr Mladek <pmladek@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h |  11 ++
 include/linux/trace_seq.h    |  12 ++
 include/trace/ftrace.h       |   6 +-
 kernel/trace/trace.c         |  69 +++----
 kernel/trace/trace.h         |   1 +
 kernel/trace/trace_output.c  | 416 +++++++++++++++++--------------------------
 kernel/trace/trace_output.h  |  16 +-
 7 files changed, 231 insertions(+), 300 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 28672e87e91..0bebb5c348b 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -138,6 +138,17 @@ enum print_line_t {
 	TRACE_TYPE_NO_CONSUME	= 3	/* Handled but ask to not consume */
 };
 
+/*
+ * Several functions return TRACE_TYPE_PARTIAL_LINE if the trace_seq
+ * overflowed, and TRACE_TYPE_HANDLED otherwise. This helper function
+ * simplifies those functions and keeps them in sync.
+ */
+static inline enum print_line_t trace_handle_return(struct trace_seq *s)
+{
+	return trace_seq_has_overflowed(s) ?
+		TRACE_TYPE_PARTIAL_LINE : TRACE_TYPE_HANDLED;
+}
+
 void tracing_generic_entry_update(struct trace_entry *entry,
 				  unsigned long flags,
 				  int pc);
diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
index ea6c9dea79e..07eda413dfc 100644
--- a/include/linux/trace_seq.h
+++ b/include/linux/trace_seq.h
@@ -40,6 +40,18 @@ trace_seq_buffer_ptr(struct trace_seq *s)
 	return s->buffer + s->len;
 }
 
+/**
+ * trace_seq_has_overflowed - return true if the trace_seq took too much
+ * @s: trace sequence descriptor
+ *
+ * Returns true if too much data was added to the trace_seq and it is
+ * now full and will not take anymore.
+ */
+static inline bool trace_seq_has_overflowed(struct trace_seq *s)
+{
+	return s->full || s->len > PAGE_SIZE - 1;
+}
+
 /*
  * Currently only defined when tracing is enabled.
  */
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 26b4f2e1327..f13471b5d27 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -280,11 +280,9 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags,	\
 	if (ret)							\
 		return ret;						\
 									\
-	ret = trace_seq_printf(s, print);				\
-	if (!ret)							\
-		return TRACE_TYPE_PARTIAL_LINE;				\
+	trace_seq_printf(s, print);					\
 									\
-	return TRACE_TYPE_HANDLED;					\
+	return trace_handle_return(s);					\
 }									\
 static struct trace_event_functions ftrace_event_type_funcs_##call = {	\
 	.trace			= ftrace_raw_output_##call,		\
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 44d56142670..3ce3c4ccfc9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2649,24 +2649,21 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 	event = ftrace_find_event(entry->type);
 
 	if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
-		if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
-			if (!trace_print_lat_context(iter))
-				goto partial;
-		} else {
-			if (!trace_print_context(iter))
-				goto partial;
-		}
+		if (iter->iter_flags & TRACE_FILE_LAT_FMT)
+			trace_print_lat_context(iter);
+		else
+			trace_print_context(iter);
 	}
 
+	if (trace_seq_has_overflowed(s))
+		return TRACE_TYPE_PARTIAL_LINE;
+
 	if (event)
 		return event->funcs->trace(iter, sym_flags, event);
 
-	if (!trace_seq_printf(s, "Unknown type %d\n", entry->type))
-		goto partial;
+	trace_seq_printf(s, "Unknown type %d\n", entry->type);
 
-	return TRACE_TYPE_HANDLED;
-partial:
-	return TRACE_TYPE_PARTIAL_LINE;
+	return trace_handle_return(s);
 }
 
 static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
@@ -2677,22 +2674,20 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
 
 	entry = iter->ent;
 
-	if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
-		if (!trace_seq_printf(s, "%d %d %llu ",
-				      entry->pid, iter->cpu, iter->ts))
-			goto partial;
-	}
+	if (trace_flags & TRACE_ITER_CONTEXT_INFO)
+		trace_seq_printf(s, "%d %d %llu ",
+				 entry->pid, iter->cpu, iter->ts);
+
+	if (trace_seq_has_overflowed(s))
+		return TRACE_TYPE_PARTIAL_LINE;
 
 	event = ftrace_find_event(entry->type);
 	if (event)
 		return event->funcs->raw(iter, 0, event);
 
-	if (!trace_seq_printf(s, "%d ?\n", entry->type))
-		goto partial;
+	trace_seq_printf(s, "%d ?\n", entry->type);
 
-	return TRACE_TYPE_HANDLED;
-partial:
-	return TRACE_TYPE_PARTIAL_LINE;
+	return trace_handle_return(s);
 }
 
 static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
@@ -2705,9 +2700,11 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 	entry = iter->ent;
 
 	if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
-		SEQ_PUT_HEX_FIELD_RET(s, entry->pid);
-		SEQ_PUT_HEX_FIELD_RET(s, iter->cpu);
-		SEQ_PUT_HEX_FIELD_RET(s, iter->ts);
+		SEQ_PUT_HEX_FIELD(s, entry->pid);
+		SEQ_PUT_HEX_FIELD(s, iter->cpu);
+		SEQ_PUT_HEX_FIELD(s, iter->ts);
+		if (trace_seq_has_overflowed(s))
+			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
 	event = ftrace_find_event(entry->type);
@@ -2717,9 +2714,9 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 			return ret;
 	}
 
-	SEQ_PUT_FIELD_RET(s, newline);
+	SEQ_PUT_FIELD(s, newline);
 
-	return TRACE_TYPE_HANDLED;
+	return trace_handle_return(s);
 }
 
 static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
@@ -2731,9 +2728,11 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
 	entry = iter->ent;
 
 	if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
-		SEQ_PUT_FIELD_RET(s, entry->pid);
-		SEQ_PUT_FIELD_RET(s, iter->cpu);
-		SEQ_PUT_FIELD_RET(s, iter->ts);
+		SEQ_PUT_FIELD(s, entry->pid);
+		SEQ_PUT_FIELD(s, iter->cpu);
+		SEQ_PUT_FIELD(s, iter->ts);
+		if (trace_seq_has_overflowed(s))
+			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
 	event = ftrace_find_event(entry->type);
@@ -2779,10 +2778,12 @@ enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
 	enum print_line_t ret;
 
-	if (iter->lost_events &&
-	    !trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
-				 iter->cpu, iter->lost_events))
-		return TRACE_TYPE_PARTIAL_LINE;
+	if (iter->lost_events) {
+		trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
+				 iter->cpu, iter->lost_events);
+		if (trace_seq_has_overflowed(&iter->seq))
+			return TRACE_TYPE_PARTIAL_LINE;
+	}
 
 	if (iter->trace && iter->trace->print_line) {
 		ret = iter->trace->print_line(iter);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 3376de623ea..19418221b30 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -14,6 +14,7 @@
 #include <linux/trace_seq.h>
 #include <linux/ftrace_event.h>
 #include <linux/compiler.h>
+#include <linux/trace_seq.h>
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 #include <asm/unistd.h>		/* For NR_SYSCALLS	     */
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index cfa91de22e2..163c11b6b8f 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -25,15 +25,12 @@ enum print_line_t trace_print_bputs_msg_only(struct trace_iterator *iter)
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry = iter->ent;
 	struct bputs_entry *field;
-	int ret;
 
 	trace_assign_type(field, entry);
 
-	ret = trace_seq_puts(s, field->str);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
+	trace_seq_puts(s, field->str);
 
-	return TRACE_TYPE_HANDLED;
+	return trace_handle_return(s);
 }
 
 enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
@@ -41,15 +38,12 @@ enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry = iter->ent;
 	struct bprint_entry *field;
-	int ret;
 
 	trace_assign_type(field, entry);
 
-	ret = trace_seq_bprintf(s, field->fmt, field->buf);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
+	trace_seq_bprintf(s, field->fmt, field->buf);
 
-	return TRACE_TYPE_HANDLED;
+	return trace_handle_return(s);
 }
 
 enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter)
@@ -57,15 +51,12 @@ enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter)
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry = iter->ent;
 	struct print_entry *field;
-	int ret;
 
 	trace_assign_type(field, entry);
 
-	ret = trace_seq_puts(s, field->buf);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
+	trace_seq_puts(s, field->buf);
 
-	return TRACE_TYPE_HANDLED;
+	return trace_handle_return(s);
 }
 
 const char *
@@ -193,7 +184,6 @@ int ftrace_raw_output_prep(struct trace_iterator *iter,
 	struct trace_seq *s = &iter->seq;
 	struct trace_seq *p = &iter->tmp_seq;
 	struct trace_entry *entry;
-	int ret;
 
 	event = container_of(trace_event, struct ftrace_event_call, event);
 	entry = iter->ent;
@@ -204,8 +194,9 @@ int ftrace_raw_output_prep(struct trace_iterator *iter,
 	}
 
 	trace_seq_init(p);
-	ret = trace_seq_printf(s, "%s: ", ftrace_event_name(event));
-	if (!ret)
+	trace_seq_printf(s, "%s: ", ftrace_event_name(event));
+
+	if (trace_seq_has_overflowed(s))
 		return TRACE_TYPE_PARTIAL_LINE;
 
 	return 0;
@@ -216,18 +207,11 @@ static int ftrace_output_raw(struct trace_iterator *iter, char *name,
 			     char *fmt, va_list ap)
 {
 	struct trace_seq *s = &iter->seq;
-	int ret;
 
-	ret = trace_seq_printf(s, "%s: ", name);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	ret = trace_seq_vprintf(s, fmt, ap);
+	trace_seq_printf(s, "%s: ", name);
+	trace_seq_vprintf(s, fmt, ap);
 
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	return TRACE_TYPE_HANDLED;
+	return trace_handle_return(s);
 }
 
 int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...)
@@ -260,7 +244,7 @@ static inline const char *kretprobed(const char *name)
 }
 #endif /* CONFIG_KRETPROBES */
 
-static int
+static void
 seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address)
 {
 #ifdef CONFIG_KALLSYMS
@@ -271,12 +255,11 @@ seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address)
 
 	name = kretprobed(str);
 
-	return trace_seq_printf(s, fmt, name);
+	trace_seq_printf(s, fmt, name);
 #endif
-	return 1;
 }
 
-static int
+static void
 seq_print_sym_offset(struct trace_seq *s, const char *fmt,
 		     unsigned long address)
 {
@@ -287,9 +270,8 @@ seq_print_sym_offset(struct trace_seq *s, const char *fmt,
 	sprint_symbol(str, address);
 	name = kretprobed(str);
 
-	return trace_seq_printf(s, fmt, name);
+	trace_seq_printf(s, fmt, name);
 #endif
-	return 1;
 }
 
 #ifndef CONFIG_64BIT
@@ -320,14 +302,14 @@ int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
 		if (file) {
 			ret = trace_seq_path(s, &file->f_path);
 			if (ret)
-				ret = trace_seq_printf(s, "[+0x%lx]",
-						       ip - vmstart);
+				trace_seq_printf(s, "[+0x%lx]",
+						 ip - vmstart);
 		}
 		up_read(&mm->mmap_sem);
 	}
 	if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file))
-		ret = trace_seq_printf(s, " <" IP_FMT ">", ip);
-	return ret;
+		trace_seq_printf(s, " <" IP_FMT ">", ip);
+	return !trace_seq_has_overflowed(s);
 }
 
 int
@@ -335,7 +317,6 @@ seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
 		      unsigned long sym_flags)
 {
 	struct mm_struct *mm = NULL;
-	int ret = 1;
 	unsigned int i;
 
 	if (trace_flags & TRACE_ITER_SYM_USEROBJ) {
@@ -354,48 +335,45 @@ seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
 	for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
 		unsigned long ip = entry->caller[i];
 
-		if (ip == ULONG_MAX || !ret)
+		if (ip == ULONG_MAX || trace_seq_has_overflowed(s))
 			break;
-		if (ret)
-			ret = trace_seq_puts(s, " => ");
+
+		trace_seq_puts(s, " => ");
+
 		if (!ip) {
-			if (ret)
-				ret = trace_seq_puts(s, "??");
-			if (ret)
-				ret = trace_seq_putc(s, '\n');
+			trace_seq_puts(s, "??");
+			trace_seq_putc(s, '\n');
 			continue;
 		}
-		if (!ret)
-			break;
-		if (ret)
-			ret = seq_print_user_ip(s, mm, ip, sym_flags);
-		ret = trace_seq_putc(s, '\n');
+
+		seq_print_user_ip(s, mm, ip, sym_flags);
+		trace_seq_putc(s, '\n');
 	}
 
 	if (mm)
 		mmput(mm);
-	return ret;
+
+	return !trace_seq_has_overflowed(s);
 }
 
 int
 seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 {
-	int ret;
-
-	if (!ip)
-		return trace_seq_putc(s, '0');
+	if (!ip) {
+		trace_seq_putc(s, '0');
+		goto out;
+	}
 
 	if (sym_flags & TRACE_ITER_SYM_OFFSET)
-		ret = seq_print_sym_offset(s, "%s", ip);
+		seq_print_sym_offset(s, "%s", ip);
 	else
-		ret = seq_print_sym_short(s, "%s", ip);
-
-	if (!ret)
-		return 0;
+		seq_print_sym_short(s, "%s", ip);
 
 	if (sym_flags & TRACE_ITER_SYM_ADDR)
-		ret = trace_seq_printf(s, " <" IP_FMT ">", ip);
-	return ret;
+		trace_seq_printf(s, " <" IP_FMT ">", ip);
+
+ out:
+	return !trace_seq_has_overflowed(s);
 }
 
 /**
@@ -413,7 +391,6 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 	char irqs_off;
 	int hardirq;
 	int softirq;
-	int ret;
 
 	hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
 	softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
@@ -445,16 +422,15 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 		softirq ? 's' :
 		'.';
 
-	if (!trace_seq_printf(s, "%c%c%c",
-			      irqs_off, need_resched, hardsoft_irq))
-		return 0;
+	trace_seq_printf(s, "%c%c%c",
+			 irqs_off, need_resched, hardsoft_irq);
 
 	if (entry->preempt_count)
-		ret = trace_seq_printf(s, "%x", entry->preempt_count);
+		trace_seq_printf(s, "%x", entry->preempt_count);
 	else
-		ret = trace_seq_putc(s, '.');
+		trace_seq_putc(s, '.');
 
-	return ret;
+	return !trace_seq_has_overflowed(s);
 }
 
 static int
@@ -464,9 +440,8 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 
 	trace_find_cmdline(entry->pid, comm);
 
-	if (!trace_seq_printf(s, "%8.8s-%-5d %3d",
-			      comm, entry->pid, cpu))
-		return 0;
+	trace_seq_printf(s, "%8.8s-%-5d %3d",
+			 comm, entry->pid, cpu);
 
 	return trace_print_lat_fmt(s, entry);
 }
@@ -493,24 +468,29 @@ lat_print_timestamp(struct trace_iterator *iter, u64 next_ts)
 		unsigned long rel_usec = do_div(rel_ts, USEC_PER_MSEC);
 		unsigned long rel_msec = (unsigned long)rel_ts;
 
-		return trace_seq_printf(
-				s, "[%08llx] %ld.%03ldms (+%ld.%03ldms): ",
-				ns2usecs(iter->ts),
-				abs_msec, abs_usec,
-				rel_msec, rel_usec);
+		trace_seq_printf(
+			s, "[%08llx] %ld.%03ldms (+%ld.%03ldms): ",
+			ns2usecs(iter->ts),
+			abs_msec, abs_usec,
+			rel_msec, rel_usec);
+
 	} else if (verbose && !in_ns) {
-		return trace_seq_printf(
-				s, "[%016llx] %lld (+%lld): ",
-				iter->ts, abs_ts, rel_ts);
+		trace_seq_printf(
+			s, "[%016llx] %lld (+%lld): ",
+			iter->ts, abs_ts, rel_ts);
+
 	} else if (!verbose && in_ns) {
-		return trace_seq_printf(
-				s, " %4lldus%c: ",
-				abs_ts,
-				rel_ts > preempt_mark_thresh_us ? '!' :
-				  rel_ts > 1 ? '+' : ' ');
+		trace_seq_printf(
+			s, " %4lldus%c: ",
+			abs_ts,
+			rel_ts > preempt_mark_thresh_us ? '!' :
+			rel_ts > 1 ? '+' : ' ');
+
 	} else { /* !verbose && !in_ns */
-		return trace_seq_printf(s, " %4lld: ", abs_ts);
+		trace_seq_printf(s, " %4lld: ", abs_ts);
 	}
+
+	return !trace_seq_has_overflowed(s);
 }
 
 int trace_print_context(struct trace_iterator *iter)
@@ -520,34 +500,29 @@ int trace_print_context(struct trace_iterator *iter)
 	unsigned long long t;
 	unsigned long secs, usec_rem;
 	char comm[TASK_COMM_LEN];
-	int ret;
 
 	trace_find_cmdline(entry->pid, comm);
 
-	ret = trace_seq_printf(s, "%16s-%-5d [%03d] ",
+	trace_seq_printf(s, "%16s-%-5d [%03d] ",
 			       comm, entry->pid, iter->cpu);
-	if (!ret)
-		return 0;
 
-	if (trace_flags & TRACE_ITER_IRQ_INFO) {
-		ret = trace_print_lat_fmt(s, entry);
-		if (!ret)
-			return 0;
-	}
+	if (trace_flags & TRACE_ITER_IRQ_INFO)
+		trace_print_lat_fmt(s, entry);
 
 	if (iter->iter_flags & TRACE_FILE_TIME_IN_NS) {
 		t = ns2usecs(iter->ts);
 		usec_rem = do_div(t, USEC_PER_SEC);
 		secs = (unsigned long)t;
-		return trace_seq_printf(s, " %5lu.%06lu: ", secs, usec_rem);
+		trace_seq_printf(s, " %5lu.%06lu: ", secs, usec_rem);
 	} else
-		return trace_seq_printf(s, " %12llu: ", iter->ts);
+		trace_seq_printf(s, " %12llu: ", iter->ts);
+
+	return !trace_seq_has_overflowed(s);
 }
 
 int trace_print_lat_context(struct trace_iterator *iter)
 {
 	u64 next_ts;
-	int ret;
 	/* trace_find_next_entry will reset ent_size */
 	int ent_size = iter->ent_size;
 	struct trace_seq *s = &iter->seq;
@@ -567,18 +542,17 @@ int trace_print_lat_context(struct trace_iterator *iter)
 
 		trace_find_cmdline(entry->pid, comm);
 
-		ret = trace_seq_printf(
-				s, "%16s %5d %3d %d %08x %08lx ",
-				comm, entry->pid, iter->cpu, entry->flags,
-				entry->preempt_count, iter->idx);
+		trace_seq_printf(
+			s, "%16s %5d %3d %d %08x %08lx ",
+			comm, entry->pid, iter->cpu, entry->flags,
+			entry->preempt_count, iter->idx);
 	} else {
-		ret = lat_print_generic(s, entry, iter->cpu);
+		lat_print_generic(s, entry, iter->cpu);
 	}
 
-	if (ret)
-		ret = lat_print_timestamp(iter, next_ts);
+	lat_print_timestamp(iter, next_ts);
 
-	return ret;
+	return !trace_seq_has_overflowed(s);
 }
 
 static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
@@ -764,10 +738,9 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_event);
 enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags,
 				  struct trace_event *event)
 {
-	if (!trace_seq_printf(&iter->seq, "type: %d\n", iter->ent->type))
-		return TRACE_TYPE_PARTIAL_LINE;
+	trace_seq_printf(&iter->seq, "type: %d\n", iter->ent->type);
 
-	return TRACE_TYPE_HANDLED;
+	return trace_handle_return(&iter->seq);
 }
 
 /* TRACE_FN */
@@ -779,24 +752,16 @@ static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, iter->ent);
 
-	if (!seq_print_ip_sym(s, field->ip, flags))
-		goto partial;
+	seq_print_ip_sym(s, field->ip, flags);
 
 	if ((flags & TRACE_ITER_PRINT_PARENT) && field->parent_ip) {
-		if (!trace_seq_puts(s, " <-"))
-			goto partial;
-		if (!seq_print_ip_sym(s,
-				      field->parent_ip,
-				      flags))
-			goto partial;
+		trace_seq_puts(s, " <-");
+		seq_print_ip_sym(s, field->parent_ip, flags);
 	}
-	if (!trace_seq_putc(s, '\n'))
-		goto partial;
 
-	return TRACE_TYPE_HANDLED;
+	trace_seq_putc(s, '\n');
 
- partial:
-	return TRACE_TYPE_PARTIAL_LINE;
+	return trace_handle_return(s);
 }
 
 static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags,
@@ -806,12 +771,11 @@ static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, iter->ent);
 
-	if (!trace_seq_printf(&iter->seq, "%lx %lx\n",
-			      field->ip,
-			      field->parent_ip))
-		return TRACE_TYPE_PARTIAL_LINE;
+	trace_seq_printf(&iter->seq, "%lx %lx\n",
+			 field->ip,
+			 field->parent_ip);
 
-	return TRACE_TYPE_HANDLED;
+	return trace_handle_return(&iter->seq);
 }
 
 static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags,
@@ -822,10 +786,10 @@ static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, iter->ent);
 
-	SEQ_PUT_HEX_FIELD_RET(s, field->ip);
-	SEQ_PUT_HEX_FIELD_RET(s, field->parent_ip);
+	SEQ_PUT_HEX_FIELD(s, field->ip);
+	SEQ_PUT_HEX_FIELD(s, field->parent_ip);
 
-	return TRACE_TYPE_HANDLED;
+	return trace_handle_return(s);
 }
 
 static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags,
@@ -836,10 +800,10 @@ static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, iter->ent);
 
-	SEQ_PUT_FIELD_RET(s, field->ip);
-	SEQ_PUT_FIELD_RET(s, field->parent_ip);
+	SEQ_PUT_FIELD(s, field->ip);
+	SEQ_PUT_FIELD(s, field->parent_ip);
 
-	return TRACE_TYPE_HANDLED;
+	return trace_handle_return(s);
 }
 
 static struct trace_event_functions trace_fn_funcs = {
@@ -868,18 +832,17 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
 	T = task_state_char(field->next_state);
 	S = task_state_char(field->prev_state);
 	trace_find_cmdline(field->next_pid, comm);
-	if (!trace_seq_printf(&iter->seq,
-			      " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
-			      field->prev_pid,
-			      field->prev_prio,
-			      S, delim,
-			      field->next_cpu,
-			      field->next_pid,
-			      field->next_prio,
-			      T, comm))
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	return TRACE_TYPE_HANDLED;
+	trace_seq_printf(&iter->seq,
+			 " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
+			 field->prev_pid,
+			 field->prev_prio,
+			 S, delim,
+			 field->next_cpu,
+			 field->next_pid,
+			 field->next_prio,
+			 T, comm);
+
+	return trace_handle_return(&iter->seq);
 }
 
 static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags,
@@ -904,17 +867,16 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S)
 	if (!S)
 		S = task_state_char(field->prev_state);
 	T = task_state_char(field->next_state);
-	if (!trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n",
-			      field->prev_pid,
-			      field->prev_prio,
-			      S,
-			      field->next_cpu,
-			      field->next_pid,
-			      field->next_prio,
-			      T))
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	return TRACE_TYPE_HANDLED;
+	trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n",
+			 field->prev_pid,
+			 field->prev_prio,
+			 S,
+			 field->next_cpu,
+			 field->next_pid,
+			 field->next_prio,
+			 T);
+
+	return trace_handle_return(&iter->seq);
 }
 
 static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags,
@@ -942,15 +904,15 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S)
 		S = task_state_char(field->prev_state);
 	T = task_state_char(field->next_state);
 
-	SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid);
-	SEQ_PUT_HEX_FIELD_RET(s, field->prev_prio);
-	SEQ_PUT_HEX_FIELD_RET(s, S);
-	SEQ_PUT_HEX_FIELD_RET(s, field->next_cpu);
-	SEQ_PUT_HEX_FIELD_RET(s, field->next_pid);
-	SEQ_PUT_HEX_FIELD_RET(s, field->next_prio);
-	SEQ_PUT_HEX_FIELD_RET(s, T);
+	SEQ_PUT_HEX_FIELD(s, field->prev_pid);
+	SEQ_PUT_HEX_FIELD(s, field->prev_prio);
+	SEQ_PUT_HEX_FIELD(s, S);
+	SEQ_PUT_HEX_FIELD(s, field->next_cpu);
+	SEQ_PUT_HEX_FIELD(s, field->next_pid);
+	SEQ_PUT_HEX_FIELD(s, field->next_prio);
+	SEQ_PUT_HEX_FIELD(s, T);
 
-	return TRACE_TYPE_HANDLED;
+	return trace_handle_return(s);
 }
 
 static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags,
@@ -973,15 +935,15 @@ static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter,
 
 	trace_assign_type(field, iter->ent);
 
-	SEQ_PUT_FIELD_RET(s, field->prev_pid);
-	SEQ_PUT_FIELD_RET(s, field->prev_prio);
-	SEQ_PUT_FIELD_RET(s, field->prev_state);
-	SEQ_PUT_FIELD_RET(s, field->next_cpu);
-	SEQ_PUT_FIELD_RET(s, field->next_pid);
-	SEQ_PUT_FIELD_RET(s, field->next_prio);
-	SEQ_PUT_FIELD_RET(s, field->next_state);
+	SEQ_PUT_FIELD(s, field->prev_pid);
+	SEQ_PUT_FIELD(s, field->prev_prio);
+	SEQ_PUT_FIELD(s, field->prev_state);
+	SEQ_PUT_FIELD(s, field->next_cpu);
+	SEQ_PUT_FIELD(s, field->next_pid);
+	SEQ_PUT_FIELD(s, field->next_prio);
+	SEQ_PUT_FIELD(s, field->next_state);
 
-	return TRACE_TYPE_HANDLED;
+	return trace_handle_return(s);
 }
 
 static struct trace_event_functions trace_ctx_funcs = {
@@ -1021,23 +983,19 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
 	trace_assign_type(field, iter->ent);
 	end = (unsigned long *)((long)iter->ent + iter->ent_size);
 
-	if (!trace_seq_puts(s, "<stack trace>\n"))
-		goto partial;
+	trace_seq_puts(s, "<stack trace>\n");
 
 	for (p = field->caller; p && *p != ULONG_MAX && p < end; p++) {
-		if (!trace_seq_puts(s, " => "))
-			goto partial;
 
-		if (!seq_print_ip_sym(s, *p, flags))
-			goto partial;
-		if (!trace_seq_putc(s, '\n'))
-			goto partial;
-	}
+		if (trace_seq_has_overflowed(s))
+			break;
 
-	return TRACE_TYPE_HANDLED;
+		trace_seq_puts(s, " => ");
+		seq_print_ip_sym(s, *p, flags);
+		trace_seq_putc(s, '\n');
+	}
 
- partial:
-	return TRACE_TYPE_PARTIAL_LINE;
+	return trace_handle_return(s);
 }
 
 static struct trace_event_functions trace_stack_funcs = {
@@ -1058,16 +1016,10 @@ static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
 
 	trace_assign_type(field, iter->ent);
 
-	if (!trace_seq_puts(s, "<user stack trace>\n"))
-		goto partial;
-
-	if (!seq_print_userip_objs(field, s, flags))
-		goto partial;
-
-	return TRACE_TYPE_HANDLED;
+	trace_seq_puts(s, "<user stack trace>\n");
+	seq_print_userip_objs(field, s, flags);
 
- partial:
-	return TRACE_TYPE_PARTIAL_LINE;
+	return trace_handle_return(s);
 }
 
 static struct trace_event_functions trace_user_stack_funcs = {
@@ -1090,19 +1042,11 @@ trace_bputs_print(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, entry);
 
-	if (!seq_print_ip_sym(s, field->ip, flags))
-		goto partial;
+	seq_print_ip_sym(s, field->ip, flags);
+	trace_seq_puts(s, ": ");
+	trace_seq_puts(s, field->str);
 
-	if (!trace_seq_puts(s, ": "))
-		goto partial;
-
-	if (!trace_seq_puts(s, field->str))
-		goto partial;
-
-	return TRACE_TYPE_HANDLED;
-
- partial:
-	return TRACE_TYPE_PARTIAL_LINE;
+	return trace_handle_return(s);
 }
 
 
@@ -1115,16 +1059,10 @@ trace_bputs_raw(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, iter->ent);
 
-	if (!trace_seq_printf(s, ": %lx : ", field->ip))
-		goto partial;
-
-	if (!trace_seq_puts(s, field->str))
-		goto partial;
+	trace_seq_printf(s, ": %lx : ", field->ip);
+	trace_seq_puts(s, field->str);
 
-	return TRACE_TYPE_HANDLED;
-
- partial:
-	return TRACE_TYPE_PARTIAL_LINE;
+	return trace_handle_return(s);
 }
 
 static struct trace_event_functions trace_bputs_funcs = {
@@ -1148,19 +1086,11 @@ trace_bprint_print(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, entry);
 
-	if (!seq_print_ip_sym(s, field->ip, flags))
-		goto partial;
-
-	if (!trace_seq_puts(s, ": "))
-		goto partial;
-
-	if (!trace_seq_bprintf(s, field->fmt, field->buf))
-		goto partial;
+	seq_print_ip_sym(s, field->ip, flags);
+	trace_seq_puts(s, ": ");
+	trace_seq_bprintf(s, field->fmt, field->buf);
 
-	return TRACE_TYPE_HANDLED;
-
- partial:
-	return TRACE_TYPE_PARTIAL_LINE;
+	return trace_handle_return(s);
 }
 
 
@@ -1173,16 +1103,10 @@ trace_bprint_raw(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, iter->ent);
 
-	if (!trace_seq_printf(s, ": %lx : ", field->ip))
-		goto partial;
-
-	if (!trace_seq_bprintf(s, field->fmt, field->buf))
-		goto partial;
+	trace_seq_printf(s, ": %lx : ", field->ip);
+	trace_seq_bprintf(s, field->fmt, field->buf);
 
-	return TRACE_TYPE_HANDLED;
-
- partial:
-	return TRACE_TYPE_PARTIAL_LINE;
+	return trace_handle_return(s);
 }
 
 static struct trace_event_functions trace_bprint_funcs = {
@@ -1204,16 +1128,10 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter,
 
 	trace_assign_type(field, iter->ent);
 
-	if (!seq_print_ip_sym(s, field->ip, flags))
-		goto partial;
-
-	if (!trace_seq_printf(s, ": %s", field->buf))
-		goto partial;
+	seq_print_ip_sym(s, field->ip, flags);
+	trace_seq_printf(s, ": %s", field->buf);
 
-	return TRACE_TYPE_HANDLED;
-
- partial:
-	return TRACE_TYPE_PARTIAL_LINE;
+	return trace_handle_return(s);
 }
 
 static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags,
@@ -1223,13 +1141,9 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, iter->ent);
 
-	if (!trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf))
-		goto partial;
-
-	return TRACE_TYPE_HANDLED;
+	trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf);
 
- partial:
-	return TRACE_TYPE_PARTIAL_LINE;
+	return trace_handle_return(&iter->seq);
 }
 
 static struct trace_event_functions trace_print_funcs = {
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index 80b25b585a7..8ef2c40efb3 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -35,17 +35,11 @@ trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry);
 extern int __unregister_ftrace_event(struct trace_event *event);
 extern struct rw_semaphore trace_event_sem;
 
-#define SEQ_PUT_FIELD_RET(s, x)				\
-do {							\
-	if (!trace_seq_putmem(s, &(x), sizeof(x)))	\
-		return TRACE_TYPE_PARTIAL_LINE;		\
-} while (0)
-
-#define SEQ_PUT_HEX_FIELD_RET(s, x)			\
-do {							\
-	if (!trace_seq_putmem_hex(s, &(x), sizeof(x)))	\
-		return TRACE_TYPE_PARTIAL_LINE;		\
-} while (0)
+#define SEQ_PUT_FIELD(s, x)				\
+	trace_seq_putmem(s, &(x), sizeof(x))
+
+#define SEQ_PUT_HEX_FIELD(s, x)				\
+	trace_seq_putmem_hex(s, &(x), sizeof(x))
 
 #endif
 
-- 
cgit v1.2.3-70-g09d2


From dba39448abb7340f86ae9b062f99d7acacb5d2d2 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 12 Nov 2014 18:07:22 -0500
Subject: tracing: Remove return values of most trace_seq_*() functions

The trace_seq_printf() and friends are used to store strings into a buffer
that can be passed around from function to function. If the trace_seq buffer
fills up, it will not print any more. The return values were somewhat
inconsistant and using trace_seq_has_overflowed() was a better way to know
if the write to the trace_seq buffer succeeded or not.

Now that all users have removed reading the return value of the printf()
type functions, they can safely return void and keep future users of them
from reading the inconsistent values as well.

Link: http://lkml.kernel.org/r/20141114011411.992510720@goodmis.org

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/trace_seq.h | 37 +++++++++------------
 kernel/trace/trace_seq.c  | 84 +++++++++++++----------------------------------
 2 files changed, 38 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
index 07eda413dfc..db8a73224f1 100644
--- a/include/linux/trace_seq.h
+++ b/include/linux/trace_seq.h
@@ -57,40 +57,37 @@ static inline bool trace_seq_has_overflowed(struct trace_seq *s)
  */
 #ifdef CONFIG_TRACING
 extern __printf(2, 3)
-int trace_seq_printf(struct trace_seq *s, const char *fmt, ...);
+void trace_seq_printf(struct trace_seq *s, const char *fmt, ...);
 extern __printf(2, 0)
-int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args);
-extern int
+void trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args);
+extern void
 trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary);
 extern int trace_print_seq(struct seq_file *m, struct trace_seq *s);
 extern int trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
 			     int cnt);
-extern int trace_seq_puts(struct trace_seq *s, const char *str);
-extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
-extern int trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len);
-extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+extern void trace_seq_puts(struct trace_seq *s, const char *str);
+extern void trace_seq_putc(struct trace_seq *s, unsigned char c);
+extern void trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len);
+extern void trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
 				unsigned int len);
 extern int trace_seq_path(struct trace_seq *s, const struct path *path);
 
-extern int trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp,
+extern void trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp,
 			     int nmaskbits);
 
 #else /* CONFIG_TRACING */
-static inline int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+static inline void trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 {
-	return 0;
 }
-static inline int
+static inline void
 trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
 {
-	return 0;
 }
 
-static inline int
+static inline void
 trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp,
 		  int nmaskbits)
 {
-	return 0;
 }
 
 static inline int trace_print_seq(struct seq_file *m, struct trace_seq *s)
@@ -102,23 +99,19 @@ static inline int trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
 {
 	return 0;
 }
-static inline int trace_seq_puts(struct trace_seq *s, const char *str)
+static inline void trace_seq_puts(struct trace_seq *s, const char *str)
 {
-	return 0;
 }
-static inline int trace_seq_putc(struct trace_seq *s, unsigned char c)
+static inline void trace_seq_putc(struct trace_seq *s, unsigned char c)
 {
-	return 0;
 }
-static inline int
+static inline void
 trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len)
 {
-	return 0;
 }
-static inline int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+static inline void trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
 				       unsigned int len)
 {
-	return 0;
 }
 static inline int trace_seq_path(struct trace_seq *s, const struct path *path)
 {
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index b100994a17f..fabfa0f190a 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -69,20 +69,15 @@ int trace_print_seq(struct seq_file *m, struct trace_seq *s)
  * trace_seq_printf() is used to store strings into a special
  * buffer (@s). Then the output may be either used by
  * the sequencer or pulled into another buffer.
- *
- * Returns 1 if we successfully written all the contents to
- *   the buffer.
-  * Returns 0 if we the length to write is bigger than the
- *   reserved buffer space. In this case, nothing gets written.
  */
-int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+void trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 {
 	unsigned int len = TRACE_SEQ_BUF_LEFT(s);
 	va_list ap;
 	int ret;
 
 	if (s->full || !len)
-		return 0;
+		return;
 
 	va_start(ap, fmt);
 	ret = vsnprintf(s->buffer + s->len, len, fmt, ap);
@@ -91,12 +86,10 @@ int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 	/* If we can't write it all, don't bother writing anything */
 	if (ret >= len) {
 		s->full = 1;
-		return 0;
+		return;
 	}
 
 	s->len += ret;
-
-	return 1;
 }
 EXPORT_SYMBOL_GPL(trace_seq_printf);
 
@@ -107,25 +100,18 @@ EXPORT_SYMBOL_GPL(trace_seq_printf);
  * @nmaskbits:	The number of bits that are valid in @maskp
  *
  * Writes a ASCII representation of a bitmask string into @s.
- *
- * Returns 1 if we successfully written all the contents to
- *   the buffer.
- * Returns 0 if we the length to write is bigger than the
- *   reserved buffer space. In this case, nothing gets written.
  */
-int trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp,
+void trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp,
 		      int nmaskbits)
 {
 	unsigned int len = TRACE_SEQ_BUF_LEFT(s);
 	int ret;
 
 	if (s->full || !len)
-		return 0;
+		return;
 
 	ret = bitmap_scnprintf(s->buffer + s->len, len, maskp, nmaskbits);
 	s->len += ret;
-
-	return 1;
 }
 EXPORT_SYMBOL_GPL(trace_seq_bitmask);
 
@@ -139,28 +125,24 @@ EXPORT_SYMBOL_GPL(trace_seq_bitmask);
  * trace_seq_printf is used to store strings into a special
  * buffer (@s). Then the output may be either used by
  * the sequencer or pulled into another buffer.
- *
- * Returns how much it wrote to the buffer.
  */
-int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+void trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
 {
 	unsigned int len = TRACE_SEQ_BUF_LEFT(s);
 	int ret;
 
 	if (s->full || !len)
-		return 0;
+		return;
 
 	ret = vsnprintf(s->buffer + s->len, len, fmt, args);
 
 	/* If we can't write it all, don't bother writing anything */
 	if (ret >= len) {
 		s->full = 1;
-		return 0;
+		return;
 	}
 
 	s->len += ret;
-
-	return len;
 }
 EXPORT_SYMBOL_GPL(trace_seq_vprintf);
 
@@ -178,28 +160,24 @@ EXPORT_SYMBOL_GPL(trace_seq_vprintf);
  *
  * This function will take the format and the binary array and finish
  * the conversion into the ASCII string within the buffer.
- *
- * Returns how much it wrote to the buffer.
  */
-int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
+void trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
 {
 	unsigned int len = TRACE_SEQ_BUF_LEFT(s);
 	int ret;
 
 	if (s->full || !len)
-		return 0;
+		return;
 
 	ret = bstr_printf(s->buffer + s->len, len, fmt, binary);
 
 	/* If we can't write it all, don't bother writing anything */
 	if (ret >= len) {
 		s->full = 1;
-		return 0;
+		return;
 	}
 
 	s->len += ret;
-
-	return len;
 }
 EXPORT_SYMBOL_GPL(trace_seq_bprintf);
 
@@ -212,25 +190,21 @@ EXPORT_SYMBOL_GPL(trace_seq_bprintf);
  * copy to user routines. This function records a simple string
  * into a special buffer (@s) for later retrieval by a sequencer
  * or other mechanism.
- *
- * Returns how much it wrote to the buffer.
  */
-int trace_seq_puts(struct trace_seq *s, const char *str)
+void trace_seq_puts(struct trace_seq *s, const char *str)
 {
 	unsigned int len = strlen(str);
 
 	if (s->full)
-		return 0;
+		return;
 
 	if (len > TRACE_SEQ_BUF_LEFT(s)) {
 		s->full = 1;
-		return 0;
+		return;
 	}
 
 	memcpy(s->buffer + s->len, str, len);
 	s->len += len;
-
-	return len;
 }
 EXPORT_SYMBOL_GPL(trace_seq_puts);
 
@@ -243,22 +217,18 @@ EXPORT_SYMBOL_GPL(trace_seq_puts);
  * copy to user routines. This function records a simple charater
  * into a special buffer (@s) for later retrieval by a sequencer
  * or other mechanism.
- *
- * Returns how much it wrote to the buffer.
  */
-int trace_seq_putc(struct trace_seq *s, unsigned char c)
+void trace_seq_putc(struct trace_seq *s, unsigned char c)
 {
 	if (s->full)
-		return 0;
+		return;
 
 	if (TRACE_SEQ_BUF_LEFT(s) < 1) {
 		s->full = 1;
-		return 0;
+		return;
 	}
 
 	s->buffer[s->len++] = c;
-
-	return 1;
 }
 EXPORT_SYMBOL_GPL(trace_seq_putc);
 
@@ -271,23 +241,19 @@ EXPORT_SYMBOL_GPL(trace_seq_putc);
  * There may be cases where raw memory needs to be written into the
  * buffer and a strcpy() would not work. Using this function allows
  * for such cases.
- *
- * Returns how much it wrote to the buffer.
  */
-int trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len)
+void trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len)
 {
 	if (s->full)
-		return 0;
+		return;
 
 	if (len > TRACE_SEQ_BUF_LEFT(s)) {
 		s->full = 1;
-		return 0;
+		return;
 	}
 
 	memcpy(s->buffer + s->len, mem, len);
 	s->len += len;
-
-	return len;
 }
 EXPORT_SYMBOL_GPL(trace_seq_putmem);
 
@@ -303,20 +269,17 @@ EXPORT_SYMBOL_GPL(trace_seq_putmem);
  * This is similar to trace_seq_putmem() except instead of just copying the
  * raw memory into the buffer it writes its ASCII representation of it
  * in hex characters.
- *
- * Returns how much it wrote to the buffer.
  */
-int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+void trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
 			 unsigned int len)
 {
 	unsigned char hex[HEX_CHARS];
 	const unsigned char *data = mem;
 	unsigned int start_len;
 	int i, j;
-	int cnt = 0;
 
 	if (s->full)
-		return 0;
+		return;
 
 	while (len) {
 		start_len = min(len, HEX_CHARS - 1);
@@ -335,9 +298,8 @@ int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
 		len -= j / 2;
 		hex[j++] = ' ';
 
-		cnt += trace_seq_putmem(s, hex, j);
+		trace_seq_putmem(s, hex, j);
 	}
-	return cnt;
 }
 EXPORT_SYMBOL_GPL(trace_seq_putmem_hex);
 
-- 
cgit v1.2.3-70-g09d2


From 8e2e095cbecad21078332cd83ae7e61ecfe12c59 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 14 Nov 2014 11:42:06 -0500
Subject: tracing: Fix return value of ftrace_raw_output_prep()

If the trace_seq of ftrace_raw_output_prep() is full this function
returns TRACE_TYPE_PARTIAL_LINE, otherwise it returns zero.

The problem is that TRACE_TYPE_PARTIAL_LINE happens to be zero!

The thing is, the caller of ftrace_raw_output_prep() expects a
success to be zero. Change that to expect it to be
TRACE_TYPE_HANDLED.

Link: http://lkml.kernel.org/r/20141114112522.GA2988@dhcp128.suse.cz

Reminded-by: Petr Mladek <pmladek@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/ftrace.h      | 2 +-
 kernel/trace/trace_output.c | 5 +----
 2 files changed, 2 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index f13471b5d27..139b5067345 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -277,7 +277,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags,	\
 	field = (typeof(field))iter->ent;				\
 									\
 	ret = ftrace_raw_output_prep(iter, trace_event);		\
-	if (ret)							\
+	if (ret != TRACE_TYPE_HANDLED)					\
 		return ret;						\
 									\
 	trace_seq_printf(s, print);					\
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 163c11b6b8f..723818bc83b 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -196,10 +196,7 @@ int ftrace_raw_output_prep(struct trace_iterator *iter,
 	trace_seq_init(p);
 	trace_seq_printf(s, "%s: ", ftrace_event_name(event));
 
-	if (trace_seq_has_overflowed(s))
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	return 0;
+	return trace_handle_return(s);
 }
 EXPORT_SYMBOL(ftrace_raw_output_prep);
 
-- 
cgit v1.2.3-70-g09d2


From 2ab4bd8ea3a6954bc79a9bbeb291cd6c2d6213a7 Mon Sep 17 00:00:00 2001
From: David Teigland <teigland@redhat.com>
Date: Fri, 17 Oct 2014 11:05:50 -0500
Subject: dlm: adopt orphan locks

A process may exit, leaving an orphan lock in the lockspace.
This adds the capability for another process to acquire the
orphan lock.  Acquiring the orphan just moves the lock from
the orphan list onto the acquiring process's list of locks.

An adopting process must specify the resource name and mode
of the lock it wants to adopt.  If a matching lock is found,
the lock is moved to the caller's 's list of locks, and the
lkid of the lock is returned like the lkid of a new lock.

If an orphan with a different mode is found, then -EAGAIN is
returned.  If no orphan lock is found on the resource, then
-ENOENT is returned.  No async completion is used because
the result is immediately available.

Also, when orphans are purged, allow a zero nodeid to refer
to the local nodeid so the caller does not need to look up
the local nodeid.

Signed-off-by: David Teigland <teigland@redhat.com>
---
 fs/dlm/lock.c                     | 76 +++++++++++++++++++++++++++++++++++++--
 fs/dlm/lock.h                     |  3 ++
 fs/dlm/user.c                     | 13 +++++--
 include/uapi/linux/dlmconstants.h |  2 +-
 4 files changed, 89 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 83f3d552030..35502d4046f 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -5886,6 +5886,78 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
 	return error;
 }
 
+/*
+ * The caller asks for an orphan lock on a given resource with a given mode.
+ * If a matching lock exists, it's moved to the owner's list of locks and
+ * the lkid is returned.
+ */
+
+int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
+		     int mode, uint32_t flags, void *name, unsigned int namelen,
+		     unsigned long timeout_cs, uint32_t *lkid)
+{
+	struct dlm_lkb *lkb;
+	struct dlm_user_args *ua;
+	int found_other_mode = 0;
+	int found = 0;
+	int rv = 0;
+
+	mutex_lock(&ls->ls_orphans_mutex);
+	list_for_each_entry(lkb, &ls->ls_orphans, lkb_ownqueue) {
+		if (lkb->lkb_resource->res_length != namelen)
+			continue;
+		if (memcmp(lkb->lkb_resource->res_name, name, namelen))
+			continue;
+		if (lkb->lkb_grmode != mode) {
+			found_other_mode = 1;
+			continue;
+		}
+
+		found = 1;
+		list_del_init(&lkb->lkb_ownqueue);
+		lkb->lkb_flags &= ~DLM_IFL_ORPHAN;
+		*lkid = lkb->lkb_id;
+		break;
+	}
+	mutex_unlock(&ls->ls_orphans_mutex);
+
+	if (!found && found_other_mode) {
+		rv = -EAGAIN;
+		goto out;
+	}
+
+	if (!found) {
+		rv = -ENOENT;
+		goto out;
+	}
+
+	lkb->lkb_exflags = flags;
+	lkb->lkb_ownpid = (int) current->pid;
+
+	ua = lkb->lkb_ua;
+
+	ua->proc = ua_tmp->proc;
+	ua->xid = ua_tmp->xid;
+	ua->castparam = ua_tmp->castparam;
+	ua->castaddr = ua_tmp->castaddr;
+	ua->bastparam = ua_tmp->bastparam;
+	ua->bastaddr = ua_tmp->bastaddr;
+	ua->user_lksb = ua_tmp->user_lksb;
+
+	/*
+	 * The lkb reference from the ls_orphans list was not
+	 * removed above, and is now considered the reference
+	 * for the proc locks list.
+	 */
+
+	spin_lock(&ua->proc->locks_spin);
+	list_add_tail(&lkb->lkb_ownqueue, &ua->proc->locks);
+	spin_unlock(&ua->proc->locks_spin);
+ out:
+	kfree(ua_tmp);
+	return rv;
+}
+
 int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
 		    uint32_t flags, uint32_t lkid, char *lvb_in)
 {
@@ -6029,7 +6101,7 @@ static int orphan_proc_lock(struct dlm_ls *ls, struct dlm_lkb *lkb)
 	struct dlm_args args;
 	int error;
 
-	hold_lkb(lkb);
+	hold_lkb(lkb); /* reference for the ls_orphans list */
 	mutex_lock(&ls->ls_orphans_mutex);
 	list_add_tail(&lkb->lkb_ownqueue, &ls->ls_orphans);
 	mutex_unlock(&ls->ls_orphans_mutex);
@@ -6217,7 +6289,7 @@ int dlm_user_purge(struct dlm_ls *ls, struct dlm_user_proc *proc,
 {
 	int error = 0;
 
-	if (nodeid != dlm_our_nodeid()) {
+	if (nodeid && (nodeid != dlm_our_nodeid())) {
 		error = send_purge(ls, nodeid, pid);
 	} else {
 		dlm_lock_recovery(ls);
diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h
index 5e0c72e36a9..ed8ebd3a859 100644
--- a/fs/dlm/lock.h
+++ b/fs/dlm/lock.h
@@ -49,6 +49,9 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, int mode,
 int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
 	int mode, uint32_t flags, uint32_t lkid, char *lvb_in,
 	unsigned long timeout_cs);
+int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
+	int mode, uint32_t flags, void *name, unsigned int namelen,
+	unsigned long timeout_cs, uint32_t *lkid);
 int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
 	uint32_t flags, uint32_t lkid, char *lvb_in);
 int dlm_user_cancel(struct dlm_ls *ls,  struct dlm_user_args *ua_tmp,
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 142e21655ee..fb85f32e9ec 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -238,6 +238,7 @@ static int device_user_lock(struct dlm_user_proc *proc,
 {
 	struct dlm_ls *ls;
 	struct dlm_user_args *ua;
+	uint32_t lkid;
 	int error = -ENOMEM;
 
 	ls = dlm_find_lockspace_local(proc->lockspace);
@@ -260,12 +261,20 @@ static int device_user_lock(struct dlm_user_proc *proc,
 	ua->bastaddr = params->bastaddr;
 	ua->xid = params->xid;
 
-	if (params->flags & DLM_LKF_CONVERT)
+	if (params->flags & DLM_LKF_CONVERT) {
 		error = dlm_user_convert(ls, ua,
 				         params->mode, params->flags,
 				         params->lkid, params->lvb,
 					 (unsigned long) params->timeout);
-	else {
+	} else if (params->flags & DLM_LKF_ORPHAN) {
+		error = dlm_user_adopt_orphan(ls, ua,
+					 params->mode, params->flags,
+					 params->name, params->namelen,
+					 (unsigned long) params->timeout,
+					 &lkid);
+		if (!error)
+			error = lkid;
+	} else {
 		error = dlm_user_request(ls, ua,
 					 params->mode, params->flags,
 					 params->name, params->namelen,
diff --git a/include/uapi/linux/dlmconstants.h b/include/uapi/linux/dlmconstants.h
index 47bf08dc756..2857bdc5b27 100644
--- a/include/uapi/linux/dlmconstants.h
+++ b/include/uapi/linux/dlmconstants.h
@@ -114,7 +114,7 @@
  *
  * DLM_LKF_ORPHAN
  *
- * not yet implemented
+ * Acquire an orphan lock.
  *
  * DLM_LKF_ALTPR
  *
-- 
cgit v1.2.3-70-g09d2


From 666547ff591cebdedc4679bf6b1b3f3383a8dea3 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 6 Apr 2014 14:03:05 -0400
Subject: separate kernel- and userland-side msghdr

Kernel-side struct msghdr is (currently) using the same layout as
userland one, but it's not a one-to-one copy - even without considering
32bit compat issues, we have msg_iov, msg_name and msg_control copied
to kernel[1].  It's fairly localized, so we get away with a few functions
where that knowledge is needed (and we could shrink that set even
more).  Pretty much everything deals with the kernel-side variant and
the few places that want userland one just use a bunch of force-casts
to paper over the differences.

The thing is, kernel-side definition of struct msghdr is *not* exposed
in include/uapi - libc doesn't see it, etc.  So we can add struct user_msghdr,
with proper annotations and let the few places that ever deal with those
beasts use it for userland pointers.  Saner typechecking aside, that will
allow to change the layout of kernel-side msghdr - e.g. replace
msg_iov/msg_iovlen there with struct iov_iter, getting rid of the need
to modify the iovec as we copy data to/from it, etc.

We could introduce kernel_msghdr instead, but that would create much more
noise - the absolute majority of the instances would need to have the
type switched to kernel_msghdr and definition of struct msghdr in
include/linux/socket.h is not going to be seen by userland anyway.

This commit just introduces user_msghdr and switches the few places that
are dealing with userland-side msghdr to it.

[1] actually, it's even trickier than that - we copy msg_control for
sendmsg, but keep the userland address on recvmsg.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm/kernel/sys_oabi-compat.c |  4 ++--
 include/linux/socket.h            | 16 +++++++++++++---
 include/linux/syscalls.h          |  6 +++---
 net/compat.c                      |  4 ++--
 net/socket.c                      | 29 ++++++++++++++++-------------
 5 files changed, 36 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index e90a3148f38..b83f3b7737f 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -400,7 +400,7 @@ asmlinkage long sys_oabi_sendto(int fd, void __user *buff,
 	return sys_sendto(fd, buff, len, flags, addr, addrlen);
 }
 
-asmlinkage long sys_oabi_sendmsg(int fd, struct msghdr __user *msg, unsigned flags)
+asmlinkage long sys_oabi_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags)
 {
 	struct sockaddr __user *addr;
 	int msg_namelen;
@@ -446,7 +446,7 @@ asmlinkage long sys_oabi_socketcall(int call, unsigned long __user *args)
 		break;
 	case SYS_SENDMSG:
 		if (copy_from_user(a, args, 3 * sizeof(long)) == 0)
-			r = sys_oabi_sendmsg(a[0], (struct msghdr __user *)a[1], a[2]);
+			r = sys_oabi_sendmsg(a[0], (struct user_msghdr __user *)a[1], a[2]);
 		break;
 	default:
 		r = sys_socketcall(call, args);
diff --git a/include/linux/socket.h b/include/linux/socket.h
index bb9b8364007..51bd6668b80 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -53,10 +53,20 @@ struct msghdr {
 	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
 	unsigned int	msg_flags;	/* flags on received message */
 };
+ 
+struct user_msghdr {
+	void		__user *msg_name;	/* ptr to socket address structure */
+	int		msg_namelen;		/* size of socket address structure */
+	struct iovec	__user *msg_iov;	/* scatter/gather array */
+	__kernel_size_t	msg_iovlen;		/* # elements in msg_iov */
+	void		__user *msg_control;	/* ancillary data */
+	__kernel_size_t	msg_controllen;		/* ancillary data buffer length */
+	unsigned int	msg_flags;		/* flags on received message */
+};
 
 /* For recvmmsg/sendmmsg */
 struct mmsghdr {
-	struct msghdr   msg_hdr;
+	struct user_msghdr  msg_hdr;
 	unsigned int        msg_len;
 };
 
@@ -319,8 +329,8 @@ extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
 struct timespec;
 
 /* The __sys_...msg variants allow MSG_CMSG_COMPAT */
-extern long __sys_recvmsg(int fd, struct msghdr __user *msg, unsigned flags);
-extern long __sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags);
+extern long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags);
+extern long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags);
 extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 			  unsigned int flags, struct timespec *timeout);
 extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index bda9b81357c..c9afdc7a7f8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -25,7 +25,7 @@ struct linux_dirent64;
 struct list_head;
 struct mmap_arg_struct;
 struct msgbuf;
-struct msghdr;
+struct user_msghdr;
 struct mmsghdr;
 struct msqid_ds;
 struct new_utsname;
@@ -601,13 +601,13 @@ asmlinkage long sys_getpeername(int, struct sockaddr __user *, int __user *);
 asmlinkage long sys_send(int, void __user *, size_t, unsigned);
 asmlinkage long sys_sendto(int, void __user *, size_t, unsigned,
 				struct sockaddr __user *, int);
-asmlinkage long sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags);
+asmlinkage long sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags);
 asmlinkage long sys_sendmmsg(int fd, struct mmsghdr __user *msg,
 			     unsigned int vlen, unsigned flags);
 asmlinkage long sys_recv(int, void __user *, size_t, unsigned);
 asmlinkage long sys_recvfrom(int, void __user *, size_t, unsigned,
 				struct sockaddr __user *, int __user *);
-asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, unsigned flags);
+asmlinkage long sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags);
 asmlinkage long sys_recvmmsg(int fd, struct mmsghdr __user *msg,
 			     unsigned int vlen, unsigned flags,
 			     struct timespec __user *timeout);
diff --git a/net/compat.c b/net/compat.c
index bc8aeefddf3..562e920b07f 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -740,7 +740,7 @@ COMPAT_SYSCALL_DEFINE3(sendmsg, int, fd, struct compat_msghdr __user *, msg, uns
 {
 	if (flags & MSG_CMSG_COMPAT)
 		return -EINVAL;
-	return __sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
+	return __sys_sendmsg(fd, (struct user_msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
 }
 
 COMPAT_SYSCALL_DEFINE4(sendmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
@@ -756,7 +756,7 @@ COMPAT_SYSCALL_DEFINE3(recvmsg, int, fd, struct compat_msghdr __user *, msg, uns
 {
 	if (flags & MSG_CMSG_COMPAT)
 		return -EINVAL;
-	return __sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
+	return __sys_recvmsg(fd, (struct user_msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
 }
 
 COMPAT_SYSCALL_DEFINE4(recv, int, fd, void __user *, buf, compat_size_t, len, unsigned int, flags)
diff --git a/net/socket.c b/net/socket.c
index fe20c319a0b..0ae8147e3ac 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1989,8 +1989,11 @@ struct used_address {
 };
 
 static int copy_msghdr_from_user(struct msghdr *kmsg,
-				 struct msghdr __user *umsg)
+				 struct user_msghdr __user *umsg)
 {
+	/* We are relying on the (currently) identical layouts.  Once
+	 * the kernel-side changes, this place will need to be updated
+	 */
 	if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
 		return -EFAULT;
 
@@ -2005,7 +2008,7 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 	return 0;
 }
 
-static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
+static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 			 struct msghdr *msg_sys, unsigned int flags,
 			 struct used_address *used_address)
 {
@@ -2123,7 +2126,7 @@ out:
  *	BSD sendmsg interface
  */
 
-long __sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags)
+long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags)
 {
 	int fput_needed, err;
 	struct msghdr msg_sys;
@@ -2140,7 +2143,7 @@ out:
 	return err;
 }
 
-SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned int, flags)
+SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags)
 {
 	if (flags & MSG_CMSG_COMPAT)
 		return -EINVAL;
@@ -2177,7 +2180,7 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 
 	while (datagrams < vlen) {
 		if (MSG_CMSG_COMPAT & flags) {
-			err = ___sys_sendmsg(sock, (struct msghdr __user *)compat_entry,
+			err = ___sys_sendmsg(sock, (struct user_msghdr __user *)compat_entry,
 					     &msg_sys, flags, &used_address);
 			if (err < 0)
 				break;
@@ -2185,7 +2188,7 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 			++compat_entry;
 		} else {
 			err = ___sys_sendmsg(sock,
-					     (struct msghdr __user *)entry,
+					     (struct user_msghdr __user *)entry,
 					     &msg_sys, flags, &used_address);
 			if (err < 0)
 				break;
@@ -2215,7 +2218,7 @@ SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg,
 	return __sys_sendmmsg(fd, mmsg, vlen, flags);
 }
 
-static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
+static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
 			 struct msghdr *msg_sys, unsigned int flags, int nosec)
 {
 	struct compat_msghdr __user *msg_compat =
@@ -2311,7 +2314,7 @@ out:
  *	BSD recvmsg interface
  */
 
-long __sys_recvmsg(int fd, struct msghdr __user *msg, unsigned flags)
+long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags)
 {
 	int fput_needed, err;
 	struct msghdr msg_sys;
@@ -2328,7 +2331,7 @@ out:
 	return err;
 }
 
-SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg,
+SYSCALL_DEFINE3(recvmsg, int, fd, struct user_msghdr __user *, msg,
 		unsigned int, flags)
 {
 	if (flags & MSG_CMSG_COMPAT)
@@ -2373,7 +2376,7 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 		 * No need to ask LSM for more than the first datagram.
 		 */
 		if (MSG_CMSG_COMPAT & flags) {
-			err = ___sys_recvmsg(sock, (struct msghdr __user *)compat_entry,
+			err = ___sys_recvmsg(sock, (struct user_msghdr __user *)compat_entry,
 					     &msg_sys, flags & ~MSG_WAITFORONE,
 					     datagrams);
 			if (err < 0)
@@ -2382,7 +2385,7 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 			++compat_entry;
 		} else {
 			err = ___sys_recvmsg(sock,
-					     (struct msghdr __user *)entry,
+					     (struct user_msghdr __user *)entry,
 					     &msg_sys, flags & ~MSG_WAITFORONE,
 					     datagrams);
 			if (err < 0)
@@ -2571,13 +2574,13 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
 				   (int __user *)a[4]);
 		break;
 	case SYS_SENDMSG:
-		err = sys_sendmsg(a0, (struct msghdr __user *)a1, a[2]);
+		err = sys_sendmsg(a0, (struct user_msghdr __user *)a1, a[2]);
 		break;
 	case SYS_SENDMMSG:
 		err = sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3]);
 		break;
 	case SYS_RECVMSG:
-		err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]);
+		err = sys_recvmsg(a0, (struct user_msghdr __user *)a1, a[2]);
 		break;
 	case SYS_RECVMMSG:
 		err = sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3],
-- 
cgit v1.2.3-70-g09d2


From 08adb7dabd4874cc5666b4490653b26534702ce0 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 10 Nov 2014 20:23:13 -0500
Subject: fold verify_iovec() into copy_msghdr_from_user()

... and do the same on the compat side of things.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/socket.h |  1 -
 include/net/compat.h   |  5 ++-
 net/compat.c           | 52 ++++++++++++----------------
 net/core/iovec.c       | 38 ---------------------
 net/socket.c           | 93 ++++++++++++++++++++++++++++----------------------
 5 files changed, 77 insertions(+), 112 deletions(-)

(limited to 'include')

diff --git a/include/linux/socket.h b/include/linux/socket.h
index 51bd6668b80..de5222832be 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -322,7 +322,6 @@ extern int csum_partial_copy_fromiovecend(unsigned char *kdata,
 extern unsigned long iov_pages(const struct iovec *iov, int offset,
 			       unsigned long nr_segs);
 
-extern int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *address, int mode);
 extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr);
 extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
 
diff --git a/include/net/compat.h b/include/net/compat.h
index 3b603b199c0..42a9c843117 100644
--- a/include/net/compat.h
+++ b/include/net/compat.h
@@ -40,9 +40,8 @@ int compat_sock_get_timestampns(struct sock *, struct timespec __user *);
 #define compat_mmsghdr	mmsghdr
 #endif /* defined(CONFIG_COMPAT) */
 
-int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *);
-int verify_compat_iovec(struct msghdr *, struct iovec *,
-			struct sockaddr_storage *, int);
+ssize_t get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *,
+		      struct sockaddr __user **, struct iovec **);
 asmlinkage long compat_sys_sendmsg(int, struct compat_msghdr __user *,
 				   unsigned int);
 asmlinkage long compat_sys_sendmmsg(int, struct compat_mmsghdr __user *,
diff --git a/net/compat.c b/net/compat.c
index 7b4b6ad1323..062f157d2a6 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -31,14 +31,18 @@
 #include <asm/uaccess.h>
 #include <net/compat.h>
 
-int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg)
+ssize_t get_compat_msghdr(struct msghdr *kmsg,
+			  struct compat_msghdr __user *umsg,
+			  struct sockaddr __user **save_addr,
+			  struct iovec **iov)
 {
-	compat_uptr_t tmp1, tmp2, tmp3;
+	compat_uptr_t uaddr, uiov, tmp3;
+	ssize_t err;
 
 	if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) ||
-	    __get_user(tmp1, &umsg->msg_name) ||
+	    __get_user(uaddr, &umsg->msg_name) ||
 	    __get_user(kmsg->msg_namelen, &umsg->msg_namelen) ||
-	    __get_user(tmp2, &umsg->msg_iov) ||
+	    __get_user(uiov, &umsg->msg_iov) ||
 	    __get_user(kmsg->msg_iovlen, &umsg->msg_iovlen) ||
 	    __get_user(tmp3, &umsg->msg_control) ||
 	    __get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
@@ -46,44 +50,32 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg)
 		return -EFAULT;
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
-	kmsg->msg_name = compat_ptr(tmp1);
-	kmsg->msg_iov = compat_ptr(tmp2);
 	kmsg->msg_control = compat_ptr(tmp3);
-	return 0;
-}
 
-/* I've named the args so it is easy to tell whose space the pointers are in. */
-int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *iov,
-		   struct sockaddr_storage *kern_address, int mode)
-{
-	struct compat_iovec __user *p;
-	struct iovec *res;
-	int err;
+	if (save_addr)
+		*save_addr = compat_ptr(uaddr);
 
-	if (kern_msg->msg_name && kern_msg->msg_namelen) {
-		if (mode == WRITE) {
-			int err = move_addr_to_kernel(kern_msg->msg_name,
-						      kern_msg->msg_namelen,
-						      kern_address);
+	if (uaddr && kmsg->msg_namelen) {
+		if (!save_addr) {
+			err = move_addr_to_kernel(compat_ptr(uaddr),
+						  kmsg->msg_namelen,
+						  kmsg->msg_name);
 			if (err < 0)
 				return err;
 		}
-		kern_msg->msg_name = kern_address;
 	} else {
-		kern_msg->msg_name = NULL;
-		kern_msg->msg_namelen = 0;
+		kmsg->msg_name = NULL;
+		kmsg->msg_namelen = 0;
 	}
 
-	if (kern_msg->msg_iovlen > UIO_MAXIOV)
+	if (kmsg->msg_iovlen > UIO_MAXIOV)
 		return -EMSGSIZE;
 
-	p = (struct compat_iovec __user *)kern_msg->msg_iov;
-	err = compat_rw_copy_check_uvector(mode, p, kern_msg->msg_iovlen,
-					   UIO_FASTIOV, iov, &res);
+	err = compat_rw_copy_check_uvector(save_addr ? READ : WRITE,
+					   compat_ptr(uiov), kmsg->msg_iovlen,
+					   UIO_FASTIOV, *iov, iov);
 	if (err >= 0)
-		kern_msg->msg_iov = res;
-	else if (res != iov)
-		kfree(res);
+		kmsg->msg_iov = *iov;
 	return err;
 }
 
diff --git a/net/core/iovec.c b/net/core/iovec.c
index 86beeea61d7..dcbe98b3726 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -27,44 +27,6 @@
 #include <net/checksum.h>
 #include <net/sock.h>
 
-/*
- *	Verify iovec. The caller must ensure that the iovec is big enough
- *	to hold the message iovec.
- *
- *	Save time not doing access_ok. copy_*_user will make this work
- *	in any case.
- */
-
-int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *address, int mode)
-{
-	struct iovec *res;
-	int err;
-
-	if (m->msg_name && m->msg_namelen) {
-		if (mode == WRITE) {
-			void __user *namep = (void __user __force *)m->msg_name;
-			int err = move_addr_to_kernel(namep, m->msg_namelen,
-						  address);
-			if (err < 0)
-				return err;
-		}
-		m->msg_name = address;
-	} else {
-		m->msg_name = NULL;
-		m->msg_namelen = 0;
-	}
-	if (m->msg_iovlen > UIO_MAXIOV)
-		return -EMSGSIZE;
-
-	err = rw_copy_check_uvector(mode, (void __user __force *)m->msg_iov,
-				    m->msg_iovlen, UIO_FASTIOV, iov, &res);
-	if (err >= 0)
-		m->msg_iov = res;
-	else if (res != iov)
-		kfree(res);
-	return err;
-}
-
 /*
  *	And now for the all-in-one: copy and checksum from a user iovec
  *	directly to a datagram
diff --git a/net/socket.c b/net/socket.c
index 59020f0b583..ee3ee39eefa 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1988,16 +1988,26 @@ struct used_address {
 	unsigned int name_len;
 };
 
-static int copy_msghdr_from_user(struct msghdr *kmsg,
-				 struct user_msghdr __user *umsg)
+static ssize_t copy_msghdr_from_user(struct msghdr *kmsg,
+				     struct user_msghdr __user *umsg,
+				     struct sockaddr __user **save_addr,
+				     struct iovec **iov)
 {
-	/* We are relying on the (currently) identical layouts.  Once
-	 * the kernel-side changes, this place will need to be updated
-	 */
-	if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
+	struct sockaddr __user *uaddr;
+	struct iovec __user *uiov;
+	ssize_t err;
+
+	if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) ||
+	    __get_user(uaddr, &umsg->msg_name) ||
+	    __get_user(kmsg->msg_namelen, &umsg->msg_namelen) ||
+	    __get_user(uiov, &umsg->msg_iov) ||
+	    __get_user(kmsg->msg_iovlen, &umsg->msg_iovlen) ||
+	    __get_user(kmsg->msg_control, &umsg->msg_control) ||
+	    __get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
+	    __get_user(kmsg->msg_flags, &umsg->msg_flags))
 		return -EFAULT;
 
-	if (kmsg->msg_name == NULL)
+	if (!uaddr)
 		kmsg->msg_namelen = 0;
 
 	if (kmsg->msg_namelen < 0)
@@ -2005,7 +2015,31 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
-	return 0;
+
+	if (save_addr)
+		*save_addr = uaddr;
+
+	if (uaddr && kmsg->msg_namelen) {
+		if (!save_addr) {
+			err = move_addr_to_kernel(uaddr, kmsg->msg_namelen,
+						  kmsg->msg_name);
+			if (err < 0)
+				return err;
+		}
+	} else {
+		kmsg->msg_name = NULL;
+		kmsg->msg_namelen = 0;
+	}
+
+	if (kmsg->msg_iovlen > UIO_MAXIOV)
+		return -EMSGSIZE;
+
+	err = rw_copy_check_uvector(save_addr ? READ : WRITE,
+				    uiov, kmsg->msg_iovlen,
+				    UIO_FASTIOV, *iov, iov);
+	if (err >= 0)
+		kmsg->msg_iov = *iov;
+	return err;
 }
 
 static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
@@ -2020,26 +2054,17 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 	    __attribute__ ((aligned(sizeof(__kernel_size_t))));
 	/* 20 is size of ipv6_pktinfo */
 	unsigned char *ctl_buf = ctl;
-	int err, ctl_len, total_len;
+	int ctl_len, total_len;
+	ssize_t err;
 
-	err = -EFAULT;
-	if (MSG_CMSG_COMPAT & flags) {
-		if (get_compat_msghdr(msg_sys, msg_compat))
-			return -EFAULT;
-	} else {
-		err = copy_msghdr_from_user(msg_sys, msg);
-		if (err)
-			return err;
-	}
+	msg_sys->msg_name = &address;
 
-	/* This will also move the address data into kernel space */
 	if (MSG_CMSG_COMPAT & flags)
-		err = verify_compat_iovec(msg_sys, iovstack, &address, WRITE);
+		err = get_compat_msghdr(msg_sys, msg_compat, NULL, &iov);
 	else
-		err = verify_iovec(msg_sys, iovstack, &address, WRITE);
+		err = copy_msghdr_from_user(msg_sys, msg, NULL, &iov);
 	if (err < 0)
 		goto out_freeiov;
-	iov = msg_sys->msg_iov;
 	total_len = err;
 
 	err = -ENOBUFS;
@@ -2215,36 +2240,24 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov = iovstack;
 	unsigned long cmsg_ptr;
-	int err, total_len, len;
+	int total_len, len;
+	ssize_t err;
 
 	/* kernel mode address */
 	struct sockaddr_storage addr;
 
 	/* user mode address pointers */
 	struct sockaddr __user *uaddr;
-	int __user *uaddr_len;
+	int __user *uaddr_len = COMPAT_NAMELEN(msg);
 
-	if (MSG_CMSG_COMPAT & flags) {
-		if (get_compat_msghdr(msg_sys, msg_compat))
-			return -EFAULT;
-	} else {
-		err = copy_msghdr_from_user(msg_sys, msg);
-		if (err)
-			return err;
-	}
+	msg_sys->msg_name = &addr;
 
-	/* Save the user-mode address (verify_iovec will change the
-	 * kernel msghdr to use the kernel address space)
-	 */
-	uaddr = (__force void __user *)msg_sys->msg_name;
-	uaddr_len = COMPAT_NAMELEN(msg);
 	if (MSG_CMSG_COMPAT & flags)
-		err = verify_compat_iovec(msg_sys, iovstack, &addr, READ);
+		err = get_compat_msghdr(msg_sys, msg_compat, &uaddr, &iov);
 	else
-		err = verify_iovec(msg_sys, iovstack, &addr, READ);
+		err = copy_msghdr_from_user(msg_sys, msg, &uaddr, &iov);
 	if (err < 0)
 		goto out_freeiov;
-	iov = msg_sys->msg_iov;
 	total_len = err;
 
 	cmsg_ptr = (unsigned long)msg_sys->msg_control;
-- 
cgit v1.2.3-70-g09d2


From 232365f660b0016dcf618723707f91f4a95013db Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 10 Nov 2014 17:30:00 -0500
Subject: bury skb_copy_to_page()

no callers since 3.0

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/net/sock.h | 23 -----------------------
 1 file changed, 23 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 83a669f83ba..df9b89bce8f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1884,29 +1884,6 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, char __user *from,
 	return 0;
 }
 
-static inline int skb_copy_to_page(struct sock *sk, char __user *from,
-				   struct sk_buff *skb, struct page *page,
-				   int off, int copy)
-{
-	if (skb->ip_summed == CHECKSUM_NONE) {
-		int err = 0;
-		__wsum csum = csum_and_copy_from_user(from,
-						     page_address(page) + off,
-							    copy, 0, &err);
-		if (err)
-			return err;
-		skb->csum = csum_block_add(skb->csum, csum, skb->len);
-	} else if (copy_from_user(page_address(page) + off, from, copy))
-		return -EFAULT;
-
-	skb->len	     += copy;
-	skb->data_len	     += copy;
-	skb->truesize	     += copy;
-	sk->sk_wmem_queued   += copy;
-	sk_mem_charge(sk, copy);
-	return 0;
-}
-
 /**
  * sk_wmem_alloc_get - returns write allocations
  * @sk: socket
-- 
cgit v1.2.3-70-g09d2


From 3a161d99c43ce74c76aecff309be4c3ba455e823 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 25 Jun 2014 15:54:42 -0400
Subject: tracing: Create seq_buf layer in trace_seq

Create a seq_buf layer that trace_seq sits on. The seq_buf will not
be limited to page size. This will allow other usages of seq_buf
instead of a hard set PAGE_SIZE one that trace_seq has.

Link: http://lkml.kernel.org/r/20141104160221.864997179@goodmis.org
Link: http://lkml.kernel.org/r/20141114011412.170377300@goodmis.org

Tested-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/seq_buf.h              |  81 +++++++++
 include/linux/trace_seq.h            |  12 +-
 kernel/trace/Makefile                |   1 +
 kernel/trace/seq_buf.c               | 341 +++++++++++++++++++++++++++++++++++
 kernel/trace/trace.c                 |  39 ++--
 kernel/trace/trace_events.c          |   6 +-
 kernel/trace/trace_functions_graph.c |   6 +-
 kernel/trace/trace_seq.c             | 178 +++++++++---------
 8 files changed, 538 insertions(+), 126 deletions(-)
 create mode 100644 include/linux/seq_buf.h
 create mode 100644 kernel/trace/seq_buf.c

(limited to 'include')

diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
new file mode 100644
index 00000000000..4f7a96a9d71
--- /dev/null
+++ b/include/linux/seq_buf.h
@@ -0,0 +1,81 @@
+#ifndef _LINUX_SEQ_BUF_H
+#define _LINUX_SEQ_BUF_H
+
+#include <linux/fs.h>
+
+/*
+ * Trace sequences are used to allow a function to call several other functions
+ * to create a string of data to use.
+ */
+
+/**
+ * seq_buf - seq buffer structure
+ * @buffer:	pointer to the buffer
+ * @size:	size of the buffer
+ * @len:	the amount of data inside the buffer
+ * @readpos:	The next position to read in the buffer.
+ */
+struct seq_buf {
+	unsigned char		*buffer;
+	unsigned int		size;
+	unsigned int		len;
+	unsigned int		readpos;
+};
+
+static inline void
+seq_buf_init(struct seq_buf *s, unsigned char *buf, unsigned int size)
+{
+	s->buffer = buf;
+	s->size = size;
+	s->len = 0;
+	s->readpos = 0;
+}
+
+/*
+ * seq_buf have a buffer that might overflow. When this happens
+ * the len and size are set to be equal.
+ */
+static inline bool
+seq_buf_has_overflowed(struct seq_buf *s)
+{
+	return s->len == s->size;
+}
+
+static inline void
+seq_buf_set_overflow(struct seq_buf *s)
+{
+	s->len = s->size;
+}
+
+/*
+ * How much buffer is left on the seq_buf?
+ */
+static inline unsigned int
+seq_buf_buffer_left(struct seq_buf *s)
+{
+	if (seq_buf_has_overflowed(s))
+		return 0;
+
+	return (s->size - 1) - s->len;
+}
+
+extern __printf(2, 3)
+int seq_buf_printf(struct seq_buf *s, const char *fmt, ...);
+extern __printf(2, 0)
+int seq_buf_vprintf(struct seq_buf *s, const char *fmt, va_list args);
+extern int
+seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary);
+extern int seq_buf_print_seq(struct seq_file *m, struct seq_buf *s);
+extern int seq_buf_to_user(struct seq_buf *s, char __user *ubuf,
+			   int cnt);
+extern int seq_buf_puts(struct seq_buf *s, const char *str);
+extern int seq_buf_putc(struct seq_buf *s, unsigned char c);
+extern int seq_buf_putmem(struct seq_buf *s, const void *mem, unsigned int len);
+extern int seq_buf_putmem_hex(struct seq_buf *s, const void *mem,
+			      unsigned int len);
+extern int seq_buf_path(struct seq_buf *s, const struct path *path);
+
+extern int seq_buf_bitmask(struct seq_buf *s, const unsigned long *maskp,
+			   int nmaskbits);
+
+#endif /* _LINUX_SEQ_BUF_H */
diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
index db8a73224f1..85d37106be3 100644
--- a/include/linux/trace_seq.h
+++ b/include/linux/trace_seq.h
@@ -1,7 +1,7 @@
 #ifndef _LINUX_TRACE_SEQ_H
 #define _LINUX_TRACE_SEQ_H
 
-#include <linux/fs.h>
+#include <linux/seq_buf.h>
 
 #include <asm/page.h>
 
@@ -12,16 +12,14 @@
 
 struct trace_seq {
 	unsigned char		buffer[PAGE_SIZE];
-	unsigned int		len;
-	unsigned int		readpos;
+	struct seq_buf		seq;
 	int			full;
 };
 
 static inline void
 trace_seq_init(struct trace_seq *s)
 {
-	s->len = 0;
-	s->readpos = 0;
+	seq_buf_init(&s->seq, s->buffer, PAGE_SIZE);
 	s->full = 0;
 }
 
@@ -37,7 +35,7 @@ trace_seq_init(struct trace_seq *s)
 static inline unsigned char *
 trace_seq_buffer_ptr(struct trace_seq *s)
 {
-	return s->buffer + s->len;
+	return s->buffer + s->seq.len;
 }
 
 /**
@@ -49,7 +47,7 @@ trace_seq_buffer_ptr(struct trace_seq *s)
  */
 static inline bool trace_seq_has_overflowed(struct trace_seq *s)
 {
-	return s->full || s->len > PAGE_SIZE - 1;
+	return s->full || seq_buf_has_overflowed(&s->seq);
 }
 
 /*
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 67d6369ddf8..edc98c72a63 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_RING_BUFFER_BENCHMARK) += ring_buffer_benchmark.o
 obj-$(CONFIG_TRACING) += trace.o
 obj-$(CONFIG_TRACING) += trace_output.o
 obj-$(CONFIG_TRACING) += trace_seq.o
+obj-$(CONFIG_TRACING) += seq_buf.o
 obj-$(CONFIG_TRACING) += trace_stat.o
 obj-$(CONFIG_TRACING) += trace_printk.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
diff --git a/kernel/trace/seq_buf.c b/kernel/trace/seq_buf.c
new file mode 100644
index 00000000000..e9a7861595d
--- /dev/null
+++ b/kernel/trace/seq_buf.c
@@ -0,0 +1,341 @@
+/*
+ * seq_buf.c
+ *
+ * Copyright (C) 2014 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * The seq_buf is a handy tool that allows you to pass a descriptor around
+ * to a buffer that other functions can write to. It is similar to the
+ * seq_file functionality but has some differences.
+ *
+ * To use it, the seq_buf must be initialized with seq_buf_init().
+ * This will set up the counters within the descriptor. You can call
+ * seq_buf_init() more than once to reset the seq_buf to start
+ * from scratch.
+ */
+#include <linux/uaccess.h>
+#include <linux/seq_file.h>
+#include <linux/seq_buf.h>
+
+/* How much buffer is written? */
+#define SEQ_BUF_USED(s) min((s)->len, (s)->size - 1)
+
+/**
+ * seq_buf_print_seq - move the contents of seq_buf into a seq_file
+ * @m: the seq_file descriptor that is the destination
+ * @s: the seq_buf descriptor that is the source.
+ *
+ * Returns zero on success, non zero otherwise
+ */
+int seq_buf_print_seq(struct seq_file *m, struct seq_buf *s)
+{
+	unsigned int len = SEQ_BUF_USED(s);
+
+	return seq_write(m, s->buffer, len);
+}
+
+/**
+ * seq_buf_vprintf - sequence printing of information.
+ * @s: seq_buf descriptor
+ * @fmt: printf format string
+ * @args: va_list of arguments from a printf() type function
+ *
+ * Writes a vnprintf() format into the sequencce buffer.
+ *
+ * Returns zero on success, -1 on overflow.
+ */
+int seq_buf_vprintf(struct seq_buf *s, const char *fmt, va_list args)
+{
+	int len;
+
+	WARN_ON(s->size == 0);
+
+	if (s->len < s->size) {
+		len = vsnprintf(s->buffer + s->len, s->size - s->len, fmt, args);
+		if (s->len + len < s->size) {
+			s->len += len;
+			return 0;
+		}
+	}
+	seq_buf_set_overflow(s);
+	return -1;
+}
+
+/**
+ * seq_buf_printf - sequence printing of information
+ * @s: seq_buf descriptor
+ * @fmt: printf format string
+ *
+ * Writes a printf() format into the sequence buffer.
+ *
+ * Returns zero on success, -1 on overflow.
+ */
+int seq_buf_printf(struct seq_buf *s, const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	va_start(ap, fmt);
+	ret = seq_buf_vprintf(s, fmt, ap);
+	va_end(ap);
+
+	return ret;
+}
+
+/**
+ * seq_buf_bitmask - write a bitmask array in its ASCII representation
+ * @s:		seq_buf descriptor
+ * @maskp:	points to an array of unsigned longs that represent a bitmask
+ * @nmaskbits:	The number of bits that are valid in @maskp
+ *
+ * Writes a ASCII representation of a bitmask string into @s.
+ *
+ * Returns zero on success, -1 on overflow.
+ */
+int seq_buf_bitmask(struct seq_buf *s, const unsigned long *maskp,
+		    int nmaskbits)
+{
+	unsigned int len = seq_buf_buffer_left(s);
+	int ret;
+
+	WARN_ON(s->size == 0);
+
+	/*
+	 * The last byte of the buffer is used to determine if we
+	 * overflowed or not.
+	 */
+	if (len > 1) {
+		ret = bitmap_scnprintf(s->buffer + s->len, len, maskp, nmaskbits);
+		if (ret < len) {
+			s->len += ret;
+			return 0;
+		}
+	}
+	seq_buf_set_overflow(s);
+	return -1;
+}
+
+/**
+ * seq_buf_bprintf - Write the printf string from binary arguments
+ * @s: seq_buf descriptor
+ * @fmt: The format string for the @binary arguments
+ * @binary: The binary arguments for @fmt.
+ *
+ * When recording in a fast path, a printf may be recorded with just
+ * saving the format and the arguments as they were passed to the
+ * function, instead of wasting cycles converting the arguments into
+ * ASCII characters. Instead, the arguments are saved in a 32 bit
+ * word array that is defined by the format string constraints.
+ *
+ * This function will take the format and the binary array and finish
+ * the conversion into the ASCII string within the buffer.
+ *
+ * Returns zero on success, -1 on overflow.
+ */
+int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary)
+{
+	unsigned int len = seq_buf_buffer_left(s);
+	int ret;
+
+	WARN_ON(s->size == 0);
+
+	if (s->len < s->size) {
+		ret = bstr_printf(s->buffer + s->len, len, fmt, binary);
+		if (s->len + ret < s->size) {
+			s->len += ret;
+			return 0;
+		}
+	}
+	seq_buf_set_overflow(s);
+	return -1;
+}
+
+/**
+ * seq_buf_puts - sequence printing of simple string
+ * @s: seq_buf descriptor
+ * @str: simple string to record
+ *
+ * Copy a simple string into the sequence buffer.
+ *
+ * Returns zero on success, -1 on overflow
+ */
+int seq_buf_puts(struct seq_buf *s, const char *str)
+{
+	unsigned int len = strlen(str);
+
+	WARN_ON(s->size == 0);
+
+	if (s->len + len < s->size) {
+		memcpy(s->buffer + s->len, str, len);
+		s->len += len;
+		return 0;
+	}
+	seq_buf_set_overflow(s);
+	return -1;
+}
+
+/**
+ * seq_buf_putc - sequence printing of simple character
+ * @s: seq_buf descriptor
+ * @c: simple character to record
+ *
+ * Copy a single character into the sequence buffer.
+ *
+ * Returns zero on success, -1 on overflow
+ */
+int seq_buf_putc(struct seq_buf *s, unsigned char c)
+{
+	WARN_ON(s->size == 0);
+
+	if (s->len + 1 < s->size) {
+		s->buffer[s->len++] = c;
+		return 0;
+	}
+	seq_buf_set_overflow(s);
+	return -1;
+}
+
+/**
+ * seq_buf_putmem - write raw data into the sequenc buffer
+ * @s: seq_buf descriptor
+ * @mem: The raw memory to copy into the buffer
+ * @len: The length of the raw memory to copy (in bytes)
+ *
+ * There may be cases where raw memory needs to be written into the
+ * buffer and a strcpy() would not work. Using this function allows
+ * for such cases.
+ *
+ * Returns zero on success, -1 on overflow
+ */
+int seq_buf_putmem(struct seq_buf *s, const void *mem, unsigned int len)
+{
+	WARN_ON(s->size == 0);
+
+	if (s->len + len < s->size) {
+		memcpy(s->buffer + s->len, mem, len);
+		s->len += len;
+		return 0;
+	}
+	seq_buf_set_overflow(s);
+	return -1;
+}
+
+#define MAX_MEMHEX_BYTES	8U
+#define HEX_CHARS		(MAX_MEMHEX_BYTES*2 + 1)
+
+/**
+ * seq_buf_putmem_hex - write raw memory into the buffer in ASCII hex
+ * @s: seq_buf descriptor
+ * @mem: The raw memory to write its hex ASCII representation of
+ * @len: The length of the raw memory to copy (in bytes)
+ *
+ * This is similar to seq_buf_putmem() except instead of just copying the
+ * raw memory into the buffer it writes its ASCII representation of it
+ * in hex characters.
+ *
+ * Returns zero on success, -1 on overflow
+ */
+int seq_buf_putmem_hex(struct seq_buf *s, const void *mem,
+		       unsigned int len)
+{
+	unsigned char hex[HEX_CHARS];
+	const unsigned char *data = mem;
+	unsigned int start_len;
+	int i, j;
+
+	WARN_ON(s->size == 0);
+
+	while (len) {
+		start_len = min(len, HEX_CHARS - 1);
+#ifdef __BIG_ENDIAN
+		for (i = 0, j = 0; i < start_len; i++) {
+#else
+		for (i = start_len-1, j = 0; i >= 0; i--) {
+#endif
+			hex[j++] = hex_asc_hi(data[i]);
+			hex[j++] = hex_asc_lo(data[i]);
+		}
+		if (WARN_ON_ONCE(j == 0 || j/2 > len))
+			break;
+
+		/* j increments twice per loop */
+		len -= j / 2;
+		hex[j++] = ' ';
+
+		seq_buf_putmem(s, hex, j);
+		if (seq_buf_has_overflowed(s))
+			return -1;
+	}
+	return 0;
+}
+
+/**
+ * seq_buf_path - copy a path into the sequence buffer
+ * @s: seq_buf descriptor
+ * @path: path to write into the sequence buffer.
+ *
+ * Write a path name into the sequence buffer.
+ *
+ * Returns zero on success, -1 on overflow
+ */
+int seq_buf_path(struct seq_buf *s, const struct path *path)
+{
+	unsigned int len = seq_buf_buffer_left(s);
+	unsigned char *p;
+
+	WARN_ON(s->size == 0);
+
+	p = d_path(path, s->buffer + s->len, len);
+	if (!IS_ERR(p)) {
+		p = mangle_path(s->buffer + s->len, p, "\n");
+		if (p) {
+			s->len = p - s->buffer;
+			return 0;
+		}
+	}
+	seq_buf_set_overflow(s);
+	return -1;
+}
+
+/**
+ * seq_buf_to_user - copy the squence buffer to user space
+ * @s: seq_buf descriptor
+ * @ubuf: The userspace memory location to copy to
+ * @cnt: The amount to copy
+ *
+ * Copies the sequence buffer into the userspace memory pointed to
+ * by @ubuf. It starts from the last read position (@s->readpos)
+ * and writes up to @cnt characters or till it reaches the end of
+ * the content in the buffer (@s->len), which ever comes first.
+ *
+ * On success, it returns a positive number of the number of bytes
+ * it copied.
+ *
+ * On failure it returns -EBUSY if all of the content in the
+ * sequence has been already read, which includes nothing in the
+ * sequence (@s->len == @s->readpos).
+ *
+ * Returns -EFAULT if the copy to userspace fails.
+ */
+int seq_buf_to_user(struct seq_buf *s, char __user *ubuf, int cnt)
+{
+	int len;
+	int ret;
+
+	if (!cnt)
+		return 0;
+
+	if (s->len <= s->readpos)
+		return -EBUSY;
+
+	len = s->len - s->readpos;
+	if (cnt > len)
+		cnt = len;
+	ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt);
+	if (ret == cnt)
+		return -EFAULT;
+
+	cnt -= ret;
+
+	s->readpos += cnt;
+	return cnt;
+}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3ce3c4ccfc9..7d7a07e9b9e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -939,19 +939,20 @@ out:
 	return ret;
 }
 
+/* TODO add a seq_buf_to_buffer() */
 static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 {
 	int len;
 
-	if (s->len <= s->readpos)
+	if (s->seq.len <= s->seq.readpos)
 		return -EBUSY;
 
-	len = s->len - s->readpos;
+	len = s->seq.len - s->seq.readpos;
 	if (cnt > len)
 		cnt = len;
-	memcpy(buf, s->buffer + s->readpos, cnt);
+	memcpy(buf, s->buffer + s->seq.readpos, cnt);
 
-	s->readpos += cnt;
+	s->seq.readpos += cnt;
 	return cnt;
 }
 
@@ -4315,6 +4316,8 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 		goto out;
 	}
 
+	trace_seq_init(&iter->seq);
+
 	/*
 	 * We make a copy of the current tracer to avoid concurrent
 	 * changes on it while we are reading.
@@ -4511,18 +4514,18 @@ waitagain:
 	trace_access_lock(iter->cpu_file);
 	while (trace_find_next_entry_inc(iter) != NULL) {
 		enum print_line_t ret;
-		int len = iter->seq.len;
+		int len = iter->seq.seq.len;
 
 		ret = print_trace_line(iter);
 		if (ret == TRACE_TYPE_PARTIAL_LINE) {
 			/* don't print partial lines */
-			iter->seq.len = len;
+			iter->seq.seq.len = len;
 			break;
 		}
 		if (ret != TRACE_TYPE_NO_CONSUME)
 			trace_consume(iter);
 
-		if (iter->seq.len >= cnt)
+		if (iter->seq.seq.len >= cnt)
 			break;
 
 		/*
@@ -4538,7 +4541,7 @@ waitagain:
 
 	/* Now copy what we have to the user */
 	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
-	if (iter->seq.readpos >= iter->seq.len)
+	if (iter->seq.seq.readpos >= iter->seq.seq.len)
 		trace_seq_init(&iter->seq);
 
 	/*
@@ -4576,16 +4579,16 @@ tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
 
 	/* Seq buffer is page-sized, exactly what we need. */
 	for (;;) {
-		count = iter->seq.len;
+		count = iter->seq.seq.len;
 		ret = print_trace_line(iter);
-		count = iter->seq.len - count;
+		count = iter->seq.seq.len - count;
 		if (rem < count) {
 			rem = 0;
-			iter->seq.len -= count;
+			iter->seq.seq.len -= count;
 			break;
 		}
 		if (ret == TRACE_TYPE_PARTIAL_LINE) {
-			iter->seq.len -= count;
+			iter->seq.seq.len -= count;
 			break;
 		}
 
@@ -4666,13 +4669,13 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		/* Copy the data into the page, so we can start over. */
 		ret = trace_seq_to_buffer(&iter->seq,
 					  page_address(spd.pages[i]),
-					  iter->seq.len);
+					  iter->seq.seq.len);
 		if (ret < 0) {
 			__free_page(spd.pages[i]);
 			break;
 		}
 		spd.partial[i].offset = 0;
-		spd.partial[i].len = iter->seq.len;
+		spd.partial[i].len = iter->seq.seq.len;
 
 		trace_seq_init(&iter->seq);
 	}
@@ -5673,7 +5676,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	cnt = ring_buffer_read_events_cpu(trace_buf->buffer, cpu);
 	trace_seq_printf(s, "read events: %ld\n", cnt);
 
-	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
+	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->seq.len);
 
 	kfree(s);
 
@@ -6636,11 +6639,11 @@ void
 trace_printk_seq(struct trace_seq *s)
 {
 	/* Probably should print a warning here. */
-	if (s->len >= TRACE_MAX_PRINT)
-		s->len = TRACE_MAX_PRINT;
+	if (s->seq.len >= TRACE_MAX_PRINT)
+		s->seq.len = TRACE_MAX_PRINT;
 
 	/* should be zero ended, but we are paranoid. */
-	s->buffer[s->len] = 0;
+	s->buffer[s->seq.len] = 0;
 
 	printk(KERN_TRACE "%s", s->buffer);
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f9d0cbe014b..4d0067dd7f8 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1044,7 +1044,7 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 	mutex_unlock(&event_mutex);
 
 	if (file)
-		r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+		r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->seq.len);
 
 	kfree(s);
 
@@ -1210,7 +1210,7 @@ subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 	trace_seq_init(s);
 
 	print_subsystem_event_filter(system, s);
-	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->seq.len);
 
 	kfree(s);
 
@@ -1265,7 +1265,7 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 	trace_seq_init(s);
 
 	func(s);
-	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->seq.len);
 
 	kfree(s);
 
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 100288d10e1..6d1342ae7a4 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -1154,9 +1154,9 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
 	}
 
 	/* Strip ending newline */
-	if (s->buffer[s->len - 1] == '\n') {
-		s->buffer[s->len - 1] = '\0';
-		s->len--;
+	if (s->buffer[s->seq.len - 1] == '\n') {
+		s->buffer[s->seq.len - 1] = '\0';
+		s->seq.len--;
 	}
 
 	trace_seq_puts(s, " */\n");
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index fabfa0f190a..8c0c54fe674 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -27,10 +27,19 @@
 #include <linux/trace_seq.h>
 
 /* How much buffer is left on the trace_seq? */
-#define TRACE_SEQ_BUF_LEFT(s) ((PAGE_SIZE - 1) - (s)->len)
+#define TRACE_SEQ_BUF_LEFT(s) seq_buf_buffer_left(&(s)->seq)
 
 /* How much buffer is written? */
-#define TRACE_SEQ_BUF_USED(s) min((s)->len, (unsigned int)(PAGE_SIZE - 1))
+#define TRACE_SEQ_BUF_USED(s) min((s)->seq.len, (unsigned int)(PAGE_SIZE - 1))
+
+/*
+ * trace_seq should work with being initialized with 0s.
+ */
+static inline void __trace_seq_init(struct trace_seq *s)
+{
+	if (unlikely(!s->seq.size))
+		trace_seq_init(s);
+}
 
 /**
  * trace_print_seq - move the contents of trace_seq into a seq_file
@@ -43,10 +52,11 @@
  */
 int trace_print_seq(struct seq_file *m, struct trace_seq *s)
 {
-	unsigned int len = TRACE_SEQ_BUF_USED(s);
 	int ret;
 
-	ret = seq_write(m, s->buffer, len);
+	__trace_seq_init(s);
+
+	ret = seq_buf_print_seq(m, &s->seq);
 
 	/*
 	 * Only reset this buffer if we successfully wrote to the
@@ -72,24 +82,23 @@ int trace_print_seq(struct seq_file *m, struct trace_seq *s)
  */
 void trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 {
-	unsigned int len = TRACE_SEQ_BUF_LEFT(s);
+	unsigned int save_len = s->seq.len;
 	va_list ap;
-	int ret;
 
-	if (s->full || !len)
+	if (s->full)
 		return;
 
+	__trace_seq_init(s);
+
 	va_start(ap, fmt);
-	ret = vsnprintf(s->buffer + s->len, len, fmt, ap);
+	seq_buf_vprintf(&s->seq, fmt, ap);
 	va_end(ap);
 
 	/* If we can't write it all, don't bother writing anything */
-	if (ret >= len) {
+	if (unlikely(seq_buf_has_overflowed(&s->seq))) {
+		s->seq.len = save_len;
 		s->full = 1;
-		return;
 	}
-
-	s->len += ret;
 }
 EXPORT_SYMBOL_GPL(trace_seq_printf);
 
@@ -104,14 +113,19 @@ EXPORT_SYMBOL_GPL(trace_seq_printf);
 void trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp,
 		      int nmaskbits)
 {
-	unsigned int len = TRACE_SEQ_BUF_LEFT(s);
-	int ret;
+	unsigned int save_len = s->seq.len;
 
-	if (s->full || !len)
+	if (s->full)
 		return;
 
-	ret = bitmap_scnprintf(s->buffer + s->len, len, maskp, nmaskbits);
-	s->len += ret;
+	__trace_seq_init(s);
+
+	seq_buf_bitmask(&s->seq, maskp, nmaskbits);
+
+	if (unlikely(seq_buf_has_overflowed(&s->seq))) {
+		s->seq.len = save_len;
+		s->full = 1;
+	}
 }
 EXPORT_SYMBOL_GPL(trace_seq_bitmask);
 
@@ -128,21 +142,20 @@ EXPORT_SYMBOL_GPL(trace_seq_bitmask);
  */
 void trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
 {
-	unsigned int len = TRACE_SEQ_BUF_LEFT(s);
-	int ret;
+	unsigned int save_len = s->seq.len;
 
-	if (s->full || !len)
+	if (s->full)
 		return;
 
-	ret = vsnprintf(s->buffer + s->len, len, fmt, args);
+	__trace_seq_init(s);
+
+	seq_buf_vprintf(&s->seq, fmt, args);
 
 	/* If we can't write it all, don't bother writing anything */
-	if (ret >= len) {
+	if (unlikely(seq_buf_has_overflowed(&s->seq))) {
+		s->seq.len = save_len;
 		s->full = 1;
-		return;
 	}
-
-	s->len += ret;
 }
 EXPORT_SYMBOL_GPL(trace_seq_vprintf);
 
@@ -163,21 +176,21 @@ EXPORT_SYMBOL_GPL(trace_seq_vprintf);
  */
 void trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
 {
-	unsigned int len = TRACE_SEQ_BUF_LEFT(s);
-	int ret;
+	unsigned int save_len = s->seq.len;
 
-	if (s->full || !len)
+	if (s->full)
 		return;
 
-	ret = bstr_printf(s->buffer + s->len, len, fmt, binary);
+	__trace_seq_init(s);
+
+	seq_buf_bprintf(&s->seq, fmt, binary);
 
 	/* If we can't write it all, don't bother writing anything */
-	if (ret >= len) {
+	if (unlikely(seq_buf_has_overflowed(&s->seq))) {
+		s->seq.len = save_len;
 		s->full = 1;
 		return;
 	}
-
-	s->len += ret;
 }
 EXPORT_SYMBOL_GPL(trace_seq_bprintf);
 
@@ -198,13 +211,14 @@ void trace_seq_puts(struct trace_seq *s, const char *str)
 	if (s->full)
 		return;
 
+	__trace_seq_init(s);
+
 	if (len > TRACE_SEQ_BUF_LEFT(s)) {
 		s->full = 1;
 		return;
 	}
 
-	memcpy(s->buffer + s->len, str, len);
-	s->len += len;
+	seq_buf_putmem(&s->seq, str, len);
 }
 EXPORT_SYMBOL_GPL(trace_seq_puts);
 
@@ -223,12 +237,14 @@ void trace_seq_putc(struct trace_seq *s, unsigned char c)
 	if (s->full)
 		return;
 
+	__trace_seq_init(s);
+
 	if (TRACE_SEQ_BUF_LEFT(s) < 1) {
 		s->full = 1;
 		return;
 	}
 
-	s->buffer[s->len++] = c;
+	seq_buf_putc(&s->seq, c);
 }
 EXPORT_SYMBOL_GPL(trace_seq_putc);
 
@@ -247,19 +263,17 @@ void trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len)
 	if (s->full)
 		return;
 
+	__trace_seq_init(s);
+
 	if (len > TRACE_SEQ_BUF_LEFT(s)) {
 		s->full = 1;
 		return;
 	}
 
-	memcpy(s->buffer + s->len, mem, len);
-	s->len += len;
+	seq_buf_putmem(&s->seq, mem, len);
 }
 EXPORT_SYMBOL_GPL(trace_seq_putmem);
 
-#define MAX_MEMHEX_BYTES	8U
-#define HEX_CHARS		(MAX_MEMHEX_BYTES*2 + 1)
-
 /**
  * trace_seq_putmem_hex - write raw memory into the buffer in ASCII hex
  * @s: trace sequence descriptor
@@ -273,32 +287,26 @@ EXPORT_SYMBOL_GPL(trace_seq_putmem);
 void trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
 			 unsigned int len)
 {
-	unsigned char hex[HEX_CHARS];
-	const unsigned char *data = mem;
-	unsigned int start_len;
-	int i, j;
+	unsigned int save_len = s->seq.len;
 
 	if (s->full)
 		return;
 
-	while (len) {
-		start_len = min(len, HEX_CHARS - 1);
-#ifdef __BIG_ENDIAN
-		for (i = 0, j = 0; i < start_len; i++) {
-#else
-		for (i = start_len-1, j = 0; i >= 0; i--) {
-#endif
-			hex[j++] = hex_asc_hi(data[i]);
-			hex[j++] = hex_asc_lo(data[i]);
-		}
-		if (WARN_ON_ONCE(j == 0 || j/2 > len))
-			break;
-
-		/* j increments twice per loop */
-		len -= j / 2;
-		hex[j++] = ' ';
-
-		trace_seq_putmem(s, hex, j);
+	__trace_seq_init(s);
+
+	/* Each byte is represented by two chars */
+	if (len * 2 > TRACE_SEQ_BUF_LEFT(s)) {
+		s->full = 1;
+		return;
+	}
+
+	/* The added spaces can still cause an overflow */
+	seq_buf_putmem_hex(&s->seq, mem, len);
+
+	if (unlikely(seq_buf_has_overflowed(&s->seq))) {
+		s->seq.len = save_len;
+		s->full = 1;
+		return;
 	}
 }
 EXPORT_SYMBOL_GPL(trace_seq_putmem_hex);
@@ -317,30 +325,28 @@ EXPORT_SYMBOL_GPL(trace_seq_putmem_hex);
  */
 int trace_seq_path(struct trace_seq *s, const struct path *path)
 {
-	unsigned char *p;
+	unsigned int save_len = s->seq.len;
+	int ret;
 
 	if (s->full)
 		return 0;
 
+	__trace_seq_init(s);
+
 	if (TRACE_SEQ_BUF_LEFT(s) < 1) {
 		s->full = 1;
 		return 0;
 	}
 
-	p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len);
-	if (!IS_ERR(p)) {
-		p = mangle_path(s->buffer + s->len, p, "\n");
-		if (p) {
-			s->len = p - s->buffer;
-			return 1;
-		}
-	} else {
-		s->buffer[s->len++] = '?';
-		return 1;
+	ret = seq_buf_path(&s->seq, path);
+
+	if (unlikely(seq_buf_has_overflowed(&s->seq))) {
+		s->seq.len = save_len;
+		s->full = 1;
+		return 0;
 	}
 
-	s->full = 1;
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(trace_seq_path);
 
@@ -366,25 +372,7 @@ EXPORT_SYMBOL_GPL(trace_seq_path);
  */
 int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, int cnt)
 {
-	int len;
-	int ret;
-
-	if (!cnt)
-		return 0;
-
-	if (s->len <= s->readpos)
-		return -EBUSY;
-
-	len = s->len - s->readpos;
-	if (cnt > len)
-		cnt = len;
-	ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt);
-	if (ret == cnt)
-		return -EFAULT;
-
-	cnt -= ret;
-
-	s->readpos += cnt;
-	return cnt;
+	__trace_seq_init(s);
+	return seq_buf_to_user(&s->seq, ubuf, cnt);
 }
 EXPORT_SYMBOL_GPL(trace_seq_to_user);
-- 
cgit v1.2.3-70-g09d2


From dd23180aacf4b27d48f40b27249f1e58c8df03be Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 29 Oct 2014 13:48:37 -0400
Subject: tracing: Convert seq_buf_path() to be like seq_path()

Rewrite seq_buf_path() like it is done in seq_path() and allow
it to accept any escape character instead of just "\n".

Making seq_buf_path() like seq_path() will help prevent problems
when converting seq_file to use the seq_buf logic.

Link: http://lkml.kernel.org/r/20141104160222.048795666@goodmis.org
Link: http://lkml.kernel.org/r/20141114011412.338523371@goodmis.org

Tested-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/seq_buf.h  |  2 +-
 kernel/trace/seq_buf.c   | 28 ++++++++++++++++------------
 kernel/trace/trace_seq.c |  5 ++---
 3 files changed, 19 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index 4f7a96a9d71..38770688a62 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -73,7 +73,7 @@ extern int seq_buf_putc(struct seq_buf *s, unsigned char c);
 extern int seq_buf_putmem(struct seq_buf *s, const void *mem, unsigned int len);
 extern int seq_buf_putmem_hex(struct seq_buf *s, const void *mem,
 			      unsigned int len);
-extern int seq_buf_path(struct seq_buf *s, const struct path *path);
+extern int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc);
 
 extern int seq_buf_bitmask(struct seq_buf *s, const unsigned long *maskp,
 			   int nmaskbits);
diff --git a/kernel/trace/seq_buf.c b/kernel/trace/seq_buf.c
index e9a7861595d..7dac34d1235 100644
--- a/kernel/trace/seq_buf.c
+++ b/kernel/trace/seq_buf.c
@@ -272,28 +272,32 @@ int seq_buf_putmem_hex(struct seq_buf *s, const void *mem,
  * seq_buf_path - copy a path into the sequence buffer
  * @s: seq_buf descriptor
  * @path: path to write into the sequence buffer.
+ * @esc: set of characters to escape in the output
  *
  * Write a path name into the sequence buffer.
  *
- * Returns zero on success, -1 on overflow
+ * Returns the number of written bytes on success, -1 on overflow
  */
-int seq_buf_path(struct seq_buf *s, const struct path *path)
+int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc)
 {
-	unsigned int len = seq_buf_buffer_left(s);
-	unsigned char *p;
+	char *buf = s->buffer + s->len;
+	size_t size = seq_buf_buffer_left(s);
+	int res = -1;
 
 	WARN_ON(s->size == 0);
 
-	p = d_path(path, s->buffer + s->len, len);
-	if (!IS_ERR(p)) {
-		p = mangle_path(s->buffer + s->len, p, "\n");
-		if (p) {
-			s->len = p - s->buffer;
-			return 0;
+	if (size) {
+		char *p = d_path(path, buf, size);
+		if (!IS_ERR(p)) {
+			char *end = mangle_path(buf, p, esc);
+			if (end)
+				res = end - buf;
 		}
 	}
-	seq_buf_set_overflow(s);
-	return -1;
+	if (res > 0)
+		s->len += res;
+
+	return res;
 }
 
 /**
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index 8c0c54fe674..74cacc930c2 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -326,7 +326,6 @@ EXPORT_SYMBOL_GPL(trace_seq_putmem_hex);
 int trace_seq_path(struct trace_seq *s, const struct path *path)
 {
 	unsigned int save_len = s->seq.len;
-	int ret;
 
 	if (s->full)
 		return 0;
@@ -338,7 +337,7 @@ int trace_seq_path(struct trace_seq *s, const struct path *path)
 		return 0;
 	}
 
-	ret = seq_buf_path(&s->seq, path);
+	seq_buf_path(&s->seq, path, "\n");
 
 	if (unlikely(seq_buf_has_overflowed(&s->seq))) {
 		s->seq.len = save_len;
@@ -346,7 +345,7 @@ int trace_seq_path(struct trace_seq *s, const struct path *path)
 		return 0;
 	}
 
-	return ret;
+	return 1;
 }
 EXPORT_SYMBOL_GPL(trace_seq_path);
 
-- 
cgit v1.2.3-70-g09d2


From 9a7777935c34b9192e28ef3d232a4b6b5414a657 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 29 Oct 2014 13:59:58 -0400
Subject: tracing: Convert seq_buf fields to be like seq_file fields

In facilitating the conversion of seq_file to use seq_buf,
have the seq_buf fields match the types used by seq_file.

Link: http://lkml.kernel.org/r/20141104160222.195301024@goodmis.org

Tested-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/seq_buf.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index 38770688a62..d14dc9023dd 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -16,10 +16,10 @@
  * @readpos:	The next position to read in the buffer.
  */
 struct seq_buf {
-	unsigned char		*buffer;
-	unsigned int		size;
-	unsigned int		len;
-	unsigned int		readpos;
+	char			*buffer;
+	size_t			size;
+	size_t			len;
+	loff_t			readpos;
 };
 
 static inline void
-- 
cgit v1.2.3-70-g09d2


From 0736c033a81547b1cdc5120fc8dd60e26a00fd28 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 29 Oct 2014 14:17:52 -0400
Subject: tracing: Add a seq_buf_clear() helper and clear len and readpos in
 init

Add a helper function seq_buf_clear() that resets the len and readpos
fields of a seq_buf. Currently it is only used in the seq_buf_init()
but will be used later when updating the seq_file code.

Link: http://lkml.kernel.org/r/20141104160222.352309995@goodmis.org

Tested-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/seq_buf.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index d14dc9023dd..5d91262433e 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -22,13 +22,18 @@ struct seq_buf {
 	loff_t			readpos;
 };
 
+static inline void seq_buf_clear(struct seq_buf *s)
+{
+	s->len = 0;
+	s->readpos = 0;
+}
+
 static inline void
 seq_buf_init(struct seq_buf *s, unsigned char *buf, unsigned int size)
 {
 	s->buffer = buf;
 	s->size = size;
-	s->len = 0;
-	s->readpos = 0;
+	seq_buf_clear(s);
 }
 
 /*
-- 
cgit v1.2.3-70-g09d2


From eeab98154dc0b49afd398afdd71c464a8af5911f Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Thu, 6 Nov 2014 16:38:28 -0500
Subject: seq_buf: Create seq_buf_used() to find out how much was written

Add a helper function seq_buf_used() that replaces the SEQ_BUF_USED()
private macro to let callers have a method to know how much of the
seq_buf was written to.

Link: http://lkml.kernel.org/r/20141114011412.170377300@goodmis.org
Link: http://lkml.kernel.org/r/20141114011413.321654244@goodmis.org

Reviewed-by: Petr Mladek <pmladek@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/seq_buf.h | 6 ++++++
 kernel/trace/seq_buf.c  | 5 +----
 2 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index 5d91262433e..93718e570d4 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -64,6 +64,12 @@ seq_buf_buffer_left(struct seq_buf *s)
 	return (s->size - 1) - s->len;
 }
 
+/* How much buffer was written? */
+static inline unsigned int seq_buf_used(struct seq_buf *s)
+{
+	return min(s->len, s->size);
+}
+
 extern __printf(2, 3)
 int seq_buf_printf(struct seq_buf *s, const char *fmt, ...);
 extern __printf(2, 0)
diff --git a/kernel/trace/seq_buf.c b/kernel/trace/seq_buf.c
index 7dac34d1235..9ec5305d9da 100644
--- a/kernel/trace/seq_buf.c
+++ b/kernel/trace/seq_buf.c
@@ -16,9 +16,6 @@
 #include <linux/seq_file.h>
 #include <linux/seq_buf.h>
 
-/* How much buffer is written? */
-#define SEQ_BUF_USED(s) min((s)->len, (s)->size - 1)
-
 /**
  * seq_buf_print_seq - move the contents of seq_buf into a seq_file
  * @m: the seq_file descriptor that is the destination
@@ -28,7 +25,7 @@
  */
 int seq_buf_print_seq(struct seq_file *m, struct seq_buf *s)
 {
-	unsigned int len = SEQ_BUF_USED(s);
+	unsigned int len = seq_buf_used(s);
 
 	return seq_write(m, s->buffer, len);
 }
-- 
cgit v1.2.3-70-g09d2


From 5ac48378414dccca735897c4d7f4e19987c8977c Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 14 Nov 2014 15:49:41 -0500
Subject: tracing: Use trace_seq_used() and seq_buf_used() instead of len

As the seq_buf->len will soon be +1 size when there's an overflow, we
must use trace_seq_used() or seq_buf_used() methods to get the real
length. This will prevent buffer overflow issues if just the len
of the seq_buf descriptor is used to copy memory.

Link: http://lkml.kernel.org/r/20141114121911.09ba3d38@gandalf.local.home

Reported-by: Petr Mladek <pmladek@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/trace_seq.h            | 20 +++++++++++++++++++-
 kernel/trace/seq_buf.c               |  2 +-
 kernel/trace/trace.c                 | 21 +++++++++++----------
 kernel/trace/trace_events.c          |  9 ++++++---
 kernel/trace/trace_functions_graph.c |  5 ++++-
 kernel/trace/trace_seq.c             |  2 +-
 6 files changed, 42 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
index 85d37106be3..cfaf5a1d4ba 100644
--- a/include/linux/trace_seq.h
+++ b/include/linux/trace_seq.h
@@ -23,6 +23,24 @@ trace_seq_init(struct trace_seq *s)
 	s->full = 0;
 }
 
+/**
+ * trace_seq_used - amount of actual data written to buffer
+ * @s: trace sequence descriptor
+ *
+ * Returns the amount of data written to the buffer.
+ *
+ * IMPORTANT!
+ *
+ * Use this instead of @s->seq.len if you need to pass the amount
+ * of data from the buffer to another buffer (userspace, or what not).
+ * The @s->seq.len on overflow is bigger than the buffer size and
+ * using it can cause access to undefined memory.
+ */
+static inline int trace_seq_used(struct trace_seq *s)
+{
+	return seq_buf_used(&s->seq);
+}
+
 /**
  * trace_seq_buffer_ptr - return pointer to next location in buffer
  * @s: trace sequence descriptor
@@ -35,7 +53,7 @@ trace_seq_init(struct trace_seq *s)
 static inline unsigned char *
 trace_seq_buffer_ptr(struct trace_seq *s)
 {
-	return s->buffer + s->seq.len;
+	return s->buffer + seq_buf_used(&s->seq);
 }
 
 /**
diff --git a/kernel/trace/seq_buf.c b/kernel/trace/seq_buf.c
index 9ec5305d9da..ce17f65268e 100644
--- a/kernel/trace/seq_buf.c
+++ b/kernel/trace/seq_buf.c
@@ -328,7 +328,7 @@ int seq_buf_to_user(struct seq_buf *s, char __user *ubuf, int cnt)
 	if (s->len <= s->readpos)
 		return -EBUSY;
 
-	len = s->len - s->readpos;
+	len = seq_buf_used(s) - s->readpos;
 	if (cnt > len)
 		cnt = len;
 	ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0aa75be843a..9023446b2c2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -944,10 +944,10 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 {
 	int len;
 
-	if (s->seq.len <= s->seq.readpos)
+	if (trace_seq_used(s) <= s->seq.readpos)
 		return -EBUSY;
 
-	len = s->seq.len - s->seq.readpos;
+	len = trace_seq_used(s) - s->seq.readpos;
 	if (cnt > len)
 		cnt = len;
 	memcpy(buf, s->buffer + s->seq.readpos, cnt);
@@ -4514,18 +4514,18 @@ waitagain:
 	trace_access_lock(iter->cpu_file);
 	while (trace_find_next_entry_inc(iter) != NULL) {
 		enum print_line_t ret;
-		int len = iter->seq.seq.len;
+		int save_len = iter->seq.seq.len;
 
 		ret = print_trace_line(iter);
 		if (ret == TRACE_TYPE_PARTIAL_LINE) {
 			/* don't print partial lines */
-			iter->seq.seq.len = len;
+			iter->seq.seq.len = save_len;
 			break;
 		}
 		if (ret != TRACE_TYPE_NO_CONSUME)
 			trace_consume(iter);
 
-		if (iter->seq.seq.len >= cnt)
+		if (trace_seq_used(&iter->seq) >= cnt)
 			break;
 
 		/*
@@ -4541,7 +4541,7 @@ waitagain:
 
 	/* Now copy what we have to the user */
 	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
-	if (iter->seq.seq.readpos >= iter->seq.seq.len)
+	if (iter->seq.seq.readpos >= trace_seq_used(&iter->seq))
 		trace_seq_init(&iter->seq);
 
 	/*
@@ -4598,7 +4598,7 @@ tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
 			break;
 		}
 
-		count = iter->seq.seq.len - save_len;
+		count = trace_seq_used(&iter->seq) - save_len;
 		if (rem < count) {
 			rem = 0;
 			iter->seq.seq.len = save_len;
@@ -4682,13 +4682,13 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		/* Copy the data into the page, so we can start over. */
 		ret = trace_seq_to_buffer(&iter->seq,
 					  page_address(spd.pages[i]),
-					  iter->seq.seq.len);
+					  trace_seq_used(&iter->seq));
 		if (ret < 0) {
 			__free_page(spd.pages[i]);
 			break;
 		}
 		spd.partial[i].offset = 0;
-		spd.partial[i].len = iter->seq.seq.len;
+		spd.partial[i].len = trace_seq_used(&iter->seq);
 
 		trace_seq_init(&iter->seq);
 	}
@@ -5689,7 +5689,8 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	cnt = ring_buffer_read_events_cpu(trace_buf->buffer, cpu);
 	trace_seq_printf(s, "read events: %ld\n", cnt);
 
-	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->seq.len);
+	count = simple_read_from_buffer(ubuf, count, ppos,
+					s->buffer, trace_seq_used(s));
 
 	kfree(s);
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 4d0067dd7f8..935cbea7853 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1044,7 +1044,8 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 	mutex_unlock(&event_mutex);
 
 	if (file)
-		r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->seq.len);
+		r = simple_read_from_buffer(ubuf, cnt, ppos,
+					    s->buffer, trace_seq_used(s));
 
 	kfree(s);
 
@@ -1210,7 +1211,8 @@ subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 	trace_seq_init(s);
 
 	print_subsystem_event_filter(system, s);
-	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->seq.len);
+	r = simple_read_from_buffer(ubuf, cnt, ppos,
+				    s->buffer, trace_seq_used(s));
 
 	kfree(s);
 
@@ -1265,7 +1267,8 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 	trace_seq_init(s);
 
 	func(s);
-	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->seq.len);
+	r = simple_read_from_buffer(ubuf, cnt, ppos,
+				    s->buffer, trace_seq_used(s));
 
 	kfree(s);
 
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 6d1342ae7a4..ec35468349a 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -1153,6 +1153,9 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
 			return ret;
 	}
 
+	if (trace_seq_has_overflowed(s))
+		goto out;
+
 	/* Strip ending newline */
 	if (s->buffer[s->seq.len - 1] == '\n') {
 		s->buffer[s->seq.len - 1] = '\0';
@@ -1160,7 +1163,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
 	}
 
 	trace_seq_puts(s, " */\n");
-
+ out:
 	return trace_handle_return(s);
 }
 
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index 74cacc930c2..f8b45d8792f 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -30,7 +30,7 @@
 #define TRACE_SEQ_BUF_LEFT(s) seq_buf_buffer_left(&(s)->seq)
 
 /* How much buffer is written? */
-#define TRACE_SEQ_BUF_USED(s) min((s)->seq.len, (unsigned int)(PAGE_SIZE - 1))
+#define TRACE_SEQ_BUF_USED(s) seq_buf_used(&(s)->seq)
 
 /*
  * trace_seq should work with being initialized with 0s.
-- 
cgit v1.2.3-70-g09d2


From 8cd709ae7658a7fd7f6630699e3229188c2591e4 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 29 Oct 2014 15:26:09 -0400
Subject: tracing: Have seq_buf use full buffer

Currently seq_buf is full when all but one byte of the buffer is
filled. Change it so that the seq_buf is full when all of the
buffer is filled.

Some of the functions would fill the buffer completely and report
everything was fine. This was inconsistent with the max of size - 1.
Changing this to be max of size makes all functions consistent.

Link: http://lkml.kernel.org/r/20141104160222.502133196@goodmis.org
Link: http://lkml.kernel.org/r/20141114011412.811957882@goodmis.org

Tested-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/seq_buf.h | 6 +++---
 kernel/trace/seq_buf.c  | 9 ++++++---
 2 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index 93718e570d4..0800a24b434 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -43,13 +43,13 @@ seq_buf_init(struct seq_buf *s, unsigned char *buf, unsigned int size)
 static inline bool
 seq_buf_has_overflowed(struct seq_buf *s)
 {
-	return s->len == s->size;
+	return s->len > s->size;
 }
 
 static inline void
 seq_buf_set_overflow(struct seq_buf *s)
 {
-	s->len = s->size;
+	s->len = s->size + 1;
 }
 
 /*
@@ -61,7 +61,7 @@ seq_buf_buffer_left(struct seq_buf *s)
 	if (seq_buf_has_overflowed(s))
 		return 0;
 
-	return (s->size - 1) - s->len;
+	return s->size - s->len;
 }
 
 /* How much buffer was written? */
diff --git a/kernel/trace/seq_buf.c b/kernel/trace/seq_buf.c
index 6fc9d021cbe..c53f1d5088e 100644
--- a/kernel/trace/seq_buf.c
+++ b/kernel/trace/seq_buf.c
@@ -26,7 +26,7 @@
  */
 static bool seq_buf_can_fit(struct seq_buf *s, size_t len)
 {
-	return s->len + len < s->size;
+	return s->len + len <= s->size;
 }
 
 /**
@@ -110,8 +110,11 @@ int seq_buf_bitmask(struct seq_buf *s, const unsigned long *maskp,
 	WARN_ON(s->size == 0);
 
 	/*
-	 * The last byte of the buffer is used to determine if we
-	 * overflowed or not.
+	 * Note, because bitmap_scnprintf() only returns the number of bytes
+	 * written and not the number that would be written, we use the last
+	 * byte of the buffer to let us know if we overflowed. There's a small
+	 * chance that the bitmap could have fit exactly inside the buffer, but
+	 * it's not that critical if that does happen.
 	 */
 	if (len > 1) {
 		ret = bitmap_scnprintf(s->buffer + s->len, len, maskp, nmaskbits);
-- 
cgit v1.2.3-70-g09d2


From 01cb06a4c229908d239149017049fdd1fca1dd51 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 29 Oct 2014 17:30:50 -0400
Subject: tracing: Add seq_buf_get_buf() and seq_buf_commit() helper functions

Add two helper functions; seq_buf_get_buf() and seq_buf_commit() that
are used by seq_buf_path(). This makes the code similar to the
seq_file: seq_path() function, and will help to be able to consolidate
the functions between seq_file and trace_seq.

Link: http://lkml.kernel.org/r/20141104160222.644881406@goodmis.org
Link: http://lkml.kernel.org/r/20141114011412.977571447@goodmis.org

Tested-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/seq_buf.h | 41 +++++++++++++++++++++++++++++++++++++++++
 kernel/trace/seq_buf.c  |  7 +++----
 2 files changed, 44 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index 0800a24b434..12c64282aa9 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -70,6 +70,47 @@ static inline unsigned int seq_buf_used(struct seq_buf *s)
 	return min(s->len, s->size);
 }
 
+/**
+ * seq_buf_get_buf - get buffer to write arbitrary data to
+ * @s: the seq_buf handle
+ * @bufp: the beginning of the buffer is stored here
+ *
+ * Return the number of bytes available in the buffer, or zero if
+ * there's no space.
+ */
+static inline size_t seq_buf_get_buf(struct seq_buf *s, char **bufp)
+{
+	WARN_ON(s->len > s->size + 1);
+
+	if (s->len < s->size) {
+		*bufp = s->buffer + s->len;
+		return s->size - s->len;
+	}
+
+	*bufp = NULL;
+	return 0;
+}
+
+/**
+ * seq_buf_commit - commit data to the buffer
+ * @s: the seq_buf handle
+ * @num: the number of bytes to commit
+ *
+ * Commit @num bytes of data written to a buffer previously acquired
+ * by seq_buf_get.  To signal an error condition, or that the data
+ * didn't fit in the available space, pass a negative @num value.
+ */
+static inline void seq_buf_commit(struct seq_buf *s, int num)
+{
+	if (num < 0) {
+		seq_buf_set_overflow(s);
+	} else {
+		/* num must be negative on overflow */
+		BUG_ON(s->len + num > s->size);
+		s->len += num;
+	}
+}
+
 extern __printf(2, 3)
 int seq_buf_printf(struct seq_buf *s, const char *fmt, ...);
 extern __printf(2, 0)
diff --git a/kernel/trace/seq_buf.c b/kernel/trace/seq_buf.c
index c53f1d5088e..086f594ac89 100644
--- a/kernel/trace/seq_buf.c
+++ b/kernel/trace/seq_buf.c
@@ -293,8 +293,8 @@ int seq_buf_putmem_hex(struct seq_buf *s, const void *mem,
  */
 int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc)
 {
-	char *buf = s->buffer + s->len;
-	size_t size = seq_buf_buffer_left(s);
+	char *buf;
+	size_t size = seq_buf_get_buf(s, &buf);
 	int res = -1;
 
 	WARN_ON(s->size == 0);
@@ -307,8 +307,7 @@ int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc)
 				res = end - buf;
 		}
 	}
-	if (res > 0)
-		s->len += res;
+	seq_buf_commit(s, res);
 
 	return res;
 }
-- 
cgit v1.2.3-70-g09d2


From 2448913ed2aa7a7424d9b9ca79861d13c746a3f1 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Mon, 3 Nov 2014 18:53:50 -0500
Subject: seq-buf: Make seq_buf_bprintf() conditional on CONFIG_BINARY_PRINTF

The function bstr_printf() from lib/vsprnintf.c is only available if
CONFIG_BINARY_PRINTF is defined. This is due to the only user currently
being the tracing infrastructure, which needs to select this config
when tracing is configured. Until there is another user of the binary
printf formats, this will continue to be the case.

Since seq_buf.c is now lives in lib/ and is compiled even without
tracing, it must encompass its use of bstr_printf() which is used
by seq_buf_printf(). This too is only used by the tracing infrastructure
and is still encapsulated by the CONFIG_BINARY_PRINTF.

Link: http://lkml.kernel.org/r/20141104160222.969013383@goodmis.org

Tested-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/seq_buf.h | 7 +++++--
 kernel/trace/seq_buf.c  | 2 ++
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index 12c64282aa9..9aafe0e24c6 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -115,8 +115,6 @@ extern __printf(2, 3)
 int seq_buf_printf(struct seq_buf *s, const char *fmt, ...);
 extern __printf(2, 0)
 int seq_buf_vprintf(struct seq_buf *s, const char *fmt, va_list args);
-extern int
-seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary);
 extern int seq_buf_print_seq(struct seq_file *m, struct seq_buf *s);
 extern int seq_buf_to_user(struct seq_buf *s, char __user *ubuf,
 			   int cnt);
@@ -130,4 +128,9 @@ extern int seq_buf_path(struct seq_buf *s, const struct path *path, const char *
 extern int seq_buf_bitmask(struct seq_buf *s, const unsigned long *maskp,
 			   int nmaskbits);
 
+#ifdef CONFIG_BINARY_PRINTF
+extern int
+seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary);
+#endif
+
 #endif /* _LINUX_SEQ_BUF_H */
diff --git a/kernel/trace/seq_buf.c b/kernel/trace/seq_buf.c
index 086f594ac89..4eedfedb9e3 100644
--- a/kernel/trace/seq_buf.c
+++ b/kernel/trace/seq_buf.c
@@ -127,6 +127,7 @@ int seq_buf_bitmask(struct seq_buf *s, const unsigned long *maskp,
 	return -1;
 }
 
+#ifdef CONFIG_BINARY_PRINTF
 /**
  * seq_buf_bprintf - Write the printf string from binary arguments
  * @s: seq_buf descriptor
@@ -161,6 +162,7 @@ int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary)
 	seq_buf_set_overflow(s);
 	return -1;
 }
+#endif /* CONFIG_BINARY_PRINTF */
 
 /**
  * seq_buf_puts - sequence printing of simple string
-- 
cgit v1.2.3-70-g09d2


From afdc34a3d3b823a12a93b822ee1efb566f884032 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Thu, 19 Jun 2014 17:33:31 -0400
Subject: printk: Add per_cpu printk func to allow printk to be diverted

Being able to divert printk to call another function besides the normal
logging is useful for such things like NMI handling. If some functions
are to be called from NMI that does printk() it is possible to lock up
the box if the nmi handler triggers when another printk is happening.

One example of this use is to perform a stack trace on all CPUs via NMI.
But if the NMI is to do the printk() it can cause the system to lock up.
By allowing the printk to be diverted to another function that can safely
record the printk output and then print it when it in a safe context
then NMIs will be safe to call these functions like show_regs().

Link: http://lkml.kernel.org/p/20140619213952.209176403@goodmis.org

Tested-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/percpu.h |  3 +++
 include/linux/printk.h |  2 ++
 kernel/printk/printk.c | 38 +++++++++++++++++++++++++++++---------
 3 files changed, 34 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index a3aa63e4763..ba2e85a0ff5 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -134,4 +134,7 @@ extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
 	(typeof(type) __percpu *)__alloc_percpu(sizeof(type),		\
 						__alignof__(type))
 
+/* To avoid include hell, as printk can not declare this, we declare it here */
+DECLARE_PER_CPU(printk_func_t, printk_func);
+
 #endif /* __LINUX_PERCPU_H */
diff --git a/include/linux/printk.h b/include/linux/printk.h
index d78125f73ac..3bbd979d32f 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -162,6 +162,8 @@ extern int kptr_restrict;
 
 extern void wake_up_klogd(void);
 
+typedef int(*printk_func_t)(const char *fmt, va_list args);
+
 void log_buf_kexec_setup(void);
 void __init setup_log_buf(int early);
 void dump_stack_set_arch_desc(const char *fmt, ...);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index ced2b84b1cb..f7b723f98cb 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1807,6 +1807,30 @@ asmlinkage int printk_emit(int facility, int level,
 }
 EXPORT_SYMBOL(printk_emit);
 
+int vprintk_default(const char *fmt, va_list args)
+{
+	int r;
+
+#ifdef CONFIG_KGDB_KDB
+	if (unlikely(kdb_trap_printk)) {
+		r = vkdb_printf(fmt, args);
+		return r;
+	}
+#endif
+	r = vprintk_emit(0, -1, NULL, 0, fmt, args);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(vprintk_default);
+
+/*
+ * This allows printk to be diverted to another function per cpu.
+ * This is useful for calling printk functions from within NMI
+ * without worrying about race conditions that can lock up the
+ * box.
+ */
+DEFINE_PER_CPU(printk_func_t, printk_func) = vprintk_default;
+
 /**
  * printk - print a kernel message
  * @fmt: format string
@@ -1830,19 +1854,15 @@ EXPORT_SYMBOL(printk_emit);
  */
 asmlinkage __visible int printk(const char *fmt, ...)
 {
+	printk_func_t vprintk_func;
 	va_list args;
 	int r;
 
-#ifdef CONFIG_KGDB_KDB
-	if (unlikely(kdb_trap_printk)) {
-		va_start(args, fmt);
-		r = vkdb_printf(fmt, args);
-		va_end(args);
-		return r;
-	}
-#endif
 	va_start(args, fmt);
-	r = vprintk_emit(0, -1, NULL, 0, fmt, args);
+	preempt_disable();
+	vprintk_func = this_cpu_read(printk_func);
+	r = vprintk_func(fmt, args);
+	preempt_enable();
 	va_end(args);
 
 	return r;
-- 
cgit v1.2.3-70-g09d2


From 62d956dc3e11138c5ffd4b2c62e4f909c5180a12 Mon Sep 17 00:00:00 2001
From: Boris BREZILLON <boris.brezillon@free-electrons.com>
Date: Mon, 20 Oct 2014 10:46:14 +0200
Subject: mtd: nand: provide detailed description for raw read/write page
 methods

read_page_raw and write_page_raw method description is not clear enough.
It clearly specifies that ECC correction should not be involved but does
not talk about specific layout (by layout I mean where in-band and
out-of-band data are stored on the NAND media) used by NAND/ECC
controllers.

Those specific layouts might impact MTD users and thus should be hidden (as
already done in the standard NAND_ECC_HW_SYNDROME implementation).

Clearly state this constraint in the nand_ecc_ctrl struct documentation.

Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 include/linux/mtd/nand.h | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index e4d451e4600..b14d190b593 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -455,8 +455,21 @@ struct nand_hw_control {
  *		be provided if an hardware ECC is available
  * @calculate:	function for ECC calculation or readback from ECC hardware
  * @correct:	function for ECC correction, matching to ECC generator (sw/hw)
- * @read_page_raw:	function to read a raw page without ECC
- * @write_page_raw:	function to write a raw page without ECC
+ * @read_page_raw:	function to read a raw page without ECC. This function
+ *			should hide the specific layout used by the ECC
+ *			controller and always return contiguous in-band and
+ *			out-of-band data even if they're not stored
+ *			contiguously on the NAND chip (e.g.
+ *			NAND_ECC_HW_SYNDROME interleaves in-band and
+ *			out-of-band data).
+ * @write_page_raw:	function to write a raw page without ECC. This function
+ *			should hide the specific layout used by the ECC
+ *			controller and consider the passed data as contiguous
+ *			in-band and out-of-band data. ECC controller is
+ *			responsible for doing the appropriate transformations
+ *			to adapt to its specific layout (e.g.
+ *			NAND_ECC_HW_SYNDROME interleaves in-band and
+ *			out-of-band data).
  * @read_page:	function to read a page according to the ECC generator
  *		requirements; returns maximum number of bitflips corrected in
  *		any single ECC step, 0 if bitflips uncorrectable, -EIO hw error
-- 
cgit v1.2.3-70-g09d2


From 3943f42c11896ce82ad3da132c8a5630313bdd0e Mon Sep 17 00:00:00 2001
From: Andrey Utkin <andrey.krieger.utkin@gmail.com>
Date: Fri, 14 Nov 2014 05:09:55 +0400
Subject: Replace mentions of "list_struct" to "list_head"

There's no such thing as "list_struct".

Signed-off-by: Andrey Utkin <andrey.krieger.utkin@gmail.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Acked-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/gpu/drm/radeon/mkregtable.c  | 24 ++++++++++++------------
 drivers/media/pci/cx18/cx18-driver.h |  2 +-
 include/linux/list.h                 | 34 +++++++++++++++++-----------------
 include/linux/plist.h                | 10 +++++-----
 include/linux/rculist.h              |  8 ++++----
 scripts/kconfig/list.h               |  6 +++---
 tools/usb/usbip/libsrc/list.h        |  2 +-
 7 files changed, 43 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/mkregtable.c b/drivers/gpu/drm/radeon/mkregtable.c
index 4a85bb644e2..b928c17bdee 100644
--- a/drivers/gpu/drm/radeon/mkregtable.c
+++ b/drivers/gpu/drm/radeon/mkregtable.c
@@ -347,7 +347,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_entry - get the struct for this entry
  * @ptr:	the &struct list_head pointer.
  * @type:	the type of the struct this is embedded in.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_entry(ptr, type, member) \
 	container_of(ptr, type, member)
@@ -356,7 +356,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_first_entry - get the first element from a list
  * @ptr:	the list head to take the element from.
  * @type:	the type of the struct this is embedded in.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Note, that list is expected to be not empty.
  */
@@ -406,7 +406,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_for_each_entry	-	iterate over list of given type
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_for_each_entry(pos, head, member)				\
 	for (pos = list_entry((head)->next, typeof(*pos), member);	\
@@ -417,7 +417,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_for_each_entry_reverse - iterate backwards over list of given type.
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_for_each_entry_reverse(pos, head, member)			\
 	for (pos = list_entry((head)->prev, typeof(*pos), member);	\
@@ -428,7 +428,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue()
  * @pos:	the type * to use as a start point
  * @head:	the head of the list
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Prepares a pos entry for use as a start point in list_for_each_entry_continue().
  */
@@ -439,7 +439,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_for_each_entry_continue - continue iteration over list of given type
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Continue to iterate over list of given type, continuing after
  * the current position.
@@ -453,7 +453,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_for_each_entry_continue_reverse - iterate backwards from the given point
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Start to iterate over list of given type backwards, continuing after
  * the current position.
@@ -467,7 +467,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_for_each_entry_from - iterate over list of given type from the current point
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Iterate over list of given type, continuing from current position.
  */
@@ -480,7 +480,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * @pos:	the type * to use as a loop cursor.
  * @n:		another type * to use as temporary storage
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_for_each_entry_safe(pos, n, head, member)			\
 	for (pos = list_entry((head)->next, typeof(*pos), member),	\
@@ -493,7 +493,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * @pos:	the type * to use as a loop cursor.
  * @n:		another type * to use as temporary storage
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Iterate over list of given type, continuing after current point,
  * safe against removal of list entry.
@@ -509,7 +509,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * @pos:	the type * to use as a loop cursor.
  * @n:		another type * to use as temporary storage
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Iterate over list of given type from current point, safe against
  * removal of list entry.
@@ -524,7 +524,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * @pos:	the type * to use as a loop cursor.
  * @n:		another type * to use as temporary storage
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Iterate backwards over list of given type, safe against removal
  * of list entry.
diff --git a/drivers/media/pci/cx18/cx18-driver.h b/drivers/media/pci/cx18/cx18-driver.h
index 57f4688ea55..da59ec31d10 100644
--- a/drivers/media/pci/cx18/cx18-driver.h
+++ b/drivers/media/pci/cx18/cx18-driver.h
@@ -290,7 +290,7 @@ struct cx18_options {
  * list_entry_is_past_end - check if a previous loop cursor is off list end
  * @pos:	the type * previously used as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Check if the entry's list_head is the head of the list, thus it's not a
  * real entry but was the loop cursor that walked past the end
diff --git a/include/linux/list.h b/include/linux/list.h
index f33f831eb3c..feb773c76ee 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -346,7 +346,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_entry - get the struct for this entry
  * @ptr:	the &struct list_head pointer.
  * @type:	the type of the struct this is embedded in.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_entry(ptr, type, member) \
 	container_of(ptr, type, member)
@@ -355,7 +355,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_first_entry - get the first element from a list
  * @ptr:	the list head to take the element from.
  * @type:	the type of the struct this is embedded in.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Note, that list is expected to be not empty.
  */
@@ -366,7 +366,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_last_entry - get the last element from a list
  * @ptr:	the list head to take the element from.
  * @type:	the type of the struct this is embedded in.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Note, that list is expected to be not empty.
  */
@@ -377,7 +377,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_first_entry_or_null - get the first element from a list
  * @ptr:	the list head to take the element from.
  * @type:	the type of the struct this is embedded in.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Note that if the list is empty, it returns NULL.
  */
@@ -387,7 +387,7 @@ static inline void list_splice_tail_init(struct list_head *list,
 /**
  * list_next_entry - get the next element in list
  * @pos:	the type * to cursor
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_next_entry(pos, member) \
 	list_entry((pos)->member.next, typeof(*(pos)), member)
@@ -395,7 +395,7 @@ static inline void list_splice_tail_init(struct list_head *list,
 /**
  * list_prev_entry - get the prev element in list
  * @pos:	the type * to cursor
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_prev_entry(pos, member) \
 	list_entry((pos)->member.prev, typeof(*(pos)), member)
@@ -441,7 +441,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_for_each_entry	-	iterate over list of given type
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_for_each_entry(pos, head, member)				\
 	for (pos = list_first_entry(head, typeof(*pos), member);	\
@@ -452,7 +452,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_for_each_entry_reverse - iterate backwards over list of given type.
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_for_each_entry_reverse(pos, head, member)			\
 	for (pos = list_last_entry(head, typeof(*pos), member);		\
@@ -463,7 +463,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue()
  * @pos:	the type * to use as a start point
  * @head:	the head of the list
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Prepares a pos entry for use as a start point in list_for_each_entry_continue().
  */
@@ -474,7 +474,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_for_each_entry_continue - continue iteration over list of given type
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Continue to iterate over list of given type, continuing after
  * the current position.
@@ -488,7 +488,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_for_each_entry_continue_reverse - iterate backwards from the given point
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Start to iterate over list of given type backwards, continuing after
  * the current position.
@@ -502,7 +502,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_for_each_entry_from - iterate over list of given type from the current point
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Iterate over list of given type, continuing from current position.
  */
@@ -515,7 +515,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * @pos:	the type * to use as a loop cursor.
  * @n:		another type * to use as temporary storage
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_for_each_entry_safe(pos, n, head, member)			\
 	for (pos = list_first_entry(head, typeof(*pos), member),	\
@@ -528,7 +528,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * @pos:	the type * to use as a loop cursor.
  * @n:		another type * to use as temporary storage
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Iterate over list of given type, continuing after current point,
  * safe against removal of list entry.
@@ -544,7 +544,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * @pos:	the type * to use as a loop cursor.
  * @n:		another type * to use as temporary storage
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Iterate over list of given type from current point, safe against
  * removal of list entry.
@@ -559,7 +559,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * @pos:	the type * to use as a loop cursor.
  * @n:		another type * to use as temporary storage
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Iterate backwards over list of given type, safe against removal
  * of list entry.
@@ -574,7 +574,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * list_safe_reset_next - reset a stale list_for_each_entry_safe loop
  * @pos:	the loop cursor used in the list_for_each_entry_safe loop
  * @n:		temporary storage used in list_for_each_entry_safe
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * list_safe_reset_next is not safe to use in general if the list may be
  * modified concurrently (eg. the lock is dropped in the loop body). An
diff --git a/include/linux/plist.h b/include/linux/plist.h
index 8b6c970cff6..97883604a3c 100644
--- a/include/linux/plist.h
+++ b/include/linux/plist.h
@@ -176,7 +176,7 @@ extern void plist_requeue(struct plist_node *node, struct plist_head *head);
  * plist_for_each_entry	- iterate over list of given type
  * @pos:	the type * to use as a loop counter
  * @head:	the head for your list
- * @mem:	the name of the list_struct within the struct
+ * @mem:	the name of the list_head within the struct
  */
 #define plist_for_each_entry(pos, head, mem)	\
 	 list_for_each_entry(pos, &(head)->node_list, mem.node_list)
@@ -185,7 +185,7 @@ extern void plist_requeue(struct plist_node *node, struct plist_head *head);
  * plist_for_each_entry_continue - continue iteration over list of given type
  * @pos:	the type * to use as a loop cursor
  * @head:	the head for your list
- * @m:		the name of the list_struct within the struct
+ * @m:		the name of the list_head within the struct
  *
  * Continue to iterate over list of given type, continuing after
  * the current position.
@@ -198,7 +198,7 @@ extern void plist_requeue(struct plist_node *node, struct plist_head *head);
  * @pos:	the type * to use as a loop counter
  * @n:		another type * to use as temporary storage
  * @head:	the head for your list
- * @m:		the name of the list_struct within the struct
+ * @m:		the name of the list_head within the struct
  *
  * Iterate over list of given type, safe against removal of list entry.
  */
@@ -229,7 +229,7 @@ static inline int plist_node_empty(const struct plist_node *node)
  * plist_first_entry - get the struct for the first entry
  * @head:	the &struct plist_head pointer
  * @type:	the type of the struct this is embedded in
- * @member:	the name of the list_struct within the struct
+ * @member:	the name of the list_head within the struct
  */
 #ifdef CONFIG_DEBUG_PI_LIST
 # define plist_first_entry(head, type, member)	\
@@ -246,7 +246,7 @@ static inline int plist_node_empty(const struct plist_node *node)
  * plist_last_entry - get the struct for the last entry
  * @head:	the &struct plist_head pointer
  * @type:	the type of the struct this is embedded in
- * @member:	the name of the list_struct within the struct
+ * @member:	the name of the list_head within the struct
  */
 #ifdef CONFIG_DEBUG_PI_LIST
 # define plist_last_entry(head, type, member)	\
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 372ad5e0dcb..664060bd2f4 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -241,7 +241,7 @@ static inline void list_splice_init_rcu(struct list_head *list,
  * list_entry_rcu - get the struct for this entry
  * @ptr:        the &struct list_head pointer.
  * @type:       the type of the struct this is embedded in.
- * @member:     the name of the list_struct within the struct.
+ * @member:     the name of the list_head within the struct.
  *
  * This primitive may safely run concurrently with the _rcu list-mutation
  * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
@@ -278,7 +278,7 @@ static inline void list_splice_init_rcu(struct list_head *list,
  * list_first_or_null_rcu - get the first element from a list
  * @ptr:        the list head to take the element from.
  * @type:       the type of the struct this is embedded in.
- * @member:     the name of the list_struct within the struct.
+ * @member:     the name of the list_head within the struct.
  *
  * Note that if the list is empty, it returns NULL.
  *
@@ -296,7 +296,7 @@ static inline void list_splice_init_rcu(struct list_head *list,
  * list_for_each_entry_rcu	-	iterate over rcu list of given type
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * This list-traversal primitive may safely run concurrently with
  * the _rcu list-mutation primitives such as list_add_rcu()
@@ -311,7 +311,7 @@ static inline void list_splice_init_rcu(struct list_head *list,
  * list_for_each_entry_continue_rcu - continue iteration over list of given type
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  *
  * Continue to iterate over list of given type, continuing after
  * the current position.
diff --git a/scripts/kconfig/list.h b/scripts/kconfig/list.h
index 685d80e1bb0..2cf23f002d3 100644
--- a/scripts/kconfig/list.h
+++ b/scripts/kconfig/list.h
@@ -34,7 +34,7 @@ struct list_head {
  * list_entry - get the struct for this entry
  * @ptr:	the &struct list_head pointer.
  * @type:	the type of the struct this is embedded in.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_entry(ptr, type, member) \
 	container_of(ptr, type, member)
@@ -43,7 +43,7 @@ struct list_head {
  * list_for_each_entry	-	iterate over list of given type
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_for_each_entry(pos, head, member)				\
 	for (pos = list_entry((head)->next, typeof(*pos), member);	\
@@ -55,7 +55,7 @@ struct list_head {
  * @pos:	the type * to use as a loop cursor.
  * @n:		another type * to use as temporary storage
  * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_for_each_entry_safe(pos, n, head, member)			\
 	for (pos = list_entry((head)->next, typeof(*pos), member),	\
diff --git a/tools/usb/usbip/libsrc/list.h b/tools/usb/usbip/libsrc/list.h
index 8d0c936e184..5eaaa78e2c6 100644
--- a/tools/usb/usbip/libsrc/list.h
+++ b/tools/usb/usbip/libsrc/list.h
@@ -98,7 +98,7 @@ static inline void list_del(struct list_head *entry)
  * list_entry - get the struct for this entry
  * @ptr:	the &struct list_head pointer.
  * @type:	the type of the struct this is embedded in.
- * @member:	the name of the list_struct within the struct.
+ * @member:	the name of the list_head within the struct.
  */
 #define list_entry(ptr, type, member) \
 	container_of(ptr, type, member)
-- 
cgit v1.2.3-70-g09d2


From f9df89d897ee0928aa4e03b30250e87f5d1e788a Mon Sep 17 00:00:00 2001
From: Eduardo Valentin <eduardo.valentin@ti.com>
Date: Mon, 6 Jan 2014 09:04:18 -0400
Subject: thermal: introduce clock cooling device

This patch introduces a new thermal cooling device based on common clock
framework. The original motivation to write this cooling device is to be
able to cool down thermal zones using clocks that feed co-processors, such
as GPUs, DSPs, Image Processing Co-processors, etc. But it is written
in a way that it can be used on top of any clock.

The implementation is pretty straight forward. The code creates
a thermal cooling device based on a pair of a struct device and a clock name.
The struct device is assumed to be usable by the OPP layer. The OPP layer
is used as source of the list of possible frequencies. The (cpufreq) frequency
table is then used as a map from frequencies to cooling states. Cooling
states are indexes to the frequency table.

The logic sits on top of common clock framework, specifically on clock
pre notifications. Any PRE_RATE_CHANGE is hijacked, and the transition is
only allowed when the new rate is within the thermal limit (cooling state -> freq).

When a thermal cooling device state transition is requested, the clock
is also checked to verify if the current clock rate is within the new
thermal limit.

Cc: Zhang Rui <rui.zhang@intel.com>
Cc: Mike Turquette <mturquette@linaro.org>
Cc: Nishanth Menon <nm@ti.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Len Brown <len.brown@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-pm@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Eduardo Valentin <eduardo.valentin@ti.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/Kconfig         |  12 +
 drivers/thermal/Makefile        |   3 +
 drivers/thermal/clock_cooling.c | 485 ++++++++++++++++++++++++++++++++++++++++
 include/linux/clock_cooling.h   |  65 ++++++
 4 files changed, 565 insertions(+)
 create mode 100644 drivers/thermal/clock_cooling.c
 create mode 100644 include/linux/clock_cooling.h

(limited to 'include')

diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index f554d25b439..efbdb8c0bb1 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -112,6 +112,18 @@ config CPU_THERMAL
 
 	  If you want this support, you should say Y here.
 
+config CLOCK_THERMAL
+	bool "Generic clock cooling support"
+	depends on COMMON_CLK
+	depends on PM_OPP
+	help
+	  This entry implements the generic clock cooling mechanism through
+	  frequency clipping. Typically used to cool off co-processors. The
+	  device that is configured to use this cooling mechanism will be
+	  controlled to reduce clock frequency whenever temperature is high.
+
+	  If you want this support, you should say Y here.
+
 config THERMAL_EMULATION
 	bool "Thermal emulation mode support"
 	help
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 39c4fe87da2..9d33532cae9 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -18,6 +18,9 @@ thermal_sys-$(CONFIG_THERMAL_GOV_USER_SPACE)	+= user_space.o
 # cpufreq cooling
 thermal_sys-$(CONFIG_CPU_THERMAL)	+= cpu_cooling.o
 
+# clock cooling
+thermal_sys-$(CONFIG_CLOCK_THERMAL)	+= clock_cooling.o
+
 # platform thermal drivers
 obj-$(CONFIG_SPEAR_THERMAL)	+= spear_thermal.o
 obj-$(CONFIG_RCAR_THERMAL)	+= rcar_thermal.o
diff --git a/drivers/thermal/clock_cooling.c b/drivers/thermal/clock_cooling.c
new file mode 100644
index 00000000000..1b4ff0f4c71
--- /dev/null
+++ b/drivers/thermal/clock_cooling.c
@@ -0,0 +1,485 @@
+/*
+ *  drivers/thermal/clock_cooling.c
+ *
+ *  Copyright (C) 2014 Eduardo Valentin <edubezval@gmail.com>
+ *
+ *  Copyright (C) 2013	Texas Instruments Inc.
+ *  Contact:  Eduardo Valentin <eduardo.valentin@ti.com>
+ *
+ *  Highly based on cpu_cooling.c.
+ *  Copyright (C) 2012	Samsung Electronics Co., Ltd(http://www.samsung.com)
+ *  Copyright (C) 2012  Amit Daniel <amit.kachhap@linaro.org>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ */
+#include <linux/clk.h>
+#include <linux/cpufreq.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/idr.h>
+#include <linux/mutex.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+#include <linux/thermal.h>
+#include <linux/clock_cooling.h>
+
+/**
+ * struct clock_cooling_device - data for cooling device with clock
+ * @id: unique integer value corresponding to each clock_cooling_device
+ *	registered.
+ * @dev: struct device pointer to the device being used to cool off using
+ *       clock frequencies.
+ * @cdev: thermal_cooling_device pointer to keep track of the
+ *	registered cooling device.
+ * @clk_rate_change_nb: reference to notifier block used to receive clock
+ *                      rate changes.
+ * @freq_table: frequency table used to keep track of available frequencies.
+ * @clock_state: integer value representing the current state of clock
+ *	cooling	devices.
+ * @clock_val: integer value representing the absolute value of the clipped
+ *	frequency.
+ * @clk: struct clk reference used to enforce clock limits.
+ * @lock: mutex lock to protect this struct.
+ *
+ * This structure is required for keeping information of each
+ * clock_cooling_device registered. In order to prevent corruption of this a
+ * mutex @lock is used.
+ */
+struct clock_cooling_device {
+	int id;
+	struct device *dev;
+	struct thermal_cooling_device *cdev;
+	struct notifier_block clk_rate_change_nb;
+	struct cpufreq_frequency_table *freq_table;
+	unsigned long clock_state;
+	unsigned long clock_val;
+	struct clk *clk;
+	struct mutex lock; /* lock to protect the content of this struct */
+};
+#define to_clock_cooling_device(x) \
+		container_of(x, struct clock_cooling_device, clk_rate_change_nb)
+static DEFINE_IDR(clock_idr);
+static DEFINE_MUTEX(cooling_clock_lock);
+
+/**
+ * clock_cooling_get_idr - function to get an unique id.
+ * @id: int * value generated by this function.
+ *
+ * This function will populate @id with an unique
+ * id, using the idr API.
+ *
+ * Return: 0 on success, an error code on failure.
+ */
+static int clock_cooling_get_idr(int *id)
+{
+	int ret;
+
+	mutex_lock(&cooling_clock_lock);
+	ret = idr_alloc(&clock_idr, NULL, 0, 0, GFP_KERNEL);
+	mutex_unlock(&cooling_clock_lock);
+	if (unlikely(ret < 0))
+		return ret;
+	*id = ret;
+
+	return 0;
+}
+
+/**
+ * release_idr - function to free the unique id.
+ * @id: int value representing the unique id.
+ */
+static void release_idr(int id)
+{
+	mutex_lock(&cooling_clock_lock);
+	idr_remove(&clock_idr, id);
+	mutex_unlock(&cooling_clock_lock);
+}
+
+/* Below code defines functions to be used for clock as cooling device */
+
+enum clock_cooling_property {
+	GET_LEVEL,
+	GET_FREQ,
+	GET_MAXL,
+};
+
+/**
+ * clock_cooling_get_property - fetch a property of interest for a give cpu.
+ * @ccdev: clock cooling device reference
+ * @input: query parameter
+ * @output: query return
+ * @property: type of query (frequency, level, max level)
+ *
+ * This is the common function to
+ * 1. get maximum clock cooling states
+ * 2. translate frequency to cooling state
+ * 3. translate cooling state to frequency
+ * Note that the code may be not in good shape
+ * but it is written in this way in order to:
+ * a) reduce duplicate code as most of the code can be shared.
+ * b) make sure the logic is consistent when translating between
+ *    cooling states and frequencies.
+ *
+ * Return: 0 on success, -EINVAL when invalid parameters are passed.
+ */
+static int clock_cooling_get_property(struct clock_cooling_device *ccdev,
+				      unsigned long input,
+				      unsigned long *output,
+				      enum clock_cooling_property property)
+{
+	int i;
+	unsigned long max_level = 0, level = 0;
+	unsigned int freq = CPUFREQ_ENTRY_INVALID;
+	int descend = -1;
+	struct cpufreq_frequency_table *pos, *table = ccdev->freq_table;
+
+	if (!output)
+		return -EINVAL;
+
+	if (!table)
+		return -EINVAL;
+
+	cpufreq_for_each_valid_entry(pos, table) {
+		/* ignore duplicate entry */
+		if (freq == pos->frequency)
+			continue;
+
+		/* get the frequency order */
+		if (freq != CPUFREQ_ENTRY_INVALID && descend == -1)
+			descend = freq > pos->frequency;
+
+		freq = pos->frequency;
+		max_level++;
+	}
+
+	/* No valid cpu frequency entry */
+	if (max_level == 0)
+		return -EINVAL;
+
+	/* max_level is an index, not a counter */
+	max_level--;
+
+	/* get max level */
+	if (property == GET_MAXL) {
+		*output = max_level;
+		return 0;
+	}
+
+	if (property == GET_FREQ)
+		level = descend ? input : (max_level - input);
+
+	i = 0;
+	cpufreq_for_each_valid_entry(pos, table) {
+		/* ignore duplicate entry */
+		if (freq == pos->frequency)
+			continue;
+
+		/* now we have a valid frequency entry */
+		freq = pos->frequency;
+
+		if (property == GET_LEVEL && (unsigned int)input == freq) {
+			/* get level by frequency */
+			*output = descend ? i : (max_level - i);
+			return 0;
+		}
+		if (property == GET_FREQ && level == i) {
+			/* get frequency by level */
+			*output = freq;
+			return 0;
+		}
+		i++;
+	}
+
+	return -EINVAL;
+}
+
+/**
+ * clock_cooling_get_level - return the cooling level of given clock cooling.
+ * @cdev: reference of a thermal cooling device of used as clock cooling device
+ * @freq: the frequency of interest
+ *
+ * This function will match the cooling level corresponding to the
+ * requested @freq and return it.
+ *
+ * Return: The matched cooling level on success or THERMAL_CSTATE_INVALID
+ * otherwise.
+ */
+unsigned long clock_cooling_get_level(struct thermal_cooling_device *cdev,
+				      unsigned long freq)
+{
+	struct clock_cooling_device *ccdev = cdev->devdata;
+	unsigned long val;
+
+	if (clock_cooling_get_property(ccdev, (unsigned long)freq, &val,
+				       GET_LEVEL))
+		return THERMAL_CSTATE_INVALID;
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(clock_cooling_get_level);
+
+/**
+ * clock_cooling_get_frequency - get the absolute value of frequency from level.
+ * @ccdev: clock cooling device reference
+ * @level: cooling level
+ *
+ * This function matches cooling level with frequency. Based on a cooling level
+ * of frequency, equals cooling state of cpu cooling device, it will return
+ * the corresponding frequency.
+ *	e.g level=0 --> 1st MAX FREQ, level=1 ---> 2nd MAX FREQ, .... etc
+ *
+ * Return: 0 on error, the corresponding frequency otherwise.
+ */
+static unsigned long
+clock_cooling_get_frequency(struct clock_cooling_device *ccdev,
+			    unsigned long level)
+{
+	int ret = 0;
+	unsigned long freq;
+
+	ret = clock_cooling_get_property(ccdev, level, &freq, GET_FREQ);
+	if (ret)
+		return 0;
+
+	return freq;
+}
+
+/**
+ * clock_cooling_apply - function to apply frequency clipping.
+ * @ccdev: clock_cooling_device pointer containing frequency clipping data.
+ * @cooling_state: value of the cooling state.
+ *
+ * Function used to make sure the clock layer is aware of current thermal
+ * limits. The limits are applied by updating the clock rate in case it is
+ * higher than the corresponding frequency based on the requested cooling_state.
+ *
+ * Return: 0 on success, an error code otherwise (-EINVAL in case wrong
+ * cooling state).
+ */
+static int clock_cooling_apply(struct clock_cooling_device *ccdev,
+			       unsigned long cooling_state)
+{
+	unsigned long clip_freq, cur_freq;
+	int ret = 0;
+
+	/* Here we write the clipping */
+	/* Check if the old cooling action is same as new cooling action */
+	if (ccdev->clock_state == cooling_state)
+		return 0;
+
+	clip_freq = clock_cooling_get_frequency(ccdev, cooling_state);
+	if (!clip_freq)
+		return -EINVAL;
+
+	cur_freq = clk_get_rate(ccdev->clk);
+
+	mutex_lock(&ccdev->lock);
+	ccdev->clock_state = cooling_state;
+	ccdev->clock_val = clip_freq;
+	/* enforce clock level */
+	if (cur_freq > clip_freq)
+		ret = clk_set_rate(ccdev->clk, clip_freq);
+	mutex_unlock(&ccdev->lock);
+
+	return ret;
+}
+
+/**
+ * clock_cooling_clock_notifier - notifier callback on clock rate changes.
+ * @nb:	struct notifier_block * with callback info.
+ * @event: value showing clock event for which this function invoked.
+ * @data: callback-specific data
+ *
+ * Callback to hijack the notification on clock transition.
+ * Every time there is a clock change, we intercept all pre change events
+ * and block the transition in case the new rate infringes thermal limits.
+ *
+ * Return: NOTIFY_DONE (success) or NOTIFY_BAD (new_rate > thermal limit).
+ */
+static int clock_cooling_clock_notifier(struct notifier_block *nb,
+					unsigned long event, void *data)
+{
+	struct clk_notifier_data *ndata = data;
+	struct clock_cooling_device *ccdev = to_clock_cooling_device(nb);
+
+	switch (event) {
+	case PRE_RATE_CHANGE:
+		/*
+		 * checks on current state
+		 * TODO: current method is not best we can find as it
+		 * allows possibly voltage transitions, in case DVFS
+		 * layer is also hijacking clock pre notifications.
+		 */
+		if (ndata->new_rate > ccdev->clock_val)
+			return NOTIFY_BAD;
+		/* fall through */
+	case POST_RATE_CHANGE:
+	case ABORT_RATE_CHANGE:
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+/* clock cooling device thermal callback functions are defined below */
+
+/**
+ * clock_cooling_get_max_state - callback function to get the max cooling state.
+ * @cdev: thermal cooling device pointer.
+ * @state: fill this variable with the max cooling state.
+ *
+ * Callback for the thermal cooling device to return the clock
+ * max cooling state.
+ *
+ * Return: 0 on success, an error code otherwise.
+ */
+static int clock_cooling_get_max_state(struct thermal_cooling_device *cdev,
+				       unsigned long *state)
+{
+	struct clock_cooling_device *ccdev = cdev->devdata;
+	unsigned long count = 0;
+	int ret;
+
+	ret = clock_cooling_get_property(ccdev, 0, &count, GET_MAXL);
+	if (!ret)
+		*state = count;
+
+	return ret;
+}
+
+/**
+ * clock_cooling_get_cur_state - function to get the current cooling state.
+ * @cdev: thermal cooling device pointer.
+ * @state: fill this variable with the current cooling state.
+ *
+ * Callback for the thermal cooling device to return the clock
+ * current cooling state.
+ *
+ * Return: 0 (success)
+ */
+static int clock_cooling_get_cur_state(struct thermal_cooling_device *cdev,
+				       unsigned long *state)
+{
+	struct clock_cooling_device *ccdev = cdev->devdata;
+
+	*state = ccdev->clock_state;
+
+	return 0;
+}
+
+/**
+ * clock_cooling_set_cur_state - function to set the current cooling state.
+ * @cdev: thermal cooling device pointer.
+ * @state: set this variable to the current cooling state.
+ *
+ * Callback for the thermal cooling device to change the clock cooling
+ * current cooling state.
+ *
+ * Return: 0 on success, an error code otherwise.
+ */
+static int clock_cooling_set_cur_state(struct thermal_cooling_device *cdev,
+				       unsigned long state)
+{
+	struct clock_cooling_device *clock_device = cdev->devdata;
+
+	return clock_cooling_apply(clock_device, state);
+}
+
+/* Bind clock callbacks to thermal cooling device ops */
+static struct thermal_cooling_device_ops const clock_cooling_ops = {
+	.get_max_state = clock_cooling_get_max_state,
+	.get_cur_state = clock_cooling_get_cur_state,
+	.set_cur_state = clock_cooling_set_cur_state,
+};
+
+/**
+ * clock_cooling_register - function to create clock cooling device.
+ * @dev: struct device pointer to the device used as clock cooling device.
+ * @clock_name: string containing the clock used as cooling mechanism.
+ *
+ * This interface function registers the clock cooling device with the name
+ * "thermal-clock-%x". The cooling device is based on clock frequencies.
+ * The struct device is assumed to be capable of DVFS transitions.
+ * The OPP layer is used to fetch and fill the available frequencies for
+ * the referred device. The ordered frequency table is used to control
+ * the clock cooling device cooling states and to limit clock transitions
+ * based on the cooling state requested by the thermal framework.
+ *
+ * Return: a valid struct thermal_cooling_device pointer on success,
+ * on failure, it returns a corresponding ERR_PTR().
+ */
+struct thermal_cooling_device *
+clock_cooling_register(struct device *dev, const char *clock_name)
+{
+	struct thermal_cooling_device *cdev;
+	struct clock_cooling_device *ccdev = NULL;
+	char dev_name[THERMAL_NAME_LENGTH];
+	int ret = 0;
+
+	ccdev = devm_kzalloc(dev, sizeof(*ccdev), GFP_KERNEL);
+	if (!ccdev)
+		return ERR_PTR(-ENOMEM);
+
+	ccdev->dev = dev;
+	ccdev->clk = devm_clk_get(dev, clock_name);
+	if (IS_ERR(ccdev->clk))
+		return ERR_CAST(ccdev->clk);
+
+	ret = clock_cooling_get_idr(&ccdev->id);
+	if (ret)
+		return ERR_PTR(-EINVAL);
+
+	snprintf(dev_name, sizeof(dev_name), "thermal-clock-%d", ccdev->id);
+
+	cdev = thermal_cooling_device_register(dev_name, ccdev,
+					       &clock_cooling_ops);
+	if (IS_ERR(cdev)) {
+		release_idr(ccdev->id);
+		return ERR_PTR(-EINVAL);
+	}
+	ccdev->cdev = cdev;
+	ccdev->clk_rate_change_nb.notifier_call = clock_cooling_clock_notifier;
+
+	/* Assuming someone has already filled the opp table for this device */
+	ret = dev_pm_opp_init_cpufreq_table(dev, &ccdev->freq_table);
+	if (ret) {
+		release_idr(ccdev->id);
+		return ERR_PTR(ret);
+	}
+	ccdev->clock_state = 0;
+	ccdev->clock_val = clock_cooling_get_frequency(ccdev, 0);
+
+	clk_notifier_register(ccdev->clk, &ccdev->clk_rate_change_nb);
+
+	return cdev;
+}
+EXPORT_SYMBOL_GPL(clock_cooling_register);
+
+/**
+ * clock_cooling_unregister - function to remove clock cooling device.
+ * @cdev: thermal cooling device pointer.
+ *
+ * This interface function unregisters the "thermal-clock-%x" cooling device.
+ */
+void clock_cooling_unregister(struct thermal_cooling_device *cdev)
+{
+	struct clock_cooling_device *ccdev;
+
+	if (!cdev)
+		return;
+
+	ccdev = cdev->devdata;
+
+	clk_notifier_unregister(ccdev->clk, &ccdev->clk_rate_change_nb);
+	dev_pm_opp_free_cpufreq_table(ccdev->dev, &ccdev->freq_table);
+
+	thermal_cooling_device_unregister(ccdev->cdev);
+	release_idr(ccdev->id);
+}
+EXPORT_SYMBOL_GPL(clock_cooling_unregister);
diff --git a/include/linux/clock_cooling.h b/include/linux/clock_cooling.h
new file mode 100644
index 00000000000..4d1019d56f7
--- /dev/null
+++ b/include/linux/clock_cooling.h
@@ -0,0 +1,65 @@
+/*
+ *  linux/include/linux/clock_cooling.h
+ *
+ *  Copyright (C) 2014 Eduardo Valentin <edubezval@gmail.com>
+ *
+ *  Copyright (C) 2013	Texas Instruments Inc.
+ *  Contact:  Eduardo Valentin <eduardo.valentin@ti.com>
+ *
+ *  Highly based on cpu_cooling.c.
+ *  Copyright (C) 2012	Samsung Electronics Co., Ltd(http://www.samsung.com)
+ *  Copyright (C) 2012  Amit Daniel <amit.kachhap@linaro.org>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ */
+
+#ifndef __CPU_COOLING_H__
+#define __CPU_COOLING_H__
+
+#include <linux/of.h>
+#include <linux/thermal.h>
+#include <linux/cpumask.h>
+
+#ifdef CONFIG_CLOCK_THERMAL
+/**
+ * clock_cooling_register - function to create clock cooling device.
+ * @dev: struct device pointer to the device used as clock cooling device.
+ * @clock_name: string containing the clock used as cooling mechanism.
+ */
+struct thermal_cooling_device *
+clock_cooling_register(struct device *dev, const char *clock_name);
+
+/**
+ * clock_cooling_unregister - function to remove clock cooling device.
+ * @cdev: thermal cooling device pointer.
+ */
+void clock_cooling_unregister(struct thermal_cooling_device *cdev);
+
+unsigned long clock_cooling_get_level(struct thermal_cooling_device *cdev,
+				      unsigned long freq);
+#else /* !CONFIG_CLOCK_THERMAL */
+static inline struct thermal_cooling_device *
+clock_cooling_register(struct device *dev, const char *clock_name)
+{
+	return NULL;
+}
+static inline
+void clock_cooling_unregister(struct thermal_cooling_device *cdev)
+{
+}
+static inline
+unsigned long clock_cooling_get_level(struct thermal_cooling_device *cdev,
+				      unsigned long freq)
+{
+	return THERMAL_CSTATE_INVALID;
+}
+#endif	/* CONFIG_CLOCK_THERMAL */
+
+#endif /* __CPU_COOLING_H__ */
-- 
cgit v1.2.3-70-g09d2


From 0199e9938f2c0e7f5476f5983f1763d28f049837 Mon Sep 17 00:00:00 2001
From: Mikko Perttunen <mperttunen@nvidia.com>
Date: Fri, 26 Sep 2014 12:43:10 +0300
Subject: of: Add bindings for nvidia,tegra124-soctherm

This adds binding documentation and headers for the Tegra124
SOCTHERM device tree node.

Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Eduardo Valentin <edubezval@gmail.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 .../devicetree/bindings/thermal/tegra-soctherm.txt | 53 ++++++++++++++++++++++
 include/dt-bindings/thermal/tegra124-soctherm.h    | 13 ++++++
 2 files changed, 66 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/thermal/tegra-soctherm.txt
 create mode 100644 include/dt-bindings/thermal/tegra124-soctherm.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/thermal/tegra-soctherm.txt b/Documentation/devicetree/bindings/thermal/tegra-soctherm.txt
new file mode 100644
index 00000000000..ecf3ed76cd4
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/tegra-soctherm.txt
@@ -0,0 +1,53 @@
+Tegra124 SOCTHERM thermal management system
+
+The SOCTHERM IP block contains thermal sensors, support for polled
+or interrupt-based thermal monitoring, CPU and GPU throttling based
+on temperature trip points, and handling external overcurrent
+notifications. It is also used to manage emergency shutdown in an
+overheating situation.
+
+Required properties :
+- compatible : "nvidia,tegra124-soctherm".
+- reg : Should contain 1 entry:
+  - SOCTHERM register set
+- interrupts : Defines the interrupt used by SOCTHERM
+- clocks : Must contain an entry for each entry in clock-names.
+  See ../clocks/clock-bindings.txt for details.
+- clock-names : Must include the following entries:
+  - tsensor
+  - soctherm
+- resets : Must contain an entry for each entry in reset-names.
+  See ../reset/reset.txt for details.
+- reset-names : Must include the following entries:
+  - soctherm
+- #thermal-sensor-cells : Should be 1. See ./thermal.txt for a description
+    of this property. See <dt-bindings/thermal/tegra124-soctherm.h> for a
+    list of valid values when referring to thermal sensors.
+
+
+Example :
+
+	soctherm@0,700e2000 {
+		compatible = "nvidia,tegra124-soctherm";
+		reg = <0x0 0x700e2000 0x0 0x1000>;
+		interrupts = <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&tegra_car TEGRA124_CLK_TSENSOR>,
+			<&tegra_car TEGRA124_CLK_SOC_THERM>;
+		clock-names = "tsensor", "soctherm";
+		resets = <&tegra_car 78>;
+		reset-names = "soctherm";
+
+		#thermal-sensor-cells = <1>;
+	};
+
+Example: referring to thermal sensors :
+
+       thermal-zones {
+                cpu {
+                        polling-delay-passive = <1000>;
+                        polling-delay = <1000>;
+
+                        thermal-sensors =
+                                <&soctherm TEGRA124_SOCTHERM_SENSOR_CPU>;
+                };
+	};
diff --git a/include/dt-bindings/thermal/tegra124-soctherm.h b/include/dt-bindings/thermal/tegra124-soctherm.h
new file mode 100644
index 00000000000..85aaf66690f
--- /dev/null
+++ b/include/dt-bindings/thermal/tegra124-soctherm.h
@@ -0,0 +1,13 @@
+/*
+ * This header provides constants for binding nvidia,tegra124-soctherm.
+ */
+
+#ifndef _DT_BINDINGS_THERMAL_TEGRA124_SOCTHERM_H
+#define _DT_BINDINGS_THERMAL_TEGRA124_SOCTHERM_H
+
+#define TEGRA124_SOCTHERM_SENSOR_CPU 0
+#define TEGRA124_SOCTHERM_SENSOR_MEM 1
+#define TEGRA124_SOCTHERM_SENSOR_GPU 2
+#define TEGRA124_SOCTHERM_SENSOR_PLLX 3
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From 2251aef64a38db60f4ae7a4a83f9203c6791f196 Mon Sep 17 00:00:00 2001
From: Eduardo Valentin <edubezval@gmail.com>
Date: Fri, 7 Nov 2014 21:24:39 -0400
Subject: thermal: of: improve of-thermal sensor registration API

Different drivers request API extensions in of-thermal. For this reason,
additional callbacks are required to fit the new drivers needs.

The current API implementation expects the registering sensor driver
to provide a get_temp and get_trend callbacks as function parameters.
As the amount of callbacks is growing, this patch changes the existing
implementation to use a .ops field to hold all the of thermal callbacks
to sensor drivers.

This patch also changes the existing of-thermal users to fit the new
API design. No functional change is introduced in this patch.

Cc: Alexandre Courbot <gnurou@gmail.com>
Cc: devicetree@vger.kernel.org
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Jean Delvare <jdelvare@suse.de>
Cc: linux-kernel@vger.kernel.org
Cc: linux-pm@vger.kernel.org
Cc: linux-tegra@vger.kernel.org
Cc: lm-sensors@lm-sensors.org
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Stephen Warren <swarren@wwwdotorg.org>
Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: Zhang Rui <rui.zhang@intel.com>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Tested-by: Mikko Perttunen <mikko.perttunen@kapsi.fi>
Reviewed-by: Mikko Perttunen <mikko.perttunen@kapsi.fi>
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Lukasz Majewski <l.majewski@samsung.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/hwmon/lm75.c                               |  9 +++--
 drivers/hwmon/ntc_thermistor.c                     |  6 +++-
 drivers/hwmon/tmp102.c                             |  6 +++-
 drivers/thermal/of-thermal.c                       | 39 ++++++++++------------
 drivers/thermal/tegra_soctherm.c                   |  7 ++--
 drivers/thermal/ti-soc-thermal/ti-thermal-common.c |  8 +++--
 include/linux/thermal.h                            | 24 +++++++++----
 7 files changed, 62 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c
index d16dbb33a53..e7c8bf9093e 100644
--- a/drivers/hwmon/lm75.c
+++ b/drivers/hwmon/lm75.c
@@ -176,6 +176,10 @@ static struct attribute *lm75_attrs[] = {
 };
 ATTRIBUTE_GROUPS(lm75);
 
+static const struct thermal_zone_of_device_ops lm75_of_thermal_ops = {
+	.get_temp = lm75_read_temp,
+};
+
 /*-----------------------------------------------------------------------*/
 
 /* device probe and removal */
@@ -291,10 +295,9 @@ lm75_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	if (IS_ERR(data->hwmon_dev))
 		return PTR_ERR(data->hwmon_dev);
 
-	data->tz = thermal_zone_of_sensor_register(data->hwmon_dev,
-						   0,
+	data->tz = thermal_zone_of_sensor_register(data->hwmon_dev, 0,
 						   data->hwmon_dev,
-						   lm75_read_temp, NULL);
+						   &lm75_of_thermal_ops);
 	if (IS_ERR(data->tz))
 		data->tz = NULL;
 
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index 4ff89b2482e..bca8521c8a9 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -486,6 +486,10 @@ static const struct attribute_group ntc_attr_group = {
 	.attrs = ntc_attributes,
 };
 
+static const struct thermal_zone_of_device_ops ntc_of_thermal_ops = {
+	.get_temp = ntc_read_temp,
+};
+
 static int ntc_thermistor_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id =
@@ -579,7 +583,7 @@ static int ntc_thermistor_probe(struct platform_device *pdev)
 								pdev_id->name);
 
 	data->tz = thermal_zone_of_sensor_register(data->dev, 0, data->dev,
-						ntc_read_temp, NULL);
+						   &ntc_of_thermal_ops);
 	if (IS_ERR(data->tz)) {
 		dev_dbg(&pdev->dev, "Failed to register to thermal fw.\n");
 		data->tz = NULL;
diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c
index 51719956cc0..ba9f478f64e 100644
--- a/drivers/hwmon/tmp102.c
+++ b/drivers/hwmon/tmp102.c
@@ -158,6 +158,10 @@ ATTRIBUTE_GROUPS(tmp102);
 #define TMP102_CONFIG  (TMP102_CONF_TM | TMP102_CONF_EM | TMP102_CONF_CR1)
 #define TMP102_CONFIG_RD_ONLY (TMP102_CONF_R0 | TMP102_CONF_R1 | TMP102_CONF_AL)
 
+static const struct thermal_zone_of_device_ops tmp102_of_thermal_ops = {
+	.get_temp = tmp102_read_temp,
+};
+
 static int tmp102_probe(struct i2c_client *client,
 				  const struct i2c_device_id *id)
 {
@@ -215,7 +219,7 @@ static int tmp102_probe(struct i2c_client *client,
 	}
 	tmp102->hwmon_dev = hwmon_dev;
 	tmp102->tz = thermal_zone_of_sensor_register(hwmon_dev, 0, hwmon_dev,
-						     tmp102_read_temp, NULL);
+						     &tmp102_of_thermal_ops);
 	if (IS_ERR(tmp102->tz))
 		tmp102->tz = NULL;
 
diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
index 62143ba3100..b7982f0a6ea 100644
--- a/drivers/thermal/of-thermal.c
+++ b/drivers/thermal/of-thermal.c
@@ -30,6 +30,7 @@
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/string.h>
+#include <linux/thermal.h>
 
 #include "thermal_core.h"
 
@@ -77,8 +78,7 @@ struct __thermal_bind_params {
  * @num_tbps: number of thermal bind params
  * @tbps: an array of thermal bind params (0..num_tbps - 1)
  * @sensor_data: sensor private data used while reading temperature and trend
- * @get_temp: sensor callback to read temperature
- * @get_trend: sensor callback to read temperature trend
+ * @ops: set of callbacks to handle the thermal zone based on DT
  */
 
 struct __thermal_zone {
@@ -96,8 +96,7 @@ struct __thermal_zone {
 
 	/* sensor interface */
 	void *sensor_data;
-	int (*get_temp)(void *, long *);
-	int (*get_trend)(void *, long *);
+	const struct thermal_zone_of_device_ops *ops;
 };
 
 /***   DT thermal zone device callbacks   ***/
@@ -107,10 +106,10 @@ static int of_thermal_get_temp(struct thermal_zone_device *tz,
 {
 	struct __thermal_zone *data = tz->devdata;
 
-	if (!data->get_temp)
+	if (!data->ops->get_temp)
 		return -EINVAL;
 
-	return data->get_temp(data->sensor_data, temp);
+	return data->ops->get_temp(data->sensor_data, temp);
 }
 
 static int of_thermal_get_trend(struct thermal_zone_device *tz, int trip,
@@ -120,10 +119,10 @@ static int of_thermal_get_trend(struct thermal_zone_device *tz, int trip,
 	long dev_trend;
 	int r;
 
-	if (!data->get_trend)
+	if (!data->ops->get_trend)
 		return -EINVAL;
 
-	r = data->get_trend(data->sensor_data, &dev_trend);
+	r = data->ops->get_trend(data->sensor_data, &dev_trend);
 	if (r)
 		return r;
 
@@ -324,8 +323,7 @@ static struct thermal_zone_device_ops of_thermal_ops = {
 static struct thermal_zone_device *
 thermal_zone_of_add_sensor(struct device_node *zone,
 			   struct device_node *sensor, void *data,
-			   int (*get_temp)(void *, long *),
-			   int (*get_trend)(void *, long *))
+			   const struct thermal_zone_of_device_ops *ops)
 {
 	struct thermal_zone_device *tzd;
 	struct __thermal_zone *tz;
@@ -336,9 +334,11 @@ thermal_zone_of_add_sensor(struct device_node *zone,
 
 	tz = tzd->devdata;
 
+	if (!ops)
+		return ERR_PTR(-EINVAL);
+
 	mutex_lock(&tzd->lock);
-	tz->get_temp = get_temp;
-	tz->get_trend = get_trend;
+	tz->ops = ops;
 	tz->sensor_data = data;
 
 	tzd->ops->get_temp = of_thermal_get_temp;
@@ -356,8 +356,7 @@ thermal_zone_of_add_sensor(struct device_node *zone,
  *             than one sensors
  * @data: a private pointer (owned by the caller) that will be passed
  *        back, when a temperature reading is needed.
- * @get_temp: a pointer to a function that reads the sensor temperature.
- * @get_trend: a pointer to a function that reads the sensor temperature trend.
+ * @ops: struct thermal_zone_of_device_ops *. Must contain at least .get_temp.
  *
  * This function will search the list of thermal zones described in device
  * tree and look for the zone that refer to the sensor device pointed by
@@ -382,9 +381,8 @@ thermal_zone_of_add_sensor(struct device_node *zone,
  * check the return value with help of IS_ERR() helper.
  */
 struct thermal_zone_device *
-thermal_zone_of_sensor_register(struct device *dev, int sensor_id,
-				void *data, int (*get_temp)(void *, long *),
-				int (*get_trend)(void *, long *))
+thermal_zone_of_sensor_register(struct device *dev, int sensor_id, void *data,
+				const struct thermal_zone_of_device_ops *ops)
 {
 	struct device_node *np, *child, *sensor_np;
 	struct thermal_zone_device *tzd = ERR_PTR(-ENODEV);
@@ -426,9 +424,7 @@ thermal_zone_of_sensor_register(struct device *dev, int sensor_id,
 
 		if (sensor_specs.np == sensor_np && id == sensor_id) {
 			tzd = thermal_zone_of_add_sensor(child, sensor_np,
-							 data,
-							 get_temp,
-							 get_trend);
+							 data, ops);
 			of_node_put(sensor_specs.np);
 			of_node_put(child);
 			goto exit;
@@ -476,8 +472,7 @@ void thermal_zone_of_sensor_unregister(struct device *dev,
 	tzd->ops->get_temp = NULL;
 	tzd->ops->get_trend = NULL;
 
-	tz->get_temp = NULL;
-	tz->get_trend = NULL;
+	tz->ops = NULL;
 	tz->sensor_data = NULL;
 	mutex_unlock(&tzd->lock);
 }
diff --git a/drivers/thermal/tegra_soctherm.c b/drivers/thermal/tegra_soctherm.c
index 70f7e9ef435..9197fc05c5c 100644
--- a/drivers/thermal/tegra_soctherm.c
+++ b/drivers/thermal/tegra_soctherm.c
@@ -317,6 +317,10 @@ static int tegra_thermctl_get_temp(void *data, long *out_temp)
 	return 0;
 }
 
+static const struct thermal_zone_of_device_ops tegra_of_thermal_ops = {
+	.get_temp = tegra_thermctl_get_temp,
+};
+
 static const struct of_device_id tegra_soctherm_of_match[] = {
 	{ .compatible = "nvidia,tegra124-soctherm" },
 	{ },
@@ -416,8 +420,7 @@ static int tegra_soctherm_probe(struct platform_device *pdev)
 		zone->shift = t124_thermctl_temp_zones[i].shift;
 
 		tz = thermal_zone_of_sensor_register(&pdev->dev, i, zone,
-						     tegra_thermctl_get_temp,
-						     NULL);
+						     &tegra_of_thermal_ops);
 		if (IS_ERR(tz)) {
 			err = PTR_ERR(tz);
 			dev_err(&pdev->dev, "failed to register sensor: %d\n",
diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
index 9eec26dc044..5fd03865e39 100644
--- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
+++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
@@ -286,6 +286,11 @@ static int ti_thermal_get_crit_temp(struct thermal_zone_device *thermal,
 	return ti_thermal_get_trip_temp(thermal, OMAP_TRIP_NUMBER - 1, temp);
 }
 
+static const struct thermal_zone_of_device_ops ti_of_thermal_ops = {
+	.get_temp = __ti_thermal_get_temp,
+	.get_trend = __ti_thermal_get_trend,
+};
+
 static struct thermal_zone_device_ops ti_thermal_ops = {
 	.get_temp = ti_thermal_get_temp,
 	.get_trend = ti_thermal_get_trend,
@@ -333,8 +338,7 @@ int ti_thermal_expose_sensor(struct ti_bandgap *bgp, int id,
 
 	/* in case this is specified by DT */
 	data->ti_thermal = thermal_zone_of_sensor_register(bgp->dev, id,
-					data, __ti_thermal_get_temp,
-					__ti_thermal_get_trend);
+					data, &ti_of_thermal_ops);
 	if (IS_ERR(data->ti_thermal)) {
 		/* Create thermal zone */
 		data->ti_thermal = thermal_zone_device_register(domain,
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index ef90838b36a..5bc28a70014 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -289,19 +289,31 @@ struct thermal_genl_event {
 	enum events event;
 };
 
+/**
+ * struct thermal_zone_of_device_ops - scallbacks for handling DT based zones
+ *
+ * Mandatory:
+ * @get_temp: a pointer to a function that reads the sensor temperature.
+ *
+ * Optional:
+ * @get_trend: a pointer to a function that reads the sensor temperature trend.
+ */
+struct thermal_zone_of_device_ops {
+	int (*get_temp)(void *, long *);
+	int (*get_trend)(void *, long *);
+};
+
 /* Function declarations */
 #ifdef CONFIG_THERMAL_OF
 struct thermal_zone_device *
-thermal_zone_of_sensor_register(struct device *dev, int id,
-				void *data, int (*get_temp)(void *, long *),
-				int (*get_trend)(void *, long *));
+thermal_zone_of_sensor_register(struct device *dev, int id, void *data,
+				const struct thermal_zone_of_device_ops *ops);
 void thermal_zone_of_sensor_unregister(struct device *dev,
 				       struct thermal_zone_device *tz);
 #else
 static inline struct thermal_zone_device *
-thermal_zone_of_sensor_register(struct device *dev, int id,
-				void *data, int (*get_temp)(void *, long *),
-				int (*get_trend)(void *, long *))
+thermal_zone_of_sensor_register(struct device *dev, int id, void *data,
+				const struct thermal_zone_of_device_ops *ops)
 {
 	return NULL;
 }
-- 
cgit v1.2.3-70-g09d2


From e639cd5bfc03de7ba642d7e8570b9e533f10e54b Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Thu, 20 Nov 2014 12:11:25 -0800
Subject: ARM: OMAP2+: Prepare to move GPMC to drivers by platform data header

We still need to support platform data for omap3 until it's booting
in device tree only mode. So let's add platform_data/omap-gpmc.h for
that, and a minimal linux/omap-gpmc.h for the save and restore used
by the PM code.

Let's also keep a minimal mach-omap2/gpmc.h still around to avoid
churn on the board-*.c files. Once omap3 boots in device tree only
mode, we can drop mach-omap2/gpmc.h and we can make the data
structures in platform_data/omap-gpmc.h private to the GPMC driver.

Note that we can now also remove gpmc-nand.h and gpmc-onenand.h.

Cc: Arnd Bergmann <arnd@arndb.de>
Acked-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/board-am3517crane.c      |   1 +
 arch/arm/mach-omap2/board-cm-t35.c           |   3 +-
 arch/arm/mach-omap2/board-cm-t3517.c         |   3 +-
 arch/arm/mach-omap2/board-flash.c            |   3 +-
 arch/arm/mach-omap2/board-flash.h            |   1 -
 arch/arm/mach-omap2/board-n8x0.c             |   2 -
 arch/arm/mach-omap2/board-omap3pandora.c     |   2 +-
 arch/arm/mach-omap2/board-rx51-peripherals.c |   3 +-
 arch/arm/mach-omap2/gpmc-nand.c              |   3 +-
 arch/arm/mach-omap2/gpmc-nand.h              |  27 ----
 arch/arm/mach-omap2/gpmc-onenand.c           |   3 +-
 arch/arm/mach-omap2/gpmc-onenand.h           |  24 ---
 arch/arm/mach-omap2/gpmc.c                   |  63 +++++++-
 arch/arm/mach-omap2/gpmc.h                   | 227 +--------------------------
 arch/arm/mach-omap2/pm34xx.c                 |   2 +-
 include/linux/omap-gpmc.h                    | 199 +++++++++++++++++++++++
 16 files changed, 271 insertions(+), 295 deletions(-)
 delete mode 100644 arch/arm/mach-omap2/gpmc-nand.h
 delete mode 100644 arch/arm/mach-omap2/gpmc-onenand.h
 create mode 100644 include/linux/omap-gpmc.h

(limited to 'include')

diff --git a/arch/arm/mach-omap2/board-am3517crane.c b/arch/arm/mach-omap2/board-am3517crane.c
index 212c3160de1..8168ddabaed 100644
--- a/arch/arm/mach-omap2/board-am3517crane.c
+++ b/arch/arm/mach-omap2/board-am3517crane.c
@@ -24,6 +24,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
+#include <linux/omap-gpmc.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c
index c6df8eec455..91738a14ecb 100644
--- a/arch/arm/mach-omap2/board-cm-t35.c
+++ b/arch/arm/mach-omap2/board-cm-t35.c
@@ -25,6 +25,7 @@
 #include <linux/input/matrix_keypad.h>
 #include <linux/delay.h>
 #include <linux/gpio.h>
+#include <linux/omap-gpmc.h>
 #include <linux/platform_data/gpio-omap.h>
 
 #include <linux/platform_data/at24.h>
@@ -51,8 +52,6 @@
 #include "sdram-micron-mt46h32m32lf-6.h"
 #include "hsmmc.h"
 #include "common-board-devices.h"
-#include "gpmc.h"
-#include "gpmc-nand.h"
 
 #define CM_T35_GPIO_PENDOWN		57
 #define SB_T35_USB_HUB_RESET_GPIO	167
diff --git a/arch/arm/mach-omap2/board-cm-t3517.c b/arch/arm/mach-omap2/board-cm-t3517.c
index 8a2c1677964..794756df852 100644
--- a/arch/arm/mach-omap2/board-cm-t3517.c
+++ b/arch/arm/mach-omap2/board-cm-t3517.c
@@ -28,6 +28,7 @@
 #include <linux/delay.h>
 #include <linux/gpio.h>
 #include <linux/leds.h>
+#include <linux/omap-gpmc.h>
 #include <linux/rtc-v3020.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
@@ -41,7 +42,6 @@
 
 #include "common.h"
 #include <linux/platform_data/mtd-nand-omap2.h>
-#include "gpmc.h"
 
 #include "am35xx.h"
 
@@ -50,7 +50,6 @@
 #include "hsmmc.h"
 #include "common-board-devices.h"
 #include "am35xx-emac.h"
-#include "gpmc-nand.h"
 
 #if defined(CONFIG_LEDS_GPIO) || defined(CONFIG_LEDS_GPIO_MODULE)
 static struct gpio_led cm_t3517_leds[] = {
diff --git a/arch/arm/mach-omap2/board-flash.c b/arch/arm/mach-omap2/board-flash.c
index 2d245c2e641..70b21cc279b 100644
--- a/arch/arm/mach-omap2/board-flash.c
+++ b/arch/arm/mach-omap2/board-flash.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/omap-gpmc.h>
 #include <linux/platform_device.h>
 #include <linux/mtd/physmap.h>
 #include <linux/io.h>
@@ -23,8 +24,6 @@
 #include "soc.h"
 #include "common.h"
 #include "board-flash.h"
-#include "gpmc-onenand.h"
-#include "gpmc-nand.h"
 
 #define REG_FPGA_REV			0x10
 #define REG_FPGA_DIP_SWITCH_INPUT2	0x60
diff --git a/arch/arm/mach-omap2/board-flash.h b/arch/arm/mach-omap2/board-flash.h
index 2fb5d41a9fa..ea9aaebe11e 100644
--- a/arch/arm/mach-omap2/board-flash.h
+++ b/arch/arm/mach-omap2/board-flash.h
@@ -12,7 +12,6 @@
  */
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
-#include "gpmc.h"
 
 #define PDC_NOR		1
 #define PDC_NAND	2
diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c
index 97767a27ca9..49c3c25808e 100644
--- a/arch/arm/mach-omap2/board-n8x0.c
+++ b/arch/arm/mach-omap2/board-n8x0.c
@@ -22,7 +22,6 @@
 #include <linux/spi/spi.h>
 #include <linux/usb/musb.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
-#include <linux/platform_data/mtd-onenand-omap2.h>
 #include <linux/mfd/menelaus.h>
 #include <sound/tlv320aic3x.h>
 
@@ -32,7 +31,6 @@
 #include "common.h"
 #include "mmc.h"
 #include "soc.h"
-#include "gpmc-onenand.h"
 #include "common-board-devices.h"
 
 #define TUSB6010_ASYNC_CS	1
diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c
index f32201656cf..7f1708738c3 100644
--- a/arch/arm/mach-omap2/board-omap3pandora.c
+++ b/arch/arm/mach-omap2/board-omap3pandora.c
@@ -24,6 +24,7 @@
 #include <linux/spi/spi.h>
 #include <linux/regulator/machine.h>
 #include <linux/i2c/twl.h>
+#include <linux/omap-gpmc.h>
 #include <linux/wl12xx.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/nand.h>
@@ -51,7 +52,6 @@
 #include "sdram-micron-mt46h32m32lf-6.h"
 #include "hsmmc.h"
 #include "common-board-devices.h"
-#include "gpmc-nand.h"
 
 #define PANDORA_WIFI_IRQ_GPIO		21
 #define PANDORA_WIFI_NRESET_GPIO	23
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index 30e7d4ce7b8..e2ad48b5d9c 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -23,6 +23,7 @@
 #include <linux/regulator/machine.h>
 #include <linux/gpio.h>
 #include <linux/gpio_keys.h>
+#include <linux/omap-gpmc.h>
 #include <linux/mmc/host.h>
 #include <linux/power/isp1704_charger.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
@@ -54,8 +55,6 @@
 #include "omap-pm.h"
 #include "hsmmc.h"
 #include "common-board-devices.h"
-#include "gpmc.h"
-#include "gpmc-onenand.h"
 #include "soc.h"
 #include "omap-secure.h"
 
diff --git a/arch/arm/mach-omap2/gpmc-nand.c b/arch/arm/mach-omap2/gpmc-nand.c
index cb7764314f1..d5951b17b73 100644
--- a/arch/arm/mach-omap2/gpmc-nand.c
+++ b/arch/arm/mach-omap2/gpmc-nand.c
@@ -12,14 +12,13 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
+#include <linux/omap-gpmc.h>
 #include <linux/mtd/nand.h>
 #include <linux/platform_data/mtd-nand-omap2.h>
 
 #include <asm/mach/flash.h>
 
-#include "gpmc.h"
 #include "soc.h"
-#include "gpmc-nand.h"
 
 /* minimum size for IO mapping */
 #define	NAND_IO_SIZE	4
diff --git a/arch/arm/mach-omap2/gpmc-nand.h b/arch/arm/mach-omap2/gpmc-nand.h
deleted file mode 100644
index d59e1281e85..00000000000
--- a/arch/arm/mach-omap2/gpmc-nand.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- *  arch/arm/mach-omap2/gpmc-nand.h
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
-
-#ifndef	__OMAP2_GPMC_NAND_H
-#define	__OMAP2_GPMC_NAND_H
-
-#include "gpmc.h"
-#include <linux/platform_data/mtd-nand-omap2.h>
-
-#if IS_ENABLED(CONFIG_MTD_NAND_OMAP2)
-extern int gpmc_nand_init(struct omap_nand_platform_data *d,
-			  struct gpmc_timings *gpmc_t);
-#else
-static inline int gpmc_nand_init(struct omap_nand_platform_data *d,
-				 struct gpmc_timings *gpmc_t)
-{
-	return 0;
-}
-#endif
-
-#endif
diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
index 8b6876c98ce..53d197e0c1f 100644
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ b/arch/arm/mach-omap2/gpmc-onenand.c
@@ -15,14 +15,13 @@
 #include <linux/platform_device.h>
 #include <linux/mtd/onenand_regs.h>
 #include <linux/io.h>
+#include <linux/omap-gpmc.h>
 #include <linux/platform_data/mtd-onenand-omap2.h>
 #include <linux/err.h>
 
 #include <asm/mach/flash.h>
 
-#include "gpmc.h"
 #include "soc.h"
-#include "gpmc-onenand.h"
 
 #define	ONENAND_IO_SIZE	SZ_128K
 
diff --git a/arch/arm/mach-omap2/gpmc-onenand.h b/arch/arm/mach-omap2/gpmc-onenand.h
deleted file mode 100644
index 216f23a8b45..00000000000
--- a/arch/arm/mach-omap2/gpmc-onenand.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- *  arch/arm/mach-omap2/gpmc-onenand.h
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
-
-#ifndef	__OMAP2_GPMC_ONENAND_H
-#define	__OMAP2_GPMC_ONENAND_H
-
-#include <linux/platform_data/mtd-onenand-omap2.h>
-
-#if IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2)
-extern void gpmc_onenand_init(struct omap_onenand_platform_data *d);
-#else
-#define board_onenand_data	NULL
-static inline void gpmc_onenand_init(struct omap_onenand_platform_data *d)
-{
-}
-#endif
-
-#endif
diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index 9ea92b6f180..0753a046fed 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -29,18 +29,17 @@
 #include <linux/of_address.h>
 #include <linux/of_mtd.h>
 #include <linux/of_device.h>
+#include <linux/omap-gpmc.h>
 #include <linux/mtd/nand.h>
 #include <linux/pm_runtime.h>
 
 #include <linux/platform_data/mtd-nand-omap2.h>
-
-#include <asm/mach-types.h>
+#include <linux/platform_data/mtd-onenand-omap2.h>
 
 #include "soc.h"
 #include "omap_device.h"
-#include "gpmc.h"
-#include "gpmc-nand.h"
-#include "gpmc-onenand.h"
+
+#include <asm/mach-types.h>
 
 #define	DEVICE_NAME		"omap-gpmc"
 
@@ -115,6 +114,60 @@
 
 #define GPMC_NR_WAITPINS		4
 
+#define GPMC_CS_CONFIG1		0x00
+#define GPMC_CS_CONFIG2		0x04
+#define GPMC_CS_CONFIG3		0x08
+#define GPMC_CS_CONFIG4		0x0c
+#define GPMC_CS_CONFIG5		0x10
+#define GPMC_CS_CONFIG6		0x14
+#define GPMC_CS_CONFIG7		0x18
+#define GPMC_CS_NAND_COMMAND	0x1c
+#define GPMC_CS_NAND_ADDRESS	0x20
+#define GPMC_CS_NAND_DATA	0x24
+
+/* Control Commands */
+#define GPMC_CONFIG_RDY_BSY	0x00000001
+#define GPMC_CONFIG_DEV_SIZE	0x00000002
+#define GPMC_CONFIG_DEV_TYPE	0x00000003
+#define GPMC_SET_IRQ_STATUS	0x00000004
+
+#define GPMC_CONFIG1_WRAPBURST_SUPP     (1 << 31)
+#define GPMC_CONFIG1_READMULTIPLE_SUPP  (1 << 30)
+#define GPMC_CONFIG1_READTYPE_ASYNC     (0 << 29)
+#define GPMC_CONFIG1_READTYPE_SYNC      (1 << 29)
+#define GPMC_CONFIG1_WRITEMULTIPLE_SUPP (1 << 28)
+#define GPMC_CONFIG1_WRITETYPE_ASYNC    (0 << 27)
+#define GPMC_CONFIG1_WRITETYPE_SYNC     (1 << 27)
+#define GPMC_CONFIG1_CLKACTIVATIONTIME(val) ((val & 3) << 25)
+#define GPMC_CONFIG1_PAGE_LEN(val)      ((val & 3) << 23)
+#define GPMC_CONFIG1_WAIT_READ_MON      (1 << 22)
+#define GPMC_CONFIG1_WAIT_WRITE_MON     (1 << 21)
+#define GPMC_CONFIG1_WAIT_MON_IIME(val) ((val & 3) << 18)
+#define GPMC_CONFIG1_WAIT_PIN_SEL(val)  ((val & 3) << 16)
+#define GPMC_CONFIG1_DEVICESIZE(val)    ((val & 3) << 12)
+#define GPMC_CONFIG1_DEVICESIZE_16      GPMC_CONFIG1_DEVICESIZE(1)
+#define GPMC_CONFIG1_DEVICETYPE(val)    ((val & 3) << 10)
+#define GPMC_CONFIG1_DEVICETYPE_NOR     GPMC_CONFIG1_DEVICETYPE(0)
+#define GPMC_CONFIG1_MUXTYPE(val)       ((val & 3) << 8)
+#define GPMC_CONFIG1_TIME_PARA_GRAN     (1 << 4)
+#define GPMC_CONFIG1_FCLK_DIV(val)      (val & 3)
+#define GPMC_CONFIG1_FCLK_DIV2          (GPMC_CONFIG1_FCLK_DIV(1))
+#define GPMC_CONFIG1_FCLK_DIV3          (GPMC_CONFIG1_FCLK_DIV(2))
+#define GPMC_CONFIG1_FCLK_DIV4          (GPMC_CONFIG1_FCLK_DIV(3))
+#define GPMC_CONFIG7_CSVALID		(1 << 6)
+
+#define GPMC_DEVICETYPE_NOR		0
+#define GPMC_DEVICETYPE_NAND		2
+#define GPMC_CONFIG_WRITEPROTECT	0x00000010
+#define WR_RD_PIN_MONITORING		0x00600000
+
+#define GPMC_ENABLE_IRQ		0x0000000d
+
+/* ECC commands */
+#define GPMC_ECC_READ		0 /* Reset Hardware ECC for read */
+#define GPMC_ECC_WRITE		1 /* Reset Hardware ECC for write */
+#define GPMC_ECC_READSYN	2 /* Reset before syndrom is read back */
+
 /* XXX: Only NAND irq has been considered,currently these are the only ones used
  */
 #define	GPMC_NR_IRQ		2
diff --git a/arch/arm/mach-omap2/gpmc.h b/arch/arm/mach-omap2/gpmc.h
index 707f6d58edd..9caa41a6cb0 100644
--- a/arch/arm/mach-omap2/gpmc.h
+++ b/arch/arm/mach-omap2/gpmc.h
@@ -6,226 +6,9 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
+ *
+ * Do not include this file in any new code, this will get removed
+ * once omap3 boots in device tree only mode.
+ *
  */
-
-#ifndef __OMAP2_GPMC_H
-#define __OMAP2_GPMC_H
-
-#include <linux/platform_data/mtd-nand-omap2.h>
-
-/* Maximum Number of Chip Selects */
-#define GPMC_CS_NUM		8
-
-#define GPMC_CS_CONFIG1		0x00
-#define GPMC_CS_CONFIG2		0x04
-#define GPMC_CS_CONFIG3		0x08
-#define GPMC_CS_CONFIG4		0x0c
-#define GPMC_CS_CONFIG5		0x10
-#define GPMC_CS_CONFIG6		0x14
-#define GPMC_CS_CONFIG7		0x18
-#define GPMC_CS_NAND_COMMAND	0x1c
-#define GPMC_CS_NAND_ADDRESS	0x20
-#define GPMC_CS_NAND_DATA	0x24
-
-/* Control Commands */
-#define GPMC_CONFIG_RDY_BSY	0x00000001
-#define GPMC_CONFIG_DEV_SIZE	0x00000002
-#define GPMC_CONFIG_DEV_TYPE	0x00000003
-#define GPMC_SET_IRQ_STATUS	0x00000004
-#define GPMC_CONFIG_WP		0x00000005
-
-#define GPMC_ENABLE_IRQ		0x0000000d
-
-/* ECC commands */
-#define GPMC_ECC_READ		0 /* Reset Hardware ECC for read */
-#define GPMC_ECC_WRITE		1 /* Reset Hardware ECC for write */
-#define GPMC_ECC_READSYN	2 /* Reset before syndrom is read back */
-
-#define GPMC_CONFIG1_WRAPBURST_SUPP     (1 << 31)
-#define GPMC_CONFIG1_READMULTIPLE_SUPP  (1 << 30)
-#define GPMC_CONFIG1_READTYPE_ASYNC     (0 << 29)
-#define GPMC_CONFIG1_READTYPE_SYNC      (1 << 29)
-#define GPMC_CONFIG1_WRITEMULTIPLE_SUPP (1 << 28)
-#define GPMC_CONFIG1_WRITETYPE_ASYNC    (0 << 27)
-#define GPMC_CONFIG1_WRITETYPE_SYNC     (1 << 27)
-#define GPMC_CONFIG1_CLKACTIVATIONTIME(val) ((val & 3) << 25)
-#define GPMC_CONFIG1_PAGE_LEN(val)      ((val & 3) << 23)
-#define GPMC_CONFIG1_WAIT_READ_MON      (1 << 22)
-#define GPMC_CONFIG1_WAIT_WRITE_MON     (1 << 21)
-#define GPMC_CONFIG1_WAIT_MON_IIME(val) ((val & 3) << 18)
-#define GPMC_CONFIG1_WAIT_PIN_SEL(val)  ((val & 3) << 16)
-#define GPMC_CONFIG1_DEVICESIZE(val)    ((val & 3) << 12)
-#define GPMC_CONFIG1_DEVICESIZE_16      GPMC_CONFIG1_DEVICESIZE(1)
-#define GPMC_CONFIG1_DEVICETYPE(val)    ((val & 3) << 10)
-#define GPMC_CONFIG1_DEVICETYPE_NOR     GPMC_CONFIG1_DEVICETYPE(0)
-#define GPMC_CONFIG1_MUXTYPE(val)       ((val & 3) << 8)
-#define GPMC_CONFIG1_TIME_PARA_GRAN     (1 << 4)
-#define GPMC_CONFIG1_FCLK_DIV(val)      (val & 3)
-#define GPMC_CONFIG1_FCLK_DIV2          (GPMC_CONFIG1_FCLK_DIV(1))
-#define GPMC_CONFIG1_FCLK_DIV3          (GPMC_CONFIG1_FCLK_DIV(2))
-#define GPMC_CONFIG1_FCLK_DIV4          (GPMC_CONFIG1_FCLK_DIV(3))
-#define GPMC_CONFIG7_CSVALID		(1 << 6)
-
-#define GPMC_DEVICETYPE_NOR		0
-#define GPMC_DEVICETYPE_NAND		2
-#define GPMC_CONFIG_WRITEPROTECT	0x00000010
-#define WR_RD_PIN_MONITORING		0x00600000
-#define GPMC_IRQ_FIFOEVENTENABLE	0x01
-#define GPMC_IRQ_COUNT_EVENT		0x02
-
-#define GPMC_BURST_4			4	/* 4 word burst */
-#define GPMC_BURST_8			8	/* 8 word burst */
-#define GPMC_BURST_16			16	/* 16 word burst */
-#define GPMC_DEVWIDTH_8BIT		1	/* 8-bit device width */
-#define GPMC_DEVWIDTH_16BIT		2	/* 16-bit device width */
-#define GPMC_MUX_AAD			1	/* Addr-Addr-Data multiplex */
-#define GPMC_MUX_AD			2	/* Addr-Data multiplex */
-
-/* bool type time settings */
-struct gpmc_bool_timings {
-	bool cycle2cyclediffcsen;
-	bool cycle2cyclesamecsen;
-	bool we_extra_delay;
-	bool oe_extra_delay;
-	bool adv_extra_delay;
-	bool cs_extra_delay;
-	bool time_para_granularity;
-};
-
-/*
- * Note that all values in this struct are in nanoseconds except sync_clk
- * (which is in picoseconds), while the register values are in gpmc_fck cycles.
- */
-struct gpmc_timings {
-	/* Minimum clock period for synchronous mode (in picoseconds) */
-	u32 sync_clk;
-
-	/* Chip-select signal timings corresponding to GPMC_CS_CONFIG2 */
-	u32 cs_on;		/* Assertion time */
-	u32 cs_rd_off;		/* Read deassertion time */
-	u32 cs_wr_off;		/* Write deassertion time */
-
-	/* ADV signal timings corresponding to GPMC_CONFIG3 */
-	u32 adv_on;		/* Assertion time */
-	u32 adv_rd_off;		/* Read deassertion time */
-	u32 adv_wr_off;		/* Write deassertion time */
-
-	/* WE signals timings corresponding to GPMC_CONFIG4 */
-	u32 we_on;		/* WE assertion time */
-	u32 we_off;		/* WE deassertion time */
-
-	/* OE signals timings corresponding to GPMC_CONFIG4 */
-	u32 oe_on;		/* OE assertion time */
-	u32 oe_off;		/* OE deassertion time */
-
-	/* Access time and cycle time timings corresponding to GPMC_CONFIG5 */
-	u32 page_burst_access;	/* Multiple access word delay */
-	u32 access;		/* Start-cycle to first data valid delay */
-	u32 rd_cycle;		/* Total read cycle time */
-	u32 wr_cycle;		/* Total write cycle time */
-
-	u32 bus_turnaround;
-	u32 cycle2cycle_delay;
-
-	u32 wait_monitoring;
-	u32 clk_activation;
-
-	/* The following are only on OMAP3430 */
-	u32 wr_access;		/* WRACCESSTIME */
-	u32 wr_data_mux_bus;	/* WRDATAONADMUXBUS */
-
-	struct gpmc_bool_timings bool_timings;
-};
-
-/* Device timings in picoseconds */
-struct gpmc_device_timings {
-	u32 t_ceasu;	/* address setup to CS valid */
-	u32 t_avdasu;	/* address setup to ADV valid */
-	/* XXX: try to combine t_avdp_r & t_avdp_w. Issue is
-	 * of tusb using these timings even for sync whilst
-	 * ideally for adv_rd/(wr)_off it should have considered
-	 * t_avdh instead. This indirectly necessitates r/w
-	 * variations of t_avdp as it is possible to have one
-	 * sync & other async
-	 */
-	u32 t_avdp_r;	/* ADV low time (what about t_cer ?) */
-	u32 t_avdp_w;
-	u32 t_aavdh;	/* address hold time */
-	u32 t_oeasu;	/* address setup to OE valid */
-	u32 t_aa;	/* access time from ADV assertion */
-	u32 t_iaa;	/* initial access time */
-	u32 t_oe;	/* access time from OE assertion */
-	u32 t_ce;	/* access time from CS asertion */
-	u32 t_rd_cycle;	/* read cycle time */
-	u32 t_cez_r;	/* read CS deassertion to high Z */
-	u32 t_cez_w;	/* write CS deassertion to high Z */
-	u32 t_oez;	/* OE deassertion to high Z */
-	u32 t_weasu;	/* address setup to WE valid */
-	u32 t_wpl;	/* write assertion time */
-	u32 t_wph;	/* write deassertion time */
-	u32 t_wr_cycle;	/* write cycle time */
-
-	u32 clk;
-	u32 t_bacc;	/* burst access valid clock to output delay */
-	u32 t_ces;	/* CS setup time to clk */
-	u32 t_avds;	/* ADV setup time to clk */
-	u32 t_avdh;	/* ADV hold time from clk */
-	u32 t_ach;	/* address hold time from clk */
-	u32 t_rdyo;	/* clk to ready valid */
-
-	u32 t_ce_rdyz;	/* XXX: description ?, or use t_cez instead */
-	u32 t_ce_avd;	/* CS on to ADV on delay */
-
-	/* XXX: check the possibility of combining
-	 * cyc_aavhd_oe & cyc_aavdh_we
-	 */
-	u8 cyc_aavdh_oe;/* read address hold time in cycles */
-	u8 cyc_aavdh_we;/* write address hold time in cycles */
-	u8 cyc_oe;	/* access time from OE assertion in cycles */
-	u8 cyc_wpl;	/* write deassertion time in cycles */
-	u32 cyc_iaa;	/* initial access time in cycles */
-
-	/* extra delays */
-	bool ce_xdelay;
-	bool avd_xdelay;
-	bool oe_xdelay;
-	bool we_xdelay;
-};
-
-struct gpmc_settings {
-	bool burst_wrap;	/* enables wrap bursting */
-	bool burst_read;	/* enables read page/burst mode */
-	bool burst_write;	/* enables write page/burst mode */
-	bool device_nand;	/* device is NAND */
-	bool sync_read;		/* enables synchronous reads */
-	bool sync_write;	/* enables synchronous writes */
-	bool wait_on_read;	/* monitor wait on reads */
-	bool wait_on_write;	/* monitor wait on writes */
-	u32 burst_len;		/* page/burst length */
-	u32 device_width;	/* device bus width (8 or 16 bit) */
-	u32 mux_add_data;	/* multiplex address & data */
-	u32 wait_pin;		/* wait-pin to be used */
-};
-
-extern int gpmc_calc_timings(struct gpmc_timings *gpmc_t,
-			     struct gpmc_settings *gpmc_s,
-			     struct gpmc_device_timings *dev_t);
-
-extern void gpmc_update_nand_reg(struct gpmc_nand_regs *reg, int cs);
-extern int gpmc_get_client_irq(unsigned irq_config);
-
-extern unsigned int gpmc_ticks_to_ns(unsigned int ticks);
-
-extern void gpmc_cs_write_reg(int cs, int idx, u32 val);
-extern int gpmc_calc_divider(unsigned int sync_clk);
-extern int gpmc_cs_set_timings(int cs, const struct gpmc_timings *t);
-extern int gpmc_cs_program_settings(int cs, struct gpmc_settings *p);
-extern int gpmc_cs_request(int cs, unsigned long size, unsigned long *base);
-extern void gpmc_cs_free(int cs);
-extern void omap3_gpmc_save_context(void);
-extern void omap3_gpmc_restore_context(void);
-extern int gpmc_configure(int cmd, int wval);
-extern void gpmc_read_settings_dt(struct device_node *np,
-				  struct gpmc_settings *p);
-
-#endif
+#include <linux/omap-gpmc.h>
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 175564c88a3..88721df6001 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -29,6 +29,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/omap-dma.h>
+#include <linux/omap-gpmc.h>
 #include <linux/platform_data/gpio-omap.h>
 
 #include <trace/events/power.h>
@@ -43,7 +44,6 @@
 #include "common.h"
 #include "cm3xxx.h"
 #include "cm-regbits-34xx.h"
-#include "gpmc.h"
 #include "prm-regbits-34xx.h"
 #include "prm3xxx.h"
 #include "pm.h"
diff --git a/include/linux/omap-gpmc.h b/include/linux/omap-gpmc.h
new file mode 100644
index 00000000000..c2080eebbb4
--- /dev/null
+++ b/include/linux/omap-gpmc.h
@@ -0,0 +1,199 @@
+/*
+ *  OMAP GPMC (General Purpose Memory Controller) defines
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ */
+
+/* Maximum Number of Chip Selects */
+#define GPMC_CS_NUM		8
+
+#define GPMC_CONFIG_WP		0x00000005
+
+#define GPMC_IRQ_FIFOEVENTENABLE	0x01
+#define GPMC_IRQ_COUNT_EVENT		0x02
+
+#define GPMC_BURST_4			4	/* 4 word burst */
+#define GPMC_BURST_8			8	/* 8 word burst */
+#define GPMC_BURST_16			16	/* 16 word burst */
+#define GPMC_DEVWIDTH_8BIT		1	/* 8-bit device width */
+#define GPMC_DEVWIDTH_16BIT		2	/* 16-bit device width */
+#define GPMC_MUX_AAD			1	/* Addr-Addr-Data multiplex */
+#define GPMC_MUX_AD			2	/* Addr-Data multiplex */
+
+/* bool type time settings */
+struct gpmc_bool_timings {
+	bool cycle2cyclediffcsen;
+	bool cycle2cyclesamecsen;
+	bool we_extra_delay;
+	bool oe_extra_delay;
+	bool adv_extra_delay;
+	bool cs_extra_delay;
+	bool time_para_granularity;
+};
+
+/*
+ * Note that all values in this struct are in nanoseconds except sync_clk
+ * (which is in picoseconds), while the register values are in gpmc_fck cycles.
+ */
+struct gpmc_timings {
+	/* Minimum clock period for synchronous mode (in picoseconds) */
+	u32 sync_clk;
+
+	/* Chip-select signal timings corresponding to GPMC_CS_CONFIG2 */
+	u32 cs_on;		/* Assertion time */
+	u32 cs_rd_off;		/* Read deassertion time */
+	u32 cs_wr_off;		/* Write deassertion time */
+
+	/* ADV signal timings corresponding to GPMC_CONFIG3 */
+	u32 adv_on;		/* Assertion time */
+	u32 adv_rd_off;		/* Read deassertion time */
+	u32 adv_wr_off;		/* Write deassertion time */
+
+	/* WE signals timings corresponding to GPMC_CONFIG4 */
+	u32 we_on;		/* WE assertion time */
+	u32 we_off;		/* WE deassertion time */
+
+	/* OE signals timings corresponding to GPMC_CONFIG4 */
+	u32 oe_on;		/* OE assertion time */
+	u32 oe_off;		/* OE deassertion time */
+
+	/* Access time and cycle time timings corresponding to GPMC_CONFIG5 */
+	u32 page_burst_access;	/* Multiple access word delay */
+	u32 access;		/* Start-cycle to first data valid delay */
+	u32 rd_cycle;		/* Total read cycle time */
+	u32 wr_cycle;		/* Total write cycle time */
+
+	u32 bus_turnaround;
+	u32 cycle2cycle_delay;
+
+	u32 wait_monitoring;
+	u32 clk_activation;
+
+	/* The following are only on OMAP3430 */
+	u32 wr_access;		/* WRACCESSTIME */
+	u32 wr_data_mux_bus;	/* WRDATAONADMUXBUS */
+
+	struct gpmc_bool_timings bool_timings;
+};
+
+/* Device timings in picoseconds */
+struct gpmc_device_timings {
+	u32 t_ceasu;	/* address setup to CS valid */
+	u32 t_avdasu;	/* address setup to ADV valid */
+	/* XXX: try to combine t_avdp_r & t_avdp_w. Issue is
+	 * of tusb using these timings even for sync whilst
+	 * ideally for adv_rd/(wr)_off it should have considered
+	 * t_avdh instead. This indirectly necessitates r/w
+	 * variations of t_avdp as it is possible to have one
+	 * sync & other async
+	 */
+	u32 t_avdp_r;	/* ADV low time (what about t_cer ?) */
+	u32 t_avdp_w;
+	u32 t_aavdh;	/* address hold time */
+	u32 t_oeasu;	/* address setup to OE valid */
+	u32 t_aa;	/* access time from ADV assertion */
+	u32 t_iaa;	/* initial access time */
+	u32 t_oe;	/* access time from OE assertion */
+	u32 t_ce;	/* access time from CS asertion */
+	u32 t_rd_cycle;	/* read cycle time */
+	u32 t_cez_r;	/* read CS deassertion to high Z */
+	u32 t_cez_w;	/* write CS deassertion to high Z */
+	u32 t_oez;	/* OE deassertion to high Z */
+	u32 t_weasu;	/* address setup to WE valid */
+	u32 t_wpl;	/* write assertion time */
+	u32 t_wph;	/* write deassertion time */
+	u32 t_wr_cycle;	/* write cycle time */
+
+	u32 clk;
+	u32 t_bacc;	/* burst access valid clock to output delay */
+	u32 t_ces;	/* CS setup time to clk */
+	u32 t_avds;	/* ADV setup time to clk */
+	u32 t_avdh;	/* ADV hold time from clk */
+	u32 t_ach;	/* address hold time from clk */
+	u32 t_rdyo;	/* clk to ready valid */
+
+	u32 t_ce_rdyz;	/* XXX: description ?, or use t_cez instead */
+	u32 t_ce_avd;	/* CS on to ADV on delay */
+
+	/* XXX: check the possibility of combining
+	 * cyc_aavhd_oe & cyc_aavdh_we
+	 */
+	u8 cyc_aavdh_oe;/* read address hold time in cycles */
+	u8 cyc_aavdh_we;/* write address hold time in cycles */
+	u8 cyc_oe;	/* access time from OE assertion in cycles */
+	u8 cyc_wpl;	/* write deassertion time in cycles */
+	u32 cyc_iaa;	/* initial access time in cycles */
+
+	/* extra delays */
+	bool ce_xdelay;
+	bool avd_xdelay;
+	bool oe_xdelay;
+	bool we_xdelay;
+};
+
+struct gpmc_settings {
+	bool burst_wrap;	/* enables wrap bursting */
+	bool burst_read;	/* enables read page/burst mode */
+	bool burst_write;	/* enables write page/burst mode */
+	bool device_nand;	/* device is NAND */
+	bool sync_read;		/* enables synchronous reads */
+	bool sync_write;	/* enables synchronous writes */
+	bool wait_on_read;	/* monitor wait on reads */
+	bool wait_on_write;	/* monitor wait on writes */
+	u32 burst_len;		/* page/burst length */
+	u32 device_width;	/* device bus width (8 or 16 bit) */
+	u32 mux_add_data;	/* multiplex address & data */
+	u32 wait_pin;		/* wait-pin to be used */
+};
+
+extern int gpmc_calc_timings(struct gpmc_timings *gpmc_t,
+			     struct gpmc_settings *gpmc_s,
+			     struct gpmc_device_timings *dev_t);
+
+struct gpmc_nand_regs;
+struct device_node;
+
+extern void gpmc_update_nand_reg(struct gpmc_nand_regs *reg, int cs);
+extern int gpmc_get_client_irq(unsigned irq_config);
+
+extern unsigned int gpmc_ticks_to_ns(unsigned int ticks);
+
+extern void gpmc_cs_write_reg(int cs, int idx, u32 val);
+extern int gpmc_calc_divider(unsigned int sync_clk);
+extern int gpmc_cs_set_timings(int cs, const struct gpmc_timings *t);
+extern int gpmc_cs_program_settings(int cs, struct gpmc_settings *p);
+extern int gpmc_cs_request(int cs, unsigned long size, unsigned long *base);
+extern void gpmc_cs_free(int cs);
+extern int gpmc_configure(int cmd, int wval);
+extern void gpmc_read_settings_dt(struct device_node *np,
+				  struct gpmc_settings *p);
+
+extern void omap3_gpmc_save_context(void);
+extern void omap3_gpmc_restore_context(void);
+
+struct gpmc_timings;
+struct omap_nand_platform_data;
+struct omap_onenand_platform_data;
+
+#if IS_ENABLED(CONFIG_MTD_NAND_OMAP2)
+extern int gpmc_nand_init(struct omap_nand_platform_data *d,
+			  struct gpmc_timings *gpmc_t);
+#else
+static inline int gpmc_nand_init(struct omap_nand_platform_data *d,
+				 struct gpmc_timings *gpmc_t)
+{
+	return 0;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2)
+extern void gpmc_onenand_init(struct omap_onenand_platform_data *d);
+#else
+#define board_onenand_data	NULL
+static inline void gpmc_onenand_init(struct omap_onenand_platform_data *d)
+{
+}
+#endif
-- 
cgit v1.2.3-70-g09d2


From 2fc9f6baa24ac230166df41ed636224969523341 Mon Sep 17 00:00:00 2001
From: Eryu Guan <guaneryu@gmail.com>
Date: Mon, 13 Oct 2014 12:42:12 +0800
Subject: Btrfs: return failure if btrfs_dev_replace_finishing() failed

device replace could fail due to another running scrub process or any
other errors btrfs_scrub_dev() may hit, but this failure doesn't get
returned to userspace.

The following steps could reproduce this issue

	mkfs -t btrfs -f /dev/sdb1 /dev/sdb2
	mount /dev/sdb1 /mnt/btrfs
	while true; do btrfs scrub start -B /mnt/btrfs >/dev/null 2>&1; done &
	btrfs replace start -Bf /dev/sdb2 /dev/sdb3 /mnt/btrfs
	# if this replace succeeded, do the following and repeat until
	# you see this log in dmesg
	# BTRFS: btrfs_scrub_dev(/dev/sdb2, 2, /dev/sdb3) failed -115
	#btrfs replace start -Bf /dev/sdb3 /dev/sdb2 /mnt/btrfs

	# once you see the error log in dmesg, check return value of
	# replace
	echo $?

Introduce a new dev replace result

BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS

to catch -EINPROGRESS explicitly and return other errors directly to
userspace.

Signed-off-by: Eryu Guan <guaneryu@gmail.com>
Signed-off-by: Chris Mason <clm@fb.com>
---
 fs/btrfs/dev-replace.c     | 12 +++++++++---
 include/uapi/linux/btrfs.h |  1 +
 2 files changed, 10 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 6f662b34ba0..971c061eb1c 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -422,9 +422,15 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 			      &dev_replace->scrub_progress, 0, 1);
 
 	ret = btrfs_dev_replace_finishing(root->fs_info, ret);
-	WARN_ON(ret);
+	/* don't warn if EINPROGRESS, someone else might be running scrub */
+	if (ret == -EINPROGRESS) {
+		args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
+		ret = 0;
+	} else {
+		WARN_ON(ret);
+	}
 
-	return 0;
+	return ret;
 
 leave:
 	dev_replace->srcdev = NULL;
@@ -542,7 +548,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 			btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 
-		return 0;
+		return scrub_ret;
 	}
 
 	printk_in_rcu(KERN_INFO
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 2f47824e7a3..611e1c5893b 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -157,6 +157,7 @@ struct btrfs_ioctl_dev_replace_status_params {
 #define BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR			0
 #define BTRFS_IOCTL_DEV_REPLACE_RESULT_NOT_STARTED		1
 #define BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED		2
+#define BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS		3
 struct btrfs_ioctl_dev_replace_args {
 	__u64 cmd;	/* in */
 	__u64 result;	/* out */
-- 
cgit v1.2.3-70-g09d2


From d451057464a7ea2fe400e56c8a7e004c875f2a84 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Wed, 19 Nov 2014 17:28:17 +0200
Subject: phy: safer to_phy() macro

This makes to_phy() macro work with other variable names
besides "dev".

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Tested-by: Vivek Gautam <gautam.vivek@samsung.com>
Acked-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 include/linux/phy/phy.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index 8cb6f815475..9fda6832429 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -110,7 +110,7 @@ struct phy_init_data {
 	.port		= _port,				\
 }
 
-#define	to_phy(dev)	(container_of((dev), struct phy, dev))
+#define	to_phy(a)	(container_of((a), struct phy, dev))
 
 #define	of_phy_provider_register(dev, xlate)	\
 	__of_phy_provider_register((dev), THIS_MODULE, (xlate))
-- 
cgit v1.2.3-70-g09d2


From b7bc15b98e843926d01eb03b9c0e196d8ddbadeb Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Wed, 19 Nov 2014 17:28:18 +0200
Subject: phy: improved lookup method

Separates registration of the phy and the lookup. The method
is copied from clkdev.c,

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 Documentation/phy.txt   | 60 ++++++++++-------------------------
 drivers/phy/phy-core.c  | 84 ++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/phy/phy.h | 16 ++++++++++
 3 files changed, 115 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/Documentation/phy.txt b/Documentation/phy.txt
index c6594af94d2..371361c69a4 100644
--- a/Documentation/phy.txt
+++ b/Documentation/phy.txt
@@ -54,18 +54,14 @@ The PHY driver should create the PHY in order for other peripheral controllers
 to make use of it. The PHY framework provides 2 APIs to create the PHY.
 
 struct phy *phy_create(struct device *dev, struct device_node *node,
-		       const struct phy_ops *ops,
-		       struct phy_init_data *init_data);
+		       const struct phy_ops *ops);
 struct phy *devm_phy_create(struct device *dev, struct device_node *node,
-			    const struct phy_ops *ops,
-			    struct phy_init_data *init_data);
+			    const struct phy_ops *ops);
 
 The PHY drivers can use one of the above 2 APIs to create the PHY by passing
-the device pointer, phy ops and init_data.
+the device pointer and phy ops.
 phy_ops is a set of function pointers for performing PHY operations such as
-init, exit, power_on and power_off. *init_data* is mandatory to get a reference
-to the PHY in the case of non-dt boot. See section *Board File Initialization*
-on how init_data should be used.
+init, exit, power_on and power_off.
 
 Inorder to dereference the private data (in phy_ops), the phy provider driver
 can use phy_set_drvdata() after creating the PHY and use phy_get_drvdata() in
@@ -137,42 +133,18 @@ There are exported APIs like phy_pm_runtime_get, phy_pm_runtime_get_sync,
 phy_pm_runtime_put, phy_pm_runtime_put_sync, phy_pm_runtime_allow and
 phy_pm_runtime_forbid for performing PM operations.
 
-8. Board File Initialization
-
-Certain board file initialization is necessary in order to get a reference
-to the PHY in the case of non-dt boot.
-Say we have a single device that implements 3 PHYs that of USB, SATA and PCIe,
-then in the board file the following initialization should be done.
-
-struct phy_consumer consumers[] = {
-	PHY_CONSUMER("dwc3.0", "usb"),
-	PHY_CONSUMER("pcie.0", "pcie"),
-	PHY_CONSUMER("sata.0", "sata"),
-};
-PHY_CONSUMER takes 2 parameters, first is the device name of the controller
-(PHY consumer) and second is the port name.
-
-struct phy_init_data init_data = {
-	.consumers = consumers,
-	.num_consumers = ARRAY_SIZE(consumers),
-};
-
-static const struct platform_device pipe3_phy_dev = {
-	.name = "pipe3-phy",
-	.id = -1,
-	.dev = {
-		.platform_data = {
-			.init_data = &init_data,
-		},
-	},
-};
-
-then, while doing phy_create, the PHY driver should pass this init_data
-	phy_create(dev, ops, pdata->init_data);
-
-and the controller driver (phy consumer) should pass the port name along with
-the device to get a reference to the PHY
-	phy_get(dev, "pcie");
+8. PHY Mappings
+
+In order to get reference to a PHY without help from DeviceTree, the framework
+offers lookups which can be compared to clkdev that allow clk structures to be
+bound to devices. A lookup can be made be made during runtime when a handle to
+the struct phy already exists.
+
+The framework offers the following API for registering and unregistering the
+lookups.
+
+int phy_create_lookup(struct phy *phy, const char *con_id, const char *dev_id);
+void phy_remove_lookup(struct phy *phy, const char *con_id, const char *dev_id);
 
 9. DeviceTree Binding
 
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 1606ce9805d..bc830773fe0 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -26,6 +26,7 @@
 static struct class *phy_class;
 static DEFINE_MUTEX(phy_provider_mutex);
 static LIST_HEAD(phy_provider_list);
+static LIST_HEAD(phys);
 static DEFINE_IDA(phy_ida);
 
 static void devm_phy_release(struct device *dev, void *res)
@@ -84,6 +85,87 @@ static struct phy *phy_lookup(struct device *device, const char *port)
 	return ERR_PTR(-ENODEV);
 }
 
+/**
+ * phy_create_lookup() - allocate and register PHY/device association
+ * @phy: the phy of the association
+ * @con_id: connection ID string on device
+ * @dev_id: the device of the association
+ *
+ * Creates and registers phy_lookup entry.
+ */
+int phy_create_lookup(struct phy *phy, const char *con_id, const char *dev_id)
+{
+	struct phy_lookup *pl;
+
+	if (!phy || !dev_id || !con_id)
+		return -EINVAL;
+
+	pl = kzalloc(sizeof(*pl), GFP_KERNEL);
+	if (!pl)
+		return -ENOMEM;
+
+	pl->dev_id = dev_id;
+	pl->con_id = con_id;
+	pl->phy = phy;
+
+	mutex_lock(&phy_provider_mutex);
+	list_add_tail(&pl->node, &phys);
+	mutex_unlock(&phy_provider_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(phy_create_lookup);
+
+/**
+ * phy_remove_lookup() - find and remove PHY/device association
+ * @phy: the phy of the association
+ * @con_id: connection ID string on device
+ * @dev_id: the device of the association
+ *
+ * Finds and unregisters phy_lookup entry that was created with
+ * phy_create_lookup().
+ */
+void phy_remove_lookup(struct phy *phy, const char *con_id, const char *dev_id)
+{
+	struct phy_lookup *pl;
+
+	if (!phy || !dev_id || !con_id)
+		return;
+
+	mutex_lock(&phy_provider_mutex);
+	list_for_each_entry(pl, &phys, node)
+		if (pl->phy == phy && !strcmp(pl->dev_id, dev_id) &&
+		    !strcmp(pl->con_id, con_id)) {
+			list_del(&pl->node);
+			kfree(pl);
+			break;
+		}
+	mutex_unlock(&phy_provider_mutex);
+}
+EXPORT_SYMBOL_GPL(phy_remove_lookup);
+
+static struct phy *phy_find(struct device *dev, const char *con_id)
+{
+	const char *dev_id = dev_name(dev);
+	struct phy_lookup *p, *pl = NULL;
+	struct phy *phy;
+
+	mutex_lock(&phy_provider_mutex);
+	list_for_each_entry(p, &phys, node)
+		if (!strcmp(p->dev_id, dev_id) && !strcmp(p->con_id, con_id)) {
+			pl = p;
+			break;
+		}
+	mutex_unlock(&phy_provider_mutex);
+
+	phy = pl ? pl->phy : ERR_PTR(-ENODEV);
+
+	/* fall-back to the old lookup method for now */
+	if (IS_ERR(phy))
+		phy = phy_lookup(dev, con_id);
+	return phy;
+}
+
 static struct phy_provider *of_phy_provider_lookup(struct device_node *node)
 {
 	struct phy_provider *phy_provider;
@@ -455,7 +537,7 @@ struct phy *phy_get(struct device *dev, const char *string)
 			string);
 		phy = _of_phy_get(dev->of_node, index);
 	} else {
-		phy = phy_lookup(dev, string);
+		phy = phy_find(dev, string);
 	}
 	if (IS_ERR(phy))
 		return phy;
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index 9fda6832429..849284e5873 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -110,6 +110,13 @@ struct phy_init_data {
 	.port		= _port,				\
 }
 
+struct phy_lookup {
+	struct list_head node;
+	const char *dev_id;
+	const char *con_id;
+	struct phy *phy;
+};
+
 #define	to_phy(a)	(container_of((a), struct phy, dev))
 
 #define	of_phy_provider_register(dev, xlate)	\
@@ -174,6 +181,8 @@ struct phy_provider *__devm_of_phy_provider_register(struct device *dev,
 void of_phy_provider_unregister(struct phy_provider *phy_provider);
 void devm_of_phy_provider_unregister(struct device *dev,
 	struct phy_provider *phy_provider);
+int phy_create_lookup(struct phy *phy, const char *con_id, const char *dev_id);
+void phy_remove_lookup(struct phy *phy, const char *con_id, const char *dev_id);
 #else
 static inline int phy_pm_runtime_get(struct phy *phy)
 {
@@ -345,6 +354,13 @@ static inline void devm_of_phy_provider_unregister(struct device *dev,
 	struct phy_provider *phy_provider)
 {
 }
+static inline int
+phy_create_lookup(struct phy *phy, const char *con_id, const char *dev_id)
+{
+	return 0;
+}
+static inline void phy_remove_lookup(struct phy *phy, const char *con_id,
+				     const char *dev_id) { }
 #endif
 
 #endif /* __DRIVERS_PHY_H */
-- 
cgit v1.2.3-70-g09d2


From df9f7b311db1edae7ec5e2c78aa92fce7b9dd34d Mon Sep 17 00:00:00 2001
From: Kiran Raparthy <kiran.kumar@linaro.org>
Date: Fri, 21 Nov 2014 11:31:20 +0530
Subject: usb: phy: introduce usb_phy_set_event interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PHY drivers require a generic interface to handle per-PHY events.

usb_phy_set_event interface sets event to phy event.
PHY drivers call this interface for each phy event.

Cc: Felipe Balbi <balbi@ti.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-kernel@vger.kernel.org
Cc: linux-usb@vger.kernel.org
Cc: Android Kernel Team <kernel-team@android.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Arve Hj�nnev�g <arve@android.com>
Cc: Benoit Goby <benoit@android.com>
[Original patch in Android from Todd]
Cc: Todd Poynor <toddpoynor@google.com>
Signed-off-by: Kiran Raparthy <kiran.kumar@linaro.org>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/phy/phy.c   | 12 ++++++++++++
 include/linux/usb/phy.h |  5 +++++
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c
index e6bf801a339..b4066a001ba 100644
--- a/drivers/usb/phy/phy.c
+++ b/drivers/usb/phy/phy.c
@@ -446,3 +446,15 @@ int usb_bind_phy(const char *dev_name, u8 index,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(usb_bind_phy);
+
+/**
+ * usb_phy_set_event - set event to phy event
+ * @x: the phy returned by usb_get_phy();
+ *
+ * This sets event to phy event
+ */
+void usb_phy_set_event(struct usb_phy *x, unsigned long event)
+{
+	x->last_event = event;
+}
+EXPORT_SYMBOL_GPL(usb_phy_set_event);
diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h
index ac7d7913694..f499c23e634 100644
--- a/include/linux/usb/phy.h
+++ b/include/linux/usb/phy.h
@@ -209,6 +209,7 @@ extern void usb_put_phy(struct usb_phy *);
 extern void devm_usb_put_phy(struct device *dev, struct usb_phy *x);
 extern int usb_bind_phy(const char *dev_name, u8 index,
 				const char *phy_dev_name);
+extern void usb_phy_set_event(struct usb_phy *x, unsigned long event);
 #else
 static inline struct usb_phy *usb_get_phy(enum usb_phy_type type)
 {
@@ -250,6 +251,10 @@ static inline int usb_bind_phy(const char *dev_name, u8 index,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline void usb_phy_set_event(struct usb_phy *x, unsigned long event)
+{
+}
 #endif
 
 static inline int
-- 
cgit v1.2.3-70-g09d2


From 04b74b27c2941e5d62120f6fee3a0a9388a30613 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 21 Nov 2014 09:16:58 -0500
Subject: printk/percpu: Define printk_func when printk is not defined

To avoid include hell, the per_cpu variable printk_func was declared
in percpu.h. But it is only defined if printk is defined.

As users of printk may also use the printk_func variable, it needs to
be defined even if CONFIG_PRINTK is not.

Also add a printk.h include in percpu.h just to be safe.

Link: http://lkml.kernel.org/r/20141121183215.01ba539c@canb.auug.org.au

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/percpu.h | 1 +
 include/linux/printk.h | 4 ++--
 kernel/printk/printk.c | 3 +++
 3 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index ba2e85a0ff5..caebf2a758d 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -5,6 +5,7 @@
 #include <linux/preempt.h>
 #include <linux/smp.h>
 #include <linux/cpumask.h>
+#include <linux/printk.h>
 #include <linux/pfn.h>
 #include <linux/init.h>
 
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 3bbd979d32f..c69be9ee8f4 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -124,6 +124,8 @@ static inline __printf(1, 2) __cold
 void early_printk(const char *s, ...) { }
 #endif
 
+typedef int(*printk_func_t)(const char *fmt, va_list args);
+
 #ifdef CONFIG_PRINTK
 asmlinkage __printf(5, 0)
 int vprintk_emit(int facility, int level,
@@ -162,8 +164,6 @@ extern int kptr_restrict;
 
 extern void wake_up_klogd(void);
 
-typedef int(*printk_func_t)(const char *fmt, va_list args);
-
 void log_buf_kexec_setup(void);
 void __init setup_log_buf(int early);
 void dump_stack_set_arch_desc(const char *fmt, ...);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index f7b723f98cb..5af2b8bc88f 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1896,6 +1896,9 @@ static size_t msg_print_text(const struct printk_log *msg, enum log_flags prev,
 			     bool syslog, char *buf, size_t size) { return 0; }
 static size_t cont_print_text(char *text, size_t size) { return 0; }
 
+/* Still needs to be defined for users */
+DEFINE_PER_CPU(printk_func_t, printk_func);
+
 #endif /* CONFIG_PRINTK */
 
 #ifdef CONFIG_EARLY_PRINTK
-- 
cgit v1.2.3-70-g09d2


From 6ef768fac9dfe3404d3fdc09909ea203a88f2f38 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 20 Nov 2014 13:45:31 +0100
Subject: kvm: x86: move ioapic.c and irq_comm.c back to arch/x86/

ia64 does not need them anymore.  Ack notifiers become x86-specific
too.

Suggested-by: Gleb Natapov <gleb@kernel.org>
Reviewed-by: Radim Krcmar <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  16 +
 arch/x86/kvm/Makefile           |   5 +-
 arch/x86/kvm/ioapic.c           | 682 ++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/ioapic.h           | 102 ++++++
 arch/x86/kvm/irq_comm.c         | 347 ++++++++++++++++++++
 arch/x86/kvm/x86.c              |   1 +
 include/linux/kvm_host.h        |  22 +-
 virt/kvm/eventfd.c              |   7 -
 virt/kvm/ioapic.c               | 682 ----------------------------------------
 virt/kvm/ioapic.h               | 103 ------
 virt/kvm/irq_comm.c             | 347 --------------------
 virt/kvm/kvm_main.c             |   3 -
 12 files changed, 1158 insertions(+), 1159 deletions(-)
 create mode 100644 arch/x86/kvm/ioapic.c
 create mode 100644 arch/x86/kvm/ioapic.h
 create mode 100644 arch/x86/kvm/irq_comm.c
 delete mode 100644 virt/kvm/ioapic.c
 delete mode 100644 virt/kvm/ioapic.h
 delete mode 100644 virt/kvm/irq_comm.c

(limited to 'include')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 769db36a300..76ff3e2d8fd 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -603,6 +603,9 @@ struct kvm_arch {
 
 	struct kvm_xen_hvm_config xen_hvm_config;
 
+	/* reads protected by irq_srcu, writes by irq_lock */
+	struct hlist_head mask_notifier_list;
+
 	/* fields used by HYPER-V emulation */
 	u64 hv_guest_os_id;
 	u64 hv_hypercall;
@@ -819,6 +822,19 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 			  const void *val, int bytes);
 u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
 
+struct kvm_irq_mask_notifier {
+	void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked);
+	int irq;
+	struct hlist_node link;
+};
+
+void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
+				    struct kvm_irq_mask_notifier *kimn);
+void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
+				      struct kvm_irq_mask_notifier *kimn);
+void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
+			     bool mask);
+
 extern bool tdp_enabled;
 
 u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 25d22b2d650..ee1cd92b03b 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -7,14 +7,13 @@ CFLAGS_vmx.o := -I.
 
 KVM := ../../../virt/kvm
 
-kvm-y			+= $(KVM)/kvm_main.o $(KVM)/ioapic.o \
-				$(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \
+kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
 				$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= $(KVM)/assigned-dev.o $(KVM)/iommu.o
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
-			   i8254.o cpuid.o pmu.o
+			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o
 kvm-intel-y		+= vmx.o
 kvm-amd-y		+= svm.o
 
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
new file mode 100644
index 00000000000..f0f7ef82b7a
--- /dev/null
+++ b/arch/x86/kvm/ioapic.c
@@ -0,0 +1,682 @@
+/*
+ *  Copyright (C) 2001  MandrakeSoft S.A.
+ *  Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ *
+ *    MandrakeSoft S.A.
+ *    43, rue d'Aboukir
+ *    75002 Paris - France
+ *    http://www.linux-mandrake.com/
+ *    http://www.mandrakesoft.com/
+ *
+ *  This library is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU Lesser General Public
+ *  License as published by the Free Software Foundation; either
+ *  version 2 of the License, or (at your option) any later version.
+ *
+ *  This library is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  Lesser General Public License for more details.
+ *
+ *  You should have received a copy of the GNU Lesser General Public
+ *  License along with this library; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ *  Yunhong Jiang <yunhong.jiang@intel.com>
+ *  Yaozu (Eddie) Dong <eddie.dong@intel.com>
+ *  Based on Xen 3.1 code.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/smp.h>
+#include <linux/hrtimer.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/current.h>
+#include <trace/events/kvm.h>
+
+#include "ioapic.h"
+#include "lapic.h"
+#include "irq.h"
+
+#if 0
+#define ioapic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg)
+#else
+#define ioapic_debug(fmt, arg...)
+#endif
+static int ioapic_service(struct kvm_ioapic *vioapic, int irq,
+		bool line_status);
+
+static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
+					  unsigned long addr,
+					  unsigned long length)
+{
+	unsigned long result = 0;
+
+	switch (ioapic->ioregsel) {
+	case IOAPIC_REG_VERSION:
+		result = ((((IOAPIC_NUM_PINS - 1) & 0xff) << 16)
+			  | (IOAPIC_VERSION_ID & 0xff));
+		break;
+
+	case IOAPIC_REG_APIC_ID:
+	case IOAPIC_REG_ARB_ID:
+		result = ((ioapic->id & 0xf) << 24);
+		break;
+
+	default:
+		{
+			u32 redir_index = (ioapic->ioregsel - 0x10) >> 1;
+			u64 redir_content;
+
+			if (redir_index < IOAPIC_NUM_PINS)
+				redir_content =
+					ioapic->redirtbl[redir_index].bits;
+			else
+				redir_content = ~0ULL;
+
+			result = (ioapic->ioregsel & 0x1) ?
+			    (redir_content >> 32) & 0xffffffff :
+			    redir_content & 0xffffffff;
+			break;
+		}
+	}
+
+	return result;
+}
+
+static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
+{
+	ioapic->rtc_status.pending_eoi = 0;
+	bitmap_zero(ioapic->rtc_status.dest_map, KVM_MAX_VCPUS);
+}
+
+static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
+
+static void rtc_status_pending_eoi_check_valid(struct kvm_ioapic *ioapic)
+{
+	if (WARN_ON(ioapic->rtc_status.pending_eoi < 0))
+		kvm_rtc_eoi_tracking_restore_all(ioapic);
+}
+
+static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
+{
+	bool new_val, old_val;
+	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+	union kvm_ioapic_redirect_entry *e;
+
+	e = &ioapic->redirtbl[RTC_GSI];
+	if (!kvm_apic_match_dest(vcpu, NULL, 0,	e->fields.dest_id,
+				e->fields.dest_mode))
+		return;
+
+	new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
+	old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
+
+	if (new_val == old_val)
+		return;
+
+	if (new_val) {
+		__set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
+		ioapic->rtc_status.pending_eoi++;
+	} else {
+		__clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
+		ioapic->rtc_status.pending_eoi--;
+		rtc_status_pending_eoi_check_valid(ioapic);
+	}
+}
+
+void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
+{
+	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+
+	spin_lock(&ioapic->lock);
+	__rtc_irq_eoi_tracking_restore_one(vcpu);
+	spin_unlock(&ioapic->lock);
+}
+
+static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic)
+{
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	if (RTC_GSI >= IOAPIC_NUM_PINS)
+		return;
+
+	rtc_irq_eoi_tracking_reset(ioapic);
+	kvm_for_each_vcpu(i, vcpu, ioapic->kvm)
+	    __rtc_irq_eoi_tracking_restore_one(vcpu);
+}
+
+static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu)
+{
+	if (test_and_clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map)) {
+		--ioapic->rtc_status.pending_eoi;
+		rtc_status_pending_eoi_check_valid(ioapic);
+	}
+}
+
+static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic)
+{
+	if (ioapic->rtc_status.pending_eoi > 0)
+		return true; /* coalesced */
+
+	return false;
+}
+
+static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
+		int irq_level, bool line_status)
+{
+	union kvm_ioapic_redirect_entry entry;
+	u32 mask = 1 << irq;
+	u32 old_irr;
+	int edge, ret;
+
+	entry = ioapic->redirtbl[irq];
+	edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
+
+	if (!irq_level) {
+		ioapic->irr &= ~mask;
+		ret = 1;
+		goto out;
+	}
+
+	/*
+	 * Return 0 for coalesced interrupts; for edge-triggered interrupts,
+	 * this only happens if a previous edge has not been delivered due
+	 * do masking.  For level interrupts, the remote_irr field tells
+	 * us if the interrupt is waiting for an EOI.
+	 *
+	 * RTC is special: it is edge-triggered, but userspace likes to know
+	 * if it has been already ack-ed via EOI because coalesced RTC
+	 * interrupts lead to time drift in Windows guests.  So we track
+	 * EOI manually for the RTC interrupt.
+	 */
+	if (irq == RTC_GSI && line_status &&
+		rtc_irq_check_coalesced(ioapic)) {
+		ret = 0;
+		goto out;
+	}
+
+	old_irr = ioapic->irr;
+	ioapic->irr |= mask;
+	if ((edge && old_irr == ioapic->irr) ||
+	    (!edge && entry.fields.remote_irr)) {
+		ret = 0;
+		goto out;
+	}
+
+	ret = ioapic_service(ioapic, irq, line_status);
+
+out:
+	trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
+	return ret;
+}
+
+static void kvm_ioapic_inject_all(struct kvm_ioapic *ioapic, unsigned long irr)
+{
+	u32 idx;
+
+	rtc_irq_eoi_tracking_reset(ioapic);
+	for_each_set_bit(idx, &irr, IOAPIC_NUM_PINS)
+		ioapic_set_irq(ioapic, idx, 1, true);
+
+	kvm_rtc_eoi_tracking_restore_all(ioapic);
+}
+
+
+static void update_handled_vectors(struct kvm_ioapic *ioapic)
+{
+	DECLARE_BITMAP(handled_vectors, 256);
+	int i;
+
+	memset(handled_vectors, 0, sizeof(handled_vectors));
+	for (i = 0; i < IOAPIC_NUM_PINS; ++i)
+		__set_bit(ioapic->redirtbl[i].fields.vector, handled_vectors);
+	memcpy(ioapic->handled_vectors, handled_vectors,
+	       sizeof(handled_vectors));
+	smp_wmb();
+}
+
+void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
+			u32 *tmr)
+{
+	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+	union kvm_ioapic_redirect_entry *e;
+	int index;
+
+	spin_lock(&ioapic->lock);
+	for (index = 0; index < IOAPIC_NUM_PINS; index++) {
+		e = &ioapic->redirtbl[index];
+		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
+		    kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) ||
+		    index == RTC_GSI) {
+			if (kvm_apic_match_dest(vcpu, NULL, 0,
+				e->fields.dest_id, e->fields.dest_mode)) {
+				__set_bit(e->fields.vector,
+					(unsigned long *)eoi_exit_bitmap);
+				if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG)
+					__set_bit(e->fields.vector,
+						(unsigned long *)tmr);
+			}
+		}
+	}
+	spin_unlock(&ioapic->lock);
+}
+
+#ifdef CONFIG_X86
+void kvm_vcpu_request_scan_ioapic(struct kvm *kvm)
+{
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+
+	if (!ioapic)
+		return;
+	kvm_make_scan_ioapic_request(kvm);
+}
+#else
+void kvm_vcpu_request_scan_ioapic(struct kvm *kvm)
+{
+	return;
+}
+#endif
+
+static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
+{
+	unsigned index;
+	bool mask_before, mask_after;
+	union kvm_ioapic_redirect_entry *e;
+
+	switch (ioapic->ioregsel) {
+	case IOAPIC_REG_VERSION:
+		/* Writes are ignored. */
+		break;
+
+	case IOAPIC_REG_APIC_ID:
+		ioapic->id = (val >> 24) & 0xf;
+		break;
+
+	case IOAPIC_REG_ARB_ID:
+		break;
+
+	default:
+		index = (ioapic->ioregsel - 0x10) >> 1;
+
+		ioapic_debug("change redir index %x val %x\n", index, val);
+		if (index >= IOAPIC_NUM_PINS)
+			return;
+		e = &ioapic->redirtbl[index];
+		mask_before = e->fields.mask;
+		if (ioapic->ioregsel & 1) {
+			e->bits &= 0xffffffff;
+			e->bits |= (u64) val << 32;
+		} else {
+			e->bits &= ~0xffffffffULL;
+			e->bits |= (u32) val;
+			e->fields.remote_irr = 0;
+		}
+		update_handled_vectors(ioapic);
+		mask_after = e->fields.mask;
+		if (mask_before != mask_after)
+			kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
+		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
+		    && ioapic->irr & (1 << index))
+			ioapic_service(ioapic, index, false);
+		kvm_vcpu_request_scan_ioapic(ioapic->kvm);
+		break;
+	}
+}
+
+static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
+{
+	union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq];
+	struct kvm_lapic_irq irqe;
+	int ret;
+
+	if (entry->fields.mask)
+		return -1;
+
+	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
+		     "vector=%x trig_mode=%x\n",
+		     entry->fields.dest_id, entry->fields.dest_mode,
+		     entry->fields.delivery_mode, entry->fields.vector,
+		     entry->fields.trig_mode);
+
+	irqe.dest_id = entry->fields.dest_id;
+	irqe.vector = entry->fields.vector;
+	irqe.dest_mode = entry->fields.dest_mode;
+	irqe.trig_mode = entry->fields.trig_mode;
+	irqe.delivery_mode = entry->fields.delivery_mode << 8;
+	irqe.level = 1;
+	irqe.shorthand = 0;
+
+	if (irqe.trig_mode == IOAPIC_EDGE_TRIG)
+		ioapic->irr &= ~(1 << irq);
+
+	if (irq == RTC_GSI && line_status) {
+		/*
+		 * pending_eoi cannot ever become negative (see
+		 * rtc_status_pending_eoi_check_valid) and the caller
+		 * ensures that it is only called if it is >= zero, namely
+		 * if rtc_irq_check_coalesced returns false).
+		 */
+		BUG_ON(ioapic->rtc_status.pending_eoi != 0);
+		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
+				ioapic->rtc_status.dest_map);
+		ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret);
+	} else
+		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);
+
+	if (ret && irqe.trig_mode == IOAPIC_LEVEL_TRIG)
+		entry->fields.remote_irr = 1;
+
+	return ret;
+}
+
+int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
+		       int level, bool line_status)
+{
+	int ret, irq_level;
+
+	BUG_ON(irq < 0 || irq >= IOAPIC_NUM_PINS);
+
+	spin_lock(&ioapic->lock);
+	irq_level = __kvm_irq_line_state(&ioapic->irq_states[irq],
+					 irq_source_id, level);
+	ret = ioapic_set_irq(ioapic, irq, irq_level, line_status);
+
+	spin_unlock(&ioapic->lock);
+
+	return ret;
+}
+
+void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id)
+{
+	int i;
+
+	spin_lock(&ioapic->lock);
+	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++)
+		__clear_bit(irq_source_id, &ioapic->irq_states[i]);
+	spin_unlock(&ioapic->lock);
+}
+
+static void kvm_ioapic_eoi_inject_work(struct work_struct *work)
+{
+	int i;
+	struct kvm_ioapic *ioapic = container_of(work, struct kvm_ioapic,
+						 eoi_inject.work);
+	spin_lock(&ioapic->lock);
+	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
+
+		if (ent->fields.trig_mode != IOAPIC_LEVEL_TRIG)
+			continue;
+
+		if (ioapic->irr & (1 << i) && !ent->fields.remote_irr)
+			ioapic_service(ioapic, i, false);
+	}
+	spin_unlock(&ioapic->lock);
+}
+
+#define IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT 10000
+
+static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
+			struct kvm_ioapic *ioapic, int vector, int trigger_mode)
+{
+	int i;
+
+	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
+
+		if (ent->fields.vector != vector)
+			continue;
+
+		if (i == RTC_GSI)
+			rtc_irq_eoi(ioapic, vcpu);
+		/*
+		 * We are dropping lock while calling ack notifiers because ack
+		 * notifier callbacks for assigned devices call into IOAPIC
+		 * recursively. Since remote_irr is cleared only after call
+		 * to notifiers if the same vector will be delivered while lock
+		 * is dropped it will be put into irr and will be delivered
+		 * after ack notifier returns.
+		 */
+		spin_unlock(&ioapic->lock);
+		kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
+		spin_lock(&ioapic->lock);
+
+		if (trigger_mode != IOAPIC_LEVEL_TRIG)
+			continue;
+
+		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
+		ent->fields.remote_irr = 0;
+		if (!ent->fields.mask && (ioapic->irr & (1 << i))) {
+			++ioapic->irq_eoi[i];
+			if (ioapic->irq_eoi[i] == IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT) {
+				/*
+				 * Real hardware does not deliver the interrupt
+				 * immediately during eoi broadcast, and this
+				 * lets a buggy guest make slow progress
+				 * even if it does not correctly handle a
+				 * level-triggered interrupt.  Emulate this
+				 * behavior if we detect an interrupt storm.
+				 */
+				schedule_delayed_work(&ioapic->eoi_inject, HZ / 100);
+				ioapic->irq_eoi[i] = 0;
+				trace_kvm_ioapic_delayed_eoi_inj(ent->bits);
+			} else {
+				ioapic_service(ioapic, i, false);
+			}
+		} else {
+			ioapic->irq_eoi[i] = 0;
+		}
+	}
+}
+
+bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector)
+{
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+	smp_rmb();
+	return test_bit(vector, ioapic->handled_vectors);
+}
+
+void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode)
+{
+	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+
+	spin_lock(&ioapic->lock);
+	__kvm_ioapic_update_eoi(vcpu, ioapic, vector, trigger_mode);
+	spin_unlock(&ioapic->lock);
+}
+
+static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_ioapic, dev);
+}
+
+static inline int ioapic_in_range(struct kvm_ioapic *ioapic, gpa_t addr)
+{
+	return ((addr >= ioapic->base_address &&
+		 (addr < ioapic->base_address + IOAPIC_MEM_LENGTH)));
+}
+
+static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
+			    void *val)
+{
+	struct kvm_ioapic *ioapic = to_ioapic(this);
+	u32 result;
+	if (!ioapic_in_range(ioapic, addr))
+		return -EOPNOTSUPP;
+
+	ioapic_debug("addr %lx\n", (unsigned long)addr);
+	ASSERT(!(addr & 0xf));	/* check alignment */
+
+	addr &= 0xff;
+	spin_lock(&ioapic->lock);
+	switch (addr) {
+	case IOAPIC_REG_SELECT:
+		result = ioapic->ioregsel;
+		break;
+
+	case IOAPIC_REG_WINDOW:
+		result = ioapic_read_indirect(ioapic, addr, len);
+		break;
+
+	default:
+		result = 0;
+		break;
+	}
+	spin_unlock(&ioapic->lock);
+
+	switch (len) {
+	case 8:
+		*(u64 *) val = result;
+		break;
+	case 1:
+	case 2:
+	case 4:
+		memcpy(val, (char *)&result, len);
+		break;
+	default:
+		printk(KERN_WARNING "ioapic: wrong length %d\n", len);
+	}
+	return 0;
+}
+
+static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
+			     const void *val)
+{
+	struct kvm_ioapic *ioapic = to_ioapic(this);
+	u32 data;
+	if (!ioapic_in_range(ioapic, addr))
+		return -EOPNOTSUPP;
+
+	ioapic_debug("ioapic_mmio_write addr=%p len=%d val=%p\n",
+		     (void*)addr, len, val);
+	ASSERT(!(addr & 0xf));	/* check alignment */
+
+	switch (len) {
+	case 8:
+	case 4:
+		data = *(u32 *) val;
+		break;
+	case 2:
+		data = *(u16 *) val;
+		break;
+	case 1:
+		data = *(u8  *) val;
+		break;
+	default:
+		printk(KERN_WARNING "ioapic: Unsupported size %d\n", len);
+		return 0;
+	}
+
+	addr &= 0xff;
+	spin_lock(&ioapic->lock);
+	switch (addr) {
+	case IOAPIC_REG_SELECT:
+		ioapic->ioregsel = data & 0xFF; /* 8-bit register */
+		break;
+
+	case IOAPIC_REG_WINDOW:
+		ioapic_write_indirect(ioapic, data);
+		break;
+
+	default:
+		break;
+	}
+	spin_unlock(&ioapic->lock);
+	return 0;
+}
+
+static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
+{
+	int i;
+
+	cancel_delayed_work_sync(&ioapic->eoi_inject);
+	for (i = 0; i < IOAPIC_NUM_PINS; i++)
+		ioapic->redirtbl[i].fields.mask = 1;
+	ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS;
+	ioapic->ioregsel = 0;
+	ioapic->irr = 0;
+	ioapic->id = 0;
+	memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS);
+	rtc_irq_eoi_tracking_reset(ioapic);
+	update_handled_vectors(ioapic);
+}
+
+static const struct kvm_io_device_ops ioapic_mmio_ops = {
+	.read     = ioapic_mmio_read,
+	.write    = ioapic_mmio_write,
+};
+
+int kvm_ioapic_init(struct kvm *kvm)
+{
+	struct kvm_ioapic *ioapic;
+	int ret;
+
+	ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL);
+	if (!ioapic)
+		return -ENOMEM;
+	spin_lock_init(&ioapic->lock);
+	INIT_DELAYED_WORK(&ioapic->eoi_inject, kvm_ioapic_eoi_inject_work);
+	kvm->arch.vioapic = ioapic;
+	kvm_ioapic_reset(ioapic);
+	kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
+	ioapic->kvm = kvm;
+	mutex_lock(&kvm->slots_lock);
+	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, ioapic->base_address,
+				      IOAPIC_MEM_LENGTH, &ioapic->dev);
+	mutex_unlock(&kvm->slots_lock);
+	if (ret < 0) {
+		kvm->arch.vioapic = NULL;
+		kfree(ioapic);
+	}
+
+	return ret;
+}
+
+void kvm_ioapic_destroy(struct kvm *kvm)
+{
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+
+	cancel_delayed_work_sync(&ioapic->eoi_inject);
+	if (ioapic) {
+		kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
+		kvm->arch.vioapic = NULL;
+		kfree(ioapic);
+	}
+}
+
+int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
+{
+	struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
+	if (!ioapic)
+		return -EINVAL;
+
+	spin_lock(&ioapic->lock);
+	memcpy(state, ioapic, sizeof(struct kvm_ioapic_state));
+	spin_unlock(&ioapic->lock);
+	return 0;
+}
+
+int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
+{
+	struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
+	if (!ioapic)
+		return -EINVAL;
+
+	spin_lock(&ioapic->lock);
+	memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
+	ioapic->irr = 0;
+	update_handled_vectors(ioapic);
+	kvm_vcpu_request_scan_ioapic(kvm);
+	kvm_ioapic_inject_all(ioapic, state->irr);
+	spin_unlock(&ioapic->lock);
+	return 0;
+}
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
new file mode 100644
index 00000000000..deac8d509f2
--- /dev/null
+++ b/arch/x86/kvm/ioapic.h
@@ -0,0 +1,102 @@
+#ifndef __KVM_IO_APIC_H
+#define __KVM_IO_APIC_H
+
+#include <linux/kvm_host.h>
+
+#include "iodev.h"
+
+struct kvm;
+struct kvm_vcpu;
+
+#define IOAPIC_NUM_PINS  KVM_IOAPIC_NUM_PINS
+#define IOAPIC_VERSION_ID 0x11	/* IOAPIC version */
+#define IOAPIC_EDGE_TRIG  0
+#define IOAPIC_LEVEL_TRIG 1
+
+#define IOAPIC_DEFAULT_BASE_ADDRESS  0xfec00000
+#define IOAPIC_MEM_LENGTH            0x100
+
+/* Direct registers. */
+#define IOAPIC_REG_SELECT  0x00
+#define IOAPIC_REG_WINDOW  0x10
+
+/* Indirect registers. */
+#define IOAPIC_REG_APIC_ID 0x00	/* x86 IOAPIC only */
+#define IOAPIC_REG_VERSION 0x01
+#define IOAPIC_REG_ARB_ID  0x02	/* x86 IOAPIC only */
+
+/*ioapic delivery mode*/
+#define	IOAPIC_FIXED			0x0
+#define	IOAPIC_LOWEST_PRIORITY		0x1
+#define	IOAPIC_PMI			0x2
+#define	IOAPIC_NMI			0x4
+#define	IOAPIC_INIT			0x5
+#define	IOAPIC_EXTINT			0x7
+
+#ifdef CONFIG_X86
+#define RTC_GSI 8
+#else
+#define RTC_GSI -1U
+#endif
+
+struct rtc_status {
+	int pending_eoi;
+	DECLARE_BITMAP(dest_map, KVM_MAX_VCPUS);
+};
+
+struct kvm_ioapic {
+	u64 base_address;
+	u32 ioregsel;
+	u32 id;
+	u32 irr;
+	u32 pad;
+	union kvm_ioapic_redirect_entry redirtbl[IOAPIC_NUM_PINS];
+	unsigned long irq_states[IOAPIC_NUM_PINS];
+	struct kvm_io_device dev;
+	struct kvm *kvm;
+	void (*ack_notifier)(void *opaque, int irq);
+	spinlock_t lock;
+	DECLARE_BITMAP(handled_vectors, 256);
+	struct rtc_status rtc_status;
+	struct delayed_work eoi_inject;
+	u32 irq_eoi[IOAPIC_NUM_PINS];
+};
+
+#ifdef DEBUG
+#define ASSERT(x)  							\
+do {									\
+	if (!(x)) {							\
+		printk(KERN_EMERG "assertion failed %s: %d: %s\n",	\
+		       __FILE__, __LINE__, #x);				\
+		BUG();							\
+	}								\
+} while (0)
+#else
+#define ASSERT(x) do { } while (0)
+#endif
+
+static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm)
+{
+	return kvm->arch.vioapic;
+}
+
+void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu);
+int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
+		int short_hand, unsigned int dest, int dest_mode);
+int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
+void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector,
+			int trigger_mode);
+bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector);
+int kvm_ioapic_init(struct kvm *kvm);
+void kvm_ioapic_destroy(struct kvm *kvm);
+int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
+		       int level, bool line_status);
+void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id);
+int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
+		struct kvm_lapic_irq *irq, unsigned long *dest_map);
+int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
+int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
+void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
+			u32 *tmr);
+
+#endif
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
new file mode 100644
index 00000000000..e9c135b639a
--- /dev/null
+++ b/arch/x86/kvm/irq_comm.c
@@ -0,0 +1,347 @@
+/*
+ * irq_comm.c: Common API for in kernel interrupt controller
+ * Copyright (c) 2007, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ * Authors:
+ *   Yaozu (Eddie) Dong <Eddie.dong@intel.com>
+ *
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <trace/events/kvm.h>
+
+#include <asm/msidef.h>
+
+#include "irq.h"
+
+#include "ioapic.h"
+
+static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
+			   struct kvm *kvm, int irq_source_id, int level,
+			   bool line_status)
+{
+#ifdef CONFIG_X86
+	struct kvm_pic *pic = pic_irqchip(kvm);
+	return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
+#else
+	return -1;
+#endif
+}
+
+static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
+			      struct kvm *kvm, int irq_source_id, int level,
+			      bool line_status)
+{
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level,
+				line_status);
+}
+
+inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
+{
+	return irq->delivery_mode == APIC_DM_LOWEST;
+}
+
+int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
+		struct kvm_lapic_irq *irq, unsigned long *dest_map)
+{
+	int i, r = -1;
+	struct kvm_vcpu *vcpu, *lowest = NULL;
+
+	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
+			kvm_is_dm_lowest_prio(irq)) {
+		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
+		irq->delivery_mode = APIC_DM_FIXED;
+	}
+
+	if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
+		return r;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!kvm_apic_present(vcpu))
+			continue;
+
+		if (!kvm_apic_match_dest(vcpu, src, irq->shorthand,
+					irq->dest_id, irq->dest_mode))
+			continue;
+
+		if (!kvm_is_dm_lowest_prio(irq)) {
+			if (r < 0)
+				r = 0;
+			r += kvm_apic_set_irq(vcpu, irq, dest_map);
+		} else if (kvm_lapic_enabled(vcpu)) {
+			if (!lowest)
+				lowest = vcpu;
+			else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
+				lowest = vcpu;
+		}
+	}
+
+	if (lowest)
+		r = kvm_apic_set_irq(lowest, irq, dest_map);
+
+	return r;
+}
+
+static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+				   struct kvm_lapic_irq *irq)
+{
+	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+
+	irq->dest_id = (e->msi.address_lo &
+			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
+	irq->vector = (e->msi.data &
+			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
+	irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
+	irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
+	irq->delivery_mode = e->msi.data & 0x700;
+	irq->level = 1;
+	irq->shorthand = 0;
+	/* TODO Deal with RH bit of MSI message address */
+}
+
+int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
+		struct kvm *kvm, int irq_source_id, int level, bool line_status)
+{
+	struct kvm_lapic_irq irq;
+
+	if (!level)
+		return -1;
+
+	kvm_set_msi_irq(e, &irq);
+
+	return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
+}
+
+
+static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
+			 struct kvm *kvm)
+{
+	struct kvm_lapic_irq irq;
+	int r;
+
+	kvm_set_msi_irq(e, &irq);
+
+	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
+		return r;
+	else
+		return -EWOULDBLOCK;
+}
+
+/*
+ * Deliver an IRQ in an atomic context if we can, or return a failure,
+ * user can retry in a process context.
+ * Return value:
+ *  -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context.
+ *  Other values - No need to retry.
+ */
+int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
+{
+	struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
+	struct kvm_kernel_irq_routing_entry *e;
+	int ret = -EINVAL;
+	int idx;
+
+	trace_kvm_set_irq(irq, level, irq_source_id);
+
+	/*
+	 * Injection into either PIC or IOAPIC might need to scan all CPUs,
+	 * which would need to be retried from thread context;  when same GSI
+	 * is connected to both PIC and IOAPIC, we'd have to report a
+	 * partial failure here.
+	 * Since there's no easy way to do this, we only support injecting MSI
+	 * which is limited to 1:1 GSI mapping.
+	 */
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	if (kvm_irq_map_gsi(kvm, entries, irq) > 0) {
+		e = &entries[0];
+		if (likely(e->type == KVM_IRQ_ROUTING_MSI))
+			ret = kvm_set_msi_inatomic(e, kvm);
+		else
+			ret = -EWOULDBLOCK;
+	}
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+	return ret;
+}
+
+int kvm_request_irq_source_id(struct kvm *kvm)
+{
+	unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
+	int irq_source_id;
+
+	mutex_lock(&kvm->irq_lock);
+	irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG);
+
+	if (irq_source_id >= BITS_PER_LONG) {
+		printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n");
+		irq_source_id = -EFAULT;
+		goto unlock;
+	}
+
+	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
+#ifdef CONFIG_X86
+	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
+#endif
+	set_bit(irq_source_id, bitmap);
+unlock:
+	mutex_unlock(&kvm->irq_lock);
+
+	return irq_source_id;
+}
+
+void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
+{
+	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
+#ifdef CONFIG_X86
+	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
+#endif
+
+	mutex_lock(&kvm->irq_lock);
+	if (irq_source_id < 0 ||
+	    irq_source_id >= BITS_PER_LONG) {
+		printk(KERN_ERR "kvm: IRQ source ID out of range!\n");
+		goto unlock;
+	}
+	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
+	if (!irqchip_in_kernel(kvm))
+		goto unlock;
+
+	kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
+#ifdef CONFIG_X86
+	kvm_pic_clear_all(pic_irqchip(kvm), irq_source_id);
+#endif
+unlock:
+	mutex_unlock(&kvm->irq_lock);
+}
+
+void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
+				    struct kvm_irq_mask_notifier *kimn)
+{
+	mutex_lock(&kvm->irq_lock);
+	kimn->irq = irq;
+	hlist_add_head_rcu(&kimn->link, &kvm->arch.mask_notifier_list);
+	mutex_unlock(&kvm->irq_lock);
+}
+
+void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
+				      struct kvm_irq_mask_notifier *kimn)
+{
+	mutex_lock(&kvm->irq_lock);
+	hlist_del_rcu(&kimn->link);
+	mutex_unlock(&kvm->irq_lock);
+	synchronize_srcu(&kvm->irq_srcu);
+}
+
+void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
+			     bool mask)
+{
+	struct kvm_irq_mask_notifier *kimn;
+	int idx, gsi;
+
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+	if (gsi != -1)
+		hlist_for_each_entry_rcu(kimn, &kvm->arch.mask_notifier_list, link)
+			if (kimn->irq == gsi)
+				kimn->func(kimn, mask);
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+}
+
+int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
+			  const struct kvm_irq_routing_entry *ue)
+{
+	int r = -EINVAL;
+	int delta;
+	unsigned max_pin;
+
+	switch (ue->type) {
+	case KVM_IRQ_ROUTING_IRQCHIP:
+		delta = 0;
+		switch (ue->u.irqchip.irqchip) {
+		case KVM_IRQCHIP_PIC_MASTER:
+			e->set = kvm_set_pic_irq;
+			max_pin = PIC_NUM_PINS;
+			break;
+		case KVM_IRQCHIP_PIC_SLAVE:
+			e->set = kvm_set_pic_irq;
+			max_pin = PIC_NUM_PINS;
+			delta = 8;
+			break;
+		case KVM_IRQCHIP_IOAPIC:
+			max_pin = KVM_IOAPIC_NUM_PINS;
+			e->set = kvm_set_ioapic_irq;
+			break;
+		default:
+			goto out;
+		}
+		e->irqchip.irqchip = ue->u.irqchip.irqchip;
+		e->irqchip.pin = ue->u.irqchip.pin + delta;
+		if (e->irqchip.pin >= max_pin)
+			goto out;
+		break;
+	case KVM_IRQ_ROUTING_MSI:
+		e->set = kvm_set_msi;
+		e->msi.address_lo = ue->u.msi.address_lo;
+		e->msi.address_hi = ue->u.msi.address_hi;
+		e->msi.data = ue->u.msi.data;
+		break;
+	default:
+		goto out;
+	}
+
+	r = 0;
+out:
+	return r;
+}
+
+#define IOAPIC_ROUTING_ENTRY(irq) \
+	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
+	  .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } }
+#define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq)
+
+#ifdef CONFIG_X86
+#  define PIC_ROUTING_ENTRY(irq) \
+	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
+	  .u.irqchip = { .irqchip = SELECT_PIC(irq), .pin = (irq) % 8 } }
+#  define ROUTING_ENTRY2(irq) \
+	IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq)
+#else
+#  define ROUTING_ENTRY2(irq) \
+	IOAPIC_ROUTING_ENTRY(irq)
+#endif
+
+static const struct kvm_irq_routing_entry default_routing[] = {
+	ROUTING_ENTRY2(0), ROUTING_ENTRY2(1),
+	ROUTING_ENTRY2(2), ROUTING_ENTRY2(3),
+	ROUTING_ENTRY2(4), ROUTING_ENTRY2(5),
+	ROUTING_ENTRY2(6), ROUTING_ENTRY2(7),
+	ROUTING_ENTRY2(8), ROUTING_ENTRY2(9),
+	ROUTING_ENTRY2(10), ROUTING_ENTRY2(11),
+	ROUTING_ENTRY2(12), ROUTING_ENTRY2(13),
+	ROUTING_ENTRY2(14), ROUTING_ENTRY2(15),
+	ROUTING_ENTRY1(16), ROUTING_ENTRY1(17),
+	ROUTING_ENTRY1(18), ROUTING_ENTRY1(19),
+	ROUTING_ENTRY1(20), ROUTING_ENTRY1(21),
+	ROUTING_ENTRY1(22), ROUTING_ENTRY1(23),
+};
+
+int kvm_setup_default_irq_routing(struct kvm *kvm)
+{
+	return kvm_set_irq_routing(kvm, default_routing,
+				   ARRAY_SIZE(default_routing), 0);
+}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a8f53a6960f..5337039427c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7264,6 +7264,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (type)
 		return -EINVAL;
 
+	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ea53b04993f..ded64cb3a08 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -395,7 +395,6 @@ struct kvm {
 	 * Update side is protected by irq_lock.
 	 */
 	struct kvm_irq_routing_table __rcu *irq_routing;
-	struct hlist_head mask_notifier_list;
 #endif
 #ifdef CONFIG_HAVE_KVM_IRQFD
 	struct hlist_head irq_ack_notifier_list;
@@ -447,6 +446,14 @@ void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
 int __must_check vcpu_load(struct kvm_vcpu *vcpu);
 void vcpu_put(struct kvm_vcpu *vcpu);
 
+#ifdef __KVM_HAVE_IOAPIC
+void kvm_vcpu_request_scan_ioapic(struct kvm *kvm);
+#else
+static inline void kvm_vcpu_request_scan_ioapic(struct kvm *kvm)
+{
+}
+#endif
+
 #ifdef CONFIG_HAVE_KVM_IRQFD
 int kvm_irqfd_init(void);
 void kvm_irqfd_exit(void);
@@ -736,19 +743,6 @@ struct kvm_assigned_dev_kernel {
 	struct pci_saved_state *pci_saved_state;
 };
 
-struct kvm_irq_mask_notifier {
-	void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked);
-	int irq;
-	struct hlist_node link;
-};
-
-void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
-				    struct kvm_irq_mask_notifier *kimn);
-void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
-				      struct kvm_irq_mask_notifier *kimn);
-void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
-			     bool mask);
-
 int kvm_irq_map_gsi(struct kvm *kvm,
 		    struct kvm_kernel_irq_routing_entry *entries, int gsi);
 int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin);
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index b0fb390943c..148b2392c76 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -36,9 +36,6 @@
 #include <linux/seqlock.h>
 #include <trace/events/kvm.h>
 
-#ifdef __KVM_HAVE_IOAPIC
-#include "ioapic.h"
-#endif
 #include "iodev.h"
 
 #ifdef CONFIG_HAVE_KVM_IRQFD
@@ -492,9 +489,7 @@ void kvm_register_irq_ack_notifier(struct kvm *kvm,
 	mutex_lock(&kvm->irq_lock);
 	hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
 	mutex_unlock(&kvm->irq_lock);
-#ifdef __KVM_HAVE_IOAPIC
 	kvm_vcpu_request_scan_ioapic(kvm);
-#endif
 }
 
 void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
@@ -504,9 +499,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 	hlist_del_init_rcu(&kian->link);
 	mutex_unlock(&kvm->irq_lock);
 	synchronize_srcu(&kvm->irq_srcu);
-#ifdef __KVM_HAVE_IOAPIC
 	kvm_vcpu_request_scan_ioapic(kvm);
-#endif
 }
 #endif
 
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
deleted file mode 100644
index f0f7ef82b7a..00000000000
--- a/virt/kvm/ioapic.c
+++ /dev/null
@@ -1,682 +0,0 @@
-/*
- *  Copyright (C) 2001  MandrakeSoft S.A.
- *  Copyright 2010 Red Hat, Inc. and/or its affiliates.
- *
- *    MandrakeSoft S.A.
- *    43, rue d'Aboukir
- *    75002 Paris - France
- *    http://www.linux-mandrake.com/
- *    http://www.mandrakesoft.com/
- *
- *  This library is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU Lesser General Public
- *  License as published by the Free Software Foundation; either
- *  version 2 of the License, or (at your option) any later version.
- *
- *  This library is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- *  Lesser General Public License for more details.
- *
- *  You should have received a copy of the GNU Lesser General Public
- *  License along with this library; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
- *  Yunhong Jiang <yunhong.jiang@intel.com>
- *  Yaozu (Eddie) Dong <eddie.dong@intel.com>
- *  Based on Xen 3.1 code.
- */
-
-#include <linux/kvm_host.h>
-#include <linux/kvm.h>
-#include <linux/mm.h>
-#include <linux/highmem.h>
-#include <linux/smp.h>
-#include <linux/hrtimer.h>
-#include <linux/io.h>
-#include <linux/slab.h>
-#include <linux/export.h>
-#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/current.h>
-#include <trace/events/kvm.h>
-
-#include "ioapic.h"
-#include "lapic.h"
-#include "irq.h"
-
-#if 0
-#define ioapic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg)
-#else
-#define ioapic_debug(fmt, arg...)
-#endif
-static int ioapic_service(struct kvm_ioapic *vioapic, int irq,
-		bool line_status);
-
-static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
-					  unsigned long addr,
-					  unsigned long length)
-{
-	unsigned long result = 0;
-
-	switch (ioapic->ioregsel) {
-	case IOAPIC_REG_VERSION:
-		result = ((((IOAPIC_NUM_PINS - 1) & 0xff) << 16)
-			  | (IOAPIC_VERSION_ID & 0xff));
-		break;
-
-	case IOAPIC_REG_APIC_ID:
-	case IOAPIC_REG_ARB_ID:
-		result = ((ioapic->id & 0xf) << 24);
-		break;
-
-	default:
-		{
-			u32 redir_index = (ioapic->ioregsel - 0x10) >> 1;
-			u64 redir_content;
-
-			if (redir_index < IOAPIC_NUM_PINS)
-				redir_content =
-					ioapic->redirtbl[redir_index].bits;
-			else
-				redir_content = ~0ULL;
-
-			result = (ioapic->ioregsel & 0x1) ?
-			    (redir_content >> 32) & 0xffffffff :
-			    redir_content & 0xffffffff;
-			break;
-		}
-	}
-
-	return result;
-}
-
-static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
-{
-	ioapic->rtc_status.pending_eoi = 0;
-	bitmap_zero(ioapic->rtc_status.dest_map, KVM_MAX_VCPUS);
-}
-
-static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
-
-static void rtc_status_pending_eoi_check_valid(struct kvm_ioapic *ioapic)
-{
-	if (WARN_ON(ioapic->rtc_status.pending_eoi < 0))
-		kvm_rtc_eoi_tracking_restore_all(ioapic);
-}
-
-static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
-{
-	bool new_val, old_val;
-	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
-	union kvm_ioapic_redirect_entry *e;
-
-	e = &ioapic->redirtbl[RTC_GSI];
-	if (!kvm_apic_match_dest(vcpu, NULL, 0,	e->fields.dest_id,
-				e->fields.dest_mode))
-		return;
-
-	new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
-	old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
-
-	if (new_val == old_val)
-		return;
-
-	if (new_val) {
-		__set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
-		ioapic->rtc_status.pending_eoi++;
-	} else {
-		__clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
-		ioapic->rtc_status.pending_eoi--;
-		rtc_status_pending_eoi_check_valid(ioapic);
-	}
-}
-
-void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
-{
-	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
-
-	spin_lock(&ioapic->lock);
-	__rtc_irq_eoi_tracking_restore_one(vcpu);
-	spin_unlock(&ioapic->lock);
-}
-
-static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic)
-{
-	struct kvm_vcpu *vcpu;
-	int i;
-
-	if (RTC_GSI >= IOAPIC_NUM_PINS)
-		return;
-
-	rtc_irq_eoi_tracking_reset(ioapic);
-	kvm_for_each_vcpu(i, vcpu, ioapic->kvm)
-	    __rtc_irq_eoi_tracking_restore_one(vcpu);
-}
-
-static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu)
-{
-	if (test_and_clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map)) {
-		--ioapic->rtc_status.pending_eoi;
-		rtc_status_pending_eoi_check_valid(ioapic);
-	}
-}
-
-static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic)
-{
-	if (ioapic->rtc_status.pending_eoi > 0)
-		return true; /* coalesced */
-
-	return false;
-}
-
-static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
-		int irq_level, bool line_status)
-{
-	union kvm_ioapic_redirect_entry entry;
-	u32 mask = 1 << irq;
-	u32 old_irr;
-	int edge, ret;
-
-	entry = ioapic->redirtbl[irq];
-	edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
-
-	if (!irq_level) {
-		ioapic->irr &= ~mask;
-		ret = 1;
-		goto out;
-	}
-
-	/*
-	 * Return 0 for coalesced interrupts; for edge-triggered interrupts,
-	 * this only happens if a previous edge has not been delivered due
-	 * do masking.  For level interrupts, the remote_irr field tells
-	 * us if the interrupt is waiting for an EOI.
-	 *
-	 * RTC is special: it is edge-triggered, but userspace likes to know
-	 * if it has been already ack-ed via EOI because coalesced RTC
-	 * interrupts lead to time drift in Windows guests.  So we track
-	 * EOI manually for the RTC interrupt.
-	 */
-	if (irq == RTC_GSI && line_status &&
-		rtc_irq_check_coalesced(ioapic)) {
-		ret = 0;
-		goto out;
-	}
-
-	old_irr = ioapic->irr;
-	ioapic->irr |= mask;
-	if ((edge && old_irr == ioapic->irr) ||
-	    (!edge && entry.fields.remote_irr)) {
-		ret = 0;
-		goto out;
-	}
-
-	ret = ioapic_service(ioapic, irq, line_status);
-
-out:
-	trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
-	return ret;
-}
-
-static void kvm_ioapic_inject_all(struct kvm_ioapic *ioapic, unsigned long irr)
-{
-	u32 idx;
-
-	rtc_irq_eoi_tracking_reset(ioapic);
-	for_each_set_bit(idx, &irr, IOAPIC_NUM_PINS)
-		ioapic_set_irq(ioapic, idx, 1, true);
-
-	kvm_rtc_eoi_tracking_restore_all(ioapic);
-}
-
-
-static void update_handled_vectors(struct kvm_ioapic *ioapic)
-{
-	DECLARE_BITMAP(handled_vectors, 256);
-	int i;
-
-	memset(handled_vectors, 0, sizeof(handled_vectors));
-	for (i = 0; i < IOAPIC_NUM_PINS; ++i)
-		__set_bit(ioapic->redirtbl[i].fields.vector, handled_vectors);
-	memcpy(ioapic->handled_vectors, handled_vectors,
-	       sizeof(handled_vectors));
-	smp_wmb();
-}
-
-void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
-			u32 *tmr)
-{
-	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
-	union kvm_ioapic_redirect_entry *e;
-	int index;
-
-	spin_lock(&ioapic->lock);
-	for (index = 0; index < IOAPIC_NUM_PINS; index++) {
-		e = &ioapic->redirtbl[index];
-		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
-		    kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) ||
-		    index == RTC_GSI) {
-			if (kvm_apic_match_dest(vcpu, NULL, 0,
-				e->fields.dest_id, e->fields.dest_mode)) {
-				__set_bit(e->fields.vector,
-					(unsigned long *)eoi_exit_bitmap);
-				if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG)
-					__set_bit(e->fields.vector,
-						(unsigned long *)tmr);
-			}
-		}
-	}
-	spin_unlock(&ioapic->lock);
-}
-
-#ifdef CONFIG_X86
-void kvm_vcpu_request_scan_ioapic(struct kvm *kvm)
-{
-	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
-
-	if (!ioapic)
-		return;
-	kvm_make_scan_ioapic_request(kvm);
-}
-#else
-void kvm_vcpu_request_scan_ioapic(struct kvm *kvm)
-{
-	return;
-}
-#endif
-
-static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
-{
-	unsigned index;
-	bool mask_before, mask_after;
-	union kvm_ioapic_redirect_entry *e;
-
-	switch (ioapic->ioregsel) {
-	case IOAPIC_REG_VERSION:
-		/* Writes are ignored. */
-		break;
-
-	case IOAPIC_REG_APIC_ID:
-		ioapic->id = (val >> 24) & 0xf;
-		break;
-
-	case IOAPIC_REG_ARB_ID:
-		break;
-
-	default:
-		index = (ioapic->ioregsel - 0x10) >> 1;
-
-		ioapic_debug("change redir index %x val %x\n", index, val);
-		if (index >= IOAPIC_NUM_PINS)
-			return;
-		e = &ioapic->redirtbl[index];
-		mask_before = e->fields.mask;
-		if (ioapic->ioregsel & 1) {
-			e->bits &= 0xffffffff;
-			e->bits |= (u64) val << 32;
-		} else {
-			e->bits &= ~0xffffffffULL;
-			e->bits |= (u32) val;
-			e->fields.remote_irr = 0;
-		}
-		update_handled_vectors(ioapic);
-		mask_after = e->fields.mask;
-		if (mask_before != mask_after)
-			kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
-		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
-		    && ioapic->irr & (1 << index))
-			ioapic_service(ioapic, index, false);
-		kvm_vcpu_request_scan_ioapic(ioapic->kvm);
-		break;
-	}
-}
-
-static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
-{
-	union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq];
-	struct kvm_lapic_irq irqe;
-	int ret;
-
-	if (entry->fields.mask)
-		return -1;
-
-	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
-		     "vector=%x trig_mode=%x\n",
-		     entry->fields.dest_id, entry->fields.dest_mode,
-		     entry->fields.delivery_mode, entry->fields.vector,
-		     entry->fields.trig_mode);
-
-	irqe.dest_id = entry->fields.dest_id;
-	irqe.vector = entry->fields.vector;
-	irqe.dest_mode = entry->fields.dest_mode;
-	irqe.trig_mode = entry->fields.trig_mode;
-	irqe.delivery_mode = entry->fields.delivery_mode << 8;
-	irqe.level = 1;
-	irqe.shorthand = 0;
-
-	if (irqe.trig_mode == IOAPIC_EDGE_TRIG)
-		ioapic->irr &= ~(1 << irq);
-
-	if (irq == RTC_GSI && line_status) {
-		/*
-		 * pending_eoi cannot ever become negative (see
-		 * rtc_status_pending_eoi_check_valid) and the caller
-		 * ensures that it is only called if it is >= zero, namely
-		 * if rtc_irq_check_coalesced returns false).
-		 */
-		BUG_ON(ioapic->rtc_status.pending_eoi != 0);
-		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
-				ioapic->rtc_status.dest_map);
-		ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret);
-	} else
-		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);
-
-	if (ret && irqe.trig_mode == IOAPIC_LEVEL_TRIG)
-		entry->fields.remote_irr = 1;
-
-	return ret;
-}
-
-int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
-		       int level, bool line_status)
-{
-	int ret, irq_level;
-
-	BUG_ON(irq < 0 || irq >= IOAPIC_NUM_PINS);
-
-	spin_lock(&ioapic->lock);
-	irq_level = __kvm_irq_line_state(&ioapic->irq_states[irq],
-					 irq_source_id, level);
-	ret = ioapic_set_irq(ioapic, irq, irq_level, line_status);
-
-	spin_unlock(&ioapic->lock);
-
-	return ret;
-}
-
-void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id)
-{
-	int i;
-
-	spin_lock(&ioapic->lock);
-	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++)
-		__clear_bit(irq_source_id, &ioapic->irq_states[i]);
-	spin_unlock(&ioapic->lock);
-}
-
-static void kvm_ioapic_eoi_inject_work(struct work_struct *work)
-{
-	int i;
-	struct kvm_ioapic *ioapic = container_of(work, struct kvm_ioapic,
-						 eoi_inject.work);
-	spin_lock(&ioapic->lock);
-	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
-		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
-
-		if (ent->fields.trig_mode != IOAPIC_LEVEL_TRIG)
-			continue;
-
-		if (ioapic->irr & (1 << i) && !ent->fields.remote_irr)
-			ioapic_service(ioapic, i, false);
-	}
-	spin_unlock(&ioapic->lock);
-}
-
-#define IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT 10000
-
-static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
-			struct kvm_ioapic *ioapic, int vector, int trigger_mode)
-{
-	int i;
-
-	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
-		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
-
-		if (ent->fields.vector != vector)
-			continue;
-
-		if (i == RTC_GSI)
-			rtc_irq_eoi(ioapic, vcpu);
-		/*
-		 * We are dropping lock while calling ack notifiers because ack
-		 * notifier callbacks for assigned devices call into IOAPIC
-		 * recursively. Since remote_irr is cleared only after call
-		 * to notifiers if the same vector will be delivered while lock
-		 * is dropped it will be put into irr and will be delivered
-		 * after ack notifier returns.
-		 */
-		spin_unlock(&ioapic->lock);
-		kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
-		spin_lock(&ioapic->lock);
-
-		if (trigger_mode != IOAPIC_LEVEL_TRIG)
-			continue;
-
-		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
-		ent->fields.remote_irr = 0;
-		if (!ent->fields.mask && (ioapic->irr & (1 << i))) {
-			++ioapic->irq_eoi[i];
-			if (ioapic->irq_eoi[i] == IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT) {
-				/*
-				 * Real hardware does not deliver the interrupt
-				 * immediately during eoi broadcast, and this
-				 * lets a buggy guest make slow progress
-				 * even if it does not correctly handle a
-				 * level-triggered interrupt.  Emulate this
-				 * behavior if we detect an interrupt storm.
-				 */
-				schedule_delayed_work(&ioapic->eoi_inject, HZ / 100);
-				ioapic->irq_eoi[i] = 0;
-				trace_kvm_ioapic_delayed_eoi_inj(ent->bits);
-			} else {
-				ioapic_service(ioapic, i, false);
-			}
-		} else {
-			ioapic->irq_eoi[i] = 0;
-		}
-	}
-}
-
-bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector)
-{
-	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
-	smp_rmb();
-	return test_bit(vector, ioapic->handled_vectors);
-}
-
-void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode)
-{
-	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
-
-	spin_lock(&ioapic->lock);
-	__kvm_ioapic_update_eoi(vcpu, ioapic, vector, trigger_mode);
-	spin_unlock(&ioapic->lock);
-}
-
-static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev)
-{
-	return container_of(dev, struct kvm_ioapic, dev);
-}
-
-static inline int ioapic_in_range(struct kvm_ioapic *ioapic, gpa_t addr)
-{
-	return ((addr >= ioapic->base_address &&
-		 (addr < ioapic->base_address + IOAPIC_MEM_LENGTH)));
-}
-
-static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
-			    void *val)
-{
-	struct kvm_ioapic *ioapic = to_ioapic(this);
-	u32 result;
-	if (!ioapic_in_range(ioapic, addr))
-		return -EOPNOTSUPP;
-
-	ioapic_debug("addr %lx\n", (unsigned long)addr);
-	ASSERT(!(addr & 0xf));	/* check alignment */
-
-	addr &= 0xff;
-	spin_lock(&ioapic->lock);
-	switch (addr) {
-	case IOAPIC_REG_SELECT:
-		result = ioapic->ioregsel;
-		break;
-
-	case IOAPIC_REG_WINDOW:
-		result = ioapic_read_indirect(ioapic, addr, len);
-		break;
-
-	default:
-		result = 0;
-		break;
-	}
-	spin_unlock(&ioapic->lock);
-
-	switch (len) {
-	case 8:
-		*(u64 *) val = result;
-		break;
-	case 1:
-	case 2:
-	case 4:
-		memcpy(val, (char *)&result, len);
-		break;
-	default:
-		printk(KERN_WARNING "ioapic: wrong length %d\n", len);
-	}
-	return 0;
-}
-
-static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
-			     const void *val)
-{
-	struct kvm_ioapic *ioapic = to_ioapic(this);
-	u32 data;
-	if (!ioapic_in_range(ioapic, addr))
-		return -EOPNOTSUPP;
-
-	ioapic_debug("ioapic_mmio_write addr=%p len=%d val=%p\n",
-		     (void*)addr, len, val);
-	ASSERT(!(addr & 0xf));	/* check alignment */
-
-	switch (len) {
-	case 8:
-	case 4:
-		data = *(u32 *) val;
-		break;
-	case 2:
-		data = *(u16 *) val;
-		break;
-	case 1:
-		data = *(u8  *) val;
-		break;
-	default:
-		printk(KERN_WARNING "ioapic: Unsupported size %d\n", len);
-		return 0;
-	}
-
-	addr &= 0xff;
-	spin_lock(&ioapic->lock);
-	switch (addr) {
-	case IOAPIC_REG_SELECT:
-		ioapic->ioregsel = data & 0xFF; /* 8-bit register */
-		break;
-
-	case IOAPIC_REG_WINDOW:
-		ioapic_write_indirect(ioapic, data);
-		break;
-
-	default:
-		break;
-	}
-	spin_unlock(&ioapic->lock);
-	return 0;
-}
-
-static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
-{
-	int i;
-
-	cancel_delayed_work_sync(&ioapic->eoi_inject);
-	for (i = 0; i < IOAPIC_NUM_PINS; i++)
-		ioapic->redirtbl[i].fields.mask = 1;
-	ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS;
-	ioapic->ioregsel = 0;
-	ioapic->irr = 0;
-	ioapic->id = 0;
-	memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS);
-	rtc_irq_eoi_tracking_reset(ioapic);
-	update_handled_vectors(ioapic);
-}
-
-static const struct kvm_io_device_ops ioapic_mmio_ops = {
-	.read     = ioapic_mmio_read,
-	.write    = ioapic_mmio_write,
-};
-
-int kvm_ioapic_init(struct kvm *kvm)
-{
-	struct kvm_ioapic *ioapic;
-	int ret;
-
-	ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL);
-	if (!ioapic)
-		return -ENOMEM;
-	spin_lock_init(&ioapic->lock);
-	INIT_DELAYED_WORK(&ioapic->eoi_inject, kvm_ioapic_eoi_inject_work);
-	kvm->arch.vioapic = ioapic;
-	kvm_ioapic_reset(ioapic);
-	kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
-	ioapic->kvm = kvm;
-	mutex_lock(&kvm->slots_lock);
-	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, ioapic->base_address,
-				      IOAPIC_MEM_LENGTH, &ioapic->dev);
-	mutex_unlock(&kvm->slots_lock);
-	if (ret < 0) {
-		kvm->arch.vioapic = NULL;
-		kfree(ioapic);
-	}
-
-	return ret;
-}
-
-void kvm_ioapic_destroy(struct kvm *kvm)
-{
-	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
-
-	cancel_delayed_work_sync(&ioapic->eoi_inject);
-	if (ioapic) {
-		kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
-		kvm->arch.vioapic = NULL;
-		kfree(ioapic);
-	}
-}
-
-int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
-{
-	struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
-	if (!ioapic)
-		return -EINVAL;
-
-	spin_lock(&ioapic->lock);
-	memcpy(state, ioapic, sizeof(struct kvm_ioapic_state));
-	spin_unlock(&ioapic->lock);
-	return 0;
-}
-
-int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
-{
-	struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
-	if (!ioapic)
-		return -EINVAL;
-
-	spin_lock(&ioapic->lock);
-	memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
-	ioapic->irr = 0;
-	update_handled_vectors(ioapic);
-	kvm_vcpu_request_scan_ioapic(kvm);
-	kvm_ioapic_inject_all(ioapic, state->irr);
-	spin_unlock(&ioapic->lock);
-	return 0;
-}
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
deleted file mode 100644
index dc3baa3a538..00000000000
--- a/virt/kvm/ioapic.h
+++ /dev/null
@@ -1,103 +0,0 @@
-#ifndef __KVM_IO_APIC_H
-#define __KVM_IO_APIC_H
-
-#include <linux/kvm_host.h>
-
-#include "iodev.h"
-
-struct kvm;
-struct kvm_vcpu;
-
-#define IOAPIC_NUM_PINS  KVM_IOAPIC_NUM_PINS
-#define IOAPIC_VERSION_ID 0x11	/* IOAPIC version */
-#define IOAPIC_EDGE_TRIG  0
-#define IOAPIC_LEVEL_TRIG 1
-
-#define IOAPIC_DEFAULT_BASE_ADDRESS  0xfec00000
-#define IOAPIC_MEM_LENGTH            0x100
-
-/* Direct registers. */
-#define IOAPIC_REG_SELECT  0x00
-#define IOAPIC_REG_WINDOW  0x10
-
-/* Indirect registers. */
-#define IOAPIC_REG_APIC_ID 0x00	/* x86 IOAPIC only */
-#define IOAPIC_REG_VERSION 0x01
-#define IOAPIC_REG_ARB_ID  0x02	/* x86 IOAPIC only */
-
-/*ioapic delivery mode*/
-#define	IOAPIC_FIXED			0x0
-#define	IOAPIC_LOWEST_PRIORITY		0x1
-#define	IOAPIC_PMI			0x2
-#define	IOAPIC_NMI			0x4
-#define	IOAPIC_INIT			0x5
-#define	IOAPIC_EXTINT			0x7
-
-#ifdef CONFIG_X86
-#define RTC_GSI 8
-#else
-#define RTC_GSI -1U
-#endif
-
-struct rtc_status {
-	int pending_eoi;
-	DECLARE_BITMAP(dest_map, KVM_MAX_VCPUS);
-};
-
-struct kvm_ioapic {
-	u64 base_address;
-	u32 ioregsel;
-	u32 id;
-	u32 irr;
-	u32 pad;
-	union kvm_ioapic_redirect_entry redirtbl[IOAPIC_NUM_PINS];
-	unsigned long irq_states[IOAPIC_NUM_PINS];
-	struct kvm_io_device dev;
-	struct kvm *kvm;
-	void (*ack_notifier)(void *opaque, int irq);
-	spinlock_t lock;
-	DECLARE_BITMAP(handled_vectors, 256);
-	struct rtc_status rtc_status;
-	struct delayed_work eoi_inject;
-	u32 irq_eoi[IOAPIC_NUM_PINS];
-};
-
-#ifdef DEBUG
-#define ASSERT(x)  							\
-do {									\
-	if (!(x)) {							\
-		printk(KERN_EMERG "assertion failed %s: %d: %s\n",	\
-		       __FILE__, __LINE__, #x);				\
-		BUG();							\
-	}								\
-} while (0)
-#else
-#define ASSERT(x) do { } while (0)
-#endif
-
-static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm)
-{
-	return kvm->arch.vioapic;
-}
-
-void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu);
-int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
-		int short_hand, unsigned int dest, int dest_mode);
-int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
-void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector,
-			int trigger_mode);
-bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector);
-int kvm_ioapic_init(struct kvm *kvm);
-void kvm_ioapic_destroy(struct kvm *kvm);
-int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
-		       int level, bool line_status);
-void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id);
-int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
-		struct kvm_lapic_irq *irq, unsigned long *dest_map);
-int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
-int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
-void kvm_vcpu_request_scan_ioapic(struct kvm *kvm);
-void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
-			u32 *tmr);
-
-#endif
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
deleted file mode 100644
index 1345bde064f..00000000000
--- a/virt/kvm/irq_comm.c
+++ /dev/null
@@ -1,347 +0,0 @@
-/*
- * irq_comm.c: Common API for in kernel interrupt controller
- * Copyright (c) 2007, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
- * Authors:
- *   Yaozu (Eddie) Dong <Eddie.dong@intel.com>
- *
- * Copyright 2010 Red Hat, Inc. and/or its affiliates.
- */
-
-#include <linux/kvm_host.h>
-#include <linux/slab.h>
-#include <linux/export.h>
-#include <trace/events/kvm.h>
-
-#include <asm/msidef.h>
-
-#include "irq.h"
-
-#include "ioapic.h"
-
-static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
-			   struct kvm *kvm, int irq_source_id, int level,
-			   bool line_status)
-{
-#ifdef CONFIG_X86
-	struct kvm_pic *pic = pic_irqchip(kvm);
-	return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
-#else
-	return -1;
-#endif
-}
-
-static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
-			      struct kvm *kvm, int irq_source_id, int level,
-			      bool line_status)
-{
-	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
-	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level,
-				line_status);
-}
-
-inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
-{
-	return irq->delivery_mode == APIC_DM_LOWEST;
-}
-
-int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
-		struct kvm_lapic_irq *irq, unsigned long *dest_map)
-{
-	int i, r = -1;
-	struct kvm_vcpu *vcpu, *lowest = NULL;
-
-	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
-			kvm_is_dm_lowest_prio(irq)) {
-		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
-		irq->delivery_mode = APIC_DM_FIXED;
-	}
-
-	if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
-		return r;
-
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (!kvm_apic_present(vcpu))
-			continue;
-
-		if (!kvm_apic_match_dest(vcpu, src, irq->shorthand,
-					irq->dest_id, irq->dest_mode))
-			continue;
-
-		if (!kvm_is_dm_lowest_prio(irq)) {
-			if (r < 0)
-				r = 0;
-			r += kvm_apic_set_irq(vcpu, irq, dest_map);
-		} else if (kvm_lapic_enabled(vcpu)) {
-			if (!lowest)
-				lowest = vcpu;
-			else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
-				lowest = vcpu;
-		}
-	}
-
-	if (lowest)
-		r = kvm_apic_set_irq(lowest, irq, dest_map);
-
-	return r;
-}
-
-static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
-				   struct kvm_lapic_irq *irq)
-{
-	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
-
-	irq->dest_id = (e->msi.address_lo &
-			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
-	irq->vector = (e->msi.data &
-			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
-	irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
-	irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
-	irq->delivery_mode = e->msi.data & 0x700;
-	irq->level = 1;
-	irq->shorthand = 0;
-	/* TODO Deal with RH bit of MSI message address */
-}
-
-int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
-		struct kvm *kvm, int irq_source_id, int level, bool line_status)
-{
-	struct kvm_lapic_irq irq;
-
-	if (!level)
-		return -1;
-
-	kvm_set_msi_irq(e, &irq);
-
-	return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
-}
-
-
-static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
-			 struct kvm *kvm)
-{
-	struct kvm_lapic_irq irq;
-	int r;
-
-	kvm_set_msi_irq(e, &irq);
-
-	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
-		return r;
-	else
-		return -EWOULDBLOCK;
-}
-
-/*
- * Deliver an IRQ in an atomic context if we can, or return a failure,
- * user can retry in a process context.
- * Return value:
- *  -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context.
- *  Other values - No need to retry.
- */
-int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
-{
-	struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
-	struct kvm_kernel_irq_routing_entry *e;
-	int ret = -EINVAL;
-	int idx;
-
-	trace_kvm_set_irq(irq, level, irq_source_id);
-
-	/*
-	 * Injection into either PIC or IOAPIC might need to scan all CPUs,
-	 * which would need to be retried from thread context;  when same GSI
-	 * is connected to both PIC and IOAPIC, we'd have to report a
-	 * partial failure here.
-	 * Since there's no easy way to do this, we only support injecting MSI
-	 * which is limited to 1:1 GSI mapping.
-	 */
-	idx = srcu_read_lock(&kvm->irq_srcu);
-	if (kvm_irq_map_gsi(kvm, entries, irq) > 0) {
-		e = &entries[0];
-		if (likely(e->type == KVM_IRQ_ROUTING_MSI))
-			ret = kvm_set_msi_inatomic(e, kvm);
-		else
-			ret = -EWOULDBLOCK;
-	}
-	srcu_read_unlock(&kvm->irq_srcu, idx);
-	return ret;
-}
-
-int kvm_request_irq_source_id(struct kvm *kvm)
-{
-	unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
-	int irq_source_id;
-
-	mutex_lock(&kvm->irq_lock);
-	irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG);
-
-	if (irq_source_id >= BITS_PER_LONG) {
-		printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n");
-		irq_source_id = -EFAULT;
-		goto unlock;
-	}
-
-	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
-#ifdef CONFIG_X86
-	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
-#endif
-	set_bit(irq_source_id, bitmap);
-unlock:
-	mutex_unlock(&kvm->irq_lock);
-
-	return irq_source_id;
-}
-
-void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
-{
-	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
-#ifdef CONFIG_X86
-	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
-#endif
-
-	mutex_lock(&kvm->irq_lock);
-	if (irq_source_id < 0 ||
-	    irq_source_id >= BITS_PER_LONG) {
-		printk(KERN_ERR "kvm: IRQ source ID out of range!\n");
-		goto unlock;
-	}
-	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
-	if (!irqchip_in_kernel(kvm))
-		goto unlock;
-
-	kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
-#ifdef CONFIG_X86
-	kvm_pic_clear_all(pic_irqchip(kvm), irq_source_id);
-#endif
-unlock:
-	mutex_unlock(&kvm->irq_lock);
-}
-
-void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
-				    struct kvm_irq_mask_notifier *kimn)
-{
-	mutex_lock(&kvm->irq_lock);
-	kimn->irq = irq;
-	hlist_add_head_rcu(&kimn->link, &kvm->mask_notifier_list);
-	mutex_unlock(&kvm->irq_lock);
-}
-
-void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
-				      struct kvm_irq_mask_notifier *kimn)
-{
-	mutex_lock(&kvm->irq_lock);
-	hlist_del_rcu(&kimn->link);
-	mutex_unlock(&kvm->irq_lock);
-	synchronize_srcu(&kvm->irq_srcu);
-}
-
-void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
-			     bool mask)
-{
-	struct kvm_irq_mask_notifier *kimn;
-	int idx, gsi;
-
-	idx = srcu_read_lock(&kvm->irq_srcu);
-	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
-	if (gsi != -1)
-		hlist_for_each_entry_rcu(kimn, &kvm->mask_notifier_list, link)
-			if (kimn->irq == gsi)
-				kimn->func(kimn, mask);
-	srcu_read_unlock(&kvm->irq_srcu, idx);
-}
-
-int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
-			  const struct kvm_irq_routing_entry *ue)
-{
-	int r = -EINVAL;
-	int delta;
-	unsigned max_pin;
-
-	switch (ue->type) {
-	case KVM_IRQ_ROUTING_IRQCHIP:
-		delta = 0;
-		switch (ue->u.irqchip.irqchip) {
-		case KVM_IRQCHIP_PIC_MASTER:
-			e->set = kvm_set_pic_irq;
-			max_pin = PIC_NUM_PINS;
-			break;
-		case KVM_IRQCHIP_PIC_SLAVE:
-			e->set = kvm_set_pic_irq;
-			max_pin = PIC_NUM_PINS;
-			delta = 8;
-			break;
-		case KVM_IRQCHIP_IOAPIC:
-			max_pin = KVM_IOAPIC_NUM_PINS;
-			e->set = kvm_set_ioapic_irq;
-			break;
-		default:
-			goto out;
-		}
-		e->irqchip.irqchip = ue->u.irqchip.irqchip;
-		e->irqchip.pin = ue->u.irqchip.pin + delta;
-		if (e->irqchip.pin >= max_pin)
-			goto out;
-		break;
-	case KVM_IRQ_ROUTING_MSI:
-		e->set = kvm_set_msi;
-		e->msi.address_lo = ue->u.msi.address_lo;
-		e->msi.address_hi = ue->u.msi.address_hi;
-		e->msi.data = ue->u.msi.data;
-		break;
-	default:
-		goto out;
-	}
-
-	r = 0;
-out:
-	return r;
-}
-
-#define IOAPIC_ROUTING_ENTRY(irq) \
-	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
-	  .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } }
-#define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq)
-
-#ifdef CONFIG_X86
-#  define PIC_ROUTING_ENTRY(irq) \
-	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
-	  .u.irqchip = { .irqchip = SELECT_PIC(irq), .pin = (irq) % 8 } }
-#  define ROUTING_ENTRY2(irq) \
-	IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq)
-#else
-#  define ROUTING_ENTRY2(irq) \
-	IOAPIC_ROUTING_ENTRY(irq)
-#endif
-
-static const struct kvm_irq_routing_entry default_routing[] = {
-	ROUTING_ENTRY2(0), ROUTING_ENTRY2(1),
-	ROUTING_ENTRY2(2), ROUTING_ENTRY2(3),
-	ROUTING_ENTRY2(4), ROUTING_ENTRY2(5),
-	ROUTING_ENTRY2(6), ROUTING_ENTRY2(7),
-	ROUTING_ENTRY2(8), ROUTING_ENTRY2(9),
-	ROUTING_ENTRY2(10), ROUTING_ENTRY2(11),
-	ROUTING_ENTRY2(12), ROUTING_ENTRY2(13),
-	ROUTING_ENTRY2(14), ROUTING_ENTRY2(15),
-	ROUTING_ENTRY1(16), ROUTING_ENTRY1(17),
-	ROUTING_ENTRY1(18), ROUTING_ENTRY1(19),
-	ROUTING_ENTRY1(20), ROUTING_ENTRY1(21),
-	ROUTING_ENTRY1(22), ROUTING_ENTRY1(23),
-};
-
-int kvm_setup_default_irq_routing(struct kvm *kvm)
-{
-	return kvm_set_irq_routing(kvm, default_routing,
-				   ARRAY_SIZE(default_routing), 0);
-}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 751ece6a595..3be43424818 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -468,9 +468,6 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	if (r)
 		goto out_err_no_disable;
 
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
-	INIT_HLIST_HEAD(&kvm->mask_notifier_list);
-#endif
 #ifdef CONFIG_HAVE_KVM_IRQFD
 	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
 #endif
-- 
cgit v1.2.3-70-g09d2


From 6b397158d07f885154b871a15f879d25b3de7579 Mon Sep 17 00:00:00 2001
From: Radim Krčmář <rkrcmar@redhat.com>
Date: Thu, 20 Nov 2014 14:43:18 +0100
Subject: kvm: remove IA64 ioctls
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

KVM ia64 is no longer present so new applications shouldn't use them.
The main problem is that they most likely didn't work even before,
because of a conflict in the #defines:

  #define KVM_SET_GUEST_DEBUG       _IOW(KVMIO,  0x9b, struct kvm_guest_debug)
  #define KVM_IA64_VCPU_SET_STACK   _IOW(KVMIO,  0x9b, void *)

The argument to KVM_SET_GUEST_DEBUG is:

  struct kvm_guest_debug {
  	__u32 control;
  	__u32 pad;
  	struct kvm_guest_debug_arch arch;
  };

  struct kvm_guest_debug_arch {
  };

meaning that sizeof(struct kvm_guest_debug) == sizeof(void *) == 8
and KVM_SET_GUEST_DEBUG == KVM_IA64_VCPU_SET_STACK.

KVM_SET_GUEST_DEBUG is handled in virt/kvm/kvm_main.c before even calling
kvm_arch_vcpu_ioctl (which would have handled KVM_IA64_VCPU_SET_STACK),
so KVM_IA64_VCPU_SET_STACK would just return -EINVAL.

Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/uapi/linux/kvm.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 6d59e5b39c9..a37fd1224f3 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1099,9 +1099,6 @@ struct kvm_s390_ucas_mapping {
 #define KVM_X86_SETUP_MCE         _IOW(KVMIO,  0x9c, __u64)
 #define KVM_X86_GET_MCE_CAP_SUPPORTED _IOR(KVMIO,  0x9d, __u64)
 #define KVM_X86_SET_MCE           _IOW(KVMIO,  0x9e, struct kvm_x86_mce)
-/* IA64 stack access */
-#define KVM_IA64_VCPU_GET_STACK   _IOR(KVMIO,  0x9a, void *)
-#define KVM_IA64_VCPU_SET_STACK   _IOW(KVMIO,  0x9b, void *)
 /* Available with KVM_CAP_VCPU_EVENTS */
 #define KVM_GET_VCPU_EVENTS       _IOR(KVMIO,  0x9f, struct kvm_vcpu_events)
 #define KVM_SET_VCPU_EVENTS       _IOW(KVMIO,  0xa0, struct kvm_vcpu_events)
-- 
cgit v1.2.3-70-g09d2


From 860f6e9eb780443381a76e3766a9698afbc5e2e5 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 19 Nov 2014 12:59:14 +0100
Subject: net: phy: add static data field to struct phy_driver

Add static driver-data field to struct phy_driver, which can be used to
store structured device-type information.

Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phy.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 07794e72013..22af8f8f580 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -433,6 +433,7 @@ struct phy_device {
  *   by this PHY
  * flags: A bitfield defining certain other features this PHY
  *   supports (like interrupts)
+ * driver_data: static driver data
  *
  * The drivers must implement config_aneg and read_status.  All
  * other functions are optional. Note that none of these
@@ -448,6 +449,7 @@ struct phy_driver {
 	unsigned int phy_id_mask;
 	u32 features;
 	u32 flags;
+	const void *driver_data;
 
 	/*
 	 * Called to issue a PHY software reset
-- 
cgit v1.2.3-70-g09d2


From 63f44b2bfccdd98193bbd602747f780c0fae0f02 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 19 Nov 2014 12:59:18 +0100
Subject: net: phy: micrel: add generic clock-mode-select support

Add generic RMII-Reference-Clock-Select support.

Several Micrel PHY have an RMII-Reference-Clock-Select bit to select
25 MHz or 50 MHz clock mode. Recently, support for configuring this
through device tree for KSZ8021 and KSZ8031 was added.

Generalise this support so that it can be configured for other PHY types
as well.

Note that some PHY revisions (of the same type) has this bit inverted.
This should be either configurable through a new device-tree property,
or preferably, determined based on PHY ID if possible.

Also note that this removes support for setting 25 MHz mode from board
files which was also added by the above mentioned commit 45f56cb82e45
("net/phy: micrel: Add clock support for KSZ8021/KSZ8031").

Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c   | 93 +++++++++++++++++++++++++---------------------
 include/linux/micrel_phy.h |  1 -
 2 files changed, 50 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index a0e94409902..d2e790cd365 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -57,7 +57,7 @@
 #define KSZPHY_CTRL_INT_ACTIVE_HIGH		BIT(9)
 #define KSZ9021_CTRL_INT_ACTIVE_HIGH		BIT(14)
 #define KS8737_CTRL_INT_ACTIVE_HIGH		BIT(14)
-#define KSZ8051_RMII_50MHZ_CLK			BIT(7)
+#define KSZPHY_RMII_REF_CLK_SEL			BIT(7)
 
 /* Write/read to/from extended registers */
 #define MII_KSZPHY_EXTREG                       0x0b
@@ -76,15 +76,19 @@
 struct kszphy_type {
 	u32 led_mode_reg;
 	bool has_broadcast_disable;
+	bool has_rmii_ref_clk_sel;
 };
 
 struct kszphy_priv {
 	const struct kszphy_type *type;
 	int led_mode;
+	bool rmii_ref_clk_sel;
+	bool rmii_ref_clk_sel_val;
 };
 
 static const struct kszphy_type ksz8021_type = {
 	.led_mode_reg		= MII_KSZPHY_CTRL_2,
+	.has_rmii_ref_clk_sel	= true,
 };
 
 static const struct kszphy_type ksz8041_type = {
@@ -100,21 +104,6 @@ static const struct kszphy_type ksz8081_type = {
 	.has_broadcast_disable	= true,
 };
 
-static int ksz_config_flags(struct phy_device *phydev)
-{
-	int regval;
-
-	if (phydev->dev_flags & (MICREL_PHY_50MHZ_CLK | MICREL_PHY_25MHZ_CLK)) {
-		regval = phy_read(phydev, MII_KSZPHY_CTRL);
-		if (phydev->dev_flags & MICREL_PHY_50MHZ_CLK)
-			regval |= KSZ8051_RMII_50MHZ_CLK;
-		else
-			regval &= ~KSZ8051_RMII_50MHZ_CLK;
-		return phy_write(phydev, MII_KSZPHY_CTRL, regval);
-	}
-	return 0;
-}
-
 static int kszphy_extended_write(struct phy_device *phydev,
 				u32 regnum, u16 val)
 {
@@ -189,6 +178,22 @@ static int ks8737_config_intr(struct phy_device *phydev)
 	return rc < 0 ? rc : 0;
 }
 
+static int kszphy_rmii_clk_sel(struct phy_device *phydev, bool val)
+{
+	int ctrl;
+
+	ctrl = phy_read(phydev, MII_KSZPHY_CTRL);
+	if (ctrl < 0)
+		return ctrl;
+
+	if (val)
+		ctrl |= KSZPHY_RMII_REF_CLK_SEL;
+	else
+		ctrl &= ~KSZPHY_RMII_REF_CLK_SEL;
+
+	return phy_write(phydev, MII_KSZPHY_CTRL, ctrl);
+}
+
 static int kszphy_setup_led(struct phy_device *phydev, u32 reg, int val)
 {
 	int rc, temp, shift;
@@ -243,6 +248,7 @@ static int kszphy_config_init(struct phy_device *phydev)
 {
 	struct kszphy_priv *priv = phydev->priv;
 	const struct kszphy_type *type;
+	int ret;
 
 	if (!priv)
 		return 0;
@@ -252,6 +258,14 @@ static int kszphy_config_init(struct phy_device *phydev)
 	if (type->has_broadcast_disable)
 		kszphy_broadcast_disable(phydev);
 
+	if (priv->rmii_ref_clk_sel) {
+		ret = kszphy_rmii_clk_sel(phydev, priv->rmii_ref_clk_sel_val);
+		if (ret) {
+			dev_err(&phydev->dev, "failed to set rmii reference clock\n");
+			return ret;
+		}
+	}
+
 	if (priv->led_mode >= 0)
 		kszphy_setup_led(phydev, type->led_mode_reg, priv->led_mode);
 
@@ -262,10 +276,8 @@ static int ksz8021_config_init(struct phy_device *phydev)
 {
 	int rc;
 
-	kszphy_config_init(phydev);
-
-	rc = ksz_config_flags(phydev);
-	if (rc < 0)
+	rc = kszphy_config_init(phydev);
+	if (rc)
 		return rc;
 
 	rc = kszphy_broadcast_disable(phydev);
@@ -273,16 +285,6 @@ static int ksz8021_config_init(struct phy_device *phydev)
 	return rc < 0 ? rc : 0;
 }
 
-static int ks8051_config_init(struct phy_device *phydev)
-{
-	int rc;
-
-	kszphy_config_init(phydev);
-
-	rc = ksz_config_flags(phydev);
-	return rc < 0 ? rc : 0;
-}
-
 static int ksz9021_load_values_from_of(struct phy_device *phydev,
 				       struct device_node *of_node, u16 reg,
 				       char *field1, char *field2,
@@ -517,6 +519,7 @@ static int kszphy_probe(struct phy_device *phydev)
 	const struct kszphy_type *type = phydev->drv->driver_data;
 	struct device_node *np = phydev->dev.of_node;
 	struct kszphy_priv *priv;
+	struct clk *clk;
 	int ret;
 
 	priv = devm_kzalloc(&phydev->dev, sizeof(*priv), GFP_KERNEL);
@@ -542,28 +545,32 @@ static int kszphy_probe(struct phy_device *phydev)
 		priv->led_mode = -1;
 	}
 
-	return 0;
-}
-
-static int ksz8021_probe(struct phy_device *phydev)
-{
-	struct clk *clk;
-
 	clk = devm_clk_get(&phydev->dev, "rmii-ref");
 	if (!IS_ERR(clk)) {
 		unsigned long rate = clk_get_rate(clk);
 
+		priv->rmii_ref_clk_sel = type->has_rmii_ref_clk_sel;
+
+		/* FIXME: add support for PHY revisions that have this bit
+		 * inverted (e.g. through new property or based on PHY ID).
+		 */
 		if (rate > 24500000 && rate < 25500000) {
-			phydev->dev_flags |= MICREL_PHY_25MHZ_CLK;
+			priv->rmii_ref_clk_sel_val = false;
 		} else if (rate > 49500000 && rate < 50500000) {
-			phydev->dev_flags |= MICREL_PHY_50MHZ_CLK;
+			priv->rmii_ref_clk_sel_val = true;
 		} else {
 			dev_err(&phydev->dev, "Clock rate out of range: %ld\n", rate);
 			return -EINVAL;
 		}
 	}
 
-	return kszphy_probe(phydev);
+	/* Support legacy board-file configuration */
+	if (phydev->dev_flags & MICREL_PHY_50MHZ_CLK) {
+		priv->rmii_ref_clk_sel = true;
+		priv->rmii_ref_clk_sel_val = true;
+	}
+
+	return 0;
 }
 
 static struct phy_driver ksphy_driver[] = {
@@ -589,7 +596,7 @@ static struct phy_driver ksphy_driver[] = {
 			   SUPPORTED_Asym_Pause),
 	.flags		= PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz8021_type,
-	.probe		= ksz8021_probe,
+	.probe		= kszphy_probe,
 	.config_init	= ksz8021_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
@@ -606,7 +613,7 @@ static struct phy_driver ksphy_driver[] = {
 			   SUPPORTED_Asym_Pause),
 	.flags		= PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz8021_type,
-	.probe		= ksz8021_probe,
+	.probe		= kszphy_probe,
 	.config_init	= ksz8021_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
@@ -658,7 +665,7 @@ static struct phy_driver ksphy_driver[] = {
 	.flags		= PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
 	.driver_data	= &ksz8051_type,
 	.probe		= kszphy_probe,
-	.config_init	= ks8051_config_init,
+	.config_init	= kszphy_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= kszphy_ack_interrupt,
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 53d33dee70e..2e5b194b9b1 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -37,7 +37,6 @@
 
 /* struct phy_device dev_flags definitions */
 #define MICREL_PHY_50MHZ_CLK	0x00000001
-#define MICREL_PHY_25MHZ_CLK	0x00000002
 
 #define MICREL_KSZ9021_EXTREG_CTRL	0xB
 #define MICREL_KSZ9021_EXTREG_DATA_WRITE	0xC
-- 
cgit v1.2.3-70-g09d2


From b960a0ac6939ef4962c5abbf33e80d1382b45fc1 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Wed, 19 Nov 2014 14:04:56 +0100
Subject: vlan: make __vlan_hwaccel_put_tag return void

Always returns the same skb it gets, so change to void.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/scsi/fcoe/fcoe.c | 6 ++----
 include/linux/if_vlan.h  | 9 ++++-----
 net/8021q/vlan_dev.c     | 2 +-
 3 files changed, 7 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 4a8ac7d8c76..73a8cc485f8 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -1669,10 +1669,8 @@ static int fcoe_xmit(struct fc_lport *lport, struct fc_frame *fp)
 	    fcoe->realdev->features & NETIF_F_HW_VLAN_CTAG_TX) {
 		/* must set skb->dev before calling vlan_put_tag */
 		skb->dev = fcoe->realdev;
-		skb = __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
-					     vlan_dev_vlan_id(fcoe->netdev));
-		if (!skb)
-			return -ENOMEM;
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+				       vlan_dev_vlan_id(fcoe->netdev));
 	} else
 		skb->dev = fcoe->netdev;
 
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index d69f0577a31..1b5dbc2711f 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -347,13 +347,11 @@ static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb,
  *
  * Puts the VLAN TCI in @skb->vlan_tci and lets the device do the rest
  */
-static inline struct sk_buff *__vlan_hwaccel_put_tag(struct sk_buff *skb,
-						     __be16 vlan_proto,
-						     u16 vlan_tci)
+static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb,
+					  __be16 vlan_proto, u16 vlan_tci)
 {
 	skb->vlan_proto = vlan_proto;
 	skb->vlan_tci = VLAN_TAG_PRESENT | vlan_tci;
-	return skb;
 }
 
 /**
@@ -368,7 +366,8 @@ static inline struct sk_buff *vlan_put_tag(struct sk_buff *skb,
 					   __be16 vlan_proto, u16 vlan_tci)
 {
 	if (vlan_hw_offload_capable(skb->dev->features, vlan_proto)) {
-		return __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
+		__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
+		return skb;
 	} else {
 		return __vlan_put_tag(skb, vlan_proto, vlan_tci);
 	}
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 0d441ec8763..d6524b2b206 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -150,7 +150,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
 		u16 vlan_tci;
 		vlan_tci = vlan->vlan_id;
 		vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority);
-		skb = __vlan_hwaccel_put_tag(skb, vlan->vlan_proto, vlan_tci);
+		__vlan_hwaccel_put_tag(skb, vlan->vlan_proto, vlan_tci);
 	}
 
 	skb->dev = vlan->real_dev;
-- 
cgit v1.2.3-70-g09d2


From b4bef1b57544b18899eb15569e3bafd8d2eeeff6 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Wed, 19 Nov 2014 14:04:57 +0100
Subject: vlan: kill vlan_put_tag helper

Since both tx and rx paths work with skb->vlan_tci, there's no need for
this function anymore. Switch users directly to __vlan_hwaccel_put_tag.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_alb.c  | 17 ++++-------------
 drivers/net/bonding/bond_main.c |  8 ++------
 drivers/net/usb/cdc_mbim.c      |  2 +-
 include/linux/if_vlan.h         | 19 -------------------
 4 files changed, 7 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index e1f1a006af8..bb9e9fc45e1 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -475,12 +475,8 @@ static void rlb_update_client(struct rlb_client_info *client_info)
 		skb->dev = client_info->slave->dev;
 
 		if (client_info->vlan_id) {
-			skb = vlan_put_tag(skb, htons(ETH_P_8021Q), client_info->vlan_id);
-			if (!skb) {
-				netdev_err(client_info->slave->bond->dev,
-					   "failed to insert VLAN tag\n");
-				continue;
-			}
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+					       client_info->vlan_id);
 		}
 
 		arp_xmit(skb);
@@ -951,13 +947,8 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[],
 	skb->priority = TC_PRIO_CONTROL;
 	skb->dev = slave->dev;
 
-	if (vid) {
-		skb = vlan_put_tag(skb, vlan_proto, vid);
-		if (!skb) {
-			netdev_err(slave->bond->dev, "failed to insert VLAN tag\n");
-			return;
-		}
-	}
+	if (vid)
+		__vlan_hwaccel_put_tag(skb, vlan_proto, vid);
 
 	dev_queue_xmit(skb);
 }
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8575fee8b35..e26c6823203 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2159,12 +2159,8 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op,
 	if (outer_tag->vlan_id) {
 		netdev_dbg(slave_dev, "outer tag: proto %X vid %X\n",
 			   ntohs(outer_tag->vlan_proto), outer_tag->vlan_id);
-		skb = vlan_put_tag(skb, outer_tag->vlan_proto,
-				   outer_tag->vlan_id);
-		if (!skb) {
-			net_err_ratelimited("failed to insert outer VLAN tag\n");
-			return;
-		}
+		__vlan_hwaccel_put_tag(skb, outer_tag->vlan_proto,
+				       outer_tag->vlan_id);
 	}
 
 xmit:
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 5ee7a1dbc02..96fc8a5bde8 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -402,7 +402,7 @@ static struct sk_buff *cdc_mbim_process_dgram(struct usbnet *dev, u8 *buf, size_
 
 	/* map MBIM session to VLAN */
 	if (tci)
-		vlan_put_tag(skb, htons(ETH_P_8021Q), tci);
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), tci);
 err:
 	return skb;
 }
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 1b5dbc2711f..75b70a5e4a6 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -354,25 +354,6 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb,
 	skb->vlan_tci = VLAN_TAG_PRESENT | vlan_tci;
 }
 
-/**
- * vlan_put_tag - inserts VLAN tag according to device features
- * @skb: skbuff to tag
- * @vlan_tci: VLAN TCI to insert
- *
- * Assumes skb->dev is the target that will xmit this frame.
- * Returns a VLAN tagged skb.
- */
-static inline struct sk_buff *vlan_put_tag(struct sk_buff *skb,
-					   __be16 vlan_proto, u16 vlan_tci)
-{
-	if (vlan_hw_offload_capable(skb->dev->features, vlan_proto)) {
-		__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
-		return skb;
-	} else {
-		return __vlan_put_tag(skb, vlan_proto, vlan_tci);
-	}
-}
-
 /**
  * __vlan_get_tag - get the VLAN ID that is part of the payload
  * @skb: skbuff to query
-- 
cgit v1.2.3-70-g09d2


From 62749e2cb3c4a7da3eaa5c01a7e787aebeff8536 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Wed, 19 Nov 2014 14:04:58 +0100
Subject: vlan: rename __vlan_put_tag to vlan_insert_tag_set_proto

Name fits better. Plus there's going to be introduced
__vlan_insert_tag later on.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c             |  4 ++--
 drivers/net/ethernet/emulex/benet/be_main.c |  6 ++++--
 drivers/net/vxlan.c                         | 12 ++++++------
 include/linux/if_vlan.h                     |  8 +++++---
 net/bridge/br_vlan.c                        |  4 ++--
 net/core/dev.c                              |  4 ++--
 net/core/netpoll.c                          |  4 ++--
 net/ipv4/geneve.c                           | 11 +++++------
 net/openvswitch/actions.c                   |  4 +++-
 net/openvswitch/datapath.c                  |  3 ++-
 net/openvswitch/vport-gre.c                 |  6 +++---
 11 files changed, 36 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index e26c6823203..c1d7da427a3 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2146,8 +2146,8 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op,
 
 		netdev_dbg(slave_dev, "inner tag: proto %X vid %X\n",
 			   ntohs(outer_tag->vlan_proto), tags->vlan_id);
-		skb = __vlan_put_tag(skb, tags->vlan_proto,
-				     tags->vlan_id);
+		skb = vlan_insert_tag_set_proto(skb, tags->vlan_proto,
+						tags->vlan_id);
 		if (!skb) {
 			net_err_ratelimited("failed to insert inner VLAN tag\n");
 			return;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 54160cc6265..d02fbc7694e 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -887,7 +887,8 @@ static struct sk_buff *be_insert_vlan_in_pkt(struct be_adapter *adapter,
 	}
 
 	if (vlan_tag) {
-		skb = __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
+		skb = vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q),
+						vlan_tag);
 		if (unlikely(!skb))
 			return skb;
 		skb->vlan_tci = 0;
@@ -896,7 +897,8 @@ static struct sk_buff *be_insert_vlan_in_pkt(struct be_adapter *adapter,
 	/* Insert the outer VLAN, if any */
 	if (adapter->qnq_vid) {
 		vlan_tag = adapter->qnq_vid;
-		skb = __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
+		skb = vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q),
+						vlan_tag);
 		if (unlikely(!skb))
 			return skb;
 		if (skip_hw_vlan)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 23b1e8c0d54..bb8fbab438e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1600,9 +1600,9 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 		return err;
 
 	if (vlan_tx_tag_present(skb)) {
-		if (WARN_ON(!__vlan_put_tag(skb,
-					    skb->vlan_proto,
-					    vlan_tx_tag_get(skb))))
+		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+						vlan_tx_tag_get(skb));
+		if (WARN_ON(!skb))
 			return -ENOMEM;
 
 		skb->vlan_tci = 0;
@@ -1644,9 +1644,9 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 		return err;
 
 	if (vlan_tx_tag_present(skb)) {
-		if (WARN_ON(!__vlan_put_tag(skb,
-					    skb->vlan_proto,
-					    vlan_tx_tag_get(skb))))
+		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+						vlan_tx_tag_get(skb));
+		if (WARN_ON(!skb))
 			return -ENOMEM;
 
 		skb->vlan_tci = 0;
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 75b70a5e4a6..46e4a15b9b5 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -320,8 +320,9 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
 }
 
 /**
- * __vlan_put_tag - regular VLAN tag inserting
+ * vlan_insert_tag_set_proto - regular VLAN tag inserting
  * @skb: skbuff to tag
+ * @vlan_proto: VLAN encapsulation protocol
  * @vlan_tci: VLAN TCI to insert
  *
  * Inserts the VLAN tag into @skb as part of the payload
@@ -330,8 +331,9 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
  * Following the skb_unshare() example, in case of error, the calling function
  * doesn't have to worry about freeing the original skb.
  */
-static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb,
-					     __be16 vlan_proto, u16 vlan_tci)
+static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb,
+							__be16 vlan_proto,
+							u16 vlan_tci)
 {
 	skb = vlan_insert_tag(skb, vlan_proto, vlan_tci);
 	if (skb)
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 150048fb99b..97b8ddf5736 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -199,8 +199,8 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 		if (skb->vlan_proto != proto) {
 			/* Protocol-mismatch, empty out vlan_tci for new tag */
 			skb_push(skb, ETH_HLEN);
-			skb = __vlan_put_tag(skb, skb->vlan_proto,
-					     vlan_tx_tag_get(skb));
+			skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+							vlan_tx_tag_get(skb));
 			if (unlikely(!skb))
 				return false;
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 1ab168e0fdf..3611e60df40 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2645,8 +2645,8 @@ static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb,
 {
 	if (vlan_tx_tag_present(skb) &&
 	    !vlan_hw_offload_capable(features, skb->vlan_proto)) {
-		skb = __vlan_put_tag(skb, skb->vlan_proto,
-				     vlan_tx_tag_get(skb));
+		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+						vlan_tx_tag_get(skb));
 		if (skb)
 			skb->vlan_tci = 0;
 	}
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index e6645b4f330..65d372384a3 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -79,8 +79,8 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	if (vlan_tx_tag_present(skb) &&
 	    !vlan_hw_offload_capable(features, skb->vlan_proto)) {
-		skb = __vlan_put_tag(skb, skb->vlan_proto,
-				     vlan_tx_tag_get(skb));
+		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+						vlan_tx_tag_get(skb));
 		if (unlikely(!skb)) {
 			/* This is actually a packet drop, but we
 			 * don't want the code that calls this
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index 31802afce34..fd430a6a1c3 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -132,12 +132,11 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 		return err;
 
 	if (vlan_tx_tag_present(skb)) {
-		if (unlikely(!__vlan_put_tag(skb,
-					     skb->vlan_proto,
-					     vlan_tx_tag_get(skb)))) {
-			err = -ENOMEM;
-			return err;
-		}
+		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+						vlan_tx_tag_get(skb));
+		if (unlikely(!skb)
+			return -ENOMEM;
+
 		skb->vlan_tci = 0;
 	}
 
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 749a3016307..426b9131ede 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -287,7 +287,9 @@ static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
 		/* push down current VLAN tag */
 		current_tag = vlan_tx_tag_get(skb);
 
-		if (!__vlan_put_tag(skb, skb->vlan_proto, current_tag))
+		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+						current_tag);
+		if (!skb)
 			return -ENOMEM;
 		/* Update mac_len for subsequent MPLS actions */
 		skb->mac_len += VLAN_HLEN;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index ab141d49bb9..c63e60e4d94 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -425,7 +425,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 		if (!nskb)
 			return -ENOMEM;
 
-		nskb = __vlan_put_tag(nskb, nskb->vlan_proto, vlan_tx_tag_get(nskb));
+		nskb = vlan_insert_tag_set_proto(nskb, nskb->vlan_proto,
+						 vlan_tx_tag_get(nskb));
 		if (!nskb)
 			return -ENOMEM;
 
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index 8e61a5c6ae7..777cd8c71d5 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -176,9 +176,9 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 	}
 
 	if (vlan_tx_tag_present(skb)) {
-		if (unlikely(!__vlan_put_tag(skb,
-					     skb->vlan_proto,
-					     vlan_tx_tag_get(skb)))) {
+		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+						vlan_tx_tag_get(skb));
+		if (unlikely(!skb) {
 			err = -ENOMEM;
 			goto err_free_rt;
 		}
-- 
cgit v1.2.3-70-g09d2


From 5968250c868ceee680aa77395b24e6ddcae17d36 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Wed, 19 Nov 2014 14:04:59 +0100
Subject: vlan: introduce *vlan_hwaccel_push_inside helpers

Use them to push skb->vlan_tci into the payload and avoid code
duplication.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c         | 22 ++++++----------------
 include/linux/if_vlan.h     | 34 ++++++++++++++++++++++++++++++++++
 net/core/dev.c              |  8 ++------
 net/core/netpoll.c          |  4 +---
 net/ipv4/geneve.c           | 11 +++--------
 net/openvswitch/datapath.c  |  4 +---
 net/openvswitch/vport-gre.c | 12 ++++--------
 7 files changed, 51 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index bb8fbab438e..64d45fa3d99 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1599,14 +1599,9 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 	if (unlikely(err))
 		return err;
 
-	if (vlan_tx_tag_present(skb)) {
-		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
-						vlan_tx_tag_get(skb));
-		if (WARN_ON(!skb))
-			return -ENOMEM;
-
-		skb->vlan_tci = 0;
-	}
+	skb = vlan_hwaccel_push_inside(skb);
+	if (WARN_ON(!skb))
+		return -ENOMEM;
 
 	vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
 	vxh->vx_flags = htonl(VXLAN_FLAGS);
@@ -1643,14 +1638,9 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 	if (unlikely(err))
 		return err;
 
-	if (vlan_tx_tag_present(skb)) {
-		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
-						vlan_tx_tag_get(skb));
-		if (WARN_ON(!skb))
-			return -ENOMEM;
-
-		skb->vlan_tci = 0;
-	}
+	skb = vlan_hwaccel_push_inside(skb);
+	if (WARN_ON(!skb))
+		return -ENOMEM;
 
 	vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
 	vxh->vx_flags = htonl(VXLAN_FLAGS);
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 46e4a15b9b5..291e6706876 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -341,6 +341,40 @@ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb,
 	return skb;
 }
 
+/*
+ * __vlan_hwaccel_push_inside - pushes vlan tag to the payload
+ * @skb: skbuff to tag
+ *
+ * Pushes the VLAN tag from @skb->vlan_tci inside to the payload.
+ *
+ * Following the skb_unshare() example, in case of error, the calling function
+ * doesn't have to worry about freeing the original skb.
+ */
+static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb)
+{
+	skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+					vlan_tx_tag_get(skb));
+	if (likely(skb))
+		skb->vlan_tci = 0;
+	return skb;
+}
+/*
+ * vlan_hwaccel_push_inside - pushes vlan tag to the payload
+ * @skb: skbuff to tag
+ *
+ * Checks is tag is present in @skb->vlan_tci and if it is, it pushes the
+ * VLAN tag from @skb->vlan_tci inside to the payload.
+ *
+ * Following the skb_unshare() example, in case of error, the calling function
+ * doesn't have to worry about freeing the original skb.
+ */
+static inline struct sk_buff *vlan_hwaccel_push_inside(struct sk_buff *skb)
+{
+	if (vlan_tx_tag_present(skb))
+		skb = __vlan_hwaccel_push_inside(skb);
+	return skb;
+}
+
 /**
  * __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting
  * @skb: skbuff to tag
diff --git a/net/core/dev.c b/net/core/dev.c
index 3611e60df40..ac4836241a9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2644,12 +2644,8 @@ static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb,
 					  netdev_features_t features)
 {
 	if (vlan_tx_tag_present(skb) &&
-	    !vlan_hw_offload_capable(features, skb->vlan_proto)) {
-		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
-						vlan_tx_tag_get(skb));
-		if (skb)
-			skb->vlan_tci = 0;
-	}
+	    !vlan_hw_offload_capable(features, skb->vlan_proto))
+		skb = __vlan_hwaccel_push_inside(skb);
 	return skb;
 }
 
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 65d372384a3..e0ad5d16c9c 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -79,8 +79,7 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	if (vlan_tx_tag_present(skb) &&
 	    !vlan_hw_offload_capable(features, skb->vlan_proto)) {
-		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
-						vlan_tx_tag_get(skb));
+		skb = __vlan_hwaccel_push_inside(skb);
 		if (unlikely(!skb)) {
 			/* This is actually a packet drop, but we
 			 * don't want the code that calls this
@@ -88,7 +87,6 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			 */
 			goto out;
 		}
-		skb->vlan_tci = 0;
 	}
 
 	status = netdev_start_xmit(skb, dev, txq, false);
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index fd430a6a1c3..a457232f013 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -131,14 +131,9 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 	if (unlikely(err))
 		return err;
 
-	if (vlan_tx_tag_present(skb)) {
-		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
-						vlan_tx_tag_get(skb));
-		if (unlikely(!skb)
-			return -ENOMEM;
-
-		skb->vlan_tci = 0;
-	}
+	skb = vlan_hwaccel_push_inside(skb);
+	if (unlikely(!skb))
+		return -ENOMEM;
 
 	gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len);
 	geneve_build_header(gnvh, tun_flags, vni, opt_len, opt);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index c63e60e4d94..f37ca3e5824 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -425,12 +425,10 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 		if (!nskb)
 			return -ENOMEM;
 
-		nskb = vlan_insert_tag_set_proto(nskb, nskb->vlan_proto,
-						 vlan_tx_tag_get(nskb));
+		nskb = __vlan_hwaccel_push_inside(nskb);
 		if (!nskb)
 			return -ENOMEM;
 
-		nskb->vlan_tci = 0;
 		skb = nskb;
 	}
 
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index 777cd8c71d5..6b69df545b1 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -175,14 +175,10 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 			goto err_free_rt;
 	}
 
-	if (vlan_tx_tag_present(skb)) {
-		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
-						vlan_tx_tag_get(skb));
-		if (unlikely(!skb) {
-			err = -ENOMEM;
-			goto err_free_rt;
-		}
-		skb->vlan_tci = 0;
+	skb = vlan_hwaccel_push_inside(skb);
+	if (unlikely(!skb)) {
+		err = -ENOMEM;
+		goto err_free_rt;
 	}
 
 	/* Push Tunnel header. */
-- 
cgit v1.2.3-70-g09d2


From 15255a43e6c917813800702e100267046e240cc0 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Wed, 19 Nov 2014 14:05:00 +0100
Subject: vlan: introduce __vlan_insert_tag helper which does not free skb

There's a need for helper which inserts vlan tag but does not free the
skb in case of an error.

Suggested-by: Pravin Shelar <pshelar@nicira.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 45 ++++++++++++++++++++++++++++++++++-----------
 1 file changed, 34 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 291e6706876..515a35e2a48 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -282,28 +282,24 @@ static inline bool vlan_hw_offload_capable(netdev_features_t features,
 }
 
 /**
- * vlan_insert_tag - regular VLAN tag inserting
+ * __vlan_insert_tag - regular VLAN tag inserting
  * @skb: skbuff to tag
  * @vlan_proto: VLAN encapsulation protocol
  * @vlan_tci: VLAN TCI to insert
  *
  * Inserts the VLAN tag into @skb as part of the payload
- * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
- *
- * Following the skb_unshare() example, in case of error, the calling function
- * doesn't have to worry about freeing the original skb.
+ * Returns error if skb_cow_head failes.
  *
  * Does not change skb->protocol so this function can be used during receive.
  */
-static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
-					      __be16 vlan_proto, u16 vlan_tci)
+static inline int __vlan_insert_tag(struct sk_buff *skb,
+				    __be16 vlan_proto, u16 vlan_tci)
 {
 	struct vlan_ethhdr *veth;
 
-	if (skb_cow_head(skb, VLAN_HLEN) < 0) {
-		dev_kfree_skb_any(skb);
-		return NULL;
-	}
+	if (skb_cow_head(skb, VLAN_HLEN) < 0)
+		return -ENOMEM;
+
 	veth = (struct vlan_ethhdr *)skb_push(skb, VLAN_HLEN);
 
 	/* Move the mac addresses to the beginning of the new header. */
@@ -316,6 +312,33 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
 	/* now, the TCI */
 	veth->h_vlan_TCI = htons(vlan_tci);
 
+	return 0;
+}
+
+/**
+ * vlan_insert_tag - regular VLAN tag inserting
+ * @skb: skbuff to tag
+ * @vlan_proto: VLAN encapsulation protocol
+ * @vlan_tci: VLAN TCI to insert
+ *
+ * Inserts the VLAN tag into @skb as part of the payload
+ * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
+ *
+ * Following the skb_unshare() example, in case of error, the calling function
+ * doesn't have to worry about freeing the original skb.
+ *
+ * Does not change skb->protocol so this function can be used during receive.
+ */
+static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
+					      __be16 vlan_proto, u16 vlan_tci)
+{
+	int err;
+
+	err = __vlan_insert_tag(skb, vlan_proto, vlan_tci);
+	if (err) {
+		dev_kfree_skb_any(skb);
+		return NULL;
+	}
 	return skb;
 }
 
-- 
cgit v1.2.3-70-g09d2


From e21951212f03b8d805795d8f71206853b2ab344d Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Wed, 19 Nov 2014 14:05:01 +0100
Subject: net: move make_writable helper into common code

note that skb_make_writable already exists in net/netfilter/core.c
but does something slightly different.

Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    |  1 +
 net/core/skbuff.c         | 12 ++++++++++++
 net/openvswitch/actions.c | 39 ++++++++++++++-------------------------
 3 files changed, 27 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 73c370e615d..e045516891a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2678,6 +2678,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet);
 unsigned int skb_gso_transport_seglen(const struct sk_buff *skb);
 struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features);
 struct sk_buff *skb_vlan_untag(struct sk_buff *skb);
+int skb_ensure_writable(struct sk_buff *skb, int write_len);
 
 struct skb_checksum_ops {
 	__wsum (*update)(const void *mem, int len, __wsum wsum);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 700189604f3..d11bbe0da35 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4151,6 +4151,18 @@ err_free:
 }
 EXPORT_SYMBOL(skb_vlan_untag);
 
+int skb_ensure_writable(struct sk_buff *skb, int write_len)
+{
+	if (!pskb_may_pull(skb, write_len))
+		return -ENOMEM;
+
+	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
+		return 0;
+
+	return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+}
+EXPORT_SYMBOL(skb_ensure_writable);
+
 /**
  * alloc_skb_with_frags - allocate skb with page frags
  *
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 426b9131ede..7ffa3771626 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -119,17 +119,6 @@ static bool is_flow_key_valid(const struct sw_flow_key *key)
 	return !!key->eth.type;
 }
 
-static int make_writable(struct sk_buff *skb, int write_len)
-{
-	if (!pskb_may_pull(skb, write_len))
-		return -ENOMEM;
-
-	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
-		return 0;
-
-	return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
-}
-
 static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 		     const struct ovs_action_push_mpls *mpls)
 {
@@ -171,7 +160,7 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	struct ethhdr *hdr;
 	int err;
 
-	err = make_writable(skb, skb->mac_len + MPLS_HLEN);
+	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
 	if (unlikely(err))
 		return err;
 
@@ -201,7 +190,7 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	__be32 *stack;
 	int err;
 
-	err = make_writable(skb, skb->mac_len + MPLS_HLEN);
+	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
 	if (unlikely(err))
 		return err;
 
@@ -223,7 +212,7 @@ static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
 	struct vlan_hdr *vhdr;
 	int err;
 
-	err = make_writable(skb, VLAN_ETH_HLEN);
+	err = skb_ensure_writable(skb, VLAN_ETH_HLEN);
 	if (unlikely(err))
 		return err;
 
@@ -310,7 +299,7 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *key,
 			const struct ovs_key_ethernet *eth_key)
 {
 	int err;
-	err = make_writable(skb, ETH_HLEN);
+	err = skb_ensure_writable(skb, ETH_HLEN);
 	if (unlikely(err))
 		return err;
 
@@ -412,8 +401,8 @@ static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *key,
 	struct iphdr *nh;
 	int err;
 
-	err = make_writable(skb, skb_network_offset(skb) +
-				 sizeof(struct iphdr));
+	err = skb_ensure_writable(skb, skb_network_offset(skb) +
+				  sizeof(struct iphdr));
 	if (unlikely(err))
 		return err;
 
@@ -450,8 +439,8 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *key,
 	__be32 *saddr;
 	__be32 *daddr;
 
-	err = make_writable(skb, skb_network_offset(skb) +
-			    sizeof(struct ipv6hdr));
+	err = skb_ensure_writable(skb, skb_network_offset(skb) +
+				  sizeof(struct ipv6hdr));
 	if (unlikely(err))
 		return err;
 
@@ -493,7 +482,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *key,
 	return 0;
 }
 
-/* Must follow make_writable() since that can move the skb data. */
+/* Must follow skb_ensure_writable() since that can move the skb data. */
 static void set_tp_port(struct sk_buff *skb, __be16 *port,
 			 __be16 new_port, __sum16 *check)
 {
@@ -523,8 +512,8 @@ static int set_udp(struct sk_buff *skb, struct sw_flow_key *key,
 	struct udphdr *uh;
 	int err;
 
-	err = make_writable(skb, skb_transport_offset(skb) +
-				 sizeof(struct udphdr));
+	err = skb_ensure_writable(skb, skb_transport_offset(skb) +
+				  sizeof(struct udphdr));
 	if (unlikely(err))
 		return err;
 
@@ -548,8 +537,8 @@ static int set_tcp(struct sk_buff *skb, struct sw_flow_key *key,
 	struct tcphdr *th;
 	int err;
 
-	err = make_writable(skb, skb_transport_offset(skb) +
-				 sizeof(struct tcphdr));
+	err = skb_ensure_writable(skb, skb_transport_offset(skb) +
+				  sizeof(struct tcphdr));
 	if (unlikely(err))
 		return err;
 
@@ -574,7 +563,7 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *key,
 	int err;
 	unsigned int sctphoff = skb_transport_offset(skb);
 
-	err = make_writable(skb, sctphoff + sizeof(struct sctphdr));
+	err = skb_ensure_writable(skb, sctphoff + sizeof(struct sctphdr));
 	if (unlikely(err))
 		return err;
 
-- 
cgit v1.2.3-70-g09d2


From 93515d53b133d66f01aec7b231fa3e40e3d2fd9a Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Wed, 19 Nov 2014 14:05:02 +0100
Subject: net: move vlan pop/push functions into common code

So it can be used from out of openvswitch code.
Did couple of cosmetic changes on the way, namely variable naming and
adding support for 8021AD proto.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    |  2 +
 net/core/skbuff.c         | 95 +++++++++++++++++++++++++++++++++++++++++++++++
 net/openvswitch/actions.c | 86 +++++-------------------------------------
 3 files changed, 106 insertions(+), 77 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e045516891a..78c299f40ba 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2679,6 +2679,8 @@ unsigned int skb_gso_transport_seglen(const struct sk_buff *skb);
 struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features);
 struct sk_buff *skb_vlan_untag(struct sk_buff *skb);
 int skb_ensure_writable(struct sk_buff *skb, int write_len);
+int skb_vlan_pop(struct sk_buff *skb);
+int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
 
 struct skb_checksum_ops {
 	__wsum (*update)(const void *mem, int len, __wsum wsum);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d11bbe0da35..c906c5f4bf6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4163,6 +4163,101 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len)
 }
 EXPORT_SYMBOL(skb_ensure_writable);
 
+/* remove VLAN header from packet and update csum accordingly. */
+static int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci)
+{
+	struct vlan_hdr *vhdr;
+	unsigned int offset = skb->data - skb_mac_header(skb);
+	int err;
+
+	__skb_push(skb, offset);
+	err = skb_ensure_writable(skb, VLAN_ETH_HLEN);
+	if (unlikely(err))
+		goto pull;
+
+	skb_postpull_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
+
+	vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
+	*vlan_tci = ntohs(vhdr->h_vlan_TCI);
+
+	memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN);
+	__skb_pull(skb, VLAN_HLEN);
+
+	vlan_set_encap_proto(skb, vhdr);
+	skb->mac_header += VLAN_HLEN;
+
+	if (skb_network_offset(skb) < ETH_HLEN)
+		skb_set_network_header(skb, ETH_HLEN);
+
+	skb_reset_mac_len(skb);
+pull:
+	__skb_pull(skb, offset);
+
+	return err;
+}
+
+int skb_vlan_pop(struct sk_buff *skb)
+{
+	u16 vlan_tci;
+	__be16 vlan_proto;
+	int err;
+
+	if (likely(vlan_tx_tag_present(skb))) {
+		skb->vlan_tci = 0;
+	} else {
+		if (unlikely((skb->protocol != htons(ETH_P_8021Q) &&
+			      skb->protocol != htons(ETH_P_8021AD)) ||
+			     skb->len < VLAN_ETH_HLEN))
+			return 0;
+
+		err = __skb_vlan_pop(skb, &vlan_tci);
+		if (err)
+			return err;
+	}
+	/* move next vlan tag to hw accel tag */
+	if (likely((skb->protocol != htons(ETH_P_8021Q) &&
+		    skb->protocol != htons(ETH_P_8021AD)) ||
+		   skb->len < VLAN_ETH_HLEN))
+		return 0;
+
+	vlan_proto = skb->protocol;
+	err = __skb_vlan_pop(skb, &vlan_tci);
+	if (unlikely(err))
+		return err;
+
+	__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
+	return 0;
+}
+EXPORT_SYMBOL(skb_vlan_pop);
+
+int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
+{
+	if (vlan_tx_tag_present(skb)) {
+		unsigned int offset = skb->data - skb_mac_header(skb);
+		int err;
+
+		/* __vlan_insert_tag expect skb->data pointing to mac header.
+		 * So change skb->data before calling it and change back to
+		 * original position later
+		 */
+		__skb_push(skb, offset);
+		err = __vlan_insert_tag(skb, skb->vlan_proto,
+					vlan_tx_tag_get(skb));
+		if (err)
+			return err;
+		skb->protocol = skb->vlan_proto;
+		skb->mac_len += VLAN_HLEN;
+		__skb_pull(skb, offset);
+
+		if (skb->ip_summed == CHECKSUM_COMPLETE)
+			skb->csum = csum_add(skb->csum, csum_partial(skb->data
+					+ (2 * ETH_ALEN), VLAN_HLEN, 0));
+	}
+	__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
+	return 0;
+}
+EXPORT_SYMBOL(skb_vlan_push);
+
 /**
  * alloc_skb_with_frags - allocate skb with page frags
  *
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 7ffa3771626..4e05ea1c2d1 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -206,93 +206,27 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	return 0;
 }
 
-/* remove VLAN header from packet and update csum accordingly. */
-static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
-{
-	struct vlan_hdr *vhdr;
-	int err;
-
-	err = skb_ensure_writable(skb, VLAN_ETH_HLEN);
-	if (unlikely(err))
-		return err;
-
-	skb_postpull_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
-
-	vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
-	*current_tci = vhdr->h_vlan_TCI;
-
-	memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN);
-	__skb_pull(skb, VLAN_HLEN);
-
-	vlan_set_encap_proto(skb, vhdr);
-	skb->mac_header += VLAN_HLEN;
-
-	if (skb_network_offset(skb) < ETH_HLEN)
-		skb_set_network_header(skb, ETH_HLEN);
-
-	/* Update mac_len for subsequent MPLS actions */
-	skb_reset_mac_len(skb);
-	return 0;
-}
-
 static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	__be16 tci;
 	int err;
 
-	if (likely(vlan_tx_tag_present(skb))) {
-		skb->vlan_tci = 0;
-	} else {
-		if (unlikely(skb->protocol != htons(ETH_P_8021Q) ||
-			     skb->len < VLAN_ETH_HLEN))
-			return 0;
-
-		err = __pop_vlan_tci(skb, &tci);
-		if (err)
-			return err;
-	}
-	/* move next vlan tag to hw accel tag */
-	if (likely(skb->protocol != htons(ETH_P_8021Q) ||
-		   skb->len < VLAN_ETH_HLEN)) {
+	err = skb_vlan_pop(skb);
+	if (vlan_tx_tag_present(skb))
+		invalidate_flow_key(key);
+	else
 		key->eth.tci = 0;
-		return 0;
-	}
-
-	invalidate_flow_key(key);
-	err = __pop_vlan_tci(skb, &tci);
-	if (unlikely(err))
-		return err;
-
-	__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), ntohs(tci));
-	return 0;
+	return err;
 }
 
 static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
 		     const struct ovs_action_push_vlan *vlan)
 {
-	if (unlikely(vlan_tx_tag_present(skb))) {
-		u16 current_tag;
-
-		/* push down current VLAN tag */
-		current_tag = vlan_tx_tag_get(skb);
-
-		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
-						current_tag);
-		if (!skb)
-			return -ENOMEM;
-		/* Update mac_len for subsequent MPLS actions */
-		skb->mac_len += VLAN_HLEN;
-
-		if (skb->ip_summed == CHECKSUM_COMPLETE)
-			skb->csum = csum_add(skb->csum, csum_partial(skb->data
-					+ (2 * ETH_ALEN), VLAN_HLEN, 0));
-
+	if (vlan_tx_tag_present(skb))
 		invalidate_flow_key(key);
-	} else {
+	else
 		key->eth.tci = vlan->vlan_tci;
-	}
-	__vlan_hwaccel_put_tag(skb, vlan->vlan_tpid, ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
-	return 0;
+	return skb_vlan_push(skb, vlan->vlan_tpid,
+			     ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
 }
 
 static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *key,
@@ -858,8 +792,6 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 		case OVS_ACTION_ATTR_PUSH_VLAN:
 			err = push_vlan(skb, key, nla_data(a));
-			if (unlikely(err)) /* skb already freed. */
-				return err;
 			break;
 
 		case OVS_ACTION_ATTR_POP_VLAN:
-- 
cgit v1.2.3-70-g09d2


From c7e2b9689ef81362a8091592da6cb6a7723f377a Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Wed, 19 Nov 2014 14:05:03 +0100
Subject: sched: introduce vlan action

This tc action allows to work with vlan tagged skbs. Two supported
sub-actions are header pop and header push.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tc_act/tc_vlan.h        |  27 +++++
 include/uapi/linux/tc_act/tc_vlan.h |  35 ++++++
 net/sched/Kconfig                   |  11 ++
 net/sched/Makefile                  |   1 +
 net/sched/act_vlan.c                | 207 ++++++++++++++++++++++++++++++++++++
 5 files changed, 281 insertions(+)
 create mode 100644 include/net/tc_act/tc_vlan.h
 create mode 100644 include/uapi/linux/tc_act/tc_vlan.h
 create mode 100644 net/sched/act_vlan.c

(limited to 'include')

diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h
new file mode 100644
index 00000000000..c809c1d2cea
--- /dev/null
+++ b/include/net/tc_act/tc_vlan.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __NET_TC_VLAN_H
+#define __NET_TC_VLAN_H
+
+#include <net/act_api.h>
+
+#define VLAN_F_POP		0x1
+#define VLAN_F_PUSH		0x2
+
+struct tcf_vlan {
+	struct tcf_common	common;
+	int			tcfv_action;
+	__be16			tcfv_push_vid;
+	__be16			tcfv_push_proto;
+};
+#define to_vlan(a) \
+	container_of(a->priv, struct tcf_vlan, common)
+
+#endif /* __NET_TC_VLAN_H */
diff --git a/include/uapi/linux/tc_act/tc_vlan.h b/include/uapi/linux/tc_act/tc_vlan.h
new file mode 100644
index 00000000000..f7b8d448b96
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_vlan.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_TC_VLAN_H
+#define __LINUX_TC_VLAN_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_VLAN 12
+
+#define TCA_VLAN_ACT_POP	1
+#define TCA_VLAN_ACT_PUSH	2
+
+struct tc_vlan {
+	tc_gen;
+	int v_action;
+};
+
+enum {
+	TCA_VLAN_UNSPEC,
+	TCA_VLAN_TM,
+	TCA_VLAN_PARMS,
+	TCA_VLAN_PUSH_VLAN_ID,
+	TCA_VLAN_PUSH_VLAN_PROTOCOL,
+	__TCA_VLAN_MAX,
+};
+#define TCA_VLAN_MAX (__TCA_VLAN_MAX - 1)
+
+#endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index a1a8e29e5fc..88618f8b794 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -686,6 +686,17 @@ config NET_ACT_CSUM
 	  To compile this code as a module, choose M here: the
 	  module will be called act_csum.
 
+config NET_ACT_VLAN
+        tristate "Vlan manipulation"
+        depends on NET_CLS_ACT
+        ---help---
+	  Say Y here to push or pop vlan headers.
+
+	  If unsure, say N.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called act_vlan.
+
 config NET_CLS_IND
 	bool "Incoming device classification"
 	depends on NET_CLS_U32 || NET_CLS_FW
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 0a869a11f3e..679f24ae7f9 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_NET_ACT_PEDIT)	+= act_pedit.o
 obj-$(CONFIG_NET_ACT_SIMP)	+= act_simple.o
 obj-$(CONFIG_NET_ACT_SKBEDIT)	+= act_skbedit.o
 obj-$(CONFIG_NET_ACT_CSUM)	+= act_csum.o
+obj-$(CONFIG_NET_ACT_VLAN)	+= act_vlan.o
 obj-$(CONFIG_NET_SCH_FIFO)	+= sch_fifo.o
 obj-$(CONFIG_NET_SCH_CBQ)	+= sch_cbq.o
 obj-$(CONFIG_NET_SCH_HTB)	+= sch_htb.o
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
new file mode 100644
index 00000000000..d735ecf0b1a
--- /dev/null
+++ b/net/sched/act_vlan.c
@@ -0,0 +1,207 @@
+/*
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_vlan.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+
+#include <linux/tc_act/tc_vlan.h>
+#include <net/tc_act/tc_vlan.h>
+
+#define VLAN_TAB_MASK     15
+
+static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
+		    struct tcf_result *res)
+{
+	struct tcf_vlan *v = a->priv;
+	int action;
+	int err;
+
+	spin_lock(&v->tcf_lock);
+	v->tcf_tm.lastuse = jiffies;
+	bstats_update(&v->tcf_bstats, skb);
+	action = v->tcf_action;
+
+	switch (v->tcfv_action) {
+	case TCA_VLAN_ACT_POP:
+		err = skb_vlan_pop(skb);
+		if (err)
+			goto drop;
+		break;
+	case TCA_VLAN_ACT_PUSH:
+		err = skb_vlan_push(skb, v->tcfv_push_proto, v->tcfv_push_vid);
+		if (err)
+			goto drop;
+		break;
+	default:
+		BUG();
+	}
+
+	goto unlock;
+
+drop:
+	action = TC_ACT_SHOT;
+	v->tcf_qstats.drops++;
+unlock:
+	spin_unlock(&v->tcf_lock);
+	return action;
+}
+
+static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
+	[TCA_VLAN_PARMS]		= { .len = sizeof(struct tc_vlan) },
+	[TCA_VLAN_PUSH_VLAN_ID]		= { .type = NLA_U16 },
+	[TCA_VLAN_PUSH_VLAN_PROTOCOL]	= { .type = NLA_U16 },
+};
+
+static int tcf_vlan_init(struct net *net, struct nlattr *nla,
+			 struct nlattr *est, struct tc_action *a,
+			 int ovr, int bind)
+{
+	struct nlattr *tb[TCA_VLAN_MAX + 1];
+	struct tc_vlan *parm;
+	struct tcf_vlan *v;
+	int action;
+	__be16 push_vid = 0;
+	__be16 push_proto = 0;
+	int ret = 0;
+	int err;
+
+	if (!nla)
+		return -EINVAL;
+
+	err = nla_parse_nested(tb, TCA_VLAN_MAX, nla, vlan_policy);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_VLAN_PARMS])
+		return -EINVAL;
+	parm = nla_data(tb[TCA_VLAN_PARMS]);
+	switch (parm->v_action) {
+	case TCA_VLAN_ACT_POP:
+		break;
+	case TCA_VLAN_ACT_PUSH:
+		if (!tb[TCA_VLAN_PUSH_VLAN_ID])
+			return -EINVAL;
+		push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]);
+		if (push_vid >= VLAN_VID_MASK)
+			return -ERANGE;
+
+		if (tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]) {
+			push_proto = nla_get_be16(tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]);
+			switch (push_proto) {
+			case htons(ETH_P_8021Q):
+			case htons(ETH_P_8021AD):
+				break;
+			default:
+				return -EPROTONOSUPPORT;
+			}
+		} else {
+			push_proto = htons(ETH_P_8021Q);
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+	action = parm->v_action;
+
+	if (!tcf_hash_check(parm->index, a, bind)) {
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*v), bind);
+		if (ret)
+			return ret;
+
+		ret = ACT_P_CREATED;
+	} else {
+		if (bind)
+			return 0;
+		tcf_hash_release(a, bind);
+		if (!ovr)
+			return -EEXIST;
+	}
+
+	v = to_vlan(a);
+
+	spin_lock_bh(&v->tcf_lock);
+
+	v->tcfv_action = action;
+	v->tcfv_push_vid = push_vid;
+	v->tcfv_push_proto = push_proto;
+
+	v->tcf_action = parm->action;
+
+	spin_unlock_bh(&v->tcf_lock);
+
+	if (ret == ACT_P_CREATED)
+		tcf_hash_insert(a);
+	return ret;
+}
+
+static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
+			 int bind, int ref)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tcf_vlan *v = a->priv;
+	struct tc_vlan opt = {
+		.index    = v->tcf_index,
+		.refcnt   = v->tcf_refcnt - ref,
+		.bindcnt  = v->tcf_bindcnt - bind,
+		.action   = v->tcf_action,
+		.v_action = v->tcfv_action,
+	};
+	struct tcf_t t;
+
+	if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	if (v->tcfv_action == TCA_VLAN_ACT_PUSH &&
+	    (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) ||
+	     nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, v->tcfv_push_proto)))
+		goto nla_put_failure;
+
+	t.install = jiffies_to_clock_t(jiffies - v->tcf_tm.install);
+	t.lastuse = jiffies_to_clock_t(jiffies - v->tcf_tm.lastuse);
+	t.expires = jiffies_to_clock_t(v->tcf_tm.expires);
+	if (nla_put(skb, TCA_VLAN_TM, sizeof(t), &t))
+		goto nla_put_failure;
+	return skb->len;
+
+nla_put_failure:
+	nlmsg_trim(skb, b);
+	return -1;
+}
+
+static struct tc_action_ops act_vlan_ops = {
+	.kind		=	"vlan",
+	.type		=	TCA_ACT_VLAN,
+	.owner		=	THIS_MODULE,
+	.act		=	tcf_vlan,
+	.dump		=	tcf_vlan_dump,
+	.init		=	tcf_vlan_init,
+};
+
+static int __init vlan_init_module(void)
+{
+	return tcf_register_action(&act_vlan_ops, VLAN_TAB_MASK);
+}
+
+static void __exit vlan_cleanup_module(void)
+{
+	tcf_unregister_action(&act_vlan_ops);
+}
+
+module_init(vlan_init_module);
+module_exit(vlan_cleanup_module);
+
+MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
+MODULE_DESCRIPTION("vlan manipulation actions");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3-70-g09d2


From f8b8be8a310a55856fd2c369dade08088d85df3b Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Date: Fri, 21 Nov 2014 05:25:16 -0500
Subject: ftrace, kprobes: Support IPMODIFY flag to find IP modify conflict

Introduce FTRACE_OPS_FL_IPMODIFY to avoid conflict among
ftrace users who may modify regs->ip to change the execution
path. If two or more users modify the regs->ip on the same
function entry, one of them will be broken. So they must add
IPMODIFY flag and make sure that ftrace_set_filter_ip() succeeds.

Note that ftrace doesn't allow ftrace_ops which has IPMODIFY
flag to have notrace hash, and the ftrace_ops must have a
filter hash (so that the ftrace_ops can hook only specific
entries), because it strongly depends on the address and
must be allowed for only few selected functions.

Link: http://lkml.kernel.org/r/20141121102516.11844.27829.stgit@localhost.localdomain

Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Vojtech Pavlik <vojtech@suse.cz>
Cc: Miroslav Benes <mbenes@suse.cz>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
[ fixed up some of the comments ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 Documentation/trace/ftrace.txt |   5 ++
 include/linux/ftrace.h         |  16 ++++-
 kernel/trace/ftrace.c          | 142 ++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 159 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 4da42616939..f10f5f5d260 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -234,6 +234,11 @@ of ftrace. Here is a list of some of the key files:
 	will be displayed on the same line as the function that
 	is returning registers.
 
+	If the callback registered to be traced by a function with
+	the "ip modify" attribute (thus the regs->ip can be changed),
+	an 'I' will be displayed on the same line as the function that
+	can be overridden.
+
   function_profile_enabled:
 
 	When set it will enable all functions with either the function
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 7b2616fa247..ed501953f0b 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -61,6 +61,11 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
 /*
  * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are
  * set in the flags member.
+ * CONTROL, SAVE_REGS, SAVE_REGS_IF_SUPPORTED, RECURSION_SAFE, STUB and
+ * IPMODIFY are a kind of attribute flags which can be set only before
+ * registering the ftrace_ops, and can not be modified while registered.
+ * Changing those attribute flags after regsitering ftrace_ops will
+ * cause unexpected results.
  *
  * ENABLED - set/unset when ftrace_ops is registered/unregistered
  * DYNAMIC - set when ftrace_ops is registered to denote dynamically
@@ -101,6 +106,10 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
  *            The ftrace_ops trampoline can be set by the ftrace users, and
  *            in such cases the arch must not modify it. Only the arch ftrace
  *            core code should set this flag.
+ * IPMODIFY - The ops can modify the IP register. This can only be set with
+ *            SAVE_REGS. If another ops with this flag set is already registered
+ *            for any of the functions that this ops will be registered for, then
+ *            this ops will fail to register or set_filter_ip.
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
@@ -116,6 +125,7 @@ enum {
 	FTRACE_OPS_FL_REMOVING			= 1 << 10,
 	FTRACE_OPS_FL_MODIFYING			= 1 << 11,
 	FTRACE_OPS_FL_ALLOC_TRAMP		= 1 << 12,
+	FTRACE_OPS_FL_IPMODIFY			= 1 << 13,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -310,6 +320,7 @@ bool is_ftrace_trampoline(unsigned long addr);
  *  ENABLED - the function is being traced
  *  REGS    - the record wants the function to save regs
  *  REGS_EN - the function is set up to save regs.
+ *  IPMODIFY - the record allows for the IP address to be changed.
  *
  * When a new ftrace_ops is registered and wants a function to save
  * pt_regs, the rec->flag REGS is set. When the function has been
@@ -323,10 +334,11 @@ enum {
 	FTRACE_FL_REGS_EN	= (1UL << 29),
 	FTRACE_FL_TRAMP		= (1UL << 28),
 	FTRACE_FL_TRAMP_EN	= (1UL << 27),
+	FTRACE_FL_IPMODIFY	= (1UL << 26),
 };
 
-#define FTRACE_REF_MAX_SHIFT	27
-#define FTRACE_FL_BITS		5
+#define FTRACE_REF_MAX_SHIFT	26
+#define FTRACE_FL_BITS		6
 #define FTRACE_FL_MASKED_BITS	((1UL << FTRACE_FL_BITS) - 1)
 #define FTRACE_FL_MASK		(FTRACE_FL_MASKED_BITS << FTRACE_REF_MAX_SHIFT)
 #define FTRACE_REF_MAX		((1UL << FTRACE_REF_MAX_SHIFT) - 1)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 588af40d33d..929a733d302 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1358,6 +1358,9 @@ ftrace_hash_rec_disable_modify(struct ftrace_ops *ops, int filter_hash);
 static void
 ftrace_hash_rec_enable_modify(struct ftrace_ops *ops, int filter_hash);
 
+static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops,
+				       struct ftrace_hash *new_hash);
+
 static int
 ftrace_hash_move(struct ftrace_ops *ops, int enable,
 		 struct ftrace_hash **dst, struct ftrace_hash *src)
@@ -1368,8 +1371,13 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 	struct ftrace_hash *new_hash;
 	int size = src->count;
 	int bits = 0;
+	int ret;
 	int i;
 
+	/* Reject setting notrace hash on IPMODIFY ftrace_ops */
+	if (ops->flags & FTRACE_OPS_FL_IPMODIFY && !enable)
+		return -EINVAL;
+
 	/*
 	 * If the new source is empty, just free dst and assign it
 	 * the empty_hash.
@@ -1403,6 +1411,16 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 	}
 
 update:
+	/* Make sure this can be applied if it is IPMODIFY ftrace_ops */
+	if (enable) {
+		/* IPMODIFY should be updated only when filter_hash updating */
+		ret = ftrace_hash_ipmodify_update(ops, new_hash);
+		if (ret < 0) {
+			free_ftrace_hash(new_hash);
+			return ret;
+		}
+	}
+
 	/*
 	 * Remove the current set, update the hash and add
 	 * them back.
@@ -1767,6 +1785,114 @@ static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops,
 	ftrace_hash_rec_update_modify(ops, filter_hash, 1);
 }
 
+/*
+ * Try to update IPMODIFY flag on each ftrace_rec. Return 0 if it is OK
+ * or no-needed to update, -EBUSY if it detects a conflict of the flag
+ * on a ftrace_rec, and -EINVAL if the new_hash tries to trace all recs.
+ * Note that old_hash and new_hash has below meanings
+ *  - If the hash is NULL, it hits all recs (if IPMODIFY is set, this is rejected)
+ *  - If the hash is EMPTY_HASH, it hits nothing
+ *  - Anything else hits the recs which match the hash entries.
+ */
+static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops,
+					 struct ftrace_hash *old_hash,
+					 struct ftrace_hash *new_hash)
+{
+	struct ftrace_page *pg;
+	struct dyn_ftrace *rec, *end = NULL;
+	int in_old, in_new;
+
+	/* Only update if the ops has been registered */
+	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return 0;
+
+	if (!(ops->flags & FTRACE_OPS_FL_IPMODIFY))
+		return 0;
+
+	/*
+	 * Since the IPMODIFY is a very address sensitive action, we do not
+	 * allow ftrace_ops to set all functions to new hash.
+	 */
+	if (!new_hash || !old_hash)
+		return -EINVAL;
+
+	/* Update rec->flags */
+	do_for_each_ftrace_rec(pg, rec) {
+		/* We need to update only differences of filter_hash */
+		in_old = !!ftrace_lookup_ip(old_hash, rec->ip);
+		in_new = !!ftrace_lookup_ip(new_hash, rec->ip);
+		if (in_old == in_new)
+			continue;
+
+		if (in_new) {
+			/* New entries must ensure no others are using it */
+			if (rec->flags & FTRACE_FL_IPMODIFY)
+				goto rollback;
+			rec->flags |= FTRACE_FL_IPMODIFY;
+		} else /* Removed entry */
+			rec->flags &= ~FTRACE_FL_IPMODIFY;
+	} while_for_each_ftrace_rec();
+
+	return 0;
+
+rollback:
+	end = rec;
+
+	/* Roll back what we did above */
+	do_for_each_ftrace_rec(pg, rec) {
+		if (rec == end)
+			goto err_out;
+
+		in_old = !!ftrace_lookup_ip(old_hash, rec->ip);
+		in_new = !!ftrace_lookup_ip(new_hash, rec->ip);
+		if (in_old == in_new)
+			continue;
+
+		if (in_new)
+			rec->flags &= ~FTRACE_FL_IPMODIFY;
+		else
+			rec->flags |= FTRACE_FL_IPMODIFY;
+	} while_for_each_ftrace_rec();
+
+err_out:
+	return -EBUSY;
+}
+
+static int ftrace_hash_ipmodify_enable(struct ftrace_ops *ops)
+{
+	struct ftrace_hash *hash = ops->func_hash->filter_hash;
+
+	if (ftrace_hash_empty(hash))
+		hash = NULL;
+
+	return __ftrace_hash_update_ipmodify(ops, EMPTY_HASH, hash);
+}
+
+/* Disabling always succeeds */
+static void ftrace_hash_ipmodify_disable(struct ftrace_ops *ops)
+{
+	struct ftrace_hash *hash = ops->func_hash->filter_hash;
+
+	if (ftrace_hash_empty(hash))
+		hash = NULL;
+
+	__ftrace_hash_update_ipmodify(ops, hash, EMPTY_HASH);
+}
+
+static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops,
+				       struct ftrace_hash *new_hash)
+{
+	struct ftrace_hash *old_hash = ops->func_hash->filter_hash;
+
+	if (ftrace_hash_empty(old_hash))
+		old_hash = NULL;
+
+	if (ftrace_hash_empty(new_hash))
+		new_hash = NULL;
+
+	return __ftrace_hash_update_ipmodify(ops, old_hash, new_hash);
+}
+
 static void print_ip_ins(const char *fmt, unsigned char *p)
 {
 	int i;
@@ -2436,6 +2562,15 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
 	 */
 	ops->flags |= FTRACE_OPS_FL_ENABLED | FTRACE_OPS_FL_ADDING;
 
+	ret = ftrace_hash_ipmodify_enable(ops);
+	if (ret < 0) {
+		/* Rollback registration process */
+		__unregister_ftrace_function(ops);
+		ftrace_start_up--;
+		ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+		return ret;
+	}
+
 	ftrace_hash_rec_enable(ops, 1);
 
 	ftrace_startup_enable(command);
@@ -2464,6 +2599,8 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	 */
 	WARN_ON_ONCE(ftrace_start_up < 0);
 
+	/* Disabling ipmodify never fails */
+	ftrace_hash_ipmodify_disable(ops);
 	ftrace_hash_rec_disable(ops, 1);
 
 	ops->flags &= ~FTRACE_OPS_FL_ENABLED;
@@ -3058,9 +3195,10 @@ static int t_show(struct seq_file *m, void *v)
 	if (iter->flags & FTRACE_ITER_ENABLED) {
 		struct ftrace_ops *ops = NULL;
 
-		seq_printf(m, " (%ld)%s",
+		seq_printf(m, " (%ld)%s%s",
 			   ftrace_rec_count(rec),
-			   rec->flags & FTRACE_FL_REGS ? " R" : "  ");
+			   rec->flags & FTRACE_FL_REGS ? " R" : "  ",
+			   rec->flags & FTRACE_FL_IPMODIFY ? " I" : "  ");
 		if (rec->flags & FTRACE_FL_TRAMP_EN) {
 			ops = ftrace_find_tramp_ops_any(rec);
 			if (ops)
-- 
cgit v1.2.3-70-g09d2


From 479163f4608214d18bc3266ab6e4b578897a3052 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@ZenIV.linux.org.uk>
Date: Thu, 20 Nov 2014 08:13:57 +0000
Subject: mlx5: don't duplicate kvfree()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx5/cq.c                     | 8 ++++----
 drivers/infiniband/hw/mlx5/mr.c                     | 4 ++--
 drivers/infiniband/hw/mlx5/qp.c                     | 8 ++++----
 drivers/infiniband/hw/mlx5/srq.c                    | 6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c        | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/port.c      | 4 ++--
 include/linux/mlx5/driver.h                         | 8 --------
 8 files changed, 19 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 10cfce5119a..c463e7bba5f 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -805,14 +805,14 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int entries,
 		}
 
 
-	mlx5_vfree(cqb);
+	kvfree(cqb);
 	return &cq->ibcq;
 
 err_cmd:
 	mlx5_core_destroy_cq(dev->mdev, &cq->mcq);
 
 err_cqb:
-	mlx5_vfree(cqb);
+	kvfree(cqb);
 	if (context)
 		destroy_cq_user(cq, context);
 	else
@@ -1159,11 +1159,11 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 	}
 	mutex_unlock(&cq->resize_mutex);
 
-	mlx5_vfree(in);
+	kvfree(in);
 	return 0;
 
 ex_alloc:
-	mlx5_vfree(in);
+	kvfree(in);
 
 ex_resize:
 	if (udata)
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 8ee7cb46e05..4c89b64aa9c 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -853,14 +853,14 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, u64 virt_addr,
 		goto err_2;
 	}
 	mr->umem = umem;
-	mlx5_vfree(in);
+	kvfree(in);
 
 	mlx5_ib_dbg(dev, "mkey = 0x%x\n", mr->mmr.key);
 
 	return mr;
 
 err_2:
-	mlx5_vfree(in);
+	kvfree(in);
 
 err_1:
 	kfree(mr);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index e261a53f9a0..0e2ef9fe0e2 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -647,7 +647,7 @@ err_unmap:
 	mlx5_ib_db_unmap_user(context, &qp->db);
 
 err_free:
-	mlx5_vfree(*in);
+	kvfree(*in);
 
 err_umem:
 	if (qp->umem)
@@ -761,7 +761,7 @@ err_wrid:
 	kfree(qp->rq.wrid);
 
 err_free:
-	mlx5_vfree(*in);
+	kvfree(*in);
 
 err_buf:
 	mlx5_buf_free(dev->mdev, &qp->buf);
@@ -971,7 +971,7 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 		goto err_create;
 	}
 
-	mlx5_vfree(in);
+	kvfree(in);
 	/* Hardware wants QPN written in big-endian order (after
 	 * shifting) for send doorbell.  Precompute this value to save
 	 * a little bit when posting sends.
@@ -988,7 +988,7 @@ err_create:
 	else if (qp->create_type == MLX5_QP_KERNEL)
 		destroy_qp_kernel(dev, qp);
 
-	mlx5_vfree(in);
+	kvfree(in);
 	return err;
 }
 
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 97cc1baaa8e..41fec66217d 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -141,7 +141,7 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
 	return 0;
 
 err_in:
-	mlx5_vfree(*in);
+	kvfree(*in);
 
 err_umem:
 	ib_umem_release(srq->umem);
@@ -209,7 +209,7 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
 	return 0;
 
 err_in:
-	mlx5_vfree(*in);
+	kvfree(*in);
 
 err_buf:
 	mlx5_buf_free(dev->mdev, &srq->buf);
@@ -306,7 +306,7 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 	in->ctx.pd = cpu_to_be32(to_mpd(pd)->pdn);
 	in->ctx.db_record = cpu_to_be64(srq->db.dma);
 	err = mlx5_core_create_srq(dev->mdev, &srq->msrq, in, inlen);
-	mlx5_vfree(in);
+	kvfree(in);
 	if (err) {
 		mlx5_ib_dbg(dev, "create SRQ failed, err %d\n", err);
 		goto err_usr_kern_srq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index ad2c96a02a5..dfd3ad0a39c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -390,7 +390,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	 */
 	eq_update_ci(eq, 1);
 
-	mlx5_vfree(in);
+	kvfree(in);
 	return 0;
 
 err_irq:
@@ -400,7 +400,7 @@ err_eq:
 	mlx5_cmd_destroy_eq(dev, eq->eqn);
 
 err_in:
-	mlx5_vfree(in);
+	kvfree(in);
 
 err_buf:
 	mlx5_buf_free(dev, &eq->buf);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index d476918ef26..4fdaae9b54d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -349,7 +349,7 @@ out_4k:
 	for (i--; i >= 0; i--)
 		free_4k(dev, be64_to_cpu(in->pas[i]));
 out_free:
-	mlx5_vfree(in);
+	kvfree(in);
 	return err;
 }
 
@@ -400,7 +400,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	}
 
 out_free:
-	mlx5_vfree(out);
+	kvfree(out);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 313965853e1..72c2d002c3b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -68,9 +68,9 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
 		memcpy(data_out, out->data, size_out);
 
 ex2:
-	mlx5_vfree(out);
+	kvfree(out);
 ex1:
-	mlx5_vfree(in);
+	kvfree(in);
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_core_access_reg);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 246310dc8be..b1bf41556b3 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -633,14 +633,6 @@ static inline void *mlx5_vzalloc(unsigned long size)
 	return rtn;
 }
 
-static inline void mlx5_vfree(const void *addr)
-{
-	if (addr && is_vmalloc_addr(addr))
-		vfree(addr);
-	else
-		kfree(addr);
-}
-
 static inline u32 mlx5_base_mkey(const u32 key)
 {
 	return key & 0xffffff00u;
-- 
cgit v1.2.3-70-g09d2


From 21f7eca555ad14e7c7b2cb59a6c6252e74ee5c8b Mon Sep 17 00:00:00 2001
From: "pang.xunlei" <pang.xunlei@linaro.org>
Date: Tue, 18 Nov 2014 19:15:16 +0800
Subject: time: Provide y2038 safe do_settimeofday() replacement

The kernel uses 32-bit signed value(time_t) for seconds elapsed
1970-01-01:00:00:00, thus it will overflow at 2038-01-19 03:14:08
on 32-bit systems. This is widely known as the y2038 problem.

As part of addressing "y2038 problem" for in-kernel uses, this patch
adds safe do_settimeofday64() using timespec64.

After this patch, do_settimeofday() is deprecated and all its call
sites will be fixed using do_settimeofday64(), after that it can be
removed.

Signed-off-by: pang.xunlei <pang.xunlei@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/timekeeping.h | 21 ++++++++++++++++++++-
 kernel/time/timekeeping.c   | 19 +++++++++----------
 2 files changed, 29 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 1caa6b04fdc..071ad7e0c98 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -10,7 +10,7 @@ extern int timekeeping_suspended;
  * Get and set timeofday
  */
 extern void do_gettimeofday(struct timeval *tv);
-extern int do_settimeofday(const struct timespec *tv);
+extern int do_settimeofday64(const struct timespec64 *ts);
 extern int do_sys_settimeofday(const struct timespec *tv,
 			       const struct timezone *tz);
 
@@ -33,6 +33,14 @@ extern int __getnstimeofday64(struct timespec64 *tv);
 extern void getnstimeofday64(struct timespec64 *tv);
 
 #if BITS_PER_LONG == 64
+/**
+ * Deprecated. Use do_settimeofday64().
+ */
+static inline int do_settimeofday(const struct timespec *ts)
+{
+	return do_settimeofday64(ts);
+}
+
 static inline int __getnstimeofday(struct timespec *ts)
 {
 	return __getnstimeofday64(ts);
@@ -54,6 +62,17 @@ static inline void ktime_get_real_ts(struct timespec *ts)
 }
 
 #else
+/**
+ * Deprecated. Use do_settimeofday64().
+ */
+static inline int do_settimeofday(const struct timespec *ts)
+{
+	struct timespec64 ts64;
+
+	ts64 = timespec_to_timespec64(*ts);
+	return do_settimeofday64(&ts64);
+}
+
 static inline int __getnstimeofday(struct timespec *ts)
 {
 	struct timespec64 ts64;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 41fcbe19ccf..10140dae71c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -703,18 +703,18 @@ void do_gettimeofday(struct timeval *tv)
 EXPORT_SYMBOL(do_gettimeofday);
 
 /**
- * do_settimeofday - Sets the time of day
- * @tv:		pointer to the timespec variable containing the new time
+ * do_settimeofday64 - Sets the time of day.
+ * @ts:     pointer to the timespec64 variable containing the new time
  *
  * Sets the time of day to the new time and update NTP and notify hrtimers
  */
-int do_settimeofday(const struct timespec *tv)
+int do_settimeofday64(const struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	struct timespec64 ts_delta, xt, tmp;
+	struct timespec64 ts_delta, xt;
 	unsigned long flags;
 
-	if (!timespec_valid_strict(tv))
+	if (!timespec64_valid_strict(ts))
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -723,13 +723,12 @@ int do_settimeofday(const struct timespec *tv)
 	timekeeping_forward_now(tk);
 
 	xt = tk_xtime(tk);
-	ts_delta.tv_sec = tv->tv_sec - xt.tv_sec;
-	ts_delta.tv_nsec = tv->tv_nsec - xt.tv_nsec;
+	ts_delta.tv_sec = ts->tv_sec - xt.tv_sec;
+	ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec;
 
 	tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta));
 
-	tmp = timespec_to_timespec64(*tv);
-	tk_set_xtime(tk, &tmp);
+	tk_set_xtime(tk, ts);
 
 	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
 
@@ -741,7 +740,7 @@ int do_settimeofday(const struct timespec *tv)
 
 	return 0;
 }
-EXPORT_SYMBOL(do_settimeofday);
+EXPORT_SYMBOL(do_settimeofday64);
 
 /**
  * timekeeping_inject_offset - Adds or subtracts from the current time.
-- 
cgit v1.2.3-70-g09d2


From 04d9089086a8231ddc69a9f3f25e971a3c1d25e6 Mon Sep 17 00:00:00 2001
From: "pang.xunlei" <pang.xunlei@linaro.org>
Date: Tue, 18 Nov 2014 19:15:17 +0800
Subject: time: Provide y2038 safe timekeeping_inject_sleeptime() replacement

As part of addressing "y2038 problem" for in-kernel uses, this
patch adds timekeeping_inject_sleeptime64() using timespec64.

After this patch, timekeeping_inject_sleeptime() is deprecated
and all its call sites will be fixed using the new interface,
after that it can be removed.

NOTE: timekeeping_inject_sleeptime() is safe actually, but we
want to eliminate timespec eventually, so comes this patch.

Signed-off-by: pang.xunlei <pang.xunlei@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/timekeeping.h | 13 ++++++++++++-
 kernel/time/timekeeping.c   | 10 ++++------
 2 files changed, 16 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 071ad7e0c98..6d76c650289 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -201,7 +201,18 @@ static inline void timekeeping_clocktai(struct timespec *ts)
 /*
  * RTC specific
  */
-extern void timekeeping_inject_sleeptime(struct timespec *delta);
+extern void timekeeping_inject_sleeptime64(struct timespec64 *delta);
+
+/**
+ * Deprecated. Use timekeeping_inject_sleeptime64().
+ */
+static inline void timekeeping_inject_sleeptime(struct timespec *delta)
+{
+	struct timespec64 delta64;
+
+	delta64 = timespec_to_timespec64(*delta);
+	timekeeping_inject_sleeptime64(&delta64);
+}
 
 /*
  * PPS accessor
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 10140dae71c..2bde974437f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1067,8 +1067,8 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
 }
 
 /**
- * timekeeping_inject_sleeptime - Adds suspend interval to timeekeeping values
- * @delta: pointer to a timespec delta value
+ * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values
+ * @delta: pointer to a timespec64 delta value
  *
  * This hook is for architectures that cannot support read_persistent_clock
  * because their RTC/persistent clock is only accessible when irqs are enabled.
@@ -1076,10 +1076,9 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
  * This function should only be called by rtc_resume(), and allows
  * a suspend offset to be injected into the timekeeping values.
  */
-void timekeeping_inject_sleeptime(struct timespec *delta)
+void timekeeping_inject_sleeptime64(struct timespec64 *delta)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	struct timespec64 tmp;
 	unsigned long flags;
 
 	/*
@@ -1094,8 +1093,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta)
 
 	timekeeping_forward_now(tk);
 
-	tmp = timespec_to_timespec64(*delta);
-	__timekeeping_inject_sleeptime(tk, &tmp);
+	__timekeeping_inject_sleeptime(tk, delta);
 
 	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
 
-- 
cgit v1.2.3-70-g09d2


From 90b6ce9c4066e0b2098dff65e52e6e7df1a51079 Mon Sep 17 00:00:00 2001
From: "pang.xunlei" <pang.xunlei@linaro.org>
Date: Tue, 18 Nov 2014 19:15:18 +0800
Subject: time: Provide y2038 safe mktime() replacement

As part of addressing "y2038 problem" for in-kernel uses, this
patch adds safe mktime64() using time64_t.

After this patch, mktime() is deprecated and all its call sites
will be fixed using mktime64(), after that it can be removed.

Signed-off-by: pang.xunlei <pang.xunlei@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/time.h | 17 ++++++++++++++---
 kernel/time/time.c   | 20 ++++++++------------
 2 files changed, 22 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/time.h b/include/linux/time.h
index 8c42cf8d244..203c2ad40d7 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -39,9 +39,20 @@ static inline int timeval_compare(const struct timeval *lhs, const struct timeva
 	return lhs->tv_usec - rhs->tv_usec;
 }
 
-extern unsigned long mktime(const unsigned int year, const unsigned int mon,
-			    const unsigned int day, const unsigned int hour,
-			    const unsigned int min, const unsigned int sec);
+extern time64_t mktime64(const unsigned int year, const unsigned int mon,
+			const unsigned int day, const unsigned int hour,
+			const unsigned int min, const unsigned int sec);
+
+/**
+ * Deprecated. Use mktime64().
+ */
+static inline unsigned long mktime(const unsigned int year,
+			const unsigned int mon, const unsigned int day,
+			const unsigned int hour, const unsigned int min,
+			const unsigned int sec)
+{
+	return mktime64(year, mon, day, hour, min, sec);
+}
 
 extern void set_normalized_timespec(struct timespec *ts, time_t sec, s64 nsec);
 
diff --git a/kernel/time/time.c b/kernel/time/time.c
index a9ae20fb0b1..65015ff2f07 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -304,7 +304,9 @@ struct timespec timespec_trunc(struct timespec t, unsigned gran)
 }
 EXPORT_SYMBOL(timespec_trunc);
 
-/* Converts Gregorian date to seconds since 1970-01-01 00:00:00.
+/*
+ * mktime64 - Converts date to seconds.
+ * Converts Gregorian date to seconds since 1970-01-01 00:00:00.
  * Assumes input in normal date format, i.e. 1980-12-31 23:59:59
  * => year=1980, mon=12, day=31, hour=23, min=59, sec=59.
  *
@@ -314,15 +316,10 @@ EXPORT_SYMBOL(timespec_trunc);
  * -year/100+year/400 terms, and add 10.]
  *
  * This algorithm was first published by Gauss (I think).
- *
- * WARNING: this function will overflow on 2106-02-07 06:28:16 on
- * machines where long is 32-bit! (However, as time_t is signed, we
- * will already get problems at other places on 2038-01-19 03:14:08)
  */
-unsigned long
-mktime(const unsigned int year0, const unsigned int mon0,
-       const unsigned int day, const unsigned int hour,
-       const unsigned int min, const unsigned int sec)
+time64_t mktime64(const unsigned int year0, const unsigned int mon0,
+		const unsigned int day, const unsigned int hour,
+		const unsigned int min, const unsigned int sec)
 {
 	unsigned int mon = mon0, year = year0;
 
@@ -332,15 +329,14 @@ mktime(const unsigned int year0, const unsigned int mon0,
 		year -= 1;
 	}
 
-	return ((((unsigned long)
+	return ((((time64_t)
 		  (year/4 - year/100 + year/400 + 367*mon/12 + day) +
 		  year*365 - 719499
 	    )*24 + hour /* now have hours */
 	  )*60 + min /* now have minutes */
 	)*60 + sec; /* finally seconds */
 }
-
-EXPORT_SYMBOL(mktime);
+EXPORT_SYMBOL(mktime64);
 
 /**
  * set_normalized_timespec - set timespec sec and nsec parts and normalize
-- 
cgit v1.2.3-70-g09d2


From cdba2ec538d9843c42cac15ff4ec54dc2ac53f8a Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Fri, 7 Nov 2014 11:03:20 -0800
Subject: time: Expose getrawmonotonic64 for in-kernel uses

Adds a timespec64 based getrawmonotonic64() implementation
that can be used as we convert internal users of
getrawmonotonic away from using timespecs.

Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/timekeeping.h | 15 ++++++++++++++-
 kernel/time/timekeeping.c   | 11 ++++++-----
 2 files changed, 20 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 6d76c650289..e40a8d60fb2 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -26,7 +26,7 @@ struct timespec __current_kernel_time(void);
  * timespec based interfaces
  */
 struct timespec get_monotonic_coarse(void);
-extern void getrawmonotonic(struct timespec *ts);
+extern void getrawmonotonic64(struct timespec64 *ts);
 extern void ktime_get_ts64(struct timespec64 *ts);
 
 extern int __getnstimeofday64(struct timespec64 *tv);
@@ -61,6 +61,11 @@ static inline void ktime_get_real_ts(struct timespec *ts)
 	getnstimeofday64(ts);
 }
 
+static inline void getrawmonotonic(struct timespec *ts)
+{
+	getrawmonotonic64(ts);
+}
+
 #else
 /**
  * Deprecated. Use do_settimeofday64().
@@ -105,6 +110,14 @@ static inline void ktime_get_real_ts(struct timespec *ts)
 	getnstimeofday64(&ts64);
 	*ts = timespec64_to_timespec(ts64);
 }
+
+static inline void getrawmonotonic(struct timespec *ts)
+{
+	struct timespec64 ts64;
+
+	getrawmonotonic64(&ts64);
+	*ts = timespec64_to_timespec(ts64);
+}
 #endif
 
 extern void getboottime(struct timespec *ts);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 2bde974437f..2e5f6321226 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -894,12 +894,12 @@ int timekeeping_notify(struct clocksource *clock)
 }
 
 /**
- * getrawmonotonic - Returns the raw monotonic time in a timespec
- * @ts:		pointer to the timespec to be set
+ * getrawmonotonic64 - Returns the raw monotonic time in a timespec
+ * @ts:		pointer to the timespec64 to be set
  *
  * Returns the raw monotonic time (completely un-modified by ntp)
  */
-void getrawmonotonic(struct timespec *ts)
+void getrawmonotonic64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct timespec64 ts64;
@@ -914,9 +914,10 @@ void getrawmonotonic(struct timespec *ts)
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
 	timespec64_add_ns(&ts64, nsecs);
-	*ts = timespec64_to_timespec(ts64);
+	*ts = ts64;
 }
-EXPORT_SYMBOL(getrawmonotonic);
+EXPORT_SYMBOL(getrawmonotonic64);
+
 
 /**
  * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres
-- 
cgit v1.2.3-70-g09d2


From 334334b5f577a2255e29d2352d53197d9b796511 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Fri, 7 Nov 2014 11:20:40 -0800
Subject: time: Expose get_monotonic_coarse64() for in-kernel uses

Adds a timespec64 based get_monotonic_coarse64() implementation
that can be used as we convert internal users of
get_monotonic_coarse away from using timespecs.

Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/timekeeping.h | 11 ++++++++++-
 kernel/time/timekeeping.c   |  4 ++--
 2 files changed, 12 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index e40a8d60fb2..8cab4b754be 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -25,7 +25,7 @@ struct timespec __current_kernel_time(void);
 /*
  * timespec based interfaces
  */
-struct timespec get_monotonic_coarse(void);
+struct timespec64 get_monotonic_coarse64(void);
 extern void getrawmonotonic64(struct timespec64 *ts);
 extern void ktime_get_ts64(struct timespec64 *ts);
 
@@ -66,6 +66,10 @@ static inline void getrawmonotonic(struct timespec *ts)
 	getrawmonotonic64(ts);
 }
 
+static inline struct timespec get_monotonic_coarse(void)
+{
+	return get_monotonic_coarse64();
+}
 #else
 /**
  * Deprecated. Use do_settimeofday64().
@@ -118,6 +122,11 @@ static inline void getrawmonotonic(struct timespec *ts)
 	getrawmonotonic64(&ts64);
 	*ts = timespec64_to_timespec(ts64);
 }
+
+static inline struct timespec get_monotonic_coarse(void)
+{
+	return timespec64_to_timespec(get_monotonic_coarse64());
+}
 #endif
 
 extern void getboottime(struct timespec *ts);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 2e5f6321226..f45e5e29a16 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1651,7 +1651,7 @@ struct timespec current_kernel_time(void)
 }
 EXPORT_SYMBOL(current_kernel_time);
 
-struct timespec get_monotonic_coarse(void)
+struct timespec64 get_monotonic_coarse64(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct timespec64 now, mono;
@@ -1667,7 +1667,7 @@ struct timespec get_monotonic_coarse(void)
 	set_normalized_timespec64(&now, now.tv_sec + mono.tv_sec,
 				now.tv_nsec + mono.tv_nsec);
 
-	return timespec64_to_timespec(now);
+	return now;
 }
 
 /*
-- 
cgit v1.2.3-70-g09d2


From c2c11ae4b6bc03b41720337028b940cbec9e316f Mon Sep 17 00:00:00 2001
From: "pang.xunlei" <pang.xunlei@linaro.org>
Date: Tue, 18 Nov 2014 19:15:19 +0800
Subject: rtc/lib: Provide y2038 safe rtc_tm_to_time()/rtc_time_to_tm()
 replacement

As part of addressing "y2038 problem" for in-kernel uses, this patch
adds safe rtc_tm_to_time64()/rtc_time64_to_tm() respectively using
time64_t.

After this patch, rtc_tm_to_time() is deprecated and all its call
sites will be fixed using corresponding safe versions, it can be
removed when having no users. Also change rtc_tm_to_time64() to
return time64_t directly instead of just as a parameter like
rtc_tm_to_time() does.

After this patch, rtc_time_to_tm() is deprecated and all its call
sites will be fixed using corresponding safe versions, it can be
removed when having no users.

In addition, change rtc_tm_to_ktime() and rtc_ktime_to_tm() to use
the safe version in passing.

Signed-off-by: pang.xunlei <pang.xunlei@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 drivers/rtc/rtc-lib.c | 38 ++++++++++++++++++++------------------
 include/linux/rtc.h   | 21 +++++++++++++++++++--
 2 files changed, 39 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/rtc/rtc-lib.c b/drivers/rtc/rtc-lib.c
index c4cf0573111..e6bfb9c42a1 100644
--- a/drivers/rtc/rtc-lib.c
+++ b/drivers/rtc/rtc-lib.c
@@ -45,16 +45,20 @@ int rtc_year_days(unsigned int day, unsigned int month, unsigned int year)
 }
 EXPORT_SYMBOL(rtc_year_days);
 
+
 /*
+ * rtc_time_to_tm64 - Converts time64_t to rtc_time.
  * Convert seconds since 01-01-1970 00:00:00 to Gregorian date.
  */
-void rtc_time_to_tm(unsigned long time, struct rtc_time *tm)
+void rtc_time64_to_tm(time64_t time, struct rtc_time *tm)
 {
 	unsigned int month, year;
+	unsigned long secs;
 	int days;
 
-	days = time / 86400;
-	time -= (unsigned int) days * 86400;
+	/* time must be positive */
+	days = div_s64(time, 86400);
+	secs = time - (unsigned int) days * 86400;
 
 	/* day of the week, 1970-01-01 was a Thursday */
 	tm->tm_wday = (days + 4) % 7;
@@ -81,14 +85,14 @@ void rtc_time_to_tm(unsigned long time, struct rtc_time *tm)
 	tm->tm_mon = month;
 	tm->tm_mday = days + 1;
 
-	tm->tm_hour = time / 3600;
-	time -= tm->tm_hour * 3600;
-	tm->tm_min = time / 60;
-	tm->tm_sec = time - tm->tm_min * 60;
+	tm->tm_hour = secs / 3600;
+	secs -= tm->tm_hour * 3600;
+	tm->tm_min = secs / 60;
+	tm->tm_sec = secs - tm->tm_min * 60;
 
 	tm->tm_isdst = 0;
 }
-EXPORT_SYMBOL(rtc_time_to_tm);
+EXPORT_SYMBOL(rtc_time64_to_tm);
 
 /*
  * Does the rtc_time represent a valid date/time?
@@ -109,24 +113,22 @@ int rtc_valid_tm(struct rtc_time *tm)
 EXPORT_SYMBOL(rtc_valid_tm);
 
 /*
+ * rtc_tm_to_time64 - Converts rtc_time to time64_t.
  * Convert Gregorian date to seconds since 01-01-1970 00:00:00.
  */
-int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time)
+time64_t rtc_tm_to_time64(struct rtc_time *tm)
 {
-	*time = mktime(tm->tm_year + 1900, tm->tm_mon + 1, tm->tm_mday,
+	return mktime64(tm->tm_year + 1900, tm->tm_mon + 1, tm->tm_mday,
 			tm->tm_hour, tm->tm_min, tm->tm_sec);
-	return 0;
 }
-EXPORT_SYMBOL(rtc_tm_to_time);
+EXPORT_SYMBOL(rtc_tm_to_time64);
 
 /*
  * Convert rtc_time to ktime
  */
 ktime_t rtc_tm_to_ktime(struct rtc_time tm)
 {
-	time_t time;
-	rtc_tm_to_time(&tm, &time);
-	return ktime_set(time, 0);
+	return ktime_set(rtc_tm_to_time64(&tm), 0);
 }
 EXPORT_SYMBOL_GPL(rtc_tm_to_ktime);
 
@@ -135,14 +137,14 @@ EXPORT_SYMBOL_GPL(rtc_tm_to_ktime);
  */
 struct rtc_time rtc_ktime_to_tm(ktime_t kt)
 {
-	struct timespec ts;
+	struct timespec64 ts;
 	struct rtc_time ret;
 
-	ts = ktime_to_timespec(kt);
+	ts = ktime_to_timespec64(kt);
 	/* Round up any ns */
 	if (ts.tv_nsec)
 		ts.tv_sec++;
-	rtc_time_to_tm(ts.tv_sec, &ret);
+	rtc_time64_to_tm(ts.tv_sec, &ret);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(rtc_ktime_to_tm);
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index c2c28975293..6d6be09a2fe 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -19,11 +19,28 @@
 extern int rtc_month_days(unsigned int month, unsigned int year);
 extern int rtc_year_days(unsigned int day, unsigned int month, unsigned int year);
 extern int rtc_valid_tm(struct rtc_time *tm);
-extern int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time);
-extern void rtc_time_to_tm(unsigned long time, struct rtc_time *tm);
+extern time64_t rtc_tm_to_time64(struct rtc_time *tm);
+extern void rtc_time64_to_tm(time64_t time, struct rtc_time *tm);
 ktime_t rtc_tm_to_ktime(struct rtc_time tm);
 struct rtc_time rtc_ktime_to_tm(ktime_t kt);
 
+/**
+ * Deprecated. Use rtc_time64_to_tm().
+ */
+static inline void rtc_time_to_tm(unsigned long time, struct rtc_time *tm)
+{
+	rtc_time64_to_tm(time, tm);
+}
+
+/**
+ * Deprecated. Use rtc_tm_to_time64().
+ */
+static inline int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time)
+{
+	*time = rtc_tm_to_time64(tm);
+
+	return 0;
+}
 
 #include <linux/device.h>
 #include <linux/seq_file.h>
-- 
cgit v1.2.3-70-g09d2


From 21b6c0512e8aca75ce76365e1aef9fb16e007100 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Thu, 20 Nov 2014 21:19:15 -0800
Subject: time: Remove timekeeping_inject_sleeptime()

Since all users have been converted to using the 64bit
timekeeping_inject_sleeptime64(), remove the old y2038
problematic timekeeping_inject_sleeptime().

Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/timekeeping.h | 11 -----------
 1 file changed, 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 8cab4b754be..961fea373f8 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -225,17 +225,6 @@ static inline void timekeeping_clocktai(struct timespec *ts)
  */
 extern void timekeeping_inject_sleeptime64(struct timespec64 *delta);
 
-/**
- * Deprecated. Use timekeeping_inject_sleeptime64().
- */
-static inline void timekeeping_inject_sleeptime(struct timespec *delta)
-{
-	struct timespec64 delta64;
-
-	delta64 = timespec_to_timespec64(*delta);
-	timekeeping_inject_sleeptime64(&delta64);
-}
-
 /*
  * PPS accessor
  */
-- 
cgit v1.2.3-70-g09d2


From 0655f6a8635b1b66f2434d5556b1044c14b1ccaf Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:07 +0100
Subject: tipc: add bearer disable/enable to new netlink api

A new netlink API for tipc that can disable or enable a tipc bearer.

The new API is separated from the old API because of a bug in the
user space client (tipc-config). The problem is that older versions
of tipc-config has a very low receive limit and adding commands to
the legacy genl_opts struct causes the ctrl_getfamily() response
message to grow, subsequently breaking the tool.

The new API utilizes netlink policies for input validation. Where the
top-level netlink attributes are tipc-logical entities, like bearer.
The top level entities then contain nested attributes. In this case
a name, nested link properties and a domain.

Netlink commands implemented in this patch:
TIPC_NL_BEARER_ENABLE
TIPC_NL_BEARER_DISABLE

Netlink logical layout of bearer enable message:
-> bearer
    -> name
    [ -> domain ]
    [
    -> properties
        -> priority
    ]

Netlink logical layout of bearer disable message:
-> bearer
    -> name

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h | 83 ++++++++++++++++++++++++++++++++
 net/tipc/bearer.c                 | 99 ++++++++++++++++++++++++++++++++++++++-
 net/tipc/bearer.h                 |  7 ++-
 net/tipc/core.h                   |  1 +
 net/tipc/link.c                   | 47 +++++++++++++++++++
 net/tipc/link.h                   |  3 ++
 net/tipc/netlink.c                | 42 ++++++++++++++++-
 net/tipc/netlink.h                | 41 ++++++++++++++++
 8 files changed, 320 insertions(+), 3 deletions(-)
 create mode 100644 include/uapi/linux/tipc_netlink.h
 create mode 100644 net/tipc/netlink.h

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
new file mode 100644
index 00000000000..b9b710faa22
--- /dev/null
+++ b/include/uapi/linux/tipc_netlink.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (c) 2014, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _LINUX_TIPC_NETLINK_H_
+#define _LINUX_TIPC_NETLINK_H_
+
+#define TIPC_GENL_V2_NAME      "TIPCv2"
+#define TIPC_GENL_V2_VERSION   0x1
+
+/* Netlink commands */
+enum {
+	TIPC_NL_UNSPEC,
+	TIPC_NL_LEGACY,
+	TIPC_NL_BEARER_DISABLE,
+	TIPC_NL_BEARER_ENABLE,
+
+	__TIPC_NL_CMD_MAX,
+	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
+};
+
+/* Top level netlink attributes */
+enum {
+	TIPC_NLA_UNSPEC,
+	TIPC_NLA_BEARER,		/* nest */
+
+	__TIPC_NLA_MAX,
+	TIPC_NLA_MAX = __TIPC_NLA_MAX - 1
+};
+
+/* Bearer info */
+enum {
+	TIPC_NLA_BEARER_UNSPEC,
+	TIPC_NLA_BEARER_NAME,		/* string */
+	TIPC_NLA_BEARER_PROP,		/* nest */
+	TIPC_NLA_BEARER_DOMAIN,		/* u32 */
+
+	__TIPC_NLA_BEARER_MAX,
+	TIPC_NLA_BEARER_MAX = __TIPC_NLA_BEARER_MAX - 1
+};
+
+/* Nest, link propreties. Valid for link, media and bearer */
+enum {
+	TIPC_NLA_PROP_UNSPEC,
+
+	TIPC_NLA_PROP_PRIO,		/* u32 */
+	TIPC_NLA_PROP_TOL,		/* u32 */
+	TIPC_NLA_PROP_WIN,		/* u32 */
+
+	__TIPC_NLA_PROP_MAX,
+	TIPC_NLA_PROP_MAX = __TIPC_NLA_PROP_MAX - 1
+};
+
+#endif
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 264474394f9..59815be0ab9 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/bearer.c: TIPC bearer code
  *
- * Copyright (c) 1996-2006, 2013, Ericsson AB
+ * Copyright (c) 1996-2006, 2013-2014, Ericsson AB
  * Copyright (c) 2004-2006, 2010-2013, Wind River Systems
  * All rights reserved.
  *
@@ -37,6 +37,7 @@
 #include "core.h"
 #include "config.h"
 #include "bearer.h"
+#include "link.h"
 #include "discover.h"
 
 #define MAX_ADDR_STR 60
@@ -49,6 +50,17 @@ static struct tipc_media * const media_info_array[] = {
 	NULL
 };
 
+static const struct nla_policy
+tipc_nl_bearer_policy[TIPC_NLA_BEARER_MAX + 1]	= {
+	[TIPC_NLA_BEARER_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_BEARER_NAME] = {
+		.type = NLA_STRING,
+		.len = TIPC_MAX_BEARER_NAME
+	},
+	[TIPC_NLA_BEARER_PROP]			= { .type = NLA_NESTED },
+	[TIPC_NLA_BEARER_DOMAIN]		= { .type = NLA_U32 }
+};
+
 struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1];
 
 static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down);
@@ -627,3 +639,88 @@ void tipc_bearer_stop(void)
 		}
 	}
 }
+
+int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	char *name;
+	struct tipc_bearer *bearer;
+	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
+
+	if (!info->attrs[TIPC_NLA_BEARER])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
+			       info->attrs[TIPC_NLA_BEARER],
+			       tipc_nl_bearer_policy);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_BEARER_NAME])
+		return -EINVAL;
+
+	name = nla_data(attrs[TIPC_NLA_BEARER_NAME]);
+
+	rtnl_lock();
+	bearer = tipc_bearer_find(name);
+	if (!bearer) {
+		rtnl_unlock();
+		return -EINVAL;
+	}
+
+	bearer_disable(bearer, false);
+	rtnl_unlock();
+
+	return 0;
+}
+
+int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	char *bearer;
+	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
+	u32 domain;
+	u32 prio;
+
+	prio = TIPC_MEDIA_LINK_PRI;
+	domain = tipc_own_addr & TIPC_CLUSTER_MASK;
+
+	if (!info->attrs[TIPC_NLA_BEARER])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
+			       info->attrs[TIPC_NLA_BEARER],
+			       tipc_nl_bearer_policy);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_BEARER_NAME])
+		return -EINVAL;
+
+	bearer = nla_data(attrs[TIPC_NLA_BEARER_NAME]);
+
+	if (attrs[TIPC_NLA_BEARER_DOMAIN])
+		domain = nla_get_u32(attrs[TIPC_NLA_BEARER_DOMAIN]);
+
+	if (attrs[TIPC_NLA_BEARER_PROP]) {
+		struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
+
+		err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_BEARER_PROP],
+					      props);
+		if (err)
+			return err;
+
+		if (props[TIPC_NLA_PROP_PRIO])
+			prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
+	}
+
+	rtnl_lock();
+	err = tipc_enable_bearer(bearer, domain, prio);
+	if (err) {
+		rtnl_unlock();
+		return err;
+	}
+	rtnl_unlock();
+
+	return 0;
+}
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index 78fccc49de2..a87e8c78d86 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/bearer.h: Include file for TIPC bearer code
  *
- * Copyright (c) 1996-2006, 2013, Ericsson AB
+ * Copyright (c) 1996-2006, 2013-2014, Ericsson AB
  * Copyright (c) 2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -38,6 +38,8 @@
 #define _TIPC_BEARER_H
 
 #include "bcast.h"
+#include "netlink.h"
+#include <net/genetlink.h>
 
 #define MAX_BEARERS	2
 #define MAX_MEDIA	2
@@ -176,6 +178,9 @@ extern struct tipc_media eth_media_info;
 extern struct tipc_media ib_media_info;
 #endif
 
+int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info);
+
 int tipc_media_set_priority(const char *name, u32 new_value);
 int tipc_media_set_window(const char *name, u32 new_value);
 void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a);
diff --git a/net/tipc/core.h b/net/tipc/core.h
index f773b148722..b578b10feef 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -41,6 +41,7 @@
 
 #include <linux/tipc.h>
 #include <linux/tipc_config.h>
+#include <linux/tipc_netlink.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 7cf8004577f..e7f365012bd 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -40,6 +40,7 @@
 #include "name_distr.h"
 #include "discover.h"
 #include "config.h"
+#include "netlink.h"
 
 #include <linux/pkt_sched.h>
 
@@ -50,6 +51,14 @@ static const char *link_co_err = "Link changeover error, ";
 static const char *link_rst_msg = "Resetting link ";
 static const char *link_unk_evt = "Unknown link event ";
 
+/* Properties valid for media, bearar and link */
+static const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = {
+	[TIPC_NLA_PROP_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_PROP_PRIO]		= { .type = NLA_U32 },
+	[TIPC_NLA_PROP_TOL]		= { .type = NLA_U32 },
+	[TIPC_NLA_PROP_WIN]		= { .type = NLA_U32 }
+};
+
 /*
  * Out-of-range value for link session numbers
  */
@@ -2376,3 +2385,41 @@ static void link_print(struct tipc_link *l_ptr, const char *str)
 	else
 		pr_cont("\n");
 }
+
+/* Parse and validate nested (link) properties valid for media, bearer and link
+ */
+int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[])
+{
+	int err;
+
+	err = nla_parse_nested(props, TIPC_NLA_PROP_MAX, prop,
+			       tipc_nl_prop_policy);
+	if (err)
+		return err;
+
+	if (props[TIPC_NLA_PROP_PRIO]) {
+		u32 prio;
+
+		prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
+		if (prio > TIPC_MAX_LINK_PRI)
+			return -EINVAL;
+	}
+
+	if (props[TIPC_NLA_PROP_TOL]) {
+		u32 tol;
+
+		tol = nla_get_u32(props[TIPC_NLA_PROP_TOL]);
+		if ((tol < TIPC_MIN_LINK_TOL) || (tol > TIPC_MAX_LINK_TOL))
+			return -EINVAL;
+	}
+
+	if (props[TIPC_NLA_PROP_WIN]) {
+		u32 win;
+
+		win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+		if ((win < TIPC_MIN_LINK_WIN) || (win > TIPC_MAX_LINK_WIN))
+			return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/net/tipc/link.h b/net/tipc/link.h
index b567a3427fd..4338294f20d 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -37,6 +37,7 @@
 #ifndef _TIPC_LINK_H
 #define _TIPC_LINK_H
 
+#include <net/genetlink.h>
 #include "msg.h"
 #include "node.h"
 
@@ -239,6 +240,8 @@ void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window);
 void tipc_link_retransmit(struct tipc_link *l_ptr,
 			  struct sk_buff *start, u32 retransmits);
 
+int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]);
+
 /*
  * Link sequence number manipulation routines (uses modulo 2**16 arithmetic)
  */
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index ad844d36534..af506ae0a12 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/netlink.c: TIPC configuration handling
  *
- * Copyright (c) 2005-2006, Ericsson AB
+ * Copyright (c) 2005-2006, 2014, Ericsson AB
  * Copyright (c) 2005-2007, Wind River Systems
  * All rights reserved.
  *
@@ -36,6 +36,7 @@
 
 #include "core.h"
 #include "config.h"
+#include "bearer.h"
 #include <net/genetlink.h>
 
 static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
@@ -68,6 +69,12 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
+static const struct nla_policy tipc_nl_policy[TIPC_NLA_MAX + 1] = {
+	[TIPC_NLA_UNSPEC]	= { .type = NLA_UNSPEC, },
+	[TIPC_NLA_BEARER]	= { .type = NLA_NESTED, },
+};
+
+/* Legacy ASCII API */
 static struct genl_family tipc_genl_family = {
 	.id		= GENL_ID_GENERATE,
 	.name		= TIPC_GENL_NAME,
@@ -76,6 +83,7 @@ static struct genl_family tipc_genl_family = {
 	.maxattr	= 0,
 };
 
+/* Legacy ASCII API */
 static struct genl_ops tipc_genl_ops[] = {
 	{
 		.cmd		= TIPC_GENL_CMD,
@@ -83,11 +91,42 @@ static struct genl_ops tipc_genl_ops[] = {
 	},
 };
 
+/* Users of the legacy API (tipc-config) can't handle that we add operations,
+ * so we have a separate genl handling for the new API.
+ */
+struct genl_family tipc_genl_v2_family = {
+	.id		= GENL_ID_GENERATE,
+	.name		= TIPC_GENL_V2_NAME,
+	.version	= TIPC_GENL_V2_VERSION,
+	.hdrsize	= 0,
+	.maxattr	= TIPC_NLA_MAX,
+};
+
+static const struct genl_ops tipc_genl_v2_ops[] = {
+	{
+		.cmd	= TIPC_NL_BEARER_DISABLE,
+		.doit	= tipc_nl_bearer_disable,
+		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_BEARER_ENABLE,
+		.doit	= tipc_nl_bearer_enable,
+		.policy = tipc_nl_policy,
+	}
+};
+
 int tipc_netlink_start(void)
 {
 	int res;
 
 	res = genl_register_family_with_ops(&tipc_genl_family, tipc_genl_ops);
+	if (res) {
+		pr_err("Failed to register legacy interface\n");
+		return res;
+	}
+
+	res = genl_register_family_with_ops(&tipc_genl_v2_family,
+					    tipc_genl_v2_ops);
 	if (res) {
 		pr_err("Failed to register netlink interface\n");
 		return res;
@@ -98,4 +137,5 @@ int tipc_netlink_start(void)
 void tipc_netlink_stop(void)
 {
 	genl_unregister_family(&tipc_genl_family);
+	genl_unregister_family(&tipc_genl_v2_family);
 }
diff --git a/net/tipc/netlink.h b/net/tipc/netlink.h
new file mode 100644
index 00000000000..e9980c0e220
--- /dev/null
+++ b/net/tipc/netlink.h
@@ -0,0 +1,41 @@
+/*
+ * net/tipc/netlink.h: Include file for TIPC netlink code
+ *
+ * Copyright (c) 2014, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_NETLINK_H
+#define _TIPC_NETLINK_H
+
+extern struct genl_family tipc_genl_v2_family;
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From 35b9dd7607f049466a66427e58818b29aeae9ea7 Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:08 +0100
Subject: tipc: add bearer get/dump to new netlink api

Add TIPC_NL_BEARER_GET command to the new tipc netlink API.

This command supports dumping all data about all bearers or getting
all information about a specific bearer.

The information about a bearer includes name, link priorities and
domain.

Netlink logical layout of bearer get message:
-> bearer
    -> name

Netlink logical layout of returned bearer information:
-> bearer
    -> name
    -> link properties
        -> priority
        -> tolerance
        -> window
    -> domain

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h |   1 +
 net/tipc/bearer.c                 | 125 ++++++++++++++++++++++++++++++++++++++
 net/tipc/bearer.h                 |   2 +
 net/tipc/netlink.c                |   6 ++
 net/tipc/netlink.h                |   6 ++
 5 files changed, 140 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index b9b710faa22..249ec7e9952 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -43,6 +43,7 @@ enum {
 	TIPC_NL_LEGACY,
 	TIPC_NL_BEARER_DISABLE,
 	TIPC_NL_BEARER_ENABLE,
+	TIPC_NL_BEARER_GET,
 
 	__TIPC_NL_CMD_MAX,
 	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 59815be0ab9..d49b8c25dd1 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -640,6 +640,131 @@ void tipc_bearer_stop(void)
 	}
 }
 
+/* Caller should hold rtnl_lock to protect the bearer */
+int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, struct tipc_bearer *bearer)
+{
+	void *hdr;
+	struct nlattr *attrs;
+	struct nlattr *prop;
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_v2_family,
+			  NLM_F_MULTI, TIPC_NL_BEARER_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start(msg->skb, TIPC_NLA_BEARER);
+	if (!attrs)
+		goto msg_full;
+
+	if (nla_put_string(msg->skb, TIPC_NLA_BEARER_NAME, bearer->name))
+		goto attr_msg_full;
+
+	prop = nla_nest_start(msg->skb, TIPC_NLA_BEARER_PROP);
+	if (!prop)
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, bearer->priority))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, bearer->tolerance))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bearer->window))
+		goto prop_msg_full;
+
+	nla_nest_end(msg->skb, prop);
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+prop_msg_full:
+	nla_nest_cancel(msg->skb, prop);
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int err;
+	int i = cb->args[0];
+	struct tipc_bearer *bearer;
+	struct tipc_nl_msg msg;
+
+	if (i == MAX_BEARERS)
+		return 0;
+
+	msg.skb = skb;
+	msg.portid = NETLINK_CB(cb->skb).portid;
+	msg.seq = cb->nlh->nlmsg_seq;
+
+	rtnl_lock();
+	for (i = 0; i < MAX_BEARERS; i++) {
+		bearer = rtnl_dereference(bearer_list[i]);
+		if (!bearer)
+			continue;
+
+		err = __tipc_nl_add_bearer(&msg, bearer);
+		if (err)
+			break;
+	}
+	rtnl_unlock();
+
+	cb->args[0] = i;
+	return skb->len;
+}
+
+int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	char *name;
+	struct sk_buff *rep;
+	struct tipc_bearer *bearer;
+	struct tipc_nl_msg msg;
+	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
+
+	if (!info->attrs[TIPC_NLA_BEARER])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
+			       info->attrs[TIPC_NLA_BEARER],
+			       tipc_nl_bearer_policy);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_BEARER_NAME])
+		return -EINVAL;
+	name = nla_data(attrs[TIPC_NLA_BEARER_NAME]);
+
+	rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!rep)
+		return -ENOMEM;
+
+	msg.skb = rep;
+	msg.portid = info->snd_portid;
+	msg.seq = info->snd_seq;
+
+	rtnl_lock();
+	bearer = tipc_bearer_find(name);
+	if (!bearer) {
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	err = __tipc_nl_add_bearer(&msg, bearer);
+	if (err)
+		goto err_out;
+	rtnl_unlock();
+
+	return genlmsg_reply(rep, info);
+err_out:
+	rtnl_unlock();
+	nlmsg_free(rep);
+
+	return err;
+}
+
 int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info)
 {
 	int err;
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index a87e8c78d86..2d07e35f91f 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -180,6 +180,8 @@ extern struct tipc_media ib_media_info;
 
 int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info);
 int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info);
 
 int tipc_media_set_priority(const char *name, u32 new_value);
 int tipc_media_set_window(const char *name, u32 new_value);
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index af506ae0a12..0c00422512f 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -112,6 +112,12 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 		.cmd	= TIPC_NL_BEARER_ENABLE,
 		.doit	= tipc_nl_bearer_enable,
 		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_BEARER_GET,
+		.doit	= tipc_nl_bearer_get,
+		.dumpit	= tipc_nl_bearer_dump,
+		.policy = tipc_nl_policy,
 	}
 };
 
diff --git a/net/tipc/netlink.h b/net/tipc/netlink.h
index e9980c0e220..e34a3fca7d3 100644
--- a/net/tipc/netlink.h
+++ b/net/tipc/netlink.h
@@ -38,4 +38,10 @@
 
 extern struct genl_family tipc_genl_v2_family;
 
+struct tipc_nl_msg {
+	struct sk_buff *skb;
+	u32 portid;
+	u32 seq;
+};
+
 #endif
-- 
cgit v1.2.3-70-g09d2


From 315c00bc9f2bd17f7ad7ed8119ca49b1125af507 Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:09 +0100
Subject: tipc: add bearer set to new netlink api

Add TIPC_NL_BEARER_SET command to the new tipc netlink API.

This command can set one or more link properties for a particular
bearer.

Netlink logical layout of bearer set message:
-> bearer
    -> name
    -> link properties
        [ -> tolerance ]
        [ -> priority ]
        [ -> window ]

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h |  1 +
 net/tipc/bearer.c                 | 49 +++++++++++++++++++++++++++++++++++++++
 net/tipc/bearer.h                 |  1 +
 net/tipc/netlink.c                |  5 ++++
 4 files changed, 56 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index 249ec7e9952..f446fba6a0c 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -44,6 +44,7 @@ enum {
 	TIPC_NL_BEARER_DISABLE,
 	TIPC_NL_BEARER_ENABLE,
 	TIPC_NL_BEARER_GET,
+	TIPC_NL_BEARER_SET,
 
 	__TIPC_NL_CMD_MAX,
 	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index d49b8c25dd1..6d547d0b3f3 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -849,3 +849,52 @@ int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info)
 
 	return 0;
 }
+
+int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	char *name;
+	struct tipc_bearer *b;
+	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
+
+	if (!info->attrs[TIPC_NLA_BEARER])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
+			       info->attrs[TIPC_NLA_BEARER],
+			       tipc_nl_bearer_policy);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_BEARER_NAME])
+		return -EINVAL;
+	name = nla_data(attrs[TIPC_NLA_BEARER_NAME]);
+
+	rtnl_lock();
+	b = tipc_bearer_find(name);
+	if (!b) {
+		rtnl_unlock();
+		return -EINVAL;
+	}
+
+	if (attrs[TIPC_NLA_BEARER_PROP]) {
+		struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
+
+		err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_BEARER_PROP],
+					      props);
+		if (err) {
+			rtnl_unlock();
+			return err;
+		}
+
+		if (props[TIPC_NLA_PROP_TOL])
+			b->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]);
+		if (props[TIPC_NLA_PROP_PRIO])
+			b->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
+		if (props[TIPC_NLA_PROP_WIN])
+			b->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+	}
+	rtnl_unlock();
+
+	return 0;
+}
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index 2d07e35f91f..c6cf9df3137 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -182,6 +182,7 @@ int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info);
 int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info);
 int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb);
 int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info);
 
 int tipc_media_set_priority(const char *name, u32 new_value);
 int tipc_media_set_window(const char *name, u32 new_value);
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 0c00422512f..a5291314a21 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -118,6 +118,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 		.doit	= tipc_nl_bearer_get,
 		.dumpit	= tipc_nl_bearer_dump,
 		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_BEARER_SET,
+		.doit	= tipc_nl_bearer_set,
+		.policy = tipc_nl_policy,
 	}
 };
 
-- 
cgit v1.2.3-70-g09d2


From 34b78a127c4fd57cf3d5c64031693d10a8e0fae1 Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:10 +0100
Subject: tipc: add sock dump to new netlink api

Add TIPC_NL_SOCK_GET command to the new tipc netlink API.

This command supports dumping of all available sockets with their
associated connection or publication(s). It could be extended to reply
with a single socket if the NLM_F_DUMP isn't set.

The information about a socket includes reference, address, connection
information / publication information.

Netlink logical layout of response message:
-> socket
    -> reference
    -> address
    [
    -> connection
        -> node
        -> socket
        [
        -> connected flag
        -> type
        -> instance
        ]
    ]
    [
    -> publication flag
    ]

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h |  28 +++++++++++
 net/tipc/netlink.c                |   7 +++
 net/tipc/socket.c                 | 101 ++++++++++++++++++++++++++++++++++++++
 net/tipc/socket.h                 |   2 +
 4 files changed, 138 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index f446fba6a0c..8c87e2490bc 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -45,6 +45,7 @@ enum {
 	TIPC_NL_BEARER_ENABLE,
 	TIPC_NL_BEARER_GET,
 	TIPC_NL_BEARER_SET,
+	TIPC_NL_SOCK_GET,
 
 	__TIPC_NL_CMD_MAX,
 	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
@@ -54,6 +55,7 @@ enum {
 enum {
 	TIPC_NLA_UNSPEC,
 	TIPC_NLA_BEARER,		/* nest */
+	TIPC_NLA_SOCK,			/* nest */
 
 	__TIPC_NLA_MAX,
 	TIPC_NLA_MAX = __TIPC_NLA_MAX - 1
@@ -70,6 +72,32 @@ enum {
 	TIPC_NLA_BEARER_MAX = __TIPC_NLA_BEARER_MAX - 1
 };
 
+/* Socket info */
+enum {
+	TIPC_NLA_SOCK_UNSPEC,
+	TIPC_NLA_SOCK_ADDR,		/* u32 */
+	TIPC_NLA_SOCK_REF,		/* u32 */
+	TIPC_NLA_SOCK_CON,		/* nest */
+	TIPC_NLA_SOCK_HAS_PUBL,		/* flag */
+
+	__TIPC_NLA_SOCK_MAX,
+	TIPC_NLA_SOCK_MAX = __TIPC_NLA_SOCK_MAX - 1
+};
+
+/* Nest, connection info */
+enum {
+	TIPC_NLA_CON_UNSPEC,
+
+	TIPC_NLA_CON_FLAG,		/* flag */
+	TIPC_NLA_CON_NODE,		/* u32 */
+	TIPC_NLA_CON_SOCK,		/* u32 */
+	TIPC_NLA_CON_TYPE,		/* u32 */
+	TIPC_NLA_CON_INST,		/* u32 */
+
+	__TIPC_NLA_CON_MAX,
+	TIPC_NLA_CON_MAX = __TIPC_NLA_CON_MAX - 1
+};
+
 /* Nest, link propreties. Valid for link, media and bearer */
 enum {
 	TIPC_NLA_PROP_UNSPEC,
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index a5291314a21..951fabeec8b 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -36,6 +36,7 @@
 
 #include "core.h"
 #include "config.h"
+#include "socket.h"
 #include "bearer.h"
 #include <net/genetlink.h>
 
@@ -72,6 +73,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
 static const struct nla_policy tipc_nl_policy[TIPC_NLA_MAX + 1] = {
 	[TIPC_NLA_UNSPEC]	= { .type = NLA_UNSPEC, },
 	[TIPC_NLA_BEARER]	= { .type = NLA_NESTED, },
+	[TIPC_NLA_SOCK]		= { .type = NLA_NESTED, },
 };
 
 /* Legacy ASCII API */
@@ -123,6 +125,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 		.cmd	= TIPC_NL_BEARER_SET,
 		.doit	= tipc_nl_bearer_set,
 		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_SOCK_GET,
+		.dumpit	= tipc_nl_sk_dump,
+		.policy = tipc_nl_policy,
 	}
 };
 
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 591bbfa082a..9e95c1ea556 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2801,3 +2801,104 @@ void tipc_socket_stop(void)
 	sock_unregister(tipc_family_ops.family);
 	proto_unregister(&tipc_proto);
 }
+
+/* Caller should hold socket lock for the passed tipc socket. */
+int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk)
+{
+	u32 peer_node;
+	u32 peer_port;
+	struct nlattr *nest;
+
+	peer_node = tsk_peer_node(tsk);
+	peer_port = tsk_peer_port(tsk);
+
+	nest = nla_nest_start(skb, TIPC_NLA_SOCK_CON);
+
+	if (nla_put_u32(skb, TIPC_NLA_CON_NODE, peer_node))
+		goto msg_full;
+	if (nla_put_u32(skb, TIPC_NLA_CON_SOCK, peer_port))
+		goto msg_full;
+
+	if (tsk->conn_type != 0) {
+		if (nla_put_flag(skb, TIPC_NLA_CON_FLAG))
+			goto msg_full;
+		if (nla_put_u32(skb, TIPC_NLA_CON_TYPE, tsk->conn_type))
+			goto msg_full;
+		if (nla_put_u32(skb, TIPC_NLA_CON_INST, tsk->conn_instance))
+			goto msg_full;
+	}
+	nla_nest_end(skb, nest);
+
+	return 0;
+
+msg_full:
+	nla_nest_cancel(skb, nest);
+
+	return -EMSGSIZE;
+}
+
+/* Caller should hold socket lock for the passed tipc socket. */
+int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb,
+		     struct tipc_sock *tsk)
+{
+	int err;
+	void *hdr;
+	struct nlattr *attrs;
+
+	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &tipc_genl_v2_family, NLM_F_MULTI, TIPC_NL_SOCK_GET);
+	if (!hdr)
+		goto msg_cancel;
+
+	attrs = nla_nest_start(skb, TIPC_NLA_SOCK);
+	if (!attrs)
+		goto genlmsg_cancel;
+	if (nla_put_u32(skb, TIPC_NLA_SOCK_REF, tsk->ref))
+		goto attr_msg_cancel;
+	if (nla_put_u32(skb, TIPC_NLA_SOCK_ADDR, tipc_own_addr))
+		goto attr_msg_cancel;
+
+	if (tsk->connected) {
+		err = __tipc_nl_add_sk_con(skb, tsk);
+		if (err)
+			goto attr_msg_cancel;
+	} else if (!list_empty(&tsk->publications)) {
+		if (nla_put_flag(skb, TIPC_NLA_SOCK_HAS_PUBL))
+			goto attr_msg_cancel;
+	}
+	nla_nest_end(skb, attrs);
+	genlmsg_end(skb, hdr);
+
+	return 0;
+
+attr_msg_cancel:
+	nla_nest_cancel(skb, attrs);
+genlmsg_cancel:
+	genlmsg_cancel(skb, hdr);
+msg_cancel:
+	return -EMSGSIZE;
+}
+
+int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int err;
+	struct tipc_sock *tsk;
+	u32 prev_ref = cb->args[0];
+	u32 ref = prev_ref;
+
+	tsk = tipc_sk_get_next(&ref);
+	for (; tsk; tsk = tipc_sk_get_next(&ref)) {
+		lock_sock(&tsk->sk);
+		err = __tipc_nl_add_sk(skb, cb, tsk);
+		release_sock(&tsk->sk);
+		tipc_sk_put(tsk);
+		if (err)
+			break;
+
+		prev_ref = ref;
+	}
+
+	cb->args[0] = prev_ref;
+
+	return skb->len;
+}
diff --git a/net/tipc/socket.h b/net/tipc/socket.h
index baa43d03901..16dfd62983a 100644
--- a/net/tipc/socket.h
+++ b/net/tipc/socket.h
@@ -36,6 +36,7 @@
 #define _TIPC_SOCK_H
 
 #include <net/sock.h>
+#include <net/genetlink.h>
 
 #define TIPC_CONNACK_INTV         256
 #define TIPC_FLOWCTRL_WIN        (TIPC_CONNACK_INTV * 2)
@@ -47,5 +48,6 @@ void tipc_sk_mcast_rcv(struct sk_buff *buf);
 void tipc_sk_reinit(void);
 int tipc_sk_ref_table_init(u32 requested_size, u32 start);
 void tipc_sk_ref_table_stop(void);
+int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb);
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From 1a1a143daf84db95dd7212086042004a3abb7bc2 Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:11 +0100
Subject: tipc: add publication dump to new netlink api

Add TIPC_NL_PUBL_GET command to the new tipc netlink API.

This command supports dumping of all publications for a specific
socket.

Netlink logical layout of request message:
    -> socket
        -> reference

Netlink logical layout of response message:
    -> publication
        -> type
        -> lower
        -> upper

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h |  18 +++++
 net/tipc/netlink.c                |  17 +++++
 net/tipc/netlink.h                |   1 +
 net/tipc/socket.c                 | 135 ++++++++++++++++++++++++++++++++++++++
 net/tipc/socket.h                 |   1 +
 5 files changed, 172 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index 8c87e2490bc..7e51ff61dcc 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -46,6 +46,7 @@ enum {
 	TIPC_NL_BEARER_GET,
 	TIPC_NL_BEARER_SET,
 	TIPC_NL_SOCK_GET,
+	TIPC_NL_PUBL_GET,
 
 	__TIPC_NL_CMD_MAX,
 	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
@@ -56,6 +57,7 @@ enum {
 	TIPC_NLA_UNSPEC,
 	TIPC_NLA_BEARER,		/* nest */
 	TIPC_NLA_SOCK,			/* nest */
+	TIPC_NLA_PUBL,			/* nest */
 
 	__TIPC_NLA_MAX,
 	TIPC_NLA_MAX = __TIPC_NLA_MAX - 1
@@ -84,6 +86,22 @@ enum {
 	TIPC_NLA_SOCK_MAX = __TIPC_NLA_SOCK_MAX - 1
 };
 
+/* Publication info */
+enum {
+	TIPC_NLA_PUBL_UNSPEC,
+
+	TIPC_NLA_PUBL_TYPE,		/* u32 */
+	TIPC_NLA_PUBL_LOWER,		/* u32 */
+	TIPC_NLA_PUBL_UPPER,		/* u32 */
+	TIPC_NLA_PUBL_SCOPE,		/* u32 */
+	TIPC_NLA_PUBL_NODE,		/* u32 */
+	TIPC_NLA_PUBL_REF,		/* u32 */
+	TIPC_NLA_PUBL_KEY,		/* u32 */
+
+	__TIPC_NLA_PUBL_MAX,
+	TIPC_NLA_PUBL_MAX = __TIPC_NLA_PUBL_MAX - 1
+};
+
 /* Nest, connection info */
 enum {
 	TIPC_NLA_CON_UNSPEC,
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 951fabeec8b..9bc64aaff46 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -74,6 +74,7 @@ static const struct nla_policy tipc_nl_policy[TIPC_NLA_MAX + 1] = {
 	[TIPC_NLA_UNSPEC]	= { .type = NLA_UNSPEC, },
 	[TIPC_NLA_BEARER]	= { .type = NLA_NESTED, },
 	[TIPC_NLA_SOCK]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_PUBL]		= { .type = NLA_NESTED, }
 };
 
 /* Legacy ASCII API */
@@ -130,9 +131,25 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 		.cmd	= TIPC_NL_SOCK_GET,
 		.dumpit	= tipc_nl_sk_dump,
 		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_PUBL_GET,
+		.dumpit	= tipc_nl_publ_dump,
+		.policy = tipc_nl_policy,
 	}
 };
 
+int tipc_nlmsg_parse(const struct nlmsghdr *nlh, struct nlattr ***attr)
+{
+	u32 maxattr = tipc_genl_v2_family.maxattr;
+
+	*attr = tipc_genl_v2_family.attrbuf;
+	if (!*attr)
+		return -EOPNOTSUPP;
+
+	return nlmsg_parse(nlh, GENL_HDRLEN, *attr, maxattr, tipc_nl_policy);
+}
+
 int tipc_netlink_start(void)
 {
 	int res;
diff --git a/net/tipc/netlink.h b/net/tipc/netlink.h
index e34a3fca7d3..1425c6869de 100644
--- a/net/tipc/netlink.h
+++ b/net/tipc/netlink.h
@@ -37,6 +37,7 @@
 #define _TIPC_NETLINK_H
 
 extern struct genl_family tipc_genl_v2_family;
+int tipc_nlmsg_parse(const struct nlmsghdr *nlh, struct nlattr ***buf);
 
 struct tipc_nl_msg {
 	struct sk_buff *skb;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 9e95c1ea556..e91809182c2 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -121,6 +121,14 @@ static const struct proto_ops msg_ops;
 static struct proto tipc_proto;
 static struct proto tipc_proto_kern;
 
+static const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = {
+	[TIPC_NLA_SOCK_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_SOCK_ADDR]		= { .type = NLA_U32 },
+	[TIPC_NLA_SOCK_REF]		= { .type = NLA_U32 },
+	[TIPC_NLA_SOCK_CON]		= { .type = NLA_NESTED },
+	[TIPC_NLA_SOCK_HAS_PUBL]	= { .type = NLA_FLAG }
+};
+
 /*
  * Revised TIPC socket locking policy:
  *
@@ -2902,3 +2910,130 @@ int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 	return skb->len;
 }
+
+/* Caller should hold socket lock for the passed tipc socket. */
+int __tipc_nl_add_sk_publ(struct sk_buff *skb, struct netlink_callback *cb,
+			  struct publication *publ)
+{
+	void *hdr;
+	struct nlattr *attrs;
+
+	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &tipc_genl_v2_family, NLM_F_MULTI, TIPC_NL_PUBL_GET);
+	if (!hdr)
+		goto msg_cancel;
+
+	attrs = nla_nest_start(skb, TIPC_NLA_PUBL);
+	if (!attrs)
+		goto genlmsg_cancel;
+
+	if (nla_put_u32(skb, TIPC_NLA_PUBL_KEY, publ->key))
+		goto attr_msg_cancel;
+	if (nla_put_u32(skb, TIPC_NLA_PUBL_TYPE, publ->type))
+		goto attr_msg_cancel;
+	if (nla_put_u32(skb, TIPC_NLA_PUBL_LOWER, publ->lower))
+		goto attr_msg_cancel;
+	if (nla_put_u32(skb, TIPC_NLA_PUBL_UPPER, publ->upper))
+		goto attr_msg_cancel;
+
+	nla_nest_end(skb, attrs);
+	genlmsg_end(skb, hdr);
+
+	return 0;
+
+attr_msg_cancel:
+	nla_nest_cancel(skb, attrs);
+genlmsg_cancel:
+	genlmsg_cancel(skb, hdr);
+msg_cancel:
+	return -EMSGSIZE;
+}
+
+/* Caller should hold socket lock for the passed tipc socket. */
+int __tipc_nl_list_sk_publ(struct sk_buff *skb, struct netlink_callback *cb,
+			   struct tipc_sock *tsk, u32 *last_publ)
+{
+	int err;
+	struct publication *p;
+
+	if (*last_publ) {
+		list_for_each_entry(p, &tsk->publications, pport_list) {
+			if (p->key == *last_publ)
+				break;
+		}
+		if (p->key != *last_publ) {
+			/* We never set seq or call nl_dump_check_consistent()
+			 * this means that setting prev_seq here will cause the
+			 * consistence check to fail in the netlink callback
+			 * handler. Resulting in the last NLMSG_DONE message
+			 * having the NLM_F_DUMP_INTR flag set.
+			 */
+			cb->prev_seq = 1;
+			*last_publ = 0;
+			return -EPIPE;
+		}
+	} else {
+		p = list_first_entry(&tsk->publications, struct publication,
+				     pport_list);
+	}
+
+	list_for_each_entry_from(p, &tsk->publications, pport_list) {
+		err = __tipc_nl_add_sk_publ(skb, cb, p);
+		if (err) {
+			*last_publ = p->key;
+			return err;
+		}
+	}
+	*last_publ = 0;
+
+	return 0;
+}
+
+int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int err;
+	u32 tsk_ref = cb->args[0];
+	u32 last_publ = cb->args[1];
+	u32 done = cb->args[2];
+	struct tipc_sock *tsk;
+
+	if (!tsk_ref) {
+		struct nlattr **attrs;
+		struct nlattr *sock[TIPC_NLA_SOCK_MAX + 1];
+
+		err = tipc_nlmsg_parse(cb->nlh, &attrs);
+		if (err)
+			return err;
+
+		err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX,
+				       attrs[TIPC_NLA_SOCK],
+				       tipc_nl_sock_policy);
+		if (err)
+			return err;
+
+		if (!sock[TIPC_NLA_SOCK_REF])
+			return -EINVAL;
+
+		tsk_ref = nla_get_u32(sock[TIPC_NLA_SOCK_REF]);
+	}
+
+	if (done)
+		return 0;
+
+	tsk = tipc_sk_get(tsk_ref);
+	if (!tsk)
+		return -EINVAL;
+
+	lock_sock(&tsk->sk);
+	err = __tipc_nl_list_sk_publ(skb, cb, tsk, &last_publ);
+	if (!err)
+		done = 1;
+	release_sock(&tsk->sk);
+	tipc_sk_put(tsk);
+
+	cb->args[0] = tsk_ref;
+	cb->args[1] = last_publ;
+	cb->args[2] = done;
+
+	return skb->len;
+}
diff --git a/net/tipc/socket.h b/net/tipc/socket.h
index 16dfd62983a..d3408938700 100644
--- a/net/tipc/socket.h
+++ b/net/tipc/socket.h
@@ -49,5 +49,6 @@ void tipc_sk_reinit(void);
 int tipc_sk_ref_table_init(u32 requested_size, u32 start);
 void tipc_sk_ref_table_stop(void);
 int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb);
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From 7be57fc6918470ecacd16b89c0d4f73d8fc265c4 Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:12 +0100
Subject: tipc: add link get/dump to new netlink api

Add TIPC_NL_LINK_GET command to the new tipc netlink API.

This command supports dumping all information about all links
(including the broadcast link) or getting all information about a
specific link (not the broadcast link).

The information about a link includes name, transmission info,
properties and link statistics.

As the tipc broadcast link is special we unfortunately have to treat
it specially. It is a deliberate decision not to abstract the
broadcast link on this (API) level.

Netlink logical layout of link response message:
    -> port
        -> name
        -> MTU
        -> RX
        -> TX
        -> up flag
        -> active flag
        -> properties
           -> priority
           -> tolerance
           -> window
        -> statistics
            -> rx_info
            -> rx_fragments
            -> rx_fragmented
            -> rx_bundles
            -> rx_bundled
            -> tx_info
            -> tx_fragments
            -> tx_fragmented
            -> tx_bundles
            -> tx_bundled
            -> msg_prof_tot
            -> msg_len_cnt
            -> msg_len_tot
            -> msg_len_p0
            -> msg_len_p1
            -> msg_len_p2
            -> msg_len_p3
            -> msg_len_p4
            -> msg_len_p5
            -> msg_len_p6
            -> rx_states
            -> rx_probes
            -> rx_nacks
            -> rx_deferred
            -> tx_states
            -> tx_probes
            -> tx_nacks
            -> tx_acks
            -> retransmitted
            -> duplicates
            -> link_congs
            -> max_queue
            -> avg_queue

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h |  62 ++++++++
 net/tipc/bcast.c                  | 111 +++++++++++++++
 net/tipc/bcast.h                  |   4 +
 net/tipc/link.c                   | 287 ++++++++++++++++++++++++++++++++++++++
 net/tipc/link.h                   |   2 +
 net/tipc/netlink.c                |  10 +-
 6 files changed, 475 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index 7e51ff61dcc..1034fb43d32 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -47,6 +47,7 @@ enum {
 	TIPC_NL_BEARER_SET,
 	TIPC_NL_SOCK_GET,
 	TIPC_NL_PUBL_GET,
+	TIPC_NL_LINK_GET,
 
 	__TIPC_NL_CMD_MAX,
 	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
@@ -58,6 +59,7 @@ enum {
 	TIPC_NLA_BEARER,		/* nest */
 	TIPC_NLA_SOCK,			/* nest */
 	TIPC_NLA_PUBL,			/* nest */
+	TIPC_NLA_LINK,			/* nest */
 
 	__TIPC_NLA_MAX,
 	TIPC_NLA_MAX = __TIPC_NLA_MAX - 1
@@ -86,6 +88,24 @@ enum {
 	TIPC_NLA_SOCK_MAX = __TIPC_NLA_SOCK_MAX - 1
 };
 
+/* Link info */
+enum {
+	TIPC_NLA_LINK_UNSPEC,
+	TIPC_NLA_LINK_NAME,		/* string */
+	TIPC_NLA_LINK_DEST,		/* u32 */
+	TIPC_NLA_LINK_MTU,		/* u32 */
+	TIPC_NLA_LINK_BROADCAST,	/* flag */
+	TIPC_NLA_LINK_UP,		/* flag */
+	TIPC_NLA_LINK_ACTIVE,		/* flag */
+	TIPC_NLA_LINK_PROP,		/* nest */
+	TIPC_NLA_LINK_STATS,		/* nest */
+	TIPC_NLA_LINK_RX,		/* u32 */
+	TIPC_NLA_LINK_TX,		/* u32 */
+
+	__TIPC_NLA_LINK_MAX,
+	TIPC_NLA_LINK_MAX = __TIPC_NLA_LINK_MAX - 1
+};
+
 /* Publication info */
 enum {
 	TIPC_NLA_PUBL_UNSPEC,
@@ -128,4 +148,46 @@ enum {
 	TIPC_NLA_PROP_MAX = __TIPC_NLA_PROP_MAX - 1
 };
 
+/* Nest, statistics info */
+enum {
+	TIPC_NLA_STATS_UNSPEC,
+
+	TIPC_NLA_STATS_RX_INFO,		/* u32 */
+	TIPC_NLA_STATS_RX_FRAGMENTS,	/* u32 */
+	TIPC_NLA_STATS_RX_FRAGMENTED,	/* u32 */
+	TIPC_NLA_STATS_RX_BUNDLES,	/* u32 */
+	TIPC_NLA_STATS_RX_BUNDLED,	/* u32 */
+	TIPC_NLA_STATS_TX_INFO,		/* u32 */
+	TIPC_NLA_STATS_TX_FRAGMENTS,	/* u32 */
+	TIPC_NLA_STATS_TX_FRAGMENTED,	/* u32 */
+	TIPC_NLA_STATS_TX_BUNDLES,	/* u32 */
+	TIPC_NLA_STATS_TX_BUNDLED,	/* u32 */
+	TIPC_NLA_STATS_MSG_PROF_TOT,	/* u32 */
+	TIPC_NLA_STATS_MSG_LEN_CNT,	/* u32 */
+	TIPC_NLA_STATS_MSG_LEN_TOT,	/* u32 */
+	TIPC_NLA_STATS_MSG_LEN_P0,	/* u32 */
+	TIPC_NLA_STATS_MSG_LEN_P1,	/* u32 */
+	TIPC_NLA_STATS_MSG_LEN_P2,	/* u32 */
+	TIPC_NLA_STATS_MSG_LEN_P3,	/* u32 */
+	TIPC_NLA_STATS_MSG_LEN_P4,	/* u32 */
+	TIPC_NLA_STATS_MSG_LEN_P5,	/* u32 */
+	TIPC_NLA_STATS_MSG_LEN_P6,	/* u32 */
+	TIPC_NLA_STATS_RX_STATES,	/* u32 */
+	TIPC_NLA_STATS_RX_PROBES,	/* u32 */
+	TIPC_NLA_STATS_RX_NACKS,	/* u32 */
+	TIPC_NLA_STATS_RX_DEFERRED,	/* u32 */
+	TIPC_NLA_STATS_TX_STATES,	/* u32 */
+	TIPC_NLA_STATS_TX_PROBES,	/* u32 */
+	TIPC_NLA_STATS_TX_NACKS,	/* u32 */
+	TIPC_NLA_STATS_TX_ACKS,		/* u32 */
+	TIPC_NLA_STATS_RETRANSMITTED,	/* u32 */
+	TIPC_NLA_STATS_DUPLICATES,	/* u32 */
+	TIPC_NLA_STATS_LINK_CONGS,	/* u32 */
+	TIPC_NLA_STATS_MAX_QUEUE,	/* u32 */
+	TIPC_NLA_STATS_AVG_QUEUE,	/* u32 */
+
+	__TIPC_NLA_STATS_MAX,
+	TIPC_NLA_STATS_MAX = __TIPC_NLA_STATS_MAX - 1
+};
+
 #endif
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index b8670bf262e..dcf3589e3cc 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -767,6 +767,117 @@ void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action)
 	tipc_bclink_unlock();
 }
 
+int __tipc_nl_add_bc_link_stat(struct sk_buff *skb, struct tipc_stats *stats)
+{
+	int i;
+	struct nlattr *nest;
+
+	struct nla_map {
+		__u32 key;
+		__u32 val;
+	};
+
+	struct nla_map map[] = {
+		{TIPC_NLA_STATS_RX_INFO, stats->recv_info},
+		{TIPC_NLA_STATS_RX_FRAGMENTS, stats->recv_fragments},
+		{TIPC_NLA_STATS_RX_FRAGMENTED, stats->recv_fragmented},
+		{TIPC_NLA_STATS_RX_BUNDLES, stats->recv_bundles},
+		{TIPC_NLA_STATS_RX_BUNDLED, stats->recv_bundled},
+		{TIPC_NLA_STATS_TX_INFO, stats->sent_info},
+		{TIPC_NLA_STATS_TX_FRAGMENTS, stats->sent_fragments},
+		{TIPC_NLA_STATS_TX_FRAGMENTED, stats->sent_fragmented},
+		{TIPC_NLA_STATS_TX_BUNDLES, stats->sent_bundles},
+		{TIPC_NLA_STATS_TX_BUNDLED, stats->sent_bundled},
+		{TIPC_NLA_STATS_RX_NACKS, stats->recv_nacks},
+		{TIPC_NLA_STATS_RX_DEFERRED, stats->deferred_recv},
+		{TIPC_NLA_STATS_TX_NACKS, stats->sent_nacks},
+		{TIPC_NLA_STATS_TX_ACKS, stats->sent_acks},
+		{TIPC_NLA_STATS_RETRANSMITTED, stats->retransmitted},
+		{TIPC_NLA_STATS_DUPLICATES, stats->duplicates},
+		{TIPC_NLA_STATS_LINK_CONGS, stats->link_congs},
+		{TIPC_NLA_STATS_MAX_QUEUE, stats->max_queue_sz},
+		{TIPC_NLA_STATS_AVG_QUEUE, stats->queue_sz_counts ?
+			(stats->accu_queue_sz / stats->queue_sz_counts) : 0}
+	};
+
+	nest = nla_nest_start(skb, TIPC_NLA_LINK_STATS);
+	if (!nest)
+		return -EMSGSIZE;
+
+	for (i = 0; i <  ARRAY_SIZE(map); i++)
+		if (nla_put_u32(skb, map[i].key, map[i].val))
+			goto msg_full;
+
+	nla_nest_end(skb, nest);
+
+	return 0;
+msg_full:
+	nla_nest_cancel(skb, nest);
+
+	return -EMSGSIZE;
+}
+
+int tipc_nl_add_bc_link(struct tipc_nl_msg *msg)
+{
+	int err;
+	void *hdr;
+	struct nlattr *attrs;
+	struct nlattr *prop;
+
+	if (!bcl)
+		return 0;
+
+	tipc_bclink_lock();
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_v2_family,
+			  NLM_F_MULTI, TIPC_NL_LINK_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK);
+	if (!attrs)
+		goto msg_full;
+
+	/* The broadcast link is always up */
+	if (nla_put_flag(msg->skb, TIPC_NLA_LINK_UP))
+		goto attr_msg_full;
+
+	if (nla_put_flag(msg->skb, TIPC_NLA_LINK_BROADCAST))
+		goto attr_msg_full;
+	if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, bcl->name))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, bcl->next_in_no))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, bcl->next_out_no))
+		goto attr_msg_full;
+
+	prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP);
+	if (!prop)
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->queue_limit[0]))
+		goto prop_msg_full;
+	nla_nest_end(msg->skb, prop);
+
+	err = __tipc_nl_add_bc_link_stat(msg->skb, &bcl->stats);
+	if (err)
+		goto attr_msg_full;
+
+	tipc_bclink_unlock();
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+prop_msg_full:
+	nla_nest_cancel(msg->skb, prop);
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	tipc_bclink_unlock();
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
 
 int tipc_bclink_stats(char *buf, const u32 buf_size)
 {
diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h
index e7b0f85a82b..443de084d3e 100644
--- a/net/tipc/bcast.h
+++ b/net/tipc/bcast.h
@@ -37,6 +37,8 @@
 #ifndef _TIPC_BCAST_H
 #define _TIPC_BCAST_H
 
+#include "netlink.h"
+
 #define MAX_NODES 4096
 #define WSIZE 32
 #define TIPC_BCLINK_RESET 1
@@ -100,4 +102,6 @@ void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action);
 uint  tipc_bclink_get_mtu(void);
 int tipc_bclink_xmit(struct sk_buff *buf);
 void tipc_bclink_wakeup_users(void);
+int tipc_nl_add_bc_link(struct tipc_nl_msg *msg);
+
 #endif
diff --git a/net/tipc/link.c b/net/tipc/link.c
index e7f365012bd..bdc4b5e5bf5 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -36,6 +36,7 @@
 
 #include "core.h"
 #include "link.h"
+#include "bcast.h"
 #include "socket.h"
 #include "name_distr.h"
 #include "discover.h"
@@ -51,6 +52,22 @@ static const char *link_co_err = "Link changeover error, ";
 static const char *link_rst_msg = "Resetting link ";
 static const char *link_unk_evt = "Unknown link event ";
 
+static const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
+	[TIPC_NLA_LINK_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_LINK_NAME] = {
+		.type = NLA_STRING,
+		.len = TIPC_MAX_LINK_NAME
+	},
+	[TIPC_NLA_LINK_MTU]		= { .type = NLA_U32 },
+	[TIPC_NLA_LINK_BROADCAST]	= { .type = NLA_FLAG },
+	[TIPC_NLA_LINK_UP]		= { .type = NLA_FLAG },
+	[TIPC_NLA_LINK_ACTIVE]		= { .type = NLA_FLAG },
+	[TIPC_NLA_LINK_PROP]		= { .type = NLA_NESTED },
+	[TIPC_NLA_LINK_STATS]		= { .type = NLA_NESTED },
+	[TIPC_NLA_LINK_RX]		= { .type = NLA_U32 },
+	[TIPC_NLA_LINK_TX]		= { .type = NLA_U32 }
+};
+
 /* Properties valid for media, bearar and link */
 static const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = {
 	[TIPC_NLA_PROP_UNSPEC]		= { .type = NLA_UNSPEC },
@@ -2423,3 +2440,273 @@ int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[])
 
 	return 0;
 }
+
+int __tipc_nl_add_stats(struct sk_buff *skb, struct tipc_stats *s)
+{
+	int i;
+	struct nlattr *stats;
+
+	struct nla_map {
+		u32 key;
+		u32 val;
+	};
+
+	struct nla_map map[] = {
+		{TIPC_NLA_STATS_RX_INFO, s->recv_info},
+		{TIPC_NLA_STATS_RX_FRAGMENTS, s->recv_fragments},
+		{TIPC_NLA_STATS_RX_FRAGMENTED, s->recv_fragmented},
+		{TIPC_NLA_STATS_RX_BUNDLES, s->recv_bundles},
+		{TIPC_NLA_STATS_RX_BUNDLED, s->recv_bundled},
+		{TIPC_NLA_STATS_TX_INFO, s->sent_info},
+		{TIPC_NLA_STATS_TX_FRAGMENTS, s->sent_fragments},
+		{TIPC_NLA_STATS_TX_FRAGMENTED, s->sent_fragmented},
+		{TIPC_NLA_STATS_TX_BUNDLES, s->sent_bundles},
+		{TIPC_NLA_STATS_TX_BUNDLED, s->sent_bundled},
+		{TIPC_NLA_STATS_MSG_PROF_TOT, (s->msg_length_counts) ?
+			s->msg_length_counts : 1},
+		{TIPC_NLA_STATS_MSG_LEN_CNT, s->msg_length_counts},
+		{TIPC_NLA_STATS_MSG_LEN_TOT, s->msg_lengths_total},
+		{TIPC_NLA_STATS_MSG_LEN_P0, s->msg_length_profile[0]},
+		{TIPC_NLA_STATS_MSG_LEN_P1, s->msg_length_profile[1]},
+		{TIPC_NLA_STATS_MSG_LEN_P2, s->msg_length_profile[2]},
+		{TIPC_NLA_STATS_MSG_LEN_P3, s->msg_length_profile[3]},
+		{TIPC_NLA_STATS_MSG_LEN_P4, s->msg_length_profile[4]},
+		{TIPC_NLA_STATS_MSG_LEN_P5, s->msg_length_profile[5]},
+		{TIPC_NLA_STATS_MSG_LEN_P6, s->msg_length_profile[6]},
+		{TIPC_NLA_STATS_RX_STATES, s->recv_states},
+		{TIPC_NLA_STATS_RX_PROBES, s->recv_probes},
+		{TIPC_NLA_STATS_RX_NACKS, s->recv_nacks},
+		{TIPC_NLA_STATS_RX_DEFERRED, s->deferred_recv},
+		{TIPC_NLA_STATS_TX_STATES, s->sent_states},
+		{TIPC_NLA_STATS_TX_PROBES, s->sent_probes},
+		{TIPC_NLA_STATS_TX_NACKS, s->sent_nacks},
+		{TIPC_NLA_STATS_TX_ACKS, s->sent_acks},
+		{TIPC_NLA_STATS_RETRANSMITTED, s->retransmitted},
+		{TIPC_NLA_STATS_DUPLICATES, s->duplicates},
+		{TIPC_NLA_STATS_LINK_CONGS, s->link_congs},
+		{TIPC_NLA_STATS_MAX_QUEUE, s->max_queue_sz},
+		{TIPC_NLA_STATS_AVG_QUEUE, s->queue_sz_counts ?
+			(s->accu_queue_sz / s->queue_sz_counts) : 0}
+	};
+
+	stats = nla_nest_start(skb, TIPC_NLA_LINK_STATS);
+	if (!stats)
+		return -EMSGSIZE;
+
+	for (i = 0; i <  ARRAY_SIZE(map); i++)
+		if (nla_put_u32(skb, map[i].key, map[i].val))
+			goto msg_full;
+
+	nla_nest_end(skb, stats);
+
+	return 0;
+msg_full:
+	nla_nest_cancel(skb, stats);
+
+	return -EMSGSIZE;
+}
+
+/* Caller should hold appropriate locks to protect the link */
+int __tipc_nl_add_link(struct tipc_nl_msg *msg, struct tipc_link *link)
+{
+	int err;
+	void *hdr;
+	struct nlattr *attrs;
+	struct nlattr *prop;
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_v2_family,
+			  NLM_F_MULTI, TIPC_NL_LINK_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK);
+	if (!attrs)
+		goto msg_full;
+
+	if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, link->name))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_LINK_DEST,
+			tipc_cluster_mask(tipc_own_addr)))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_LINK_MTU, link->max_pkt))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->next_in_no))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, link->next_out_no))
+		goto attr_msg_full;
+
+	if (tipc_link_is_up(link))
+		if (nla_put_flag(msg->skb, TIPC_NLA_LINK_UP))
+			goto attr_msg_full;
+	if (tipc_link_is_active(link))
+		if (nla_put_flag(msg->skb, TIPC_NLA_LINK_ACTIVE))
+			goto attr_msg_full;
+
+	prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP);
+	if (!prop)
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, link->tolerance))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN,
+			link->queue_limit[TIPC_LOW_IMPORTANCE]))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority))
+		goto prop_msg_full;
+	nla_nest_end(msg->skb, prop);
+
+	err = __tipc_nl_add_stats(msg->skb, &link->stats);
+	if (err)
+		goto attr_msg_full;
+
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+prop_msg_full:
+	nla_nest_cancel(msg->skb, prop);
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+/* Caller should hold node lock  */
+int __tipc_nl_add_node_links(struct tipc_nl_msg *msg, struct tipc_node *node,
+			     u32 *prev_link)
+{
+	u32 i;
+	int err;
+
+	for (i = *prev_link; i < MAX_BEARERS; i++) {
+		*prev_link = i;
+
+		if (!node->links[i])
+			continue;
+
+		err = __tipc_nl_add_link(msg, node->links[i]);
+		if (err)
+			return err;
+	}
+	*prev_link = 0;
+
+	return 0;
+}
+
+int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct tipc_node *node;
+	struct tipc_nl_msg msg;
+	u32 prev_node = cb->args[0];
+	u32 prev_link = cb->args[1];
+	int done = cb->args[2];
+	int err;
+
+	if (done)
+		return 0;
+
+	msg.skb = skb;
+	msg.portid = NETLINK_CB(cb->skb).portid;
+	msg.seq = cb->nlh->nlmsg_seq;
+
+	rcu_read_lock();
+
+	if (prev_node) {
+		node = tipc_node_find(prev_node);
+		if (!node) {
+			/* We never set seq or call nl_dump_check_consistent()
+			 * this means that setting prev_seq here will cause the
+			 * consistence check to fail in the netlink callback
+			 * handler. Resulting in the last NLMSG_DONE message
+			 * having the NLM_F_DUMP_INTR flag set.
+			 */
+			cb->prev_seq = 1;
+			goto out;
+		}
+
+		list_for_each_entry_continue_rcu(node, &tipc_node_list, list) {
+			tipc_node_lock(node);
+			err = __tipc_nl_add_node_links(&msg, node, &prev_link);
+			tipc_node_unlock(node);
+			if (err)
+				goto out;
+
+			prev_node = node->addr;
+		}
+	} else {
+		err = tipc_nl_add_bc_link(&msg);
+		if (err)
+			goto out;
+
+		list_for_each_entry_rcu(node, &tipc_node_list, list) {
+			tipc_node_lock(node);
+			err = __tipc_nl_add_node_links(&msg, node, &prev_link);
+			tipc_node_unlock(node);
+			if (err)
+				goto out;
+
+			prev_node = node->addr;
+		}
+	}
+	done = 1;
+out:
+	rcu_read_unlock();
+
+	cb->args[0] = prev_node;
+	cb->args[1] = prev_link;
+	cb->args[2] = done;
+
+	return skb->len;
+}
+
+int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info)
+{
+	struct sk_buff *ans_skb;
+	struct tipc_nl_msg msg;
+	struct tipc_link *link;
+	struct tipc_node *node;
+	char *name;
+	int bearer_id;
+	int err;
+
+	if (!info->attrs[TIPC_NLA_LINK_NAME])
+		return -EINVAL;
+
+	name = nla_data(info->attrs[TIPC_NLA_LINK_NAME]);
+	node = tipc_link_find_owner(name, &bearer_id);
+	if (!node)
+		return -EINVAL;
+
+	ans_skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!ans_skb)
+		return -ENOMEM;
+
+	msg.skb = ans_skb;
+	msg.portid = info->snd_portid;
+	msg.seq = info->snd_seq;
+
+	tipc_node_lock(node);
+	link = node->links[bearer_id];
+	if (!link) {
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	err = __tipc_nl_add_link(&msg, link);
+	if (err)
+		goto err_out;
+
+	tipc_node_unlock(node);
+
+	return genlmsg_reply(ans_skb, info);
+
+err_out:
+	tipc_node_unlock(node);
+	nlmsg_free(ans_skb);
+
+	return err;
+}
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 4338294f20d..8e3542a4a03 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -240,6 +240,8 @@ void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window);
 void tipc_link_retransmit(struct tipc_link *l_ptr,
 			  struct sk_buff *start, u32 retransmits);
 
+int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info);
 int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]);
 
 /*
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 9bc64aaff46..ea168b889ca 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -38,6 +38,7 @@
 #include "config.h"
 #include "socket.h"
 #include "bearer.h"
+#include "link.h"
 #include <net/genetlink.h>
 
 static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
@@ -74,7 +75,8 @@ static const struct nla_policy tipc_nl_policy[TIPC_NLA_MAX + 1] = {
 	[TIPC_NLA_UNSPEC]	= { .type = NLA_UNSPEC, },
 	[TIPC_NLA_BEARER]	= { .type = NLA_NESTED, },
 	[TIPC_NLA_SOCK]		= { .type = NLA_NESTED, },
-	[TIPC_NLA_PUBL]		= { .type = NLA_NESTED, }
+	[TIPC_NLA_PUBL]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_LINK]		= { .type = NLA_NESTED, },
 };
 
 /* Legacy ASCII API */
@@ -136,6 +138,12 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 		.cmd	= TIPC_NL_PUBL_GET,
 		.dumpit	= tipc_nl_publ_dump,
 		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_LINK_GET,
+		.doit   = tipc_nl_link_get,
+		.dumpit	= tipc_nl_link_dump,
+		.policy = tipc_nl_policy,
 	}
 };
 
-- 
cgit v1.2.3-70-g09d2


From f96ce7a20d6972a834202f3cdd6a53fd0ee26a8e Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:13 +0100
Subject: tipc: add link set to new netlink api

Add TIPC_NL_LINK_SET to the new tipc netlink API.

This command can set one or more link properties for a particular
link.

Netlink logical layout of link set message:
-> link
    -> name
    -> properties
        [ -> tolerance ]
        [ -> priority ]
        [ -> window ]

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h |  1 +
 net/tipc/link.c                   | 73 +++++++++++++++++++++++++++++++++++++++
 net/tipc/link.h                   |  1 +
 net/tipc/netlink.c                |  5 +++
 4 files changed, 80 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index 1034fb43d32..2deb7fd8d85 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -48,6 +48,7 @@ enum {
 	TIPC_NL_SOCK_GET,
 	TIPC_NL_PUBL_GET,
 	TIPC_NL_LINK_GET,
+	TIPC_NL_LINK_SET,
 
 	__TIPC_NL_CMD_MAX,
 	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
diff --git a/net/tipc/link.c b/net/tipc/link.c
index bdc4b5e5bf5..6785dcfd2d2 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -2441,6 +2441,79 @@ int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[])
 	return 0;
 }
 
+int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	int res = 0;
+	int bearer_id;
+	char *name;
+	struct tipc_link *link;
+	struct tipc_node *node;
+	struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1];
+
+	if (!info->attrs[TIPC_NLA_LINK])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
+			       info->attrs[TIPC_NLA_LINK],
+			       tipc_nl_link_policy);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_LINK_NAME])
+		return -EINVAL;
+
+	name = nla_data(attrs[TIPC_NLA_LINK_NAME]);
+
+	node = tipc_link_find_owner(name, &bearer_id);
+	if (!node)
+		return -EINVAL;
+
+	tipc_node_lock(node);
+
+	link = node->links[bearer_id];
+	if (!link) {
+		res = -EINVAL;
+		goto out;
+	}
+
+	if (attrs[TIPC_NLA_LINK_PROP]) {
+		struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
+
+		err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_LINK_PROP],
+					      props);
+		if (err) {
+			res = err;
+			goto out;
+		}
+
+		if (props[TIPC_NLA_PROP_TOL]) {
+			u32 tol;
+
+			tol = nla_get_u32(props[TIPC_NLA_PROP_TOL]);
+			link_set_supervision_props(link, tol);
+			tipc_link_proto_xmit(link, STATE_MSG, 0, 0, tol, 0, 0);
+		}
+		if (props[TIPC_NLA_PROP_PRIO]) {
+			u32 prio;
+
+			prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
+			link->priority = prio;
+			tipc_link_proto_xmit(link, STATE_MSG, 0, 0, 0, prio, 0);
+		}
+		if (props[TIPC_NLA_PROP_WIN]) {
+			u32 win;
+
+			win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+			tipc_link_set_queue_limits(link, win);
+		}
+	}
+
+out:
+	tipc_node_unlock(node);
+
+	return res;
+}
 int __tipc_nl_add_stats(struct sk_buff *skb, struct tipc_stats *s)
 {
 	int i;
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 8e3542a4a03..3738ba11ce0 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -242,6 +242,7 @@ void tipc_link_retransmit(struct tipc_link *l_ptr,
 
 int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb);
 int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info);
 int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]);
 
 /*
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index ea168b889ca..d4444e59bf9 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -144,6 +144,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 		.doit   = tipc_nl_link_get,
 		.dumpit	= tipc_nl_link_dump,
 		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_LINK_SET,
+		.doit	= tipc_nl_link_set,
+		.policy = tipc_nl_policy,
 	}
 };
 
-- 
cgit v1.2.3-70-g09d2


From ae36342b50a91cff188e417201452dc075a8f444 Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:14 +0100
Subject: tipc: add link stat reset to new netlink api

Add TIPC_NL_LINK_RESET_STATS command to the new netlink API.

This command resets the link statistics for a particular link.

Netlink logical layout of link reset message:
-> link
    -> name

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h |  1 +
 net/tipc/link.c                   | 49 +++++++++++++++++++++++++++++++++++++++
 net/tipc/link.h                   |  1 +
 net/tipc/netlink.c                |  5 ++++
 4 files changed, 56 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index 2deb7fd8d85..574882a301b 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -49,6 +49,7 @@ enum {
 	TIPC_NL_PUBL_GET,
 	TIPC_NL_LINK_GET,
 	TIPC_NL_LINK_SET,
+	TIPC_NL_LINK_RESET_STATS,
 
 	__TIPC_NL_CMD_MAX,
 	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 6785dcfd2d2..629e8cf393b 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -2783,3 +2783,52 @@ err_out:
 
 	return err;
 }
+
+int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	char *link_name;
+	unsigned int bearer_id;
+	struct tipc_link *link;
+	struct tipc_node *node;
+	struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1];
+
+	if (!info->attrs[TIPC_NLA_LINK])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
+			       info->attrs[TIPC_NLA_LINK],
+			       tipc_nl_link_policy);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_LINK_NAME])
+		return -EINVAL;
+
+	link_name = nla_data(attrs[TIPC_NLA_LINK_NAME]);
+
+	if (strcmp(link_name, tipc_bclink_name) == 0) {
+		err = tipc_bclink_reset_stats();
+		if (err)
+			return err;
+		return 0;
+	}
+
+	node = tipc_link_find_owner(link_name, &bearer_id);
+	if (!node)
+		return -EINVAL;
+
+	tipc_node_lock(node);
+
+	link = node->links[bearer_id];
+	if (!link) {
+		tipc_node_unlock(node);
+		return -EINVAL;
+	}
+
+	link_reset_statistics(link);
+
+	tipc_node_unlock(node);
+
+	return 0;
+}
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 3738ba11ce0..f463e7be801 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -243,6 +243,7 @@ void tipc_link_retransmit(struct tipc_link *l_ptr,
 int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb);
 int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info);
 int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info);
 int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]);
 
 /*
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index d4444e59bf9..68bfd11f232 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -149,6 +149,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 		.cmd	= TIPC_NL_LINK_SET,
 		.doit	= tipc_nl_link_set,
 		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_LINK_RESET_STATS,
+		.doit   = tipc_nl_link_reset_stats,
+		.policy = tipc_nl_policy,
 	}
 };
 
-- 
cgit v1.2.3-70-g09d2


From 46f15c6794fb744bb7741d26143a85b9012c10d4 Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:15 +0100
Subject: tipc: add media get/dump to new netlink api

Add TIPC_NL_MEDIA_GET command to the new tipc netlink API.

This command supports dumping all information about all defined
media as well as getting all information about a specific media.

The information about a media includes name and link properties.

Netlink logical layout of media get response message:
-> media
    -> name
    -> link properties
        -> tolerance
        -> priority
        -> window

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h |  12 ++++
 net/tipc/bearer.c                 | 125 ++++++++++++++++++++++++++++++++++++++
 net/tipc/bearer.h                 |   3 +
 net/tipc/netlink.c                |   7 +++
 4 files changed, 147 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index 574882a301b..4101b70991c 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -50,6 +50,7 @@ enum {
 	TIPC_NL_LINK_GET,
 	TIPC_NL_LINK_SET,
 	TIPC_NL_LINK_RESET_STATS,
+	TIPC_NL_MEDIA_GET,
 
 	__TIPC_NL_CMD_MAX,
 	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
@@ -62,6 +63,7 @@ enum {
 	TIPC_NLA_SOCK,			/* nest */
 	TIPC_NLA_PUBL,			/* nest */
 	TIPC_NLA_LINK,			/* nest */
+	TIPC_NLA_MEDIA,			/* nest */
 
 	__TIPC_NLA_MAX,
 	TIPC_NLA_MAX = __TIPC_NLA_MAX - 1
@@ -108,6 +110,16 @@ enum {
 	TIPC_NLA_LINK_MAX = __TIPC_NLA_LINK_MAX - 1
 };
 
+/* Media info */
+enum {
+	TIPC_NLA_MEDIA_UNSPEC,
+	TIPC_NLA_MEDIA_NAME,		/* string */
+	TIPC_NLA_MEDIA_PROP,		/* nest */
+
+	__TIPC_NLA_MEDIA_MAX,
+	TIPC_NLA_MEDIA_MAX = __TIPC_NLA_MEDIA_MAX - 1
+};
+
 /* Publication info */
 enum {
 	TIPC_NLA_PUBL_UNSPEC,
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 6d547d0b3f3..26630a51fca 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -61,6 +61,12 @@ tipc_nl_bearer_policy[TIPC_NLA_BEARER_MAX + 1]	= {
 	[TIPC_NLA_BEARER_DOMAIN]		= { .type = NLA_U32 }
 };
 
+static const struct nla_policy tipc_nl_media_policy[TIPC_NLA_MEDIA_MAX + 1] = {
+	[TIPC_NLA_MEDIA_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_MEDIA_NAME]		= { .type = NLA_STRING },
+	[TIPC_NLA_MEDIA_PROP]		= { .type = NLA_NESTED }
+};
+
 struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1];
 
 static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down);
@@ -898,3 +904,122 @@ int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info)
 
 	return 0;
 }
+
+int __tipc_nl_add_media(struct tipc_nl_msg *msg, struct tipc_media *media)
+{
+	void *hdr;
+	struct nlattr *attrs;
+	struct nlattr *prop;
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_v2_family,
+			  NLM_F_MULTI, TIPC_NL_MEDIA_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start(msg->skb, TIPC_NLA_MEDIA);
+	if (!attrs)
+		goto msg_full;
+
+	if (nla_put_string(msg->skb, TIPC_NLA_MEDIA_NAME, media->name))
+		goto attr_msg_full;
+
+	prop = nla_nest_start(msg->skb, TIPC_NLA_MEDIA_PROP);
+	if (!prop)
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, media->priority))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, media->tolerance))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, media->window))
+		goto prop_msg_full;
+
+	nla_nest_end(msg->skb, prop);
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+prop_msg_full:
+	nla_nest_cancel(msg->skb, prop);
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int err;
+	int i = cb->args[0];
+	struct tipc_nl_msg msg;
+
+	if (i == MAX_MEDIA)
+		return 0;
+
+	msg.skb = skb;
+	msg.portid = NETLINK_CB(cb->skb).portid;
+	msg.seq = cb->nlh->nlmsg_seq;
+
+	rtnl_lock();
+	for (; media_info_array[i] != NULL; i++) {
+		err = __tipc_nl_add_media(&msg, media_info_array[i]);
+		if (err)
+			break;
+	}
+	rtnl_unlock();
+
+	cb->args[0] = i;
+	return skb->len;
+}
+
+int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	char *name;
+	struct tipc_nl_msg msg;
+	struct tipc_media *media;
+	struct sk_buff *rep;
+	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
+
+	if (!info->attrs[TIPC_NLA_MEDIA])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_MEDIA_MAX,
+			       info->attrs[TIPC_NLA_MEDIA],
+			       tipc_nl_media_policy);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_MEDIA_NAME])
+		return -EINVAL;
+	name = nla_data(attrs[TIPC_NLA_MEDIA_NAME]);
+
+	rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!rep)
+		return -ENOMEM;
+
+	msg.skb = rep;
+	msg.portid = info->snd_portid;
+	msg.seq = info->snd_seq;
+
+	rtnl_lock();
+	media = tipc_media_find(name);
+	if (!media) {
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	err = __tipc_nl_add_media(&msg, media);
+	if (err)
+		goto err_out;
+	rtnl_unlock();
+
+	return genlmsg_reply(rep, info);
+err_out:
+	rtnl_unlock();
+	nlmsg_free(rep);
+
+	return err;
+}
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index c6cf9df3137..bacd225bccf 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -184,6 +184,9 @@ int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb);
 int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info);
 int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info);
 
+int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info);
+
 int tipc_media_set_priority(const char *name, u32 new_value);
 int tipc_media_set_window(const char *name, u32 new_value);
 void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a);
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 68bfd11f232..742e51a0afb 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -77,6 +77,7 @@ static const struct nla_policy tipc_nl_policy[TIPC_NLA_MAX + 1] = {
 	[TIPC_NLA_SOCK]		= { .type = NLA_NESTED, },
 	[TIPC_NLA_PUBL]		= { .type = NLA_NESTED, },
 	[TIPC_NLA_LINK]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_MEDIA]	= { .type = NLA_NESTED, },
 };
 
 /* Legacy ASCII API */
@@ -154,6 +155,12 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 		.cmd	= TIPC_NL_LINK_RESET_STATS,
 		.doit   = tipc_nl_link_reset_stats,
 		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_MEDIA_GET,
+		.doit	= tipc_nl_media_get,
+		.dumpit	= tipc_nl_media_dump,
+		.policy = tipc_nl_policy,
 	}
 };
 
-- 
cgit v1.2.3-70-g09d2


From 1e55417d8fc6f6d93b1cc6995b911d48ded2adfb Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:16 +0100
Subject: tipc: add media set to new netlink api

Add TIPC_NL_MEDIA_SET command to the new tipc netlink API.

This command can set one or more link properties for a particular
media.

Netlink logical layout of bearer set message:
-> media
    -> name
    -> link properties
        [ -> tolerance ]
        [ -> priority ]
        [ -> window ]

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h |  1 +
 net/tipc/bearer.c                 | 47 +++++++++++++++++++++++++++++++++++++++
 net/tipc/bearer.h                 |  1 +
 net/tipc/netlink.c                |  5 +++++
 4 files changed, 54 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index 4101b70991c..43beef28d67 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -51,6 +51,7 @@ enum {
 	TIPC_NL_LINK_SET,
 	TIPC_NL_LINK_RESET_STATS,
 	TIPC_NL_MEDIA_GET,
+	TIPC_NL_MEDIA_SET,
 
 	__TIPC_NL_CMD_MAX,
 	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 26630a51fca..5f6f32369c1 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -1023,3 +1023,50 @@ err_out:
 
 	return err;
 }
+
+int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	char *name;
+	struct tipc_media *m;
+	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
+
+	if (!info->attrs[TIPC_NLA_MEDIA])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_MEDIA_MAX,
+			       info->attrs[TIPC_NLA_MEDIA],
+			       tipc_nl_media_policy);
+
+	if (!attrs[TIPC_NLA_MEDIA_NAME])
+		return -EINVAL;
+	name = nla_data(attrs[TIPC_NLA_MEDIA_NAME]);
+
+	rtnl_lock();
+	m = tipc_media_find(name);
+	if (!m) {
+		rtnl_unlock();
+		return -EINVAL;
+	}
+
+	if (attrs[TIPC_NLA_MEDIA_PROP]) {
+		struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
+
+		err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_MEDIA_PROP],
+					      props);
+		if (err) {
+			rtnl_unlock();
+			return err;
+		}
+
+		if (props[TIPC_NLA_PROP_TOL])
+			m->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]);
+		if (props[TIPC_NLA_PROP_PRIO])
+			m->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
+		if (props[TIPC_NLA_PROP_WIN])
+			m->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+	}
+	rtnl_unlock();
+
+	return 0;
+}
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index bacd225bccf..b1d905209e8 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -186,6 +186,7 @@ int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info);
 
 int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb);
 int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info);
 
 int tipc_media_set_priority(const char *name, u32 new_value);
 int tipc_media_set_window(const char *name, u32 new_value);
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 742e51a0afb..8673e370b7e 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -161,6 +161,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 		.doit	= tipc_nl_media_get,
 		.dumpit	= tipc_nl_media_dump,
 		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_MEDIA_SET,
+		.doit	= tipc_nl_media_set,
+		.policy = tipc_nl_policy,
 	}
 };
 
-- 
cgit v1.2.3-70-g09d2


From 3e4b6ab58d614934e7ca99bdf448089695d34ffa Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:17 +0100
Subject: tipc: add node get/dump to new netlink api

Add TIPC_NL_NODE_GET to the new tipc netlink API.

This command can dump the address and node status of all nodes in the
tipc cluster.

Netlink logical layout of returned node/address data:
-> node
    -> address
    -> up flag

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h | 12 +++++
 net/tipc/netlink.c                |  7 +++
 net/tipc/node.c                   | 96 +++++++++++++++++++++++++++++++++++++++
 net/tipc/node.h                   |  4 +-
 4 files changed, 118 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index 43beef28d67..08a793374e8 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -52,6 +52,7 @@ enum {
 	TIPC_NL_LINK_RESET_STATS,
 	TIPC_NL_MEDIA_GET,
 	TIPC_NL_MEDIA_SET,
+	TIPC_NL_NODE_GET,
 
 	__TIPC_NL_CMD_MAX,
 	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
@@ -65,6 +66,7 @@ enum {
 	TIPC_NLA_PUBL,			/* nest */
 	TIPC_NLA_LINK,			/* nest */
 	TIPC_NLA_MEDIA,			/* nest */
+	TIPC_NLA_NODE,			/* nest */
 
 	__TIPC_NLA_MAX,
 	TIPC_NLA_MAX = __TIPC_NLA_MAX - 1
@@ -121,6 +123,16 @@ enum {
 	TIPC_NLA_MEDIA_MAX = __TIPC_NLA_MEDIA_MAX - 1
 };
 
+/* Node info */
+enum {
+	TIPC_NLA_NODE_UNSPEC,
+	TIPC_NLA_NODE_ADDR,		/* u32 */
+	TIPC_NLA_NODE_UP,		/* flag */
+
+	__TIPC_NLA_NODE_MAX,
+	TIPC_NLA_NODE_MAX = __TIPC_NLA_NODE_MAX - 1
+};
+
 /* Publication info */
 enum {
 	TIPC_NLA_PUBL_UNSPEC,
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 8673e370b7e..5b0e3c8457d 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -39,6 +39,7 @@
 #include "socket.h"
 #include "bearer.h"
 #include "link.h"
+#include "node.h"
 #include <net/genetlink.h>
 
 static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
@@ -78,6 +79,7 @@ static const struct nla_policy tipc_nl_policy[TIPC_NLA_MAX + 1] = {
 	[TIPC_NLA_PUBL]		= { .type = NLA_NESTED, },
 	[TIPC_NLA_LINK]		= { .type = NLA_NESTED, },
 	[TIPC_NLA_MEDIA]	= { .type = NLA_NESTED, },
+	[TIPC_NLA_NODE]		= { .type = NLA_NESTED, }
 };
 
 /* Legacy ASCII API */
@@ -166,6 +168,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 		.cmd	= TIPC_NL_MEDIA_SET,
 		.doit	= tipc_nl_media_set,
 		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_NODE_GET,
+		.dumpit	= tipc_nl_node_dump,
+		.policy = tipc_nl_policy,
 	}
 };
 
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 5781634e957..72a75d4838b 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -58,6 +58,12 @@ struct tipc_sock_conn {
 	struct list_head list;
 };
 
+static const struct nla_policy tipc_nl_node_policy[TIPC_NLA_NODE_MAX + 1] = {
+	[TIPC_NLA_NODE_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_NODE_ADDR]		= { .type = NLA_U32 },
+	[TIPC_NLA_NODE_UP]		= { .type = NLA_FLAG }
+};
+
 /*
  * A trivial power-of-two bitmask technique is used for speed, since this
  * operation is done for every incoming TIPC packet. The number of hash table
@@ -601,3 +607,93 @@ void tipc_node_unlock(struct tipc_node *node)
 		tipc_nametbl_withdraw(TIPC_LINK_STATE, addr,
 				      link_id, addr);
 }
+
+/* Caller should hold node lock for the passed node */
+int __tipc_nl_add_node(struct tipc_nl_msg *msg, struct tipc_node *node)
+{
+	void *hdr;
+	struct nlattr *attrs;
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_v2_family,
+			  NLM_F_MULTI, TIPC_NL_NODE_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start(msg->skb, TIPC_NLA_NODE);
+	if (!attrs)
+		goto msg_full;
+
+	if (nla_put_u32(msg->skb, TIPC_NLA_NODE_ADDR, node->addr))
+		goto attr_msg_full;
+	if (tipc_node_is_up(node))
+		if (nla_put_flag(msg->skb, TIPC_NLA_NODE_UP))
+			goto attr_msg_full;
+
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int err;
+	int done = cb->args[0];
+	int last_addr = cb->args[1];
+	struct tipc_node *node;
+	struct tipc_nl_msg msg;
+
+	if (done)
+		return 0;
+
+	msg.skb = skb;
+	msg.portid = NETLINK_CB(cb->skb).portid;
+	msg.seq = cb->nlh->nlmsg_seq;
+
+	rcu_read_lock();
+
+	if (last_addr && !tipc_node_find(last_addr)) {
+		rcu_read_unlock();
+		/* We never set seq or call nl_dump_check_consistent() this
+		 * means that setting prev_seq here will cause the consistence
+		 * check to fail in the netlink callback handler. Resulting in
+		 * the NLMSG_DONE message having the NLM_F_DUMP_INTR flag set if
+		 * the node state changed while we released the lock.
+		 */
+		cb->prev_seq = 1;
+		return -EPIPE;
+	}
+
+	list_for_each_entry_rcu(node, &tipc_node_list, list) {
+		if (last_addr) {
+			if (node->addr == last_addr)
+				last_addr = 0;
+			else
+				continue;
+		}
+
+		tipc_node_lock(node);
+		err = __tipc_nl_add_node(&msg, node);
+		if (err) {
+			last_addr = node->addr;
+			tipc_node_unlock(node);
+			goto out;
+		}
+
+		tipc_node_unlock(node);
+	}
+	done = 1;
+out:
+	cb->args[0] = done;
+	cb->args[1] = last_addr;
+	rcu_read_unlock();
+
+	return skb->len;
+}
diff --git a/net/tipc/node.h b/net/tipc/node.h
index 04e91458bb2..005fbcef321 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/node.h: Include file for TIPC node management routines
  *
- * Copyright (c) 2000-2006, Ericsson AB
+ * Copyright (c) 2000-2006, 2014, Ericsson AB
  * Copyright (c) 2005, 2010-2014, Wind River Systems
  * All rights reserved.
  *
@@ -145,6 +145,8 @@ void tipc_node_unlock(struct tipc_node *node);
 int tipc_node_add_conn(u32 dnode, u32 port, u32 peer_port);
 void tipc_node_remove_conn(u32 dnode, u32 port);
 
+int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb);
+
 static inline void tipc_node_lock(struct tipc_node *node)
 {
 	spin_lock_bh(&node->lock);
-- 
cgit v1.2.3-70-g09d2


From fd3cf2ad519f73c2f7a46460ebedf32ad246520c Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:18 +0100
Subject: tipc: add net dump to new netlink api

Add TIPC_NL_NET_GET command to the new tipc netlink API.

This command dumps the network id of the node.

Netlink logical layout of returned network data:
-> net
    -> id

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h | 11 ++++++++
 net/tipc/net.c                    | 59 +++++++++++++++++++++++++++++++++++++++
 net/tipc/net.h                    |  7 ++++-
 net/tipc/netlink.c                |  9 +++++-
 4 files changed, 84 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index 08a793374e8..dcfd42002da 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -53,6 +53,7 @@ enum {
 	TIPC_NL_MEDIA_GET,
 	TIPC_NL_MEDIA_SET,
 	TIPC_NL_NODE_GET,
+	TIPC_NL_NET_GET,
 
 	__TIPC_NL_CMD_MAX,
 	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
@@ -67,6 +68,7 @@ enum {
 	TIPC_NLA_LINK,			/* nest */
 	TIPC_NLA_MEDIA,			/* nest */
 	TIPC_NLA_NODE,			/* nest */
+	TIPC_NLA_NET,			/* nest */
 
 	__TIPC_NLA_MAX,
 	TIPC_NLA_MAX = __TIPC_NLA_MAX - 1
@@ -133,6 +135,15 @@ enum {
 	TIPC_NLA_NODE_MAX = __TIPC_NLA_NODE_MAX - 1
 };
 
+/* Net info */
+enum {
+	TIPC_NLA_NET_UNSPEC,
+	TIPC_NLA_NET_ID,		/* u32 */
+
+	__TIPC_NLA_NET_MAX,
+	TIPC_NLA_NET_MAX = __TIPC_NLA_NET_MAX - 1
+};
+
 /* Publication info */
 enum {
 	TIPC_NLA_PUBL_UNSPEC,
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 93b9944a6a8..d9e666a1be9 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -42,6 +42,11 @@
 #include "node.h"
 #include "config.h"
 
+static const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = {
+	[TIPC_NLA_NET_UNSPEC]	= { .type = NLA_UNSPEC },
+	[TIPC_NLA_NET_ID]	= { .type = NLA_U32 }
+};
+
 /*
  * The TIPC locking policy is designed to ensure a very fine locking
  * granularity, permitting complete parallel access to individual
@@ -138,3 +143,57 @@ void tipc_net_stop(void)
 
 	pr_info("Left network mode\n");
 }
+
+static int __tipc_nl_add_net(struct tipc_nl_msg *msg)
+{
+	void *hdr;
+	struct nlattr *attrs;
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_v2_family,
+			  NLM_F_MULTI, TIPC_NL_NET_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start(msg->skb, TIPC_NLA_NET);
+	if (!attrs)
+		goto msg_full;
+
+	if (nla_put_u32(msg->skb, TIPC_NLA_NET_ID, tipc_net_id))
+		goto attr_msg_full;
+
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int err;
+	int done = cb->args[0];
+	struct tipc_nl_msg msg;
+
+	if (done)
+		return 0;
+
+	msg.skb = skb;
+	msg.portid = NETLINK_CB(cb->skb).portid;
+	msg.seq = cb->nlh->nlmsg_seq;
+
+	err = __tipc_nl_add_net(&msg);
+	if (err)
+		goto out;
+
+	done = 1;
+out:
+	cb->args[0] = done;
+
+	return skb->len;
+}
diff --git a/net/tipc/net.h b/net/tipc/net.h
index 59ef3388be2..60dc22fe926 100644
--- a/net/tipc/net.h
+++ b/net/tipc/net.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/net.h: Include file for TIPC network routing code
  *
- * Copyright (c) 1995-2006, Ericsson AB
+ * Copyright (c) 1995-2006, 2014, Ericsson AB
  * Copyright (c) 2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -37,7 +37,12 @@
 #ifndef _TIPC_NET_H
 #define _TIPC_NET_H
 
+#include <net/genetlink.h>
+
 int tipc_net_start(u32 addr);
+
 void tipc_net_stop(void);
 
+int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb);
+
 #endif
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 5b0e3c8457d..c143f9c20f6 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -40,6 +40,7 @@
 #include "bearer.h"
 #include "link.h"
 #include "node.h"
+#include "net.h"
 #include <net/genetlink.h>
 
 static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
@@ -79,7 +80,8 @@ static const struct nla_policy tipc_nl_policy[TIPC_NLA_MAX + 1] = {
 	[TIPC_NLA_PUBL]		= { .type = NLA_NESTED, },
 	[TIPC_NLA_LINK]		= { .type = NLA_NESTED, },
 	[TIPC_NLA_MEDIA]	= { .type = NLA_NESTED, },
-	[TIPC_NLA_NODE]		= { .type = NLA_NESTED, }
+	[TIPC_NLA_NODE]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_NET]		= { .type = NLA_NESTED, }
 };
 
 /* Legacy ASCII API */
@@ -173,6 +175,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 		.cmd	= TIPC_NL_NODE_GET,
 		.dumpit	= tipc_nl_node_dump,
 		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_NET_GET,
+		.dumpit	= tipc_nl_net_dump,
+		.policy = tipc_nl_policy,
 	}
 };
 
-- 
cgit v1.2.3-70-g09d2


From 27c21416727af73df45051acb05331c0f10e50f6 Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:19 +0100
Subject: tipc: add net set to new netlink api

Add TIPC_NL_NET_SET command to the new tipc netlink API.

This command can set the network id and network (tipc) address.

Netlink logical layout of network set message:
-> net
     [ -> id ]
     [ -> address ]

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h |  2 ++
 net/tipc/net.c                    | 47 +++++++++++++++++++++++++++++++++++++++
 net/tipc/net.h                    |  1 +
 net/tipc/netlink.c                |  5 +++++
 4 files changed, 55 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index dcfd42002da..fb980e27f42 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -54,6 +54,7 @@ enum {
 	TIPC_NL_MEDIA_SET,
 	TIPC_NL_NODE_GET,
 	TIPC_NL_NET_GET,
+	TIPC_NL_NET_SET,
 
 	__TIPC_NL_CMD_MAX,
 	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
@@ -139,6 +140,7 @@ enum {
 enum {
 	TIPC_NLA_NET_UNSPEC,
 	TIPC_NLA_NET_ID,		/* u32 */
+	TIPC_NLA_NET_ADDR,		/* u32 */
 
 	__TIPC_NLA_NET_MAX,
 	TIPC_NLA_NET_MAX = __TIPC_NLA_NET_MAX - 1
diff --git a/net/tipc/net.c b/net/tipc/net.c
index d9e666a1be9..cf13df3cde8 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -197,3 +197,50 @@ out:
 
 	return skb->len;
 }
+
+int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	struct nlattr *attrs[TIPC_NLA_NET_MAX + 1];
+
+	if (!info->attrs[TIPC_NLA_NET])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_NET_MAX,
+			       info->attrs[TIPC_NLA_NET],
+			       tipc_nl_net_policy);
+	if (err)
+		return err;
+
+	if (attrs[TIPC_NLA_NET_ID]) {
+		u32 val;
+
+		/* Can't change net id once TIPC has joined a network */
+		if (tipc_own_addr)
+			return -EPERM;
+
+		val = nla_get_u32(attrs[TIPC_NLA_NET_ID]);
+		if (val < 1 || val > 9999)
+			return -EINVAL;
+
+		tipc_net_id = val;
+	}
+
+	if (attrs[TIPC_NLA_NET_ADDR]) {
+		u32 addr;
+
+		/* Can't change net addr once TIPC has joined a network */
+		if (tipc_own_addr)
+			return -EPERM;
+
+		addr = nla_get_u32(attrs[TIPC_NLA_NET_ADDR]);
+		if (!tipc_addr_node_valid(addr))
+			return -EINVAL;
+
+		rtnl_lock();
+		tipc_net_start(addr);
+		rtnl_unlock();
+	}
+
+	return 0;
+}
diff --git a/net/tipc/net.h b/net/tipc/net.h
index 60dc22fe926..a81c1b9eb15 100644
--- a/net/tipc/net.h
+++ b/net/tipc/net.h
@@ -44,5 +44,6 @@ int tipc_net_start(u32 addr);
 void tipc_net_stop(void);
 
 int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info);
 
 #endif
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index c143f9c20f6..cb37d30378a 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -180,6 +180,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 		.cmd	= TIPC_NL_NET_GET,
 		.dumpit	= tipc_nl_net_dump,
 		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_NET_SET,
+		.doit	= tipc_nl_net_set,
+		.policy = tipc_nl_policy,
 	}
 };
 
-- 
cgit v1.2.3-70-g09d2


From 1593123a6a4914ccac4699d7f93cdf8057a7d822 Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Thu, 20 Nov 2014 10:29:20 +0100
Subject: tipc: add name table dump to new netlink api

Add TIPC_NL_NAME_TABLE_GET command to the new tipc netlink API.

This command supports dumping the name table of all nodes.

Netlink logical layout of name table response message:
-> name table
    -> publication
        -> type
        -> lower
        -> upper
        -> scope
        -> node
        -> ref
        -> key

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h |  11 +++
 net/tipc/name_table.c             | 190 +++++++++++++++++++++++++++++++++++++-
 net/tipc/name_table.h             |   4 +-
 net/tipc/netlink.c                |   9 +-
 4 files changed, 211 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index fb980e27f42..8d723824ad6 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -55,6 +55,7 @@ enum {
 	TIPC_NL_NODE_GET,
 	TIPC_NL_NET_GET,
 	TIPC_NL_NET_SET,
+	TIPC_NL_NAME_TABLE_GET,
 
 	__TIPC_NL_CMD_MAX,
 	TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
@@ -70,6 +71,7 @@ enum {
 	TIPC_NLA_MEDIA,			/* nest */
 	TIPC_NLA_NODE,			/* nest */
 	TIPC_NLA_NET,			/* nest */
+	TIPC_NLA_NAME_TABLE,		/* nest */
 
 	__TIPC_NLA_MAX,
 	TIPC_NLA_MAX = __TIPC_NLA_MAX - 1
@@ -146,6 +148,15 @@ enum {
 	TIPC_NLA_NET_MAX = __TIPC_NLA_NET_MAX - 1
 };
 
+/* Name table info */
+enum {
+	TIPC_NLA_NAME_TABLE_UNSPEC,
+	TIPC_NLA_NAME_TABLE_PUBL,	/* nest */
+
+	__TIPC_NLA_NAME_TABLE_MAX,
+	TIPC_NLA_NAME_TABLE_MAX = __TIPC_NLA_NAME_TABLE_MAX - 1
+};
+
 /* Publication info */
 enum {
 	TIPC_NLA_PUBL_UNSPEC,
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 3a6a0a7c075..30ca8e0e0f8 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/name_table.c: TIPC name table code
  *
- * Copyright (c) 2000-2006, Ericsson AB
+ * Copyright (c) 2000-2006, 2014, Ericsson AB
  * Copyright (c) 2004-2008, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -42,6 +42,12 @@
 
 #define TIPC_NAMETBL_SIZE 1024		/* must be a power of 2 */
 
+static const struct nla_policy
+tipc_nl_name_table_policy[TIPC_NLA_NAME_TABLE_MAX + 1] = {
+	[TIPC_NLA_NAME_TABLE_UNSPEC]	= { .type = NLA_UNSPEC },
+	[TIPC_NLA_NAME_TABLE_PUBL]	= { .type = NLA_NESTED }
+};
+
 /**
  * struct name_info - name sequence publication info
  * @node_list: circular list of publications made by own node
@@ -995,3 +1001,185 @@ void tipc_nametbl_stop(void)
 	table.types = NULL;
 	write_unlock_bh(&tipc_nametbl_lock);
 }
+
+int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg, struct name_seq *seq,
+				 struct sub_seq *sseq, u32 *last_publ)
+{
+	void *hdr;
+	struct nlattr *attrs;
+	struct nlattr *publ;
+	struct publication *p;
+
+	if (*last_publ) {
+		list_for_each_entry(p, &sseq->info->zone_list, zone_list)
+			if (p->key == *last_publ)
+				break;
+		if (p->key != *last_publ)
+			return -EPIPE;
+	} else {
+		p = list_first_entry(&sseq->info->zone_list, struct publication,
+				     zone_list);
+	}
+
+	list_for_each_entry_from(p, &sseq->info->zone_list, zone_list) {
+		*last_publ = p->key;
+
+		hdr = genlmsg_put(msg->skb, msg->portid, msg->seq,
+				  &tipc_genl_v2_family, NLM_F_MULTI,
+				  TIPC_NL_NAME_TABLE_GET);
+		if (!hdr)
+			return -EMSGSIZE;
+
+		attrs = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE);
+		if (!attrs)
+			goto msg_full;
+
+		publ = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE_PUBL);
+		if (!publ)
+			goto attr_msg_full;
+
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_TYPE, seq->type))
+			goto publ_msg_full;
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_LOWER, sseq->lower))
+			goto publ_msg_full;
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_UPPER, sseq->upper))
+			goto publ_msg_full;
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_SCOPE, p->scope))
+			goto publ_msg_full;
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_NODE, p->node))
+			goto publ_msg_full;
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_REF, p->ref))
+			goto publ_msg_full;
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_KEY, p->key))
+			goto publ_msg_full;
+
+		nla_nest_end(msg->skb, publ);
+		nla_nest_end(msg->skb, attrs);
+		genlmsg_end(msg->skb, hdr);
+	}
+	*last_publ = 0;
+
+	return 0;
+
+publ_msg_full:
+	nla_nest_cancel(msg->skb, publ);
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+int __tipc_nl_subseq_list(struct tipc_nl_msg *msg, struct name_seq *seq,
+			  u32 *last_lower, u32 *last_publ)
+{
+	struct sub_seq *sseq;
+	struct sub_seq *sseq_start;
+	int err;
+
+	if (*last_lower) {
+		sseq_start = nameseq_find_subseq(seq, *last_lower);
+		if (!sseq_start)
+			return -EPIPE;
+	} else {
+		sseq_start = seq->sseqs;
+	}
+
+	for (sseq = sseq_start; sseq != &seq->sseqs[seq->first_free]; sseq++) {
+		err = __tipc_nl_add_nametable_publ(msg, seq, sseq, last_publ);
+		if (err) {
+			*last_lower = sseq->lower;
+			return err;
+		}
+	}
+	*last_lower = 0;
+
+	return 0;
+}
+
+int __tipc_nl_seq_list(struct tipc_nl_msg *msg, u32 *last_type, u32 *last_lower,
+		       u32 *last_publ)
+{
+	struct hlist_head *seq_head;
+	struct name_seq *seq;
+	int err;
+	int i;
+
+	if (*last_type)
+		i = hash(*last_type);
+	else
+		i = 0;
+
+	for (; i < TIPC_NAMETBL_SIZE; i++) {
+		seq_head = &table.types[i];
+
+		if (*last_type) {
+			seq = nametbl_find_seq(*last_type);
+			if (!seq)
+				return -EPIPE;
+		} else {
+			seq = hlist_entry_safe((seq_head)->first,
+					       struct name_seq, ns_list);
+			if (!seq)
+				continue;
+		}
+
+		hlist_for_each_entry_from(seq, ns_list) {
+			spin_lock_bh(&seq->lock);
+
+			err = __tipc_nl_subseq_list(msg, seq, last_lower,
+						    last_publ);
+
+			if (err) {
+				*last_type = seq->type;
+				spin_unlock_bh(&seq->lock);
+				return err;
+			}
+			spin_unlock_bh(&seq->lock);
+		}
+		*last_type = 0;
+	}
+	return 0;
+}
+
+int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int err;
+	int done = cb->args[3];
+	u32 last_type = cb->args[0];
+	u32 last_lower = cb->args[1];
+	u32 last_publ = cb->args[2];
+	struct tipc_nl_msg msg;
+
+	if (done)
+		return 0;
+
+	msg.skb = skb;
+	msg.portid = NETLINK_CB(cb->skb).portid;
+	msg.seq = cb->nlh->nlmsg_seq;
+
+	read_lock_bh(&tipc_nametbl_lock);
+
+	err = __tipc_nl_seq_list(&msg, &last_type, &last_lower, &last_publ);
+	if (!err) {
+		done = 1;
+	} else if (err != -EMSGSIZE) {
+		/* We never set seq or call nl_dump_check_consistent() this
+		 * means that setting prev_seq here will cause the consistence
+		 * check to fail in the netlink callback handler. Resulting in
+		 * the NLMSG_DONE message having the NLM_F_DUMP_INTR flag set if
+		 * we got an error.
+		 */
+		cb->prev_seq = 1;
+	}
+
+	read_unlock_bh(&tipc_nametbl_lock);
+
+	cb->args[0] = last_type;
+	cb->args[1] = last_lower;
+	cb->args[2] = last_publ;
+	cb->args[3] = done;
+
+	return skb->len;
+}
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index f02f48b9a21..b38ebecac76 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/name_table.h: Include file for TIPC name table code
  *
- * Copyright (c) 2000-2006, Ericsson AB
+ * Copyright (c) 2000-2006, 2014, Ericsson AB
  * Copyright (c) 2004-2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -84,6 +84,8 @@ struct publication {
 
 extern rwlock_t tipc_nametbl_lock;
 
+int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb);
+
 struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space);
 u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *node);
 int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit,
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index cb37d30378a..b891e3905bc 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -37,6 +37,7 @@
 #include "core.h"
 #include "config.h"
 #include "socket.h"
+#include "name_table.h"
 #include "bearer.h"
 #include "link.h"
 #include "node.h"
@@ -81,7 +82,8 @@ static const struct nla_policy tipc_nl_policy[TIPC_NLA_MAX + 1] = {
 	[TIPC_NLA_LINK]		= { .type = NLA_NESTED, },
 	[TIPC_NLA_MEDIA]	= { .type = NLA_NESTED, },
 	[TIPC_NLA_NODE]		= { .type = NLA_NESTED, },
-	[TIPC_NLA_NET]		= { .type = NLA_NESTED, }
+	[TIPC_NLA_NET]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_NAME_TABLE]	= { .type = NLA_NESTED, }
 };
 
 /* Legacy ASCII API */
@@ -185,6 +187,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 		.cmd	= TIPC_NL_NET_SET,
 		.doit	= tipc_nl_net_set,
 		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_NAME_TABLE_GET,
+		.dumpit	= tipc_nl_name_table_dump,
+		.policy = tipc_nl_policy,
 	}
 };
 
-- 
cgit v1.2.3-70-g09d2


From dbc98635e0d42f0e62ea92813df1e0e4c90f8375 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Wed, 19 Nov 2014 17:28:21 +0200
Subject: phy: remove the old lookup method

The users of the old method are now converted to the new one.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
[ kishon@ti.com : made phy-berlin-usb.c and phy-miphy28lp.c to use the updated
		  devm_phy_create API.]
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/phy/phy-bcm-kona-usb2.c      |  2 +-
 drivers/phy/phy-berlin-sata.c        |  2 +-
 drivers/phy/phy-berlin-usb.c         |  3 +--
 drivers/phy/phy-core.c               | 49 +++---------------------------------
 drivers/phy/phy-exynos-dp-video.c    |  2 +-
 drivers/phy/phy-exynos-mipi-video.c  |  2 +-
 drivers/phy/phy-exynos5-usbdrd.c     |  3 +--
 drivers/phy/phy-exynos5250-sata.c    |  2 +-
 drivers/phy/phy-hix5hd2-sata.c       |  2 +-
 drivers/phy/phy-miphy28lp.c          |  2 +-
 drivers/phy/phy-miphy365x.c          |  2 +-
 drivers/phy/phy-mvebu-sata.c         |  2 +-
 drivers/phy/phy-omap-usb2.c          |  2 +-
 drivers/phy/phy-qcom-apq8064-sata.c  |  3 +--
 drivers/phy/phy-qcom-ipq806x-sata.c  |  3 +--
 drivers/phy/phy-rcar-gen2.c          |  2 +-
 drivers/phy/phy-samsung-usb2.c       |  3 +--
 drivers/phy/phy-spear1310-miphy.c    |  2 +-
 drivers/phy/phy-spear1340-miphy.c    |  2 +-
 drivers/phy/phy-stih407-usb.c        |  2 +-
 drivers/phy/phy-stih41x-usb.c        |  2 +-
 drivers/phy/phy-sun4i-usb.c          |  2 +-
 drivers/phy/phy-ti-pipe3.c           |  2 +-
 drivers/phy/phy-twl4030-usb.c        |  2 +-
 drivers/phy/phy-xgene.c              |  2 +-
 drivers/pinctrl/pinctrl-tegra-xusb.c |  4 +--
 include/linux/phy/phy.h              | 38 +++-------------------------
 27 files changed, 34 insertions(+), 110 deletions(-)

(limited to 'include')

diff --git a/drivers/phy/phy-bcm-kona-usb2.c b/drivers/phy/phy-bcm-kona-usb2.c
index c1e0ca335c0..ef2dc1aab2b 100644
--- a/drivers/phy/phy-bcm-kona-usb2.c
+++ b/drivers/phy/phy-bcm-kona-usb2.c
@@ -117,7 +117,7 @@ static int bcm_kona_usb2_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, phy);
 
-	gphy = devm_phy_create(dev, NULL, &ops, NULL);
+	gphy = devm_phy_create(dev, NULL, &ops);
 	if (IS_ERR(gphy))
 		return PTR_ERR(gphy);
 
diff --git a/drivers/phy/phy-berlin-sata.c b/drivers/phy/phy-berlin-sata.c
index 873e7a890fe..3e599dc9616 100644
--- a/drivers/phy/phy-berlin-sata.c
+++ b/drivers/phy/phy-berlin-sata.c
@@ -249,7 +249,7 @@ static int phy_berlin_sata_probe(struct platform_device *pdev)
 		if (!phy_desc)
 			return -ENOMEM;
 
-		phy = devm_phy_create(dev, NULL, &phy_berlin_sata_ops, NULL);
+		phy = devm_phy_create(dev, NULL, &phy_berlin_sata_ops);
 		if (IS_ERR(phy)) {
 			dev_err(dev, "failed to create PHY %d\n", phy_id);
 			return PTR_ERR(phy);
diff --git a/drivers/phy/phy-berlin-usb.c b/drivers/phy/phy-berlin-usb.c
index f9f13067f50..c8a8d53a6ec 100644
--- a/drivers/phy/phy-berlin-usb.c
+++ b/drivers/phy/phy-berlin-usb.c
@@ -192,8 +192,7 @@ static int phy_berlin_usb_probe(struct platform_device *pdev)
 
 	priv->pll_divider = *((u32 *)match->data);
 
-	priv->phy = devm_phy_create(&pdev->dev, NULL, &phy_berlin_usb_ops,
-				    NULL);
+	priv->phy = devm_phy_create(&pdev->dev, NULL, &phy_berlin_usb_ops);
 	if (IS_ERR(priv->phy)) {
 		dev_err(&pdev->dev, "failed to create PHY\n");
 		return PTR_ERR(priv->phy);
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index bc830773fe0..a12d3533831 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -55,36 +55,6 @@ static int devm_phy_match(struct device *dev, void *res, void *match_data)
 	return res == match_data;
 }
 
-static struct phy *phy_lookup(struct device *device, const char *port)
-{
-	unsigned int count;
-	struct phy *phy;
-	struct device *dev;
-	struct phy_consumer *consumers;
-	struct class_dev_iter iter;
-
-	class_dev_iter_init(&iter, phy_class, NULL, NULL);
-	while ((dev = class_dev_iter_next(&iter))) {
-		phy = to_phy(dev);
-
-		if (!phy->init_data)
-			continue;
-		count = phy->init_data->num_consumers;
-		consumers = phy->init_data->consumers;
-		while (count--) {
-			if (!strcmp(consumers->dev_name, dev_name(device)) &&
-					!strcmp(consumers->port, port)) {
-				class_dev_iter_exit(&iter);
-				return phy;
-			}
-			consumers++;
-		}
-	}
-
-	class_dev_iter_exit(&iter);
-	return ERR_PTR(-ENODEV);
-}
-
 /**
  * phy_create_lookup() - allocate and register PHY/device association
  * @phy: the phy of the association
@@ -148,7 +118,6 @@ static struct phy *phy_find(struct device *dev, const char *con_id)
 {
 	const char *dev_id = dev_name(dev);
 	struct phy_lookup *p, *pl = NULL;
-	struct phy *phy;
 
 	mutex_lock(&phy_provider_mutex);
 	list_for_each_entry(p, &phys, node)
@@ -158,12 +127,7 @@ static struct phy *phy_find(struct device *dev, const char *con_id)
 		}
 	mutex_unlock(&phy_provider_mutex);
 
-	phy = pl ? pl->phy : ERR_PTR(-ENODEV);
-
-	/* fall-back to the old lookup method for now */
-	if (IS_ERR(phy))
-		phy = phy_lookup(dev, con_id);
-	return phy;
+	return pl ? pl->phy : ERR_PTR(-ENODEV);
 }
 
 static struct phy_provider *of_phy_provider_lookup(struct device_node *node)
@@ -662,13 +626,11 @@ EXPORT_SYMBOL_GPL(devm_of_phy_get);
  * @dev: device that is creating the new phy
  * @node: device node of the phy
  * @ops: function pointers for performing phy operations
- * @init_data: contains the list of PHY consumers or NULL
  *
  * Called to create a phy using phy framework.
  */
 struct phy *phy_create(struct device *dev, struct device_node *node,
-		       const struct phy_ops *ops,
-		       struct phy_init_data *init_data)
+		       const struct phy_ops *ops)
 {
 	int ret;
 	int id;
@@ -706,7 +668,6 @@ struct phy *phy_create(struct device *dev, struct device_node *node,
 	phy->dev.of_node = node ?: dev->of_node;
 	phy->id = id;
 	phy->ops = ops;
-	phy->init_data = init_data;
 
 	ret = dev_set_name(&phy->dev, "phy-%s.%d", dev_name(dev), id);
 	if (ret)
@@ -741,7 +702,6 @@ EXPORT_SYMBOL_GPL(phy_create);
  * @dev: device that is creating the new phy
  * @node: device node of the phy
  * @ops: function pointers for performing phy operations
- * @init_data: contains the list of PHY consumers or NULL
  *
  * Creates a new PHY device adding it to the PHY class.
  * While at that, it also associates the device with the phy using devres.
@@ -749,8 +709,7 @@ EXPORT_SYMBOL_GPL(phy_create);
  * then, devres data is freed.
  */
 struct phy *devm_phy_create(struct device *dev, struct device_node *node,
-			    const struct phy_ops *ops,
-			    struct phy_init_data *init_data)
+			    const struct phy_ops *ops)
 {
 	struct phy **ptr, *phy;
 
@@ -758,7 +717,7 @@ struct phy *devm_phy_create(struct device *dev, struct device_node *node,
 	if (!ptr)
 		return ERR_PTR(-ENOMEM);
 
-	phy = phy_create(dev, node, ops, init_data);
+	phy = phy_create(dev, node, ops);
 	if (!IS_ERR(phy)) {
 		*ptr = phy;
 		devres_add(dev, ptr);
diff --git a/drivers/phy/phy-exynos-dp-video.c b/drivers/phy/phy-exynos-dp-video.c
index 84f49e5a3f2..f86cbe68dda 100644
--- a/drivers/phy/phy-exynos-dp-video.c
+++ b/drivers/phy/phy-exynos-dp-video.c
@@ -112,7 +112,7 @@ static int exynos_dp_video_phy_probe(struct platform_device *pdev)
 	match = of_match_node(exynos_dp_video_phy_of_match, dev->of_node);
 	state->drvdata = match->data;
 
-	phy = devm_phy_create(dev, NULL, &exynos_dp_video_phy_ops, NULL);
+	phy = devm_phy_create(dev, NULL, &exynos_dp_video_phy_ops);
 	if (IS_ERR(phy)) {
 		dev_err(dev, "failed to create Display Port PHY\n");
 		return PTR_ERR(phy);
diff --git a/drivers/phy/phy-exynos-mipi-video.c b/drivers/phy/phy-exynos-mipi-video.c
index 6a9bef13861..943e0f88a12 100644
--- a/drivers/phy/phy-exynos-mipi-video.c
+++ b/drivers/phy/phy-exynos-mipi-video.c
@@ -137,7 +137,7 @@ static int exynos_mipi_video_phy_probe(struct platform_device *pdev)
 
 	for (i = 0; i < EXYNOS_MIPI_PHYS_NUM; i++) {
 		struct phy *phy = devm_phy_create(dev, NULL,
-					&exynos_mipi_video_phy_ops, NULL);
+						  &exynos_mipi_video_phy_ops);
 		if (IS_ERR(phy)) {
 			dev_err(dev, "failed to create PHY %d\n", i);
 			return PTR_ERR(phy);
diff --git a/drivers/phy/phy-exynos5-usbdrd.c b/drivers/phy/phy-exynos5-usbdrd.c
index f756aca871d..b3ca3bc2314 100644
--- a/drivers/phy/phy-exynos5-usbdrd.c
+++ b/drivers/phy/phy-exynos5-usbdrd.c
@@ -637,8 +637,7 @@ static int exynos5_usbdrd_phy_probe(struct platform_device *pdev)
 
 	for (i = 0; i < EXYNOS5_DRDPHYS_NUM; i++) {
 		struct phy *phy = devm_phy_create(dev, NULL,
-						  &exynos5_usbdrd_phy_ops,
-						  NULL);
+						  &exynos5_usbdrd_phy_ops);
 		if (IS_ERR(phy)) {
 			dev_err(dev, "Failed to create usbdrd_phy phy\n");
 			return PTR_ERR(phy);
diff --git a/drivers/phy/phy-exynos5250-sata.c b/drivers/phy/phy-exynos5250-sata.c
index 54cf4ae60d2..bc858cc800a 100644
--- a/drivers/phy/phy-exynos5250-sata.c
+++ b/drivers/phy/phy-exynos5250-sata.c
@@ -210,7 +210,7 @@ static int exynos_sata_phy_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	sata_phy->phy = devm_phy_create(dev, NULL, &exynos_sata_phy_ops, NULL);
+	sata_phy->phy = devm_phy_create(dev, NULL, &exynos_sata_phy_ops);
 	if (IS_ERR(sata_phy->phy)) {
 		clk_disable_unprepare(sata_phy->phyclk);
 		dev_err(dev, "failed to create PHY\n");
diff --git a/drivers/phy/phy-hix5hd2-sata.c b/drivers/phy/phy-hix5hd2-sata.c
index d5d978085c6..a80ff9d7fe1 100644
--- a/drivers/phy/phy-hix5hd2-sata.c
+++ b/drivers/phy/phy-hix5hd2-sata.c
@@ -156,7 +156,7 @@ static int hix5hd2_sata_phy_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->peri_ctrl))
 		priv->peri_ctrl = NULL;
 
-	phy = devm_phy_create(dev, NULL, &hix5hd2_sata_phy_ops, NULL);
+	phy = devm_phy_create(dev, NULL, &hix5hd2_sata_phy_ops);
 	if (IS_ERR(phy)) {
 		dev_err(dev, "failed to create PHY\n");
 		return PTR_ERR(phy);
diff --git a/drivers/phy/phy-miphy28lp.c b/drivers/phy/phy-miphy28lp.c
index 87dcc9ab7f2..e34da13885e 100644
--- a/drivers/phy/phy-miphy28lp.c
+++ b/drivers/phy/phy-miphy28lp.c
@@ -1231,7 +1231,7 @@ static int miphy28lp_probe(struct platform_device *pdev)
 
 		miphy_dev->phys[port] = miphy_phy;
 
-		phy = devm_phy_create(&pdev->dev, child, &miphy28lp_ops, NULL);
+		phy = devm_phy_create(&pdev->dev, child, &miphy28lp_ops);
 		if (IS_ERR(phy)) {
 			dev_err(&pdev->dev, "failed to create PHY\n");
 			return PTR_ERR(phy);
diff --git a/drivers/phy/phy-miphy365x.c b/drivers/phy/phy-miphy365x.c
index 801afaf2d44..239930edfe1 100644
--- a/drivers/phy/phy-miphy365x.c
+++ b/drivers/phy/phy-miphy365x.c
@@ -593,7 +593,7 @@ static int miphy365x_probe(struct platform_device *pdev)
 
 		miphy_dev->phys[port] = miphy_phy;
 
-		phy = devm_phy_create(&pdev->dev, child, &miphy365x_ops, NULL);
+		phy = devm_phy_create(&pdev->dev, child, &miphy365x_ops);
 		if (IS_ERR(phy)) {
 			dev_err(&pdev->dev, "failed to create PHY\n");
 			return PTR_ERR(phy);
diff --git a/drivers/phy/phy-mvebu-sata.c b/drivers/phy/phy-mvebu-sata.c
index d395558cb12..03b94f92e6f 100644
--- a/drivers/phy/phy-mvebu-sata.c
+++ b/drivers/phy/phy-mvebu-sata.c
@@ -101,7 +101,7 @@ static int phy_mvebu_sata_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->clk))
 		return PTR_ERR(priv->clk);
 
-	phy = devm_phy_create(&pdev->dev, NULL, &phy_mvebu_sata_ops, NULL);
+	phy = devm_phy_create(&pdev->dev, NULL, &phy_mvebu_sata_ops);
 	if (IS_ERR(phy))
 		return PTR_ERR(phy);
 
diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c
index f091576b644..5dab3ec71a1 100644
--- a/drivers/phy/phy-omap-usb2.c
+++ b/drivers/phy/phy-omap-usb2.c
@@ -260,7 +260,7 @@ static int omap_usb2_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, phy);
 	pm_runtime_enable(phy->dev);
 
-	generic_phy = devm_phy_create(phy->dev, NULL, &ops, NULL);
+	generic_phy = devm_phy_create(phy->dev, NULL, &ops);
 	if (IS_ERR(generic_phy)) {
 		pm_runtime_disable(phy->dev);
 		return PTR_ERR(generic_phy);
diff --git a/drivers/phy/phy-qcom-apq8064-sata.c b/drivers/phy/phy-qcom-apq8064-sata.c
index 7b3ddfb6589..4b243f7a10e 100644
--- a/drivers/phy/phy-qcom-apq8064-sata.c
+++ b/drivers/phy/phy-qcom-apq8064-sata.c
@@ -228,8 +228,7 @@ static int qcom_apq8064_sata_phy_probe(struct platform_device *pdev)
 	if (IS_ERR(phy->mmio))
 		return PTR_ERR(phy->mmio);
 
-	generic_phy = devm_phy_create(dev, NULL, &qcom_apq8064_sata_phy_ops,
-				      NULL);
+	generic_phy = devm_phy_create(dev, NULL, &qcom_apq8064_sata_phy_ops);
 	if (IS_ERR(generic_phy)) {
 		dev_err(dev, "%s: failed to create phy\n", __func__);
 		return PTR_ERR(generic_phy);
diff --git a/drivers/phy/phy-qcom-ipq806x-sata.c b/drivers/phy/phy-qcom-ipq806x-sata.c
index 759b0bf5b6b..6f2fe262791 100644
--- a/drivers/phy/phy-qcom-ipq806x-sata.c
+++ b/drivers/phy/phy-qcom-ipq806x-sata.c
@@ -150,8 +150,7 @@ static int qcom_ipq806x_sata_phy_probe(struct platform_device *pdev)
 	if (IS_ERR(phy->mmio))
 		return PTR_ERR(phy->mmio);
 
-	generic_phy = devm_phy_create(dev, NULL, &qcom_ipq806x_sata_phy_ops,
-				      NULL);
+	generic_phy = devm_phy_create(dev, NULL, &qcom_ipq806x_sata_phy_ops);
 	if (IS_ERR(generic_phy)) {
 		dev_err(dev, "%s: failed to create phy\n", __func__);
 		return PTR_ERR(generic_phy);
diff --git a/drivers/phy/phy-rcar-gen2.c b/drivers/phy/phy-rcar-gen2.c
index 2793af17799..778276aba3a 100644
--- a/drivers/phy/phy-rcar-gen2.c
+++ b/drivers/phy/phy-rcar-gen2.c
@@ -304,7 +304,7 @@ static int rcar_gen2_phy_probe(struct platform_device *pdev)
 			phy->select_value = select_value[channel_num][n];
 
 			phy->phy = devm_phy_create(dev, NULL,
-						   &rcar_gen2_phy_ops, NULL);
+						   &rcar_gen2_phy_ops);
 			if (IS_ERR(phy->phy)) {
 				dev_err(dev, "Failed to create PHY\n");
 				return PTR_ERR(phy->phy);
diff --git a/drivers/phy/phy-samsung-usb2.c b/drivers/phy/phy-samsung-usb2.c
index 908949dfb4d..4a12f66b7fb 100644
--- a/drivers/phy/phy-samsung-usb2.c
+++ b/drivers/phy/phy-samsung-usb2.c
@@ -202,8 +202,7 @@ static int samsung_usb2_phy_probe(struct platform_device *pdev)
 		struct samsung_usb2_phy_instance *p = &drv->instances[i];
 
 		dev_dbg(dev, "Creating phy \"%s\"\n", label);
-		p->phy = devm_phy_create(dev, NULL, &samsung_usb2_phy_ops,
-					 NULL);
+		p->phy = devm_phy_create(dev, NULL, &samsung_usb2_phy_ops);
 		if (IS_ERR(p->phy)) {
 			dev_err(drv->dev, "Failed to create usb2_phy \"%s\"\n",
 				label);
diff --git a/drivers/phy/phy-spear1310-miphy.c b/drivers/phy/phy-spear1310-miphy.c
index 5f4c586ee95..9f47fae7eec 100644
--- a/drivers/phy/phy-spear1310-miphy.c
+++ b/drivers/phy/phy-spear1310-miphy.c
@@ -227,7 +227,7 @@ static int spear1310_miphy_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	priv->phy = devm_phy_create(dev, NULL, &spear1310_miphy_ops, NULL);
+	priv->phy = devm_phy_create(dev, NULL, &spear1310_miphy_ops);
 	if (IS_ERR(priv->phy)) {
 		dev_err(dev, "failed to create SATA PCIe PHY\n");
 		return PTR_ERR(priv->phy);
diff --git a/drivers/phy/phy-spear1340-miphy.c b/drivers/phy/phy-spear1340-miphy.c
index 1ecd0945bad..e42bc200275 100644
--- a/drivers/phy/phy-spear1340-miphy.c
+++ b/drivers/phy/phy-spear1340-miphy.c
@@ -259,7 +259,7 @@ static int spear1340_miphy_probe(struct platform_device *pdev)
 		return PTR_ERR(priv->misc);
 	}
 
-	priv->phy = devm_phy_create(dev, NULL, &spear1340_miphy_ops, NULL);
+	priv->phy = devm_phy_create(dev, NULL, &spear1340_miphy_ops);
 	if (IS_ERR(priv->phy)) {
 		dev_err(dev, "failed to create SATA PCIe PHY\n");
 		return PTR_ERR(priv->phy);
diff --git a/drivers/phy/phy-stih407-usb.c b/drivers/phy/phy-stih407-usb.c
index 42428d4181e..74f0fab3cd8 100644
--- a/drivers/phy/phy-stih407-usb.c
+++ b/drivers/phy/phy-stih407-usb.c
@@ -137,7 +137,7 @@ static int stih407_usb2_picophy_probe(struct platform_device *pdev)
 	}
 	phy_dev->param = res->start;
 
-	phy = devm_phy_create(dev, NULL, &stih407_usb2_picophy_data, NULL);
+	phy = devm_phy_create(dev, NULL, &stih407_usb2_picophy_data);
 	if (IS_ERR(phy)) {
 		dev_err(dev, "failed to create Display Port PHY\n");
 		return PTR_ERR(phy);
diff --git a/drivers/phy/phy-stih41x-usb.c b/drivers/phy/phy-stih41x-usb.c
index 9f16cb8e01f..4ab581eadac 100644
--- a/drivers/phy/phy-stih41x-usb.c
+++ b/drivers/phy/phy-stih41x-usb.c
@@ -148,7 +148,7 @@ static int stih41x_usb_phy_probe(struct platform_device *pdev)
 		return PTR_ERR(phy_dev->clk);
 	}
 
-	phy = devm_phy_create(dev, NULL, &stih41x_usb_phy_ops, NULL);
+	phy = devm_phy_create(dev, NULL, &stih41x_usb_phy_ops);
 
 	if (IS_ERR(phy)) {
 		dev_err(dev, "failed to create phy\n");
diff --git a/drivers/phy/phy-sun4i-usb.c b/drivers/phy/phy-sun4i-usb.c
index 6bd2b0c972c..fb02a67c918 100644
--- a/drivers/phy/phy-sun4i-usb.c
+++ b/drivers/phy/phy-sun4i-usb.c
@@ -298,7 +298,7 @@ static int sun4i_usb_phy_probe(struct platform_device *pdev)
 				return PTR_ERR(phy->pmu);
 		}
 
-		phy->phy = devm_phy_create(dev, NULL, &sun4i_usb_phy_ops, NULL);
+		phy->phy = devm_phy_create(dev, NULL, &sun4i_usb_phy_ops);
 		if (IS_ERR(phy->phy)) {
 			dev_err(dev, "failed to create PHY %d\n", i);
 			return PTR_ERR(phy->phy);
diff --git a/drivers/phy/phy-ti-pipe3.c b/drivers/phy/phy-ti-pipe3.c
index ab1e22d9a1e..c297b7a10d3 100644
--- a/drivers/phy/phy-ti-pipe3.c
+++ b/drivers/phy/phy-ti-pipe3.c
@@ -399,7 +399,7 @@ static int ti_pipe3_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, phy);
 	pm_runtime_enable(phy->dev);
 
-	generic_phy = devm_phy_create(phy->dev, NULL, &ops, NULL);
+	generic_phy = devm_phy_create(phy->dev, NULL, &ops);
 	if (IS_ERR(generic_phy))
 		return PTR_ERR(generic_phy);
 
diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c
index c45a3aa4f2c..d19e4a06b85 100644
--- a/drivers/phy/phy-twl4030-usb.c
+++ b/drivers/phy/phy-twl4030-usb.c
@@ -678,7 +678,7 @@ static int twl4030_usb_probe(struct platform_device *pdev)
 	otg->set_host		= twl4030_set_host;
 	otg->set_peripheral	= twl4030_set_peripheral;
 
-	phy = devm_phy_create(twl->dev, NULL, &ops, NULL);
+	phy = devm_phy_create(twl->dev, NULL, &ops);
 	if (IS_ERR(phy)) {
 		dev_dbg(&pdev->dev, "Failed to create PHY\n");
 		return PTR_ERR(phy);
diff --git a/drivers/phy/phy-xgene.c b/drivers/phy/phy-xgene.c
index f8a51b16ade..29214a36ea2 100644
--- a/drivers/phy/phy-xgene.c
+++ b/drivers/phy/phy-xgene.c
@@ -1707,7 +1707,7 @@ static int xgene_phy_probe(struct platform_device *pdev)
 	ctx->dev = &pdev->dev;
 	platform_set_drvdata(pdev, ctx);
 
-	ctx->phy = devm_phy_create(ctx->dev, NULL, &xgene_phy_ops, NULL);
+	ctx->phy = devm_phy_create(ctx->dev, NULL, &xgene_phy_ops);
 	if (IS_ERR(ctx->phy)) {
 		dev_dbg(&pdev->dev, "Failed to create PHY\n");
 		rc = PTR_ERR(ctx->phy);
diff --git a/drivers/pinctrl/pinctrl-tegra-xusb.c b/drivers/pinctrl/pinctrl-tegra-xusb.c
index 1631ec94fb0..a84299b922c 100644
--- a/drivers/pinctrl/pinctrl-tegra-xusb.c
+++ b/drivers/pinctrl/pinctrl-tegra-xusb.c
@@ -910,7 +910,7 @@ static int tegra_xusb_padctl_probe(struct platform_device *pdev)
 		goto reset;
 	}
 
-	phy = devm_phy_create(&pdev->dev, NULL, &pcie_phy_ops, NULL);
+	phy = devm_phy_create(&pdev->dev, NULL, &pcie_phy_ops);
 	if (IS_ERR(phy)) {
 		err = PTR_ERR(phy);
 		goto unregister;
@@ -919,7 +919,7 @@ static int tegra_xusb_padctl_probe(struct platform_device *pdev)
 	padctl->phys[TEGRA_XUSB_PADCTL_PCIE] = phy;
 	phy_set_drvdata(phy, padctl);
 
-	phy = devm_phy_create(&pdev->dev, NULL, &sata_phy_ops, NULL);
+	phy = devm_phy_create(&pdev->dev, NULL, &sata_phy_ops);
 	if (IS_ERR(phy)) {
 		err = PTR_ERR(phy);
 		goto unregister;
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index 849284e5873..a0197fa1b11 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -61,7 +61,6 @@ struct phy {
 	struct device		dev;
 	int			id;
 	const struct phy_ops	*ops;
-	struct phy_init_data	*init_data;
 	struct mutex		mutex;
 	int			init_count;
 	int			power_count;
@@ -84,32 +83,6 @@ struct phy_provider {
 		struct of_phandle_args *args);
 };
 
-/**
- * struct phy_consumer - represents the phy consumer
- * @dev_name: the device name of the controller that will use this PHY device
- * @port: name given to the consumer port
- */
-struct phy_consumer {
-	const char *dev_name;
-	const char *port;
-};
-
-/**
- * struct phy_init_data - contains the list of PHY consumers
- * @num_consumers: number of consumers for this PHY device
- * @consumers: list of PHY consumers
- */
-struct phy_init_data {
-	unsigned int num_consumers;
-	struct phy_consumer *consumers;
-};
-
-#define PHY_CONSUMER(_dev_name, _port)				\
-{								\
-	.dev_name	= _dev_name,				\
-	.port		= _port,				\
-}
-
 struct phy_lookup {
 	struct list_head node;
 	const char *dev_id;
@@ -166,10 +139,9 @@ struct phy *of_phy_get(struct device_node *np, const char *con_id);
 struct phy *of_phy_simple_xlate(struct device *dev,
 	struct of_phandle_args *args);
 struct phy *phy_create(struct device *dev, struct device_node *node,
-		       const struct phy_ops *ops,
-		       struct phy_init_data *init_data);
+		       const struct phy_ops *ops);
 struct phy *devm_phy_create(struct device *dev, struct device_node *node,
-	const struct phy_ops *ops, struct phy_init_data *init_data);
+			    const struct phy_ops *ops);
 void phy_destroy(struct phy *phy);
 void devm_phy_destroy(struct device *dev, struct phy *phy);
 struct phy_provider *__of_phy_provider_register(struct device *dev,
@@ -310,16 +282,14 @@ static inline struct phy *of_phy_simple_xlate(struct device *dev,
 
 static inline struct phy *phy_create(struct device *dev,
 				     struct device_node *node,
-				     const struct phy_ops *ops,
-				     struct phy_init_data *init_data)
+				     const struct phy_ops *ops)
 {
 	return ERR_PTR(-ENOSYS);
 }
 
 static inline struct phy *devm_phy_create(struct device *dev,
 					  struct device_node *node,
-					  const struct phy_ops *ops,
-					  struct phy_init_data *init_data)
+					  const struct phy_ops *ops)
 {
 	return ERR_PTR(-ENOSYS);
 }
-- 
cgit v1.2.3-70-g09d2


From eadac03e898617521f327faf265932b73ecc3e0f Mon Sep 17 00:00:00 2001
From: Pranith Kumar <bobby.prani@gmail.com>
Date: Fri, 21 Nov 2014 10:05:59 -0500
Subject: percpu: Replace smp_read_barrier_depends() with
 lockless_dereference()

Recently lockless_dereference() was added which can be used in place of
hard-coding smp_read_barrier_depends(). The following PATCH makes the change.

Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/percpu-refcount.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index d5c89e0dd0e..6b0c8187214 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -128,10 +128,8 @@ static inline void percpu_ref_kill(struct percpu_ref *ref)
 static inline bool __ref_is_percpu(struct percpu_ref *ref,
 					  unsigned long __percpu **percpu_countp)
 {
-	unsigned long percpu_ptr = ACCESS_ONCE(ref->percpu_count_ptr);
-
 	/* paired with smp_store_release() in percpu_ref_reinit() */
-	smp_read_barrier_depends();
+	unsigned long percpu_ptr = lockless_dereference(ref->percpu_count_ptr);
 
 	if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC))
 		return false;
-- 
cgit v1.2.3-70-g09d2


From 9f7789f845cc100dd0d94fa1aa083e3373dc03db Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Sat, 22 Nov 2014 08:37:11 -0800
Subject: asm-generic: Remove asm-generic arch_bprm_mm_init()

This is a follow-on to commit 62e88b1c00de 'mm: Make
arch_unmap()/bprm_mm_init() available to all architectures'

I removed the asm-generic version of arch_unmap() in that patch,
but missed arch_bprm_mm_init().  So this broke the build for
architectures using asm-generic/mmu_context.h who actually have
an MMU.

Fixes: 62e88b1c00de 'mm: Make arch_unmap()/bprm_mm_init() available to all architectures'
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: linux-arch@vger.kernel.org
Cc: x86@kernel.org
Link: http://lkml.kernel.org/r/20141122163711.0F037EE6@viggo.jf.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/asm-generic/mmu_context.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/mmu_context.h b/include/asm-generic/mmu_context.h
index 1f2a8f9c926..a7eec910ba6 100644
--- a/include/asm-generic/mmu_context.h
+++ b/include/asm-generic/mmu_context.h
@@ -42,9 +42,4 @@ static inline void activate_mm(struct mm_struct *prev_mm,
 {
 }
 
-static inline void arch_bprm_mm_init(struct mm_struct *mm,
-			struct vm_area_struct *vma)
-{
-}
-
 #endif /* __ASM_GENERIC_MMU_CONTEXT_H */
-- 
cgit v1.2.3-70-g09d2


From 49c71d1c3dccff640cc082875bd8d62988d63df9 Mon Sep 17 00:00:00 2001
From: Fugang Duan <b38611@freescale.com>
Date: Wed, 24 Sep 2014 10:11:18 +0800
Subject: ARM: imx6sx: add imx6sx iomux-gpr field define

Add imx6sx iomux-gpr register field define in "imx6q-iomuxc-gpr.h" header
file, which is not fully define all iomux-gpr registers and fields, only
align with freescale internal tree related GPR macro define.

Signed-off-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: Shawn Guo <shawn.guo@freescale.com>
---
 include/linux/mfd/syscon/imx6q-iomuxc-gpr.h | 39 +++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

(limited to 'include')

diff --git a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h
index ff44374a1a4..c877cad61a1 100644
--- a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h
+++ b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h
@@ -395,4 +395,43 @@
 #define IMX6SL_GPR1_FEC_CLOCK_MUX1_SEL_MASK    (0x3 << 17)
 #define IMX6SL_GPR1_FEC_CLOCK_MUX2_SEL_MASK    (0x1 << 14)
 
+/* For imx6sx iomux gpr register field define */
+#define IMX6SX_GPR1_VDEC_SW_RST_MASK			(0x1 << 20)
+#define IMX6SX_GPR1_VDEC_SW_RST_RESET			(0x1 << 20)
+#define IMX6SX_GPR1_VDEC_SW_RST_RELEASE			(0x0 << 20)
+#define IMX6SX_GPR1_VADC_SW_RST_MASK			(0x1 << 19)
+#define IMX6SX_GPR1_VADC_SW_RST_RESET			(0x1 << 19)
+#define IMX6SX_GPR1_VADC_SW_RST_RELEASE			(0x0 << 19)
+#define IMX6SX_GPR1_FEC_CLOCK_MUX_SEL_MASK		(0x3 << 13)
+#define IMX6SX_GPR1_FEC_CLOCK_PAD_DIR_MASK		(0x3 << 17)
+#define IMX6SX_GPR1_FEC_CLOCK_MUX_SEL_EXT		(0x3 << 13)
+
+#define IMX6SX_GPR4_FEC_ENET1_STOP_REQ			(0x1 << 3)
+#define IMX6SX_GPR4_FEC_ENET2_STOP_REQ			(0x1 << 4)
+
+#define IMX6SX_GPR5_DISP_MUX_LDB_CTRL_MASK		(0x1 << 3)
+#define IMX6SX_GPR5_DISP_MUX_LDB_CTRL_LCDIF1		(0x0 << 3)
+#define IMX6SX_GPR5_DISP_MUX_LDB_CTRL_LCDIF2		(0x1 << 3)
+
+#define IMX6SX_GPR5_CSI2_MUX_CTRL_MASK			(0x3 << 27)
+#define IMX6SX_GPR5_CSI2_MUX_CTRL_EXT_PIN		(0x0 << 27)
+#define IMX6SX_GPR5_CSI2_MUX_CTRL_CVD			(0x1 << 27)
+#define IMX6SX_GPR5_CSI2_MUX_CTRL_VDAC_TO_CSI		(0x2 << 27)
+#define IMX6SX_GPR5_CSI2_MUX_CTRL_GND			(0x3 << 27)
+#define IMX6SX_GPR5_VADC_TO_CSI_CAPTURE_EN_MASK		(0x1 << 26)
+#define IMX6SX_GPR5_VADC_TO_CSI_CAPTURE_EN_ENABLE	(0x1 << 26)
+#define IMX6SX_GPR5_VADC_TO_CSI_CAPTURE_EN_DISABLE	(0x0 << 26)
+#define IMX6SX_GPR5_CSI1_MUX_CTRL_MASK			(0x3 << 4)
+#define IMX6SX_GPR5_CSI1_MUX_CTRL_EXT_PIN		(0x0 << 4)
+#define IMX6SX_GPR5_CSI1_MUX_CTRL_CVD			(0x1 << 4)
+#define IMX6SX_GPR5_CSI1_MUX_CTRL_VDAC_TO_CSI		(0x2 << 4)
+#define IMX6SX_GPR5_CSI1_MUX_CTRL_GND			(0x3 << 4)
+
+#define IMX6SX_GPR5_DISP_MUX_DCIC2_LCDIF2		(0x0 << 2)
+#define IMX6SX_GPR5_DISP_MUX_DCIC2_LVDS			(0x1 << 2)
+#define IMX6SX_GPR5_DISP_MUX_DCIC2_MASK			(0x1 << 2)
+#define IMX6SX_GPR5_DISP_MUX_DCIC1_LCDIF1		(0x0 << 1)
+#define IMX6SX_GPR5_DISP_MUX_DCIC1_LVDS			(0x1 << 1)
+#define IMX6SX_GPR5_DISP_MUX_DCIC1_MASK			(0x1 << 1)
+
 #endif /* __LINUX_IMX6Q_IOMUXC_GPR_H */
-- 
cgit v1.2.3-70-g09d2


From 6f0628aa9f0fb7c877e52d4d8c6edb11bcd91736 Mon Sep 17 00:00:00 2001
From: Lucas Stach <l.stach@pengutronix.de>
Date: Fri, 26 Sep 2014 15:41:00 +0200
Subject: ARM: imx5: add step clock, used when reprogramming PLL1

This is the bypass clock used to feed the ARM partition
while we reprogram PLL1 to another rate.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Signed-off-by: Shawn Guo <shawn.guo@freescale.com>
---
 arch/arm/mach-imx/clk-imx51-imx53.c    | 9 ++++++++-
 include/dt-bindings/clock/imx5-clock.h | 4 +++-
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-imx/clk-imx51-imx53.c b/arch/arm/mach-imx/clk-imx51-imx53.c
index 72d65214223..aafccf4b47c 100644
--- a/arch/arm/mach-imx/clk-imx51-imx53.c
+++ b/arch/arm/mach-imx/clk-imx51-imx53.c
@@ -125,6 +125,8 @@ static const char *mx53_spdif_xtal_sel[] = { "osc", "ckih", "ckih2", "pll4_sw",
 static const char *spdif_sel[] = { "pll1_sw", "pll2_sw", "pll3_sw", "spdif_xtal_sel", };
 static const char *spdif0_com_sel[] = { "spdif0_podf", "ssi1_root_gate", };
 static const char *mx51_spdif1_com_sel[] = { "spdif1_podf", "ssi2_root_gate", };
+static const char *step_sels[] = { "lp_apm", };
+static const char *cpu_podf_sels[] = { "pll1_sw", "step_sel" };
 
 static struct clk *clk[IMX5_CLK_END];
 static struct clk_onecell_data clk_data;
@@ -193,7 +195,9 @@ static void __init mx5_clocks_common_init(void __iomem *ccm_base)
 	clk[IMX5_CLK_USB_PHY_PODF]	= imx_clk_divider("usb_phy_podf", "usb_phy_pred", MXC_CCM_CDCDR, 0, 3);
 	clk[IMX5_CLK_USB_PHY_SEL]	= imx_clk_mux("usb_phy_sel", MXC_CCM_CSCMR1, 26, 1,
 						usb_phy_sel_str, ARRAY_SIZE(usb_phy_sel_str));
-	clk[IMX5_CLK_CPU_PODF]		= imx_clk_divider("cpu_podf", "pll1_sw", MXC_CCM_CACRR, 0, 3);
+	clk[IMX5_CLK_STEP_SEL]		= imx_clk_mux("step_sel", MXC_CCM_CCSR, 7, 2, step_sels, ARRAY_SIZE(step_sels));
+	clk[IMX5_CLK_CPU_PODF_SEL]	= imx_clk_mux("cpu_podf_sel", MXC_CCM_CCSR, 2, 1, cpu_podf_sels, ARRAY_SIZE(cpu_podf_sels));
+	clk[IMX5_CLK_CPU_PODF]		= imx_clk_divider("cpu_podf", "cpu_podf_sel", MXC_CCM_CACRR, 0, 3);
 	clk[IMX5_CLK_DI_PRED]		= imx_clk_divider("di_pred", "pll3_sw", MXC_CCM_CDCDR, 6, 3);
 	clk[IMX5_CLK_IIM_GATE]		= imx_clk_gate2("iim_gate", "ipg", MXC_CCM_CCGR0, 30);
 	clk[IMX5_CLK_UART1_IPG_GATE]	= imx_clk_gate2("uart1_ipg_gate", "ipg", MXC_CCM_CCGR1, 6);
@@ -551,6 +555,9 @@ static void __init mx53_clocks_init(struct device_node *np)
 	/* move can bus clk to 24MHz */
 	clk_set_parent(clk[IMX5_CLK_CAN_SEL], clk[IMX5_CLK_LP_APM]);
 
+	/* make sure step clock is running from 24MHz */
+	clk_set_parent(clk[IMX5_CLK_STEP_SEL], clk[IMX5_CLK_LP_APM]);
+
 	clk_prepare_enable(clk[IMX5_CLK_IIM_GATE]);
 	imx_print_silicon_rev("i.MX53", mx53_revision());
 	clk_disable_unprepare(clk[IMX5_CLK_IIM_GATE]);
diff --git a/include/dt-bindings/clock/imx5-clock.h b/include/dt-bindings/clock/imx5-clock.h
index 5f2667ecd98..1a36ff4ace1 100644
--- a/include/dt-bindings/clock/imx5-clock.h
+++ b/include/dt-bindings/clock/imx5-clock.h
@@ -198,6 +198,8 @@
 #define IMX5_CLK_OCRAM			186
 #define IMX5_CLK_SAHARA_IPG_GATE	187
 #define IMX5_CLK_SATA_REF		188
-#define IMX5_CLK_END			189
+#define IMX5_CLK_STEP_SEL		189
+#define IMX5_CLK_CPU_PODF_SEL		190
+#define IMX5_CLK_END			191
 
 #endif /* __DT_BINDINGS_CLOCK_IMX5_H */
-- 
cgit v1.2.3-70-g09d2


From 82a40b54820601aad0facf72050c62ae7fc7d4df Mon Sep 17 00:00:00 2001
From: Lucas Stach <l.stach@pengutronix.de>
Date: Fri, 26 Sep 2014 15:41:02 +0200
Subject: ARM: imx53: clk: add ARM clock

The ARM clock is a virtual clock feeding the ARM partition of
the SoC. It controls multiple other clocks to ensure the right
sequencing when cpufreq changes the CPU clock rate.

Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Signed-off-by: Shawn Guo <shawn.guo@freescale.com>
---
 arch/arm/mach-imx/clk-imx51-imx53.c    | 5 +++++
 include/dt-bindings/clock/imx5-clock.h | 3 ++-
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/arm/mach-imx/clk-imx51-imx53.c b/arch/arm/mach-imx/clk-imx51-imx53.c
index aafccf4b47c..0f7e536147c 100644
--- a/arch/arm/mach-imx/clk-imx51-imx53.c
+++ b/arch/arm/mach-imx/clk-imx51-imx53.c
@@ -541,6 +541,11 @@ static void __init mx53_clocks_init(struct device_node *np)
 	clk[IMX5_CLK_CKO2]		= imx_clk_gate2("cko2", "cko2_podf", MXC_CCM_CCOSR, 24);
 	clk[IMX5_CLK_SPDIF_XTAL_SEL]	= imx_clk_mux("spdif_xtal_sel", MXC_CCM_CSCMR1, 2, 2,
 						mx53_spdif_xtal_sel, ARRAY_SIZE(mx53_spdif_xtal_sel));
+	clk[IMX5_CLK_ARM]		= imx_clk_cpu("arm", "cpu_podf",
+						clk[IMX5_CLK_CPU_PODF],
+						clk[IMX5_CLK_CPU_PODF_SEL],
+						clk[IMX5_CLK_PLL1_SW],
+						clk[IMX5_CLK_STEP_SEL]);
 
 	imx_check_clocks(clk, ARRAY_SIZE(clk));
 
diff --git a/include/dt-bindings/clock/imx5-clock.h b/include/dt-bindings/clock/imx5-clock.h
index 1a36ff4ace1..f4b7478e23c 100644
--- a/include/dt-bindings/clock/imx5-clock.h
+++ b/include/dt-bindings/clock/imx5-clock.h
@@ -200,6 +200,7 @@
 #define IMX5_CLK_SATA_REF		188
 #define IMX5_CLK_STEP_SEL		189
 #define IMX5_CLK_CPU_PODF_SEL		190
-#define IMX5_CLK_END			191
+#define IMX5_CLK_ARM			191
+#define IMX5_CLK_END			192
 
 #endif /* __DT_BINDINGS_CLOCK_IMX5_H */
-- 
cgit v1.2.3-70-g09d2


From 891d4a48f7da39de2be17a59b47df62dccf0f3d5 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Sun, 9 Nov 2014 23:10:33 +0800
Subject: PCI/MSI: Rename __read_msi_msg() to __pci_read_msi_msg()

Rename __read_msi_msg() to __pci_read_msi_msg() and kill unused
read_msi_msg(). It's a preparation to separate generic MSI code from
PCI core.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/powerpc/platforms/pseries/msi.c | 2 +-
 arch/x86/pci/xen.c                   | 2 +-
 drivers/pci/msi.c                    | 9 +--------
 include/linux/msi.h                  | 5 +++--
 4 files changed, 6 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 8ab5add4ac8..90f756d0f58 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -476,7 +476,7 @@ again:
 		irq_set_msi_desc(virq, entry);
 
 		/* Read config space back so we can restore after reset */
-		__read_msi_msg(entry, &msg);
+		__pci_read_msi_msg(entry, &msg);
 		entry->msg = msg;
 	}
 
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 466b978e13a..ff0068b8ce5 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -229,7 +229,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		return 1;
 
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
-		__read_msi_msg(msidesc, &msg);
+		__pci_read_msi_msg(msidesc, &msg);
 		pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
 			((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
 		if (msg.data != XEN_PIRQ_MSI_DATA ||
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 5cb471ec3e6..c77adc735f8 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -252,7 +252,7 @@ void default_restore_msi_irqs(struct pci_dev *dev)
 		default_restore_msi_irq(dev, entry->irq);
 }
 
-void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
+void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
 	BUG_ON(entry->dev->current_state != PCI_D0);
 
@@ -282,13 +282,6 @@ void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 	}
 }
 
-void read_msi_msg(unsigned int irq, struct msi_msg *msg)
-{
-	struct msi_desc *entry = irq_get_msi_desc(irq);
-
-	__read_msi_msg(entry, msg);
-}
-
 void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
 	/* Assert that the cache is valid, assuming that
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 6704991b017..f36c37b46f1 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -16,12 +16,11 @@ struct irq_data;
 struct msi_desc;
 void mask_msi_irq(struct irq_data *data);
 void unmask_msi_irq(struct irq_data *data);
-void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
-void read_msi_msg(unsigned int irq, struct msi_msg *msg);
 void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg);
 void write_msi_msg(unsigned int irq, struct msi_msg *msg);
+
 u32 __msix_mask_irq(struct msi_desc *desc, u32 flag);
 u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag);
 
@@ -51,6 +50,8 @@ struct msi_desc {
 	struct msi_msg msg;
 };
 
+void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
+
 /*
  * The arch hooks to setup up msi irqs. Those functions are
  * implemented as weak symbols so that they /can/ be overriden by
-- 
cgit v1.2.3-70-g09d2


From 83a18912b0e8d275001bca6fc9c0fe519d98f280 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Sun, 9 Nov 2014 23:10:34 +0800
Subject: PCI/MSI: Rename write_msi_msg() to pci_write_msi_msg()

Rename write_msi_msg() to pci_write_msi_msg() to mark it as PCI
specific.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/arm/mach-iop13xx/msi.c            |  2 +-
 arch/ia64/kernel/msi_ia64.c            |  4 ++--
 arch/ia64/sn/kernel/msi_sn.c           |  4 ++--
 arch/mips/pci/msi-octeon.c             |  2 +-
 arch/mips/pci/msi-xlp.c                |  4 ++--
 arch/mips/pci/pci-xlr.c                |  2 +-
 arch/powerpc/platforms/cell/axon_msi.c |  2 +-
 arch/powerpc/platforms/powernv/pci.c   |  2 +-
 arch/powerpc/sysdev/fsl_msi.c          |  2 +-
 arch/powerpc/sysdev/mpic_pasemi_msi.c  |  2 +-
 arch/powerpc/sysdev/mpic_u3msi.c       |  2 +-
 arch/powerpc/sysdev/ppc4xx_hsta_msi.c  |  2 +-
 arch/powerpc/sysdev/ppc4xx_msi.c       |  2 +-
 arch/s390/pci/pci.c                    |  2 +-
 arch/sparc/kernel/pci_msi.c            |  2 +-
 arch/tile/kernel/pci_gx.c              |  2 +-
 arch/x86/kernel/apic/io_apic.c         |  4 ++--
 arch/x86/pci/xen.c                     |  2 +-
 drivers/irqchip/irq-armada-370-xp.c    |  2 +-
 drivers/pci/host/pci-tegra.c           |  2 +-
 drivers/pci/host/pcie-designware.c     |  2 +-
 drivers/pci/host/pcie-rcar.c           |  2 +-
 drivers/pci/host/pcie-xilinx.c         |  2 +-
 drivers/pci/msi.c                      | 10 +++++-----
 drivers/vfio/pci/vfio_pci_intrs.c      |  2 +-
 include/linux/msi.h                    | 14 ++++++++++++--
 26 files changed, 45 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-iop13xx/msi.c b/arch/arm/mach-iop13xx/msi.c
index e7730cf9c15..3f7739cdb85 100644
--- a/arch/arm/mach-iop13xx/msi.c
+++ b/arch/arm/mach-iop13xx/msi.c
@@ -153,7 +153,7 @@ int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)
 	id = iop13xx_cpu_id();
 	msg.data = (id << IOP13XX_MU_MIMR_CORE_SELECT) | (irq & 0x7f);
 
-	write_msi_msg(irq, &msg);
+	pci_write_msi_msg(irq, &msg);
 	irq_set_chip_and_handler(irq, &iop13xx_msi_chip, handle_simple_irq);
 
 	return 0;
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 8c3730c3c63..35b10dd2bb7 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -35,7 +35,7 @@ static int ia64_set_msi_irq_affinity(struct irq_data *idata,
 	data |= MSI_DATA_VECTOR(irq_to_vector(irq));
 	msg.data = data;
 
-	write_msi_msg(irq, &msg);
+	pci_write_msi_msg(irq, &msg);
 	cpumask_copy(idata->affinity, cpumask_of(cpu));
 
 	return 0;
@@ -71,7 +71,7 @@ int ia64_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)
 		MSI_DATA_DELIVERY_FIXED |
 		MSI_DATA_VECTOR(vector);
 
-	write_msi_msg(irq, &msg);
+	pci_write_msi_msg(irq, &msg);
 	irq_set_chip_and_handler(irq, &ia64_msi_chip, handle_edge_irq);
 
 	return 0;
diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c
index 446e7799928..433cafed5c3 100644
--- a/arch/ia64/sn/kernel/msi_sn.c
+++ b/arch/ia64/sn/kernel/msi_sn.c
@@ -145,7 +145,7 @@ int sn_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *entry)
 	msg.data = 0x100 + irq;
 
 	irq_set_msi_desc(irq, entry);
-	write_msi_msg(irq, &msg);
+	pci_write_msi_msg(irq, &msg);
 	irq_set_chip_and_handler(irq, &sn_msi_chip, handle_edge_irq);
 
 	return 0;
@@ -205,7 +205,7 @@ static int sn_set_msi_irq_affinity(struct irq_data *data,
 	msg.address_hi = (u32)(bus_addr >> 32);
 	msg.address_lo = (u32)(bus_addr & 0x00000000ffffffff);
 
-	write_msi_msg(irq, &msg);
+	pci_write_msi_msg(irq, &msg);
 	cpumask_copy(data->affinity, cpu_mask);
 
 	return 0;
diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index 63bbe07a1cc..cffaaf4aae3 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -178,7 +178,7 @@ msi_irq_allocated:
 	pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
 
 	irq_set_msi_desc(irq, desc);
-	write_msi_msg(irq, &msg);
+	pci_write_msi_msg(irq, &msg);
 	return 0;
 }
 
diff --git a/arch/mips/pci/msi-xlp.c b/arch/mips/pci/msi-xlp.c
index fa374fe3746..81ea2b40db6 100644
--- a/arch/mips/pci/msi-xlp.c
+++ b/arch/mips/pci/msi-xlp.c
@@ -345,7 +345,7 @@ static int xlp_setup_msi(uint64_t lnkbase, int node, int link,
 	if (ret < 0)
 		return ret;
 
-	write_msi_msg(xirq, &msg);
+	pci_write_msi_msg(xirq, &msg);
 	return 0;
 }
 
@@ -448,7 +448,7 @@ static int xlp_setup_msix(uint64_t lnkbase, int node, int link,
 		return ret;
 	}
 
-	write_msi_msg(xirq, &msg);
+	pci_write_msi_msg(xirq, &msg);
 	return 0;
 }
 
diff --git a/arch/mips/pci/pci-xlr.c b/arch/mips/pci/pci-xlr.c
index 0dde80332d3..26d2dabef28 100644
--- a/arch/mips/pci/pci-xlr.c
+++ b/arch/mips/pci/pci-xlr.c
@@ -260,7 +260,7 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
 	if (ret < 0)
 		return ret;
 
-	write_msi_msg(irq, &msg);
+	pci_write_msi_msg(irq, &msg);
 	return 0;
 }
 #endif
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index 862b32702d2..26fa3432352 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -279,7 +279,7 @@ static int axon_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 
 		irq_set_msi_desc(virq, entry);
 		msg.data = virq;
-		write_msi_msg(virq, &msg);
+		pci_write_msi_msg(virq, &msg);
 	}
 
 	return 0;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index b3ca77ddf36..e79a38a1df9 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -91,7 +91,7 @@ static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 			return rc;
 		}
 		irq_set_msi_desc(virq, entry);
-		write_msi_msg(virq, &msg);
+		pci_write_msi_msg(virq, &msg);
 	}
 	return 0;
 }
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index de40b48b460..bd5a9f7c002 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -242,7 +242,7 @@ static int fsl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 		irq_set_msi_desc(virq, entry);
 
 		fsl_compose_msi_msg(pdev, hwirq, &msg, msi_data);
-		write_msi_msg(virq, &msg);
+		pci_write_msi_msg(virq, &msg);
 	}
 	return 0;
 
diff --git a/arch/powerpc/sysdev/mpic_pasemi_msi.c b/arch/powerpc/sysdev/mpic_pasemi_msi.c
index 15dccd35fa1..45a6f407883 100644
--- a/arch/powerpc/sysdev/mpic_pasemi_msi.c
+++ b/arch/powerpc/sysdev/mpic_pasemi_msi.c
@@ -136,7 +136,7 @@ static int pasemi_msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 		 * register to generate MSI [512...1023]
 		 */
 		msg.data = hwirq-0x200;
-		write_msi_msg(virq, &msg);
+		pci_write_msi_msg(virq, &msg);
 	}
 
 	return 0;
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index 623d7fba15b..ac6f1f9d03c 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -171,7 +171,7 @@ static int u3msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 		printk("u3msi: allocated virq 0x%x (hw 0x%x) addr 0x%lx\n",
 			  virq, hwirq, (unsigned long)addr);
 		msg.data = hwirq;
-		write_msi_msg(virq, &msg);
+		pci_write_msi_msg(virq, &msg);
 
 		hwirq++;
 	}
diff --git a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
index a6a4dbda907..908105f835d 100644
--- a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
@@ -85,7 +85,7 @@ static int hsta_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 			msi_bitmap_free_hwirqs(&ppc4xx_hsta_msi.bmp, irq, 1);
 			return -EINVAL;
 		}
-		write_msi_msg(hwirq, &msg);
+		pci_write_msi_msg(hwirq, &msg);
 	}
 
 	return 0;
diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c
index 22b5200636e..518eabbe0bd 100644
--- a/arch/powerpc/sysdev/ppc4xx_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_msi.c
@@ -116,7 +116,7 @@ static int ppc4xx_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 
 		irq_set_msi_desc(virq, entry);
 		msg.data = int_no;
-		write_msi_msg(virq, &msg);
+		pci_write_msi_msg(virq, &msg);
 	}
 	return 0;
 }
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 552b9908aa7..ad1a9e2a183 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -403,7 +403,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 		msg.data = hwirq;
 		msg.address_lo = zdev->msi_addr & 0xffffffff;
 		msg.address_hi = zdev->msi_addr >> 32;
-		write_msi_msg(irq, &msg);
+		pci_write_msi_msg(irq, &msg);
 		airq_iv_set_data(zdev->aibv, hwirq, irq);
 		hwirq++;
 	}
diff --git a/arch/sparc/kernel/pci_msi.c b/arch/sparc/kernel/pci_msi.c
index 580651af73f..73db0ed80d8 100644
--- a/arch/sparc/kernel/pci_msi.c
+++ b/arch/sparc/kernel/pci_msi.c
@@ -161,7 +161,7 @@ static int sparc64_setup_msi_irq(unsigned int *irq_p,
 	msg.data = msi;
 
 	irq_set_msi_desc(*irq_p, entry);
-	write_msi_msg(*irq_p, &msg);
+	pci_write_msi_msg(*irq_p, &msg);
 
 	return 0;
 
diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c
index e39f9c54280..376d9f1d995 100644
--- a/arch/tile/kernel/pci_gx.c
+++ b/arch/tile/kernel/pci_gx.c
@@ -1590,7 +1590,7 @@ int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)
 	msg.address_hi = msi_addr >> 32;
 	msg.address_lo = msi_addr & 0xffffffff;
 
-	write_msi_msg(irq, &msg);
+	pci_write_msi_msg(irq, &msg);
 	irq_set_chip_and_handler(irq, &tilegx_msi_chip, handle_level_irq);
 	irq_set_handler_data(irq, controller);
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 1183d545da1..d775aef42b8 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3158,7 +3158,7 @@ msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
-	__write_msi_msg(data->msi_desc, &msg);
+	__pci_write_msi_msg(data->msi_desc, &msg);
 
 	return IRQ_SET_MASK_OK_NOCOPY;
 }
@@ -3196,7 +3196,7 @@ int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 	 * MSI message denotes a contiguous group of IRQs, written for 0th IRQ.
 	 */
 	if (!irq_offset)
-		write_msi_msg(irq, &msg);
+		pci_write_msi_msg(irq, &msg);
 
 	setup_remapped_irq(irq, irq_cfg(irq), chip);
 
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index ff0068b8ce5..1819a91bbb9 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -240,7 +240,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 				goto error;
 			}
 			xen_msi_compose_msg(dev, pirq, &msg);
-			__write_msi_msg(msidesc, &msg);
+			__pci_write_msi_msg(msidesc, &msg);
 			dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
 		} else {
 			dev_dbg(&dev->dev,
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 4e202375e02..8c7f077abb0 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -156,7 +156,7 @@ static int armada_370_xp_setup_msi_irq(struct msi_controller *chip,
 	msg.address_hi = 0;
 	msg.data = 0xf00 | (hwirq + 16);
 
-	write_msi_msg(virq, &msg);
+	pci_write_msi_msg(virq, &msg);
 	return 0;
 }
 
diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c
index 1f01faa918c..31841718bed 100644
--- a/drivers/pci/host/pci-tegra.c
+++ b/drivers/pci/host/pci-tegra.c
@@ -1299,7 +1299,7 @@ static int tegra_msi_setup_irq(struct msi_controller *chip,
 	msg.address_hi = 0;
 	msg.data = hwirq;
 
-	write_msi_msg(irq, &msg);
+	pci_write_msi_msg(irq, &msg);
 
 	return 0;
 }
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index 5278d3e6307..e03f4e7e1f7 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -298,7 +298,7 @@ static int dw_msi_setup_irq(struct msi_controller *chip, struct pci_dev *pdev,
 	else
 		msg.data = pos;
 
-	write_msi_msg(irq, &msg);
+	pci_write_msi_msg(irq, &msg);
 
 	return 0;
 }
diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c
index c2e3fcb55fd..c1177cd55ce 100644
--- a/drivers/pci/host/pcie-rcar.c
+++ b/drivers/pci/host/pcie-rcar.c
@@ -640,7 +640,7 @@ static int rcar_msi_setup_irq(struct msi_controller *chip, struct pci_dev *pdev,
 	msg.address_hi = rcar_pci_read_reg(pcie, PCIEMSIAUR);
 	msg.data = hwirq;
 
-	write_msi_msg(irq, &msg);
+	pci_write_msi_msg(irq, &msg);
 
 	return 0;
 }
diff --git a/drivers/pci/host/pcie-xilinx.c b/drivers/pci/host/pcie-xilinx.c
index eca292347c6..67683380f0f 100644
--- a/drivers/pci/host/pcie-xilinx.c
+++ b/drivers/pci/host/pcie-xilinx.c
@@ -375,7 +375,7 @@ static int xilinx_pcie_msi_setup_irq(struct msi_controller *chip,
 	msg.address_lo = msg_addr;
 	msg.data = irq;
 
-	write_msi_msg(irq, &msg);
+	pci_write_msi_msg(irq, &msg);
 
 	return 0;
 }
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index c77adc735f8..156ba8f809b 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -130,7 +130,7 @@ static void default_restore_msi_irq(struct pci_dev *dev, int irq)
 	}
 
 	if (entry)
-		__write_msi_msg(entry, &entry->msg);
+		__pci_write_msi_msg(entry, &entry->msg);
 }
 
 void __weak arch_restore_msi_irqs(struct pci_dev *dev)
@@ -300,7 +300,7 @@ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
 }
 EXPORT_SYMBOL_GPL(get_cached_msi_msg);
 
-void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
+void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
 	if (entry->dev->current_state != PCI_D0) {
 		/* Don't touch the hardware now */
@@ -337,13 +337,13 @@ void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 	entry->msg = *msg;
 }
 
-void write_msi_msg(unsigned int irq, struct msi_msg *msg)
+void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
 	struct msi_desc *entry = irq_get_msi_desc(irq);
 
-	__write_msi_msg(entry, msg);
+	__pci_write_msi_msg(entry, msg);
 }
-EXPORT_SYMBOL_GPL(write_msi_msg);
+EXPORT_SYMBOL_GPL(pci_write_msi_msg);
 
 static void free_msi_irqs(struct pci_dev *dev)
 {
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 553212f037c..e8d695b3f54 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -560,7 +560,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 		struct msi_msg msg;
 
 		get_cached_msi_msg(irq, &msg);
-		write_msi_msg(irq, &msg);
+		pci_write_msi_msg(irq, &msg);
 	}
 
 	ret = request_irq(irq, vfio_msihandler, 0,
diff --git a/include/linux/msi.h b/include/linux/msi.h
index f36c37b46f1..301adecbc34 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -17,9 +17,7 @@ struct msi_desc;
 void mask_msi_irq(struct irq_data *data);
 void unmask_msi_irq(struct irq_data *data);
 void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
-void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg);
-void write_msi_msg(unsigned int irq, struct msi_msg *msg);
 
 u32 __msix_mask_irq(struct msi_desc *desc, u32 flag);
 u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag);
@@ -51,6 +49,18 @@ struct msi_desc {
 };
 
 void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
+void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
+void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg);
+
+/* Conversion helpers. Should be removed after merging */
+static inline void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
+{
+	__pci_write_msi_msg(entry, msg);
+}
+static inline void write_msi_msg(int irq, struct msi_msg *msg)
+{
+	pci_write_msi_msg(irq, msg);
+}
 
 /*
  * The arch hooks to setup up msi irqs. Those functions are
-- 
cgit v1.2.3-70-g09d2


From 23ed8d57f3b87520e045ba0e3a2340638b31198a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 23 Nov 2014 11:55:58 +0100
Subject: PCI/MSI: Rename mask/unmask_msi_irq et al

mask/unmask_msi_irq and __mask_msi/msix_irq are PCI/MSI specific
functions and should be named accordingly. This is a preparatory patch
to support MSI on non PCI devices.

Rename mask/unmask_msi_irq to pci_msi_mask/unmask_irq and document the
functions. Provide conversion helpers.

Rename __mask_msi/msix_irq to __pci_msi/msix_desc_mask so its clear
that they operated on msi_desc. Fixup the only user outside of
pci/msi.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 arch/s390/pci/pci.c |  4 ++--
 drivers/pci/msi.c   | 24 ++++++++++++++++--------
 include/linux/msi.h | 18 +++++++++++++-----
 3 files changed, 31 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index ad1a9e2a183..fb54bbdbb48 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -448,9 +448,9 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
 	/* Release MSI interrupts */
 	list_for_each_entry(msi, &pdev->msi_list, list) {
 		if (msi->msi_attrib.is_msix)
-			__msix_mask_irq(msi, 1);
+			__pci_msix_desc_mask_irq(msi, 1);
 		else
-			__msi_mask_irq(msi, 1, 1);
+			__pci_msi_desc_mask_irq(msi, 1, 1);
 		irq_set_msi_desc(msi->irq, NULL);
 		irq_free_desc(msi->irq);
 		msi->msg.address_lo = 0;
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 156ba8f809b..b5bf2f64177 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -173,7 +173,7 @@ static inline __attribute_const__ u32 msi_mask(unsigned x)
  * reliably as devices without an INTx disable bit will then generate a
  * level IRQ which will never be cleared.
  */
-u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 {
 	u32 mask_bits = desc->masked;
 
@@ -189,7 +189,7 @@ u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 
 static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 {
-	desc->masked = __msi_mask_irq(desc, mask, flag);
+	desc->masked = __pci_msi_desc_mask_irq(desc, mask, flag);
 }
 
 /*
@@ -199,7 +199,7 @@ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
  * file.  This saves a few milliseconds when initialising devices with lots
  * of MSI-X interrupts.
  */
-u32 __msix_mask_irq(struct msi_desc *desc, u32 flag)
+u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag)
 {
 	u32 mask_bits = desc->masked;
 	unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
@@ -218,7 +218,7 @@ u32 __msix_mask_irq(struct msi_desc *desc, u32 flag)
 
 static void msix_mask_irq(struct msi_desc *desc, u32 flag)
 {
-	desc->masked = __msix_mask_irq(desc, flag);
+	desc->masked = __pci_msix_desc_mask_irq(desc, flag);
 }
 
 static void msi_set_mask_bit(struct irq_data *data, u32 flag)
@@ -234,12 +234,20 @@ static void msi_set_mask_bit(struct irq_data *data, u32 flag)
 	}
 }
 
-void mask_msi_irq(struct irq_data *data)
+/**
+ * pci_msi_mask_irq - Generic irq chip callback to mask PCI/MSI interrupts
+ * @data:	pointer to irqdata associated to that interrupt
+ */
+void pci_msi_mask_irq(struct irq_data *data)
 {
 	msi_set_mask_bit(data, 1);
 }
 
-void unmask_msi_irq(struct irq_data *data)
+/**
+ * pci_msi_unmask_irq - Generic irq chip callback to unmask PCI/MSI interrupts
+ * @data:	pointer to irqdata associated to that interrupt
+ */
+void pci_msi_unmask_irq(struct irq_data *data)
 {
 	msi_set_mask_bit(data, 0);
 }
@@ -858,7 +866,7 @@ void pci_msi_shutdown(struct pci_dev *dev)
 	/* Return the device with MSI unmasked as initial states */
 	mask = msi_mask(desc->msi_attrib.multi_cap);
 	/* Keep cached state to be restored */
-	__msi_mask_irq(desc, mask, ~mask);
+	__pci_msi_desc_mask_irq(desc, mask, ~mask);
 
 	/* Restore dev->irq to its default pin-assertion irq */
 	dev->irq = desc->msi_attrib.default_irq;
@@ -956,7 +964,7 @@ void pci_msix_shutdown(struct pci_dev *dev)
 	/* Return the device with MSI-X masked as initial states */
 	list_for_each_entry(entry, &dev->msi_list, list) {
 		/* Keep cached states to be restored */
-		__msix_mask_irq(entry, 1);
+		__pci_msix_desc_mask_irq(entry, 1);
 	}
 
 	msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 301adecbc34..1dcad0c1e80 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -14,14 +14,9 @@ extern int pci_msi_ignore_mask;
 /* Helper functions */
 struct irq_data;
 struct msi_desc;
-void mask_msi_irq(struct irq_data *data);
-void unmask_msi_irq(struct irq_data *data);
 void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg);
 
-u32 __msix_mask_irq(struct msi_desc *desc, u32 flag);
-u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag);
-
 struct msi_desc {
 	struct {
 		__u8	is_msix	: 1;
@@ -52,6 +47,11 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg);
 
+u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag);
+u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag);
+void pci_msi_mask_irq(struct irq_data *data);
+void pci_msi_unmask_irq(struct irq_data *data);
+
 /* Conversion helpers. Should be removed after merging */
 static inline void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
@@ -61,6 +61,14 @@ static inline void write_msi_msg(int irq, struct msi_msg *msg)
 {
 	pci_write_msi_msg(irq, msg);
 }
+static inline void mask_msi_irq(struct irq_data *data)
+{
+	pci_msi_mask_irq(data);
+}
+static inline void unmask_msi_irq(struct irq_data *data)
+{
+	pci_msi_unmask_irq(data);
+}
 
 /*
  * The arch hooks to setup up msi irqs. Those functions are
-- 
cgit v1.2.3-70-g09d2


From d31eb342409b24e3d2e1989c775f3361e93acc08 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Sat, 15 Nov 2014 22:24:03 +0800
Subject: PCI/MSI: Introduce helpers to hide struct msi_desc implementation
 details

Introduce helpers to hide struct msi_desc implementation details,
so we could easily support non-PCI-compliant MSI devices later by
moving msi_list into struct device.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Alexander Gordeev <agordeev@redhat.com>
Link: http://lkml.kernel.org/r/1416061447-9472-6-git-send-email-jiang.liu@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/msi.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/linux/msi.h b/include/linux/msi.h
index 1dcad0c1e80..e0d08517bd3 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -43,6 +43,25 @@ struct msi_desc {
 	struct msi_msg msg;
 };
 
+/* Helpers to hide struct msi_desc implementation details */
+#define msi_desc_to_dev(desc)		(&(desc)->dev.dev)
+#define dev_to_msi_list(dev)		(&to_pci_dev((dev))->msi_list)
+#define first_msi_entry(dev)		\
+	list_first_entry(dev_to_msi_list((dev)), struct msi_desc, list)
+#define for_each_msi_entry(desc, dev)	\
+	list_for_each_entry((desc), dev_to_msi_list((dev)), list)
+
+#ifdef CONFIG_PCI_MSI
+#define first_pci_msi_entry(pdev)	first_msi_entry(&(pdev)->dev)
+#define for_each_pci_msi_entry(desc, pdev)	\
+	for_each_msi_entry((desc), &(pdev)->dev)
+
+static inline struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc)
+{
+	return desc->dev;
+}
+#endif /* CONFIG_PCI_MSI */
+
 void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg);
-- 
cgit v1.2.3-70-g09d2


From f8264e34965aaf43203912ed8f7b543c00c8d70f Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Thu, 6 Nov 2014 22:20:14 +0800
Subject: irqdomain: Introduce new interfaces to support hierarchy irqdomains

We plan to use hierarchy irqdomain to suppport CPU vector assignment,
interrupt remapping controller, IO-APIC controller, MSI interrupt
and hypertransport interrupt etc on x86 platforms. So extend irqdomain
interfaces to support hierarchy irqdomain.

There are already many clients of current irqdomain interfaces.
To minimize the changes, we choose to introduce new version 2 interfaces
to support hierarchy instead of extending existing irqdomain interfaces.

According to Thomas's suggestion, the most important design decision is
to build hierarchy struct irq_data to support hierarchy irqdomain, so
hierarchy irqdomain related data could be saved in struct irq_data.
With support of hierarchy irq_data, we could also support stacked
irq_chips. This is most useful in case of set_affinity().

The new hierarchy irqdomain introduces following interfaces:
1) irq_domain_alloc_irqs()/irq_domain_free_irqs(): allocate/release IRQ
   and related resources.
2) __irq_domain_alloc_irqs(): a special version to support legacy IRQs.
3) irq_domain_activate_irq()/irq_domain_deactivate_irq(): program
   interrupt controllers to activate/deactivate interrupt.

There are also several help functions to ease irqdomain implemenations:
1) irq_domain_get_irq_data(): get irq_data associated with a specific
   irqdomain.
2) irq_domain_set_hwirq_and_chip(): save irqdomain specific data into
   irq_data.
3) irq_domain_alloc_irqs_parent()/irq_domain_free_irqs_parent(): invoke
   parent irqdomain's alloc/free callbacks.

We also changed irq_startup()/irq_shutdown() to invoke
irq_domain_activate_irq()/irq_domain_deactivate_irq() to program
interrupt controller when start/stop interrupts.

[ tglx: Folded parts of the later patch series in ]

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 Documentation/IRQ-domain.txt |  71 ++++++++
 include/linux/irq.h          |   5 +
 include/linux/irqdomain.h    |  98 ++++++++++
 kernel/irq/Kconfig           |   5 +
 kernel/irq/chip.c            |   3 +
 kernel/irq/irqdomain.c       | 415 +++++++++++++++++++++++++++++++++++++++++--
 6 files changed, 581 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/Documentation/IRQ-domain.txt b/Documentation/IRQ-domain.txt
index 8a8b82c9ca5..39cfa72732f 100644
--- a/Documentation/IRQ-domain.txt
+++ b/Documentation/IRQ-domain.txt
@@ -151,3 +151,74 @@ used and no descriptor gets allocated it is very important to make sure
 that the driver using the simple domain call irq_create_mapping()
 before any irq_find_mapping() since the latter will actually work
 for the static IRQ assignment case.
+
+==== Hierarchy IRQ domain ====
+On some architectures, there may be multiple interrupt controllers
+involved in delivering an interrupt from the device to the target CPU.
+Let's look at a typical interrupt delivering path on x86 platforms:
+
+Device --> IOAPIC -> Interrupt remapping Controller -> Local APIC -> CPU
+
+There are three interrupt controllers involved:
+1) IOAPIC controller
+2) Interrupt remapping controller
+3) Local APIC controller
+
+To support such a hardware topology and make software architecture match
+hardware architecture, an irq_domain data structure is built for each
+interrupt controller and those irq_domains are organized into hierarchy.
+When building irq_domain hierarchy, the irq_domain near to the device is
+child and the irq_domain near to CPU is parent. So a hierarchy structure
+as below will be built for the example above.
+	CPU Vector irq_domain (root irq_domain to manage CPU vectors)
+		^
+		|
+	Interrupt Remapping irq_domain (manage irq_remapping entries)
+		^
+		|
+	IOAPIC irq_domain (manage IOAPIC delivery entries/pins)
+
+There are four major interfaces to use hierarchy irq_domain:
+1) irq_domain_alloc_irqs(): allocate IRQ descriptors and interrupt
+   controller related resources to deliver these interrupts.
+2) irq_domain_free_irqs(): free IRQ descriptors and interrupt controller
+   related resources associated with these interrupts.
+3) irq_domain_activate_irq(): activate interrupt controller hardware to
+   deliver the interrupt.
+3) irq_domain_deactivate_irq(): deactivate interrupt controller hardware
+   to stop delivering the interrupt.
+
+Following changes are needed to support hierarchy irq_domain.
+1) a new field 'parent' is added to struct irq_domain; it's used to
+   maintain irq_domain hierarchy information.
+2) a new field 'parent_data' is added to struct irq_data; it's used to
+   build hierarchy irq_data to match hierarchy irq_domains. The irq_data
+   is used to store irq_domain pointer and hardware irq number.
+3) new callbacks are added to struct irq_domain_ops to support hierarchy
+   irq_domain operations.
+
+With support of hierarchy irq_domain and hierarchy irq_data ready, an
+irq_domain structure is built for each interrupt controller, and an
+irq_data structure is allocated for each irq_domain associated with an
+IRQ. Now we could go one step further to support stacked(hierarchy)
+irq_chip. That is, an irq_chip is associated with each irq_data along
+the hierarchy. A child irq_chip may implement a required action by
+itself or by cooperating with its parent irq_chip.
+
+With stacked irq_chip, interrupt controller driver only needs to deal
+with the hardware managed by itself and may ask for services from its
+parent irq_chip when needed. So we could achieve a much cleaner
+software architecture.
+
+For an interrupt controller driver to support hierarchy irq_domain, it
+needs to:
+1) Implement irq_domain_ops.alloc and irq_domain_ops.free
+2) Optionally implement irq_domain_ops.activate and
+   irq_domain_ops.deactivate.
+3) Optionally implement an irq_chip to manage the interrupt controller
+   hardware.
+4) No need to implement irq_domain_ops.map and irq_domain_ops.unmap,
+   they are unused with hierarchy irq_domain.
+
+Hierarchy irq_domain may also be used to support other architectures,
+such as ARM, ARM64 etc.
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 03f48d936f6..13ba412ce3a 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -133,6 +133,8 @@ struct irq_domain;
  * @chip:		low level interrupt hardware access
  * @domain:		Interrupt translation domain; responsible for mapping
  *			between hwirq number and linux irq number.
+ * @parent_data:	pointer to parent struct irq_data to support hierarchy
+ *			irq_domain
  * @handler_data:	per-IRQ data for the irq_chip methods
  * @chip_data:		platform-specific per-chip private data for the chip
  *			methods, to allow shared chip implementations
@@ -151,6 +153,9 @@ struct irq_data {
 	unsigned int		state_use_accessors;
 	struct irq_chip		*chip;
 	struct irq_domain	*domain;
+#ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+	struct irq_data		*parent_data;
+#endif
 	void			*handler_data;
 	void			*chip_data;
 	struct msi_desc		*msi_desc;
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index b0f9d16e48f..f8563dcfd25 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -38,6 +38,8 @@
 struct device_node;
 struct irq_domain;
 struct of_device_id;
+struct irq_chip;
+struct irq_data;
 
 /* Number of irqs reserved for a legacy isa controller */
 #define NUM_ISA_INTERRUPTS	16
@@ -64,6 +66,16 @@ struct irq_domain_ops {
 	int (*xlate)(struct irq_domain *d, struct device_node *node,
 		     const u32 *intspec, unsigned int intsize,
 		     unsigned long *out_hwirq, unsigned int *out_type);
+
+#ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+	/* extended V2 interfaces to support hierarchy irq_domains */
+	int (*alloc)(struct irq_domain *d, unsigned int virq,
+		     unsigned int nr_irqs, void *arg);
+	void (*free)(struct irq_domain *d, unsigned int virq,
+		     unsigned int nr_irqs);
+	void (*activate)(struct irq_domain *d, struct irq_data *irq_data);
+	void (*deactivate)(struct irq_domain *d, struct irq_data *irq_data);
+#endif
 };
 
 extern struct irq_domain_ops irq_generic_chip_ops;
@@ -77,6 +89,7 @@ struct irq_domain_chip_generic;
  * @ops: pointer to irq_domain methods
  * @host_data: private data pointer for use by owner.  Not touched by irq_domain
  *             core code.
+ * @flags: host per irq_domain flags
  *
  * Optional elements
  * @of_node: Pointer to device tree nodes associated with the irq_domain. Used
@@ -84,6 +97,7 @@ struct irq_domain_chip_generic;
  * @gc: Pointer to a list of generic chips. There is a helper function for
  *      setting up one or more generic chips for interrupt controllers
  *      drivers using the generic chip library which uses this pointer.
+ * @parent: Pointer to parent irq_domain to support hierarchy irq_domains
  *
  * Revmap data, used internally by irq_domain
  * @revmap_direct_max_irq: The largest hwirq that can be set for controllers that
@@ -97,10 +111,14 @@ struct irq_domain {
 	const char *name;
 	const struct irq_domain_ops *ops;
 	void *host_data;
+	unsigned int flags;
 
 	/* Optional data */
 	struct device_node *of_node;
 	struct irq_domain_chip_generic *gc;
+#ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+	struct irq_domain *parent;
+#endif
 
 	/* reverse map data. The linear map gets appended to the irq_domain */
 	irq_hw_number_t hwirq_max;
@@ -110,6 +128,19 @@ struct irq_domain {
 	unsigned int linear_revmap[];
 };
 
+/* Irq domain flags */
+enum {
+	/* Irq domain is hierarchical */
+	IRQ_DOMAIN_FLAG_HIERARCHY	= (1 << 0),
+
+	/*
+	 * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved
+	 * for implementation specific purposes and ignored by the
+	 * core code.
+	 */
+	IRQ_DOMAIN_FLAG_NONCORE		= (1 << 16),
+};
+
 #ifdef CONFIG_IRQ_DOMAIN
 struct irq_domain *__irq_domain_add(struct device_node *of_node, int size,
 				    irq_hw_number_t hwirq_max, int direct_max,
@@ -220,8 +251,75 @@ int irq_domain_xlate_onetwocell(struct irq_domain *d, struct device_node *ctrlr,
 			const u32 *intspec, unsigned int intsize,
 			irq_hw_number_t *out_hwirq, unsigned int *out_type);
 
+/* V2 interfaces to support hierarchy IRQ domains. */
+extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain,
+						unsigned int virq);
+#ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
+				   unsigned int nr_irqs, int node, void *arg,
+				   bool realloc);
+extern void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs);
+extern void irq_domain_activate_irq(struct irq_data *irq_data);
+extern void irq_domain_deactivate_irq(struct irq_data *irq_data);
+
+static inline int irq_domain_alloc_irqs(struct irq_domain *domain,
+			unsigned int nr_irqs, int node, void *arg)
+{
+	return __irq_domain_alloc_irqs(domain, -1, nr_irqs, node, arg, false);
+}
+
+extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain,
+					 unsigned int virq,
+					 irq_hw_number_t hwirq,
+					 struct irq_chip *chip,
+					 void *chip_data);
+extern void irq_domain_reset_irq_data(struct irq_data *irq_data);
+extern void irq_domain_free_irqs_common(struct irq_domain *domain,
+					unsigned int virq,
+					unsigned int nr_irqs);
+extern void irq_domain_free_irqs_top(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs);
+
+static inline int irq_domain_alloc_irqs_parent(struct irq_domain *domain,
+					       unsigned int irq_base,
+					       unsigned int nr_irqs, void *arg)
+{
+	if (domain->parent && domain->parent->ops->alloc)
+		return domain->parent->ops->alloc(domain->parent, irq_base,
+						  nr_irqs, arg);
+	return -ENOSYS;
+}
+
+static inline void irq_domain_free_irqs_parent(struct irq_domain *domain,
+				unsigned int irq_base, unsigned int nr_irqs)
+{
+	if (domain->parent && domain->parent->ops->free)
+		domain->parent->ops->free(domain->parent, irq_base, nr_irqs);
+}
+
+static inline bool irq_domain_is_hierarchy(struct irq_domain *domain)
+{
+	return domain->flags & IRQ_DOMAIN_FLAG_HIERARCHY;
+}
+#else	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
+static inline void irq_domain_activate_irq(struct irq_data *data) { }
+static inline void irq_domain_deactivate_irq(struct irq_data *data) { }
+static inline int irq_domain_alloc_irqs(struct irq_domain *domain,
+			unsigned int nr_irqs, int node, void *arg)
+{
+	return -1;
+}
+
+static inline bool irq_domain_is_hierarchy(struct irq_domain *domain)
+{
+	return false;
+}
+#endif	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
+
 #else /* CONFIG_IRQ_DOMAIN */
 static inline void irq_dispose_mapping(unsigned int virq) { }
+static inline void irq_domain_activate_irq(struct irq_data *data) { }
+static inline void irq_domain_deactivate_irq(struct irq_data *data) { }
 #endif /* !CONFIG_IRQ_DOMAIN */
 
 #endif /* _LINUX_IRQDOMAIN_H */
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 225086b2652..4f2eb2b1f23 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -55,6 +55,11 @@ config GENERIC_IRQ_CHIP
 config IRQ_DOMAIN
 	bool
 
+# Support for hierarchical irq domains
+config IRQ_DOMAIN_HIERARCHY
+	bool
+	select IRQ_DOMAIN
+
 config HANDLE_DOMAIN_IRQ
 	bool
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index e5202f00cab..72a93086216 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
+#include <linux/irqdomain.h>
 
 #include <trace/events/irq.h>
 
@@ -178,6 +179,7 @@ int irq_startup(struct irq_desc *desc, bool resend)
 	irq_state_clr_disabled(desc);
 	desc->depth = 0;
 
+	irq_domain_activate_irq(&desc->irq_data);
 	if (desc->irq_data.chip->irq_startup) {
 		ret = desc->irq_data.chip->irq_startup(&desc->irq_data);
 		irq_state_clr_masked(desc);
@@ -199,6 +201,7 @@ void irq_shutdown(struct irq_desc *desc)
 		desc->irq_data.chip->irq_disable(&desc->irq_data);
 	else
 		desc->irq_data.chip->irq_mask(&desc->irq_data);
+	irq_domain_deactivate_irq(&desc->irq_data);
 	irq_state_set_masked(desc);
 }
 
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 6534ff6ce02..43f3be6fac7 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -23,6 +23,10 @@ static DEFINE_MUTEX(irq_domain_mutex);
 static DEFINE_MUTEX(revmap_trees_mutex);
 static struct irq_domain *irq_default_domain;
 
+static int irq_domain_alloc_descs(int virq, unsigned int nr_irqs,
+				  irq_hw_number_t hwirq, int node);
+static void irq_domain_check_hierarchy(struct irq_domain *domain);
+
 /**
  * __irq_domain_add() - Allocate a new irq_domain data structure
  * @of_node: optional device-tree node of the interrupt controller
@@ -30,7 +34,7 @@ static struct irq_domain *irq_default_domain;
  * @hwirq_max: Maximum number of interrupts supported by controller
  * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no
  *              direct mapping
- * @ops: map/unmap domain callbacks
+ * @ops: domain callbacks
  * @host_data: Controller private data pointer
  *
  * Allocates and initialize and irq_domain structure.
@@ -56,6 +60,7 @@ struct irq_domain *__irq_domain_add(struct device_node *of_node, int size,
 	domain->hwirq_max = hwirq_max;
 	domain->revmap_size = size;
 	domain->revmap_direct_max_irq = direct_max;
+	irq_domain_check_hierarchy(domain);
 
 	mutex_lock(&irq_domain_mutex);
 	list_add(&domain->link, &irq_domain_list);
@@ -109,7 +114,7 @@ EXPORT_SYMBOL_GPL(irq_domain_remove);
  * @first_irq: first number of irq block assigned to the domain,
  *	pass zero to assign irqs on-the-fly. If first_irq is non-zero, then
  *	pre-map all of the irqs in the domain to virqs starting at first_irq.
- * @ops: map/unmap domain callbacks
+ * @ops: domain callbacks
  * @host_data: Controller private data pointer
  *
  * Allocates an irq_domain, and optionally if first_irq is positive then also
@@ -174,10 +179,8 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
 
 	domain = __irq_domain_add(of_node, first_hwirq + size,
 				  first_hwirq + size, 0, ops, host_data);
-	if (!domain)
-		return NULL;
-
-	irq_domain_associate_many(domain, first_irq, first_hwirq, size);
+	if (domain)
+		irq_domain_associate_many(domain, first_irq, first_hwirq, size);
 
 	return domain;
 }
@@ -388,7 +391,6 @@ EXPORT_SYMBOL_GPL(irq_create_direct_mapping);
 unsigned int irq_create_mapping(struct irq_domain *domain,
 				irq_hw_number_t hwirq)
 {
-	unsigned int hint;
 	int virq;
 
 	pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
@@ -410,12 +412,8 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
 	}
 
 	/* Allocate a virtual interrupt number */
-	hint = hwirq % nr_irqs;
-	if (hint == 0)
-		hint++;
-	virq = irq_alloc_desc_from(hint, of_node_to_nid(domain->of_node));
-	if (virq <= 0)
-		virq = irq_alloc_desc_from(1, of_node_to_nid(domain->of_node));
+	virq = irq_domain_alloc_descs(-1, 1, hwirq,
+				      of_node_to_nid(domain->of_node));
 	if (virq <= 0) {
 		pr_debug("-> virq allocation failed\n");
 		return 0;
@@ -471,7 +469,7 @@ unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data)
 	struct irq_domain *domain;
 	irq_hw_number_t hwirq;
 	unsigned int type = IRQ_TYPE_NONE;
-	unsigned int virq;
+	int virq;
 
 	domain = irq_data->np ? irq_find_host(irq_data->np) : irq_default_domain;
 	if (!domain) {
@@ -480,6 +478,11 @@ unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data)
 		return 0;
 	}
 
+	if (irq_domain_is_hierarchy(domain)) {
+		virq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, irq_data);
+		return virq <= 0 ? 0 : virq;
+	}
+
 	/* If domain has no translation, then we assume interrupt line */
 	if (domain->ops->xlate == NULL)
 		hwirq = irq_data->args[0];
@@ -540,8 +543,8 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
 		return 0;
 
 	if (hwirq < domain->revmap_direct_max_irq) {
-		data = irq_get_irq_data(hwirq);
-		if (data && (data->domain == domain) && (data->hwirq == hwirq))
+		data = irq_domain_get_irq_data(domain, hwirq);
+		if (data && data->hwirq == hwirq)
 			return hwirq;
 	}
 
@@ -709,3 +712,383 @@ const struct irq_domain_ops irq_domain_simple_ops = {
 	.xlate = irq_domain_xlate_onetwocell,
 };
 EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
+
+static int irq_domain_alloc_descs(int virq, unsigned int cnt,
+				  irq_hw_number_t hwirq, int node)
+{
+	unsigned int hint;
+
+	if (virq >= 0) {
+		virq = irq_alloc_descs(virq, virq, cnt, node);
+	} else {
+		hint = hwirq % nr_irqs;
+		if (hint == 0)
+			hint++;
+		virq = irq_alloc_descs_from(hint, cnt, node);
+		if (virq <= 0 && hint > 1)
+			virq = irq_alloc_descs_from(1, cnt, node);
+	}
+
+	return virq;
+}
+
+#ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+static void irq_domain_insert_irq(int virq)
+{
+	struct irq_data *data;
+
+	for (data = irq_get_irq_data(virq); data; data = data->parent_data) {
+		struct irq_domain *domain = data->domain;
+		irq_hw_number_t hwirq = data->hwirq;
+
+		if (hwirq < domain->revmap_size) {
+			domain->linear_revmap[hwirq] = virq;
+		} else {
+			mutex_lock(&revmap_trees_mutex);
+			radix_tree_insert(&domain->revmap_tree, hwirq, data);
+			mutex_unlock(&revmap_trees_mutex);
+		}
+
+		/* If not already assigned, give the domain the chip's name */
+		if (!domain->name && data->chip)
+			domain->name = data->chip->name;
+	}
+
+	irq_clear_status_flags(virq, IRQ_NOREQUEST);
+}
+
+static void irq_domain_remove_irq(int virq)
+{
+	struct irq_data *data;
+
+	irq_set_status_flags(virq, IRQ_NOREQUEST);
+	irq_set_chip_and_handler(virq, NULL, NULL);
+	synchronize_irq(virq);
+	smp_mb();
+
+	for (data = irq_get_irq_data(virq); data; data = data->parent_data) {
+		struct irq_domain *domain = data->domain;
+		irq_hw_number_t hwirq = data->hwirq;
+
+		if (hwirq < domain->revmap_size) {
+			domain->linear_revmap[hwirq] = 0;
+		} else {
+			mutex_lock(&revmap_trees_mutex);
+			radix_tree_delete(&domain->revmap_tree, hwirq);
+			mutex_unlock(&revmap_trees_mutex);
+		}
+	}
+}
+
+static struct irq_data *irq_domain_insert_irq_data(struct irq_domain *domain,
+						   struct irq_data *child)
+{
+	struct irq_data *irq_data;
+
+	irq_data = kzalloc_node(sizeof(*irq_data), GFP_KERNEL, child->node);
+	if (irq_data) {
+		child->parent_data = irq_data;
+		irq_data->irq = child->irq;
+		irq_data->node = child->node;
+		irq_data->domain = domain;
+	}
+
+	return irq_data;
+}
+
+static void irq_domain_free_irq_data(unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *irq_data, *tmp;
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_get_irq_data(virq + i);
+		tmp = irq_data->parent_data;
+		irq_data->parent_data = NULL;
+		irq_data->domain = NULL;
+
+		while (tmp) {
+			irq_data = tmp;
+			tmp = tmp->parent_data;
+			kfree(irq_data);
+		}
+	}
+}
+
+static int irq_domain_alloc_irq_data(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *irq_data;
+	struct irq_domain *parent;
+	int i;
+
+	/* The outermost irq_data is embedded in struct irq_desc */
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_get_irq_data(virq + i);
+		irq_data->domain = domain;
+
+		for (parent = domain->parent; parent; parent = parent->parent) {
+			irq_data = irq_domain_insert_irq_data(parent, irq_data);
+			if (!irq_data) {
+				irq_domain_free_irq_data(virq, i + 1);
+				return -ENOMEM;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * irq_domain_get_irq_data - Get irq_data associated with @virq and @domain
+ * @domain:	domain to match
+ * @virq:	IRQ number to get irq_data
+ */
+struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain,
+					 unsigned int virq)
+{
+	struct irq_data *irq_data;
+
+	for (irq_data = irq_get_irq_data(virq); irq_data;
+	     irq_data = irq_data->parent_data)
+		if (irq_data->domain == domain)
+			return irq_data;
+
+	return NULL;
+}
+
+/**
+ * irq_domain_set_hwirq_and_chip - Set hwirq and irqchip of @virq at @domain
+ * @domain:	Interrupt domain to match
+ * @virq:	IRQ number
+ * @hwirq:	The hwirq number
+ * @chip:	The associated interrupt chip
+ * @chip_data:	The associated chip data
+ */
+int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq,
+				  irq_hw_number_t hwirq, struct irq_chip *chip,
+				  void *chip_data)
+{
+	struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+
+	if (!irq_data)
+		return -ENOENT;
+
+	irq_data->hwirq = hwirq;
+	irq_data->chip = chip ? chip : &no_irq_chip;
+	irq_data->chip_data = chip_data;
+
+	return 0;
+}
+
+/**
+ * irq_domain_reset_irq_data - Clear hwirq, chip and chip_data in @irq_data
+ * @irq_data:	The pointer to irq_data
+ */
+void irq_domain_reset_irq_data(struct irq_data *irq_data)
+{
+	irq_data->hwirq = 0;
+	irq_data->chip = &no_irq_chip;
+	irq_data->chip_data = NULL;
+}
+
+/**
+ * irq_domain_free_irqs_common - Clear irq_data and free the parent
+ * @domain:	Interrupt domain to match
+ * @virq:	IRQ number to start with
+ * @nr_irqs:	The number of irqs to free
+ */
+void irq_domain_free_irqs_common(struct irq_domain *domain, unsigned int virq,
+				 unsigned int nr_irqs)
+{
+	struct irq_data *irq_data;
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		if (irq_data)
+			irq_domain_reset_irq_data(irq_data);
+	}
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+}
+
+/**
+ * irq_domain_free_irqs_top - Clear handler and handler data, clear irqdata and free parent
+ * @domain:	Interrupt domain to match
+ * @virq:	IRQ number to start with
+ * @nr_irqs:	The number of irqs to free
+ */
+void irq_domain_free_irqs_top(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs)
+{
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_set_handler_data(virq + i, NULL);
+		irq_set_handler(virq + i, NULL);
+	}
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
+
+/**
+ * __irq_domain_alloc_irqs - Allocate IRQs from domain
+ * @domain:	domain to allocate from
+ * @irq_base:	allocate specified IRQ nubmer if irq_base >= 0
+ * @nr_irqs:	number of IRQs to allocate
+ * @node:	NUMA node id for memory allocation
+ * @arg:	domain specific argument
+ * @realloc:	IRQ descriptors have already been allocated if true
+ *
+ * Allocate IRQ numbers and initialized all data structures to support
+ * hierarchy IRQ domains.
+ * Parameter @realloc is mainly to support legacy IRQs.
+ * Returns error code or allocated IRQ number
+ *
+ * The whole process to setup an IRQ has been split into two steps.
+ * The first step, __irq_domain_alloc_irqs(), is to allocate IRQ
+ * descriptor and required hardware resources. The second step,
+ * irq_domain_activate_irq(), is to program hardwares with preallocated
+ * resources. In this way, it's easier to rollback when failing to
+ * allocate resources.
+ */
+int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
+			    unsigned int nr_irqs, int node, void *arg,
+			    bool realloc)
+{
+	int i, ret, virq;
+
+	if (domain == NULL) {
+		domain = irq_default_domain;
+		if (WARN(!domain, "domain is NULL; cannot allocate IRQ\n"))
+			return -EINVAL;
+	}
+
+	if (!domain->ops->alloc) {
+		pr_debug("domain->ops->alloc() is NULL\n");
+		return -ENOSYS;
+	}
+
+	if (realloc && irq_base >= 0) {
+		virq = irq_base;
+	} else {
+		virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node);
+		if (virq < 0) {
+			pr_debug("cannot allocate IRQ(base %d, count %d)\n",
+				 irq_base, nr_irqs);
+			return virq;
+		}
+	}
+
+	if (irq_domain_alloc_irq_data(domain, virq, nr_irqs)) {
+		pr_debug("cannot allocate memory for IRQ%d\n", virq);
+		ret = -ENOMEM;
+		goto out_free_desc;
+	}
+
+	mutex_lock(&irq_domain_mutex);
+	ret = domain->ops->alloc(domain, virq, nr_irqs, arg);
+	if (ret < 0) {
+		mutex_unlock(&irq_domain_mutex);
+		goto out_free_irq_data;
+	}
+	for (i = 0; i < nr_irqs; i++)
+		irq_domain_insert_irq(virq + i);
+	mutex_unlock(&irq_domain_mutex);
+
+	return virq;
+
+out_free_irq_data:
+	irq_domain_free_irq_data(virq, nr_irqs);
+out_free_desc:
+	irq_free_descs(virq, nr_irqs);
+	return ret;
+}
+
+/**
+ * irq_domain_free_irqs - Free IRQ number and associated data structures
+ * @virq:	base IRQ number
+ * @nr_irqs:	number of IRQs to free
+ */
+void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *data = irq_get_irq_data(virq);
+	int i;
+
+	if (WARN(!data || !data->domain || !data->domain->ops->free,
+		 "NULL pointer, cannot free irq\n"))
+		return;
+
+	mutex_lock(&irq_domain_mutex);
+	for (i = 0; i < nr_irqs; i++)
+		irq_domain_remove_irq(virq + i);
+	data->domain->ops->free(data->domain, virq, nr_irqs);
+	mutex_unlock(&irq_domain_mutex);
+
+	irq_domain_free_irq_data(virq, nr_irqs);
+	irq_free_descs(virq, nr_irqs);
+}
+
+/**
+ * irq_domain_activate_irq - Call domain_ops->activate recursively to activate
+ *			     interrupt
+ * @irq_data:	outermost irq_data associated with interrupt
+ *
+ * This is the second step to call domain_ops->activate to program interrupt
+ * controllers, so the interrupt could actually get delivered.
+ */
+void irq_domain_activate_irq(struct irq_data *irq_data)
+{
+	if (irq_data && irq_data->domain) {
+		struct irq_domain *domain = irq_data->domain;
+
+		if (irq_data->parent_data)
+			irq_domain_activate_irq(irq_data->parent_data);
+		if (domain->ops->activate)
+			domain->ops->activate(domain, irq_data);
+	}
+}
+
+/**
+ * irq_domain_deactivate_irq - Call domain_ops->deactivate recursively to
+ *			       deactivate interrupt
+ * @irq_data: outermost irq_data associated with interrupt
+ *
+ * It calls domain_ops->deactivate to program interrupt controllers to disable
+ * interrupt delivery.
+ */
+void irq_domain_deactivate_irq(struct irq_data *irq_data)
+{
+	if (irq_data && irq_data->domain) {
+		struct irq_domain *domain = irq_data->domain;
+
+		if (domain->ops->deactivate)
+			domain->ops->deactivate(domain, irq_data);
+		if (irq_data->parent_data)
+			irq_domain_deactivate_irq(irq_data->parent_data);
+	}
+}
+
+static void irq_domain_check_hierarchy(struct irq_domain *domain)
+{
+	/* Hierarchy irq_domains must implement callback alloc() */
+	if (domain->ops->alloc)
+		domain->flags |= IRQ_DOMAIN_FLAG_HIERARCHY;
+}
+#else	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
+/**
+ * irq_domain_get_irq_data - Get irq_data associated with @virq and @domain
+ * @domain:	domain to match
+ * @virq:	IRQ number to get irq_data
+ */
+struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain,
+					 unsigned int virq)
+{
+	struct irq_data *irq_data = irq_get_irq_data(virq);
+
+	return (irq_data && irq_data->domain == domain) ? irq_data : NULL;
+}
+
+static void irq_domain_check_hierarchy(struct irq_domain *domain)
+{
+}
+#endif	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
-- 
cgit v1.2.3-70-g09d2


From 85f08c17de26f117be6ca7aa260d2ec02a2248ba Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Thu, 6 Nov 2014 22:20:16 +0800
Subject: genirq: Introduce helper functions to support stacked irq_chip

Now we already support hierarchy irq_data, so introduce several helpers
to support stacked irq_chips.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h |  5 +++++
 kernel/irq/chip.c   | 28 ++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 13ba412ce3a..0adcbbbf2e8 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -443,6 +443,11 @@ extern void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_nested_irq(unsigned int irq);
 
+#ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+extern void irq_chip_ack_parent(struct irq_data *data);
+extern int irq_chip_retrigger_hierarchy(struct irq_data *data);
+#endif
+
 /* Handling of unhandled and spurious interrupts: */
 extern void note_interrupt(unsigned int irq, struct irq_desc *desc,
 			   irqreturn_t action_ret);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 72a93086216..dd1d3c4c93a 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -850,3 +850,31 @@ void irq_cpu_offline(void)
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	}
 }
+
+#ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+/**
+ * irq_chip_ack_parent - Acknowledge the parent interrupt
+ * @data:	Pointer to interrupt specific data
+ */
+void irq_chip_ack_parent(struct irq_data *data)
+{
+	data = data->parent_data;
+	data->chip->irq_ack(data);
+}
+
+/**
+ * irq_chip_retrigger_hierarchy - Retrigger an interrupt in hardware
+ * @data:	Pointer to interrupt specific data
+ *
+ * Iterate through the domain hierarchy of the interrupt and check
+ * whether a hw retrigger function exists. If yes, invoke it.
+ */
+int irq_chip_retrigger_hierarchy(struct irq_data *data)
+{
+	for (data = data->parent_data; data; data = data->parent_data)
+		if (data->chip && data->chip->irq_retrigger)
+			return data->chip->irq_retrigger(data);
+
+	return -ENOSYS;
+}
+#endif
-- 
cgit v1.2.3-70-g09d2


From 56e8abab615e0c5858cfb9fa0015a44641762b9d Mon Sep 17 00:00:00 2001
From: Yingjoe Chen <yingjoe.chen@mediatek.com>
Date: Thu, 13 Nov 2014 23:37:05 +0800
Subject: genirq: Add more helper functions to support stacked irq_chip

Add more helper function for stacked irq_chip to just call parent's
function.

Signed-off-by: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Pawel Moll <pawel.moll@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Jason Cooper <jason@lakedaemon.net>
Cc: Gran Likely <grant.likely@linaro.org>
Cc: Boris BREZILLON <boris.brezillon@free-electrons.com>
Cc: <linux-arm-kernel@lists.infradead.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Cc: <srv_heupstream@mediatek.com>
Cc: <yingjoe.chen@gmail.com>
Cc: <hc.yen@mediatek.com>
Cc: <eddie.huang@mediatek.com>
Cc: <nathan.chung@mediatek.com>
Cc: <yh.chen@mediatek.com>
Cc: Sascha Hauer <kernel@pengutronix.de>
Cc: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Link: http://lkml.kernel.org/r/1415893029-2971-3-git-send-email-yingjoe.chen@mediatek.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h |  6 ++++++
 kernel/irq/chip.c   | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 54 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 0adcbbbf2e8..fad4bf6f15f 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -446,6 +446,12 @@ extern void handle_nested_irq(unsigned int irq);
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 extern void irq_chip_ack_parent(struct irq_data *data);
 extern int irq_chip_retrigger_hierarchy(struct irq_data *data);
+extern void irq_chip_mask_parent(struct irq_data *data);
+extern void irq_chip_unmask_parent(struct irq_data *data);
+extern void irq_chip_eoi_parent(struct irq_data *data);
+extern int irq_chip_set_affinity_parent(struct irq_data *data,
+					const struct cpumask *dest,
+					bool force);
 #endif
 
 /* Handling of unhandled and spurious interrupts: */
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index dd1d3c4c93a..47f4c6469a4 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -862,6 +862,54 @@ void irq_chip_ack_parent(struct irq_data *data)
 	data->chip->irq_ack(data);
 }
 
+/**
+ * irq_chip_mask_parent - Mask the parent interrupt
+ * @data:	Pointer to interrupt specific data
+ */
+void irq_chip_mask_parent(struct irq_data *data)
+{
+	data = data->parent_data;
+	data->chip->irq_mask(data);
+}
+
+/**
+ * irq_chip_unmask_parent - Unmask the parent interrupt
+ * @data:	Pointer to interrupt specific data
+ */
+void irq_chip_unmask_parent(struct irq_data *data)
+{
+	data = data->parent_data;
+	data->chip->irq_unmask(data);
+}
+
+/**
+ * irq_chip_eoi_parent - Invoke EOI on the parent interrupt
+ * @data:	Pointer to interrupt specific data
+ */
+void irq_chip_eoi_parent(struct irq_data *data)
+{
+	data = data->parent_data;
+	data->chip->irq_eoi(data);
+}
+
+/**
+ * irq_chip_set_affinity_parent - Set affinity on the parent interrupt
+ * @data:	Pointer to interrupt specific data
+ * @dest:	The affinity mask to set
+ * @force:	Flag to enforce setting (disable online checks)
+ *
+ * Conditinal, as the underlying parent chip might not implement it.
+ */
+int irq_chip_set_affinity_parent(struct irq_data *data,
+				 const struct cpumask *dest, bool force)
+{
+	data = data->parent_data;
+	if (data->chip->irq_set_affinity)
+		return data->chip->irq_set_affinity(data, dest, force);
+
+	return -ENOSYS;
+}
+
 /**
  * irq_chip_retrigger_hierarchy - Retrigger an interrupt in hardware
  * @data:	Pointer to interrupt specific data
-- 
cgit v1.2.3-70-g09d2


From 515085ef7ee74694bc9b02bc45196452defad59a Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Thu, 6 Nov 2014 22:20:17 +0800
Subject: genirq: Introduce irq_chip.irq_compose_msi_msg() to support stacked
 irqchip

Add callback irq_compose_msi_msg to struct irq_chip, which will be used
to support stacked irqchip.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h |  5 +++++
 kernel/irq/chip.c   | 26 ++++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index fad4bf6f15f..d58e5893546 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -29,6 +29,7 @@ struct seq_file;
 struct module;
 struct irq_desc;
 struct irq_data;
+struct msi_msg;
 typedef	void (*irq_flow_handler_t)(unsigned int irq,
 					    struct irq_desc *desc);
 typedef	void (*irq_preflow_handler_t)(struct irq_data *data);
@@ -320,6 +321,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
  *				any other callback related to this irq
  * @irq_release_resources:	optional to release resources acquired with
  *				irq_request_resources
+ * @irq_compose_msi_msg:	optional to compose message content for MSI
  * @flags:		chip specific flags
  */
 struct irq_chip {
@@ -356,6 +358,8 @@ struct irq_chip {
 	int		(*irq_request_resources)(struct irq_data *data);
 	void		(*irq_release_resources)(struct irq_data *data);
 
+	void		(*irq_compose_msi_msg)(struct irq_data *data, struct msi_msg *msg);
+
 	unsigned long	flags;
 };
 
@@ -443,6 +447,7 @@ extern void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_nested_irq(unsigned int irq);
 
+extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg);
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 extern void irq_chip_ack_parent(struct irq_data *data);
 extern int irq_chip_retrigger_hierarchy(struct irq_data *data);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 47f4c6469a4..63c16d165e7 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -926,3 +926,29 @@ int irq_chip_retrigger_hierarchy(struct irq_data *data)
 	return -ENOSYS;
 }
 #endif
+
+/**
+ * irq_chip_compose_msi_msg - Componse msi message for a irq chip
+ * @data:	Pointer to interrupt specific data
+ * @msg:	Pointer to the MSI message
+ *
+ * For hierarchical domains we find the first chip in the hierarchy
+ * which implements the irq_compose_msi_msg callback. For non
+ * hierarchical we use the top level chip.
+ */
+int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct irq_data *pos = NULL;
+
+#ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+	for (; data; data = data->parent_data)
+#endif
+		if (data->chip && data->chip->irq_compose_msi_msg)
+			pos = data;
+	if (!pos)
+		return -ENOSYS;
+
+	pos->chip->irq_compose_msi_msg(pos, msg);
+
+	return 0;
+}
-- 
cgit v1.2.3-70-g09d2


From 2cb625478f8cea0f72b565007a35e1eb7882ac3a Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Thu, 6 Nov 2014 22:20:18 +0800
Subject: genirq: Add IRQ_SET_MASK_OK_DONE to support stacked irqchip

Add IRQ_SET_MASK_OK_DONE in addition to IRQ_SET_MASK_OK and
IRQ_SET_MASK_OK_NOCOPY to support stacked irqchip. IRQ_SET_MASK_OK_DONE
is the same as IRQ_SET_MASK_OK to irq core. To stacked irqchip, it means
that ascendant irqchips have done all the work and no more handling
needed in descendant irqchips.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h | 4 ++++
 kernel/irq/manage.c | 2 ++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index d58e5893546..566b1e54132 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -114,10 +114,14 @@ enum {
  *
  * IRQ_SET_MASK_OK	- OK, core updates irq_data.affinity
  * IRQ_SET_MASK_NOCPY	- OK, chip did update irq_data.affinity
+ * IRQ_SET_MASK_OK_DONE	- Same as IRQ_SET_MASK_OK for core. Special code to
+ *			  support stacked irqchips, which indicates skipping
+ *			  all descendent irqchips.
  */
 enum {
 	IRQ_SET_MASK_OK = 0,
 	IRQ_SET_MASK_OK_NOCOPY,
+	IRQ_SET_MASK_OK_DONE,
 };
 
 struct msi_desc;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0a9104b4608..80692373abd 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -183,6 +183,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	ret = chip->irq_set_affinity(data, mask, force);
 	switch (ret) {
 	case IRQ_SET_MASK_OK:
+	case IRQ_SET_MASK_OK_DONE:
 		cpumask_copy(data->affinity, mask);
 	case IRQ_SET_MASK_OK_NOCOPY:
 		irq_set_thread_affinity(desc);
@@ -600,6 +601,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 
 	switch (ret) {
 	case IRQ_SET_MASK_OK:
+	case IRQ_SET_MASK_OK_DONE:
 		irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK);
 		irqd_set(&desc->irq_data, flags);
 
-- 
cgit v1.2.3-70-g09d2


From 75ffc0075007ca649131a2c42863ce6995d9bf80 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 11 Nov 2014 21:58:34 +0100
Subject: genirq: Split out flow handler typedefs into seperate header file

Required to avoid circular include dependencies.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h        |  6 +-----
 include/linux/irqhandler.h | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 5 deletions(-)
 create mode 100644 include/linux/irqhandler.h

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 566b1e54132..677482bd8b9 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -15,6 +15,7 @@
 #include <linux/spinlock.h>
 #include <linux/cpumask.h>
 #include <linux/gfp.h>
+#include <linux/irqhandler.h>
 #include <linux/irqreturn.h>
 #include <linux/irqnr.h>
 #include <linux/errno.h>
@@ -27,12 +28,7 @@
 
 struct seq_file;
 struct module;
-struct irq_desc;
-struct irq_data;
 struct msi_msg;
-typedef	void (*irq_flow_handler_t)(unsigned int irq,
-					    struct irq_desc *desc);
-typedef	void (*irq_preflow_handler_t)(struct irq_data *data);
 
 /*
  * IRQ line status.
diff --git a/include/linux/irqhandler.h b/include/linux/irqhandler.h
new file mode 100644
index 00000000000..62d54300419
--- /dev/null
+++ b/include/linux/irqhandler.h
@@ -0,0 +1,14 @@
+#ifndef _LINUX_IRQHANDLER_H
+#define _LINUX_IRQHANDLER_H
+
+/*
+ * Interrupt flow handler typedefs are defined here to avoid circular
+ * include dependencies.
+ */
+
+struct irq_desc;
+struct irq_data;
+typedef	void (*irq_flow_handler_t)(unsigned int irq, struct irq_desc *desc);
+typedef	void (*irq_preflow_handler_t)(struct irq_data *data);
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From 1b5377087cb4e68d719a875120894fddfbcbf0f9 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Sun, 9 Nov 2014 23:10:24 +0800
Subject: genirq: Introduce helper irq_domain_set_info() to reduce duplicated
 code

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irqdomain.h |  5 +++++
 kernel/irq/irqdomain.c    | 21 +++++++++++++++++++++
 2 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index f8563dcfd25..7aca1adb68a 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -33,6 +33,7 @@
 #define _LINUX_IRQDOMAIN_H
 
 #include <linux/types.h>
+#include <linux/irqhandler.h>
 #include <linux/radix-tree.h>
 
 struct device_node;
@@ -273,6 +274,10 @@ extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain,
 					 irq_hw_number_t hwirq,
 					 struct irq_chip *chip,
 					 void *chip_data);
+extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq,
+				irq_hw_number_t hwirq, struct irq_chip *chip,
+				void *chip_data, irq_flow_handler_t handler,
+				void *handler_data, const char *handler_name);
 extern void irq_domain_reset_irq_data(struct irq_data *irq_data);
 extern void irq_domain_free_irqs_common(struct irq_domain *domain,
 					unsigned int virq,
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 9a61de21933..4e62832ace8 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -890,6 +890,27 @@ int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq,
 	return 0;
 }
 
+/**
+ * irq_domain_set_info - Set the complete data for a @virq in @domain
+ * @domain:		Interrupt domain to match
+ * @virq:		IRQ number
+ * @hwirq:		The hardware interrupt number
+ * @chip:		The associated interrupt chip
+ * @chip_data:		The associated interrupt chip data
+ * @handler:		The interrupt flow handler
+ * @handler_data:	The interrupt flow handler data
+ * @handler_name:	The interrupt handler name
+ */
+void irq_domain_set_info(struct irq_domain *domain, unsigned int virq,
+			 irq_hw_number_t hwirq, struct irq_chip *chip,
+			 void *chip_data, irq_flow_handler_t handler,
+			 void *handler_data, const char *handler_name)
+{
+	irq_domain_set_hwirq_and_chip(domain, virq, hwirq, chip, chip_data);
+	__irq_set_handler(virq, handler, 0, handler_name);
+	irq_set_handler_data(virq, handler_data);
+}
+
 /**
  * irq_domain_reset_irq_data - Clear hwirq, chip and chip_data in @irq_data
  * @irq_data:	The pointer to irq_data
-- 
cgit v1.2.3-70-g09d2


From 36d727310cb9f85efb5ac089ffb1797e7c3538e1 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Sat, 15 Nov 2014 22:24:01 +0800
Subject: irqdomain: Implement a method to automatically call parent domains
 alloc/free

Add a flags to irq_domain.flags to control whether the irqdomain core
should automatically call parent irqdomain's alloc/free callbacks. It
help to reduce hierarchy irqdomains users' code size.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Link: http://lkml.kernel.org/r/1416061447-9472-4-git-send-email-jiang.liu@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irqdomain.h | 24 ++++++--------
 kernel/irq/irqdomain.c    | 82 +++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 89 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 7aca1adb68a..dd2709bdad5 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -134,6 +134,9 @@ enum {
 	/* Irq domain is hierarchical */
 	IRQ_DOMAIN_FLAG_HIERARCHY	= (1 << 0),
 
+	/* Core calls alloc/free recursive through the domain hierarchy. */
+	IRQ_DOMAIN_FLAG_AUTO_RECURSIVE	= (1 << 1),
+
 	/*
 	 * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved
 	 * for implementation specific purposes and ignored by the
@@ -285,22 +288,13 @@ extern void irq_domain_free_irqs_common(struct irq_domain *domain,
 extern void irq_domain_free_irqs_top(struct irq_domain *domain,
 				     unsigned int virq, unsigned int nr_irqs);
 
-static inline int irq_domain_alloc_irqs_parent(struct irq_domain *domain,
-					       unsigned int irq_base,
-					       unsigned int nr_irqs, void *arg)
-{
-	if (domain->parent && domain->parent->ops->alloc)
-		return domain->parent->ops->alloc(domain->parent, irq_base,
-						  nr_irqs, arg);
-	return -ENOSYS;
-}
+extern int irq_domain_alloc_irqs_parent(struct irq_domain *domain,
+					unsigned int irq_base,
+					unsigned int nr_irqs, void *arg);
 
-static inline void irq_domain_free_irqs_parent(struct irq_domain *domain,
-				unsigned int irq_base, unsigned int nr_irqs)
-{
-	if (domain->parent && domain->parent->ops->free)
-		domain->parent->ops->free(domain->parent, irq_base, nr_irqs);
-}
+extern void irq_domain_free_irqs_parent(struct irq_domain *domain,
+					unsigned int irq_base,
+					unsigned int nr_irqs);
 
 static inline bool irq_domain_is_hierarchy(struct irq_domain *domain)
 {
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 4e62832ace8..9c88db7056d 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -960,6 +960,43 @@ void irq_domain_free_irqs_top(struct irq_domain *domain, unsigned int virq,
 	irq_domain_free_irqs_common(domain, virq, nr_irqs);
 }
 
+static bool irq_domain_is_auto_recursive(struct irq_domain *domain)
+{
+	return domain->flags & IRQ_DOMAIN_FLAG_AUTO_RECURSIVE;
+}
+
+static void irq_domain_free_irqs_recursive(struct irq_domain *domain,
+					   unsigned int irq_base,
+					   unsigned int nr_irqs)
+{
+	domain->ops->free(domain, irq_base, nr_irqs);
+	if (irq_domain_is_auto_recursive(domain)) {
+		BUG_ON(!domain->parent);
+		irq_domain_free_irqs_recursive(domain->parent, irq_base,
+					       nr_irqs);
+	}
+}
+
+static int irq_domain_alloc_irqs_recursive(struct irq_domain *domain,
+					   unsigned int irq_base,
+					   unsigned int nr_irqs, void *arg)
+{
+	int ret = 0;
+	struct irq_domain *parent = domain->parent;
+	bool recursive = irq_domain_is_auto_recursive(domain);
+
+	BUG_ON(recursive && !parent);
+	if (recursive)
+		ret = irq_domain_alloc_irqs_recursive(parent, irq_base,
+						      nr_irqs, arg);
+	if (ret >= 0)
+		ret = domain->ops->alloc(domain, irq_base, nr_irqs, arg);
+	if (ret < 0 && recursive)
+		irq_domain_free_irqs_recursive(parent, irq_base, nr_irqs);
+
+	return ret;
+}
+
 /**
  * __irq_domain_alloc_irqs - Allocate IRQs from domain
  * @domain:	domain to allocate from
@@ -1016,7 +1053,7 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 	}
 
 	mutex_lock(&irq_domain_mutex);
-	ret = domain->ops->alloc(domain, virq, nr_irqs, arg);
+	ret = irq_domain_alloc_irqs_recursive(domain, virq, nr_irqs, arg);
 	if (ret < 0) {
 		mutex_unlock(&irq_domain_mutex);
 		goto out_free_irq_data;
@@ -1051,13 +1088,54 @@ void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs)
 	mutex_lock(&irq_domain_mutex);
 	for (i = 0; i < nr_irqs; i++)
 		irq_domain_remove_irq(virq + i);
-	data->domain->ops->free(data->domain, virq, nr_irqs);
+	irq_domain_free_irqs_recursive(data->domain, virq, nr_irqs);
 	mutex_unlock(&irq_domain_mutex);
 
 	irq_domain_free_irq_data(virq, nr_irqs);
 	irq_free_descs(virq, nr_irqs);
 }
 
+/**
+ * irq_domain_alloc_irqs_parent - Allocate interrupts from parent domain
+ * @irq_base:	Base IRQ number
+ * @nr_irqs:	Number of IRQs to allocate
+ * @arg:	Allocation data (arch/domain specific)
+ *
+ * Check whether the domain has been setup recursive. If not allocate
+ * through the parent domain.
+ */
+int irq_domain_alloc_irqs_parent(struct irq_domain *domain,
+				 unsigned int irq_base, unsigned int nr_irqs,
+				 void *arg)
+{
+	/* irq_domain_alloc_irqs_recursive() has called parent's alloc() */
+	if (irq_domain_is_auto_recursive(domain))
+		return 0;
+
+	domain = domain->parent;
+	if (domain)
+		return irq_domain_alloc_irqs_recursive(domain, irq_base,
+						       nr_irqs, arg);
+	return -ENOSYS;
+}
+
+/**
+ * irq_domain_free_irqs_parent - Free interrupts from parent domain
+ * @irq_base:	Base IRQ number
+ * @nr_irqs:	Number of IRQs to free
+ *
+ * Check whether the domain has been setup recursive. If not free
+ * through the parent domain.
+ */
+void irq_domain_free_irqs_parent(struct irq_domain *domain,
+				 unsigned int irq_base, unsigned int nr_irqs)
+{
+	/* irq_domain_free_irqs_recursive() will call parent's free */
+	if (!irq_domain_is_auto_recursive(domain) && domain->parent)
+		irq_domain_free_irqs_recursive(domain->parent, irq_base,
+					       nr_irqs);
+}
+
 /**
  * irq_domain_activate_irq - Call domain_ops->activate recursively to activate
  *			     interrupt
-- 
cgit v1.2.3-70-g09d2


From afb7da83b9f476728623130703acb553d7c7c4d9 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Sat, 15 Nov 2014 22:24:02 +0800
Subject: irqdomain: Introduce helper function irq_domain_add_hierarchy()

Introduce helper function irq_domain_add_hierarchy(), which creates
a linear irqdomain if parameter 'size' is not zero, otherwise creates
a tree irqdomain.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Link: http://lkml.kernel.org/r/1416061447-9472-5-git-send-email-jiang.liu@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irqdomain.h |  4 ++++
 kernel/irq/irqdomain.c    | 36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+)

(limited to 'include')

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index dd2709bdad5..676d7306a36 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -259,6 +259,10 @@ int irq_domain_xlate_onetwocell(struct irq_domain *d, struct device_node *ctrlr,
 extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain,
 						unsigned int virq);
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+extern struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent,
+			unsigned int flags, unsigned int size,
+			struct device_node *node,
+			const struct irq_domain_ops *ops, void *host_data);
 extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 				   unsigned int nr_irqs, int node, void *arg,
 				   bool realloc);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 9c88db7056d..7fac311057b 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -742,6 +742,42 @@ static int irq_domain_alloc_descs(int virq, unsigned int cnt,
 }
 
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
+/**
+ * irq_domain_add_hierarchy - Add a irqdomain into the hierarchy
+ * @parent:	Parent irq domain to associate with the new domain
+ * @flags:	Irq domain flags associated to the domain
+ * @size:	Size of the domain. See below
+ * @node:	Optional device-tree node of the interrupt controller
+ * @ops:	Pointer to the interrupt domain callbacks
+ * @host_data:	Controller private data pointer
+ *
+ * If @size is 0 a tree domain is created, otherwise a linear domain.
+ *
+ * If successful the parent is associated to the new domain and the
+ * domain flags are set.
+ * Returns pointer to IRQ domain, or NULL on failure.
+ */
+struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent,
+					    unsigned int flags,
+					    unsigned int size,
+					    struct device_node *node,
+					    const struct irq_domain_ops *ops,
+					    void *host_data)
+{
+	struct irq_domain *domain;
+
+	if (size)
+		domain = irq_domain_add_linear(node, size, ops, host_data);
+	else
+		domain = irq_domain_add_tree(node, ops, host_data);
+	if (domain) {
+		domain->parent = parent;
+		domain->flags |= flags;
+	}
+
+	return domain;
+}
+
 static void irq_domain_insert_irq(int virq)
 {
 	struct irq_data *data;
-- 
cgit v1.2.3-70-g09d2


From 9dde55b72dc80bfae4280ddce5dbd69ba8240813 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Sun, 9 Nov 2014 23:10:28 +0800
Subject: genirq: Introduce callback irq_chip.irq_write_msi_msg

Introduce callback irq_chip.irq_write_msi_msg, so we can share common
code among MSI alike interrupt controllers, such as HPET and DMAR.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 677482bd8b9..8badf34baf0 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -322,6 +322,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
  * @irq_release_resources:	optional to release resources acquired with
  *				irq_request_resources
  * @irq_compose_msi_msg:	optional to compose message content for MSI
+ * @irq_write_msi_msg:	optional to write message content for MSI
  * @flags:		chip specific flags
  */
 struct irq_chip {
@@ -359,6 +360,7 @@ struct irq_chip {
 	void		(*irq_release_resources)(struct irq_data *data);
 
 	void		(*irq_compose_msi_msg)(struct irq_data *data, struct msi_msg *msg);
+	void		(*irq_write_msi_msg)(struct irq_data *data, struct msi_msg *msg);
 
 	unsigned long	flags;
 };
@@ -459,6 +461,12 @@ extern int irq_chip_set_affinity_parent(struct irq_data *data,
 					bool force);
 #endif
 
+static inline void irq_chip_write_msi_msg(struct irq_data *data,
+					  struct msi_msg *msg)
+{
+	data->chip->irq_write_msi_msg(data, msg);
+}
+
 /* Handling of unhandled and spurious interrupts: */
 extern void note_interrupt(unsigned int irq, struct irq_desc *desc,
 			   irqreturn_t action_ret);
-- 
cgit v1.2.3-70-g09d2


From f3cf8bb0d6c3c11ddedf01f02f856f2ae8c33aa4 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Wed, 12 Nov 2014 11:39:03 +0100
Subject: genirq: Add generic msi irq domain support

Implement the basic functions for MSI interrupt support with
hierarchical interrupt domains.

[ tglx: Extracted and combined from several patches ]

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/msi.h |  45 +++++++++++++++++
 kernel/irq/Kconfig  |  10 ++++
 kernel/irq/Makefile |   1 +
 kernel/irq/msi.c    | 141 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 197 insertions(+)
 create mode 100644 kernel/irq/msi.c

(limited to 'include')

diff --git a/include/linux/msi.h b/include/linux/msi.h
index e0d08517bd3..b5ca2456769 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -114,4 +114,49 @@ struct msi_controller {
 	void (*teardown_irq)(struct msi_controller *chip, unsigned int irq);
 };
 
+#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
+struct irq_domain;
+struct irq_chip;
+struct device_node;
+struct msi_domain_info;
+
+/**
+ * struct msi_domain_ops - MSI interrupt domain callbacks
+ * @get_hwirq:		Retrieve the resulting hw irq number
+ * @msi_init:		Domain specific init function for MSI interrupts
+ * @msi_free:		Domain specific function to free a MSI interrupts
+ */
+struct msi_domain_ops {
+	irq_hw_number_t	(*get_hwirq)(struct msi_domain_info *info, void *arg);
+	int		(*msi_init)(struct irq_domain *domain,
+				    struct msi_domain_info *info,
+				    unsigned int virq, irq_hw_number_t hwirq,
+				    void *arg);
+	void		(*msi_free)(struct irq_domain *domain,
+				    struct msi_domain_info *info,
+				    unsigned int virq);
+};
+
+/**
+ * struct msi_domain_info - MSI interrupt domain data
+ * @ops:	The callback data structure
+ * @chip:	The associated interrupt chip
+ * @data:	Domain specific data
+ */
+struct msi_domain_info {
+	struct msi_domain_ops	*ops;
+	struct irq_chip		*chip;
+	void			*data;
+};
+
+int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,
+			    bool force);
+
+struct irq_domain *msi_create_irq_domain(struct device_node *of_node,
+					 struct msi_domain_info *info,
+					 struct irq_domain *parent);
+struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain);
+
+#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */
+
 #endif /* LINUX_MSI_H */
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 4f2eb2b1f23..9a76e3beda5 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -60,6 +60,16 @@ config IRQ_DOMAIN_HIERARCHY
 	bool
 	select IRQ_DOMAIN
 
+# Generic MSI interrupt support
+config GENERIC_MSI_IRQ
+	bool
+
+# Generic MSI hierarchical interrupt domain support
+config GENERIC_MSI_IRQ_DOMAIN
+	bool
+	select IRQ_DOMAIN_HIERARCHY
+	select GENERIC_MSI_IRQ
+
 config HANDLE_DOMAIN_IRQ
 	bool
 
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index fff17381f0a..d12123526e2 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -6,3 +6,4 @@ obj-$(CONFIG_IRQ_DOMAIN) += irqdomain.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
 obj-$(CONFIG_PM_SLEEP) += pm.o
+obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
new file mode 100644
index 00000000000..5e0cef4741d
--- /dev/null
+++ b/kernel/irq/msi.c
@@ -0,0 +1,141 @@
+/*
+ * linux/kernel/irq/msi.c
+ *
+ * Copyright (C) 2014 Intel Corp.
+ * Author: Jiang Liu <jiang.liu@linux.intel.com>
+ *
+ * This file is licensed under GPLv2.
+ *
+ * This file contains common code to support Message Signalled Interrupt for
+ * PCI compatible and non PCI compatible devices.
+ */
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/msi.h>
+
+#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
+/**
+ * msi_domain_set_affinity - Generic affinity setter function for MSI domains
+ * @irq_data:	The irq data associated to the interrupt
+ * @mask:	The affinity mask to set
+ * @force:	Flag to enforce setting (disable online checks)
+ *
+ * Intended to be used by MSI interrupt controllers which are
+ * implemented with hierarchical domains.
+ */
+int msi_domain_set_affinity(struct irq_data *irq_data,
+			    const struct cpumask *mask, bool force)
+{
+	struct irq_data *parent = irq_data->parent_data;
+	struct msi_msg msg;
+	int ret;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) {
+		BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg));
+		irq_chip_write_msi_msg(irq_data, &msg);
+	}
+
+	return ret;
+}
+
+static void msi_domain_activate(struct irq_domain *domain,
+				struct irq_data *irq_data)
+{
+	struct msi_msg msg;
+
+	BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg));
+	irq_chip_write_msi_msg(irq_data, &msg);
+}
+
+static void msi_domain_deactivate(struct irq_domain *domain,
+				  struct irq_data *irq_data)
+{
+	struct msi_msg msg;
+
+	memset(&msg, 0, sizeof(msg));
+	irq_chip_write_msi_msg(irq_data, &msg);
+}
+
+static int msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
+			    unsigned int nr_irqs, void *arg)
+{
+	struct msi_domain_info *info = domain->host_data;
+	struct msi_domain_ops *ops = info->ops;
+	irq_hw_number_t hwirq = ops->get_hwirq(info, arg);
+	int i, ret;
+
+	if (irq_find_mapping(domain, hwirq) > 0)
+		return -EEXIST;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < nr_irqs; i++) {
+		ret = ops->msi_init(domain, info, virq + i, hwirq + i, arg);
+		if (ret < 0) {
+			if (ops->msi_free) {
+				for (i--; i > 0; i--)
+					ops->msi_free(domain, info, virq + i);
+			}
+			irq_domain_free_irqs_top(domain, virq, nr_irqs);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void msi_domain_free(struct irq_domain *domain, unsigned int virq,
+			    unsigned int nr_irqs)
+{
+	struct msi_domain_info *info = domain->host_data;
+	int i;
+
+	if (info->ops->msi_free) {
+		for (i = 0; i < nr_irqs; i++)
+			info->ops->msi_free(domain, info, virq + i);
+	}
+	irq_domain_free_irqs_top(domain, virq, nr_irqs);
+}
+
+static struct irq_domain_ops msi_domain_ops = {
+	.alloc		= msi_domain_alloc,
+	.free		= msi_domain_free,
+	.activate	= msi_domain_activate,
+	.deactivate	= msi_domain_deactivate,
+};
+
+/**
+ * msi_create_irq_domain - Create a MSI interrupt domain
+ * @of_node:	Optional device-tree node of the interrupt controller
+ * @info:	MSI domain info
+ * @parent:	Parent irq domain
+ */
+struct irq_domain *msi_create_irq_domain(struct device_node *of_node,
+					 struct msi_domain_info *info,
+					 struct irq_domain *parent)
+{
+	struct irq_domain *domain;
+
+	domain = irq_domain_add_tree(of_node, &msi_domain_ops, info);
+	if (domain)
+		domain->parent = parent;
+
+	return domain;
+}
+
+/**
+ * msi_get_domain_info - Get the MSI interrupt domain info for @domain
+ * @domain:	The interrupt domain to retrieve data from
+ *
+ * Returns the pointer to the msi_domain_info stored in
+ * @domain->host_data.
+ */
+struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain)
+{
+	return (struct msi_domain_info *)domain->host_data;
+}
+
+#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */
-- 
cgit v1.2.3-70-g09d2


From 926ff9ad76e097011030feaee904395e06eea17a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 17 Nov 2014 18:09:34 +0100
Subject: asm-generic: Add msi.h

To support MSI irq domains we want a generic data structure for
allocation, but we need the option to provide an architecture specific
version of it. So instead of playing #ifdef games in linux/msi.h we
add a generic header file and let architectures decide whether to
include it or to provide their own implementation and provide the
required typedef.

I know that typedefs are not really nice, but in this case there are no
forward declarations required and it's the simplest solution.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Cc: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Alexander Gordeev <agordeev@redhat.com>
---
 include/asm-generic/msi.h | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100644 include/asm-generic/msi.h

(limited to 'include')

diff --git a/include/asm-generic/msi.h b/include/asm-generic/msi.h
new file mode 100644
index 00000000000..61c58d8878c
--- /dev/null
+++ b/include/asm-generic/msi.h
@@ -0,0 +1,32 @@
+#ifndef __ASM_GENERIC_MSI_H
+#define __ASM_GENERIC_MSI_H
+
+#include <linux/types.h>
+
+#ifndef NUM_MSI_ALLOC_SCRATCHPAD_REGS
+# define NUM_MSI_ALLOC_SCRATCHPAD_REGS	2
+#endif
+
+struct msi_desc;
+
+/**
+ * struct msi_alloc_info - Default structure for MSI interrupt allocation.
+ * @desc:	Pointer to msi descriptor
+ * @hwirq:	Associated hw interrupt number in the domain
+ * @scratchpad:	Storage for implementation specific scratch data
+ *
+ * Architectures can provide their own implementation by not including
+ * asm-generic/msi.h into their arch specific header file.
+ */
+typedef struct msi_alloc_info {
+	struct msi_desc			*desc;
+	irq_hw_number_t			hwirq;
+	union {
+		unsigned long		ul;
+		void			*ptr;
+	} scratchpad[NUM_MSI_ALLOC_SCRATCHPAD_REGS];
+} msi_alloc_info_t;
+
+#define GENERIC_MSI_DOMAIN_OPS		1
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From d9109698be6e7439e6082aa00d79d4556114739b Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Sat, 15 Nov 2014 22:24:04 +0800
Subject: genirq: Introduce msi_domain_alloc/free_irqs()

Introduce msi_domain_{alloc|free}_irqs() to alloc/free interrupts
from generic MSI irqdomain.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Alexander Gordeev <agordeev@redhat.com>
Link: http://lkml.kernel.org/r/1416061447-9472-7-git-send-email-jiang.liu@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/msi.h | 29 +++++++++++++++++++++
 kernel/irq/msi.c    | 75 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 104 insertions(+)

(limited to 'include')

diff --git a/include/linux/msi.h b/include/linux/msi.h
index b5ca2456769..7a93a988dce 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -115,6 +115,9 @@ struct msi_controller {
 };
 
 #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
+
+#include <asm/msi.h>
+
 struct irq_domain;
 struct irq_chip;
 struct device_node;
@@ -125,6 +128,18 @@ struct msi_domain_info;
  * @get_hwirq:		Retrieve the resulting hw irq number
  * @msi_init:		Domain specific init function for MSI interrupts
  * @msi_free:		Domain specific function to free a MSI interrupts
+ * @msi_check:		Callback for verification of the domain/info/dev data
+ * @msi_prepare:	Prepare the allocation of the interrupts in the domain
+ * @msi_finish:		Optional callbacl to finalize the allocation
+ * @set_desc:		Set the msi descriptor for an interrupt
+ * @handle_error:	Optional error handler if the allocation fails
+ *
+ * @get_hwirq, @msi_init and @msi_free are callbacks used by
+ * msi_create_irq_domain() and related interfaces
+ *
+ * @msi_check, @msi_prepare, @msi_finish, @set_desc and @handle_error
+ * are callbacks used by msi_irq_domain_alloc_irqs() and related
+ * interfaces which are based on msi_desc.
  */
 struct msi_domain_ops {
 	irq_hw_number_t	(*get_hwirq)(struct msi_domain_info *info, void *arg);
@@ -135,6 +150,17 @@ struct msi_domain_ops {
 	void		(*msi_free)(struct irq_domain *domain,
 				    struct msi_domain_info *info,
 				    unsigned int virq);
+	int		(*msi_check)(struct irq_domain *domain,
+				     struct msi_domain_info *info,
+				     struct device *dev);
+	int		(*msi_prepare)(struct irq_domain *domain,
+				       struct device *dev, int nvec,
+				       msi_alloc_info_t *arg);
+	void		(*msi_finish)(msi_alloc_info_t *arg, int retval);
+	void		(*set_desc)(msi_alloc_info_t *arg,
+				    struct msi_desc *desc);
+	int		(*handle_error)(struct irq_domain *domain,
+					struct msi_desc *desc, int error);
 };
 
 /**
@@ -155,6 +181,9 @@ int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,
 struct irq_domain *msi_create_irq_domain(struct device_node *of_node,
 					 struct msi_domain_info *info,
 					 struct irq_domain *parent);
+int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
+			  int nvec);
+void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev);
 struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain);
 
 #endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 5e0cef4741d..23111aaa06b 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -13,6 +13,9 @@
 #include <linux/irqdomain.h>
 #include <linux/msi.h>
 
+/* Temparory solution for building, will be removed later */
+#include <linux/pci.h>
+
 #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
 /**
  * msi_domain_set_affinity - Generic affinity setter function for MSI domains
@@ -126,6 +129,78 @@ struct irq_domain *msi_create_irq_domain(struct device_node *of_node,
 	return domain;
 }
 
+/**
+ * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain
+ * @domain:	The domain to allocate from
+ * @dev:	Pointer to device struct of the device for which the interrupts
+ *		are allocated
+ * @nvec:	The number of interrupts to allocate
+ *
+ * Returns 0 on success or an error code.
+ */
+int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
+			  int nvec)
+{
+	struct msi_domain_info *info = domain->host_data;
+	struct msi_domain_ops *ops = info->ops;
+	msi_alloc_info_t arg;
+	struct msi_desc *desc;
+	int i, ret, virq = -1;
+
+	ret = ops->msi_check(domain, info, dev);
+	if (ret == 0)
+		ret = ops->msi_prepare(domain, dev, nvec, &arg);
+	if (ret)
+		return ret;
+
+	for_each_msi_entry(desc, dev) {
+		ops->set_desc(&arg, desc);
+
+		virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used,
+					       dev_to_node(dev), &arg, false);
+		if (virq < 0) {
+			ret = -ENOSPC;
+			if (ops->handle_error)
+				ret = ops->handle_error(domain, desc, ret);
+			if (ops->msi_finish)
+				ops->msi_finish(&arg, ret);
+			return ret;
+		}
+
+		for (i = 0; i < desc->nvec_used; i++)
+			irq_set_msi_desc_off(virq, i, desc);
+	}
+
+	if (ops->msi_finish)
+		ops->msi_finish(&arg, 0);
+
+	for_each_msi_entry(desc, dev) {
+		if (desc->nvec_used == 1)
+			dev_dbg(dev, "irq %d for MSI\n", virq);
+		else
+			dev_dbg(dev, "irq [%d-%d] for MSI\n",
+				virq, virq + desc->nvec_used - 1);
+	}
+
+	return 0;
+}
+
+/**
+ * msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated tp @dev
+ * @domain:	The domain to managing the interrupts
+ * @dev:	Pointer to device struct of the device for which the interrupts
+ *		are free
+ */
+void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
+{
+	struct msi_desc *desc;
+
+	for_each_msi_entry(desc, dev) {
+		irq_domain_free_irqs(desc->irq, desc->nvec_used);
+		desc->irq = 0;
+	}
+}
+
 /**
  * msi_get_domain_info - Get the MSI interrupt domain info for @domain
  * @domain:	The interrupt domain to retrieve data from
-- 
cgit v1.2.3-70-g09d2


From aeeb59657c35da64068336c20068da237f41ab76 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Sat, 15 Nov 2014 22:24:05 +0800
Subject: genirq: Provide default callbacks for msi_domain_ops

Extend struct msi_domain_info and provide default callbacks for
msi_domain_ops.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Alexander Gordeev <agordeev@redhat.com>
Link: http://lkml.kernel.org/r/1416061447-9472-8-git-send-email-jiang.liu@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/msi.h |  42 +++++++++++++++++---
 kernel/irq/msi.c    | 111 ++++++++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 140 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/msi.h b/include/linux/msi.h
index 7a93a988dce..0098e2c8fd4 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -116,6 +116,7 @@ struct msi_controller {
 
 #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
 
+#include <linux/irqhandler.h>
 #include <asm/msi.h>
 
 struct irq_domain;
@@ -142,11 +143,12 @@ struct msi_domain_info;
  * interfaces which are based on msi_desc.
  */
 struct msi_domain_ops {
-	irq_hw_number_t	(*get_hwirq)(struct msi_domain_info *info, void *arg);
+	irq_hw_number_t	(*get_hwirq)(struct msi_domain_info *info,
+				     msi_alloc_info_t *arg);
 	int		(*msi_init)(struct irq_domain *domain,
 				    struct msi_domain_info *info,
 				    unsigned int virq, irq_hw_number_t hwirq,
-				    void *arg);
+				    msi_alloc_info_t *arg);
 	void		(*msi_free)(struct irq_domain *domain,
 				    struct msi_domain_info *info,
 				    unsigned int virq);
@@ -165,16 +167,46 @@ struct msi_domain_ops {
 
 /**
  * struct msi_domain_info - MSI interrupt domain data
- * @ops:	The callback data structure
- * @chip:	The associated interrupt chip
- * @data:	Domain specific data
+ * @flags:		Flags to decribe features and capabilities
+ * @ops:		The callback data structure
+ * @chip:		Optional: associated interrupt chip
+ * @chip_data:		Optional: associated interrupt chip data
+ * @handler:		Optional: associated interrupt flow handler
+ * @handler_data:	Optional: associated interrupt flow handler data
+ * @handler_name:	Optional: associated interrupt flow handler name
+ * @data:		Optional: domain specific data
  */
 struct msi_domain_info {
+	u32			flags;
 	struct msi_domain_ops	*ops;
 	struct irq_chip		*chip;
+	void			*chip_data;
+	irq_flow_handler_t	handler;
+	void			*handler_data;
+	const char		*handler_name;
 	void			*data;
 };
 
+/* Flags for msi_domain_info */
+enum {
+	/*
+	 * Init non implemented ops callbacks with default MSI domain
+	 * callbacks.
+	 */
+	MSI_FLAG_USE_DEF_DOM_OPS	= (1 << 0),
+	/*
+	 * Init non implemented chip callbacks with default MSI chip
+	 * callbacks.
+	 */
+	MSI_FLAG_USE_DEF_CHIP_OPS	= (1 << 1),
+	/* Build identity map between hwirq and irq */
+	MSI_FLAG_IDENTITY_MAP		= (1 << 2),
+	/* Support multiple PCI MSI interrupts */
+	MSI_FLAG_MULTI_PCI_MSI		= (1 << 3),
+	/* Support PCI MSIX interrupts */
+	MSI_FLAG_PCI_MSIX		= (1 << 4),
+};
+
 int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,
 			    bool force);
 
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 23111aaa06b..d0fe84d881f 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -9,6 +9,8 @@
  * This file contains common code to support Message Signalled Interrupt for
  * PCI compatible and non PCI compatible devices.
  */
+#include <linux/types.h>
+#include <linux/device.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/msi.h>
@@ -110,23 +112,112 @@ static struct irq_domain_ops msi_domain_ops = {
 	.deactivate	= msi_domain_deactivate,
 };
 
+#ifdef GENERIC_MSI_DOMAIN_OPS
+static irq_hw_number_t msi_domain_ops_get_hwirq(struct msi_domain_info *info,
+						msi_alloc_info_t *arg)
+{
+	return arg->hwirq;
+}
+
+static int msi_domain_ops_prepare(struct irq_domain *domain, struct device *dev,
+				  int nvec, msi_alloc_info_t *arg)
+{
+	memset(arg, 0, sizeof(*arg));
+	return 0;
+}
+
+static void msi_domain_ops_set_desc(msi_alloc_info_t *arg,
+				    struct msi_desc *desc)
+{
+	arg->desc = desc;
+}
+#else
+#define msi_domain_ops_get_hwirq	NULL
+#define msi_domain_ops_prepare		NULL
+#define msi_domain_ops_set_desc		NULL
+#endif /* !GENERIC_MSI_DOMAIN_OPS */
+
+static int msi_domain_ops_init(struct irq_domain *domain,
+			       struct msi_domain_info *info,
+			       unsigned int virq, irq_hw_number_t hwirq,
+			       msi_alloc_info_t *arg)
+{
+	irq_domain_set_hwirq_and_chip(domain, virq, hwirq, info->chip,
+				      info->chip_data);
+	if (info->handler && info->handler_name) {
+		__irq_set_handler(virq, info->handler, 0, info->handler_name);
+		if (info->handler_data)
+			irq_set_handler_data(virq, info->handler_data);
+	}
+	return 0;
+}
+
+static int msi_domain_ops_check(struct irq_domain *domain,
+				struct msi_domain_info *info,
+				struct device *dev)
+{
+	return 0;
+}
+
+static struct msi_domain_ops msi_domain_ops_default = {
+	.get_hwirq	= msi_domain_ops_get_hwirq,
+	.msi_init	= msi_domain_ops_init,
+	.msi_check	= msi_domain_ops_check,
+	.msi_prepare	= msi_domain_ops_prepare,
+	.set_desc	= msi_domain_ops_set_desc,
+};
+
+static void msi_domain_update_dom_ops(struct msi_domain_info *info)
+{
+	struct msi_domain_ops *ops = info->ops;
+
+	if (ops == NULL) {
+		info->ops = &msi_domain_ops_default;
+		return;
+	}
+
+	if (ops->get_hwirq == NULL)
+		ops->get_hwirq = msi_domain_ops_default.get_hwirq;
+	if (ops->msi_init == NULL)
+		ops->msi_init = msi_domain_ops_default.msi_init;
+	if (ops->msi_check == NULL)
+		ops->msi_check = msi_domain_ops_default.msi_check;
+	if (ops->msi_prepare == NULL)
+		ops->msi_prepare = msi_domain_ops_default.msi_prepare;
+	if (ops->set_desc == NULL)
+		ops->set_desc = msi_domain_ops_default.set_desc;
+}
+
+static void msi_domain_update_chip_ops(struct msi_domain_info *info)
+{
+	struct irq_chip *chip = info->chip;
+
+	BUG_ON(!chip);
+	if (!chip->irq_mask)
+		chip->irq_mask = pci_msi_mask_irq;
+	if (!chip->irq_unmask)
+		chip->irq_unmask = pci_msi_unmask_irq;
+	if (!chip->irq_set_affinity)
+		chip->irq_set_affinity = msi_domain_set_affinity;
+}
+
 /**
  * msi_create_irq_domain - Create a MSI interrupt domain
  * @of_node:	Optional device-tree node of the interrupt controller
  * @info:	MSI domain info
  * @parent:	Parent irq domain
  */
-struct irq_domain *msi_create_irq_domain(struct device_node *of_node,
+struct irq_domain *msi_create_irq_domain(struct device_node *node,
 					 struct msi_domain_info *info,
 					 struct irq_domain *parent)
 {
-	struct irq_domain *domain;
+	if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
+		msi_domain_update_dom_ops(info);
+	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
+		msi_domain_update_chip_ops(info);
 
-	domain = irq_domain_add_tree(of_node, &msi_domain_ops, info);
-	if (domain)
-		domain->parent = parent;
-
-	return domain;
+	return irq_domain_add_hierarchy(parent, 0, 0, node, &msi_domain_ops,
+					info);
 }
 
 /**
@@ -155,8 +246,12 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 
 	for_each_msi_entry(desc, dev) {
 		ops->set_desc(&arg, desc);
+		if (info->flags & MSI_FLAG_IDENTITY_MAP)
+			virq = (int)ops->get_hwirq(info, &arg);
+		else
+			virq = -1;
 
-		virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used,
+		virq = __irq_domain_alloc_irqs(domain, virq, desc->nvec_used,
 					       dev_to_node(dev), &arg, false);
 		if (virq < 0) {
 			ret = -ENOSPC;
-- 
cgit v1.2.3-70-g09d2


From 3878eaefb89aa841ae4c2150490cee864ac628cb Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Tue, 11 Nov 2014 21:02:18 +0800
Subject: PCI/MSI: Enhance core to support hierarchy irqdomain

Enhance PCI MSI core to support hierarchy irqdomain, so the common
code can be shared across architectures.

[ tglx: Extracted and combined from several patches ]

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 drivers/pci/Kconfig |   5 ++
 drivers/pci/msi.c   | 168 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/msi.h |  14 +++++
 3 files changed, 187 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 82f95f4512f..cced84233ac 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -17,6 +17,11 @@ config PCI_MSI
 
 	   If you don't know what to do here, say Y.
 
+config PCI_MSI_IRQ_DOMAIN
+	bool
+	depends on PCI_MSI
+	select GENERIC_MSI_IRQ_DOMAIN
+
 config PCI_DEBUG
 	bool "PCI Debugging"
 	depends on PCI && DEBUG_KERNEL
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 103700e127b..36b0c2e5592 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -19,6 +19,7 @@
 #include <linux/errno.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/irqdomain.h>
 
 #include "pci.h"
 
@@ -1091,3 +1092,170 @@ int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
 	return nvec;
 }
 EXPORT_SYMBOL(pci_enable_msix_range);
+
+#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
+/**
+ * pci_msi_domain_write_msg - Helper to write MSI message to PCI config space
+ * @irq_data:	Pointer to interrupt data of the MSI interrupt
+ * @msg:	Pointer to the message
+ */
+void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg)
+{
+	struct msi_desc *desc = irq_data->msi_desc;
+
+	/*
+	 * For MSI-X desc->irq is always equal to irq_data->irq. For
+	 * MSI only the first interrupt of MULTI MSI passes the test.
+	 */
+	if (desc->irq == irq_data->irq)
+		__pci_write_msi_msg(desc, msg);
+}
+
+/**
+ * pci_msi_domain_calc_hwirq - Generate a unique ID for an MSI source
+ * @dev:	Pointer to the PCI device
+ * @desc:	Pointer to the msi descriptor
+ *
+ * The ID number is only used within the irqdomain.
+ */
+irq_hw_number_t pci_msi_domain_calc_hwirq(struct pci_dev *dev,
+					  struct msi_desc *desc)
+{
+	return (irq_hw_number_t)desc->msi_attrib.entry_nr |
+		PCI_DEVID(dev->bus->number, dev->devfn) << 11 |
+		(pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27;
+}
+
+static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc)
+{
+	return !desc->msi_attrib.is_msix && desc->nvec_used > 1;
+}
+
+/**
+ * pci_msi_domain_check_cap - Verify that @domain supports the capabilities for @dev
+ * @domain:	The interrupt domain to check
+ * @info:	The domain info for verification
+ * @dev:	The device to check
+ *
+ * Returns:
+ *  0 if the functionality is supported
+ *  1 if Multi MSI is requested, but the domain does not support it
+ *  -ENOTSUPP otherwise
+ */
+int pci_msi_domain_check_cap(struct irq_domain *domain,
+			     struct msi_domain_info *info, struct device *dev)
+{
+	struct msi_desc *desc = first_pci_msi_entry(to_pci_dev(dev));
+
+	/* Special handling to support pci_enable_msi_range() */
+	if (pci_msi_desc_is_multi_msi(desc) &&
+	    !(info->flags & MSI_FLAG_MULTI_PCI_MSI))
+		return 1;
+	else if (desc->msi_attrib.is_msix && !(info->flags & MSI_FLAG_PCI_MSIX))
+		return -ENOTSUPP;
+
+	return 0;
+}
+
+static int pci_msi_domain_handle_error(struct irq_domain *domain,
+				       struct msi_desc *desc, int error)
+{
+	/* Special handling to support pci_enable_msi_range() */
+	if (pci_msi_desc_is_multi_msi(desc) && error == -ENOSPC)
+		return 1;
+
+	return error;
+}
+
+#ifdef GENERIC_MSI_DOMAIN_OPS
+static void pci_msi_domain_set_desc(msi_alloc_info_t *arg,
+				    struct msi_desc *desc)
+{
+	arg->desc = desc;
+	arg->hwirq = pci_msi_domain_calc_hwirq(msi_desc_to_pci_dev(desc),
+					       desc);
+}
+#else
+#define pci_msi_domain_set_desc		NULL
+#endif
+
+static struct msi_domain_ops pci_msi_domain_ops_default = {
+	.set_desc	= pci_msi_domain_set_desc,
+	.msi_check	= pci_msi_domain_check_cap,
+	.handle_error	= pci_msi_domain_handle_error,
+};
+
+static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info)
+{
+	struct msi_domain_ops *ops = info->ops;
+
+	if (ops == NULL) {
+		info->ops = &pci_msi_domain_ops_default;
+	} else {
+		if (ops->set_desc == NULL)
+			ops->set_desc = pci_msi_domain_set_desc;
+		if (ops->msi_check == NULL)
+			ops->msi_check = pci_msi_domain_check_cap;
+		if (ops->handle_error == NULL)
+			ops->handle_error = pci_msi_domain_handle_error;
+	}
+}
+
+static void pci_msi_domain_update_chip_ops(struct msi_domain_info *info)
+{
+	struct irq_chip *chip = info->chip;
+
+	BUG_ON(!chip);
+	if (!chip->irq_write_msi_msg)
+		chip->irq_write_msi_msg = pci_msi_domain_write_msg;
+}
+
+/**
+ * pci_msi_create_irq_domain - Creat a MSI interrupt domain
+ * @node:	Optional device-tree node of the interrupt controller
+ * @info:	MSI domain info
+ * @parent:	Parent irq domain
+ *
+ * Updates the domain and chip ops and creates a MSI interrupt domain.
+ *
+ * Returns:
+ * A domain pointer or NULL in case of failure.
+ */
+struct irq_domain *pci_msi_create_irq_domain(struct device_node *node,
+					     struct msi_domain_info *info,
+					     struct irq_domain *parent)
+{
+	if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
+		pci_msi_domain_update_dom_ops(info);
+	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
+		pci_msi_domain_update_chip_ops(info);
+
+	return msi_create_irq_domain(node, info, parent);
+}
+
+/**
+ * pci_msi_domain_alloc_irqs - Allocate interrupts for @dev in @domain
+ * @domain:	The interrupt domain to allocate from
+ * @dev:	The device for which to allocate
+ * @nvec:	The number of interrupts to allocate
+ * @type:	Unused to allow simpler migration from the arch_XXX interfaces
+ *
+ * Returns:
+ * A virtual interrupt number or an error code in case of failure
+ */
+int pci_msi_domain_alloc_irqs(struct irq_domain *domain, struct pci_dev *dev,
+			      int nvec, int type)
+{
+	return msi_domain_alloc_irqs(domain, &dev->dev, nvec);
+}
+
+/**
+ * pci_msi_domain_free_irqs - Free interrupts for @dev in @domain
+ * @domain:	The interrupt domain
+ * @dev:	The device for which to free interrupts
+ */
+void pci_msi_domain_free_irqs(struct irq_domain *domain, struct pci_dev *dev)
+{
+	msi_domain_free_irqs(domain, &dev->dev);
+}
+#endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 0098e2c8fd4..1628788aee2 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -220,4 +220,18 @@ struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain);
 
 #endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */
 
+#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
+void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg);
+struct irq_domain *pci_msi_create_irq_domain(struct device_node *node,
+					     struct msi_domain_info *info,
+					     struct irq_domain *parent);
+int pci_msi_domain_alloc_irqs(struct irq_domain *domain, struct pci_dev *dev,
+			      int nvec, int type);
+void pci_msi_domain_free_irqs(struct irq_domain *domain, struct pci_dev *dev);
+irq_hw_number_t pci_msi_domain_calc_hwirq(struct pci_dev *dev,
+					  struct msi_desc *desc);
+int pci_msi_domain_check_cap(struct irq_domain *domain,
+			     struct msi_domain_info *info, struct device *dev);
+#endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */
+
 #endif /* LINUX_MSI_H */
-- 
cgit v1.2.3-70-g09d2


From 8e047adae969701c6cec136484bb9de8572af934 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Sat, 15 Nov 2014 22:24:07 +0800
Subject: PCI/MSI: Provide mechanism to alloc/free MSI/MSIX interrupt from
 irqdomain

Provide mechanism to directly alloc/free MSI/MSIX interrupt from
irqdomain, which will be used to replace arch_setup_msi_irq()/
arch_setup_msi_irqs()/arch_teardown_msi_irq()/arch_teardown_msi_irqs().

To kill weak functions, this patch introduce a new weak function
arch_get_pci_msi_domain(), which is to retrieve the MSI irqdomain
for a PCI device. This weak function could be killed once we get
a common way to associate MSI domain with PCI device.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yijing Wang <wangyijing@huawei.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Alexander Gordeev <agordeev@redhat.com>
Link: http://lkml.kernel.org/r/1416061447-9472-10-git-send-email-jiang.liu@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 drivers/pci/msi.c   | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++---
 include/linux/msi.h |  3 +++
 2 files changed, 67 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 36b0c2e5592..4befe09053c 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -28,6 +28,40 @@ int pci_msi_ignore_mask;
 
 #define msix_table_size(flags)	((flags & PCI_MSIX_FLAGS_QSIZE) + 1)
 
+#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
+static struct irq_domain *pci_msi_default_domain;
+static DEFINE_MUTEX(pci_msi_domain_lock);
+
+struct irq_domain * __weak arch_get_pci_msi_domain(struct pci_dev *dev)
+{
+	return pci_msi_default_domain;
+}
+
+static int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	struct irq_domain *domain;
+
+	domain = arch_get_pci_msi_domain(dev);
+	if (domain)
+		return pci_msi_domain_alloc_irqs(domain, dev, nvec, type);
+
+	return arch_setup_msi_irqs(dev, nvec, type);
+}
+
+static void pci_msi_teardown_msi_irqs(struct pci_dev *dev)
+{
+	struct irq_domain *domain;
+
+	domain = arch_get_pci_msi_domain(dev);
+	if (domain)
+		pci_msi_domain_free_irqs(domain, dev);
+	else
+		arch_teardown_msi_irqs(dev);
+}
+#else
+#define pci_msi_setup_msi_irqs		arch_setup_msi_irqs
+#define pci_msi_teardown_msi_irqs	arch_teardown_msi_irqs
+#endif
 
 /* Arch hooks */
 
@@ -348,7 +382,7 @@ static void free_msi_irqs(struct pci_dev *dev)
 			for (i = 0; i < entry->nvec_used; i++)
 				BUG_ON(irq_has_action(entry->irq + i));
 
-	arch_teardown_msi_irqs(dev);
+	pci_msi_teardown_msi_irqs(dev);
 
 	list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) {
 		if (entry->msi_attrib.is_msix) {
@@ -600,7 +634,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec)
 	list_add_tail(&entry->list, &dev->msi_list);
 
 	/* Configure MSI capability structure */
-	ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
+	ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
 	if (ret) {
 		msi_mask_irq(entry, mask, ~mask);
 		free_msi_irqs(dev);
@@ -715,7 +749,7 @@ static int msix_capability_init(struct pci_dev *dev,
 	if (ret)
 		return ret;
 
-	ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
+	ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
 	if (ret)
 		goto out_avail;
 
@@ -1258,4 +1292,31 @@ void pci_msi_domain_free_irqs(struct irq_domain *domain, struct pci_dev *dev)
 {
 	msi_domain_free_irqs(domain, &dev->dev);
 }
+
+/**
+ * pci_msi_create_default_irq_domain - Create a default MSI interrupt domain
+ * @node:	Optional device-tree node of the interrupt controller
+ * @info:	MSI domain info
+ * @parent:	Parent irq domain
+ *
+ * Returns: A domain pointer or NULL in case of failure. If successful
+ * the default PCI/MSI irqdomain pointer is updated.
+ */
+struct irq_domain *pci_msi_create_default_irq_domain(struct device_node *node,
+		struct msi_domain_info *info, struct irq_domain *parent)
+{
+	struct irq_domain *domain;
+
+	mutex_lock(&pci_msi_domain_lock);
+	if (pci_msi_default_domain) {
+		pr_err("PCI: default irq domain for PCI MSI has already been created.\n");
+		domain = NULL;
+	} else {
+		domain = pci_msi_create_irq_domain(node, info, parent);
+		pci_msi_default_domain = domain;
+	}
+	mutex_unlock(&pci_msi_domain_lock);
+
+	return domain;
+}
 #endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 1628788aee2..692f217ae81 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -228,6 +228,9 @@ struct irq_domain *pci_msi_create_irq_domain(struct device_node *node,
 int pci_msi_domain_alloc_irqs(struct irq_domain *domain, struct pci_dev *dev,
 			      int nvec, int type);
 void pci_msi_domain_free_irqs(struct irq_domain *domain, struct pci_dev *dev);
+struct irq_domain *pci_msi_create_default_irq_domain(struct device_node *node,
+		 struct msi_domain_info *info, struct irq_domain *parent);
+
 irq_hw_number_t pci_msi_domain_calc_hwirq(struct pci_dev *dev,
 					  struct msi_desc *desc);
 int pci_msi_domain_check_cap(struct irq_domain *domain,
-- 
cgit v1.2.3-70-g09d2


From 020c312658d61297ffe43b412441c69b1c36fb1b Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Sat, 15 Nov 2014 10:49:12 +0000
Subject: PCI/MSI: Allow an msi_controller to be associated to an irq domain

With the new stacked irq domains, it becomes pretty tempting to
allocate an MSI domain per PCI bus, which would remove the requirement
of either relying on arch-specific code, or a default PCI MSI domain.

By allowing the msi_controller structure to carry a pointer to an
irq_domain, we can easily use this in pci_msi_setup_msi_irqs.  The
existing code can still be used as a fallback if the MSI driver does
not populate the domain field.

Tested on arm64 with the GICv3 ITS driver.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Jiang Liu <jiang.liu@linux.intel.com>
Link: http://lkml.kernel.org/r/1416048553-29289-2-git-send-email-marc.zyngier@arm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 drivers/pci/msi.c   | 16 ++++++++++++++--
 include/linux/msi.h |  3 +++
 2 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 4befe09053c..476f4b1a272 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -37,11 +37,23 @@ struct irq_domain * __weak arch_get_pci_msi_domain(struct pci_dev *dev)
 	return pci_msi_default_domain;
 }
 
+static struct irq_domain *pci_msi_get_domain(struct pci_dev *dev)
+{
+	struct irq_domain *domain = NULL;
+
+	if (dev->bus->msi)
+		domain = dev->bus->msi->domain;
+	if (!domain)
+		domain = arch_get_pci_msi_domain(dev);
+
+	return domain;
+}
+
 static int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
 	struct irq_domain *domain;
 
-	domain = arch_get_pci_msi_domain(dev);
+	domain = pci_msi_get_domain(dev);
 	if (domain)
 		return pci_msi_domain_alloc_irqs(domain, dev, nvec, type);
 
@@ -52,7 +64,7 @@ static void pci_msi_teardown_msi_irqs(struct pci_dev *dev)
 {
 	struct irq_domain *domain;
 
-	domain = arch_get_pci_msi_domain(dev);
+	domain = pci_msi_get_domain(dev);
 	if (domain)
 		pci_msi_domain_free_irqs(domain, dev);
 	else
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 692f217ae81..8ac4a68ffae 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -108,6 +108,9 @@ struct msi_controller {
 	struct device *dev;
 	struct device_node *of_node;
 	struct list_head list;
+#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
+	struct irq_domain *domain;
+#endif
 
 	int (*setup_irq)(struct msi_controller *chip, struct pci_dev *dev,
 			 struct msi_desc *desc);
-- 
cgit v1.2.3-70-g09d2


From c274e03af70544506cd7214fcc2d4c4376c2c6f4 Mon Sep 17 00:00:00 2001
From: Radim Krčmář <rkrcmar@redhat.com>
Date: Fri, 21 Nov 2014 22:21:50 +0100
Subject: kvm: x86: move assigned-dev.c and iommu.c to arch/x86/
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that ia64 is gone, we can hide deprecated device assignment in x86.

Notable changes:
 - kvm_vm_ioctl_assigned_device() was moved to x86/kvm_arch_vm_ioctl()

The easy parts were removed from generic kvm code, remaining
 - kvm_iommu_(un)map_pages() would require new code to be moved
 - struct kvm_assigned_dev_kernel depends on struct kvm_irq_ack_notifier

Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |   23 +
 arch/x86/kvm/Makefile           |    2 +-
 arch/x86/kvm/assigned-dev.c     | 1026 +++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/iommu.c            |  358 ++++++++++++++
 arch/x86/kvm/x86.c              |    2 +-
 include/linux/kvm_host.h        |   26 -
 virt/kvm/assigned-dev.c         | 1026 ---------------------------------------
 virt/kvm/iommu.c                |  358 --------------
 virt/kvm/kvm_main.c             |    2 -
 9 files changed, 1409 insertions(+), 1414 deletions(-)
 create mode 100644 arch/x86/kvm/assigned-dev.c
 create mode 100644 arch/x86/kvm/iommu.c
 delete mode 100644 virt/kvm/assigned-dev.c
 delete mode 100644 virt/kvm/iommu.c

(limited to 'include')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 76ff3e2d8fd..d549cf8bfb6 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1112,4 +1112,27 @@ int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
 void kvm_handle_pmu_event(struct kvm_vcpu *vcpu);
 void kvm_deliver_pmi(struct kvm_vcpu *vcpu);
 
+#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
+int kvm_iommu_map_guest(struct kvm *kvm);
+int kvm_iommu_unmap_guest(struct kvm *kvm);
+
+long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
+				  unsigned long arg);
+
+void kvm_free_all_assigned_devices(struct kvm *kvm);
+#else
+static inline int kvm_iommu_unmap_guest(struct kvm *kvm)
+{
+	return 0;
+}
+
+static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
+						unsigned long arg)
+{
+	return -ENOTTY;
+}
+
+static inline void kvm_free_all_assigned_devices(struct kvm *kvm) {}
+#endif
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index ee1cd92b03b..08f790dfadc 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -9,11 +9,11 @@ KVM := ../../../virt/kvm
 
 kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
 				$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
-kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= $(KVM)/assigned-dev.o $(KVM)/iommu.o
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
 			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o
+kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= assigned-dev.o iommu.o
 kvm-intel-y		+= vmx.o
 kvm-amd-y		+= svm.o
 
diff --git a/arch/x86/kvm/assigned-dev.c b/arch/x86/kvm/assigned-dev.c
new file mode 100644
index 00000000000..e05000e200d
--- /dev/null
+++ b/arch/x86/kvm/assigned-dev.c
@@ -0,0 +1,1026 @@
+/*
+ * Kernel-based Virtual Machine - device assignment support
+ *
+ * Copyright (C) 2010 Red Hat, Inc. and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/namei.h>
+#include <linux/fs.h>
+#include "irq.h"
+
+static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
+						      int assigned_dev_id)
+{
+	struct list_head *ptr;
+	struct kvm_assigned_dev_kernel *match;
+
+	list_for_each(ptr, head) {
+		match = list_entry(ptr, struct kvm_assigned_dev_kernel, list);
+		if (match->assigned_dev_id == assigned_dev_id)
+			return match;
+	}
+	return NULL;
+}
+
+static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
+				    *assigned_dev, int irq)
+{
+	int i, index;
+	struct msix_entry *host_msix_entries;
+
+	host_msix_entries = assigned_dev->host_msix_entries;
+
+	index = -1;
+	for (i = 0; i < assigned_dev->entries_nr; i++)
+		if (irq == host_msix_entries[i].vector) {
+			index = i;
+			break;
+		}
+	if (index < 0)
+		printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n");
+
+	return index;
+}
+
+static irqreturn_t kvm_assigned_dev_intx(int irq, void *dev_id)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+	int ret;
+
+	spin_lock(&assigned_dev->intx_lock);
+	if (pci_check_and_mask_intx(assigned_dev->dev)) {
+		assigned_dev->host_irq_disabled = true;
+		ret = IRQ_WAKE_THREAD;
+	} else
+		ret = IRQ_NONE;
+	spin_unlock(&assigned_dev->intx_lock);
+
+	return ret;
+}
+
+static void
+kvm_assigned_dev_raise_guest_irq(struct kvm_assigned_dev_kernel *assigned_dev,
+				 int vector)
+{
+	if (unlikely(assigned_dev->irq_requested_type &
+		     KVM_DEV_IRQ_GUEST_INTX)) {
+		spin_lock(&assigned_dev->intx_mask_lock);
+		if (!(assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX))
+			kvm_set_irq(assigned_dev->kvm,
+				    assigned_dev->irq_source_id, vector, 1,
+				    false);
+		spin_unlock(&assigned_dev->intx_mask_lock);
+	} else
+		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+			    vector, 1, false);
+}
+
+static irqreturn_t kvm_assigned_dev_thread_intx(int irq, void *dev_id)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+
+	if (!(assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
+		spin_lock_irq(&assigned_dev->intx_lock);
+		disable_irq_nosync(irq);
+		assigned_dev->host_irq_disabled = true;
+		spin_unlock_irq(&assigned_dev->intx_lock);
+	}
+
+	kvm_assigned_dev_raise_guest_irq(assigned_dev,
+					 assigned_dev->guest_irq);
+
+	return IRQ_HANDLED;
+}
+
+#ifdef __KVM_HAVE_MSI
+static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+	int ret = kvm_set_irq_inatomic(assigned_dev->kvm,
+				       assigned_dev->irq_source_id,
+				       assigned_dev->guest_irq, 1);
+	return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED;
+}
+
+static irqreturn_t kvm_assigned_dev_thread_msi(int irq, void *dev_id)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+
+	kvm_assigned_dev_raise_guest_irq(assigned_dev,
+					 assigned_dev->guest_irq);
+
+	return IRQ_HANDLED;
+}
+#endif
+
+#ifdef __KVM_HAVE_MSIX
+static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+	int index = find_index_from_host_irq(assigned_dev, irq);
+	u32 vector;
+	int ret = 0;
+
+	if (index >= 0) {
+		vector = assigned_dev->guest_msix_entries[index].vector;
+		ret = kvm_set_irq_inatomic(assigned_dev->kvm,
+					   assigned_dev->irq_source_id,
+					   vector, 1);
+	}
+
+	return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED;
+}
+
+static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+	int index = find_index_from_host_irq(assigned_dev, irq);
+	u32 vector;
+
+	if (index >= 0) {
+		vector = assigned_dev->guest_msix_entries[index].vector;
+		kvm_assigned_dev_raise_guest_irq(assigned_dev, vector);
+	}
+
+	return IRQ_HANDLED;
+}
+#endif
+
+/* Ack the irq line for an assigned device */
+static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
+{
+	struct kvm_assigned_dev_kernel *dev =
+		container_of(kian, struct kvm_assigned_dev_kernel,
+			     ack_notifier);
+
+	kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0, false);
+
+	spin_lock(&dev->intx_mask_lock);
+
+	if (!(dev->flags & KVM_DEV_ASSIGN_MASK_INTX)) {
+		bool reassert = false;
+
+		spin_lock_irq(&dev->intx_lock);
+		/*
+		 * The guest IRQ may be shared so this ack can come from an
+		 * IRQ for another guest device.
+		 */
+		if (dev->host_irq_disabled) {
+			if (!(dev->flags & KVM_DEV_ASSIGN_PCI_2_3))
+				enable_irq(dev->host_irq);
+			else if (!pci_check_and_unmask_intx(dev->dev))
+				reassert = true;
+			dev->host_irq_disabled = reassert;
+		}
+		spin_unlock_irq(&dev->intx_lock);
+
+		if (reassert)
+			kvm_set_irq(dev->kvm, dev->irq_source_id,
+				    dev->guest_irq, 1, false);
+	}
+
+	spin_unlock(&dev->intx_mask_lock);
+}
+
+static void deassign_guest_irq(struct kvm *kvm,
+			       struct kvm_assigned_dev_kernel *assigned_dev)
+{
+	if (assigned_dev->ack_notifier.gsi != -1)
+		kvm_unregister_irq_ack_notifier(kvm,
+						&assigned_dev->ack_notifier);
+
+	kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+		    assigned_dev->guest_irq, 0, false);
+
+	if (assigned_dev->irq_source_id != -1)
+		kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
+	assigned_dev->irq_source_id = -1;
+	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK);
+}
+
+/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */
+static void deassign_host_irq(struct kvm *kvm,
+			      struct kvm_assigned_dev_kernel *assigned_dev)
+{
+	/*
+	 * We disable irq here to prevent further events.
+	 *
+	 * Notice this maybe result in nested disable if the interrupt type is
+	 * INTx, but it's OK for we are going to free it.
+	 *
+	 * If this function is a part of VM destroy, please ensure that till
+	 * now, the kvm state is still legal for probably we also have to wait
+	 * on a currently running IRQ handler.
+	 */
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+		int i;
+		for (i = 0; i < assigned_dev->entries_nr; i++)
+			disable_irq(assigned_dev->host_msix_entries[i].vector);
+
+		for (i = 0; i < assigned_dev->entries_nr; i++)
+			free_irq(assigned_dev->host_msix_entries[i].vector,
+				 assigned_dev);
+
+		assigned_dev->entries_nr = 0;
+		kfree(assigned_dev->host_msix_entries);
+		kfree(assigned_dev->guest_msix_entries);
+		pci_disable_msix(assigned_dev->dev);
+	} else {
+		/* Deal with MSI and INTx */
+		if ((assigned_dev->irq_requested_type &
+		     KVM_DEV_IRQ_HOST_INTX) &&
+		    (assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
+			spin_lock_irq(&assigned_dev->intx_lock);
+			pci_intx(assigned_dev->dev, false);
+			spin_unlock_irq(&assigned_dev->intx_lock);
+			synchronize_irq(assigned_dev->host_irq);
+		} else
+			disable_irq(assigned_dev->host_irq);
+
+		free_irq(assigned_dev->host_irq, assigned_dev);
+
+		if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI)
+			pci_disable_msi(assigned_dev->dev);
+	}
+
+	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK);
+}
+
+static int kvm_deassign_irq(struct kvm *kvm,
+			    struct kvm_assigned_dev_kernel *assigned_dev,
+			    unsigned long irq_requested_type)
+{
+	unsigned long guest_irq_type, host_irq_type;
+
+	if (!irqchip_in_kernel(kvm))
+		return -EINVAL;
+	/* no irq assignment to deassign */
+	if (!assigned_dev->irq_requested_type)
+		return -ENXIO;
+
+	host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK;
+	guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK;
+
+	if (host_irq_type)
+		deassign_host_irq(kvm, assigned_dev);
+	if (guest_irq_type)
+		deassign_guest_irq(kvm, assigned_dev);
+
+	return 0;
+}
+
+static void kvm_free_assigned_irq(struct kvm *kvm,
+				  struct kvm_assigned_dev_kernel *assigned_dev)
+{
+	kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type);
+}
+
+static void kvm_free_assigned_device(struct kvm *kvm,
+				     struct kvm_assigned_dev_kernel
+				     *assigned_dev)
+{
+	kvm_free_assigned_irq(kvm, assigned_dev);
+
+	pci_reset_function(assigned_dev->dev);
+	if (pci_load_and_free_saved_state(assigned_dev->dev,
+					  &assigned_dev->pci_saved_state))
+		printk(KERN_INFO "%s: Couldn't reload %s saved state\n",
+		       __func__, dev_name(&assigned_dev->dev->dev));
+	else
+		pci_restore_state(assigned_dev->dev);
+
+	pci_clear_dev_assigned(assigned_dev->dev);
+
+	pci_release_regions(assigned_dev->dev);
+	pci_disable_device(assigned_dev->dev);
+	pci_dev_put(assigned_dev->dev);
+
+	list_del(&assigned_dev->list);
+	kfree(assigned_dev);
+}
+
+void kvm_free_all_assigned_devices(struct kvm *kvm)
+{
+	struct list_head *ptr, *ptr2;
+	struct kvm_assigned_dev_kernel *assigned_dev;
+
+	list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) {
+		assigned_dev = list_entry(ptr,
+					  struct kvm_assigned_dev_kernel,
+					  list);
+
+		kvm_free_assigned_device(kvm, assigned_dev);
+	}
+}
+
+static int assigned_device_enable_host_intx(struct kvm *kvm,
+					    struct kvm_assigned_dev_kernel *dev)
+{
+	irq_handler_t irq_handler;
+	unsigned long flags;
+
+	dev->host_irq = dev->dev->irq;
+
+	/*
+	 * We can only share the IRQ line with other host devices if we are
+	 * able to disable the IRQ source at device-level - independently of
+	 * the guest driver. Otherwise host devices may suffer from unbounded
+	 * IRQ latencies when the guest keeps the line asserted.
+	 */
+	if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) {
+		irq_handler = kvm_assigned_dev_intx;
+		flags = IRQF_SHARED;
+	} else {
+		irq_handler = NULL;
+		flags = IRQF_ONESHOT;
+	}
+	if (request_threaded_irq(dev->host_irq, irq_handler,
+				 kvm_assigned_dev_thread_intx, flags,
+				 dev->irq_name, dev))
+		return -EIO;
+
+	if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) {
+		spin_lock_irq(&dev->intx_lock);
+		pci_intx(dev->dev, true);
+		spin_unlock_irq(&dev->intx_lock);
+	}
+	return 0;
+}
+
+#ifdef __KVM_HAVE_MSI
+static int assigned_device_enable_host_msi(struct kvm *kvm,
+					   struct kvm_assigned_dev_kernel *dev)
+{
+	int r;
+
+	if (!dev->dev->msi_enabled) {
+		r = pci_enable_msi(dev->dev);
+		if (r)
+			return r;
+	}
+
+	dev->host_irq = dev->dev->irq;
+	if (request_threaded_irq(dev->host_irq, kvm_assigned_dev_msi,
+				 kvm_assigned_dev_thread_msi, 0,
+				 dev->irq_name, dev)) {
+		pci_disable_msi(dev->dev);
+		return -EIO;
+	}
+
+	return 0;
+}
+#endif
+
+#ifdef __KVM_HAVE_MSIX
+static int assigned_device_enable_host_msix(struct kvm *kvm,
+					    struct kvm_assigned_dev_kernel *dev)
+{
+	int i, r = -EINVAL;
+
+	/* host_msix_entries and guest_msix_entries should have been
+	 * initialized */
+	if (dev->entries_nr == 0)
+		return r;
+
+	r = pci_enable_msix_exact(dev->dev,
+				  dev->host_msix_entries, dev->entries_nr);
+	if (r)
+		return r;
+
+	for (i = 0; i < dev->entries_nr; i++) {
+		r = request_threaded_irq(dev->host_msix_entries[i].vector,
+					 kvm_assigned_dev_msix,
+					 kvm_assigned_dev_thread_msix,
+					 0, dev->irq_name, dev);
+		if (r)
+			goto err;
+	}
+
+	return 0;
+err:
+	for (i -= 1; i >= 0; i--)
+		free_irq(dev->host_msix_entries[i].vector, dev);
+	pci_disable_msix(dev->dev);
+	return r;
+}
+
+#endif
+
+static int assigned_device_enable_guest_intx(struct kvm *kvm,
+				struct kvm_assigned_dev_kernel *dev,
+				struct kvm_assigned_irq *irq)
+{
+	dev->guest_irq = irq->guest_irq;
+	dev->ack_notifier.gsi = irq->guest_irq;
+	return 0;
+}
+
+#ifdef __KVM_HAVE_MSI
+static int assigned_device_enable_guest_msi(struct kvm *kvm,
+			struct kvm_assigned_dev_kernel *dev,
+			struct kvm_assigned_irq *irq)
+{
+	dev->guest_irq = irq->guest_irq;
+	dev->ack_notifier.gsi = -1;
+	return 0;
+}
+#endif
+
+#ifdef __KVM_HAVE_MSIX
+static int assigned_device_enable_guest_msix(struct kvm *kvm,
+			struct kvm_assigned_dev_kernel *dev,
+			struct kvm_assigned_irq *irq)
+{
+	dev->guest_irq = irq->guest_irq;
+	dev->ack_notifier.gsi = -1;
+	return 0;
+}
+#endif
+
+static int assign_host_irq(struct kvm *kvm,
+			   struct kvm_assigned_dev_kernel *dev,
+			   __u32 host_irq_type)
+{
+	int r = -EEXIST;
+
+	if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK)
+		return r;
+
+	snprintf(dev->irq_name, sizeof(dev->irq_name), "kvm:%s",
+		 pci_name(dev->dev));
+
+	switch (host_irq_type) {
+	case KVM_DEV_IRQ_HOST_INTX:
+		r = assigned_device_enable_host_intx(kvm, dev);
+		break;
+#ifdef __KVM_HAVE_MSI
+	case KVM_DEV_IRQ_HOST_MSI:
+		r = assigned_device_enable_host_msi(kvm, dev);
+		break;
+#endif
+#ifdef __KVM_HAVE_MSIX
+	case KVM_DEV_IRQ_HOST_MSIX:
+		r = assigned_device_enable_host_msix(kvm, dev);
+		break;
+#endif
+	default:
+		r = -EINVAL;
+	}
+	dev->host_irq_disabled = false;
+
+	if (!r)
+		dev->irq_requested_type |= host_irq_type;
+
+	return r;
+}
+
+static int assign_guest_irq(struct kvm *kvm,
+			    struct kvm_assigned_dev_kernel *dev,
+			    struct kvm_assigned_irq *irq,
+			    unsigned long guest_irq_type)
+{
+	int id;
+	int r = -EEXIST;
+
+	if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK)
+		return r;
+
+	id = kvm_request_irq_source_id(kvm);
+	if (id < 0)
+		return id;
+
+	dev->irq_source_id = id;
+
+	switch (guest_irq_type) {
+	case KVM_DEV_IRQ_GUEST_INTX:
+		r = assigned_device_enable_guest_intx(kvm, dev, irq);
+		break;
+#ifdef __KVM_HAVE_MSI
+	case KVM_DEV_IRQ_GUEST_MSI:
+		r = assigned_device_enable_guest_msi(kvm, dev, irq);
+		break;
+#endif
+#ifdef __KVM_HAVE_MSIX
+	case KVM_DEV_IRQ_GUEST_MSIX:
+		r = assigned_device_enable_guest_msix(kvm, dev, irq);
+		break;
+#endif
+	default:
+		r = -EINVAL;
+	}
+
+	if (!r) {
+		dev->irq_requested_type |= guest_irq_type;
+		if (dev->ack_notifier.gsi != -1)
+			kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier);
+	} else {
+		kvm_free_irq_source_id(kvm, dev->irq_source_id);
+		dev->irq_source_id = -1;
+	}
+
+	return r;
+}
+
+/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */
+static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
+				   struct kvm_assigned_irq *assigned_irq)
+{
+	int r = -EINVAL;
+	struct kvm_assigned_dev_kernel *match;
+	unsigned long host_irq_type, guest_irq_type;
+
+	if (!irqchip_in_kernel(kvm))
+		return r;
+
+	mutex_lock(&kvm->lock);
+	r = -ENODEV;
+	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      assigned_irq->assigned_dev_id);
+	if (!match)
+		goto out;
+
+	host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK);
+	guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK);
+
+	r = -EINVAL;
+	/* can only assign one type at a time */
+	if (hweight_long(host_irq_type) > 1)
+		goto out;
+	if (hweight_long(guest_irq_type) > 1)
+		goto out;
+	if (host_irq_type == 0 && guest_irq_type == 0)
+		goto out;
+
+	r = 0;
+	if (host_irq_type)
+		r = assign_host_irq(kvm, match, host_irq_type);
+	if (r)
+		goto out;
+
+	if (guest_irq_type)
+		r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type);
+out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm,
+					 struct kvm_assigned_irq
+					 *assigned_irq)
+{
+	int r = -ENODEV;
+	struct kvm_assigned_dev_kernel *match;
+	unsigned long irq_type;
+
+	mutex_lock(&kvm->lock);
+
+	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      assigned_irq->assigned_dev_id);
+	if (!match)
+		goto out;
+
+	irq_type = assigned_irq->flags & (KVM_DEV_IRQ_HOST_MASK |
+					  KVM_DEV_IRQ_GUEST_MASK);
+	r = kvm_deassign_irq(kvm, match, irq_type);
+out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+/*
+ * We want to test whether the caller has been granted permissions to
+ * use this device.  To be able to configure and control the device,
+ * the user needs access to PCI configuration space and BAR resources.
+ * These are accessed through PCI sysfs.  PCI config space is often
+ * passed to the process calling this ioctl via file descriptor, so we
+ * can't rely on access to that file.  We can check for permissions
+ * on each of the BAR resource files, which is a pretty clear
+ * indicator that the user has been granted access to the device.
+ */
+static int probe_sysfs_permissions(struct pci_dev *dev)
+{
+#ifdef CONFIG_SYSFS
+	int i;
+	bool bar_found = false;
+
+	for (i = PCI_STD_RESOURCES; i <= PCI_STD_RESOURCE_END; i++) {
+		char *kpath, *syspath;
+		struct path path;
+		struct inode *inode;
+		int r;
+
+		if (!pci_resource_len(dev, i))
+			continue;
+
+		kpath = kobject_get_path(&dev->dev.kobj, GFP_KERNEL);
+		if (!kpath)
+			return -ENOMEM;
+
+		/* Per sysfs-rules, sysfs is always at /sys */
+		syspath = kasprintf(GFP_KERNEL, "/sys%s/resource%d", kpath, i);
+		kfree(kpath);
+		if (!syspath)
+			return -ENOMEM;
+
+		r = kern_path(syspath, LOOKUP_FOLLOW, &path);
+		kfree(syspath);
+		if (r)
+			return r;
+
+		inode = path.dentry->d_inode;
+
+		r = inode_permission(inode, MAY_READ | MAY_WRITE | MAY_ACCESS);
+		path_put(&path);
+		if (r)
+			return r;
+
+		bar_found = true;
+	}
+
+	/* If no resources, probably something special */
+	if (!bar_found)
+		return -EPERM;
+
+	return 0;
+#else
+	return -EINVAL; /* No way to control the device without sysfs */
+#endif
+}
+
+static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
+				      struct kvm_assigned_pci_dev *assigned_dev)
+{
+	int r = 0, idx;
+	struct kvm_assigned_dev_kernel *match;
+	struct pci_dev *dev;
+
+	if (!(assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU))
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+	idx = srcu_read_lock(&kvm->srcu);
+
+	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      assigned_dev->assigned_dev_id);
+	if (match) {
+		/* device already assigned */
+		r = -EEXIST;
+		goto out;
+	}
+
+	match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL);
+	if (match == NULL) {
+		printk(KERN_INFO "%s: Couldn't allocate memory\n",
+		       __func__);
+		r = -ENOMEM;
+		goto out;
+	}
+	dev = pci_get_domain_bus_and_slot(assigned_dev->segnr,
+				   assigned_dev->busnr,
+				   assigned_dev->devfn);
+	if (!dev) {
+		printk(KERN_INFO "%s: host device not found\n", __func__);
+		r = -EINVAL;
+		goto out_free;
+	}
+
+	/* Don't allow bridges to be assigned */
+	if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL) {
+		r = -EPERM;
+		goto out_put;
+	}
+
+	r = probe_sysfs_permissions(dev);
+	if (r)
+		goto out_put;
+
+	if (pci_enable_device(dev)) {
+		printk(KERN_INFO "%s: Could not enable PCI device\n", __func__);
+		r = -EBUSY;
+		goto out_put;
+	}
+	r = pci_request_regions(dev, "kvm_assigned_device");
+	if (r) {
+		printk(KERN_INFO "%s: Could not get access to device regions\n",
+		       __func__);
+		goto out_disable;
+	}
+
+	pci_reset_function(dev);
+	pci_save_state(dev);
+	match->pci_saved_state = pci_store_saved_state(dev);
+	if (!match->pci_saved_state)
+		printk(KERN_DEBUG "%s: Couldn't store %s saved state\n",
+		       __func__, dev_name(&dev->dev));
+
+	if (!pci_intx_mask_supported(dev))
+		assigned_dev->flags &= ~KVM_DEV_ASSIGN_PCI_2_3;
+
+	match->assigned_dev_id = assigned_dev->assigned_dev_id;
+	match->host_segnr = assigned_dev->segnr;
+	match->host_busnr = assigned_dev->busnr;
+	match->host_devfn = assigned_dev->devfn;
+	match->flags = assigned_dev->flags;
+	match->dev = dev;
+	spin_lock_init(&match->intx_lock);
+	spin_lock_init(&match->intx_mask_lock);
+	match->irq_source_id = -1;
+	match->kvm = kvm;
+	match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
+
+	list_add(&match->list, &kvm->arch.assigned_dev_head);
+
+	if (!kvm->arch.iommu_domain) {
+		r = kvm_iommu_map_guest(kvm);
+		if (r)
+			goto out_list_del;
+	}
+	r = kvm_assign_device(kvm, match);
+	if (r)
+		goto out_list_del;
+
+out:
+	srcu_read_unlock(&kvm->srcu, idx);
+	mutex_unlock(&kvm->lock);
+	return r;
+out_list_del:
+	if (pci_load_and_free_saved_state(dev, &match->pci_saved_state))
+		printk(KERN_INFO "%s: Couldn't reload %s saved state\n",
+		       __func__, dev_name(&dev->dev));
+	list_del(&match->list);
+	pci_release_regions(dev);
+out_disable:
+	pci_disable_device(dev);
+out_put:
+	pci_dev_put(dev);
+out_free:
+	kfree(match);
+	srcu_read_unlock(&kvm->srcu, idx);
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
+		struct kvm_assigned_pci_dev *assigned_dev)
+{
+	int r = 0;
+	struct kvm_assigned_dev_kernel *match;
+
+	mutex_lock(&kvm->lock);
+
+	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      assigned_dev->assigned_dev_id);
+	if (!match) {
+		printk(KERN_INFO "%s: device hasn't been assigned before, "
+		  "so cannot be deassigned\n", __func__);
+		r = -EINVAL;
+		goto out;
+	}
+
+	kvm_deassign_device(kvm, match);
+
+	kvm_free_assigned_device(kvm, match);
+
+out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+
+#ifdef __KVM_HAVE_MSIX
+static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
+				    struct kvm_assigned_msix_nr *entry_nr)
+{
+	int r = 0;
+	struct kvm_assigned_dev_kernel *adev;
+
+	mutex_lock(&kvm->lock);
+
+	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      entry_nr->assigned_dev_id);
+	if (!adev) {
+		r = -EINVAL;
+		goto msix_nr_out;
+	}
+
+	if (adev->entries_nr == 0) {
+		adev->entries_nr = entry_nr->entry_nr;
+		if (adev->entries_nr == 0 ||
+		    adev->entries_nr > KVM_MAX_MSIX_PER_DEV) {
+			r = -EINVAL;
+			goto msix_nr_out;
+		}
+
+		adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) *
+						entry_nr->entry_nr,
+						GFP_KERNEL);
+		if (!adev->host_msix_entries) {
+			r = -ENOMEM;
+			goto msix_nr_out;
+		}
+		adev->guest_msix_entries =
+			kzalloc(sizeof(struct msix_entry) * entry_nr->entry_nr,
+				GFP_KERNEL);
+		if (!adev->guest_msix_entries) {
+			kfree(adev->host_msix_entries);
+			r = -ENOMEM;
+			goto msix_nr_out;
+		}
+	} else /* Not allowed set MSI-X number twice */
+		r = -EINVAL;
+msix_nr_out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm,
+				       struct kvm_assigned_msix_entry *entry)
+{
+	int r = 0, i;
+	struct kvm_assigned_dev_kernel *adev;
+
+	mutex_lock(&kvm->lock);
+
+	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      entry->assigned_dev_id);
+
+	if (!adev) {
+		r = -EINVAL;
+		goto msix_entry_out;
+	}
+
+	for (i = 0; i < adev->entries_nr; i++)
+		if (adev->guest_msix_entries[i].vector == 0 ||
+		    adev->guest_msix_entries[i].entry == entry->entry) {
+			adev->guest_msix_entries[i].entry = entry->entry;
+			adev->guest_msix_entries[i].vector = entry->gsi;
+			adev->host_msix_entries[i].entry = entry->entry;
+			break;
+		}
+	if (i == adev->entries_nr) {
+		r = -ENOSPC;
+		goto msix_entry_out;
+	}
+
+msix_entry_out:
+	mutex_unlock(&kvm->lock);
+
+	return r;
+}
+#endif
+
+static int kvm_vm_ioctl_set_pci_irq_mask(struct kvm *kvm,
+		struct kvm_assigned_pci_dev *assigned_dev)
+{
+	int r = 0;
+	struct kvm_assigned_dev_kernel *match;
+
+	mutex_lock(&kvm->lock);
+
+	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      assigned_dev->assigned_dev_id);
+	if (!match) {
+		r = -ENODEV;
+		goto out;
+	}
+
+	spin_lock(&match->intx_mask_lock);
+
+	match->flags &= ~KVM_DEV_ASSIGN_MASK_INTX;
+	match->flags |= assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX;
+
+	if (match->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) {
+		if (assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX) {
+			kvm_set_irq(match->kvm, match->irq_source_id,
+				    match->guest_irq, 0, false);
+			/*
+			 * Masking at hardware-level is performed on demand,
+			 * i.e. when an IRQ actually arrives at the host.
+			 */
+		} else if (!(assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
+			/*
+			 * Unmask the IRQ line if required. Unmasking at
+			 * device level will be performed by user space.
+			 */
+			spin_lock_irq(&match->intx_lock);
+			if (match->host_irq_disabled) {
+				enable_irq(match->host_irq);
+				match->host_irq_disabled = false;
+			}
+			spin_unlock_irq(&match->intx_lock);
+		}
+	}
+
+	spin_unlock(&match->intx_mask_lock);
+
+out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
+				  unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	int r;
+
+	switch (ioctl) {
+	case KVM_ASSIGN_PCI_DEVICE: {
+		struct kvm_assigned_pci_dev assigned_dev;
+
+		r = -EFAULT;
+		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
+			goto out;
+		r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev);
+		if (r)
+			goto out;
+		break;
+	}
+	case KVM_ASSIGN_IRQ: {
+		r = -EOPNOTSUPP;
+		break;
+	}
+	case KVM_ASSIGN_DEV_IRQ: {
+		struct kvm_assigned_irq assigned_irq;
+
+		r = -EFAULT;
+		if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
+			goto out;
+		r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq);
+		if (r)
+			goto out;
+		break;
+	}
+	case KVM_DEASSIGN_DEV_IRQ: {
+		struct kvm_assigned_irq assigned_irq;
+
+		r = -EFAULT;
+		if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
+			goto out;
+		r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq);
+		if (r)
+			goto out;
+		break;
+	}
+	case KVM_DEASSIGN_PCI_DEVICE: {
+		struct kvm_assigned_pci_dev assigned_dev;
+
+		r = -EFAULT;
+		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
+			goto out;
+		r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev);
+		if (r)
+			goto out;
+		break;
+	}
+#ifdef __KVM_HAVE_MSIX
+	case KVM_ASSIGN_SET_MSIX_NR: {
+		struct kvm_assigned_msix_nr entry_nr;
+		r = -EFAULT;
+		if (copy_from_user(&entry_nr, argp, sizeof entry_nr))
+			goto out;
+		r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr);
+		if (r)
+			goto out;
+		break;
+	}
+	case KVM_ASSIGN_SET_MSIX_ENTRY: {
+		struct kvm_assigned_msix_entry entry;
+		r = -EFAULT;
+		if (copy_from_user(&entry, argp, sizeof entry))
+			goto out;
+		r = kvm_vm_ioctl_set_msix_entry(kvm, &entry);
+		if (r)
+			goto out;
+		break;
+	}
+#endif
+	case KVM_ASSIGN_SET_INTX_MASK: {
+		struct kvm_assigned_pci_dev assigned_dev;
+
+		r = -EFAULT;
+		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
+			goto out;
+		r = kvm_vm_ioctl_set_pci_irq_mask(kvm, &assigned_dev);
+		break;
+	}
+	default:
+		r = -ENOTTY;
+		break;
+	}
+out:
+	return r;
+}
diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c
new file mode 100644
index 00000000000..c1e6ae989a4
--- /dev/null
+++ b/arch/x86/kvm/iommu.c
@@ -0,0 +1,358 @@
+/*
+ * Copyright (c) 2006, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Copyright (C) 2006-2008 Intel Corporation
+ * Copyright IBM Corporation, 2008
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ *
+ * Author: Allen M. Kay <allen.m.kay@intel.com>
+ * Author: Weidong Han <weidong.han@intel.com>
+ * Author: Ben-Ami Yassour <benami@il.ibm.com>
+ */
+
+#include <linux/list.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/stat.h>
+#include <linux/dmar.h>
+#include <linux/iommu.h>
+#include <linux/intel-iommu.h>
+
+static bool allow_unsafe_assigned_interrupts;
+module_param_named(allow_unsafe_assigned_interrupts,
+		   allow_unsafe_assigned_interrupts, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(allow_unsafe_assigned_interrupts,
+ "Enable device assignment on platforms without interrupt remapping support.");
+
+static int kvm_iommu_unmap_memslots(struct kvm *kvm);
+static void kvm_iommu_put_pages(struct kvm *kvm,
+				gfn_t base_gfn, unsigned long npages);
+
+static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
+			   unsigned long npages)
+{
+	gfn_t end_gfn;
+	pfn_t pfn;
+
+	pfn     = gfn_to_pfn_memslot(slot, gfn);
+	end_gfn = gfn + npages;
+	gfn    += 1;
+
+	if (is_error_noslot_pfn(pfn))
+		return pfn;
+
+	while (gfn < end_gfn)
+		gfn_to_pfn_memslot(slot, gfn++);
+
+	return pfn;
+}
+
+static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
+{
+	unsigned long i;
+
+	for (i = 0; i < npages; ++i)
+		kvm_release_pfn_clean(pfn + i);
+}
+
+int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+	gfn_t gfn, end_gfn;
+	pfn_t pfn;
+	int r = 0;
+	struct iommu_domain *domain = kvm->arch.iommu_domain;
+	int flags;
+
+	/* check if iommu exists and in use */
+	if (!domain)
+		return 0;
+
+	gfn     = slot->base_gfn;
+	end_gfn = gfn + slot->npages;
+
+	flags = IOMMU_READ;
+	if (!(slot->flags & KVM_MEM_READONLY))
+		flags |= IOMMU_WRITE;
+	if (!kvm->arch.iommu_noncoherent)
+		flags |= IOMMU_CACHE;
+
+
+	while (gfn < end_gfn) {
+		unsigned long page_size;
+
+		/* Check if already mapped */
+		if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) {
+			gfn += 1;
+			continue;
+		}
+
+		/* Get the page size we could use to map */
+		page_size = kvm_host_page_size(kvm, gfn);
+
+		/* Make sure the page_size does not exceed the memslot */
+		while ((gfn + (page_size >> PAGE_SHIFT)) > end_gfn)
+			page_size >>= 1;
+
+		/* Make sure gfn is aligned to the page size we want to map */
+		while ((gfn << PAGE_SHIFT) & (page_size - 1))
+			page_size >>= 1;
+
+		/* Make sure hva is aligned to the page size we want to map */
+		while (__gfn_to_hva_memslot(slot, gfn) & (page_size - 1))
+			page_size >>= 1;
+
+		/*
+		 * Pin all pages we are about to map in memory. This is
+		 * important because we unmap and unpin in 4kb steps later.
+		 */
+		pfn = kvm_pin_pages(slot, gfn, page_size >> PAGE_SHIFT);
+		if (is_error_noslot_pfn(pfn)) {
+			gfn += 1;
+			continue;
+		}
+
+		/* Map into IO address space */
+		r = iommu_map(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn),
+			      page_size, flags);
+		if (r) {
+			printk(KERN_ERR "kvm_iommu_map_address:"
+			       "iommu failed to map pfn=%llx\n", pfn);
+			kvm_unpin_pages(kvm, pfn, page_size >> PAGE_SHIFT);
+			goto unmap_pages;
+		}
+
+		gfn += page_size >> PAGE_SHIFT;
+
+
+	}
+
+	return 0;
+
+unmap_pages:
+	kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn);
+	return r;
+}
+
+static int kvm_iommu_map_memslots(struct kvm *kvm)
+{
+	int idx, r = 0;
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+
+	if (kvm->arch.iommu_noncoherent)
+		kvm_arch_register_noncoherent_dma(kvm);
+
+	idx = srcu_read_lock(&kvm->srcu);
+	slots = kvm_memslots(kvm);
+
+	kvm_for_each_memslot(memslot, slots) {
+		r = kvm_iommu_map_pages(kvm, memslot);
+		if (r)
+			break;
+	}
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return r;
+}
+
+int kvm_assign_device(struct kvm *kvm,
+		      struct kvm_assigned_dev_kernel *assigned_dev)
+{
+	struct pci_dev *pdev = NULL;
+	struct iommu_domain *domain = kvm->arch.iommu_domain;
+	int r;
+	bool noncoherent;
+
+	/* check if iommu exists and in use */
+	if (!domain)
+		return 0;
+
+	pdev = assigned_dev->dev;
+	if (pdev == NULL)
+		return -ENODEV;
+
+	r = iommu_attach_device(domain, &pdev->dev);
+	if (r) {
+		dev_err(&pdev->dev, "kvm assign device failed ret %d", r);
+		return r;
+	}
+
+	noncoherent = !iommu_capable(&pci_bus_type, IOMMU_CAP_CACHE_COHERENCY);
+
+	/* Check if need to update IOMMU page table for guest memory */
+	if (noncoherent != kvm->arch.iommu_noncoherent) {
+		kvm_iommu_unmap_memslots(kvm);
+		kvm->arch.iommu_noncoherent = noncoherent;
+		r = kvm_iommu_map_memslots(kvm);
+		if (r)
+			goto out_unmap;
+	}
+
+	pci_set_dev_assigned(pdev);
+
+	dev_info(&pdev->dev, "kvm assign device\n");
+
+	return 0;
+out_unmap:
+	kvm_iommu_unmap_memslots(kvm);
+	return r;
+}
+
+int kvm_deassign_device(struct kvm *kvm,
+			struct kvm_assigned_dev_kernel *assigned_dev)
+{
+	struct iommu_domain *domain = kvm->arch.iommu_domain;
+	struct pci_dev *pdev = NULL;
+
+	/* check if iommu exists and in use */
+	if (!domain)
+		return 0;
+
+	pdev = assigned_dev->dev;
+	if (pdev == NULL)
+		return -ENODEV;
+
+	iommu_detach_device(domain, &pdev->dev);
+
+	pci_clear_dev_assigned(pdev);
+
+	dev_info(&pdev->dev, "kvm deassign device\n");
+
+	return 0;
+}
+
+int kvm_iommu_map_guest(struct kvm *kvm)
+{
+	int r;
+
+	if (!iommu_present(&pci_bus_type)) {
+		printk(KERN_ERR "%s: iommu not found\n", __func__);
+		return -ENODEV;
+	}
+
+	mutex_lock(&kvm->slots_lock);
+
+	kvm->arch.iommu_domain = iommu_domain_alloc(&pci_bus_type);
+	if (!kvm->arch.iommu_domain) {
+		r = -ENOMEM;
+		goto out_unlock;
+	}
+
+	if (!allow_unsafe_assigned_interrupts &&
+	    !iommu_capable(&pci_bus_type, IOMMU_CAP_INTR_REMAP)) {
+		printk(KERN_WARNING "%s: No interrupt remapping support,"
+		       " disallowing device assignment."
+		       " Re-enble with \"allow_unsafe_assigned_interrupts=1\""
+		       " module option.\n", __func__);
+		iommu_domain_free(kvm->arch.iommu_domain);
+		kvm->arch.iommu_domain = NULL;
+		r = -EPERM;
+		goto out_unlock;
+	}
+
+	r = kvm_iommu_map_memslots(kvm);
+	if (r)
+		kvm_iommu_unmap_memslots(kvm);
+
+out_unlock:
+	mutex_unlock(&kvm->slots_lock);
+	return r;
+}
+
+static void kvm_iommu_put_pages(struct kvm *kvm,
+				gfn_t base_gfn, unsigned long npages)
+{
+	struct iommu_domain *domain;
+	gfn_t end_gfn, gfn;
+	pfn_t pfn;
+	u64 phys;
+
+	domain  = kvm->arch.iommu_domain;
+	end_gfn = base_gfn + npages;
+	gfn     = base_gfn;
+
+	/* check if iommu exists and in use */
+	if (!domain)
+		return;
+
+	while (gfn < end_gfn) {
+		unsigned long unmap_pages;
+		size_t size;
+
+		/* Get physical address */
+		phys = iommu_iova_to_phys(domain, gfn_to_gpa(gfn));
+
+		if (!phys) {
+			gfn++;
+			continue;
+		}
+
+		pfn  = phys >> PAGE_SHIFT;
+
+		/* Unmap address from IO address space */
+		size       = iommu_unmap(domain, gfn_to_gpa(gfn), PAGE_SIZE);
+		unmap_pages = 1ULL << get_order(size);
+
+		/* Unpin all pages we just unmapped to not leak any memory */
+		kvm_unpin_pages(kvm, pfn, unmap_pages);
+
+		gfn += unmap_pages;
+	}
+}
+
+void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+	kvm_iommu_put_pages(kvm, slot->base_gfn, slot->npages);
+}
+
+static int kvm_iommu_unmap_memslots(struct kvm *kvm)
+{
+	int idx;
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	slots = kvm_memslots(kvm);
+
+	kvm_for_each_memslot(memslot, slots)
+		kvm_iommu_unmap_pages(kvm, memslot);
+
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	if (kvm->arch.iommu_noncoherent)
+		kvm_arch_unregister_noncoherent_dma(kvm);
+
+	return 0;
+}
+
+int kvm_iommu_unmap_guest(struct kvm *kvm)
+{
+	struct iommu_domain *domain = kvm->arch.iommu_domain;
+
+	/* check if iommu exists and in use */
+	if (!domain)
+		return 0;
+
+	mutex_lock(&kvm->slots_lock);
+	kvm_iommu_unmap_memslots(kvm);
+	kvm->arch.iommu_domain = NULL;
+	kvm->arch.iommu_noncoherent = false;
+	mutex_unlock(&kvm->slots_lock);
+
+	iommu_domain_free(domain);
+	return 0;
+}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5337039427c..782e4eaf456 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4007,7 +4007,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	}
 
 	default:
-		;
+		r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg);
 	}
 out:
 	return r;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ded64cb3a08..aa56894ce83 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -764,8 +764,6 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
-int kvm_iommu_map_guest(struct kvm *kvm);
-int kvm_iommu_unmap_guest(struct kvm *kvm);
 int kvm_assign_device(struct kvm *kvm,
 		      struct kvm_assigned_dev_kernel *assigned_dev);
 int kvm_deassign_device(struct kvm *kvm,
@@ -781,11 +779,6 @@ static inline void kvm_iommu_unmap_pages(struct kvm *kvm,
 					 struct kvm_memory_slot *slot)
 {
 }
-
-static inline int kvm_iommu_unmap_guest(struct kvm *kvm)
-{
-	return 0;
-}
 #endif
 
 static inline void kvm_guest_enter(void)
@@ -1005,25 +998,6 @@ static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; }
 
 #endif
 
-#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
-
-long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
-				  unsigned long arg);
-
-void kvm_free_all_assigned_devices(struct kvm *kvm);
-
-#else
-
-static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
-						unsigned long arg)
-{
-	return -ENOTTY;
-}
-
-static inline void kvm_free_all_assigned_devices(struct kvm *kvm) {}
-
-#endif
-
 static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
 {
 	set_bit(req, &vcpu->requests);
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
deleted file mode 100644
index e05000e200d..00000000000
--- a/virt/kvm/assigned-dev.c
+++ /dev/null
@@ -1,1026 +0,0 @@
-/*
- * Kernel-based Virtual Machine - device assignment support
- *
- * Copyright (C) 2010 Red Hat, Inc. and/or its affiliates.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
- */
-
-#include <linux/kvm_host.h>
-#include <linux/kvm.h>
-#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
-#include <linux/errno.h>
-#include <linux/spinlock.h>
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-#include <linux/slab.h>
-#include <linux/namei.h>
-#include <linux/fs.h>
-#include "irq.h"
-
-static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
-						      int assigned_dev_id)
-{
-	struct list_head *ptr;
-	struct kvm_assigned_dev_kernel *match;
-
-	list_for_each(ptr, head) {
-		match = list_entry(ptr, struct kvm_assigned_dev_kernel, list);
-		if (match->assigned_dev_id == assigned_dev_id)
-			return match;
-	}
-	return NULL;
-}
-
-static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
-				    *assigned_dev, int irq)
-{
-	int i, index;
-	struct msix_entry *host_msix_entries;
-
-	host_msix_entries = assigned_dev->host_msix_entries;
-
-	index = -1;
-	for (i = 0; i < assigned_dev->entries_nr; i++)
-		if (irq == host_msix_entries[i].vector) {
-			index = i;
-			break;
-		}
-	if (index < 0)
-		printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n");
-
-	return index;
-}
-
-static irqreturn_t kvm_assigned_dev_intx(int irq, void *dev_id)
-{
-	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
-	int ret;
-
-	spin_lock(&assigned_dev->intx_lock);
-	if (pci_check_and_mask_intx(assigned_dev->dev)) {
-		assigned_dev->host_irq_disabled = true;
-		ret = IRQ_WAKE_THREAD;
-	} else
-		ret = IRQ_NONE;
-	spin_unlock(&assigned_dev->intx_lock);
-
-	return ret;
-}
-
-static void
-kvm_assigned_dev_raise_guest_irq(struct kvm_assigned_dev_kernel *assigned_dev,
-				 int vector)
-{
-	if (unlikely(assigned_dev->irq_requested_type &
-		     KVM_DEV_IRQ_GUEST_INTX)) {
-		spin_lock(&assigned_dev->intx_mask_lock);
-		if (!(assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX))
-			kvm_set_irq(assigned_dev->kvm,
-				    assigned_dev->irq_source_id, vector, 1,
-				    false);
-		spin_unlock(&assigned_dev->intx_mask_lock);
-	} else
-		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
-			    vector, 1, false);
-}
-
-static irqreturn_t kvm_assigned_dev_thread_intx(int irq, void *dev_id)
-{
-	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
-
-	if (!(assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
-		spin_lock_irq(&assigned_dev->intx_lock);
-		disable_irq_nosync(irq);
-		assigned_dev->host_irq_disabled = true;
-		spin_unlock_irq(&assigned_dev->intx_lock);
-	}
-
-	kvm_assigned_dev_raise_guest_irq(assigned_dev,
-					 assigned_dev->guest_irq);
-
-	return IRQ_HANDLED;
-}
-
-#ifdef __KVM_HAVE_MSI
-static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id)
-{
-	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
-	int ret = kvm_set_irq_inatomic(assigned_dev->kvm,
-				       assigned_dev->irq_source_id,
-				       assigned_dev->guest_irq, 1);
-	return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED;
-}
-
-static irqreturn_t kvm_assigned_dev_thread_msi(int irq, void *dev_id)
-{
-	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
-
-	kvm_assigned_dev_raise_guest_irq(assigned_dev,
-					 assigned_dev->guest_irq);
-
-	return IRQ_HANDLED;
-}
-#endif
-
-#ifdef __KVM_HAVE_MSIX
-static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id)
-{
-	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
-	int index = find_index_from_host_irq(assigned_dev, irq);
-	u32 vector;
-	int ret = 0;
-
-	if (index >= 0) {
-		vector = assigned_dev->guest_msix_entries[index].vector;
-		ret = kvm_set_irq_inatomic(assigned_dev->kvm,
-					   assigned_dev->irq_source_id,
-					   vector, 1);
-	}
-
-	return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED;
-}
-
-static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id)
-{
-	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
-	int index = find_index_from_host_irq(assigned_dev, irq);
-	u32 vector;
-
-	if (index >= 0) {
-		vector = assigned_dev->guest_msix_entries[index].vector;
-		kvm_assigned_dev_raise_guest_irq(assigned_dev, vector);
-	}
-
-	return IRQ_HANDLED;
-}
-#endif
-
-/* Ack the irq line for an assigned device */
-static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
-{
-	struct kvm_assigned_dev_kernel *dev =
-		container_of(kian, struct kvm_assigned_dev_kernel,
-			     ack_notifier);
-
-	kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0, false);
-
-	spin_lock(&dev->intx_mask_lock);
-
-	if (!(dev->flags & KVM_DEV_ASSIGN_MASK_INTX)) {
-		bool reassert = false;
-
-		spin_lock_irq(&dev->intx_lock);
-		/*
-		 * The guest IRQ may be shared so this ack can come from an
-		 * IRQ for another guest device.
-		 */
-		if (dev->host_irq_disabled) {
-			if (!(dev->flags & KVM_DEV_ASSIGN_PCI_2_3))
-				enable_irq(dev->host_irq);
-			else if (!pci_check_and_unmask_intx(dev->dev))
-				reassert = true;
-			dev->host_irq_disabled = reassert;
-		}
-		spin_unlock_irq(&dev->intx_lock);
-
-		if (reassert)
-			kvm_set_irq(dev->kvm, dev->irq_source_id,
-				    dev->guest_irq, 1, false);
-	}
-
-	spin_unlock(&dev->intx_mask_lock);
-}
-
-static void deassign_guest_irq(struct kvm *kvm,
-			       struct kvm_assigned_dev_kernel *assigned_dev)
-{
-	if (assigned_dev->ack_notifier.gsi != -1)
-		kvm_unregister_irq_ack_notifier(kvm,
-						&assigned_dev->ack_notifier);
-
-	kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
-		    assigned_dev->guest_irq, 0, false);
-
-	if (assigned_dev->irq_source_id != -1)
-		kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
-	assigned_dev->irq_source_id = -1;
-	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK);
-}
-
-/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */
-static void deassign_host_irq(struct kvm *kvm,
-			      struct kvm_assigned_dev_kernel *assigned_dev)
-{
-	/*
-	 * We disable irq here to prevent further events.
-	 *
-	 * Notice this maybe result in nested disable if the interrupt type is
-	 * INTx, but it's OK for we are going to free it.
-	 *
-	 * If this function is a part of VM destroy, please ensure that till
-	 * now, the kvm state is still legal for probably we also have to wait
-	 * on a currently running IRQ handler.
-	 */
-	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
-		int i;
-		for (i = 0; i < assigned_dev->entries_nr; i++)
-			disable_irq(assigned_dev->host_msix_entries[i].vector);
-
-		for (i = 0; i < assigned_dev->entries_nr; i++)
-			free_irq(assigned_dev->host_msix_entries[i].vector,
-				 assigned_dev);
-
-		assigned_dev->entries_nr = 0;
-		kfree(assigned_dev->host_msix_entries);
-		kfree(assigned_dev->guest_msix_entries);
-		pci_disable_msix(assigned_dev->dev);
-	} else {
-		/* Deal with MSI and INTx */
-		if ((assigned_dev->irq_requested_type &
-		     KVM_DEV_IRQ_HOST_INTX) &&
-		    (assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
-			spin_lock_irq(&assigned_dev->intx_lock);
-			pci_intx(assigned_dev->dev, false);
-			spin_unlock_irq(&assigned_dev->intx_lock);
-			synchronize_irq(assigned_dev->host_irq);
-		} else
-			disable_irq(assigned_dev->host_irq);
-
-		free_irq(assigned_dev->host_irq, assigned_dev);
-
-		if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI)
-			pci_disable_msi(assigned_dev->dev);
-	}
-
-	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK);
-}
-
-static int kvm_deassign_irq(struct kvm *kvm,
-			    struct kvm_assigned_dev_kernel *assigned_dev,
-			    unsigned long irq_requested_type)
-{
-	unsigned long guest_irq_type, host_irq_type;
-
-	if (!irqchip_in_kernel(kvm))
-		return -EINVAL;
-	/* no irq assignment to deassign */
-	if (!assigned_dev->irq_requested_type)
-		return -ENXIO;
-
-	host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK;
-	guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK;
-
-	if (host_irq_type)
-		deassign_host_irq(kvm, assigned_dev);
-	if (guest_irq_type)
-		deassign_guest_irq(kvm, assigned_dev);
-
-	return 0;
-}
-
-static void kvm_free_assigned_irq(struct kvm *kvm,
-				  struct kvm_assigned_dev_kernel *assigned_dev)
-{
-	kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type);
-}
-
-static void kvm_free_assigned_device(struct kvm *kvm,
-				     struct kvm_assigned_dev_kernel
-				     *assigned_dev)
-{
-	kvm_free_assigned_irq(kvm, assigned_dev);
-
-	pci_reset_function(assigned_dev->dev);
-	if (pci_load_and_free_saved_state(assigned_dev->dev,
-					  &assigned_dev->pci_saved_state))
-		printk(KERN_INFO "%s: Couldn't reload %s saved state\n",
-		       __func__, dev_name(&assigned_dev->dev->dev));
-	else
-		pci_restore_state(assigned_dev->dev);
-
-	pci_clear_dev_assigned(assigned_dev->dev);
-
-	pci_release_regions(assigned_dev->dev);
-	pci_disable_device(assigned_dev->dev);
-	pci_dev_put(assigned_dev->dev);
-
-	list_del(&assigned_dev->list);
-	kfree(assigned_dev);
-}
-
-void kvm_free_all_assigned_devices(struct kvm *kvm)
-{
-	struct list_head *ptr, *ptr2;
-	struct kvm_assigned_dev_kernel *assigned_dev;
-
-	list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) {
-		assigned_dev = list_entry(ptr,
-					  struct kvm_assigned_dev_kernel,
-					  list);
-
-		kvm_free_assigned_device(kvm, assigned_dev);
-	}
-}
-
-static int assigned_device_enable_host_intx(struct kvm *kvm,
-					    struct kvm_assigned_dev_kernel *dev)
-{
-	irq_handler_t irq_handler;
-	unsigned long flags;
-
-	dev->host_irq = dev->dev->irq;
-
-	/*
-	 * We can only share the IRQ line with other host devices if we are
-	 * able to disable the IRQ source at device-level - independently of
-	 * the guest driver. Otherwise host devices may suffer from unbounded
-	 * IRQ latencies when the guest keeps the line asserted.
-	 */
-	if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) {
-		irq_handler = kvm_assigned_dev_intx;
-		flags = IRQF_SHARED;
-	} else {
-		irq_handler = NULL;
-		flags = IRQF_ONESHOT;
-	}
-	if (request_threaded_irq(dev->host_irq, irq_handler,
-				 kvm_assigned_dev_thread_intx, flags,
-				 dev->irq_name, dev))
-		return -EIO;
-
-	if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) {
-		spin_lock_irq(&dev->intx_lock);
-		pci_intx(dev->dev, true);
-		spin_unlock_irq(&dev->intx_lock);
-	}
-	return 0;
-}
-
-#ifdef __KVM_HAVE_MSI
-static int assigned_device_enable_host_msi(struct kvm *kvm,
-					   struct kvm_assigned_dev_kernel *dev)
-{
-	int r;
-
-	if (!dev->dev->msi_enabled) {
-		r = pci_enable_msi(dev->dev);
-		if (r)
-			return r;
-	}
-
-	dev->host_irq = dev->dev->irq;
-	if (request_threaded_irq(dev->host_irq, kvm_assigned_dev_msi,
-				 kvm_assigned_dev_thread_msi, 0,
-				 dev->irq_name, dev)) {
-		pci_disable_msi(dev->dev);
-		return -EIO;
-	}
-
-	return 0;
-}
-#endif
-
-#ifdef __KVM_HAVE_MSIX
-static int assigned_device_enable_host_msix(struct kvm *kvm,
-					    struct kvm_assigned_dev_kernel *dev)
-{
-	int i, r = -EINVAL;
-
-	/* host_msix_entries and guest_msix_entries should have been
-	 * initialized */
-	if (dev->entries_nr == 0)
-		return r;
-
-	r = pci_enable_msix_exact(dev->dev,
-				  dev->host_msix_entries, dev->entries_nr);
-	if (r)
-		return r;
-
-	for (i = 0; i < dev->entries_nr; i++) {
-		r = request_threaded_irq(dev->host_msix_entries[i].vector,
-					 kvm_assigned_dev_msix,
-					 kvm_assigned_dev_thread_msix,
-					 0, dev->irq_name, dev);
-		if (r)
-			goto err;
-	}
-
-	return 0;
-err:
-	for (i -= 1; i >= 0; i--)
-		free_irq(dev->host_msix_entries[i].vector, dev);
-	pci_disable_msix(dev->dev);
-	return r;
-}
-
-#endif
-
-static int assigned_device_enable_guest_intx(struct kvm *kvm,
-				struct kvm_assigned_dev_kernel *dev,
-				struct kvm_assigned_irq *irq)
-{
-	dev->guest_irq = irq->guest_irq;
-	dev->ack_notifier.gsi = irq->guest_irq;
-	return 0;
-}
-
-#ifdef __KVM_HAVE_MSI
-static int assigned_device_enable_guest_msi(struct kvm *kvm,
-			struct kvm_assigned_dev_kernel *dev,
-			struct kvm_assigned_irq *irq)
-{
-	dev->guest_irq = irq->guest_irq;
-	dev->ack_notifier.gsi = -1;
-	return 0;
-}
-#endif
-
-#ifdef __KVM_HAVE_MSIX
-static int assigned_device_enable_guest_msix(struct kvm *kvm,
-			struct kvm_assigned_dev_kernel *dev,
-			struct kvm_assigned_irq *irq)
-{
-	dev->guest_irq = irq->guest_irq;
-	dev->ack_notifier.gsi = -1;
-	return 0;
-}
-#endif
-
-static int assign_host_irq(struct kvm *kvm,
-			   struct kvm_assigned_dev_kernel *dev,
-			   __u32 host_irq_type)
-{
-	int r = -EEXIST;
-
-	if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK)
-		return r;
-
-	snprintf(dev->irq_name, sizeof(dev->irq_name), "kvm:%s",
-		 pci_name(dev->dev));
-
-	switch (host_irq_type) {
-	case KVM_DEV_IRQ_HOST_INTX:
-		r = assigned_device_enable_host_intx(kvm, dev);
-		break;
-#ifdef __KVM_HAVE_MSI
-	case KVM_DEV_IRQ_HOST_MSI:
-		r = assigned_device_enable_host_msi(kvm, dev);
-		break;
-#endif
-#ifdef __KVM_HAVE_MSIX
-	case KVM_DEV_IRQ_HOST_MSIX:
-		r = assigned_device_enable_host_msix(kvm, dev);
-		break;
-#endif
-	default:
-		r = -EINVAL;
-	}
-	dev->host_irq_disabled = false;
-
-	if (!r)
-		dev->irq_requested_type |= host_irq_type;
-
-	return r;
-}
-
-static int assign_guest_irq(struct kvm *kvm,
-			    struct kvm_assigned_dev_kernel *dev,
-			    struct kvm_assigned_irq *irq,
-			    unsigned long guest_irq_type)
-{
-	int id;
-	int r = -EEXIST;
-
-	if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK)
-		return r;
-
-	id = kvm_request_irq_source_id(kvm);
-	if (id < 0)
-		return id;
-
-	dev->irq_source_id = id;
-
-	switch (guest_irq_type) {
-	case KVM_DEV_IRQ_GUEST_INTX:
-		r = assigned_device_enable_guest_intx(kvm, dev, irq);
-		break;
-#ifdef __KVM_HAVE_MSI
-	case KVM_DEV_IRQ_GUEST_MSI:
-		r = assigned_device_enable_guest_msi(kvm, dev, irq);
-		break;
-#endif
-#ifdef __KVM_HAVE_MSIX
-	case KVM_DEV_IRQ_GUEST_MSIX:
-		r = assigned_device_enable_guest_msix(kvm, dev, irq);
-		break;
-#endif
-	default:
-		r = -EINVAL;
-	}
-
-	if (!r) {
-		dev->irq_requested_type |= guest_irq_type;
-		if (dev->ack_notifier.gsi != -1)
-			kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier);
-	} else {
-		kvm_free_irq_source_id(kvm, dev->irq_source_id);
-		dev->irq_source_id = -1;
-	}
-
-	return r;
-}
-
-/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */
-static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
-				   struct kvm_assigned_irq *assigned_irq)
-{
-	int r = -EINVAL;
-	struct kvm_assigned_dev_kernel *match;
-	unsigned long host_irq_type, guest_irq_type;
-
-	if (!irqchip_in_kernel(kvm))
-		return r;
-
-	mutex_lock(&kvm->lock);
-	r = -ENODEV;
-	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
-				      assigned_irq->assigned_dev_id);
-	if (!match)
-		goto out;
-
-	host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK);
-	guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK);
-
-	r = -EINVAL;
-	/* can only assign one type at a time */
-	if (hweight_long(host_irq_type) > 1)
-		goto out;
-	if (hweight_long(guest_irq_type) > 1)
-		goto out;
-	if (host_irq_type == 0 && guest_irq_type == 0)
-		goto out;
-
-	r = 0;
-	if (host_irq_type)
-		r = assign_host_irq(kvm, match, host_irq_type);
-	if (r)
-		goto out;
-
-	if (guest_irq_type)
-		r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type);
-out:
-	mutex_unlock(&kvm->lock);
-	return r;
-}
-
-static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm,
-					 struct kvm_assigned_irq
-					 *assigned_irq)
-{
-	int r = -ENODEV;
-	struct kvm_assigned_dev_kernel *match;
-	unsigned long irq_type;
-
-	mutex_lock(&kvm->lock);
-
-	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
-				      assigned_irq->assigned_dev_id);
-	if (!match)
-		goto out;
-
-	irq_type = assigned_irq->flags & (KVM_DEV_IRQ_HOST_MASK |
-					  KVM_DEV_IRQ_GUEST_MASK);
-	r = kvm_deassign_irq(kvm, match, irq_type);
-out:
-	mutex_unlock(&kvm->lock);
-	return r;
-}
-
-/*
- * We want to test whether the caller has been granted permissions to
- * use this device.  To be able to configure and control the device,
- * the user needs access to PCI configuration space and BAR resources.
- * These are accessed through PCI sysfs.  PCI config space is often
- * passed to the process calling this ioctl via file descriptor, so we
- * can't rely on access to that file.  We can check for permissions
- * on each of the BAR resource files, which is a pretty clear
- * indicator that the user has been granted access to the device.
- */
-static int probe_sysfs_permissions(struct pci_dev *dev)
-{
-#ifdef CONFIG_SYSFS
-	int i;
-	bool bar_found = false;
-
-	for (i = PCI_STD_RESOURCES; i <= PCI_STD_RESOURCE_END; i++) {
-		char *kpath, *syspath;
-		struct path path;
-		struct inode *inode;
-		int r;
-
-		if (!pci_resource_len(dev, i))
-			continue;
-
-		kpath = kobject_get_path(&dev->dev.kobj, GFP_KERNEL);
-		if (!kpath)
-			return -ENOMEM;
-
-		/* Per sysfs-rules, sysfs is always at /sys */
-		syspath = kasprintf(GFP_KERNEL, "/sys%s/resource%d", kpath, i);
-		kfree(kpath);
-		if (!syspath)
-			return -ENOMEM;
-
-		r = kern_path(syspath, LOOKUP_FOLLOW, &path);
-		kfree(syspath);
-		if (r)
-			return r;
-
-		inode = path.dentry->d_inode;
-
-		r = inode_permission(inode, MAY_READ | MAY_WRITE | MAY_ACCESS);
-		path_put(&path);
-		if (r)
-			return r;
-
-		bar_found = true;
-	}
-
-	/* If no resources, probably something special */
-	if (!bar_found)
-		return -EPERM;
-
-	return 0;
-#else
-	return -EINVAL; /* No way to control the device without sysfs */
-#endif
-}
-
-static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
-				      struct kvm_assigned_pci_dev *assigned_dev)
-{
-	int r = 0, idx;
-	struct kvm_assigned_dev_kernel *match;
-	struct pci_dev *dev;
-
-	if (!(assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU))
-		return -EINVAL;
-
-	mutex_lock(&kvm->lock);
-	idx = srcu_read_lock(&kvm->srcu);
-
-	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
-				      assigned_dev->assigned_dev_id);
-	if (match) {
-		/* device already assigned */
-		r = -EEXIST;
-		goto out;
-	}
-
-	match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL);
-	if (match == NULL) {
-		printk(KERN_INFO "%s: Couldn't allocate memory\n",
-		       __func__);
-		r = -ENOMEM;
-		goto out;
-	}
-	dev = pci_get_domain_bus_and_slot(assigned_dev->segnr,
-				   assigned_dev->busnr,
-				   assigned_dev->devfn);
-	if (!dev) {
-		printk(KERN_INFO "%s: host device not found\n", __func__);
-		r = -EINVAL;
-		goto out_free;
-	}
-
-	/* Don't allow bridges to be assigned */
-	if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL) {
-		r = -EPERM;
-		goto out_put;
-	}
-
-	r = probe_sysfs_permissions(dev);
-	if (r)
-		goto out_put;
-
-	if (pci_enable_device(dev)) {
-		printk(KERN_INFO "%s: Could not enable PCI device\n", __func__);
-		r = -EBUSY;
-		goto out_put;
-	}
-	r = pci_request_regions(dev, "kvm_assigned_device");
-	if (r) {
-		printk(KERN_INFO "%s: Could not get access to device regions\n",
-		       __func__);
-		goto out_disable;
-	}
-
-	pci_reset_function(dev);
-	pci_save_state(dev);
-	match->pci_saved_state = pci_store_saved_state(dev);
-	if (!match->pci_saved_state)
-		printk(KERN_DEBUG "%s: Couldn't store %s saved state\n",
-		       __func__, dev_name(&dev->dev));
-
-	if (!pci_intx_mask_supported(dev))
-		assigned_dev->flags &= ~KVM_DEV_ASSIGN_PCI_2_3;
-
-	match->assigned_dev_id = assigned_dev->assigned_dev_id;
-	match->host_segnr = assigned_dev->segnr;
-	match->host_busnr = assigned_dev->busnr;
-	match->host_devfn = assigned_dev->devfn;
-	match->flags = assigned_dev->flags;
-	match->dev = dev;
-	spin_lock_init(&match->intx_lock);
-	spin_lock_init(&match->intx_mask_lock);
-	match->irq_source_id = -1;
-	match->kvm = kvm;
-	match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
-
-	list_add(&match->list, &kvm->arch.assigned_dev_head);
-
-	if (!kvm->arch.iommu_domain) {
-		r = kvm_iommu_map_guest(kvm);
-		if (r)
-			goto out_list_del;
-	}
-	r = kvm_assign_device(kvm, match);
-	if (r)
-		goto out_list_del;
-
-out:
-	srcu_read_unlock(&kvm->srcu, idx);
-	mutex_unlock(&kvm->lock);
-	return r;
-out_list_del:
-	if (pci_load_and_free_saved_state(dev, &match->pci_saved_state))
-		printk(KERN_INFO "%s: Couldn't reload %s saved state\n",
-		       __func__, dev_name(&dev->dev));
-	list_del(&match->list);
-	pci_release_regions(dev);
-out_disable:
-	pci_disable_device(dev);
-out_put:
-	pci_dev_put(dev);
-out_free:
-	kfree(match);
-	srcu_read_unlock(&kvm->srcu, idx);
-	mutex_unlock(&kvm->lock);
-	return r;
-}
-
-static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
-		struct kvm_assigned_pci_dev *assigned_dev)
-{
-	int r = 0;
-	struct kvm_assigned_dev_kernel *match;
-
-	mutex_lock(&kvm->lock);
-
-	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
-				      assigned_dev->assigned_dev_id);
-	if (!match) {
-		printk(KERN_INFO "%s: device hasn't been assigned before, "
-		  "so cannot be deassigned\n", __func__);
-		r = -EINVAL;
-		goto out;
-	}
-
-	kvm_deassign_device(kvm, match);
-
-	kvm_free_assigned_device(kvm, match);
-
-out:
-	mutex_unlock(&kvm->lock);
-	return r;
-}
-
-
-#ifdef __KVM_HAVE_MSIX
-static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
-				    struct kvm_assigned_msix_nr *entry_nr)
-{
-	int r = 0;
-	struct kvm_assigned_dev_kernel *adev;
-
-	mutex_lock(&kvm->lock);
-
-	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
-				      entry_nr->assigned_dev_id);
-	if (!adev) {
-		r = -EINVAL;
-		goto msix_nr_out;
-	}
-
-	if (adev->entries_nr == 0) {
-		adev->entries_nr = entry_nr->entry_nr;
-		if (adev->entries_nr == 0 ||
-		    adev->entries_nr > KVM_MAX_MSIX_PER_DEV) {
-			r = -EINVAL;
-			goto msix_nr_out;
-		}
-
-		adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) *
-						entry_nr->entry_nr,
-						GFP_KERNEL);
-		if (!adev->host_msix_entries) {
-			r = -ENOMEM;
-			goto msix_nr_out;
-		}
-		adev->guest_msix_entries =
-			kzalloc(sizeof(struct msix_entry) * entry_nr->entry_nr,
-				GFP_KERNEL);
-		if (!adev->guest_msix_entries) {
-			kfree(adev->host_msix_entries);
-			r = -ENOMEM;
-			goto msix_nr_out;
-		}
-	} else /* Not allowed set MSI-X number twice */
-		r = -EINVAL;
-msix_nr_out:
-	mutex_unlock(&kvm->lock);
-	return r;
-}
-
-static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm,
-				       struct kvm_assigned_msix_entry *entry)
-{
-	int r = 0, i;
-	struct kvm_assigned_dev_kernel *adev;
-
-	mutex_lock(&kvm->lock);
-
-	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
-				      entry->assigned_dev_id);
-
-	if (!adev) {
-		r = -EINVAL;
-		goto msix_entry_out;
-	}
-
-	for (i = 0; i < adev->entries_nr; i++)
-		if (adev->guest_msix_entries[i].vector == 0 ||
-		    adev->guest_msix_entries[i].entry == entry->entry) {
-			adev->guest_msix_entries[i].entry = entry->entry;
-			adev->guest_msix_entries[i].vector = entry->gsi;
-			adev->host_msix_entries[i].entry = entry->entry;
-			break;
-		}
-	if (i == adev->entries_nr) {
-		r = -ENOSPC;
-		goto msix_entry_out;
-	}
-
-msix_entry_out:
-	mutex_unlock(&kvm->lock);
-
-	return r;
-}
-#endif
-
-static int kvm_vm_ioctl_set_pci_irq_mask(struct kvm *kvm,
-		struct kvm_assigned_pci_dev *assigned_dev)
-{
-	int r = 0;
-	struct kvm_assigned_dev_kernel *match;
-
-	mutex_lock(&kvm->lock);
-
-	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
-				      assigned_dev->assigned_dev_id);
-	if (!match) {
-		r = -ENODEV;
-		goto out;
-	}
-
-	spin_lock(&match->intx_mask_lock);
-
-	match->flags &= ~KVM_DEV_ASSIGN_MASK_INTX;
-	match->flags |= assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX;
-
-	if (match->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) {
-		if (assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX) {
-			kvm_set_irq(match->kvm, match->irq_source_id,
-				    match->guest_irq, 0, false);
-			/*
-			 * Masking at hardware-level is performed on demand,
-			 * i.e. when an IRQ actually arrives at the host.
-			 */
-		} else if (!(assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
-			/*
-			 * Unmask the IRQ line if required. Unmasking at
-			 * device level will be performed by user space.
-			 */
-			spin_lock_irq(&match->intx_lock);
-			if (match->host_irq_disabled) {
-				enable_irq(match->host_irq);
-				match->host_irq_disabled = false;
-			}
-			spin_unlock_irq(&match->intx_lock);
-		}
-	}
-
-	spin_unlock(&match->intx_mask_lock);
-
-out:
-	mutex_unlock(&kvm->lock);
-	return r;
-}
-
-long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
-				  unsigned long arg)
-{
-	void __user *argp = (void __user *)arg;
-	int r;
-
-	switch (ioctl) {
-	case KVM_ASSIGN_PCI_DEVICE: {
-		struct kvm_assigned_pci_dev assigned_dev;
-
-		r = -EFAULT;
-		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
-			goto out;
-		r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev);
-		if (r)
-			goto out;
-		break;
-	}
-	case KVM_ASSIGN_IRQ: {
-		r = -EOPNOTSUPP;
-		break;
-	}
-	case KVM_ASSIGN_DEV_IRQ: {
-		struct kvm_assigned_irq assigned_irq;
-
-		r = -EFAULT;
-		if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
-			goto out;
-		r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq);
-		if (r)
-			goto out;
-		break;
-	}
-	case KVM_DEASSIGN_DEV_IRQ: {
-		struct kvm_assigned_irq assigned_irq;
-
-		r = -EFAULT;
-		if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
-			goto out;
-		r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq);
-		if (r)
-			goto out;
-		break;
-	}
-	case KVM_DEASSIGN_PCI_DEVICE: {
-		struct kvm_assigned_pci_dev assigned_dev;
-
-		r = -EFAULT;
-		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
-			goto out;
-		r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev);
-		if (r)
-			goto out;
-		break;
-	}
-#ifdef __KVM_HAVE_MSIX
-	case KVM_ASSIGN_SET_MSIX_NR: {
-		struct kvm_assigned_msix_nr entry_nr;
-		r = -EFAULT;
-		if (copy_from_user(&entry_nr, argp, sizeof entry_nr))
-			goto out;
-		r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr);
-		if (r)
-			goto out;
-		break;
-	}
-	case KVM_ASSIGN_SET_MSIX_ENTRY: {
-		struct kvm_assigned_msix_entry entry;
-		r = -EFAULT;
-		if (copy_from_user(&entry, argp, sizeof entry))
-			goto out;
-		r = kvm_vm_ioctl_set_msix_entry(kvm, &entry);
-		if (r)
-			goto out;
-		break;
-	}
-#endif
-	case KVM_ASSIGN_SET_INTX_MASK: {
-		struct kvm_assigned_pci_dev assigned_dev;
-
-		r = -EFAULT;
-		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
-			goto out;
-		r = kvm_vm_ioctl_set_pci_irq_mask(kvm, &assigned_dev);
-		break;
-	}
-	default:
-		r = -ENOTTY;
-		break;
-	}
-out:
-	return r;
-}
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
deleted file mode 100644
index c1e6ae989a4..00000000000
--- a/virt/kvm/iommu.c
+++ /dev/null
@@ -1,358 +0,0 @@
-/*
- * Copyright (c) 2006, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
- *
- * Copyright (C) 2006-2008 Intel Corporation
- * Copyright IBM Corporation, 2008
- * Copyright 2010 Red Hat, Inc. and/or its affiliates.
- *
- * Author: Allen M. Kay <allen.m.kay@intel.com>
- * Author: Weidong Han <weidong.han@intel.com>
- * Author: Ben-Ami Yassour <benami@il.ibm.com>
- */
-
-#include <linux/list.h>
-#include <linux/kvm_host.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/stat.h>
-#include <linux/dmar.h>
-#include <linux/iommu.h>
-#include <linux/intel-iommu.h>
-
-static bool allow_unsafe_assigned_interrupts;
-module_param_named(allow_unsafe_assigned_interrupts,
-		   allow_unsafe_assigned_interrupts, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(allow_unsafe_assigned_interrupts,
- "Enable device assignment on platforms without interrupt remapping support.");
-
-static int kvm_iommu_unmap_memslots(struct kvm *kvm);
-static void kvm_iommu_put_pages(struct kvm *kvm,
-				gfn_t base_gfn, unsigned long npages);
-
-static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
-			   unsigned long npages)
-{
-	gfn_t end_gfn;
-	pfn_t pfn;
-
-	pfn     = gfn_to_pfn_memslot(slot, gfn);
-	end_gfn = gfn + npages;
-	gfn    += 1;
-
-	if (is_error_noslot_pfn(pfn))
-		return pfn;
-
-	while (gfn < end_gfn)
-		gfn_to_pfn_memslot(slot, gfn++);
-
-	return pfn;
-}
-
-static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
-{
-	unsigned long i;
-
-	for (i = 0; i < npages; ++i)
-		kvm_release_pfn_clean(pfn + i);
-}
-
-int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
-{
-	gfn_t gfn, end_gfn;
-	pfn_t pfn;
-	int r = 0;
-	struct iommu_domain *domain = kvm->arch.iommu_domain;
-	int flags;
-
-	/* check if iommu exists and in use */
-	if (!domain)
-		return 0;
-
-	gfn     = slot->base_gfn;
-	end_gfn = gfn + slot->npages;
-
-	flags = IOMMU_READ;
-	if (!(slot->flags & KVM_MEM_READONLY))
-		flags |= IOMMU_WRITE;
-	if (!kvm->arch.iommu_noncoherent)
-		flags |= IOMMU_CACHE;
-
-
-	while (gfn < end_gfn) {
-		unsigned long page_size;
-
-		/* Check if already mapped */
-		if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) {
-			gfn += 1;
-			continue;
-		}
-
-		/* Get the page size we could use to map */
-		page_size = kvm_host_page_size(kvm, gfn);
-
-		/* Make sure the page_size does not exceed the memslot */
-		while ((gfn + (page_size >> PAGE_SHIFT)) > end_gfn)
-			page_size >>= 1;
-
-		/* Make sure gfn is aligned to the page size we want to map */
-		while ((gfn << PAGE_SHIFT) & (page_size - 1))
-			page_size >>= 1;
-
-		/* Make sure hva is aligned to the page size we want to map */
-		while (__gfn_to_hva_memslot(slot, gfn) & (page_size - 1))
-			page_size >>= 1;
-
-		/*
-		 * Pin all pages we are about to map in memory. This is
-		 * important because we unmap and unpin in 4kb steps later.
-		 */
-		pfn = kvm_pin_pages(slot, gfn, page_size >> PAGE_SHIFT);
-		if (is_error_noslot_pfn(pfn)) {
-			gfn += 1;
-			continue;
-		}
-
-		/* Map into IO address space */
-		r = iommu_map(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn),
-			      page_size, flags);
-		if (r) {
-			printk(KERN_ERR "kvm_iommu_map_address:"
-			       "iommu failed to map pfn=%llx\n", pfn);
-			kvm_unpin_pages(kvm, pfn, page_size >> PAGE_SHIFT);
-			goto unmap_pages;
-		}
-
-		gfn += page_size >> PAGE_SHIFT;
-
-
-	}
-
-	return 0;
-
-unmap_pages:
-	kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn);
-	return r;
-}
-
-static int kvm_iommu_map_memslots(struct kvm *kvm)
-{
-	int idx, r = 0;
-	struct kvm_memslots *slots;
-	struct kvm_memory_slot *memslot;
-
-	if (kvm->arch.iommu_noncoherent)
-		kvm_arch_register_noncoherent_dma(kvm);
-
-	idx = srcu_read_lock(&kvm->srcu);
-	slots = kvm_memslots(kvm);
-
-	kvm_for_each_memslot(memslot, slots) {
-		r = kvm_iommu_map_pages(kvm, memslot);
-		if (r)
-			break;
-	}
-	srcu_read_unlock(&kvm->srcu, idx);
-
-	return r;
-}
-
-int kvm_assign_device(struct kvm *kvm,
-		      struct kvm_assigned_dev_kernel *assigned_dev)
-{
-	struct pci_dev *pdev = NULL;
-	struct iommu_domain *domain = kvm->arch.iommu_domain;
-	int r;
-	bool noncoherent;
-
-	/* check if iommu exists and in use */
-	if (!domain)
-		return 0;
-
-	pdev = assigned_dev->dev;
-	if (pdev == NULL)
-		return -ENODEV;
-
-	r = iommu_attach_device(domain, &pdev->dev);
-	if (r) {
-		dev_err(&pdev->dev, "kvm assign device failed ret %d", r);
-		return r;
-	}
-
-	noncoherent = !iommu_capable(&pci_bus_type, IOMMU_CAP_CACHE_COHERENCY);
-
-	/* Check if need to update IOMMU page table for guest memory */
-	if (noncoherent != kvm->arch.iommu_noncoherent) {
-		kvm_iommu_unmap_memslots(kvm);
-		kvm->arch.iommu_noncoherent = noncoherent;
-		r = kvm_iommu_map_memslots(kvm);
-		if (r)
-			goto out_unmap;
-	}
-
-	pci_set_dev_assigned(pdev);
-
-	dev_info(&pdev->dev, "kvm assign device\n");
-
-	return 0;
-out_unmap:
-	kvm_iommu_unmap_memslots(kvm);
-	return r;
-}
-
-int kvm_deassign_device(struct kvm *kvm,
-			struct kvm_assigned_dev_kernel *assigned_dev)
-{
-	struct iommu_domain *domain = kvm->arch.iommu_domain;
-	struct pci_dev *pdev = NULL;
-
-	/* check if iommu exists and in use */
-	if (!domain)
-		return 0;
-
-	pdev = assigned_dev->dev;
-	if (pdev == NULL)
-		return -ENODEV;
-
-	iommu_detach_device(domain, &pdev->dev);
-
-	pci_clear_dev_assigned(pdev);
-
-	dev_info(&pdev->dev, "kvm deassign device\n");
-
-	return 0;
-}
-
-int kvm_iommu_map_guest(struct kvm *kvm)
-{
-	int r;
-
-	if (!iommu_present(&pci_bus_type)) {
-		printk(KERN_ERR "%s: iommu not found\n", __func__);
-		return -ENODEV;
-	}
-
-	mutex_lock(&kvm->slots_lock);
-
-	kvm->arch.iommu_domain = iommu_domain_alloc(&pci_bus_type);
-	if (!kvm->arch.iommu_domain) {
-		r = -ENOMEM;
-		goto out_unlock;
-	}
-
-	if (!allow_unsafe_assigned_interrupts &&
-	    !iommu_capable(&pci_bus_type, IOMMU_CAP_INTR_REMAP)) {
-		printk(KERN_WARNING "%s: No interrupt remapping support,"
-		       " disallowing device assignment."
-		       " Re-enble with \"allow_unsafe_assigned_interrupts=1\""
-		       " module option.\n", __func__);
-		iommu_domain_free(kvm->arch.iommu_domain);
-		kvm->arch.iommu_domain = NULL;
-		r = -EPERM;
-		goto out_unlock;
-	}
-
-	r = kvm_iommu_map_memslots(kvm);
-	if (r)
-		kvm_iommu_unmap_memslots(kvm);
-
-out_unlock:
-	mutex_unlock(&kvm->slots_lock);
-	return r;
-}
-
-static void kvm_iommu_put_pages(struct kvm *kvm,
-				gfn_t base_gfn, unsigned long npages)
-{
-	struct iommu_domain *domain;
-	gfn_t end_gfn, gfn;
-	pfn_t pfn;
-	u64 phys;
-
-	domain  = kvm->arch.iommu_domain;
-	end_gfn = base_gfn + npages;
-	gfn     = base_gfn;
-
-	/* check if iommu exists and in use */
-	if (!domain)
-		return;
-
-	while (gfn < end_gfn) {
-		unsigned long unmap_pages;
-		size_t size;
-
-		/* Get physical address */
-		phys = iommu_iova_to_phys(domain, gfn_to_gpa(gfn));
-
-		if (!phys) {
-			gfn++;
-			continue;
-		}
-
-		pfn  = phys >> PAGE_SHIFT;
-
-		/* Unmap address from IO address space */
-		size       = iommu_unmap(domain, gfn_to_gpa(gfn), PAGE_SIZE);
-		unmap_pages = 1ULL << get_order(size);
-
-		/* Unpin all pages we just unmapped to not leak any memory */
-		kvm_unpin_pages(kvm, pfn, unmap_pages);
-
-		gfn += unmap_pages;
-	}
-}
-
-void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
-{
-	kvm_iommu_put_pages(kvm, slot->base_gfn, slot->npages);
-}
-
-static int kvm_iommu_unmap_memslots(struct kvm *kvm)
-{
-	int idx;
-	struct kvm_memslots *slots;
-	struct kvm_memory_slot *memslot;
-
-	idx = srcu_read_lock(&kvm->srcu);
-	slots = kvm_memslots(kvm);
-
-	kvm_for_each_memslot(memslot, slots)
-		kvm_iommu_unmap_pages(kvm, memslot);
-
-	srcu_read_unlock(&kvm->srcu, idx);
-
-	if (kvm->arch.iommu_noncoherent)
-		kvm_arch_unregister_noncoherent_dma(kvm);
-
-	return 0;
-}
-
-int kvm_iommu_unmap_guest(struct kvm *kvm)
-{
-	struct iommu_domain *domain = kvm->arch.iommu_domain;
-
-	/* check if iommu exists and in use */
-	if (!domain)
-		return 0;
-
-	mutex_lock(&kvm->slots_lock);
-	kvm_iommu_unmap_memslots(kvm);
-	kvm->arch.iommu_domain = NULL;
-	kvm->arch.iommu_noncoherent = false;
-	mutex_unlock(&kvm->slots_lock);
-
-	iommu_domain_free(domain);
-	return 0;
-}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 3be43424818..5b4533079ea 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2582,8 +2582,6 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
-		if (r == -ENOTTY)
-			r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg);
 	}
 out:
 	return r;
-- 
cgit v1.2.3-70-g09d2


From 40e7fcb19293cbdff02c74cb0668413480f82ea1 Mon Sep 17 00:00:00 2001
From: Lan Tianyu <tianyu.lan@intel.com>
Date: Sun, 23 Nov 2014 21:22:54 +0800
Subject: ACPI: Add _DEP support to fix battery issue on Asus T100TA

ACPI 5.0 introduces _DEP (Operation Region Dependencies) to designate
device objects that OSPM should assign a higher priority in start
ordering due to future operation region accesses.

On Asus T100TA, ACPI battery info are read from a I2C slave device via
I2C operation region. Before I2C operation region handler is installed,
battery _STA always returns 0. There is a _DEP method of designating
start order under battery device node.

This patch is to implement _DEP feature to fix battery issue on the
Asus T100TA.  Introducing acpi_dep_list and adding dep_unmet count
in struct acpi_device. During ACPI namespace scan, create struct
acpi_dep_data for a valid pair of master (device pointed to by _DEP)/
slave(device with _DEP), record master's and slave's ACPI handle in
it and put it into acpi_dep_list. The dep_unmet count will increase
by one if there is a device under its _DEP. Driver's probe() should
return EPROBE_DEFER when find dep_unmet is larger than 0. When I2C
operation region handler is installed, remove all struct acpi_dep_data
on the acpi_dep_list whose master is pointed to I2C host controller
and decrease slave's dep_unmet. When dep_unmet decreases to 0, all
_DEP conditions are met and then do acpi_bus_attach() for the device
in order to resolve battery _STA issue on the Asus T100TA.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=69011
Tested-by: Jan-Michael Brummer <jan.brummer@tabos.org>
Tested-by: Adam Williamson <adamw@happyassassin.net>
Tested-by: Michael Shigorin <shigorin@gmail.com>
Acked-by: Wolfram Sang <wsa@the-dreams.de>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Lan Tianyu <tianyu.lan@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/battery.c  |  4 +++
 drivers/acpi/scan.c     | 85 +++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/i2c/i2c-core.c  |  1 +
 include/acpi/acpi_bus.h |  1 +
 include/linux/acpi.h    |  1 +
 5 files changed, 92 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 8ec8a89a20a..d98ba435581 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -1180,6 +1180,10 @@ static int acpi_battery_add(struct acpi_device *device)
 
 	if (!device)
 		return -EINVAL;
+
+	if (device->dep_unmet)
+		return -EPROBE_DEFER;
+
 	battery = kzalloc(sizeof(struct acpi_battery), GFP_KERNEL);
 	if (!battery)
 		return -ENOMEM;
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 0476e90b209..00189ad63c8 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -36,6 +36,8 @@ bool acpi_force_hot_remove;
 
 static const char *dummy_hid = "device";
 
+static LIST_HEAD(acpi_dep_list);
+static DEFINE_MUTEX(acpi_dep_list_lock);
 static LIST_HEAD(acpi_bus_id_list);
 static DEFINE_MUTEX(acpi_scan_lock);
 static LIST_HEAD(acpi_scan_handlers_list);
@@ -43,6 +45,12 @@ DEFINE_MUTEX(acpi_device_lock);
 LIST_HEAD(acpi_wakeup_device_list);
 static DEFINE_MUTEX(acpi_hp_context_lock);
 
+struct acpi_dep_data {
+	struct list_head node;
+	acpi_handle master;
+	acpi_handle slave;
+};
+
 struct acpi_device_bus_id{
 	char bus_id[15];
 	unsigned int instance_no;
@@ -2086,6 +2094,59 @@ static void acpi_scan_init_hotplug(struct acpi_device *adev)
 	}
 }
 
+static void acpi_device_dep_initialize(struct acpi_device *adev)
+{
+	struct acpi_dep_data *dep;
+	struct acpi_handle_list dep_devices;
+	acpi_status status;
+	int i;
+
+	if (!acpi_has_method(adev->handle, "_DEP"))
+		return;
+
+	status = acpi_evaluate_reference(adev->handle, "_DEP", NULL,
+					&dep_devices);
+	if (ACPI_FAILURE(status)) {
+		dev_err(&adev->dev, "Failed to evaluate _DEP.\n");
+		return;
+	}
+
+	for (i = 0; i < dep_devices.count; i++) {
+		struct acpi_device_info *info;
+		int skip;
+
+		status = acpi_get_object_info(dep_devices.handles[i], &info);
+		if (ACPI_FAILURE(status)) {
+			dev_err(&adev->dev, "Error reading device info\n");
+			continue;
+		}
+
+		/*
+		 * Skip the dependency of Windows System Power
+		 * Management Controller
+		 */
+		skip = info->valid & ACPI_VALID_HID &&
+			!strcmp(info->hardware_id.string, "INT3396");
+
+		kfree(info);
+
+		if (skip)
+			continue;
+
+		dep = kzalloc(sizeof(struct acpi_dep_data), GFP_KERNEL);
+		if (!dep)
+			return;
+
+		dep->master = dep_devices.handles[i];
+		dep->slave  = adev->handle;
+		adev->dep_unmet++;
+
+		mutex_lock(&acpi_dep_list_lock);
+		list_add_tail(&dep->node , &acpi_dep_list);
+		mutex_unlock(&acpi_dep_list_lock);
+	}
+}
+
 static acpi_status acpi_bus_check_add(acpi_handle handle, u32 lvl_not_used,
 				      void *not_used, void **return_value)
 {
@@ -2112,6 +2173,7 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, u32 lvl_not_used,
 		return AE_CTRL_DEPTH;
 
 	acpi_scan_init_hotplug(device);
+	acpi_device_dep_initialize(device);
 
  out:
 	if (!*return_value)
@@ -2232,6 +2294,29 @@ static void acpi_bus_attach(struct acpi_device *device)
 		device->handler->hotplug.notify_online(device);
 }
 
+void acpi_walk_dep_device_list(acpi_handle handle)
+{
+	struct acpi_dep_data *dep, *tmp;
+	struct acpi_device *adev;
+
+	mutex_lock(&acpi_dep_list_lock);
+	list_for_each_entry_safe(dep, tmp, &acpi_dep_list, node) {
+		if (dep->master == handle) {
+			acpi_bus_get_device(dep->slave, &adev);
+			if (!adev)
+				continue;
+
+			adev->dep_unmet--;
+			if (!adev->dep_unmet)
+				acpi_bus_attach(adev);
+			list_del(&dep->node);
+			kfree(dep);
+		}
+	}
+	mutex_unlock(&acpi_dep_list_lock);
+}
+EXPORT_SYMBOL_GPL(acpi_walk_dep_device_list);
+
 /**
  * acpi_bus_scan - Add ACPI device node objects in a given namespace scope.
  * @handle: Root of the namespace scope to scan.
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index f43b4e11647..68aeb8eedae 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -403,6 +403,7 @@ static int acpi_i2c_install_space_handler(struct i2c_adapter *adapter)
 		return -ENOMEM;
 	}
 
+	acpi_walk_dep_device_list(handle);
 	return 0;
 }
 
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index f34a0835aa4..ea3697dc704 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -359,6 +359,7 @@ struct acpi_device {
 	void *driver_data;
 	struct device dev;
 	unsigned int physical_node_count;
+	unsigned int dep_unmet;
 	struct list_head physical_node_list;
 	struct mutex physical_node_lock;
 	void (*remove)(struct acpi_device *);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 407a12f663e..6cb310388c8 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -431,6 +431,7 @@ static inline bool acpi_driver_match_device(struct device *dev,
 
 int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *);
 int acpi_device_modalias(struct device *, char *, int);
+void acpi_walk_dep_device_list(acpi_handle handle);
 
 struct platform_device *acpi_create_platform_device(struct acpi_device *);
 #define ACPI_PTR(_ptr)	(_ptr)
-- 
cgit v1.2.3-70-g09d2


From 4060bbe9931eca2ed3c2124022a070a75d507472 Mon Sep 17 00:00:00 2001
From: Andrew Bresticker <abrestic@chromium.org>
Date: Mon, 20 Oct 2014 12:03:53 -0700
Subject: MIPS: Move gic.h to include/linux/irqchip/mips-gic.h

Now that the MIPS GIC irqchip lives in drivers/irqchip/, move
its header over to include/linux/irqchip/.

Signed-off-by: Andrew Bresticker <abrestic@chromium.org>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jason Cooper <jason@lakedaemon.net>
Cc: Paul Burton <paul.burton@imgtec.com>
Cc: Qais Yousef <qais.yousef@imgtec.com>
Cc: John Crispin <blogic@openwrt.org>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8129/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/gic.h                  | 325 ---------------------------
 arch/mips/include/asm/mips-boards/maltaint.h |   2 +-
 arch/mips/include/asm/mips-boards/sead3int.h |   2 +-
 arch/mips/kernel/cevt-gic.c                  |   2 +-
 arch/mips/kernel/cevt-r4k.c                  |   2 +-
 arch/mips/kernel/csrc-gic.c                  |   3 +-
 arch/mips/kernel/smp-cmp.c                   |   2 +-
 arch/mips/kernel/smp-cps.c                   |   2 +-
 arch/mips/kernel/smp-gic.c                   |   2 +-
 arch/mips/kernel/smp-mt.c                    |   2 +-
 arch/mips/mti-malta/malta-int.c              |   2 +-
 arch/mips/mti-malta/malta-time.c             |   2 +-
 arch/mips/mti-sead3/sead3-ehci.c             |   2 +-
 arch/mips/mti-sead3/sead3-int.c              |   2 +-
 arch/mips/mti-sead3/sead3-net.c              |   2 +-
 arch/mips/mti-sead3/sead3-platform.c         |   2 +-
 arch/mips/mti-sead3/sead3-time.c             |   2 +-
 drivers/irqchip/irq-mips-gic.c               |   2 +-
 include/linux/irqchip/mips-gic.h             | 325 +++++++++++++++++++++++++++
 19 files changed, 342 insertions(+), 343 deletions(-)
 delete mode 100644 arch/mips/include/asm/gic.h
 create mode 100644 include/linux/irqchip/mips-gic.h

(limited to 'include')

diff --git a/arch/mips/include/asm/gic.h b/arch/mips/include/asm/gic.h
deleted file mode 100644
index 285944ca9f6..00000000000
--- a/arch/mips/include/asm/gic.h
+++ /dev/null
@@ -1,325 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2000, 07 MIPS Technologies, Inc.
- *
- * GIC Register Definitions
- *
- */
-#ifndef _ASM_GICREGS_H
-#define _ASM_GICREGS_H
-
-#include <linux/bitmap.h>
-#include <linux/threads.h>
-
-#include <irq.h>
-
-#define GIC_MAX_INTRS			256
-
-/* Constants */
-#define GIC_POL_POS			1
-#define GIC_POL_NEG			0
-#define GIC_TRIG_EDGE			1
-#define GIC_TRIG_LEVEL			0
-#define GIC_TRIG_DUAL_ENABLE		1
-#define GIC_TRIG_DUAL_DISABLE		0
-
-#define MSK(n) ((1 << (n)) - 1)
-
-/* Accessors */
-#define GIC_REG(segment, offset) (segment##_##SECTION_OFS + offset##_##OFS)
-
-/* GIC Address Space */
-#define SHARED_SECTION_OFS		0x0000
-#define SHARED_SECTION_SIZE		0x8000
-#define VPE_LOCAL_SECTION_OFS		0x8000
-#define VPE_LOCAL_SECTION_SIZE		0x4000
-#define VPE_OTHER_SECTION_OFS		0xc000
-#define VPE_OTHER_SECTION_SIZE		0x4000
-#define USM_VISIBLE_SECTION_OFS		0x10000
-#define USM_VISIBLE_SECTION_SIZE	0x10000
-
-/* Register Map for Shared Section */
-
-#define GIC_SH_CONFIG_OFS		0x0000
-
-/* Shared Global Counter */
-#define GIC_SH_COUNTER_31_00_OFS	0x0010
-#define GIC_SH_COUNTER_63_32_OFS	0x0014
-#define GIC_SH_REVISIONID_OFS		0x0020
-
-/* Interrupt Polarity */
-#define GIC_SH_POL_31_0_OFS		0x0100
-#define GIC_SH_POL_63_32_OFS		0x0104
-#define GIC_SH_POL_95_64_OFS		0x0108
-#define GIC_SH_POL_127_96_OFS		0x010c
-#define GIC_SH_POL_159_128_OFS		0x0110
-#define GIC_SH_POL_191_160_OFS		0x0114
-#define GIC_SH_POL_223_192_OFS		0x0118
-#define GIC_SH_POL_255_224_OFS		0x011c
-
-/* Edge/Level Triggering */
-#define GIC_SH_TRIG_31_0_OFS		0x0180
-#define GIC_SH_TRIG_63_32_OFS		0x0184
-#define GIC_SH_TRIG_95_64_OFS		0x0188
-#define GIC_SH_TRIG_127_96_OFS		0x018c
-#define GIC_SH_TRIG_159_128_OFS		0x0190
-#define GIC_SH_TRIG_191_160_OFS		0x0194
-#define GIC_SH_TRIG_223_192_OFS		0x0198
-#define GIC_SH_TRIG_255_224_OFS		0x019c
-
-/* Dual Edge Triggering */
-#define GIC_SH_DUAL_31_0_OFS		0x0200
-#define GIC_SH_DUAL_63_32_OFS		0x0204
-#define GIC_SH_DUAL_95_64_OFS		0x0208
-#define GIC_SH_DUAL_127_96_OFS		0x020c
-#define GIC_SH_DUAL_159_128_OFS		0x0210
-#define GIC_SH_DUAL_191_160_OFS		0x0214
-#define GIC_SH_DUAL_223_192_OFS		0x0218
-#define GIC_SH_DUAL_255_224_OFS		0x021c
-
-/* Set/Clear corresponding bit in Edge Detect Register */
-#define GIC_SH_WEDGE_OFS		0x0280
-
-/* Reset Mask - Disables Interrupt */
-#define GIC_SH_RMASK_31_0_OFS		0x0300
-#define GIC_SH_RMASK_63_32_OFS		0x0304
-#define GIC_SH_RMASK_95_64_OFS		0x0308
-#define GIC_SH_RMASK_127_96_OFS		0x030c
-#define GIC_SH_RMASK_159_128_OFS	0x0310
-#define GIC_SH_RMASK_191_160_OFS	0x0314
-#define GIC_SH_RMASK_223_192_OFS	0x0318
-#define GIC_SH_RMASK_255_224_OFS	0x031c
-
-/* Set Mask (WO) - Enables Interrupt */
-#define GIC_SH_SMASK_31_0_OFS		0x0380
-#define GIC_SH_SMASK_63_32_OFS		0x0384
-#define GIC_SH_SMASK_95_64_OFS		0x0388
-#define GIC_SH_SMASK_127_96_OFS		0x038c
-#define GIC_SH_SMASK_159_128_OFS	0x0390
-#define GIC_SH_SMASK_191_160_OFS	0x0394
-#define GIC_SH_SMASK_223_192_OFS	0x0398
-#define GIC_SH_SMASK_255_224_OFS	0x039c
-
-/* Global Interrupt Mask Register (RO) - Bit Set == Interrupt enabled */
-#define GIC_SH_MASK_31_0_OFS		0x0400
-#define GIC_SH_MASK_63_32_OFS		0x0404
-#define GIC_SH_MASK_95_64_OFS		0x0408
-#define GIC_SH_MASK_127_96_OFS		0x040c
-#define GIC_SH_MASK_159_128_OFS		0x0410
-#define GIC_SH_MASK_191_160_OFS		0x0414
-#define GIC_SH_MASK_223_192_OFS		0x0418
-#define GIC_SH_MASK_255_224_OFS		0x041c
-
-/* Pending Global Interrupts (RO) */
-#define GIC_SH_PEND_31_0_OFS		0x0480
-#define GIC_SH_PEND_63_32_OFS		0x0484
-#define GIC_SH_PEND_95_64_OFS		0x0488
-#define GIC_SH_PEND_127_96_OFS		0x048c
-#define GIC_SH_PEND_159_128_OFS		0x0490
-#define GIC_SH_PEND_191_160_OFS		0x0494
-#define GIC_SH_PEND_223_192_OFS		0x0498
-#define GIC_SH_PEND_255_224_OFS		0x049c
-
-#define GIC_SH_INTR_MAP_TO_PIN_BASE_OFS 0x0500
-
-/* Maps Interrupt X to a Pin */
-#define GIC_SH_MAP_TO_PIN(intr)		(4 * (intr))
-
-#define GIC_SH_INTR_MAP_TO_VPE_BASE_OFS 0x2000
-
-/* Maps Interrupt X to a VPE */
-#define GIC_SH_MAP_TO_VPE_REG_OFF(intr, vpe) \
-	((32 * (intr)) + (((vpe) / 32) * 4))
-#define GIC_SH_MAP_TO_VPE_REG_BIT(vpe)	(1 << ((vpe) % 32))
-
-/* Convert an interrupt number to a byte offset/bit for multi-word registers */
-#define GIC_INTR_OFS(intr) (((intr) / 32)*4)
-#define GIC_INTR_BIT(intr) ((intr) % 32)
-
-/* Polarity : Reset Value is always 0 */
-#define GIC_SH_SET_POLARITY_OFS		0x0100
-
-/* Triggering : Reset Value is always 0 */
-#define GIC_SH_SET_TRIGGER_OFS		0x0180
-
-/* Dual edge triggering : Reset Value is always 0 */
-#define GIC_SH_SET_DUAL_OFS		0x0200
-
-/* Mask manipulation */
-#define GIC_SH_SMASK_OFS		0x0380
-#define GIC_SH_RMASK_OFS		0x0300
-
-/* Register Map for Local Section */
-#define GIC_VPE_CTL_OFS			0x0000
-#define GIC_VPE_PEND_OFS		0x0004
-#define GIC_VPE_MASK_OFS		0x0008
-#define GIC_VPE_RMASK_OFS		0x000c
-#define GIC_VPE_SMASK_OFS		0x0010
-#define GIC_VPE_WD_MAP_OFS		0x0040
-#define GIC_VPE_COMPARE_MAP_OFS		0x0044
-#define GIC_VPE_TIMER_MAP_OFS		0x0048
-#define GIC_VPE_FDC_MAP_OFS		0x004c
-#define GIC_VPE_PERFCTR_MAP_OFS		0x0050
-#define GIC_VPE_SWINT0_MAP_OFS		0x0054
-#define GIC_VPE_SWINT1_MAP_OFS		0x0058
-#define GIC_VPE_OTHER_ADDR_OFS		0x0080
-#define GIC_VPE_WD_CONFIG0_OFS		0x0090
-#define GIC_VPE_WD_COUNT0_OFS		0x0094
-#define GIC_VPE_WD_INITIAL0_OFS		0x0098
-#define GIC_VPE_COMPARE_LO_OFS		0x00a0
-#define GIC_VPE_COMPARE_HI_OFS		0x00a4
-
-#define GIC_VPE_EIC_SHADOW_SET_BASE_OFS	0x0100
-#define GIC_VPE_EIC_SS(intr)		(4 * (intr))
-
-#define GIC_VPE_EIC_VEC_BASE_OFS	0x0800
-#define GIC_VPE_EIC_VEC(intr)		(4 * (intr))
-
-#define GIC_VPE_TENABLE_NMI_OFS		0x1000
-#define GIC_VPE_TENABLE_YQ_OFS		0x1004
-#define GIC_VPE_TENABLE_INT_31_0_OFS	0x1080
-#define GIC_VPE_TENABLE_INT_63_32_OFS	0x1084
-
-/* User Mode Visible Section Register Map */
-#define GIC_UMV_SH_COUNTER_31_00_OFS	0x0000
-#define GIC_UMV_SH_COUNTER_63_32_OFS	0x0004
-
-/* Masks */
-#define GIC_SH_CONFIG_COUNTSTOP_SHF	28
-#define GIC_SH_CONFIG_COUNTSTOP_MSK	(MSK(1) << GIC_SH_CONFIG_COUNTSTOP_SHF)
-
-#define GIC_SH_CONFIG_COUNTBITS_SHF	24
-#define GIC_SH_CONFIG_COUNTBITS_MSK	(MSK(4) << GIC_SH_CONFIG_COUNTBITS_SHF)
-
-#define GIC_SH_CONFIG_NUMINTRS_SHF	16
-#define GIC_SH_CONFIG_NUMINTRS_MSK	(MSK(8) << GIC_SH_CONFIG_NUMINTRS_SHF)
-
-#define GIC_SH_CONFIG_NUMVPES_SHF	0
-#define GIC_SH_CONFIG_NUMVPES_MSK	(MSK(8) << GIC_SH_CONFIG_NUMVPES_SHF)
-
-#define GIC_SH_WEDGE_SET(intr)		(intr | (0x1 << 31))
-#define GIC_SH_WEDGE_CLR(intr)		(intr & ~(0x1 << 31))
-
-#define GIC_MAP_TO_PIN_SHF		31
-#define GIC_MAP_TO_PIN_MSK		(MSK(1) << GIC_MAP_TO_PIN_SHF)
-#define GIC_MAP_TO_NMI_SHF		30
-#define GIC_MAP_TO_NMI_MSK		(MSK(1) << GIC_MAP_TO_NMI_SHF)
-#define GIC_MAP_TO_YQ_SHF		29
-#define GIC_MAP_TO_YQ_MSK		(MSK(1) << GIC_MAP_TO_YQ_SHF)
-#define GIC_MAP_SHF			0
-#define GIC_MAP_MSK			(MSK(6) << GIC_MAP_SHF)
-
-/* GIC_VPE_CTL Masks */
-#define GIC_VPE_CTL_FDC_RTBL_SHF	4
-#define GIC_VPE_CTL_FDC_RTBL_MSK	(MSK(1) << GIC_VPE_CTL_FDC_RTBL_SHF)
-#define GIC_VPE_CTL_SWINT_RTBL_SHF	3
-#define GIC_VPE_CTL_SWINT_RTBL_MSK	(MSK(1) << GIC_VPE_CTL_SWINT_RTBL_SHF)
-#define GIC_VPE_CTL_PERFCNT_RTBL_SHF	2
-#define GIC_VPE_CTL_PERFCNT_RTBL_MSK	(MSK(1) << GIC_VPE_CTL_PERFCNT_RTBL_SHF)
-#define GIC_VPE_CTL_TIMER_RTBL_SHF	1
-#define GIC_VPE_CTL_TIMER_RTBL_MSK	(MSK(1) << GIC_VPE_CTL_TIMER_RTBL_SHF)
-#define GIC_VPE_CTL_EIC_MODE_SHF	0
-#define GIC_VPE_CTL_EIC_MODE_MSK	(MSK(1) << GIC_VPE_CTL_EIC_MODE_SHF)
-
-/* GIC_VPE_PEND Masks */
-#define GIC_VPE_PEND_WD_SHF		0
-#define GIC_VPE_PEND_WD_MSK		(MSK(1) << GIC_VPE_PEND_WD_SHF)
-#define GIC_VPE_PEND_CMP_SHF		1
-#define GIC_VPE_PEND_CMP_MSK		(MSK(1) << GIC_VPE_PEND_CMP_SHF)
-#define GIC_VPE_PEND_TIMER_SHF		2
-#define GIC_VPE_PEND_TIMER_MSK		(MSK(1) << GIC_VPE_PEND_TIMER_SHF)
-#define GIC_VPE_PEND_PERFCOUNT_SHF	3
-#define GIC_VPE_PEND_PERFCOUNT_MSK	(MSK(1) << GIC_VPE_PEND_PERFCOUNT_SHF)
-#define GIC_VPE_PEND_SWINT0_SHF		4
-#define GIC_VPE_PEND_SWINT0_MSK		(MSK(1) << GIC_VPE_PEND_SWINT0_SHF)
-#define GIC_VPE_PEND_SWINT1_SHF		5
-#define GIC_VPE_PEND_SWINT1_MSK		(MSK(1) << GIC_VPE_PEND_SWINT1_SHF)
-
-/* GIC_VPE_RMASK Masks */
-#define GIC_VPE_RMASK_WD_SHF		0
-#define GIC_VPE_RMASK_WD_MSK		(MSK(1) << GIC_VPE_RMASK_WD_SHF)
-#define GIC_VPE_RMASK_CMP_SHF		1
-#define GIC_VPE_RMASK_CMP_MSK		(MSK(1) << GIC_VPE_RMASK_CMP_SHF)
-#define GIC_VPE_RMASK_TIMER_SHF		2
-#define GIC_VPE_RMASK_TIMER_MSK		(MSK(1) << GIC_VPE_RMASK_TIMER_SHF)
-#define GIC_VPE_RMASK_PERFCNT_SHF	3
-#define GIC_VPE_RMASK_PERFCNT_MSK	(MSK(1) << GIC_VPE_RMASK_PERFCNT_SHF)
-#define GIC_VPE_RMASK_SWINT0_SHF	4
-#define GIC_VPE_RMASK_SWINT0_MSK	(MSK(1) << GIC_VPE_RMASK_SWINT0_SHF)
-#define GIC_VPE_RMASK_SWINT1_SHF	5
-#define GIC_VPE_RMASK_SWINT1_MSK	(MSK(1) << GIC_VPE_RMASK_SWINT1_SHF)
-
-/* GIC_VPE_SMASK Masks */
-#define GIC_VPE_SMASK_WD_SHF		0
-#define GIC_VPE_SMASK_WD_MSK		(MSK(1) << GIC_VPE_SMASK_WD_SHF)
-#define GIC_VPE_SMASK_CMP_SHF		1
-#define GIC_VPE_SMASK_CMP_MSK		(MSK(1) << GIC_VPE_SMASK_CMP_SHF)
-#define GIC_VPE_SMASK_TIMER_SHF		2
-#define GIC_VPE_SMASK_TIMER_MSK		(MSK(1) << GIC_VPE_SMASK_TIMER_SHF)
-#define GIC_VPE_SMASK_PERFCNT_SHF	3
-#define GIC_VPE_SMASK_PERFCNT_MSK	(MSK(1) << GIC_VPE_SMASK_PERFCNT_SHF)
-#define GIC_VPE_SMASK_SWINT0_SHF	4
-#define GIC_VPE_SMASK_SWINT0_MSK	(MSK(1) << GIC_VPE_SMASK_SWINT0_SHF)
-#define GIC_VPE_SMASK_SWINT1_SHF	5
-#define GIC_VPE_SMASK_SWINT1_MSK	(MSK(1) << GIC_VPE_SMASK_SWINT1_SHF)
-
-/* GIC nomenclature for Core Interrupt Pins. */
-#define GIC_CPU_INT0		0 /* Core Interrupt 2 */
-#define GIC_CPU_INT1		1 /* .		      */
-#define GIC_CPU_INT2		2 /* .		      */
-#define GIC_CPU_INT3		3 /* .		      */
-#define GIC_CPU_INT4		4 /* .		      */
-#define GIC_CPU_INT5		5 /* Core Interrupt 7 */
-
-/* Add 2 to convert GIC CPU pin to core interrupt */
-#define GIC_CPU_PIN_OFFSET	2
-
-/* Add 2 to convert non-EIC hardware interrupt to EIC vector number. */
-#define GIC_CPU_TO_VEC_OFFSET	(2)
-
-/* Mapped interrupt to pin X, then GIC will generate the vector (X+1). */
-#define GIC_PIN_TO_VEC_OFFSET	(1)
-
-/* Local GIC interrupts. */
-#define GIC_LOCAL_INT_WD	0 /* GIC watchdog */
-#define GIC_LOCAL_INT_COMPARE	1 /* GIC count and compare timer */
-#define GIC_LOCAL_INT_TIMER	2 /* CPU timer interrupt */
-#define GIC_LOCAL_INT_PERFCTR	3 /* CPU performance counter */
-#define GIC_LOCAL_INT_SWINT0	4 /* CPU software interrupt 0 */
-#define GIC_LOCAL_INT_SWINT1	5 /* CPU software interrupt 1 */
-#define GIC_LOCAL_INT_FDC	6 /* CPU fast debug channel */
-#define GIC_NUM_LOCAL_INTRS	7
-
-/* Convert between local/shared IRQ number and GIC HW IRQ number. */
-#define GIC_LOCAL_HWIRQ_BASE	0
-#define GIC_LOCAL_TO_HWIRQ(x)	(GIC_LOCAL_HWIRQ_BASE + (x))
-#define GIC_HWIRQ_TO_LOCAL(x)	((x) - GIC_LOCAL_HWIRQ_BASE)
-#define GIC_SHARED_HWIRQ_BASE	GIC_NUM_LOCAL_INTRS
-#define GIC_SHARED_TO_HWIRQ(x)	(GIC_SHARED_HWIRQ_BASE + (x))
-#define GIC_HWIRQ_TO_SHARED(x)	((x) - GIC_SHARED_HWIRQ_BASE)
-
-#include <linux/clocksource.h>
-#include <linux/irq.h>
-
-extern unsigned int gic_present;
-extern unsigned int gic_frequency;
-
-extern void gic_init(unsigned long gic_base_addr,
-	unsigned long gic_addrspace_size, unsigned int cpu_vec,
-	unsigned int irqbase);
-extern void gic_clocksource_init(unsigned int);
-extern cycle_t gic_read_count(void);
-extern unsigned int gic_get_count_width(void);
-extern cycle_t gic_read_compare(void);
-extern void gic_write_compare(cycle_t cnt);
-extern void gic_write_cpu_compare(cycle_t cnt, int cpu);
-extern void gic_send_ipi(unsigned int intr);
-extern unsigned int plat_ipi_call_int_xlate(unsigned int);
-extern unsigned int plat_ipi_resched_int_xlate(unsigned int);
-extern unsigned int gic_get_timer_pending(void);
-extern int gic_get_c0_compare_int(void);
-extern int gic_get_c0_perfcount_int(void);
-#endif /* _ASM_GICREGS_H */
diff --git a/arch/mips/include/asm/mips-boards/maltaint.h b/arch/mips/include/asm/mips-boards/maltaint.h
index 38b06a02743..987ff580466 100644
--- a/arch/mips/include/asm/mips-boards/maltaint.h
+++ b/arch/mips/include/asm/mips-boards/maltaint.h
@@ -10,7 +10,7 @@
 #ifndef _MIPS_MALTAINT_H
 #define _MIPS_MALTAINT_H
 
-#include <asm/gic.h>
+#include <linux/irqchip/mips-gic.h>
 
 /*
  * Interrupts 0..15 are used for Malta ISA compatible interrupts
diff --git a/arch/mips/include/asm/mips-boards/sead3int.h b/arch/mips/include/asm/mips-boards/sead3int.h
index 59d6c32c759..8932c7de041 100644
--- a/arch/mips/include/asm/mips-boards/sead3int.h
+++ b/arch/mips/include/asm/mips-boards/sead3int.h
@@ -10,7 +10,7 @@
 #ifndef _MIPS_SEAD3INT_H
 #define _MIPS_SEAD3INT_H
 
-#include <asm/gic.h>
+#include <linux/irqchip/mips-gic.h>
 
 /* SEAD-3 GIC address space definitions. */
 #define GIC_BASE_ADDR		0x1b1c0000
diff --git a/arch/mips/kernel/cevt-gic.c b/arch/mips/kernel/cevt-gic.c
index 4f9262ab04f..9caa68a2bcd 100644
--- a/arch/mips/kernel/cevt-gic.c
+++ b/arch/mips/kernel/cevt-gic.c
@@ -10,9 +10,9 @@
 #include <linux/percpu.h>
 #include <linux/smp.h>
 #include <linux/irq.h>
+#include <linux/irqchip/mips-gic.h>
 
 #include <asm/time.h>
-#include <asm/gic.h>
 #include <asm/mips-boards/maltaint.h>
 
 DEFINE_PER_CPU(struct clock_event_device, gic_clockevent_device);
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index fd0ef8d851c..6acaad0480a 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -11,10 +11,10 @@
 #include <linux/percpu.h>
 #include <linux/smp.h>
 #include <linux/irq.h>
+#include <linux/irqchip/mips-gic.h>
 
 #include <asm/time.h>
 #include <asm/cevt-r4k.h>
-#include <asm/gic.h>
 
 static int mips_next_event(unsigned long delta,
 			   struct clock_event_device *evt)
diff --git a/arch/mips/kernel/csrc-gic.c b/arch/mips/kernel/csrc-gic.c
index ab615c6c51a..0bf28e6aca7 100644
--- a/arch/mips/kernel/csrc-gic.c
+++ b/arch/mips/kernel/csrc-gic.c
@@ -6,10 +6,9 @@
  * Copyright (C) 2012 MIPS Technologies, Inc.  All rights reserved.
  */
 #include <linux/init.h>
+#include <linux/irqchip/mips-gic.h>
 #include <linux/time.h>
 
-#include <asm/gic.h>
-
 static cycle_t gic_hpt_read(struct clocksource *cs)
 {
 	return gic_read_count();
diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c
index fc8a5155342..1e0a93c5a3e 100644
--- a/arch/mips/kernel/smp-cmp.c
+++ b/arch/mips/kernel/smp-cmp.c
@@ -24,6 +24,7 @@
 #include <linux/cpumask.h>
 #include <linux/interrupt.h>
 #include <linux/compiler.h>
+#include <linux/irqchip/mips-gic.h>
 
 #include <linux/atomic.h>
 #include <asm/cacheflush.h>
@@ -37,7 +38,6 @@
 #include <asm/mipsmtregs.h>
 #include <asm/mips_mt.h>
 #include <asm/amon.h>
-#include <asm/gic.h>
 
 static void cmp_init_secondary(void)
 {
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index cd20acad7f1..bed7590e475 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -9,13 +9,13 @@
  */
 
 #include <linux/io.h>
+#include <linux/irqchip/mips-gic.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/smp.h>
 #include <linux/types.h>
 
 #include <asm/bcache.h>
-#include <asm/gic.h>
 #include <asm/mips-cm.h>
 #include <asm/mips-cpc.h>
 #include <asm/mips_mt.h>
diff --git a/arch/mips/kernel/smp-gic.c b/arch/mips/kernel/smp-gic.c
index 3b21a96d1cc..5f0ab5bcd01 100644
--- a/arch/mips/kernel/smp-gic.c
+++ b/arch/mips/kernel/smp-gic.c
@@ -12,9 +12,9 @@
  * option) any later version.
  */
 
+#include <linux/irqchip/mips-gic.h>
 #include <linux/printk.h>
 
-#include <asm/gic.h>
 #include <asm/mips-cpc.h>
 #include <asm/smp-ops.h>
 
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index d60475fe595..ad86951b73b 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -21,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/cpumask.h>
 #include <linux/interrupt.h>
+#include <linux/irqchip/mips-gic.h>
 #include <linux/compiler.h>
 #include <linux/smp.h>
 
@@ -34,7 +35,6 @@
 #include <asm/mipsregs.h>
 #include <asm/mipsmtregs.h>
 #include <asm/mips_mt.h>
-#include <asm/gic.h>
 
 static void __init smvp_copy_vpe_config(void)
 {
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index a058e0ba2a2..d1392f8f581 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -18,6 +18,7 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/irqchip/mips-gic.h>
 #include <linux/kernel_stat.h>
 #include <linux/kernel.h>
 #include <linux/random.h>
@@ -33,7 +34,6 @@
 #include <asm/mips-boards/generic.h>
 #include <asm/mips-boards/msc01_pci.h>
 #include <asm/msc01_ic.h>
-#include <asm/gic.h>
 #include <asm/setup.h>
 #include <asm/rtlx.h>
 
diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c
index 39f3902ed34..608655f8e6d 100644
--- a/arch/mips/mti-malta/malta-time.c
+++ b/arch/mips/mti-malta/malta-time.c
@@ -24,6 +24,7 @@
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
+#include <linux/irqchip/mips-gic.h>
 #include <linux/timex.h>
 #include <linux/mc146818rtc.h>
 
@@ -37,7 +38,6 @@
 #include <asm/time.h>
 #include <asm/mc146818-time.h>
 #include <asm/msc01_ic.h>
-#include <asm/gic.h>
 
 #include <asm/mips-boards/generic.h>
 #include <asm/mips-boards/maltaint.h>
diff --git a/arch/mips/mti-sead3/sead3-ehci.c b/arch/mips/mti-sead3/sead3-ehci.c
index 4ddaa0fd580..014dd7ba4d6 100644
--- a/arch/mips/mti-sead3/sead3-ehci.c
+++ b/arch/mips/mti-sead3/sead3-ehci.c
@@ -9,8 +9,8 @@
 #include <linux/irq.h>
 #include <linux/dma-mapping.h>
 #include <linux/platform_device.h>
+#include <linux/irqchip/mips-gic.h>
 
-#include <asm/gic.h>
 #include <asm/mips-boards/sead3int.h>
 
 struct resource ehci_resources[] = {
diff --git a/arch/mips/mti-sead3/sead3-int.c b/arch/mips/mti-sead3/sead3-int.c
index 02bf0dba112..e31e17f81ee 100644
--- a/arch/mips/mti-sead3/sead3-int.c
+++ b/arch/mips/mti-sead3/sead3-int.c
@@ -7,9 +7,9 @@
  */
 #include <linux/init.h>
 #include <linux/irq.h>
+#include <linux/irqchip/mips-gic.h>
 #include <linux/io.h>
 
-#include <asm/gic.h>
 #include <asm/irq_cpu.h>
 #include <asm/setup.h>
 
diff --git a/arch/mips/mti-sead3/sead3-net.c b/arch/mips/mti-sead3/sead3-net.c
index c9f728a41bd..46176b80457 100644
--- a/arch/mips/mti-sead3/sead3-net.c
+++ b/arch/mips/mti-sead3/sead3-net.c
@@ -7,10 +7,10 @@
  */
 #include <linux/module.h>
 #include <linux/irq.h>
+#include <linux/irqchip/mips-gic.h>
 #include <linux/platform_device.h>
 #include <linux/smsc911x.h>
 
-#include <asm/gic.h>
 #include <asm/mips-boards/sead3int.h>
 
 static struct smsc911x_platform_config sead3_smsc911x_data = {
diff --git a/arch/mips/mti-sead3/sead3-platform.c b/arch/mips/mti-sead3/sead3-platform.c
index d9661eb6fd6..53ee6f1f018 100644
--- a/arch/mips/mti-sead3/sead3-platform.c
+++ b/arch/mips/mti-sead3/sead3-platform.c
@@ -7,9 +7,9 @@
  */
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/irqchip/mips-gic.h>
 #include <linux/serial_8250.h>
 
-#include <asm/gic.h>
 #include <asm/mips-boards/sead3int.h>
 
 #define UART(base)							\
diff --git a/arch/mips/mti-sead3/sead3-time.c b/arch/mips/mti-sead3/sead3-time.c
index fd40de352c5..ec1dd2491f9 100644
--- a/arch/mips/mti-sead3/sead3-time.c
+++ b/arch/mips/mti-sead3/sead3-time.c
@@ -6,9 +6,9 @@
  * Copyright (C) 2012 MIPS Technologies, Inc.  All rights reserved.
  */
 #include <linux/init.h>
+#include <linux/irqchip/mips-gic.h>
 
 #include <asm/cpu.h>
-#include <asm/gic.h>
 #include <asm/setup.h>
 #include <asm/time.h>
 #include <asm/irq.h>
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 88086d7e7c5..bf0f7c97808 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -9,13 +9,13 @@
 #include <linux/bitmap.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irqchip/mips-gic.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/irq.h>
 #include <linux/clocksource.h>
 
 #include <asm/io.h>
-#include <asm/gic.h>
 #include <asm/setup.h>
 #include <asm/traps.h>
 #include <linux/hardirq.h>
diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h
new file mode 100644
index 00000000000..285944ca9f6
--- /dev/null
+++ b/include/linux/irqchip/mips-gic.h
@@ -0,0 +1,325 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2000, 07 MIPS Technologies, Inc.
+ *
+ * GIC Register Definitions
+ *
+ */
+#ifndef _ASM_GICREGS_H
+#define _ASM_GICREGS_H
+
+#include <linux/bitmap.h>
+#include <linux/threads.h>
+
+#include <irq.h>
+
+#define GIC_MAX_INTRS			256
+
+/* Constants */
+#define GIC_POL_POS			1
+#define GIC_POL_NEG			0
+#define GIC_TRIG_EDGE			1
+#define GIC_TRIG_LEVEL			0
+#define GIC_TRIG_DUAL_ENABLE		1
+#define GIC_TRIG_DUAL_DISABLE		0
+
+#define MSK(n) ((1 << (n)) - 1)
+
+/* Accessors */
+#define GIC_REG(segment, offset) (segment##_##SECTION_OFS + offset##_##OFS)
+
+/* GIC Address Space */
+#define SHARED_SECTION_OFS		0x0000
+#define SHARED_SECTION_SIZE		0x8000
+#define VPE_LOCAL_SECTION_OFS		0x8000
+#define VPE_LOCAL_SECTION_SIZE		0x4000
+#define VPE_OTHER_SECTION_OFS		0xc000
+#define VPE_OTHER_SECTION_SIZE		0x4000
+#define USM_VISIBLE_SECTION_OFS		0x10000
+#define USM_VISIBLE_SECTION_SIZE	0x10000
+
+/* Register Map for Shared Section */
+
+#define GIC_SH_CONFIG_OFS		0x0000
+
+/* Shared Global Counter */
+#define GIC_SH_COUNTER_31_00_OFS	0x0010
+#define GIC_SH_COUNTER_63_32_OFS	0x0014
+#define GIC_SH_REVISIONID_OFS		0x0020
+
+/* Interrupt Polarity */
+#define GIC_SH_POL_31_0_OFS		0x0100
+#define GIC_SH_POL_63_32_OFS		0x0104
+#define GIC_SH_POL_95_64_OFS		0x0108
+#define GIC_SH_POL_127_96_OFS		0x010c
+#define GIC_SH_POL_159_128_OFS		0x0110
+#define GIC_SH_POL_191_160_OFS		0x0114
+#define GIC_SH_POL_223_192_OFS		0x0118
+#define GIC_SH_POL_255_224_OFS		0x011c
+
+/* Edge/Level Triggering */
+#define GIC_SH_TRIG_31_0_OFS		0x0180
+#define GIC_SH_TRIG_63_32_OFS		0x0184
+#define GIC_SH_TRIG_95_64_OFS		0x0188
+#define GIC_SH_TRIG_127_96_OFS		0x018c
+#define GIC_SH_TRIG_159_128_OFS		0x0190
+#define GIC_SH_TRIG_191_160_OFS		0x0194
+#define GIC_SH_TRIG_223_192_OFS		0x0198
+#define GIC_SH_TRIG_255_224_OFS		0x019c
+
+/* Dual Edge Triggering */
+#define GIC_SH_DUAL_31_0_OFS		0x0200
+#define GIC_SH_DUAL_63_32_OFS		0x0204
+#define GIC_SH_DUAL_95_64_OFS		0x0208
+#define GIC_SH_DUAL_127_96_OFS		0x020c
+#define GIC_SH_DUAL_159_128_OFS		0x0210
+#define GIC_SH_DUAL_191_160_OFS		0x0214
+#define GIC_SH_DUAL_223_192_OFS		0x0218
+#define GIC_SH_DUAL_255_224_OFS		0x021c
+
+/* Set/Clear corresponding bit in Edge Detect Register */
+#define GIC_SH_WEDGE_OFS		0x0280
+
+/* Reset Mask - Disables Interrupt */
+#define GIC_SH_RMASK_31_0_OFS		0x0300
+#define GIC_SH_RMASK_63_32_OFS		0x0304
+#define GIC_SH_RMASK_95_64_OFS		0x0308
+#define GIC_SH_RMASK_127_96_OFS		0x030c
+#define GIC_SH_RMASK_159_128_OFS	0x0310
+#define GIC_SH_RMASK_191_160_OFS	0x0314
+#define GIC_SH_RMASK_223_192_OFS	0x0318
+#define GIC_SH_RMASK_255_224_OFS	0x031c
+
+/* Set Mask (WO) - Enables Interrupt */
+#define GIC_SH_SMASK_31_0_OFS		0x0380
+#define GIC_SH_SMASK_63_32_OFS		0x0384
+#define GIC_SH_SMASK_95_64_OFS		0x0388
+#define GIC_SH_SMASK_127_96_OFS		0x038c
+#define GIC_SH_SMASK_159_128_OFS	0x0390
+#define GIC_SH_SMASK_191_160_OFS	0x0394
+#define GIC_SH_SMASK_223_192_OFS	0x0398
+#define GIC_SH_SMASK_255_224_OFS	0x039c
+
+/* Global Interrupt Mask Register (RO) - Bit Set == Interrupt enabled */
+#define GIC_SH_MASK_31_0_OFS		0x0400
+#define GIC_SH_MASK_63_32_OFS		0x0404
+#define GIC_SH_MASK_95_64_OFS		0x0408
+#define GIC_SH_MASK_127_96_OFS		0x040c
+#define GIC_SH_MASK_159_128_OFS		0x0410
+#define GIC_SH_MASK_191_160_OFS		0x0414
+#define GIC_SH_MASK_223_192_OFS		0x0418
+#define GIC_SH_MASK_255_224_OFS		0x041c
+
+/* Pending Global Interrupts (RO) */
+#define GIC_SH_PEND_31_0_OFS		0x0480
+#define GIC_SH_PEND_63_32_OFS		0x0484
+#define GIC_SH_PEND_95_64_OFS		0x0488
+#define GIC_SH_PEND_127_96_OFS		0x048c
+#define GIC_SH_PEND_159_128_OFS		0x0490
+#define GIC_SH_PEND_191_160_OFS		0x0494
+#define GIC_SH_PEND_223_192_OFS		0x0498
+#define GIC_SH_PEND_255_224_OFS		0x049c
+
+#define GIC_SH_INTR_MAP_TO_PIN_BASE_OFS 0x0500
+
+/* Maps Interrupt X to a Pin */
+#define GIC_SH_MAP_TO_PIN(intr)		(4 * (intr))
+
+#define GIC_SH_INTR_MAP_TO_VPE_BASE_OFS 0x2000
+
+/* Maps Interrupt X to a VPE */
+#define GIC_SH_MAP_TO_VPE_REG_OFF(intr, vpe) \
+	((32 * (intr)) + (((vpe) / 32) * 4))
+#define GIC_SH_MAP_TO_VPE_REG_BIT(vpe)	(1 << ((vpe) % 32))
+
+/* Convert an interrupt number to a byte offset/bit for multi-word registers */
+#define GIC_INTR_OFS(intr) (((intr) / 32)*4)
+#define GIC_INTR_BIT(intr) ((intr) % 32)
+
+/* Polarity : Reset Value is always 0 */
+#define GIC_SH_SET_POLARITY_OFS		0x0100
+
+/* Triggering : Reset Value is always 0 */
+#define GIC_SH_SET_TRIGGER_OFS		0x0180
+
+/* Dual edge triggering : Reset Value is always 0 */
+#define GIC_SH_SET_DUAL_OFS		0x0200
+
+/* Mask manipulation */
+#define GIC_SH_SMASK_OFS		0x0380
+#define GIC_SH_RMASK_OFS		0x0300
+
+/* Register Map for Local Section */
+#define GIC_VPE_CTL_OFS			0x0000
+#define GIC_VPE_PEND_OFS		0x0004
+#define GIC_VPE_MASK_OFS		0x0008
+#define GIC_VPE_RMASK_OFS		0x000c
+#define GIC_VPE_SMASK_OFS		0x0010
+#define GIC_VPE_WD_MAP_OFS		0x0040
+#define GIC_VPE_COMPARE_MAP_OFS		0x0044
+#define GIC_VPE_TIMER_MAP_OFS		0x0048
+#define GIC_VPE_FDC_MAP_OFS		0x004c
+#define GIC_VPE_PERFCTR_MAP_OFS		0x0050
+#define GIC_VPE_SWINT0_MAP_OFS		0x0054
+#define GIC_VPE_SWINT1_MAP_OFS		0x0058
+#define GIC_VPE_OTHER_ADDR_OFS		0x0080
+#define GIC_VPE_WD_CONFIG0_OFS		0x0090
+#define GIC_VPE_WD_COUNT0_OFS		0x0094
+#define GIC_VPE_WD_INITIAL0_OFS		0x0098
+#define GIC_VPE_COMPARE_LO_OFS		0x00a0
+#define GIC_VPE_COMPARE_HI_OFS		0x00a4
+
+#define GIC_VPE_EIC_SHADOW_SET_BASE_OFS	0x0100
+#define GIC_VPE_EIC_SS(intr)		(4 * (intr))
+
+#define GIC_VPE_EIC_VEC_BASE_OFS	0x0800
+#define GIC_VPE_EIC_VEC(intr)		(4 * (intr))
+
+#define GIC_VPE_TENABLE_NMI_OFS		0x1000
+#define GIC_VPE_TENABLE_YQ_OFS		0x1004
+#define GIC_VPE_TENABLE_INT_31_0_OFS	0x1080
+#define GIC_VPE_TENABLE_INT_63_32_OFS	0x1084
+
+/* User Mode Visible Section Register Map */
+#define GIC_UMV_SH_COUNTER_31_00_OFS	0x0000
+#define GIC_UMV_SH_COUNTER_63_32_OFS	0x0004
+
+/* Masks */
+#define GIC_SH_CONFIG_COUNTSTOP_SHF	28
+#define GIC_SH_CONFIG_COUNTSTOP_MSK	(MSK(1) << GIC_SH_CONFIG_COUNTSTOP_SHF)
+
+#define GIC_SH_CONFIG_COUNTBITS_SHF	24
+#define GIC_SH_CONFIG_COUNTBITS_MSK	(MSK(4) << GIC_SH_CONFIG_COUNTBITS_SHF)
+
+#define GIC_SH_CONFIG_NUMINTRS_SHF	16
+#define GIC_SH_CONFIG_NUMINTRS_MSK	(MSK(8) << GIC_SH_CONFIG_NUMINTRS_SHF)
+
+#define GIC_SH_CONFIG_NUMVPES_SHF	0
+#define GIC_SH_CONFIG_NUMVPES_MSK	(MSK(8) << GIC_SH_CONFIG_NUMVPES_SHF)
+
+#define GIC_SH_WEDGE_SET(intr)		(intr | (0x1 << 31))
+#define GIC_SH_WEDGE_CLR(intr)		(intr & ~(0x1 << 31))
+
+#define GIC_MAP_TO_PIN_SHF		31
+#define GIC_MAP_TO_PIN_MSK		(MSK(1) << GIC_MAP_TO_PIN_SHF)
+#define GIC_MAP_TO_NMI_SHF		30
+#define GIC_MAP_TO_NMI_MSK		(MSK(1) << GIC_MAP_TO_NMI_SHF)
+#define GIC_MAP_TO_YQ_SHF		29
+#define GIC_MAP_TO_YQ_MSK		(MSK(1) << GIC_MAP_TO_YQ_SHF)
+#define GIC_MAP_SHF			0
+#define GIC_MAP_MSK			(MSK(6) << GIC_MAP_SHF)
+
+/* GIC_VPE_CTL Masks */
+#define GIC_VPE_CTL_FDC_RTBL_SHF	4
+#define GIC_VPE_CTL_FDC_RTBL_MSK	(MSK(1) << GIC_VPE_CTL_FDC_RTBL_SHF)
+#define GIC_VPE_CTL_SWINT_RTBL_SHF	3
+#define GIC_VPE_CTL_SWINT_RTBL_MSK	(MSK(1) << GIC_VPE_CTL_SWINT_RTBL_SHF)
+#define GIC_VPE_CTL_PERFCNT_RTBL_SHF	2
+#define GIC_VPE_CTL_PERFCNT_RTBL_MSK	(MSK(1) << GIC_VPE_CTL_PERFCNT_RTBL_SHF)
+#define GIC_VPE_CTL_TIMER_RTBL_SHF	1
+#define GIC_VPE_CTL_TIMER_RTBL_MSK	(MSK(1) << GIC_VPE_CTL_TIMER_RTBL_SHF)
+#define GIC_VPE_CTL_EIC_MODE_SHF	0
+#define GIC_VPE_CTL_EIC_MODE_MSK	(MSK(1) << GIC_VPE_CTL_EIC_MODE_SHF)
+
+/* GIC_VPE_PEND Masks */
+#define GIC_VPE_PEND_WD_SHF		0
+#define GIC_VPE_PEND_WD_MSK		(MSK(1) << GIC_VPE_PEND_WD_SHF)
+#define GIC_VPE_PEND_CMP_SHF		1
+#define GIC_VPE_PEND_CMP_MSK		(MSK(1) << GIC_VPE_PEND_CMP_SHF)
+#define GIC_VPE_PEND_TIMER_SHF		2
+#define GIC_VPE_PEND_TIMER_MSK		(MSK(1) << GIC_VPE_PEND_TIMER_SHF)
+#define GIC_VPE_PEND_PERFCOUNT_SHF	3
+#define GIC_VPE_PEND_PERFCOUNT_MSK	(MSK(1) << GIC_VPE_PEND_PERFCOUNT_SHF)
+#define GIC_VPE_PEND_SWINT0_SHF		4
+#define GIC_VPE_PEND_SWINT0_MSK		(MSK(1) << GIC_VPE_PEND_SWINT0_SHF)
+#define GIC_VPE_PEND_SWINT1_SHF		5
+#define GIC_VPE_PEND_SWINT1_MSK		(MSK(1) << GIC_VPE_PEND_SWINT1_SHF)
+
+/* GIC_VPE_RMASK Masks */
+#define GIC_VPE_RMASK_WD_SHF		0
+#define GIC_VPE_RMASK_WD_MSK		(MSK(1) << GIC_VPE_RMASK_WD_SHF)
+#define GIC_VPE_RMASK_CMP_SHF		1
+#define GIC_VPE_RMASK_CMP_MSK		(MSK(1) << GIC_VPE_RMASK_CMP_SHF)
+#define GIC_VPE_RMASK_TIMER_SHF		2
+#define GIC_VPE_RMASK_TIMER_MSK		(MSK(1) << GIC_VPE_RMASK_TIMER_SHF)
+#define GIC_VPE_RMASK_PERFCNT_SHF	3
+#define GIC_VPE_RMASK_PERFCNT_MSK	(MSK(1) << GIC_VPE_RMASK_PERFCNT_SHF)
+#define GIC_VPE_RMASK_SWINT0_SHF	4
+#define GIC_VPE_RMASK_SWINT0_MSK	(MSK(1) << GIC_VPE_RMASK_SWINT0_SHF)
+#define GIC_VPE_RMASK_SWINT1_SHF	5
+#define GIC_VPE_RMASK_SWINT1_MSK	(MSK(1) << GIC_VPE_RMASK_SWINT1_SHF)
+
+/* GIC_VPE_SMASK Masks */
+#define GIC_VPE_SMASK_WD_SHF		0
+#define GIC_VPE_SMASK_WD_MSK		(MSK(1) << GIC_VPE_SMASK_WD_SHF)
+#define GIC_VPE_SMASK_CMP_SHF		1
+#define GIC_VPE_SMASK_CMP_MSK		(MSK(1) << GIC_VPE_SMASK_CMP_SHF)
+#define GIC_VPE_SMASK_TIMER_SHF		2
+#define GIC_VPE_SMASK_TIMER_MSK		(MSK(1) << GIC_VPE_SMASK_TIMER_SHF)
+#define GIC_VPE_SMASK_PERFCNT_SHF	3
+#define GIC_VPE_SMASK_PERFCNT_MSK	(MSK(1) << GIC_VPE_SMASK_PERFCNT_SHF)
+#define GIC_VPE_SMASK_SWINT0_SHF	4
+#define GIC_VPE_SMASK_SWINT0_MSK	(MSK(1) << GIC_VPE_SMASK_SWINT0_SHF)
+#define GIC_VPE_SMASK_SWINT1_SHF	5
+#define GIC_VPE_SMASK_SWINT1_MSK	(MSK(1) << GIC_VPE_SMASK_SWINT1_SHF)
+
+/* GIC nomenclature for Core Interrupt Pins. */
+#define GIC_CPU_INT0		0 /* Core Interrupt 2 */
+#define GIC_CPU_INT1		1 /* .		      */
+#define GIC_CPU_INT2		2 /* .		      */
+#define GIC_CPU_INT3		3 /* .		      */
+#define GIC_CPU_INT4		4 /* .		      */
+#define GIC_CPU_INT5		5 /* Core Interrupt 7 */
+
+/* Add 2 to convert GIC CPU pin to core interrupt */
+#define GIC_CPU_PIN_OFFSET	2
+
+/* Add 2 to convert non-EIC hardware interrupt to EIC vector number. */
+#define GIC_CPU_TO_VEC_OFFSET	(2)
+
+/* Mapped interrupt to pin X, then GIC will generate the vector (X+1). */
+#define GIC_PIN_TO_VEC_OFFSET	(1)
+
+/* Local GIC interrupts. */
+#define GIC_LOCAL_INT_WD	0 /* GIC watchdog */
+#define GIC_LOCAL_INT_COMPARE	1 /* GIC count and compare timer */
+#define GIC_LOCAL_INT_TIMER	2 /* CPU timer interrupt */
+#define GIC_LOCAL_INT_PERFCTR	3 /* CPU performance counter */
+#define GIC_LOCAL_INT_SWINT0	4 /* CPU software interrupt 0 */
+#define GIC_LOCAL_INT_SWINT1	5 /* CPU software interrupt 1 */
+#define GIC_LOCAL_INT_FDC	6 /* CPU fast debug channel */
+#define GIC_NUM_LOCAL_INTRS	7
+
+/* Convert between local/shared IRQ number and GIC HW IRQ number. */
+#define GIC_LOCAL_HWIRQ_BASE	0
+#define GIC_LOCAL_TO_HWIRQ(x)	(GIC_LOCAL_HWIRQ_BASE + (x))
+#define GIC_HWIRQ_TO_LOCAL(x)	((x) - GIC_LOCAL_HWIRQ_BASE)
+#define GIC_SHARED_HWIRQ_BASE	GIC_NUM_LOCAL_INTRS
+#define GIC_SHARED_TO_HWIRQ(x)	(GIC_SHARED_HWIRQ_BASE + (x))
+#define GIC_HWIRQ_TO_SHARED(x)	((x) - GIC_SHARED_HWIRQ_BASE)
+
+#include <linux/clocksource.h>
+#include <linux/irq.h>
+
+extern unsigned int gic_present;
+extern unsigned int gic_frequency;
+
+extern void gic_init(unsigned long gic_base_addr,
+	unsigned long gic_addrspace_size, unsigned int cpu_vec,
+	unsigned int irqbase);
+extern void gic_clocksource_init(unsigned int);
+extern cycle_t gic_read_count(void);
+extern unsigned int gic_get_count_width(void);
+extern cycle_t gic_read_compare(void);
+extern void gic_write_compare(cycle_t cnt);
+extern void gic_write_cpu_compare(cycle_t cnt, int cpu);
+extern void gic_send_ipi(unsigned int intr);
+extern unsigned int plat_ipi_call_int_xlate(unsigned int);
+extern unsigned int plat_ipi_resched_int_xlate(unsigned int);
+extern unsigned int gic_get_timer_pending(void);
+extern int gic_get_c0_compare_int(void);
+extern int gic_get_c0_perfcount_int(void);
+#endif /* _ASM_GICREGS_H */
-- 
cgit v1.2.3-70-g09d2


From 774c105ed8d791b709b40082d107f5bb40254374 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@imgtec.com>
Date: Thu, 11 Sep 2014 08:30:16 +0100
Subject: binfmt_elf: allow arch code to examine PT_LOPROC ... PT_HIPROC
 headers

MIPS is introducing new variants of its O32 ABI which differ in their
handling of floating point, in order to enable a gradual transition
towards a world where mips32 binaries can take advantage of new hardware
features only available when configured for certain FP modes. In order
to do this ELF binaries are being augmented with a new section that
indicates, amongst other things, the FP mode requirements of the binary.
The presence & location of such a section is indicated by a program
header in the PT_LOPROC ... PT_HIPROC range.

In order to allow the MIPS architecture code to examine the program
header & section in question, pass all program headers in this range
to an architecture-specific arch_elf_pt_proc function. This function
may return an error if the header is deemed invalid or unsuitable for
the system, in which case that error will be returned from
load_elf_binary and upwards through the execve syscall.

A means is required for the architecture code to make a decision once
it is known that all such headers have been seen, but before it is too
late to return from an execve syscall. For this purpose the
arch_check_elf function is added, and called once, after all PT_LOPROC
to PT_HIPROC headers have been passed to arch_elf_pt_proc but before
the code which invoked execve has been lost. This enables the
architecture code to make a decision based upon all the headers present
in an ELF binary and its interpreter, as is required to forbid
conflicting FP ABI requirements between an ELF & its interpreter.

In order to allow data to be stored throughout the calls to the above
functions, struct arch_elf_state is introduced.

Finally a variant of the SET_PERSONALITY macro is introduced which
accepts a pointer to the struct arch_elf_state, allowing it to act
based upon state observed from the architecture specific program
headers.

Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: linux-mips@linux-mips.org
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/7679/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 fs/Kconfig.binfmt   |   3 ++
 fs/binfmt_elf.c     | 105 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/elf.h |   5 +++
 3 files changed, 111 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 370b24cee4d..c055d56ec63 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -30,6 +30,9 @@ config COMPAT_BINFMT_ELF
 config ARCH_BINFMT_ELF_RANDOMIZE_PIE
 	bool
 
+config ARCH_BINFMT_ELF_STATE
+	bool
+
 config BINFMT_ELF_FDPIC
 	bool "Kernel support for FDPIC ELF binaries"
 	default y
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 26a951f115c..a333cd982d3 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -440,6 +440,74 @@ out:
 	return elf_phdata;
 }
 
+#ifndef CONFIG_ARCH_BINFMT_ELF_STATE
+
+/**
+ * struct arch_elf_state - arch-specific ELF loading state
+ *
+ * This structure is used to preserve architecture specific data during
+ * the loading of an ELF file, throughout the checking of architecture
+ * specific ELF headers & through to the point where the ELF load is
+ * known to be proceeding (ie. SET_PERSONALITY).
+ *
+ * This implementation is a dummy for architectures which require no
+ * specific state.
+ */
+struct arch_elf_state {
+};
+
+#define INIT_ARCH_ELF_STATE {}
+
+/**
+ * arch_elf_pt_proc() - check a PT_LOPROC..PT_HIPROC ELF program header
+ * @ehdr:	The main ELF header
+ * @phdr:	The program header to check
+ * @elf:	The open ELF file
+ * @is_interp:	True if the phdr is from the interpreter of the ELF being
+ *		loaded, else false.
+ * @state:	Architecture-specific state preserved throughout the process
+ *		of loading the ELF.
+ *
+ * Inspects the program header phdr to validate its correctness and/or
+ * suitability for the system. Called once per ELF program header in the
+ * range PT_LOPROC to PT_HIPROC, for both the ELF being loaded and its
+ * interpreter.
+ *
+ * Return: Zero to proceed with the ELF load, non-zero to fail the ELF load
+ *         with that return code.
+ */
+static inline int arch_elf_pt_proc(struct elfhdr *ehdr,
+				   struct elf_phdr *phdr,
+				   struct file *elf, bool is_interp,
+				   struct arch_elf_state *state)
+{
+	/* Dummy implementation, always proceed */
+	return 0;
+}
+
+/**
+ * arch_check_elf() - check a PT_LOPROC..PT_HIPROC ELF program header
+ * @ehdr:	The main ELF header
+ * @has_interp:	True if the ELF has an interpreter, else false.
+ * @state:	Architecture-specific state preserved throughout the process
+ *		of loading the ELF.
+ *
+ * Provides a final opportunity for architecture code to reject the loading
+ * of the ELF & cause an exec syscall to return an error. This is called after
+ * all program headers to be checked by arch_elf_pt_proc have been.
+ *
+ * Return: Zero to proceed with the ELF load, non-zero to fail the ELF load
+ *         with that return code.
+ */
+static inline int arch_check_elf(struct elfhdr *ehdr, bool has_interp,
+				 struct arch_elf_state *state)
+{
+	/* Dummy implementation, always proceed */
+	return 0;
+}
+
+#endif /* !CONFIG_ARCH_BINFMT_ELF_STATE */
+
 /* This is much more generalized than the library routine read function,
    so we keep this separate.  Technically the library read function
    is only provided so that we can read a.out libraries that have
@@ -611,6 +679,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		struct elfhdr elf_ex;
 		struct elfhdr interp_elf_ex;
 	} *loc;
+	struct arch_elf_state arch_state = INIT_ARCH_ELF_STATE;
 
 	loc = kmalloc(sizeof(*loc), GFP_KERNEL);
 	if (!loc) {
@@ -705,12 +774,21 @@ static int load_elf_binary(struct linux_binprm *bprm)
 
 	elf_ppnt = elf_phdata;
 	for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++)
-		if (elf_ppnt->p_type == PT_GNU_STACK) {
+		switch (elf_ppnt->p_type) {
+		case PT_GNU_STACK:
 			if (elf_ppnt->p_flags & PF_X)
 				executable_stack = EXSTACK_ENABLE_X;
 			else
 				executable_stack = EXSTACK_DISABLE_X;
 			break;
+
+		case PT_LOPROC ... PT_HIPROC:
+			retval = arch_elf_pt_proc(&loc->elf_ex, elf_ppnt,
+						  bprm->file, false,
+						  &arch_state);
+			if (retval)
+				goto out_free_dentry;
+			break;
 		}
 
 	/* Some simple consistency checks for the interpreter */
@@ -728,8 +806,30 @@ static int load_elf_binary(struct linux_binprm *bprm)
 						   interpreter);
 		if (!interp_elf_phdata)
 			goto out_free_dentry;
+
+		/* Pass PT_LOPROC..PT_HIPROC headers to arch code */
+		elf_ppnt = interp_elf_phdata;
+		for (i = 0; i < loc->interp_elf_ex.e_phnum; i++, elf_ppnt++)
+			switch (elf_ppnt->p_type) {
+			case PT_LOPROC ... PT_HIPROC:
+				retval = arch_elf_pt_proc(&loc->interp_elf_ex,
+							  elf_ppnt, interpreter,
+							  true, &arch_state);
+				if (retval)
+					goto out_free_dentry;
+				break;
+			}
 	}
 
+	/*
+	 * Allow arch code to reject the ELF at this point, whilst it's
+	 * still possible to return an error to the code that invoked
+	 * the exec syscall.
+	 */
+	retval = arch_check_elf(&loc->elf_ex, !!interpreter, &arch_state);
+	if (retval)
+		goto out_free_dentry;
+
 	/* Flush all traces of the currently running executable */
 	retval = flush_old_exec(bprm);
 	if (retval)
@@ -737,7 +837,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 
 	/* Do this immediately, since STACK_TOP as used in setup_arg_pages
 	   may depend on the personality.  */
-	SET_PERSONALITY(loc->elf_ex);
+	SET_PERSONALITY2(loc->elf_ex, &arch_state);
 	if (elf_read_implies_exec(loc->elf_ex, executable_stack))
 		current->personality |= READ_IMPLIES_EXEC;
 
@@ -929,6 +1029,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		}
 	}
 
+	kfree(interp_elf_phdata);
 	kfree(elf_phdata);
 
 	set_binfmt(&elf_format);
diff --git a/include/linux/elf.h b/include/linux/elf.h
index 67a5fa7830c..20fa8d8ae31 100644
--- a/include/linux/elf.h
+++ b/include/linux/elf.h
@@ -15,6 +15,11 @@
 	set_personality(PER_LINUX | (current->personality & (~PER_MASK)))
 #endif
 
+#ifndef SET_PERSONALITY2
+#define SET_PERSONALITY2(ex, state) \
+	SET_PERSONALITY(ex)
+#endif
+
 #if ELF_CLASS == ELFCLASS32
 
 extern Elf32_Dyn _DYNAMIC [];
-- 
cgit v1.2.3-70-g09d2


From 824f3f7fa2b441416e3d9aaf1f19feab7db44747 Mon Sep 17 00:00:00 2001
From: Andrew Bresticker <abrestic@chromium.org>
Date: Mon, 20 Oct 2014 12:03:54 -0700
Subject: irqchip: mips-gic: Clean up header file

Remove duplicate #defines and unnecessary #includes, fix parenthesization,
and re-order register definitions in ascending order.

Signed-off-by: Andrew Bresticker <abrestic@chromium.org>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jason Cooper <jason@lakedaemon.net>
Cc: Paul Burton <paul.burton@imgtec.com>
Cc: Qais Yousef <qais.yousef@imgtec.com>
Cc: John Crispin <blogic@openwrt.org>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8128/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 drivers/irqchip/irq-mips-gic.c   |   4 +-
 include/linux/irqchip/mips-gic.h | 129 ++++++++-------------------------------
 2 files changed, 29 insertions(+), 104 deletions(-)

(limited to 'include')

diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index bf0f7c97808..eaebeea36d2 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -253,8 +253,8 @@ static unsigned int gic_get_int(void)
 	intrmask = intrmask_regs[smp_processor_id()].intrmask;
 	pcpu_mask = pcpu_masks[smp_processor_id()].pcpu_mask;
 
-	pending_reg = GIC_REG(SHARED, GIC_SH_PEND_31_0);
-	intrmask_reg = GIC_REG(SHARED, GIC_SH_MASK_31_0);
+	pending_reg = GIC_REG(SHARED, GIC_SH_PEND);
+	intrmask_reg = GIC_REG(SHARED, GIC_SH_MASK);
 
 	for (i = 0; i < BITS_TO_LONGS(gic_shared_intrs); i++) {
 		pending[i] = gic_read(pending_reg);
diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h
index 285944ca9f6..0350effb7cc 100644
--- a/include/linux/irqchip/mips-gic.h
+++ b/include/linux/irqchip/mips-gic.h
@@ -4,17 +4,11 @@
  * for more details.
  *
  * Copyright (C) 2000, 07 MIPS Technologies, Inc.
- *
- * GIC Register Definitions
- *
  */
-#ifndef _ASM_GICREGS_H
-#define _ASM_GICREGS_H
-
-#include <linux/bitmap.h>
-#include <linux/threads.h>
+#ifndef __LINUX_IRQCHIP_MIPS_GIC_H
+#define __LINUX_IRQCHIP_MIPS_GIC_H
 
-#include <irq.h>
+#include <linux/clocksource.h>
 
 #define GIC_MAX_INTRS			256
 
@@ -50,108 +44,42 @@
 #define GIC_SH_COUNTER_63_32_OFS	0x0014
 #define GIC_SH_REVISIONID_OFS		0x0020
 
-/* Interrupt Polarity */
-#define GIC_SH_POL_31_0_OFS		0x0100
-#define GIC_SH_POL_63_32_OFS		0x0104
-#define GIC_SH_POL_95_64_OFS		0x0108
-#define GIC_SH_POL_127_96_OFS		0x010c
-#define GIC_SH_POL_159_128_OFS		0x0110
-#define GIC_SH_POL_191_160_OFS		0x0114
-#define GIC_SH_POL_223_192_OFS		0x0118
-#define GIC_SH_POL_255_224_OFS		0x011c
-
-/* Edge/Level Triggering */
-#define GIC_SH_TRIG_31_0_OFS		0x0180
-#define GIC_SH_TRIG_63_32_OFS		0x0184
-#define GIC_SH_TRIG_95_64_OFS		0x0188
-#define GIC_SH_TRIG_127_96_OFS		0x018c
-#define GIC_SH_TRIG_159_128_OFS		0x0190
-#define GIC_SH_TRIG_191_160_OFS		0x0194
-#define GIC_SH_TRIG_223_192_OFS		0x0198
-#define GIC_SH_TRIG_255_224_OFS		0x019c
-
-/* Dual Edge Triggering */
-#define GIC_SH_DUAL_31_0_OFS		0x0200
-#define GIC_SH_DUAL_63_32_OFS		0x0204
-#define GIC_SH_DUAL_95_64_OFS		0x0208
-#define GIC_SH_DUAL_127_96_OFS		0x020c
-#define GIC_SH_DUAL_159_128_OFS		0x0210
-#define GIC_SH_DUAL_191_160_OFS		0x0214
-#define GIC_SH_DUAL_223_192_OFS		0x0218
-#define GIC_SH_DUAL_255_224_OFS		0x021c
+/* Convert an interrupt number to a byte offset/bit for multi-word registers */
+#define GIC_INTR_OFS(intr)		(((intr) / 32) * 4)
+#define GIC_INTR_BIT(intr)		((intr) % 32)
+
+/* Polarity : Reset Value is always 0 */
+#define GIC_SH_SET_POLARITY_OFS		0x0100
+
+/* Triggering : Reset Value is always 0 */
+#define GIC_SH_SET_TRIGGER_OFS		0x0180
+
+/* Dual edge triggering : Reset Value is always 0 */
+#define GIC_SH_SET_DUAL_OFS		0x0200
 
 /* Set/Clear corresponding bit in Edge Detect Register */
 #define GIC_SH_WEDGE_OFS		0x0280
 
-/* Reset Mask - Disables Interrupt */
-#define GIC_SH_RMASK_31_0_OFS		0x0300
-#define GIC_SH_RMASK_63_32_OFS		0x0304
-#define GIC_SH_RMASK_95_64_OFS		0x0308
-#define GIC_SH_RMASK_127_96_OFS		0x030c
-#define GIC_SH_RMASK_159_128_OFS	0x0310
-#define GIC_SH_RMASK_191_160_OFS	0x0314
-#define GIC_SH_RMASK_223_192_OFS	0x0318
-#define GIC_SH_RMASK_255_224_OFS	0x031c
-
-/* Set Mask (WO) - Enables Interrupt */
-#define GIC_SH_SMASK_31_0_OFS		0x0380
-#define GIC_SH_SMASK_63_32_OFS		0x0384
-#define GIC_SH_SMASK_95_64_OFS		0x0388
-#define GIC_SH_SMASK_127_96_OFS		0x038c
-#define GIC_SH_SMASK_159_128_OFS	0x0390
-#define GIC_SH_SMASK_191_160_OFS	0x0394
-#define GIC_SH_SMASK_223_192_OFS	0x0398
-#define GIC_SH_SMASK_255_224_OFS	0x039c
+/* Mask manipulation */
+#define GIC_SH_RMASK_OFS		0x0300
+#define GIC_SH_SMASK_OFS		0x0380
 
 /* Global Interrupt Mask Register (RO) - Bit Set == Interrupt enabled */
-#define GIC_SH_MASK_31_0_OFS		0x0400
-#define GIC_SH_MASK_63_32_OFS		0x0404
-#define GIC_SH_MASK_95_64_OFS		0x0408
-#define GIC_SH_MASK_127_96_OFS		0x040c
-#define GIC_SH_MASK_159_128_OFS		0x0410
-#define GIC_SH_MASK_191_160_OFS		0x0414
-#define GIC_SH_MASK_223_192_OFS		0x0418
-#define GIC_SH_MASK_255_224_OFS		0x041c
+#define GIC_SH_MASK_OFS			0x0400
 
 /* Pending Global Interrupts (RO) */
-#define GIC_SH_PEND_31_0_OFS		0x0480
-#define GIC_SH_PEND_63_32_OFS		0x0484
-#define GIC_SH_PEND_95_64_OFS		0x0488
-#define GIC_SH_PEND_127_96_OFS		0x048c
-#define GIC_SH_PEND_159_128_OFS		0x0490
-#define GIC_SH_PEND_191_160_OFS		0x0494
-#define GIC_SH_PEND_223_192_OFS		0x0498
-#define GIC_SH_PEND_255_224_OFS		0x049c
-
-#define GIC_SH_INTR_MAP_TO_PIN_BASE_OFS 0x0500
+#define GIC_SH_PEND_OFS			0x0480
 
 /* Maps Interrupt X to a Pin */
+#define GIC_SH_INTR_MAP_TO_PIN_BASE_OFS 0x0500
 #define GIC_SH_MAP_TO_PIN(intr)		(4 * (intr))
 
-#define GIC_SH_INTR_MAP_TO_VPE_BASE_OFS 0x2000
-
 /* Maps Interrupt X to a VPE */
+#define GIC_SH_INTR_MAP_TO_VPE_BASE_OFS 0x2000
 #define GIC_SH_MAP_TO_VPE_REG_OFF(intr, vpe) \
 	((32 * (intr)) + (((vpe) / 32) * 4))
 #define GIC_SH_MAP_TO_VPE_REG_BIT(vpe)	(1 << ((vpe) % 32))
 
-/* Convert an interrupt number to a byte offset/bit for multi-word registers */
-#define GIC_INTR_OFS(intr) (((intr) / 32)*4)
-#define GIC_INTR_BIT(intr) ((intr) % 32)
-
-/* Polarity : Reset Value is always 0 */
-#define GIC_SH_SET_POLARITY_OFS		0x0100
-
-/* Triggering : Reset Value is always 0 */
-#define GIC_SH_SET_TRIGGER_OFS		0x0180
-
-/* Dual edge triggering : Reset Value is always 0 */
-#define GIC_SH_SET_DUAL_OFS		0x0200
-
-/* Mask manipulation */
-#define GIC_SH_SMASK_OFS		0x0380
-#define GIC_SH_RMASK_OFS		0x0300
-
 /* Register Map for Local Section */
 #define GIC_VPE_CTL_OFS			0x0000
 #define GIC_VPE_PEND_OFS		0x0004
@@ -200,8 +128,8 @@
 #define GIC_SH_CONFIG_NUMVPES_SHF	0
 #define GIC_SH_CONFIG_NUMVPES_MSK	(MSK(8) << GIC_SH_CONFIG_NUMVPES_SHF)
 
-#define GIC_SH_WEDGE_SET(intr)		(intr | (0x1 << 31))
-#define GIC_SH_WEDGE_CLR(intr)		(intr & ~(0x1 << 31))
+#define GIC_SH_WEDGE_SET(intr)		((intr) | (0x1 << 31))
+#define GIC_SH_WEDGE_CLR(intr)		((intr) & ~(0x1 << 31))
 
 #define GIC_MAP_TO_PIN_SHF		31
 #define GIC_MAP_TO_PIN_MSK		(MSK(1) << GIC_MAP_TO_PIN_SHF)
@@ -278,10 +206,10 @@
 #define GIC_CPU_PIN_OFFSET	2
 
 /* Add 2 to convert non-EIC hardware interrupt to EIC vector number. */
-#define GIC_CPU_TO_VEC_OFFSET	(2)
+#define GIC_CPU_TO_VEC_OFFSET	2
 
 /* Mapped interrupt to pin X, then GIC will generate the vector (X+1). */
-#define GIC_PIN_TO_VEC_OFFSET	(1)
+#define GIC_PIN_TO_VEC_OFFSET	1
 
 /* Local GIC interrupts. */
 #define GIC_LOCAL_INT_WD	0 /* GIC watchdog */
@@ -301,9 +229,6 @@
 #define GIC_SHARED_TO_HWIRQ(x)	(GIC_SHARED_HWIRQ_BASE + (x))
 #define GIC_HWIRQ_TO_SHARED(x)	((x) - GIC_SHARED_HWIRQ_BASE)
 
-#include <linux/clocksource.h>
-#include <linux/irq.h>
-
 extern unsigned int gic_present;
 extern unsigned int gic_frequency;
 
@@ -322,4 +247,4 @@ extern unsigned int plat_ipi_resched_int_xlate(unsigned int);
 extern unsigned int gic_get_timer_pending(void);
 extern int gic_get_c0_compare_int(void);
 extern int gic_get_c0_perfcount_int(void);
-#endif /* _ASM_GICREGS_H */
+#endif /* __LINUX_IRQCHIP_MIPS_GIC_H */
-- 
cgit v1.2.3-70-g09d2


From b0854514537e4e2f0a599ca05d18fe95dcd3ee42 Mon Sep 17 00:00:00 2001
From: Andrew Bresticker <abrestic@chromium.org>
Date: Mon, 20 Oct 2014 12:04:01 -0700
Subject: clocksource: mips-gic: Move gic_frequency to clocksource driver

There's no reason for gic_frequency to be global any more and it
certainly doesn't belong in the GIC irqchip driver, so move it to
the GIC clocksource driver.

Signed-off-by: Andrew Bresticker <abrestic@chromium.org>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jason Cooper <jason@lakedaemon.net>
Cc: Paul Burton <paul.burton@imgtec.com>
Cc: Qais Yousef <qais.yousef@imgtec.com>
Cc: John Crispin <blogic@openwrt.org>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8137/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/mti-malta/malta-time.c     | 2 ++
 drivers/clocksource/mips-gic-timer.c | 3 +++
 drivers/irqchip/irq-mips-gic.c       | 1 -
 include/linux/irqchip/mips-gic.h     | 1 -
 4 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c
index 028fae07700..ce02dbdedc6 100644
--- a/arch/mips/mti-malta/malta-time.c
+++ b/arch/mips/mti-malta/malta-time.c
@@ -46,6 +46,8 @@ static int mips_cpu_timer_irq;
 static int mips_cpu_perf_irq;
 extern int cp0_perfcount_irq;
 
+static unsigned int gic_frequency;
+
 static void mips_timer_dispatch(void)
 {
 	do_IRQ(mips_cpu_timer_irq);
diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c
index 2603f50e570..bced17d2d2c 100644
--- a/drivers/clocksource/mips-gic-timer.c
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -17,6 +17,7 @@
 
 static DEFINE_PER_CPU(struct clock_event_device, gic_clockevent_device);
 static int gic_timer_irq_installed;
+static unsigned int gic_frequency;
 
 static int gic_next_event(unsigned long delta, struct clock_event_device *evt)
 {
@@ -112,6 +113,8 @@ static struct clocksource gic_clocksource = {
 
 void __init gic_clocksource_init(unsigned int frequency)
 {
+	gic_frequency = frequency;
+
 	/* Set clocksource mask. */
 	gic_clocksource.mask = CLOCKSOURCE_MASK(gic_get_count_width());
 
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index cb674696810..7ec3c18f133 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -18,7 +18,6 @@
 #include <asm/setup.h>
 #include <asm/traps.h>
 
-unsigned int gic_frequency;
 unsigned int gic_present;
 
 struct gic_pcpu_mask {
diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h
index 0350effb7cc..420f77b34d0 100644
--- a/include/linux/irqchip/mips-gic.h
+++ b/include/linux/irqchip/mips-gic.h
@@ -230,7 +230,6 @@
 #define GIC_HWIRQ_TO_SHARED(x)	((x) - GIC_SHARED_HWIRQ_BASE)
 
 extern unsigned int gic_present;
-extern unsigned int gic_frequency;
 
 extern void gic_init(unsigned long gic_base_addr,
 	unsigned long gic_addrspace_size, unsigned int cpu_vec,
-- 
cgit v1.2.3-70-g09d2


From 2ff404005e9f94ee3d05b6b0dac8204c1fcc2346 Mon Sep 17 00:00:00 2001
From: Andrew Bresticker <abrestic@chromium.org>
Date: Wed, 12 Nov 2014 11:43:37 -0800
Subject: of: Add binding document for MIPS GIC

The Global Interrupt Controller (GIC) present on certain MIPS systems
can be used to route external interrupts to individual VPEs and CPU
interrupt vectors.  It also supports a timer and software-generated
interrupts.

Signed-off-by: Andrew Bresticker <abrestic@chromium.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Pawel Moll <pawel.moll@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ian Campbell <ijc+devicetree@hellion.org.uk>
Cc: Kumar Gala <galak@codeaurora.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jason Cooper <jason@lakedaemon.net>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: John Crispin <blogic@openwrt.org>
Cc: David Daney <ddaney.cavm@gmail.com>
Cc: Qais Yousef <qais.yousef@imgtec.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: linux-mips@linux-mips.org
Cc: devicetree@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/8420/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 .../bindings/interrupt-controller/mips-gic.txt     | 55 ++++++++++++++++++++++
 .../dt-bindings/interrupt-controller/mips-gic.h    |  9 ++++
 2 files changed, 64 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/interrupt-controller/mips-gic.txt
 create mode 100644 include/dt-bindings/interrupt-controller/mips-gic.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/interrupt-controller/mips-gic.txt b/Documentation/devicetree/bindings/interrupt-controller/mips-gic.txt
new file mode 100644
index 00000000000..5a65478e5d4
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/mips-gic.txt
@@ -0,0 +1,55 @@
+MIPS Global Interrupt Controller (GIC)
+
+The MIPS GIC routes external interrupts to individual VPEs and IRQ pins.
+It also supports local (per-processor) interrupts and software-generated
+interrupts which can be used as IPIs.  The GIC also includes a free-running
+global timer, per-CPU count/compare timers, and a watchdog.
+
+Required properties:
+- compatible : Should be "mti,gic".
+- interrupt-controller : Identifies the node as an interrupt controller
+- #interrupt-cells : Specifies the number of cells needed to encode an
+  interrupt specifier.  Should be 3.
+  - The first cell is the type of interrupt, local or shared.
+    See <include/dt-bindings/interrupt-controller/mips-gic.h>.
+  - The second cell is the GIC interrupt number.
+  - The third cell encodes the interrupt flags.
+    See <include/dt-bindings/interrupt-controller/irq.h> for a list of valid
+    flags.
+
+Optional properties:
+- reg : Base address and length of the GIC registers.  If not present,
+  the base address reported by the hardware GCR_GIC_BASE will be used.
+- mti,reserved-cpu-vectors : Specifies the list of CPU interrupt vectors
+  to which the GIC may not route interrupts.  Valid values are 2 - 7.
+  This property is ignored if the CPU is started in EIC mode.
+
+Required properties for timer sub-node:
+- compatible : Should be "mti,gic-timer".
+- interrupts : Interrupt for the GIC local timer.
+- clock-frequency : Clock frequency at which the GIC timers operate.
+
+Example:
+
+	gic: interrupt-controller@1bdc0000 {
+		compatible = "mti,gic";
+		reg = <0x1bdc0000 0x20000>;
+
+		interrupt-controller;
+		#interrupt-cells = <3>;
+
+		mti,reserved-cpu-vectors = <7>;
+
+		timer {
+			compatible = "mti,gic-timer";
+			interrupts = <GIC_LOCAL 1 IRQ_TYPE_NONE>;
+			clock-frequency = <50000000>;
+		};
+	};
+
+	uart@18101400 {
+		...
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SHARED 24 IRQ_TYPE_LEVEL_HIGH>;
+		...
+	};
diff --git a/include/dt-bindings/interrupt-controller/mips-gic.h b/include/dt-bindings/interrupt-controller/mips-gic.h
new file mode 100644
index 00000000000..cf35a577e37
--- /dev/null
+++ b/include/dt-bindings/interrupt-controller/mips-gic.h
@@ -0,0 +1,9 @@
+#ifndef _DT_BINDINGS_INTERRUPT_CONTROLLER_MIPS_GIC_H
+#define _DT_BINDINGS_INTERRUPT_CONTROLLER_MIPS_GIC_H
+
+#include <dt-bindings/interrupt-controller/irq.h>
+
+#define GIC_SHARED 0
+#define GIC_LOCAL 1
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From 227158db160449b6513d2e31894a135104b90e90 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 6 Apr 2014 18:47:38 -0400
Subject: new helper: skb_copy_and_csum_datagram_msg()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/skbuff.h | 5 +++++
 net/ipv4/udp.c         | 5 ++---
 net/ipv6/raw.c         | 2 +-
 net/ipv6/udp.c         | 2 +-
 4 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 78c299f40ba..cbe4b2078b3 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2651,6 +2651,11 @@ static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
 }
 int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, int hlen,
 				     struct iovec *iov);
+static inline int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen,
+			    struct msghdr *msg)
+{
+	return skb_copy_and_csum_datagram_iovec(skb, hlen, msg->msg_iov);
+}
 int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
 				 const struct iovec *from, int from_offset,
 				 int len);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 4a16b912907..b2d606833ce 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1284,9 +1284,8 @@ try_again:
 		err = skb_copy_datagram_msg(skb, sizeof(struct udphdr),
 					    msg, copied);
 	else {
-		err = skb_copy_and_csum_datagram_iovec(skb,
-						       sizeof(struct udphdr),
-						       msg->msg_iov);
+		err = skb_copy_and_csum_datagram_msg(skb, sizeof(struct udphdr),
+						     msg);
 
 		if (err == -EINVAL)
 			goto csum_copy_err;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 0cbcf98f2ca..8baa53e17a3 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -492,7 +492,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 			goto csum_copy_err;
 		err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	} else {
-		err = skb_copy_and_csum_datagram_iovec(skb, 0, msg->msg_iov);
+		err = skb_copy_and_csum_datagram_msg(skb, 0, msg);
 		if (err == -EINVAL)
 			goto csum_copy_err;
 	}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index dbc0b042bdd..7cfb5d745a2 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -428,7 +428,7 @@ try_again:
 		err = skb_copy_datagram_msg(skb, sizeof(struct udphdr),
 					    msg, copied);
 	else {
-		err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov);
+		err = skb_copy_and_csum_datagram_msg(skb, sizeof(struct udphdr), msg);
 		if (err == -EINVAL)
 			goto csum_copy_err;
 	}
-- 
cgit v1.2.3-70-g09d2


From 6ce8e9ce5989ae13f493062975304700be86d20e Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 6 Apr 2014 21:25:44 -0400
Subject: new helper: memcpy_from_msg()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 crypto/algif_skcipher.c     | 10 +++++-----
 drivers/isdn/mISDN/socket.c |  2 +-
 drivers/net/ppp/pppoe.c     |  2 +-
 include/linux/skbuff.h      |  5 +++++
 include/net/sctp/sm.h       |  2 +-
 net/appletalk/ddp.c         |  2 +-
 net/ax25/af_ax25.c          |  2 +-
 net/bluetooth/hci_sock.c    |  2 +-
 net/bluetooth/mgmt.c        |  2 +-
 net/bluetooth/rfcomm/sock.c |  2 +-
 net/bluetooth/sco.c         |  2 +-
 net/caif/caif_socket.c      |  4 ++--
 net/can/bcm.c               | 19 ++++++++-----------
 net/can/raw.c               |  2 +-
 net/dccp/proto.c            |  2 +-
 net/decnet/af_decnet.c      |  2 +-
 net/ieee802154/dgram.c      |  2 +-
 net/ieee802154/raw.c        |  2 +-
 net/ipv4/ping.c             |  2 +-
 net/ipv4/tcp_input.c        |  2 +-
 net/irda/af_irda.c          |  6 +++---
 net/iucv/af_iucv.c          |  2 +-
 net/key/af_key.c            |  2 +-
 net/l2tp/l2tp_ip.c          |  2 +-
 net/l2tp/l2tp_ppp.c         |  3 +--
 net/llc/af_llc.c            |  2 +-
 net/netlink/af_netlink.c    |  2 +-
 net/netrom/af_netrom.c      |  2 +-
 net/nfc/llcp_commands.c     |  4 ++--
 net/nfc/rawsock.c           |  2 +-
 net/packet/af_packet.c      |  5 ++---
 net/phonet/datagram.c       |  2 +-
 net/phonet/pep.c            |  2 +-
 net/rose/af_rose.c          |  2 +-
 net/sctp/sm_make_chunk.c    |  4 ++--
 net/x25/af_x25.c            |  2 +-
 36 files changed, 57 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 83187f497c7..c3b482bee20 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -298,9 +298,9 @@ static int skcipher_sendmsg(struct kiocb *unused, struct socket *sock,
 			len = min_t(unsigned long, len,
 				    PAGE_SIZE - sg->offset - sg->length);
 
-			err = memcpy_fromiovec(page_address(sg_page(sg)) +
-					       sg->offset + sg->length,
-					       msg->msg_iov, len);
+			err = memcpy_from_msg(page_address(sg_page(sg)) +
+					      sg->offset + sg->length,
+					      msg, len);
 			if (err)
 				goto unlock;
 
@@ -337,8 +337,8 @@ static int skcipher_sendmsg(struct kiocb *unused, struct socket *sock,
 			if (!sg_page(sg + i))
 				goto unlock;
 
-			err = memcpy_fromiovec(page_address(sg_page(sg + i)),
-					       msg->msg_iov, plen);
+			err = memcpy_from_msg(page_address(sg_page(sg + i)),
+					      msg, plen);
 			if (err) {
 				__free_page(sg_page(sg + i));
 				sg_assign_page(sg + i, NULL);
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index dcbd8589f0c..84b35925ee4 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -203,7 +203,7 @@ mISDN_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	if (!skb)
 		goto done;
 
-	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
+	if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
 		err = -EFAULT;
 		goto done;
 	}
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 443cbbf5c55..d2408a5e43a 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -869,7 +869,7 @@ static int pppoe_sendmsg(struct kiocb *iocb, struct socket *sock,
 	ph = (struct pppoe_hdr *)skb_put(skb, total_len + sizeof(struct pppoe_hdr));
 	start = (char *)&ph->tag[0];
 
-	error = memcpy_fromiovec(start, m->msg_iov, total_len);
+	error = memcpy_from_msg(start, m, total_len);
 	if (error < 0) {
 		kfree_skb(skb);
 		goto end;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index cbe4b2078b3..97dc5f8123b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2687,6 +2687,11 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len);
 int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
 
+static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len)
+{
+	return memcpy_fromiovec(data, msg->msg_iov, len);
+}
+
 struct skb_checksum_ops {
 	__wsum (*update)(const void *mem, int len, __wsum wsum);
 	__wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len);
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 72a31db47de..487ef34bbd6 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -219,7 +219,7 @@ struct sctp_chunk *sctp_make_abort_no_data(const struct sctp_association *,
 				      const struct sctp_chunk *,
 				      __u32 tsn);
 struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *,
-					const struct msghdr *, size_t msg_len);
+					struct msghdr *, size_t msg_len);
 struct sctp_chunk *sctp_make_abort_violation(const struct sctp_association *,
 				   const struct sctp_chunk *,
 				   const __u8 *,
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 425942db17f..0d0766ea5ab 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1659,7 +1659,7 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 
 	SOCK_DEBUG(sk, "SK %p: Copy user data (%Zd bytes).\n", sk, len);
 
-	err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	err = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (err) {
 		kfree_skb(skb);
 		err = -EFAULT;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index f4f835e1937..ca049a7c928 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1549,7 +1549,7 @@ static int ax25_sendmsg(struct kiocb *iocb, struct socket *sock,
 	skb_reserve(skb, size - len);
 
 	/* User data follows immediately after the AX.25 data */
-	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
+	if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
 		err = -EFAULT;
 		kfree_skb(skb);
 		goto out;
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 5e2cd253597..2c245fdf319 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -947,7 +947,7 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	if (!skb)
 		goto done;
 
-	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
+	if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
 		err = -EFAULT;
 		goto drop;
 	}
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index cbeef5f62f3..f3e4a16fb15 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -5767,7 +5767,7 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	if (!buf)
 		return -ENOMEM;
 
-	if (memcpy_fromiovec(buf, msg->msg_iov, msglen)) {
+	if (memcpy_from_msg(buf, msg, msglen)) {
 		err = -EFAULT;
 		goto done;
 	}
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 8bbbb5ec468..2348176401a 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -588,7 +588,7 @@ static int rfcomm_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 		}
 		skb_reserve(skb, RFCOMM_SKB_HEAD_RESERVE);
 
-		err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
+		err = memcpy_from_msg(skb_put(skb, size), msg, size);
 		if (err) {
 			kfree_skb(skb);
 			if (sent == 0)
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 7ee9e4ab00f..30e5ea3f1ad 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -285,7 +285,7 @@ static int sco_send_frame(struct sock *sk, struct msghdr *msg, int len)
 	if (!skb)
 		return err;
 
-	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
+	if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
 		kfree_skb(skb);
 		return -EFAULT;
 	}
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index fbcd156099f..230f14026c1 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -566,7 +566,7 @@ static int caif_seqpkt_sendmsg(struct kiocb *kiocb, struct socket *sock,
 
 	skb_reserve(skb, cf_sk->headroom);
 
-	ret = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	ret = memcpy_from_msg(skb_put(skb, len), msg, len);
 
 	if (ret)
 		goto err;
@@ -641,7 +641,7 @@ static int caif_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		 */
 		size = min_t(int, size, skb_tailroom(skb));
 
-		err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
+		err = memcpy_from_msg(skb_put(skb, size), msg, size);
 		if (err) {
 			kfree_skb(skb);
 			goto out_err;
diff --git a/net/can/bcm.c b/net/can/bcm.c
index dcb75c0e66c..b9a1f715df1 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -858,8 +858,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 		/* update can_frames content */
 		for (i = 0; i < msg_head->nframes; i++) {
-			err = memcpy_fromiovec((u8 *)&op->frames[i],
-					       msg->msg_iov, CFSIZ);
+			err = memcpy_from_msg((u8 *)&op->frames[i], msg, CFSIZ);
 
 			if (op->frames[i].can_dlc > 8)
 				err = -EINVAL;
@@ -894,8 +893,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			op->frames = &op->sframe;
 
 		for (i = 0; i < msg_head->nframes; i++) {
-			err = memcpy_fromiovec((u8 *)&op->frames[i],
-					       msg->msg_iov, CFSIZ);
+			err = memcpy_from_msg((u8 *)&op->frames[i], msg, CFSIZ);
 
 			if (op->frames[i].can_dlc > 8)
 				err = -EINVAL;
@@ -1024,9 +1022,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 		if (msg_head->nframes) {
 			/* update can_frames content */
-			err = memcpy_fromiovec((u8 *)op->frames,
-					       msg->msg_iov,
-					       msg_head->nframes * CFSIZ);
+			err = memcpy_from_msg((u8 *)op->frames, msg,
+					      msg_head->nframes * CFSIZ);
 			if (err < 0)
 				return err;
 
@@ -1072,8 +1069,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		}
 
 		if (msg_head->nframes) {
-			err = memcpy_fromiovec((u8 *)op->frames, msg->msg_iov,
-					       msg_head->nframes * CFSIZ);
+			err = memcpy_from_msg((u8 *)op->frames, msg,
+					      msg_head->nframes * CFSIZ);
 			if (err < 0) {
 				if (op->frames != &op->sframe)
 					kfree(op->frames);
@@ -1209,7 +1206,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk)
 
 	can_skb_reserve(skb);
 
-	err = memcpy_fromiovec(skb_put(skb, CFSIZ), msg->msg_iov, CFSIZ);
+	err = memcpy_from_msg(skb_put(skb, CFSIZ), msg, CFSIZ);
 	if (err < 0) {
 		kfree_skb(skb);
 		return err;
@@ -1285,7 +1282,7 @@ static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 	/* read message head information */
 
-	ret = memcpy_fromiovec((u8 *)&msg_head, msg->msg_iov, MHSIZ);
+	ret = memcpy_from_msg((u8 *)&msg_head, msg, MHSIZ);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/can/raw.c b/net/can/raw.c
index 081e81fd017..0e4004fb687 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -703,7 +703,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock,
 	can_skb_reserve(skb);
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 
-	err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
+	err = memcpy_from_msg(skb_put(skb, size), msg, size);
 	if (err < 0)
 		goto free_skb;
 
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 8e6ae9422a7..19f03873908 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -781,7 +781,7 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		goto out_release;
 
 	skb_reserve(skb, sk->sk_prot->max_header);
-	rc = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (rc != 0)
 		goto out_discard;
 
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 25733d53814..e2e2e3cb911 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -2032,7 +2032,7 @@ static int dn_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 		skb_reserve(skb, 64 + DN_MAX_NSP_DATA_HEADER);
 
-		if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
+		if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
 			err = -EFAULT;
 			goto out;
 		}
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
index b8555ec7138..2c7a93e7167 100644
--- a/net/ieee802154/dgram.c
+++ b/net/ieee802154/dgram.c
@@ -276,7 +276,7 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk,
 	if (err < 0)
 		goto out_skb;
 
-	err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
+	err = memcpy_from_msg(skb_put(skb, size), msg, size);
 	if (err < 0)
 		goto out_skb;
 
diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c
index 21c38945ab8..61e9d297294 100644
--- a/net/ieee802154/raw.c
+++ b/net/ieee802154/raw.c
@@ -150,7 +150,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk,
 	skb_reset_mac_header(skb);
 	skb_reset_network_header(skb);
 
-	err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
+	err = memcpy_from_msg(skb_put(skb, size), msg, size);
 	if (err < 0)
 		goto out_skb;
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index ce2920f5bef..ef8f6ee9047 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -660,7 +660,7 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
 	 *	Fetch the ICMP header provided by the userland.
 	 *	iovec is modified! The ICMP header is consumed.
 	 */
-	if (memcpy_fromiovec(user_icmph, msg->msg_iov, icmph_len))
+	if (memcpy_from_msg(user_icmph, msg, icmph_len))
 		return -EFAULT;
 
 	if (family == AF_INET) {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d22a31f27ab..69de1a1c05c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4368,7 +4368,7 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 	if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
 		goto err_free;
 
-	if (memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size))
+	if (memcpy_from_msg(skb_put(skb, size), msg, size))
 		goto err_free;
 
 	TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index e8c40905592..9052462cf42 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1319,7 +1319,7 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock,
 	skb_reserve(skb, self->max_header_size + 16);
 	skb_reset_transport_header(skb);
 	skb_put(skb, len);
-	err = memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len);
+	err = memcpy_from_msg(skb_transport_header(skb), msg, len);
 	if (err) {
 		kfree_skb(skb);
 		goto out_err;
@@ -1569,7 +1569,7 @@ static int irda_sendmsg_dgram(struct kiocb *iocb, struct socket *sock,
 
 	pr_debug("%s(), appending user data\n", __func__);
 	skb_put(skb, len);
-	err = memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len);
+	err = memcpy_from_msg(skb_transport_header(skb), msg, len);
 	if (err) {
 		kfree_skb(skb);
 		goto out;
@@ -1678,7 +1678,7 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 
 	pr_debug("%s(), appending user data\n", __func__);
 	skb_put(skb, len);
-	err = memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len);
+	err = memcpy_from_msg(skb_transport_header(skb), msg, len);
 	if (err) {
 		kfree_skb(skb);
 		goto out;
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 057b5647ef9..1cd3f810723 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1122,7 +1122,7 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	}
 	if (iucv->transport == AF_IUCV_TRANS_HIPER)
 		skb_reserve(skb, sizeof(struct af_iucv_trans_hdr) + ETH_HLEN);
-	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
+	if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
 		err = -EFAULT;
 		goto fail;
 	}
diff --git a/net/key/af_key.c b/net/key/af_key.c
index e5883091a8c..f8ac939d52b 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3611,7 +3611,7 @@ static int pfkey_sendmsg(struct kiocb *kiocb,
 		goto out;
 
 	err = -EFAULT;
-	if (memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len))
+	if (memcpy_from_msg(skb_put(skb,len), msg, len))
 		goto out;
 
 	hdr = pfkey_get_base_msg(skb, &err);
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index a6cc1fed2b5..05dfc8aa36a 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -441,7 +441,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 	*((__be32 *) skb_put(skb, 4)) = 0;
 
 	/* Copy user data into skb */
-	rc = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (rc < 0) {
 		kfree_skb(skb);
 		goto error;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index c559bcdf467..cc7a828fc91 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -346,8 +346,7 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh
 	skb_put(skb, 2);
 
 	/* Copy user data into skb */
-	error = memcpy_fromiovec(skb_put(skb, total_len), m->msg_iov,
-				 total_len);
+	error = memcpy_from_msg(skb_put(skb, total_len), m, total_len);
 	if (error < 0) {
 		kfree_skb(skb);
 		goto error_put_sess_tun;
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index af662669f95..2c0b83ce43b 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -921,7 +921,7 @@ static int llc_ui_sendmsg(struct kiocb *iocb, struct socket *sock,
 	skb->dev      = llc->dev;
 	skb->protocol = llc_proto_type(addr->sllc_arphrd);
 	skb_reserve(skb, hdrlen);
-	rc = memcpy_fromiovec(skb_put(skb, copied), msg->msg_iov, copied);
+	rc = memcpy_from_msg(skb_put(skb, copied), msg, copied);
 	if (rc)
 		goto out;
 	if (sk->sk_type == SOCK_DGRAM || addr->sllc_ua) {
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index e1aad6eeac1..63aa5c8acf1 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2325,7 +2325,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	NETLINK_CB(skb).flags	= netlink_skb_flags;
 
 	err = -EFAULT;
-	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
+	if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
 		kfree_skb(skb);
 		goto out;
 	}
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 7e13f6afcd1..69f1d5e9959 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1113,7 +1113,7 @@ static int nr_sendmsg(struct kiocb *iocb, struct socket *sock,
 	skb_put(skb, len);
 
 	/* User data follows immediately after the NET/ROM transport header */
-	if (memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len)) {
+	if (memcpy_from_msg(skb_transport_header(skb), msg, len)) {
 		kfree_skb(skb);
 		err = -EFAULT;
 		goto out;
diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c
index a3ad69a4c64..c4da0c2d8a1 100644
--- a/net/nfc/llcp_commands.c
+++ b/net/nfc/llcp_commands.c
@@ -665,7 +665,7 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock,
 	if (msg_data == NULL)
 		return -ENOMEM;
 
-	if (memcpy_fromiovec(msg_data, msg->msg_iov, len)) {
+	if (memcpy_from_msg(msg_data, msg, len)) {
 		kfree(msg_data);
 		return -EFAULT;
 	}
@@ -731,7 +731,7 @@ int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap,
 	if (msg_data == NULL)
 		return -ENOMEM;
 
-	if (memcpy_fromiovec(msg_data, msg->msg_iov, len)) {
+	if (memcpy_from_msg(msg_data, msg, len)) {
 		kfree(msg_data);
 		return -EFAULT;
 	}
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index 9d7d2b7ba5e..373e138c0ab 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -231,7 +231,7 @@ static int rawsock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	if (skb == NULL)
 		return rc;
 
-	rc = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (rc < 0) {
 		kfree_skb(skb);
 		return rc;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 58af58026dd..07ac95014ec 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1676,7 +1676,7 @@ retry:
 			if (len < hhlen)
 				skb_reset_network_header(skb);
 		}
-		err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+		err = memcpy_from_msg(skb_put(skb, len), msg, len);
 		if (err)
 			goto out_free;
 		goto retry;
@@ -2446,8 +2446,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 		len -= vnet_hdr_len;
 
-		err = memcpy_fromiovec((void *)&vnet_hdr, msg->msg_iov,
-				       vnet_hdr_len);
+		err = memcpy_from_msg((void *)&vnet_hdr, msg, vnet_hdr_len);
 		if (err < 0)
 			goto out_unlock;
 
diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c
index 0918bc21eae..26054b4b467 100644
--- a/net/phonet/datagram.c
+++ b/net/phonet/datagram.c
@@ -109,7 +109,7 @@ static int pn_sendmsg(struct kiocb *iocb, struct sock *sk,
 		return err;
 	skb_reserve(skb, MAX_PHONET_HEADER);
 
-	err = memcpy_fromiovec((void *)skb_put(skb, len), msg->msg_iov, len);
+	err = memcpy_from_msg((void *)skb_put(skb, len), msg, len);
 	if (err < 0) {
 		kfree_skb(skb);
 		return err;
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 9cd069dfaf6..5d3f2b7507d 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -1141,7 +1141,7 @@ static int pep_sendmsg(struct kiocb *iocb, struct sock *sk,
 		return err;
 
 	skb_reserve(skb, MAX_PHONET_HEADER + 3 + pn->aligned);
-	err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	err = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (err < 0)
 		goto outfree;
 
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 9b600c20a7a..43bac7c4dd9 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1121,7 +1121,7 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock,
 	skb_reset_transport_header(skb);
 	skb_put(skb, len);
 
-	err = memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len);
+	err = memcpy_from_msg(skb_transport_header(skb), msg, len);
 	if (err) {
 		kfree_skb(skb);
 		return err;
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 9f32741abb1..e49bccebb0c 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1001,7 +1001,7 @@ no_mem:
 
 /* Helper to create ABORT with a SCTP_ERROR_USER_ABORT error.  */
 struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *asoc,
-					const struct msghdr *msg,
+					struct msghdr *msg,
 					size_t paylen)
 {
 	struct sctp_chunk *retval;
@@ -1018,7 +1018,7 @@ struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *asoc,
 		if (!payload)
 			goto err_payload;
 
-		err = memcpy_fromiovec(payload, msg->msg_iov, paylen);
+		err = memcpy_from_msg(payload, msg, paylen);
 		if (err < 0)
 			goto err_copy;
 	}
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 59e785bfde6..d9149b68b9b 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1170,7 +1170,7 @@ static int x25_sendmsg(struct kiocb *iocb, struct socket *sock,
 	skb_reset_transport_header(skb);
 	skb_put(skb, len);
 
-	rc = memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len);
+	rc = memcpy_from_msg(skb_transport_header(skb), msg, len);
 	if (rc)
 		goto out_kfree_skb;
 
-- 
cgit v1.2.3-70-g09d2


From e169371823827dae1fd1d15bceb0fe5497c1a5ba Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 6 Apr 2014 21:28:01 -0400
Subject: switch ipxrtr_route_packet() from iovec to msghdr

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/net/ipx.h   | 2 +-
 net/ipx/af_ipx.c    | 3 +--
 net/ipx/ipx_route.c | 4 ++--
 3 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/ipx.h b/include/net/ipx.h
index 320f47b64a7..e5cff6811b3 100644
--- a/include/net/ipx.h
+++ b/include/net/ipx.h
@@ -150,7 +150,7 @@ int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc,
 		     unsigned char *node);
 void ipxrtr_del_routes(struct ipx_interface *intrfc);
 int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx,
-			struct iovec *iov, size_t len, int noblock);
+			struct msghdr *msg, size_t len, int noblock);
 int ipxrtr_route_skb(struct sk_buff *skb);
 struct ipx_route *ipxrtr_lookup(__be32 net);
 int ipxrtr_ioctl(unsigned int cmd, void __user *arg);
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 97dc4320ac1..f11ad1d95e0 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1745,8 +1745,7 @@ static int ipx_sendmsg(struct kiocb *iocb, struct socket *sock,
 		memcpy(usipx->sipx_node, ipxs->dest_addr.node, IPX_NODE_LEN);
 	}
 
-	rc = ipxrtr_route_packet(sk, usipx, msg->msg_iov, len,
-				 flags & MSG_DONTWAIT);
+	rc = ipxrtr_route_packet(sk, usipx, msg, len, flags & MSG_DONTWAIT);
 	if (rc >= 0)
 		rc = len;
 out:
diff --git a/net/ipx/ipx_route.c b/net/ipx/ipx_route.c
index 67e7ad3d46b..3e2a32a9f3b 100644
--- a/net/ipx/ipx_route.c
+++ b/net/ipx/ipx_route.c
@@ -165,7 +165,7 @@ int ipxrtr_route_skb(struct sk_buff *skb)
  * Route an outgoing frame from a socket.
  */
 int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx,
-			struct iovec *iov, size_t len, int noblock)
+			struct msghdr *msg, size_t len, int noblock)
 {
 	struct sk_buff *skb;
 	struct ipx_sock *ipxs = ipx_sk(sk);
@@ -229,7 +229,7 @@ int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx,
 	memcpy(ipx->ipx_dest.node, usipx->sipx_node, IPX_NODE_LEN);
 	ipx->ipx_dest.sock		= usipx->sipx_port;
 
-	rc = memcpy_fromiovec(skb_put(skb, len), iov, len);
+	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (rc) {
 		kfree_skb(skb);
 		goto out_put;
-- 
cgit v1.2.3-70-g09d2


From 7eab8d9e8a722ca07bc785f73e21c3d3418defa6 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 6 Apr 2014 21:51:23 -0400
Subject: new helper: memcpy_to_msg()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 crypto/algif_hash.c    | 2 +-
 include/linux/skbuff.h | 5 +++++
 net/caif/caif_socket.c | 2 +-
 net/can/bcm.c          | 2 +-
 net/can/raw.c          | 2 +-
 net/decnet/af_decnet.c | 2 +-
 net/ipv4/tcp.c         | 2 +-
 net/irda/af_irda.c     | 2 +-
 net/packet/af_packet.c | 3 +--
 9 files changed, 13 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 850246206b1..35c93ff11f3 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -174,7 +174,7 @@ static int hash_recvmsg(struct kiocb *unused, struct socket *sock,
 			goto unlock;
 	}
 
-	err = memcpy_toiovec(msg->msg_iov, ctx->result, len);
+	err = memcpy_to_msg(msg, ctx->result, len);
 
 unlock:
 	release_sock(sk);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 97dc5f8123b..d048347a010 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2692,6 +2692,11 @@ static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len)
 	return memcpy_fromiovec(data, msg->msg_iov, len);
 }
 
+static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len)
+{
+	return memcpy_toiovec(msg->msg_iov, data, len);
+}
+
 struct skb_checksum_ops {
 	__wsum (*update)(const void *mem, int len, __wsum wsum);
 	__wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len);
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 230f14026c1..ac618b0b8a4 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -418,7 +418,7 @@ unlock:
 		}
 		release_sock(sk);
 		chunk = min_t(unsigned int, skb->len, size);
-		if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
+		if (memcpy_to_msg(msg, skb->data, chunk)) {
 			skb_queue_head(&sk->sk_receive_queue, skb);
 			if (copied == 0)
 				copied = -EFAULT;
diff --git a/net/can/bcm.c b/net/can/bcm.c
index b9a1f715df1..01671187e3f 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1555,7 +1555,7 @@ static int bcm_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (skb->len < size)
 		size = skb->len;
 
-	err = memcpy_toiovec(msg->msg_iov, skb->data, size);
+	err = memcpy_to_msg(msg, skb->data, size);
 	if (err < 0) {
 		skb_free_datagram(sk, skb);
 		return err;
diff --git a/net/can/raw.c b/net/can/raw.c
index 0e4004fb687..dfdcffbb107 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -750,7 +750,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock,
 	else
 		size = skb->len;
 
-	err = memcpy_toiovec(msg->msg_iov, skb->data, size);
+	err = memcpy_to_msg(msg, skb->data, size);
 	if (err < 0) {
 		skb_free_datagram(sk, skb);
 		return err;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index e2e2e3cb911..810228646de 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1760,7 +1760,7 @@ static int dn_recvmsg(struct kiocb *iocb, struct socket *sock,
 		if ((chunk + copied) > size)
 			chunk = size - copied;
 
-		if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
+		if (memcpy_to_msg(msg, skb->data, chunk)) {
 			rv = -EFAULT;
 			break;
 		}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c239f4740d1..435443bfc3c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1349,7 +1349,7 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
 
 		if (len > 0) {
 			if (!(flags & MSG_TRUNC))
-				err = memcpy_toiovec(msg->msg_iov, &c, 1);
+				err = memcpy_to_msg(msg, &c, 1);
 			len = 1;
 		} else
 			msg->msg_flags |= MSG_TRUNC;
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 9052462cf42..568edc72d73 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1466,7 +1466,7 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
 		}
 
 		chunk = min_t(unsigned int, skb->len, size);
-		if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
+		if (memcpy_to_msg(msg, skb->data, chunk)) {
 			skb_queue_head(&sk->sk_receive_queue, skb);
 			if (copied == 0)
 				copied = -EFAULT;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 07ac95014ec..108d7f381b8 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2949,8 +2949,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 			vnet_hdr.flags = VIRTIO_NET_HDR_F_DATA_VALID;
 		} /* else everything is zero */
 
-		err = memcpy_toiovec(msg->msg_iov, (void *)&vnet_hdr,
-				     vnet_hdr_len);
+		err = memcpy_to_msg(msg, (void *)&vnet_hdr, vnet_hdr_len);
 		if (err < 0)
 			goto out_free;
 	}
-- 
cgit v1.2.3-70-g09d2


From 3a654f975bf99165016fe257a3d2b4e6716e4931 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 19 Jun 2014 14:15:22 -0400
Subject: new helpers: skb_copy_datagram_from_iter() and
 zerocopy_sg_from_iter()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/skbuff.h |   3 ++
 net/core/datagram.c    | 116 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 119 insertions(+)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d048347a010..a01cd9ad0b5 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2659,10 +2659,13 @@ static inline int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen,
 int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
 				 const struct iovec *from, int from_offset,
 				 int len);
+int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
+				 struct iov_iter *from, int len);
 int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *frm,
 			   int offset, size_t count);
 int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
 			   struct iov_iter *to, int size);
+int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm);
 void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
 void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb);
 int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 26391a3fe3e..3ea038431ce 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -572,6 +572,78 @@ fault:
 }
 EXPORT_SYMBOL(skb_copy_datagram_from_iovec);
 
+int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
+				 struct iov_iter *from,
+				 int len)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+	struct sk_buff *frag_iter;
+
+	/* Copy header. */
+	if (copy > 0) {
+		if (copy > len)
+			copy = len;
+		if (copy_from_iter(skb->data + offset, copy, from) != copy)
+			goto fault;
+		if ((len -= copy) == 0)
+			return 0;
+		offset += copy;
+	}
+
+	/* Copy paged appendix. Hmm... why does this look so complicated? */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_frag_size(frag);
+		if ((copy = end - offset) > 0) {
+			size_t copied;
+
+			if (copy > len)
+				copy = len;
+			copied = copy_page_from_iter(skb_frag_page(frag),
+					  frag->page_offset + offset - start,
+					  copy, from);
+			if (copied != copy)
+				goto fault;
+
+			if (!(len -= copy))
+				return 0;
+			offset += copy;
+		}
+		start = end;
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		if ((copy = end - offset) > 0) {
+			if (copy > len)
+				copy = len;
+			if (skb_copy_datagram_from_iter(frag_iter,
+							offset - start,
+							from, copy))
+				goto fault;
+			if ((len -= copy) == 0)
+				return 0;
+			offset += copy;
+		}
+		start = end;
+	}
+	if (!len)
+		return 0;
+
+fault:
+	return -EFAULT;
+}
+EXPORT_SYMBOL(skb_copy_datagram_from_iter);
+
 /**
  *	zerocopy_sg_from_iovec - Build a zerocopy datagram from an iovec
  *	@skb: buffer to copy
@@ -643,6 +715,50 @@ int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
 }
 EXPORT_SYMBOL(zerocopy_sg_from_iovec);
 
+int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
+{
+	int len = iov_iter_count(from);
+	int copy = min_t(int, skb_headlen(skb), len);
+	int frag = 0;
+
+	/* copy up to skb headlen */
+	if (skb_copy_datagram_from_iter(skb, 0, from, copy))
+		return -EFAULT;
+
+	while (iov_iter_count(from)) {
+		struct page *pages[MAX_SKB_FRAGS];
+		size_t start;
+		ssize_t copied;
+		unsigned long truesize;
+		int n = 0;
+
+		if (frag == MAX_SKB_FRAGS)
+			return -EMSGSIZE;
+
+		copied = iov_iter_get_pages(from, pages, ~0U,
+					    MAX_SKB_FRAGS - frag, &start);
+		if (copied < 0)
+			return -EFAULT;
+
+		iov_iter_advance(from, copied);
+
+		truesize = PAGE_ALIGN(copied + start);
+		skb->data_len += copied;
+		skb->len += copied;
+		skb->truesize += truesize;
+		atomic_add(truesize, &skb->sk->sk_wmem_alloc);
+		while (copied) {
+			int size = min_t(int, copied, PAGE_SIZE - start);
+			skb_fill_page_desc(skb, frag++, pages[n], start, size);
+			start = 0;
+			copied -= size;
+			n++;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL(zerocopy_sg_from_iter);
+
 static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 				      u8 __user *to, int len,
 				      __wsum *csump)
-- 
cgit v1.2.3-70-g09d2


From 195e952d03a797aa953f62ffe24ec58693e17ed8 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 6 Nov 2014 00:56:48 -0500
Subject: kill zerocopy_sg_from_iovec()

no users left

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/skbuff.h |  2 --
 net/core/datagram.c    | 65 ++------------------------------------------------
 2 files changed, 2 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a01cd9ad0b5..178cdbde82f 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2661,8 +2661,6 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
 				 int len);
 int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 				 struct iov_iter *from, int len);
-int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *frm,
-			   int offset, size_t count);
 int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
 			   struct iov_iter *to, int size);
 int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 3ea038431ce..c4d832efebb 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -645,76 +645,15 @@ fault:
 EXPORT_SYMBOL(skb_copy_datagram_from_iter);
 
 /**
- *	zerocopy_sg_from_iovec - Build a zerocopy datagram from an iovec
+ *	zerocopy_sg_from_iter - Build a zerocopy datagram from an iov_iter
  *	@skb: buffer to copy
- *	@from: io vector to copy from
- *	@offset: offset in the io vector to start copying from
- *	@count: amount of vectors to copy to buffer from
+ *	@from: the source to copy from
  *
  *	The function will first copy up to headlen, and then pin the userspace
  *	pages and build frags through them.
  *
  *	Returns 0, -EFAULT or -EMSGSIZE.
- *	Note: the iovec is not modified during the copy
  */
-int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
-				  int offset, size_t count)
-{
-	int len = iov_length(from, count) - offset;
-	int copy = min_t(int, skb_headlen(skb), len);
-	int size;
-	int i = 0;
-
-	/* copy up to skb headlen */
-	if (skb_copy_datagram_from_iovec(skb, 0, from, offset, copy))
-		return -EFAULT;
-
-	if (len == copy)
-		return 0;
-
-	offset += copy;
-	while (count--) {
-		struct page *page[MAX_SKB_FRAGS];
-		int num_pages;
-		unsigned long base;
-		unsigned long truesize;
-
-		/* Skip over from offset and copied */
-		if (offset >= from->iov_len) {
-			offset -= from->iov_len;
-			++from;
-			continue;
-		}
-		len = from->iov_len - offset;
-		base = (unsigned long)from->iov_base + offset;
-		size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
-		if (i + size > MAX_SKB_FRAGS)
-			return -EMSGSIZE;
-		num_pages = get_user_pages_fast(base, size, 0, &page[i]);
-		if (num_pages != size) {
-			release_pages(&page[i], num_pages, 0);
-			return -EFAULT;
-		}
-		truesize = size * PAGE_SIZE;
-		skb->data_len += len;
-		skb->len += len;
-		skb->truesize += truesize;
-		atomic_add(truesize, &skb->sk->sk_wmem_alloc);
-		while (len) {
-			int off = base & ~PAGE_MASK;
-			int size = min_t(int, len, PAGE_SIZE - off);
-			skb_fill_page_desc(skb, i, page[i], off, size);
-			base += size;
-			len -= size;
-			i++;
-		}
-		offset = 0;
-		++from;
-	}
-	return 0;
-}
-EXPORT_SYMBOL(zerocopy_sg_from_iovec);
-
 int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
 {
 	int len = iov_iter_count(from);
-- 
cgit v1.2.3-70-g09d2


From 8feb2fb2bb986c533e18037d3c45a5f779421992 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 6 Nov 2014 01:10:59 -0500
Subject: switch AF_PACKET and AF_UNIX to skb_copy_datagram_from_iter()

... and kill skb_copy_datagram_iovec()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/skbuff.h |  3 --
 net/core/datagram.c    | 88 ++------------------------------------------------
 net/packet/af_packet.c | 11 +++++--
 net/unix/af_unix.c     | 11 +++++--
 4 files changed, 18 insertions(+), 95 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 178cdbde82f..7691ad5b477 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2656,9 +2656,6 @@ static inline int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen,
 {
 	return skb_copy_and_csum_datagram_iovec(skb, hlen, msg->msg_iov);
 }
-int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
-				 const struct iovec *from, int from_offset,
-				 int len);
 int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 				 struct iov_iter *from, int len);
 int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
diff --git a/net/core/datagram.c b/net/core/datagram.c
index c4d832efebb..b6e303b0f01 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -480,98 +480,14 @@ short_copy:
 EXPORT_SYMBOL(skb_copy_datagram_iter);
 
 /**
- *	skb_copy_datagram_from_iovec - Copy a datagram from an iovec.
+ *	skb_copy_datagram_from_iter - Copy a datagram from an iov_iter.
  *	@skb: buffer to copy
  *	@offset: offset in the buffer to start copying to
- *	@from: io vector to copy to
- *	@from_offset: offset in the io vector to start copying from
+ *	@from: the copy source
  *	@len: amount of data to copy to buffer from iovec
  *
  *	Returns 0 or -EFAULT.
- *	Note: the iovec is not modified during the copy.
  */
-int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
-				 const struct iovec *from, int from_offset,
-				 int len)
-{
-	int start = skb_headlen(skb);
-	int i, copy = start - offset;
-	struct sk_buff *frag_iter;
-
-	/* Copy header. */
-	if (copy > 0) {
-		if (copy > len)
-			copy = len;
-		if (memcpy_fromiovecend(skb->data + offset, from, from_offset,
-					copy))
-			goto fault;
-		if ((len -= copy) == 0)
-			return 0;
-		offset += copy;
-		from_offset += copy;
-	}
-
-	/* Copy paged appendix. Hmm... why does this look so complicated? */
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		int end;
-		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
-		WARN_ON(start > offset + len);
-
-		end = start + skb_frag_size(frag);
-		if ((copy = end - offset) > 0) {
-			int err;
-			u8  *vaddr;
-			struct page *page = skb_frag_page(frag);
-
-			if (copy > len)
-				copy = len;
-			vaddr = kmap(page);
-			err = memcpy_fromiovecend(vaddr + frag->page_offset +
-						  offset - start,
-						  from, from_offset, copy);
-			kunmap(page);
-			if (err)
-				goto fault;
-
-			if (!(len -= copy))
-				return 0;
-			offset += copy;
-			from_offset += copy;
-		}
-		start = end;
-	}
-
-	skb_walk_frags(skb, frag_iter) {
-		int end;
-
-		WARN_ON(start > offset + len);
-
-		end = start + frag_iter->len;
-		if ((copy = end - offset) > 0) {
-			if (copy > len)
-				copy = len;
-			if (skb_copy_datagram_from_iovec(frag_iter,
-							 offset - start,
-							 from,
-							 from_offset,
-							 copy))
-				goto fault;
-			if ((len -= copy) == 0)
-				return 0;
-			offset += copy;
-			from_offset += copy;
-		}
-		start = end;
-	}
-	if (!len)
-		return 0;
-
-fault:
-	return -EFAULT;
-}
-EXPORT_SYMBOL(skb_copy_datagram_from_iovec);
-
 int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 				 struct iov_iter *from,
 				 int len)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 108d7f381b8..dfb148e9fda 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2408,6 +2408,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	unsigned short gso_type = 0;
 	int hlen, tlen;
 	int extra_len = 0;
+	struct iov_iter from;
+	ssize_t n;
+
+	iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, len);
 
 	/*
 	 *	Get and verify the address.
@@ -2446,8 +2450,9 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 		len -= vnet_hdr_len;
 
-		err = memcpy_from_msg((void *)&vnet_hdr, msg, vnet_hdr_len);
-		if (err < 0)
+		err = -EFAULT;
+		n = copy_from_iter(&vnet_hdr, vnet_hdr_len, &from);
+		if (n != vnet_hdr_len)
 			goto out_unlock;
 
 		if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
@@ -2517,7 +2522,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	}
 
 	/* Returns -EFAULT on error */
-	err = skb_copy_datagram_from_iovec(skb, offset, msg->msg_iov, 0, len);
+	err = skb_copy_datagram_from_iter(skb, offset, &from, len);
 	if (err)
 		goto out_free;
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5eee625d113..4450d622660 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1459,6 +1459,9 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	struct scm_cookie tmp_scm;
 	int max_level;
 	int data_len = 0;
+	struct iov_iter from;
+
+	iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, len);
 
 	if (NULL == siocb->scm)
 		siocb->scm = &tmp_scm;
@@ -1516,7 +1519,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	skb_put(skb, len - data_len);
 	skb->data_len = data_len;
 	skb->len = len;
-	err = skb_copy_datagram_from_iovec(skb, 0, msg->msg_iov, 0, len);
+	err = skb_copy_datagram_from_iter(skb, 0, &from, len);
 	if (err)
 		goto out_free;
 
@@ -1638,6 +1641,9 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	bool fds_sent = false;
 	int max_level;
 	int data_len;
+	struct iov_iter from;
+
+	iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, len);
 
 	if (NULL == siocb->scm)
 		siocb->scm = &tmp_scm;
@@ -1694,8 +1700,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		skb_put(skb, size - data_len);
 		skb->data_len = data_len;
 		skb->len = size;
-		err = skb_copy_datagram_from_iovec(skb, 0, msg->msg_iov,
-						   sent, size);
+		err = skb_copy_datagram_from_iter(skb, 0, &from, size);
 		if (err) {
 			kfree_skb(skb);
 			goto out_err;
-- 
cgit v1.2.3-70-g09d2


From e0eb093e794452791b0f932a0120f410f614ad82 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 15 Nov 2014 01:11:23 -0500
Subject: switch sctp_user_addto_chunk() and sctp_datamsg_from_user() to
 passing iov_iter

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/net/sctp/structs.h |  6 +++---
 net/sctp/chunk.c           |  9 ++++-----
 net/sctp/sm_make_chunk.c   | 16 ++++++++--------
 net/sctp/socket.c          |  5 ++++-
 4 files changed, 19 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 806e3b5b335..2bb2fcf5b11 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -531,7 +531,7 @@ struct sctp_datamsg {
 
 struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *,
 					    struct sctp_sndrcvinfo *,
-					    struct msghdr *, int len);
+					    struct iov_iter *);
 void sctp_datamsg_free(struct sctp_datamsg *);
 void sctp_datamsg_put(struct sctp_datamsg *);
 void sctp_chunk_fail(struct sctp_chunk *, int error);
@@ -647,8 +647,8 @@ struct sctp_chunk {
 
 void sctp_chunk_hold(struct sctp_chunk *);
 void sctp_chunk_put(struct sctp_chunk *);
-int sctp_user_addto_chunk(struct sctp_chunk *chunk, int off, int len,
-			  struct iovec *data);
+int sctp_user_addto_chunk(struct sctp_chunk *chunk, int len,
+			  struct iov_iter *from);
 void sctp_chunk_free(struct sctp_chunk *);
 void  *sctp_addto_chunk(struct sctp_chunk *, int len, const void *data);
 struct sctp_chunk *sctp_chunkify(struct sk_buff *,
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index 158701da2d3..a3380917f19 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -164,7 +164,7 @@ static void sctp_datamsg_assign(struct sctp_datamsg *msg, struct sctp_chunk *chu
  */
 struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 					    struct sctp_sndrcvinfo *sinfo,
-					    struct msghdr *msgh, int msg_len)
+					    struct iov_iter *from)
 {
 	int max, whole, i, offset, over, err;
 	int len, first_len;
@@ -172,6 +172,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 	struct sctp_chunk *chunk;
 	struct sctp_datamsg *msg;
 	struct list_head *pos, *temp;
+	size_t msg_len = iov_iter_count(from);
 	__u8 frag;
 
 	msg = sctp_datamsg_new(GFP_KERNEL);
@@ -279,12 +280,10 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 			goto errout;
 		}
 
-		err = sctp_user_addto_chunk(chunk, offset, len, msgh->msg_iov);
+		err = sctp_user_addto_chunk(chunk, len, from);
 		if (err < 0)
 			goto errout_chunk_free;
 
-		offset += len;
-
 		/* Put the chunk->skb back into the form expected by send.  */
 		__skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr
 			   - (__u8 *)chunk->skb->data);
@@ -317,7 +316,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 			goto errout;
 		}
 
-		err = sctp_user_addto_chunk(chunk, offset, over, msgh->msg_iov);
+		err = sctp_user_addto_chunk(chunk, over, from);
 
 		/* Put the chunk->skb back into the form expected by send.  */
 		__skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index e49bccebb0c..e49e231cef5 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1491,26 +1491,26 @@ static void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk,
  * chunk is not big enough.
  * Returns a kernel err value.
  */
-int sctp_user_addto_chunk(struct sctp_chunk *chunk, int off, int len,
-			  struct iovec *data)
+int sctp_user_addto_chunk(struct sctp_chunk *chunk, int len,
+			  struct iov_iter *from)
 {
-	__u8 *target;
-	int err = 0;
+	void *target;
+	ssize_t copied;
 
 	/* Make room in chunk for data.  */
 	target = skb_put(chunk->skb, len);
 
 	/* Copy data (whole iovec) into chunk */
-	if ((err = memcpy_fromiovecend(target, data, off, len)))
-		goto out;
+	copied = copy_from_iter(target, len, from);
+	if (copied != len)
+		return -EFAULT;
 
 	/* Adjust the chunk length field.  */
 	chunk->chunk_hdr->length =
 		htons(ntohs(chunk->chunk_hdr->length) + len);
 	chunk->chunk_end = skb_tail_pointer(chunk->skb);
 
-out:
-	return err;
+	return 0;
 }
 
 /* Helper function to assign a TSN if needed.  This assumes that both
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 85e0b653edd..0397ac9fd98 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1609,6 +1609,9 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk,
 	__u16 sinfo_flags = 0;
 	long timeo;
 	int err;
+	struct iov_iter from;
+
+	iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, msg_len);
 
 	err = 0;
 	sp = sctp_sk(sk);
@@ -1947,7 +1950,7 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk,
 	}
 
 	/* Break the message into multiple chunks of maximum size. */
-	datamsg = sctp_datamsg_from_user(asoc, sinfo, msg, msg_len);
+	datamsg = sctp_datamsg_from_user(asoc, sinfo, &from);
 	if (IS_ERR(datamsg)) {
 		err = PTR_ERR(datamsg);
 		goto out_free;
-- 
cgit v1.2.3-70-g09d2


From 0f7db23a07af5de22940f08c3f88a0741d4df0bc Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 20 Nov 2014 04:05:34 -0500
Subject: vmci_transport: switch ->enqeue_dgram, ->enqueue_stream and
 ->dequeue_stream to msghdr

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/net/af_vsock.h         |  6 +++---
 net/vmw_vsock/af_vsock.c       |  6 +++---
 net/vmw_vsock/vmci_transport.c | 14 +++++++-------
 3 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 42827786940..0d87674fb77 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -103,14 +103,14 @@ struct vsock_transport {
 	int (*dgram_dequeue)(struct kiocb *kiocb, struct vsock_sock *vsk,
 			     struct msghdr *msg, size_t len, int flags);
 	int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *,
-			     struct iovec *, size_t len);
+			     struct msghdr *, size_t len);
 	bool (*dgram_allow)(u32 cid, u32 port);
 
 	/* STREAM. */
 	/* TODO: stream_bind() */
-	ssize_t (*stream_dequeue)(struct vsock_sock *, struct iovec *,
+	ssize_t (*stream_dequeue)(struct vsock_sock *, struct msghdr *,
 				  size_t len, int flags);
-	ssize_t (*stream_enqueue)(struct vsock_sock *, struct iovec *,
+	ssize_t (*stream_enqueue)(struct vsock_sock *, struct msghdr *,
 				  size_t len);
 	s64 (*stream_has_data)(struct vsock_sock *);
 	s64 (*stream_has_space)(struct vsock_sock *);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 85d232bed87..1d0e39c9a3e 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1013,7 +1013,7 @@ static int vsock_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		goto out;
 	}
 
-	err = transport->dgram_enqueue(vsk, remote_addr, msg->msg_iov, len);
+	err = transport->dgram_enqueue(vsk, remote_addr, msg, len);
 
 out:
 	release_sock(sk);
@@ -1617,7 +1617,7 @@ static int vsock_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		 */
 
 		written = transport->stream_enqueue(
-				vsk, msg->msg_iov,
+				vsk, msg,
 				len - total_written);
 		if (written < 0) {
 			err = -ENOMEM;
@@ -1739,7 +1739,7 @@ vsock_stream_recvmsg(struct kiocb *kiocb,
 				break;
 
 			read = transport->stream_dequeue(
-					vsk, msg->msg_iov,
+					vsk, msg,
 					len - copied, flags);
 			if (read < 0) {
 				err = -ENOMEM;
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index a57ddef7d5a..c1c03895297 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1697,7 +1697,7 @@ static int vmci_transport_dgram_bind(struct vsock_sock *vsk,
 static int vmci_transport_dgram_enqueue(
 	struct vsock_sock *vsk,
 	struct sockaddr_vm *remote_addr,
-	struct iovec *iov,
+	struct msghdr *msg,
 	size_t len)
 {
 	int err;
@@ -1714,7 +1714,7 @@ static int vmci_transport_dgram_enqueue(
 	if (!dg)
 		return -ENOMEM;
 
-	memcpy_fromiovec(VMCI_DG_PAYLOAD(dg), iov, len);
+	memcpy_from_msg(VMCI_DG_PAYLOAD(dg), msg, len);
 
 	dg->dst = vmci_make_handle(remote_addr->svm_cid,
 				   remote_addr->svm_port);
@@ -1835,22 +1835,22 @@ static int vmci_transport_connect(struct vsock_sock *vsk)
 
 static ssize_t vmci_transport_stream_dequeue(
 	struct vsock_sock *vsk,
-	struct iovec *iov,
+	struct msghdr *msg,
 	size_t len,
 	int flags)
 {
 	if (flags & MSG_PEEK)
-		return vmci_qpair_peekv(vmci_trans(vsk)->qpair, iov, len, 0);
+		return vmci_qpair_peekv(vmci_trans(vsk)->qpair, msg->msg_iov, len, 0);
 	else
-		return vmci_qpair_dequev(vmci_trans(vsk)->qpair, iov, len, 0);
+		return vmci_qpair_dequev(vmci_trans(vsk)->qpair, msg->msg_iov, len, 0);
 }
 
 static ssize_t vmci_transport_stream_enqueue(
 	struct vsock_sock *vsk,
-	struct iovec *iov,
+	struct msghdr *msg,
 	size_t len)
 {
-	return vmci_qpair_enquev(vmci_trans(vsk)->qpair, iov, len, 0);
+	return vmci_qpair_enquev(vmci_trans(vsk)->qpair, msg->msg_iov, len, 0);
 }
 
 static s64 vmci_transport_stream_has_data(struct vsock_sock *vsk)
-- 
cgit v1.2.3-70-g09d2


From c40ecc12cfdb630332198a04e2832ae8218a61f1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 13 Nov 2014 14:25:11 +0100
Subject: scsi: avoid ->change_queue_depth indirection for queue full tracking

All drivers use the implementation for ramping the queue up and down, so
instead of overloading the change_queue_depth method call the
implementation diretly if the driver opts into it by setting the
track_queue_depth flag in the host template.

Note that a few drivers validated the new queue depth in their
change_queue_depth method, but as we never go over the queue depth
set during slave_configure or the sysfs file this isn't nessecary
and can safely be removed.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Venkatesh Srinivas <venkateshs@google.com>
---
 drivers/infiniband/ulp/iser/iscsi_iser.c |  1 +
 drivers/infiniband/ulp/srp/ib_srp.c      | 20 ++++++-------
 drivers/s390/scsi/zfcp_scsi.c            | 15 ++--------
 drivers/scsi/aic94xx/aic94xx_init.c      |  1 +
 drivers/scsi/be2iscsi/be_main.c          |  2 +-
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c        |  1 +
 drivers/scsi/bnx2i/bnx2i_iscsi.c         |  1 +
 drivers/scsi/cxgbi/cxgb3i/cxgb3i.c       |  1 +
 drivers/scsi/cxgbi/cxgb4i/cxgb4i.c       |  1 +
 drivers/scsi/fcoe/fcoe.c                 |  1 +
 drivers/scsi/fnic/fnic_main.c            |  1 +
 drivers/scsi/ibmvscsi/ibmvfc.c           |  1 +
 drivers/scsi/isci/init.c                 |  1 +
 drivers/scsi/iscsi_tcp.c                 |  1 +
 drivers/scsi/libfc/fc_fcp.c              | 14 +--------
 drivers/scsi/libiscsi.c                  | 14 +--------
 drivers/scsi/libsas/sas_scsi_host.c      | 17 ++---------
 drivers/scsi/lpfc/lpfc_scsi.c            | 23 ++-------------
 drivers/scsi/mpt2sas/mpt2sas_scsih.c     | 10 ++-----
 drivers/scsi/mpt3sas/mpt3sas_scsih.c     | 10 ++-----
 drivers/scsi/mvsas/mv_init.c             |  1 +
 drivers/scsi/pm8001/pm8001_init.c        |  1 +
 drivers/scsi/qla2xxx/qla_os.c            | 48 ++-----------------------------
 drivers/scsi/qla4xxx/ql4_os.c            | 16 +++--------
 drivers/scsi/scsi_debug.c                | 49 ++++++++------------------------
 drivers/scsi/scsi_error.c                | 15 ++++------
 drivers/scsi/ufs/ufshcd.c                | 14 ++-------
 drivers/scsi/virtio_scsi.c               | 15 ++--------
 drivers/target/loopback/tcm_loop.c       | 15 ++--------
 include/scsi/scsi_host.h                 |  7 +++--
 30 files changed, 73 insertions(+), 244 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index f42ab14105a..812a2891de5 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -922,6 +922,7 @@ static struct scsi_host_template iscsi_iser_sht = {
 	.use_clustering         = DISABLE_CLUSTERING,
 	.proc_name              = "iscsi_iser",
 	.this_id                = -1,
+	.track_queue_depth	= 1,
 };
 
 static struct iscsi_transport iscsi_iser_transport = {
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 57b5ff1bbcb..98a30355893 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -2402,7 +2402,7 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event)
  * srp_change_queue_depth - setting device queue depth
  * @sdev: scsi device struct
  * @qdepth: requested queue depth
- * @reason: SCSI_QDEPTH_DEFAULT/SCSI_QDEPTH_QFULL/SCSI_QDEPTH_RAMP_UP
+ * @reason: SCSI_QDEPTH_DEFAULT
  * (see include/scsi/scsi_host.h for definition)
  *
  * Returns queue depth.
@@ -2412,18 +2412,13 @@ srp_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 {
 	struct Scsi_Host *shost = sdev->host;
 	int max_depth;
-	if (reason == SCSI_QDEPTH_DEFAULT || reason == SCSI_QDEPTH_RAMP_UP) {
-		max_depth = shost->can_queue;
-		if (!sdev->tagged_supported)
-			max_depth = 1;
-		if (qdepth > max_depth)
-			qdepth = max_depth;
-		scsi_adjust_queue_depth(sdev, qdepth);
-	} else if (reason == SCSI_QDEPTH_QFULL)
-		scsi_track_queue_full(sdev, qdepth);
-	else
-		return -EOPNOTSUPP;
 
+	max_depth = shost->can_queue;
+	if (!sdev->tagged_supported)
+		max_depth = 1;
+	if (qdepth > max_depth)
+		qdepth = max_depth;
+	scsi_adjust_queue_depth(sdev, qdepth);
 	return sdev->queue_depth;
 }
 
@@ -2766,6 +2761,7 @@ static struct scsi_host_template srp_template = {
 	.use_clustering			= ENABLE_CLUSTERING,
 	.shost_attrs			= srp_host_attrs,
 	.use_blk_tags			= 1,
+	.track_queue_depth		= 1,
 };
 
 static int srp_sdev_count(struct Scsi_Host *host)
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index b5dfa51f396..179bf3d8af6 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -35,19 +35,7 @@ MODULE_PARM_DESC(allow_lun_scan, "For NPIV, scan and attach all storage LUNs");
 static int zfcp_scsi_change_queue_depth(struct scsi_device *sdev, int depth,
 					int reason)
 {
-	switch (reason) {
-	case SCSI_QDEPTH_DEFAULT:
-		scsi_adjust_queue_depth(sdev, depth);
-		break;
-	case SCSI_QDEPTH_QFULL:
-		scsi_track_queue_full(sdev, depth);
-		break;
-	case SCSI_QDEPTH_RAMP_UP:
-		scsi_adjust_queue_depth(sdev, depth);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
+	scsi_adjust_queue_depth(sdev, depth);
 	return sdev->queue_depth;
 }
 
@@ -320,6 +308,7 @@ static struct scsi_host_template zfcp_scsi_host_template = {
 	.use_clustering		 = 1,
 	.shost_attrs		 = zfcp_sysfs_shost_attrs,
 	.sdev_attrs		 = zfcp_sysfs_sdev_attrs,
+	.track_queue_depth	 = 1,
 };
 
 /**
diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c
index 579dc2f460c..a64cf932d03 100644
--- a/drivers/scsi/aic94xx/aic94xx_init.c
+++ b/drivers/scsi/aic94xx/aic94xx_init.c
@@ -84,6 +84,7 @@ static struct scsi_host_template aic94xx_sht = {
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
 	.use_blk_tags		= 1,
+	.track_queue_depth	= 1,
 };
 
 static int asd_map_memio(struct asd_ha_struct *asd_ha)
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 30d74a06b99..d9b999a3416 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -570,7 +570,7 @@ static struct scsi_host_template beiscsi_sht = {
 	.cmd_per_lun = BEISCSI_CMD_PER_LUN,
 	.use_clustering = ENABLE_CLUSTERING,
 	.vendor_id = SCSI_NL_VID_TYPE_PCI | BE_VENDOR_ID,
-
+	.track_queue_depth = 1,
 };
 
 static struct scsi_transport_template *beiscsi_scsi_transport;
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 2262c75f45d..cc537972f3e 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -2792,6 +2792,7 @@ static struct scsi_host_template bnx2fc_shost_template = {
 	.sg_tablesize		= BNX2FC_MAX_BDS_PER_CMD,
 	.max_sectors		= 1024,
 	.use_blk_tags		= 1,
+	.track_queue_depth	= 1,
 };
 
 static struct libfc_function_template bnx2fc_libfc_fcn_templ = {
diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c
index 7a36388822a..9de1c20bb0f 100644
--- a/drivers/scsi/bnx2i/bnx2i_iscsi.c
+++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c
@@ -2268,6 +2268,7 @@ static struct scsi_host_template bnx2i_host_template = {
 	.use_clustering		= ENABLE_CLUSTERING,
 	.sg_tablesize		= ISCSI_MAX_BDS_PER_CMD,
 	.shost_attrs		= bnx2i_dev_attributes,
+	.track_queue_depth	= 1,
 };
 
 struct iscsi_transport bnx2i_iscsi_transport = {
diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
index 49692a1ac44..99ea67dcdd2 100644
--- a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
+++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
@@ -96,6 +96,7 @@ static struct scsi_host_template cxgb3i_host_template = {
 	.target_alloc	= iscsi_target_alloc,
 	.use_clustering	= DISABLE_CLUSTERING,
 	.this_id	= -1,
+	.track_queue_depth = 1,
 };
 
 static struct iscsi_transport cxgb3i_iscsi_transport = {
diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index 81bb3bd7909..af86e8f57b8 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -99,6 +99,7 @@ static struct scsi_host_template cxgb4i_host_template = {
 	.target_alloc	= iscsi_target_alloc,
 	.use_clustering	= DISABLE_CLUSTERING,
 	.this_id	= -1,
+	.track_queue_depth = 1,
 };
 
 static struct iscsi_transport cxgb4i_iscsi_transport = {
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index a3eeb684249..97229860398 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -289,6 +289,7 @@ static struct scsi_host_template fcoe_shost_template = {
 	.sg_tablesize = SG_ALL,
 	.max_sectors = 0xffff,
 	.use_blk_tags = 1,
+	.track_queue_depth = 1,
 };
 
 /**
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index 1e5706ed9a4..86b496c8633 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -120,6 +120,7 @@ static struct scsi_host_template fnic_host_template = {
 	.max_sectors = 0xffff,
 	.shost_attrs = fnic_attrs,
 	.use_blk_tags = 1,
+	.track_queue_depth = 1,
 };
 
 static void
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 147b80e07b0..381449d5be7 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -3103,6 +3103,7 @@ static struct scsi_host_template driver_template = {
 	.use_clustering = ENABLE_CLUSTERING,
 	.shost_attrs = ibmvfc_attrs,
 	.use_blk_tags = 1,
+	.track_queue_depth = 1,
 };
 
 /**
diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c
index 89756205601..a81e546595d 100644
--- a/drivers/scsi/isci/init.c
+++ b/drivers/scsi/isci/init.c
@@ -173,6 +173,7 @@ static struct scsi_host_template isci_sht = {
 	.ioctl				= sas_ioctl,
 	.shost_attrs			= isci_host_attrs,
 	.use_blk_tags			= 1,
+	.track_queue_depth		= 1,
 };
 
 static struct sas_domain_function_template isci_transport_ops  = {
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 427af0f24b0..a575d845b66 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -966,6 +966,7 @@ static struct scsi_host_template iscsi_sw_tcp_sht = {
 	.target_alloc		= iscsi_target_alloc,
 	.proc_name		= "iscsi_tcp",
 	.this_id		= -1,
+	.track_queue_depth	= 1,
 };
 
 static struct iscsi_transport iscsi_sw_tcp_transport = {
diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index bf954ee050f..0d2d024e77c 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -2173,19 +2173,7 @@ EXPORT_SYMBOL(fc_slave_alloc);
  */
 int fc_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 {
-	switch (reason) {
-	case SCSI_QDEPTH_DEFAULT:
-		scsi_adjust_queue_depth(sdev, qdepth);
-		break;
-	case SCSI_QDEPTH_QFULL:
-		scsi_track_queue_full(sdev, qdepth);
-		break;
-	case SCSI_QDEPTH_RAMP_UP:
-		scsi_adjust_queue_depth(sdev, qdepth);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
+	scsi_adjust_queue_depth(sdev, qdepth);
 	return sdev->queue_depth;
 }
 EXPORT_SYMBOL(fc_change_queue_depth);
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index d521624dedf..79e977484ad 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1773,19 +1773,7 @@ EXPORT_SYMBOL_GPL(iscsi_queuecommand);
 
 int iscsi_change_queue_depth(struct scsi_device *sdev, int depth, int reason)
 {
-	switch (reason) {
-	case SCSI_QDEPTH_DEFAULT:
-		scsi_adjust_queue_depth(sdev, depth);
-		break;
-	case SCSI_QDEPTH_QFULL:
-		scsi_track_queue_full(sdev, depth);
-		break;
-	case SCSI_QDEPTH_RAMP_UP:
-		scsi_adjust_queue_depth(sdev, depth);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
+	scsi_adjust_queue_depth(sdev, depth);
 	return sdev->queue_depth;
 }
 EXPORT_SYMBOL_GPL(iscsi_change_queue_depth);
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 89e8b687a67..914e4116513 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -961,20 +961,9 @@ int sas_change_queue_depth(struct scsi_device *sdev, int depth, int reason)
 		return __ata_change_queue_depth(dev->sata_dev.ap, sdev, depth,
 						reason);
 
-	switch (reason) {
-	case SCSI_QDEPTH_DEFAULT:
-	case SCSI_QDEPTH_RAMP_UP:
-		if (!sdev->tagged_supported)
-			depth = 1;
-		scsi_adjust_queue_depth(sdev, depth);
-		break;
-	case SCSI_QDEPTH_QFULL:
-		scsi_track_queue_full(sdev, depth);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
+	if (!sdev->tagged_supported)
+		depth = 1;
+	scsi_adjust_queue_depth(sdev, depth);
 	return depth;
 }
 
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 80351fff1a0..52285492036 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -255,26 +255,7 @@ lpfc_update_stats(struct lpfc_hba *phba, struct  lpfc_scsi_buf *lpfc_cmd)
 static int
 lpfc_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 {
-	struct lpfc_vport *vport = (struct lpfc_vport *) sdev->host->hostdata;
-
-	switch (reason) {
-	case SCSI_QDEPTH_DEFAULT:
-		/* change request from sysfs, fall through */
-	case SCSI_QDEPTH_RAMP_UP:
-		scsi_adjust_queue_depth(sdev, qdepth);
-		break;
-	case SCSI_QDEPTH_QFULL:
-		if (scsi_track_queue_full(sdev, qdepth) == 0)
-			return sdev->queue_depth;
-
-		lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP,
-				 "0711 detected queue full - lun queue "
-				 "depth adjusted to %d.\n", sdev->queue_depth);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
+	scsi_adjust_queue_depth(sdev, qdepth);
 	return sdev->queue_depth;
 }
 
@@ -5918,6 +5899,7 @@ struct scsi_host_template lpfc_template = {
 	.change_queue_depth	= lpfc_change_queue_depth,
 	.change_queue_type	= scsi_change_queue_type,
 	.use_blk_tags		= 1,
+	.track_queue_depth	= 1,
 };
 
 struct scsi_host_template lpfc_vport_template = {
@@ -5942,4 +5924,5 @@ struct scsi_host_template lpfc_vport_template = {
 	.change_queue_depth	= lpfc_change_queue_depth,
 	.change_queue_type	= scsi_change_queue_type,
 	.use_blk_tags		= 1,
+	.track_queue_depth	= 1,
 };
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index 42fef914d44..b006e1e9fcb 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -1229,7 +1229,7 @@ _scsih_adjust_queue_depth(struct scsi_device *sdev, int qdepth)
  * _scsih_change_queue_depth - setting device queue depth
  * @sdev: scsi device struct
  * @qdepth: requested queue depth
- * @reason: SCSI_QDEPTH_DEFAULT/SCSI_QDEPTH_QFULL/SCSI_QDEPTH_RAMP_UP
+ * @reason: SCSI_QDEPTH_DEFAULT
  * (see include/scsi/scsi_host.h for definition)
  *
  * Returns queue depth.
@@ -1237,12 +1237,7 @@ _scsih_adjust_queue_depth(struct scsi_device *sdev, int qdepth)
 static int
 _scsih_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 {
-	if (reason == SCSI_QDEPTH_DEFAULT || reason == SCSI_QDEPTH_RAMP_UP)
-		_scsih_adjust_queue_depth(sdev, qdepth);
-	else if (reason == SCSI_QDEPTH_QFULL)
-		scsi_track_queue_full(sdev, qdepth);
-	else
-		return -EOPNOTSUPP;
+	_scsih_adjust_queue_depth(sdev, qdepth);
 
 	if (sdev->inquiry_len > 7)
 		sdev_printk(KERN_INFO, sdev, "qdepth(%d), tagged(%d), "
@@ -7637,6 +7632,7 @@ static struct scsi_host_template scsih_driver_template = {
 	.use_clustering			= ENABLE_CLUSTERING,
 	.shost_attrs			= mpt2sas_host_attrs,
 	.sdev_attrs			= mpt2sas_dev_attrs,
+	.track_queue_depth		= 1,
 };
 
 /**
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index b23c2e7588e..568dcaed36c 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -1097,7 +1097,7 @@ _scsih_adjust_queue_depth(struct scsi_device *sdev, int qdepth)
  * _scsih_change_queue_depth - setting device queue depth
  * @sdev: scsi device struct
  * @qdepth: requested queue depth
- * @reason: SCSI_QDEPTH_DEFAULT/SCSI_QDEPTH_QFULL/SCSI_QDEPTH_RAMP_UP
+ * @reason: SCSI_QDEPTH_DEFAULT
  * (see include/scsi/scsi_host.h for definition)
  *
  * Returns queue depth.
@@ -1105,12 +1105,7 @@ _scsih_adjust_queue_depth(struct scsi_device *sdev, int qdepth)
 static int
 _scsih_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 {
-	if (reason == SCSI_QDEPTH_DEFAULT || reason == SCSI_QDEPTH_RAMP_UP)
-		_scsih_adjust_queue_depth(sdev, qdepth);
-	else if (reason == SCSI_QDEPTH_QFULL)
-		scsi_track_queue_full(sdev, qdepth);
-	else
-		return -EOPNOTSUPP;
+	_scsih_adjust_queue_depth(sdev, qdepth);
 
 	if (sdev->inquiry_len > 7)
 		sdev_printk(KERN_INFO, sdev, "qdepth(%d), tagged(%d), " \
@@ -7266,6 +7261,7 @@ static struct scsi_host_template scsih_driver_template = {
 	.use_clustering			= ENABLE_CLUSTERING,
 	.shost_attrs			= mpt3sas_host_attrs,
 	.sdev_attrs			= mpt3sas_dev_attrs,
+	.track_queue_depth		= 1,
 };
 
 /**
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index d3c1fa5e76f..ac7c0307840 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -77,6 +77,7 @@ static struct scsi_host_template mvs_sht = {
 	.ioctl			= sas_ioctl,
 	.shost_attrs		= mvst_host_attrs,
 	.use_blk_tags		= 1,
+	.track_queue_depth	= 1,
 };
 
 static struct sas_domain_function_template mvs_transport_ops = {
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index 3ff759a3b74..19ae6cab5e4 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -90,6 +90,7 @@ static struct scsi_host_template pm8001_sht = {
 	.ioctl			= sas_ioctl,
 	.shost_attrs		= pm8001_host_attrs,
 	.use_blk_tags		= 1,
+	.track_queue_depth	= 1,
 };
 
 /**
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 33166ebec7d..20049b176b6 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -270,6 +270,7 @@ struct scsi_host_template qla2xxx_driver_template = {
 
 	.supported_mode		= MODE_INITIATOR,
 	.use_blk_tags		= 1,
+	.track_queue_depth	= 1,
 };
 
 static struct scsi_transport_template *qla2xxx_transport_template = NULL;
@@ -1415,55 +1416,10 @@ qla2xxx_slave_destroy(struct scsi_device *sdev)
 	sdev->hostdata = NULL;
 }
 
-static void qla2x00_handle_queue_full(struct scsi_device *sdev, int qdepth)
-{
-	fc_port_t *fcport = (struct fc_port *) sdev->hostdata;
-
-	if (!scsi_track_queue_full(sdev, qdepth))
-		return;
-
-	ql_dbg(ql_dbg_io, fcport->vha, 0x3029,
-	    "Queue depth adjusted-down to %d for nexus=%ld:%d:%llu.\n",
-	    sdev->queue_depth, fcport->vha->host_no, sdev->id, sdev->lun);
-}
-
-static void qla2x00_adjust_sdev_qdepth_up(struct scsi_device *sdev, int qdepth)
-{
-	fc_port_t *fcport = sdev->hostdata;
-	struct scsi_qla_host *vha = fcport->vha;
-	struct req_que *req = NULL;
-
-	req = vha->req;
-	if (!req)
-		return;
-
-	if (req->max_q_depth <= sdev->queue_depth || req->max_q_depth < qdepth)
-		return;
-
-	scsi_adjust_queue_depth(sdev, qdepth);
-
-	ql_dbg(ql_dbg_io, vha, 0x302a,
-	    "Queue depth adjusted-up to %d for nexus=%ld:%d:%llu.\n",
-	    sdev->queue_depth, fcport->vha->host_no, sdev->id, sdev->lun);
-}
-
 static int
 qla2x00_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 {
-	switch (reason) {
-	case SCSI_QDEPTH_DEFAULT:
-		scsi_adjust_queue_depth(sdev, qdepth);
-		break;
-	case SCSI_QDEPTH_QFULL:
-		qla2x00_handle_queue_full(sdev, qdepth);
-		break;
-	case SCSI_QDEPTH_RAMP_UP:
-		qla2x00_adjust_sdev_qdepth_up(sdev, qdepth);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
+	scsi_adjust_queue_depth(sdev, qdepth);
 	return sdev->queue_depth;
 }
 
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index f8724f2e015..2bfde373ea2 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -164,8 +164,6 @@ static int qla4xxx_eh_host_reset(struct scsi_cmnd *cmd);
 static int qla4xxx_slave_alloc(struct scsi_device *device);
 static umode_t qla4_attr_is_visible(int param_type, int param);
 static int qla4xxx_host_reset(struct Scsi_Host *shost, int reset_type);
-static int qla4xxx_change_queue_depth(struct scsi_device *sdev, int qdepth,
-				      int reason);
 
 /*
  * iSCSI Flash DDB sysfs entry points
@@ -203,7 +201,7 @@ static struct scsi_host_template qla4xxx_driver_template = {
 	.eh_timed_out		= qla4xxx_eh_cmd_timed_out,
 
 	.slave_alloc		= qla4xxx_slave_alloc,
-	.change_queue_depth	= qla4xxx_change_queue_depth,
+	.change_queue_depth	= iscsi_change_queue_depth,
 
 	.this_id		= -1,
 	.cmd_per_lun		= 3,
@@ -9065,15 +9063,6 @@ static int qla4xxx_slave_alloc(struct scsi_device *sdev)
 	return 0;
 }
 
-static int qla4xxx_change_queue_depth(struct scsi_device *sdev, int qdepth,
-				      int reason)
-{
-	if (!ql4xqfulltracking)
-		return -EOPNOTSUPP;
-
-	return iscsi_change_queue_depth(sdev, qdepth, reason);
-}
-
 /**
  * qla4xxx_del_from_active_array - returns an active srb
  * @ha: Pointer to host adapter structure.
@@ -9873,6 +9862,9 @@ static int __init qla4xxx_module_init(void)
 {
 	int ret;
 
+	if (ql4xqfulltracking)
+		qla4xxx_driver_template.track_queue_depth = 1;
+
 	/* Allocate cache for SRBs. */
 	srb_cachep = kmem_cache_create("qla4xxx_srbs", sizeof(struct srb), 0,
 				       SLAB_HWCACHE_ALIGN, NULL);
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index fce393f3e7e..84cf82e0782 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -4472,7 +4472,6 @@ static int
 sdebug_change_qdepth(struct scsi_device *sdev, int qdepth, int reason)
 {
 	int num_in_q = 0;
-	int bad = 0;
 	unsigned long iflags;
 	struct sdebug_dev_info *devip;
 
@@ -4484,43 +4483,18 @@ sdebug_change_qdepth(struct scsi_device *sdev, int qdepth, int reason)
 	}
 	num_in_q = atomic_read(&devip->num_in_q);
 	spin_unlock_irqrestore(&queued_arr_lock, iflags);
-	if (reason == SCSI_QDEPTH_DEFAULT || reason == SCSI_QDEPTH_RAMP_UP) {
-		if (qdepth < 1)
-			qdepth = 1;
-		/* allow to exceed max host queued_arr elements for testing */
-		if (qdepth > SCSI_DEBUG_CANQUEUE + 10)
-			qdepth = SCSI_DEBUG_CANQUEUE + 10;
-		scsi_adjust_queue_depth(sdev, qdepth);
-	} else if (reason == SCSI_QDEPTH_QFULL)
-		scsi_track_queue_full(sdev, qdepth);
-	else
-		bad = 1;
-	if (bad)
-		sdev_printk(KERN_WARNING, sdev,
-			    "%s: unknown reason=0x%x\n", __func__, reason);
+
+	if (qdepth < 1)
+		qdepth = 1;
+	/* allow to exceed max host queued_arr elements for testing */
+	if (qdepth > SCSI_DEBUG_CANQUEUE + 10)
+		qdepth = SCSI_DEBUG_CANQUEUE + 10;
+	scsi_adjust_queue_depth(sdev, qdepth);
+
 	if (SCSI_DEBUG_OPT_Q_NOISE & scsi_debug_opts) {
-		if (SCSI_QDEPTH_QFULL == reason)
-			sdev_printk(KERN_INFO, sdev,
-			    "%s: -> %d, num_in_q=%d, reason: queue full\n",
-				    __func__, qdepth, num_in_q);
-		else {
-			const char *cp;
-
-			switch (reason) {
-			case SCSI_QDEPTH_DEFAULT:
-				cp = "default (sysfs ?)";
-				break;
-			case SCSI_QDEPTH_RAMP_UP:
-				cp = "ramp up";
-				break;
-			default:
-				cp = "unknown";
-				break;
-			}
-			sdev_printk(KERN_INFO, sdev,
-				    "%s: qdepth=%d, num_in_q=%d, reason: %s\n",
-				    __func__, qdepth, num_in_q, cp);
-		}
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: qdepth=%d, num_in_q=%d\n",
+			    __func__, qdepth, num_in_q);
 	}
 	return sdev->queue_depth;
 }
@@ -4576,6 +4550,7 @@ static struct scsi_host_template sdebug_driver_template = {
 	.max_sectors =		-1U,
 	.use_clustering = 	DISABLE_CLUSTERING,
 	.module =		THIS_MODULE,
+	.track_queue_depth =	1,
 };
 
 static int sdebug_driver_probe(struct device * dev)
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index a6f6b9222b5..2d0f5155ee5 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -610,7 +610,7 @@ static void scsi_handle_queue_ramp_up(struct scsi_device *sdev)
 	struct scsi_host_template *sht = sdev->host->hostt;
 	struct scsi_device *tmp_sdev;
 
-	if (!sht->change_queue_depth ||
+	if (!sht->track_queue_depth ||
 	    sdev->queue_depth >= sdev->max_queue_depth)
 		return;
 
@@ -631,12 +631,8 @@ static void scsi_handle_queue_ramp_up(struct scsi_device *sdev)
 		    tmp_sdev->id != sdev->id ||
 		    tmp_sdev->queue_depth == sdev->max_queue_depth)
 			continue;
-		/*
-		 * call back into LLD to increase queue_depth by one
-		 * with ramp up reason code.
-		 */
-		sht->change_queue_depth(tmp_sdev, tmp_sdev->queue_depth + 1,
-					SCSI_QDEPTH_RAMP_UP);
+
+		scsi_adjust_queue_depth(tmp_sdev, tmp_sdev->queue_depth + 1);
 		sdev->last_queue_ramp_up = jiffies;
 	}
 }
@@ -646,7 +642,7 @@ static void scsi_handle_queue_full(struct scsi_device *sdev)
 	struct scsi_host_template *sht = sdev->host->hostt;
 	struct scsi_device *tmp_sdev;
 
-	if (!sht->change_queue_depth)
+	if (!sht->track_queue_depth)
 		return;
 
 	shost_for_each_device(tmp_sdev, sdev->host) {
@@ -658,8 +654,7 @@ static void scsi_handle_queue_full(struct scsi_device *sdev)
 		 * the device when we got the queue full so we start
 		 * from the highest possible value and work our way down.
 		 */
-		sht->change_queue_depth(tmp_sdev, tmp_sdev->queue_depth - 1,
-					SCSI_QDEPTH_QFULL);
+		scsi_track_queue_full(tmp_sdev, tmp_sdev->queue_depth - 1);
 	}
 }
 
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 362b818ad82..e96ab253e3e 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -2800,18 +2800,7 @@ static int ufshcd_change_queue_depth(struct scsi_device *sdev,
 	if (depth > hba->nutrs)
 		depth = hba->nutrs;
 
-	switch (reason) {
-	case SCSI_QDEPTH_DEFAULT:
-	case SCSI_QDEPTH_RAMP_UP:
-		scsi_adjust_queue_depth(sdev, depth);
-		break;
-	case SCSI_QDEPTH_QFULL:
-		scsi_track_queue_full(sdev, depth);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
+	scsi_adjust_queue_depth(sdev, depth);
 	return depth;
 }
 
@@ -4231,6 +4220,7 @@ static struct scsi_host_template ufshcd_driver_template = {
 	.can_queue		= UFSHCD_CAN_QUEUE,
 	.max_host_blocked	= 1,
 	.use_blk_tags		= 1,
+	.track_queue_depth	= 1,
 };
 
 static int ufshcd_config_vreg_load(struct device *dev, struct ufs_vreg *vreg,
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 8e40347da0a..0f7e4c7ff8c 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -691,18 +691,7 @@ static int virtscsi_change_queue_depth(struct scsi_device *sdev,
 	struct Scsi_Host *shost = sdev->host;
 	int max_depth = shost->cmd_per_lun;
 
-	switch (reason) {
-	case SCSI_QDEPTH_QFULL: /* Drop qdepth in response to BUSY state */
-		scsi_track_queue_full(sdev, qdepth);
-		break;
-	case SCSI_QDEPTH_RAMP_UP: /* Raise qdepth after BUSY state resolved */
-	case SCSI_QDEPTH_DEFAULT: /* Manual change via sysfs */
-		scsi_adjust_queue_depth(sdev, min(max_depth, qdepth));
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
+	scsi_adjust_queue_depth(sdev, min(max_depth, qdepth));
 	return sdev->queue_depth;
 }
 
@@ -770,6 +759,7 @@ static struct scsi_host_template virtscsi_host_template_single = {
 	.use_clustering = ENABLE_CLUSTERING,
 	.target_alloc = virtscsi_target_alloc,
 	.target_destroy = virtscsi_target_destroy,
+	.track_queue_depth = 1,
 };
 
 static struct scsi_host_template virtscsi_host_template_multi = {
@@ -788,6 +778,7 @@ static struct scsi_host_template virtscsi_host_template_multi = {
 	.use_clustering = ENABLE_CLUSTERING,
 	.target_alloc = virtscsi_target_alloc,
 	.target_destroy = virtscsi_target_destroy,
+	.track_queue_depth = 1,
 };
 
 #define virtscsi_config_get(vdev, fld) \
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 0ed96644ec9..670b75a6224 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -119,19 +119,7 @@ static int tcm_loop_change_queue_depth(
 	int depth,
 	int reason)
 {
-	switch (reason) {
-	case SCSI_QDEPTH_DEFAULT:
-		scsi_adjust_queue_depth(sdev, depth);
-		break;
-	case SCSI_QDEPTH_QFULL:
-		scsi_track_queue_full(sdev, depth);
-		break;
-	case SCSI_QDEPTH_RAMP_UP:
-		scsi_adjust_queue_depth(sdev, depth);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
+	scsi_adjust_queue_depth(sdev, depth);
 	return sdev->queue_depth;
 }
 
@@ -423,6 +411,7 @@ static struct scsi_host_template tcm_loop_driver_template = {
 	.slave_alloc		= tcm_loop_slave_alloc,
 	.module			= THIS_MODULE,
 	.use_blk_tags		= 1,
+	.track_queue_depth	= 1,
 };
 
 static int tcm_loop_driver_probe(struct device *dev)
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 61a81bf77e2..a0b13a5cd25 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -48,8 +48,6 @@ struct blk_queue_tags;
 
 enum {
 	SCSI_QDEPTH_DEFAULT,	/* default requested change, e.g. from sysfs */
-	SCSI_QDEPTH_QFULL,	/* scsi-ml requested due to queue full */
-	SCSI_QDEPTH_RAMP_UP,	/* scsi-ml requested due to threshold event */
 };
 
 struct scsi_host_template {
@@ -426,6 +424,11 @@ struct scsi_host_template {
 	 */
 	unsigned use_blk_tags:1;
 
+	/*
+	 * Track QUEUE_FULL events and reduce queue depth on demand.
+	 */
+	unsigned track_queue_depth:1;
+
 	/*
 	 * This specifies the mode that a LLD supports.
 	 */
-- 
cgit v1.2.3-70-g09d2


From db5ed4dfd5dd0142ec36ff7b335e0ec3b836b3e6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 13 Nov 2014 15:08:42 +0100
Subject: scsi: drop reason argument from ->change_queue_depth

Drop the now unused reason argument from the ->change_queue_depth method.
Also add a return value to scsi_adjust_queue_depth, and rename it to
scsi_change_queue_depth now that it can be used as the default
->change_queue_depth implementation.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 Documentation/scsi/scsi_mid_low_api.txt   | 20 +++++++--------
 drivers/ata/libata-scsi.c                 | 17 ++++---------
 drivers/ata/sata_nv.c                     |  2 +-
 drivers/infiniband/ulp/iser/iscsi_iser.c  |  2 +-
 drivers/infiniband/ulp/srp/ib_srp.c       |  7 ++----
 drivers/message/fusion/mptscsih.c         | 12 +++------
 drivers/message/fusion/mptscsih.h         |  3 +--
 drivers/s390/scsi/zfcp_scsi.c             | 11 ++-------
 drivers/scsi/3w-9xxx.c                    | 13 +---------
 drivers/scsi/3w-sas.c                     | 13 +---------
 drivers/scsi/3w-xxxx.c                    | 13 +---------
 drivers/scsi/53c700.c                     | 19 ++++++--------
 drivers/scsi/BusLogic.c                   |  4 +--
 drivers/scsi/aacraid/linit.c              | 18 ++++++--------
 drivers/scsi/advansys.c                   |  8 +++---
 drivers/scsi/aic7xxx/aic79xx_osm.c        |  4 +--
 drivers/scsi/aic7xxx/aic7xxx_osm.c        |  4 +--
 drivers/scsi/arcmsr/arcmsr_hba.c          |  9 ++-----
 drivers/scsi/be2iscsi/be_main.c           |  2 +-
 drivers/scsi/bfa/bfad_im.c                |  4 +--
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c         |  2 +-
 drivers/scsi/bnx2i/bnx2i_iscsi.c          |  2 +-
 drivers/scsi/csiostor/csio_scsi.c         |  2 +-
 drivers/scsi/cxgbi/cxgb3i/cxgb3i.c        |  2 +-
 drivers/scsi/cxgbi/cxgb4i/cxgb4i.c        |  2 +-
 drivers/scsi/dpt_i2o.c                    |  2 +-
 drivers/scsi/eata.c                       |  6 ++---
 drivers/scsi/esas2r/esas2r.h              |  1 -
 drivers/scsi/esas2r/esas2r_main.c         | 11 +--------
 drivers/scsi/esp_scsi.c                   |  2 +-
 drivers/scsi/fcoe/fcoe.c                  |  2 +-
 drivers/scsi/fnic/fnic_main.c             |  4 +--
 drivers/scsi/hpsa.c                       | 16 +-----------
 drivers/scsi/hptiop.c                     |  8 ++----
 drivers/scsi/ibmvscsi/ibmvfc.c            |  9 ++-----
 drivers/scsi/ibmvscsi/ibmvscsi.c          | 10 ++------
 drivers/scsi/ipr.c                        | 10 +++-----
 drivers/scsi/ips.c                        |  2 +-
 drivers/scsi/iscsi_tcp.c                  |  2 +-
 drivers/scsi/libfc/fc_fcp.c               | 15 +----------
 drivers/scsi/libiscsi.c                   |  7 ------
 drivers/scsi/libsas/sas_scsi_host.c       | 12 ++++-----
 drivers/scsi/lpfc/lpfc_scsi.c             | 26 +++-----------------
 drivers/scsi/megaraid/megaraid_mbox.c     | 21 +---------------
 drivers/scsi/megaraid/megaraid_sas_base.c | 13 +---------
 drivers/scsi/mpt2sas/mpt2sas_scsih.c      | 10 +++-----
 drivers/scsi/mpt3sas/mpt3sas_scsih.c      | 10 +++-----
 drivers/scsi/ncr53c8xx.c                  |  2 +-
 drivers/scsi/pmcraid.c                    | 12 ++-------
 drivers/scsi/qla1280.c                    |  4 +--
 drivers/scsi/qla2xxx/qla_os.c             | 12 ++-------
 drivers/scsi/qla4xxx/ql4_os.c             |  4 +--
 drivers/scsi/scsi.c                       | 41 +++++++++++--------------------
 drivers/scsi/scsi_debug.c                 |  4 +--
 drivers/scsi/scsi_error.c                 |  2 +-
 drivers/scsi/scsi_scan.c                  |  2 +-
 drivers/scsi/scsi_sysfs.c                 |  3 +--
 drivers/scsi/storvsc_drv.c                |  2 +-
 drivers/scsi/sym53c8xx_2/sym_glue.c       |  2 +-
 drivers/scsi/tmscsim.c                    |  2 +-
 drivers/scsi/u14-34f.c                    | 10 ++++----
 drivers/scsi/ufs/ufshcd.c                 | 13 +++-------
 drivers/scsi/virtio_scsi.c                |  8 ++----
 drivers/scsi/vmw_pvscsi.c                 | 12 ++-------
 drivers/scsi/wd7000.c                     |  1 -
 drivers/target/loopback/tcm_loop.c        | 15 +----------
 drivers/usb/storage/uas.c                 |  2 +-
 include/linux/libata.h                    |  4 +--
 include/scsi/libfc.h                      |  1 -
 include/scsi/libiscsi.h                   |  2 --
 include/scsi/libsas.h                     |  3 +--
 include/scsi/scsi_device.h                |  2 +-
 include/scsi/scsi_host.h                  |  8 ++----
 73 files changed, 155 insertions(+), 412 deletions(-)

(limited to 'include')

diff --git a/Documentation/scsi/scsi_mid_low_api.txt b/Documentation/scsi/scsi_mid_low_api.txt
index bee7d86b9dc..731bc4f4c5e 100644
--- a/Documentation/scsi/scsi_mid_low_api.txt
+++ b/Documentation/scsi/scsi_mid_low_api.txt
@@ -149,7 +149,7 @@ scsi_add_host()  ---->
 scsi_scan_host()  -------+
                          |
                     slave_alloc()
-                    slave_configure() -->  scsi_adjust_queue_depth()
+                    slave_configure() -->  scsi_change_queue_depth()
                          |
                     slave_alloc()
                     slave_configure()
@@ -159,7 +159,7 @@ scsi_scan_host()  -------+
 ------------------------------------------------------------
 
 If the LLD wants to adjust the default queue settings, it can invoke
-scsi_adjust_queue_depth() in its slave_configure() routine.
+scsi_change_queue_depth() in its slave_configure() routine.
 
 *** For scsi devices that the mid level tries to scan but do not
     respond, a slave_alloc(), slave_destroy() pair is called.
@@ -203,7 +203,7 @@ LLD                   mid level                    LLD
 scsi_add_device()  ------+
                          |
                     slave_alloc()
-                    slave_configure()   [--> scsi_adjust_queue_depth()]
+                    slave_configure()   [--> scsi_change_queue_depth()]
 ------------------------------------------------------------
 
 In a similar fashion, an LLD may become aware that a SCSI device has been
@@ -261,7 +261,7 @@ init_this_scsi_driver() ----+
                             |                scsi_register()
                             |
                       slave_alloc()
-                      slave_configure()  -->  scsi_adjust_queue_depth()
+                      slave_configure()  -->  scsi_change_queue_depth()
                       slave_alloc()   ***
                       slave_destroy() ***
                             |
@@ -271,7 +271,7 @@ init_this_scsi_driver() ----+
                       slave_destroy() ***
 ------------------------------------------------------------
 
-The mid level invokes scsi_adjust_queue_depth() with "cmd_per_lun" for that
+The mid level invokes scsi_change_queue_depth() with "cmd_per_lun" for that
 host as the queue length. These settings can be overridden by a
 slave_configure() supplied by the LLD.
 
@@ -368,7 +368,7 @@ names all start with "scsi_".
 Summary:
    scsi_add_device - creates new scsi device (lu) instance
    scsi_add_host - perform sysfs registration and set up transport class
-   scsi_adjust_queue_depth - change the queue depth on a SCSI device
+   scsi_change_queue_depth - change the queue depth on a SCSI device
    scsi_bios_ptable - return copy of block device's partition table
    scsi_block_requests - prevent further commands being queued to given host
    scsi_host_alloc - return a new scsi_host instance whose refcount==1
@@ -436,7 +436,7 @@ int scsi_add_host(struct Scsi_Host *shost, struct device * dev)
 
 
 /**
- * scsi_adjust_queue_depth - allow LLD to change queue depth on a SCSI device
+ * scsi_change_queue_depth - allow LLD to change queue depth on a SCSI device
  * @sdev:       pointer to SCSI device to change queue depth on
  * @tags        Number of tags allowed if tagged queuing enabled,
  *              or number of commands the LLD can queue up
@@ -453,7 +453,7 @@ int scsi_add_host(struct Scsi_Host *shost, struct device * dev)
  *      Defined in: drivers/scsi/scsi.c [see source code for more notes]
  *
  **/
-void scsi_adjust_queue_depth(struct scsi_device *sdev, int tags)
+int scsi_change_queue_depth(struct scsi_device *sdev, int tags)
 
 
 /**
@@ -1214,7 +1214,7 @@ of interest:
                    for disk firmware uploads.
     cmd_per_lun  - maximum number of commands that can be queued on devices
                    controlled by the host. Overridden by LLD calls to
-                   scsi_adjust_queue_depth().
+                   scsi_change_queue_depth().
     unchecked_isa_dma - 1=>only use bottom 16 MB of ram (ISA DMA addressing
                    restriction), 0=>can use full 32 bit (or better) DMA
                    address space
@@ -1254,7 +1254,7 @@ struct scsi_cmnd
 Instances of this structure convey SCSI commands to the LLD and responses
 back to the mid level. The SCSI mid level will ensure that no more SCSI
 commands become queued against the LLD than are indicated by
-scsi_adjust_queue_depth() (or struct Scsi_Host::cmd_per_lun). There will
+scsi_change_queue_depth() (or struct Scsi_Host::cmd_per_lun). There will
 be at least one instance of struct scsi_cmnd available for each SCSI device.
 Members of interest:
     cmnd         - array containing SCSI command
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index c8bb6abbf12..de46385dbe7 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1164,7 +1164,7 @@ static int ata_scsi_dev_config(struct scsi_device *sdev,
 
 		depth = min(sdev->host->can_queue, ata_id_queue_depth(dev->id));
 		depth = min(ATA_MAX_QUEUE - 1, depth);
-		scsi_adjust_queue_depth(sdev, depth);
+		scsi_change_queue_depth(sdev, depth);
 	}
 
 	blk_queue_flush_queueable(q, false);
@@ -1243,21 +1243,17 @@ void ata_scsi_slave_destroy(struct scsi_device *sdev)
  *	@ap: ATA port to which the device change the queue depth
  *	@sdev: SCSI device to configure queue depth for
  *	@queue_depth: new queue depth
- *	@reason: calling context
  *
  *	libsas and libata have different approaches for associating a sdev to
  *	its ata_port.
  *
  */
 int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev,
-			     int queue_depth, int reason)
+			     int queue_depth)
 {
 	struct ata_device *dev;
 	unsigned long flags;
 
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
 	if (queue_depth < 1 || queue_depth == sdev->queue_depth)
 		return sdev->queue_depth;
 
@@ -1282,15 +1278,13 @@ int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev,
 	if (sdev->queue_depth == queue_depth)
 		return -EINVAL;
 
-	scsi_adjust_queue_depth(sdev, queue_depth);
-	return queue_depth;
+	return scsi_change_queue_depth(sdev, queue_depth);
 }
 
 /**
  *	ata_scsi_change_queue_depth - SCSI callback for queue depth config
  *	@sdev: SCSI device to configure queue depth for
  *	@queue_depth: new queue depth
- *	@reason: calling context
  *
  *	This is libata standard hostt->change_queue_depth callback.
  *	SCSI will call into this callback when user tries to set queue
@@ -1302,12 +1296,11 @@ int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev,
  *	RETURNS:
  *	Newly configured queue depth.
  */
-int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth,
-				int reason)
+int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth)
 {
 	struct ata_port *ap = ata_shost_to_port(sdev->host);
 
-	return __ata_change_queue_depth(ap, sdev, queue_depth, reason);
+	return __ata_change_queue_depth(ap, sdev, queue_depth);
 }
 
 /**
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index cdf99fac139..1db6f5ce5e8 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -1951,7 +1951,7 @@ static int nv_swncq_slave_config(struct scsi_device *sdev)
 	ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num));
 
 	if (strncmp(model_num, "Maxtor", 6) == 0) {
-		ata_scsi_change_queue_depth(sdev, 1, SCSI_QDEPTH_DEFAULT);
+		ata_scsi_change_queue_depth(sdev, 1);
 		ata_dev_notice(dev, "Disabling SWNCQ mode (depth %x)\n",
 			       sdev->queue_depth);
 	}
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 812a2891de5..20ca6a61947 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -911,7 +911,7 @@ static struct scsi_host_template iscsi_iser_sht = {
 	.module                 = THIS_MODULE,
 	.name                   = "iSCSI Initiator over iSER",
 	.queuecommand           = iscsi_queuecommand,
-	.change_queue_depth	= iscsi_change_queue_depth,
+	.change_queue_depth	= scsi_change_queue_depth,
 	.sg_tablesize           = ISCSI_ISER_SG_TABLESIZE,
 	.max_sectors		= 1024,
 	.cmd_per_lun            = ISER_DEF_CMD_PER_LUN,
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 8d13a19e04b..5461924c9f1 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -2402,18 +2402,15 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event)
  * srp_change_queue_depth - setting device queue depth
  * @sdev: scsi device struct
  * @qdepth: requested queue depth
- * @reason: SCSI_QDEPTH_DEFAULT
- * (see include/scsi/scsi_host.h for definition)
  *
  * Returns queue depth.
  */
 static int
-srp_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
+srp_change_queue_depth(struct scsi_device *sdev, int qdepth)
 {
 	if (!sdev->tagged_supported)
 		qdepth = 1;
-	scsi_adjust_queue_depth(sdev, qdepth);
-	return sdev->queue_depth;
+	return scsi_change_queue_depth(sdev, qdepth);
 }
 
 static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag,
diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c
index dee06d6f0b6..6c9fc11efb8 100644
--- a/drivers/message/fusion/mptscsih.c
+++ b/drivers/message/fusion/mptscsih.c
@@ -2311,12 +2311,11 @@ mptscsih_slave_destroy(struct scsi_device *sdev)
  *	mptscsih_change_queue_depth - This function will set a devices queue depth
  *	@sdev: per scsi_device pointer
  *	@qdepth: requested queue depth
- *	@reason: calling context
  *
  *	Adding support for new 'change_queue_depth' api.
 */
 int
-mptscsih_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
+mptscsih_change_queue_depth(struct scsi_device *sdev, int qdepth)
 {
 	MPT_SCSI_HOST		*hd = shost_priv(sdev->host);
 	VirtTarget 		*vtarget;
@@ -2327,9 +2326,6 @@ mptscsih_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 	starget = scsi_target(sdev);
 	vtarget = starget->hostdata;
 
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
 	if (ioc->bus_type == SPI) {
 		if (!(vtarget->tflags & MPT_TARGET_FLAGS_Q_YES))
 			max_depth = 1;
@@ -2347,8 +2343,7 @@ mptscsih_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
 	if (qdepth > max_depth)
 		qdepth = max_depth;
 
-	scsi_adjust_queue_depth(sdev, qdepth);
-	return sdev->queue_depth;
+	return scsi_change_queue_depth(sdev, qdepth);
 }
 
 /*
@@ -2392,8 +2387,7 @@ mptscsih_slave_configure(struct scsi_device *sdev)
 		    ioc->name, vtarget->negoFlags, vtarget->maxOffset,
 		    vtarget->minSyncFactor));
 
-	mptscsih_change_queue_depth(sdev, MPT_SCSI_CMD_PER_DEV_HIGH,
-				    SCSI_QDEPTH_DEFAULT);
+	mptscsih_change_queue_depth(sdev, MPT_SCSI_CMD_PER_DEV_HIGH);
 	dsprintk(ioc, printk(MYIOC_s_DEBUG_FMT
 		"tagged %d, simple %d\n",
 		ioc->name,sdev->tagged_supported, sdev->simple_tags));
diff --git a/drivers/message/fusion/mptscsih.h b/drivers/message/fusion/mptscsih.h
index e1b1a198a62..2baeefd9be7 100644
--- a/drivers/message/fusion/mptscsih.h
+++ b/drivers/message/fusion/mptscsih.h
@@ -128,8 +128,7 @@ extern int mptscsih_taskmgmt_complete(MPT_ADAPTER *ioc, MPT_FRAME_HDR *mf, MPT_F
 extern int mptscsih_scandv_complete(MPT_ADAPTER *ioc, MPT_FRAME_HDR *mf, MPT_FRAME_HDR *r);
 extern int mptscsih_event_process(MPT_ADAPTER *ioc, EventNotificationReply_t *pEvReply);
 extern int mptscsih_ioc_reset(MPT_ADAPTER *ioc, int post_reset);
-extern int mptscsih_change_queue_depth(struct scsi_device *sdev, int qdepth,
-				       int reason);
+extern int mptscsih_change_queue_depth(struct scsi_device *sdev, int qdepth);
 extern u8 mptscsih_raid_id_to_num(MPT_ADAPTER *ioc, u8 channel, u8 id);
 extern int mptscsih_is_phys_disk(MPT_ADAPTER *ioc, u8 channel, u8 id);
 extern struct device_attribute *mptscsih_host_attrs[];
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index 179bf3d8af6..75f4bfc2b98 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -32,13 +32,6 @@ static bool allow_lun_scan = 1;
 module_param(allow_lun_scan, bool, 0600);
 MODULE_PARM_DESC(allow_lun_scan, "For NPIV, scan and attach all storage LUNs");
 
-static int zfcp_scsi_change_queue_depth(struct scsi_device *sdev, int depth,
-					int reason)
-{
-	scsi_adjust_queue_depth(sdev, depth);
-	return sdev->queue_depth;
-}
-
 static void zfcp_scsi_slave_destroy(struct scsi_device *sdev)
 {
 	struct zfcp_scsi_dev *zfcp_sdev = sdev_to_zfcp(sdev);
@@ -54,7 +47,7 @@ static void zfcp_scsi_slave_destroy(struct scsi_device *sdev)
 static int zfcp_scsi_slave_configure(struct scsi_device *sdp)
 {
 	if (sdp->tagged_supported)
-		scsi_adjust_queue_depth(sdp, default_depth);
+		scsi_change_queue_depth(sdp, default_depth);
 	return 0;
 }
 
@@ -293,7 +286,7 @@ static struct scsi_host_template zfcp_scsi_host_template = {
 	.slave_alloc		 = zfcp_scsi_slave_alloc,
 	.slave_configure	 = zfcp_scsi_slave_configure,
 	.slave_destroy		 = zfcp_scsi_slave_destroy,
-	.change_queue_depth	 = zfcp_scsi_change_queue_depth,
+	.change_queue_depth	 = scsi_change_queue_depth,
 	.proc_name		 = "zfcp",
 	.can_queue		 = 4096,
 	.this_id		 = -1,
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index 1cf37032290..cd4129ff7ae 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -189,17 +189,6 @@ static ssize_t twa_show_stats(struct device *dev,
 	return len;
 } /* End twa_show_stats() */
 
-/* This function will set a devices queue depth */
-static int twa_change_queue_depth(struct scsi_device *sdev, int queue_depth,
-				  int reason)
-{
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
-	scsi_adjust_queue_depth(sdev, queue_depth);
-	return queue_depth;
-} /* End twa_change_queue_depth() */
-
 /* Create sysfs 'stats' entry */
 static struct device_attribute twa_host_stats_attr = {
 	.attr = {
@@ -2014,7 +2003,7 @@ static struct scsi_host_template driver_template = {
 	.queuecommand		= twa_scsi_queue,
 	.eh_host_reset_handler	= twa_scsi_eh_reset,
 	.bios_param		= twa_scsi_biosparam,
-	.change_queue_depth	= twa_change_queue_depth,
+	.change_queue_depth	= scsi_change_queue_depth,
 	.can_queue		= TW_Q_LENGTH-2,
 	.slave_configure	= twa_slave_configure,
 	.this_id		= -1,
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index 547756b7d5b..2361772d590 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -191,17 +191,6 @@ static ssize_t twl_show_stats(struct device *dev,
 	return len;
 } /* End twl_show_stats() */
 
-/* This function will set a devices queue depth */
-static int twl_change_queue_depth(struct scsi_device *sdev, int queue_depth,
-				  int reason)
-{
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
-	scsi_adjust_queue_depth(sdev, queue_depth);
-	return queue_depth;
-} /* End twl_change_queue_depth() */
-
 /* stats sysfs attribute initializer */
 static struct device_attribute twl_host_stats_attr = {
 	.attr = {
@@ -1588,7 +1577,7 @@ static struct scsi_host_template driver_template = {
 	.queuecommand		= twl_scsi_queue,
 	.eh_host_reset_handler	= twl_scsi_eh_reset,
 	.bios_param		= twl_scsi_biosparam,
-	.change_queue_depth	= twl_change_queue_depth,
+	.change_queue_depth	= scsi_change_queue_depth,
 	.can_queue		= TW_Q_LENGTH-2,
 	.slave_configure	= twl_slave_configure,
 	.this_id		= -1,
diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index 261a4c1da96..c75f2048319 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -523,17 +523,6 @@ static ssize_t tw_show_stats(struct device *dev, struct device_attribute *attr,
 	return len;
 } /* End tw_show_stats() */
 
-/* This function will set a devices queue depth */
-static int tw_change_queue_depth(struct scsi_device *sdev, int queue_depth,
-				 int reason)
-{
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
-	scsi_adjust_queue_depth(sdev, queue_depth);
-	return queue_depth;
-} /* End tw_change_queue_depth() */
-
 /* Create sysfs 'stats' entry */
 static struct device_attribute tw_host_stats_attr = {
 	.attr = {
@@ -2268,7 +2257,7 @@ static struct scsi_host_template driver_template = {
 	.queuecommand		= tw_scsi_queue,
 	.eh_host_reset_handler	= tw_scsi_eh_reset,
 	.bios_param		= tw_scsi_biosparam,
-	.change_queue_depth	= tw_change_queue_depth,
+	.change_queue_depth	= scsi_change_queue_depth,
 	.can_queue		= TW_Q_LENGTH-2,
 	.slave_configure	= tw_slave_configure,
 	.this_id		= -1,
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index d7557b93211..aa915da2a5e 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -175,7 +175,7 @@ STATIC void NCR_700_chip_reset(struct Scsi_Host *host);
 STATIC int NCR_700_slave_alloc(struct scsi_device *SDpnt);
 STATIC int NCR_700_slave_configure(struct scsi_device *SDpnt);
 STATIC void NCR_700_slave_destroy(struct scsi_device *SDpnt);
-static int NCR_700_change_queue_depth(struct scsi_device *SDpnt, int depth, int reason);
+static int NCR_700_change_queue_depth(struct scsi_device *SDpnt, int depth);
 static int NCR_700_change_queue_type(struct scsi_device *SDpnt, int depth);
 
 STATIC struct device_attribute *NCR_700_dev_attrs[];
@@ -904,7 +904,7 @@ process_message(struct Scsi_Host *host,	struct NCR_700_Host_Parameters *hostdata
 			hostdata->tag_negotiated &= ~(1<<scmd_id(SCp));
 
 			SCp->device->tagged_supported = 0;
-			scsi_adjust_queue_depth(SCp->device, host->cmd_per_lun);
+			scsi_change_queue_depth(SCp->device, host->cmd_per_lun);
 			scsi_set_tag_type(SCp->device, 0);
 		} else {
 			shost_printk(KERN_WARNING, host,
@@ -2052,7 +2052,7 @@ NCR_700_slave_configure(struct scsi_device *SDp)
 
 	/* to do here: allocate memory; build a queue_full list */
 	if(SDp->tagged_supported) {
-		scsi_adjust_queue_depth(SDp, NCR_700_DEFAULT_TAGS);
+		scsi_change_queue_depth(SDp, NCR_700_DEFAULT_TAGS);
 		NCR_700_set_tag_neg_state(SDp, NCR_700_START_TAG_NEGOTIATION);
 	}
 
@@ -2075,16 +2075,11 @@ NCR_700_slave_destroy(struct scsi_device *SDp)
 }
 
 static int
-NCR_700_change_queue_depth(struct scsi_device *SDp, int depth, int reason)
+NCR_700_change_queue_depth(struct scsi_device *SDp, int depth)
 {
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
 	if (depth > NCR_700_MAX_TAGS)
 		depth = NCR_700_MAX_TAGS;
-
-	scsi_adjust_queue_depth(SDp, depth);
-	return depth;
+	return scsi_change_queue_depth(SDp, depth);
 }
 
 static int NCR_700_change_queue_type(struct scsi_device *SDp, int tag_type)
@@ -2105,12 +2100,12 @@ static int NCR_700_change_queue_type(struct scsi_device *SDp, int tag_type)
 	if (!tag_type) {
 		/* shift back to the default unqueued number of commands
 		 * (the user can still raise this) */
-		scsi_adjust_queue_depth(SDp, SDp->host->cmd_per_lun);
+		scsi_change_queue_depth(SDp, SDp->host->cmd_per_lun);
 		hostdata->tag_negotiated &= ~(1 << sdev_id(SDp));
 	} else {
 		/* Here, we cleared the negotiation flag above, so this
 		 * will force the driver to renegotiate */
-		scsi_adjust_queue_depth(SDp, SDp->queue_depth);
+		scsi_change_queue_depth(SDp, SDp->queue_depth);
 		if (change_tag)
 			NCR_700_set_tag_neg_state(SDp, NCR_700_START_TAG_NEGOTIATION);
 	}
diff --git a/drivers/scsi/BusLogic.c b/drivers/scsi/BusLogic.c
index 5aa476b6b8a..8d66a6469e2 100644
--- a/drivers/scsi/BusLogic.c
+++ b/drivers/scsi/BusLogic.c
@@ -2327,12 +2327,12 @@ static int blogic_slaveconfig(struct scsi_device *dev)
 		if (qdepth == 0)
 			qdepth = BLOGIC_MAX_AUTO_TAG_DEPTH;
 		adapter->qdepth[tgt_id] = qdepth;
-		scsi_adjust_queue_depth(dev, qdepth);
+		scsi_change_queue_depth(dev, qdepth);
 	} else {
 		adapter->tagq_ok &= ~(1 << tgt_id);
 		qdepth = adapter->untag_qdepth;
 		adapter->qdepth[tgt_id] = qdepth;
-		scsi_adjust_queue_depth(dev, qdepth);
+		scsi_change_queue_depth(dev, qdepth);
 	}
 	qdepth = 0;
 	for (tgt_id = 0; tgt_id < adapter->maxdev; tgt_id++)
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 41b9c68bca6..d11c23aad04 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -462,9 +462,9 @@ static int aac_slave_configure(struct scsi_device *sdev)
 			depth = 256;
 		else if (depth < 2)
 			depth = 2;
-		scsi_adjust_queue_depth(sdev, depth);
+		scsi_change_queue_depth(sdev, depth);
 	} else
-		scsi_adjust_queue_depth(sdev, 1);
+		scsi_change_queue_depth(sdev, 1);
 
 	return 0;
 }
@@ -478,12 +478,8 @@ static int aac_slave_configure(struct scsi_device *sdev)
  *	total capacity and the queue depth supported by the target device.
  */
 
-static int aac_change_queue_depth(struct scsi_device *sdev, int depth,
-				  int reason)
+static int aac_change_queue_depth(struct scsi_device *sdev, int depth)
 {
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
 	if (sdev->tagged_supported && (sdev->type == TYPE_DISK) &&
 	    (sdev_channel(sdev) == CONTAINER_CHANNEL)) {
 		struct scsi_device * dev;
@@ -504,10 +500,10 @@ static int aac_change_queue_depth(struct scsi_device *sdev, int depth,
 			depth = 256;
 		else if (depth < 2)
 			depth = 2;
-		scsi_adjust_queue_depth(sdev, depth);
-	} else
-		scsi_adjust_queue_depth(sdev, 1);
-	return sdev->queue_depth;
+		return scsi_change_queue_depth(sdev, depth);
+	}
+
+	return scsi_change_queue_depth(sdev, 1);
 }
 
 static ssize_t aac_show_raid_level(struct device *dev, struct device_attribute *attr, char *buf)
diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
index ae4840e4c1c..6719a3390eb 100644
--- a/drivers/scsi/advansys.c
+++ b/drivers/scsi/advansys.c
@@ -7706,7 +7706,7 @@ advansys_narrow_slave_configure(struct scsi_device *sdev, ASC_DVC_VAR *asc_dvc)
 				asc_dvc->cfg->can_tagged_qng |= tid_bit;
 				asc_dvc->use_tagged_qng |= tid_bit;
 			}
-			scsi_adjust_queue_depth(sdev, 
+			scsi_change_queue_depth(sdev, 
 						asc_dvc->max_dvc_qng[sdev->id]);
 		}
 	} else {
@@ -7847,10 +7847,8 @@ advansys_wide_slave_configure(struct scsi_device *sdev, ADV_DVC_VAR *adv_dvc)
 		}
 	}
 
-	if ((adv_dvc->tagqng_able & tidmask) && sdev->tagged_supported) {
-		scsi_adjust_queue_depth(sdev,
-					adv_dvc->max_dvc_qng);
-	}
+	if ((adv_dvc->tagqng_able & tidmask) && sdev->tagged_supported)
+		scsi_change_queue_depth(sdev, adv_dvc->max_dvc_qng);
 }
 
 /*
diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c
index 80cb4fd7caa..d5c7b193d8d 100644
--- a/drivers/scsi/aic7xxx/aic79xx_osm.c
+++ b/drivers/scsi/aic7xxx/aic79xx_osm.c
@@ -1470,7 +1470,7 @@ ahd_platform_set_tags(struct ahd_softc *ahd, struct scsi_device *sdev,
 	switch ((dev->flags & (AHD_DEV_Q_BASIC|AHD_DEV_Q_TAGGED))) {
 	case AHD_DEV_Q_BASIC:
 	case AHD_DEV_Q_TAGGED:
-		scsi_adjust_queue_depth(sdev,
+		scsi_change_queue_depth(sdev,
 				dev->openings + dev->active);
 		break;
 	default:
@@ -1480,7 +1480,7 @@ ahd_platform_set_tags(struct ahd_softc *ahd, struct scsi_device *sdev,
 		 * serially on the controller/device.  This should
 		 * remove some latency.
 		 */
-		scsi_adjust_queue_depth(sdev, 1);
+		scsi_change_queue_depth(sdev, 1);
 		break;
 	}
 }
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c
index a6a27d5398d..88360116dbc 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c
@@ -1336,7 +1336,7 @@ ahc_platform_set_tags(struct ahc_softc *ahc, struct scsi_device *sdev,
 	switch ((dev->flags & (AHC_DEV_Q_BASIC|AHC_DEV_Q_TAGGED))) {
 	case AHC_DEV_Q_BASIC:
 	case AHC_DEV_Q_TAGGED:
-		scsi_adjust_queue_depth(sdev,
+		scsi_change_queue_depth(sdev,
 				dev->openings + dev->active);
 	default:
 		/*
@@ -1345,7 +1345,7 @@ ahc_platform_set_tags(struct ahc_softc *ahc, struct scsi_device *sdev,
 		 * serially on the controller/device.  This should
 		 * remove some latency.
 		 */
-		scsi_adjust_queue_depth(sdev, 2);
+		scsi_change_queue_depth(sdev, 2);
 		break;
 	}
 }
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 209f77162d0..914c39f9f38 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -114,16 +114,11 @@ static void arcmsr_hardware_reset(struct AdapterControlBlock *acb);
 static const char *arcmsr_info(struct Scsi_Host *);
 static irqreturn_t arcmsr_interrupt(struct AdapterControlBlock *acb);
 static void arcmsr_free_irq(struct pci_dev *, struct AdapterControlBlock *);
-static int arcmsr_adjust_disk_queue_depth(struct scsi_device *sdev,
-					  int queue_depth, int reason)
+static int arcmsr_adjust_disk_queue_depth(struct scsi_device *sdev, int queue_depth)
 {
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
 	if (queue_depth > ARCMSR_MAX_CMD_PERLUN)
 		queue_depth = ARCMSR_MAX_CMD_PERLUN;
-	scsi_adjust_queue_depth(sdev, queue_depth);
-	return queue_depth;
+	return scsi_change_queue_depth(sdev, queue_depth);
 }
 
 static struct scsi_host_template arcmsr_scsi_host_template = {
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index d9b999a3416..f3193406776 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -556,7 +556,7 @@ static struct scsi_host_template beiscsi_sht = {
 	.name = "Emulex 10Gbe open-iscsi Initiator Driver",
 	.proc_name = DRV_NAME,
 	.queuecommand = iscsi_queuecommand,
-	.change_queue_depth = iscsi_change_queue_depth,
+	.change_queue_depth = scsi_change_queue_depth,
 	.slave_configure = beiscsi_slave_configure,
 	.target_alloc = iscsi_target_alloc,
 	.eh_abort_handler = beiscsi_eh_abort,
diff --git a/drivers/scsi/bfa/bfad_im.c b/drivers/scsi/bfa/bfad_im.c
index 87b09cd232c..7223b000674 100644
--- a/drivers/scsi/bfa/bfad_im.c
+++ b/drivers/scsi/bfa/bfad_im.c
@@ -776,7 +776,7 @@ bfad_thread_workq(struct bfad_s *bfad)
 static int
 bfad_im_slave_configure(struct scsi_device *sdev)
 {
-	scsi_adjust_queue_depth(sdev, bfa_lun_queue_depth);
+	scsi_change_queue_depth(sdev, bfa_lun_queue_depth);
 	return 0;
 }
 
@@ -866,7 +866,7 @@ bfad_ramp_up_qdepth(struct bfad_itnim_s *itnim, struct scsi_device *sdev)
 			if (bfa_lun_queue_depth > tmp_sdev->queue_depth) {
 				if (tmp_sdev->id != sdev->id)
 					continue;
-				scsi_adjust_queue_depth(tmp_sdev,
+				scsi_change_queue_depth(tmp_sdev,
 					tmp_sdev->queue_depth + 1);
 
 				itnim->last_ramp_up_time = jiffies;
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index cc537972f3e..386c2cfad30 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -2784,7 +2784,7 @@ static struct scsi_host_template bnx2fc_shost_template = {
 	.eh_target_reset_handler = bnx2fc_eh_target_reset, /* tgt reset */
 	.eh_host_reset_handler	= fc_eh_host_reset,
 	.slave_alloc		= fc_slave_alloc,
-	.change_queue_depth	= fc_change_queue_depth,
+	.change_queue_depth	= scsi_change_queue_depth,
 	.change_queue_type	= scsi_change_queue_type,
 	.this_id		= -1,
 	.cmd_per_lun		= 3,
diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c
index 9de1c20bb0f..e53078d0330 100644
--- a/drivers/scsi/bnx2i/bnx2i_iscsi.c
+++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c
@@ -2259,7 +2259,7 @@ static struct scsi_host_template bnx2i_host_template = {
 	.eh_abort_handler	= iscsi_eh_abort,
 	.eh_device_reset_handler = iscsi_eh_device_reset,
 	.eh_target_reset_handler = iscsi_eh_recover_target,
-	.change_queue_depth	= iscsi_change_queue_depth,
+	.change_queue_depth	= scsi_change_queue_depth,
 	.target_alloc		= iscsi_target_alloc,
 	.can_queue		= 2048,
 	.max_sectors		= 127,
diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c
index 44a8cc51428..4d0b6ce55f2 100644
--- a/drivers/scsi/csiostor/csio_scsi.c
+++ b/drivers/scsi/csiostor/csio_scsi.c
@@ -2241,7 +2241,7 @@ csio_slave_alloc(struct scsi_device *sdev)
 static int
 csio_slave_configure(struct scsi_device *sdev)
 {
-	scsi_adjust_queue_depth(sdev, csio_lun_qdepth);
+	scsi_change_queue_depth(sdev, csio_lun_qdepth);
 	return 0;
 }
 
diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
index 99ea67dcdd2..3db4c63978c 100644
--- a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
+++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
@@ -86,7 +86,7 @@ static struct scsi_host_template cxgb3i_host_template = {
 	.proc_name	= DRV_MODULE_NAME,
 	.can_queue	= CXGB3I_SCSI_HOST_QDEPTH,
 	.queuecommand	= iscsi_queuecommand,
-	.change_queue_depth = iscsi_change_queue_depth,
+	.change_queue_depth = scsi_change_queue_depth,
 	.sg_tablesize	= SG_ALL,
 	.max_sectors	= 0xFFFF,
 	.cmd_per_lun	= ISCSI_DEF_CMD_PER_LUN,
diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index af86e8f57b8..efe42ef7d92 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -89,7 +89,7 @@ static struct scsi_host_template cxgb4i_host_template = {
 	.proc_name	= DRV_MODULE_NAME,
 	.can_queue	= CXGB4I_SCSI_HOST_QDEPTH,
 	.queuecommand	= iscsi_queuecommand,
-	.change_queue_depth = iscsi_change_queue_depth,
+	.change_queue_depth = scsi_change_queue_depth,
 	.sg_tablesize	= SG_ALL,
 	.max_sectors	= 0xFFFF,
 	.cmd_per_lun	= ISCSI_DEF_CMD_PER_LUN,
diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c
index 1af8d54bcde..0bf976936a1 100644
--- a/drivers/scsi/dpt_i2o.c
+++ b/drivers/scsi/dpt_i2o.c
@@ -415,7 +415,7 @@ static int adpt_slave_configure(struct scsi_device * device)
 	pHba = (adpt_hba *) host->hostdata[0];
 
 	if (host->can_queue && device->tagged_supported) {
-		scsi_adjust_queue_depth(device,
+		scsi_change_queue_depth(device,
 				host->can_queue - 1);
 	}
 	return 0;
diff --git a/drivers/scsi/eata.c b/drivers/scsi/eata.c
index bc0f918f172..227dd2c2ec2 100644
--- a/drivers/scsi/eata.c
+++ b/drivers/scsi/eata.c
@@ -952,12 +952,12 @@ static int eata2x_slave_configure(struct scsi_device *dev)
 		} else {
 			tag_suffix = ", no tags";
 		}
-		scsi_adjust_queue_depth(dev, tqd);
+		scsi_change_queue_depth(dev, tqd);
 	} else if (TLDEV(dev->type) && linked_comm) {
-		scsi_adjust_queue_depth(dev, tqd);
+		scsi_change_queue_depth(dev, tqd);
 		tag_suffix = ", untagged";
 	} else {
-		scsi_adjust_queue_depth(dev, utqd);
+		scsi_change_queue_depth(dev, utqd);
 		tag_suffix = "";
 	}
 
diff --git a/drivers/scsi/esas2r/esas2r.h b/drivers/scsi/esas2r/esas2r.h
index 1941d837f6f..b6030e3edd0 100644
--- a/drivers/scsi/esas2r/esas2r.h
+++ b/drivers/scsi/esas2r/esas2r.h
@@ -972,7 +972,6 @@ u8 handle_hba_ioctl(struct esas2r_adapter *a,
 		    struct atto_ioctl *ioctl_hba);
 int esas2r_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd);
 int esas2r_show_info(struct seq_file *m, struct Scsi_Host *sh);
-int esas2r_change_queue_depth(struct scsi_device *dev, int depth, int reason);
 long esas2r_proc_ioctl(struct file *fp, unsigned int cmd, unsigned long arg);
 
 /* SCSI error handler (eh) functions */
diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c
index 30fce64faf7..593ff8a63c7 100644
--- a/drivers/scsi/esas2r/esas2r_main.c
+++ b/drivers/scsi/esas2r/esas2r_main.c
@@ -254,7 +254,7 @@ static struct scsi_host_template driver_template = {
 	.use_clustering			= ENABLE_CLUSTERING,
 	.emulated			= 0,
 	.proc_name			= ESAS2R_DRVR_NAME,
-	.change_queue_depth		= esas2r_change_queue_depth,
+	.change_queue_depth		= scsi_change_queue_depth,
 	.change_queue_type		= scsi_change_queue_type,
 	.max_sectors			= 0xFFFF,
 	.use_blk_tags			= 1,
@@ -1257,15 +1257,6 @@ int esas2r_target_reset(struct scsi_cmnd *cmd)
 	return esas2r_dev_targ_reset(cmd, true);
 }
 
-int esas2r_change_queue_depth(struct scsi_device *dev, int depth, int reason)
-{
-	esas2r_log(ESAS2R_LOG_INFO, "change_queue_depth %p, %d", dev, depth);
-
-	scsi_adjust_queue_depth(dev, depth);
-
-	return dev->queue_depth;
-}
-
 void esas2r_log_request_failure(struct esas2r_adapter *a,
 				struct esas2r_request *rq)
 {
diff --git a/drivers/scsi/esp_scsi.c b/drivers/scsi/esp_scsi.c
index 38c23e0b73a..7e7687f73de 100644
--- a/drivers/scsi/esp_scsi.c
+++ b/drivers/scsi/esp_scsi.c
@@ -2407,7 +2407,7 @@ static int esp_slave_configure(struct scsi_device *dev)
 		/* XXX make this configurable somehow XXX */
 		int goal_tags = min(ESP_DEFAULT_TAGS, ESP_MAX_TAG);
 
-		scsi_adjust_queue_depth(dev, goal_tags);
+		scsi_change_queue_depth(dev, goal_tags);
 	}
 
 	tp->flags |= ESP_TGT_DISCONNECT;
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 97229860398..308a016fdae 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -280,7 +280,7 @@ static struct scsi_host_template fcoe_shost_template = {
 	.eh_device_reset_handler = fc_eh_device_reset,
 	.eh_host_reset_handler = fc_eh_host_reset,
 	.slave_alloc = fc_slave_alloc,
-	.change_queue_depth = fc_change_queue_depth,
+	.change_queue_depth = scsi_change_queue_depth,
 	.change_queue_type = scsi_change_queue_type,
 	.this_id = -1,
 	.cmd_per_lun = 3,
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index 86b496c8633..0c1f8177b5b 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -98,7 +98,7 @@ static int fnic_slave_alloc(struct scsi_device *sdev)
 	if (!rport || fc_remote_port_chkready(rport))
 		return -ENXIO;
 
-	scsi_adjust_queue_depth(sdev, fnic_max_qdepth);
+	scsi_change_queue_depth(sdev, fnic_max_qdepth);
 	return 0;
 }
 
@@ -110,7 +110,7 @@ static struct scsi_host_template fnic_host_template = {
 	.eh_device_reset_handler = fnic_device_reset,
 	.eh_host_reset_handler = fnic_host_reset,
 	.slave_alloc = fnic_slave_alloc,
-	.change_queue_depth = fc_change_queue_depth,
+	.change_queue_depth = scsi_change_queue_depth,
 	.change_queue_type = scsi_change_queue_type,
 	.this_id = -1,
 	.cmd_per_lun = 3,
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 617f218e2a1..6bb4611b238 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -216,8 +216,6 @@ static int hpsa_scsi_queue_command(struct Scsi_Host *h, struct scsi_cmnd *cmd);
 static void hpsa_scan_start(struct Scsi_Host *);
 static int hpsa_scan_finished(struct Scsi_Host *sh,
 	unsigned long elapsed_time);
-static int hpsa_change_queue_depth(struct scsi_device *sdev,
-	int qdepth, int reason);
 
 static int hpsa_eh_device_reset_handler(struct scsi_cmnd *scsicmd);
 static int hpsa_eh_abort_handler(struct scsi_cmnd *scsicmd);
@@ -673,7 +671,7 @@ static struct scsi_host_template hpsa_driver_template = {
 	.queuecommand		= hpsa_scsi_queue_command,
 	.scan_start		= hpsa_scan_start,
 	.scan_finished		= hpsa_scan_finished,
-	.change_queue_depth	= hpsa_change_queue_depth,
+	.change_queue_depth	= scsi_change_queue_depth,
 	.this_id		= -1,
 	.use_clustering		= ENABLE_CLUSTERING,
 	.eh_abort_handler	= hpsa_eh_abort_handler,
@@ -4074,18 +4072,6 @@ static int hpsa_scan_finished(struct Scsi_Host *sh,
 	return finished;
 }
 
-static int hpsa_change_queue_depth(struct scsi_device *sdev,
-	int qdepth, int reason)
-{
-	struct ctlr_info *h = sdev_to_hba(sdev);
-
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -ENOTSUPP;
-
-	scsi_adjust_queue_depth(sdev, qdepth);
-	return sdev->queue_depth;
-}
-
 static void hpsa_unregister_scsi(struct ctlr_info *h)
 {
 	/* we are being forcibly unloaded, and may not refuse. */
diff --git a/drivers/scsi/hptiop.c b/drivers/scsi/hptiop.c
index 151893148ab..e995218476e 100644
--- a/drivers/scsi/hptiop.c
+++ b/drivers/scsi/hptiop.c
@@ -1118,17 +1118,13 @@ static int hptiop_reset(struct scsi_cmnd *scp)
 }
 
 static int hptiop_adjust_disk_queue_depth(struct scsi_device *sdev,
-					  int queue_depth, int reason)
+					  int queue_depth)
 {
 	struct hptiop_hba *hba = (struct hptiop_hba *)sdev->host->hostdata;
 
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
 	if (queue_depth > hba->max_requests)
 		queue_depth = hba->max_requests;
-	scsi_adjust_queue_depth(sdev, queue_depth);
-	return queue_depth;
+	return scsi_change_queue_depth(sdev, queue_depth);
 }
 
 static ssize_t hptiop_show_version(struct device *dev,
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 381449d5be7..f58c6d8e026 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -2900,17 +2900,12 @@ static int ibmvfc_slave_configure(struct scsi_device *sdev)
  * Return value:
  * 	actual depth set
  **/
-static int ibmvfc_change_queue_depth(struct scsi_device *sdev, int qdepth,
-				     int reason)
+static int ibmvfc_change_queue_depth(struct scsi_device *sdev, int qdepth)
 {
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
 	if (qdepth > IBMVFC_MAX_CMDS_PER_LUN)
 		qdepth = IBMVFC_MAX_CMDS_PER_LUN;
 
-	scsi_adjust_queue_depth(sdev, qdepth);
-	return sdev->queue_depth;
+	return scsi_change_queue_depth(sdev, qdepth);
 }
 
 static ssize_t ibmvfc_show_host_partition_name(struct device *dev,
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index e8c3cdf0d03..acea5d6eebd 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -1941,17 +1941,11 @@ static int ibmvscsi_slave_configure(struct scsi_device *sdev)
  * Return value:
  * 	actual depth set
  **/
-static int ibmvscsi_change_queue_depth(struct scsi_device *sdev, int qdepth,
-				       int reason)
+static int ibmvscsi_change_queue_depth(struct scsi_device *sdev, int qdepth)
 {
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
 	if (qdepth > IBMVSCSI_MAX_CMDS_PER_LUN)
 		qdepth = IBMVSCSI_MAX_CMDS_PER_LUN;
-
-	scsi_adjust_queue_depth(sdev, qdepth);
-	return sdev->queue_depth;
+	return scsi_change_queue_depth(sdev, qdepth);
 }
 
 /* ------------------------------------------------------------
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index d8d16625a87..54029438935 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -4328,16 +4328,12 @@ static int ipr_free_dump(struct ipr_ioa_cfg *ioa_cfg) { return 0; };
  * Return value:
  * 	actual depth set
  **/
-static int ipr_change_queue_depth(struct scsi_device *sdev, int qdepth,
-				  int reason)
+static int ipr_change_queue_depth(struct scsi_device *sdev, int qdepth)
 {
 	struct ipr_ioa_cfg *ioa_cfg = (struct ipr_ioa_cfg *)sdev->host->hostdata;
 	struct ipr_resource_entry *res;
 	unsigned long lock_flags = 0;
 
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
 	spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
 	res = (struct ipr_resource_entry *)sdev->hostdata;
 
@@ -4345,7 +4341,7 @@ static int ipr_change_queue_depth(struct scsi_device *sdev, int qdepth,
 		qdepth = IPR_MAX_CMD_PER_ATA_LUN;
 	spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
 
-	scsi_adjust_queue_depth(sdev, qdepth);
+	scsi_change_queue_depth(sdev, qdepth);
 	return sdev->queue_depth;
 }
 
@@ -4752,7 +4748,7 @@ static int ipr_slave_configure(struct scsi_device *sdev)
 		spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
 
 		if (ap) {
-			scsi_adjust_queue_depth(sdev, IPR_MAX_CMD_PER_ATA_LUN);
+			scsi_change_queue_depth(sdev, IPR_MAX_CMD_PER_ATA_LUN);
 			ata_sas_slave_configure(sdev, ap);
 		}
 
diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c
index 454741a8da4..e5c28435d76 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -1210,7 +1210,7 @@ ips_slave_configure(struct scsi_device * SDptr)
 		min = ha->max_cmds / 2;
 		if (ha->enq->ucLogDriveCount <= 2)
 			min = ha->max_cmds - 1;
-		scsi_adjust_queue_depth(SDptr, min);
+		scsi_change_queue_depth(SDptr, min);
 	}
 
 	SDptr->skip_ms_page_8 = 1;
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index a575d845b66..0b8af186e70 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -952,7 +952,7 @@ static struct scsi_host_template iscsi_sw_tcp_sht = {
 	.module			= THIS_MODULE,
 	.name			= "iSCSI Initiator over TCP/IP",
 	.queuecommand           = iscsi_queuecommand,
-	.change_queue_depth	= iscsi_change_queue_depth,
+	.change_queue_depth	= scsi_change_queue_depth,
 	.can_queue		= ISCSI_DEF_XMIT_CMDS_MAX - 1,
 	.sg_tablesize		= 4096,
 	.max_sectors		= 0xFFFF,
diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index 0d2d024e77c..c6795941b45 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -2160,24 +2160,11 @@ int fc_slave_alloc(struct scsi_device *sdev)
 	if (!rport || fc_remote_port_chkready(rport))
 		return -ENXIO;
 
-	scsi_adjust_queue_depth(sdev, FC_FCP_DFLT_QUEUE_DEPTH);
+	scsi_change_queue_depth(sdev, FC_FCP_DFLT_QUEUE_DEPTH);
 	return 0;
 }
 EXPORT_SYMBOL(fc_slave_alloc);
 
-/**
- * fc_change_queue_depth() - Change a device's queue depth
- * @sdev:   The SCSI device whose queue depth is to change
- * @qdepth: The new queue depth
- * @reason: The resason for the change
- */
-int fc_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
-{
-	scsi_adjust_queue_depth(sdev, qdepth);
-	return sdev->queue_depth;
-}
-EXPORT_SYMBOL(fc_change_queue_depth);
-
 /**
  * fc_fcp_destory() - Tear down the FCP layer for a given local port
  * @lport: The local port that no longer needs the FCP layer
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 79e977484ad..8053f24f034 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1771,13 +1771,6 @@ fault:
 }
 EXPORT_SYMBOL_GPL(iscsi_queuecommand);
 
-int iscsi_change_queue_depth(struct scsi_device *sdev, int depth, int reason)
-{
-	scsi_adjust_queue_depth(sdev, depth);
-	return sdev->queue_depth;
-}
-EXPORT_SYMBOL_GPL(iscsi_change_queue_depth);
-
 int iscsi_target_alloc(struct scsi_target *starget)
 {
 	struct iscsi_cls_session *cls_session = starget_to_session(starget);
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 914e4116513..b492293d51f 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -940,12 +940,12 @@ int sas_slave_configure(struct scsi_device *scsi_dev)
 	sas_read_port_mode_page(scsi_dev);
 
 	if (scsi_dev->tagged_supported) {
-		scsi_adjust_queue_depth(scsi_dev, SAS_DEF_QD);
+		scsi_change_queue_depth(scsi_dev, SAS_DEF_QD);
 	} else {
 		SAS_DPRINTK("device %llx, LUN %llx doesn't support "
 			    "TCQ\n", SAS_ADDR(dev->sas_addr),
 			    scsi_dev->lun);
-		scsi_adjust_queue_depth(scsi_dev, 1);
+		scsi_change_queue_depth(scsi_dev, 1);
 	}
 
 	scsi_dev->allow_restart = 1;
@@ -953,18 +953,16 @@ int sas_slave_configure(struct scsi_device *scsi_dev)
 	return 0;
 }
 
-int sas_change_queue_depth(struct scsi_device *sdev, int depth, int reason)
+int sas_change_queue_depth(struct scsi_device *sdev, int depth)
 {
 	struct domain_device *dev = sdev_to_domain_dev(sdev);
 
 	if (dev_is_sata(dev))
-		return __ata_change_queue_depth(dev->sata_dev.ap, sdev, depth,
-						reason);
+		return __ata_change_queue_depth(dev->sata_dev.ap, sdev, depth);
 
 	if (!sdev->tagged_supported)
 		depth = 1;
-	scsi_adjust_queue_depth(sdev, depth);
-	return depth;
+	return scsi_change_queue_depth(sdev, depth);
 }
 
 int sas_change_queue_type(struct scsi_device *scsi_dev, int type)
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 52285492036..fd85952b621 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -242,23 +242,6 @@ lpfc_update_stats(struct lpfc_hba *phba, struct  lpfc_scsi_buf *lpfc_cmd)
 	spin_unlock_irqrestore(shost->host_lock, flags);
 }
 
-/**
- * lpfc_change_queue_depth - Alter scsi device queue depth
- * @sdev: Pointer the scsi device on which to change the queue depth.
- * @qdepth: New queue depth to set the sdev to.
- * @reason: The reason for the queue depth change.
- *
- * This function is called by the midlayer and the LLD to alter the queue
- * depth for a scsi device. This function sets the queue depth to the new
- * value and sends an event out to log the queue depth change.
- **/
-static int
-lpfc_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
-{
-	scsi_adjust_queue_depth(sdev, qdepth);
-	return sdev->queue_depth;
-}
-
 /**
  * lpfc_rampdown_queue_depth - Post RAMP_DOWN_QUEUE event to worker thread
  * @phba: The Hba for which this call is being executed.
@@ -344,8 +327,7 @@ lpfc_ramp_down_queue_handler(struct lpfc_hba *phba)
 				else
 					new_queue_depth = sdev->queue_depth -
 								new_queue_depth;
-				lpfc_change_queue_depth(sdev, new_queue_depth,
-							SCSI_QDEPTH_DEFAULT);
+				scsi_change_queue_depth(sdev, new_queue_depth);
 			}
 		}
 	lpfc_destroy_vport_work_array(phba, vports);
@@ -5513,7 +5495,7 @@ lpfc_slave_configure(struct scsi_device *sdev)
 	struct lpfc_vport *vport = (struct lpfc_vport *) sdev->host->hostdata;
 	struct lpfc_hba   *phba = vport->phba;
 
-	scsi_adjust_queue_depth(sdev, vport->cfg_lun_queue_depth);
+	scsi_change_queue_depth(sdev, vport->cfg_lun_queue_depth);
 
 	if (phba->cfg_poll & ENABLE_FCP_RING_POLLING) {
 		lpfc_sli_handle_fast_ring_event(phba,
@@ -5896,7 +5878,7 @@ struct scsi_host_template lpfc_template = {
 	.shost_attrs		= lpfc_hba_attrs,
 	.max_sectors		= 0xFFFF,
 	.vendor_id		= LPFC_NL_VENDOR_ID,
-	.change_queue_depth	= lpfc_change_queue_depth,
+	.change_queue_depth	= scsi_change_queue_depth,
 	.change_queue_type	= scsi_change_queue_type,
 	.use_blk_tags		= 1,
 	.track_queue_depth	= 1,
@@ -5921,7 +5903,7 @@ struct scsi_host_template lpfc_vport_template = {
 	.use_clustering		= ENABLE_CLUSTERING,
 	.shost_attrs		= lpfc_vport_attrs,
 	.max_sectors		= 0xFFFF,
-	.change_queue_depth	= lpfc_change_queue_depth,
+	.change_queue_depth	= scsi_change_queue_depth,
 	.change_queue_type	= scsi_change_queue_type,
 	.use_blk_tags		= 1,
 	.track_queue_depth	= 1,
diff --git a/drivers/scsi/megaraid/megaraid_mbox.c b/drivers/scsi/megaraid/megaraid_mbox.c
index d56eb9d3d40..f0987f22ea7 100644
--- a/drivers/scsi/megaraid/megaraid_mbox.c
+++ b/drivers/scsi/megaraid/megaraid_mbox.c
@@ -332,25 +332,6 @@ static struct device_attribute *megaraid_sdev_attrs[] = {
 	NULL,
 };
 
-/**
- * megaraid_change_queue_depth - Change the device's queue depth
- * @sdev:	scsi device struct
- * @qdepth:	depth to set
- * @reason:	calling context
- *
- * Return value:
- * 	actual depth set
- */
-static int megaraid_change_queue_depth(struct scsi_device *sdev, int qdepth,
-				       int reason)
-{
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
-	scsi_adjust_queue_depth(sdev, qdepth);
-	return sdev->queue_depth;
-}
-
 /*
  * Scsi host template for megaraid unified driver
  */
@@ -363,7 +344,7 @@ static struct scsi_host_template megaraid_template_g = {
 	.eh_device_reset_handler	= megaraid_reset_handler,
 	.eh_bus_reset_handler		= megaraid_reset_handler,
 	.eh_host_reset_handler		= megaraid_reset_handler,
-	.change_queue_depth		= megaraid_change_queue_depth,
+	.change_queue_depth		= scsi_change_queue_depth,
 	.use_clustering			= ENABLE_CLUSTERING,
 	.no_write_same			= 1,
 	.sdev_attrs			= megaraid_sdev_attrs,
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 69a9dd6ae04..f05580e693d 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -2591,17 +2591,6 @@ megasas_service_aen(struct megasas_instance *instance, struct megasas_cmd *cmd)
 	}
 }
 
-static int megasas_change_queue_depth(struct scsi_device *sdev,
-				      int queue_depth, int reason)
-{
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
-	scsi_adjust_queue_depth(sdev, queue_depth);
-
-	return queue_depth;
-}
-
 static ssize_t
 megasas_fw_crash_buffer_store(struct device *cdev,
 	struct device_attribute *attr, const char *buf, size_t count)
@@ -2766,7 +2755,7 @@ static struct scsi_host_template megasas_template = {
 	.shost_attrs = megaraid_host_attrs,
 	.bios_param = megasas_bios_param,
 	.use_clustering = ENABLE_CLUSTERING,
-	.change_queue_depth = megasas_change_queue_depth,
+	.change_queue_depth = scsi_change_queue_depth,
 	.no_write_same = 1,
 };
 
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index b006e1e9fcb..12229de433b 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -1222,20 +1222,18 @@ _scsih_adjust_queue_depth(struct scsi_device *sdev, int qdepth)
 		max_depth = 1;
 	if (qdepth > max_depth)
 		qdepth = max_depth;
-	scsi_adjust_queue_depth(sdev, qdepth);
+	scsi_change_queue_depth(sdev, qdepth);
 }
 
 /**
  * _scsih_change_queue_depth - setting device queue depth
  * @sdev: scsi device struct
  * @qdepth: requested queue depth
- * @reason: SCSI_QDEPTH_DEFAULT
- * (see include/scsi/scsi_host.h for definition)
  *
  * Returns queue depth.
  */
 static int
-_scsih_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
+_scsih_change_queue_depth(struct scsi_device *sdev, int qdepth)
 {
 	_scsih_adjust_queue_depth(sdev, qdepth);
 
@@ -2077,7 +2075,7 @@ _scsih_slave_configure(struct scsi_device *sdev)
 			    r_level, raid_device->handle,
 			    (unsigned long long)raid_device->wwid,
 			    raid_device->num_pds, ds);
-		_scsih_change_queue_depth(sdev, qdepth, SCSI_QDEPTH_DEFAULT);
+		_scsih_change_queue_depth(sdev, qdepth);
 		/* raid transport support */
 		if (!ioc->is_warpdrive)
 			_scsih_set_level(sdev, raid_device->volume_type);
@@ -2142,7 +2140,7 @@ _scsih_slave_configure(struct scsi_device *sdev)
 		_scsih_display_sata_capabilities(ioc, handle, sdev);
 
 
-	_scsih_change_queue_depth(sdev, qdepth, SCSI_QDEPTH_DEFAULT);
+	_scsih_change_queue_depth(sdev, qdepth);
 
 	if (ssp_target) {
 		sas_read_port_mode_page(sdev);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 568dcaed36c..de175b9915e 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -1090,20 +1090,18 @@ _scsih_adjust_queue_depth(struct scsi_device *sdev, int qdepth)
 		max_depth = 1;
 	if (qdepth > max_depth)
 		qdepth = max_depth;
-	scsi_adjust_queue_depth(sdev, qdepth);
+	scsi_change_queue_depth(sdev, qdepth);
 }
 
 /**
  * _scsih_change_queue_depth - setting device queue depth
  * @sdev: scsi device struct
  * @qdepth: requested queue depth
- * @reason: SCSI_QDEPTH_DEFAULT
- * (see include/scsi/scsi_host.h for definition)
  *
  * Returns queue depth.
  */
 static int
-_scsih_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
+_scsih_change_queue_depth(struct scsi_device *sdev, int qdepth)
 {
 	_scsih_adjust_queue_depth(sdev, qdepth);
 
@@ -1734,7 +1732,7 @@ _scsih_slave_configure(struct scsi_device *sdev)
 			 raid_device->num_pds, ds);
 
 
-		_scsih_change_queue_depth(sdev, qdepth, SCSI_QDEPTH_DEFAULT);
+		_scsih_change_queue_depth(sdev, qdepth);
 
 /* raid transport support */
 		_scsih_set_level(sdev, raid_device->volume_type);
@@ -1800,7 +1798,7 @@ _scsih_slave_configure(struct scsi_device *sdev)
 		_scsih_display_sata_capabilities(ioc, handle, sdev);
 
 
-	_scsih_change_queue_depth(sdev, qdepth, SCSI_QDEPTH_DEFAULT);
+	_scsih_change_queue_depth(sdev, qdepth);
 
 	if (ssp_target) {
 		sas_read_port_mode_page(sdev);
diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c
index 9c331b7bfdc..5b93ed810f6 100644
--- a/drivers/scsi/ncr53c8xx.c
+++ b/drivers/scsi/ncr53c8xx.c
@@ -7997,7 +7997,7 @@ static int ncr53c8xx_slave_configure(struct scsi_device *device)
 	if (depth_to_use > MAX_TAGS)
 		depth_to_use = MAX_TAGS;
 
-	scsi_adjust_queue_depth(device, depth_to_use);
+	scsi_change_queue_depth(device, depth_to_use);
 
 	/*
 	**	Since the queue depth is not tunable under Linux,
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index d8b9ba251fb..b1b1f66b1ab 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -285,23 +285,15 @@ static void pmcraid_slave_destroy(struct scsi_device *scsi_dev)
  * pmcraid_change_queue_depth - Change the device's queue depth
  * @scsi_dev: scsi device struct
  * @depth: depth to set
- * @reason: calling context
  *
  * Return value
  *	actual depth set
  */
-static int pmcraid_change_queue_depth(struct scsi_device *scsi_dev, int depth,
-				      int reason)
+static int pmcraid_change_queue_depth(struct scsi_device *scsi_dev, int depth)
 {
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		return -EOPNOTSUPP;
-
 	if (depth > PMCRAID_MAX_CMD_PER_LUN)
 		depth = PMCRAID_MAX_CMD_PER_LUN;
-
-	scsi_adjust_queue_depth(scsi_dev, depth);
-
-	return scsi_dev->queue_depth;
+	return scsi_change_queue_depth(scsi_dev, depth);
 }
 
 /**
diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c
index adedb6ef8ee..c68a66e8cfc 100644
--- a/drivers/scsi/qla1280.c
+++ b/drivers/scsi/qla1280.c
@@ -1224,9 +1224,9 @@ qla1280_slave_configure(struct scsi_device *device)
 
 	if (device->tagged_supported &&
 	    (ha->bus_settings[bus].qtag_enables & (BIT_0 << target))) {
-		scsi_adjust_queue_depth(device, ha->bus_settings[bus].hiwat);
+		scsi_change_queue_depth(device, ha->bus_settings[bus].hiwat);
 	} else {
-		scsi_adjust_queue_depth(device, default_depth);
+		scsi_change_queue_depth(device, default_depth);
 	}
 
 	nv->bus[bus].target[target].parameter.enable_sync = device->sdtr;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 20049b176b6..6b4d9235368 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -236,7 +236,6 @@ static int qla2xxx_eh_target_reset(struct scsi_cmnd *);
 static int qla2xxx_eh_bus_reset(struct scsi_cmnd *);
 static int qla2xxx_eh_host_reset(struct scsi_cmnd *);
 
-static int qla2x00_change_queue_depth(struct scsi_device *, int, int);
 static void qla2x00_clear_drv_active(struct qla_hw_data *);
 static void qla2x00_free_device(scsi_qla_host_t *);
 static void qla83xx_disable_laser(scsi_qla_host_t *vha);
@@ -258,7 +257,7 @@ struct scsi_host_template qla2xxx_driver_template = {
 	.slave_destroy		= qla2xxx_slave_destroy,
 	.scan_finished		= qla2xxx_scan_finished,
 	.scan_start		= qla2xxx_scan_start,
-	.change_queue_depth	= qla2x00_change_queue_depth,
+	.change_queue_depth	= scsi_change_queue_depth,
 	.change_queue_type	= scsi_change_queue_type,
 	.this_id		= -1,
 	.cmd_per_lun		= 3,
@@ -1406,7 +1405,7 @@ qla2xxx_slave_configure(struct scsi_device *sdev)
 	if (IS_T10_PI_CAPABLE(vha->hw))
 		blk_queue_update_dma_alignment(sdev->request_queue, 0x7);
 
-	scsi_adjust_queue_depth(sdev, req->max_q_depth);
+	scsi_change_queue_depth(sdev, req->max_q_depth);
 	return 0;
 }
 
@@ -1416,13 +1415,6 @@ qla2xxx_slave_destroy(struct scsi_device *sdev)
 	sdev->hostdata = NULL;
 }
 
-static int
-qla2x00_change_queue_depth(struct scsi_device *sdev, int qdepth, int reason)
-{
-	scsi_adjust_queue_depth(sdev, qdepth);
-	return sdev->queue_depth;
-}
-
 /**
  * qla2x00_config_dma_addressing() - Configure OS DMA addressing method.
  * @ha: HA context
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 2bfde373ea2..6d25879d87c 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -201,7 +201,7 @@ static struct scsi_host_template qla4xxx_driver_template = {
 	.eh_timed_out		= qla4xxx_eh_cmd_timed_out,
 
 	.slave_alloc		= qla4xxx_slave_alloc,
-	.change_queue_depth	= iscsi_change_queue_depth,
+	.change_queue_depth	= scsi_change_queue_depth,
 
 	.this_id		= -1,
 	.cmd_per_lun		= 3,
@@ -9059,7 +9059,7 @@ static int qla4xxx_slave_alloc(struct scsi_device *sdev)
 	if (ql4xmaxqdepth != 0 && ql4xmaxqdepth <= 0xffffU)
 		queue_depth = ql4xmaxqdepth;
 
-	scsi_adjust_queue_depth(sdev, queue_depth);
+	scsi_change_queue_depth(sdev, queue_depth);
 	return 0;
 }
 
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 106fa2f886d..5ea15fc7d2f 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -742,30 +742,18 @@ void scsi_finish_command(struct scsi_cmnd *cmd)
 }
 
 /**
- * scsi_adjust_queue_depth - Let low level drivers change a device's queue depth
+ * scsi_change_queue_depth - change a device's queue depth
  * @sdev: SCSI Device in question
- * @tags: Number of tags allowed if tagged queueing enabled,
- *        or number of commands the low level driver can
- *        queue up in non-tagged mode (as per cmd_per_lun).
+ * @depth: number of commands allowed to be queued to the driver
  *
- * Returns:	Nothing
- *
- * Lock Status:	None held on entry
- *
- * Notes:	Low level drivers may call this at any time and we will do
- * 		the right thing depending on whether or not the device is
- * 		currently active and whether or not it even has the
- * 		command blocks built yet.
+ * Sets the device queue depth and returns the new value.
  */
-void scsi_adjust_queue_depth(struct scsi_device *sdev, int tags)
+int scsi_change_queue_depth(struct scsi_device *sdev, int depth)
 {
 	unsigned long flags;
 
-	/*
-	 * refuse to set tagged depth to an unworkable size
-	 */
-	if (tags <= 0)
-		return;
+	if (depth <= 0)
+		goto out;
 
 	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
 
@@ -780,15 +768,17 @@ void scsi_adjust_queue_depth(struct scsi_device *sdev, int tags)
 	 */
 	if (!shost_use_blk_mq(sdev->host) && !sdev->host->bqt) {
 		if (blk_queue_tagged(sdev->request_queue) &&
-		    blk_queue_resize_tags(sdev->request_queue, tags) != 0)
-			goto out;
+		    blk_queue_resize_tags(sdev->request_queue, depth) != 0)
+			goto out_unlock;
 	}
 
-	sdev->queue_depth = tags;
- out:
+	sdev->queue_depth = depth;
+out_unlock:
 	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
+out:
+	return sdev->queue_depth;
 }
-EXPORT_SYMBOL(scsi_adjust_queue_depth);
+EXPORT_SYMBOL(scsi_change_queue_depth);
 
 /**
  * scsi_track_queue_full - track QUEUE_FULL events to adjust queue depth
@@ -833,12 +823,11 @@ int scsi_track_queue_full(struct scsi_device *sdev, int depth)
 	if (sdev->last_queue_full_depth < 8) {
 		/* Drop back to untagged */
 		scsi_set_tag_type(sdev, 0);
-		scsi_adjust_queue_depth(sdev, sdev->host->cmd_per_lun);
+		scsi_change_queue_depth(sdev, sdev->host->cmd_per_lun);
 		return -1;
 	}
 
-	scsi_adjust_queue_depth(sdev, depth);
-	return depth;
+	return scsi_change_queue_depth(sdev, depth);
 }
 EXPORT_SYMBOL(scsi_track_queue_full);
 
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 84cf82e0782..ce71b6d4393 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -4469,7 +4469,7 @@ sdebug_queuecommand_lock_or_not(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
 }
 
 static int
-sdebug_change_qdepth(struct scsi_device *sdev, int qdepth, int reason)
+sdebug_change_qdepth(struct scsi_device *sdev, int qdepth)
 {
 	int num_in_q = 0;
 	unsigned long iflags;
@@ -4489,7 +4489,7 @@ sdebug_change_qdepth(struct scsi_device *sdev, int qdepth, int reason)
 	/* allow to exceed max host queued_arr elements for testing */
 	if (qdepth > SCSI_DEBUG_CANQUEUE + 10)
 		qdepth = SCSI_DEBUG_CANQUEUE + 10;
-	scsi_adjust_queue_depth(sdev, qdepth);
+	scsi_change_queue_depth(sdev, qdepth);
 
 	if (SCSI_DEBUG_OPT_Q_NOISE & scsi_debug_opts) {
 		sdev_printk(KERN_INFO, sdev,
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 2d0f5155ee5..1f63559184b 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -632,7 +632,7 @@ static void scsi_handle_queue_ramp_up(struct scsi_device *sdev)
 		    tmp_sdev->queue_depth == sdev->max_queue_depth)
 			continue;
 
-		scsi_adjust_queue_depth(tmp_sdev, tmp_sdev->queue_depth + 1);
+		scsi_change_queue_depth(tmp_sdev, tmp_sdev->queue_depth + 1);
 		sdev->last_queue_ramp_up = jiffies;
 	}
 }
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index d97597e6337..0af713375db 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -292,7 +292,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 		blk_queue_init_tags(sdev->request_queue,
 				    sdev->host->cmd_per_lun, shost->bqt);
 	}
-	scsi_adjust_queue_depth(sdev, sdev->host->cmd_per_lun);
+	scsi_change_queue_depth(sdev, sdev->host->cmd_per_lun);
 
 	scsi_sysfs_device_initialize(sdev);
 
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index bffd5abdcd1..1cb64a8e18c 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -880,8 +880,7 @@ sdev_store_queue_depth(struct device *dev, struct device_attribute *attr,
 	if (depth < 1 || depth > sht->can_queue)
 		return -EINVAL;
 
-	retval = sht->change_queue_depth(sdev, depth,
-					 SCSI_QDEPTH_DEFAULT);
+	retval = sht->change_queue_depth(sdev, depth);
 	if (retval < 0)
 		return retval;
 
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index ff8befbdf17..e3ba251fb6e 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1429,7 +1429,7 @@ static void storvsc_device_destroy(struct scsi_device *sdevice)
 
 static int storvsc_device_configure(struct scsi_device *sdevice)
 {
-	scsi_adjust_queue_depth(sdevice, STORVSC_MAX_IO_REQUESTS);
+	scsi_change_queue_depth(sdevice, STORVSC_MAX_IO_REQUESTS);
 
 	blk_queue_max_segment_size(sdevice->request_queue, PAGE_SIZE);
 
diff --git a/drivers/scsi/sym53c8xx_2/sym_glue.c b/drivers/scsi/sym53c8xx_2/sym_glue.c
index 3557b385251..5d00e514ff2 100644
--- a/drivers/scsi/sym53c8xx_2/sym_glue.c
+++ b/drivers/scsi/sym53c8xx_2/sym_glue.c
@@ -820,7 +820,7 @@ static int sym53c8xx_slave_configure(struct scsi_device *sdev)
 	if (reqtags > SYM_CONF_MAX_TAG)
 		reqtags = SYM_CONF_MAX_TAG;
 	depth_to_use = reqtags ? reqtags : 1;
-	scsi_adjust_queue_depth(sdev, depth_to_use);
+	scsi_change_queue_depth(sdev, depth_to_use);
 	lp->s.scdev_depth = depth_to_use;
 	sym_tune_dev_queuing(tp, sdev->lun, reqtags);
 
diff --git a/drivers/scsi/tmscsim.c b/drivers/scsi/tmscsim.c
index 844c9a048c0..6c3c2cef389 100644
--- a/drivers/scsi/tmscsim.c
+++ b/drivers/scsi/tmscsim.c
@@ -2194,7 +2194,7 @@ static int dc390_slave_configure(struct scsi_device *sdev)
 
 	if (sdev->tagged_supported && (dcb->DevMode & TAG_QUEUEING_)) {
 		dcb->SyncMode |= EN_TAG_QUEUEING;
-		scsi_adjust_queue_depth(sdev, acb->TagMaxNum);
+		scsi_change_queue_depth(sdev, acb->TagMaxNum);
 	}
 
 	return 0;
diff --git a/drivers/scsi/u14-34f.c b/drivers/scsi/u14-34f.c
index aa0f4035afa..14eb50b95a1 100644
--- a/drivers/scsi/u14-34f.c
+++ b/drivers/scsi/u14-34f.c
@@ -696,25 +696,25 @@ static int u14_34f_slave_configure(struct scsi_device *dev) {
    if (TLDEV(dev->type) && dev->tagged_supported)
 
       if (tag_mode == TAG_SIMPLE) {
-         scsi_adjust_queue_depth(dev, tqd);
+         scsi_change_queue_depth(dev, tqd);
          tag_suffix = ", simple tags";
          }
       else if (tag_mode == TAG_ORDERED) {
-         scsi_adjust_queue_depth(dev, tqd);
+         scsi_change_queue_depth(dev, tqd);
          tag_suffix = ", ordered tags";
          }
       else {
-         scsi_adjust_queue_depth(dev, tqd);
+         scsi_change_queue_depth(dev, tqd);
          tag_suffix = ", no tags";
          }
 
    else if (TLDEV(dev->type) && linked_comm) {
-      scsi_adjust_queue_depth(dev, tqd);
+      scsi_change_queue_depth(dev, tqd);
       tag_suffix = ", untagged";
       }
 
    else {
-      scsi_adjust_queue_depth(dev, utqd);
+      scsi_change_queue_depth(dev, utqd);
       tag_suffix = "";
       }
 
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index e96ab253e3e..0c4f98ee604 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -2695,7 +2695,7 @@ static void ufshcd_set_queue_depth(struct scsi_device *sdev)
 
 	dev_dbg(hba->dev, "%s: activate tcq with queue depth %d\n",
 			__func__, lun_qdepth);
-	scsi_adjust_queue_depth(sdev, lun_qdepth);
+	scsi_change_queue_depth(sdev, lun_qdepth);
 }
 
 /*
@@ -2787,21 +2787,16 @@ static int ufshcd_slave_alloc(struct scsi_device *sdev)
  * ufshcd_change_queue_depth - change queue depth
  * @sdev: pointer to SCSI device
  * @depth: required depth to set
- * @reason: reason for changing the depth
  *
- * Change queue depth according to the reason and make sure
- * the max. limits are not crossed.
+ * Change queue depth and make sure the max. limits are not crossed.
  */
-static int ufshcd_change_queue_depth(struct scsi_device *sdev,
-		int depth, int reason)
+static int ufshcd_change_queue_depth(struct scsi_device *sdev, int depth)
 {
 	struct ufs_hba *hba = shost_priv(sdev->host);
 
 	if (depth > hba->nutrs)
 		depth = hba->nutrs;
-
-	scsi_adjust_queue_depth(sdev, depth);
-	return depth;
+	return scsi_change_queue_depth(sdev, depth);
 }
 
 /**
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 0f7e4c7ff8c..22e70126425 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -682,17 +682,13 @@ static int virtscsi_device_reset(struct scsi_cmnd *sc)
  * virtscsi_change_queue_depth() - Change a virtscsi target's queue depth
  * @sdev:	Virtscsi target whose queue depth to change
  * @qdepth:	New queue depth
- * @reason:	Reason for the queue depth change.
  */
-static int virtscsi_change_queue_depth(struct scsi_device *sdev,
-				       int qdepth,
-				       int reason)
+static int virtscsi_change_queue_depth(struct scsi_device *sdev, int qdepth)
 {
 	struct Scsi_Host *shost = sdev->host;
 	int max_depth = shost->cmd_per_lun;
 
-	scsi_adjust_queue_depth(sdev, min(max_depth, qdepth));
-	return sdev->queue_depth;
+	return scsi_change_queue_depth(sdev, min(max_depth, qdepth));
 }
 
 static int virtscsi_abort(struct scsi_cmnd *sc)
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 03ad24be728..ade1f1d013b 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -504,19 +504,11 @@ static void pvscsi_setup_all_rings(const struct pvscsi_adapter *adapter)
 	}
 }
 
-static int pvscsi_change_queue_depth(struct scsi_device *sdev,
-				     int qdepth,
-				     int reason)
+static int pvscsi_change_queue_depth(struct scsi_device *sdev, int qdepth)
 {
-	if (reason != SCSI_QDEPTH_DEFAULT)
-		/*
-		 * We support only changing default.
-		 */
-		return -EOPNOTSUPP;
-
 	if (!sdev->tagged_supported)
 		qdepth = 1;
-	scsi_adjust_queue_depth(sdev, qdepth);
+	scsi_change_queue_depth(sdev, qdepth);
 
 	if (sdev->inquiry_len > 7)
 		sdev_printk(KERN_INFO, sdev,
diff --git a/drivers/scsi/wd7000.c b/drivers/scsi/wd7000.c
index 32674236fec..f94d73611ab 100644
--- a/drivers/scsi/wd7000.c
+++ b/drivers/scsi/wd7000.c
@@ -1653,7 +1653,6 @@ static struct scsi_host_template driver_template = {
 	.can_queue		= WD7000_Q,
 	.this_id		= 7,
 	.sg_tablesize		= WD7000_SG,
-	.cmd_per_lun		= 1,
 	.unchecked_isa_dma	= 1,
 	.use_clustering		= ENABLE_CLUSTERING,
 };
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 670b75a6224..4d1b7224a7f 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -110,19 +110,6 @@ static struct device_driver tcm_loop_driverfs = {
  */
 struct device *tcm_loop_primary;
 
-/*
- * Copied from drivers/scsi/libfc/fc_fcp.c:fc_change_queue_depth() and
- * drivers/scsi/libiscsi.c:iscsi_change_queue_depth()
- */
-static int tcm_loop_change_queue_depth(
-	struct scsi_device *sdev,
-	int depth,
-	int reason)
-{
-	scsi_adjust_queue_depth(sdev, depth);
-	return sdev->queue_depth;
-}
-
 static void tcm_loop_submission_work(struct work_struct *work)
 {
 	struct tcm_loop_cmd *tl_cmd =
@@ -397,7 +384,7 @@ static struct scsi_host_template tcm_loop_driver_template = {
 	.proc_name		= "tcm_loopback",
 	.name			= "TCM_Loopback",
 	.queuecommand		= tcm_loop_queuecommand,
-	.change_queue_depth	= tcm_loop_change_queue_depth,
+	.change_queue_depth	= scsi_change_queue_depth,
 	.change_queue_type	= scsi_change_queue_type,
 	.eh_abort_handler = tcm_loop_abort_task,
 	.eh_device_reset_handler = tcm_loop_device_reset,
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 33f211b56a4..4047edfb64e 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -799,7 +799,7 @@ static int uas_slave_configure(struct scsi_device *sdev)
 	if (devinfo->flags & US_FL_NO_REPORT_OPCODES)
 		sdev->no_report_opcodes = 1;
 
-	scsi_adjust_queue_depth(sdev, devinfo->qdepth - 2);
+	scsi_change_queue_depth(sdev, devinfo->qdepth - 2);
 	return 0;
 }
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index bd5fefeaf54..bfbc817c34e 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1191,9 +1191,9 @@ extern void ata_scsi_unlock_native_capacity(struct scsi_device *sdev);
 extern int ata_scsi_slave_config(struct scsi_device *sdev);
 extern void ata_scsi_slave_destroy(struct scsi_device *sdev);
 extern int ata_scsi_change_queue_depth(struct scsi_device *sdev,
-				       int queue_depth, int reason);
+				       int queue_depth);
 extern int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev,
-				    int queue_depth, int reason);
+				    int queue_depth);
 extern struct ata_device *ata_dev_pair(struct ata_device *adev);
 extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev);
 extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap);
diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h
index 2e0cf568a9c..93d14daf099 100644
--- a/include/scsi/libfc.h
+++ b/include/scsi/libfc.h
@@ -1105,7 +1105,6 @@ int fc_eh_abort(struct scsi_cmnd *);
 int fc_eh_device_reset(struct scsi_cmnd *);
 int fc_eh_host_reset(struct scsi_cmnd *);
 int fc_slave_alloc(struct scsi_device *);
-int fc_change_queue_depth(struct scsi_device *, int qdepth, int reason);
 
 /*
  * ELS/CT interface
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index 728c9ad9feb..4d1c46aac33 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -378,8 +378,6 @@ struct iscsi_host {
 /*
  * scsi host template
  */
-extern int iscsi_change_queue_depth(struct scsi_device *sdev, int depth,
-				    int reason);
 extern int iscsi_eh_abort(struct scsi_cmnd *sc);
 extern int iscsi_eh_recover_target(struct scsi_cmnd *sc);
 extern int iscsi_eh_session_reset(struct scsi_cmnd *sc);
diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h
index ef7872c20da..1f8b33ec612 100644
--- a/include/scsi/libsas.h
+++ b/include/scsi/libsas.h
@@ -704,8 +704,7 @@ int sas_queue_up(struct sas_task *task);
 extern int sas_queuecommand(struct Scsi_Host * ,struct scsi_cmnd *);
 extern int sas_target_alloc(struct scsi_target *);
 extern int sas_slave_configure(struct scsi_device *);
-extern int sas_change_queue_depth(struct scsi_device *, int new_depth,
-				  int reason);
+extern int sas_change_queue_depth(struct scsi_device *, int new_depth);
 extern int sas_change_queue_type(struct scsi_device *, int qt);
 extern int sas_bios_param(struct scsi_device *,
 			  struct block_device *,
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 0aeaa003c3c..6364e23454d 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -380,7 +380,7 @@ extern struct scsi_device *__scsi_iterate_devices(struct Scsi_Host *,
 #define __shost_for_each_device(sdev, shost) \
 	list_for_each_entry((sdev), &((shost)->__devices), siblings)
 
-extern void scsi_adjust_queue_depth(struct scsi_device *, int);
+extern int scsi_change_queue_depth(struct scsi_device *, int);
 extern int scsi_track_queue_full(struct scsi_device *, int);
 
 extern int scsi_set_medium_removal(struct scsi_device *, char);
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index a0b13a5cd25..c8a462ef9a4 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -46,10 +46,6 @@ struct blk_queue_tags;
 #define DISABLE_CLUSTERING 0
 #define ENABLE_CLUSTERING 1
 
-enum {
-	SCSI_QDEPTH_DEFAULT,	/* default requested change, e.g. from sysfs */
-};
-
 struct scsi_host_template {
 	struct module *module;
 	const char *name;
@@ -193,7 +189,7 @@ struct scsi_host_template {
 	 * Things currently recommended to be handled at this time include:
 	 *
 	 * 1.  Setting the device queue depth.  Proper setting of this is
-	 *     described in the comments for scsi_adjust_queue_depth.
+	 *     described in the comments for scsi_change_queue_depth.
 	 * 2.  Determining if the device supports the various synchronous
 	 *     negotiation protocols.  The device struct will already have
 	 *     responded to INQUIRY and the results of the standard items
@@ -279,7 +275,7 @@ struct scsi_host_template {
 	 *
 	 * Status: OPTIONAL
 	 */
-	int (* change_queue_depth)(struct scsi_device *, int, int);
+	int (* change_queue_depth)(struct scsi_device *, int);
 
 	/*
 	 * Fill in this function to allow the changing of tag types
-- 
cgit v1.2.3-70-g09d2


From 5d26a105b5a73e5635eae0629b42fa0a90e07b7b Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 20 Nov 2014 17:05:53 -0800
Subject: crypto: prefix module autoloading with "crypto-"

This prefixes all crypto module loading with "crypto-" so we never run
the risk of exposing module auto-loading to userspace via a crypto API,
as demonstrated by Mathias Krause:

https://lkml.org/lkml/2013/3/4/70

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm/crypto/aes_glue.c                  |  4 ++--
 arch/arm/crypto/sha1_glue.c                 |  2 +-
 arch/arm/crypto/sha1_neon_glue.c            |  2 +-
 arch/arm/crypto/sha512_neon_glue.c          |  4 ++--
 arch/arm64/crypto/aes-ce-ccm-glue.c         |  2 +-
 arch/arm64/crypto/aes-glue.c                |  8 ++++----
 arch/powerpc/crypto/sha1.c                  |  2 +-
 arch/s390/crypto/aes_s390.c                 |  2 +-
 arch/s390/crypto/des_s390.c                 |  4 ++--
 arch/s390/crypto/ghash_s390.c               |  2 +-
 arch/s390/crypto/sha1_s390.c                |  2 +-
 arch/s390/crypto/sha256_s390.c              |  4 ++--
 arch/s390/crypto/sha512_s390.c              |  4 ++--
 arch/sparc/crypto/aes_glue.c                |  2 +-
 arch/sparc/crypto/camellia_glue.c           |  2 +-
 arch/sparc/crypto/crc32c_glue.c             |  2 +-
 arch/sparc/crypto/des_glue.c                |  2 +-
 arch/sparc/crypto/md5_glue.c                |  2 +-
 arch/sparc/crypto/sha1_glue.c               |  2 +-
 arch/sparc/crypto/sha256_glue.c             |  4 ++--
 arch/sparc/crypto/sha512_glue.c             |  4 ++--
 arch/x86/crypto/aes_glue.c                  |  4 ++--
 arch/x86/crypto/aesni-intel_glue.c          |  2 +-
 arch/x86/crypto/blowfish_glue.c             |  4 ++--
 arch/x86/crypto/camellia_aesni_avx2_glue.c  |  4 ++--
 arch/x86/crypto/camellia_aesni_avx_glue.c   |  4 ++--
 arch/x86/crypto/camellia_glue.c             |  4 ++--
 arch/x86/crypto/cast5_avx_glue.c            |  2 +-
 arch/x86/crypto/cast6_avx_glue.c            |  2 +-
 arch/x86/crypto/crc32-pclmul_glue.c         |  4 ++--
 arch/x86/crypto/crc32c-intel_glue.c         |  4 ++--
 arch/x86/crypto/crct10dif-pclmul_glue.c     |  4 ++--
 arch/x86/crypto/des3_ede_glue.c             |  8 ++++----
 arch/x86/crypto/ghash-clmulni-intel_glue.c  |  2 +-
 arch/x86/crypto/salsa20_glue.c              |  4 ++--
 arch/x86/crypto/serpent_avx2_glue.c         |  4 ++--
 arch/x86/crypto/serpent_avx_glue.c          |  2 +-
 arch/x86/crypto/serpent_sse2_glue.c         |  2 +-
 arch/x86/crypto/sha1_ssse3_glue.c           |  2 +-
 arch/x86/crypto/sha256_ssse3_glue.c         |  4 ++--
 arch/x86/crypto/sha512_ssse3_glue.c         |  4 ++--
 arch/x86/crypto/twofish_avx_glue.c          |  2 +-
 arch/x86/crypto/twofish_glue.c              |  4 ++--
 arch/x86/crypto/twofish_glue_3way.c         |  4 ++--
 crypto/842.c                                |  1 +
 crypto/aes_generic.c                        |  2 +-
 crypto/ansi_cprng.c                         |  2 +-
 crypto/anubis.c                             |  1 +
 crypto/api.c                                |  4 ++--
 crypto/arc4.c                               |  1 +
 crypto/blowfish_generic.c                   |  2 +-
 crypto/camellia_generic.c                   |  2 +-
 crypto/cast5_generic.c                      |  2 +-
 crypto/cast6_generic.c                      |  2 +-
 crypto/ccm.c                                |  4 ++--
 crypto/crc32.c                              |  1 +
 crypto/crc32c_generic.c                     |  2 +-
 crypto/crct10dif_generic.c                  |  2 +-
 crypto/crypto_null.c                        |  6 +++---
 crypto/ctr.c                                |  2 +-
 crypto/deflate.c                            |  2 +-
 crypto/des_generic.c                        |  2 +-
 crypto/fcrypt.c                             |  1 +
 crypto/gcm.c                                |  6 +++---
 crypto/ghash-generic.c                      |  2 +-
 crypto/khazad.c                             |  1 +
 crypto/krng.c                               |  2 +-
 crypto/lz4.c                                |  1 +
 crypto/lz4hc.c                              |  1 +
 crypto/lzo.c                                |  1 +
 crypto/md4.c                                |  2 +-
 crypto/md5.c                                |  1 +
 crypto/michael_mic.c                        |  1 +
 crypto/rmd128.c                             |  1 +
 crypto/rmd160.c                             |  1 +
 crypto/rmd256.c                             |  1 +
 crypto/rmd320.c                             |  1 +
 crypto/salsa20_generic.c                    |  2 +-
 crypto/seed.c                               |  1 +
 crypto/serpent_generic.c                    |  4 ++--
 crypto/sha1_generic.c                       |  2 +-
 crypto/sha256_generic.c                     |  4 ++--
 crypto/sha512_generic.c                     |  4 ++--
 crypto/tea.c                                |  4 ++--
 crypto/tgr192.c                             |  4 ++--
 crypto/twofish_generic.c                    |  2 +-
 crypto/wp512.c                              |  4 ++--
 crypto/zlib.c                               |  1 +
 drivers/crypto/padlock-aes.c                |  2 +-
 drivers/crypto/padlock-sha.c                |  8 ++++----
 drivers/crypto/qat/qat_common/adf_ctl_drv.c |  3 ++-
 drivers/crypto/ux500/cryp/cryp_core.c       |  4 ++--
 drivers/crypto/ux500/hash/hash_core.c       |  8 ++++----
 drivers/s390/crypto/ap_bus.c                |  3 ++-
 include/linux/crypto.h                      | 13 +++++++++++++
 95 files changed, 155 insertions(+), 123 deletions(-)

(limited to 'include')

diff --git a/arch/arm/crypto/aes_glue.c b/arch/arm/crypto/aes_glue.c
index 3003fa1f6fb..0409b8f8978 100644
--- a/arch/arm/crypto/aes_glue.c
+++ b/arch/arm/crypto/aes_glue.c
@@ -93,6 +93,6 @@ module_exit(aes_fini);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm (ASM)");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
-MODULE_ALIAS("aes-asm");
+MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("aes-asm");
 MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>");
diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c
index 84f2a756588..e31b0440c61 100644
--- a/arch/arm/crypto/sha1_glue.c
+++ b/arch/arm/crypto/sha1_glue.c
@@ -171,5 +171,5 @@ module_exit(sha1_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm (ARM)");
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
 MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>");
diff --git a/arch/arm/crypto/sha1_neon_glue.c b/arch/arm/crypto/sha1_neon_glue.c
index 6f1b411b1d5..0b0083757d4 100644
--- a/arch/arm/crypto/sha1_neon_glue.c
+++ b/arch/arm/crypto/sha1_neon_glue.c
@@ -194,4 +194,4 @@ module_exit(sha1_neon_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, NEON accelerated");
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
diff --git a/arch/arm/crypto/sha512_neon_glue.c b/arch/arm/crypto/sha512_neon_glue.c
index 0d2758ff5e1..f3452c66059 100644
--- a/arch/arm/crypto/sha512_neon_glue.c
+++ b/arch/arm/crypto/sha512_neon_glue.c
@@ -301,5 +301,5 @@ module_exit(sha512_neon_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, NEON accelerated");
 
-MODULE_ALIAS("sha512");
-MODULE_ALIAS("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index 9e6cdde9b43..0156a268e16 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -294,4 +294,4 @@ module_exit(aes_mod_exit);
 MODULE_DESCRIPTION("Synchronous AES in CCM mode using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("ccm(aes)");
+MODULE_ALIAS_CRYPTO("ccm(aes)");
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 79cd911ef88..5f63a791b2f 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -38,10 +38,10 @@ MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
 #define aes_xts_encrypt		neon_aes_xts_encrypt
 #define aes_xts_decrypt		neon_aes_xts_decrypt
 MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 NEON");
-MODULE_ALIAS("ecb(aes)");
-MODULE_ALIAS("cbc(aes)");
-MODULE_ALIAS("ctr(aes)");
-MODULE_ALIAS("xts(aes)");
+MODULE_ALIAS_CRYPTO("ecb(aes)");
+MODULE_ALIAS_CRYPTO("cbc(aes)");
+MODULE_ALIAS_CRYPTO("ctr(aes)");
+MODULE_ALIAS_CRYPTO("xts(aes)");
 #endif
 
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
diff --git a/arch/powerpc/crypto/sha1.c b/arch/powerpc/crypto/sha1.c
index f9e8b9491ef..0f88c7b4111 100644
--- a/arch/powerpc/crypto/sha1.c
+++ b/arch/powerpc/crypto/sha1.c
@@ -154,4 +154,4 @@ module_exit(sha1_powerpc_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
 
-MODULE_ALIAS("sha1-powerpc");
+MODULE_ALIAS_CRYPTO("sha1-powerpc");
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index 23223cd63e5..1f272b24fc0 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -979,7 +979,7 @@ static void __exit aes_s390_fini(void)
 module_init(aes_s390_init);
 module_exit(aes_s390_fini);
 
-MODULE_ALIAS("aes-all");
+MODULE_ALIAS_CRYPTO("aes-all");
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm");
 MODULE_LICENSE("GPL");
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 7acb77f7ef1..9e05cc453a4 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -619,8 +619,8 @@ static void __exit des_s390_exit(void)
 module_init(des_s390_init);
 module_exit(des_s390_exit);
 
-MODULE_ALIAS("des");
-MODULE_ALIAS("des3_ede");
+MODULE_ALIAS_CRYPTO("des");
+MODULE_ALIAS_CRYPTO("des3_ede");
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms");
diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c
index d43485d142e..7940dc90e80 100644
--- a/arch/s390/crypto/ghash_s390.c
+++ b/arch/s390/crypto/ghash_s390.c
@@ -160,7 +160,7 @@ static void __exit ghash_mod_exit(void)
 module_init(ghash_mod_init);
 module_exit(ghash_mod_exit);
 
-MODULE_ALIAS("ghash");
+MODULE_ALIAS_CRYPTO("ghash");
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("GHASH Message Digest Algorithm, s390 implementation");
diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c
index a1b3a9dc9d8..5b2bee32369 100644
--- a/arch/s390/crypto/sha1_s390.c
+++ b/arch/s390/crypto/sha1_s390.c
@@ -103,6 +103,6 @@ static void __exit sha1_s390_fini(void)
 module_init(sha1_s390_init);
 module_exit(sha1_s390_fini);
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c
index 9b853809a49..b74ff158108 100644
--- a/arch/s390/crypto/sha256_s390.c
+++ b/arch/s390/crypto/sha256_s390.c
@@ -143,7 +143,7 @@ static void __exit sha256_s390_fini(void)
 module_init(sha256_s390_init);
 module_exit(sha256_s390_fini);
 
-MODULE_ALIAS("sha256");
-MODULE_ALIAS("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA256 and SHA224 Secure Hash Algorithm");
diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c
index 32a81383b69..0c36989ba18 100644
--- a/arch/s390/crypto/sha512_s390.c
+++ b/arch/s390/crypto/sha512_s390.c
@@ -86,7 +86,7 @@ static struct shash_alg sha512_alg = {
 	}
 };
 
-MODULE_ALIAS("sha512");
+MODULE_ALIAS_CRYPTO("sha512");
 
 static int sha384_init(struct shash_desc *desc)
 {
@@ -126,7 +126,7 @@ static struct shash_alg sha384_alg = {
 	}
 };
 
-MODULE_ALIAS("sha384");
+MODULE_ALIAS_CRYPTO("sha384");
 
 static int __init init(void)
 {
diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c
index df922f52d76..705408766ab 100644
--- a/arch/sparc/crypto/aes_glue.c
+++ b/arch/sparc/crypto/aes_glue.c
@@ -499,6 +499,6 @@ module_exit(aes_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("AES Secure Hash Algorithm, sparc64 aes opcode accelerated");
 
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/camellia_glue.c b/arch/sparc/crypto/camellia_glue.c
index 888f6260b4e..641f55cb61c 100644
--- a/arch/sparc/crypto/camellia_glue.c
+++ b/arch/sparc/crypto/camellia_glue.c
@@ -322,6 +322,6 @@ module_exit(camellia_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, sparc64 camellia opcode accelerated");
 
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/crc32c_glue.c b/arch/sparc/crypto/crc32c_glue.c
index 5162fad912c..d1064e46efe 100644
--- a/arch/sparc/crypto/crc32c_glue.c
+++ b/arch/sparc/crypto/crc32c_glue.c
@@ -176,6 +176,6 @@ module_exit(crc32c_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CRC32c (Castagnoli), sparc64 crc32c opcode accelerated");
 
-MODULE_ALIAS("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/des_glue.c b/arch/sparc/crypto/des_glue.c
index 3065bc61f9d..d1150097299 100644
--- a/arch/sparc/crypto/des_glue.c
+++ b/arch/sparc/crypto/des_glue.c
@@ -532,6 +532,6 @@ module_exit(des_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms, sparc64 des opcode accelerated");
 
-MODULE_ALIAS("des");
+MODULE_ALIAS_CRYPTO("des");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c
index 09a9ea1dfb6..64c7ff5f72a 100644
--- a/arch/sparc/crypto/md5_glue.c
+++ b/arch/sparc/crypto/md5_glue.c
@@ -185,6 +185,6 @@ module_exit(md5_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD5 Secure Hash Algorithm, sparc64 md5 opcode accelerated");
 
-MODULE_ALIAS("md5");
+MODULE_ALIAS_CRYPTO("md5");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/sha1_glue.c b/arch/sparc/crypto/sha1_glue.c
index 6cd5f29e1e0..1b3e47accc7 100644
--- a/arch/sparc/crypto/sha1_glue.c
+++ b/arch/sparc/crypto/sha1_glue.c
@@ -180,6 +180,6 @@ module_exit(sha1_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, sparc64 sha1 opcode accelerated");
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/sha256_glue.c b/arch/sparc/crypto/sha256_glue.c
index 04f555ab268..41f27cca2a2 100644
--- a/arch/sparc/crypto/sha256_glue.c
+++ b/arch/sparc/crypto/sha256_glue.c
@@ -237,7 +237,7 @@ module_exit(sha256_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm, sparc64 sha256 opcode accelerated");
 
-MODULE_ALIAS("sha224");
-MODULE_ALIAS("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/sha512_glue.c b/arch/sparc/crypto/sha512_glue.c
index f04d1994d19..9fff88541b8 100644
--- a/arch/sparc/crypto/sha512_glue.c
+++ b/arch/sparc/crypto/sha512_glue.c
@@ -222,7 +222,7 @@ module_exit(sha512_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA-384 and SHA-512 Secure Hash Algorithm, sparc64 sha512 opcode accelerated");
 
-MODULE_ALIAS("sha384");
-MODULE_ALIAS("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
 
 #include "crop_devid.c"
diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c
index aafe8ce0d65..e26984f7ab8 100644
--- a/arch/x86/crypto/aes_glue.c
+++ b/arch/x86/crypto/aes_glue.c
@@ -66,5 +66,5 @@ module_exit(aes_fini);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, asm optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
-MODULE_ALIAS("aes-asm");
+MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("aes-asm");
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index bcebf754466..ae855f4f64b 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1546,4 +1546,4 @@ module_exit(aesni_exit);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c
index 8af519ed73d..17c05531dfd 100644
--- a/arch/x86/crypto/blowfish_glue.c
+++ b/arch/x86/crypto/blowfish_glue.c
@@ -478,5 +478,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Blowfish Cipher Algorithm, asm optimized");
-MODULE_ALIAS("blowfish");
-MODULE_ALIAS("blowfish-asm");
+MODULE_ALIAS_CRYPTO("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish-asm");
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index 4209a76fcda..9a07fafe383 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -582,5 +582,5 @@ module_exit(camellia_aesni_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX2 optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 87a041a10f4..ed38d959add 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -574,5 +574,5 @@ module_exit(camellia_aesni_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index c171dcbf192..5c8b6266a39 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -1725,5 +1725,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, asm optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index e57e20ab5e0..60ada677a92 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -491,4 +491,4 @@ module_exit(cast5_exit);
 
 MODULE_DESCRIPTION("Cast5 Cipher Algorithm, AVX optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("cast5");
+MODULE_ALIAS_CRYPTO("cast5");
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index 09f3677393e..0160f68a57f 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -611,4 +611,4 @@ module_exit(cast6_exit);
 
 MODULE_DESCRIPTION("Cast6 Cipher Algorithm, AVX optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("cast6");
+MODULE_ALIAS_CRYPTO("cast6");
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index 9d014a74ef9..1937fc1d876 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -197,5 +197,5 @@ module_exit(crc32_pclmul_mod_fini);
 MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
 MODULE_LICENSE("GPL");
 
-MODULE_ALIAS("crc32");
-MODULE_ALIAS("crc32-pclmul");
+MODULE_ALIAS_CRYPTO("crc32");
+MODULE_ALIAS_CRYPTO("crc32-pclmul");
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 6812ad98355..28640c3d6af 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -280,5 +280,5 @@ MODULE_AUTHOR("Austin Zhang <austin.zhang@intel.com>, Kent Liu <kent.liu@intel.c
 MODULE_DESCRIPTION("CRC32c (Castagnoli) optimization using Intel Hardware.");
 MODULE_LICENSE("GPL");
 
-MODULE_ALIAS("crc32c");
-MODULE_ALIAS("crc32c-intel");
+MODULE_ALIAS_CRYPTO("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c-intel");
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index 7845d7fd54c..b6c67bf30fd 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -147,5 +147,5 @@ MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
 MODULE_DESCRIPTION("T10 DIF CRC calculation accelerated with PCLMULQDQ.");
 MODULE_LICENSE("GPL");
 
-MODULE_ALIAS("crct10dif");
-MODULE_ALIAS("crct10dif-pclmul");
+MODULE_ALIAS_CRYPTO("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif-pclmul");
diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c
index 0e9c0668fe4..38a14f818ef 100644
--- a/arch/x86/crypto/des3_ede_glue.c
+++ b/arch/x86/crypto/des3_ede_glue.c
@@ -502,8 +502,8 @@ module_exit(des3_ede_x86_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Triple DES EDE Cipher Algorithm, asm optimized");
-MODULE_ALIAS("des3_ede");
-MODULE_ALIAS("des3_ede-asm");
-MODULE_ALIAS("des");
-MODULE_ALIAS("des-asm");
+MODULE_ALIAS_CRYPTO("des3_ede");
+MODULE_ALIAS_CRYPTO("des3_ede-asm");
+MODULE_ALIAS_CRYPTO("des");
+MODULE_ALIAS_CRYPTO("des-asm");
 MODULE_AUTHOR("Jussi Kivilinna <jussi.kivilinna@iki.fi>");
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 88bb7ba8b17..8253d85aa16 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -341,4 +341,4 @@ module_exit(ghash_pclmulqdqni_mod_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("GHASH Message Digest Algorithm, "
 		   "acclerated by PCLMULQDQ-NI");
-MODULE_ALIAS("ghash");
+MODULE_ALIAS_CRYPTO("ghash");
diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c
index 5e8e67739bb..399a29d067d 100644
--- a/arch/x86/crypto/salsa20_glue.c
+++ b/arch/x86/crypto/salsa20_glue.c
@@ -119,5 +119,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm (optimized assembly version)");
-MODULE_ALIAS("salsa20");
-MODULE_ALIAS("salsa20-asm");
+MODULE_ALIAS_CRYPTO("salsa20");
+MODULE_ALIAS_CRYPTO("salsa20-asm");
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 2fae489b152..437e47a4d30 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -558,5 +558,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX2 optimized");
-MODULE_ALIAS("serpent");
-MODULE_ALIAS("serpent-asm");
+MODULE_ALIAS_CRYPTO("serpent");
+MODULE_ALIAS_CRYPTO("serpent-asm");
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index ff487087097..7e217398b4e 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -617,4 +617,4 @@ module_exit(serpent_exit);
 
 MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("serpent");
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index 8c95f863730..bf025adaea0 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -618,4 +618,4 @@ module_exit(serpent_sse2_exit);
 
 MODULE_DESCRIPTION("Serpent Cipher Algorithm, SSE2 optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("serpent");
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 74d16ef707c..6c20fe04a73 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -278,4 +278,4 @@ module_exit(sha1_ssse3_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index f248546da1c..4dc100d8290 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -318,5 +318,5 @@ module_exit(sha256_ssse3_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
-MODULE_ALIAS("sha256");
-MODULE_ALIAS("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index 8626b03e83b..26a5898a6f2 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -326,5 +326,5 @@ module_exit(sha512_ssse3_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
-MODULE_ALIAS("sha512");
-MODULE_ALIAS("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index 4e3c665be12..1ac531ea9bc 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -579,4 +579,4 @@ module_exit(twofish_exit);
 
 MODULE_DESCRIPTION("Twofish Cipher Algorithm, AVX optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("twofish");
+MODULE_ALIAS_CRYPTO("twofish");
diff --git a/arch/x86/crypto/twofish_glue.c b/arch/x86/crypto/twofish_glue.c
index 0a520230350..77e06c2da83 100644
--- a/arch/x86/crypto/twofish_glue.c
+++ b/arch/x86/crypto/twofish_glue.c
@@ -96,5 +96,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION ("Twofish Cipher Algorithm, asm optimized");
-MODULE_ALIAS("twofish");
-MODULE_ALIAS("twofish-asm");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-asm");
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 13e63b3e1df..56d8a08ee47 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -495,5 +495,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Twofish Cipher Algorithm, 3-way parallel asm optimized");
-MODULE_ALIAS("twofish");
-MODULE_ALIAS("twofish-asm");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-asm");
diff --git a/crypto/842.c b/crypto/842.c
index 65c7a89cfa0..b48f4f108c4 100644
--- a/crypto/842.c
+++ b/crypto/842.c
@@ -180,3 +180,4 @@ module_exit(nx842_mod_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("842 Compression Algorithm");
+MODULE_ALIAS_CRYPTO("842");
diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c
index fd0d6b45497..9b3c54c1cbe 100644
--- a/crypto/aes_generic.c
+++ b/crypto/aes_generic.c
@@ -1474,4 +1474,4 @@ module_exit(aes_fini);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
diff --git a/crypto/ansi_cprng.c b/crypto/ansi_cprng.c
index 666f1962a16..b4485a10838 100644
--- a/crypto/ansi_cprng.c
+++ b/crypto/ansi_cprng.c
@@ -476,4 +476,4 @@ module_param(dbg, int, 0);
 MODULE_PARM_DESC(dbg, "Boolean to enable debugging (0/1 == off/on)");
 module_init(prng_mod_init);
 module_exit(prng_mod_fini);
-MODULE_ALIAS("stdrng");
+MODULE_ALIAS_CRYPTO("stdrng");
diff --git a/crypto/anubis.c b/crypto/anubis.c
index 008c8a4fb67..4bb187c2a90 100644
--- a/crypto/anubis.c
+++ b/crypto/anubis.c
@@ -704,3 +704,4 @@ module_exit(anubis_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Anubis Cryptographic Algorithm");
+MODULE_ALIAS_CRYPTO("anubis");
diff --git a/crypto/api.c b/crypto/api.c
index a2b39c5f364..2a81e98a002 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -216,11 +216,11 @@ struct crypto_alg *crypto_larval_lookup(const char *name, u32 type, u32 mask)
 
 	alg = crypto_alg_lookup(name, type, mask);
 	if (!alg) {
-		request_module("%s", name);
+		request_module("crypto-%s", name);
 
 		if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask &
 		      CRYPTO_ALG_NEED_FALLBACK))
-			request_module("%s-all", name);
+			request_module("crypto-%s-all", name);
 
 		alg = crypto_alg_lookup(name, type, mask);
 	}
diff --git a/crypto/arc4.c b/crypto/arc4.c
index 5a772c3657d..f1a81925558 100644
--- a/crypto/arc4.c
+++ b/crypto/arc4.c
@@ -166,3 +166,4 @@ module_exit(arc4_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("ARC4 Cipher Algorithm");
 MODULE_AUTHOR("Jon Oberheide <jon@oberheide.org>");
+MODULE_ALIAS_CRYPTO("arc4");
diff --git a/crypto/blowfish_generic.c b/crypto/blowfish_generic.c
index 8baf5447d35..7bd71f02d0d 100644
--- a/crypto/blowfish_generic.c
+++ b/crypto/blowfish_generic.c
@@ -138,4 +138,4 @@ module_exit(blowfish_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Blowfish Cipher Algorithm");
-MODULE_ALIAS("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish");
diff --git a/crypto/camellia_generic.c b/crypto/camellia_generic.c
index 26bcd7a2d6b..1b74c5a3e89 100644
--- a/crypto/camellia_generic.c
+++ b/crypto/camellia_generic.c
@@ -1098,4 +1098,4 @@ module_exit(camellia_fini);
 
 MODULE_DESCRIPTION("Camellia Cipher Algorithm");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("camellia");
+MODULE_ALIAS_CRYPTO("camellia");
diff --git a/crypto/cast5_generic.c b/crypto/cast5_generic.c
index 5558f630a0e..84c86db67ec 100644
--- a/crypto/cast5_generic.c
+++ b/crypto/cast5_generic.c
@@ -549,4 +549,4 @@ module_exit(cast5_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Cast5 Cipher Algorithm");
-MODULE_ALIAS("cast5");
+MODULE_ALIAS_CRYPTO("cast5");
diff --git a/crypto/cast6_generic.c b/crypto/cast6_generic.c
index de732528a43..f408f0bd8de 100644
--- a/crypto/cast6_generic.c
+++ b/crypto/cast6_generic.c
@@ -291,4 +291,4 @@ module_exit(cast6_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Cast6 Cipher Algorithm");
-MODULE_ALIAS("cast6");
+MODULE_ALIAS_CRYPTO("cast6");
diff --git a/crypto/ccm.c b/crypto/ccm.c
index 1df84217f7c..647575b4128 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -879,5 +879,5 @@ module_exit(crypto_ccm_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Counter with CBC MAC");
-MODULE_ALIAS("ccm_base");
-MODULE_ALIAS("rfc4309");
+MODULE_ALIAS_CRYPTO("ccm_base");
+MODULE_ALIAS_CRYPTO("rfc4309");
diff --git a/crypto/crc32.c b/crypto/crc32.c
index 9d1c4156989..187ded28cb0 100644
--- a/crypto/crc32.c
+++ b/crypto/crc32.c
@@ -156,3 +156,4 @@ module_exit(crc32_mod_fini);
 MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
 MODULE_DESCRIPTION("CRC32 calculations wrapper for lib/crc32");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("crc32");
diff --git a/crypto/crc32c_generic.c b/crypto/crc32c_generic.c
index d9c7beba8e5..2a062025749 100644
--- a/crypto/crc32c_generic.c
+++ b/crypto/crc32c_generic.c
@@ -170,5 +170,5 @@ module_exit(crc32c_mod_fini);
 MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>");
 MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c");
 MODULE_SOFTDEP("pre: crc32c");
diff --git a/crypto/crct10dif_generic.c b/crypto/crct10dif_generic.c
index 877e7114ec5..08bb4f50452 100644
--- a/crypto/crct10dif_generic.c
+++ b/crypto/crct10dif_generic.c
@@ -124,4 +124,4 @@ module_exit(crct10dif_mod_fini);
 MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
 MODULE_DESCRIPTION("T10 DIF CRC calculation.");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif");
diff --git a/crypto/crypto_null.c b/crypto/crypto_null.c
index 1dc54bb95a8..a20319132e3 100644
--- a/crypto/crypto_null.c
+++ b/crypto/crypto_null.c
@@ -145,9 +145,9 @@ static struct crypto_alg null_algs[3] = { {
 	.coa_decompress		=	null_compress } }
 } };
 
-MODULE_ALIAS("compress_null");
-MODULE_ALIAS("digest_null");
-MODULE_ALIAS("cipher_null");
+MODULE_ALIAS_CRYPTO("compress_null");
+MODULE_ALIAS_CRYPTO("digest_null");
+MODULE_ALIAS_CRYPTO("cipher_null");
 
 static int __init crypto_null_mod_init(void)
 {
diff --git a/crypto/ctr.c b/crypto/ctr.c
index f2b94f27bb2..3d81ff7e6b4 100644
--- a/crypto/ctr.c
+++ b/crypto/ctr.c
@@ -466,4 +466,4 @@ module_exit(crypto_ctr_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CTR Counter block mode");
-MODULE_ALIAS("rfc3686");
+MODULE_ALIAS_CRYPTO("rfc3686");
diff --git a/crypto/deflate.c b/crypto/deflate.c
index b57d70eb156..95d8d37c502 100644
--- a/crypto/deflate.c
+++ b/crypto/deflate.c
@@ -222,4 +222,4 @@ module_exit(deflate_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Deflate Compression Algorithm for IPCOMP");
 MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
-
+MODULE_ALIAS_CRYPTO("deflate");
diff --git a/crypto/des_generic.c b/crypto/des_generic.c
index 298d464ab7d..42912948776 100644
--- a/crypto/des_generic.c
+++ b/crypto/des_generic.c
@@ -983,7 +983,7 @@ static struct crypto_alg des_algs[2] = { {
 	.cia_decrypt		=	des3_ede_decrypt } }
 } };
 
-MODULE_ALIAS("des3_ede");
+MODULE_ALIAS_CRYPTO("des3_ede");
 
 static int __init des_generic_mod_init(void)
 {
diff --git a/crypto/fcrypt.c b/crypto/fcrypt.c
index 021d7fec6bc..77286ea2886 100644
--- a/crypto/fcrypt.c
+++ b/crypto/fcrypt.c
@@ -420,3 +420,4 @@ module_exit(fcrypt_mod_fini);
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_DESCRIPTION("FCrypt Cipher Algorithm");
 MODULE_AUTHOR("David Howells <dhowells@redhat.com>");
+MODULE_ALIAS_CRYPTO("fcrypt");
diff --git a/crypto/gcm.c b/crypto/gcm.c
index 276cdac567b..aefb74a3f52 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -1441,6 +1441,6 @@ module_exit(crypto_gcm_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Galois/Counter Mode");
 MODULE_AUTHOR("Mikko Herranen <mh1@iki.fi>");
-MODULE_ALIAS("gcm_base");
-MODULE_ALIAS("rfc4106");
-MODULE_ALIAS("rfc4543");
+MODULE_ALIAS_CRYPTO("gcm_base");
+MODULE_ALIAS_CRYPTO("rfc4106");
+MODULE_ALIAS_CRYPTO("rfc4543");
diff --git a/crypto/ghash-generic.c b/crypto/ghash-generic.c
index 9d3f0c69a86..4e97fae9666 100644
--- a/crypto/ghash-generic.c
+++ b/crypto/ghash-generic.c
@@ -172,4 +172,4 @@ module_exit(ghash_mod_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("GHASH Message Digest Algorithm");
-MODULE_ALIAS("ghash");
+MODULE_ALIAS_CRYPTO("ghash");
diff --git a/crypto/khazad.c b/crypto/khazad.c
index 60e7cd66fac..873eb5ded6d 100644
--- a/crypto/khazad.c
+++ b/crypto/khazad.c
@@ -880,3 +880,4 @@ module_exit(khazad_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Khazad Cryptographic Algorithm");
+MODULE_ALIAS_CRYPTO("khazad");
diff --git a/crypto/krng.c b/crypto/krng.c
index a2d2b72fc13..67c88b33121 100644
--- a/crypto/krng.c
+++ b/crypto/krng.c
@@ -62,4 +62,4 @@ module_exit(krng_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Kernel Random Number Generator");
-MODULE_ALIAS("stdrng");
+MODULE_ALIAS_CRYPTO("stdrng");
diff --git a/crypto/lz4.c b/crypto/lz4.c
index 34d072b72a7..aefbceaf310 100644
--- a/crypto/lz4.c
+++ b/crypto/lz4.c
@@ -104,3 +104,4 @@ module_exit(lz4_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("LZ4 Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lz4");
diff --git a/crypto/lz4hc.c b/crypto/lz4hc.c
index 9218b3fed5e..a1d3b5bd3d8 100644
--- a/crypto/lz4hc.c
+++ b/crypto/lz4hc.c
@@ -104,3 +104,4 @@ module_exit(lz4hc_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("LZ4HC Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lz4hc");
diff --git a/crypto/lzo.c b/crypto/lzo.c
index a8ff2f778dc..4b3e92525da 100644
--- a/crypto/lzo.c
+++ b/crypto/lzo.c
@@ -107,3 +107,4 @@ module_exit(lzo_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("LZO Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lzo");
diff --git a/crypto/md4.c b/crypto/md4.c
index 0477a6a01d5..3515af425cc 100644
--- a/crypto/md4.c
+++ b/crypto/md4.c
@@ -255,4 +255,4 @@ module_exit(md4_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD4 Message Digest Algorithm");
-
+MODULE_ALIAS_CRYPTO("md4");
diff --git a/crypto/md5.c b/crypto/md5.c
index 7febeaab923..36f5e5b103f 100644
--- a/crypto/md5.c
+++ b/crypto/md5.c
@@ -168,3 +168,4 @@ module_exit(md5_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD5 Message Digest Algorithm");
+MODULE_ALIAS_CRYPTO("md5");
diff --git a/crypto/michael_mic.c b/crypto/michael_mic.c
index 079b761bc70..46195e0d0f4 100644
--- a/crypto/michael_mic.c
+++ b/crypto/michael_mic.c
@@ -184,3 +184,4 @@ module_exit(michael_mic_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Michael MIC");
 MODULE_AUTHOR("Jouni Malinen <j@w1.fi>");
+MODULE_ALIAS_CRYPTO("michael_mic");
diff --git a/crypto/rmd128.c b/crypto/rmd128.c
index 8a0f68b7f25..049486ede93 100644
--- a/crypto/rmd128.c
+++ b/crypto/rmd128.c
@@ -327,3 +327,4 @@ module_exit(rmd128_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
 MODULE_DESCRIPTION("RIPEMD-128 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd128");
diff --git a/crypto/rmd160.c b/crypto/rmd160.c
index 525d7bb752c..de585e51d45 100644
--- a/crypto/rmd160.c
+++ b/crypto/rmd160.c
@@ -371,3 +371,4 @@ module_exit(rmd160_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
 MODULE_DESCRIPTION("RIPEMD-160 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd160");
diff --git a/crypto/rmd256.c b/crypto/rmd256.c
index 69293d9b56e..4ec02a754e0 100644
--- a/crypto/rmd256.c
+++ b/crypto/rmd256.c
@@ -346,3 +346,4 @@ module_exit(rmd256_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
 MODULE_DESCRIPTION("RIPEMD-256 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd256");
diff --git a/crypto/rmd320.c b/crypto/rmd320.c
index 09f97dfdfbb..770f2cb369f 100644
--- a/crypto/rmd320.c
+++ b/crypto/rmd320.c
@@ -395,3 +395,4 @@ module_exit(rmd320_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
 MODULE_DESCRIPTION("RIPEMD-320 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd320");
diff --git a/crypto/salsa20_generic.c b/crypto/salsa20_generic.c
index 9a4770c0228..3d0f9df30ac 100644
--- a/crypto/salsa20_generic.c
+++ b/crypto/salsa20_generic.c
@@ -248,4 +248,4 @@ module_exit(salsa20_generic_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm");
-MODULE_ALIAS("salsa20");
+MODULE_ALIAS_CRYPTO("salsa20");
diff --git a/crypto/seed.c b/crypto/seed.c
index 9c904d6d215..c6ba8438be4 100644
--- a/crypto/seed.c
+++ b/crypto/seed.c
@@ -476,3 +476,4 @@ module_exit(seed_fini);
 MODULE_DESCRIPTION("SEED Cipher Algorithm");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Hye-Shik Chang <perky@FreeBSD.org>, Kim Hyun <hkim@kisa.or.kr>");
+MODULE_ALIAS_CRYPTO("seed");
diff --git a/crypto/serpent_generic.c b/crypto/serpent_generic.c
index 7ddbd7e8885..a53b5e2af33 100644
--- a/crypto/serpent_generic.c
+++ b/crypto/serpent_generic.c
@@ -665,5 +665,5 @@ module_exit(serpent_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Serpent and tnepres (kerneli compatible serpent reversed) Cipher Algorithm");
 MODULE_AUTHOR("Dag Arne Osvik <osvik@ii.uib.no>");
-MODULE_ALIAS("tnepres");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("tnepres");
+MODULE_ALIAS_CRYPTO("serpent");
diff --git a/crypto/sha1_generic.c b/crypto/sha1_generic.c
index 7bb04743278..039e58cfa15 100644
--- a/crypto/sha1_generic.c
+++ b/crypto/sha1_generic.c
@@ -153,4 +153,4 @@ module_exit(sha1_generic_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
diff --git a/crypto/sha256_generic.c b/crypto/sha256_generic.c
index 65e7b76b057..5eb21b12003 100644
--- a/crypto/sha256_generic.c
+++ b/crypto/sha256_generic.c
@@ -384,5 +384,5 @@ module_exit(sha256_generic_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm");
 
-MODULE_ALIAS("sha224");
-MODULE_ALIAS("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c
index 95db67197cd..8d0b19ed4f4 100644
--- a/crypto/sha512_generic.c
+++ b/crypto/sha512_generic.c
@@ -288,5 +288,5 @@ module_exit(sha512_generic_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA-512 and SHA-384 Secure Hash Algorithms");
 
-MODULE_ALIAS("sha384");
-MODULE_ALIAS("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
diff --git a/crypto/tea.c b/crypto/tea.c
index 0a572323ee4..495be2d0077 100644
--- a/crypto/tea.c
+++ b/crypto/tea.c
@@ -270,8 +270,8 @@ static void __exit tea_mod_fini(void)
 	crypto_unregister_algs(tea_algs, ARRAY_SIZE(tea_algs));
 }
 
-MODULE_ALIAS("xtea");
-MODULE_ALIAS("xeta");
+MODULE_ALIAS_CRYPTO("xtea");
+MODULE_ALIAS_CRYPTO("xeta");
 
 module_init(tea_mod_init);
 module_exit(tea_mod_fini);
diff --git a/crypto/tgr192.c b/crypto/tgr192.c
index 3c7af0d1ff7..6e5651c66cf 100644
--- a/crypto/tgr192.c
+++ b/crypto/tgr192.c
@@ -676,8 +676,8 @@ static void __exit tgr192_mod_fini(void)
 	crypto_unregister_shashes(tgr_algs, ARRAY_SIZE(tgr_algs));
 }
 
-MODULE_ALIAS("tgr160");
-MODULE_ALIAS("tgr128");
+MODULE_ALIAS_CRYPTO("tgr160");
+MODULE_ALIAS_CRYPTO("tgr128");
 
 module_init(tgr192_mod_init);
 module_exit(tgr192_mod_fini);
diff --git a/crypto/twofish_generic.c b/crypto/twofish_generic.c
index 2d5000552d0..523ad8c4e35 100644
--- a/crypto/twofish_generic.c
+++ b/crypto/twofish_generic.c
@@ -211,4 +211,4 @@ module_exit(twofish_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION ("Twofish Cipher Algorithm");
-MODULE_ALIAS("twofish");
+MODULE_ALIAS_CRYPTO("twofish");
diff --git a/crypto/wp512.c b/crypto/wp512.c
index ec64e7762fb..0de42eb3d04 100644
--- a/crypto/wp512.c
+++ b/crypto/wp512.c
@@ -1167,8 +1167,8 @@ static void __exit wp512_mod_fini(void)
 	crypto_unregister_shashes(wp_algs, ARRAY_SIZE(wp_algs));
 }
 
-MODULE_ALIAS("wp384");
-MODULE_ALIAS("wp256");
+MODULE_ALIAS_CRYPTO("wp384");
+MODULE_ALIAS_CRYPTO("wp256");
 
 module_init(wp512_mod_init);
 module_exit(wp512_mod_fini);
diff --git a/crypto/zlib.c b/crypto/zlib.c
index c9ee681d57f..0eefa9d237a 100644
--- a/crypto/zlib.c
+++ b/crypto/zlib.c
@@ -378,3 +378,4 @@ module_exit(zlib_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Zlib Compression Algorithm");
 MODULE_AUTHOR("Sony Corporation");
+MODULE_ALIAS_CRYPTO("zlib");
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index 633ba945e15..c178ed8c390 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -563,4 +563,4 @@ MODULE_DESCRIPTION("VIA PadLock AES algorithm support");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Michal Ludvig");
 
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index bace885634f..95f7d27ce49 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -593,7 +593,7 @@ MODULE_DESCRIPTION("VIA PadLock SHA1/SHA256 algorithms support.");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Michal Ludvig");
 
-MODULE_ALIAS("sha1-all");
-MODULE_ALIAS("sha256-all");
-MODULE_ALIAS("sha1-padlock");
-MODULE_ALIAS("sha256-padlock");
+MODULE_ALIAS_CRYPTO("sha1-all");
+MODULE_ALIAS_CRYPTO("sha256-all");
+MODULE_ALIAS_CRYPTO("sha1-padlock");
+MODULE_ALIAS_CRYPTO("sha256-padlock");
diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
index 244d73378f0..7ee93f881db 100644
--- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c
+++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
@@ -52,6 +52,7 @@
 #include <linux/pci.h>
 #include <linux/cdev.h>
 #include <linux/uaccess.h>
+#include <linux/crypto.h>
 
 #include "adf_accel_devices.h"
 #include "adf_common_drv.h"
@@ -487,4 +488,4 @@ module_exit(adf_unregister_ctl_device_driver);
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel");
 MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
-MODULE_ALIAS("intel_qat");
+MODULE_ALIAS_CRYPTO("intel_qat");
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index 83811aab207..7c035de9055 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -1812,7 +1812,7 @@ module_exit(ux500_cryp_mod_fini);
 module_param(cryp_mode, int, 0);
 
 MODULE_DESCRIPTION("Driver for ST-Ericsson UX500 CRYP crypto engine.");
-MODULE_ALIAS("aes-all");
-MODULE_ALIAS("des-all");
+MODULE_ALIAS_CRYPTO("aes-all");
+MODULE_ALIAS_CRYPTO("des-all");
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index 5af53b5508b..76ecc8d143d 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -1997,7 +1997,7 @@ module_exit(ux500_hash_mod_fini);
 MODULE_DESCRIPTION("Driver for ST-Ericsson UX500 HASH engine.");
 MODULE_LICENSE("GPL");
 
-MODULE_ALIAS("sha1-all");
-MODULE_ALIAS("sha256-all");
-MODULE_ALIAS("hmac-sha1-all");
-MODULE_ALIAS("hmac-sha256-all");
+MODULE_ALIAS_CRYPTO("sha1-all");
+MODULE_ALIAS_CRYPTO("sha256-all");
+MODULE_ALIAS_CRYPTO("hmac-sha1-all");
+MODULE_ALIAS_CRYPTO("hmac-sha256-all");
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 99485415dcc..91e97ec0141 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -44,6 +44,7 @@
 #include <linux/hrtimer.h>
 #include <linux/ktime.h>
 #include <asm/facility.h>
+#include <linux/crypto.h>
 
 #include "ap_bus.h"
 
@@ -71,7 +72,7 @@ MODULE_AUTHOR("IBM Corporation");
 MODULE_DESCRIPTION("Adjunct Processor Bus driver, " \
 		   "Copyright IBM Corp. 2006, 2012");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("z90crypt");
+MODULE_ALIAS_CRYPTO("z90crypt");
 
 /*
  * Module parameter
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 208a63290b2..9c8776d0ada 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -25,6 +25,19 @@
 #include <linux/string.h>
 #include <linux/uaccess.h>
 
+/*
+ * Autoloaded crypto modules should only use a prefixed name to avoid allowing
+ * arbitrary modules to be loaded. Loading from userspace may still need the
+ * unprefixed names, so retains those aliases as well.
+ * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3
+ * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro
+ * expands twice on the same line. Instead, use a separate base name for the
+ * alias.
+ */
+#define MODULE_ALIAS_CRYPTO(name)	\
+		__MODULE_INFO(alias, alias_userspace, name);	\
+		__MODULE_INFO(alias, alias_crypto, "crypto-" name)
+
 /*
  * Algorithm masks and types.
  */
-- 
cgit v1.2.3-70-g09d2


From 394ffa503bc40e32d7f54a9b817264e81ce131b4 Mon Sep 17 00:00:00 2001
From: Gu Zheng <guz.fnst@cn.fujitsu.com>
Date: Mon, 24 Nov 2014 11:05:22 +0800
Subject: blk: introduce generic io stat accounting help function

Many block drivers accounting io stat based on bio (e.g. NVMe...),
the blk_account_io_start/end() which is based on request
does not make sense to them, so here we introduce the similar help
function named generic_start/end_io_acct base on raw sectors, and it can
simplify some driver's open io accounting code.

Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/bio.c         | 28 ++++++++++++++++++++++++++++
 include/linux/bio.h |  5 +++++
 2 files changed, 33 insertions(+)

(limited to 'include')

diff --git a/block/bio.c b/block/bio.c
index 3e6e1986a5b..3d4a072375e 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1739,6 +1739,34 @@ void bio_check_pages_dirty(struct bio *bio)
 	}
 }
 
+void generic_start_io_acct(int rw, unsigned long sectors,
+			   struct hd_struct *part)
+{
+	int cpu = part_stat_lock();
+
+	part_round_stats(cpu, part);
+	part_stat_inc(cpu, part, ios[rw]);
+	part_stat_add(cpu, part, sectors[rw], sectors);
+	part_inc_in_flight(part, rw);
+
+	part_stat_unlock();
+}
+EXPORT_SYMBOL(generic_start_io_acct);
+
+void generic_end_io_acct(int rw, struct hd_struct *part,
+			 unsigned long start_time)
+{
+	unsigned long duration = jiffies - start_time;
+	int cpu = part_stat_lock();
+
+	part_stat_add(cpu, part, ticks[rw], duration);
+	part_round_stats(cpu, part);
+	part_dec_in_flight(part, rw);
+
+	part_stat_unlock();
+}
+EXPORT_SYMBOL(generic_end_io_acct);
+
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
 void bio_flush_dcache_pages(struct bio *bi)
 {
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 7347f486cec..efead0b532c 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -443,6 +443,11 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int,
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
 
+void generic_start_io_acct(int rw, unsigned long sectors,
+			   struct hd_struct *part);
+void generic_end_io_acct(int rw, struct hd_struct *part,
+			 unsigned long start_time);
+
 #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
 # error	"You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
 #endif
-- 
cgit v1.2.3-70-g09d2


From a1c8a5512b7cddc81767172f0de37b155cea039f Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.wolfsonmicro.com>
Date: Mon, 24 Nov 2014 14:10:52 +0000
Subject: regulator: core: Add PRE_DISABLE notification

Add a PRE_DISABLE notification so that consumers can use a
notifier to run any steps required to prepare for the
regulator being switched off. Since the regulator disable
can fail an abort notification is also added.

Signed-off-by: Richard Fitzgerald <rf@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/core.c           | 16 ++++++++++++++++
 include/linux/regulator/consumer.h |  4 ++++
 2 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index cd87c0c3703..53de911a095 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1976,9 +1976,18 @@ static int _regulator_disable(struct regulator_dev *rdev)
 
 		/* we are last user */
 		if (_regulator_can_change_status(rdev)) {
+			ret = _notifier_call_chain(rdev,
+						   REGULATOR_EVENT_PRE_DISABLE,
+						   NULL);
+			if (ret & NOTIFY_STOP_MASK)
+				return -EINVAL;
+
 			ret = _regulator_do_disable(rdev);
 			if (ret < 0) {
 				rdev_err(rdev, "failed to disable\n");
+				_notifier_call_chain(rdev,
+						REGULATOR_EVENT_ABORT_DISABLE,
+						NULL);
 				return ret;
 			}
 			_notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE,
@@ -2035,9 +2044,16 @@ static int _regulator_force_disable(struct regulator_dev *rdev)
 {
 	int ret = 0;
 
+	ret = _notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE |
+			REGULATOR_EVENT_PRE_DISABLE, NULL);
+	if (ret & NOTIFY_STOP_MASK)
+		return -EINVAL;
+
 	ret = _regulator_do_disable(rdev);
 	if (ret < 0) {
 		rdev_err(rdev, "failed to force disable\n");
+		_notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE |
+				REGULATOR_EVENT_ABORT_DISABLE, NULL);
 		return ret;
 	}
 
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index d347c805f92..9efddd2a63e 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -99,6 +99,8 @@ struct regmap;
  *                      Data passed is "struct pre_voltage_change_data"
  * ABORT_VOLTAGE_CHANGE Regulator voltage change failed for some reason.
  *                      Data passed is old voltage cast to (void *).
+ * PRE_DISABLE    Regulator is about to be disabled
+ * ABORT_DISABLE  Regulator disable failed for some reason
  *
  * NOTE: These events can be OR'ed together when passed into handler.
  */
@@ -113,6 +115,8 @@ struct regmap;
 #define REGULATOR_EVENT_DISABLE 		0x80
 #define REGULATOR_EVENT_PRE_VOLTAGE_CHANGE	0x100
 #define REGULATOR_EVENT_ABORT_VOLTAGE_CHANGE	0x200
+#define REGULATOR_EVENT_PRE_DISABLE		0x400
+#define REGULATOR_EVENT_ABORT_DISABLE		0x800
 
 /**
  * struct pre_voltage_change_data - Data sent with PRE_VOLTAGE_CHANGE event
-- 
cgit v1.2.3-70-g09d2


From c9eab58f6466cef3d9cd760a96e4de5e060e5195 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 24 Nov 2014 15:27:17 +0100
Subject: KVM: x86: move device assignment out of kvm_host.h

Create a new header, and hide the device assignment functions there.
Move struct kvm_assigned_dev_kernel to assigned-dev.c by modifying
arch/x86/kvm/iommu.c to take a PCI device struct.

Based on a patch by Radim Krcmar <rkrcmark@redhat.com>.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h | 23 -----------------------
 arch/x86/kvm/assigned-dev.c     | 30 ++++++++++++++++++++++++++++--
 arch/x86/kvm/assigned-dev.h     | 32 ++++++++++++++++++++++++++++++++
 arch/x86/kvm/iommu.c            | 11 +++--------
 arch/x86/kvm/x86.c              |  1 +
 include/linux/kvm_host.h        | 29 -----------------------------
 6 files changed, 64 insertions(+), 62 deletions(-)
 create mode 100644 arch/x86/kvm/assigned-dev.h

(limited to 'include')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d549cf8bfb6..76ff3e2d8fd 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1112,27 +1112,4 @@ int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
 void kvm_handle_pmu_event(struct kvm_vcpu *vcpu);
 void kvm_deliver_pmi(struct kvm_vcpu *vcpu);
 
-#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
-int kvm_iommu_map_guest(struct kvm *kvm);
-int kvm_iommu_unmap_guest(struct kvm *kvm);
-
-long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
-				  unsigned long arg);
-
-void kvm_free_all_assigned_devices(struct kvm *kvm);
-#else
-static inline int kvm_iommu_unmap_guest(struct kvm *kvm)
-{
-	return 0;
-}
-
-static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
-						unsigned long arg)
-{
-	return -ENOTTY;
-}
-
-static inline void kvm_free_all_assigned_devices(struct kvm *kvm) {}
-#endif
-
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/kvm/assigned-dev.c b/arch/x86/kvm/assigned-dev.c
index e05000e200d..6eb5c20ee37 100644
--- a/arch/x86/kvm/assigned-dev.c
+++ b/arch/x86/kvm/assigned-dev.c
@@ -20,6 +20,32 @@
 #include <linux/namei.h>
 #include <linux/fs.h>
 #include "irq.h"
+#include "assigned-dev.h"
+
+struct kvm_assigned_dev_kernel {
+	struct kvm_irq_ack_notifier ack_notifier;
+	struct list_head list;
+	int assigned_dev_id;
+	int host_segnr;
+	int host_busnr;
+	int host_devfn;
+	unsigned int entries_nr;
+	int host_irq;
+	bool host_irq_disabled;
+	bool pci_2_3;
+	struct msix_entry *host_msix_entries;
+	int guest_irq;
+	struct msix_entry *guest_msix_entries;
+	unsigned long irq_requested_type;
+	int irq_source_id;
+	int flags;
+	struct pci_dev *dev;
+	struct kvm *kvm;
+	spinlock_t intx_lock;
+	spinlock_t intx_mask_lock;
+	char irq_name[32];
+	struct pci_saved_state *pci_saved_state;
+};
 
 static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
 						      int assigned_dev_id)
@@ -748,7 +774,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 		if (r)
 			goto out_list_del;
 	}
-	r = kvm_assign_device(kvm, match);
+	r = kvm_assign_device(kvm, match->dev);
 	if (r)
 		goto out_list_del;
 
@@ -790,7 +816,7 @@ static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
 		goto out;
 	}
 
-	kvm_deassign_device(kvm, match);
+	kvm_deassign_device(kvm, match->dev);
 
 	kvm_free_assigned_device(kvm, match);
 
diff --git a/arch/x86/kvm/assigned-dev.h b/arch/x86/kvm/assigned-dev.h
new file mode 100644
index 00000000000..a428c1a211b
--- /dev/null
+++ b/arch/x86/kvm/assigned-dev.h
@@ -0,0 +1,32 @@
+#ifndef ARCH_X86_KVM_ASSIGNED_DEV_H
+#define ARCH_X86_KVM_ASSIGNED_DEV_H
+
+#include <linux/kvm_host.h>
+
+#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
+int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev);
+int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev);
+
+int kvm_iommu_map_guest(struct kvm *kvm);
+int kvm_iommu_unmap_guest(struct kvm *kvm);
+
+long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
+				  unsigned long arg);
+
+void kvm_free_all_assigned_devices(struct kvm *kvm);
+#else
+static inline int kvm_iommu_unmap_guest(struct kvm *kvm)
+{
+	return 0;
+}
+
+static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
+						unsigned long arg)
+{
+	return -ENOTTY;
+}
+
+static inline void kvm_free_all_assigned_devices(struct kvm *kvm) {}
+#endif /* CONFIG_KVM_DEVICE_ASSIGNMENT */
+
+#endif /* ARCH_X86_KVM_ASSIGNED_DEV_H */
diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c
index c1e6ae989a4..17b73eeac8a 100644
--- a/arch/x86/kvm/iommu.c
+++ b/arch/x86/kvm/iommu.c
@@ -31,6 +31,7 @@
 #include <linux/dmar.h>
 #include <linux/iommu.h>
 #include <linux/intel-iommu.h>
+#include "assigned-dev.h"
 
 static bool allow_unsafe_assigned_interrupts;
 module_param_named(allow_unsafe_assigned_interrupts,
@@ -169,10 +170,8 @@ static int kvm_iommu_map_memslots(struct kvm *kvm)
 	return r;
 }
 
-int kvm_assign_device(struct kvm *kvm,
-		      struct kvm_assigned_dev_kernel *assigned_dev)
+int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev)
 {
-	struct pci_dev *pdev = NULL;
 	struct iommu_domain *domain = kvm->arch.iommu_domain;
 	int r;
 	bool noncoherent;
@@ -181,7 +180,6 @@ int kvm_assign_device(struct kvm *kvm,
 	if (!domain)
 		return 0;
 
-	pdev = assigned_dev->dev;
 	if (pdev == NULL)
 		return -ENODEV;
 
@@ -212,17 +210,14 @@ out_unmap:
 	return r;
 }
 
-int kvm_deassign_device(struct kvm *kvm,
-			struct kvm_assigned_dev_kernel *assigned_dev)
+int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev)
 {
 	struct iommu_domain *domain = kvm->arch.iommu_domain;
-	struct pci_dev *pdev = NULL;
 
 	/* check if iommu exists and in use */
 	if (!domain)
 		return 0;
 
-	pdev = assigned_dev->dev;
 	if (pdev == NULL)
 		return -ENODEV;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 782e4eaf456..c42bca47f7f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -27,6 +27,7 @@
 #include "kvm_cache_regs.h"
 #include "x86.h"
 #include "cpuid.h"
+#include "assigned-dev.h"
 
 #include <linux/clocksource.h>
 #include <linux/interrupt.h>
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index aa56894ce83..231dd947222 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -718,31 +718,6 @@ struct kvm_irq_ack_notifier {
 	void (*irq_acked)(struct kvm_irq_ack_notifier *kian);
 };
 
-struct kvm_assigned_dev_kernel {
-	struct kvm_irq_ack_notifier ack_notifier;
-	struct list_head list;
-	int assigned_dev_id;
-	int host_segnr;
-	int host_busnr;
-	int host_devfn;
-	unsigned int entries_nr;
-	int host_irq;
-	bool host_irq_disabled;
-	bool pci_2_3;
-	struct msix_entry *host_msix_entries;
-	int guest_irq;
-	struct msix_entry *guest_msix_entries;
-	unsigned long irq_requested_type;
-	int irq_source_id;
-	int flags;
-	struct pci_dev *dev;
-	struct kvm *kvm;
-	spinlock_t intx_lock;
-	spinlock_t intx_mask_lock;
-	char irq_name[32];
-	struct pci_saved_state *pci_saved_state;
-};
-
 int kvm_irq_map_gsi(struct kvm *kvm,
 		    struct kvm_kernel_irq_routing_entry *entries, int gsi);
 int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin);
@@ -764,10 +739,6 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
-int kvm_assign_device(struct kvm *kvm,
-		      struct kvm_assigned_dev_kernel *assigned_dev);
-int kvm_deassign_device(struct kvm *kvm,
-			struct kvm_assigned_dev_kernel *assigned_dev);
 #else
 static inline int kvm_iommu_map_pages(struct kvm *kvm,
 				      struct kvm_memory_slot *slot)
-- 
cgit v1.2.3-70-g09d2


From 860a0d9e511f278bedab62d555a457c18e0841d5 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Tue, 28 Oct 2014 14:24:12 -0400
Subject: sunrpc: add some tracepoints in svc_rqst handling functions

...just around svc_send, svc_recv and svc_process for now.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 include/trace/events/sunrpc.h | 55 +++++++++++++++++++++++++++++++++++++++++++
 net/sunrpc/svc.c              | 21 ++++++++++-------
 net/sunrpc/svc_xprt.c         | 31 ++++++++++++++++--------
 3 files changed, 88 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 1fef3e6e943..6260f513421 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -6,6 +6,7 @@
 
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/svc.h>
 #include <net/tcp_states.h>
 #include <linux/net.h>
 #include <linux/tracepoint.h>
@@ -306,6 +307,60 @@ DEFINE_RPC_SOCKET_EVENT_DONE(rpc_socket_reset_connection);
 DEFINE_RPC_SOCKET_EVENT(rpc_socket_close);
 DEFINE_RPC_SOCKET_EVENT(rpc_socket_shutdown);
 
+TRACE_EVENT(svc_recv,
+	TP_PROTO(struct svc_rqst *rqst, int status),
+
+	TP_ARGS(rqst, status),
+
+	TP_STRUCT__entry(
+		__field(struct sockaddr *, addr)
+		__field(__be32, xid)
+		__field(int, status)
+	),
+
+	TP_fast_assign(
+		__entry->addr = (struct sockaddr *)&rqst->rq_addr;
+		__entry->xid = status > 0 ? rqst->rq_xid : 0;
+		__entry->status = status;
+	),
+
+	TP_printk("addr=%pIScp xid=0x%x status=%d", __entry->addr,
+			be32_to_cpu(__entry->xid), __entry->status)
+);
+
+DECLARE_EVENT_CLASS(svc_rqst_status,
+
+	TP_PROTO(struct svc_rqst *rqst, int status),
+
+	TP_ARGS(rqst, status),
+
+	TP_STRUCT__entry(
+		__field(struct sockaddr *, addr)
+		__field(__be32, xid)
+		__field(int, dropme)
+		__field(int, status)
+	),
+
+	TP_fast_assign(
+		__entry->addr = (struct sockaddr *)&rqst->rq_addr;
+		__entry->xid = rqst->rq_xid;
+		__entry->dropme = (int)rqst->rq_dropme;
+		__entry->status = status;
+	),
+
+	TP_printk("addr=%pIScp rq_xid=0x%x dropme=%d status=%d",
+		__entry->addr, be32_to_cpu(__entry->xid), __entry->dropme,
+		__entry->status)
+);
+
+DEFINE_EVENT(svc_rqst_status, svc_process,
+	TP_PROTO(struct svc_rqst *rqst, int status),
+	TP_ARGS(rqst, status));
+
+DEFINE_EVENT(svc_rqst_status, svc_send,
+	TP_PROTO(struct svc_rqst *rqst, int status),
+	TP_ARGS(rqst, status));
+
 #endif /* _TRACE_SUNRPC_H */
 
 #include <trace/define_trace.h>
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index ca8a7958f4e..371a8bbb43d 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -28,6 +28,8 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/bc_xprt.h>
 
+#include <trace/events/sunrpc.h>
+
 #define RPCDBG_FACILITY	RPCDBG_SVCDSP
 
 static void svc_unregister(const struct svc_serv *serv, struct net *net);
@@ -1314,24 +1316,25 @@ svc_process(struct svc_rqst *rqstp)
 	rqstp->rq_res.tail[0].iov_base = NULL;
 	rqstp->rq_res.tail[0].iov_len = 0;
 
-	rqstp->rq_xid = svc_getu32(argv);
-
 	dir  = svc_getnl(argv);
 	if (dir != 0) {
 		/* direction != CALL */
 		svc_printk(rqstp, "bad direction %d, dropping request\n", dir);
 		serv->sv_stats->rpcbadfmt++;
-		svc_drop(rqstp);
-		return 0;
+		goto out_drop;
 	}
 
 	/* Returns 1 for send, 0 for drop */
-	if (svc_process_common(rqstp, argv, resv))
-		return svc_send(rqstp);
-	else {
-		svc_drop(rqstp);
-		return 0;
+	if (likely(svc_process_common(rqstp, argv, resv))) {
+		int ret = svc_send(rqstp);
+
+		trace_svc_process(rqstp, ret);
+		return ret;
 	}
+out_drop:
+	trace_svc_process(rqstp, 0);
+	svc_drop(rqstp);
+	return 0;
 }
 
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index c179ca2a5aa..bbb3b044b87 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -15,6 +15,7 @@
 #include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/xprt.h>
 #include <linux/module.h>
+#include <trace/events/sunrpc.h>
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
@@ -773,35 +774,43 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 
 	err = svc_alloc_arg(rqstp);
 	if (err)
-		return err;
+		goto out;
 
 	try_to_freeze();
 	cond_resched();
+	err = -EINTR;
 	if (signalled() || kthread_should_stop())
-		return -EINTR;
+		goto out;
 
 	xprt = svc_get_next_xprt(rqstp, timeout);
-	if (IS_ERR(xprt))
-		return PTR_ERR(xprt);
+	if (IS_ERR(xprt)) {
+		err = PTR_ERR(xprt);
+		goto out;
+	}
 
 	len = svc_handle_xprt(rqstp, xprt);
 
 	/* No data, incomplete (TCP) read, or accept() */
+	err = -EAGAIN;
 	if (len <= 0)
-		goto out;
+		goto out_release;
 
 	clear_bit(XPT_OLD, &xprt->xpt_flags);
 
 	rqstp->rq_secure = xprt->xpt_ops->xpo_secure_port(rqstp);
 	rqstp->rq_chandle.defer = svc_defer;
+	rqstp->rq_xid = svc_getu32(&rqstp->rq_arg.head[0]);
 
 	if (serv->sv_stats)
 		serv->sv_stats->netcnt++;
+	trace_svc_recv(rqstp, len);
 	return len;
-out:
+out_release:
 	rqstp->rq_res.len = 0;
 	svc_xprt_release(rqstp);
-	return -EAGAIN;
+out:
+	trace_svc_recv(rqstp, err);
+	return err;
 }
 EXPORT_SYMBOL_GPL(svc_recv);
 
@@ -821,12 +830,12 @@ EXPORT_SYMBOL_GPL(svc_drop);
 int svc_send(struct svc_rqst *rqstp)
 {
 	struct svc_xprt	*xprt;
-	int		len;
+	int		len = -EFAULT;
 	struct xdr_buf	*xb;
 
 	xprt = rqstp->rq_xprt;
 	if (!xprt)
-		return -EFAULT;
+		goto out;
 
 	/* release the receive skb before sending the reply */
 	rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp);
@@ -849,7 +858,9 @@ int svc_send(struct svc_rqst *rqstp)
 	svc_xprt_release(rqstp);
 
 	if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN)
-		return 0;
+		len = 0;
+out:
+	trace_svc_send(rqstp, len);
 	return len;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 3705ad64f123271b2b88dbff0c9891b7b90299d2 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Tue, 28 Oct 2014 14:24:13 -0400
Subject: sunrpc: add new tracepoints in xprt handling code

...so we can keep track of when calls are sent and replies received.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 include/trace/events/sunrpc.h | 63 +++++++++++++++++++++++++++++++++++++++++++
 net/sunrpc/xprt.c             |  9 ++++++-
 net/sunrpc/xprtsock.c         |  8 +++++-
 3 files changed, 78 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 6260f513421..5edb16bcd83 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -307,6 +307,69 @@ DEFINE_RPC_SOCKET_EVENT_DONE(rpc_socket_reset_connection);
 DEFINE_RPC_SOCKET_EVENT(rpc_socket_close);
 DEFINE_RPC_SOCKET_EVENT(rpc_socket_shutdown);
 
+DECLARE_EVENT_CLASS(rpc_xprt_event,
+	TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status),
+
+	TP_ARGS(xprt, xid, status),
+
+	TP_STRUCT__entry(
+		__field(__be32, xid)
+		__field(int, status)
+		__string(addr, xprt->address_strings[RPC_DISPLAY_ADDR])
+		__string(port, xprt->address_strings[RPC_DISPLAY_PORT])
+	),
+
+	TP_fast_assign(
+		__entry->xid = xid;
+		__entry->status = status;
+		__assign_str(addr, xprt->address_strings[RPC_DISPLAY_ADDR]);
+		__assign_str(port, xprt->address_strings[RPC_DISPLAY_PORT]);
+	),
+
+	TP_printk("peer=%s/%s xid=0x%x status=%d", __get_str(addr),
+			__get_str(port), be32_to_cpu(__entry->xid),
+			__entry->status)
+);
+
+DEFINE_EVENT(rpc_xprt_event, xprt_lookup_rqst,
+	TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status),
+	TP_ARGS(xprt, xid, status));
+
+DEFINE_EVENT(rpc_xprt_event, xprt_transmit,
+	TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status),
+	TP_ARGS(xprt, xid, status));
+
+DEFINE_EVENT(rpc_xprt_event, xprt_complete_rqst,
+	TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status),
+	TP_ARGS(xprt, xid, status));
+
+TRACE_EVENT(xs_tcp_data_ready,
+	TP_PROTO(struct rpc_xprt *xprt, int err, unsigned int total),
+
+	TP_ARGS(xprt, err, total),
+
+	TP_STRUCT__entry(
+		__field(int, err)
+		__field(unsigned int, total)
+		__string(addr, xprt ? xprt->address_strings[RPC_DISPLAY_ADDR] :
+				"(null)")
+		__string(port, xprt ? xprt->address_strings[RPC_DISPLAY_PORT] :
+				"(null)")
+	),
+
+	TP_fast_assign(
+		__entry->err = err;
+		__entry->total = total;
+		__assign_str(addr, xprt ?
+			xprt->address_strings[RPC_DISPLAY_ADDR] : "(null)");
+		__assign_str(port, xprt ?
+			xprt->address_strings[RPC_DISPLAY_PORT] : "(null)");
+	),
+
+	TP_printk("peer=[%s]:%s err=%d total=%u", __get_str(addr),
+			__get_str(port), __entry->err, __entry->total)
+);
+
 TRACE_EVENT(svc_recv,
 	TP_PROTO(struct svc_rqst *rqst, int status),
 
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 56e4e150e80..1b2e5e616ca 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -49,6 +49,8 @@
 #include <linux/sunrpc/metrics.h>
 #include <linux/sunrpc/bc_xprt.h>
 
+#include <trace/events/sunrpc.h>
+
 #include "sunrpc.h"
 
 /*
@@ -772,11 +774,14 @@ struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid)
 	struct rpc_rqst *entry;
 
 	list_for_each_entry(entry, &xprt->recv, rq_list)
-		if (entry->rq_xid == xid)
+		if (entry->rq_xid == xid) {
+			trace_xprt_lookup_rqst(xprt, xid, 0);
 			return entry;
+		}
 
 	dprintk("RPC:       xprt_lookup_rqst did not find xid %08x\n",
 			ntohl(xid));
+	trace_xprt_lookup_rqst(xprt, xid, -ENOENT);
 	xprt->stat.bad_xids++;
 	return NULL;
 }
@@ -810,6 +815,7 @@ void xprt_complete_rqst(struct rpc_task *task, int copied)
 
 	dprintk("RPC: %5u xid %08x complete (%d bytes received)\n",
 			task->tk_pid, ntohl(req->rq_xid), copied);
+	trace_xprt_complete_rqst(xprt, req->rq_xid, copied);
 
 	xprt->stat.recvs++;
 	req->rq_rtt = ktime_sub(ktime_get(), req->rq_xtime);
@@ -926,6 +932,7 @@ void xprt_transmit(struct rpc_task *task)
 
 	req->rq_xtime = ktime_get();
 	status = xprt->ops->send_request(task);
+	trace_xprt_transmit(xprt, req->rq_xid, status);
 	if (status != 0) {
 		task->tk_status = status;
 		return;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 3b305ab17af..b63e26272dc 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1454,12 +1454,15 @@ static void xs_tcp_data_ready(struct sock *sk)
 	struct rpc_xprt *xprt;
 	read_descriptor_t rd_desc;
 	int read;
+	unsigned long total = 0;
 
 	dprintk("RPC:       xs_tcp_data_ready...\n");
 
 	read_lock_bh(&sk->sk_callback_lock);
-	if (!(xprt = xprt_from_sock(sk)))
+	if (!(xprt = xprt_from_sock(sk))) {
+		read = 0;
 		goto out;
+	}
 	/* Any data means we had a useful conversation, so
 	 * the we don't need to delay the next reconnect
 	 */
@@ -1471,8 +1474,11 @@ static void xs_tcp_data_ready(struct sock *sk)
 	do {
 		rd_desc.count = 65536;
 		read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
+		if (read > 0)
+			total += read;
 	} while (read > 0);
 out:
+	trace_xs_tcp_data_ready(xprt, read, total);
 	read_unlock_bh(&sk->sk_callback_lock);
 }
 
-- 
cgit v1.2.3-70-g09d2


From 1a867a0898b2e366a1eb5b7fe21413a2b2b1629f Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Tue, 28 Oct 2014 14:24:14 -0400
Subject: sunrpc: add tracepoints in xs_tcp_data_recv

Add tracepoints inside the main loop on xs_tcp_data_recv that allow
us to keep an eye on what's happening during each phase of it.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 include/linux/sunrpc/xprtsock.h | 59 +++++++++++++++++++++++++++++++++++++++
 include/trace/events/sunrpc.h   | 44 ++++++++++++++++++++++++++++-
 net/sunrpc/xprtsock.c           | 61 ++---------------------------------------
 3 files changed, 104 insertions(+), 60 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h
index 1ad36cc25b2..7591788e9fb 100644
--- a/include/linux/sunrpc/xprtsock.h
+++ b/include/linux/sunrpc/xprtsock.h
@@ -17,6 +17,65 @@ void		cleanup_socket_xprt(void);
 #define RPC_DEF_MIN_RESVPORT	(665U)
 #define RPC_DEF_MAX_RESVPORT	(1023U)
 
+struct sock_xprt {
+	struct rpc_xprt		xprt;
+
+	/*
+	 * Network layer
+	 */
+	struct socket *		sock;
+	struct sock *		inet;
+
+	/*
+	 * State of TCP reply receive
+	 */
+	__be32			tcp_fraghdr,
+				tcp_xid,
+				tcp_calldir;
+
+	u32			tcp_offset,
+				tcp_reclen;
+
+	unsigned long		tcp_copied,
+				tcp_flags;
+
+	/*
+	 * Connection of transports
+	 */
+	struct delayed_work	connect_worker;
+	struct sockaddr_storage	srcaddr;
+	unsigned short		srcport;
+
+	/*
+	 * UDP socket buffer size parameters
+	 */
+	size_t			rcvsize,
+				sndsize;
+
+	/*
+	 * Saved socket callback addresses
+	 */
+	void			(*old_data_ready)(struct sock *);
+	void			(*old_state_change)(struct sock *);
+	void			(*old_write_space)(struct sock *);
+	void			(*old_error_report)(struct sock *);
+};
+
+/*
+ * TCP receive state flags
+ */
+#define TCP_RCV_LAST_FRAG	(1UL << 0)
+#define TCP_RCV_COPY_FRAGHDR	(1UL << 1)
+#define TCP_RCV_COPY_XID	(1UL << 2)
+#define TCP_RCV_COPY_DATA	(1UL << 3)
+#define TCP_RCV_READ_CALLDIR	(1UL << 4)
+#define TCP_RCV_COPY_CALLDIR	(1UL << 5)
+
+/*
+ * TCP RPC flags
+ */
+#define TCP_RPC_REPLY		(1UL << 6)
+
 #endif /* __KERNEL__ */
 
 #endif /* _LINUX_SUNRPC_XPRTSOCK_H */
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 5edb16bcd83..171ca4ff6d9 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -7,6 +7,7 @@
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/svc.h>
+#include <linux/sunrpc/xprtsock.h>
 #include <net/tcp_states.h>
 #include <linux/net.h>
 #include <linux/tracepoint.h>
@@ -326,7 +327,7 @@ DECLARE_EVENT_CLASS(rpc_xprt_event,
 		__assign_str(port, xprt->address_strings[RPC_DISPLAY_PORT]);
 	),
 
-	TP_printk("peer=%s/%s xid=0x%x status=%d", __get_str(addr),
+	TP_printk("peer=[%s]:%s xid=0x%x status=%d", __get_str(addr),
 			__get_str(port), be32_to_cpu(__entry->xid),
 			__entry->status)
 );
@@ -370,6 +371,47 @@ TRACE_EVENT(xs_tcp_data_ready,
 			__get_str(port), __entry->err, __entry->total)
 );
 
+#define rpc_show_sock_xprt_flags(flags) \
+	__print_flags(flags, "|", \
+		{ TCP_RCV_LAST_FRAG, "TCP_RCV_LAST_FRAG" }, \
+		{ TCP_RCV_COPY_FRAGHDR, "TCP_RCV_COPY_FRAGHDR" }, \
+		{ TCP_RCV_COPY_XID, "TCP_RCV_COPY_XID" }, \
+		{ TCP_RCV_COPY_DATA, "TCP_RCV_COPY_DATA" }, \
+		{ TCP_RCV_READ_CALLDIR, "TCP_RCV_READ_CALLDIR" }, \
+		{ TCP_RCV_COPY_CALLDIR, "TCP_RCV_COPY_CALLDIR" }, \
+		{ TCP_RPC_REPLY, "TCP_RPC_REPLY" })
+
+TRACE_EVENT(xs_tcp_data_recv,
+	TP_PROTO(struct sock_xprt *xs),
+
+	TP_ARGS(xs),
+
+	TP_STRUCT__entry(
+		__string(addr, xs->xprt.address_strings[RPC_DISPLAY_ADDR])
+		__string(port, xs->xprt.address_strings[RPC_DISPLAY_PORT])
+		__field(__be32, xid)
+		__field(unsigned long, flags)
+		__field(unsigned long, copied)
+		__field(unsigned int, reclen)
+		__field(unsigned long, offset)
+	),
+
+	TP_fast_assign(
+		__assign_str(addr, xs->xprt.address_strings[RPC_DISPLAY_ADDR]);
+		__assign_str(port, xs->xprt.address_strings[RPC_DISPLAY_PORT]);
+		__entry->xid = xs->tcp_xid;
+		__entry->flags = xs->tcp_flags;
+		__entry->copied = xs->tcp_copied;
+		__entry->reclen = xs->tcp_reclen;
+		__entry->offset = xs->tcp_offset;
+	),
+
+	TP_printk("peer=[%s]:%s xid=0x%x flags=%s copied=%lu reclen=%u offset=%lu",
+			__get_str(addr), __get_str(port), be32_to_cpu(__entry->xid),
+			rpc_show_sock_xprt_flags(__entry->flags),
+			__entry->copied, __entry->reclen, __entry->offset)
+);
+
 TRACE_EVENT(svc_recv,
 	TP_PROTO(struct svc_rqst *rqst, int status),
 
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index b63e26272dc..31c015196a2 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -216,65 +216,6 @@ static inline void xs_pktdump(char *msg, u32 *packet, unsigned int count)
 }
 #endif
 
-struct sock_xprt {
-	struct rpc_xprt		xprt;
-
-	/*
-	 * Network layer
-	 */
-	struct socket *		sock;
-	struct sock *		inet;
-
-	/*
-	 * State of TCP reply receive
-	 */
-	__be32			tcp_fraghdr,
-				tcp_xid,
-				tcp_calldir;
-
-	u32			tcp_offset,
-				tcp_reclen;
-
-	unsigned long		tcp_copied,
-				tcp_flags;
-
-	/*
-	 * Connection of transports
-	 */
-	struct delayed_work	connect_worker;
-	struct sockaddr_storage	srcaddr;
-	unsigned short		srcport;
-
-	/*
-	 * UDP socket buffer size parameters
-	 */
-	size_t			rcvsize,
-				sndsize;
-
-	/*
-	 * Saved socket callback addresses
-	 */
-	void			(*old_data_ready)(struct sock *);
-	void			(*old_state_change)(struct sock *);
-	void			(*old_write_space)(struct sock *);
-	void			(*old_error_report)(struct sock *);
-};
-
-/*
- * TCP receive state flags
- */
-#define TCP_RCV_LAST_FRAG	(1UL << 0)
-#define TCP_RCV_COPY_FRAGHDR	(1UL << 1)
-#define TCP_RCV_COPY_XID	(1UL << 2)
-#define TCP_RCV_COPY_DATA	(1UL << 3)
-#define TCP_RCV_READ_CALLDIR	(1UL << 4)
-#define TCP_RCV_COPY_CALLDIR	(1UL << 5)
-
-/*
- * TCP RPC flags
- */
-#define TCP_RPC_REPLY		(1UL << 6)
-
 static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
 {
 	return (struct rpc_xprt *) sk->sk_user_data;
@@ -1415,6 +1356,7 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns
 
 	dprintk("RPC:       xs_tcp_data_recv started\n");
 	do {
+		trace_xs_tcp_data_recv(transport);
 		/* Read in a new fragment marker if necessary */
 		/* Can we ever really expect to get completely empty fragments? */
 		if (transport->tcp_flags & TCP_RCV_COPY_FRAGHDR) {
@@ -1439,6 +1381,7 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns
 		/* Skip over any trailing bytes on short reads */
 		xs_tcp_read_discard(transport, &desc);
 	} while (desc.count);
+	trace_xs_tcp_data_recv(transport);
 	dprintk("RPC:       xs_tcp_data_recv done\n");
 	return len - desc.count;
 }
-- 
cgit v1.2.3-70-g09d2


From a6e4599f8d232b5911c46bb16f5a79b86f3dfb75 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sun, 23 Nov 2014 15:04:12 +0100
Subject: ASoC: uda134x: Remove is_powered_on_standby from platform data

According to its documentation the is_powered_on_standby field of the
uda134x platform data is supposed to prevent the the driver from shutting
down the ADC and DAC in standby mode. This behavior was broken in commit
commit f0fba2ad1b6b ("ASoC: multi-component - ASoC Multi-Component Support")
almost 5 years ago and all the flag does now is cause the driver to go to
SND_SOC_BIAS_ON in probe, just for the ASoC core to put it back into
SND_SOC_BIAS_STANDBY right after probe.

Apparently the intended behavior has not been missed, so just remove
is_powered_on_standby from the platform data struct.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/uda134x.h    | 12 ------------
 sound/soc/codecs/uda134x.c |  5 +----
 2 files changed, 1 insertion(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/sound/uda134x.h b/include/sound/uda134x.h
index e475659bd3b..509efb05017 100644
--- a/include/sound/uda134x.h
+++ b/include/sound/uda134x.h
@@ -18,18 +18,6 @@ struct uda134x_platform_data {
 	struct l3_pins l3;
 	void (*power) (int);
 	int model;
-	/*
-	  ALSA SOC usually puts the device in standby mode when it's not used
-	  for sometime. If you unset is_powered_on_standby the driver will
-	  turn off the ADC/DAC when this callback is invoked and turn it back
-	  on when needed. Unfortunately this will result in a very light bump
-	  (it can be audible only with good earphones). If this bothers you
-	  set is_powered_on_standby, you will have slightly higher power
-	  consumption. Please note that sending the L3 command for ADC is
-	  enough to make the bump, so it doesn't make difference if you
-	  completely take off power from the codec.
-	*/
-	int is_powered_on_standby;
 #define UDA134X_UDA1340 1
 #define UDA134X_UDA1341 2
 #define UDA134X_UDA1344 3
diff --git a/sound/soc/codecs/uda134x.c b/sound/soc/codecs/uda134x.c
index 32b2f78aa62..54240f14211 100644
--- a/sound/soc/codecs/uda134x.c
+++ b/sound/soc/codecs/uda134x.c
@@ -518,10 +518,7 @@ static int uda134x_soc_probe(struct snd_soc_codec *codec)
 
 	uda134x_reset(codec);
 
-	if (pd->is_powered_on_standby)
-		uda134x_set_bias_level(codec, SND_SOC_BIAS_ON);
-	else
-		uda134x_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
+	uda134x_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
 
 	if (pd->model == UDA134X_UDA1341) {
 		widgets = uda1341_dapm_widgets;
-- 
cgit v1.2.3-70-g09d2


From b671358ad7916beb7ca9e5c304ae88afc7da4557 Mon Sep 17 00:00:00 2001
From: Beniamino Galvani <b.galvani@gmail.com>
Date: Sat, 22 Nov 2014 16:21:39 +0100
Subject: spi: core: Add spi_transfer_is_last() helper

This adds the function spi_transfer_is_last() which can be used by
drivers to know whether a given transfer is the last one in the
current message.

Signed-off-by: Beniamino Galvani <b.galvani@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/spi.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 46d188a9947..a6ef2a8e6de 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -1049,4 +1049,10 @@ spi_unregister_device(struct spi_device *spi)
 extern const struct spi_device_id *
 spi_get_device_id(const struct spi_device *sdev);
 
+static inline bool
+spi_transfer_is_last(struct spi_master *master, struct spi_transfer *xfer)
+{
+	return list_is_last(&xfer->transfer_list, &master->cur_msg->transfers);
+}
+
 #endif /* __LINUX_SPI_H */
-- 
cgit v1.2.3-70-g09d2


From 3c356bde19e9a728b26a231a23099c8057dbe881 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 5 Sep 2014 18:20:23 -0700
Subject: scsi: stop passing a gfp_mask argument down the command setup path

There is no reason for ULDs to pass in a flag on how to allocate the S/G
lists.  While we don't need GFP_ATOMIC for the blk-mq case because we
don't hold locks, that decision can be made way down the chain without
having to pass a pointless gfp_mask argument.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/scsi/scsi_lib.c  | 20 +++++++++-----------
 drivers/scsi/sd.c        |  6 +++---
 drivers/scsi/sr.c        |  2 +-
 include/scsi/scsi_cmnd.h |  2 +-
 4 files changed, 14 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 2179851cdaf..fcdc585278b 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -588,10 +588,10 @@ static void scsi_free_sgtable(struct scsi_data_buffer *sdb, bool mq)
 	__sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, mq, scsi_sg_free);
 }
 
-static int scsi_alloc_sgtable(struct scsi_data_buffer *sdb, int nents,
-			      gfp_t gfp_mask, bool mq)
+static int scsi_alloc_sgtable(struct scsi_data_buffer *sdb, int nents, bool mq)
 {
 	struct scatterlist *first_chunk = NULL;
+	gfp_t gfp_mask = mq ? GFP_NOIO : GFP_ATOMIC;
 	int ret;
 
 	BUG_ON(!nents);
@@ -1077,8 +1077,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	}
 }
 
-static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb,
-			     gfp_t gfp_mask)
+static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb)
 {
 	int count;
 
@@ -1086,7 +1085,7 @@ static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb,
 	 * If sg table allocation fails, requeue request later.
 	 */
 	if (unlikely(scsi_alloc_sgtable(sdb, req->nr_phys_segments,
-					gfp_mask, req->mq_ctx != NULL)))
+					req->mq_ctx != NULL)))
 		return BLKPREP_DEFER;
 
 	/* 
@@ -1111,7 +1110,7 @@ static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb,
  *		BLKPREP_DEFER if the failure is retryable
  *		BLKPREP_KILL if the failure is fatal
  */
-int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask)
+int scsi_init_io(struct scsi_cmnd *cmd)
 {
 	struct scsi_device *sdev = cmd->device;
 	struct request *rq = cmd->request;
@@ -1120,7 +1119,7 @@ int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask)
 
 	BUG_ON(!rq->nr_phys_segments);
 
-	error = scsi_init_sgtable(rq, &cmd->sdb, gfp_mask);
+	error = scsi_init_sgtable(rq, &cmd->sdb);
 	if (error)
 		goto err_exit;
 
@@ -1136,8 +1135,7 @@ int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask)
 			rq->next_rq->special = bidi_sdb;
 		}
 
-		error = scsi_init_sgtable(rq->next_rq, rq->next_rq->special,
-					  GFP_ATOMIC);
+		error = scsi_init_sgtable(rq->next_rq, rq->next_rq->special);
 		if (error)
 			goto err_exit;
 	}
@@ -1149,7 +1147,7 @@ int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask)
 		BUG_ON(prot_sdb == NULL);
 		ivecs = blk_rq_count_integrity_sg(rq->q, rq->bio);
 
-		if (scsi_alloc_sgtable(prot_sdb, ivecs, gfp_mask, is_mq)) {
+		if (scsi_alloc_sgtable(prot_sdb, ivecs, is_mq)) {
 			error = BLKPREP_DEFER;
 			goto err_exit;
 		}
@@ -1218,7 +1216,7 @@ static int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req)
 	 * submit a request without an attached bio.
 	 */
 	if (req->bio) {
-		int ret = scsi_init_io(cmd, GFP_ATOMIC);
+		int ret = scsi_init_io(cmd);
 		if (unlikely(ret))
 			return ret;
 	} else {
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 95bfb7bfbb9..f2e9b1dad57 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -786,7 +786,7 @@ static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd)
 	 * amount of blocks described by the request.
 	 */
 	blk_add_request_payload(rq, page, len);
-	ret = scsi_init_io(cmd, GFP_ATOMIC);
+	ret = scsi_init_io(cmd);
 	rq->__data_len = nr_bytes;
 
 out:
@@ -880,7 +880,7 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 	 * knows how much to actually write.
 	 */
 	rq->__data_len = sdp->sector_size;
-	ret = scsi_init_io(cmd, GFP_ATOMIC);
+	ret = scsi_init_io(cmd);
 	rq->__data_len = nr_bytes;
 	return ret;
 }
@@ -914,7 +914,7 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 	int ret;
 	unsigned char protect;
 
-	ret = scsi_init_io(SCpnt, GFP_ATOMIC);
+	ret = scsi_init_io(SCpnt);
 	if (ret != BLKPREP_OK)
 		goto out;
 	SCpnt = rq->special;
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 3d5399e341a..5ebadc2ace9 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -387,7 +387,7 @@ static int sr_init_command(struct scsi_cmnd *SCpnt)
 	struct request *rq = SCpnt->request;
 	int ret;
 
-	ret = scsi_init_io(SCpnt, GFP_ATOMIC);
+	ret = scsi_init_io(SCpnt);
 	if (ret != BLKPREP_OK)
 		goto out;
 	SCpnt = rq->special;
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index e119142e565..9fc1aecfc81 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -163,7 +163,7 @@ extern void *scsi_kmap_atomic_sg(struct scatterlist *sg, int sg_count,
 				 size_t *offset, size_t *len);
 extern void scsi_kunmap_atomic_sg(void *virt);
 
-extern int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask);
+extern int scsi_init_io(struct scsi_cmnd *cmd);
 
 extern int scsi_dma_map(struct scsi_cmnd *cmd);
 extern void scsi_dma_unmap(struct scsi_cmnd *cmd);
-- 
cgit v1.2.3-70-g09d2


From 3af6b35261182ff185db1f0fd271254147e2663e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 12 Nov 2014 18:34:51 +0100
Subject: scsi: remove scsi_driver owner field

The driver core driver structure has grown an owner field and now
requires it to be set for all modular drivers.  Set it up for
all scsi_driver instances and get rid of the now superflous
scsi_driver owner field.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reported-by: Shane M Seymour <shane.seymour@hp.com>
Reviewed-by: Ewan D. Milne <emilne@redhat.com
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/scsi/ch.c          | 2 +-
 drivers/scsi/osd/osd_uld.c | 2 +-
 drivers/scsi/osst.c        | 2 +-
 drivers/scsi/scsi_scan.c   | 9 ++++-----
 drivers/scsi/sd.c          | 2 +-
 drivers/scsi/ses.c         | 2 +-
 drivers/scsi/sr.c          | 2 +-
 drivers/scsi/st.c          | 2 +-
 include/scsi/scsi_driver.h | 1 -
 9 files changed, 11 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index 4f502f95f3b..6bac8a746ee 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -972,9 +972,9 @@ static int ch_remove(struct device *dev)
 }
 
 static struct scsi_driver ch_template = {
-	.owner     	= THIS_MODULE,
 	.gendrv     	= {
 		.name	= "ch",
+		.owner	= THIS_MODULE,
 		.probe  = ch_probe,
 		.remove = ch_remove,
 	},
diff --git a/drivers/scsi/osd/osd_uld.c b/drivers/scsi/osd/osd_uld.c
index 92cdd4b0652..243eab3d10d 100644
--- a/drivers/scsi/osd/osd_uld.c
+++ b/drivers/scsi/osd/osd_uld.c
@@ -540,9 +540,9 @@ static int osd_remove(struct device *dev)
  */
 
 static struct scsi_driver osd_driver = {
-	.owner			= THIS_MODULE,
 	.gendrv = {
 		.name		= osd_name,
+		.owner		= THIS_MODULE,
 		.probe		= osd_probe,
 		.remove		= osd_remove,
 	}
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index 8c384648eef..5033223f628 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -172,9 +172,9 @@ static int osst_probe(struct device *);
 static int osst_remove(struct device *);
 
 static struct scsi_driver osst_template = {
-	.owner			= THIS_MODULE,
 	.gendrv = {
 		.name		=  "osst",
+		.owner		= THIS_MODULE,
 		.probe		= osst_probe,
 		.remove		= osst_remove,
 	}
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index d97597e6337..0cda53adfd3 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -1593,16 +1593,15 @@ EXPORT_SYMBOL(scsi_add_device);
 
 void scsi_rescan_device(struct device *dev)
 {
-	struct scsi_driver *drv;
-	
 	if (!dev->driver)
 		return;
 
-	drv = to_scsi_driver(dev->driver);
-	if (try_module_get(drv->owner)) {
+	if (try_module_get(dev->driver->owner)) {
+		struct scsi_driver *drv = to_scsi_driver(dev->driver);
+
 		if (drv->rescan)
 			drv->rescan(dev);
-		module_put(drv->owner);
+		module_put(dev->driver->owner);
 	}
 }
 EXPORT_SYMBOL(scsi_rescan_device);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index f2e9b1dad57..54abcb220ab 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -510,9 +510,9 @@ static const struct dev_pm_ops sd_pm_ops = {
 };
 
 static struct scsi_driver sd_template = {
-	.owner			= THIS_MODULE,
 	.gendrv = {
 		.name		= "sd",
+		.owner		= THIS_MODULE,
 		.probe		= sd_probe,
 		.remove		= sd_remove,
 		.shutdown	= sd_shutdown,
diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
index 80bfece1a2d..b7e79e7646a 100644
--- a/drivers/scsi/ses.c
+++ b/drivers/scsi/ses.c
@@ -693,9 +693,9 @@ static struct class_interface ses_interface = {
 };
 
 static struct scsi_driver ses_template = {
-	.owner			= THIS_MODULE,
 	.gendrv = {
 		.name		= "ses",
+		.owner		= THIS_MODULE,
 		.probe		= ses_probe,
 		.remove		= ses_remove,
 	},
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 5ebadc2ace9..8bd54a64efd 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -88,9 +88,9 @@ static struct dev_pm_ops sr_pm_ops = {
 };
 
 static struct scsi_driver sr_template = {
-	.owner			= THIS_MODULE,
 	.gendrv = {
 		.name   	= "sr",
+		.owner		= THIS_MODULE,
 		.probe		= sr_probe,
 		.remove		= sr_remove,
 		.pm		= &sr_pm_ops,
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index e46e02b24ba..128d3b55bdd 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -202,9 +202,9 @@ static int do_create_sysfs_files(void);
 static void do_remove_sysfs_files(void);
 
 static struct scsi_driver st_template = {
-	.owner			= THIS_MODULE,
 	.gendrv = {
 		.name		= "st",
+		.owner		= THIS_MODULE,
 		.probe		= st_probe,
 		.remove		= st_remove,
 	},
diff --git a/include/scsi/scsi_driver.h b/include/scsi/scsi_driver.h
index c2b759809d8..891a658aa86 100644
--- a/include/scsi/scsi_driver.h
+++ b/include/scsi/scsi_driver.h
@@ -9,7 +9,6 @@ struct scsi_cmnd;
 struct scsi_device;
 
 struct scsi_driver {
-	struct module		*owner;
 	struct device_driver	gendrv;
 
 	void (*rescan)(struct device *);
-- 
cgit v1.2.3-70-g09d2


From eb846d9f147455e4e5e1863bfb5e31974bb69b7c Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Mon, 17 Nov 2014 14:25:19 +0100
Subject: scsi: rename SERVICE_ACTION_IN to SERVICE_ACTION_IN_16

SPC-3 defines SERVICE ACTION IN(12) and SERVICE ACTION IN(16).
So rename SERVICE_ACTION_IN to SERVICE_ACTION_IN_16 to be
consistent with SPC and to allow for better distinction.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Tested-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 block/scsi_ioctl.c                         | 2 +-
 drivers/ata/libata-scsi.c                  | 2 +-
 drivers/block/nvme-scsi.c                  | 4 ++--
 drivers/scsi/aacraid/aachba.c              | 4 ++--
 drivers/scsi/aacraid/linit.c               | 2 +-
 drivers/scsi/constants.c                   | 1 -
 drivers/scsi/gdth.c                        | 4 ++--
 drivers/scsi/scsi_debug.c                  | 2 +-
 drivers/scsi/scsi_trace.c                  | 2 +-
 drivers/scsi/sd.c                          | 2 +-
 drivers/target/target_core_alua.c          | 2 +-
 drivers/target/target_core_sbc.c           | 2 +-
 drivers/usb/gadget/legacy/tcm_usb_gadget.c | 2 +-
 include/scsi/scsi.h                        | 2 +-
 include/trace/events/scsi.h                | 2 +-
 include/trace/events/target.h              | 2 +-
 tools/lib/traceevent/plugin_scsi.c         | 4 ++--
 17 files changed, 20 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 1e053d91124..c7bbc190f16 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -142,7 +142,7 @@ static void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter)
 	__set_bit(GPCMD_VERIFY_10, filter->read_ok);
 	__set_bit(VERIFY_16, filter->read_ok);
 	__set_bit(REPORT_LUNS, filter->read_ok);
-	__set_bit(SERVICE_ACTION_IN, filter->read_ok);
+	__set_bit(SERVICE_ACTION_IN_16, filter->read_ok);
 	__set_bit(RECEIVE_DIAGNOSTIC, filter->read_ok);
 	__set_bit(MAINTENANCE_IN, filter->read_ok);
 	__set_bit(GPCMD_READ_BUFFER_CAPACITY, filter->read_ok);
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index c8bb6abbf12..fc6a60abe51 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3570,7 +3570,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd)
 		ata_scsi_rbuf_fill(&args, ata_scsiop_read_cap);
 		break;
 
-	case SERVICE_ACTION_IN:
+	case SERVICE_ACTION_IN_16:
 		if ((scsicmd[1] & 0x1f) == SAI_READ_CAPACITY_16)
 			ata_scsi_rbuf_fill(&args, ata_scsiop_read_cap);
 		else
diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c
index a4cd6d691c6..0b4b2775600 100644
--- a/drivers/block/nvme-scsi.c
+++ b/drivers/block/nvme-scsi.c
@@ -329,7 +329,7 @@ INQUIRY_EVPD_BIT_MASK) ? 1 : 0)
 (GET_U32_FROM_CDB(cdb, READ_CAP_16_CDB_ALLOC_LENGTH_OFFSET))
 
 #define IS_READ_CAP_16(cdb)					\
-((cdb[0] == SERVICE_ACTION_IN && cdb[1] == SAI_READ_CAPACITY_16) ? 1 : 0)
+((cdb[0] == SERVICE_ACTION_IN_16 && cdb[1] == SAI_READ_CAPACITY_16) ? 1 : 0)
 
 /* Request Sense Helper Macros */
 #define GET_REQUEST_SENSE_ALLOC_LENGTH(cdb)			\
@@ -2947,7 +2947,7 @@ static int nvme_scsi_translate(struct nvme_ns *ns, struct sg_io_hdr *hdr)
 	case READ_CAPACITY:
 		retcode = nvme_trans_read_capacity(ns, hdr, cmd);
 		break;
-	case SERVICE_ACTION_IN:
+	case SERVICE_ACTION_IN_16:
 		if (IS_READ_CAP_16(cmd))
 			retcode = nvme_trans_read_capacity(ns, hdr, cmd);
 		else
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index 681434e2dfe..b32e77db0c4 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -2181,7 +2181,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 			  (fsa_dev_ptr[cid].sense_data.sense_key ==
 			   NOT_READY)) {
 				switch (scsicmd->cmnd[0]) {
-				case SERVICE_ACTION_IN:
+				case SERVICE_ACTION_IN_16:
 					if (!(dev->raw_io_interface) ||
 					    !(dev->raw_io_64) ||
 					    ((scsicmd->cmnd[1] & 0x1f) != SAI_READ_CAPACITY_16))
@@ -2309,7 +2309,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		scsi_sg_copy_from_buffer(scsicmd, &inq_data, sizeof(inq_data));
 		return aac_get_container_name(scsicmd);
 	}
-	case SERVICE_ACTION_IN:
+	case SERVICE_ACTION_IN_16:
 		if (!(dev->raw_io_interface) ||
 		    !(dev->raw_io_64) ||
 		    ((scsicmd->cmnd[1] & 0x1f) != SAI_READ_CAPACITY_16))
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 41b9c68bca6..4c340d88c33 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -555,7 +555,7 @@ static int aac_eh_abort(struct scsi_cmnd* cmd)
 		AAC_DRIVERNAME,
 		host->host_no, sdev_channel(dev), sdev_id(dev), dev->lun);
 	switch (cmd->cmnd[0]) {
-	case SERVICE_ACTION_IN:
+	case SERVICE_ACTION_IN_16:
 		if (!(aac->raw_io_interface) ||
 		    !(aac->raw_io_64) ||
 		    ((cmd->cmnd[1] & 0x1f) != SAI_READ_CAPACITY_16))
diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index 0cf43f6e464..52afabd23d9 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -24,7 +24,6 @@
 #define SERVICE_ACTION_IN_12 0xab
 #define SERVICE_ACTION_OUT_12 0xa9
 #define SERVICE_ACTION_BIDIRECTIONAL 0x9d
-#define SERVICE_ACTION_IN_16 0x9e
 #define SERVICE_ACTION_OUT_16 0x9f
 #define THIRD_PARTY_COPY_OUT 0x83
 #define THIRD_PARTY_COPY_IN 0x84
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index 4ebbeae161e..71e13804437 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -2159,7 +2159,7 @@ static void gdth_next(gdth_ha_str *ha)
               case VERIFY:
               case START_STOP:
               case MODE_SENSE:
-              case SERVICE_ACTION_IN:
+              case SERVICE_ACTION_IN_16:
                 TRACE(("cache cmd %x/%x/%x/%x/%x/%x\n",nscp->cmnd[0],
                        nscp->cmnd[1],nscp->cmnd[2],nscp->cmnd[3],
                        nscp->cmnd[4],nscp->cmnd[5]));
@@ -2391,7 +2391,7 @@ static int gdth_internal_cache_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp)
         gdth_copy_internal_data(ha, scp, (char*)&rdc, sizeof(gdth_rdcap_data));
         break;
 
-      case SERVICE_ACTION_IN:
+      case SERVICE_ACTION_IN_16:
         if ((scp->cmnd[1] & 0x1f) == SAI_READ_CAPACITY_16 &&
             (ha->cache_feat & GDT_64BIT)) {
             gdth_rdcap16_data rdc16;
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index b02571390d0..378e0aae29c 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -4210,7 +4210,7 @@ scsi_debug_queuecommand(struct scsi_cmnd *SCpnt)
 	case READ_CAPACITY:
 		errsts = resp_readcap(SCpnt, devip);
 		break;
-	case SERVICE_ACTION_IN:
+	case SERVICE_ACTION_IN_16:
 		if (cmd[1] == SAI_READ_CAPACITY_16)
 			errsts = resp_readcap16(SCpnt, devip);
 		else if (cmd[1] == SAI_GET_LBA_STATUS) {
diff --git a/drivers/scsi/scsi_trace.c b/drivers/scsi/scsi_trace.c
index 503594e5f76..82af28b9029 100644
--- a/drivers/scsi/scsi_trace.c
+++ b/drivers/scsi/scsi_trace.c
@@ -278,7 +278,7 @@ scsi_trace_parse_cdb(struct trace_seq *p, unsigned char *cdb, int len)
 		return scsi_trace_rw16(p, cdb, len);
 	case UNMAP:
 		return scsi_trace_unmap(p, cdb, len);
-	case SERVICE_ACTION_IN:
+	case SERVICE_ACTION_IN_16:
 		return scsi_trace_service_action_in(p, cdb, len);
 	case VARIABLE_LENGTH_CMD:
 		return scsi_trace_varlen(p, cdb, len);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 54abcb220ab..fedab3c21dd 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1982,7 +1982,7 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
 
 	do {
 		memset(cmd, 0, 16);
-		cmd[0] = SERVICE_ACTION_IN;
+		cmd[0] = SERVICE_ACTION_IN_16;
 		cmd[1] = SAI_READ_CAPACITY_16;
 		cmd[13] = RC16_LEN;
 		memset(buffer, 0, RC16_LEN);
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index fb87780929d..75cbde1f7c5 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -576,7 +576,7 @@ static inline int core_alua_state_standby(
 	case SEND_DIAGNOSTIC:
 	case READ_CAPACITY:
 		return 0;
-	case SERVICE_ACTION_IN:
+	case SERVICE_ACTION_IN_16:
 		switch (cdb[1] & 0x1f) {
 		case SAI_READ_CAPACITY_16:
 			return 0;
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index ebe62afb957..8d171ff77e7 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -852,7 +852,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 		size = READ_CAP_LEN;
 		cmd->execute_cmd = sbc_emulate_readcapacity;
 		break;
-	case SERVICE_ACTION_IN:
+	case SERVICE_ACTION_IN_16:
 		switch (cmd->t_task_cdb[1] & 0x1f) {
 		case SAI_READ_CAPACITY_16:
 			cmd->execute_cmd = sbc_emulate_readcapacity_16;
diff --git a/drivers/usb/gadget/legacy/tcm_usb_gadget.c b/drivers/usb/gadget/legacy/tcm_usb_gadget.c
index 6cdb7a534f2..024f58475a9 100644
--- a/drivers/usb/gadget/legacy/tcm_usb_gadget.c
+++ b/drivers/usb/gadget/legacy/tcm_usb_gadget.c
@@ -912,7 +912,7 @@ static int get_cmd_dir(const unsigned char *cdb)
 	case INQUIRY:
 	case MODE_SENSE:
 	case MODE_SENSE_10:
-	case SERVICE_ACTION_IN:
+	case SERVICE_ACTION_IN_16:
 	case MAINTENANCE_IN:
 	case PERSISTENT_RESERVE_IN:
 	case SECURITY_PROTOCOL_IN:
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index d17178e6fcd..b354c0de324 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -151,7 +151,7 @@ enum scsi_timeouts {
 #define VERIFY_16	      0x8f
 #define SYNCHRONIZE_CACHE_16  0x91
 #define WRITE_SAME_16	      0x93
-#define SERVICE_ACTION_IN     0x9e
+#define SERVICE_ACTION_IN_16  0x9e
 /* values for service action in */
 #define	SAI_READ_CAPACITY_16  0x10
 #define SAI_GET_LBA_STATUS    0x12
diff --git a/include/trace/events/scsi.h b/include/trace/events/scsi.h
index db6c93510f7..079bd10a01b 100644
--- a/include/trace/events/scsi.h
+++ b/include/trace/events/scsi.h
@@ -94,7 +94,7 @@
 		scsi_opcode_name(WRITE_16),			\
 		scsi_opcode_name(VERIFY_16),			\
 		scsi_opcode_name(WRITE_SAME_16),		\
-		scsi_opcode_name(SERVICE_ACTION_IN),		\
+		scsi_opcode_name(SERVICE_ACTION_IN_16),		\
 		scsi_opcode_name(SAI_READ_CAPACITY_16),		\
 		scsi_opcode_name(SAI_GET_LBA_STATUS),		\
 		scsi_opcode_name(MI_REPORT_TARGET_PGS),		\
diff --git a/include/trace/events/target.h b/include/trace/events/target.h
index da9cc0f05c9..45403443dd8 100644
--- a/include/trace/events/target.h
+++ b/include/trace/events/target.h
@@ -96,7 +96,7 @@
 		scsi_opcode_name(WRITE_16),			\
 		scsi_opcode_name(VERIFY_16),			\
 		scsi_opcode_name(WRITE_SAME_16),		\
-		scsi_opcode_name(SERVICE_ACTION_IN),		\
+		scsi_opcode_name(SERVICE_ACTION_IN_16),		\
 		scsi_opcode_name(SAI_READ_CAPACITY_16),		\
 		scsi_opcode_name(SAI_GET_LBA_STATUS),		\
 		scsi_opcode_name(MI_REPORT_TARGET_PGS),		\
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
index eda326fc862..c699f477a10 100644
--- a/tools/lib/traceevent/plugin_scsi.c
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -107,7 +107,7 @@ typedef unsigned int u32;
 #define VERIFY_16			0x8f
 #define SYNCHRONIZE_CACHE_16		0x91
 #define WRITE_SAME_16			0x93
-#define SERVICE_ACTION_IN		0x9e
+#define SERVICE_ACTION_IN_16		0x9e
 /* values for service action in */
 #define	SAI_READ_CAPACITY_16		0x10
 #define SAI_GET_LBA_STATUS		0x12
@@ -393,7 +393,7 @@ scsi_trace_parse_cdb(struct trace_seq *p, unsigned char *cdb, int len)
 		return scsi_trace_rw16(p, cdb, len);
 	case UNMAP:
 		return scsi_trace_unmap(p, cdb, len);
-	case SERVICE_ACTION_IN:
+	case SERVICE_ACTION_IN_16:
 		return scsi_trace_service_action_in(p, cdb, len);
 	case VARIABLE_LENGTH_CMD:
 		return scsi_trace_varlen(p, cdb, len);
-- 
cgit v1.2.3-70-g09d2


From 85686f696d81a4bcfa5e51ee9ee2b6aae5531c6f Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Mon, 17 Nov 2014 14:25:20 +0100
Subject: scsi: add SPC-3 command definitions

SPC-3 defines SERVICE ACTION IN(12), SERVICE_ACTION OUT(12),
SERVICE ACTION OUT(16), and SERVICE ACTION BIDIRECTIONAL.
And READ MEDIA SERIAL NUMBER has long since been deprecated.
So update callers to refer to the new cdb name.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Tested-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/constants.c           |  4 ----
 drivers/target/target_core_pr.c    |  2 +-
 include/scsi/scsi.h                | 10 +++++++---
 tools/lib/traceevent/plugin_scsi.c |  5 ++++-
 4 files changed, 12 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index 52afabd23d9..aee62f60b43 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -21,10 +21,6 @@
 
 
 /* Commands with service actions that change the command name */
-#define SERVICE_ACTION_IN_12 0xab
-#define SERVICE_ACTION_OUT_12 0xa9
-#define SERVICE_ACTION_BIDIRECTIONAL 0x9d
-#define SERVICE_ACTION_OUT_16 0x9f
 #define THIRD_PARTY_COPY_OUT 0x83
 #define THIRD_PARTY_COPY_IN 0x84
 
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 8c60a1a1ae8..806bfba894c 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -459,7 +459,7 @@ static int core_scsi3_pr_seq_non_holder(
 	case ACCESS_CONTROL_OUT:
 	case INQUIRY:
 	case LOG_SENSE:
-	case READ_MEDIA_SERIAL_NUMBER:
+	case SERVICE_ACTION_IN_12:
 	case REPORT_LUNS:
 	case REQUEST_SENSE:
 	case PERSISTENT_RESERVE_IN:
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index b354c0de324..8a7f8ad58aa 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -128,8 +128,10 @@ enum scsi_timeouts {
 #define MOVE_MEDIUM           0xa5
 #define EXCHANGE_MEDIUM       0xa6
 #define READ_12               0xa8
+#define SERVICE_ACTION_OUT_12 0xa9
 #define WRITE_12              0xaa
-#define READ_MEDIA_SERIAL_NUMBER 0xab
+#define READ_MEDIA_SERIAL_NUMBER 0xab /* Obsolete with SPC-2 */
+#define SERVICE_ACTION_IN_12  0xab
 #define WRITE_VERIFY_12       0xae
 #define VERIFY_12	      0xaf
 #define SEARCH_HIGH_12        0xb0
@@ -151,7 +153,9 @@ enum scsi_timeouts {
 #define VERIFY_16	      0x8f
 #define SYNCHRONIZE_CACHE_16  0x91
 #define WRITE_SAME_16	      0x93
+#define SERVICE_ACTION_BIDIRECTIONAL 0x9d
 #define SERVICE_ACTION_IN_16  0x9e
+#define SERVICE_ACTION_OUT_16 0x9f
 /* values for service action in */
 #define	SAI_READ_CAPACITY_16  0x10
 #define SAI_GET_LBA_STATUS    0x12
@@ -165,8 +169,8 @@ enum scsi_timeouts {
 #define MI_REPORT_ALIASES     0x0b
 #define MI_REPORT_SUPPORTED_OPERATION_CODES 0x0c
 #define MI_REPORT_SUPPORTED_TASK_MANAGEMENT_FUNCTIONS 0x0d
-#define MI_REPORT_PRIORITY   0x0e
-#define MI_REPORT_TIMESTAMP  0x0f
+#define MI_REPORT_PRIORITY    0x0e
+#define MI_REPORT_TIMESTAMP   0x0f
 #define MI_MANAGEMENT_PROTOCOL_IN 0x10
 /* value for MI_REPORT_TARGET_PGS ext header */
 #define MI_EXT_HDR_PARAM_FMT  0x20
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
index c699f477a10..3727de48c8d 100644
--- a/tools/lib/traceevent/plugin_scsi.c
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -85,8 +85,9 @@ typedef unsigned int u32;
 #define MOVE_MEDIUM			0xa5
 #define EXCHANGE_MEDIUM			0xa6
 #define READ_12				0xa8
+#define SERVICE_ACTION_OUT_12		0xa9
 #define WRITE_12			0xaa
-#define READ_MEDIA_SERIAL_NUMBER	0xab
+#define SERVICE_ACTION_IN_12		0xab
 #define WRITE_VERIFY_12			0xae
 #define VERIFY_12			0xaf
 #define SEARCH_HIGH_12			0xb0
@@ -107,7 +108,9 @@ typedef unsigned int u32;
 #define VERIFY_16			0x8f
 #define SYNCHRONIZE_CACHE_16		0x91
 #define WRITE_SAME_16			0x93
+#define SERVICE_ACTION_BIDIRECTIONAL	0x9d
 #define SERVICE_ACTION_IN_16		0x9e
+#define SERVICE_ACTION_OUT_16		0x9f
 /* values for service action in */
 #define	SAI_READ_CAPACITY_16		0x10
 #define SAI_GET_LBA_STATUS		0x12
-- 
cgit v1.2.3-70-g09d2


From 2ad7bf3638411cb547f2823df08166c13ab04269 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Sun, 23 Nov 2014 23:07:46 -0800
Subject: ipvlan: Initial check-in of the IPVLAN driver.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This driver is very similar to the macvlan driver except that it
uses L3 on the frame to determine the logical interface while
functioning as packet dispatcher. It inherits L2 of the master
device hence the packets on wire will have the same L2 for all
the packets originating from all virtual devices off of the same
master device.

This driver was developed keeping the namespace use-case in
mind. Hence most of the examples given here take that as the
base setup where main-device belongs to the default-ns and
virtual devices are assigned to the additional namespaces.

The device operates in two different modes and the difference
in these two modes in primarily in the TX side.

(a) L2 mode : In this mode, the device behaves as a L2 device.
TX processing upto L2 happens on the stack of the virtual device
associated with (namespace). Packets are switched after that
into the main device (default-ns) and queued for xmit.

RX processing is simple and all multicast, broadcast (if
applicable), and unicast belonging to the address(es) are
delivered to the virtual devices.

(b) L3 mode : In this mode, the device behaves like a L3 device.
TX processing upto L3 happens on the stack of the virtual device
associated with (namespace). Packets are switched to the
main-device (default-ns) for the L2 processing. Hence the routing
table of the default-ns will be used in this mode.

RX processins is somewhat similar to the L2 mode except that in
this mode only Unicast packets are delivered to the virtual device
while main-dev will handle all other packets.

The devices can be added using the "ip" command from the iproute2
package -

	ip link add link <master> <virtual> type ipvlan mode [ l2 | l3 ]

Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Laurent Chavey <chavey@google.com>
Cc: Tim Hockin <thockin@google.com>
Cc: Brandon Philips <brandon.philips@coreos.com>
Cc: Pavel Emelianov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ipvlan.txt | 107 +++++
 drivers/net/Kconfig                 |  18 +
 drivers/net/Makefile                |   1 +
 drivers/net/ipvlan/Makefile         |   7 +
 drivers/net/ipvlan/ipvlan.h         | 130 ++++++
 drivers/net/ipvlan/ipvlan_core.c    | 607 +++++++++++++++++++++++++++
 drivers/net/ipvlan/ipvlan_main.c    | 789 ++++++++++++++++++++++++++++++++++++
 include/linux/netdevice.h           |   4 +
 include/uapi/linux/if_link.h        |  15 +
 9 files changed, 1678 insertions(+)
 create mode 100644 Documentation/networking/ipvlan.txt
 create mode 100644 drivers/net/ipvlan/Makefile
 create mode 100644 drivers/net/ipvlan/ipvlan.h
 create mode 100644 drivers/net/ipvlan/ipvlan_core.c
 create mode 100644 drivers/net/ipvlan/ipvlan_main.c

(limited to 'include')

diff --git a/Documentation/networking/ipvlan.txt b/Documentation/networking/ipvlan.txt
new file mode 100644
index 00000000000..cf996394e46
--- /dev/null
+++ b/Documentation/networking/ipvlan.txt
@@ -0,0 +1,107 @@
+
+                            IPVLAN Driver HOWTO
+
+Initial Release:
+	Mahesh Bandewar <maheshb AT google.com>
+
+1. Introduction:
+	This is conceptually very similar to the macvlan driver with one major
+exception of using L3 for mux-ing /demux-ing among slaves. This property makes
+the master device share the L2 with it's slave devices. I have developed this
+driver in conjuntion with network namespaces and not sure if there is use case
+outside of it.
+
+
+2. Building and Installation:
+	In order to build the driver, please select the config item CONFIG_IPVLAN.
+The driver can be built into the kernel (CONFIG_IPVLAN=y) or as a module
+(CONFIG_IPVLAN=m).
+
+
+3. Configuration:
+	There are no module parameters for this driver and it can be configured
+using IProute2/ip utility.
+
+	ip link add link <master-dev> <slave-dev> type ipvlan mode { l2 | L3 }
+
+	e.g. ip link add link ipvl0 eth0 type ipvlan mode l2
+
+
+4. Operating modes:
+	IPvlan has two modes of operation - L2 and L3. For a given master device,
+you can select one of these two modes and all slaves on that master will
+operate in the same (selected) mode. The RX mode is almost identical except
+that in L3 mode the slaves wont receive any multicast / broadcast traffic.
+L3 mode is more restrictive since routing is controlled from the other (mostly)
+default namespace.
+
+4.1 L2 mode:
+	In this mode TX processing happens on the stack instance attached to the
+slave device and packets are switched and queued to the master device to send
+out. In this mode the slaves will RX/TX multicast and broadcast (if applicable)
+as well.
+
+4.2 L3 mode:
+	In this mode TX processing upto L3 happens on the stack instance attached
+to the slave device and packets are switched to the stack instance of the
+master device for the L2 processing and routing from that instance will be
+used before packets are queued on the outbound device. In this mode the slaves
+will not receive nor can send multicast / broadcast traffic.
+
+
+5. What to choose (macvlan vs. ipvlan)?
+	These two devices are very similar in many regards and the specific use
+case could very well define which device to choose. if one of the following
+situations defines your use case then you can choose to use ipvlan -
+	(a) The Linux host that is connected to the external switch / router has
+policy configured that allows only one mac per port.
+	(b) No of virtual devices created on a master exceed the mac capacity and
+puts the NIC in promiscous mode and degraded performance is a concern.
+	(c) If the slave device is to be put into the hostile / untrusted network
+namespace where L2 on the slave could be changed / misused.
+
+
+6. Example configuration:
+
+  +=============================================================+
+  |  Host: host1                                                |
+  |                                                             |
+  |   +----------------------+      +----------------------+    |
+  |   |   NS:ns0             |      |  NS:ns1              |    |
+  |   |                      |      |                      |    |
+  |   |                      |      |                      |    |
+  |   |        ipvl0         |      |         ipvl1        |    |
+  |   +----------#-----------+      +-----------#----------+    |
+  |              #                              #               |
+  |              ################################               |
+  |                              # eth0                         |
+  +==============================#==============================+
+
+
+	(a) Create two network namespaces - ns0, ns1
+		ip netns add ns0
+		ip netns add ns1
+
+	(b) Create two ipvlan slaves on eth0 (master device)
+		ip link add link eth0 ipvl0 type ipvlan mode l2
+		ip link add link eth0 ipvl1 type ipvlan mode l2
+
+	(c) Assign slaves to the respective network namespaces
+		ip link set dev ipvl0 netns ns0
+		ip link set dev ipvl1 netns ns1
+
+	(d) Now switch to the namespace (ns0 or ns1) to configure the slave devices
+		- For ns0
+			(1) ip netns exec ns0 bash
+			(2) ip link set dev ipvl0 up
+			(3) ip link set dev lo up
+			(4) ip -4 addr add 127.0.0.1 dev lo
+			(5) ip -4 addr add $IPADDR dev ipvl0
+			(6) ip -4 route add default via $ROUTER dev ipvl0
+		- For ns1
+			(1) ip netns exec ns1 bash
+			(2) ip link set dev ipvl1 up
+			(3) ip link set dev lo up
+			(4) ip -4 addr add 127.0.0.1 dev lo
+			(5) ip -4 addr add $IPADDR dev ipvl1
+			(6) ip -4 route add default via $ROUTER dev ipvl1
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index f9009be3f30..b6d64f54657 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -145,6 +145,24 @@ config MACVTAP
 	  To compile this driver as a module, choose M here: the module
 	  will be called macvtap.
 
+
+config IPVLAN
+    tristate "IP-VLAN support"
+    ---help---
+      This allows one to create virtual devices off of a main interface
+      and packets will be delivered based on the dest L3 (IPv6/IPv4 addr)
+      on packets. All interfaces (including the main interface) share L2
+      making it transparent to the connected L2 switch.
+
+      Ipvlan devices can be added using the "ip" command from the
+      iproute2 package starting with the iproute2-X.Y.ZZ release:
+
+      "ip link add link <main-dev> [ NAME ] type ipvlan"
+
+      To compile this driver as a module, choose M here: the module
+      will be called ipvlan.
+
+
 config VXLAN
        tristate "Virtual eXtensible Local Area Network (VXLAN)"
        depends on INET
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 61aefdd1e17..e25fdd7d905 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -6,6 +6,7 @@
 # Networking Core Drivers
 #
 obj-$(CONFIG_BONDING) += bonding/
+obj-$(CONFIG_IPVLAN) += ipvlan/
 obj-$(CONFIG_DUMMY) += dummy.o
 obj-$(CONFIG_EQUALIZER) += eql.o
 obj-$(CONFIG_IFB) += ifb.o
diff --git a/drivers/net/ipvlan/Makefile b/drivers/net/ipvlan/Makefile
new file mode 100644
index 00000000000..df79910192d
--- /dev/null
+++ b/drivers/net/ipvlan/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the Ethernet Ipvlan driver
+#
+
+obj-$(CONFIG_IPVLAN) += ipvlan.o
+
+ipvlan-objs := ipvlan_core.o ipvlan_main.o
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
new file mode 100644
index 00000000000..ab3e7614ed7
--- /dev/null
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -0,0 +1,130 @@
+/*
+ * Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ */
+#ifndef __IPVLAN_H
+#define __IPVLAN_H
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rculist.h>
+#include <linux/notifier.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/if_arp.h>
+#include <linux/if_link.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/inetdevice.h>
+#include <net/rtnetlink.h>
+#include <net/gre.h>
+#include <net/route.h>
+#include <net/addrconf.h>
+
+#define IPVLAN_DRV	"ipvlan"
+#define IPV_DRV_VER	"0.1"
+
+#define IPVLAN_HASH_SIZE	(1 << BITS_PER_BYTE)
+#define IPVLAN_HASH_MASK	(IPVLAN_HASH_SIZE - 1)
+
+#define IPVLAN_MAC_FILTER_BITS	8
+#define IPVLAN_MAC_FILTER_SIZE	(1 << IPVLAN_MAC_FILTER_BITS)
+#define IPVLAN_MAC_FILTER_MASK	(IPVLAN_MAC_FILTER_SIZE - 1)
+
+typedef enum {
+	IPVL_IPV6 = 0,
+	IPVL_ICMPV6,
+	IPVL_IPV4,
+	IPVL_ARP,
+} ipvl_hdr_type;
+
+struct ipvl_pcpu_stats {
+	u64			rx_pkts;
+	u64			rx_bytes;
+	u64			rx_mcast;
+	u64			tx_pkts;
+	u64			tx_bytes;
+	struct u64_stats_sync	syncp;
+	u32			rx_errs;
+	u32			tx_drps;
+};
+
+struct ipvl_port;
+
+struct ipvl_dev {
+	struct net_device	*dev;
+	struct list_head	pnode;
+	struct ipvl_port	*port;
+	struct net_device	*phy_dev;
+	struct list_head	addrs;
+	int			ipv4cnt;
+	int			ipv6cnt;
+	struct ipvl_pcpu_stats	*pcpu_stats;
+	DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE);
+	netdev_features_t	sfeatures;
+	u32			msg_enable;
+	u16			mtu_adj;
+};
+
+struct ipvl_addr {
+	struct ipvl_dev		*master; /* Back pointer to master */
+	union {
+		struct in6_addr	ip6;	 /* IPv6 address on logical interface */
+		struct in_addr	ip4;	 /* IPv4 address on logical interface */
+	} ipu;
+#define ip6addr	ipu.ip6
+#define ip4addr ipu.ip4
+	struct hlist_node	hlnode;  /* Hash-table linkage */
+	struct list_head	anode;   /* logical-interface linkage */
+	struct rcu_head		rcu;
+	ipvl_hdr_type		atype;
+};
+
+struct ipvl_port {
+	struct net_device	*dev;
+	struct hlist_head	hlhead[IPVLAN_HASH_SIZE];
+	struct list_head	ipvlans;
+	struct rcu_head		rcu;
+	int			count;
+	u16			mode;
+};
+
+static inline struct ipvl_port *ipvlan_port_get_rcu(const struct net_device *d)
+{
+	return rcu_dereference(d->rx_handler_data);
+}
+
+static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d)
+{
+	return rtnl_dereference(d->rx_handler_data);
+}
+
+static inline bool ipvlan_dev_master(struct net_device *d)
+{
+	return d->priv_flags & IFF_IPVLAN_MASTER;
+}
+
+static inline bool ipvlan_dev_slave(struct net_device *d)
+{
+	return d->priv_flags & IFF_IPVLAN_SLAVE;
+}
+
+void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev);
+void ipvlan_set_port_mode(struct ipvl_port *port, u32 nval);
+void ipvlan_init_secret(void);
+unsigned int ipvlan_mac_hash(const unsigned char *addr);
+rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb);
+int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev);
+void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr);
+bool ipvlan_addr_busy(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6);
+struct ipvl_addr *ipvlan_ht_addr_lookup(const struct ipvl_port *port,
+					const void *iaddr, bool is_v6);
+void ipvlan_ht_addr_del(struct ipvl_addr *addr, bool sync);
+#endif /* __IPVLAN_H */
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
new file mode 100644
index 00000000000..a14d8778324
--- /dev/null
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -0,0 +1,607 @@
+/* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ */
+
+#include "ipvlan.h"
+
+static u32 ipvlan_jhash_secret;
+
+void ipvlan_init_secret(void)
+{
+	net_get_random_once(&ipvlan_jhash_secret, sizeof(ipvlan_jhash_secret));
+}
+
+static void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
+			    unsigned int len, bool success, bool mcast)
+{
+	if (!ipvlan)
+		return;
+
+	if (likely(success)) {
+		struct ipvl_pcpu_stats *pcptr;
+
+		pcptr = this_cpu_ptr(ipvlan->pcpu_stats);
+		u64_stats_update_begin(&pcptr->syncp);
+		pcptr->rx_pkts++;
+		pcptr->rx_bytes += len;
+		if (mcast)
+			pcptr->rx_mcast++;
+		u64_stats_update_end(&pcptr->syncp);
+	} else {
+		this_cpu_inc(ipvlan->pcpu_stats->rx_errs);
+	}
+}
+
+static u8 ipvlan_get_v6_hash(const void *iaddr)
+{
+	const struct in6_addr *ip6_addr = iaddr;
+
+	return __ipv6_addr_jhash(ip6_addr, ipvlan_jhash_secret) &
+	       IPVLAN_HASH_MASK;
+}
+
+static u8 ipvlan_get_v4_hash(const void *iaddr)
+{
+	const struct in_addr *ip4_addr = iaddr;
+
+	return jhash_1word(ip4_addr->s_addr, ipvlan_jhash_secret) &
+	       IPVLAN_HASH_MASK;
+}
+
+struct ipvl_addr *ipvlan_ht_addr_lookup(const struct ipvl_port *port,
+					const void *iaddr, bool is_v6)
+{
+	struct ipvl_addr *addr;
+	u8 hash;
+
+	hash = is_v6 ? ipvlan_get_v6_hash(iaddr) :
+	       ipvlan_get_v4_hash(iaddr);
+	hlist_for_each_entry_rcu(addr, &port->hlhead[hash], hlnode) {
+		if (is_v6 && addr->atype == IPVL_IPV6 &&
+		    ipv6_addr_equal(&addr->ip6addr, iaddr))
+			return addr;
+		else if (!is_v6 && addr->atype == IPVL_IPV4 &&
+			 addr->ip4addr.s_addr ==
+				((struct in_addr *)iaddr)->s_addr)
+			return addr;
+	}
+	return NULL;
+}
+
+void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr)
+{
+	struct ipvl_port *port = ipvlan->port;
+	u8 hash;
+
+	hash = (addr->atype == IPVL_IPV6) ?
+	       ipvlan_get_v6_hash(&addr->ip6addr) :
+	       ipvlan_get_v4_hash(&addr->ip4addr);
+	hlist_add_head_rcu(&addr->hlnode, &port->hlhead[hash]);
+}
+
+void ipvlan_ht_addr_del(struct ipvl_addr *addr, bool sync)
+{
+	hlist_del_rcu(&addr->hlnode);
+	if (sync)
+		synchronize_rcu();
+}
+
+bool ipvlan_addr_busy(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6)
+{
+	struct ipvl_port *port = ipvlan->port;
+	struct ipvl_addr *addr;
+
+	list_for_each_entry(addr, &ipvlan->addrs, anode) {
+		if ((is_v6 && addr->atype == IPVL_IPV6 &&
+		    ipv6_addr_equal(&addr->ip6addr, iaddr)) ||
+		    (!is_v6 && addr->atype == IPVL_IPV4 &&
+		    addr->ip4addr.s_addr == ((struct in_addr *)iaddr)->s_addr))
+			return true;
+	}
+
+	if (ipvlan_ht_addr_lookup(port, iaddr, is_v6))
+		return true;
+
+	return false;
+}
+
+static void *ipvlan_get_L3_hdr(struct sk_buff *skb, int *type)
+{
+	void *lyr3h = NULL;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_ARP): {
+		struct arphdr *arph;
+
+		if (unlikely(!pskb_may_pull(skb, sizeof(*arph))))
+			return NULL;
+
+		arph = arp_hdr(skb);
+		*type = IPVL_ARP;
+		lyr3h = arph;
+		break;
+	}
+	case htons(ETH_P_IP): {
+		u32 pktlen;
+		struct iphdr *ip4h;
+
+		if (unlikely(!pskb_may_pull(skb, sizeof(*ip4h))))
+			return NULL;
+
+		ip4h = ip_hdr(skb);
+		pktlen = ntohs(ip4h->tot_len);
+		if (ip4h->ihl < 5 || ip4h->version != 4)
+			return NULL;
+		if (skb->len < pktlen || pktlen < (ip4h->ihl * 4))
+			return NULL;
+
+		*type = IPVL_IPV4;
+		lyr3h = ip4h;
+		break;
+	}
+	case htons(ETH_P_IPV6): {
+		struct ipv6hdr *ip6h;
+
+		if (unlikely(!pskb_may_pull(skb, sizeof(*ip6h))))
+			return NULL;
+
+		ip6h = ipv6_hdr(skb);
+		if (ip6h->version != 6)
+			return NULL;
+
+		*type = IPVL_IPV6;
+		lyr3h = ip6h;
+		/* Only Neighbour Solicitation pkts need different treatment */
+		if (ipv6_addr_any(&ip6h->saddr) &&
+		    ip6h->nexthdr == NEXTHDR_ICMP) {
+			*type = IPVL_ICMPV6;
+			lyr3h = ip6h + 1;
+		}
+		break;
+	}
+	default:
+		return NULL;
+	}
+
+	return lyr3h;
+}
+
+unsigned int ipvlan_mac_hash(const unsigned char *addr)
+{
+	u32 hash = jhash_1word(__get_unaligned_cpu32(addr+2),
+			       ipvlan_jhash_secret);
+
+	return hash & IPVLAN_MAC_FILTER_MASK;
+}
+
+static void ipvlan_multicast_frame(struct ipvl_port *port, struct sk_buff *skb,
+				   const struct ipvl_dev *in_dev, bool local)
+{
+	struct ethhdr *eth = eth_hdr(skb);
+	struct ipvl_dev *ipvlan;
+	struct sk_buff *nskb;
+	unsigned int len;
+	unsigned int mac_hash;
+	int ret;
+
+	if (skb->protocol == htons(ETH_P_PAUSE))
+		return;
+
+	list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+		if (local && (ipvlan == in_dev))
+			continue;
+
+		mac_hash = ipvlan_mac_hash(eth->h_dest);
+		if (!test_bit(mac_hash, ipvlan->mac_filters))
+			continue;
+
+		ret = NET_RX_DROP;
+		len = skb->len + ETH_HLEN;
+		nskb = skb_clone(skb, GFP_ATOMIC);
+		if (!nskb)
+			goto mcast_acct;
+
+		if (ether_addr_equal(eth->h_dest, ipvlan->phy_dev->broadcast))
+			nskb->pkt_type = PACKET_BROADCAST;
+		else
+			nskb->pkt_type = PACKET_MULTICAST;
+
+		nskb->dev = ipvlan->dev;
+		if (local)
+			ret = dev_forward_skb(ipvlan->dev, nskb);
+		else
+			ret = netif_rx(nskb);
+mcast_acct:
+		ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
+	}
+
+	/* Locally generated? ...Forward a copy to the main-device as
+	 * well. On the RX side we'll ignore it (wont give it to any
+	 * of the virtual devices.
+	 */
+	if (local) {
+		nskb = skb_clone(skb, GFP_ATOMIC);
+		if (nskb) {
+			if (ether_addr_equal(eth->h_dest, port->dev->broadcast))
+				nskb->pkt_type = PACKET_BROADCAST;
+			else
+				nskb->pkt_type = PACKET_MULTICAST;
+
+			dev_forward_skb(port->dev, nskb);
+		}
+	}
+}
+
+static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff *skb,
+			    bool local)
+{
+	struct ipvl_dev *ipvlan = addr->master;
+	struct net_device *dev = ipvlan->dev;
+	unsigned int len;
+	rx_handler_result_t ret = RX_HANDLER_CONSUMED;
+	bool success = false;
+
+	len = skb->len + ETH_HLEN;
+	if (unlikely(!(dev->flags & IFF_UP))) {
+		kfree_skb(skb);
+		goto out;
+	}
+
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		goto out;
+
+	skb->dev = dev;
+	skb->pkt_type = PACKET_HOST;
+
+	if (local) {
+		if (dev_forward_skb(ipvlan->dev, skb) == NET_RX_SUCCESS)
+			success = true;
+	} else {
+		ret = RX_HANDLER_ANOTHER;
+		success = true;
+	}
+
+out:
+	ipvlan_count_rx(ipvlan, len, success, false);
+	return ret;
+}
+
+static struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port,
+					    void *lyr3h, int addr_type,
+					    bool use_dest)
+{
+	struct ipvl_addr *addr = NULL;
+
+	if (addr_type == IPVL_IPV6) {
+		struct ipv6hdr *ip6h;
+		struct in6_addr *i6addr;
+
+		ip6h = (struct ipv6hdr *)lyr3h;
+		i6addr = use_dest ? &ip6h->daddr : &ip6h->saddr;
+		addr = ipvlan_ht_addr_lookup(port, i6addr, true);
+	} else if (addr_type == IPVL_ICMPV6) {
+		struct nd_msg *ndmh;
+		struct in6_addr *i6addr;
+
+		/* Make sure that the NeighborSolicitation ICMPv6 packets
+		 * are handled to avoid DAD issue.
+		 */
+		ndmh = (struct nd_msg *)lyr3h;
+		if (ndmh->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) {
+			i6addr = &ndmh->target;
+			addr = ipvlan_ht_addr_lookup(port, i6addr, true);
+		}
+	} else if (addr_type == IPVL_IPV4) {
+		struct iphdr *ip4h;
+		__be32 *i4addr;
+
+		ip4h = (struct iphdr *)lyr3h;
+		i4addr = use_dest ? &ip4h->daddr : &ip4h->saddr;
+		addr = ipvlan_ht_addr_lookup(port, i4addr, false);
+	} else if (addr_type == IPVL_ARP) {
+		struct arphdr *arph;
+		unsigned char *arp_ptr;
+		__be32 dip;
+
+		arph = (struct arphdr *)lyr3h;
+		arp_ptr = (unsigned char *)(arph + 1);
+		if (use_dest)
+			arp_ptr += (2 * port->dev->addr_len) + 4;
+		else
+			arp_ptr += port->dev->addr_len;
+
+		memcpy(&dip, arp_ptr, 4);
+		addr = ipvlan_ht_addr_lookup(port, &dip, false);
+	}
+
+	return addr;
+}
+
+static int ipvlan_process_v4_outbound(struct sk_buff *skb)
+{
+	const struct iphdr *ip4h = ip_hdr(skb);
+	struct net_device *dev = skb->dev;
+	struct rtable *rt;
+	int err, ret = NET_XMIT_DROP;
+	struct flowi4 fl4 = {
+		.flowi4_oif = dev->iflink,
+		.flowi4_tos = RT_TOS(ip4h->tos),
+		.flowi4_flags = FLOWI_FLAG_ANYSRC,
+		.daddr = ip4h->daddr,
+		.saddr = ip4h->saddr,
+	};
+
+	rt = ip_route_output_flow(dev_net(dev), &fl4, NULL);
+	if (IS_ERR(rt))
+		goto err;
+
+	if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
+		ip_rt_put(rt);
+		goto err;
+	}
+	skb_dst_drop(skb);
+	skb_dst_set(skb, &rt->dst);
+	err = ip_local_out(skb);
+	if (unlikely(net_xmit_eval(err)))
+		dev->stats.tx_errors++;
+	else
+		ret = NET_XMIT_SUCCESS;
+	goto out;
+err:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+out:
+	return ret;
+}
+
+static int ipvlan_process_v6_outbound(struct sk_buff *skb)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	struct net_device *dev = skb->dev;
+	struct dst_entry *dst;
+	int err, ret = NET_XMIT_DROP;
+	struct flowi6 fl6 = {
+		.flowi6_iif = skb->dev->ifindex,
+		.daddr = ip6h->daddr,
+		.saddr = ip6h->saddr,
+		.flowi6_flags = FLOWI_FLAG_ANYSRC,
+		.flowlabel = ip6_flowinfo(ip6h),
+		.flowi6_mark = skb->mark,
+		.flowi6_proto = ip6h->nexthdr,
+	};
+
+	dst = ip6_route_output(dev_net(dev), NULL, &fl6);
+	if (IS_ERR(dst))
+		goto err;
+
+	skb_dst_drop(skb);
+	skb_dst_set(skb, dst);
+	err = ip6_local_out(skb);
+	if (unlikely(net_xmit_eval(err)))
+		dev->stats.tx_errors++;
+	else
+		ret = NET_XMIT_SUCCESS;
+	goto out;
+err:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+out:
+	return ret;
+}
+
+static int ipvlan_process_outbound(struct sk_buff *skb,
+				   const struct ipvl_dev *ipvlan)
+{
+	struct ethhdr *ethh = eth_hdr(skb);
+	int ret = NET_XMIT_DROP;
+
+	/* In this mode we dont care about multicast and broadcast traffic */
+	if (is_multicast_ether_addr(ethh->h_dest)) {
+		pr_warn_ratelimited("Dropped {multi|broad}cast of type= [%x]\n",
+				    ntohs(skb->protocol));
+		kfree_skb(skb);
+		goto out;
+	}
+
+	/* The ipvlan is a pseudo-L2 device, so the packets that we receive
+	 * will have L2; which need to discarded and processed further
+	 * in the net-ns of the main-device.
+	 */
+	if (skb_mac_header_was_set(skb)) {
+		skb_pull(skb, sizeof(*ethh));
+		skb->mac_header = (typeof(skb->mac_header))~0U;
+		skb_reset_network_header(skb);
+	}
+
+	if (skb->protocol == htons(ETH_P_IPV6))
+		ret = ipvlan_process_v6_outbound(skb);
+	else if (skb->protocol == htons(ETH_P_IP))
+		ret = ipvlan_process_v4_outbound(skb);
+	else {
+		pr_warn_ratelimited("Dropped outbound packet type=%x\n",
+				    ntohs(skb->protocol));
+		kfree_skb(skb);
+	}
+out:
+	return ret;
+}
+
+static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct ipvl_dev *ipvlan = netdev_priv(dev);
+	void *lyr3h;
+	struct ipvl_addr *addr;
+	int addr_type;
+
+	lyr3h = ipvlan_get_L3_hdr(skb, &addr_type);
+	if (!lyr3h)
+		goto out;
+
+	addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true);
+	if (addr)
+		return ipvlan_rcv_frame(addr, skb, true);
+
+out:
+	skb->dev = ipvlan->phy_dev;
+	return ipvlan_process_outbound(skb, ipvlan);
+}
+
+static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ethhdr *eth = eth_hdr(skb);
+	struct ipvl_addr *addr;
+	void *lyr3h;
+	int addr_type;
+
+	if (ether_addr_equal(eth->h_dest, eth->h_source)) {
+		lyr3h = ipvlan_get_L3_hdr(skb, &addr_type);
+		if (lyr3h) {
+			addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true);
+			if (addr)
+				return ipvlan_rcv_frame(addr, skb, true);
+		}
+		skb = skb_share_check(skb, GFP_ATOMIC);
+		if (!skb)
+			return NET_XMIT_DROP;
+
+		/* Packet definitely does not belong to any of the
+		 * virtual devices, but the dest is local. So forward
+		 * the skb for the main-dev. At the RX side we just return
+		 * RX_PASS for it to be processed further on the stack.
+		 */
+		return dev_forward_skb(ipvlan->phy_dev, skb);
+
+	} else if (is_multicast_ether_addr(eth->h_dest)) {
+		u8 ip_summed = skb->ip_summed;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		ipvlan_multicast_frame(ipvlan->port, skb, ipvlan, true);
+		skb->ip_summed = ip_summed;
+	}
+
+	skb->dev = ipvlan->phy_dev;
+	return dev_queue_xmit(skb);
+}
+
+int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ipvl_port *port = ipvlan_port_get_rcu(ipvlan->phy_dev);
+
+	if (!port)
+		goto out;
+
+	if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr))))
+		goto out;
+
+	switch(port->mode) {
+	case IPVLAN_MODE_L2:
+		return ipvlan_xmit_mode_l2(skb, dev);
+	case IPVLAN_MODE_L3:
+		return ipvlan_xmit_mode_l3(skb, dev);
+	}
+
+	/* Should not reach here */
+	WARN_ONCE(true, "ipvlan_queue_xmit() called for mode = [%hx]\n",
+			  port->mode);
+out:
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
+
+static bool ipvlan_external_frame(struct sk_buff *skb, struct ipvl_port *port)
+{
+	struct ethhdr *eth = eth_hdr(skb);
+	struct ipvl_addr *addr;
+	void *lyr3h;
+	int addr_type;
+
+	if (ether_addr_equal(eth->h_source, skb->dev->dev_addr)) {
+		lyr3h = ipvlan_get_L3_hdr(skb, &addr_type);
+		if (!lyr3h)
+			return true;
+
+		addr = ipvlan_addr_lookup(port, lyr3h, addr_type, false);
+		if (addr)
+			return false;
+	}
+
+	return true;
+}
+
+static rx_handler_result_t ipvlan_handle_mode_l3(struct sk_buff **pskb,
+						 struct ipvl_port *port)
+{
+	void *lyr3h;
+	int addr_type;
+	struct ipvl_addr *addr;
+	struct sk_buff *skb = *pskb;
+	rx_handler_result_t ret = RX_HANDLER_PASS;
+
+	lyr3h = ipvlan_get_L3_hdr(skb, &addr_type);
+	if (!lyr3h)
+		goto out;
+
+	addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true);
+	if (addr)
+		ret = ipvlan_rcv_frame(addr, skb, false);
+
+out:
+	return ret;
+}
+
+static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb,
+						 struct ipvl_port *port)
+{
+	struct sk_buff *skb = *pskb;
+	struct ethhdr *eth = eth_hdr(skb);
+	rx_handler_result_t ret = RX_HANDLER_PASS;
+	void *lyr3h;
+	int addr_type;
+
+	if (is_multicast_ether_addr(eth->h_dest)) {
+		if (ipvlan_external_frame(skb, port))
+			ipvlan_multicast_frame(port, skb, NULL, false);
+	} else {
+		struct ipvl_addr *addr;
+
+		lyr3h = ipvlan_get_L3_hdr(skb, &addr_type);
+		if (!lyr3h)
+			return ret;
+
+		addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true);
+		if (addr)
+			ret = ipvlan_rcv_frame(addr, skb, false);
+	}
+
+	return ret;
+}
+
+rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb)
+{
+	struct sk_buff *skb = *pskb;
+	struct ipvl_port *port = ipvlan_port_get_rcu(skb->dev);
+
+	if (!port)
+		return RX_HANDLER_PASS;
+
+	switch (port->mode) {
+	case IPVLAN_MODE_L2:
+		return ipvlan_handle_mode_l2(pskb, port);
+	case IPVLAN_MODE_L3:
+		return ipvlan_handle_mode_l3(pskb, port);
+	}
+
+	/* Should not reach here */
+	WARN_ONCE(true, "ipvlan_handle_frame() called for mode = [%hx]\n",
+			  port->mode);
+	kfree_skb(skb);
+	return NET_RX_DROP;
+}
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
new file mode 100644
index 00000000000..c3df84bd285
--- /dev/null
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -0,0 +1,789 @@
+/* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ */
+
+#include "ipvlan.h"
+
+void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev)
+{
+	ipvlan->dev->mtu = dev->mtu - ipvlan->mtu_adj;
+}
+
+void ipvlan_set_port_mode(struct ipvl_port *port, u32 nval)
+{
+	struct ipvl_dev *ipvlan;
+
+	if (port->mode != nval) {
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+			if (nval == IPVLAN_MODE_L3)
+				ipvlan->dev->flags |= IFF_NOARP;
+			else
+				ipvlan->dev->flags &= ~IFF_NOARP;
+		}
+		port->mode = nval;
+	}
+}
+
+static int ipvlan_port_create(struct net_device *dev)
+{
+	struct ipvl_port *port;
+	int err, idx;
+
+	if (dev->type != ARPHRD_ETHER || dev->flags & IFF_LOOPBACK) {
+		netdev_err(dev, "Master is either lo or non-ether device\n");
+		return -EINVAL;
+	}
+	port = kzalloc(sizeof(struct ipvl_port), GFP_KERNEL);
+	if (!port)
+		return -ENOMEM;
+
+	port->dev = dev;
+	port->mode = IPVLAN_MODE_L3;
+	INIT_LIST_HEAD(&port->ipvlans);
+	for (idx = 0; idx < IPVLAN_HASH_SIZE; idx++)
+		INIT_HLIST_HEAD(&port->hlhead[idx]);
+
+	err = netdev_rx_handler_register(dev, ipvlan_handle_frame, port);
+	if (err)
+		goto err;
+
+	dev->priv_flags |= IFF_IPVLAN_MASTER;
+	return 0;
+
+err:
+	kfree_rcu(port, rcu);
+	return err;
+}
+
+static void ipvlan_port_destroy(struct net_device *dev)
+{
+	struct ipvl_port *port = ipvlan_port_get_rtnl(dev);
+
+	dev->priv_flags &= ~IFF_IPVLAN_MASTER;
+	netdev_rx_handler_unregister(dev);
+	kfree_rcu(port, rcu);
+}
+
+/* ipvlan network devices have devices nesting below it and are a special
+ * "super class" of normal network devices; split their locks off into a
+ * separate class since they always nest.
+ */
+static struct lock_class_key ipvlan_netdev_xmit_lock_key;
+static struct lock_class_key ipvlan_netdev_addr_lock_key;
+
+#define IPVLAN_FEATURES \
+	(NETIF_F_SG | NETIF_F_ALL_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
+	 NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_GSO_ROBUST | \
+	 NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GRO | NETIF_F_RXCSUM | \
+	 NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)
+
+#define IPVLAN_STATE_MASK \
+	((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
+
+static void ipvlan_set_lockdep_class_one(struct net_device *dev,
+					 struct netdev_queue *txq,
+					 void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock, &ipvlan_netdev_xmit_lock_key);
+}
+
+static void ipvlan_set_lockdep_class(struct net_device *dev)
+{
+	lockdep_set_class(&dev->addr_list_lock, &ipvlan_netdev_addr_lock_key);
+	netdev_for_each_tx_queue(dev, ipvlan_set_lockdep_class_one, NULL);
+}
+
+static int ipvlan_init(struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	const struct net_device *phy_dev = ipvlan->phy_dev;
+
+	dev->state = (dev->state & ~IPVLAN_STATE_MASK) |
+		     (phy_dev->state & IPVLAN_STATE_MASK);
+	dev->features = phy_dev->features & IPVLAN_FEATURES;
+	dev->features |= NETIF_F_LLTX;
+	dev->gso_max_size = phy_dev->gso_max_size;
+	dev->iflink = phy_dev->ifindex;
+	dev->hard_header_len = phy_dev->hard_header_len;
+
+	ipvlan_set_lockdep_class(dev);
+
+	ipvlan->pcpu_stats = alloc_percpu(struct ipvl_pcpu_stats);
+	if (!ipvlan->pcpu_stats)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void ipvlan_uninit(struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ipvl_port *port = ipvlan->port;
+
+	if (ipvlan->pcpu_stats)
+		free_percpu(ipvlan->pcpu_stats);
+
+	port->count -= 1;
+	if (!port->count)
+		ipvlan_port_destroy(port->dev);
+}
+
+static int ipvlan_open(struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct net_device *phy_dev = ipvlan->phy_dev;
+	struct ipvl_addr *addr;
+
+	if (ipvlan->port->mode == IPVLAN_MODE_L3)
+		dev->flags |= IFF_NOARP;
+	else
+		dev->flags &= ~IFF_NOARP;
+
+	if (ipvlan->ipv6cnt > 0 || ipvlan->ipv4cnt > 0) {
+		list_for_each_entry(addr, &ipvlan->addrs, anode)
+			ipvlan_ht_addr_add(ipvlan, addr);
+	}
+	return dev_uc_add(phy_dev, phy_dev->dev_addr);
+}
+
+static int ipvlan_stop(struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct net_device *phy_dev = ipvlan->phy_dev;
+	struct ipvl_addr *addr;
+
+	dev_uc_unsync(phy_dev, dev);
+	dev_mc_unsync(phy_dev, dev);
+
+	dev_uc_del(phy_dev, phy_dev->dev_addr);
+
+	if (ipvlan->ipv6cnt > 0 || ipvlan->ipv4cnt > 0) {
+		list_for_each_entry(addr, &ipvlan->addrs, anode)
+			ipvlan_ht_addr_del(addr, !dev->dismantle);
+	}
+	return 0;
+}
+
+netdev_tx_t ipvlan_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct ipvl_dev *ipvlan = netdev_priv(dev);
+	int skblen = skb->len;
+	int ret;
+
+	ret = ipvlan_queue_xmit(skb, dev);
+	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
+		struct ipvl_pcpu_stats *pcptr;
+
+		pcptr = this_cpu_ptr(ipvlan->pcpu_stats);
+
+		u64_stats_update_begin(&pcptr->syncp);
+		pcptr->tx_pkts++;
+		pcptr->tx_bytes += skblen;
+		u64_stats_update_end(&pcptr->syncp);
+	} else {
+		this_cpu_inc(ipvlan->pcpu_stats->tx_drps);
+	}
+	return ret;
+}
+
+static netdev_features_t ipvlan_fix_features(struct net_device *dev,
+					     netdev_features_t features)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	return features & (ipvlan->sfeatures | ~IPVLAN_FEATURES);
+}
+
+static void ipvlan_change_rx_flags(struct net_device *dev, int change)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct net_device *phy_dev = ipvlan->phy_dev;
+
+	if (change & IFF_ALLMULTI)
+		dev_set_allmulti(phy_dev, dev->flags & IFF_ALLMULTI? 1 : -1);
+}
+
+static void ipvlan_set_broadcast_mac_filter(struct ipvl_dev *ipvlan, bool set)
+{
+	struct net_device *dev = ipvlan->dev;
+	unsigned int hashbit = ipvlan_mac_hash(dev->broadcast);
+
+	if (set && !test_bit(hashbit, ipvlan->mac_filters))
+		__set_bit(hashbit, ipvlan->mac_filters);
+	else if (!set && test_bit(hashbit, ipvlan->mac_filters))
+		__clear_bit(hashbit, ipvlan->mac_filters);
+}
+
+static void ipvlan_set_multicast_mac_filter(struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) {
+		bitmap_fill(ipvlan->mac_filters, IPVLAN_MAC_FILTER_SIZE);
+	} else {
+		struct netdev_hw_addr *ha;
+		DECLARE_BITMAP(mc_filters, IPVLAN_MAC_FILTER_SIZE);
+
+		bitmap_zero(mc_filters, IPVLAN_MAC_FILTER_SIZE);
+		netdev_for_each_mc_addr(ha, dev)
+			__set_bit(ipvlan_mac_hash(ha->addr), mc_filters);
+
+		bitmap_copy(ipvlan->mac_filters, mc_filters,
+			    IPVLAN_MAC_FILTER_SIZE);
+	}
+	dev_uc_sync(ipvlan->phy_dev, dev);
+	dev_mc_sync(ipvlan->phy_dev, dev);
+}
+
+static struct rtnl_link_stats64 *ipvlan_get_stats64(struct net_device *dev,
+						    struct rtnl_link_stats64 *s)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	if (ipvlan->pcpu_stats) {
+		struct ipvl_pcpu_stats *pcptr;
+		u64 rx_pkts, rx_bytes, rx_mcast, tx_pkts, tx_bytes;
+		u32 rx_errs = 0, tx_drps = 0;
+		u32 strt;
+		int idx;
+
+		for_each_possible_cpu(idx) {
+			pcptr = per_cpu_ptr(ipvlan->pcpu_stats, idx);
+			do {
+				strt= u64_stats_fetch_begin_irq(&pcptr->syncp);
+				rx_pkts = pcptr->rx_pkts;
+				rx_bytes = pcptr->rx_bytes;
+				rx_mcast = pcptr->rx_mcast;
+				tx_pkts = pcptr->tx_pkts;
+				tx_bytes = pcptr->tx_bytes;
+			} while (u64_stats_fetch_retry_irq(&pcptr->syncp,
+							   strt));
+
+			s->rx_packets += rx_pkts;
+			s->rx_bytes += rx_bytes;
+			s->multicast += rx_mcast;
+			s->tx_packets += tx_pkts;
+			s->tx_bytes += tx_bytes;
+
+			/* u32 values are updated without syncp protection. */
+			rx_errs += pcptr->rx_errs;
+			tx_drps += pcptr->tx_drps;
+		}
+		s->rx_errors = rx_errs;
+		s->rx_dropped = rx_errs;
+		s->tx_dropped = tx_drps;
+	}
+	return s;
+}
+
+static int ipvlan_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct net_device *phy_dev = ipvlan->phy_dev;
+
+	return vlan_vid_add(phy_dev, proto, vid);
+}
+
+static int ipvlan_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
+				   u16 vid)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct net_device *phy_dev = ipvlan->phy_dev;
+
+	vlan_vid_del(phy_dev, proto, vid);
+	return 0;
+}
+
+static const struct net_device_ops ipvlan_netdev_ops = {
+	.ndo_init		= ipvlan_init,
+	.ndo_uninit		= ipvlan_uninit,
+	.ndo_open		= ipvlan_open,
+	.ndo_stop		= ipvlan_stop,
+	.ndo_start_xmit		= ipvlan_start_xmit,
+	.ndo_fix_features	= ipvlan_fix_features,
+	.ndo_change_rx_flags	= ipvlan_change_rx_flags,
+	.ndo_set_rx_mode	= ipvlan_set_multicast_mac_filter,
+	.ndo_get_stats64	= ipvlan_get_stats64,
+	.ndo_vlan_rx_add_vid	= ipvlan_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= ipvlan_vlan_rx_kill_vid,
+};
+
+static int ipvlan_hard_header(struct sk_buff *skb, struct net_device *dev,
+			      unsigned short type, const void *daddr,
+			      const void *saddr, unsigned len)
+{
+	const struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct net_device *phy_dev = ipvlan->phy_dev;
+
+	/* TODO Probably use a different field than dev_addr so that the
+	 * mac-address on the virtual device is portable and can be carried
+	 * while the packets use the mac-addr on the physical device.
+	 */
+	return dev_hard_header(skb, phy_dev, type, daddr,
+			       saddr ? : dev->dev_addr, len);
+}
+
+static const struct header_ops ipvlan_header_ops = {
+	.create  	= ipvlan_hard_header,
+	.rebuild	= eth_rebuild_header,
+	.parse		= eth_header_parse,
+	.cache		= eth_header_cache,
+	.cache_update	= eth_header_cache_update,
+};
+
+static int ipvlan_ethtool_get_settings(struct net_device *dev,
+				       struct ethtool_cmd *cmd)
+{
+	const struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	return __ethtool_get_settings(ipvlan->phy_dev, cmd);
+}
+
+static void ipvlan_ethtool_get_drvinfo(struct net_device *dev,
+				       struct ethtool_drvinfo *drvinfo)
+{
+	strlcpy(drvinfo->driver, IPVLAN_DRV, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, IPV_DRV_VER, sizeof(drvinfo->version));
+}
+
+static u32 ipvlan_ethtool_get_msglevel(struct net_device *dev)
+{
+	const struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	return ipvlan->msg_enable;
+}
+
+static void ipvlan_ethtool_set_msglevel(struct net_device *dev, u32 value)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	ipvlan->msg_enable = value;
+}
+
+static const struct ethtool_ops ipvlan_ethtool_ops = {
+	.get_link	= ethtool_op_get_link,
+	.get_settings	= ipvlan_ethtool_get_settings,
+	.get_drvinfo	= ipvlan_ethtool_get_drvinfo,
+	.get_msglevel	= ipvlan_ethtool_get_msglevel,
+	.set_msglevel	= ipvlan_ethtool_set_msglevel,
+};
+
+static int ipvlan_nl_changelink(struct net_device *dev,
+				struct nlattr *tb[], struct nlattr *data[])
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev);
+
+	if (data && data[IFLA_IPVLAN_MODE]) {
+		u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
+
+		ipvlan_set_port_mode(port, nmode);
+	}
+	return 0;
+}
+
+static size_t ipvlan_nl_getsize(const struct net_device *dev)
+{
+	return (0
+		+ nla_total_size(2) /* IFLA_IPVLAN_MODE */
+		);
+}
+
+static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	if (data && data[IFLA_IPVLAN_MODE]) {
+		u16 mode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
+
+		if (mode < IPVLAN_MODE_L2 || mode >= IPVLAN_MODE_MAX)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static int ipvlan_nl_fillinfo(struct sk_buff *skb,
+			      const struct net_device *dev)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev);
+	int ret = -EINVAL;
+
+	if (!port)
+		goto err;
+
+	ret = -EMSGSIZE;
+	if (nla_put_u16(skb, IFLA_IPVLAN_MODE, port->mode))
+		goto err;
+
+	return 0;
+
+err:
+	return ret;
+}
+
+static int ipvlan_link_new(struct net *src_net, struct net_device *dev,
+			   struct nlattr *tb[], struct nlattr *data[])
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ipvl_port *port;
+	struct net_device *phy_dev;
+	int err;
+
+	if (!tb[IFLA_LINK])
+		return -EINVAL;
+
+	phy_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+	if (!phy_dev)
+		return -ENODEV;
+
+	if (ipvlan_dev_slave(phy_dev)) {
+		struct ipvl_dev *tmp = netdev_priv(phy_dev);
+
+		phy_dev = tmp->phy_dev;
+	} else if (!ipvlan_dev_master(phy_dev)) {
+		err = ipvlan_port_create(phy_dev);
+		if (err < 0)
+			return err;
+	}
+
+	port = ipvlan_port_get_rtnl(phy_dev);
+	if (data && data[IFLA_IPVLAN_MODE])
+		port->mode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
+
+	ipvlan->phy_dev = phy_dev;
+	ipvlan->dev = dev;
+	ipvlan->port = port;
+	ipvlan->sfeatures = IPVLAN_FEATURES;
+	INIT_LIST_HEAD(&ipvlan->addrs);
+	ipvlan->ipv4cnt = 0;
+	ipvlan->ipv6cnt = 0;
+
+	/* TODO Probably put random address here to be presented to the
+	 * world but keep using the physical-dev address for the outgoing
+	 * packets.
+	 */
+	memcpy(dev->dev_addr, phy_dev->dev_addr, ETH_ALEN);
+
+	dev->priv_flags |= IFF_IPVLAN_SLAVE;
+
+	port->count += 1;
+	err = register_netdevice(dev);
+	if (err < 0)
+		goto ipvlan_destroy_port;
+
+	err = netdev_upper_dev_link(phy_dev, dev);
+	if (err)
+		goto ipvlan_destroy_port;
+
+	list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans);
+	netif_stacked_transfer_operstate(phy_dev, dev);
+	return 0;
+
+ipvlan_destroy_port:
+	port->count -= 1;
+	if (!port->count)
+		ipvlan_port_destroy(phy_dev);
+
+	return err;
+}
+
+static void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
+{
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct ipvl_addr *addr, *next;
+
+	if (ipvlan->ipv6cnt > 0 || ipvlan->ipv4cnt > 0) {
+		list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) {
+			ipvlan_ht_addr_del(addr, !dev->dismantle);
+			list_del_rcu(&addr->anode);
+		}
+	}
+	list_del_rcu(&ipvlan->pnode);
+	unregister_netdevice_queue(dev, head);
+	netdev_upper_dev_unlink(ipvlan->phy_dev, dev);
+}
+
+static void ipvlan_link_setup(struct net_device *dev)
+{
+	ether_setup(dev);
+
+	dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
+	dev->priv_flags |= IFF_UNICAST_FLT;
+	dev->netdev_ops = &ipvlan_netdev_ops;
+	dev->destructor = free_netdev;
+	dev->header_ops = &ipvlan_header_ops;
+	dev->ethtool_ops = &ipvlan_ethtool_ops;
+	dev->tx_queue_len = 0;
+}
+
+static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] =
+{
+	[IFLA_IPVLAN_MODE] = { .type = NLA_U16 },
+};
+
+static struct rtnl_link_ops ipvlan_link_ops = {
+	.kind		= "ipvlan",
+	.priv_size	= sizeof(struct ipvl_dev),
+
+	.get_size	= ipvlan_nl_getsize,
+	.policy		= ipvlan_nl_policy,
+	.validate	= ipvlan_nl_validate,
+	.fill_info	= ipvlan_nl_fillinfo,
+	.changelink	= ipvlan_nl_changelink,
+	.maxtype	= IFLA_IPVLAN_MAX,
+
+	.setup		= ipvlan_link_setup,
+	.newlink	= ipvlan_link_new,
+	.dellink	= ipvlan_link_delete,
+};
+
+int ipvlan_link_register(struct rtnl_link_ops *ops)
+{
+	return rtnl_link_register(ops);
+}
+
+static int ipvlan_device_event(struct notifier_block *unused,
+			       unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct ipvl_dev *ipvlan, *next;
+	struct ipvl_port *port;
+	LIST_HEAD(lst_kill);
+
+	if (!ipvlan_dev_master(dev))
+		return NOTIFY_DONE;
+
+	port = ipvlan_port_get_rtnl(dev);
+
+	switch (event) {
+	case NETDEV_CHANGE:
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode)
+			netif_stacked_transfer_operstate(ipvlan->phy_dev,
+							 ipvlan->dev);
+		break;
+
+	case NETDEV_UNREGISTER:
+		if (dev->reg_state != NETREG_UNREGISTERING)
+			break;
+
+		list_for_each_entry_safe(ipvlan, next, &port->ipvlans,
+					 pnode)
+			ipvlan->dev->rtnl_link_ops->dellink(ipvlan->dev,
+							    &lst_kill);
+		unregister_netdevice_many(&lst_kill);
+		break;
+
+	case NETDEV_FEAT_CHANGE:
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+			ipvlan->dev->features = dev->features & IPVLAN_FEATURES;
+			ipvlan->dev->gso_max_size = dev->gso_max_size;
+			netdev_features_change(ipvlan->dev);
+		}
+		break;
+
+	case NETDEV_CHANGEMTU:
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode)
+			ipvlan_adjust_mtu(ipvlan, dev);
+		break;
+
+	case NETDEV_PRE_TYPE_CHANGE:
+		/* Forbid underlying device to change its type. */
+		return NOTIFY_BAD;
+	}
+	return NOTIFY_DONE;
+}
+
+static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
+{
+	struct ipvl_addr *addr;
+
+	if (ipvlan_addr_busy(ipvlan, ip6_addr, true)) {
+		netif_err(ipvlan, ifup, ipvlan->dev,
+			  "Failed to add IPv6=%pI6c addr for %s intf\n",
+			  ip6_addr, ipvlan->dev->name);
+		return -EINVAL;
+	}
+	addr = kzalloc(sizeof(struct ipvl_addr), GFP_ATOMIC);
+	if (!addr)
+		return -ENOMEM;
+
+	addr->master = ipvlan;
+	memcpy(&addr->ip6addr, ip6_addr, sizeof(struct in6_addr));
+	addr->atype = IPVL_IPV6;
+	list_add_tail_rcu(&addr->anode, &ipvlan->addrs);
+	ipvlan->ipv6cnt++;
+	ipvlan_ht_addr_add(ipvlan, addr);
+
+	return 0;
+}
+
+static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
+{
+	struct ipvl_addr *addr;
+
+	addr = ipvlan_ht_addr_lookup(ipvlan->port, ip6_addr, true);
+	if (!addr)
+		return;
+
+	ipvlan_ht_addr_del(addr, true);
+	list_del_rcu(&addr->anode);
+	ipvlan->ipv6cnt--;
+	WARN_ON(ipvlan->ipv6cnt < 0);
+	kfree_rcu(addr, rcu);
+
+	return;
+}
+
+static int ipvlan_addr6_event(struct notifier_block *unused,
+			      unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *if6 = (struct inet6_ifaddr *)ptr;
+	struct net_device *dev = (struct net_device *)if6->idev->dev;
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+	if (!ipvlan_dev_slave(dev))
+		return NOTIFY_DONE;
+
+	if (!ipvlan || !ipvlan->port)
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_UP:
+		if (ipvlan_add_addr6(ipvlan, &if6->addr))
+			return NOTIFY_BAD;
+		break;
+
+	case NETDEV_DOWN:
+		ipvlan_del_addr6(ipvlan, &if6->addr);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
+{
+	struct ipvl_addr *addr;
+
+	if (ipvlan_addr_busy(ipvlan, ip4_addr, false)) {
+		netif_err(ipvlan, ifup, ipvlan->dev,
+			  "Failed to add IPv4=%pI4 on %s intf.\n",
+			  ip4_addr, ipvlan->dev->name);
+		return -EINVAL;
+	}
+	addr = kzalloc(sizeof(struct ipvl_addr), GFP_KERNEL);
+	if (!addr)
+		return -ENOMEM;
+
+	addr->master = ipvlan;
+	memcpy(&addr->ip4addr, ip4_addr, sizeof(struct in_addr));
+	addr->atype = IPVL_IPV4;
+	list_add_tail_rcu(&addr->anode, &ipvlan->addrs);
+	ipvlan->ipv4cnt++;
+	ipvlan_ht_addr_add(ipvlan, addr);
+	ipvlan_set_broadcast_mac_filter(ipvlan, true);
+
+	return 0;
+}
+
+static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
+{
+	struct ipvl_addr *addr;
+
+	addr = ipvlan_ht_addr_lookup(ipvlan->port, ip4_addr, false);
+	if (!addr)
+		return;
+
+	ipvlan_ht_addr_del(addr, true);
+	list_del_rcu(&addr->anode);
+	ipvlan->ipv4cnt--;
+	WARN_ON(ipvlan->ipv4cnt < 0);
+	if (!ipvlan->ipv4cnt)
+	    ipvlan_set_broadcast_mac_filter(ipvlan, false);
+	kfree_rcu(addr, rcu);
+
+	return;
+}
+
+static int ipvlan_addr4_event(struct notifier_block *unused,
+			      unsigned long event, void *ptr)
+{
+	struct in_ifaddr *if4 = (struct in_ifaddr *)ptr;
+	struct net_device *dev = (struct net_device *)if4->ifa_dev->dev;
+	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct in_addr ip4_addr;
+
+	if (!ipvlan_dev_slave(dev))
+		return NOTIFY_DONE;
+
+	if (!ipvlan || !ipvlan->port)
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_UP:
+		ip4_addr.s_addr = if4->ifa_address;
+		if (ipvlan_add_addr4(ipvlan, &ip4_addr))
+			return NOTIFY_BAD;
+		break;
+
+	case NETDEV_DOWN:
+		ip4_addr.s_addr = if4->ifa_address;
+		ipvlan_del_addr4(ipvlan, &ip4_addr);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block ipvlan_addr4_notifier_block __read_mostly = {
+	.notifier_call = ipvlan_addr4_event,
+};
+
+static struct notifier_block ipvlan_notifier_block __read_mostly = {
+	.notifier_call = ipvlan_device_event,
+};
+
+static struct notifier_block ipvlan_addr6_notifier_block __read_mostly = {
+	.notifier_call = ipvlan_addr6_event,
+};
+
+static int __init ipvlan_init_module(void)
+{
+	int err;
+
+	ipvlan_init_secret();
+	register_netdevice_notifier(&ipvlan_notifier_block);
+	register_inet6addr_notifier(&ipvlan_addr6_notifier_block);
+	register_inetaddr_notifier(&ipvlan_addr4_notifier_block);
+
+	err = ipvlan_link_register(&ipvlan_link_ops);
+	if (err < 0)
+		goto error;
+
+	return 0;
+error:
+	unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block);
+	unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block);
+	unregister_netdevice_notifier(&ipvlan_notifier_block);
+	return err;
+}
+
+static void __exit ipvlan_cleanup_module(void)
+{
+	rtnl_link_unregister(&ipvlan_link_ops);
+	unregister_netdevice_notifier(&ipvlan_notifier_block);
+	unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block);
+	unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block);
+}
+
+module_init(ipvlan_init_module);
+module_exit(ipvlan_cleanup_module);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>");
+MODULE_DESCRIPTION("Driver for L3 (IPv6/IPv4) based VLANs");
+MODULE_ALIAS_RTNL_LINK("ipvlan");
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5cd50878757..2cb772495f7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1230,6 +1230,8 @@ enum netdev_priv_flags {
 	IFF_LIVE_ADDR_CHANGE		= 1<<20,
 	IFF_MACVLAN			= 1<<21,
 	IFF_XMIT_DST_RELEASE_PERM	= 1<<22,
+	IFF_IPVLAN_MASTER		= 1<<23,
+	IFF_IPVLAN_SLAVE		= 1<<24,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1255,6 +1257,8 @@ enum netdev_priv_flags {
 #define IFF_LIVE_ADDR_CHANGE		IFF_LIVE_ADDR_CHANGE
 #define IFF_MACVLAN			IFF_MACVLAN
 #define IFF_XMIT_DST_RELEASE_PERM	IFF_XMIT_DST_RELEASE_PERM
+#define IFF_IPVLAN_MASTER		IFF_IPVLAN_MASTER
+#define IFF_IPVLAN_SLAVE		IFF_IPVLAN_SLAVE
 
 /**
  *	struct net_device - The DEVICE structure.
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 7072d832501..36bddc23363 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -330,6 +330,21 @@ enum macvlan_macaddr_mode {
 
 #define MACVLAN_FLAG_NOPROMISC	1
 
+/* IPVLAN section */
+enum {
+	IFLA_IPVLAN_UNSPEC,
+	IFLA_IPVLAN_MODE,
+	__IFLA_IPVLAN_MAX
+};
+
+#define IFLA_IPVLAN_MAX (__IFLA_IPVLAN_MAX - 1)
+
+enum ipvlan_mode {
+	IPVLAN_MODE_L2 = 0,
+	IPVLAN_MODE_L3,
+	IPVLAN_MODE_MAX
+};
+
 /* VXLAN section */
 enum {
 	IFLA_VXLAN_UNSPEC,
-- 
cgit v1.2.3-70-g09d2


From 08dcf9fd194cf19d3b282a81cc3539202e768ca4 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Mon, 24 Nov 2014 11:30:26 +0100
Subject: tc_vlan: fix type of tcfv_push_vid

Should be u16. So fix it to kill the sparse warning.

Fixes: c7e2b9689ef8136 "sched: introduce vlan action"
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tc_act/tc_vlan.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h
index c809c1d2cea..93b70ade1ff 100644
--- a/include/net/tc_act/tc_vlan.h
+++ b/include/net/tc_act/tc_vlan.h
@@ -18,7 +18,7 @@
 struct tcf_vlan {
 	struct tcf_common	common;
 	int			tcfv_action;
-	__be16			tcfv_push_vid;
+	u16			tcfv_push_vid;
 	__be16			tcfv_push_proto;
 };
 #define to_vlan(a) \
-- 
cgit v1.2.3-70-g09d2


From 4f0372150b1fbf2167cfe21d2e6eac1933fb36ac Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Mon, 24 Nov 2014 14:24:54 +0100
Subject: tipc: add tipc_netlink.h to uapi Kbuild

tipc_netlink.h is the user-space header for the new netlink api. It
was accidentally left out of the uapi Kbuild list when the api was
added.

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/Kbuild | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 72298b6887a..a1e8175cc48 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -389,6 +389,7 @@ header-y += times.h
 header-y += timex.h
 header-y += tiocl.h
 header-y += tipc_config.h
+header-y += tipc_netlink.h
 header-y += tipc.h
 header-y += toshiba.h
 header-y += tty_flags.h
-- 
cgit v1.2.3-70-g09d2


From cb1410c71e0b6b2eba8c1890645a76ff86169d24 Mon Sep 17 00:00:00 2001
From: Weston Andros Adamson <dros@primarydata.com>
Date: Wed, 12 Nov 2014 12:08:00 -0500
Subject: NFS: fix subtle change in COMMIT behavior

Recent work in the pgio layer made it possible for there to be more than one
request per page. This caused a subtle change in commit behavior, because
write.c:nfs_commit_unstable_pages compares the number of *pages* waiting for
writeback against the number of requests on a commit list to choose when to
send a COMMIT in a non-blocking flush.

This is probably hard to hit in normal operation - you have to be using
rsize/wsize < PAGE_SIZE, or pnfs with lots of boundaries that are not page
aligned to have a noticeable change in behavior.

Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/callback_proc.c |  2 +-
 fs/nfs/inode.c         |  8 ++++----
 fs/nfs/pagelist.c      | 11 ++++++++---
 fs/nfs/write.c         | 17 ++++++++++++-----
 include/linux/nfs_fs.h |  4 ++--
 5 files changed, 27 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 73466b93409..e36a9d78ea4 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -49,7 +49,7 @@ __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
 		goto out_iput;
 	res->size = i_size_read(inode);
 	res->change_attr = delegation->change_attr;
-	if (nfsi->npages != 0)
+	if (nfsi->nrequests != 0)
 		res->change_attr++;
 	res->ctime = inode->i_ctime;
 	res->mtime = inode->i_mtime;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 00689a8a85e..2b48ce58a58 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1149,7 +1149,7 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr
 	if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE)
 			&& (fattr->valid & NFS_ATTR_FATTR_SIZE)
 			&& i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size)
-			&& nfsi->npages == 0) {
+			&& nfsi->nrequests == 0) {
 		i_size_write(inode, nfs_size_to_loff_t(fattr->size));
 		ret |= NFS_INO_INVALID_ATTR;
 	}
@@ -1192,7 +1192,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
 		cur_size = i_size_read(inode);
 		new_isize = nfs_size_to_loff_t(fattr->size);
-		if (cur_size != new_isize && nfsi->npages == 0)
+		if (cur_size != new_isize && nfsi->nrequests == 0)
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
 	}
 
@@ -1619,7 +1619,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		if (new_isize != cur_isize) {
 			/* Do we perhaps have any outstanding writes, or has
 			 * the file grown beyond our last write? */
-			if ((nfsi->npages == 0) || new_isize > cur_isize) {
+			if ((nfsi->nrequests == 0) || new_isize > cur_isize) {
 				i_size_write(inode, new_isize);
 				invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
 				invalid &= ~NFS_INO_REVAL_PAGECACHE;
@@ -1784,7 +1784,7 @@ static void init_once(void *foo)
 	INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
 	INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
 	INIT_LIST_HEAD(&nfsi->commit_info.list);
-	nfsi->npages = 0;
+	nfsi->nrequests = 0;
 	nfsi->commit_info.ncommit = 0;
 	atomic_set(&nfsi->commit_info.rpcs_out, 0);
 	atomic_set(&nfsi->silly_count, 1);
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index ed0db61f854..2b5e769beb1 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -258,6 +258,7 @@ bool nfs_page_group_sync_on_bit(struct nfs_page *req, unsigned int bit)
 static inline void
 nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev)
 {
+	struct inode *inode;
 	WARN_ON_ONCE(prev == req);
 
 	if (!prev) {
@@ -276,12 +277,16 @@ nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev)
 		 * nfs_page_group_destroy is called */
 		kref_get(&req->wb_head->wb_kref);
 
-		/* grab extra ref if head request has extra ref from
-		 * the write/commit path to handle handoff between write
-		 * and commit lists */
+		/* grab extra ref and bump the request count if head request
+		 * has extra ref from the write/commit path to handle handoff
+		 * between write and commit lists. */
 		if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) {
+			inode = page_file_mapping(req->wb_page)->host;
 			set_bit(PG_INODE_REF, &req->wb_flags);
 			kref_get(&req->wb_kref);
+			spin_lock(&inode->i_lock);
+			NFS_I(inode)->nrequests++;
+			spin_unlock(&inode->i_lock);
 		}
 	}
 }
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index f83b02dc916..d489ff3f438 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -670,7 +670,8 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 	nfs_lock_request(req);
 
 	spin_lock(&inode->i_lock);
-	if (!nfsi->npages && NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
+	if (!nfsi->nrequests &&
+	    NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		inode->i_version++;
 	/*
 	 * Swap-space should not get truncated. Hence no need to plug the race
@@ -681,9 +682,11 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 		SetPagePrivate(req->wb_page);
 		set_page_private(req->wb_page, (unsigned long)req);
 	}
-	nfsi->npages++;
+	nfsi->nrequests++;
 	/* this a head request for a page group - mark it as having an
-	 * extra reference so sub groups can follow suit */
+	 * extra reference so sub groups can follow suit.
+	 * This flag also informs pgio layer when to bump nrequests when
+	 * adding subrequests. */
 	WARN_ON(test_and_set_bit(PG_INODE_REF, &req->wb_flags));
 	kref_get(&req->wb_kref);
 	spin_unlock(&inode->i_lock);
@@ -709,7 +712,11 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 			wake_up_page(head->wb_page, PG_private);
 			clear_bit(PG_MAPPED, &head->wb_flags);
 		}
-		nfsi->npages--;
+		nfsi->nrequests--;
+		spin_unlock(&inode->i_lock);
+	} else {
+		spin_lock(&inode->i_lock);
+		nfsi->nrequests--;
 		spin_unlock(&inode->i_lock);
 	}
 
@@ -1735,7 +1742,7 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr
 		/* Don't commit yet if this is a non-blocking flush and there
 		 * are a lot of outstanding writes for this mapping.
 		 */
-		if (nfsi->commit_info.ncommit <= (nfsi->npages >> 1))
+		if (nfsi->commit_info.ncommit <= (nfsi->nrequests >> 1))
 			goto out_mark_dirty;
 
 		/* don't wait for the COMMIT response */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index c72d1ad41ad..6d627b92df5 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -163,7 +163,7 @@ struct nfs_inode {
 	 */
 	__be32			cookieverf[2];
 
-	unsigned long		npages;
+	unsigned long		nrequests;
 	struct nfs_mds_commit_info commit_info;
 
 	/* Open contexts for shared mmap writes */
@@ -520,7 +520,7 @@ extern void nfs_commit_free(struct nfs_commit_data *data);
 static inline int
 nfs_have_writebacks(struct inode *inode)
 {
-	return NFS_I(inode)->npages != 0;
+	return NFS_I(inode)->nrequests != 0;
 }
 
 /*
-- 
cgit v1.2.3-70-g09d2


From 10b89567db51e143c2f0828839332502916d012d Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Mon, 17 Nov 2014 16:58:03 -0500
Subject: lockd: eliminate LOCKD_DEBUG

LOCKD_DEBUG is always the same value as CONFIG_SUNRPC_DEBUG, so we can
just use it instead.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/lockd/svclock.c          | 2 +-
 include/linux/lockd/debug.h | 6 +-----
 2 files changed, 2 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 13db95f5417..56598742dde 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -53,7 +53,7 @@ static const struct rpc_call_ops nlmsvc_grant_ops;
 static LIST_HEAD(nlm_blocked);
 static DEFINE_SPINLOCK(nlm_blocked_lock);
 
-#ifdef LOCKD_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie)
 {
 	/*
diff --git a/include/linux/lockd/debug.h b/include/linux/lockd/debug.h
index 257d3779f2a..0ca8109934e 100644
--- a/include/linux/lockd/debug.h
+++ b/include/linux/lockd/debug.h
@@ -17,12 +17,8 @@
  * Enable lockd debugging.
  * Requires RPC_DEBUG.
  */
-#ifdef RPC_DEBUG
-# define LOCKD_DEBUG		1
-#endif
-
 #undef ifdebug
-#if defined(RPC_DEBUG) && defined(LOCKD_DEBUG)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define ifdebug(flag)		if (unlikely(nlm_debug & NLMDBG_##flag))
 #else
 # define ifdebug(flag)		if (0)
-- 
cgit v1.2.3-70-g09d2


From b53a2340d0d30468b7315992ba77fe188c3bc5c8 Mon Sep 17 00:00:00 2001
From: Pantelis Antoniou <pantelis.antoniou@konsulko.com>
Date: Tue, 28 Oct 2014 22:33:53 +0200
Subject: of/reconfig: Add of_reconfig_get_state_change() of notifier helper.

Introduce of_reconfig_get_state_change() which allows an of notifier
to query about device state changes.

Signed-off-by: Pantelis Antoniou <pantelis.antoniou@konsulko.com>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 drivers/of/dynamic.c | 96 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/of.h   |  7 ++++
 2 files changed, 103 insertions(+)

(limited to 'include')

diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index 661ad2f5c00..6659c39ab3a 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -85,6 +85,102 @@ int of_reconfig_notify(unsigned long action, void *p)
 	return notifier_to_errno(rc);
 }
 
+/*
+ * of_reconfig_get_state_change()	- Returns new state of device
+ * @action	- action of the of notifier
+ * @arg		- argument of the of notifier
+ *
+ * Returns the new state of a device based on the notifier used.
+ * Returns 0 on device going from enabled to disabled, 1 on device
+ * going from disabled to enabled and -1 on no change.
+ */
+int of_reconfig_get_state_change(unsigned long action, void *arg)
+{
+	struct device_node *dn;
+	struct property *prop, *old_prop;
+	struct of_prop_reconfig *pr;
+	int is_status, status_state, old_status_state, prev_state, new_state;
+
+	/* figure out if a device should be created or destroyed */
+	dn = NULL;
+	prop = old_prop = NULL;
+	switch (action) {
+	case OF_RECONFIG_ATTACH_NODE:
+	case OF_RECONFIG_DETACH_NODE:
+		dn = arg;
+		prop = of_find_property(dn, "status", NULL);
+		break;
+	case OF_RECONFIG_ADD_PROPERTY:
+	case OF_RECONFIG_REMOVE_PROPERTY:
+		pr = arg;
+		dn = pr->dn;
+		prop = pr->prop;
+		break;
+	case OF_RECONFIG_UPDATE_PROPERTY:
+		pr = arg;
+		dn = pr->dn;
+		prop = pr->prop;
+		old_prop = pr->old_prop;
+		break;
+	default:
+		return OF_RECONFIG_NO_CHANGE;
+	}
+
+	is_status = 0;
+	status_state = -1;
+	old_status_state = -1;
+	prev_state = -1;
+	new_state = -1;
+
+	if (prop && !strcmp(prop->name, "status")) {
+		is_status = 1;
+		status_state = !strcmp(prop->value, "okay") ||
+			       !strcmp(prop->value, "ok");
+		if (old_prop)
+			old_status_state = !strcmp(old_prop->value, "okay") ||
+					   !strcmp(old_prop->value, "ok");
+	}
+
+	switch (action) {
+	case OF_RECONFIG_ATTACH_NODE:
+		prev_state = 0;
+		/* -1 & 0 status either missing or okay */
+		new_state = status_state != 0;
+		break;
+	case OF_RECONFIG_DETACH_NODE:
+		/* -1 & 0 status either missing or okay */
+		prev_state = status_state != 0;
+		new_state = 0;
+		break;
+	case OF_RECONFIG_ADD_PROPERTY:
+		if (is_status) {
+			/* no status property -> enabled (legacy) */
+			prev_state = 1;
+			new_state = status_state;
+		}
+		break;
+	case OF_RECONFIG_REMOVE_PROPERTY:
+		if (is_status) {
+			prev_state = status_state;
+			/* no status property -> enabled (legacy) */
+			new_state = 1;
+		}
+		break;
+	case OF_RECONFIG_UPDATE_PROPERTY:
+		if (is_status) {
+			prev_state = old_status_state != 0;
+			new_state = status_state != 0;
+		}
+		break;
+	}
+
+	if (prev_state == new_state)
+		return OF_RECONFIG_NO_CHANGE;
+
+	return new_state ? OF_RECONFIG_CHANGE_ADD : OF_RECONFIG_CHANGE_REMOVE;
+}
+EXPORT_SYMBOL_GPL(of_reconfig_get_state_change);
+
 int of_property_notify(int action, struct device_node *np,
 		       struct property *prop, struct property *oldprop)
 {
diff --git a/include/linux/of.h b/include/linux/of.h
index 27635c89d8c..8e3a264c869 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -327,6 +327,7 @@ struct of_prop_reconfig {
 extern int of_reconfig_notifier_register(struct notifier_block *);
 extern int of_reconfig_notifier_unregister(struct notifier_block *);
 extern int of_reconfig_notify(unsigned long, void *);
+extern int of_reconfig_get_state_change(unsigned long action, void *arg);
 
 extern int of_attach_node(struct device_node *);
 extern int of_detach_node(struct device_node *);
@@ -887,6 +888,12 @@ struct of_changeset {
 	struct list_head entries;
 };
 
+enum of_reconfig_change {
+	OF_RECONFIG_NO_CHANGE = 0,
+	OF_RECONFIG_CHANGE_ADD,
+	OF_RECONFIG_CHANGE_REMOVE,
+};
+
 #ifdef CONFIG_OF_DYNAMIC
 extern void of_changeset_init(struct of_changeset *ocs);
 extern void of_changeset_destroy(struct of_changeset *ocs);
-- 
cgit v1.2.3-70-g09d2


From f6892d193fb9d694a1b50550649ba6e82f8abec1 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@linaro.org>
Date: Fri, 21 Nov 2014 15:14:58 +0000
Subject: of/reconfig: Add empty stubs for the of_reconfig methods

To simplify subsystem setup code, make empty stubs for the
of_reconfig_*() methods. This is particularly useful for registering and
unregistering the notifiers so that it doesn't impact the flow of the
subsystem setup code.

Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 include/linux/of.h | 29 +++++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/of.h b/include/linux/of.h
index 8e3a264c869..b59ee21933a 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -324,11 +324,6 @@ struct of_prop_reconfig {
 	struct property		*old_prop;
 };
 
-extern int of_reconfig_notifier_register(struct notifier_block *);
-extern int of_reconfig_notifier_unregister(struct notifier_block *);
-extern int of_reconfig_notify(unsigned long, void *);
-extern int of_reconfig_get_state_change(unsigned long action, void *arg);
-
 extern int of_attach_node(struct device_node *);
 extern int of_detach_node(struct device_node *);
 
@@ -895,6 +890,11 @@ enum of_reconfig_change {
 };
 
 #ifdef CONFIG_OF_DYNAMIC
+extern int of_reconfig_notifier_register(struct notifier_block *);
+extern int of_reconfig_notifier_unregister(struct notifier_block *);
+extern int of_reconfig_notify(unsigned long, void *);
+extern int of_reconfig_get_state_change(unsigned long action, void *arg);
+
 extern void of_changeset_init(struct of_changeset *ocs);
 extern void of_changeset_destroy(struct of_changeset *ocs);
 extern int of_changeset_apply(struct of_changeset *ocs);
@@ -932,7 +932,24 @@ static inline int of_changeset_update_property(struct of_changeset *ocs,
 {
 	return of_changeset_action(ocs, OF_RECONFIG_UPDATE_PROPERTY, np, prop);
 }
-#endif
+#else /* CONFIG_OF_DYNAMIC */
+static inline int of_reconfig_notifier_register(struct notifier_block *nb)
+{
+	return -EINVAL;
+}
+static inline int of_reconfig_notifier_unregister(struct notifier_block *nb)
+{
+	return -EINVAL;
+}
+static inline int of_reconfig_notify(unsigned long action, void *arg)
+{
+	return -EINVAL;
+}
+static inline int of_reconfig_get_state_change(unsigned long action, void *arg)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_OF_DYNAMIC */
 
 /* CONFIG_OF_RESOLVE api */
 extern int of_resolve_phandles(struct device_node *tree);
-- 
cgit v1.2.3-70-g09d2


From f5242e5a883bf1c1aba6bfd87b85e7dda0e62191 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@linaro.org>
Date: Mon, 24 Nov 2014 17:58:01 +0000
Subject: of/reconfig: Always use the same structure for notifiers

The OF_RECONFIG notifier callback uses a different structure depending
on whether it is a node change or a property change. This is silly, and
not very safe. Rework the code to use the same data structure regardless
of the type of notifier.

Signed-off-by: Grant Likely <grant.likely@linaro.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Pantelis Antoniou <pantelis.antoniou@konsulko.com>
Cc: <linuxppc-dev@lists.ozlabs.org>
---
 arch/powerpc/mm/numa.c                          |  3 +-
 arch/powerpc/platforms/pseries/hotplug-cpu.c    |  7 +++--
 arch/powerpc/platforms/pseries/hotplug-memory.c | 15 +++++----
 arch/powerpc/platforms/pseries/iommu.c          |  5 +--
 arch/powerpc/platforms/pseries/setup.c          |  5 +--
 drivers/crypto/nx/nx-842.c                      |  4 +--
 drivers/of/dynamic.c                            | 41 +++++++++++++------------
 include/linux/of.h                              | 23 ++++++++------
 8 files changed, 54 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index b9d1dfdbe5b..9fe6002c1d5 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1711,12 +1711,11 @@ static void stage_topology_update(int core_id)
 static int dt_update_callback(struct notifier_block *nb,
 				unsigned long action, void *data)
 {
-	struct of_prop_reconfig *update;
+	struct of_reconfig_data *update = data;
 	int rc = NOTIFY_DONE;
 
 	switch (action) {
 	case OF_RECONFIG_UPDATE_PROPERTY:
-		update = (struct of_prop_reconfig *)data;
 		if (!of_prop_cmp(update->dn->type, "cpu") &&
 		    !of_prop_cmp(update->prop->name, "ibm,associativity")) {
 			u32 core_id;
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 5c375f93c66..f30cf4d136a 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -340,16 +340,17 @@ static void pseries_remove_processor(struct device_node *np)
 }
 
 static int pseries_smp_notifier(struct notifier_block *nb,
-				unsigned long action, void *node)
+				unsigned long action, void *data)
 {
+	struct of_reconfig_data *rd = data;
 	int err = 0;
 
 	switch (action) {
 	case OF_RECONFIG_ATTACH_NODE:
-		err = pseries_add_processor(node);
+		err = pseries_add_processor(rd->dn);
 		break;
 	case OF_RECONFIG_DETACH_NODE:
-		pseries_remove_processor(node);
+		pseries_remove_processor(rd->dn);
 		break;
 	}
 	return notifier_from_errno(err);
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 3c4c0dcd90d..1bbb78fab53 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -183,7 +183,7 @@ static int pseries_add_mem_node(struct device_node *np)
 	return (ret < 0) ? -EINVAL : 0;
 }
 
-static int pseries_update_drconf_memory(struct of_prop_reconfig *pr)
+static int pseries_update_drconf_memory(struct of_reconfig_data *pr)
 {
 	struct of_drconf_cell *new_drmem, *old_drmem;
 	unsigned long memblock_size;
@@ -232,22 +232,21 @@ static int pseries_update_drconf_memory(struct of_prop_reconfig *pr)
 }
 
 static int pseries_memory_notifier(struct notifier_block *nb,
-				   unsigned long action, void *node)
+				   unsigned long action, void *data)
 {
-	struct of_prop_reconfig *pr;
+	struct of_reconfig_data *rd = data;
 	int err = 0;
 
 	switch (action) {
 	case OF_RECONFIG_ATTACH_NODE:
-		err = pseries_add_mem_node(node);
+		err = pseries_add_mem_node(rd->dn);
 		break;
 	case OF_RECONFIG_DETACH_NODE:
-		err = pseries_remove_mem_node(node);
+		err = pseries_remove_mem_node(rd->dn);
 		break;
 	case OF_RECONFIG_UPDATE_PROPERTY:
-		pr = (struct of_prop_reconfig *)node;
-		if (!strcmp(pr->prop->name, "ibm,dynamic-memory"))
-			err = pseries_update_drconf_memory(pr);
+		if (!strcmp(rd->prop->name, "ibm,dynamic-memory"))
+			err = pseries_update_drconf_memory(rd);
 		break;
 	}
 	return notifier_from_errno(err);
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index e32e00976a9..3e5bfdafee6 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -1251,10 +1251,11 @@ static struct notifier_block iommu_mem_nb = {
 	.notifier_call = iommu_mem_notifier,
 };
 
-static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *node)
+static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *data)
 {
 	int err = NOTIFY_OK;
-	struct device_node *np = node;
+	struct of_reconfig_data *rd = data;
+	struct device_node *np = rd->dn;
 	struct pci_dn *pci = PCI_DN(np);
 	struct direct_window *window;
 
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 125c589eeef..ed8a90022a3 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -251,9 +251,10 @@ static void __init pseries_discover_pic(void)
 	       " interrupt-controller\n");
 }
 
-static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *node)
+static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *data)
 {
-	struct device_node *np = node;
+	struct of_reconfig_data *rd = data;
+	struct device_node *np = rd->dn;
 	struct pci_dn *pci = NULL;
 	int err = NOTIFY_OK;
 
diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c
index 061407d5952..887196e9b50 100644
--- a/drivers/crypto/nx/nx-842.c
+++ b/drivers/crypto/nx/nx-842.c
@@ -1009,9 +1009,9 @@ error_out:
  *		notifier_to_errno() to decode this value
  */
 static int nx842_OF_notifier(struct notifier_block *np, unsigned long action,
-			     void *update)
+			     void *data)
 {
-	struct of_prop_reconfig *upd = update;
+	struct of_reconfig_data *upd = data;
 	struct nx842_devdata *local_devdata;
 	struct device_node *node = NULL;
 
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index cc106529dca..3351ef40812 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -87,18 +87,17 @@ const char *action_names[] = {
 };
 #endif
 
-int of_reconfig_notify(unsigned long action, void *p)
+int of_reconfig_notify(unsigned long action, struct of_reconfig_data *p)
 {
 	int rc;
 #ifdef DEBUG
-	struct device_node *dn = p;
-	struct of_prop_reconfig *pr = p;
+	struct of_reconfig_data *pr = p;
 
 	switch (action) {
 	case OF_RECONFIG_ATTACH_NODE:
 	case OF_RECONFIG_DETACH_NODE:
 		pr_debug("of/notify %-15s %s\n", action_names[action],
-			dn->full_name);
+			pr->dn->full_name);
 		break;
 	case OF_RECONFIG_ADD_PROPERTY:
 	case OF_RECONFIG_REMOVE_PROPERTY:
@@ -122,31 +121,22 @@ int of_reconfig_notify(unsigned long action, void *p)
  * Returns 0 on device going from enabled to disabled, 1 on device
  * going from disabled to enabled and -1 on no change.
  */
-int of_reconfig_get_state_change(unsigned long action, void *arg)
+int of_reconfig_get_state_change(unsigned long action, struct of_reconfig_data *pr)
 {
-	struct device_node *dn;
-	struct property *prop, *old_prop;
-	struct of_prop_reconfig *pr;
+	struct property *prop, *old_prop = NULL;
 	int is_status, status_state, old_status_state, prev_state, new_state;
 
 	/* figure out if a device should be created or destroyed */
-	dn = NULL;
-	prop = old_prop = NULL;
 	switch (action) {
 	case OF_RECONFIG_ATTACH_NODE:
 	case OF_RECONFIG_DETACH_NODE:
-		dn = arg;
-		prop = of_find_property(dn, "status", NULL);
+		prop = of_find_property(pr->dn, "status", NULL);
 		break;
 	case OF_RECONFIG_ADD_PROPERTY:
 	case OF_RECONFIG_REMOVE_PROPERTY:
-		pr = arg;
-		dn = pr->dn;
 		prop = pr->prop;
 		break;
 	case OF_RECONFIG_UPDATE_PROPERTY:
-		pr = arg;
-		dn = pr->dn;
 		prop = pr->prop;
 		old_prop = pr->old_prop;
 		break;
@@ -212,7 +202,7 @@ EXPORT_SYMBOL_GPL(of_reconfig_get_state_change);
 int of_property_notify(int action, struct device_node *np,
 		       struct property *prop, struct property *oldprop)
 {
-	struct of_prop_reconfig pr;
+	struct of_reconfig_data pr;
 
 	/* only call notifiers if the node is attached */
 	if (!of_node_is_attached(np))
@@ -250,8 +240,12 @@ void __of_attach_node(struct device_node *np)
  */
 int of_attach_node(struct device_node *np)
 {
+	struct of_reconfig_data rd;
 	unsigned long flags;
 
+	memset(&rd, 0, sizeof(rd));
+	rd.dn = np;
+
 	mutex_lock(&of_mutex);
 	raw_spin_lock_irqsave(&devtree_lock, flags);
 	__of_attach_node(np);
@@ -260,7 +254,7 @@ int of_attach_node(struct device_node *np)
 	__of_attach_node_sysfs(np);
 	mutex_unlock(&of_mutex);
 
-	of_reconfig_notify(OF_RECONFIG_ATTACH_NODE, np);
+	of_reconfig_notify(OF_RECONFIG_ATTACH_NODE, &rd);
 
 	return 0;
 }
@@ -298,9 +292,13 @@ void __of_detach_node(struct device_node *np)
  */
 int of_detach_node(struct device_node *np)
 {
+	struct of_reconfig_data rd;
 	unsigned long flags;
 	int rc = 0;
 
+	memset(&rd, 0, sizeof(rd));
+	rd.dn = np;
+
 	mutex_lock(&of_mutex);
 	raw_spin_lock_irqsave(&devtree_lock, flags);
 	__of_detach_node(np);
@@ -309,7 +307,7 @@ int of_detach_node(struct device_node *np)
 	__of_detach_node_sysfs(np);
 	mutex_unlock(&of_mutex);
 
-	of_reconfig_notify(OF_RECONFIG_DETACH_NODE, np);
+	of_reconfig_notify(OF_RECONFIG_DETACH_NODE, &rd);
 
 	return rc;
 }
@@ -505,6 +503,7 @@ static void __of_changeset_entry_invert(struct of_changeset_entry *ce,
 
 static void __of_changeset_entry_notify(struct of_changeset_entry *ce, bool revert)
 {
+	struct of_reconfig_data rd;
 	struct of_changeset_entry ce_inverted;
 	int ret;
 
@@ -516,7 +515,9 @@ static void __of_changeset_entry_notify(struct of_changeset_entry *ce, bool reve
 	switch (ce->action) {
 	case OF_RECONFIG_ATTACH_NODE:
 	case OF_RECONFIG_DETACH_NODE:
-		ret = of_reconfig_notify(ce->action, ce->np);
+		memset(&rd, 0, sizeof(rd));
+		rd.dn = ce->np;
+		ret = of_reconfig_notify(ce->action, &rd);
 		break;
 	case OF_RECONFIG_ADD_PROPERTY:
 	case OF_RECONFIG_REMOVE_PROPERTY:
diff --git a/include/linux/of.h b/include/linux/of.h
index b59ee21933a..fe1dec87fd6 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -73,6 +73,12 @@ struct of_phandle_args {
 	uint32_t args[MAX_PHANDLE_ARGS];
 };
 
+struct of_reconfig_data {
+	struct device_node	*dn;
+	struct property		*prop;
+	struct property		*old_prop;
+};
+
 /* initialize a node */
 extern struct kobj_type of_node_ktype;
 static inline void of_node_init(struct device_node *node)
@@ -318,12 +324,6 @@ extern int of_update_property(struct device_node *np, struct property *newprop);
 #define OF_RECONFIG_REMOVE_PROPERTY	0x0004
 #define OF_RECONFIG_UPDATE_PROPERTY	0x0005
 
-struct of_prop_reconfig {
-	struct device_node	*dn;
-	struct property		*prop;
-	struct property		*old_prop;
-};
-
 extern int of_attach_node(struct device_node *);
 extern int of_detach_node(struct device_node *);
 
@@ -892,8 +892,9 @@ enum of_reconfig_change {
 #ifdef CONFIG_OF_DYNAMIC
 extern int of_reconfig_notifier_register(struct notifier_block *);
 extern int of_reconfig_notifier_unregister(struct notifier_block *);
-extern int of_reconfig_notify(unsigned long, void *);
-extern int of_reconfig_get_state_change(unsigned long action, void *arg);
+extern int of_reconfig_notify(unsigned long, struct of_reconfig_data *rd);
+extern int of_reconfig_get_state_change(unsigned long action,
+					struct of_reconfig_data *arg);
 
 extern void of_changeset_init(struct of_changeset *ocs);
 extern void of_changeset_destroy(struct of_changeset *ocs);
@@ -941,11 +942,13 @@ static inline int of_reconfig_notifier_unregister(struct notifier_block *nb)
 {
 	return -EINVAL;
 }
-static inline int of_reconfig_notify(unsigned long action, void *arg)
+static inline int of_reconfig_notify(unsigned long action,
+				     struct of_reconfig_data *arg)
 {
 	return -EINVAL;
 }
-static inline int of_reconfig_get_state_change(unsigned long action, void *arg)
+static inline int of_reconfig_get_state_change(unsigned long action,
+						struct of_reconfig_data *arg)
 {
 	return -EINVAL;
 }
-- 
cgit v1.2.3-70-g09d2


From 801d728c10db4b28e01590b46bf1f0df930760cc Mon Sep 17 00:00:00 2001
From: Pantelis Antoniou <pantelis.antoniou@konsulko.com>
Date: Tue, 28 Oct 2014 22:36:01 +0200
Subject: of/reconfig: Add OF_DYNAMIC notifier for platform_bus_type

Add OF notifier handler needed for creating/destroying platform devices
according to dynamic runtime changes in the DT live tree.

Signed-off-by: Pantelis Antoniou <pantelis.antoniou@konsulko.com>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 drivers/base/platform.c     |  1 +
 drivers/of/platform.c       | 55 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/of_platform.h |  6 +++++
 3 files changed, 62 insertions(+)

(limited to 'include')

diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index b2afc29403f..233ececd15a 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -1006,6 +1006,7 @@ int __init platform_bus_init(void)
 	error =  bus_register(&platform_bus_type);
 	if (error)
 		device_unregister(&platform_bus);
+	of_platform_register_reconfig_notifier();
 	return error;
 }
 
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 656cccf0e68..cd87a36495b 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -550,4 +550,59 @@ void of_platform_depopulate(struct device *parent)
 }
 EXPORT_SYMBOL_GPL(of_platform_depopulate);
 
+#ifdef CONFIG_OF_DYNAMIC
+static int of_platform_notify(struct notifier_block *nb,
+				unsigned long action, void *arg)
+{
+	struct of_reconfig_data *rd = arg;
+	struct platform_device *pdev_parent, *pdev;
+	bool children_left;
+
+	switch (of_reconfig_get_state_change(action, rd)) {
+	case OF_RECONFIG_CHANGE_ADD:
+		/* verify that the parent is a bus */
+		if (!of_node_check_flag(rd->dn->parent, OF_POPULATED_BUS))
+			return NOTIFY_OK;	/* not for us */
+
+		/* pdev_parent may be NULL when no bus platform device */
+		pdev_parent = of_find_device_by_node(rd->dn->parent);
+		pdev = of_platform_device_create(rd->dn, NULL,
+				pdev_parent ? &pdev_parent->dev : NULL);
+		of_dev_put(pdev_parent);
+
+		if (pdev == NULL) {
+			pr_err("%s: failed to create for '%s'\n",
+					__func__, rd->dn->full_name);
+			/* of_platform_device_create tosses the error code */
+			return notifier_from_errno(-EINVAL);
+		}
+		break;
+
+	case OF_RECONFIG_CHANGE_REMOVE:
+		/* find our device by node */
+		pdev = of_find_device_by_node(rd->dn);
+		if (pdev == NULL)
+			return NOTIFY_OK;	/* no? not meant for us */
+
+		/* unregister takes one ref away */
+		of_platform_device_destroy(&pdev->dev, &children_left);
+
+		/* and put the reference of the find */
+		of_dev_put(pdev);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block platform_of_notifier = {
+	.notifier_call = of_platform_notify,
+};
+
+void of_platform_register_reconfig_notifier(void)
+{
+	WARN_ON(of_reconfig_notifier_register(&platform_of_notifier));
+}
+#endif /* CONFIG_OF_DYNAMIC */
+
 #endif /* CONFIG_OF_ADDRESS */
diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index c2b0627a231..8a860f096c3 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -84,4 +84,10 @@ static inline int of_platform_populate(struct device_node *root,
 static inline void of_platform_depopulate(struct device *parent) { }
 #endif
 
+#ifdef CONFIG_OF_DYNAMIC
+extern void of_platform_register_reconfig_notifier(void);
+#else
+static inline void of_platform_register_reconfig_notifier(void) { }
+#endif
+
 #endif	/* _LINUX_OF_PLATFORM_H */
-- 
cgit v1.2.3-70-g09d2


From 7518b5890d8ac366faa2326ce2356ef6392ce63d Mon Sep 17 00:00:00 2001
From: Pantelis Antoniou <pantelis.antoniou@konsulko.com>
Date: Tue, 28 Oct 2014 22:35:58 +0200
Subject: of/overlay: Introduce DT overlay support

Overlays are a method to dynamically modify part of the kernel's
device tree with dynamically loaded data. Add the core functionality to
parse, apply and remove an overlay changeset. The core functionality
takes care of managing the overlay data format and performing the add
and remove. Drivers are expected to use the overlay functionality to
support custom expansion busses commonly found on consumer development
boards like the BeagleBone or Raspberry Pi.

The overlay code uses CONFIG_OF_DYNAMIC changesets to perform the low
level work of modifying the devicetree.

Documentation about internal and APIs is provided in
	Documentation/devicetree/overlay-notes.txt

v2:
- Switch from __of_node_alloc() to __of_node_dup()
- Documentation fixups
- Remove 2-pass processing of properties
- Remove separate ov_lock; just use the DT mutex.
v1:
- Drop delete capability using '-' prefix. The '-' prefixed names
are valid properties and nodes and there is no need for it just yet.
- Do not update special properties - name & phandle ones.
- Change order of node attachment, so that the special property update
works.

Signed-off-by: Pantelis Antoniou <pantelis.antoniou@konsulko.com>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 Documentation/devicetree/overlay-notes.txt | 133 +++++++
 drivers/of/Kconfig                         |   7 +
 drivers/of/Makefile                        |   1 +
 drivers/of/overlay.c                       | 562 +++++++++++++++++++++++++++++
 include/linux/of.h                         |  31 ++
 5 files changed, 734 insertions(+)
 create mode 100644 Documentation/devicetree/overlay-notes.txt
 create mode 100644 drivers/of/overlay.c

(limited to 'include')

diff --git a/Documentation/devicetree/overlay-notes.txt b/Documentation/devicetree/overlay-notes.txt
new file mode 100644
index 00000000000..30ae758e3ee
--- /dev/null
+++ b/Documentation/devicetree/overlay-notes.txt
@@ -0,0 +1,133 @@
+Device Tree Overlay Notes
+-------------------------
+
+This document describes the implementation of the in-kernel
+device tree overlay functionality residing in drivers/of/overlay.c and is a
+companion document to Documentation/devicetree/dt-object-internal.txt[1] &
+Documentation/devicetree/dynamic-resolution-notes.txt[2]
+
+How overlays work
+-----------------
+
+A Device Tree's overlay purpose is to modify the kernel's live tree, and
+have the modification affecting the state of the the kernel in a way that
+is reflecting the changes.
+Since the kernel mainly deals with devices, any new device node that result
+in an active device should have it created while if the device node is either
+disabled or removed all together, the affected device should be deregistered.
+
+Lets take an example where we have a foo board with the following base tree
+which is taken from [1].
+
+---- foo.dts -----------------------------------------------------------------
+	/* FOO platform */
+	/ {
+		compatible = "corp,foo";
+
+		/* shared resources */
+		res: res {
+		};
+
+		/* On chip peripherals */
+		ocp: ocp {
+			/* peripherals that are always instantiated */
+			peripheral1 { ... };
+		}
+	};
+---- foo.dts -----------------------------------------------------------------
+
+The overlay bar.dts, when loaded (and resolved as described in [2]) should
+
+---- bar.dts -----------------------------------------------------------------
+/plugin/;	/* allow undefined label references and record them */
+/ {
+	....	/* various properties for loader use; i.e. part id etc. */
+	fragment@0 {
+		target = <&ocp>;
+		__overlay__ {
+			/* bar peripheral */
+			bar {
+				compatible = "corp,bar";
+				... /* various properties and child nodes */
+			}
+		};
+	};
+};
+---- bar.dts -----------------------------------------------------------------
+
+result in foo+bar.dts
+
+---- foo+bar.dts -------------------------------------------------------------
+	/* FOO platform + bar peripheral */
+	/ {
+		compatible = "corp,foo";
+
+		/* shared resources */
+		res: res {
+		};
+
+		/* On chip peripherals */
+		ocp: ocp {
+			/* peripherals that are always instantiated */
+			peripheral1 { ... };
+
+			/* bar peripheral */
+			bar {
+				compatible = "corp,bar";
+				... /* various properties and child nodes */
+			}
+		}
+	};
+---- foo+bar.dts -------------------------------------------------------------
+
+As a result of the the overlay, a new device node (bar) has been created
+so a bar platform device will be registered and if a matching device driver
+is loaded the device will be created as expected.
+
+Overlay in-kernel API
+--------------------------------
+
+The API is quite easy to use.
+
+1. Call of_overlay_create() to create and apply an overlay. The return value
+is a cookie identifying this overlay.
+
+2. Call of_overlay_destroy() to remove and cleanup the overlay previously
+created via the call to of_overlay_create(). Removal of an overlay that
+is stacked by another will not be permitted.
+
+Finally, if you need to remove all overlays in one-go, just call
+of_overlay_destroy_all() which will remove every single one in the correct
+order.
+
+Overlay DTS Format
+------------------
+
+The DTS of an overlay should have the following format:
+
+{
+	/* ignored properties by the overlay */
+
+	fragment@0 {	/* first child node */
+
+		target=<phandle>;	/* phandle target of the overlay */
+	or
+		target-path="/path";	/* target path of the overlay */
+
+		__overlay__ {
+			property-a;	/* add property-a to the target */
+			node-a {	/* add to an existing, or create a node-a */
+				...
+			};
+		};
+	}
+	fragment@1 {	/* second child node */
+		...
+	};
+	/* more fragments follow */
+}
+
+Using the non-phandle based target method allows one to use a base DT which does
+not contain a __symbols__ node, i.e. it was not compiled with the -@ option.
+The __symbols__ node is only required for the target=<phandle> method, since it
+contains the information required to map from a phandle to a tree location.
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index fbe8f8d418f..18b2e2539f8 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -84,4 +84,11 @@ config OF_RESERVED_MEM
 config OF_RESOLVE
 	bool
 
+config OF_OVERLAY
+	bool
+	depends on OF
+	select OF_DYNAMIC
+	select OF_DEVICE
+	select OF_RESOLVE
+
 endmenu # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index d90553fcd37..7563f36c71d 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_OF_PCI_IRQ)  += of_pci_irq.o
 obj-$(CONFIG_OF_MTD)	+= of_mtd.o
 obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o
 obj-$(CONFIG_OF_RESOLVE)  += resolver.o
+obj-$(CONFIG_OF_OVERLAY) += overlay.o
 
 CFLAGS_fdt.o = -I$(src)/../../scripts/dtc/libfdt
 CFLAGS_fdt_address.o = -I$(src)/../../scripts/dtc/libfdt
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
new file mode 100644
index 00000000000..ea63fbd228e
--- /dev/null
+++ b/drivers/of/overlay.c
@@ -0,0 +1,562 @@
+/*
+ * Functions for working with device tree overlays
+ *
+ * Copyright (C) 2012 Pantelis Antoniou <panto@antoniou-consulting.com>
+ * Copyright (C) 2012 Texas Instruments Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+#undef DEBUG
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+
+#include "of_private.h"
+
+/**
+ * struct of_overlay_info - Holds a single overlay info
+ * @target:	target of the overlay operation
+ * @overlay:	pointer to the overlay contents node
+ *
+ * Holds a single overlay state, including all the overlay logs &
+ * records.
+ */
+struct of_overlay_info {
+	struct device_node *target;
+	struct device_node *overlay;
+};
+
+/**
+ * struct of_overlay - Holds a complete overlay transaction
+ * @node:	List on which we are located
+ * @count:	Count of ovinfo structures
+ * @ovinfo_tab:	Overlay info table (count sized)
+ * @cset:	Changeset to be used
+ *
+ * Holds a complete overlay transaction
+ */
+struct of_overlay {
+	int id;
+	struct list_head node;
+	int count;
+	struct of_overlay_info *ovinfo_tab;
+	struct of_changeset cset;
+};
+
+static int of_overlay_apply_one(struct of_overlay *ov,
+		struct device_node *target, const struct device_node *overlay);
+
+static int of_overlay_apply_single_property(struct of_overlay *ov,
+		struct device_node *target, struct property *prop)
+{
+	struct property *propn, *tprop;
+
+	/* NOTE: Multiple changes of single properties not supported */
+	tprop = of_find_property(target, prop->name, NULL);
+
+	/* special properties are not meant to be updated (silent NOP) */
+	if (of_prop_cmp(prop->name, "name") == 0 ||
+	    of_prop_cmp(prop->name, "phandle") == 0 ||
+	    of_prop_cmp(prop->name, "linux,phandle") == 0)
+		return 0;
+
+	propn = __of_prop_dup(prop, GFP_KERNEL);
+	if (propn == NULL)
+		return -ENOMEM;
+
+	/* not found? add */
+	if (tprop == NULL)
+		return of_changeset_add_property(&ov->cset, target, propn);
+
+	/* found? update */
+	return of_changeset_update_property(&ov->cset, target, propn);
+}
+
+static int of_overlay_apply_single_device_node(struct of_overlay *ov,
+		struct device_node *target, struct device_node *child)
+{
+	const char *cname;
+	struct device_node *tchild, *grandchild;
+	int ret = 0;
+
+	cname = kbasename(child->full_name);
+	if (cname == NULL)
+		return -ENOMEM;
+
+	/* NOTE: Multiple mods of created nodes not supported */
+	tchild = of_get_child_by_name(target, cname);
+	if (tchild != NULL) {
+		/* apply overlay recursively */
+		ret = of_overlay_apply_one(ov, tchild, child);
+		of_node_put(tchild);
+	} else {
+		/* create empty tree as a target */
+		tchild = __of_node_dup(child, "%s/%s", target->full_name, cname);
+		if (!tchild)
+			return -ENOMEM;
+
+		/* point to parent */
+		tchild->parent = target;
+
+		ret = of_changeset_attach_node(&ov->cset, tchild);
+		if (ret)
+			return ret;
+
+		ret = of_overlay_apply_one(ov, tchild, child);
+		if (ret)
+			return ret;
+
+		/* The properties are already copied, now do the child nodes */
+		for_each_child_of_node(child, grandchild) {
+			ret = of_overlay_apply_single_device_node(ov, tchild, grandchild);
+			if (ret) {
+				pr_err("%s: Failed to apply single node @%s/%s\n",
+					__func__, tchild->full_name,
+					grandchild->name);
+				return ret;
+			}
+		}
+	}
+
+	return ret;
+}
+
+/*
+ * Apply a single overlay node recursively.
+ *
+ * Note that the in case of an error the target node is left
+ * in a inconsistent state. Error recovery should be performed
+ * by using the changeset.
+ */
+static int of_overlay_apply_one(struct of_overlay *ov,
+		struct device_node *target, const struct device_node *overlay)
+{
+	struct device_node *child;
+	struct property *prop;
+	int ret;
+
+	for_each_property_of_node(overlay, prop) {
+		ret = of_overlay_apply_single_property(ov, target, prop);
+		if (ret) {
+			pr_err("%s: Failed to apply prop @%s/%s\n",
+				__func__, target->full_name, prop->name);
+			return ret;
+		}
+	}
+
+	for_each_child_of_node(overlay, child) {
+		ret = of_overlay_apply_single_device_node(ov, target, child);
+		if (ret != 0) {
+			pr_err("%s: Failed to apply single node @%s/%s\n",
+					__func__, target->full_name,
+					child->name);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * of_overlay_apply() - Apply @count overlays pointed at by @ovinfo_tab
+ * @ov:		Overlay to apply
+ *
+ * Applies the overlays given, while handling all error conditions
+ * appropriately. Either the operation succeeds, or if it fails the
+ * live tree is reverted to the state before the attempt.
+ * Returns 0, or an error if the overlay attempt failed.
+ */
+static int of_overlay_apply(struct of_overlay *ov)
+{
+	int i, err;
+
+	/* first we apply the overlays atomically */
+	for (i = 0; i < ov->count; i++) {
+		struct of_overlay_info *ovinfo = &ov->ovinfo_tab[i];
+
+		err = of_overlay_apply_one(ov, ovinfo->target, ovinfo->overlay);
+		if (err != 0) {
+			pr_err("%s: overlay failed '%s'\n",
+				__func__, ovinfo->target->full_name);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Find the target node using a number of different strategies
+ * in order of preference
+ *
+ * "target" property containing the phandle of the target
+ * "target-path" property containing the path of the target
+ */
+static struct device_node *find_target_node(struct device_node *info_node)
+{
+	const char *path;
+	u32 val;
+	int ret;
+
+	/* first try to go by using the target as a phandle */
+	ret = of_property_read_u32(info_node, "target", &val);
+	if (ret == 0)
+		return of_find_node_by_phandle(val);
+
+	/* now try to locate by path */
+	ret = of_property_read_string(info_node, "target-path", &path);
+	if (ret == 0)
+		return of_find_node_by_path(path);
+
+	pr_err("%s: Failed to find target for node %p (%s)\n", __func__,
+		info_node, info_node->name);
+
+	return NULL;
+}
+
+/**
+ * of_fill_overlay_info() - Fill an overlay info structure
+ * @ov		Overlay to fill
+ * @info_node:	Device node containing the overlay
+ * @ovinfo:	Pointer to the overlay info structure to fill
+ *
+ * Fills an overlay info structure with the overlay information
+ * from a device node. This device node must have a target property
+ * which contains a phandle of the overlay target node, and an
+ * __overlay__ child node which has the overlay contents.
+ * Both ovinfo->target & ovinfo->overlay have their references taken.
+ *
+ * Returns 0 on success, or a negative error value.
+ */
+static int of_fill_overlay_info(struct of_overlay *ov,
+		struct device_node *info_node, struct of_overlay_info *ovinfo)
+{
+	ovinfo->overlay = of_get_child_by_name(info_node, "__overlay__");
+	if (ovinfo->overlay == NULL)
+		goto err_fail;
+
+	ovinfo->target = find_target_node(info_node);
+	if (ovinfo->target == NULL)
+		goto err_fail;
+
+	return 0;
+
+err_fail:
+	of_node_put(ovinfo->target);
+	of_node_put(ovinfo->overlay);
+
+	memset(ovinfo, 0, sizeof(*ovinfo));
+	return -EINVAL;
+}
+
+/**
+ * of_build_overlay_info() - Build an overlay info array
+ * @ov		Overlay to build
+ * @tree:	Device node containing all the overlays
+ *
+ * Helper function that given a tree containing overlay information,
+ * allocates and builds an overlay info array containing it, ready
+ * for use using of_overlay_apply.
+ *
+ * Returns 0 on success with the @cntp @ovinfop pointers valid,
+ * while on error a negative error value is returned.
+ */
+static int of_build_overlay_info(struct of_overlay *ov,
+		struct device_node *tree)
+{
+	struct device_node *node;
+	struct of_overlay_info *ovinfo;
+	int cnt, err;
+
+	/* worst case; every child is a node */
+	cnt = 0;
+	for_each_child_of_node(tree, node)
+		cnt++;
+
+	ovinfo = kcalloc(cnt, sizeof(*ovinfo), GFP_KERNEL);
+	if (ovinfo == NULL)
+		return -ENOMEM;
+
+	cnt = 0;
+	for_each_child_of_node(tree, node) {
+		memset(&ovinfo[cnt], 0, sizeof(*ovinfo));
+		err = of_fill_overlay_info(ov, node, &ovinfo[cnt]);
+		if (err == 0)
+			cnt++;
+	}
+
+	/* if nothing filled, return error */
+	if (cnt == 0) {
+		kfree(ovinfo);
+		return -ENODEV;
+	}
+
+	ov->count = cnt;
+	ov->ovinfo_tab = ovinfo;
+
+	return 0;
+}
+
+/**
+ * of_free_overlay_info() - Free an overlay info array
+ * @ov		Overlay to free the overlay info from
+ * @ovinfo_tab:	Array of overlay_info's to free
+ *
+ * Releases the memory of a previously allocated ovinfo array
+ * by of_build_overlay_info.
+ * Returns 0, or an error if the arguments are bogus.
+ */
+static int of_free_overlay_info(struct of_overlay *ov)
+{
+	struct of_overlay_info *ovinfo;
+	int i;
+
+	/* do it in reverse */
+	for (i = ov->count - 1; i >= 0; i--) {
+		ovinfo = &ov->ovinfo_tab[i];
+
+		of_node_put(ovinfo->target);
+		of_node_put(ovinfo->overlay);
+	}
+	kfree(ov->ovinfo_tab);
+
+	return 0;
+}
+
+static LIST_HEAD(ov_list);
+static DEFINE_IDR(ov_idr);
+
+/**
+ * of_overlay_create() - Create and apply an overlay
+ * @tree:	Device node containing all the overlays
+ *
+ * Creates and applies an overlay while also keeping track
+ * of the overlay in a list. This list can be used to prevent
+ * illegal overlay removals.
+ *
+ * Returns the id of the created overlay, or an negative error number
+ */
+int of_overlay_create(struct device_node *tree)
+{
+	struct of_overlay *ov;
+	int err, id;
+
+	/* allocate the overlay structure */
+	ov = kzalloc(sizeof(*ov), GFP_KERNEL);
+	if (ov == NULL)
+		return -ENOMEM;
+	ov->id = -1;
+
+	INIT_LIST_HEAD(&ov->node);
+
+	of_changeset_init(&ov->cset);
+
+	mutex_lock(&of_mutex);
+
+	id = idr_alloc(&ov_idr, ov, 0, 0, GFP_KERNEL);
+	if (id < 0) {
+		pr_err("%s: idr_alloc() failed for tree@%s\n",
+				__func__, tree->full_name);
+		err = id;
+		goto err_destroy_trans;
+	}
+	ov->id = id;
+
+	/* build the overlay info structures */
+	err = of_build_overlay_info(ov, tree);
+	if (err) {
+		pr_err("%s: of_build_overlay_info() failed for tree@%s\n",
+				__func__, tree->full_name);
+		goto err_free_idr;
+	}
+
+	/* apply the overlay */
+	err = of_overlay_apply(ov);
+	if (err) {
+		pr_err("%s: of_overlay_apply() failed for tree@%s\n",
+				__func__, tree->full_name);
+		goto err_abort_trans;
+	}
+
+	/* apply the changeset */
+	err = of_changeset_apply(&ov->cset);
+	if (err) {
+		pr_err("%s: of_changeset_apply() failed for tree@%s\n",
+				__func__, tree->full_name);
+		goto err_revert_overlay;
+	}
+
+	/* add to the tail of the overlay list */
+	list_add_tail(&ov->node, &ov_list);
+
+	mutex_unlock(&of_mutex);
+
+	return id;
+
+err_revert_overlay:
+err_abort_trans:
+	of_free_overlay_info(ov);
+err_free_idr:
+	idr_remove(&ov_idr, ov->id);
+err_destroy_trans:
+	of_changeset_destroy(&ov->cset);
+	kfree(ov);
+	mutex_unlock(&of_mutex);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(of_overlay_create);
+
+/* check whether the given node, lies under the given tree */
+static int overlay_subtree_check(struct device_node *tree,
+		struct device_node *dn)
+{
+	struct device_node *child;
+
+	/* match? */
+	if (tree == dn)
+		return 1;
+
+	for_each_child_of_node(tree, child) {
+		if (overlay_subtree_check(child, dn))
+			return 1;
+	}
+
+	return 0;
+}
+
+/* check whether this overlay is the topmost */
+static int overlay_is_topmost(struct of_overlay *ov, struct device_node *dn)
+{
+	struct of_overlay *ovt;
+	struct of_changeset_entry *ce;
+
+	list_for_each_entry_reverse(ovt, &ov_list, node) {
+		/* if we hit ourselves, we're done */
+		if (ovt == ov)
+			break;
+
+		/* check against each subtree affected by this overlay */
+		list_for_each_entry(ce, &ovt->cset.entries, node) {
+			if (overlay_subtree_check(ce->np, dn)) {
+				pr_err("%s: #%d clashes #%d @%s\n",
+					__func__, ov->id, ovt->id,
+					dn->full_name);
+				return 0;
+			}
+		}
+	}
+
+	/* overlay is topmost */
+	return 1;
+}
+
+/*
+ * We can safely remove the overlay only if it's the top-most one.
+ * Newly applied overlays are inserted at the tail of the overlay list,
+ * so a top most overlay is the one that is closest to the tail.
+ *
+ * The topmost check is done by exploiting this property. For each
+ * affected device node in the log list we check if this overlay is
+ * the one closest to the tail. If another overlay has affected this
+ * device node and is closest to the tail, then removal is not permited.
+ */
+static int overlay_removal_is_ok(struct of_overlay *ov)
+{
+	struct of_changeset_entry *ce;
+
+	list_for_each_entry(ce, &ov->cset.entries, node) {
+		if (!overlay_is_topmost(ov, ce->np)) {
+			pr_err("%s: overlay #%d is not topmost\n",
+					__func__, ov->id);
+			return 0;
+		}
+	}
+
+	return 1;
+}
+
+/**
+ * of_overlay_destroy() - Removes an overlay
+ * @id:	Overlay id number returned by a previous call to of_overlay_create
+ *
+ * Removes an overlay if it is permissible.
+ *
+ * Returns 0 on success, or an negative error number
+ */
+int of_overlay_destroy(int id)
+{
+	struct of_overlay *ov;
+	int err;
+
+	mutex_lock(&of_mutex);
+
+	ov = idr_find(&ov_idr, id);
+	if (ov == NULL) {
+		err = -ENODEV;
+		pr_err("%s: Could not find overlay #%d\n",
+				__func__, id);
+		goto out;
+	}
+
+	/* check whether the overlay is safe to remove */
+	if (!overlay_removal_is_ok(ov)) {
+		err = -EBUSY;
+		pr_err("%s: removal check failed for overlay #%d\n",
+				__func__, id);
+		goto out;
+	}
+
+
+	list_del(&ov->node);
+	of_changeset_revert(&ov->cset);
+	of_free_overlay_info(ov);
+	idr_remove(&ov_idr, id);
+	of_changeset_destroy(&ov->cset);
+	kfree(ov);
+
+	err = 0;
+
+out:
+	mutex_unlock(&of_mutex);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(of_overlay_destroy);
+
+/**
+ * of_overlay_destroy_all() - Removes all overlays from the system
+ *
+ * Removes all overlays from the system in the correct order.
+ *
+ * Returns 0 on success, or an negative error number
+ */
+int of_overlay_destroy_all(void)
+{
+	struct of_overlay *ov, *ovn;
+
+	mutex_lock(&of_mutex);
+
+	/* the tail of list is guaranteed to be safe to remove */
+	list_for_each_entry_safe_reverse(ov, ovn, &ov_list, node) {
+		list_del(&ov->node);
+		of_changeset_revert(&ov->cset);
+		of_free_overlay_info(ov);
+		idr_remove(&ov_idr, ov->id);
+		kfree(ov);
+	}
+
+	mutex_unlock(&of_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_overlay_destroy_all);
diff --git a/include/linux/of.h b/include/linux/of.h
index fe1dec87fd6..aa01cf5852f 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -23,6 +23,7 @@
 #include <linux/spinlock.h>
 #include <linux/topology.h>
 #include <linux/notifier.h>
+#include <linux/list.h>
 
 #include <asm/byteorder.h>
 #include <asm/errno.h>
@@ -957,4 +958,34 @@ static inline int of_reconfig_get_state_change(unsigned long action,
 /* CONFIG_OF_RESOLVE api */
 extern int of_resolve_phandles(struct device_node *tree);
 
+/**
+ * Overlay support
+ */
+
+#ifdef CONFIG_OF_OVERLAY
+
+/* ID based overlays; the API for external users */
+int of_overlay_create(struct device_node *tree);
+int of_overlay_destroy(int id);
+int of_overlay_destroy_all(void);
+
+#else
+
+static inline int of_overlay_create(struct device_node *tree)
+{
+	return -ENOTSUPP;
+}
+
+static inline int of_overlay_destroy(int id)
+{
+	return -ENOTSUPP;
+}
+
+static inline int of_overlay_destroy_all(void)
+{
+	return -ENOTSUPP;
+}
+
+#endif
+
 #endif /* _LINUX_OF_H */
-- 
cgit v1.2.3-70-g09d2


From f895b252d4edf66b2895fb5a7b17a638665f3e1f Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Mon, 17 Nov 2014 16:58:04 -0500
Subject: sunrpc: eliminate RPC_DEBUG

It's always set to whatever CONFIG_SUNRPC_DEBUG is, so just use that.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 include/linux/sunrpc/auth.h             | 2 +-
 include/linux/sunrpc/debug.h            | 9 +++------
 include/linux/sunrpc/sched.h            | 8 ++++----
 include/uapi/linux/nfsd/debug.h         | 2 +-
 net/sunrpc/auth.c                       | 4 ++--
 net/sunrpc/auth_generic.c               | 2 +-
 net/sunrpc/auth_gss/auth_gss.c          | 2 +-
 net/sunrpc/auth_gss/gss_generic_token.c | 2 +-
 net/sunrpc/auth_gss/gss_krb5_crypto.c   | 2 +-
 net/sunrpc/auth_gss/gss_krb5_keys.c     | 2 +-
 net/sunrpc/auth_gss/gss_krb5_mech.c     | 2 +-
 net/sunrpc/auth_gss/gss_krb5_seal.c     | 2 +-
 net/sunrpc/auth_gss/gss_krb5_seqnum.c   | 2 +-
 net/sunrpc/auth_gss/gss_krb5_unseal.c   | 2 +-
 net/sunrpc/auth_gss/gss_krb5_wrap.c     | 2 +-
 net/sunrpc/auth_gss/gss_mech_switch.c   | 2 +-
 net/sunrpc/auth_gss/gss_rpc_xdr.h       | 2 +-
 net/sunrpc/auth_gss/svcauth_gss.c       | 2 +-
 net/sunrpc/auth_null.c                  | 4 ++--
 net/sunrpc/auth_unix.c                  | 2 +-
 net/sunrpc/backchannel_rqst.c           | 2 +-
 net/sunrpc/clnt.c                       | 6 +++---
 net/sunrpc/rpcb_clnt.c                  | 2 +-
 net/sunrpc/sched.c                      | 4 ++--
 net/sunrpc/sunrpc_syms.c                | 4 ++--
 net/sunrpc/svc.c                        | 2 +-
 net/sunrpc/sysctl.c                     | 2 +-
 net/sunrpc/xprt.c                       | 2 +-
 net/sunrpc/xprtrdma/rpc_rdma.c          | 4 ++--
 net/sunrpc/xprtrdma/transport.c         | 8 ++++----
 net/sunrpc/xprtrdma/verbs.c             | 8 ++++----
 net/sunrpc/xprtsock.c                   | 8 ++++----
 32 files changed, 53 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 8e030075fe7..a7cbb570cc5 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -53,7 +53,7 @@ struct rpc_cred {
 	struct rcu_head		cr_rcu;
 	struct rpc_auth *	cr_auth;
 	const struct rpc_credops *cr_ops;
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	unsigned long		cr_magic;	/* 0x0f4aa4f0 */
 #endif
 	unsigned long		cr_expire;	/* when to gc */
diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h
index 9385bd74c86..51143757b8f 100644
--- a/include/linux/sunrpc/debug.h
+++ b/include/linux/sunrpc/debug.h
@@ -14,9 +14,6 @@
 /*
  * Enable RPC debugging/profiling.
  */
-#ifdef CONFIG_SUNRPC_DEBUG
-#define  RPC_DEBUG
-#endif
 #ifdef CONFIG_TRACEPOINTS
 #define RPC_TRACEPOINTS
 #endif
@@ -25,7 +22,7 @@
 /*
  * Debugging macros etc
  */
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 extern unsigned int		rpc_debug;
 extern unsigned int		nfs_debug;
 extern unsigned int		nfsd_debug;
@@ -36,7 +33,7 @@ extern unsigned int		nlm_debug;
 #define dprintk_rcu(args...)	dfprintk_rcu(FACILITY, ## args)
 
 #undef ifdebug
-#ifdef RPC_DEBUG			
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define ifdebug(fac)		if (unlikely(rpc_debug & RPCDBG_##fac))
 
 # define dfprintk(fac, args...)	\
@@ -65,7 +62,7 @@ extern unsigned int		nlm_debug;
 /*
  * Sysctl interface for RPC debugging
  */
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 void		rpc_register_sysctl(void);
 void		rpc_unregister_sysctl(void);
 #endif
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 1a8959944c5..fecdbf1b479 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -79,7 +79,7 @@ struct rpc_task {
 	unsigned short		tk_flags;	/* misc flags */
 	unsigned short		tk_timeouts;	/* maj timeouts */
 
-#if defined(RPC_DEBUG) || defined(RPC_TRACEPOINTS)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || defined(RPC_TRACEPOINTS)
 	unsigned short		tk_pid;		/* debugging aid */
 #endif
 	unsigned char		tk_priority : 2,/* Task priority */
@@ -187,7 +187,7 @@ struct rpc_wait_queue {
 	unsigned char		nr;			/* # tasks remaining for cookie */
 	unsigned short		qlen;			/* total # tasks waiting in queue */
 	struct rpc_timer	timer_list;
-#if defined(RPC_DEBUG) || defined(RPC_TRACEPOINTS)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || defined(RPC_TRACEPOINTS)
 	const char *		name;
 #endif
 };
@@ -237,7 +237,7 @@ void		rpc_free(void *);
 int		rpciod_up(void);
 void		rpciod_down(void);
 int		__rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *);
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 struct net;
 void		rpc_show_tasks(struct net *);
 #endif
@@ -251,7 +251,7 @@ static inline int rpc_wait_for_completion_task(struct rpc_task *task)
 	return __rpc_wait_for_completion_task(task, NULL);
 }
 
-#if defined(RPC_DEBUG) || defined (RPC_TRACEPOINTS)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || defined (RPC_TRACEPOINTS)
 static inline const char * rpc_qname(const struct rpc_wait_queue *q)
 {
 	return ((q && q->name) ? q->name : "unknown");
diff --git a/include/uapi/linux/nfsd/debug.h b/include/uapi/linux/nfsd/debug.h
index a6f453c740b..1fdc95bb237 100644
--- a/include/uapi/linux/nfsd/debug.h
+++ b/include/uapi/linux/nfsd/debug.h
@@ -15,7 +15,7 @@
  * Enable debugging for nfsd.
  * Requires RPC_DEBUG.
  */
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define NFSD_DEBUG		1
 #endif
 
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 383eb919ac0..47f38be4155 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -16,7 +16,7 @@
 #include <linux/sunrpc/gss_api.h>
 #include <linux/spinlock.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
@@ -646,7 +646,7 @@ rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred,
 	cred->cr_auth = auth;
 	cred->cr_ops = ops;
 	cred->cr_expire = jiffies;
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	cred->cr_magic = RPCAUTH_CRED_MAGIC;
 #endif
 	cred->cr_uid = acred->uid;
diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c
index 6f6b829c9e8..41248b1820c 100644
--- a/net/sunrpc/auth_generic.c
+++ b/net/sunrpc/auth_generic.c
@@ -14,7 +14,7 @@
 #include <linux/sunrpc/debug.h>
 #include <linux/sunrpc/sched.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 53ed8d3f889..dace13d7638 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -66,7 +66,7 @@ static unsigned int gss_expired_cred_retry_delay = GSS_RETRY_EXPIRED;
 #define GSS_KEY_EXPIRE_TIMEO 240
 static unsigned int gss_key_expire_timeo = GSS_KEY_EXPIRE_TIMEO;
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_generic_token.c b/net/sunrpc/auth_gss/gss_generic_token.c
index c586e92bcf7..254defe446a 100644
--- a/net/sunrpc/auth_gss/gss_generic_token.c
+++ b/net/sunrpc/auth_gss/gss_generic_token.c
@@ -38,7 +38,7 @@
 #include <linux/sunrpc/gss_asn1.h>
 
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index f5ed9f6ece0..b5408e8a37f 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -45,7 +45,7 @@
 #include <linux/sunrpc/gss_krb5.h>
 #include <linux/sunrpc/xdr.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c
index 24589bd2a4b..234fa8d0fd9 100644
--- a/net/sunrpc/auth_gss/gss_krb5_keys.c
+++ b/net/sunrpc/auth_gss/gss_krb5_keys.c
@@ -61,7 +61,7 @@
 #include <linux/sunrpc/xdr.h>
 #include <linux/lcm.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index 0d3c158ef8f..28db442a003 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -45,7 +45,7 @@
 #include <linux/crypto.h>
 #include <linux/sunrpc/gss_krb5_enctypes.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c
index 42768e5c399..1d74d653e6c 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seal.c
@@ -64,7 +64,7 @@
 #include <linux/random.h>
 #include <linux/crypto.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
index 62ac90c62cb..20d55c793eb 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
@@ -35,7 +35,7 @@
 #include <linux/sunrpc/gss_krb5.h>
 #include <linux/crypto.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c
index 6c981ddc19f..dcf9515d9ae 100644
--- a/net/sunrpc/auth_gss/gss_krb5_unseal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c
@@ -62,7 +62,7 @@
 #include <linux/sunrpc/gss_krb5.h>
 #include <linux/crypto.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c
index 4b614c604fe..ca7e92a32f8 100644
--- a/net/sunrpc/auth_gss/gss_krb5_wrap.c
+++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c
@@ -35,7 +35,7 @@
 #include <linux/pagemap.h>
 #include <linux/crypto.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c
index 92d5ab99fbf..7063d856a59 100644
--- a/net/sunrpc/auth_gss/gss_mech_switch.c
+++ b/net/sunrpc/auth_gss/gss_mech_switch.c
@@ -46,7 +46,7 @@
 #include <linux/sunrpc/gss_api.h>
 #include <linux/sunrpc/clnt.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.h b/net/sunrpc/auth_gss/gss_rpc_xdr.h
index 685a688f3d8..9d88c6239f0 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.h
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.h
@@ -25,7 +25,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/xprtsock.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index c548ab213f7..de856ddf5fe 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -51,7 +51,7 @@
 #include "gss_rpc_upcall.h"
 
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c
index 712c123e04e..c2a2b584a05 100644
--- a/net/sunrpc/auth_null.c
+++ b/net/sunrpc/auth_null.c
@@ -10,7 +10,7 @@
 #include <linux/module.h>
 #include <linux/sunrpc/clnt.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
@@ -138,7 +138,7 @@ struct rpc_cred null_cred = {
 	.cr_ops		= &null_credops,
 	.cr_count	= ATOMIC_INIT(1),
 	.cr_flags	= 1UL << RPCAUTH_CRED_UPTODATE,
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	.cr_magic	= RPCAUTH_CRED_MAGIC,
 #endif
 };
diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c
index d5d69236629..4feda2d0a83 100644
--- a/net/sunrpc/auth_unix.c
+++ b/net/sunrpc/auth_unix.c
@@ -25,7 +25,7 @@ struct unx_cred {
 
 #define UNX_WRITESLACK		(21 + (UNX_MAXNODENAME >> 2))
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 9761a0da964..651f49ab601 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -27,7 +27,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #include <linux/export.h>
 #include <linux/sunrpc/bc_xprt.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 #define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 9acd6ce88db..36c64ef460c 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -42,7 +42,7 @@
 #include "sunrpc.h"
 #include "netns.h"
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_CALL
 #endif
 
@@ -1396,7 +1396,7 @@ rpc_restart_call(struct rpc_task *task)
 }
 EXPORT_SYMBOL_GPL(rpc_restart_call);
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 static const char *rpc_proc_name(const struct rpc_task *task)
 {
 	const struct rpc_procinfo *proc = task->tk_msg.rpc_proc;
@@ -2421,7 +2421,7 @@ struct rpc_task *rpc_call_null(struct rpc_clnt *clnt, struct rpc_cred *cred, int
 }
 EXPORT_SYMBOL_GPL(rpc_call_null);
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 static void rpc_show_header(void)
 {
 	printk(KERN_INFO "-pid- flgs status -client- --rqstp- "
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 1891a1022c1..05202012bcf 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -32,7 +32,7 @@
 
 #include "netns.h"
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_BIND
 #endif
 
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index fe3441abdbe..574b2977fc4 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -24,7 +24,7 @@
 
 #include "sunrpc.h"
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 #define RPCDBG_FACILITY		RPCDBG_SCHED
 #endif
 
@@ -258,7 +258,7 @@ static int rpc_wait_bit_killable(struct wait_bit_key *key)
 	return 0;
 }
 
-#if defined(RPC_DEBUG) || defined(RPC_TRACEPOINTS)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || defined(RPC_TRACEPOINTS)
 static void rpc_task_set_debuginfo(struct rpc_task *task)
 {
 	static atomic_t rpc_pid;
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index cd30120de9e..f632e476ab6 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -97,7 +97,7 @@ init_sunrpc(void)
 	err = register_rpc_pipefs();
 	if (err)
 		goto out4;
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	rpc_register_sysctl();
 #endif
 	svc_init_xprt_sock();	/* svc sock transport */
@@ -123,7 +123,7 @@ cleanup_sunrpc(void)
 	unregister_rpc_pipefs();
 	rpc_destroy_mempool();
 	unregister_pernet_subsys(&sunrpc_net_ops);
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	rpc_unregister_sysctl();
 #endif
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 371a8bbb43d..2783fd80c22 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1042,7 +1042,7 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net)
 /*
  * dprintk the given error with the address of the client that caused it.
  */
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 static __printf(2, 3)
 void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...)
 {
diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c
index c99c58e2ee6..887f0183b4c 100644
--- a/net/sunrpc/sysctl.c
+++ b/net/sunrpc/sysctl.c
@@ -37,7 +37,7 @@ EXPORT_SYMBOL_GPL(nfsd_debug);
 unsigned int	nlm_debug;
 EXPORT_SYMBOL_GPL(nlm_debug);
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 
 static struct ctl_table_header *sunrpc_table_header;
 static struct ctl_table sunrpc_table[];
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 1b2e5e616ca..894d071426b 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -57,7 +57,7 @@
  * Local variables
  */
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_XPRT
 #endif
 
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 6166c985fe2..df01d124936 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -49,11 +49,11 @@
 
 #include <linux/highmem.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 static const char transfertypes[][12] = {
 	"pure inline",	/* no chunks */
 	" read chunk",	/* some argument via rdma read */
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 6a4615dd026..ef58ebadb3a 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -55,7 +55,7 @@
 
 #include "xprt_rdma.h"
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
@@ -75,7 +75,7 @@ static unsigned int xprt_rdma_inline_write_padding;
 static unsigned int xprt_rdma_memreg_strategy = RPCRDMA_FRMR;
                 int xprt_rdma_pad_optimize = 0;
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 
 static unsigned int min_slot_table_size = RPCRDMA_MIN_SLOT_TABLE;
 static unsigned int max_slot_table_size = RPCRDMA_MAX_SLOT_TABLE;
@@ -705,7 +705,7 @@ static void __exit xprt_rdma_cleanup(void)
 	int rc;
 
 	dprintk("RPCRDMA Module Removed, deregister RPC RDMA transport\n");
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	if (sunrpc_table_header) {
 		unregister_sysctl_table(sunrpc_table_header);
 		sunrpc_table_header = NULL;
@@ -736,7 +736,7 @@ static int __init xprt_rdma_init(void)
 	dprintk("\tPadding %d\n\tMemreg %d\n",
 		xprt_rdma_inline_write_padding, xprt_rdma_memreg_strategy);
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	if (!sunrpc_table_header)
 		sunrpc_table_header = register_sysctl_table(sunrpc_table);
 #endif
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 61c41298b4e..b92b04083e4 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -57,7 +57,7 @@
  * Globals/Macros
  */
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
@@ -313,7 +313,7 @@ rpcrdma_flush_cqs(struct rpcrdma_ep *ep)
 	rpcrdma_sendcq_upcall(ep->rep_attr.send_cq, ep);
 }
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 static const char * const conn[] = {
 	"address resolved",
 	"address error",
@@ -344,7 +344,7 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event)
 	struct rpcrdma_xprt *xprt = id->context;
 	struct rpcrdma_ia *ia = &xprt->rx_ia;
 	struct rpcrdma_ep *ep = &xprt->rx_ep;
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	struct sockaddr_in *addr = (struct sockaddr_in *) &ep->rep_remote_addr;
 #endif
 	struct ib_qp_attr attr;
@@ -408,7 +408,7 @@ connected:
 		break;
 	}
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	if (connstate == 1) {
 		int ird = attr.max_dest_rd_atomic;
 		int tird = ep->rep_remote_cma.responder_resources;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 31c015196a2..87ce7e8bb8d 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -75,7 +75,7 @@ static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO;
  * someone else's file names!
  */
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 
 static unsigned int min_slot_table_size = RPC_MIN_SLOT_TABLE;
 static unsigned int max_slot_table_size = RPC_MAX_SLOT_TABLE;
@@ -186,7 +186,7 @@ static struct ctl_table sunrpc_table[] = {
  */
 #define XS_IDLE_DISC_TO		(5U * 60 * HZ)
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # undef  RPC_DEBUG_DATA
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
@@ -2991,7 +2991,7 @@ static struct xprt_class	xs_bc_tcp_transport = {
  */
 int init_socket_xprt(void)
 {
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	if (!sunrpc_table_header)
 		sunrpc_table_header = register_sysctl_table(sunrpc_table);
 #endif
@@ -3010,7 +3010,7 @@ int init_socket_xprt(void)
  */
 void cleanup_socket_xprt(void)
 {
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	if (sunrpc_table_header) {
 		unregister_sysctl_table(sunrpc_table_header);
 		sunrpc_table_header = NULL;
-- 
cgit v1.2.3-70-g09d2


From 1306729b0d4f4a0bd0d098711ed3d938dc5a1a28 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Mon, 17 Nov 2014 16:58:05 -0500
Subject: sunrpc: eliminate RPC_TRACEPOINTS

It's always set to the same value as CONFIG_TRACEPOINTS, so we can just
use that instead.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 include/linux/sunrpc/debug.h | 9 ---------
 include/linux/sunrpc/sched.h | 6 +++---
 net/sunrpc/sched.c           | 2 +-
 3 files changed, 4 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h
index 51143757b8f..43f38ee9668 100644
--- a/include/linux/sunrpc/debug.h
+++ b/include/linux/sunrpc/debug.h
@@ -10,15 +10,6 @@
 
 #include <uapi/linux/sunrpc/debug.h>
 
-
-/*
- * Enable RPC debugging/profiling.
- */
-#ifdef CONFIG_TRACEPOINTS
-#define RPC_TRACEPOINTS
-#endif
-/* #define  RPC_PROFILE */
-
 /*
  * Debugging macros etc
  */
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index fecdbf1b479..5f1e6bd4c31 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -79,7 +79,7 @@ struct rpc_task {
 	unsigned short		tk_flags;	/* misc flags */
 	unsigned short		tk_timeouts;	/* maj timeouts */
 
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || defined(RPC_TRACEPOINTS)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS)
 	unsigned short		tk_pid;		/* debugging aid */
 #endif
 	unsigned char		tk_priority : 2,/* Task priority */
@@ -187,7 +187,7 @@ struct rpc_wait_queue {
 	unsigned char		nr;			/* # tasks remaining for cookie */
 	unsigned short		qlen;			/* total # tasks waiting in queue */
 	struct rpc_timer	timer_list;
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || defined(RPC_TRACEPOINTS)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS)
 	const char *		name;
 #endif
 };
@@ -251,7 +251,7 @@ static inline int rpc_wait_for_completion_task(struct rpc_task *task)
 	return __rpc_wait_for_completion_task(task, NULL);
 }
 
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || defined (RPC_TRACEPOINTS)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS)
 static inline const char * rpc_qname(const struct rpc_wait_queue *q)
 {
 	return ((q && q->name) ? q->name : "unknown");
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 574b2977fc4..d20f2329eea 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -258,7 +258,7 @@ static int rpc_wait_bit_killable(struct wait_bit_key *key)
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || defined(RPC_TRACEPOINTS)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS)
 static void rpc_task_set_debuginfo(struct rpc_task *task)
 {
 	static atomic_t rpc_pid;
-- 
cgit v1.2.3-70-g09d2


From 4ed0d6a9cf80a4a1f74e18d36a2ee5ef391a8f27 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Sun, 23 Nov 2014 09:39:53 -0300
Subject: [media] v4l2-common: remove unused helper functions

Several control helper functions are no longer needed since most drivers
are now converted to the control framework. So we can delete them.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/v4l2-core/v4l2-common.c | 95 -----------------------------------
 include/media/v4l2-common.h           | 10 ----
 2 files changed, 105 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index 2e9d81f4c1a..84932093265 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -135,101 +135,6 @@ int v4l2_ctrl_query_fill(struct v4l2_queryctrl *qctrl, s32 _min, s32 _max, s32 _
 }
 EXPORT_SYMBOL(v4l2_ctrl_query_fill);
 
-/* Fill in a struct v4l2_querymenu based on the struct v4l2_queryctrl and
-   the menu. The qctrl pointer may be NULL, in which case it is ignored.
-   If menu_items is NULL, then the menu items are retrieved using
-   v4l2_ctrl_get_menu. */
-int v4l2_ctrl_query_menu(struct v4l2_querymenu *qmenu, struct v4l2_queryctrl *qctrl,
-	       const char * const *menu_items)
-{
-	int i;
-
-	qmenu->reserved = 0;
-	if (menu_items == NULL)
-		menu_items = v4l2_ctrl_get_menu(qmenu->id);
-	if (menu_items == NULL ||
-	    (qctrl && (qmenu->index < qctrl->minimum || qmenu->index > qctrl->maximum)))
-		return -EINVAL;
-	for (i = 0; i < qmenu->index && menu_items[i]; i++) ;
-	if (menu_items[i] == NULL || menu_items[i][0] == '\0')
-		return -EINVAL;
-	strlcpy(qmenu->name, menu_items[qmenu->index], sizeof(qmenu->name));
-	return 0;
-}
-EXPORT_SYMBOL(v4l2_ctrl_query_menu);
-
-/* Fill in a struct v4l2_querymenu based on the specified array of valid
-   menu items (terminated by V4L2_CTRL_MENU_IDS_END).
-   Use this if there are 'holes' in the list of valid menu items. */
-int v4l2_ctrl_query_menu_valid_items(struct v4l2_querymenu *qmenu, const u32 *ids)
-{
-	const char * const *menu_items = v4l2_ctrl_get_menu(qmenu->id);
-
-	qmenu->reserved = 0;
-	if (menu_items == NULL || ids == NULL)
-		return -EINVAL;
-	while (*ids != V4L2_CTRL_MENU_IDS_END) {
-		if (*ids++ == qmenu->index) {
-			strlcpy(qmenu->name, menu_items[qmenu->index],
-					sizeof(qmenu->name));
-			return 0;
-		}
-	}
-	return -EINVAL;
-}
-EXPORT_SYMBOL(v4l2_ctrl_query_menu_valid_items);
-
-/* ctrl_classes points to an array of u32 pointers, the last element is
-   a NULL pointer. Each u32 array is a 0-terminated array of control IDs.
-   Each array must be sorted low to high and belong to the same control
-   class. The array of u32 pointers must also be sorted, from low class IDs
-   to high class IDs.
-
-   This function returns the first ID that follows after the given ID.
-   When no more controls are available 0 is returned. */
-u32 v4l2_ctrl_next(const u32 * const * ctrl_classes, u32 id)
-{
-	u32 ctrl_class = V4L2_CTRL_ID2CLASS(id);
-	const u32 *pctrl;
-
-	if (ctrl_classes == NULL)
-		return 0;
-
-	/* if no query is desired, then check if the ID is part of ctrl_classes */
-	if ((id & V4L2_CTRL_FLAG_NEXT_CTRL) == 0) {
-		/* find class */
-		while (*ctrl_classes && V4L2_CTRL_ID2CLASS(**ctrl_classes) != ctrl_class)
-			ctrl_classes++;
-		if (*ctrl_classes == NULL)
-			return 0;
-		pctrl = *ctrl_classes;
-		/* find control ID */
-		while (*pctrl && *pctrl != id) pctrl++;
-		return *pctrl ? id : 0;
-	}
-	id &= V4L2_CTRL_ID_MASK;
-	id++;	/* select next control */
-	/* find first class that matches (or is greater than) the class of
-	   the ID */
-	while (*ctrl_classes && V4L2_CTRL_ID2CLASS(**ctrl_classes) < ctrl_class)
-		ctrl_classes++;
-	/* no more classes */
-	if (*ctrl_classes == NULL)
-		return 0;
-	pctrl = *ctrl_classes;
-	/* find first ctrl within the class that is >= ID */
-	while (*pctrl && *pctrl < id) pctrl++;
-	if (*pctrl)
-		return *pctrl;
-	/* we are at the end of the controls of the current class. */
-	/* continue with next class if available */
-	ctrl_classes++;
-	if (*ctrl_classes == NULL)
-		return 0;
-	return **ctrl_classes;
-}
-EXPORT_SYMBOL(v4l2_ctrl_next);
-
 /* I2C Helper functions */
 
 #if IS_ENABLED(CONFIG_I2C)
diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h
index 48f974866f1..6b4951de759 100644
--- a/include/media/v4l2-common.h
+++ b/include/media/v4l2-common.h
@@ -88,16 +88,6 @@ const char *v4l2_ctrl_get_name(u32 id);
 const char * const *v4l2_ctrl_get_menu(u32 id);
 const s64 *v4l2_ctrl_get_int_menu(u32 id, u32 *len);
 int v4l2_ctrl_query_fill(struct v4l2_queryctrl *qctrl, s32 min, s32 max, s32 step, s32 def);
-int v4l2_ctrl_query_menu(struct v4l2_querymenu *qmenu,
-		struct v4l2_queryctrl *qctrl, const char * const *menu_items);
-#define V4L2_CTRL_MENU_IDS_END (0xffffffff)
-int v4l2_ctrl_query_menu_valid_items(struct v4l2_querymenu *qmenu, const u32 *ids);
-
-/* Note: ctrl_classes points to an array of u32 pointers. Each u32 array is a
-   0-terminated array of control IDs. Each array must be sorted low to high
-   and belong to the same control class. The array of u32 pointers must also
-   be sorted, from low class IDs to high class IDs. */
-u32 v4l2_ctrl_next(const u32 * const *ctrl_classes, u32 id);
 
 /* ------------------------------------------------------------------------- */
 
-- 
cgit v1.2.3-70-g09d2


From 79fbc209f11b82d8cad37e20da71851fdceecfbd Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Sun, 23 Nov 2014 09:39:54 -0300
Subject: [media] v4l2-ctrl: move function prototypes from common.h to ctrls.h

For some unknown reason several control prototypes where in v4l2-common.c
instead of in v4l2-ctrls.h. Move them and document them.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/v4l2-common.h |  3 ---
 include/media/v4l2-ctrls.h  | 25 +++++++++++++++++++++++++
 2 files changed, 25 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h
index 6b4951de759..c69d91d32e5 100644
--- a/include/media/v4l2-common.h
+++ b/include/media/v4l2-common.h
@@ -84,9 +84,6 @@
 
 int v4l2_ctrl_check(struct v4l2_ext_control *ctrl, struct v4l2_queryctrl *qctrl,
 		const char * const *menu_items);
-const char *v4l2_ctrl_get_name(u32 id);
-const char * const *v4l2_ctrl_get_menu(u32 id);
-const s64 *v4l2_ctrl_get_int_menu(u32 id, u32 *len);
 int v4l2_ctrl_query_fill(struct v4l2_queryctrl *qctrl, s32 min, s32 max, s32 step, s32 def);
 
 /* ------------------------------------------------------------------------- */
diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h
index b7cd7a665e3..911f3e54283 100644
--- a/include/media/v4l2-ctrls.h
+++ b/include/media/v4l2-ctrls.h
@@ -670,6 +670,31 @@ static inline int v4l2_ctrl_modify_range(struct v4l2_ctrl *ctrl,
   */
 void v4l2_ctrl_notify(struct v4l2_ctrl *ctrl, v4l2_ctrl_notify_fnc notify, void *priv);
 
+/** v4l2_ctrl_get_name() - Get the name of the control
+ * @id:		The control ID.
+ *
+ * This function returns the name of the given control ID or NULL if it isn't
+ * a known control.
+ */
+const char *v4l2_ctrl_get_name(u32 id);
+
+/** v4l2_ctrl_get_menu() - Get the menu string array of the control
+ * @id:		The control ID.
+ *
+ * This function returns the NULL-terminated menu string array name of the
+ * given control ID or NULL if it isn't a known menu control.
+ */
+const char * const *v4l2_ctrl_get_menu(u32 id);
+
+/** v4l2_ctrl_get_int_menu() - Get the integer menu array of the control
+ * @id:		The control ID.
+ * @len:	The size of the integer array.
+ *
+ * This function returns the integer array of the given control ID or NULL if it
+ * if it isn't a known integer menu control.
+ */
+const s64 *v4l2_ctrl_get_int_menu(u32 id, u32 *len);
+
 /** v4l2_ctrl_g_ctrl() - Helper function to get the control's value from within a driver.
   * @ctrl:	The control.
   *
-- 
cgit v1.2.3-70-g09d2


From 4daee77976718b3e8136e37872d7ad5c36754e25 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Sun, 23 Nov 2014 09:39:55 -0300
Subject: [media] v4l2-common: move v4l2_ctrl_check to cx2341x

The v4l2_ctrl_check() helper function is now only used in cx2341x.
Move it there and make it static.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/common/cx2341x.c        | 29 +++++++++++++++++++++++++++++
 drivers/media/v4l2-core/v4l2-common.c | 30 ------------------------------
 include/media/v4l2-common.h           |  4 +---
 3 files changed, 30 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/drivers/media/common/cx2341x.c b/drivers/media/common/cx2341x.c
index be763150b8a..c07b9db51b0 100644
--- a/drivers/media/common/cx2341x.c
+++ b/drivers/media/common/cx2341x.c
@@ -931,6 +931,35 @@ static void cx2341x_calc_audio_properties(struct cx2341x_mpeg_params *params)
 	}
 }
 
+/* Check for correctness of the ctrl's value based on the data from
+   struct v4l2_queryctrl and the available menu items. Note that
+   menu_items may be NULL, in that case it is ignored. */
+static int v4l2_ctrl_check(struct v4l2_ext_control *ctrl, struct v4l2_queryctrl *qctrl,
+		const char * const *menu_items)
+{
+	if (qctrl->flags & V4L2_CTRL_FLAG_DISABLED)
+		return -EINVAL;
+	if (qctrl->flags & V4L2_CTRL_FLAG_GRABBED)
+		return -EBUSY;
+	if (qctrl->type == V4L2_CTRL_TYPE_STRING)
+		return 0;
+	if (qctrl->type == V4L2_CTRL_TYPE_BUTTON ||
+	    qctrl->type == V4L2_CTRL_TYPE_INTEGER64 ||
+	    qctrl->type == V4L2_CTRL_TYPE_CTRL_CLASS)
+		return 0;
+	if (ctrl->value < qctrl->minimum || ctrl->value > qctrl->maximum)
+		return -ERANGE;
+	if (qctrl->type == V4L2_CTRL_TYPE_MENU && menu_items != NULL) {
+		if (menu_items[ctrl->value] == NULL ||
+		    menu_items[ctrl->value][0] == '\0')
+			return -EINVAL;
+	}
+	if (qctrl->type == V4L2_CTRL_TYPE_BITMASK &&
+			(ctrl->value & ~qctrl->maximum))
+		return -ERANGE;
+	return 0;
+}
+
 int cx2341x_ext_ctrls(struct cx2341x_mpeg_params *params, int busy,
 		  struct v4l2_ext_controls *ctrls, unsigned int cmd)
 {
diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index 84932093265..5b808500e7e 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -80,36 +80,6 @@ MODULE_LICENSE("GPL");
 
 /* Helper functions for control handling			     */
 
-/* Check for correctness of the ctrl's value based on the data from
-   struct v4l2_queryctrl and the available menu items. Note that
-   menu_items may be NULL, in that case it is ignored. */
-int v4l2_ctrl_check(struct v4l2_ext_control *ctrl, struct v4l2_queryctrl *qctrl,
-		const char * const *menu_items)
-{
-	if (qctrl->flags & V4L2_CTRL_FLAG_DISABLED)
-		return -EINVAL;
-	if (qctrl->flags & V4L2_CTRL_FLAG_GRABBED)
-		return -EBUSY;
-	if (qctrl->type == V4L2_CTRL_TYPE_STRING)
-		return 0;
-	if (qctrl->type == V4L2_CTRL_TYPE_BUTTON ||
-	    qctrl->type == V4L2_CTRL_TYPE_INTEGER64 ||
-	    qctrl->type == V4L2_CTRL_TYPE_CTRL_CLASS)
-		return 0;
-	if (ctrl->value < qctrl->minimum || ctrl->value > qctrl->maximum)
-		return -ERANGE;
-	if (qctrl->type == V4L2_CTRL_TYPE_MENU && menu_items != NULL) {
-		if (menu_items[ctrl->value] == NULL ||
-		    menu_items[ctrl->value][0] == '\0')
-			return -EINVAL;
-	}
-	if (qctrl->type == V4L2_CTRL_TYPE_BITMASK &&
-			(ctrl->value & ~qctrl->maximum))
-		return -ERANGE;
-	return 0;
-}
-EXPORT_SYMBOL(v4l2_ctrl_check);
-
 /* Fill in a struct v4l2_queryctrl */
 int v4l2_ctrl_query_fill(struct v4l2_queryctrl *qctrl, s32 _min, s32 _max, s32 _step, s32 _def)
 {
diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h
index c69d91d32e5..1cc0c5ba16b 100644
--- a/include/media/v4l2-common.h
+++ b/include/media/v4l2-common.h
@@ -80,10 +80,8 @@
 
 /* ------------------------------------------------------------------------- */
 
-/* Control helper functions */
+/* Control helper function */
 
-int v4l2_ctrl_check(struct v4l2_ext_control *ctrl, struct v4l2_queryctrl *qctrl,
-		const char * const *menu_items);
 int v4l2_ctrl_query_fill(struct v4l2_queryctrl *qctrl, s32 min, s32 max, s32 step, s32 def);
 
 /* ------------------------------------------------------------------------- */
-- 
cgit v1.2.3-70-g09d2


From cf227429c74778cc9f8caf734d1f161f8f021915 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Tue, 18 Nov 2014 09:50:57 -0300
Subject: [media] videobuf2-core.h: improve documentation

Document that drivers can access/modify the buffer contents in buf_prepare
and buf_finish. That was not clearly stated before.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Pawel Osciak <pawel@osciak.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/videobuf2-core.h | 32 +++++++++++++++++---------------
 1 file changed, 17 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 6ef2d01197d..70ace7cc608 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -270,22 +270,24 @@ struct vb2_buffer {
  *			queue setup from completing successfully; optional.
  * @buf_prepare:	called every time the buffer is queued from userspace
  *			and from the VIDIOC_PREPARE_BUF ioctl; drivers may
- *			perform any initialization required before each hardware
- *			operation in this callback; drivers that support
- *			VIDIOC_CREATE_BUFS must also validate the buffer size;
- *			if an error is returned, the buffer will not be queued
- *			in driver; optional.
+ *			perform any initialization required before each
+ *			hardware operation in this callback; drivers can
+ *			access/modify the buffer here as it is still synced for
+ *			the CPU; drivers that support VIDIOC_CREATE_BUFS must
+ *			also validate the buffer size; if an error is returned,
+ *			the buffer will not be queued in driver; optional.
  * @buf_finish:		called before every dequeue of the buffer back to
- *			userspace; drivers may perform any operations required
- *			before userspace accesses the buffer; optional. The
- *			buffer state can be one of the following: DONE and
- *			ERROR occur while streaming is in progress, and the
- *			PREPARED state occurs when the queue has been canceled
- *			and all pending buffers are being returned to their
- *			default DEQUEUED state. Typically you only have to do
- *			something if the state is VB2_BUF_STATE_DONE, since in
- *			all other cases the buffer contents will be ignored
- *			anyway.
+ *			userspace; the buffer is synced for the CPU, so drivers
+ *			can access/modify the buffer contents; drivers may
+ *			perform any operations required before userspace
+ *			accesses the buffer; optional. The buffer state can be
+ *			one of the following: DONE and ERROR occur while
+ *			streaming is in progress, and the PREPARED state occurs
+ *			when the queue has been canceled and all pending
+ *			buffers are being returned to their default DEQUEUED
+ *			state. Typically you only have to do something if the
+ *			state is VB2_BUF_STATE_DONE, since in all other cases
+ *			the buffer contents will be ignored anyway.
  * @buf_cleanup:	called once before the buffer is freed; drivers may
  *			perform any additional cleanup; optional.
  * @start_streaming:	called once to enter 'streaming' state; the driver may
-- 
cgit v1.2.3-70-g09d2


From cd474037c4a9a9c15cab46ff26ceeed1bbda6abb Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Tue, 18 Nov 2014 09:50:58 -0300
Subject: [media] vb2: replace 'write' by 'dma_dir'

The 'write' argument is very ambiguous. I first assumed that if it is 1,
then we're doing video output but instead it meant the reverse.

Since it is used to setup the dma_dir value anyway it is now replaced by
the correct dma_dir value which is unambiguous.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Pawel Osciak <pawel@osciak.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/v4l2-core/videobuf2-core.c       | 10 ++++---
 drivers/media/v4l2-core/videobuf2-dma-contig.c | 40 ++++++++++++++------------
 drivers/media/v4l2-core/videobuf2-dma-sg.c     | 13 +++++----
 drivers/media/v4l2-core/videobuf2-vmalloc.c    | 16 ++++++-----
 include/media/videobuf2-core.h                 |  6 ++--
 5 files changed, 47 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index f2e43de3dd8..573f6fb9b40 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -1358,7 +1358,8 @@ static int __qbuf_userptr(struct vb2_buffer *vb, const struct v4l2_buffer *b)
 	void *mem_priv;
 	unsigned int plane;
 	int ret;
-	int write = !V4L2_TYPE_IS_OUTPUT(q->type);
+	enum dma_data_direction dma_dir =
+		V4L2_TYPE_IS_OUTPUT(q->type) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
 	bool reacquired = vb->planes[0].mem_priv == NULL;
 
 	memset(planes, 0, sizeof(planes[0]) * vb->num_planes);
@@ -1400,7 +1401,7 @@ static int __qbuf_userptr(struct vb2_buffer *vb, const struct v4l2_buffer *b)
 		/* Acquire each plane's memory */
 		mem_priv = call_ptr_memop(vb, get_userptr, q->alloc_ctx[plane],
 				      planes[plane].m.userptr,
-				      planes[plane].length, write);
+				      planes[plane].length, dma_dir);
 		if (IS_ERR_OR_NULL(mem_priv)) {
 			dprintk(1, "failed acquiring userspace "
 						"memory for plane %d\n", plane);
@@ -1461,7 +1462,8 @@ static int __qbuf_dmabuf(struct vb2_buffer *vb, const struct v4l2_buffer *b)
 	void *mem_priv;
 	unsigned int plane;
 	int ret;
-	int write = !V4L2_TYPE_IS_OUTPUT(q->type);
+	enum dma_data_direction dma_dir =
+		V4L2_TYPE_IS_OUTPUT(q->type) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
 	bool reacquired = vb->planes[0].mem_priv == NULL;
 
 	memset(planes, 0, sizeof(planes[0]) * vb->num_planes);
@@ -1509,7 +1511,7 @@ static int __qbuf_dmabuf(struct vb2_buffer *vb, const struct v4l2_buffer *b)
 
 		/* Acquire each plane's memory */
 		mem_priv = call_ptr_memop(vb, attach_dmabuf, q->alloc_ctx[plane],
-			dbuf, planes[plane].length, write);
+			dbuf, planes[plane].length, dma_dir);
 		if (IS_ERR(mem_priv)) {
 			dprintk(1, "failed to attach dmabuf\n");
 			ret = PTR_ERR(mem_priv);
diff --git a/drivers/media/v4l2-core/videobuf2-dma-contig.c b/drivers/media/v4l2-core/videobuf2-dma-contig.c
index 4a02ade14b4..2bdffd38357 100644
--- a/drivers/media/v4l2-core/videobuf2-dma-contig.c
+++ b/drivers/media/v4l2-core/videobuf2-dma-contig.c
@@ -229,7 +229,7 @@ static int vb2_dc_mmap(void *buf_priv, struct vm_area_struct *vma)
 
 struct vb2_dc_attachment {
 	struct sg_table sgt;
-	enum dma_data_direction dir;
+	enum dma_data_direction dma_dir;
 };
 
 static int vb2_dc_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev,
@@ -264,7 +264,7 @@ static int vb2_dc_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev,
 		wr = sg_next(wr);
 	}
 
-	attach->dir = DMA_NONE;
+	attach->dma_dir = DMA_NONE;
 	dbuf_attach->priv = attach;
 
 	return 0;
@@ -282,16 +282,16 @@ static void vb2_dc_dmabuf_ops_detach(struct dma_buf *dbuf,
 	sgt = &attach->sgt;
 
 	/* release the scatterlist cache */
-	if (attach->dir != DMA_NONE)
+	if (attach->dma_dir != DMA_NONE)
 		dma_unmap_sg(db_attach->dev, sgt->sgl, sgt->orig_nents,
-			attach->dir);
+			attach->dma_dir);
 	sg_free_table(sgt);
 	kfree(attach);
 	db_attach->priv = NULL;
 }
 
 static struct sg_table *vb2_dc_dmabuf_ops_map(
-	struct dma_buf_attachment *db_attach, enum dma_data_direction dir)
+	struct dma_buf_attachment *db_attach, enum dma_data_direction dma_dir)
 {
 	struct vb2_dc_attachment *attach = db_attach->priv;
 	/* stealing dmabuf mutex to serialize map/unmap operations */
@@ -303,27 +303,27 @@ static struct sg_table *vb2_dc_dmabuf_ops_map(
 
 	sgt = &attach->sgt;
 	/* return previously mapped sg table */
-	if (attach->dir == dir) {
+	if (attach->dma_dir == dma_dir) {
 		mutex_unlock(lock);
 		return sgt;
 	}
 
 	/* release any previous cache */
-	if (attach->dir != DMA_NONE) {
+	if (attach->dma_dir != DMA_NONE) {
 		dma_unmap_sg(db_attach->dev, sgt->sgl, sgt->orig_nents,
-			attach->dir);
-		attach->dir = DMA_NONE;
+			attach->dma_dir);
+		attach->dma_dir = DMA_NONE;
 	}
 
 	/* mapping to the client with new direction */
-	ret = dma_map_sg(db_attach->dev, sgt->sgl, sgt->orig_nents, dir);
+	ret = dma_map_sg(db_attach->dev, sgt->sgl, sgt->orig_nents, dma_dir);
 	if (ret <= 0) {
 		pr_err("failed to map scatterlist\n");
 		mutex_unlock(lock);
 		return ERR_PTR(-EIO);
 	}
 
-	attach->dir = dir;
+	attach->dma_dir = dma_dir;
 
 	mutex_unlock(lock);
 
@@ -331,7 +331,7 @@ static struct sg_table *vb2_dc_dmabuf_ops_map(
 }
 
 static void vb2_dc_dmabuf_ops_unmap(struct dma_buf_attachment *db_attach,
-	struct sg_table *sgt, enum dma_data_direction dir)
+	struct sg_table *sgt, enum dma_data_direction dma_dir)
 {
 	/* nothing to be done here */
 }
@@ -460,7 +460,8 @@ static int vb2_dc_get_user_pfn(unsigned long start, int n_pages,
 }
 
 static int vb2_dc_get_user_pages(unsigned long start, struct page **pages,
-	int n_pages, struct vm_area_struct *vma, int write)
+	int n_pages, struct vm_area_struct *vma,
+	enum dma_data_direction dma_dir)
 {
 	if (vma_is_io(vma)) {
 		unsigned int i;
@@ -482,7 +483,7 @@ static int vb2_dc_get_user_pages(unsigned long start, struct page **pages,
 		int n;
 
 		n = get_user_pages(current, current->mm, start & PAGE_MASK,
-			n_pages, write, 1, pages, NULL);
+			n_pages, dma_dir == DMA_FROM_DEVICE, 1, pages, NULL);
 		/* negative error means that no page was pinned */
 		n = max(n, 0);
 		if (n != n_pages) {
@@ -551,7 +552,7 @@ static inline dma_addr_t vb2_dc_pfn_to_dma(struct device *dev, unsigned long pfn
 #endif
 
 static void *vb2_dc_get_userptr(void *alloc_ctx, unsigned long vaddr,
-	unsigned long size, int write)
+	unsigned long size, enum dma_data_direction dma_dir)
 {
 	struct vb2_dc_conf *conf = alloc_ctx;
 	struct vb2_dc_buf *buf;
@@ -582,7 +583,7 @@ static void *vb2_dc_get_userptr(void *alloc_ctx, unsigned long vaddr,
 		return ERR_PTR(-ENOMEM);
 
 	buf->dev = conf->dev;
-	buf->dma_dir = write ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+	buf->dma_dir = dma_dir;
 
 	start = vaddr & PAGE_MASK;
 	offset = vaddr & ~PAGE_MASK;
@@ -618,7 +619,8 @@ static void *vb2_dc_get_userptr(void *alloc_ctx, unsigned long vaddr,
 	}
 
 	/* extract page list from userspace mapping */
-	ret = vb2_dc_get_user_pages(start, pages, n_pages, vma, write);
+	ret = vb2_dc_get_user_pages(start, pages, n_pages, vma,
+				    dma_dir == DMA_FROM_DEVICE);
 	if (ret) {
 		unsigned long pfn;
 		if (vb2_dc_get_user_pfn(start, n_pages, vma, &pfn) == 0) {
@@ -782,7 +784,7 @@ static void vb2_dc_detach_dmabuf(void *mem_priv)
 }
 
 static void *vb2_dc_attach_dmabuf(void *alloc_ctx, struct dma_buf *dbuf,
-	unsigned long size, int write)
+	unsigned long size, enum dma_data_direction dma_dir)
 {
 	struct vb2_dc_conf *conf = alloc_ctx;
 	struct vb2_dc_buf *buf;
@@ -804,7 +806,7 @@ static void *vb2_dc_attach_dmabuf(void *alloc_ctx, struct dma_buf *dbuf,
 		return dba;
 	}
 
-	buf->dma_dir = write ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+	buf->dma_dir = dma_dir;
 	buf->size = size;
 	buf->db_attach = dba;
 
diff --git a/drivers/media/v4l2-core/videobuf2-dma-sg.c b/drivers/media/v4l2-core/videobuf2-dma-sg.c
index 9b163a440f8..6b54a14ee82 100644
--- a/drivers/media/v4l2-core/videobuf2-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf2-dma-sg.c
@@ -33,8 +33,8 @@ module_param(debug, int, 0644);
 struct vb2_dma_sg_buf {
 	void				*vaddr;
 	struct page			**pages;
-	int				write;
 	int				offset;
+	enum dma_data_direction		dma_dir;
 	struct sg_table			sg_table;
 	size_t				size;
 	unsigned int			num_pages;
@@ -97,7 +97,7 @@ static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size, gfp_t gfp_fla
 		return NULL;
 
 	buf->vaddr = NULL;
-	buf->write = 0;
+	buf->dma_dir = DMA_NONE;
 	buf->offset = 0;
 	buf->size = size;
 	/* size is already page aligned */
@@ -162,7 +162,8 @@ static inline int vma_is_io(struct vm_area_struct *vma)
 }
 
 static void *vb2_dma_sg_get_userptr(void *alloc_ctx, unsigned long vaddr,
-				    unsigned long size, int write)
+				    unsigned long size,
+				    enum dma_data_direction dma_dir)
 {
 	struct vb2_dma_sg_buf *buf;
 	unsigned long first, last;
@@ -174,7 +175,7 @@ static void *vb2_dma_sg_get_userptr(void *alloc_ctx, unsigned long vaddr,
 		return NULL;
 
 	buf->vaddr = NULL;
-	buf->write = write;
+	buf->dma_dir = dma_dir;
 	buf->offset = vaddr & ~PAGE_MASK;
 	buf->size = size;
 
@@ -221,7 +222,7 @@ static void *vb2_dma_sg_get_userptr(void *alloc_ctx, unsigned long vaddr,
 		num_pages_from_user = get_user_pages(current, current->mm,
 					     vaddr & PAGE_MASK,
 					     buf->num_pages,
-					     write,
+					     buf->dma_dir == DMA_FROM_DEVICE,
 					     1, /* force */
 					     buf->pages,
 					     NULL);
@@ -265,7 +266,7 @@ static void vb2_dma_sg_put_userptr(void *buf_priv)
 		vm_unmap_ram(buf->vaddr, buf->num_pages);
 	sg_free_table(&buf->sg_table);
 	while (--i >= 0) {
-		if (buf->write)
+		if (buf->dma_dir == DMA_FROM_DEVICE)
 			set_page_dirty_lock(buf->pages[i]);
 		if (!vma_is_io(buf->vma))
 			put_page(buf->pages[i]);
diff --git a/drivers/media/v4l2-core/videobuf2-vmalloc.c b/drivers/media/v4l2-core/videobuf2-vmalloc.c
index 313d9771b2b..fc1eb45a614 100644
--- a/drivers/media/v4l2-core/videobuf2-vmalloc.c
+++ b/drivers/media/v4l2-core/videobuf2-vmalloc.c
@@ -25,7 +25,7 @@ struct vb2_vmalloc_buf {
 	void				*vaddr;
 	struct page			**pages;
 	struct vm_area_struct		*vma;
-	int				write;
+	enum dma_data_direction		dma_dir;
 	unsigned long			size;
 	unsigned int			n_pages;
 	atomic_t			refcount;
@@ -70,7 +70,8 @@ static void vb2_vmalloc_put(void *buf_priv)
 }
 
 static void *vb2_vmalloc_get_userptr(void *alloc_ctx, unsigned long vaddr,
-				     unsigned long size, int write)
+				     unsigned long size,
+				     enum dma_data_direction dma_dir)
 {
 	struct vb2_vmalloc_buf *buf;
 	unsigned long first, last;
@@ -82,7 +83,7 @@ static void *vb2_vmalloc_get_userptr(void *alloc_ctx, unsigned long vaddr,
 	if (!buf)
 		return NULL;
 
-	buf->write = write;
+	buf->dma_dir = dma_dir;
 	offset = vaddr & ~PAGE_MASK;
 	buf->size = size;
 
@@ -107,7 +108,8 @@ static void *vb2_vmalloc_get_userptr(void *alloc_ctx, unsigned long vaddr,
 		/* current->mm->mmap_sem is taken by videobuf2 core */
 		n_pages = get_user_pages(current, current->mm,
 					 vaddr & PAGE_MASK, buf->n_pages,
-					 write, 1, /* force */
+					 dma_dir == DMA_FROM_DEVICE,
+					 1, /* force */
 					 buf->pages, NULL);
 		if (n_pages != buf->n_pages)
 			goto fail_get_user_pages;
@@ -144,7 +146,7 @@ static void vb2_vmalloc_put_userptr(void *buf_priv)
 		if (vaddr)
 			vm_unmap_ram((void *)vaddr, buf->n_pages);
 		for (i = 0; i < buf->n_pages; ++i) {
-			if (buf->write)
+			if (buf->dma_dir == DMA_FROM_DEVICE)
 				set_page_dirty_lock(buf->pages[i]);
 			put_page(buf->pages[i]);
 		}
@@ -240,7 +242,7 @@ static void vb2_vmalloc_detach_dmabuf(void *mem_priv)
 }
 
 static void *vb2_vmalloc_attach_dmabuf(void *alloc_ctx, struct dma_buf *dbuf,
-	unsigned long size, int write)
+	unsigned long size, enum dma_data_direction dma_dir)
 {
 	struct vb2_vmalloc_buf *buf;
 
@@ -252,7 +254,7 @@ static void *vb2_vmalloc_attach_dmabuf(void *alloc_ctx, struct dma_buf *dbuf,
 		return ERR_PTR(-ENOMEM);
 
 	buf->dbuf = dbuf;
-	buf->write = write;
+	buf->dma_dir = dma_dir;
 	buf->size = size;
 
 	return buf;
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 70ace7cc608..d607871749c 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -87,14 +87,16 @@ struct vb2_mem_ops {
 	struct dma_buf *(*get_dmabuf)(void *buf_priv, unsigned long flags);
 
 	void		*(*get_userptr)(void *alloc_ctx, unsigned long vaddr,
-					unsigned long size, int write);
+					unsigned long size,
+					enum dma_data_direction dma_dir);
 	void		(*put_userptr)(void *buf_priv);
 
 	void		(*prepare)(void *buf_priv);
 	void		(*finish)(void *buf_priv);
 
 	void		*(*attach_dmabuf)(void *alloc_ctx, struct dma_buf *dbuf,
-				unsigned long size, int write);
+					  unsigned long size,
+					  enum dma_data_direction dma_dir);
 	void		(*detach_dmabuf)(void *buf_priv);
 	int		(*map_dmabuf)(void *buf_priv);
 	void		(*unmap_dmabuf)(void *buf_priv);
-- 
cgit v1.2.3-70-g09d2


From d935c57e8fb6902a9ede603bb55d9e158f75f09a Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Tue, 18 Nov 2014 09:50:59 -0300
Subject: [media] vb2: add dma_dir to the alloc memop

This is needed for the next patch where the dma-sg alloc memop needs
to know the dma_dir.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Pawel Osciak <pawel@osciak.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/v4l2-core/videobuf2-core.c       | 4 +++-
 drivers/media/v4l2-core/videobuf2-dma-contig.c | 4 +++-
 drivers/media/v4l2-core/videobuf2-dma-sg.c     | 5 +++--
 drivers/media/v4l2-core/videobuf2-vmalloc.c    | 4 +++-
 include/media/videobuf2-core.h                 | 4 +++-
 5 files changed, 15 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 573f6fb9b40..7aed8f22e07 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -189,6 +189,8 @@ static void __vb2_queue_cancel(struct vb2_queue *q);
 static int __vb2_buf_mem_alloc(struct vb2_buffer *vb)
 {
 	struct vb2_queue *q = vb->vb2_queue;
+	enum dma_data_direction dma_dir =
+		V4L2_TYPE_IS_OUTPUT(q->type) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
 	void *mem_priv;
 	int plane;
 
@@ -200,7 +202,7 @@ static int __vb2_buf_mem_alloc(struct vb2_buffer *vb)
 		unsigned long size = PAGE_ALIGN(q->plane_sizes[plane]);
 
 		mem_priv = call_ptr_memop(vb, alloc, q->alloc_ctx[plane],
-				      size, q->gfp_flags);
+				      size, dma_dir, q->gfp_flags);
 		if (IS_ERR_OR_NULL(mem_priv))
 			goto free;
 
diff --git a/drivers/media/v4l2-core/videobuf2-dma-contig.c b/drivers/media/v4l2-core/videobuf2-dma-contig.c
index 2bdffd38357..c4305bf3dbe 100644
--- a/drivers/media/v4l2-core/videobuf2-dma-contig.c
+++ b/drivers/media/v4l2-core/videobuf2-dma-contig.c
@@ -155,7 +155,8 @@ static void vb2_dc_put(void *buf_priv)
 	kfree(buf);
 }
 
-static void *vb2_dc_alloc(void *alloc_ctx, unsigned long size, gfp_t gfp_flags)
+static void *vb2_dc_alloc(void *alloc_ctx, unsigned long size,
+			  enum dma_data_direction dma_dir, gfp_t gfp_flags)
 {
 	struct vb2_dc_conf *conf = alloc_ctx;
 	struct device *dev = conf->dev;
@@ -176,6 +177,7 @@ static void *vb2_dc_alloc(void *alloc_ctx, unsigned long size, gfp_t gfp_flags)
 	/* Prevent the device from being released while the buffer is used */
 	buf->dev = get_device(dev);
 	buf->size = size;
+	buf->dma_dir = dma_dir;
 
 	buf->handler.refcount = &buf->refcount;
 	buf->handler.put = vb2_dc_put;
diff --git a/drivers/media/v4l2-core/videobuf2-dma-sg.c b/drivers/media/v4l2-core/videobuf2-dma-sg.c
index 6b54a14ee82..2529b831725 100644
--- a/drivers/media/v4l2-core/videobuf2-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf2-dma-sg.c
@@ -86,7 +86,8 @@ static int vb2_dma_sg_alloc_compacted(struct vb2_dma_sg_buf *buf,
 	return 0;
 }
 
-static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size, gfp_t gfp_flags)
+static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size,
+			      enum dma_data_direction dma_dir, gfp_t gfp_flags)
 {
 	struct vb2_dma_sg_buf *buf;
 	int ret;
@@ -97,7 +98,7 @@ static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size, gfp_t gfp_fla
 		return NULL;
 
 	buf->vaddr = NULL;
-	buf->dma_dir = DMA_NONE;
+	buf->dma_dir = dma_dir;
 	buf->offset = 0;
 	buf->size = size;
 	/* size is already page aligned */
diff --git a/drivers/media/v4l2-core/videobuf2-vmalloc.c b/drivers/media/v4l2-core/videobuf2-vmalloc.c
index fc1eb45a614..bba2460961d 100644
--- a/drivers/media/v4l2-core/videobuf2-vmalloc.c
+++ b/drivers/media/v4l2-core/videobuf2-vmalloc.c
@@ -35,7 +35,8 @@ struct vb2_vmalloc_buf {
 
 static void vb2_vmalloc_put(void *buf_priv);
 
-static void *vb2_vmalloc_alloc(void *alloc_ctx, unsigned long size, gfp_t gfp_flags)
+static void *vb2_vmalloc_alloc(void *alloc_ctx, unsigned long size,
+			       enum dma_data_direction dma_dir, gfp_t gfp_flags)
 {
 	struct vb2_vmalloc_buf *buf;
 
@@ -45,6 +46,7 @@ static void *vb2_vmalloc_alloc(void *alloc_ctx, unsigned long size, gfp_t gfp_fl
 
 	buf->size = size;
 	buf->vaddr = vmalloc_user(buf->size);
+	buf->dma_dir = dma_dir;
 	buf->handler.refcount = &buf->refcount;
 	buf->handler.put = vb2_vmalloc_put;
 	buf->handler.arg = buf;
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index d607871749c..bd2cec2d6c3 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -82,7 +82,9 @@ struct vb2_threadio_data;
  *				  unmap_dmabuf.
  */
 struct vb2_mem_ops {
-	void		*(*alloc)(void *alloc_ctx, unsigned long size, gfp_t gfp_flags);
+	void		*(*alloc)(void *alloc_ctx, unsigned long size,
+				  enum dma_data_direction dma_dir,
+				  gfp_t gfp_flags);
 	void		(*put)(void *buf_priv);
 	struct dma_buf *(*get_dmabuf)(void *buf_priv, unsigned long flags);
 
-- 
cgit v1.2.3-70-g09d2


From 0c3a14c177aa85afb991e7c2be3921aa9a52a893 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Tue, 18 Nov 2014 09:51:01 -0300
Subject: [media] vb2-dma-sg: add allocation context to dma-sg

Require that dma-sg also uses an allocation context. This is in preparation
for adding prepare/finish memops to sync the memory between DMA and CPU.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Pawel Osciak <pawel@osciak.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/pci/cx23885/cx23885-417.c         |  1 +
 drivers/media/pci/cx23885/cx23885-core.c        | 10 +++++++-
 drivers/media/pci/cx23885/cx23885-dvb.c         |  1 +
 drivers/media/pci/cx23885/cx23885-vbi.c         |  1 +
 drivers/media/pci/cx23885/cx23885-video.c       |  1 +
 drivers/media/pci/cx23885/cx23885.h             |  1 +
 drivers/media/pci/saa7134/saa7134-core.c        | 18 ++++++++++----
 drivers/media/pci/saa7134/saa7134-ts.c          |  1 +
 drivers/media/pci/saa7134/saa7134-vbi.c         |  1 +
 drivers/media/pci/saa7134/saa7134-video.c       |  1 +
 drivers/media/pci/saa7134/saa7134.h             |  1 +
 drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c  | 10 ++++++++
 drivers/media/pci/solo6x10/solo6x10.h           |  1 +
 drivers/media/pci/tw68/tw68-core.c              | 15 +++++++++---
 drivers/media/pci/tw68/tw68-video.c             |  1 +
 drivers/media/pci/tw68/tw68.h                   |  1 +
 drivers/media/platform/marvell-ccic/mcam-core.c | 13 +++++++++-
 drivers/media/platform/marvell-ccic/mcam-core.h |  1 +
 drivers/media/v4l2-core/videobuf2-dma-sg.c      | 32 +++++++++++++++++++++++++
 include/media/videobuf2-dma-sg.h                |  3 +++
 20 files changed, 104 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/media/pci/cx23885/cx23885-417.c b/drivers/media/pci/cx23885/cx23885-417.c
index 3948db386fb..d72a3ec348e 100644
--- a/drivers/media/pci/cx23885/cx23885-417.c
+++ b/drivers/media/pci/cx23885/cx23885-417.c
@@ -1148,6 +1148,7 @@ static int queue_setup(struct vb2_queue *q, const struct v4l2_format *fmt,
 	dev->ts1.ts_packet_count = mpeglines;
 	*num_planes = 1;
 	sizes[0] = mpeglinesize * mpeglines;
+	alloc_ctxs[0] = dev->alloc_ctx;
 	*num_buffers = mpegbufs;
 	return 0;
 }
diff --git a/drivers/media/pci/cx23885/cx23885-core.c b/drivers/media/pci/cx23885/cx23885-core.c
index 331eddac722..d452b5c076e 100644
--- a/drivers/media/pci/cx23885/cx23885-core.c
+++ b/drivers/media/pci/cx23885/cx23885-core.c
@@ -1997,9 +1997,14 @@ static int cx23885_initdev(struct pci_dev *pci_dev,
 	if (!pci_dma_supported(pci_dev, 0xffffffff)) {
 		printk("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name);
 		err = -EIO;
-		goto fail_irq;
+		goto fail_context;
 	}
 
+	dev->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev);
+	if (IS_ERR(dev->alloc_ctx)) {
+		err = PTR_ERR(dev->alloc_ctx);
+		goto fail_context;
+	}
 	err = request_irq(pci_dev->irq, cx23885_irq,
 			  IRQF_SHARED, dev->name, dev);
 	if (err < 0) {
@@ -2028,6 +2033,8 @@ static int cx23885_initdev(struct pci_dev *pci_dev,
 	return 0;
 
 fail_irq:
+	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
+fail_context:
 	cx23885_dev_unregister(dev);
 fail_ctrl:
 	v4l2_ctrl_handler_free(hdl);
@@ -2053,6 +2060,7 @@ static void cx23885_finidev(struct pci_dev *pci_dev)
 	free_irq(pci_dev->irq, dev);
 
 	cx23885_dev_unregister(dev);
+	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
 	v4l2_ctrl_handler_free(&dev->ctrl_handler);
 	v4l2_device_unregister(v4l2_dev);
 	kfree(dev);
diff --git a/drivers/media/pci/cx23885/cx23885-dvb.c b/drivers/media/pci/cx23885/cx23885-dvb.c
index 1ed92eeb46d..44fafba65c6 100644
--- a/drivers/media/pci/cx23885/cx23885-dvb.c
+++ b/drivers/media/pci/cx23885/cx23885-dvb.c
@@ -102,6 +102,7 @@ static int queue_setup(struct vb2_queue *q, const struct v4l2_format *fmt,
 	port->ts_packet_count = 32;
 	*num_planes = 1;
 	sizes[0] = port->ts_packet_size * port->ts_packet_count;
+	alloc_ctxs[0] = port->dev->alloc_ctx;
 	*num_buffers = 32;
 	return 0;
 }
diff --git a/drivers/media/pci/cx23885/cx23885-vbi.c b/drivers/media/pci/cx23885/cx23885-vbi.c
index a7c6ef8f3ea..1d339a69f0c 100644
--- a/drivers/media/pci/cx23885/cx23885-vbi.c
+++ b/drivers/media/pci/cx23885/cx23885-vbi.c
@@ -132,6 +132,7 @@ static int queue_setup(struct vb2_queue *q, const struct v4l2_format *fmt,
 		lines = VBI_NTSC_LINE_COUNT;
 	*num_planes = 1;
 	sizes[0] = lines * VBI_LINE_LENGTH * 2;
+	alloc_ctxs[0] = dev->alloc_ctx;
 	return 0;
 }
 
diff --git a/drivers/media/pci/cx23885/cx23885-video.c b/drivers/media/pci/cx23885/cx23885-video.c
index 091f5dbe65a..371eecfe7b3 100644
--- a/drivers/media/pci/cx23885/cx23885-video.c
+++ b/drivers/media/pci/cx23885/cx23885-video.c
@@ -323,6 +323,7 @@ static int queue_setup(struct vb2_queue *q, const struct v4l2_format *fmt,
 
 	*num_planes = 1;
 	sizes[0] = (dev->fmt->depth * dev->width * dev->height) >> 3;
+	alloc_ctxs[0] = dev->alloc_ctx;
 	return 0;
 }
 
diff --git a/drivers/media/pci/cx23885/cx23885.h b/drivers/media/pci/cx23885/cx23885.h
index cf4efa461ce..f55cd12da0f 100644
--- a/drivers/media/pci/cx23885/cx23885.h
+++ b/drivers/media/pci/cx23885/cx23885.h
@@ -425,6 +425,7 @@ struct cx23885_dev {
 	struct vb2_queue           vb2_vidq;
 	struct cx23885_dmaqueue    vbiq;
 	struct vb2_queue           vb2_vbiq;
+	void			   *alloc_ctx;
 
 	spinlock_t                 slock;
 
diff --git a/drivers/media/pci/saa7134/saa7134-core.c b/drivers/media/pci/saa7134/saa7134-core.c
index 236ed725f93..a349e964e0b 100644
--- a/drivers/media/pci/saa7134/saa7134-core.c
+++ b/drivers/media/pci/saa7134/saa7134-core.c
@@ -1001,13 +1001,18 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 	saa7134_board_init1(dev);
 	saa7134_hwinit1(dev);
 
+	dev->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev);
+	if (IS_ERR(dev->alloc_ctx)) {
+		err = PTR_ERR(dev->alloc_ctx);
+		goto fail3;
+	}
 	/* get irq */
 	err = request_irq(pci_dev->irq, saa7134_irq,
 			  IRQF_SHARED, dev->name, dev);
 	if (err < 0) {
 		printk(KERN_ERR "%s: can't get IRQ %d\n",
 		       dev->name,pci_dev->irq);
-		goto fail3;
+		goto fail4;
 	}
 
 	/* wait a bit, register i2c bus */
@@ -1065,7 +1070,7 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 	if (err < 0) {
 		printk(KERN_INFO "%s: can't register video device\n",
 		       dev->name);
-		goto fail4;
+		goto fail5;
 	}
 	printk(KERN_INFO "%s: registered device %s [v4l2]\n",
 	       dev->name, video_device_node_name(dev->video_dev));
@@ -1078,7 +1083,7 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 	err = video_register_device(dev->vbi_dev,VFL_TYPE_VBI,
 				    vbi_nr[dev->nr]);
 	if (err < 0)
-		goto fail4;
+		goto fail5;
 	printk(KERN_INFO "%s: registered device %s\n",
 	       dev->name, video_device_node_name(dev->vbi_dev));
 
@@ -1089,7 +1094,7 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 		err = video_register_device(dev->radio_dev,VFL_TYPE_RADIO,
 					    radio_nr[dev->nr]);
 		if (err < 0)
-			goto fail4;
+			goto fail5;
 		printk(KERN_INFO "%s: registered device %s\n",
 		       dev->name, video_device_node_name(dev->radio_dev));
 	}
@@ -1103,10 +1108,12 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 	request_submodules(dev);
 	return 0;
 
- fail4:
+ fail5:
 	saa7134_unregister_video(dev);
 	saa7134_i2c_unregister(dev);
 	free_irq(pci_dev->irq, dev);
+ fail4:
+	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
  fail3:
 	saa7134_hwfini(dev);
 	iounmap(dev->lmmio);
@@ -1173,6 +1180,7 @@ static void saa7134_finidev(struct pci_dev *pci_dev)
 
 	/* release resources */
 	free_irq(pci_dev->irq, dev);
+	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
 	iounmap(dev->lmmio);
 	release_mem_region(pci_resource_start(pci_dev,0),
 			   pci_resource_len(pci_dev,0));
diff --git a/drivers/media/pci/saa7134/saa7134-ts.c b/drivers/media/pci/saa7134/saa7134-ts.c
index bd25323bd94..8eff4a7d8ba 100644
--- a/drivers/media/pci/saa7134/saa7134-ts.c
+++ b/drivers/media/pci/saa7134/saa7134-ts.c
@@ -142,6 +142,7 @@ int saa7134_ts_queue_setup(struct vb2_queue *q, const struct v4l2_format *fmt,
 		*nbuffers = 3;
 	*nplanes = 1;
 	sizes[0] = size;
+	alloc_ctxs[0] = dev->alloc_ctx;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(saa7134_ts_queue_setup);
diff --git a/drivers/media/pci/saa7134/saa7134-vbi.c b/drivers/media/pci/saa7134/saa7134-vbi.c
index 4f0b1012e4f..e2cc684a7c1 100644
--- a/drivers/media/pci/saa7134/saa7134-vbi.c
+++ b/drivers/media/pci/saa7134/saa7134-vbi.c
@@ -156,6 +156,7 @@ static int queue_setup(struct vb2_queue *q, const struct v4l2_format *fmt,
 	*nbuffers = saa7134_buffer_count(size, *nbuffers);
 	*nplanes = 1;
 	sizes[0] = size;
+	alloc_ctxs[0] = dev->alloc_ctx;
 	return 0;
 }
 
diff --git a/drivers/media/pci/saa7134/saa7134-video.c b/drivers/media/pci/saa7134/saa7134-video.c
index fc4a427cb51..ba029953db9 100644
--- a/drivers/media/pci/saa7134/saa7134-video.c
+++ b/drivers/media/pci/saa7134/saa7134-video.c
@@ -932,6 +932,7 @@ static int queue_setup(struct vb2_queue *q, const struct v4l2_format *fmt,
 	*nbuffers = saa7134_buffer_count(size, *nbuffers);
 	*nplanes = 1;
 	sizes[0] = size;
+	alloc_ctxs[0] = dev->alloc_ctx;
 	return 0;
 }
 
diff --git a/drivers/media/pci/saa7134/saa7134.h b/drivers/media/pci/saa7134/saa7134.h
index 1a82dd07205..c644c7da685 100644
--- a/drivers/media/pci/saa7134/saa7134.h
+++ b/drivers/media/pci/saa7134/saa7134.h
@@ -588,6 +588,7 @@ struct saa7134_dev {
 
 
 	/* video+ts+vbi capture */
+	void			   *alloc_ctx;
 	struct saa7134_dmaqueue    video_q;
 	struct vb2_queue           video_vbq;
 	struct saa7134_dmaqueue    vbi_q;
diff --git a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c b/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c
index 30e09d935ce..4f6bfba5806 100644
--- a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c
+++ b/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c
@@ -718,7 +718,10 @@ static int solo_enc_queue_setup(struct vb2_queue *q,
 				unsigned int *num_planes, unsigned int sizes[],
 				void *alloc_ctxs[])
 {
+	struct solo_enc_dev *solo_enc = vb2_get_drv_priv(q);
+
 	sizes[0] = FRAME_BUF_SIZE;
+	alloc_ctxs[0] = solo_enc->alloc_ctx;
 	*num_planes = 1;
 
 	if (*num_buffers < MIN_VID_BUFFERS)
@@ -1266,6 +1269,11 @@ static struct solo_enc_dev *solo_enc_alloc(struct solo_dev *solo_dev,
 		return ERR_PTR(-ENOMEM);
 
 	hdl = &solo_enc->hdl;
+	solo_enc->alloc_ctx = vb2_dma_sg_init_ctx(&solo_dev->pdev->dev);
+	if (IS_ERR(solo_enc->alloc_ctx)) {
+		ret = PTR_ERR(solo_enc->alloc_ctx);
+		goto hdl_free;
+	}
 	v4l2_ctrl_handler_init(hdl, 10);
 	v4l2_ctrl_new_std(hdl, &solo_ctrl_ops,
 			V4L2_CID_BRIGHTNESS, 0, 255, 1, 128);
@@ -1369,6 +1377,7 @@ pci_free:
 			solo_enc->desc_items, solo_enc->desc_dma);
 hdl_free:
 	v4l2_ctrl_handler_free(hdl);
+	vb2_dma_sg_cleanup_ctx(solo_enc->alloc_ctx);
 	kfree(solo_enc);
 	return ERR_PTR(ret);
 }
@@ -1383,6 +1392,7 @@ static void solo_enc_free(struct solo_enc_dev *solo_enc)
 			solo_enc->desc_items, solo_enc->desc_dma);
 	video_unregister_device(solo_enc->vfd);
 	v4l2_ctrl_handler_free(&solo_enc->hdl);
+	vb2_dma_sg_cleanup_ctx(solo_enc->alloc_ctx);
 	kfree(solo_enc);
 }
 
diff --git a/drivers/media/pci/solo6x10/solo6x10.h b/drivers/media/pci/solo6x10/solo6x10.h
index 72017b7f0a7..bd8edfa319b 100644
--- a/drivers/media/pci/solo6x10/solo6x10.h
+++ b/drivers/media/pci/solo6x10/solo6x10.h
@@ -180,6 +180,7 @@ struct solo_enc_dev {
 	u32			sequence;
 	struct vb2_queue	vidq;
 	struct list_head	vidq_active;
+	void			*alloc_ctx;
 	int			desc_count;
 	int			desc_nelts;
 	struct solo_p2m_desc	*desc_items;
diff --git a/drivers/media/pci/tw68/tw68-core.c b/drivers/media/pci/tw68/tw68-core.c
index 63f0b64057c..c135165a8b2 100644
--- a/drivers/media/pci/tw68/tw68-core.c
+++ b/drivers/media/pci/tw68/tw68-core.c
@@ -304,13 +304,19 @@ static int tw68_initdev(struct pci_dev *pci_dev,
 	/* Then do any initialisation wanted before interrupts are on */
 	tw68_hw_init1(dev);
 
+	dev->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev);
+	if (IS_ERR(dev->alloc_ctx)) {
+		err = PTR_ERR(dev->alloc_ctx);
+		goto fail3;
+	}
+
 	/* get irq */
 	err = devm_request_irq(&pci_dev->dev, pci_dev->irq, tw68_irq,
 			  IRQF_SHARED, dev->name, dev);
 	if (err < 0) {
 		pr_err("%s: can't get IRQ %d\n",
 		       dev->name, pci_dev->irq);
-		goto fail3;
+		goto fail4;
 	}
 
 	/*
@@ -324,7 +330,7 @@ static int tw68_initdev(struct pci_dev *pci_dev,
 	if (err < 0) {
 		pr_err("%s: can't register video device\n",
 		       dev->name);
-		goto fail4;
+		goto fail5;
 	}
 	tw_setl(TW68_INTMASK, dev->pci_irqmask);
 
@@ -333,8 +339,10 @@ static int tw68_initdev(struct pci_dev *pci_dev,
 
 	return 0;
 
-fail4:
+fail5:
 	video_unregister_device(&dev->vdev);
+fail4:
+	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
 fail3:
 	iounmap(dev->lmmio);
 fail2:
@@ -358,6 +366,7 @@ static void tw68_finidev(struct pci_dev *pci_dev)
 	/* unregister */
 	video_unregister_device(&dev->vdev);
 	v4l2_ctrl_handler_free(&dev->hdl);
+	vb2_dma_sg_cleanup_ctx(dev->alloc_ctx);
 
 	/* release resources */
 	iounmap(dev->lmmio);
diff --git a/drivers/media/pci/tw68/tw68-video.c b/drivers/media/pci/tw68/tw68-video.c
index 5c94ac7c88d..50dcce6251f 100644
--- a/drivers/media/pci/tw68/tw68-video.c
+++ b/drivers/media/pci/tw68/tw68-video.c
@@ -384,6 +384,7 @@ static int tw68_queue_setup(struct vb2_queue *q, const struct v4l2_format *fmt,
 	unsigned tot_bufs = q->num_buffers + *num_buffers;
 
 	sizes[0] = (dev->fmt->depth * dev->width * dev->height) >> 3;
+	alloc_ctxs[0] = dev->alloc_ctx;
 	/*
 	 * We allow create_bufs, but only if the sizeimage is the same as the
 	 * current sizeimage. The tw68_buffer_count calculation becomes quite
diff --git a/drivers/media/pci/tw68/tw68.h b/drivers/media/pci/tw68/tw68.h
index 2c8abe26b13..7a7501bd165 100644
--- a/drivers/media/pci/tw68/tw68.h
+++ b/drivers/media/pci/tw68/tw68.h
@@ -181,6 +181,7 @@ struct tw68_dev {
 	unsigned		field;
 	struct vb2_queue	vidq;
 	struct list_head	active;
+	void			*alloc_ctx;
 
 	/* various v4l controls */
 	const struct tw68_tvnorm *tvnorm;	/* video */
diff --git a/drivers/media/platform/marvell-ccic/mcam-core.c b/drivers/media/platform/marvell-ccic/mcam-core.c
index f0eeb6cd262..c3ff5388aeb 100644
--- a/drivers/media/platform/marvell-ccic/mcam-core.c
+++ b/drivers/media/platform/marvell-ccic/mcam-core.c
@@ -1079,6 +1079,8 @@ static int mcam_vb_queue_setup(struct vb2_queue *vq,
 		*nbufs = minbufs;
 	if (cam->buffer_mode == B_DMA_contig)
 		alloc_ctxs[0] = cam->vb_alloc_ctx;
+	else if (cam->buffer_mode == B_DMA_sg)
+		alloc_ctxs[0] = cam->vb_alloc_ctx_sg;
 	return 0;
 }
 
@@ -1286,10 +1288,12 @@ static int mcam_setup_vb2(struct mcam_camera *cam)
 		vq->ops = &mcam_vb2_ops;
 		vq->mem_ops = &vb2_dma_contig_memops;
 		vq->buf_struct_size = sizeof(struct mcam_vb_buffer);
-		cam->vb_alloc_ctx = vb2_dma_contig_init_ctx(cam->dev);
 		vq->io_modes = VB2_MMAP | VB2_USERPTR;
 		cam->dma_setup = mcam_ctlr_dma_contig;
 		cam->frame_complete = mcam_dma_contig_done;
+		cam->vb_alloc_ctx = vb2_dma_contig_init_ctx(cam->dev);
+		if (IS_ERR(cam->vb_alloc_ctx))
+			return PTR_ERR(cam->vb_alloc_ctx);
 #endif
 		break;
 	case B_DMA_sg:
@@ -1300,6 +1304,9 @@ static int mcam_setup_vb2(struct mcam_camera *cam)
 		vq->io_modes = VB2_MMAP | VB2_USERPTR;
 		cam->dma_setup = mcam_ctlr_dma_sg;
 		cam->frame_complete = mcam_dma_sg_done;
+		cam->vb_alloc_ctx_sg = vb2_dma_sg_init_ctx(cam->dev);
+		if (IS_ERR(cam->vb_alloc_ctx_sg))
+			return PTR_ERR(cam->vb_alloc_ctx_sg);
 #endif
 		break;
 	case B_vmalloc:
@@ -1325,6 +1332,10 @@ static void mcam_cleanup_vb2(struct mcam_camera *cam)
 	if (cam->buffer_mode == B_DMA_contig)
 		vb2_dma_contig_cleanup_ctx(cam->vb_alloc_ctx);
 #endif
+#ifdef MCAM_MODE_DMA_SG
+	if (cam->buffer_mode == B_DMA_sg)
+		vb2_dma_sg_cleanup_ctx(cam->vb_alloc_ctx_sg);
+#endif
 }
 
 
diff --git a/drivers/media/platform/marvell-ccic/mcam-core.h b/drivers/media/platform/marvell-ccic/mcam-core.h
index 60a8e1cfeff..aa0c6eac254 100644
--- a/drivers/media/platform/marvell-ccic/mcam-core.h
+++ b/drivers/media/platform/marvell-ccic/mcam-core.h
@@ -176,6 +176,7 @@ struct mcam_camera {
 	/* DMA buffers - DMA modes */
 	struct mcam_vb_buffer *vb_bufs[MAX_DMA_BUFS];
 	struct vb2_alloc_ctx *vb_alloc_ctx;
+	struct vb2_alloc_ctx *vb_alloc_ctx_sg;
 
 	/* Mode-specific ops, set at open time */
 	void (*dma_setup)(struct mcam_camera *cam);
diff --git a/drivers/media/v4l2-core/videobuf2-dma-sg.c b/drivers/media/v4l2-core/videobuf2-dma-sg.c
index 2529b831725..2bf13dc4df3 100644
--- a/drivers/media/v4l2-core/videobuf2-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf2-dma-sg.c
@@ -30,7 +30,12 @@ module_param(debug, int, 0644);
 			printk(KERN_DEBUG "vb2-dma-sg: " fmt, ## arg);	\
 	} while (0)
 
+struct vb2_dma_sg_conf {
+	struct device		*dev;
+};
+
 struct vb2_dma_sg_buf {
+	struct device			*dev;
 	void				*vaddr;
 	struct page			**pages;
 	int				offset;
@@ -89,10 +94,13 @@ static int vb2_dma_sg_alloc_compacted(struct vb2_dma_sg_buf *buf,
 static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size,
 			      enum dma_data_direction dma_dir, gfp_t gfp_flags)
 {
+	struct vb2_dma_sg_conf *conf = alloc_ctx;
 	struct vb2_dma_sg_buf *buf;
 	int ret;
 	int num_pages;
 
+	if (WARN_ON(alloc_ctx == NULL))
+		return NULL;
 	buf = kzalloc(sizeof *buf, GFP_KERNEL);
 	if (!buf)
 		return NULL;
@@ -118,6 +126,8 @@ static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size,
 	if (ret)
 		goto fail_table_alloc;
 
+	/* Prevent the device from being released while the buffer is used */
+	buf->dev = get_device(conf->dev);
 	buf->handler.refcount = &buf->refcount;
 	buf->handler.put = vb2_dma_sg_put;
 	buf->handler.arg = buf;
@@ -153,6 +163,7 @@ static void vb2_dma_sg_put(void *buf_priv)
 		while (--i >= 0)
 			__free_page(buf->pages[i]);
 		kfree(buf->pages);
+		put_device(buf->dev);
 		kfree(buf);
 	}
 }
@@ -356,6 +367,27 @@ const struct vb2_mem_ops vb2_dma_sg_memops = {
 };
 EXPORT_SYMBOL_GPL(vb2_dma_sg_memops);
 
+void *vb2_dma_sg_init_ctx(struct device *dev)
+{
+	struct vb2_dma_sg_conf *conf;
+
+	conf = kzalloc(sizeof(*conf), GFP_KERNEL);
+	if (!conf)
+		return ERR_PTR(-ENOMEM);
+
+	conf->dev = dev;
+
+	return conf;
+}
+EXPORT_SYMBOL_GPL(vb2_dma_sg_init_ctx);
+
+void vb2_dma_sg_cleanup_ctx(void *alloc_ctx)
+{
+	if (!IS_ERR_OR_NULL(alloc_ctx))
+		kfree(alloc_ctx);
+}
+EXPORT_SYMBOL_GPL(vb2_dma_sg_cleanup_ctx);
+
 MODULE_DESCRIPTION("dma scatter/gather memory handling routines for videobuf2");
 MODULE_AUTHOR("Andrzej Pietrasiewicz");
 MODULE_LICENSE("GPL");
diff --git a/include/media/videobuf2-dma-sg.h b/include/media/videobuf2-dma-sg.h
index 7b89852779a..14ce3068b64 100644
--- a/include/media/videobuf2-dma-sg.h
+++ b/include/media/videobuf2-dma-sg.h
@@ -21,6 +21,9 @@ static inline struct sg_table *vb2_dma_sg_plane_desc(
 	return (struct sg_table *)vb2_plane_cookie(vb, plane_no);
 }
 
+void *vb2_dma_sg_init_ctx(struct device *dev);
+void vb2_dma_sg_cleanup_ctx(void *alloc_ctx);
+
 extern const struct vb2_mem_ops vb2_dma_sg_memops;
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From 2d4e2d020516632288e8c8d1f8be2f3042d6b8de Mon Sep 17 00:00:00 2001
From: Bard Liao <bardliao@realtek.com>
Date: Tue, 18 Nov 2014 16:50:18 +0800
Subject: ASoC: rt5645: multiple JD mode support

There are 3 JD modes in RT5645. This patch configure register
values according to platform data.

Signed-off-by: Bard Liao <bardliao@realtek.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/rt5645.h    |  1 +
 sound/soc/codecs/rt5645.c | 35 ++++++++++++++++++++++++++++++++++-
 sound/soc/codecs/rt5645.h |  7 +++++++
 3 files changed, 42 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/rt5645.h b/include/sound/rt5645.h
index 937f421bc66..120d9610054 100644
--- a/include/sound/rt5645.h
+++ b/include/sound/rt5645.h
@@ -26,6 +26,7 @@ struct rt5645_platform_data {
 
 	/* true if codec's jd function is used */
 	bool en_jd_func;
+	unsigned int jd_mode;
 };
 
 #endif
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index ef88b506a01..6e9cd8e743a 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -2239,7 +2239,8 @@ static int rt5645_jack_detect(struct snd_soc_codec *codec)
 
 		snd_soc_dapm_disable_pin(&codec->dapm, "micbias1");
 		snd_soc_dapm_disable_pin(&codec->dapm, "micbias2");
-		snd_soc_dapm_disable_pin(&codec->dapm, "LDO2");
+		if (rt5645->pdata.jd_mode == 0)
+			snd_soc_dapm_disable_pin(&codec->dapm, "LDO2");
 		snd_soc_dapm_disable_pin(&codec->dapm, "Mic Det Power");
 		snd_soc_dapm_sync(&codec->dapm);
 	}
@@ -2543,6 +2544,38 @@ static int rt5645_i2c_probe(struct i2c_client *i2c,
 			RT5645_IRQ_CLK_INT, RT5645_IRQ_CLK_INT);
 	}
 
+	if (rt5645->pdata.jd_mode) {
+		regmap_update_bits(rt5645->regmap, RT5645_IRQ_CTRL2,
+				   RT5645_IRQ_JD_1_1_EN, RT5645_IRQ_JD_1_1_EN);
+		regmap_update_bits(rt5645->regmap, RT5645_GEN_CTRL3,
+				   RT5645_JD_PSV_MODE, RT5645_JD_PSV_MODE);
+		regmap_update_bits(rt5645->regmap, RT5645_HPO_MIXER,
+				   RT5645_IRQ_PSV_MODE, RT5645_IRQ_PSV_MODE);
+		regmap_update_bits(rt5645->regmap, RT5645_MICBIAS,
+				   RT5645_MIC2_OVCD_EN, RT5645_MIC2_OVCD_EN);
+		regmap_update_bits(rt5645->regmap, RT5645_GPIO_CTRL1,
+				   RT5645_GP1_PIN_IRQ, RT5645_GP1_PIN_IRQ);
+		switch (rt5645->pdata.jd_mode) {
+		case 1:
+			regmap_update_bits(rt5645->regmap, RT5645_A_JD_CTRL1,
+					   RT5645_JD1_MODE_MASK,
+					   RT5645_JD1_MODE_0);
+			break;
+		case 2:
+			regmap_update_bits(rt5645->regmap, RT5645_A_JD_CTRL1,
+					   RT5645_JD1_MODE_MASK,
+					   RT5645_JD1_MODE_1);
+			break;
+		case 3:
+			regmap_update_bits(rt5645->regmap, RT5645_A_JD_CTRL1,
+					   RT5645_JD1_MODE_MASK,
+					   RT5645_JD1_MODE_2);
+			break;
+		default:
+			break;
+		}
+	}
+
 	if (rt5645->i2c->irq) {
 		ret = request_threaded_irq(rt5645->i2c->irq, NULL, rt5645_irq,
 			IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
diff --git a/sound/soc/codecs/rt5645.h b/sound/soc/codecs/rt5645.h
index c72220abdbc..a815e36a2bd 100644
--- a/sound/soc/codecs/rt5645.h
+++ b/sound/soc/codecs/rt5645.h
@@ -594,6 +594,7 @@
 #define RT5645_M_DAC1_HM_SFT			14
 #define RT5645_M_HPVOL_HM			(0x1 << 13)
 #define RT5645_M_HPVOL_HM_SFT			13
+#define RT5645_IRQ_PSV_MODE			(0x1 << 12)
 
 /* SPK Left Mixer Control (0x46) */
 #define RT5645_G_RM_L_SM_L_MASK			(0x3 << 14)
@@ -1350,6 +1351,10 @@
 #define RT5645_PWR_CLK25M_PU			(0x1 << 4)
 #define RT5645_IRQ_CLK_MCLK			(0x0 << 3)
 #define RT5645_IRQ_CLK_INT			(0x1 << 3)
+#define RT5645_JD1_MODE_MASK			(0x3 << 0)
+#define RT5645_JD1_MODE_0			(0x0 << 0)
+#define RT5645_JD1_MODE_1			(0x1 << 0)
+#define RT5645_JD1_MODE_2			(0x2 << 0)
 
 /* VAD Control 4 (0x9d) */
 #define RT5645_VAD_SEL_MASK			(0x3 << 8)
@@ -1638,6 +1643,7 @@
 #define RT5645_OT_P_SFT				10
 #define RT5645_OT_P_NOR				(0x0 << 10)
 #define RT5645_OT_P_INV				(0x1 << 10)
+#define RT5645_IRQ_JD_1_1_EN			(0x1 << 9)
 
 /* IRQ Control 2 (0xbe) */
 #define RT5645_IRQ_MB1_OC_MASK			(0x1 << 15)
@@ -2120,6 +2126,7 @@ enum {
 #define RT5645_RXDP2_SEL_SFT			(3)
 
 /* General Control3 (0xfc) */
+#define RT5645_JD_PSV_MODE			(0x1 << 12)
 #define RT5645_IRQ_CLK_GATE_CTRL		(0x1 << 11)
 #define RT5645_MICINDET_MANU			(0x1 << 7)
 
-- 
cgit v1.2.3-70-g09d2


From 93b0f3eeebdce6f32417187b5d24ea218a3e7fb4 Mon Sep 17 00:00:00 2001
From: Jean-Francois Moine <moinejf@free.fr>
Date: Tue, 25 Nov 2014 13:16:12 +0100
Subject: ASoC: core: add multi-codec support in DT

This patch exports a core function which handles the DT description
of multi-codec links (as: "sound-dai = <&hdmi 0>, <&spdif_codec>;")
and creates a CODEC component array in the DAI link.

Signed-off-by: Jean-Francois Moine <moinejf@free.fr>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  |   3 ++
 sound/soc/soc-core.c | 110 ++++++++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 98 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 7ba7130037a..2750e6ad012 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1451,6 +1451,9 @@ unsigned int snd_soc_of_parse_daifmt(struct device_node *np,
 				     struct device_node **framemaster);
 int snd_soc_of_get_dai_name(struct device_node *of_node,
 			    const char **dai_name);
+int snd_soc_of_get_dai_link_codecs(struct device *dev,
+				   struct device_node *of_node,
+				   struct snd_soc_dai_link *dai_link);
 
 #include <sound/soc-dai.h>
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 4c8f8a23a0e..72a3ad04704 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -4750,36 +4750,30 @@ unsigned int snd_soc_of_parse_daifmt(struct device_node *np,
 }
 EXPORT_SYMBOL_GPL(snd_soc_of_parse_daifmt);
 
-int snd_soc_of_get_dai_name(struct device_node *of_node,
-			    const char **dai_name)
+static int snd_soc_get_dai_name(struct of_phandle_args *args,
+				const char **dai_name)
 {
 	struct snd_soc_component *pos;
-	struct of_phandle_args args;
-	int ret;
-
-	ret = of_parse_phandle_with_args(of_node, "sound-dai",
-					 "#sound-dai-cells", 0, &args);
-	if (ret)
-		return ret;
-
-	ret = -EPROBE_DEFER;
+	int ret = -EPROBE_DEFER;
 
 	mutex_lock(&client_mutex);
 	list_for_each_entry(pos, &component_list, list) {
-		if (pos->dev->of_node != args.np)
+		if (pos->dev->of_node != args->np)
 			continue;
 
 		if (pos->driver->of_xlate_dai_name) {
-			ret = pos->driver->of_xlate_dai_name(pos, &args, dai_name);
+			ret = pos->driver->of_xlate_dai_name(pos,
+							     args,
+							     dai_name);
 		} else {
 			int id = -1;
 
-			switch (args.args_count) {
+			switch (args->args_count) {
 			case 0:
 				id = 0; /* same as dai_drv[0] */
 				break;
 			case 1:
-				id = args.args[0];
+				id = args->args[0];
 				break;
 			default:
 				/* not supported */
@@ -4801,6 +4795,21 @@ int snd_soc_of_get_dai_name(struct device_node *of_node,
 		break;
 	}
 	mutex_unlock(&client_mutex);
+	return ret;
+}
+
+int snd_soc_of_get_dai_name(struct device_node *of_node,
+			    const char **dai_name)
+{
+	struct of_phandle_args args;
+	int ret;
+
+	ret = of_parse_phandle_with_args(of_node, "sound-dai",
+					 "#sound-dai-cells", 0, &args);
+	if (ret)
+		return ret;
+
+	ret = snd_soc_get_dai_name(&args, dai_name);
 
 	of_node_put(args.np);
 
@@ -4808,6 +4817,77 @@ int snd_soc_of_get_dai_name(struct device_node *of_node,
 }
 EXPORT_SYMBOL_GPL(snd_soc_of_get_dai_name);
 
+/*
+ * snd_soc_of_get_dai_link_codecs - Parse a list of CODECs in the devicetree
+ * @dev: Card device
+ * @of_node: Device node
+ * @dai_link: DAI link
+ *
+ * Builds an array of CODEC DAI components from the DAI link property
+ * 'sound-dai'.
+ * The array is set in the DAI link and the number of DAIs is set accordingly.
+ * The device nodes in the array (of_node) must be dereferenced by the caller.
+ *
+ * Returns 0 for success
+ */
+int snd_soc_of_get_dai_link_codecs(struct device *dev,
+				   struct device_node *of_node,
+				   struct snd_soc_dai_link *dai_link)
+{
+	struct of_phandle_args args;
+	struct snd_soc_dai_link_component *component;
+	char *name;
+	int index, num_codecs, ret;
+
+	/* Count the number of CODECs */
+	name = "sound-dai";
+	num_codecs = of_count_phandle_with_args(of_node, name,
+						"#sound-dai-cells");
+	if (num_codecs <= 0) {
+		if (num_codecs == -ENOENT)
+			dev_err(dev, "No 'sound-dai' property\n");
+		else
+			dev_err(dev, "Bad phandle in 'sound-dai'\n");
+		return num_codecs;
+	}
+	component = devm_kzalloc(dev,
+				 sizeof *component * num_codecs,
+				 GFP_KERNEL);
+	if (!component)
+		return -ENOMEM;
+	dai_link->codecs = component;
+	dai_link->num_codecs = num_codecs;
+
+	/* Parse the list */
+	for (index = 0, component = dai_link->codecs;
+	     index < dai_link->num_codecs;
+	     index++, component++) {
+		ret = of_parse_phandle_with_args(of_node, name,
+						 "#sound-dai-cells",
+						  index, &args);
+		if (ret)
+			goto err;
+		component->of_node = args.np;
+		ret = snd_soc_get_dai_name(&args, &component->dai_name);
+		if (ret < 0)
+			goto err;
+	}
+	return 0;
+err:
+	for (index = 0, component = dai_link->codecs;
+	     index < dai_link->num_codecs;
+	     index++, component++) {
+		if (!component->of_node)
+			break;
+		of_node_put(component->of_node);
+		component->of_node = NULL;
+	}
+	dai_link->codecs = NULL;
+	dai_link->num_codecs = 0;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(snd_soc_of_get_dai_link_codecs);
+
 static int __init snd_soc_init(void)
 {
 #ifdef CONFIG_DEBUG_FS
-- 
cgit v1.2.3-70-g09d2


From bf4bea8e9a9058319a19f8c2710a6f0ef2459983 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Mon, 10 Nov 2014 08:33:56 +0000
Subject: kvm: fix kvm_is_mmio_pfn() and rename to kvm_is_reserved_pfn()

This reverts commit 85c8555ff0 ("KVM: check for !is_zero_pfn() in
kvm_is_mmio_pfn()") and renames the function to kvm_is_reserved_pfn.

The problem being addressed by the patch above was that some ARM code
based the memory mapping attributes of a pfn on the return value of
kvm_is_mmio_pfn(), whose name indeed suggests that such pfns should
be mapped as device memory.

However, kvm_is_mmio_pfn() doesn't do quite what it says on the tin,
and the existing non-ARM users were already using it in a way which
suggests that its name should probably have been 'kvm_is_reserved_pfn'
from the beginning, e.g., whether or not to call get_page/put_page on
it etc. This means that returning false for the zero page is a mistake
and the patch above should be reverted.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/ia64/kvm/kvm-ia64.c |  2 +-
 arch/x86/kvm/mmu.c       |  6 +++---
 include/linux/kvm_host.h |  2 +-
 virt/kvm/kvm_main.c      | 16 ++++++++--------
 4 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index ec6b9acb6be..dbe46f43884 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1563,7 +1563,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 
 	for (i = 0; i < npages; i++) {
 		pfn = gfn_to_pfn(kvm, base_gfn + i);
-		if (!kvm_is_mmio_pfn(pfn)) {
+		if (!kvm_is_reserved_pfn(pfn)) {
 			kvm_set_pmt_entry(kvm, base_gfn + i,
 					pfn << PAGE_SHIFT,
 				_PAGE_AR_RWX | _PAGE_MA_WB);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ac1c4de3a48..978f402006e 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -630,7 +630,7 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
 	 * kvm mmu, before reclaiming the page, we should
 	 * unmap it from mmu first.
 	 */
-	WARN_ON(!kvm_is_mmio_pfn(pfn) && !page_count(pfn_to_page(pfn)));
+	WARN_ON(!kvm_is_reserved_pfn(pfn) && !page_count(pfn_to_page(pfn)));
 
 	if (!shadow_accessed_mask || old_spte & shadow_accessed_mask)
 		kvm_set_pfn_accessed(pfn);
@@ -2461,7 +2461,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		spte |= PT_PAGE_SIZE_MASK;
 	if (tdp_enabled)
 		spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
-			kvm_is_mmio_pfn(pfn));
+			kvm_is_reserved_pfn(pfn));
 
 	if (host_writable)
 		spte |= SPTE_HOST_WRITEABLE;
@@ -2737,7 +2737,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 	 * PT_PAGE_TABLE_LEVEL and there would be no adjustment done
 	 * here.
 	 */
-	if (!is_error_noslot_pfn(pfn) && !kvm_is_mmio_pfn(pfn) &&
+	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
 	    level == PT_PAGE_TABLE_LEVEL &&
 	    PageTransCompound(pfn_to_page(pfn)) &&
 	    !has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ea53b04993f..a6059bdf7b0 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -703,7 +703,7 @@ void kvm_arch_sync_events(struct kvm *kvm);
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
 
-bool kvm_is_mmio_pfn(pfn_t pfn);
+bool kvm_is_reserved_pfn(pfn_t pfn);
 
 struct kvm_irq_ack_notifier {
 	struct hlist_node link;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 25ffac9e947..3cee7b16705 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -107,10 +107,10 @@ EXPORT_SYMBOL_GPL(kvm_rebooting);
 
 static bool largepages_enabled = true;
 
-bool kvm_is_mmio_pfn(pfn_t pfn)
+bool kvm_is_reserved_pfn(pfn_t pfn)
 {
 	if (pfn_valid(pfn))
-		return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn));
+		return PageReserved(pfn_to_page(pfn));
 
 	return true;
 }
@@ -1321,7 +1321,7 @@ static pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
 	else if ((vma->vm_flags & VM_PFNMAP)) {
 		pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) +
 			vma->vm_pgoff;
-		BUG_ON(!kvm_is_mmio_pfn(pfn));
+		BUG_ON(!kvm_is_reserved_pfn(pfn));
 	} else {
 		if (async && vma_is_valid(vma, write_fault))
 			*async = true;
@@ -1427,7 +1427,7 @@ static struct page *kvm_pfn_to_page(pfn_t pfn)
 	if (is_error_noslot_pfn(pfn))
 		return KVM_ERR_PTR_BAD_PAGE;
 
-	if (kvm_is_mmio_pfn(pfn)) {
+	if (kvm_is_reserved_pfn(pfn)) {
 		WARN_ON(1);
 		return KVM_ERR_PTR_BAD_PAGE;
 	}
@@ -1456,7 +1456,7 @@ EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
 void kvm_release_pfn_clean(pfn_t pfn)
 {
-	if (!is_error_noslot_pfn(pfn) && !kvm_is_mmio_pfn(pfn))
+	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn))
 		put_page(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
@@ -1477,7 +1477,7 @@ static void kvm_release_pfn_dirty(pfn_t pfn)
 
 void kvm_set_pfn_dirty(pfn_t pfn)
 {
-	if (!kvm_is_mmio_pfn(pfn)) {
+	if (!kvm_is_reserved_pfn(pfn)) {
 		struct page *page = pfn_to_page(pfn);
 		if (!PageReserved(page))
 			SetPageDirty(page);
@@ -1487,14 +1487,14 @@ EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
 
 void kvm_set_pfn_accessed(pfn_t pfn)
 {
-	if (!kvm_is_mmio_pfn(pfn))
+	if (!kvm_is_reserved_pfn(pfn))
 		mark_page_accessed(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
 
 void kvm_get_pfn(pfn_t pfn)
 {
-	if (!kvm_is_mmio_pfn(pfn))
+	if (!kvm_is_reserved_pfn(pfn))
 		get_page(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_get_pfn);
-- 
cgit v1.2.3-70-g09d2


From 1050dcda3052912984b26fb6d2695a3f41792000 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Mon, 17 Nov 2014 14:58:51 +0000
Subject: kvm: add a memslot flag for incoherent memory regions

Memory regions may be incoherent with the caches, typically when the
guest has mapped a host system RAM backed memory region as uncached.
Add a flag KVM_MEMSLOT_INCOHERENT so that we can tag these memslots
and handle them appropriately when mapping them.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 include/linux/kvm_host.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a6059bdf7b0..e4d8f705fec 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -43,6 +43,7 @@
  * include/linux/kvm_h.
  */
 #define KVM_MEMSLOT_INVALID	(1UL << 16)
+#define KVM_MEMSLOT_INCOHERENT	(1UL << 17)
 
 /* Two fragments for cross MMIO pages. */
 #define KVM_MAX_MMIO_FRAGMENTS	2
-- 
cgit v1.2.3-70-g09d2


From 7ff28aee40c42676abc3baab122d45826726ea49 Mon Sep 17 00:00:00 2001
From: Ondrej Zary <linux@rainbow-software.org>
Date: Mon, 24 Nov 2014 23:24:40 +0100
Subject: eeprom-93cx6: Add (read-only) support for 8-bit mode

Add read-only support for EEPROMs configured in 8-bit mode (ORG pin connected
to GND).
This will be used by wd719x driver.

Signed-off-by: Ondrej Zary <linux@rainbow-software.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/misc/eeprom/eeprom_93cx6.c | 62 +++++++++++++++++++++++++++++++++++++-
 include/linux/eeprom_93cx6.h       |  4 +++
 2 files changed, 65 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/misc/eeprom/eeprom_93cx6.c b/drivers/misc/eeprom/eeprom_93cx6.c
index 0ff4b02177b..0cf2c9d676b 100644
--- a/drivers/misc/eeprom/eeprom_93cx6.c
+++ b/drivers/misc/eeprom/eeprom_93cx6.c
@@ -170,7 +170,7 @@ static void eeprom_93cx6_read_bits(struct eeprom_93cx6 *eeprom,
 }
 
 /**
- * eeprom_93cx6_read - Read multiple words from eeprom
+ * eeprom_93cx6_read - Read a word from eeprom
  * @eeprom: Pointer to eeprom structure
  * @word: Word index from where we should start reading
  * @data: target pointer where the information will have to be stored
@@ -234,6 +234,66 @@ void eeprom_93cx6_multiread(struct eeprom_93cx6 *eeprom, const u8 word,
 }
 EXPORT_SYMBOL_GPL(eeprom_93cx6_multiread);
 
+/**
+ * eeprom_93cx6_readb - Read a byte from eeprom
+ * @eeprom: Pointer to eeprom structure
+ * @word: Byte index from where we should start reading
+ * @data: target pointer where the information will have to be stored
+ *
+ * This function will read a byte of the eeprom data
+ * into the given data pointer.
+ */
+void eeprom_93cx6_readb(struct eeprom_93cx6 *eeprom, const u8 byte,
+	u8 *data)
+{
+	u16 command;
+	u16 tmp;
+
+	/*
+	 * Initialize the eeprom register
+	 */
+	eeprom_93cx6_startup(eeprom);
+
+	/*
+	 * Select the read opcode and the byte to be read.
+	 */
+	command = (PCI_EEPROM_READ_OPCODE << (eeprom->width + 1)) | byte;
+	eeprom_93cx6_write_bits(eeprom, command,
+		PCI_EEPROM_WIDTH_OPCODE + eeprom->width + 1);
+
+	/*
+	 * Read the requested 8 bits.
+	 */
+	eeprom_93cx6_read_bits(eeprom, &tmp, 8);
+	*data = tmp & 0xff;
+
+	/*
+	 * Cleanup eeprom register.
+	 */
+	eeprom_93cx6_cleanup(eeprom);
+}
+EXPORT_SYMBOL_GPL(eeprom_93cx6_readb);
+
+/**
+ * eeprom_93cx6_multireadb - Read multiple bytes from eeprom
+ * @eeprom: Pointer to eeprom structure
+ * @byte: Index from where we should start reading
+ * @data: target pointer where the information will have to be stored
+ * @words: Number of bytes that should be read.
+ *
+ * This function will read all requested bytes from the eeprom,
+ * this is done by calling eeprom_93cx6_readb() multiple times.
+ */
+void eeprom_93cx6_multireadb(struct eeprom_93cx6 *eeprom, const u8 byte,
+	u8 *data, const u16 bytes)
+{
+	unsigned int i;
+
+	for (i = 0; i < bytes; i++)
+		eeprom_93cx6_readb(eeprom, byte + i, &data[i]);
+}
+EXPORT_SYMBOL_GPL(eeprom_93cx6_multireadb);
+
 /**
  * eeprom_93cx6_wren - set the write enable state
  * @eeprom: Pointer to eeprom structure
diff --git a/include/linux/eeprom_93cx6.h b/include/linux/eeprom_93cx6.h
index e50f98b0297..eb0b1988050 100644
--- a/include/linux/eeprom_93cx6.h
+++ b/include/linux/eeprom_93cx6.h
@@ -75,6 +75,10 @@ extern void eeprom_93cx6_read(struct eeprom_93cx6 *eeprom,
 	const u8 word, u16 *data);
 extern void eeprom_93cx6_multiread(struct eeprom_93cx6 *eeprom,
 	const u8 word, __le16 *data, const u16 words);
+extern void eeprom_93cx6_readb(struct eeprom_93cx6 *eeprom,
+	const u8 byte, u8 *data);
+extern void eeprom_93cx6_multireadb(struct eeprom_93cx6 *eeprom,
+	const u8 byte, u8 *data, const u16 bytes);
 
 extern void eeprom_93cx6_wren(struct eeprom_93cx6 *eeprom, bool enable);
 
-- 
cgit v1.2.3-70-g09d2


From 79e886599e6416d0de26e8562e4464577d081c3d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Wed, 19 Nov 2014 17:13:11 +0100
Subject: crypto: algif - add and use sock_kzfree_s() instead of
 memzero_explicit()

Commit e1bd95bf7c25 ("crypto: algif - zeroize IV buffer") and
2a6af25befd0 ("crypto: algif - zeroize message digest buffer")
added memzero_explicit() calls on buffers that are later on
passed back to sock_kfree_s().

This is a discussed follow-up that, instead, extends the sock
API and adds sock_kzfree_s(), which internally uses kzfree()
instead of kfree() for passing the buffers back to slab.

Having sock_kzfree_s() allows to keep the changes more minimal
by just having a drop-in replacement instead of adding
memzero_explicit() calls everywhere before sock_kfree_s().

In kzfree(), the compiler is not allowed to optimize the memset()
away and thus there's no need for memzero_explicit(). Both,
sock_kfree_s() and sock_kzfree_s() are wrappers for
__sock_kfree_s() and call into kfree() resp. kzfree(); here,
__sock_kfree_s() needs to be explicitly inlined as we want the
compiler to optimize the call and condition away and thus it
produces e.g. on x86_64 the _same_ assembler output for
sock_kfree_s() before and after, and thus also allows for
avoiding code duplication.

Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/algif_hash.c     |  6 ++----
 crypto/algif_skcipher.c |  3 +--
 include/net/sock.h      |  1 +
 net/core/sock.c         | 24 ++++++++++++++++++++----
 4 files changed, 24 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index f75db4ce48b..e6050396a3b 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -258,10 +258,8 @@ static void hash_sock_destruct(struct sock *sk)
 	struct alg_sock *ask = alg_sk(sk);
 	struct hash_ctx *ctx = ask->private;
 
-	memzero_explicit(ctx->result,
-		     crypto_ahash_digestsize(crypto_ahash_reqtfm(&ctx->req)));
-	sock_kfree_s(sk, ctx->result,
-		     crypto_ahash_digestsize(crypto_ahash_reqtfm(&ctx->req)));
+	sock_kzfree_s(sk, ctx->result,
+		      crypto_ahash_digestsize(crypto_ahash_reqtfm(&ctx->req)));
 	sock_kfree_s(sk, ctx, ctx->len);
 	af_alg_release_parent(sk);
 }
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 85e3bdbe214..34389964000 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -566,8 +566,7 @@ static void skcipher_sock_destruct(struct sock *sk)
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(&ctx->req);
 
 	skcipher_free_sgl(sk);
-	memzero_explicit(ctx->iv, crypto_ablkcipher_ivsize(tfm));
-	sock_kfree_s(sk, ctx->iv, crypto_ablkcipher_ivsize(tfm));
+	sock_kzfree_s(sk, ctx->iv, crypto_ablkcipher_ivsize(tfm));
 	sock_kfree_s(sk, ctx, ctx->len);
 	af_alg_release_parent(sk);
 }
diff --git a/include/net/sock.h b/include/net/sock.h
index 7db3db112ba..37d6cc5dcf3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1588,6 +1588,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 				     int *errcode, int max_page_order);
 void *sock_kmalloc(struct sock *sk, int size, gfp_t priority);
 void sock_kfree_s(struct sock *sk, void *mem, int size);
+void sock_kzfree_s(struct sock *sk, void *mem, int size);
 void sk_send_sigurg(struct sock *sk);
 
 /*
diff --git a/net/core/sock.c b/net/core/sock.c
index 15e0c67b106..04ce26a996b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1713,18 +1713,34 @@ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
 }
 EXPORT_SYMBOL(sock_kmalloc);
 
-/*
- * Free an option memory block.
+/* Free an option memory block. Note, we actually want the inline
+ * here as this allows gcc to detect the nullify and fold away the
+ * condition entirely.
  */
-void sock_kfree_s(struct sock *sk, void *mem, int size)
+static inline void __sock_kfree_s(struct sock *sk, void *mem, int size,
+				  const bool nullify)
 {
 	if (WARN_ON_ONCE(!mem))
 		return;
-	kfree(mem);
+	if (nullify)
+		kzfree(mem);
+	else
+		kfree(mem);
 	atomic_sub(size, &sk->sk_omem_alloc);
 }
+
+void sock_kfree_s(struct sock *sk, void *mem, int size)
+{
+	__sock_kfree_s(sk, mem, size, false);
+}
 EXPORT_SYMBOL(sock_kfree_s);
 
+void sock_kzfree_s(struct sock *sk, void *mem, int size)
+{
+	__sock_kfree_s(sk, mem, size, true);
+}
+EXPORT_SYMBOL(sock_kzfree_s);
+
 /* It is almost wait_for_tcp_memory minus release_sock/lock_sock.
    I think, these locks should be removed for datagram sockets.
  */
-- 
cgit v1.2.3-70-g09d2


From 1cc6adfef42615478e9af1228377acbc9f54f00f Mon Sep 17 00:00:00 2001
From: Josh Wu <josh.wu@atmel.com>
Date: Tue, 25 Nov 2014 05:54:27 -0300
Subject: [media] media: v4l2-image-sizes.h: add SVGA, XGA and UXGA size
 definitions

Add SVGA, UXGA and XGA size definitions to v4l2-image-sizes.h.
The definitions are sorted by alphabet order.

Signed-off-by: Josh Wu <josh.wu@atmel.com>
Acked-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/v4l2-image-sizes.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/media/v4l2-image-sizes.h b/include/media/v4l2-image-sizes.h
index 10daf92ff1a..c70c917b97a 100644
--- a/include/media/v4l2-image-sizes.h
+++ b/include/media/v4l2-image-sizes.h
@@ -25,10 +25,19 @@
 #define QVGA_WIDTH	320
 #define QVGA_HEIGHT	240
 
+#define SVGA_WIDTH	800
+#define SVGA_HEIGHT	680
+
 #define SXGA_WIDTH	1280
 #define SXGA_HEIGHT	1024
 
 #define VGA_WIDTH	640
 #define VGA_HEIGHT	480
 
+#define UXGA_WIDTH	1600
+#define UXGA_HEIGHT	1200
+
+#define XGA_WIDTH	1024
+#define XGA_HEIGHT	768
+
 #endif /* _IMAGE_SIZES_H */
-- 
cgit v1.2.3-70-g09d2


From 3bc2ee91a470c52fb3979c23c12d43283455f10d Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Tue, 18 Nov 2014 17:59:39 +0900
Subject: mfd: sec-core: Add support for S2MPS13 device

This patch adds the support for Samsung S2MPS13 PMIC device to the sec-core MFD
driver. The S2MPS13 is very similar with existing S2MPS14 and includes PMIC/
RTC/CLOCK devices.

Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Acked-by: Sangbeom Kim <sbkim73@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/sec-core.c           | 16 ++++++++++++++++
 drivers/mfd/sec-irq.c            | 23 +++++++++++++++++------
 include/linux/mfd/samsung/core.h |  1 +
 3 files changed, 34 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c
index dba7e2b6f8e..d086e8cee1d 100644
--- a/drivers/mfd/sec-core.c
+++ b/drivers/mfd/sec-core.c
@@ -74,6 +74,15 @@ static const struct mfd_cell s2mps11_devs[] = {
 	}
 };
 
+static const struct mfd_cell s2mps13_devs[] = {
+	{ .name = "s2mps13-pmic", },
+	{ .name = "s2mps13-rtc", },
+	{
+		.name = "s2mps13-clk",
+		.of_compatible = "samsung,s2mps13-clk",
+	},
+};
+
 static const struct mfd_cell s2mps14_devs[] = {
 	{
 		.name = "s2mps14-pmic",
@@ -107,6 +116,9 @@ static const struct of_device_id sec_dt_match[] = {
 	}, {
 		.compatible = "samsung,s2mps11-pmic",
 		.data = (void *)S2MPS11X,
+	}, {
+		.compatible = "samsung,s2mps13-pmic",
+		.data = (void *)S2MPS13X,
 	}, {
 		.compatible = "samsung,s2mps14-pmic",
 		.data = (void *)S2MPS14X,
@@ -378,6 +390,10 @@ static int sec_pmic_probe(struct i2c_client *i2c,
 		sec_devs = s2mps11_devs;
 		num_sec_devs = ARRAY_SIZE(s2mps11_devs);
 		break;
+	case S2MPS13X:
+		sec_devs = s2mps13_devs;
+		num_sec_devs = ARRAY_SIZE(s2mps13_devs);
+		break;
 	case S2MPS14X:
 		sec_devs = s2mps14_devs;
 		num_sec_devs = ARRAY_SIZE(s2mps14_devs);
diff --git a/drivers/mfd/sec-irq.c b/drivers/mfd/sec-irq.c
index f9a57869e3e..ba86a918c2d 100644
--- a/drivers/mfd/sec-irq.c
+++ b/drivers/mfd/sec-irq.c
@@ -389,14 +389,22 @@ static const struct regmap_irq_chip s2mps11_irq_chip = {
 	.ack_base = S2MPS11_REG_INT1,
 };
 
+#define S2MPS1X_IRQ_CHIP_COMMON_DATA		\
+	.irqs = s2mps14_irqs,			\
+	.num_irqs = ARRAY_SIZE(s2mps14_irqs),	\
+	.num_regs = 3,				\
+	.status_base = S2MPS14_REG_INT1,	\
+	.mask_base = S2MPS14_REG_INT1M,		\
+	.ack_base = S2MPS14_REG_INT1		\
+
+static const struct regmap_irq_chip s2mps13_irq_chip = {
+	.name = "s2mps13",
+	S2MPS1X_IRQ_CHIP_COMMON_DATA,
+};
+
 static const struct regmap_irq_chip s2mps14_irq_chip = {
 	.name = "s2mps14",
-	.irqs = s2mps14_irqs,
-	.num_irqs = ARRAY_SIZE(s2mps14_irqs),
-	.num_regs = 3,
-	.status_base = S2MPS14_REG_INT1,
-	.mask_base = S2MPS14_REG_INT1M,
-	.ack_base = S2MPS14_REG_INT1,
+	S2MPS1X_IRQ_CHIP_COMMON_DATA,
 };
 
 static const struct regmap_irq_chip s2mpu02_irq_chip = {
@@ -452,6 +460,9 @@ int sec_irq_init(struct sec_pmic_dev *sec_pmic)
 	case S2MPS11X:
 		sec_irq_chip = &s2mps11_irq_chip;
 		break;
+	case S2MPS13X:
+		sec_irq_chip = &s2mps13_irq_chip;
+		break;
 	case S2MPS14X:
 		sec_irq_chip = &s2mps14_irq_chip;
 		break;
diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h
index 1825edacbda..0c0343e06ba 100644
--- a/include/linux/mfd/samsung/core.h
+++ b/include/linux/mfd/samsung/core.h
@@ -41,6 +41,7 @@ enum sec_device_type {
 	S5M8767X,
 	S2MPA01,
 	S2MPS11X,
+	S2MPS13X,
 	S2MPS14X,
 	S2MPU02,
 };
-- 
cgit v1.2.3-70-g09d2


From 76b9840b24ae049b39f1b3cf0e49f21b7c41748f Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Tue, 18 Nov 2014 17:59:40 +0900
Subject: regulator: s2mps11: Add support S2MPS13 regulator device

This patch adds S2MPS13 regulator device to existing S2MPS11 device driver.
The S2MPS13 has just different number of regulators from S2MPS14.
The S2MPS13 regulator device includes LDO[1-40] and BUCK[1-10].

Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Acked-by: Sangbeom Kim <sbkim73@samsung.com>
Acked-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/sec-core.c              |  13 +++
 drivers/regulator/Kconfig           |  10 +-
 drivers/regulator/s2mps11.c         | 102 +++++++++++++++++++-
 include/linux/mfd/samsung/core.h    |   1 +
 include/linux/mfd/samsung/s2mps13.h | 186 ++++++++++++++++++++++++++++++++++++
 5 files changed, 304 insertions(+), 8 deletions(-)
 create mode 100644 include/linux/mfd/samsung/s2mps13.h

(limited to 'include')

diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c
index d086e8cee1d..b39960532f7 100644
--- a/drivers/mfd/sec-core.c
+++ b/drivers/mfd/sec-core.c
@@ -27,6 +27,7 @@
 #include <linux/mfd/samsung/irq.h>
 #include <linux/mfd/samsung/s2mpa01.h>
 #include <linux/mfd/samsung/s2mps11.h>
+#include <linux/mfd/samsung/s2mps13.h>
 #include <linux/mfd/samsung/s2mps14.h>
 #include <linux/mfd/samsung/s2mpu02.h>
 #include <linux/mfd/samsung/s5m8763.h>
@@ -206,6 +207,15 @@ static const struct regmap_config s2mps11_regmap_config = {
 	.cache_type = REGCACHE_FLAT,
 };
 
+static const struct regmap_config s2mps13_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = S2MPS13_REG_LDODSCH5,
+	.volatile_reg = s2mps11_volatile,
+	.cache_type = REGCACHE_FLAT,
+};
+
 static const struct regmap_config s2mps14_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
@@ -337,6 +347,9 @@ static int sec_pmic_probe(struct i2c_client *i2c,
 	case S2MPS11X:
 		regmap = &s2mps11_regmap_config;
 		break;
+	case S2MPS13X:
+		regmap = &s2mps13_regmap_config;
+		break;
 	case S2MPS14X:
 		regmap = &s2mps14_regmap_config;
 		break;
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 55d7b7b0f2e..5e061347be9 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -529,13 +529,13 @@ config REGULATOR_S2MPA01
 	 via I2C bus. S2MPA01 has 10 Bucks and 26 LDO outputs.
 
 config REGULATOR_S2MPS11
-	tristate "Samsung S2MPS11/S2MPS14/S2MPU02 voltage regulator"
+	tristate "Samsung S2MPS11/S2MPS13/S2MPS14/S2MPU02 voltage regulator"
 	depends on MFD_SEC_CORE
 	help
-	 This driver supports a Samsung S2MPS11/S2MPS14/S2MPU02 voltage output
-	 regulator via I2C bus. The chip is comprised of high efficient Buck
-	 converters including Dual-Phase Buck converter, Buck-Boost converter,
-	 various LDOs.
+	 This driver supports a Samsung S2MPS11/S2MPS13/S2MPS14/S2MPU02 voltage
+	 output regulator via I2C bus. The chip is comprised of high efficient
+	 Buck converters including Dual-Phase Buck converter, Buck-Boost
+	 converter, various LDOs.
 
 config REGULATOR_S5M8767
 	tristate "Samsung S5M8767A voltage regulator"
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index adab82d5279..738dc7763d4 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -30,6 +30,7 @@
 #include <linux/of_gpio.h>
 #include <linux/mfd/samsung/core.h>
 #include <linux/mfd/samsung/s2mps11.h>
+#include <linux/mfd/samsung/s2mps13.h>
 #include <linux/mfd/samsung/s2mps14.h>
 #include <linux/mfd/samsung/s2mpu02.h>
 
@@ -45,10 +46,10 @@ struct s2mps11_info {
 	enum sec_device_type dev_type;
 
 	/*
-	 * One bit for each S2MPS14/S2MPU02 regulator whether the suspend mode
-	 * was enabled.
+	 * One bit for each S2MPS13/S2MPS14/S2MPU02 regulator whether
+	 * the suspend mode was enabled.
 	 */
-	unsigned long long s2mps14_suspend_state:35;
+	unsigned long long s2mps14_suspend_state:50;
 
 	/* Array of size rdev_num with GPIO-s for external sleep control */
 	int *ext_control_gpio;
@@ -369,12 +370,101 @@ static const struct regulator_desc s2mps11_regulators[] = {
 	regulator_desc_s2mps11_buck6_10(10, MIN_750_MV, STEP_12_5_MV),
 };
 
+static struct regulator_ops s2mps14_reg_ops;
+
+#define regulator_desc_s2mps13_ldo(num, min, step, min_sel) {	\
+	.name		= "LDO"#num,				\
+	.id		= S2MPS13_LDO##num,			\
+	.ops		= &s2mps14_reg_ops,			\
+	.type		= REGULATOR_VOLTAGE,			\
+	.owner		= THIS_MODULE,				\
+	.min_uV		= min,					\
+	.uV_step	= step,					\
+	.linear_min_sel	= min_sel,				\
+	.n_voltages	= S2MPS14_LDO_N_VOLTAGES,		\
+	.vsel_reg	= S2MPS13_REG_L1CTRL + num - 1,		\
+	.vsel_mask	= S2MPS14_LDO_VSEL_MASK,		\
+	.enable_reg	= S2MPS13_REG_L1CTRL + num - 1,		\
+	.enable_mask	= S2MPS14_ENABLE_MASK			\
+}
+
+#define regulator_desc_s2mps13_buck(num, min, step, min_sel) {	\
+	.name		= "BUCK"#num,				\
+	.id		= S2MPS13_BUCK##num,			\
+	.ops		= &s2mps14_reg_ops,			\
+	.type		= REGULATOR_VOLTAGE,			\
+	.owner		= THIS_MODULE,				\
+	.min_uV		= min,					\
+	.uV_step	= step,					\
+	.linear_min_sel	= min_sel,				\
+	.n_voltages	= S2MPS14_BUCK_N_VOLTAGES,		\
+	.ramp_delay	= S2MPS13_BUCK_RAMP_DELAY,		\
+	.vsel_reg	= S2MPS13_REG_B1OUT + (num - 1) * 2,	\
+	.vsel_mask	= S2MPS14_BUCK_VSEL_MASK,		\
+	.enable_reg	= S2MPS13_REG_B1CTRL + (num - 1) * 2,	\
+	.enable_mask	= S2MPS14_ENABLE_MASK			\
+}
+
+static const struct regulator_desc s2mps13_regulators[] = {
+	regulator_desc_s2mps13_ldo(1,  MIN_800_MV,  STEP_12_5_MV, 0x00),
+	regulator_desc_s2mps13_ldo(2,  MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_ldo(3,  MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(4,  MIN_800_MV,  STEP_12_5_MV, 0x00),
+	regulator_desc_s2mps13_ldo(5,  MIN_800_MV,  STEP_12_5_MV, 0x00),
+	regulator_desc_s2mps13_ldo(6,  MIN_800_MV,  STEP_12_5_MV, 0x00),
+	regulator_desc_s2mps13_ldo(7,  MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(8,  MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(9,  MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(10, MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_ldo(11, MIN_800_MV,  STEP_25_MV,   0x10),
+	regulator_desc_s2mps13_ldo(12, MIN_800_MV,  STEP_25_MV,   0x10),
+	regulator_desc_s2mps13_ldo(13, MIN_800_MV,  STEP_25_MV,   0x10),
+	regulator_desc_s2mps13_ldo(14, MIN_800_MV,  STEP_12_5_MV, 0x00),
+	regulator_desc_s2mps13_ldo(15, MIN_800_MV,  STEP_12_5_MV, 0x00),
+	regulator_desc_s2mps13_ldo(16, MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_ldo(17, MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_ldo(18, MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(19, MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(20, MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_ldo(21, MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(22, MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(23, MIN_800_MV,  STEP_12_5_MV, 0x00),
+	regulator_desc_s2mps13_ldo(24, MIN_800_MV,  STEP_12_5_MV, 0x00),
+	regulator_desc_s2mps13_ldo(25, MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_ldo(26, MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_ldo(27, MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_ldo(28, MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(29, MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_ldo(30, MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_ldo(31, MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(32, MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(33, MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_ldo(34, MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(35, MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_ldo(36, MIN_800_MV,  STEP_12_5_MV, 0x00),
+	regulator_desc_s2mps13_ldo(37, MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(38, MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_ldo(39, MIN_1000_MV, STEP_25_MV,   0x08),
+	regulator_desc_s2mps13_ldo(40, MIN_1400_MV, STEP_50_MV,   0x0C),
+	regulator_desc_s2mps13_buck(1,  MIN_500_MV,  STEP_6_25_MV, 0x10),
+	regulator_desc_s2mps13_buck(2,  MIN_500_MV,  STEP_6_25_MV, 0x10),
+	regulator_desc_s2mps13_buck(3,  MIN_500_MV,  STEP_6_25_MV, 0x10),
+	regulator_desc_s2mps13_buck(4,  MIN_500_MV,  STEP_6_25_MV, 0x10),
+	regulator_desc_s2mps13_buck(5,  MIN_500_MV,  STEP_6_25_MV, 0x10),
+	regulator_desc_s2mps13_buck(6,  MIN_500_MV,  STEP_6_25_MV, 0x10),
+	regulator_desc_s2mps13_buck(7,  MIN_500_MV,  STEP_6_25_MV, 0x10),
+	regulator_desc_s2mps13_buck(8,  MIN_1000_MV, STEP_12_5_MV, 0x20),
+	regulator_desc_s2mps13_buck(9,  MIN_1000_MV, STEP_12_5_MV, 0x20),
+	regulator_desc_s2mps13_buck(10, MIN_500_MV,  STEP_6_25_MV, 0x10),
+};
+
 static int s2mps14_regulator_enable(struct regulator_dev *rdev)
 {
 	struct s2mps11_info *s2mps11 = rdev_get_drvdata(rdev);
 	unsigned int val;
 
 	switch (s2mps11->dev_type) {
+	case S2MPS13X:
 	case S2MPS14X:
 		if (s2mps11->s2mps14_suspend_state & (1 << rdev_get_id(rdev)))
 			val = S2MPS14_ENABLE_SUSPEND;
@@ -406,6 +496,7 @@ static int s2mps14_regulator_set_suspend_disable(struct regulator_dev *rdev)
 
 	/* Below LDO should be always on or does not support suspend mode. */
 	switch (s2mps11->dev_type) {
+	case S2MPS13X:
 	case S2MPS14X:
 		switch (rdev_id) {
 		case S2MPS14_LDO3:
@@ -831,6 +922,10 @@ static int s2mps11_pmic_probe(struct platform_device *pdev)
 		s2mps11->rdev_num = ARRAY_SIZE(s2mps11_regulators);
 		regulators = s2mps11_regulators;
 		break;
+	case S2MPS13X:
+		s2mps11->rdev_num = ARRAY_SIZE(s2mps13_regulators);
+		regulators = s2mps13_regulators;
+		break;
 	case S2MPS14X:
 		s2mps11->rdev_num = ARRAY_SIZE(s2mps14_regulators);
 		regulators = s2mps14_regulators;
@@ -927,6 +1022,7 @@ out:
 
 static const struct platform_device_id s2mps11_pmic_id[] = {
 	{ "s2mps11-pmic", S2MPS11X},
+	{ "s2mps13-pmic", S2MPS13X},
 	{ "s2mps14-pmic", S2MPS14X},
 	{ "s2mpu02-pmic", S2MPU02},
 	{ },
diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h
index 0c0343e06ba..3fdb7cfbffb 100644
--- a/include/linux/mfd/samsung/core.h
+++ b/include/linux/mfd/samsung/core.h
@@ -28,6 +28,7 @@
 #define MIN_800_MV		800000
 #define MIN_750_MV		750000
 #define MIN_600_MV		600000
+#define MIN_500_MV		500000
 
 /* Macros to represent steps for LDO/BUCK */
 #define STEP_50_MV		50000
diff --git a/include/linux/mfd/samsung/s2mps13.h b/include/linux/mfd/samsung/s2mps13.h
new file mode 100644
index 00000000000..ce5dda8958f
--- /dev/null
+++ b/include/linux/mfd/samsung/s2mps13.h
@@ -0,0 +1,186 @@
+/*
+ * s2mps13.h
+ *
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd
+ *              http://www.samsung.com
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __LINUX_MFD_S2MPS13_H
+#define __LINUX_MFD_S2MPS13_H
+
+/* S2MPS13 registers */
+enum s2mps13_reg {
+	S2MPS13_REG_ID,
+	S2MPS13_REG_INT1,
+	S2MPS13_REG_INT2,
+	S2MPS13_REG_INT3,
+	S2MPS13_REG_INT1M,
+	S2MPS13_REG_INT2M,
+	S2MPS13_REG_INT3M,
+	S2MPS13_REG_ST1,
+	S2MPS13_REG_ST2,
+	S2MPS13_REG_PWRONSRC,
+	S2MPS13_REG_OFFSRC,
+	S2MPS13_REG_BU_CHG,
+	S2MPS13_REG_RTCCTRL,
+	S2MPS13_REG_CTRL1,
+	S2MPS13_REG_CTRL2,
+	S2MPS13_REG_RSVD1,
+	S2MPS13_REG_RSVD2,
+	S2MPS13_REG_RSVD3,
+	S2MPS13_REG_RSVD4,
+	S2MPS13_REG_RSVD5,
+	S2MPS13_REG_RSVD6,
+	S2MPS13_REG_CTRL3,
+	S2MPS13_REG_RSVD7,
+	S2MPS13_REG_RSVD8,
+	S2MPS13_REG_WRSTBI,
+	S2MPS13_REG_B1CTRL,
+	S2MPS13_REG_B1OUT,
+	S2MPS13_REG_B2CTRL,
+	S2MPS13_REG_B2OUT,
+	S2MPS13_REG_B3CTRL,
+	S2MPS13_REG_B3OUT,
+	S2MPS13_REG_B4CTRL,
+	S2MPS13_REG_B4OUT,
+	S2MPS13_REG_B5CTRL,
+	S2MPS13_REG_B5OUT,
+	S2MPS13_REG_B6CTRL,
+	S2MPS13_REG_B6OUT,
+	S2MPS13_REG_B7CTRL,
+	S2MPS13_REG_B7OUT,
+	S2MPS13_REG_B8CTRL,
+	S2MPS13_REG_B8OUT,
+	S2MPS13_REG_B9CTRL,
+	S2MPS13_REG_B9OUT,
+	S2MPS13_REG_B10CTRL,
+	S2MPS13_REG_B10OUT,
+	S2MPS13_REG_BB1CTRL,
+	S2MPS13_REG_BB1OUT,
+	S2MPS13_REG_BUCK_RAMP1,
+	S2MPS13_REG_BUCK_RAMP2,
+	S2MPS13_REG_LDO_DVS1,
+	S2MPS13_REG_LDO_DVS2,
+	S2MPS13_REG_LDO_DVS3,
+	S2MPS13_REG_B6OUT2,
+	S2MPS13_REG_L1CTRL,
+	S2MPS13_REG_L2CTRL,
+	S2MPS13_REG_L3CTRL,
+	S2MPS13_REG_L4CTRL,
+	S2MPS13_REG_L5CTRL,
+	S2MPS13_REG_L6CTRL,
+	S2MPS13_REG_L7CTRL,
+	S2MPS13_REG_L8CTRL,
+	S2MPS13_REG_L9CTRL,
+	S2MPS13_REG_L10CTRL,
+	S2MPS13_REG_L11CTRL,
+	S2MPS13_REG_L12CTRL,
+	S2MPS13_REG_L13CTRL,
+	S2MPS13_REG_L14CTRL,
+	S2MPS13_REG_L15CTRL,
+	S2MPS13_REG_L16CTRL,
+	S2MPS13_REG_L17CTRL,
+	S2MPS13_REG_L18CTRL,
+	S2MPS13_REG_L19CTRL,
+	S2MPS13_REG_L20CTRL,
+	S2MPS13_REG_L21CTRL,
+	S2MPS13_REG_L22CTRL,
+	S2MPS13_REG_L23CTRL,
+	S2MPS13_REG_L24CTRL,
+	S2MPS13_REG_L25CTRL,
+	S2MPS13_REG_L26CTRL,
+	S2MPS13_REG_L27CTRL,
+	S2MPS13_REG_L28CTRL,
+	S2MPS13_REG_L30CTRL,
+	S2MPS13_REG_L31CTRL,
+	S2MPS13_REG_L32CTRL,
+	S2MPS13_REG_L33CTRL,
+	S2MPS13_REG_L34CTRL,
+	S2MPS13_REG_L35CTRL,
+	S2MPS13_REG_L36CTRL,
+	S2MPS13_REG_L37CTRL,
+	S2MPS13_REG_L38CTRL,
+	S2MPS13_REG_L39CTRL,
+	S2MPS13_REG_L40CTRL,
+	S2MPS13_REG_LDODSCH1,
+	S2MPS13_REG_LDODSCH2,
+	S2MPS13_REG_LDODSCH3,
+	S2MPS13_REG_LDODSCH4,
+	S2MPS13_REG_LDODSCH5,
+};
+
+/*  regulator ids */
+enum s2mps13_regulators {
+	S2MPS13_LDO1,
+	S2MPS13_LDO2,
+	S2MPS13_LDO3,
+	S2MPS13_LDO4,
+	S2MPS13_LDO5,
+	S2MPS13_LDO6,
+	S2MPS13_LDO7,
+	S2MPS13_LDO8,
+	S2MPS13_LDO9,
+	S2MPS13_LDO10,
+	S2MPS13_LDO11,
+	S2MPS13_LDO12,
+	S2MPS13_LDO13,
+	S2MPS13_LDO14,
+	S2MPS13_LDO15,
+	S2MPS13_LDO16,
+	S2MPS13_LDO17,
+	S2MPS13_LDO18,
+	S2MPS13_LDO19,
+	S2MPS13_LDO20,
+	S2MPS13_LDO21,
+	S2MPS13_LDO22,
+	S2MPS13_LDO23,
+	S2MPS13_LDO24,
+	S2MPS13_LDO25,
+	S2MPS13_LDO26,
+	S2MPS13_LDO27,
+	S2MPS13_LDO28,
+	S2MPS13_LDO29,
+	S2MPS13_LDO30,
+	S2MPS13_LDO31,
+	S2MPS13_LDO32,
+	S2MPS13_LDO33,
+	S2MPS13_LDO34,
+	S2MPS13_LDO35,
+	S2MPS13_LDO36,
+	S2MPS13_LDO37,
+	S2MPS13_LDO38,
+	S2MPS13_LDO39,
+	S2MPS13_LDO40,
+	S2MPS13_BUCK1,
+	S2MPS13_BUCK2,
+	S2MPS13_BUCK3,
+	S2MPS13_BUCK4,
+	S2MPS13_BUCK5,
+	S2MPS13_BUCK6,
+	S2MPS13_BUCK7,
+	S2MPS13_BUCK8,
+	S2MPS13_BUCK9,
+	S2MPS13_BUCK10,
+
+	S2MPS13_REGULATOR_MAX,
+};
+
+/*
+ * Default ramp delay in uv/us. Datasheet says that ramp delay can be
+ * controlled however it does not specify which register is used for that.
+ * Let's assume that default value will be set.
+ */
+#define S2MPS13_BUCK_RAMP_DELAY		12500
+
+#endif /*  __LINUX_MFD_S2MPS13_H */
-- 
cgit v1.2.3-70-g09d2


From 2c86e9fb7263dbca2c21a086090d32ba90129f7b Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@free-electrons.com>
Date: Mon, 6 Oct 2014 15:48:43 +0200
Subject: mfd: Add atmel-hlcdc driver

The HLCDC IP available on some Atmel SoCs (i.e. at91sam9n12, at91sam9x5
family or sama5d3 family) exposes 2 subdevices:
- a display controller (controlled by a DRM driver)
- a PWM chip

The MFD device provides a regmap and several clocks (those connected
to this hardware block) to its subdevices.

This way concurrent accesses to the iomem range are handled by the regmap
framework, and each subdevice can safely access HLCDC registers.

Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Tested-by: Anthony Harivel <anthony.harivel@emtrion.de>
Tested-by: Ludovic Desroches <ludovic.desroches@atmel.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/Kconfig             |   6 ++
 drivers/mfd/Makefile            |   1 +
 drivers/mfd/atmel-hlcdc.c       | 122 ++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/atmel-hlcdc.h |  85 ++++++++++++++++++++++++++++
 4 files changed, 214 insertions(+)
 create mode 100644 drivers/mfd/atmel-hlcdc.c
 create mode 100644 include/linux/mfd/atmel-hlcdc.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index fdbb4018183..bd4a155a956 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -59,6 +59,12 @@ config MFD_AAT2870_CORE
 	  additional drivers must be enabled in order to use the
 	  functionality of the device.
 
+config MFD_ATMEL_HLCDC
+	tristate
+	select MFD_CORE
+	select REGMAP_MMIO
+	depends on OF
+
 config MFD_BCM590XX
 	tristate "Broadcom BCM590xx PMUs"
 	select MFD_CORE
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 10bbd0b9096..2cd7e743280 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -157,6 +157,7 @@ obj-$(CONFIG_MFD_SPMI_PMIC)	+= qcom-spmi-pmic.o
 obj-$(CONFIG_TPS65911_COMPARATOR)	+= tps65911-comparator.o
 obj-$(CONFIG_MFD_TPS65090)	+= tps65090.o
 obj-$(CONFIG_MFD_AAT2870_CORE)	+= aat2870-core.o
+obj-$(CONFIG_MFD_ATMEL_HLCDC)	+= atmel-hlcdc.o
 obj-$(CONFIG_MFD_INTEL_MSIC)	+= intel_msic.o
 obj-$(CONFIG_MFD_PALMAS)	+= palmas.o
 obj-$(CONFIG_MFD_VIPERBOARD)    += viperboard.o
diff --git a/drivers/mfd/atmel-hlcdc.c b/drivers/mfd/atmel-hlcdc.c
new file mode 100644
index 00000000000..cfd58f4cc5c
--- /dev/null
+++ b/drivers/mfd/atmel-hlcdc.c
@@ -0,0 +1,122 @@
+/*
+ * Copyright (C) 2014 Free Electrons
+ * Copyright (C) 2014 Atmel
+ *
+ * Author: Boris BREZILLON <boris.brezillon@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/clk.h>
+#include <linux/mfd/atmel-hlcdc.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#define ATMEL_HLCDC_REG_MAX		(0x4000 - 0x4)
+
+static const struct mfd_cell atmel_hlcdc_cells[] = {
+	{
+		.name = "atmel-hlcdc-pwm",
+		.of_compatible = "atmel,hlcdc-pwm",
+	},
+	{
+		.name = "atmel-hlcdc-dc",
+		.of_compatible = "atmel,hlcdc-display-controller",
+	},
+};
+
+static const struct regmap_config atmel_hlcdc_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = ATMEL_HLCDC_REG_MAX,
+};
+
+static int atmel_hlcdc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct atmel_hlcdc *hlcdc;
+	struct resource *res;
+	void __iomem *regs;
+
+	hlcdc = devm_kzalloc(dev, sizeof(*hlcdc), GFP_KERNEL);
+	if (!hlcdc)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	hlcdc->irq = platform_get_irq(pdev, 0);
+	if (hlcdc->irq < 0)
+		return hlcdc->irq;
+
+	hlcdc->periph_clk = devm_clk_get(dev, "periph_clk");
+	if (IS_ERR(hlcdc->periph_clk)) {
+		dev_err(dev, "failed to get peripheral clock\n");
+		return PTR_ERR(hlcdc->periph_clk);
+	}
+
+	hlcdc->sys_clk = devm_clk_get(dev, "sys_clk");
+	if (IS_ERR(hlcdc->sys_clk)) {
+		dev_err(dev, "failed to get system clock\n");
+		return PTR_ERR(hlcdc->sys_clk);
+	}
+
+	hlcdc->slow_clk = devm_clk_get(dev, "slow_clk");
+	if (IS_ERR(hlcdc->slow_clk)) {
+		dev_err(dev, "failed to get slow clock\n");
+		return PTR_ERR(hlcdc->slow_clk);
+	}
+
+	hlcdc->regmap = devm_regmap_init_mmio(dev, regs,
+					      &atmel_hlcdc_regmap_config);
+	if (IS_ERR(hlcdc->regmap))
+		return PTR_ERR(hlcdc->regmap);
+
+	dev_set_drvdata(dev, hlcdc);
+
+	return mfd_add_devices(dev, -1, atmel_hlcdc_cells,
+			       ARRAY_SIZE(atmel_hlcdc_cells),
+			       NULL, 0, NULL);
+}
+
+static int atmel_hlcdc_remove(struct platform_device *pdev)
+{
+	mfd_remove_devices(&pdev->dev);
+
+	return 0;
+}
+
+static const struct of_device_id atmel_hlcdc_match[] = {
+	{ .compatible = "atmel,sama5d3-hlcdc" },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver atmel_hlcdc_driver = {
+	.probe = atmel_hlcdc_probe,
+	.remove = atmel_hlcdc_remove,
+	.driver = {
+		.name = "atmel-hlcdc",
+		.of_match_table = atmel_hlcdc_match,
+	},
+};
+module_platform_driver(atmel_hlcdc_driver);
+
+MODULE_ALIAS("platform:atmel-hlcdc");
+MODULE_AUTHOR("Boris Brezillon <boris.brezillon@free-electrons.com>");
+MODULE_DESCRIPTION("Atmel HLCDC driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mfd/atmel-hlcdc.h b/include/linux/mfd/atmel-hlcdc.h
new file mode 100644
index 00000000000..1279ab1644b
--- /dev/null
+++ b/include/linux/mfd/atmel-hlcdc.h
@@ -0,0 +1,85 @@
+/*
+ * Copyright (C) 2014 Free Electrons
+ * Copyright (C) 2014 Atmel
+ *
+ * Author: Boris BREZILLON <boris.brezillon@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __LINUX_MFD_HLCDC_H
+#define __LINUX_MFD_HLCDC_H
+
+#include <linux/clk.h>
+#include <linux/regmap.h>
+
+#define ATMEL_HLCDC_CFG(i)		((i) * 0x4)
+#define ATMEL_HLCDC_SIG_CFG		LCDCFG(5)
+#define ATMEL_HLCDC_HSPOL		BIT(0)
+#define ATMEL_HLCDC_VSPOL		BIT(1)
+#define ATMEL_HLCDC_VSPDLYS		BIT(2)
+#define ATMEL_HLCDC_VSPDLYE		BIT(3)
+#define ATMEL_HLCDC_DISPPOL		BIT(4)
+#define ATMEL_HLCDC_DITHER		BIT(6)
+#define ATMEL_HLCDC_DISPDLY		BIT(7)
+#define ATMEL_HLCDC_MODE_MASK		GENMASK(9, 8)
+#define ATMEL_HLCDC_PP			BIT(10)
+#define ATMEL_HLCDC_VSPSU		BIT(12)
+#define ATMEL_HLCDC_VSPHO		BIT(13)
+#define ATMEL_HLCDC_GUARDTIME_MASK	GENMASK(20, 16)
+
+#define ATMEL_HLCDC_EN			0x20
+#define ATMEL_HLCDC_DIS			0x24
+#define ATMEL_HLCDC_SR			0x28
+#define ATMEL_HLCDC_IER			0x2c
+#define ATMEL_HLCDC_IDR			0x30
+#define ATMEL_HLCDC_IMR			0x34
+#define ATMEL_HLCDC_ISR			0x38
+
+#define ATMEL_HLCDC_CLKPOL		BIT(0)
+#define ATMEL_HLCDC_CLKSEL		BIT(2)
+#define ATMEL_HLCDC_CLKPWMSEL		BIT(3)
+#define ATMEL_HLCDC_CGDIS(i)		BIT(8 + (i))
+#define ATMEL_HLCDC_CLKDIV_SHFT		16
+#define ATMEL_HLCDC_CLKDIV_MASK		GENMASK(23, 16)
+#define ATMEL_HLCDC_CLKDIV(div)		((div - 2) << ATMEL_HLCDC_CLKDIV_SHFT)
+
+#define ATMEL_HLCDC_PIXEL_CLK		BIT(0)
+#define ATMEL_HLCDC_SYNC		BIT(1)
+#define ATMEL_HLCDC_DISP		BIT(2)
+#define ATMEL_HLCDC_PWM			BIT(3)
+#define ATMEL_HLCDC_SIP			BIT(4)
+
+#define ATMEL_HLCDC_SOF			BIT(0)
+#define ATMEL_HLCDC_SYNCDIS		BIT(1)
+#define ATMEL_HLCDC_FIFOERR		BIT(4)
+#define ATMEL_HLCDC_LAYER_STATUS(x)	BIT((x) + 8)
+
+/**
+ * Structure shared by the MFD device and its subdevices.
+ *
+ * @regmap: register map used to access HLCDC IP registers
+ * @periph_clk: the hlcdc peripheral clock
+ * @sys_clk: the hlcdc system clock
+ * @slow_clk: the system slow clk
+ * @irq: the hlcdc irq
+ */
+struct atmel_hlcdc {
+	struct regmap *regmap;
+	struct clk *periph_clk;
+	struct clk *sys_clk;
+	struct clk *slow_clk;
+	int irq;
+};
+
+#endif /* __LINUX_MFD_HLCDC_H */
-- 
cgit v1.2.3-70-g09d2


From 6cbac55368324ec2a0e59e192c5b596d0f4569f7 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Fri, 10 Oct 2014 10:23:53 +0200
Subject: mfd: max77693: Remove unused define

Remove old MAX77693_NUM_IRQ_MUIC_REGS define. Not used anywhere.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/max77693-private.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index fc17d56581b..6392a156545 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -26,7 +26,6 @@
 
 #include <linux/i2c.h>
 
-#define MAX77693_NUM_IRQ_MUIC_REGS	3
 #define MAX77693_REG_INVALID		(0xff)
 
 /* Slave addr = 0xCC: PMIC, Charger, Flash LED */
-- 
cgit v1.2.3-70-g09d2


From 5cb5d9616a47d5383a85379afa4429382ef46b38 Mon Sep 17 00:00:00 2001
From: Micky Ching <micky_ching@realsil.com.cn>
Date: Fri, 10 Oct 2014 13:58:44 +0800
Subject: mfd: rtsx: Fix PM suspend for 5227 & 5249

Fix rts5227&5249 failed send buffer cmd after suspend,
PM_CTRL3 should reset before send any buffer cmd after suspend.
Otherwise, buffer cmd will failed, this will lead resume fail.

Signed-off-by: Micky Ching <micky_ching@realsil.com.cn>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/Makefile         |  2 +-
 drivers/mfd/rts5227.c        |  6 ++++++
 drivers/mfd/rts5249.c        |  4 ++++
 drivers/mfd/rtsx_gops.c      | 37 +++++++++++++++++++++++++++++++++++++
 drivers/mfd/rtsx_pcr.h       |  3 +++
 include/linux/mfd/rtsx_pci.h | 28 ++++++++++++++++++++++++++++
 6 files changed, 79 insertions(+), 1 deletion(-)
 create mode 100644 drivers/mfd/rtsx_gops.c

(limited to 'include')

diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 2cd7e743280..53467e21138 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_MFD_CROS_EC)	+= cros_ec.o
 obj-$(CONFIG_MFD_CROS_EC_I2C)	+= cros_ec_i2c.o
 obj-$(CONFIG_MFD_CROS_EC_SPI)	+= cros_ec_spi.o
 
-rtsx_pci-objs			:= rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o
+rtsx_pci-objs			:= rtsx_pcr.o rtsx_gops.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o
 obj-$(CONFIG_MFD_RTSX_PCI)	+= rtsx_pci.o
 obj-$(CONFIG_MFD_RTSX_USB)	+= rtsx_usb.o
 
diff --git a/drivers/mfd/rts5227.c b/drivers/mfd/rts5227.c
index 9c8eec80cee..32407404d83 100644
--- a/drivers/mfd/rts5227.c
+++ b/drivers/mfd/rts5227.c
@@ -130,6 +130,12 @@ static int rts5227_extra_init_hw(struct rtsx_pcr *pcr)
 
 static int rts5227_optimize_phy(struct rtsx_pcr *pcr)
 {
+	int err;
+
+	err = rtsx_gops_pm_reset(pcr);
+	if (err < 0)
+		return err;
+
 	/* Optimize RX sensitivity */
 	return rtsx_pci_write_phy_register(pcr, 0x00, 0xBA42);
 }
diff --git a/drivers/mfd/rts5249.c b/drivers/mfd/rts5249.c
index 573de7bfcce..cf425cc959d 100644
--- a/drivers/mfd/rts5249.c
+++ b/drivers/mfd/rts5249.c
@@ -130,6 +130,10 @@ static int rts5249_optimize_phy(struct rtsx_pcr *pcr)
 {
 	int err;
 
+	err = rtsx_gops_pm_reset(pcr);
+	if (err < 0)
+		return err;
+
 	err = rtsx_pci_write_phy_register(pcr, PHY_REG_REV,
 			PHY_REG_REV_RESV | PHY_REG_REV_RXIDLE_LATCHED |
 			PHY_REG_REV_P1_EN | PHY_REG_REV_RXIDLE_EN |
diff --git a/drivers/mfd/rtsx_gops.c b/drivers/mfd/rtsx_gops.c
new file mode 100644
index 00000000000..b1a98c67859
--- /dev/null
+++ b/drivers/mfd/rtsx_gops.c
@@ -0,0 +1,37 @@
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009-2013 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Micky Ching <micky_ching@realsil.com.cn>
+ */
+
+#include <linux/mfd/rtsx_pci.h>
+#include "rtsx_pcr.h"
+
+int rtsx_gops_pm_reset(struct rtsx_pcr *pcr)
+{
+	int err;
+
+	/* init aspm */
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0xFF, 0x00);
+	err = rtsx_pci_update_cfg_byte(pcr, LCTLR, ~LCTLR_ASPM_CTL_MASK, 0x00);
+	if (err < 0)
+		return err;
+
+	/* reset PM_CTRL3 before send buffer cmd */
+	return rtsx_pci_write_register(pcr, PM_CTRL3, D3_DELINK_MODE_EN, 0x00);
+}
diff --git a/drivers/mfd/rtsx_pcr.h b/drivers/mfd/rtsx_pcr.h
index 07e4c2ebf05..fe2bbb67def 100644
--- a/drivers/mfd/rtsx_pcr.h
+++ b/drivers/mfd/rtsx_pcr.h
@@ -72,4 +72,7 @@ do {									\
 	pcr->ms_pull_ctl_disable_tbl = __device##_ms_pull_ctl_disable_tbl; \
 } while (0)
 
+/* generic operations */
+int rtsx_gops_pm_reset(struct rtsx_pcr *pcr);
+
 #endif
diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h
index 74346d5e789..1604dda4edc 100644
--- a/include/linux/mfd/rtsx_pci.h
+++ b/include/linux/mfd/rtsx_pci.h
@@ -707,6 +707,14 @@
 #define PM_CTRL1			0xFF44
 #define PM_CTRL2			0xFF45
 #define PM_CTRL3			0xFF46
+#define   SDIO_SEND_PME_EN		0x80
+#define   FORCE_RC_MODE_ON		0x40
+#define   FORCE_RX50_LINK_ON		0x20
+#define   D3_DELINK_MODE_EN		0x10
+#define   USE_PESRTB_CTL_DELINK		0x08
+#define   DELAY_PIN_WAKE		0x04
+#define   RESET_PIN_WAKE		0x02
+#define   PM_WAKE_EN			0x01
 #define PM_CTRL4			0xFF47
 
 /* Memory mapping */
@@ -752,6 +760,14 @@
 #define PHY_DUM_REG			0x1F
 
 #define LCTLR				0x80
+#define   LCTLR_EXT_SYNC		0x80
+#define   LCTLR_COMMON_CLOCK_CFG	0x40
+#define   LCTLR_RETRAIN_LINK		0x20
+#define   LCTLR_LINK_DISABLE		0x10
+#define   LCTLR_RCB			0x08
+#define   LCTLR_RESERVED		0x04
+#define   LCTLR_ASPM_CTL_MASK		0x03
+
 #define PCR_SETTING_REG1		0x724
 #define PCR_SETTING_REG2		0x814
 #define PCR_SETTING_REG3		0x747
@@ -967,4 +983,16 @@ static inline u8 *rtsx_pci_get_cmd_data(struct rtsx_pcr *pcr)
 	return (u8 *)(pcr->host_cmds_ptr);
 }
 
+static inline int rtsx_pci_update_cfg_byte(struct rtsx_pcr *pcr, int addr,
+		u8 mask, u8 append)
+{
+	int err;
+	u8 val;
+
+	err = pci_read_config_byte(pcr->pci, addr, &val);
+	if (err < 0)
+		return err;
+	return pci_write_config_byte(pcr->pci, addr, (val & mask) | append);
+}
+
 #endif
-- 
cgit v1.2.3-70-g09d2


From 7d082baa349e59ce3de6452abc05e5de6436aad4 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 9 Oct 2014 09:18:38 -0700
Subject: mfd: ab8500-sysctrl: Drop ab8500_restart

ab8500_restart is not called from anywhere in the kernel, so drop it.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/ab8500-sysctrl.c              | 57 -------------------------------
 include/linux/mfd/abx500/ab8500-sysctrl.h |  1 -
 2 files changed, 58 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/ab8500-sysctrl.c b/drivers/mfd/ab8500-sysctrl.c
index 8e0dae59844..94dbcdd2a1f 100644
--- a/drivers/mfd/ab8500-sysctrl.c
+++ b/drivers/mfd/ab8500-sysctrl.c
@@ -85,63 +85,6 @@ shutdown:
 	}
 }
 
-/*
- * Use the AB WD to reset the platform. It will perform a hard
- * reset instead of a soft reset. Write the reset reason to
- * the AB before reset, which can be read upon restart.
- */
-void ab8500_restart(char mode, const char *cmd)
-{
-	struct ab8500_platform_data *plat;
-	struct ab8500_sysctrl_platform_data *pdata;
-	u16 reason = 0;
-	u8 val;
-
-	if (sysctrl_dev == NULL) {
-		pr_err("%s: sysctrl not initialized\n", __func__);
-		return;
-	}
-
-	plat = dev_get_platdata(sysctrl_dev->parent);
-	pdata = plat->sysctrl;
-	if (pdata && pdata->reboot_reason_code)
-		reason = pdata->reboot_reason_code(cmd);
-	else
-		pr_warn("[%s] No reboot reason set. Default reason %d\n",
-			__func__, reason);
-
-	/*
-	 * Disable RTC alarm, just a precaution so that no alarm
-	 * is running when WD reset is executed.
-	 */
-	abx500_get_register_interruptible(sysctrl_dev, AB8500_RTC,
-		RTC_CTRL , &val);
-	abx500_set_register_interruptible(sysctrl_dev, AB8500_RTC,
-		RTC_CTRL , (val & ~RTC_ALARM_ENABLE));
-
-	/*
-	 * Android is not using the RTC alarm registers during reboot
-	 * so we borrow them for writing the reason of reset
-	 */
-
-	/* reason[8 LSB] */
-	val = reason & 0xFF;
-	abx500_set_register_interruptible(sysctrl_dev, AB8500_RTC,
-		AB8500_ALARM_MIN_LOW , val);
-
-	/* reason[8 MSB] */
-	val = (reason>>8) & 0xFF;
-	abx500_set_register_interruptible(sysctrl_dev, AB8500_RTC,
-		AB8500_ALARM_MIN_MID , val);
-
-	/* Setting WD timeout to 0 */
-	ab8500_sysctrl_write(AB8500_MAINWDOGTIMER, 0xFF, 0x0);
-
-	/* Setting the parameters to AB8500 WD*/
-	ab8500_sysctrl_write(AB8500_MAINWDOGCTRL, 0xFF, (AB8500_ENABLE_WD |
-		AB8500_WD_RESTART_ON_EXPIRE | AB8500_KICK_WD));
-}
-
 static inline bool valid_bank(u8 bank)
 {
 	return ((bank == AB8500_SYS_CTRL1_BLOCK) ||
diff --git a/include/linux/mfd/abx500/ab8500-sysctrl.h b/include/linux/mfd/abx500/ab8500-sysctrl.h
index adba89d9c66..689312745b2 100644
--- a/include/linux/mfd/abx500/ab8500-sysctrl.h
+++ b/include/linux/mfd/abx500/ab8500-sysctrl.h
@@ -12,7 +12,6 @@
 
 int ab8500_sysctrl_read(u16 reg, u8 *value);
 int ab8500_sysctrl_write(u16 reg, u8 mask, u8 value);
-void ab8500_restart(char mode, const char *cmd);
 
 #else
 
-- 
cgit v1.2.3-70-g09d2


From 47958c5ab4035bd91f05598f76a61cd9f7f2934c Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Date: Tue, 4 Nov 2014 15:24:36 +0000
Subject: mfd: arizona: Document HP_CTRL_1L and HP_CTRL_1R registers

These registers are documented in the datasheet and used as part of the
extcon driver. Expose them properly through regmap as the datasheet
notes they should be treated as volatile do so.

Signed-off-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
---
 drivers/mfd/wm5102-tables.c           |  6 +++--
 drivers/mfd/wm5110-tables.c           |  4 ++++
 drivers/mfd/wm8997-tables.c           |  4 ++++
 include/linux/mfd/arizona/registers.h | 42 +++++++++++++++++++++++++++++++++++
 4 files changed, 54 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/wm5102-tables.c b/drivers/mfd/wm5102-tables.c
index d6f35bbf795..b326a82017e 100644
--- a/drivers/mfd/wm5102-tables.c
+++ b/drivers/mfd/wm5102-tables.c
@@ -336,8 +336,6 @@ static const struct reg_default wm5102_reg_default[] = {
 	{ 0x00000218, 0x01A6 },   /* R536   - Mic Bias Ctrl 1 */ 
 	{ 0x00000219, 0x01A6 },   /* R537   - Mic Bias Ctrl 2 */ 
 	{ 0x0000021A, 0x01A6 },   /* R538   - Mic Bias Ctrl 3 */ 
-	{ 0x00000225, 0x0400 },   /* R549   - HP Ctrl 1L */
-	{ 0x00000226, 0x0400 },   /* R550   - HP Ctrl 1R */
 	{ 0x00000293, 0x0000 },   /* R659   - Accessory Detect Mode 1 */ 
 	{ 0x0000029B, 0x0020 },   /* R667   - Headphone Detect 1 */ 
 	{ 0x0000029C, 0x0000 },   /* R668   - Headphone Detect 2 */
@@ -1112,6 +1110,8 @@ static bool wm5102_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_MIC_BIAS_CTRL_1:
 	case ARIZONA_MIC_BIAS_CTRL_2:
 	case ARIZONA_MIC_BIAS_CTRL_3:
+	case ARIZONA_HP_CTRL_1L:
+	case ARIZONA_HP_CTRL_1R:
 	case ARIZONA_ACCESSORY_DETECT_MODE_1:
 	case ARIZONA_HEADPHONE_DETECT_1:
 	case ARIZONA_HEADPHONE_DETECT_2:
@@ -1949,6 +1949,8 @@ static bool wm5102_volatile_register(struct device *dev, unsigned int reg)
 	case ARIZONA_DSP1_SCRATCH_1:
 	case ARIZONA_DSP1_SCRATCH_2:
 	case ARIZONA_DSP1_SCRATCH_3:
+	case ARIZONA_HP_CTRL_1L:
+	case ARIZONA_HP_CTRL_1R:
 	case ARIZONA_HEADPHONE_DETECT_2:
 	case ARIZONA_HP_DACVAL:
 	case ARIZONA_MIC_DETECT_3:
diff --git a/drivers/mfd/wm5110-tables.c b/drivers/mfd/wm5110-tables.c
index 4642b5b816a..c75390ad4f4 100644
--- a/drivers/mfd/wm5110-tables.c
+++ b/drivers/mfd/wm5110-tables.c
@@ -1790,6 +1790,8 @@ static bool wm5110_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_MIC_BIAS_CTRL_1:
 	case ARIZONA_MIC_BIAS_CTRL_2:
 	case ARIZONA_MIC_BIAS_CTRL_3:
+	case ARIZONA_HP_CTRL_1L:
+	case ARIZONA_HP_CTRL_1R:
 	case ARIZONA_ACCESSORY_DETECT_MODE_1:
 	case ARIZONA_HEADPHONE_DETECT_1:
 	case ARIZONA_HEADPHONE_DETECT_2:
@@ -2825,6 +2827,8 @@ static bool wm5110_volatile_register(struct device *dev, unsigned int reg)
 	case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS:
 	case ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS:
 	case ARIZONA_MIC_DETECT_3:
+	case ARIZONA_HP_CTRL_1L:
+	case ARIZONA_HP_CTRL_1R:
 	case ARIZONA_HEADPHONE_DETECT_2:
 	case ARIZONA_INPUT_ENABLES_STATUS:
 	case ARIZONA_OUTPUT_STATUS_1:
diff --git a/drivers/mfd/wm8997-tables.c b/drivers/mfd/wm8997-tables.c
index f44d195d449..c0c25d75aac 100644
--- a/drivers/mfd/wm8997-tables.c
+++ b/drivers/mfd/wm8997-tables.c
@@ -887,6 +887,8 @@ static bool wm8997_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_MIC_BIAS_CTRL_1:
 	case ARIZONA_MIC_BIAS_CTRL_2:
 	case ARIZONA_MIC_BIAS_CTRL_3:
+	case ARIZONA_HP_CTRL_1L:
+	case ARIZONA_HP_CTRL_1R:
 	case ARIZONA_ACCESSORY_DETECT_MODE_1:
 	case ARIZONA_HEADPHONE_DETECT_1:
 	case ARIZONA_HEADPHONE_DETECT_2:
@@ -1479,6 +1481,8 @@ static bool wm8997_volatile_register(struct device *dev, unsigned int reg)
 	case ARIZONA_SAMPLE_RATE_3_STATUS:
 	case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS:
 	case ARIZONA_MIC_DETECT_3:
+	case ARIZONA_HP_CTRL_1L:
+	case ARIZONA_HP_CTRL_1R:
 	case ARIZONA_HEADPHONE_DETECT_2:
 	case ARIZONA_INPUT_ENABLES_STATUS:
 	case ARIZONA_OUTPUT_STATUS_1:
diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h
index c0b075f6bc3..d521f327b34 100644
--- a/include/linux/mfd/arizona/registers.h
+++ b/include/linux/mfd/arizona/registers.h
@@ -125,6 +125,8 @@
 #define ARIZONA_MIC_BIAS_CTRL_1                  0x218
 #define ARIZONA_MIC_BIAS_CTRL_2                  0x219
 #define ARIZONA_MIC_BIAS_CTRL_3                  0x21A
+#define ARIZONA_HP_CTRL_1L                       0x225
+#define ARIZONA_HP_CTRL_1R                       0x226
 #define ARIZONA_ACCESSORY_DETECT_MODE_1          0x293
 #define ARIZONA_HEADPHONE_DETECT_1               0x29B
 #define ARIZONA_HEADPHONE_DETECT_2               0x29C
@@ -2244,6 +2246,46 @@
 #define ARIZONA_MICB3_ENA_SHIFT                       0  /* MICB3_ENA */
 #define ARIZONA_MICB3_ENA_WIDTH                       1  /* MICB3_ENA */
 
+/*
+ * R549 (0x225) - HP Ctrl 1L
+ */
+#define ARIZONA_RMV_SHRT_HP1L                    0x4000  /* RMV_SHRT_HP1L */
+#define ARIZONA_RMV_SHRT_HP1L_MASK               0x4000  /* RMV_SHRT_HP1L */
+#define ARIZONA_RMV_SHRT_HP1L_SHIFT                  14  /* RMV_SHRT_HP1L */
+#define ARIZONA_RMV_SHRT_HP1L_WIDTH                   1  /* RMV_SHRT_HP1L */
+#define ARIZONA_HP1L_FLWR                        0x0004  /* HP1L_FLWR */
+#define ARIZONA_HP1L_FLWR_MASK                   0x0004  /* HP1L_FLWR */
+#define ARIZONA_HP1L_FLWR_SHIFT                       2  /* HP1L_FLWR */
+#define ARIZONA_HP1L_FLWR_WIDTH                       1  /* HP1L_FLWR */
+#define ARIZONA_HP1L_SHRTI                       0x0002  /* HP1L_SHRTI */
+#define ARIZONA_HP1L_SHRTI_MASK                  0x0002  /* HP1L_SHRTI */
+#define ARIZONA_HP1L_SHRTI_SHIFT                      1  /* HP1L_SHRTI */
+#define ARIZONA_HP1L_SHRTI_WIDTH                      1  /* HP1L_SHRTI */
+#define ARIZONA_HP1L_SHRTO                       0x0001  /* HP1L_SHRTO */
+#define ARIZONA_HP1L_SHRTO_MASK                  0x0001  /* HP1L_SHRTO */
+#define ARIZONA_HP1L_SHRTO_SHIFT                      0  /* HP1L_SHRTO */
+#define ARIZONA_HP1L_SHRTO_WIDTH                      1  /* HP1L_SHRTO */
+
+/*
+ * R550 (0x226) - HP Ctrl 1R
+ */
+#define ARIZONA_RMV_SHRT_HP1R                    0x4000  /* RMV_SHRT_HP1R */
+#define ARIZONA_RMV_SHRT_HP1R_MASK               0x4000  /* RMV_SHRT_HP1R */
+#define ARIZONA_RMV_SHRT_HP1R_SHIFT                  14  /* RMV_SHRT_HP1R */
+#define ARIZONA_RMV_SHRT_HP1R_WIDTH                   1  /* RMV_SHRT_HP1R */
+#define ARIZONA_HP1R_FLWR                        0x0004  /* HP1R_FLWR */
+#define ARIZONA_HP1R_FLWR_MASK                   0x0004  /* HP1R_FLWR */
+#define ARIZONA_HP1R_FLWR_SHIFT                       2  /* HP1R_FLWR */
+#define ARIZONA_HP1R_FLWR_WIDTH                       1  /* HP1R_FLWR */
+#define ARIZONA_HP1R_SHRTI                       0x0002  /* HP1R_SHRTI */
+#define ARIZONA_HP1R_SHRTI_MASK                  0x0002  /* HP1R_SHRTI */
+#define ARIZONA_HP1R_SHRTI_SHIFT                      1  /* HP1R_SHRTI */
+#define ARIZONA_HP1R_SHRTI_WIDTH                      1  /* HP1R_SHRTI */
+#define ARIZONA_HP1R_SHRTO                       0x0001  /* HP1R_SHRTO */
+#define ARIZONA_HP1R_SHRTO_MASK                  0x0001  /* HP1R_SHRTO */
+#define ARIZONA_HP1R_SHRTO_SHIFT                      0  /* HP1R_SHRTO */
+#define ARIZONA_HP1R_SHRTO_WIDTH                      1  /* HP1R_SHRTO */
+
 /*
  * R659 (0x293) - Accessory Detect Mode 1
  */
-- 
cgit v1.2.3-70-g09d2


From 90f2d0f7bf069b1a2798156b7dcc8e7d1e874406 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 28 Oct 2014 11:06:56 +0100
Subject: mfd: tc3589x: get rid of static base

The TC3589x driver is now a device tree-only driver, so we want
only dynamic IRQs and GPIO numbers from the tc3589x, no static
assignments.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-tc3589x.c | 2 +-
 drivers/mfd/tc3589x.c       | 9 +++------
 include/linux/mfd/tc3589x.h | 8 --------
 3 files changed, 4 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c
index ae0f6466eb0..abdcf58935f 100644
--- a/drivers/gpio/gpio-tc3589x.c
+++ b/drivers/gpio/gpio-tc3589x.c
@@ -262,7 +262,7 @@ static int tc3589x_gpio_probe(struct platform_device *pdev)
 	tc3589x_gpio->chip = template_chip;
 	tc3589x_gpio->chip.ngpio = tc3589x->num_gpio;
 	tc3589x_gpio->chip.dev = &pdev->dev;
-	tc3589x_gpio->chip.base = (pdata) ? pdata->gpio_base : -1;
+	tc3589x_gpio->chip.base = -1;
 
 #ifdef CONFIG_OF_GPIO
 	tc3589x_gpio->chip.of_node = np;
diff --git a/drivers/mfd/tc3589x.c b/drivers/mfd/tc3589x.c
index 0072e668c20..aacb3720065 100644
--- a/drivers/mfd/tc3589x.c
+++ b/drivers/mfd/tc3589x.c
@@ -241,10 +241,8 @@ static struct irq_domain_ops tc3589x_irq_ops = {
 
 static int tc3589x_irq_init(struct tc3589x *tc3589x, struct device_node *np)
 {
-	int base = tc3589x->irq_base;
-
 	tc3589x->domain = irq_domain_add_simple(
-		np, TC3589x_NR_INTERNAL_IRQS, base,
+		np, TC3589x_NR_INTERNAL_IRQS, 0,
 		&tc3589x_irq_ops, tc3589x);
 
 	if (!tc3589x->domain) {
@@ -298,7 +296,7 @@ static int tc3589x_device_init(struct tc3589x *tc3589x)
 	if (blocks & TC3589x_BLOCK_GPIO) {
 		ret = mfd_add_devices(tc3589x->dev, -1, tc3589x_dev_gpio,
 				      ARRAY_SIZE(tc3589x_dev_gpio), NULL,
-				      tc3589x->irq_base, tc3589x->domain);
+				      0, tc3589x->domain);
 		if (ret) {
 			dev_err(tc3589x->dev, "failed to add gpio child\n");
 			return ret;
@@ -309,7 +307,7 @@ static int tc3589x_device_init(struct tc3589x *tc3589x)
 	if (blocks & TC3589x_BLOCK_KEYPAD) {
 		ret = mfd_add_devices(tc3589x->dev, -1, tc3589x_dev_keypad,
 				      ARRAY_SIZE(tc3589x_dev_keypad), NULL,
-				      tc3589x->irq_base, tc3589x->domain);
+				      0, tc3589x->domain);
 		if (ret) {
 			dev_err(tc3589x->dev, "failed to keypad child\n");
 			return ret;
@@ -404,7 +402,6 @@ static int tc3589x_probe(struct i2c_client *i2c,
 	tc3589x->dev = &i2c->dev;
 	tc3589x->i2c = i2c;
 	tc3589x->pdata = pdata;
-	tc3589x->irq_base = pdata->irq_base;
 
 	switch (version) {
 	case TC3589X_TC35893:
diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h
index e6088c2e209..e1c12d84c26 100644
--- a/include/linux/mfd/tc3589x.h
+++ b/include/linux/mfd/tc3589x.h
@@ -164,13 +164,10 @@ struct tc3589x_keypad_platform_data {
 
 /**
  * struct tc3589x_gpio_platform_data - TC3589x GPIO platform data
- * @gpio_base: first gpio number assigned to TC3589x.  A maximum of
- *	       %TC3589x_NR_GPIOS GPIOs will be allocated.
  * @setup: callback for board-specific initialization
  * @remove: callback for board-specific teardown
  */
 struct tc3589x_gpio_platform_data {
-	int gpio_base;
 	void (*setup)(struct tc3589x *tc3589x, unsigned gpio_base);
 	void (*remove)(struct tc3589x *tc3589x, unsigned gpio_base);
 };
@@ -178,18 +175,13 @@ struct tc3589x_gpio_platform_data {
 /**
  * struct tc3589x_platform_data - TC3589x platform data
  * @block: bitmask of blocks to enable (use TC3589x_BLOCK_*)
- * @irq_base: base IRQ number.  %TC3589x_NR_IRQS irqs will be used.
  * @gpio: GPIO-specific platform data
  * @keypad: keypad-specific platform data
  */
 struct tc3589x_platform_data {
 	unsigned int block;
-	int irq_base;
 	struct tc3589x_gpio_platform_data *gpio;
 	const struct tc3589x_keypad_platform_data *keypad;
 };
 
-#define TC3589x_NR_GPIOS	24
-#define TC3589x_NR_IRQS		TC3589x_INT_GPIO(TC3589x_NR_GPIOS)
-
 #endif
-- 
cgit v1.2.3-70-g09d2


From 783f6fc4cecd770dfdb1418c7c890dbeb3bf3c91 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Date: Tue, 4 Nov 2014 13:04:07 +0000
Subject: mfd: wm5110: Add missing registers for AIF2 channels 3-6

When the extra 4 channels were added to AIF2 the necessary frame control
registers were not given defaults and marked readable. This patch fixes
this.

Signed-off-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
---
 drivers/mfd/wm5110-tables.c           | 16 ++++++++++++++++
 include/linux/mfd/arizona/registers.h |  8 ++++++++
 2 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/drivers/mfd/wm5110-tables.c b/drivers/mfd/wm5110-tables.c
index c75390ad4f4..12cad94b403 100644
--- a/drivers/mfd/wm5110-tables.c
+++ b/drivers/mfd/wm5110-tables.c
@@ -895,8 +895,16 @@ static const struct reg_default wm5110_reg_default[] = {
 	{ 0x00000548, 0x1818 },    /* R1352  - AIF2 Frame Ctrl 2 */
 	{ 0x00000549, 0x0000 },    /* R1353  - AIF2 Frame Ctrl 3 */
 	{ 0x0000054A, 0x0001 },    /* R1354  - AIF2 Frame Ctrl 4 */
+	{ 0x0000054B, 0x0002 },    /* R1355  - AIF2 Frame Ctrl 5 */
+	{ 0x0000054C, 0x0003 },    /* R1356  - AIF2 Frame Ctrl 6 */
+	{ 0x0000054D, 0x0004 },    /* R1357  - AIF2 Frame Ctrl 7 */
+	{ 0x0000054E, 0x0005 },    /* R1358  - AIF2 Frame Ctrl 8 */
 	{ 0x00000551, 0x0000 },    /* R1361  - AIF2 Frame Ctrl 11 */
 	{ 0x00000552, 0x0001 },    /* R1362  - AIF2 Frame Ctrl 12 */
+	{ 0x00000553, 0x0002 },    /* R1363  - AIF2 Frame Ctrl 13 */
+	{ 0x00000554, 0x0003 },    /* R1364  - AIF2 Frame Ctrl 14 */
+	{ 0x00000555, 0x0004 },    /* R1365  - AIF2 Frame Ctrl 15 */
+	{ 0x00000556, 0x0005 },    /* R1366  - AIF2 Frame Ctrl 16 */
 	{ 0x00000559, 0x0000 },    /* R1369  - AIF2 Tx Enables */
 	{ 0x0000055A, 0x0000 },    /* R1370  - AIF2 Rx Enables */
 	{ 0x00000580, 0x000C },    /* R1408  - AIF3 BCLK Ctrl */
@@ -1936,8 +1944,16 @@ static bool wm5110_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_AIF2_FRAME_CTRL_2:
 	case ARIZONA_AIF2_FRAME_CTRL_3:
 	case ARIZONA_AIF2_FRAME_CTRL_4:
+	case ARIZONA_AIF2_FRAME_CTRL_5:
+	case ARIZONA_AIF2_FRAME_CTRL_6:
+	case ARIZONA_AIF2_FRAME_CTRL_7:
+	case ARIZONA_AIF2_FRAME_CTRL_8:
 	case ARIZONA_AIF2_FRAME_CTRL_11:
 	case ARIZONA_AIF2_FRAME_CTRL_12:
+	case ARIZONA_AIF2_FRAME_CTRL_13:
+	case ARIZONA_AIF2_FRAME_CTRL_14:
+	case ARIZONA_AIF2_FRAME_CTRL_15:
+	case ARIZONA_AIF2_FRAME_CTRL_16:
 	case ARIZONA_AIF2_TX_ENABLES:
 	case ARIZONA_AIF2_RX_ENABLES:
 	case ARIZONA_AIF3_BCLK_CTRL:
diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h
index d521f327b34..aacc10d7789 100644
--- a/include/linux/mfd/arizona/registers.h
+++ b/include/linux/mfd/arizona/registers.h
@@ -281,8 +281,16 @@
 #define ARIZONA_AIF2_FRAME_CTRL_2                0x548
 #define ARIZONA_AIF2_FRAME_CTRL_3                0x549
 #define ARIZONA_AIF2_FRAME_CTRL_4                0x54A
+#define ARIZONA_AIF2_FRAME_CTRL_5                0x54B
+#define ARIZONA_AIF2_FRAME_CTRL_6                0x54C
+#define ARIZONA_AIF2_FRAME_CTRL_7                0x54D
+#define ARIZONA_AIF2_FRAME_CTRL_8                0x54E
 #define ARIZONA_AIF2_FRAME_CTRL_11               0x551
 #define ARIZONA_AIF2_FRAME_CTRL_12               0x552
+#define ARIZONA_AIF2_FRAME_CTRL_13               0x553
+#define ARIZONA_AIF2_FRAME_CTRL_14               0x554
+#define ARIZONA_AIF2_FRAME_CTRL_15               0x555
+#define ARIZONA_AIF2_FRAME_CTRL_16               0x556
 #define ARIZONA_AIF2_TX_ENABLES                  0x559
 #define ARIZONA_AIF2_RX_ENABLES                  0x55A
 #define ARIZONA_AIF2_FORCE_WRITE                 0x55B
-- 
cgit v1.2.3-70-g09d2


From cbd7584e6ead1b79fb0b81573f158b57fa1f0b49 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 25 Nov 2014 11:41:49 -0500
Subject: ext4: fix block reservation for bigalloc filesystems

For bigalloc filesystems we have to check whether newly requested inode
block isn't already part of a cluster for which we already have delayed
allocation reservation. This check happens in ext4_ext_map_blocks() and
that function sets EXT4_MAP_FROM_CLUSTER if that's the case. However if
ext4_da_map_blocks() finds in extent cache information about the block,
we don't call into ext4_ext_map_blocks() and thus we always end up
getting new reservation even if the space for cluster is already
reserved. This results in overreservation and premature ENOSPC reports.

Fix the problem by checking for existing cluster reservation already in
ext4_da_map_blocks(). That simplifies the logic and actually allows us
to get rid of the EXT4_MAP_FROM_CLUSTER flag completely.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h              | 21 +--------------------
 fs/ext4/extents.c           | 12 ++++--------
 fs/ext4/inode.c             | 27 ++++-----------------------
 include/trace/events/ext4.h |  3 +--
 4 files changed, 10 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 21a3b38395f..7b3f3b1decf 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -158,17 +158,8 @@ struct ext4_allocation_request {
 #define EXT4_MAP_MAPPED		(1 << BH_Mapped)
 #define EXT4_MAP_UNWRITTEN	(1 << BH_Unwritten)
 #define EXT4_MAP_BOUNDARY	(1 << BH_Boundary)
-/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of
- * ext4_map_blocks wants to know whether or not the underlying cluster has
- * already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that
- * the requested mapping was from previously mapped (or delayed allocated)
- * cluster. We use BH_AllocFromCluster only for this flag. BH_AllocFromCluster
- * should never appear on buffer_head's state flags.
- */
-#define EXT4_MAP_FROM_CLUSTER	(1 << BH_AllocFromCluster)
 #define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
-				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
-				 EXT4_MAP_FROM_CLUSTER)
+				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY)
 
 struct ext4_map_blocks {
 	ext4_fsblk_t m_pblk;
@@ -2789,16 +2780,6 @@ extern int ext4_bio_write_page(struct ext4_io_submit *io,
 /* mmp.c */
 extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
 
-/*
- * Note that these flags will never ever appear in a buffer_head's state flag.
- * See EXT4_MAP_... to see where this is used.
- */
-enum ext4_state_bits {
-	BH_AllocFromCluster	/* allocated blocks were part of already
-				 * allocated cluster. */
-	= BH_JBDPrivateStart
-};
-
 /*
  * Add new method to test whether block and inode bitmaps are properly
  * initialized. With uninit_bg reading the block from disk is not enough
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 9eae2f4916c..7ef2f11aca5 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4282,6 +4282,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	ext4_io_end_t *io = ext4_inode_aio(inode);
 	ext4_lblk_t cluster_offset;
 	int set_unwritten = 0;
+	bool map_from_cluster = false;
 
 	ext_debug("blocks %u/%u requested for inode %lu\n",
 		  map->m_lblk, map->m_len, inode->i_ino);
@@ -4358,10 +4359,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		}
 	}
 
-	if ((sbi->s_cluster_ratio > 1) &&
-	    ext4_find_delalloc_cluster(inode, map->m_lblk))
-		map->m_flags |= EXT4_MAP_FROM_CLUSTER;
-
 	/*
 	 * requested block isn't allocated yet;
 	 * we couldn't try to create block if create flag is zero
@@ -4379,7 +4376,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	/*
 	 * Okay, we need to do block allocation.
 	 */
-	map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
 	newex.ee_block = cpu_to_le32(map->m_lblk);
 	cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
 
@@ -4391,7 +4387,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	    get_implied_cluster_alloc(inode->i_sb, map, ex, path)) {
 		ar.len = allocated = map->m_len;
 		newblock = map->m_pblk;
-		map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+		map_from_cluster = true;
 		goto got_allocated_blocks;
 	}
 
@@ -4412,7 +4408,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	    get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) {
 		ar.len = allocated = map->m_len;
 		newblock = map->m_pblk;
-		map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+		map_from_cluster = true;
 		goto got_allocated_blocks;
 	}
 
@@ -4538,7 +4534,7 @@ got_allocated_blocks:
 		 */
 		reserved_clusters = get_reserved_cluster_alloc(inode,
 						map->m_lblk, allocated);
-		if (map->m_flags & EXT4_MAP_FROM_CLUSTER) {
+		if (map_from_cluster) {
 			if (reserved_clusters) {
 				/*
 				 * We have clusters reserved for this range.
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 3356ab5395f..2315e45161e 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -416,11 +416,6 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
 	}
 	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
 		up_read((&EXT4_I(inode)->i_data_sem));
-	/*
-	 * Clear EXT4_MAP_FROM_CLUSTER and EXT4_MAP_BOUNDARY flag
-	 * because it shouldn't be marked in es_map->m_flags.
-	 */
-	map->m_flags &= ~(EXT4_MAP_FROM_CLUSTER | EXT4_MAP_BOUNDARY);
 
 	/*
 	 * We don't check m_len because extent will be collpased in status
@@ -1434,19 +1429,9 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 	 * file system block.
 	 */
 	down_read(&EXT4_I(inode)->i_data_sem);
-	if (ext4_has_inline_data(inode)) {
-		/*
-		 * We will soon create blocks for this page, and let
-		 * us pretend as if the blocks aren't allocated yet.
-		 * In case of clusters, we have to handle the work
-		 * of mapping from cluster so that the reserved space
-		 * is calculated properly.
-		 */
-		if ((EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) &&
-		    ext4_find_delalloc_cluster(inode, map->m_lblk))
-			map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+	if (ext4_has_inline_data(inode))
 		retval = 0;
-	} else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+	else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		retval = ext4_ext_map_blocks(NULL, inode, map,
 					     EXT4_GET_BLOCKS_NO_PUT_HOLE);
 	else
@@ -1465,7 +1450,8 @@ add_delayed:
 		 * then we don't need to reserve it again. However we still need
 		 * to reserve metadata for every block we're going to write.
 		 */
-		if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) {
+		if (EXT4_SB(inode->i_sb)->s_cluster_ratio <= 1 ||
+		    !ext4_find_delalloc_cluster(inode, map->m_lblk)) {
 			ret = ext4_da_reserve_space(inode, iblock);
 			if (ret) {
 				/* not enough space to reserve */
@@ -1481,11 +1467,6 @@ add_delayed:
 			goto out_unlock;
 		}
 
-		/* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served
-		 * and it should not appear on the bh->b_state.
-		 */
-		map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
-
 		map_bh(bh, inode->i_sb, invalid_block);
 		set_buffer_new(bh);
 		set_buffer_delay(bh);
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index ff4bd1b3524..bb7dcbe9965 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -50,8 +50,7 @@ struct extent_status;
 	{ EXT4_MAP_NEW,		"N" },			\
 	{ EXT4_MAP_MAPPED,	"M" },			\
 	{ EXT4_MAP_UNWRITTEN,	"U" },			\
-	{ EXT4_MAP_BOUNDARY,	"B" },			\
-	{ EXT4_MAP_FROM_CLUSTER, "C" })
+	{ EXT4_MAP_BOUNDARY,	"B" })
 
 #define show_free_flags(flags) __print_flags(flags, "|",	\
 	{ EXT4_FREE_BLOCKS_METADATA,		"METADATA" },	\
-- 
cgit v1.2.3-70-g09d2


From 2f8e0a7c6c89f850ebd5d6c0b9a08317030d1b89 Mon Sep 17 00:00:00 2001
From: Zheng Liu <wenqing.lz@taobao.com>
Date: Tue, 25 Nov 2014 11:44:37 -0500
Subject: ext4: cache extent hole in extent status tree for
 ext4_da_map_blocks()

Currently extent status tree doesn't cache extent hole when a write
looks up in extent tree to make sure whether a block has been allocated
or not.  In this case, we don't put extent hole in extent cache because
later this extent might be removed and a new delayed extent might be
added back.  But it will cause a defect when we do a lot of writes.  If
we don't put extent hole in extent cache, the following writes also need
to access extent tree to look at whether or not a block has been
allocated.  It brings a cache miss.  This commit fixes this defect.
Also if the inode doesn't have any extent, this extent hole will be
cached as well.

Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Signed-off-by: Zheng Liu <wenqing.lz@taobao.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h              |  4 +---
 fs/ext4/extents.c           | 31 ++++++++++++++++---------------
 fs/ext4/inode.c             |  6 ++----
 include/trace/events/ext4.h |  3 +--
 4 files changed, 20 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 7b3f3b1decf..98da4cda9d1 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -556,10 +556,8 @@ enum {
 #define EXT4_GET_BLOCKS_KEEP_SIZE		0x0080
 	/* Do not take i_data_sem locking in ext4_map_blocks */
 #define EXT4_GET_BLOCKS_NO_LOCK			0x0100
-	/* Do not put hole in extent cache */
-#define EXT4_GET_BLOCKS_NO_PUT_HOLE		0x0200
 	/* Convert written extents to unwritten */
-#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN	0x0400
+#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN	0x0200
 
 /*
  * The bit position of these flags must not overlap with any of the
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 7ef2f11aca5..1ee24d74270 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2306,16 +2306,16 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
 				ext4_lblk_t block)
 {
 	int depth = ext_depth(inode);
-	unsigned long len = 0;
-	ext4_lblk_t lblock = 0;
+	ext4_lblk_t len;
+	ext4_lblk_t lblock;
 	struct ext4_extent *ex;
+	struct extent_status es;
 
 	ex = path[depth].p_ext;
 	if (ex == NULL) {
-		/*
-		 * there is no extent yet, so gap is [0;-] and we
-		 * don't cache it
-		 */
+		/* there is no extent yet, so gap is [0;-] */
+		lblock = 0;
+		len = EXT_MAX_BLOCKS;
 		ext_debug("cache gap(whole file):");
 	} else if (block < le32_to_cpu(ex->ee_block)) {
 		lblock = block;
@@ -2324,9 +2324,6 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
 				block,
 				le32_to_cpu(ex->ee_block),
 				 ext4_ext_get_actual_len(ex));
-		if (!ext4_find_delalloc_range(inode, lblock, lblock + len - 1))
-			ext4_es_insert_extent(inode, lblock, len, ~0,
-					      EXTENT_STATUS_HOLE);
 	} else if (block >= le32_to_cpu(ex->ee_block)
 			+ ext4_ext_get_actual_len(ex)) {
 		ext4_lblk_t next;
@@ -2340,14 +2337,19 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
 				block);
 		BUG_ON(next == lblock);
 		len = next - lblock;
-		if (!ext4_find_delalloc_range(inode, lblock, lblock + len - 1))
-			ext4_es_insert_extent(inode, lblock, len, ~0,
-					      EXTENT_STATUS_HOLE);
 	} else {
 		BUG();
 	}
 
-	ext_debug(" -> %u:%lu\n", lblock, len);
+	ext4_es_find_delayed_extent_range(inode, lblock, lblock + len - 1, &es);
+	if (es.es_len) {
+		/* There's delayed extent containing lblock? */
+		if (es.es_lblk <= lblock)
+			return;
+		len = min(es.es_lblk - lblock, len);
+	}
+	ext_debug(" -> %u:%u\n", lblock, len);
+	ext4_es_insert_extent(inode, lblock, len, ~0, EXTENT_STATUS_HOLE);
 }
 
 /*
@@ -4368,8 +4370,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		 * put just found gap into cache to speed up
 		 * subsequent requests
 		 */
-		if ((flags & EXT4_GET_BLOCKS_NO_PUT_HOLE) == 0)
-			ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
+		ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
 		goto out2;
 	}
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2315e45161e..d5a46a8df70 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1432,11 +1432,9 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 	if (ext4_has_inline_data(inode))
 		retval = 0;
 	else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-		retval = ext4_ext_map_blocks(NULL, inode, map,
-					     EXT4_GET_BLOCKS_NO_PUT_HOLE);
+		retval = ext4_ext_map_blocks(NULL, inode, map, 0);
 	else
-		retval = ext4_ind_map_blocks(NULL, inode, map,
-					     EXT4_GET_BLOCKS_NO_PUT_HOLE);
+		retval = ext4_ind_map_blocks(NULL, inode, map, 0);
 
 add_delayed:
 	if (retval == 0) {
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index bb7dcbe9965..cd37a584ee8 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -43,8 +43,7 @@ struct extent_status;
 	{ EXT4_GET_BLOCKS_METADATA_NOFAIL,	"METADATA_NOFAIL" },	\
 	{ EXT4_GET_BLOCKS_NO_NORMALIZE,		"NO_NORMALIZE" },	\
 	{ EXT4_GET_BLOCKS_KEEP_SIZE,		"KEEP_SIZE" },		\
-	{ EXT4_GET_BLOCKS_NO_LOCK,		"NO_LOCK" },		\
-	{ EXT4_GET_BLOCKS_NO_PUT_HOLE,		"NO_PUT_HOLE" })
+	{ EXT4_GET_BLOCKS_NO_LOCK,		"NO_LOCK" })
 
 #define show_mflags(flags) __print_flags(flags, "",	\
 	{ EXT4_MAP_NEW,		"N" },			\
-- 
cgit v1.2.3-70-g09d2


From edaa53cac8fd4b96ed4b8f96c4933158ff2dd337 Mon Sep 17 00:00:00 2001
From: Zheng Liu <wenqing.lz@taobao.com>
Date: Tue, 25 Nov 2014 11:45:37 -0500
Subject: ext4: change LRU to round-robin in extent status tree shrinker

In this commit we discard the lru algorithm for inodes with extent
status tree because it takes significant effort to maintain a lru list
in extent status tree shrinker and the shrinker can take a long time to
scan this lru list in order to reclaim some objects.

We replace the lru ordering with a simple round-robin.  After that we
never need to keep a lru list.  That means that the list needn't be
sorted if the shrinker can not reclaim any objects in the first round.

Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Signed-off-by: Zheng Liu <wenqing.lz@taobao.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h              |  10 +-
 fs/ext4/extents.c           |   4 +-
 fs/ext4/extents_status.c    | 224 +++++++++++++++++++-------------------------
 fs/ext4/extents_status.h    |   7 +-
 fs/ext4/inode.c             |   4 +-
 fs/ext4/ioctl.c             |   4 +-
 fs/ext4/super.c             |   7 +-
 include/trace/events/ext4.h |  11 +--
 8 files changed, 118 insertions(+), 153 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 98da4cda9d1..ab6caf55f5b 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -878,10 +878,9 @@ struct ext4_inode_info {
 	/* extents status tree */
 	struct ext4_es_tree i_es_tree;
 	rwlock_t i_es_lock;
-	struct list_head i_es_lru;
+	struct list_head i_es_list;
 	unsigned int i_es_all_nr;	/* protected by i_es_lock */
-	unsigned int i_es_lru_nr;	/* protected by i_es_lock */
-	unsigned long i_touch_when;	/* jiffies of last accessing */
+	unsigned int i_es_shk_nr;	/* protected by i_es_lock */
 
 	/* ialloc */
 	ext4_group_t	i_last_alloc_group;
@@ -1322,10 +1321,11 @@ struct ext4_sb_info {
 
 	/* Reclaim extents from extent status tree */
 	struct shrinker s_es_shrinker;
-	struct list_head s_es_lru;
+	struct list_head s_es_list;
+	long s_es_nr_inode;
 	struct ext4_es_stats s_es_stats;
 	struct mb_cache *s_mb_cache;
-	spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
+	spinlock_t s_es_lock ____cacheline_aligned_in_smp;
 
 	/* Ratelimit ext4 messages. */
 	struct ratelimit_state s_err_ratelimit_state;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 1ee24d74270..e406f66a903 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4632,7 +4632,7 @@ out2:
 
 	trace_ext4_ext_map_blocks_exit(inode, flags, map,
 				       err ? err : allocated);
-	ext4_es_lru_add(inode);
+	ext4_es_list_add(inode);
 	return err ? err : allocated;
 }
 
@@ -5191,7 +5191,7 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		error = ext4_fill_fiemap_extents(inode, start_blk,
 						 len_blks, fieinfo);
 	}
-	ext4_es_lru_add(inode);
+	ext4_es_list_add(inode);
 	return error;
 }
 
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 94e7855ae71..0193ca10739 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -149,8 +149,8 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 			      ext4_lblk_t end);
 static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
 				       int nr_to_scan);
-static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
-			    struct ext4_inode_info *locked_ei);
+static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
+		       struct ext4_inode_info *locked_ei);
 
 int __init ext4_init_es(void)
 {
@@ -298,6 +298,36 @@ out:
 	trace_ext4_es_find_delayed_extent_range_exit(inode, es);
 }
 
+void ext4_es_list_add(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+	if (!list_empty(&ei->i_es_list))
+		return;
+
+	spin_lock(&sbi->s_es_lock);
+	if (list_empty(&ei->i_es_list)) {
+		list_add_tail(&ei->i_es_list, &sbi->s_es_list);
+		sbi->s_es_nr_inode++;
+	}
+	spin_unlock(&sbi->s_es_lock);
+}
+
+void ext4_es_list_del(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+	spin_lock(&sbi->s_es_lock);
+	if (!list_empty(&ei->i_es_list)) {
+		list_del_init(&ei->i_es_list);
+		sbi->s_es_nr_inode--;
+		WARN_ON_ONCE(sbi->s_es_nr_inode < 0);
+	}
+	spin_unlock(&sbi->s_es_lock);
+}
+
 static struct extent_status *
 ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len,
 		     ext4_fsblk_t pblk)
@@ -314,9 +344,9 @@ ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len,
 	 * We don't count delayed extent because we never try to reclaim them
 	 */
 	if (!ext4_es_is_delayed(es)) {
-		EXT4_I(inode)->i_es_lru_nr++;
+		EXT4_I(inode)->i_es_shk_nr++;
 		percpu_counter_inc(&EXT4_SB(inode->i_sb)->
-					s_es_stats.es_stats_lru_cnt);
+					s_es_stats.es_stats_shk_cnt);
 	}
 
 	EXT4_I(inode)->i_es_all_nr++;
@@ -330,12 +360,12 @@ static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
 	EXT4_I(inode)->i_es_all_nr--;
 	percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt);
 
-	/* Decrease the lru counter when this es is not delayed */
+	/* Decrease the shrink counter when this es is not delayed */
 	if (!ext4_es_is_delayed(es)) {
-		BUG_ON(EXT4_I(inode)->i_es_lru_nr == 0);
-		EXT4_I(inode)->i_es_lru_nr--;
+		BUG_ON(EXT4_I(inode)->i_es_shk_nr == 0);
+		EXT4_I(inode)->i_es_shk_nr--;
 		percpu_counter_dec(&EXT4_SB(inode->i_sb)->
-					s_es_stats.es_stats_lru_cnt);
+					s_es_stats.es_stats_shk_cnt);
 	}
 
 	kmem_cache_free(ext4_es_cachep, es);
@@ -683,8 +713,8 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 		goto error;
 retry:
 	err = __es_insert_extent(inode, &newes);
-	if (err == -ENOMEM && __ext4_es_shrink(EXT4_SB(inode->i_sb), 1,
-					       EXT4_I(inode)))
+	if (err == -ENOMEM && __es_shrink(EXT4_SB(inode->i_sb),
+					  1, EXT4_I(inode)))
 		goto retry;
 	if (err == -ENOMEM && !ext4_es_is_delayed(&newes))
 		err = 0;
@@ -841,8 +871,8 @@ retry:
 				es->es_lblk = orig_es.es_lblk;
 				es->es_len = orig_es.es_len;
 				if ((err == -ENOMEM) &&
-				    __ext4_es_shrink(EXT4_SB(inode->i_sb), 1,
-						     EXT4_I(inode)))
+				    __es_shrink(EXT4_SB(inode->i_sb),
+							1, EXT4_I(inode)))
 					goto retry;
 				goto out;
 			}
@@ -914,6 +944,11 @@ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 	end = lblk + len - 1;
 	BUG_ON(end < lblk);
 
+	/*
+	 * ext4_clear_inode() depends on us taking i_es_lock unconditionally
+	 * so that we are sure __es_shrink() is done with the inode before it
+	 * is reclaimed.
+	 */
 	write_lock(&EXT4_I(inode)->i_es_lock);
 	err = __es_remove_extent(inode, lblk, end);
 	write_unlock(&EXT4_I(inode)->i_es_lock);
@@ -921,114 +956,80 @@ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 	return err;
 }
 
-static int ext4_inode_touch_time_cmp(void *priv, struct list_head *a,
-				     struct list_head *b)
-{
-	struct ext4_inode_info *eia, *eib;
-	eia = list_entry(a, struct ext4_inode_info, i_es_lru);
-	eib = list_entry(b, struct ext4_inode_info, i_es_lru);
-
-	if (ext4_test_inode_state(&eia->vfs_inode, EXT4_STATE_EXT_PRECACHED) &&
-	    !ext4_test_inode_state(&eib->vfs_inode, EXT4_STATE_EXT_PRECACHED))
-		return 1;
-	if (!ext4_test_inode_state(&eia->vfs_inode, EXT4_STATE_EXT_PRECACHED) &&
-	    ext4_test_inode_state(&eib->vfs_inode, EXT4_STATE_EXT_PRECACHED))
-		return -1;
-	if (eia->i_touch_when == eib->i_touch_when)
-		return 0;
-	if (time_after(eia->i_touch_when, eib->i_touch_when))
-		return 1;
-	else
-		return -1;
-}
-
-static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
-			    struct ext4_inode_info *locked_ei)
+static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
+		       struct ext4_inode_info *locked_ei)
 {
 	struct ext4_inode_info *ei;
 	struct ext4_es_stats *es_stats;
-	struct list_head *cur, *tmp;
-	LIST_HEAD(skipped);
 	ktime_t start_time;
 	u64 scan_time;
+	int nr_to_walk;
 	int nr_shrunk = 0;
-	int retried = 0, skip_precached = 1, nr_skipped = 0;
+	int retried = 0, nr_skipped = 0;
 
 	es_stats = &sbi->s_es_stats;
 	start_time = ktime_get();
-	spin_lock(&sbi->s_es_lru_lock);
 
 retry:
-	list_for_each_safe(cur, tmp, &sbi->s_es_lru) {
+	spin_lock(&sbi->s_es_lock);
+	nr_to_walk = sbi->s_es_nr_inode;
+	while (nr_to_walk-- > 0) {
 		int shrunk;
 
-		/*
-		 * If we have already reclaimed all extents from extent
-		 * status tree, just stop the loop immediately.
-		 */
-		if (percpu_counter_read_positive(
-				&es_stats->es_stats_lru_cnt) == 0)
-			break;
-
-		ei = list_entry(cur, struct ext4_inode_info, i_es_lru);
+		if (list_empty(&sbi->s_es_list)) {
+			spin_unlock(&sbi->s_es_lock);
+			goto out;
+		}
+		ei = list_first_entry(&sbi->s_es_list, struct ext4_inode_info,
+				      i_es_list);
+		/* Move the inode to the tail */
+		list_move(&ei->i_es_list, sbi->s_es_list.prev);
 
 		/*
-		 * Skip the inode that is newer than the last_sorted
-		 * time.  Normally we try hard to avoid shrinking
-		 * precached inodes, but we will as a last resort.
+		 * Normally we try hard to avoid shrinking precached inodes,
+		 * but we will as a last resort.
 		 */
-		if ((es_stats->es_stats_last_sorted < ei->i_touch_when) ||
-		    (skip_precached && ext4_test_inode_state(&ei->vfs_inode,
-						EXT4_STATE_EXT_PRECACHED))) {
+		if (!retried && ext4_test_inode_state(&ei->vfs_inode,
+						EXT4_STATE_EXT_PRECACHED)) {
 			nr_skipped++;
-			list_move_tail(cur, &skipped);
 			continue;
 		}
 
-		if (ei->i_es_lru_nr == 0 || ei == locked_ei ||
-		    !write_trylock(&ei->i_es_lock))
+		if (ei == locked_ei || !write_trylock(&ei->i_es_lock)) {
+			nr_skipped++;
 			continue;
+		}
+		/*
+		 * Now we hold i_es_lock which protects us from inode reclaim
+		 * freeing inode under us
+		 */
+		spin_unlock(&sbi->s_es_lock);
 
 		shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan);
-		if (ei->i_es_lru_nr == 0)
-			list_del_init(&ei->i_es_lru);
 		write_unlock(&ei->i_es_lock);
 
 		nr_shrunk += shrunk;
 		nr_to_scan -= shrunk;
+
 		if (nr_to_scan == 0)
-			break;
+			goto out;
+		spin_lock(&sbi->s_es_lock);
 	}
-
-	/* Move the newer inodes into the tail of the LRU list. */
-	list_splice_tail(&skipped, &sbi->s_es_lru);
-	INIT_LIST_HEAD(&skipped);
+	spin_unlock(&sbi->s_es_lock);
 
 	/*
 	 * If we skipped any inodes, and we weren't able to make any
-	 * forward progress, sort the list and try again.
+	 * forward progress, try again to scan precached inodes.
 	 */
 	if ((nr_shrunk == 0) && nr_skipped && !retried) {
 		retried++;
-		list_sort(NULL, &sbi->s_es_lru, ext4_inode_touch_time_cmp);
-		es_stats->es_stats_last_sorted = jiffies;
-		ei = list_first_entry(&sbi->s_es_lru, struct ext4_inode_info,
-				      i_es_lru);
-		/*
-		 * If there are no non-precached inodes left on the
-		 * list, start releasing precached extents.
-		 */
-		if (ext4_test_inode_state(&ei->vfs_inode,
-					  EXT4_STATE_EXT_PRECACHED))
-			skip_precached = 0;
 		goto retry;
 	}
 
-	spin_unlock(&sbi->s_es_lru_lock);
-
 	if (locked_ei && nr_shrunk == 0)
 		nr_shrunk = __es_try_to_reclaim_extents(locked_ei, nr_to_scan);
 
+out:
 	scan_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
 	if (likely(es_stats->es_stats_scan_time))
 		es_stats->es_stats_scan_time = (scan_time +
@@ -1043,7 +1044,7 @@ retry:
 	else
 		es_stats->es_stats_shrunk = nr_shrunk;
 
-	trace_ext4_es_shrink(sbi->s_sb, nr_shrunk, scan_time, skip_precached,
+	trace_ext4_es_shrink(sbi->s_sb, nr_shrunk, scan_time,
 			     nr_skipped, retried);
 	return nr_shrunk;
 }
@@ -1055,7 +1056,7 @@ static unsigned long ext4_es_count(struct shrinker *shrink,
 	struct ext4_sb_info *sbi;
 
 	sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker);
-	nr = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_lru_cnt);
+	nr = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt);
 	trace_ext4_es_shrink_count(sbi->s_sb, sc->nr_to_scan, nr);
 	return nr;
 }
@@ -1068,13 +1069,13 @@ static unsigned long ext4_es_scan(struct shrinker *shrink,
 	int nr_to_scan = sc->nr_to_scan;
 	int ret, nr_shrunk;
 
-	ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_lru_cnt);
+	ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt);
 	trace_ext4_es_shrink_scan_enter(sbi->s_sb, nr_to_scan, ret);
 
 	if (!nr_to_scan)
 		return ret;
 
-	nr_shrunk = __ext4_es_shrink(sbi, nr_to_scan, NULL);
+	nr_shrunk = __es_shrink(sbi, nr_to_scan, NULL);
 
 	trace_ext4_es_shrink_scan_exit(sbi->s_sb, nr_shrunk, ret);
 	return nr_shrunk;
@@ -1102,28 +1103,24 @@ static int ext4_es_seq_shrinker_info_show(struct seq_file *seq, void *v)
 		return 0;
 
 	/* here we just find an inode that has the max nr. of objects */
-	spin_lock(&sbi->s_es_lru_lock);
-	list_for_each_entry(ei, &sbi->s_es_lru, i_es_lru) {
+	spin_lock(&sbi->s_es_lock);
+	list_for_each_entry(ei, &sbi->s_es_list, i_es_list) {
 		inode_cnt++;
 		if (max && max->i_es_all_nr < ei->i_es_all_nr)
 			max = ei;
 		else if (!max)
 			max = ei;
 	}
-	spin_unlock(&sbi->s_es_lru_lock);
+	spin_unlock(&sbi->s_es_lock);
 
 	seq_printf(seq, "stats:\n  %lld objects\n  %lld reclaimable objects\n",
 		   percpu_counter_sum_positive(&es_stats->es_stats_all_cnt),
-		   percpu_counter_sum_positive(&es_stats->es_stats_lru_cnt));
+		   percpu_counter_sum_positive(&es_stats->es_stats_shk_cnt));
 	seq_printf(seq, "  %lu/%lu cache hits/misses\n",
 		   es_stats->es_stats_cache_hits,
 		   es_stats->es_stats_cache_misses);
-	if (es_stats->es_stats_last_sorted != 0)
-		seq_printf(seq, "  %u ms last sorted interval\n",
-			   jiffies_to_msecs(jiffies -
-					    es_stats->es_stats_last_sorted));
 	if (inode_cnt)
-		seq_printf(seq, "  %d inodes on lru list\n", inode_cnt);
+		seq_printf(seq, "  %d inodes on list\n", inode_cnt);
 
 	seq_printf(seq, "average:\n  %llu us scan time\n",
 	    div_u64(es_stats->es_stats_scan_time, 1000));
@@ -1132,7 +1129,7 @@ static int ext4_es_seq_shrinker_info_show(struct seq_file *seq, void *v)
 		seq_printf(seq,
 		    "maximum:\n  %lu inode (%u objects, %u reclaimable)\n"
 		    "  %llu us max scan time\n",
-		    max->vfs_inode.i_ino, max->i_es_all_nr, max->i_es_lru_nr,
+		    max->vfs_inode.i_ino, max->i_es_all_nr, max->i_es_shk_nr,
 		    div_u64(es_stats->es_stats_max_scan_time, 1000));
 
 	return 0;
@@ -1181,9 +1178,9 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi)
 {
 	int err;
 
-	INIT_LIST_HEAD(&sbi->s_es_lru);
-	spin_lock_init(&sbi->s_es_lru_lock);
-	sbi->s_es_stats.es_stats_last_sorted = 0;
+	INIT_LIST_HEAD(&sbi->s_es_list);
+	sbi->s_es_nr_inode = 0;
+	spin_lock_init(&sbi->s_es_lock);
 	sbi->s_es_stats.es_stats_shrunk = 0;
 	sbi->s_es_stats.es_stats_cache_hits = 0;
 	sbi->s_es_stats.es_stats_cache_misses = 0;
@@ -1192,7 +1189,7 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi)
 	err = percpu_counter_init(&sbi->s_es_stats.es_stats_all_cnt, 0, GFP_KERNEL);
 	if (err)
 		return err;
-	err = percpu_counter_init(&sbi->s_es_stats.es_stats_lru_cnt, 0, GFP_KERNEL);
+	err = percpu_counter_init(&sbi->s_es_stats.es_stats_shk_cnt, 0, GFP_KERNEL);
 	if (err)
 		goto err1;
 
@@ -1210,7 +1207,7 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi)
 	return 0;
 
 err2:
-	percpu_counter_destroy(&sbi->s_es_stats.es_stats_lru_cnt);
+	percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt);
 err1:
 	percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt);
 	return err;
@@ -1221,37 +1218,10 @@ void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi)
 	if (sbi->s_proc)
 		remove_proc_entry("es_shrinker_info", sbi->s_proc);
 	percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt);
-	percpu_counter_destroy(&sbi->s_es_stats.es_stats_lru_cnt);
+	percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt);
 	unregister_shrinker(&sbi->s_es_shrinker);
 }
 
-void ext4_es_lru_add(struct inode *inode)
-{
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-
-	ei->i_touch_when = jiffies;
-
-	if (!list_empty(&ei->i_es_lru))
-		return;
-
-	spin_lock(&sbi->s_es_lru_lock);
-	if (list_empty(&ei->i_es_lru))
-		list_add_tail(&ei->i_es_lru, &sbi->s_es_lru);
-	spin_unlock(&sbi->s_es_lru_lock);
-}
-
-void ext4_es_lru_del(struct inode *inode)
-{
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-
-	spin_lock(&sbi->s_es_lru_lock);
-	if (!list_empty(&ei->i_es_lru))
-		list_del_init(&ei->i_es_lru);
-	spin_unlock(&sbi->s_es_lru_lock);
-}
-
 static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
 				       int nr_to_scan)
 {
@@ -1263,7 +1233,7 @@ static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
 	static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
 				      DEFAULT_RATELIMIT_BURST);
 
-	if (ei->i_es_lru_nr == 0)
+	if (ei->i_es_shk_nr == 0)
 		return 0;
 
 	if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED) &&
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index efd5f970b50..0e6a33e81e5 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -65,14 +65,13 @@ struct ext4_es_tree {
 };
 
 struct ext4_es_stats {
-	unsigned long es_stats_last_sorted;
 	unsigned long es_stats_shrunk;
 	unsigned long es_stats_cache_hits;
 	unsigned long es_stats_cache_misses;
 	u64 es_stats_scan_time;
 	u64 es_stats_max_scan_time;
 	struct percpu_counter es_stats_all_cnt;
-	struct percpu_counter es_stats_lru_cnt;
+	struct percpu_counter es_stats_shk_cnt;
 };
 
 extern int __init ext4_init_es(void);
@@ -151,7 +150,7 @@ static inline void ext4_es_store_pblock_status(struct extent_status *es,
 
 extern int ext4_es_register_shrinker(struct ext4_sb_info *sbi);
 extern void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi);
-extern void ext4_es_lru_add(struct inode *inode);
-extern void ext4_es_lru_del(struct inode *inode);
+extern void ext4_es_list_add(struct inode *inode);
+extern void ext4_es_list_del(struct inode *inode);
 
 #endif /* _EXT4_EXTENTS_STATUS_H */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d5a46a8df70..540b0b0481a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -486,7 +486,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 
 	/* Lookup extent status tree firstly */
 	if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
-		ext4_es_lru_add(inode);
+		ext4_es_list_add(inode);
 		if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
 			map->m_pblk = ext4_es_pblock(&es) +
 					map->m_lblk - es.es_lblk;
@@ -1388,7 +1388,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 
 	/* Lookup extent status tree firstly */
 	if (ext4_es_lookup_extent(inode, iblock, &es)) {
-		ext4_es_lru_add(inode);
+		ext4_es_list_add(inode);
 		if (ext4_es_is_hole(&es)) {
 			retval = 0;
 			down_read(&EXT4_I(inode)->i_data_sem);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index bfda18a1559..7b377c41dd8 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -78,8 +78,8 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2)
 	memswap(&ei1->i_disksize, &ei2->i_disksize, sizeof(ei1->i_disksize));
 	ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS);
 	ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS);
-	ext4_es_lru_del(inode1);
-	ext4_es_lru_del(inode2);
+	ext4_es_list_del(inode1);
+	ext4_es_list_del(inode2);
 
 	isize = i_size_read(inode1);
 	i_size_write(inode1, i_size_read(inode2));
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 4b79f39ebf6..32df08e99ca 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -871,10 +871,9 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	spin_lock_init(&ei->i_prealloc_lock);
 	ext4_es_init_tree(&ei->i_es_tree);
 	rwlock_init(&ei->i_es_lock);
-	INIT_LIST_HEAD(&ei->i_es_lru);
+	INIT_LIST_HEAD(&ei->i_es_list);
 	ei->i_es_all_nr = 0;
-	ei->i_es_lru_nr = 0;
-	ei->i_touch_when = 0;
+	ei->i_es_shk_nr = 0;
 	ei->i_reserved_data_blocks = 0;
 	ei->i_reserved_meta_blocks = 0;
 	ei->i_allocated_meta_blocks = 0;
@@ -963,7 +962,7 @@ void ext4_clear_inode(struct inode *inode)
 	dquot_drop(inode);
 	ext4_discard_preallocations(inode);
 	ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
-	ext4_es_lru_del(inode);
+	ext4_es_list_del(inode);
 	if (EXT4_I(inode)->jinode) {
 		jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode),
 					       EXT4_I(inode)->jinode);
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index cd37a584ee8..6cfb841fea7 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -2450,15 +2450,14 @@ TRACE_EVENT(ext4_collapse_range,
 
 TRACE_EVENT(ext4_es_shrink,
 	TP_PROTO(struct super_block *sb, int nr_shrunk, u64 scan_time,
-		 int skip_precached, int nr_skipped, int retried),
+		 int nr_skipped, int retried),
 
-	TP_ARGS(sb, nr_shrunk, scan_time, skip_precached, nr_skipped, retried),
+	TP_ARGS(sb, nr_shrunk, scan_time, nr_skipped, retried),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,		dev		)
 		__field(	int,		nr_shrunk	)
 		__field(	unsigned long long, scan_time	)
-		__field(	int,		skip_precached	)
 		__field(	int,		nr_skipped	)
 		__field(	int,		retried		)
 	),
@@ -2467,16 +2466,14 @@ TRACE_EVENT(ext4_es_shrink,
 		__entry->dev		= sb->s_dev;
 		__entry->nr_shrunk	= nr_shrunk;
 		__entry->scan_time	= div_u64(scan_time, 1000);
-		__entry->skip_precached = skip_precached;
 		__entry->nr_skipped	= nr_skipped;
 		__entry->retried	= retried;
 	),
 
-	TP_printk("dev %d,%d nr_shrunk %d, scan_time %llu skip_precached %d "
+	TP_printk("dev %d,%d nr_shrunk %d, scan_time %llu "
 		  "nr_skipped %d retried %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_shrunk,
-		  __entry->scan_time, __entry->skip_precached,
-		  __entry->nr_skipped, __entry->retried)
+		  __entry->scan_time, __entry->nr_skipped, __entry->retried)
 );
 
 #endif /* _TRACE_EXT4_H */
-- 
cgit v1.2.3-70-g09d2


From e874bf5f7647a9fdf14d72dbb376ec95327e3a81 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 25 Nov 2014 21:41:03 +0100
Subject: ASoC: Disable regmap helpers if regmap is disabled

If regmap is disabled there will be no users of the ASoC regmap helpers.
Furthermore regmap_exit() will no be defined causing the following compile
error:
	sound/soc/soc-core.c: In function 'snd_soc_component_exit_regmap':
	sound/soc/soc-core.c:2645:2: error: implicit declaration of function
		'regmap_exit' [-Werror=implicit-function-declaration]

So disable the helpers if regmap is disabled.

Reported-by: kbuild test robot <fengguang.wu@intel.com>
Fixes: 20feb881988c ASoC: Add helper functions for deferred regmap setup")
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  | 4 ++++
 sound/soc/soc-core.c | 4 ++++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 80ca937a20d..b5323483593 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1286,6 +1286,8 @@ void snd_soc_component_async_complete(struct snd_soc_component *component);
 int snd_soc_component_test_bits(struct snd_soc_component *component,
 	unsigned int reg, unsigned int mask, unsigned int value);
 
+#ifdef CONFIG_REGMAP
+
 void snd_soc_component_init_regmap(struct snd_soc_component *component,
 	struct regmap *regmap);
 void snd_soc_component_exit_regmap(struct snd_soc_component *component);
@@ -1321,6 +1323,8 @@ static inline void snd_soc_codec_exit_regmap(struct snd_soc_codec *codec)
 	snd_soc_component_exit_regmap(&codec->component);
 }
 
+#endif
+
 /* device driver data */
 
 static inline void snd_soc_card_set_drvdata(struct snd_soc_card *card,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index db74c061f52..1edc519d628 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -3661,6 +3661,8 @@ static void snd_soc_component_setup_regmap(struct snd_soc_component *component)
 		component->val_bytes = val_bytes;
 }
 
+#ifdef CONFIG_REGMAP
+
 /**
  * snd_soc_component_init_regmap() - Initialize regmap instance for the component
  * @component: The component for which to initialize the regmap instance
@@ -3696,6 +3698,8 @@ void snd_soc_component_exit_regmap(struct snd_soc_component *component)
 }
 EXPORT_SYMBOL_GPL(snd_soc_component_exit_regmap);
 
+#endif
+
 static void snd_soc_component_add_unlocked(struct snd_soc_component *component)
 {
 	if (!component->write && !component->read) {
-- 
cgit v1.2.3-70-g09d2


From edef1297f33a4546559d905457b435a5ea160bab Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sat, 8 Nov 2014 20:15:09 -0500
Subject: SUNRPC: serialize iostats updates

Occasionally mountstats reports a negative retransmission rate.
Ensure that two RPCs completing concurrently don't confuse the sums
in the transport's op_metrics array.

Since pNFS filelayout can invoke rpc_count_iostats() on another
transport from xprt_release(), we can't rely on simply holding the
transport_lock in xprt_release(). There's nothing for it but hard
serialization. One spin lock per RPC operation should make this as
painless as it can be.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/metrics.h |  3 +++
 net/sunrpc/stats.c             | 21 ++++++++++++++++-----
 2 files changed, 19 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h
index 1565bbe86d5..eecb5a71e6c 100644
--- a/include/linux/sunrpc/metrics.h
+++ b/include/linux/sunrpc/metrics.h
@@ -27,10 +27,13 @@
 
 #include <linux/seq_file.h>
 #include <linux/ktime.h>
+#include <linux/spinlock.h>
 
 #define RPC_IOSTATS_VERS	"1.0"
 
 struct rpc_iostats {
+	spinlock_t		om_lock;
+
 	/*
 	 * These counters give an idea about how many request
 	 * transmissions are required, on average, to complete that
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index 54530490944..9711a155bc5 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -116,7 +116,15 @@ EXPORT_SYMBOL_GPL(svc_seq_show);
  */
 struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt)
 {
-	return kcalloc(clnt->cl_maxproc, sizeof(struct rpc_iostats), GFP_KERNEL);
+	struct rpc_iostats *stats;
+	int i;
+
+	stats = kcalloc(clnt->cl_maxproc, sizeof(*stats), GFP_KERNEL);
+	if (stats) {
+		for (i = 0; i < clnt->cl_maxproc; i++)
+			spin_lock_init(&stats[i].om_lock);
+	}
+	return stats;
 }
 EXPORT_SYMBOL_GPL(rpc_alloc_iostats);
 
@@ -135,20 +143,21 @@ EXPORT_SYMBOL_GPL(rpc_free_iostats);
  * rpc_count_iostats - tally up per-task stats
  * @task: completed rpc_task
  * @stats: array of stat structures
- *
- * Relies on the caller for serialization.
  */
 void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
 {
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_iostats *op_metrics;
-	ktime_t delta;
+	ktime_t delta, now;
 
 	if (!stats || !req)
 		return;
 
+	now = ktime_get();
 	op_metrics = &stats[task->tk_msg.rpc_proc->p_statidx];
 
+	spin_lock(&op_metrics->om_lock);
+
 	op_metrics->om_ops++;
 	op_metrics->om_ntrans += req->rq_ntrans;
 	op_metrics->om_timeouts += task->tk_timeouts;
@@ -161,8 +170,10 @@ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
 
 	op_metrics->om_rtt = ktime_add(op_metrics->om_rtt, req->rq_rtt);
 
-	delta = ktime_sub(ktime_get(), task->tk_start);
+	delta = ktime_sub(now, task->tk_start);
 	op_metrics->om_execute = ktime_add(op_metrics->om_execute, delta);
+
+	spin_unlock(&op_metrics->om_lock);
 }
 EXPORT_SYMBOL_GPL(rpc_count_iostats);
 
-- 
cgit v1.2.3-70-g09d2


From f4ac1674f5da420ef17896f0f222c5215ebcde80 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@netapp.com>
Date: Tue, 25 Nov 2014 13:18:15 -0500
Subject: nfs: Add ALLOCATE support

This patch adds support for using the NFS v4.2 operation ALLOCATE to
preallocate data in a file.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/inode.c            |  1 +
 fs/nfs/nfs42.h            |  1 +
 fs/nfs/nfs42proc.c        | 58 ++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs42xdr.c         | 75 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4_fs.h          |  1 +
 fs/nfs/nfs4file.c         | 28 ++++++++++++++++++
 fs/nfs/nfs4proc.c         |  3 +-
 fs/nfs/nfs4xdr.c          |  1 +
 include/linux/nfs4.h      |  1 +
 include/linux/nfs_fs_sb.h |  1 +
 include/linux/nfs_xdr.h   | 14 +++++++++
 11 files changed, 183 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 2b48ce58a58..4bffe637ea3 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -192,6 +192,7 @@ void nfs_zap_caches(struct inode *inode)
 	nfs_zap_caches_locked(inode);
 	spin_unlock(&inode->i_lock);
 }
+EXPORT_SYMBOL_GPL(nfs_zap_caches);
 
 void nfs_zap_mapping(struct inode *inode, struct address_space *mapping)
 {
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index d10333a197b..42656a9cf48 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -6,6 +6,7 @@
 #define __LINUX_FS_NFS_NFS4_2_H
 
 /* nfs4.2proc.c */
+int nfs42_proc_allocate(struct file *, loff_t, loff_t);
 loff_t nfs42_proc_llseek(struct file *, loff_t, int);
 
 /* nfs4.2xdr.h */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 056f5aafecc..581f34e9d8a 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -32,6 +32,64 @@ static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file,
 	return ret;
 }
 
+static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
+				 loff_t offset, loff_t len)
+{
+	struct inode *inode = file_inode(filep);
+	struct nfs42_falloc_args args = {
+		.falloc_fh	= NFS_FH(inode),
+		.falloc_offset	= offset,
+		.falloc_length	= len,
+	};
+	struct nfs42_falloc_res res;
+	struct nfs_server *server = NFS_SERVER(inode);
+	int status;
+
+	msg->rpc_argp = &args;
+	msg->rpc_resp = &res;
+
+	status = nfs42_set_rw_stateid(&args.falloc_stateid, filep, FMODE_WRITE);
+	if (status)
+		return status;
+
+	return nfs4_call_sync(server->client, server, msg,
+			      &args.seq_args, &res.seq_res, 0);
+}
+
+static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
+				loff_t offset, loff_t len)
+{
+	struct nfs_server *server = NFS_SERVER(file_inode(filep));
+	struct nfs4_exception exception = { };
+	int err;
+
+	do {
+		err = _nfs42_proc_fallocate(msg, filep, offset, len);
+		if (err == -ENOTSUPP)
+			return -EOPNOTSUPP;
+		err = nfs4_handle_exception(server, err, &exception);
+	} while (exception.retry);
+
+	return err;
+}
+
+int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
+{
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE],
+	};
+	struct inode *inode = file_inode(filep);
+	int err;
+
+	if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE))
+		return -EOPNOTSUPP;
+
+	err = nfs42_proc_fallocate(&msg, filep, offset, len);
+	if (err == -EOPNOTSUPP)
+		NFS_SERVER(inode)->caps &= ~NFS_CAP_ALLOCATE;
+	return err;
+}
+
 loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 {
 	struct inode *inode = file_inode(filep);
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index c90469b604b..4248d034479 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -4,6 +4,12 @@
 #ifndef __LINUX_FS_NFS_NFS4_2XDR_H
 #define __LINUX_FS_NFS_NFS4_2XDR_H
 
+#define encode_fallocate_maxsz		(encode_stateid_maxsz + \
+					 2 /* offset */ + \
+					 2 /* length */)
+#define encode_allocate_maxsz		(op_encode_hdr_maxsz + \
+					 encode_fallocate_maxsz)
+#define decode_allocate_maxsz		(op_decode_hdr_maxsz)
 #define encode_seek_maxsz		(op_encode_hdr_maxsz + \
 					 encode_stateid_maxsz + \
 					 2 /* offset */ + \
@@ -14,6 +20,12 @@
 					 2 /* offset */ + \
 					 2 /* length */)
 
+#define NFS4_enc_allocate_sz		(compound_encode_hdr_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_allocate_maxsz)
+#define NFS4_dec_allocate_sz		(compound_decode_hdr_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_allocate_maxsz)
 #define NFS4_enc_seek_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
 					 encode_seek_maxsz)
@@ -22,6 +34,22 @@
 					 decode_seek_maxsz)
 
 
+static void encode_fallocate(struct xdr_stream *xdr,
+			     struct nfs42_falloc_args *args)
+{
+	encode_nfs4_stateid(xdr, &args->falloc_stateid);
+	encode_uint64(xdr, args->falloc_offset);
+	encode_uint64(xdr, args->falloc_length);
+}
+
+static void encode_allocate(struct xdr_stream *xdr,
+			    struct nfs42_falloc_args *args,
+			    struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_ALLOCATE, decode_allocate_maxsz, hdr);
+	encode_fallocate(xdr, args);
+}
+
 static void encode_seek(struct xdr_stream *xdr,
 			struct nfs42_seek_args *args,
 			struct compound_hdr *hdr)
@@ -32,6 +60,24 @@ static void encode_seek(struct xdr_stream *xdr,
 	encode_uint32(xdr, args->sa_what);
 }
 
+/*
+ * Encode ALLOCATE request
+ */
+static void nfs4_xdr_enc_allocate(struct rpc_rqst *req,
+				  struct xdr_stream *xdr,
+				  struct nfs42_falloc_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->falloc_fh, &hdr);
+	encode_allocate(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
 /*
  * Encode SEEK request
  */
@@ -50,6 +96,11 @@ static void nfs4_xdr_enc_seek(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
+static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
+{
+	return decode_op_hdr(xdr, OP_ALLOCATE);
+}
+
 static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res)
 {
 	int status;
@@ -72,6 +123,30 @@ out_overflow:
 	return -EIO;
 }
 
+/*
+ * Decode ALLOCATE request
+ */
+static int nfs4_xdr_dec_allocate(struct rpc_rqst *rqstp,
+				 struct xdr_stream *xdr,
+				 struct nfs42_falloc_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_allocate(xdr, res);
+out:
+	return status;
+}
+
 /*
  * Decode SEEK request
  */
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index be6cac37ea1..a08178764cf 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -226,6 +226,7 @@ int nfs4_replace_transport(struct nfs_server *server,
 				const struct nfs4_fs_locations *locations);
 
 /* nfs4proc.c */
+extern int nfs4_handle_exception(struct nfs_server *, int, struct nfs4_exception *);
 extern int nfs4_call_sync(struct rpc_clnt *, struct nfs_server *,
 			  struct rpc_message *, struct nfs4_sequence_args *,
 			  struct nfs4_sequence_res *, int);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index c51fb4db9bf..f78e9fd0735 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -3,6 +3,8 @@
  *
  *  Copyright (C) 1992  Rick Sladkey
  */
+#include <linux/fs.h>
+#include <linux/falloc.h>
 #include <linux/nfs_fs.h>
 #include "internal.h"
 #include "fscache.h"
@@ -134,6 +136,29 @@ static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
 		return nfs_file_llseek(filep, offset, whence);
 	}
 }
+
+static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t len)
+{
+	struct inode *inode = file_inode(filep);
+	long ret;
+
+	if (!S_ISREG(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	if (mode != 0)
+		return -EOPNOTSUPP;
+
+	ret = inode_newsize_ok(inode, offset + len);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&inode->i_mutex);
+	ret = nfs42_proc_allocate(filep, offset, len);
+	mutex_unlock(&inode->i_mutex);
+
+	nfs_zap_caches(inode);
+	return ret;
+}
 #endif /* CONFIG_NFS_V4_2 */
 
 const struct file_operations nfs4_file_operations = {
@@ -155,6 +180,9 @@ const struct file_operations nfs4_file_operations = {
 	.flock		= nfs_flock,
 	.splice_read	= nfs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
+#ifdef CONFIG_NFS_V4_2
+	.fallocate	= nfs42_fallocate,
+#endif /* CONFIG_NFS_V4_2 */
 	.check_flags	= nfs_check_flags,
 	.setlease	= simple_nosetlease,
 };
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 3138913d1cd..b1b403b0ca0 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -342,7 +342,7 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
 /* This is the error handling routine for processes that are allowed
  * to sleep.
  */
-static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception)
+int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception)
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_state *state = exception->state;
@@ -8424,6 +8424,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
 		| NFS_CAP_ATOMIC_OPEN_V1
+		| NFS_CAP_ALLOCATE
 		| NFS_CAP_SEEK,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 206c08a60c7..0a1484561e4 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7394,6 +7394,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 #endif /* CONFIG_NFS_V4_1 */
 #ifdef CONFIG_NFS_V4_2
 	PROC(SEEK,		enc_seek,		dec_seek),
+	PROC(ALLOCATE,		enc_allocate,		dec_allocate),
 #endif /* CONFIG_NFS_V4_2 */
 };
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 356acc2846f..2b28a21edcd 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -490,6 +490,7 @@ enum {
 
 	/* nfs42 */
 	NFSPROC4_CLNT_SEEK,
+	NFSPROC4_CLNT_ALLOCATE,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index a32ba0d7a98..df6ed429b40 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -231,5 +231,6 @@ struct nfs_server {
 #define NFS_CAP_ATOMIC_OPEN_V1	(1U << 17)
 #define NFS_CAP_SECURITY_LABEL	(1U << 18)
 #define NFS_CAP_SEEK		(1U << 19)
+#define NFS_CAP_ALLOCATE	(1U << 20)
 
 #endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 47ebb4fafd8..467c84efb59 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1243,6 +1243,20 @@ nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo)
 #endif /* CONFIG_NFS_V4_1 */
 
 #ifdef CONFIG_NFS_V4_2
+struct nfs42_falloc_args {
+	struct nfs4_sequence_args	seq_args;
+
+	struct nfs_fh			*falloc_fh;
+	nfs4_stateid			 falloc_stateid;
+	u64				 falloc_offset;
+	u64				 falloc_length;
+};
+
+struct nfs42_falloc_res {
+	struct nfs4_sequence_res	seq_res;
+	unsigned int			status;
+};
+
 struct nfs42_seek_args {
 	struct nfs4_sequence_args	seq_args;
 
-- 
cgit v1.2.3-70-g09d2


From 624bd5b7b683c978c6d5f4e9f6142cfb3470983d Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@netapp.com>
Date: Tue, 25 Nov 2014 13:18:16 -0500
Subject: nfs: Add DEALLOCATE support

This patch adds support for using the NFS v4.2 operation DEALLOCATE to
punch holes in a file.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/nfs42.h            |  1 +
 fs/nfs/nfs42proc.c        | 17 +++++++++++++
 fs/nfs/nfs42xdr.c         | 64 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4file.c         |  7 ++++--
 fs/nfs/nfs4proc.c         |  1 +
 fs/nfs/nfs4xdr.c          |  1 +
 include/linux/nfs4.h      |  1 +
 include/linux/nfs_fs_sb.h |  1 +
 8 files changed, 91 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 42656a9cf48..7afb8947dfd 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -7,6 +7,7 @@
 
 /* nfs4.2proc.c */
 int nfs42_proc_allocate(struct file *, loff_t, loff_t);
+int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
 loff_t nfs42_proc_llseek(struct file *, loff_t, int);
 
 /* nfs4.2xdr.h */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 581f34e9d8a..cb170722769 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -90,6 +90,23 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
 	return err;
 }
 
+int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
+{
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DEALLOCATE],
+	};
+	struct inode *inode = file_inode(filep);
+	int err;
+
+	if (!nfs_server_capable(inode, NFS_CAP_DEALLOCATE))
+		return -EOPNOTSUPP;
+
+	err = nfs42_proc_fallocate(&msg, filep, offset, len);
+	if (err == -EOPNOTSUPP)
+		NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE;
+	return err;
+}
+
 loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 {
 	struct inode *inode = file_inode(filep);
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 4248d034479..038a7e1521f 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -10,6 +10,9 @@
 #define encode_allocate_maxsz		(op_encode_hdr_maxsz + \
 					 encode_fallocate_maxsz)
 #define decode_allocate_maxsz		(op_decode_hdr_maxsz)
+#define encode_deallocate_maxsz		(op_encode_hdr_maxsz + \
+					 encode_fallocate_maxsz)
+#define decode_deallocate_maxsz		(op_decode_hdr_maxsz)
 #define encode_seek_maxsz		(op_encode_hdr_maxsz + \
 					 encode_stateid_maxsz + \
 					 2 /* offset */ + \
@@ -26,6 +29,12 @@
 #define NFS4_dec_allocate_sz		(compound_decode_hdr_maxsz + \
 					 decode_putfh_maxsz + \
 					 decode_allocate_maxsz)
+#define NFS4_enc_deallocate_sz		(compound_encode_hdr_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_deallocate_maxsz)
+#define NFS4_dec_deallocate_sz		(compound_decode_hdr_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_deallocate_maxsz)
 #define NFS4_enc_seek_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
 					 encode_seek_maxsz)
@@ -50,6 +59,14 @@ static void encode_allocate(struct xdr_stream *xdr,
 	encode_fallocate(xdr, args);
 }
 
+static void encode_deallocate(struct xdr_stream *xdr,
+			      struct nfs42_falloc_args *args,
+			      struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_DEALLOCATE, decode_deallocate_maxsz, hdr);
+	encode_fallocate(xdr, args);
+}
+
 static void encode_seek(struct xdr_stream *xdr,
 			struct nfs42_seek_args *args,
 			struct compound_hdr *hdr)
@@ -78,6 +95,24 @@ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
+/*
+ * Encode DEALLOCATE request
+ */
+static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
+				    struct xdr_stream *xdr,
+				    struct nfs42_falloc_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->falloc_fh, &hdr);
+	encode_deallocate(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
 /*
  * Encode SEEK request
  */
@@ -101,6 +136,11 @@ static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
 	return decode_op_hdr(xdr, OP_ALLOCATE);
 }
 
+static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
+{
+	return decode_op_hdr(xdr, OP_DEALLOCATE);
+}
+
 static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res)
 {
 	int status;
@@ -147,6 +187,30 @@ out:
 	return status;
 }
 
+/*
+ * Decode DEALLOCATE request
+ */
+static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
+				   struct xdr_stream *xdr,
+				   struct nfs42_falloc_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_deallocate(xdr, res);
+out:
+	return status;
+}
+
 /*
  * Decode SEEK request
  */
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index f78e9fd0735..8b46389c4c5 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -145,7 +145,7 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t
 	if (!S_ISREG(inode->i_mode))
 		return -EOPNOTSUPP;
 
-	if (mode != 0)
+	if ((mode != 0) && (mode != (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE)))
 		return -EOPNOTSUPP;
 
 	ret = inode_newsize_ok(inode, offset + len);
@@ -153,7 +153,10 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t
 		return ret;
 
 	mutex_lock(&inode->i_mutex);
-	ret = nfs42_proc_allocate(filep, offset, len);
+	if (mode & FALLOC_FL_PUNCH_HOLE)
+		ret = nfs42_proc_deallocate(filep, offset, len);
+	else
+		ret = nfs42_proc_allocate(filep, offset, len);
 	mutex_unlock(&inode->i_mutex);
 
 	nfs_zap_caches(inode);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index b1b403b0ca0..e7f8d5ff258 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -8425,6 +8425,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_STATEID_NFSV41
 		| NFS_CAP_ATOMIC_OPEN_V1
 		| NFS_CAP_ALLOCATE
+		| NFS_CAP_DEALLOCATE
 		| NFS_CAP_SEEK,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 0a1484561e4..03d0fa62a06 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7395,6 +7395,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 #ifdef CONFIG_NFS_V4_2
 	PROC(SEEK,		enc_seek,		dec_seek),
 	PROC(ALLOCATE,		enc_allocate,		dec_allocate),
+	PROC(DEALLOCATE,	enc_deallocate,		dec_deallocate),
 #endif /* CONFIG_NFS_V4_2 */
 };
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 2b28a21edcd..022b761dbf0 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -491,6 +491,7 @@ enum {
 	/* nfs42 */
 	NFSPROC4_CLNT_SEEK,
 	NFSPROC4_CLNT_ALLOCATE,
+	NFSPROC4_CLNT_DEALLOCATE,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index df6ed429b40..1e37fbb78f7 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -232,5 +232,6 @@ struct nfs_server {
 #define NFS_CAP_SECURITY_LABEL	(1U << 18)
 #define NFS_CAP_SEEK		(1U << 19)
 #define NFS_CAP_ALLOCATE	(1U << 20)
+#define NFS_CAP_DEALLOCATE	(1U << 21)
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From c362effe5cda4df02aa7670d58636ea73979e304 Mon Sep 17 00:00:00 2001
From: Jean-Francois Moine <moinejf@free.fr>
Date: Tue, 25 Nov 2014 12:14:48 +0100
Subject: ASoC: Remove 'const' from the device_node pointers

As Russell King's explained it, there should not be pointers to
struct device_node:

"struct device_node is a ref-counted structure.  That means if you
 store a reference to it, you should "get" it, and you should "put"
 it once you've done.  The act of "put"ing the pointed-to structure
 involves writing to that structure, so it is totally unappropriate
 to store a device_node structure as a const pointer.  It forces you
 to have to cast it back to a non-const pointer at various points
 in time to use various OF function calls."

[This isn't quite the application here, we're not geting or putting the
pointer though we did add some other users who call non-const OF
functions -- broonie]

Signed-off-by: Jean-Francois Moine <moinejf@free.fr>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index edbb07ba4cb..d1f3dac91b3 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -881,7 +881,7 @@ struct snd_soc_platform_driver {
 
 struct snd_soc_dai_link_component {
 	const char *name;
-	const struct device_node *of_node;
+	struct device_node *of_node;
 	const char *dai_name;
 };
 
@@ -983,7 +983,7 @@ struct snd_soc_codec_conf {
 	 * DT/OF node, but not both.
 	 */
 	const char *dev_name;
-	const struct device_node *of_node;
+	struct device_node *of_node;
 
 	/*
 	 * optional map of kcontrol, widget and path name prefixes that are
@@ -1000,7 +1000,7 @@ struct snd_soc_aux_dev {
 	 * DT/OF node, but not both.
 	 */
 	const char *codec_name;
-	const struct device_node *codec_of_node;
+	struct device_node *codec_of_node;
 
 	/* codec/machine specific init - e.g. add machine controls */
 	int (*init)(struct snd_soc_component *component);
-- 
cgit v1.2.3-70-g09d2


From bccac16eeaa8c2428981891d09380672b229f48b Mon Sep 17 00:00:00 2001
From: Sudeep Holla <Sudeep.Holla@arm.com>
Date: Tue, 25 Nov 2014 14:48:49 +0000
Subject: ACPI / processor: remove unused variabled from acpi_processor_power
 structure

Few elements in the acpi_processor_power structure are unused. It could
be remnant in the header missed while the code got removed from the
corresponding driver file.

This patch removes those unused variables in the structure declaration.

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/processor.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index cbb6cd3a98d..3ca9b751f12 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -67,9 +67,6 @@ struct acpi_processor_cx {
 };
 
 struct acpi_processor_power {
-	struct acpi_processor_cx *state;
-	unsigned long bm_check_timestamp;
-	u32 default_state;
 	int count;
 	struct acpi_processor_cx states[ACPI_PROCESSOR_MAX_POWER];
 	int timer_broadcast_on_state;
-- 
cgit v1.2.3-70-g09d2


From 3ffb1a8193bead7bf4ef0fec2dae050c70e4c1c1 Mon Sep 17 00:00:00 2001
From: Kevin Cernekee <cernekee@gmail.com>
Date: Wed, 12 Nov 2014 12:53:59 -0800
Subject: serial: core: Add big-endian iotype

Since most drivers interpret UPIO_MEM32 to mean "little-endian" and use
readl/writel to access the registers, add a parallel UPIO_MEM32BE to
request the use of big-endian MMIO accessors (ioread32be/iowrite32be).

Signed-off-by: Kevin Cernekee <cernekee@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c |  2 ++
 include/linux/serial_core.h      | 13 +++++++------
 2 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 5c8b8f50f78..57ca61b1467 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -2153,6 +2153,7 @@ uart_report_port(struct uart_driver *drv, struct uart_port *port)
 		break;
 	case UPIO_MEM:
 	case UPIO_MEM32:
+	case UPIO_MEM32BE:
 	case UPIO_AU:
 	case UPIO_TSI:
 		snprintf(address, sizeof(address),
@@ -2796,6 +2797,7 @@ int uart_match_port(struct uart_port *port1, struct uart_port *port2)
 		       (port1->hub6   == port2->hub6);
 	case UPIO_MEM:
 	case UPIO_MEM32:
+	case UPIO_MEM32BE:
 	case UPIO_AU:
 	case UPIO_TSI:
 		return (port1->mapbase == port2->mapbase);
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 3231a43f6ac..057038cf278 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -142,12 +142,13 @@ struct uart_port {
 	unsigned char		iotype;			/* io access style */
 	unsigned char		unused1;
 
-#define UPIO_PORT		(0)
-#define UPIO_HUB6		(1)
-#define UPIO_MEM		(2)
-#define UPIO_MEM32		(3)
-#define UPIO_AU			(4)			/* Au1x00 and RT288x type IO */
-#define UPIO_TSI		(5)			/* Tsi108/109 type IO */
+#define UPIO_PORT		(0)			/* 8b I/O port access */
+#define UPIO_HUB6		(1)			/* Hub6 ISA card */
+#define UPIO_MEM		(2)			/* 8b MMIO access */
+#define UPIO_MEM32		(3)			/* 32b little endian */
+#define UPIO_MEM32BE		(4)			/* 32b big endian */
+#define UPIO_AU			(5)			/* Au1x00 and RT288x type IO */
+#define UPIO_TSI		(6)			/* Tsi108/109 type IO */
 
 	unsigned int		read_status_mask;	/* driver specific */
 	unsigned int		ignore_status_mask;	/* driver specific */
-- 
cgit v1.2.3-70-g09d2


From 641519cb61bc766c3b4a70fd9ef14fc9509bf8bf Mon Sep 17 00:00:00 2001
From: Brian Norris <computersforpeace@gmail.com>
Date: Tue, 4 Nov 2014 11:32:45 -0800
Subject: mtd: nand: add ATO manufacturer info

Tested with ATO AFND1G08U3, 128MiB NAND.

Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/nand/nand_ids.c | 1 +
 include/linux/mtd/nand.h    | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/mtd/nand/nand_ids.c b/drivers/mtd/nand/nand_ids.c
index fbde8910524..dd620c19c61 100644
--- a/drivers/mtd/nand/nand_ids.c
+++ b/drivers/mtd/nand/nand_ids.c
@@ -178,6 +178,7 @@ struct nand_manufacturers nand_manuf_ids[] = {
 	{NAND_MFR_EON, "Eon"},
 	{NAND_MFR_SANDISK, "SanDisk"},
 	{NAND_MFR_INTEL, "Intel"},
+	{NAND_MFR_ATO, "ATO"},
 	{0x0, "Unknown"}
 };
 
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index b14d190b593..3d4ea7eb2b6 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -736,6 +736,7 @@ struct nand_chip {
 #define NAND_MFR_EON		0x92
 #define NAND_MFR_SANDISK	0x45
 #define NAND_MFR_INTEL		0x89
+#define NAND_MFR_ATO		0x9b
 
 /* The maximum expected count of bytes in the NAND ID sequence */
 #define NAND_MAX_ID_LEN 8
-- 
cgit v1.2.3-70-g09d2


From eee47538ec1f26198cf5da675975b61d7f16135b Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@free-electrons.com>
Date: Thu, 13 Nov 2014 12:47:46 +0100
Subject: phy: add support for USB cluster on the Armada 375 SoC

The Armada 375 SoC comes with an USB2 host and device controller and
an USB3 controller. The USB cluster control register allows to manage
common features of both USB controllers.

This commit adds a driver integrated in the generic PHY framework to
control this USB cluster feature.

Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
[ kishon@ti.com : Made it to use the updated devm_phy_create API and
		  soem cosmentic changes in Kconfig file.]
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
Acked-by: Jason Cooper <jason@lakedaemon.net>
---
 drivers/phy/Kconfig              |   6 ++
 drivers/phy/Makefile             |   1 +
 drivers/phy/phy-armada375-usb2.c | 158 +++++++++++++++++++++++++++++++++++++++
 include/dt-bindings/phy/phy.h    |   1 +
 4 files changed, 166 insertions(+)
 create mode 100644 drivers/phy/phy-armada375-usb2.c

(limited to 'include')

diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index 96d43d5acc5..ccad8809ecb 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -29,6 +29,12 @@ config PHY_BERLIN_SATA
 	help
 	  Enable this to support the SATA PHY on Marvell Berlin SoCs.
 
+config ARMADA375_USBCLUSTER_PHY
+	def_bool y
+	depends on MACH_ARMADA_375 || COMPILE_TEST
+	depends on OF
+	select GENERIC_PHY
+
 config PHY_EXYNOS_MIPI_VIDEO
 	tristate "S5P/EXYNOS SoC series MIPI CSI-2/DSI PHY driver"
 	depends on HAS_IOMEM
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index 68022f698f5..aa74f961e44 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -5,6 +5,7 @@
 obj-$(CONFIG_GENERIC_PHY)		+= phy-core.o
 obj-$(CONFIG_PHY_BERLIN_USB)		+= phy-berlin-usb.o
 obj-$(CONFIG_PHY_BERLIN_SATA)		+= phy-berlin-sata.o
+obj-$(CONFIG_ARMADA375_USBCLUSTER_PHY)	+= phy-armada375-usb2.o
 obj-$(CONFIG_BCM_KONA_USB2_PHY)		+= phy-bcm-kona-usb2.o
 obj-$(CONFIG_PHY_EXYNOS_DP_VIDEO)	+= phy-exynos-dp-video.o
 obj-$(CONFIG_PHY_EXYNOS_MIPI_VIDEO)	+= phy-exynos-mipi-video.o
diff --git a/drivers/phy/phy-armada375-usb2.c b/drivers/phy/phy-armada375-usb2.c
new file mode 100644
index 00000000000..ac7d99d01cb
--- /dev/null
+++ b/drivers/phy/phy-armada375-usb2.c
@@ -0,0 +1,158 @@
+/*
+ * USB cluster support for Armada 375 platform.
+ *
+ * Copyright (C) 2014 Marvell
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2 or later. This program is licensed "as is"
+ * without any warranty of any kind, whether express or implied.
+ *
+ * Armada 375 comes with an USB2 host and device controller and an
+ * USB3 controller. The USB cluster control register allows to manage
+ * common features of both USB controllers.
+ */
+
+#include <dt-bindings/phy/phy.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+
+#define USB2_PHY_CONFIG_DISABLE BIT(0)
+
+struct armada375_cluster_phy {
+	struct phy *phy;
+	void __iomem *reg;
+	bool use_usb3;
+	int phy_provided;
+};
+
+static int armada375_usb_phy_init(struct phy *phy)
+{
+	struct armada375_cluster_phy *cluster_phy;
+	u32 reg;
+
+	cluster_phy = dev_get_drvdata(phy->dev.parent);
+	if (!cluster_phy)
+		return -ENODEV;
+
+	reg = readl(cluster_phy->reg);
+	if (cluster_phy->use_usb3)
+		reg |= USB2_PHY_CONFIG_DISABLE;
+	else
+		reg &= ~USB2_PHY_CONFIG_DISABLE;
+	writel(reg, cluster_phy->reg);
+
+	return 0;
+}
+
+static struct phy_ops armada375_usb_phy_ops = {
+	.init = armada375_usb_phy_init,
+	.owner = THIS_MODULE,
+};
+
+/*
+ * Only one controller can use this PHY. We shouldn't have the case
+ * when two controllers want to use this PHY. But if this case occurs
+ * then we provide a phy to the first one and return an error for the
+ * next one. This error has also to be an error returned by
+ * devm_phy_optional_get() so different from ENODEV for USB2. In the
+ * USB3 case it still optional and we use ENODEV.
+ */
+static struct phy *armada375_usb_phy_xlate(struct device *dev,
+					struct of_phandle_args *args)
+{
+	struct armada375_cluster_phy *cluster_phy = dev_get_drvdata(dev);
+
+	if (!cluster_phy)
+		return  ERR_PTR(-ENODEV);
+
+	/*
+	 * Either the phy had never been requested and then the first
+	 * usb claiming it can get it, or it had already been
+	 * requested in this case, we only allow to use it with the
+	 * same configuration.
+	 */
+	if (WARN_ON((cluster_phy->phy_provided != PHY_NONE) &&
+			(cluster_phy->phy_provided != args->args[0]))) {
+		dev_err(dev, "This PHY has already been provided!\n");
+		dev_err(dev, "Check your device tree, only one controller can use it\n.");
+		if (args->args[0] == PHY_TYPE_USB2)
+			return ERR_PTR(-EBUSY);
+		else
+			return ERR_PTR(-ENODEV);
+	}
+
+	if (args->args[0] == PHY_TYPE_USB2)
+		cluster_phy->use_usb3 = false;
+	else if (args->args[0] == PHY_TYPE_USB3)
+		cluster_phy->use_usb3 = true;
+	else {
+		dev_err(dev, "Invalid PHY mode\n");
+		return ERR_PTR(-ENODEV);
+	}
+
+	/* Store which phy mode is used for next test */
+	cluster_phy->phy_provided = args->args[0];
+
+	return cluster_phy->phy;
+}
+
+static int armada375_usb_phy_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct phy *phy;
+	struct phy_provider *phy_provider;
+	void __iomem *usb_cluster_base;
+	struct resource *res;
+	struct armada375_cluster_phy *cluster_phy;
+
+	cluster_phy = devm_kzalloc(dev, sizeof(*cluster_phy), GFP_KERNEL);
+	if (!cluster_phy)
+		return  -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	usb_cluster_base = devm_ioremap_resource(&pdev->dev, res);
+	if (!usb_cluster_base)
+		return -ENOMEM;
+
+	phy = devm_phy_create(dev, NULL, &armada375_usb_phy_ops);
+	if (IS_ERR(phy)) {
+		dev_err(dev, "failed to create PHY\n");
+		return PTR_ERR(phy);
+	}
+
+	cluster_phy->phy = phy;
+	cluster_phy->reg = usb_cluster_base;
+
+	dev_set_drvdata(dev, cluster_phy);
+
+	phy_provider = devm_of_phy_provider_register(&pdev->dev,
+						     armada375_usb_phy_xlate);
+	return PTR_ERR_OR_ZERO(phy_provider);
+}
+
+static const struct of_device_id of_usb_cluster_table[] = {
+	{ .compatible = "marvell,armada-375-usb-cluster", },
+	{ /* end of list */ },
+};
+MODULE_DEVICE_TABLE(of, of_usb_cluster_table);
+
+static struct platform_driver armada375_usb_phy_driver = {
+	.probe	= armada375_usb_phy_probe,
+	.driver = {
+		.of_match_table	= of_usb_cluster_table,
+		.name  = "armada-375-usb-cluster",
+		.owner = THIS_MODULE,
+	}
+};
+module_platform_driver(armada375_usb_phy_driver);
+
+MODULE_DESCRIPTION("Armada 375 USB cluster driver");
+MODULE_AUTHOR("Gregory CLEMENT <gregory.clement@free-electrons.com>");
+MODULE_LICENSE("GPL");
diff --git a/include/dt-bindings/phy/phy.h b/include/dt-bindings/phy/phy.h
index e8c6a3f04b8..6c901930eb3 100644
--- a/include/dt-bindings/phy/phy.h
+++ b/include/dt-bindings/phy/phy.h
@@ -10,6 +10,7 @@
 #ifndef _DT_BINDINGS_PHY
 #define _DT_BINDINGS_PHY
 
+#define PHY_NONE		0
 #define PHY_TYPE_SATA		1
 #define PHY_TYPE_PCIE		2
 #define PHY_TYPE_USB2		3
-- 
cgit v1.2.3-70-g09d2


From 4f4f85fa0b96a35429ebb4bc278d70ae0f72113c Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Tue, 29 Jul 2014 10:17:53 +0200
Subject: clk: tegra: Implement memory-controller clock

The memory controller clock runs either at half or the same frequency as
the EMC clock.

Reviewed-By: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Acked-by: Mike Turquette <mturquette@linaro.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/clk/tegra/clk-divider.c          | 13 +++++++++++++
 drivers/clk/tegra/clk-tegra114.c         |  7 ++++++-
 drivers/clk/tegra/clk-tegra124.c         |  7 ++++++-
 drivers/clk/tegra/clk-tegra20.c          |  8 +++++++-
 drivers/clk/tegra/clk-tegra30.c          |  7 ++++++-
 drivers/clk/tegra/clk.h                  |  2 ++
 include/dt-bindings/clock/tegra114-car.h |  2 +-
 include/dt-bindings/clock/tegra124-car.h |  2 +-
 include/dt-bindings/clock/tegra20-car.h  |  2 +-
 9 files changed, 43 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/tegra/clk-divider.c b/drivers/clk/tegra/clk-divider.c
index 290f9c1a374..59a5714dfe1 100644
--- a/drivers/clk/tegra/clk-divider.c
+++ b/drivers/clk/tegra/clk-divider.c
@@ -185,3 +185,16 @@ struct clk *tegra_clk_register_divider(const char *name,
 
 	return clk;
 }
+
+static const struct clk_div_table mc_div_table[] = {
+	{ .val = 0, .div = 2 },
+	{ .val = 1, .div = 1 },
+	{ .val = 0, .div = 0 },
+};
+
+struct clk *tegra_clk_register_mc(const char *name, const char *parent_name,
+				  void __iomem *reg, spinlock_t *lock)
+{
+	return clk_register_divider_table(NULL, name, parent_name, 0, reg,
+					  16, 1, 0, mc_div_table, lock);
+}
diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c
index f760f31d05c..0b03d2cf726 100644
--- a/drivers/clk/tegra/clk-tegra114.c
+++ b/drivers/clk/tegra/clk-tegra114.c
@@ -173,6 +173,7 @@ static DEFINE_SPINLOCK(pll_d_lock);
 static DEFINE_SPINLOCK(pll_d2_lock);
 static DEFINE_SPINLOCK(pll_u_lock);
 static DEFINE_SPINLOCK(pll_re_lock);
+static DEFINE_SPINLOCK(emc_lock);
 
 static struct div_nmp pllxc_nmp = {
 	.divm_shift = 0,
@@ -1228,7 +1229,11 @@ static __init void tegra114_periph_clk_init(void __iomem *clk_base,
 			       ARRAY_SIZE(mux_pllmcp_clkm),
 			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + CLK_SOURCE_EMC,
-			       29, 3, 0, NULL);
+			       29, 3, 0, &emc_lock);
+
+	clk = tegra_clk_register_mc("mc", "emc_mux", clk_base + CLK_SOURCE_EMC,
+				    &emc_lock);
+	clks[TEGRA114_CLK_MC] = clk;
 
 	for (i = 0; i < ARRAY_SIZE(tegra_periph_clk_list); i++) {
 		data = &tegra_periph_clk_list[i];
diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index e3a85842ce0..f5f9baca7bb 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -132,6 +132,7 @@ static DEFINE_SPINLOCK(pll_d2_lock);
 static DEFINE_SPINLOCK(pll_e_lock);
 static DEFINE_SPINLOCK(pll_re_lock);
 static DEFINE_SPINLOCK(pll_u_lock);
+static DEFINE_SPINLOCK(emc_lock);
 
 /* possible OSC frequencies in Hz */
 static unsigned long tegra124_input_freq[] = {
@@ -1127,7 +1128,11 @@ static __init void tegra124_periph_clk_init(void __iomem *clk_base,
 	clk = clk_register_mux(NULL, "emc_mux", mux_pllmcp_clkm,
 			       ARRAY_SIZE(mux_pllmcp_clkm), 0,
 			       clk_base + CLK_SOURCE_EMC,
-			       29, 3, 0, NULL);
+			       29, 3, 0, &emc_lock);
+
+	clk = tegra_clk_register_mc("mc", "emc_mux", clk_base + CLK_SOURCE_EMC,
+				    &emc_lock);
+	clks[TEGRA124_CLK_MC] = clk;
 
 	/* cml0 */
 	clk = clk_register_gate(NULL, "cml0", "pll_e", 0, clk_base + PLLE_AUX,
diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c
index dace2b1b5ae..41272dcc9e2 100644
--- a/drivers/clk/tegra/clk-tegra20.c
+++ b/drivers/clk/tegra/clk-tegra20.c
@@ -140,6 +140,8 @@ static struct cpu_clk_suspend_context {
 static void __iomem *clk_base;
 static void __iomem *pmc_base;
 
+static DEFINE_SPINLOCK(emc_lock);
+
 #define TEGRA_INIT_DATA_MUX(_name, _parents, _offset,	\
 			    _clk_num, _gate_flags, _clk_id)	\
 	TEGRA_INIT_DATA(_name, NULL, NULL, _parents, _offset,	\
@@ -819,11 +821,15 @@ static void __init tegra20_periph_clk_init(void)
 			       ARRAY_SIZE(mux_pllmcp_clkm),
 			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + CLK_SOURCE_EMC,
-			       30, 2, 0, NULL);
+			       30, 2, 0, &emc_lock);
 	clk = tegra_clk_register_periph_gate("emc", "emc_mux", 0, clk_base, 0,
 				    57, periph_clk_enb_refcnt);
 	clks[TEGRA20_CLK_EMC] = clk;
 
+	clk = tegra_clk_register_mc("mc", "emc_mux", clk_base + CLK_SOURCE_EMC,
+				    &emc_lock);
+	clks[TEGRA20_CLK_MC] = clk;
+
 	/* dsi */
 	clk = tegra_clk_register_periph_gate("dsi", "pll_d", 0, clk_base, 0,
 				    48, periph_clk_enb_refcnt);
diff --git a/drivers/clk/tegra/clk-tegra30.c b/drivers/clk/tegra/clk-tegra30.c
index 5bbacd01094..4b9d8bd3d0b 100644
--- a/drivers/clk/tegra/clk-tegra30.c
+++ b/drivers/clk/tegra/clk-tegra30.c
@@ -177,6 +177,7 @@ static unsigned long input_freq;
 
 static DEFINE_SPINLOCK(cml_lock);
 static DEFINE_SPINLOCK(pll_d_lock);
+static DEFINE_SPINLOCK(emc_lock);
 
 #define TEGRA_INIT_DATA_MUX(_name, _parents, _offset,	\
 			    _clk_num, _gate_flags, _clk_id)	\
@@ -1157,11 +1158,15 @@ static void __init tegra30_periph_clk_init(void)
 			       ARRAY_SIZE(mux_pllmcp_clkm),
 			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + CLK_SOURCE_EMC,
-			       30, 2, 0, NULL);
+			       30, 2, 0, &emc_lock);
 	clk = tegra_clk_register_periph_gate("emc", "emc_mux", 0, clk_base, 0,
 				    57, periph_clk_enb_refcnt);
 	clks[TEGRA30_CLK_EMC] = clk;
 
+	clk = tegra_clk_register_mc("mc", "emc_mux", clk_base + CLK_SOURCE_EMC,
+				    &emc_lock);
+	clks[TEGRA30_CLK_MC] = clk;
+
 	/* cml0 */
 	clk = clk_register_gate(NULL, "cml0", "pll_e", 0, clk_base + PLLE_AUX,
 				0, 0, &cml_lock);
diff --git a/drivers/clk/tegra/clk.h b/drivers/clk/tegra/clk.h
index 16ec8d6bb87..4e458aa8d45 100644
--- a/drivers/clk/tegra/clk.h
+++ b/drivers/clk/tegra/clk.h
@@ -86,6 +86,8 @@ struct clk *tegra_clk_register_divider(const char *name,
 		const char *parent_name, void __iomem *reg,
 		unsigned long flags, u8 clk_divider_flags, u8 shift, u8 width,
 		u8 frac_width, spinlock_t *lock);
+struct clk *tegra_clk_register_mc(const char *name, const char *parent_name,
+				  void __iomem *reg, spinlock_t *lock);
 
 /*
  * Tegra PLL:
diff --git a/include/dt-bindings/clock/tegra114-car.h b/include/dt-bindings/clock/tegra114-car.h
index fc12621fb43..534c03f8ad7 100644
--- a/include/dt-bindings/clock/tegra114-car.h
+++ b/include/dt-bindings/clock/tegra114-car.h
@@ -49,7 +49,7 @@
 #define TEGRA114_CLK_I2S0 30
 /* 31 */
 
-/* 32 */
+#define TEGRA114_CLK_MC 32
 /* 33 */
 #define TEGRA114_CLK_APBDMA 34
 /* 35 */
diff --git a/include/dt-bindings/clock/tegra124-car.h b/include/dt-bindings/clock/tegra124-car.h
index 6bac637fd63..af9bc9a3ddb 100644
--- a/include/dt-bindings/clock/tegra124-car.h
+++ b/include/dt-bindings/clock/tegra124-car.h
@@ -48,7 +48,7 @@
 #define TEGRA124_CLK_I2S0 30
 /* 31 */
 
-/* 32 */
+#define TEGRA124_CLK_MC 32
 /* 33 */
 #define TEGRA124_CLK_APBDMA 34
 /* 35 */
diff --git a/include/dt-bindings/clock/tegra20-car.h b/include/dt-bindings/clock/tegra20-car.h
index 9406207cfac..04500b243a4 100644
--- a/include/dt-bindings/clock/tegra20-car.h
+++ b/include/dt-bindings/clock/tegra20-car.h
@@ -49,7 +49,7 @@
 /* 30 */
 #define TEGRA20_CLK_CACHE2 31
 
-#define TEGRA20_CLK_MEM 32
+#define TEGRA20_CLK_MC 32
 #define TEGRA20_CLK_AHBDMA 33
 #define TEGRA20_CLK_APBDMA 34
 /* 35 */
-- 
cgit v1.2.3-70-g09d2


From 5b97f49d653d366d8cb03cab40f8c45eb59dc70c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 26 Nov 2014 12:37:43 +0100
Subject: cfg80211: refactor the various CQM event sending code

Much of the code can be shared by moving it into helper functions
for the CQM event sending.

Also move the code closer together, even in the header file.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h |  54 ++++++------
 net/wireless/nl80211.c | 222 ++++++++++++++++++++++---------------------------
 2 files changed, 126 insertions(+), 150 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index bb748c4da5a..1d15f1dfdaa 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4642,33 +4642,6 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev,
 			      enum nl80211_cqm_rssi_threshold_event rssi_event,
 			      gfp_t gfp);
 
-/**
- * cfg80211_radar_event - radar detection event
- * @wiphy: the wiphy
- * @chandef: chandef for the current channel
- * @gfp: context flags
- *
- * This function is called when a radar is detected on the current chanenl.
- */
-void cfg80211_radar_event(struct wiphy *wiphy,
-			  struct cfg80211_chan_def *chandef, gfp_t gfp);
-
-/**
- * cfg80211_cac_event - Channel availability check (CAC) event
- * @netdev: network device
- * @chandef: chandef for the current channel
- * @event: type of event
- * @gfp: context flags
- *
- * This function is called when a Channel availability check (CAC) is finished
- * or aborted. This must be called to notify the completion of a CAC process,
- * also by full-MAC drivers.
- */
-void cfg80211_cac_event(struct net_device *netdev,
-			const struct cfg80211_chan_def *chandef,
-			enum nl80211_radar_event event, gfp_t gfp);
-
-
 /**
  * cfg80211_cqm_pktloss_notify - notify userspace about packetloss to peer
  * @dev: network device
@@ -4696,6 +4669,33 @@ void cfg80211_cqm_pktloss_notify(struct net_device *dev,
 void cfg80211_cqm_txe_notify(struct net_device *dev, const u8 *peer,
 			     u32 num_packets, u32 rate, u32 intvl, gfp_t gfp);
 
+/**
+ * cfg80211_radar_event - radar detection event
+ * @wiphy: the wiphy
+ * @chandef: chandef for the current channel
+ * @gfp: context flags
+ *
+ * This function is called when a radar is detected on the current chanenl.
+ */
+void cfg80211_radar_event(struct wiphy *wiphy,
+			  struct cfg80211_chan_def *chandef, gfp_t gfp);
+
+/**
+ * cfg80211_cac_event - Channel availability check (CAC) event
+ * @netdev: network device
+ * @chandef: chandef for the current channel
+ * @event: type of event
+ * @gfp: context flags
+ *
+ * This function is called when a Channel availability check (CAC) is finished
+ * or aborted. This must be called to notify the completion of a CAC process,
+ * also by full-MAC drivers.
+ */
+void cfg80211_cac_event(struct net_device *netdev,
+			const struct cfg80211_chan_def *chandef,
+			enum nl80211_radar_event event, gfp_t gfp);
+
+
 /**
  * cfg80211_gtk_rekey_notify - notify userspace about driver rekeying
  * @dev: network device
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index b5e3c489239..9c4d0102d34 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -11766,55 +11766,132 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
 }
 EXPORT_SYMBOL(cfg80211_mgmt_tx_status);
 
-void cfg80211_cqm_rssi_notify(struct net_device *dev,
-			      enum nl80211_cqm_rssi_threshold_event rssi_event,
-			      gfp_t gfp)
+static struct sk_buff *cfg80211_prepare_cqm(struct net_device *dev,
+					    const char *mac, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
-	struct sk_buff *msg;
-	struct nlattr *pinfoattr;
-	void *hdr;
-
-	trace_cfg80211_cqm_rssi_notify(dev, rssi_event);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+	struct sk_buff *msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp);
+	void **cb;
 
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp);
 	if (!msg)
-		return;
+		return NULL;
 
-	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_NOTIFY_CQM);
-	if (!hdr) {
+	cb = (void **)msg->cb;
+
+	cb[0] = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_NOTIFY_CQM);
+	if (!cb[0]) {
 		nlmsg_free(msg);
-		return;
+		return NULL;
 	}
 
 	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
 	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex))
 		goto nla_put_failure;
 
-	pinfoattr = nla_nest_start(msg, NL80211_ATTR_CQM);
-	if (!pinfoattr)
+	if (mac && nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac))
 		goto nla_put_failure;
 
-	if (nla_put_u32(msg, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT,
-			rssi_event))
+	cb[1] = nla_nest_start(msg, NL80211_ATTR_CQM);
+	if (!cb[1])
 		goto nla_put_failure;
 
-	nla_nest_end(msg, pinfoattr);
+	cb[2] = rdev;
 
-	genlmsg_end(msg, hdr);
+	return msg;
+ nla_put_failure:
+	nlmsg_free(msg);
+	return NULL;
+}
+
+static void cfg80211_send_cqm(struct sk_buff *msg, gfp_t gfp)
+{
+	void **cb = (void **)msg->cb;
+	struct cfg80211_registered_device *rdev = cb[2];
+
+	nla_nest_end(msg, cb[1]);
+	genlmsg_end(msg, cb[0]);
+
+	memset(msg->cb, 0, sizeof(msg->cb));
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				NL80211_MCGRP_MLME, gfp);
+}
+
+void cfg80211_cqm_rssi_notify(struct net_device *dev,
+			      enum nl80211_cqm_rssi_threshold_event rssi_event,
+			      gfp_t gfp)
+{
+	struct sk_buff *msg;
+
+	trace_cfg80211_cqm_rssi_notify(dev, rssi_event);
+
+	msg = cfg80211_prepare_cqm(dev, NULL, gfp);
+	if (!msg)
+		return;
+
+	if (nla_put_u32(msg, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT,
+			rssi_event))
+		goto nla_put_failure;
+
+	cfg80211_send_cqm(msg, gfp);
+
 	return;
 
  nla_put_failure:
-	genlmsg_cancel(msg, hdr);
 	nlmsg_free(msg);
 }
 EXPORT_SYMBOL(cfg80211_cqm_rssi_notify);
 
+void cfg80211_cqm_txe_notify(struct net_device *dev,
+			     const u8 *peer, u32 num_packets,
+			     u32 rate, u32 intvl, gfp_t gfp)
+{
+	struct sk_buff *msg;
+
+	msg = cfg80211_prepare_cqm(dev, peer, gfp);
+	if (!msg)
+		return;
+
+	if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_PKTS, num_packets))
+		goto nla_put_failure;
+
+	if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_RATE, rate))
+		goto nla_put_failure;
+
+	if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_INTVL, intvl))
+		goto nla_put_failure;
+
+	cfg80211_send_cqm(msg, gfp);
+	return;
+
+ nla_put_failure:
+	nlmsg_free(msg);
+}
+EXPORT_SYMBOL(cfg80211_cqm_txe_notify);
+
+void cfg80211_cqm_pktloss_notify(struct net_device *dev,
+				 const u8 *peer, u32 num_packets, gfp_t gfp)
+{
+	struct sk_buff *msg;
+
+	trace_cfg80211_cqm_pktloss_notify(dev, peer, num_packets);
+
+	msg = cfg80211_prepare_cqm(dev, peer, gfp);
+	if (!msg)
+		return;
+
+	if (nla_put_u32(msg, NL80211_ATTR_CQM_PKT_LOSS_EVENT, num_packets))
+		goto nla_put_failure;
+
+	cfg80211_send_cqm(msg, gfp);
+	return;
+
+ nla_put_failure:
+	nlmsg_free(msg);
+}
+EXPORT_SYMBOL(cfg80211_cqm_pktloss_notify);
+
 static void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev,
 				     struct net_device *netdev, const u8 *bssid,
 				     const u8 *replay_ctr, gfp_t gfp)
@@ -12003,59 +12080,6 @@ void cfg80211_ch_switch_started_notify(struct net_device *dev,
 }
 EXPORT_SYMBOL(cfg80211_ch_switch_started_notify);
 
-void cfg80211_cqm_txe_notify(struct net_device *dev,
-			     const u8 *peer, u32 num_packets,
-			     u32 rate, u32 intvl, gfp_t gfp)
-{
-	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
-	struct sk_buff *msg;
-	struct nlattr *pinfoattr;
-	void *hdr;
-
-	msg = nlmsg_new(NLMSG_GOODSIZE, gfp);
-	if (!msg)
-		return;
-
-	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_NOTIFY_CQM);
-	if (!hdr) {
-		nlmsg_free(msg);
-		return;
-	}
-
-	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
-	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
-	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, peer))
-		goto nla_put_failure;
-
-	pinfoattr = nla_nest_start(msg, NL80211_ATTR_CQM);
-	if (!pinfoattr)
-		goto nla_put_failure;
-
-	if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_PKTS, num_packets))
-		goto nla_put_failure;
-
-	if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_RATE, rate))
-		goto nla_put_failure;
-
-	if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_INTVL, intvl))
-		goto nla_put_failure;
-
-	nla_nest_end(msg, pinfoattr);
-
-	genlmsg_end(msg, hdr);
-
-	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				NL80211_MCGRP_MLME, gfp);
-	return;
-
- nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	nlmsg_free(msg);
-}
-EXPORT_SYMBOL(cfg80211_cqm_txe_notify);
-
 void
 nl80211_radar_notify(struct cfg80211_registered_device *rdev,
 		     const struct cfg80211_chan_def *chandef,
@@ -12104,54 +12128,6 @@ nl80211_radar_notify(struct cfg80211_registered_device *rdev,
 	nlmsg_free(msg);
 }
 
-void cfg80211_cqm_pktloss_notify(struct net_device *dev,
-				 const u8 *peer, u32 num_packets, gfp_t gfp)
-{
-	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
-	struct sk_buff *msg;
-	struct nlattr *pinfoattr;
-	void *hdr;
-
-	trace_cfg80211_cqm_pktloss_notify(dev, peer, num_packets);
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp);
-	if (!msg)
-		return;
-
-	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_NOTIFY_CQM);
-	if (!hdr) {
-		nlmsg_free(msg);
-		return;
-	}
-
-	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
-	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
-	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, peer))
-		goto nla_put_failure;
-
-	pinfoattr = nla_nest_start(msg, NL80211_ATTR_CQM);
-	if (!pinfoattr)
-		goto nla_put_failure;
-
-	if (nla_put_u32(msg, NL80211_ATTR_CQM_PKT_LOSS_EVENT, num_packets))
-		goto nla_put_failure;
-
-	nla_nest_end(msg, pinfoattr);
-
-	genlmsg_end(msg, hdr);
-
-	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				NL80211_MCGRP_MLME, gfp);
-	return;
-
- nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	nlmsg_free(msg);
-}
-EXPORT_SYMBOL(cfg80211_cqm_pktloss_notify);
-
 void cfg80211_probe_status(struct net_device *dev, const u8 *addr,
 			   u64 cookie, bool acked, gfp_t gfp)
 {
-- 
cgit v1.2.3-70-g09d2


From 9b8ffea6efb0d0edcac265a1ca422188fc1b6dfb Mon Sep 17 00:00:00 2001
From: Vincent Wan <vincent.wan@amd.com>
Date: Wed, 5 Nov 2014 14:09:00 +0800
Subject: mmc: sdhci: Add a quirk for AMD SDHC transfer mode register need to
 be cleared for cmd without data

SDHC controller in AMD chipsets require SDHC transfer mode
register to be cleared for commands without data. The issue was
uncovered during testing eMMC cards on KB/ML based platforms

Signed-off-by: Vincent Wan <vincent.wan@amd.com>
Signed-off-by: Wan Zongshun <mcuos.com@gmail.com>
Signed-off-by: Arindam Nath <arindam.nath@amd.com>
Tested-by: Vikram B <vikram.b@amd.com>
Tested-by: Raghavendra Swamy <raghavendra.swamy@amd.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.c  | 9 +++++++--
 include/linux/mmc/sdhci.h | 2 ++
 2 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index f895ab07fcc..a743d5227ed 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -915,10 +915,15 @@ static void sdhci_set_transfer_mode(struct sdhci_host *host,
 	struct mmc_data *data = cmd->data;
 
 	if (data == NULL) {
+		if (host->quirks2 &
+			SDHCI_QUIRK2_CLEAR_TRANSFERMODE_REG_BEFORE_CMD) {
+			sdhci_writew(host, 0x0, SDHCI_TRANSFER_MODE);
+		} else {
 		/* clear Auto CMD settings for no data CMDs */
-		mode = sdhci_readw(host, SDHCI_TRANSFER_MODE);
-		sdhci_writew(host, mode & ~(SDHCI_TRNS_AUTO_CMD12 |
+			mode = sdhci_readw(host, SDHCI_TRANSFER_MODE);
+			sdhci_writew(host, mode & ~(SDHCI_TRNS_AUTO_CMD12 |
 				SDHCI_TRNS_AUTO_CMD23), SDHCI_TRANSFER_MODE);
+		}
 		return;
 	}
 
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index 931ac5e0545..ae7f357b78c 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -102,6 +102,8 @@ struct sdhci_host {
 #define SDHCI_QUIRK2_STOP_WITH_TC			(1<<8)
 /* Controller does not support 64-bit DMA */
 #define SDHCI_QUIRK2_BROKEN_64_BIT_DMA			(1<<9)
+/* need clear transfer mode register before send cmd */
+#define SDHCI_QUIRK2_CLEAR_TRANSFERMODE_REG_BEFORE_CMD	(1<<10)
 
 	int irq;		/* Device IRQ */
 	void __iomem *ioaddr;	/* Mapped address */
-- 
cgit v1.2.3-70-g09d2


From 69d99fdcfd7815dfb2318f0777a46181d5bf42dc Mon Sep 17 00:00:00 2001
From: Prabu Thangamuthu <Prabu.T@synopsys.com>
Date: Mon, 20 Oct 2014 07:12:33 +0000
Subject: mmc: dw_mmc: Add IDMAC 64-bit address mode support

Synopsys DW_MMC IP core supports Internal DMA Controller with 64-bit address mode from IP version 2.70a onwards.
Updated the driver to support IDMAC 64-bit addressing mode.

Signed-off-by: Prabu Thangamuthu <prabu.t@synopsys.com>
Reviewed-by: Alim Akhtar <alim.akhtar@samsung.com>
Acked-by: Jaehoon Chung <jh80.chung@samsung.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/dw_mmc.c  | 199 ++++++++++++++++++++++++++++++++++++---------
 drivers/mmc/host/dw_mmc.h  |  11 +++
 include/linux/mmc/dw_mmc.h |   2 +
 3 files changed, 174 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index bb46b1b8d16..5a37c33879a 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -61,6 +61,24 @@
 				 SDMMC_IDMAC_INT_FBE | SDMMC_IDMAC_INT_RI | \
 				 SDMMC_IDMAC_INT_TI)
 
+struct idmac_desc_64addr {
+	u32		des0;	/* Control Descriptor */
+
+	u32		des1;	/* Reserved */
+
+	u32		des2;	/*Buffer sizes */
+#define IDMAC_64ADDR_SET_BUFFER1_SIZE(d, s) \
+	((d)->des2 = ((d)->des2 & 0x03ffe000) | ((s) & 0x1fff))
+
+	u32		des3;	/* Reserved */
+
+	u32		des4;	/* Lower 32-bits of Buffer Address Pointer 1*/
+	u32		des5;	/* Upper 32-bits of Buffer Address Pointer 1*/
+
+	u32		des6;	/* Lower 32-bits of Next Descriptor Address */
+	u32		des7;	/* Upper 32-bits of Next Descriptor Address */
+};
+
 struct idmac_desc {
 	u32		des0;	/* Control Descriptor */
 #define IDMAC_DES0_DIC	BIT(1)
@@ -414,30 +432,66 @@ static void dw_mci_translate_sglist(struct dw_mci *host, struct mmc_data *data,
 				    unsigned int sg_len)
 {
 	int i;
-	struct idmac_desc *desc = host->sg_cpu;
+	if (host->dma_64bit_address == 1) {
+		struct idmac_desc_64addr *desc = host->sg_cpu;
 
-	for (i = 0; i < sg_len; i++, desc++) {
-		unsigned int length = sg_dma_len(&data->sg[i]);
-		u32 mem_addr = sg_dma_address(&data->sg[i]);
+		for (i = 0; i < sg_len; i++, desc++) {
+			unsigned int length = sg_dma_len(&data->sg[i]);
+			u64 mem_addr = sg_dma_address(&data->sg[i]);
 
-		/* Set the OWN bit and disable interrupts for this descriptor */
-		desc->des0 = IDMAC_DES0_OWN | IDMAC_DES0_DIC | IDMAC_DES0_CH;
+			/*
+			 * Set the OWN bit and disable interrupts for this
+			 * descriptor
+			 */
+			desc->des0 = IDMAC_DES0_OWN | IDMAC_DES0_DIC |
+						IDMAC_DES0_CH;
+			/* Buffer length */
+			IDMAC_64ADDR_SET_BUFFER1_SIZE(desc, length);
+
+			/* Physical address to DMA to/from */
+			desc->des4 = mem_addr & 0xffffffff;
+			desc->des5 = mem_addr >> 32;
+		}
 
-		/* Buffer length */
-		IDMAC_SET_BUFFER1_SIZE(desc, length);
+		/* Set first descriptor */
+		desc = host->sg_cpu;
+		desc->des0 |= IDMAC_DES0_FD;
 
-		/* Physical address to DMA to/from */
-		desc->des2 = mem_addr;
-	}
+		/* Set last descriptor */
+		desc = host->sg_cpu + (i - 1) *
+				sizeof(struct idmac_desc_64addr);
+		desc->des0 &= ~(IDMAC_DES0_CH | IDMAC_DES0_DIC);
+		desc->des0 |= IDMAC_DES0_LD;
+
+	} else {
+		struct idmac_desc *desc = host->sg_cpu;
+
+		for (i = 0; i < sg_len; i++, desc++) {
+			unsigned int length = sg_dma_len(&data->sg[i]);
+			u32 mem_addr = sg_dma_address(&data->sg[i]);
+
+			/*
+			 * Set the OWN bit and disable interrupts for this
+			 * descriptor
+			 */
+			desc->des0 = IDMAC_DES0_OWN | IDMAC_DES0_DIC |
+						IDMAC_DES0_CH;
+			/* Buffer length */
+			IDMAC_SET_BUFFER1_SIZE(desc, length);
+
+			/* Physical address to DMA to/from */
+			desc->des2 = mem_addr;
+		}
 
-	/* Set first descriptor */
-	desc = host->sg_cpu;
-	desc->des0 |= IDMAC_DES0_FD;
+		/* Set first descriptor */
+		desc = host->sg_cpu;
+		desc->des0 |= IDMAC_DES0_FD;
 
-	/* Set last descriptor */
-	desc = host->sg_cpu + (i - 1) * sizeof(struct idmac_desc);
-	desc->des0 &= ~(IDMAC_DES0_CH | IDMAC_DES0_DIC);
-	desc->des0 |= IDMAC_DES0_LD;
+		/* Set last descriptor */
+		desc = host->sg_cpu + (i - 1) * sizeof(struct idmac_desc);
+		desc->des0 &= ~(IDMAC_DES0_CH | IDMAC_DES0_DIC);
+		desc->des0 |= IDMAC_DES0_LD;
+	}
 
 	wmb();
 }
@@ -470,29 +524,71 @@ static void dw_mci_idmac_start_dma(struct dw_mci *host, unsigned int sg_len)
 
 static int dw_mci_idmac_init(struct dw_mci *host)
 {
-	struct idmac_desc *p;
 	int i;
 
-	/* Number of descriptors in the ring buffer */
-	host->ring_size = PAGE_SIZE / sizeof(struct idmac_desc);
+	if (host->dma_64bit_address == 1) {
+		struct idmac_desc_64addr *p;
+		/* Number of descriptors in the ring buffer */
+		host->ring_size = PAGE_SIZE / sizeof(struct idmac_desc_64addr);
+
+		/* Forward link the descriptor list */
+		for (i = 0, p = host->sg_cpu; i < host->ring_size - 1;
+								i++, p++) {
+			p->des6 = (host->sg_dma +
+					(sizeof(struct idmac_desc_64addr) *
+							(i + 1))) & 0xffffffff;
+
+			p->des7 = (u64)(host->sg_dma +
+					(sizeof(struct idmac_desc_64addr) *
+							(i + 1))) >> 32;
+			/* Initialize reserved and buffer size fields to "0" */
+			p->des1 = 0;
+			p->des2 = 0;
+			p->des3 = 0;
+		}
+
+		/* Set the last descriptor as the end-of-ring descriptor */
+		p->des6 = host->sg_dma & 0xffffffff;
+		p->des7 = (u64)host->sg_dma >> 32;
+		p->des0 = IDMAC_DES0_ER;
+
+	} else {
+		struct idmac_desc *p;
+		/* Number of descriptors in the ring buffer */
+		host->ring_size = PAGE_SIZE / sizeof(struct idmac_desc);
 
-	/* Forward link the descriptor list */
-	for (i = 0, p = host->sg_cpu; i < host->ring_size - 1; i++, p++)
-		p->des3 = host->sg_dma + (sizeof(struct idmac_desc) * (i + 1));
+		/* Forward link the descriptor list */
+		for (i = 0, p = host->sg_cpu; i < host->ring_size - 1; i++, p++)
+			p->des3 = host->sg_dma + (sizeof(struct idmac_desc) *
+								(i + 1));
 
-	/* Set the last descriptor as the end-of-ring descriptor */
-	p->des3 = host->sg_dma;
-	p->des0 = IDMAC_DES0_ER;
+		/* Set the last descriptor as the end-of-ring descriptor */
+		p->des3 = host->sg_dma;
+		p->des0 = IDMAC_DES0_ER;
+	}
 
 	dw_mci_idmac_reset(host);
 
-	/* Mask out interrupts - get Tx & Rx complete only */
-	mci_writel(host, IDSTS, IDMAC_INT_CLR);
-	mci_writel(host, IDINTEN, SDMMC_IDMAC_INT_NI | SDMMC_IDMAC_INT_RI |
-		   SDMMC_IDMAC_INT_TI);
+	if (host->dma_64bit_address == 1) {
+		/* Mask out interrupts - get Tx & Rx complete only */
+		mci_writel(host, IDSTS64, IDMAC_INT_CLR);
+		mci_writel(host, IDINTEN64, SDMMC_IDMAC_INT_NI |
+				SDMMC_IDMAC_INT_RI | SDMMC_IDMAC_INT_TI);
+
+		/* Set the descriptor base address */
+		mci_writel(host, DBADDRL, host->sg_dma & 0xffffffff);
+		mci_writel(host, DBADDRU, (u64)host->sg_dma >> 32);
+
+	} else {
+		/* Mask out interrupts - get Tx & Rx complete only */
+		mci_writel(host, IDSTS, IDMAC_INT_CLR);
+		mci_writel(host, IDINTEN, SDMMC_IDMAC_INT_NI |
+				SDMMC_IDMAC_INT_RI | SDMMC_IDMAC_INT_TI);
+
+		/* Set the descriptor base address */
+		mci_writel(host, DBADDR, host->sg_dma);
+	}
 
-	/* Set the descriptor base address */
-	mci_writel(host, DBADDR, host->sg_dma);
 	return 0;
 }
 
@@ -2066,11 +2162,22 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 
 #ifdef CONFIG_MMC_DW_IDMAC
 	/* Handle DMA interrupts */
-	pending = mci_readl(host, IDSTS);
-	if (pending & (SDMMC_IDMAC_INT_TI | SDMMC_IDMAC_INT_RI)) {
-		mci_writel(host, IDSTS, SDMMC_IDMAC_INT_TI | SDMMC_IDMAC_INT_RI);
-		mci_writel(host, IDSTS, SDMMC_IDMAC_INT_NI);
-		host->dma_ops->complete(host);
+	if (host->dma_64bit_address == 1) {
+		pending = mci_readl(host, IDSTS64);
+		if (pending & (SDMMC_IDMAC_INT_TI | SDMMC_IDMAC_INT_RI)) {
+			mci_writel(host, IDSTS64, SDMMC_IDMAC_INT_TI |
+							SDMMC_IDMAC_INT_RI);
+			mci_writel(host, IDSTS64, SDMMC_IDMAC_INT_NI);
+			host->dma_ops->complete(host);
+		}
+	} else {
+		pending = mci_readl(host, IDSTS);
+		if (pending & (SDMMC_IDMAC_INT_TI | SDMMC_IDMAC_INT_RI)) {
+			mci_writel(host, IDSTS, SDMMC_IDMAC_INT_TI |
+							SDMMC_IDMAC_INT_RI);
+			mci_writel(host, IDSTS, SDMMC_IDMAC_INT_NI);
+			host->dma_ops->complete(host);
+		}
 	}
 #endif
 
@@ -2245,6 +2352,22 @@ static void dw_mci_cleanup_slot(struct dw_mci_slot *slot, unsigned int id)
 
 static void dw_mci_init_dma(struct dw_mci *host)
 {
+	int addr_config;
+	/* Check ADDR_CONFIG bit in HCON to find IDMAC address bus width */
+	addr_config = (mci_readl(host, HCON) >> 27) & 0x01;
+
+	if (addr_config == 1) {
+		/* host supports IDMAC in 64-bit address mode */
+		host->dma_64bit_address = 1;
+		dev_info(host->dev, "IDMAC supports 64-bit address mode.\n");
+		if (!dma_set_mask(host->dev, DMA_BIT_MASK(64)))
+			dma_set_coherent_mask(host->dev, DMA_BIT_MASK(64));
+	} else {
+		/* host supports IDMAC in 32-bit address mode */
+		host->dma_64bit_address = 0;
+		dev_info(host->dev, "IDMAC supports 32-bit address mode.\n");
+	}
+
 	/* Alloc memory for sg translation */
 	host->sg_cpu = dmam_alloc_coherent(host->dev, PAGE_SIZE,
 					  &host->sg_dma, GFP_KERNEL);
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index 71d499557ed..58d8a54d644 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -55,6 +55,17 @@
 #define SDMMC_BUFADDR		0x098
 #define SDMMC_CDTHRCTL		0x100
 #define SDMMC_DATA(x)		(x)
+/*
+* Registers to support idmac 64-bit address mode
+*/
+#define SDMMC_DBADDRL		0x088
+#define SDMMC_DBADDRU		0x08c
+#define SDMMC_IDSTS64		0x090
+#define SDMMC_IDINTEN64		0x094
+#define SDMMC_DSCADDRL		0x098
+#define SDMMC_DSCADDRU		0x09c
+#define SDMMC_BUFADDRL		0x0A0
+#define SDMMC_BUFADDRU		0x0A4
 
 /*
  * Data offset is difference according to Version
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index 69d08144cfa..0a551152d60 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -54,6 +54,7 @@ struct mmc_data;
  *	transfer is in progress.
  * @use_dma: Whether DMA channel is initialized or not.
  * @using_dma: Whether DMA is in use for the current transfer.
+ * @dma_64bit_address: Whether DMA supports 64-bit address mode or not.
  * @sg_dma: Bus address of DMA buffer.
  * @sg_cpu: Virtual address of DMA buffer.
  * @dma_ops: Pointer to platform-specific DMA callbacks.
@@ -139,6 +140,7 @@ struct dw_mci {
 	/* DMA interface members*/
 	int			use_dma;
 	int			using_dma;
+	int			dma_64bit_address;
 
 	dma_addr_t		sg_dma;
 	void			*sg_cpu;
-- 
cgit v1.2.3-70-g09d2


From 549c0b18485d10bb419a81b24efe719df75089bd Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 6 Nov 2014 15:19:05 +0200
Subject: mmc: sdhci: Clear also HS400 1.2V capability if 1.2V is not supported

1.2V HS200 mode capability is cleared if there is not a voltage
regulator that supports 1.2V.  Do the same for 1.2V HS400 mode.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.c | 13 +++++++------
 include/linux/mmc/host.h |  1 +
 2 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index c2f4754a28b..5589563761f 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -3115,16 +3115,17 @@ int sdhci_add_host(struct sdhci_host *host)
 		/* SD3.0: SDR104 is supported so (for eMMC) the caps2
 		 * field can be promoted to support HS200.
 		 */
-		if (!(host->quirks2 & SDHCI_QUIRK2_BROKEN_HS200)) {
+		if (!(host->quirks2 & SDHCI_QUIRK2_BROKEN_HS200))
 			mmc->caps2 |= MMC_CAP2_HS200;
-			if (IS_ERR(mmc->supply.vqmmc) ||
-					!regulator_is_supported_voltage
-					(mmc->supply.vqmmc, 1100000, 1300000))
-				mmc->caps2 &= ~MMC_CAP2_HS200_1_2V_SDR;
-		}
 	} else if (caps[1] & SDHCI_SUPPORT_SDR50)
 		mmc->caps |= MMC_CAP_UHS_SDR50;
 
+	if ((mmc->caps2 & MMC_CAP2_HSX00_1_2V) &&
+	    (IS_ERR(mmc->supply.vqmmc) ||
+	     !regulator_is_supported_voltage(mmc->supply.vqmmc, 1100000,
+					     1300000)))
+		mmc->caps2 &= ~MMC_CAP2_HSX00_1_2V;
+
 	if ((caps[1] & SDHCI_SUPPORT_DDR50) &&
 		!(host->quirks2 & SDHCI_QUIRK2_BROKEN_DDR50))
 		mmc->caps |= MMC_CAP_UHS_DDR50;
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index df0c15396bb..9f322706f7c 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -289,6 +289,7 @@ struct mmc_host {
 #define MMC_CAP2_HS400_1_2V	(1 << 16)	/* Can support HS400 1.2V */
 #define MMC_CAP2_HS400		(MMC_CAP2_HS400_1_8V | \
 				 MMC_CAP2_HS400_1_2V)
+#define MMC_CAP2_HSX00_1_2V	(MMC_CAP2_HS200_1_2V_SDR | MMC_CAP2_HS400_1_2V)
 #define MMC_CAP2_SDIO_IRQ_NOTHREAD (1 << 17)
 
 	mmc_pm_flag_t		pm_caps;	/* supported pm features */
-- 
cgit v1.2.3-70-g09d2


From e9fb05d5bca7428f2749d059559e9657c710fe53 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 6 Nov 2014 15:19:06 +0200
Subject: mmc: sdhci: Add HS400 support to SDHCI driver

MMC core already has support for HS400.  Add HS400
support to SDHCI driver.  The SDHC Standard specification
does not define HS400 so consequently HS400 support is
non-standard.  However HS400 is not selected without
the host controller setting the corresponding capability
flags so host controllers not yet supporting HS400
will not be affected.  To support that, a quirk
SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 is introduced to
enable the use of capabilities register reserved bit-63
to indicate HS400 support.

Because HS400 is non-standard for SDHCI, it is possible
that different vendors will do things in different ways.
However HS200 support faced the same issue but currently
there is only one solution.  As such, no attempt has
been made to provide for alternate HS400 solutions except
for SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.c  | 13 ++++++++++++-
 drivers/mmc/host/sdhci.h  |  3 +++
 include/linux/mmc/sdhci.h |  2 ++
 3 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 5589563761f..73de62a58d7 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1148,6 +1148,9 @@ static u16 sdhci_get_preset_value(struct sdhci_host *host)
 	case MMC_TIMING_UHS_DDR50:
 		preset = sdhci_readw(host, SDHCI_PRESET_FOR_DDR50);
 		break;
+	case MMC_TIMING_MMC_HS400:
+		preset = sdhci_readw(host, SDHCI_PRESET_FOR_HS400);
+		break;
 	default:
 		pr_warn("%s: Invalid UHS-I mode selected\n",
 			mmc_hostname(host->mmc));
@@ -1475,6 +1478,8 @@ void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing)
 	else if ((timing == MMC_TIMING_UHS_DDR50) ||
 		 (timing == MMC_TIMING_MMC_DDR52))
 		ctrl_2 |= SDHCI_CTRL_UHS_DDR50;
+	else if (timing == MMC_TIMING_MMC_HS400)
+		ctrl_2 |= SDHCI_CTRL_HS400; /* Non-standard */
 	sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2);
 }
 EXPORT_SYMBOL_GPL(sdhci_set_uhs_signaling);
@@ -1546,7 +1551,8 @@ static void sdhci_do_set_ios(struct sdhci_host *host, struct mmc_ios *ios)
 		u16 clk, ctrl_2;
 
 		/* In case of UHS-I modes, set High Speed Enable */
-		if ((ios->timing == MMC_TIMING_MMC_HS200) ||
+		if ((ios->timing == MMC_TIMING_MMC_HS400) ||
+		    (ios->timing == MMC_TIMING_MMC_HS200) ||
 		    (ios->timing == MMC_TIMING_MMC_DDR52) ||
 		    (ios->timing == MMC_TIMING_UHS_SDR50) ||
 		    (ios->timing == MMC_TIMING_UHS_SDR104) ||
@@ -1893,6 +1899,7 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	 * tuning function has to be executed.
 	 */
 	switch (host->timing) {
+	case MMC_TIMING_MMC_HS400:
 	case MMC_TIMING_MMC_HS200:
 	case MMC_TIMING_UHS_SDR104:
 		break;
@@ -3120,6 +3127,10 @@ int sdhci_add_host(struct sdhci_host *host)
 	} else if (caps[1] & SDHCI_SUPPORT_SDR50)
 		mmc->caps |= MMC_CAP_UHS_SDR50;
 
+	if (host->quirks2 & SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 &&
+	    (caps[1] & SDHCI_SUPPORT_HS400))
+		mmc->caps2 |= MMC_CAP2_HS400;
+
 	if ((mmc->caps2 & MMC_CAP2_HSX00_1_2V) &&
 	    (IS_ERR(mmc->supply.vqmmc) ||
 	     !regulator_is_supported_voltage(mmc->supply.vqmmc, 1100000,
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 79937cfff4c..ddd31cda237 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -161,6 +161,7 @@
 #define   SDHCI_CTRL_UHS_SDR50		0x0002
 #define   SDHCI_CTRL_UHS_SDR104		0x0003
 #define   SDHCI_CTRL_UHS_DDR50		0x0004
+#define   SDHCI_CTRL_HS400		0x0005 /* Non-standard */
 #define  SDHCI_CTRL_VDD_180		0x0008
 #define  SDHCI_CTRL_DRV_TYPE_MASK	0x0030
 #define   SDHCI_CTRL_DRV_TYPE_B		0x0000
@@ -203,6 +204,7 @@
 #define  SDHCI_RETUNING_MODE_SHIFT		14
 #define  SDHCI_CLOCK_MUL_MASK	0x00FF0000
 #define  SDHCI_CLOCK_MUL_SHIFT	16
+#define  SDHCI_SUPPORT_HS400	0x80000000 /* Non-standard */
 
 #define SDHCI_CAPABILITIES_1	0x44
 
@@ -235,6 +237,7 @@
 #define SDHCI_PRESET_FOR_SDR50 0x6A
 #define SDHCI_PRESET_FOR_SDR104        0x6C
 #define SDHCI_PRESET_FOR_DDR50 0x6E
+#define SDHCI_PRESET_FOR_HS400 0x74 /* Non-standard */
 #define SDHCI_PRESET_DRV_MASK  0xC000
 #define SDHCI_PRESET_DRV_SHIFT  14
 #define SDHCI_PRESET_CLKGEN_SEL_MASK   0x400
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index ae7f357b78c..375af80bde7 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -104,6 +104,8 @@ struct sdhci_host {
 #define SDHCI_QUIRK2_BROKEN_64_BIT_DMA			(1<<9)
 /* need clear transfer mode register before send cmd */
 #define SDHCI_QUIRK2_CLEAR_TRANSFERMODE_REG_BEFORE_CMD	(1<<10)
+/* Capability register bit-63 indicates HS400 support */
+#define SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400		(1<<11)
 
 	int irq;		/* Device IRQ */
 	void __iomem *ioaddr;	/* Mapped address */
-- 
cgit v1.2.3-70-g09d2


From 551434389074791da30b7afbf44c4bbe9b8b0116 Mon Sep 17 00:00:00 2001
From: Andreas Fenkart <afenkart@gmail.com>
Date: Sat, 8 Nov 2014 15:33:09 +0100
Subject: ARM: OMAP1/2+: MMC: separate platform data for mmc and mmc hs driver

- omap mmc driver supports multiplexing, omap_mmc_hs doesn't
this leads to one of the major confusions in the omap_hsmmc driver

- platform data should be read-only for the driver
most callbacks are not set by the omap3 platform init code while still
required. So they are set from the driver probe function, which is against
the paradigm that platform-data should not be modified by the driver
typical examples are card_detect, read_only callbacks

un-bundling by searching for driver name \"omap_hsmmc in the
arch/arm folder. omap_hsmmc_platform_data is not initialized directly,
but from omap2_hsmmc_info, which is defined in a separate header file
not touched by this patch

hwmod includes platform headers to declare features of the platform. All
the declared features are prefixed OMAP_HSMMC. There is no need to
include platform header from hwmod other except for feature defines

Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Andreas Fenkart <afenkart@gmail.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 arch/arm/mach-omap2/hsmmc.c                        |  26 ++--
 arch/arm/mach-omap2/omap_hwmod_2430_data.c         |   4 +-
 .../mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c |   8 +-
 arch/arm/mach-omap2/omap_hwmod_3xxx_data.c         |   8 +-
 arch/arm/mach-omap2/omap_hwmod_44xx_data.c         |   4 +-
 arch/arm/mach-omap2/omap_hwmod_54xx_data.c         |   4 +-
 arch/arm/mach-omap2/omap_hwmod_7xx_data.c          |   4 +-
 drivers/mmc/host/omap_hsmmc.c                      |  28 ++--
 include/linux/platform_data/hsmmc-omap.h           | 149 +++++++++++++++++++++
 include/linux/platform_data/mmc-omap.h             |  27 ----
 10 files changed, 192 insertions(+), 70 deletions(-)
 create mode 100644 include/linux/platform_data/hsmmc-omap.h

(limited to 'include')

diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c
index 73e28ac45d9..9edd7596d1e 100644
--- a/arch/arm/mach-omap2/hsmmc.c
+++ b/arch/arm/mach-omap2/hsmmc.c
@@ -16,7 +16,7 @@
 #include <linux/gpio.h>
 #include <linux/mmc/host.h>
 #include <linux/platform_data/gpio-omap.h>
-#include <linux/platform_data/mmc-omap.h>
+#include <linux/platform_data/hsmmc-omap.h>
 
 #include "soc.h"
 #include "omap_device.h"
@@ -48,7 +48,7 @@ static void omap_hsmmc1_before_set_reg(struct device *dev, int slot,
 				  int power_on, int vdd)
 {
 	u32 reg, prog_io;
-	struct omap_mmc_platform_data *mmc = dev->platform_data;
+	struct omap_hsmmc_platform_data *mmc = dev->platform_data;
 
 	if (mmc->slots[0].remux)
 		mmc->slots[0].remux(dev, slot, power_on);
@@ -121,7 +121,7 @@ static void omap_hsmmc1_after_set_reg(struct device *dev, int slot,
 	}
 }
 
-static void hsmmc2_select_input_clk_src(struct omap_mmc_platform_data *mmc)
+static void hsmmc2_select_input_clk_src(struct omap_hsmmc_platform_data *mmc)
 {
 	u32 reg;
 
@@ -136,7 +136,7 @@ static void hsmmc2_select_input_clk_src(struct omap_mmc_platform_data *mmc)
 static void hsmmc2_before_set_reg(struct device *dev, int slot,
 				   int power_on, int vdd)
 {
-	struct omap_mmc_platform_data *mmc = dev->platform_data;
+	struct omap_hsmmc_platform_data *mmc = dev->platform_data;
 
 	if (mmc->slots[0].remux)
 		mmc->slots[0].remux(dev, slot, power_on);
@@ -148,7 +148,7 @@ static void hsmmc2_before_set_reg(struct device *dev, int slot,
 static int am35x_hsmmc2_set_power(struct device *dev, int slot,
 				  int power_on, int vdd)
 {
-	struct omap_mmc_platform_data *mmc = dev->platform_data;
+	struct omap_hsmmc_platform_data *mmc = dev->platform_data;
 
 	if (power_on)
 		hsmmc2_select_input_clk_src(mmc);
@@ -162,8 +162,8 @@ static int nop_mmc_set_power(struct device *dev, int slot, int power_on,
 	return 0;
 }
 
-static inline void omap_hsmmc_mux(struct omap_mmc_platform_data *mmc_controller,
-			int controller_nr)
+static inline void omap_hsmmc_mux(struct omap_hsmmc_platform_data
+				  *mmc_controller, int controller_nr)
 {
 	if (gpio_is_valid(mmc_controller->slots[0].switch_pin) &&
 		(mmc_controller->slots[0].switch_pin < OMAP_MAX_GPIO_LINES))
@@ -244,7 +244,7 @@ static inline void omap_hsmmc_mux(struct omap_mmc_platform_data *mmc_controller,
 }
 
 static int __init omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c,
-					struct omap_mmc_platform_data *mmc)
+					struct omap_hsmmc_platform_data *mmc)
 {
 	char *hc_name;
 
@@ -369,7 +369,7 @@ static int omap_hsmmc_done;
 void omap_hsmmc_late_init(struct omap2_hsmmc_info *c)
 {
 	struct platform_device *pdev;
-	struct omap_mmc_platform_data *mmc_pdata;
+	struct omap_hsmmc_platform_data *mmc_pdata;
 	int res;
 
 	if (omap_hsmmc_done != 1)
@@ -409,12 +409,12 @@ static void __init omap_hsmmc_init_one(struct omap2_hsmmc_info *hsmmcinfo,
 	struct omap_device *od;
 	struct platform_device *pdev;
 	char oh_name[MAX_OMAP_MMC_HWMOD_NAME_LEN];
-	struct omap_mmc_platform_data *mmc_data;
-	struct omap_mmc_dev_attr *mmc_dev_attr;
+	struct omap_hsmmc_platform_data *mmc_data;
+	struct omap_hsmmc_dev_attr *mmc_dev_attr;
 	char *name;
 	int res;
 
-	mmc_data = kzalloc(sizeof(struct omap_mmc_platform_data), GFP_KERNEL);
+	mmc_data = kzalloc(sizeof(*mmc_data), GFP_KERNEL);
 	if (!mmc_data) {
 		pr_err("Cannot allocate memory for mmc device!\n");
 		return;
@@ -464,7 +464,7 @@ static void __init omap_hsmmc_init_one(struct omap2_hsmmc_info *hsmmcinfo,
 	}
 
 	res = platform_device_add_data(pdev, mmc_data,
-			      sizeof(struct omap_mmc_platform_data));
+			      sizeof(struct omap_hsmmc_platform_data));
 	if (res) {
 		pr_err("Could not add pdata for %s\n", name);
 		goto put_pdev;
diff --git a/arch/arm/mach-omap2/omap_hwmod_2430_data.c b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
index cd95e820c6d..79127b35fe6 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2430_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
@@ -15,7 +15,7 @@
 
 #include <linux/i2c-omap.h>
 #include <linux/platform_data/asoc-ti-mcbsp.h>
-#include <linux/platform_data/mmc-omap.h>
+#include <linux/platform_data/hsmmc-omap.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
 #include <linux/omap-dma.h>
 #include <plat/dmtimer.h>
@@ -372,7 +372,7 @@ static struct omap_hwmod_opt_clk omap2430_mmc1_opt_clks[] = {
 	{ .role = "dbck", .clk = "mmchsdb1_fck" },
 };
 
-static struct omap_mmc_dev_attr mmc1_dev_attr = {
+static struct omap_hsmmc_dev_attr mmc1_dev_attr = {
 	.flags = OMAP_HSMMC_SUPPORTS_DUAL_VOLT,
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
index bf8c12d595b..cabc5695b50 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
@@ -15,7 +15,7 @@
  */
 
 #include <linux/platform_data/gpio-omap.h>
-#include <linux/platform_data/mmc-omap.h>
+#include <linux/platform_data/hsmmc-omap.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
 #include "omap_hwmod.h"
 #include "i2c.h"
@@ -836,7 +836,7 @@ static struct omap_hwmod_class am33xx_mmc_hwmod_class = {
 };
 
 /* mmc0 */
-static struct omap_mmc_dev_attr am33xx_mmc0_dev_attr = {
+static struct omap_hsmmc_dev_attr am33xx_mmc0_dev_attr = {
 	.flags		= OMAP_HSMMC_SUPPORTS_DUAL_VOLT,
 };
 
@@ -854,7 +854,7 @@ struct omap_hwmod am33xx_mmc0_hwmod = {
 };
 
 /* mmc1 */
-static struct omap_mmc_dev_attr am33xx_mmc1_dev_attr = {
+static struct omap_hsmmc_dev_attr am33xx_mmc1_dev_attr = {
 	.flags		= OMAP_HSMMC_SUPPORTS_DUAL_VOLT,
 };
 
@@ -872,7 +872,7 @@ struct omap_hwmod am33xx_mmc1_hwmod = {
 };
 
 /* mmc2 */
-static struct omap_mmc_dev_attr am33xx_mmc2_dev_attr = {
+static struct omap_hsmmc_dev_attr am33xx_mmc2_dev_attr = {
 	.flags		= OMAP_HSMMC_SUPPORTS_DUAL_VOLT,
 };
 struct omap_hwmod am33xx_mmc2_hwmod = {
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index 5f244a90eee..11468eea387 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -18,7 +18,7 @@
 #include <linux/i2c-omap.h>
 #include <linux/power/smartreflex.h>
 #include <linux/platform_data/gpio-omap.h>
-#include <linux/platform_data/mmc-omap.h>
+#include <linux/platform_data/hsmmc-omap.h>
 
 #include <linux/omap-dma.h>
 #include "l3_3xxx.h"
@@ -1786,12 +1786,12 @@ static struct omap_hwmod_opt_clk omap34xx_mmc1_opt_clks[] = {
 	{ .role = "dbck", .clk = "omap_32k_fck", },
 };
 
-static struct omap_mmc_dev_attr mmc1_dev_attr = {
+static struct omap_hsmmc_dev_attr mmc1_dev_attr = {
 	.flags = OMAP_HSMMC_SUPPORTS_DUAL_VOLT,
 };
 
 /* See 35xx errata 2.1.1.128 in SPRZ278F */
-static struct omap_mmc_dev_attr mmc1_pre_es3_dev_attr = {
+static struct omap_hsmmc_dev_attr mmc1_pre_es3_dev_attr = {
 	.flags = (OMAP_HSMMC_SUPPORTS_DUAL_VOLT |
 		  OMAP_HSMMC_BROKEN_MULTIBLOCK_READ),
 };
@@ -1854,7 +1854,7 @@ static struct omap_hwmod_opt_clk omap34xx_mmc2_opt_clks[] = {
 };
 
 /* See 35xx errata 2.1.1.128 in SPRZ278F */
-static struct omap_mmc_dev_attr mmc2_pre_es3_dev_attr = {
+static struct omap_hsmmc_dev_attr mmc2_pre_es3_dev_attr = {
 	.flags = OMAP_HSMMC_BROKEN_MULTIBLOCK_READ,
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index c385185c755..d8a3cf1c178 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -22,7 +22,7 @@
 
 #include <linux/io.h>
 #include <linux/platform_data/gpio-omap.h>
-#include <linux/platform_data/mmc-omap.h>
+#include <linux/platform_data/hsmmc-omap.h>
 #include <linux/power/smartreflex.h>
 #include <linux/i2c-omap.h>
 
@@ -1952,7 +1952,7 @@ static struct omap_hwmod_dma_info omap44xx_mmc1_sdma_reqs[] = {
 };
 
 /* mmc1 dev_attr */
-static struct omap_mmc_dev_attr mmc1_dev_attr = {
+static struct omap_hsmmc_dev_attr mmc1_dev_attr = {
 	.flags	= OMAP_HSMMC_SUPPORTS_DUAL_VOLT,
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
index 13bf6a72c5e..5ec786a76d3 100644
--- a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
@@ -19,7 +19,7 @@
 
 #include <linux/io.h>
 #include <linux/platform_data/gpio-omap.h>
-#include <linux/platform_data/mmc-omap.h>
+#include <linux/platform_data/hsmmc-omap.h>
 #include <linux/power/smartreflex.h>
 #include <linux/i2c-omap.h>
 
@@ -1269,7 +1269,7 @@ static struct omap_hwmod_opt_clk mmc1_opt_clks[] = {
 };
 
 /* mmc1 dev_attr */
-static struct omap_mmc_dev_attr mmc1_dev_attr = {
+static struct omap_hsmmc_dev_attr mmc1_dev_attr = {
 	.flags	= OMAP_HSMMC_SUPPORTS_DUAL_VOLT,
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 8523821fe78..711c97e9099 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -19,7 +19,7 @@
 
 #include <linux/io.h>
 #include <linux/platform_data/gpio-omap.h>
-#include <linux/platform_data/mmc-omap.h>
+#include <linux/platform_data/hsmmc-omap.h>
 #include <linux/power/smartreflex.h>
 #include <linux/i2c-omap.h>
 
@@ -1301,7 +1301,7 @@ static struct omap_hwmod_opt_clk mmc1_opt_clks[] = {
 };
 
 /* mmc1 dev_attr */
-static struct omap_mmc_dev_attr mmc1_dev_attr = {
+static struct omap_hsmmc_dev_attr mmc1_dev_attr = {
 	.flags	= OMAP_HSMMC_SUPPORTS_DUAL_VOLT,
 };
 
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index df27bb4fc09..4957c5fe555 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -42,7 +42,7 @@
 #include <linux/regulator/consumer.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/pm_runtime.h>
-#include <linux/platform_data/mmc-omap.h>
+#include <linux/platform_data/hsmmc-omap.h>
 
 /* OMAP HSMMC Host Controller Registers */
 #define OMAP_HSMMC_SYSSTATUS	0x0014
@@ -220,7 +220,7 @@ struct omap_hsmmc_host {
 #define HSMMC_SDIO_IRQ_ENABLED	(1 << 1)        /* SDIO irq enabled */
 #define HSMMC_WAKE_IRQ_ENABLED	(1 << 2)
 	struct omap_hsmmc_next	next_data;
-	struct	omap_mmc_platform_data	*pdata;
+	struct	omap_hsmmc_platform_data	*pdata;
 };
 
 struct omap_mmc_of_data {
@@ -233,7 +233,7 @@ static void omap_hsmmc_start_dma_transfer(struct omap_hsmmc_host *host);
 static int omap_hsmmc_card_detect(struct device *dev, int slot)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
-	struct omap_mmc_platform_data *mmc = host->pdata;
+	struct omap_hsmmc_platform_data *mmc = host->pdata;
 
 	/* NOTE: assumes card detect signal is active-low */
 	return !gpio_get_value_cansleep(mmc->slots[0].switch_pin);
@@ -242,7 +242,7 @@ static int omap_hsmmc_card_detect(struct device *dev, int slot)
 static int omap_hsmmc_get_wp(struct device *dev, int slot)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
-	struct omap_mmc_platform_data *mmc = host->pdata;
+	struct omap_hsmmc_platform_data *mmc = host->pdata;
 
 	/* NOTE: assumes write protect signal is active-high */
 	return gpio_get_value_cansleep(mmc->slots[0].gpio_wp);
@@ -251,7 +251,7 @@ static int omap_hsmmc_get_wp(struct device *dev, int slot)
 static int omap_hsmmc_get_cover_state(struct device *dev, int slot)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
-	struct omap_mmc_platform_data *mmc = host->pdata;
+	struct omap_hsmmc_platform_data *mmc = host->pdata;
 
 	/* NOTE: assumes card detect signal is active-low */
 	return !gpio_get_value_cansleep(mmc->slots[0].switch_pin);
@@ -262,7 +262,7 @@ static int omap_hsmmc_get_cover_state(struct device *dev, int slot)
 static int omap_hsmmc_suspend_cdirq(struct device *dev, int slot)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
-	struct omap_mmc_platform_data *mmc = host->pdata;
+	struct omap_hsmmc_platform_data *mmc = host->pdata;
 
 	disable_irq(mmc->slots[0].card_detect_irq);
 	return 0;
@@ -271,7 +271,7 @@ static int omap_hsmmc_suspend_cdirq(struct device *dev, int slot)
 static int omap_hsmmc_resume_cdirq(struct device *dev, int slot)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
-	struct omap_mmc_platform_data *mmc = host->pdata;
+	struct omap_hsmmc_platform_data *mmc = host->pdata;
 
 	enable_irq(mmc->slots[0].card_detect_irq);
 	return 0;
@@ -449,7 +449,7 @@ static inline int omap_hsmmc_have_reg(void)
 
 #endif
 
-static int omap_hsmmc_gpio_init(struct omap_mmc_platform_data *pdata)
+static int omap_hsmmc_gpio_init(struct omap_hsmmc_platform_data *pdata)
 {
 	int ret;
 
@@ -492,7 +492,7 @@ err_free_sp:
 	return ret;
 }
 
-static void omap_hsmmc_gpio_free(struct omap_mmc_platform_data *pdata)
+static void omap_hsmmc_gpio_free(struct omap_hsmmc_platform_data *pdata)
 {
 	if (gpio_is_valid(pdata->slots[0].gpio_wp))
 		gpio_free(pdata->slots[0].gpio_wp);
@@ -1286,7 +1286,7 @@ static void omap_hsmmc_protect_card(struct omap_hsmmc_host *host)
 static irqreturn_t omap_hsmmc_detect(int irq, void *dev_id)
 {
 	struct omap_hsmmc_host *host = dev_id;
-	struct omap_mmc_slot_data *slot = &mmc_slot(host);
+	struct omap_hsmmc_slot_data *slot = &mmc_slot(host);
 	int carddetect;
 
 	sysfs_notify(&host->mmc->class_dev.kobj, NULL, "cover_switch");
@@ -1957,9 +1957,9 @@ static const struct of_device_id omap_mmc_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, omap_mmc_of_match);
 
-static struct omap_mmc_platform_data *of_get_hsmmc_pdata(struct device *dev)
+static struct omap_hsmmc_platform_data *of_get_hsmmc_pdata(struct device *dev)
 {
-	struct omap_mmc_platform_data *pdata;
+	struct omap_hsmmc_platform_data *pdata;
 	struct device_node *np = dev->of_node;
 	u32 bus_width, max_freq;
 	int cd_gpio, wp_gpio;
@@ -2009,7 +2009,7 @@ static struct omap_mmc_platform_data *of_get_hsmmc_pdata(struct device *dev)
 	return pdata;
 }
 #else
-static inline struct omap_mmc_platform_data
+static inline struct omap_hsmmc_platform_data
 			*of_get_hsmmc_pdata(struct device *dev)
 {
 	return ERR_PTR(-EINVAL);
@@ -2018,7 +2018,7 @@ static inline struct omap_mmc_platform_data
 
 static int omap_hsmmc_probe(struct platform_device *pdev)
 {
-	struct omap_mmc_platform_data *pdata = pdev->dev.platform_data;
+	struct omap_hsmmc_platform_data *pdata = pdev->dev.platform_data;
 	struct mmc_host *mmc;
 	struct omap_hsmmc_host *host = NULL;
 	struct resource *res;
diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h
new file mode 100644
index 00000000000..7dd42e54a58
--- /dev/null
+++ b/include/linux/platform_data/hsmmc-omap.h
@@ -0,0 +1,149 @@
+/*
+ * MMC definitions for OMAP2
+ *
+ * Copyright (C) 2006 Nokia Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define OMAP_HSMMC_MAX_SLOTS	1
+
+/*
+ * struct omap_hsmmc_dev_attr.flags possibilities
+ *
+ * OMAP_HSMMC_SUPPORTS_DUAL_VOLT: Some HSMMC controller instances can
+ *    operate with either 1.8Vdc or 3.0Vdc card voltages; this flag
+ *    should be set if this is the case.  See for example Section 22.5.3
+ *    "MMC/SD/SDIO1 Bus Voltage Selection" of the OMAP34xx Multimedia
+ *    Device Silicon Revision 3.1.x Revision ZR (July 2011) (SWPU223R).
+ *
+ * OMAP_HSMMC_BROKEN_MULTIBLOCK_READ: Multiple-block read transfers
+ *    don't work correctly on some MMC controller instances on some
+ *    OMAP3 SoCs; this flag should be set if this is the case.  See
+ *    for example Advisory 2.1.1.128 "MMC: Multiple Block Read
+ *    Operation Issue" in _OMAP3530/3525/3515/3503 Silicon Errata_
+ *    Revision F (October 2010) (SPRZ278F).
+ */
+#define OMAP_HSMMC_SUPPORTS_DUAL_VOLT		BIT(0)
+#define OMAP_HSMMC_BROKEN_MULTIBLOCK_READ	BIT(1)
+#define OMAP_HSMMC_SWAKEUP_MISSING		BIT(2)
+
+struct omap_hsmmc_dev_attr {
+	u8 flags;
+};
+
+struct mmc_card;
+
+struct omap_hsmmc_platform_data {
+	/* back-link to device */
+	struct device *dev;
+
+	/* number of slots per controller */
+	unsigned nr_slots:2;
+
+	/* set if your board has components or wiring that limits the
+	 * maximum frequency on the MMC bus */
+	unsigned int max_freq;
+
+	/* switch the bus to a new slot */
+	int (*switch_slot)(struct device *dev, int slot);
+	/* initialize board-specific MMC functionality, can be NULL if
+	 * not supported */
+	int (*init)(struct device *dev);
+	void (*cleanup)(struct device *dev);
+	void (*shutdown)(struct device *dev);
+
+	/* To handle board related suspend/resume functionality for MMC */
+	int (*suspend)(struct device *dev, int slot);
+	int (*resume)(struct device *dev, int slot);
+
+	/* Return context loss count due to PM states changing */
+	int (*get_context_loss_count)(struct device *dev);
+
+	/* Integrating attributes from the omap_hwmod layer */
+	u8 controller_flags;
+
+	/* Register offset deviation */
+	u16 reg_offset;
+
+	struct omap_hsmmc_slot_data {
+		/*
+		 * 4/8 wires and any additional host capabilities
+		 * need to OR'd all capabilities (ref. linux/mmc/host.h)
+		 */
+		u8  wires;	/* Used for the MMC driver on omap1 and 2420 */
+		u32 caps;	/* Used for the MMC driver on 2430 and later */
+		u32 pm_caps;	/* PM capabilities of the mmc */
+
+		/*
+		 * nomux means "standard" muxing is wrong on this board, and
+		 * that board-specific code handled it before common init logic.
+		 */
+		unsigned nomux:1;
+
+		/* switch pin can be for card detect (default) or card cover */
+		unsigned cover:1;
+
+		/* use the internal clock */
+		unsigned internal_clock:1;
+
+		/* nonremovable e.g. eMMC */
+		unsigned nonremovable:1;
+
+		/* Try to sleep or power off when possible */
+		unsigned power_saving:1;
+
+		/* If using power_saving and the MMC power is not to go off */
+		unsigned no_off:1;
+
+		/* eMMC does not handle power off when not in sleep state */
+		unsigned no_regulator_off_init:1;
+
+		/* Regulator off remapped to sleep */
+		unsigned vcc_aux_disable_is_sleep:1;
+
+		/* we can put the features above into this variable */
+#define HSMMC_HAS_PBIAS		(1 << 0)
+#define HSMMC_HAS_UPDATED_RESET	(1 << 1)
+#define HSMMC_HAS_HSPE_SUPPORT	(1 << 2)
+		unsigned features;
+
+		int switch_pin;			/* gpio (card detect) */
+		int gpio_wp;			/* gpio (write protect) */
+
+		int (*set_bus_mode)(struct device *dev, int slot, int bus_mode);
+		int (*set_power)(struct device *dev, int slot,
+				 int power_on, int vdd);
+		int (*get_ro)(struct device *dev, int slot);
+		void (*remux)(struct device *dev, int slot, int power_on);
+		/* Call back before enabling / disabling regulators */
+		void (*before_set_reg)(struct device *dev, int slot,
+				       int power_on, int vdd);
+		/* Call back after enabling / disabling regulators */
+		void (*after_set_reg)(struct device *dev, int slot,
+				      int power_on, int vdd);
+		/* if we have special card, init it using this callback */
+		void (*init_card)(struct mmc_card *card);
+
+		/* return MMC cover switch state, can be NULL if not supported.
+		 *
+		 * possible return values:
+		 *   0 - closed
+		 *   1 - open
+		 */
+		int (*get_cover_state)(struct device *dev, int slot);
+
+		const char *name;
+		u32 ocr_mask;
+
+		/* Card detection IRQs */
+		int card_detect_irq;
+
+		int (*card_detect)(struct device *dev, int slot);
+
+		unsigned int ban_openended:1;
+
+	} slots[OMAP_HSMMC_MAX_SLOTS];
+};
diff --git a/include/linux/platform_data/mmc-omap.h b/include/linux/platform_data/mmc-omap.h
index 51e70cf25cb..5c188f4e9be 100644
--- a/include/linux/platform_data/mmc-omap.h
+++ b/include/linux/platform_data/mmc-omap.h
@@ -10,32 +10,8 @@
 
 #define OMAP_MMC_MAX_SLOTS	2
 
-/*
- * struct omap_mmc_dev_attr.flags possibilities
- *
- * OMAP_HSMMC_SUPPORTS_DUAL_VOLT: Some HSMMC controller instances can
- *    operate with either 1.8Vdc or 3.0Vdc card voltages; this flag
- *    should be set if this is the case.  See for example Section 22.5.3
- *    "MMC/SD/SDIO1 Bus Voltage Selection" of the OMAP34xx Multimedia
- *    Device Silicon Revision 3.1.x Revision ZR (July 2011) (SWPU223R).
- *
- * OMAP_HSMMC_BROKEN_MULTIBLOCK_READ: Multiple-block read transfers
- *    don't work correctly on some MMC controller instances on some
- *    OMAP3 SoCs; this flag should be set if this is the case.  See
- *    for example Advisory 2.1.1.128 "MMC: Multiple Block Read
- *    Operation Issue" in _OMAP3530/3525/3515/3503 Silicon Errata_
- *    Revision F (October 2010) (SPRZ278F).
- */
-#define OMAP_HSMMC_SUPPORTS_DUAL_VOLT		BIT(0)
-#define OMAP_HSMMC_BROKEN_MULTIBLOCK_READ	BIT(1)
-#define OMAP_HSMMC_SWAKEUP_MISSING		BIT(2)
-
 struct mmc_card;
 
-struct omap_mmc_dev_attr {
-	u8 flags;
-};
-
 struct omap_mmc_platform_data {
 	/* back-link to device */
 	struct device *dev;
@@ -106,9 +82,6 @@ struct omap_mmc_platform_data {
 		unsigned vcc_aux_disable_is_sleep:1;
 
 		/* we can put the features above into this variable */
-#define HSMMC_HAS_PBIAS		(1 << 0)
-#define HSMMC_HAS_UPDATED_RESET	(1 << 1)
-#define HSMMC_HAS_HSPE_SUPPORT	(1 << 2)
 #define MMC_OMAP7XX		(1 << 3)
 #define MMC_OMAP15XX		(1 << 4)
 #define MMC_OMAP16XX		(1 << 5)
-- 
cgit v1.2.3-70-g09d2


From a74fecdf795e1d219fcdb6470b6a0709ff7e3e76 Mon Sep 17 00:00:00 2001
From: Andreas Fenkart <afenkart@gmail.com>
Date: Sat, 8 Nov 2014 15:33:10 +0100
Subject: mmc: omap_hsmmc: remove unused fields in platform_data

platform data is built from omap2_hsmmc_info, remove all fields that
are never set in omap_hsmmc_info, hence never copied to platform data.
Note that the omap_hsmmc driver is not affected by this patch those
fields were completely unused.

Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Andreas Fenkart <afenkart@gmail.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 arch/arm/mach-omap2/hsmmc.c              | 14 --------------
 arch/arm/mach-omap2/hsmmc.h              |  6 ------
 include/linux/platform_data/hsmmc-omap.h | 19 -------------------
 3 files changed, 39 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c
index 9edd7596d1e..75b75b96040 100644
--- a/arch/arm/mach-omap2/hsmmc.c
+++ b/arch/arm/mach-omap2/hsmmc.c
@@ -263,9 +263,7 @@ static int __init omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c,
 	mmc->slots[0].name = hc_name;
 	mmc->nr_slots = 1;
 	mmc->slots[0].caps = c->caps;
-	mmc->slots[0].pm_caps = c->pm_caps;
 	mmc->slots[0].internal_clock = !c->ext_clock;
-	mmc->max_freq = c->max_freq;
 	mmc->reg_offset = 0;
 	mmc->get_context_loss_count = hsmmc_get_context_loss;
 
@@ -281,18 +279,6 @@ static int __init omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c,
 	if (c->nonremovable)
 		mmc->slots[0].nonremovable = 1;
 
-	if (c->power_saving)
-		mmc->slots[0].power_saving = 1;
-
-	if (c->no_off)
-		mmc->slots[0].no_off = 1;
-
-	if (c->no_off_init)
-		mmc->slots[0].no_regulator_off_init = c->no_off_init;
-
-	if (c->vcc_aux_disable_is_sleep)
-		mmc->slots[0].vcc_aux_disable_is_sleep = 1;
-
 	/*
 	 * NOTE:  MMC slots should have a Vcc regulator set up.
 	 * This may be from a TWL4030-family chip, another
diff --git a/arch/arm/mach-omap2/hsmmc.h b/arch/arm/mach-omap2/hsmmc.h
index 7f2e790e092..bdc8870dde7 100644
--- a/arch/arm/mach-omap2/hsmmc.h
+++ b/arch/arm/mach-omap2/hsmmc.h
@@ -12,23 +12,17 @@ struct omap2_hsmmc_info {
 	u8	mmc;		/* controller 1/2/3 */
 	u32	caps;		/* 4/8 wires and any additional host
 				 * capabilities OR'd (ref. linux/mmc/host.h) */
-	u32	pm_caps;	/* PM capabilities */
 	bool	transceiver;	/* MMC-2 option */
 	bool	ext_clock;	/* use external pin for input clock */
 	bool	cover_only;	/* No card detect - just cover switch */
 	bool	nonremovable;	/* Nonremovable e.g. eMMC */
 	bool	power_saving;	/* Try to sleep or power off when possible */
-	bool	no_off;		/* power_saving and power is not to go off */
-	bool	no_off_init;	/* no power off when not in MMC sleep state */
-	bool	vcc_aux_disable_is_sleep; /* Regulator off remapped to sleep */
 	bool	deferred;	/* mmc needs a deferred probe */
 	int	gpio_cd;	/* or -EINVAL */
 	int	gpio_wp;	/* or -EINVAL */
 	char	*name;		/* or NULL for default */
 	struct platform_device *pdev;	/* mmc controller instance */
 	int	ocr_mask;	/* temporary HACK */
-	int	max_freq;	/* maximum clock, if constrained by external
-				 * circuitry, or 0 for default */
 	/* Remux (pad configuration) when powering on/off */
 	void (*remux)(struct device *dev, int slot, int power_on);
 	/* init some special card */
diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h
index 7dd42e54a58..11d7ed99603 100644
--- a/include/linux/platform_data/hsmmc-omap.h
+++ b/include/linux/platform_data/hsmmc-omap.h
@@ -73,16 +73,9 @@ struct omap_hsmmc_platform_data {
 		 * 4/8 wires and any additional host capabilities
 		 * need to OR'd all capabilities (ref. linux/mmc/host.h)
 		 */
-		u8  wires;	/* Used for the MMC driver on omap1 and 2420 */
 		u32 caps;	/* Used for the MMC driver on 2430 and later */
 		u32 pm_caps;	/* PM capabilities of the mmc */
 
-		/*
-		 * nomux means "standard" muxing is wrong on this board, and
-		 * that board-specific code handled it before common init logic.
-		 */
-		unsigned nomux:1;
-
 		/* switch pin can be for card detect (default) or card cover */
 		unsigned cover:1;
 
@@ -92,18 +85,9 @@ struct omap_hsmmc_platform_data {
 		/* nonremovable e.g. eMMC */
 		unsigned nonremovable:1;
 
-		/* Try to sleep or power off when possible */
-		unsigned power_saving:1;
-
-		/* If using power_saving and the MMC power is not to go off */
-		unsigned no_off:1;
-
 		/* eMMC does not handle power off when not in sleep state */
 		unsigned no_regulator_off_init:1;
 
-		/* Regulator off remapped to sleep */
-		unsigned vcc_aux_disable_is_sleep:1;
-
 		/* we can put the features above into this variable */
 #define HSMMC_HAS_PBIAS		(1 << 0)
 #define HSMMC_HAS_UPDATED_RESET	(1 << 1)
@@ -142,8 +126,5 @@ struct omap_hsmmc_platform_data {
 		int card_detect_irq;
 
 		int (*card_detect)(struct device *dev, int slot);
-
-		unsigned int ban_openended:1;
-
 	} slots[OMAP_HSMMC_MAX_SLOTS];
 };
-- 
cgit v1.2.3-70-g09d2


From bb09d15114a55ae050f5315f2dfd6d1c989ecacd Mon Sep 17 00:00:00 2001
From: Andreas Fenkart <afenkart@gmail.com>
Date: Sat, 8 Nov 2014 15:33:11 +0100
Subject: mmc: omap_hsmmc: remove un-initialized callbacks from platform data

these callbacks are not set, probably legacy omap 1/2 features

Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Andreas Fenkart <afenkart@gmail.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/omap_hsmmc.c            | 15 +--------------
 include/linux/platform_data/hsmmc-omap.h |  9 ---------
 2 files changed, 1 insertion(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 4957c5fe555..03e8e9aa375 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -2204,18 +2204,10 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 		goto err_irq;
 	}
 
-	if (pdata->init != NULL) {
-		if (pdata->init(&pdev->dev) != 0) {
-			dev_err(mmc_dev(host->mmc),
-				"Unable to configure MMC IRQs\n");
-			goto err_irq;
-		}
-	}
-
 	if (omap_hsmmc_have_reg() && !mmc_slot(host).set_power) {
 		ret = omap_hsmmc_reg_get(host);
 		if (ret)
-			goto err_reg;
+			goto err_irq;
 		host->use_reg = 1;
 	}
 
@@ -2278,9 +2270,6 @@ err_slot_name:
 err_irq_cd:
 	if (host->use_reg)
 		omap_hsmmc_reg_put(host);
-err_reg:
-	if (host->pdata->cleanup)
-		host->pdata->cleanup(&pdev->dev);
 err_irq:
 	if (host->tx_chan)
 		dma_release_channel(host->tx_chan);
@@ -2306,8 +2295,6 @@ static int omap_hsmmc_remove(struct platform_device *pdev)
 	mmc_remove_host(host->mmc);
 	if (host->use_reg)
 		omap_hsmmc_reg_put(host);
-	if (host->pdata->cleanup)
-		host->pdata->cleanup(&pdev->dev);
 
 	if (host->tx_chan)
 		dma_release_channel(host->tx_chan);
diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h
index 11d7ed99603..7e70e15154e 100644
--- a/include/linux/platform_data/hsmmc-omap.h
+++ b/include/linux/platform_data/hsmmc-omap.h
@@ -47,14 +47,6 @@ struct omap_hsmmc_platform_data {
 	 * maximum frequency on the MMC bus */
 	unsigned int max_freq;
 
-	/* switch the bus to a new slot */
-	int (*switch_slot)(struct device *dev, int slot);
-	/* initialize board-specific MMC functionality, can be NULL if
-	 * not supported */
-	int (*init)(struct device *dev);
-	void (*cleanup)(struct device *dev);
-	void (*shutdown)(struct device *dev);
-
 	/* To handle board related suspend/resume functionality for MMC */
 	int (*suspend)(struct device *dev, int slot);
 	int (*resume)(struct device *dev, int slot);
@@ -97,7 +89,6 @@ struct omap_hsmmc_platform_data {
 		int switch_pin;			/* gpio (card detect) */
 		int gpio_wp;			/* gpio (write protect) */
 
-		int (*set_bus_mode)(struct device *dev, int slot, int bus_mode);
 		int (*set_power)(struct device *dev, int slot,
 				 int power_on, int vdd);
 		int (*get_ro)(struct device *dev, int slot);
-- 
cgit v1.2.3-70-g09d2


From df206c313987bff595d2199f3bbf9b160e666b32 Mon Sep 17 00:00:00 2001
From: Andreas Fenkart <afenkart@gmail.com>
Date: Sat, 8 Nov 2014 15:33:13 +0100
Subject: mmc: omap_hsmmc: remove unused get_context_loss_count callback

trigger of this callback has been removed in 0a82e06e6183

Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Andreas Fenkart <afenkart@gmail.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 arch/arm/mach-omap2/hsmmc.c              | 12 ------------
 include/linux/platform_data/hsmmc-omap.h |  3 ---
 2 files changed, 15 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c
index 75b75b96040..c65efc3cf81 100644
--- a/arch/arm/mach-omap2/hsmmc.c
+++ b/arch/arm/mach-omap2/hsmmc.c
@@ -33,17 +33,6 @@ static u16 control_devconf1_offset;
 
 #define HSMMC_NAME_LEN	9
 
-#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_PM)
-
-static int hsmmc_get_context_loss(struct device *dev)
-{
-	return omap_pm_get_dev_context_loss_count(dev);
-}
-
-#else
-#define hsmmc_get_context_loss NULL
-#endif
-
 static void omap_hsmmc1_before_set_reg(struct device *dev, int slot,
 				  int power_on, int vdd)
 {
@@ -265,7 +254,6 @@ static int __init omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c,
 	mmc->slots[0].caps = c->caps;
 	mmc->slots[0].internal_clock = !c->ext_clock;
 	mmc->reg_offset = 0;
-	mmc->get_context_loss_count = hsmmc_get_context_loss;
 
 	mmc->slots[0].switch_pin = c->gpio_cd;
 	mmc->slots[0].gpio_wp = c->gpio_wp;
diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h
index 7e70e15154e..35d494f7d62 100644
--- a/include/linux/platform_data/hsmmc-omap.h
+++ b/include/linux/platform_data/hsmmc-omap.h
@@ -51,9 +51,6 @@ struct omap_hsmmc_platform_data {
 	int (*suspend)(struct device *dev, int slot);
 	int (*resume)(struct device *dev, int slot);
 
-	/* Return context loss count due to PM states changing */
-	int (*get_context_loss_count)(struct device *dev);
-
 	/* Integrating attributes from the omap_hwmod layer */
 	u8 controller_flags;
 
-- 
cgit v1.2.3-70-g09d2


From 326119c9923711d782e71e197429b1bab16125e1 Mon Sep 17 00:00:00 2001
From: Andreas Fenkart <afenkart@gmail.com>
Date: Sat, 8 Nov 2014 15:33:14 +0100
Subject: mmc: omap_hsmmc: remove unnecessary omap_hsmmc_slot_data indirection

omap_hsmmc supports only one slot per controller, see OMAP_MMC_MAX_SLOTS.
This unnecessary indirection leads to confusion in the omap_hsmmc driver.
For example the card_detect callback is not installed by platform code
but from the driver probe function. So it should be a field of
omap_hsmmc_host. But since it is declared under the platform slot while
the drivers struct omap_hsmmc_host has no slot abstraction, this looks
like a bug, especially when not familiar that this driver only supports
1 slot anyway.
Either we should add a slot abstraction to omap_hsmmc_host or remove
it from the platform data struct. Removed since slot multiplexing is
an un-implemented feature

Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Andreas Fenkart <afenkart@gmail.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 arch/arm/mach-omap2/hsmmc.c              |  88 ++++++++--------
 drivers/mmc/host/omap_hsmmc.c            | 175 ++++++++++++++++---------------
 include/linux/platform_data/hsmmc-omap.h | 100 +++++++++---------
 3 files changed, 181 insertions(+), 182 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c
index c65efc3cf81..4e2896ad011 100644
--- a/arch/arm/mach-omap2/hsmmc.c
+++ b/arch/arm/mach-omap2/hsmmc.c
@@ -39,8 +39,8 @@ static void omap_hsmmc1_before_set_reg(struct device *dev, int slot,
 	u32 reg, prog_io;
 	struct omap_hsmmc_platform_data *mmc = dev->platform_data;
 
-	if (mmc->slots[0].remux)
-		mmc->slots[0].remux(dev, slot, power_on);
+	if (mmc->remux)
+		mmc->remux(dev, slot, power_on);
 
 	/*
 	 * Assume we power both OMAP VMMC1 (for CMD, CLK, DAT0..3) and the
@@ -62,7 +62,7 @@ static void omap_hsmmc1_before_set_reg(struct device *dev, int slot,
 			omap_ctrl_writel(reg, OMAP243X_CONTROL_DEVCONF1);
 		}
 
-		if (mmc->slots[0].internal_clock) {
+		if (mmc->internal_clock) {
 			reg = omap_ctrl_readl(OMAP2_CONTROL_DEVCONF0);
 			reg |= OMAP2_MMCSDIO1ADPCLKISEL;
 			omap_ctrl_writel(reg, OMAP2_CONTROL_DEVCONF0);
@@ -115,7 +115,7 @@ static void hsmmc2_select_input_clk_src(struct omap_hsmmc_platform_data *mmc)
 	u32 reg;
 
 	reg = omap_ctrl_readl(control_devconf1_offset);
-	if (mmc->slots[0].internal_clock)
+	if (mmc->internal_clock)
 		reg |= OMAP2_MMCSDIO2ADPCLKISEL;
 	else
 		reg &= ~OMAP2_MMCSDIO2ADPCLKISEL;
@@ -127,8 +127,8 @@ static void hsmmc2_before_set_reg(struct device *dev, int slot,
 {
 	struct omap_hsmmc_platform_data *mmc = dev->platform_data;
 
-	if (mmc->slots[0].remux)
-		mmc->slots[0].remux(dev, slot, power_on);
+	if (mmc->remux)
+		mmc->remux(dev, slot, power_on);
 
 	if (power_on)
 		hsmmc2_select_input_clk_src(mmc);
@@ -154,14 +154,14 @@ static int nop_mmc_set_power(struct device *dev, int slot, int power_on,
 static inline void omap_hsmmc_mux(struct omap_hsmmc_platform_data
 				  *mmc_controller, int controller_nr)
 {
-	if (gpio_is_valid(mmc_controller->slots[0].switch_pin) &&
-		(mmc_controller->slots[0].switch_pin < OMAP_MAX_GPIO_LINES))
-		omap_mux_init_gpio(mmc_controller->slots[0].switch_pin,
-					OMAP_PIN_INPUT_PULLUP);
-	if (gpio_is_valid(mmc_controller->slots[0].gpio_wp) &&
-		(mmc_controller->slots[0].gpio_wp < OMAP_MAX_GPIO_LINES))
-		omap_mux_init_gpio(mmc_controller->slots[0].gpio_wp,
-					OMAP_PIN_INPUT_PULLUP);
+	if (gpio_is_valid(mmc_controller->switch_pin) &&
+	    (mmc_controller->switch_pin < OMAP_MAX_GPIO_LINES))
+		omap_mux_init_gpio(mmc_controller->switch_pin,
+				   OMAP_PIN_INPUT_PULLUP);
+	if (gpio_is_valid(mmc_controller->gpio_wp) &&
+	    (mmc_controller->gpio_wp < OMAP_MAX_GPIO_LINES))
+		omap_mux_init_gpio(mmc_controller->gpio_wp,
+				   OMAP_PIN_INPUT_PULLUP);
 	if (cpu_is_omap34xx()) {
 		if (controller_nr == 0) {
 			omap_mux_init_signal("sdmmc1_clk",
@@ -170,7 +170,7 @@ static inline void omap_hsmmc_mux(struct omap_hsmmc_platform_data
 				OMAP_PIN_INPUT_PULLUP);
 			omap_mux_init_signal("sdmmc1_dat0",
 				OMAP_PIN_INPUT_PULLUP);
-			if (mmc_controller->slots[0].caps &
+			if (mmc_controller->caps &
 				(MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA)) {
 				omap_mux_init_signal("sdmmc1_dat1",
 					OMAP_PIN_INPUT_PULLUP);
@@ -179,7 +179,7 @@ static inline void omap_hsmmc_mux(struct omap_hsmmc_platform_data
 				omap_mux_init_signal("sdmmc1_dat3",
 					OMAP_PIN_INPUT_PULLUP);
 			}
-			if (mmc_controller->slots[0].caps &
+			if (mmc_controller->caps &
 						MMC_CAP_8_BIT_DATA) {
 				omap_mux_init_signal("sdmmc1_dat4",
 					OMAP_PIN_INPUT_PULLUP);
@@ -204,7 +204,7 @@ static inline void omap_hsmmc_mux(struct omap_hsmmc_platform_data
 			 * For 8 wire configurations, Lines DAT4, 5, 6 and 7
 			 * need to be muxed in the board-*.c files
 			 */
-			if (mmc_controller->slots[0].caps &
+			if (mmc_controller->caps &
 				(MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA)) {
 				omap_mux_init_signal("sdmmc2_dat1",
 					OMAP_PIN_INPUT_PULLUP);
@@ -213,7 +213,7 @@ static inline void omap_hsmmc_mux(struct omap_hsmmc_platform_data
 				omap_mux_init_signal("sdmmc2_dat3",
 					OMAP_PIN_INPUT_PULLUP);
 			}
-			if (mmc_controller->slots[0].caps &
+			if (mmc_controller->caps &
 							MMC_CAP_8_BIT_DATA) {
 				omap_mux_init_signal("sdmmc2_dat4.sdmmc2_dat4",
 					OMAP_PIN_INPUT_PULLUP);
@@ -249,23 +249,23 @@ static int __init omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c,
 	else
 		snprintf(hc_name, (HSMMC_NAME_LEN + 1), "mmc%islot%i",
 								c->mmc, 1);
-	mmc->slots[0].name = hc_name;
+	mmc->name = hc_name;
 	mmc->nr_slots = 1;
-	mmc->slots[0].caps = c->caps;
-	mmc->slots[0].internal_clock = !c->ext_clock;
+	mmc->caps = c->caps;
+	mmc->internal_clock = !c->ext_clock;
 	mmc->reg_offset = 0;
 
-	mmc->slots[0].switch_pin = c->gpio_cd;
-	mmc->slots[0].gpio_wp = c->gpio_wp;
+	mmc->switch_pin = c->gpio_cd;
+	mmc->gpio_wp = c->gpio_wp;
 
-	mmc->slots[0].remux = c->remux;
-	mmc->slots[0].init_card = c->init_card;
+	mmc->remux = c->remux;
+	mmc->init_card = c->init_card;
 
 	if (c->cover_only)
-		mmc->slots[0].cover = 1;
+		mmc->cover = 1;
 
 	if (c->nonremovable)
-		mmc->slots[0].nonremovable = 1;
+		mmc->nonremovable = 1;
 
 	/*
 	 * NOTE:  MMC slots should have a Vcc regulator set up.
@@ -275,42 +275,42 @@ static int __init omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c,
 	 * temporary HACK: ocr_mask instead of fixed supply
 	 */
 	if (soc_is_am35xx())
-		mmc->slots[0].ocr_mask = MMC_VDD_165_195 |
+		mmc->ocr_mask = MMC_VDD_165_195 |
 					 MMC_VDD_26_27 |
 					 MMC_VDD_27_28 |
 					 MMC_VDD_29_30 |
 					 MMC_VDD_30_31 |
 					 MMC_VDD_31_32;
 	else
-		mmc->slots[0].ocr_mask = c->ocr_mask;
+		mmc->ocr_mask = c->ocr_mask;
 
 	if (!soc_is_am35xx())
-		mmc->slots[0].features |= HSMMC_HAS_PBIAS;
+		mmc->features |= HSMMC_HAS_PBIAS;
 
 	switch (c->mmc) {
 	case 1:
-		if (mmc->slots[0].features & HSMMC_HAS_PBIAS) {
+		if (mmc->features & HSMMC_HAS_PBIAS) {
 			/* on-chip level shifting via PBIAS0/PBIAS1 */
-			mmc->slots[0].before_set_reg =
+			mmc->before_set_reg =
 					omap_hsmmc1_before_set_reg;
-			mmc->slots[0].after_set_reg =
+			mmc->after_set_reg =
 					omap_hsmmc1_after_set_reg;
 		}
 
 		if (soc_is_am35xx())
-			mmc->slots[0].set_power = nop_mmc_set_power;
+			mmc->set_power = nop_mmc_set_power;
 
 		/* OMAP3630 HSMMC1 supports only 4-bit */
 		if (cpu_is_omap3630() &&
 				(c->caps & MMC_CAP_8_BIT_DATA)) {
 			c->caps &= ~MMC_CAP_8_BIT_DATA;
 			c->caps |= MMC_CAP_4_BIT_DATA;
-			mmc->slots[0].caps = c->caps;
+			mmc->caps = c->caps;
 		}
 		break;
 	case 2:
 		if (soc_is_am35xx())
-			mmc->slots[0].set_power = am35x_hsmmc2_set_power;
+			mmc->set_power = am35x_hsmmc2_set_power;
 
 		if (c->ext_clock)
 			c->transceiver = 1;
@@ -318,17 +318,17 @@ static int __init omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c,
 			c->caps &= ~MMC_CAP_8_BIT_DATA;
 			c->caps |= MMC_CAP_4_BIT_DATA;
 		}
-		if (mmc->slots[0].features & HSMMC_HAS_PBIAS) {
+		if (mmc->features & HSMMC_HAS_PBIAS) {
 			/* off-chip level shifting, or none */
-			mmc->slots[0].before_set_reg = hsmmc2_before_set_reg;
-			mmc->slots[0].after_set_reg = NULL;
+			mmc->before_set_reg = hsmmc2_before_set_reg;
+			mmc->after_set_reg = NULL;
 		}
 		break;
 	case 3:
 	case 4:
 	case 5:
-		mmc->slots[0].before_set_reg = NULL;
-		mmc->slots[0].after_set_reg = NULL;
+		mmc->before_set_reg = NULL;
+		mmc->after_set_reg = NULL;
 		break;
 	default:
 		pr_err("MMC%d configuration not supported!\n", c->mmc);
@@ -363,8 +363,8 @@ void omap_hsmmc_late_init(struct omap2_hsmmc_info *c)
 		if (!mmc_pdata)
 			continue;
 
-		mmc_pdata->slots[0].switch_pin = c->gpio_cd;
-		mmc_pdata->slots[0].gpio_wp = c->gpio_wp;
+		mmc_pdata->switch_pin = c->gpio_cd;
+		mmc_pdata->gpio_wp = c->gpio_wp;
 
 		res = omap_device_register(pdev);
 		if (res)
@@ -464,7 +464,7 @@ put_pdev:
 	platform_device_put(pdev);
 
 free_name:
-	kfree(mmc_data->slots[0].name);
+	kfree(mmc_data->name);
 
 free_mmc:
 	kfree(mmc_data);
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 03e8e9aa375..291b9e125d4 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -155,7 +155,7 @@
  * omap.c controller driver. Luckily this is not currently done on any known
  * omap_hsmmc.c device.
  */
-#define mmc_slot(host)		(host->pdata->slots[host->slot_id])
+#define mmc_pdata(host)		host->pdata
 
 /*
  * MMC Host controller read/write API's
@@ -236,7 +236,7 @@ static int omap_hsmmc_card_detect(struct device *dev, int slot)
 	struct omap_hsmmc_platform_data *mmc = host->pdata;
 
 	/* NOTE: assumes card detect signal is active-low */
-	return !gpio_get_value_cansleep(mmc->slots[0].switch_pin);
+	return !gpio_get_value_cansleep(mmc->switch_pin);
 }
 
 static int omap_hsmmc_get_wp(struct device *dev, int slot)
@@ -245,7 +245,7 @@ static int omap_hsmmc_get_wp(struct device *dev, int slot)
 	struct omap_hsmmc_platform_data *mmc = host->pdata;
 
 	/* NOTE: assumes write protect signal is active-high */
-	return gpio_get_value_cansleep(mmc->slots[0].gpio_wp);
+	return gpio_get_value_cansleep(mmc->gpio_wp);
 }
 
 static int omap_hsmmc_get_cover_state(struct device *dev, int slot)
@@ -254,7 +254,7 @@ static int omap_hsmmc_get_cover_state(struct device *dev, int slot)
 	struct omap_hsmmc_platform_data *mmc = host->pdata;
 
 	/* NOTE: assumes card detect signal is active-low */
-	return !gpio_get_value_cansleep(mmc->slots[0].switch_pin);
+	return !gpio_get_value_cansleep(mmc->switch_pin);
 }
 
 #ifdef CONFIG_PM
@@ -264,7 +264,7 @@ static int omap_hsmmc_suspend_cdirq(struct device *dev, int slot)
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
 	struct omap_hsmmc_platform_data *mmc = host->pdata;
 
-	disable_irq(mmc->slots[0].card_detect_irq);
+	disable_irq(mmc->card_detect_irq);
 	return 0;
 }
 
@@ -273,7 +273,7 @@ static int omap_hsmmc_resume_cdirq(struct device *dev, int slot)
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
 	struct omap_hsmmc_platform_data *mmc = host->pdata;
 
-	enable_irq(mmc->slots[0].card_detect_irq);
+	enable_irq(mmc->card_detect_irq);
 	return 0;
 }
 
@@ -300,8 +300,8 @@ static int omap_hsmmc_set_power(struct device *dev, int slot, int power_on,
 	if (!host->vcc)
 		return 0;
 
-	if (mmc_slot(host).before_set_reg)
-		mmc_slot(host).before_set_reg(dev, slot, power_on, vdd);
+	if (mmc_pdata(host)->before_set_reg)
+		mmc_pdata(host)->before_set_reg(dev, slot, power_on, vdd);
 
 	if (host->pbias) {
 		if (host->pbias_enabled == 1) {
@@ -363,8 +363,8 @@ static int omap_hsmmc_set_power(struct device *dev, int slot, int power_on,
 		}
 	}
 
-	if (mmc_slot(host).after_set_reg)
-		mmc_slot(host).after_set_reg(dev, slot, power_on, vdd);
+	if (mmc_pdata(host)->after_set_reg)
+		mmc_pdata(host)->after_set_reg(dev, slot, power_on, vdd);
 
 error_set_power:
 	return ret;
@@ -383,18 +383,18 @@ static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host)
 	} else {
 		host->vcc = reg;
 		ocr_value = mmc_regulator_get_ocrmask(reg);
-		if (!mmc_slot(host).ocr_mask) {
-			mmc_slot(host).ocr_mask = ocr_value;
+		if (!mmc_pdata(host)->ocr_mask) {
+			mmc_pdata(host)->ocr_mask = ocr_value;
 		} else {
-			if (!(mmc_slot(host).ocr_mask & ocr_value)) {
+			if (!(mmc_pdata(host)->ocr_mask & ocr_value)) {
 				dev_err(host->dev, "ocrmask %x is not supported\n",
-					mmc_slot(host).ocr_mask);
-				mmc_slot(host).ocr_mask = 0;
+					mmc_pdata(host)->ocr_mask);
+				mmc_pdata(host)->ocr_mask = 0;
 				return -EINVAL;
 			}
 		}
 	}
-	mmc_slot(host).set_power = omap_hsmmc_set_power;
+	mmc_pdata(host)->set_power = omap_hsmmc_set_power;
 
 	/* Allow an aux regulator */
 	reg = devm_regulator_get_optional(host->dev, "vmmc_aux");
@@ -404,7 +404,7 @@ static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host)
 	host->pbias = IS_ERR(reg) ? NULL : reg;
 
 	/* For eMMC do not power off when not in sleep state */
-	if (mmc_slot(host).no_regulator_off_init)
+	if (mmc_pdata(host)->no_regulator_off_init)
 		return 0;
 	/*
 	 * To disable boot_on regulator, enable regulator
@@ -412,10 +412,10 @@ static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host)
 	 */
 	if ((host->vcc && regulator_is_enabled(host->vcc) > 0) ||
 	    (host->vcc_aux && regulator_is_enabled(host->vcc_aux))) {
-		int vdd = ffs(mmc_slot(host).ocr_mask) - 1;
+		int vdd = ffs(mmc_pdata(host)->ocr_mask) - 1;
 
-		mmc_slot(host).set_power(host->dev, host->slot_id, 1, vdd);
-		mmc_slot(host).set_power(host->dev, host->slot_id, 0, 0);
+		mmc_pdata(host)->set_power(host->dev, host->slot_id, 1, vdd);
+		mmc_pdata(host)->set_power(host->dev, host->slot_id, 0, 0);
 	}
 
 	return 0;
@@ -423,7 +423,7 @@ static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host)
 
 static void omap_hsmmc_reg_put(struct omap_hsmmc_host *host)
 {
-	mmc_slot(host).set_power = NULL;
+	mmc_pdata(host)->set_power = NULL;
 }
 
 static inline int omap_hsmmc_have_reg(void)
@@ -453,51 +453,53 @@ static int omap_hsmmc_gpio_init(struct omap_hsmmc_platform_data *pdata)
 {
 	int ret;
 
-	if (gpio_is_valid(pdata->slots[0].switch_pin)) {
-		if (pdata->slots[0].cover)
-			pdata->slots[0].get_cover_state =
+	if (gpio_is_valid(pdata->switch_pin)) {
+		if (pdata->cover)
+			pdata->get_cover_state =
 					omap_hsmmc_get_cover_state;
 		else
-			pdata->slots[0].card_detect = omap_hsmmc_card_detect;
-		pdata->slots[0].card_detect_irq =
-				gpio_to_irq(pdata->slots[0].switch_pin);
-		ret = gpio_request(pdata->slots[0].switch_pin, "mmc_cd");
+			pdata->card_detect = omap_hsmmc_card_detect;
+		pdata->card_detect_irq =
+				gpio_to_irq(pdata->switch_pin);
+		ret = gpio_request(pdata->switch_pin, "mmc_cd");
 		if (ret)
 			return ret;
-		ret = gpio_direction_input(pdata->slots[0].switch_pin);
+		ret = gpio_direction_input(pdata->switch_pin);
 		if (ret)
 			goto err_free_sp;
-	} else
-		pdata->slots[0].switch_pin = -EINVAL;
+	} else {
+		pdata->switch_pin = -EINVAL;
+	}
 
-	if (gpio_is_valid(pdata->slots[0].gpio_wp)) {
-		pdata->slots[0].get_ro = omap_hsmmc_get_wp;
-		ret = gpio_request(pdata->slots[0].gpio_wp, "mmc_wp");
+	if (gpio_is_valid(pdata->gpio_wp)) {
+		pdata->get_ro = omap_hsmmc_get_wp;
+		ret = gpio_request(pdata->gpio_wp, "mmc_wp");
 		if (ret)
 			goto err_free_cd;
-		ret = gpio_direction_input(pdata->slots[0].gpio_wp);
+		ret = gpio_direction_input(pdata->gpio_wp);
 		if (ret)
 			goto err_free_wp;
-	} else
-		pdata->slots[0].gpio_wp = -EINVAL;
+	} else {
+		pdata->gpio_wp = -EINVAL;
+	}
 
 	return 0;
 
 err_free_wp:
-	gpio_free(pdata->slots[0].gpio_wp);
+	gpio_free(pdata->gpio_wp);
 err_free_cd:
-	if (gpio_is_valid(pdata->slots[0].switch_pin))
+	if (gpio_is_valid(pdata->switch_pin))
 err_free_sp:
-		gpio_free(pdata->slots[0].switch_pin);
+		gpio_free(pdata->switch_pin);
 	return ret;
 }
 
 static void omap_hsmmc_gpio_free(struct omap_hsmmc_platform_data *pdata)
 {
-	if (gpio_is_valid(pdata->slots[0].gpio_wp))
-		gpio_free(pdata->slots[0].gpio_wp);
-	if (gpio_is_valid(pdata->slots[0].switch_pin))
-		gpio_free(pdata->slots[0].switch_pin);
+	if (gpio_is_valid(pdata->gpio_wp))
+		gpio_free(pdata->gpio_wp);
+	if (gpio_is_valid(pdata->switch_pin))
+		gpio_free(pdata->switch_pin);
 }
 
 /*
@@ -607,7 +609,7 @@ static void omap_hsmmc_set_clock(struct omap_hsmmc_host *host)
 	 *	  in capabilities register
 	 *	- MMC/SD clock coming out of controller > 25MHz
 	 */
-	if ((mmc_slot(host).features & HSMMC_HAS_HSPE_SUPPORT) &&
+	if ((mmc_pdata(host)->features & HSMMC_HAS_HSPE_SUPPORT) &&
 	    (ios->timing != MMC_TIMING_MMC_DDR52) &&
 	    ((OMAP_HSMMC_READ(host->base, CAPA) & HSS) == HSS)) {
 		regval = OMAP_HSMMC_READ(host->base, HCTL);
@@ -791,8 +793,8 @@ int omap_hsmmc_cover_is_closed(struct omap_hsmmc_host *host)
 {
 	int r = 1;
 
-	if (mmc_slot(host).get_cover_state)
-		r = mmc_slot(host).get_cover_state(host->dev, host->slot_id);
+	if (mmc_pdata(host)->get_cover_state)
+		r = mmc_pdata(host)->get_cover_state(host->dev, host->slot_id);
 	return r;
 }
 
@@ -816,7 +818,7 @@ omap_hsmmc_show_slot_name(struct device *dev, struct device_attribute *attr,
 	struct mmc_host *mmc = container_of(dev, struct mmc_host, class_dev);
 	struct omap_hsmmc_host *host = mmc_priv(mmc);
 
-	return sprintf(buf, "%s\n", mmc_slot(host).name);
+	return sprintf(buf, "%s\n", mmc_pdata(host)->name);
 }
 
 static DEVICE_ATTR(slot_name, S_IRUGO, omap_hsmmc_show_slot_name, NULL);
@@ -1061,7 +1063,7 @@ static inline void omap_hsmmc_reset_controller_fsm(struct omap_hsmmc_host *host,
 	 * OMAP4 ES2 and greater has an updated reset logic.
 	 * Monitor a 0->1 transition first
 	 */
-	if (mmc_slot(host).features & HSMMC_HAS_UPDATED_RESET) {
+	if (mmc_pdata(host)->features & HSMMC_HAS_UPDATED_RESET) {
 		while ((!(OMAP_HSMMC_READ(host->base, SYSCTL) & bit))
 					&& (i++ < limit))
 			udelay(1);
@@ -1210,12 +1212,12 @@ static int omap_hsmmc_switch_opcond(struct omap_hsmmc_host *host, int vdd)
 		clk_disable_unprepare(host->dbclk);
 
 	/* Turn the power off */
-	ret = mmc_slot(host).set_power(host->dev, host->slot_id, 0, 0);
+	ret = mmc_pdata(host)->set_power(host->dev, host->slot_id, 0, 0);
 
 	/* Turn the power ON with given VDD 1.8 or 3.0v */
 	if (!ret)
-		ret = mmc_slot(host).set_power(host->dev, host->slot_id, 1,
-					       vdd);
+		ret = mmc_pdata(host)->set_power(host->dev, host->slot_id, 1,
+						 vdd);
 	pm_runtime_get_sync(host->dev);
 	if (host->dbclk)
 		clk_prepare_enable(host->dbclk);
@@ -1259,11 +1261,11 @@ err:
 /* Protect the card while the cover is open */
 static void omap_hsmmc_protect_card(struct omap_hsmmc_host *host)
 {
-	if (!mmc_slot(host).get_cover_state)
+	if (!mmc_pdata(host)->get_cover_state)
 		return;
 
 	host->reqs_blocked = 0;
-	if (mmc_slot(host).get_cover_state(host->dev, host->slot_id)) {
+	if (mmc_pdata(host)->get_cover_state(host->dev, host->slot_id)) {
 		if (host->protect_card) {
 			dev_info(host->dev, "%s: cover is closed, "
 					 "card is now accessible\n",
@@ -1286,13 +1288,13 @@ static void omap_hsmmc_protect_card(struct omap_hsmmc_host *host)
 static irqreturn_t omap_hsmmc_detect(int irq, void *dev_id)
 {
 	struct omap_hsmmc_host *host = dev_id;
-	struct omap_hsmmc_slot_data *slot = &mmc_slot(host);
+	struct omap_hsmmc_platform_data *pdata = host->pdata;
 	int carddetect;
 
 	sysfs_notify(&host->mmc->class_dev.kobj, NULL, "cover_switch");
 
-	if (slot->card_detect)
-		carddetect = slot->card_detect(host->dev, host->slot_id);
+	if (pdata->card_detect)
+		carddetect = pdata->card_detect(host->dev, host->slot_id);
 	else {
 		omap_hsmmc_protect_card(host);
 		carddetect = -ENOSYS;
@@ -1618,12 +1620,12 @@ static void omap_hsmmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	if (ios->power_mode != host->power_mode) {
 		switch (ios->power_mode) {
 		case MMC_POWER_OFF:
-			mmc_slot(host).set_power(host->dev, host->slot_id,
-						 0, 0);
+			mmc_pdata(host)->set_power(host->dev, host->slot_id,
+						   0, 0);
 			break;
 		case MMC_POWER_UP:
-			mmc_slot(host).set_power(host->dev, host->slot_id,
-						 1, ios->vdd);
+			mmc_pdata(host)->set_power(host->dev, host->slot_id,
+						   1, ios->vdd);
 			break;
 		case MMC_POWER_ON:
 			do_send_init_stream = 1;
@@ -1668,26 +1670,26 @@ static int omap_hsmmc_get_cd(struct mmc_host *mmc)
 {
 	struct omap_hsmmc_host *host = mmc_priv(mmc);
 
-	if (!mmc_slot(host).card_detect)
+	if (!mmc_pdata(host)->card_detect)
 		return -ENOSYS;
-	return mmc_slot(host).card_detect(host->dev, host->slot_id);
+	return mmc_pdata(host)->card_detect(host->dev, host->slot_id);
 }
 
 static int omap_hsmmc_get_ro(struct mmc_host *mmc)
 {
 	struct omap_hsmmc_host *host = mmc_priv(mmc);
 
-	if (!mmc_slot(host).get_ro)
+	if (!mmc_pdata(host)->get_ro)
 		return -ENOSYS;
-	return mmc_slot(host).get_ro(host->dev, 0);
+	return mmc_pdata(host)->get_ro(host->dev, 0);
 }
 
 static void omap_hsmmc_init_card(struct mmc_host *mmc, struct mmc_card *card)
 {
 	struct omap_hsmmc_host *host = mmc_priv(mmc);
 
-	if (mmc_slot(host).init_card)
-		mmc_slot(host).init_card(card);
+	if (mmc_pdata(host)->init_card)
+		mmc_pdata(host)->init_card(card);
 }
 
 static void omap_hsmmc_enable_sdio_irq(struct mmc_host *mmc, int enable)
@@ -1978,33 +1980,33 @@ static struct omap_hsmmc_platform_data *of_get_hsmmc_pdata(struct device *dev)
 
 	/* This driver only supports 1 slot */
 	pdata->nr_slots = 1;
-	pdata->slots[0].switch_pin = cd_gpio;
-	pdata->slots[0].gpio_wp = wp_gpio;
+	pdata->switch_pin = cd_gpio;
+	pdata->gpio_wp = wp_gpio;
 
 	if (of_find_property(np, "ti,non-removable", NULL)) {
-		pdata->slots[0].nonremovable = true;
-		pdata->slots[0].no_regulator_off_init = true;
+		pdata->nonremovable = true;
+		pdata->no_regulator_off_init = true;
 	}
 	of_property_read_u32(np, "bus-width", &bus_width);
 	if (bus_width == 4)
-		pdata->slots[0].caps |= MMC_CAP_4_BIT_DATA;
+		pdata->caps |= MMC_CAP_4_BIT_DATA;
 	else if (bus_width == 8)
-		pdata->slots[0].caps |= MMC_CAP_8_BIT_DATA;
+		pdata->caps |= MMC_CAP_8_BIT_DATA;
 
 	if (of_find_property(np, "ti,needs-special-reset", NULL))
-		pdata->slots[0].features |= HSMMC_HAS_UPDATED_RESET;
+		pdata->features |= HSMMC_HAS_UPDATED_RESET;
 
 	if (!of_property_read_u32(np, "max-frequency", &max_freq))
 		pdata->max_freq = max_freq;
 
 	if (of_find_property(np, "ti,needs-special-hs-handling", NULL))
-		pdata->slots[0].features |= HSMMC_HAS_HSPE_SUPPORT;
+		pdata->features |= HSMMC_HAS_HSPE_SUPPORT;
 
 	if (of_find_property(np, "keep-power-in-suspend", NULL))
-		pdata->slots[0].pm_caps |= MMC_PM_KEEP_POWER;
+		pdata->pm_caps |= MMC_PM_KEEP_POWER;
 
 	if (of_find_property(np, "enable-sdio-wakeup", NULL))
-		pdata->slots[0].pm_caps |= MMC_PM_WAKE_SDIO_IRQ;
+		pdata->pm_caps |= MMC_PM_WAKE_SDIO_IRQ;
 
 	return pdata;
 }
@@ -2144,14 +2146,14 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 	mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED |
 		     MMC_CAP_WAIT_WHILE_BUSY | MMC_CAP_ERASE;
 
-	mmc->caps |= mmc_slot(host).caps;
+	mmc->caps |= mmc_pdata(host)->caps;
 	if (mmc->caps & MMC_CAP_8_BIT_DATA)
 		mmc->caps |= MMC_CAP_4_BIT_DATA;
 
-	if (mmc_slot(host).nonremovable)
+	if (mmc_pdata(host)->nonremovable)
 		mmc->caps |= MMC_CAP_NONREMOVABLE;
 
-	mmc->pm_caps = mmc_slot(host).pm_caps;
+	mmc->pm_caps = mmc_pdata(host)->pm_caps;
 
 	omap_hsmmc_conf_bus_power(host);
 
@@ -2204,19 +2206,19 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 		goto err_irq;
 	}
 
-	if (omap_hsmmc_have_reg() && !mmc_slot(host).set_power) {
+	if (omap_hsmmc_have_reg() && !mmc_pdata(host)->set_power) {
 		ret = omap_hsmmc_reg_get(host);
 		if (ret)
 			goto err_irq;
 		host->use_reg = 1;
 	}
 
-	mmc->ocr_avail = mmc_slot(host).ocr_mask;
+	mmc->ocr_avail = mmc_pdata(host)->ocr_mask;
 
 	/* Request IRQ for card detect */
-	if ((mmc_slot(host).card_detect_irq)) {
+	if ((mmc_pdata(host)->card_detect_irq)) {
 		ret = devm_request_threaded_irq(&pdev->dev,
-						mmc_slot(host).card_detect_irq,
+						mmc_pdata(host)->card_detect_irq,
 						NULL, omap_hsmmc_detect,
 					   IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
 					   mmc_hostname(mmc), host);
@@ -2247,12 +2249,13 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 
 	mmc_add_host(mmc);
 
-	if (mmc_slot(host).name != NULL) {
+	if (mmc_pdata(host)->name != NULL) {
 		ret = device_create_file(&mmc->class_dev, &dev_attr_slot_name);
 		if (ret < 0)
 			goto err_slot_name;
 	}
-	if (mmc_slot(host).card_detect_irq && mmc_slot(host).get_cover_state) {
+	if (mmc_pdata(host)->card_detect_irq &&
+	    mmc_pdata(host)->get_cover_state) {
 		ret = device_create_file(&mmc->class_dev,
 					&dev_attr_cover_switch);
 		if (ret < 0)
diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h
index 35d494f7d62..26912143adc 100644
--- a/include/linux/platform_data/hsmmc-omap.h
+++ b/include/linux/platform_data/hsmmc-omap.h
@@ -8,8 +8,6 @@
  * published by the Free Software Foundation.
  */
 
-#define OMAP_HSMMC_MAX_SLOTS	1
-
 /*
  * struct omap_hsmmc_dev_attr.flags possibilities
  *
@@ -57,62 +55,60 @@ struct omap_hsmmc_platform_data {
 	/* Register offset deviation */
 	u16 reg_offset;
 
-	struct omap_hsmmc_slot_data {
-		/*
-		 * 4/8 wires and any additional host capabilities
-		 * need to OR'd all capabilities (ref. linux/mmc/host.h)
-		 */
-		u32 caps;	/* Used for the MMC driver on 2430 and later */
-		u32 pm_caps;	/* PM capabilities of the mmc */
+	/*
+	 * 4/8 wires and any additional host capabilities
+	 * need to OR'd all capabilities (ref. linux/mmc/host.h)
+	 */
+	u32 caps;	/* Used for the MMC driver on 2430 and later */
+	u32 pm_caps;	/* PM capabilities of the mmc */
 
-		/* switch pin can be for card detect (default) or card cover */
-		unsigned cover:1;
+	/* switch pin can be for card detect (default) or card cover */
+	unsigned cover:1;
 
-		/* use the internal clock */
-		unsigned internal_clock:1;
+	/* use the internal clock */
+	unsigned internal_clock:1;
 
-		/* nonremovable e.g. eMMC */
-		unsigned nonremovable:1;
+	/* nonremovable e.g. eMMC */
+	unsigned nonremovable:1;
 
-		/* eMMC does not handle power off when not in sleep state */
-		unsigned no_regulator_off_init:1;
+	/* eMMC does not handle power off when not in sleep state */
+	unsigned no_regulator_off_init:1;
 
-		/* we can put the features above into this variable */
+	/* we can put the features above into this variable */
 #define HSMMC_HAS_PBIAS		(1 << 0)
 #define HSMMC_HAS_UPDATED_RESET	(1 << 1)
 #define HSMMC_HAS_HSPE_SUPPORT	(1 << 2)
-		unsigned features;
-
-		int switch_pin;			/* gpio (card detect) */
-		int gpio_wp;			/* gpio (write protect) */
-
-		int (*set_power)(struct device *dev, int slot,
-				 int power_on, int vdd);
-		int (*get_ro)(struct device *dev, int slot);
-		void (*remux)(struct device *dev, int slot, int power_on);
-		/* Call back before enabling / disabling regulators */
-		void (*before_set_reg)(struct device *dev, int slot,
-				       int power_on, int vdd);
-		/* Call back after enabling / disabling regulators */
-		void (*after_set_reg)(struct device *dev, int slot,
-				      int power_on, int vdd);
-		/* if we have special card, init it using this callback */
-		void (*init_card)(struct mmc_card *card);
-
-		/* return MMC cover switch state, can be NULL if not supported.
-		 *
-		 * possible return values:
-		 *   0 - closed
-		 *   1 - open
-		 */
-		int (*get_cover_state)(struct device *dev, int slot);
-
-		const char *name;
-		u32 ocr_mask;
-
-		/* Card detection IRQs */
-		int card_detect_irq;
-
-		int (*card_detect)(struct device *dev, int slot);
-	} slots[OMAP_HSMMC_MAX_SLOTS];
+	unsigned features;
+
+	int switch_pin;			/* gpio (card detect) */
+	int gpio_wp;			/* gpio (write protect) */
+
+	int (*set_power)(struct device *dev, int slot,
+			 int power_on, int vdd);
+	int (*get_ro)(struct device *dev, int slot);
+	void (*remux)(struct device *dev, int slot, int power_on);
+	/* Call back before enabling / disabling regulators */
+	void (*before_set_reg)(struct device *dev, int slot,
+			       int power_on, int vdd);
+	/* Call back after enabling / disabling regulators */
+	void (*after_set_reg)(struct device *dev, int slot,
+			      int power_on, int vdd);
+	/* if we have special card, init it using this callback */
+	void (*init_card)(struct mmc_card *card);
+
+	/* return MMC cover switch state, can be NULL if not supported.
+	 *
+	 * possible return values:
+	 *   0 - closed
+	 *   1 - open
+	 */
+	int (*get_cover_state)(struct device *dev, int slot);
+
+	const char *name;
+	u32 ocr_mask;
+
+	/* Card detection IRQs */
+	int card_detect_irq;
+
+	int (*card_detect)(struct device *dev, int slot);
 };
-- 
cgit v1.2.3-70-g09d2


From b5cd43f062717b6c92f93bc0c593764e144ea331 Mon Sep 17 00:00:00 2001
From: Andreas Fenkart <afenkart@gmail.com>
Date: Sat, 8 Nov 2014 15:33:16 +0100
Subject: mmc: omap_hsmmc: Remove unnecessary callbacks from platform data

These callbacks are set during driver probe and not from the platform
init, -- evtl. they had been for oamp 1/2 -- for omap3 they are local
functions of the driver. These indirection could be dropped
altogether in favor of regular function calls TODO

Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Andreas Fenkart <afenkart@gmail.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/omap_hsmmc.c            | 75 +++++++++++++++++++-------------
 include/linux/platform_data/hsmmc-omap.h | 18 --------
 2 files changed, 45 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 8a216c92c5a..f4f1bcd632f 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -221,6 +221,25 @@ struct omap_hsmmc_host {
 #define HSMMC_WAKE_IRQ_ENABLED	(1 << 2)
 	struct omap_hsmmc_next	next_data;
 	struct	omap_hsmmc_platform_data	*pdata;
+
+	/* To handle board related suspend/resume functionality for MMC */
+	int (*suspend)(struct device *dev, int slot);
+	int (*resume)(struct device *dev, int slot);
+
+	/* return MMC cover switch state, can be NULL if not supported.
+	 *
+	 * possible return values:
+	 *   0 - closed
+	 *   1 - open
+	 */
+	int (*get_cover_state)(struct device *dev, int slot);
+
+	/* Card detection IRQs */
+	int card_detect_irq;
+
+	int (*card_detect)(struct device *dev, int slot);
+	int (*get_ro)(struct device *dev, int slot);
+
 };
 
 struct omap_mmc_of_data {
@@ -262,18 +281,16 @@ static int omap_hsmmc_get_cover_state(struct device *dev, int slot)
 static int omap_hsmmc_suspend_cdirq(struct device *dev, int slot)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
-	struct omap_hsmmc_platform_data *mmc = host->pdata;
 
-	disable_irq(mmc->card_detect_irq);
+	disable_irq(host->card_detect_irq);
 	return 0;
 }
 
 static int omap_hsmmc_resume_cdirq(struct device *dev, int slot)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
-	struct omap_hsmmc_platform_data *mmc = host->pdata;
 
-	enable_irq(mmc->card_detect_irq);
+	enable_irq(host->card_detect_irq);
 	return 0;
 }
 
@@ -456,11 +473,11 @@ static int omap_hsmmc_gpio_init(struct omap_hsmmc_host *host,
 
 	if (gpio_is_valid(pdata->switch_pin)) {
 		if (pdata->cover)
-			pdata->get_cover_state =
-					omap_hsmmc_get_cover_state;
+			host->get_cover_state =
+				omap_hsmmc_get_cover_state;
 		else
-			pdata->card_detect = omap_hsmmc_card_detect;
-		pdata->card_detect_irq =
+			host->card_detect = omap_hsmmc_card_detect;
+		host->card_detect_irq =
 				gpio_to_irq(pdata->switch_pin);
 		ret = gpio_request(pdata->switch_pin, "mmc_cd");
 		if (ret)
@@ -473,7 +490,7 @@ static int omap_hsmmc_gpio_init(struct omap_hsmmc_host *host,
 	}
 
 	if (gpio_is_valid(pdata->gpio_wp)) {
-		pdata->get_ro = omap_hsmmc_get_wp;
+		host->get_ro = omap_hsmmc_get_wp;
 		ret = gpio_request(pdata->gpio_wp, "mmc_wp");
 		if (ret)
 			goto err_free_cd;
@@ -795,8 +812,8 @@ int omap_hsmmc_cover_is_closed(struct omap_hsmmc_host *host)
 {
 	int r = 1;
 
-	if (mmc_pdata(host)->get_cover_state)
-		r = mmc_pdata(host)->get_cover_state(host->dev, host->slot_id);
+	if (host->get_cover_state)
+		r = host->get_cover_state(host->dev, host->slot_id);
 	return r;
 }
 
@@ -1263,11 +1280,11 @@ err:
 /* Protect the card while the cover is open */
 static void omap_hsmmc_protect_card(struct omap_hsmmc_host *host)
 {
-	if (!mmc_pdata(host)->get_cover_state)
+	if (!host->get_cover_state)
 		return;
 
 	host->reqs_blocked = 0;
-	if (mmc_pdata(host)->get_cover_state(host->dev, host->slot_id)) {
+	if (host->get_cover_state(host->dev, host->slot_id)) {
 		if (host->protect_card) {
 			dev_info(host->dev, "%s: cover is closed, "
 					 "card is now accessible\n",
@@ -1290,13 +1307,12 @@ static void omap_hsmmc_protect_card(struct omap_hsmmc_host *host)
 static irqreturn_t omap_hsmmc_detect(int irq, void *dev_id)
 {
 	struct omap_hsmmc_host *host = dev_id;
-	struct omap_hsmmc_platform_data *pdata = host->pdata;
 	int carddetect;
 
 	sysfs_notify(&host->mmc->class_dev.kobj, NULL, "cover_switch");
 
-	if (pdata->card_detect)
-		carddetect = pdata->card_detect(host->dev, host->slot_id);
+	if (host->card_detect)
+		carddetect = host->card_detect(host->dev, host->slot_id);
 	else {
 		omap_hsmmc_protect_card(host);
 		carddetect = -ENOSYS;
@@ -1672,18 +1688,18 @@ static int omap_hsmmc_get_cd(struct mmc_host *mmc)
 {
 	struct omap_hsmmc_host *host = mmc_priv(mmc);
 
-	if (!mmc_pdata(host)->card_detect)
+	if (!host->card_detect)
 		return -ENOSYS;
-	return mmc_pdata(host)->card_detect(host->dev, host->slot_id);
+	return host->card_detect(host->dev, host->slot_id);
 }
 
 static int omap_hsmmc_get_ro(struct mmc_host *mmc)
 {
 	struct omap_hsmmc_host *host = mmc_priv(mmc);
 
-	if (!mmc_pdata(host)->get_ro)
+	if (!host->get_ro)
 		return -ENOSYS;
-	return mmc_pdata(host)->get_ro(host->dev, 0);
+	return host->get_ro(host->dev, 0);
 }
 
 static void omap_hsmmc_init_card(struct mmc_host *mmc, struct mmc_card *card)
@@ -2218,9 +2234,9 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 	mmc->ocr_avail = mmc_pdata(host)->ocr_mask;
 
 	/* Request IRQ for card detect */
-	if ((mmc_pdata(host)->card_detect_irq)) {
+	if (host->card_detect_irq) {
 		ret = devm_request_threaded_irq(&pdev->dev,
-						mmc_pdata(host)->card_detect_irq,
+						host->card_detect_irq,
 						NULL, omap_hsmmc_detect,
 					   IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
 					   mmc_hostname(mmc), host);
@@ -2229,8 +2245,8 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 				"Unable to grab MMC CD IRQ\n");
 			goto err_irq_cd;
 		}
-		pdata->suspend = omap_hsmmc_suspend_cdirq;
-		pdata->resume = omap_hsmmc_resume_cdirq;
+		host->suspend = omap_hsmmc_suspend_cdirq;
+		host->resume = omap_hsmmc_resume_cdirq;
 	}
 
 	omap_hsmmc_disable_irq(host);
@@ -2256,8 +2272,7 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 		if (ret < 0)
 			goto err_slot_name;
 	}
-	if (mmc_pdata(host)->card_detect_irq &&
-	    mmc_pdata(host)->get_cover_state) {
+	if (host->card_detect_irq && host->get_cover_state) {
 		ret = device_create_file(&mmc->class_dev,
 					&dev_attr_cover_switch);
 		if (ret < 0)
@@ -2322,8 +2337,8 @@ static int omap_hsmmc_prepare(struct device *dev)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
 
-	if (host->pdata->suspend)
-		return host->pdata->suspend(dev, host->slot_id);
+	if (host->suspend)
+		return host->suspend(dev, host->slot_id);
 
 	return 0;
 }
@@ -2332,8 +2347,8 @@ static void omap_hsmmc_complete(struct device *dev)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
 
-	if (host->pdata->resume)
-		host->pdata->resume(dev, host->slot_id);
+	if (host->resume)
+		host->resume(dev, host->slot_id);
 
 }
 
diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h
index 26912143adc..68ffec14b56 100644
--- a/include/linux/platform_data/hsmmc-omap.h
+++ b/include/linux/platform_data/hsmmc-omap.h
@@ -45,10 +45,6 @@ struct omap_hsmmc_platform_data {
 	 * maximum frequency on the MMC bus */
 	unsigned int max_freq;
 
-	/* To handle board related suspend/resume functionality for MMC */
-	int (*suspend)(struct device *dev, int slot);
-	int (*resume)(struct device *dev, int slot);
-
 	/* Integrating attributes from the omap_hwmod layer */
 	u8 controller_flags;
 
@@ -85,7 +81,6 @@ struct omap_hsmmc_platform_data {
 
 	int (*set_power)(struct device *dev, int slot,
 			 int power_on, int vdd);
-	int (*get_ro)(struct device *dev, int slot);
 	void (*remux)(struct device *dev, int slot, int power_on);
 	/* Call back before enabling / disabling regulators */
 	void (*before_set_reg)(struct device *dev, int slot,
@@ -96,19 +91,6 @@ struct omap_hsmmc_platform_data {
 	/* if we have special card, init it using this callback */
 	void (*init_card)(struct mmc_card *card);
 
-	/* return MMC cover switch state, can be NULL if not supported.
-	 *
-	 * possible return values:
-	 *   0 - closed
-	 *   1 - open
-	 */
-	int (*get_cover_state)(struct device *dev, int slot);
-
 	const char *name;
 	u32 ocr_mask;
-
-	/* Card detection IRQs */
-	int card_detect_irq;
-
-	int (*card_detect)(struct device *dev, int slot);
 };
-- 
cgit v1.2.3-70-g09d2


From 80412ca8abf087354891108d2f888ad3de56e73c Mon Sep 17 00:00:00 2001
From: Andreas Fenkart <afenkart@gmail.com>
Date: Sat, 8 Nov 2014 15:33:17 +0100
Subject: mmc: omap_hsmmc: remove unused slot_id parameter

omap_hsmmc only supports one slot. So slot id is always zero, and
slot id was never used in the callbacks anyway

Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Andreas Fenkart <afenkart@gmail.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 arch/arm/mach-omap2/board-rx51-peripherals.c |  2 +-
 arch/arm/mach-omap2/hsmmc.c                  | 21 ++++-----
 arch/arm/mach-omap2/hsmmc.h                  |  2 +-
 drivers/mmc/host/omap_hsmmc.c                | 65 +++++++++++-----------------
 include/linux/platform_data/hsmmc-omap.h     | 14 ++----
 5 files changed, 40 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index 0a8ac844b75..3d5040f82e9 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -484,7 +484,7 @@ static struct omap_mux_partition *partition;
  * Current flows to eMMC when eMMC is off and the data lines are pulled up,
  * so pull them down. N.B. we pull 8 lines because we are using 8 lines.
  */
-static void rx51_mmc2_remux(struct device *dev, int slot, int power_on)
+static void rx51_mmc2_remux(struct device *dev, int power_on)
 {
 	if (power_on)
 		omap_mux_write_array(partition, rx51_mmc2_on_mux);
diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c
index 4e2896ad011..dc6e79c4484 100644
--- a/arch/arm/mach-omap2/hsmmc.c
+++ b/arch/arm/mach-omap2/hsmmc.c
@@ -33,14 +33,14 @@ static u16 control_devconf1_offset;
 
 #define HSMMC_NAME_LEN	9
 
-static void omap_hsmmc1_before_set_reg(struct device *dev, int slot,
-				  int power_on, int vdd)
+static void omap_hsmmc1_before_set_reg(struct device *dev,
+				       int power_on, int vdd)
 {
 	u32 reg, prog_io;
 	struct omap_hsmmc_platform_data *mmc = dev->platform_data;
 
 	if (mmc->remux)
-		mmc->remux(dev, slot, power_on);
+		mmc->remux(dev, power_on);
 
 	/*
 	 * Assume we power both OMAP VMMC1 (for CMD, CLK, DAT0..3) and the
@@ -86,8 +86,7 @@ static void omap_hsmmc1_before_set_reg(struct device *dev, int slot,
 	}
 }
 
-static void omap_hsmmc1_after_set_reg(struct device *dev, int slot,
-				 int power_on, int vdd)
+static void omap_hsmmc1_after_set_reg(struct device *dev, int power_on, int vdd)
 {
 	u32 reg;
 
@@ -122,20 +121,18 @@ static void hsmmc2_select_input_clk_src(struct omap_hsmmc_platform_data *mmc)
 	omap_ctrl_writel(reg, control_devconf1_offset);
 }
 
-static void hsmmc2_before_set_reg(struct device *dev, int slot,
-				   int power_on, int vdd)
+static void hsmmc2_before_set_reg(struct device *dev, int power_on, int vdd)
 {
 	struct omap_hsmmc_platform_data *mmc = dev->platform_data;
 
 	if (mmc->remux)
-		mmc->remux(dev, slot, power_on);
+		mmc->remux(dev, power_on);
 
 	if (power_on)
 		hsmmc2_select_input_clk_src(mmc);
 }
 
-static int am35x_hsmmc2_set_power(struct device *dev, int slot,
-				  int power_on, int vdd)
+static int am35x_hsmmc2_set_power(struct device *dev, int power_on, int vdd)
 {
 	struct omap_hsmmc_platform_data *mmc = dev->platform_data;
 
@@ -145,8 +142,7 @@ static int am35x_hsmmc2_set_power(struct device *dev, int slot,
 	return 0;
 }
 
-static int nop_mmc_set_power(struct device *dev, int slot, int power_on,
-							int vdd)
+static int nop_mmc_set_power(struct device *dev, int power_on, int vdd)
 {
 	return 0;
 }
@@ -250,7 +246,6 @@ static int __init omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c,
 		snprintf(hc_name, (HSMMC_NAME_LEN + 1), "mmc%islot%i",
 								c->mmc, 1);
 	mmc->name = hc_name;
-	mmc->nr_slots = 1;
 	mmc->caps = c->caps;
 	mmc->internal_clock = !c->ext_clock;
 	mmc->reg_offset = 0;
diff --git a/arch/arm/mach-omap2/hsmmc.h b/arch/arm/mach-omap2/hsmmc.h
index 30c78c17eb7..148cd9b1549 100644
--- a/arch/arm/mach-omap2/hsmmc.h
+++ b/arch/arm/mach-omap2/hsmmc.h
@@ -23,7 +23,7 @@ struct omap2_hsmmc_info {
 	struct platform_device *pdev;	/* mmc controller instance */
 	int	ocr_mask;	/* temporary HACK */
 	/* Remux (pad configuration) when powering on/off */
-	void (*remux)(struct device *dev, int slot, int power_on);
+	void (*remux)(struct device *dev, int power_on);
 	/* init some special card */
 	void (*init_card)(struct mmc_card *card);
 };
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index f4f1bcd632f..82b40b85293 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -207,7 +207,6 @@ struct omap_hsmmc_host {
 	int			use_dma, dma_ch;
 	struct dma_chan		*tx_chan;
 	struct dma_chan		*rx_chan;
-	int			slot_id;
 	int			response_busy;
 	int			context_loss;
 	int			protect_card;
@@ -223,8 +222,8 @@ struct omap_hsmmc_host {
 	struct	omap_hsmmc_platform_data	*pdata;
 
 	/* To handle board related suspend/resume functionality for MMC */
-	int (*suspend)(struct device *dev, int slot);
-	int (*resume)(struct device *dev, int slot);
+	int (*suspend)(struct device *dev);
+	int (*resume)(struct device *dev);
 
 	/* return MMC cover switch state, can be NULL if not supported.
 	 *
@@ -232,13 +231,13 @@ struct omap_hsmmc_host {
 	 *   0 - closed
 	 *   1 - open
 	 */
-	int (*get_cover_state)(struct device *dev, int slot);
+	int (*get_cover_state)(struct device *dev);
 
 	/* Card detection IRQs */
 	int card_detect_irq;
 
-	int (*card_detect)(struct device *dev, int slot);
-	int (*get_ro)(struct device *dev, int slot);
+	int (*card_detect)(struct device *dev);
+	int (*get_ro)(struct device *dev);
 
 };
 
@@ -249,7 +248,7 @@ struct omap_mmc_of_data {
 
 static void omap_hsmmc_start_dma_transfer(struct omap_hsmmc_host *host);
 
-static int omap_hsmmc_card_detect(struct device *dev, int slot)
+static int omap_hsmmc_card_detect(struct device *dev)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
 	struct omap_hsmmc_platform_data *mmc = host->pdata;
@@ -258,7 +257,7 @@ static int omap_hsmmc_card_detect(struct device *dev, int slot)
 	return !gpio_get_value_cansleep(mmc->switch_pin);
 }
 
-static int omap_hsmmc_get_wp(struct device *dev, int slot)
+static int omap_hsmmc_get_wp(struct device *dev)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
 	struct omap_hsmmc_platform_data *mmc = host->pdata;
@@ -267,7 +266,7 @@ static int omap_hsmmc_get_wp(struct device *dev, int slot)
 	return gpio_get_value_cansleep(mmc->gpio_wp);
 }
 
-static int omap_hsmmc_get_cover_state(struct device *dev, int slot)
+static int omap_hsmmc_get_cover_state(struct device *dev)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
 	struct omap_hsmmc_platform_data *mmc = host->pdata;
@@ -278,7 +277,7 @@ static int omap_hsmmc_get_cover_state(struct device *dev, int slot)
 
 #ifdef CONFIG_PM
 
-static int omap_hsmmc_suspend_cdirq(struct device *dev, int slot)
+static int omap_hsmmc_suspend_cdirq(struct device *dev)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
 
@@ -286,7 +285,7 @@ static int omap_hsmmc_suspend_cdirq(struct device *dev, int slot)
 	return 0;
 }
 
-static int omap_hsmmc_resume_cdirq(struct device *dev, int slot)
+static int omap_hsmmc_resume_cdirq(struct device *dev)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
 
@@ -303,8 +302,7 @@ static int omap_hsmmc_resume_cdirq(struct device *dev, int slot)
 
 #ifdef CONFIG_REGULATOR
 
-static int omap_hsmmc_set_power(struct device *dev, int slot, int power_on,
-				   int vdd)
+static int omap_hsmmc_set_power(struct device *dev, int power_on, int vdd)
 {
 	struct omap_hsmmc_host *host =
 		platform_get_drvdata(to_platform_device(dev));
@@ -318,7 +316,7 @@ static int omap_hsmmc_set_power(struct device *dev, int slot, int power_on,
 		return 0;
 
 	if (mmc_pdata(host)->before_set_reg)
-		mmc_pdata(host)->before_set_reg(dev, slot, power_on, vdd);
+		mmc_pdata(host)->before_set_reg(dev, power_on, vdd);
 
 	if (host->pbias) {
 		if (host->pbias_enabled == 1) {
@@ -381,7 +379,7 @@ static int omap_hsmmc_set_power(struct device *dev, int slot, int power_on,
 	}
 
 	if (mmc_pdata(host)->after_set_reg)
-		mmc_pdata(host)->after_set_reg(dev, slot, power_on, vdd);
+		mmc_pdata(host)->after_set_reg(dev, power_on, vdd);
 
 error_set_power:
 	return ret;
@@ -431,8 +429,8 @@ static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host)
 	    (host->vcc_aux && regulator_is_enabled(host->vcc_aux))) {
 		int vdd = ffs(mmc_pdata(host)->ocr_mask) - 1;
 
-		mmc_pdata(host)->set_power(host->dev, host->slot_id, 1, vdd);
-		mmc_pdata(host)->set_power(host->dev, host->slot_id, 0, 0);
+		mmc_pdata(host)->set_power(host->dev, 1, vdd);
+		mmc_pdata(host)->set_power(host->dev, 0, 0);
 	}
 
 	return 0;
@@ -813,7 +811,7 @@ int omap_hsmmc_cover_is_closed(struct omap_hsmmc_host *host)
 	int r = 1;
 
 	if (host->get_cover_state)
-		r = host->get_cover_state(host->dev, host->slot_id);
+		r = host->get_cover_state(host->dev);
 	return r;
 }
 
@@ -1231,12 +1229,11 @@ static int omap_hsmmc_switch_opcond(struct omap_hsmmc_host *host, int vdd)
 		clk_disable_unprepare(host->dbclk);
 
 	/* Turn the power off */
-	ret = mmc_pdata(host)->set_power(host->dev, host->slot_id, 0, 0);
+	ret = mmc_pdata(host)->set_power(host->dev, 0, 0);
 
 	/* Turn the power ON with given VDD 1.8 or 3.0v */
 	if (!ret)
-		ret = mmc_pdata(host)->set_power(host->dev, host->slot_id, 1,
-						 vdd);
+		ret = mmc_pdata(host)->set_power(host->dev, 1, vdd);
 	pm_runtime_get_sync(host->dev);
 	if (host->dbclk)
 		clk_prepare_enable(host->dbclk);
@@ -1284,7 +1281,7 @@ static void omap_hsmmc_protect_card(struct omap_hsmmc_host *host)
 		return;
 
 	host->reqs_blocked = 0;
-	if (host->get_cover_state(host->dev, host->slot_id)) {
+	if (host->get_cover_state(host->dev)) {
 		if (host->protect_card) {
 			dev_info(host->dev, "%s: cover is closed, "
 					 "card is now accessible\n",
@@ -1312,7 +1309,7 @@ static irqreturn_t omap_hsmmc_detect(int irq, void *dev_id)
 	sysfs_notify(&host->mmc->class_dev.kobj, NULL, "cover_switch");
 
 	if (host->card_detect)
-		carddetect = host->card_detect(host->dev, host->slot_id);
+		carddetect = host->card_detect(host->dev);
 	else {
 		omap_hsmmc_protect_card(host);
 		carddetect = -ENOSYS;
@@ -1638,12 +1635,10 @@ static void omap_hsmmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	if (ios->power_mode != host->power_mode) {
 		switch (ios->power_mode) {
 		case MMC_POWER_OFF:
-			mmc_pdata(host)->set_power(host->dev, host->slot_id,
-						   0, 0);
+			mmc_pdata(host)->set_power(host->dev, 0, 0);
 			break;
 		case MMC_POWER_UP:
-			mmc_pdata(host)->set_power(host->dev, host->slot_id,
-						   1, ios->vdd);
+			mmc_pdata(host)->set_power(host->dev, 1, ios->vdd);
 			break;
 		case MMC_POWER_ON:
 			do_send_init_stream = 1;
@@ -1690,7 +1685,7 @@ static int omap_hsmmc_get_cd(struct mmc_host *mmc)
 
 	if (!host->card_detect)
 		return -ENOSYS;
-	return host->card_detect(host->dev, host->slot_id);
+	return host->card_detect(host->dev);
 }
 
 static int omap_hsmmc_get_ro(struct mmc_host *mmc)
@@ -1699,7 +1694,7 @@ static int omap_hsmmc_get_ro(struct mmc_host *mmc)
 
 	if (!host->get_ro)
 		return -ENOSYS;
-	return host->get_ro(host->dev, 0);
+	return host->get_ro(host->dev);
 }
 
 static void omap_hsmmc_init_card(struct mmc_host *mmc, struct mmc_card *card)
@@ -1996,8 +1991,6 @@ static struct omap_hsmmc_platform_data *of_get_hsmmc_pdata(struct device *dev)
 	if (of_find_property(np, "ti,dual-volt", NULL))
 		pdata->controller_flags |= OMAP_HSMMC_SUPPORTS_DUAL_VOLT;
 
-	/* This driver only supports 1 slot */
-	pdata->nr_slots = 1;
 	pdata->switch_pin = cd_gpio;
 	pdata->gpio_wp = wp_gpio;
 
@@ -2068,11 +2061,6 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	if (pdata->nr_slots == 0) {
-		dev_err(&pdev->dev, "No Slots\n");
-		return -ENXIO;
-	}
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq = platform_get_irq(pdev, 0);
 	if (res == NULL || irq < 0)
@@ -2095,7 +2083,6 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 	host->use_dma	= 1;
 	host->dma_ch	= -1;
 	host->irq	= irq;
-	host->slot_id	= 0;
 	host->mapbase	= res->start + pdata->reg_offset;
 	host->base	= base + pdata->reg_offset;
 	host->power_mode = MMC_POWER_OFF;
@@ -2338,7 +2325,7 @@ static int omap_hsmmc_prepare(struct device *dev)
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
 
 	if (host->suspend)
-		return host->suspend(dev, host->slot_id);
+		return host->suspend(dev);
 
 	return 0;
 }
@@ -2348,7 +2335,7 @@ static void omap_hsmmc_complete(struct device *dev)
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
 
 	if (host->resume)
-		host->resume(dev, host->slot_id);
+		host->resume(dev);
 
 }
 
diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h
index 68ffec14b56..67bbcf0785f 100644
--- a/include/linux/platform_data/hsmmc-omap.h
+++ b/include/linux/platform_data/hsmmc-omap.h
@@ -38,9 +38,6 @@ struct omap_hsmmc_platform_data {
 	/* back-link to device */
 	struct device *dev;
 
-	/* number of slots per controller */
-	unsigned nr_slots:2;
-
 	/* set if your board has components or wiring that limits the
 	 * maximum frequency on the MMC bus */
 	unsigned int max_freq;
@@ -79,15 +76,12 @@ struct omap_hsmmc_platform_data {
 	int switch_pin;			/* gpio (card detect) */
 	int gpio_wp;			/* gpio (write protect) */
 
-	int (*set_power)(struct device *dev, int slot,
-			 int power_on, int vdd);
-	void (*remux)(struct device *dev, int slot, int power_on);
+	int (*set_power)(struct device *dev, int power_on, int vdd);
+	void (*remux)(struct device *dev, int power_on);
 	/* Call back before enabling / disabling regulators */
-	void (*before_set_reg)(struct device *dev, int slot,
-			       int power_on, int vdd);
+	void (*before_set_reg)(struct device *dev, int power_on, int vdd);
 	/* Call back after enabling / disabling regulators */
-	void (*after_set_reg)(struct device *dev, int slot,
-			      int power_on, int vdd);
+	void (*after_set_reg)(struct device *dev, int power_on, int vdd);
 	/* if we have special card, init it using this callback */
 	void (*init_card)(struct mmc_card *card);
 
-- 
cgit v1.2.3-70-g09d2


From 767562348b72cb2612f5991ad35a5c0448254939 Mon Sep 17 00:00:00 2001
From: Addy Ke <addy.ke@rock-chips.com>
Date: Tue, 4 Nov 2014 22:03:09 +0800
Subject: mmc: dw_mmc: add support for the other bit of sdio interrupt

The bit of sdio interrupt is 16 in designware implementation,
but it is 24 on Rockchip SoCs.This patch add sdio_id0 for the
number of slot0 in the SDIO interrupt registers.

Signed-off-by: Addy Ke <addy.ke@rock-chips.com>
Reviewed-by: Doug Anderson <dianders@chromium.org>
Acked-by: Jaehoon Chung <jh80.chung@samsung.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/dw_mmc-rockchip.c | 10 ++++++++++
 drivers/mmc/host/dw_mmc.c          | 12 +++++++-----
 drivers/mmc/host/dw_mmc.h          |  2 ++
 include/linux/mmc/dw_mmc.h         |  3 +++
 4 files changed, 22 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
index bbb4ec386e5..5650ac488cf 100644
--- a/drivers/mmc/host/dw_mmc-rockchip.c
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -68,14 +68,24 @@ static void dw_mci_rk3288_set_ios(struct dw_mci *host, struct mmc_ios *ios)
 	}
 }
 
+static int dw_mci_rockchip_init(struct dw_mci *host)
+{
+	/* It is slot 8 on Rockchip SoCs */
+	host->sdio_id0 = 8;
+
+	return 0;
+}
+
 static const struct dw_mci_drv_data rk2928_drv_data = {
 	.prepare_command        = dw_mci_rockchip_prepare_command,
+	.init			= dw_mci_rockchip_init,
 };
 
 static const struct dw_mci_drv_data rk3288_drv_data = {
 	.prepare_command        = dw_mci_rockchip_prepare_command,
 	.set_ios		= dw_mci_rk3288_set_ios,
 	.setup_clock    = dw_mci_rk3288_setup_clock,
+	.init			= dw_mci_rockchip_init,
 };
 
 static const struct of_device_id dw_mci_rockchip_match[] = {
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 5a37c33879a..b4c30448566 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -919,7 +919,7 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot, bool force_clkinit)
 
 		/* enable clock; only low power if no SDIO */
 		clk_en_a = SDMMC_CLKEN_ENABLE << slot->id;
-		if (!(mci_readl(host, INTMASK) & SDMMC_INT_SDIO(slot->id)))
+		if (!(mci_readl(host, INTMASK) & SDMMC_INT_SDIO(slot->sdio_id)))
 			clk_en_a |= SDMMC_CLKEN_LOW_PWR << slot->id;
 		mci_writel(host, CLKENA, clk_en_a);
 
@@ -1280,10 +1280,10 @@ static void dw_mci_enable_sdio_irq(struct mmc_host *mmc, int enb)
 		dw_mci_disable_low_power(slot);
 
 		mci_writel(host, INTMASK,
-			   (int_mask | SDMMC_INT_SDIO(slot->id)));
+			   (int_mask | SDMMC_INT_SDIO(slot->sdio_id)));
 	} else {
 		mci_writel(host, INTMASK,
-			   (int_mask & ~SDMMC_INT_SDIO(slot->id)));
+			   (int_mask & ~SDMMC_INT_SDIO(slot->sdio_id)));
 	}
 }
 
@@ -2152,8 +2152,9 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 		/* Handle SDIO Interrupts */
 		for (i = 0; i < host->num_slots; i++) {
 			struct dw_mci_slot *slot = host->slot[i];
-			if (pending & SDMMC_INT_SDIO(i)) {
-				mci_writel(host, RINTSTS, SDMMC_INT_SDIO(i));
+			if (pending & SDMMC_INT_SDIO(slot->sdio_id)) {
+				mci_writel(host, RINTSTS,
+					   SDMMC_INT_SDIO(slot->sdio_id));
 				mmc_signal_sdio_irq(slot->mmc);
 			}
 		}
@@ -2252,6 +2253,7 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 
 	slot = mmc_priv(mmc);
 	slot->id = id;
+	slot->sdio_id = host->sdio_id0 + id;
 	slot->mmc = mmc;
 	slot->host = host;
 	host->slot[id] = slot;
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index 58d8a54d644..0d0f7a271d6 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -225,6 +225,7 @@ extern int dw_mci_resume(struct dw_mci *host);
  *	with CONFIG_MMC_CLKGATE.
  * @flags: Random state bits associated with the slot.
  * @id: Number of this slot.
+ * @sdio_id: Number of this slot in the SDIO interrupt registers.
  */
 struct dw_mci_slot {
 	struct mmc_host		*mmc;
@@ -244,6 +245,7 @@ struct dw_mci_slot {
 #define DW_MMC_CARD_PRESENT	0
 #define DW_MMC_CARD_NEED_INIT	1
 	int			id;
+	int			sdio_id;
 };
 
 struct dw_mci_tuning_data {
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index 0a551152d60..42b724e8d50 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -97,6 +97,7 @@ struct mmc_data;
  * @quirks: Set of quirks that apply to specific versions of the IP.
  * @irq_flags: The flags to be passed to request_irq.
  * @irq: The irq value to be passed to request_irq.
+ * @sdio_id0: Number of slot0 in the SDIO interrupt registers.
  *
  * Locking
  * =======
@@ -193,6 +194,8 @@ struct dw_mci {
 	bool			vqmmc_enabled;
 	unsigned long		irq_flags; /* IRQ flags */
 	int			irq;
+
+	int			sdio_id0;
 };
 
 /* DMA ops for Internal/External DMAC interface */
-- 
cgit v1.2.3-70-g09d2


From 996903de92f0c7a32d8c83f37d7ebcea0def8660 Mon Sep 17 00:00:00 2001
From: Minda Chen <Minda.Chen@csr.com>
Date: Wed, 26 Nov 2014 13:05:33 +0800
Subject: mmc: core: add core-level function for sending tuning commands

According to the SD card spec, Add a manual tuning command function
for SDR104/HS200.
Sending command 19 or command 21 to read data and compare with the
tunning block pattern.

This patch will help to decrease some platform private codes in SDHCI
platform_execute_tuning() callbacks.

Signed-off-by: Minda Chen <Minda.Chen@csr.com>
Signed-off-by: Barry Song <Baohua.Song@csr.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/mmc_ops.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mmc/core.h   |  1 +
 2 files changed, 71 insertions(+)

(limited to 'include')

diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 23aa3a380f2..12b2a32df34 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -547,6 +547,76 @@ int mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 }
 EXPORT_SYMBOL_GPL(mmc_switch);
 
+int mmc_send_tuning(struct mmc_card *card)
+{
+	struct mmc_request mrq = {NULL};
+	struct mmc_command cmd = {0};
+	struct mmc_data data = {0};
+	struct scatterlist sg;
+	struct mmc_host *mmc = card->host;
+	struct mmc_ios *ios = &mmc->ios;
+	const u8 *tuning_block_pattern;
+	int size, err = 0;
+	u8 *data_buf;
+	u32 opcode;
+
+	if (ios->bus_width == MMC_BUS_WIDTH_8) {
+		tuning_block_pattern = tuning_blk_pattern_8bit;
+		size = sizeof(tuning_blk_pattern_8bit);
+		opcode = MMC_SEND_TUNING_BLOCK_HS200;
+	} else if (ios->bus_width == MMC_BUS_WIDTH_4) {
+		tuning_block_pattern = tuning_blk_pattern_4bit;
+		size = sizeof(tuning_blk_pattern_4bit);
+		opcode = MMC_SEND_TUNING_BLOCK;
+	} else
+		return -EINVAL;
+
+	data_buf = kzalloc(size, GFP_KERNEL);
+	if (!data_buf)
+		return -ENOMEM;
+
+	mrq.cmd = &cmd;
+	mrq.data = &data;
+
+	cmd.opcode = opcode;
+	cmd.flags = MMC_RSP_R1 | MMC_CMD_ADTC;
+
+	data.blksz = size;
+	data.blocks = 1;
+	data.flags = MMC_DATA_READ;
+
+	/*
+	 * According to the tuning specs, Tuning process
+	 * is normally shorter 40 executions of CMD19,
+	 * and timeout value should be shorter than 150 ms
+	 */
+	data.timeout_ns = 150 * NSEC_PER_MSEC;
+
+	data.sg = &sg;
+	data.sg_len = 1;
+	sg_init_one(&sg, data_buf, size);
+
+	mmc_wait_for_req(mmc, &mrq);
+
+	if (cmd.error) {
+		err = cmd.error;
+		goto out;
+	}
+
+	if (data.error) {
+		err = data.error;
+		goto out;
+	}
+
+	if (memcmp(data_buf, tuning_block_pattern, size))
+		err = -EIO;
+
+out:
+	kfree(data_buf);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mmc_send_tuning);
+
 static int
 mmc_send_bus_test(struct mmc_card *card, struct mmc_host *host, u8 opcode,
 		  u8 len)
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index b11e43c1063..c4bdaa12869 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -154,6 +154,7 @@ extern void mmc_start_bkops(struct mmc_card *card, bool from_exception);
 extern int __mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int, bool,
 			bool, bool);
 extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int);
+extern int mmc_send_tuning(struct mmc_card *card);
 extern int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd);
 
 #define MMC_ERASE_ARG		0x00000000
-- 
cgit v1.2.3-70-g09d2


From f5c1434c217fd72ac0d24d3142d09e49a3d4e72e Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Mon, 24 Nov 2014 14:35:10 +0000
Subject: irqchip: GICv3: rework redistributor structure

The basic GICv3 driver has almost no use for the redistributor
(other than the basic per-CPU interrupts), but the ITS needs
a lot more from them.

As such, rework the set of data structures. The behaviour of the
GICv3 driver is otherwise unaffected.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Link: https://lkml.kernel.org/r/1416839720-18400-4-git-send-email-marc.zyngier@arm.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
---
 drivers/irqchip/irq-gic-v3.c       | 73 +++++++++++++++++++++++---------------
 include/linux/irqchip/arm-gic-v3.h | 15 ++++++++
 2 files changed, 59 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 4cb355aff3c..43e57da0d80 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -34,20 +34,25 @@
 #include "irq-gic-common.h"
 #include "irqchip.h"
 
+struct redist_region {
+	void __iomem		*redist_base;
+	phys_addr_t		phys_base;
+};
+
 struct gic_chip_data {
 	void __iomem		*dist_base;
-	void __iomem		**redist_base;
-	void __iomem * __percpu	*rdist;
+	struct redist_region	*redist_regions;
+	struct rdists		rdists;
 	struct irq_domain	*domain;
 	u64			redist_stride;
-	u32			redist_regions;
+	u32			nr_redist_regions;
 	unsigned int		irq_nr;
 };
 
 static struct gic_chip_data gic_data __read_mostly;
 
-#define gic_data_rdist()		(this_cpu_ptr(gic_data.rdist))
-#define gic_data_rdist_rd_base()	(*gic_data_rdist())
+#define gic_data_rdist()		(this_cpu_ptr(gic_data.rdists.rdist))
+#define gic_data_rdist_rd_base()	(gic_data_rdist()->rd_base)
 #define gic_data_rdist_sgi_base()	(gic_data_rdist_rd_base() + SZ_64K)
 
 /* Our default, arbitrary priority value. Linux only uses one anyway. */
@@ -333,8 +338,8 @@ static int gic_populate_rdist(void)
 	       MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 |
 	       MPIDR_AFFINITY_LEVEL(mpidr, 0));
 
-	for (i = 0; i < gic_data.redist_regions; i++) {
-		void __iomem *ptr = gic_data.redist_base[i];
+	for (i = 0; i < gic_data.nr_redist_regions; i++) {
+		void __iomem *ptr = gic_data.redist_regions[i].redist_base;
 		u32 reg;
 
 		reg = readl_relaxed(ptr + GICR_PIDR2) & GIC_PIDR2_ARCH_MASK;
@@ -347,10 +352,13 @@ static int gic_populate_rdist(void)
 		do {
 			typer = readq_relaxed(ptr + GICR_TYPER);
 			if ((typer >> 32) == aff) {
+				u64 offset = ptr - gic_data.redist_regions[i].redist_base;
 				gic_data_rdist_rd_base() = ptr;
-				pr_info("CPU%d: found redistributor %llx @%p\n",
+				gic_data_rdist()->phys_base = gic_data.redist_regions[i].phys_base + offset;
+				pr_info("CPU%d: found redistributor %llx region %d:%pa\n",
 					smp_processor_id(),
-					(unsigned long long)mpidr, ptr);
+					(unsigned long long)mpidr,
+					i, &gic_data_rdist()->phys_base);
 				return 0;
 			}
 
@@ -673,9 +681,10 @@ static const struct irq_domain_ops gic_irq_domain_ops = {
 static int __init gic_of_init(struct device_node *node, struct device_node *parent)
 {
 	void __iomem *dist_base;
-	void __iomem **redist_base;
+	struct redist_region *rdist_regs;
 	u64 redist_stride;
-	u32 redist_regions;
+	u32 nr_redist_regions;
+	u32 typer;
 	u32 reg;
 	int gic_irqs;
 	int err;
@@ -696,48 +705,54 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare
 		goto out_unmap_dist;
 	}
 
-	if (of_property_read_u32(node, "#redistributor-regions", &redist_regions))
-		redist_regions = 1;
+	if (of_property_read_u32(node, "#redistributor-regions", &nr_redist_regions))
+		nr_redist_regions = 1;
 
-	redist_base = kzalloc(sizeof(*redist_base) * redist_regions, GFP_KERNEL);
-	if (!redist_base) {
+	rdist_regs = kzalloc(sizeof(*rdist_regs) * nr_redist_regions, GFP_KERNEL);
+	if (!rdist_regs) {
 		err = -ENOMEM;
 		goto out_unmap_dist;
 	}
 
-	for (i = 0; i < redist_regions; i++) {
-		redist_base[i] = of_iomap(node, 1 + i);
-		if (!redist_base[i]) {
+	for (i = 0; i < nr_redist_regions; i++) {
+		struct resource res;
+		int ret;
+
+		ret = of_address_to_resource(node, 1 + i, &res);
+		rdist_regs[i].redist_base = of_iomap(node, 1 + i);
+		if (ret || !rdist_regs[i].redist_base) {
 			pr_err("%s: couldn't map region %d\n",
 			       node->full_name, i);
 			err = -ENODEV;
 			goto out_unmap_rdist;
 		}
+		rdist_regs[i].phys_base = res.start;
 	}
 
 	if (of_property_read_u64(node, "redistributor-stride", &redist_stride))
 		redist_stride = 0;
 
 	gic_data.dist_base = dist_base;
-	gic_data.redist_base = redist_base;
-	gic_data.redist_regions = redist_regions;
+	gic_data.redist_regions = rdist_regs;
+	gic_data.nr_redist_regions = nr_redist_regions;
 	gic_data.redist_stride = redist_stride;
 
 	/*
 	 * Find out how many interrupts are supported.
 	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
 	 */
-	gic_irqs = readl_relaxed(gic_data.dist_base + GICD_TYPER) & 0x1f;
-	gic_irqs = (gic_irqs + 1) * 32;
+	typer = readl_relaxed(gic_data.dist_base + GICD_TYPER);
+	gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer);
+	gic_irqs = GICD_TYPER_IRQS(typer);
 	if (gic_irqs > 1020)
 		gic_irqs = 1020;
 	gic_data.irq_nr = gic_irqs;
 
 	gic_data.domain = irq_domain_add_tree(node, &gic_irq_domain_ops,
 					      &gic_data);
-	gic_data.rdist = alloc_percpu(typeof(*gic_data.rdist));
+	gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist));
 
-	if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdist)) {
+	if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) {
 		err = -ENOMEM;
 		goto out_free;
 	}
@@ -754,12 +769,12 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare
 out_free:
 	if (gic_data.domain)
 		irq_domain_remove(gic_data.domain);
-	free_percpu(gic_data.rdist);
+	free_percpu(gic_data.rdists.rdist);
 out_unmap_rdist:
-	for (i = 0; i < redist_regions; i++)
-		if (redist_base[i])
-			iounmap(redist_base[i]);
-	kfree(redist_base);
+	for (i = 0; i < nr_redist_regions; i++)
+		if (rdist_regs[i].redist_base)
+			iounmap(rdist_regs[i].redist_base);
+	kfree(rdist_regs);
 out_unmap_dist:
 	iounmap(dist_base);
 	return err;
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 03a4ea37ba8..040615a48bf 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -49,6 +49,10 @@
 #define GICD_CTLR_ENABLE_G1A		(1U << 1)
 #define GICD_CTLR_ENABLE_G1		(1U << 0)
 
+#define GICD_TYPER_ID_BITS(typer)	((((typer) >> 19) & 0x1f) + 1)
+#define GICD_TYPER_IRQS(typer)		((((typer) & 0x1f) + 1) * 32)
+#define GICD_TYPER_LPIS			(1U << 17)
+
 #define GICD_IROUTER_SPI_MODE_ONE	(0U << 31)
 #define GICD_IROUTER_SPI_MODE_ANY	(1U << 31)
 
@@ -189,6 +193,17 @@
 
 #include <linux/stringify.h>
 
+struct rdists {
+	struct {
+		void __iomem	*rd_base;
+		struct page	*pend_page;
+		phys_addr_t	phys_base;
+	} __percpu		*rdist;
+	struct page		*prop_page;
+	int			id_bits;
+	u64			flags;
+};
+
 static inline void gic_write_eoir(u64 irq)
 {
 	asm volatile("msr_s " __stringify(ICC_EOIR1_EL1) ", %0" : : "r" (irq));
-- 
cgit v1.2.3-70-g09d2


From cc2d3216f53c9fff0030eb71cacc4ce5f39d1d7e Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Mon, 24 Nov 2014 14:35:11 +0000
Subject: irqchip: GICv3: ITS command queue

The ITS is configured through a number commands that the driver
issues to the HW using a memory-based circular buffer.

This patch implements the subset of commands that are required
for Linux.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Link: https://lkml.kernel.org/r/1416839720-18400-5-git-send-email-marc.zyngier@arm.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
---
 drivers/irqchip/irq-gic-v3-its.c   | 511 +++++++++++++++++++++++++++++++++++++
 include/linux/irqchip/arm-gic-v3.h | 102 ++++++++
 2 files changed, 613 insertions(+)
 create mode 100644 drivers/irqchip/irq-gic-v3-its.c

(limited to 'include')

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
new file mode 100644
index 00000000000..a5ab12c7d7f
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -0,0 +1,511 @@
+/*
+ * Copyright (C) 2013, 2014 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/bitmap.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/log2.h>
+#include <linux/mm.h>
+#include <linux/msi.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_pci.h>
+#include <linux/of_platform.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/exception.h>
+
+#include "irqchip.h"
+
+#define ITS_FLAGS_CMDQ_NEEDS_FLUSHING		(1 << 0)
+
+/*
+ * Collection structure - just an ID, and a redistributor address to
+ * ping. We use one per CPU as a bag of interrupts assigned to this
+ * CPU.
+ */
+struct its_collection {
+	u64			target_address;
+	u16			col_id;
+};
+
+/*
+ * The ITS structure - contains most of the infrastructure, with the
+ * msi_controller, the command queue, the collections, and the list of
+ * devices writing to it.
+ */
+struct its_node {
+	raw_spinlock_t		lock;
+	struct list_head	entry;
+	struct msi_controller	msi_chip;
+	struct irq_domain	*domain;
+	void __iomem		*base;
+	unsigned long		phys_base;
+	struct its_cmd_block	*cmd_base;
+	struct its_cmd_block	*cmd_write;
+	void			*tables[GITS_BASER_NR_REGS];
+	struct its_collection	*collections;
+	struct list_head	its_device_list;
+	u64			flags;
+	u32			ite_size;
+};
+
+#define ITS_ITT_ALIGN		SZ_256
+
+/*
+ * The ITS view of a device - belongs to an ITS, a collection, owns an
+ * interrupt translation table, and a list of interrupts.
+ */
+struct its_device {
+	struct list_head	entry;
+	struct its_node		*its;
+	struct its_collection	*collection;
+	void			*itt;
+	unsigned long		*lpi_map;
+	irq_hw_number_t		lpi_base;
+	int			nr_lpis;
+	u32			nr_ites;
+	u32			device_id;
+};
+
+/*
+ * ITS command descriptors - parameters to be encoded in a command
+ * block.
+ */
+struct its_cmd_desc {
+	union {
+		struct {
+			struct its_device *dev;
+			u32 event_id;
+		} its_inv_cmd;
+
+		struct {
+			struct its_device *dev;
+			u32 event_id;
+		} its_int_cmd;
+
+		struct {
+			struct its_device *dev;
+			int valid;
+		} its_mapd_cmd;
+
+		struct {
+			struct its_collection *col;
+			int valid;
+		} its_mapc_cmd;
+
+		struct {
+			struct its_device *dev;
+			u32 phys_id;
+			u32 event_id;
+		} its_mapvi_cmd;
+
+		struct {
+			struct its_device *dev;
+			struct its_collection *col;
+			u32 id;
+		} its_movi_cmd;
+
+		struct {
+			struct its_device *dev;
+			u32 event_id;
+		} its_discard_cmd;
+
+		struct {
+			struct its_collection *col;
+		} its_invall_cmd;
+	};
+};
+
+/*
+ * The ITS command block, which is what the ITS actually parses.
+ */
+struct its_cmd_block {
+	u64	raw_cmd[4];
+};
+
+#define ITS_CMD_QUEUE_SZ		SZ_64K
+#define ITS_CMD_QUEUE_NR_ENTRIES	(ITS_CMD_QUEUE_SZ / sizeof(struct its_cmd_block))
+
+typedef struct its_collection *(*its_cmd_builder_t)(struct its_cmd_block *,
+						    struct its_cmd_desc *);
+
+static void its_encode_cmd(struct its_cmd_block *cmd, u8 cmd_nr)
+{
+	cmd->raw_cmd[0] &= ~0xffUL;
+	cmd->raw_cmd[0] |= cmd_nr;
+}
+
+static void its_encode_devid(struct its_cmd_block *cmd, u32 devid)
+{
+	cmd->raw_cmd[0] &= ~(0xffffUL << 32);
+	cmd->raw_cmd[0] |= ((u64)devid) << 32;
+}
+
+static void its_encode_event_id(struct its_cmd_block *cmd, u32 id)
+{
+	cmd->raw_cmd[1] &= ~0xffffffffUL;
+	cmd->raw_cmd[1] |= id;
+}
+
+static void its_encode_phys_id(struct its_cmd_block *cmd, u32 phys_id)
+{
+	cmd->raw_cmd[1] &= 0xffffffffUL;
+	cmd->raw_cmd[1] |= ((u64)phys_id) << 32;
+}
+
+static void its_encode_size(struct its_cmd_block *cmd, u8 size)
+{
+	cmd->raw_cmd[1] &= ~0x1fUL;
+	cmd->raw_cmd[1] |= size & 0x1f;
+}
+
+static void its_encode_itt(struct its_cmd_block *cmd, u64 itt_addr)
+{
+	cmd->raw_cmd[2] &= ~0xffffffffffffUL;
+	cmd->raw_cmd[2] |= itt_addr & 0xffffffffff00UL;
+}
+
+static void its_encode_valid(struct its_cmd_block *cmd, int valid)
+{
+	cmd->raw_cmd[2] &= ~(1UL << 63);
+	cmd->raw_cmd[2] |= ((u64)!!valid) << 63;
+}
+
+static void its_encode_target(struct its_cmd_block *cmd, u64 target_addr)
+{
+	cmd->raw_cmd[2] &= ~(0xffffffffUL << 16);
+	cmd->raw_cmd[2] |= (target_addr & (0xffffffffUL << 16));
+}
+
+static void its_encode_collection(struct its_cmd_block *cmd, u16 col)
+{
+	cmd->raw_cmd[2] &= ~0xffffUL;
+	cmd->raw_cmd[2] |= col;
+}
+
+static inline void its_fixup_cmd(struct its_cmd_block *cmd)
+{
+	/* Let's fixup BE commands */
+	cmd->raw_cmd[0] = cpu_to_le64(cmd->raw_cmd[0]);
+	cmd->raw_cmd[1] = cpu_to_le64(cmd->raw_cmd[1]);
+	cmd->raw_cmd[2] = cpu_to_le64(cmd->raw_cmd[2]);
+	cmd->raw_cmd[3] = cpu_to_le64(cmd->raw_cmd[3]);
+}
+
+static struct its_collection *its_build_mapd_cmd(struct its_cmd_block *cmd,
+						 struct its_cmd_desc *desc)
+{
+	unsigned long itt_addr;
+	u8 size = order_base_2(desc->its_mapd_cmd.dev->nr_ites);
+
+	itt_addr = virt_to_phys(desc->its_mapd_cmd.dev->itt);
+	itt_addr = ALIGN(itt_addr, ITS_ITT_ALIGN);
+
+	its_encode_cmd(cmd, GITS_CMD_MAPD);
+	its_encode_devid(cmd, desc->its_mapd_cmd.dev->device_id);
+	its_encode_size(cmd, size - 1);
+	its_encode_itt(cmd, itt_addr);
+	its_encode_valid(cmd, desc->its_mapd_cmd.valid);
+
+	its_fixup_cmd(cmd);
+
+	return desc->its_mapd_cmd.dev->collection;
+}
+
+static struct its_collection *its_build_mapc_cmd(struct its_cmd_block *cmd,
+						 struct its_cmd_desc *desc)
+{
+	its_encode_cmd(cmd, GITS_CMD_MAPC);
+	its_encode_collection(cmd, desc->its_mapc_cmd.col->col_id);
+	its_encode_target(cmd, desc->its_mapc_cmd.col->target_address);
+	its_encode_valid(cmd, desc->its_mapc_cmd.valid);
+
+	its_fixup_cmd(cmd);
+
+	return desc->its_mapc_cmd.col;
+}
+
+static struct its_collection *its_build_mapvi_cmd(struct its_cmd_block *cmd,
+						  struct its_cmd_desc *desc)
+{
+	its_encode_cmd(cmd, GITS_CMD_MAPVI);
+	its_encode_devid(cmd, desc->its_mapvi_cmd.dev->device_id);
+	its_encode_event_id(cmd, desc->its_mapvi_cmd.event_id);
+	its_encode_phys_id(cmd, desc->its_mapvi_cmd.phys_id);
+	its_encode_collection(cmd, desc->its_mapvi_cmd.dev->collection->col_id);
+
+	its_fixup_cmd(cmd);
+
+	return desc->its_mapvi_cmd.dev->collection;
+}
+
+static struct its_collection *its_build_movi_cmd(struct its_cmd_block *cmd,
+						 struct its_cmd_desc *desc)
+{
+	its_encode_cmd(cmd, GITS_CMD_MOVI);
+	its_encode_devid(cmd, desc->its_movi_cmd.dev->device_id);
+	its_encode_event_id(cmd, desc->its_movi_cmd.id);
+	its_encode_collection(cmd, desc->its_movi_cmd.col->col_id);
+
+	its_fixup_cmd(cmd);
+
+	return desc->its_movi_cmd.dev->collection;
+}
+
+static struct its_collection *its_build_discard_cmd(struct its_cmd_block *cmd,
+						    struct its_cmd_desc *desc)
+{
+	its_encode_cmd(cmd, GITS_CMD_DISCARD);
+	its_encode_devid(cmd, desc->its_discard_cmd.dev->device_id);
+	its_encode_event_id(cmd, desc->its_discard_cmd.event_id);
+
+	its_fixup_cmd(cmd);
+
+	return desc->its_discard_cmd.dev->collection;
+}
+
+static struct its_collection *its_build_inv_cmd(struct its_cmd_block *cmd,
+						struct its_cmd_desc *desc)
+{
+	its_encode_cmd(cmd, GITS_CMD_INV);
+	its_encode_devid(cmd, desc->its_inv_cmd.dev->device_id);
+	its_encode_event_id(cmd, desc->its_inv_cmd.event_id);
+
+	its_fixup_cmd(cmd);
+
+	return desc->its_inv_cmd.dev->collection;
+}
+
+static struct its_collection *its_build_invall_cmd(struct its_cmd_block *cmd,
+						   struct its_cmd_desc *desc)
+{
+	its_encode_cmd(cmd, GITS_CMD_INVALL);
+	its_encode_collection(cmd, desc->its_mapc_cmd.col->col_id);
+
+	its_fixup_cmd(cmd);
+
+	return NULL;
+}
+
+static u64 its_cmd_ptr_to_offset(struct its_node *its,
+				 struct its_cmd_block *ptr)
+{
+	return (ptr - its->cmd_base) * sizeof(*ptr);
+}
+
+static int its_queue_full(struct its_node *its)
+{
+	int widx;
+	int ridx;
+
+	widx = its->cmd_write - its->cmd_base;
+	ridx = readl_relaxed(its->base + GITS_CREADR) / sizeof(struct its_cmd_block);
+
+	/* This is incredibly unlikely to happen, unless the ITS locks up. */
+	if (((widx + 1) % ITS_CMD_QUEUE_NR_ENTRIES) == ridx)
+		return 1;
+
+	return 0;
+}
+
+static struct its_cmd_block *its_allocate_entry(struct its_node *its)
+{
+	struct its_cmd_block *cmd;
+	u32 count = 1000000;	/* 1s! */
+
+	while (its_queue_full(its)) {
+		count--;
+		if (!count) {
+			pr_err_ratelimited("ITS queue not draining\n");
+			return NULL;
+		}
+		cpu_relax();
+		udelay(1);
+	}
+
+	cmd = its->cmd_write++;
+
+	/* Handle queue wrapping */
+	if (its->cmd_write == (its->cmd_base + ITS_CMD_QUEUE_NR_ENTRIES))
+		its->cmd_write = its->cmd_base;
+
+	return cmd;
+}
+
+static struct its_cmd_block *its_post_commands(struct its_node *its)
+{
+	u64 wr = its_cmd_ptr_to_offset(its, its->cmd_write);
+
+	writel_relaxed(wr, its->base + GITS_CWRITER);
+
+	return its->cmd_write;
+}
+
+static void its_flush_cmd(struct its_node *its, struct its_cmd_block *cmd)
+{
+	/*
+	 * Make sure the commands written to memory are observable by
+	 * the ITS.
+	 */
+	if (its->flags & ITS_FLAGS_CMDQ_NEEDS_FLUSHING)
+		__flush_dcache_area(cmd, sizeof(*cmd));
+	else
+		dsb(ishst);
+}
+
+static void its_wait_for_range_completion(struct its_node *its,
+					  struct its_cmd_block *from,
+					  struct its_cmd_block *to)
+{
+	u64 rd_idx, from_idx, to_idx;
+	u32 count = 1000000;	/* 1s! */
+
+	from_idx = its_cmd_ptr_to_offset(its, from);
+	to_idx = its_cmd_ptr_to_offset(its, to);
+
+	while (1) {
+		rd_idx = readl_relaxed(its->base + GITS_CREADR);
+		if (rd_idx >= to_idx || rd_idx < from_idx)
+			break;
+
+		count--;
+		if (!count) {
+			pr_err_ratelimited("ITS queue timeout\n");
+			return;
+		}
+		cpu_relax();
+		udelay(1);
+	}
+}
+
+static void its_send_single_command(struct its_node *its,
+				    its_cmd_builder_t builder,
+				    struct its_cmd_desc *desc)
+{
+	struct its_cmd_block *cmd, *sync_cmd, *next_cmd;
+	struct its_collection *sync_col;
+
+	raw_spin_lock(&its->lock);
+
+	cmd = its_allocate_entry(its);
+	if (!cmd) {		/* We're soooooo screewed... */
+		pr_err_ratelimited("ITS can't allocate, dropping command\n");
+		raw_spin_unlock(&its->lock);
+		return;
+	}
+	sync_col = builder(cmd, desc);
+	its_flush_cmd(its, cmd);
+
+	if (sync_col) {
+		sync_cmd = its_allocate_entry(its);
+		if (!sync_cmd) {
+			pr_err_ratelimited("ITS can't SYNC, skipping\n");
+			goto post;
+		}
+		its_encode_cmd(sync_cmd, GITS_CMD_SYNC);
+		its_encode_target(sync_cmd, sync_col->target_address);
+		its_fixup_cmd(sync_cmd);
+		its_flush_cmd(its, sync_cmd);
+	}
+
+post:
+	next_cmd = its_post_commands(its);
+	raw_spin_unlock(&its->lock);
+
+	its_wait_for_range_completion(its, cmd, next_cmd);
+}
+
+static void its_send_inv(struct its_device *dev, u32 event_id)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_inv_cmd.dev = dev;
+	desc.its_inv_cmd.event_id = event_id;
+
+	its_send_single_command(dev->its, its_build_inv_cmd, &desc);
+}
+
+static void its_send_mapd(struct its_device *dev, int valid)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_mapd_cmd.dev = dev;
+	desc.its_mapd_cmd.valid = !!valid;
+
+	its_send_single_command(dev->its, its_build_mapd_cmd, &desc);
+}
+
+static void its_send_mapc(struct its_node *its, struct its_collection *col,
+			  int valid)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_mapc_cmd.col = col;
+	desc.its_mapc_cmd.valid = !!valid;
+
+	its_send_single_command(its, its_build_mapc_cmd, &desc);
+}
+
+static void its_send_mapvi(struct its_device *dev, u32 irq_id, u32 id)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_mapvi_cmd.dev = dev;
+	desc.its_mapvi_cmd.phys_id = irq_id;
+	desc.its_mapvi_cmd.event_id = id;
+
+	its_send_single_command(dev->its, its_build_mapvi_cmd, &desc);
+}
+
+static void its_send_movi(struct its_device *dev,
+			  struct its_collection *col, u32 id)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_movi_cmd.dev = dev;
+	desc.its_movi_cmd.col = col;
+	desc.its_movi_cmd.id = id;
+
+	its_send_single_command(dev->its, its_build_movi_cmd, &desc);
+}
+
+static void its_send_discard(struct its_device *dev, u32 id)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_discard_cmd.dev = dev;
+	desc.its_discard_cmd.event_id = id;
+
+	its_send_single_command(dev->its, its_build_discard_cmd, &desc);
+}
+
+static void its_send_invall(struct its_node *its, struct its_collection *col)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_invall_cmd.col = col;
+
+	its_send_single_command(its, its_build_invall_cmd, &desc);
+}
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 040615a48bf..21c9d70426d 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -80,9 +80,27 @@
 #define GICR_MOVALLR			0x0110
 #define GICR_PIDR2			GICD_PIDR2
 
+#define GICR_CTLR_ENABLE_LPIS		(1UL << 0)
+
+#define GICR_TYPER_CPU_NUMBER(r)	(((r) >> 8) & 0xffff)
+
 #define GICR_WAKER_ProcessorSleep	(1U << 1)
 #define GICR_WAKER_ChildrenAsleep	(1U << 2)
 
+#define GICR_PROPBASER_NonShareable	(0U << 10)
+#define GICR_PROPBASER_InnerShareable	(1U << 10)
+#define GICR_PROPBASER_OuterShareable	(2U << 10)
+#define GICR_PROPBASER_SHAREABILITY_MASK (3UL << 10)
+#define GICR_PROPBASER_nCnB		(0U << 7)
+#define GICR_PROPBASER_nC		(1U << 7)
+#define GICR_PROPBASER_RaWt		(2U << 7)
+#define GICR_PROPBASER_RaWb		(3U << 7)
+#define GICR_PROPBASER_WaWt		(4U << 7)
+#define GICR_PROPBASER_WaWb		(5U << 7)
+#define GICR_PROPBASER_RaWaWt		(6U << 7)
+#define GICR_PROPBASER_RaWaWb		(7U << 7)
+#define GICR_PROPBASER_IDBITS_MASK	(0x1f)
+
 /*
  * Re-Distributor registers, offsets from SGI_base
  */
@@ -95,9 +113,93 @@
 #define GICR_IPRIORITYR0		GICD_IPRIORITYR
 #define GICR_ICFGR0			GICD_ICFGR
 
+#define GICR_TYPER_PLPIS		(1U << 0)
 #define GICR_TYPER_VLPIS		(1U << 1)
 #define GICR_TYPER_LAST			(1U << 4)
 
+#define LPI_PROP_GROUP1			(1 << 1)
+#define LPI_PROP_ENABLED		(1 << 0)
+
+/*
+ * ITS registers, offsets from ITS_base
+ */
+#define GITS_CTLR			0x0000
+#define GITS_IIDR			0x0004
+#define GITS_TYPER			0x0008
+#define GITS_CBASER			0x0080
+#define GITS_CWRITER			0x0088
+#define GITS_CREADR			0x0090
+#define GITS_BASER			0x0100
+#define GITS_PIDR2			GICR_PIDR2
+
+#define GITS_TRANSLATER			0x10040
+
+#define GITS_TYPER_PTA			(1UL << 19)
+
+#define GITS_CBASER_VALID		(1UL << 63)
+#define GITS_CBASER_nCnB		(0UL << 59)
+#define GITS_CBASER_nC			(1UL << 59)
+#define GITS_CBASER_RaWt		(2UL << 59)
+#define GITS_CBASER_RaWb		(3UL << 59)
+#define GITS_CBASER_WaWt		(4UL << 59)
+#define GITS_CBASER_WaWb		(5UL << 59)
+#define GITS_CBASER_RaWaWt		(6UL << 59)
+#define GITS_CBASER_RaWaWb		(7UL << 59)
+#define GITS_CBASER_NonShareable	(0UL << 10)
+#define GITS_CBASER_InnerShareable	(1UL << 10)
+#define GITS_CBASER_OuterShareable	(2UL << 10)
+#define GITS_CBASER_SHAREABILITY_MASK	(3UL << 10)
+
+#define GITS_BASER_NR_REGS		8
+
+#define GITS_BASER_VALID		(1UL << 63)
+#define GITS_BASER_nCnB			(0UL << 59)
+#define GITS_BASER_nC			(1UL << 59)
+#define GITS_BASER_RaWt			(2UL << 59)
+#define GITS_BASER_RaWb			(3UL << 59)
+#define GITS_BASER_WaWt			(4UL << 59)
+#define GITS_BASER_WaWb			(5UL << 59)
+#define GITS_BASER_RaWaWt		(6UL << 59)
+#define GITS_BASER_RaWaWb		(7UL << 59)
+#define GITS_BASER_TYPE_SHIFT		(56)
+#define GITS_BASER_TYPE(r)		(((r) >> GITS_BASER_TYPE_SHIFT) & 7)
+#define GITS_BASER_ENTRY_SIZE_SHIFT	(48)
+#define GITS_BASER_ENTRY_SIZE(r)	((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0xff) + 1)
+#define GITS_BASER_NonShareable		(0UL << 10)
+#define GITS_BASER_InnerShareable	(1UL << 10)
+#define GITS_BASER_OuterShareable	(2UL << 10)
+#define GITS_BASER_SHAREABILITY_SHIFT	(10)
+#define GITS_BASER_SHAREABILITY_MASK	(3UL << GITS_BASER_SHAREABILITY_SHIFT)
+#define GITS_BASER_PAGE_SIZE_SHIFT	(8)
+#define GITS_BASER_PAGE_SIZE_4K		(0UL << GITS_BASER_PAGE_SIZE_SHIFT)
+#define GITS_BASER_PAGE_SIZE_16K	(1UL << GITS_BASER_PAGE_SIZE_SHIFT)
+#define GITS_BASER_PAGE_SIZE_64K	(2UL << GITS_BASER_PAGE_SIZE_SHIFT)
+#define GITS_BASER_PAGE_SIZE_MASK	(3UL << GITS_BASER_PAGE_SIZE_SHIFT)
+
+#define GITS_BASER_TYPE_NONE		0
+#define GITS_BASER_TYPE_DEVICE		1
+#define GITS_BASER_TYPE_VCPU		2
+#define GITS_BASER_TYPE_CPU		3
+#define GITS_BASER_TYPE_COLLECTION	4
+#define GITS_BASER_TYPE_RESERVED5	5
+#define GITS_BASER_TYPE_RESERVED6	6
+#define GITS_BASER_TYPE_RESERVED7	7
+
+/*
+ * ITS commands
+ */
+#define GITS_CMD_MAPD			0x08
+#define GITS_CMD_MAPC			0x09
+#define GITS_CMD_MAPVI			0x0a
+#define GITS_CMD_MOVI			0x01
+#define GITS_CMD_DISCARD		0x0f
+#define GITS_CMD_INV			0x0c
+#define GITS_CMD_MOVALL			0x0e
+#define GITS_CMD_INVALL			0x0d
+#define GITS_CMD_INT			0x03
+#define GITS_CMD_CLEAR			0x04
+#define GITS_CMD_SYNC			0x05
+
 /*
  * CPU interface registers
  */
-- 
cgit v1.2.3-70-g09d2


From b48ac83d6bbc20a973c3e8133fd1ebda873d026a Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Mon, 24 Nov 2014 14:35:16 +0000
Subject: irqchip: GICv3: ITS: MSI support

Now, the bit of code that allow us to use the ITS as a MSI controller.
Both MSI and MSI-X are supported.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Link: https://lkml.kernel.org/r/1416839720-18400-10-git-send-email-marc.zyngier@arm.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
---
 drivers/irqchip/irq-gic-v3-its.c   | 176 +++++++++++++++++++++++++++++++++++++
 include/linux/irqchip/arm-gic-v3.h |   6 ++
 2 files changed, 182 insertions(+)

(limited to 'include')

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index d687fd43fbb..532c6df8999 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -587,12 +587,47 @@ static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	return IRQ_SET_MASK_OK_DONE;
 }
 
+static void its_irq_compose_msi_msg(struct irq_data *d, struct msi_msg *msg)
+{
+	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+	struct its_node *its;
+	u64 addr;
+
+	its = its_dev->its;
+	addr = its->phys_base + GITS_TRANSLATER;
+
+	msg->address_lo		= addr & ((1UL << 32) - 1);
+	msg->address_hi		= addr >> 32;
+	msg->data		= its_get_event_id(d);
+}
+
 static struct irq_chip its_irq_chip = {
 	.name			= "ITS",
 	.irq_mask		= its_mask_irq,
 	.irq_unmask		= its_unmask_irq,
 	.irq_eoi		= its_eoi_irq,
 	.irq_set_affinity	= its_set_affinity,
+	.irq_compose_msi_msg	= its_irq_compose_msi_msg,
+};
+
+static void its_mask_msi_irq(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
+
+static void its_unmask_msi_irq(struct irq_data *d)
+{
+	pci_msi_unmask_irq(d);
+	irq_chip_unmask_parent(d);
+}
+
+static struct irq_chip its_msi_irq_chip = {
+	.name			= "ITS-MSI",
+	.irq_unmask		= its_unmask_msi_irq,
+	.irq_mask		= its_mask_msi_irq,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_write_msi_msg	= pci_msi_domain_write_msg,
 };
 
 /*
@@ -1055,3 +1090,144 @@ static void its_free_device(struct its_device *its_dev)
 	kfree(its_dev->itt);
 	kfree(its_dev);
 }
+
+static int its_alloc_device_irq(struct its_device *dev, irq_hw_number_t *hwirq)
+{
+	int idx;
+
+	idx = find_first_zero_bit(dev->lpi_map, dev->nr_lpis);
+	if (idx == dev->nr_lpis)
+		return -ENOSPC;
+
+	*hwirq = dev->lpi_base + idx;
+	set_bit(idx, dev->lpi_map);
+
+	/* Map the GIC irq ID to the device */
+	its_send_mapvi(dev, *hwirq, idx);
+
+	return 0;
+}
+
+static int its_msi_prepare(struct irq_domain *domain, struct device *dev,
+			   int nvec, msi_alloc_info_t *info)
+{
+	struct pci_dev *pdev;
+	struct its_node *its;
+	u32 dev_id;
+	struct its_device *its_dev;
+
+	if (!dev_is_pci(dev))
+		return -EINVAL;
+
+	pdev = to_pci_dev(dev);
+	dev_id = PCI_DEVID(pdev->bus->number, pdev->devfn);
+	its = domain->parent->host_data;
+
+	its_dev = its_find_device(its, dev_id);
+	if (WARN_ON(its_dev))
+		return -EINVAL;
+
+	its_dev = its_create_device(its, dev_id, nvec);
+	if (!its_dev)
+		return -ENOMEM;
+
+	dev_dbg(&pdev->dev, "ITT %d entries, %d bits\n", nvec, ilog2(nvec));
+
+	info->scratchpad[0].ptr = its_dev;
+	info->scratchpad[1].ptr = dev;
+	return 0;
+}
+
+static struct msi_domain_ops its_pci_msi_ops = {
+	.msi_prepare	= its_msi_prepare,
+};
+
+static struct msi_domain_info its_pci_msi_domain_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		   MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX),
+	.ops	= &its_pci_msi_ops,
+	.chip	= &its_msi_irq_chip,
+};
+
+static int its_irq_gic_domain_alloc(struct irq_domain *domain,
+				    unsigned int virq,
+				    irq_hw_number_t hwirq)
+{
+	struct of_phandle_args args;
+
+	args.np = domain->parent->of_node;
+	args.args_count = 3;
+	args.args[0] = GIC_IRQ_TYPE_LPI;
+	args.args[1] = hwirq;
+	args.args[2] = IRQ_TYPE_EDGE_RISING;
+
+	return irq_domain_alloc_irqs_parent(domain, virq, 1, &args);
+}
+
+static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				unsigned int nr_irqs, void *args)
+{
+	msi_alloc_info_t *info = args;
+	struct its_device *its_dev = info->scratchpad[0].ptr;
+	irq_hw_number_t hwirq;
+	int err;
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		err = its_alloc_device_irq(its_dev, &hwirq);
+		if (err)
+			return err;
+
+		err = its_irq_gic_domain_alloc(domain, virq + i, hwirq);
+		if (err)
+			return err;
+
+		irq_domain_set_hwirq_and_chip(domain, virq + i,
+					      hwirq, &its_irq_chip, its_dev);
+		dev_dbg(info->scratchpad[1].ptr, "ID:%d pID:%d vID:%d\n",
+			(int)(hwirq - its_dev->lpi_base), (int)hwirq, virq + i);
+	}
+
+	return 0;
+}
+
+static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
+				unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		struct irq_data *data = irq_domain_get_irq_data(domain,
+								virq + i);
+		int event = its_get_event_id(data);
+
+		/* Stop the delivery of interrupts */
+		its_send_discard(its_dev, event);
+
+		/* Mark interrupt index as unused */
+		clear_bit(event, its_dev->lpi_map);
+
+		/* Nuke the entry in the domain */
+		irq_domain_reset_irq_data(d);
+	}
+
+	/* If all interrupts have been freed, start mopping the floor */
+	if (bitmap_empty(its_dev->lpi_map, its_dev->nr_lpis)) {
+		its_lpi_free(its_dev->lpi_map,
+			     its_dev->lpi_base,
+			     its_dev->nr_lpis);
+
+		/* Unmap device/itt */
+		its_send_mapd(its_dev, 0);
+		its_free_device(its_dev);
+	}
+
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+}
+
+static const struct irq_domain_ops its_domain_ops = {
+	.alloc			= its_irq_domain_alloc,
+	.free			= its_irq_domain_free,
+};
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 21c9d70426d..0ed30d7d933 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -295,6 +295,12 @@
 
 #include <linux/stringify.h>
 
+/*
+ * We need a value to serve as a irq-type for LPIs. Choose one that will
+ * hopefully pique the interest of the reviewer.
+ */
+#define GIC_IRQ_TYPE_LPI		0xa110c8ed
+
 struct rdists {
 	struct {
 		void __iomem	*rd_base;
-- 
cgit v1.2.3-70-g09d2


From da33f31de3e1eebb198109c1cccdc3a094e369c4 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Mon, 24 Nov 2014 14:35:18 +0000
Subject: irqchip: GICv3: ITS: plug ITS init into main GICv3 code

As the ITS is always a subsystem if GICv3, its probing/init is
driven by the main GICv3 code.

Plug that code in (guarded by a config option).

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Link: https://lkml.kernel.org/r/1416839720-18400-12-git-send-email-marc.zyngier@arm.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
---
 drivers/irqchip/irq-gic-v3.c       | 41 ++++++++++++++++++++++++++++++++------
 include/linux/irqchip/arm-gic-v3.h |  5 +++++
 2 files changed, 40 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 43e57da0d80..1a146ccee70 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -76,9 +76,6 @@ static inline void __iomem *gic_dist_base(struct irq_data *d)
 	if (d->hwirq <= 1023)		/* SPI -> dist_base */
 		return gic_data.dist_base;
 
-	if (d->hwirq >= 8192)
-		BUG();		/* LPI Detected!!! */
-
 	return NULL;
 }
 
@@ -276,11 +273,11 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs
 	do {
 		irqnr = gic_read_iar();
 
-		if (likely(irqnr > 15 && irqnr < 1020)) {
+		if (likely(irqnr > 15 && irqnr < 1020) || irqnr >= 8192) {
 			int err;
 			err = handle_domain_irq(gic_data.domain, irqnr, regs);
 			if (err) {
-				WARN_ONCE(true, "Unexpected SPI received!\n");
+				WARN_ONCE(true, "Unexpected interrupt received!\n");
 				gic_write_eoir(irqnr);
 			}
 			continue;
@@ -393,6 +390,11 @@ static void gic_cpu_sys_reg_init(void)
 	gic_write_grpen1(1);
 }
 
+static int gic_dist_supports_lpis(void)
+{
+	return !!(readl_relaxed(gic_data.dist_base + GICD_TYPER) & GICD_TYPER_LPIS);
+}
+
 static void gic_cpu_init(void)
 {
 	void __iomem *rbase;
@@ -407,6 +409,10 @@ static void gic_cpu_init(void)
 
 	gic_cpu_config(rbase, gic_redist_wait_for_rwp);
 
+	/* Give LPIs a spin */
+	if (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) && gic_dist_supports_lpis())
+		its_cpu_init();
+
 	/* initialise system registers */
 	gic_cpu_sys_reg_init();
 }
@@ -593,12 +599,21 @@ static struct irq_chip gic_chip = {
 	.irq_set_affinity	= gic_set_affinity,
 };
 
+#define GIC_ID_NR		(1U << gic_data.rdists.id_bits)
+
 static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 			      irq_hw_number_t hw)
 {
 	/* SGIs are private to the core kernel */
 	if (hw < 16)
 		return -EPERM;
+	/* Nothing here */
+	if (hw >= gic_data.irq_nr && hw < 8192)
+		return -EPERM;
+	/* Off limits */
+	if (hw >= GIC_ID_NR)
+		return -EPERM;
+
 	/* PPIs */
 	if (hw < 32) {
 		irq_set_percpu_devid(irq);
@@ -612,7 +627,15 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 				    handle_fasteoi_irq, NULL, NULL);
 		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
 	}
-	irq_set_chip_data(irq, d->host_data);
+	/* LPIs */
+	if (hw >= 8192 && hw < GIC_ID_NR) {
+		if (!gic_dist_supports_lpis())
+			return -EPERM;
+		irq_domain_set_info(d, irq, hw, &gic_chip, d->host_data,
+				    handle_fasteoi_irq, NULL, NULL);
+		set_irq_flags(irq, IRQF_VALID);
+	}
+
 	return 0;
 }
 
@@ -633,6 +656,9 @@ static int gic_irq_domain_xlate(struct irq_domain *d,
 	case 1:			/* PPI */
 		*out_hwirq = intspec[1] + 16;
 		break;
+	case GIC_IRQ_TYPE_LPI:	/* LPI */
+		*out_hwirq = intspec[1];
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -759,6 +785,9 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare
 
 	set_handle_irq(gic_handle_irq);
 
+	if (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) && gic_dist_supports_lpis())
+		its_init(node, &gic_data.rdists, gic_data.domain);
+
 	gic_smp_init();
 	gic_dist_init();
 	gic_cpu_init();
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 0ed30d7d933..1e8b0cf3079 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -318,6 +318,11 @@ static inline void gic_write_eoir(u64 irq)
 	isb();
 }
 
+struct irq_domain;
+int its_cpu_init(void);
+int its_init(struct device_node *node, struct rdists *rdists,
+	     struct irq_domain *domain);
+
 #endif
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From 853a33ce6932601030f550653aea91a0e0a71511 Mon Sep 17 00:00:00 2001
From: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
Date: Tue, 25 Nov 2014 18:47:22 +0000
Subject: irqchip: gic-v2m: Add support for ARM GICv2m MSI(-X) doorbell

ARM GICv2m specification extends GICv2 to support MSI(-X) with
a new register frame. This allows a GICv2 based system to support
MSI with minimal changes.

Signed-off-by: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
[maz: converted the driver to use stacked irq domains,
      updated changelog]
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Link: https://lkml.kernel.org/r/1416941243-7181-2-git-send-email-marc.zyngier@arm.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
---
 arch/arm64/Kconfig              |   1 +
 drivers/irqchip/Kconfig         |   6 +
 drivers/irqchip/Makefile        |   1 +
 drivers/irqchip/irq-gic-v2m.c   | 333 ++++++++++++++++++++++++++++++++++++++++
 drivers/irqchip/irq-gic.c       |   4 +
 include/linux/irqchip/arm-gic.h |   2 +
 6 files changed, 347 insertions(+)
 create mode 100644 drivers/irqchip/irq-gic-v2m.c

(limited to 'include')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1f49c288457..e06e1a99eaf 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -12,6 +12,7 @@ config ARM64
 	select ARM_ARCH_TIMER
 	select ARM_GIC
 	select AUDIT_ARCH_COMPAT_GENERIC
+	select ARM_GIC_V2M if PCI_MSI
 	select ARM_GIC_V3
 	select ARM_GIC_V3_ITS if PCI_MSI
 	select BUILDTIME_EXTABLE_SORT
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index d47fa846763..e72e2396063 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -8,6 +8,12 @@ config ARM_GIC
 	select IRQ_DOMAIN_HIERARCHY
 	select MULTI_IRQ_HANDLER
 
+config ARM_GIC_V2M
+	bool
+	depends on ARM_GIC
+	depends on PCI && PCI_MSI
+	select PCI_MSI_IRQ_DOMAIN
+
 config GIC_NON_BANKED
 	bool
 
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 2029e79c07a..983634d61b2 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_ARCH_SUNXI)		+= irq-sun4i.o
 obj-$(CONFIG_ARCH_SUNXI)		+= irq-sunxi-nmi.o
 obj-$(CONFIG_ARCH_SPEAR3XX)		+= spear-shirq.o
 obj-$(CONFIG_ARM_GIC)			+= irq-gic.o irq-gic-common.o
+obj-$(CONFIG_ARM_GIC_V2M)		+= irq-gic-v2m.o
 obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-common.o
 obj-$(CONFIG_ARM_GIC_V3_ITS)		+= irq-gic-v3-its.o
 obj-$(CONFIG_ARM_NVIC)			+= irq-nvic.o
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
new file mode 100644
index 00000000000..fdf706555d7
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -0,0 +1,333 @@
+/*
+ * ARM GIC v2m MSI(-X) support
+ * Support for Message Signaled Interrupts for systems that
+ * implement ARM Generic Interrupt Controller: GICv2m.
+ *
+ * Copyright (C) 2014 Advanced Micro Devices, Inc.
+ * Authors: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
+ *	    Harish Kasiviswanathan <harish.kasiviswanathan@amd.com>
+ *	    Brandon Anderson <brandon.anderson@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) "GICv2m: " fmt
+
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/of_address.h>
+#include <linux/of_pci.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+/*
+* MSI_TYPER:
+*     [31:26] Reserved
+*     [25:16] lowest SPI assigned to MSI
+*     [15:10] Reserved
+*     [9:0]   Numer of SPIs assigned to MSI
+*/
+#define V2M_MSI_TYPER		       0x008
+#define V2M_MSI_TYPER_BASE_SHIFT       16
+#define V2M_MSI_TYPER_BASE_MASK	       0x3FF
+#define V2M_MSI_TYPER_NUM_MASK	       0x3FF
+#define V2M_MSI_SETSPI_NS	       0x040
+#define V2M_MIN_SPI		       32
+#define V2M_MAX_SPI		       1019
+
+#define V2M_MSI_TYPER_BASE_SPI(x)      \
+	       (((x) >> V2M_MSI_TYPER_BASE_SHIFT) & V2M_MSI_TYPER_BASE_MASK)
+
+#define V2M_MSI_TYPER_NUM_SPI(x)       ((x) & V2M_MSI_TYPER_NUM_MASK)
+
+struct v2m_data {
+	spinlock_t msi_cnt_lock;
+	struct msi_controller mchip;
+	struct resource res;	/* GICv2m resource */
+	void __iomem *base;	/* GICv2m virt address */
+	u32 spi_start;		/* The SPI number that MSIs start */
+	u32 nr_spis;		/* The number of SPIs for MSIs */
+	unsigned long *bm;	/* MSI vector bitmap */
+	struct irq_domain *domain;
+};
+
+static void gicv2m_mask_msi_irq(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
+
+static void gicv2m_unmask_msi_irq(struct irq_data *d)
+{
+	pci_msi_unmask_irq(d);
+	irq_chip_unmask_parent(d);
+}
+
+static struct irq_chip gicv2m_msi_irq_chip = {
+	.name			= "MSI",
+	.irq_mask		= gicv2m_mask_msi_irq,
+	.irq_unmask		= gicv2m_unmask_msi_irq,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_write_msi_msg	= pci_msi_domain_write_msg,
+};
+
+static struct msi_domain_info gicv2m_msi_domain_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		   MSI_FLAG_PCI_MSIX),
+	.chip	= &gicv2m_msi_irq_chip,
+};
+
+static int gicv2m_set_affinity(struct irq_data *irq_data,
+			       const struct cpumask *mask, bool force)
+{
+	int ret;
+
+	ret = irq_chip_set_affinity_parent(irq_data, mask, force);
+	if (ret == IRQ_SET_MASK_OK)
+		ret = IRQ_SET_MASK_OK_DONE;
+
+	return ret;
+}
+
+static void gicv2m_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct v2m_data *v2m = irq_data_get_irq_chip_data(data);
+	phys_addr_t addr = v2m->res.start + V2M_MSI_SETSPI_NS;
+
+	msg->address_hi = (u32) (addr >> 32);
+	msg->address_lo = (u32) (addr);
+	msg->data = data->hwirq;
+}
+
+static struct irq_chip gicv2m_irq_chip = {
+	.name			= "GICv2m",
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_affinity	= gicv2m_set_affinity,
+	.irq_compose_msi_msg	= gicv2m_compose_msi_msg,
+};
+
+static int gicv2m_irq_gic_domain_alloc(struct irq_domain *domain,
+				       unsigned int virq,
+				       irq_hw_number_t hwirq)
+{
+	struct of_phandle_args args;
+	struct irq_data *d;
+	int err;
+
+	args.np = domain->parent->of_node;
+	args.args_count = 3;
+	args.args[0] = 0;
+	args.args[1] = hwirq - 32;
+	args.args[2] = IRQ_TYPE_EDGE_RISING;
+
+	err = irq_domain_alloc_irqs_parent(domain, virq, 1, &args);
+	if (err)
+		return err;
+
+	/* Configure the interrupt line to be edge */
+	d = irq_domain_get_irq_data(domain->parent, virq);
+	d->chip->irq_set_type(d, IRQ_TYPE_EDGE_RISING);
+	return 0;
+}
+
+static void gicv2m_unalloc_msi(struct v2m_data *v2m, unsigned int hwirq)
+{
+	int pos;
+
+	pos = hwirq - v2m->spi_start;
+	if (pos < 0 || pos >= v2m->nr_spis) {
+		pr_err("Failed to teardown msi. Invalid hwirq %d\n", hwirq);
+		return;
+	}
+
+	spin_lock(&v2m->msi_cnt_lock);
+	__clear_bit(pos, v2m->bm);
+	spin_unlock(&v2m->msi_cnt_lock);
+}
+
+static int gicv2m_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				   unsigned int nr_irqs, void *args)
+{
+	struct v2m_data *v2m = domain->host_data;
+	int hwirq, offset, err = 0;
+
+	spin_lock(&v2m->msi_cnt_lock);
+	offset = find_first_zero_bit(v2m->bm, v2m->nr_spis);
+	if (offset < v2m->nr_spis)
+		__set_bit(offset, v2m->bm);
+	else
+		err = -ENOSPC;
+	spin_unlock(&v2m->msi_cnt_lock);
+
+	if (err)
+		return err;
+
+	hwirq = v2m->spi_start + offset;
+
+	err = gicv2m_irq_gic_domain_alloc(domain, virq, hwirq);
+	if (err) {
+		gicv2m_unalloc_msi(v2m, hwirq);
+		return err;
+	}
+
+	irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
+				      &gicv2m_irq_chip, v2m);
+
+	return 0;
+}
+
+static void gicv2m_irq_domain_free(struct irq_domain *domain,
+				   unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct v2m_data *v2m = irq_data_get_irq_chip_data(d);
+
+	BUG_ON(nr_irqs != 1);
+	gicv2m_unalloc_msi(v2m, d->hwirq);
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+}
+
+static const struct irq_domain_ops gicv2m_domain_ops = {
+	.alloc			= gicv2m_irq_domain_alloc,
+	.free			= gicv2m_irq_domain_free,
+};
+
+static bool is_msi_spi_valid(u32 base, u32 num)
+{
+	if (base < V2M_MIN_SPI) {
+		pr_err("Invalid MSI base SPI (base:%u)\n", base);
+		return false;
+	}
+
+	if ((num == 0) || (base + num > V2M_MAX_SPI)) {
+		pr_err("Number of SPIs (%u) exceed maximum (%u)\n",
+		       num, V2M_MAX_SPI - V2M_MIN_SPI + 1);
+		return false;
+	}
+
+	return true;
+}
+
+static int __init gicv2m_init_one(struct device_node *node,
+				  struct irq_domain *parent)
+{
+	int ret;
+	struct v2m_data *v2m;
+
+	v2m = kzalloc(sizeof(struct v2m_data), GFP_KERNEL);
+	if (!v2m) {
+		pr_err("Failed to allocate struct v2m_data.\n");
+		return -ENOMEM;
+	}
+
+	ret = of_address_to_resource(node, 0, &v2m->res);
+	if (ret) {
+		pr_err("Failed to allocate v2m resource.\n");
+		goto err_free_v2m;
+	}
+
+	v2m->base = ioremap(v2m->res.start, resource_size(&v2m->res));
+	if (!v2m->base) {
+		pr_err("Failed to map GICv2m resource\n");
+		ret = -ENOMEM;
+		goto err_free_v2m;
+	}
+
+	if (!of_property_read_u32(node, "arm,msi-base-spi", &v2m->spi_start) &&
+	    !of_property_read_u32(node, "arm,msi-num-spis", &v2m->nr_spis)) {
+		pr_info("Overriding V2M MSI_TYPER (base:%u, num:%u)\n",
+			v2m->spi_start, v2m->nr_spis);
+	} else {
+		u32 typer = readl_relaxed(v2m->base + V2M_MSI_TYPER);
+
+		v2m->spi_start = V2M_MSI_TYPER_BASE_SPI(typer);
+		v2m->nr_spis = V2M_MSI_TYPER_NUM_SPI(typer);
+	}
+
+	if (!is_msi_spi_valid(v2m->spi_start, v2m->nr_spis)) {
+		ret = -EINVAL;
+		goto err_iounmap;
+	}
+
+	v2m->bm = kzalloc(sizeof(long) * BITS_TO_LONGS(v2m->nr_spis),
+			  GFP_KERNEL);
+	if (!v2m->bm) {
+		ret = -ENOMEM;
+		goto err_iounmap;
+	}
+
+	v2m->domain = irq_domain_add_tree(NULL, &gicv2m_domain_ops, v2m);
+	if (!v2m->domain) {
+		pr_err("Failed to create GICv2m domain\n");
+		ret = -ENOMEM;
+		goto err_free_bm;
+	}
+
+	v2m->domain->parent = parent;
+	v2m->mchip.of_node = node;
+	v2m->mchip.domain = pci_msi_create_irq_domain(node,
+						      &gicv2m_msi_domain_info,
+						      v2m->domain);
+	if (!v2m->mchip.domain) {
+		pr_err("Failed to create MSI domain\n");
+		ret = -ENOMEM;
+		goto err_free_domains;
+	}
+
+	spin_lock_init(&v2m->msi_cnt_lock);
+
+	ret = of_pci_msi_chip_add(&v2m->mchip);
+	if (ret) {
+		pr_err("Failed to add msi_chip.\n");
+		goto err_free_domains;
+	}
+
+	pr_info("Node %s: range[%#lx:%#lx], SPI[%d:%d]\n", node->name,
+		(unsigned long)v2m->res.start, (unsigned long)v2m->res.end,
+		v2m->spi_start, (v2m->spi_start + v2m->nr_spis));
+
+	return 0;
+
+err_free_domains:
+	if (v2m->mchip.domain)
+		irq_domain_remove(v2m->mchip.domain);
+	if (v2m->domain)
+		irq_domain_remove(v2m->domain);
+err_free_bm:
+	kfree(v2m->bm);
+err_iounmap:
+	iounmap(v2m->base);
+err_free_v2m:
+	kfree(v2m);
+	return ret;
+}
+
+static struct of_device_id gicv2m_device_id[] = {
+	{	.compatible	= "arm,gic-v2m-frame",	},
+	{},
+};
+
+int __init gicv2m_of_init(struct device_node *node, struct irq_domain *parent)
+{
+	int ret = 0;
+	struct device_node *child;
+
+	for (child = of_find_matching_node(node, gicv2m_device_id); child;
+	     child = of_find_matching_node(child, gicv2m_device_id)) {
+		if (!of_find_property(child, "msi-controller", NULL))
+			continue;
+
+		ret = gicv2m_init_one(child, parent);
+		if (ret) {
+			of_node_put(node);
+			break;
+		}
+	}
+
+	return ret;
+}
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index ab6069b09c9..5a71be79786 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1066,6 +1066,10 @@ gic_of_init(struct device_node *node, struct device_node *parent)
 		irq = irq_of_parse_and_map(node, 0);
 		gic_cascade_irq(gic_cnt, irq);
 	}
+
+	if (IS_ENABLED(CONFIG_ARM_GIC_V2M))
+		gicv2m_of_init(node, gic_data[gic_cnt].domain);
+
 	gic_cnt++;
 	return 0;
 }
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 13eed92c7d2..60b09ed58ca 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -106,6 +106,8 @@ static inline void gic_init(unsigned int nr, int start,
 	gic_init_bases(nr, start, dist, cpu, 0, NULL);
 }
 
+int gicv2m_of_init(struct device_node *node, struct irq_domain *parent);
+
 void gic_send_sgi(unsigned int cpu_id, unsigned int irq);
 int gic_get_cpu_id(unsigned int cpu);
 void gic_migrate_target(unsigned int new_cpu_id);
-- 
cgit v1.2.3-70-g09d2


From 7c967b224a9a7061009ccbc47e1a0b605f1b6d81 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Tue, 25 Nov 2014 11:21:19 -0800
Subject: net: Add remcsum_adjust as common function for remote checksum
 offload

This function does the work to update a checksum field as part of
remote checksum offload.

remcsum_adjust does the following:

1) Subtract out the calculated checksum from the beginning of the
   packet (ptr arg) to the start offset.
2) Adjust the checksum field indicated by offset based on the modified
   checksum value from above step.
3) Return the difference in the old checksum field value and the
   new one. The caller will use this to update skb->csum and NAPI csum.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/checksum.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/net/checksum.h b/include/net/checksum.h
index 6465bae80a4..e339a9513e2 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -151,4 +151,20 @@ static inline void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb,
 				 (__force __be32)to, pseudohdr);
 }
 
+static inline __wsum remcsum_adjust(void *ptr, __wsum csum,
+				    int start, int offset)
+{
+	__sum16 *psum = (__sum16 *)(ptr + offset);
+	__wsum delta;
+
+	/* Subtract out checksum up to start */
+	csum = csum_sub(csum, csum_partial(ptr, start, 0));
+
+	/* Set derived checksum in packet */
+	delta = csum_sub(csum_fold(csum), *psum);
+	*psum = csum_fold(csum);
+
+	return delta;
+}
+
 #endif
-- 
cgit v1.2.3-70-g09d2


From 947c88592f17bd299ff677049c3cda36cc6f93dd Mon Sep 17 00:00:00 2001
From: Peter Chen <peter.chen@freescale.com>
Date: Wed, 26 Nov 2014 13:44:31 +0800
Subject: usb: chipidea: remove flag CI_HDRC_REQUIRE_TRANSCEIVER

Now, USB PHY is mandatory for chipidea core, the flag
CI_HDRC_REQUIRE_TRANSCEIVER is useless.

Signed-off-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/chipidea/ci_hdrc_imx.c | 3 +--
 drivers/usb/chipidea/ci_hdrc_msm.c | 1 -
 include/linux/usb/chipidea.h       | 1 -
 3 files changed, 1 insertion(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 75421c2187f..450a168974d 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -106,8 +106,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 	struct ci_hdrc_platform_data pdata = {
 		.name		= dev_name(&pdev->dev),
 		.capoffset	= DEF_CAPOFFSET,
-		.flags		= CI_HDRC_REQUIRE_TRANSCEIVER |
-				  CI_HDRC_DISABLE_STREAMING,
+		.flags		= CI_HDRC_DISABLE_STREAMING,
 	};
 	int ret;
 	const struct of_device_id *of_id =
diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c
index 3edf969ed79..d79ecc08a1b 100644
--- a/drivers/usb/chipidea/ci_hdrc_msm.c
+++ b/drivers/usb/chipidea/ci_hdrc_msm.c
@@ -46,7 +46,6 @@ static struct ci_hdrc_platform_data ci_hdrc_msm_platdata = {
 	.name			= "ci_hdrc_msm",
 	.capoffset		= DEF_CAPOFFSET,
 	.flags			= CI_HDRC_REGS_SHARED |
-				  CI_HDRC_REQUIRE_TRANSCEIVER |
 				  CI_HDRC_DISABLE_STREAMING,
 
 	.notify_event		= ci_hdrc_msm_notify_event,
diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h
index c01bf4ea27b..535997a6681 100644
--- a/include/linux/usb/chipidea.h
+++ b/include/linux/usb/chipidea.h
@@ -19,7 +19,6 @@ struct ci_hdrc_platform_data {
 	enum usb_phy_interface phy_mode;
 	unsigned long	 flags;
 #define CI_HDRC_REGS_SHARED		BIT(0)
-#define CI_HDRC_REQUIRE_TRANSCEIVER	BIT(1)
 #define CI_HDRC_DISABLE_STREAMING	BIT(3)
 	/*
 	 * Only set it when DCCPARAMS.DC==1 and DCCPARAMS.HC==1,
-- 
cgit v1.2.3-70-g09d2


From 1ae2b01658a5ae00786d4bda191fbf6f38e5dbb0 Mon Sep 17 00:00:00 2001
From: Jeff Chen <cym@rock-chips.com>
Date: Tue, 25 Nov 2014 16:13:02 -0800
Subject: clk: rockchip: add binding ID for DMC (memory controller) clocks on
 rk3288

The DMC clocks need to be turned off at runtime, so we should have IDs
so we can export them.

Signed-off-by: Jeff Chen <cym@rock-chips.com>
[dianders: split into two patches; adjusted commit msg]
Signed-off-by: Doug Anderson <dianders@chromium.org>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 include/dt-bindings/clock/rk3288-cru.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/dt-bindings/clock/rk3288-cru.h b/include/dt-bindings/clock/rk3288-cru.h
index 100a08c4769..8e19ed58db3 100644
--- a/include/dt-bindings/clock/rk3288-cru.h
+++ b/include/dt-bindings/clock/rk3288-cru.h
@@ -141,6 +141,10 @@
 #define PCLK_VIO2_H2P		361
 #define PCLK_CPU		362
 #define PCLK_PERI		363
+#define PCLK_DDRUPCTL0		364
+#define PCLK_PUBL0		365
+#define PCLK_DDRUPCTL1		366
+#define PCLK_PUBL1		367
 
 /* hclk gates */
 #define HCLK_GPS		448
-- 
cgit v1.2.3-70-g09d2


From e5262d0568dc9e10de79a726dfd7edb712a2c10b Mon Sep 17 00:00:00 2001
From: Weike Chen <alvin.chen@intel.com>
Date: Wed, 26 Nov 2014 02:35:10 -0800
Subject: spi: spi-pxa2xx: SPI support for Intel Quark X1000

There are two SPI controllers exported by PCI subsystem for Intel Quark X1000.
The SPI memory mapped I/O registers supported by Quark are different from
the current implementation, and Quark only supports the registers of 'SSCR0',
'SSCR1', 'SSSR', 'SSDR', and 'DDS_RATE'. This patch is to enable the SPI for
Intel Quark X1000.

This piece of work is derived from Dan O'Donovan's initial work for Intel Quark
X1000 SPI enabling.

Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Weike Chen <alvin.chen@intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-pxa2xx-pci.c |   8 ++
 drivers/spi/spi-pxa2xx.c     | 197 +++++++++++++++++++++++++++++++++++++++----
 drivers/spi/spi-pxa2xx.h     |  16 ++--
 include/linux/pxa2xx_ssp.h   |  20 +++++
 4 files changed, 219 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c
index 6beee8ce2d6..fa7399e84bb 100644
--- a/drivers/spi/spi-pxa2xx-pci.c
+++ b/drivers/spi/spi-pxa2xx-pci.c
@@ -19,6 +19,7 @@ enum {
 	PORT_BSW0,
 	PORT_BSW1,
 	PORT_BSW2,
+	PORT_QUARK_X1000,
 };
 
 struct pxa_spi_info {
@@ -92,6 +93,12 @@ static struct pxa_spi_info spi_info_configs[] = {
 		.tx_param = &bsw2_tx_param,
 		.rx_param = &bsw2_rx_param,
 	},
+	[PORT_QUARK_X1000] = {
+		.type = QUARK_X1000_SSP,
+		.port_id = -1,
+		.num_chipselect = 1,
+		.max_clk_rate = 50000000,
+	},
 };
 
 static int pxa2xx_spi_pci_probe(struct pci_dev *dev,
@@ -191,6 +198,7 @@ static void pxa2xx_spi_pci_remove(struct pci_dev *dev)
 
 static const struct pci_device_id pxa2xx_spi_pci_devices[] = {
 	{ PCI_VDEVICE(INTEL, 0x2e6a), PORT_CE4100 },
+	{ PCI_VDEVICE(INTEL, 0x0935), PORT_QUARK_X1000 },
 	{ PCI_VDEVICE(INTEL, 0x0f0e), PORT_BYT },
 	{ PCI_VDEVICE(INTEL, 0x228e), PORT_BSW0 },
 	{ PCI_VDEVICE(INTEL, 0x2290), PORT_BSW1 },
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index d4d29c59415..1a1df5092ac 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -63,10 +63,64 @@ MODULE_ALIAS("platform:pxa2xx-spi");
 				| SSCR1_RFT | SSCR1_TFT | SSCR1_MWDS \
 				| SSCR1_SPH | SSCR1_SPO | SSCR1_LBM)
 
+#define QUARK_X1000_SSCR1_CHANGE_MASK (QUARK_X1000_SSCR1_STRF	\
+				| QUARK_X1000_SSCR1_EFWR	\
+				| QUARK_X1000_SSCR1_RFT		\
+				| QUARK_X1000_SSCR1_TFT		\
+				| SSCR1_SPH | SSCR1_SPO | SSCR1_LBM)
+
 #define LPSS_RX_THRESH_DFLT	64
 #define LPSS_TX_LOTHRESH_DFLT	160
 #define LPSS_TX_HITHRESH_DFLT	224
 
+struct quark_spi_rate {
+	u32 bitrate;
+	u32 dds_clk_rate;
+	u32 clk_div;
+};
+
+/*
+ * 'rate', 'dds', 'clk_div' lookup table, which is defined in
+ * the Quark SPI datasheet.
+ */
+static const struct quark_spi_rate quark_spi_rate_table[] = {
+/*	bitrate,	dds_clk_rate,	clk_div */
+	{50000000,	0x800000,	0},
+	{40000000,	0x666666,	0},
+	{25000000,	0x400000,	0},
+	{20000000,	0x666666,	1},
+	{16667000,	0x800000,	2},
+	{13333000,	0x666666,	2},
+	{12500000,	0x200000,	0},
+	{10000000,	0x800000,	4},
+	{8000000,	0x666666,	4},
+	{6250000,	0x400000,	3},
+	{5000000,	0x400000,	4},
+	{4000000,	0x666666,	9},
+	{3125000,	0x80000,	0},
+	{2500000,	0x400000,	9},
+	{2000000,	0x666666,	19},
+	{1563000,	0x40000,	0},
+	{1250000,	0x200000,	9},
+	{1000000,	0x400000,	24},
+	{800000,	0x666666,	49},
+	{781250,	0x20000,	0},
+	{625000,	0x200000,	19},
+	{500000,	0x400000,	49},
+	{400000,	0x666666,	99},
+	{390625,	0x10000,	0},
+	{250000,	0x400000,	99},
+	{200000,	0x666666,	199},
+	{195313,	0x8000,		0},
+	{125000,	0x100000,	49},
+	{100000,	0x200000,	124},
+	{50000,		0x100000,	124},
+	{25000,		0x80000,	124},
+	{10016,		0x20000,	77},
+	{5040,		0x20000,	154},
+	{1002,		0x8000,		194},
+};
+
 /* Offset from drv_data->lpss_base */
 #define GENERAL_REG		0x08
 #define GENERAL_REG_RXTO_HOLDOFF_DISABLE BIT(24)
@@ -80,9 +134,16 @@ static bool is_lpss_ssp(const struct driver_data *drv_data)
 	return drv_data->ssp_type == LPSS_SSP;
 }
 
+static bool is_quark_x1000_ssp(const struct driver_data *drv_data)
+{
+	return drv_data->ssp_type == QUARK_X1000_SSP;
+}
+
 static u32 pxa2xx_spi_get_ssrc1_change_mask(const struct driver_data *drv_data)
 {
 	switch (drv_data->ssp_type) {
+	case QUARK_X1000_SSP:
+		return QUARK_X1000_SSCR1_CHANGE_MASK;
 	default:
 		return SSCR1_CHANGE_MASK;
 	}
@@ -92,6 +153,8 @@ static u32
 pxa2xx_spi_get_rx_default_thre(const struct driver_data *drv_data)
 {
 	switch (drv_data->ssp_type) {
+	case QUARK_X1000_SSP:
+		return RX_THRESH_QUARK_X1000_DFLT;
 	default:
 		return RX_THRESH_DFLT;
 	}
@@ -103,6 +166,9 @@ static bool pxa2xx_spi_txfifo_full(const struct driver_data *drv_data)
 	u32 mask;
 
 	switch (drv_data->ssp_type) {
+	case QUARK_X1000_SSP:
+		mask = QUARK_X1000_SSSR_TFL_MASK;
+		break;
 	default:
 		mask = SSSR_TFL_MASK;
 		break;
@@ -117,6 +183,9 @@ static void pxa2xx_spi_clear_rx_thre(const struct driver_data *drv_data,
 	u32 mask;
 
 	switch (drv_data->ssp_type) {
+	case QUARK_X1000_SSP:
+		mask = QUARK_X1000_SSCR1_RFT;
+		break;
 	default:
 		mask = SSCR1_RFT;
 		break;
@@ -128,6 +197,9 @@ static void pxa2xx_spi_set_rx_thre(const struct driver_data *drv_data,
 				   u32 *sccr1_reg, u32 threshold)
 {
 	switch (drv_data->ssp_type) {
+	case QUARK_X1000_SSP:
+		*sccr1_reg |= QUARK_X1000_SSCR1_RxTresh(threshold);
+		break;
 	default:
 		*sccr1_reg |= SSCR1_RxTresh(threshold);
 		break;
@@ -138,6 +210,11 @@ static u32 pxa2xx_configure_sscr0(const struct driver_data *drv_data,
 				  u32 clk_div, u8 bits)
 {
 	switch (drv_data->ssp_type) {
+	case QUARK_X1000_SSP:
+		return clk_div
+			| QUARK_X1000_SSCR0_Motorola
+			| QUARK_X1000_SSCR0_DataSize(bits > 32 ? 8 : bits)
+			| SSCR0_SSE;
 	default:
 		return clk_div
 			| SSCR0_Motorola
@@ -654,6 +731,28 @@ static irqreturn_t ssp_int(int irq, void *dev_id)
 	return drv_data->transfer_handler(drv_data);
 }
 
+/*
+ * The Quark SPI data sheet gives a table, and for the given 'rate',
+ * the 'dds' and 'clk_div' can be found in the table.
+ */
+static u32 quark_x1000_set_clk_regvals(u32 rate, u32 *dds, u32 *clk_div)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(quark_spi_rate_table); i++) {
+		if (rate >= quark_spi_rate_table[i].bitrate) {
+			*dds = quark_spi_rate_table[i].dds_clk_rate;
+			*clk_div = quark_spi_rate_table[i].clk_div;
+			return quark_spi_rate_table[i].bitrate;
+		}
+	}
+
+	*dds = quark_spi_rate_table[i-1].dds_clk_rate;
+	*clk_div = quark_spi_rate_table[i-1].clk_div;
+
+	return quark_spi_rate_table[i-1].bitrate;
+}
+
 static unsigned int ssp_get_clk_div(struct driver_data *drv_data, int rate)
 {
 	unsigned long ssp_clk = drv_data->max_clk_rate;
@@ -667,6 +766,20 @@ static unsigned int ssp_get_clk_div(struct driver_data *drv_data, int rate)
 		return ((ssp_clk / rate - 1) & 0xfff) << 8;
 }
 
+static unsigned int pxa2xx_ssp_get_clk_div(struct driver_data *drv_data,
+					   struct chip_data *chip, int rate)
+{
+	u32 clk_div;
+
+	switch (drv_data->ssp_type) {
+	case QUARK_X1000_SSP:
+		quark_x1000_set_clk_regvals(rate, &chip->dds_rate, &clk_div);
+		return clk_div << 8;
+	default:
+		return ssp_get_clk_div(drv_data, rate);
+	}
+}
+
 static void pump_transfers(unsigned long data)
 {
 	struct driver_data *drv_data = (struct driver_data *)data;
@@ -769,7 +882,7 @@ static void pump_transfers(unsigned long data)
 		if (transfer->bits_per_word)
 			bits = transfer->bits_per_word;
 
-		clk_div = ssp_get_clk_div(drv_data, speed);
+		clk_div = pxa2xx_ssp_get_clk_div(drv_data, chip, speed);
 
 		if (bits <= 8) {
 			drv_data->n_bytes = 1;
@@ -837,6 +950,10 @@ static void pump_transfers(unsigned long data)
 			write_SSITF(chip->lpss_tx_threshold, reg);
 	}
 
+	if (is_quark_x1000_ssp(drv_data) &&
+	    (read_DDS_RATE(reg) != chip->dds_rate))
+		write_DDS_RATE(chip->dds_rate, reg);
+
 	/* see if we need to reload the config registers */
 	if ((read_SSCR0(reg) != cr0) ||
 	    (read_SSCR1(reg) & change_mask) != (cr1 & change_mask)) {
@@ -940,14 +1057,22 @@ static int setup(struct spi_device *spi)
 	unsigned int clk_div;
 	uint tx_thres, tx_hi_thres, rx_thres;
 
-	if (is_lpss_ssp(drv_data)) {
+	switch (drv_data->ssp_type) {
+	case QUARK_X1000_SSP:
+		tx_thres = TX_THRESH_QUARK_X1000_DFLT;
+		tx_hi_thres = 0;
+		rx_thres = RX_THRESH_QUARK_X1000_DFLT;
+		break;
+	case LPSS_SSP:
 		tx_thres = LPSS_TX_LOTHRESH_DFLT;
 		tx_hi_thres = LPSS_TX_HITHRESH_DFLT;
 		rx_thres = LPSS_RX_THRESH_DFLT;
-	} else {
+		break;
+	default:
 		tx_thres = TX_THRESH_DFLT;
 		tx_hi_thres = 0;
 		rx_thres = RX_THRESH_DFLT;
+		break;
 	}
 
 	/* Only alloc on first setup */
@@ -1000,9 +1125,6 @@ static int setup(struct spi_device *spi)
 		chip->enable_dma = drv_data->master_info->enable_dma;
 	}
 
-	chip->threshold = (SSCR1_RxTresh(rx_thres) & SSCR1_RFT) |
-			(SSCR1_TxTresh(tx_thres) & SSCR1_TFT);
-
 	chip->lpss_rx_threshold = SSIRF_RxThresh(rx_thres);
 	chip->lpss_tx_threshold = SSITF_TxLoThresh(tx_thres)
 				| SSITF_TxHiThresh(tx_hi_thres);
@@ -1021,11 +1143,24 @@ static int setup(struct spi_device *spi)
 		}
 	}
 
-	clk_div = ssp_get_clk_div(drv_data, spi->max_speed_hz);
+	clk_div = pxa2xx_ssp_get_clk_div(drv_data, chip, spi->max_speed_hz);
 	chip->speed_hz = spi->max_speed_hz;
 
 	chip->cr0 = pxa2xx_configure_sscr0(drv_data, clk_div,
 					   spi->bits_per_word);
+	switch (drv_data->ssp_type) {
+	case QUARK_X1000_SSP:
+		chip->threshold = (QUARK_X1000_SSCR1_RxTresh(rx_thres)
+				   & QUARK_X1000_SSCR1_RFT)
+				   | (QUARK_X1000_SSCR1_TxTresh(tx_thres)
+				   & QUARK_X1000_SSCR1_TFT);
+		break;
+	default:
+		chip->threshold = (SSCR1_RxTresh(rx_thres) & SSCR1_RFT) |
+			(SSCR1_TxTresh(tx_thres) & SSCR1_TFT);
+		break;
+	}
+
 	chip->cr1 &= ~(SSCR1_SPO | SSCR1_SPH);
 	chip->cr1 |= (((spi->mode & SPI_CPHA) != 0) ? SSCR1_SPH : 0)
 			| (((spi->mode & SPI_CPOL) != 0) ? SSCR1_SPO : 0);
@@ -1054,7 +1189,8 @@ static int setup(struct spi_device *spi)
 		chip->read = u16_reader;
 		chip->write = u16_writer;
 	} else if (spi->bits_per_word <= 32) {
-		chip->cr0 |= SSCR0_EDSS;
+		if (!is_quark_x1000_ssp(drv_data))
+			chip->cr0 |= SSCR0_EDSS;
 		chip->n_bytes = 4;
 		chip->read = u32_reader;
 		chip->write = u32_writer;
@@ -1205,7 +1341,15 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 	drv_data->ioaddr = ssp->mmio_base;
 	drv_data->ssdr_physical = ssp->phys_base + SSDR;
 	if (pxa25x_ssp_comp(drv_data)) {
-		master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
+		switch (drv_data->ssp_type) {
+		case QUARK_X1000_SSP:
+			master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
+			break;
+		default:
+			master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
+			break;
+		}
+
 		drv_data->int_cr1 = SSCR1_TIE | SSCR1_RIE;
 		drv_data->dma_cr1 = 0;
 		drv_data->clear_sr = SSSR_ROR;
@@ -1243,16 +1387,35 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 
 	/* Load default SSP configuration */
 	write_SSCR0(0, drv_data->ioaddr);
-	write_SSCR1(SSCR1_RxTresh(RX_THRESH_DFLT) |
-				SSCR1_TxTresh(TX_THRESH_DFLT),
-				drv_data->ioaddr);
-	write_SSCR0(SSCR0_SCR(2)
-			| SSCR0_Motorola
-			| SSCR0_DataSize(8),
-			drv_data->ioaddr);
+	switch (drv_data->ssp_type) {
+	case QUARK_X1000_SSP:
+		write_SSCR1(QUARK_X1000_SSCR1_RxTresh(
+					RX_THRESH_QUARK_X1000_DFLT) |
+			    QUARK_X1000_SSCR1_TxTresh(
+					TX_THRESH_QUARK_X1000_DFLT),
+			    drv_data->ioaddr);
+
+		/* using the Motorola SPI protocol and use 8 bit frame */
+		write_SSCR0(QUARK_X1000_SSCR0_Motorola
+			    | QUARK_X1000_SSCR0_DataSize(8),
+			    drv_data->ioaddr);
+		break;
+	default:
+		write_SSCR1(SSCR1_RxTresh(RX_THRESH_DFLT) |
+			    SSCR1_TxTresh(TX_THRESH_DFLT),
+			    drv_data->ioaddr);
+		write_SSCR0(SSCR0_SCR(2)
+			    | SSCR0_Motorola
+			    | SSCR0_DataSize(8),
+			    drv_data->ioaddr);
+		break;
+	}
+
 	if (!pxa25x_ssp_comp(drv_data))
 		write_SSTO(0, drv_data->ioaddr);
-	write_SSPSP(0, drv_data->ioaddr);
+
+	if (!is_quark_x1000_ssp(drv_data))
+		write_SSPSP(0, drv_data->ioaddr);
 
 	lpss_ssp_setup(drv_data);
 
diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h
index 5adc2a11c7b..6bec59c90cd 100644
--- a/drivers/spi/spi-pxa2xx.h
+++ b/drivers/spi/spi-pxa2xx.h
@@ -93,6 +93,7 @@ struct driver_data {
 struct chip_data {
 	u32 cr0;
 	u32 cr1;
+	u32 dds_rate;
 	u32 psp;
 	u32 timeout;
 	u8 n_bytes;
@@ -126,6 +127,7 @@ DEFINE_SSP_REG(SSCR1, 0x04)
 DEFINE_SSP_REG(SSSR, 0x08)
 DEFINE_SSP_REG(SSITR, 0x0c)
 DEFINE_SSP_REG(SSDR, 0x10)
+DEFINE_SSP_REG(DDS_RATE, 0x28)  /* DDS Clock Rate */
 DEFINE_SSP_REG(SSTO, 0x28)
 DEFINE_SSP_REG(SSPSP, 0x2c)
 DEFINE_SSP_REG(SSITF, SSITF)
@@ -141,18 +143,22 @@ DEFINE_SSP_REG(SSIRF, SSIRF)
 
 static inline int pxa25x_ssp_comp(struct driver_data *drv_data)
 {
-	if (drv_data->ssp_type == PXA25x_SSP)
+	switch (drv_data->ssp_type) {
+	case PXA25x_SSP:
+	case CE4100_SSP:
+	case QUARK_X1000_SSP:
 		return 1;
-	if (drv_data->ssp_type == CE4100_SSP)
-		return 1;
-	return 0;
+	default:
+		return 0;
+	}
 }
 
 static inline void write_SSSR_CS(struct driver_data *drv_data, u32 val)
 {
 	void __iomem *reg = drv_data->ioaddr;
 
-	if (drv_data->ssp_type == CE4100_SSP)
+	if (drv_data->ssp_type == CE4100_SSP ||
+	    drv_data->ssp_type == QUARK_X1000_SSP)
 		val |= read_SSSR(reg) & SSSR_ALT_FRM_MASK;
 
 	write_SSSR(val, reg);
diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index f2b40511616..77aed9ea1d2 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -108,6 +108,25 @@
 #define SSCR1_RxTresh(x) (((x) - 1) << 10) /* level [1..4] */
 #endif
 
+/* QUARK_X1000 SSCR0 bit definition */
+#define QUARK_X1000_SSCR0_DSS	(0x1F)		/* Data Size Select (mask) */
+#define QUARK_X1000_SSCR0_DataSize(x)  ((x) - 1)	/* Data Size Select [4..32] */
+#define QUARK_X1000_SSCR0_FRF	(0x3 << 5)	/* FRame Format (mask) */
+#define QUARK_X1000_SSCR0_Motorola	(0x0 << 5)	/* Motorola's Serial Peripheral Interface (SPI) */
+
+#define RX_THRESH_QUARK_X1000_DFLT	1
+#define TX_THRESH_QUARK_X1000_DFLT	16
+
+#define QUARK_X1000_SSSR_TFL_MASK	(0x1F << 8)	/* Transmit FIFO Level mask */
+#define QUARK_X1000_SSSR_RFL_MASK	(0x1F << 13)	/* Receive FIFO Level mask */
+
+#define QUARK_X1000_SSCR1_TFT	(0x1F << 6)	/* Transmit FIFO Threshold (mask) */
+#define QUARK_X1000_SSCR1_TxTresh(x) (((x) - 1) << 6)	/* level [1..32] */
+#define QUARK_X1000_SSCR1_RFT	(0x1F << 11)	/* Receive FIFO Threshold (mask) */
+#define QUARK_X1000_SSCR1_RxTresh(x) (((x) - 1) << 11)	/* level [1..32] */
+#define QUARK_X1000_SSCR1_STRF       (1 << 17)		/* Select FIFO or EFWR */
+#define QUARK_X1000_SSCR1_EFWR	(1 << 16)		/* Enable FIFO Write/Read */
+
 /* extra bits in PXA255, PXA26x and PXA27x SSP ports */
 #define SSCR0_TISSP		(1 << 4)	/* TI Sync Serial Protocol */
 #define SSCR0_PSP		(3 << 4)	/* PSP - Programmable Serial Protocol */
@@ -175,6 +194,7 @@ enum pxa_ssp_type {
 	PXA910_SSP,
 	CE4100_SSP,
 	LPSS_SSP,
+	QUARK_X1000_SSP,
 };
 
 struct ssp_device {
-- 
cgit v1.2.3-70-g09d2


From 87e1e0f29f703e91c54e81f05d831432ec659dde Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Date: Mon, 10 Nov 2014 14:43:52 +0100
Subject: regulator: Add mode mapping function to struct regulator_desc

The "regulator-initial-mode" and "regulator-mode" DT properties allows
to configure the regulator operating modes at startup or when a system
enters into a susend state.

But these properties use as valid values the operating modes supported
by each device while the core deals with the standard operating modes.
So a mapping function is needed to translate from the hardware specific
modes to the standard ones.

This mapping is a non-varying configuration for each regulator, so add
a function pointer to struct regulator_desc that will allow drivers to
define their callback to do the modes translation.

Signed-off-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/regulator/driver.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index fc0ee0ce832..73dd073afef 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -243,6 +243,8 @@ enum regulator_type {
  *
  * @enable_time: Time taken for initial enable of regulator (in uS).
  * @off_on_delay: guard time (in uS), before re-enabling a regulator
+ *
+ * @of_map_mode: Maps a hardware mode defined in a DeviceTree to a standard mode
  */
 struct regulator_desc {
 	const char *name;
@@ -285,6 +287,8 @@ struct regulator_desc {
 	unsigned int enable_time;
 
 	unsigned int off_on_delay;
+
+	unsigned int (*of_map_mode)(unsigned int mode);
 };
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 072e78b12bf5182a3e2e460388214a291023ef1c Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Date: Mon, 10 Nov 2014 14:43:53 +0100
Subject: regulator: of: Add regulator desc param to
 of_get_regulator_init_data()

The of_get_regulator_init_data() function is used to extract the regulator
init_data but information on how to extract certain data is defined in the
static regulator descriptor (e.g: how to map the hardware operating modes).

Add a const struct regulator_desc * parameter to the function signature so
the parsing logic could use the information in the struct regulator_desc.

of_get_regulator_init_data() relies on of_get_regulation_constraints() to
actually extract the init_data so it has to pass the struct regulator_desc
but that is modified on a later patch.

Signed-off-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/88pm8607.c               |  3 ++-
 drivers/regulator/anatop-regulator.c       |  5 ++--
 drivers/regulator/arizona-ldo1.c           |  8 +++---
 drivers/regulator/arizona-micsupp.c        |  8 +++---
 drivers/regulator/da9052-regulator.c       |  3 ++-
 drivers/regulator/da9210-regulator.c       |  2 +-
 drivers/regulator/fan53555.c               | 17 ++++++------
 drivers/regulator/fixed.c                  | 19 +++++++------
 drivers/regulator/gpio-regulator.c         | 18 +++++++------
 drivers/regulator/max8952.c                |  2 +-
 drivers/regulator/max8973-regulator.c      |  3 ++-
 drivers/regulator/max8997.c                |  3 ++-
 drivers/regulator/max8998.c                |  5 ++--
 drivers/regulator/mc13xxx-regulator-core.c |  3 ++-
 drivers/regulator/of_regulator.c           |  9 ++++---
 drivers/regulator/pwm-regulator.c          |  3 ++-
 drivers/regulator/qcom_rpm-regulator.c     |  9 ++++---
 drivers/regulator/s5m8767.c                |  3 ++-
 drivers/regulator/sky81452-regulator.c     |  2 +-
 drivers/regulator/stw481x-vmmc.c           |  3 ++-
 drivers/regulator/ti-abb-regulator.c       |  3 ++-
 drivers/regulator/tps51632-regulator.c     | 43 ++++++++++++++++--------------
 drivers/regulator/tps62360-regulator.c     | 31 +++++++++++----------
 drivers/regulator/tps65218-regulator.c     |  3 ++-
 drivers/regulator/twl-regulator.c          |  3 ++-
 drivers/regulator/vexpress.c               |  3 ++-
 include/linux/regulator/of_regulator.h     |  8 ++++--
 27 files changed, 130 insertions(+), 92 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/88pm8607.c b/drivers/regulator/88pm8607.c
index 6d77dcd7dcf..3fe47bd6615 100644
--- a/drivers/regulator/88pm8607.c
+++ b/drivers/regulator/88pm8607.c
@@ -330,7 +330,8 @@ static int pm8607_regulator_dt_init(struct platform_device *pdev,
 	for_each_child_of_node(nproot, np) {
 		if (!of_node_cmp(np->name, info->desc.name)) {
 			config->init_data =
-				of_get_regulator_init_data(&pdev->dev, np);
+				of_get_regulator_init_data(&pdev->dev, np,
+							   &info->desc);
 			config->of_node = np;
 			break;
 		}
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 4f730af70e7..6eaef9f6442 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -189,17 +189,18 @@ static int anatop_regulator_probe(struct platform_device *pdev)
 	int ret = 0;
 	u32 val;
 
-	initdata = of_get_regulator_init_data(dev, np);
 	sreg = devm_kzalloc(dev, sizeof(*sreg), GFP_KERNEL);
 	if (!sreg)
 		return -ENOMEM;
-	sreg->initdata = initdata;
 	sreg->name = of_get_property(np, "regulator-name", NULL);
 	rdesc = &sreg->rdesc;
 	rdesc->name = sreg->name;
 	rdesc->type = REGULATOR_VOLTAGE;
 	rdesc->owner = THIS_MODULE;
 
+	initdata = of_get_regulator_init_data(dev, np, rdesc);
+	sreg->initdata = initdata;
+
 	anatop_np = of_get_parent(np);
 	if (!anatop_np)
 		return -ENODEV;
diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c
index 4c9db589f6c..b1eea7f7648 100644
--- a/drivers/regulator/arizona-ldo1.c
+++ b/drivers/regulator/arizona-ldo1.c
@@ -179,7 +179,8 @@ static const struct regulator_init_data arizona_ldo1_default = {
 };
 
 static int arizona_ldo1_of_get_pdata(struct arizona *arizona,
-				     struct regulator_config *config)
+				     struct regulator_config *config,
+				     const struct regulator_desc *desc)
 {
 	struct arizona_pdata *pdata = &arizona->pdata;
 	struct arizona_ldo1 *ldo1 = config->driver_data;
@@ -194,7 +195,8 @@ static int arizona_ldo1_of_get_pdata(struct arizona *arizona,
 	if (init_node) {
 		config->of_node = init_node;
 
-		init_data = of_get_regulator_init_data(arizona->dev, init_node);
+		init_data = of_get_regulator_init_data(arizona->dev, init_node,
+						       desc);
 
 		if (init_data) {
 			init_data->consumer_supplies = &ldo1->supply;
@@ -257,7 +259,7 @@ static int arizona_ldo1_probe(struct platform_device *pdev)
 
 	if (IS_ENABLED(CONFIG_OF)) {
 		if (!dev_get_platdata(arizona->dev)) {
-			ret = arizona_ldo1_of_get_pdata(arizona, &config);
+			ret = arizona_ldo1_of_get_pdata(arizona, &config, desc);
 			if (ret < 0)
 				return ret;
 		}
diff --git a/drivers/regulator/arizona-micsupp.c b/drivers/regulator/arizona-micsupp.c
index ce9aca5f8ee..c313ef4c3a2 100644
--- a/drivers/regulator/arizona-micsupp.c
+++ b/drivers/regulator/arizona-micsupp.c
@@ -198,7 +198,8 @@ static const struct regulator_init_data arizona_micsupp_ext_default = {
 };
 
 static int arizona_micsupp_of_get_pdata(struct arizona *arizona,
-					struct regulator_config *config)
+					struct regulator_config *config,
+					const struct regulator_desc *desc)
 {
 	struct arizona_pdata *pdata = &arizona->pdata;
 	struct arizona_micsupp *micsupp = config->driver_data;
@@ -210,7 +211,7 @@ static int arizona_micsupp_of_get_pdata(struct arizona *arizona,
 	if (np) {
 		config->of_node = np;
 
-		init_data = of_get_regulator_init_data(arizona->dev, np);
+		init_data = of_get_regulator_init_data(arizona->dev, np, desc);
 
 		if (init_data) {
 			init_data->consumer_supplies = &micsupp->supply;
@@ -264,7 +265,8 @@ static int arizona_micsupp_probe(struct platform_device *pdev)
 
 	if (IS_ENABLED(CONFIG_OF)) {
 		if (!dev_get_platdata(arizona->dev)) {
-			ret = arizona_micsupp_of_get_pdata(arizona, &config);
+			ret = arizona_micsupp_of_get_pdata(arizona, &config,
+							   desc);
 			if (ret < 0)
 				return ret;
 		}
diff --git a/drivers/regulator/da9052-regulator.c b/drivers/regulator/da9052-regulator.c
index 00033625a09..3945f1006d2 100644
--- a/drivers/regulator/da9052-regulator.c
+++ b/drivers/regulator/da9052-regulator.c
@@ -436,7 +436,8 @@ static int da9052_regulator_probe(struct platform_device *pdev)
 			if (!of_node_cmp(np->name,
 					 regulator->info->reg_desc.name)) {
 				config.init_data = of_get_regulator_init_data(
-					&pdev->dev, np);
+					&pdev->dev, np,
+					&regulator->info->reg_desc);
 				config.of_node = np;
 				break;
 			}
diff --git a/drivers/regulator/da9210-regulator.c b/drivers/regulator/da9210-regulator.c
index 7a320dd11c4..bc6100103f7 100644
--- a/drivers/regulator/da9210-regulator.c
+++ b/drivers/regulator/da9210-regulator.c
@@ -147,7 +147,7 @@ static int da9210_i2c_probe(struct i2c_client *i2c,
 
 	config.dev = &i2c->dev;
 	config.init_data = pdata ? &pdata->da9210_constraints :
-		of_get_regulator_init_data(dev, dev->of_node);
+		of_get_regulator_init_data(dev, dev->of_node, &da9210_reg);
 	config.driver_data = chip;
 	config.regmap = chip->regmap;
 	config.of_node = dev->of_node;
diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c
index f8e4257aef9..6c43ab2d512 100644
--- a/drivers/regulator/fan53555.c
+++ b/drivers/regulator/fan53555.c
@@ -302,7 +302,8 @@ static struct regmap_config fan53555_regmap_config = {
 };
 
 static struct fan53555_platform_data *fan53555_parse_dt(struct device *dev,
-							struct device_node *np)
+					      struct device_node *np,
+					      const struct regulator_desc *desc)
 {
 	struct fan53555_platform_data *pdata;
 	int ret;
@@ -312,7 +313,7 @@ static struct fan53555_platform_data *fan53555_parse_dt(struct device *dev,
 	if (!pdata)
 		return NULL;
 
-	pdata->regulator = of_get_regulator_init_data(dev, np);
+	pdata->regulator = of_get_regulator_init_data(dev, np, desc);
 
 	ret = of_property_read_u32(np, "fcs,suspend-voltage-selector",
 				   &tmp);
@@ -347,20 +348,20 @@ static int fan53555_regulator_probe(struct i2c_client *client,
 	unsigned int val;
 	int ret;
 
+	di = devm_kzalloc(&client->dev, sizeof(struct fan53555_device_info),
+					GFP_KERNEL);
+	if (!di)
+		return -ENOMEM;
+
 	pdata = dev_get_platdata(&client->dev);
 	if (!pdata)
-		pdata = fan53555_parse_dt(&client->dev, np);
+		pdata = fan53555_parse_dt(&client->dev, np, &di->desc);
 
 	if (!pdata || !pdata->regulator) {
 		dev_err(&client->dev, "Platform data not found!\n");
 		return -ENODEV;
 	}
 
-	di = devm_kzalloc(&client->dev, sizeof(struct fan53555_device_info),
-					GFP_KERNEL);
-	if (!di)
-		return -ENOMEM;
-
 	di->regulator = pdata->regulator;
 	if (client->dev.of_node) {
 		const struct of_device_id *match;
diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c
index 354105eff1f..6cfcbc8b659 100644
--- a/drivers/regulator/fixed.c
+++ b/drivers/regulator/fixed.c
@@ -40,13 +40,15 @@ struct fixed_voltage_data {
 /**
  * of_get_fixed_voltage_config - extract fixed_voltage_config structure info
  * @dev: device requesting for fixed_voltage_config
+ * @desc: regulator description
  *
  * Populates fixed_voltage_config structure by extracting data from device
  * tree node, returns a pointer to the populated structure of NULL if memory
  * alloc fails.
  */
 static struct fixed_voltage_config *
-of_get_fixed_voltage_config(struct device *dev)
+of_get_fixed_voltage_config(struct device *dev,
+			    const struct regulator_desc *desc)
 {
 	struct fixed_voltage_config *config;
 	struct device_node *np = dev->of_node;
@@ -57,7 +59,7 @@ of_get_fixed_voltage_config(struct device *dev)
 	if (!config)
 		return ERR_PTR(-ENOMEM);
 
-	config->init_data = of_get_regulator_init_data(dev, dev->of_node);
+	config->init_data = of_get_regulator_init_data(dev, dev->of_node, desc);
 	if (!config->init_data)
 		return ERR_PTR(-EINVAL);
 
@@ -112,8 +114,14 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev)
 	struct regulator_config cfg = { };
 	int ret;
 
+	drvdata = devm_kzalloc(&pdev->dev, sizeof(struct fixed_voltage_data),
+			       GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
 	if (pdev->dev.of_node) {
-		config = of_get_fixed_voltage_config(&pdev->dev);
+		config = of_get_fixed_voltage_config(&pdev->dev,
+						     &drvdata->desc);
 		if (IS_ERR(config))
 			return PTR_ERR(config);
 	} else {
@@ -123,11 +131,6 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev)
 	if (!config)
 		return -ENOMEM;
 
-	drvdata = devm_kzalloc(&pdev->dev, sizeof(struct fixed_voltage_data),
-			       GFP_KERNEL);
-	if (!drvdata)
-		return -ENOMEM;
-
 	drvdata->desc.name = devm_kstrdup(&pdev->dev,
 					  config->supply_name,
 					  GFP_KERNEL);
diff --git a/drivers/regulator/gpio-regulator.c b/drivers/regulator/gpio-regulator.c
index 989b23b377c..5c3bcae478b 100644
--- a/drivers/regulator/gpio-regulator.c
+++ b/drivers/regulator/gpio-regulator.c
@@ -133,7 +133,8 @@ static struct regulator_ops gpio_regulator_voltage_ops = {
 };
 
 static struct gpio_regulator_config *
-of_get_gpio_regulator_config(struct device *dev, struct device_node *np)
+of_get_gpio_regulator_config(struct device *dev, struct device_node *np,
+			     const struct regulator_desc *desc)
 {
 	struct gpio_regulator_config *config;
 	const char *regtype;
@@ -146,7 +147,7 @@ of_get_gpio_regulator_config(struct device *dev, struct device_node *np)
 	if (!config)
 		return ERR_PTR(-ENOMEM);
 
-	config->init_data = of_get_regulator_init_data(dev, np);
+	config->init_data = of_get_regulator_init_data(dev, np, desc);
 	if (!config->init_data)
 		return ERR_PTR(-EINVAL);
 
@@ -243,17 +244,18 @@ static int gpio_regulator_probe(struct platform_device *pdev)
 	struct regulator_config cfg = { };
 	int ptr, ret, state;
 
-	if (np) {
-		config = of_get_gpio_regulator_config(&pdev->dev, np);
-		if (IS_ERR(config))
-			return PTR_ERR(config);
-	}
-
 	drvdata = devm_kzalloc(&pdev->dev, sizeof(struct gpio_regulator_data),
 			       GFP_KERNEL);
 	if (drvdata == NULL)
 		return -ENOMEM;
 
+	if (np) {
+		config = of_get_gpio_regulator_config(&pdev->dev, np,
+						      &drvdata->desc);
+		if (IS_ERR(config))
+			return PTR_ERR(config);
+	}
+
 	drvdata->desc.name = kstrdup(config->supply_name, GFP_KERNEL);
 	if (drvdata->desc.name == NULL) {
 		dev_err(&pdev->dev, "Failed to allocate supply name\n");
diff --git a/drivers/regulator/max8952.c b/drivers/regulator/max8952.c
index f7f9efcfedb..6e54d786b22 100644
--- a/drivers/regulator/max8952.c
+++ b/drivers/regulator/max8952.c
@@ -174,7 +174,7 @@ static struct max8952_platform_data *max8952_parse_dt(struct device *dev)
 	if (of_property_read_u32(np, "max8952,ramp-speed", &pd->ramp_speed))
 		dev_warn(dev, "max8952,ramp-speed property not specified, defaulting to 32mV/us\n");
 
-	pd->reg_data = of_get_regulator_init_data(dev, np);
+	pd->reg_data = of_get_regulator_init_data(dev, np, &regulator);
 	if (!pd->reg_data) {
 		dev_err(dev, "Failed to parse regulator init data\n");
 		return NULL;
diff --git a/drivers/regulator/max8973-regulator.c b/drivers/regulator/max8973-regulator.c
index dbedf1768db..c3d55c2db59 100644
--- a/drivers/regulator/max8973-regulator.c
+++ b/drivers/regulator/max8973-regulator.c
@@ -458,7 +458,8 @@ static int max8973_probe(struct i2c_client *client,
 
 	config.dev = &client->dev;
 	config.init_data = pdata ? pdata->reg_init_data :
-		of_get_regulator_init_data(&client->dev, client->dev.of_node);
+		of_get_regulator_init_data(&client->dev, client->dev.of_node,
+					   &max->desc);
 	config.driver_data = max;
 	config.of_node = client->dev.of_node;
 	config.regmap = max->regmap;
diff --git a/drivers/regulator/max8997.c b/drivers/regulator/max8997.c
index 9c31e215a52..726fde1d883 100644
--- a/drivers/regulator/max8997.c
+++ b/drivers/regulator/max8997.c
@@ -953,7 +953,8 @@ static int max8997_pmic_dt_parse_pdata(struct platform_device *pdev,
 
 		rdata->id = i;
 		rdata->initdata = of_get_regulator_init_data(&pdev->dev,
-							     reg_np);
+							     reg_np,
+							     &regulators[i]);
 		rdata->reg_node = reg_np;
 		rdata++;
 	}
diff --git a/drivers/regulator/max8998.c b/drivers/regulator/max8998.c
index 961091b4655..59e34a05a4a 100644
--- a/drivers/regulator/max8998.c
+++ b/drivers/regulator/max8998.c
@@ -686,8 +686,9 @@ static int max8998_pmic_dt_parse_pdata(struct max8998_dev *iodev,
 			continue;
 
 		rdata->id = regulators[i].id;
-		rdata->initdata = of_get_regulator_init_data(
-							iodev->dev, reg_np);
+		rdata->initdata = of_get_regulator_init_data(iodev->dev,
+							     reg_np,
+							     &regulators[i]);
 		rdata->reg_node = reg_np;
 		++rdata;
 	}
diff --git a/drivers/regulator/mc13xxx-regulator-core.c b/drivers/regulator/mc13xxx-regulator-core.c
index afba024953e..0281c31ae2e 100644
--- a/drivers/regulator/mc13xxx-regulator-core.c
+++ b/drivers/regulator/mc13xxx-regulator-core.c
@@ -194,7 +194,8 @@ struct mc13xxx_regulator_init_data *mc13xxx_parse_regulators_dt(
 					 regulators[i].desc.name)) {
 				p->id = i;
 				p->init_data = of_get_regulator_init_data(
-							&pdev->dev, child);
+							&pdev->dev, child,
+							&regulators[i].desc);
 				p->node = child;
 				p++;
 
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 50be70878d2..3687a1c38c1 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -120,13 +120,16 @@ static void of_get_regulation_constraints(struct device_node *np,
 /**
  * of_get_regulator_init_data - extract regulator_init_data structure info
  * @dev: device requesting for regulator_init_data
+ * @node: regulator device node
+ * @desc: regulator description
  *
  * Populates regulator_init_data structure by extracting data from device
  * tree node, returns a pointer to the populated struture or NULL if memory
  * alloc fails.
  */
 struct regulator_init_data *of_get_regulator_init_data(struct device *dev,
-						struct device_node *node)
+					  struct device_node *node,
+					  const struct regulator_desc *desc)
 {
 	struct regulator_init_data *init_data;
 
@@ -218,7 +221,7 @@ int of_regulator_match(struct device *dev, struct device_node *node,
 				continue;
 
 			match->init_data =
-				of_get_regulator_init_data(dev, child);
+				of_get_regulator_init_data(dev, child, NULL);
 			if (!match->init_data) {
 				dev_err(dev,
 					"failed to parse DT for regulator %s\n",
@@ -265,7 +268,7 @@ struct regulator_init_data *regulator_of_get_init_data(struct device *dev,
 		if (strcmp(desc->of_match, name))
 			continue;
 
-		init_data = of_get_regulator_init_data(dev, child);
+		init_data = of_get_regulator_init_data(dev, child, desc);
 		if (!init_data) {
 			dev_err(dev,
 				"failed to parse DT for regulator %s\n",
diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c
index d3f55eaea05..91f34ca3a9a 100644
--- a/drivers/regulator/pwm-regulator.c
+++ b/drivers/regulator/pwm-regulator.c
@@ -149,7 +149,8 @@ static int pwm_regulator_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	config.init_data = of_get_regulator_init_data(&pdev->dev, np);
+	config.init_data = of_get_regulator_init_data(&pdev->dev, np,
+						      &drvdata->desc);
 	if (!config.init_data)
 		return -ENOMEM;
 
diff --git a/drivers/regulator/qcom_rpm-regulator.c b/drivers/regulator/qcom_rpm-regulator.c
index b55cd5b50eb..dabd28a359d 100644
--- a/drivers/regulator/qcom_rpm-regulator.c
+++ b/drivers/regulator/qcom_rpm-regulator.c
@@ -643,10 +643,6 @@ static int rpm_reg_probe(struct platform_device *pdev)
 	match = of_match_device(rpm_of_match, &pdev->dev);
 	template = match->data;
 
-	initdata = of_get_regulator_init_data(&pdev->dev, pdev->dev.of_node);
-	if (!initdata)
-		return -EINVAL;
-
 	vreg = devm_kmalloc(&pdev->dev, sizeof(*vreg), GFP_KERNEL);
 	if (!vreg) {
 		dev_err(&pdev->dev, "failed to allocate vreg\n");
@@ -666,6 +662,11 @@ static int rpm_reg_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
+	initdata = of_get_regulator_init_data(&pdev->dev, pdev->dev.of_node,
+					      &vreg->desc);
+	if (!initdata)
+		return -EINVAL;
+
 	key = "reg";
 	ret = of_property_read_u32(pdev->dev.of_node, key, &val);
 	if (ret) {
diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c
index 0ab5cbeeb79..26932fe42b4 100644
--- a/drivers/regulator/s5m8767.c
+++ b/drivers/regulator/s5m8767.c
@@ -581,7 +581,8 @@ static int s5m8767_pmic_dt_parse_pdata(struct platform_device *pdev,
 
 		rdata->id = i;
 		rdata->initdata = of_get_regulator_init_data(
-						&pdev->dev, reg_np);
+						&pdev->dev, reg_np,
+						&regulators[i]);
 		rdata->reg_node = reg_np;
 		rdata++;
 		rmode->id = i;
diff --git a/drivers/regulator/sky81452-regulator.c b/drivers/regulator/sky81452-regulator.c
index 97aff0ccd65..75deae706f8 100644
--- a/drivers/regulator/sky81452-regulator.c
+++ b/drivers/regulator/sky81452-regulator.c
@@ -76,7 +76,7 @@ static struct regulator_init_data *sky81452_reg_parse_dt(struct device *dev)
 		return NULL;
 	}
 
-	init_data = of_get_regulator_init_data(dev, np);
+	init_data = of_get_regulator_init_data(dev, np, &sky81452_reg);
 
 	of_node_put(np);
 	return init_data;
diff --git a/drivers/regulator/stw481x-vmmc.c b/drivers/regulator/stw481x-vmmc.c
index a7e152696a0..b4f1696456a 100644
--- a/drivers/regulator/stw481x-vmmc.c
+++ b/drivers/regulator/stw481x-vmmc.c
@@ -72,7 +72,8 @@ static int stw481x_vmmc_regulator_probe(struct platform_device *pdev)
 	config.regmap = stw481x->map;
 	config.of_node = pdev->dev.of_node;
 	config.init_data = of_get_regulator_init_data(&pdev->dev,
-						      pdev->dev.of_node);
+						      pdev->dev.of_node,
+						      &vmmc_regulator);
 
 	stw481x->vmmc_regulator = devm_regulator_register(&pdev->dev,
 						&vmmc_regulator, &config);
diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c
index a2dabb575b9..1ef5aba96f1 100644
--- a/drivers/regulator/ti-abb-regulator.c
+++ b/drivers/regulator/ti-abb-regulator.c
@@ -837,7 +837,8 @@ skip_opt:
 		return -EINVAL;
 	}
 
-	initdata = of_get_regulator_init_data(dev, pdev->dev.of_node);
+	initdata = of_get_regulator_init_data(dev, pdev->dev.of_node,
+					      &abb->rdesc);
 	if (!initdata) {
 		dev_err(dev, "%s: Unable to alloc regulator init data\n",
 			__func__);
diff --git a/drivers/regulator/tps51632-regulator.c b/drivers/regulator/tps51632-regulator.c
index f31f22e3e1b..c213e37eb69 100644
--- a/drivers/regulator/tps51632-regulator.c
+++ b/drivers/regulator/tps51632-regulator.c
@@ -221,7 +221,8 @@ static const struct of_device_id tps51632_of_match[] = {
 MODULE_DEVICE_TABLE(of, tps51632_of_match);
 
 static struct tps51632_regulator_platform_data *
-	of_get_tps51632_platform_data(struct device *dev)
+	of_get_tps51632_platform_data(struct device *dev,
+				      const struct regulator_desc *desc)
 {
 	struct tps51632_regulator_platform_data *pdata;
 	struct device_node *np = dev->of_node;
@@ -230,7 +231,8 @@ static struct tps51632_regulator_platform_data *
 	if (!pdata)
 		return NULL;
 
-	pdata->reg_init_data = of_get_regulator_init_data(dev, dev->of_node);
+	pdata->reg_init_data = of_get_regulator_init_data(dev, dev->of_node,
+							  desc);
 	if (!pdata->reg_init_data) {
 		dev_err(dev, "Not able to get OF regulator init data\n");
 		return NULL;
@@ -248,7 +250,8 @@ static struct tps51632_regulator_platform_data *
 }
 #else
 static struct tps51632_regulator_platform_data *
-	of_get_tps51632_platform_data(struct device *dev)
+	of_get_tps51632_platform_data(struct device *dev,
+				      const struct regulator_desc *desc)
 {
 	return NULL;
 }
@@ -273,9 +276,25 @@ static int tps51632_probe(struct i2c_client *client,
 		}
 	}
 
+	tps = devm_kzalloc(&client->dev, sizeof(*tps), GFP_KERNEL);
+	if (!tps)
+		return -ENOMEM;
+
+	tps->dev = &client->dev;
+	tps->desc.name = client->name;
+	tps->desc.id = 0;
+	tps->desc.ramp_delay = TPS51632_DEFAULT_RAMP_DELAY;
+	tps->desc.min_uV = TPS51632_MIN_VOLTAGE;
+	tps->desc.uV_step = TPS51632_VOLTAGE_STEP_10mV;
+	tps->desc.linear_min_sel = TPS51632_MIN_VSEL;
+	tps->desc.n_voltages = TPS51632_MAX_VSEL + 1;
+	tps->desc.ops = &tps51632_dcdc_ops;
+	tps->desc.type = REGULATOR_VOLTAGE;
+	tps->desc.owner = THIS_MODULE;
+
 	pdata = dev_get_platdata(&client->dev);
 	if (!pdata && client->dev.of_node)
-		pdata = of_get_tps51632_platform_data(&client->dev);
+		pdata = of_get_tps51632_platform_data(&client->dev, &tps->desc);
 	if (!pdata) {
 		dev_err(&client->dev, "No Platform data\n");
 		return -EINVAL;
@@ -296,22 +315,6 @@ static int tps51632_probe(struct i2c_client *client,
 		}
 	}
 
-	tps = devm_kzalloc(&client->dev, sizeof(*tps), GFP_KERNEL);
-	if (!tps)
-		return -ENOMEM;
-
-	tps->dev = &client->dev;
-	tps->desc.name = client->name;
-	tps->desc.id = 0;
-	tps->desc.ramp_delay = TPS51632_DEFAULT_RAMP_DELAY;
-	tps->desc.min_uV = TPS51632_MIN_VOLTAGE;
-	tps->desc.uV_step = TPS51632_VOLTAGE_STEP_10mV;
-	tps->desc.linear_min_sel = TPS51632_MIN_VSEL;
-	tps->desc.n_voltages = TPS51632_MAX_VSEL + 1;
-	tps->desc.ops = &tps51632_dcdc_ops;
-	tps->desc.type = REGULATOR_VOLTAGE;
-	tps->desc.owner = THIS_MODULE;
-
 	if (pdata->enable_pwm_dvfs)
 		tps->desc.vsel_reg = TPS51632_VOLTAGE_BASE_REG;
 	else
diff --git a/drivers/regulator/tps62360-regulator.c b/drivers/regulator/tps62360-regulator.c
index a1672044e51..a1fd626c6c9 100644
--- a/drivers/regulator/tps62360-regulator.c
+++ b/drivers/regulator/tps62360-regulator.c
@@ -293,7 +293,8 @@ static const struct regmap_config tps62360_regmap_config = {
 };
 
 static struct tps62360_regulator_platform_data *
-	of_get_tps62360_platform_data(struct device *dev)
+	of_get_tps62360_platform_data(struct device *dev,
+				      const struct regulator_desc *desc)
 {
 	struct tps62360_regulator_platform_data *pdata;
 	struct device_node *np = dev->of_node;
@@ -302,7 +303,8 @@ static struct tps62360_regulator_platform_data *
 	if (!pdata)
 		return NULL;
 
-	pdata->reg_init_data = of_get_regulator_init_data(dev, dev->of_node);
+	pdata->reg_init_data = of_get_regulator_init_data(dev, dev->of_node,
+							  desc);
 	if (!pdata->reg_init_data) {
 		dev_err(dev, "Not able to get OF regulator init data\n");
 		return NULL;
@@ -350,6 +352,17 @@ static int tps62360_probe(struct i2c_client *client,
 
 	pdata = dev_get_platdata(&client->dev);
 
+	tps = devm_kzalloc(&client->dev, sizeof(*tps), GFP_KERNEL);
+	if (!tps)
+		return -ENOMEM;
+
+	tps->desc.name = client->name;
+	tps->desc.id = 0;
+	tps->desc.ops = &tps62360_dcdc_ops;
+	tps->desc.type = REGULATOR_VOLTAGE;
+	tps->desc.owner = THIS_MODULE;
+	tps->desc.uV_step = 10000;
+
 	if (client->dev.of_node) {
 		const struct of_device_id *match;
 		match = of_match_device(of_match_ptr(tps62360_of_match),
@@ -360,7 +373,8 @@ static int tps62360_probe(struct i2c_client *client,
 		}
 		chip_id = (int)(long)match->data;
 		if (!pdata)
-			pdata = of_get_tps62360_platform_data(&client->dev);
+			pdata = of_get_tps62360_platform_data(&client->dev,
+							      &tps->desc);
 	} else if (id) {
 		chip_id = id->driver_data;
 	} else {
@@ -374,10 +388,6 @@ static int tps62360_probe(struct i2c_client *client,
 		return -EIO;
 	}
 
-	tps = devm_kzalloc(&client->dev, sizeof(*tps), GFP_KERNEL);
-	if (!tps)
-		return -ENOMEM;
-
 	tps->en_discharge = pdata->en_discharge;
 	tps->en_internal_pulldn = pdata->en_internal_pulldn;
 	tps->vsel0_gpio = pdata->vsel0_gpio;
@@ -401,13 +411,6 @@ static int tps62360_probe(struct i2c_client *client,
 		return -ENODEV;
 	}
 
-	tps->desc.name = client->name;
-	tps->desc.id = 0;
-	tps->desc.ops = &tps62360_dcdc_ops;
-	tps->desc.type = REGULATOR_VOLTAGE;
-	tps->desc.owner = THIS_MODULE;
-	tps->desc.uV_step = 10000;
-
 	tps->regmap = devm_regmap_init_i2c(client, &tps62360_regmap_config);
 	if (IS_ERR(tps->regmap)) {
 		ret = PTR_ERR(tps->regmap);
diff --git a/drivers/regulator/tps65218-regulator.c b/drivers/regulator/tps65218-regulator.c
index f0a40281b9c..263cc85d620 100644
--- a/drivers/regulator/tps65218-regulator.c
+++ b/drivers/regulator/tps65218-regulator.c
@@ -231,7 +231,8 @@ static int tps65218_regulator_probe(struct platform_device *pdev)
 
 	template = match->data;
 	id = template->id;
-	init_data = of_get_regulator_init_data(&pdev->dev, pdev->dev.of_node);
+	init_data = of_get_regulator_init_data(&pdev->dev, pdev->dev.of_node,
+					       &regulators[id]);
 
 	platform_set_drvdata(pdev, tps);
 
diff --git a/drivers/regulator/twl-regulator.c b/drivers/regulator/twl-regulator.c
index 0b4f8660fdb..dd727bca198 100644
--- a/drivers/regulator/twl-regulator.c
+++ b/drivers/regulator/twl-regulator.c
@@ -1104,7 +1104,8 @@ static int twlreg_probe(struct platform_device *pdev)
 		template = match->data;
 		id = template->desc.id;
 		initdata = of_get_regulator_init_data(&pdev->dev,
-						      pdev->dev.of_node);
+						      pdev->dev.of_node,
+						      &template->desc);
 		drvdata = NULL;
 	} else {
 		id = pdev->id;
diff --git a/drivers/regulator/vexpress.c b/drivers/regulator/vexpress.c
index 02e7267ccf9..5e7c789023a 100644
--- a/drivers/regulator/vexpress.c
+++ b/drivers/regulator/vexpress.c
@@ -74,7 +74,8 @@ static int vexpress_regulator_probe(struct platform_device *pdev)
 	reg->desc.owner = THIS_MODULE;
 	reg->desc.continuous_voltage_range = true;
 
-	init_data = of_get_regulator_init_data(&pdev->dev, pdev->dev.of_node);
+	init_data = of_get_regulator_init_data(&pdev->dev, pdev->dev.of_node,
+					       &reg->desc);
 	if (!init_data)
 		return -EINVAL;
 
diff --git a/include/linux/regulator/of_regulator.h b/include/linux/regulator/of_regulator.h
index f9217965aaa..8d1d136c0fb 100644
--- a/include/linux/regulator/of_regulator.h
+++ b/include/linux/regulator/of_regulator.h
@@ -6,6 +6,8 @@
 #ifndef __LINUX_OF_REG_H
 #define __LINUX_OF_REG_H
 
+struct regulator_desc;
+
 struct of_regulator_match {
 	const char *name;
 	void *driver_data;
@@ -16,14 +18,16 @@ struct of_regulator_match {
 #if defined(CONFIG_OF)
 extern struct regulator_init_data
 	*of_get_regulator_init_data(struct device *dev,
-				    struct device_node *node);
+				    struct device_node *node,
+				    const struct regulator_desc *desc);
 extern int of_regulator_match(struct device *dev, struct device_node *node,
 			      struct of_regulator_match *matches,
 			      unsigned int num_matches);
 #else
 static inline struct regulator_init_data
 	*of_get_regulator_init_data(struct device *dev,
-				    struct device_node *node)
+				    struct device_node *node,
+				    const struct regulator_desc *desc)
 {
 	return NULL;
 }
-- 
cgit v1.2.3-70-g09d2


From 75d6b2faf79cbe9086e831351d5d9085f1852928 Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Date: Mon, 10 Nov 2014 14:43:54 +0100
Subject: regulator: of: Pass the regulator description in the match table

Drivers can use the of_regulator_match() function to parse the regulator
init_data from DT. A match table is used to specify the name of the node
containing the regulators, the device node and to return the init_data
to the caller.

But also the static regulator descriptor is needed to correctly extract
some DT properties like the regulator initial and suspend modes. Use the
match table to pass that information.

Signed-off-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/of_regulator.c       | 3 ++-
 include/linux/regulator/of_regulator.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 3687a1c38c1..64c09a37ac7 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -221,7 +221,8 @@ int of_regulator_match(struct device *dev, struct device_node *node,
 				continue;
 
 			match->init_data =
-				of_get_regulator_init_data(dev, child, NULL);
+				of_get_regulator_init_data(dev, child,
+							   match->desc);
 			if (!match->init_data) {
 				dev_err(dev,
 					"failed to parse DT for regulator %s\n",
diff --git a/include/linux/regulator/of_regulator.h b/include/linux/regulator/of_regulator.h
index 8d1d136c0fb..763953f7e3b 100644
--- a/include/linux/regulator/of_regulator.h
+++ b/include/linux/regulator/of_regulator.h
@@ -13,6 +13,7 @@ struct of_regulator_match {
 	void *driver_data;
 	struct regulator_init_data *init_data;
 	struct device_node *of_node;
+	const struct regulator_desc *desc;
 };
 
 #if defined(CONFIG_OF)
-- 
cgit v1.2.3-70-g09d2


From 98f0334263f177dd22ca7c685cde04b47cc57b05 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 26 Nov 2014 12:42:02 +0100
Subject: cfg80211: clean up beacon loss CQM event

Having it as a sub-event for RSSI thresholds is very ugly,
but luckily no userspace actually uses the events yet.

Move the event to its own function call internally and to
its own event attribute in nl80211.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ti/wlcore/event.c |  5 +----
 include/net/cfg80211.h                 |  9 +++++++++
 include/net/mac80211.h                 |  8 ++++++++
 include/uapi/linux/nl80211.h           |  7 ++++---
 net/mac80211/mlme.c                    | 14 +++++++++++---
 net/mac80211/trace.h                   |  6 ++++++
 net/wireless/nl80211.c                 | 23 +++++++++++++++++++++++
 7 files changed, 62 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ti/wlcore/event.c b/drivers/net/wireless/ti/wlcore/event.c
index 16d10281798..5153640f453 100644
--- a/drivers/net/wireless/ti/wlcore/event.c
+++ b/drivers/net/wireless/ti/wlcore/event.c
@@ -259,10 +259,7 @@ void wlcore_event_beacon_loss(struct wl1271 *wl, unsigned long roles_bitmap)
 					     &wlvif->connection_loss_work,
 					     msecs_to_jiffies(delay));
 
-		ieee80211_cqm_rssi_notify(
-				vif,
-				NL80211_CQM_RSSI_BEACON_LOSS_EVENT,
-				GFP_KERNEL);
+		ieee80211_cqm_beacon_loss_notify(vif, GFP_KERNEL);
 	}
 }
 EXPORT_SYMBOL_GPL(wlcore_event_beacon_loss);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 1d15f1dfdaa..4ebb816241f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4669,6 +4669,15 @@ void cfg80211_cqm_pktloss_notify(struct net_device *dev,
 void cfg80211_cqm_txe_notify(struct net_device *dev, const u8 *peer,
 			     u32 num_packets, u32 rate, u32 intvl, gfp_t gfp);
 
+/**
+ * cfg80211_cqm_beacon_loss_notify - beacon loss event
+ * @dev: network device
+ * @gfp: context flags
+ *
+ * Notify userspace about beacon loss from the connected AP.
+ */
+void cfg80211_cqm_beacon_loss_notify(struct net_device *dev, gfp_t gfp);
+
 /**
  * cfg80211_radar_event - radar detection event
  * @wiphy: the wiphy
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index cff3a26a9da..66cbfe46428 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -4671,6 +4671,14 @@ void ieee80211_cqm_rssi_notify(struct ieee80211_vif *vif,
 			       enum nl80211_cqm_rssi_threshold_event rssi_event,
 			       gfp_t gfp);
 
+/**
+ * ieee80211_cqm_beacon_loss_notify - inform CQM of beacon loss
+ *
+ * @vif: &struct ieee80211_vif pointer from the add_interface callback.
+ * @gfp: context flags
+ */
+void ieee80211_cqm_beacon_loss_notify(struct ieee80211_vif *vif, gfp_t gfp);
+
 /**
  * ieee80211_radar_detected - inform that a radar was detected
  *
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index d7752451043..b37bd5a1cb8 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3451,6 +3451,8 @@ enum nl80211_ps_state {
  *	interval in which %NL80211_ATTR_CQM_TXE_PKTS and
  *	%NL80211_ATTR_CQM_TXE_RATE must be satisfied before generating an
  *	%NL80211_CMD_NOTIFY_CQM. Set to 0 to turn off TX error reporting.
+ * @NL80211_ATTR_CQM_BEACON_LOSS_EVENT: flag attribute that's set in a beacon
+ *	loss event
  * @__NL80211_ATTR_CQM_AFTER_LAST: internal
  * @NL80211_ATTR_CQM_MAX: highest key attribute
  */
@@ -3463,6 +3465,7 @@ enum nl80211_attr_cqm {
 	NL80211_ATTR_CQM_TXE_RATE,
 	NL80211_ATTR_CQM_TXE_PKTS,
 	NL80211_ATTR_CQM_TXE_INTVL,
+	NL80211_ATTR_CQM_BEACON_LOSS_EVENT,
 
 	/* keep last */
 	__NL80211_ATTR_CQM_AFTER_LAST,
@@ -3475,9 +3478,7 @@ enum nl80211_attr_cqm {
  *      configured threshold
  * @NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH: The RSSI is higher than the
  *      configured threshold
- * @NL80211_CQM_RSSI_BEACON_LOSS_EVENT: The device experienced beacon loss.
- *	(Note that deauth/disassoc will still follow if the AP is not
- *	available. This event might get used as roaming event, etc.)
+ * @NL80211_CQM_RSSI_BEACON_LOSS_EVENT: (reserved, never sent)
  */
 enum nl80211_cqm_rssi_threshold_event {
 	NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW,
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 36e39ed4dfd..8a23a64b9a6 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2266,9 +2266,7 @@ static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata,
 				     "detected beacon loss from AP (missed %d beacons) - probing\n",
 				     beacon_loss_count);
 
-		ieee80211_cqm_rssi_notify(&sdata->vif,
-					  NL80211_CQM_RSSI_BEACON_LOSS_EVENT,
-					  GFP_KERNEL);
+		ieee80211_cqm_beacon_loss_notify(&sdata->vif, GFP_KERNEL);
 	}
 
 	/*
@@ -4901,3 +4899,13 @@ void ieee80211_cqm_rssi_notify(struct ieee80211_vif *vif,
 	cfg80211_cqm_rssi_notify(sdata->dev, rssi_event, gfp);
 }
 EXPORT_SYMBOL(ieee80211_cqm_rssi_notify);
+
+void ieee80211_cqm_beacon_loss_notify(struct ieee80211_vif *vif, gfp_t gfp)
+{
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+
+	trace_api_cqm_beacon_loss_notify(sdata->local, sdata);
+
+	cfg80211_cqm_beacon_loss_notify(sdata->dev, gfp);
+}
+EXPORT_SYMBOL(ieee80211_cqm_beacon_loss_notify);
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 85ccfbe863d..8e461a02c6a 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -1829,6 +1829,12 @@ TRACE_EVENT(api_cqm_rssi_notify,
 	)
 );
 
+DEFINE_EVENT(local_sdata_evt, api_cqm_beacon_loss_notify,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata),
+	TP_ARGS(local, sdata)
+);
+
 TRACE_EVENT(api_scan_completed,
 	TP_PROTO(struct ieee80211_local *local, bool aborted),
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 9c4d0102d34..e11980e74a0 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -11826,6 +11826,10 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev,
 
 	trace_cfg80211_cqm_rssi_notify(dev, rssi_event);
 
+	if (WARN_ON(rssi_event != NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW &&
+		    rssi_event != NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH))
+		return;
+
 	msg = cfg80211_prepare_cqm(dev, NULL, gfp);
 	if (!msg)
 		return;
@@ -11892,6 +11896,25 @@ void cfg80211_cqm_pktloss_notify(struct net_device *dev,
 }
 EXPORT_SYMBOL(cfg80211_cqm_pktloss_notify);
 
+void cfg80211_cqm_beacon_loss_notify(struct net_device *dev, gfp_t gfp)
+{
+	struct sk_buff *msg;
+
+	msg = cfg80211_prepare_cqm(dev, NULL, gfp);
+	if (!msg)
+		return;
+
+	if (nla_put_flag(msg, NL80211_ATTR_CQM_BEACON_LOSS_EVENT))
+		goto nla_put_failure;
+
+	cfg80211_send_cqm(msg, gfp);
+	return;
+
+ nla_put_failure:
+	nlmsg_free(msg);
+}
+EXPORT_SYMBOL(cfg80211_cqm_beacon_loss_notify);
+
 static void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev,
 				     struct net_device *netdev, const u8 *bssid,
 				     const u8 *replay_ctr, gfp_t gfp)
-- 
cgit v1.2.3-70-g09d2


From f08bb472bff3c0397fb7d6f47bc5cec41dad76e3 Mon Sep 17 00:00:00 2001
From: Ashwin Chaugule <ashwin.chaugule@linaro.org>
Date: Wed, 26 Nov 2014 22:01:13 +0800
Subject: ACPI / table: Add new function to get table entries

The acpi_table_parse() function has a callback that
passes a pointer to a table_header. Add a new function
which takes this pointer and parses its entries. This
eliminates the need to re-traverse all the tables for
each call. e.g. as in acpi_table_parse_madt() which is
normally called after acpi_table_parse().

Acked-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Ashwin Chaugule <ashwin.chaugule@linaro.org>
Signed-off-by: Tomasz Nowicki <tomasz.nowicki@linaro.org>
Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/tables.c | 63 +++++++++++++++++++++++++++++++++++----------------
 include/linux/acpi.h  |  4 ++++
 2 files changed, 48 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index 6d5a6cda073..f1debe97dcf 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -190,30 +190,24 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
 	}
 }
 
-
 int __init
-acpi_table_parse_entries(char *id,
-			     unsigned long table_size,
-			     int entry_id,
-			     acpi_tbl_entry_handler handler,
-			     unsigned int max_entries)
+acpi_parse_entries(char *id, unsigned long table_size,
+		acpi_tbl_entry_handler handler,
+		struct acpi_table_header *table_header,
+		int entry_id, unsigned int max_entries)
 {
-	struct acpi_table_header *table_header = NULL;
 	struct acpi_subtable_header *entry;
-	unsigned int count = 0;
+	int count = 0;
 	unsigned long table_end;
-	acpi_size tbl_size;
 
 	if (acpi_disabled)
 		return -ENODEV;
 
-	if (!handler)
+	if (!id || !handler)
 		return -EINVAL;
 
-	if (strncmp(id, ACPI_SIG_MADT, 4) == 0)
-		acpi_get_table_with_size(id, acpi_apic_instance, &table_header, &tbl_size);
-	else
-		acpi_get_table_with_size(id, 0, &table_header, &tbl_size);
+	if (!table_size)
+		return -EINVAL;
 
 	if (!table_header) {
 		pr_warn("%4.4s not present\n", id);
@@ -232,7 +226,7 @@ acpi_table_parse_entries(char *id,
 		if (entry->type == entry_id
 		    && (!max_entries || count++ < max_entries))
 			if (handler(entry, table_end))
-				goto err;
+				return -EINVAL;
 
 		/*
 		 * If entry->length is 0, break from this loop to avoid
@@ -240,22 +234,53 @@ acpi_table_parse_entries(char *id,
 		 */
 		if (entry->length == 0) {
 			pr_err("[%4.4s:0x%02x] Invalid zero length\n", id, entry_id);
-			goto err;
+			return -EINVAL;
 		}
 
 		entry = (struct acpi_subtable_header *)
 		    ((unsigned long)entry + entry->length);
 	}
+
 	if (max_entries && count > max_entries) {
 		pr_warn("[%4.4s:0x%02x] ignored %i entries of %i found\n",
 			id, entry_id, count - max_entries, count);
 	}
 
-	early_acpi_os_unmap_memory((char *)table_header, tbl_size);
 	return count;
-err:
+}
+
+int __init
+acpi_table_parse_entries(char *id,
+			 unsigned long table_size,
+			 int entry_id,
+			 acpi_tbl_entry_handler handler,
+			 unsigned int max_entries)
+{
+	struct acpi_table_header *table_header = NULL;
+	acpi_size tbl_size;
+	int count;
+	u32 instance = 0;
+
+	if (acpi_disabled)
+		return -ENODEV;
+
+	if (!id || !handler)
+		return -EINVAL;
+
+	if (!strncmp(id, ACPI_SIG_MADT, 4))
+		instance = acpi_apic_instance;
+
+	acpi_get_table_with_size(id, instance, &table_header, &tbl_size);
+	if (!table_header) {
+		pr_warn("%4.4s not present\n", id);
+		return -ENODEV;
+	}
+
+	count = acpi_parse_entries(id, table_size, handler, table_header,
+			entry_id, max_entries);
+
 	early_acpi_os_unmap_memory((char *)table_header, tbl_size);
-	return -EINVAL;
+	return count;
 }
 
 int __init
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 407a12f663e..3bd0c59e1fb 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -123,6 +123,10 @@ int acpi_numa_init (void);
 
 int acpi_table_init (void);
 int acpi_table_parse(char *id, acpi_tbl_table_handler handler);
+int __init acpi_parse_entries(char *id, unsigned long table_size,
+			      acpi_tbl_entry_handler handler,
+			      struct acpi_table_header *table_header,
+			      int entry_id, unsigned int max_entries);
 int __init acpi_table_parse_entries(char *id, unsigned long table_size,
 				    int entry_id,
 				    acpi_tbl_entry_handler handler,
-- 
cgit v1.2.3-70-g09d2


From 8ee885a98e2653a7f9c84d37cd8c5b6edf21b77f Mon Sep 17 00:00:00 2001
From: Pankaj Dubey <pankaj.dubey@samsung.com>
Date: Thu, 13 Nov 2014 14:12:48 +0530
Subject: coresight: fixed comments in coresight.h

fixes following minor issues in code comments in coresight.h
- typo %s/enpoint/endpoint
- alignment of comment section for struct coresight_desc
- correction of comment for struct coresight_connection and
  struct coresight_device.

Signed-off-by: Pankaj Dubey <pankaj.dubey@samsung.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/coresight.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index bdde4199c74..5d3c54311f7 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -87,7 +87,7 @@ struct coresight_dev_subtype {
  * @cpu:	the CPU a source belongs to. Only applicable for ETM/PTMs.
  * @name:	name of the component as shown under sysfs.
  * @nr_inport:	number of input ports for this component.
- * @outports:	list of remote enpoint port number.
+ * @outports:	list of remote endpoint port number.
  * @child_names:name of all child components connected to this device.
  * @child_ports:child component port number the current component is
 		connected  to.
@@ -113,7 +113,7 @@ struct coresight_platform_data {
 		by @coresight_ops.
  * @pdata:	platform data collected from DT.
  * @dev:	The device entity associated to this component.
- * @groups	:operations specific to this component. These will end up
+ * @groups:	operations specific to this component. These will end up
 		in the component's sysfs sub-directory.
  */
 struct coresight_desc {
@@ -127,7 +127,6 @@ struct coresight_desc {
 
 /**
  * struct coresight_connection - representation of a single connection
- * @ref_count:	keeping count a port' references.
  * @outport:	a connection's output port number.
  * @chid_name:	remote component's name.
  * @child_port:	remote component's port number @output is connected to.
@@ -143,6 +142,7 @@ struct coresight_connection {
 
 /**
  * struct coresight_device - representation of a device as used by the framework
+ * @conns:	array of coresight_connections associated to this component.
  * @nr_inport:	number of input port associated to this component.
  * @nr_outport:	number of output port associated to this component.
  * @type:	as defined by @coresight_dev_type.
-- 
cgit v1.2.3-70-g09d2


From 5b48e0605a84c3d2ccd06f6218df90e737c10559 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Wed, 26 Nov 2014 14:47:09 -0800
Subject: spmi: Remove shutdown/suspend/resume kernel-doc

These members of the driver structure are not present.
Remove them from the kernel-doc.

Cc: Josh Cartwright <joshc@codeaurora.org>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/spmi.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/spmi.h b/include/linux/spmi.h
index 91f5eab9e42..f84212cd3b7 100644
--- a/include/linux/spmi.h
+++ b/include/linux/spmi.h
@@ -134,9 +134,6 @@ void spmi_controller_remove(struct spmi_controller *ctrl);
  *		this structure.
  * @probe:	binds this driver to a SPMI device.
  * @remove:	unbinds this driver from the SPMI device.
- * @shutdown:	standard shutdown callback used during powerdown/halt.
- * @suspend:	standard suspend callback used during system suspend.
- * @resume:	standard resume callback used during system resume.
  *
  * If PM runtime support is desired for a slave, a device driver can call
  * pm_runtime_put() from their probe() routine (and a balancing
-- 
cgit v1.2.3-70-g09d2


From 98210b7f73f1db182bd9a558a031093cd166e907 Mon Sep 17 00:00:00 2001
From: Arend van Spriel <arend@broadcom.com>
Date: Sun, 9 Nov 2014 11:31:58 +0100
Subject: debugfs: add helper function to create device related seq_file

This patch adds a helper function that simplifies adding a
so-called single_open sequence file for device drivers. The
calling device driver needs to provide a read function and
a device pointer. The field struct seq_file::private will
reference the device pointer upon call to the read function
so the driver can obtain his data from it and do its task
of providing the file content using seq_printf() calls and
alike. Using this helper function also gets rid of the need
to specify file operations per debugfs file.

Signed-off-by: Arend van Spriel <arend@broadcom.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/debugfs/file.c       | 54 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/debugfs.h | 16 ++++++++++++++-
 2 files changed, 69 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 76c08c2beb2..a2f8ec70fe8 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -22,6 +22,7 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/atomic.h>
+#include <linux/device.h>
 
 static ssize_t default_read_file(struct file *file, char __user *buf,
 				 size_t count, loff_t *ppos)
@@ -761,3 +762,56 @@ struct dentry *debugfs_create_regset32(const char *name, umode_t mode,
 EXPORT_SYMBOL_GPL(debugfs_create_regset32);
 
 #endif /* CONFIG_HAS_IOMEM */
+
+struct debugfs_devm_entry {
+	int (*read)(struct seq_file *seq, void *data);
+	struct device *dev;
+};
+
+static int debugfs_devm_entry_open(struct inode *inode, struct file *f)
+{
+	struct debugfs_devm_entry *entry = inode->i_private;
+
+	return single_open(f, entry->read, entry->dev);
+}
+
+static const struct file_operations debugfs_devm_entry_ops = {
+	.owner = THIS_MODULE,
+	.open = debugfs_devm_entry_open,
+	.release = single_release,
+	.read = seq_read,
+	.llseek = seq_lseek
+};
+
+/**
+ * debugfs_create_devm_seqfile - create a debugfs file that is bound to device.
+ *
+ * @dev: device related to this debugfs file.
+ * @name: name of the debugfs file.
+ * @parent: a pointer to the parent dentry for this file.  This should be a
+ *	directory dentry if set.  If this parameter is %NULL, then the
+ *	file will be created in the root of the debugfs filesystem.
+ * @read_fn: function pointer called to print the seq_file content.
+ */
+struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name,
+					   struct dentry *parent,
+					   int (*read_fn)(struct seq_file *s,
+							  void *data))
+{
+	struct debugfs_devm_entry *entry;
+
+	if (IS_ERR(parent))
+		return ERR_PTR(-ENOENT);
+
+	entry = devm_kzalloc(dev, sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return ERR_PTR(-ENOMEM);
+
+	entry->read = read_fn;
+	entry->dev = dev;
+
+	return debugfs_create_file(name, S_IRUGO, parent, entry,
+				   &debugfs_devm_entry_ops);
+}
+EXPORT_SYMBOL_GPL(debugfs_create_devm_seqfile);
+
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index 4d0b4d1aa13..4bbe2ace972 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -99,13 +99,18 @@ struct dentry *debugfs_create_u32_array(const char *name, umode_t mode,
 					struct dentry *parent,
 					u32 *array, u32 elements);
 
+struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name,
+					   struct dentry *parent,
+					   int (*read_fn)(struct seq_file *s,
+							  void *data));
+
 bool debugfs_initialized(void);
 
 #else
 
 #include <linux/err.h>
 
-/* 
+/*
  * We do not return NULL from these functions if CONFIG_DEBUG_FS is not enabled
  * so users have a chance to detect if there was a real error or not.  We don't
  * want to duplicate the design decision mistakes of procfs and devfs again.
@@ -251,6 +256,15 @@ static inline struct dentry *debugfs_create_u32_array(const char *name, umode_t
 	return ERR_PTR(-ENODEV);
 }
 
+static inline struct dentry *debugfs_create_devm_seqfile(struct device *dev,
+							 const char *name,
+							 struct dentry *parent,
+					   int (*read_fn)(struct seq_file *s,
+							  void *data))
+{
+	return ERR_PTR(-ENODEV);
+}
+
 #endif
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From e135303bd5bebcd22bcf8a6b06ec0dd5a9432708 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 17 Nov 2014 18:18:22 -0800
Subject: device: Add dev_<level>_once variants

Add the equivalents to pr_<level>_once.

Suggested-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/device.h | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

(limited to 'include')

diff --git a/include/linux/device.h b/include/linux/device.h
index ce1f21608b1..99fb07cb4f0 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1118,6 +1118,41 @@ do {						     \
 })
 #endif
 
+#ifdef CONFIG_PRINTK
+#define dev_level_once(dev_level, dev, fmt, ...)			\
+do {									\
+	static bool __print_once __read_mostly;				\
+									\
+	if (!__print_once) {						\
+		__print_once = true;					\
+		dev_level(dev, fmt, ##__VA_ARGS__);			\
+	}								\
+} while (0)
+#else
+#define dev_level_once(dev_level, dev, fmt, ...)			\
+do {									\
+	if (0)								\
+		dev_level(dev, fmt, ##__VA_ARGS__);			\
+} while (0)
+#endif
+
+#define dev_emerg_once(dev, fmt, ...)					\
+	dev_level_once(dev_emerg, dev, fmt, ##__VA_ARGS__)
+#define dev_alert_once(dev, fmt, ...)					\
+	dev_level_once(dev_alert, dev, fmt, ##__VA_ARGS__)
+#define dev_crit_once(dev, fmt, ...)					\
+	dev_level_once(dev_crit, dev, fmt, ##__VA_ARGS__)
+#define dev_err_once(dev, fmt, ...)					\
+	dev_level_once(dev_err, dev, fmt, ##__VA_ARGS__)
+#define dev_warn_once(dev, fmt, ...)					\
+	dev_level_once(dev_warn, dev, fmt, ##__VA_ARGS__)
+#define dev_notice_once(dev, fmt, ...)					\
+	dev_level_once(dev_notice, dev, fmt, ##__VA_ARGS__)
+#define dev_info_once(dev, fmt, ...)					\
+	dev_level_once(dev_info, dev, fmt, ##__VA_ARGS__)
+#define dev_dbg_once(dev, fmt, ...)					\
+	dev_level_once(dev_info, dev, fmt, ##__VA_ARGS__)
+
 #define dev_level_ratelimited(dev_level, dev, fmt, ...)			\
 do {									\
 	static DEFINE_RATELIMIT_STATE(_rs,				\
-- 
cgit v1.2.3-70-g09d2


From 97b0c7bd2e86c6e1e00c6b7178cf953d5f70c71a Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Tue, 11 Nov 2014 18:33:01 +0000
Subject: mailbox: add tx_prepare client callback

If the mailbox controller expects the payload is in place before
initiating the transmit, then it's impossible to reuse the list
maintained by core mailbox code currently. Maintaining another list
for sending the message in the controller seems totally unnecessary
as core mailbox library already provides that feature.

This patch introduces tx_prepare callback in mbox_client which
can be used by the core mailbox library before initiating the
transaction through mbox->ops->send_data. The client driver can
implement this callback to ensure the payload is copied to the
shared memory.

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/mailbox.c      | 2 ++
 include/linux/mailbox_client.h | 3 +++
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c
index c281e556287..58789b02770 100644
--- a/drivers/mailbox/mailbox.c
+++ b/drivers/mailbox/mailbox.c
@@ -78,6 +78,8 @@ static void msg_submit(struct mbox_chan *chan)
 
 	data = chan->msg_data[idx];
 
+	if (chan->cl->tx_prepare)
+		chan->cl->tx_prepare(chan->cl, data);
 	/* Try to submit a message to the MBOX controller */
 	err = chan->mbox->ops->send_data(chan, data);
 	if (!err) {
diff --git a/include/linux/mailbox_client.h b/include/linux/mailbox_client.h
index 307d9cab202..1726ccbd800 100644
--- a/include/linux/mailbox_client.h
+++ b/include/linux/mailbox_client.h
@@ -25,6 +25,8 @@ struct mbox_chan;
  *			if the client receives some ACK packet for transmission.
  *			Unused if the controller already has TX_Done/RTR IRQ.
  * @rx_callback:	Atomic callback to provide client the data received
+ * @tx_prepare: 	Atomic callback to ask client to prepare the payload
+ *			before initiating the transmission if required.
  * @tx_done:		Atomic callback to tell client of data transmission
  */
 struct mbox_client {
@@ -34,6 +36,7 @@ struct mbox_client {
 	bool knows_txdone;
 
 	void (*rx_callback)(struct mbox_client *cl, void *mssg);
+	void (*tx_prepare)(struct mbox_client *cl, void *mssg);
 	void (*tx_done)(struct mbox_client *cl, void *mssg, int r);
 };
 
-- 
cgit v1.2.3-70-g09d2


From 8841a66aaa7c3b1dfeeb4192d05f2ca86df58f00 Mon Sep 17 00:00:00 2001
From: Suman Anna <s-anna@ti.com>
Date: Mon, 3 Nov 2014 17:05:50 -0600
Subject: mailbox/omap: adapt to the new mailbox framework

The OMAP mailbox driver and its existing clients (remoteproc
for OMAP4+) are adapted to use the generic mailbox framework.

The main changes for the adaptation are:
  - The tasklet used for Tx is replaced with the state machine from
    the generic mailbox framework. The workqueue used for processing
    the received messages stays intact for minimizing the effects on
    the OMAP mailbox clients.
  - The existing exported client API, omap_mbox_get, omap_mbox_put and
    omap_mbox_send_msg are deleted, as the framework provides equivalent
    functionality. A OMAP-specific omap_mbox_request_channel is added
    though to support non-DT way of requesting mailboxes.
  - The OMAP mailbox driver is integrated with the mailbox framework
    through the proper implementations of mbox_chan_ops, except for
    .last_tx_done and .peek_data. The OMAP mailbox driver does not need
    these ops, as it is completely interrupt driven.
  - The OMAP mailbox driver uses a custom of_xlate controller ops that
    allows phandles for the pargs specifier instead of indexing to avoid
    any channel registration order dependencies.
  - The new framework does not support multiple clients operating on a
    single channel, so the reference counting logic is simplified.
  - The remoteproc driver (current client) is adapted to use the new API.
    The notifier callbacks used within this client is replaced with the
    regular callbacks from the newer framework.
  - The exported OMAP mailbox API are limited to omap_mbox_save_ctx,
    omap_mbox_restore_ctx, omap_mbox_enable_irq & omap_mbox_disable_irq,
    with the signature modified to take in the new mbox_chan handle instead
    of the OMAP specific omap_mbox handle. The first 2 will be removed when
    the OMAP mailbox driver is adapted to runtime_pm. The other exported
    API omap_mbox_request_channel will be removed once existing legacy
    users are converted to DT.

Signed-off-by: Suman Anna <s-anna@ti.com>
Cc: Ohad Ben-Cohen <ohad@wizery.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 .../devicetree/bindings/mailbox/omap-mailbox.txt   |  23 ++
 drivers/mailbox/omap-mailbox.c                     | 346 ++++++++++++---------
 drivers/remoteproc/omap_remoteproc.c               |  51 +--
 include/linux/omap-mailbox.h                       |  16 +-
 4 files changed, 256 insertions(+), 180 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/mailbox/omap-mailbox.txt b/Documentation/devicetree/bindings/mailbox/omap-mailbox.txt
index 48edc4b92af..d1a043339c1 100644
--- a/Documentation/devicetree/bindings/mailbox/omap-mailbox.txt
+++ b/Documentation/devicetree/bindings/mailbox/omap-mailbox.txt
@@ -43,6 +43,9 @@ Required properties:
 			device. The format is dependent on which interrupt
 			controller the OMAP device uses
 - ti,hwmods:		Name of the hwmod associated with the mailbox
+- #mbox-cells:		Common mailbox binding property to identify the number
+			of cells required for the mailbox specifier. Should be
+			1
 - ti,mbox-num-users:	Number of targets (processor devices) that the mailbox
 			device can interrupt
 - ti,mbox-num-fifos:	Number of h/w fifo queues within the mailbox IP block
@@ -72,6 +75,18 @@ data that represent the following:
     Cell #3 (usr_id)  - mailbox user id for identifying the interrupt line
                         associated with generating a tx/rx fifo interrupt.
 
+Mailbox Users:
+==============
+A device needing to communicate with a target processor device should specify
+them using the common mailbox binding properties, "mboxes" and the optional
+"mbox-names" (please see Documentation/devicetree/bindings/mailbox/mailbox.txt
+for details). Each value of the mboxes property should contain a phandle to the
+mailbox controller device node and an args specifier that will be the phandle to
+the intended sub-mailbox child node to be used for communication. The equivalent
+"mbox-names" property value can be used to give a name to the communication channel
+to be used by the client user.
+
+
 Example:
 --------
 
@@ -81,6 +96,7 @@ mailbox: mailbox@4a0f4000 {
 	reg = <0x4a0f4000 0x200>;
 	interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
 	ti,hwmods = "mailbox";
+	#mbox-cells = <1>;
 	ti,mbox-num-users = <3>;
 	ti,mbox-num-fifos = <8>;
 	mbox_ipu: mbox_ipu {
@@ -93,12 +109,19 @@ mailbox: mailbox@4a0f4000 {
 	};
 };
 
+dsp {
+	...
+	mboxes = <&mailbox &mbox_dsp>;
+	...
+};
+
 /* AM33xx */
 mailbox: mailbox@480C8000 {
 	compatible = "ti,omap4-mailbox";
 	reg = <0x480C8000 0x200>;
 	interrupts = <77>;
 	ti,hwmods = "mailbox";
+	#mbox-cells = <1>;
 	ti,mbox-num-users = <4>;
 	ti,mbox-num-fifos = <8>;
 	mbox_wkupm3: wkup_m3 {
diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c
index bcc7ee12927..66b83ca94dc 100644
--- a/drivers/mailbox/omap-mailbox.c
+++ b/drivers/mailbox/omap-mailbox.c
@@ -29,13 +29,14 @@
 #include <linux/slab.h>
 #include <linux/kfifo.h>
 #include <linux/err.h>
-#include <linux/notifier.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/platform_data/mailbox-omap.h>
 #include <linux/omap-mailbox.h>
+#include <linux/mailbox_controller.h>
+#include <linux/mailbox_client.h>
 
 #define MAILBOX_REVISION		0x000
 #define MAILBOX_MESSAGE(m)		(0x040 + 4 * (m))
@@ -80,7 +81,6 @@ struct omap_mbox_queue {
 	spinlock_t		lock;
 	struct kfifo		fifo;
 	struct work_struct	work;
-	struct tasklet_struct	tasklet;
 	struct omap_mbox	*mbox;
 	bool full;
 };
@@ -92,6 +92,7 @@ struct omap_mbox_device {
 	u32 num_users;
 	u32 num_fifos;
 	struct omap_mbox **mboxes;
+	struct mbox_controller controller;
 	struct list_head elem;
 };
 
@@ -110,15 +111,14 @@ struct omap_mbox_fifo_info {
 struct omap_mbox {
 	const char		*name;
 	int			irq;
-	struct omap_mbox_queue	*txq, *rxq;
+	struct omap_mbox_queue	*rxq;
 	struct device		*dev;
 	struct omap_mbox_device *parent;
 	struct omap_mbox_fifo	tx_fifo;
 	struct omap_mbox_fifo	rx_fifo;
 	u32			ctx[OMAP4_MBOX_NR_REGS];
 	u32			intr_type;
-	int			use_count;
-	struct blocking_notifier_head	notifier;
+	struct mbox_chan	*chan;
 };
 
 /* global variables for the mailbox devices */
@@ -129,6 +129,14 @@ static unsigned int mbox_kfifo_size = CONFIG_OMAP_MBOX_KFIFO_SIZE;
 module_param(mbox_kfifo_size, uint, S_IRUGO);
 MODULE_PARM_DESC(mbox_kfifo_size, "Size of omap's mailbox kfifo (bytes)");
 
+static struct omap_mbox *mbox_chan_to_omap_mbox(struct mbox_chan *chan)
+{
+	if (!chan || !chan->con_priv)
+		return NULL;
+
+	return (struct omap_mbox *)chan->con_priv;
+}
+
 static inline
 unsigned int mbox_read_reg(struct omap_mbox_device *mdev, size_t ofs)
 {
@@ -194,41 +202,14 @@ static int is_mbox_irq(struct omap_mbox *mbox, omap_mbox_irq_t irq)
 	return (int)(enable & status & bit);
 }
 
-/*
- * message sender
- */
-int omap_mbox_msg_send(struct omap_mbox *mbox, mbox_msg_t msg)
-{
-	struct omap_mbox_queue *mq = mbox->txq;
-	int ret = 0, len;
-
-	spin_lock_bh(&mq->lock);
-
-	if (kfifo_avail(&mq->fifo) < sizeof(msg)) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	if (kfifo_is_empty(&mq->fifo) && !mbox_fifo_full(mbox)) {
-		mbox_fifo_write(mbox, msg);
-		goto out;
-	}
-
-	len = kfifo_in(&mq->fifo, (unsigned char *)&msg, sizeof(msg));
-	WARN_ON(len != sizeof(msg));
-
-	tasklet_schedule(&mbox->txq->tasklet);
-
-out:
-	spin_unlock_bh(&mq->lock);
-	return ret;
-}
-EXPORT_SYMBOL(omap_mbox_msg_send);
-
-void omap_mbox_save_ctx(struct omap_mbox *mbox)
+void omap_mbox_save_ctx(struct mbox_chan *chan)
 {
 	int i;
 	int nr_regs;
+	struct omap_mbox *mbox = mbox_chan_to_omap_mbox(chan);
+
+	if (WARN_ON(!mbox))
+		return;
 
 	if (mbox->intr_type)
 		nr_regs = OMAP4_MBOX_NR_REGS;
@@ -243,10 +224,14 @@ void omap_mbox_save_ctx(struct omap_mbox *mbox)
 }
 EXPORT_SYMBOL(omap_mbox_save_ctx);
 
-void omap_mbox_restore_ctx(struct omap_mbox *mbox)
+void omap_mbox_restore_ctx(struct mbox_chan *chan)
 {
 	int i;
 	int nr_regs;
+	struct omap_mbox *mbox = mbox_chan_to_omap_mbox(chan);
+
+	if (WARN_ON(!mbox))
+		return;
 
 	if (mbox->intr_type)
 		nr_regs = OMAP4_MBOX_NR_REGS;
@@ -254,14 +239,13 @@ void omap_mbox_restore_ctx(struct omap_mbox *mbox)
 		nr_regs = MBOX_NR_REGS;
 	for (i = 0; i < nr_regs; i++) {
 		mbox_write_reg(mbox->parent, mbox->ctx[i], i * sizeof(u32));
-
 		dev_dbg(mbox->dev, "%s: [%02x] %08x\n", __func__,
 			i, mbox->ctx[i]);
 	}
 }
 EXPORT_SYMBOL(omap_mbox_restore_ctx);
 
-void omap_mbox_enable_irq(struct omap_mbox *mbox, omap_mbox_irq_t irq)
+static void _omap_mbox_enable_irq(struct omap_mbox *mbox, omap_mbox_irq_t irq)
 {
 	u32 l;
 	struct omap_mbox_fifo *fifo = (irq == IRQ_TX) ?
@@ -273,9 +257,8 @@ void omap_mbox_enable_irq(struct omap_mbox *mbox, omap_mbox_irq_t irq)
 	l |= bit;
 	mbox_write_reg(mbox->parent, l, irqenable);
 }
-EXPORT_SYMBOL(omap_mbox_enable_irq);
 
-void omap_mbox_disable_irq(struct omap_mbox *mbox, omap_mbox_irq_t irq)
+static void _omap_mbox_disable_irq(struct omap_mbox *mbox, omap_mbox_irq_t irq)
 {
 	struct omap_mbox_fifo *fifo = (irq == IRQ_TX) ?
 				&mbox->tx_fifo : &mbox->rx_fifo;
@@ -291,28 +274,28 @@ void omap_mbox_disable_irq(struct omap_mbox *mbox, omap_mbox_irq_t irq)
 
 	mbox_write_reg(mbox->parent, bit, irqdisable);
 }
-EXPORT_SYMBOL(omap_mbox_disable_irq);
 
-static void mbox_tx_tasklet(unsigned long tx_data)
+void omap_mbox_enable_irq(struct mbox_chan *chan, omap_mbox_irq_t irq)
 {
-	struct omap_mbox *mbox = (struct omap_mbox *)tx_data;
-	struct omap_mbox_queue *mq = mbox->txq;
-	mbox_msg_t msg;
-	int ret;
+	struct omap_mbox *mbox = mbox_chan_to_omap_mbox(chan);
 
-	while (kfifo_len(&mq->fifo)) {
-		if (mbox_fifo_full(mbox)) {
-			omap_mbox_enable_irq(mbox, IRQ_TX);
-			break;
-		}
+	if (WARN_ON(!mbox))
+		return;
 
-		ret = kfifo_out(&mq->fifo, (unsigned char *)&msg,
-								sizeof(msg));
-		WARN_ON(ret != sizeof(msg));
+	_omap_mbox_enable_irq(mbox, irq);
+}
+EXPORT_SYMBOL(omap_mbox_enable_irq);
 
-		mbox_fifo_write(mbox, msg);
-	}
+void omap_mbox_disable_irq(struct mbox_chan *chan, omap_mbox_irq_t irq)
+{
+	struct omap_mbox *mbox = mbox_chan_to_omap_mbox(chan);
+
+	if (WARN_ON(!mbox))
+		return;
+
+	_omap_mbox_disable_irq(mbox, irq);
 }
+EXPORT_SYMBOL(omap_mbox_disable_irq);
 
 /*
  * Message receiver(workqueue)
@@ -328,12 +311,11 @@ static void mbox_rx_work(struct work_struct *work)
 		len = kfifo_out(&mq->fifo, (unsigned char *)&msg, sizeof(msg));
 		WARN_ON(len != sizeof(msg));
 
-		blocking_notifier_call_chain(&mq->mbox->notifier, len,
-								(void *)msg);
+		mbox_chan_received_data(mq->mbox->chan, (void *)msg);
 		spin_lock_irq(&mq->lock);
 		if (mq->full) {
 			mq->full = false;
-			omap_mbox_enable_irq(mq->mbox, IRQ_RX);
+			_omap_mbox_enable_irq(mq->mbox, IRQ_RX);
 		}
 		spin_unlock_irq(&mq->lock);
 	}
@@ -344,9 +326,9 @@ static void mbox_rx_work(struct work_struct *work)
  */
 static void __mbox_tx_interrupt(struct omap_mbox *mbox)
 {
-	omap_mbox_disable_irq(mbox, IRQ_TX);
+	_omap_mbox_disable_irq(mbox, IRQ_TX);
 	ack_mbox_irq(mbox, IRQ_TX);
-	tasklet_schedule(&mbox->txq->tasklet);
+	mbox_chan_txdone(mbox->chan, 0);
 }
 
 static void __mbox_rx_interrupt(struct omap_mbox *mbox)
@@ -357,7 +339,7 @@ static void __mbox_rx_interrupt(struct omap_mbox *mbox)
 
 	while (!mbox_fifo_empty(mbox)) {
 		if (unlikely(kfifo_avail(&mq->fifo) < sizeof(msg))) {
-			omap_mbox_disable_irq(mbox, IRQ_RX);
+			_omap_mbox_disable_irq(mbox, IRQ_RX);
 			mq->full = true;
 			goto nomem;
 		}
@@ -388,11 +370,13 @@ static irqreturn_t mbox_interrupt(int irq, void *p)
 }
 
 static struct omap_mbox_queue *mbox_queue_alloc(struct omap_mbox *mbox,
-					void (*work) (struct work_struct *),
-					void (*tasklet)(unsigned long))
+					void (*work)(struct work_struct *))
 {
 	struct omap_mbox_queue *mq;
 
+	if (!work)
+		return NULL;
+
 	mq = kzalloc(sizeof(struct omap_mbox_queue), GFP_KERNEL);
 	if (!mq)
 		return NULL;
@@ -402,12 +386,9 @@ static struct omap_mbox_queue *mbox_queue_alloc(struct omap_mbox *mbox,
 	if (kfifo_alloc(&mq->fifo, mbox_kfifo_size, GFP_KERNEL))
 		goto error;
 
-	if (work)
-		INIT_WORK(&mq->work, work);
-
-	if (tasklet)
-		tasklet_init(&mq->tasklet, tasklet, (unsigned long)mbox);
+	INIT_WORK(&mq->work, work);
 	return mq;
+
 error:
 	kfree(mq);
 	return NULL;
@@ -423,71 +404,35 @@ static int omap_mbox_startup(struct omap_mbox *mbox)
 {
 	int ret = 0;
 	struct omap_mbox_queue *mq;
-	struct omap_mbox_device *mdev = mbox->parent;
 
-	mutex_lock(&mdev->cfg_lock);
-	ret = pm_runtime_get_sync(mdev->dev);
-	if (unlikely(ret < 0))
-		goto fail_startup;
-
-	if (!mbox->use_count++) {
-		mq = mbox_queue_alloc(mbox, NULL, mbox_tx_tasklet);
-		if (!mq) {
-			ret = -ENOMEM;
-			goto fail_alloc_txq;
-		}
-		mbox->txq = mq;
+	mq = mbox_queue_alloc(mbox, mbox_rx_work);
+	if (!mq)
+		return -ENOMEM;
+	mbox->rxq = mq;
+	mq->mbox = mbox;
+
+	ret = request_irq(mbox->irq, mbox_interrupt, IRQF_SHARED,
+			  mbox->name, mbox);
+	if (unlikely(ret)) {
+		pr_err("failed to register mailbox interrupt:%d\n", ret);
+		goto fail_request_irq;
+	}
 
-		mq = mbox_queue_alloc(mbox, mbox_rx_work, NULL);
-		if (!mq) {
-			ret = -ENOMEM;
-			goto fail_alloc_rxq;
-		}
-		mbox->rxq = mq;
-		mq->mbox = mbox;
-		ret = request_irq(mbox->irq, mbox_interrupt, IRQF_SHARED,
-							mbox->name, mbox);
-		if (unlikely(ret)) {
-			pr_err("failed to register mailbox interrupt:%d\n",
-									ret);
-			goto fail_request_irq;
-		}
+	_omap_mbox_enable_irq(mbox, IRQ_RX);
 
-		omap_mbox_enable_irq(mbox, IRQ_RX);
-	}
-	mutex_unlock(&mdev->cfg_lock);
 	return 0;
 
 fail_request_irq:
 	mbox_queue_free(mbox->rxq);
-fail_alloc_rxq:
-	mbox_queue_free(mbox->txq);
-fail_alloc_txq:
-	pm_runtime_put_sync(mdev->dev);
-	mbox->use_count--;
-fail_startup:
-	mutex_unlock(&mdev->cfg_lock);
 	return ret;
 }
 
 static void omap_mbox_fini(struct omap_mbox *mbox)
 {
-	struct omap_mbox_device *mdev = mbox->parent;
-
-	mutex_lock(&mdev->cfg_lock);
-
-	if (!--mbox->use_count) {
-		omap_mbox_disable_irq(mbox, IRQ_RX);
-		free_irq(mbox->irq, mbox);
-		tasklet_kill(&mbox->txq->tasklet);
-		flush_work(&mbox->rxq->work);
-		mbox_queue_free(mbox->txq);
-		mbox_queue_free(mbox->rxq);
-	}
-
-	pm_runtime_put_sync(mdev->dev);
-
-	mutex_unlock(&mdev->cfg_lock);
+	_omap_mbox_disable_irq(mbox, IRQ_RX);
+	free_irq(mbox->irq, mbox);
+	flush_work(&mbox->rxq->work);
+	mbox_queue_free(mbox->rxq);
 }
 
 static struct omap_mbox *omap_mbox_device_find(struct omap_mbox_device *mdev,
@@ -509,42 +454,55 @@ static struct omap_mbox *omap_mbox_device_find(struct omap_mbox_device *mdev,
 	return mbox;
 }
 
-struct omap_mbox *omap_mbox_get(const char *name, struct notifier_block *nb)
+struct mbox_chan *omap_mbox_request_channel(struct mbox_client *cl,
+					    const char *chan_name)
 {
+	struct device *dev = cl->dev;
 	struct omap_mbox *mbox = NULL;
 	struct omap_mbox_device *mdev;
+	struct mbox_chan *chan;
+	unsigned long flags;
 	int ret;
 
+	if (!dev)
+		return ERR_PTR(-ENODEV);
+
+	if (dev->of_node) {
+		pr_err("%s: please use mbox_request_channel(), this API is supported only for OMAP non-DT usage\n",
+		       __func__);
+		return ERR_PTR(-ENODEV);
+	}
+
 	mutex_lock(&omap_mbox_devices_lock);
 	list_for_each_entry(mdev, &omap_mbox_devices, elem) {
-		mbox = omap_mbox_device_find(mdev, name);
+		mbox = omap_mbox_device_find(mdev, chan_name);
 		if (mbox)
 			break;
 	}
 	mutex_unlock(&omap_mbox_devices_lock);
 
-	if (!mbox)
+	if (!mbox || !mbox->chan)
 		return ERR_PTR(-ENOENT);
 
-	if (nb)
-		blocking_notifier_chain_register(&mbox->notifier, nb);
+	chan = mbox->chan;
+	spin_lock_irqsave(&chan->lock, flags);
+	chan->msg_free = 0;
+	chan->msg_count = 0;
+	chan->active_req = NULL;
+	chan->cl = cl;
+	init_completion(&chan->tx_complete);
+	spin_unlock_irqrestore(&chan->lock, flags);
 
-	ret = omap_mbox_startup(mbox);
+	ret = chan->mbox->ops->startup(chan);
 	if (ret) {
-		blocking_notifier_chain_unregister(&mbox->notifier, nb);
-		return ERR_PTR(-ENODEV);
+		pr_err("Unable to startup the chan (%d)\n", ret);
+		mbox_free_channel(chan);
+		chan = ERR_PTR(ret);
 	}
 
-	return mbox;
-}
-EXPORT_SYMBOL(omap_mbox_get);
-
-void omap_mbox_put(struct omap_mbox *mbox, struct notifier_block *nb)
-{
-	blocking_notifier_chain_unregister(&mbox->notifier, nb);
-	omap_mbox_fini(mbox);
+	return chan;
 }
-EXPORT_SYMBOL(omap_mbox_put);
+EXPORT_SYMBOL(omap_mbox_request_channel);
 
 static struct class omap_mbox_class = { .name = "mbox", };
 
@@ -560,25 +518,25 @@ static int omap_mbox_register(struct omap_mbox_device *mdev)
 	mboxes = mdev->mboxes;
 	for (i = 0; mboxes[i]; i++) {
 		struct omap_mbox *mbox = mboxes[i];
-		mbox->dev = device_create(&omap_mbox_class,
-				mdev->dev, 0, mbox, "%s", mbox->name);
+		mbox->dev = device_create(&omap_mbox_class, mdev->dev,
+					0, mbox, "%s", mbox->name);
 		if (IS_ERR(mbox->dev)) {
 			ret = PTR_ERR(mbox->dev);
 			goto err_out;
 		}
-
-		BLOCKING_INIT_NOTIFIER_HEAD(&mbox->notifier);
 	}
 
 	mutex_lock(&omap_mbox_devices_lock);
 	list_add(&mdev->elem, &omap_mbox_devices);
 	mutex_unlock(&omap_mbox_devices_lock);
 
-	return 0;
+	ret = mbox_controller_register(&mdev->controller);
 
 err_out:
-	while (i--)
-		device_unregister(mboxes[i]->dev);
+	if (ret) {
+		while (i--)
+			device_unregister(mboxes[i]->dev);
+	}
 	return ret;
 }
 
@@ -594,12 +552,64 @@ static int omap_mbox_unregister(struct omap_mbox_device *mdev)
 	list_del(&mdev->elem);
 	mutex_unlock(&omap_mbox_devices_lock);
 
+	mbox_controller_unregister(&mdev->controller);
+
 	mboxes = mdev->mboxes;
 	for (i = 0; mboxes[i]; i++)
 		device_unregister(mboxes[i]->dev);
 	return 0;
 }
 
+static int omap_mbox_chan_startup(struct mbox_chan *chan)
+{
+	struct omap_mbox *mbox = mbox_chan_to_omap_mbox(chan);
+	struct omap_mbox_device *mdev = mbox->parent;
+	int ret = 0;
+
+	mutex_lock(&mdev->cfg_lock);
+	pm_runtime_get_sync(mdev->dev);
+	ret = omap_mbox_startup(mbox);
+	if (ret)
+		pm_runtime_put_sync(mdev->dev);
+	mutex_unlock(&mdev->cfg_lock);
+	return ret;
+}
+
+static void omap_mbox_chan_shutdown(struct mbox_chan *chan)
+{
+	struct omap_mbox *mbox = mbox_chan_to_omap_mbox(chan);
+	struct omap_mbox_device *mdev = mbox->parent;
+
+	mutex_lock(&mdev->cfg_lock);
+	omap_mbox_fini(mbox);
+	pm_runtime_put_sync(mdev->dev);
+	mutex_unlock(&mdev->cfg_lock);
+}
+
+static int omap_mbox_chan_send_data(struct mbox_chan *chan, void *data)
+{
+	struct omap_mbox *mbox = mbox_chan_to_omap_mbox(chan);
+	int ret = -EBUSY;
+
+	if (!mbox)
+		return -EINVAL;
+
+	if (!mbox_fifo_full(mbox)) {
+		mbox_fifo_write(mbox, (mbox_msg_t)data);
+		ret = 0;
+	}
+
+	/* always enable the interrupt */
+	_omap_mbox_enable_irq(mbox, IRQ_TX);
+	return ret;
+}
+
+static struct mbox_chan_ops omap_mbox_chan_ops = {
+	.startup        = omap_mbox_chan_startup,
+	.send_data      = omap_mbox_chan_send_data,
+	.shutdown       = omap_mbox_chan_shutdown,
+};
+
 static const struct of_device_id omap_mailbox_of_match[] = {
 	{
 		.compatible	= "ti,omap2-mailbox",
@@ -619,10 +629,35 @@ static const struct of_device_id omap_mailbox_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, omap_mailbox_of_match);
 
+static struct mbox_chan *omap_mbox_of_xlate(struct mbox_controller *controller,
+					    const struct of_phandle_args *sp)
+{
+	phandle phandle = sp->args[0];
+	struct device_node *node;
+	struct omap_mbox_device *mdev;
+	struct omap_mbox *mbox;
+
+	mdev = container_of(controller, struct omap_mbox_device, controller);
+	if (WARN_ON(!mdev))
+		return NULL;
+
+	node = of_find_node_by_phandle(phandle);
+	if (!node) {
+		pr_err("%s: could not find node phandle 0x%x\n",
+		       __func__, phandle);
+		return NULL;
+	}
+
+	mbox = omap_mbox_device_find(mdev, node->name);
+	of_node_put(node);
+	return mbox ? mbox->chan : NULL;
+}
+
 static int omap_mbox_probe(struct platform_device *pdev)
 {
 	struct resource *mem;
 	int ret;
+	struct mbox_chan *chnls;
 	struct omap_mbox **list, *mbox, *mboxblk;
 	struct omap_mbox_pdata *pdata = pdev->dev.platform_data;
 	struct omap_mbox_dev_info *info = NULL;
@@ -727,6 +762,11 @@ static int omap_mbox_probe(struct platform_device *pdev)
 	if (!list)
 		return -ENOMEM;
 
+	chnls = devm_kzalloc(&pdev->dev, (info_count + 1) * sizeof(*chnls),
+			     GFP_KERNEL);
+	if (!chnls)
+		return -ENOMEM;
+
 	mboxblk = devm_kzalloc(&pdev->dev, info_count * sizeof(*mbox),
 			       GFP_KERNEL);
 	if (!mboxblk)
@@ -758,6 +798,8 @@ static int omap_mbox_probe(struct platform_device *pdev)
 		mbox->irq = platform_get_irq(pdev, finfo->tx_irq);
 		if (mbox->irq < 0)
 			return mbox->irq;
+		mbox->chan = &chnls[i];
+		chnls[i].con_priv = mbox;
 		list[i] = mbox++;
 	}
 
@@ -766,6 +808,14 @@ static int omap_mbox_probe(struct platform_device *pdev)
 	mdev->num_users = num_users;
 	mdev->num_fifos = num_fifos;
 	mdev->mboxes = list;
+
+	/* OMAP does not have a Tx-Done IRQ, but rather a Tx-Ready IRQ */
+	mdev->controller.txdone_irq = true;
+	mdev->controller.dev = mdev->dev;
+	mdev->controller.ops = &omap_mbox_chan_ops;
+	mdev->controller.chans = chnls;
+	mdev->controller.num_chans = info_count;
+	mdev->controller.of_xlate = omap_mbox_of_xlate;
 	ret = omap_mbox_register(mdev);
 	if (ret)
 		return ret;
diff --git a/drivers/remoteproc/omap_remoteproc.c b/drivers/remoteproc/omap_remoteproc.c
index 51689721ea7..cf92f6e7c5d 100644
--- a/drivers/remoteproc/omap_remoteproc.c
+++ b/drivers/remoteproc/omap_remoteproc.c
@@ -27,6 +27,7 @@
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/remoteproc.h>
+#include <linux/mailbox_client.h>
 #include <linux/omap-mailbox.h>
 
 #include <linux/platform_data/remoteproc-omap.h>
@@ -36,20 +37,19 @@
 
 /**
  * struct omap_rproc - omap remote processor state
- * @mbox: omap mailbox handle
- * @nb: notifier block that will be invoked on inbound mailbox messages
+ * @mbox: mailbox channel handle
+ * @client: mailbox client to request the mailbox channel
  * @rproc: rproc handle
  */
 struct omap_rproc {
-	struct omap_mbox *mbox;
-	struct notifier_block nb;
+	struct mbox_chan *mbox;
+	struct mbox_client client;
 	struct rproc *rproc;
 };
 
 /**
  * omap_rproc_mbox_callback() - inbound mailbox message handler
- * @this: notifier block
- * @index: unused
+ * @client: mailbox client pointer used for requesting the mailbox channel
  * @data: mailbox payload
  *
  * This handler is invoked by omap's mailbox driver whenever a mailbox
@@ -61,13 +61,13 @@ struct omap_rproc {
  * that indicates different events. Those values are deliberately very
  * big so they don't coincide with virtqueue indices.
  */
-static int omap_rproc_mbox_callback(struct notifier_block *this,
-					unsigned long index, void *data)
+static void omap_rproc_mbox_callback(struct mbox_client *client, void *data)
 {
-	mbox_msg_t msg = (mbox_msg_t) data;
-	struct omap_rproc *oproc = container_of(this, struct omap_rproc, nb);
+	struct omap_rproc *oproc = container_of(client, struct omap_rproc,
+						client);
 	struct device *dev = oproc->rproc->dev.parent;
 	const char *name = oproc->rproc->name;
+	u32 msg = (u32)data;
 
 	dev_dbg(dev, "mbox msg: 0x%x\n", msg);
 
@@ -84,8 +84,6 @@ static int omap_rproc_mbox_callback(struct notifier_block *this,
 		if (rproc_vq_interrupt(oproc->rproc, msg) == IRQ_NONE)
 			dev_dbg(dev, "no message was found in vqid %d\n", msg);
 	}
-
-	return NOTIFY_DONE;
 }
 
 /* kick a virtqueue */
@@ -96,8 +94,8 @@ static void omap_rproc_kick(struct rproc *rproc, int vqid)
 	int ret;
 
 	/* send the index of the triggered virtqueue in the mailbox payload */
-	ret = omap_mbox_msg_send(oproc->mbox, vqid);
-	if (ret)
+	ret = mbox_send_message(oproc->mbox, (void *)vqid);
+	if (ret < 0)
 		dev_err(dev, "omap_mbox_msg_send failed: %d\n", ret);
 }
 
@@ -115,17 +113,22 @@ static int omap_rproc_start(struct rproc *rproc)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct omap_rproc_pdata *pdata = pdev->dev.platform_data;
 	int ret;
+	struct mbox_client *client = &oproc->client;
 
 	if (pdata->set_bootaddr)
 		pdata->set_bootaddr(rproc->bootaddr);
 
-	oproc->nb.notifier_call = omap_rproc_mbox_callback;
+	client->dev = dev;
+	client->tx_done = NULL;
+	client->rx_callback = omap_rproc_mbox_callback;
+	client->tx_block = false;
+	client->knows_txdone = false;
 
-	/* every omap rproc is assigned a mailbox instance for messaging */
-	oproc->mbox = omap_mbox_get(pdata->mbox_name, &oproc->nb);
+	oproc->mbox = omap_mbox_request_channel(client, pdata->mbox_name);
 	if (IS_ERR(oproc->mbox)) {
-		ret = PTR_ERR(oproc->mbox);
-		dev_err(dev, "omap_mbox_get failed: %d\n", ret);
+		ret = -EBUSY;
+		dev_err(dev, "mbox_request_channel failed: %ld\n",
+			PTR_ERR(oproc->mbox));
 		return ret;
 	}
 
@@ -136,9 +139,9 @@ static int omap_rproc_start(struct rproc *rproc)
 	 * Note that the reply will _not_ arrive immediately: this message
 	 * will wait in the mailbox fifo until the remote processor is booted.
 	 */
-	ret = omap_mbox_msg_send(oproc->mbox, RP_MBOX_ECHO_REQUEST);
-	if (ret) {
-		dev_err(dev, "omap_mbox_get failed: %d\n", ret);
+	ret = mbox_send_message(oproc->mbox, (void *)RP_MBOX_ECHO_REQUEST);
+	if (ret < 0) {
+		dev_err(dev, "mbox_send_message failed: %d\n", ret);
 		goto put_mbox;
 	}
 
@@ -151,7 +154,7 @@ static int omap_rproc_start(struct rproc *rproc)
 	return 0;
 
 put_mbox:
-	omap_mbox_put(oproc->mbox, &oproc->nb);
+	mbox_free_channel(oproc->mbox);
 	return ret;
 }
 
@@ -168,7 +171,7 @@ static int omap_rproc_stop(struct rproc *rproc)
 	if (ret)
 		return ret;
 
-	omap_mbox_put(oproc->mbox, &oproc->nb);
+	mbox_free_channel(oproc->mbox);
 
 	return 0;
 }
diff --git a/include/linux/omap-mailbox.h b/include/linux/omap-mailbox.h
index f8322d9cd23..587bbdd31f5 100644
--- a/include/linux/omap-mailbox.h
+++ b/include/linux/omap-mailbox.h
@@ -10,20 +10,20 @@
 #define OMAP_MAILBOX_H
 
 typedef u32 mbox_msg_t;
-struct omap_mbox;
 
 typedef int __bitwise omap_mbox_irq_t;
 #define IRQ_TX ((__force omap_mbox_irq_t) 1)
 #define IRQ_RX ((__force omap_mbox_irq_t) 2)
 
-int omap_mbox_msg_send(struct omap_mbox *, mbox_msg_t msg);
+struct mbox_chan;
+struct mbox_client;
 
-struct omap_mbox *omap_mbox_get(const char *, struct notifier_block *nb);
-void omap_mbox_put(struct omap_mbox *mbox, struct notifier_block *nb);
+struct mbox_chan *omap_mbox_request_channel(struct mbox_client *cl,
+					    const char *chan_name);
 
-void omap_mbox_save_ctx(struct omap_mbox *mbox);
-void omap_mbox_restore_ctx(struct omap_mbox *mbox);
-void omap_mbox_enable_irq(struct omap_mbox *mbox, omap_mbox_irq_t irq);
-void omap_mbox_disable_irq(struct omap_mbox *mbox, omap_mbox_irq_t irq);
+void omap_mbox_save_ctx(struct mbox_chan *chan);
+void omap_mbox_restore_ctx(struct mbox_chan *chan);
+void omap_mbox_enable_irq(struct mbox_chan *chan, omap_mbox_irq_t irq);
+void omap_mbox_disable_irq(struct mbox_chan *chan, omap_mbox_irq_t irq);
 
 #endif /* OMAP_MAILBOX_H */
-- 
cgit v1.2.3-70-g09d2


From 002fe7c831404d179266cfe0dad00a67333256f1 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Wed, 26 Nov 2014 20:57:50 +0100
Subject: ASoC: cq93vc: Remove unused state struct

While two of the fields in the cq93vc driver state struct are initialized
none of them are ever acutally read again. So remove the whole struct.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/mfd/davinci_voicecodec.h | 7 -------
 sound/soc/codecs/cq93vc.c              | 8 --------
 2 files changed, 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/mfd/davinci_voicecodec.h b/include/linux/mfd/davinci_voicecodec.h
index cb01496bfa4..8e1cdbef3da 100644
--- a/include/linux/mfd/davinci_voicecodec.h
+++ b/include/linux/mfd/davinci_voicecodec.h
@@ -99,12 +99,6 @@ struct davinci_vcif {
 	dma_addr_t dma_rx_addr;
 };
 
-struct cq93vc {
-	struct platform_device *pdev;
-	struct snd_soc_codec *codec;
-	u32 sysclk;
-};
-
 struct davinci_vc;
 
 struct davinci_vc {
@@ -122,7 +116,6 @@ struct davinci_vc {
 
 	/* Client devices */
 	struct davinci_vcif davinci_vcif;
-	struct cq93vc cq93vc;
 };
 
 #endif
diff --git a/sound/soc/codecs/cq93vc.c b/sound/soc/codecs/cq93vc.c
index 537327c7f7f..036a877746b 100644
--- a/sound/soc/codecs/cq93vc.c
+++ b/sound/soc/codecs/cq93vc.c
@@ -62,14 +62,10 @@ static int cq93vc_mute(struct snd_soc_dai *dai, int mute)
 static int cq93vc_set_dai_sysclk(struct snd_soc_dai *codec_dai,
 				 int clk_id, unsigned int freq, int dir)
 {
-	struct snd_soc_codec *codec = codec_dai->codec;
-	struct davinci_vc *davinci_vc = codec->dev->platform_data;
-
 	switch (freq) {
 	case 22579200:
 	case 27000000:
 	case 33868800:
-		davinci_vc->cq93vc.sysclk = freq;
 		return 0;
 	}
 
@@ -135,10 +131,6 @@ static int cq93vc_resume(struct snd_soc_codec *codec)
 
 static int cq93vc_probe(struct snd_soc_codec *codec)
 {
-	struct davinci_vc *davinci_vc = codec->dev->platform_data;
-
-	davinci_vc->cq93vc.codec = codec;
-
 	/* Off, with power on */
 	cq93vc_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
 
-- 
cgit v1.2.3-70-g09d2


From c41884ce0562841b98fa9790c9209c9073121a15 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 24 Nov 2014 15:25:57 +0100
Subject: netfilter: conntrack: avoid zeroing timer

add a __nfct_init_offset annotation member to struct nf_conn to make
it clear which members are covered by the memset when the conntrack
is allocated.

This avoids zeroing timer_list and ct_net; both are already inited
explicitly.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack.h | 15 +++++++++------
 net/netfilter/nf_conntrack_core.c    | 11 ++++-------
 2 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index c8a7db605e0..f0daed2b54d 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -92,12 +92,18 @@ struct nf_conn {
 	/* Have we seen traffic both ways yet? (bitset) */
 	unsigned long status;
 
-	/* If we were expected by an expectation, this will be it */
-	struct nf_conn *master;
-
 	/* Timer function; drops refcnt when it goes off. */
 	struct timer_list timeout;
 
+#ifdef CONFIG_NET_NS
+	struct net *ct_net;
+#endif
+	/* all members below initialized via memset */
+	u8 __nfct_init_offset[0];
+
+	/* If we were expected by an expectation, this will be it */
+	struct nf_conn *master;
+
 #if defined(CONFIG_NF_CONNTRACK_MARK)
 	u_int32_t mark;
 #endif
@@ -108,9 +114,6 @@ struct nf_conn {
 
 	/* Extensions */
 	struct nf_ct_ext *ext;
-#ifdef CONFIG_NET_NS
-	struct net *ct_net;
-#endif
 
 	/* Storage reserved for other modules, must be the last member */
 	union nf_conntrack_proto proto;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 2c699757bcc..9ef88c8dd68 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -826,22 +826,19 @@ __nf_conntrack_alloc(struct net *net, u16 zone,
 		atomic_dec(&net->ct.count);
 		return ERR_PTR(-ENOMEM);
 	}
-	/*
-	 * Let ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.next
-	 * and ct->tuplehash[IP_CT_DIR_REPLY].hnnode.next unchanged.
-	 */
-	memset(&ct->tuplehash[IP_CT_DIR_MAX], 0,
-	       offsetof(struct nf_conn, proto) -
-	       offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX]));
 	spin_lock_init(&ct->lock);
 	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
 	ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL;
 	ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;
 	/* save hash for reusing when confirming */
 	*(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash;
+	ct->status = 0;
 	/* Don't set timer yet: wait for confirmation */
 	setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct);
 	write_pnet(&ct->ct_net, net);
+	memset(&ct->__nfct_init_offset[0], 0,
+	       offsetof(struct nf_conn, proto) -
+	       offsetof(struct nf_conn, __nfct_init_offset[0]));
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	if (zone) {
 		struct nf_conntrack_zone *nf_ct_zone;
-- 
cgit v1.2.3-70-g09d2


From 68b0faa87d167ec87ba2a26be62241ad94eb449b Mon Sep 17 00:00:00 2001
From: Alvaro Neira <alvaroneay@gmail.com>
Date: Wed, 26 Nov 2014 10:21:36 +0100
Subject: netfilter: nf_tables_bridge: export nft_reject_ip*hdr_validate
 functions

This patch exports the functions nft_reject_iphdr_validate and
nft_reject_ip6hdr_validate to use it in follow up patches.
These functions check if the IPv4/IPv6 header is correct.

Signed-off-by: Alvaro Neira Ayuso <alvaroneay@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables_bridge.h |  7 +++++
 net/bridge/netfilter/nf_tables_bridge.c  | 48 +++++++++++++++++++++++++++++
 net/bridge/netfilter/nft_reject_bridge.c | 52 +++-----------------------------
 3 files changed, 60 insertions(+), 47 deletions(-)
 create mode 100644 include/net/netfilter/nf_tables_bridge.h

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables_bridge.h b/include/net/netfilter/nf_tables_bridge.h
new file mode 100644
index 00000000000..511fb79f6da
--- /dev/null
+++ b/include/net/netfilter/nf_tables_bridge.h
@@ -0,0 +1,7 @@
+#ifndef _NET_NF_TABLES_BRIDGE_H
+#define _NET_NF_TABLES_BRIDGE_H
+
+int nft_bridge_iphdr_validate(struct sk_buff *skb);
+int nft_bridge_ip6hdr_validate(struct sk_buff *skb);
+
+#endif /* _NET_NF_TABLES_BRIDGE_H */
diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c
index 074c557ab50..d468c19faec 100644
--- a/net/bridge/netfilter/nf_tables_bridge.c
+++ b/net/bridge/netfilter/nf_tables_bridge.c
@@ -13,6 +13,54 @@
 #include <linux/module.h>
 #include <linux/netfilter_bridge.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_bridge.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+
+int nft_bridge_iphdr_validate(struct sk_buff *skb)
+{
+	struct iphdr *iph;
+	u32 len;
+
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		return 0;
+
+	iph = ip_hdr(skb);
+	if (iph->ihl < 5 || iph->version != 4)
+		return 0;
+
+	len = ntohs(iph->tot_len);
+	if (skb->len < len)
+		return 0;
+	else if (len < (iph->ihl*4))
+		return 0;
+
+	if (!pskb_may_pull(skb, iph->ihl*4))
+		return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(nft_bridge_iphdr_validate);
+
+int nft_bridge_ip6hdr_validate(struct sk_buff *skb)
+{
+	struct ipv6hdr *hdr;
+	u32 pkt_len;
+
+	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+		return 0;
+
+	hdr = ipv6_hdr(skb);
+	if (hdr->version != 6)
+		return 0;
+
+	pkt_len = ntohs(hdr->payload_len);
+	if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
+		return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(nft_bridge_ip6hdr_validate);
 
 static unsigned int
 nft_do_chain_bridge(const struct nf_hook_ops *ops,
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index 48da2c54a69..b0330aecbf9 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -14,6 +14,7 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nft_reject.h>
+#include <net/netfilter/nf_tables_bridge.h>
 #include <net/netfilter/ipv4/nf_reject.h>
 #include <net/netfilter/ipv6/nf_reject.h>
 #include <linux/ip.h>
@@ -35,30 +36,6 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb,
 	skb_pull(nskb, ETH_HLEN);
 }
 
-static int nft_reject_iphdr_validate(struct sk_buff *oldskb)
-{
-	struct iphdr *iph;
-	u32 len;
-
-	if (!pskb_may_pull(oldskb, sizeof(struct iphdr)))
-		return 0;
-
-	iph = ip_hdr(oldskb);
-	if (iph->ihl < 5 || iph->version != 4)
-		return 0;
-
-	len = ntohs(iph->tot_len);
-	if (oldskb->len < len)
-		return 0;
-	else if (len < (iph->ihl*4))
-		return 0;
-
-	if (!pskb_may_pull(oldskb, iph->ihl*4))
-		return 0;
-
-	return 1;
-}
-
 static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, int hook)
 {
 	struct sk_buff *nskb;
@@ -66,7 +43,7 @@ static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, int hook)
 	const struct tcphdr *oth;
 	struct tcphdr _oth;
 
-	if (!nft_reject_iphdr_validate(oldskb))
+	if (!nft_bridge_iphdr_validate(oldskb))
 		return;
 
 	oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook);
@@ -101,7 +78,7 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook,
 	void *payload;
 	__wsum csum;
 
-	if (!nft_reject_iphdr_validate(oldskb))
+	if (!nft_bridge_iphdr_validate(oldskb))
 		return;
 
 	/* IP header checks: fragment. */
@@ -146,25 +123,6 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook,
 	br_deliver(br_port_get_rcu(oldskb->dev), nskb);
 }
 
-static int nft_reject_ip6hdr_validate(struct sk_buff *oldskb)
-{
-	struct ipv6hdr *hdr;
-	u32 pkt_len;
-
-	if (!pskb_may_pull(oldskb, sizeof(struct ipv6hdr)))
-		return 0;
-
-	hdr = ipv6_hdr(oldskb);
-	if (hdr->version != 6)
-		return 0;
-
-	pkt_len = ntohs(hdr->payload_len);
-	if (pkt_len + sizeof(struct ipv6hdr) > oldskb->len)
-		return 0;
-
-	return 1;
-}
-
 static void nft_reject_br_send_v6_tcp_reset(struct net *net,
 					    struct sk_buff *oldskb, int hook)
 {
@@ -174,7 +132,7 @@ static void nft_reject_br_send_v6_tcp_reset(struct net *net,
 	unsigned int otcplen;
 	struct ipv6hdr *nip6h;
 
-	if (!nft_reject_ip6hdr_validate(oldskb))
+	if (!nft_bridge_ip6hdr_validate(oldskb))
 		return;
 
 	oth = nf_reject_ip6_tcphdr_get(oldskb, &_oth, &otcplen, hook);
@@ -207,7 +165,7 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
 	unsigned int len;
 	void *payload;
 
-	if (!nft_reject_ip6hdr_validate(oldskb))
+	if (!nft_bridge_ip6hdr_validate(oldskb))
 		return;
 
 	/* Include "As much of invoking packet as possible without the ICMPv6
-- 
cgit v1.2.3-70-g09d2


From b59eaf9e2871735ea7cc7e3dbf8bf83bddd786b9 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 26 Nov 2014 12:46:50 +0100
Subject: netfilter: combine IPv4 and IPv6 nf_nat_redirect code in one module

This resolves linking problems with CONFIG_IPV6=n:

net/built-in.o: In function `redirect_tg6':
xt_REDIRECT.c:(.text+0x6d021): undefined reference to `nf_nat_redirect_ipv6'

Reported-by: Andreas Ruprecht <rupran@einserver.de>
Reported-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/ipv4/nf_nat_redirect.h |   9 --
 include/net/netfilter/ipv6/nf_nat_redirect.h |   8 --
 include/net/netfilter/nf_nat_redirect.h      |  12 +++
 net/ipv4/netfilter/Kconfig                   |   8 +-
 net/ipv4/netfilter/Makefile                  |   1 -
 net/ipv4/netfilter/nf_nat_redirect_ipv4.c    |  82 -----------------
 net/ipv4/netfilter/nft_redir_ipv4.c          |   2 +-
 net/ipv6/netfilter/Kconfig                   |   8 +-
 net/ipv6/netfilter/Makefile                  |   1 -
 net/ipv6/netfilter/nf_nat_redirect_ipv6.c    |  75 ----------------
 net/ipv6/netfilter/nft_redir_ipv6.c          |   2 +-
 net/netfilter/Kconfig                        |  10 ++-
 net/netfilter/Makefile                       |   1 +
 net/netfilter/nf_nat_redirect.c              | 127 +++++++++++++++++++++++++++
 net/netfilter/xt_REDIRECT.c                  |   3 +-
 15 files changed, 153 insertions(+), 196 deletions(-)
 delete mode 100644 include/net/netfilter/ipv4/nf_nat_redirect.h
 delete mode 100644 include/net/netfilter/ipv6/nf_nat_redirect.h
 create mode 100644 include/net/netfilter/nf_nat_redirect.h
 delete mode 100644 net/ipv4/netfilter/nf_nat_redirect_ipv4.c
 delete mode 100644 net/ipv6/netfilter/nf_nat_redirect_ipv6.c
 create mode 100644 net/netfilter/nf_nat_redirect.c

(limited to 'include')

diff --git a/include/net/netfilter/ipv4/nf_nat_redirect.h b/include/net/netfilter/ipv4/nf_nat_redirect.h
deleted file mode 100644
index 19e1df3a0a4..00000000000
--- a/include/net/netfilter/ipv4/nf_nat_redirect.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _NF_NAT_REDIRECT_IPV4_H_
-#define _NF_NAT_REDIRECT_IPV4_H_
-
-unsigned int
-nf_nat_redirect_ipv4(struct sk_buff *skb,
-		     const struct nf_nat_ipv4_multi_range_compat *mr,
-		     unsigned int hooknum);
-
-#endif /* _NF_NAT_REDIRECT_IPV4_H_ */
diff --git a/include/net/netfilter/ipv6/nf_nat_redirect.h b/include/net/netfilter/ipv6/nf_nat_redirect.h
deleted file mode 100644
index 1ebdffc461c..00000000000
--- a/include/net/netfilter/ipv6/nf_nat_redirect.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _NF_NAT_REDIRECT_IPV6_H_
-#define _NF_NAT_REDIRECT_IPV6_H_
-
-unsigned int
-nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
-		     unsigned int hooknum);
-
-#endif /* _NF_NAT_REDIRECT_IPV6_H_ */
diff --git a/include/net/netfilter/nf_nat_redirect.h b/include/net/netfilter/nf_nat_redirect.h
new file mode 100644
index 00000000000..73b72954330
--- /dev/null
+++ b/include/net/netfilter/nf_nat_redirect.h
@@ -0,0 +1,12 @@
+#ifndef _NF_NAT_REDIRECT_H_
+#define _NF_NAT_REDIRECT_H_
+
+unsigned int
+nf_nat_redirect_ipv4(struct sk_buff *skb,
+		     const struct nf_nat_ipv4_multi_range_compat *mr,
+		     unsigned int hooknum);
+unsigned int
+nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+		     unsigned int hooknum);
+
+#endif /* _NF_NAT_REDIRECT_H_ */
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 8358b2da154..59f883d9cad 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -104,12 +104,6 @@ config NF_NAT_MASQUERADE_IPV4
 	  This is the kernel functionality to provide NAT in the masquerade
 	  flavour (automatic source address selection).
 
-config NF_NAT_REDIRECT_IPV4
-	tristate "IPv4 redirect support"
-	help
-	  This is the kernel functionality to provide NAT in the redirect
-	  flavour (redirect packets to local machine).
-
 config NFT_MASQ_IPV4
 	tristate "IPv4 masquerading support for nf_tables"
 	depends on NF_TABLES_IPV4
@@ -123,7 +117,7 @@ config NFT_REDIR_IPV4
 	tristate "IPv4 redirect support for nf_tables"
 	depends on NF_TABLES_IPV4
 	depends on NFT_REDIR
-	select NF_NAT_REDIRECT_IPV4
+	select NF_NAT_REDIRECT
 	help
 	  This is the expression that provides IPv4 redirect support for
 	  nf_tables.
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 902bcd1597b..7fe6c703528 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -31,7 +31,6 @@ obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o
 obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o
 obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
 obj-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o
-obj-$(CONFIG_NF_NAT_REDIRECT_IPV4) += nf_nat_redirect_ipv4.o
 
 # NAT protocols (nf_nat)
 obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
diff --git a/net/ipv4/netfilter/nf_nat_redirect_ipv4.c b/net/ipv4/netfilter/nf_nat_redirect_ipv4.c
deleted file mode 100644
index a220552fc53..00000000000
--- a/net/ipv4/netfilter/nf_nat_redirect_ipv4.c
+++ /dev/null
@@ -1,82 +0,0 @@
-/*
- * (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
- * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Based on Rusty Russell's IPv4 REDIRECT target. Development of IPv6
- * NAT funded by Astaro.
- */
-
-#include <linux/if.h>
-#include <linux/inetdevice.h>
-#include <linux/ip.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/netfilter.h>
-#include <linux/types.h>
-#include <linux/netfilter_ipv4.h>
-#include <linux/netfilter/x_tables.h>
-#include <net/addrconf.h>
-#include <net/checksum.h>
-#include <net/protocol.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/ipv4/nf_nat_redirect.h>
-
-unsigned int
-nf_nat_redirect_ipv4(struct sk_buff *skb,
-		     const struct nf_nat_ipv4_multi_range_compat *mr,
-		     unsigned int hooknum)
-{
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	__be32 newdst;
-	struct nf_nat_range newrange;
-
-	NF_CT_ASSERT(hooknum == NF_INET_PRE_ROUTING ||
-		     hooknum == NF_INET_LOCAL_OUT);
-
-	ct = nf_ct_get(skb, &ctinfo);
-	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED));
-
-	/* Local packets: make them go to loopback */
-	if (hooknum == NF_INET_LOCAL_OUT) {
-		newdst = htonl(0x7F000001);
-	} else {
-		struct in_device *indev;
-		struct in_ifaddr *ifa;
-
-		newdst = 0;
-
-		rcu_read_lock();
-		indev = __in_dev_get_rcu(skb->dev);
-		if (indev != NULL) {
-			ifa = indev->ifa_list;
-			newdst = ifa->ifa_local;
-		}
-		rcu_read_unlock();
-
-		if (!newdst)
-			return NF_DROP;
-	}
-
-	/* Transfer from original range. */
-	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
-	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
-	newrange.flags	     = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS;
-	newrange.min_addr.ip = newdst;
-	newrange.max_addr.ip = newdst;
-	newrange.min_proto   = mr->range[0].min;
-	newrange.max_proto   = mr->range[0].max;
-
-	/* Hand modified range to generic setup. */
-	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
-}
-EXPORT_SYMBOL_GPL(nf_nat_redirect_ipv4);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
index 643c5967aa2..ff2d23d8c87 100644
--- a/net/ipv4/netfilter/nft_redir_ipv4.c
+++ b/net/ipv4/netfilter/nft_redir_ipv4.c
@@ -14,7 +14,7 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_nat.h>
-#include <net/netfilter/ipv4/nf_nat_redirect.h>
+#include <net/netfilter/nf_nat_redirect.h>
 #include <net/netfilter/nft_redir.h>
 
 static void nft_redir_ipv4_eval(const struct nft_expr *expr,
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 0dbe5c7953e..a069822936e 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -82,12 +82,6 @@ config NF_NAT_MASQUERADE_IPV6
 	  This is the kernel functionality to provide NAT in the masquerade
 	  flavour (automatic source address selection) for IPv6.
 
-config NF_NAT_REDIRECT_IPV6
-	tristate "IPv6 redirect support"
-	help
-	  This is the kernel functionality to provide NAT in the redirect
-	  flavour (redirect packet to local machine) for IPv6.
-
 config NFT_MASQ_IPV6
 	tristate "IPv6 masquerade support for nf_tables"
 	depends on NF_TABLES_IPV6
@@ -101,7 +95,7 @@ config NFT_REDIR_IPV6
 	tristate "IPv6 redirect support for nf_tables"
 	depends on NF_TABLES_IPV6
 	depends on NFT_REDIR
-	select NF_NAT_REDIRECT_IPV6
+	select NF_NAT_REDIRECT
 	help
 	  This is the expression that provides IPv4 redirect support for
 	  nf_tables.
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index d2ac9f5f212..c36e0a5490d 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o
 nf_nat_ipv6-y		:= nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o
 obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o
 obj-$(CONFIG_NF_NAT_MASQUERADE_IPV6) += nf_nat_masquerade_ipv6.o
-obj-$(CONFIG_NF_NAT_REDIRECT_IPV6) += nf_nat_redirect_ipv6.o
 
 # defrag
 nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
diff --git a/net/ipv6/netfilter/nf_nat_redirect_ipv6.c b/net/ipv6/netfilter/nf_nat_redirect_ipv6.c
deleted file mode 100644
index ea1308aeb04..00000000000
--- a/net/ipv6/netfilter/nf_nat_redirect_ipv6.c
+++ /dev/null
@@ -1,75 +0,0 @@
-/*
- * (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
- * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Based on Rusty Russell's IPv4 REDIRECT target. Development of IPv6
- * NAT funded by Astaro.
- */
-
-#include <linux/if.h>
-#include <linux/inetdevice.h>
-#include <linux/ip.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/netfilter.h>
-#include <linux/types.h>
-#include <linux/netfilter_ipv6.h>
-#include <linux/netfilter/x_tables.h>
-#include <net/addrconf.h>
-#include <net/checksum.h>
-#include <net/protocol.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/ipv6/nf_nat_redirect.h>
-
-static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT;
-
-unsigned int
-nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
-		     unsigned int hooknum)
-{
-	struct nf_nat_range newrange;
-	struct in6_addr newdst;
-	enum ip_conntrack_info ctinfo;
-	struct nf_conn *ct;
-
-	ct = nf_ct_get(skb, &ctinfo);
-	if (hooknum == NF_INET_LOCAL_OUT) {
-		newdst = loopback_addr;
-	} else {
-		struct inet6_dev *idev;
-		struct inet6_ifaddr *ifa;
-		bool addr = false;
-
-		rcu_read_lock();
-		idev = __in6_dev_get(skb->dev);
-		if (idev != NULL) {
-			list_for_each_entry(ifa, &idev->addr_list, if_list) {
-				newdst = ifa->addr;
-				addr = true;
-				break;
-			}
-		}
-		rcu_read_unlock();
-
-		if (!addr)
-			return NF_DROP;
-	}
-
-	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
-	newrange.min_addr.in6	= newdst;
-	newrange.max_addr.in6	= newdst;
-	newrange.min_proto	= range->min_proto;
-	newrange.max_proto	= range->max_proto;
-
-	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
-}
-EXPORT_SYMBOL_GPL(nf_nat_redirect_ipv6);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c
index 83420eeaad1..2433a6bfb19 100644
--- a/net/ipv6/netfilter/nft_redir_ipv6.c
+++ b/net/ipv6/netfilter/nft_redir_ipv6.c
@@ -15,7 +15,7 @@
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nft_redir.h>
-#include <net/netfilter/ipv6/nf_nat_redirect.h>
+#include <net/netfilter/nf_nat_redirect.h>
 
 static void nft_redir_ipv6_eval(const struct nft_expr *expr,
 				struct nft_data data[NFT_REG_MAX + 1],
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 57f15a9aa48..b02660fa9eb 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -411,6 +411,13 @@ config NF_NAT_TFTP
 	depends on NF_CONNTRACK && NF_NAT
 	default NF_NAT && NF_CONNTRACK_TFTP
 
+config NF_NAT_REDIRECT
+        tristate "IPv4/IPv6 redirect support"
+	depends on NF_NAT
+        help
+          This is the kernel functionality to redirect packets to local
+          machine through NAT.
+
 config NETFILTER_SYNPROXY
 	tristate
 
@@ -844,8 +851,7 @@ config NETFILTER_XT_TARGET_RATEEST
 config NETFILTER_XT_TARGET_REDIRECT
 	tristate "REDIRECT target support"
 	depends on NF_NAT
-	select NF_NAT_REDIRECT_IPV4 if NF_NAT_IPV4
-	select NF_NAT_REDIRECT_IPV6 if NF_NAT_IPV6
+	select NF_NAT_REDIRECT
 	---help---
 	REDIRECT is a special case of NAT: all incoming connections are
 	mapped onto the incoming interface's address, causing the packets to
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index f3eb4680f2e..89f73a9e987 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -51,6 +51,7 @@ nf_nat-y	:= nf_nat_core.o nf_nat_proto_unknown.o nf_nat_proto_common.o \
 obj-$(CONFIG_NF_LOG_COMMON) += nf_log_common.o
 
 obj-$(CONFIG_NF_NAT) += nf_nat.o
+obj-$(CONFIG_NF_NAT_REDIRECT) += nf_nat_redirect.o
 
 # NAT protocols (nf_nat)
 obj-$(CONFIG_NF_NAT_PROTO_DCCP) += nf_nat_proto_dccp.o
diff --git a/net/netfilter/nf_nat_redirect.c b/net/netfilter/nf_nat_redirect.c
new file mode 100644
index 00000000000..97b75f9bfbc
--- /dev/null
+++ b/net/netfilter/nf_nat_redirect.c
@@ -0,0 +1,127 @@
+/*
+ * (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on Rusty Russell's IPv4 REDIRECT target. Development of IPv6
+ * NAT funded by Astaro.
+ */
+
+#include <linux/if.h>
+#include <linux/inetdevice.h>
+#include <linux/ip.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/netfilter.h>
+#include <linux/types.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/addrconf.h>
+#include <net/checksum.h>
+#include <net/protocol.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_nat_redirect.h>
+
+unsigned int
+nf_nat_redirect_ipv4(struct sk_buff *skb,
+		     const struct nf_nat_ipv4_multi_range_compat *mr,
+		     unsigned int hooknum)
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	__be32 newdst;
+	struct nf_nat_range newrange;
+
+	NF_CT_ASSERT(hooknum == NF_INET_PRE_ROUTING ||
+		     hooknum == NF_INET_LOCAL_OUT);
+
+	ct = nf_ct_get(skb, &ctinfo);
+	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED));
+
+	/* Local packets: make them go to loopback */
+	if (hooknum == NF_INET_LOCAL_OUT) {
+		newdst = htonl(0x7F000001);
+	} else {
+		struct in_device *indev;
+		struct in_ifaddr *ifa;
+
+		newdst = 0;
+
+		rcu_read_lock();
+		indev = __in_dev_get_rcu(skb->dev);
+		if (indev != NULL) {
+			ifa = indev->ifa_list;
+			newdst = ifa->ifa_local;
+		}
+		rcu_read_unlock();
+
+		if (!newdst)
+			return NF_DROP;
+	}
+
+	/* Transfer from original range. */
+	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
+	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
+	newrange.flags	     = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.ip = newdst;
+	newrange.max_addr.ip = newdst;
+	newrange.min_proto   = mr->range[0].min;
+	newrange.max_proto   = mr->range[0].max;
+
+	/* Hand modified range to generic setup. */
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
+}
+EXPORT_SYMBOL_GPL(nf_nat_redirect_ipv4);
+
+static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT;
+
+unsigned int
+nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+		     unsigned int hooknum)
+{
+	struct nf_nat_range newrange;
+	struct in6_addr newdst;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (hooknum == NF_INET_LOCAL_OUT) {
+		newdst = loopback_addr;
+	} else {
+		struct inet6_dev *idev;
+		struct inet6_ifaddr *ifa;
+		bool addr = false;
+
+		rcu_read_lock();
+		idev = __in6_dev_get(skb->dev);
+		if (idev != NULL) {
+			list_for_each_entry(ifa, &idev->addr_list, if_list) {
+				newdst = ifa->addr;
+				addr = true;
+				break;
+			}
+		}
+		rcu_read_unlock();
+
+		if (!addr)
+			return NF_DROP;
+	}
+
+	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.in6	= newdst;
+	newrange.max_addr.in6	= newdst;
+	newrange.min_proto	= range->min_proto;
+	newrange.max_proto	= range->max_proto;
+
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
+}
+EXPORT_SYMBOL_GPL(nf_nat_redirect_ipv6);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
diff --git a/net/netfilter/xt_REDIRECT.c b/net/netfilter/xt_REDIRECT.c
index b6ec67efd90..03f0b370e17 100644
--- a/net/netfilter/xt_REDIRECT.c
+++ b/net/netfilter/xt_REDIRECT.c
@@ -26,8 +26,7 @@
 #include <net/checksum.h>
 #include <net/protocol.h>
 #include <net/netfilter/nf_nat.h>
-#include <net/netfilter/ipv4/nf_nat_redirect.h>
-#include <net/netfilter/ipv6/nf_nat_redirect.h>
+#include <net/netfilter/nf_nat_redirect.h>
 
 static unsigned int
 redirect_tg6(struct sk_buff *skb, const struct xt_action_param *par)
-- 
cgit v1.2.3-70-g09d2


From 5f42424354f5b0ca5413b4fb8528d150692c85b7 Mon Sep 17 00:00:00 2001
From: Rojhalat Ibrahim <imr@rtschenk.de>
Date: Tue, 4 Nov 2014 17:12:06 +0100
Subject: gpiolib: allow simultaneous setting of multiple GPIO outputs

Introduce new functions gpiod_set_array & gpiod_set_raw_array to the consumer
interface which allow setting multiple outputs with just one function call.
Also add an optional set_multiple function to the driver interface. Without an
implementation of that function in the chip driver outputs are set
sequentially.

Implementing the set_multiple function in a chip driver allows for:
- Improved performance for certain use cases. The original motivation for this
  was the task of configuring an FPGA. In that specific case, where 9 GPIO
  lines have to be set many times, configuration time goes down from 48 s to
  20 s when using the new function.
- Simultaneous glitch-free setting of multiple pins on any kind of parallel
  bus attached to GPIOs provided they all reside on the same chip and bank.

Limitations:
  Performance is only improved for normal high-low outputs. Open drain and
  open source outputs are always set separately from each other. Those kinds
  of outputs could probably be accelerated in a similar way if we could
  forgo the error checking when setting GPIO directions.

Change log:
  v6: - rebase on current linux-gpio devel branch
  v5: - check can_sleep property per chip
      - remove superfluous checks
      - supplement documentation
  v4: - add gpiod_set_array function for setting logical values
      - change interface of the set_multiple driver function to use
        unsigned long as type for the bit fields
      - use generic bitops (which also use unsigned long for bit fields)
      - do not use ARCH_NR_GPIOS any more
  v3: - add documentation
      - change commit message
  v2: - use descriptor interface
      - allow arbitrary groups of GPIOs spanning multiple chips

Signed-off-by: Rojhalat Ibrahim <imr@rtschenk.de>
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Mark Brown <broonie@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/gpio/consumer.txt |  27 +++++++
 drivers/gpio/gpiolib.c          | 168 ++++++++++++++++++++++++++++++++++++++++
 include/linux/gpio/consumer.h   |  38 +++++++++
 include/linux/gpio/driver.h     |   4 +
 4 files changed, 237 insertions(+)

(limited to 'include')

diff --git a/Documentation/gpio/consumer.txt b/Documentation/gpio/consumer.txt
index 6ce544191ca..c67f806401a 100644
--- a/Documentation/gpio/consumer.txt
+++ b/Documentation/gpio/consumer.txt
@@ -199,6 +199,33 @@ The active-low state of a GPIO can also be queried using the following call:
 Note that these functions should only be used with great moderation ; a driver
 should not have to care about the physical line level.
 
+
+Set multiple GPIO outputs with a single function call
+-----------------------------------------------------
+The following functions set the output values of an array of GPIOs:
+
+	void gpiod_set_array(unsigned int array_size,
+			     struct gpio_desc **desc_array,
+			     int *value_array)
+	void gpiod_set_raw_array(unsigned int array_size,
+				 struct gpio_desc **desc_array,
+				 int *value_array)
+	void gpiod_set_array_cansleep(unsigned int array_size,
+				      struct gpio_desc **desc_array,
+				      int *value_array)
+	void gpiod_set_raw_array_cansleep(unsigned int array_size,
+					  struct gpio_desc **desc_array,
+					  int *value_array)
+
+The array can be an arbitrary set of GPIOs. The functions will try to set
+GPIOs belonging to the same bank or chip simultaneously if supported by the
+corresponding chip driver. In that case a significantly improved performance
+can be expected. If simultaneous setting is not possible the GPIOs will be set
+sequentially.
+Note that for optimal performance GPIOs belonging to the same chip should be
+contiguous within the array of descriptors.
+
+
 GPIOs mapped to IRQs
 --------------------
 GPIO lines can quite often be used as IRQs. You can get the IRQ number
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 50e18a4b3a9..eb739a51e77 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1254,6 +1254,88 @@ static void _gpiod_set_raw_value(struct gpio_desc *desc, bool value)
 		chip->set(chip, gpio_chip_hwgpio(desc), value);
 }
 
+/*
+ * set multiple outputs on the same chip;
+ * use the chip's set_multiple function if available;
+ * otherwise set the outputs sequentially;
+ * @mask: bit mask array; one bit per output; BITS_PER_LONG bits per word
+ *        defines which outputs are to be changed
+ * @bits: bit value array; one bit per output; BITS_PER_LONG bits per word
+ *        defines the values the outputs specified by mask are to be set to
+ */
+static void gpio_chip_set_multiple(struct gpio_chip *chip,
+				   unsigned long *mask, unsigned long *bits)
+{
+	if (chip->set_multiple) {
+		chip->set_multiple(chip, mask, bits);
+	} else {
+		int i;
+		for (i = 0; i < chip->ngpio; i++) {
+			if (mask[BIT_WORD(i)] == 0) {
+				/* no more set bits in this mask word;
+				 * skip ahead to the next word */
+				i = (BIT_WORD(i) + 1) * BITS_PER_LONG - 1;
+				continue;
+			}
+			/* set outputs if the corresponding mask bit is set */
+			if (__test_and_clear_bit(i, mask)) {
+				chip->set(chip, i, test_bit(i, bits));
+			}
+		}
+	}
+}
+
+static void gpiod_set_array_priv(bool raw, bool can_sleep,
+				 unsigned int array_size,
+				 struct gpio_desc **desc_array,
+				 int *value_array)
+{
+	int i = 0;
+
+	while (i < array_size) {
+		struct gpio_chip *chip = desc_array[i]->chip;
+		unsigned long mask[BITS_TO_LONGS(chip->ngpio)];
+		unsigned long bits[BITS_TO_LONGS(chip->ngpio)];
+		int count = 0;
+
+		if (!can_sleep) {
+			WARN_ON(chip->can_sleep);
+		}
+		memset(mask, 0, sizeof(mask));
+		do {
+			struct gpio_desc *desc = desc_array[i];
+			int hwgpio = gpio_chip_hwgpio(desc);
+			int value = value_array[i];
+
+			if (!raw && test_bit(FLAG_ACTIVE_LOW, &desc->flags))
+				value = !value;
+			trace_gpio_value(desc_to_gpio(desc), 0, value);
+			/*
+			 * collect all normal outputs belonging to the same chip
+			 * open drain and open source outputs are set individually
+			 */
+			if (test_bit(FLAG_OPEN_DRAIN, &desc->flags)) {
+				_gpio_set_open_drain_value(desc,value);
+			} else if (test_bit(FLAG_OPEN_SOURCE, &desc->flags)) {
+				_gpio_set_open_source_value(desc, value);
+			} else {
+				__set_bit(hwgpio, mask);
+				if (value) {
+					__set_bit(hwgpio, bits);
+				} else {
+					__clear_bit(hwgpio, bits);
+				}
+				count++;
+			}
+			i++;
+		} while ((i < array_size) && (desc_array[i]->chip == chip));
+		/* push collected bits to outputs */
+		if (count != 0) {
+			gpio_chip_set_multiple(chip, mask, bits);
+		}
+	}
+}
+
 /**
  * gpiod_set_raw_value() - assign a gpio's raw value
  * @desc: gpio whose value will be assigned
@@ -1298,6 +1380,48 @@ void gpiod_set_value(struct gpio_desc *desc, int value)
 }
 EXPORT_SYMBOL_GPL(gpiod_set_value);
 
+/**
+ * gpiod_set_raw_array() - assign values to an array of GPIOs
+ * @array_size: number of elements in the descriptor / value arrays
+ * @desc_array: array of GPIO descriptors whose values will be assigned
+ * @value_array: array of values to assign
+ *
+ * Set the raw values of the GPIOs, i.e. the values of the physical lines
+ * without regard for their ACTIVE_LOW status.
+ *
+ * This function should be called from contexts where we cannot sleep, and will
+ * complain if the GPIO chip functions potentially sleep.
+ */
+void gpiod_set_raw_array(unsigned int array_size,
+			 struct gpio_desc **desc_array, int *value_array)
+{
+	if (!desc_array)
+		return;
+	gpiod_set_array_priv(true, false, array_size, desc_array, value_array);
+}
+EXPORT_SYMBOL_GPL(gpiod_set_raw_array);
+
+/**
+ * gpiod_set_array() - assign values to an array of GPIOs
+ * @array_size: number of elements in the descriptor / value arrays
+ * @desc_array: array of GPIO descriptors whose values will be assigned
+ * @value_array: array of values to assign
+ *
+ * Set the logical values of the GPIOs, i.e. taking their ACTIVE_LOW status
+ * into account.
+ *
+ * This function should be called from contexts where we cannot sleep, and will
+ * complain if the GPIO chip functions potentially sleep.
+ */
+void gpiod_set_array(unsigned int array_size,
+		     struct gpio_desc **desc_array, int *value_array)
+{
+	if (!desc_array)
+		return;
+	gpiod_set_array_priv(false, false, array_size, desc_array, value_array);
+}
+EXPORT_SYMBOL_GPL(gpiod_set_array);
+
 /**
  * gpiod_cansleep() - report whether gpio value access may sleep
  * @desc: gpio to check
@@ -1457,6 +1581,50 @@ void gpiod_set_value_cansleep(struct gpio_desc *desc, int value)
 }
 EXPORT_SYMBOL_GPL(gpiod_set_value_cansleep);
 
+/**
+ * gpiod_set_raw_array_cansleep() - assign values to an array of GPIOs
+ * @array_size: number of elements in the descriptor / value arrays
+ * @desc_array: array of GPIO descriptors whose values will be assigned
+ * @value_array: array of values to assign
+ *
+ * Set the raw values of the GPIOs, i.e. the values of the physical lines
+ * without regard for their ACTIVE_LOW status.
+ *
+ * This function is to be called from contexts that can sleep.
+ */
+void gpiod_set_raw_array_cansleep(unsigned int array_size,
+				  struct gpio_desc **desc_array,
+				  int *value_array)
+{
+	might_sleep_if(extra_checks);
+	if (!desc_array)
+		return;
+	gpiod_set_array_priv(true, true, array_size, desc_array, value_array);
+}
+EXPORT_SYMBOL_GPL(gpiod_set_raw_array_cansleep);
+
+/**
+ * gpiod_set_array_cansleep() - assign values to an array of GPIOs
+ * @array_size: number of elements in the descriptor / value arrays
+ * @desc_array: array of GPIO descriptors whose values will be assigned
+ * @value_array: array of values to assign
+ *
+ * Set the logical values of the GPIOs, i.e. taking their ACTIVE_LOW status
+ * into account.
+ *
+ * This function is to be called from contexts that can sleep.
+ */
+void gpiod_set_array_cansleep(unsigned int array_size,
+			      struct gpio_desc **desc_array,
+			      int *value_array)
+{
+	might_sleep_if(extra_checks);
+	if (!desc_array)
+		return;
+	gpiod_set_array_priv(false, true, array_size, desc_array, value_array);
+}
+EXPORT_SYMBOL_GPL(gpiod_set_array_cansleep);
+
 /**
  * gpiod_add_lookup_table() - register GPIO device consumers
  * @table: table of consumers to register
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 12f146fa660..83c0a61c605 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -74,14 +74,24 @@ int gpiod_direction_output_raw(struct gpio_desc *desc, int value);
 /* Value get/set from non-sleeping context */
 int gpiod_get_value(const struct gpio_desc *desc);
 void gpiod_set_value(struct gpio_desc *desc, int value);
+void gpiod_set_array(unsigned int array_size,
+		     struct gpio_desc **desc_array, int *value_array);
 int gpiod_get_raw_value(const struct gpio_desc *desc);
 void gpiod_set_raw_value(struct gpio_desc *desc, int value);
+void gpiod_set_raw_array(unsigned int array_size,
+			 struct gpio_desc **desc_array, int *value_array);
 
 /* Value get/set from sleeping context */
 int gpiod_get_value_cansleep(const struct gpio_desc *desc);
 void gpiod_set_value_cansleep(struct gpio_desc *desc, int value);
+void gpiod_set_array_cansleep(unsigned int array_size,
+			      struct gpio_desc **desc_array,
+			      int *value_array);
 int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc);
 void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value);
+void gpiod_set_raw_array_cansleep(unsigned int array_size,
+				  struct gpio_desc **desc_array,
+				  int *value_array);
 
 int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce);
 
@@ -210,6 +220,13 @@ static inline void gpiod_set_value(struct gpio_desc *desc, int value)
 	/* GPIO can never have been requested */
 	WARN_ON(1);
 }
+static inline void gpiod_set_array(unsigned int array_size,
+				   struct gpio_desc **desc_array,
+				   int *value_array)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+}
 static inline int gpiod_get_raw_value(const struct gpio_desc *desc)
 {
 	/* GPIO can never have been requested */
@@ -221,6 +238,13 @@ static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value)
 	/* GPIO can never have been requested */
 	WARN_ON(1);
 }
+static inline void gpiod_set_raw_array(unsigned int array_size,
+				       struct gpio_desc **desc_array,
+				       int *value_array)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+}
 
 static inline int gpiod_get_value_cansleep(const struct gpio_desc *desc)
 {
@@ -233,6 +257,13 @@ static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value)
 	/* GPIO can never have been requested */
 	WARN_ON(1);
 }
+static inline void gpiod_set_array_cansleep(unsigned int array_size,
+					    struct gpio_desc **desc_array,
+					    int *value_array)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+}
 static inline int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc)
 {
 	/* GPIO can never have been requested */
@@ -245,6 +276,13 @@ static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc,
 	/* GPIO can never have been requested */
 	WARN_ON(1);
 }
+static inline void gpiod_set_raw_array_cansleep(unsigned int array_size,
+						struct gpio_desc **desc_array,
+						int *value_array)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+}
 
 static inline int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce)
 {
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index ff200a75501..c497c62889d 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -32,6 +32,7 @@ struct seq_file;
  * @get: returns value for signal "offset"; for output signals this
  *	returns either the value actually sensed, or zero
  * @set: assigns output value for signal "offset"
+ * @set_multiple: assigns output values for multiple signals defined by "mask"
  * @set_debounce: optional hook for setting debounce time for specified gpio in
  *      interrupt triggered gpio chips
  * @to_irq: optional hook supporting non-static gpio_to_irq() mappings;
@@ -89,6 +90,9 @@ struct gpio_chip {
 						unsigned offset);
 	void			(*set)(struct gpio_chip *chip,
 						unsigned offset, int value);
+	void			(*set_multiple)(struct gpio_chip *chip,
+						unsigned long *mask,
+						unsigned long *bits);
 	int			(*set_debounce)(struct gpio_chip *chip,
 						unsigned offset,
 						unsigned debounce);
-- 
cgit v1.2.3-70-g09d2


From 79855d178557cc3e3ffd179fd26a64cef48dfb30 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 5 Nov 2014 10:36:28 +0100
Subject: libsas: remove task_collector mode

The task_collector mode (or "latency_injector", (C) Dan Willians) is an
optional I/O path in libsas that queues up scsi commands instead of
directly sending it to the hardware.  It generall increases latencies
to in the optiomal case slightly reduce mmio traffic to the hardware.

Only the obsolete aic94xx driver and the mvsas driver allowed to use
it without recompiling the kernel, and most drivers didn't support it
at all.

Remove the giant blob of code to allow better optimizations for scsi-mq
in the future.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Dan Williams <dan.j.williams@intel.com>
---
 Documentation/scsi/libsas.txt       |  82 +----------------
 drivers/scsi/aic94xx/aic94xx.h      |   2 +-
 drivers/scsi/aic94xx/aic94xx_hwi.c  |   3 +-
 drivers/scsi/aic94xx/aic94xx_init.c |  11 ---
 drivers/scsi/aic94xx/aic94xx_task.c |  13 ++-
 drivers/scsi/isci/init.c            |   2 -
 drivers/scsi/isci/task.c            | 147 ++++++++++++++----------------
 drivers/scsi/isci/task.h            |   1 -
 drivers/scsi/libsas/sas_ata.c       |   9 +-
 drivers/scsi/libsas/sas_expander.c  |   2 +-
 drivers/scsi/libsas/sas_init.c      |  21 -----
 drivers/scsi/libsas/sas_internal.h  |   2 -
 drivers/scsi/libsas/sas_scsi_host.c | 176 +-----------------------------------
 drivers/scsi/mvsas/mv_init.c        |  22 -----
 drivers/scsi/mvsas/mv_sas.c         | 109 +---------------------
 drivers/scsi/mvsas/mv_sas.h         |  10 +-
 drivers/scsi/pm8001/pm8001_init.c   |   2 -
 drivers/scsi/pm8001/pm8001_sas.c    |  22 +----
 drivers/scsi/pm8001/pm8001_sas.h    |   3 +-
 include/scsi/libsas.h               |  14 +--
 20 files changed, 97 insertions(+), 556 deletions(-)

(limited to 'include')

diff --git a/Documentation/scsi/libsas.txt b/Documentation/scsi/libsas.txt
index 3cc9c7843e1..8cac6492aad 100644
--- a/Documentation/scsi/libsas.txt
+++ b/Documentation/scsi/libsas.txt
@@ -226,9 +226,6 @@ static int register_sas_ha(struct my_sas_ha *my_ha)
 	my_ha->sas_ha.lldd_dev_found = my_dev_found;
 	my_ha->sas_ha.lldd_dev_gone = my_dev_gone;
 
-	my_ha->sas_ha.lldd_max_execute_num = lldd_max_execute_num; (1)
-
-	my_ha->sas_ha.lldd_queue_size = ha_can_queue;
 	my_ha->sas_ha.lldd_execute_task = my_execute_task;
 
 	my_ha->sas_ha.lldd_abort_task     = my_abort_task;
@@ -247,28 +244,6 @@ static int register_sas_ha(struct my_sas_ha *my_ha)
 	return sas_register_ha(&my_ha->sas_ha);
 }
 
-(1) This is normally a LLDD parameter, something of the
-lines of a task collector.  What it tells the SAS Layer is
-whether the SAS layer should run in Direct Mode (default:
-value 0 or 1) or Task Collector Mode (value greater than 1).
-
-In Direct Mode, the SAS Layer calls Execute Task as soon as
-it has a command to send to the SDS, _and_ this is a single
-command, i.e. not linked.
-
-Some hardware (e.g. aic94xx) has the capability to DMA more
-than one task at a time (interrupt) from host memory.  Task
-Collector Mode is an optional feature for HAs which support
-this in their hardware.  (Again, it is completely optional
-even if your hardware supports it.)
-
-In Task Collector Mode, the SAS Layer would do _natural_
-coalescing of tasks and at the appropriate moment it would
-call your driver to DMA more than one task in a single HA
-interrupt. DMBS may want to use this by insmod/modprobe
-setting the lldd_max_execute_num to something greater than
-1.
-
 (2) SAS 1.1 does not define I_T Nexus Reset TMF.
 
 Events
@@ -325,71 +300,22 @@ PHYE_SPINUP_HOLD -- SATA is present, COMWAKE not sent.
 
 The Execute Command SCSI RPC:
 
-	int (*lldd_execute_task)(struct sas_task *, int num,
-				 unsigned long gfp_flags);
+	int (*lldd_execute_task)(struct sas_task *, gfp_t gfp_flags);
 
-Used to queue a task to the SAS LLDD.  @task is the tasks to
-be executed.  @num should be the number of tasks being
-queued at this function call (they are linked listed via
-task::list), @gfp_mask should be the gfp_mask defining the
-context of the caller.
+Used to queue a task to the SAS LLDD.  @task is the task to be executed.
+@gfp_mask is the gfp_mask defining the context of the caller.
 
 This function should implement the Execute Command SCSI RPC,
-or if you're sending a SCSI Task as linked commands, you
-should also use this function.
 
-That is, when lldd_execute_task() is called, the command(s)
+That is, when lldd_execute_task() is called, the command
 go out on the transport *immediately*.  There is *no*
 queuing of any sort and at any level in a SAS LLDD.
 
-The use of task::list is two-fold, one for linked commands,
-the other discussed below.
-
-It is possible to queue up more than one task at a time, by
-initializing the list element of struct sas_task, and
-passing the number of tasks enlisted in this manner in num.
-
 Returns: -SAS_QUEUE_FULL, -ENOMEM, nothing was queued;
 	 0, the task(s) were queued.
 
-If you want to pass num > 1, then either
-A) you're the only caller of this function and keep track
-   of what you've queued to the LLDD, or
-B) you know what you're doing and have a strategy of
-   retrying.
-
-As opposed to queuing one task at a time (function call),
-batch queuing of tasks, by having num > 1, greatly
-simplifies LLDD code, sequencer code, and _hardware design_,
-and has some performance advantages in certain situations
-(DBMS).
-
-The LLDD advertises if it can take more than one command at
-a time at lldd_execute_task(), by setting the
-lldd_max_execute_num parameter (controlled by "collector"
-module parameter in aic94xx SAS LLDD).
-
-You should leave this to the default 1, unless you know what
-you're doing.
-
-This is a function of the LLDD, to which the SAS layer can
-cater to.
-
-int lldd_queue_size
-	The host adapter's queue size.  This is the maximum
-number of commands the lldd can have pending to domain
-devices on behalf of all upper layers submitting through
-lldd_execute_task().
-
-You really want to set this to something (much) larger than
-1.
-
-This _really_ has absolutely nothing to do with queuing.
-There is no queuing in SAS LLDDs.
-
 struct sas_task {
 	dev -- the device this task is destined to
-	list -- must be initialized (INIT_LIST_HEAD)
 	task_proto -- _one_ of enum sas_proto
 	scatter -- pointer to scatter gather list array
 	num_scatter -- number of elements in scatter
diff --git a/drivers/scsi/aic94xx/aic94xx.h b/drivers/scsi/aic94xx/aic94xx.h
index 66cda669b41..26d4ad9ede2 100644
--- a/drivers/scsi/aic94xx/aic94xx.h
+++ b/drivers/scsi/aic94xx/aic94xx.h
@@ -78,7 +78,7 @@ void asd_dev_gone(struct domain_device *dev);
 
 void asd_invalidate_edb(struct asd_ascb *ascb, int edb_id);
 
-int  asd_execute_task(struct sas_task *, int num, gfp_t gfp_flags);
+int  asd_execute_task(struct sas_task *task, gfp_t gfp_flags);
 
 void asd_set_dmamode(struct domain_device *dev);
 
diff --git a/drivers/scsi/aic94xx/aic94xx_hwi.c b/drivers/scsi/aic94xx/aic94xx_hwi.c
index 4df867e07b2..9f636a34d59 100644
--- a/drivers/scsi/aic94xx/aic94xx_hwi.c
+++ b/drivers/scsi/aic94xx/aic94xx_hwi.c
@@ -1200,8 +1200,7 @@ static void asd_start_scb_timers(struct list_head *list)
  * Case A: we can send the whole batch at once.  Increment "pending"
  * in the beginning of this function, when it is checked, in order to
  * eliminate races when this function is called by multiple processes.
- * Case B: should never happen if the managing layer considers
- * lldd_queue_size.
+ * Case B: should never happen.
  */
 int asd_post_ascb_list(struct asd_ha_struct *asd_ha, struct asd_ascb *ascb,
 		       int num)
diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c
index a64cf932d03..14fc018436c 100644
--- a/drivers/scsi/aic94xx/aic94xx_init.c
+++ b/drivers/scsi/aic94xx/aic94xx_init.c
@@ -49,14 +49,6 @@ MODULE_PARM_DESC(use_msi, "\n"
 	"\tEnable(1) or disable(0) using PCI MSI.\n"
 	"\tDefault: 0");
 
-static int lldd_max_execute_num = 0;
-module_param_named(collector, lldd_max_execute_num, int, S_IRUGO);
-MODULE_PARM_DESC(collector, "\n"
-	"\tIf greater than one, tells the SAS Layer to run in Task Collector\n"
-	"\tMode.  If 1 or 0, tells the SAS Layer to run in Direct Mode.\n"
-	"\tThe aic94xx SAS LLDD supports both modes.\n"
-	"\tDefault: 0 (Direct Mode).\n");
-
 static struct scsi_transport_template *aic94xx_transport_template;
 static int asd_scan_finished(struct Scsi_Host *, unsigned long);
 static void asd_scan_start(struct Scsi_Host *);
@@ -711,9 +703,6 @@ static int asd_register_sas_ha(struct asd_ha_struct *asd_ha)
 	asd_ha->sas_ha.sas_port= sas_ports;
 	asd_ha->sas_ha.num_phys= ASD_MAX_PHYS;
 
-	asd_ha->sas_ha.lldd_queue_size = asd_ha->seq.can_queue;
-	asd_ha->sas_ha.lldd_max_execute_num = lldd_max_execute_num;
-
 	return sas_register_ha(&asd_ha->sas_ha);
 }
 
diff --git a/drivers/scsi/aic94xx/aic94xx_task.c b/drivers/scsi/aic94xx/aic94xx_task.c
index 59b86e260ce..5ff1ce7ba1f 100644
--- a/drivers/scsi/aic94xx/aic94xx_task.c
+++ b/drivers/scsi/aic94xx/aic94xx_task.c
@@ -543,8 +543,7 @@ static int asd_can_queue(struct asd_ha_struct *asd_ha, int num)
 	return res;
 }
 
-int asd_execute_task(struct sas_task *task, const int num,
-		     gfp_t gfp_flags)
+int asd_execute_task(struct sas_task *task, gfp_t gfp_flags)
 {
 	int res = 0;
 	LIST_HEAD(alist);
@@ -553,11 +552,11 @@ int asd_execute_task(struct sas_task *task, const int num,
 	struct asd_ha_struct *asd_ha = task->dev->port->ha->lldd_ha;
 	unsigned long flags;
 
-	res = asd_can_queue(asd_ha, num);
+	res = asd_can_queue(asd_ha, 1);
 	if (res)
 		return res;
 
-	res = num;
+	res = 1;
 	ascb = asd_ascb_alloc_list(asd_ha, &res, gfp_flags);
 	if (res) {
 		res = -ENOMEM;
@@ -568,7 +567,7 @@ int asd_execute_task(struct sas_task *task, const int num,
 	list_for_each_entry(a, &alist, list) {
 		a->uldd_task = t;
 		t->lldd_task = a;
-		t = list_entry(t->list.next, struct sas_task, list);
+		break;
 	}
 	list_for_each_entry(a, &alist, list) {
 		t = a->uldd_task;
@@ -601,7 +600,7 @@ int asd_execute_task(struct sas_task *task, const int num,
 	}
 	list_del_init(&alist);
 
-	res = asd_post_ascb_list(asd_ha, ascb, num);
+	res = asd_post_ascb_list(asd_ha, ascb, 1);
 	if (unlikely(res)) {
 		a = NULL;
 		__list_add(&alist, ascb->list.prev, &ascb->list);
@@ -639,6 +638,6 @@ out_err_unmap:
 out_err:
 	if (ascb)
 		asd_ascb_free_list(ascb);
-	asd_can_dequeue(asd_ha, num);
+	asd_can_dequeue(asd_ha, 1);
 	return res;
 }
diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c
index a81e546595d..724c6265b66 100644
--- a/drivers/scsi/isci/init.c
+++ b/drivers/scsi/isci/init.c
@@ -260,8 +260,6 @@ static int isci_register_sas_ha(struct isci_host *isci_host)
 	sas_ha->sas_port = sas_ports;
 	sas_ha->num_phys = SCI_MAX_PHYS;
 
-	sas_ha->lldd_queue_size = ISCI_CAN_QUEUE_VAL;
-	sas_ha->lldd_max_execute_num = 1;
 	sas_ha->strict_wide_ports = 1;
 
 	sas_register_ha(sas_ha);
diff --git a/drivers/scsi/isci/task.c b/drivers/scsi/isci/task.c
index 5d6fda72d65..3f63c6318b0 100644
--- a/drivers/scsi/isci/task.c
+++ b/drivers/scsi/isci/task.c
@@ -117,104 +117,97 @@ static inline int isci_device_io_ready(struct isci_remote_device *idev,
  *    functions. This function is called by libsas to send a task down to
  *    hardware.
  * @task: This parameter specifies the SAS task to send.
- * @num: This parameter specifies the number of tasks to queue.
  * @gfp_flags: This parameter specifies the context of this call.
  *
  * status, zero indicates success.
  */
-int isci_task_execute_task(struct sas_task *task, int num, gfp_t gfp_flags)
+int isci_task_execute_task(struct sas_task *task, gfp_t gfp_flags)
 {
 	struct isci_host *ihost = dev_to_ihost(task->dev);
 	struct isci_remote_device *idev;
 	unsigned long flags;
+	enum sci_status status = SCI_FAILURE;
 	bool io_ready;
 	u16 tag;
 
-	dev_dbg(&ihost->pdev->dev, "%s: num=%d\n", __func__, num);
+	spin_lock_irqsave(&ihost->scic_lock, flags);
+	idev = isci_lookup_device(task->dev);
+	io_ready = isci_device_io_ready(idev, task);
+	tag = isci_alloc_tag(ihost);
+	spin_unlock_irqrestore(&ihost->scic_lock, flags);
 
-	for_each_sas_task(num, task) {
-		enum sci_status status = SCI_FAILURE;
+	dev_dbg(&ihost->pdev->dev,
+		"task: %p, dev: %p idev: %p:%#lx cmd = %p\n",
+		task, task->dev, idev, idev ? idev->flags : 0,
+		task->uldd_task);
 
-		spin_lock_irqsave(&ihost->scic_lock, flags);
-		idev = isci_lookup_device(task->dev);
-		io_ready = isci_device_io_ready(idev, task);
-		tag = isci_alloc_tag(ihost);
-		spin_unlock_irqrestore(&ihost->scic_lock, flags);
+	if (!idev) {
+		isci_task_refuse(ihost, task, SAS_TASK_UNDELIVERED,
+				 SAS_DEVICE_UNKNOWN);
+	} else if (!io_ready || tag == SCI_CONTROLLER_INVALID_IO_TAG) {
+		/* Indicate QUEUE_FULL so that the scsi midlayer
+		 * retries.
+		  */
+		isci_task_refuse(ihost, task, SAS_TASK_COMPLETE,
+				 SAS_QUEUE_FULL);
+	} else {
+		/* There is a device and it's ready for I/O. */
+		spin_lock_irqsave(&task->task_state_lock, flags);
 
-		dev_dbg(&ihost->pdev->dev,
-			"task: %p, num: %d dev: %p idev: %p:%#lx cmd = %p\n",
-			task, num, task->dev, idev, idev ? idev->flags : 0,
-			task->uldd_task);
-
-		if (!idev) {
-			isci_task_refuse(ihost, task, SAS_TASK_UNDELIVERED,
-					 SAS_DEVICE_UNKNOWN);
-		} else if (!io_ready || tag == SCI_CONTROLLER_INVALID_IO_TAG) {
-			/* Indicate QUEUE_FULL so that the scsi midlayer
-			 * retries.
-			  */
-			isci_task_refuse(ihost, task, SAS_TASK_COMPLETE,
-					 SAS_QUEUE_FULL);
+		if (task->task_state_flags & SAS_TASK_STATE_ABORTED) {
+			/* The I/O was aborted. */
+			spin_unlock_irqrestore(&task->task_state_lock, flags);
+
+			isci_task_refuse(ihost, task,
+					 SAS_TASK_UNDELIVERED,
+					 SAM_STAT_TASK_ABORTED);
 		} else {
-			/* There is a device and it's ready for I/O. */
-			spin_lock_irqsave(&task->task_state_lock, flags);
-
-			if (task->task_state_flags & SAS_TASK_STATE_ABORTED) {
-				/* The I/O was aborted. */
-				spin_unlock_irqrestore(&task->task_state_lock,
-						       flags);
-
-				isci_task_refuse(ihost, task,
-						 SAS_TASK_UNDELIVERED,
-						 SAM_STAT_TASK_ABORTED);
-			} else {
-				task->task_state_flags |= SAS_TASK_AT_INITIATOR;
+			task->task_state_flags |= SAS_TASK_AT_INITIATOR;
+			spin_unlock_irqrestore(&task->task_state_lock, flags);
+
+			/* build and send the request. */
+			status = isci_request_execute(ihost, idev, task, tag);
+
+			if (status != SCI_SUCCESS) {
+				spin_lock_irqsave(&task->task_state_lock, flags);
+				/* Did not really start this command. */
+				task->task_state_flags &= ~SAS_TASK_AT_INITIATOR;
 				spin_unlock_irqrestore(&task->task_state_lock, flags);
 
-				/* build and send the request. */
-				status = isci_request_execute(ihost, idev, task, tag);
-
-				if (status != SCI_SUCCESS) {
-
-					spin_lock_irqsave(&task->task_state_lock, flags);
-					/* Did not really start this command. */
-					task->task_state_flags &= ~SAS_TASK_AT_INITIATOR;
-					spin_unlock_irqrestore(&task->task_state_lock, flags);
-
-					if (test_bit(IDEV_GONE, &idev->flags)) {
-
-						/* Indicate that the device
-						 * is gone.
-						 */
-						isci_task_refuse(ihost, task,
-							SAS_TASK_UNDELIVERED,
-							SAS_DEVICE_UNKNOWN);
-					} else {
-						/* Indicate QUEUE_FULL so that
-						 * the scsi midlayer retries.
-						 * If the request failed for
-						 * remote device reasons, it
-						 * gets returned as
-						 * SAS_TASK_UNDELIVERED next
-						 * time through.
-						 */
-						isci_task_refuse(ihost, task,
-							SAS_TASK_COMPLETE,
-							SAS_QUEUE_FULL);
-					}
+				if (test_bit(IDEV_GONE, &idev->flags)) {
+					/* Indicate that the device
+					 * is gone.
+					 */
+					isci_task_refuse(ihost, task,
+						SAS_TASK_UNDELIVERED,
+						SAS_DEVICE_UNKNOWN);
+				} else {
+					/* Indicate QUEUE_FULL so that
+					 * the scsi midlayer retries.
+					 * If the request failed for
+					 * remote device reasons, it
+					 * gets returned as
+					 * SAS_TASK_UNDELIVERED next
+					 * time through.
+					 */
+					isci_task_refuse(ihost, task,
+						SAS_TASK_COMPLETE,
+						SAS_QUEUE_FULL);
 				}
 			}
 		}
-		if (status != SCI_SUCCESS && tag != SCI_CONTROLLER_INVALID_IO_TAG) {
-			spin_lock_irqsave(&ihost->scic_lock, flags);
-			/* command never hit the device, so just free
-			 * the tci and skip the sequence increment
-			 */
-			isci_tci_free(ihost, ISCI_TAG_TCI(tag));
-			spin_unlock_irqrestore(&ihost->scic_lock, flags);
-		}
-		isci_put_device(idev);
 	}
+
+	if (status != SCI_SUCCESS && tag != SCI_CONTROLLER_INVALID_IO_TAG) {
+		spin_lock_irqsave(&ihost->scic_lock, flags);
+		/* command never hit the device, so just free
+		 * the tci and skip the sequence increment
+		 */
+		isci_tci_free(ihost, ISCI_TAG_TCI(tag));
+		spin_unlock_irqrestore(&ihost->scic_lock, flags);
+	}
+
+	isci_put_device(idev);
 	return 0;
 }
 
diff --git a/drivers/scsi/isci/task.h b/drivers/scsi/isci/task.h
index 9c06cbad1d2..8f4531f22ac 100644
--- a/drivers/scsi/isci/task.h
+++ b/drivers/scsi/isci/task.h
@@ -131,7 +131,6 @@ static inline void isci_print_tmf(struct isci_host *ihost, struct isci_tmf *tmf)
 
 int isci_task_execute_task(
 	struct sas_task *task,
-	int num,
 	gfp_t gfp_flags);
 
 int isci_task_abort_task(
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 766098af4eb..577770fdee8 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -171,7 +171,6 @@ static void sas_ata_task_done(struct sas_task *task)
 	spin_unlock_irqrestore(ap->lock, flags);
 
 qc_already_gone:
-	list_del_init(&task->list);
 	sas_free_task(task);
 }
 
@@ -244,12 +243,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 	if (qc->scsicmd)
 		ASSIGN_SAS_TASK(qc->scsicmd, task);
 
-	if (sas_ha->lldd_max_execute_num < 2)
-		ret = i->dft->lldd_execute_task(task, 1, GFP_ATOMIC);
-	else
-		ret = sas_queue_up(task);
-
-	/* Examine */
+	ret = i->dft->lldd_execute_task(task, GFP_ATOMIC);
 	if (ret) {
 		SAS_DPRINTK("lldd_execute_task returned: %d\n", ret);
 
@@ -485,7 +479,6 @@ static void sas_ata_internal_abort(struct sas_task *task)
 
 	return;
  out:
-	list_del_init(&task->list);
 	sas_free_task(task);
 }
 
diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index 0cac7d8fd0f..022bb6e10d9 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -96,7 +96,7 @@ static int smp_execute_task(struct domain_device *dev, void *req, int req_size,
 		task->slow_task->timer.expires = jiffies + SMP_TIMEOUT*HZ;
 		add_timer(&task->slow_task->timer);
 
-		res = i->dft->lldd_execute_task(task, 1, GFP_KERNEL);
+		res = i->dft->lldd_execute_task(task, GFP_KERNEL);
 
 		if (res) {
 			del_timer(&task->slow_task->timer);
diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c
index dbc8a793fd8..362da44f294 100644
--- a/drivers/scsi/libsas/sas_init.c
+++ b/drivers/scsi/libsas/sas_init.c
@@ -45,7 +45,6 @@ struct sas_task *sas_alloc_task(gfp_t flags)
 	struct sas_task *task = kmem_cache_zalloc(sas_task_cache, flags);
 
 	if (task) {
-		INIT_LIST_HEAD(&task->list);
 		spin_lock_init(&task->task_state_lock);
 		task->task_state_flags = SAS_TASK_STATE_PENDING;
 	}
@@ -77,7 +76,6 @@ EXPORT_SYMBOL_GPL(sas_alloc_slow_task);
 void sas_free_task(struct sas_task *task)
 {
 	if (task) {
-		BUG_ON(!list_empty(&task->list));
 		kfree(task->slow_task);
 		kmem_cache_free(sas_task_cache, task);
 	}
@@ -127,11 +125,6 @@ int sas_register_ha(struct sas_ha_struct *sas_ha)
 	spin_lock_init(&sas_ha->phy_port_lock);
 	sas_hash_addr(sas_ha->hashed_sas_addr, sas_ha->sas_addr);
 
-	if (sas_ha->lldd_queue_size == 0)
-		sas_ha->lldd_queue_size = 1;
-	else if (sas_ha->lldd_queue_size == -1)
-		sas_ha->lldd_queue_size = 128; /* Sanity */
-
 	set_bit(SAS_HA_REGISTERED, &sas_ha->state);
 	spin_lock_init(&sas_ha->lock);
 	mutex_init(&sas_ha->drain_mutex);
@@ -157,15 +150,6 @@ int sas_register_ha(struct sas_ha_struct *sas_ha)
 		goto Undo_ports;
 	}
 
-	if (sas_ha->lldd_max_execute_num > 1) {
-		error = sas_init_queue(sas_ha);
-		if (error) {
-			printk(KERN_NOTICE "couldn't start queue thread:%d, "
-			       "running in direct mode\n", error);
-			sas_ha->lldd_max_execute_num = 1;
-		}
-	}
-
 	INIT_LIST_HEAD(&sas_ha->eh_done_q);
 	INIT_LIST_HEAD(&sas_ha->eh_ata_q);
 
@@ -201,11 +185,6 @@ int sas_unregister_ha(struct sas_ha_struct *sas_ha)
 	__sas_drain_work(sas_ha);
 	mutex_unlock(&sas_ha->drain_mutex);
 
-	if (sas_ha->lldd_max_execute_num > 1) {
-		sas_shutdown_queue(sas_ha);
-		sas_ha->lldd_max_execute_num = 1;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h
index 7e7ba83f0a2..9cf0bc260b0 100644
--- a/drivers/scsi/libsas/sas_internal.h
+++ b/drivers/scsi/libsas/sas_internal.h
@@ -66,9 +66,7 @@ void sas_unregister_ports(struct sas_ha_struct *sas_ha);
 
 enum blk_eh_timer_return sas_scsi_timed_out(struct scsi_cmnd *);
 
-int  sas_init_queue(struct sas_ha_struct *sas_ha);
 int  sas_init_events(struct sas_ha_struct *sas_ha);
-void sas_shutdown_queue(struct sas_ha_struct *sas_ha);
 void sas_disable_revalidation(struct sas_ha_struct *ha);
 void sas_enable_revalidation(struct sas_ha_struct *ha);
 void __sas_drain_work(struct sas_ha_struct *ha);
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index b492293d51f..72918d227ea 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -112,7 +112,6 @@ static void sas_end_task(struct scsi_cmnd *sc, struct sas_task *task)
 
 	sc->result = (hs << 16) | stat;
 	ASSIGN_SAS_TASK(sc, NULL);
-	list_del_init(&task->list);
 	sas_free_task(task);
 }
 
@@ -138,7 +137,6 @@ static void sas_scsi_task_done(struct sas_task *task)
 
 	if (unlikely(!sc)) {
 		SAS_DPRINTK("task_done called with non existing SCSI cmnd!\n");
-		list_del_init(&task->list);
 		sas_free_task(task);
 		return;
 	}
@@ -179,31 +177,10 @@ static struct sas_task *sas_create_task(struct scsi_cmnd *cmd,
 	return task;
 }
 
-int sas_queue_up(struct sas_task *task)
-{
-	struct sas_ha_struct *sas_ha = task->dev->port->ha;
-	struct scsi_core *core = &sas_ha->core;
-	unsigned long flags;
-	LIST_HEAD(list);
-
-	spin_lock_irqsave(&core->task_queue_lock, flags);
-	if (sas_ha->lldd_queue_size < core->task_queue_size + 1) {
-		spin_unlock_irqrestore(&core->task_queue_lock, flags);
-		return -SAS_QUEUE_FULL;
-	}
-	list_add_tail(&task->list, &core->task_queue);
-	core->task_queue_size += 1;
-	spin_unlock_irqrestore(&core->task_queue_lock, flags);
-	wake_up_process(core->queue_thread);
-
-	return 0;
-}
-
 int sas_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 {
 	struct sas_internal *i = to_sas_internal(host->transportt);
 	struct domain_device *dev = cmd_to_domain_dev(cmd);
-	struct sas_ha_struct *sas_ha = dev->port->ha;
 	struct sas_task *task;
 	int res = 0;
 
@@ -224,12 +201,7 @@ int sas_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	if (!task)
 		return SCSI_MLQUEUE_HOST_BUSY;
 
-	/* Queue up, Direct Mode or Task Collector Mode. */
-	if (sas_ha->lldd_max_execute_num < 2)
-		res = i->dft->lldd_execute_task(task, 1, GFP_ATOMIC);
-	else
-		res = sas_queue_up(task);
-
+	res = i->dft->lldd_execute_task(task, GFP_ATOMIC);
 	if (res)
 		goto out_free_task;
 	return 0;
@@ -323,37 +295,17 @@ enum task_disposition {
 	TASK_IS_DONE,
 	TASK_IS_ABORTED,
 	TASK_IS_AT_LU,
-	TASK_IS_NOT_AT_HA,
 	TASK_IS_NOT_AT_LU,
 	TASK_ABORT_FAILED,
 };
 
 static enum task_disposition sas_scsi_find_task(struct sas_task *task)
 {
-	struct sas_ha_struct *ha = task->dev->port->ha;
 	unsigned long flags;
 	int i, res;
 	struct sas_internal *si =
 		to_sas_internal(task->dev->port->ha->core.shost->transportt);
 
-	if (ha->lldd_max_execute_num > 1) {
-		struct scsi_core *core = &ha->core;
-		struct sas_task *t, *n;
-
-		mutex_lock(&core->task_queue_flush);
-		spin_lock_irqsave(&core->task_queue_lock, flags);
-		list_for_each_entry_safe(t, n, &core->task_queue, list)
-			if (task == t) {
-				list_del_init(&t->list);
-				break;
-			}
-		spin_unlock_irqrestore(&core->task_queue_lock, flags);
-		mutex_unlock(&core->task_queue_flush);
-
-		if (task == t)
-			return TASK_IS_NOT_AT_HA;
-	}
-
 	for (i = 0; i < 5; i++) {
 		SAS_DPRINTK("%s: aborting task 0x%p\n", __func__, task);
 		res = si->dft->lldd_abort_task(task);
@@ -667,14 +619,6 @@ static void sas_eh_handle_sas_errors(struct Scsi_Host *shost, struct list_head *
 		cmd->eh_eflags = 0;
 
 		switch (res) {
-		case TASK_IS_NOT_AT_HA:
-			SAS_DPRINTK("%s: task 0x%p is not at ha: %s\n",
-				    __func__, task,
-				    cmd->retries ? "retry" : "aborted");
-			if (cmd->retries)
-				cmd->retries--;
-			sas_eh_finish_cmd(cmd);
-			continue;
 		case TASK_IS_DONE:
 			SAS_DPRINTK("%s: task 0x%p is done\n", __func__,
 				    task);
@@ -836,9 +780,6 @@ retry:
 		scsi_eh_ready_devs(shost, &eh_work_q, &ha->eh_done_q);
 
 out:
-	if (ha->lldd_max_execute_num > 1)
-		wake_up_process(ha->core.queue_thread);
-
 	sas_eh_handle_resets(shost);
 
 	/* now link into libata eh --- if we have any ata devices */
@@ -984,121 +925,6 @@ int sas_bios_param(struct scsi_device *scsi_dev,
 	return 0;
 }
 
-/* ---------- Task Collector Thread implementation ---------- */
-
-static void sas_queue(struct sas_ha_struct *sas_ha)
-{
-	struct scsi_core *core = &sas_ha->core;
-	unsigned long flags;
-	LIST_HEAD(q);
-	int can_queue;
-	int res;
-	struct sas_internal *i = to_sas_internal(core->shost->transportt);
-
-	mutex_lock(&core->task_queue_flush);
-	spin_lock_irqsave(&core->task_queue_lock, flags);
-	while (!kthread_should_stop() &&
-	       !list_empty(&core->task_queue) &&
-	       !test_bit(SAS_HA_FROZEN, &sas_ha->state)) {
-
-		can_queue = sas_ha->lldd_queue_size - core->task_queue_size;
-		if (can_queue >= 0) {
-			can_queue = core->task_queue_size;
-			list_splice_init(&core->task_queue, &q);
-		} else {
-			struct list_head *a, *n;
-
-			can_queue = sas_ha->lldd_queue_size;
-			list_for_each_safe(a, n, &core->task_queue) {
-				list_move_tail(a, &q);
-				if (--can_queue == 0)
-					break;
-			}
-			can_queue = sas_ha->lldd_queue_size;
-		}
-		core->task_queue_size -= can_queue;
-		spin_unlock_irqrestore(&core->task_queue_lock, flags);
-		{
-			struct sas_task *task = list_entry(q.next,
-							   struct sas_task,
-							   list);
-			list_del_init(&q);
-			res = i->dft->lldd_execute_task(task, can_queue,
-							GFP_KERNEL);
-			if (unlikely(res))
-				__list_add(&q, task->list.prev, &task->list);
-		}
-		spin_lock_irqsave(&core->task_queue_lock, flags);
-		if (res) {
-			list_splice_init(&q, &core->task_queue); /*at head*/
-			core->task_queue_size += can_queue;
-		}
-	}
-	spin_unlock_irqrestore(&core->task_queue_lock, flags);
-	mutex_unlock(&core->task_queue_flush);
-}
-
-/**
- * sas_queue_thread -- The Task Collector thread
- * @_sas_ha: pointer to struct sas_ha
- */
-static int sas_queue_thread(void *_sas_ha)
-{
-	struct sas_ha_struct *sas_ha = _sas_ha;
-
-	while (1) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		schedule();
-		sas_queue(sas_ha);
-		if (kthread_should_stop())
-			break;
-	}
-
-	return 0;
-}
-
-int sas_init_queue(struct sas_ha_struct *sas_ha)
-{
-	struct scsi_core *core = &sas_ha->core;
-
-	spin_lock_init(&core->task_queue_lock);
-	mutex_init(&core->task_queue_flush);
-	core->task_queue_size = 0;
-	INIT_LIST_HEAD(&core->task_queue);
-
-	core->queue_thread = kthread_run(sas_queue_thread, sas_ha,
-					 "sas_queue_%d", core->shost->host_no);
-	if (IS_ERR(core->queue_thread))
-		return PTR_ERR(core->queue_thread);
-	return 0;
-}
-
-void sas_shutdown_queue(struct sas_ha_struct *sas_ha)
-{
-	unsigned long flags;
-	struct scsi_core *core = &sas_ha->core;
-	struct sas_task *task, *n;
-
-	kthread_stop(core->queue_thread);
-
-	if (!list_empty(&core->task_queue))
-		SAS_DPRINTK("HA: %llx: scsi core task queue is NOT empty!?\n",
-			    SAS_ADDR(sas_ha->sas_addr));
-
-	spin_lock_irqsave(&core->task_queue_lock, flags);
-	list_for_each_entry_safe(task, n, &core->task_queue, list) {
-		struct scsi_cmnd *cmd = task->uldd_task;
-
-		list_del_init(&task->list);
-
-		ASSIGN_SAS_TASK(cmd, NULL);
-		sas_free_task(task);
-		cmd->result = DID_ABORT << 16;
-		cmd->scsi_done(cmd);
-	}
-	spin_unlock_irqrestore(&core->task_queue_lock, flags);
-}
-
 /*
  * Tell an upper layer that it needs to initiate an abort for a given task.
  * This should only ever be called by an LLDD.
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index ac7c0307840..f15df3de679 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -26,18 +26,9 @@
 
 #include "mv_sas.h"
 
-static int lldd_max_execute_num = 1;
-module_param_named(collector, lldd_max_execute_num, int, S_IRUGO);
-MODULE_PARM_DESC(collector, "\n"
-	"\tIf greater than one, tells the SAS Layer to run in Task Collector\n"
-	"\tMode.  If 1 or 0, tells the SAS Layer to run in Direct Mode.\n"
-	"\tThe mvsas SAS LLDD supports both modes.\n"
-	"\tDefault: 1 (Direct Mode).\n");
-
 int interrupt_coalescing = 0x80;
 
 static struct scsi_transport_template *mvs_stt;
-struct kmem_cache *mvs_task_list_cache;
 static const struct mvs_chip_info mvs_chips[] = {
 	[chip_6320] =	{ 1, 2, 0x400, 17, 16, 6,  9, &mvs_64xx_dispatch, },
 	[chip_6440] =	{ 1, 4, 0x400, 17, 16, 6,  9, &mvs_64xx_dispatch, },
@@ -513,14 +504,11 @@ static void  mvs_post_sas_ha_init(struct Scsi_Host *shost,
 
 	sha->num_phys = nr_core * chip_info->n_phy;
 
-	sha->lldd_max_execute_num = lldd_max_execute_num;
-
 	if (mvi->flags & MVF_FLAG_SOC)
 		can_queue = MVS_SOC_CAN_QUEUE;
 	else
 		can_queue = MVS_CHIP_SLOT_SZ;
 
-	sha->lldd_queue_size = can_queue;
 	shost->sg_tablesize = min_t(u16, SG_ALL, MVS_MAX_SG);
 	shost->can_queue = can_queue;
 	mvi->shost->cmd_per_lun = MVS_QUEUE_SIZE;
@@ -833,16 +821,7 @@ static int __init mvs_init(void)
 	if (!mvs_stt)
 		return -ENOMEM;
 
-	mvs_task_list_cache = kmem_cache_create("mvs_task_list", sizeof(struct mvs_task_list),
-							 0, SLAB_HWCACHE_ALIGN, NULL);
-	if (!mvs_task_list_cache) {
-		rc = -ENOMEM;
-		mv_printk("%s: mvs_task_list_cache alloc failed! \n", __func__);
-		goto err_out;
-	}
-
 	rc = pci_register_driver(&mvs_pci_driver);
-
 	if (rc)
 		goto err_out;
 
@@ -857,7 +836,6 @@ static void __exit mvs_exit(void)
 {
 	pci_unregister_driver(&mvs_pci_driver);
 	sas_release_transport(mvs_stt);
-	kmem_cache_destroy(mvs_task_list_cache);
 }
 
 struct device_attribute *mvst_host_attrs[] = {
diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c
index ac52f7c9951..85d86a5cdb6 100644
--- a/drivers/scsi/mvsas/mv_sas.c
+++ b/drivers/scsi/mvsas/mv_sas.c
@@ -852,43 +852,7 @@ prep_out:
 	return rc;
 }
 
-static struct mvs_task_list *mvs_task_alloc_list(int *num, gfp_t gfp_flags)
-{
-	struct mvs_task_list *first = NULL;
-
-	for (; *num > 0; --*num) {
-		struct mvs_task_list *mvs_list = kmem_cache_zalloc(mvs_task_list_cache, gfp_flags);
-
-		if (!mvs_list)
-			break;
-
-		INIT_LIST_HEAD(&mvs_list->list);
-		if (!first)
-			first = mvs_list;
-		else
-			list_add_tail(&mvs_list->list, &first->list);
-
-	}
-
-	return first;
-}
-
-static inline void mvs_task_free_list(struct mvs_task_list *mvs_list)
-{
-	LIST_HEAD(list);
-	struct list_head *pos, *a;
-	struct mvs_task_list *mlist = NULL;
-
-	__list_add(&list, mvs_list->list.prev, &mvs_list->list);
-
-	list_for_each_safe(pos, a, &list) {
-		list_del_init(pos);
-		mlist = list_entry(pos, struct mvs_task_list, list);
-		kmem_cache_free(mvs_task_list_cache, mlist);
-	}
-}
-
-static int mvs_task_exec(struct sas_task *task, const int num, gfp_t gfp_flags,
+static int mvs_task_exec(struct sas_task *task, gfp_t gfp_flags,
 				struct completion *completion, int is_tmf,
 				struct mvs_tmf_task *tmf)
 {
@@ -912,74 +876,9 @@ static int mvs_task_exec(struct sas_task *task, const int num, gfp_t gfp_flags,
 	return rc;
 }
 
-static int mvs_collector_task_exec(struct sas_task *task, const int num, gfp_t gfp_flags,
-				struct completion *completion, int is_tmf,
-				struct mvs_tmf_task *tmf)
+int mvs_queue_command(struct sas_task *task, gfp_t gfp_flags)
 {
-	struct domain_device *dev = task->dev;
-	struct mvs_prv_info *mpi = dev->port->ha->lldd_ha;
-	struct mvs_info *mvi = NULL;
-	struct sas_task *t = task;
-	struct mvs_task_list *mvs_list = NULL, *a;
-	LIST_HEAD(q);
-	int pass[2] = {0};
-	u32 rc = 0;
-	u32 n = num;
-	unsigned long flags = 0;
-
-	mvs_list = mvs_task_alloc_list(&n, gfp_flags);
-	if (n) {
-		printk(KERN_ERR "%s: mvs alloc list failed.\n", __func__);
-		rc = -ENOMEM;
-		goto free_list;
-	}
-
-	__list_add(&q, mvs_list->list.prev, &mvs_list->list);
-
-	list_for_each_entry(a, &q, list) {
-		a->task = t;
-		t = list_entry(t->list.next, struct sas_task, list);
-	}
-
-	list_for_each_entry(a, &q , list) {
-
-		t = a->task;
-		mvi = ((struct mvs_device *)t->dev->lldd_dev)->mvi_info;
-
-		spin_lock_irqsave(&mvi->lock, flags);
-		rc = mvs_task_prep(t, mvi, is_tmf, tmf, &pass[mvi->id]);
-		if (rc)
-			dev_printk(KERN_ERR, mvi->dev, "mvsas exec failed[%d]!\n", rc);
-		spin_unlock_irqrestore(&mvi->lock, flags);
-	}
-
-	if (likely(pass[0]))
-			MVS_CHIP_DISP->start_delivery(mpi->mvi[0],
-				(mpi->mvi[0]->tx_prod - 1) & (MVS_CHIP_SLOT_SZ - 1));
-
-	if (likely(pass[1]))
-			MVS_CHIP_DISP->start_delivery(mpi->mvi[1],
-				(mpi->mvi[1]->tx_prod - 1) & (MVS_CHIP_SLOT_SZ - 1));
-
-	list_del_init(&q);
-
-free_list:
-	if (mvs_list)
-		mvs_task_free_list(mvs_list);
-
-	return rc;
-}
-
-int mvs_queue_command(struct sas_task *task, const int num,
-			gfp_t gfp_flags)
-{
-	struct mvs_device *mvi_dev = task->dev->lldd_dev;
-	struct sas_ha_struct *sas = mvi_dev->mvi_info->sas;
-
-	if (sas->lldd_max_execute_num < 2)
-		return mvs_task_exec(task, num, gfp_flags, NULL, 0, NULL);
-	else
-		return mvs_collector_task_exec(task, num, gfp_flags, NULL, 0, NULL);
+	return mvs_task_exec(task, gfp_flags, NULL, 0, NULL);
 }
 
 static void mvs_slot_free(struct mvs_info *mvi, u32 rx_desc)
@@ -1411,7 +1310,7 @@ static int mvs_exec_internal_tmf_task(struct domain_device *dev,
 		task->slow_task->timer.expires = jiffies + MVS_TASK_TIMEOUT*HZ;
 		add_timer(&task->slow_task->timer);
 
-		res = mvs_task_exec(task, 1, GFP_KERNEL, NULL, 1, tmf);
+		res = mvs_task_exec(task, GFP_KERNEL, NULL, 1, tmf);
 
 		if (res) {
 			del_timer(&task->slow_task->timer);
diff --git a/drivers/scsi/mvsas/mv_sas.h b/drivers/scsi/mvsas/mv_sas.h
index d6b19dc80be..dc409c04747 100644
--- a/drivers/scsi/mvsas/mv_sas.h
+++ b/drivers/scsi/mvsas/mv_sas.h
@@ -65,7 +65,6 @@ extern struct mvs_tgt_initiator mvs_tgt;
 extern struct mvs_info *tgt_mvi;
 extern const struct mvs_dispatch mvs_64xx_dispatch;
 extern const struct mvs_dispatch mvs_94xx_dispatch;
-extern struct kmem_cache *mvs_task_list_cache;
 
 #define DEV_IS_EXPANDER(type)	\
 	((type == SAS_EDGE_EXPANDER_DEVICE) || (type == SAS_FANOUT_EXPANDER_DEVICE))
@@ -440,12 +439,6 @@ struct mvs_task_exec_info {
 	int n_elem;
 };
 
-struct mvs_task_list {
-	struct sas_task *task;
-	struct list_head list;
-};
-
-
 /******************** function prototype *********************/
 void mvs_get_sas_addr(void *buf, u32 buflen);
 void mvs_tag_clear(struct mvs_info *mvi, u32 tag);
@@ -462,8 +455,7 @@ void mvs_set_sas_addr(struct mvs_info *mvi, int port_id, u32 off_lo,
 		      u32 off_hi, u64 sas_addr);
 void mvs_scan_start(struct Scsi_Host *shost);
 int mvs_scan_finished(struct Scsi_Host *shost, unsigned long time);
-int mvs_queue_command(struct sas_task *task, const int num,
-			gfp_t gfp_flags);
+int mvs_queue_command(struct sas_task *task, gfp_t gfp_flags);
 int mvs_abort_task(struct sas_task *task);
 int mvs_abort_task_set(struct domain_device *dev, u8 *lun);
 int mvs_clear_aca(struct domain_device *dev, u8 *lun);
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index 19ae6cab5e4..329aba0083a 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -601,8 +601,6 @@ static void  pm8001_post_sas_ha_init(struct Scsi_Host *shost,
 	sha->lldd_module = THIS_MODULE;
 	sha->sas_addr = &pm8001_ha->sas_addr[0];
 	sha->num_phys = chip_info->n_phy;
-	sha->lldd_max_execute_num = 1;
-	sha->lldd_queue_size = PM8001_CAN_QUEUE;
 	sha->core.shost = shost;
 }
 
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index 76570e6a547..b93f289b42b 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -350,7 +350,7 @@ static int sas_find_local_port_id(struct domain_device *dev)
   */
 #define DEV_IS_GONE(pm8001_dev)	\
 	((!pm8001_dev || (pm8001_dev->dev_type == SAS_PHY_UNUSED)))
-static int pm8001_task_exec(struct sas_task *task, const int num,
+static int pm8001_task_exec(struct sas_task *task,
 	gfp_t gfp_flags, int is_tmf, struct pm8001_tmf_task *tmf)
 {
 	struct domain_device *dev = task->dev;
@@ -360,7 +360,6 @@ static int pm8001_task_exec(struct sas_task *task, const int num,
 	struct sas_task *t = task;
 	struct pm8001_ccb_info *ccb;
 	u32 tag = 0xdeadbeef, rc, n_elem = 0;
-	u32 n = num;
 	unsigned long flags = 0;
 
 	if (!dev->port) {
@@ -387,18 +386,12 @@ static int pm8001_task_exec(struct sas_task *task, const int num,
 				spin_unlock_irqrestore(&pm8001_ha->lock, flags);
 				t->task_done(t);
 				spin_lock_irqsave(&pm8001_ha->lock, flags);
-				if (n > 1)
-					t = list_entry(t->list.next,
-							struct sas_task, list);
 				continue;
 			} else {
 				struct task_status_struct *ts = &t->task_status;
 				ts->resp = SAS_TASK_UNDELIVERED;
 				ts->stat = SAS_PHY_DOWN;
 				t->task_done(t);
-				if (n > 1)
-					t = list_entry(t->list.next,
-							struct sas_task, list);
 				continue;
 			}
 		}
@@ -460,9 +453,7 @@ static int pm8001_task_exec(struct sas_task *task, const int num,
 		t->task_state_flags |= SAS_TASK_AT_INITIATOR;
 		spin_unlock(&t->task_state_lock);
 		pm8001_dev->running_req++;
-		if (n > 1)
-			t = list_entry(t->list.next, struct sas_task, list);
-	} while (--n);
+	} while (0);
 	rc = 0;
 	goto out_done;
 
@@ -483,14 +474,11 @@ out_done:
   * pm8001_queue_command - register for upper layer used, all IO commands sent
   * to HBA are from this interface.
   * @task: the task to be execute.
-  * @num: if can_queue great than 1, the task can be queued up. for SMP task,
-  * we always execute one one time
   * @gfp_flags: gfp_flags
   */
-int pm8001_queue_command(struct sas_task *task, const int num,
-		gfp_t gfp_flags)
+int pm8001_queue_command(struct sas_task *task, gfp_t gfp_flags)
 {
-	return pm8001_task_exec(task, num, gfp_flags, 0, NULL);
+	return pm8001_task_exec(task, gfp_flags, 0, NULL);
 }
 
 /**
@@ -708,7 +696,7 @@ static int pm8001_exec_internal_tmf_task(struct domain_device *dev,
 		task->slow_task->timer.expires = jiffies + PM8001_TASK_TIMEOUT*HZ;
 		add_timer(&task->slow_task->timer);
 
-		res = pm8001_task_exec(task, 1, GFP_KERNEL, 1, tmf);
+		res = pm8001_task_exec(task, GFP_KERNEL, 1, tmf);
 
 		if (res) {
 			del_timer(&task->slow_task->timer);
diff --git a/drivers/scsi/pm8001/pm8001_sas.h b/drivers/scsi/pm8001/pm8001_sas.h
index f6b2ac59dae..8dd8b7840f0 100644
--- a/drivers/scsi/pm8001/pm8001_sas.h
+++ b/drivers/scsi/pm8001/pm8001_sas.h
@@ -623,8 +623,7 @@ int pm8001_phy_control(struct asd_sas_phy *sas_phy, enum phy_func func,
 	void *funcdata);
 void pm8001_scan_start(struct Scsi_Host *shost);
 int pm8001_scan_finished(struct Scsi_Host *shost, unsigned long time);
-int pm8001_queue_command(struct sas_task *task, const int num,
-	gfp_t gfp_flags);
+int pm8001_queue_command(struct sas_task *task, gfp_t gfp_flags);
 int pm8001_abort_task(struct sas_task *task);
 int pm8001_abort_task_set(struct domain_device *dev, u8 *lun);
 int pm8001_clear_aca(struct domain_device *dev, u8 *lun);
diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h
index 1f8b33ec612..832dcc9f86e 100644
--- a/include/scsi/libsas.h
+++ b/include/scsi/libsas.h
@@ -365,12 +365,6 @@ struct asd_sas_phy {
 struct scsi_core {
 	struct Scsi_Host *shost;
 
-	struct mutex	  task_queue_flush;
-	spinlock_t        task_queue_lock;
-	struct list_head  task_queue;
-	int               task_queue_size;
-
-	struct task_struct *queue_thread;
 };
 
 struct sas_ha_event {
@@ -422,9 +416,6 @@ struct sas_ha_struct {
 	struct asd_sas_port **sas_port; /* array of valid pointers, must be set */
 	int             num_phys; /* must be set, gt 0, static */
 
-	/* The class calls this to send a task for execution. */
-	int lldd_max_execute_num;
-	int lldd_queue_size;
 	int strict_wide_ports; /* both sas_addr and attached_sas_addr must match
 				* their siblings when forming wide ports */
 
@@ -612,7 +603,6 @@ struct sas_ssp_task {
 
 struct sas_task {
 	struct domain_device *dev;
-	struct list_head      list;
 
 	spinlock_t   task_state_lock;
 	unsigned     task_state_flags;
@@ -665,8 +655,7 @@ struct sas_domain_function_template {
 	int  (*lldd_dev_found)(struct domain_device *);
 	void (*lldd_dev_gone)(struct domain_device *);
 
-	int (*lldd_execute_task)(struct sas_task *, int num,
-				 gfp_t gfp_flags);
+	int (*lldd_execute_task)(struct sas_task *, gfp_t gfp_flags);
 
 	/* Task Management Functions. Must be called from process context. */
 	int (*lldd_abort_task)(struct sas_task *);
@@ -700,7 +689,6 @@ extern void sas_suspend_ha(struct sas_ha_struct *sas_ha);
 int sas_set_phy_speed(struct sas_phy *phy,
 		      struct sas_phy_linkrates *rates);
 int sas_phy_reset(struct sas_phy *phy, int hard_reset);
-int sas_queue_up(struct sas_task *task);
 extern int sas_queuecommand(struct Scsi_Host * ,struct scsi_cmnd *);
 extern int sas_target_alloc(struct scsi_target *);
 extern int sas_slave_configure(struct scsi_device *);
-- 
cgit v1.2.3-70-g09d2


From b4b9d2ccf0be61c69213f6ae4e33377c05194ef4 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Wed, 26 Nov 2014 14:44:43 -0500
Subject: sunrpc: add debugfs file for displaying client rpc_task queue

It's possible to get a dump of the RPC task queue by writing a value to
/proc/sys/sunrpc/rpc_debug. If you write any value to that file, you get
a dump of the RPC client task list into the log buffer. This is a rather
inconvenient interface however, and makes it hard to get immediate info
about the task queue.

Add a new directory hierarchy under debugfs:

    sunrpc/
        rpc_clnt/
            <clientid>/

Within each clientid directory we create a new "tasks" file that will
dump info similar to what shows up in the log buffer, but with a few
small differences -- we avoid printing raw kernel addresses in favor of
symbolic names and the XID is also displayed.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 include/linux/sunrpc/clnt.h  |   4 +
 include/linux/sunrpc/debug.h |  31 +++++++
 net/sunrpc/Kconfig           |   1 +
 net/sunrpc/Makefile          |   1 +
 net/sunrpc/clnt.c            |  10 ++-
 net/sunrpc/debugfs.c         | 191 +++++++++++++++++++++++++++++++++++++++++++
 net/sunrpc/sunrpc_syms.c     |   8 ++
 7 files changed, 245 insertions(+), 1 deletion(-)
 create mode 100644 net/sunrpc/debugfs.c

(limited to 'include')

diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 70736b98c72..d86acc63b25 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -63,6 +63,9 @@ struct rpc_clnt {
 	struct rpc_rtt		cl_rtt_default;
 	struct rpc_timeout	cl_timeout_default;
 	const struct rpc_program *cl_program;
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+	struct dentry		*cl_debugfs;	/* debugfs directory */
+#endif
 };
 
 /*
@@ -176,5 +179,6 @@ size_t		rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t);
 const char	*rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t);
 int		rpc_localaddr(struct rpc_clnt *, struct sockaddr *, size_t);
 
+const char *rpc_proc_name(const struct rpc_task *task);
 #endif /* __KERNEL__ */
 #endif /* _LINUX_SUNRPC_CLNT_H */
diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h
index 43f38ee9668..83533970709 100644
--- a/include/linux/sunrpc/debug.h
+++ b/include/linux/sunrpc/debug.h
@@ -53,9 +53,40 @@ extern unsigned int		nlm_debug;
 /*
  * Sysctl interface for RPC debugging
  */
+
+struct rpc_clnt;
+
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 void		rpc_register_sysctl(void);
 void		rpc_unregister_sysctl(void);
+int		sunrpc_debugfs_init(void);
+void		sunrpc_debugfs_exit(void);
+int		rpc_clnt_debugfs_register(struct rpc_clnt *);
+void		rpc_clnt_debugfs_unregister(struct rpc_clnt *);
+#else
+static inline int
+sunrpc_debugfs_init(void)
+{
+	return 0;
+}
+
+static inline void
+sunrpc_debugfs_exit(void)
+{
+	return;
+}
+
+static inline int
+rpc_clnt_debugfs_register(struct rpc_clnt *clnt)
+{
+	return 0;
+}
+
+static inline void
+rpc_clnt_debugfs_unregister(struct rpc_clnt *clnt)
+{
+	return;
+}
 #endif
 
 #endif /* _LINUX_SUNRPC_DEBUG_H_ */
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 0754d0f466d..fb78117b896 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -35,6 +35,7 @@ config RPCSEC_GSS_KRB5
 config SUNRPC_DEBUG
 	bool "RPC: Enable dprintk debugging"
 	depends on SUNRPC && SYSCTL
+	select DEBUG_FS
 	help
 	  This option enables a sysctl-based debugging interface
 	  that is be used by the 'rpcdebug' utility to turn on or off
diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile
index e5a7a1cac8f..15e6f6c23c5 100644
--- a/net/sunrpc/Makefile
+++ b/net/sunrpc/Makefile
@@ -14,6 +14,7 @@ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \
 	    addr.o rpcb_clnt.o timer.o xdr.o \
 	    sunrpc_syms.o cache.o rpc_pipe.o \
 	    svc_xprt.o
+sunrpc-$(CONFIG_SUNRPC_DEBUG) += debugfs.o
 sunrpc-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel_rqst.o bc_svc.o
 sunrpc-$(CONFIG_PROC_FS) += stats.o
 sunrpc-$(CONFIG_SYSCTL) += sysctl.o
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 36c64ef460c..05da12a3394 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -305,6 +305,10 @@ static int rpc_client_register(struct rpc_clnt *clnt,
 	struct super_block *pipefs_sb;
 	int err;
 
+	err = rpc_clnt_debugfs_register(clnt);
+	if (err)
+		return err;
+
 	pipefs_sb = rpc_get_sb_net(net);
 	if (pipefs_sb) {
 		err = rpc_setup_pipedir(pipefs_sb, clnt);
@@ -331,6 +335,7 @@ err_auth:
 out:
 	if (pipefs_sb)
 		rpc_put_sb_net(net);
+	rpc_clnt_debugfs_unregister(clnt);
 	return err;
 }
 
@@ -670,6 +675,7 @@ int rpc_switch_client_transport(struct rpc_clnt *clnt,
 
 	rpc_unregister_client(clnt);
 	__rpc_clnt_remove_pipedir(clnt);
+	rpc_clnt_debugfs_unregister(clnt);
 
 	/*
 	 * A new transport was created.  "clnt" therefore
@@ -771,6 +777,7 @@ rpc_free_client(struct rpc_clnt *clnt)
 			rcu_dereference(clnt->cl_xprt)->servername);
 	if (clnt->cl_parent != clnt)
 		parent = clnt->cl_parent;
+	rpc_clnt_debugfs_unregister(clnt);
 	rpc_clnt_remove_pipedir(clnt);
 	rpc_unregister_client(clnt);
 	rpc_free_iostats(clnt->cl_metrics);
@@ -1397,7 +1404,8 @@ rpc_restart_call(struct rpc_task *task)
 EXPORT_SYMBOL_GPL(rpc_restart_call);
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
-static const char *rpc_proc_name(const struct rpc_task *task)
+const char
+*rpc_proc_name(const struct rpc_task *task)
 {
 	const struct rpc_procinfo *proc = task->tk_msg.rpc_proc;
 
diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c
new file mode 100644
index 00000000000..3d7745683ca
--- /dev/null
+++ b/net/sunrpc/debugfs.c
@@ -0,0 +1,191 @@
+/**
+ * debugfs interface for sunrpc
+ *
+ * (c) 2014 Jeff Layton <jlayton@primarydata.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/sunrpc/sched.h>
+#include <linux/sunrpc/clnt.h>
+#include "netns.h"
+
+static struct dentry *topdir;
+static struct dentry *rpc_clnt_dir;
+
+struct rpc_clnt_iter {
+	struct rpc_clnt	*clnt;
+	loff_t		pos;
+};
+
+static int
+tasks_show(struct seq_file *f, void *v)
+{
+	u32 xid = 0;
+	struct rpc_task *task = v;
+	struct rpc_clnt *clnt = task->tk_client;
+	const char *rpc_waitq = "none";
+
+	if (RPC_IS_QUEUED(task))
+		rpc_waitq = rpc_qname(task->tk_waitqueue);
+
+	if (task->tk_rqstp)
+		xid = be32_to_cpu(task->tk_rqstp->rq_xid);
+
+	seq_printf(f, "%5u %04x %6d 0x%x 0x%x %8ld %ps %sv%u %s a:%ps q:%s\n",
+		task->tk_pid, task->tk_flags, task->tk_status,
+		clnt->cl_clid, xid, task->tk_timeout, task->tk_ops,
+		clnt->cl_program->name, clnt->cl_vers, rpc_proc_name(task),
+		task->tk_action, rpc_waitq);
+	return 0;
+}
+
+static void *
+tasks_start(struct seq_file *f, loff_t *ppos)
+	__acquires(&clnt->cl_lock)
+{
+	struct rpc_clnt_iter *iter = f->private;
+	loff_t pos = *ppos;
+	struct rpc_clnt *clnt = iter->clnt;
+	struct rpc_task *task;
+
+	iter->pos = pos + 1;
+	spin_lock(&clnt->cl_lock);
+	list_for_each_entry(task, &clnt->cl_tasks, tk_task)
+		if (pos-- == 0)
+			return task;
+	return NULL;
+}
+
+static void *
+tasks_next(struct seq_file *f, void *v, loff_t *pos)
+{
+	struct rpc_clnt_iter *iter = f->private;
+	struct rpc_clnt *clnt = iter->clnt;
+	struct rpc_task *task = v;
+	struct list_head *next = task->tk_task.next;
+
+	++iter->pos;
+	++*pos;
+
+	/* If there's another task on list, return it */
+	if (next == &clnt->cl_tasks)
+		return NULL;
+	return list_entry(next, struct rpc_task, tk_task);
+}
+
+static void
+tasks_stop(struct seq_file *f, void *v)
+	__releases(&clnt->cl_lock)
+{
+	struct rpc_clnt_iter *iter = f->private;
+	struct rpc_clnt *clnt = iter->clnt;
+
+	spin_unlock(&clnt->cl_lock);
+}
+
+static const struct seq_operations tasks_seq_operations = {
+	.start	= tasks_start,
+	.next	= tasks_next,
+	.stop	= tasks_stop,
+	.show	= tasks_show,
+};
+
+static int tasks_open(struct inode *inode, struct file *filp)
+{
+	int ret = seq_open_private(filp, &tasks_seq_operations,
+					sizeof(struct rpc_clnt_iter));
+
+	if (!ret) {
+		struct seq_file *seq = filp->private_data;
+		struct rpc_clnt_iter *iter = seq->private;
+
+		iter->clnt = inode->i_private;
+
+		if (!atomic_inc_not_zero(&iter->clnt->cl_count)) {
+			seq_release_private(inode, filp);
+			ret = -EINVAL;
+		}
+	}
+
+	return ret;
+}
+
+static int
+tasks_release(struct inode *inode, struct file *filp)
+{
+	struct seq_file *seq = filp->private_data;
+	struct rpc_clnt_iter *iter = seq->private;
+
+	rpc_release_client(iter->clnt);
+	return seq_release_private(inode, filp);
+}
+
+static const struct file_operations tasks_fops = {
+	.owner		= THIS_MODULE,
+	.open		= tasks_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= tasks_release,
+};
+
+int
+rpc_clnt_debugfs_register(struct rpc_clnt *clnt)
+{
+	int len;
+	char name[9]; /* 8 for hex digits + NULL terminator */
+
+	/* Already registered? */
+	if (clnt->cl_debugfs)
+		return 0;
+
+	len = snprintf(name, sizeof(name), "%x", clnt->cl_clid);
+	if (len >= sizeof(name))
+		return -EINVAL;
+
+	/* make the per-client dir */
+	clnt->cl_debugfs = debugfs_create_dir(name, rpc_clnt_dir);
+	if (!clnt->cl_debugfs)
+		return -ENOMEM;
+
+	/* make tasks file */
+	if (!debugfs_create_file("tasks", S_IFREG | S_IRUSR, clnt->cl_debugfs,
+				 clnt, &tasks_fops)) {
+		debugfs_remove_recursive(clnt->cl_debugfs);
+		clnt->cl_debugfs = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void
+rpc_clnt_debugfs_unregister(struct rpc_clnt *clnt)
+{
+	debugfs_remove_recursive(clnt->cl_debugfs);
+	clnt->cl_debugfs = NULL;
+}
+
+void __exit
+sunrpc_debugfs_exit(void)
+{
+	debugfs_remove_recursive(topdir);
+}
+
+int __init
+sunrpc_debugfs_init(void)
+{
+	topdir = debugfs_create_dir("sunrpc", NULL);
+	if (!topdir)
+		goto out;
+
+	rpc_clnt_dir = debugfs_create_dir("rpc_clnt", topdir);
+	if (!rpc_clnt_dir)
+		goto out_remove;
+
+	return 0;
+out_remove:
+	debugfs_remove_recursive(topdir);
+	topdir = NULL;
+out:
+	return -ENOMEM;
+}
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index f632e476ab6..e37fbed8795 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -97,6 +97,11 @@ init_sunrpc(void)
 	err = register_rpc_pipefs();
 	if (err)
 		goto out4;
+
+	err = sunrpc_debugfs_init();
+	if (err)
+		goto out5;
+
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	rpc_register_sysctl();
 #endif
@@ -104,6 +109,8 @@ init_sunrpc(void)
 	init_socket_xprt();	/* clnt sock transport */
 	return 0;
 
+out5:
+	unregister_rpc_pipefs();
 out4:
 	unregister_pernet_subsys(&sunrpc_net_ops);
 out3:
@@ -120,6 +127,7 @@ cleanup_sunrpc(void)
 	rpcauth_remove_module();
 	cleanup_socket_xprt();
 	svc_cleanup_xprt_sock();
+	sunrpc_debugfs_exit();
 	unregister_rpc_pipefs();
 	rpc_destroy_mempool();
 	unregister_pernet_subsys(&sunrpc_net_ops);
-- 
cgit v1.2.3-70-g09d2


From 388f0c776781fe64ce951701bfe712b2182a31f2 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Wed, 26 Nov 2014 14:44:44 -0500
Subject: sunrpc: add a debugfs rpc_xprt directory with an info file in it

Add a new directory heirarchy under the debugfs sunrpc/ directory:

    sunrpc/
        rpc_xprt/
            <xprt id>/

Within that directory, we can put files that give info about the
xprts. We do have the (minor) problem that there is no succinct,
unique identifier for rpc_xprts. So we generate them synthetically
with a static atomic_t counter.

For now, this directory just holds an "info" file, but we may add
other files to it in the future.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 include/linux/sunrpc/debug.h |  15 ++++++
 include/linux/sunrpc/xprt.h  |   3 ++
 net/sunrpc/debugfs.c         | 115 ++++++++++++++++++++++++++++++++++++++++---
 net/sunrpc/xprt.c            |   8 +++
 4 files changed, 134 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h
index 83533970709..c57d8ea0716 100644
--- a/include/linux/sunrpc/debug.h
+++ b/include/linux/sunrpc/debug.h
@@ -55,6 +55,7 @@ extern unsigned int		nlm_debug;
  */
 
 struct rpc_clnt;
+struct rpc_xprt;
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 void		rpc_register_sysctl(void);
@@ -63,6 +64,8 @@ int		sunrpc_debugfs_init(void);
 void		sunrpc_debugfs_exit(void);
 int		rpc_clnt_debugfs_register(struct rpc_clnt *);
 void		rpc_clnt_debugfs_unregister(struct rpc_clnt *);
+int		rpc_xprt_debugfs_register(struct rpc_xprt *);
+void		rpc_xprt_debugfs_unregister(struct rpc_xprt *);
 #else
 static inline int
 sunrpc_debugfs_init(void)
@@ -87,6 +90,18 @@ rpc_clnt_debugfs_unregister(struct rpc_clnt *clnt)
 {
 	return;
 }
+
+static inline int
+rpc_xprt_debugfs_register(struct rpc_xprt *xprt)
+{
+	return 0;
+}
+
+static inline void
+rpc_xprt_debugfs_unregister(struct rpc_xprt *xprt)
+{
+	return;
+}
 #endif
 
 #endif /* _LINUX_SUNRPC_DEBUG_H_ */
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index cf391eef2e6..9d27ac45b90 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -239,6 +239,9 @@ struct rpc_xprt {
 	struct net		*xprt_net;
 	const char		*servername;
 	const char		*address_strings[RPC_DISPLAY_MAX];
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+	struct dentry		*debugfs;		/* debugfs directory */
+#endif
 };
 
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c
index 3d7745683ca..e811f390f9f 100644
--- a/net/sunrpc/debugfs.c
+++ b/net/sunrpc/debugfs.c
@@ -11,6 +11,7 @@
 
 static struct dentry *topdir;
 static struct dentry *rpc_clnt_dir;
+static struct dentry *rpc_xprt_dir;
 
 struct rpc_clnt_iter {
 	struct rpc_clnt	*clnt;
@@ -131,8 +132,8 @@ static const struct file_operations tasks_fops = {
 int
 rpc_clnt_debugfs_register(struct rpc_clnt *clnt)
 {
-	int len;
-	char name[9]; /* 8 for hex digits + NULL terminator */
+	int len, err;
+	char name[24]; /* enough for "../../rpc_xprt/ + 8 hex digits + NULL */
 
 	/* Already registered? */
 	if (clnt->cl_debugfs)
@@ -148,14 +149,28 @@ rpc_clnt_debugfs_register(struct rpc_clnt *clnt)
 		return -ENOMEM;
 
 	/* make tasks file */
+	err = -ENOMEM;
 	if (!debugfs_create_file("tasks", S_IFREG | S_IRUSR, clnt->cl_debugfs,
-				 clnt, &tasks_fops)) {
-		debugfs_remove_recursive(clnt->cl_debugfs);
-		clnt->cl_debugfs = NULL;
-		return -ENOMEM;
-	}
+				 clnt, &tasks_fops))
+		goto out_err;
+
+	err = -EINVAL;
+	rcu_read_lock();
+	len = snprintf(name, sizeof(name), "../../rpc_xprt/%s",
+			rcu_dereference(clnt->cl_xprt)->debugfs->d_name.name);
+	rcu_read_unlock();
+	if (len >= sizeof(name))
+		goto out_err;
+
+	err = -ENOMEM;
+	if (!debugfs_create_symlink("xprt", clnt->cl_debugfs, name))
+		goto out_err;
 
 	return 0;
+out_err:
+	debugfs_remove_recursive(clnt->cl_debugfs);
+	clnt->cl_debugfs = NULL;
+	return err;
 }
 
 void
@@ -165,6 +180,88 @@ rpc_clnt_debugfs_unregister(struct rpc_clnt *clnt)
 	clnt->cl_debugfs = NULL;
 }
 
+static int
+xprt_info_show(struct seq_file *f, void *v)
+{
+	struct rpc_xprt *xprt = f->private;
+
+	seq_printf(f, "netid: %s\n", xprt->address_strings[RPC_DISPLAY_NETID]);
+	seq_printf(f, "addr:  %s\n", xprt->address_strings[RPC_DISPLAY_ADDR]);
+	seq_printf(f, "port:  %s\n", xprt->address_strings[RPC_DISPLAY_PORT]);
+	seq_printf(f, "state: 0x%lx\n", xprt->state);
+	return 0;
+}
+
+static int
+xprt_info_open(struct inode *inode, struct file *filp)
+{
+	int ret;
+	struct rpc_xprt *xprt = inode->i_private;
+
+	ret = single_open(filp, xprt_info_show, xprt);
+
+	if (!ret) {
+		if (!xprt_get(xprt)) {
+			single_release(inode, filp);
+			ret = -EINVAL;
+		}
+	}
+	return ret;
+}
+
+static int
+xprt_info_release(struct inode *inode, struct file *filp)
+{
+	struct rpc_xprt *xprt = inode->i_private;
+
+	xprt_put(xprt);
+	return single_release(inode, filp);
+}
+
+static const struct file_operations xprt_info_fops = {
+	.owner		= THIS_MODULE,
+	.open		= xprt_info_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= xprt_info_release,
+};
+
+int
+rpc_xprt_debugfs_register(struct rpc_xprt *xprt)
+{
+	int len, id;
+	static atomic_t	cur_id;
+	char		name[9]; /* 8 hex digits + NULL term */
+
+	id = (unsigned int)atomic_inc_return(&cur_id);
+
+	len = snprintf(name, sizeof(name), "%x", id);
+	if (len >= sizeof(name))
+		return -EINVAL;
+
+	/* make the per-client dir */
+	xprt->debugfs = debugfs_create_dir(name, rpc_xprt_dir);
+	if (!xprt->debugfs)
+		return -ENOMEM;
+
+	/* make tasks file */
+	if (!debugfs_create_file("info", S_IFREG | S_IRUSR, xprt->debugfs,
+				 xprt, &xprt_info_fops)) {
+		debugfs_remove_recursive(xprt->debugfs);
+		xprt->debugfs = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void
+rpc_xprt_debugfs_unregister(struct rpc_xprt *xprt)
+{
+	debugfs_remove_recursive(xprt->debugfs);
+	xprt->debugfs = NULL;
+}
+
 void __exit
 sunrpc_debugfs_exit(void)
 {
@@ -182,6 +279,10 @@ sunrpc_debugfs_init(void)
 	if (!rpc_clnt_dir)
 		goto out_remove;
 
+	rpc_xprt_dir = debugfs_create_dir("rpc_xprt", topdir);
+	if (!rpc_xprt_dir)
+		goto out_remove;
+
 	return 0;
 out_remove:
 	debugfs_remove_recursive(topdir);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 894d071426b..ebbefad21a3 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1303,6 +1303,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net)
  */
 struct rpc_xprt *xprt_create_transport(struct xprt_create *args)
 {
+	int err;
 	struct rpc_xprt	*xprt;
 	struct xprt_class *t;
 
@@ -1343,6 +1344,12 @@ found:
 		return ERR_PTR(-ENOMEM);
 	}
 
+	err = rpc_xprt_debugfs_register(xprt);
+	if (err) {
+		xprt_destroy(xprt);
+		return ERR_PTR(err);
+	}
+
 	dprintk("RPC:       created transport %p with %u slots\n", xprt,
 			xprt->max_reqs);
 out:
@@ -1359,6 +1366,7 @@ static void xprt_destroy(struct rpc_xprt *xprt)
 	dprintk("RPC:       destroying transport %p\n", xprt);
 	del_timer_sync(&xprt->timer);
 
+	rpc_xprt_debugfs_unregister(xprt);
 	rpc_destroy_wait_queue(&xprt->binding);
 	rpc_destroy_wait_queue(&xprt->pending);
 	rpc_destroy_wait_queue(&xprt->sending);
-- 
cgit v1.2.3-70-g09d2


From 4dcd78d80d37a360f5faab422a4e48b2cfd4abe4 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Thu, 27 Nov 2014 14:26:00 +0800
Subject: ACPICA: iASL: Add support for to_PLD macro.

This macro is intended to simplify the constuction of _PLD buffers.
NOTE: Prototype only, subject to change before this macro is
added to the ACPI specification. David E. Box.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/utxface.c |  4 +++-
 include/acpi/acbuffer.h       | 14 +++++++++++---
 2 files changed, 14 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index 502a8492dc8..49c873c6875 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -531,7 +531,9 @@ acpi_decode_pld_buffer(u8 *in_buffer,
 	ACPI_MOVE_32_TO_32(&dword, &buffer[0]);
 	pld_info->revision = ACPI_PLD_GET_REVISION(&dword);
 	pld_info->ignore_color = ACPI_PLD_GET_IGNORE_COLOR(&dword);
-	pld_info->color = ACPI_PLD_GET_COLOR(&dword);
+	pld_info->red = ACPI_PLD_GET_RED(&dword);
+	pld_info->green = ACPI_PLD_GET_GREEN(&dword);
+	pld_info->blue = ACPI_PLD_GET_BLUE(&dword);
 
 	/* Second 32-bit DWord */
 
diff --git a/include/acpi/acbuffer.h b/include/acpi/acbuffer.h
index 88cb477524a..d5ec6c87810 100644
--- a/include/acpi/acbuffer.h
+++ b/include/acpi/acbuffer.h
@@ -111,7 +111,9 @@ struct acpi_gtm_info {
 struct acpi_pld_info {
 	u8 revision;
 	u8 ignore_color;
-	u32 color;
+	u8 red;
+	u8 green;
+	u8 blue;
 	u16 width;
 	u16 height;
 	u8 user_visible;
@@ -155,8 +157,14 @@ struct acpi_pld_info {
 #define ACPI_PLD_GET_IGNORE_COLOR(dword)        ACPI_GET_BITS (dword, 7, ACPI_1BIT_MASK)
 #define ACPI_PLD_SET_IGNORE_COLOR(dword,value)  ACPI_SET_BITS (dword, 7, ACPI_1BIT_MASK, value)	/* Offset 7, Len 1 */
 
-#define ACPI_PLD_GET_COLOR(dword)               ACPI_GET_BITS (dword, 8, ACPI_24BIT_MASK)
-#define ACPI_PLD_SET_COLOR(dword,value)         ACPI_SET_BITS (dword, 8, ACPI_24BIT_MASK, value)	/* Offset 8, Len 24 */
+#define ACPI_PLD_GET_RED(dword)                 ACPI_GET_BITS (dword, 8, ACPI_8BIT_MASK)
+#define ACPI_PLD_SET_RED(dword,value)           ACPI_SET_BITS (dword, 8, ACPI_8BIT_MASK, value)	/* Offset 8, Len 8 */
+
+#define ACPI_PLD_GET_GREEN(dword)               ACPI_GET_BITS (dword, 16, ACPI_8BIT_MASK)
+#define ACPI_PLD_SET_GREEN(dword,value)         ACPI_SET_BITS (dword, 16, ACPI_8BIT_MASK, value)	/* Offset 16, Len 8 */
+
+#define ACPI_PLD_GET_BLUE(dword)                ACPI_GET_BITS (dword, 24, ACPI_8BIT_MASK)
+#define ACPI_PLD_SET_BLUE(dword,value)          ACPI_SET_BITS (dword, 24, ACPI_8BIT_MASK, value)	/* Offset 24, Len 8 */
 
 /* Second 32-bit dword, bits 33:63 */
 
-- 
cgit v1.2.3-70-g09d2


From e5874591d67f6f4ee10df88d321692aeccb4bcf4 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Thu, 27 Nov 2014 14:26:35 +0800
Subject: ACPICA: Update version to 20141107.

Version 20141107.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpixf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index ab2acf629a6..5ba78464c1b 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -46,7 +46,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20140926
+#define ACPI_CA_VERSION                 0x20141107
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
-- 
cgit v1.2.3-70-g09d2


From 6d288b169bdfbed28d308b077af3d9196025cd8b Mon Sep 17 00:00:00 2001
From: Sonny Rao <sonnyrao@chromium.org>
Date: Tue, 18 Nov 2014 23:15:19 -0800
Subject: clk: rockchip: rk3288 export i2s0_clkout for use in DT

This exposes the clock that comes out of the i2s block which generally
goes to the audio codec.

Signed-off-by: Sonny Rao <sonnyrao@chromium.org>
[removed CLK_SET_RATE_PARENT from original patch]
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 drivers/clk/rockchip/clk-rk3288.c      | 2 +-
 include/dt-bindings/clock/rk3288-cru.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/clk/rockchip/clk-rk3288.c b/drivers/clk/rockchip/clk-rk3288.c
index 232809725c5..a43045b05d9 100644
--- a/drivers/clk/rockchip/clk-rk3288.c
+++ b/drivers/clk/rockchip/clk-rk3288.c
@@ -308,7 +308,7 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 			RK3288_CLKGATE_CON(4), 2, GFLAGS),
 	MUX(0, "i2s_pre", mux_i2s_pre_p, CLK_SET_RATE_PARENT,
 			RK3288_CLKSEL_CON(4), 8, 2, MFLAGS),
-	COMPOSITE_NODIV(0, "i2s0_clkout", mux_i2s_clkout_p, 0,
+	COMPOSITE_NODIV(SCLK_I2S0_OUT, "i2s0_clkout", mux_i2s_clkout_p, 0,
 			RK3288_CLKSEL_CON(4), 12, 1, MFLAGS,
 			RK3288_CLKGATE_CON(4), 0, GFLAGS),
 	GATE(SCLK_I2S0, "sclk_i2s0", "i2s_pre", CLK_SET_RATE_PARENT,
diff --git a/include/dt-bindings/clock/rk3288-cru.h b/include/dt-bindings/clock/rk3288-cru.h
index 8e19ed58db3..edf011039b0 100644
--- a/include/dt-bindings/clock/rk3288-cru.h
+++ b/include/dt-bindings/clock/rk3288-cru.h
@@ -71,6 +71,7 @@
 #define SCLK_HDMI_CEC		110
 #define SCLK_HEVC_CABAC		111
 #define SCLK_HEVC_CORE		112
+#define SCLK_I2S0_OUT		113
 
 #define DCLK_VOP0		190
 #define DCLK_VOP1		191
-- 
cgit v1.2.3-70-g09d2


From c1c9f2cced4e3ba22b3fc25603dd3bd2ec7dc173 Mon Sep 17 00:00:00 2001
From: Alexandru M Stan <amstan@chromium.org>
Date: Wed, 26 Nov 2014 17:30:26 -0800
Subject: clk: rockchip: add bindings for the mmc clocks

These clocks represent the physical clocks (including phases) and they will
later be used for clock phase tuning.

Suggested-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Alexandru M Stan <amstan@chromium.org>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 include/dt-bindings/clock/rk3288-cru.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/dt-bindings/clock/rk3288-cru.h b/include/dt-bindings/clock/rk3288-cru.h
index edf011039b0..f60ce72a2b2 100644
--- a/include/dt-bindings/clock/rk3288-cru.h
+++ b/include/dt-bindings/clock/rk3288-cru.h
@@ -72,6 +72,14 @@
 #define SCLK_HEVC_CABAC		111
 #define SCLK_HEVC_CORE		112
 #define SCLK_I2S0_OUT		113
+#define SCLK_SDMMC_DRV		114
+#define SCLK_SDIO0_DRV		115
+#define SCLK_SDIO1_DRV		116
+#define SCLK_EMMC_DRV		117
+#define SCLK_SDMMC_SAMPLE	118
+#define SCLK_SDIO0_SAMPLE	119
+#define SCLK_SDIO1_SAMPLE	120
+#define SCLK_EMMC_SAMPLE	121
 
 #define DCLK_VOP0		190
 #define DCLK_VOP1		191
-- 
cgit v1.2.3-70-g09d2


From 766a85d7bc5d7f1ddd6de28bdb844eae45ec63b0 Mon Sep 17 00:00:00 2001
From: AKASHI Takahiro <takahiro.akashi@linaro.org>
Date: Fri, 28 Nov 2014 05:26:34 +0000
Subject: arm64: ptrace: add NT_ARM_SYSTEM_CALL regset

This regeset is intended to be used to get and set a system call number
while tracing.
There was some discussion about possible approaches to do so:

(1) modify x8 register with ptrace(PTRACE_SETREGSET) indirectly,
    and update regs->syscallno later on in syscall_trace_enter(), or
(2) define a dedicated regset for this purpose as on s390, or
(3) support ptrace(PTRACE_SET_SYSCALL) as on arch/arm

Thinking of the fact that user_pt_regs doesn't expose 'syscallno' to
tracer as well as that secure_computing() expects a changed syscall number,
especially case of -1, to be visible before this function returns in
syscall_trace_enter(), (1) doesn't work well.
We will take (2) since it looks much cleaner.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/ptrace.c | 35 +++++++++++++++++++++++++++++++++++
 include/uapi/linux/elf.h   |  1 +
 2 files changed, 36 insertions(+)

(limited to 'include')

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 8a4ae8e7321..f576781d8d3 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -551,6 +551,32 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset,
 	return ret;
 }
 
+static int system_call_get(struct task_struct *target,
+			   const struct user_regset *regset,
+			   unsigned int pos, unsigned int count,
+			   void *kbuf, void __user *ubuf)
+{
+	int syscallno = task_pt_regs(target)->syscallno;
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &syscallno, 0, -1);
+}
+
+static int system_call_set(struct task_struct *target,
+			   const struct user_regset *regset,
+			   unsigned int pos, unsigned int count,
+			   const void *kbuf, const void __user *ubuf)
+{
+	int syscallno, ret;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &syscallno, 0, -1);
+	if (ret)
+		return ret;
+
+	task_pt_regs(target)->syscallno = syscallno;
+	return ret;
+}
+
 enum aarch64_regset {
 	REGSET_GPR,
 	REGSET_FPR,
@@ -559,6 +585,7 @@ enum aarch64_regset {
 	REGSET_HW_BREAK,
 	REGSET_HW_WATCH,
 #endif
+	REGSET_SYSTEM_CALL,
 };
 
 static const struct user_regset aarch64_regsets[] = {
@@ -608,6 +635,14 @@ static const struct user_regset aarch64_regsets[] = {
 		.set = hw_break_set,
 	},
 #endif
+	[REGSET_SYSTEM_CALL] = {
+		.core_note_type = NT_ARM_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(int),
+		.align = sizeof(int),
+		.get = system_call_get,
+		.set = system_call_set,
+	},
 };
 
 static const struct user_regset_view user_aarch64_view = {
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index ea9bf2561b9..71e1d0ed92f 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -397,6 +397,7 @@ typedef struct elf64_shdr {
 #define NT_ARM_TLS	0x401		/* ARM TLS register */
 #define NT_ARM_HW_BREAK	0x402		/* ARM hardware breakpoint registers */
 #define NT_ARM_HW_WATCH	0x403		/* ARM hardware watchpoint registers */
+#define NT_ARM_SYSTEM_CALL	0x404	/* ARM system call number */
 #define NT_METAG_CBUF	0x500		/* Metag catch buffer registers */
 #define NT_METAG_RPIPE	0x501		/* Metag read pipeline state */
 #define NT_METAG_TLS	0x502		/* Metag TLS pointer */
-- 
cgit v1.2.3-70-g09d2


From 65a2ae8d5bd0ab9fb5846c0223d5dcf74e87f9d2 Mon Sep 17 00:00:00 2001
From: AKASHI Takahiro <takahiro.akashi@linaro.org>
Date: Fri, 28 Nov 2014 05:26:36 +0000
Subject: asm-generic: add generic seccomp.h for secure computing mode 1

Those values (__NR_seccomp_*) are used solely in secure_computing()
to identify mode 1 system calls. If compat system calls have different
syscall numbers, asm/seccomp.h may override them.

Acked-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 include/asm-generic/seccomp.h | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)
 create mode 100644 include/asm-generic/seccomp.h

(limited to 'include')

diff --git a/include/asm-generic/seccomp.h b/include/asm-generic/seccomp.h
new file mode 100644
index 00000000000..9fa1f653ed3
--- /dev/null
+++ b/include/asm-generic/seccomp.h
@@ -0,0 +1,30 @@
+/*
+ * include/asm-generic/seccomp.h
+ *
+ * Copyright (C) 2014 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _ASM_GENERIC_SECCOMP_H
+#define _ASM_GENERIC_SECCOMP_H
+
+#include <linux/unistd.h>
+
+#if defined(CONFIG_COMPAT) && !defined(__NR_seccomp_read_32)
+#define __NR_seccomp_read_32		__NR_read
+#define __NR_seccomp_write_32		__NR_write
+#define __NR_seccomp_exit_32		__NR_exit
+#define __NR_seccomp_sigreturn_32	__NR_rt_sigreturn
+#endif /* CONFIG_COMPAT && ! already defined */
+
+#define __NR_seccomp_read		__NR_read
+#define __NR_seccomp_write		__NR_write
+#define __NR_seccomp_exit		__NR_exit
+#ifndef __NR_seccomp_sigreturn
+#define __NR_seccomp_sigreturn		__NR_rt_sigreturn
+#endif
+
+#endif /* _ASM_GENERIC_SECCOMP_H */
-- 
cgit v1.2.3-70-g09d2


From 05afedcb89189df5cea30a13b2a5b4aa70572749 Mon Sep 17 00:00:00 2001
From: "Mark A. Greer" <mgreer@animalcreek.com>
Date: Tue, 23 Sep 2014 16:38:05 -0700
Subject: NFC: digital: Add Target-mode NFC-DEP DID Support

When in Target mode, the Initiator specifies whether
subsequent DEP_REQ and DEP_RES frames will include
a DID byte by the value passed in the ATR_REQ.  If
the DID value in the ATR_REQ is '0' then no DID
byte will be included.  If the DID value is between
'1' and '14' then a DID byte containing the same
value must be included in subsequent DEP_REQ and
DEP_RES frames.  Any other DID value is invalid.
This is specified in sections 14.8.1.2 and 14.8.2.2
of the NFC Digital Protocol Spec.

Checking the DID value (if it should be there at all),
is not currently supported by the digital layer's
NFC-DEP code.  Add this support by remembering the
DID value in the ATR_REQ, checking the DID value of
received DEP_REQ frames (if it should be there at all),
and including the remembered DID value in DEP_RES
frames when appropriate.

Reviewed-by: Thierry Escande <thierry.escande@linux.intel.com>
Tested-by: Thierry Escande <thierry.escande@linux.intel.com>
Signed-off-by: Mark A. Greer <mgreer@animalcreek.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/digital.h |  1 +
 net/nfc/digital_dep.c     | 30 ++++++++++++++++++++++++++----
 2 files changed, 27 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h
index d9a5cf7ac1c..80c6183989f 100644
--- a/include/net/nfc/digital.h
+++ b/include/net/nfc/digital.h
@@ -225,6 +225,7 @@ struct nfc_digital_dev {
 	u8 curr_protocol;
 	u8 curr_rf_tech;
 	u8 curr_nfc_dep_pni;
+	u8 did;
 
 	u16 target_fsc;
 
diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c
index d07c9ab993c..7d1c794556c 100644
--- a/net/nfc/digital_dep.c
+++ b/net/nfc/digital_dep.c
@@ -32,6 +32,8 @@
 #define DIGITAL_ATR_REQ_MIN_SIZE 16
 #define DIGITAL_ATR_REQ_MAX_SIZE 64
 
+#define DIGITAL_DID_MAX	14
+
 #define DIGITAL_LR_BITS_PAYLOAD_SIZE_254B 0x30
 #define DIGITAL_FSL_BITS_PAYLOAD_SIZE_254B \
 				(DIGITAL_LR_BITS_PAYLOAD_SIZE_254B >> 4)
@@ -40,12 +42,13 @@
 #define DIGITAL_NFC_DEP_PFB_TYPE(pfb) ((pfb) & 0xE0)
 
 #define DIGITAL_NFC_DEP_PFB_TIMEOUT_BIT 0x10
+#define DIGITAL_NFC_DEP_PFB_DID_BIT	0x04
 
 #define DIGITAL_NFC_DEP_PFB_IS_TIMEOUT(pfb) \
 				((pfb) & DIGITAL_NFC_DEP_PFB_TIMEOUT_BIT)
 #define DIGITAL_NFC_DEP_MI_BIT_SET(pfb)  ((pfb) & 0x10)
 #define DIGITAL_NFC_DEP_NAD_BIT_SET(pfb) ((pfb) & 0x08)
-#define DIGITAL_NFC_DEP_DID_BIT_SET(pfb) ((pfb) & 0x04)
+#define DIGITAL_NFC_DEP_DID_BIT_SET(pfb) ((pfb) & DIGITAL_NFC_DEP_PFB_DID_BIT)
 #define DIGITAL_NFC_DEP_PFB_PNI(pfb)     ((pfb) & 0x03)
 
 #define DIGITAL_NFC_DEP_PFB_I_PDU          0x00
@@ -557,8 +560,17 @@ static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg,
 
 	pfb = dep_req->pfb;
 
-	if (DIGITAL_NFC_DEP_DID_BIT_SET(pfb))
-		size++;
+	if (DIGITAL_NFC_DEP_DID_BIT_SET(pfb)) {
+		if (ddev->did && (ddev->did == resp->data[3])) {
+			size++;
+		} else {
+			rc = -EIO;
+			goto exit;
+		}
+	} else if (ddev->did) {
+		rc = -EIO;
+		goto exit;
+	}
 
 	if (size > resp->len) {
 		rc = -EIO;
@@ -600,6 +612,13 @@ int digital_tg_send_dep_res(struct nfc_digital_dev *ddev, struct sk_buff *skb)
 	dep_res->cmd = DIGITAL_CMD_DEP_RES;
 	dep_res->pfb = ddev->curr_nfc_dep_pni;
 
+	if (ddev->did) {
+		dep_res->pfb |= DIGITAL_NFC_DEP_PFB_DID_BIT;
+
+		memcpy(skb_put(skb, sizeof(ddev->did)), &ddev->did,
+		       sizeof(ddev->did));
+	}
+
 	digital_skb_push_dep_sod(ddev, skb);
 
 	ddev->skb_add_crc(skb);
@@ -828,11 +847,14 @@ void digital_tg_recv_atr_req(struct nfc_digital_dev *ddev, void *arg,
 	atr_req = (struct digital_atr_req *)resp->data;
 
 	if (atr_req->dir != DIGITAL_NFC_DEP_FRAME_DIR_OUT ||
-	    atr_req->cmd != DIGITAL_CMD_ATR_REQ) {
+	    atr_req->cmd != DIGITAL_CMD_ATR_REQ ||
+	    atr_req->did > DIGITAL_DID_MAX) {
 		rc = -EINVAL;
 		goto exit;
 	}
 
+	ddev->did = atr_req->did;
+
 	rc = digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING,
 				     NFC_DIGITAL_FRAMING_NFC_DEP_ACTIVATED);
 	if (rc)
-- 
cgit v1.2.3-70-g09d2


From b08147cbc4d1b63d65f6c7c522fed9ef3212bc52 Mon Sep 17 00:00:00 2001
From: "Mark A. Greer" <mgreer@animalcreek.com>
Date: Tue, 23 Sep 2014 16:38:08 -0700
Subject: NFC: digital: Implement NFC-DEP max payload lengths

The maximum payload for NFC-DEP exchanges (i.e., the
number of bytes between SoD and EoD) is negotiated
using the ATR_REQ, ATR_RES, and PSL_REQ commands.
The valid maximum lengths are 64, 128, 192, and 254
bytes.

Currently, NFC-DEP code assumes that both sides are
always using 254 byte maximums and ignores attempts
by the peer to change it.  Instead, implement the
negotiation code, enforce the local maximum when
receiving data from the peer, and don't send payloads
that exceed the remote's maximum.  The default local
maximum is 254 bytes.

Reviewed-by: Thierry Escande <thierry.escande@linux.intel.com>
Tested-by: Thierry Escande <thierry.escande@linux.intel.com>
Signed-off-by: Mark A. Greer <mgreer@animalcreek.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/digital.h |   3 ++
 net/nfc/digital_dep.c     | 108 +++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 101 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h
index 80c6183989f..42dbc6e6ee2 100644
--- a/include/net/nfc/digital.h
+++ b/include/net/nfc/digital.h
@@ -227,6 +227,9 @@ struct nfc_digital_dev {
 	u8 curr_nfc_dep_pni;
 	u8 did;
 
+	u8 local_payload_max;
+	u8 remote_payload_max;
+
 	u16 target_fsc;
 
 	int (*skb_check_crc)(struct sk_buff *skb);
diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c
index 95a69898d5f..b78790088b8 100644
--- a/net/nfc/digital_dep.c
+++ b/net/nfc/digital_dep.c
@@ -34,9 +34,12 @@
 
 #define DIGITAL_DID_MAX	14
 
-#define DIGITAL_LR_BITS_PAYLOAD_SIZE_254B 0x30
-#define DIGITAL_FSL_BITS_PAYLOAD_SIZE_254B \
-				(DIGITAL_LR_BITS_PAYLOAD_SIZE_254B >> 4)
+#define DIGITAL_PAYLOAD_SIZE_MAX	254
+#define DIGITAL_PAYLOAD_BITS_TO_PP(s)	(((s) & 0x3) << 4)
+#define DIGITAL_PAYLOAD_PP_TO_BITS(s)	(((s) >> 4) & 0x3)
+#define DIGITAL_PAYLOAD_BITS_TO_FSL(s)	((s) & 0x3)
+#define DIGITAL_PAYLOAD_FSL_TO_BITS(s)	((s) & 0x3)
+
 #define DIGITAL_GB_BIT	0x02
 
 #define DIGITAL_NFC_DEP_PFB_TYPE(pfb) ((pfb) & 0xE0)
@@ -101,6 +104,32 @@ struct digital_dep_req_res {
 static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 				    struct sk_buff *resp);
 
+static const u8 digital_payload_bits_map[4] = {
+	[0] = 64,
+	[1] = 128,
+	[2] = 192,
+	[3] = 254
+};
+
+static u8 digital_payload_bits_to_size(u8 payload_bits)
+{
+	if (payload_bits >= ARRAY_SIZE(digital_payload_bits_map))
+		return 0;
+
+	return digital_payload_bits_map[payload_bits];
+}
+
+static u8 digital_payload_size_to_bits(u8 payload_size)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(digital_payload_bits_map); i++)
+		if (digital_payload_bits_map[i] == payload_size)
+			return i;
+
+	return 0xff;
+}
+
 static void digital_skb_push_dep_sod(struct nfc_digital_dev *ddev,
 				     struct sk_buff *skb)
 {
@@ -202,6 +231,7 @@ static int digital_in_send_psl_req(struct nfc_digital_dev *ddev,
 	struct sk_buff *skb;
 	struct digital_psl_req *psl_req;
 	int rc;
+	u8 payload_size, payload_bits;
 
 	skb = digital_skb_alloc(ddev, sizeof(*psl_req));
 	if (!skb)
@@ -215,7 +245,13 @@ static int digital_in_send_psl_req(struct nfc_digital_dev *ddev,
 	psl_req->cmd = DIGITAL_CMD_PSL_REQ;
 	psl_req->did = 0;
 	psl_req->brs = (0x2 << 3) | 0x2; /* 424F both directions */
-	psl_req->fsl = DIGITAL_FSL_BITS_PAYLOAD_SIZE_254B;
+
+	payload_size = min(ddev->local_payload_max, ddev->remote_payload_max);
+	payload_bits = digital_payload_size_to_bits(payload_size);
+	psl_req->fsl = DIGITAL_PAYLOAD_BITS_TO_FSL(payload_bits);
+
+	ddev->local_payload_max = payload_size;
+	ddev->remote_payload_max = payload_size;
 
 	digital_skb_push_dep_sod(ddev, skb);
 
@@ -234,7 +270,7 @@ static void digital_in_recv_atr_res(struct nfc_digital_dev *ddev, void *arg,
 {
 	struct nfc_target *target = arg;
 	struct digital_atr_res *atr_res;
-	u8 gb_len;
+	u8 gb_len, payload_bits;
 	int rc;
 
 	if (IS_ERR(resp)) {
@@ -264,6 +300,14 @@ static void digital_in_recv_atr_res(struct nfc_digital_dev *ddev, void *arg,
 
 	atr_res = (struct digital_atr_res *)resp->data;
 
+	payload_bits = DIGITAL_PAYLOAD_PP_TO_BITS(atr_res->pp);
+	ddev->remote_payload_max = digital_payload_bits_to_size(payload_bits);
+
+	if (!ddev->remote_payload_max) {
+		rc = -EINVAL;
+		goto exit;
+	}
+
 	rc = nfc_set_remote_general_bytes(ddev->nfc_dev, atr_res->gb, gb_len);
 	if (rc)
 		goto exit;
@@ -295,6 +339,7 @@ int digital_in_send_atr_req(struct nfc_digital_dev *ddev,
 	struct digital_atr_req *atr_req;
 	uint size;
 	int rc;
+	u8 payload_bits;
 
 	size = DIGITAL_ATR_REQ_MIN_SIZE + gb_len;
 
@@ -323,7 +368,9 @@ int digital_in_send_atr_req(struct nfc_digital_dev *ddev,
 	atr_req->bs = 0;
 	atr_req->br = 0;
 
-	atr_req->pp = DIGITAL_LR_BITS_PAYLOAD_SIZE_254B;
+	ddev->local_payload_max = DIGITAL_PAYLOAD_SIZE_MAX;
+	payload_bits = digital_payload_size_to_bits(ddev->local_payload_max);
+	atr_req->pp = DIGITAL_PAYLOAD_BITS_TO_PP(payload_bits);
 
 	if (gb_len) {
 		atr_req->pp |= DIGITAL_GB_BIT;
@@ -403,6 +450,11 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 		goto exit;
 	}
 
+	if (resp->len > ddev->local_payload_max) {
+		rc = -EMSGSIZE;
+		goto exit;
+	}
+
 	size = sizeof(struct digital_dep_req_res);
 	dep_res = (struct digital_dep_req_res *)resp->data;
 
@@ -498,6 +550,9 @@ int digital_in_send_dep_req(struct nfc_digital_dev *ddev,
 
 	skb_push(skb, sizeof(struct digital_dep_req_res));
 
+	if (skb->len > ddev->remote_payload_max)
+		return -EMSGSIZE;
+
 	dep_req = (struct digital_dep_req_res *)skb->data;
 	dep_req->dir = DIGITAL_NFC_DEP_FRAME_DIR_OUT;
 	dep_req->cmd = DIGITAL_CMD_DEP_REQ;
@@ -564,6 +619,11 @@ static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg,
 		goto exit;
 	}
 
+	if (resp->len > ddev->local_payload_max) {
+		rc = -EMSGSIZE;
+		goto exit;
+	}
+
 	size = sizeof(struct digital_dep_req_res);
 	dep_req = (struct digital_dep_req_res *)resp->data;
 
@@ -639,6 +699,10 @@ int digital_tg_send_dep_res(struct nfc_digital_dev *ddev, struct sk_buff *skb)
 	struct digital_dep_req_res *dep_res;
 
 	skb_push(skb, sizeof(struct digital_dep_req_res));
+
+	if (skb->len > ddev->remote_payload_max)
+		return -EMSGSIZE;
+
 	dep_res = (struct digital_dep_req_res *)skb->data;
 
 	dep_res->dir = DIGITAL_NFC_DEP_FRAME_DIR_IN;
@@ -719,7 +783,7 @@ static void digital_tg_recv_psl_req(struct nfc_digital_dev *ddev, void *arg,
 	int rc;
 	struct digital_psl_req *psl_req;
 	u8 rf_tech;
-	u8 dsi;
+	u8 dsi, payload_size, payload_bits;
 
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
@@ -764,6 +828,18 @@ static void digital_tg_recv_psl_req(struct nfc_digital_dev *ddev, void *arg,
 		goto exit;
 	}
 
+	payload_bits = DIGITAL_PAYLOAD_FSL_TO_BITS(psl_req->fsl);
+	payload_size = digital_payload_bits_to_size(payload_bits);
+
+	if (!payload_size || (payload_size > min(ddev->local_payload_max,
+						 ddev->remote_payload_max))) {
+		rc = -EINVAL;
+		goto exit;
+	}
+
+	ddev->local_payload_max = payload_size;
+	ddev->remote_payload_max = payload_size;
+
 	rc = digital_tg_send_psl_res(ddev, psl_req->did, rf_tech);
 
 exit:
@@ -795,7 +871,7 @@ static int digital_tg_send_atr_res(struct nfc_digital_dev *ddev,
 {
 	struct digital_atr_res *atr_res;
 	struct sk_buff *skb;
-	u8 *gb;
+	u8 *gb, payload_bits;
 	size_t gb_len;
 	int rc;
 
@@ -816,7 +892,11 @@ static int digital_tg_send_atr_res(struct nfc_digital_dev *ddev,
 	atr_res->cmd = DIGITAL_CMD_ATR_RES;
 	memcpy(atr_res->nfcid3, atr_req->nfcid3, sizeof(atr_req->nfcid3));
 	atr_res->to = 8;
-	atr_res->pp = DIGITAL_LR_BITS_PAYLOAD_SIZE_254B;
+
+	ddev->local_payload_max = DIGITAL_PAYLOAD_SIZE_MAX;
+	payload_bits = digital_payload_size_to_bits(ddev->local_payload_max);
+	atr_res->pp = DIGITAL_PAYLOAD_BITS_TO_PP(payload_bits);
+
 	if (gb_len) {
 		skb_put(skb, gb_len);
 
@@ -844,7 +924,7 @@ void digital_tg_recv_atr_req(struct nfc_digital_dev *ddev, void *arg,
 	int rc;
 	struct digital_atr_req *atr_req;
 	size_t gb_len, min_size;
-	u8 poll_tech_count;
+	u8 poll_tech_count, payload_bits;
 
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
@@ -893,6 +973,14 @@ void digital_tg_recv_atr_req(struct nfc_digital_dev *ddev, void *arg,
 		goto exit;
 	}
 
+	payload_bits = DIGITAL_PAYLOAD_PP_TO_BITS(atr_req->pp);
+	ddev->remote_payload_max = digital_payload_bits_to_size(payload_bits);
+
+	if (!ddev->remote_payload_max) {
+		rc = -EINVAL;
+		goto exit;
+	}
+
 	ddev->did = atr_req->did;
 
 	rc = digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING,
-- 
cgit v1.2.3-70-g09d2


From 3bd2a5bcc6cd7b8d588aa9ffa947177721eba18e Mon Sep 17 00:00:00 2001
From: "Mark A. Greer" <mgreer@animalcreek.com>
Date: Tue, 23 Sep 2014 16:38:09 -0700
Subject: NFC: digital: Add NFC-DEP Send Chaining Support

When the NFC-DEP code is given a packet to send
that is larger than the peer's maximum payload,
its supposed to set the 'MI' bit in the 'I' PDU's
Protocol Frame Byte (PFB).  Setting this bit
indicates that NFC-DEP chaining is to occur.

When NFC-DEP chaining is progress, sender 'I' PDUs
are acknowledged with 'ACK' PDUs until the last 'I'
PDU in the chain (which has the 'MI' bit cleared)
is responded to with a normal 'I' PDU.  This can
occur while in Initiator mode or in Target mode.

Sender NFC-DEP chaining is currently not implemented
in the digital layer so add that support.  Unfortunately,
since sending a frame may require writing the CRC to the
end of the data, the relevant data part of the original
skb must be copied for each intermediate frame.

Reviewed-by: Thierry Escande <thierry.escande@linux.intel.com>
Tested-by: Thierry Escande <thierry.escande@linux.intel.com>
Signed-off-by: Mark A. Greer <mgreer@animalcreek.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/digital.h |   3 ++
 net/nfc/digital_dep.c     | 126 +++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 112 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h
index 42dbc6e6ee2..2fdff00e06c 100644
--- a/include/net/nfc/digital.h
+++ b/include/net/nfc/digital.h
@@ -230,6 +230,9 @@ struct nfc_digital_dev {
 	u8 local_payload_max;
 	u8 remote_payload_max;
 
+	struct sk_buff *chaining_skb;
+	struct digital_data_exch *data_exch;
+
 	u16 target_fsc;
 
 	int (*skb_check_crc)(struct sk_buff *skb);
diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c
index b78790088b8..e613c294e42 100644
--- a/net/nfc/digital_dep.c
+++ b/net/nfc/digital_dep.c
@@ -42,14 +42,20 @@
 
 #define DIGITAL_GB_BIT	0x02
 
+#define DIGITAL_NFC_DEP_REQ_RES_HEADROOM	2 /* SoD: [SB (NFC-A)] + LEN */
+#define DIGITAL_NFC_DEP_REQ_RES_TAILROOM	2 /* EoD: 2-byte CRC */
+
 #define DIGITAL_NFC_DEP_PFB_TYPE(pfb) ((pfb) & 0xE0)
 
 #define DIGITAL_NFC_DEP_PFB_TIMEOUT_BIT 0x10
+#define DIGITAL_NFC_DEP_PFB_MI_BIT	0x10
+#define DIGITAL_NFC_DEP_PFB_NACK_BIT	0x10
 #define DIGITAL_NFC_DEP_PFB_DID_BIT	0x04
 
 #define DIGITAL_NFC_DEP_PFB_IS_TIMEOUT(pfb) \
 				((pfb) & DIGITAL_NFC_DEP_PFB_TIMEOUT_BIT)
-#define DIGITAL_NFC_DEP_MI_BIT_SET(pfb)  ((pfb) & 0x10)
+#define DIGITAL_NFC_DEP_MI_BIT_SET(pfb)  ((pfb) & DIGITAL_NFC_DEP_PFB_MI_BIT)
+#define DIGITAL_NFC_DEP_NACK_BIT_SET(pfb) ((pfb) & DIGITAL_NFC_DEP_PFB_NACK_BIT)
 #define DIGITAL_NFC_DEP_NAD_BIT_SET(pfb) ((pfb) & 0x08)
 #define DIGITAL_NFC_DEP_DID_BIT_SET(pfb) ((pfb) & DIGITAL_NFC_DEP_PFB_DID_BIT)
 #define DIGITAL_NFC_DEP_PFB_PNI(pfb)     ((pfb) & 0x03)
@@ -161,6 +167,40 @@ static int digital_skb_pull_dep_sod(struct nfc_digital_dev *ddev,
 	return 0;
 }
 
+static struct sk_buff *
+digital_send_dep_data_prep(struct nfc_digital_dev *ddev, struct sk_buff *skb,
+			   struct digital_dep_req_res *dep_req_res,
+			   struct digital_data_exch *data_exch)
+{
+	struct sk_buff *new_skb;
+
+	if (skb->len > ddev->remote_payload_max) {
+		dep_req_res->pfb |= DIGITAL_NFC_DEP_PFB_MI_BIT;
+
+		new_skb = digital_skb_alloc(ddev, ddev->remote_payload_max);
+		if (!new_skb) {
+			kfree_skb(ddev->chaining_skb);
+			ddev->chaining_skb = NULL;
+
+			return ERR_PTR(-ENOMEM);
+		}
+
+		skb_reserve(new_skb, ddev->tx_headroom + NFC_HEADER_SIZE +
+					DIGITAL_NFC_DEP_REQ_RES_HEADROOM);
+		memcpy(skb_put(new_skb, ddev->remote_payload_max), skb->data,
+		       ddev->remote_payload_max);
+		skb_pull(skb, ddev->remote_payload_max);
+
+		ddev->chaining_skb = skb;
+		ddev->data_exch = data_exch;
+	} else {
+		ddev->chaining_skb = NULL;
+		new_skb = skb;
+	}
+
+	return new_skb;
+}
+
 static void digital_in_recv_psl_res(struct nfc_digital_dev *ddev, void *arg,
 				    struct sk_buff *resp)
 {
@@ -498,8 +538,6 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 		break;
 
 	case DIGITAL_NFC_DEP_PFB_ACK_NACK_PDU:
-		pr_err("Received a ACK/NACK PDU\n");
-
 		if (DIGITAL_NFC_DEP_PFB_PNI(pfb) != ddev->curr_nfc_dep_pni) {
 			PROTOCOL_ERR("14.12.3.3");
 			rc = -EIO;
@@ -509,6 +547,17 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 		ddev->curr_nfc_dep_pni =
 			DIGITAL_NFC_DEP_PFB_PNI(ddev->curr_nfc_dep_pni + 1);
 
+		if (ddev->chaining_skb && !DIGITAL_NFC_DEP_NACK_BIT_SET(pfb)) {
+			rc = digital_in_send_dep_req(ddev, NULL,
+						     ddev->chaining_skb,
+						     ddev->data_exch);
+			if (rc)
+				goto error;
+
+			return;
+		}
+
+		pr_err("Received a ACK/NACK PDU\n");
 		rc = -EINVAL;
 		goto exit;
 
@@ -538,6 +587,9 @@ exit:
 error:
 	kfree(data_exch);
 
+	kfree_skb(ddev->chaining_skb);
+	ddev->chaining_skb = NULL;
+
 	if (rc)
 		kfree_skb(resp);
 }
@@ -547,23 +599,38 @@ int digital_in_send_dep_req(struct nfc_digital_dev *ddev,
 			    struct digital_data_exch *data_exch)
 {
 	struct digital_dep_req_res *dep_req;
+	struct sk_buff *chaining_skb, *tmp_skb;
+	int rc;
 
 	skb_push(skb, sizeof(struct digital_dep_req_res));
 
-	if (skb->len > ddev->remote_payload_max)
-		return -EMSGSIZE;
-
 	dep_req = (struct digital_dep_req_res *)skb->data;
+
 	dep_req->dir = DIGITAL_NFC_DEP_FRAME_DIR_OUT;
 	dep_req->cmd = DIGITAL_CMD_DEP_REQ;
 	dep_req->pfb = ddev->curr_nfc_dep_pni;
 
-	digital_skb_push_dep_sod(ddev, skb);
+	chaining_skb = ddev->chaining_skb;
 
-	ddev->skb_add_crc(skb);
+	tmp_skb = digital_send_dep_data_prep(ddev, skb, dep_req, data_exch);
+	if (IS_ERR(tmp_skb))
+		return PTR_ERR(tmp_skb);
+
+	digital_skb_push_dep_sod(ddev, tmp_skb);
+
+	ddev->skb_add_crc(tmp_skb);
+
+	rc = digital_in_send_cmd(ddev, tmp_skb, 1500, digital_in_recv_dep_res,
+				 data_exch);
+	if (rc) {
+		if (tmp_skb != skb)
+			kfree_skb(tmp_skb);
 
-	return digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res,
-				   data_exch);
+		kfree_skb(chaining_skb);
+		ddev->chaining_skb = NULL;
+	}
+
+	return rc;
 }
 
 static void digital_tg_set_rf_tech(struct nfc_digital_dev *ddev, u8 rf_tech)
@@ -678,6 +745,14 @@ static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg,
 			goto exit;
 		}
 
+		if (ddev->chaining_skb && !DIGITAL_NFC_DEP_NACK_BIT_SET(pfb)) {
+			rc = digital_tg_send_dep_res(ddev, ddev->chaining_skb);
+			if (rc)
+				goto exit;
+
+			return;
+		}
+
 		pr_err("Received a ACK/NACK PDU\n");
 		rc = -EINVAL;
 		goto exit;
@@ -690,6 +765,9 @@ static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg,
 	rc = nfc_tm_data_received(ddev->nfc_dev, resp);
 
 exit:
+	kfree_skb(ddev->chaining_skb);
+	ddev->chaining_skb = NULL;
+
 	if (rc)
 		kfree_skb(resp);
 }
@@ -697,12 +775,11 @@ exit:
 int digital_tg_send_dep_res(struct nfc_digital_dev *ddev, struct sk_buff *skb)
 {
 	struct digital_dep_req_res *dep_res;
+	struct sk_buff *chaining_skb, *tmp_skb;
+	int rc;
 
 	skb_push(skb, sizeof(struct digital_dep_req_res));
 
-	if (skb->len > ddev->remote_payload_max)
-		return -EMSGSIZE;
-
 	dep_res = (struct digital_dep_req_res *)skb->data;
 
 	dep_res->dir = DIGITAL_NFC_DEP_FRAME_DIR_IN;
@@ -719,12 +796,27 @@ int digital_tg_send_dep_res(struct nfc_digital_dev *ddev, struct sk_buff *skb)
 	ddev->curr_nfc_dep_pni =
 		DIGITAL_NFC_DEP_PFB_PNI(ddev->curr_nfc_dep_pni + 1);
 
-	digital_skb_push_dep_sod(ddev, skb);
+	chaining_skb = ddev->chaining_skb;
 
-	ddev->skb_add_crc(skb);
+	tmp_skb = digital_send_dep_data_prep(ddev, skb, dep_res, NULL);
+	if (IS_ERR(tmp_skb))
+		return PTR_ERR(tmp_skb);
+
+	digital_skb_push_dep_sod(ddev, tmp_skb);
 
-	return digital_tg_send_cmd(ddev, skb, 1500, digital_tg_recv_dep_req,
-				   NULL);
+	ddev->skb_add_crc(tmp_skb);
+
+	rc = digital_tg_send_cmd(ddev, tmp_skb, 1500, digital_tg_recv_dep_req,
+				 NULL);
+	if (rc) {
+		if (tmp_skb != skb)
+			kfree_skb(tmp_skb);
+
+		kfree_skb(chaining_skb);
+		ddev->chaining_skb = NULL;
+	}
+
+	return rc;
 }
 
 static void digital_tg_send_psl_res_complete(struct nfc_digital_dev *ddev,
-- 
cgit v1.2.3-70-g09d2


From a80509c76bf2b10dae76f3caea343ac4b85c72b4 Mon Sep 17 00:00:00 2001
From: "Mark A. Greer" <mgreer@animalcreek.com>
Date: Tue, 23 Sep 2014 16:38:11 -0700
Subject: NFC: digital: Add NFC-DEP Initiator-side NACK Support

When an NFC-DEP Initiator receives a frame with
an incorrect CRC or with a parity error, and the
frame is at least 4 bytes long, its supposed to
send a NACK to the Target.  The Initiator can
send up to 'N(retry,nack)' consecutive NACKs
where 2 <= 'N(retry,nack)' <= 5.  When the limit
is exceeded, a PROTOCOL EXCEPTION is raised.
Any other type of transmission error is to be
ignored and the Initiator should continue
waiting for a new frame.  This is described
in section 14.12.5.4 of the NFC Digital Protocol
Spec.

The digital layer's NFC-DEP code doesn't implement
any of this so add it.  This support diverges from
the spec in two significant ways:

a) NACKs will be sent for ANY error reported by the
   driver except a timeout.  This is done because
   there is currently no way for the digital layer
   to distinguish a CRC or parity error from any
   other type of error reported by the driver.

b) All other errors will cause a PROTOCOL EXCEPTION
   even frames with CRC errors that are less than 4
   bytes.

The value chosen for 'N(retry,nack)' is 2.

Targets do not send NACK PDUs.

Reviewed-by: Thierry Escande <thierry.escande@linux.intel.com>
Tested-by: Thierry Escande <thierry.escande@linux.intel.com>
Signed-off-by: Mark A. Greer <mgreer@animalcreek.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/digital.h |  2 ++
 net/nfc/digital_dep.c     | 69 +++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 66 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h
index 2fdff00e06c..2fd498cdb81 100644
--- a/include/net/nfc/digital.h
+++ b/include/net/nfc/digital.h
@@ -233,6 +233,8 @@ struct nfc_digital_dev {
 	struct sk_buff *chaining_skb;
 	struct digital_data_exch *data_exch;
 
+	int nack_count;
+
 	u16 target_fsc;
 
 	int (*skb_check_crc)(struct sk_buff *skb);
diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c
index 35a9edf0e36..9840e858ec5 100644
--- a/net/nfc/digital_dep.c
+++ b/net/nfc/digital_dep.c
@@ -17,6 +17,8 @@
 
 #include "digital.h"
 
+#define DIGITAL_NFC_DEP_N_RETRY_NACK	2
+
 #define DIGITAL_NFC_DEP_FRAME_DIR_OUT 0xD4
 #define DIGITAL_NFC_DEP_FRAME_DIR_IN  0xD5
 
@@ -529,6 +531,38 @@ static int digital_in_send_ack(struct nfc_digital_dev *ddev,
 	return rc;
 }
 
+static int digital_in_send_nack(struct nfc_digital_dev *ddev,
+				struct digital_data_exch *data_exch)
+{
+	struct digital_dep_req_res *dep_req;
+	struct sk_buff *skb;
+	int rc;
+
+	skb = digital_skb_alloc(ddev, 1);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_push(skb, sizeof(struct digital_dep_req_res));
+
+	dep_req = (struct digital_dep_req_res *)skb->data;
+
+	dep_req->dir = DIGITAL_NFC_DEP_FRAME_DIR_OUT;
+	dep_req->cmd = DIGITAL_CMD_DEP_REQ;
+	dep_req->pfb = DIGITAL_NFC_DEP_PFB_ACK_NACK_PDU |
+		       DIGITAL_NFC_DEP_PFB_NACK_BIT | ddev->curr_nfc_dep_pni;
+
+	digital_skb_push_dep_sod(ddev, skb);
+
+	ddev->skb_add_crc(skb);
+
+	rc = digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res,
+				 data_exch);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
+}
+
 static int digital_in_send_rtox(struct nfc_digital_dev *ddev,
 				struct digital_data_exch *data_exch, u8 rtox)
 {
@@ -575,20 +609,43 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
 		resp = NULL;
+
+		if ((rc != -ETIMEDOUT) &&
+		    (ddev->nack_count++ < DIGITAL_NFC_DEP_N_RETRY_NACK)) {
+			rc = digital_in_send_nack(ddev, data_exch);
+			if (rc)
+				goto error;
+
+			return;
+		}
+
+		goto exit;
+	}
+
+	rc = digital_skb_pull_dep_sod(ddev, resp);
+	if (rc) {
+		PROTOCOL_ERR("14.4.1.2");
 		goto exit;
 	}
 
 	rc = ddev->skb_check_crc(resp);
 	if (rc) {
+		if ((resp->len >= 4) &&
+		    (ddev->nack_count++ < DIGITAL_NFC_DEP_N_RETRY_NACK)) {
+			rc = digital_in_send_nack(ddev, data_exch);
+			if (rc)
+				goto error;
+
+			kfree_skb(resp);
+
+			return;
+		}
+
 		PROTOCOL_ERR("14.4.1.6");
 		goto error;
 	}
 
-	rc = digital_skb_pull_dep_sod(ddev, resp);
-	if (rc) {
-		PROTOCOL_ERR("14.4.1.2");
-		goto exit;
-	}
+	ddev->nack_count = 0;
 
 	if (resp->len > ddev->local_payload_max) {
 		rc = -EMSGSIZE;
@@ -721,6 +778,8 @@ int digital_in_send_dep_req(struct nfc_digital_dev *ddev,
 	dep_req->cmd = DIGITAL_CMD_DEP_REQ;
 	dep_req->pfb = ddev->curr_nfc_dep_pni;
 
+	ddev->nack_count = 0;
+
 	chaining_skb = ddev->chaining_skb;
 
 	tmp_skb = digital_send_dep_data_prep(ddev, skb, dep_req, data_exch);
-- 
cgit v1.2.3-70-g09d2


From 49dbb14e30c3249f98fe243c3e21b91d10c5c59b Mon Sep 17 00:00:00 2001
From: "Mark A. Greer" <mgreer@animalcreek.com>
Date: Tue, 23 Sep 2014 16:38:12 -0700
Subject: NFC: digital: Add NFC-DEP Target-side NACK Support

When an NFC-DEP Target receives a NACK PDU with
a PNI equal to 1 less than the current PNI, it
is supposed to re-send the last PDU.  This is
implied in section 14.12.5.4 of the NFC Digital
Protocol Spec.

The digital layer's NFC-DEP code doesn't implement
Target-side NACK handing so add it.  The last PDU
that was sent is saved in the 'nfc_digital_dev'
structure's 'saved_skb' member.  The skb will have
an additional reference taken to ensure that the skb
isn't freed when the driver performs a kfree_skb()
on the skb.  The length of the skb/PDU is also saved
so the length can be restored when re-sending the PDU
in the skb (the driver will perform an skb_pull() so
an skb_push() needs to be done to restore the skb's
data pointer/length).

Reviewed-by: Thierry Escande <thierry.escande@linux.intel.com>
Tested-by: Thierry Escande <thierry.escande@linux.intel.com>
Signed-off-by: Mark A. Greer <mgreer@animalcreek.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/digital.h |  3 +++
 net/nfc/digital_dep.c     | 62 ++++++++++++++++++++++++++++++++++++++---------
 2 files changed, 54 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h
index 2fd498cdb81..7400a8126cd 100644
--- a/include/net/nfc/digital.h
+++ b/include/net/nfc/digital.h
@@ -235,6 +235,9 @@ struct nfc_digital_dev {
 
 	int nack_count;
 
+	struct sk_buff *saved_skb;
+	unsigned int saved_skb_len;
+
 	u16 target_fsc;
 
 	int (*skb_check_crc)(struct sk_buff *skb);
diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c
index 9840e858ec5..31418edbe78 100644
--- a/net/nfc/digital_dep.c
+++ b/net/nfc/digital_dep.c
@@ -864,14 +864,29 @@ static int digital_tg_send_ack(struct nfc_digital_dev *ddev,
 
 	ddev->skb_add_crc(skb);
 
+	ddev->saved_skb = skb_get(skb);
+	ddev->saved_skb_len = skb->len;
+
 	rc = digital_tg_send_cmd(ddev, skb, 1500, digital_tg_recv_dep_req,
 				 data_exch);
-	if (rc)
+	if (rc) {
 		kfree_skb(skb);
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+	}
 
 	return rc;
 }
 
+static int digital_tg_send_saved_skb(struct nfc_digital_dev *ddev)
+{
+	skb_get(ddev->saved_skb);
+	skb_push(ddev->saved_skb, ddev->saved_skb_len);
+
+	return digital_tg_send_cmd(ddev, ddev->saved_skb, 1500,
+				   digital_tg_recv_dep_req, NULL);
+}
+
 static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg,
 				    struct sk_buff *resp)
 {
@@ -948,6 +963,9 @@ static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg,
 			goto exit;
 		}
 
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+
 		resp = digital_recv_dep_data_gather(ddev, pfb, resp,
 						    digital_tg_send_ack, NULL);
 		if (IS_ERR(resp)) {
@@ -966,23 +984,36 @@ static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg,
 		rc = 0;
 		break;
 	case DIGITAL_NFC_DEP_PFB_ACK_NACK_PDU:
-		if (DIGITAL_NFC_DEP_PFB_PNI(pfb) != ddev->curr_nfc_dep_pni) {
-			PROTOCOL_ERR("14.12.3.4");
-			rc = -EIO;
-			goto exit;
-		}
+		if (!DIGITAL_NFC_DEP_NACK_BIT_SET(pfb)) { /* ACK */
+			if ((DIGITAL_NFC_DEP_PFB_PNI(pfb) !=
+						ddev->curr_nfc_dep_pni) ||
+			    !ddev->chaining_skb || !ddev->saved_skb) {
+				rc = -EIO;
+				goto exit;
+			}
+
+			kfree_skb(ddev->saved_skb);
+			ddev->saved_skb = NULL;
 
-		if (ddev->chaining_skb && !DIGITAL_NFC_DEP_NACK_BIT_SET(pfb)) {
 			rc = digital_tg_send_dep_res(ddev, ddev->chaining_skb);
 			if (rc)
 				goto exit;
+		} else { /* NACK */
+			if ((DIGITAL_NFC_DEP_PFB_PNI(pfb + 1) !=
+						ddev->curr_nfc_dep_pni) ||
+			    !ddev->saved_skb) {
+				rc = -EIO;
+				goto exit;
+			}
 
-			return;
+			rc = digital_tg_send_saved_skb(ddev);
+			if (rc) {
+				kfree_skb(ddev->saved_skb);
+				goto exit;
+			}
 		}
 
-		pr_err("Received a ACK/NACK PDU\n");
-		rc = -EINVAL;
-		goto exit;
+		return;
 	case DIGITAL_NFC_DEP_PFB_SUPERVISOR_PDU:
 		pr_err("Received a SUPERVISOR PDU\n");
 		rc = -EINVAL;
@@ -995,6 +1026,9 @@ exit:
 	kfree_skb(ddev->chaining_skb);
 	ddev->chaining_skb = NULL;
 
+	kfree_skb(ddev->saved_skb);
+	ddev->saved_skb = NULL;
+
 	if (rc)
 		kfree_skb(resp);
 }
@@ -1033,6 +1067,9 @@ int digital_tg_send_dep_res(struct nfc_digital_dev *ddev, struct sk_buff *skb)
 
 	ddev->skb_add_crc(tmp_skb);
 
+	ddev->saved_skb = skb_get(tmp_skb);
+	ddev->saved_skb_len = tmp_skb->len;
+
 	rc = digital_tg_send_cmd(ddev, tmp_skb, 1500, digital_tg_recv_dep_req,
 				 NULL);
 	if (rc) {
@@ -1041,6 +1078,9 @@ int digital_tg_send_dep_res(struct nfc_digital_dev *ddev, struct sk_buff *skb)
 
 		kfree_skb(chaining_skb);
 		ddev->chaining_skb = NULL;
+
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
 	}
 
 	return rc;
-- 
cgit v1.2.3-70-g09d2


From 384ab1d174a11292af63674a26eaa99864db9b48 Mon Sep 17 00:00:00 2001
From: "Mark A. Greer" <mgreer@animalcreek.com>
Date: Tue, 23 Sep 2014 16:38:13 -0700
Subject: NFC: digital: Add NFC-DEP Initiator-side ATN Support

When an NFC-DEP Initiator times out when waiting for
a DEP_RES from the Target, its supposed to send an
ATN to the Target.  The Target should respond to the
ATN with a similar ATN PDU and the Initiator can then
resend the last non-ATN PDU that it sent.  No more
than 'N(retry,atn)' are to be send where
2 <= 'N(retry,atn)' <= 5.  If the Initiator had just
sent a NACK PDU when the timeout occurred, it is to
continue sending NACKs until 'N(retry,nack)' NACKs
have been send.  This is described in section
14.12.5.6 of the NFC-DEP Digital Protocol Spec.

The digital layer's NFC-DEP code doesn't implement
this so add that support.

The value chosen for 'N(retry,atn)' is 2.

Reviewed-by: Thierry Escande <thierry.escande@linux.intel.com>
Tested-by: Thierry Escande <thierry.escande@linux.intel.com>
Signed-off-by: Mark A. Greer <mgreer@animalcreek.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/digital.h |   1 +
 net/nfc/digital_dep.c     | 104 +++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 99 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h
index 7400a8126cd..0ae101eef0f 100644
--- a/include/net/nfc/digital.h
+++ b/include/net/nfc/digital.h
@@ -233,6 +233,7 @@ struct nfc_digital_dev {
 	struct sk_buff *chaining_skb;
 	struct digital_data_exch *data_exch;
 
+	int atn_count;
 	int nack_count;
 
 	struct sk_buff *saved_skb;
diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c
index 31418edbe78..8f1fefd2ed1 100644
--- a/net/nfc/digital_dep.c
+++ b/net/nfc/digital_dep.c
@@ -18,6 +18,7 @@
 #include "digital.h"
 
 #define DIGITAL_NFC_DEP_N_RETRY_NACK	2
+#define DIGITAL_NFC_DEP_N_RETRY_ATN	2
 
 #define DIGITAL_NFC_DEP_FRAME_DIR_OUT 0xD4
 #define DIGITAL_NFC_DEP_FRAME_DIR_IN  0xD5
@@ -523,10 +524,16 @@ static int digital_in_send_ack(struct nfc_digital_dev *ddev,
 
 	ddev->skb_add_crc(skb);
 
+	ddev->saved_skb = skb_get(skb);
+	ddev->saved_skb_len = skb->len;
+
 	rc = digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res,
 				 data_exch);
-	if (rc)
+	if (rc) {
 		kfree_skb(skb);
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+	}
 
 	return rc;
 }
@@ -563,6 +570,37 @@ static int digital_in_send_nack(struct nfc_digital_dev *ddev,
 	return rc;
 }
 
+static int digital_in_send_atn(struct nfc_digital_dev *ddev,
+			       struct digital_data_exch *data_exch)
+{
+	struct digital_dep_req_res *dep_req;
+	struct sk_buff *skb;
+	int rc;
+
+	skb = digital_skb_alloc(ddev, 1);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_push(skb, sizeof(struct digital_dep_req_res));
+
+	dep_req = (struct digital_dep_req_res *)skb->data;
+
+	dep_req->dir = DIGITAL_NFC_DEP_FRAME_DIR_OUT;
+	dep_req->cmd = DIGITAL_CMD_DEP_REQ;
+	dep_req->pfb = DIGITAL_NFC_DEP_PFB_SUPERVISOR_PDU;
+
+	digital_skb_push_dep_sod(ddev, skb);
+
+	ddev->skb_add_crc(skb);
+
+	rc = digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res,
+				 data_exch);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
+}
+
 static int digital_in_send_rtox(struct nfc_digital_dev *ddev,
 				struct digital_data_exch *data_exch, u8 rtox)
 {
@@ -589,14 +627,30 @@ static int digital_in_send_rtox(struct nfc_digital_dev *ddev,
 
 	ddev->skb_add_crc(skb);
 
+	ddev->saved_skb = skb_get(skb);
+	ddev->saved_skb_len = skb->len;
+
 	rc = digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res,
 				 data_exch);
-	if (rc)
+	if (rc) {
 		kfree_skb(skb);
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+	}
 
 	return rc;
 }
 
+static int digital_in_send_saved_skb(struct nfc_digital_dev *ddev,
+				     struct digital_data_exch *data_exch)
+{
+	skb_get(ddev->saved_skb);
+	skb_push(ddev->saved_skb, ddev->saved_skb_len);
+
+	return digital_in_send_cmd(ddev, ddev->saved_skb, 1500,
+				   digital_in_recv_dep_res, data_exch);
+}
+
 static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 				    struct sk_buff *resp)
 {
@@ -610,12 +664,23 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 		rc = PTR_ERR(resp);
 		resp = NULL;
 
-		if ((rc != -ETIMEDOUT) &&
+		if (((rc != -ETIMEDOUT) || ddev->nack_count) &&
 		    (ddev->nack_count++ < DIGITAL_NFC_DEP_N_RETRY_NACK)) {
+			ddev->atn_count = 0;
+
 			rc = digital_in_send_nack(ddev, data_exch);
 			if (rc)
 				goto error;
 
+			return;
+		} else if ((rc == -ETIMEDOUT) &&
+			   (ddev->atn_count++ < DIGITAL_NFC_DEP_N_RETRY_ATN)) {
+			ddev->nack_count = 0;
+
+			rc = digital_in_send_atn(ddev, data_exch);
+			if (rc)
+				goto error;
+
 			return;
 		}
 
@@ -632,6 +697,8 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 	if (rc) {
 		if ((resp->len >= 4) &&
 		    (ddev->nack_count++ < DIGITAL_NFC_DEP_N_RETRY_NACK)) {
+			ddev->atn_count = 0;
+
 			rc = digital_in_send_nack(ddev, data_exch);
 			if (rc)
 				goto error;
@@ -645,6 +712,7 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 		goto error;
 	}
 
+	ddev->atn_count = 0;
 	ddev->nack_count = 0;
 
 	if (resp->len > ddev->local_payload_max) {
@@ -692,6 +760,9 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 		ddev->curr_nfc_dep_pni =
 			DIGITAL_NFC_DEP_PFB_PNI(ddev->curr_nfc_dep_pni + 1);
 
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+
 		resp = digital_recv_dep_data_gather(ddev, pfb, resp,
 						    digital_in_send_ack,
 						    data_exch);
@@ -722,6 +793,9 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 			DIGITAL_NFC_DEP_PFB_PNI(ddev->curr_nfc_dep_pni + 1);
 
 		if (ddev->chaining_skb && !DIGITAL_NFC_DEP_NACK_BIT_SET(pfb)) {
+			kfree_skb(ddev->saved_skb);
+			ddev->saved_skb = NULL;
+
 			rc = digital_in_send_dep_req(ddev, NULL,
 						     ddev->chaining_skb,
 						     ddev->data_exch);
@@ -736,11 +810,19 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 		goto exit;
 
 	case DIGITAL_NFC_DEP_PFB_SUPERVISOR_PDU:
-		if (!DIGITAL_NFC_DEP_PFB_IS_TIMEOUT(pfb)) {
-			rc = -EINVAL;
-			goto error;
+		if (!DIGITAL_NFC_DEP_PFB_IS_TIMEOUT(pfb)) { /* ATN */
+			rc = digital_in_send_saved_skb(ddev, data_exch);
+			if (rc) {
+				kfree_skb(ddev->saved_skb);
+				goto error;
+			}
+
+			return;
 		}
 
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+
 		rc = digital_in_send_rtox(ddev, data_exch, resp->data[0]);
 		if (rc)
 			goto error;
@@ -758,6 +840,9 @@ error:
 	kfree_skb(ddev->chaining_skb);
 	ddev->chaining_skb = NULL;
 
+	kfree_skb(ddev->saved_skb);
+	ddev->saved_skb = NULL;
+
 	if (rc)
 		kfree_skb(resp);
 }
@@ -778,6 +863,7 @@ int digital_in_send_dep_req(struct nfc_digital_dev *ddev,
 	dep_req->cmd = DIGITAL_CMD_DEP_REQ;
 	dep_req->pfb = ddev->curr_nfc_dep_pni;
 
+	ddev->atn_count = 0;
 	ddev->nack_count = 0;
 
 	chaining_skb = ddev->chaining_skb;
@@ -790,6 +876,9 @@ int digital_in_send_dep_req(struct nfc_digital_dev *ddev,
 
 	ddev->skb_add_crc(tmp_skb);
 
+	ddev->saved_skb = skb_get(tmp_skb);
+	ddev->saved_skb_len = tmp_skb->len;
+
 	rc = digital_in_send_cmd(ddev, tmp_skb, 1500, digital_in_recv_dep_res,
 				 data_exch);
 	if (rc) {
@@ -798,6 +887,9 @@ int digital_in_send_dep_req(struct nfc_digital_dev *ddev,
 
 		kfree_skb(chaining_skb);
 		ddev->chaining_skb = NULL;
+
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
 	}
 
 	return rc;
-- 
cgit v1.2.3-70-g09d2


From 90d78c13965859d87622b37a221ebf29522585a8 Mon Sep 17 00:00:00 2001
From: Julien Lefrique <lefrique@marvell.com>
Date: Tue, 21 Oct 2014 16:52:45 +0200
Subject: NFC: NCI: Enable NFC-DEP in Listen A and Listen F

Send LA_SEL_INFO and LF_PROTOCOL_TYPE with NFC-DEP protocol enabled.
Configure 212 Kbit/s and 412 Kbit/s bit rates for Listen F.

Signed-off-by: Julien Lefrique <lefrique@marvell.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci.h | 10 ++++++++++
 net/nfc/nci/core.c    | 29 +++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h
index 9eca9ae2280..36cf65386b8 100644
--- a/include/net/nfc/nci.h
+++ b/include/net/nfc/nci.h
@@ -106,6 +106,16 @@
 
 /* NCI Configuration Parameter Tags */
 #define NCI_PN_ATR_REQ_GEN_BYTES				0x29
+#define NCI_LA_SEL_INFO						0x32
+#define NCI_LF_PROTOCOL_TYPE					0x50
+#define NCI_LF_CON_BITR_F					0x54
+
+/* NCI Configuration Parameters masks */
+#define NCI_LA_SEL_INFO_ISO_DEP_MASK				0x20
+#define NCI_LA_SEL_INFO_NFC_DEP_MASK				0x40
+#define NCI_LF_PROTOCOL_TYPE_NFC_DEP_MASK			0x02
+#define NCI_LF_CON_BITR_F_212					0x02
+#define NCI_LF_CON_BITR_F_424					0x04
 
 /* NCI Reset types */
 #define NCI_RESET_TYPE_KEEP_CONFIG				0x00
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index d376e4abe0f..61f92678a64 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -474,6 +474,29 @@ static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev)
 			   msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT));
 }
 
+static int nci_set_listen_parameters(struct nfc_dev *nfc_dev)
+{
+	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+	int rc;
+	__u8 val;
+
+	val = NCI_LA_SEL_INFO_NFC_DEP_MASK;
+
+	rc = nci_set_config(ndev, NCI_LA_SEL_INFO, 1, &val);
+	if (rc)
+		return rc;
+
+	val = NCI_LF_PROTOCOL_TYPE_NFC_DEP_MASK;
+
+	rc = nci_set_config(ndev, NCI_LF_PROTOCOL_TYPE, 1, &val);
+	if (rc)
+		return rc;
+
+	val = NCI_LF_CON_BITR_F_212 | NCI_LF_CON_BITR_F_424;
+
+	return nci_set_config(ndev, NCI_LF_CON_BITR_F, 1, &val);
+}
+
 static int nci_start_poll(struct nfc_dev *nfc_dev,
 			  __u32 im_protocols, __u32 tm_protocols)
 {
@@ -510,6 +533,12 @@ static int nci_start_poll(struct nfc_dev *nfc_dev,
 		}
 	}
 
+	if (tm_protocols & NFC_PROTO_NFC_DEP_MASK) {
+		rc = nci_set_listen_parameters(nfc_dev);
+		if (rc)
+			pr_err("failed to set listen parameters\n");
+	}
+
 	param.im_protocols = im_protocols;
 	param.tm_protocols = tm_protocols;
 	rc = nci_request(ndev, nci_rf_discover_req, (unsigned long)&param,
-- 
cgit v1.2.3-70-g09d2


From a99903ec4566eeeaaaf611499cae00abbe844938 Mon Sep 17 00:00:00 2001
From: Julien Lefrique <lefrique@marvell.com>
Date: Tue, 21 Oct 2014 16:52:46 +0200
Subject: NFC: NCI: Handle Target mode activation

Changes:

 * Extract the Listen mode activation parameters from RF_INTF_ACTIVATED_NTF.

 * Store the General Bytes of ATR_REQ.

 * Signal that Target mode is activated in case of an activation in NFC-DEP.

 * Update the NCI state accordingly.

 * Use the various constants defined in nfc.h.

 * Fix the ATR_REQ and ATR_RES maximum size. As per NCI 1.0 and NCI 1.1, the
   Activation Parameters for both Poll and Listen mode contain all the bytes of
   ATR_REQ/ATR_RES starting and including Byte 3 as defined in [DIGITAL].
   In [DIGITAL], the maximum size of ATR_REQ/ATR_RES is 64 bytes and they are
   numbered starting from Byte 1.

Signed-off-by: Julien Lefrique <lefrique@marvell.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci.h      |  26 +++++++--
 include/net/nfc/nci_core.h |   3 +
 include/net/nfc/nfc.h      |   2 +
 include/uapi/linux/nfc.h   |  20 ++++---
 net/nfc/nci/ntf.c          | 133 +++++++++++++++++++++++++++++++++++++--------
 5 files changed, 146 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h
index 36cf65386b8..fffadc706e0 100644
--- a/include/net/nfc/nci.h
+++ b/include/net/nfc/nci.h
@@ -28,6 +28,8 @@
 #ifndef __NCI_H
 #define __NCI_H
 
+#include <net/nfc/nfc.h>
+
 /* NCI constants */
 #define NCI_MAX_NUM_MAPPING_CONFIGS				10
 #define NCI_MAX_NUM_RF_CONFIGS					10
@@ -73,6 +75,8 @@
 #define NCI_NFC_A_ACTIVE_LISTEN_MODE				0x83
 #define NCI_NFC_F_ACTIVE_LISTEN_MODE				0x85
 
+#define NCI_RF_TECH_MODE_LISTEN_MASK				0x80
+
 /* NCI RF Technologies */
 #define NCI_NFC_RF_TECHNOLOGY_A					0x00
 #define NCI_NFC_RF_TECHNOLOGY_B					0x01
@@ -324,26 +328,31 @@ struct nci_core_intf_error_ntf {
 struct rf_tech_specific_params_nfca_poll {
 	__u16	sens_res;
 	__u8	nfcid1_len;	/* 0, 4, 7, or 10 Bytes */
-	__u8	nfcid1[10];
+	__u8	nfcid1[NFC_NFCID1_MAXSIZE];
 	__u8	sel_res_len;	/* 0 or 1 Bytes */
 	__u8	sel_res;
 } __packed;
 
 struct rf_tech_specific_params_nfcb_poll {
 	__u8	sensb_res_len;
-	__u8	sensb_res[12];	/* 11 or 12 Bytes */
+	__u8	sensb_res[NFC_SENSB_RES_MAXSIZE];	/* 11 or 12 Bytes */
 } __packed;
 
 struct rf_tech_specific_params_nfcf_poll {
 	__u8	bit_rate;
 	__u8	sensf_res_len;
-	__u8	sensf_res[18];	/* 16 or 18 Bytes */
+	__u8	sensf_res[NFC_SENSF_RES_MAXSIZE];	/* 16 or 18 Bytes */
 } __packed;
 
 struct rf_tech_specific_params_nfcv_poll {
 	__u8	res_flags;
 	__u8	dsfid;
-	__u8	uid[8];	/* 8 Bytes */
+	__u8	uid[NFC_ISO15693_UID_MAXSIZE];	/* 8 Bytes */
+} __packed;
+
+struct rf_tech_specific_params_nfcf_listen {
+	__u8	local_nfcid2_len;
+	__u8	local_nfcid2[NFC_NFCID2_MAXSIZE];	/* 0 or 8 Bytes */
 } __packed;
 
 struct nci_rf_discover_ntf {
@@ -375,7 +384,12 @@ struct activation_params_nfcb_poll_iso_dep {
 
 struct activation_params_poll_nfc_dep {
 	__u8	atr_res_len;
-	__u8	atr_res[63];
+	__u8	atr_res[NFC_ATR_RES_MAXSIZE - 2]; /* ATR_RES from byte 3 */
+};
+
+struct activation_params_listen_nfc_dep {
+	__u8	atr_req_len;
+	__u8	atr_req[NFC_ATR_REQ_MAXSIZE - 2]; /* ATR_REQ from byte 3 */
 };
 
 struct nci_rf_intf_activated_ntf {
@@ -392,6 +406,7 @@ struct nci_rf_intf_activated_ntf {
 		struct rf_tech_specific_params_nfcb_poll nfcb_poll;
 		struct rf_tech_specific_params_nfcf_poll nfcf_poll;
 		struct rf_tech_specific_params_nfcv_poll nfcv_poll;
+		struct rf_tech_specific_params_nfcf_listen nfcf_listen;
 	} rf_tech_specific_params;
 
 	__u8	data_exch_rf_tech_and_mode;
@@ -403,6 +418,7 @@ struct nci_rf_intf_activated_ntf {
 		struct activation_params_nfca_poll_iso_dep nfca_poll_iso_dep;
 		struct activation_params_nfcb_poll_iso_dep nfcb_poll_iso_dep;
 		struct activation_params_poll_nfc_dep poll_nfc_dep;
+		struct activation_params_listen_nfc_dep listen_nfc_dep;
 	} activation_params;
 
 } __packed;
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 75d10e625c4..cfea60748a3 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -4,6 +4,7 @@
  *
  *  Copyright (C) 2011 Texas Instruments, Inc.
  *  Copyright (C) 2013 Intel Corporation. All rights reserved.
+ *  Copyright (C) 2014 Marvell International Ltd.
  *
  *  Written by Ilan Elias <ilane@ti.com>
  *
@@ -49,6 +50,8 @@ enum nci_state {
 	NCI_W4_ALL_DISCOVERIES,
 	NCI_W4_HOST_SELECT,
 	NCI_POLL_ACTIVE,
+	NCI_LISTEN_ACTIVE,
+	NCI_LISTEN_SLEEP,
 };
 
 /* NCI timeouts */
diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index 6c583e244de..12adb817c27 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -1,5 +1,6 @@
 /*
  * Copyright (C) 2011 Instituto Nokia de Tecnologia
+ * Copyright (C) 2014 Marvell International Ltd.
  *
  * Authors:
  *    Lauro Ramos Venancio <lauro.venancio@openbossa.org>
@@ -87,6 +88,7 @@ struct nfc_ops {
 #define NFC_TARGET_IDX_ANY -1
 #define NFC_MAX_GT_LEN 48
 #define NFC_ATR_RES_GT_OFFSET 15
+#define NFC_ATR_REQ_GT_OFFSET 14
 
 /**
  * struct nfc_target - NFC target descriptiom
diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h
index 9b19b446192..19a75daac14 100644
--- a/include/uapi/linux/nfc.h
+++ b/include/uapi/linux/nfc.h
@@ -196,15 +196,17 @@ enum nfc_sdp_attr {
 };
 #define NFC_SDP_ATTR_MAX (__NFC_SDP_ATTR_AFTER_LAST - 1)
 
-#define NFC_DEVICE_NAME_MAXSIZE 8
-#define NFC_NFCID1_MAXSIZE 10
-#define NFC_NFCID2_MAXSIZE 8
-#define NFC_NFCID3_MAXSIZE 10
-#define NFC_SENSB_RES_MAXSIZE 12
-#define NFC_SENSF_RES_MAXSIZE 18
-#define NFC_GB_MAXSIZE        48
-#define NFC_FIRMWARE_NAME_MAXSIZE 32
-#define NFC_ISO15693_UID_MAXSIZE 8
+#define NFC_DEVICE_NAME_MAXSIZE		8
+#define NFC_NFCID1_MAXSIZE		10
+#define NFC_NFCID2_MAXSIZE		8
+#define NFC_NFCID3_MAXSIZE		10
+#define NFC_SENSB_RES_MAXSIZE		12
+#define NFC_SENSF_RES_MAXSIZE		18
+#define NFC_ATR_REQ_MAXSIZE		64
+#define NFC_ATR_RES_MAXSIZE		64
+#define NFC_GB_MAXSIZE			48
+#define NFC_FIRMWARE_NAME_MAXSIZE	32
+#define NFC_ISO15693_UID_MAXSIZE	8
 
 /* NFC protocols */
 #define NFC_PROTO_JEWEL		1
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index 205b35f666d..46b2a90ac55 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -167,6 +167,18 @@ static __u8 *nci_extract_rf_params_nfcv_passive_poll(struct nci_dev *ndev,
 	return data;
 }
 
+static __u8 *nci_extract_rf_params_nfcf_passive_listen(struct nci_dev *ndev,
+			struct rf_tech_specific_params_nfcf_listen *nfcf_listen,
+						     __u8 *data)
+{
+	nfcf_listen->local_nfcid2_len = min_t(__u8, *data++,
+					      NFC_NFCID2_MAXSIZE);
+	memcpy(nfcf_listen->local_nfcid2, data, nfcf_listen->local_nfcid2_len);
+	data += nfcf_listen->local_nfcid2_len;
+
+	return data;
+}
+
 __u32 nci_get_prop_rf_protocol(struct nci_dev *ndev, __u8 rf_protocol)
 {
 	if (ndev->ops->get_rfprotocol)
@@ -401,17 +413,29 @@ static int nci_extract_activation_params_nfc_dep(struct nci_dev *ndev,
 			struct nci_rf_intf_activated_ntf *ntf, __u8 *data)
 {
 	struct activation_params_poll_nfc_dep *poll;
+	struct activation_params_listen_nfc_dep *listen;
 
 	switch (ntf->activation_rf_tech_and_mode) {
 	case NCI_NFC_A_PASSIVE_POLL_MODE:
 	case NCI_NFC_F_PASSIVE_POLL_MODE:
 		poll = &ntf->activation_params.poll_nfc_dep;
-		poll->atr_res_len = min_t(__u8, *data++, 63);
+		poll->atr_res_len = min_t(__u8, *data++,
+					  NFC_ATR_RES_MAXSIZE - 2);
 		pr_debug("atr_res_len %d\n", poll->atr_res_len);
 		if (poll->atr_res_len > 0)
 			memcpy(poll->atr_res, data, poll->atr_res_len);
 		break;
 
+	case NCI_NFC_A_PASSIVE_LISTEN_MODE:
+	case NCI_NFC_F_PASSIVE_LISTEN_MODE:
+		listen = &ntf->activation_params.listen_nfc_dep;
+		listen->atr_req_len = min_t(__u8, *data++,
+					    NFC_ATR_REQ_MAXSIZE - 2);
+		pr_debug("atr_req_len %d\n", listen->atr_req_len);
+		if (listen->atr_req_len > 0)
+			memcpy(listen->atr_req, data, listen->atr_req_len);
+		break;
+
 	default:
 		pr_err("unsupported activation_rf_tech_and_mode 0x%x\n",
 		       ntf->activation_rf_tech_and_mode);
@@ -444,6 +468,50 @@ static void nci_target_auto_activated(struct nci_dev *ndev,
 	nfc_targets_found(ndev->nfc_dev, ndev->targets, ndev->n_targets);
 }
 
+static int nci_store_general_bytes_nfc_dep(struct nci_dev *ndev,
+		struct nci_rf_intf_activated_ntf *ntf)
+{
+	ndev->remote_gb_len = 0;
+
+	if (ntf->activation_params_len <= 0)
+		return NCI_STATUS_OK;
+
+	switch (ntf->activation_rf_tech_and_mode) {
+	case NCI_NFC_A_PASSIVE_POLL_MODE:
+	case NCI_NFC_F_PASSIVE_POLL_MODE:
+		/* ATR_RES general bytes at offset 15 */
+		ndev->remote_gb_len = min_t(__u8,
+			(ntf->activation_params.poll_nfc_dep.atr_res_len
+						- NFC_ATR_RES_GT_OFFSET),
+			NFC_MAX_GT_LEN);
+		memcpy(ndev->remote_gb,
+		       (ntf->activation_params.poll_nfc_dep .atr_res
+						+ NFC_ATR_RES_GT_OFFSET),
+		       ndev->remote_gb_len);
+		break;
+
+	case NCI_NFC_A_PASSIVE_LISTEN_MODE:
+	case NCI_NFC_F_PASSIVE_LISTEN_MODE:
+		/* ATR_REQ general bytes at offset 14 */
+		ndev->remote_gb_len = min_t(__u8,
+			(ntf->activation_params.listen_nfc_dep.atr_req_len
+						- NFC_ATR_REQ_GT_OFFSET),
+			NFC_MAX_GT_LEN);
+		memcpy(ndev->remote_gb,
+		       (ntf->activation_params.listen_nfc_dep.atr_req
+						+ NFC_ATR_REQ_GT_OFFSET),
+		       ndev->remote_gb_len);
+		break;
+
+	default:
+		pr_err("unsupported activation_rf_tech_and_mode 0x%x\n",
+		       ntf->activation_rf_tech_and_mode);
+		return NCI_STATUS_RF_PROTOCOL_ERROR;
+	}
+
+	return NCI_STATUS_OK;
+}
+
 static void nci_rf_intf_activated_ntf_packet(struct nci_dev *ndev,
 					     struct sk_buff *skb)
 {
@@ -493,6 +561,16 @@ static void nci_rf_intf_activated_ntf_packet(struct nci_dev *ndev,
 				&(ntf.rf_tech_specific_params.nfcv_poll), data);
 			break;
 
+		case NCI_NFC_A_PASSIVE_LISTEN_MODE:
+			/* no RF technology specific parameters */
+			break;
+
+		case NCI_NFC_F_PASSIVE_LISTEN_MODE:
+			data = nci_extract_rf_params_nfcf_passive_listen(ndev,
+				&(ntf.rf_tech_specific_params.nfcf_listen),
+				data);
+			break;
+
 		default:
 			pr_err("unsupported activation_rf_tech_and_mode 0x%x\n",
 			       ntf.activation_rf_tech_and_mode);
@@ -546,32 +624,39 @@ exit:
 
 		/* store general bytes to be reported later in dep_link_up */
 		if (ntf.rf_interface == NCI_RF_INTERFACE_NFC_DEP) {
-			ndev->remote_gb_len = 0;
-
-			if (ntf.activation_params_len > 0) {
-				/* ATR_RES general bytes at offset 15 */
-				ndev->remote_gb_len = min_t(__u8,
-					(ntf.activation_params
-					.poll_nfc_dep.atr_res_len
-					- NFC_ATR_RES_GT_OFFSET),
-					NFC_MAX_GT_LEN);
-				memcpy(ndev->remote_gb,
-				       (ntf.activation_params.poll_nfc_dep
-				       .atr_res + NFC_ATR_RES_GT_OFFSET),
-				       ndev->remote_gb_len);
-			}
+			err = nci_store_general_bytes_nfc_dep(ndev, &ntf);
+			if (err != NCI_STATUS_OK)
+				pr_err("unable to store general bytes\n");
 		}
 	}
 
-	if (atomic_read(&ndev->state) == NCI_DISCOVERY) {
-		/* A single target was found and activated automatically */
-		atomic_set(&ndev->state, NCI_POLL_ACTIVE);
-		if (err == NCI_STATUS_OK)
-			nci_target_auto_activated(ndev, &ntf);
-	} else {	/* ndev->state == NCI_W4_HOST_SELECT */
-		/* A selected target was activated, so complete the request */
-		atomic_set(&ndev->state, NCI_POLL_ACTIVE);
-		nci_req_complete(ndev, err);
+	if (!(ntf.activation_rf_tech_and_mode & NCI_RF_TECH_MODE_LISTEN_MASK)) {
+		/* Poll mode */
+		if (atomic_read(&ndev->state) == NCI_DISCOVERY) {
+			/* A single target was found and activated
+			 * automatically */
+			atomic_set(&ndev->state, NCI_POLL_ACTIVE);
+			if (err == NCI_STATUS_OK)
+				nci_target_auto_activated(ndev, &ntf);
+		} else {	/* ndev->state == NCI_W4_HOST_SELECT */
+			/* A selected target was activated, so complete the
+			 * request */
+			atomic_set(&ndev->state, NCI_POLL_ACTIVE);
+			nci_req_complete(ndev, err);
+		}
+	} else {
+		/* Listen mode */
+		atomic_set(&ndev->state, NCI_LISTEN_ACTIVE);
+		if (err == NCI_STATUS_OK &&
+		    ntf.rf_protocol == NCI_RF_PROTOCOL_NFC_DEP) {
+			err = nfc_tm_activated(ndev->nfc_dev,
+					       NFC_PROTO_NFC_DEP_MASK,
+					       NFC_COMM_PASSIVE,
+					       ndev->remote_gb,
+					       ndev->remote_gb_len);
+			if (err != NCI_STATUS_OK)
+				pr_err("error when signaling tm activation\n");
+		}
 	}
 }
 
-- 
cgit v1.2.3-70-g09d2


From 529ee06682a5691eec25991c506357caf7341c93 Mon Sep 17 00:00:00 2001
From: Julien Lefrique <lefrique@marvell.com>
Date: Tue, 21 Oct 2014 16:52:47 +0200
Subject: NFC: NCI: Configure ATR_RES general bytes

The Target responds to the ATR_REQ with the ATR_RES. Configure the General
Bytes in ATR_RES with the first three octets equal to the NFC Forum LLCP
magic number, followed by some LLC Parameters TLVs described in section
4.5 of [LLCP].

Signed-off-by: Julien Lefrique <lefrique@marvell.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci.h |  1 +
 net/nfc/nci/core.c    | 10 +++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h
index fffadc706e0..e7257a4653b 100644
--- a/include/net/nfc/nci.h
+++ b/include/net/nfc/nci.h
@@ -110,6 +110,7 @@
 
 /* NCI Configuration Parameter Tags */
 #define NCI_PN_ATR_REQ_GEN_BYTES				0x29
+#define NCI_LN_ATR_RES_GEN_BYTES				0x61
 #define NCI_LA_SEL_INFO						0x32
 #define NCI_LF_PROTOCOL_TYPE					0x50
 #define NCI_LF_CON_BITR_F					0x54
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 61f92678a64..8f8bfdf145c 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -460,6 +460,7 @@ static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev)
 {
 	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
 	struct nci_set_config_param param;
+	int rc;
 
 	param.val = nfc_get_local_general_bytes(nfc_dev, &param.len);
 	if ((param.val == NULL) || (param.len == 0))
@@ -470,6 +471,13 @@ static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev)
 
 	param.id = NCI_PN_ATR_REQ_GEN_BYTES;
 
+	rc = nci_request(ndev, nci_set_config_req, (unsigned long)&param,
+			 msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT));
+	if (rc)
+		return rc;
+
+	param.id = NCI_LN_ATR_RES_GEN_BYTES;
+
 	return nci_request(ndev, nci_set_config_req, (unsigned long)&param,
 			   msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT));
 }
@@ -525,7 +533,7 @@ static int nci_start_poll(struct nfc_dev *nfc_dev,
 			return -EBUSY;
 	}
 
-	if (im_protocols & NFC_PROTO_NFC_DEP_MASK) {
+	if ((im_protocols | tm_protocols) & NFC_PROTO_NFC_DEP_MASK) {
 		rc = nci_set_local_general_bytes(nfc_dev);
 		if (rc) {
 			pr_err("failed to set local general bytes\n");
-- 
cgit v1.2.3-70-g09d2


From ad932f046fbe9839479350e7b88082a7d1dea498 Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Thu, 27 Nov 2014 09:44:55 +0200
Subject: cfg80211: leave invalid channels on regdomain change

When the regulatory settings change, some channels might become invalid.
Disconnect interfaces acting on these channels, after giving userspace
code a grace period to leave them.

This mode is currently opt-in, and not all interface operating modes are
supported for regulatory-enforcement checks. A wiphy that wishes to use
the new enforcement code must specify an appropriate regulatory flag,
and all its supported interface modes must be supported by the checking
code.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Reviewed-by: Luis R. Rodriguez <mcgrof@suse.com>
[fix some indentation, typos]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/regulatory.h |  12 ++++++
 net/wireless/core.c      |  14 +++++++
 net/wireless/reg.c       | 107 ++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 132 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/regulatory.h b/include/net/regulatory.h
index dad7ab20a8c..b776d72d84b 100644
--- a/include/net/regulatory.h
+++ b/include/net/regulatory.h
@@ -136,6 +136,17 @@ struct regulatory_request {
  *      otherwise initiating radiation is not allowed. This will enable the
  *      relaxations enabled under the CFG80211_REG_RELAX_NO_IR configuration
  *      option
+ * @REGULATORY_IGNORE_STALE_KICKOFF: the regulatory core will _not_ make sure
+ *	all interfaces on this wiphy reside on allowed channels. If this flag
+ *	is not set, upon a regdomain change, the interfaces are given a grace
+ *	period (currently 60 seconds) to disconnect or move to an allowed
+ *	channel. Interfaces on forbidden channels are forcibly disconnected.
+ *	Currently these types of interfaces are supported for enforcement:
+ *	NL80211_IFTYPE_ADHOC, NL80211_IFTYPE_STATION, NL80211_IFTYPE_AP,
+ *	NL80211_IFTYPE_AP_VLAN, NL80211_IFTYPE_MONITOR,
+ *	NL80211_IFTYPE_P2P_CLIENT, NL80211_IFTYPE_P2P_GO,
+ *	NL80211_IFTYPE_P2P_DEVICE. The flag will be set by default if a device
+ *	includes any modes unsupported for enforcement checking.
  */
 enum ieee80211_regulatory_flags {
 	REGULATORY_CUSTOM_REG			= BIT(0),
@@ -144,6 +155,7 @@ enum ieee80211_regulatory_flags {
 	REGULATORY_COUNTRY_IE_FOLLOW_POWER	= BIT(3),
 	REGULATORY_COUNTRY_IE_IGNORE		= BIT(4),
 	REGULATORY_ENABLE_RELAX_NO_IR           = BIT(5),
+	REGULATORY_IGNORE_STALE_KICKOFF         = BIT(6),
 };
 
 struct ieee80211_freq_range {
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 4c2e501203d..53dda7728f8 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -546,6 +546,20 @@ int wiphy_register(struct wiphy *wiphy)
 		     !rdev->ops->tdls_cancel_channel_switch)))
 		return -EINVAL;
 
+	/*
+	 * if a wiphy has unsupported modes for regulatory channel enforcement,
+	 * opt-out of enforcement checking
+	 */
+	if (wiphy->interface_modes & ~(BIT(NL80211_IFTYPE_STATION) |
+				       BIT(NL80211_IFTYPE_P2P_CLIENT) |
+				       BIT(NL80211_IFTYPE_AP) |
+				       BIT(NL80211_IFTYPE_P2P_GO) |
+				       BIT(NL80211_IFTYPE_ADHOC) |
+				       BIT(NL80211_IFTYPE_P2P_DEVICE) |
+				       BIT(NL80211_IFTYPE_AP_VLAN) |
+				       BIT(NL80211_IFTYPE_MONITOR)))
+		wiphy->regulatory_flags |= REGULATORY_IGNORE_STALE_KICKOFF;
+
 	if (WARN_ON(wiphy->coalesce &&
 		    (!wiphy->coalesce->n_rules ||
 		     !wiphy->coalesce->n_patterns) &&
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 32d8310b0f8..47be6163381 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -56,6 +56,7 @@
 #include <net/cfg80211.h>
 #include "core.h"
 #include "reg.h"
+#include "rdev-ops.h"
 #include "regdb.h"
 #include "nl80211.h"
 
@@ -66,6 +67,12 @@
 #define REG_DBG_PRINT(args...)
 #endif
 
+/*
+ * Grace period we give before making sure all current interfaces reside on
+ * channels allowed by the current regulatory domain.
+ */
+#define REG_ENFORCE_GRACE_MS 60000
+
 /**
  * enum reg_request_treatment - regulatory request treatment
  *
@@ -210,6 +217,9 @@ struct reg_beacon {
 	struct ieee80211_channel chan;
 };
 
+static void reg_check_chans_work(struct work_struct *work);
+static DECLARE_DELAYED_WORK(reg_check_chans, reg_check_chans_work);
+
 static void reg_todo(struct work_struct *work);
 static DECLARE_WORK(reg_work, reg_todo);
 
@@ -1518,6 +1528,96 @@ static void reg_call_notifier(struct wiphy *wiphy,
 		wiphy->reg_notifier(wiphy, request);
 }
 
+static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev)
+{
+	struct ieee80211_channel *ch;
+	struct cfg80211_chan_def chandef;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+	bool ret = true;
+
+	wdev_lock(wdev);
+
+	if (!wdev->netdev || !netif_running(wdev->netdev))
+		goto out;
+
+	switch (wdev->iftype) {
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_P2P_GO:
+		if (!wdev->beacon_interval)
+			goto out;
+
+		ret = cfg80211_reg_can_beacon(wiphy,
+					      &wdev->chandef, wdev->iftype);
+		break;
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_P2P_CLIENT:
+	case NL80211_IFTYPE_ADHOC:
+		if (!wdev->current_bss ||
+		    !wdev->current_bss->pub.channel)
+			goto out;
+
+		ch = wdev->current_bss->pub.channel;
+		if (rdev->ops->get_channel &&
+		    !rdev_get_channel(rdev, wdev, &chandef))
+			ret = cfg80211_chandef_usable(wiphy, &chandef,
+						      IEEE80211_CHAN_DISABLED);
+		else
+			ret = !(ch->flags & IEEE80211_CHAN_DISABLED);
+		break;
+	case NL80211_IFTYPE_MONITOR:
+	case NL80211_IFTYPE_AP_VLAN:
+	case NL80211_IFTYPE_P2P_DEVICE:
+		/* no enforcement required */
+		break;
+	default:
+		/* others not implemented for now */
+		WARN_ON(1);
+		break;
+	}
+
+out:
+	wdev_unlock(wdev);
+	return ret;
+}
+
+static void reg_leave_invalid_chans(struct wiphy *wiphy)
+{
+	struct wireless_dev *wdev;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+
+	ASSERT_RTNL();
+
+	list_for_each_entry(wdev, &rdev->wdev_list, list)
+		if (!reg_wdev_chan_valid(wiphy, wdev))
+			cfg80211_leave(rdev, wdev);
+}
+
+static void reg_check_chans_work(struct work_struct *work)
+{
+	struct cfg80211_registered_device *rdev;
+
+	REG_DBG_PRINT("Verifying active interfaces after reg change\n");
+	rtnl_lock();
+
+	list_for_each_entry(rdev, &cfg80211_rdev_list, list)
+		if (!(rdev->wiphy.regulatory_flags &
+		      REGULATORY_IGNORE_STALE_KICKOFF))
+			reg_leave_invalid_chans(&rdev->wiphy);
+
+	rtnl_unlock();
+}
+
+static void reg_check_channels(void)
+{
+	/*
+	 * Give usermode a chance to do something nicer (move to another
+	 * channel, orderly disconnection), before forcing a disconnection.
+	 */
+	mod_delayed_work(system_power_efficient_wq,
+			 &reg_check_chans,
+			 msecs_to_jiffies(REG_ENFORCE_GRACE_MS));
+}
+
 static void wiphy_update_regulatory(struct wiphy *wiphy,
 				    enum nl80211_reg_initiator initiator)
 {
@@ -1557,6 +1657,8 @@ static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator)
 		wiphy = &rdev->wiphy;
 		wiphy_update_regulatory(wiphy, initiator);
 	}
+
+	reg_check_channels();
 }
 
 static void handle_channel_custom(struct wiphy *wiphy,
@@ -1976,8 +2078,10 @@ static void reg_process_hint(struct regulatory_request *reg_request)
 
 	/* This is required so that the orig_* parameters are saved */
 	if (treatment == REG_REQ_ALREADY_SET && wiphy &&
-	    wiphy->regulatory_flags & REGULATORY_STRICT_REG)
+	    wiphy->regulatory_flags & REGULATORY_STRICT_REG) {
 		wiphy_update_regulatory(wiphy, reg_request->initiator);
+		reg_check_channels();
+	}
 
 	return;
 
@@ -2858,6 +2962,7 @@ void regulatory_exit(void)
 
 	cancel_work_sync(&reg_work);
 	cancel_delayed_work_sync(&reg_timeout);
+	cancel_delayed_work_sync(&reg_check_chans);
 
 	/* Lock to suppress warnings */
 	rtnl_lock();
-- 
cgit v1.2.3-70-g09d2


From 8e53b0f190af2954309bbad76a78177ead15d824 Mon Sep 17 00:00:00 2001
From: Alexandre Courbot <acourbot@nvidia.com>
Date: Tue, 25 Nov 2014 17:16:31 +0900
Subject: gpio: remove const modifier from gpiod_get_direction()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Although gpiod_get_direction() can be considered side-effect free for
consumers, its internals involve setting or clearing bits in the
affected GPIO descriptor, for which we need to force-cast the const
descriptor variable to non-const. This could lead to incorrect behavior
if the compiler decides to optimize here, so remove this const
attribute. The intent is to make gpiod_get_direction() private anyway,
so it does not really matter.

Reported-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib-sysfs.c  | 2 +-
 drivers/gpio/gpiolib.c        | 8 +++-----
 include/linux/gpio/consumer.h | 2 +-
 3 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c
index 781fbed00fc..2ac1800b58b 100644
--- a/drivers/gpio/gpiolib-sysfs.c
+++ b/drivers/gpio/gpiolib-sysfs.c
@@ -41,7 +41,7 @@ static DEFINE_MUTEX(sysfs_lock);
 static ssize_t gpio_direction_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	const struct gpio_desc	*desc = dev_get_drvdata(dev);
+	struct gpio_desc	*desc = dev_get_drvdata(dev);
 	ssize_t			status;
 
 	mutex_lock(&sysfs_lock);
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 5619922ebf4..0b271ef87c0 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -148,7 +148,7 @@ static int gpiochip_find_base(int ngpio)
  *
  * This function may sleep if gpiod_cansleep() is true.
  */
-int gpiod_get_direction(const struct gpio_desc *desc)
+int gpiod_get_direction(struct gpio_desc *desc)
 {
 	struct gpio_chip	*chip;
 	unsigned		offset;
@@ -164,13 +164,11 @@ int gpiod_get_direction(const struct gpio_desc *desc)
 	if (status > 0) {
 		/* GPIOF_DIR_IN, or other positive */
 		status = 1;
-		/* FLAG_IS_OUT is just a cache of the result of get_direction(),
-		 * so it does not affect constness per se */
-		clear_bit(FLAG_IS_OUT, &((struct gpio_desc *)desc)->flags);
+		clear_bit(FLAG_IS_OUT, &desc->flags);
 	}
 	if (status == 0) {
 		/* GPIOF_DIR_OUT */
-		set_bit(FLAG_IS_OUT, &((struct gpio_desc *)desc)->flags);
+		set_bit(FLAG_IS_OUT, &desc->flags);
 	}
 	return status;
 }
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 83c0a61c605..d54d158ca32 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -66,7 +66,7 @@ __devm_gpiod_get_index_optional(struct device *dev, const char *con_id,
 			      unsigned int index, enum gpiod_flags flags);
 void devm_gpiod_put(struct device *dev, struct gpio_desc *desc);
 
-int gpiod_get_direction(const struct gpio_desc *desc);
+int gpiod_get_direction(struct gpio_desc *desc);
 int gpiod_direction_input(struct gpio_desc *desc);
 int gpiod_direction_output(struct gpio_desc *desc, int value);
 int gpiod_direction_output_raw(struct gpio_desc *desc, int value);
-- 
cgit v1.2.3-70-g09d2


From f684565e0af43586bfc3e005d173f94b0f902a5d Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@openwrt.org>
Date: Wed, 19 Nov 2014 20:08:08 +0100
Subject: mac80211: add tx_status_noskb to rate_control_ops

This op works like .tx_status, except it does not need access to the
skb. This will be used by drivers that cannot match tx status
information to specific packets.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 4 ++++
 net/mac80211/rate.h    | 6 +++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 66cbfe46428..01dfd22e45f 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -4837,6 +4837,10 @@ struct rate_control_ops {
 	void (*free_sta)(void *priv, struct ieee80211_sta *sta,
 			 void *priv_sta);
 
+	void (*tx_status_noskb)(void *priv,
+				struct ieee80211_supported_band *sband,
+				struct ieee80211_sta *sta, void *priv_sta,
+				struct ieee80211_tx_info *info);
 	void (*tx_status)(void *priv, struct ieee80211_supported_band *sband,
 			  struct ieee80211_sta *sta, void *priv_sta,
 			  struct sk_buff *skb);
diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h
index 18babe30283..dd25964a300 100644
--- a/net/mac80211/rate.h
+++ b/net/mac80211/rate.h
@@ -37,11 +37,15 @@ static inline void rate_control_tx_status(struct ieee80211_local *local,
 	struct rate_control_ref *ref = local->rate_ctrl;
 	struct ieee80211_sta *ista = &sta->sta;
 	void *priv_sta = sta->rate_ctrl_priv;
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 
 	if (!ref || !test_sta_flag(sta, WLAN_STA_RATE_CONTROL))
 		return;
 
-	ref->ops->tx_status(ref->priv, sband, ista, priv_sta, skb);
+	if (ref->ops->tx_status)
+		ref->ops->tx_status(ref->priv, sband, ista, priv_sta, skb);
+	else
+		ref->ops->tx_status_noskb(ref->priv, sband, ista, priv_sta, info);
 }
 
 
-- 
cgit v1.2.3-70-g09d2


From f027c2aca0cf43e0f15fc8de8841f7b566163d94 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@openwrt.org>
Date: Wed, 19 Nov 2014 20:08:13 +0100
Subject: mac80211: add ieee80211_tx_status_noskb

This can be used by drivers that cannot reliably map tx status
information onto specific skbs.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 20 +++++++++++++++++++
 net/mac80211/rate.h    | 18 +++++++++++++++++
 net/mac80211/status.c  | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 92 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 01dfd22e45f..58d719ddaa6 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3618,6 +3618,26 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif,
 void ieee80211_tx_status(struct ieee80211_hw *hw,
 			 struct sk_buff *skb);
 
+/**
+ * ieee80211_tx_status_noskb - transmit status callback without skb
+ *
+ * This function can be used as a replacement for ieee80211_tx_status
+ * in drivers that cannot reliably map tx status information back to
+ * specific skbs.
+ *
+ * Calls to this function for a single hardware must be synchronized
+ * against each other. Calls to this function, ieee80211_tx_status_ni()
+ * and ieee80211_tx_status_irqsafe() may not be mixed for a single hardware.
+ *
+ * @hw: the hardware the frame was transmitted by
+ * @sta: the receiver station to which this packet is sent
+ *	(NULL for multicast packets)
+ * @info: tx status information
+ */
+void ieee80211_tx_status_noskb(struct ieee80211_hw *hw,
+			       struct ieee80211_sta *sta,
+			       struct ieee80211_tx_info *info);
+
 /**
  * ieee80211_tx_status_ni - transmit status callback (in process context)
  *
diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h
index dd25964a300..38652f09fea 100644
--- a/net/mac80211/rate.h
+++ b/net/mac80211/rate.h
@@ -48,6 +48,24 @@ static inline void rate_control_tx_status(struct ieee80211_local *local,
 		ref->ops->tx_status_noskb(ref->priv, sband, ista, priv_sta, info);
 }
 
+static inline void
+rate_control_tx_status_noskb(struct ieee80211_local *local,
+			     struct ieee80211_supported_band *sband,
+			     struct sta_info *sta,
+			     struct ieee80211_tx_info *info)
+{
+	struct rate_control_ref *ref = local->rate_ctrl;
+	struct ieee80211_sta *ista = &sta->sta;
+	void *priv_sta = sta->rate_ctrl_priv;
+
+	if (!ref || !test_sta_flag(sta, WLAN_STA_RATE_CONTROL))
+		return;
+
+	if (WARN_ON_ONCE(!ref->ops->tx_status_noskb))
+		return;
+
+	ref->ops->tx_status_noskb(ref->priv, sband, ista, priv_sta, info);
+}
 
 static inline void rate_control_rate_init(struct sta_info *sta)
 {
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index fee9c5ee51a..bb146f377ee 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -656,6 +656,60 @@ static int ieee80211_tx_get_rates(struct ieee80211_hw *hw,
 	return rates_idx;
 }
 
+void ieee80211_tx_status_noskb(struct ieee80211_hw *hw,
+			       struct ieee80211_sta *pubsta,
+			       struct ieee80211_tx_info *info)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
+	struct ieee80211_supported_band *sband;
+	int retry_count;
+	int rates_idx;
+	bool acked;
+
+	rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count);
+
+	sband = hw->wiphy->bands[info->band];
+
+	acked = !!(info->flags & IEEE80211_TX_STAT_ACK);
+	if (pubsta) {
+		struct sta_info *sta;
+
+		sta = container_of(pubsta, struct sta_info, sta);
+
+		if (!acked)
+			sta->tx_retry_failed++;
+		sta->tx_retry_count += retry_count;
+
+		if (acked) {
+			sta->last_rx = jiffies;
+
+			if (sta->lost_packets)
+				sta->lost_packets = 0;
+
+			/* Track when last TDLS packet was ACKed */
+			if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH))
+				sta->last_tdls_pkt_time = jiffies;
+		} else {
+			ieee80211_lost_packet(sta, info);
+		}
+
+		rate_control_tx_status_noskb(local, sband, sta, info);
+	}
+
+	if (acked) {
+		    local->dot11TransmittedFrameCount++;
+		    if (!pubsta)
+			    local->dot11MulticastTransmittedFrameCount++;
+		    if (retry_count > 0)
+			    local->dot11RetryCount++;
+		    if (retry_count > 1)
+			    local->dot11MultipleRetryCount++;
+	} else {
+		local->dot11FailedCount++;
+	}
+}
+EXPORT_SYMBOL(ieee80211_tx_status_noskb);
+
 void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct sk_buff *skb2;
-- 
cgit v1.2.3-70-g09d2


From 81cc3f868d30884c6f2d2bf5d1861fbeb24ddebd Mon Sep 17 00:00:00 2001
From: Pawel Moll <pawel.moll@arm.com>
Date: Tue, 25 Nov 2014 18:17:34 +0000
Subject: ARM: vexpress: Remove non-DT code

Now, with the CLCD DT support available, there is no
more reason to keep the non-DT support for V2P-CA9.

Removed, together with "some" supporting code. It was
necessary to make PLAT_VERSATILE_SCHED_CLOCK optional
and selected by the machines still interested in it.

Acked-by: Mike Turquette <mturquette@linaro.org>
Signed-off-by: Pawel Moll <pawel.moll@arm.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/Kconfig                                  |   2 +
 arch/arm/mach-vexpress/Kconfig                    |   3 -
 arch/arm/mach-vexpress/Makefile                   |   3 +-
 arch/arm/mach-vexpress/core.h                     |   7 -
 arch/arm/mach-vexpress/ct-ca9x4.c                 | 212 ------------
 arch/arm/mach-vexpress/include/mach/ct-ca9x4.h    |  47 ---
 arch/arm/mach-vexpress/include/mach/hardware.h    |   1 -
 arch/arm/mach-vexpress/include/mach/irqs.h        |   6 -
 arch/arm/mach-vexpress/include/mach/motherboard.h |  88 -----
 arch/arm/mach-vexpress/platsmp.c                  |  42 ---
 arch/arm/mach-vexpress/v2m.c                      | 374 ----------------------
 arch/arm/plat-versatile/Kconfig                   |   2 +-
 drivers/clk/versatile/Makefile                    |   1 -
 drivers/clk/versatile/clk-vexpress-osc.c          |   7 -
 drivers/clk/versatile/clk-vexpress.c              |  86 -----
 drivers/misc/vexpress-syscfg.c                    |  60 +---
 include/linux/vexpress.h                          |  19 --
 17 files changed, 17 insertions(+), 943 deletions(-)
 delete mode 100644 arch/arm/mach-vexpress/ct-ca9x4.c
 delete mode 100644 arch/arm/mach-vexpress/include/mach/ct-ca9x4.h
 delete mode 100644 arch/arm/mach-vexpress/include/mach/hardware.h
 delete mode 100644 arch/arm/mach-vexpress/include/mach/irqs.h
 delete mode 100644 arch/arm/mach-vexpress/include/mach/motherboard.h
 delete mode 100644 drivers/clk/versatile/clk-vexpress.c

(limited to 'include')

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 89c4b5ccc68..6c6fdb8a36e 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -350,6 +350,7 @@ config ARCH_REALVIEW
 	select ICST
 	select NEED_MACH_MEMORY_H
 	select PLAT_VERSATILE
+	select PLAT_VERSATILE_SCHED_CLOCK
 	help
 	  This enables support for ARM Ltd RealView boards.
 
@@ -365,6 +366,7 @@ config ARCH_VERSATILE
 	select ICST
 	select PLAT_VERSATILE
 	select PLAT_VERSATILE_CLOCK
+	select PLAT_VERSATILE_SCHED_CLOCK
 	select VERSATILE_FPGA_IRQ
 	help
 	  This enables support for ARM Ltd Versatile board.
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index b2cfba16c4e..9a96bab12ef 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -49,9 +49,6 @@ config ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA
 	  build a working kernel, you must also enable relevant core
 	  tile support or Flattened Device Tree based support options.
 
-config ARCH_VEXPRESS_CA9X4
-	bool "Versatile Express Cortex-A9x4 tile"
-
 config ARCH_VEXPRESS_DCSCB
 	bool "Dual Cluster System Control Block (DCSCB) support"
 	depends on MCPM
diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
index fc649bc09d0..f5c1006dd6a 100644
--- a/arch/arm/mach-vexpress/Makefile
+++ b/arch/arm/mach-vexpress/Makefile
@@ -1,11 +1,10 @@
 #
 # Makefile for the linux kernel.
 #
-ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
+ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := \
 	-I$(srctree)/arch/arm/plat-versatile/include
 
 obj-y					:= v2m.o
-obj-$(CONFIG_ARCH_VEXPRESS_CA9X4)	+= ct-ca9x4.o
 obj-$(CONFIG_ARCH_VEXPRESS_DCSCB)	+= dcscb.o	dcscb_setup.o
 CFLAGS_dcscb.o				+= -march=armv7-a
 CFLAGS_REMOVE_dcscb.o			= -pg
diff --git a/arch/arm/mach-vexpress/core.h b/arch/arm/mach-vexpress/core.h
index 152fad91b3a..2a11d3ac8c6 100644
--- a/arch/arm/mach-vexpress/core.h
+++ b/arch/arm/mach-vexpress/core.h
@@ -1,12 +1,5 @@
-/* 2MB large area for motherboard's peripherals static mapping */
-#define V2M_PERIPH 0xf8000000
-
-/* Tile's peripherals static mappings should start here */
-#define V2T_PERIPH 0xf8200000
-
 bool vexpress_smp_init_ops(void);
 
-extern struct smp_operations	vexpress_smp_ops;
 extern struct smp_operations	vexpress_smp_dt_ops;
 
 extern void vexpress_cpu_die(unsigned int cpu);
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
deleted file mode 100644
index 27bea049380..00000000000
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ /dev/null
@@ -1,212 +0,0 @@
-/*
- * Versatile Express Core Tile Cortex A9x4 Support
- */
-#include <linux/init.h>
-#include <linux/gfp.h>
-#include <linux/device.h>
-#include <linux/dma-mapping.h>
-#include <linux/platform_device.h>
-#include <linux/amba/bus.h>
-#include <linux/amba/clcd.h>
-#include <linux/platform_data/video-clcd-versatile.h>
-#include <linux/clkdev.h>
-#include <linux/vexpress.h>
-#include <linux/irqchip/arm-gic.h>
-
-#include <asm/hardware/arm_timer.h>
-#include <asm/hardware/cache-l2x0.h>
-#include <asm/smp_scu.h>
-#include <asm/smp_twd.h>
-
-#include <mach/ct-ca9x4.h>
-
-#include <asm/hardware/timer-sp.h>
-
-#include <asm/mach/map.h>
-#include <asm/mach/time.h>
-
-#include "core.h"
-
-#include <mach/motherboard.h>
-#include <mach/irqs.h>
-
-static struct map_desc ct_ca9x4_io_desc[] __initdata = {
-	{
-		.virtual        = V2T_PERIPH,
-		.pfn            = __phys_to_pfn(CT_CA9X4_MPIC),
-		.length         = SZ_8K,
-		.type           = MT_DEVICE,
-	},
-};
-
-static void __init ct_ca9x4_map_io(void)
-{
-	iotable_init(ct_ca9x4_io_desc, ARRAY_SIZE(ct_ca9x4_io_desc));
-}
-
-static void __init ca9x4_l2_init(void)
-{
-#ifdef CONFIG_CACHE_L2X0
-	void __iomem *l2x0_base = ioremap(CT_CA9X4_L2CC, SZ_4K);
-
-	if (l2x0_base) {
-		/* set RAM latencies to 1 cycle for this core tile. */
-		writel(0, l2x0_base + L310_TAG_LATENCY_CTRL);
-		writel(0, l2x0_base + L310_DATA_LATENCY_CTRL);
-
-		l2x0_init(l2x0_base, 0x00400000, 0xfe0fffff);
-	} else {
-		pr_err("L2C: unable to map L2 cache controller\n");
-	}
-#endif
-}
-
-#ifdef CONFIG_HAVE_ARM_TWD
-static DEFINE_TWD_LOCAL_TIMER(twd_local_timer, A9_MPCORE_TWD, IRQ_LOCALTIMER);
-
-static void __init ca9x4_twd_init(void)
-{
-	int err = twd_local_timer_register(&twd_local_timer);
-	if (err)
-		pr_err("twd_local_timer_register failed %d\n", err);
-}
-#else
-#define ca9x4_twd_init()	do {} while(0)
-#endif
-
-static void __init ct_ca9x4_init_irq(void)
-{
-	gic_init(0, 29, ioremap(A9_MPCORE_GIC_DIST, SZ_4K),
-		 ioremap(A9_MPCORE_GIC_CPU, SZ_256));
-	ca9x4_twd_init();
-	ca9x4_l2_init();
-}
-
-static int ct_ca9x4_clcd_setup(struct clcd_fb *fb)
-{
-	unsigned long framesize = 1024 * 768 * 2;
-
-	fb->panel = versatile_clcd_get_panel("XVGA");
-	if (!fb->panel)
-		return -EINVAL;
-
-	return versatile_clcd_setup_dma(fb, framesize);
-}
-
-static struct clcd_board ct_ca9x4_clcd_data = {
-	.name		= "CT-CA9X4",
-	.caps		= CLCD_CAP_5551 | CLCD_CAP_565,
-	.check		= clcdfb_check,
-	.decode		= clcdfb_decode,
-	.setup		= ct_ca9x4_clcd_setup,
-	.mmap		= versatile_clcd_mmap_dma,
-	.remove		= versatile_clcd_remove_dma,
-};
-
-static AMBA_AHB_DEVICE(clcd, "ct:clcd", 0, CT_CA9X4_CLCDC, IRQ_CT_CA9X4_CLCDC, &ct_ca9x4_clcd_data);
-static AMBA_APB_DEVICE(dmc, "ct:dmc", 0, CT_CA9X4_DMC, IRQ_CT_CA9X4_DMC, NULL);
-static AMBA_APB_DEVICE(smc, "ct:smc", 0, CT_CA9X4_SMC, IRQ_CT_CA9X4_SMC, NULL);
-static AMBA_APB_DEVICE(gpio, "ct:gpio", 0, CT_CA9X4_GPIO, IRQ_CT_CA9X4_GPIO, NULL);
-
-static struct amba_device *ct_ca9x4_amba_devs[] __initdata = {
-	&clcd_device,
-	&dmc_device,
-	&smc_device,
-	&gpio_device,
-};
-
-static struct resource pmu_resources[] = {
-	[0] = {
-		.start	= IRQ_CT_CA9X4_PMU_CPU0,
-		.end	= IRQ_CT_CA9X4_PMU_CPU0,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[1] = {
-		.start	= IRQ_CT_CA9X4_PMU_CPU1,
-		.end	= IRQ_CT_CA9X4_PMU_CPU1,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = {
-		.start	= IRQ_CT_CA9X4_PMU_CPU2,
-		.end	= IRQ_CT_CA9X4_PMU_CPU2,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[3] = {
-		.start	= IRQ_CT_CA9X4_PMU_CPU3,
-		.end	= IRQ_CT_CA9X4_PMU_CPU3,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device pmu_device = {
-	.name		= "arm-pmu",
-	.id		= -1,
-	.num_resources	= ARRAY_SIZE(pmu_resources),
-	.resource	= pmu_resources,
-};
-
-static struct clk_lookup osc1_lookup = {
-	.dev_id		= "ct:clcd",
-};
-
-static struct platform_device osc1_device = {
-	.name		= "vexpress-osc",
-	.id		= 1,
-	.num_resources	= 1,
-	.resource	= (struct resource []) {
-		VEXPRESS_RES_FUNC(0xf, 1),
-	},
-	.dev.platform_data = &osc1_lookup,
-};
-
-static void __init ct_ca9x4_init(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(ct_ca9x4_amba_devs); i++)
-		amba_device_register(ct_ca9x4_amba_devs[i], &iomem_resource);
-
-	platform_device_register(&pmu_device);
-	vexpress_syscfg_device_register(&osc1_device);
-}
-
-#ifdef CONFIG_SMP
-static void *ct_ca9x4_scu_base __initdata;
-
-static void __init ct_ca9x4_init_cpu_map(void)
-{
-	int i, ncores;
-
-	ct_ca9x4_scu_base = ioremap(A9_MPCORE_SCU, SZ_128);
-	if (WARN_ON(!ct_ca9x4_scu_base))
-		return;
-
-	ncores = scu_get_core_count(ct_ca9x4_scu_base);
-
-	if (ncores > nr_cpu_ids) {
-		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
-			ncores, nr_cpu_ids);
-		ncores = nr_cpu_ids;
-	}
-
-	for (i = 0; i < ncores; ++i)
-		set_cpu_possible(i, true);
-}
-
-static void __init ct_ca9x4_smp_enable(unsigned int max_cpus)
-{
-	scu_enable(ct_ca9x4_scu_base);
-}
-#endif
-
-struct ct_desc ct_ca9x4_desc __initdata = {
-	.id		= V2M_CT_ID_CA9,
-	.name		= "CA9x4",
-	.map_io		= ct_ca9x4_map_io,
-	.init_irq	= ct_ca9x4_init_irq,
-	.init_tile	= ct_ca9x4_init,
-#ifdef CONFIG_SMP
-	.init_cpu_map	= ct_ca9x4_init_cpu_map,
-	.smp_enable	= ct_ca9x4_smp_enable,
-#endif
-};
diff --git a/arch/arm/mach-vexpress/include/mach/ct-ca9x4.h b/arch/arm/mach-vexpress/include/mach/ct-ca9x4.h
deleted file mode 100644
index 84acf8439d4..00000000000
--- a/arch/arm/mach-vexpress/include/mach/ct-ca9x4.h
+++ /dev/null
@@ -1,47 +0,0 @@
-#ifndef __MACH_CT_CA9X4_H
-#define __MACH_CT_CA9X4_H
-
-/*
- * Physical base addresses
- */
-#define CT_CA9X4_CLCDC		(0x10020000)
-#define CT_CA9X4_AXIRAM		(0x10060000)
-#define CT_CA9X4_DMC		(0x100e0000)
-#define CT_CA9X4_SMC		(0x100e1000)
-#define CT_CA9X4_SCC		(0x100e2000)
-#define CT_CA9X4_SP804_TIMER	(0x100e4000)
-#define CT_CA9X4_SP805_WDT	(0x100e5000)
-#define CT_CA9X4_TZPC		(0x100e6000)
-#define CT_CA9X4_GPIO		(0x100e8000)
-#define CT_CA9X4_FASTAXI	(0x100e9000)
-#define CT_CA9X4_SLOWAXI	(0x100ea000)
-#define CT_CA9X4_TZASC		(0x100ec000)
-#define CT_CA9X4_CORESIGHT	(0x10200000)
-#define CT_CA9X4_MPIC		(0x1e000000)
-#define CT_CA9X4_SYSTIMER	(0x1e004000)
-#define CT_CA9X4_SYSWDT		(0x1e007000)
-#define CT_CA9X4_L2CC		(0x1e00a000)
-
-#define A9_MPCORE_SCU		(CT_CA9X4_MPIC + 0x0000)
-#define A9_MPCORE_GIC_CPU	(CT_CA9X4_MPIC + 0x0100)
-#define A9_MPCORE_GIT		(CT_CA9X4_MPIC + 0x0200)
-#define A9_MPCORE_TWD		(CT_CA9X4_MPIC + 0x0600)
-#define A9_MPCORE_GIC_DIST	(CT_CA9X4_MPIC + 0x1000)
-
-/*
- * Interrupts.  Those in {} are for AMBA devices
- */
-#define IRQ_CT_CA9X4_CLCDC	{ 76 }
-#define IRQ_CT_CA9X4_DMC	{ 0 }
-#define IRQ_CT_CA9X4_SMC	{ 77, 78 }
-#define IRQ_CT_CA9X4_TIMER0	80
-#define IRQ_CT_CA9X4_TIMER1	81
-#define IRQ_CT_CA9X4_GPIO	{ 82 }
-#define IRQ_CT_CA9X4_PMU_CPU0	92
-#define IRQ_CT_CA9X4_PMU_CPU1	93
-#define IRQ_CT_CA9X4_PMU_CPU2	94
-#define IRQ_CT_CA9X4_PMU_CPU3	95
-
-extern struct ct_desc ct_ca9x4_desc;
-
-#endif
diff --git a/arch/arm/mach-vexpress/include/mach/hardware.h b/arch/arm/mach-vexpress/include/mach/hardware.h
deleted file mode 100644
index 40a8c178f10..00000000000
--- a/arch/arm/mach-vexpress/include/mach/hardware.h
+++ /dev/null
@@ -1 +0,0 @@
-/* empty */
diff --git a/arch/arm/mach-vexpress/include/mach/irqs.h b/arch/arm/mach-vexpress/include/mach/irqs.h
deleted file mode 100644
index f8f7f782eb5..00000000000
--- a/arch/arm/mach-vexpress/include/mach/irqs.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#define IRQ_LOCALTIMER		29
-#define IRQ_LOCALWDOG		30
-
-#ifndef CONFIG_SPARSE_IRQ
-#define NR_IRQS	256
-#endif
diff --git a/arch/arm/mach-vexpress/include/mach/motherboard.h b/arch/arm/mach-vexpress/include/mach/motherboard.h
deleted file mode 100644
index 68abc8b7278..00000000000
--- a/arch/arm/mach-vexpress/include/mach/motherboard.h
+++ /dev/null
@@ -1,88 +0,0 @@
-#ifndef __MACH_MOTHERBOARD_H
-#define __MACH_MOTHERBOARD_H
-
-/*
- * Physical addresses, offset from V2M_PA_CS0-3
- */
-#define V2M_NOR0		(V2M_PA_CS0)
-#define V2M_NOR1		(V2M_PA_CS1)
-#define V2M_SRAM		(V2M_PA_CS2)
-#define V2M_VIDEO_SRAM		(V2M_PA_CS3 + 0x00000000)
-#define V2M_LAN9118		(V2M_PA_CS3 + 0x02000000)
-#define V2M_ISP1761		(V2M_PA_CS3 + 0x03000000)
-
-/*
- * Physical addresses, offset from V2M_PA_CS7
- */
-#define V2M_SYSREGS		(V2M_PA_CS7 + 0x00000000)
-#define V2M_SYSCTL		(V2M_PA_CS7 + 0x00001000)
-#define V2M_SERIAL_BUS_PCI	(V2M_PA_CS7 + 0x00002000)
-
-#define V2M_AACI		(V2M_PA_CS7 + 0x00004000)
-#define V2M_MMCI		(V2M_PA_CS7 + 0x00005000)
-#define V2M_KMI0		(V2M_PA_CS7 + 0x00006000)
-#define V2M_KMI1		(V2M_PA_CS7 + 0x00007000)
-
-#define V2M_UART0		(V2M_PA_CS7 + 0x00009000)
-#define V2M_UART1		(V2M_PA_CS7 + 0x0000a000)
-#define V2M_UART2		(V2M_PA_CS7 + 0x0000b000)
-#define V2M_UART3		(V2M_PA_CS7 + 0x0000c000)
-
-#define V2M_WDT			(V2M_PA_CS7 + 0x0000f000)
-
-#define V2M_TIMER01		(V2M_PA_CS7 + 0x00011000)
-#define V2M_TIMER23		(V2M_PA_CS7 + 0x00012000)
-
-#define V2M_SERIAL_BUS_DVI	(V2M_PA_CS7 + 0x00016000)
-#define V2M_RTC			(V2M_PA_CS7 + 0x00017000)
-
-#define V2M_CF			(V2M_PA_CS7 + 0x0001a000)
-#define V2M_CLCD		(V2M_PA_CS7 + 0x0001f000)
-
-
-/*
- * Interrupts.  Those in {} are for AMBA devices
- */
-#define IRQ_V2M_WDT		{ (32 + 0) }
-#define IRQ_V2M_TIMER0		(32 + 2)
-#define IRQ_V2M_TIMER1		(32 + 2)
-#define IRQ_V2M_TIMER2		(32 + 3)
-#define IRQ_V2M_TIMER3		(32 + 3)
-#define IRQ_V2M_RTC		{ (32 + 4) }
-#define IRQ_V2M_UART0		{ (32 + 5) }
-#define IRQ_V2M_UART1		{ (32 + 6) }
-#define IRQ_V2M_UART2		{ (32 + 7) }
-#define IRQ_V2M_UART3		{ (32 + 8) }
-#define IRQ_V2M_MMCI		{ (32 + 9), (32 + 10) }
-#define IRQ_V2M_AACI		{ (32 + 11) }
-#define IRQ_V2M_KMI0		{ (32 + 12) }
-#define IRQ_V2M_KMI1		{ (32 + 13) }
-#define IRQ_V2M_CLCD		{ (32 + 14) }
-#define IRQ_V2M_LAN9118		(32 + 15)
-#define IRQ_V2M_ISP1761		(32 + 16)
-#define IRQ_V2M_PCIE		(32 + 17)
-
-
-/*
- * Core tile IDs
- */
-#define V2M_CT_ID_CA9		0x0c000191
-#define V2M_CT_ID_UNSUPPORTED	0xff000191
-#define V2M_CT_ID_MASK		0xff000fff
-
-struct ct_desc {
-	u32			id;
-	const char		*name;
-	void			(*map_io)(void);
-	void			(*init_early)(void);
-	void			(*init_irq)(void);
-	void			(*init_tile)(void);
-#ifdef CONFIG_SMP
-	void			(*init_cpu_map)(void);
-	void			(*smp_enable)(unsigned int);
-#endif
-};
-
-extern struct ct_desc *ct_desc;
-
-#endif
diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c
index a1f3804fd5a..83188cf1875 100644
--- a/arch/arm/mach-vexpress/platsmp.c
+++ b/arch/arm/mach-vexpress/platsmp.c
@@ -19,48 +19,10 @@
 #include <asm/smp_scu.h>
 #include <asm/mach/map.h>
 
-#include <mach/motherboard.h>
-
 #include <plat/platsmp.h>
 
 #include "core.h"
 
-/*
- * Initialise the CPU possible map early - this describes the CPUs
- * which may be present or become present in the system.
- */
-static void __init vexpress_smp_init_cpus(void)
-{
-	ct_desc->init_cpu_map();
-}
-
-static void __init vexpress_smp_prepare_cpus(unsigned int max_cpus)
-{
-	/*
-	 * Initialise the present map, which describes the set of CPUs
-	 * actually populated at the present time.
-	 */
-	ct_desc->smp_enable(max_cpus);
-
-	/*
-	 * Write the address of secondary startup into the
-	 * system-wide flags register. The boot monitor waits
-	 * until it receives a soft interrupt, and then the
-	 * secondary CPU branches to this address.
-	 */
-	vexpress_flags_set(virt_to_phys(versatile_secondary_startup));
-}
-
-struct smp_operations __initdata vexpress_smp_ops = {
-	.smp_init_cpus		= vexpress_smp_init_cpus,
-	.smp_prepare_cpus	= vexpress_smp_prepare_cpus,
-	.smp_secondary_init	= versatile_secondary_init,
-	.smp_boot_secondary	= versatile_boot_secondary,
-#ifdef CONFIG_HOTPLUG_CPU
-	.cpu_die		= vexpress_cpu_die,
-#endif
-};
-
 bool __init vexpress_smp_init_ops(void)
 {
 #ifdef CONFIG_MCPM
@@ -79,8 +41,6 @@ bool __init vexpress_smp_init_ops(void)
 	return false;
 }
 
-#if defined(CONFIG_OF)
-
 static const struct of_device_id vexpress_smp_dt_scu_match[] __initconst = {
 	{ .compatible = "arm,cortex-a5-scu", },
 	{ .compatible = "arm,cortex-a9-scu", },
@@ -112,5 +72,3 @@ struct smp_operations __initdata vexpress_smp_dt_ops = {
 	.cpu_die		= vexpress_cpu_die,
 #endif
 };
-
-#endif
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 6ff681a24ba..a0400f4cca8 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -1,380 +1,7 @@
-/*
- * Versatile Express V2M Motherboard Support
- */
-#include <linux/device.h>
-#include <linux/amba/bus.h>
-#include <linux/amba/mmci.h>
-#include <linux/io.h>
-#include <linux/smp.h>
-#include <linux/init.h>
-#include <linux/of_address.h>
-#include <linux/of_fdt.h>
-#include <linux/of_irq.h>
-#include <linux/of_platform.h>
-#include <linux/platform_device.h>
-#include <linux/ata_platform.h>
-#include <linux/smsc911x.h>
-#include <linux/spinlock.h>
-#include <linux/usb/isp1760.h>
-#include <linux/mtd/physmap.h>
-#include <linux/regulator/fixed.h>
-#include <linux/regulator/machine.h>
-#include <linux/vexpress.h>
-#include <linux/clkdev.h>
-
-#include <asm/mach-types.h>
-#include <asm/sizes.h>
 #include <asm/mach/arch.h>
-#include <asm/mach/map.h>
-#include <asm/mach/time.h>
-#include <asm/hardware/arm_timer.h>
-#include <asm/hardware/cache-l2x0.h>
-#include <asm/hardware/timer-sp.h>
-
-#include <mach/ct-ca9x4.h>
-#include <mach/motherboard.h>
-
-#include <plat/sched_clock.h>
-#include <plat/platsmp.h>
 
 #include "core.h"
 
-#define V2M_PA_CS0	0x40000000
-#define V2M_PA_CS1	0x44000000
-#define V2M_PA_CS2	0x48000000
-#define V2M_PA_CS3	0x4c000000
-#define V2M_PA_CS7	0x10000000
-
-static struct map_desc v2m_io_desc[] __initdata = {
-	{
-		.virtual	= V2M_PERIPH,
-		.pfn		= __phys_to_pfn(V2M_PA_CS7),
-		.length		= SZ_128K,
-		.type		= MT_DEVICE,
-	},
-};
-
-static void __init v2m_sp804_init(void __iomem *base, unsigned int irq)
-{
-	if (WARN_ON(!base || irq == NO_IRQ))
-		return;
-
-	sp804_clocksource_init(base + TIMER_2_BASE, "v2m-timer1");
-	sp804_clockevents_init(base + TIMER_1_BASE, irq, "v2m-timer0");
-}
-
-
-static struct resource v2m_pcie_i2c_resource = {
-	.start	= V2M_SERIAL_BUS_PCI,
-	.end	= V2M_SERIAL_BUS_PCI + SZ_4K - 1,
-	.flags	= IORESOURCE_MEM,
-};
-
-static struct platform_device v2m_pcie_i2c_device = {
-	.name		= "versatile-i2c",
-	.id		= 0,
-	.num_resources	= 1,
-	.resource	= &v2m_pcie_i2c_resource,
-};
-
-static struct resource v2m_ddc_i2c_resource = {
-	.start	= V2M_SERIAL_BUS_DVI,
-	.end	= V2M_SERIAL_BUS_DVI + SZ_4K - 1,
-	.flags	= IORESOURCE_MEM,
-};
-
-static struct platform_device v2m_ddc_i2c_device = {
-	.name		= "versatile-i2c",
-	.id		= 1,
-	.num_resources	= 1,
-	.resource	= &v2m_ddc_i2c_resource,
-};
-
-static struct resource v2m_eth_resources[] = {
-	{
-		.start	= V2M_LAN9118,
-		.end	= V2M_LAN9118 + SZ_64K - 1,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= IRQ_V2M_LAN9118,
-		.end	= IRQ_V2M_LAN9118,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct smsc911x_platform_config v2m_eth_config = {
-	.flags		= SMSC911X_USE_32BIT,
-	.irq_polarity	= SMSC911X_IRQ_POLARITY_ACTIVE_HIGH,
-	.irq_type	= SMSC911X_IRQ_TYPE_PUSH_PULL,
-	.phy_interface	= PHY_INTERFACE_MODE_MII,
-};
-
-static struct platform_device v2m_eth_device = {
-	.name		= "smsc911x",
-	.id		= -1,
-	.resource	= v2m_eth_resources,
-	.num_resources	= ARRAY_SIZE(v2m_eth_resources),
-	.dev.platform_data = &v2m_eth_config,
-};
-
-static struct regulator_consumer_supply v2m_eth_supplies[] = {
-	REGULATOR_SUPPLY("vddvario", "smsc911x"),
-	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
-};
-
-static struct resource v2m_usb_resources[] = {
-	{
-		.start	= V2M_ISP1761,
-		.end	= V2M_ISP1761 + SZ_128K - 1,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= IRQ_V2M_ISP1761,
-		.end	= IRQ_V2M_ISP1761,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct isp1760_platform_data v2m_usb_config = {
-	.is_isp1761		= true,
-	.bus_width_16		= false,
-	.port1_otg		= true,
-	.analog_oc		= false,
-	.dack_polarity_high	= false,
-	.dreq_polarity_high	= false,
-};
-
-static struct platform_device v2m_usb_device = {
-	.name		= "isp1760",
-	.id		= -1,
-	.resource	= v2m_usb_resources,
-	.num_resources	= ARRAY_SIZE(v2m_usb_resources),
-	.dev.platform_data = &v2m_usb_config,
-};
-
-static struct physmap_flash_data v2m_flash_data = {
-	.width		= 4,
-};
-
-static struct resource v2m_flash_resources[] = {
-	{
-		.start	= V2M_NOR0,
-		.end	= V2M_NOR0 + SZ_64M - 1,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= V2M_NOR1,
-		.end	= V2M_NOR1 + SZ_64M - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device v2m_flash_device = {
-	.name		= "physmap-flash",
-	.id		= -1,
-	.resource	= v2m_flash_resources,
-	.num_resources	= ARRAY_SIZE(v2m_flash_resources),
-	.dev.platform_data = &v2m_flash_data,
-};
-
-static struct pata_platform_info v2m_pata_data = {
-	.ioport_shift	= 2,
-};
-
-static struct resource v2m_pata_resources[] = {
-	{
-		.start	= V2M_CF,
-		.end	= V2M_CF + 0xff,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= V2M_CF + 0x100,
-		.end	= V2M_CF + SZ_4K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device v2m_cf_device = {
-	.name		= "pata_platform",
-	.id		= -1,
-	.resource	= v2m_pata_resources,
-	.num_resources	= ARRAY_SIZE(v2m_pata_resources),
-	.dev.platform_data = &v2m_pata_data,
-};
-
-static struct mmci_platform_data v2m_mmci_data = {
-	.ocr_mask	= MMC_VDD_32_33|MMC_VDD_33_34,
-	.status		= vexpress_get_mci_cardin,
-	.gpio_cd	= -1,
-	.gpio_wp	= -1,
-};
-
-static struct resource v2m_sysreg_resources[] = {
-	{
-		.start	= V2M_SYSREGS,
-		.end	= V2M_SYSREGS + 0xfff,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device v2m_sysreg_device = {
-	.name		= "vexpress-sysreg",
-	.id		= -1,
-	.resource	= v2m_sysreg_resources,
-	.num_resources	= ARRAY_SIZE(v2m_sysreg_resources),
-};
-
-static struct platform_device v2m_muxfpga_device = {
-	.name		= "vexpress-muxfpga",
-	.id		= 0,
-	.num_resources	= 1,
-	.resource	= (struct resource []) {
-		VEXPRESS_RES_FUNC(0, 7),
-	}
-};
-
-static struct platform_device v2m_shutdown_device = {
-	.name		= "vexpress-shutdown",
-	.id		= 0,
-	.num_resources	= 1,
-	.resource	= (struct resource []) {
-		VEXPRESS_RES_FUNC(0, 8),
-	}
-};
-
-static struct platform_device v2m_reboot_device = {
-	.name		= "vexpress-reboot",
-	.id		= 0,
-	.num_resources	= 1,
-	.resource	= (struct resource []) {
-		VEXPRESS_RES_FUNC(0, 9),
-	}
-};
-
-static struct platform_device v2m_dvimode_device = {
-	.name		= "vexpress-dvimode",
-	.id		= 0,
-	.num_resources	= 1,
-	.resource	= (struct resource []) {
-		VEXPRESS_RES_FUNC(0, 11),
-	}
-};
-
-static AMBA_APB_DEVICE(aaci,  "mb:aaci",  0, V2M_AACI, IRQ_V2M_AACI, NULL);
-static AMBA_APB_DEVICE(mmci,  "mb:mmci",  0, V2M_MMCI, IRQ_V2M_MMCI, &v2m_mmci_data);
-static AMBA_APB_DEVICE(kmi0,  "mb:kmi0",  0, V2M_KMI0, IRQ_V2M_KMI0, NULL);
-static AMBA_APB_DEVICE(kmi1,  "mb:kmi1",  0, V2M_KMI1, IRQ_V2M_KMI1, NULL);
-static AMBA_APB_DEVICE(uart0, "mb:uart0", 0, V2M_UART0, IRQ_V2M_UART0, NULL);
-static AMBA_APB_DEVICE(uart1, "mb:uart1", 0, V2M_UART1, IRQ_V2M_UART1, NULL);
-static AMBA_APB_DEVICE(uart2, "mb:uart2", 0, V2M_UART2, IRQ_V2M_UART2, NULL);
-static AMBA_APB_DEVICE(uart3, "mb:uart3", 0, V2M_UART3, IRQ_V2M_UART3, NULL);
-static AMBA_APB_DEVICE(wdt,   "mb:wdt",   0, V2M_WDT, IRQ_V2M_WDT, NULL);
-static AMBA_APB_DEVICE(rtc,   "mb:rtc",   0, V2M_RTC, IRQ_V2M_RTC, NULL);
-
-static struct amba_device *v2m_amba_devs[] __initdata = {
-	&aaci_device,
-	&mmci_device,
-	&kmi0_device,
-	&kmi1_device,
-	&uart0_device,
-	&uart1_device,
-	&uart2_device,
-	&uart3_device,
-	&wdt_device,
-	&rtc_device,
-};
-
-static void __init v2m_timer_init(void)
-{
-	vexpress_clk_init(ioremap(V2M_SYSCTL, SZ_4K));
-	v2m_sp804_init(ioremap(V2M_TIMER01, SZ_4K), IRQ_V2M_TIMER0);
-}
-
-static void __init v2m_init_early(void)
-{
-	if (ct_desc->init_early)
-		ct_desc->init_early();
-	versatile_sched_clock_init(vexpress_get_24mhz_clock_base(), 24000000);
-}
-
-struct ct_desc *ct_desc;
-
-static struct ct_desc *ct_descs[] __initdata = {
-#ifdef CONFIG_ARCH_VEXPRESS_CA9X4
-	&ct_ca9x4_desc,
-#endif
-};
-
-static void __init v2m_populate_ct_desc(void)
-{
-	int i;
-	u32 current_tile_id;
-
-	ct_desc = NULL;
-	current_tile_id = vexpress_get_procid(VEXPRESS_SITE_MASTER)
-				& V2M_CT_ID_MASK;
-
-	for (i = 0; i < ARRAY_SIZE(ct_descs) && !ct_desc; ++i)
-		if (ct_descs[i]->id == current_tile_id)
-			ct_desc = ct_descs[i];
-
-	if (!ct_desc)
-		panic("vexpress: this kernel does not support core tile ID 0x%08x when booting via ATAGs.\n"
-		      "You may need a device tree blob or a different kernel to boot on this board.\n",
-		      current_tile_id);
-}
-
-static void __init v2m_map_io(void)
-{
-	iotable_init(v2m_io_desc, ARRAY_SIZE(v2m_io_desc));
-	vexpress_sysreg_early_init(ioremap(V2M_SYSREGS, SZ_4K));
-	v2m_populate_ct_desc();
-	ct_desc->map_io();
-}
-
-static void __init v2m_init_irq(void)
-{
-	ct_desc->init_irq();
-}
-
-static void __init v2m_init(void)
-{
-	int i;
-
-	regulator_register_fixed(0, v2m_eth_supplies,
-			ARRAY_SIZE(v2m_eth_supplies));
-
-	platform_device_register(&v2m_sysreg_device);
-	platform_device_register(&v2m_pcie_i2c_device);
-	platform_device_register(&v2m_ddc_i2c_device);
-	platform_device_register(&v2m_flash_device);
-	platform_device_register(&v2m_cf_device);
-	platform_device_register(&v2m_eth_device);
-	platform_device_register(&v2m_usb_device);
-
-	for (i = 0; i < ARRAY_SIZE(v2m_amba_devs); i++)
-		amba_device_register(v2m_amba_devs[i], &iomem_resource);
-
-	vexpress_syscfg_device_register(&v2m_muxfpga_device);
-	vexpress_syscfg_device_register(&v2m_shutdown_device);
-	vexpress_syscfg_device_register(&v2m_reboot_device);
-	vexpress_syscfg_device_register(&v2m_dvimode_device);
-
-	ct_desc->init_tile();
-}
-
-MACHINE_START(VEXPRESS, "ARM-Versatile Express")
-	.atag_offset	= 0x100,
-	.smp		= smp_ops(vexpress_smp_ops),
-	.map_io		= v2m_map_io,
-	.init_early	= v2m_init_early,
-	.init_irq	= v2m_init_irq,
-	.init_time	= v2m_timer_init,
-	.init_machine	= v2m_init,
-MACHINE_END
-
-static void __init v2m_dt_init(void)
-{
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-}
-
 static const char * const v2m_dt_match[] __initconst = {
 	"arm,vexpress",
 	NULL,
@@ -386,5 +13,4 @@ DT_MACHINE_START(VEXPRESS_DT, "ARM-Versatile Express")
 	.l2c_aux_mask	= 0xfe0fffff,
 	.smp		= smp_ops(vexpress_smp_dt_ops),
 	.smp_init	= smp_init_ops(vexpress_smp_init_ops),
-	.init_machine	= v2m_dt_init,
 MACHINE_END
diff --git a/arch/arm/plat-versatile/Kconfig b/arch/arm/plat-versatile/Kconfig
index a301ca2c7d0..49b8ef91584 100644
--- a/arch/arm/plat-versatile/Kconfig
+++ b/arch/arm/plat-versatile/Kconfig
@@ -4,6 +4,6 @@ config PLAT_VERSATILE_CLOCK
 	bool
 
 config PLAT_VERSATILE_SCHED_CLOCK
-	def_bool y
+	bool
 
 endif
diff --git a/drivers/clk/versatile/Makefile b/drivers/clk/versatile/Makefile
index 162e519cb0f..8ff03744fe9 100644
--- a/drivers/clk/versatile/Makefile
+++ b/drivers/clk/versatile/Makefile
@@ -2,6 +2,5 @@
 obj-$(CONFIG_ICST)		+= clk-icst.o clk-versatile.o
 obj-$(CONFIG_INTEGRATOR_IMPD1)	+= clk-impd1.o
 obj-$(CONFIG_ARCH_REALVIEW)	+= clk-realview.o
-obj-$(CONFIG_ARCH_VEXPRESS)	+= clk-vexpress.o
 obj-$(CONFIG_CLK_SP810)		+= clk-sp810.o
 obj-$(CONFIG_CLK_VEXPRESS_OSC)	+= clk-vexpress-osc.o
diff --git a/drivers/clk/versatile/clk-vexpress-osc.c b/drivers/clk/versatile/clk-vexpress-osc.c
index 529a59c0fbf..765f1e0eeeb 100644
--- a/drivers/clk/versatile/clk-vexpress-osc.c
+++ b/drivers/clk/versatile/clk-vexpress-osc.c
@@ -70,7 +70,6 @@ static struct clk_ops vexpress_osc_ops = {
 
 static int vexpress_osc_probe(struct platform_device *pdev)
 {
-	struct clk_lookup *cl = pdev->dev.platform_data; /* Non-DT lookup */
 	struct clk_init_data init;
 	struct vexpress_osc *osc;
 	struct clk *clk;
@@ -106,12 +105,6 @@ static int vexpress_osc_probe(struct platform_device *pdev)
 
 	of_clk_add_provider(pdev->dev.of_node, of_clk_src_simple_get, clk);
 
-	/* Only happens for non-DT cases */
-	if (cl) {
-		cl->clk = clk;
-		clkdev_add(cl);
-	}
-
 	dev_dbg(&pdev->dev, "Registered clock '%s'\n", init.name);
 
 	return 0;
diff --git a/drivers/clk/versatile/clk-vexpress.c b/drivers/clk/versatile/clk-vexpress.c
deleted file mode 100644
index 2d5e1b4820e..00000000000
--- a/drivers/clk/versatile/clk-vexpress.c
+++ /dev/null
@@ -1,86 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * Copyright (C) 2012 ARM Limited
- */
-
-#include <linux/amba/sp810.h>
-#include <linux/clkdev.h>
-#include <linux/clk-provider.h>
-#include <linux/err.h>
-#include <linux/vexpress.h>
-
-static struct clk *vexpress_sp810_timerclken[4];
-static DEFINE_SPINLOCK(vexpress_sp810_lock);
-
-static void __init vexpress_sp810_init(void __iomem *base)
-{
-	int i;
-
-	if (WARN_ON(!base))
-		return;
-
-	for (i = 0; i < ARRAY_SIZE(vexpress_sp810_timerclken); i++) {
-		char name[12];
-		const char *parents[] = {
-			"v2m:refclk32khz", /* REFCLK */
-			"v2m:refclk1mhz" /* TIMCLK */
-		};
-
-		snprintf(name, ARRAY_SIZE(name), "timerclken%d", i);
-
-		vexpress_sp810_timerclken[i] = clk_register_mux(NULL, name,
-				parents, 2, CLK_SET_RATE_NO_REPARENT,
-				base + SCCTRL, SCCTRL_TIMERENnSEL_SHIFT(i), 1,
-				0, &vexpress_sp810_lock);
-
-		if (WARN_ON(IS_ERR(vexpress_sp810_timerclken[i])))
-			break;
-	}
-}
-
-
-static const char * const vexpress_clk_24mhz_periphs[] __initconst = {
-	"mb:uart0", "mb:uart1", "mb:uart2", "mb:uart3",
-	"mb:mmci", "mb:kmi0", "mb:kmi1"
-};
-
-void __init vexpress_clk_init(void __iomem *sp810_base)
-{
-	struct clk *clk;
-	int i;
-
-	clk = clk_register_fixed_rate(NULL, "dummy_apb_pclk", NULL,
-			CLK_IS_ROOT, 0);
-	WARN_ON(clk_register_clkdev(clk, "apb_pclk", NULL));
-
-	clk = clk_register_fixed_rate(NULL, "v2m:clk_24mhz", NULL,
-			CLK_IS_ROOT, 24000000);
-	for (i = 0; i < ARRAY_SIZE(vexpress_clk_24mhz_periphs); i++)
-		WARN_ON(clk_register_clkdev(clk, NULL,
-				vexpress_clk_24mhz_periphs[i]));
-
-	clk = clk_register_fixed_rate(NULL, "v2m:refclk32khz", NULL,
-			CLK_IS_ROOT, 32768);
-	WARN_ON(clk_register_clkdev(clk, NULL, "v2m:wdt"));
-
-	clk = clk_register_fixed_rate(NULL, "v2m:refclk1mhz", NULL,
-			CLK_IS_ROOT, 1000000);
-
-	vexpress_sp810_init(sp810_base);
-
-	for (i = 0; i < ARRAY_SIZE(vexpress_sp810_timerclken); i++)
-		WARN_ON(clk_set_parent(vexpress_sp810_timerclken[i], clk));
-
-	WARN_ON(clk_register_clkdev(vexpress_sp810_timerclken[0],
-				"v2m-timer0", "sp804"));
-	WARN_ON(clk_register_clkdev(vexpress_sp810_timerclken[1],
-				"v2m-timer1", "sp804"));
-}
diff --git a/drivers/misc/vexpress-syscfg.c b/drivers/misc/vexpress-syscfg.c
index b3a812384a6..c344483fa7d 100644
--- a/drivers/misc/vexpress-syscfg.c
+++ b/drivers/misc/vexpress-syscfg.c
@@ -145,7 +145,7 @@ static struct regmap_config vexpress_syscfg_regmap_config = {
 static struct regmap *vexpress_syscfg_regmap_init(struct device *dev,
 		void *context)
 {
-	struct platform_device *pdev = to_platform_device(dev);
+	int err;
 	struct vexpress_syscfg *syscfg = context;
 	struct vexpress_syscfg_func *func;
 	struct property *prop;
@@ -155,32 +155,18 @@ static struct regmap *vexpress_syscfg_regmap_init(struct device *dev,
 	u32 site, position, dcc;
 	int i;
 
-	if (dev->of_node) {
-		int err = vexpress_config_get_topo(dev->of_node, &site,
+	err = vexpress_config_get_topo(dev->of_node, &site,
 				&position, &dcc);
+	if (err)
+		return ERR_PTR(err);
 
-		if (err)
-			return ERR_PTR(err);
-
-		prop = of_find_property(dev->of_node,
-				"arm,vexpress-sysreg,func", NULL);
-		if (!prop)
-			return ERR_PTR(-EINVAL);
-
-		num = prop->length / sizeof(u32) / 2;
-		val = prop->value;
-	} else {
-		if (pdev->num_resources != 1 ||
-				pdev->resource[0].flags != IORESOURCE_BUS)
-			return ERR_PTR(-EFAULT);
-
-		site = pdev->resource[0].start;
-		if (site == VEXPRESS_SITE_MASTER)
-			site = vexpress_config_get_master();
-		position = 0;
-		dcc = 0;
-		num = 1;
-	}
+	prop = of_find_property(dev->of_node,
+			"arm,vexpress-sysreg,func", NULL);
+	if (!prop)
+		return ERR_PTR(-EINVAL);
+
+	num = prop->length / sizeof(u32) / 2;
+	val = prop->value;
 
 	/*
 	 * "arm,vexpress-energy" function used to be described
@@ -207,13 +193,8 @@ static struct regmap *vexpress_syscfg_regmap_init(struct device *dev,
 	for (i = 0; i < num; i++) {
 		u32 function, device;
 
-		if (dev->of_node) {
-			function = be32_to_cpup(val++);
-			device = be32_to_cpup(val++);
-		} else {
-			function = pdev->resource[0].end;
-			device = pdev->id;
-		}
+		function = be32_to_cpup(val++);
+		device = be32_to_cpup(val++);
 
 		dev_dbg(dev, "func %p: %u/%u/%u/%u/%u\n",
 				func, site, position, dcc,
@@ -265,17 +246,6 @@ static struct vexpress_config_bridge_ops vexpress_syscfg_bridge_ops = {
 };
 
 
-/* Non-DT hack, to be gone... */
-static struct device *vexpress_syscfg_bridge;
-
-int vexpress_syscfg_device_register(struct platform_device *pdev)
-{
-	pdev->dev.parent = vexpress_syscfg_bridge;
-
-	return platform_device_register(pdev);
-}
-
-
 static int vexpress_syscfg_probe(struct platform_device *pdev)
 {
 	struct vexpress_syscfg *syscfg;
@@ -303,10 +273,6 @@ static int vexpress_syscfg_probe(struct platform_device *pdev)
 	if (IS_ERR(bridge))
 		return PTR_ERR(bridge);
 
-	/* Non-DT case */
-	if (!pdev->dev.of_node)
-		vexpress_syscfg_bridge = bridge;
-
 	return 0;
 }
 
diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h
index a4c9547aae6..f8e76e08ebe 100644
--- a/include/linux/vexpress.h
+++ b/include/linux/vexpress.h
@@ -15,8 +15,6 @@
 #define _LINUX_VEXPRESS_H
 
 #include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/reboot.h>
 #include <linux/regmap.h>
 
 #define VEXPRESS_SITE_MB		0
@@ -24,13 +22,6 @@
 #define VEXPRESS_SITE_DB2		2
 #define VEXPRESS_SITE_MASTER		0xf
 
-#define VEXPRESS_RES_FUNC(_site, _func)	\
-{					\
-	.start = (_site),		\
-	.end = (_func),			\
-	.flags = IORESOURCE_BUS,	\
-}
-
 /* Config infrastructure */
 
 void vexpress_config_set_master(u32 site);
@@ -58,16 +49,6 @@ struct regmap *devm_regmap_init_vexpress_config(struct device *dev);
 
 /* Platform control */
 
-unsigned int vexpress_get_mci_cardin(struct device *dev);
-u32 vexpress_get_procid(int site);
-void *vexpress_get_24mhz_clock_base(void);
 void vexpress_flags_set(u32 data);
 
-void vexpress_sysreg_early_init(void __iomem *base);
-int vexpress_syscfg_device_register(struct platform_device *pdev);
-
-/* Clocks */
-
-void vexpress_clk_init(void __iomem *sp810_base);
-
 #endif
-- 
cgit v1.2.3-70-g09d2


From df870c78848aac4d953f61a8926a792de8133b9e Mon Sep 17 00:00:00 2001
From: Jason Cooper <jason@lakedaemon.net>
Date: Thu, 27 Nov 2014 18:27:49 +0000
Subject: irqchip: gic: Remove warning by including linux/irqdomain.h

Commit

  853a33ce6932 irqchip: gic-v2m: Add support for ARM GICv2m MSI(-X) doorbell

Introduced a series of warnings when building ARM multi_v7_defconfig:

  include/linux/irqchip/arm-gic.h:109:53: warning: its scope is only this definition or declaration, which is probably not what you want
  In file included from arch/arm/mach-ux500/pm.c:13:0:
  include/linux/irqchip/arm-gic.h:109:53: warning: 'struct irq_domain' declared inside parameter list
   int gicv2m_of_init(struct device_node *node, struct irq_domain *parent);
                                                       ^

Fix this by adding the proper include.

Signed-off-by: Jason Cooper <jason@lakedaemon.net>
[ jac merged much more correct version from Marc into this patch ]
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Link: https://lkml.kernel.org/r/1417170975-1163-1-git-send-email-marc.zyngier@arm.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
---
 include/linux/irqchip/arm-gic.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 60b09ed58ca..71d706d5f16 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -91,6 +91,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/irqdomain.h>
+
 struct device_node;
 
 extern struct irq_chip gic_arch_extn;
-- 
cgit v1.2.3-70-g09d2


From 90452e61137a3e88aa705d3efcb3874f3ce8d390 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 27 Nov 2014 06:07:49 +0530
Subject: cpufreq: Fix formatting issues in 'struct cpufreq_driver'

Adding any new callback to 'struct cpufreq_driver' gives following checkpatch
warning:

WARNING: Unnecessary space before function pointer arguments
+	void	(*ready)	(struct cpufreq_policy *policy);

This is because we have been using a tab spacing between function pointer name
and its arguments and the new one tried to follow that.

Though we normally don't try to fix every checkpatch warning, specially around
formatting issues as that creates unnecessary noise over lists. But I thought we
better fix this so that new additions don't generate these warnings plus it
looks far better/symmetric now.

So, remove these tab spacing issues in 'struct cpufreq_driver' only + fix
alignment of all members.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Eduardo Valentin <edubezval@gmail.com>
Tested-by: Eduardo Valentin <edubezval@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/cpufreq.h | 50 ++++++++++++++++++++++++-------------------------
 1 file changed, 25 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 503b085b783..db3c1308567 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -217,26 +217,26 @@ __ATTR(_name, 0644, show_##_name, store_##_name)
 
 
 struct cpufreq_driver {
-	char			name[CPUFREQ_NAME_LEN];
-	u8			flags;
-	void			*driver_data;
+	char		name[CPUFREQ_NAME_LEN];
+	u8		flags;
+	void		*driver_data;
 
 	/* needed by all drivers */
-	int	(*init)		(struct cpufreq_policy *policy);
-	int	(*verify)	(struct cpufreq_policy *policy);
+	int		(*init)(struct cpufreq_policy *policy);
+	int		(*verify)(struct cpufreq_policy *policy);
 
 	/* define one out of two */
-	int	(*setpolicy)	(struct cpufreq_policy *policy);
+	int		(*setpolicy)(struct cpufreq_policy *policy);
 
 	/*
 	 * On failure, should always restore frequency to policy->restore_freq
 	 * (i.e. old freq).
 	 */
-	int	(*target)	(struct cpufreq_policy *policy,	/* Deprecated */
-				 unsigned int target_freq,
-				 unsigned int relation);
-	int	(*target_index)	(struct cpufreq_policy *policy,
-				 unsigned int index);
+	int		(*target)(struct cpufreq_policy *policy,
+				  unsigned int target_freq,
+				  unsigned int relation);	/* Deprecated */
+	int		(*target_index)(struct cpufreq_policy *policy,
+					unsigned int index);
 	/*
 	 * Only for drivers with target_index() and CPUFREQ_ASYNC_NOTIFICATION
 	 * unset.
@@ -252,27 +252,27 @@ struct cpufreq_driver {
 	 * wish to switch to intermediate frequency for some target frequency.
 	 * In that case core will directly call ->target_index().
 	 */
-	unsigned int (*get_intermediate)(struct cpufreq_policy *policy,
-					 unsigned int index);
-	int	(*target_intermediate)(struct cpufreq_policy *policy,
-				       unsigned int index);
+	unsigned int	(*get_intermediate)(struct cpufreq_policy *policy,
+					    unsigned int index);
+	int		(*target_intermediate)(struct cpufreq_policy *policy,
+					       unsigned int index);
 
 	/* should be defined, if possible */
-	unsigned int	(*get)	(unsigned int cpu);
+	unsigned int	(*get)(unsigned int cpu);
 
 	/* optional */
-	int	(*bios_limit)	(int cpu, unsigned int *limit);
+	int		(*bios_limit)(int cpu, unsigned int *limit);
 
-	int	(*exit)		(struct cpufreq_policy *policy);
-	void	(*stop_cpu)	(struct cpufreq_policy *policy);
-	int	(*suspend)	(struct cpufreq_policy *policy);
-	int	(*resume)	(struct cpufreq_policy *policy);
-	struct freq_attr	**attr;
+	int		(*exit)(struct cpufreq_policy *policy);
+	void		(*stop_cpu)(struct cpufreq_policy *policy);
+	int		(*suspend)(struct cpufreq_policy *policy);
+	int		(*resume)(struct cpufreq_policy *policy);
+	struct freq_attr **attr;
 
 	/* platform specific boost support code */
-	bool                    boost_supported;
-	bool                    boost_enabled;
-	int     (*set_boost)    (int state);
+	bool		boost_supported;
+	bool		boost_enabled;
+	int		(*set_boost)(int state);
 };
 
 /* flags */
-- 
cgit v1.2.3-70-g09d2


From 7c45cf31b3ab9be270a7bf6af2926631dc566436 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 27 Nov 2014 06:07:51 +0530
Subject: cpufreq: Introduce ->ready() callback for cpufreq drivers

Currently there is no callback for cpufreq drivers which is called once the
policy is ready to be used. There are some requirements where such a callback is
required.

One of them is registering a cooling device with the help of
of_cpufreq_cooling_register(). This routine tries to get 'struct cpufreq_policy'
for CPUs which isn't yet initialed at the time ->init() is called and so we face
issues while registering the cooling device.

Because we can't register cooling device from ->init(), we need a callback that
is called after the policy is ready to be used and hence we introduce ->ready()
callback.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Eduardo Valentin <edubezval@gmail.com>
Tested-by: Eduardo Valentin <edubezval@gmail.com>
Reviewed-by: Lukasz Majewski <l.majewski@samsung.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c | 5 +++++
 include/linux/cpufreq.h   | 4 ++++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index de2c3e198b6..a09a29c312a 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1285,8 +1285,13 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	up_write(&policy->rwsem);
 
 	kobject_uevent(&policy->kobj, KOBJ_ADD);
+
 	up_read(&cpufreq_rwsem);
 
+	/* Callback for handling stuff after policy is ready */
+	if (cpufreq_driver->ready)
+		cpufreq_driver->ready(policy);
+
 	pr_debug("initialization complete\n");
 
 	return 0;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index db3c1308567..4d078cebafd 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -267,6 +267,10 @@ struct cpufreq_driver {
 	void		(*stop_cpu)(struct cpufreq_policy *policy);
 	int		(*suspend)(struct cpufreq_policy *policy);
 	int		(*resume)(struct cpufreq_policy *policy);
+
+	/* Will be called after the driver is fully initialized */
+	void		(*ready)(struct cpufreq_policy *policy);
+
 	struct freq_attr **attr;
 
 	/* platform specific boost support code */
-- 
cgit v1.2.3-70-g09d2


From 129eec55df6ab1b5ecdd89fd7db7a2cd103200b5 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 27 Nov 2014 08:54:06 +0530
Subject: PM / OPP Introduce APIs to remove OPPs

OPPs are created statically (from DT) or dynamically. Currently we don't free
OPPs that are created statically, when the module unloads. And so if the module
is inserted back again, we get warning for duplicate OPPs as the same were
already present.

Also, there might be a need to remove dynamic OPPs in future and so API for that
is also added.

This patch adds helper APIs to remove/free existing static and dynamic OPPs.

Because the OPPs are used both under RCU and SRCU, we have to wait for grace
period of both. And so are using kfree_rcu() from within call_srcu().

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp.c | 102 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pm_opp.h   |  12 +++++-
 2 files changed, 113 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index b249b0127ef..977474a3c64 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -79,6 +79,7 @@ struct dev_pm_opp {
  *		however addition is possible and is secured by dev_opp_list_lock
  * @dev:	device pointer
  * @srcu_head:	notifier head to notify the OPP availability changes.
+ * @rcu_head:	RCU callback head used for deferred freeing
  * @opp_list:	list of opps
  *
  * This is an internal data structure maintaining the link to opps attached to
@@ -90,6 +91,7 @@ struct device_opp {
 
 	struct device *dev;
 	struct srcu_notifier_head srcu_head;
+	struct rcu_head rcu_head;
 	struct list_head opp_list;
 };
 
@@ -498,6 +500,76 @@ int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_add);
 
+static void kfree_opp_rcu(struct rcu_head *head)
+{
+	struct dev_pm_opp *opp = container_of(head, struct dev_pm_opp, rcu_head);
+
+	kfree_rcu(opp, rcu_head);
+}
+
+static void kfree_device_rcu(struct rcu_head *head)
+{
+	struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head);
+
+	kfree(device_opp);
+}
+
+void __dev_pm_opp_remove(struct device_opp *dev_opp, struct dev_pm_opp *opp)
+{
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp);
+	list_del_rcu(&opp->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, kfree_opp_rcu);
+
+	if (list_empty(&dev_opp->opp_list)) {
+		list_del_rcu(&dev_opp->node);
+		call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head,
+			  kfree_device_rcu);
+	}
+}
+
+/**
+ * dev_pm_opp_remove()  - Remove an OPP from OPP list
+ * @dev:	device for which we do this operation
+ * @freq:	OPP to remove with matching 'freq'
+ *
+ * This function removes an opp from the opp list.
+ */
+void dev_pm_opp_remove(struct device *dev, unsigned long freq)
+{
+	struct dev_pm_opp *opp;
+	struct device_opp *dev_opp;
+	bool found = false;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		goto unlock;
+
+	list_for_each_entry(opp, &dev_opp->opp_list, node) {
+		if (opp->rate == freq) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
+			 __func__, freq);
+		goto unlock;
+	}
+
+	__dev_pm_opp_remove(dev_opp, opp);
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
+
 /**
  * opp_set_availability() - helper to set the availability of an opp
  * @dev:		device for which we do this operation
@@ -687,4 +759,34 @@ int of_init_opp_table(struct device *dev)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(of_init_opp_table);
+
+/**
+ * of_free_opp_table() - Free OPP table entries created from static DT entries
+ * @dev:	device pointer used to lookup device OPPs.
+ *
+ * Free OPPs created using static entries present in DT.
+ */
+void of_free_opp_table(struct device *dev)
+{
+	struct device_opp *dev_opp = find_device_opp(dev);
+	struct dev_pm_opp *opp, *tmp;
+
+	/* Check for existing list for 'dev' */
+	dev_opp = find_device_opp(dev);
+	if (WARN(IS_ERR(dev_opp), "%s: dev_opp: %ld\n", dev_name(dev),
+		 PTR_ERR(dev_opp)))
+		return;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Free static OPPs */
+	list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) {
+		if (!opp->dynamic)
+			__dev_pm_opp_remove(dev_opp, opp);
+	}
+
+	mutex_unlock(&dev_opp_list_lock);
+}
+EXPORT_SYMBOL_GPL(of_free_opp_table);
 #endif
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 0330217abfa..cec2d454091 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -21,7 +21,7 @@ struct dev_pm_opp;
 struct device;
 
 enum dev_pm_opp_event {
-	OPP_EVENT_ADD, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE,
+	OPP_EVENT_ADD, OPP_EVENT_REMOVE, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE,
 };
 
 #if defined(CONFIG_PM_OPP)
@@ -44,6 +44,7 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 
 int dev_pm_opp_add(struct device *dev, unsigned long freq,
 		   unsigned long u_volt);
+void dev_pm_opp_remove(struct device *dev, unsigned long freq);
 
 int dev_pm_opp_enable(struct device *dev, unsigned long freq);
 
@@ -90,6 +91,10 @@ static inline int dev_pm_opp_add(struct device *dev, unsigned long freq,
 	return -EINVAL;
 }
 
+static inline void dev_pm_opp_remove(struct device *dev, unsigned long freq)
+{
+}
+
 static inline int dev_pm_opp_enable(struct device *dev, unsigned long freq)
 {
 	return 0;
@@ -109,11 +114,16 @@ static inline struct srcu_notifier_head *dev_pm_opp_get_notifier(
 
 #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF)
 int of_init_opp_table(struct device *dev);
+void of_free_opp_table(struct device *dev);
 #else
 static inline int of_init_opp_table(struct device *dev)
 {
 	return -EINVAL;
 }
+
+static inline void of_free_opp_table(struct device *dev)
+{
+}
 #endif
 
 #endif		/* __LINUX_OPP_H__ */
-- 
cgit v1.2.3-70-g09d2


From 4749c02b8da6d8dbc29218652985bda844017e95 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Date: Fri, 21 Nov 2014 17:00:04 +0100
Subject: bus: mvebu-mbus: provide a mechanism to save SDRAM window
 configuration

On Marvell EBU platforms, when doing suspend/resume, the SDRAM window
configuration must be saved on suspend, and restored on
resume. However, it needs to be restored on resume *before*
re-entering the kernel, because the SDRAM window configuration defines
the layout of the memory. For this reason, it cannot simply be done in
the ->suspend() and ->resume() hooks of the mvebu-mbus driver.

Instead, it needs to be restored by the bootloader "boot info"
mechanism used when resuming. This mechanism allows the kernel to
define a list of (address, value) pairs when suspending, that the
bootloader will restore on resume before jumping back into the kernel.

This commit therefore adds a new function to the mvebu-mbus driver,
called mvebu_mbus_save_cpu_target(), which will be called by the
platform code to make the mvebu-mbus driver save the SDRAM window
configuration in a way that can be understood by the bootloader "boot
info" mechanism.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Reviewed-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Link: https://lkml.kernel.org/r/1416585613-2113-8-git-send-email-thomas.petazzoni@free-electrons.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
---
 drivers/bus/mvebu-mbus.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mbus.h     |  1 +
 2 files changed, 57 insertions(+)

(limited to 'include')

diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index e8c159399c8..eb7682dc123 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -110,6 +110,8 @@ struct mvebu_mbus_soc_data {
 	bool has_mbus_bridge;
 	unsigned int (*win_cfg_offset)(const int win);
 	void (*setup_cpu_target)(struct mvebu_mbus_state *s);
+	int (*save_cpu_target)(struct mvebu_mbus_state *s,
+			       u32 *store_addr);
 	int (*show_cpu_target)(struct mvebu_mbus_state *s,
 			       struct seq_file *seq, void *v);
 };
@@ -128,6 +130,7 @@ struct mvebu_mbus_state {
 	void __iomem *mbuswins_base;
 	void __iomem *sdramwins_base;
 	void __iomem *mbusbridge_base;
+	phys_addr_t sdramwins_phys_base;
 	struct dentry *debugfs_root;
 	struct dentry *debugfs_sdram;
 	struct dentry *debugfs_devs;
@@ -541,6 +544,28 @@ mvebu_mbus_default_setup_cpu_target(struct mvebu_mbus_state *mbus)
 	mvebu_mbus_dram_info.num_cs = cs;
 }
 
+static int
+mvebu_mbus_default_save_cpu_target(struct mvebu_mbus_state *mbus,
+				   u32 *store_addr)
+{
+	int i;
+
+	for (i = 0; i < 4; i++) {
+		u32 base = readl(mbus->sdramwins_base + DDR_BASE_CS_OFF(i));
+		u32 size = readl(mbus->sdramwins_base + DDR_SIZE_CS_OFF(i));
+
+		writel(mbus->sdramwins_phys_base + DDR_BASE_CS_OFF(i),
+		       store_addr++);
+		writel(base, store_addr++);
+		writel(mbus->sdramwins_phys_base + DDR_SIZE_CS_OFF(i),
+		       store_addr++);
+		writel(size, store_addr++);
+	}
+
+	/* We've written 16 words to the store address */
+	return 16;
+}
+
 static void __init
 mvebu_mbus_dove_setup_cpu_target(struct mvebu_mbus_state *mbus)
 {
@@ -571,11 +596,35 @@ mvebu_mbus_dove_setup_cpu_target(struct mvebu_mbus_state *mbus)
 	mvebu_mbus_dram_info.num_cs = cs;
 }
 
+static int
+mvebu_mbus_dove_save_cpu_target(struct mvebu_mbus_state *mbus,
+				u32 *store_addr)
+{
+	int i;
+
+	for (i = 0; i < 2; i++) {
+		u32 map = readl(mbus->sdramwins_base + DOVE_DDR_BASE_CS_OFF(i));
+
+		writel(mbus->sdramwins_phys_base + DOVE_DDR_BASE_CS_OFF(i),
+		       store_addr++);
+		writel(map, store_addr++);
+	}
+
+	/* We've written 4 words to the store address */
+	return 4;
+}
+
+int mvebu_mbus_save_cpu_target(u32 *store_addr)
+{
+	return mbus_state.soc->save_cpu_target(&mbus_state, store_addr);
+}
+
 static const struct mvebu_mbus_soc_data armada_370_xp_mbus_data = {
 	.num_wins            = 20,
 	.num_remappable_wins = 8,
 	.has_mbus_bridge     = true,
 	.win_cfg_offset      = armada_370_xp_mbus_win_offset,
+	.save_cpu_target     = mvebu_mbus_default_save_cpu_target,
 	.setup_cpu_target    = mvebu_mbus_default_setup_cpu_target,
 	.show_cpu_target     = mvebu_sdram_debug_show_orion,
 };
@@ -584,6 +633,7 @@ static const struct mvebu_mbus_soc_data kirkwood_mbus_data = {
 	.num_wins            = 8,
 	.num_remappable_wins = 4,
 	.win_cfg_offset      = orion_mbus_win_offset,
+	.save_cpu_target     = mvebu_mbus_default_save_cpu_target,
 	.setup_cpu_target    = mvebu_mbus_default_setup_cpu_target,
 	.show_cpu_target     = mvebu_sdram_debug_show_orion,
 };
@@ -592,6 +642,7 @@ static const struct mvebu_mbus_soc_data dove_mbus_data = {
 	.num_wins            = 8,
 	.num_remappable_wins = 4,
 	.win_cfg_offset      = orion_mbus_win_offset,
+	.save_cpu_target     = mvebu_mbus_dove_save_cpu_target,
 	.setup_cpu_target    = mvebu_mbus_dove_setup_cpu_target,
 	.show_cpu_target     = mvebu_sdram_debug_show_dove,
 };
@@ -604,6 +655,7 @@ static const struct mvebu_mbus_soc_data orion5x_4win_mbus_data = {
 	.num_wins            = 8,
 	.num_remappable_wins = 4,
 	.win_cfg_offset      = orion_mbus_win_offset,
+	.save_cpu_target     = mvebu_mbus_default_save_cpu_target,
 	.setup_cpu_target    = mvebu_mbus_default_setup_cpu_target,
 	.show_cpu_target     = mvebu_sdram_debug_show_orion,
 };
@@ -612,6 +664,7 @@ static const struct mvebu_mbus_soc_data orion5x_2win_mbus_data = {
 	.num_wins            = 8,
 	.num_remappable_wins = 2,
 	.win_cfg_offset      = orion_mbus_win_offset,
+	.save_cpu_target     = mvebu_mbus_default_save_cpu_target,
 	.setup_cpu_target    = mvebu_mbus_default_setup_cpu_target,
 	.show_cpu_target     = mvebu_sdram_debug_show_orion,
 };
@@ -620,6 +673,7 @@ static const struct mvebu_mbus_soc_data mv78xx0_mbus_data = {
 	.num_wins            = 14,
 	.num_remappable_wins = 8,
 	.win_cfg_offset      = mv78xx0_mbus_win_offset,
+	.save_cpu_target     = mvebu_mbus_default_save_cpu_target,
 	.setup_cpu_target    = mvebu_mbus_default_setup_cpu_target,
 	.show_cpu_target     = mvebu_sdram_debug_show_orion,
 };
@@ -804,6 +858,8 @@ static int __init mvebu_mbus_common_init(struct mvebu_mbus_state *mbus,
 		return -ENOMEM;
 	}
 
+	mbus->sdramwins_phys_base = sdramwins_phys_base;
+
 	if (mbusbridge_phys_base) {
 		mbus->mbusbridge_base = ioremap(mbusbridge_phys_base,
 						mbusbridge_size);
diff --git a/include/linux/mbus.h b/include/linux/mbus.h
index 550c88fb026..611b69fa859 100644
--- a/include/linux/mbus.h
+++ b/include/linux/mbus.h
@@ -61,6 +61,7 @@ static inline const struct mbus_dram_target_info *mv_mbus_dram_info(void)
 }
 #endif
 
+int mvebu_mbus_save_cpu_target(u32 *store_addr);
 void mvebu_mbus_get_pcie_mem_aperture(struct resource *res);
 void mvebu_mbus_get_pcie_io_aperture(struct resource *res);
 int mvebu_mbus_add_window_remap_by_id(unsigned int target,
-- 
cgit v1.2.3-70-g09d2


From f30d0a815bb9b8ac1a3ab4d0c333d2379220d91d Mon Sep 17 00:00:00 2001
From: Arend van Spriel <arend@broadcom.com>
Date: Sun, 30 Nov 2014 16:31:21 +0100
Subject: fs: debugfs: add forward declaration for struct device type

The function debugfs_create_devm_seqfile() has a parameter of type
struct device pointer. This type needs to be forward declared to
avoid compilation issues on certain architectures and/or kernel
configurations. The function was introduced with:

  commit 98210b7f73f1db182bd9a558a031093cd166e907
  Author: Arend van Spriel <arend@broadcom.com>
  Date:   Sun Nov 9 11:31:58 2014 +0100

     debugfs: add helper function to create device related seq_file

The reported build failure for sparc64 architecture was:

  make.cross ARCH=sparc64

All warnings:

   In file included from fs/debugfs/file.c:21:0:
   include/linux/debugfs.h:105:10: warning: 'struct device' declared
   inside parameter list
             void *data));
             ^

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Arend van Spriel <arend@broadcom.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/debugfs.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index 4bbe2ace972..e3e9f31f91d 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -20,6 +20,7 @@
 
 #include <linux/types.h>
 
+struct device;
 struct file_operations;
 
 struct debugfs_blob_wrapper {
-- 
cgit v1.2.3-70-g09d2


From ddbb4db4ced1ba784fcd3500179a7291b6c5d7b7 Mon Sep 17 00:00:00 2001
From: Alan Tull <atull@opensource.altera.com>
Date: Wed, 15 Oct 2014 13:55:09 -0500
Subject: hwmon: (pmbus) Add regulator support

Add support for simple on/off control of each channel.

To add regulator support, the pmbus part driver needs to add
regulator_desc information and number of regulators to its
pmbus_driver_info struct.

regulator_desc can be declared using default macro for a
regulator (PMBUS_REGULATOR) that is in pmbus.h

The regulator_init_data can be initialized from either
platform data or the device tree.

Signed-off-by: Alan Tull <atull@opensource.altera.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/pmbus.h      | 26 ++++++++++++
 drivers/hwmon/pmbus/pmbus_core.c | 87 ++++++++++++++++++++++++++++++++++++++++
 include/linux/i2c/pmbus.h        |  4 ++
 3 files changed, 117 insertions(+)

(limited to 'include')

diff --git a/drivers/hwmon/pmbus/pmbus.h b/drivers/hwmon/pmbus/pmbus.h
index 3ae79a7d1b0..89a23ff836e 100644
--- a/drivers/hwmon/pmbus/pmbus.h
+++ b/drivers/hwmon/pmbus/pmbus.h
@@ -19,6 +19,8 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#include <linux/regulator/driver.h>
+
 #ifndef PMBUS_H
 #define PMBUS_H
 
@@ -185,6 +187,11 @@
 #define PMBUS_VIRT_VMON_OV_FAULT_LIMIT	(PMBUS_VIRT_BASE + 34)
 #define PMBUS_VIRT_STATUS_VMON		(PMBUS_VIRT_BASE + 35)
 
+/*
+ * OPERATION
+ */
+#define PB_OPERATION_CONTROL_ON		(1<<7)
+
 /*
  * CAPABILITY
  */
@@ -365,8 +372,27 @@ struct pmbus_driver_info {
 	 */
 	int (*identify)(struct i2c_client *client,
 			struct pmbus_driver_info *info);
+
+	/* Regulator functionality, if supported by this chip driver. */
+	int num_regulators;
+	const struct regulator_desc *reg_desc;
 };
 
+/* Regulator ops */
+
+extern struct regulator_ops pmbus_regulator_ops;
+
+/* Macro for filling in array of struct regulator_desc */
+#define PMBUS_REGULATOR(_name, _id)				\
+	[_id] = {						\
+		.name = (_name # _id),				\
+		.id = (_id),					\
+		.of_match = of_match_ptr(_name # _id),		\
+		.regulators_node = of_match_ptr("regulators"),	\
+		.ops = &pmbus_regulator_ops,			\
+		.owner = THIS_MODULE,				\
+	}
+
 /* Function declarations */
 
 void pmbus_clear_cache(struct i2c_client *client);
diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c
index d6c3701eb7f..f2e47c7dd80 100644
--- a/drivers/hwmon/pmbus/pmbus_core.c
+++ b/drivers/hwmon/pmbus/pmbus_core.c
@@ -29,6 +29,8 @@
 #include <linux/hwmon-sysfs.h>
 #include <linux/jiffies.h>
 #include <linux/i2c/pmbus.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
 #include "pmbus.h"
 
 /*
@@ -1758,6 +1760,84 @@ static int pmbus_init_common(struct i2c_client *client, struct pmbus_data *data,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_REGULATOR)
+static int pmbus_regulator_is_enabled(struct regulator_dev *rdev)
+{
+	struct device *dev = rdev_get_dev(rdev);
+	struct i2c_client *client = to_i2c_client(dev->parent);
+	u8 page = rdev_get_id(rdev);
+	int ret;
+
+	ret = pmbus_read_byte_data(client, page, PMBUS_OPERATION);
+	if (ret < 0)
+		return ret;
+
+	return !!(ret & PB_OPERATION_CONTROL_ON);
+}
+
+static int _pmbus_regulator_on_off(struct regulator_dev *rdev, bool enable)
+{
+	struct device *dev = rdev_get_dev(rdev);
+	struct i2c_client *client = to_i2c_client(dev->parent);
+	u8 page = rdev_get_id(rdev);
+
+	return pmbus_update_byte_data(client, page, PMBUS_OPERATION,
+				      PB_OPERATION_CONTROL_ON,
+				      enable ? PB_OPERATION_CONTROL_ON : 0);
+}
+
+static int pmbus_regulator_enable(struct regulator_dev *rdev)
+{
+	return _pmbus_regulator_on_off(rdev, 1);
+}
+
+static int pmbus_regulator_disable(struct regulator_dev *rdev)
+{
+	return _pmbus_regulator_on_off(rdev, 0);
+}
+
+struct regulator_ops pmbus_regulator_ops = {
+	.enable = pmbus_regulator_enable,
+	.disable = pmbus_regulator_disable,
+	.is_enabled = pmbus_regulator_is_enabled,
+};
+EXPORT_SYMBOL_GPL(pmbus_regulator_ops);
+
+static int pmbus_regulator_register(struct pmbus_data *data)
+{
+	struct device *dev = data->dev;
+	const struct pmbus_driver_info *info = data->info;
+	const struct pmbus_platform_data *pdata = dev_get_platdata(dev);
+	struct regulator_dev *rdev;
+	int i;
+
+	for (i = 0; i < info->num_regulators; i++) {
+		struct regulator_config config = { };
+
+		config.dev = dev;
+		config.driver_data = data;
+
+		if (pdata && pdata->reg_init_data)
+			config.init_data = &pdata->reg_init_data[i];
+
+		rdev = devm_regulator_register(dev, &info->reg_desc[i],
+					       &config);
+		if (IS_ERR(rdev)) {
+			dev_err(dev, "Failed to register %s regulator\n",
+				info->reg_desc[i].name);
+			return PTR_ERR(rdev);
+		}
+	}
+
+	return 0;
+}
+#else
+static int pmbus_regulator_register(struct pmbus_data *data)
+{
+	return 0;
+}
+#endif
+
 int pmbus_do_probe(struct i2c_client *client, const struct i2c_device_id *id,
 		   struct pmbus_driver_info *info)
 {
@@ -1812,8 +1892,15 @@ int pmbus_do_probe(struct i2c_client *client, const struct i2c_device_id *id,
 		dev_err(dev, "Failed to register hwmon device\n");
 		goto out_kfree;
 	}
+
+	ret = pmbus_regulator_register(data);
+	if (ret)
+		goto out_unregister;
+
 	return 0;
 
+out_unregister:
+	hwmon_device_unregister(data->hwmon_dev);
 out_kfree:
 	kfree(data->group.attrs);
 	return ret;
diff --git a/include/linux/i2c/pmbus.h b/include/linux/i2c/pmbus.h
index 69280db02c4..ee3c2aba2a8 100644
--- a/include/linux/i2c/pmbus.h
+++ b/include/linux/i2c/pmbus.h
@@ -40,6 +40,10 @@
 
 struct pmbus_platform_data {
 	u32 flags;		/* Device specific flags */
+
+	/* regulator support */
+	int num_regulators;
+	struct regulator_init_data *reg_init_data;
 };
 
 #endif /* _PMBUS_H_ */
-- 
cgit v1.2.3-70-g09d2


From 50211be80290b061a923ea7e2d36a6865a48920a Mon Sep 17 00:00:00 2001
From: Jyri Sarha <jsarha@ti.com>
Date: Fri, 15 Aug 2014 15:44:44 +0300
Subject: ASoC: omap-hdmi-audio: Add platform device for OMAP HDMI audio
 support

The platform device should only be registered from OMAPDSS HDMI
driver. The platform driver registers and unregisters all ASoC
components needed for OMAP HDMI audio.

The hdmi audio driver implements cpu-dai component using the callbacks
provided by OMAPDSS and registers the component under DSS HDMI
device. Omap-pcm is registered for platform component also under DSS
HDMI device. Dummy codec is used as as codec component. The hdmi audio
driver implements also the card and registers it under its own
platform device.

Signed-off-by: Jyri Sarha <jsarha@ti.com>
Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 include/sound/omap-hdmi-audio.h  |  43 +++++
 sound/soc/omap/Kconfig           |  15 ++
 sound/soc/omap/Makefile          |   2 +
 sound/soc/omap/omap-hdmi-audio.c | 407 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 467 insertions(+)
 create mode 100644 include/sound/omap-hdmi-audio.h
 create mode 100644 sound/soc/omap/omap-hdmi-audio.c

(limited to 'include')

diff --git a/include/sound/omap-hdmi-audio.h b/include/sound/omap-hdmi-audio.h
new file mode 100644
index 00000000000..afdb416898e
--- /dev/null
+++ b/include/sound/omap-hdmi-audio.h
@@ -0,0 +1,43 @@
+/*
+ * hdmi-audio.c -- OMAP4+ DSS HDMI audio support library
+ *
+ * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Author: Jyri Sarha <jsarha@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ */
+
+#include <video/omapdss.h>
+
+#ifndef __OMAP_HDMI_AUDIO_H__
+#define __OMAP_HDMI_AUDIO_H__
+
+struct omap_hdmi_audio_ops {
+	int (*audio_startup)(struct device *dev,
+			     void (*abort_cb)(struct device *dev));
+	int (*audio_shutdown)(struct device *dev);
+	int (*audio_start)(struct device *dev);
+	void (*audio_stop)(struct device *dev);
+	int (*audio_config)(struct device *dev,
+			    struct omap_dss_audio *dss_audio);
+};
+
+/* HDMI audio initalization data */
+struct omap_hdmi_audio_pdata {
+	struct device *dev;
+	enum omapdss_version dss_version;
+	phys_addr_t audio_dma_addr;
+
+	const struct omap_hdmi_audio_ops *ops;
+};
+
+#endif /* __OMAP_HDMI_AUDIO_H__ */
diff --git a/sound/soc/omap/Kconfig b/sound/soc/omap/Kconfig
index d44463a7b0f..2b32b3e58bf 100644
--- a/sound/soc/omap/Kconfig
+++ b/sound/soc/omap/Kconfig
@@ -15,6 +15,21 @@ config SND_OMAP_SOC_MCPDM
 config SND_OMAP_SOC_HDMI
 	tristate
 
+config SND_OMAP_SOC_HDMI_AUDIO
+	tristate "HDMI audio support for OMAP4+ based SoCs"
+	depends on SND_OMAP_SOC
+	help
+	  For HDMI audio to work OMAPDSS HDMI support should be
+	  enabled.
+	  The hdmi audio driver implements cpu-dai component using the
+	  callbacks provided by OMAPDSS and registers the component
+	  under DSS HDMI device. Omap-pcm is registered for platform
+	  component also under DSS HDMI device. Dummy codec is used as
+	  as codec component. The hdmi audio driver implements also
+	  the card and registers it under its own platform device.
+	  The device for the dirver is registered by OMAPDSS hdmi
+	  driver.
+
 config SND_OMAP_SOC_N810
 	tristate "SoC Audio support for Nokia N810"
 	depends on SND_OMAP_SOC && MACH_NOKIA_N810 && I2C
diff --git a/sound/soc/omap/Makefile b/sound/soc/omap/Makefile
index a725905b2c6..40688a6e8e9 100644
--- a/sound/soc/omap/Makefile
+++ b/sound/soc/omap/Makefile
@@ -4,12 +4,14 @@ snd-soc-omap-dmic-objs := omap-dmic.o
 snd-soc-omap-mcbsp-objs := omap-mcbsp.o mcbsp.o
 snd-soc-omap-mcpdm-objs := omap-mcpdm.o
 snd-soc-omap-hdmi-objs := omap-hdmi.o
+snd-soc-omap-hdmi-audio-objs := omap-hdmi-audio.o
 
 obj-$(CONFIG_SND_OMAP_SOC) += snd-soc-omap.o
 obj-$(CONFIG_SND_OMAP_SOC_DMIC) += snd-soc-omap-dmic.o
 obj-$(CONFIG_SND_OMAP_SOC_MCBSP) += snd-soc-omap-mcbsp.o
 obj-$(CONFIG_SND_OMAP_SOC_MCPDM) += snd-soc-omap-mcpdm.o
 obj-$(CONFIG_SND_OMAP_SOC_HDMI) += snd-soc-omap-hdmi.o
+obj-$(CONFIG_SND_OMAP_SOC_HDMI_AUDIO) += snd-soc-omap-hdmi-audio.o
 
 # OMAP Machine Support
 snd-soc-n810-objs := n810.o
diff --git a/sound/soc/omap/omap-hdmi-audio.c b/sound/soc/omap/omap-hdmi-audio.c
new file mode 100644
index 00000000000..3f9ac7dbdc8
--- /dev/null
+++ b/sound/soc/omap/omap-hdmi-audio.c
@@ -0,0 +1,407 @@
+/*
+ * omap-hdmi-audio.c -- OMAP4+ DSS HDMI audio support library
+ *
+ * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Author: Jyri Sarha <jsarha@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/platform_device.h>
+#include <sound/soc.h>
+#include <sound/pcm_params.h>
+#include <sound/dmaengine_pcm.h>
+#include <uapi/sound/asound.h>
+#include <sound/asoundef.h>
+#include <sound/omap-pcm.h>
+#include <sound/omap-hdmi-audio.h>
+#include <video/omapdss.h>
+
+#define DRV_NAME "omap-hdmi-audio"
+
+struct hdmi_audio_data {
+	struct snd_soc_card *card;
+
+	const struct omap_hdmi_audio_ops *ops;
+	struct device *dssdev;
+	struct snd_dmaengine_dai_dma_data dma_data;
+	struct omap_dss_audio dss_audio;
+	struct snd_aes_iec958 iec;
+	struct snd_cea_861_aud_if cea;
+
+	struct mutex current_stream_lock;
+	struct snd_pcm_substream *current_stream;
+};
+
+static
+struct hdmi_audio_data *card_drvdata_substream(struct snd_pcm_substream *ss)
+{
+	struct snd_soc_pcm_runtime *rtd = ss->private_data;
+
+	return snd_soc_card_get_drvdata(rtd->card);
+}
+
+static void hdmi_dai_abort(struct device *dev)
+{
+	struct hdmi_audio_data *ad = dev_get_drvdata(dev);
+
+	mutex_lock(&ad->current_stream_lock);
+	if (ad->current_stream && ad->current_stream->runtime &&
+	    snd_pcm_running(ad->current_stream)) {
+		dev_err(dev, "HDMI display disabled, aborting playback\n");
+		snd_pcm_stream_lock_irq(ad->current_stream);
+		snd_pcm_stop(ad->current_stream, SNDRV_PCM_STATE_DISCONNECTED);
+		snd_pcm_stream_unlock_irq(ad->current_stream);
+	}
+	mutex_unlock(&ad->current_stream_lock);
+}
+
+static int hdmi_dai_startup(struct snd_pcm_substream *substream,
+			    struct snd_soc_dai *dai)
+{
+	struct hdmi_audio_data *ad = card_drvdata_substream(substream);
+	int ret;
+	/*
+	 * Make sure that the period bytes are multiple of the DMA packet size.
+	 * Largest packet size we use is 32 32-bit words = 128 bytes
+	 */
+	ret = snd_pcm_hw_constraint_step(substream->runtime, 0,
+					 SNDRV_PCM_HW_PARAM_PERIOD_BYTES, 128);
+	if (ret < 0) {
+		dev_err(dai->dev, "could not apply constraint\n");
+		return ret;
+	}
+
+	snd_soc_dai_set_dma_data(dai, substream, &ad->dma_data);
+
+	mutex_lock(&ad->current_stream_lock);
+	ad->current_stream = substream;
+	mutex_unlock(&ad->current_stream_lock);
+
+	ret = ad->ops->audio_startup(ad->dssdev, hdmi_dai_abort);
+
+	if (ret) {
+		mutex_lock(&ad->current_stream_lock);
+		ad->current_stream = NULL;
+		mutex_unlock(&ad->current_stream_lock);
+	}
+
+	return ret;
+}
+
+static int hdmi_dai_hw_params(struct snd_pcm_substream *substream,
+			      struct snd_pcm_hw_params *params,
+			      struct snd_soc_dai *dai)
+{
+	struct hdmi_audio_data *ad = card_drvdata_substream(substream);
+	struct snd_aes_iec958 *iec = &ad->iec;
+	struct snd_cea_861_aud_if *cea = &ad->cea;
+
+	WARN_ON(ad->current_stream != substream);
+
+	switch (params_format(params)) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+		ad->dma_data.maxburst = 16;
+		break;
+	case SNDRV_PCM_FORMAT_S24_LE:
+		ad->dma_data.maxburst = 32;
+		break;
+	default:
+		dev_err(dai->dev, "format not supported!\n");
+		return -EINVAL;
+	}
+
+	ad->dss_audio.iec = iec;
+	ad->dss_audio.cea = cea;
+	/*
+	 * fill the IEC-60958 channel status word
+	 */
+	/* initialize the word bytes */
+	memset(iec->status, 0, sizeof(iec->status));
+
+	/* specify IEC-60958-3 (commercial use) */
+	iec->status[0] &= ~IEC958_AES0_PROFESSIONAL;
+
+	/* specify that the audio is LPCM*/
+	iec->status[0] &= ~IEC958_AES0_NONAUDIO;
+
+	iec->status[0] |= IEC958_AES0_CON_NOT_COPYRIGHT;
+
+	iec->status[0] |= IEC958_AES0_CON_EMPHASIS_NONE;
+
+	iec->status[0] |= IEC958_AES1_PRO_MODE_NOTID;
+
+	iec->status[1] = IEC958_AES1_CON_GENERAL;
+
+	iec->status[2] |= IEC958_AES2_CON_SOURCE_UNSPEC;
+
+	iec->status[2] |= IEC958_AES2_CON_CHANNEL_UNSPEC;
+
+	switch (params_rate(params)) {
+	case 32000:
+		iec->status[3] |= IEC958_AES3_CON_FS_32000;
+		break;
+	case 44100:
+		iec->status[3] |= IEC958_AES3_CON_FS_44100;
+		break;
+	case 48000:
+		iec->status[3] |= IEC958_AES3_CON_FS_48000;
+		break;
+	case 88200:
+		iec->status[3] |= IEC958_AES3_CON_FS_88200;
+		break;
+	case 96000:
+		iec->status[3] |= IEC958_AES3_CON_FS_96000;
+		break;
+	case 176400:
+		iec->status[3] |= IEC958_AES3_CON_FS_176400;
+		break;
+	case 192000:
+		iec->status[3] |= IEC958_AES3_CON_FS_192000;
+		break;
+	default:
+		dev_err(dai->dev, "rate not supported!\n");
+		return -EINVAL;
+	}
+
+	/* specify the clock accuracy */
+	iec->status[3] |= IEC958_AES3_CON_CLOCK_1000PPM;
+
+	/*
+	 * specify the word length. The same word length value can mean
+	 * two different lengths. Hence, we need to specify the maximum
+	 * word length as well.
+	 */
+	switch (params_format(params)) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+		iec->status[4] |= IEC958_AES4_CON_WORDLEN_20_16;
+		iec->status[4] &= ~IEC958_AES4_CON_MAX_WORDLEN_24;
+		break;
+	case SNDRV_PCM_FORMAT_S24_LE:
+		iec->status[4] |= IEC958_AES4_CON_WORDLEN_24_20;
+		iec->status[4] |= IEC958_AES4_CON_MAX_WORDLEN_24;
+		break;
+	default:
+		dev_err(dai->dev, "format not supported!\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Fill the CEA-861 audio infoframe (see spec for details)
+	 */
+
+	cea->db1_ct_cc = (params_channels(params) - 1)
+		& CEA861_AUDIO_INFOFRAME_DB1CC;
+	cea->db1_ct_cc |= CEA861_AUDIO_INFOFRAME_DB1CT_FROM_STREAM;
+
+	cea->db2_sf_ss = CEA861_AUDIO_INFOFRAME_DB2SF_FROM_STREAM;
+	cea->db2_sf_ss |= CEA861_AUDIO_INFOFRAME_DB2SS_FROM_STREAM;
+
+	cea->db3 = 0; /* not used, all zeros */
+
+	/*
+	 * The OMAP HDMI IP requires to use the 8-channel channel code when
+	 * transmitting more than two channels.
+	 */
+	if (params_channels(params) == 2)
+		cea->db4_ca = 0x0;
+	else
+		cea->db4_ca = 0x13;
+
+	cea->db5_dminh_lsv = CEA861_AUDIO_INFOFRAME_DB5_DM_INH_PROHIBITED;
+	/* the expression is trivial but makes clear what we are doing */
+	cea->db5_dminh_lsv |= (0 & CEA861_AUDIO_INFOFRAME_DB5_LSV);
+
+	return ad->ops->audio_config(ad->dssdev, &ad->dss_audio);
+}
+
+static int hdmi_dai_trigger(struct snd_pcm_substream *substream, int cmd,
+			    struct snd_soc_dai *dai)
+{
+	struct hdmi_audio_data *ad = card_drvdata_substream(substream);
+	int err = 0;
+
+	WARN_ON(ad->current_stream != substream);
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		err = ad->ops->audio_start(ad->dssdev);
+		break;
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		ad->ops->audio_stop(ad->dssdev);
+		break;
+	default:
+		err = -EINVAL;
+	}
+	return err;
+}
+
+static void hdmi_dai_shutdown(struct snd_pcm_substream *substream,
+			      struct snd_soc_dai *dai)
+{
+	struct hdmi_audio_data *ad = card_drvdata_substream(substream);
+
+	WARN_ON(ad->current_stream != substream);
+
+	ad->ops->audio_shutdown(ad->dssdev);
+
+	mutex_lock(&ad->current_stream_lock);
+	ad->current_stream = NULL;
+	mutex_unlock(&ad->current_stream_lock);
+}
+
+static const struct snd_soc_dai_ops hdmi_dai_ops = {
+	.startup	= hdmi_dai_startup,
+	.hw_params	= hdmi_dai_hw_params,
+	.trigger	= hdmi_dai_trigger,
+	.shutdown	= hdmi_dai_shutdown,
+};
+
+static const struct snd_soc_component_driver omap_hdmi_component = {
+	.name = "omapdss_hdmi",
+};
+
+static struct snd_soc_dai_driver omap5_hdmi_dai = {
+	.name = "omap5-hdmi-dai",
+	.playback = {
+		.channels_min = 2,
+		.channels_max = 8,
+		.rates = (SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_44100 |
+			  SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_88200 |
+			  SNDRV_PCM_RATE_96000 | SNDRV_PCM_RATE_176400 |
+			  SNDRV_PCM_RATE_192000),
+		.formats = SNDRV_PCM_FMTBIT_S16_LE,
+	},
+	.ops = &hdmi_dai_ops,
+};
+
+static struct snd_soc_dai_driver omap4_hdmi_dai = {
+	.name = "omap4-hdmi-dai",
+	.playback = {
+		.channels_min = 2,
+		.channels_max = 8,
+		.rates = (SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_44100 |
+			  SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_88200 |
+			  SNDRV_PCM_RATE_96000 | SNDRV_PCM_RATE_176400 |
+			  SNDRV_PCM_RATE_192000),
+		.formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE,
+	},
+	.ops = &hdmi_dai_ops,
+};
+
+static int omap_hdmi_audio_probe(struct platform_device *pdev)
+{
+	struct omap_hdmi_audio_pdata *ha = pdev->dev.platform_data;
+	struct device *dev = &pdev->dev;
+	struct hdmi_audio_data *ad;
+	struct snd_soc_dai_driver *dai_drv;
+	struct snd_soc_card *card;
+	int ret;
+
+	if (!ha) {
+		dev_err(dev, "No platform data\n");
+		return -EINVAL;
+	}
+
+	ad = devm_kzalloc(dev, sizeof(*ad), GFP_KERNEL);
+	if (!ad)
+		return -ENOMEM;
+	ad->dssdev = ha->dev;
+	ad->ops = ha->ops;
+	ad->dma_data.addr = ha->audio_dma_addr;
+	ad->dma_data.filter_data = "audio_tx";
+	ad->dma_data.addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	mutex_init(&ad->current_stream_lock);
+
+	switch (ha->dss_version) {
+	case OMAPDSS_VER_OMAP4430_ES1:
+	case OMAPDSS_VER_OMAP4430_ES2:
+	case OMAPDSS_VER_OMAP4:
+		dai_drv = &omap4_hdmi_dai;
+		break;
+	case OMAPDSS_VER_OMAP5:
+		dai_drv = &omap5_hdmi_dai;
+		break;
+	default:
+		return -EINVAL;
+	}
+	ret = snd_soc_register_component(ad->dssdev, &omap_hdmi_component,
+					 dai_drv, 1);
+	if (ret)
+		return ret;
+
+	ret = omap_pcm_platform_register(ad->dssdev);
+	if (ret)
+		return ret;
+
+	card = devm_kzalloc(dev, sizeof(*card), GFP_KERNEL);
+	card->name = devm_kasprintf(dev, GFP_KERNEL,
+				    "HDMI %s", dev_name(ad->dssdev));
+	card->owner = THIS_MODULE;
+	card->dai_link =
+		devm_kzalloc(dev, sizeof(*(card->dai_link)), GFP_KERNEL);
+	card->dai_link->name = card->name;
+	card->dai_link->stream_name = card->name;
+	card->dai_link->cpu_dai_name = dev_name(ad->dssdev);
+	card->dai_link->platform_name = dev_name(ad->dssdev);
+	card->dai_link->codec_name = "snd-soc-dummy";
+	card->dai_link->codec_dai_name = "snd-soc-dummy-dai";
+	card->num_links = 1;
+	card->dev = dev;
+
+	ret = snd_soc_register_card(card);
+	if (ret) {
+		dev_err(dev, "snd_soc_register_card failed (%d)\n", ret);
+		snd_soc_unregister_component(ad->dssdev);
+		return ret;
+	}
+
+	ad->card = card;
+	snd_soc_card_set_drvdata(card, ad);
+
+	dev_set_drvdata(dev, ad);
+
+	return 0;
+}
+
+static int omap_hdmi_audio_remove(struct platform_device *pdev)
+{
+	struct hdmi_audio_data *ad = platform_get_drvdata(pdev);
+
+	snd_soc_unregister_card(ad->card);
+	snd_soc_unregister_component(ad->dssdev);
+	return 0;
+}
+
+static struct platform_driver hdmi_audio_driver = {
+	.driver = {
+		.name = DRV_NAME,
+		.owner = THIS_MODULE,
+	},
+	.probe = omap_hdmi_audio_probe,
+	.remove = omap_hdmi_audio_remove,
+};
+
+module_platform_driver(hdmi_audio_driver);
+
+MODULE_AUTHOR("Jyri Sarha <jsarha@ti.com>");
+MODULE_DESCRIPTION("OMAP HDMI Audio Driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:" DRV_NAME);
-- 
cgit v1.2.3-70-g09d2


From 84a845de578a6d46e13307edc2fb27b423213eff Mon Sep 17 00:00:00 2001
From: Jyri Sarha <jsarha@ti.com>
Date: Wed, 25 Jun 2014 20:20:57 +0300
Subject: OMAPDSS: Remove all references to obsolete HDMI audio callbacks

In new model these callbacks are obsolete since the ASoC component
drivers are integrated into the HDMI drivers and no callbacks are
needed anymore.

Signed-off-by: Jyri Sarha <jsarha@ti.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 .../fbdev/omap2/displays-new/connector-hdmi.c      | 99 ----------------------
 .../fbdev/omap2/displays-new/encoder-tpd12s015.c   | 56 ------------
 include/video/omapdss.h                            | 40 ---------
 3 files changed, 195 deletions(-)

(limited to 'include')

diff --git a/drivers/video/fbdev/omap2/displays-new/connector-hdmi.c b/drivers/video/fbdev/omap2/displays-new/connector-hdmi.c
index 7b25967a91e..219f14f5967 100644
--- a/drivers/video/fbdev/omap2/displays-new/connector-hdmi.c
+++ b/drivers/video/fbdev/omap2/displays-new/connector-hdmi.c
@@ -170,98 +170,6 @@ static bool hdmic_detect(struct omap_dss_device *dssdev)
 		return in->ops.hdmi->detect(in);
 }
 
-static int hdmic_audio_enable(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = to_panel_data(dssdev);
-	struct omap_dss_device *in = ddata->in;
-	int r;
-
-	/* enable audio only if the display is active */
-	if (!omapdss_device_is_enabled(dssdev))
-		return -EPERM;
-
-	r = in->ops.hdmi->audio_enable(in);
-	if (r)
-		return r;
-
-	dssdev->audio_state = OMAP_DSS_AUDIO_ENABLED;
-
-	return 0;
-}
-
-static void hdmic_audio_disable(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = to_panel_data(dssdev);
-	struct omap_dss_device *in = ddata->in;
-
-	in->ops.hdmi->audio_disable(in);
-
-	dssdev->audio_state = OMAP_DSS_AUDIO_DISABLED;
-}
-
-static int hdmic_audio_start(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = to_panel_data(dssdev);
-	struct omap_dss_device *in = ddata->in;
-	int r;
-
-	/*
-	 * No need to check the panel state. It was checked when trasitioning
-	 * to AUDIO_ENABLED.
-	 */
-	if (dssdev->audio_state != OMAP_DSS_AUDIO_ENABLED)
-		return -EPERM;
-
-	r = in->ops.hdmi->audio_start(in);
-	if (r)
-		return r;
-
-	dssdev->audio_state = OMAP_DSS_AUDIO_PLAYING;
-
-	return 0;
-}
-
-static void hdmic_audio_stop(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = to_panel_data(dssdev);
-	struct omap_dss_device *in = ddata->in;
-
-	in->ops.hdmi->audio_stop(in);
-
-	dssdev->audio_state = OMAP_DSS_AUDIO_ENABLED;
-}
-
-static bool hdmic_audio_supported(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = to_panel_data(dssdev);
-	struct omap_dss_device *in = ddata->in;
-
-	if (!omapdss_device_is_enabled(dssdev))
-		return false;
-
-	return in->ops.hdmi->audio_supported(in);
-}
-
-static int hdmic_audio_config(struct omap_dss_device *dssdev,
-		struct omap_dss_audio *audio)
-{
-	struct panel_drv_data *ddata = to_panel_data(dssdev);
-	struct omap_dss_device *in = ddata->in;
-	int r;
-
-	/* config audio only if the display is active */
-	if (!omapdss_device_is_enabled(dssdev))
-		return -EPERM;
-
-	r = in->ops.hdmi->audio_config(in, audio);
-	if (r)
-		return r;
-
-	dssdev->audio_state = OMAP_DSS_AUDIO_CONFIGURED;
-
-	return 0;
-}
-
 static int hdmic_set_hdmi_mode(struct omap_dss_device *dssdev, bool hdmi_mode)
 {
 	struct panel_drv_data *ddata = to_panel_data(dssdev);
@@ -296,13 +204,6 @@ static struct omap_dss_driver hdmic_driver = {
 	.detect			= hdmic_detect,
 	.set_hdmi_mode		= hdmic_set_hdmi_mode,
 	.set_hdmi_infoframe	= hdmic_set_infoframe,
-
-	.audio_enable		= hdmic_audio_enable,
-	.audio_disable		= hdmic_audio_disable,
-	.audio_start		= hdmic_audio_start,
-	.audio_stop		= hdmic_audio_stop,
-	.audio_supported	= hdmic_audio_supported,
-	.audio_config		= hdmic_audio_config,
 };
 
 static int hdmic_probe_pdata(struct platform_device *pdev)
diff --git a/drivers/video/fbdev/omap2/displays-new/encoder-tpd12s015.c b/drivers/video/fbdev/omap2/displays-new/encoder-tpd12s015.c
index 1891967b650..c7a3ce2c512 100644
--- a/drivers/video/fbdev/omap2/displays-new/encoder-tpd12s015.c
+++ b/drivers/video/fbdev/omap2/displays-new/encoder-tpd12s015.c
@@ -193,55 +193,6 @@ static bool tpd_detect(struct omap_dss_device *dssdev)
 	return gpio_get_value_cansleep(ddata->hpd_gpio);
 }
 
-static int tpd_audio_enable(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = to_panel_data(dssdev);
-	struct omap_dss_device *in = ddata->in;
-
-	return in->ops.hdmi->audio_enable(in);
-}
-
-static void tpd_audio_disable(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = to_panel_data(dssdev);
-	struct omap_dss_device *in = ddata->in;
-
-	in->ops.hdmi->audio_disable(in);
-}
-
-static int tpd_audio_start(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = to_panel_data(dssdev);
-	struct omap_dss_device *in = ddata->in;
-
-	return in->ops.hdmi->audio_start(in);
-}
-
-static void tpd_audio_stop(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = to_panel_data(dssdev);
-	struct omap_dss_device *in = ddata->in;
-
-	in->ops.hdmi->audio_stop(in);
-}
-
-static bool tpd_audio_supported(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = to_panel_data(dssdev);
-	struct omap_dss_device *in = ddata->in;
-
-	return in->ops.hdmi->audio_supported(in);
-}
-
-static int tpd_audio_config(struct omap_dss_device *dssdev,
-		struct omap_dss_audio *audio)
-{
-	struct panel_drv_data *ddata = to_panel_data(dssdev);
-	struct omap_dss_device *in = ddata->in;
-
-	return in->ops.hdmi->audio_config(in, audio);
-}
-
 static int tpd_set_infoframe(struct omap_dss_device *dssdev,
 		const struct hdmi_avi_infoframe *avi)
 {
@@ -275,13 +226,6 @@ static const struct omapdss_hdmi_ops tpd_hdmi_ops = {
 	.detect			= tpd_detect,
 	.set_infoframe		= tpd_set_infoframe,
 	.set_hdmi_mode		= tpd_set_hdmi_mode,
-
-	.audio_enable		= tpd_audio_enable,
-	.audio_disable		= tpd_audio_disable,
-	.audio_start		= tpd_audio_start,
-	.audio_stop		= tpd_audio_stop,
-	.audio_supported	= tpd_audio_supported,
-	.audio_config		= tpd_audio_config,
 };
 
 static int tpd_probe_pdata(struct platform_device *pdev)
diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index 1db32023396..6a84498ea51 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -166,13 +166,6 @@ enum omap_dss_display_state {
 	OMAP_DSS_DISPLAY_ACTIVE,
 };
 
-enum omap_dss_audio_state {
-	OMAP_DSS_AUDIO_DISABLED = 0,
-	OMAP_DSS_AUDIO_ENABLED,
-	OMAP_DSS_AUDIO_CONFIGURED,
-	OMAP_DSS_AUDIO_PLAYING,
-};
-
 struct omap_dss_audio {
 	struct snd_aes_iec958 *iec;
 	struct snd_cea_861_aud_if *cea;
@@ -635,19 +628,6 @@ struct omapdss_hdmi_ops {
 	int (*set_hdmi_mode)(struct omap_dss_device *dssdev, bool hdmi_mode);
 	int (*set_infoframe)(struct omap_dss_device *dssdev,
 		const struct hdmi_avi_infoframe *avi);
-
-	/*
-	 * Note: These functions might sleep. Do not call while
-	 * holding a spinlock/readlock.
-	 */
-	int (*audio_enable)(struct omap_dss_device *dssdev);
-	void (*audio_disable)(struct omap_dss_device *dssdev);
-	bool (*audio_supported)(struct omap_dss_device *dssdev);
-	int (*audio_config)(struct omap_dss_device *dssdev,
-		struct omap_dss_audio *audio);
-	/* Note: These functions may not sleep */
-	int (*audio_start)(struct omap_dss_device *dssdev);
-	void (*audio_stop)(struct omap_dss_device *dssdev);
 };
 
 struct omapdss_dsi_ops {
@@ -783,8 +763,6 @@ struct omap_dss_device {
 
 	enum omap_dss_display_state state;
 
-	enum omap_dss_audio_state audio_state;
-
 	/* OMAP DSS output specific fields */
 
 	struct list_head list;
@@ -861,24 +839,6 @@ struct omap_dss_driver {
 	int (*set_hdmi_mode)(struct omap_dss_device *dssdev, bool hdmi_mode);
 	int (*set_hdmi_infoframe)(struct omap_dss_device *dssdev,
 		const struct hdmi_avi_infoframe *avi);
-
-	/*
-	 * For display drivers that support audio. This encompasses
-	 * HDMI and DisplayPort at the moment.
-	 */
-	/*
-	 * Note: These functions might sleep. Do not call while
-	 * holding a spinlock/readlock.
-	 */
-	int (*audio_enable)(struct omap_dss_device *dssdev);
-	void (*audio_disable)(struct omap_dss_device *dssdev);
-	bool (*audio_supported)(struct omap_dss_device *dssdev);
-	int (*audio_config)(struct omap_dss_device *dssdev,
-		struct omap_dss_audio *audio);
-	/* Note: These functions may not sleep */
-	int (*audio_start)(struct omap_dss_device *dssdev);
-	void (*audio_stop)(struct omap_dss_device *dssdev);
-
 };
 
 enum omapdss_version omapdss_get_version(void);
-- 
cgit v1.2.3-70-g09d2


From 1cd076bf67793942ed921b766f7d461de2ebc0a2 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Wed, 27 Aug 2014 14:40:58 +0100
Subject: iommu: provide early initialisation hook for IOMMU drivers

IOMMU drivers must be initialised before any of their upstream devices,
otherwise the relevant iommu_ops won't be configured for the bus in
question. To solve this, a number of IOMMU drivers use initcalls to
initialise the driver before anything has a chance to be probed.

Whilst this solves the immediate problem, it leaves the job of probing
the IOMMU completely separate from the iommu_ops to configure the IOMMU,
which are called on a per-bus basis and require the driver to figure out
exactly which instance of the IOMMU is being requested. In particular,
the add_device callback simply passes a struct device to the driver,
which then has to parse firmware tables or probe buses to identify the
relevant IOMMU instance.

This patch takes the first step in addressing this problem by adding an
early initialisation pass for IOMMU drivers, giving them the ability to
store some per-instance data in their iommu_ops structure and store that
in their of_node. This can later be used when parsing OF masters to
identify the IOMMU instance in question.

Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Joerg Roedel <jroedel@suse.de>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 drivers/iommu/of_iommu.c          | 17 +++++++++++++++++
 include/asm-generic/vmlinux.lds.h |  2 ++
 include/linux/iommu.h             |  2 ++
 include/linux/of_iommu.h          | 25 +++++++++++++++++++++++++
 4 files changed, 46 insertions(+)

(limited to 'include')

diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index e550ccb7634..89b90340696 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -22,6 +22,9 @@
 #include <linux/of.h>
 #include <linux/of_iommu.h>
 
+static const struct of_device_id __iommu_of_table_sentinel
+	__used __section(__iommu_of_table_end);
+
 /**
  * of_get_dma_window - Parse *dma-window property and returns 0 if found.
  *
@@ -89,3 +92,17 @@ int of_get_dma_window(struct device_node *dn, const char *prefix, int index,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(of_get_dma_window);
+
+void __init of_iommu_init(void)
+{
+	struct device_node *np;
+	const struct of_device_id *match, *matches = &__iommu_of_table;
+
+	for_each_matching_node_and_match(np, matches, &match) {
+		const of_iommu_init_fn init_fn = match->data;
+
+		if (init_fn(np))
+			pr_err("Failed to initialise IOMMU %s\n",
+				of_node_full_name(np));
+	}
+}
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index aa70cbda327..bee5d683074 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -164,6 +164,7 @@
 #define CLKSRC_OF_TABLES()	OF_TABLE(CONFIG_CLKSRC_OF, clksrc)
 #define IRQCHIP_OF_MATCH_TABLE() OF_TABLE(CONFIG_IRQCHIP, irqchip)
 #define CLK_OF_TABLES()		OF_TABLE(CONFIG_COMMON_CLK, clk)
+#define IOMMU_OF_TABLES()	OF_TABLE(CONFIG_OF_IOMMU, iommu)
 #define RESERVEDMEM_OF_TABLES()	OF_TABLE(CONFIG_OF_RESERVED_MEM, reservedmem)
 #define CPU_METHOD_OF_TABLES()	OF_TABLE(CONFIG_SMP, cpu_method)
 #define EARLYCON_OF_TABLES()	OF_TABLE(CONFIG_SERIAL_EARLYCON, earlycon)
@@ -497,6 +498,7 @@
 	CLK_OF_TABLES()							\
 	RESERVEDMEM_OF_TABLES()						\
 	CLKSRC_OF_TABLES()						\
+	IOMMU_OF_TABLES()						\
 	CPU_METHOD_OF_TABLES()						\
 	KERNEL_DTB()							\
 	IRQCHIP_OF_MATCH_TABLE()					\
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index e6a7c9ff72f..7b83f9f8e11 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -103,6 +103,7 @@ enum iommu_attr {
  * @domain_get_attr: Query domain attributes
  * @domain_set_attr: Change domain attributes
  * @pgsize_bitmap: bitmap of supported page sizes
+ * @priv: per-instance data private to the iommu driver
  */
 struct iommu_ops {
 	bool (*capable)(enum iommu_cap);
@@ -133,6 +134,7 @@ struct iommu_ops {
 	u32 (*domain_get_windows)(struct iommu_domain *domain);
 
 	unsigned long pgsize_bitmap;
+	void *priv;
 };
 
 #define IOMMU_GROUP_NOTIFY_ADD_DEVICE		1 /* Device added */
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index 51a560f34bc..5762cdc8eff 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -1,12 +1,17 @@
 #ifndef __OF_IOMMU_H
 #define __OF_IOMMU_H
 
+#include <linux/iommu.h>
+#include <linux/of.h>
+
 #ifdef CONFIG_OF_IOMMU
 
 extern int of_get_dma_window(struct device_node *dn, const char *prefix,
 			     int index, unsigned long *busno, dma_addr_t *addr,
 			     size_t *size);
 
+extern void of_iommu_init(void);
+
 #else
 
 static inline int of_get_dma_window(struct device_node *dn, const char *prefix,
@@ -16,6 +21,26 @@ static inline int of_get_dma_window(struct device_node *dn, const char *prefix,
 	return -EINVAL;
 }
 
+static inline void of_iommu_init(void) { }
+
 #endif	/* CONFIG_OF_IOMMU */
 
+static inline void of_iommu_set_ops(struct device_node *np,
+				    const struct iommu_ops *ops)
+{
+	np->data = (struct iommu_ops *)ops;
+}
+
+static inline struct iommu_ops *of_iommu_get_ops(struct device_node *np)
+{
+	return np->data;
+}
+
+extern struct of_device_id __iommu_of_table;
+
+typedef int (*of_iommu_init_fn)(struct device_node *);
+
+#define IOMMU_OF_DECLARE(name, compat, fn) \
+	_OF_DECLARE(iommu, name, compat, fn, of_iommu_init_fn)
+
 #endif /* __OF_IOMMU_H */
-- 
cgit v1.2.3-70-g09d2


From a3a60f81ee6f8fa65a57fa186b395bcd1f1bb097 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Wed, 27 Aug 2014 15:49:10 +0100
Subject: dma-mapping: replace set_arch_dma_coherent_ops with
 arch_setup_dma_ops

set_arch_dma_coherent_ops is called from of_dma_configure in order to
swizzle the architectural dma-mapping functions over to a cache-coherent
implementation. This is currently implemented only for ARM.

In anticipation of re-using this mechanism for IOMMU-backed dma-mapping
ops too, this patch replaces the function with a broader
arch_setup_dma_ops callback which will be extended in future.

Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm/include/asm/dma-mapping.h |  8 ++++----
 drivers/of/platform.c              | 31 +++++++++++++------------------
 include/linux/dma-mapping.h        |  7 ++-----
 3 files changed, 19 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 85738b20002..dc3420e7775 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -121,12 +121,12 @@ static inline unsigned long dma_max_pfn(struct device *dev)
 }
 #define dma_max_pfn(dev) dma_max_pfn(dev)
 
-static inline int set_arch_dma_coherent_ops(struct device *dev)
+static inline void arch_setup_dma_ops(struct device *dev, bool coherent)
 {
-	set_dma_ops(dev, &arm_coherent_dma_ops);
-	return 0;
+	if (coherent)
+		set_dma_ops(dev, &arm_coherent_dma_ops);
 }
-#define set_arch_dma_coherent_ops(dev)	set_arch_dma_coherent_ops(dev)
+#define arch_setup_dma_ops arch_setup_dma_ops
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 3b64d0bf5bb..ff1f4e9afcc 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -164,6 +164,8 @@ static void of_dma_configure(struct device *dev)
 {
 	u64 dma_addr, paddr, size;
 	int ret;
+	bool coherent;
+	unsigned long offset;
 
 	/*
 	 * Set default dma-mask to 32 bit. Drivers are expected to setup
@@ -178,28 +180,21 @@ static void of_dma_configure(struct device *dev)
 	if (!dev->dma_mask)
 		dev->dma_mask = &dev->coherent_dma_mask;
 
-	/*
-	 * if dma-coherent property exist, call arch hook to setup
-	 * dma coherent operations.
-	 */
-	if (of_dma_is_coherent(dev->of_node)) {
-		set_arch_dma_coherent_ops(dev);
-		dev_dbg(dev, "device is dma coherent\n");
-	}
-
-	/*
-	 * if dma-ranges property doesn't exist - just return else
-	 * setup the dma offset
-	 */
 	ret = of_dma_get_range(dev->of_node, &dma_addr, &paddr, &size);
 	if (ret < 0) {
-		dev_dbg(dev, "no dma range information to setup\n");
-		return;
+		dma_addr = offset = 0;
+		size = dev->coherent_dma_mask;
+	} else {
+		offset = PFN_DOWN(paddr - dma_addr);
+		dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", dev->dma_pfn_offset);
 	}
+	dev->dma_pfn_offset = offset;
+
+	coherent = of_dma_is_coherent(dev->of_node);
+	dev_dbg(dev, "device is%sdma coherent\n",
+		coherent ? " " : " not ");
 
-	/* DMA ranges found. Calculate and set dma_pfn_offset */
-	dev->dma_pfn_offset = PFN_DOWN(paddr - dma_addr);
-	dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", dev->dma_pfn_offset);
+	arch_setup_dma_ops(dev, coherent);
 }
 
 /**
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index d5d388160f4..8a1560f95d4 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -129,11 +129,8 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask)
 
 extern u64 dma_get_required_mask(struct device *dev);
 
-#ifndef set_arch_dma_coherent_ops
-static inline int set_arch_dma_coherent_ops(struct device *dev)
-{
-	return 0;
-}
+#ifndef arch_setup_dma_ops
+static inline void arch_setup_dma_ops(struct device *dev, bool coherent) { }
 #endif
 
 static inline unsigned int dma_get_max_seg_size(struct device *dev)
-- 
cgit v1.2.3-70-g09d2


From d0f60a44f5120a8e1c48995285c7d8d1e4915b35 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Wed, 27 Aug 2014 16:15:59 +0100
Subject: iommu: add new iommu_ops callback for adding an OF device

This patch adds a new function to the iommu_ops structure to allow an
OF device to be added to a specific IOMMU instance using the recently
merged generic devicetree binding for IOMMUs. The callback (of_xlate)
takes a struct device representing the master and an of_phandle_args
representing the IOMMU and the correspondong IDs for the new master.

Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Joerg Roedel <jroedel@suse.de>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 include/linux/iommu.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 7b83f9f8e11..415c7613d02 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -21,6 +21,7 @@
 
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <linux/of.h>
 #include <linux/types.h>
 #include <trace/events/iommu.h>
 
@@ -102,6 +103,7 @@ enum iommu_attr {
  * @remove_device: remove device from iommu grouping
  * @domain_get_attr: Query domain attributes
  * @domain_set_attr: Change domain attributes
+ * @of_xlate: add OF master IDs to iommu grouping
  * @pgsize_bitmap: bitmap of supported page sizes
  * @priv: per-instance data private to the iommu driver
  */
@@ -133,6 +135,10 @@ struct iommu_ops {
 	/* Get the numer of window per domain */
 	u32 (*domain_get_windows)(struct iommu_domain *domain);
 
+#ifdef CONFIG_OF_IOMMU
+	int (*of_xlate)(struct device *dev, struct of_phandle_args *args);
+#endif
+
 	unsigned long pgsize_bitmap;
 	void *priv;
 };
-- 
cgit v1.2.3-70-g09d2


From 7eba1d51485197fa77c43c42eae3ce04b4b1c1c0 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Wed, 27 Aug 2014 16:20:32 +0100
Subject: iommu: provide helper function to configure an IOMMU for an of master

The generic IOMMU device-tree bindings can be used to add arbitrary OF
masters to an IOMMU with a compliant binding.

This patch introduces of_iommu_configure, which does exactly that.

Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Joerg Roedel <jroedel@suse.de>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 drivers/iommu/Kconfig    |  2 +-
 drivers/iommu/of_iommu.c | 33 +++++++++++++++++++++++++++++++++
 include/linux/of_iommu.h |  6 ++++++
 3 files changed, 40 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index dd5112265cc..6d13f962f15 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -15,7 +15,7 @@ if IOMMU_SUPPORT
 
 config OF_IOMMU
        def_bool y
-       depends on OF
+       depends on OF && IOMMU_API
 
 config FSL_PAMU
 	bool "Freescale IOMMU support"
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 89b90340696..73236d3cc95 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -18,6 +18,7 @@
  */
 
 #include <linux/export.h>
+#include <linux/iommu.h>
 #include <linux/limits.h>
 #include <linux/of.h>
 #include <linux/of_iommu.h>
@@ -93,6 +94,38 @@ int of_get_dma_window(struct device_node *dn, const char *prefix, int index,
 }
 EXPORT_SYMBOL_GPL(of_get_dma_window);
 
+struct iommu_ops *of_iommu_configure(struct device *dev)
+{
+	struct of_phandle_args iommu_spec;
+	struct device_node *np;
+	struct iommu_ops *ops = NULL;
+	int idx = 0;
+
+	/*
+	 * We don't currently walk up the tree looking for a parent IOMMU.
+	 * See the `Notes:' section of
+	 * Documentation/devicetree/bindings/iommu/iommu.txt
+	 */
+	while (!of_parse_phandle_with_args(dev->of_node, "iommus",
+					   "#iommu-cells", idx,
+					   &iommu_spec)) {
+		np = iommu_spec.np;
+		ops = of_iommu_get_ops(np);
+
+		if (!ops || !ops->of_xlate || ops->of_xlate(dev, &iommu_spec))
+			goto err_put_node;
+
+		of_node_put(np);
+		idx++;
+	}
+
+	return ops;
+
+err_put_node:
+	of_node_put(np);
+	return NULL;
+}
+
 void __init of_iommu_init(void)
 {
 	struct device_node *np;
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index 5762cdc8eff..d03abbb11c3 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -1,6 +1,7 @@
 #ifndef __OF_IOMMU_H
 #define __OF_IOMMU_H
 
+#include <linux/device.h>
 #include <linux/iommu.h>
 #include <linux/of.h>
 
@@ -11,6 +12,7 @@ extern int of_get_dma_window(struct device_node *dn, const char *prefix,
 			     size_t *size);
 
 extern void of_iommu_init(void);
+extern struct iommu_ops *of_iommu_configure(struct device *dev);
 
 #else
 
@@ -22,6 +24,10 @@ static inline int of_get_dma_window(struct device_node *dn, const char *prefix,
 }
 
 static inline void of_iommu_init(void) { }
+static inline struct iommu_ops *of_iommu_configure(struct device *dev)
+{
+	return NULL;
+}
 
 #endif	/* CONFIG_OF_IOMMU */
 
-- 
cgit v1.2.3-70-g09d2


From 97890ba9289c66e23f2f2d431937693b6498d6f6 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Wed, 27 Aug 2014 16:24:20 +0100
Subject: dma-mapping: detect and configure IOMMU in of_dma_configure

This patch extends of_dma_configure so that it sets up the IOMMU for a
device, as well as the coherent/non-coherent DMA mapping ops.

Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm/include/asm/dma-mapping.h |  4 +++-
 drivers/of/platform.c              | 21 ++++++++++++++-------
 include/linux/dma-mapping.h        |  8 +++++++-
 3 files changed, 24 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index dc3420e7775..f3c0d953f6a 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -121,7 +121,9 @@ static inline unsigned long dma_max_pfn(struct device *dev)
 }
 #define dma_max_pfn(dev) dma_max_pfn(dev)
 
-static inline void arch_setup_dma_ops(struct device *dev, bool coherent)
+static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
+				      u64 size, struct iommu_ops *iommu,
+				      bool coherent)
 {
 	if (coherent)
 		set_dma_ops(dev, &arm_coherent_dma_ops);
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index ff1f4e9afcc..b89caf8c758 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -19,6 +19,7 @@
 #include <linux/slab.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
+#include <linux/of_iommu.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
@@ -166,6 +167,7 @@ static void of_dma_configure(struct device *dev)
 	int ret;
 	bool coherent;
 	unsigned long offset;
+	struct iommu_ops *iommu;
 
 	/*
 	 * Set default dma-mask to 32 bit. Drivers are expected to setup
@@ -194,7 +196,16 @@ static void of_dma_configure(struct device *dev)
 	dev_dbg(dev, "device is%sdma coherent\n",
 		coherent ? " " : " not ");
 
-	arch_setup_dma_ops(dev, coherent);
+	iommu = of_iommu_configure(dev);
+	dev_dbg(dev, "device is%sbehind an iommu\n",
+		iommu ? " " : " not ");
+
+	arch_setup_dma_ops(dev, dma_addr, size, iommu, coherent);
+}
+
+static void of_dma_deconfigure(struct device *dev)
+{
+	arch_teardown_dma_ops(dev);
 }
 
 /**
@@ -223,16 +234,12 @@ static struct platform_device *of_platform_device_create_pdata(
 	if (!dev)
 		goto err_clear_flag;
 
-	of_dma_configure(&dev->dev);
 	dev->dev.bus = &platform_bus_type;
 	dev->dev.platform_data = platform_data;
-
-	/* We do not fill the DMA ops for platform devices by default.
-	 * This is currently the responsibility of the platform code
-	 * to do such, possibly using a device notifier
-	 */
+	of_dma_configure(&dev->dev);
 
 	if (of_device_add(dev) != 0) {
+		of_dma_deconfigure(&dev->dev);
 		platform_device_put(dev);
 		goto err_clear_flag;
 	}
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 8a1560f95d4..c3007cb4bfa 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -130,7 +130,13 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask)
 extern u64 dma_get_required_mask(struct device *dev);
 
 #ifndef arch_setup_dma_ops
-static inline void arch_setup_dma_ops(struct device *dev, bool coherent) { }
+static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
+				      u64 size, struct iommu_ops *iommu,
+				      bool coherent) { }
+#endif
+
+#ifndef arch_teardown_dma_ops
+static inline void arch_teardown_dma_ops(struct device *dev) { }
 #endif
 
 static inline unsigned int dma_get_max_seg_size(struct device *dev)
-- 
cgit v1.2.3-70-g09d2


From d5735d64e1cebb3748e64f926fa7c35ffabd7afa Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Mon, 17 Nov 2014 09:06:42 -0300
Subject: [media] videodev2.h: improve colorspace support

Add support for the new AdobeRGB and BT.2020 colorspaces as needed for
HDMI 2.0.

Add support to specify the Y'CbCr encoding and quantization range explicitly.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/uapi/linux/videodev2.h | 99 +++++++++++++++++++++++++++++++++++++-----
 1 file changed, 89 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 1c2f84fd4d9..ced659e1b9f 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -178,30 +178,103 @@ enum v4l2_memory {
 
 /* see also http://vektor.theorem.ca/graphics/ycbcr/ */
 enum v4l2_colorspace {
-	/* ITU-R 601 -- broadcast NTSC/PAL */
+	/* SMPTE 170M: used for broadcast NTSC/PAL SDTV */
 	V4L2_COLORSPACE_SMPTE170M     = 1,
 
-	/* 1125-Line (US) HDTV */
+	/* Obsolete pre-1998 SMPTE 240M HDTV standard, superseded by Rec 709 */
 	V4L2_COLORSPACE_SMPTE240M     = 2,
 
-	/* HD and modern captures. */
+	/* Rec.709: used for HDTV */
 	V4L2_COLORSPACE_REC709        = 3,
 
-	/* broken BT878 extents (601, luma range 16-253 instead of 16-235) */
+	/*
+	 * Deprecated, do not use. No driver will ever return this. This was
+	 * based on a misunderstanding of the bt878 datasheet.
+	 */
 	V4L2_COLORSPACE_BT878         = 4,
 
-	/* These should be useful.  Assume 601 extents. */
+	/*
+	 * NTSC 1953 colorspace. This only makes sense when dealing with
+	 * really, really old NTSC recordings. Superseded by SMPTE 170M.
+	 */
 	V4L2_COLORSPACE_470_SYSTEM_M  = 5,
+
+	/*
+	 * EBU Tech 3213 PAL/SECAM colorspace. This only makes sense when
+	 * dealing with really old PAL/SECAM recordings. Superseded by
+	 * SMPTE 170M.
+	 */
 	V4L2_COLORSPACE_470_SYSTEM_BG = 6,
 
-	/* I know there will be cameras that send this.  So, this is
-	 * unspecified chromaticities and full 0-255 on each of the
-	 * Y'CbCr components
+	/*
+	 * Effectively shorthand for V4L2_COLORSPACE_SRGB, V4L2_YCBCR_ENC_601
+	 * and V4L2_QUANTIZATION_FULL_RANGE. To be used for (Motion-)JPEG.
 	 */
 	V4L2_COLORSPACE_JPEG          = 7,
 
-	/* For RGB colourspaces, this is probably a good start. */
+	/* For RGB colorspaces such as produces by most webcams. */
 	V4L2_COLORSPACE_SRGB          = 8,
+
+	/* AdobeRGB colorspace */
+	V4L2_COLORSPACE_ADOBERGB      = 9,
+
+	/* BT.2020 colorspace, used for UHDTV. */
+	V4L2_COLORSPACE_BT2020        = 10,
+};
+
+enum v4l2_ycbcr_encoding {
+	/*
+	 * Mapping of V4L2_YCBCR_ENC_DEFAULT to actual encodings for the
+	 * various colorspaces:
+	 *
+	 * V4L2_COLORSPACE_SMPTE170M, V4L2_COLORSPACE_470_SYSTEM_M,
+	 * V4L2_COLORSPACE_470_SYSTEM_BG, V4L2_COLORSPACE_ADOBERGB and
+	 * V4L2_COLORSPACE_JPEG: V4L2_YCBCR_ENC_601
+	 *
+	 * V4L2_COLORSPACE_REC709: V4L2_YCBCR_ENC_709
+	 *
+	 * V4L2_COLORSPACE_SRGB: V4L2_YCBCR_ENC_SYCC
+	 *
+	 * V4L2_COLORSPACE_BT2020: V4L2_YCBCR_ENC_BT2020
+	 *
+	 * V4L2_COLORSPACE_SMPTE240M: V4L2_YCBCR_ENC_SMPTE240M
+	 */
+	V4L2_YCBCR_ENC_DEFAULT        = 0,
+
+	/* ITU-R 601 -- SDTV */
+	V4L2_YCBCR_ENC_601            = 1,
+
+	/* Rec. 709 -- HDTV */
+	V4L2_YCBCR_ENC_709            = 2,
+
+	/* ITU-R 601/EN 61966-2-4 Extended Gamut -- SDTV */
+	V4L2_YCBCR_ENC_XV601          = 3,
+
+	/* Rec. 709/EN 61966-2-4 Extended Gamut -- HDTV */
+	V4L2_YCBCR_ENC_XV709          = 4,
+
+	/* sYCC (Y'CbCr encoding of sRGB) */
+	V4L2_YCBCR_ENC_SYCC           = 5,
+
+	/* BT.2020 Non-constant Luminance Y'CbCr */
+	V4L2_YCBCR_ENC_BT2020         = 6,
+
+	/* BT.2020 Constant Luminance Y'CbcCrc */
+	V4L2_YCBCR_ENC_BT2020_CONST_LUM = 7,
+
+	/* SMPTE 240M -- Obsolete HDTV */
+	V4L2_YCBCR_ENC_SMPTE240M      = 8,
+};
+
+enum v4l2_quantization {
+	/*
+	 * The default for R'G'B' quantization is always full range. For
+	 * Y'CbCr the quantization is always limited range, except for
+	 * SYCC, XV601, XV709 or JPEG: those are full range.
+	 */
+	V4L2_QUANTIZATION_DEFAULT     = 0,
+	V4L2_QUANTIZATION_FULL_RANGE  = 1,
+	V4L2_QUANTIZATION_LIM_RANGE   = 2,
 };
 
 enum v4l2_priority {
@@ -294,6 +367,8 @@ struct v4l2_pix_format {
 	__u32			colorspace;	/* enum v4l2_colorspace */
 	__u32			priv;		/* private data, depends on pixelformat */
 	__u32			flags;		/* format flags (V4L2_PIX_FMT_FLAG_*) */
+	__u32			ycbcr_enc;	/* enum v4l2_ycbcr_encoding */
+	__u32			quantization;	/* enum v4l2_quantization */
 };
 
 /*      Pixel format         FOURCC                          depth  Description  */
@@ -1777,6 +1852,8 @@ struct v4l2_plane_pix_format {
  * @plane_fmt:		per-plane information
  * @num_planes:		number of planes for this format
  * @flags:		format flags (V4L2_PIX_FMT_FLAG_*)
+ * @ycbcr_enc:		enum v4l2_ycbcr_encoding, Y'CbCr encoding
+ * @quantization:	enum v4l2_quantization, colorspace quantization
  */
 struct v4l2_pix_format_mplane {
 	__u32				width;
@@ -1788,7 +1865,9 @@ struct v4l2_pix_format_mplane {
 	struct v4l2_plane_pix_format	plane_fmt[VIDEO_MAX_PLANES];
 	__u8				num_planes;
 	__u8				flags;
-	__u8				reserved[10];
+	__u8				ycbcr_enc;
+	__u8				quantization;
+	__u8				reserved[8];
 } __attribute__ ((packed));
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 11ff030c73655ecd7b153c6bd00d26d27e6cc199 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Mon, 17 Nov 2014 09:10:33 -0300
Subject: [media] v4l2-mediabus: improve colorspace support

Add and copy the new ycbcr_enc and quantization fields.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/v4l2-mediabus.h      | 4 ++++
 include/uapi/linux/v4l2-mediabus.h | 6 +++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h
index 59d7397fb0e..38d960d8dcc 100644
--- a/include/media/v4l2-mediabus.h
+++ b/include/media/v4l2-mediabus.h
@@ -94,6 +94,8 @@ static inline void v4l2_fill_pix_format(struct v4l2_pix_format *pix_fmt,
 	pix_fmt->height = mbus_fmt->height;
 	pix_fmt->field = mbus_fmt->field;
 	pix_fmt->colorspace = mbus_fmt->colorspace;
+	pix_fmt->ycbcr_enc = mbus_fmt->ycbcr_enc;
+	pix_fmt->quantization = mbus_fmt->quantization;
 }
 
 static inline void v4l2_fill_mbus_format(struct v4l2_mbus_framefmt *mbus_fmt,
@@ -104,6 +106,8 @@ static inline void v4l2_fill_mbus_format(struct v4l2_mbus_framefmt *mbus_fmt,
 	mbus_fmt->height = pix_fmt->height;
 	mbus_fmt->field = pix_fmt->field;
 	mbus_fmt->colorspace = pix_fmt->colorspace;
+	mbus_fmt->ycbcr_enc = pix_fmt->ycbcr_enc;
+	mbus_fmt->quantization = pix_fmt->quantization;
 	mbus_fmt->code = code;
 }
 
diff --git a/include/uapi/linux/v4l2-mediabus.h b/include/uapi/linux/v4l2-mediabus.h
index b1934a3961e..5a86d8ede09 100644
--- a/include/uapi/linux/v4l2-mediabus.h
+++ b/include/uapi/linux/v4l2-mediabus.h
@@ -22,6 +22,8 @@
  * @code:	data format code (from enum v4l2_mbus_pixelcode)
  * @field:	used interlacing type (from enum v4l2_field)
  * @colorspace:	colorspace of the data (from enum v4l2_colorspace)
+ * @ycbcr_enc:	YCbCr encoding of the data (from enum v4l2_ycbcr_encoding)
+ * @quantization: quantization of the data (from enum v4l2_quantization)
  */
 struct v4l2_mbus_framefmt {
 	__u32			width;
@@ -29,7 +31,9 @@ struct v4l2_mbus_framefmt {
 	__u32			code;
 	__u32			field;
 	__u32			colorspace;
-	__u32			reserved[7];
+	__u32			ycbcr_enc;
+	__u32			quantization;
+	__u32			reserved[5];
 };
 
 #ifndef __KERNEL__
-- 
cgit v1.2.3-70-g09d2


From 8f73110f6bac043026bc923b0a66abe24dd48058 Mon Sep 17 00:00:00 2001
From: Romain Perier <romain.perier@gmail.com>
Date: Tue, 25 Nov 2014 12:28:25 +0000
Subject: of: Rename "poweroff-source" property to "system-power-controller"

It reverts commit a4b4e0461ec5 ("of: Add standard property for poweroff capability").
As discussed on the mailing list, it makes more sense to rename back to the
old established property name, without the vendor prefix. Problem being that
the word "source" usually tends to be used for inputs and that is out of control
of the OS. The poweroff capability is an output which simply turns the
system-power off. Also, this property might be used by drivers which power-off
the system and power back on subsequent RTC alarms. This seems to suggest to
remove "poweroff" from the property name and to choose "system-power-controller"
as the more generic name. This patchs adds the required renaming changes and
defines an helper function which checks if this property is set.

Signed-off-by: Romain Perier <romain.perier@gmail.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
Acked-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/power/power-controller.txt     | 18 ++++++++++++++++++
 Documentation/devicetree/bindings/power/poweroff.txt   | 18 ------------------
 .../bindings/regulator/act8865-regulator.txt           |  4 ++--
 drivers/regulator/act8865-regulator.c                  |  2 +-
 include/linux/of.h                                     |  6 +++---
 5 files changed, 24 insertions(+), 24 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/power/power-controller.txt
 delete mode 100644 Documentation/devicetree/bindings/power/poweroff.txt

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/power/power-controller.txt b/Documentation/devicetree/bindings/power/power-controller.txt
new file mode 100644
index 00000000000..845868bf327
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/power-controller.txt
@@ -0,0 +1,18 @@
+* Generic Poweroff capability
+
+Power-management integrated circuits or miscellaneous harware components are
+sometimes able to control the system power. The device driver associated to these
+components might needs to define poweroff capability, which tells to the kernel
+how to switch off the system. The corresponding driver must have the standard
+property "poweroff-source" in its device node. This property marks the device as
+able to shutdown the system. In order to test if this property is found
+programmatically, use the helper function "of_system_has_poweroff_source" from
+of.h .
+
+Example:
+
+act8846: act8846@5 {
+	 compatible = "active-semi,act8846";
+	 status = "okay";
+	 poweroff-source;
+}
diff --git a/Documentation/devicetree/bindings/power/poweroff.txt b/Documentation/devicetree/bindings/power/poweroff.txt
deleted file mode 100644
index 845868bf327..00000000000
--- a/Documentation/devicetree/bindings/power/poweroff.txt
+++ /dev/null
@@ -1,18 +0,0 @@
-* Generic Poweroff capability
-
-Power-management integrated circuits or miscellaneous harware components are
-sometimes able to control the system power. The device driver associated to these
-components might needs to define poweroff capability, which tells to the kernel
-how to switch off the system. The corresponding driver must have the standard
-property "poweroff-source" in its device node. This property marks the device as
-able to shutdown the system. In order to test if this property is found
-programmatically, use the helper function "of_system_has_poweroff_source" from
-of.h .
-
-Example:
-
-act8846: act8846@5 {
-	 compatible = "active-semi,act8846";
-	 status = "okay";
-	 poweroff-source;
-}
diff --git a/Documentation/devicetree/bindings/regulator/act8865-regulator.txt b/Documentation/devicetree/bindings/regulator/act8865-regulator.txt
index 01a5b0766e5..dad6358074a 100644
--- a/Documentation/devicetree/bindings/regulator/act8865-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/act8865-regulator.txt
@@ -6,8 +6,8 @@ Required properties:
 - reg: I2C slave address
 
 Optional properties:
-- poweroff-source: Telling whether or not this pmic is controlling
-  the system power. See Documentation/devicetree/bindings/power/poweroff.txt .
+- system-power-controller: Telling whether or not this pmic is controlling
+  the system power. See Documentation/devicetree/bindings/power/power-controller.txt .
 
 Any standard regulator properties can be used to configure the single regulator.
 
diff --git a/drivers/regulator/act8865-regulator.c b/drivers/regulator/act8865-regulator.c
index 76301ed0f8d..9eec453b745 100644
--- a/drivers/regulator/act8865-regulator.c
+++ b/drivers/regulator/act8865-regulator.c
@@ -365,7 +365,7 @@ static int act8865_pmic_probe(struct i2c_client *client,
 		return ret;
 	}
 
-	if (of_system_has_poweroff_source(dev->of_node)) {
+	if (of_device_is_system_power_controller(dev->of_node)) {
 		if (!pm_power_off) {
 			act8865_i2c_client = client;
 			act8865->off_reg = off_reg;
diff --git a/include/linux/of.h b/include/linux/of.h
index 27b3ba1e9e5..25767725661 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -867,14 +867,14 @@ static inline int of_changeset_update_property(struct of_changeset *ocs,
 extern int of_resolve_phandles(struct device_node *tree);
 
 /**
- * of_system_has_poweroff_source - Tells if poweroff-source is found for device_node
+ * of_device_is_system_power_controller - Tells if system-power-controller is found for device_node
  * @np: Pointer to the given device_node
  *
  * return true if present false otherwise
  */
-static inline bool of_system_has_poweroff_source(const struct device_node *np)
+static inline bool of_device_is_system_power_controller(const struct device_node *np)
 {
-	return of_property_read_bool(np, "poweroff-source");
+	return of_property_read_bool(np, "system-power-controller");
 }
 
 #endif /* _LINUX_OF_H */
-- 
cgit v1.2.3-70-g09d2


From 8d65ef760d50cc625c5364cba89be838b21c66a7 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Mon, 17 Nov 2014 17:02:57 -0500
Subject: sunrpc: eliminate the XPT_DETACHED flag

All it does is indicate whether a xprt has already been deleted from
a list or not, which is unnecessary since we use list_del_init and it's
always set and checked under the sv_lock anyway.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_xprt.h | 7 +++----
 net/sunrpc/svc_xprt.c           | 4 +---
 2 files changed, 4 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index ce6e4182a5b..79f6f8f3dc0 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -63,10 +63,9 @@ struct svc_xprt {
 #define	XPT_CHNGBUF	7		/* need to change snd/rcv buf sizes */
 #define	XPT_DEFERRED	8		/* deferred request pending */
 #define	XPT_OLD		9		/* used for xprt aging mark+sweep */
-#define	XPT_DETACHED	10		/* detached from tempsocks list */
-#define XPT_LISTENER	11		/* listening endpoint */
-#define XPT_CACHE_AUTH	12		/* cache auth info */
-#define XPT_LOCAL	13		/* connection from loopback interface */
+#define XPT_LISTENER	10		/* listening endpoint */
+#define XPT_CACHE_AUTH	11		/* cache auth info */
+#define XPT_LOCAL	12		/* connection from loopback interface */
 
 	struct svc_serv		*xpt_server;	/* service for transport */
 	atomic_t    	    	xpt_reserved;	/* space on outq that is rsvd */
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index c179ca2a5aa..97a75c17142 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -884,7 +884,6 @@ static void svc_age_temp_xprts(unsigned long closure)
 			continue;
 		list_del_init(le);
 		set_bit(XPT_CLOSE, &xprt->xpt_flags);
-		set_bit(XPT_DETACHED, &xprt->xpt_flags);
 		dprintk("queuing xprt %p for closing\n", xprt);
 
 		/* a thread will dequeue and close it soon */
@@ -924,8 +923,7 @@ static void svc_delete_xprt(struct svc_xprt *xprt)
 	xprt->xpt_ops->xpo_detach(xprt);
 
 	spin_lock_bh(&serv->sv_lock);
-	if (!test_and_set_bit(XPT_DETACHED, &xprt->xpt_flags))
-		list_del_init(&xprt->xpt_list);
+	list_del_init(&xprt->xpt_list);
 	WARN_ON_ONCE(!list_empty(&xprt->xpt_ready));
 	if (test_bit(XPT_TEMP, &xprt->xpt_flags))
 		serv->sv_tmpcnt--;
-- 
cgit v1.2.3-70-g09d2


From dabb05c6670e6e4415d7b56cd5864a5dbd90207f Mon Sep 17 00:00:00 2001
From: Mathieu Magnaudet <mathieu.magnaudet@gmail.com>
Date: Thu, 27 Nov 2014 16:02:36 +0100
Subject: HID: make hid_report_len as a static inline function in hid.h

In several hid drivers it is necessary to calculate the length of an
hid_report. This patch exports the existing static function hid_report_len of
hid-core.c as an inline function in hid.h

Signed-off-by: Mathieu Magnaudet <mathieu.magnaudet@enac.fr>
Reviewed-by: Benjamin Tissoires <benjamin.tissoires@gmail.com>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-core.c        |  6 ------
 drivers/hid/hid-input.c       |  2 +-
 drivers/hid/hid-multitouch.c  |  2 +-
 drivers/hid/usbhid/hid-core.c |  3 +--
 drivers/hid/wacom_sys.c       |  8 +-------
 include/linux/hid.h           | 11 +++++++++++
 6 files changed, 15 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 3402033fa52..ee6ba7625e7 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1280,12 +1280,6 @@ void hid_output_report(struct hid_report *report, __u8 *data)
 }
 EXPORT_SYMBOL_GPL(hid_output_report);
 
-static int hid_report_len(struct hid_report *report)
-{
-	/* equivalent to DIV_ROUND_UP(report->size, 8) + !!(report->id > 0) */
-	return ((report->size - 1) >> 3) + 1 + (report->id > 0);
-}
-
 /*
  * Allocator for buffer that is going to be passed to hid_output_report()
  */
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 725f22ca47f..1e95f4df414 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -1215,7 +1215,7 @@ static void hidinput_led_worker(struct work_struct *work)
 		return hid->ll_driver->request(hid, report, HID_REQ_SET_REPORT);
 
 	/* fall back to generic raw-output-report */
-	len = ((report->size - 1) >> 3) + 1 + (report->id > 0);
+	len = hid_report_len(report);
 	buf = hid_alloc_report_buf(report, GFP_KERNEL);
 	if (!buf)
 		return;
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 683cda6c60c..f65e78b4699 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -827,7 +827,7 @@ static void mt_set_input_mode(struct hid_device *hdev)
 	r = re->report_id_hash[td->inputmode];
 	if (r) {
 		if (cls->quirks & MT_QUIRK_FORCE_GET_FEATURE) {
-			report_len = ((r->size - 1) >> 3) + 1 + (r->id > 0);
+			report_len = hid_report_len(r);
 			buf = hid_alloc_report_buf(r, GFP_KERNEL);
 			if (!buf) {
 				hid_err(hdev, "failed to allocate buffer for report\n");
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index ca6849a0121..b6cb7a5e4b2 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -338,8 +338,7 @@ static int hid_submit_out(struct hid_device *hid)
 	report = usbhid->out[usbhid->outtail].report;
 	raw_report = usbhid->out[usbhid->outtail].raw_report;
 
-	usbhid->urbout->transfer_buffer_length = ((report->size - 1) >> 3) +
-						 1 + (report->id > 0);
+	usbhid->urbout->transfer_buffer_length = hid_report_len(report);
 	usbhid->urbout->dev = hid_to_usb_dev(hid);
 	if (raw_report) {
 		memcpy(usbhid->outbuf, raw_report,
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 8593047bb72..8e02a4a6fde 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -1321,12 +1321,6 @@ static void wacom_calculate_res(struct wacom_features *features)
 						    features->unitExpo);
 }
 
-static int wacom_hid_report_len(struct hid_report *report)
-{
-	/* equivalent to DIV_ROUND_UP(report->size, 8) + !!(report->id > 0) */
-	return ((report->size - 1) >> 3) + 1 + (report->id > 0);
-}
-
 static size_t wacom_compute_pktlen(struct hid_device *hdev)
 {
 	struct hid_report_enum *report_enum;
@@ -1336,7 +1330,7 @@ static size_t wacom_compute_pktlen(struct hid_device *hdev)
 	report_enum = hdev->report_enum + HID_INPUT_REPORT;
 
 	list_for_each_entry(report, &report_enum->report_list, list) {
-		size_t report_size = wacom_hid_report_len(report);
+		size_t report_size = hid_report_len(report);
 		if (report_size > size)
 			size = report_size;
 	}
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 78ea9bf941c..2366fda010c 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -1063,6 +1063,17 @@ static inline void hid_hw_wait(struct hid_device *hdev)
 		hdev->ll_driver->wait(hdev);
 }
 
+/**
+ * hid_report_len - calculate the report length
+ *
+ * @report: the report we want to know the length
+ */
+static inline int hid_report_len(struct hid_report *report)
+{
+	/* equivalent to DIV_ROUND_UP(report->size, 8) + !!(report->id > 0) */
+	return ((report->size - 1) >> 3) + 1 + (report->id > 0);
+}
+
 int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, int size,
 		int interrupt);
 
-- 
cgit v1.2.3-70-g09d2


From c50f13c672df758b59e026c15b9118f3ed46edc4 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 1 Dec 2014 23:50:16 +0100
Subject: ACPICA: Save current masks of enabled GPEs after enable register
 writes

There is a race condition between acpi_hw_disable_all_gpes() or
acpi_enable_all_wakeup_gpes() and acpi_ev_asynch_enable_gpe() such
that if the latter wins the race, it may mistakenly enable a GPE
disabled by the former.  This may lead to premature system wakeups
during system suspend and potentially to more serious consequences.

The source of the problem is how acpi_hw_low_set_gpe() works when
passed ACPI_GPE_CONDITIONAL_ENABLE as the second argument.  In that
case, the GPE will be enabled if the corresponding bit is set in the
enable_for_run mask of the GPE enable register containing that bit.
However, acpi_hw_disable_all_gpes() and acpi_enable_all_wakeup_gpes()
don't modify the enable_for_run masks of GPE registers when writing
to them.  In consequence, if acpi_ev_asynch_enable_gpe(), which
eventually calls acpi_hw_low_set_gpe() with the second argument
equal to ACPI_GPE_CONDITIONAL_ENABLE, is executed in parallel with
one of these functions, it may reverse changes made by them.

To fix the problem, introduce a new enable_mask field in struct
acpi_gpe_register_info in which to store the current mask of
enabled GPEs and modify acpi_hw_low_set_gpe() to take this
mask into account instead of enable_for_run when its second
argument is equal to ACPI_GPE_CONDITIONAL_ENABLE.  Also modify
the low-level routines called by acpi_hw_disable_all_gpes(),
acpi_enable_all_wakeup_gpes() and acpi_enable_all_runtime_gpes()
to update the enable_mask masks of GPE registers after all
(successful) writes to those registers.

Acked-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/aclocal.h |  1 +
 drivers/acpi/acpica/evgpe.c   |  6 ++---
 drivers/acpi/acpica/hwgpe.c   | 53 +++++++++++++++++++++++++++++++++++--------
 include/acpi/actypes.h        |  4 ++++
 4 files changed, 51 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 80c74e90f3c..680d23bbae7 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -454,6 +454,7 @@ struct acpi_gpe_register_info {
 	u16 base_gpe_number;	/* Base GPE number for this register */
 	u8 enable_for_wake;	/* GPEs to keep enabled when sleeping */
 	u8 enable_for_run;	/* GPEs to keep enabled when running */
+	u8 enable_mask;		/* Current mask of enabled GPEs */
 };
 
 /*
diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index 2095dfb72bc..81db932b15e 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -134,7 +134,7 @@ acpi_status acpi_ev_enable_gpe(struct acpi_gpe_event_info *gpe_event_info)
 
 	/* Enable the requested GPE */
 
-	status = acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_ENABLE);
+	status = acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_ENABLE_SAVE);
 	return_ACPI_STATUS(status);
 }
 
@@ -213,7 +213,7 @@ acpi_ev_remove_gpe_reference(struct acpi_gpe_event_info *gpe_event_info)
 		if (ACPI_SUCCESS(status)) {
 			status =
 			    acpi_hw_low_set_gpe(gpe_event_info,
-						ACPI_GPE_DISABLE);
+						ACPI_GPE_DISABLE_SAVE);
 		}
 
 		if (ACPI_FAILURE(status)) {
@@ -655,7 +655,7 @@ acpi_status acpi_ev_finish_gpe(struct acpi_gpe_event_info * gpe_event_info)
 
 	/*
 	 * Enable this GPE, conditionally. This means that the GPE will
-	 * only be physically enabled if the enable_for_run bit is set
+	 * only be physically enabled if the enable_mask bit is set
 	 * in the event_info.
 	 */
 	(void)acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_CONDITIONAL_ENABLE);
diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c
index 48ac7b7b59c..494027f5c06 100644
--- a/drivers/acpi/acpica/hwgpe.c
+++ b/drivers/acpi/acpica/hwgpe.c
@@ -115,12 +115,12 @@ acpi_hw_low_set_gpe(struct acpi_gpe_event_info *gpe_event_info, u32 action)
 	/* Set or clear just the bit that corresponds to this GPE */
 
 	register_bit = acpi_hw_get_gpe_register_bit(gpe_event_info);
-	switch (action) {
+	switch (action & ~ACPI_GPE_SAVE_MASK) {
 	case ACPI_GPE_CONDITIONAL_ENABLE:
 
-		/* Only enable if the enable_for_run bit is set */
+		/* Only enable if the corresponding enable_mask bit is set */
 
-		if (!(register_bit & gpe_register_info->enable_for_run)) {
+		if (!(register_bit & gpe_register_info->enable_mask)) {
 			return (AE_BAD_PARAMETER);
 		}
 
@@ -145,6 +145,9 @@ acpi_hw_low_set_gpe(struct acpi_gpe_event_info *gpe_event_info, u32 action)
 	/* Write the updated enable mask */
 
 	status = acpi_hw_write(enable_mask, &gpe_register_info->enable_address);
+	if (ACPI_SUCCESS(status) && (action & ACPI_GPE_SAVE_MASK)) {
+		gpe_register_info->enable_mask = enable_mask;
+	}
 	return (status);
 }
 
@@ -260,6 +263,32 @@ acpi_hw_get_gpe_status(struct acpi_gpe_event_info * gpe_event_info,
 	return (AE_OK);
 }
 
+/******************************************************************************
+ *
+ * FUNCTION:    acpi_hw_gpe_enable_write
+ *
+ * PARAMETERS:  enable_mask         - Bit mask to write to the GPE register
+ *              gpe_register_info   - Gpe Register info
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Write the enable mask byte to the given GPE register.
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_hw_gpe_enable_write(u8 enable_mask,
+			 struct acpi_gpe_register_info *gpe_register_info)
+{
+	acpi_status status;
+
+	status = acpi_hw_write(enable_mask, &gpe_register_info->enable_address);
+	if (ACPI_SUCCESS(status)) {
+		gpe_register_info->enable_mask = enable_mask;
+	}
+	return (status);
+}
+
 /******************************************************************************
  *
  * FUNCTION:    acpi_hw_disable_gpe_block
@@ -287,8 +316,8 @@ acpi_hw_disable_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 		/* Disable all GPEs in this register */
 
 		status =
-		    acpi_hw_write(0x00,
-				  &gpe_block->register_info[i].enable_address);
+		    acpi_hw_gpe_enable_write(0x00,
+					     &gpe_block->register_info[i]);
 		if (ACPI_FAILURE(status)) {
 			return (status);
 		}
@@ -355,21 +384,23 @@ acpi_hw_enable_runtime_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 {
 	u32 i;
 	acpi_status status;
+	struct acpi_gpe_register_info *gpe_register_info;
 
 	/* NOTE: assumes that all GPEs are currently disabled */
 
 	/* Examine each GPE Register within the block */
 
 	for (i = 0; i < gpe_block->register_count; i++) {
-		if (!gpe_block->register_info[i].enable_for_run) {
+		gpe_register_info = &gpe_block->register_info[i];
+		if (!gpe_register_info->enable_for_run) {
 			continue;
 		}
 
 		/* Enable all "runtime" GPEs in this register */
 
 		status =
-		    acpi_hw_write(gpe_block->register_info[i].enable_for_run,
-				  &gpe_block->register_info[i].enable_address);
+		    acpi_hw_gpe_enable_write(gpe_register_info->enable_for_run,
+					     gpe_register_info);
 		if (ACPI_FAILURE(status)) {
 			return (status);
 		}
@@ -399,10 +430,12 @@ acpi_hw_enable_wakeup_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 {
 	u32 i;
 	acpi_status status;
+	struct acpi_gpe_register_info *gpe_register_info;
 
 	/* Examine each GPE Register within the block */
 
 	for (i = 0; i < gpe_block->register_count; i++) {
+		gpe_register_info = &gpe_block->register_info[i];
 
 		/*
 		 * Enable all "wake" GPEs in this register and disable the
@@ -410,8 +443,8 @@ acpi_hw_enable_wakeup_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 		 */
 
 		status =
-		    acpi_hw_write(gpe_block->register_info[i].enable_for_wake,
-				  &gpe_block->register_info[i].enable_address);
+		    acpi_hw_gpe_enable_write(gpe_register_info->enable_for_wake,
+					     gpe_register_info);
 		if (ACPI_FAILURE(status)) {
 			return (status);
 		}
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 7000e66f768..bbef17368e4 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -736,6 +736,10 @@ typedef u32 acpi_event_status;
 #define ACPI_GPE_ENABLE                 0
 #define ACPI_GPE_DISABLE                1
 #define ACPI_GPE_CONDITIONAL_ENABLE     2
+#define ACPI_GPE_SAVE_MASK              4
+
+#define ACPI_GPE_ENABLE_SAVE            (ACPI_GPE_ENABLE | ACPI_GPE_SAVE_MASK)
+#define ACPI_GPE_DISABLE_SAVE           (ACPI_GPE_DISABLE | ACPI_GPE_SAVE_MASK)
 
 /*
  * GPE info flags - Per GPE
-- 
cgit v1.2.3-70-g09d2


From 40af86a40cdcabd48ab9636fe13d6763a7d74bc9 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Thu, 13 Nov 2014 00:30:23 +0100
Subject: NFC: st21nfca: Remove gpio_irq field in static and dts configuration

- phy->gpio_irq is never done out of the request resources.
- irq_of_parse_and_map is already done in the i2c core so client->irq is
already set when entering in st21nfca_hci_i2c_of_request_resources
- In case of static platform configuration client->irq can be set directly
- It simplifies the code a bit.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/st21nfca/i2c.c             | 30 +-----------------------------
 include/linux/platform_data/st21nfca.h |  1 -
 2 files changed, 1 insertion(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c
index 22bc8c2311c..44e1c769e33 100644
--- a/drivers/nfc/st21nfca/i2c.c
+++ b/drivers/nfc/st21nfca/i2c.c
@@ -72,7 +72,6 @@ struct st21nfca_i2c_phy {
 	struct nfc_hci_dev *hdev;
 
 	unsigned int gpio_ena;
-	unsigned int gpio_irq;
 	unsigned int irq_polarity;
 
 	struct sk_buff *pending_skb;
@@ -536,15 +535,7 @@ static int st21nfca_hci_i2c_of_request_resources(struct i2c_client *client)
 
 	phy->gpio_ena = gpio;
 
-	/* IRQ */
-	r = irq_of_parse_and_map(pp, 0);
-	if (r < 0) {
-		nfc_err(&client->dev, "Unable to get irq, error: %d\n", r);
-		return r;
-	}
-
-	phy->irq_polarity = irq_get_trigger_type(r);
-	client->irq = r;
+	phy->irq_polarity = irq_get_trigger_type(client->irq);
 
 	return 0;
 }
@@ -560,7 +551,6 @@ static int st21nfca_hci_i2c_request_resources(struct i2c_client *client)
 	struct st21nfca_nfc_platform_data *pdata;
 	struct st21nfca_i2c_phy *phy = i2c_get_clientdata(client);
 	int r;
-	int irq;
 
 	pdata = client->dev.platform_data;
 	if (pdata == NULL) {
@@ -569,17 +559,9 @@ static int st21nfca_hci_i2c_request_resources(struct i2c_client *client)
 	}
 
 	/* store for later use */
-	phy->gpio_irq = pdata->gpio_irq;
 	phy->gpio_ena = pdata->gpio_ena;
 	phy->irq_polarity = pdata->irq_polarity;
 
-	r = devm_gpio_request_one(&client->dev, phy->gpio_irq, GPIOF_IN,
-				  "wake_up");
-	if (r) {
-		pr_err("%s : gpio_request failed\n", __FILE__);
-		return -ENODEV;
-	}
-
 	if (phy->gpio_ena > 0) {
 		r = devm_gpio_request_one(&client->dev, phy->gpio_ena,
 					  GPIOF_OUT_INIT_HIGH, "clf_enable");
@@ -589,16 +571,6 @@ static int st21nfca_hci_i2c_request_resources(struct i2c_client *client)
 		}
 	}
 
-	/* IRQ */
-	irq = gpio_to_irq(phy->gpio_irq);
-	if (irq < 0) {
-		nfc_err(&client->dev,
-				"Unable to get irq number for GPIO %d error %d\n",
-				phy->gpio_irq, r);
-		return -ENODEV;
-	}
-	client->irq = irq;
-
 	return 0;
 }
 
diff --git a/include/linux/platform_data/st21nfca.h b/include/linux/platform_data/st21nfca.h
index 1730312398f..5087fff96d8 100644
--- a/include/linux/platform_data/st21nfca.h
+++ b/include/linux/platform_data/st21nfca.h
@@ -24,7 +24,6 @@
 #define ST21NFCA_HCI_DRIVER_NAME "st21nfca_hci"
 
 struct st21nfca_nfc_platform_data {
-	unsigned int gpio_irq;
 	unsigned int gpio_ena;
 	unsigned int irq_polarity;
 };
-- 
cgit v1.2.3-70-g09d2


From a80d0cb6f6addc5a1f3852466fe8d37ca4fe1350 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Thu, 13 Nov 2014 00:30:26 +0100
Subject: NFC: st21nfcb: Remove gpio_irq field in static and dts configuration

- phy->gpio_irq is never done out of the request resources.
- irq_of_parse_and_map is already done in the i2c core so client->irq is
already set when entering in st21nfcb_hci_i2c_of_request_resources
- In case of static platform configuration client->irq can be set directly.
- It simplifies the code a bit.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/st21nfcb/i2c.c             | 30 +-----------------------------
 include/linux/platform_data/st21nfcb.h |  1 -
 2 files changed, 1 insertion(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/nfc/st21nfcb/i2c.c b/drivers/nfc/st21nfcb/i2c.c
index 73f7ddef57c..e0c4901936f 100644
--- a/drivers/nfc/st21nfcb/i2c.c
+++ b/drivers/nfc/st21nfcb/i2c.c
@@ -50,7 +50,6 @@ struct st21nfcb_i2c_phy {
 	struct i2c_client *i2c_dev;
 	struct llt_ndlc *ndlc;
 
-	unsigned int gpio_irq;
 	unsigned int gpio_reset;
 	unsigned int irq_polarity;
 
@@ -262,15 +261,7 @@ static int st21nfcb_nci_i2c_of_request_resources(struct i2c_client *client)
 	}
 	phy->gpio_reset = gpio;
 
-	/* IRQ */
-	r = irq_of_parse_and_map(pp, 0);
-	if (r < 0) {
-		nfc_err(&client->dev, "Unable to get irq, error: %d\n", r);
-		return r;
-	}
-
-	phy->irq_polarity = irq_get_trigger_type(r);
-	client->irq = r;
+	phy->irq_polarity = irq_get_trigger_type(client->irq);
 
 	return 0;
 }
@@ -286,7 +277,6 @@ static int st21nfcb_nci_i2c_request_resources(struct i2c_client *client)
 	struct st21nfcb_nfc_platform_data *pdata;
 	struct st21nfcb_i2c_phy *phy = i2c_get_clientdata(client);
 	int r;
-	int irq;
 
 	pdata = client->dev.platform_data;
 	if (pdata == NULL) {
@@ -295,17 +285,9 @@ static int st21nfcb_nci_i2c_request_resources(struct i2c_client *client)
 	}
 
 	/* store for later use */
-	phy->gpio_irq = pdata->gpio_irq;
 	phy->gpio_reset = pdata->gpio_reset;
 	phy->irq_polarity = pdata->irq_polarity;
 
-	r = devm_gpio_request_one(&client->dev, phy->gpio_irq,
-				GPIOF_IN, "clf_irq");
-	if (r) {
-		pr_err("%s : gpio_request failed\n", __FILE__);
-		return -ENODEV;
-	}
-
 	r = devm_gpio_request_one(&client->dev,
 			phy->gpio_reset, GPIOF_OUT_INIT_HIGH, "clf_reset");
 	if (r) {
@@ -313,16 +295,6 @@ static int st21nfcb_nci_i2c_request_resources(struct i2c_client *client)
 		return -ENODEV;
 	}
 
-	/* IRQ */
-	irq = gpio_to_irq(phy->gpio_irq);
-	if (irq < 0) {
-		nfc_err(&client->dev,
-			"Unable to get irq number for GPIO %d error %d\n",
-			phy->gpio_irq, r);
-		return -ENODEV;
-	}
-	client->irq = irq;
-
 	return 0;
 }
 
diff --git a/include/linux/platform_data/st21nfcb.h b/include/linux/platform_data/st21nfcb.h
index 2d11f1f5efa..c3b432f5b63 100644
--- a/include/linux/platform_data/st21nfcb.h
+++ b/include/linux/platform_data/st21nfcb.h
@@ -24,7 +24,6 @@
 #define ST21NFCB_NCI_DRIVER_NAME "st21nfcb_nci"
 
 struct st21nfcb_nfc_platform_data {
-	unsigned int gpio_irq;
 	unsigned int gpio_reset;
 	unsigned int irq_polarity;
 };
-- 
cgit v1.2.3-70-g09d2


From 9b8d32b7acdcd237d3e58154d59551c71556fec1 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Thu, 13 Nov 2014 00:30:34 +0100
Subject: NFC: hci: Add se_io HCI operand

se_io allows to send apdu over the CLF to the embedded Secure Element.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/hci.h |  3 +++
 net/nfc/hci/core.c    | 14 ++++++++++++++
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index 7ee8f4cc610..50bc66f0121 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -57,6 +57,9 @@ struct nfc_hci_ops {
 	int (*discover_se)(struct nfc_hci_dev *dev);
 	int (*enable_se)(struct nfc_hci_dev *dev, u32 se_idx);
 	int (*disable_se)(struct nfc_hci_dev *dev, u32 se_idx);
+	int (*se_io)(struct nfc_hci_dev *dev, u32 se_idx,
+		      u8 *apdu, size_t apdu_length,
+		      se_io_cb_t cb, void *cb_context);
 };
 
 /* Pipes */
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index 117708263ce..58b1610ca54 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -717,6 +717,19 @@ static int hci_disable_se(struct nfc_dev *nfc_dev, u32 se_idx)
 	return 0;
 }
 
+static int hci_se_io(struct nfc_dev *nfc_dev, u32 se_idx,
+		     u8 *apdu, size_t apdu_length,
+		     se_io_cb_t cb, void *cb_context)
+{
+	struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev);
+
+	if (hdev->ops->se_io)
+		return hdev->ops->se_io(hdev, se_idx, apdu,
+					apdu_length, cb, cb_context);
+
+	return 0;
+}
+
 static void nfc_hci_failure(struct nfc_hci_dev *hdev, int err)
 {
 	mutex_lock(&hdev->msg_tx_mutex);
@@ -830,6 +843,7 @@ static struct nfc_ops hci_nfc_ops = {
 	.discover_se = hci_discover_se,
 	.enable_se = hci_enable_se,
 	.disable_se = hci_disable_se,
+	.se_io = hci_se_io,
 };
 
 struct nfc_hci_dev *nfc_hci_allocate_device(struct nfc_hci_ops *ops,
-- 
cgit v1.2.3-70-g09d2


From ba4db551bb48943bcebdacc30219d35a1248de11 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Thu, 13 Nov 2014 00:30:35 +0100
Subject: NFC: nci: Update nci_discover_se to run proprietary commands to
 discover all available secure element

Some NFC controller using NCI protocols may need a proprietary commands
flow to discover all available secure element

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci_core.h | 1 +
 net/nfc/nci/core.c         | 5 +++++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index cfea60748a3..8399a7964de 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -72,6 +72,7 @@ struct nci_ops {
 	int   (*send)(struct nci_dev *ndev, struct sk_buff *skb);
 	int   (*setup)(struct nci_dev *ndev);
 	__u32 (*get_rfprotocol)(struct nci_dev *ndev, __u8 rf_protocol);
+	int   (*discover_se)(struct nci_dev *ndev);
 };
 
 #define NCI_MAX_SUPPORTED_RF_INTERFACES		4
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index a354d1985d5..4044973084a 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -756,6 +756,11 @@ static int nci_disable_se(struct nfc_dev *nfc_dev, u32 se_idx)
 
 static int nci_discover_se(struct nfc_dev *nfc_dev)
 {
+	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+
+	if (ndev->ops->discover_se)
+		return ndev->ops->discover_se(ndev);
+
 	return 0;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 93bca2bfa4b79b689603b56feeea0ebed2842cbe Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Thu, 13 Nov 2014 00:30:36 +0100
Subject: NFC: nci: Update nci_enable_se to run proprietary commands to enable
 a secure element

Some NFC controller using NCI protocols may need a proprietary commands
flow to enable a secure element

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci_core.h | 1 +
 net/nfc/nci/core.c         | 5 +++++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 8399a7964de..db2d1279011 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -73,6 +73,7 @@ struct nci_ops {
 	int   (*setup)(struct nci_dev *ndev);
 	__u32 (*get_rfprotocol)(struct nci_dev *ndev, __u8 rf_protocol);
 	int   (*discover_se)(struct nci_dev *ndev);
+	int   (*enable_se)(struct nci_dev *ndev, u32 se_idx);
 };
 
 #define NCI_MAX_SUPPORTED_RF_INTERFACES		4
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 4044973084a..6c36ec6e477 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -746,6 +746,11 @@ static int nci_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb)
 
 static int nci_enable_se(struct nfc_dev *nfc_dev, u32 se_idx)
 {
+	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+
+	if (ndev->ops->enable_se)
+		return ndev->ops->enable_se(ndev, se_idx);
+
 	return 0;
 }
 
-- 
cgit v1.2.3-70-g09d2


From e9ef9431a347185a8a6a88b072506047d329e480 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Thu, 13 Nov 2014 00:30:37 +0100
Subject: NFC: nci: Update nci_disable_se to run proprietary commands to
 disable a secure element

Some NFC controller using NCI protocols may need a proprietary commands
flow to disable a secure element

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci_core.h | 1 +
 net/nfc/nci/core.c         | 5 +++++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index db2d1279011..dd97dd7176e 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -73,6 +73,7 @@ struct nci_ops {
 	int   (*setup)(struct nci_dev *ndev);
 	__u32 (*get_rfprotocol)(struct nci_dev *ndev, __u8 rf_protocol);
 	int   (*discover_se)(struct nci_dev *ndev);
+	int   (*disable_se)(struct nci_dev *ndev, u32 se_idx);
 	int   (*enable_se)(struct nci_dev *ndev, u32 se_idx);
 };
 
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 6c36ec6e477..bcb70a6b17c 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -756,6 +756,11 @@ static int nci_enable_se(struct nfc_dev *nfc_dev, u32 se_idx)
 
 static int nci_disable_se(struct nfc_dev *nfc_dev, u32 se_idx)
 {
+	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+
+	if (ndev->ops->disable_se)
+		return ndev->ops->disable_se(ndev, se_idx);
+
 	return 0;
 }
 
-- 
cgit v1.2.3-70-g09d2


From a688bf55c5908d2206307a9f76d31172ee2b2d92 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Thu, 13 Nov 2014 00:30:38 +0100
Subject: NFC: nci: Add se_io NCI operand

se_io allows to send apdu over the CLF to the embedded Secure Element.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci_core.h |  3 +++
 net/nfc/nci/core.c         | 14 ++++++++++++++
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index dd97dd7176e..9e51bb4d841 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -75,6 +75,9 @@ struct nci_ops {
 	int   (*discover_se)(struct nci_dev *ndev);
 	int   (*disable_se)(struct nci_dev *ndev, u32 se_idx);
 	int   (*enable_se)(struct nci_dev *ndev, u32 se_idx);
+	int   (*se_io)(struct nci_dev *ndev, u32 se_idx,
+				u8 *apdu, size_t apdu_length,
+				se_io_cb_t cb, void *cb_context);
 };
 
 #define NCI_MAX_SUPPORTED_RF_INTERFACES		4
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index bcb70a6b17c..552b13ba7b3 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -774,6 +774,19 @@ static int nci_discover_se(struct nfc_dev *nfc_dev)
 	return 0;
 }
 
+static int nci_se_io(struct nfc_dev *nfc_dev, u32 se_idx,
+		     u8 *apdu, size_t apdu_length,
+		     se_io_cb_t cb, void *cb_context)
+{
+	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+
+	if (ndev->ops->se_io)
+		return ndev->ops->se_io(ndev, se_idx, apdu,
+				apdu_length, cb, cb_context);
+
+	return 0;
+}
+
 static struct nfc_ops nci_nfc_ops = {
 	.dev_up = nci_dev_up,
 	.dev_down = nci_dev_down,
@@ -788,6 +801,7 @@ static struct nfc_ops nci_nfc_ops = {
 	.enable_se = nci_enable_se,
 	.disable_se = nci_disable_se,
 	.discover_se = nci_discover_se,
+	.se_io = nci_se_io,
 };
 
 /* ---- Interface to NCI drivers ---- */
-- 
cgit v1.2.3-70-g09d2


From 73112edca9be1d7c37d0b94348c82c3742c3ef58 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu, 27 Nov 2014 13:59:20 -0800
Subject: target: Move dev_cit to struct se_subsystem_api

This patch adds initial support for dev_cit as external config_item_type.

This includes a new struct target_backend_cits to hold the external CITs
within struct se_subsystem_api, and target_core_setup_sub_cits() to be
used by backend drivers ahead of transport_subsystem_register().

It adds a TB_CIT_SETUP() helper following target_core_fabric_configfs.c
to perform the config_item_type assignments.

Also, drop left-over target_core_dev_cit from target_core_configfs.c code
and update comments.

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_configfs.c | 33 ++++++++++++++++++++++++---------
 drivers/target/target_core_hba.c      |  1 +
 include/target/target_core_backend.h  |  9 +++++++++
 3 files changed, 34 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 41498b69664..f7b2186ba57 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -50,6 +50,19 @@
 #include "target_core_rd.h"
 #include "target_core_xcopy.h"
 
+#define TB_CIT_SETUP(_name, _item_ops, _group_ops, _attrs)		\
+static void target_core_setup_##_name##_cit(struct se_subsystem_api *sa) \
+{									\
+	struct target_backend_cits *tbc = &sa->tb_cits;			\
+	struct config_item_type *cit = &tbc->tb_##_name##_cit;		\
+									\
+	cit->ct_item_ops = _item_ops;					\
+	cit->ct_group_ops = _group_ops;					\
+	cit->ct_attrs = _attrs;						\
+	cit->ct_owner = sa->owner;					\
+	pr_debug("Setup generic %s\n", __stringify(_name));		\
+}
+
 extern struct t10_alua_lu_gp *default_lu_gp;
 
 static LIST_HEAD(g_tf_list);
@@ -1470,7 +1483,7 @@ static struct config_item_type target_core_dev_pr_cit = {
 
 /*  End functions for struct config_item_type target_core_dev_pr_cit */
 
-/*  Start functions for struct config_item_type target_core_dev_cit */
+/*  Start functions for struct config_item_type tb_dev_cit */
 
 static ssize_t target_core_show_dev_info(void *p, char *page)
 {
@@ -1934,7 +1947,7 @@ static struct target_core_configfs_attribute target_core_attr_dev_lba_map = {
 	.store	= target_core_store_dev_lba_map,
 };
 
-static struct configfs_attribute *lio_core_dev_attrs[] = {
+static struct configfs_attribute *target_core_dev_attrs[] = {
 	&target_core_attr_dev_info.attr,
 	&target_core_attr_dev_control.attr,
 	&target_core_attr_dev_alias.attr,
@@ -1993,13 +2006,9 @@ static struct configfs_item_operations target_core_dev_item_ops = {
 	.store_attribute	= target_core_dev_store,
 };
 
-static struct config_item_type target_core_dev_cit = {
-	.ct_item_ops		= &target_core_dev_item_ops,
-	.ct_attrs		= lio_core_dev_attrs,
-	.ct_owner		= THIS_MODULE,
-};
+TB_CIT_SETUP(dev, &target_core_dev_item_ops, NULL, target_core_dev_attrs);
 
-/* End functions for struct config_item_type target_core_dev_cit */
+/* End functions for struct config_item_type tb_dev_cit */
 
 /* Start functions for struct config_item_type target_core_alua_lu_gp_cit */
 
@@ -2815,7 +2824,7 @@ static struct config_group *target_core_make_subdev(
 	if (!dev_cg->default_groups)
 		goto out_free_device;
 
-	config_group_init_type_name(dev_cg, name, &target_core_dev_cit);
+	config_group_init_type_name(dev_cg, name, &t->tb_cits.tb_dev_cit);
 	config_group_init_type_name(&dev->dev_attrib.da_group, "attrib",
 			&target_core_dev_attrib_cit);
 	config_group_init_type_name(&dev->dev_pr_group, "pr",
@@ -3119,6 +3128,12 @@ static struct config_item_type target_core_cit = {
 
 /* Stop functions for struct config_item_type target_core_hba_cit */
 
+void target_core_setup_sub_cits(struct se_subsystem_api *sa)
+{
+	target_core_setup_dev_cit(sa);
+}
+EXPORT_SYMBOL(target_core_setup_sub_cits);
+
 static int __init target_core_init_configfs(void)
 {
 	struct config_group *target_cg, *hba_cg = NULL, *alua_cg = NULL;
diff --git a/drivers/target/target_core_hba.c b/drivers/target/target_core_hba.c
index e6e496ff954..ff95f95dcd1 100644
--- a/drivers/target/target_core_hba.c
+++ b/drivers/target/target_core_hba.c
@@ -36,6 +36,7 @@
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
 #include <target/target_core_fabric.h>
+#include <target/target_core_configfs.h>
 
 #include "target_core_internal.h"
 
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 9adc1bca117..7b84436541b 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -5,6 +5,10 @@
 #define TRANSPORT_PLUGIN_VHBA_PDEV		2
 #define TRANSPORT_PLUGIN_VHBA_VDEV		3
 
+struct target_backend_cits {
+	struct config_item_type tb_dev_cit;
+};
+
 struct se_subsystem_api {
 	struct list_head sub_api_list;
 
@@ -44,6 +48,8 @@ struct se_subsystem_api {
 	int (*init_prot)(struct se_device *);
 	int (*format_prot)(struct se_device *);
 	void (*free_prot)(struct se_device *);
+
+	struct target_backend_cits tb_cits;
 };
 
 struct sbc_ops {
@@ -96,4 +102,7 @@ sense_reason_t	transport_generic_map_mem_to_cmd(struct se_cmd *,
 
 void	array_free(void *array, int n);
 
+/* From target_core_configfs.c to setup default backend config_item_types */
+void	target_core_setup_sub_cits(struct se_subsystem_api *);
+
 #endif /* TARGET_CORE_BACKEND_H */
-- 
cgit v1.2.3-70-g09d2


From f79a897efa6a95d698c4064e48e0a5afddc0ad9f Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu, 27 Nov 2014 14:51:14 -0800
Subject: target: Move dev_attrib_cit to struct se_subsystem_api

This patch adds support for dev_attrib_cit as an external config_item_type
using TB_CIT_SETUP() helper macro, and sets both ct_item_ops + ct_attr
following existing code.

It updates target_core_make_subdev() + target_core_setup_dev_attrib_cit() +
struct target_backend_cits, and drops left-over target_core_dev_attrib_cit
from target_core_configfs.c code and update comments.

This patch introduces no functional change from existing code.

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_configfs.c | 14 ++++++--------
 include/target/target_core_backend.h  |  1 +
 2 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index f7b2186ba57..78ed857cc7b 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -584,7 +584,7 @@ EXPORT_SYMBOL(target_fabric_configfs_deregister);
 // Stop functions called by external Target Fabrics Modules
 //############################################################################*/
 
-/* Start functions for struct config_item_type target_core_dev_attrib_cit */
+/* Start functions for struct config_item_type tb_dev_attrib_cit */
 
 #define DEF_DEV_ATTRIB_SHOW(_name)					\
 static ssize_t target_core_dev_show_attr_##_name(			\
@@ -767,13 +767,10 @@ static struct configfs_item_operations target_core_dev_attrib_ops = {
 	.store_attribute	= target_core_dev_attrib_attr_store,
 };
 
-static struct config_item_type target_core_dev_attrib_cit = {
-	.ct_item_ops		= &target_core_dev_attrib_ops,
-	.ct_attrs		= target_core_dev_attrib_attrs,
-	.ct_owner		= THIS_MODULE,
-};
+TB_CIT_SETUP(dev_attrib, &target_core_dev_attrib_ops, NULL,
+	     target_core_dev_attrib_attrs);
 
-/* End functions for struct config_item_type target_core_dev_attrib_cit */
+/* End functions for struct config_item_type tb_dev_attrib_cit */
 
 /*  Start functions for struct config_item_type target_core_dev_wwn_cit */
 
@@ -2826,7 +2823,7 @@ static struct config_group *target_core_make_subdev(
 
 	config_group_init_type_name(dev_cg, name, &t->tb_cits.tb_dev_cit);
 	config_group_init_type_name(&dev->dev_attrib.da_group, "attrib",
-			&target_core_dev_attrib_cit);
+			&t->tb_cits.tb_dev_attrib_cit);
 	config_group_init_type_name(&dev->dev_pr_group, "pr",
 			&target_core_dev_pr_cit);
 	config_group_init_type_name(&dev->t10_wwn.t10_wwn_group, "wwn",
@@ -3131,6 +3128,7 @@ static struct config_item_type target_core_cit = {
 void target_core_setup_sub_cits(struct se_subsystem_api *sa)
 {
 	target_core_setup_dev_cit(sa);
+	target_core_setup_dev_attrib_cit(sa);
 }
 EXPORT_SYMBOL(target_core_setup_sub_cits);
 
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 7b84436541b..735f85672ec 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -7,6 +7,7 @@
 
 struct target_backend_cits {
 	struct config_item_type tb_dev_cit;
+	struct config_item_type tb_dev_attrib_cit;
 };
 
 struct se_subsystem_api {
-- 
cgit v1.2.3-70-g09d2


From 91e2e39ba89cd627beddafea2a760684adcec89d Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu, 27 Nov 2014 14:57:01 -0800
Subject: target: Move dev_pr_cit to struct se_subsystem_api

This patch adds support for dev_pr_cit as an external config_item_type
using TB_CIT_SETUP() helper macro, and sets both ct_item_ops + ct_attr
following existing code.

It updates target_core_make_subdev() + target_core_setup_dev_attrib_cit() +
struct target_backend_cits, and drops left-over target_core_dev_pr_cit
from target_core_configfs.c code and update comments.

This patch introduces no functional change from existing code.

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_configfs.c | 13 +++++--------
 include/target/target_core_backend.h  |  1 +
 2 files changed, 6 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 78ed857cc7b..49d51ba40fc 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -1011,7 +1011,7 @@ static struct config_item_type target_core_dev_wwn_cit = {
 
 /*  End functions for struct config_item_type target_core_dev_wwn_cit */
 
-/*  Start functions for struct config_item_type target_core_dev_pr_cit */
+/*  Start functions for struct config_item_type tb_dev_pr_cit */
 
 CONFIGFS_EATTR_STRUCT(target_core_dev_pr, se_device);
 #define SE_DEV_PR_ATTR(_name, _mode)					\
@@ -1472,13 +1472,9 @@ static struct configfs_item_operations target_core_dev_pr_ops = {
 	.store_attribute	= target_core_dev_pr_attr_store,
 };
 
-static struct config_item_type target_core_dev_pr_cit = {
-	.ct_item_ops		= &target_core_dev_pr_ops,
-	.ct_attrs		= target_core_dev_pr_attrs,
-	.ct_owner		= THIS_MODULE,
-};
+TB_CIT_SETUP(dev_pr, &target_core_dev_pr_ops, NULL, target_core_dev_pr_attrs);
 
-/*  End functions for struct config_item_type target_core_dev_pr_cit */
+/*  End functions for struct config_item_type tb_dev_pr_cit */
 
 /*  Start functions for struct config_item_type tb_dev_cit */
 
@@ -2825,7 +2821,7 @@ static struct config_group *target_core_make_subdev(
 	config_group_init_type_name(&dev->dev_attrib.da_group, "attrib",
 			&t->tb_cits.tb_dev_attrib_cit);
 	config_group_init_type_name(&dev->dev_pr_group, "pr",
-			&target_core_dev_pr_cit);
+			&t->tb_cits.tb_dev_pr_cit);
 	config_group_init_type_name(&dev->t10_wwn.t10_wwn_group, "wwn",
 			&target_core_dev_wwn_cit);
 	config_group_init_type_name(&dev->t10_alua.alua_tg_pt_gps_group,
@@ -3129,6 +3125,7 @@ void target_core_setup_sub_cits(struct se_subsystem_api *sa)
 {
 	target_core_setup_dev_cit(sa);
 	target_core_setup_dev_attrib_cit(sa);
+	target_core_setup_dev_pr_cit(sa);
 }
 EXPORT_SYMBOL(target_core_setup_sub_cits);
 
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 735f85672ec..a47e78989b6 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -8,6 +8,7 @@
 struct target_backend_cits {
 	struct config_item_type tb_dev_cit;
 	struct config_item_type tb_dev_attrib_cit;
+	struct config_item_type tb_dev_pr_cit;
 };
 
 struct se_subsystem_api {
-- 
cgit v1.2.3-70-g09d2


From f8d389c6f6074aa382963ae13f9d77d99ec3e92d Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu, 27 Nov 2014 15:01:12 -0800
Subject: target: Move dev_wwn_cit to struct se_subsystem_api

This patch adds support for dev_wwn_cit as an external config_item_type
using TB_CIT_SETUP() helper macro, and sets both ct_item_ops + ct_attr
following existing code.

It updates target_core_make_subdev() + target_core_setup_dev_attrib_cit() +
struct target_backend_cits, and drops left-over target_core_dev_wwn_cit
from target_core_configfs.c code and update comments.

This patch introduces no functional change from existing code.

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_configfs.c | 13 +++++--------
 include/target/target_core_backend.h  |  1 +
 2 files changed, 6 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 49d51ba40fc..43d180e0393 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -772,7 +772,7 @@ TB_CIT_SETUP(dev_attrib, &target_core_dev_attrib_ops, NULL,
 
 /* End functions for struct config_item_type tb_dev_attrib_cit */
 
-/*  Start functions for struct config_item_type target_core_dev_wwn_cit */
+/*  Start functions for struct config_item_type tb_dev_wwn_cit */
 
 CONFIGFS_EATTR_STRUCT(target_core_dev_wwn, t10_wwn);
 #define SE_DEV_WWN_ATTR(_name, _mode)					\
@@ -1003,13 +1003,9 @@ static struct configfs_item_operations target_core_dev_wwn_ops = {
 	.store_attribute	= target_core_dev_wwn_attr_store,
 };
 
-static struct config_item_type target_core_dev_wwn_cit = {
-	.ct_item_ops		= &target_core_dev_wwn_ops,
-	.ct_attrs		= target_core_dev_wwn_attrs,
-	.ct_owner		= THIS_MODULE,
-};
+TB_CIT_SETUP(dev_wwn, &target_core_dev_wwn_ops, NULL, target_core_dev_wwn_attrs);
 
-/*  End functions for struct config_item_type target_core_dev_wwn_cit */
+/*  End functions for struct config_item_type tb_dev_wwn_cit */
 
 /*  Start functions for struct config_item_type tb_dev_pr_cit */
 
@@ -2823,7 +2819,7 @@ static struct config_group *target_core_make_subdev(
 	config_group_init_type_name(&dev->dev_pr_group, "pr",
 			&t->tb_cits.tb_dev_pr_cit);
 	config_group_init_type_name(&dev->t10_wwn.t10_wwn_group, "wwn",
-			&target_core_dev_wwn_cit);
+			&t->tb_cits.tb_dev_wwn_cit);
 	config_group_init_type_name(&dev->t10_alua.alua_tg_pt_gps_group,
 			"alua", &target_core_alua_tg_pt_gps_cit);
 	config_group_init_type_name(&dev->dev_stat_grps.stat_group,
@@ -3126,6 +3122,7 @@ void target_core_setup_sub_cits(struct se_subsystem_api *sa)
 	target_core_setup_dev_cit(sa);
 	target_core_setup_dev_attrib_cit(sa);
 	target_core_setup_dev_pr_cit(sa);
+	target_core_setup_dev_wwn_cit(sa);
 }
 EXPORT_SYMBOL(target_core_setup_sub_cits);
 
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index a47e78989b6..68fad781498 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -9,6 +9,7 @@ struct target_backend_cits {
 	struct config_item_type tb_dev_cit;
 	struct config_item_type tb_dev_attrib_cit;
 	struct config_item_type tb_dev_pr_cit;
+	struct config_item_type tb_dev_wwn_cit;
 };
 
 struct se_subsystem_api {
-- 
cgit v1.2.3-70-g09d2


From 72aca57bd3fef535972b64c9cd76a088107c589c Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu, 27 Nov 2014 15:06:23 -0800
Subject: target: Move dev_alua_tg_pt_gps_cit to struct se_subsystem_api

This patch adds support for dev_alua_tg_pt_gps_cit as an external config_item_type
using TB_CIT_SETUP() helper macro, and sets only ct_group_ops following
existing code.

It updates target_core_make_subdev() + target_core_setup_dev_attrib_cit() +
struct target_backend_cits, and drops left-over target_core_dev_alua_tg_pt_gps_cit
from target_core_configfs.c code and update comments.

This patch introduces no functional change from existing code.

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_configfs.c | 12 +++++-------
 include/target/target_core_backend.h  |  1 +
 2 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 43d180e0393..0cf41ad54bb 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -2677,7 +2677,7 @@ static struct config_item_type target_core_alua_tg_pt_gp_cit = {
 
 /* End functions for struct config_item_type target_core_alua_tg_pt_gp_cit */
 
-/* Start functions for struct config_item_type target_core_alua_tg_pt_gps_cit */
+/* Start functions for struct config_item_type tb_alua_tg_pt_gps_cit */
 
 static struct config_group *target_core_alua_create_tg_pt_gp(
 	struct config_group *group,
@@ -2728,12 +2728,9 @@ static struct configfs_group_operations target_core_alua_tg_pt_gps_group_ops = {
 	.drop_item		= &target_core_alua_drop_tg_pt_gp,
 };
 
-static struct config_item_type target_core_alua_tg_pt_gps_cit = {
-	.ct_group_ops		= &target_core_alua_tg_pt_gps_group_ops,
-	.ct_owner		= THIS_MODULE,
-};
+TB_CIT_SETUP(dev_alua_tg_pt_gps, NULL, &target_core_alua_tg_pt_gps_group_ops, NULL);
 
-/* End functions for struct config_item_type target_core_alua_tg_pt_gps_cit */
+/* End functions for struct config_item_type tb_alua_tg_pt_gps_cit */
 
 /* Start functions for struct config_item_type target_core_alua_cit */
 
@@ -2821,7 +2818,7 @@ static struct config_group *target_core_make_subdev(
 	config_group_init_type_name(&dev->t10_wwn.t10_wwn_group, "wwn",
 			&t->tb_cits.tb_dev_wwn_cit);
 	config_group_init_type_name(&dev->t10_alua.alua_tg_pt_gps_group,
-			"alua", &target_core_alua_tg_pt_gps_cit);
+			"alua", &t->tb_cits.tb_dev_alua_tg_pt_gps_cit);
 	config_group_init_type_name(&dev->dev_stat_grps.stat_group,
 			"statistics", &target_core_stat_cit);
 
@@ -3123,6 +3120,7 @@ void target_core_setup_sub_cits(struct se_subsystem_api *sa)
 	target_core_setup_dev_attrib_cit(sa);
 	target_core_setup_dev_pr_cit(sa);
 	target_core_setup_dev_wwn_cit(sa);
+	target_core_setup_dev_alua_tg_pt_gps_cit(sa);
 }
 EXPORT_SYMBOL(target_core_setup_sub_cits);
 
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 68fad781498..157d173f28f 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -10,6 +10,7 @@ struct target_backend_cits {
 	struct config_item_type tb_dev_attrib_cit;
 	struct config_item_type tb_dev_pr_cit;
 	struct config_item_type tb_dev_wwn_cit;
+	struct config_item_type tb_dev_alua_tg_pt_gps_cit;
 };
 
 struct se_subsystem_api {
-- 
cgit v1.2.3-70-g09d2


From d23ab570bcb1de0256f1dcea0b8ad3af8e534e40 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu, 27 Nov 2014 15:09:32 -0800
Subject: target: Move dev_stat_cit to struct se_subsystem_api

This patch adds support for dev_stat_cit as an external config_item_type
using TB_CIT_SETUP() helper macro, and sets only ct_group_ops following
existing code.

It updates target_core_make_subdev() + target_core_setup_dev_attrib_cit() +
struct target_backend_cits, and drops left-over target_core_dev_stat_cit
from target_core_configfs.c code and update comments.

This patch introduces no functional change from existing code.

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_configfs.c | 12 +++++-------
 include/target/target_core_backend.h  |  1 +
 2 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 0cf41ad54bb..2903d893162 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -2748,7 +2748,7 @@ static struct config_item_type target_core_alua_cit = {
 
 /* End functions for struct config_item_type target_core_alua_cit */
 
-/* Start functions for struct config_item_type target_core_stat_cit */
+/* Start functions for struct config_item_type tb_dev_stat_cit */
 
 static struct config_group *target_core_stat_mkdir(
 	struct config_group *group,
@@ -2769,12 +2769,9 @@ static struct configfs_group_operations target_core_stat_group_ops = {
 	.drop_item		= &target_core_stat_rmdir,
 };
 
-static struct config_item_type target_core_stat_cit = {
-	.ct_group_ops		= &target_core_stat_group_ops,
-	.ct_owner		= THIS_MODULE,
-};
+TB_CIT_SETUP(dev_stat, NULL, &target_core_stat_group_ops, NULL);
 
-/* End functions for struct config_item_type target_core_stat_cit */
+/* End functions for struct config_item_type tb_dev_stat_cit */
 
 /* Start functions for struct config_item_type target_core_hba_cit */
 
@@ -2820,7 +2817,7 @@ static struct config_group *target_core_make_subdev(
 	config_group_init_type_name(&dev->t10_alua.alua_tg_pt_gps_group,
 			"alua", &t->tb_cits.tb_dev_alua_tg_pt_gps_cit);
 	config_group_init_type_name(&dev->dev_stat_grps.stat_group,
-			"statistics", &target_core_stat_cit);
+			"statistics", &t->tb_cits.tb_dev_stat_cit);
 
 	dev_cg->default_groups[0] = &dev->dev_attrib.da_group;
 	dev_cg->default_groups[1] = &dev->dev_pr_group;
@@ -3121,6 +3118,7 @@ void target_core_setup_sub_cits(struct se_subsystem_api *sa)
 	target_core_setup_dev_pr_cit(sa);
 	target_core_setup_dev_wwn_cit(sa);
 	target_core_setup_dev_alua_tg_pt_gps_cit(sa);
+	target_core_setup_dev_stat_cit(sa);
 }
 EXPORT_SYMBOL(target_core_setup_sub_cits);
 
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 157d173f28f..83a3726eabc 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -11,6 +11,7 @@ struct target_backend_cits {
 	struct config_item_type tb_dev_pr_cit;
 	struct config_item_type tb_dev_wwn_cit;
 	struct config_item_type tb_dev_alua_tg_pt_gps_cit;
+	struct config_item_type tb_dev_stat_cit;
 };
 
 struct se_subsystem_api {
-- 
cgit v1.2.3-70-g09d2


From 7a23f890b7c11b63dfc2a6c7ae1f0a631ed84865 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu, 27 Nov 2014 18:57:27 -0800
Subject: target: Add target_core_backend_configfs.h helper macros

This patch adds a number of configfs e-attr macros following
what existing target_core_configfs.c code does for internal
target_backend_dev_attrib setup, and similar to how target
fabric drivers allow for external config_item_type + cit->ct_attrs.
assignment.

This is useful for backend drivers like PSCSI who need to only
expose a small subset of device attributes, while still retaining
a default list of attributes for other backend drivers like
IBLOCK, FILEIO, RAMDISK, and TCMU.

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 include/target/target_core_backend_configfs.h | 53 +++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)
 create mode 100644 include/target/target_core_backend_configfs.h

(limited to 'include')

diff --git a/include/target/target_core_backend_configfs.h b/include/target/target_core_backend_configfs.h
new file mode 100644
index 00000000000..f91935b5ef2
--- /dev/null
+++ b/include/target/target_core_backend_configfs.h
@@ -0,0 +1,53 @@
+#ifndef TARGET_CORE_BACKEND_CONFIGFS_H
+#define TARGET_CORE_BACKEND_CONFIGFS_H
+
+#include <target/configfs_macros.h>
+
+#define DEF_TB_DEV_ATTRIB_SHOW(_backend, _name)				\
+static ssize_t _backend##_dev_show_attr_##_name(			\
+	struct se_dev_attrib *da,					\
+	char *page)							\
+{									\
+	return snprintf(page, PAGE_SIZE, "%u\n",			\
+			(u32)da->da_dev->dev_attrib._name);		\
+}
+
+#define DEF_TB_DEV_ATTRIB_STORE(_backend, _name)			\
+static ssize_t _backend##_dev_store_attr_##_name(			\
+	struct se_dev_attrib *da,					\
+	const char *page,						\
+	size_t count)							\
+{									\
+	unsigned long val;						\
+	int ret;							\
+									\
+	ret = kstrtoul(page, 0, &val);					\
+	if (ret < 0) {							\
+		pr_err("kstrtoul() failed with ret: %d\n", ret);	\
+		return -EINVAL;						\
+	}								\
+	ret = se_dev_set_##_name(da->da_dev, (u32)val);			\
+									\
+	return (!ret) ? count : -EINVAL;				\
+}
+
+#define DEF_TB_DEV_ATTRIB(_backend, _name)				\
+DEF_TB_DEV_ATTRIB_SHOW(_backend, _name);				\
+DEF_TB_DEV_ATTRIB_STORE(_backend, _name);
+
+#define DEF_TB_DEV_ATTRIB_RO(_backend, name)				\
+DEF_TB_DEV_ATTRIB_SHOW(_backend, name);
+
+CONFIGFS_EATTR_STRUCT(target_backend_dev_attrib, se_dev_attrib);
+#define TB_DEV_ATTR(_backend, _name, _mode)				\
+static struct target_backend_dev_attrib_attribute _backend##_dev_attrib_##_name = \
+		__CONFIGFS_EATTR(_name, _mode,				\
+		_backend##_dev_show_attr_##_name,			\
+		_backend##_dev_store_attr_##_name);
+
+#define TB_DEV_ATTR_RO(_backend, _name)						\
+static struct target_backend_dev_attrib_attribute _backend##_dev_attrib_##_name = \
+	__CONFIGFS_EATTR_RO(_name,					\
+	_backend##_dev_show_attr_##_name);
+
+#endif /* TARGET_CORE_BACKEND_CONFIGFS_H */
-- 
cgit v1.2.3-70-g09d2


From d30cd1238c2f89662c82d5d2c4686971a6dc3693 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu, 27 Nov 2014 19:15:48 -0800
Subject: target: Add EXPORT_SYMBOL for existing se_dev_set_*

Now that target_core_backend_configfs.h macros will be using these
se_dev_set attribute functions externally to allow backend drivers
to populate different attributes, go ahead and add EXPORT_SYMBOL()
for the existing default set of 30 device attributes.

Also update target_core_backend.h with proper function prototypes.

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c   | 26 ++++++++++++++++++++++++++
 drivers/target/target_core_iblock.c   |  1 +
 drivers/target/target_core_internal.h | 28 ----------------------------
 include/target/target_core_backend.h  | 29 +++++++++++++++++++++++++++++
 4 files changed, 56 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index c45f9e907e4..953fff79bc1 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -659,6 +659,7 @@ int se_dev_set_max_unmap_lba_count(
 			dev, dev->dev_attrib.max_unmap_lba_count);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_max_unmap_lba_count);
 
 int se_dev_set_max_unmap_block_desc_count(
 	struct se_device *dev,
@@ -670,6 +671,7 @@ int se_dev_set_max_unmap_block_desc_count(
 			dev, dev->dev_attrib.max_unmap_block_desc_count);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_max_unmap_block_desc_count);
 
 int se_dev_set_unmap_granularity(
 	struct se_device *dev,
@@ -680,6 +682,7 @@ int se_dev_set_unmap_granularity(
 			dev, dev->dev_attrib.unmap_granularity);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_unmap_granularity);
 
 int se_dev_set_unmap_granularity_alignment(
 	struct se_device *dev,
@@ -690,6 +693,7 @@ int se_dev_set_unmap_granularity_alignment(
 			dev, dev->dev_attrib.unmap_granularity_alignment);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_unmap_granularity_alignment);
 
 int se_dev_set_max_write_same_len(
 	struct se_device *dev,
@@ -700,6 +704,7 @@ int se_dev_set_max_write_same_len(
 			dev, dev->dev_attrib.max_write_same_len);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_max_write_same_len);
 
 static void dev_set_t10_wwn_model_alias(struct se_device *dev)
 {
@@ -738,6 +743,7 @@ int se_dev_set_emulate_model_alias(struct se_device *dev, int flag)
 
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_emulate_model_alias);
 
 int se_dev_set_emulate_dpo(struct se_device *dev, int flag)
 {
@@ -753,6 +759,7 @@ int se_dev_set_emulate_dpo(struct se_device *dev, int flag)
 
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_emulate_dpo);
 
 int se_dev_set_emulate_fua_write(struct se_device *dev, int flag)
 {
@@ -771,6 +778,7 @@ int se_dev_set_emulate_fua_write(struct se_device *dev, int flag)
 			dev, dev->dev_attrib.emulate_fua_write);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_emulate_fua_write);
 
 int se_dev_set_emulate_fua_read(struct se_device *dev, int flag)
 {
@@ -786,6 +794,7 @@ int se_dev_set_emulate_fua_read(struct se_device *dev, int flag)
 
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_emulate_fua_read);
 
 int se_dev_set_emulate_write_cache(struct se_device *dev, int flag)
 {
@@ -809,6 +818,7 @@ int se_dev_set_emulate_write_cache(struct se_device *dev, int flag)
 			dev, dev->dev_attrib.emulate_write_cache);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_emulate_write_cache);
 
 int se_dev_set_emulate_ua_intlck_ctrl(struct se_device *dev, int flag)
 {
@@ -829,6 +839,7 @@ int se_dev_set_emulate_ua_intlck_ctrl(struct se_device *dev, int flag)
 
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_emulate_ua_intlck_ctrl);
 
 int se_dev_set_emulate_tas(struct se_device *dev, int flag)
 {
@@ -849,6 +860,7 @@ int se_dev_set_emulate_tas(struct se_device *dev, int flag)
 
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_emulate_tas);
 
 int se_dev_set_emulate_tpu(struct se_device *dev, int flag)
 {
@@ -870,6 +882,7 @@ int se_dev_set_emulate_tpu(struct se_device *dev, int flag)
 				dev, flag);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_emulate_tpu);
 
 int se_dev_set_emulate_tpws(struct se_device *dev, int flag)
 {
@@ -891,6 +904,7 @@ int se_dev_set_emulate_tpws(struct se_device *dev, int flag)
 				dev, flag);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_emulate_tpws);
 
 int se_dev_set_emulate_caw(struct se_device *dev, int flag)
 {
@@ -904,6 +918,7 @@ int se_dev_set_emulate_caw(struct se_device *dev, int flag)
 
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_emulate_caw);
 
 int se_dev_set_emulate_3pc(struct se_device *dev, int flag)
 {
@@ -917,6 +932,7 @@ int se_dev_set_emulate_3pc(struct se_device *dev, int flag)
 
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_emulate_3pc);
 
 int se_dev_set_pi_prot_type(struct se_device *dev, int flag)
 {
@@ -970,6 +986,7 @@ int se_dev_set_pi_prot_type(struct se_device *dev, int flag)
 
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_pi_prot_type);
 
 int se_dev_set_pi_prot_format(struct se_device *dev, int flag)
 {
@@ -1005,6 +1022,7 @@ int se_dev_set_pi_prot_format(struct se_device *dev, int flag)
 
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_pi_prot_format);
 
 int se_dev_set_enforce_pr_isids(struct se_device *dev, int flag)
 {
@@ -1017,6 +1035,7 @@ int se_dev_set_enforce_pr_isids(struct se_device *dev, int flag)
 		(dev->dev_attrib.enforce_pr_isids) ? "Enabled" : "Disabled");
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_enforce_pr_isids);
 
 int se_dev_set_force_pr_aptpl(struct se_device *dev, int flag)
 {
@@ -1034,6 +1053,7 @@ int se_dev_set_force_pr_aptpl(struct se_device *dev, int flag)
 	pr_debug("dev[%p]: SE Device force_pr_aptpl: %d\n", dev, flag);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_force_pr_aptpl);
 
 int se_dev_set_is_nonrot(struct se_device *dev, int flag)
 {
@@ -1046,6 +1066,7 @@ int se_dev_set_is_nonrot(struct se_device *dev, int flag)
 	       dev, flag);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_is_nonrot);
 
 int se_dev_set_emulate_rest_reord(struct se_device *dev, int flag)
 {
@@ -1058,6 +1079,7 @@ int se_dev_set_emulate_rest_reord(struct se_device *dev, int flag)
 	pr_debug("dev[%p]: SE Device emulate_rest_reord: %d\n", dev, flag);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_emulate_rest_reord);
 
 /*
  * Note, this can only be called on unexported SE Device Object.
@@ -1101,6 +1123,7 @@ int se_dev_set_queue_depth(struct se_device *dev, u32 queue_depth)
 			dev, queue_depth);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_queue_depth);
 
 int se_dev_set_fabric_max_sectors(struct se_device *dev, u32 fabric_max_sectors)
 {
@@ -1155,6 +1178,7 @@ int se_dev_set_fabric_max_sectors(struct se_device *dev, u32 fabric_max_sectors)
 			dev, fabric_max_sectors);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_fabric_max_sectors);
 
 int se_dev_set_optimal_sectors(struct se_device *dev, u32 optimal_sectors)
 {
@@ -1181,6 +1205,7 @@ int se_dev_set_optimal_sectors(struct se_device *dev, u32 optimal_sectors)
 			dev, optimal_sectors);
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_optimal_sectors);
 
 int se_dev_set_block_size(struct se_device *dev, u32 block_size)
 {
@@ -1218,6 +1243,7 @@ int se_dev_set_block_size(struct se_device *dev, u32 block_size)
 
 	return 0;
 }
+EXPORT_SYMBOL(se_dev_set_block_size);
 
 struct se_lun *core_dev_add_lun(
 	struct se_portal_group *tpg,
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 7e6b857c6b3..5e69d36af10 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -858,6 +858,7 @@ static bool iblock_get_write_cache(struct se_device *dev)
 	return q->flush_flags & REQ_FLUSH;
 }
 
+
 static struct se_subsystem_api iblock_template = {
 	.name			= "iblock",
 	.inquiry_prod		= "IBLOCK",
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index e31f42f369f..60381db9002 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -18,34 +18,6 @@ int	core_dev_export(struct se_device *, struct se_portal_group *,
 		struct se_lun *);
 void	core_dev_unexport(struct se_device *, struct se_portal_group *,
 		struct se_lun *);
-int	se_dev_set_task_timeout(struct se_device *, u32);
-int	se_dev_set_max_unmap_lba_count(struct se_device *, u32);
-int	se_dev_set_max_unmap_block_desc_count(struct se_device *, u32);
-int	se_dev_set_unmap_granularity(struct se_device *, u32);
-int	se_dev_set_unmap_granularity_alignment(struct se_device *, u32);
-int	se_dev_set_max_write_same_len(struct se_device *, u32);
-int	se_dev_set_emulate_model_alias(struct se_device *, int);
-int	se_dev_set_emulate_dpo(struct se_device *, int);
-int	se_dev_set_emulate_fua_write(struct se_device *, int);
-int	se_dev_set_emulate_fua_read(struct se_device *, int);
-int	se_dev_set_emulate_write_cache(struct se_device *, int);
-int	se_dev_set_emulate_ua_intlck_ctrl(struct se_device *, int);
-int	se_dev_set_emulate_tas(struct se_device *, int);
-int	se_dev_set_emulate_tpu(struct se_device *, int);
-int	se_dev_set_emulate_tpws(struct se_device *, int);
-int	se_dev_set_emulate_caw(struct se_device *, int);
-int	se_dev_set_emulate_3pc(struct se_device *, int);
-int	se_dev_set_pi_prot_type(struct se_device *, int);
-int	se_dev_set_pi_prot_format(struct se_device *, int);
-int	se_dev_set_enforce_pr_isids(struct se_device *, int);
-int	se_dev_set_force_pr_aptpl(struct se_device *, int);
-int	se_dev_set_is_nonrot(struct se_device *, int);
-int	se_dev_set_emulate_rest_reord(struct se_device *dev, int);
-int	se_dev_set_queue_depth(struct se_device *, u32);
-int	se_dev_set_max_sectors(struct se_device *, u32);
-int	se_dev_set_fabric_max_sectors(struct se_device *, u32);
-int	se_dev_set_optimal_sectors(struct se_device *, u32);
-int	se_dev_set_block_size(struct se_device *, u32);
 struct se_lun *core_dev_add_lun(struct se_portal_group *, struct se_device *, u32);
 void	core_dev_del_lun(struct se_portal_group *, struct se_lun *);
 struct se_lun *core_get_lun_from_tpg(struct se_portal_group *, u32);
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 83a3726eabc..430cfaf9228 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -110,4 +110,33 @@ void	array_free(void *array, int n);
 /* From target_core_configfs.c to setup default backend config_item_types */
 void	target_core_setup_sub_cits(struct se_subsystem_api *);
 
+/* attribute helpers from target_core_device.c for backend drivers */
+int	se_dev_set_max_unmap_lba_count(struct se_device *, u32);
+int	se_dev_set_max_unmap_block_desc_count(struct se_device *, u32);
+int	se_dev_set_unmap_granularity(struct se_device *, u32);
+int	se_dev_set_unmap_granularity_alignment(struct se_device *, u32);
+int	se_dev_set_max_write_same_len(struct se_device *, u32);
+int	se_dev_set_emulate_model_alias(struct se_device *, int);
+int	se_dev_set_emulate_dpo(struct se_device *, int);
+int	se_dev_set_emulate_fua_write(struct se_device *, int);
+int	se_dev_set_emulate_fua_read(struct se_device *, int);
+int	se_dev_set_emulate_write_cache(struct se_device *, int);
+int	se_dev_set_emulate_ua_intlck_ctrl(struct se_device *, int);
+int	se_dev_set_emulate_tas(struct se_device *, int);
+int	se_dev_set_emulate_tpu(struct se_device *, int);
+int	se_dev_set_emulate_tpws(struct se_device *, int);
+int	se_dev_set_emulate_caw(struct se_device *, int);
+int	se_dev_set_emulate_3pc(struct se_device *, int);
+int	se_dev_set_pi_prot_type(struct se_device *, int);
+int	se_dev_set_pi_prot_format(struct se_device *, int);
+int	se_dev_set_enforce_pr_isids(struct se_device *, int);
+int	se_dev_set_force_pr_aptpl(struct se_device *, int);
+int	se_dev_set_is_nonrot(struct se_device *, int);
+int	se_dev_set_emulate_rest_reord(struct se_device *dev, int);
+int	se_dev_set_queue_depth(struct se_device *, u32);
+int	se_dev_set_max_sectors(struct se_device *, u32);
+int	se_dev_set_fabric_max_sectors(struct se_device *, u32);
+int	se_dev_set_optimal_sectors(struct se_device *, u32);
+int	se_dev_set_block_size(struct se_device *, u32);
+
 #endif /* TARGET_CORE_BACKEND_H */
-- 
cgit v1.2.3-70-g09d2


From e6c39f703a878b8d9427ca7b4dc8f97874d12ae6 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu, 27 Nov 2014 19:49:36 -0800
Subject: target: Add DEF_TB_DEFAULT_ATTRIBS macro for virtual device attrs

This helper macro adds the default set of 30 device attributes for
virtual devices from existing target_core_configfs.c code, and moves
the definitions into a single macro to create the structs necessary
for backend drivers.

It allows them to populate their own external struct configfs_attribute
for se_subsystem_api->tb_cits.tb_dev_attrib_cit.ct_attrs.

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 include/target/target_core_backend_configfs.h | 67 +++++++++++++++++++++++++++
 1 file changed, 67 insertions(+)

(limited to 'include')

diff --git a/include/target/target_core_backend_configfs.h b/include/target/target_core_backend_configfs.h
index f91935b5ef2..3247d753010 100644
--- a/include/target/target_core_backend_configfs.h
+++ b/include/target/target_core_backend_configfs.h
@@ -50,4 +50,71 @@ static struct target_backend_dev_attrib_attribute _backend##_dev_attrib_##_name
 	__CONFIGFS_EATTR_RO(_name,					\
 	_backend##_dev_show_attr_##_name);
 
+/*
+ * Default list of target backend device attributes as defined by
+ * struct se_dev_attrib
+ */
+
+#define DEF_TB_DEFAULT_ATTRIBS(_backend)				\
+	DEF_TB_DEV_ATTRIB(_backend, emulate_model_alias);		\
+	TB_DEV_ATTR(_backend, emulate_model_alias, S_IRUGO | S_IWUSR);	\
+	DEF_TB_DEV_ATTRIB(_backend, emulate_dpo);			\
+	TB_DEV_ATTR(_backend, emulate_dpo, S_IRUGO | S_IWUSR);		\
+	DEF_TB_DEV_ATTRIB(_backend, emulate_fua_write);			\
+	TB_DEV_ATTR(_backend, emulate_fua_write, S_IRUGO | S_IWUSR);	\
+	DEF_TB_DEV_ATTRIB(_backend, emulate_fua_read);			\
+	TB_DEV_ATTR(_backend, emulate_fua_read, S_IRUGO | S_IWUSR);	\
+	DEF_TB_DEV_ATTRIB(_backend, emulate_write_cache);		\
+	TB_DEV_ATTR(_backend, emulate_write_cache, S_IRUGO | S_IWUSR);	\
+	DEF_TB_DEV_ATTRIB(_backend, emulate_ua_intlck_ctrl);		\
+	TB_DEV_ATTR(_backend, emulate_ua_intlck_ctrl, S_IRUGO | S_IWUSR); \
+	DEF_TB_DEV_ATTRIB(_backend, emulate_tas);			\
+	TB_DEV_ATTR(_backend, emulate_tas, S_IRUGO | S_IWUSR);		\
+	DEF_TB_DEV_ATTRIB(_backend, emulate_tpu);			\
+	TB_DEV_ATTR(_backend, emulate_tpu, S_IRUGO | S_IWUSR);		\
+	DEF_TB_DEV_ATTRIB(_backend, emulate_tpws);			\
+	TB_DEV_ATTR(_backend, emulate_tpws, S_IRUGO | S_IWUSR);		\
+	DEF_TB_DEV_ATTRIB(_backend, emulate_caw);			\
+	TB_DEV_ATTR(_backend, emulate_caw, S_IRUGO | S_IWUSR);		\
+	DEF_TB_DEV_ATTRIB(_backend, emulate_3pc);			\
+	TB_DEV_ATTR(_backend, emulate_3pc, S_IRUGO | S_IWUSR);		\
+	DEF_TB_DEV_ATTRIB(_backend, pi_prot_type);			\
+	TB_DEV_ATTR(_backend, pi_prot_type, S_IRUGO | S_IWUSR);		\
+	DEF_TB_DEV_ATTRIB_RO(_backend, hw_pi_prot_type);		\
+	TB_DEV_ATTR_RO(_backend, hw_pi_prot_type);			\
+	DEF_TB_DEV_ATTRIB(_backend, pi_prot_format);			\
+	TB_DEV_ATTR(_backend, pi_prot_format, S_IRUGO | S_IWUSR);	\
+	DEF_TB_DEV_ATTRIB(_backend, enforce_pr_isids);			\
+	TB_DEV_ATTR(_backend, enforce_pr_isids, S_IRUGO | S_IWUSR);	\
+	DEF_TB_DEV_ATTRIB(_backend, is_nonrot);				\
+	TB_DEV_ATTR(_backend, is_nonrot, S_IRUGO | S_IWUSR);		\
+	DEF_TB_DEV_ATTRIB(_backend, emulate_rest_reord);		\
+	TB_DEV_ATTR(_backend, emulate_rest_reord, S_IRUGO | S_IWUSR);	\
+	DEF_TB_DEV_ATTRIB(_backend, force_pr_aptpl);			\
+	TB_DEV_ATTR(_backend, force_pr_aptpl, S_IRUGO | S_IWUSR);	\
+	DEF_TB_DEV_ATTRIB_RO(_backend, hw_block_size);			\
+	TB_DEV_ATTR_RO(_backend, hw_block_size);			\
+	DEF_TB_DEV_ATTRIB(_backend, block_size);			\
+	TB_DEV_ATTR(_backend, block_size, S_IRUGO | S_IWUSR);		\
+	DEF_TB_DEV_ATTRIB_RO(_backend, hw_max_sectors);			\
+	TB_DEV_ATTR_RO(_backend, hw_max_sectors);			\
+	DEF_TB_DEV_ATTRIB(_backend, fabric_max_sectors);		\
+	TB_DEV_ATTR(_backend, fabric_max_sectors, S_IRUGO | S_IWUSR);	\
+	DEF_TB_DEV_ATTRIB(_backend, optimal_sectors);			\
+	TB_DEV_ATTR(_backend, optimal_sectors, S_IRUGO | S_IWUSR);	\
+	DEF_TB_DEV_ATTRIB_RO(_backend, hw_queue_depth);			\
+	TB_DEV_ATTR_RO(_backend, hw_queue_depth);			\
+	DEF_TB_DEV_ATTRIB(_backend, queue_depth);			\
+	TB_DEV_ATTR(_backend, queue_depth, S_IRUGO | S_IWUSR);		\
+	DEF_TB_DEV_ATTRIB(_backend, max_unmap_lba_count);		\
+	TB_DEV_ATTR(_backend, max_unmap_lba_count, S_IRUGO | S_IWUSR);	\
+	DEF_TB_DEV_ATTRIB(_backend, max_unmap_block_desc_count);	\
+	TB_DEV_ATTR(_backend, max_unmap_block_desc_count, S_IRUGO | S_IWUSR); \
+	DEF_TB_DEV_ATTRIB(_backend, unmap_granularity);			\
+	TB_DEV_ATTR(_backend, unmap_granularity, S_IRUGO | S_IWUSR);	\
+	DEF_TB_DEV_ATTRIB(_backend, unmap_granularity_alignment);	\
+	TB_DEV_ATTR(_backend, unmap_granularity_alignment, S_IRUGO | S_IWUSR); \
+	DEF_TB_DEV_ATTRIB(_backend, max_write_same_len);		\
+	TB_DEV_ATTR(_backend, max_write_same_len, S_IRUGO | S_IWUSR);
+
 #endif /* TARGET_CORE_BACKEND_CONFIGFS_H */
-- 
cgit v1.2.3-70-g09d2


From 0bd49fc75aab94a7bf3cd2f7c70e03b600635c65 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Tue, 2 Dec 2014 10:09:26 +0200
Subject: Bluetooth: Track both local and remote L2CAP fixed channel mask

To pave the way for future fixed channels to be added easily we should
track both the local and remote mask on a per-L2CAP connection (struct
l2cap_conn) basis. So far the code has used a global variable in a racy
way which anyway needs fixing.

This patch renames the existing conn->fixed_chan_mask that tracked
the remote mask to conn->remote_fixed_chan and adds a new variable
conn->local_fixed_chan to track the local mask. Since the HS support
info is now available in the local mask we can remove the
conn->hs_enabled variable.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h |  4 ++--
 net/bluetooth/l2cap_core.c    | 37 ++++++++++++++++++-------------------
 2 files changed, 20 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 061e648052c..d71dc357935 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -619,8 +619,8 @@ struct l2cap_conn {
 	unsigned int		mtu;
 
 	__u32			feat_mask;
-	__u8			fixed_chan_mask;
-	bool			hs_enabled;
+	__u8			remote_fixed_chan;
+	__u8			local_fixed_chan;
 
 	__u8			info_state;
 	__u8			info_ident;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index c2d1489c228..43349ed4c24 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -46,7 +46,6 @@
 bool disable_ertm;
 
 static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN | L2CAP_FEAT_UCD;
-static u8 l2cap_fixed_chan[8] = { L2CAP_FC_SIG_BREDR | L2CAP_FC_CONNLESS, };
 
 static LIST_HEAD(chan_list);
 static DEFINE_RWLOCK(chan_list_lock);
@@ -1120,10 +1119,10 @@ static bool __amp_capable(struct l2cap_chan *chan)
 	struct hci_dev *hdev;
 	bool amp_available = false;
 
-	if (!conn->hs_enabled)
+	if (!(conn->local_fixed_chan & L2CAP_FC_A2MP))
 		return false;
 
-	if (!(conn->fixed_chan_mask & L2CAP_FC_A2MP))
+	if (!(conn->remote_fixed_chan & L2CAP_FC_A2MP))
 		return false;
 
 	read_lock(&hci_dev_list_lock);
@@ -3096,12 +3095,14 @@ static inline __u8 l2cap_select_mode(__u8 mode, __u16 remote_feat_mask)
 
 static inline bool __l2cap_ews_supported(struct l2cap_conn *conn)
 {
-	return conn->hs_enabled && conn->feat_mask & L2CAP_FEAT_EXT_WINDOW;
+	return ((conn->local_fixed_chan & L2CAP_FC_A2MP) &&
+		(conn->feat_mask & L2CAP_FEAT_EXT_WINDOW));
 }
 
 static inline bool __l2cap_efs_supported(struct l2cap_conn *conn)
 {
-	return conn->hs_enabled && conn->feat_mask & L2CAP_FEAT_EXT_FLOW;
+	return ((conn->local_fixed_chan & L2CAP_FC_A2MP) &&
+		(conn->feat_mask & L2CAP_FEAT_EXT_FLOW));
 }
 
 static void __l2cap_set_ertm_timeouts(struct l2cap_chan *chan,
@@ -3330,7 +3331,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data)
 			break;
 
 		case L2CAP_CONF_EWS:
-			if (!chan->conn->hs_enabled)
+			if (!(chan->conn->local_fixed_chan & L2CAP_FC_A2MP))
 				return -ECONNREFUSED;
 
 			set_bit(FLAG_EXT_CTRL, &chan->flags);
@@ -4334,7 +4335,7 @@ static inline int l2cap_information_req(struct l2cap_conn *conn,
 		if (!disable_ertm)
 			feat_mask |= L2CAP_FEAT_ERTM | L2CAP_FEAT_STREAMING
 				| L2CAP_FEAT_FCS;
-		if (conn->hs_enabled)
+		if (conn->local_fixed_chan & L2CAP_FC_A2MP)
 			feat_mask |= L2CAP_FEAT_EXT_FLOW
 				| L2CAP_FEAT_EXT_WINDOW;
 
@@ -4345,14 +4346,10 @@ static inline int l2cap_information_req(struct l2cap_conn *conn,
 		u8 buf[12];
 		struct l2cap_info_rsp *rsp = (struct l2cap_info_rsp *) buf;
 
-		if (conn->hs_enabled)
-			l2cap_fixed_chan[0] |= L2CAP_FC_A2MP;
-		else
-			l2cap_fixed_chan[0] &= ~L2CAP_FC_A2MP;
-
 		rsp->type   = cpu_to_le16(L2CAP_IT_FIXED_CHAN);
 		rsp->result = cpu_to_le16(L2CAP_IR_SUCCESS);
-		memcpy(rsp->data, l2cap_fixed_chan, sizeof(l2cap_fixed_chan));
+		rsp->data[0] = conn->local_fixed_chan;
+		memset(rsp->data + 1, 0, 7);
 		l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(buf),
 			       buf);
 	} else {
@@ -4418,7 +4415,7 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn,
 		break;
 
 	case L2CAP_IT_FIXED_CHAN:
-		conn->fixed_chan_mask = rsp->data[0];
+		conn->remote_fixed_chan = rsp->data[0];
 		conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE;
 		conn->info_ident = 0;
 
@@ -4442,7 +4439,7 @@ static int l2cap_create_channel_req(struct l2cap_conn *conn,
 	if (cmd_len != sizeof(*req))
 		return -EPROTO;
 
-	if (!conn->hs_enabled)
+	if (!(conn->local_fixed_chan & L2CAP_FC_A2MP))
 		return -EINVAL;
 
 	psm = le16_to_cpu(req->psm);
@@ -4872,7 +4869,7 @@ static inline int l2cap_move_channel_req(struct l2cap_conn *conn,
 
 	BT_DBG("icid 0x%4.4x, dest_amp_id %d", icid, req->dest_amp_id);
 
-	if (!conn->hs_enabled)
+	if (!(conn->local_fixed_chan & L2CAP_FC_A2MP))
 		return -EINVAL;
 
 	chan = l2cap_get_chan_by_dcid(conn, icid);
@@ -6964,9 +6961,11 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon)
 
 	conn->feat_mask = 0;
 
-	if (hcon->type == ACL_LINK)
-		conn->hs_enabled = test_bit(HCI_HS_ENABLED,
-					    &hcon->hdev->dev_flags);
+	conn->local_fixed_chan = L2CAP_FC_SIG_BREDR | L2CAP_FC_CONNLESS;
+
+	if (hcon->type == ACL_LINK &&
+	    test_bit(HCI_HS_ENABLED, &hcon->hdev->dev_flags))
+		conn->local_fixed_chan |= L2CAP_FC_A2MP;
 
 	mutex_init(&conn->ident_lock);
 	mutex_init(&conn->chan_lock);
-- 
cgit v1.2.3-70-g09d2


From 3f4994cfc15f38a3159c6e3a4b3ab2e1481a6b02 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Tue, 2 Dec 2014 16:52:06 +1100
Subject: kcmp: Move kcmp.h into uapi

kcmp.h appears to be part of the API, it's documented in kcmp(2), and
the selftests/kcmp code uses it. So move it to uapi so it's actually
exported.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Acked-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
---
 include/linux/kcmp.h      | 17 -----------------
 include/uapi/linux/Kbuild |  1 +
 include/uapi/linux/kcmp.h | 17 +++++++++++++++++
 3 files changed, 18 insertions(+), 17 deletions(-)
 delete mode 100644 include/linux/kcmp.h
 create mode 100644 include/uapi/linux/kcmp.h

(limited to 'include')

diff --git a/include/linux/kcmp.h b/include/linux/kcmp.h
deleted file mode 100644
index 2dcd1b3aafc..00000000000
--- a/include/linux/kcmp.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef _LINUX_KCMP_H
-#define _LINUX_KCMP_H
-
-/* Comparison type */
-enum kcmp_type {
-	KCMP_FILE,
-	KCMP_VM,
-	KCMP_FILES,
-	KCMP_FS,
-	KCMP_SIGHAND,
-	KCMP_IO,
-	KCMP_SYSVSEM,
-
-	KCMP_TYPES,
-};
-
-#endif /* _LINUX_KCMP_H */
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index b70237e8bc3..1cf50d682db 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -209,6 +209,7 @@ header-y += ivtvfb.h
 header-y += ixjuser.h
 header-y += jffs2.h
 header-y += joystick.h
+header-y += kcmp.h
 header-y += kd.h
 header-y += kdev_t.h
 header-y += kernel-page-flags.h
diff --git a/include/uapi/linux/kcmp.h b/include/uapi/linux/kcmp.h
new file mode 100644
index 00000000000..84df14b3736
--- /dev/null
+++ b/include/uapi/linux/kcmp.h
@@ -0,0 +1,17 @@
+#ifndef _UAPI_LINUX_KCMP_H
+#define _UAPI_LINUX_KCMP_H
+
+/* Comparison type */
+enum kcmp_type {
+	KCMP_FILE,
+	KCMP_VM,
+	KCMP_FILES,
+	KCMP_FS,
+	KCMP_SIGHAND,
+	KCMP_IO,
+	KCMP_SYSVSEM,
+
+	KCMP_TYPES,
+};
+
+#endif /* _UAPI_LINUX_KCMP_H */
-- 
cgit v1.2.3-70-g09d2


From 3682f49f32051765ed6eb77fc882f0458f7d44c3 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Tue, 2 Dec 2014 21:27:50 +0100
Subject: NFC: netlink: Add new netlink command NFC_CMD_ACTIVATE_TARGET

Some tag might get deactivated after some read or write tentative.
This may happen for example with Mifare Ultralight C tag when trying
to read the last 4 blocks (starting block 0x2c) configured as write
only.
NFC_CMD_ACTIVATE_TARGET will try to reselect the tag in order to
detect if it got remove from the field or if it is still present.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/uapi/linux/nfc.h |  1 +
 net/nfc/netlink.c        | 30 ++++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h
index 19a75daac14..3c5efb1bc39 100644
--- a/include/uapi/linux/nfc.h
+++ b/include/uapi/linux/nfc.h
@@ -116,6 +116,7 @@ enum nfc_commands {
 	NFC_EVENT_SE_TRANSACTION,
 	NFC_CMD_GET_SE,
 	NFC_CMD_SE_IO,
+	NFC_CMD_ACTIVATE_TARGET,
 /* private: internal use only */
 	__NFC_CMD_AFTER_LAST
 };
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 43cb1c17e26..95818314aea 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -810,6 +810,31 @@ out:
 	return rc;
 }
 
+static int nfc_genl_activate_target(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nfc_dev *dev;
+	u32 device_idx, target_idx, protocol;
+	int rc;
+
+	if (!info->attrs[NFC_ATTR_DEVICE_INDEX])
+		return -EINVAL;
+
+	device_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]);
+
+	dev = nfc_get_device(device_idx);
+	if (!dev)
+		return -ENODEV;
+
+	target_idx = nla_get_u32(info->attrs[NFC_ATTR_TARGET_INDEX]);
+	protocol = nla_get_u32(info->attrs[NFC_ATTR_PROTOCOLS]);
+
+	nfc_deactivate_target(dev, target_idx);
+	rc = nfc_activate_target(dev, target_idx, protocol);
+
+	nfc_put_device(dev);
+	return 0;
+}
+
 static int nfc_genl_dep_link_up(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nfc_dev *dev;
@@ -1455,6 +1480,11 @@ static const struct genl_ops nfc_genl_ops[] = {
 		.doit = nfc_genl_se_io,
 		.policy = nfc_genl_policy,
 	},
+	{
+		.cmd = NFC_CMD_ACTIVATE_TARGET,
+		.doit = nfc_genl_activate_target,
+		.policy = nfc_genl_policy,
+	},
 };
 
 
-- 
cgit v1.2.3-70-g09d2


From b3a55b9c5d44d0ed38eb6e8593a47578801730de Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Tue, 2 Dec 2014 21:27:52 +0100
Subject: NFC: hci: Add specific hci macro to not create a pipe

Some pipe are only created by other host (different than the
Terminal Host).
The pipe values will for example be notified by
NFC_HCI_ADM_NOTIFY_PIPE_CREATED.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/hci.h | 1 +
 net/nfc/hci/command.c | 3 +++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index 50bc66f0121..14bd0e1c47f 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -64,6 +64,7 @@ struct nfc_hci_ops {
 
 /* Pipes */
 #define NFC_HCI_INVALID_PIPE	0x80
+#define NFC_HCI_DO_NOT_CREATE_PIPE	0x81
 #define NFC_HCI_LINK_MGMT_PIPE	0x00
 #define NFC_HCI_ADMIN_PIPE	0x01
 
diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c
index 677d24bb70f..91df487aa0a 100644
--- a/net/nfc/hci/command.c
+++ b/net/nfc/hci/command.c
@@ -345,6 +345,9 @@ int nfc_hci_connect_gate(struct nfc_hci_dev *hdev, u8 dest_host, u8 dest_gate,
 
 	pr_debug("\n");
 
+	if (hdev->gate2pipe[dest_gate] == NFC_HCI_DO_NOT_CREATE_PIPE)
+		return 0;
+
 	if (hdev->gate2pipe[dest_gate] != NFC_HCI_INVALID_PIPE)
 		return -EADDRINUSE;
 
-- 
cgit v1.2.3-70-g09d2


From e479ce479743984a5d4581749f9aaa9c3bfd65e4 Mon Sep 17 00:00:00 2001
From: Julien Lefrique <lefrique@marvell.com>
Date: Tue, 2 Dec 2014 16:25:01 +0100
Subject: NFC: NCI: Fix max length of General Bytes in ATR_RES

The maximum size of ATR_REQ and ATR_RES is 64 bytes.
The maximum number of General Bytes is calculated by
the maximum number of data bytes in the ATR_REQ/ATR_RES,
substracted by the number of mandatory data bytes.

ATR_REQ: 16 mandatory data bytes, giving a maximum of
48 General Bytes.
ATR_RES: 17 mandatory data bytes, giving a maximum of
47 General Bytes.

Regression introduced in commit a99903ec.

Signed-off-by: Julien Lefrique <lefrique@marvell.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/uapi/linux/nfc.h | 2 ++
 net/nfc/nci/ntf.c        | 8 +++-----
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h
index 3c5efb1bc39..8119255feae 100644
--- a/include/uapi/linux/nfc.h
+++ b/include/uapi/linux/nfc.h
@@ -205,6 +205,8 @@ enum nfc_sdp_attr {
 #define NFC_SENSF_RES_MAXSIZE		18
 #define NFC_ATR_REQ_MAXSIZE		64
 #define NFC_ATR_RES_MAXSIZE		64
+#define NFC_ATR_REQ_GB_MAXSIZE		48
+#define NFC_ATR_RES_GB_MAXSIZE		47
 #define NFC_GB_MAXSIZE			48
 #define NFC_FIRMWARE_NAME_MAXSIZE	32
 #define NFC_ISO15693_UID_MAXSIZE	8
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index 8dee73d0c4e..22e453cb787 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -479,24 +479,22 @@ static int nci_store_general_bytes_nfc_dep(struct nci_dev *ndev,
 	switch (ntf->activation_rf_tech_and_mode) {
 	case NCI_NFC_A_PASSIVE_POLL_MODE:
 	case NCI_NFC_F_PASSIVE_POLL_MODE:
-		/* ATR_RES general bytes at offset 15 */
 		ndev->remote_gb_len = min_t(__u8,
 			(ntf->activation_params.poll_nfc_dep.atr_res_len
 						- NFC_ATR_RES_GT_OFFSET),
-			NFC_MAX_GT_LEN);
+			NFC_ATR_RES_GB_MAXSIZE);
 		memcpy(ndev->remote_gb,
-		       (ntf->activation_params.poll_nfc_dep .atr_res
+		       (ntf->activation_params.poll_nfc_dep.atr_res
 						+ NFC_ATR_RES_GT_OFFSET),
 		       ndev->remote_gb_len);
 		break;
 
 	case NCI_NFC_A_PASSIVE_LISTEN_MODE:
 	case NCI_NFC_F_PASSIVE_LISTEN_MODE:
-		/* ATR_REQ general bytes at offset 14 */
 		ndev->remote_gb_len = min_t(__u8,
 			(ntf->activation_params.listen_nfc_dep.atr_req_len
 						- NFC_ATR_REQ_GT_OFFSET),
-			NFC_MAX_GT_LEN);
+			NFC_ATR_REQ_GB_MAXSIZE);
 		memcpy(ndev->remote_gb,
 		       (ntf->activation_params.listen_nfc_dep.atr_req
 						+ NFC_ATR_REQ_GT_OFFSET),
-- 
cgit v1.2.3-70-g09d2


From b7485f6b035a87685ce35e0e52deee6467811eb0 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Fri, 28 Nov 2014 14:34:13 +0100
Subject: neigh: sort Neighbor Cache Entry Flags

Suggested-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/neighbour.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
index 4a1d7e96dfe..2f043af7fcd 100644
--- a/include/uapi/linux/neighbour.h
+++ b/include/uapi/linux/neighbour.h
@@ -35,11 +35,10 @@ enum {
  */
 
 #define NTF_USE		0x01
-#define NTF_PROXY	0x08	/* == ATF_PUBL */
-#define NTF_ROUTER	0x80
-
 #define NTF_SELF	0x02
 #define NTF_MASTER	0x04
+#define NTF_PROXY	0x08	/* == ATF_PUBL */
+#define NTF_ROUTER	0x80
 
 /*
  *	Neighbor Cache Entry States.
-- 
cgit v1.2.3-70-g09d2


From f6f6424ba773da6221ecaaa70973eb4dacfa03b2 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Fri, 28 Nov 2014 14:34:15 +0100
Subject: net: make vid as a parameter for ndo_fdb_add/ndo_fdb_del

Do the work of parsing NDA_VLAN directly in rtnetlink code, pass simple
u16 vid to drivers from there.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c      |  2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c    |  4 +-
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c |  9 +++--
 drivers/net/macvlan.c                            |  4 +-
 drivers/net/vxlan.c                              |  4 +-
 include/linux/netdevice.h                        |  8 ++--
 include/linux/rtnetlink.h                        |  6 ++-
 net/bridge/br_fdb.c                              | 39 ++----------------
 net/bridge/br_private.h                          |  4 +-
 net/core/rtnetlink.c                             | 50 ++++++++++++++++++++----
 10 files changed, 70 insertions(+), 60 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 7262077ad54..5ed5e4036dd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7536,7 +7536,7 @@ static int i40e_get_phys_port_id(struct net_device *netdev,
  */
 static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			    struct net_device *dev,
-			    const unsigned char *addr,
+			    const unsigned char *addr, u16 vid,
 			    u16 flags)
 {
 	struct i40e_netdev_priv *np = netdev_priv(dev);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 52776f9e1f7..74aadeb56ad 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7708,7 +7708,7 @@ static int ixgbe_set_features(struct net_device *netdev,
 
 static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			     struct net_device *dev,
-			     const unsigned char *addr,
+			     const unsigned char *addr, u16 vid,
 			     u16 flags)
 {
 	/* guarantee we can provide a unique filter for the unicast address */
@@ -7717,7 +7717,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			return -ENOMEM;
 	}
 
-	return ndo_dflt_fdb_add(ndm, tb, dev, addr, flags);
+	return ndo_dflt_fdb_add(ndm, tb, dev, addr, vid, flags);
 }
 
 static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index a913b3ad2f8..3227c8063ed 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -376,13 +376,14 @@ static int qlcnic_set_mac(struct net_device *netdev, void *p)
 }
 
 static int qlcnic_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
-			struct net_device *netdev, const unsigned char *addr)
+			struct net_device *netdev,
+			const unsigned char *addr, u16 vid)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	int err = -EOPNOTSUPP;
 
 	if (!adapter->fdb_mac_learn)
-		return ndo_dflt_fdb_del(ndm, tb, netdev, addr);
+		return ndo_dflt_fdb_del(ndm, tb, netdev, addr, vid);
 
 	if ((adapter->flags & QLCNIC_ESWITCH_ENABLED) ||
 	    qlcnic_sriov_check(adapter)) {
@@ -401,13 +402,13 @@ static int qlcnic_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
 
 static int qlcnic_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			struct net_device *netdev,
-			const unsigned char *addr, u16 flags)
+			const unsigned char *addr, u16 vid, u16 flags)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	int err = 0;
 
 	if (!adapter->fdb_mac_learn)
-		return ndo_dflt_fdb_add(ndm, tb, netdev, addr, flags);
+		return ndo_dflt_fdb_add(ndm, tb, netdev, addr, vid, flags);
 
 	if (!(adapter->flags & QLCNIC_ESWITCH_ENABLED) &&
 	    !qlcnic_sriov_check(adapter)) {
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 11d4b3506d6..9538674587a 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -873,7 +873,7 @@ static int macvlan_vlan_rx_kill_vid(struct net_device *dev,
 
 static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			   struct net_device *dev,
-			   const unsigned char *addr,
+			   const unsigned char *addr, u16 vid,
 			   u16 flags)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
@@ -898,7 +898,7 @@ static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 
 static int macvlan_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
 			   struct net_device *dev,
-			   const unsigned char *addr)
+			   const unsigned char *addr, u16 vid)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	int err = -EINVAL;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d802a1ae456..31ecb03368c 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -849,7 +849,7 @@ static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan,
 /* Add static entry (via netlink) */
 static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			 struct net_device *dev,
-			 const unsigned char *addr, u16 flags)
+			 const unsigned char *addr, u16 vid, u16 flags)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	/* struct net *net = dev_net(vxlan->dev); */
@@ -885,7 +885,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 /* Delete entry (via netlink) */
 static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 			    struct net_device *dev,
-			    const unsigned char *addr)
+			    const unsigned char *addr, u16 vid)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_fdb *f;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2cb772495f7..589929cf470 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -951,11 +951,11 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *
  * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[],
  *		      struct net_device *dev,
- *		      const unsigned char *addr, u16 flags)
+ *		      const unsigned char *addr, u16 vid, u16 flags)
  *	Adds an FDB entry to dev for addr.
  * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[],
  *		      struct net_device *dev,
- *		      const unsigned char *addr)
+ *		      const unsigned char *addr, u16 vid)
  *	Deletes the FDB entry from dev coresponding to addr.
  * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb,
  *		       struct net_device *dev, struct net_device *filter_dev,
@@ -1128,11 +1128,13 @@ struct net_device_ops {
 					       struct nlattr *tb[],
 					       struct net_device *dev,
 					       const unsigned char *addr,
+					       u16 vid,
 					       u16 flags);
 	int			(*ndo_fdb_del)(struct ndmsg *ndm,
 					       struct nlattr *tb[],
 					       struct net_device *dev,
-					       const unsigned char *addr);
+					       const unsigned char *addr,
+					       u16 vid);
 	int			(*ndo_fdb_dump)(struct sk_buff *skb,
 						struct netlink_callback *cb,
 						struct net_device *dev,
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 6cacbce1a06..063f0f581fe 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -94,11 +94,13 @@ extern int ndo_dflt_fdb_add(struct ndmsg *ndm,
 			    struct nlattr *tb[],
 			    struct net_device *dev,
 			    const unsigned char *addr,
-			     u16 flags);
+			    u16 vid,
+			    u16 flags);
 extern int ndo_dflt_fdb_del(struct ndmsg *ndm,
 			    struct nlattr *tb[],
 			    struct net_device *dev,
-			    const unsigned char *addr);
+			    const unsigned char *addr,
+			    u16 vid);
 
 extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 				   struct net_device *dev, u16 mode);
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 08ef4e7a243..b1be971eb06 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -805,33 +805,17 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p,
 /* Add new permanent fdb entry with RTM_NEWNEIGH */
 int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	       struct net_device *dev,
-	       const unsigned char *addr, u16 nlh_flags)
+	       const unsigned char *addr, u16 vid, u16 nlh_flags)
 {
 	struct net_bridge_port *p;
 	int err = 0;
 	struct net_port_vlans *pv;
-	unsigned short vid = VLAN_N_VID;
 
 	if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) {
 		pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state);
 		return -EINVAL;
 	}
 
-	if (tb[NDA_VLAN]) {
-		if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) {
-			pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n");
-			return -EINVAL;
-		}
-
-		vid = nla_get_u16(tb[NDA_VLAN]);
-
-		if (!vid || vid >= VLAN_VID_MASK) {
-			pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n",
-				vid);
-			return -EINVAL;
-		}
-	}
-
 	if (is_zero_ether_addr(addr)) {
 		pr_info("bridge: RTM_NEWNEIGH with invalid ether address\n");
 		return -EINVAL;
@@ -845,7 +829,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	}
 
 	pv = nbp_get_vlan_info(p);
-	if (vid != VLAN_N_VID) {
+	if (vid) {
 		if (!pv || !test_bit(vid, pv->vlan_bitmap)) {
 			pr_info("bridge: RTM_NEWNEIGH with unconfigured "
 				"vlan %d on port %s\n", vid, dev->name);
@@ -903,27 +887,12 @@ static int __br_fdb_delete(struct net_bridge_port *p,
 /* Remove neighbor entry with RTM_DELNEIGH */
 int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 		  struct net_device *dev,
-		  const unsigned char *addr)
+		  const unsigned char *addr, u16 vid)
 {
 	struct net_bridge_port *p;
 	int err;
 	struct net_port_vlans *pv;
-	unsigned short vid = VLAN_N_VID;
-
-	if (tb[NDA_VLAN]) {
-		if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) {
-			pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n");
-			return -EINVAL;
-		}
 
-		vid = nla_get_u16(tb[NDA_VLAN]);
-
-		if (!vid || vid >= VLAN_VID_MASK) {
-			pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n",
-				vid);
-			return -EINVAL;
-		}
-	}
 	p = br_port_get_rtnl(dev);
 	if (p == NULL) {
 		pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n",
@@ -932,7 +901,7 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 	}
 
 	pv = nbp_get_vlan_info(p);
-	if (vid != VLAN_N_VID) {
+	if (vid) {
 		if (!pv || !test_bit(vid, pv->vlan_bitmap)) {
 			pr_info("bridge: RTM_DELNEIGH with unconfigured "
 				"vlan %d on port %s\n", vid, dev->name);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 5b370773ad9..1b529da8234 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -404,9 +404,9 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
 		   const unsigned char *addr, u16 vid, bool added_by_user);
 
 int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
-		  struct net_device *dev, const unsigned char *addr);
+		  struct net_device *dev, const unsigned char *addr, u16 vid);
 int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev,
-	       const unsigned char *addr, u16 nlh_flags);
+	       const unsigned char *addr, u16 vid, u16 nlh_flags);
 int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		struct net_device *dev, struct net_device *fdev, int idx);
 int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index b9b7dfaf202..1a233c1c8ab 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -36,6 +36,7 @@
 #include <linux/mutex.h>
 #include <linux/if_addr.h>
 #include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
 #include <linux/pci.h>
 #include <linux/etherdevice.h>
 
@@ -2312,7 +2313,7 @@ errout:
 int ndo_dflt_fdb_add(struct ndmsg *ndm,
 		     struct nlattr *tb[],
 		     struct net_device *dev,
-		     const unsigned char *addr,
+		     const unsigned char *addr, u16 vid,
 		     u16 flags)
 {
 	int err = -EINVAL;
@@ -2338,6 +2339,28 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm,
 }
 EXPORT_SYMBOL(ndo_dflt_fdb_add);
 
+static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid)
+{
+	u16 vid = 0;
+
+	if (vlan_attr) {
+		if (nla_len(vlan_attr) != sizeof(u16)) {
+			pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan\n");
+			return -EINVAL;
+		}
+
+		vid = nla_get_u16(vlan_attr);
+
+		if (!vid || vid >= VLAN_VID_MASK) {
+			pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan id %d\n",
+				vid);
+			return -EINVAL;
+		}
+	}
+	*p_vid = vid;
+	return 0;
+}
+
 static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
@@ -2345,6 +2368,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *tb[NDA_MAX+1];
 	struct net_device *dev;
 	u8 *addr;
+	u16 vid;
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
@@ -2370,6 +2394,10 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	addr = nla_data(tb[NDA_LLADDR]);
 
+	err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+	if (err)
+		return err;
+
 	err = -EOPNOTSUPP;
 
 	/* Support fdb on master device the net/bridge default case */
@@ -2378,7 +2406,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 		struct net_device *br_dev = netdev_master_upper_dev_get(dev);
 		const struct net_device_ops *ops = br_dev->netdev_ops;
 
-		err = ops->ndo_fdb_add(ndm, tb, dev, addr, nlh->nlmsg_flags);
+		err = ops->ndo_fdb_add(ndm, tb, dev, addr, vid,
+				       nlh->nlmsg_flags);
 		if (err)
 			goto out;
 		else
@@ -2389,9 +2418,10 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if ((ndm->ndm_flags & NTF_SELF)) {
 		if (dev->netdev_ops->ndo_fdb_add)
 			err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr,
+							   vid,
 							   nlh->nlmsg_flags);
 		else
-			err = ndo_dflt_fdb_add(ndm, tb, dev, addr,
+			err = ndo_dflt_fdb_add(ndm, tb, dev, addr, vid,
 					       nlh->nlmsg_flags);
 
 		if (!err) {
@@ -2409,7 +2439,7 @@ out:
 int ndo_dflt_fdb_del(struct ndmsg *ndm,
 		     struct nlattr *tb[],
 		     struct net_device *dev,
-		     const unsigned char *addr)
+		     const unsigned char *addr, u16 vid)
 {
 	int err = -EINVAL;
 
@@ -2438,6 +2468,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct net_device *dev;
 	int err = -EINVAL;
 	__u8 *addr;
+	u16 vid;
 
 	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
@@ -2465,6 +2496,10 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	addr = nla_data(tb[NDA_LLADDR]);
 
+	err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+	if (err)
+		return err;
+
 	err = -EOPNOTSUPP;
 
 	/* Support fdb on master device the net/bridge default case */
@@ -2474,7 +2509,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 		const struct net_device_ops *ops = br_dev->netdev_ops;
 
 		if (ops->ndo_fdb_del)
-			err = ops->ndo_fdb_del(ndm, tb, dev, addr);
+			err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid);
 
 		if (err)
 			goto out;
@@ -2485,9 +2520,10 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 	/* Embedded bridge, macvlan, and any other device support */
 	if (ndm->ndm_flags & NTF_SELF) {
 		if (dev->netdev_ops->ndo_fdb_del)
-			err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr);
+			err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr,
+							   vid);
 		else
-			err = ndo_dflt_fdb_del(ndm, tb, dev, addr);
+			err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid);
 
 		if (!err) {
 			rtnl_fdb_notify(dev, addr, RTM_DELNEIGH);
-- 
cgit v1.2.3-70-g09d2


From 02637fce3e0103ba086b9c33b6d529e69460e4b6 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Fri, 28 Nov 2014 14:34:16 +0100
Subject: net: rename netdev_phys_port_id to more generic name

So this can be reused for identification of other "items" as well.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Reviewed-by: Thomas Graf <tgraf@suug.ch>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c |  2 +-
 drivers/net/ethernet/intel/i40e/i40e_main.c      |  2 +-
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c   |  2 +-
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c |  2 +-
 include/linux/netdevice.h                        | 16 ++++++++--------
 net/core/dev.c                                   |  2 +-
 net/core/net-sysfs.c                             |  2 +-
 net/core/rtnetlink.c                             |  6 +++---
 8 files changed, 17 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index c4bd025c74c..336ef3cf577 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12537,7 +12537,7 @@ static int bnx2x_validate_addr(struct net_device *dev)
 }
 
 static int bnx2x_get_phys_port_id(struct net_device *netdev,
-				  struct netdev_phys_port_id *ppid)
+				  struct netdev_phys_item_id *ppid)
 {
 	struct bnx2x *bp = netdev_priv(netdev);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5ed5e4036dd..9ae4270db0b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7511,7 +7511,7 @@ static void i40e_del_vxlan_port(struct net_device *netdev,
 
 #endif
 static int i40e_get_phys_port_id(struct net_device *netdev,
-				 struct netdev_phys_port_id *ppid)
+				 struct netdev_phys_item_id *ppid)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index b7c99780aef..1597fb07576 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2259,7 +2259,7 @@ static int mlx4_en_set_vf_link_state(struct net_device *dev, int vf, int link_st
 
 #define PORT_ID_BYTE_LEN 8
 static int mlx4_en_get_phys_port_id(struct net_device *dev,
-				    struct netdev_phys_port_id *ppid)
+				    struct netdev_phys_item_id *ppid)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_dev *mdev = priv->mdev->dev;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 3227c8063ed..1aa25b13ace 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -461,7 +461,7 @@ static void qlcnic_82xx_cancel_idc_work(struct qlcnic_adapter *adapter)
 }
 
 static int qlcnic_get_phys_port_id(struct net_device *netdev,
-				   struct netdev_phys_port_id *ppid)
+				   struct netdev_phys_item_id *ppid)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 589929cf470..4bd41d72559 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -754,13 +754,13 @@ struct netdev_fcoe_hbainfo {
 };
 #endif
 
-#define MAX_PHYS_PORT_ID_LEN 32
+#define MAX_PHYS_ITEM_ID_LEN 32
 
-/* This structure holds a unique identifier to identify the
- * physical port used by a netdevice.
+/* This structure holds a unique identifier to identify some
+ * physical item (port for example) used by a netdevice.
  */
-struct netdev_phys_port_id {
-	unsigned char id[MAX_PHYS_PORT_ID_LEN];
+struct netdev_phys_item_id {
+	unsigned char id[MAX_PHYS_ITEM_ID_LEN];
 	unsigned char id_len;
 };
 
@@ -976,7 +976,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *	USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function.
  *
  * int (*ndo_get_phys_port_id)(struct net_device *dev,
- *			       struct netdev_phys_port_id *ppid);
+ *			       struct netdev_phys_item_id *ppid);
  *	Called to get ID of physical port of this device. If driver does
  *	not implement this, it is assumed that the hw is not able to have
  *	multiple net devices on single physical port.
@@ -1152,7 +1152,7 @@ struct net_device_ops {
 	int			(*ndo_change_carrier)(struct net_device *dev,
 						      bool new_carrier);
 	int			(*ndo_get_phys_port_id)(struct net_device *dev,
-							struct netdev_phys_port_id *ppid);
+							struct netdev_phys_item_id *ppid);
 	void			(*ndo_add_vxlan_port)(struct  net_device *dev,
 						      sa_family_t sa_family,
 						      __be16 port);
@@ -2870,7 +2870,7 @@ void dev_set_group(struct net_device *, int);
 int dev_set_mac_address(struct net_device *, struct sockaddr *);
 int dev_change_carrier(struct net_device *, bool new_carrier);
 int dev_get_phys_port_id(struct net_device *dev,
-			 struct netdev_phys_port_id *ppid);
+			 struct netdev_phys_item_id *ppid);
 struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev);
 struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 				    struct netdev_queue *txq, int *ret);
diff --git a/net/core/dev.c b/net/core/dev.c
index ac4836241a9..0814a560e5f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5846,7 +5846,7 @@ EXPORT_SYMBOL(dev_change_carrier);
  *	Get device physical port ID
  */
 int dev_get_phys_port_id(struct net_device *dev,
-			 struct netdev_phys_port_id *ppid)
+			 struct netdev_phys_item_id *ppid)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 1a24602cd54..26c46f4726c 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -404,7 +404,7 @@ static ssize_t phys_port_id_show(struct device *dev,
 		return restart_syscall();
 
 	if (dev_isalive(netdev)) {
-		struct netdev_phys_port_id ppid;
+		struct netdev_phys_item_id ppid;
 
 		ret = dev_get_phys_port_id(netdev, &ppid);
 		if (!ret)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1a233c1c8ab..0640f1fbe9d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -869,7 +869,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
 	       + rtnl_link_get_size(dev) /* IFLA_LINKINFO */
 	       + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
-	       + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */
+	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_PORT_ID */
 }
 
 static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
@@ -953,7 +953,7 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev,
 static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
 {
 	int err;
-	struct netdev_phys_port_id ppid;
+	struct netdev_phys_item_id ppid;
 
 	err = dev_get_phys_port_id(dev, &ppid);
 	if (err) {
@@ -1197,7 +1197,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_PROMISCUITY]	= { .type = NLA_U32 },
 	[IFLA_NUM_TX_QUEUES]	= { .type = NLA_U32 },
 	[IFLA_NUM_RX_QUEUES]	= { .type = NLA_U32 },
-	[IFLA_PHYS_PORT_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN },
+	[IFLA_PHYS_PORT_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
 	[IFLA_CARRIER_CHANGES]	= { .type = NLA_U32 },  /* ignored */
 };
 
-- 
cgit v1.2.3-70-g09d2


From 007f790c8276271de26416f90d55561bcc96588a Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Fri, 28 Nov 2014 14:34:17 +0100
Subject: net: introduce generic switch devices support

The goal of this is to provide a possibility to support various switch
chips. Drivers should implement relevant ndos to do so. Now there is
only one ndo defined:
- for getting physical switch id is in place.

Note that user can use random port netdevice to access the switch.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Reviewed-by: Thomas Graf <tgraf@suug.ch>
Acked-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/switchdev.txt | 59 ++++++++++++++++++++++++++++++++++
 MAINTAINERS                            |  7 ++++
 include/linux/netdevice.h              | 10 ++++++
 include/net/switchdev.h                | 30 +++++++++++++++++
 net/Kconfig                            |  1 +
 net/Makefile                           |  3 ++
 net/switchdev/Kconfig                  | 13 ++++++++
 net/switchdev/Makefile                 |  5 +++
 net/switchdev/switchdev.c              | 33 +++++++++++++++++++
 9 files changed, 161 insertions(+)
 create mode 100644 Documentation/networking/switchdev.txt
 create mode 100644 include/net/switchdev.h
 create mode 100644 net/switchdev/Kconfig
 create mode 100644 net/switchdev/Makefile
 create mode 100644 net/switchdev/switchdev.c

(limited to 'include')

diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt
new file mode 100644
index 00000000000..f981a9295a3
--- /dev/null
+++ b/Documentation/networking/switchdev.txt
@@ -0,0 +1,59 @@
+Switch (and switch-ish) device drivers HOWTO
+===========================
+
+Please note that the word "switch" is here used in very generic meaning.
+This include devices supporting L2/L3 but also various flow offloading chips,
+including switches embedded into SR-IOV NICs.
+
+Lets describe a topology a bit. Imagine the following example:
+
+       +----------------------------+    +---------------+
+       |     SOME switch chip       |    |      CPU      |
+       +----------------------------+    +---------------+
+       port1 port2 port3 port4 MNGMNT    |     PCI-E     |
+         |     |     |     |     |       +---------------+
+        PHY   PHY    |     |     |         |  NIC0 NIC1
+                     |     |     |         |   |    |
+                     |     |     +- PCI-E -+   |    |
+                     |     +------- MII -------+    |
+                     +------------- MII ------------+
+
+In this example, there are two independent lines between the switch silicon
+and CPU. NIC0 and NIC1 drivers are not aware of a switch presence. They are
+separate from the switch driver. SOME switch chip is by managed by a driver
+via PCI-E device MNGMNT. Note that MNGMNT device, NIC0 and NIC1 may be
+connected to some other type of bus.
+
+Now, for the previous example show the representation in kernel:
+
+       +----------------------------+    +---------------+
+       |     SOME switch chip       |    |      CPU      |
+       +----------------------------+    +---------------+
+       sw0p0 sw0p1 sw0p2 sw0p3 MNGMNT    |     PCI-E     |
+         |     |     |     |     |       +---------------+
+        PHY   PHY    |     |     |         |  eth0 eth1
+                     |     |     |         |   |    |
+                     |     |     +- PCI-E -+   |    |
+                     |     +------- MII -------+    |
+                     +------------- MII ------------+
+
+Lets call the example switch driver for SOME switch chip "SOMEswitch". This
+driver takes care of PCI-E device MNGMNT. There is a netdevice instance sw0pX
+created for each port of a switch. These netdevices are instances
+of "SOMEswitch" driver. sw0pX netdevices serve as a "representation"
+of the switch chip. eth0 and eth1 are instances of some other existing driver.
+
+The only difference of the switch-port netdevice from the ordinary netdevice
+is that is implements couple more NDOs:
+
+  ndo_switch_parent_id_get - This returns the same ID for two port netdevices
+			     of the same physical switch chip. This is
+			     mandatory to be implemented by all switch drivers
+			     and serves the caller for recognition of a port
+			     netdevice.
+  ndo_switch_parent_* - Functions that serve for a manipulation of the switch
+			chip itself (it can be though of as a "parent" of the
+			port, therefore the name). They are not port-specific.
+			Caller might use arbitrary port netdevice of the same
+			switch and it will make no difference.
+  ndo_switch_port_* - Functions that serve for a port-specific manipulation.
diff --git a/MAINTAINERS b/MAINTAINERS
index 6b880deae3d..3aba0ac2d5a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9059,6 +9059,13 @@ F:	lib/swiotlb.c
 F:	arch/*/kernel/pci-swiotlb.c
 F:	include/linux/swiotlb.h
 
+SWITCHDEV
+M:	Jiri Pirko <jiri@resnulli.us>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	net/switchdev/
+F:	include/net/switchdev.h
+
 SYNOPSYS ARC ARCHITECTURE
 M:	Vineet Gupta <vgupta@synopsys.com>
 S:	Supported
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4bd41d72559..3603f31e78f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1018,6 +1018,12 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *	performing GSO on a packet. The device returns true if it is
  *	able to GSO the packet, false otherwise. If the return value is
  *	false the stack will do software GSO.
+ *
+ * int (*ndo_switch_parent_id_get)(struct net_device *dev,
+ *				   struct netdev_phys_item_id *psid);
+ *	Called to get an ID of the switch chip this port is part of.
+ *	If driver implements this, it indicates that it represents a port
+ *	of a switch chip.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1171,6 +1177,10 @@ struct net_device_ops {
 	int			(*ndo_get_lock_subclass)(struct net_device *dev);
 	bool			(*ndo_gso_check) (struct sk_buff *skb,
 						  struct net_device *dev);
+#ifdef CONFIG_NET_SWITCHDEV
+	int			(*ndo_switch_parent_id_get)(struct net_device *dev,
+							    struct netdev_phys_item_id *psid);
+#endif
 };
 
 /**
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
new file mode 100644
index 00000000000..7a52360a144
--- /dev/null
+++ b/include/net/switchdev.h
@@ -0,0 +1,30 @@
+/*
+ * include/net/switchdev.h - Switch device API
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef _LINUX_SWITCHDEV_H_
+#define _LINUX_SWITCHDEV_H_
+
+#include <linux/netdevice.h>
+
+#ifdef CONFIG_NET_SWITCHDEV
+
+int netdev_switch_parent_id_get(struct net_device *dev,
+				struct netdev_phys_item_id *psid);
+
+#else
+
+static inline int netdev_switch_parent_id_get(struct net_device *dev,
+					      struct netdev_phys_item_id *psid)
+{
+	return -EOPNOTSUPP;
+}
+
+#endif
+
+#endif /* _LINUX_SWITCHDEV_H_ */
diff --git a/net/Kconfig b/net/Kconfig
index 99815b5454b..ff9ffc17fa0 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -228,6 +228,7 @@ source "net/vmw_vsock/Kconfig"
 source "net/netlink/Kconfig"
 source "net/mpls/Kconfig"
 source "net/hsr/Kconfig"
+source "net/switchdev/Kconfig"
 
 config RPS
 	boolean
diff --git a/net/Makefile b/net/Makefile
index 7ed1970074b..95fc694e4dd 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -73,3 +73,6 @@ obj-$(CONFIG_OPENVSWITCH)	+= openvswitch/
 obj-$(CONFIG_VSOCKETS)	+= vmw_vsock/
 obj-$(CONFIG_NET_MPLS_GSO)	+= mpls/
 obj-$(CONFIG_HSR)		+= hsr/
+ifneq ($(CONFIG_NET_SWITCHDEV),)
+obj-y				+= switchdev/
+endif
diff --git a/net/switchdev/Kconfig b/net/switchdev/Kconfig
new file mode 100644
index 00000000000..155754588fd
--- /dev/null
+++ b/net/switchdev/Kconfig
@@ -0,0 +1,13 @@
+#
+# Configuration for Switch device support
+#
+
+config NET_SWITCHDEV
+	boolean "Switch (and switch-ish) device support (EXPERIMENTAL)"
+	depends on INET
+	---help---
+	  This module provides glue between core networking code and device
+	  drivers in order to support hardware switch chips in very generic
+	  meaning of the word "switch". This include devices supporting L2/L3 but
+	  also various flow offloading chips, including switches embedded into
+	  SR-IOV NICs.
diff --git a/net/switchdev/Makefile b/net/switchdev/Makefile
new file mode 100644
index 00000000000..5ed63ed324d
--- /dev/null
+++ b/net/switchdev/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Switch device API
+#
+
+obj-$(CONFIG_NET_SWITCHDEV) += switchdev.o
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
new file mode 100644
index 00000000000..66973deaae5
--- /dev/null
+++ b/net/switchdev/switchdev.c
@@ -0,0 +1,33 @@
+/*
+ * net/switchdev/switchdev.c - Switch device API
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <net/switchdev.h>
+
+/**
+ *	netdev_switch_parent_id_get - Get ID of a switch
+ *	@dev: port device
+ *	@psid: switch ID
+ *
+ *	Get ID of a switch this port is part of.
+ */
+int netdev_switch_parent_id_get(struct net_device *dev,
+				struct netdev_phys_item_id *psid)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!ops->ndo_switch_parent_id_get)
+		return -EOPNOTSUPP;
+	return ops->ndo_switch_parent_id_get(dev, psid);
+}
+EXPORT_SYMBOL(netdev_switch_parent_id_get);
-- 
cgit v1.2.3-70-g09d2


From 82f2841291cfaf4d225aa1766424280254d3e3b2 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Fri, 28 Nov 2014 14:34:18 +0100
Subject: rtnl: expose physical switch id for particular device

The netdevice represents a port in a switch, it will expose
IFLA_PHYS_SWITCH_ID value via rtnl. Two netdevices with the same value
belong to one physical switch.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Reviewed-by: Thomas Graf <tgraf@suug.ch>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_link.h |  1 +
 net/core/rtnetlink.c         | 26 +++++++++++++++++++++++++-
 2 files changed, 26 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 36bddc23363..623f1a7c762 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -145,6 +145,7 @@ enum {
 	IFLA_CARRIER,
 	IFLA_PHYS_PORT_ID,
 	IFLA_CARRIER_CHANGES,
+	IFLA_PHYS_SWITCH_ID,
 	__IFLA_MAX
 };
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 0640f1fbe9d..aa5cd2c53a5 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -44,6 +44,7 @@
 
 #include <linux/inet.h>
 #include <linux/netdevice.h>
+#include <net/switchdev.h>
 #include <net/ip.h>
 #include <net/protocol.h>
 #include <net/arp.h>
@@ -869,7 +870,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
 	       + rtnl_link_get_size(dev) /* IFLA_LINKINFO */
 	       + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
-	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_PORT_ID */
+	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
+	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_SWITCH_ID */
 }
 
 static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
@@ -968,6 +970,24 @@ static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
 	return 0;
 }
 
+static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
+{
+	int err;
+	struct netdev_phys_item_id psid;
+
+	err = netdev_switch_parent_id_get(dev, &psid);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	if (nla_put(skb, IFLA_PHYS_SWITCH_ID, psid.id_len, psid.id))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
 static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			    int type, u32 pid, u32 seq, u32 change,
 			    unsigned int flags, u32 ext_filter_mask)
@@ -1040,6 +1060,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 	if (rtnl_phys_port_id_fill(skb, dev))
 		goto nla_put_failure;
 
+	if (rtnl_phys_switch_id_fill(skb, dev))
+		goto nla_put_failure;
+
 	attr = nla_reserve(skb, IFLA_STATS,
 			sizeof(struct rtnl_link_stats));
 	if (attr == NULL)
@@ -1199,6 +1222,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_NUM_RX_QUEUES]	= { .type = NLA_U32 },
 	[IFLA_PHYS_PORT_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
 	[IFLA_CARRIER_CHANGES]	= { .type = NLA_U32 },  /* ignored */
+	[IFLA_PHYS_SWITCH_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
-- 
cgit v1.2.3-70-g09d2


From 38dcf357aed299186ecb090cc2f5290cc17d637d Mon Sep 17 00:00:00 2001
From: Scott Feldman <sfeldma@gmail.com>
Date: Fri, 28 Nov 2014 14:34:20 +0100
Subject: bridge: call netdev_sw_port_stp_update when bridge port STP status
 changes

To notify switch driver of change in STP state of bridge port, add new
.ndo op and provide switchdev wrapper func to call ndo op. Use it in bridge
code then.

Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  5 +++++
 include/net/switchdev.h   |  7 +++++++
 net/bridge/br_stp.c       |  7 +++++++
 net/switchdev/switchdev.c | 19 +++++++++++++++++++
 4 files changed, 38 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3603f31e78f..29c92ee9ed5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1024,6 +1024,9 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *	Called to get an ID of the switch chip this port is part of.
  *	If driver implements this, it indicates that it represents a port
  *	of a switch chip.
+ * int (*ndo_switch_port_stp_update)(struct net_device *dev, u8 state);
+ *	Called to notify switch device port of bridge port STP
+ *	state change.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1180,6 +1183,8 @@ struct net_device_ops {
 #ifdef CONFIG_NET_SWITCHDEV
 	int			(*ndo_switch_parent_id_get)(struct net_device *dev,
 							    struct netdev_phys_item_id *psid);
+	int			(*ndo_switch_port_stp_update)(struct net_device *dev,
+							      u8 state);
 #endif
 };
 
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 7a52360a144..8a6d1641fd9 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -16,6 +16,7 @@
 
 int netdev_switch_parent_id_get(struct net_device *dev,
 				struct netdev_phys_item_id *psid);
+int netdev_switch_port_stp_update(struct net_device *dev, u8 state);
 
 #else
 
@@ -25,6 +26,12 @@ static inline int netdev_switch_parent_id_get(struct net_device *dev,
 	return -EOPNOTSUPP;
 }
 
+static inline int netdev_switch_port_stp_update(struct net_device *dev,
+						u8 state)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif
 
 #endif /* _LINUX_SWITCHDEV_H_ */
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 2b047bcf42a..fb3ebe61551 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -12,6 +12,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/rculist.h>
+#include <net/switchdev.h>
 
 #include "br_private.h"
 #include "br_private_stp.h"
@@ -38,7 +39,13 @@ void br_log_state(const struct net_bridge_port *p)
 
 void br_set_state(struct net_bridge_port *p, unsigned int state)
 {
+	int err;
+
 	p->state = state;
+	err = netdev_switch_port_stp_update(p->dev, state);
+	if (err && err != -EOPNOTSUPP)
+		br_warn(p->br, "error setting offload STP state on port %u(%s)\n",
+				(unsigned int) p->port_no, p->dev->name);
 }
 
 /* called under bridge lock */
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 66973deaae5..d162b21b14b 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -31,3 +31,22 @@ int netdev_switch_parent_id_get(struct net_device *dev,
 	return ops->ndo_switch_parent_id_get(dev, psid);
 }
 EXPORT_SYMBOL(netdev_switch_parent_id_get);
+
+/**
+ *	netdev_switch_port_stp_update - Notify switch device port of STP
+ *					state change
+ *	@dev: port device
+ *	@state: port STP state
+ *
+ *	Notify switch device port of bridge port STP state change.
+ */
+int netdev_switch_port_stp_update(struct net_device *dev, u8 state)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!ops->ndo_switch_port_stp_update)
+		return -EOPNOTSUPP;
+	WARN_ON(!ops->ndo_switch_parent_id_get);
+	return ops->ndo_switch_port_stp_update(dev, state);
+}
+EXPORT_SYMBOL(netdev_switch_port_stp_update);
-- 
cgit v1.2.3-70-g09d2


From cf6b8e1eedffd9ef9a22c0c9453d752b07daf89a Mon Sep 17 00:00:00 2001
From: Scott Feldman <sfeldma@gmail.com>
Date: Fri, 28 Nov 2014 14:34:21 +0100
Subject: bridge: add API to notify bridge driver of learned FBD on offloaded
 device

When the swdev device learns a new mac/vlan on a port, it sends some async
notification to the driver and the driver installs an FDB in the device.
To give a holistic system view, the learned mac/vlan should be reflected
in the bridge's FBD table, so the user, using normal iproute2 cmds, can view
what is currently learned by the device.  This API on the bridge driver gives
a way for the swdev driver to install an FBD entry in the bridge FBD table.
(And remove one).

This is equivalent to the device running these cmds:

  bridge fdb [add|del] <mac> dev <dev> vid <vlan id> master

This patch needs some extra eyeballs for review, in paricular around the
locking and contexts.

Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_bridge.h      | 18 +++++++++
 include/uapi/linux/neighbour.h |  1 +
 net/bridge/br_fdb.c            | 91 +++++++++++++++++++++++++++++++++++++++++-
 net/bridge/br_private.h        |  3 +-
 4 files changed, 111 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 808dcb8cc04..fa2eca62512 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -37,6 +37,24 @@ extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __use
 typedef int br_should_route_hook_t(struct sk_buff *skb);
 extern br_should_route_hook_t __rcu *br_should_route_hook;
 
+#if IS_ENABLED(CONFIG_BRIDGE)
+int br_fdb_external_learn_add(struct net_device *dev,
+			      const unsigned char *addr, u16 vid);
+int br_fdb_external_learn_del(struct net_device *dev,
+			      const unsigned char *addr, u16 vid);
+#else
+static inline int br_fdb_external_learn_add(struct net_device *dev,
+					    const unsigned char *addr, u16 vid)
+{
+	return 0;
+}
+static inline int br_fdb_external_learn_del(struct net_device *dev,
+					    const unsigned char *addr, u16 vid)
+{
+	return 0;
+}
+#endif
+
 #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)
 int br_multicast_list_adjacent(struct net_device *dev,
 			       struct list_head *br_ip_list);
diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
index 2f043af7fcd..f3d77f9f1e0 100644
--- a/include/uapi/linux/neighbour.h
+++ b/include/uapi/linux/neighbour.h
@@ -38,6 +38,7 @@ enum {
 #define NTF_SELF	0x02
 #define NTF_MASTER	0x04
 #define NTF_PROXY	0x08	/* == ATF_PUBL */
+#define NTF_EXT_LEARNED	0x10
 #define NTF_ROUTER	0x80
 
 /*
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index b1be971eb06..cc36e59db7d 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -481,6 +481,7 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head,
 		fdb->is_local = 0;
 		fdb->is_static = 0;
 		fdb->added_by_user = 0;
+		fdb->added_by_external_learn = 0;
 		fdb->updated = fdb->used = jiffies;
 		hlist_add_head_rcu(&fdb->hlist, head);
 	}
@@ -613,7 +614,7 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br,
 	ndm->ndm_family	 = AF_BRIDGE;
 	ndm->ndm_pad1    = 0;
 	ndm->ndm_pad2    = 0;
-	ndm->ndm_flags	 = 0;
+	ndm->ndm_flags	 = fdb->added_by_external_learn ? NTF_EXT_LEARNED : 0;
 	ndm->ndm_type	 = 0;
 	ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex;
 	ndm->ndm_state   = fdb_to_nud(fdb);
@@ -983,3 +984,91 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p)
 		}
 	}
 }
+
+int br_fdb_external_learn_add(struct net_device *dev,
+			      const unsigned char *addr, u16 vid)
+{
+	struct net_bridge_port *p;
+	struct net_bridge *br;
+	struct hlist_head *head;
+	struct net_bridge_fdb_entry *fdb;
+	int err = 0;
+
+	rtnl_lock();
+
+	p = br_port_get_rtnl(dev);
+	if (!p) {
+		pr_info("bridge: %s not a bridge port\n", dev->name);
+		err = -EINVAL;
+		goto err_rtnl_unlock;
+	}
+
+	br = p->br;
+
+	spin_lock_bh(&br->hash_lock);
+
+	head = &br->hash[br_mac_hash(addr, vid)];
+	fdb = fdb_find(head, addr, vid);
+	if (!fdb) {
+		fdb = fdb_create(head, p, addr, vid);
+		if (!fdb) {
+			err = -ENOMEM;
+			goto err_unlock;
+		}
+		fdb->added_by_external_learn = 1;
+		fdb_notify(br, fdb, RTM_NEWNEIGH);
+	} else if (fdb->added_by_external_learn) {
+		/* Refresh entry */
+		fdb->updated = fdb->used = jiffies;
+	} else if (!fdb->added_by_user) {
+		/* Take over SW learned entry */
+		fdb->added_by_external_learn = 1;
+		fdb->updated = jiffies;
+		fdb_notify(br, fdb, RTM_NEWNEIGH);
+	}
+
+err_unlock:
+	spin_unlock_bh(&br->hash_lock);
+err_rtnl_unlock:
+	rtnl_unlock();
+
+	return err;
+}
+EXPORT_SYMBOL(br_fdb_external_learn_add);
+
+int br_fdb_external_learn_del(struct net_device *dev,
+			      const unsigned char *addr, u16 vid)
+{
+	struct net_bridge_port *p;
+	struct net_bridge *br;
+	struct hlist_head *head;
+	struct net_bridge_fdb_entry *fdb;
+	int err = 0;
+
+	rtnl_lock();
+
+	p = br_port_get_rtnl(dev);
+	if (!p) {
+		pr_info("bridge: %s not a bridge port\n", dev->name);
+		err = -EINVAL;
+		goto err_rtnl_unlock;
+	}
+
+	br = p->br;
+
+	spin_lock_bh(&br->hash_lock);
+
+	head = &br->hash[br_mac_hash(addr, vid)];
+	fdb = fdb_find(head, addr, vid);
+	if (fdb && fdb->added_by_external_learn)
+		fdb_delete(br, fdb);
+	else
+		err = -ENOENT;
+
+	spin_unlock_bh(&br->hash_lock);
+err_rtnl_unlock:
+	rtnl_unlock();
+
+	return err;
+}
+EXPORT_SYMBOL(br_fdb_external_learn_del);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 1b529da8234..cc36fb3efbd 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -100,7 +100,8 @@ struct net_bridge_fdb_entry
 	mac_addr			addr;
 	unsigned char			is_local:1,
 					is_static:1,
-					added_by_user:1;
+					added_by_user:1,
+					added_by_external_learn:1;
 	__u16				vlan_id;
 };
 
-- 
cgit v1.2.3-70-g09d2


From 065c212a9e25172069f368b36228379521dadb65 Mon Sep 17 00:00:00 2001
From: Scott Feldman <sfeldma@gmail.com>
Date: Fri, 28 Nov 2014 14:34:22 +0100
Subject: bridge: move private brport flags to if_bridge.h so port drivers can
 use flags

Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_bridge.h | 12 ++++++++++++
 net/bridge/br_private.h   | 10 ----------
 2 files changed, 12 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index fa2eca62512..2c81a8efd24 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -15,6 +15,7 @@
 
 #include <linux/netdevice.h>
 #include <uapi/linux/if_bridge.h>
+#include <linux/bitops.h>
 
 struct br_ip {
 	union {
@@ -32,6 +33,17 @@ struct br_ip_list {
 	struct br_ip addr;
 };
 
+#define BR_HAIRPIN_MODE		BIT(0)
+#define BR_BPDU_GUARD		BIT(1)
+#define BR_ROOT_BLOCK		BIT(2)
+#define BR_MULTICAST_FAST_LEAVE	BIT(3)
+#define BR_ADMIN_COST		BIT(4)
+#define BR_LEARNING		BIT(5)
+#define BR_FLOOD		BIT(6)
+#define BR_AUTO_MASK		(BR_FLOOD | BR_LEARNING)
+#define BR_PROMISC		BIT(7)
+#define BR_PROXYARP		BIT(8)
+
 extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *));
 
 typedef int br_should_route_hook_t(struct sk_buff *skb);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index cc36fb3efbd..aea3d1339b3 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -164,16 +164,6 @@ struct net_bridge_port
 	struct rcu_head			rcu;
 
 	unsigned long 			flags;
-#define BR_HAIRPIN_MODE		0x00000001
-#define BR_BPDU_GUARD           0x00000002
-#define BR_ROOT_BLOCK		0x00000004
-#define BR_MULTICAST_FAST_LEAVE	0x00000008
-#define BR_ADMIN_COST		0x00000010
-#define BR_LEARNING		0x00000020
-#define BR_FLOOD		0x00000040
-#define BR_AUTO_MASK (BR_FLOOD | BR_LEARNING)
-#define BR_PROMISC		0x00000080
-#define BR_PROXYARP		0x00000100
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	struct bridge_mcast_own_query	ip4_own_query;
-- 
cgit v1.2.3-70-g09d2


From efacacdaf7cb5a0592ed772e3731636b2742e34a Mon Sep 17 00:00:00 2001
From: Scott Feldman <sfeldma@gmail.com>
Date: Fri, 28 Nov 2014 14:34:23 +0100
Subject: bridge: add new brport flag LEARNING_SYNC

This policy flag controls syncing of learned FDB entries to bridge's FDB.  If
on, FDB entries learned on bridge port device will be synced.  If off, device
may still learn new FDB entries but they will not be synced with bridge's FDB.

Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_bridge.h    | 1 +
 include/uapi/linux/if_link.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 2c81a8efd24..0a8ce762a47 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -43,6 +43,7 @@ struct br_ip_list {
 #define BR_AUTO_MASK		(BR_FLOOD | BR_LEARNING)
 #define BR_PROMISC		BIT(7)
 #define BR_PROXYARP		BIT(8)
+#define BR_LEARNING_SYNC	BIT(9)
 
 extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *));
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 623f1a7c762..f7d0d2d7173 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -245,6 +245,7 @@ enum {
 	IFLA_BRPORT_LEARNING,	/* mac learning */
 	IFLA_BRPORT_UNICAST_FLOOD, /* flood unicast traffic */
 	IFLA_BRPORT_PROXYARP,	/* proxy ARP */
+	IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
-- 
cgit v1.2.3-70-g09d2


From 345cd494a324c149ef7293f4bedf2d7131a6de7c Mon Sep 17 00:00:00 2001
From: Scott Feldman <sfeldma@gmail.com>
Date: Fri, 28 Nov 2014 14:34:24 +0100
Subject: bridge: add new hwmode swdev

Current hwmode settings are "vepa" or "veb".  These are for NIC interfaces
with basic bridging function offloaded to HW.  Add new "swdev" for full
switch device offloads.

Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index da17e456908..296a556454e 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -105,6 +105,7 @@ struct __fdb_entry {
 
 #define BRIDGE_MODE_VEB		0	/* Default loopback mode */
 #define BRIDGE_MODE_VEPA	1	/* 802.1Qbg defined VEPA mode */
+#define BRIDGE_MODE_SWDEV	2	/* Full switch device offload */
 
 /* Bridge management nested attributes
  * [IFLA_AF_SPEC] = {
-- 
cgit v1.2.3-70-g09d2


From 2c3c031c8f8930861815fa1685d7c5e8ccec047c Mon Sep 17 00:00:00 2001
From: Scott Feldman <sfeldma@gmail.com>
Date: Fri, 28 Nov 2014 14:34:25 +0100
Subject: bridge: add brport flags to dflt bridge_getlink

To allow brport device to return current brport flags set on port.  Add
returned flags to nested IFLA_PROTINFO netlink msg built in dflt getlink.
With this change, netlink msg returned for bridge_getlink contains the port's
offloaded flag settings (the port's SELF settings).

Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_main.c   |  3 ++-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c |  2 +-
 include/linux/rtnetlink.h                     |  3 ++-
 net/core/rtnetlink.c                          | 39 ++++++++++++++++++++++++++-
 4 files changed, 43 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index dc77ec2bdaf..e0ab7673afe 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -4367,7 +4367,8 @@ static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 
 	return ndo_dflt_bridge_getlink(skb, pid, seq, dev,
 				       hsw_mode == PORT_FWD_TYPE_VEPA ?
-				       BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB);
+				       BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB,
+				       0, 0);
 }
 
 #ifdef CONFIG_BE2NET_VXLAN
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 74aadeb56ad..9afa167d52a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7778,7 +7778,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	else
 		mode = BRIDGE_MODE_VEPA;
 
-	return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode);
+	return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode, 0, 0);
 }
 
 static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 063f0f581fe..3b0419072f8 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -103,5 +103,6 @@ extern int ndo_dflt_fdb_del(struct ndmsg *ndm,
 			    u16 vid);
 
 extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
-				   struct net_device *dev, u16 mode);
+				   struct net_device *dev, u16 mode,
+				   u32 flags, u32 mask);
 #endif	/* __LINUX_RTNETLINK_H */
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index aa5cd2c53a5..61cb7e7cc3c 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2687,12 +2687,22 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+static int brport_nla_put_flag(struct sk_buff *skb, u32 flags, u32 mask,
+			       unsigned int attrnum, unsigned int flag)
+{
+	if (mask & flag)
+		return nla_put_u8(skb, attrnum, !!(flags & flag));
+	return 0;
+}
+
 int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
-			    struct net_device *dev, u16 mode)
+			    struct net_device *dev, u16 mode,
+			    u32 flags, u32 mask)
 {
 	struct nlmsghdr *nlh;
 	struct ifinfomsg *ifm;
 	struct nlattr *br_afspec;
+	struct nlattr *protinfo;
 	u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
 	struct net_device *br_dev = netdev_master_upper_dev_get(dev);
 
@@ -2731,6 +2741,33 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	}
 	nla_nest_end(skb, br_afspec);
 
+	protinfo = nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED);
+	if (!protinfo)
+		goto nla_put_failure;
+
+	if (brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_MODE, BR_HAIRPIN_MODE) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_GUARD, BR_BPDU_GUARD) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_FAST_LEAVE,
+				BR_MULTICAST_FAST_LEAVE) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_LEARNING, BR_LEARNING) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_LEARNING_SYNC, BR_LEARNING_SYNC) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_PROXYARP, BR_PROXYARP)) {
+		nla_nest_cancel(skb, protinfo);
+		goto nla_put_failure;
+	}
+
+	nla_nest_end(skb, protinfo);
+
 	return nlmsg_end(skb, nlh);
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
-- 
cgit v1.2.3-70-g09d2


From a51b9199b1e092da5ee4a89852e84b4c52ae6044 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Sun, 30 Nov 2014 19:56:53 +0100
Subject: netfilter: ipset: Alignment problem between 64bit kernel 32bit
 userspace

Sven-Haegar Koch reported the issue:

sims:~# iptables -A OUTPUT -m set --match-set testset src -j ACCEPT
iptables: Invalid argument. Run `dmesg' for more information.

In syslog:
x_tables: ip_tables: set.3 match: invalid size 48 (kernel) != (user) 32

which was introduced by the counter extension in ipset.

The patch fixes the alignment issue with introducing a new set match
revision with the fixed underlying 'struct ip_set_counter_match'
structure.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/ipset/ip_set.h |  8 +++-
 include/uapi/linux/netfilter/xt_set.h       | 13 ++++-
 net/netfilter/xt_set.c                      | 73 +++++++++++++++++++++++++++--
 3 files changed, 88 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h
index ca03119111a..5ab4e60894c 100644
--- a/include/uapi/linux/netfilter/ipset/ip_set.h
+++ b/include/uapi/linux/netfilter/ipset/ip_set.h
@@ -256,11 +256,17 @@ enum {
 	IPSET_COUNTER_GT,
 };
 
-struct ip_set_counter_match {
+/* Backward compatibility for set match v3 */
+struct ip_set_counter_match0 {
 	__u8 op;
 	__u64 value;
 };
 
+struct ip_set_counter_match {
+	__aligned_u64 value;
+	__u8 op;
+};
+
 /* Interface to iptables/ip6tables */
 
 #define SO_IP_SET		83
diff --git a/include/uapi/linux/netfilter/xt_set.h b/include/uapi/linux/netfilter/xt_set.h
index d6a1df1f294..d4e02348384 100644
--- a/include/uapi/linux/netfilter/xt_set.h
+++ b/include/uapi/linux/netfilter/xt_set.h
@@ -66,8 +66,8 @@ struct xt_set_info_target_v2 {
 
 struct xt_set_info_match_v3 {
 	struct xt_set_info match_set;
-	struct ip_set_counter_match packets;
-	struct ip_set_counter_match bytes;
+	struct ip_set_counter_match0 packets;
+	struct ip_set_counter_match0 bytes;
 	__u32 flags;
 };
 
@@ -81,4 +81,13 @@ struct xt_set_info_target_v3 {
 	__u32 timeout;
 };
 
+/* Revision 4 match */
+
+struct xt_set_info_match_v4 {
+	struct xt_set_info match_set;
+	struct ip_set_counter_match packets;
+	struct ip_set_counter_match bytes;
+	__u32 flags;
+};
+
 #endif /*_XT_SET_H*/
diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c
index 5732cd64acc..0d47afea968 100644
--- a/net/netfilter/xt_set.c
+++ b/net/netfilter/xt_set.c
@@ -157,7 +157,7 @@ set_match_v1_destroy(const struct xt_mtdtor_param *par)
 /* Revision 3 match */
 
 static bool
-match_counter(u64 counter, const struct ip_set_counter_match *info)
+match_counter0(u64 counter, const struct ip_set_counter_match0 *info)
 {
 	switch (info->op) {
 	case IPSET_COUNTER_NONE:
@@ -192,14 +192,60 @@ set_match_v3(const struct sk_buff *skb, struct xt_action_param *par)
 	if (!(ret && opt.cmdflags & IPSET_FLAG_MATCH_COUNTERS))
 		return ret;
 
-	if (!match_counter(opt.ext.packets, &info->packets))
+	if (!match_counter0(opt.ext.packets, &info->packets))
 		return 0;
-	return match_counter(opt.ext.bytes, &info->bytes);
+	return match_counter0(opt.ext.bytes, &info->bytes);
 }
 
 #define set_match_v3_checkentry	set_match_v1_checkentry
 #define set_match_v3_destroy	set_match_v1_destroy
 
+/* Revision 4 match */
+
+static bool
+match_counter(u64 counter, const struct ip_set_counter_match *info)
+{
+	switch (info->op) {
+	case IPSET_COUNTER_NONE:
+		return true;
+	case IPSET_COUNTER_EQ:
+		return counter == info->value;
+	case IPSET_COUNTER_NE:
+		return counter != info->value;
+	case IPSET_COUNTER_LT:
+		return counter < info->value;
+	case IPSET_COUNTER_GT:
+		return counter > info->value;
+	}
+	return false;
+}
+
+static bool
+set_match_v4(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct xt_set_info_match_v4 *info = par->matchinfo;
+	ADT_OPT(opt, par->family, info->match_set.dim,
+		info->match_set.flags, info->flags, UINT_MAX);
+	int ret;
+
+	if (info->packets.op != IPSET_COUNTER_NONE ||
+	    info->bytes.op != IPSET_COUNTER_NONE)
+		opt.cmdflags |= IPSET_FLAG_MATCH_COUNTERS;
+
+	ret = match_set(info->match_set.index, skb, par, &opt,
+			info->match_set.flags & IPSET_INV_MATCH);
+
+	if (!(ret && opt.cmdflags & IPSET_FLAG_MATCH_COUNTERS))
+		return ret;
+
+	if (!match_counter(opt.ext.packets, &info->packets))
+		return 0;
+	return match_counter(opt.ext.bytes, &info->bytes);
+}
+
+#define set_match_v4_checkentry	set_match_v1_checkentry
+#define set_match_v4_destroy	set_match_v1_destroy
+
 /* Revision 0 interface: backward compatible with netfilter/iptables */
 
 static unsigned int
@@ -573,6 +619,27 @@ static struct xt_match set_matches[] __read_mostly = {
 		.destroy	= set_match_v3_destroy,
 		.me		= THIS_MODULE
 	},
+	/* new revision for counters support: update, match */
+	{
+		.name		= "set",
+		.family		= NFPROTO_IPV4,
+		.revision	= 4,
+		.match		= set_match_v4,
+		.matchsize	= sizeof(struct xt_set_info_match_v4),
+		.checkentry	= set_match_v4_checkentry,
+		.destroy	= set_match_v4_destroy,
+		.me		= THIS_MODULE
+	},
+	{
+		.name		= "set",
+		.family		= NFPROTO_IPV6,
+		.revision	= 4,
+		.match		= set_match_v4,
+		.matchsize	= sizeof(struct xt_set_info_match_v4),
+		.checkentry	= set_match_v4_checkentry,
+		.destroy	= set_match_v4_destroy,
+		.me		= THIS_MODULE
+	},
 };
 
 static struct xt_target set_targets[] __read_mostly = {
-- 
cgit v1.2.3-70-g09d2


From 23fb8de376181a30c35195351ec6230167098b48 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 23 May 2014 13:15:37 +0300
Subject: Bluetooth: Add mgmt support for LE Secure Connections LTK types

We need a dedicated LTK type for LTK resulting from a Secure Connections
based SMP pairing. This patch adds a new define for it and ensures that
both the New LTK event as well as the Load LTKs command supports it.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/mgmt.h |  3 +++
 net/bluetooth/mgmt.c         | 33 ++++++++++++++++++++++++++-------
 net/bluetooth/smp.h          | 13 +++++++++++++
 3 files changed, 42 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index b391fd66346..9b382ea34fd 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -184,6 +184,9 @@ struct mgmt_cp_load_link_keys {
 
 #define MGMT_LTK_UNAUTHENTICATED	0x00
 #define MGMT_LTK_AUTHENTICATED		0x01
+#define MGMT_LTK_P256_UNAUTH		0x02
+#define MGMT_LTK_P256_AUTH		0x03
+#define MGMT_LTK_P256_DEBUG		0x04
 
 struct mgmt_ltk_info {
 	struct mgmt_addr_info addr;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index cbeef5f62f3..7974a39a42d 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4910,18 +4910,26 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 		else
 			addr_type = ADDR_LE_DEV_RANDOM;
 
-		if (key->master)
-			type = SMP_LTK;
-		else
-			type = SMP_LTK_SLAVE;
-
 		switch (key->type) {
 		case MGMT_LTK_UNAUTHENTICATED:
 			authenticated = 0x00;
+			type = key->master ? SMP_LTK : SMP_LTK_SLAVE;
 			break;
 		case MGMT_LTK_AUTHENTICATED:
 			authenticated = 0x01;
+			type = key->master ? SMP_LTK : SMP_LTK_SLAVE;
+			break;
+		case MGMT_LTK_P256_UNAUTH:
+			authenticated = 0x00;
+			type = SMP_LTK_P256;
+			break;
+		case MGMT_LTK_P256_AUTH:
+			authenticated = 0x01;
+			type = SMP_LTK_P256;
 			break;
+		case MGMT_LTK_P256_DEBUG:
+			authenticated = 0x00;
+			type = SMP_LTK_P256_DEBUG;
 		default:
 			continue;
 		}
@@ -6101,8 +6109,19 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 
 static u8 mgmt_ltk_type(struct smp_ltk *ltk)
 {
-	if (ltk->authenticated)
-		return MGMT_LTK_AUTHENTICATED;
+	switch (ltk->type) {
+	case SMP_LTK:
+	case SMP_LTK_SLAVE:
+		if (ltk->authenticated)
+			return MGMT_LTK_AUTHENTICATED;
+		return MGMT_LTK_UNAUTHENTICATED;
+	case SMP_LTK_P256:
+		if (ltk->authenticated)
+			return MGMT_LTK_P256_AUTH;
+		return MGMT_LTK_P256_UNAUTH;
+	case SMP_LTK_P256_DEBUG:
+		return MGMT_LTK_P256_DEBUG;
+	}
 
 	return MGMT_LTK_UNAUTHENTICATED;
 }
diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h
index 7c3c351909f..81d24c0ea08 100644
--- a/net/bluetooth/smp.h
+++ b/net/bluetooth/smp.h
@@ -146,8 +146,21 @@ enum {
 	SMP_STK,
 	SMP_LTK,
 	SMP_LTK_SLAVE,
+	SMP_LTK_P256,
+	SMP_LTK_P256_DEBUG,
 };
 
+static inline bool smp_ltk_is_sc(struct smp_ltk *key)
+{
+	switch (key->type) {
+	case SMP_LTK_P256:
+	case SMP_LTK_P256_DEBUG:
+		return true;
+	}
+
+	return false;
+}
+
 static inline u8 smp_ltk_sec_level(struct smp_ltk *key)
 {
 	if (key->authenticated)
-- 
cgit v1.2.3-70-g09d2


From 710f11c08e9f18a8a642024880804436c0969514 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Mon, 26 May 2014 11:21:22 +0300
Subject: Bluetooth: Use custom macro for testing BR/EDR SC enabled

Since the HCI_SC_ENABLED flag will also be used for controllers without
BR/EDR Secure Connections support whenever we need to check specifically
for SC for BR/EDR we also need to check that the controller actually
supports it. This patch adds a convenience macro for check all the
necessary conditions and converts the places in the code that need it to
use it.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h | 3 +++
 net/bluetooth/hci_core.c         | 4 +---
 net/bluetooth/hci_event.c        | 2 +-
 net/bluetooth/mgmt.c             | 5 ++---
 4 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 396c09840fd..7f08ea36d24 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -999,6 +999,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 
 #define hdev_is_powered(hdev) (test_bit(HCI_UP, &hdev->flags) && \
 				!test_bit(HCI_AUTO_OFF, &hdev->dev_flags))
+#define bredr_sc_enabled(dev) ((lmp_sc_capable(dev) || \
+				test_bit(HCI_FORCE_SC, &(dev)->dbg_flags)) && \
+			       test_bit(HCI_SC_ENABLED, &(dev)->dev_flags))
 
 /* ----- HCI protocols ----- */
 #define HCI_PROTO_DEFER             0x01
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 5c319a49a5a..2586e405adb 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1734,9 +1734,7 @@ static void hci_init4_req(struct hci_request *req, unsigned long opt)
 		hci_req_add(req, HCI_OP_READ_SYNC_TRAIN_PARAMS, 0, NULL);
 
 	/* Enable Secure Connections if supported and configured */
-	if ((lmp_sc_capable(hdev) ||
-	     test_bit(HCI_FORCE_SC, &hdev->dbg_flags)) &&
-	    test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) {
+	if (bredr_sc_enabled(hdev)) {
 		u8 support = 0x01;
 		hci_req_add(req, HCI_OP_WRITE_SC_SUPPORT,
 			    sizeof(support), &support);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index d76d4f82118..f980fc46ea5 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -4027,7 +4027,7 @@ static void hci_remote_oob_data_request_evt(struct hci_dev *hdev,
 
 	data = hci_find_remote_oob_data(hdev, &ev->bdaddr);
 	if (data) {
-		if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) {
+		if (bredr_sc_enabled(hdev)) {
 			struct hci_cp_remote_oob_ext_data_reply cp;
 
 			bacpy(&cp.bdaddr, &ev->bdaddr);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 7974a39a42d..868769543d8 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3562,7 +3562,7 @@ static int read_local_oob_data(struct sock *sk, struct hci_dev *hdev,
 		goto unlock;
 	}
 
-	if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags))
+	if (bredr_sc_enabled(hdev))
 		err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_EXT_DATA,
 				   0, NULL);
 	else
@@ -6803,8 +6803,7 @@ void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192,
 		cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
 			   mgmt_status(status));
 	} else {
-		if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags) &&
-		    hash256 && rand256) {
+		if (bredr_sc_enabled(hdev) && hash256 && rand256) {
 			struct mgmt_rp_read_local_oob_ext_data rp;
 
 			memcpy(rp.hash192, hash192, sizeof(rp.hash192));
-- 
cgit v1.2.3-70-g09d2


From 0ac3dbf9995281261abecfd2970406dd4e07955b Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Thu, 29 May 2014 15:00:03 +0300
Subject: Bluetooth: Remove unused hci_find_ltk function

Now that LTKs are always looked up based on bdaddr (with EDiv/Rand
checks done after a successful lookup) the hci_find_ltk function is not
needed anymore. This patch removes the function.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  2 --
 net/bluetooth/hci_core.c         | 28 ----------------------------
 2 files changed, 30 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 7f08ea36d24..b41969b561d 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -921,8 +921,6 @@ struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr);
 struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn,
 				  bdaddr_t *bdaddr, u8 *val, u8 type,
 				  u8 pin_len, bool *persistent);
-struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, __le64 rand,
-			     u8 role);
 struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			    u8 addr_type, u8 type, u8 authenticated,
 			    u8 tk[16], u8 enc_size, __le16 ediv, __le64 rand);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index e091e8ffeb8..cb9bc8e2c58 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3185,34 +3185,6 @@ static u8 ltk_role(u8 type)
 	return HCI_ROLE_SLAVE;
 }
 
-struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, __le64 rand,
-			     u8 role)
-{
-	struct smp_ltk *k;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(k, &hdev->long_term_keys, list) {
-		if (k->ediv != ediv || k->rand != rand)
-			continue;
-
-		if (smp_ltk_is_sc(k)) {
-			if (k->type == SMP_LTK_P256_DEBUG &&
-			    !test_bit(HCI_KEEP_DEBUG_KEYS, &hdev->dev_flags))
-				continue;
-			rcu_read_unlock();
-			return k;
-		}
-
-		if (ltk_role(k->type) == role) {
-			rcu_read_unlock();
-			return k;
-		}
-	}
-	rcu_read_unlock();
-
-	return NULL;
-}
-
 struct smp_ltk *hci_find_ltk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr,
 				     u8 addr_type, u8 role)
 {
-- 
cgit v1.2.3-70-g09d2


From f3a73d97b3b78584e111478d07dfd063453f112e Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Thu, 29 May 2014 15:02:59 +0300
Subject: Bluetooth: Rename hci_find_ltk_by_addr to hci_find_ltk

Now that hci_find_ltk_by_addr is the only LTK lookup function there's no
need to keep the long name anymore. This patch shortens the function
name to simply hci_find_ltk.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h | 4 ++--
 net/bluetooth/hci_core.c         | 6 +++---
 net/bluetooth/hci_event.c        | 3 +--
 net/bluetooth/smp.c              | 6 ++----
 4 files changed, 8 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index b41969b561d..90929641d0f 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -924,8 +924,8 @@ struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn,
 struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			    u8 addr_type, u8 type, u8 authenticated,
 			    u8 tk[16], u8 enc_size, __le16 ediv, __le64 rand);
-struct smp_ltk *hci_find_ltk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr,
-				     u8 addr_type, u8 role);
+struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			     u8 addr_type, u8 role);
 int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type);
 void hci_smp_ltks_clear(struct hci_dev *hdev);
 int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index cb9bc8e2c58..6c3220e9484 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3185,8 +3185,8 @@ static u8 ltk_role(u8 type)
 	return HCI_ROLE_SLAVE;
 }
 
-struct smp_ltk *hci_find_ltk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr,
-				     u8 addr_type, u8 role)
+struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			     u8 addr_type, u8 role)
 {
 	struct smp_ltk *k;
 
@@ -3313,7 +3313,7 @@ struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	struct smp_ltk *key, *old_key;
 	u8 role = ltk_role(type);
 
-	old_key = hci_find_ltk_by_addr(hdev, bdaddr, addr_type, role);
+	old_key = hci_find_ltk(hdev, bdaddr, addr_type, role);
 	if (old_key)
 		key = old_key;
 	else {
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 0058b545c5e..34ecbf0b7e5 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -4590,8 +4590,7 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	if (conn == NULL)
 		goto not_found;
 
-	ltk = hci_find_ltk_by_addr(hdev, &conn->dst, conn->dst_type,
-				   conn->role);
+	ltk = hci_find_ltk(hdev, &conn->dst, conn->dst_type, conn->role);
 	if (!ltk)
 		goto not_found;
 
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 4ecbf2774fb..0973e37073e 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -1118,8 +1118,7 @@ static bool smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level)
 	struct smp_ltk *key;
 	struct hci_conn *hcon = conn->hcon;
 
-	key = hci_find_ltk_by_addr(hcon->hdev, &hcon->dst, hcon->dst_type,
-				   hcon->role);
+	key = hci_find_ltk(hcon->hdev, &hcon->dst, hcon->dst_type, hcon->role);
 	if (!key)
 		return false;
 
@@ -1152,8 +1151,7 @@ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level,
 	 */
 	if (key_pref == SMP_USE_LTK &&
 	    test_bit(HCI_CONN_STK_ENCRYPT, &hcon->flags) &&
-	    hci_find_ltk_by_addr(hcon->hdev, &hcon->dst, hcon->dst_type,
-				 hcon->role))
+	    hci_find_ltk(hcon->hdev, &hcon->dst, hcon->dst_type, hcon->role))
 		return false;
 
 	if (hcon->sec_level >= sec_level)
-- 
cgit v1.2.3-70-g09d2


From fe8bc5ac67a36b05c4ec91643736d44373096a76 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Thu, 14 Aug 2014 12:33:17 +0300
Subject: Bluetooth: Add hci_conn flag for new link key generation

For LE Secure Connections we want to trigger cross transport key
generation only if a new link key was actually created during the BR/EDR
connection. This patch adds a new flag to track this information.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h | 1 +
 net/bluetooth/hci_event.c        | 3 +++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 90929641d0f..42f9362a83c 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -559,6 +559,7 @@ enum {
 	HCI_CONN_AUTH_INITIATOR,
 	HCI_CONN_DROP,
 	HCI_CONN_PARAM_REMOVAL_PEND,
+	HCI_CONN_NEW_LINK_KEY,
 };
 
 static inline bool hci_conn_ssp_enabled(struct hci_conn *conn)
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 34ecbf0b7e5..c3d6390e3b7 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3249,6 +3249,8 @@ static void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
 	if (conn) {
+		clear_bit(HCI_CONN_NEW_LINK_KEY, &conn->flags);
+
 		if ((key->type == HCI_LK_UNAUTH_COMBINATION_P192 ||
 		     key->type == HCI_LK_UNAUTH_COMBINATION_P256) &&
 		    conn->auth_type != 0xff && (conn->auth_type & 0x01)) {
@@ -3301,6 +3303,7 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	conn->disc_timeout = HCI_DISCONN_TIMEOUT;
 	hci_conn_drop(conn);
 
+	set_bit(HCI_CONN_NEW_LINK_KEY, &conn->flags);
 	conn_set_key(conn, ev->key_type, conn->pin_length);
 
 	if (!test_bit(HCI_MGMT, &hdev->dev_flags))
-- 
cgit v1.2.3-70-g09d2


From 858cdc78be8be19b7176cafe06d3db3acfb345d4 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Thu, 16 Oct 2014 10:45:31 +0200
Subject: Bluetooth: Add debugfs switch for forcing SMP over BR/EDR

To make it possible to use LE SC functionality over BR/EDR with pre-4.1
controllers (that do not support BR/EDR SC links) it's useful to be able
to force LE SC operations even over a traditional SSP protected link.
This patch adds a debugfs switch to force a special debug flag which is
used to skip the checks for BR/EDR SC support.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h |  1 +
 net/bluetooth/hci_core.c    | 47 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index e56f9099f8e..569c077778b 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -163,6 +163,7 @@ enum {
 enum {
 	HCI_DUT_MODE,
 	HCI_FORCE_SC,
+	HCI_FORCE_LESC,
 	HCI_FORCE_STATIC_ADDR,
 };
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 2fa9f2b2bee..581e13e9dc3 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -406,6 +406,49 @@ static const struct file_operations force_sc_support_fops = {
 	.llseek		= default_llseek,
 };
 
+static ssize_t force_lesc_support_read(struct file *file, char __user *user_buf,
+				       size_t count, loff_t *ppos)
+{
+	struct hci_dev *hdev = file->private_data;
+	char buf[3];
+
+	buf[0] = test_bit(HCI_FORCE_LESC, &hdev->dbg_flags) ? 'Y': 'N';
+	buf[1] = '\n';
+	buf[2] = '\0';
+	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static ssize_t force_lesc_support_write(struct file *file,
+					const char __user *user_buf,
+					size_t count, loff_t *ppos)
+{
+	struct hci_dev *hdev = file->private_data;
+	char buf[32];
+	size_t buf_size = min(count, (sizeof(buf)-1));
+	bool enable;
+
+	if (copy_from_user(buf, user_buf, buf_size))
+		return -EFAULT;
+
+	buf[buf_size] = '\0';
+	if (strtobool(buf, &enable))
+		return -EINVAL;
+
+	if (enable == test_bit(HCI_FORCE_LESC, &hdev->dbg_flags))
+		return -EALREADY;
+
+	change_bit(HCI_FORCE_LESC, &hdev->dbg_flags);
+
+	return count;
+}
+
+static const struct file_operations force_lesc_support_fops = {
+	.open		= simple_open,
+	.read		= force_lesc_support_read,
+	.write		= force_lesc_support_write,
+	.llseek		= default_llseek,
+};
+
 static ssize_t sc_only_mode_read(struct file *file, char __user *user_buf,
 				 size_t count, loff_t *ppos)
 {
@@ -1817,6 +1860,10 @@ static int __hci_init(struct hci_dev *hdev)
 				    hdev, &force_sc_support_fops);
 		debugfs_create_file("sc_only_mode", 0444, hdev->debugfs,
 				    hdev, &sc_only_mode_fops);
+		if (lmp_le_capable(hdev))
+			debugfs_create_file("force_lesc_support", 0644,
+					    hdev->debugfs, hdev,
+					    &force_lesc_support_fops);
 	}
 
 	if (lmp_sniff_capable(hdev)) {
-- 
cgit v1.2.3-70-g09d2


From ef8efe4bf8b5fe1a9342ae964c428aed1be7863b Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Wed, 13 Aug 2014 15:12:32 +0300
Subject: Bluetooth: Add skeleton for BR/EDR SMP channel

This patch adds the very basic code for creating and destroying SMP
L2CAP channels for BR/EDR connections.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  1 +
 include/net/bluetooth/l2cap.h    |  2 +
 net/bluetooth/smp.c              | 89 ++++++++++++++++++++++++++++++++--------
 3 files changed, 74 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 42f9362a83c..f39e65096b1 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -306,6 +306,7 @@ struct hci_dev {
 	__u32			req_result;
 
 	void			*smp_data;
+	void			*smp_bredr_data;
 
 	struct discovery_state	discovery;
 	struct hci_conn_hash	conn_hash;
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index d71dc357935..eee3ef530e7 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -141,6 +141,7 @@ struct l2cap_conninfo {
 #define L2CAP_FC_ATT		0x10
 #define L2CAP_FC_SIG_LE		0x20
 #define L2CAP_FC_SMP_LE		0x40
+#define L2CAP_FC_SMP_BREDR	0x80
 
 /* L2CAP Control Field bit masks */
 #define L2CAP_CTRL_SAR			0xC000
@@ -255,6 +256,7 @@ struct l2cap_conn_rsp {
 #define L2CAP_CID_ATT		0x0004
 #define L2CAP_CID_LE_SIGNALING	0x0005
 #define L2CAP_CID_SMP		0x0006
+#define L2CAP_CID_SMP_BREDR	0x0007
 #define L2CAP_CID_DYN_START	0x0040
 #define L2CAP_CID_DYN_END	0xffff
 #define L2CAP_CID_LE_DYN_END	0x007f
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 779160485a5..135e725119c 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -2504,6 +2504,9 @@ static void smp_resume_cb(struct l2cap_chan *chan)
 
 	BT_DBG("chan %p", chan);
 
+	if (hcon->type == ACL_LINK)
+		return;
+
 	if (!smp)
 		return;
 
@@ -2527,10 +2530,14 @@ static void smp_ready_cb(struct l2cap_chan *chan)
 
 static int smp_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb)
 {
+	struct hci_conn *hcon = chan->conn->hcon;
 	int err;
 
 	BT_DBG("chan %p", chan);
 
+	if (hcon->type == ACL_LINK)
+		return -EOPNOTSUPP;
+
 	err = smp_sig_channel(chan, skb);
 	if (err) {
 		struct smp_chan *smp = chan->data;
@@ -2627,34 +2634,40 @@ static const struct l2cap_ops smp_root_chan_ops = {
 	.memcpy_fromiovec	= l2cap_chan_no_memcpy_fromiovec,
 };
 
-int smp_register(struct hci_dev *hdev)
+static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid)
 {
 	struct l2cap_chan *chan;
 	struct crypto_blkcipher	*tfm_aes;
 
-	BT_DBG("%s", hdev->name);
+	if (cid == L2CAP_CID_SMP_BREDR) {
+		tfm_aes = NULL;
+		goto create_chan;
+	}
 
 	tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, 0);
 	if (IS_ERR(tfm_aes)) {
-		int err = PTR_ERR(tfm_aes);
 		BT_ERR("Unable to create crypto context");
-		return err;
+		return ERR_PTR(PTR_ERR(tfm_aes));
 	}
 
+create_chan:
 	chan = l2cap_chan_create();
 	if (!chan) {
 		crypto_free_blkcipher(tfm_aes);
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	chan->data = tfm_aes;
 
-	l2cap_add_scid(chan, L2CAP_CID_SMP);
+	l2cap_add_scid(chan, cid);
 
 	l2cap_chan_set_defaults(chan);
 
 	bacpy(&chan->src, &hdev->bdaddr);
-	chan->src_type = BDADDR_LE_PUBLIC;
+	if (cid == L2CAP_CID_SMP)
+		chan->src_type = BDADDR_LE_PUBLIC;
+	else
+		chan->src_type = BDADDR_BREDR;
 	chan->state = BT_LISTEN;
 	chan->mode = L2CAP_MODE_BASIC;
 	chan->imtu = L2CAP_DEFAULT_MTU;
@@ -2663,20 +2676,14 @@ int smp_register(struct hci_dev *hdev)
 	/* Set correct nesting level for a parent/listening channel */
 	atomic_set(&chan->nesting, L2CAP_NESTING_PARENT);
 
-	hdev->smp_data = chan;
-
-	return 0;
+	return chan;
 }
 
-void smp_unregister(struct hci_dev *hdev)
+static void smp_del_chan(struct l2cap_chan *chan)
 {
-	struct l2cap_chan *chan = hdev->smp_data;
-	struct crypto_blkcipher *tfm_aes;
-
-	if (!chan)
-		return;
+	struct crypto_blkcipher	*tfm_aes;
 
-	BT_DBG("%s chan %p", hdev->name, chan);
+	BT_DBG("chan %p", chan);
 
 	tfm_aes = chan->data;
 	if (tfm_aes) {
@@ -2684,6 +2691,52 @@ void smp_unregister(struct hci_dev *hdev)
 		crypto_free_blkcipher(tfm_aes);
 	}
 
-	hdev->smp_data = NULL;
 	l2cap_chan_put(chan);
 }
+
+int smp_register(struct hci_dev *hdev)
+{
+	struct l2cap_chan *chan;
+
+	BT_DBG("%s", hdev->name);
+
+	chan = smp_add_cid(hdev, L2CAP_CID_SMP);
+	if (IS_ERR(chan))
+		return PTR_ERR(chan);
+
+	hdev->smp_data = chan;
+
+	if (!lmp_sc_capable(hdev) &&
+	    !test_bit(HCI_FORCE_LESC, &hdev->dbg_flags))
+		return 0;
+
+	chan = smp_add_cid(hdev, L2CAP_CID_SMP_BREDR);
+	if (IS_ERR(chan)) {
+		int err = PTR_ERR(chan);
+		chan = hdev->smp_data;
+		hdev->smp_data = NULL;
+		smp_del_chan(chan);
+		return err;
+	}
+
+	hdev->smp_bredr_data = chan;
+
+	return 0;
+}
+
+void smp_unregister(struct hci_dev *hdev)
+{
+	struct l2cap_chan *chan;
+
+	if (hdev->smp_bredr_data) {
+		chan = hdev->smp_bredr_data;
+		hdev->smp_bredr_data = NULL;
+		smp_del_chan(chan);
+	}
+
+	if (hdev->smp_data) {
+		chan = hdev->smp_data;
+		hdev->smp_data = NULL;
+		smp_del_chan(chan);
+	}
+}
-- 
cgit v1.2.3-70-g09d2


From 81328d5cca7e1cff6296a63a3c1b671d09ddb3ee Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Sun, 26 Oct 2014 20:33:47 +0100
Subject: Bluetooth: Unify remote OOB data functions

There's no need to duplicate code for the 192 vs 192+256 variants of the
OOB data functions. This is also helpful to pave the way to support LE
SC OOB data where only 256 bit data is provided.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  6 ++----
 net/bluetooth/hci_core.c         | 46 +++++++++++++---------------------------
 net/bluetooth/mgmt.c             |  9 ++++----
 3 files changed, 22 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index f39e65096b1..3e89ece7503 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -944,10 +944,8 @@ void hci_remote_oob_data_clear(struct hci_dev *hdev);
 struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev,
 					  bdaddr_t *bdaddr);
 int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
-			    u8 *hash, u8 *rand);
-int hci_add_remote_oob_ext_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
-				u8 *hash192, u8 *rand192,
-				u8 *hash256, u8 *rand256);
+			    u8 *hash192, u8 *rand192,
+			    u8 *hash256, u8 *rand256);
 int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr);
 
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 581e13e9dc3..967fbfe80f1 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3517,7 +3517,8 @@ void hci_remote_oob_data_clear(struct hci_dev *hdev)
 }
 
 int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
-			    u8 *hash, u8 *rand)
+			    u8 *hash192, u8 *rand192,
+			    u8 *hash256, u8 *rand256)
 {
 	struct oob_data *data;
 
@@ -3531,38 +3532,21 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
 		list_add(&data->list, &hdev->remote_oob_data);
 	}
 
-	memcpy(data->hash192, hash, sizeof(data->hash192));
-	memcpy(data->rand192, rand, sizeof(data->rand192));
-
-	memset(data->hash256, 0, sizeof(data->hash256));
-	memset(data->rand256, 0, sizeof(data->rand256));
-
-	BT_DBG("%s for %pMR", hdev->name, bdaddr);
-
-	return 0;
-}
-
-int hci_add_remote_oob_ext_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
-				u8 *hash192, u8 *rand192,
-				u8 *hash256, u8 *rand256)
-{
-	struct oob_data *data;
-
-	data = hci_find_remote_oob_data(hdev, bdaddr);
-	if (!data) {
-		data = kmalloc(sizeof(*data), GFP_KERNEL);
-		if (!data)
-			return -ENOMEM;
-
-		bacpy(&data->bdaddr, bdaddr);
-		list_add(&data->list, &hdev->remote_oob_data);
+	if (hash192 && rand192) {
+		memcpy(data->hash192, hash192, sizeof(data->hash192));
+		memcpy(data->rand192, rand192, sizeof(data->rand192));
+	} else {
+		memset(data->hash192, 0, sizeof(data->hash192));
+		memset(data->rand192, 0, sizeof(data->rand192));
 	}
 
-	memcpy(data->hash192, hash192, sizeof(data->hash192));
-	memcpy(data->rand192, rand192, sizeof(data->rand192));
-
-	memcpy(data->hash256, hash256, sizeof(data->hash256));
-	memcpy(data->rand256, rand256, sizeof(data->rand256));
+	if (hash256 && rand256) {
+		memcpy(data->hash256, hash256, sizeof(data->hash256));
+		memcpy(data->rand256, rand256, sizeof(data->rand256));
+	} else {
+		memset(data->hash256, 0, sizeof(data->hash256));
+		memset(data->rand256, 0, sizeof(data->rand256));
+	}
 
 	BT_DBG("%s for %pMR", hdev->name, bdaddr);
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 6e8165364b7..0d92ba99ca9 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3599,7 +3599,8 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
 		}
 
 		err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr,
-					      cp->hash, cp->rand);
+					      cp->hash, cp->rand,
+					      NULL, NULL);
 		if (err < 0)
 			status = MGMT_STATUS_FAILED;
 		else
@@ -3619,9 +3620,9 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
 			goto unlock;
 		}
 
-		err = hci_add_remote_oob_ext_data(hdev, &cp->addr.bdaddr,
-						  cp->hash192, cp->rand192,
-						  cp->hash256, cp->rand256);
+		err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr,
+					      cp->hash192, cp->rand192,
+					      cp->hash256, cp->rand256);
 		if (err < 0)
 			status = MGMT_STATUS_FAILED;
 		else
-- 
cgit v1.2.3-70-g09d2


From 6928a9245f2998478047dcc3efad30734766a226 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Sun, 26 Oct 2014 20:46:09 +0100
Subject: Bluetooth: Store address type with OOB data

To be able to support OOB data for LE pairing we need to store the
address type of the remote device. This patch extends the relevant
functions and data types with a bdaddr_type variable.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  8 +++++---
 net/bluetooth/hci_core.c         | 26 ++++++++++++++++----------
 net/bluetooth/hci_event.c        |  4 ++--
 net/bluetooth/mgmt.c             | 11 ++++++-----
 4 files changed, 29 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 3e89ece7503..1dae7001fc3 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -140,6 +140,7 @@ struct link_key {
 struct oob_data {
 	struct list_head list;
 	bdaddr_t bdaddr;
+	u8 bdaddr_type;
 	u8 hash192[16];
 	u8 rand192[16];
 	u8 hash256[16];
@@ -942,11 +943,12 @@ void hci_smp_irks_clear(struct hci_dev *hdev);
 
 void hci_remote_oob_data_clear(struct hci_dev *hdev);
 struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev,
-					  bdaddr_t *bdaddr);
+					  bdaddr_t *bdaddr, u8 bdaddr_type);
 int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
-			    u8 *hash192, u8 *rand192,
+			    u8 bdaddr_type, u8 *hash192, u8 *rand192,
 			    u8 *hash256, u8 *rand256);
-int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr);
+int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			       u8 bdaddr_type);
 
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb);
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 967fbfe80f1..c8123f04a33 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2160,7 +2160,7 @@ u32 hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data,
 
 	BT_DBG("cache %p, %pMR", cache, &data->bdaddr);
 
-	hci_remove_remote_oob_data(hdev, &data->bdaddr);
+	hci_remove_remote_oob_data(hdev, &data->bdaddr, BDADDR_BREDR);
 
 	if (!data->ssp_mode)
 		flags |= MGMT_DEV_FOUND_LEGACY_PAIRING;
@@ -3479,26 +3479,31 @@ static void hci_cmd_timeout(struct work_struct *work)
 }
 
 struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev,
-					  bdaddr_t *bdaddr)
+					  bdaddr_t *bdaddr, u8 bdaddr_type)
 {
 	struct oob_data *data;
 
-	list_for_each_entry(data, &hdev->remote_oob_data, list)
-		if (bacmp(bdaddr, &data->bdaddr) == 0)
-			return data;
+	list_for_each_entry(data, &hdev->remote_oob_data, list) {
+		if (bacmp(bdaddr, &data->bdaddr) != 0)
+			continue;
+		if (data->bdaddr_type != bdaddr_type)
+			continue;
+		return data;
+	}
 
 	return NULL;
 }
 
-int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr)
+int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			       u8 bdaddr_type)
 {
 	struct oob_data *data;
 
-	data = hci_find_remote_oob_data(hdev, bdaddr);
+	data = hci_find_remote_oob_data(hdev, bdaddr, bdaddr_type);
 	if (!data)
 		return -ENOENT;
 
-	BT_DBG("%s removing %pMR", hdev->name, bdaddr);
+	BT_DBG("%s removing %pMR (%u)", hdev->name, bdaddr, bdaddr_type);
 
 	list_del(&data->list);
 	kfree(data);
@@ -3517,18 +3522,19 @@ void hci_remote_oob_data_clear(struct hci_dev *hdev)
 }
 
 int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
-			    u8 *hash192, u8 *rand192,
+			    u8 bdaddr_type, u8 *hash192, u8 *rand192,
 			    u8 *hash256, u8 *rand256)
 {
 	struct oob_data *data;
 
-	data = hci_find_remote_oob_data(hdev, bdaddr);
+	data = hci_find_remote_oob_data(hdev, bdaddr, bdaddr_type);
 	if (!data) {
 		data = kmalloc(sizeof(*data), GFP_KERNEL);
 		if (!data)
 			return -ENOMEM;
 
 		bacpy(&data->bdaddr, bdaddr);
+		data->bdaddr_type = bdaddr_type;
 		list_add(&data->list, &hdev->remote_oob_data);
 	}
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index c3d6390e3b7..f4e2a61bb6a 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3773,7 +3773,7 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 		cp.authentication = conn->auth_type;
 
-		if (hci_find_remote_oob_data(hdev, &conn->dst) &&
+		if (hci_find_remote_oob_data(hdev, &conn->dst, BDADDR_BREDR) &&
 		    (conn->out || test_bit(HCI_CONN_REMOTE_OOB, &conn->flags)))
 			cp.oob_data = 0x01;
 		else
@@ -4028,7 +4028,7 @@ static void hci_remote_oob_data_request_evt(struct hci_dev *hdev,
 	if (!test_bit(HCI_MGMT, &hdev->dev_flags))
 		goto unlock;
 
-	data = hci_find_remote_oob_data(hdev, &ev->bdaddr);
+	data = hci_find_remote_oob_data(hdev, &ev->bdaddr, BDADDR_BREDR);
 	if (data) {
 		if (bredr_sc_enabled(hdev)) {
 			struct hci_cp_remote_oob_ext_data_reply cp;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 0d92ba99ca9..57de9f7222a 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3599,8 +3599,8 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
 		}
 
 		err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr,
-					      cp->hash, cp->rand,
-					      NULL, NULL);
+					      cp->addr.type, cp->hash,
+					      cp->rand, NULL, NULL);
 		if (err < 0)
 			status = MGMT_STATUS_FAILED;
 		else
@@ -3621,8 +3621,9 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
 		}
 
 		err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr,
-					      cp->hash192, cp->rand192,
-					      cp->hash256, cp->rand256);
+					      cp->addr.type, cp->hash192,
+					      cp->rand192, cp->hash256,
+					      cp->rand256);
 		if (err < 0)
 			status = MGMT_STATUS_FAILED;
 		else
@@ -3663,7 +3664,7 @@ static int remove_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
 		goto done;
 	}
 
-	err = hci_remove_remote_oob_data(hdev, &cp->addr.bdaddr);
+	err = hci_remove_remote_oob_data(hdev, &cp->addr.bdaddr, cp->addr.type);
 	if (err < 0)
 		status = MGMT_STATUS_INVALID_PARAMS;
 	else
-- 
cgit v1.2.3-70-g09d2


From 75c28c09af99a0db0ccd8b4395469761aa736543 Mon Sep 17 00:00:00 2001
From: Leif Lindholm <leif.lindholm@linaro.org>
Date: Fri, 28 Nov 2014 11:34:28 +0000
Subject: of: add optional options parameter to of_find_node_by_path()

Update of_find_node_by_path():
1) Rename function to of_find_node_opts_by_path(), adding an optional
   pointer argument. Provide a static inline wrapper version of
   of_find_node_by_path() which calls the new function with NULL as
   the optional argument.
2) Ignore any part of the path beyond and including the ':' separator.
3) Set the new provided pointer argument to the beginning of the string
   following the ':' separator.
4: Add tests.

Signed-off-by: Leif Lindholm <leif.lindholm@linaro.org>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 drivers/of/base.c     | 20 ++++++++++++++++----
 drivers/of/unittest.c | 30 ++++++++++++++++++++++++++++++
 include/linux/of.h    | 14 +++++++++++++-
 3 files changed, 59 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/of/base.c b/drivers/of/base.c
index 99bc95e83d0..bdf051d0a7e 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -714,10 +714,15 @@ static struct device_node *__of_find_node_by_path(struct device_node *parent,
 {
 	struct device_node *child;
 	int len = strchrnul(path, '/') - path;
+	int term;
 
 	if (!len)
 		return NULL;
 
+	term = strchrnul(path, ':') - path;
+	if (term < len)
+		len = term;
+
 	__for_each_child_of_node(parent, child) {
 		const char *name = strrchr(child->full_name, '/');
 		if (WARN(!name, "malformed device_node %s\n", child->full_name))
@@ -730,11 +735,14 @@ static struct device_node *__of_find_node_by_path(struct device_node *parent,
 }
 
 /**
- *	of_find_node_by_path - Find a node matching a full OF path
+ *	of_find_node_opts_by_path - Find a node matching a full OF path
  *	@path: Either the full path to match, or if the path does not
  *	       start with '/', the name of a property of the /aliases
  *	       node (an alias).  In the case of an alias, the node
  *	       matching the alias' value will be returned.
+ *	@opts: Address of a pointer into which to store the start of
+ *	       an options string appended to the end of the path with
+ *	       a ':' separator.
  *
  *	Valid paths:
  *		/foo/bar	Full path
@@ -744,11 +752,15 @@ static struct device_node *__of_find_node_by_path(struct device_node *parent,
  *	Returns a node pointer with refcount incremented, use
  *	of_node_put() on it when done.
  */
-struct device_node *of_find_node_by_path(const char *path)
+struct device_node *of_find_node_opts_by_path(const char *path, const char **opts)
 {
 	struct device_node *np = NULL;
 	struct property *pp;
 	unsigned long flags;
+	const char *separator = strchr(path, ':');
+
+	if (opts)
+		*opts = separator ? separator + 1 : NULL;
 
 	if (strcmp(path, "/") == 0)
 		return of_node_get(of_root);
@@ -756,7 +768,7 @@ struct device_node *of_find_node_by_path(const char *path)
 	/* The path could begin with an alias */
 	if (*path != '/') {
 		char *p = strchrnul(path, '/');
-		int len = p - path;
+		int len = separator ? separator - path : p - path;
 
 		/* of_aliases must not be NULL */
 		if (!of_aliases)
@@ -785,7 +797,7 @@ struct device_node *of_find_node_by_path(const char *path)
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	return np;
 }
-EXPORT_SYMBOL(of_find_node_by_path);
+EXPORT_SYMBOL(of_find_node_opts_by_path);
 
 /**
  *	of_find_node_by_name - Find a node by its "name" property
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 7a7ae07d592..1807a045864 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -47,6 +47,7 @@ static bool selftest_live_tree;
 static void __init of_selftest_find_node_by_name(void)
 {
 	struct device_node *np;
+	const char *options;
 
 	np = of_find_node_by_path("/testcase-data");
 	selftest(np && !strcmp("/testcase-data", np->full_name),
@@ -87,6 +88,35 @@ static void __init of_selftest_find_node_by_name(void)
 	np = of_find_node_by_path("testcase-alias/missing-path");
 	selftest(!np, "non-existent alias with relative path returned node %s\n", np->full_name);
 	of_node_put(np);
+
+	np = of_find_node_opts_by_path("/testcase-data:testoption", &options);
+	selftest(np && !strcmp("testoption", options),
+		 "option path test failed\n");
+	of_node_put(np);
+
+	np = of_find_node_opts_by_path("/testcase-data:testoption", NULL);
+	selftest(np, "NULL option path test failed\n");
+	of_node_put(np);
+
+	np = of_find_node_opts_by_path("testcase-alias:testaliasoption",
+				       &options);
+	selftest(np && !strcmp("testaliasoption", options),
+		 "option alias path test failed\n");
+	of_node_put(np);
+
+	np = of_find_node_opts_by_path("testcase-alias:testaliasoption", NULL);
+	selftest(np, "NULL option alias path test failed\n");
+	of_node_put(np);
+
+	options = "testoption";
+	np = of_find_node_opts_by_path("testcase-alias", &options);
+	selftest(np && !options, "option clearing test failed\n");
+	of_node_put(np);
+
+	options = "testoption";
+	np = of_find_node_opts_by_path("/", &options);
+	selftest(np && !options, "option clearing root node test failed\n");
+	of_node_put(np);
 }
 
 static void __init of_selftest_dynamic(void)
diff --git a/include/linux/of.h b/include/linux/of.h
index aa01cf5852f..8b021db3e16 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -236,7 +236,13 @@ extern struct device_node *of_find_matching_node_and_match(
 	const struct of_device_id *matches,
 	const struct of_device_id **match);
 
-extern struct device_node *of_find_node_by_path(const char *path);
+extern struct device_node *of_find_node_opts_by_path(const char *path,
+	const char **opts);
+static inline struct device_node *of_find_node_by_path(const char *path)
+{
+	return of_find_node_opts_by_path(path, NULL);
+}
+
 extern struct device_node *of_find_node_by_phandle(phandle handle);
 extern struct device_node *of_get_parent(const struct device_node *node);
 extern struct device_node *of_get_next_parent(struct device_node *node);
@@ -383,6 +389,12 @@ static inline struct device_node *of_find_node_by_path(const char *path)
 	return NULL;
 }
 
+static inline struct device_node *of_find_node_opts_by_path(const char *path,
+	const char **opts)
+{
+	return NULL;
+}
+
 static inline struct device_node *of_get_parent(const struct device_node *node)
 {
 	return NULL;
-- 
cgit v1.2.3-70-g09d2


From 70161ff336674ecfd20614a9c0c61cb17a6e9e83 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@linaro.org>
Date: Fri, 28 Nov 2014 16:03:33 +0000
Subject: of: Drop ->next pointer from struct device_node

The ->next pointer in struct device_node is a hanger-on from when it was
used to iterate over the whole tree by a particular device_type property
value. Those days are long over, but the fdt unflattening code still
uses it to put nodes in the unflattened tree into the same order as node
in the flat tree. By reworking the unflattening code to reverse the list
after unflattening all the children of a node, the pointer can be
dropped which gives a small amount of memory savings.

Signed-off-by: Grant Likely <grant.likely@linaro.org>
Acked-by: Frank Rowand <frank.rowand@sonymobile.com>
Cc: Gaurav Minocha <gaurav.minocha.os@gmail.com>
---
 drivers/of/fdt.c   | 24 ++++++++++++++++++------
 include/linux/of.h |  1 -
 2 files changed, 18 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 7f6ee31d565..a41f9fdb1aa 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -226,12 +226,8 @@ static void * unflatten_dt_node(void *blob,
 		prev_pp = &np->properties;
 		if (dad != NULL) {
 			np->parent = dad;
-			/* we temporarily use the next field as `last_child'*/
-			if (dad->next == NULL)
-				dad->child = np;
-			else
-				dad->next->sibling = np;
-			dad->next = np;
+			np->sibling = dad->child;
+			dad->child = np;
 		}
 	}
 	/* process properties */
@@ -329,6 +325,22 @@ static void * unflatten_dt_node(void *blob,
 
 	if (*poffset < 0 && *poffset != -FDT_ERR_NOTFOUND)
 		pr_err("unflatten: error %d processing FDT\n", *poffset);
+
+	/*
+	 * Reverse the child list. Some drivers assumes node order matches .dts
+	 * node order
+	 */
+	if (!dryrun && np->child) {
+		struct device_node *child = np->child;
+		np->child = NULL;
+		while (child) {
+			struct device_node *next = child->sibling;
+			child->sibling = np->child;
+			np->child = child;
+			child = next;
+		}
+	}
+
 	if (nodepp)
 		*nodepp = np;
 
diff --git a/include/linux/of.h b/include/linux/of.h
index 8b021db3e16..3f0f0ffbd5e 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -56,7 +56,6 @@ struct device_node {
 	struct	device_node *parent;
 	struct	device_node *child;
 	struct	device_node *sibling;
-	struct	device_node *next;	/* next device of same type */
 	struct	kobject kobj;
 	unsigned long _flags;
 	void	*data;
-- 
cgit v1.2.3-70-g09d2


From 4afbe1760d89fec07e7a8cce58beb1b4921a194c Mon Sep 17 00:00:00 2001
From: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Date: Tue, 2 Dec 2014 08:54:18 +0100
Subject: clk: Remove unused function __clk_get_prepare_count

Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Michael Turquette <mturquette@linaro.org>
---
 drivers/clk/clk.c            | 5 -----
 include/linux/clk-provider.h | 1 -
 2 files changed, 6 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 5307225684e..42f940ff5ed 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -574,11 +574,6 @@ unsigned int __clk_get_enable_count(struct clk *clk)
 	return !clk ? 0 : clk->enable_count;
 }
 
-unsigned int __clk_get_prepare_count(struct clk *clk)
-{
-	return !clk ? 0 : clk->prepare_count;
-}
-
 unsigned long __clk_get_rate(struct clk *clk)
 {
 	unsigned long ret;
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 2839c639f09..fcf3252b829 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -544,7 +544,6 @@ u8 __clk_get_num_parents(struct clk *clk);
 struct clk *__clk_get_parent(struct clk *clk);
 struct clk *clk_get_parent_by_index(struct clk *clk, u8 index);
 unsigned int __clk_get_enable_count(struct clk *clk);
-unsigned int __clk_get_prepare_count(struct clk *clk);
 unsigned long __clk_get_rate(struct clk *clk);
 unsigned long __clk_get_accuracy(struct clk *clk);
 unsigned long __clk_get_flags(struct clk *clk);
-- 
cgit v1.2.3-70-g09d2


From 920f1c7472f35cd3b3a3add10cccb0ef12376a17 Mon Sep 17 00:00:00 2001
From: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Date: Tue, 2 Dec 2014 08:54:20 +0100
Subject: clk: Don't expose __clk_get_accuracy

As it's only used internally, in drivers/clk/clk.c.

Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Michael Turquette <mturquette@linaro.org>
---
 drivers/clk/clk.c            | 2 +-
 include/linux/clk-provider.h | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 609e9db1a69..73247e90ee5 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -596,7 +596,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(__clk_get_rate);
 
-unsigned long __clk_get_accuracy(struct clk *clk)
+static unsigned long __clk_get_accuracy(struct clk *clk)
 {
 	if (!clk)
 		return 0;
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index fcf3252b829..270137aaf3a 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -545,7 +545,6 @@ struct clk *__clk_get_parent(struct clk *clk);
 struct clk *clk_get_parent_by_index(struct clk *clk, u8 index);
 unsigned int __clk_get_enable_count(struct clk *clk);
 unsigned long __clk_get_rate(struct clk *clk);
-unsigned long __clk_get_accuracy(struct clk *clk);
 unsigned long __clk_get_flags(struct clk *clk);
 bool __clk_is_prepared(struct clk *clk);
 bool __clk_is_enabled(struct clk *clk);
-- 
cgit v1.2.3-70-g09d2


From 61c7cddfad266ebb86176723f9c679f25cf705fe Mon Sep 17 00:00:00 2001
From: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Date: Tue, 2 Dec 2014 08:54:21 +0100
Subject: clk: change clk_debugfs_add_file to take a struct clk_hw

Instead of struct clk, as this should be only used by providers.

Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Michael Turquette <mturquette@linaro.org>
---
 drivers/clk/clk.c            | 6 +++---
 include/linux/clk-provider.h | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 73247e90ee5..f549e8b1d5e 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -354,13 +354,13 @@ out:
 	mutex_unlock(&clk_debug_lock);
 }
 
-struct dentry *clk_debugfs_add_file(struct clk *clk, char *name, umode_t mode,
+struct dentry *clk_debugfs_add_file(struct clk_hw *hw, char *name, umode_t mode,
 				void *data, const struct file_operations *fops)
 {
 	struct dentry *d = NULL;
 
-	if (clk->dentry)
-		d = debugfs_create_file(name, mode, clk->dentry, data, fops);
+	if (hw->clk->dentry)
+		d = debugfs_create_file(name, mode, hw->clk->dentry, data, fops);
 
 	return d;
 }
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 270137aaf3a..5e06f23eed4 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -650,7 +650,7 @@ static inline void clk_writel(u32 val, u32 __iomem *reg)
 #endif	/* platform dependent I/O accessors */
 
 #ifdef CONFIG_DEBUG_FS
-struct dentry *clk_debugfs_add_file(struct clk *clk, char *name, umode_t mode,
+struct dentry *clk_debugfs_add_file(struct clk_hw *hw, char *name, umode_t mode,
 				void *data, const struct file_operations *fops);
 #endif
 
-- 
cgit v1.2.3-70-g09d2


From aa35071c590461f95d0179cc8e730d49d610f773 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Wed, 3 Dec 2014 15:46:48 +0100
Subject: drm/ttm: optionally move duplicates to a separate list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds an optional list_head parameter to ttm_eu_reserve_buffers.
If specified duplicates in the execbuf list are no longer reported as errors,
but moved to this list instead.

Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/qxl/qxl_release.c        |  3 ++-
 drivers/gpu/drm/radeon/radeon_gem.c      |  2 +-
 drivers/gpu/drm/radeon/radeon_object.c   |  2 +-
 drivers/gpu/drm/ttm/ttm_execbuf_util.c   | 10 +++++++++-
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c  |  6 ++++--
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c |  2 +-
 include/drm/ttm/ttm_execbuf_util.h       |  9 ++++++++-
 7 files changed, 26 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 446e71ca36c..d9b25684ac9 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -264,7 +264,8 @@ int qxl_release_reserve_list(struct qxl_release *release, bool no_intr)
 	if (list_is_singular(&release->bos))
 		return 0;
 
-	ret = ttm_eu_reserve_buffers(&release->ticket, &release->bos, !no_intr);
+	ret = ttm_eu_reserve_buffers(&release->ticket, &release->bos,
+				     !no_intr, NULL);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 6162bd29a59..fe48f229043 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -564,7 +564,7 @@ static void radeon_gem_va_update_vm(struct radeon_device *rdev,
 	if (!vm_bos)
 		return;
 
-	r = ttm_eu_reserve_buffers(&ticket, &list, true);
+	r = ttm_eu_reserve_buffers(&ticket, &list, true, NULL);
 	if (r)
 		goto error_free;
 
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 4ab07473bb2..a4a3ac824b4 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -508,7 +508,7 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
 	u64 bytes_moved = 0, initial_bytes_moved;
 	u64 bytes_moved_threshold = radeon_bo_get_threshold_for_moves(rdev);
 
-	r = ttm_eu_reserve_buffers(ticket, head, true);
+	r = ttm_eu_reserve_buffers(ticket, head, true, NULL);
 	if (unlikely(r != 0)) {
 		return r;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index 8ce508e7620..3820ae97a03 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -93,7 +93,8 @@ EXPORT_SYMBOL(ttm_eu_backoff_reservation);
  */
 
 int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
-			   struct list_head *list, bool intr)
+			   struct list_head *list, bool intr,
+			   struct list_head *dups)
 {
 	struct ttm_bo_global *glob;
 	struct ttm_validate_buffer *entry;
@@ -117,6 +118,13 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 			__ttm_bo_unreserve(bo);
 
 			ret = -EBUSY;
+
+		} else if (ret == -EALREADY && dups) {
+			struct ttm_validate_buffer *safe = entry;
+			entry = list_prev_entry(entry, head);
+			list_del(&safe->head);
+			list_add(&safe->head, dups);
+			continue;
 		}
 
 		if (!ret) {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 596cd6dafd3..33176d05db3 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -2487,7 +2487,8 @@ int vmw_execbuf_process(struct drm_file *file_priv,
 	if (unlikely(ret != 0))
 		goto out_err_nores;
 
-	ret = ttm_eu_reserve_buffers(&ticket, &sw_context->validate_nodes, true);
+	ret = ttm_eu_reserve_buffers(&ticket, &sw_context->validate_nodes,
+				     true, NULL);
 	if (unlikely(ret != 0))
 		goto out_err;
 
@@ -2677,7 +2678,8 @@ void __vmw_execbuf_release_pinned_bo(struct vmw_private *dev_priv,
 	query_val.shared = false;
 	list_add_tail(&query_val.head, &validate_list);
 
-	ret = ttm_eu_reserve_buffers(&ticket, &validate_list, false);
+	ret = ttm_eu_reserve_buffers(&ticket, &validate_list,
+				     false, NULL);
 	if (unlikely(ret != 0)) {
 		vmw_execbuf_unpin_panic(dev_priv);
 		goto out_no_reserve;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 026de7cea0f..210ef15b1d0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -1222,7 +1222,7 @@ vmw_resource_check_buffer(struct vmw_resource *res,
 	val_buf->bo = ttm_bo_reference(&res->backup->base);
 	val_buf->shared = false;
 	list_add_tail(&val_buf->head, &val_list);
-	ret = ttm_eu_reserve_buffers(NULL, &val_list, interruptible);
+	ret = ttm_eu_reserve_buffers(NULL, &val_list, interruptible, NULL);
 	if (unlikely(ret != 0))
 		goto out_no_reserve;
 
diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h
index 46044171441..b620c317c77 100644
--- a/include/drm/ttm/ttm_execbuf_util.h
+++ b/include/drm/ttm/ttm_execbuf_util.h
@@ -68,6 +68,7 @@ extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
  *           non-blocking reserves should be tried.
  * @list:    thread private list of ttm_validate_buffer structs.
  * @intr:    should the wait be interruptible
+ * @dups:    [out] optional list of duplicates.
  *
  * Tries to reserve bos pointed to by the list entries for validation.
  * If the function returns 0, all buffers are marked as "unfenced",
@@ -83,6 +84,11 @@ extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
  * calling process receives a signal while waiting. In that case, no
  * buffers on the list will be reserved upon return.
  *
+ * If dups is non NULL all buffers already reserved by the current thread
+ * (e.g. duplicates) are added to this list, otherwise -EALREADY is returned
+ * on the first already reserved buffer and all buffers from the list are
+ * unreserved again.
+ *
  * Buffers reserved by this function should be unreserved by
  * a call to either ttm_eu_backoff_reservation() or
  * ttm_eu_fence_buffer_objects() when command submission is complete or
@@ -90,7 +96,8 @@ extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
  */
 
 extern int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
-				  struct list_head *list, bool intr);
+				  struct list_head *list, bool intr,
+				  struct list_head *dups);
 
 /**
  * function ttm_eu_fence_buffer_objects.
-- 
cgit v1.2.3-70-g09d2


From c11f6f5bb1e07db79c4c97d768b32b63378c69e0 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 1 Dec 2014 12:50:21 +0100
Subject: PM / Domains: Initial PM clock support for genpd

It's quite common for PM domains to use PM clocks. Typically from SOC
specific code, the per device PM clock list is created and
pm_clk_suspend|resume() are invoked to handle clock gating/ungating.

A step towards consolidation is to integrate PM clock support into
genpd, which is what this patch does.

In this initial step, the calls to the pm_clk_suspend|resume() are
handled within genpd, but the per device PM clock list still needs to
be created from SOC specific code. It seems reasonable to have gendp to
handle that as well, but that left to future patches to address.

It's not every users of genpd that are keen on using PM clocks, thus we
need to provide this a configuration option for genpd. Therefore let's
add flag field in the genpd struct to keep this information and define
a new GENDP_FLAG_PM_CLK bit for it.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 7 +++++++
 include/linux/pm_domain.h   | 4 ++++
 2 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 1bfb54ce60e..5d7b7548873 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -12,6 +12,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_qos.h>
+#include <linux/pm_clock.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/sched.h>
@@ -1948,6 +1949,12 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->domain.ops.complete = pm_genpd_complete;
 	genpd->dev_ops.save_state = pm_genpd_default_save_state;
 	genpd->dev_ops.restore_state = pm_genpd_default_restore_state;
+
+	if (genpd->flags & GENPD_FLAG_PM_CLK) {
+		genpd->dev_ops.stop = pm_clk_suspend;
+		genpd->dev_ops.start = pm_clk_resume;
+	}
+
 	mutex_lock(&gpd_list_lock);
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 9d254e25f86..1dd6c7f6416 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -17,6 +17,9 @@
 #include <linux/notifier.h>
 #include <linux/cpuidle.h>
 
+/* Defines used for the flags field in the struct generic_pm_domain */
+#define GENPD_FLAG_PM_CLK	(1U << 0) /* PM domain uses PM clk */
+
 enum gpd_status {
 	GPD_STATE_ACTIVE = 0,	/* PM domain is active */
 	GPD_STATE_WAIT_MASTER,	/* PM domain's master is being waited for */
@@ -76,6 +79,7 @@ struct generic_pm_domain {
 			  struct device *dev);
 	void (*detach_dev)(struct generic_pm_domain *domain,
 			   struct device *dev);
+	unsigned int flags;		/* Bit field of configs for genpd */
 };
 
 static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd)
-- 
cgit v1.2.3-70-g09d2


From d30d819dc83107812d9b2876e5e7194e511ed6af Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 27 Nov 2014 22:38:05 +0100
Subject: PM: Drop CONFIG_PM_RUNTIME from the driver core

After commit b2b49ccbdd54 (PM: Kconfig: Set PM_RUNTIME if PM_SLEEP is
selected) PM_RUNTIME is always set if PM is set, so quite a few
depend on CONFIG_PM or even may be dropped entirely in some cases.

Replace CONFIG_PM_RUNTIME with CONFIG_PM in the PM core code.

Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/clock_ops.c       | 69 ++----------------------------------
 drivers/base/power/domain.c          | 34 ++----------------
 drivers/base/power/domain_governor.c | 11 ------
 drivers/base/power/power.h           | 56 +++++++++++++----------------
 drivers/base/power/qos.c             |  5 ---
 drivers/base/power/runtime.c         |  9 -----
 drivers/base/power/sysfs.c           | 19 +---------
 include/linux/pm.h                   |  2 +-
 include/linux/pm_domain.h            |  8 ++---
 include/linux/pm_qos.h               | 38 +++++++++-----------
 include/linux/pm_runtime.h           | 21 +++++------
 kernel/power/Kconfig                 |  4 ---
 12 files changed, 60 insertions(+), 216 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index b32b5d47b3c..d626576a4f7 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -256,10 +256,6 @@ void pm_clk_destroy(struct device *dev)
 	}
 }
 
-#endif /* CONFIG_PM */
-
-#ifdef CONFIG_PM_RUNTIME
-
 /**
  * pm_clk_suspend - Disable clocks in a device's PM clock list.
  * @dev: Device to disable the clocks for.
@@ -373,68 +369,7 @@ static int pm_clk_notify(struct notifier_block *nb,
 	return 0;
 }
 
-#else /* !CONFIG_PM_RUNTIME */
-
-#ifdef CONFIG_PM
-
-/**
- * pm_clk_suspend - Disable clocks in a device's PM clock list.
- * @dev: Device to disable the clocks for.
- */
-int pm_clk_suspend(struct device *dev)
-{
-	struct pm_subsys_data *psd = dev_to_psd(dev);
-	struct pm_clock_entry *ce;
-	unsigned long flags;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	/* If there is no driver, the clocks are already disabled. */
-	if (!psd || !dev->driver)
-		return 0;
-
-	spin_lock_irqsave(&psd->lock, flags);
-
-	list_for_each_entry_reverse(ce, &psd->clock_list, node) {
-		if (ce->status < PCE_STATUS_ERROR) {
-			if (ce->status == PCE_STATUS_ENABLED)
-				clk_disable(ce->clk);
-			ce->status = PCE_STATUS_ACQUIRED;
-		}
-	}
-
-	spin_unlock_irqrestore(&psd->lock, flags);
-
-	return 0;
-}
-
-/**
- * pm_clk_resume - Enable clocks in a device's PM clock list.
- * @dev: Device to enable the clocks for.
- */
-int pm_clk_resume(struct device *dev)
-{
-	struct pm_subsys_data *psd = dev_to_psd(dev);
-	struct pm_clock_entry *ce;
-	unsigned long flags;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	/* If there is no driver, the clocks should remain disabled. */
-	if (!psd || !dev->driver)
-		return 0;
-
-	spin_lock_irqsave(&psd->lock, flags);
-
-	list_for_each_entry(ce, &psd->clock_list, node)
-		__pm_clk_enable(dev, ce);
-
-	spin_unlock_irqrestore(&psd->lock, flags);
-
-	return 0;
-}
-
-#endif /* CONFIG_PM */
+#else /* !CONFIG_PM */
 
 /**
  * enable_clock - Enable a device clock.
@@ -514,7 +449,7 @@ static int pm_clk_notify(struct notifier_block *nb,
 	return 0;
 }
 
-#endif /* !CONFIG_PM_RUNTIME */
+#endif /* !CONFIG_PM */
 
 /**
  * pm_clk_add_notifier - Add bus type notifier for power management clocks.
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index fb83d4acd40..7c5c7410d76 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -280,8 +280,6 @@ int pm_genpd_name_poweron(const char *domain_name)
 	return genpd ? pm_genpd_poweron(genpd) : -EINVAL;
 }
 
-#ifdef CONFIG_PM_RUNTIME
-
 static int genpd_start_dev_no_timing(struct generic_pm_domain *genpd,
 				     struct device *dev)
 {
@@ -755,24 +753,6 @@ static int __init genpd_poweroff_unused(void)
 }
 late_initcall(genpd_poweroff_unused);
 
-#else
-
-static inline int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
-					    unsigned long val, void *ptr)
-{
-	return NOTIFY_DONE;
-}
-
-static inline void
-genpd_queue_power_off_work(struct generic_pm_domain *genpd) {}
-
-static inline void genpd_power_off_work_fn(struct work_struct *work) {}
-
-#define pm_genpd_runtime_suspend	NULL
-#define pm_genpd_runtime_resume		NULL
-
-#endif /* CONFIG_PM_RUNTIME */
-
 #ifdef CONFIG_PM_SLEEP
 
 /**
@@ -1364,7 +1344,7 @@ void pm_genpd_syscore_poweron(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron);
 
-#else
+#else /* !CONFIG_PM_SLEEP */
 
 #define pm_genpd_prepare		NULL
 #define pm_genpd_suspend		NULL
@@ -2220,7 +2200,7 @@ int genpd_dev_pm_attach(struct device *dev)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
-#endif
+#endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
 
 
 /***        debugfs support        ***/
@@ -2236,10 +2216,8 @@ static struct dentry *pm_genpd_debugfs_dir;
 
 /*
  * TODO: This function is a slightly modified version of rtpm_status_show
- * from sysfs.c, but dependencies between PM_GENERIC_DOMAINS and PM_RUNTIME
- * are too loose to generalize it.
+ * from sysfs.c, so generalize it.
  */
-#ifdef CONFIG_PM_RUNTIME
 static void rtpm_status_str(struct seq_file *s, struct device *dev)
 {
 	static const char * const status_lookup[] = {
@@ -2261,12 +2239,6 @@ static void rtpm_status_str(struct seq_file *s, struct device *dev)
 
 	seq_puts(s, p);
 }
-#else
-static void rtpm_status_str(struct seq_file *s, struct device *dev)
-{
-	seq_puts(s, "active");
-}
-#endif
 
 static int pm_genpd_summary_one(struct seq_file *s,
 		struct generic_pm_domain *gpd)
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index d88a62e104d..2a4154a09e4 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -11,8 +11,6 @@
 #include <linux/pm_qos.h>
 #include <linux/hrtimer.h>
 
-#ifdef CONFIG_PM_RUNTIME
-
 static int dev_update_qos_constraint(struct device *dev, void *data)
 {
 	s64 *constraint_ns_p = data;
@@ -227,15 +225,6 @@ static bool always_on_power_down_ok(struct dev_pm_domain *domain)
 	return false;
 }
 
-#else /* !CONFIG_PM_RUNTIME */
-
-static inline bool default_stop_ok(struct device *dev) { return false; }
-
-#define default_power_down_ok	NULL
-#define always_on_power_down_ok	NULL
-
-#endif /* !CONFIG_PM_RUNTIME */
-
 struct dev_power_governor simple_qos_governor = {
 	.stop_ok = default_stop_ok,
 	.power_down_ok = default_power_down_ok,
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index a21223d9592..b6b8a273c5d 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -9,7 +9,7 @@ static inline void device_pm_init_common(struct device *dev)
 	}
 }
 
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 
 static inline void pm_runtime_early_init(struct device *dev)
 {
@@ -20,7 +20,21 @@ static inline void pm_runtime_early_init(struct device *dev)
 extern void pm_runtime_init(struct device *dev);
 extern void pm_runtime_remove(struct device *dev);
 
-#else /* !CONFIG_PM_RUNTIME */
+/*
+ * sysfs.c
+ */
+
+extern int dpm_sysfs_add(struct device *dev);
+extern void dpm_sysfs_remove(struct device *dev);
+extern void rpm_sysfs_remove(struct device *dev);
+extern int wakeup_sysfs_add(struct device *dev);
+extern void wakeup_sysfs_remove(struct device *dev);
+extern int pm_qos_sysfs_add_resume_latency(struct device *dev);
+extern void pm_qos_sysfs_remove_resume_latency(struct device *dev);
+extern int pm_qos_sysfs_add_flags(struct device *dev);
+extern void pm_qos_sysfs_remove_flags(struct device *dev);
+
+#else /* CONFIG_PM */
 
 static inline void pm_runtime_early_init(struct device *dev)
 {
@@ -30,7 +44,15 @@ static inline void pm_runtime_early_init(struct device *dev)
 static inline void pm_runtime_init(struct device *dev) {}
 static inline void pm_runtime_remove(struct device *dev) {}
 
-#endif /* !CONFIG_PM_RUNTIME */
+static inline int dpm_sysfs_add(struct device *dev) { return 0; }
+static inline void dpm_sysfs_remove(struct device *dev) {}
+static inline void rpm_sysfs_remove(struct device *dev) {}
+static inline int wakeup_sysfs_add(struct device *dev) { return 0; }
+static inline void wakeup_sysfs_remove(struct device *dev) {}
+static inline int pm_qos_sysfs_add(struct device *dev) { return 0; }
+static inline void pm_qos_sysfs_remove(struct device *dev) {}
+
+#endif
 
 #ifdef CONFIG_PM_SLEEP
 
@@ -77,31 +99,3 @@ static inline void device_pm_init(struct device *dev)
 	device_pm_sleep_init(dev);
 	pm_runtime_init(dev);
 }
-
-#ifdef CONFIG_PM
-
-/*
- * sysfs.c
- */
-
-extern int dpm_sysfs_add(struct device *dev);
-extern void dpm_sysfs_remove(struct device *dev);
-extern void rpm_sysfs_remove(struct device *dev);
-extern int wakeup_sysfs_add(struct device *dev);
-extern void wakeup_sysfs_remove(struct device *dev);
-extern int pm_qos_sysfs_add_resume_latency(struct device *dev);
-extern void pm_qos_sysfs_remove_resume_latency(struct device *dev);
-extern int pm_qos_sysfs_add_flags(struct device *dev);
-extern void pm_qos_sysfs_remove_flags(struct device *dev);
-
-#else /* CONFIG_PM */
-
-static inline int dpm_sysfs_add(struct device *dev) { return 0; }
-static inline void dpm_sysfs_remove(struct device *dev) {}
-static inline void rpm_sysfs_remove(struct device *dev) {}
-static inline int wakeup_sysfs_add(struct device *dev) { return 0; }
-static inline void wakeup_sysfs_remove(struct device *dev) {}
-static inline int pm_qos_sysfs_add(struct device *dev) { return 0; }
-static inline void pm_qos_sysfs_remove(struct device *dev) {}
-
-#endif
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 36b9eb4862c..a8fe4c1a8d0 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -599,7 +599,6 @@ int dev_pm_qos_add_ancestor_request(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_qos_add_ancestor_request);
 
-#ifdef CONFIG_PM_RUNTIME
 static void __dev_pm_qos_drop_user_request(struct device *dev,
 					   enum dev_pm_qos_req_type type)
 {
@@ -880,7 +879,3 @@ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val)
 	mutex_unlock(&dev_pm_qos_mtx);
 	return ret;
 }
-#else /* !CONFIG_PM_RUNTIME */
-static void __dev_pm_qos_hide_latency_limit(struct device *dev) {}
-static void __dev_pm_qos_hide_flags(struct device *dev) {}
-#endif /* CONFIG_PM_RUNTIME */
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 8f1ab8446ca..5070c4fe854 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -45,8 +45,6 @@ static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset)
 #define RPM_GET_CALLBACK(dev, callback) \
 		__rpm_get_callback(dev, offsetof(struct dev_pm_ops, callback))
 
-#ifdef CONFIG_PM_RUNTIME
-
 static int rpm_resume(struct device *dev, int rpmflags);
 static int rpm_suspend(struct device *dev, int rpmflags);
 
@@ -1399,7 +1397,6 @@ void pm_runtime_remove(struct device *dev)
 	if (dev->power.irq_safe && dev->parent)
 		pm_runtime_put(dev->parent);
 }
-#endif
 
 /**
  * pm_runtime_force_suspend - Force a device into suspend state if needed.
@@ -1419,12 +1416,6 @@ int pm_runtime_force_suspend(struct device *dev)
 	int ret = 0;
 
 	pm_runtime_disable(dev);
-
-	/*
-	 * Note that pm_runtime_status_suspended() returns false while
-	 * !CONFIG_PM_RUNTIME, which means the device will be put into low
-	 * power state.
-	 */
 	if (pm_runtime_status_suspended(dev))
 		return 0;
 
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index a9d26ed11bf..d2be3f9c211 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -95,7 +95,6 @@
 const char power_group_name[] = "power";
 EXPORT_SYMBOL_GPL(power_group_name);
 
-#ifdef CONFIG_PM_RUNTIME
 static const char ctrl_auto[] = "auto";
 static const char ctrl_on[] = "on";
 
@@ -330,7 +329,6 @@ static ssize_t pm_qos_remote_wakeup_store(struct device *dev,
 
 static DEVICE_ATTR(pm_qos_remote_wakeup, 0644,
 		   pm_qos_remote_wakeup_show, pm_qos_remote_wakeup_store);
-#endif /* CONFIG_PM_RUNTIME */
 
 #ifdef CONFIG_PM_SLEEP
 static const char _enabled[] = "enabled";
@@ -531,8 +529,6 @@ static DEVICE_ATTR(wakeup_prevent_sleep_time_ms, 0444,
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PM_ADVANCED_DEBUG
-#ifdef CONFIG_PM_RUNTIME
-
 static ssize_t rtpm_usagecount_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
@@ -562,10 +558,7 @@ static DEVICE_ATTR(runtime_usage, 0444, rtpm_usagecount_show, NULL);
 static DEVICE_ATTR(runtime_active_kids, 0444, rtpm_children_show, NULL);
 static DEVICE_ATTR(runtime_enabled, 0444, rtpm_enabled_show, NULL);
 
-#endif
-
 #ifdef CONFIG_PM_SLEEP
-
 static ssize_t async_show(struct device *dev, struct device_attribute *attr,
 			  char *buf)
 {
@@ -595,7 +588,7 @@ static ssize_t async_store(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR(async, 0644, async_show, async_store);
 
-#endif
+#endif /* CONFIG_PM_SLEEP */
 #endif /* CONFIG_PM_ADVANCED_DEBUG */
 
 static struct attribute *power_attrs[] = {
@@ -603,12 +596,10 @@ static struct attribute *power_attrs[] = {
 #ifdef CONFIG_PM_SLEEP
 	&dev_attr_async.attr,
 #endif
-#ifdef CONFIG_PM_RUNTIME
 	&dev_attr_runtime_status.attr,
 	&dev_attr_runtime_usage.attr,
 	&dev_attr_runtime_active_kids.attr,
 	&dev_attr_runtime_enabled.attr,
-#endif
 #endif /* CONFIG_PM_ADVANCED_DEBUG */
 	NULL,
 };
@@ -640,7 +631,6 @@ static struct attribute_group pm_wakeup_attr_group = {
 };
 
 static struct attribute *runtime_attrs[] = {
-#ifdef CONFIG_PM_RUNTIME
 #ifndef CONFIG_PM_ADVANCED_DEBUG
 	&dev_attr_runtime_status.attr,
 #endif
@@ -648,7 +638,6 @@ static struct attribute *runtime_attrs[] = {
 	&dev_attr_runtime_suspended_time.attr,
 	&dev_attr_runtime_active_time.attr,
 	&dev_attr_autosuspend_delay_ms.attr,
-#endif /* CONFIG_PM_RUNTIME */
 	NULL,
 };
 static struct attribute_group pm_runtime_attr_group = {
@@ -657,9 +646,7 @@ static struct attribute_group pm_runtime_attr_group = {
 };
 
 static struct attribute *pm_qos_resume_latency_attrs[] = {
-#ifdef CONFIG_PM_RUNTIME
 	&dev_attr_pm_qos_resume_latency_us.attr,
-#endif /* CONFIG_PM_RUNTIME */
 	NULL,
 };
 static struct attribute_group pm_qos_resume_latency_attr_group = {
@@ -668,9 +655,7 @@ static struct attribute_group pm_qos_resume_latency_attr_group = {
 };
 
 static struct attribute *pm_qos_latency_tolerance_attrs[] = {
-#ifdef CONFIG_PM_RUNTIME
 	&dev_attr_pm_qos_latency_tolerance_us.attr,
-#endif /* CONFIG_PM_RUNTIME */
 	NULL,
 };
 static struct attribute_group pm_qos_latency_tolerance_attr_group = {
@@ -679,10 +664,8 @@ static struct attribute_group pm_qos_latency_tolerance_attr_group = {
 };
 
 static struct attribute *pm_qos_flags_attrs[] = {
-#ifdef CONFIG_PM_RUNTIME
 	&dev_attr_pm_qos_no_power_off.attr,
 	&dev_attr_pm_qos_remote_wakeup.attr,
-#endif /* CONFIG_PM_RUNTIME */
 	NULL,
 };
 static struct attribute_group pm_qos_flags_attr_group = {
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 383fd68aaee..53b56cf5db3 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -576,7 +576,7 @@ struct dev_pm_info {
 #else
 	unsigned int		should_wakeup:1;
 #endif
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 	struct timer_list	suspend_timer;
 	unsigned long		timer_expires;
 	struct work_struct	work;
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 2e0e06daf8c..f9dedf2f410 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -147,6 +147,7 @@ extern void pm_genpd_init(struct generic_pm_domain *genpd,
 
 extern int pm_genpd_poweron(struct generic_pm_domain *genpd);
 extern int pm_genpd_name_poweron(const char *domain_name);
+extern void pm_genpd_poweroff_unused(void);
 
 extern struct dev_power_governor simple_qos_governor;
 extern struct dev_power_governor pm_domain_always_on_gov;
@@ -221,6 +222,7 @@ static inline int pm_genpd_name_poweron(const char *domain_name)
 {
 	return -ENOSYS;
 }
+static inline void pm_genpd_poweroff_unused(void) {}
 #define simple_qos_governor NULL
 #define pm_domain_always_on_gov NULL
 #endif
@@ -237,12 +239,6 @@ static inline int pm_genpd_name_add_device(const char *domain_name,
 	return __pm_genpd_name_add_device(domain_name, dev, NULL);
 }
 
-#ifdef CONFIG_PM_GENERIC_DOMAINS_RUNTIME
-extern void pm_genpd_poweroff_unused(void);
-#else
-static inline void pm_genpd_poweroff_unused(void) {}
-#endif
-
 #ifdef CONFIG_PM_GENERIC_DOMAINS_SLEEP
 extern void pm_genpd_syscore_poweroff(struct device *dev);
 extern void pm_genpd_syscore_poweron(struct device *dev);
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 636e8283450..7b3ae0cffc0 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -154,6 +154,23 @@ void dev_pm_qos_constraints_destroy(struct device *dev);
 int dev_pm_qos_add_ancestor_request(struct device *dev,
 				    struct dev_pm_qos_request *req,
 				    enum dev_pm_qos_req_type type, s32 value);
+int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value);
+void dev_pm_qos_hide_latency_limit(struct device *dev);
+int dev_pm_qos_expose_flags(struct device *dev, s32 value);
+void dev_pm_qos_hide_flags(struct device *dev);
+int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set);
+s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev);
+int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val);
+
+static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev)
+{
+	return dev->power.qos->resume_latency_req->data.pnode.prio;
+}
+
+static inline s32 dev_pm_qos_requested_flags(struct device *dev)
+{
+	return dev->power.qos->flags_req->data.flr.flags;
+}
 #else
 static inline enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev,
 							  s32 mask)
@@ -200,27 +217,6 @@ static inline int dev_pm_qos_add_ancestor_request(struct device *dev,
 						  enum dev_pm_qos_req_type type,
 						  s32 value)
 			{ return 0; }
-#endif
-
-#ifdef CONFIG_PM_RUNTIME
-int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value);
-void dev_pm_qos_hide_latency_limit(struct device *dev);
-int dev_pm_qos_expose_flags(struct device *dev, s32 value);
-void dev_pm_qos_hide_flags(struct device *dev);
-int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set);
-s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev);
-int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val);
-
-static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev)
-{
-	return dev->power.qos->resume_latency_req->data.pnode.prio;
-}
-
-static inline s32 dev_pm_qos_requested_flags(struct device *dev)
-{
-	return dev->power.qos->flags_req->data.flr.flags;
-}
-#else
 static inline int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value)
 			{ return 0; }
 static inline void dev_pm_qos_hide_latency_limit(struct device *dev) {}
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 367f49b9a1c..eda4feede04 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -35,16 +35,6 @@ extern int pm_generic_runtime_suspend(struct device *dev);
 extern int pm_generic_runtime_resume(struct device *dev);
 extern int pm_runtime_force_suspend(struct device *dev);
 extern int pm_runtime_force_resume(struct device *dev);
-#else
-static inline bool queue_pm_work(struct work_struct *work) { return false; }
-
-static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; }
-static inline int pm_generic_runtime_resume(struct device *dev) { return 0; }
-static inline int pm_runtime_force_suspend(struct device *dev) { return 0; }
-static inline int pm_runtime_force_resume(struct device *dev) { return 0; }
-#endif
-
-#ifdef CONFIG_PM_RUNTIME
 
 extern int __pm_runtime_idle(struct device *dev, int rpmflags);
 extern int __pm_runtime_suspend(struct device *dev, int rpmflags);
@@ -128,7 +118,14 @@ static inline void pm_runtime_mark_last_busy(struct device *dev)
 	ACCESS_ONCE(dev->power.last_busy) = jiffies;
 }
 
-#else /* !CONFIG_PM_RUNTIME */
+#else /* !CONFIG_PM */
+
+static inline bool queue_pm_work(struct work_struct *work) { return false; }
+
+static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; }
+static inline int pm_generic_runtime_resume(struct device *dev) { return 0; }
+static inline int pm_runtime_force_suspend(struct device *dev) { return 0; }
+static inline int pm_runtime_force_resume(struct device *dev) { return 0; }
 
 static inline int __pm_runtime_idle(struct device *dev, int rpmflags)
 {
@@ -179,7 +176,7 @@ static inline unsigned long pm_runtime_autosuspend_expiration(
 static inline void pm_runtime_set_memalloc_noio(struct device *dev,
 						bool enable){}
 
-#endif /* !CONFIG_PM_RUNTIME */
+#endif /* !CONFIG_PM */
 
 static inline int pm_runtime_idle(struct device *dev)
 {
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 95d712e3677..f8dc1cc8c4c 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -298,10 +298,6 @@ config PM_GENERIC_DOMAINS_SLEEP
 	def_bool y
 	depends on PM_SLEEP && PM_GENERIC_DOMAINS
 
-config PM_GENERIC_DOMAINS_RUNTIME
-	def_bool y
-	depends on PM_RUNTIME && PM_GENERIC_DOMAINS
-
 config PM_GENERIC_DOMAINS_OF
 	def_bool y
 	depends on PM_GENERIC_DOMAINS && OF
-- 
cgit v1.2.3-70-g09d2


From 5de21bb998b8e816e6a1df1f2c04d95fb6e27a5d Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 27 Nov 2014 22:38:23 +0100
Subject: ACPI / PM: Drop CONFIG_PM_RUNTIME from the ACPI core

After commit b2b49ccbdd54 (PM: Kconfig: Set PM_RUNTIME if PM_SLEEP is
selected) PM_RUNTIME is always set if PM is set, so quite a few
depend on CONFIG_PM.

Replace CONFIG_PM_RUNTIME with CONFIG_PM in the ACPI core code.

Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpi_lpss.c |  4 +---
 drivers/acpi/device_pm.c |  8 ++------
 drivers/acpi/pci_irq.c   |  2 +-
 include/acpi/acpi_bus.h  |  6 +-----
 include/linux/acpi.h     | 26 +++++++++++---------------
 5 files changed, 16 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index d1dd0ada14b..4f3febf8a58 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -588,7 +588,6 @@ static int acpi_lpss_resume_early(struct device *dev)
 }
 #endif /* CONFIG_PM_SLEEP */
 
-#ifdef CONFIG_PM_RUNTIME
 static int acpi_lpss_runtime_suspend(struct device *dev)
 {
 	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
@@ -631,11 +630,11 @@ static int acpi_lpss_runtime_resume(struct device *dev)
 
 	return pm_generic_runtime_resume(dev);
 }
-#endif /* CONFIG_PM_RUNTIME */
 #endif /* CONFIG_PM */
 
 static struct dev_pm_domain acpi_lpss_pm_domain = {
 	.ops = {
+#ifdef CONFIG_PM
 #ifdef CONFIG_PM_SLEEP
 		.prepare = acpi_subsys_prepare,
 		.complete = acpi_subsys_complete,
@@ -647,7 +646,6 @@ static struct dev_pm_domain acpi_lpss_pm_domain = {
 		.poweroff_late = acpi_lpss_suspend_late,
 		.restore_early = acpi_lpss_resume_early,
 #endif
-#ifdef CONFIG_PM_RUNTIME
 		.runtime_suspend = acpi_lpss_runtime_suspend,
 		.runtime_resume = acpi_lpss_runtime_resume,
 #endif
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 7db19316076..20c0a670c75 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -692,7 +692,6 @@ static int acpi_device_wakeup(struct acpi_device *adev, u32 target_state,
 	return 0;
 }
 
-#ifdef CONFIG_PM_RUNTIME
 /**
  * acpi_pm_device_run_wake - Enable/disable remote wakeup for given device.
  * @dev: Device to enable/disable the platform to wake up.
@@ -714,7 +713,6 @@ int acpi_pm_device_run_wake(struct device *phys_dev, bool enable)
 	return acpi_device_wakeup(adev, ACPI_STATE_S0, enable);
 }
 EXPORT_SYMBOL(acpi_pm_device_run_wake);
-#endif /* CONFIG_PM_RUNTIME */
 
 #ifdef CONFIG_PM_SLEEP
 /**
@@ -773,7 +771,6 @@ static int acpi_dev_pm_full_power(struct acpi_device *adev)
 		acpi_device_set_power(adev, ACPI_STATE_D0) : 0;
 }
 
-#ifdef CONFIG_PM_RUNTIME
 /**
  * acpi_dev_runtime_suspend - Put device into a low-power state using ACPI.
  * @dev: Device to put into a low-power state.
@@ -855,7 +852,6 @@ int acpi_subsys_runtime_resume(struct device *dev)
 	return ret ? ret : pm_generic_runtime_resume(dev);
 }
 EXPORT_SYMBOL_GPL(acpi_subsys_runtime_resume);
-#endif /* CONFIG_PM_RUNTIME */
 
 #ifdef CONFIG_PM_SLEEP
 /**
@@ -1023,10 +1019,9 @@ EXPORT_SYMBOL_GPL(acpi_subsys_freeze);
 
 static struct dev_pm_domain acpi_general_pm_domain = {
 	.ops = {
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 		.runtime_suspend = acpi_subsys_runtime_suspend,
 		.runtime_resume = acpi_subsys_runtime_resume,
-#endif
 #ifdef CONFIG_PM_SLEEP
 		.prepare = acpi_subsys_prepare,
 		.complete = acpi_subsys_complete,
@@ -1037,6 +1032,7 @@ static struct dev_pm_domain acpi_general_pm_domain = {
 		.poweroff = acpi_subsys_suspend,
 		.poweroff_late = acpi_subsys_suspend_late,
 		.restore_early = acpi_subsys_resume_early,
+#endif
 #endif
 	},
 };
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 6e6b80eb0bb..7cc4e33179f 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -484,7 +484,7 @@ void acpi_pci_irq_disable(struct pci_dev *dev)
 	/* Keep IOAPIC pin configuration when suspending */
 	if (dev->dev.power.is_prepared)
 		return;
-#ifdef	CONFIG_PM_RUNTIME
+#ifdef	CONFIG_PM
 	if (dev->dev.power.runtime_status == RPM_SUSPENDING)
 		return;
 #endif
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index f34a0835aa4..78f7521417e 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -516,6 +516,7 @@ acpi_status acpi_add_pm_notifier(struct acpi_device *adev, struct device *dev,
 				 void (*work_func)(struct work_struct *work));
 acpi_status acpi_remove_pm_notifier(struct acpi_device *adev);
 int acpi_pm_device_sleep_state(struct device *, int *, int);
+int acpi_pm_device_run_wake(struct device *, bool);
 #else
 static inline acpi_status acpi_add_pm_notifier(struct acpi_device *adev,
 					       struct device *dev,
@@ -535,11 +536,6 @@ static inline int acpi_pm_device_sleep_state(struct device *d, int *p, int m)
 	return (m >= ACPI_STATE_D0 && m <= ACPI_STATE_D3_COLD) ?
 		m : ACPI_STATE_D0;
 }
-#endif
-
-#ifdef CONFIG_PM_RUNTIME
-int acpi_pm_device_run_wake(struct device *, bool);
-#else
 static inline int acpi_pm_device_run_wake(struct device *dev, bool enable)
 {
 	return -ENODEV;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 407a12f663e..77329be250b 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -553,16 +553,26 @@ static inline void arch_reserve_mem_area(acpi_physical_address addr,
 #define acpi_os_set_prepare_sleep(func, pm1a_ctrl, pm1b_ctrl) do { } while (0)
 #endif
 
-#if defined(CONFIG_ACPI) && defined(CONFIG_PM_RUNTIME)
+#if defined(CONFIG_ACPI) && defined(CONFIG_PM)
 int acpi_dev_runtime_suspend(struct device *dev);
 int acpi_dev_runtime_resume(struct device *dev);
 int acpi_subsys_runtime_suspend(struct device *dev);
 int acpi_subsys_runtime_resume(struct device *dev);
+struct acpi_device *acpi_dev_pm_get_node(struct device *dev);
+int acpi_dev_pm_attach(struct device *dev, bool power_on);
 #else
 static inline int acpi_dev_runtime_suspend(struct device *dev) { return 0; }
 static inline int acpi_dev_runtime_resume(struct device *dev) { return 0; }
 static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; }
 static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; }
+static inline struct acpi_device *acpi_dev_pm_get_node(struct device *dev)
+{
+	return NULL;
+}
+static inline int acpi_dev_pm_attach(struct device *dev, bool power_on)
+{
+	return -ENODEV;
+}
 #endif
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP)
@@ -585,20 +595,6 @@ static inline int acpi_subsys_suspend(struct device *dev) { return 0; }
 static inline int acpi_subsys_freeze(struct device *dev) { return 0; }
 #endif
 
-#if defined(CONFIG_ACPI) && defined(CONFIG_PM)
-struct acpi_device *acpi_dev_pm_get_node(struct device *dev);
-int acpi_dev_pm_attach(struct device *dev, bool power_on);
-#else
-static inline struct acpi_device *acpi_dev_pm_get_node(struct device *dev)
-{
-	return NULL;
-}
-static inline int acpi_dev_pm_attach(struct device *dev, bool power_on)
-{
-	return -ENODEV;
-}
-#endif
-
 #ifdef CONFIG_ACPI
 __printf(3, 4)
 void acpi_handle_printk(const char *level, acpi_handle handle,
-- 
cgit v1.2.3-70-g09d2


From 6ed23b806e73bdd5b17722df507b0f4570c606b6 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 4 Dec 2014 00:34:11 +0100
Subject: PM: Merge the SET*_RUNTIME_PM_OPS() macros

The SET_PM_RUNTIME_PM_OPS() and SET_RUNTIME_PM_OPS() macros are
identical except that one of them is not empty for CONFIG_PM set,
while the other one is not empty for CONFIG_PM_RUNTIME set,
respectively.

However, after commit b2b49ccbdd54 (PM: Kconfig: Set PM_RUNTIME if
PM_SLEEP is selected) PM_RUNTIME is always set if PM is set, so one
of these macros is now redundant.

For this reason, replace SET_PM_RUNTIME_PM_OPS() with
SET_RUNTIME_PM_OPS() everywhere and redefine the SET_PM_RUNTIME_PM_OPS
symbol as SET_RUNTIME_PM_OPS in case new code is starting to use the
macro being removed here.

Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/amba/bus.c                |  2 +-
 drivers/dma/ste_dma40.c           |  2 +-
 drivers/gpio/gpio-zynq.c          |  2 +-
 drivers/i2c/busses/i2c-hix5hd2.c  |  2 +-
 drivers/i2c/busses/i2c-nomadik.c  |  2 +-
 drivers/mmc/host/mmci.c           |  2 +-
 drivers/mmc/host/sh_mobile_sdhi.c |  2 +-
 drivers/mmc/host/tmio_mmc.c       |  2 +-
 drivers/spi/spi-pl022.c           |  2 +-
 include/linux/pm.h                | 11 ++---------
 10 files changed, 11 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 47bbdc1b5be..973a3332a85 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -124,7 +124,7 @@ static const struct dev_pm_ops amba_pm = {
 	.thaw		= pm_generic_thaw,
 	.poweroff	= pm_generic_poweroff,
 	.restore	= pm_generic_restore,
-	SET_PM_RUNTIME_PM_OPS(
+	SET_RUNTIME_PM_OPS(
 		amba_pm_runtime_suspend,
 		amba_pm_runtime_resume,
 		NULL
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 5fe59335e24..d9ca3e32d74 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -3051,7 +3051,7 @@ static int dma40_runtime_resume(struct device *dev)
 
 static const struct dev_pm_ops dma40_pm_ops = {
 	SET_LATE_SYSTEM_SLEEP_PM_OPS(dma40_suspend, dma40_resume)
-	SET_PM_RUNTIME_PM_OPS(dma40_runtime_suspend,
+	SET_RUNTIME_PM_OPS(dma40_runtime_suspend,
 				dma40_runtime_resume,
 				NULL)
 };
diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index 74cd480bf8d..184c4b1b255 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -578,7 +578,7 @@ static void zynq_gpio_free(struct gpio_chip *chip, unsigned offset)
 
 static const struct dev_pm_ops zynq_gpio_dev_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(zynq_gpio_suspend, zynq_gpio_resume)
-	SET_PM_RUNTIME_PM_OPS(zynq_gpio_runtime_suspend,
+	SET_RUNTIME_PM_OPS(zynq_gpio_runtime_suspend,
 			zynq_gpio_runtime_resume, NULL)
 };
 
diff --git a/drivers/i2c/busses/i2c-hix5hd2.c b/drivers/i2c/busses/i2c-hix5hd2.c
index 9490d0f4255..8fe78d08e01 100644
--- a/drivers/i2c/busses/i2c-hix5hd2.c
+++ b/drivers/i2c/busses/i2c-hix5hd2.c
@@ -528,7 +528,7 @@ static int hix5hd2_i2c_runtime_resume(struct device *dev)
 #endif
 
 static const struct dev_pm_ops hix5hd2_i2c_pm_ops = {
-	SET_PM_RUNTIME_PM_OPS(hix5hd2_i2c_runtime_suspend,
+	SET_RUNTIME_PM_OPS(hix5hd2_i2c_runtime_suspend,
 			      hix5hd2_i2c_runtime_resume,
 			      NULL)
 };
diff --git a/drivers/i2c/busses/i2c-nomadik.c b/drivers/i2c/busses/i2c-nomadik.c
index 9ad038d223c..97998946c4f 100644
--- a/drivers/i2c/busses/i2c-nomadik.c
+++ b/drivers/i2c/busses/i2c-nomadik.c
@@ -932,7 +932,7 @@ static int nmk_i2c_runtime_resume(struct device *dev)
 
 static const struct dev_pm_ops nmk_i2c_pm = {
 	SET_LATE_SYSTEM_SLEEP_PM_OPS(nmk_i2c_suspend_late, nmk_i2c_resume_early)
-	SET_PM_RUNTIME_PM_OPS(nmk_i2c_runtime_suspend,
+	SET_RUNTIME_PM_OPS(nmk_i2c_runtime_suspend,
 			nmk_i2c_runtime_resume,
 			NULL)
 };
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 43af791e2e4..184ea59afa7 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -1843,7 +1843,7 @@ static int mmci_runtime_resume(struct device *dev)
 static const struct dev_pm_ops mmci_dev_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
 				pm_runtime_force_resume)
-	SET_PM_RUNTIME_PM_OPS(mmci_runtime_suspend, mmci_runtime_resume, NULL)
+	SET_RUNTIME_PM_OPS(mmci_runtime_suspend, mmci_runtime_resume, NULL)
 };
 
 static struct amba_id mmci_ids[] = {
diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index a2e81a1ea6a..00c8ebdf8ec 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -375,7 +375,7 @@ static int sh_mobile_sdhi_remove(struct platform_device *pdev)
 static const struct dev_pm_ops tmio_mmc_dev_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
 			pm_runtime_force_resume)
-	SET_PM_RUNTIME_PM_OPS(tmio_mmc_host_runtime_suspend,
+	SET_RUNTIME_PM_OPS(tmio_mmc_host_runtime_suspend,
 			tmio_mmc_host_runtime_resume,
 			NULL)
 };
diff --git a/drivers/mmc/host/tmio_mmc.c b/drivers/mmc/host/tmio_mmc.c
index 659028ddb8b..2616fdfdbbe 100644
--- a/drivers/mmc/host/tmio_mmc.c
+++ b/drivers/mmc/host/tmio_mmc.c
@@ -135,7 +135,7 @@ static int tmio_mmc_remove(struct platform_device *pdev)
 
 static const struct dev_pm_ops tmio_mmc_dev_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(tmio_mmc_suspend, tmio_mmc_resume)
-	SET_PM_RUNTIME_PM_OPS(tmio_mmc_host_runtime_suspend,
+	SET_RUNTIME_PM_OPS(tmio_mmc_host_runtime_suspend,
 			tmio_mmc_host_runtime_resume,
 			NULL)
 };
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index fc2dd844160..89ca162801d 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -2377,7 +2377,7 @@ static int pl022_runtime_resume(struct device *dev)
 
 static const struct dev_pm_ops pl022_dev_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(pl022_suspend, pl022_resume)
-	SET_PM_RUNTIME_PM_OPS(pl022_runtime_suspend, pl022_runtime_resume, NULL)
+	SET_RUNTIME_PM_OPS(pl022_runtime_suspend, pl022_runtime_resume, NULL)
 };
 
 static struct vendor_data vendor_arm = {
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 53b56cf5db3..1dc338f6d4a 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -342,7 +342,7 @@ struct dev_pm_ops {
 #define SET_LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn)
 #endif
 
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \
 	.runtime_suspend = suspend_fn, \
 	.runtime_resume = resume_fn, \
@@ -351,14 +351,7 @@ struct dev_pm_ops {
 #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn)
 #endif
 
-#ifdef CONFIG_PM
-#define SET_PM_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \
-	.runtime_suspend = suspend_fn, \
-	.runtime_resume = resume_fn, \
-	.runtime_idle = idle_fn,
-#else
-#define SET_PM_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn)
-#endif
+#define SET_PM_RUNTIME_PM_OPS	SET_RUNTIME_PM_OPS
 
 /*
  * Use this if you want to use the same suspend and resume callbacks for suspend
-- 
cgit v1.2.3-70-g09d2


From ceb6c9c862c86423f41c1e20ecf8d454f837f519 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Sat, 29 Nov 2014 23:47:05 +0100
Subject: USB / PM: Drop CONFIG_PM_RUNTIME from the USB core

After commit b2b49ccbdd54 (PM: Kconfig: Set PM_RUNTIME if PM_SLEEP is
selected) PM_RUNTIME is always set if PM is set, so quite a few
depend on CONFIG_PM (or even dropped in some cases).

Replace CONFIG_PM_RUNTIME with CONFIG_PM in the USB core code
and documentation.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/ABI/stable/sysfs-bus-usb  | 14 ++++++--------
 Documentation/ABI/testing/sysfs-bus-usb | 19 +++++++++----------
 Documentation/usb/power-management.txt  | 17 +++++++++--------
 drivers/usb/core/driver.c               |  6 +-----
 drivers/usb/core/hcd-pci.c              | 11 -----------
 drivers/usb/core/hcd.c                  | 12 ++++--------
 drivers/usb/core/hub.c                  |  6 +++---
 drivers/usb/core/port.c                 |  4 ++--
 drivers/usb/core/sysfs.c                | 13 ++++---------
 drivers/usb/core/usb.c                  |  4 +---
 drivers/usb/core/usb.h                  | 23 +++++++++--------------
 drivers/usb/host/ehci-pci.c             |  2 +-
 drivers/usb/host/sl811-hcd.c            |  5 ++---
 drivers/usb/host/u132-hcd.c             |  3 +--
 drivers/usb/host/xhci-hub.c             |  2 +-
 drivers/usb/host/xhci.c                 | 29 ++++++++++++-----------------
 drivers/usb/phy/phy-msm-usb.c           |  2 +-
 include/linux/usb.h                     |  2 +-
 include/linux/usb/hcd.h                 |  7 ++-----
 19 files changed, 69 insertions(+), 112 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/stable/sysfs-bus-usb b/Documentation/ABI/stable/sysfs-bus-usb
index e2bc700a6f9..831f15d9672 100644
--- a/Documentation/ABI/stable/sysfs-bus-usb
+++ b/Documentation/ABI/stable/sysfs-bus-usb
@@ -32,10 +32,9 @@ Date:		January 2008
 KernelVersion:	2.6.25
 Contact:	Sarah Sharp <sarah.a.sharp@intel.com>
 Description:
-		If CONFIG_PM_RUNTIME is enabled then this file
-		is present.  When read, it returns the total time (in msec)
-		that the USB device has been connected to the machine.  This
-		file is read-only.
+		If CONFIG_PM is enabled, then this file is present.  When read,
+		it returns the total time (in msec) that the USB device has been
+		connected to the machine.  This file is read-only.
 Users:
 		PowerTOP <powertop@lists.01.org>
 		https://01.org/powertop/
@@ -45,10 +44,9 @@ Date:		January 2008
 KernelVersion:	2.6.25
 Contact:	Sarah Sharp <sarah.a.sharp@intel.com>
 Description:
-		If CONFIG_PM_RUNTIME is enabled then this file
-		is present.  When read, it returns the total time (in msec)
-		that the USB device has been active, i.e. not in a suspended
-		state.  This file is read-only.
+		If CONFIG_PM is enabled, then this file is present.  When read,
+		it returns the total time (in msec) that the USB device has been
+		active, i.e. not in a suspended state.  This file is read-only.
 
 		Tools can use this file and the connected_duration file to
 		compute the percentage of time that a device has been active.
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb
index 614d451cee4..e5cc7633d01 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb
+++ b/Documentation/ABI/testing/sysfs-bus-usb
@@ -104,16 +104,15 @@ What:		/sys/bus/usb/devices/.../power/usb2_hardware_lpm
 Date:		September 2011
 Contact:	Andiry Xu <andiry.xu@amd.com>
 Description:
-		If CONFIG_PM_RUNTIME is set and a USB 2.0 lpm-capable device
-		is plugged in to a xHCI host which support link PM, it will
-		perform a LPM test; if the test is passed and host supports
-		USB2 hardware LPM (xHCI 1.0 feature), USB2 hardware LPM will
-		be enabled for the device and the USB device directory will
-		contain a file named power/usb2_hardware_lpm.  The file holds
-		a string value (enable or disable) indicating whether or not
-		USB2 hardware LPM is enabled for the device. Developer can
-		write y/Y/1 or n/N/0 to the file to enable/disable the
-		feature.
+		If CONFIG_PM is set and a USB 2.0 lpm-capable device is plugged
+		in to a xHCI host which support link PM, it will perform a LPM
+		test; if the test is passed and host supports USB2 hardware LPM
+		(xHCI 1.0 feature), USB2 hardware LPM will be enabled for the
+		device and the USB device directory will contain a file named
+		power/usb2_hardware_lpm.  The file holds a string value (enable
+		or disable) indicating whether or not USB2 hardware LPM is
+		enabled for the device. Developer can write y/Y/1 or n/N/0 to
+		the file to enable/disable the feature.
 
 What:		/sys/bus/usb/devices/.../removable
 Date:		February 2012
diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt
index 7b90fe034c4..b5f83911732 100644
--- a/Documentation/usb/power-management.txt
+++ b/Documentation/usb/power-management.txt
@@ -47,14 +47,15 @@ dynamic PM is implemented in the USB subsystem, although system PM is
 covered to some extent (see Documentation/power/*.txt for more
 information about system PM).
 
-Note: Dynamic PM support for USB is present only if the kernel was
-built with CONFIG_USB_SUSPEND enabled (which depends on
-CONFIG_PM_RUNTIME).  System PM support is present only if the kernel
-was built with CONFIG_SUSPEND or CONFIG_HIBERNATION enabled.
-
-(Starting with the 3.10 kernel release, dynamic PM support for USB is
-present whenever the kernel was built with CONFIG_PM_RUNTIME enabled.
-The CONFIG_USB_SUSPEND option has been eliminated.)
+System PM support is present only if the kernel was built with CONFIG_SUSPEND
+or CONFIG_HIBERNATION enabled.  Dynamic PM support for USB is present whenever
+the kernel was built with CONFIG_PM enabled.
+
+[Historically, dynamic PM support for USB was present only if the
+kernel had been built with CONFIG_USB_SUSPEND enabled (which depended on
+CONFIG_PM_RUNTIME).  Starting with the 3.10 kernel release, dynamic PM support
+for USB was present whenever the kernel was built with CONFIG_PM_RUNTIME
+enabled.  The CONFIG_USB_SUSPEND option had been eliminated.]
 
 
 	What is Remote Wakeup?
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 9bffd26cea0..874dec31a11 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -1493,10 +1493,6 @@ int usb_resume(struct device *dev, pm_message_t msg)
 	return status;
 }
 
-#endif /* CONFIG_PM */
-
-#ifdef CONFIG_PM_RUNTIME
-
 /**
  * usb_enable_autosuspend - allow a USB device to be autosuspended
  * @udev: the USB device which may be autosuspended
@@ -1876,7 +1872,7 @@ int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable)
 	return ret;
 }
 
-#endif /* CONFIG_PM_RUNTIME */
+#endif /* CONFIG_PM */
 
 struct bus_type usb_bus_type = {
 	.name =		"usb",
diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c
index efc953119ce..9eb1cff28bd 100644
--- a/drivers/usb/core/hcd-pci.c
+++ b/drivers/usb/core/hcd-pci.c
@@ -429,7 +429,6 @@ static int check_root_hub_suspended(struct device *dev)
 	return 0;
 }
 
-#if defined(CONFIG_PM_SLEEP) || defined(CONFIG_PM_RUNTIME)
 static int suspend_common(struct device *dev, bool do_wakeup)
 {
 	struct pci_dev		*pci_dev = to_pci_dev(dev);
@@ -528,7 +527,6 @@ static int resume_common(struct device *dev, int event)
 	}
 	return retval;
 }
-#endif	/* SLEEP || RUNTIME */
 
 #ifdef	CONFIG_PM_SLEEP
 
@@ -607,8 +605,6 @@ static int hcd_pci_restore(struct device *dev)
 
 #endif	/* CONFIG_PM_SLEEP */
 
-#ifdef	CONFIG_PM_RUNTIME
-
 static int hcd_pci_runtime_suspend(struct device *dev)
 {
 	int	retval;
@@ -630,13 +626,6 @@ static int hcd_pci_runtime_resume(struct device *dev)
 	return retval;
 }
 
-#else
-
-#define hcd_pci_runtime_suspend	NULL
-#define hcd_pci_runtime_resume	NULL
-
-#endif	/* CONFIG_PM_RUNTIME */
-
 const struct dev_pm_ops usb_hcd_pci_pm_ops = {
 	.suspend	= hcd_pci_suspend,
 	.suspend_noirq	= hcd_pci_suspend_noirq,
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index a6efb4184f2..278be0515e8 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2258,10 +2258,6 @@ int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg)
 	return status;
 }
 
-#endif	/* CONFIG_PM */
-
-#ifdef	CONFIG_PM_RUNTIME
-
 /* Workqueue routine for root-hub remote wakeup */
 static void hcd_resume_work(struct work_struct *work)
 {
@@ -2293,7 +2289,7 @@ void usb_hcd_resume_root_hub (struct usb_hcd *hcd)
 }
 EXPORT_SYMBOL_GPL(usb_hcd_resume_root_hub);
 
-#endif	/* CONFIG_PM_RUNTIME */
+#endif	/* CONFIG_PM */
 
 /*-------------------------------------------------------------------------*/
 
@@ -2476,7 +2472,7 @@ struct usb_hcd *usb_create_shared_hcd(const struct hc_driver *driver,
 	init_timer(&hcd->rh_timer);
 	hcd->rh_timer.function = rh_timer_func;
 	hcd->rh_timer.data = (unsigned long) hcd;
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 	INIT_WORK(&hcd->wakeup_work, hcd_resume_work);
 #endif
 
@@ -2790,7 +2786,7 @@ error_create_attr_group:
 	hcd->rh_registered = 0;
 	spin_unlock_irq(&hcd_root_hub_lock);
 
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 	cancel_work_sync(&hcd->wakeup_work);
 #endif
 	mutex_lock(&usb_bus_list_lock);
@@ -2858,7 +2854,7 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 	hcd->rh_registered = 0;
 	spin_unlock_irq (&hcd_root_hub_lock);
 
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 	cancel_work_sync(&hcd->wakeup_work);
 #endif
 
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index b649fef2e35..c9596525ba8 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1737,7 +1737,7 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	 * - If user has indicated to prevent autosuspend by passing
 	 *   usbcore.autosuspend = -1 then keep autosuspend disabled.
 	 */
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 	if (hdev->dev.power.autosuspend_delay >= 0)
 		pm_runtime_set_autosuspend_delay(&hdev->dev, 0);
 #endif
@@ -3449,7 +3449,7 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg)
 	return status;
 }
 
-#ifdef	CONFIG_PM_RUNTIME
+#ifdef	CONFIG_PM
 
 int usb_remote_wakeup(struct usb_device *udev)
 {
@@ -4856,7 +4856,7 @@ static void hub_port_connect_change(struct usb_hub *hub, int port1,
 			udev->state != USB_STATE_NOTATTACHED) {
 		if (portstatus & USB_PORT_STAT_ENABLE) {
 			status = 0;		/* Nothing to do */
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 		} else if (udev->state == USB_STATE_SUSPENDED &&
 				udev->persist_enabled) {
 			/* For a suspended device, treat this as a
diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c
index cd3f9dc24a0..210618319f1 100644
--- a/drivers/usb/core/port.c
+++ b/drivers/usb/core/port.c
@@ -72,7 +72,7 @@ static void usb_port_device_release(struct device *dev)
 	kfree(port_dev);
 }
 
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 static int usb_port_runtime_resume(struct device *dev)
 {
 	struct usb_port *port_dev = to_usb_port(dev);
@@ -171,7 +171,7 @@ static int usb_port_runtime_suspend(struct device *dev)
 #endif
 
 static const struct dev_pm_ops usb_port_pm_ops = {
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 	.runtime_suspend =	usb_port_runtime_suspend,
 	.runtime_resume =	usb_port_runtime_resume,
 #endif
diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c
index 1236c6011c7..d26973844a4 100644
--- a/drivers/usb/core/sysfs.c
+++ b/drivers/usb/core/sysfs.c
@@ -334,14 +334,6 @@ static void remove_persist_attributes(struct device *dev)
 			&dev_attr_persist.attr,
 			power_group_name);
 }
-#else
-
-#define add_persist_attributes(dev)	0
-#define remove_persist_attributes(dev)	do {} while (0)
-
-#endif	/* CONFIG_PM */
-
-#ifdef	CONFIG_PM_RUNTIME
 
 static ssize_t connected_duration_show(struct device *dev,
 				       struct device_attribute *attr, char *buf)
@@ -585,10 +577,13 @@ static void remove_power_attributes(struct device *dev)
 
 #else
 
+#define add_persist_attributes(dev)	0
+#define remove_persist_attributes(dev)	do {} while (0)
+
 #define add_power_attributes(dev)	0
 #define remove_power_attributes(dev)	do {} while (0)
 
-#endif	/* CONFIG_PM_RUNTIME */
+#endif	/* CONFIG_PM */
 
 
 /* Descriptor fields */
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index 2dd2362198d..2a92b97f014 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -49,7 +49,7 @@ const char *usbcore_name = "usbcore";
 
 static bool nousb;	/* Disable USB when built into kernel image */
 
-#ifdef	CONFIG_PM_RUNTIME
+#ifdef	CONFIG_PM
 static int usb_autosuspend_delay = 2;		/* Default delay value,
 						 * in seconds */
 module_param_named(autosuspend, usb_autosuspend_delay, int, 0644);
@@ -348,11 +348,9 @@ static const struct dev_pm_ops usb_device_pm_ops = {
 	.thaw =		usb_dev_thaw,
 	.poweroff =	usb_dev_poweroff,
 	.restore =	usb_dev_restore,
-#ifdef CONFIG_PM_RUNTIME
 	.runtime_suspend =	usb_runtime_suspend,
 	.runtime_resume =	usb_runtime_resume,
 	.runtime_idle =		usb_runtime_idle,
-#endif
 };
 
 #endif	/* CONFIG_PM */
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index b1b34d0557c..7eb1e26798e 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -75,6 +75,14 @@ extern int usb_resume_complete(struct device *dev);
 extern int usb_port_suspend(struct usb_device *dev, pm_message_t msg);
 extern int usb_port_resume(struct usb_device *dev, pm_message_t msg);
 
+extern void usb_autosuspend_device(struct usb_device *udev);
+extern int usb_autoresume_device(struct usb_device *udev);
+extern int usb_remote_wakeup(struct usb_device *dev);
+extern int usb_runtime_suspend(struct device *dev);
+extern int usb_runtime_resume(struct device *dev);
+extern int usb_runtime_idle(struct device *dev);
+extern int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable);
+
 #else
 
 static inline int usb_port_suspend(struct usb_device *udev, pm_message_t msg)
@@ -87,20 +95,6 @@ static inline int usb_port_resume(struct usb_device *udev, pm_message_t msg)
 	return 0;
 }
 
-#endif
-
-#ifdef CONFIG_PM_RUNTIME
-
-extern void usb_autosuspend_device(struct usb_device *udev);
-extern int usb_autoresume_device(struct usb_device *udev);
-extern int usb_remote_wakeup(struct usb_device *dev);
-extern int usb_runtime_suspend(struct device *dev);
-extern int usb_runtime_resume(struct device *dev);
-extern int usb_runtime_idle(struct device *dev);
-extern int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable);
-
-#else
-
 #define usb_autosuspend_device(udev)		do {} while (0)
 static inline int usb_autoresume_device(struct usb_device *udev)
 {
@@ -111,6 +105,7 @@ static inline int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable)
 {
 	return 0;
 }
+
 #endif
 
 extern struct bus_type usb_bus_type;
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index ca7b964124a..851006a0d97 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -305,7 +305,7 @@ static int ehci_pci_setup(struct usb_hcd *hcd)
 		}
 	}
 
-#ifdef	CONFIG_PM_RUNTIME
+#ifdef	CONFIG_PM
 	if (ehci->no_selective_suspend && device_can_wakeup(&pdev->dev))
 		ehci_warn(ehci, "selective suspend/wakeup unavailable\n");
 #endif
diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c
index ad0c348e68e..25fb1da8d3d 100644
--- a/drivers/usb/host/sl811-hcd.c
+++ b/drivers/usb/host/sl811-hcd.c
@@ -22,7 +22,7 @@
  * and usb-storage.
  *
  * TODO:
- * - usb suspend/resume triggered by sl811 (with PM_RUNTIME)
+ * - usb suspend/resume triggered by sl811
  * - various issues noted in the code
  * - performance work; use both register banks; ...
  * - use urb->iso_frame_desc[] with ISO transfers
@@ -1752,8 +1752,7 @@ sl811h_probe(struct platform_device *dev)
 #ifdef	CONFIG_PM
 
 /* for this device there's no useful distinction between the controller
- * and its root hub, except that the root hub only gets direct PM calls
- * when CONFIG_PM_RUNTIME is enabled.
+ * and its root hub.
  */
 
 static int
diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c
index c0671750671..bf86630b3ce 100644
--- a/drivers/usb/host/u132-hcd.c
+++ b/drivers/usb/host/u132-hcd.c
@@ -3144,8 +3144,7 @@ static int u132_probe(struct platform_device *pdev)
 #ifdef CONFIG_PM
 /*
  * for this device there's no useful distinction between the controller
- * and its root hub, except that the root hub only gets direct PM calls
- * when CONFIG_PM_RUNTIME is enabled.
+ * and its root hub.
  */
 static int u132_suspend(struct platform_device *pdev, pm_message_t state)
 {
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 696160d48ae..f674abd7686 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -1146,7 +1146,7 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
 			set_bit(port_index, &bus_state->bus_suspended);
 		}
 		/* USB core sets remote wake mask for USB 3.0 hubs,
-		 * including the USB 3.0 roothub, but only if CONFIG_PM_RUNTIME
+		 * including the USB 3.0 roothub, but only if CONFIG_PM
 		 * is enabled, so also enable remote wake here.
 		 */
 		if (hcd->self.root_hub->do_remote_wakeup
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 2a5d45b4cb1..61173ca9cb8 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -4024,7 +4024,7 @@ static int __maybe_unused xhci_change_max_exit_latency(struct xhci_hcd *xhci,
 	return ret;
 }
 
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 
 /* BESL to HIRD Encoding array for USB2 LPM */
 static int xhci_besl_encoding[16] = {125, 150, 200, 300, 400, 500, 1000, 2000,
@@ -4239,24 +4239,8 @@ int xhci_update_device(struct usb_hcd *hcd, struct usb_device *udev)
 	return 0;
 }
 
-#else
-
-int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd,
-				struct usb_device *udev, int enable)
-{
-	return 0;
-}
-
-int xhci_update_device(struct usb_hcd *hcd, struct usb_device *udev)
-{
-	return 0;
-}
-
-#endif /* CONFIG_PM_RUNTIME */
-
 /*---------------------- USB 3.0 Link PM functions ------------------------*/
 
-#ifdef CONFIG_PM
 /* Service interval in nanoseconds = 2^(bInterval - 1) * 125us * 1000ns / 1us */
 static unsigned long long xhci_service_interval_to_ns(
 		struct usb_endpoint_descriptor *desc)
@@ -4687,6 +4671,17 @@ int xhci_disable_usb3_lpm_timeout(struct usb_hcd *hcd,
 }
 #else /* CONFIG_PM */
 
+int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd,
+				struct usb_device *udev, int enable)
+{
+	return 0;
+}
+
+int xhci_update_device(struct usb_hcd *hcd, struct usb_device *udev)
+{
+	return 0;
+}
+
 int xhci_enable_usb3_lpm_timeout(struct usb_hcd *hcd,
 			struct usb_device *udev, enum usb3_link_state state)
 {
diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c
index 7843ef7dd0f..29be0e654ec 100644
--- a/drivers/usb/phy/phy-msm-usb.c
+++ b/drivers/usb/phy/phy-msm-usb.c
@@ -1761,7 +1761,7 @@ static int msm_otg_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 static int msm_otg_runtime_idle(struct device *dev)
 {
 	struct msm_otg *motg = dev_get_drvdata(dev);
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 447a7e2fc19..f89c24a03bd 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -637,7 +637,7 @@ static inline bool usb_acpi_power_manageable(struct usb_device *hdev, int index)
 #endif
 
 /* USB autosuspend and autoresume */
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 extern void usb_enable_autosuspend(struct usb_device *udev);
 extern void usb_disable_autosuspend(struct usb_device *udev);
 
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index cd96a2bc338..668898e29d0 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -93,7 +93,7 @@ struct usb_hcd {
 
 	struct timer_list	rh_timer;	/* drives root-hub polling */
 	struct urb		*status_urb;	/* the current status urb */
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 	struct work_struct	wakeup_work;	/* for remote wakeup */
 #endif
 
@@ -625,16 +625,13 @@ extern int usb_find_interface_driver(struct usb_device *dev,
 extern void usb_root_hub_lost_power(struct usb_device *rhdev);
 extern int hcd_bus_suspend(struct usb_device *rhdev, pm_message_t msg);
 extern int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg);
-#endif /* CONFIG_PM */
-
-#ifdef CONFIG_PM_RUNTIME
 extern void usb_hcd_resume_root_hub(struct usb_hcd *hcd);
 #else
 static inline void usb_hcd_resume_root_hub(struct usb_hcd *hcd)
 {
 	return;
 }
-#endif /* CONFIG_PM_RUNTIME */
+#endif /* CONFIG_PM */
 
 /*-------------------------------------------------------------------------*/
 
-- 
cgit v1.2.3-70-g09d2


From 47fafbc701fecf112cfa580f61db229b9f68aba4 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 4 Dec 2014 01:00:23 +0100
Subject: block / PM: Replace CONFIG_PM_RUNTIME with CONFIG_PM

After commit b2b49ccbdd54 (PM: Kconfig: Set PM_RUNTIME if PM_SLEEP is
selected) PM_RUNTIME is always set if PM is set, so #ifdef blocks
depending on CONFIG_PM_RUNTIME may now be changed to depend on
CONFIG_PM.

Replace CONFIG_PM_RUNTIME with CONFIG_PM in the block device core.

Reviewed-by: Aaron Lu <aaron.lu@intel.com>
Acked-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 block/blk-core.c       | 6 +++---
 block/elevator.c       | 2 +-
 include/linux/blkdev.h | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 0421b53e643..2bb7d9c0f63 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1325,7 +1325,7 @@ void part_round_stats(int cpu, struct hd_struct *part)
 }
 EXPORT_SYMBOL_GPL(part_round_stats);
 
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 static void blk_pm_put_request(struct request *rq)
 {
 	if (rq->q->dev && !(rq->cmd_flags & REQ_PM) && !--rq->q->nr_pending)
@@ -2134,7 +2134,7 @@ void blk_account_io_done(struct request *req)
 	}
 }
 
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 /*
  * Don't process normal requests when queue is suspended
  * or in the process of suspending/resuming
@@ -3159,7 +3159,7 @@ void blk_finish_plug(struct blk_plug *plug)
 }
 EXPORT_SYMBOL(blk_finish_plug);
 
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 /**
  * blk_pm_runtime_init - Block layer runtime PM initialization routine
  * @q: the queue of the device
diff --git a/block/elevator.c b/block/elevator.c
index afa3b037a17..59794d0d38e 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -539,7 +539,7 @@ void elv_bio_merged(struct request_queue *q, struct request *rq,
 		e->type->ops.elevator_bio_merged_fn(q, rq, bio);
 }
 
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 static void blk_pm_requeue_request(struct request *rq)
 {
 	if (rq->q->dev && !(rq->cmd_flags & REQ_PM))
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index aac0f9ea952..534dc402c54 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -398,7 +398,7 @@ struct request_queue {
 	 */
 	struct kobject mq_kobj;
 
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 	struct device		*dev;
 	int			rpm_status;
 	unsigned int		nr_pending;
@@ -1057,7 +1057,7 @@ extern void blk_put_queue(struct request_queue *);
 /*
  * block layer runtime pm functions
  */
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev);
 extern int blk_pre_runtime_suspend(struct request_queue *q);
 extern void blk_post_runtime_suspend(struct request_queue *q, int err);
-- 
cgit v1.2.3-70-g09d2


From 646cafc6aa4d6004d189de1cdc267ab562069ba9 Mon Sep 17 00:00:00 2001
From: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Date: Tue, 2 Dec 2014 08:54:22 +0100
Subject: clk: Change clk_ops->determine_rate to return a clk_hw as the best
 parent

This is in preparation for clock providers to not have to deal with struct clk.

Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Michael Turquette <mturquette@linaro.org>
---
 Documentation/clk.txt               |  2 +-
 arch/mips/alchemy/common/clock.c    | 10 +++++-----
 drivers/clk/at91/clk-programmable.c |  4 ++--
 drivers/clk/bcm/clk-kona.c          |  4 ++--
 drivers/clk/clk-composite.c         |  9 +++++----
 drivers/clk/clk.c                   | 17 +++++++++++------
 drivers/clk/hisilicon/clk-hi3620.c  |  2 +-
 drivers/clk/mmp/clk-mix.c           |  4 ++--
 drivers/clk/qcom/clk-pll.c          |  2 +-
 drivers/clk/qcom/clk-rcg.c          | 20 ++++++++++++--------
 drivers/clk/qcom/clk-rcg2.c         | 28 +++++++++++++++++-----------
 drivers/clk/sunxi/clk-factors.c     |  4 ++--
 drivers/clk/sunxi/clk-sun6i-ar100.c |  4 ++--
 include/linux/clk-provider.h        |  4 ++--
 14 files changed, 65 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/Documentation/clk.txt b/Documentation/clk.txt
index 1fee72f4d33..4ff84623d5e 100644
--- a/Documentation/clk.txt
+++ b/Documentation/clk.txt
@@ -74,7 +74,7 @@ the operations defined in clk.h:
 		long		(*determine_rate)(struct clk_hw *hw,
 						unsigned long rate,
 						unsigned long *best_parent_rate,
-						struct clk **best_parent_clk);
+						struct clk_hw **best_parent_clk);
 		int		(*set_parent)(struct clk_hw *hw, u8 index);
 		u8		(*get_parent)(struct clk_hw *hw);
 		int		(*set_rate)(struct clk_hw *hw,
diff --git a/arch/mips/alchemy/common/clock.c b/arch/mips/alchemy/common/clock.c
index d7557cde271..f42dd0a4af2 100644
--- a/arch/mips/alchemy/common/clock.c
+++ b/arch/mips/alchemy/common/clock.c
@@ -375,7 +375,7 @@ static long alchemy_calc_div(unsigned long rate, unsigned long prate,
 
 static long alchemy_clk_fgcs_detr(struct clk_hw *hw, unsigned long rate,
 					unsigned long *best_parent_rate,
-					struct clk **best_parent_clk,
+					struct clk_hw **best_parent_clk,
 					int scale, int maxdiv)
 {
 	struct clk *pc, *bpc, *free;
@@ -454,7 +454,7 @@ static long alchemy_clk_fgcs_detr(struct clk_hw *hw, unsigned long rate,
 	}
 
 	*best_parent_rate = bpr;
-	*best_parent_clk = bpc;
+	*best_parent_clk = __clk_get_hw(bpc);
 	return br;
 }
 
@@ -548,7 +548,7 @@ static unsigned long alchemy_clk_fgv1_recalc(struct clk_hw *hw,
 
 static long alchemy_clk_fgv1_detr(struct clk_hw *hw, unsigned long rate,
 					unsigned long *best_parent_rate,
-					struct clk **best_parent_clk)
+					struct clk_hw **best_parent_clk)
 {
 	return alchemy_clk_fgcs_detr(hw, rate, best_parent_rate,
 				     best_parent_clk, 2, 512);
@@ -680,7 +680,7 @@ static unsigned long alchemy_clk_fgv2_recalc(struct clk_hw *hw,
 
 static long alchemy_clk_fgv2_detr(struct clk_hw *hw, unsigned long rate,
 					unsigned long *best_parent_rate,
-					struct clk **best_parent_clk)
+					struct clk_hw **best_parent_clk)
 {
 	struct alchemy_fgcs_clk *c = to_fgcs_clk(hw);
 	int scale, maxdiv;
@@ -899,7 +899,7 @@ static int alchemy_clk_csrc_setr(struct clk_hw *hw, unsigned long rate,
 
 static long alchemy_clk_csrc_detr(struct clk_hw *hw, unsigned long rate,
 					unsigned long *best_parent_rate,
-					struct clk **best_parent_clk)
+					struct clk_hw **best_parent_clk)
 {
 	struct alchemy_fgcs_clk *c = to_fgcs_clk(hw);
 	int scale = c->dt[2] == 3 ? 1 : 2; /* au1300 check */
diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c
index 62e2509f9df..bbdb1b985c9 100644
--- a/drivers/clk/at91/clk-programmable.c
+++ b/drivers/clk/at91/clk-programmable.c
@@ -57,7 +57,7 @@ static unsigned long clk_programmable_recalc_rate(struct clk_hw *hw,
 static long clk_programmable_determine_rate(struct clk_hw *hw,
 					    unsigned long rate,
 					    unsigned long *best_parent_rate,
-					    struct clk **best_parent_clk)
+					    struct clk_hw **best_parent_hw)
 {
 	struct clk *parent = NULL;
 	long best_rate = -EINVAL;
@@ -84,7 +84,7 @@ static long clk_programmable_determine_rate(struct clk_hw *hw,
 		if (best_rate < 0 || (rate - tmp_rate) < (rate - best_rate)) {
 			best_rate = tmp_rate;
 			*best_parent_rate = parent_rate;
-			*best_parent_clk = parent;
+			*best_parent_hw = __clk_get_hw(parent);
 		}
 
 		if (!best_rate)
diff --git a/drivers/clk/bcm/clk-kona.c b/drivers/clk/bcm/clk-kona.c
index 95af2e665dd..1c06f6f3a8c 100644
--- a/drivers/clk/bcm/clk-kona.c
+++ b/drivers/clk/bcm/clk-kona.c
@@ -1032,7 +1032,7 @@ static long kona_peri_clk_round_rate(struct clk_hw *hw, unsigned long rate,
 }
 
 static long kona_peri_clk_determine_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long *best_parent_rate, struct clk **best_parent)
+		unsigned long *best_parent_rate, struct clk_hw **best_parent)
 {
 	struct kona_clk *bcm_clk = to_kona_clk(hw);
 	struct clk *clk = hw->clk;
@@ -1075,7 +1075,7 @@ static long kona_peri_clk_determine_rate(struct clk_hw *hw, unsigned long rate,
 		if (delta < best_delta) {
 			best_delta = delta;
 			best_rate = other_rate;
-			*best_parent = parent;
+			*best_parent = __clk_get_hw(parent);
 			*best_parent_rate = parent_rate;
 		}
 	}
diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c
index b9355daf806..4386697236a 100644
--- a/drivers/clk/clk-composite.c
+++ b/drivers/clk/clk-composite.c
@@ -57,7 +57,7 @@ static unsigned long clk_composite_recalc_rate(struct clk_hw *hw,
 
 static long clk_composite_determine_rate(struct clk_hw *hw, unsigned long rate,
 					unsigned long *best_parent_rate,
-					struct clk **best_parent_p)
+					struct clk_hw **best_parent_p)
 {
 	struct clk_composite *composite = to_clk_composite(hw);
 	const struct clk_ops *rate_ops = composite->rate_ops;
@@ -80,8 +80,9 @@ static long clk_composite_determine_rate(struct clk_hw *hw, unsigned long rate,
 		*best_parent_p = NULL;
 
 		if (__clk_get_flags(hw->clk) & CLK_SET_RATE_NO_REPARENT) {
-			*best_parent_p = clk_get_parent(mux_hw->clk);
-			*best_parent_rate = __clk_get_rate(*best_parent_p);
+			parent = clk_get_parent(mux_hw->clk);
+			*best_parent_p = __clk_get_hw(parent);
+			*best_parent_rate = __clk_get_rate(parent);
 
 			return rate_ops->round_rate(rate_hw, rate,
 						    best_parent_rate);
@@ -103,7 +104,7 @@ static long clk_composite_determine_rate(struct clk_hw *hw, unsigned long rate,
 
 			if (!rate_diff || !*best_parent_p
 				       || best_rate_diff > rate_diff) {
-				*best_parent_p = parent;
+				*best_parent_p = __clk_get_hw(parent);
 				*best_parent_rate = parent_rate;
 				best_rate_diff = rate_diff;
 				best_rate = tmp_rate;
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index f549e8b1d5e..44cdc47a6cc 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -702,7 +702,7 @@ struct clk *__clk_lookup(const char *name)
  */
 long __clk_mux_determine_rate(struct clk_hw *hw, unsigned long rate,
 			      unsigned long *best_parent_rate,
-			      struct clk **best_parent_p)
+			      struct clk_hw **best_parent_p)
 {
 	struct clk *clk = hw->clk, *parent, *best_parent = NULL;
 	int i, num_parents;
@@ -738,7 +738,7 @@ long __clk_mux_determine_rate(struct clk_hw *hw, unsigned long rate,
 
 out:
 	if (best_parent)
-		*best_parent_p = best_parent;
+		*best_parent_p = best_parent->hw;
 	*best_parent_rate = best;
 
 	return best;
@@ -946,6 +946,7 @@ unsigned long __clk_round_rate(struct clk *clk, unsigned long rate)
 {
 	unsigned long parent_rate = 0;
 	struct clk *parent;
+	struct clk_hw *parent_hw;
 
 	if (!clk)
 		return 0;
@@ -954,10 +955,11 @@ unsigned long __clk_round_rate(struct clk *clk, unsigned long rate)
 	if (parent)
 		parent_rate = parent->rate;
 
-	if (clk->ops->determine_rate)
+	if (clk->ops->determine_rate) {
+		parent_hw = parent ? parent->hw : NULL;
 		return clk->ops->determine_rate(clk->hw, rate, &parent_rate,
-						&parent);
-	else if (clk->ops->round_rate)
+						&parent_hw);
+	} else if (clk->ops->round_rate)
 		return clk->ops->round_rate(clk->hw, rate, &parent_rate);
 	else if (clk->flags & CLK_SET_RATE_PARENT)
 		return __clk_round_rate(clk->parent, rate);
@@ -1345,6 +1347,7 @@ static struct clk *clk_calc_new_rates(struct clk *clk, unsigned long rate)
 {
 	struct clk *top = clk;
 	struct clk *old_parent, *parent;
+	struct clk_hw *parent_hw;
 	unsigned long best_parent_rate = 0;
 	unsigned long new_rate;
 	int p_index = 0;
@@ -1360,9 +1363,11 @@ static struct clk *clk_calc_new_rates(struct clk *clk, unsigned long rate)
 
 	/* find the closest rate and parent clk/rate */
 	if (clk->ops->determine_rate) {
+		parent_hw = parent ? parent->hw : NULL;
 		new_rate = clk->ops->determine_rate(clk->hw, rate,
 						    &best_parent_rate,
-						    &parent);
+						    &parent_hw);
+		parent = parent_hw->clk;
 	} else if (clk->ops->round_rate) {
 		new_rate = clk->ops->round_rate(clk->hw, rate,
 						&best_parent_rate);
diff --git a/drivers/clk/hisilicon/clk-hi3620.c b/drivers/clk/hisilicon/clk-hi3620.c
index 640ea3327c3..007144f81f5 100644
--- a/drivers/clk/hisilicon/clk-hi3620.c
+++ b/drivers/clk/hisilicon/clk-hi3620.c
@@ -296,7 +296,7 @@ static unsigned long mmc_clk_recalc_rate(struct clk_hw *hw,
 
 static long mmc_clk_determine_rate(struct clk_hw *hw, unsigned long rate,
 			      unsigned long *best_parent_rate,
-			      struct clk **best_parent_p)
+			      struct clk_hw **best_parent_p)
 {
 	struct clk_mmc *mclk = to_mmc(hw);
 	unsigned long best = 0;
diff --git a/drivers/clk/mmp/clk-mix.c b/drivers/clk/mmp/clk-mix.c
index b79742c47d5..48fa53c7ce5 100644
--- a/drivers/clk/mmp/clk-mix.c
+++ b/drivers/clk/mmp/clk-mix.c
@@ -203,7 +203,7 @@ error:
 
 static long mmp_clk_mix_determine_rate(struct clk_hw *hw, unsigned long rate,
 					unsigned long *best_parent_rate,
-					struct clk **best_parent_clk)
+					struct clk_hw **best_parent_clk)
 {
 	struct mmp_clk_mix *mix = to_clk_mix(hw);
 	struct mmp_clk_mix_clk_table *item;
@@ -264,7 +264,7 @@ static long mmp_clk_mix_determine_rate(struct clk_hw *hw, unsigned long rate,
 
 found:
 	*best_parent_rate = parent_rate_best;
-	*best_parent_clk = parent_best;
+	*best_parent_clk = __clk_get_hw(parent_best);
 
 	return mix_rate_best;
 }
diff --git a/drivers/clk/qcom/clk-pll.c b/drivers/clk/qcom/clk-pll.c
index b823bc3b625..60873a7f45d 100644
--- a/drivers/clk/qcom/clk-pll.c
+++ b/drivers/clk/qcom/clk-pll.c
@@ -141,7 +141,7 @@ struct pll_freq_tbl *find_freq(const struct pll_freq_tbl *f, unsigned long rate)
 
 static long
 clk_pll_determine_rate(struct clk_hw *hw, unsigned long rate,
-		       unsigned long *p_rate, struct clk **p)
+		       unsigned long *p_rate, struct clk_hw **p)
 {
 	struct clk_pll *pll = to_clk_pll(hw);
 	const struct pll_freq_tbl *f;
diff --git a/drivers/clk/qcom/clk-rcg.c b/drivers/clk/qcom/clk-rcg.c
index b6e6959e89a..0b93972c880 100644
--- a/drivers/clk/qcom/clk-rcg.c
+++ b/drivers/clk/qcom/clk-rcg.c
@@ -368,16 +368,17 @@ clk_dyn_rcg_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 
 static long _freq_tbl_determine_rate(struct clk_hw *hw,
 		const struct freq_tbl *f, unsigned long rate,
-		unsigned long *p_rate, struct clk **p)
+		unsigned long *p_rate, struct clk_hw **p_hw)
 {
 	unsigned long clk_flags;
+	struct clk *p;
 
 	f = qcom_find_freq(f, rate);
 	if (!f)
 		return -EINVAL;
 
 	clk_flags = __clk_get_flags(hw->clk);
-	*p = clk_get_parent_by_index(hw->clk, f->src);
+	p = clk_get_parent_by_index(hw->clk, f->src);
 	if (clk_flags & CLK_SET_RATE_PARENT) {
 		rate = rate * f->pre_div;
 		if (f->n) {
@@ -387,15 +388,16 @@ static long _freq_tbl_determine_rate(struct clk_hw *hw,
 			rate = tmp;
 		}
 	} else {
-		rate =  __clk_get_rate(*p);
+		rate =  __clk_get_rate(p);
 	}
+	*p_hw = __clk_get_hw(p);
 	*p_rate = rate;
 
 	return f->freq;
 }
 
 static long clk_rcg_determine_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long *p_rate, struct clk **p)
+		unsigned long *p_rate, struct clk_hw **p)
 {
 	struct clk_rcg *rcg = to_clk_rcg(hw);
 
@@ -403,7 +405,7 @@ static long clk_rcg_determine_rate(struct clk_hw *hw, unsigned long rate,
 }
 
 static long clk_dyn_rcg_determine_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long *p_rate, struct clk **p)
+		unsigned long *p_rate, struct clk_hw **p)
 {
 	struct clk_dyn_rcg *rcg = to_clk_dyn_rcg(hw);
 
@@ -411,13 +413,15 @@ static long clk_dyn_rcg_determine_rate(struct clk_hw *hw, unsigned long rate,
 }
 
 static long clk_rcg_bypass_determine_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long *p_rate, struct clk **p)
+		unsigned long *p_rate, struct clk_hw **p_hw)
 {
 	struct clk_rcg *rcg = to_clk_rcg(hw);
 	const struct freq_tbl *f = rcg->freq_tbl;
+	struct clk *p;
 
-	*p = clk_get_parent_by_index(hw->clk, f->src);
-	*p_rate = __clk_round_rate(*p, rate);
+	p = clk_get_parent_by_index(hw->clk, f->src);
+	*p_hw = __clk_get_hw(p);
+	*p_rate = __clk_round_rate(p, rate);
 
 	return *p_rate;
 }
diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
index cfa9eb4fe9c..08b8b3729f5 100644
--- a/drivers/clk/qcom/clk-rcg2.c
+++ b/drivers/clk/qcom/clk-rcg2.c
@@ -175,16 +175,17 @@ clk_rcg2_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 
 static long _freq_tbl_determine_rate(struct clk_hw *hw,
 		const struct freq_tbl *f, unsigned long rate,
-		unsigned long *p_rate, struct clk **p)
+		unsigned long *p_rate, struct clk_hw **p_hw)
 {
 	unsigned long clk_flags;
+	struct clk *p;
 
 	f = qcom_find_freq(f, rate);
 	if (!f)
 		return -EINVAL;
 
 	clk_flags = __clk_get_flags(hw->clk);
-	*p = clk_get_parent_by_index(hw->clk, f->src);
+	p = clk_get_parent_by_index(hw->clk, f->src);
 	if (clk_flags & CLK_SET_RATE_PARENT) {
 		if (f->pre_div) {
 			rate /= 2;
@@ -198,15 +199,16 @@ static long _freq_tbl_determine_rate(struct clk_hw *hw,
 			rate = tmp;
 		}
 	} else {
-		rate =  __clk_get_rate(*p);
+		rate =  __clk_get_rate(p);
 	}
+	*p_hw = __clk_get_hw(p);
 	*p_rate = rate;
 
 	return f->freq;
 }
 
 static long clk_rcg2_determine_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long *p_rate, struct clk **p)
+		unsigned long *p_rate, struct clk_hw **p)
 {
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 
@@ -359,7 +361,7 @@ static int clk_edp_pixel_set_rate_and_parent(struct clk_hw *hw,
 }
 
 static long clk_edp_pixel_determine_rate(struct clk_hw *hw, unsigned long rate,
-				 unsigned long *p_rate, struct clk **p)
+				 unsigned long *p_rate, struct clk_hw **p)
 {
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 	const struct freq_tbl *f = rcg->freq_tbl;
@@ -371,7 +373,7 @@ static long clk_edp_pixel_determine_rate(struct clk_hw *hw, unsigned long rate,
 	u32 hid_div;
 
 	/* Force the correct parent */
-	*p = clk_get_parent_by_index(hw->clk, f->src);
+	*p = __clk_get_hw(clk_get_parent_by_index(hw->clk, f->src));
 
 	if (src_rate == 810000000)
 		frac = frac_table_810m;
@@ -410,18 +412,20 @@ const struct clk_ops clk_edp_pixel_ops = {
 EXPORT_SYMBOL_GPL(clk_edp_pixel_ops);
 
 static long clk_byte_determine_rate(struct clk_hw *hw, unsigned long rate,
-			 unsigned long *p_rate, struct clk **p)
+			 unsigned long *p_rate, struct clk_hw **p_hw)
 {
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 	const struct freq_tbl *f = rcg->freq_tbl;
 	unsigned long parent_rate, div;
 	u32 mask = BIT(rcg->hid_width) - 1;
+	struct clk *p;
 
 	if (rate == 0)
 		return -EINVAL;
 
-	*p = clk_get_parent_by_index(hw->clk, f->src);
-	*p_rate = parent_rate = __clk_round_rate(*p, rate);
+	p = clk_get_parent_by_index(hw->clk, f->src);
+	*p_hw = __clk_get_hw(p);
+	*p_rate = parent_rate = __clk_round_rate(p, rate);
 
 	div = DIV_ROUND_UP((2 * parent_rate), rate) - 1;
 	div = min_t(u32, div, mask);
@@ -472,14 +476,16 @@ static const struct frac_entry frac_table_pixel[] = {
 };
 
 static long clk_pixel_determine_rate(struct clk_hw *hw, unsigned long rate,
-				 unsigned long *p_rate, struct clk **p)
+				 unsigned long *p_rate, struct clk_hw **p)
 {
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 	unsigned long request, src_rate;
 	int delta = 100000;
 	const struct freq_tbl *f = rcg->freq_tbl;
 	const struct frac_entry *frac = frac_table_pixel;
-	struct clk *parent = *p = clk_get_parent_by_index(hw->clk, f->src);
+	struct clk *parent = clk_get_parent_by_index(hw->clk, f->src);
+
+	*p = __clk_get_hw(parent);
 
 	for (; frac->num; frac++) {
 		request = (rate * frac->den) / frac->num;
diff --git a/drivers/clk/sunxi/clk-factors.c b/drivers/clk/sunxi/clk-factors.c
index 5521e866fa5..62e08fb5855 100644
--- a/drivers/clk/sunxi/clk-factors.c
+++ b/drivers/clk/sunxi/clk-factors.c
@@ -81,7 +81,7 @@ static long clk_factors_round_rate(struct clk_hw *hw, unsigned long rate,
 
 static long clk_factors_determine_rate(struct clk_hw *hw, unsigned long rate,
 				       unsigned long *best_parent_rate,
-				       struct clk **best_parent_p)
+				       struct clk_hw **best_parent_p)
 {
 	struct clk *clk = hw->clk, *parent, *best_parent = NULL;
 	int i, num_parents;
@@ -108,7 +108,7 @@ static long clk_factors_determine_rate(struct clk_hw *hw, unsigned long rate,
 	}
 
 	if (best_parent)
-		*best_parent_p = best_parent;
+		*best_parent_p = __clk_get_hw(best_parent);
 	*best_parent_rate = best;
 
 	return best_child_rate;
diff --git a/drivers/clk/sunxi/clk-sun6i-ar100.c b/drivers/clk/sunxi/clk-sun6i-ar100.c
index acca53290be..3d282fb8f85 100644
--- a/drivers/clk/sunxi/clk-sun6i-ar100.c
+++ b/drivers/clk/sunxi/clk-sun6i-ar100.c
@@ -46,7 +46,7 @@ static unsigned long ar100_recalc_rate(struct clk_hw *hw,
 
 static long ar100_determine_rate(struct clk_hw *hw, unsigned long rate,
 				 unsigned long *best_parent_rate,
-				 struct clk **best_parent_clk)
+				 struct clk_hw **best_parent_clk)
 {
 	int nparents = __clk_get_num_parents(hw->clk);
 	long best_rate = -EINVAL;
@@ -100,7 +100,7 @@ static long ar100_determine_rate(struct clk_hw *hw, unsigned long rate,
 
 		tmp_rate = (parent_rate >> shift) / div;
 		if (!*best_parent_clk || tmp_rate > best_rate) {
-			*best_parent_clk = parent;
+			*best_parent_clk = __clk_get_hw(parent);
 			*best_parent_rate = parent_rate;
 			best_rate = tmp_rate;
 		}
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 5e06f23eed4..d936409520f 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -176,7 +176,7 @@ struct clk_ops {
 					unsigned long *parent_rate);
 	long		(*determine_rate)(struct clk_hw *hw, unsigned long rate,
 					unsigned long *best_parent_rate,
-					struct clk **best_parent_clk);
+					struct clk_hw **best_parent_hw);
 	int		(*set_parent)(struct clk_hw *hw, u8 index);
 	u8		(*get_parent)(struct clk_hw *hw);
 	int		(*set_rate)(struct clk_hw *hw, unsigned long rate,
@@ -551,7 +551,7 @@ bool __clk_is_enabled(struct clk *clk);
 struct clk *__clk_lookup(const char *name);
 long __clk_mux_determine_rate(struct clk_hw *hw, unsigned long rate,
 			      unsigned long *best_parent_rate,
-			      struct clk **best_parent_p);
+			      struct clk_hw **best_parent_p);
 
 /*
  * FIXME clock api without lock protection
-- 
cgit v1.2.3-70-g09d2


From efc3c1df5fda0aee84f53c226d55804e6dbede4f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Nov 2014 15:36:18 +0100
Subject: scsi: remove ->change_queue_type method

Since we got rid of ordered tag support in 2010 the prime use case of
switching on and off ordered tags has been obsolete.  The other function
of enabling/disabling tagging entirely has only been correctly implemented
by the 53c700 driver and isn't generally useful.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/infiniband/ulp/srp/ib_srp.c  |  1 -
 drivers/scsi/53c700.c                | 35 -----------------------------------
 drivers/scsi/aic94xx/aic94xx_init.c  |  1 -
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c    |  1 -
 drivers/scsi/esas2r/esas2r_main.c    |  1 -
 drivers/scsi/fcoe/fcoe.c             |  1 -
 drivers/scsi/fnic/fnic_main.c        |  1 -
 drivers/scsi/ibmvscsi/ibmvfc.c       |  1 -
 drivers/scsi/ipr.c                   | 25 -------------------------
 drivers/scsi/isci/init.c             |  1 -
 drivers/scsi/libsas/sas_scsi_host.c  |  8 --------
 drivers/scsi/lpfc/lpfc_scsi.c        |  2 --
 drivers/scsi/mpt2sas/mpt2sas_scsih.c |  1 -
 drivers/scsi/mpt3sas/mpt3sas_scsih.c |  1 -
 drivers/scsi/mvsas/mv_init.c         |  1 -
 drivers/scsi/pm8001/pm8001_init.c    |  1 -
 drivers/scsi/pmcraid.c               |  1 -
 drivers/scsi/qla2xxx/qla_os.c        |  1 -
 drivers/scsi/scsi.c                  | 16 ----------------
 drivers/scsi/scsi_debug.c            | 27 ---------------------------
 drivers/scsi/scsi_sysfs.c            | 30 ++++--------------------------
 drivers/target/loopback/tcm_loop.c   |  1 -
 include/scsi/libsas.h                |  1 -
 include/scsi/scsi_host.h             | 13 -------------
 include/scsi/scsi_tcq.h              |  3 ---
 25 files changed, 4 insertions(+), 171 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 5461924c9f1..a1640364144 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -2740,7 +2740,6 @@ static struct scsi_host_template srp_template = {
 	.info				= srp_target_info,
 	.queuecommand			= srp_queuecommand,
 	.change_queue_depth             = srp_change_queue_depth,
-	.change_queue_type              = scsi_change_queue_type,
 	.eh_abort_handler		= srp_abort,
 	.eh_device_reset_handler	= srp_reset_device,
 	.eh_host_reset_handler		= srp_reset_host,
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index aa915da2a5e..e7229114b52 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -176,7 +176,6 @@ STATIC int NCR_700_slave_alloc(struct scsi_device *SDpnt);
 STATIC int NCR_700_slave_configure(struct scsi_device *SDpnt);
 STATIC void NCR_700_slave_destroy(struct scsi_device *SDpnt);
 static int NCR_700_change_queue_depth(struct scsi_device *SDpnt, int depth);
-static int NCR_700_change_queue_type(struct scsi_device *SDpnt, int depth);
 
 STATIC struct device_attribute *NCR_700_dev_attrs[];
 
@@ -326,7 +325,6 @@ NCR_700_detect(struct scsi_host_template *tpnt,
 	tpnt->slave_destroy = NCR_700_slave_destroy;
 	tpnt->slave_alloc = NCR_700_slave_alloc;
 	tpnt->change_queue_depth = NCR_700_change_queue_depth;
-	tpnt->change_queue_type = NCR_700_change_queue_type;
 	tpnt->use_blk_tags = 1;
 
 	if(tpnt->name == NULL)
@@ -2082,39 +2080,6 @@ NCR_700_change_queue_depth(struct scsi_device *SDp, int depth)
 	return scsi_change_queue_depth(SDp, depth);
 }
 
-static int NCR_700_change_queue_type(struct scsi_device *SDp, int tag_type)
-{
-	int change_tag = ((tag_type ==0 &&  scsi_get_tag_type(SDp) != 0)
-			  || (tag_type != 0 && scsi_get_tag_type(SDp) == 0));
-	struct NCR_700_Host_Parameters *hostdata = 
-		(struct NCR_700_Host_Parameters *)SDp->host->hostdata[0];
-
-	/* We have a global (per target) flag to track whether TCQ is
-	 * enabled, so we'll be turning it off for the entire target here.
-	 * our tag algorithm will fail if we mix tagged and untagged commands,
-	 * so quiesce the device before doing this */
-	if (change_tag)
-		scsi_target_quiesce(SDp->sdev_target);
-
-	scsi_set_tag_type(SDp, tag_type);
-	if (!tag_type) {
-		/* shift back to the default unqueued number of commands
-		 * (the user can still raise this) */
-		scsi_change_queue_depth(SDp, SDp->host->cmd_per_lun);
-		hostdata->tag_negotiated &= ~(1 << sdev_id(SDp));
-	} else {
-		/* Here, we cleared the negotiation flag above, so this
-		 * will force the driver to renegotiate */
-		scsi_change_queue_depth(SDp, SDp->queue_depth);
-		if (change_tag)
-			NCR_700_set_tag_neg_state(SDp, NCR_700_START_TAG_NEGOTIATION);
-	}
-	if (change_tag)
-		scsi_target_resume(SDp->sdev_target);
-
-	return tag_type;
-}
-
 static ssize_t
 NCR_700_show_active_tags(struct device *dev, struct device_attribute *attr, char *buf)
 {
diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c
index 14fc018436c..02a2512b76a 100644
--- a/drivers/scsi/aic94xx/aic94xx_init.c
+++ b/drivers/scsi/aic94xx/aic94xx_init.c
@@ -63,7 +63,6 @@ static struct scsi_host_template aic94xx_sht = {
 	.scan_finished		= asd_scan_finished,
 	.scan_start		= asd_scan_start,
 	.change_queue_depth	= sas_change_queue_depth,
-	.change_queue_type	= sas_change_queue_type,
 	.bios_param		= sas_bios_param,
 	.can_queue		= 1,
 	.cmd_per_lun		= 1,
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 386c2cfad30..17a29e97ca0 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -2785,7 +2785,6 @@ static struct scsi_host_template bnx2fc_shost_template = {
 	.eh_host_reset_handler	= fc_eh_host_reset,
 	.slave_alloc		= fc_slave_alloc,
 	.change_queue_depth	= scsi_change_queue_depth,
-	.change_queue_type	= scsi_change_queue_type,
 	.this_id		= -1,
 	.cmd_per_lun		= 3,
 	.use_clustering		= ENABLE_CLUSTERING,
diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c
index 593ff8a63c7..7e1c21e6736 100644
--- a/drivers/scsi/esas2r/esas2r_main.c
+++ b/drivers/scsi/esas2r/esas2r_main.c
@@ -255,7 +255,6 @@ static struct scsi_host_template driver_template = {
 	.emulated			= 0,
 	.proc_name			= ESAS2R_DRVR_NAME,
 	.change_queue_depth		= scsi_change_queue_depth,
-	.change_queue_type		= scsi_change_queue_type,
 	.max_sectors			= 0xFFFF,
 	.use_blk_tags			= 1,
 };
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 308a016fdae..49df2130bd0 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -281,7 +281,6 @@ static struct scsi_host_template fcoe_shost_template = {
 	.eh_host_reset_handler = fc_eh_host_reset,
 	.slave_alloc = fc_slave_alloc,
 	.change_queue_depth = scsi_change_queue_depth,
-	.change_queue_type = scsi_change_queue_type,
 	.this_id = -1,
 	.cmd_per_lun = 3,
 	.can_queue = FCOE_MAX_OUTSTANDING_COMMANDS,
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index 0c1f8177b5b..8a0d4d7b325 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -111,7 +111,6 @@ static struct scsi_host_template fnic_host_template = {
 	.eh_host_reset_handler = fnic_host_reset,
 	.slave_alloc = fnic_slave_alloc,
 	.change_queue_depth = scsi_change_queue_depth,
-	.change_queue_type = scsi_change_queue_type,
 	.this_id = -1,
 	.cmd_per_lun = 3,
 	.can_queue = FNIC_DFLT_IO_REQ,
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index f58c6d8e026..6e3596471ca 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -3089,7 +3089,6 @@ static struct scsi_host_template driver_template = {
 	.target_alloc = ibmvfc_target_alloc,
 	.scan_finished = ibmvfc_scan_finished,
 	.change_queue_depth = ibmvfc_change_queue_depth,
-	.change_queue_type = scsi_change_queue_type,
 	.cmd_per_lun = 16,
 	.can_queue = IBMVFC_MAX_REQUESTS_DEFAULT,
 	.this_id = -1,
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 54029438935..c35ef5f01e9 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -4345,30 +4345,6 @@ static int ipr_change_queue_depth(struct scsi_device *sdev, int qdepth)
 	return sdev->queue_depth;
 }
 
-/**
- * ipr_change_queue_type - Change the device's queue type
- * @dsev:		scsi device struct
- * @tag_type:	type of tags to use
- *
- * Return value:
- * 	actual queue type set
- **/
-static int ipr_change_queue_type(struct scsi_device *sdev, int tag_type)
-{
-	struct ipr_ioa_cfg *ioa_cfg = (struct ipr_ioa_cfg *)sdev->host->hostdata;
-	struct ipr_resource_entry *res;
-	unsigned long lock_flags = 0;
-
-	spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
-	res = (struct ipr_resource_entry *)sdev->hostdata;
-	if (res && ipr_is_gscsi(res))
-		tag_type = scsi_change_queue_type(sdev, tag_type);
-	else
-		tag_type = 0;
-	spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
-	return tag_type;
-}
-
 /**
  * ipr_show_adapter_handle - Show the adapter's resource handle for this device
  * @dev:	device struct
@@ -6302,7 +6278,6 @@ static struct scsi_host_template driver_template = {
 	.target_alloc = ipr_target_alloc,
 	.target_destroy = ipr_target_destroy,
 	.change_queue_depth = ipr_change_queue_depth,
-	.change_queue_type = ipr_change_queue_type,
 	.bios_param = ipr_biosparam,
 	.can_queue = IPR_MAX_COMMANDS,
 	.this_id = -1,
diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c
index 724c6265b66..cd41b63a2f1 100644
--- a/drivers/scsi/isci/init.c
+++ b/drivers/scsi/isci/init.c
@@ -158,7 +158,6 @@ static struct scsi_host_template isci_sht = {
 	.scan_finished			= isci_host_scan_finished,
 	.scan_start			= isci_host_start,
 	.change_queue_depth		= sas_change_queue_depth,
-	.change_queue_type		= sas_change_queue_type,
 	.bios_param			= sas_bios_param,
 	.can_queue			= ISCI_CAN_QUEUE_VAL,
 	.cmd_per_lun			= 1,
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 72918d227ea..519dac4e341 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -906,13 +906,6 @@ int sas_change_queue_depth(struct scsi_device *sdev, int depth)
 	return scsi_change_queue_depth(sdev, depth);
 }
 
-int sas_change_queue_type(struct scsi_device *scsi_dev, int type)
-{
-	if (dev_is_sata(sdev_to_domain_dev(scsi_dev)))
-		return -EINVAL;
-	return scsi_change_queue_type(scsi_dev, type);
-}
-
 int sas_bios_param(struct scsi_device *scsi_dev,
 			  struct block_device *bdev,
 			  sector_t capacity, int *hsc)
@@ -1011,7 +1004,6 @@ EXPORT_SYMBOL_GPL(sas_queuecommand);
 EXPORT_SYMBOL_GPL(sas_target_alloc);
 EXPORT_SYMBOL_GPL(sas_slave_configure);
 EXPORT_SYMBOL_GPL(sas_change_queue_depth);
-EXPORT_SYMBOL_GPL(sas_change_queue_type);
 EXPORT_SYMBOL_GPL(sas_bios_param);
 EXPORT_SYMBOL_GPL(sas_task_abort);
 EXPORT_SYMBOL_GPL(sas_phy_reset);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index fd85952b621..4f9222eb226 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -5879,7 +5879,6 @@ struct scsi_host_template lpfc_template = {
 	.max_sectors		= 0xFFFF,
 	.vendor_id		= LPFC_NL_VENDOR_ID,
 	.change_queue_depth	= scsi_change_queue_depth,
-	.change_queue_type	= scsi_change_queue_type,
 	.use_blk_tags		= 1,
 	.track_queue_depth	= 1,
 };
@@ -5904,7 +5903,6 @@ struct scsi_host_template lpfc_vport_template = {
 	.shost_attrs		= lpfc_vport_attrs,
 	.max_sectors		= 0xFFFF,
 	.change_queue_depth	= scsi_change_queue_depth,
-	.change_queue_type	= scsi_change_queue_type,
 	.use_blk_tags		= 1,
 	.track_queue_depth	= 1,
 };
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index 8431eb10bbb..6a1c036a6f3 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -7592,7 +7592,6 @@ static struct scsi_host_template scsih_driver_template = {
 	.scan_finished			= _scsih_scan_finished,
 	.scan_start			= _scsih_scan_start,
 	.change_queue_depth 		= _scsih_change_queue_depth,
-	.change_queue_type		= scsi_change_queue_type,
 	.eh_abort_handler		= _scsih_abort,
 	.eh_device_reset_handler	= _scsih_dev_reset,
 	.eh_target_reset_handler	= _scsih_target_reset,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index a2b60991efd..94261ee9e72 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -7229,7 +7229,6 @@ static struct scsi_host_template scsih_driver_template = {
 	.scan_finished			= _scsih_scan_finished,
 	.scan_start			= _scsih_scan_start,
 	.change_queue_depth		= _scsih_change_queue_depth,
-	.change_queue_type		= scsi_change_queue_type,
 	.eh_abort_handler		= _scsih_abort,
 	.eh_device_reset_handler	= _scsih_dev_reset,
 	.eh_target_reset_handler	= _scsih_target_reset,
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index f15df3de679..53030b0e801 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -54,7 +54,6 @@ static struct scsi_host_template mvs_sht = {
 	.scan_finished		= mvs_scan_finished,
 	.scan_start		= mvs_scan_start,
 	.change_queue_depth	= sas_change_queue_depth,
-	.change_queue_type	= sas_change_queue_type,
 	.bios_param		= sas_bios_param,
 	.can_queue		= 1,
 	.cmd_per_lun		= 1,
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index 329aba0083a..65555916d3b 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -76,7 +76,6 @@ static struct scsi_host_template pm8001_sht = {
 	.scan_finished		= pm8001_scan_finished,
 	.scan_start		= pm8001_scan_start,
 	.change_queue_depth	= sas_change_queue_depth,
-	.change_queue_type	= sas_change_queue_type,
 	.bios_param		= sas_bios_param,
 	.can_queue		= 1,
 	.cmd_per_lun		= 1,
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index b1b1f66b1ab..8c27b6a77ec 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -4251,7 +4251,6 @@ static struct scsi_host_template pmcraid_host_template = {
 	.slave_configure = pmcraid_slave_configure,
 	.slave_destroy = pmcraid_slave_destroy,
 	.change_queue_depth = pmcraid_change_queue_depth,
-	.change_queue_type  = scsi_change_queue_type,
 	.can_queue = PMCRAID_MAX_IO_CMD,
 	.this_id = -1,
 	.sg_tablesize = PMCRAID_MAX_IOADLS,
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 6b4d9235368..12ca291c138 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -258,7 +258,6 @@ struct scsi_host_template qla2xxx_driver_template = {
 	.scan_finished		= qla2xxx_scan_finished,
 	.scan_start		= qla2xxx_scan_start,
 	.change_queue_depth	= scsi_change_queue_depth,
-	.change_queue_type	= scsi_change_queue_type,
 	.this_id		= -1,
 	.cmd_per_lun		= 3,
 	.use_clustering		= ENABLE_CLUSTERING,
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 5ea15fc7d2f..72282ae3009 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -831,22 +831,6 @@ int scsi_track_queue_full(struct scsi_device *sdev, int depth)
 }
 EXPORT_SYMBOL(scsi_track_queue_full);
 
-/**
- * scsi_change_queue_type() - Change a device's queue type
- * @sdev:     The SCSI device whose queue depth is to change
- * @tag_type: Identifier for queue type
- */
-int scsi_change_queue_type(struct scsi_device *sdev, int tag_type)
-{
-	if (!sdev->tagged_supported)
-		return 0;
-
-	scsi_set_tag_type(sdev, tag_type);
-	return tag_type;
-
-}
-EXPORT_SYMBOL(scsi_change_queue_type);
-
 /**
  * scsi_vpd_inquiry - Request a device provide us with a VPD page
  * @sdev: The device to ask
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index aa4b6b80aad..87b5361d893 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -4987,32 +4987,6 @@ sdebug_change_qdepth(struct scsi_device *sdev, int qdepth)
 	return sdev->queue_depth;
 }
 
-static int
-sdebug_change_qtype(struct scsi_device *sdev, int qtype)
-{
-	qtype = scsi_change_queue_type(sdev, qtype);
-	if (SCSI_DEBUG_OPT_Q_NOISE & scsi_debug_opts) {
-		const char *cp;
-
-		switch (qtype) {
-		case 0:
-			cp = "untagged";
-			break;
-		case MSG_SIMPLE_TAG:
-			cp = "simple tags";
-			break;
-		case MSG_ORDERED_TAG:
-			cp = "ordered tags";
-			break;
-		default:
-			cp = "unknown";
-			break;
-		}
-		sdev_printk(KERN_INFO, sdev, "%s: to %s\n", __func__, cp);
-	}
-	return qtype;
-}
-
 static int
 check_inject(struct scsi_cmnd *scp)
 {
@@ -5212,7 +5186,6 @@ static struct scsi_host_template sdebug_driver_template = {
 	.ioctl =		scsi_debug_ioctl,
 	.queuecommand =		sdebug_queuecommand_lock_or_not,
 	.change_queue_depth =	sdebug_change_qdepth,
-	.change_queue_type =	sdebug_change_qtype,
 	.eh_abort_handler =	scsi_debug_abort,
 	.eh_device_reset_handler = scsi_debug_device_reset,
 	.eh_target_reset_handler = scsi_debug_target_reset,
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 1cb64a8e18c..1ac38e73df7 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -738,30 +738,12 @@ store_queue_type_field(struct device *dev, struct device_attribute *attr,
 		       const char *buf, size_t count)
 {
 	struct scsi_device *sdev = to_scsi_device(dev);
-	struct scsi_host_template *sht = sdev->host->hostt;
-	int tag_type = 0, retval;
-	int prev_tag_type = scsi_get_tag_type(sdev);
-
-	if (!sdev->tagged_supported || !sht->change_queue_type)
-		return -EINVAL;
 
-	/*
-	 * We're never issueing order tags these days, but allow the value
-	 * for backwards compatibility.
-	 */
-	if (strncmp(buf, "ordered", 7) == 0 ||
-	    strncmp(buf, "simple", 6) == 0)
-		tag_type = MSG_SIMPLE_TAG;
-	else if (strncmp(buf, "none", 4) != 0)
+	if (!sdev->tagged_supported)
 		return -EINVAL;
-
-	if (tag_type == prev_tag_type)
-		return count;
-
-	retval = sht->change_queue_type(sdev, tag_type);
-	if (retval < 0)
-		return retval;
-
+		
+	sdev_printk(KERN_INFO, sdev,
+		    "ignoring write to deprecated queue_type attribute");
 	return count;
 }
 
@@ -938,10 +920,6 @@ static umode_t scsi_sdev_attr_is_visible(struct kobject *kobj,
 	    !sdev->host->hostt->change_queue_depth)
 		return 0;
 
-	if (attr == &dev_attr_queue_type.attr &&
-	    !sdev->host->hostt->change_queue_type)
-		return S_IRUGO;
-
 	return attr->mode;
 }
 
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 4d1b7224a7f..24e2c94e429 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -385,7 +385,6 @@ static struct scsi_host_template tcm_loop_driver_template = {
 	.name			= "TCM_Loopback",
 	.queuecommand		= tcm_loop_queuecommand,
 	.change_queue_depth	= scsi_change_queue_depth,
-	.change_queue_type	= scsi_change_queue_type,
 	.eh_abort_handler = tcm_loop_abort_task,
 	.eh_device_reset_handler = tcm_loop_device_reset,
 	.eh_target_reset_handler = tcm_loop_target_reset,
diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h
index 832dcc9f86e..8280234fba9 100644
--- a/include/scsi/libsas.h
+++ b/include/scsi/libsas.h
@@ -693,7 +693,6 @@ extern int sas_queuecommand(struct Scsi_Host * ,struct scsi_cmnd *);
 extern int sas_target_alloc(struct scsi_target *);
 extern int sas_slave_configure(struct scsi_device *);
 extern int sas_change_queue_depth(struct scsi_device *, int new_depth);
-extern int sas_change_queue_type(struct scsi_device *, int qt);
 extern int sas_bios_param(struct scsi_device *,
 			  struct block_device *,
 			  sector_t capacity, int *hsc);
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index c8a462ef9a4..c2fa8b49cb2 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -277,19 +277,6 @@ struct scsi_host_template {
 	 */
 	int (* change_queue_depth)(struct scsi_device *, int);
 
-	/*
-	 * Fill in this function to allow the changing of tag types
-	 * (this also allows the enabling/disabling of tag command
-	 * queueing).  An error should only be returned if something
-	 * went wrong in the driver while trying to set the tag type.
-	 * If the driver doesn't support the requested tag type, then
-	 * it should set the closest type it does support without
-	 * returning an error.  Returns the actual tag type set.
-	 *
-	 * Status: OPTIONAL
-	 */
-	int (* change_queue_type)(struct scsi_device *, int);
-
 	/*
 	 * This function determines the BIOS parameters for a given
 	 * harddisk.  These tend to be numbers that are made up by
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index fe4a7029941..59578beac05 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -15,9 +15,6 @@
 
 
 #ifdef CONFIG_BLOCK
-
-int scsi_change_queue_type(struct scsi_device *sdev, int tag_type);
-
 /**
  * scsi_get_tag_type - get the type of tag the device supports
  * @sdev:	the scsi device
-- 
cgit v1.2.3-70-g09d2


From 17ea01267c75c5a2e00f3603037715d0d2ce4a58 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Nov 2014 15:36:20 +0100
Subject: scsi: remove scsi_get_tag_type

Both remaining users are better of just checking sdev->simple_tags
directly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/scsi/53c700.c   |  4 ++--
 drivers/scsi/ipr.c      |  2 +-
 include/scsi/scsi_tcq.h | 13 -------------
 3 files changed, 3 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index e7229114b52..2c87a7ac1d8 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -1816,8 +1816,8 @@ NCR_700_queuecommand_lck(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *)
 		hostdata->tag_negotiated &= ~(1<<scmd_id(SCp));
 	}
 
-	if((hostdata->tag_negotiated &(1<<scmd_id(SCp)))
-	   && scsi_get_tag_type(SCp->device)) {
+	if ((hostdata->tag_negotiated & (1<<scmd_id(SCp))) &&
+	    SCp->device->simple_tags) {
 		slot->tag = SCp->request->tag;
 		CDEBUG(KERN_DEBUG, SCp, "sending out tag %d, slot %p\n",
 		       slot->tag, slot);
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index c35ef5f01e9..c91c7c5da56 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -5755,7 +5755,7 @@ static void ipr_erp_cancel_all(struct ipr_cmnd *ipr_cmd)
 
 	ipr_reinit_ipr_cmnd_for_erp(ipr_cmd);
 
-	if (!scsi_get_tag_type(scsi_cmd->device)) {
+	if (!scsi_cmd->device->simple_tags) {
 		ipr_erp_request_sense(ipr_cmd);
 		return;
 	}
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index 59578beac05..681e010c2c4 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -15,19 +15,6 @@
 
 
 #ifdef CONFIG_BLOCK
-/**
- * scsi_get_tag_type - get the type of tag the device supports
- * @sdev:	the scsi device
- */
-static inline int scsi_get_tag_type(struct scsi_device *sdev)
-{
-	if (!sdev->tagged_supported)
-		return 0;
-	if (sdev->simple_tags)
-		return MSG_SIMPLE_TAG;
-	return 0;
-}
-
 static inline void scsi_set_tag_type(struct scsi_device *sdev, int tag)
 {
 	switch (tag) {
-- 
cgit v1.2.3-70-g09d2


From 4e484896ac8b1877097770bc630802d5535e8d46 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Nov 2014 15:36:21 +0100
Subject: scsi: remove scsi_set_tag_type

There is no benefit over just setting sdev->simple_tags directly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/scsi/53c700.c   |  2 +-
 include/scsi/scsi_tcq.h | 15 ---------------
 2 files changed, 1 insertion(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index 2c87a7ac1d8..82abfce1cb4 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -902,8 +902,8 @@ process_message(struct Scsi_Host *host,	struct NCR_700_Host_Parameters *hostdata
 			hostdata->tag_negotiated &= ~(1<<scmd_id(SCp));
 
 			SCp->device->tagged_supported = 0;
+			SCp->device->simple_tags = 0;
 			scsi_change_queue_depth(SCp->device, host->cmd_per_lun);
-			scsi_set_tag_type(SCp->device, 0);
 		} else {
 			shost_printk(KERN_WARNING, host,
 				"(%d:%d) Unexpected REJECT Message %s\n",
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index 681e010c2c4..e624acabd7a 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -15,21 +15,6 @@
 
 
 #ifdef CONFIG_BLOCK
-static inline void scsi_set_tag_type(struct scsi_device *sdev, int tag)
-{
-	switch (tag) {
-	case MSG_ORDERED_TAG:
-	case MSG_SIMPLE_TAG:
-		sdev->simple_tags = 1;
-		break;
-	case 0:
-		/* fall through */
-	default:
-		sdev->simple_tags = 0;
-		break;
-	}
-}
-
 static inline struct scsi_cmnd *scsi_mq_find_tag(struct Scsi_Host *shost,
 						 int unique_tag)
 {
-- 
cgit v1.2.3-70-g09d2


From 68d81f40047cc4f99e86807e1160fb07a7b856c7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Mon, 24 Nov 2014 07:07:25 -0800
Subject: scsi: remove MSG_*_TAG defines

For SPI drivers use the message definitions from scsi.h, and for target
drivers introduce a new TCM_*_TAG namespace.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com
---
 drivers/infiniband/ulp/srpt/ib_srpt.c      | 10 +++++-----
 drivers/scsi/advansys.c                    |  8 ++++----
 drivers/scsi/qla2xxx/qla_target.c          | 12 ++++++------
 drivers/scsi/scsi_debug.c                  |  1 -
 drivers/scsi/scsi_transport_spi.c          |  2 +-
 drivers/target/iscsi/iscsi_target.c        | 14 +++++++-------
 drivers/target/loopback/tcm_loop.c         |  4 ++--
 drivers/target/sbp/sbp_target.c            |  2 +-
 drivers/target/target_core_pscsi.c         |  2 +-
 drivers/target/target_core_sbc.c           |  2 +-
 drivers/target/target_core_spc.c           |  4 ++--
 drivers/target/target_core_transport.c     | 16 ++++++++--------
 drivers/target/tcm_fc/tfc_cmd.c            |  8 ++++----
 drivers/usb/gadget/legacy/tcm_usb_gadget.c | 10 +++++-----
 drivers/xen/xen-scsiback.c                 |  2 +-
 include/scsi/scsi_tcq.h                    |  5 -----
 include/target/target_core_base.h          |  6 ++++++
 include/trace/events/target.h              |  8 ++++----
 18 files changed, 58 insertions(+), 58 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 7206547c13c..3a0ca61b02c 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -1708,17 +1708,17 @@ static int srpt_handle_cmd(struct srpt_rdma_ch *ch,
 
 	switch (srp_cmd->task_attr) {
 	case SRP_CMD_SIMPLE_Q:
-		cmd->sam_task_attr = MSG_SIMPLE_TAG;
+		cmd->sam_task_attr = TCM_SIMPLE_TAG;
 		break;
 	case SRP_CMD_ORDERED_Q:
 	default:
-		cmd->sam_task_attr = MSG_ORDERED_TAG;
+		cmd->sam_task_attr = TCM_ORDERED_TAG;
 		break;
 	case SRP_CMD_HEAD_OF_Q:
-		cmd->sam_task_attr = MSG_HEAD_TAG;
+		cmd->sam_task_attr = TCM_HEAD_TAG;
 		break;
 	case SRP_CMD_ACA:
-		cmd->sam_task_attr = MSG_ACA_TAG;
+		cmd->sam_task_attr = TCM_ACA_TAG;
 		break;
 	}
 
@@ -1733,7 +1733,7 @@ static int srpt_handle_cmd(struct srpt_rdma_ch *ch,
 				       sizeof(srp_cmd->lun));
 	rc = target_submit_cmd(cmd, ch->sess, srp_cmd->cdb,
 			&send_ioctx->sense_data[0], unpacked_lun, data_len,
-			MSG_SIMPLE_TAG, dir, TARGET_SCF_ACK_KREF);
+			TCM_SIMPLE_TAG, dir, TARGET_SCF_ACK_KREF);
 	if (rc != 0) {
 		ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		goto send_sense;
diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
index 6719a3390eb..2c5ce48c8f9 100644
--- a/drivers/scsi/advansys.c
+++ b/drivers/scsi/advansys.c
@@ -7921,9 +7921,9 @@ static int asc_build_req(struct asc_board *boardp, struct scsi_cmnd *scp,
 	 */
 	if ((asc_dvc->cur_dvc_qng[scp->device->id] > 0) &&
 	    (boardp->reqcnt[scp->device->id] % 255) == 0) {
-		asc_scsi_q->q2.tag_code = MSG_ORDERED_TAG;
+		asc_scsi_q->q2.tag_code = ORDERED_QUEUE_TAG;
 	} else {
-		asc_scsi_q->q2.tag_code = MSG_SIMPLE_TAG;
+		asc_scsi_q->q2.tag_code = SIMPLE_QUEUE_TAG;
 	}
 
 	/* Build ASC_SCSI_Q */
@@ -8351,7 +8351,7 @@ static int AscPutReadyQueue(ASC_DVC_VAR *asc_dvc, ASC_SCSI_Q *scsiq, uchar q_no)
 	}
 	q_addr = ASC_QNO_TO_QADDR(q_no);
 	if ((scsiq->q1.target_id & asc_dvc->use_tagged_qng) == 0) {
-		scsiq->q2.tag_code &= ~MSG_SIMPLE_TAG;
+		scsiq->q2.tag_code &= ~SIMPLE_QUEUE_TAG;
 	}
 	scsiq->q1.status = QS_FREE;
 	AscMemWordCopyPtrToLram(iop_base,
@@ -8669,7 +8669,7 @@ static int AscExeScsiQueue(ASC_DVC_VAR *asc_dvc, ASC_SCSI_Q *scsiq)
 		}
 	}
 	if (disable_syn_offset_one_fix) {
-		scsiq->q2.tag_code &= ~MSG_SIMPLE_TAG;
+		scsiq->q2.tag_code &= ~SIMPLE_QUEUE_TAG;
 		scsiq->q2.tag_code |= (ASC_TAG_FLAG_DISABLE_ASYN_USE_SYN_FIX |
 				       ASC_TAG_FLAG_DISABLE_DISCONNECT);
 	} else {
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index a902fa1db7a..57418258c10 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -3218,25 +3218,25 @@ static inline int qlt_get_fcp_task_attr(struct scsi_qla_host *vha,
 
 	switch (task_codes) {
 	case ATIO_SIMPLE_QUEUE:
-		fcp_task_attr = MSG_SIMPLE_TAG;
+		fcp_task_attr = TCM_SIMPLE_TAG;
 		break;
 	case ATIO_HEAD_OF_QUEUE:
-		fcp_task_attr = MSG_HEAD_TAG;
+		fcp_task_attr = TCM_HEAD_TAG;
 		break;
 	case ATIO_ORDERED_QUEUE:
-		fcp_task_attr = MSG_ORDERED_TAG;
+		fcp_task_attr = TCM_ORDERED_TAG;
 		break;
 	case ATIO_ACA_QUEUE:
-		fcp_task_attr = MSG_ACA_TAG;
+		fcp_task_attr = TCM_ACA_TAG;
 		break;
 	case ATIO_UNTAGGED:
-		fcp_task_attr = MSG_SIMPLE_TAG;
+		fcp_task_attr = TCM_SIMPLE_TAG;
 		break;
 	default:
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05d,
 		    "qla_target: unknown task code %x, use ORDERED instead\n",
 		    task_codes);
-		fcp_task_attr = MSG_ORDERED_TAG;
+		fcp_task_attr = TCM_ORDERED_TAG;
 		break;
 	}
 
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 87b5361d893..d81158b7132 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -128,7 +128,6 @@ static const char *scsi_debug_version_date = "20141022";
 #define DEF_REMOVABLE false
 #define DEF_SCSI_LEVEL   6    /* INQUIRY, byte2 [6->SPC-4] */
 #define DEF_SECTOR_SIZE 512
-#define DEF_TAGGED_QUEUING 0 /* 0 | MSG_SIMPLE_TAG | MSG_ORDERED_TAG */
 #define DEF_UNMAP_ALIGNMENT 0
 #define DEF_UNMAP_GRANULARITY 1
 #define DEF_UNMAP_MAX_BLOCKS 0xFFFFFFFF
diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c
index fa2aece76cc..31bbb0da339 100644
--- a/drivers/scsi/scsi_transport_spi.c
+++ b/drivers/scsi/scsi_transport_spi.c
@@ -1221,7 +1221,7 @@ EXPORT_SYMBOL_GPL(spi_populate_ppr_msg);
 int spi_populate_tag_msg(unsigned char *msg, struct scsi_cmnd *cmd)
 {
         if (cmd->flags & SCMD_TAGGED) {
-		*msg++ = MSG_SIMPLE_TAG;
+		*msg++ = SIMPLE_QUEUE_TAG;
         	*msg++ = cmd->request->tag;
         	return 2;
 	}
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index b19e4329ba0..67802ccfcde 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -943,17 +943,17 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	 */
 	if ((iscsi_task_attr == ISCSI_ATTR_UNTAGGED) ||
 	    (iscsi_task_attr == ISCSI_ATTR_SIMPLE))
-		sam_task_attr = MSG_SIMPLE_TAG;
+		sam_task_attr = TCM_SIMPLE_TAG;
 	else if (iscsi_task_attr == ISCSI_ATTR_ORDERED)
-		sam_task_attr = MSG_ORDERED_TAG;
+		sam_task_attr = TCM_ORDERED_TAG;
 	else if (iscsi_task_attr == ISCSI_ATTR_HEAD_OF_QUEUE)
-		sam_task_attr = MSG_HEAD_TAG;
+		sam_task_attr = TCM_HEAD_TAG;
 	else if (iscsi_task_attr == ISCSI_ATTR_ACA)
-		sam_task_attr = MSG_ACA_TAG;
+		sam_task_attr = TCM_ACA_TAG;
 	else {
 		pr_debug("Unknown iSCSI Task Attribute: 0x%02x, using"
-			" MSG_SIMPLE_TAG\n", iscsi_task_attr);
-		sam_task_attr = MSG_SIMPLE_TAG;
+			" TCM_SIMPLE_TAG\n", iscsi_task_attr);
+		sam_task_attr = TCM_SIMPLE_TAG;
 	}
 
 	cmd->iscsi_opcode	= ISCSI_OP_SCSI_CMD;
@@ -1811,7 +1811,7 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 		transport_init_se_cmd(&cmd->se_cmd,
 				      &lio_target_fabric_configfs->tf_ops,
 				      conn->sess->se_sess, 0, DMA_NONE,
-				      MSG_SIMPLE_TAG, cmd->sense_buffer + 2);
+				      TCM_SIMPLE_TAG, cmd->sense_buffer + 2);
 
 		target_get_sess_cmd(conn->sess->se_sess, &cmd->se_cmd, true);
 		sess_ref = true;
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 24e2c94e429..dda9a08c939 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -168,7 +168,7 @@ static void tcm_loop_submission_work(struct work_struct *work)
 
 	rc = target_submit_cmd_map_sgls(se_cmd, tl_nexus->se_sess, sc->cmnd,
 			&tl_cmd->tl_sense_buf[0], tl_cmd->sc->device->lun,
-			transfer_length, MSG_SIMPLE_TAG,
+			transfer_length, TCM_SIMPLE_TAG,
 			sc->sc_data_direction, 0,
 			scsi_sglist(sc), scsi_sg_count(sc),
 			sgl_bidi, sgl_bidi_count,
@@ -248,7 +248,7 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg,
 	 * Initialize struct se_cmd descriptor from target_core_mod infrastructure
 	 */
 	transport_init_se_cmd(se_cmd, se_tpg->se_tpg_tfo, se_sess, 0,
-				DMA_NONE, MSG_SIMPLE_TAG,
+				DMA_NONE, TCM_SIMPLE_TAG,
 				&tl_cmd->tl_sense_buf[0]);
 
 	rc = core_tmr_alloc_req(se_cmd, tl_tmr, tmr, GFP_KERNEL);
diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c
index e7e93727553..9512af6a811 100644
--- a/drivers/target/sbp/sbp_target.c
+++ b/drivers/target/sbp/sbp_target.c
@@ -1237,7 +1237,7 @@ static void sbp_handle_command(struct sbp_target_request *req)
 
 	if (target_submit_cmd(&req->se_cmd, sess->se_sess, req->cmd_buf,
 			      req->sense_buf, unpacked_lun, data_length,
-			      MSG_SIMPLE_TAG, data_dir, 0))
+			      TCM_SIMPLE_TAG, data_dir, 0))
 		goto err;
 
 	return;
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 7c8291f0bbb..caf03d5b3ca 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -1094,7 +1094,7 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 	req->retries = PS_RETRY;
 
 	blk_execute_rq_nowait(pdv->pdv_sd->request_queue, NULL, req,
-			(cmd->sam_task_attr == MSG_HEAD_TAG),
+			(cmd->sam_task_attr == TCM_HEAD_TAG),
 			pscsi_req_done);
 
 	return 0;
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index ebe62afb957..d6e06af696e 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -485,7 +485,7 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd)
 	cmd->t_data_nents_orig = cmd->t_data_nents;
 	cmd->t_data_nents = 1;
 
-	cmd->sam_task_attr = MSG_HEAD_TAG;
+	cmd->sam_task_attr = TCM_HEAD_TAG;
 	cmd->transport_complete_callback = compare_and_write_post;
 	/*
 	 * Now reset ->execute_cmd() to the normal sbc_execute_rw() handler
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index bc286a67af7..1307600fe72 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -1357,7 +1357,7 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		 * Do implicit HEAD_OF_QUEUE processing for INQUIRY.
 		 * See spc4r17 section 5.3
 		 */
-		cmd->sam_task_attr = MSG_HEAD_TAG;
+		cmd->sam_task_attr = TCM_HEAD_TAG;
 		cmd->execute_cmd = spc_emulate_inquiry;
 		break;
 	case SECURITY_PROTOCOL_IN:
@@ -1391,7 +1391,7 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		 * Do implicit HEAD_OF_QUEUE processing for REPORT_LUNS
 		 * See spc4r17 section 5.3
 		 */
-		cmd->sam_task_attr = MSG_HEAD_TAG;
+		cmd->sam_task_attr = TCM_HEAD_TAG;
 		break;
 	case TEST_UNIT_READY:
 		cmd->execute_cmd = spc_emulate_testunitready;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 9ea0d5f03f7..d9b5010c3bf 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1159,7 +1159,7 @@ transport_check_alloc_task_attr(struct se_cmd *cmd)
 	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
 		return 0;
 
-	if (cmd->sam_task_attr == MSG_ACA_TAG) {
+	if (cmd->sam_task_attr == TCM_ACA_TAG) {
 		pr_debug("SAM Task Attribute ACA"
 			" emulation is not supported\n");
 		return TCM_INVALID_CDB_FIELD;
@@ -1531,7 +1531,7 @@ int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess,
 	BUG_ON(!se_tpg);
 
 	transport_init_se_cmd(se_cmd, se_tpg->se_tpg_tfo, se_sess,
-			      0, DMA_NONE, MSG_SIMPLE_TAG, sense);
+			      0, DMA_NONE, TCM_SIMPLE_TAG, sense);
 	/*
 	 * FIXME: Currently expect caller to handle se_cmd->se_tmr_req
 	 * allocation failure.
@@ -1718,12 +1718,12 @@ static bool target_handle_task_attr(struct se_cmd *cmd)
 	 * to allow the passed struct se_cmd list of tasks to the front of the list.
 	 */
 	switch (cmd->sam_task_attr) {
-	case MSG_HEAD_TAG:
+	case TCM_HEAD_TAG:
 		pr_debug("Added HEAD_OF_QUEUE for CDB: 0x%02x, "
 			 "se_ordered_id: %u\n",
 			 cmd->t_task_cdb[0], cmd->se_ordered_id);
 		return false;
-	case MSG_ORDERED_TAG:
+	case TCM_ORDERED_TAG:
 		atomic_inc_mb(&dev->dev_ordered_sync);
 
 		pr_debug("Added ORDERED for CDB: 0x%02x to ordered list, "
@@ -1828,7 +1828,7 @@ static void target_restart_delayed_cmds(struct se_device *dev)
 
 		__target_execute_cmd(cmd);
 
-		if (cmd->sam_task_attr == MSG_ORDERED_TAG)
+		if (cmd->sam_task_attr == TCM_ORDERED_TAG)
 			break;
 	}
 }
@@ -1844,18 +1844,18 @@ static void transport_complete_task_attr(struct se_cmd *cmd)
 	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
 		return;
 
-	if (cmd->sam_task_attr == MSG_SIMPLE_TAG) {
+	if (cmd->sam_task_attr == TCM_SIMPLE_TAG) {
 		atomic_dec_mb(&dev->simple_cmds);
 		dev->dev_cur_ordered_id++;
 		pr_debug("Incremented dev->dev_cur_ordered_id: %u for"
 			" SIMPLE: %u\n", dev->dev_cur_ordered_id,
 			cmd->se_ordered_id);
-	} else if (cmd->sam_task_attr == MSG_HEAD_TAG) {
+	} else if (cmd->sam_task_attr == TCM_HEAD_TAG) {
 		dev->dev_cur_ordered_id++;
 		pr_debug("Incremented dev_cur_ordered_id: %u for"
 			" HEAD_OF_QUEUE: %u\n", dev->dev_cur_ordered_id,
 			cmd->se_ordered_id);
-	} else if (cmd->sam_task_attr == MSG_ORDERED_TAG) {
+	} else if (cmd->sam_task_attr == TCM_ORDERED_TAG) {
 		atomic_dec_mb(&dev->dev_ordered_sync);
 
 		dev->dev_cur_ordered_id++;
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index be0c0d08c56..edcafa4490c 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -554,17 +554,17 @@ static void ft_send_work(struct work_struct *work)
 	 */
 	switch (fcp->fc_pri_ta & FCP_PTA_MASK) {
 	case FCP_PTA_HEADQ:
-		task_attr = MSG_HEAD_TAG;
+		task_attr = TCM_HEAD_TAG;
 		break;
 	case FCP_PTA_ORDERED:
-		task_attr = MSG_ORDERED_TAG;
+		task_attr = TCM_ORDERED_TAG;
 		break;
 	case FCP_PTA_ACA:
-		task_attr = MSG_ACA_TAG;
+		task_attr = TCM_ACA_TAG;
 		break;
 	case FCP_PTA_SIMPLE: /* Fallthrough */
 	default:
-		task_attr = MSG_SIMPLE_TAG;
+		task_attr = TCM_SIMPLE_TAG;
 	}
 
 	fc_seq_exch(cmd->seq)->lp->tt.seq_set_resp(cmd->seq, ft_recv_seq, cmd);
diff --git a/drivers/usb/gadget/legacy/tcm_usb_gadget.c b/drivers/usb/gadget/legacy/tcm_usb_gadget.c
index 6cdb7a534f2..283ee14ca0f 100644
--- a/drivers/usb/gadget/legacy/tcm_usb_gadget.c
+++ b/drivers/usb/gadget/legacy/tcm_usb_gadget.c
@@ -1131,19 +1131,19 @@ static int usbg_submit_command(struct f_uas *fu,
 
 	switch (cmd_iu->prio_attr & 0x7) {
 	case UAS_HEAD_TAG:
-		cmd->prio_attr = MSG_HEAD_TAG;
+		cmd->prio_attr = TCM_HEAD_TAG;
 		break;
 	case UAS_ORDERED_TAG:
-		cmd->prio_attr = MSG_ORDERED_TAG;
+		cmd->prio_attr = TCM_ORDERED_TAG;
 		break;
 	case UAS_ACA:
-		cmd->prio_attr = MSG_ACA_TAG;
+		cmd->prio_attr = TCM_ACA_TAG;
 		break;
 	default:
 		pr_debug_once("Unsupported prio_attr: %02x.\n",
 				cmd_iu->prio_attr);
 	case UAS_SIMPLE_TAG:
-		cmd->prio_attr = MSG_SIMPLE_TAG;
+		cmd->prio_attr = TCM_SIMPLE_TAG;
 		break;
 	}
 
@@ -1240,7 +1240,7 @@ static int bot_submit_command(struct f_uas *fu,
 		goto err;
 	}
 
-	cmd->prio_attr = MSG_SIMPLE_TAG;
+	cmd->prio_attr = TCM_SIMPLE_TAG;
 	se_cmd = &cmd->se_cmd;
 	cmd->unpacked_lun = cbw->Lun;
 	cmd->is_read = cbw->Flags & US_BULK_FLAG_IN ? 1 : 0;
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 50610a6acf3..e999496eda3 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -606,7 +606,7 @@ static void scsiback_device_action(struct vscsibk_pend *pending_req,
 	init_waitqueue_head(&tmr->tmr_wait);
 
 	transport_init_se_cmd(se_cmd, tpg->se_tpg.se_tpg_tfo,
-		tpg->tpg_nexus->tvn_se_sess, 0, DMA_NONE, MSG_SIMPLE_TAG,
+		tpg->tpg_nexus->tvn_se_sess, 0, DMA_NONE, TCM_SIMPLE_TAG,
 		&pending_req->sense_buffer[0]);
 
 	rc = core_tmr_alloc_req(se_cmd, tmr, act, GFP_KERNEL);
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index e624acabd7a..9708b28bd2a 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -6,11 +6,6 @@
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 
-#define MSG_SIMPLE_TAG	0x20
-#define MSG_HEAD_TAG	0x21
-#define MSG_ORDERED_TAG	0x22
-#define MSG_ACA_TAG	0x24	/* unsupported */
-
 #define SCSI_NO_TAG	(-1)    /* identify no tag in use */
 
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 23c518a0340..397fb635766 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -476,6 +476,12 @@ struct se_dif_v1_tuple {
 	__be32			ref_tag;
 };
 
+/* for sam_task_attr */
+#define TCM_SIMPLE_TAG	0x20
+#define TCM_HEAD_TAG	0x21
+#define TCM_ORDERED_TAG	0x22
+#define TCM_ACA_TAG	0x24
+
 struct se_cmd {
 	/* SAM response code being sent to initiator */
 	u8			scsi_status;
diff --git a/include/trace/events/target.h b/include/trace/events/target.h
index da9cc0f05c9..a4566806c11 100644
--- a/include/trace/events/target.h
+++ b/include/trace/events/target.h
@@ -109,10 +109,10 @@
 
 #define show_task_attribute_name(val)				\
 	__print_symbolic(val,					\
-		{ MSG_SIMPLE_TAG,	"SIMPLE"	},	\
-		{ MSG_HEAD_TAG,		"HEAD"		},	\
-		{ MSG_ORDERED_TAG,	"ORDERED"	},	\
-		{ MSG_ACA_TAG,		"ACA"		} )
+		{ TCM_SIMPLE_TAG,	"SIMPLE"	},	\
+		{ TCM_HEAD_TAG,		"HEAD"		},	\
+		{ TCM_ORDERED_TAG,	"ORDERED"	},	\
+		{ TCM_ACA_TAG,		"ACA"		} )
 
 #define show_scsi_status_name(val)				\
 	__print_symbolic(val,					\
-- 
cgit v1.2.3-70-g09d2


From e9e87eb3f9180b2b0470409b24fb39b8a1941520 Mon Sep 17 00:00:00 2001
From: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Date: Tue, 11 Nov 2014 11:14:45 +0000
Subject: xen/arm: remove handling of XENFEAT_grant_map_identity

The feature has been removed from Xen. Also Linux cannot use it on ARM32
without CONFIG_ARM_LPAE.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm/xen/enlighten.c         |  5 ---
 arch/arm/xen/mm32.c              | 85 +---------------------------------------
 include/xen/interface/features.h |  3 --
 3 files changed, 1 insertion(+), 92 deletions(-)

(limited to 'include')

diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 0e15f011f9c..c7ca936ebd9 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -261,11 +261,6 @@ static int __init xen_guest_init(void)
 
 	xen_setup_features();
 
-	if (!xen_feature(XENFEAT_grant_map_identity)) {
-		pr_warn("Please upgrade your Xen.\n"
-				"If your platform has any non-coherent DMA devices, they won't work properly.\n");
-	}
-
 	if (xen_feature(XENFEAT_dom0))
 		xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
 	else
diff --git a/arch/arm/xen/mm32.c b/arch/arm/xen/mm32.c
index 3b99860fd7a..a5a93fce913 100644
--- a/arch/arm/xen/mm32.c
+++ b/arch/arm/xen/mm32.c
@@ -5,70 +5,6 @@
 
 #include <xen/features.h>
 
-static DEFINE_PER_CPU(unsigned long, xen_mm32_scratch_virt);
-static DEFINE_PER_CPU(pte_t *, xen_mm32_scratch_ptep);
-
-static int alloc_xen_mm32_scratch_page(int cpu)
-{
-	struct page *page;
-	unsigned long virt;
-	pmd_t *pmdp;
-	pte_t *ptep;
-
-	if (per_cpu(xen_mm32_scratch_ptep, cpu) != NULL)
-		return 0;
-
-	page = alloc_page(GFP_KERNEL);
-	if (page == NULL) {
-		pr_warn("Failed to allocate xen_mm32_scratch_page for cpu %d\n", cpu);
-		return -ENOMEM;
-	}
-
-	virt = (unsigned long)__va(page_to_phys(page));
-	pmdp = pmd_offset(pud_offset(pgd_offset_k(virt), virt), virt);
-	ptep = pte_offset_kernel(pmdp, virt);
-
-	per_cpu(xen_mm32_scratch_virt, cpu) = virt;
-	per_cpu(xen_mm32_scratch_ptep, cpu) = ptep;
-
-	return 0;
-}
-
-static int xen_mm32_cpu_notify(struct notifier_block *self,
-				    unsigned long action, void *hcpu)
-{
-	int cpu = (long)hcpu;
-	switch (action) {
-	case CPU_UP_PREPARE:
-		if (alloc_xen_mm32_scratch_page(cpu))
-			return NOTIFY_BAD;
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block xen_mm32_cpu_notifier = {
-	.notifier_call	= xen_mm32_cpu_notify,
-};
-
-static void* xen_mm32_remap_page(dma_addr_t handle)
-{
-	unsigned long virt = get_cpu_var(xen_mm32_scratch_virt);
-	pte_t *ptep = __get_cpu_var(xen_mm32_scratch_ptep);
-
-	*ptep = pfn_pte(handle >> PAGE_SHIFT, PAGE_KERNEL);
-	local_flush_tlb_kernel_page(virt);
-
-	return (void*)virt;
-}
-
-static void xen_mm32_unmap(void *vaddr)
-{
-	put_cpu_var(xen_mm32_scratch_virt);
-}
-
 
 /* functions called by SWIOTLB */
 
@@ -88,13 +24,7 @@ static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
 	
 		if (!pfn_valid(pfn))
 		{
-			/* Cannot map the page, we don't know its physical address.
-			 * Return and hope for the best */
-			if (!xen_feature(XENFEAT_grant_map_identity))
-				return;
-			vaddr = xen_mm32_remap_page(handle) + offset;
-			op(vaddr, len, dir);
-			xen_mm32_unmap(vaddr - offset);
+			/* TODO: cache flush */
 		} else {
 			struct page *page = pfn_to_page(pfn);
 
@@ -181,22 +111,9 @@ void xen_dma_sync_single_for_device(struct device *hwdev,
 
 int __init xen_mm32_init(void)
 {
-	int cpu;
-
 	if (!xen_initial_domain())
 		return 0;
 
-	register_cpu_notifier(&xen_mm32_cpu_notifier);
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		if (alloc_xen_mm32_scratch_page(cpu)) {
-			put_online_cpus();
-			unregister_cpu_notifier(&xen_mm32_cpu_notifier);
-			return -ENOMEM;
-		}
-	}
-	put_online_cpus();
-
 	return 0;
 }
 arch_initcall(xen_mm32_init);
diff --git a/include/xen/interface/features.h b/include/xen/interface/features.h
index 14334d0161d..131a6ccdba2 100644
--- a/include/xen/interface/features.h
+++ b/include/xen/interface/features.h
@@ -53,9 +53,6 @@
 /* operation as Dom0 is supported */
 #define XENFEAT_dom0                      11
 
-/* Xen also maps grant references at pfn = mfn */
-#define XENFEAT_grant_map_identity        12
-
 #define XENFEAT_NR_SUBMAPS 1
 
 #endif /* __XEN_PUBLIC_FEATURES_H__ */
-- 
cgit v1.2.3-70-g09d2


From da095a996090a412c3b6292c7a8680661dca157d Mon Sep 17 00:00:00 2001
From: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Date: Fri, 21 Nov 2014 11:08:39 +0000
Subject: xen/arm: introduce GNTTABOP_cache_flush

Introduce support for new hypercall GNTTABOP_cache_flush.
Use it to perform cache flashing on pages used for dma when necessary.

If GNTTABOP_cache_flush is supported by the hypervisor, we don't need to
bounce dma map operations that involve foreign grants and non-coherent
devices.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
---
 arch/arm/xen/mm.c                   | 34 ++++++++++++++++++++++++++++++++--
 include/xen/interface/grant_table.h | 19 +++++++++++++++++++
 2 files changed, 51 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 28ebf3ecee4..351b24a979d 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -12,6 +12,7 @@
 #include <linux/swiotlb.h>
 
 #include <xen/xen.h>
+#include <xen/interface/grant_table.h>
 #include <xen/interface/memory.h>
 #include <xen/swiotlb-xen.h>
 
@@ -24,12 +25,14 @@ enum dma_cache_op {
        DMA_UNMAP,
        DMA_MAP,
 };
+static bool hypercall_cflush = false;
 
 /* functions called by SWIOTLB */
 
 static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
 	size_t size, enum dma_data_direction dir, enum dma_cache_op op)
 {
+	struct gnttab_cache_flush cflush;
 	unsigned long pfn;
 	size_t left = size;
 
@@ -39,7 +42,26 @@ static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
 	do {
 		size_t len = left;
 	
-		/* TODO: cache flush */
+		/* buffers in highmem or foreign pages cannot cross page
+		 * boundaries */
+		if (len + offset > PAGE_SIZE)
+			len = PAGE_SIZE - offset;
+
+		cflush.op = 0;
+		cflush.a.dev_bus_addr = pfn << PAGE_SHIFT;
+		cflush.offset = offset;
+		cflush.length = len;
+
+		if (op == DMA_UNMAP && dir != DMA_TO_DEVICE)
+			cflush.op = GNTTAB_CACHE_INVAL;
+		if (op == DMA_MAP) {
+			if (dir == DMA_FROM_DEVICE)
+				cflush.op = GNTTAB_CACHE_INVAL;
+			else
+				cflush.op = GNTTAB_CACHE_CLEAN;
+		}
+		if (cflush.op)
+			HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
 
 		offset = 0;
 		pfn++;
@@ -104,7 +126,7 @@ bool xen_arch_need_swiotlb(struct device *dev,
 			   unsigned long pfn,
 			   unsigned long mfn)
 {
-	return ((pfn != mfn) && !is_device_dma_coherent(dev));
+	return (!hypercall_cflush && (pfn != mfn) && !is_device_dma_coherent(dev));
 }
 
 int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
@@ -147,10 +169,18 @@ static struct dma_map_ops xen_swiotlb_dma_ops = {
 
 int __init xen_mm_init(void)
 {
+	struct gnttab_cache_flush cflush;
 	if (!xen_initial_domain())
 		return 0;
 	xen_swiotlb_init(1, false);
 	xen_dma_ops = &xen_swiotlb_dma_ops;
+
+	cflush.op = 0;
+	cflush.a.dev_bus_addr = 0;
+	cflush.offset = 0;
+	cflush.length = 0;
+	if (HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1) != -ENOSYS)
+		hypercall_cflush = true;
 	return 0;
 }
 arch_initcall(xen_mm_init);
diff --git a/include/xen/interface/grant_table.h b/include/xen/interface/grant_table.h
index e40fae9bf11..bcce56439d6 100644
--- a/include/xen/interface/grant_table.h
+++ b/include/xen/interface/grant_table.h
@@ -478,6 +478,25 @@ struct gnttab_get_version {
 };
 DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_version);
 
+/*
+ * Issue one or more cache maintenance operations on a portion of a
+ * page granted to the calling domain by a foreign domain.
+ */
+#define GNTTABOP_cache_flush          12
+struct gnttab_cache_flush {
+    union {
+        uint64_t dev_bus_addr;
+        grant_ref_t ref;
+    } a;
+    uint16_t offset;   /* offset from start of grant */
+    uint16_t length;   /* size within the grant */
+#define GNTTAB_CACHE_CLEAN          (1<<0)
+#define GNTTAB_CACHE_INVAL          (1<<1)
+#define GNTTAB_CACHE_SOURCE_GREF    (1<<31)
+    uint32_t op;
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush);
+
 /*
  * Bitfield values for update_pin_status.flags.
  */
-- 
cgit v1.2.3-70-g09d2


From ac8010221d3fa8697151dfe9a1bb2c504adc68c1 Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Wed, 3 Dec 2014 16:40:27 -0500
Subject: driver core: Provide an wrapper around the mutex to do lockdep
 warnings

Instead of open-coding it in drivers that want to double check
that their functions are indeed holding the device lock.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Suggested-by: David Vrabel <david.vrabel@citrix.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
---
 drivers/xen/xen-pciback/pci_stub.c | 2 +-
 include/linux/device.h             | 5 +++++
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c
index 9cbe1a31c1e..8b77089edda 100644
--- a/drivers/xen/xen-pciback/pci_stub.c
+++ b/drivers/xen/xen-pciback/pci_stub.c
@@ -278,7 +278,7 @@ void pcistub_put_pci_dev(struct pci_dev *dev)
 	/* Cleanup our device
 	 * (so it's ready for the next domain)
 	 */
-	lockdep_assert_held(&dev->dev.mutex);
+	device_lock_assert(&dev->dev);
 	__pci_reset_function_locked(dev);
 	pci_restore_state(dev);
 
diff --git a/include/linux/device.h b/include/linux/device.h
index ce1f21608b1..41d6a7555c6 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -911,6 +911,11 @@ static inline void device_unlock(struct device *dev)
 	mutex_unlock(&dev->mutex);
 }
 
+static inline void device_lock_assert(struct device *dev)
+{
+	lockdep_assert_held(&dev->mutex);
+}
+
 void driver_init(void);
 
 /*
-- 
cgit v1.2.3-70-g09d2


From 98d9b271250bd83337e3ed66d63e7deefcda8712 Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Wed, 3 Dec 2014 16:40:31 -0500
Subject: PCI: Expose pci_load_saved_state for public consumption.

We have the pci_load_and_free_saved_state, and pci_store_saved_state
but are missing the functionality to just load the state
multiple times in the PCI device without having to free/save
the state.

This patch makes it possible to use this function.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
---
 drivers/pci/pci.c   | 5 +++--
 include/linux/pci.h | 2 ++
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 625a4ace10b..f00a9d63fd7 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1142,8 +1142,8 @@ EXPORT_SYMBOL_GPL(pci_store_saved_state);
  * @dev: PCI device that we're dealing with
  * @state: Saved state returned from pci_store_saved_state()
  */
-static int pci_load_saved_state(struct pci_dev *dev,
-				struct pci_saved_state *state)
+int pci_load_saved_state(struct pci_dev *dev,
+			 struct pci_saved_state *state)
 {
 	struct pci_cap_saved_data *cap;
 
@@ -1171,6 +1171,7 @@ static int pci_load_saved_state(struct pci_dev *dev,
 	dev->state_saved = true;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pci_load_saved_state);
 
 /**
  * pci_load_and_free_saved_state - Reload the save state pointed to by state,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 4c8ac5fcc22..42ae347d3fc 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1004,6 +1004,8 @@ void __iomem __must_check *pci_platform_rom(struct pci_dev *pdev, size_t *size);
 int pci_save_state(struct pci_dev *dev);
 void pci_restore_state(struct pci_dev *dev);
 struct pci_saved_state *pci_store_saved_state(struct pci_dev *dev);
+int pci_load_saved_state(struct pci_dev *dev,
+			 struct pci_saved_state *state);
 int pci_load_and_free_saved_state(struct pci_dev *dev,
 				  struct pci_saved_state **state);
 struct pci_cap_saved_state *pci_find_saved_cap(struct pci_dev *dev, char cap);
-- 
cgit v1.2.3-70-g09d2


From d4ae84a02bc65cec29608bc417a969fc2ec75449 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Mon, 1 Dec 2014 17:29:25 +0000
Subject: kvm: search_memslots: add simple LRU memslot caching

In typical guest boot workload only 2-3 memslots are used
extensively, and at that it's mostly the same memslot
lookup operation.

Adding LRU cache improves average lookup time from
46 to 28 cycles (~40%) for this workload.

Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 231dd947222..1a371447fd4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -353,6 +353,7 @@ struct kvm_memslots {
 	struct kvm_memory_slot memslots[KVM_MEM_SLOTS_NUM];
 	/* The mapping table from slot id to the index in memslots[]. */
 	short id_to_index[KVM_MEM_SLOTS_NUM];
+	atomic_t lru_slot;
 };
 
 struct kvm {
@@ -790,12 +791,19 @@ static inline void kvm_guest_exit(void)
 static inline struct kvm_memory_slot *
 search_memslots(struct kvm_memslots *slots, gfn_t gfn)
 {
-	struct kvm_memory_slot *memslot;
+	int slot = atomic_read(&slots->lru_slot);
+	struct kvm_memory_slot *memslot = &slots->memslots[slot];
+
+	if (gfn >= memslot->base_gfn &&
+	    gfn < memslot->base_gfn + memslot->npages)
+		return memslot;
 
 	kvm_for_each_memslot(memslot, slots)
 		if (gfn >= memslot->base_gfn &&
-		      gfn < memslot->base_gfn + memslot->npages)
+		      gfn < memslot->base_gfn + memslot->npages) {
+			atomic_set(&slots->lru_slot, memslot - slots->memslots);
 			return memslot;
+		}
 
 	return NULL;
 }
-- 
cgit v1.2.3-70-g09d2


From 9c1a5d38780e652275aa55362dbee0d7e827e069 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Mon, 1 Dec 2014 17:29:27 +0000
Subject: kvm: optimize GFN to memslot lookup with large slots amount

Current linear search doesn't scale well when
large amount of memslots is used and looked up slot
is not in the beginning memslots array.
Taking in account that memslots don't overlap, it's
possible to switch sorting order of memslots array from
'npages' to 'base_gfn' and use binary search for
memslot lookup by GFN.

As result of switching to binary search lookup times
are reduced with large amount of memslots.

Following is a table of search_memslot() cycles
during WS2008R2 guest boot.

                         boot,          boot + ~10 min
                         mostly same    of using it,
                         slot lookup    randomized lookup
                max      average        average
                cycles   cycles         cycles

13 slots      : 1450       28           30

13 slots      : 1400       30           40
binary search

117 slots     : 13000      30           460

117 slots     : 2000       35           180
binary search

Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 34 ++++++++++++++++++++++------------
 virt/kvm/kvm_main.c      |  8 +++++++-
 2 files changed, 29 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1a371447fd4..193bca68372 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -354,6 +354,7 @@ struct kvm_memslots {
 	/* The mapping table from slot id to the index in memslots[]. */
 	short id_to_index[KVM_MEM_SLOTS_NUM];
 	atomic_t lru_slot;
+	int used_slots;
 };
 
 struct kvm {
@@ -791,19 +792,28 @@ static inline void kvm_guest_exit(void)
 static inline struct kvm_memory_slot *
 search_memslots(struct kvm_memslots *slots, gfn_t gfn)
 {
+	int start = 0, end = slots->used_slots;
 	int slot = atomic_read(&slots->lru_slot);
-	struct kvm_memory_slot *memslot = &slots->memslots[slot];
-
-	if (gfn >= memslot->base_gfn &&
-	    gfn < memslot->base_gfn + memslot->npages)
-		return memslot;
-
-	kvm_for_each_memslot(memslot, slots)
-		if (gfn >= memslot->base_gfn &&
-		      gfn < memslot->base_gfn + memslot->npages) {
-			atomic_set(&slots->lru_slot, memslot - slots->memslots);
-			return memslot;
-		}
+	struct kvm_memory_slot *memslots = slots->memslots;
+
+	if (gfn >= memslots[slot].base_gfn &&
+	    gfn < memslots[slot].base_gfn + memslots[slot].npages)
+		return &memslots[slot];
+
+	while (start < end) {
+		slot = start + (end - start) / 2;
+
+		if (gfn >= memslots[slot].base_gfn)
+			end = slot;
+		else
+			start = slot + 1;
+	}
+
+	if (gfn >= memslots[start].base_gfn &&
+	    gfn < memslots[start].base_gfn + memslots[start].npages) {
+		atomic_set(&slots->lru_slot, start);
+		return &memslots[start];
+	}
 
 	return NULL;
 }
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 162817f853e..759af6596a0 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -679,8 +679,14 @@ static void update_memslots(struct kvm_memslots *slots,
 	struct kvm_memory_slot *mslots = slots->memslots;
 
 	WARN_ON(mslots[i].id != id);
-	if (!new->npages)
+	if (!new->npages) {
 		new->base_gfn = 0;
+		if (mslots[i].npages)
+			slots->used_slots--;
+	} else {
+		if (!mslots[i].npages)
+			slots->used_slots++;
+	}
 
 	while (i < KVM_MEM_SLOTS_NUM - 1 &&
 	       new->base_gfn <= mslots[i + 1].base_gfn) {
-- 
cgit v1.2.3-70-g09d2


From 0b4bc768dc289731983ba5223555ffabe08eefdd Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@iki.fi>
Date: Wed, 15 Oct 2014 13:38:15 -0300
Subject: [media] v4l: Add V4L2_SEL_TGT_NATIVE_SIZE selection target

The V4L2_SEL_TGT_NATIVE_SIZE target is used to denote e.g. the size of a
sensor's pixel array.

Signed-off-by: Sakari Ailus <sakari.ailus@iki.fi>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 Documentation/DocBook/media/v4l/selections-common.xml | 16 ++++++++++++++++
 include/uapi/linux/v4l2-common.h                      |  2 ++
 2 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/Documentation/DocBook/media/v4l/selections-common.xml b/Documentation/DocBook/media/v4l/selections-common.xml
index 7502f784b8c..d6d56fb6f9c 100644
--- a/Documentation/DocBook/media/v4l/selections-common.xml
+++ b/Documentation/DocBook/media/v4l/selections-common.xml
@@ -62,6 +62,22 @@
 	    <entry>Yes</entry>
 	    <entry>Yes</entry>
 	  </row>
+	  <row>
+	    <entry><constant>V4L2_SEL_TGT_NATIVE_SIZE</constant></entry>
+	    <entry>0x0003</entry>
+	    <entry>The native size of the device, e.g. a sensor's
+	    pixel array. <structfield>left</structfield> and
+	    <structfield>top</structfield> fields are zero for this
+	    target. Setting the native size will generally only make
+	    sense for memory to memory devices where the software can
+	    create a canvas of a given size in which for example a
+	    video frame can be composed. In that case
+	    V4L2_SEL_TGT_NATIVE_SIZE can be used to configure the size
+	    of that canvas.
+	    </entry>
+	    <entry>Yes</entry>
+	    <entry>Yes</entry>
+	  </row>
 	  <row>
 	    <entry><constant>V4L2_SEL_TGT_COMPOSE</constant></entry>
 	    <entry>0x0100</entry>
diff --git a/include/uapi/linux/v4l2-common.h b/include/uapi/linux/v4l2-common.h
index 2f6f8cafe77..15273987093 100644
--- a/include/uapi/linux/v4l2-common.h
+++ b/include/uapi/linux/v4l2-common.h
@@ -43,6 +43,8 @@
 #define V4L2_SEL_TGT_CROP_DEFAULT	0x0001
 /* Cropping bounds */
 #define V4L2_SEL_TGT_CROP_BOUNDS	0x0002
+/* Native frame size */
+#define V4L2_SEL_TGT_NATIVE_SIZE	0x0003
 /* Current composing area */
 #define V4L2_SEL_TGT_COMPOSE		0x0100
 /* Default composing area */
-- 
cgit v1.2.3-70-g09d2


From 8af0345926c8cdbbf80102aa3eab8a6519c23272 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@iki.fi>
Date: Tue, 18 Nov 2014 02:27:00 -0300
Subject: [media] v4l: Add input and output capability flags for native size
 setting

Add input and output capability flags for setting native size of the device,
and document them.

Signed-off-by: Sakari Ailus <sakari.ailus@iki.fi>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 Documentation/DocBook/media/v4l/vidioc-enuminput.xml  | 8 ++++++++
 Documentation/DocBook/media/v4l/vidioc-enumoutput.xml | 8 ++++++++
 include/uapi/linux/videodev2.h                        | 2 ++
 3 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/Documentation/DocBook/media/v4l/vidioc-enuminput.xml b/Documentation/DocBook/media/v4l/vidioc-enuminput.xml
index 493a39a8ef2..603fecef908 100644
--- a/Documentation/DocBook/media/v4l/vidioc-enuminput.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-enuminput.xml
@@ -287,6 +287,14 @@ input/output interface to linux-media@vger.kernel.org on 19 Oct 2009.
 	    <entry>0x00000004</entry>
 	    <entry>This input supports setting the TV standard by using VIDIOC_S_STD.</entry>
 	  </row>
+	  <row>
+	    <entry><constant>V4L2_IN_CAP_NATIVE_SIZE</constant></entry>
+	    <entry>0x00000008</entry>
+	    <entry>This input supports setting the native size using
+	    the <constant>V4L2_SEL_TGT_NATIVE_SIZE</constant>
+	    selection target, see <xref
+	    linkend="v4l2-selections-common"/>.</entry>
+	  </row>
 	</tbody>
       </tgroup>
     </table>
diff --git a/Documentation/DocBook/media/v4l/vidioc-enumoutput.xml b/Documentation/DocBook/media/v4l/vidioc-enumoutput.xml
index 2654e097df3..773fb1258c2 100644
--- a/Documentation/DocBook/media/v4l/vidioc-enumoutput.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-enumoutput.xml
@@ -172,6 +172,14 @@ input/output interface to linux-media@vger.kernel.org on 19 Oct 2009.
 	    <entry>0x00000004</entry>
 	    <entry>This output supports setting the TV standard by using VIDIOC_S_STD.</entry>
 	  </row>
+	  <row>
+	    <entry><constant>V4L2_OUT_CAP_NATIVE_SIZE</constant></entry>
+	    <entry>0x00000008</entry>
+	    <entry>This output supports setting the native size using
+	    the <constant>V4L2_SEL_TGT_NATIVE_SIZE</constant>
+	    selection target, see <xref
+	    linkend="v4l2-selections-common"/>.</entry>
+	  </row>
 	</tbody>
       </tgroup>
     </table>
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index ced659e1b9f..d279c1b75cf 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -1324,6 +1324,7 @@ struct v4l2_input {
 #define V4L2_IN_CAP_DV_TIMINGS		0x00000002 /* Supports S_DV_TIMINGS */
 #define V4L2_IN_CAP_CUSTOM_TIMINGS	V4L2_IN_CAP_DV_TIMINGS /* For compatibility */
 #define V4L2_IN_CAP_STD			0x00000004 /* Supports S_STD */
+#define V4L2_IN_CAP_NATIVE_SIZE		0x00000008 /* Supports setting native size */
 
 /*
  *	V I D E O   O U T P U T S
@@ -1347,6 +1348,7 @@ struct v4l2_output {
 #define V4L2_OUT_CAP_DV_TIMINGS		0x00000002 /* Supports S_DV_TIMINGS */
 #define V4L2_OUT_CAP_CUSTOM_TIMINGS	V4L2_OUT_CAP_DV_TIMINGS /* For compatibility */
 #define V4L2_OUT_CAP_STD		0x00000004 /* Supports S_STD */
+#define V4L2_OUT_CAP_NATIVE_SIZE	0x00000008 /* Supports setting native size */
 
 /*
  *	C O N T R O L S
-- 
cgit v1.2.3-70-g09d2


From 8918465163171322c77a19d5258a95f56d89d2e4 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Wed, 16 Apr 2014 09:24:44 +0200
Subject: memory: Add NVIDIA Tegra memory controller support

The memory controller on NVIDIA Tegra exposes various knobs that can be
used to tune the behaviour of the clients attached to it.

Currently this driver sets up the latency allowance registers to the HW
defaults. Eventually an API should be exported by this driver (via a
custom API or a generic subsystem) to allow clients to register latency
requirements.

This driver also registers an IOMMU (SMMU) that's implemented by the
memory controller. It is supported on Tegra30, Tegra114 and Tegra124
currently. Tegra20 has a GART instead.

The Tegra SMMU operates on memory clients and SWGROUPs. A memory client
is a unidirectional, special-purpose DMA master. A SWGROUP represents a
set of memory clients that form a logical functional unit corresponding
to a single device. Typically a device has two clients: one client for
read transactions and one client for write transactions, but there are
also devices that have only read clients, but many of them (such as the
display controllers).

Because there is no 1:1 relationship between memory clients and devices
the driver keeps a table of memory clients and the SWGROUPs that they
belong to per SoC. Note that this is an exception and due to the fact
that the SMMU is tightly integrated with the rest of the Tegra SoC. The
use of these tables is discouraged in drivers for generic IOMMU devices
such as the ARM SMMU because the same IOMMU could be used in any number
of SoCs and keeping such tables for each SoC would not scale.

Acked-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/iommu/Kconfig                    |   12 +-
 drivers/iommu/tegra-smmu.c               | 1610 ++++++++++--------------------
 drivers/memory/Kconfig                   |   12 +-
 drivers/memory/Makefile                  |    3 +-
 drivers/memory/tegra/Kconfig             |    7 +
 drivers/memory/tegra/Makefile            |    7 +
 drivers/memory/tegra/mc.c                |  301 ++++++
 drivers/memory/tegra/mc.h                |   40 +
 drivers/memory/tegra/tegra114.c          |  948 ++++++++++++++++++
 drivers/memory/tegra/tegra124.c          |  995 ++++++++++++++++++
 drivers/memory/tegra/tegra30.c           |  970 ++++++++++++++++++
 drivers/memory/tegra30-mc.c              |  378 -------
 include/dt-bindings/memory/tegra114-mc.h |   25 +
 include/dt-bindings/memory/tegra124-mc.h |   31 +
 include/dt-bindings/memory/tegra30-mc.h  |   24 +
 include/soc/tegra/mc.h                   |  107 ++
 16 files changed, 3988 insertions(+), 1482 deletions(-)
 create mode 100644 drivers/memory/tegra/Kconfig
 create mode 100644 drivers/memory/tegra/Makefile
 create mode 100644 drivers/memory/tegra/mc.c
 create mode 100644 drivers/memory/tegra/mc.h
 create mode 100644 drivers/memory/tegra/tegra114.c
 create mode 100644 drivers/memory/tegra/tegra124.c
 create mode 100644 drivers/memory/tegra/tegra30.c
 delete mode 100644 drivers/memory/tegra30-mc.c
 create mode 100644 include/dt-bindings/memory/tegra114-mc.h
 create mode 100644 include/dt-bindings/memory/tegra124-mc.h
 create mode 100644 include/dt-bindings/memory/tegra30-mc.h
 create mode 100644 include/soc/tegra/mc.h

(limited to 'include')

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index dd5112265cc..6dbfbc20949 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -163,14 +163,14 @@ config TEGRA_IOMMU_GART
 	  hardware included on Tegra SoCs.
 
 config TEGRA_IOMMU_SMMU
-	bool "Tegra SMMU IOMMU Support"
-	depends on ARCH_TEGRA && TEGRA_AHB
+	bool "NVIDIA Tegra SMMU Support"
+	depends on ARCH_TEGRA
+	depends on TEGRA_AHB
+	depends on TEGRA_MC
 	select IOMMU_API
 	help
-	  Enables support for remapping discontiguous physical memory
-	  shared with the operating system into contiguous I/O virtual
-	  space through the SMMU (System Memory Management Unit)
-	  hardware included on Tegra SoCs.
+	  This driver supports the IOMMU hardware (SMMU) found on NVIDIA Tegra
+	  SoCs (Tegra30 up to Tegra124).
 
 config EXYNOS_IOMMU
 	bool "Exynos IOMMU Support"
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 73e845a6692..6e134c7c227 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -1,1296 +1,732 @@
 /*
- * IOMMU API for SMMU in Tegra30
+ * Copyright (C) 2011-2014 NVIDIA CORPORATION.  All rights reserved.
  *
- * Copyright (c) 2011-2013, NVIDIA CORPORATION.  All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
  */
 
-#define pr_fmt(fmt)	"%s(): " fmt, __func__
-
 #include <linux/err.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/spinlock.h>
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
-#include <linux/mm.h>
-#include <linux/pagemap.h>
-#include <linux/device.h>
-#include <linux/sched.h>
 #include <linux/iommu.h>
-#include <linux/io.h>
+#include <linux/kernel.h>
 #include <linux/of.h>
-#include <linux/of_iommu.h>
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
 
 #include <soc/tegra/ahb.h>
+#include <soc/tegra/mc.h>
 
-#include <asm/page.h>
-#include <asm/cacheflush.h>
-
-enum smmu_hwgrp {
-	HWGRP_AFI,
-	HWGRP_AVPC,
-	HWGRP_DC,
-	HWGRP_DCB,
-	HWGRP_EPP,
-	HWGRP_G2,
-	HWGRP_HC,
-	HWGRP_HDA,
-	HWGRP_ISP,
-	HWGRP_MPE,
-	HWGRP_NV,
-	HWGRP_NV2,
-	HWGRP_PPCS,
-	HWGRP_SATA,
-	HWGRP_VDE,
-	HWGRP_VI,
-
-	HWGRP_COUNT,
-
-	HWGRP_END = ~0,
-};
+struct tegra_smmu {
+	void __iomem *regs;
+	struct device *dev;
 
-#define HWG_AFI		(1 << HWGRP_AFI)
-#define HWG_AVPC	(1 << HWGRP_AVPC)
-#define HWG_DC		(1 << HWGRP_DC)
-#define HWG_DCB		(1 << HWGRP_DCB)
-#define HWG_EPP		(1 << HWGRP_EPP)
-#define HWG_G2		(1 << HWGRP_G2)
-#define HWG_HC		(1 << HWGRP_HC)
-#define HWG_HDA		(1 << HWGRP_HDA)
-#define HWG_ISP		(1 << HWGRP_ISP)
-#define HWG_MPE		(1 << HWGRP_MPE)
-#define HWG_NV		(1 << HWGRP_NV)
-#define HWG_NV2		(1 << HWGRP_NV2)
-#define HWG_PPCS	(1 << HWGRP_PPCS)
-#define HWG_SATA	(1 << HWGRP_SATA)
-#define HWG_VDE		(1 << HWGRP_VDE)
-#define HWG_VI		(1 << HWGRP_VI)
-
-/* bitmap of the page sizes currently supported */
-#define SMMU_IOMMU_PGSIZES	(SZ_4K)
-
-#define SMMU_CONFIG				0x10
-#define SMMU_CONFIG_DISABLE			0
-#define SMMU_CONFIG_ENABLE			1
-
-/* REVISIT: To support multiple MCs */
-enum {
-	_MC = 0,
-};
+	struct tegra_mc *mc;
+	const struct tegra_smmu_soc *soc;
 
-enum {
-	_TLB = 0,
-	_PTC,
-};
+	unsigned long *asids;
+	struct mutex lock;
 
-#define SMMU_CACHE_CONFIG_BASE			0x14
-#define __SMMU_CACHE_CONFIG(mc, cache)		(SMMU_CACHE_CONFIG_BASE + 4 * cache)
-#define SMMU_CACHE_CONFIG(cache)		__SMMU_CACHE_CONFIG(_MC, cache)
-
-#define SMMU_CACHE_CONFIG_STATS_SHIFT		31
-#define SMMU_CACHE_CONFIG_STATS_ENABLE		(1 << SMMU_CACHE_CONFIG_STATS_SHIFT)
-#define SMMU_CACHE_CONFIG_STATS_TEST_SHIFT	30
-#define SMMU_CACHE_CONFIG_STATS_TEST		(1 << SMMU_CACHE_CONFIG_STATS_TEST_SHIFT)
-
-#define SMMU_TLB_CONFIG_HIT_UNDER_MISS__ENABLE	(1 << 29)
-#define SMMU_TLB_CONFIG_ACTIVE_LINES__VALUE	0x10
-#define SMMU_TLB_CONFIG_RESET_VAL		0x20000010
-
-#define SMMU_PTC_CONFIG_CACHE__ENABLE		(1 << 29)
-#define SMMU_PTC_CONFIG_INDEX_MAP__PATTERN	0x3f
-#define SMMU_PTC_CONFIG_RESET_VAL		0x2000003f
-
-#define SMMU_PTB_ASID				0x1c
-#define SMMU_PTB_ASID_CURRENT_SHIFT		0
-
-#define SMMU_PTB_DATA				0x20
-#define SMMU_PTB_DATA_RESET_VAL			0
-#define SMMU_PTB_DATA_ASID_NONSECURE_SHIFT	29
-#define SMMU_PTB_DATA_ASID_WRITABLE_SHIFT	30
-#define SMMU_PTB_DATA_ASID_READABLE_SHIFT	31
-
-#define SMMU_TLB_FLUSH				0x30
-#define SMMU_TLB_FLUSH_VA_MATCH_ALL		0
-#define SMMU_TLB_FLUSH_VA_MATCH_SECTION		2
-#define SMMU_TLB_FLUSH_VA_MATCH_GROUP		3
-#define SMMU_TLB_FLUSH_ASID_SHIFT		29
-#define SMMU_TLB_FLUSH_ASID_MATCH_DISABLE	0
-#define SMMU_TLB_FLUSH_ASID_MATCH_ENABLE	1
-#define SMMU_TLB_FLUSH_ASID_MATCH_SHIFT		31
-
-#define SMMU_PTC_FLUSH				0x34
-#define SMMU_PTC_FLUSH_TYPE_ALL			0
-#define SMMU_PTC_FLUSH_TYPE_ADR			1
-#define SMMU_PTC_FLUSH_ADR_SHIFT		4
-
-#define SMMU_ASID_SECURITY			0x38
-
-#define SMMU_STATS_CACHE_COUNT_BASE		0x1f0
-
-#define SMMU_STATS_CACHE_COUNT(mc, cache, hitmiss)		\
-	(SMMU_STATS_CACHE_COUNT_BASE + 8 * cache + 4 * hitmiss)
-
-#define SMMU_TRANSLATION_ENABLE_0		0x228
-#define SMMU_TRANSLATION_ENABLE_1		0x22c
-#define SMMU_TRANSLATION_ENABLE_2		0x230
-
-#define SMMU_AFI_ASID	0x238   /* PCIE */
-#define SMMU_AVPC_ASID	0x23c   /* AVP */
-#define SMMU_DC_ASID	0x240   /* Display controller */
-#define SMMU_DCB_ASID	0x244   /* Display controller B */
-#define SMMU_EPP_ASID	0x248   /* Encoder pre-processor */
-#define SMMU_G2_ASID	0x24c   /* 2D engine */
-#define SMMU_HC_ASID	0x250   /* Host1x */
-#define SMMU_HDA_ASID	0x254   /* High-def audio */
-#define SMMU_ISP_ASID	0x258   /* Image signal processor */
-#define SMMU_MPE_ASID	0x264   /* MPEG encoder */
-#define SMMU_NV_ASID	0x268   /* (3D) */
-#define SMMU_NV2_ASID	0x26c   /* (3D) */
-#define SMMU_PPCS_ASID	0x270   /* AHB */
-#define SMMU_SATA_ASID	0x278   /* SATA */
-#define SMMU_VDE_ASID	0x27c   /* Video decoder */
-#define SMMU_VI_ASID	0x280   /* Video input */
-
-#define SMMU_PDE_NEXT_SHIFT		28
-
-#define SMMU_TLB_FLUSH_VA_SECTION__MASK		0xffc00000
-#define SMMU_TLB_FLUSH_VA_SECTION__SHIFT	12 /* right shift */
-#define SMMU_TLB_FLUSH_VA_GROUP__MASK		0xffffc000
-#define SMMU_TLB_FLUSH_VA_GROUP__SHIFT		12 /* right shift */
-#define SMMU_TLB_FLUSH_VA(iova, which)	\
-	((((iova) & SMMU_TLB_FLUSH_VA_##which##__MASK) >> \
-		SMMU_TLB_FLUSH_VA_##which##__SHIFT) |	\
-	SMMU_TLB_FLUSH_VA_MATCH_##which)
-#define SMMU_PTB_ASID_CUR(n)	\
-		((n) << SMMU_PTB_ASID_CURRENT_SHIFT)
-#define SMMU_TLB_FLUSH_ASID_MATCH_disable		\
-		(SMMU_TLB_FLUSH_ASID_MATCH_DISABLE <<	\
-			SMMU_TLB_FLUSH_ASID_MATCH_SHIFT)
-#define SMMU_TLB_FLUSH_ASID_MATCH__ENABLE		\
-		(SMMU_TLB_FLUSH_ASID_MATCH_ENABLE <<	\
-			SMMU_TLB_FLUSH_ASID_MATCH_SHIFT)
-
-#define SMMU_PAGE_SHIFT 12
-#define SMMU_PAGE_SIZE	(1 << SMMU_PAGE_SHIFT)
-#define SMMU_PAGE_MASK	((1 << SMMU_PAGE_SHIFT) - 1)
-
-#define SMMU_PDIR_COUNT	1024
-#define SMMU_PDIR_SIZE	(sizeof(unsigned long) * SMMU_PDIR_COUNT)
-#define SMMU_PTBL_COUNT	1024
-#define SMMU_PTBL_SIZE	(sizeof(unsigned long) * SMMU_PTBL_COUNT)
-#define SMMU_PDIR_SHIFT	12
-#define SMMU_PDE_SHIFT	12
-#define SMMU_PTE_SHIFT	12
-#define SMMU_PFN_MASK	0x000fffff
-
-#define SMMU_ADDR_TO_PFN(addr)	((addr) >> 12)
-#define SMMU_ADDR_TO_PDN(addr)	((addr) >> 22)
-#define SMMU_PDN_TO_ADDR(pdn)	((pdn) << 22)
-
-#define _READABLE	(1 << SMMU_PTB_DATA_ASID_READABLE_SHIFT)
-#define _WRITABLE	(1 << SMMU_PTB_DATA_ASID_WRITABLE_SHIFT)
-#define _NONSECURE	(1 << SMMU_PTB_DATA_ASID_NONSECURE_SHIFT)
-#define _PDE_NEXT	(1 << SMMU_PDE_NEXT_SHIFT)
-#define _MASK_ATTR	(_READABLE | _WRITABLE | _NONSECURE)
-
-#define _PDIR_ATTR	(_READABLE | _WRITABLE | _NONSECURE)
-
-#define _PDE_ATTR	(_READABLE | _WRITABLE | _NONSECURE)
-#define _PDE_ATTR_N	(_PDE_ATTR | _PDE_NEXT)
-#define _PDE_VACANT(pdn)	(((pdn) << 10) | _PDE_ATTR)
-
-#define _PTE_ATTR	(_READABLE | _WRITABLE | _NONSECURE)
-#define _PTE_VACANT(addr)	(((addr) >> SMMU_PAGE_SHIFT) | _PTE_ATTR)
-
-#define SMMU_MK_PDIR(page, attr)	\
-		((page_to_phys(page) >> SMMU_PDIR_SHIFT) | (attr))
-#define SMMU_MK_PDE(page, attr)		\
-		(unsigned long)((page_to_phys(page) >> SMMU_PDE_SHIFT) | (attr))
-#define SMMU_EX_PTBL_PAGE(pde)		\
-		pfn_to_page((unsigned long)(pde) & SMMU_PFN_MASK)
-#define SMMU_PFN_TO_PTE(pfn, attr)	(unsigned long)((pfn) | (attr))
-
-#define SMMU_ASID_ENABLE(asid)	((asid) | (1 << 31))
-#define SMMU_ASID_DISABLE	0
-#define SMMU_ASID_ASID(n)	((n) & ~SMMU_ASID_ENABLE(0))
-
-#define NUM_SMMU_REG_BANKS	3
-
-#define smmu_client_enable_hwgrp(c, m)	smmu_client_set_hwgrp(c, m, 1)
-#define smmu_client_disable_hwgrp(c)	smmu_client_set_hwgrp(c, 0, 0)
-#define __smmu_client_enable_hwgrp(c, m) __smmu_client_set_hwgrp(c, m, 1)
-#define __smmu_client_disable_hwgrp(c)	__smmu_client_set_hwgrp(c, 0, 0)
-
-#define HWGRP_INIT(client) [HWGRP_##client] = SMMU_##client##_ASID
-
-static const u32 smmu_hwgrp_asid_reg[] = {
-	HWGRP_INIT(AFI),
-	HWGRP_INIT(AVPC),
-	HWGRP_INIT(DC),
-	HWGRP_INIT(DCB),
-	HWGRP_INIT(EPP),
-	HWGRP_INIT(G2),
-	HWGRP_INIT(HC),
-	HWGRP_INIT(HDA),
-	HWGRP_INIT(ISP),
-	HWGRP_INIT(MPE),
-	HWGRP_INIT(NV),
-	HWGRP_INIT(NV2),
-	HWGRP_INIT(PPCS),
-	HWGRP_INIT(SATA),
-	HWGRP_INIT(VDE),
-	HWGRP_INIT(VI),
+	struct list_head list;
 };
-#define HWGRP_ASID_REG(x) (smmu_hwgrp_asid_reg[x])
 
-/*
- * Per client for address space
- */
-struct smmu_client {
-	struct device		*dev;
-	struct list_head	list;
-	struct smmu_as		*as;
-	u32			hwgrp;
+struct tegra_smmu_as {
+	struct iommu_domain *domain;
+	struct tegra_smmu *smmu;
+	unsigned int use_count;
+	struct page *count;
+	struct page *pd;
+	unsigned id;
+	u32 attr;
 };
 
-/*
- * Per address space
- */
-struct smmu_as {
-	struct smmu_device	*smmu;	/* back pointer to container */
-	unsigned int		asid;
-	spinlock_t		lock;	/* for pagetable */
-	struct page		*pdir_page;
-	unsigned long		pdir_attr;
-	unsigned long		pde_attr;
-	unsigned long		pte_attr;
-	unsigned int		*pte_count;
-
-	struct list_head	client;
-	spinlock_t		client_lock; /* for client list */
-};
+static inline void smmu_writel(struct tegra_smmu *smmu, u32 value,
+			       unsigned long offset)
+{
+	writel(value, smmu->regs + offset);
+}
 
-struct smmu_debugfs_info {
-	struct smmu_device *smmu;
-	int mc;
-	int cache;
-};
+static inline u32 smmu_readl(struct tegra_smmu *smmu, unsigned long offset)
+{
+	return readl(smmu->regs + offset);
+}
 
-/*
- * Per SMMU device - IOMMU device
- */
-struct smmu_device {
-	void __iomem	*regbase;	/* register offset base */
-	void __iomem	**regs;		/* register block start address array */
-	void __iomem	**rege;		/* register block end address array */
-	int		nregs;		/* number of register blocks */
-
-	unsigned long	iovmm_base;	/* remappable base address */
-	unsigned long	page_count;	/* total remappable size */
-	spinlock_t	lock;
-	char		*name;
-	struct device	*dev;
-	struct page *avp_vector_page;	/* dummy page shared by all AS's */
+#define SMMU_CONFIG 0x010
+#define  SMMU_CONFIG_ENABLE (1 << 0)
 
-	/*
-	 * Register image savers for suspend/resume
-	 */
-	unsigned long translation_enable_0;
-	unsigned long translation_enable_1;
-	unsigned long translation_enable_2;
-	unsigned long asid_security;
+#define SMMU_TLB_CONFIG 0x14
+#define  SMMU_TLB_CONFIG_HIT_UNDER_MISS (1 << 29)
+#define  SMMU_TLB_CONFIG_ROUND_ROBIN_ARBITRATION (1 << 28)
+#define  SMMU_TLB_CONFIG_ACTIVE_LINES(x) ((x) & 0x3f)
 
-	struct dentry *debugfs_root;
-	struct smmu_debugfs_info *debugfs_info;
+#define SMMU_PTC_CONFIG 0x18
+#define  SMMU_PTC_CONFIG_ENABLE (1 << 29)
+#define  SMMU_PTC_CONFIG_REQ_LIMIT(x) (((x) & 0x0f) << 24)
+#define  SMMU_PTC_CONFIG_INDEX_MAP(x) ((x) & 0x3f)
 
-	struct device_node *ahb;
+#define SMMU_PTB_ASID 0x01c
+#define  SMMU_PTB_ASID_VALUE(x) ((x) & 0x7f)
 
-	int		num_as;
-	struct smmu_as	as[0];		/* Run-time allocated array */
-};
+#define SMMU_PTB_DATA 0x020
+#define  SMMU_PTB_DATA_VALUE(page, attr) (page_to_phys(page) >> 12 | (attr))
 
-static struct smmu_device *smmu_handle; /* unique for a system */
+#define SMMU_MK_PDE(page, attr) (page_to_phys(page) >> SMMU_PTE_SHIFT | (attr))
 
-/*
- *	SMMU register accessors
- */
-static bool inline smmu_valid_reg(struct smmu_device *smmu,
-				  void __iomem *addr)
-{
-	int i;
+#define SMMU_TLB_FLUSH 0x030
+#define  SMMU_TLB_FLUSH_VA_MATCH_ALL     (0 << 0)
+#define  SMMU_TLB_FLUSH_VA_MATCH_SECTION (2 << 0)
+#define  SMMU_TLB_FLUSH_VA_MATCH_GROUP   (3 << 0)
+#define  SMMU_TLB_FLUSH_ASID(x)          (((x) & 0x7f) << 24)
+#define  SMMU_TLB_FLUSH_VA_SECTION(addr) ((((addr) & 0xffc00000) >> 12) | \
+					  SMMU_TLB_FLUSH_VA_MATCH_SECTION)
+#define  SMMU_TLB_FLUSH_VA_GROUP(addr)   ((((addr) & 0xffffc000) >> 12) | \
+					  SMMU_TLB_FLUSH_VA_MATCH_GROUP)
+#define  SMMU_TLB_FLUSH_ASID_MATCH       (1 << 31)
 
-	for (i = 0; i < smmu->nregs; i++) {
-		if (addr < smmu->regs[i])
-			break;
-		if (addr <= smmu->rege[i])
-			return true;
-	}
+#define SMMU_PTC_FLUSH 0x034
+#define  SMMU_PTC_FLUSH_TYPE_ALL (0 << 0)
+#define  SMMU_PTC_FLUSH_TYPE_ADR (1 << 0)
 
-	return false;
-}
+#define SMMU_PTC_FLUSH_HI 0x9b8
+#define  SMMU_PTC_FLUSH_HI_MASK 0x3
 
-static inline u32 smmu_read(struct smmu_device *smmu, size_t offs)
-{
-	void __iomem *addr = smmu->regbase + offs;
+/* per-SWGROUP SMMU_*_ASID register */
+#define SMMU_ASID_ENABLE (1 << 31)
+#define SMMU_ASID_MASK 0x7f
+#define SMMU_ASID_VALUE(x) ((x) & SMMU_ASID_MASK)
 
-	BUG_ON(!smmu_valid_reg(smmu, addr));
+/* page table definitions */
+#define SMMU_NUM_PDE 1024
+#define SMMU_NUM_PTE 1024
 
-	return readl(addr);
-}
+#define SMMU_SIZE_PD (SMMU_NUM_PDE * 4)
+#define SMMU_SIZE_PT (SMMU_NUM_PTE * 4)
 
-static inline void smmu_write(struct smmu_device *smmu, u32 val, size_t offs)
-{
-	void __iomem *addr = smmu->regbase + offs;
+#define SMMU_PDE_SHIFT 22
+#define SMMU_PTE_SHIFT 12
 
-	BUG_ON(!smmu_valid_reg(smmu, addr));
+#define SMMU_PFN_MASK 0x000fffff
 
-	writel(val, addr);
-}
+#define SMMU_PD_READABLE	(1 << 31)
+#define SMMU_PD_WRITABLE	(1 << 30)
+#define SMMU_PD_NONSECURE	(1 << 29)
 
-#define VA_PAGE_TO_PA(va, page)	\
-	(page_to_phys(page) + ((unsigned long)(va) & ~PAGE_MASK))
+#define SMMU_PDE_READABLE	(1 << 31)
+#define SMMU_PDE_WRITABLE	(1 << 30)
+#define SMMU_PDE_NONSECURE	(1 << 29)
+#define SMMU_PDE_NEXT		(1 << 28)
 
-#define FLUSH_CPU_DCACHE(va, page, size)	\
-	do {	\
-		unsigned long _pa_ = VA_PAGE_TO_PA(va, page);		\
-		__cpuc_flush_dcache_area((void *)(va), (size_t)(size));	\
-		outer_flush_range(_pa_, _pa_+(size_t)(size));		\
-	} while (0)
+#define SMMU_PTE_READABLE	(1 << 31)
+#define SMMU_PTE_WRITABLE	(1 << 30)
+#define SMMU_PTE_NONSECURE	(1 << 29)
 
-/*
- * Any interaction between any block on PPSB and a block on APB or AHB
- * must have these read-back barriers to ensure the APB/AHB bus
- * transaction is complete before initiating activity on the PPSB
- * block.
- */
-#define FLUSH_SMMU_REGS(smmu)	smmu_read(smmu, SMMU_CONFIG)
+#define SMMU_PDE_ATTR		(SMMU_PDE_READABLE | SMMU_PDE_WRITABLE | \
+				 SMMU_PDE_NONSECURE)
+#define SMMU_PTE_ATTR		(SMMU_PTE_READABLE | SMMU_PTE_WRITABLE | \
+				 SMMU_PTE_NONSECURE)
 
-#define smmu_client_hwgrp(c) (u32)((c)->dev->platform_data)
-
-static int __smmu_client_set_hwgrp(struct smmu_client *c,
-				   unsigned long map, int on)
+static inline void smmu_flush_ptc(struct tegra_smmu *smmu, struct page *page,
+				  unsigned long offset)
 {
-	int i;
-	struct smmu_as *as = c->as;
-	u32 val, offs, mask = SMMU_ASID_ENABLE(as->asid);
-	struct smmu_device *smmu = as->smmu;
-
-	WARN_ON(!on && map);
-	if (on && !map)
-		return -EINVAL;
-	if (!on)
-		map = smmu_client_hwgrp(c);
-
-	for_each_set_bit(i, &map, HWGRP_COUNT) {
-		offs = HWGRP_ASID_REG(i);
-		val = smmu_read(smmu, offs);
-		if (on) {
-			if (WARN_ON(val & mask))
-				goto err_hw_busy;
-			val |= mask;
-		} else {
-			WARN_ON((val & mask) == mask);
-			val &= ~mask;
+	phys_addr_t phys = page ? page_to_phys(page) : 0;
+	u32 value;
+
+	if (page) {
+		offset &= ~(smmu->mc->soc->atom_size - 1);
+
+		if (smmu->mc->soc->num_address_bits > 32) {
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+			value = (phys >> 32) & SMMU_PTC_FLUSH_HI_MASK;
+#else
+			value = 0;
+#endif
+			smmu_writel(smmu, value, SMMU_PTC_FLUSH_HI);
 		}
-		smmu_write(smmu, val, offs);
-	}
-	FLUSH_SMMU_REGS(smmu);
-	c->hwgrp = map;
-	return 0;
 
-err_hw_busy:
-	for_each_set_bit(i, &map, HWGRP_COUNT) {
-		offs = HWGRP_ASID_REG(i);
-		val = smmu_read(smmu, offs);
-		val &= ~mask;
-		smmu_write(smmu, val, offs);
+		value = (phys + offset) | SMMU_PTC_FLUSH_TYPE_ADR;
+	} else {
+		value = SMMU_PTC_FLUSH_TYPE_ALL;
 	}
-	return -EBUSY;
+
+	smmu_writel(smmu, value, SMMU_PTC_FLUSH);
 }
 
-static int smmu_client_set_hwgrp(struct smmu_client *c, u32 map, int on)
+static inline void smmu_flush_tlb(struct tegra_smmu *smmu)
 {
-	u32 val;
-	unsigned long flags;
-	struct smmu_as *as = c->as;
-	struct smmu_device *smmu = as->smmu;
-
-	spin_lock_irqsave(&smmu->lock, flags);
-	val = __smmu_client_set_hwgrp(c, map, on);
-	spin_unlock_irqrestore(&smmu->lock, flags);
-	return val;
+	smmu_writel(smmu, SMMU_TLB_FLUSH_VA_MATCH_ALL, SMMU_TLB_FLUSH);
 }
 
-/*
- * Flush all TLB entries and all PTC entries
- * Caller must lock smmu
- */
-static void smmu_flush_regs(struct smmu_device *smmu, int enable)
+static inline void smmu_flush_tlb_asid(struct tegra_smmu *smmu,
+				       unsigned long asid)
 {
-	u32 val;
-
-	smmu_write(smmu, SMMU_PTC_FLUSH_TYPE_ALL, SMMU_PTC_FLUSH);
-	FLUSH_SMMU_REGS(smmu);
-	val = SMMU_TLB_FLUSH_VA_MATCH_ALL |
-		SMMU_TLB_FLUSH_ASID_MATCH_disable;
-	smmu_write(smmu, val, SMMU_TLB_FLUSH);
+	u32 value;
 
-	if (enable)
-		smmu_write(smmu, SMMU_CONFIG_ENABLE, SMMU_CONFIG);
-	FLUSH_SMMU_REGS(smmu);
+	value = SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_ASID(asid) |
+		SMMU_TLB_FLUSH_VA_MATCH_ALL;
+	smmu_writel(smmu, value, SMMU_TLB_FLUSH);
 }
 
-static int smmu_setup_regs(struct smmu_device *smmu)
+static inline void smmu_flush_tlb_section(struct tegra_smmu *smmu,
+					  unsigned long asid,
+					  unsigned long iova)
 {
-	int i;
-	u32 val;
+	u32 value;
 
-	for (i = 0; i < smmu->num_as; i++) {
-		struct smmu_as *as = &smmu->as[i];
-		struct smmu_client *c;
-
-		smmu_write(smmu, SMMU_PTB_ASID_CUR(as->asid), SMMU_PTB_ASID);
-		val = as->pdir_page ?
-			SMMU_MK_PDIR(as->pdir_page, as->pdir_attr) :
-			SMMU_PTB_DATA_RESET_VAL;
-		smmu_write(smmu, val, SMMU_PTB_DATA);
-
-		list_for_each_entry(c, &as->client, list)
-			__smmu_client_set_hwgrp(c, c->hwgrp, 1);
-	}
-
-	smmu_write(smmu, smmu->translation_enable_0, SMMU_TRANSLATION_ENABLE_0);
-	smmu_write(smmu, smmu->translation_enable_1, SMMU_TRANSLATION_ENABLE_1);
-	smmu_write(smmu, smmu->translation_enable_2, SMMU_TRANSLATION_ENABLE_2);
-	smmu_write(smmu, smmu->asid_security, SMMU_ASID_SECURITY);
-	smmu_write(smmu, SMMU_TLB_CONFIG_RESET_VAL, SMMU_CACHE_CONFIG(_TLB));
-	smmu_write(smmu, SMMU_PTC_CONFIG_RESET_VAL, SMMU_CACHE_CONFIG(_PTC));
-
-	smmu_flush_regs(smmu, 1);
-
-	return tegra_ahb_enable_smmu(smmu->ahb);
+	value = SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_ASID(asid) |
+		SMMU_TLB_FLUSH_VA_SECTION(iova);
+	smmu_writel(smmu, value, SMMU_TLB_FLUSH);
 }
 
-static void flush_ptc_and_tlb(struct smmu_device *smmu,
-		      struct smmu_as *as, dma_addr_t iova,
-		      unsigned long *pte, struct page *page, int is_pde)
+static inline void smmu_flush_tlb_group(struct tegra_smmu *smmu,
+					unsigned long asid,
+					unsigned long iova)
 {
-	u32 val;
-	unsigned long tlb_flush_va = is_pde
-		?  SMMU_TLB_FLUSH_VA(iova, SECTION)
-		:  SMMU_TLB_FLUSH_VA(iova, GROUP);
-
-	val = SMMU_PTC_FLUSH_TYPE_ADR | VA_PAGE_TO_PA(pte, page);
-	smmu_write(smmu, val, SMMU_PTC_FLUSH);
-	FLUSH_SMMU_REGS(smmu);
-	val = tlb_flush_va |
-		SMMU_TLB_FLUSH_ASID_MATCH__ENABLE |
-		(as->asid << SMMU_TLB_FLUSH_ASID_SHIFT);
-	smmu_write(smmu, val, SMMU_TLB_FLUSH);
-	FLUSH_SMMU_REGS(smmu);
-}
+	u32 value;
 
-static void free_ptbl(struct smmu_as *as, dma_addr_t iova)
-{
-	unsigned long pdn = SMMU_ADDR_TO_PDN(iova);
-	unsigned long *pdir = (unsigned long *)page_address(as->pdir_page);
-
-	if (pdir[pdn] != _PDE_VACANT(pdn)) {
-		dev_dbg(as->smmu->dev, "pdn: %lx\n", pdn);
-
-		ClearPageReserved(SMMU_EX_PTBL_PAGE(pdir[pdn]));
-		__free_page(SMMU_EX_PTBL_PAGE(pdir[pdn]));
-		pdir[pdn] = _PDE_VACANT(pdn);
-		FLUSH_CPU_DCACHE(&pdir[pdn], as->pdir_page, sizeof pdir[pdn]);
-		flush_ptc_and_tlb(as->smmu, as, iova, &pdir[pdn],
-				  as->pdir_page, 1);
-	}
+	value = SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_ASID(asid) |
+		SMMU_TLB_FLUSH_VA_GROUP(iova);
+	smmu_writel(smmu, value, SMMU_TLB_FLUSH);
 }
 
-static void free_pdir(struct smmu_as *as)
+static inline void smmu_flush(struct tegra_smmu *smmu)
 {
-	unsigned addr;
-	int count;
-	struct device *dev = as->smmu->dev;
-
-	if (!as->pdir_page)
-		return;
-
-	addr = as->smmu->iovmm_base;
-	count = as->smmu->page_count;
-	while (count-- > 0) {
-		free_ptbl(as, addr);
-		addr += SMMU_PAGE_SIZE * SMMU_PTBL_COUNT;
-	}
-	ClearPageReserved(as->pdir_page);
-	__free_page(as->pdir_page);
-	as->pdir_page = NULL;
-	devm_kfree(dev, as->pte_count);
-	as->pte_count = NULL;
+	smmu_readl(smmu, SMMU_CONFIG);
 }
 
-/*
- * Maps PTBL for given iova and returns the PTE address
- * Caller must unmap the mapped PTBL returned in *ptbl_page_p
- */
-static unsigned long *locate_pte(struct smmu_as *as,
-				 dma_addr_t iova, bool allocate,
-				 struct page **ptbl_page_p,
-				 unsigned int **count)
+static int tegra_smmu_alloc_asid(struct tegra_smmu *smmu, unsigned int *idp)
 {
-	unsigned long ptn = SMMU_ADDR_TO_PFN(iova);
-	unsigned long pdn = SMMU_ADDR_TO_PDN(iova);
-	unsigned long *pdir = page_address(as->pdir_page);
-	unsigned long *ptbl;
-
-	if (pdir[pdn] != _PDE_VACANT(pdn)) {
-		/* Mapped entry table already exists */
-		*ptbl_page_p = SMMU_EX_PTBL_PAGE(pdir[pdn]);
-		ptbl = page_address(*ptbl_page_p);
-	} else if (!allocate) {
-		return NULL;
-	} else {
-		int pn;
-		unsigned long addr = SMMU_PDN_TO_ADDR(pdn);
+	unsigned long id;
 
-		/* Vacant - allocate a new page table */
-		dev_dbg(as->smmu->dev, "New PTBL pdn: %lx\n", pdn);
+	mutex_lock(&smmu->lock);
 
-		*ptbl_page_p = alloc_page(GFP_ATOMIC);
-		if (!*ptbl_page_p) {
-			dev_err(as->smmu->dev,
-				"failed to allocate smmu_device page table\n");
-			return NULL;
-		}
-		SetPageReserved(*ptbl_page_p);
-		ptbl = (unsigned long *)page_address(*ptbl_page_p);
-		for (pn = 0; pn < SMMU_PTBL_COUNT;
-		     pn++, addr += SMMU_PAGE_SIZE) {
-			ptbl[pn] = _PTE_VACANT(addr);
-		}
-		FLUSH_CPU_DCACHE(ptbl, *ptbl_page_p, SMMU_PTBL_SIZE);
-		pdir[pdn] = SMMU_MK_PDE(*ptbl_page_p,
-					as->pde_attr | _PDE_NEXT);
-		FLUSH_CPU_DCACHE(&pdir[pdn], as->pdir_page, sizeof pdir[pdn]);
-		flush_ptc_and_tlb(as->smmu, as, iova, &pdir[pdn],
-				  as->pdir_page, 1);
+	id = find_first_zero_bit(smmu->asids, smmu->soc->num_asids);
+	if (id >= smmu->soc->num_asids) {
+		mutex_unlock(&smmu->lock);
+		return -ENOSPC;
 	}
-	*count = &as->pte_count[pdn];
 
-	return &ptbl[ptn % SMMU_PTBL_COUNT];
+	set_bit(id, smmu->asids);
+	*idp = id;
+
+	mutex_unlock(&smmu->lock);
+	return 0;
 }
 
-#ifdef CONFIG_SMMU_SIG_DEBUG
-static void put_signature(struct smmu_as *as,
-			  dma_addr_t iova, unsigned long pfn)
+static void tegra_smmu_free_asid(struct tegra_smmu *smmu, unsigned int id)
 {
-	struct page *page;
-	unsigned long *vaddr;
-
-	page = pfn_to_page(pfn);
-	vaddr = page_address(page);
-	if (!vaddr)
-		return;
-
-	vaddr[0] = iova;
-	vaddr[1] = pfn << PAGE_SHIFT;
-	FLUSH_CPU_DCACHE(vaddr, page, sizeof(vaddr[0]) * 2);
+	mutex_lock(&smmu->lock);
+	clear_bit(id, smmu->asids);
+	mutex_unlock(&smmu->lock);
 }
-#else
-static inline void put_signature(struct smmu_as *as,
-				 unsigned long addr, unsigned long pfn)
+
+static bool tegra_smmu_capable(enum iommu_cap cap)
 {
+	return false;
 }
-#endif
 
-/*
- * Caller must not hold as->lock
- */
-static int alloc_pdir(struct smmu_as *as)
+static int tegra_smmu_domain_init(struct iommu_domain *domain)
 {
-	unsigned long *pdir, flags;
-	int pdn, err = 0;
-	u32 val;
-	struct smmu_device *smmu = as->smmu;
-	struct page *page;
-	unsigned int *cnt;
+	struct tegra_smmu_as *as;
+	unsigned int i;
+	uint32_t *pd;
 
-	/*
-	 * do the allocation, then grab as->lock
-	 */
-	cnt = devm_kzalloc(smmu->dev,
-			   sizeof(cnt[0]) * SMMU_PDIR_COUNT,
-			   GFP_KERNEL);
-	page = alloc_page(GFP_KERNEL | __GFP_DMA);
+	as = kzalloc(sizeof(*as), GFP_KERNEL);
+	if (!as)
+		return -ENOMEM;
 
-	spin_lock_irqsave(&as->lock, flags);
+	as->attr = SMMU_PD_READABLE | SMMU_PD_WRITABLE | SMMU_PD_NONSECURE;
+	as->domain = domain;
 
-	if (as->pdir_page) {
-		/* We raced, free the redundant */
-		err = -EAGAIN;
-		goto err_out;
+	as->pd = alloc_page(GFP_KERNEL | __GFP_DMA);
+	if (!as->pd) {
+		kfree(as);
+		return -ENOMEM;
 	}
 
-	if (!page || !cnt) {
-		dev_err(smmu->dev, "failed to allocate at %s\n", __func__);
-		err = -ENOMEM;
-		goto err_out;
+	as->count = alloc_page(GFP_KERNEL);
+	if (!as->count) {
+		__free_page(as->pd);
+		kfree(as);
+		return -ENOMEM;
 	}
 
-	as->pdir_page = page;
-	as->pte_count = cnt;
+	/* clear PDEs */
+	pd = page_address(as->pd);
+	SetPageReserved(as->pd);
 
-	SetPageReserved(as->pdir_page);
-	pdir = page_address(as->pdir_page);
+	for (i = 0; i < SMMU_NUM_PDE; i++)
+		pd[i] = 0;
 
-	for (pdn = 0; pdn < SMMU_PDIR_COUNT; pdn++)
-		pdir[pdn] = _PDE_VACANT(pdn);
-	FLUSH_CPU_DCACHE(pdir, as->pdir_page, SMMU_PDIR_SIZE);
-	val = SMMU_PTC_FLUSH_TYPE_ADR | VA_PAGE_TO_PA(pdir, as->pdir_page);
-	smmu_write(smmu, val, SMMU_PTC_FLUSH);
-	FLUSH_SMMU_REGS(as->smmu);
-	val = SMMU_TLB_FLUSH_VA_MATCH_ALL |
-		SMMU_TLB_FLUSH_ASID_MATCH__ENABLE |
-		(as->asid << SMMU_TLB_FLUSH_ASID_SHIFT);
-	smmu_write(smmu, val, SMMU_TLB_FLUSH);
-	FLUSH_SMMU_REGS(as->smmu);
+	/* clear PDE usage counters */
+	pd = page_address(as->count);
+	SetPageReserved(as->count);
 
-	spin_unlock_irqrestore(&as->lock, flags);
-
-	return 0;
+	for (i = 0; i < SMMU_NUM_PDE; i++)
+		pd[i] = 0;
 
-err_out:
-	spin_unlock_irqrestore(&as->lock, flags);
+	domain->priv = as;
 
-	devm_kfree(smmu->dev, cnt);
-	if (page)
-		__free_page(page);
-	return err;
+	return 0;
 }
 
-static void __smmu_iommu_unmap(struct smmu_as *as, dma_addr_t iova)
+static void tegra_smmu_domain_destroy(struct iommu_domain *domain)
 {
-	unsigned long *pte;
-	struct page *page;
-	unsigned int *count;
+	struct tegra_smmu_as *as = domain->priv;
 
-	pte = locate_pte(as, iova, false, &page, &count);
-	if (WARN_ON(!pte))
-		return;
+	/* TODO: free page directory and page tables */
+	ClearPageReserved(as->pd);
 
-	if (WARN_ON(*pte == _PTE_VACANT(iova)))
-		return;
-
-	*pte = _PTE_VACANT(iova);
-	FLUSH_CPU_DCACHE(pte, page, sizeof(*pte));
-	flush_ptc_and_tlb(as->smmu, as, iova, pte, page, 0);
-	if (!--(*count))
-		free_ptbl(as, iova);
+	kfree(as);
 }
 
-static void __smmu_iommu_map_pfn(struct smmu_as *as, dma_addr_t iova,
-				 unsigned long pfn)
+static const struct tegra_smmu_swgroup *
+tegra_smmu_find_swgroup(struct tegra_smmu *smmu, unsigned int swgroup)
 {
-	struct smmu_device *smmu = as->smmu;
-	unsigned long *pte;
-	unsigned int *count;
-	struct page *page;
+	const struct tegra_smmu_swgroup *group = NULL;
+	unsigned int i;
 
-	pte = locate_pte(as, iova, true, &page, &count);
-	if (WARN_ON(!pte))
-		return;
+	for (i = 0; i < smmu->soc->num_swgroups; i++) {
+		if (smmu->soc->swgroups[i].swgroup == swgroup) {
+			group = &smmu->soc->swgroups[i];
+			break;
+		}
+	}
 
-	if (*pte == _PTE_VACANT(iova))
-		(*count)++;
-	*pte = SMMU_PFN_TO_PTE(pfn, as->pte_attr);
-	if (unlikely((*pte == _PTE_VACANT(iova))))
-		(*count)--;
-	FLUSH_CPU_DCACHE(pte, page, sizeof(*pte));
-	flush_ptc_and_tlb(smmu, as, iova, pte, page, 0);
-	put_signature(as, iova, pfn);
+	return group;
 }
 
-static int smmu_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t pa, size_t bytes, int prot)
+static void tegra_smmu_enable(struct tegra_smmu *smmu, unsigned int swgroup,
+			      unsigned int asid)
 {
-	struct smmu_as *as = domain->priv;
-	unsigned long pfn = __phys_to_pfn(pa);
-	unsigned long flags;
+	const struct tegra_smmu_swgroup *group;
+	unsigned int i;
+	u32 value;
 
-	dev_dbg(as->smmu->dev, "[%d] %08lx:%pa\n", as->asid, iova, &pa);
+	for (i = 0; i < smmu->soc->num_clients; i++) {
+		const struct tegra_mc_client *client = &smmu->soc->clients[i];
 
-	if (!pfn_valid(pfn))
-		return -ENOMEM;
-
-	spin_lock_irqsave(&as->lock, flags);
-	__smmu_iommu_map_pfn(as, iova, pfn);
-	spin_unlock_irqrestore(&as->lock, flags);
-	return 0;
-}
-
-static size_t smmu_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
-			       size_t bytes)
-{
-	struct smmu_as *as = domain->priv;
-	unsigned long flags;
+		if (client->swgroup != swgroup)
+			continue;
 
-	dev_dbg(as->smmu->dev, "[%d] %08lx\n", as->asid, iova);
+		value = smmu_readl(smmu, client->smmu.reg);
+		value |= BIT(client->smmu.bit);
+		smmu_writel(smmu, value, client->smmu.reg);
+	}
 
-	spin_lock_irqsave(&as->lock, flags);
-	__smmu_iommu_unmap(as, iova);
-	spin_unlock_irqrestore(&as->lock, flags);
-	return SMMU_PAGE_SIZE;
+	group = tegra_smmu_find_swgroup(smmu, swgroup);
+	if (group) {
+		value = smmu_readl(smmu, group->reg);
+		value &= ~SMMU_ASID_MASK;
+		value |= SMMU_ASID_VALUE(asid);
+		value |= SMMU_ASID_ENABLE;
+		smmu_writel(smmu, value, group->reg);
+	}
 }
 
-static phys_addr_t smmu_iommu_iova_to_phys(struct iommu_domain *domain,
-					   dma_addr_t iova)
+static void tegra_smmu_disable(struct tegra_smmu *smmu, unsigned int swgroup,
+			       unsigned int asid)
 {
-	struct smmu_as *as = domain->priv;
-	unsigned long *pte;
-	unsigned int *count;
-	struct page *page;
-	unsigned long pfn;
-	unsigned long flags;
+	const struct tegra_smmu_swgroup *group;
+	unsigned int i;
+	u32 value;
 
-	spin_lock_irqsave(&as->lock, flags);
+	group = tegra_smmu_find_swgroup(smmu, swgroup);
+	if (group) {
+		value = smmu_readl(smmu, group->reg);
+		value &= ~SMMU_ASID_MASK;
+		value |= SMMU_ASID_VALUE(asid);
+		value &= ~SMMU_ASID_ENABLE;
+		smmu_writel(smmu, value, group->reg);
+	}
 
-	pte = locate_pte(as, iova, true, &page, &count);
-	pfn = *pte & SMMU_PFN_MASK;
-	WARN_ON(!pfn_valid(pfn));
-	dev_dbg(as->smmu->dev,
-		"iova:%08llx pfn:%08lx asid:%d\n", (unsigned long long)iova,
-		 pfn, as->asid);
+	for (i = 0; i < smmu->soc->num_clients; i++) {
+		const struct tegra_mc_client *client = &smmu->soc->clients[i];
 
-	spin_unlock_irqrestore(&as->lock, flags);
-	return PFN_PHYS(pfn);
-}
+		if (client->swgroup != swgroup)
+			continue;
 
-static bool smmu_iommu_capable(enum iommu_cap cap)
-{
-	return false;
+		value = smmu_readl(smmu, client->smmu.reg);
+		value &= ~BIT(client->smmu.bit);
+		smmu_writel(smmu, value, client->smmu.reg);
+	}
 }
 
-static int smmu_iommu_attach_dev(struct iommu_domain *domain,
-				 struct device *dev)
+static int tegra_smmu_as_prepare(struct tegra_smmu *smmu,
+				 struct tegra_smmu_as *as)
 {
-	struct smmu_as *as = domain->priv;
-	struct smmu_device *smmu = as->smmu;
-	struct smmu_client *client, *c;
-	u32 map;
+	u32 value;
 	int err;
 
-	client = devm_kzalloc(smmu->dev, sizeof(*c), GFP_KERNEL);
-	if (!client)
-		return -ENOMEM;
-	client->dev = dev;
-	client->as = as;
-	map = (unsigned long)dev->platform_data;
-	if (!map)
-		return -EINVAL;
-
-	err = smmu_client_enable_hwgrp(client, map);
-	if (err)
-		goto err_hwgrp;
-
-	spin_lock(&as->client_lock);
-	list_for_each_entry(c, &as->client, list) {
-		if (c->dev == dev) {
-			dev_err(smmu->dev,
-				"%s is already attached\n", dev_name(c->dev));
-			err = -EINVAL;
-			goto err_client;
-		}
+	if (as->use_count > 0) {
+		as->use_count++;
+		return 0;
 	}
-	list_add(&client->list, &as->client);
-	spin_unlock(&as->client_lock);
 
-	/*
-	 * Reserve "page zero" for AVP vectors using a common dummy
-	 * page.
-	 */
-	if (map & HWG_AVPC) {
-		struct page *page;
+	err = tegra_smmu_alloc_asid(smmu, &as->id);
+	if (err < 0)
+		return err;
 
-		page = as->smmu->avp_vector_page;
-		__smmu_iommu_map_pfn(as, 0, page_to_pfn(page));
+	smmu->soc->ops->flush_dcache(as->pd, 0, SMMU_SIZE_PD);
+	smmu_flush_ptc(smmu, as->pd, 0);
+	smmu_flush_tlb_asid(smmu, as->id);
 
-		pr_info("Reserve \"page zero\" for AVP vectors using a common dummy\n");
-	}
+	smmu_writel(smmu, as->id & 0x7f, SMMU_PTB_ASID);
+	value = SMMU_PTB_DATA_VALUE(as->pd, as->attr);
+	smmu_writel(smmu, value, SMMU_PTB_DATA);
+	smmu_flush(smmu);
 
-	dev_dbg(smmu->dev, "%s is attached\n", dev_name(dev));
-	return 0;
+	as->smmu = smmu;
+	as->use_count++;
 
-err_client:
-	smmu_client_disable_hwgrp(client);
-	spin_unlock(&as->client_lock);
-err_hwgrp:
-	devm_kfree(smmu->dev, client);
-	return err;
+	return 0;
 }
 
-static void smmu_iommu_detach_dev(struct iommu_domain *domain,
-				  struct device *dev)
+static void tegra_smmu_as_unprepare(struct tegra_smmu *smmu,
+				    struct tegra_smmu_as *as)
 {
-	struct smmu_as *as = domain->priv;
-	struct smmu_device *smmu = as->smmu;
-	struct smmu_client *c;
-
-	spin_lock(&as->client_lock);
-
-	list_for_each_entry(c, &as->client, list) {
-		if (c->dev == dev) {
-			smmu_client_disable_hwgrp(c);
-			list_del(&c->list);
-			devm_kfree(smmu->dev, c);
-			c->as = NULL;
-			dev_dbg(smmu->dev,
-				"%s is detached\n", dev_name(c->dev));
-			goto out;
-		}
-	}
-	dev_err(smmu->dev, "Couldn't find %s\n", dev_name(dev));
-out:
-	spin_unlock(&as->client_lock);
+	if (--as->use_count > 0)
+		return;
+
+	tegra_smmu_free_asid(smmu, as->id);
+	as->smmu = NULL;
 }
 
-static int smmu_iommu_domain_init(struct iommu_domain *domain)
+static int tegra_smmu_attach_dev(struct iommu_domain *domain,
+				 struct device *dev)
 {
-	int i, err = -EAGAIN;
-	unsigned long flags;
-	struct smmu_as *as;
-	struct smmu_device *smmu = smmu_handle;
+	struct tegra_smmu *smmu = dev->archdata.iommu;
+	struct tegra_smmu_as *as = domain->priv;
+	struct device_node *np = dev->of_node;
+	struct of_phandle_args args;
+	unsigned int index = 0;
+	int err = 0;
 
-	/* Look for a free AS with lock held */
-	for  (i = 0; i < smmu->num_as; i++) {
-		as = &smmu->as[i];
+	while (!of_parse_phandle_with_args(np, "iommus", "#iommu-cells", index,
+					   &args)) {
+		unsigned int swgroup = args.args[0];
 
-		if (as->pdir_page)
+		if (args.np != smmu->dev->of_node) {
+			of_node_put(args.np);
 			continue;
+		}
 
-		err = alloc_pdir(as);
-		if (!err)
-			goto found;
+		of_node_put(args.np);
 
-		if (err != -EAGAIN)
-			break;
+		err = tegra_smmu_as_prepare(smmu, as);
+		if (err < 0)
+			return err;
+
+		tegra_smmu_enable(smmu, swgroup, as->id);
+		index++;
 	}
-	if (i == smmu->num_as)
-		dev_err(smmu->dev,  "no free AS\n");
-	return err;
 
-found:
-	spin_lock_irqsave(&smmu->lock, flags);
+	if (index == 0)
+		return -ENODEV;
 
-	/* Update PDIR register */
-	smmu_write(smmu, SMMU_PTB_ASID_CUR(as->asid), SMMU_PTB_ASID);
-	smmu_write(smmu,
-		   SMMU_MK_PDIR(as->pdir_page, as->pdir_attr), SMMU_PTB_DATA);
-	FLUSH_SMMU_REGS(smmu);
+	return 0;
+}
 
-	spin_unlock_irqrestore(&smmu->lock, flags);
+static void tegra_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	struct tegra_smmu_as *as = domain->priv;
+	struct device_node *np = dev->of_node;
+	struct tegra_smmu *smmu = as->smmu;
+	struct of_phandle_args args;
+	unsigned int index = 0;
 
-	domain->priv = as;
+	while (!of_parse_phandle_with_args(np, "iommus", "#iommu-cells", index,
+					   &args)) {
+		unsigned int swgroup = args.args[0];
 
-	domain->geometry.aperture_start = smmu->iovmm_base;
-	domain->geometry.aperture_end   = smmu->iovmm_base +
-		smmu->page_count * SMMU_PAGE_SIZE - 1;
-	domain->geometry.force_aperture = true;
+		if (args.np != smmu->dev->of_node) {
+			of_node_put(args.np);
+			continue;
+		}
 
-	dev_dbg(smmu->dev, "smmu_as@%p\n", as);
+		of_node_put(args.np);
 
-	return 0;
+		tegra_smmu_disable(smmu, swgroup, as->id);
+		tegra_smmu_as_unprepare(smmu, as);
+		index++;
+	}
 }
 
-static void smmu_iommu_domain_destroy(struct iommu_domain *domain)
+static u32 *as_get_pte(struct tegra_smmu_as *as, dma_addr_t iova,
+		       struct page **pagep)
 {
-	struct smmu_as *as = domain->priv;
-	struct smmu_device *smmu = as->smmu;
-	unsigned long flags;
+	u32 *pd = page_address(as->pd), *pt, *count;
+	u32 pde = (iova >> SMMU_PDE_SHIFT) & 0x3ff;
+	u32 pte = (iova >> SMMU_PTE_SHIFT) & 0x3ff;
+	struct tegra_smmu *smmu = as->smmu;
+	struct page *page;
+	unsigned int i;
+
+	if (pd[pde] == 0) {
+		page = alloc_page(GFP_KERNEL | __GFP_DMA);
+		if (!page)
+			return NULL;
 
-	spin_lock_irqsave(&as->lock, flags);
+		pt = page_address(page);
+		SetPageReserved(page);
 
-	if (as->pdir_page) {
-		spin_lock(&smmu->lock);
-		smmu_write(smmu, SMMU_PTB_ASID_CUR(as->asid), SMMU_PTB_ASID);
-		smmu_write(smmu, SMMU_PTB_DATA_RESET_VAL, SMMU_PTB_DATA);
-		FLUSH_SMMU_REGS(smmu);
-		spin_unlock(&smmu->lock);
+		for (i = 0; i < SMMU_NUM_PTE; i++)
+			pt[i] = 0;
 
-		free_pdir(as);
-	}
+		smmu->soc->ops->flush_dcache(page, 0, SMMU_SIZE_PT);
 
-	if (!list_empty(&as->client)) {
-		struct smmu_client *c;
+		pd[pde] = SMMU_MK_PDE(page, SMMU_PDE_ATTR | SMMU_PDE_NEXT);
 
-		list_for_each_entry(c, &as->client, list)
-			smmu_iommu_detach_dev(domain, c->dev);
+		smmu->soc->ops->flush_dcache(as->pd, pde << 2, 4);
+		smmu_flush_ptc(smmu, as->pd, pde << 2);
+		smmu_flush_tlb_section(smmu, as->id, iova);
+		smmu_flush(smmu);
+	} else {
+		page = pfn_to_page(pd[pde] & SMMU_PFN_MASK);
+		pt = page_address(page);
 	}
 
-	spin_unlock_irqrestore(&as->lock, flags);
+	*pagep = page;
 
-	domain->priv = NULL;
-	dev_dbg(smmu->dev, "smmu_as@%p\n", as);
-}
+	/* Keep track of entries in this page table. */
+	count = page_address(as->count);
+	if (pt[pte] == 0)
+		count[pde]++;
 
-static const struct iommu_ops smmu_iommu_ops = {
-	.capable	= smmu_iommu_capable,
-	.domain_init	= smmu_iommu_domain_init,
-	.domain_destroy	= smmu_iommu_domain_destroy,
-	.attach_dev	= smmu_iommu_attach_dev,
-	.detach_dev	= smmu_iommu_detach_dev,
-	.map		= smmu_iommu_map,
-	.unmap		= smmu_iommu_unmap,
-	.map_sg		= default_iommu_map_sg,
-	.iova_to_phys	= smmu_iommu_iova_to_phys,
-	.pgsize_bitmap	= SMMU_IOMMU_PGSIZES,
-};
-
-/* Should be in the order of enum */
-static const char * const smmu_debugfs_mc[] = { "mc", };
-static const char * const smmu_debugfs_cache[] = {  "tlb", "ptc", };
+	return &pt[pte];
+}
 
-static ssize_t smmu_debugfs_stats_write(struct file *file,
-					const char __user *buffer,
-					size_t count, loff_t *pos)
+static void as_put_pte(struct tegra_smmu_as *as, dma_addr_t iova)
 {
-	struct smmu_debugfs_info *info;
-	struct smmu_device *smmu;
-	int i;
-	enum {
-		_OFF = 0,
-		_ON,
-		_RESET,
-	};
-	const char * const command[] = {
-		[_OFF]		= "off",
-		[_ON]		= "on",
-		[_RESET]	= "reset",
-	};
-	char str[] = "reset";
-	u32 val;
-	size_t offs;
+	u32 pde = (iova >> SMMU_PDE_SHIFT) & 0x3ff;
+	u32 pte = (iova >> SMMU_PTE_SHIFT) & 0x3ff;
+	u32 *count = page_address(as->count);
+	u32 *pd = page_address(as->pd), *pt;
+	struct page *page;
 
-	count = min_t(size_t, count, sizeof(str));
-	if (copy_from_user(str, buffer, count))
-		return -EINVAL;
+	page = pfn_to_page(pd[pde] & SMMU_PFN_MASK);
+	pt = page_address(page);
 
-	for (i = 0; i < ARRAY_SIZE(command); i++)
-		if (strncmp(str, command[i],
-			    strlen(command[i])) == 0)
-			break;
+	/*
+	 * When no entries in this page table are used anymore, return the
+	 * memory page to the system.
+	 */
+	if (pt[pte] != 0) {
+		if (--count[pde] == 0) {
+			ClearPageReserved(page);
+			__free_page(page);
+			pd[pde] = 0;
+		}
 
-	if (i == ARRAY_SIZE(command))
-		return -EINVAL;
-
-	info = file_inode(file)->i_private;
-	smmu = info->smmu;
-
-	offs = SMMU_CACHE_CONFIG(info->cache);
-	val = smmu_read(smmu, offs);
-	switch (i) {
-	case _OFF:
-		val &= ~SMMU_CACHE_CONFIG_STATS_ENABLE;
-		val &= ~SMMU_CACHE_CONFIG_STATS_TEST;
-		smmu_write(smmu, val, offs);
-		break;
-	case _ON:
-		val |= SMMU_CACHE_CONFIG_STATS_ENABLE;
-		val &= ~SMMU_CACHE_CONFIG_STATS_TEST;
-		smmu_write(smmu, val, offs);
-		break;
-	case _RESET:
-		val |= SMMU_CACHE_CONFIG_STATS_TEST;
-		smmu_write(smmu, val, offs);
-		val &= ~SMMU_CACHE_CONFIG_STATS_TEST;
-		smmu_write(smmu, val, offs);
-		break;
-	default:
-		BUG();
-		break;
+		pt[pte] = 0;
 	}
-
-	dev_dbg(smmu->dev, "%s() %08x, %08x @%08x\n", __func__,
-		val, smmu_read(smmu, offs), offs);
-
-	return count;
 }
 
-static int smmu_debugfs_stats_show(struct seq_file *s, void *v)
+static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
+			  phys_addr_t paddr, size_t size, int prot)
 {
-	struct smmu_debugfs_info *info = s->private;
-	struct smmu_device *smmu = info->smmu;
-	int i;
-	const char * const stats[] = { "hit", "miss", };
+	struct tegra_smmu_as *as = domain->priv;
+	struct tegra_smmu *smmu = as->smmu;
+	unsigned long offset;
+	struct page *page;
+	u32 *pte;
 
+	pte = as_get_pte(as, iova, &page);
+	if (!pte)
+		return -ENOMEM;
 
-	for (i = 0; i < ARRAY_SIZE(stats); i++) {
-		u32 val;
-		size_t offs;
+	*pte = __phys_to_pfn(paddr) | SMMU_PTE_ATTR;
+	offset = offset_in_page(pte);
 
-		offs = SMMU_STATS_CACHE_COUNT(info->mc, info->cache, i);
-		val = smmu_read(smmu, offs);
-		seq_printf(s, "%s:%08x ", stats[i], val);
+	smmu->soc->ops->flush_dcache(page, offset, 4);
+	smmu_flush_ptc(smmu, page, offset);
+	smmu_flush_tlb_group(smmu, as->id, iova);
+	smmu_flush(smmu);
 
-		dev_dbg(smmu->dev, "%s() %s %08x @%08x\n", __func__,
-			stats[i], val, offs);
-	}
-	seq_printf(s, "\n");
 	return 0;
 }
 
-static int smmu_debugfs_stats_open(struct inode *inode, struct file *file)
+static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
+			       size_t size)
 {
-	return single_open(file, smmu_debugfs_stats_show, inode->i_private);
-}
+	struct tegra_smmu_as *as = domain->priv;
+	struct tegra_smmu *smmu = as->smmu;
+	unsigned long offset;
+	struct page *page;
+	u32 *pte;
 
-static const struct file_operations smmu_debugfs_stats_fops = {
-	.open		= smmu_debugfs_stats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= smmu_debugfs_stats_write,
-};
+	pte = as_get_pte(as, iova, &page);
+	if (!pte)
+		return 0;
 
-static void smmu_debugfs_delete(struct smmu_device *smmu)
-{
-	debugfs_remove_recursive(smmu->debugfs_root);
-	kfree(smmu->debugfs_info);
+	offset = offset_in_page(pte);
+	as_put_pte(as, iova);
+
+	smmu->soc->ops->flush_dcache(page, offset, 4);
+	smmu_flush_ptc(smmu, page, offset);
+	smmu_flush_tlb_group(smmu, as->id, iova);
+	smmu_flush(smmu);
+
+	return size;
 }
 
-static void smmu_debugfs_create(struct smmu_device *smmu)
+static phys_addr_t tegra_smmu_iova_to_phys(struct iommu_domain *domain,
+					   dma_addr_t iova)
 {
-	int i;
-	size_t bytes;
-	struct dentry *root;
-
-	bytes = ARRAY_SIZE(smmu_debugfs_mc) * ARRAY_SIZE(smmu_debugfs_cache) *
-		sizeof(*smmu->debugfs_info);
-	smmu->debugfs_info = kmalloc(bytes, GFP_KERNEL);
-	if (!smmu->debugfs_info)
-		return;
-
-	root = debugfs_create_dir(dev_name(smmu->dev), NULL);
-	if (!root)
-		goto err_out;
-	smmu->debugfs_root = root;
-
-	for (i = 0; i < ARRAY_SIZE(smmu_debugfs_mc); i++) {
-		int j;
-		struct dentry *mc;
-
-		mc = debugfs_create_dir(smmu_debugfs_mc[i], root);
-		if (!mc)
-			goto err_out;
-
-		for (j = 0; j < ARRAY_SIZE(smmu_debugfs_cache); j++) {
-			struct dentry *cache;
-			struct smmu_debugfs_info *info;
-
-			info = smmu->debugfs_info;
-			info += i * ARRAY_SIZE(smmu_debugfs_mc) + j;
-			info->smmu = smmu;
-			info->mc = i;
-			info->cache = j;
-
-			cache = debugfs_create_file(smmu_debugfs_cache[j],
-						    S_IWUGO | S_IRUGO, mc,
-						    (void *)info,
-						    &smmu_debugfs_stats_fops);
-			if (!cache)
-				goto err_out;
-		}
-	}
+	struct tegra_smmu_as *as = domain->priv;
+	struct page *page;
+	unsigned long pfn;
+	u32 *pte;
 
-	return;
+	pte = as_get_pte(as, iova, &page);
+	pfn = *pte & SMMU_PFN_MASK;
 
-err_out:
-	smmu_debugfs_delete(smmu);
+	return PFN_PHYS(pfn);
 }
 
-static int tegra_smmu_suspend(struct device *dev)
+static struct tegra_smmu *tegra_smmu_find(struct device_node *np)
 {
-	struct smmu_device *smmu = dev_get_drvdata(dev);
+	struct platform_device *pdev;
+	struct tegra_mc *mc;
 
-	smmu->translation_enable_0 = smmu_read(smmu, SMMU_TRANSLATION_ENABLE_0);
-	smmu->translation_enable_1 = smmu_read(smmu, SMMU_TRANSLATION_ENABLE_1);
-	smmu->translation_enable_2 = smmu_read(smmu, SMMU_TRANSLATION_ENABLE_2);
-	smmu->asid_security = smmu_read(smmu, SMMU_ASID_SECURITY);
-	return 0;
+	pdev = of_find_device_by_node(np);
+	if (!pdev)
+		return NULL;
+
+	mc = platform_get_drvdata(pdev);
+	if (!mc)
+		return NULL;
+
+	return mc->smmu;
 }
 
-static int tegra_smmu_resume(struct device *dev)
+static int tegra_smmu_add_device(struct device *dev)
 {
-	struct smmu_device *smmu = dev_get_drvdata(dev);
-	unsigned long flags;
-	int err;
+	struct device_node *np = dev->of_node;
+	struct of_phandle_args args;
+	unsigned int index = 0;
 
-	spin_lock_irqsave(&smmu->lock, flags);
-	err = smmu_setup_regs(smmu);
-	spin_unlock_irqrestore(&smmu->lock, flags);
-	return err;
+	while (of_parse_phandle_with_args(np, "iommus", "#iommu-cells", index,
+					  &args) == 0) {
+		struct tegra_smmu *smmu;
+
+		smmu = tegra_smmu_find(args.np);
+		if (smmu) {
+			/*
+			 * Only a single IOMMU master interface is currently
+			 * supported by the Linux kernel, so abort after the
+			 * first match.
+			 */
+			dev->archdata.iommu = smmu;
+			break;
+		}
+
+		index++;
+	}
+
+	return 0;
 }
 
-static int tegra_smmu_probe(struct platform_device *pdev)
+static void tegra_smmu_remove_device(struct device *dev)
 {
-	struct smmu_device *smmu;
-	struct device *dev = &pdev->dev;
-	int i, asids, err = 0;
-	dma_addr_t uninitialized_var(base);
-	size_t bytes, uninitialized_var(size);
+	dev->archdata.iommu = NULL;
+}
 
-	if (smmu_handle)
-		return -EIO;
+static const struct iommu_ops tegra_smmu_ops = {
+	.capable = tegra_smmu_capable,
+	.domain_init = tegra_smmu_domain_init,
+	.domain_destroy = tegra_smmu_domain_destroy,
+	.attach_dev = tegra_smmu_attach_dev,
+	.detach_dev = tegra_smmu_detach_dev,
+	.add_device = tegra_smmu_add_device,
+	.remove_device = tegra_smmu_remove_device,
+	.map = tegra_smmu_map,
+	.unmap = tegra_smmu_unmap,
+	.map_sg = default_iommu_map_sg,
+	.iova_to_phys = tegra_smmu_iova_to_phys,
 
-	BUILD_BUG_ON(PAGE_SHIFT != SMMU_PAGE_SHIFT);
+	.pgsize_bitmap = SZ_4K,
+};
 
-	if (of_property_read_u32(dev->of_node, "nvidia,#asids", &asids))
-		return -ENODEV;
+static void tegra_smmu_ahb_enable(void)
+{
+	static const struct of_device_id ahb_match[] = {
+		{ .compatible = "nvidia,tegra30-ahb", },
+		{ }
+	};
+	struct device_node *ahb;
 
-	bytes = sizeof(*smmu) + asids * sizeof(*smmu->as);
-	smmu = devm_kzalloc(dev, bytes, GFP_KERNEL);
-	if (!smmu) {
-		dev_err(dev, "failed to allocate smmu_device\n");
-		return -ENOMEM;
+	ahb = of_find_matching_node(NULL, ahb_match);
+	if (ahb) {
+		tegra_ahb_enable_smmu(ahb);
+		of_node_put(ahb);
 	}
+}
 
-	smmu->nregs = pdev->num_resources;
-	smmu->regs = devm_kzalloc(dev, 2 * smmu->nregs * sizeof(*smmu->regs),
-				  GFP_KERNEL);
-	smmu->rege = smmu->regs + smmu->nregs;
-	if (!smmu->regs)
-		return -ENOMEM;
-	for (i = 0; i < smmu->nregs; i++) {
-		struct resource *res;
-
-		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
-		smmu->regs[i] = devm_ioremap_resource(&pdev->dev, res);
-		if (IS_ERR(smmu->regs[i]))
-			return PTR_ERR(smmu->regs[i]);
-		smmu->rege[i] = smmu->regs[i] + resource_size(res) - 1;
-	}
-	/* Same as "mc" 1st regiter block start address */
-	smmu->regbase = (void __iomem *)((u32)smmu->regs[0] & PAGE_MASK);
+struct tegra_smmu *tegra_smmu_probe(struct device *dev,
+				    const struct tegra_smmu_soc *soc,
+				    struct tegra_mc *mc)
+{
+	struct tegra_smmu *smmu;
+	size_t size;
+	u32 value;
+	int err;
 
-	err = of_get_dma_window(dev->of_node, NULL, 0, NULL, &base, &size);
-	if (err)
-		return -ENODEV;
+	/* This can happen on Tegra20 which doesn't have an SMMU */
+	if (!soc)
+		return NULL;
 
-	if (size & SMMU_PAGE_MASK)
-		return -EINVAL;
+	smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
+	if (!smmu)
+		return ERR_PTR(-ENOMEM);
 
-	size >>= SMMU_PAGE_SHIFT;
-	if (!size)
-		return -EINVAL;
+	/*
+	 * This is a bit of a hack. Ideally we'd want to simply return this
+	 * value. However the IOMMU registration process will attempt to add
+	 * all devices to the IOMMU when bus_set_iommu() is called. In order
+	 * not to rely on global variables to track the IOMMU instance, we
+	 * set it here so that it can be looked up from the .add_device()
+	 * callback via the IOMMU device's .drvdata field.
+	 */
+	mc->smmu = smmu;
 
-	smmu->ahb = of_parse_phandle(dev->of_node, "nvidia,ahb", 0);
-	if (!smmu->ahb)
-		return -ENODEV;
+	size = BITS_TO_LONGS(soc->num_asids) * sizeof(long);
 
-	smmu->dev = dev;
-	smmu->num_as = asids;
-	smmu->iovmm_base = base;
-	smmu->page_count = size;
-
-	smmu->translation_enable_0 = ~0;
-	smmu->translation_enable_1 = ~0;
-	smmu->translation_enable_2 = ~0;
-	smmu->asid_security = 0;
-
-	for (i = 0; i < smmu->num_as; i++) {
-		struct smmu_as *as = &smmu->as[i];
-
-		as->smmu = smmu;
-		as->asid = i;
-		as->pdir_attr = _PDIR_ATTR;
-		as->pde_attr = _PDE_ATTR;
-		as->pte_attr = _PTE_ATTR;
-
-		spin_lock_init(&as->lock);
-		spin_lock_init(&as->client_lock);
-		INIT_LIST_HEAD(&as->client);
-	}
-	spin_lock_init(&smmu->lock);
-	err = smmu_setup_regs(smmu);
-	if (err)
-		return err;
-	platform_set_drvdata(pdev, smmu);
+	smmu->asids = devm_kzalloc(dev, size, GFP_KERNEL);
+	if (!smmu->asids)
+		return ERR_PTR(-ENOMEM);
 
-	smmu->avp_vector_page = alloc_page(GFP_KERNEL);
-	if (!smmu->avp_vector_page)
-		return -ENOMEM;
+	mutex_init(&smmu->lock);
 
-	smmu_debugfs_create(smmu);
-	smmu_handle = smmu;
-	bus_set_iommu(&platform_bus_type, &smmu_iommu_ops);
-	return 0;
-}
+	smmu->regs = mc->regs;
+	smmu->soc = soc;
+	smmu->dev = dev;
+	smmu->mc = mc;
 
-static int tegra_smmu_remove(struct platform_device *pdev)
-{
-	struct smmu_device *smmu = platform_get_drvdata(pdev);
-	int i;
+	value = SMMU_PTC_CONFIG_ENABLE | SMMU_PTC_CONFIG_INDEX_MAP(0x3f);
 
-	smmu_debugfs_delete(smmu);
+	if (soc->supports_request_limit)
+		value |= SMMU_PTC_CONFIG_REQ_LIMIT(8);
 
-	smmu_write(smmu, SMMU_CONFIG_DISABLE, SMMU_CONFIG);
-	for (i = 0; i < smmu->num_as; i++)
-		free_pdir(&smmu->as[i]);
-	__free_page(smmu->avp_vector_page);
-	smmu_handle = NULL;
-	return 0;
-}
+	smmu_writel(smmu, value, SMMU_PTC_CONFIG);
 
-static const struct dev_pm_ops tegra_smmu_pm_ops = {
-	.suspend	= tegra_smmu_suspend,
-	.resume		= tegra_smmu_resume,
-};
+	value = SMMU_TLB_CONFIG_HIT_UNDER_MISS |
+		SMMU_TLB_CONFIG_ACTIVE_LINES(0x20);
 
-static const struct of_device_id tegra_smmu_of_match[] = {
-	{ .compatible = "nvidia,tegra30-smmu", },
-	{ },
-};
-MODULE_DEVICE_TABLE(of, tegra_smmu_of_match);
-
-static struct platform_driver tegra_smmu_driver = {
-	.probe		= tegra_smmu_probe,
-	.remove		= tegra_smmu_remove,
-	.driver = {
-		.owner	= THIS_MODULE,
-		.name	= "tegra-smmu",
-		.pm	= &tegra_smmu_pm_ops,
-		.of_match_table = tegra_smmu_of_match,
-	},
-};
+	if (soc->supports_round_robin_arbitration)
+		value |= SMMU_TLB_CONFIG_ROUND_ROBIN_ARBITRATION;
 
-static int tegra_smmu_init(void)
-{
-	return platform_driver_register(&tegra_smmu_driver);
-}
+	smmu_writel(smmu, value, SMMU_TLB_CONFIG);
 
-static void __exit tegra_smmu_exit(void)
-{
-	platform_driver_unregister(&tegra_smmu_driver);
-}
+	smmu_flush_ptc(smmu, NULL, 0);
+	smmu_flush_tlb(smmu);
+	smmu_writel(smmu, SMMU_CONFIG_ENABLE, SMMU_CONFIG);
+	smmu_flush(smmu);
+
+	tegra_smmu_ahb_enable();
 
-subsys_initcall(tegra_smmu_init);
-module_exit(tegra_smmu_exit);
+	err = bus_set_iommu(&platform_bus_type, &tegra_smmu_ops);
+	if (err < 0)
+		return ERR_PTR(err);
 
-MODULE_DESCRIPTION("IOMMU API for SMMU in Tegra30");
-MODULE_AUTHOR("Hiroshi DOYU <hdoyu@nvidia.com>");
-MODULE_ALIAS("platform:tegra-smmu");
-MODULE_LICENSE("GPL v2");
+	return smmu;
+}
diff --git a/drivers/memory/Kconfig b/drivers/memory/Kconfig
index 6d91c27fd4c..08bd4cfca2a 100644
--- a/drivers/memory/Kconfig
+++ b/drivers/memory/Kconfig
@@ -61,16 +61,6 @@ config TEGRA20_MC
 	  analysis, especially for IOMMU/GART(Graphics Address
 	  Relocation Table) module.
 
-config TEGRA30_MC
-	bool "Tegra30 Memory Controller(MC) driver"
-	default y
-	depends on ARCH_TEGRA_3x_SOC
-	help
-	  This driver is for the Memory Controller(MC) module available
-	  in Tegra30 SoCs, mainly for a address translation fault
-	  analysis, especially for IOMMU/SMMU(System Memory Management
-	  Unit) module.
-
 config FSL_CORENET_CF
 	tristate "Freescale CoreNet Error Reporting"
 	depends on FSL_SOC_BOOKE
@@ -85,4 +75,6 @@ config FSL_IFC
 	bool
 	depends on FSL_SOC
 
+source "drivers/memory/tegra/Kconfig"
+
 endif
diff --git a/drivers/memory/Makefile b/drivers/memory/Makefile
index c32d31981be..ad98bb23262 100644
--- a/drivers/memory/Makefile
+++ b/drivers/memory/Makefile
@@ -12,4 +12,5 @@ obj-$(CONFIG_FSL_CORENET_CF)	+= fsl-corenet-cf.o
 obj-$(CONFIG_FSL_IFC)		+= fsl_ifc.o
 obj-$(CONFIG_MVEBU_DEVBUS)	+= mvebu-devbus.o
 obj-$(CONFIG_TEGRA20_MC)	+= tegra20-mc.o
-obj-$(CONFIG_TEGRA30_MC)	+= tegra30-mc.o
+
+obj-$(CONFIG_TEGRA_MC)		+= tegra/
diff --git a/drivers/memory/tegra/Kconfig b/drivers/memory/tegra/Kconfig
new file mode 100644
index 00000000000..57108762182
--- /dev/null
+++ b/drivers/memory/tegra/Kconfig
@@ -0,0 +1,7 @@
+config TEGRA_MC
+	bool "NVIDIA Tegra Memory Controller support"
+	default y
+	depends on ARCH_TEGRA
+	help
+	  This driver supports the Memory Controller (MC) hardware found on
+	  NVIDIA Tegra SoCs.
diff --git a/drivers/memory/tegra/Makefile b/drivers/memory/tegra/Makefile
new file mode 100644
index 00000000000..0d9f497b786
--- /dev/null
+++ b/drivers/memory/tegra/Makefile
@@ -0,0 +1,7 @@
+tegra-mc-y := mc.o
+
+tegra-mc-$(CONFIG_ARCH_TEGRA_3x_SOC)  += tegra30.o
+tegra-mc-$(CONFIG_ARCH_TEGRA_114_SOC) += tegra114.o
+tegra-mc-$(CONFIG_ARCH_TEGRA_124_SOC) += tegra124.o
+
+obj-$(CONFIG_TEGRA_MC) += tegra-mc.o
diff --git a/drivers/memory/tegra/mc.c b/drivers/memory/tegra/mc.c
new file mode 100644
index 00000000000..fe3c44e7e1d
--- /dev/null
+++ b/drivers/memory/tegra/mc.c
@@ -0,0 +1,301 @@
+/*
+ * Copyright (C) 2014 NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "mc.h"
+
+#define MC_INTSTATUS 0x000
+#define  MC_INT_DECERR_MTS (1 << 16)
+#define  MC_INT_SECERR_SEC (1 << 13)
+#define  MC_INT_DECERR_VPR (1 << 12)
+#define  MC_INT_INVALID_APB_ASID_UPDATE (1 << 11)
+#define  MC_INT_INVALID_SMMU_PAGE (1 << 10)
+#define  MC_INT_ARBITRATION_EMEM (1 << 9)
+#define  MC_INT_SECURITY_VIOLATION (1 << 8)
+#define  MC_INT_DECERR_EMEM (1 << 6)
+
+#define MC_INTMASK 0x004
+
+#define MC_ERR_STATUS 0x08
+#define  MC_ERR_STATUS_TYPE_SHIFT 28
+#define  MC_ERR_STATUS_TYPE_INVALID_SMMU_PAGE (6 << MC_ERR_STATUS_TYPE_SHIFT)
+#define  MC_ERR_STATUS_TYPE_MASK (0x7 << MC_ERR_STATUS_TYPE_SHIFT)
+#define  MC_ERR_STATUS_READABLE (1 << 27)
+#define  MC_ERR_STATUS_WRITABLE (1 << 26)
+#define  MC_ERR_STATUS_NONSECURE (1 << 25)
+#define  MC_ERR_STATUS_ADR_HI_SHIFT 20
+#define  MC_ERR_STATUS_ADR_HI_MASK 0x3
+#define  MC_ERR_STATUS_SECURITY (1 << 17)
+#define  MC_ERR_STATUS_RW (1 << 16)
+#define  MC_ERR_STATUS_CLIENT_MASK 0x7f
+
+#define MC_ERR_ADR 0x0c
+
+#define MC_EMEM_ARB_CFG 0x90
+#define  MC_EMEM_ARB_CFG_CYCLES_PER_UPDATE(x)	(((x) & 0x1ff) << 0)
+#define  MC_EMEM_ARB_CFG_CYCLES_PER_UPDATE_MASK	0x1ff
+#define MC_EMEM_ARB_MISC0 0xd8
+
+static const struct of_device_id tegra_mc_of_match[] = {
+#ifdef CONFIG_ARCH_TEGRA_3x_SOC
+	{ .compatible = "nvidia,tegra30-mc", .data = &tegra30_mc_soc },
+#endif
+#ifdef CONFIG_ARCH_TEGRA_114_SOC
+	{ .compatible = "nvidia,tegra114-mc", .data = &tegra114_mc_soc },
+#endif
+#ifdef CONFIG_ARCH_TEGRA_124_SOC
+	{ .compatible = "nvidia,tegra124-mc", .data = &tegra124_mc_soc },
+#endif
+	{ }
+};
+MODULE_DEVICE_TABLE(of, tegra_mc_of_match);
+
+static int tegra_mc_setup_latency_allowance(struct tegra_mc *mc)
+{
+	unsigned long long tick;
+	unsigned int i;
+	u32 value;
+
+	/* compute the number of MC clock cycles per tick */
+	tick = mc->tick * clk_get_rate(mc->clk);
+	do_div(tick, NSEC_PER_SEC);
+
+	value = readl(mc->regs + MC_EMEM_ARB_CFG);
+	value &= ~MC_EMEM_ARB_CFG_CYCLES_PER_UPDATE_MASK;
+	value |= MC_EMEM_ARB_CFG_CYCLES_PER_UPDATE(tick);
+	writel(value, mc->regs + MC_EMEM_ARB_CFG);
+
+	/* write latency allowance defaults */
+	for (i = 0; i < mc->soc->num_clients; i++) {
+		const struct tegra_mc_la *la = &mc->soc->clients[i].la;
+		u32 value;
+
+		value = readl(mc->regs + la->reg);
+		value &= ~(la->mask << la->shift);
+		value |= (la->def & la->mask) << la->shift;
+		writel(value, mc->regs + la->reg);
+	}
+
+	return 0;
+}
+
+static const char *const status_names[32] = {
+	[ 1] = "External interrupt",
+	[ 6] = "EMEM address decode error",
+	[ 8] = "Security violation",
+	[ 9] = "EMEM arbitration error",
+	[10] = "Page fault",
+	[11] = "Invalid APB ASID update",
+	[12] = "VPR violation",
+	[13] = "Secure carveout violation",
+	[16] = "MTS carveout violation",
+};
+
+static const char *const error_names[8] = {
+	[2] = "EMEM decode error",
+	[3] = "TrustZone violation",
+	[4] = "Carveout violation",
+	[6] = "SMMU translation error",
+};
+
+static irqreturn_t tegra_mc_irq(int irq, void *data)
+{
+	struct tegra_mc *mc = data;
+	unsigned long status, mask;
+	unsigned int bit;
+
+	/* mask all interrupts to avoid flooding */
+	status = mc_readl(mc, MC_INTSTATUS);
+	mask = mc_readl(mc, MC_INTMASK);
+
+	for_each_set_bit(bit, &status, 32) {
+		const char *error = status_names[bit] ?: "unknown";
+		const char *client = "unknown", *desc;
+		const char *direction, *secure;
+		phys_addr_t addr = 0;
+		unsigned int i;
+		char perm[7];
+		u8 id, type;
+		u32 value;
+
+		value = mc_readl(mc, MC_ERR_STATUS);
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+		if (mc->soc->num_address_bits > 32) {
+			addr = ((value >> MC_ERR_STATUS_ADR_HI_SHIFT) &
+				MC_ERR_STATUS_ADR_HI_MASK);
+			addr <<= 32;
+		}
+#endif
+
+		if (value & MC_ERR_STATUS_RW)
+			direction = "write";
+		else
+			direction = "read";
+
+		if (value & MC_ERR_STATUS_SECURITY)
+			secure = "secure ";
+		else
+			secure = "";
+
+		id = value & MC_ERR_STATUS_CLIENT_MASK;
+
+		for (i = 0; i < mc->soc->num_clients; i++) {
+			if (mc->soc->clients[i].id == id) {
+				client = mc->soc->clients[i].name;
+				break;
+			}
+		}
+
+		type = (value & MC_ERR_STATUS_TYPE_MASK) >>
+		       MC_ERR_STATUS_TYPE_SHIFT;
+		desc = error_names[type];
+
+		switch (value & MC_ERR_STATUS_TYPE_MASK) {
+		case MC_ERR_STATUS_TYPE_INVALID_SMMU_PAGE:
+			perm[0] = ' ';
+			perm[1] = '[';
+
+			if (value & MC_ERR_STATUS_READABLE)
+				perm[2] = 'R';
+			else
+				perm[2] = '-';
+
+			if (value & MC_ERR_STATUS_WRITABLE)
+				perm[3] = 'W';
+			else
+				perm[3] = '-';
+
+			if (value & MC_ERR_STATUS_NONSECURE)
+				perm[4] = '-';
+			else
+				perm[4] = 'S';
+
+			perm[5] = ']';
+			perm[6] = '\0';
+			break;
+
+		default:
+			perm[0] = '\0';
+			break;
+		}
+
+		value = mc_readl(mc, MC_ERR_ADR);
+		addr |= value;
+
+		dev_err_ratelimited(mc->dev, "%s: %s%s @%pa: %s (%s%s)\n",
+				    client, secure, direction, &addr, error,
+				    desc, perm);
+	}
+
+	/* clear interrupts */
+	mc_writel(mc, status, MC_INTSTATUS);
+
+	return IRQ_HANDLED;
+}
+
+static int tegra_mc_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *match;
+	struct resource *res;
+	struct tegra_mc *mc;
+	u32 value;
+	int err;
+
+	match = of_match_node(tegra_mc_of_match, pdev->dev.of_node);
+	if (!match)
+		return -ENODEV;
+
+	mc = devm_kzalloc(&pdev->dev, sizeof(*mc), GFP_KERNEL);
+	if (!mc)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, mc);
+	mc->soc = match->data;
+	mc->dev = &pdev->dev;
+
+	/* length of MC tick in nanoseconds */
+	mc->tick = 30;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	mc->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(mc->regs))
+		return PTR_ERR(mc->regs);
+
+	mc->clk = devm_clk_get(&pdev->dev, "mc");
+	if (IS_ERR(mc->clk)) {
+		dev_err(&pdev->dev, "failed to get MC clock: %ld\n",
+			PTR_ERR(mc->clk));
+		return PTR_ERR(mc->clk);
+	}
+
+	err = tegra_mc_setup_latency_allowance(mc);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to setup latency allowance: %d\n",
+			err);
+		return err;
+	}
+
+	if (IS_ENABLED(CONFIG_TEGRA_IOMMU_SMMU)) {
+		mc->smmu = tegra_smmu_probe(&pdev->dev, mc->soc->smmu, mc);
+		if (IS_ERR(mc->smmu)) {
+			dev_err(&pdev->dev, "failed to probe SMMU: %ld\n",
+				PTR_ERR(mc->smmu));
+			return PTR_ERR(mc->smmu);
+		}
+	}
+
+	mc->irq = platform_get_irq(pdev, 0);
+	if (mc->irq < 0) {
+		dev_err(&pdev->dev, "interrupt not specified\n");
+		return mc->irq;
+	}
+
+	err = devm_request_irq(&pdev->dev, mc->irq, tegra_mc_irq, IRQF_SHARED,
+			       dev_name(&pdev->dev), mc);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to request IRQ#%u: %d\n", mc->irq,
+			err);
+		return err;
+	}
+
+	value = MC_INT_DECERR_MTS | MC_INT_SECERR_SEC | MC_INT_DECERR_VPR |
+		MC_INT_INVALID_APB_ASID_UPDATE | MC_INT_INVALID_SMMU_PAGE |
+		MC_INT_ARBITRATION_EMEM | MC_INT_SECURITY_VIOLATION |
+		MC_INT_DECERR_EMEM;
+	mc_writel(mc, value, MC_INTMASK);
+
+	return 0;
+}
+
+static struct platform_driver tegra_mc_driver = {
+	.driver = {
+		.name = "tegra-mc",
+		.of_match_table = tegra_mc_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.prevent_deferred_probe = true,
+	.probe = tegra_mc_probe,
+};
+
+static int tegra_mc_init(void)
+{
+	return platform_driver_register(&tegra_mc_driver);
+}
+arch_initcall(tegra_mc_init);
+
+MODULE_AUTHOR("Thierry Reding <treding@nvidia.com>");
+MODULE_DESCRIPTION("NVIDIA Tegra Memory Controller driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/memory/tegra/mc.h b/drivers/memory/tegra/mc.h
new file mode 100644
index 00000000000..d5d21147fc7
--- /dev/null
+++ b/drivers/memory/tegra/mc.h
@@ -0,0 +1,40 @@
+/*
+ * Copyright (C) 2014 NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MEMORY_TEGRA_MC_H
+#define MEMORY_TEGRA_MC_H
+
+#include <linux/io.h>
+#include <linux/types.h>
+
+#include <soc/tegra/mc.h>
+
+static inline u32 mc_readl(struct tegra_mc *mc, unsigned long offset)
+{
+	return readl(mc->regs + offset);
+}
+
+static inline void mc_writel(struct tegra_mc *mc, u32 value,
+			     unsigned long offset)
+{
+	writel(value, mc->regs + offset);
+}
+
+#ifdef CONFIG_ARCH_TEGRA_3x_SOC
+extern const struct tegra_mc_soc tegra30_mc_soc;
+#endif
+
+#ifdef CONFIG_ARCH_TEGRA_114_SOC
+extern const struct tegra_mc_soc tegra114_mc_soc;
+#endif
+
+#ifdef CONFIG_ARCH_TEGRA_124_SOC
+extern const struct tegra_mc_soc tegra124_mc_soc;
+#endif
+
+#endif /* MEMORY_TEGRA_MC_H */
diff --git a/drivers/memory/tegra/tegra114.c b/drivers/memory/tegra/tegra114.c
new file mode 100644
index 00000000000..511e9a25c15
--- /dev/null
+++ b/drivers/memory/tegra/tegra114.c
@@ -0,0 +1,948 @@
+/*
+ * Copyright (C) 2014 NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/of.h>
+#include <linux/mm.h>
+
+#include <asm/cacheflush.h>
+
+#include <dt-bindings/memory/tegra114-mc.h>
+
+#include "mc.h"
+
+static const struct tegra_mc_client tegra114_mc_clients[] = {
+	{
+		.id = 0x00,
+		.name = "ptcr",
+		.swgroup = TEGRA_SWGROUP_PTC,
+	}, {
+		.id = 0x01,
+		.name = "display0a",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 1,
+		},
+		.la = {
+			.reg = 0x2e8,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x02,
+		.name = "display0ab",
+		.swgroup = TEGRA_SWGROUP_DCB,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 2,
+		},
+		.la = {
+			.reg = 0x2f4,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x03,
+		.name = "display0b",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 3,
+		},
+		.la = {
+			.reg = 0x2e8,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x04,
+		.name = "display0bb",
+		.swgroup = TEGRA_SWGROUP_DCB,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 4,
+		},
+		.la = {
+			.reg = 0x2f4,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x05,
+		.name = "display0c",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 5,
+		},
+		.la = {
+			.reg = 0x2ec,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x06,
+		.name = "display0cb",
+		.swgroup = TEGRA_SWGROUP_DCB,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 6,
+		},
+		.la = {
+			.reg = 0x2f8,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x09,
+		.name = "eppup",
+		.swgroup = TEGRA_SWGROUP_EPP,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 9,
+		},
+		.la = {
+			.reg = 0x300,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x33,
+		},
+	}, {
+		.id = 0x0a,
+		.name = "g2pr",
+		.swgroup = TEGRA_SWGROUP_G2,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 10,
+		},
+		.la = {
+			.reg = 0x308,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x09,
+		},
+	}, {
+		.id = 0x0b,
+		.name = "g2sr",
+		.swgroup = TEGRA_SWGROUP_G2,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 11,
+		},
+		.la = {
+			.reg = 0x308,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x09,
+		},
+	}, {
+		.id = 0x0f,
+		.name = "avpcarm7r",
+		.swgroup = TEGRA_SWGROUP_AVPC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 15,
+		},
+		.la = {
+			.reg = 0x2e4,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x04,
+		},
+	}, {
+		.id = 0x10,
+		.name = "displayhc",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 16,
+		},
+		.la = {
+			.reg = 0x2f0,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x68,
+		},
+	}, {
+		.id = 0x11,
+		.name = "displayhcb",
+		.swgroup = TEGRA_SWGROUP_DCB,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 17,
+		},
+		.la = {
+			.reg = 0x2fc,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x68,
+		},
+	}, {
+		.id = 0x12,
+		.name = "fdcdrd",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 18,
+		},
+		.la = {
+			.reg = 0x334,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x0c,
+		},
+	}, {
+		.id = 0x13,
+		.name = "fdcdrd2",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 19,
+		},
+		.la = {
+			.reg = 0x33c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x0c,
+		},
+	}, {
+		.id = 0x14,
+		.name = "g2dr",
+		.swgroup = TEGRA_SWGROUP_G2,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 20,
+		},
+		.la = {
+			.reg = 0x30c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x0a,
+		},
+	}, {
+		.id = 0x15,
+		.name = "hdar",
+		.swgroup = TEGRA_SWGROUP_HDA,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 21,
+		},
+		.la = {
+			.reg = 0x318,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x16,
+		.name = "host1xdmar",
+		.swgroup = TEGRA_SWGROUP_HC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 22,
+		},
+		.la = {
+			.reg = 0x310,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x10,
+		},
+	}, {
+		.id = 0x17,
+		.name = "host1xr",
+		.swgroup = TEGRA_SWGROUP_HC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 23,
+		},
+		.la = {
+			.reg = 0x310,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xa5,
+		},
+	}, {
+		.id = 0x18,
+		.name = "idxsrd",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 24,
+		},
+		.la = {
+			.reg = 0x334,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x0b,
+		},
+	}, {
+		.id = 0x1c,
+		.name = "msencsrd",
+		.swgroup = TEGRA_SWGROUP_MSENC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 28,
+		},
+		.la = {
+			.reg = 0x328,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x1d,
+		.name = "ppcsahbdmar",
+		.swgroup = TEGRA_SWGROUP_PPCS,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 29,
+		},
+		.la = {
+			.reg = 0x344,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	}, {
+		.id = 0x1e,
+		.name = "ppcsahbslvr",
+		.swgroup = TEGRA_SWGROUP_PPCS,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 30,
+		},
+		.la = {
+			.reg = 0x344,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xe8,
+		},
+	}, {
+		.id = 0x20,
+		.name = "texl2srd",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 0,
+		},
+		.la = {
+			.reg = 0x338,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x0c,
+		},
+	}, {
+		.id = 0x22,
+		.name = "vdebsevr",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 2,
+		},
+		.la = {
+			.reg = 0x354,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x23,
+		.name = "vdember",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 3,
+		},
+		.la = {
+			.reg = 0x354,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x24,
+		.name = "vdemcer",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 4,
+		},
+		.la = {
+			.reg = 0x358,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xb8,
+		},
+	}, {
+		.id = 0x25,
+		.name = "vdetper",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 5,
+		},
+		.la = {
+			.reg = 0x358,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xee,
+		},
+	}, {
+		.id = 0x26,
+		.name = "mpcorelpr",
+		.swgroup = TEGRA_SWGROUP_MPCORELP,
+		.la = {
+			.reg = 0x324,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x04,
+		},
+	}, {
+		.id = 0x27,
+		.name = "mpcorer",
+		.swgroup = TEGRA_SWGROUP_MPCORE,
+		.la = {
+			.reg = 0x320,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x04,
+		},
+	}, {
+		.id = 0x28,
+		.name = "eppu",
+		.swgroup = TEGRA_SWGROUP_EPP,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 8,
+		},
+		.la = {
+			.reg = 0x300,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x33,
+		},
+	}, {
+		.id = 0x29,
+		.name = "eppv",
+		.swgroup = TEGRA_SWGROUP_EPP,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 9,
+		},
+		.la = {
+			.reg = 0x304,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x6c,
+		},
+	}, {
+		.id = 0x2a,
+		.name = "eppy",
+		.swgroup = TEGRA_SWGROUP_EPP,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 10,
+		},
+		.la = {
+			.reg = 0x304,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x6c,
+		},
+	}, {
+		.id = 0x2b,
+		.name = "msencswr",
+		.swgroup = TEGRA_SWGROUP_MSENC,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 11,
+		},
+		.la = {
+			.reg = 0x328,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x2c,
+		.name = "viwsb",
+		.swgroup = TEGRA_SWGROUP_VI,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 12,
+		},
+		.la = {
+			.reg = 0x364,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x47,
+		},
+	}, {
+		.id = 0x2d,
+		.name = "viwu",
+		.swgroup = TEGRA_SWGROUP_VI,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 13,
+		},
+		.la = {
+			.reg = 0x368,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x2e,
+		.name = "viwv",
+		.swgroup = TEGRA_SWGROUP_VI,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 14,
+		},
+		.la = {
+			.reg = 0x368,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x2f,
+		.name = "viwy",
+		.swgroup = TEGRA_SWGROUP_VI,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 15,
+		},
+		.la = {
+			.reg = 0x36c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x47,
+		},
+	}, {
+		.id = 0x30,
+		.name = "g2dw",
+		.swgroup = TEGRA_SWGROUP_G2,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 16,
+		},
+		.la = {
+			.reg = 0x30c,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x9,
+		},
+	}, {
+		.id = 0x32,
+		.name = "avpcarm7w",
+		.swgroup = TEGRA_SWGROUP_AVPC,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 18,
+		},
+		.la = {
+			.reg = 0x2e4,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x0e,
+		},
+	}, {
+		.id = 0x33,
+		.name = "fdcdwr",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 19,
+		},
+		.la = {
+			.reg = 0x338,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x10,
+		},
+	}, {
+		.id = 0x34,
+		.name = "fdcwr2",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 20,
+		},
+		.la = {
+			.reg = 0x340,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x10,
+		},
+	}, {
+		.id = 0x35,
+		.name = "hdaw",
+		.swgroup = TEGRA_SWGROUP_HDA,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 21,
+		},
+		.la = {
+			.reg = 0x318,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x36,
+		.name = "host1xw",
+		.swgroup = TEGRA_SWGROUP_HC,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 22,
+		},
+		.la = {
+			.reg = 0x314,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x25,
+		},
+	}, {
+		.id = 0x37,
+		.name = "ispw",
+		.swgroup = TEGRA_SWGROUP_ISP,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 23,
+		},
+		.la = {
+			.reg = 0x31c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x38,
+		.name = "mpcorelpw",
+		.swgroup = TEGRA_SWGROUP_MPCORELP,
+		.la = {
+			.reg = 0x324,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x39,
+		.name = "mpcorew",
+		.swgroup = TEGRA_SWGROUP_MPCORE,
+		.la = {
+			.reg = 0x320,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x0e,
+		},
+	}, {
+		.id = 0x3b,
+		.name = "ppcsahbdmaw",
+		.swgroup = TEGRA_SWGROUP_PPCS,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 27,
+		},
+		.la = {
+			.reg = 0x348,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xa5,
+		},
+	}, {
+		.id = 0x3c,
+		.name = "ppcsahbslvw",
+		.swgroup = TEGRA_SWGROUP_PPCS,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 28,
+		},
+		.la = {
+			.reg = 0x348,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xe8,
+		},
+	}, {
+		.id = 0x3e,
+		.name = "vdebsevw",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 30,
+		},
+		.la = {
+			.reg = 0x35c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x3f,
+		.name = "vdedbgw",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 31,
+		},
+		.la = {
+			.reg = 0x35c,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x40,
+		.name = "vdembew",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 0,
+		},
+		.la = {
+			.reg = 0x360,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x89,
+		},
+	}, {
+		.id = 0x41,
+		.name = "vdetpmw",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 1,
+		},
+		.la = {
+			.reg = 0x360,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x59,
+		},
+	}, {
+		.id = 0x4a,
+		.name = "xusb_hostr",
+		.swgroup = TEGRA_SWGROUP_XUSB_HOST,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 10,
+		},
+		.la = {
+			.reg = 0x37c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xa5,
+		},
+	}, {
+		.id = 0x4b,
+		.name = "xusb_hostw",
+		.swgroup = TEGRA_SWGROUP_XUSB_HOST,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 11,
+		},
+		.la = {
+			.reg = 0x37c,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xa5,
+		},
+	}, {
+		.id = 0x4c,
+		.name = "xusb_devr",
+		.swgroup = TEGRA_SWGROUP_XUSB_DEV,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 12,
+		},
+		.la = {
+			.reg = 0x380,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xa5,
+		},
+	}, {
+		.id = 0x4d,
+		.name = "xusb_devw",
+		.swgroup = TEGRA_SWGROUP_XUSB_DEV,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 13,
+		},
+		.la = {
+			.reg = 0x380,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xa5,
+		},
+	}, {
+		.id = 0x4e,
+		.name = "fdcdwr3",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 14,
+		},
+		.la = {
+			.reg = 0x388,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x10,
+		},
+	}, {
+		.id = 0x4f,
+		.name = "fdcdrd3",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 15,
+		},
+		.la = {
+			.reg = 0x384,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x0c,
+		},
+	}, {
+		.id = 0x50,
+		.name = "fdcwr4",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 16,
+		},
+		.la = {
+			.reg = 0x388,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x10,
+		},
+	}, {
+		.id = 0x51,
+		.name = "fdcrd4",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 17,
+		},
+		.la = {
+			.reg = 0x384,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x0c,
+		},
+	}, {
+		.id = 0x52,
+		.name = "emucifr",
+		.swgroup = TEGRA_SWGROUP_EMUCIF,
+		.la = {
+			.reg = 0x38c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x04,
+		},
+	}, {
+		.id = 0x53,
+		.name = "emucifw",
+		.swgroup = TEGRA_SWGROUP_EMUCIF,
+		.la = {
+			.reg = 0x38c,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x0e,
+		},
+	}, {
+		.id = 0x54,
+		.name = "tsecsrd",
+		.swgroup = TEGRA_SWGROUP_TSEC,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 20,
+		},
+		.la = {
+			.reg = 0x390,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	}, {
+		.id = 0x55,
+		.name = "tsecswr",
+		.swgroup = TEGRA_SWGROUP_TSEC,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 21,
+		},
+		.la = {
+			.reg = 0x390,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	},
+};
+
+static const struct tegra_smmu_swgroup tegra114_swgroups[] = {
+	{ .swgroup = TEGRA_SWGROUP_DC,        .reg = 0x240 },
+	{ .swgroup = TEGRA_SWGROUP_DCB,       .reg = 0x244 },
+	{ .swgroup = TEGRA_SWGROUP_EPP,       .reg = 0x248 },
+	{ .swgroup = TEGRA_SWGROUP_G2,        .reg = 0x24c },
+	{ .swgroup = TEGRA_SWGROUP_AVPC,      .reg = 0x23c },
+	{ .swgroup = TEGRA_SWGROUP_NV,        .reg = 0x268 },
+	{ .swgroup = TEGRA_SWGROUP_HDA,       .reg = 0x254 },
+	{ .swgroup = TEGRA_SWGROUP_HC,        .reg = 0x250 },
+	{ .swgroup = TEGRA_SWGROUP_MSENC,     .reg = 0x264 },
+	{ .swgroup = TEGRA_SWGROUP_PPCS,      .reg = 0x270 },
+	{ .swgroup = TEGRA_SWGROUP_VDE,       .reg = 0x27c },
+	{ .swgroup = TEGRA_SWGROUP_VI,        .reg = 0x280 },
+	{ .swgroup = TEGRA_SWGROUP_ISP,       .reg = 0x258 },
+	{ .swgroup = TEGRA_SWGROUP_XUSB_HOST, .reg = 0x288 },
+	{ .swgroup = TEGRA_SWGROUP_XUSB_DEV,  .reg = 0x28c },
+	{ .swgroup = TEGRA_SWGROUP_TSEC,      .reg = 0x294 },
+};
+
+static void tegra114_flush_dcache(struct page *page, unsigned long offset,
+				  size_t size)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	void *virt = page_address(page) + offset;
+
+	__cpuc_flush_dcache_area(virt, size);
+	outer_flush_range(phys, phys + size);
+}
+
+static const struct tegra_smmu_ops tegra114_smmu_ops = {
+	.flush_dcache = tegra114_flush_dcache,
+};
+
+static const struct tegra_smmu_soc tegra114_smmu_soc = {
+	.clients = tegra114_mc_clients,
+	.num_clients = ARRAY_SIZE(tegra114_mc_clients),
+	.swgroups = tegra114_swgroups,
+	.num_swgroups = ARRAY_SIZE(tegra114_swgroups),
+	.supports_round_robin_arbitration = false,
+	.supports_request_limit = false,
+	.num_asids = 4,
+	.ops = &tegra114_smmu_ops,
+};
+
+const struct tegra_mc_soc tegra114_mc_soc = {
+	.clients = tegra114_mc_clients,
+	.num_clients = ARRAY_SIZE(tegra114_mc_clients),
+	.num_address_bits = 32,
+	.atom_size = 32,
+	.smmu = &tegra114_smmu_soc,
+};
diff --git a/drivers/memory/tegra/tegra124.c b/drivers/memory/tegra/tegra124.c
new file mode 100644
index 00000000000..278d40b854c
--- /dev/null
+++ b/drivers/memory/tegra/tegra124.c
@@ -0,0 +1,995 @@
+/*
+ * Copyright (C) 2014 NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/of.h>
+#include <linux/mm.h>
+
+#include <asm/cacheflush.h>
+
+#include <dt-bindings/memory/tegra124-mc.h>
+
+#include "mc.h"
+
+static const struct tegra_mc_client tegra124_mc_clients[] = {
+	{
+		.id = 0x00,
+		.name = "ptcr",
+		.swgroup = TEGRA_SWGROUP_PTC,
+	}, {
+		.id = 0x01,
+		.name = "display0a",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 1,
+		},
+		.la = {
+			.reg = 0x2e8,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xc2,
+		},
+	}, {
+		.id = 0x02,
+		.name = "display0ab",
+		.swgroup = TEGRA_SWGROUP_DCB,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 2,
+		},
+		.la = {
+			.reg = 0x2f4,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xc6,
+		},
+	}, {
+		.id = 0x03,
+		.name = "display0b",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 3,
+		},
+		.la = {
+			.reg = 0x2e8,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	}, {
+		.id = 0x04,
+		.name = "display0bb",
+		.swgroup = TEGRA_SWGROUP_DCB,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 4,
+		},
+		.la = {
+			.reg = 0x2f4,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	}, {
+		.id = 0x05,
+		.name = "display0c",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 5,
+		},
+		.la = {
+			.reg = 0x2ec,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	}, {
+		.id = 0x06,
+		.name = "display0cb",
+		.swgroup = TEGRA_SWGROUP_DCB,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 6,
+		},
+		.la = {
+			.reg = 0x2f8,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	}, {
+		.id = 0x0e,
+		.name = "afir",
+		.swgroup = TEGRA_SWGROUP_AFI,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 14,
+		},
+		.la = {
+			.reg = 0x2e0,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x13,
+		},
+	}, {
+		.id = 0x0f,
+		.name = "avpcarm7r",
+		.swgroup = TEGRA_SWGROUP_AVPC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 15,
+		},
+		.la = {
+			.reg = 0x2e4,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x04,
+		},
+	}, {
+		.id = 0x10,
+		.name = "displayhc",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 16,
+		},
+		.la = {
+			.reg = 0x2f0,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	}, {
+		.id = 0x11,
+		.name = "displayhcb",
+		.swgroup = TEGRA_SWGROUP_DCB,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 17,
+		},
+		.la = {
+			.reg = 0x2fc,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	}, {
+		.id = 0x15,
+		.name = "hdar",
+		.swgroup = TEGRA_SWGROUP_HDA,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 21,
+		},
+		.la = {
+			.reg = 0x318,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x24,
+		},
+	}, {
+		.id = 0x16,
+		.name = "host1xdmar",
+		.swgroup = TEGRA_SWGROUP_HC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 22,
+		},
+		.la = {
+			.reg = 0x310,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x1e,
+		},
+	}, {
+		.id = 0x17,
+		.name = "host1xr",
+		.swgroup = TEGRA_SWGROUP_HC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 23,
+		},
+		.la = {
+			.reg = 0x310,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	}, {
+		.id = 0x1c,
+		.name = "msencsrd",
+		.swgroup = TEGRA_SWGROUP_MSENC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 28,
+		},
+		.la = {
+			.reg = 0x328,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x23,
+		},
+	}, {
+		.id = 0x1d,
+		.name = "ppcsahbdmar",
+		.swgroup = TEGRA_SWGROUP_PPCS,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 29,
+		},
+		.la = {
+			.reg = 0x344,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x49,
+		},
+	}, {
+		.id = 0x1e,
+		.name = "ppcsahbslvr",
+		.swgroup = TEGRA_SWGROUP_PPCS,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 30,
+		},
+		.la = {
+			.reg = 0x344,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x1a,
+		},
+	}, {
+		.id = 0x1f,
+		.name = "satar",
+		.swgroup = TEGRA_SWGROUP_SATA,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 31,
+		},
+		.la = {
+			.reg = 0x350,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x65,
+		},
+	}, {
+		.id = 0x22,
+		.name = "vdebsevr",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 2,
+		},
+		.la = {
+			.reg = 0x354,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x4f,
+		},
+	}, {
+		.id = 0x23,
+		.name = "vdember",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 3,
+		},
+		.la = {
+			.reg = 0x354,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x3d,
+		},
+	}, {
+		.id = 0x24,
+		.name = "vdemcer",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 4,
+		},
+		.la = {
+			.reg = 0x358,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x66,
+		},
+	}, {
+		.id = 0x25,
+		.name = "vdetper",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 5,
+		},
+		.la = {
+			.reg = 0x358,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xa5,
+		},
+	}, {
+		.id = 0x26,
+		.name = "mpcorelpr",
+		.swgroup = TEGRA_SWGROUP_MPCORELP,
+		.la = {
+			.reg = 0x324,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x04,
+		},
+	}, {
+		.id = 0x27,
+		.name = "mpcorer",
+		.swgroup = TEGRA_SWGROUP_MPCORE,
+		.la = {
+			.reg = 0x320,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x04,
+		},
+	}, {
+		.id = 0x2b,
+		.name = "msencswr",
+		.swgroup = TEGRA_SWGROUP_MSENC,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 11,
+		},
+		.la = {
+			.reg = 0x328,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x31,
+		.name = "afiw",
+		.swgroup = TEGRA_SWGROUP_AFI,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 17,
+		},
+		.la = {
+			.reg = 0x2e0,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x32,
+		.name = "avpcarm7w",
+		.swgroup = TEGRA_SWGROUP_AVPC,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 18,
+		},
+		.la = {
+			.reg = 0x2e4,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x35,
+		.name = "hdaw",
+		.swgroup = TEGRA_SWGROUP_HDA,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 21,
+		},
+		.la = {
+			.reg = 0x318,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x36,
+		.name = "host1xw",
+		.swgroup = TEGRA_SWGROUP_HC,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 22,
+		},
+		.la = {
+			.reg = 0x314,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x38,
+		.name = "mpcorelpw",
+		.swgroup = TEGRA_SWGROUP_MPCORELP,
+		.la = {
+			.reg = 0x324,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x39,
+		.name = "mpcorew",
+		.swgroup = TEGRA_SWGROUP_MPCORE,
+		.la = {
+			.reg = 0x320,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x3b,
+		.name = "ppcsahbdmaw",
+		.swgroup = TEGRA_SWGROUP_PPCS,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 27,
+		},
+		.la = {
+			.reg = 0x348,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x3c,
+		.name = "ppcsahbslvw",
+		.swgroup = TEGRA_SWGROUP_PPCS,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 28,
+		},
+		.la = {
+			.reg = 0x348,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x3d,
+		.name = "sataw",
+		.swgroup = TEGRA_SWGROUP_SATA,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 29,
+		},
+		.la = {
+			.reg = 0x350,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x65,
+		},
+	}, {
+		.id = 0x3e,
+		.name = "vdebsevw",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 30,
+		},
+		.la = {
+			.reg = 0x35c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x3f,
+		.name = "vdedbgw",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 31,
+		},
+		.la = {
+			.reg = 0x35c,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x40,
+		.name = "vdembew",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 0,
+		},
+		.la = {
+			.reg = 0x360,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x41,
+		.name = "vdetpmw",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 1,
+		},
+		.la = {
+			.reg = 0x360,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x44,
+		.name = "ispra",
+		.swgroup = TEGRA_SWGROUP_ISP2,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 4,
+		},
+		.la = {
+			.reg = 0x370,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x18,
+		},
+	}, {
+		.id = 0x46,
+		.name = "ispwa",
+		.swgroup = TEGRA_SWGROUP_ISP2,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 6,
+		},
+		.la = {
+			.reg = 0x374,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x47,
+		.name = "ispwb",
+		.swgroup = TEGRA_SWGROUP_ISP2,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 7,
+		},
+		.la = {
+			.reg = 0x374,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x4a,
+		.name = "xusb_hostr",
+		.swgroup = TEGRA_SWGROUP_XUSB_HOST,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 10,
+		},
+		.la = {
+			.reg = 0x37c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x39,
+		},
+	}, {
+		.id = 0x4b,
+		.name = "xusb_hostw",
+		.swgroup = TEGRA_SWGROUP_XUSB_HOST,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 11,
+		},
+		.la = {
+			.reg = 0x37c,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x4c,
+		.name = "xusb_devr",
+		.swgroup = TEGRA_SWGROUP_XUSB_DEV,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 12,
+		},
+		.la = {
+			.reg = 0x380,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x39,
+		},
+	}, {
+		.id = 0x4d,
+		.name = "xusb_devw",
+		.swgroup = TEGRA_SWGROUP_XUSB_DEV,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 13,
+		},
+		.la = {
+			.reg = 0x380,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x4e,
+		.name = "isprab",
+		.swgroup = TEGRA_SWGROUP_ISP2B,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 14,
+		},
+		.la = {
+			.reg = 0x384,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x18,
+		},
+	}, {
+		.id = 0x50,
+		.name = "ispwab",
+		.swgroup = TEGRA_SWGROUP_ISP2B,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 16,
+		},
+		.la = {
+			.reg = 0x388,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x51,
+		.name = "ispwbb",
+		.swgroup = TEGRA_SWGROUP_ISP2B,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 17,
+		},
+		.la = {
+			.reg = 0x388,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x54,
+		.name = "tsecsrd",
+		.swgroup = TEGRA_SWGROUP_TSEC,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 20,
+		},
+		.la = {
+			.reg = 0x390,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x9b,
+		},
+	}, {
+		.id = 0x55,
+		.name = "tsecswr",
+		.swgroup = TEGRA_SWGROUP_TSEC,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 21,
+		},
+		.la = {
+			.reg = 0x390,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x56,
+		.name = "a9avpscr",
+		.swgroup = TEGRA_SWGROUP_A9AVP,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 22,
+		},
+		.la = {
+			.reg = 0x3a4,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x04,
+		},
+	}, {
+		.id = 0x57,
+		.name = "a9avpscw",
+		.swgroup = TEGRA_SWGROUP_A9AVP,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 23,
+		},
+		.la = {
+			.reg = 0x3a4,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x58,
+		.name = "gpusrd",
+		.swgroup = TEGRA_SWGROUP_GPU,
+		.smmu = {
+			/* read-only */
+			.reg = 0x230,
+			.bit = 24,
+		},
+		.la = {
+			.reg = 0x3c8,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x1a,
+		},
+	}, {
+		.id = 0x59,
+		.name = "gpuswr",
+		.swgroup = TEGRA_SWGROUP_GPU,
+		.smmu = {
+			/* read-only */
+			.reg = 0x230,
+			.bit = 25,
+		},
+		.la = {
+			.reg = 0x3c8,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x5a,
+		.name = "displayt",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 26,
+		},
+		.la = {
+			.reg = 0x2f0,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	}, {
+		.id = 0x60,
+		.name = "sdmmcra",
+		.swgroup = TEGRA_SWGROUP_SDMMC1A,
+		.smmu = {
+			.reg = 0x234,
+			.bit = 0,
+		},
+		.la = {
+			.reg = 0x3b8,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x49,
+		},
+	}, {
+		.id = 0x61,
+		.name = "sdmmcraa",
+		.swgroup = TEGRA_SWGROUP_SDMMC2A,
+		.smmu = {
+			.reg = 0x234,
+			.bit = 1,
+		},
+		.la = {
+			.reg = 0x3bc,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x49,
+		},
+	}, {
+		.id = 0x62,
+		.name = "sdmmcr",
+		.swgroup = TEGRA_SWGROUP_SDMMC3A,
+		.smmu = {
+			.reg = 0x234,
+			.bit = 2,
+		},
+		.la = {
+			.reg = 0x3c0,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x49,
+		},
+	}, {
+		.id = 0x63,
+		.swgroup = TEGRA_SWGROUP_SDMMC4A,
+		.name = "sdmmcrab",
+		.smmu = {
+			.reg = 0x234,
+			.bit = 3,
+		},
+		.la = {
+			.reg = 0x3c4,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x49,
+		},
+	}, {
+		.id = 0x64,
+		.name = "sdmmcwa",
+		.swgroup = TEGRA_SWGROUP_SDMMC1A,
+		.smmu = {
+			.reg = 0x234,
+			.bit = 4,
+		},
+		.la = {
+			.reg = 0x3b8,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x65,
+		.name = "sdmmcwaa",
+		.swgroup = TEGRA_SWGROUP_SDMMC2A,
+		.smmu = {
+			.reg = 0x234,
+			.bit = 5,
+		},
+		.la = {
+			.reg = 0x3bc,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x66,
+		.name = "sdmmcw",
+		.swgroup = TEGRA_SWGROUP_SDMMC3A,
+		.smmu = {
+			.reg = 0x234,
+			.bit = 6,
+		},
+		.la = {
+			.reg = 0x3c0,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x67,
+		.name = "sdmmcwab",
+		.swgroup = TEGRA_SWGROUP_SDMMC4A,
+		.smmu = {
+			.reg = 0x234,
+			.bit = 7,
+		},
+		.la = {
+			.reg = 0x3c4,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x6c,
+		.name = "vicsrd",
+		.swgroup = TEGRA_SWGROUP_VIC,
+		.smmu = {
+			.reg = 0x234,
+			.bit = 12,
+		},
+		.la = {
+			.reg = 0x394,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x1a,
+		},
+	}, {
+		.id = 0x6d,
+		.name = "vicswr",
+		.swgroup = TEGRA_SWGROUP_VIC,
+		.smmu = {
+			.reg = 0x234,
+			.bit = 13,
+		},
+		.la = {
+			.reg = 0x394,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x72,
+		.name = "viw",
+		.swgroup = TEGRA_SWGROUP_VI,
+		.smmu = {
+			.reg = 0x234,
+			.bit = 18,
+		},
+		.la = {
+			.reg = 0x398,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x73,
+		.name = "displayd",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x234,
+			.bit = 19,
+		},
+		.la = {
+			.reg = 0x3c8,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	},
+};
+
+static const struct tegra_smmu_swgroup tegra124_swgroups[] = {
+	{ .swgroup = TEGRA_SWGROUP_DC,        .reg = 0x240 },
+	{ .swgroup = TEGRA_SWGROUP_DCB,       .reg = 0x244 },
+	{ .swgroup = TEGRA_SWGROUP_AFI,       .reg = 0x238 },
+	{ .swgroup = TEGRA_SWGROUP_AVPC,      .reg = 0x23c },
+	{ .swgroup = TEGRA_SWGROUP_HDA,       .reg = 0x254 },
+	{ .swgroup = TEGRA_SWGROUP_HC,        .reg = 0x250 },
+	{ .swgroup = TEGRA_SWGROUP_MSENC,     .reg = 0x264 },
+	{ .swgroup = TEGRA_SWGROUP_PPCS,      .reg = 0x270 },
+	{ .swgroup = TEGRA_SWGROUP_SATA,      .reg = 0x274 },
+	{ .swgroup = TEGRA_SWGROUP_VDE,       .reg = 0x27c },
+	{ .swgroup = TEGRA_SWGROUP_ISP2,      .reg = 0x258 },
+	{ .swgroup = TEGRA_SWGROUP_XUSB_HOST, .reg = 0x288 },
+	{ .swgroup = TEGRA_SWGROUP_XUSB_DEV,  .reg = 0x28c },
+	{ .swgroup = TEGRA_SWGROUP_ISP2B,     .reg = 0xaa4 },
+	{ .swgroup = TEGRA_SWGROUP_TSEC,      .reg = 0x294 },
+	{ .swgroup = TEGRA_SWGROUP_A9AVP,     .reg = 0x290 },
+	{ .swgroup = TEGRA_SWGROUP_GPU,       .reg = 0xaac },
+	{ .swgroup = TEGRA_SWGROUP_SDMMC1A,   .reg = 0xa94 },
+	{ .swgroup = TEGRA_SWGROUP_SDMMC2A,   .reg = 0xa98 },
+	{ .swgroup = TEGRA_SWGROUP_SDMMC3A,   .reg = 0xa9c },
+	{ .swgroup = TEGRA_SWGROUP_SDMMC4A,   .reg = 0xaa0 },
+	{ .swgroup = TEGRA_SWGROUP_VIC,       .reg = 0x284 },
+	{ .swgroup = TEGRA_SWGROUP_VI,        .reg = 0x280 },
+};
+
+#ifdef CONFIG_ARCH_TEGRA_124_SOC
+static void tegra124_flush_dcache(struct page *page, unsigned long offset,
+				  size_t size)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	void *virt = page_address(page) + offset;
+
+	__cpuc_flush_dcache_area(virt, size);
+	outer_flush_range(phys, phys + size);
+}
+
+static const struct tegra_smmu_ops tegra124_smmu_ops = {
+	.flush_dcache = tegra124_flush_dcache,
+};
+
+static const struct tegra_smmu_soc tegra124_smmu_soc = {
+	.clients = tegra124_mc_clients,
+	.num_clients = ARRAY_SIZE(tegra124_mc_clients),
+	.swgroups = tegra124_swgroups,
+	.num_swgroups = ARRAY_SIZE(tegra124_swgroups),
+	.supports_round_robin_arbitration = true,
+	.supports_request_limit = true,
+	.num_asids = 128,
+	.ops = &tegra124_smmu_ops,
+};
+
+const struct tegra_mc_soc tegra124_mc_soc = {
+	.clients = tegra124_mc_clients,
+	.num_clients = ARRAY_SIZE(tegra124_mc_clients),
+	.num_address_bits = 34,
+	.atom_size = 32,
+	.smmu = &tegra124_smmu_soc,
+};
+#endif /* CONFIG_ARCH_TEGRA_124_SOC */
diff --git a/drivers/memory/tegra/tegra30.c b/drivers/memory/tegra/tegra30.c
new file mode 100644
index 00000000000..71fe9376fe5
--- /dev/null
+++ b/drivers/memory/tegra/tegra30.c
@@ -0,0 +1,970 @@
+/*
+ * Copyright (C) 2014 NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/of.h>
+#include <linux/mm.h>
+
+#include <asm/cacheflush.h>
+
+#include <dt-bindings/memory/tegra30-mc.h>
+
+#include "mc.h"
+
+static const struct tegra_mc_client tegra30_mc_clients[] = {
+	{
+		.id = 0x00,
+		.name = "ptcr",
+		.swgroup = TEGRA_SWGROUP_PTC,
+	}, {
+		.id = 0x01,
+		.name = "display0a",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 1,
+		},
+		.la = {
+			.reg = 0x2e8,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x02,
+		.name = "display0ab",
+		.swgroup = TEGRA_SWGROUP_DCB,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 2,
+		},
+		.la = {
+			.reg = 0x2f4,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x03,
+		.name = "display0b",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 3,
+		},
+		.la = {
+			.reg = 0x2e8,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x04,
+		.name = "display0bb",
+		.swgroup = TEGRA_SWGROUP_DCB,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 4,
+		},
+		.la = {
+			.reg = 0x2f4,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x05,
+		.name = "display0c",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 5,
+		},
+		.la = {
+			.reg = 0x2ec,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x06,
+		.name = "display0cb",
+		.swgroup = TEGRA_SWGROUP_DCB,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 6,
+		},
+		.la = {
+			.reg = 0x2f8,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x07,
+		.name = "display1b",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 7,
+		},
+		.la = {
+			.reg = 0x2ec,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x08,
+		.name = "display1bb",
+		.swgroup = TEGRA_SWGROUP_DCB,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 8,
+		},
+		.la = {
+			.reg = 0x2f8,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x4e,
+		},
+	}, {
+		.id = 0x09,
+		.name = "eppup",
+		.swgroup = TEGRA_SWGROUP_EPP,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 9,
+		},
+		.la = {
+			.reg = 0x300,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x17,
+		},
+	}, {
+		.id = 0x0a,
+		.name = "g2pr",
+		.swgroup = TEGRA_SWGROUP_G2,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 10,
+		},
+		.la = {
+			.reg = 0x308,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x09,
+		},
+	}, {
+		.id = 0x0b,
+		.name = "g2sr",
+		.swgroup = TEGRA_SWGROUP_G2,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 11,
+		},
+		.la = {
+			.reg = 0x308,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x09,
+		},
+	}, {
+		.id = 0x0c,
+		.name = "mpeunifbr",
+		.swgroup = TEGRA_SWGROUP_MPE,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 12,
+		},
+		.la = {
+			.reg = 0x328,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	}, {
+		.id = 0x0d,
+		.name = "viruv",
+		.swgroup = TEGRA_SWGROUP_VI,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 13,
+		},
+		.la = {
+			.reg = 0x364,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x2c,
+		},
+	}, {
+		.id = 0x0e,
+		.name = "afir",
+		.swgroup = TEGRA_SWGROUP_AFI,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 14,
+		},
+		.la = {
+			.reg = 0x2e0,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x10,
+		},
+	}, {
+		.id = 0x0f,
+		.name = "avpcarm7r",
+		.swgroup = TEGRA_SWGROUP_AVPC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 15,
+		},
+		.la = {
+			.reg = 0x2e4,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x04,
+		},
+	}, {
+		.id = 0x10,
+		.name = "displayhc",
+		.swgroup = TEGRA_SWGROUP_DC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 16,
+		},
+		.la = {
+			.reg = 0x2f0,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x11,
+		.name = "displayhcb",
+		.swgroup = TEGRA_SWGROUP_DCB,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 17,
+		},
+		.la = {
+			.reg = 0x2fc,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x12,
+		.name = "fdcdrd",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 18,
+		},
+		.la = {
+			.reg = 0x334,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x0a,
+		},
+	}, {
+		.id = 0x13,
+		.name = "fdcdrd2",
+		.swgroup = TEGRA_SWGROUP_NV2,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 19,
+		},
+		.la = {
+			.reg = 0x33c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x0a,
+		},
+	}, {
+		.id = 0x14,
+		.name = "g2dr",
+		.swgroup = TEGRA_SWGROUP_G2,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 20,
+		},
+		.la = {
+			.reg = 0x30c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x0a,
+		},
+	}, {
+		.id = 0x15,
+		.name = "hdar",
+		.swgroup = TEGRA_SWGROUP_HDA,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 21,
+		},
+		.la = {
+			.reg = 0x318,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x16,
+		.name = "host1xdmar",
+		.swgroup = TEGRA_SWGROUP_HC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 22,
+		},
+		.la = {
+			.reg = 0x310,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x05,
+		},
+	}, {
+		.id = 0x17,
+		.name = "host1xr",
+		.swgroup = TEGRA_SWGROUP_HC,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 23,
+		},
+		.la = {
+			.reg = 0x310,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x50,
+		},
+	}, {
+		.id = 0x18,
+		.name = "idxsrd",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 24,
+		},
+		.la = {
+			.reg = 0x334,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x13,
+		},
+	}, {
+		.id = 0x19,
+		.name = "idxsrd2",
+		.swgroup = TEGRA_SWGROUP_NV2,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 25,
+		},
+		.la = {
+			.reg = 0x33c,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x13,
+		},
+	}, {
+		.id = 0x1a,
+		.name = "mpe_ipred",
+		.swgroup = TEGRA_SWGROUP_MPE,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 26,
+		},
+		.la = {
+			.reg = 0x328,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x80,
+		},
+	}, {
+		.id = 0x1b,
+		.name = "mpeamemrd",
+		.swgroup = TEGRA_SWGROUP_MPE,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 27,
+		},
+		.la = {
+			.reg = 0x32c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x42,
+		},
+	}, {
+		.id = 0x1c,
+		.name = "mpecsrd",
+		.swgroup = TEGRA_SWGROUP_MPE,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 28,
+		},
+		.la = {
+			.reg = 0x32c,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x1d,
+		.name = "ppcsahbdmar",
+		.swgroup = TEGRA_SWGROUP_PPCS,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 29,
+		},
+		.la = {
+			.reg = 0x344,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x10,
+		},
+	}, {
+		.id = 0x1e,
+		.name = "ppcsahbslvr",
+		.swgroup = TEGRA_SWGROUP_PPCS,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 30,
+		},
+		.la = {
+			.reg = 0x344,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x12,
+		},
+	}, {
+		.id = 0x1f,
+		.name = "satar",
+		.swgroup = TEGRA_SWGROUP_SATA,
+		.smmu = {
+			.reg = 0x228,
+			.bit = 31,
+		},
+		.la = {
+			.reg = 0x350,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x33,
+		},
+	}, {
+		.id = 0x20,
+		.name = "texsrd",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 0,
+		},
+		.la = {
+			.reg = 0x338,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x13,
+		},
+	}, {
+		.id = 0x21,
+		.name = "texsrd2",
+		.swgroup = TEGRA_SWGROUP_NV2,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 1,
+		},
+		.la = {
+			.reg = 0x340,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x13,
+		},
+	}, {
+		.id = 0x22,
+		.name = "vdebsevr",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 2,
+		},
+		.la = {
+			.reg = 0x354,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x23,
+		.name = "vdember",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 3,
+		},
+		.la = {
+			.reg = 0x354,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xd0,
+		},
+	}, {
+		.id = 0x24,
+		.name = "vdemcer",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 4,
+		},
+		.la = {
+			.reg = 0x358,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x2a,
+		},
+	}, {
+		.id = 0x25,
+		.name = "vdetper",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 5,
+		},
+		.la = {
+			.reg = 0x358,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x74,
+		},
+	}, {
+		.id = 0x26,
+		.name = "mpcorelpr",
+		.swgroup = TEGRA_SWGROUP_MPCORELP,
+		.la = {
+			.reg = 0x324,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x04,
+		},
+	}, {
+		.id = 0x27,
+		.name = "mpcorer",
+		.swgroup = TEGRA_SWGROUP_MPCORE,
+		.la = {
+			.reg = 0x320,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x04,
+		},
+	}, {
+		.id = 0x28,
+		.name = "eppu",
+		.swgroup = TEGRA_SWGROUP_EPP,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 8,
+		},
+		.la = {
+			.reg = 0x300,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x6c,
+		},
+	}, {
+		.id = 0x29,
+		.name = "eppv",
+		.swgroup = TEGRA_SWGROUP_EPP,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 9,
+		},
+		.la = {
+			.reg = 0x304,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x6c,
+		},
+	}, {
+		.id = 0x2a,
+		.name = "eppy",
+		.swgroup = TEGRA_SWGROUP_EPP,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 10,
+		},
+		.la = {
+			.reg = 0x304,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x6c,
+		},
+	}, {
+		.id = 0x2b,
+		.name = "mpeunifbw",
+		.swgroup = TEGRA_SWGROUP_MPE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 11,
+		},
+		.la = {
+			.reg = 0x330,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x13,
+		},
+	}, {
+		.id = 0x2c,
+		.name = "viwsb",
+		.swgroup = TEGRA_SWGROUP_VI,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 12,
+		},
+		.la = {
+			.reg = 0x364,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x12,
+		},
+	}, {
+		.id = 0x2d,
+		.name = "viwu",
+		.swgroup = TEGRA_SWGROUP_VI,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 13,
+		},
+		.la = {
+			.reg = 0x368,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xb2,
+		},
+	}, {
+		.id = 0x2e,
+		.name = "viwv",
+		.swgroup = TEGRA_SWGROUP_VI,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 14,
+		},
+		.la = {
+			.reg = 0x368,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xb2,
+		},
+	}, {
+		.id = 0x2f,
+		.name = "viwy",
+		.swgroup = TEGRA_SWGROUP_VI,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 15,
+		},
+		.la = {
+			.reg = 0x36c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x12,
+		},
+	}, {
+		.id = 0x30,
+		.name = "g2dw",
+		.swgroup = TEGRA_SWGROUP_G2,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 16,
+		},
+		.la = {
+			.reg = 0x30c,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x9,
+		},
+	}, {
+		.id = 0x31,
+		.name = "afiw",
+		.swgroup = TEGRA_SWGROUP_AFI,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 17,
+		},
+		.la = {
+			.reg = 0x2e0,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x0c,
+		},
+	}, {
+		.id = 0x32,
+		.name = "avpcarm7w",
+		.swgroup = TEGRA_SWGROUP_AVPC,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 18,
+		},
+		.la = {
+			.reg = 0x2e4,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x0e,
+		},
+	}, {
+		.id = 0x33,
+		.name = "fdcdwr",
+		.swgroup = TEGRA_SWGROUP_NV,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 19,
+		},
+		.la = {
+			.reg = 0x338,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x0a,
+		},
+	}, {
+		.id = 0x34,
+		.name = "fdcwr2",
+		.swgroup = TEGRA_SWGROUP_NV2,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 20,
+		},
+		.la = {
+			.reg = 0x340,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x0a,
+		},
+	}, {
+		.id = 0x35,
+		.name = "hdaw",
+		.swgroup = TEGRA_SWGROUP_HDA,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 21,
+		},
+		.la = {
+			.reg = 0x318,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x36,
+		.name = "host1xw",
+		.swgroup = TEGRA_SWGROUP_HC,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 22,
+		},
+		.la = {
+			.reg = 0x314,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x10,
+		},
+	}, {
+		.id = 0x37,
+		.name = "ispw",
+		.swgroup = TEGRA_SWGROUP_ISP,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 23,
+		},
+		.la = {
+			.reg = 0x31c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x38,
+		.name = "mpcorelpw",
+		.swgroup = TEGRA_SWGROUP_MPCORELP,
+		.la = {
+			.reg = 0x324,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x0e,
+		},
+	}, {
+		.id = 0x39,
+		.name = "mpcorew",
+		.swgroup = TEGRA_SWGROUP_MPCORE,
+		.la = {
+			.reg = 0x320,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x0e,
+		},
+	}, {
+		.id = 0x3a,
+		.name = "mpecswr",
+		.swgroup = TEGRA_SWGROUP_MPE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 26,
+		},
+		.la = {
+			.reg = 0x330,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x3b,
+		.name = "ppcsahbdmaw",
+		.swgroup = TEGRA_SWGROUP_PPCS,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 27,
+		},
+		.la = {
+			.reg = 0x348,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x10,
+		},
+	}, {
+		.id = 0x3c,
+		.name = "ppcsahbslvw",
+		.swgroup = TEGRA_SWGROUP_PPCS,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 28,
+		},
+		.la = {
+			.reg = 0x348,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x06,
+		},
+	}, {
+		.id = 0x3d,
+		.name = "sataw",
+		.swgroup = TEGRA_SWGROUP_SATA,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 29,
+		},
+		.la = {
+			.reg = 0x350,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x33,
+		},
+	}, {
+		.id = 0x3e,
+		.name = "vdebsevw",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 30,
+		},
+		.la = {
+			.reg = 0x35c,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x3f,
+		.name = "vdedbgw",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x22c,
+			.bit = 31,
+		},
+		.la = {
+			.reg = 0x35c,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0xff,
+		},
+	}, {
+		.id = 0x40,
+		.name = "vdembew",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 0,
+		},
+		.la = {
+			.reg = 0x360,
+			.shift = 0,
+			.mask = 0xff,
+			.def = 0x42,
+		},
+	}, {
+		.id = 0x41,
+		.name = "vdetpmw",
+		.swgroup = TEGRA_SWGROUP_VDE,
+		.smmu = {
+			.reg = 0x230,
+			.bit = 1,
+		},
+		.la = {
+			.reg = 0x360,
+			.shift = 16,
+			.mask = 0xff,
+			.def = 0x2a,
+		},
+	},
+};
+
+static const struct tegra_smmu_swgroup tegra30_swgroups[] = {
+	{ .swgroup = TEGRA_SWGROUP_DC,   .reg = 0x240 },
+	{ .swgroup = TEGRA_SWGROUP_DCB,  .reg = 0x244 },
+	{ .swgroup = TEGRA_SWGROUP_EPP,  .reg = 0x248 },
+	{ .swgroup = TEGRA_SWGROUP_G2,   .reg = 0x24c },
+	{ .swgroup = TEGRA_SWGROUP_MPE,  .reg = 0x264 },
+	{ .swgroup = TEGRA_SWGROUP_VI,   .reg = 0x280 },
+	{ .swgroup = TEGRA_SWGROUP_AFI,  .reg = 0x238 },
+	{ .swgroup = TEGRA_SWGROUP_AVPC, .reg = 0x23c },
+	{ .swgroup = TEGRA_SWGROUP_NV,   .reg = 0x268 },
+	{ .swgroup = TEGRA_SWGROUP_NV2,  .reg = 0x26c },
+	{ .swgroup = TEGRA_SWGROUP_HDA,  .reg = 0x254 },
+	{ .swgroup = TEGRA_SWGROUP_HC,   .reg = 0x250 },
+	{ .swgroup = TEGRA_SWGROUP_PPCS, .reg = 0x270 },
+	{ .swgroup = TEGRA_SWGROUP_SATA, .reg = 0x278 },
+	{ .swgroup = TEGRA_SWGROUP_VDE,  .reg = 0x27c },
+	{ .swgroup = TEGRA_SWGROUP_ISP,  .reg = 0x258 },
+};
+
+static void tegra30_flush_dcache(struct page *page, unsigned long offset,
+				 size_t size)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	void *virt = page_address(page) + offset;
+
+	__cpuc_flush_dcache_area(virt, size);
+	outer_flush_range(phys, phys + size);
+}
+
+static const struct tegra_smmu_ops tegra30_smmu_ops = {
+	.flush_dcache = tegra30_flush_dcache,
+};
+
+static const struct tegra_smmu_soc tegra30_smmu_soc = {
+	.clients = tegra30_mc_clients,
+	.num_clients = ARRAY_SIZE(tegra30_mc_clients),
+	.swgroups = tegra30_swgroups,
+	.num_swgroups = ARRAY_SIZE(tegra30_swgroups),
+	.supports_round_robin_arbitration = false,
+	.supports_request_limit = false,
+	.num_asids = 4,
+	.ops = &tegra30_smmu_ops,
+};
+
+const struct tegra_mc_soc tegra30_mc_soc = {
+	.clients = tegra30_mc_clients,
+	.num_clients = ARRAY_SIZE(tegra30_mc_clients),
+	.num_address_bits = 32,
+	.atom_size = 16,
+	.smmu = &tegra30_smmu_soc,
+};
diff --git a/drivers/memory/tegra30-mc.c b/drivers/memory/tegra30-mc.c
deleted file mode 100644
index ef7934535fd..00000000000
--- a/drivers/memory/tegra30-mc.c
+++ /dev/null
@@ -1,378 +0,0 @@
-/*
- * Tegra30 Memory Controller
- *
- * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
- */
-
-#include <linux/err.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/ratelimit.h>
-#include <linux/platform_device.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-
-#define DRV_NAME "tegra30-mc"
-
-#define MC_INTSTATUS			0x0
-#define MC_INTMASK			0x4
-
-#define MC_INT_ERR_SHIFT		6
-#define MC_INT_ERR_MASK			(0x1f << MC_INT_ERR_SHIFT)
-#define MC_INT_DECERR_EMEM		BIT(MC_INT_ERR_SHIFT)
-#define MC_INT_SECURITY_VIOLATION	BIT(MC_INT_ERR_SHIFT + 2)
-#define MC_INT_ARBITRATION_EMEM		BIT(MC_INT_ERR_SHIFT + 3)
-#define MC_INT_INVALID_SMMU_PAGE	BIT(MC_INT_ERR_SHIFT + 4)
-
-#define MC_ERR_STATUS			0x8
-#define MC_ERR_ADR			0xc
-
-#define MC_ERR_TYPE_SHIFT		28
-#define MC_ERR_TYPE_MASK		(7 << MC_ERR_TYPE_SHIFT)
-#define MC_ERR_TYPE_DECERR_EMEM		2
-#define MC_ERR_TYPE_SECURITY_TRUSTZONE	3
-#define MC_ERR_TYPE_SECURITY_CARVEOUT	4
-#define MC_ERR_TYPE_INVALID_SMMU_PAGE	6
-
-#define MC_ERR_INVALID_SMMU_PAGE_SHIFT	25
-#define MC_ERR_INVALID_SMMU_PAGE_MASK	(7 << MC_ERR_INVALID_SMMU_PAGE_SHIFT)
-#define MC_ERR_RW_SHIFT			16
-#define MC_ERR_RW			BIT(MC_ERR_RW_SHIFT)
-#define MC_ERR_SECURITY			BIT(MC_ERR_RW_SHIFT + 1)
-
-#define SECURITY_VIOLATION_TYPE		BIT(30)	/* 0=TRUSTZONE, 1=CARVEOUT */
-
-#define MC_EMEM_ARB_CFG			0x90
-#define MC_EMEM_ARB_OUTSTANDING_REQ	0x94
-#define MC_EMEM_ARB_TIMING_RCD		0x98
-#define MC_EMEM_ARB_TIMING_RP		0x9c
-#define MC_EMEM_ARB_TIMING_RC		0xa0
-#define MC_EMEM_ARB_TIMING_RAS		0xa4
-#define MC_EMEM_ARB_TIMING_FAW		0xa8
-#define MC_EMEM_ARB_TIMING_RRD		0xac
-#define MC_EMEM_ARB_TIMING_RAP2PRE	0xb0
-#define MC_EMEM_ARB_TIMING_WAP2PRE	0xb4
-#define MC_EMEM_ARB_TIMING_R2R		0xb8
-#define MC_EMEM_ARB_TIMING_W2W		0xbc
-#define MC_EMEM_ARB_TIMING_R2W		0xc0
-#define MC_EMEM_ARB_TIMING_W2R		0xc4
-
-#define MC_EMEM_ARB_DA_TURNS		0xd0
-#define MC_EMEM_ARB_DA_COVERS		0xd4
-#define MC_EMEM_ARB_MISC0		0xd8
-#define MC_EMEM_ARB_MISC1		0xdc
-
-#define MC_EMEM_ARB_RING3_THROTTLE	0xe4
-#define MC_EMEM_ARB_OVERRIDE		0xe8
-
-#define MC_TIMING_CONTROL		0xfc
-
-#define MC_CLIENT_ID_MASK		0x7f
-
-#define NUM_MC_REG_BANKS		4
-
-struct tegra30_mc {
-	void __iomem *regs[NUM_MC_REG_BANKS];
-	struct device *dev;
-	u32 ctx[0];
-};
-
-static inline u32 mc_readl(struct tegra30_mc *mc, u32 offs)
-{
-	u32 val = 0;
-
-	if (offs < 0x10)
-		val = readl(mc->regs[0] + offs);
-	else if (offs < 0x1f0)
-		val = readl(mc->regs[1] + offs - 0x3c);
-	else if (offs < 0x228)
-		val = readl(mc->regs[2] + offs - 0x200);
-	else if (offs < 0x400)
-		val = readl(mc->regs[3] + offs - 0x284);
-
-	return val;
-}
-
-static inline void mc_writel(struct tegra30_mc *mc, u32 val, u32 offs)
-{
-	if (offs < 0x10)
-		writel(val, mc->regs[0] + offs);
-	else if (offs < 0x1f0)
-		writel(val, mc->regs[1] + offs - 0x3c);
-	else if (offs < 0x228)
-		writel(val, mc->regs[2] + offs - 0x200);
-	else if (offs < 0x400)
-		writel(val, mc->regs[3] + offs - 0x284);
-}
-
-static const char * const tegra30_mc_client[] = {
-	"csr_ptcr",
-	"cbr_display0a",
-	"cbr_display0ab",
-	"cbr_display0b",
-	"cbr_display0bb",
-	"cbr_display0c",
-	"cbr_display0cb",
-	"cbr_display1b",
-	"cbr_display1bb",
-	"cbr_eppup",
-	"cbr_g2pr",
-	"cbr_g2sr",
-	"cbr_mpeunifbr",
-	"cbr_viruv",
-	"csr_afir",
-	"csr_avpcarm7r",
-	"csr_displayhc",
-	"csr_displayhcb",
-	"csr_fdcdrd",
-	"csr_fdcdrd2",
-	"csr_g2dr",
-	"csr_hdar",
-	"csr_host1xdmar",
-	"csr_host1xr",
-	"csr_idxsrd",
-	"csr_idxsrd2",
-	"csr_mpe_ipred",
-	"csr_mpeamemrd",
-	"csr_mpecsrd",
-	"csr_ppcsahbdmar",
-	"csr_ppcsahbslvr",
-	"csr_satar",
-	"csr_texsrd",
-	"csr_texsrd2",
-	"csr_vdebsevr",
-	"csr_vdember",
-	"csr_vdemcer",
-	"csr_vdetper",
-	"csr_mpcorelpr",
-	"csr_mpcorer",
-	"cbw_eppu",
-	"cbw_eppv",
-	"cbw_eppy",
-	"cbw_mpeunifbw",
-	"cbw_viwsb",
-	"cbw_viwu",
-	"cbw_viwv",
-	"cbw_viwy",
-	"ccw_g2dw",
-	"csw_afiw",
-	"csw_avpcarm7w",
-	"csw_fdcdwr",
-	"csw_fdcdwr2",
-	"csw_hdaw",
-	"csw_host1xw",
-	"csw_ispw",
-	"csw_mpcorelpw",
-	"csw_mpcorew",
-	"csw_mpecswr",
-	"csw_ppcsahbdmaw",
-	"csw_ppcsahbslvw",
-	"csw_sataw",
-	"csw_vdebsevw",
-	"csw_vdedbgw",
-	"csw_vdembew",
-	"csw_vdetpmw",
-};
-
-static void tegra30_mc_decode(struct tegra30_mc *mc, int n)
-{
-	u32 err, addr;
-	const char * const mc_int_err[] = {
-		"MC_DECERR",
-		"Unknown",
-		"MC_SECURITY_ERR",
-		"MC_ARBITRATION_EMEM",
-		"MC_SMMU_ERR",
-	};
-	const char * const err_type[] = {
-		"Unknown",
-		"Unknown",
-		"DECERR_EMEM",
-		"SECURITY_TRUSTZONE",
-		"SECURITY_CARVEOUT",
-		"Unknown",
-		"INVALID_SMMU_PAGE",
-		"Unknown",
-	};
-	char attr[6];
-	int cid, perm, type, idx;
-	const char *client = "Unknown";
-
-	idx = n - MC_INT_ERR_SHIFT;
-	if ((idx < 0) || (idx >= ARRAY_SIZE(mc_int_err)) || (idx == 1)) {
-		dev_err_ratelimited(mc->dev, "Unknown interrupt status %08lx\n",
-				    BIT(n));
-		return;
-	}
-
-	err = mc_readl(mc, MC_ERR_STATUS);
-
-	type = (err & MC_ERR_TYPE_MASK) >> MC_ERR_TYPE_SHIFT;
-	perm = (err & MC_ERR_INVALID_SMMU_PAGE_MASK) >>
-		MC_ERR_INVALID_SMMU_PAGE_SHIFT;
-	if (type == MC_ERR_TYPE_INVALID_SMMU_PAGE)
-		sprintf(attr, "%c-%c-%c",
-			(perm & BIT(2)) ? 'R' : '-',
-			(perm & BIT(1)) ? 'W' : '-',
-			(perm & BIT(0)) ? 'S' : '-');
-	else
-		attr[0] = '\0';
-
-	cid = err & MC_CLIENT_ID_MASK;
-	if (cid < ARRAY_SIZE(tegra30_mc_client))
-		client = tegra30_mc_client[cid];
-
-	addr = mc_readl(mc, MC_ERR_ADR);
-
-	dev_err_ratelimited(mc->dev, "%s (0x%08x): 0x%08x %s (%s %s %s %s)\n",
-			   mc_int_err[idx], err, addr, client,
-			   (err & MC_ERR_SECURITY) ? "secure" : "non-secure",
-			   (err & MC_ERR_RW) ? "write" : "read",
-			   err_type[type], attr);
-}
-
-static const u32 tegra30_mc_ctx[] = {
-	MC_EMEM_ARB_CFG,
-	MC_EMEM_ARB_OUTSTANDING_REQ,
-	MC_EMEM_ARB_TIMING_RCD,
-	MC_EMEM_ARB_TIMING_RP,
-	MC_EMEM_ARB_TIMING_RC,
-	MC_EMEM_ARB_TIMING_RAS,
-	MC_EMEM_ARB_TIMING_FAW,
-	MC_EMEM_ARB_TIMING_RRD,
-	MC_EMEM_ARB_TIMING_RAP2PRE,
-	MC_EMEM_ARB_TIMING_WAP2PRE,
-	MC_EMEM_ARB_TIMING_R2R,
-	MC_EMEM_ARB_TIMING_W2W,
-	MC_EMEM_ARB_TIMING_R2W,
-	MC_EMEM_ARB_TIMING_W2R,
-	MC_EMEM_ARB_DA_TURNS,
-	MC_EMEM_ARB_DA_COVERS,
-	MC_EMEM_ARB_MISC0,
-	MC_EMEM_ARB_MISC1,
-	MC_EMEM_ARB_RING3_THROTTLE,
-	MC_EMEM_ARB_OVERRIDE,
-	MC_INTMASK,
-};
-
-#ifdef CONFIG_PM
-static int tegra30_mc_suspend(struct device *dev)
-{
-	int i;
-	struct tegra30_mc *mc = dev_get_drvdata(dev);
-
-	for (i = 0; i < ARRAY_SIZE(tegra30_mc_ctx); i++)
-		mc->ctx[i] = mc_readl(mc, tegra30_mc_ctx[i]);
-	return 0;
-}
-
-static int tegra30_mc_resume(struct device *dev)
-{
-	int i;
-	struct tegra30_mc *mc = dev_get_drvdata(dev);
-
-	for (i = 0; i < ARRAY_SIZE(tegra30_mc_ctx); i++)
-		mc_writel(mc, mc->ctx[i], tegra30_mc_ctx[i]);
-
-	mc_writel(mc, 1, MC_TIMING_CONTROL);
-	/* Read-back to ensure that write reached */
-	mc_readl(mc, MC_TIMING_CONTROL);
-	return 0;
-}
-#endif
-
-static UNIVERSAL_DEV_PM_OPS(tegra30_mc_pm,
-			    tegra30_mc_suspend,
-			    tegra30_mc_resume, NULL);
-
-static const struct of_device_id tegra30_mc_of_match[] = {
-	{ .compatible = "nvidia,tegra30-mc", },
-	{},
-};
-
-static irqreturn_t tegra30_mc_isr(int irq, void *data)
-{
-	u32 stat, mask, bit;
-	struct tegra30_mc *mc = data;
-
-	stat = mc_readl(mc, MC_INTSTATUS);
-	mask = mc_readl(mc, MC_INTMASK);
-	mask &= stat;
-	if (!mask)
-		return IRQ_NONE;
-	while ((bit = ffs(mask)) != 0) {
-		tegra30_mc_decode(mc, bit - 1);
-		mask &= ~BIT(bit - 1);
-	}
-
-	mc_writel(mc, stat, MC_INTSTATUS);
-	return IRQ_HANDLED;
-}
-
-static int tegra30_mc_probe(struct platform_device *pdev)
-{
-	struct resource *irq;
-	struct tegra30_mc *mc;
-	size_t bytes;
-	int err, i;
-	u32 intmask;
-
-	bytes = sizeof(*mc) + sizeof(u32) * ARRAY_SIZE(tegra30_mc_ctx);
-	mc = devm_kzalloc(&pdev->dev, bytes, GFP_KERNEL);
-	if (!mc)
-		return -ENOMEM;
-	mc->dev = &pdev->dev;
-
-	for (i = 0; i < ARRAY_SIZE(mc->regs); i++) {
-		struct resource *res;
-
-		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
-		mc->regs[i] = devm_ioremap_resource(&pdev->dev, res);
-		if (IS_ERR(mc->regs[i]))
-			return PTR_ERR(mc->regs[i]);
-	}
-
-	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!irq)
-		return -ENODEV;
-	err = devm_request_irq(&pdev->dev, irq->start, tegra30_mc_isr,
-			       IRQF_SHARED, dev_name(&pdev->dev), mc);
-	if (err)
-		return -ENODEV;
-
-	platform_set_drvdata(pdev, mc);
-
-	intmask = MC_INT_INVALID_SMMU_PAGE |
-		MC_INT_DECERR_EMEM | MC_INT_SECURITY_VIOLATION;
-	mc_writel(mc, intmask, MC_INTMASK);
-	return 0;
-}
-
-static struct platform_driver tegra30_mc_driver = {
-	.probe = tegra30_mc_probe,
-	.driver = {
-		.name = DRV_NAME,
-		.owner = THIS_MODULE,
-		.of_match_table = tegra30_mc_of_match,
-		.pm = &tegra30_mc_pm,
-	},
-};
-module_platform_driver(tegra30_mc_driver);
-
-MODULE_AUTHOR("Hiroshi DOYU <hdoyu@nvidia.com>");
-MODULE_DESCRIPTION("Tegra30 MC driver");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/include/dt-bindings/memory/tegra114-mc.h b/include/dt-bindings/memory/tegra114-mc.h
new file mode 100644
index 00000000000..8f48985a313
--- /dev/null
+++ b/include/dt-bindings/memory/tegra114-mc.h
@@ -0,0 +1,25 @@
+#ifndef DT_BINDINGS_MEMORY_TEGRA114_MC_H
+#define DT_BINDINGS_MEMORY_TEGRA114_MC_H
+
+#define TEGRA_SWGROUP_PTC	0
+#define TEGRA_SWGROUP_DC	1
+#define TEGRA_SWGROUP_DCB	2
+#define TEGRA_SWGROUP_EPP	3
+#define TEGRA_SWGROUP_G2	4
+#define TEGRA_SWGROUP_AVPC	5
+#define TEGRA_SWGROUP_NV	6
+#define TEGRA_SWGROUP_HDA	7
+#define TEGRA_SWGROUP_HC	8
+#define TEGRA_SWGROUP_MSENC	9
+#define TEGRA_SWGROUP_PPCS	10
+#define TEGRA_SWGROUP_VDE	11
+#define TEGRA_SWGROUP_MPCORELP	12
+#define TEGRA_SWGROUP_MPCORE	13
+#define TEGRA_SWGROUP_VI	14
+#define TEGRA_SWGROUP_ISP	15
+#define TEGRA_SWGROUP_XUSB_HOST	16
+#define TEGRA_SWGROUP_XUSB_DEV	17
+#define TEGRA_SWGROUP_EMUCIF	18
+#define TEGRA_SWGROUP_TSEC	19
+
+#endif
diff --git a/include/dt-bindings/memory/tegra124-mc.h b/include/dt-bindings/memory/tegra124-mc.h
new file mode 100644
index 00000000000..7d8ee798f34
--- /dev/null
+++ b/include/dt-bindings/memory/tegra124-mc.h
@@ -0,0 +1,31 @@
+#ifndef DT_BINDINGS_MEMORY_TEGRA124_MC_H
+#define DT_BINDINGS_MEMORY_TEGRA124_MC_H
+
+#define TEGRA_SWGROUP_PTC	0
+#define TEGRA_SWGROUP_DC	1
+#define TEGRA_SWGROUP_DCB	2
+#define TEGRA_SWGROUP_AFI	3
+#define TEGRA_SWGROUP_AVPC	4
+#define TEGRA_SWGROUP_HDA	5
+#define TEGRA_SWGROUP_HC	6
+#define TEGRA_SWGROUP_MSENC	7
+#define TEGRA_SWGROUP_PPCS	8
+#define TEGRA_SWGROUP_SATA	9
+#define TEGRA_SWGROUP_VDE	10
+#define TEGRA_SWGROUP_MPCORELP	11
+#define TEGRA_SWGROUP_MPCORE	12
+#define TEGRA_SWGROUP_ISP2	13
+#define TEGRA_SWGROUP_XUSB_HOST	14
+#define TEGRA_SWGROUP_XUSB_DEV	15
+#define TEGRA_SWGROUP_ISP2B	16
+#define TEGRA_SWGROUP_TSEC	17
+#define TEGRA_SWGROUP_A9AVP	18
+#define TEGRA_SWGROUP_GPU	19
+#define TEGRA_SWGROUP_SDMMC1A	20
+#define TEGRA_SWGROUP_SDMMC2A	21
+#define TEGRA_SWGROUP_SDMMC3A	22
+#define TEGRA_SWGROUP_SDMMC4A	23
+#define TEGRA_SWGROUP_VIC	24
+#define TEGRA_SWGROUP_VI	25
+
+#endif
diff --git a/include/dt-bindings/memory/tegra30-mc.h b/include/dt-bindings/memory/tegra30-mc.h
new file mode 100644
index 00000000000..502beb03d77
--- /dev/null
+++ b/include/dt-bindings/memory/tegra30-mc.h
@@ -0,0 +1,24 @@
+#ifndef DT_BINDINGS_MEMORY_TEGRA30_MC_H
+#define DT_BINDINGS_MEMORY_TEGRA30_MC_H
+
+#define TEGRA_SWGROUP_PTC	0
+#define TEGRA_SWGROUP_DC	1
+#define TEGRA_SWGROUP_DCB	2
+#define TEGRA_SWGROUP_EPP	3
+#define TEGRA_SWGROUP_G2	4
+#define TEGRA_SWGROUP_MPE	5
+#define TEGRA_SWGROUP_VI	6
+#define TEGRA_SWGROUP_AFI	7
+#define TEGRA_SWGROUP_AVPC	8
+#define TEGRA_SWGROUP_NV	9
+#define TEGRA_SWGROUP_NV2	10
+#define TEGRA_SWGROUP_HDA	11
+#define TEGRA_SWGROUP_HC	12
+#define TEGRA_SWGROUP_PPCS	13
+#define TEGRA_SWGROUP_SATA	14
+#define TEGRA_SWGROUP_VDE	15
+#define TEGRA_SWGROUP_MPCORELP	16
+#define TEGRA_SWGROUP_MPCORE	17
+#define TEGRA_SWGROUP_ISP	18
+
+#endif
diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h
new file mode 100644
index 00000000000..63deb8d9f82
--- /dev/null
+++ b/include/soc/tegra/mc.h
@@ -0,0 +1,107 @@
+/*
+ * Copyright (C) 2014 NVIDIA Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __SOC_TEGRA_MC_H__
+#define __SOC_TEGRA_MC_H__
+
+#include <linux/types.h>
+
+struct clk;
+struct device;
+struct page;
+
+struct tegra_smmu_enable {
+	unsigned int reg;
+	unsigned int bit;
+};
+
+/* latency allowance */
+struct tegra_mc_la {
+	unsigned int reg;
+	unsigned int shift;
+	unsigned int mask;
+	unsigned int def;
+};
+
+struct tegra_mc_client {
+	unsigned int id;
+	const char *name;
+	unsigned int swgroup;
+
+	unsigned int fifo_size;
+
+	struct tegra_smmu_enable smmu;
+	struct tegra_mc_la la;
+};
+
+struct tegra_smmu_swgroup {
+	unsigned int swgroup;
+	unsigned int reg;
+};
+
+struct tegra_smmu_ops {
+	void (*flush_dcache)(struct page *page, unsigned long offset,
+			     size_t size);
+};
+
+struct tegra_smmu_soc {
+	const struct tegra_mc_client *clients;
+	unsigned int num_clients;
+
+	const struct tegra_smmu_swgroup *swgroups;
+	unsigned int num_swgroups;
+
+	bool supports_round_robin_arbitration;
+	bool supports_request_limit;
+
+	unsigned int num_asids;
+
+	const struct tegra_smmu_ops *ops;
+};
+
+struct tegra_mc;
+struct tegra_smmu;
+
+#ifdef CONFIG_TEGRA_IOMMU_SMMU
+struct tegra_smmu *tegra_smmu_probe(struct device *dev,
+				    const struct tegra_smmu_soc *soc,
+				    struct tegra_mc *mc);
+#else
+static inline struct tegra_smmu *
+tegra_smmu_probe(struct device *dev, const struct tegra_smmu_soc *soc,
+		 struct tegra_mc *mc)
+{
+	return NULL;
+}
+#endif
+
+struct tegra_mc_soc {
+	const struct tegra_mc_client *clients;
+	unsigned int num_clients;
+
+	const unsigned int *emem_regs;
+	unsigned int num_emem_regs;
+
+	unsigned int num_address_bits;
+	unsigned int atom_size;
+
+	const struct tegra_smmu_soc *smmu;
+};
+
+struct tegra_mc {
+	struct device *dev;
+	struct tegra_smmu *smmu;
+	void __iomem *regs;
+	struct clk *clk;
+	int irq;
+
+	const struct tegra_mc_soc *soc;
+	unsigned long tick;
+};
+
+#endif /* __SOC_TEGRA_MC_H__ */
-- 
cgit v1.2.3-70-g09d2


From 91d63156c9e6b4aa83297b19289e366e1fdcfad4 Mon Sep 17 00:00:00 2001
From: Josh Wu <josh.wu@atmel.com>
Date: Thu, 27 Nov 2014 00:15:01 -0300
Subject: [media] media: v4l2-image-sizes.h: correct the SVGA height definition

SVGA height should be 600 not 680.

Reported-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Josh Wu <josh.wu@atmel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/v4l2-image-sizes.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/media/v4l2-image-sizes.h b/include/media/v4l2-image-sizes.h
index c70c917b97a..a07d7a683bd 100644
--- a/include/media/v4l2-image-sizes.h
+++ b/include/media/v4l2-image-sizes.h
@@ -26,7 +26,7 @@
 #define QVGA_HEIGHT	240
 
 #define SVGA_WIDTH	800
-#define SVGA_HEIGHT	680
+#define SVGA_HEIGHT	600
 
 #define SXGA_WIDTH	1280
 #define SXGA_HEIGHT	1024
-- 
cgit v1.2.3-70-g09d2


From 435d5f4bb2ccba3b791d9ef61d2590e30b8e806e Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 31 Oct 2014 22:56:04 -0400
Subject: common object embedded into various struct ....ns

for now - just move corresponding ->proc_inum instances over there

Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/mount.h                     | 3 ++-
 fs/namespace.c                 | 6 +++---
 include/linux/ipc_namespace.h  | 3 ++-
 include/linux/ns_common.h      | 8 ++++++++
 include/linux/pid_namespace.h  | 3 ++-
 include/linux/user_namespace.h | 3 ++-
 include/linux/utsname.h        | 3 ++-
 include/net/net_namespace.h    | 3 ++-
 init/version.c                 | 2 +-
 ipc/msgutil.c                  | 2 +-
 ipc/namespace.c                | 8 ++++----
 kernel/pid.c                   | 2 +-
 kernel/pid_namespace.c         | 6 +++---
 kernel/user.c                  | 2 +-
 kernel/user_namespace.c        | 6 +++---
 kernel/utsname.c               | 6 +++---
 net/core/net_namespace.c       | 6 +++---
 17 files changed, 43 insertions(+), 29 deletions(-)
 create mode 100644 include/linux/ns_common.h

(limited to 'include')

diff --git a/fs/mount.h b/fs/mount.h
index f82c6284090..0ad6f760ce5 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -1,10 +1,11 @@
 #include <linux/mount.h>
 #include <linux/seq_file.h>
 #include <linux/poll.h>
+#include <linux/ns_common.h>
 
 struct mnt_namespace {
 	atomic_t		count;
-	unsigned int		proc_inum;
+	struct ns_common	ns;
 	struct mount *	root;
 	struct list_head	list;
 	struct user_namespace	*user_ns;
diff --git a/fs/namespace.c b/fs/namespace.c
index 5b66b2b3624..adc2ea2532a 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2640,7 +2640,7 @@ dput_out:
 
 static void free_mnt_ns(struct mnt_namespace *ns)
 {
-	proc_free_inum(ns->proc_inum);
+	proc_free_inum(ns->ns.inum);
 	put_user_ns(ns->user_ns);
 	kfree(ns);
 }
@@ -2662,7 +2662,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
 	new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
 	if (!new_ns)
 		return ERR_PTR(-ENOMEM);
-	ret = proc_alloc_inum(&new_ns->proc_inum);
+	ret = proc_alloc_inum(&new_ns->ns.inum);
 	if (ret) {
 		kfree(new_ns);
 		return ERR_PTR(ret);
@@ -3201,7 +3201,7 @@ static int mntns_install(struct nsproxy *nsproxy, void *ns)
 static unsigned int mntns_inum(void *ns)
 {
 	struct mnt_namespace *mnt_ns = ns;
-	return mnt_ns->proc_inum;
+	return mnt_ns->ns.inum;
 }
 
 const struct proc_ns_operations mntns_operations = {
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index 35e7eca4e33..52a64012815 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -6,6 +6,7 @@
 #include <linux/rwsem.h>
 #include <linux/notifier.h>
 #include <linux/nsproxy.h>
+#include <linux/ns_common.h>
 
 /*
  * ipc namespace events
@@ -68,7 +69,7 @@ struct ipc_namespace {
 	/* user_ns which owns the ipc ns */
 	struct user_namespace *user_ns;
 
-	unsigned int	proc_inum;
+	struct ns_common ns;
 };
 
 extern struct ipc_namespace init_ipc_ns;
diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
new file mode 100644
index 00000000000..e7db1cd5404
--- /dev/null
+++ b/include/linux/ns_common.h
@@ -0,0 +1,8 @@
+#ifndef _LINUX_NS_COMMON_H
+#define _LINUX_NS_COMMON_H
+
+struct ns_common {
+	unsigned int inum;
+};
+
+#endif
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 1997ffc295a..b9cf6c51b18 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -8,6 +8,7 @@
 #include <linux/threads.h>
 #include <linux/nsproxy.h>
 #include <linux/kref.h>
+#include <linux/ns_common.h>
 
 struct pidmap {
        atomic_t nr_free;
@@ -43,7 +44,7 @@ struct pid_namespace {
 	kgid_t pid_gid;
 	int hide_pid;
 	int reboot;	/* group exit code if this pidns was rebooted */
-	unsigned int proc_inum;
+	struct ns_common ns;
 };
 
 extern struct pid_namespace init_pid_ns;
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index e95372654f0..4cf06c140e2 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -3,6 +3,7 @@
 
 #include <linux/kref.h>
 #include <linux/nsproxy.h>
+#include <linux/ns_common.h>
 #include <linux/sched.h>
 #include <linux/err.h>
 
@@ -26,7 +27,7 @@ struct user_namespace {
 	int			level;
 	kuid_t			owner;
 	kgid_t			group;
-	unsigned int		proc_inum;
+	struct ns_common	ns;
 
 	/* Register of per-UID persistent keyrings for this namespace */
 #ifdef CONFIG_PERSISTENT_KEYRINGS
diff --git a/include/linux/utsname.h b/include/linux/utsname.h
index 239e27733d6..5093f58ae19 100644
--- a/include/linux/utsname.h
+++ b/include/linux/utsname.h
@@ -5,6 +5,7 @@
 #include <linux/sched.h>
 #include <linux/kref.h>
 #include <linux/nsproxy.h>
+#include <linux/ns_common.h>
 #include <linux/err.h>
 #include <uapi/linux/utsname.h>
 
@@ -23,7 +24,7 @@ struct uts_namespace {
 	struct kref kref;
 	struct new_utsname name;
 	struct user_namespace *user_ns;
-	unsigned int proc_inum;
+	struct ns_common ns;
 };
 extern struct uts_namespace init_uts_ns;
 
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index e0d64667a4b..2e8756b8c77 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -26,6 +26,7 @@
 #endif
 #include <net/netns/nftables.h>
 #include <net/netns/xfrm.h>
+#include <linux/ns_common.h>
 
 struct user_namespace;
 struct proc_dir_entry;
@@ -60,7 +61,7 @@ struct net {
 
 	struct user_namespace   *user_ns;	/* Owning user namespace */
 
-	unsigned int		proc_inum;
+	struct ns_common	ns;
 
 	struct proc_dir_entry 	*proc_net;
 	struct proc_dir_entry 	*proc_net_stat;
diff --git a/init/version.c b/init/version.c
index 1a4718e500f..e23dbdabb26 100644
--- a/init/version.c
+++ b/init/version.c
@@ -35,7 +35,7 @@ struct uts_namespace init_uts_ns = {
 		.domainname	= UTS_DOMAINNAME,
 	},
 	.user_ns = &init_user_ns,
-	.proc_inum = PROC_UTS_INIT_INO,
+	.ns.inum = PROC_UTS_INIT_INO,
 };
 EXPORT_SYMBOL_GPL(init_uts_ns);
 
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index 7e7095974d5..5930471a290 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -31,7 +31,7 @@ DEFINE_SPINLOCK(mq_lock);
 struct ipc_namespace init_ipc_ns = {
 	.count		= ATOMIC_INIT(1),
 	.user_ns = &init_user_ns,
-	.proc_inum = PROC_IPC_INIT_INO,
+	.ns.inum = PROC_IPC_INIT_INO,
 };
 
 atomic_t nr_ipc_ns = ATOMIC_INIT(1);
diff --git a/ipc/namespace.c b/ipc/namespace.c
index b54468e48e3..177fa9db391 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -26,7 +26,7 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 	if (ns == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	err = proc_alloc_inum(&ns->proc_inum);
+	err = proc_alloc_inum(&ns->ns.inum);
 	if (err) {
 		kfree(ns);
 		return ERR_PTR(err);
@@ -35,7 +35,7 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 	atomic_set(&ns->count, 1);
 	err = mq_init_ns(ns);
 	if (err) {
-		proc_free_inum(ns->proc_inum);
+		proc_free_inum(ns->ns.inum);
 		kfree(ns);
 		return ERR_PTR(err);
 	}
@@ -119,7 +119,7 @@ static void free_ipc_ns(struct ipc_namespace *ns)
 	 */
 	ipcns_notify(IPCNS_REMOVED);
 	put_user_ns(ns->user_ns);
-	proc_free_inum(ns->proc_inum);
+	proc_free_inum(ns->ns.inum);
 	kfree(ns);
 }
 
@@ -186,7 +186,7 @@ static unsigned int ipcns_inum(void *vp)
 {
 	struct ipc_namespace *ns = vp;
 
-	return ns->proc_inum;
+	return ns->ns.inum;
 }
 
 const struct proc_ns_operations ipcns_operations = {
diff --git a/kernel/pid.c b/kernel/pid.c
index 9b9a2669814..3650698cf1d 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -79,7 +79,7 @@ struct pid_namespace init_pid_ns = {
 	.level = 0,
 	.child_reaper = &init_task,
 	.user_ns = &init_user_ns,
-	.proc_inum = PROC_PID_INIT_INO,
+	.ns.inum = PROC_PID_INIT_INO,
 };
 EXPORT_SYMBOL_GPL(init_pid_ns);
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index db95d8eb761..99e27e5bf90 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -105,7 +105,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 	if (ns->pid_cachep == NULL)
 		goto out_free_map;
 
-	err = proc_alloc_inum(&ns->proc_inum);
+	err = proc_alloc_inum(&ns->ns.inum);
 	if (err)
 		goto out_free_map;
 
@@ -142,7 +142,7 @@ static void destroy_pid_namespace(struct pid_namespace *ns)
 {
 	int i;
 
-	proc_free_inum(ns->proc_inum);
+	proc_free_inum(ns->ns.inum);
 	for (i = 0; i < PIDMAP_ENTRIES; i++)
 		kfree(ns->pidmap[i].page);
 	put_user_ns(ns->user_ns);
@@ -365,7 +365,7 @@ static int pidns_install(struct nsproxy *nsproxy, void *ns)
 static unsigned int pidns_inum(void *ns)
 {
 	struct pid_namespace *pid_ns = ns;
-	return pid_ns->proc_inum;
+	return pid_ns->ns.inum;
 }
 
 const struct proc_ns_operations pidns_operations = {
diff --git a/kernel/user.c b/kernel/user.c
index 4efa39350e4..a7ca84bad8e 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -50,7 +50,7 @@ struct user_namespace init_user_ns = {
 	.count = ATOMIC_INIT(3),
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
-	.proc_inum = PROC_USER_INIT_INO,
+	.ns.inum = PROC_USER_INIT_INO,
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 	.persistent_keyring_register_sem =
 	__RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index aa312b0dc3e..fde58408267 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -86,7 +86,7 @@ int create_user_ns(struct cred *new)
 	if (!ns)
 		return -ENOMEM;
 
-	ret = proc_alloc_inum(&ns->proc_inum);
+	ret = proc_alloc_inum(&ns->ns.inum);
 	if (ret) {
 		kmem_cache_free(user_ns_cachep, ns);
 		return ret;
@@ -136,7 +136,7 @@ void free_user_ns(struct user_namespace *ns)
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 		key_put(ns->persistent_keyring_register);
 #endif
-		proc_free_inum(ns->proc_inum);
+		proc_free_inum(ns->ns.inum);
 		kmem_cache_free(user_ns_cachep, ns);
 		ns = parent;
 	} while (atomic_dec_and_test(&parent->count));
@@ -891,7 +891,7 @@ static int userns_install(struct nsproxy *nsproxy, void *ns)
 static unsigned int userns_inum(void *ns)
 {
 	struct user_namespace *user_ns = ns;
-	return user_ns->proc_inum;
+	return user_ns->ns.inum;
 }
 
 const struct proc_ns_operations userns_operations = {
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 883aaaa7de8..b1cd00b828f 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -42,7 +42,7 @@ static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns,
 	if (!ns)
 		return ERR_PTR(-ENOMEM);
 
-	err = proc_alloc_inum(&ns->proc_inum);
+	err = proc_alloc_inum(&ns->ns.inum);
 	if (err) {
 		kfree(ns);
 		return ERR_PTR(err);
@@ -84,7 +84,7 @@ void free_uts_ns(struct kref *kref)
 
 	ns = container_of(kref, struct uts_namespace, kref);
 	put_user_ns(ns->user_ns);
-	proc_free_inum(ns->proc_inum);
+	proc_free_inum(ns->ns.inum);
 	kfree(ns);
 }
 
@@ -127,7 +127,7 @@ static unsigned int utsns_inum(void *vp)
 {
 	struct uts_namespace *ns = vp;
 
-	return ns->proc_inum;
+	return ns->ns.inum;
 }
 
 const struct proc_ns_operations utsns_operations = {
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 7f155175bba..f2f756ce99d 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -386,12 +386,12 @@ EXPORT_SYMBOL_GPL(get_net_ns_by_pid);
 
 static __net_init int net_ns_net_init(struct net *net)
 {
-	return proc_alloc_inum(&net->proc_inum);
+	return proc_alloc_inum(&net->ns.inum);
 }
 
 static __net_exit void net_ns_net_exit(struct net *net)
 {
-	proc_free_inum(net->proc_inum);
+	proc_free_inum(net->ns.inum);
 }
 
 static struct pernet_operations __net_initdata net_ns_ops = {
@@ -664,7 +664,7 @@ static int netns_install(struct nsproxy *nsproxy, void *ns)
 static unsigned int netns_inum(void *ns)
 {
 	struct net *net = ns;
-	return net->proc_inum;
+	return net->ns.inum;
 }
 
 const struct proc_ns_operations netns_operations = {
-- 
cgit v1.2.3-70-g09d2


From 64964528b24ea390824f0e5ce9d34b8d39b28cde Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 1 Nov 2014 00:37:32 -0400
Subject: make proc_ns_operations work with struct ns_common * instead of void
 *

We can do that now.  And kill ->inum(), while we are at it - all instances
are identical.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namespace.c           | 13 +++----------
 fs/proc/inode.c          |  2 +-
 fs/proc/namespaces.c     |  8 ++++----
 include/linux/proc_ns.h  | 10 +++++-----
 ipc/namespace.c          | 12 +++---------
 kernel/pid_namespace.c   | 12 +++---------
 kernel/user_namespace.c  | 12 +++---------
 kernel/utsname.c         | 12 +++---------
 net/core/net_namespace.c | 12 +++---------
 9 files changed, 28 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index 5c21fdadabe..b9c16c3f63f 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3149,7 +3149,7 @@ found:
 	return visible;
 }
 
-static void *mntns_get(struct task_struct *task)
+static struct ns_common *mntns_get(struct task_struct *task)
 {
 	struct ns_common *ns = NULL;
 	struct nsproxy *nsproxy;
@@ -3165,12 +3165,12 @@ static void *mntns_get(struct task_struct *task)
 	return ns;
 }
 
-static void mntns_put(void *ns)
+static void mntns_put(struct ns_common *ns)
 {
 	put_mnt_ns(to_mnt_ns(ns));
 }
 
-static int mntns_install(struct nsproxy *nsproxy, void *ns)
+static int mntns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 {
 	struct fs_struct *fs = current->fs;
 	struct mnt_namespace *mnt_ns = to_mnt_ns(ns);
@@ -3203,17 +3203,10 @@ static int mntns_install(struct nsproxy *nsproxy, void *ns)
 	return 0;
 }
 
-static unsigned int mntns_inum(void *ns)
-{
-	struct ns_common *p = ns;
-	return p->inum;
-}
-
 const struct proc_ns_operations mntns_operations = {
 	.name		= "mnt",
 	.type		= CLONE_NEWNS,
 	.get		= mntns_get,
 	.put		= mntns_put,
 	.install	= mntns_install,
-	.inum		= mntns_inum,
 };
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 333080d7a67..43b703c6cd3 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -33,7 +33,7 @@ static void proc_evict_inode(struct inode *inode)
 	struct proc_dir_entry *de;
 	struct ctl_table_header *head;
 	const struct proc_ns_operations *ns_ops;
-	void *ns;
+	struct ns_common *ns;
 
 	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 89026095f2b..995e8e98237 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -64,7 +64,7 @@ static struct dentry *proc_ns_get_dentry(struct super_block *sb,
 	struct inode *inode;
 	struct proc_inode *ei;
 	struct qstr qname = { .name = "", };
-	void *ns;
+	struct ns_common *ns;
 
 	ns = ns_ops->get(task);
 	if (!ns)
@@ -76,7 +76,7 @@ static struct dentry *proc_ns_get_dentry(struct super_block *sb,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	inode = iget_locked(sb, ns_ops->inum(ns));
+	inode = iget_locked(sb, ns->inum);
 	if (!inode) {
 		dput(dentry);
 		ns_ops->put(ns);
@@ -144,7 +144,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
 	struct proc_inode *ei = PROC_I(inode);
 	const struct proc_ns_operations *ns_ops = ei->ns.ns_ops;
 	struct task_struct *task;
-	void *ns;
+	struct ns_common *ns;
 	char name[50];
 	int res = -EACCES;
 
@@ -160,7 +160,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
 	if (!ns)
 		goto out_put_task;
 
-	snprintf(name, sizeof(name), "%s:[%u]", ns_ops->name, ns_ops->inum(ns));
+	snprintf(name, sizeof(name), "%s:[%u]", ns_ops->name, ns->inum);
 	res = readlink_copy(buffer, buflen, name);
 	ns_ops->put(ns);
 out_put_task:
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 34a1e105bef..f284959391f 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -6,18 +6,18 @@
 
 struct pid_namespace;
 struct nsproxy;
+struct ns_common;
 
 struct proc_ns_operations {
 	const char *name;
 	int type;
-	void *(*get)(struct task_struct *task);
-	void (*put)(void *ns);
-	int (*install)(struct nsproxy *nsproxy, void *ns);
-	unsigned int (*inum)(void *ns);
+	struct ns_common *(*get)(struct task_struct *task);
+	void (*put)(struct ns_common *ns);
+	int (*install)(struct nsproxy *nsproxy, struct ns_common *ns);
 };
 
 struct proc_ns {
-	void *ns;
+	struct ns_common *ns;
 	const struct proc_ns_operations *ns_ops;
 };
 
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 3c1e8d3bd7d..531029a67fe 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -154,7 +154,7 @@ static inline struct ipc_namespace *to_ipc_ns(struct ns_common *ns)
 	return container_of(ns, struct ipc_namespace, ns);
 }
 
-static void *ipcns_get(struct task_struct *task)
+static struct ns_common *ipcns_get(struct task_struct *task)
 {
 	struct ipc_namespace *ns = NULL;
 	struct nsproxy *nsproxy;
@@ -168,12 +168,12 @@ static void *ipcns_get(struct task_struct *task)
 	return ns ? &ns->ns : NULL;
 }
 
-static void ipcns_put(void *ns)
+static void ipcns_put(struct ns_common *ns)
 {
 	return put_ipc_ns(to_ipc_ns(ns));
 }
 
-static int ipcns_install(struct nsproxy *nsproxy, void *new)
+static int ipcns_install(struct nsproxy *nsproxy, struct ns_common *new)
 {
 	struct ipc_namespace *ns = to_ipc_ns(new);
 	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
@@ -187,16 +187,10 @@ static int ipcns_install(struct nsproxy *nsproxy, void *new)
 	return 0;
 }
 
-static unsigned int ipcns_inum(void *vp)
-{
-	return ((struct ns_common *)vp)->inum;
-}
-
 const struct proc_ns_operations ipcns_operations = {
 	.name		= "ipc",
 	.type		= CLONE_NEWIPC,
 	.get		= ipcns_get,
 	.put		= ipcns_put,
 	.install	= ipcns_install,
-	.inum		= ipcns_inum,
 };
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index dd961ad86fb..79aabce49a8 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -318,7 +318,7 @@ static inline struct pid_namespace *to_pid_ns(struct ns_common *ns)
 	return container_of(ns, struct pid_namespace, ns);
 }
 
-static void *pidns_get(struct task_struct *task)
+static struct ns_common *pidns_get(struct task_struct *task)
 {
 	struct pid_namespace *ns;
 
@@ -331,12 +331,12 @@ static void *pidns_get(struct task_struct *task)
 	return ns ? &ns->ns : NULL;
 }
 
-static void pidns_put(void *ns)
+static void pidns_put(struct ns_common *ns)
 {
 	put_pid_ns(to_pid_ns(ns));
 }
 
-static int pidns_install(struct nsproxy *nsproxy, void *ns)
+static int pidns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 {
 	struct pid_namespace *active = task_active_pid_ns(current);
 	struct pid_namespace *ancestor, *new = to_pid_ns(ns);
@@ -367,18 +367,12 @@ static int pidns_install(struct nsproxy *nsproxy, void *ns)
 	return 0;
 }
 
-static unsigned int pidns_inum(void *ns)
-{
-	return ((struct ns_common *)ns)->inum;
-}
-
 const struct proc_ns_operations pidns_operations = {
 	.name		= "pid",
 	.type		= CLONE_NEWPID,
 	.get		= pidns_get,
 	.put		= pidns_put,
 	.install	= pidns_install,
-	.inum		= pidns_inum,
 };
 
 static __init int pid_namespaces_init(void)
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 1ab2209228f..29cd5ccfc37 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -846,7 +846,7 @@ static inline struct user_namespace *to_user_ns(struct ns_common *ns)
 	return container_of(ns, struct user_namespace, ns);
 }
 
-static void *userns_get(struct task_struct *task)
+static struct ns_common *userns_get(struct task_struct *task)
 {
 	struct user_namespace *user_ns;
 
@@ -857,12 +857,12 @@ static void *userns_get(struct task_struct *task)
 	return user_ns ? &user_ns->ns : NULL;
 }
 
-static void userns_put(void *ns)
+static void userns_put(struct ns_common *ns)
 {
 	put_user_ns(to_user_ns(ns));
 }
 
-static int userns_install(struct nsproxy *nsproxy, void *ns)
+static int userns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 {
 	struct user_namespace *user_ns = to_user_ns(ns);
 	struct cred *cred;
@@ -893,18 +893,12 @@ static int userns_install(struct nsproxy *nsproxy, void *ns)
 	return commit_creds(cred);
 }
 
-static unsigned int userns_inum(void *ns)
-{
-	return ((struct ns_common *)ns)->inum;
-}
-
 const struct proc_ns_operations userns_operations = {
 	.name		= "user",
 	.type		= CLONE_NEWUSER,
 	.get		= userns_get,
 	.put		= userns_put,
 	.install	= userns_install,
-	.inum		= userns_inum,
 };
 
 static __init int user_namespaces_init(void)
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 1917f74be8e..20697befe46 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -93,7 +93,7 @@ static inline struct uts_namespace *to_uts_ns(struct ns_common *ns)
 	return container_of(ns, struct uts_namespace, ns);
 }
 
-static void *utsns_get(struct task_struct *task)
+static struct ns_common *utsns_get(struct task_struct *task)
 {
 	struct uts_namespace *ns = NULL;
 	struct nsproxy *nsproxy;
@@ -109,12 +109,12 @@ static void *utsns_get(struct task_struct *task)
 	return ns ? &ns->ns : NULL;
 }
 
-static void utsns_put(void *ns)
+static void utsns_put(struct ns_common *ns)
 {
 	put_uts_ns(to_uts_ns(ns));
 }
 
-static int utsns_install(struct nsproxy *nsproxy, void *new)
+static int utsns_install(struct nsproxy *nsproxy, struct ns_common *new)
 {
 	struct uts_namespace *ns = to_uts_ns(new);
 
@@ -128,16 +128,10 @@ static int utsns_install(struct nsproxy *nsproxy, void *new)
 	return 0;
 }
 
-static unsigned int utsns_inum(void *vp)
-{
-	return ((struct ns_common *)vp)->inum;
-}
-
 const struct proc_ns_operations utsns_operations = {
 	.name		= "uts",
 	.type		= CLONE_NEWUTS,
 	.get		= utsns_get,
 	.put		= utsns_put,
 	.install	= utsns_install,
-	.inum		= utsns_inum,
 };
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 97f4dc2132a..2161f0979fc 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -629,7 +629,7 @@ void unregister_pernet_device(struct pernet_operations *ops)
 EXPORT_SYMBOL_GPL(unregister_pernet_device);
 
 #ifdef CONFIG_NET_NS
-static void *netns_get(struct task_struct *task)
+static struct ns_common *netns_get(struct task_struct *task)
 {
 	struct net *net = NULL;
 	struct nsproxy *nsproxy;
@@ -648,12 +648,12 @@ static inline struct net *to_net_ns(struct ns_common *ns)
 	return container_of(ns, struct net, ns);
 }
 
-static void netns_put(void *ns)
+static void netns_put(struct ns_common *ns)
 {
 	put_net(to_net_ns(ns));
 }
 
-static int netns_install(struct nsproxy *nsproxy, void *ns)
+static int netns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 {
 	struct net *net = to_net_ns(ns);
 
@@ -666,17 +666,11 @@ static int netns_install(struct nsproxy *nsproxy, void *ns)
 	return 0;
 }
 
-static unsigned int netns_inum(void *ns)
-{
-	return ((struct ns_common *)ns)->inum;
-}
-
 const struct proc_ns_operations netns_operations = {
 	.name		= "net",
 	.type		= CLONE_NEWNET,
 	.get		= netns_get,
 	.put		= netns_put,
 	.install	= netns_install,
-	.inum		= netns_inum,
 };
 #endif
-- 
cgit v1.2.3-70-g09d2


From 6344c433a452b1a05d03a61a6a85d89f793bb7b8 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 1 Nov 2014 00:45:45 -0400
Subject: new helpers: ns_alloc_inum/ns_free_inum

take struct ns_common *, for now simply wrappers around proc_{alloc,free}_inum()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namespace.c           | 4 ++--
 include/linux/proc_ns.h  | 3 +++
 ipc/namespace.c          | 6 +++---
 kernel/pid_namespace.c   | 4 ++--
 kernel/user_namespace.c  | 4 ++--
 kernel/utsname.c         | 4 ++--
 net/core/net_namespace.c | 4 ++--
 7 files changed, 16 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index b9c16c3f63f..30738d20086 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2645,7 +2645,7 @@ dput_out:
 
 static void free_mnt_ns(struct mnt_namespace *ns)
 {
-	proc_free_inum(ns->ns.inum);
+	ns_free_inum(&ns->ns);
 	put_user_ns(ns->user_ns);
 	kfree(ns);
 }
@@ -2667,7 +2667,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
 	new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
 	if (!new_ns)
 		return ERR_PTR(-ENOMEM);
-	ret = proc_alloc_inum(&new_ns->ns.inum);
+	ret = ns_alloc_inum(&new_ns->ns);
 	if (ret) {
 		kfree(new_ns);
 		return ERR_PTR(ret);
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index f284959391f..f5780ee7f8f 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -71,4 +71,7 @@ static inline bool proc_ns_inode(struct inode *inode) { return false; }
 
 #endif /* CONFIG_PROC_FS */
 
+#define ns_alloc_inum(ns) proc_alloc_inum(&(ns)->inum)
+#define ns_free_inum(ns) proc_free_inum((ns)->inum)
+
 #endif /* _LINUX_PROC_NS_H */
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 531029a67fe..bcdd7a5c122 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -26,7 +26,7 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 	if (ns == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	err = proc_alloc_inum(&ns->ns.inum);
+	err = ns_alloc_inum(&ns->ns);
 	if (err) {
 		kfree(ns);
 		return ERR_PTR(err);
@@ -35,7 +35,7 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 	atomic_set(&ns->count, 1);
 	err = mq_init_ns(ns);
 	if (err) {
-		proc_free_inum(ns->ns.inum);
+		ns_free_inum(&ns->ns);
 		kfree(ns);
 		return ERR_PTR(err);
 	}
@@ -119,7 +119,7 @@ static void free_ipc_ns(struct ipc_namespace *ns)
 	 */
 	ipcns_notify(IPCNS_REMOVED);
 	put_user_ns(ns->user_ns);
-	proc_free_inum(ns->ns.inum);
+	ns_free_inum(&ns->ns);
 	kfree(ns);
 }
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 79aabce49a8..5aa9158a84d 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -105,7 +105,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 	if (ns->pid_cachep == NULL)
 		goto out_free_map;
 
-	err = proc_alloc_inum(&ns->ns.inum);
+	err = ns_alloc_inum(&ns->ns);
 	if (err)
 		goto out_free_map;
 
@@ -142,7 +142,7 @@ static void destroy_pid_namespace(struct pid_namespace *ns)
 {
 	int i;
 
-	proc_free_inum(ns->ns.inum);
+	ns_free_inum(&ns->ns);
 	for (i = 0; i < PIDMAP_ENTRIES; i++)
 		kfree(ns->pidmap[i].page);
 	put_user_ns(ns->user_ns);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 29cd5ccfc37..6bf8177768e 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -86,7 +86,7 @@ int create_user_ns(struct cred *new)
 	if (!ns)
 		return -ENOMEM;
 
-	ret = proc_alloc_inum(&ns->ns.inum);
+	ret = ns_alloc_inum(&ns->ns);
 	if (ret) {
 		kmem_cache_free(user_ns_cachep, ns);
 		return ret;
@@ -136,7 +136,7 @@ void free_user_ns(struct user_namespace *ns)
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 		key_put(ns->persistent_keyring_register);
 #endif
-		proc_free_inum(ns->ns.inum);
+		ns_free_inum(&ns->ns);
 		kmem_cache_free(user_ns_cachep, ns);
 		ns = parent;
 	} while (atomic_dec_and_test(&parent->count));
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 20697befe46..c2a2b321d88 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -42,7 +42,7 @@ static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns,
 	if (!ns)
 		return ERR_PTR(-ENOMEM);
 
-	err = proc_alloc_inum(&ns->ns.inum);
+	err = ns_alloc_inum(&ns->ns);
 	if (err) {
 		kfree(ns);
 		return ERR_PTR(err);
@@ -84,7 +84,7 @@ void free_uts_ns(struct kref *kref)
 
 	ns = container_of(kref, struct uts_namespace, kref);
 	put_user_ns(ns->user_ns);
-	proc_free_inum(ns->ns.inum);
+	ns_free_inum(&ns->ns);
 	kfree(ns);
 }
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 2161f0979fc..da775f53f3f 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -386,12 +386,12 @@ EXPORT_SYMBOL_GPL(get_net_ns_by_pid);
 
 static __net_init int net_ns_net_init(struct net *net)
 {
-	return proc_alloc_inum(&net->ns.inum);
+	return ns_alloc_inum(&net->ns);
 }
 
 static __net_exit void net_ns_net_exit(struct net *net)
 {
-	proc_free_inum(net->ns.inum);
+	ns_free_inum(&net->ns);
 }
 
 static struct pernet_operations __net_initdata net_ns_ops = {
-- 
cgit v1.2.3-70-g09d2


From 33c429405a2c8d9e42afb9fee88a63cfb2de1e98 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 1 Nov 2014 02:32:53 -0400
Subject: copy address of proc_ns_ops into ns_common

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namespace.c            | 1 +
 fs/proc/inode.c           | 6 ++----
 include/linux/ns_common.h | 3 +++
 init/version.c            | 3 +++
 ipc/msgutil.c             | 3 +++
 ipc/namespace.c           | 1 +
 kernel/nsproxy.c          | 8 ++++----
 kernel/pid.c              | 3 +++
 kernel/pid_namespace.c    | 1 +
 kernel/user.c             | 3 +++
 kernel/user_namespace.c   | 1 +
 kernel/utsname.c          | 2 ++
 net/core/net_namespace.c  | 9 +++++++--
 13 files changed, 34 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index 30738d20086..f815218f92d 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2672,6 +2672,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
 		kfree(new_ns);
 		return ERR_PTR(ret);
 	}
+	new_ns->ns.ops = &mntns_operations;
 	new_ns->seq = atomic64_add_return(1, &mnt_ns_seq);
 	atomic_set(&new_ns->count, 1);
 	new_ns->root = NULL;
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 43b703c6cd3..a212996e098 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -32,7 +32,6 @@ static void proc_evict_inode(struct inode *inode)
 {
 	struct proc_dir_entry *de;
 	struct ctl_table_header *head;
-	const struct proc_ns_operations *ns_ops;
 	struct ns_common *ns;
 
 	truncate_inode_pages_final(&inode->i_data);
@@ -51,10 +50,9 @@ static void proc_evict_inode(struct inode *inode)
 		sysctl_head_put(head);
 	}
 	/* Release any associated namespace */
-	ns_ops = PROC_I(inode)->ns.ns_ops;
 	ns = PROC_I(inode)->ns.ns;
-	if (ns_ops && ns)
-		ns_ops->put(ns);
+	if (ns && ns->ops)
+		ns->ops->put(ns);
 }
 
 static struct kmem_cache * proc_inode_cachep;
diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index e7db1cd5404..ce23cf4bbe6 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -1,7 +1,10 @@
 #ifndef _LINUX_NS_COMMON_H
 #define _LINUX_NS_COMMON_H
 
+struct proc_ns_operations;
+
 struct ns_common {
+	const struct proc_ns_operations *ops;
 	unsigned int inum;
 };
 
diff --git a/init/version.c b/init/version.c
index e23dbdabb26..fe41a63efed 100644
--- a/init/version.c
+++ b/init/version.c
@@ -36,6 +36,9 @@ struct uts_namespace init_uts_ns = {
 	},
 	.user_ns = &init_user_ns,
 	.ns.inum = PROC_UTS_INIT_INO,
+#ifdef CONFIG_UTS_NS
+	.ns.ops = &utsns_operations,
+#endif
 };
 EXPORT_SYMBOL_GPL(init_uts_ns);
 
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index 5930471a290..2b491590eba 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -32,6 +32,9 @@ struct ipc_namespace init_ipc_ns = {
 	.count		= ATOMIC_INIT(1),
 	.user_ns = &init_user_ns,
 	.ns.inum = PROC_IPC_INIT_INO,
+#ifdef CONFIG_IPC_NS
+	.ns.ops = &ipcns_operations,
+#endif
 };
 
 atomic_t nr_ipc_ns = ATOMIC_INIT(1);
diff --git a/ipc/namespace.c b/ipc/namespace.c
index bcdd7a5c122..382e2aa42d8 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -31,6 +31,7 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 		kfree(ns);
 		return ERR_PTR(err);
 	}
+	ns->ns.ops = &ipcns_operations;
 
 	atomic_set(&ns->count, 1);
 	err = mq_init_ns(ns);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index ef42d0ab311..87c37221cb7 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -220,11 +220,11 @@ void exit_task_namespaces(struct task_struct *p)
 
 SYSCALL_DEFINE2(setns, int, fd, int, nstype)
 {
-	const struct proc_ns_operations *ops;
 	struct task_struct *tsk = current;
 	struct nsproxy *new_nsproxy;
 	struct proc_ns *ei;
 	struct file *file;
+	struct ns_common *ns;
 	int err;
 
 	file = proc_ns_fget(fd);
@@ -233,8 +233,8 @@ SYSCALL_DEFINE2(setns, int, fd, int, nstype)
 
 	err = -EINVAL;
 	ei = get_proc_ns(file_inode(file));
-	ops = ei->ns_ops;
-	if (nstype && (ops->type != nstype))
+	ns = ei->ns;
+	if (nstype && (ns->ops->type != nstype))
 		goto out;
 
 	new_nsproxy = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs);
@@ -243,7 +243,7 @@ SYSCALL_DEFINE2(setns, int, fd, int, nstype)
 		goto out;
 	}
 
-	err = ops->install(new_nsproxy, ei->ns);
+	err = ns->ops->install(new_nsproxy, ns);
 	if (err) {
 		free_nsproxy(new_nsproxy);
 		goto out;
diff --git a/kernel/pid.c b/kernel/pid.c
index 3650698cf1d..c17a993a4d2 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -80,6 +80,9 @@ struct pid_namespace init_pid_ns = {
 	.child_reaper = &init_task,
 	.user_ns = &init_user_ns,
 	.ns.inum = PROC_PID_INIT_INO,
+#ifdef CONFIG_PID_NS
+	.ns.ops = &pidns_operations,
+#endif
 };
 EXPORT_SYMBOL_GPL(init_pid_ns);
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 5aa9158a84d..e1bafe3b47b 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -108,6 +108,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 	err = ns_alloc_inum(&ns->ns);
 	if (err)
 		goto out_free_map;
+	ns->ns.ops = &pidns_operations;
 
 	kref_init(&ns->kref);
 	ns->level = level;
diff --git a/kernel/user.c b/kernel/user.c
index a7ca84bad8e..69b800aebf1 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,9 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.ns.inum = PROC_USER_INIT_INO,
+#ifdef CONFIG_USER_NS
+	.ns.ops = &userns_operations,
+#endif
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 	.persistent_keyring_register_sem =
 	__RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 6bf8177768e..1491ad00388 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -91,6 +91,7 @@ int create_user_ns(struct cred *new)
 		kmem_cache_free(user_ns_cachep, ns);
 		return ret;
 	}
+	ns->ns.ops = &userns_operations;
 
 	atomic_set(&ns->count, 1);
 	/* Leave the new->user_ns reference with the new user namespace. */
diff --git a/kernel/utsname.c b/kernel/utsname.c
index c2a2b321d88..831ea710823 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -48,6 +48,8 @@ static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns,
 		return ERR_PTR(err);
 	}
 
+	ns->ns.ops = &utsns_operations;
+
 	down_read(&uts_sem);
 	memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
 	ns->user_ns = get_user_ns(user_ns);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index da775f53f3f..4d4acaf7b49 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -339,6 +339,7 @@ struct net *get_net_ns_by_fd(int fd)
 {
 	struct proc_ns *ei;
 	struct file *file;
+	struct ns_common *ns;
 	struct net *net;
 
 	file = proc_ns_fget(fd);
@@ -346,8 +347,9 @@ struct net *get_net_ns_by_fd(int fd)
 		return ERR_CAST(file);
 
 	ei = get_proc_ns(file_inode(file));
-	if (ei->ns_ops == &netns_operations)
-		net = get_net(container_of(ei->ns, struct net, ns));
+	ns = ei->ns;
+	if (ns->ops == &netns_operations)
+		net = get_net(container_of(ns, struct net, ns));
 	else
 		net = ERR_PTR(-EINVAL);
 
@@ -386,6 +388,9 @@ EXPORT_SYMBOL_GPL(get_net_ns_by_pid);
 
 static __net_init int net_ns_net_init(struct net *net)
 {
+#ifdef CONFIG_NET_NS
+	net->ns.ops = &netns_operations;
+#endif
 	return ns_alloc_inum(&net->ns);
 }
 
-- 
cgit v1.2.3-70-g09d2


From f77c80142e1afe6d5c16975ca5d7d1fc324b16f9 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 1 Nov 2014 03:13:17 -0400
Subject: bury struct proc_ns in fs/proc

a) make get_proc_ns() return a pointer to struct ns_common
b) mirror ns_ops in dentry->d_fsdata of ns dentries, so that
is_mnt_ns_file() could get away with fewer dereferences.

That way struct proc_ns becomes invisible outside of fs/proc/*.c

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namespace.c           | 13 ++-----------
 fs/proc/internal.h       |  5 +++++
 fs/proc/namespaces.c     |  7 ++++---
 include/linux/proc_ns.h  |  9 ++-------
 kernel/nsproxy.c         |  4 +---
 net/core/net_namespace.c |  4 +---
 6 files changed, 15 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index f815218f92d..9dfb4cac0c4 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1570,16 +1570,7 @@ static bool is_mnt_ns_file(struct dentry *dentry)
 {
 	/* Is this a proxy for a mount namespace? */
 	struct inode *inode = dentry->d_inode;
-	struct proc_ns *ei;
-
-	if (!proc_ns_inode(inode))
-		return false;
-
-	ei = get_proc_ns(inode);
-	if (ei->ns_ops != &mntns_operations)
-		return false;
-
-	return true;
+	return proc_ns_inode(inode) && dentry->d_fsdata == &mntns_operations;
 }
 
 struct mnt_namespace *to_mnt_ns(struct ns_common *ns)
@@ -1596,7 +1587,7 @@ static bool mnt_ns_loop(struct dentry *dentry)
 	if (!is_mnt_ns_file(dentry))
 		return false;
 
-	mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode)->ns);
+	mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode));
 	return current->nsproxy->mnt_ns->seq >= mnt_ns->seq;
 }
 
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index aa7a0ee182e..0fabc48d905 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -57,6 +57,11 @@ union proc_op {
 		struct task_struct *task);
 };
 
+struct proc_ns {
+	struct ns_common *ns;
+	const struct proc_ns_operations *ns_ops;
+};
+
 struct proc_inode {
 	struct pid *pid;
 	int fd;
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 995e8e98237..18fc1cf899d 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -45,7 +45,7 @@ static const struct inode_operations ns_inode_operations = {
 static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
 {
 	struct inode *inode = dentry->d_inode;
-	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns.ns_ops;
+	const struct proc_ns_operations *ns_ops = dentry->d_fsdata;
 
 	return dynamic_dname(dentry, buffer, buflen, "%s:[%lu]",
 		ns_ops->name, inode->i_ino);
@@ -75,6 +75,7 @@ static struct dentry *proc_ns_get_dentry(struct super_block *sb,
 		ns_ops->put(ns);
 		return ERR_PTR(-ENOMEM);
 	}
+	dentry->d_fsdata = (void *)ns_ops;
 
 	inode = iget_locked(sb, ns->inum);
 	if (!inode) {
@@ -286,9 +287,9 @@ out_invalid:
 	return ERR_PTR(-EINVAL);
 }
 
-struct proc_ns *get_proc_ns(struct inode *inode)
+struct ns_common *get_proc_ns(struct inode *inode)
 {
-	return &PROC_I(inode)->ns;
+	return PROC_I(inode)->ns.ns;
 }
 
 bool proc_ns_inode(struct inode *inode)
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index f5780ee7f8f..2837ff41cfe 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -16,11 +16,6 @@ struct proc_ns_operations {
 	int (*install)(struct nsproxy *nsproxy, struct ns_common *ns);
 };
 
-struct proc_ns {
-	struct ns_common *ns;
-	const struct proc_ns_operations *ns_ops;
-};
-
 extern const struct proc_ns_operations netns_operations;
 extern const struct proc_ns_operations utsns_operations;
 extern const struct proc_ns_operations ipcns_operations;
@@ -44,7 +39,7 @@ enum {
 extern int pid_ns_prepare_proc(struct pid_namespace *ns);
 extern void pid_ns_release_proc(struct pid_namespace *ns);
 extern struct file *proc_ns_fget(int fd);
-extern struct proc_ns *get_proc_ns(struct inode *);
+extern struct ns_common *get_proc_ns(struct inode *);
 extern int proc_alloc_inum(unsigned int *pino);
 extern void proc_free_inum(unsigned int inum);
 extern bool proc_ns_inode(struct inode *inode);
@@ -59,7 +54,7 @@ static inline struct file *proc_ns_fget(int fd)
 	return ERR_PTR(-EINVAL);
 }
 
-static inline struct proc_ns *get_proc_ns(struct inode *inode) { return NULL; }
+static inline struct ns_common *get_proc_ns(struct inode *inode) { return NULL; }
 
 static inline int proc_alloc_inum(unsigned int *inum)
 {
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 87c37221cb7..49746c81ad8 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -222,7 +222,6 @@ SYSCALL_DEFINE2(setns, int, fd, int, nstype)
 {
 	struct task_struct *tsk = current;
 	struct nsproxy *new_nsproxy;
-	struct proc_ns *ei;
 	struct file *file;
 	struct ns_common *ns;
 	int err;
@@ -232,8 +231,7 @@ SYSCALL_DEFINE2(setns, int, fd, int, nstype)
 		return PTR_ERR(file);
 
 	err = -EINVAL;
-	ei = get_proc_ns(file_inode(file));
-	ns = ei->ns;
+	ns = get_proc_ns(file_inode(file));
 	if (nstype && (ns->ops->type != nstype))
 		goto out;
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 4d4acaf7b49..ce780c722e4 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -337,7 +337,6 @@ EXPORT_SYMBOL_GPL(__put_net);
 
 struct net *get_net_ns_by_fd(int fd)
 {
-	struct proc_ns *ei;
 	struct file *file;
 	struct ns_common *ns;
 	struct net *net;
@@ -346,8 +345,7 @@ struct net *get_net_ns_by_fd(int fd)
 	if (IS_ERR(file))
 		return ERR_CAST(file);
 
-	ei = get_proc_ns(file_inode(file));
-	ns = ei->ns;
+	ns = get_proc_ns(file_inode(file));
 	if (ns->ops == &netns_operations)
 		net = get_net(container_of(ns, struct net, ns));
 	else
-- 
cgit v1.2.3-70-g09d2


From d0747f10ed5fec3d1f40c4b350dc9673011fc8e2 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.m@jp.panasonic.com>
Date: Thu, 4 Dec 2014 14:42:25 -0800
Subject: uapi: fix to export linux/vm_sockets.h

A typo "header=y" was introduced by commit 7071cf7fc435 ("uapi: add
missing network related headers to kbuild").

Signed-off-by: Masahiro Yamada <yamada.m@jp.panasonic.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/uapi/linux/Kbuild | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 4c94f31a8c9..8523f9bb72f 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -427,7 +427,7 @@ header-y += virtio_net.h
 header-y += virtio_pci.h
 header-y += virtio_ring.h
 header-y += virtio_rng.h
-header=y += vm_sockets.h
+header-y += vm_sockets.h
 header-y += vt.h
 header-y += wait.h
 header-y += wanrouter.h
-- 
cgit v1.2.3-70-g09d2


From a89612aac3cc6b13e6738bd70e05faf6f3fc8d9e Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 5 Dec 2014 10:55:53 +0100
Subject: Bluetooth: Add HCI_RSSI_INVALID for unknown RSSI value

The Bluetooth core specification defines the value 127 as invalid for
RSSI values. So instead of hard coding it, lets add a constant for it.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 569c077778b..b6f7be1eb91 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -412,6 +412,7 @@ enum {
 
 /* The core spec defines 127 as the "not available" value */
 #define HCI_TX_POWER_INVALID	127
+#define HCI_RSSI_INVALID	127
 
 #define HCI_ROLE_MASTER		0x00
 #define HCI_ROLE_SLAVE		0x01
-- 
cgit v1.2.3-70-g09d2


From 7e61df5423fe88a3e92bce59fb47686e52fb1d84 Mon Sep 17 00:00:00 2001
From: Jakub Pawlowski <jpawlowski@google.com>
Date: Fri, 5 Dec 2014 10:55:54 +0100
Subject: Bluetooth: Add definitions for MGMT_OP_START_SERVICE_DISCOVERY

This patch adds the opcode and structure for Start Service Discovery
operation.

Signed-off-by: Jakub Pawlowski <jpawlowski@google.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/mgmt.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 9b382ea34fd..95c34d5180f 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -498,6 +498,15 @@ struct mgmt_cp_set_public_address {
 } __packed;
 #define MGMT_SET_PUBLIC_ADDRESS_SIZE	6
 
+#define MGMT_OP_START_SERVICE_DISCOVERY	0x003A
+struct mgmt_cp_start_service_discovery {
+	__u8 type;
+	__s8 rssi;
+	__le16 uuid_count;
+	__u8 uuids[0][16];
+} __packed;
+#define MGMT_START_SERVICE_DISCOVERY_SIZE 4
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16	opcode;
-- 
cgit v1.2.3-70-g09d2


From 37eab042be2196751ff108e6892951338b9a0969 Mon Sep 17 00:00:00 2001
From: Jakub Pawlowski <jpawlowski@google.com>
Date: Fri, 5 Dec 2014 10:55:55 +0100
Subject: Bluetooth: Add extra discovery fields for storing filter information

With the upcoming addition of support for Start Service Discovery, the
discovery handling needs to filter on RSSI and UUID values. For that
they need to be stored in the discovery handling. This patch adds the
appropiate fields and also make sure they are reset when discovery
has been stopped.

Signed-off-by: Jakub Pawlowski <jpawlowski@google.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  4 ++++
 net/bluetooth/hci_core.c         | 14 ++++++++++++++
 net/bluetooth/mgmt.c             |  2 ++
 3 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 1dae7001fc3..83ca58b9f4c 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -75,6 +75,9 @@ struct discovery_state {
 	u32			last_adv_flags;
 	u8			last_adv_data[HCI_MAX_AD_LENGTH];
 	u8			last_adv_data_len;
+	s8			rssi;
+	u16			uuid_count;
+	u8			(*uuids)[16];
 };
 
 struct hci_conn_hash {
@@ -503,6 +506,7 @@ static inline void discovery_init(struct hci_dev *hdev)
 	INIT_LIST_HEAD(&hdev->discovery.all);
 	INIT_LIST_HEAD(&hdev->discovery.unknown);
 	INIT_LIST_HEAD(&hdev->discovery.resolve);
+	hdev->discovery.rssi = HCI_RSSI_INVALID;
 }
 
 bool hci_discovery_active(struct hci_dev *hdev);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index f0018562b02..42f86dc3fb4 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2052,6 +2052,20 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state)
 	case DISCOVERY_STOPPED:
 		hci_update_background_scan(hdev);
 
+		/* Reset RSSI and UUID filters to ensure Start Discovery
+		 * and Start Service Discovery operate properly no matter
+		 * which one started the previous discovery.
+		 *
+		 * While the Start Discovery and Start Service Discovery
+		 * operations will set proper values for RSSI and UUID
+		 * count, it is important to actually free the allocated
+		 * list of UUIDs here.
+		 */
+		hdev->discovery.rssi = HCI_RSSI_INVALID;
+		hdev->discovery.uuid_count = 0;
+		kfree(hdev->discovery.uuids);
+		hdev->discovery.uuids = NULL;
+
 		if (old_state != DISCOVERY_STARTING)
 			mgmt_discovering(hdev, 0);
 		break;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 415ba417932..b6a0f3e6b71 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3867,6 +3867,8 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
 	}
 
 	hdev->discovery.type = cp->type;
+	hdev->discovery.rssi = HCI_RSSI_INVALID;
+	hdev->discovery.uuid_count = 0;
 
 	hci_req_init(&req, hdev);
 
-- 
cgit v1.2.3-70-g09d2


From 0256325ed666af8346c89deb9d437c2209f463cb Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 5 Dec 2014 11:45:21 +0100
Subject: Bluetooth: Add helper function for clearing the discovery filter

The discovery filter allocates memory for its UUID list. So use
a helper function to free it and reset it to default states.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 8 ++++++++
 net/bluetooth/hci_core.c         | 5 +----
 2 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 83ca58b9f4c..f07b1450b3c 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -509,6 +509,14 @@ static inline void discovery_init(struct hci_dev *hdev)
 	hdev->discovery.rssi = HCI_RSSI_INVALID;
 }
 
+static inline void hci_discovery_filter_clear(struct hci_dev *hdev)
+{
+	hdev->discovery.rssi = HCI_RSSI_INVALID;
+	hdev->discovery.uuid_count = 0;
+	kfree(hdev->discovery.uuids);
+	hdev->discovery.uuids = NULL;
+}
+
 bool hci_discovery_active(struct hci_dev *hdev);
 
 void hci_discovery_set_state(struct hci_dev *hdev, int state);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 42f86dc3fb4..3c81b5cdda8 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2061,10 +2061,7 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state)
 		 * count, it is important to actually free the allocated
 		 * list of UUIDs here.
 		 */
-		hdev->discovery.rssi = HCI_RSSI_INVALID;
-		hdev->discovery.uuid_count = 0;
-		kfree(hdev->discovery.uuids);
-		hdev->discovery.uuids = NULL;
+		hci_discovery_filter_clear(hdev);
 
 		if (old_state != DISCOVERY_STARTING)
 			mgmt_discovering(hdev, 0);
-- 
cgit v1.2.3-70-g09d2


From da25cf6a9869cff52b4fd189fdcd322ad2daf023 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 5 Dec 2014 13:03:35 +0100
Subject: Bluetooth: Report invalid RSSI for service discovery and background
 scan

When using Start Service Discovery and when background scanning is used
to report devices, the RSSI is reported or the value 127 is provided in
case RSSI in unavailable.

For Start Discovery the value 0 is reported to keep backwards
compatibility with the existing users.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  3 +++
 net/bluetooth/mgmt.c             | 12 ++++++++++--
 2 files changed, 13 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index f07b1450b3c..3c7827005c2 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -75,6 +75,7 @@ struct discovery_state {
 	u32			last_adv_flags;
 	u8			last_adv_data[HCI_MAX_AD_LENGTH];
 	u8			last_adv_data_len;
+	bool			report_invalid_rssi;
 	s8			rssi;
 	u16			uuid_count;
 	u8			(*uuids)[16];
@@ -506,11 +507,13 @@ static inline void discovery_init(struct hci_dev *hdev)
 	INIT_LIST_HEAD(&hdev->discovery.all);
 	INIT_LIST_HEAD(&hdev->discovery.unknown);
 	INIT_LIST_HEAD(&hdev->discovery.resolve);
+	hdev->discovery.report_invalid_rssi = true;
 	hdev->discovery.rssi = HCI_RSSI_INVALID;
 }
 
 static inline void hci_discovery_filter_clear(struct hci_dev *hdev)
 {
+	hdev->discovery.report_invalid_rssi = true;
 	hdev->discovery.rssi = HCI_RSSI_INVALID;
 	hdev->discovery.uuid_count = 0;
 	kfree(hdev->discovery.uuids);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 3ca2818d1c8..a91e484886f 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3912,6 +3912,7 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
 	hci_discovery_filter_clear(hdev);
 
 	hdev->discovery.type = cp->type;
+	hdev->discovery.report_invalid_rssi = false;
 
 	hci_req_init(&req, hdev);
 
@@ -7022,8 +7023,15 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 
 	memset(buf, 0, sizeof(buf));
 
-	/* Reset invalid RSSI to 0 to keep backwards API compliance */
-	if (rssi == HCI_RSSI_INVALID)
+	/* In case of device discovery with BR/EDR devices (pre 1.2), the
+	 * RSSI value was reported as 0 when not available. This behavior
+	 * is kept when using device discovery. This is required for full
+	 * backwards compatibility with the API.
+	 *
+	 * However when using service discovery, the value 127 will be
+	 * returned when the RSSI is not available.
+	 */
+	if (rssi == HCI_RSSI_INVALID && !hdev->discovery.report_invalid_rssi)
 		rssi = 0;
 
 	bacpy(&ev->addr.bdaddr, bdaddr);
-- 
cgit v1.2.3-70-g09d2


From a42a7a1fb5f1f9004b023594609dc22da02fc08b Mon Sep 17 00:00:00 2001
From: Robin Murphy <Robin.Murphy@arm.com>
Date: Fri, 5 Dec 2014 13:41:02 +0000
Subject: iommu: store DT-probed IOMMU data privately

Since the data pointer in the DT node is public and may be overwritten
by conflicting code, move the DT-probed IOMMU ops to a private list
where they will be safe.

Acked-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
[will: added missing #include and missing ')']
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 drivers/iommu/of_iommu.c | 39 +++++++++++++++++++++++++++++++++++++++
 include/linux/of_iommu.h | 12 ++----------
 2 files changed, 41 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 73236d3cc95..af1dc6a1c0a 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -22,6 +22,7 @@
 #include <linux/limits.h>
 #include <linux/of.h>
 #include <linux/of_iommu.h>
+#include <linux/slab.h>
 
 static const struct of_device_id __iommu_of_table_sentinel
 	__used __section(__iommu_of_table_end);
@@ -94,6 +95,44 @@ int of_get_dma_window(struct device_node *dn, const char *prefix, int index,
 }
 EXPORT_SYMBOL_GPL(of_get_dma_window);
 
+struct of_iommu_node {
+	struct list_head list;
+	struct device_node *np;
+	struct iommu_ops *ops;
+};
+static LIST_HEAD(of_iommu_list);
+static DEFINE_SPINLOCK(of_iommu_lock);
+
+void of_iommu_set_ops(struct device_node *np, struct iommu_ops *ops)
+{
+	struct of_iommu_node *iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
+
+	if (WARN_ON(!iommu))
+		return;
+
+	INIT_LIST_HEAD(&iommu->list);
+	iommu->np = np;
+	iommu->ops = ops;
+	spin_lock(&of_iommu_lock);
+	list_add_tail(&iommu->list, &of_iommu_list);
+	spin_unlock(&of_iommu_lock);
+}
+
+struct iommu_ops *of_iommu_get_ops(struct device_node *np)
+{
+	struct of_iommu_node *node;
+	struct iommu_ops *ops = NULL;
+
+	spin_lock(&of_iommu_lock);
+	list_for_each_entry(node, &of_iommu_list, list)
+		if (node->np == np) {
+			ops = node->ops;
+			break;
+		}
+	spin_unlock(&of_iommu_lock);
+	return ops;
+}
+
 struct iommu_ops *of_iommu_configure(struct device *dev)
 {
 	struct of_phandle_args iommu_spec;
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index d03abbb11c3..16c75547d72 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -31,16 +31,8 @@ static inline struct iommu_ops *of_iommu_configure(struct device *dev)
 
 #endif	/* CONFIG_OF_IOMMU */
 
-static inline void of_iommu_set_ops(struct device_node *np,
-				    const struct iommu_ops *ops)
-{
-	np->data = (struct iommu_ops *)ops;
-}
-
-static inline struct iommu_ops *of_iommu_get_ops(struct device_node *np)
-{
-	return np->data;
-}
+void of_iommu_set_ops(struct device_node *np, struct iommu_ops *ops);
+struct iommu_ops *of_iommu_get_ops(struct device_node *np);
 
 extern struct of_device_id __iommu_of_table;
 
-- 
cgit v1.2.3-70-g09d2


From aba96bada40d19a0afbc3bfcb3a47e29e23df7ea Mon Sep 17 00:00:00 2001
From: Vinod Koul <vinod.koul@intel.com>
Date: Fri, 5 Dec 2014 20:49:07 +0530
Subject: dmaengine: clarify the issue_pending expectations

Although Documentation explicitly mentions the expectations, the comment in
header can be lead to different expectation so clear up the confusion

Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 include/linux/dmaengine.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 653a1fd07ae..40cd75e21ea 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -447,7 +447,8 @@ struct dmaengine_unmap_data {
  * 	communicate status
  * @phys: physical address of the descriptor
  * @chan: target channel for this operation
- * @tx_submit: set the prepared descriptor(s) to be executed by the engine
+ * @tx_submit: accept the descriptor, assign ordered cookie and mark the
+ * descriptor pending. To be pushed on .issue_pending() call
  * @callback: routine to call after this operation is complete
  * @callback_param: general parameter to pass to the callback routine
  * ---async_tx api specific fields---
-- 
cgit v1.2.3-70-g09d2


From af8e80731a94ff9de9508b01d9e5d931d538dc6b Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 3 Dec 2014 20:55:42 +0100
Subject: crypto: af_alg - add user space interface for AEAD

AEAD requires the caller to specify the following information separate
from the data stream. This information allows the AEAD interface handler
to identify the AAD, ciphertext/plaintext and the authentication tag:

        * Associated authentication data of arbitrary length and
          length

        * Length of authentication tag for encryption

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/af_alg.c             | 6 ++++++
 include/crypto/if_alg.h     | 1 +
 include/uapi/linux/if_alg.h | 2 ++
 3 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 6a3ad801158..68ff1137dd7 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -421,6 +421,12 @@ int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con)
 			con->op = *(u32 *)CMSG_DATA(cmsg);
 			break;
 
+		case ALG_SET_AEAD_ASSOCLEN:
+			if (cmsg->cmsg_len < CMSG_LEN(sizeof(u32)))
+				return -EINVAL;
+			con->aead_assoclen = *(u32 *)CMSG_DATA(cmsg);
+			break;
+
 		default:
 			return -EINVAL;
 		}
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index d61c1117021..cd62bf4289e 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -42,6 +42,7 @@ struct af_alg_completion {
 struct af_alg_control {
 	struct af_alg_iv *iv;
 	int op;
+	unsigned int aead_assoclen;
 };
 
 struct af_alg_type {
diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h
index 0f9acce5b1f..f2acd2fde1f 100644
--- a/include/uapi/linux/if_alg.h
+++ b/include/uapi/linux/if_alg.h
@@ -32,6 +32,8 @@ struct af_alg_iv {
 #define ALG_SET_KEY			1
 #define ALG_SET_IV			2
 #define ALG_SET_OP			3
+#define ALG_SET_AEAD_ASSOCLEN		4
+#define ALG_SET_AEAD_AUTHSIZE		5
 
 /* Operations */
 #define ALG_OP_DECRYPT			0
-- 
cgit v1.2.3-70-g09d2


From 2331fd46f5452944f32a2bc78fa05026617887c6 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 5 Dec 2014 16:20:10 +0100
Subject: Bluetooth: Move LE advertising report defines to the right location

All Bluetooth commands and events are ordered by its opcode or event
id, but for some reason this one now stands out. So move it to its
correct spot in the list.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 38 +++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index b6f7be1eb91..edb55e54e03 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1751,6 +1751,25 @@ struct hci_ev_le_conn_complete {
 	__u8     clk_accurancy;
 } __packed;
 
+/* Advertising report event types */
+#define LE_ADV_IND		0x00
+#define LE_ADV_DIRECT_IND	0x01
+#define LE_ADV_SCAN_IND		0x02
+#define LE_ADV_NONCONN_IND	0x03
+#define LE_ADV_SCAN_RSP		0x04
+
+#define ADDR_LE_DEV_PUBLIC	0x00
+#define ADDR_LE_DEV_RANDOM	0x01
+
+#define HCI_EV_LE_ADVERTISING_REPORT	0x02
+struct hci_ev_le_advertising_info {
+	__u8	 evt_type;
+	__u8	 bdaddr_type;
+	bdaddr_t bdaddr;
+	__u8	 length;
+	__u8	 data[0];
+} __packed;
+
 #define HCI_EV_LE_CONN_UPDATE_COMPLETE	0x03
 struct hci_ev_le_conn_update_complete {
 	__u8     status;
@@ -1776,25 +1795,6 @@ struct hci_ev_le_remote_conn_param_req {
 	__le16 timeout;
 } __packed;
 
-/* Advertising report event types */
-#define LE_ADV_IND		0x00
-#define LE_ADV_DIRECT_IND	0x01
-#define LE_ADV_SCAN_IND		0x02
-#define LE_ADV_NONCONN_IND	0x03
-#define LE_ADV_SCAN_RSP		0x04
-
-#define ADDR_LE_DEV_PUBLIC	0x00
-#define ADDR_LE_DEV_RANDOM	0x01
-
-#define HCI_EV_LE_ADVERTISING_REPORT	0x02
-struct hci_ev_le_advertising_info {
-	__u8	 evt_type;
-	__u8	 bdaddr_type;
-	bdaddr_t bdaddr;
-	__u8	 length;
-	__u8	 data[0];
-} __packed;
-
 /* Internal events generated by Bluetooth stack */
 #define HCI_EV_STACK_INTERNAL	0xfd
 struct hci_ev_stack_internal {
-- 
cgit v1.2.3-70-g09d2


From 32c9d43fa5deac40eee5a689428367982f147044 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 5 Dec 2014 16:20:11 +0100
Subject: Bluetooth: Add definitions for LE Direct Advertising Report event

This patch adds the event id and data structures for the LE Direct
Advertising Report event.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index edb55e54e03..ffebd393af4 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1795,6 +1795,16 @@ struct hci_ev_le_remote_conn_param_req {
 	__le16 timeout;
 } __packed;
 
+#define HCI_EV_LE_DIRECT_ADV_REPORT	0x0B
+struct hci_ev_le_direct_adv_info {
+	__u8	 evt_type;
+	__u8	 bdaddr_type;
+	bdaddr_t bdaddr;
+	__u8	 direct_addr_type;
+	bdaddr_t direct_addr;
+	__s8	 rssi;
+} __packed;
+
 /* Internal events generated by Bluetooth stack */
 #define HCI_EV_STACK_INTERNAL	0xfd
 struct hci_ev_stack_internal {
-- 
cgit v1.2.3-70-g09d2


From 4b71bba45c420065044bf040b2284893ab900d03 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 5 Dec 2014 16:20:12 +0100
Subject: Bluetooth: Enabled LE Direct Advertising Report event if supported

When the controller supports the Extended Scanner Filter Policies, it
supports the LE Direct Advertising Report event. However by default
that event is blocked by the LE event mask. It is required to enable
it during controller setup.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 1 +
 net/bluetooth/hci_core.c    | 8 ++++++++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index ffebd393af4..40129b3838b 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -343,6 +343,7 @@ enum {
 #define HCI_LE_ENCRYPTION		0x01
 #define HCI_LE_CONN_PARAM_REQ_PROC	0x02
 #define HCI_LE_PING			0x10
+#define HCI_LE_EXT_SCAN_POLICY		0x80
 
 /* Connection modes */
 #define HCI_CM_ACTIVE	0x0000
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 523700eefdd..da8969e08b0 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1735,6 +1735,14 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt)
 						 * Parameter Request
 						 */
 
+		/* If the controller supports Extended Scanner Filter
+		 * Policies, enable the correspondig event.
+		 */
+		if (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY)
+			events[1] |= 0x04;	/* LE Direct Advertising
+						 * Report
+						 */
+
 		hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, sizeof(events),
 			    events);
 
-- 
cgit v1.2.3-70-g09d2


From 7ff4d90b4c24a03666f296c3d4878cd39001e81e Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 5 Dec 2014 17:19:27 -0600
Subject: groups: Consolidate the setgroups permission checks

Today there are 3 instances of setgroups and due to an oversight their
permission checking has diverged.  Add a common function so that
they may all share the same permission checking code.

This corrects the current oversight in the current permission checks
and adds a helper to avoid this in the future.

A user namespace security fix will update this new helper, shortly.

Cc: stable@vger.kernel.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 arch/s390/kernel/compat_linux.c | 2 +-
 include/linux/cred.h            | 1 +
 kernel/groups.c                 | 9 ++++++++-
 kernel/uid16.c                  | 2 +-
 4 files changed, 11 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index ca38139423a..437e6115927 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -249,7 +249,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplis
 	struct group_info *group_info;
 	int retval;
 
-	if (!capable(CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/include/linux/cred.h b/include/linux/cred.h
index b2d0820837c..2fb2ca2127e 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -68,6 +68,7 @@ extern void groups_free(struct group_info *);
 extern int set_current_groups(struct group_info *);
 extern void set_groups(struct cred *, struct group_info *);
 extern int groups_search(const struct group_info *, kgid_t);
+extern bool may_setgroups(void);
 
 /* access the groups "array" with this macro */
 #define GROUP_AT(gi, i) \
diff --git a/kernel/groups.c b/kernel/groups.c
index 451698f86cf..02d8a251c47 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -213,6 +213,13 @@ out:
 	return i;
 }
 
+bool may_setgroups(void)
+{
+	struct user_namespace *user_ns = current_user_ns();
+
+	return ns_capable(user_ns, CAP_SETGID);
+}
+
 /*
  *	SMP: Our groups are copy-on-write. We can set them safely
  *	without another task interfering.
@@ -223,7 +230,7 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!ns_capable(current_user_ns(), CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 602e5bbbcef..d58cc4d8f0d 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -176,7 +176,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!ns_capable(current_user_ns(), CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
-- 
cgit v1.2.3-70-g09d2


From 4fc11e61f46dd66730a18e8136607386007ee8c9 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.m@jp.panasonic.com>
Date: Mon, 1 Dec 2014 10:16:17 +0900
Subject: uapi: fix to export linux/vm_sockets.h

A typo "header=y" was introduced by commit 7071cf7fc435
(uapi: add missing network related headers to kbuild).

Signed-off-by: Masahiro Yamada <yamada.m@jp.panasonic.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/Kbuild | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 4c94f31a8c9..8523f9bb72f 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -427,7 +427,7 @@ header-y += virtio_net.h
 header-y += virtio_pci.h
 header-y += virtio_ring.h
 header-y += virtio_rng.h
-header=y += vm_sockets.h
+header-y += vm_sockets.h
 header-y += vt.h
 header-y += wait.h
 header-y += wanrouter.h
-- 
cgit v1.2.3-70-g09d2


From ddd872bc3098f9d9abe1680a6b2013e59e3337f7 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Mon, 1 Dec 2014 15:06:34 -0800
Subject: bpf: verifier: add checks for BPF_ABS | BPF_IND instructions

introduce program type BPF_PROG_TYPE_SOCKET_FILTER that is used
for attaching programs to sockets where ctx == skb.

add verifier checks for ABS/IND instructions which can only be seen
in socket filters, therefore the check:
  if (env->prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER)
    verbose("BPF_LD_ABS|IND instructions are only allowed in socket filters\n");

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/bpf.h |  1 +
 kernel/bpf/verifier.c    | 70 ++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 69 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4a3d0f84f17..45da7ec7d27 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -117,6 +117,7 @@ enum bpf_map_type {
 
 enum bpf_prog_type {
 	BPF_PROG_TYPE_UNSPEC,
+	BPF_PROG_TYPE_SOCKET_FILTER,
 };
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b6a1f7c14a6..a28e09c7825 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1172,6 +1172,70 @@ static int check_ld_imm(struct verifier_env *env, struct bpf_insn *insn)
 	return 0;
 }
 
+/* verify safety of LD_ABS|LD_IND instructions:
+ * - they can only appear in the programs where ctx == skb
+ * - since they are wrappers of function calls, they scratch R1-R5 registers,
+ *   preserve R6-R9, and store return value into R0
+ *
+ * Implicit input:
+ *   ctx == skb == R6 == CTX
+ *
+ * Explicit input:
+ *   SRC == any register
+ *   IMM == 32-bit immediate
+ *
+ * Output:
+ *   R0 - 8/16/32-bit skb data converted to cpu endianness
+ */
+static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn)
+{
+	struct reg_state *regs = env->cur_state.regs;
+	u8 mode = BPF_MODE(insn->code);
+	struct reg_state *reg;
+	int i, err;
+
+	if (env->prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) {
+		verbose("BPF_LD_ABS|IND instructions are only allowed in socket filters\n");
+		return -EINVAL;
+	}
+
+	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
+	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
+		verbose("BPF_LD_ABS uses reserved fields\n");
+		return -EINVAL;
+	}
+
+	/* check whether implicit source operand (register R6) is readable */
+	err = check_reg_arg(regs, BPF_REG_6, SRC_OP);
+	if (err)
+		return err;
+
+	if (regs[BPF_REG_6].type != PTR_TO_CTX) {
+		verbose("at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
+		return -EINVAL;
+	}
+
+	if (mode == BPF_IND) {
+		/* check explicit source operand */
+		err = check_reg_arg(regs, insn->src_reg, SRC_OP);
+		if (err)
+			return err;
+	}
+
+	/* reset caller saved regs to unreadable */
+	for (i = 0; i < CALLER_SAVED_REGS; i++) {
+		reg = regs + caller_saved[i];
+		reg->type = NOT_INIT;
+		reg->imm = 0;
+	}
+
+	/* mark destination R0 register as readable, since it contains
+	 * the value fetched from the packet
+	 */
+	regs[BPF_REG_0].type = UNKNOWN_VALUE;
+	return 0;
+}
+
 /* non-recursive DFS pseudo code
  * 1  procedure DFS-iterative(G,v):
  * 2      label v as discovered
@@ -1677,8 +1741,10 @@ process_bpf_exit:
 			u8 mode = BPF_MODE(insn->code);
 
 			if (mode == BPF_ABS || mode == BPF_IND) {
-				verbose("LD_ABS is not supported yet\n");
-				return -EINVAL;
+				err = check_ld_abs(env, insn);
+				if (err)
+					return err;
+
 			} else if (mode == BPF_IMM) {
 				err = check_ld_imm(env, insn);
 				if (err)
-- 
cgit v1.2.3-70-g09d2


From 89aa075832b0da4402acebd698d0411dcc82d03e Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Mon, 1 Dec 2014 15:06:35 -0800
Subject: net: sock: allow eBPF programs to be attached to sockets

introduce new setsockopt() command:

setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd, sizeof(prog_fd))

where prog_fd was received from syscall bpf(BPF_PROG_LOAD, attr, ...)
and attr->prog_type == BPF_PROG_TYPE_SOCKET_FILTER

setsockopt() calls bpf_prog_get() which increments refcnt of the program,
so it doesn't get unloaded while socket is using the program.

The same eBPF program can be attached to multiple sockets.

User task exit automatically closes socket which calls sk_filter_uncharge()
which decrements refcnt of eBPF program

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/alpha/include/uapi/asm/socket.h   |  3 ++
 arch/avr32/include/uapi/asm/socket.h   |  3 ++
 arch/cris/include/uapi/asm/socket.h    |  3 ++
 arch/frv/include/uapi/asm/socket.h     |  3 ++
 arch/ia64/include/uapi/asm/socket.h    |  3 ++
 arch/m32r/include/uapi/asm/socket.h    |  3 ++
 arch/mips/include/uapi/asm/socket.h    |  3 ++
 arch/mn10300/include/uapi/asm/socket.h |  3 ++
 arch/parisc/include/uapi/asm/socket.h  |  3 ++
 arch/powerpc/include/uapi/asm/socket.h |  3 ++
 arch/s390/include/uapi/asm/socket.h    |  3 ++
 arch/sparc/include/uapi/asm/socket.h   |  3 ++
 arch/xtensa/include/uapi/asm/socket.h  |  3 ++
 include/linux/bpf.h                    |  4 ++
 include/linux/filter.h                 |  1 +
 include/uapi/asm-generic/socket.h      |  3 ++
 net/core/filter.c                      | 97 +++++++++++++++++++++++++++++++++-
 net/core/sock.c                        | 13 +++++
 18 files changed, 155 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index e2fe0700b3b..9a20821b111 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -89,4 +89,7 @@
 
 #define SO_INCOMING_CPU		49
 
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h
index 92121b0f5b9..2b65ed6b277 100644
--- a/arch/avr32/include/uapi/asm/socket.h
+++ b/arch/avr32/include/uapi/asm/socket.h
@@ -82,4 +82,7 @@
 
 #define SO_INCOMING_CPU		49
 
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 #endif /* _UAPI__ASM_AVR32_SOCKET_H */
diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h
index 60f60f5b9b3..e2503d9f186 100644
--- a/arch/cris/include/uapi/asm/socket.h
+++ b/arch/cris/include/uapi/asm/socket.h
@@ -84,6 +84,9 @@
 
 #define SO_INCOMING_CPU		49
 
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 #endif /* _ASM_SOCKET_H */
 
 
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index 2c6890209ea..4823ad12557 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -82,5 +82,8 @@
 
 #define SO_INCOMING_CPU		49
 
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 #endif /* _ASM_SOCKET_H */
 
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 09a93fb566f..59be3d87f86 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -91,4 +91,7 @@
 
 #define SO_INCOMING_CPU		49
 
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index e8589819c27..7bc4cb27385 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -82,4 +82,7 @@
 
 #define SO_INCOMING_CPU		49
 
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 #endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 2e9ee8c55a1..dec3c850f36 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -100,4 +100,7 @@
 
 #define SO_INCOMING_CPU		49
 
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index f3492e8c9f7..cab7d6d5005 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -82,4 +82,7 @@
 
 #define SO_INCOMING_CPU		49
 
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 7984a1cab3d..a5cd40cd8ee 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -81,4 +81,7 @@
 
 #define SO_INCOMING_CPU		0x402A
 
+#define SO_ATTACH_BPF		0x402B
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index 3474e4ef166..c046666038f 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -89,4 +89,7 @@
 
 #define SO_INCOMING_CPU		49
 
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 #endif	/* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index 8457636c33e..296942d56e6 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -88,4 +88,7 @@
 
 #define SO_INCOMING_CPU		49
 
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 4a8003a9416..e6a16c40be5 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -78,6 +78,9 @@
 
 #define SO_INCOMING_CPU		0x0033
 
+#define SO_ATTACH_BPF		0x0034
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index c46f6a69684..4120af08616 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -93,4 +93,7 @@
 
 #define SO_INCOMING_CPU		49
 
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 #endif	/* _XTENSA_SOCKET_H */
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 75e94eaa228..bbfceb75645 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -128,7 +128,11 @@ struct bpf_prog_aux {
 	struct work_struct work;
 };
 
+#ifdef CONFIG_BPF_SYSCALL
 void bpf_prog_put(struct bpf_prog *prog);
+#else
+static inline void bpf_prog_put(struct bpf_prog *prog) {}
+#endif
 struct bpf_prog *bpf_prog_get(u32 ufd);
 /* verify correctness of eBPF program */
 int bpf_check(struct bpf_prog *fp, union bpf_attr *attr);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index ca95abd2bed..caac2087a4d 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -381,6 +381,7 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog);
 void bpf_prog_destroy(struct bpf_prog *fp);
 
 int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
+int sk_attach_bpf(u32 ufd, struct sock *sk);
 int sk_detach_filter(struct sock *sk);
 
 int bpf_check_classic(const struct sock_filter *filter, unsigned int flen);
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index f541ccefd4a..5c15c2a5c12 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -84,4 +84,7 @@
 
 #define SO_INCOMING_CPU		49
 
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
 #endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/net/core/filter.c b/net/core/filter.c
index 647b12265e1..8cc3c03078b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -44,6 +44,7 @@
 #include <linux/ratelimit.h>
 #include <linux/seccomp.h>
 #include <linux/if_vlan.h>
+#include <linux/bpf.h>
 
 /**
  *	sk_filter - run a packet through a socket filter
@@ -813,8 +814,12 @@ static void bpf_release_orig_filter(struct bpf_prog *fp)
 
 static void __bpf_prog_release(struct bpf_prog *prog)
 {
-	bpf_release_orig_filter(prog);
-	bpf_prog_free(prog);
+	if (prog->aux->prog_type == BPF_PROG_TYPE_SOCKET_FILTER) {
+		bpf_prog_put(prog);
+	} else {
+		bpf_release_orig_filter(prog);
+		bpf_prog_free(prog);
+	}
 }
 
 static void __sk_filter_release(struct sk_filter *fp)
@@ -1088,6 +1093,94 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(sk_attach_filter);
 
+#ifdef CONFIG_BPF_SYSCALL
+int sk_attach_bpf(u32 ufd, struct sock *sk)
+{
+	struct sk_filter *fp, *old_fp;
+	struct bpf_prog *prog;
+
+	if (sock_flag(sk, SOCK_FILTER_LOCKED))
+		return -EPERM;
+
+	prog = bpf_prog_get(ufd);
+	if (!prog)
+		return -EINVAL;
+
+	if (prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) {
+		/* valid fd, but invalid program type */
+		bpf_prog_put(prog);
+		return -EINVAL;
+	}
+
+	fp = kmalloc(sizeof(*fp), GFP_KERNEL);
+	if (!fp) {
+		bpf_prog_put(prog);
+		return -ENOMEM;
+	}
+	fp->prog = prog;
+
+	atomic_set(&fp->refcnt, 0);
+
+	if (!sk_filter_charge(sk, fp)) {
+		__sk_filter_release(fp);
+		return -ENOMEM;
+	}
+
+	old_fp = rcu_dereference_protected(sk->sk_filter,
+					   sock_owned_by_user(sk));
+	rcu_assign_pointer(sk->sk_filter, fp);
+
+	if (old_fp)
+		sk_filter_uncharge(sk, old_fp);
+
+	return 0;
+}
+
+/* allow socket filters to call
+ * bpf_map_lookup_elem(), bpf_map_update_elem(), bpf_map_delete_elem()
+ */
+static const struct bpf_func_proto *sock_filter_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_map_lookup_elem:
+		return &bpf_map_lookup_elem_proto;
+	case BPF_FUNC_map_update_elem:
+		return &bpf_map_update_elem_proto;
+	case BPF_FUNC_map_delete_elem:
+		return &bpf_map_delete_elem_proto;
+	default:
+		return NULL;
+	}
+}
+
+static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type)
+{
+	/* skb fields cannot be accessed yet */
+	return false;
+}
+
+static struct bpf_verifier_ops sock_filter_ops = {
+	.get_func_proto = sock_filter_func_proto,
+	.is_valid_access = sock_filter_is_valid_access,
+};
+
+static struct bpf_prog_type_list tl = {
+	.ops = &sock_filter_ops,
+	.type = BPF_PROG_TYPE_SOCKET_FILTER,
+};
+
+static int __init register_sock_filter_ops(void)
+{
+	bpf_register_prog_type(&tl);
+	return 0;
+}
+late_initcall(register_sock_filter_ops);
+#else
+int sk_attach_bpf(u32 ufd, struct sock *sk)
+{
+	return -EOPNOTSUPP;
+}
+#endif
 int sk_detach_filter(struct sock *sk)
 {
 	int ret = -ENOENT;
diff --git a/net/core/sock.c b/net/core/sock.c
index 0725cf0cb68..9a56b2000c3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -888,6 +888,19 @@ set_rcvbuf:
 		}
 		break;
 
+	case SO_ATTACH_BPF:
+		ret = -EINVAL;
+		if (optlen == sizeof(u32)) {
+			u32 ufd;
+
+			ret = -EFAULT;
+			if (copy_from_user(&ufd, optval, sizeof(ufd)))
+				break;
+
+			ret = sk_attach_bpf(ufd, sk);
+		}
+		break;
+
 	case SO_DETACH_FILTER:
 		ret = sk_detach_filter(sk);
 		break;
-- 
cgit v1.2.3-70-g09d2


From 6cfad789610342443923737a9def8b637151dc4d Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Thu, 27 Nov 2014 08:08:10 +0000
Subject: ASoC: rsnd: rename SSI function name of PIO

Current R-Car sound SSI PIO/DMA mode are using interrupt.
it is no longer "xxx_pio_xxx", rename it.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/rcar_snd.h |  8 ++++----
 sound/soc/sh/rcar/ssi.c  | 23 +++++++++++------------
 2 files changed, 15 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/sound/rcar_snd.h b/include/sound/rcar_snd.h
index d76412b84b4..83284cae464 100644
--- a/include/sound/rcar_snd.h
+++ b/include/sound/rcar_snd.h
@@ -36,14 +36,14 @@
 #define RSND_SSI_CLK_PIN_SHARE		(1 << 31)
 #define RSND_SSI_NO_BUSIF		(1 << 30) /* SSI+DMA without BUSIF */
 
-#define RSND_SSI(_dma_id, _pio_irq, _flags)		\
-{ .dma_id = _dma_id, .pio_irq = _pio_irq, .flags = _flags }
+#define RSND_SSI(_dma_id, _irq, _flags)		\
+{ .dma_id = _dma_id, .irq = _irq, .flags = _flags }
 #define RSND_SSI_UNUSED \
-{ .dma_id = -1, .pio_irq = -1, .flags = 0 }
+{ .dma_id = -1, .irq = -1, .flags = 0 }
 
 struct rsnd_ssi_platform_info {
 	int dma_id;
-	int pio_irq;
+	int irq;
 	u32 flags;
 };
 
diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c
index 6f7080b017f..3844fbef466 100644
--- a/sound/soc/sh/rcar/ssi.c
+++ b/sound/soc/sh/rcar/ssi.c
@@ -82,7 +82,7 @@ struct rsnd_ssi {
 #define rsnd_ssi_nr(priv) ((priv)->ssi_nr)
 #define rsnd_mod_to_ssi(_mod) container_of((_mod), struct rsnd_ssi, mod)
 #define rsnd_dma_to_ssi(dma)  rsnd_mod_to_ssi(rsnd_dma_to_mod(dma))
-#define rsnd_ssi_pio_available(ssi) ((ssi)->info->pio_irq > 0)
+#define rsnd_ssi_pio_available(ssi) ((ssi)->info->irq > 0)
 #define rsnd_ssi_dma_available(ssi) \
 	rsnd_dma_available(rsnd_mod_to_dma(&(ssi)->mod))
 #define rsnd_ssi_clk_from_parent(ssi) ((ssi)->parent)
@@ -352,9 +352,6 @@ static void rsnd_ssi_record_error(struct rsnd_ssi *ssi, u32 status)
 	}
 }
 
-/*
- *		SSI PIO
- */
 static int rsnd_ssi_start(struct rsnd_mod *mod,
 			  struct rsnd_dai *rdai)
 {
@@ -386,7 +383,7 @@ static int rsnd_ssi_stop(struct rsnd_mod *mod,
 	return 0;
 }
 
-static irqreturn_t rsnd_ssi_pio_interrupt(int irq, void *data)
+static irqreturn_t rsnd_ssi_interrupt(int irq, void *data)
 {
 	struct rsnd_ssi *ssi = data;
 	struct rsnd_dai *rdai = ssi->rdai;
@@ -436,17 +433,19 @@ static irqreturn_t rsnd_ssi_pio_interrupt(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+/*
+ *		SSI PIO
+ */
 static int rsnd_ssi_pio_probe(struct rsnd_mod *mod,
 			      struct rsnd_dai *rdai)
 {
 	struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
 	struct device *dev = rsnd_priv_to_dev(priv);
 	struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod);
-	int irq = ssi->info->pio_irq;
 	int ret;
 
-	ret = devm_request_irq(dev, irq,
-			       rsnd_ssi_pio_interrupt,
+	ret = devm_request_irq(dev, ssi->info->irq,
+			       rsnd_ssi_interrupt,
 			       IRQF_SHARED,
 			       dev_name(dev), ssi);
 	if (ret)
@@ -477,8 +476,8 @@ static int rsnd_ssi_dma_probe(struct rsnd_mod *mod,
 	int dma_id = ssi->info->dma_id;
 	int ret;
 
-	ret = devm_request_irq(dev, ssi->info->pio_irq,
-			       rsnd_ssi_pio_interrupt,
+	ret = devm_request_irq(dev, ssi->info->irq,
+			       rsnd_ssi_interrupt,
 			       IRQF_SHARED,
 			       dev_name(dev), ssi);
 	if (ret)
@@ -509,7 +508,7 @@ static int rsnd_ssi_dma_remove(struct rsnd_mod *mod,
 	struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
 	struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod);
 	struct device *dev = rsnd_priv_to_dev(priv);
-	int irq = ssi->info->pio_irq;
+	int irq = ssi->info->irq;
 
 	rsnd_dma_quit(rsnd_mod_to_priv(mod), rsnd_mod_to_dma(mod));
 
@@ -680,7 +679,7 @@ static void rsnd_of_parse_ssi(struct platform_device *pdev,
 		/*
 		 * irq
 		 */
-		ssi_info->pio_irq = irq_of_parse_and_map(np, 0);
+		ssi_info->irq = irq_of_parse_and_map(np, 0);
 
 		/*
 		 * DMA
-- 
cgit v1.2.3-70-g09d2


From bac78aabcfece0c493b2ad824c68fbdc20448cbc Mon Sep 17 00:00:00 2001
From: Andri Yngvason <andri.yngvason@marel.com>
Date: Wed, 3 Dec 2014 17:54:13 +0000
Subject: can: dev: Consolidate and unify state change handling

The handling of can error states is different between platforms.
This is an attempt to correct that problem.

I've moved this handling into a generic function for changing the
error state. This ensures that error state changes are handled
the same way everywhere (where this function is used).

This new mechanism also adds reverse state transitioning in error
frames, i.e. the user will be notified through the socket interface
when the state goes down.

Signed-off-by: Andri Yngvason <andri.yngvason@marel.com>
Acked-by: Wolfgang Grandegger <wg@grandegger.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev.c          | 78 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/can/dev.h        |  3 ++
 include/uapi/linux/can/error.h |  1 +
 3 files changed, 82 insertions(+)

(limited to 'include')

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 2cfe5012e4e..3ec8f6f25e5 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -273,6 +273,84 @@ static int can_get_bittiming(struct net_device *dev, struct can_bittiming *bt,
 	return err;
 }
 
+static void can_update_state_error_stats(struct net_device *dev,
+					 enum can_state new_state)
+{
+	struct can_priv *priv = netdev_priv(dev);
+
+	if (new_state <= priv->state)
+		return;
+
+	switch (new_state) {
+	case CAN_STATE_ERROR_WARNING:
+		priv->can_stats.error_warning++;
+		break;
+	case CAN_STATE_ERROR_PASSIVE:
+		priv->can_stats.error_passive++;
+		break;
+	case CAN_STATE_BUS_OFF:
+	default:
+		break;
+	};
+}
+
+static int can_tx_state_to_frame(struct net_device *dev, enum can_state state)
+{
+	switch (state) {
+	case CAN_STATE_ERROR_ACTIVE:
+		return CAN_ERR_CRTL_ACTIVE;
+	case CAN_STATE_ERROR_WARNING:
+		return CAN_ERR_CRTL_TX_WARNING;
+	case CAN_STATE_ERROR_PASSIVE:
+		return CAN_ERR_CRTL_TX_PASSIVE;
+	default:
+		return 0;
+	}
+}
+
+static int can_rx_state_to_frame(struct net_device *dev, enum can_state state)
+{
+	switch (state) {
+	case CAN_STATE_ERROR_ACTIVE:
+		return CAN_ERR_CRTL_ACTIVE;
+	case CAN_STATE_ERROR_WARNING:
+		return CAN_ERR_CRTL_RX_WARNING;
+	case CAN_STATE_ERROR_PASSIVE:
+		return CAN_ERR_CRTL_RX_PASSIVE;
+	default:
+		return 0;
+	}
+}
+
+void can_change_state(struct net_device *dev, struct can_frame *cf,
+		      enum can_state tx_state, enum can_state rx_state)
+{
+	struct can_priv *priv = netdev_priv(dev);
+	enum can_state new_state = max(tx_state, rx_state);
+
+	if (unlikely(new_state == priv->state)) {
+		netdev_warn(dev, "%s: oops, state did not change", __func__);
+		return;
+	}
+
+	netdev_dbg(dev, "New error state: %d\n", new_state);
+
+	can_update_state_error_stats(dev, new_state);
+	priv->state = new_state;
+
+	if (unlikely(new_state == CAN_STATE_BUS_OFF)) {
+		cf->can_id |= CAN_ERR_BUSOFF;
+		return;
+	}
+
+	cf->can_id |= CAN_ERR_CRTL;
+	cf->data[1] |= tx_state >= rx_state ?
+		       can_tx_state_to_frame(dev, tx_state) : 0;
+	cf->data[1] |= tx_state <= rx_state ?
+		       can_rx_state_to_frame(dev, rx_state) : 0;
+}
+EXPORT_SYMBOL_GPL(can_change_state);
+
 /*
  * Local echo of CAN messages
  *
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index b37ea95bc34..c05ff0f9f9a 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -127,6 +127,9 @@ void unregister_candev(struct net_device *dev);
 int can_restart_now(struct net_device *dev);
 void can_bus_off(struct net_device *dev);
 
+void can_change_state(struct net_device *dev, struct can_frame *cf,
+		      enum can_state tx_state, enum can_state rx_state);
+
 void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
 		      unsigned int idx);
 unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx);
diff --git a/include/uapi/linux/can/error.h b/include/uapi/linux/can/error.h
index c247446ab25..1c508be9687 100644
--- a/include/uapi/linux/can/error.h
+++ b/include/uapi/linux/can/error.h
@@ -71,6 +71,7 @@
 #define CAN_ERR_CRTL_TX_PASSIVE  0x20 /* reached error passive status TX */
 				      /* (at least one error counter exceeds */
 				      /* the protocol-defined level of 127)  */
+#define CAN_ERR_CRTL_ACTIVE      0x40 /* recovered to error active state */
 
 /* error in CAN protocol (type) / data[2] */
 #define CAN_ERR_PROT_UNSPEC      0x00 /* unspecified */
-- 
cgit v1.2.3-70-g09d2


From 74faaf7aa64c76b60db0f5c994fd43a46be772ce Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 6 Dec 2014 21:20:20 +0100
Subject: genirq: Move irq_chip_write_msi_msg() helper to core

No point to expose this to the world. The only legitimate user is the
core code.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
---
 include/linux/irq.h | 6 ------
 kernel/irq/msi.c    | 6 ++++++
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 8badf34baf0..33da579d727 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -461,12 +461,6 @@ extern int irq_chip_set_affinity_parent(struct irq_data *data,
 					bool force);
 #endif
 
-static inline void irq_chip_write_msi_msg(struct irq_data *data,
-					  struct msi_msg *msg)
-{
-	data->chip->irq_write_msi_msg(data, msg);
-}
-
 /* Handling of unhandled and spurious interrupts: */
 extern void note_interrupt(unsigned int irq, struct irq_desc *desc,
 			   irqreturn_t action_ret);
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index f477a2f8ce5..3e18163f336 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -32,6 +32,12 @@ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
 EXPORT_SYMBOL_GPL(get_cached_msi_msg);
 
 #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
+static inline void irq_chip_write_msi_msg(struct irq_data *data,
+					  struct msi_msg *msg)
+{
+	data->chip->irq_write_msi_msg(data, msg);
+}
+
 /**
  * msi_domain_set_affinity - Generic affinity setter function for MSI domains
  * @irq_data:	The irq data associated to the interrupt
-- 
cgit v1.2.3-70-g09d2


From 00f634bc522dedc8418fb6d967a76cc4c10376a5 Mon Sep 17 00:00:00 2001
From: Ley Foon Tan <lftan@altera.com>
Date: Thu, 6 Nov 2014 15:19:34 +0800
Subject: asm-generic: add generic futex for !CONFIG_SMP

Follow m68k futex implementation for !CONFIG_SMP.

Signed-off-by: Ley Foon Tan <lftan@altera.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
---
 include/asm-generic/futex.h | 114 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 114 insertions(+)

(limited to 'include')

diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index 01f227e1425..b59b5a52637 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -5,6 +5,119 @@
 #include <linux/uaccess.h>
 #include <asm/errno.h>
 
+#ifndef CONFIG_SMP
+/*
+ * The following implementation only for uniprocessor machines.
+ * For UP, it's relies on the fact that pagefault_disable() also disables
+ * preemption to ensure mutual exclusion.
+ *
+ */
+
+/**
+ * futex_atomic_op_inuser() - Atomic arithmetic operation with constant
+ *			  argument and comparison of the previous
+ *			  futex value with another constant.
+ *
+ * @encoded_op:	encoded operation to execute
+ * @uaddr:	pointer to user space address
+ *
+ * Return:
+ * 0 - On success
+ * <0 - On error
+ */
+static inline int
+futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+{
+	int op = (encoded_op >> 28) & 7;
+	int cmp = (encoded_op >> 24) & 15;
+	int oparg = (encoded_op << 8) >> 20;
+	int cmparg = (encoded_op << 20) >> 20;
+	int oldval, ret;
+	u32 tmp;
+
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+		oparg = 1 << oparg;
+
+	pagefault_disable();
+
+	ret = -EFAULT;
+	if (unlikely(get_user(oldval, uaddr) != 0))
+		goto out_pagefault_enable;
+
+	ret = 0;
+	tmp = oldval;
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		tmp = oparg;
+		break;
+	case FUTEX_OP_ADD:
+		tmp += oparg;
+		break;
+	case FUTEX_OP_OR:
+		tmp |= oparg;
+		break;
+	case FUTEX_OP_ANDN:
+		tmp &= ~oparg;
+		break;
+	case FUTEX_OP_XOR:
+		tmp ^= oparg;
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	if (ret == 0 && unlikely(put_user(tmp, uaddr) != 0))
+		ret = -EFAULT;
+
+out_pagefault_enable:
+	pagefault_enable();
+
+	if (ret == 0) {
+		switch (cmp) {
+		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
+		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
+		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
+		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
+		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
+		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
+		default: ret = -ENOSYS;
+		}
+	}
+	return ret;
+}
+
+/**
+ * futex_atomic_cmpxchg_inatomic() - Compare and exchange the content of the
+ *				uaddr with newval if the current value is
+ *				oldval.
+ * @uval:	pointer to store content of @uaddr
+ * @uaddr:	pointer to user space address
+ * @oldval:	old value
+ * @newval:	new value to store to @uaddr
+ *
+ * Return:
+ * 0 - On success
+ * <0 - On error
+ */
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	u32 val;
+
+	if (unlikely(get_user(val, uaddr) != 0))
+		return -EFAULT;
+
+	if (val == oldval && unlikely(put_user(newval, uaddr) != 0))
+		return -EFAULT;
+
+	*uval = val;
+
+	return 0;
+}
+
+#else
 static inline int
 futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
@@ -54,4 +167,5 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	return -ENOSYS;
 }
 
+#endif /* CONFIG_SMP */
 #endif
-- 
cgit v1.2.3-70-g09d2


From 4fdace8d4f8bee9ba163646e8530394f9c36e67e Mon Sep 17 00:00:00 2001
From: Ley Foon Tan <lftan@altera.com>
Date: Thu, 6 Nov 2014 15:19:54 +0800
Subject: Add ELF machine define for Nios2

Signed-off-by: Ley Foon Tan <lftan@altera.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
---
 include/uapi/linux/elf-em.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h
index aa90bc98b6e..ae99f7743cf 100644
--- a/include/uapi/linux/elf-em.h
+++ b/include/uapi/linux/elf-em.h
@@ -34,6 +34,7 @@
 #define EM_MN10300	89	/* Panasonic/MEI MN10300, AM33 */
 #define EM_OPENRISC     92     /* OpenRISC 32-bit embedded processor */
 #define EM_BLACKFIN     106     /* ADI Blackfin Processor */
+#define EM_ALTERA_NIOS2	113	/* Altera Nios II soft-core processor */
 #define EM_TI_C6000	140	/* TI C6X DSPs */
 #define EM_AARCH64	183	/* ARM 64 bit */
 #define EM_FRV		0x5441	/* Fujitsu FR-V */
-- 
cgit v1.2.3-70-g09d2


From fe5afb13d46e76b07ab7e732f2b694dcafef4d9d Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 5 Dec 2014 11:31:22 +0100
Subject: mmc: core: Let mmc_send_tuning() to take struct mmc_host* as
 parameter

To be able to use mmc_send_tuning() prior the struct mmc_card has been
allocated, let's convert it to take the struct mmc_host* as parameter
instead.

Suggested-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Dong Aisheng <b29396@freescale.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
---
 drivers/mmc/core/mmc_ops.c | 7 +++----
 include/linux/mmc/core.h   | 2 +-
 2 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 12b2a32df34..3b044c5b029 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -547,14 +547,13 @@ int mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 }
 EXPORT_SYMBOL_GPL(mmc_switch);
 
-int mmc_send_tuning(struct mmc_card *card)
+int mmc_send_tuning(struct mmc_host *host)
 {
 	struct mmc_request mrq = {NULL};
 	struct mmc_command cmd = {0};
 	struct mmc_data data = {0};
 	struct scatterlist sg;
-	struct mmc_host *mmc = card->host;
-	struct mmc_ios *ios = &mmc->ios;
+	struct mmc_ios *ios = &host->ios;
 	const u8 *tuning_block_pattern;
 	int size, err = 0;
 	u8 *data_buf;
@@ -596,7 +595,7 @@ int mmc_send_tuning(struct mmc_card *card)
 	data.sg_len = 1;
 	sg_init_one(&sg, data_buf, size);
 
-	mmc_wait_for_req(mmc, &mrq);
+	mmc_wait_for_req(host, &mrq);
 
 	if (cmd.error) {
 		err = cmd.error;
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index c4bdaa12869..cb2b0400d28 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -154,7 +154,7 @@ extern void mmc_start_bkops(struct mmc_card *card, bool from_exception);
 extern int __mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int, bool,
 			bool, bool);
 extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int);
-extern int mmc_send_tuning(struct mmc_card *card);
+extern int mmc_send_tuning(struct mmc_host *host);
 extern int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd);
 
 #define MMC_ERASE_ARG		0x00000000
-- 
cgit v1.2.3-70-g09d2


From a3b63979f8a32af9e975a793fd0f612d42072740 Mon Sep 17 00:00:00 2001
From: Micky Ching <micky_ching@realsil.com.cn>
Date: Fri, 5 Dec 2014 13:54:26 +0800
Subject: mfd: rtsx: Add func to split u32 into register

Add helper function to write u32 to registers, if we want to put u32
value to 4 continuous register, this can help us reduce tedious work.

Signed-off-by: Micky Ching <micky_ching@realsil.com.cn>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/rtsx_pci.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h
index 1604dda4edc..0c12628e91c 100644
--- a/include/linux/mfd/rtsx_pci.h
+++ b/include/linux/mfd/rtsx_pci.h
@@ -558,6 +558,7 @@
 #define SD_SAMPLE_POINT_CTL		0xFDA7
 #define SD_PUSH_POINT_CTL		0xFDA8
 #define SD_CMD0				0xFDA9
+#define   SD_CMD_START			0x40
 #define SD_CMD1				0xFDAA
 #define SD_CMD2				0xFDAB
 #define SD_CMD3				0xFDAC
@@ -995,4 +996,12 @@ static inline int rtsx_pci_update_cfg_byte(struct rtsx_pcr *pcr, int addr,
 	return pci_write_config_byte(pcr->pci, addr, (val & mask) | append);
 }
 
+static inline void rtsx_pci_write_be32(struct rtsx_pcr *pcr, u16 reg, u32 val)
+{
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, reg,     0xFF, val >> 24);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, reg + 1, 0xFF, val >> 16);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, reg + 2, 0xFF, val >> 8);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, reg + 3, 0xFF, val);
+}
+
 #endif
-- 
cgit v1.2.3-70-g09d2


From bf35df66f1c613b46e054ca35ceb5caddacc6fa8 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 8 Dec 2014 15:44:47 +0100
Subject: ALSA: jack: Add dummy snd_jack_set_key() definition
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For fixing a build error with CONFIG_SND_JACK=n
  sound/soc/codecs/ts3a227e.c:223:2: error: implicit declaration of function ‘snd_jack_set_key’ [-Werror=implicit-function-declaration]

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/jack.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/sound/jack.h b/include/sound/jack.h
index 67f2bbcd515..218235030eb 100644
--- a/include/sound/jack.h
+++ b/include/sound/jack.h
@@ -105,6 +105,13 @@ static inline void snd_jack_set_parent(struct snd_jack *jack,
 {
 }
 
+static inline int snd_jack_set_key(struct snd_jack *jack,
+				   enum snd_jack_types type,
+				   int keytype)
+{
+	return 0;
+}
+
 static inline void snd_jack_report(struct snd_jack *jack, int status)
 {
 }
-- 
cgit v1.2.3-70-g09d2


From ad9914ac3b1f5c12ef2cf1c58a6ddda306fb79d4 Mon Sep 17 00:00:00 2001
From: Lukasz Majewski <l.majewski@samsung.com>
Date: Mon, 8 Dec 2014 18:04:19 +0100
Subject: thermal: of: Rename struct __thermal_trip to struct thermal_trip

This patch changes name of struct __thermal_trip to thermal_trip and moves
declaration of the latter to ./include/linux/thermal.h for better visibility.

Signed-off-by: Lukasz Majewski <l.majewski@samsung.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/of-thermal.c | 21 +++------------------
 include/linux/thermal.h      | 15 +++++++++++++++
 2 files changed, 18 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
index 87b9cfe28eb..d3ac117e2dd 100644
--- a/drivers/thermal/of-thermal.c
+++ b/drivers/thermal/of-thermal.c
@@ -36,21 +36,6 @@
 
 /***   Private data structures to represent thermal device tree data ***/
 
-/**
- * struct __thermal_trip - representation of a point in temperature domain
- * @np: pointer to struct device_node that this trip point was created from
- * @temperature: temperature value in miliCelsius
- * @hysteresis: relative hysteresis in miliCelsius
- * @type: trip point type
- */
-
-struct __thermal_trip {
-	struct device_node *np;
-	unsigned long int temperature;
-	unsigned long int hysteresis;
-	enum thermal_trip_type type;
-};
-
 /**
  * struct __thermal_bind_param - a match between trip and cooling device
  * @cooling_device: a pointer to identify the referred cooling device
@@ -88,7 +73,7 @@ struct __thermal_zone {
 
 	/* trip data */
 	int ntrips;
-	struct __thermal_trip *trips;
+	struct thermal_trip *trips;
 
 	/* cooling binding data */
 	int num_tbps;
@@ -538,7 +523,7 @@ EXPORT_SYMBOL_GPL(thermal_zone_of_sensor_unregister);
  */
 static int thermal_of_populate_bind_params(struct device_node *np,
 					   struct __thermal_bind_params *__tbp,
-					   struct __thermal_trip *trips,
+					   struct thermal_trip *trips,
 					   int ntrips)
 {
 	struct of_phandle_args cooling_spec;
@@ -641,7 +626,7 @@ static int thermal_of_get_trip_type(struct device_node *np,
  * Return: 0 on success, proper error code otherwise
  */
 static int thermal_of_populate_trip(struct device_node *np,
-				    struct __thermal_trip *trip)
+				    struct thermal_trip *trip)
 {
 	int prop;
 	int ret;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 5bc28a70014..b8d91efa854 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -303,6 +303,21 @@ struct thermal_zone_of_device_ops {
 	int (*get_trend)(void *, long *);
 };
 
+/**
+ * struct thermal_trip - representation of a point in temperature domain
+ * @np: pointer to struct device_node that this trip point was created from
+ * @temperature: temperature value in miliCelsius
+ * @hysteresis: relative hysteresis in miliCelsius
+ * @type: trip point type
+ */
+
+struct thermal_trip {
+	struct device_node *np;
+	unsigned long int temperature;
+	unsigned long int hysteresis;
+	enum thermal_trip_type type;
+};
+
 /* Function declarations */
 #ifdef CONFIG_THERMAL_OF
 struct thermal_zone_device *
-- 
cgit v1.2.3-70-g09d2


From b49b55bd4fba6aa9bb25459e0ac3991c60c4aba4 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Mon, 20 Oct 2014 16:13:19 +1000
Subject: drm/displayid: add displayid defines and edid extension (v2)

These are just taken from the DisplayID v1.3 spec, and the
DDC spec.

v2: use __packed (Jani)

Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drm_displayid.h | 76 +++++++++++++++++++++++++++++++++++++++++++++
 include/drm/drm_edid.h      |  2 ++
 2 files changed, 78 insertions(+)
 create mode 100644 include/drm/drm_displayid.h

(limited to 'include')

diff --git a/include/drm/drm_displayid.h b/include/drm/drm_displayid.h
new file mode 100644
index 00000000000..623b4e98e74
--- /dev/null
+++ b/include/drm/drm_displayid.h
@@ -0,0 +1,76 @@
+/*
+ * Copyright © 2014 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef DRM_DISPLAYID_H
+#define DRM_DISPLAYID_H
+
+#define DATA_BLOCK_PRODUCT_ID 0x00
+#define DATA_BLOCK_DISPLAY_PARAMETERS 0x01
+#define DATA_BLOCK_COLOR_CHARACTERISTICS 0x02
+#define DATA_BLOCK_TYPE_1_DETAILED_TIMING 0x03
+#define DATA_BLOCK_TYPE_2_DETAILED_TIMING 0x04
+#define DATA_BLOCK_TYPE_3_SHORT_TIMING 0x05
+#define DATA_BLOCK_TYPE_4_DMT_TIMING 0x06
+#define DATA_BLOCK_VESA_TIMING 0x07
+#define DATA_BLOCK_CEA_TIMING 0x08
+#define DATA_BLOCK_VIDEO_TIMING_RANGE 0x09
+#define DATA_BLOCK_PRODUCT_SERIAL_NUMBER 0x0a
+#define DATA_BLOCK_GP_ASCII_STRING 0x0b
+#define DATA_BLOCK_DISPLAY_DEVICE_DATA 0x0c
+#define DATA_BLOCK_INTERFACE_POWER_SEQUENCING 0x0d
+#define DATA_BLOCK_TRANSFER_CHARACTERISTICS 0x0e
+#define DATA_BLOCK_DISPLAY_INTERFACE 0x0f
+#define DATA_BLOCK_STEREO_DISPLAY_INTERFACE 0x10
+#define DATA_BLOCK_TILED_DISPLAY 0x12
+
+#define DATA_BLOCK_VENDOR_SPECIFIC 0x7f
+
+#define PRODUCT_TYPE_EXTENSION 0
+#define PRODUCT_TYPE_TEST 1
+#define PRODUCT_TYPE_PANEL 2
+#define PRODUCT_TYPE_MONITOR 3
+#define PRODUCT_TYPE_TV 4
+#define PRODUCT_TYPE_REPEATER 5
+#define PRODUCT_TYPE_DIRECT_DRIVE 6
+
+struct displayid_hdr {
+	u8 rev;
+	u8 bytes;
+	u8 prod_id;
+	u8 ext_count;
+} __packed;
+
+struct displayid_block {
+	u8 tag;
+	u8 rev;
+	u8 num_bytes;
+} __packed;
+
+struct displayid_tiled_block {
+	struct displayid_block base;
+	u8 tile_cap;
+	u8 topo[3];
+	u8 tile_size[4];
+	u8 tile_pixel_bezel[5];
+	u8 topology_id[8];
+} __packed;
+
+#endif
diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h
index d59240ffb1f..87d85e81d3a 100644
--- a/include/drm/drm_edid.h
+++ b/include/drm/drm_edid.h
@@ -27,12 +27,14 @@
 
 #define EDID_LENGTH 128
 #define DDC_ADDR 0x50
+#define DDC_ADDR2 0x52 /* E-DDC 1.2 - where DisplayID can hide */
 
 #define CEA_EXT	    0x02
 #define VTB_EXT	    0x10
 #define DI_EXT	    0x40
 #define LS_EXT	    0x50
 #define MI_EXT	    0x60
+#define DISPLAYID_EXT 0x70
 
 struct est_timings {
 	u8 t1;
-- 
cgit v1.2.3-70-g09d2


From 138f9ebb9755a8cf09fd6a9ff8d011aaf5fb478f Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Mon, 20 Oct 2014 16:17:17 +1000
Subject: drm: add tile_group support. (v3)

A tile group is an identifier shared by a single monitor,
DisplayID topology has 8 bytes we can use for this, just
use those for now until something else comes up in the
future. We assign these to an idr and use the idr to
tell userspace what connectors are in the same tile group.

DisplayID v1.3 says the serial number must be unique for
displays from the same manufacturer.

v2:
destroy idr (dvdhrm)
add docbook (danvet)
airlied:- not sure how to make docbook add fns to tile group section.

v3: fix missing unlock.

Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 Documentation/DocBook/drm.tmpl |  4 ++
 drivers/gpu/drm/drm_crtc.c     | 99 ++++++++++++++++++++++++++++++++++++++++++
 include/drm/drm_crtc.h         | 16 +++++++
 3 files changed, 119 insertions(+)

(limited to 'include')

diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index 56e2a9b65c6..bc4b5ab5848 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -2412,6 +2412,10 @@ void intel_crt_init(struct drm_device *dev)
 !Edrivers/gpu/drm/drm_plane_helper.c
 !Pdrivers/gpu/drm/drm_plane_helper.c overview
     </sect2>
+    <sect2>
+	  <title>Tile group</title>
+!Pdrivers/gpu/drm/drm_crtc.c Tile group
+    </sect2>
   </sect1>
 
   <!-- Internals: kms properties -->
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index de79283eaea..0d1eaa9966e 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -5152,6 +5152,7 @@ void drm_mode_config_init(struct drm_device *dev)
 	INIT_LIST_HEAD(&dev->mode_config.property_blob_list);
 	INIT_LIST_HEAD(&dev->mode_config.plane_list);
 	idr_init(&dev->mode_config.crtc_idr);
+	idr_init(&dev->mode_config.tile_idr);
 
 	drm_modeset_lock_all(dev);
 	drm_mode_create_standard_connector_properties(dev);
@@ -5239,6 +5240,7 @@ void drm_mode_config_cleanup(struct drm_device *dev)
 		crtc->funcs->destroy(crtc);
 	}
 
+	idr_destroy(&dev->mode_config.tile_idr);
 	idr_destroy(&dev->mode_config.crtc_idr);
 	drm_modeset_lock_fini(&dev->mode_config.connection_mutex);
 }
@@ -5261,3 +5263,100 @@ struct drm_property *drm_mode_create_rotation_property(struct drm_device *dev,
 					   supported_rotations);
 }
 EXPORT_SYMBOL(drm_mode_create_rotation_property);
+
+/**
+ * DOC: Tile group
+ *
+ * Tile groups are used to represent tiled monitors with a unique
+ * integer identifier. Tiled monitors using DisplayID v1.3 have
+ * a unique 8-byte handle, we store this in a tile group, so we
+ * have a common identifier for all tiles in a monitor group.
+ */
+static void drm_tile_group_free(struct kref *kref)
+{
+	struct drm_tile_group *tg = container_of(kref, struct drm_tile_group, refcount);
+	struct drm_device *dev = tg->dev;
+	mutex_lock(&dev->mode_config.idr_mutex);
+	idr_remove(&dev->mode_config.tile_idr, tg->id);
+	mutex_unlock(&dev->mode_config.idr_mutex);
+	kfree(tg);
+}
+
+/**
+ * drm_mode_put_tile_group - drop a reference to a tile group.
+ * @dev: DRM device
+ * @tg: tile group to drop reference to.
+ *
+ * drop reference to tile group and free if 0.
+ */
+void drm_mode_put_tile_group(struct drm_device *dev,
+			     struct drm_tile_group *tg)
+{
+	kref_put(&tg->refcount, drm_tile_group_free);
+}
+
+/**
+ * drm_mode_get_tile_group - get a reference to an existing tile group
+ * @dev: DRM device
+ * @topology: 8-bytes unique per monitor.
+ *
+ * Use the unique bytes to get a reference to an existing tile group.
+ *
+ * RETURNS:
+ * tile group or NULL if not found.
+ */
+struct drm_tile_group *drm_mode_get_tile_group(struct drm_device *dev,
+					       char topology[8])
+{
+	struct drm_tile_group *tg;
+	int id;
+	mutex_lock(&dev->mode_config.idr_mutex);
+	idr_for_each_entry(&dev->mode_config.tile_idr, tg, id) {
+		if (!memcmp(tg->group_data, topology, 8)) {
+			if (!kref_get_unless_zero(&tg->refcount))
+				tg = NULL;
+			mutex_unlock(&dev->mode_config.idr_mutex);
+			return tg;
+		}
+	}
+	mutex_unlock(&dev->mode_config.idr_mutex);
+	return NULL;
+}
+
+/**
+ * drm_mode_create_tile_group - create a tile group from a displayid description
+ * @dev: DRM device
+ * @topology: 8-bytes unique per monitor.
+ *
+ * Create a tile group for the unique monitor, and get a unique
+ * identifier for the tile group.
+ *
+ * RETURNS:
+ * new tile group or error.
+ */
+struct drm_tile_group *drm_mode_create_tile_group(struct drm_device *dev,
+						  char topology[8])
+{
+	struct drm_tile_group *tg;
+	int ret;
+
+	tg = kzalloc(sizeof(*tg), GFP_KERNEL);
+	if (!tg)
+		return ERR_PTR(-ENOMEM);
+
+	kref_init(&tg->refcount);
+	memcpy(tg->group_data, topology, 8);
+	tg->dev = dev;
+
+	mutex_lock(&dev->mode_config.idr_mutex);
+	ret = idr_alloc(&dev->mode_config.tile_idr, tg, 1, 0, GFP_KERNEL);
+	if (ret >= 0) {
+		tg->id = ret;
+	} else {
+		kfree(tg);
+		tg = ERR_PTR(ret);
+	}
+
+	mutex_unlock(&dev->mode_config.idr_mutex);
+	return tg;
+}
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index dd2c16e4333..8f760a2373f 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -137,6 +137,14 @@ struct drm_display_info {
 	u8 cea_rev;
 };
 
+/* data corresponds to displayid vend/prod/serial */
+struct drm_tile_group {
+	struct kref refcount;
+	struct drm_device *dev;
+	int id;
+	u8 group_data[8];
+};
+
 struct drm_framebuffer_funcs {
 	/* note: use drm_framebuffer_remove() */
 	void (*destroy)(struct drm_framebuffer *framebuffer);
@@ -978,6 +986,7 @@ struct drm_mode_config {
 	struct drm_modeset_acquire_ctx *acquire_ctx; /* for legacy _lock_all() / _unlock_all() */
 	struct mutex idr_mutex; /* for IDR management */
 	struct idr crtc_idr; /* use this idr for all IDs, fb, crtc, connector, modes - just makes life easier */
+	struct idr tile_idr; /* use this idr for all IDs, fb, crtc, connector, modes - just makes life easier */
 	/* this is limited to one for now */
 
 	struct mutex fb_lock; /* proctects global and per-file fb lists */
@@ -1326,6 +1335,13 @@ extern void drm_set_preferred_mode(struct drm_connector *connector,
 extern int drm_edid_header_is_valid(const u8 *raw_edid);
 extern bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid);
 extern bool drm_edid_is_valid(struct edid *edid);
+
+extern struct drm_tile_group *drm_mode_create_tile_group(struct drm_device *dev,
+							 char topology[8]);
+extern struct drm_tile_group *drm_mode_get_tile_group(struct drm_device *dev,
+					       char topology[8]);
+extern void drm_mode_put_tile_group(struct drm_device *dev,
+				   struct drm_tile_group *tg);
 struct drm_display_mode *drm_mode_find_dmt(struct drm_device *dev,
 					   int hsize, int vsize, int fresh,
 					   bool rb);
-- 
cgit v1.2.3-70-g09d2


From c6a0aed4d493936f61cd153db84531026705c94d Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Mon, 20 Oct 2014 16:28:02 +1000
Subject: drm/mst: cached EDID for logical ports (v2)

Logical ports are never going to have EDID changes,
they are used for the internal ports on MST monitors.

We cache the EDIDs from these to save time at MST probe.

v2: drop misplace tile property line, meant for other patch.

Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_dp_mst_topology.c | 19 +++++++++++++++++--
 drivers/gpu/drm/i915/intel_dp_mst.c   |  2 +-
 include/drm/drm_dp_mst_helper.h       |  4 +++-
 3 files changed, 21 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 9798bb79fe5..0a9d3aad3cb 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -861,6 +861,8 @@ static void drm_dp_destroy_port(struct kref *kref)
 	struct drm_dp_mst_topology_mgr *mgr = port->mgr;
 	if (!port->input) {
 		port->vcpi.num_slots = 0;
+
+		kfree(port->cached_edid);
 		if (port->connector)
 			(*port->mgr->cbs->destroy_connector)(mgr, port->connector);
 		drm_dp_port_teardown_pdt(port, port->pdt);
@@ -1100,6 +1102,10 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb,
 		char proppath[255];
 		build_mst_prop_path(port, mstb, proppath, sizeof(proppath));
 		port->connector = (*mstb->mgr->cbs->add_connector)(mstb->mgr, port, proppath);
+
+		if (port->port_num >= 8) {
+			port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc);
+		}
 	}
 
 	/* put reference to this port */
@@ -2170,7 +2176,8 @@ EXPORT_SYMBOL(drm_dp_mst_hpd_irq);
  * This returns the current connection state for a port. It validates the
  * port pointer still exists so the caller doesn't require a reference
  */
-enum drm_connector_status drm_dp_mst_detect_port(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port)
+enum drm_connector_status drm_dp_mst_detect_port(struct drm_connector *connector,
+						 struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port)
 {
 	enum drm_connector_status status = connector_status_disconnected;
 
@@ -2189,6 +2196,10 @@ enum drm_connector_status drm_dp_mst_detect_port(struct drm_dp_mst_topology_mgr
 
 	case DP_PEER_DEVICE_SST_SINK:
 		status = connector_status_connected;
+		/* for logical ports - cache the EDID */
+		if (port->port_num >= 8 && !port->cached_edid) {
+			port->cached_edid = drm_get_edid(connector, &port->aux.ddc);
+		}
 		break;
 	case DP_PEER_DEVICE_DP_LEGACY_CONV:
 		if (port->ldps)
@@ -2220,7 +2231,11 @@ struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_
 	if (!port)
 		return NULL;
 
-	edid = drm_get_edid(connector, &port->aux.ddc);
+	if (port->cached_edid)
+		edid = drm_edid_duplicate(port->cached_edid);
+	else
+		edid = drm_get_edid(connector, &port->aux.ddc);
+
 	drm_dp_put_port(port);
 	return edid;
 }
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index bfe35950637..428bb304162 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -283,7 +283,7 @@ intel_dp_mst_detect(struct drm_connector *connector, bool force)
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 	struct intel_dp *intel_dp = intel_connector->mst_port;
 
-	return drm_dp_mst_detect_port(&intel_dp->mst_mgr, intel_connector->port);
+	return drm_dp_mst_detect_port(connector, &intel_dp->mst_mgr, intel_connector->port);
 }
 
 static int
diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h
index cec6383bbdb..00c1da92724 100644
--- a/include/drm/drm_dp_mst_helper.h
+++ b/include/drm/drm_dp_mst_helper.h
@@ -92,6 +92,8 @@ struct drm_dp_mst_port {
 	struct drm_dp_vcpi vcpi;
 	struct drm_connector *connector;
 	struct drm_dp_mst_topology_mgr *mgr;
+
+	struct edid *cached_edid; /* for DP logical ports - make tiling work */
 };
 
 /**
@@ -474,7 +476,7 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms
 int drm_dp_mst_hpd_irq(struct drm_dp_mst_topology_mgr *mgr, u8 *esi, bool *handled);
 
 
-enum drm_connector_status drm_dp_mst_detect_port(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port);
+enum drm_connector_status drm_dp_mst_detect_port(struct drm_connector *connector, struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port);
 
 struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port);
 
-- 
cgit v1.2.3-70-g09d2


From 40d9b043a89e2301e1f97ade055a73ecc28e9afe Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Mon, 20 Oct 2014 16:29:33 +1000
Subject: drm/connector: store tile information from displayid (v3)

This creates a tile group from DisplayID block, and
stores the pieces of parsed info from the DisplayID block
into the connector.

v2: add missing signoff, add new connector bits to docs.

v3: remove some debugging.

Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_crtc.c |   5 ++
 drivers/gpu/drm/drm_edid.c | 144 ++++++++++++++++++++++++++++++++++++++++++++-
 include/drm/drm_crtc.h     |  18 ++++++
 3 files changed, 164 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 0d1eaa9966e..eb89327fb73 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -908,6 +908,11 @@ void drm_connector_cleanup(struct drm_connector *connector)
 	struct drm_device *dev = connector->dev;
 	struct drm_display_mode *mode, *t;
 
+	if (connector->tile_group) {
+		drm_mode_put_tile_group(dev, connector->tile_group);
+		connector->tile_group = NULL;
+	}
+
 	list_for_each_entry_safe(mode, t, &connector->probed_modes, head)
 		drm_mode_remove(connector, mode);
 
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index a7b5a71856a..72fd8820e18 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -34,6 +34,7 @@
 #include <linux/module.h>
 #include <drm/drmP.h>
 #include <drm/drm_edid.h>
+#include <drm/drm_displayid.h>
 
 #define version_greater(edid, maj, min) \
 	(((edid)->version > (maj)) || \
@@ -1014,6 +1015,8 @@ module_param_named(edid_fixup, edid_fixup, int, 0400);
 MODULE_PARM_DESC(edid_fixup,
 		 "Minimum number of valid EDID header bytes (0-8, default 6)");
 
+static void drm_get_displayid(struct drm_connector *connector,
+			      struct edid *edid);
 /**
  * drm_edid_block_valid - Sanity check the EDID block (base or extension)
  * @raw_edid: pointer to raw EDID block
@@ -1308,10 +1311,15 @@ EXPORT_SYMBOL(drm_probe_ddc);
 struct edid *drm_get_edid(struct drm_connector *connector,
 			  struct i2c_adapter *adapter)
 {
+	struct edid *edid;
+
 	if (!drm_probe_ddc(adapter))
 		return NULL;
 
-	return drm_do_get_edid(connector, drm_do_probe_ddc_edid, adapter);
+	edid = drm_do_get_edid(connector, drm_do_probe_ddc_edid, adapter);
+	if (edid)
+		drm_get_displayid(connector, edid);
+	return edid;
 }
 EXPORT_SYMBOL(drm_get_edid);
 
@@ -2406,7 +2414,7 @@ add_detailed_modes(struct drm_connector *connector, struct edid *edid,
 /*
  * Search EDID for CEA extension block.
  */
-static u8 *drm_find_cea_extension(struct edid *edid)
+static u8 *drm_find_edid_extension(struct edid *edid, int ext_id)
 {
 	u8 *edid_ext = NULL;
 	int i;
@@ -2418,7 +2426,7 @@ static u8 *drm_find_cea_extension(struct edid *edid)
 	/* Find CEA extension */
 	for (i = 0; i < edid->extensions; i++) {
 		edid_ext = (u8 *)edid + EDID_LENGTH * (i + 1);
-		if (edid_ext[0] == CEA_EXT)
+		if (edid_ext[0] == ext_id)
 			break;
 	}
 
@@ -2428,6 +2436,16 @@ static u8 *drm_find_cea_extension(struct edid *edid)
 	return edid_ext;
 }
 
+static u8 *drm_find_cea_extension(struct edid *edid)
+{
+	return drm_find_edid_extension(edid, CEA_EXT);
+}
+
+static u8 *drm_find_displayid_extension(struct edid *edid)
+{
+	return drm_find_edid_extension(edid, DISPLAYID_EXT);
+}
+
 /*
  * Calculate the alternate clock for the CEA mode
  * (60Hz vs. 59.94Hz etc.)
@@ -3888,3 +3906,123 @@ drm_hdmi_vendor_infoframe_from_display_mode(struct hdmi_vendor_infoframe *frame,
 	return 0;
 }
 EXPORT_SYMBOL(drm_hdmi_vendor_infoframe_from_display_mode);
+
+static int drm_parse_display_id(struct drm_connector *connector,
+				u8 *displayid, int length,
+				bool is_edid_extension)
+{
+	/* if this is an EDID extension the first byte will be 0x70 */
+	int idx = 0;
+	struct displayid_hdr *base;
+	struct displayid_block *block;
+	u8 csum = 0;
+	int i;
+
+	if (is_edid_extension)
+		idx = 1;
+
+	base = (struct displayid_hdr *)&displayid[idx];
+
+	DRM_DEBUG_KMS("base revision 0x%x, length %d, %d %d\n",
+		      base->rev, base->bytes, base->prod_id, base->ext_count);
+
+	if (base->bytes + 5 > length - idx)
+		return -EINVAL;
+
+	for (i = idx; i <= base->bytes + 5; i++) {
+		csum += displayid[i];
+	}
+	if (csum) {
+		DRM_ERROR("DisplayID checksum invalid, remainder is %d\n", csum);
+		return -EINVAL;
+	}
+
+	block = (struct displayid_block *)&displayid[idx + 4];
+	DRM_DEBUG_KMS("block id %d, rev %d, len %d\n",
+		      block->tag, block->rev, block->num_bytes);
+
+	switch (block->tag) {
+	case DATA_BLOCK_TILED_DISPLAY: {
+		struct displayid_tiled_block *tile = (struct displayid_tiled_block *)block;
+
+		u16 w, h;
+		u8 tile_v_loc, tile_h_loc;
+		u8 num_v_tile, num_h_tile;
+		struct drm_tile_group *tg;
+
+		w = tile->tile_size[0] | tile->tile_size[1] << 8;
+		h = tile->tile_size[2] | tile->tile_size[3] << 8;
+
+		num_v_tile = (tile->topo[0] & 0xf) | (tile->topo[2] & 0x30);
+		num_h_tile = (tile->topo[0] >> 4) | ((tile->topo[2] >> 2) & 0x30);
+		tile_v_loc = (tile->topo[1] & 0xf) | ((tile->topo[2] & 0x3) << 4);
+		tile_h_loc = (tile->topo[1] >> 4) | (((tile->topo[2] >> 2) & 0x3) << 4);
+
+		connector->has_tile = true;
+		if (tile->tile_cap & 0x80)
+			connector->tile_is_single_monitor = true;
+
+		connector->num_h_tile = num_h_tile + 1;
+		connector->num_v_tile = num_v_tile + 1;
+		connector->tile_h_loc = tile_h_loc;
+		connector->tile_v_loc = tile_v_loc;
+		connector->tile_h_size = w + 1;
+		connector->tile_v_size = h + 1;
+
+		DRM_DEBUG_KMS("tile cap 0x%x\n", tile->tile_cap);
+		DRM_DEBUG_KMS("tile_size %d x %d\n", w + 1, h + 1);
+		DRM_DEBUG_KMS("topo num tiles %dx%d, location %dx%d\n",
+		       num_h_tile + 1, num_v_tile + 1, tile_h_loc, tile_v_loc);
+		DRM_DEBUG_KMS("vend %c%c%c\n", tile->topology_id[0], tile->topology_id[1], tile->topology_id[2]);
+
+		tg = drm_mode_get_tile_group(connector->dev, tile->topology_id);
+		if (!tg) {
+			tg = drm_mode_create_tile_group(connector->dev, tile->topology_id);
+		}
+		if (!tg)
+			return -ENOMEM;
+
+		if (connector->tile_group != tg) {
+			/* if we haven't got a pointer,
+			   take the reference, drop ref to old tile group */
+			if (connector->tile_group) {
+				drm_mode_put_tile_group(connector->dev, connector->tile_group);
+			}
+			connector->tile_group = tg;
+		} else
+			/* if same tile group, then release the ref we just took. */
+			drm_mode_put_tile_group(connector->dev, tg);
+	}
+		break;
+	default:
+		printk("unknown displayid tag %d\n", block->tag);
+		break;
+	}
+	return 0;
+}
+
+static void drm_get_displayid(struct drm_connector *connector,
+			      struct edid *edid)
+{
+	void *displayid = NULL;
+	int ret;
+	connector->has_tile = false;
+	displayid = drm_find_displayid_extension(edid);
+	if (!displayid) {
+		/* drop reference to any tile group we had */
+		goto out_drop_ref;
+	}
+
+	ret = drm_parse_display_id(connector, displayid, EDID_LENGTH, true);
+	if (ret < 0)
+		goto out_drop_ref;
+	if (!connector->has_tile)
+		goto out_drop_ref;
+	return;
+out_drop_ref:
+	if (connector->tile_group) {
+		drm_mode_put_tile_group(connector->dev, connector->tile_group);
+		connector->tile_group = NULL;
+	}
+	return;
+}
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 8f760a2373f..01744ed7925 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -607,6 +607,15 @@ struct drm_encoder {
  * @bad_edid_counter: track sinks that give us an EDID with invalid checksum
  * @debugfs_entry: debugfs directory for this connector
  * @state: current atomic state for this connector
+ * @has_tile: is this connector connected to a tiled monitor
+ * @tile_group: tile group for the connected monitor
+ * @tile_is_single_monitor: whether the tile is one monitor housing
+ * @num_h_tile: number of horizontal tiles in the tile group
+ * @num_v_tile: number of vertical tiles in the tile group
+ * @tile_h_loc: horizontal location of this tile
+ * @tile_v_loc: vertical location of this tile
+ * @tile_h_size: horizontal size of this tile.
+ * @tile_v_size: vertical size of this tile.
  *
  * Each connector may be connected to one or more CRTCs, or may be clonable by
  * another connector if they can share a CRTC.  Each connector also has a specific
@@ -669,6 +678,15 @@ struct drm_connector {
 	struct dentry *debugfs_entry;
 
 	struct drm_connector_state *state;
+
+	/* DisplayID bits */
+	bool has_tile;
+	struct drm_tile_group *tile_group;
+	bool tile_is_single_monitor;
+
+	uint8_t num_h_tile, num_v_tile;
+	uint8_t tile_h_loc, tile_v_loc;
+	uint16_t tile_h_size, tile_v_size;
 };
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 6f134d7bb4347ab4c66ef123efb838fedb54186f Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Mon, 20 Oct 2014 16:30:50 +1000
Subject: drm/tile: expose the tile property to userspace (v3)

This takes the tiling info from the connector and
exposes it to userspace, as a blob object in a
connector property.

The contents of the blob is ABI.

v2: add property + function documentation.

v3: move property setup from previous patch.
add boilerplate + fix long line (Daniel)

Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 Documentation/DocBook/drm.tmpl        |  9 ++++++-
 drivers/gpu/drm/drm_crtc.c            | 51 +++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/drm_dp_mst_topology.c |  1 +
 drivers/gpu/drm/i915/intel_dp_mst.c   |  2 ++
 include/drm/drm_crtc.h                |  4 +++
 5 files changed, 66 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index bc4b5ab5848..60c1063d417 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -2551,7 +2551,7 @@ void intel_crt_init(struct drm_device *dev)
 	</tr>
 	<tr>
 	<td rowspan="23" valign="top" >DRM</td>
-	<td rowspan="3" valign="top" >Generic</td>
+	<td rowspan="4" valign="top" >Generic</td>
 	<td valign="top" >“EDID”</td>
 	<td valign="top" >BLOB | IMMUTABLE</td>
 	<td valign="top" >0</td>
@@ -2573,6 +2573,13 @@ void intel_crt_init(struct drm_device *dev)
 	<td valign="top" >Contains topology path to a connector.</td>
 	</tr>
 	<tr>
+	<td valign="top" >“TILE”</td>
+	<td valign="top" >BLOB | IMMUTABLE</td>
+	<td valign="top" >0</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >Contains tiling information for a connector.</td>
+	</tr>
+	<tr>
 	<td rowspan="1" valign="top" >Plane</td>
 	<td valign="top" >“type”</td>
 	<td valign="top" >ENUM | IMMUTABLE</td>
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index eb89327fb73..4a44f894f63 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -1344,6 +1344,11 @@ static int drm_mode_create_standard_connector_properties(struct drm_device *dev)
 				       "PATH", 0);
 	dev->mode_config.path_property = dev_path;
 
+	dev->mode_config.tile_property = drm_property_create(dev,
+							     DRM_MODE_PROP_BLOB |
+							     DRM_MODE_PROP_IMMUTABLE,
+							     "TILE", 0);
+
 	return 0;
 }
 
@@ -4087,6 +4092,52 @@ int drm_mode_connector_set_path_property(struct drm_connector *connector,
 }
 EXPORT_SYMBOL(drm_mode_connector_set_path_property);
 
+/**
+ * drm_mode_connector_set_tile_property - set tile property on connector
+ * @connector: connector to set property on.
+ *
+ * This looks up the tile information for a connector, and creates a
+ * property for userspace to parse if it exists. The property is of
+ * the form of 8 integers using ':' as a separator.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
+int drm_mode_connector_set_tile_property(struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+	int ret, size;
+	char tile[256];
+
+	if (connector->tile_blob_ptr)
+		drm_property_destroy_blob(dev, connector->tile_blob_ptr);
+
+	if (!connector->has_tile) {
+		connector->tile_blob_ptr = NULL;
+		ret = drm_object_property_set_value(&connector->base,
+						    dev->mode_config.tile_property, 0);
+		return ret;
+	}
+
+	snprintf(tile, 256, "%d:%d:%d:%d:%d:%d:%d:%d",
+		 connector->tile_group->id, connector->tile_is_single_monitor,
+		 connector->num_h_tile, connector->num_v_tile,
+		 connector->tile_h_loc, connector->tile_v_loc,
+		 connector->tile_h_size, connector->tile_v_size);
+	size = strlen(tile) + 1;
+
+	connector->tile_blob_ptr = drm_property_create_blob(connector->dev,
+							    size, tile);
+	if (!connector->tile_blob_ptr)
+		return -EINVAL;
+
+	ret = drm_object_property_set_value(&connector->base,
+					    dev->mode_config.tile_property,
+					    connector->tile_blob_ptr->base.id);
+	return ret;
+}
+EXPORT_SYMBOL(drm_mode_connector_set_tile_property);
+
 /**
  * drm_mode_connector_update_edid_property - update the edid property of a connector
  * @connector: drm connector
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 0a9d3aad3cb..9a5b68717ec 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -2236,6 +2236,7 @@ struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_
 	else
 		edid = drm_get_edid(connector, &port->aux.ddc);
 
+	drm_mode_connector_set_tile_property(connector);
 	drm_dp_put_port(port);
 	return edid;
 }
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 428bb304162..7f8c6a66680 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -414,6 +414,8 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 	intel_dp_add_properties(intel_dp, connector);
 
 	drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0);
+	drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0);
+
 	drm_mode_connector_set_path_property(connector, pathprop);
 	drm_reinit_primary_mode_group(dev);
 	mutex_lock(&dev->mode_config.mutex);
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 01744ed7925..b86329813ad 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -651,6 +651,8 @@ struct drm_connector {
 
 	struct drm_property_blob *path_blob_ptr;
 
+	struct drm_property_blob *tile_blob_ptr;
+
 	uint8_t polled; /* DRM_CONNECTOR_POLL_* */
 
 	/* requested DPMS state */
@@ -1048,6 +1050,7 @@ struct drm_mode_config {
 	struct drm_property *edid_property;
 	struct drm_property *dpms_property;
 	struct drm_property *path_property;
+	struct drm_property *tile_property;
 	struct drm_property *plane_type_property;
 	struct drm_property *rotation_property;
 
@@ -1217,6 +1220,7 @@ extern void drm_mode_config_cleanup(struct drm_device *dev);
 
 extern int drm_mode_connector_set_path_property(struct drm_connector *connector,
 						const char *path);
+int drm_mode_connector_set_tile_property(struct drm_connector *connector);
 extern int drm_mode_connector_update_edid_property(struct drm_connector *connector,
 						   const struct edid *edid);
 
-- 
cgit v1.2.3-70-g09d2


From b0ee9e7fa5b461a91f24d1d03b10c6bf162c86f9 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Mon, 20 Oct 2014 16:31:53 +1000
Subject: drm/fb: add support for tiled monitor configurations. (v2)

This adds fbdev/con support for tiled monitors, so that we
only set a mode on the correct half of the monitor, or
span the two halves if needed.

v2: remove unneeded ERROR, fix | vs ||

Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_fb_helper.c    | 121 +++++++++++++++++++++++++++++++------
 drivers/gpu/drm/i915/intel_fbdev.c |  24 +++++++-
 include/drm/drm_fb_helper.h        |   6 ++
 3 files changed, 128 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index a467460f2aa..52ce26d6b4f 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1000,19 +1000,21 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 	crtc_count = 0;
 	for (i = 0; i < fb_helper->crtc_count; i++) {
 		struct drm_display_mode *desired_mode;
+		int x, y;
 		desired_mode = fb_helper->crtc_info[i].desired_mode;
-
+		x = fb_helper->crtc_info[i].x;
+		y = fb_helper->crtc_info[i].y;
 		if (desired_mode) {
 			if (gamma_size == 0)
 				gamma_size = fb_helper->crtc_info[i].mode_set.crtc->gamma_size;
-			if (desired_mode->hdisplay < sizes.fb_width)
-				sizes.fb_width = desired_mode->hdisplay;
-			if (desired_mode->vdisplay < sizes.fb_height)
-				sizes.fb_height = desired_mode->vdisplay;
-			if (desired_mode->hdisplay > sizes.surface_width)
-				sizes.surface_width = desired_mode->hdisplay;
-			if (desired_mode->vdisplay > sizes.surface_height)
-				sizes.surface_height = desired_mode->vdisplay;
+			if (desired_mode->hdisplay + x < sizes.fb_width)
+				sizes.fb_width = desired_mode->hdisplay + x;
+			if (desired_mode->vdisplay + y < sizes.fb_height)
+				sizes.fb_height = desired_mode->vdisplay + y;
+			if (desired_mode->hdisplay + x > sizes.surface_width)
+				sizes.surface_width = desired_mode->hdisplay + x;
+			if (desired_mode->vdisplay + y > sizes.surface_height)
+				sizes.surface_height = desired_mode->vdisplay + y;
 			crtc_count++;
 		}
 	}
@@ -1312,6 +1314,7 @@ static void drm_enable_connectors(struct drm_fb_helper *fb_helper,
 
 static bool drm_target_cloned(struct drm_fb_helper *fb_helper,
 			      struct drm_display_mode **modes,
+			      struct drm_fb_offset *offsets,
 			      bool *enabled, int width, int height)
 {
 	int count, i, j;
@@ -1383,27 +1386,88 @@ static bool drm_target_cloned(struct drm_fb_helper *fb_helper,
 	return false;
 }
 
+static int drm_get_tile_offsets(struct drm_fb_helper *fb_helper,
+				struct drm_display_mode **modes,
+				struct drm_fb_offset *offsets,
+				int idx,
+				int h_idx, int v_idx)
+{
+	struct drm_fb_helper_connector *fb_helper_conn;
+	int i;
+	int hoffset = 0, voffset = 0;
+
+	for (i = 0; i < fb_helper->connector_count; i++) {
+		fb_helper_conn = fb_helper->connector_info[i];
+		if (!fb_helper_conn->connector->has_tile)
+			continue;
+
+		if (!modes[i] && (h_idx || v_idx)) {
+			DRM_DEBUG_KMS("no modes for connector tiled %d %d\n", i,
+				      fb_helper_conn->connector->base.id);
+			continue;
+		}
+		if (fb_helper_conn->connector->tile_h_loc < h_idx)
+			hoffset += modes[i]->hdisplay;
+
+		if (fb_helper_conn->connector->tile_v_loc < v_idx)
+			voffset += modes[i]->vdisplay;
+	}
+	offsets[idx].x = hoffset;
+	offsets[idx].y = voffset;
+	DRM_DEBUG_KMS("returned %d %d for %d %d\n", hoffset, voffset, h_idx, v_idx);
+	return 0;
+}
+
 static bool drm_target_preferred(struct drm_fb_helper *fb_helper,
 				 struct drm_display_mode **modes,
+				 struct drm_fb_offset *offsets,
 				 bool *enabled, int width, int height)
 {
 	struct drm_fb_helper_connector *fb_helper_conn;
 	int i;
-
+	uint64_t conn_configured = 0, mask;
+	int tile_pass = 0;
+	mask = (1 << fb_helper->connector_count) - 1;
+retry:
 	for (i = 0; i < fb_helper->connector_count; i++) {
 		fb_helper_conn = fb_helper->connector_info[i];
 
-		if (enabled[i] == false)
+		if (conn_configured & (1 << i))
+			continue;
+
+		if (enabled[i] == false) {
+			conn_configured |= (1 << i);
+			continue;
+		}
+
+		/* first pass over all the untiled connectors */
+		if (tile_pass == 0 && fb_helper_conn->connector->has_tile)
 			continue;
 
+		if (tile_pass == 1) {
+			if (fb_helper_conn->connector->tile_h_loc != 0 ||
+			    fb_helper_conn->connector->tile_v_loc != 0)
+				continue;
+
+		} else {
+			if (fb_helper_conn->connector->tile_h_loc != tile_pass -1 &&
+			    fb_helper_conn->connector->tile_v_loc != tile_pass - 1)
+			/* if this tile_pass doesn't cover any of the tiles - keep going */
+				continue;
+
+			/* find the tile offsets for this pass - need
+			   to find all tiles left and above */
+			drm_get_tile_offsets(fb_helper, modes, offsets,
+					     i, fb_helper_conn->connector->tile_h_loc, fb_helper_conn->connector->tile_v_loc);
+		}
 		DRM_DEBUG_KMS("looking for cmdline mode on connector %d\n",
 			      fb_helper_conn->connector->base.id);
 
 		/* got for command line mode first */
 		modes[i] = drm_pick_cmdline_mode(fb_helper_conn, width, height);
 		if (!modes[i]) {
-			DRM_DEBUG_KMS("looking for preferred mode on connector %d\n",
-				      fb_helper_conn->connector->base.id);
+			DRM_DEBUG_KMS("looking for preferred mode on connector %d %d\n",
+				      fb_helper_conn->connector->base.id, fb_helper_conn->connector->tile_group ? fb_helper_conn->connector->tile_group->id : 0);
 			modes[i] = drm_has_preferred_mode(fb_helper_conn, width, height);
 		}
 		/* No preferred modes, pick one off the list */
@@ -1413,6 +1477,12 @@ static bool drm_target_preferred(struct drm_fb_helper *fb_helper,
 		}
 		DRM_DEBUG_KMS("found mode %s\n", modes[i] ? modes[i]->name :
 			  "none");
+		conn_configured |= (1 << i);
+	}
+
+	if ((conn_configured & mask) != mask) {
+		tile_pass++;
+		goto retry;
 	}
 	return true;
 }
@@ -1502,6 +1572,7 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper)
 	struct drm_device *dev = fb_helper->dev;
 	struct drm_fb_helper_crtc **crtcs;
 	struct drm_display_mode **modes;
+	struct drm_fb_offset *offsets;
 	struct drm_mode_set *modeset;
 	bool *enabled;
 	int width, height;
@@ -1516,9 +1587,11 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper)
 			sizeof(struct drm_fb_helper_crtc *), GFP_KERNEL);
 	modes = kcalloc(dev->mode_config.num_connector,
 			sizeof(struct drm_display_mode *), GFP_KERNEL);
+	offsets = kcalloc(dev->mode_config.num_connector,
+			  sizeof(struct drm_fb_offset), GFP_KERNEL);
 	enabled = kcalloc(dev->mode_config.num_connector,
 			  sizeof(bool), GFP_KERNEL);
-	if (!crtcs || !modes || !enabled) {
+	if (!crtcs || !modes || !enabled || !offsets) {
 		DRM_ERROR("Memory allocation failed\n");
 		goto out;
 	}
@@ -1528,14 +1601,16 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper)
 
 	if (!(fb_helper->funcs->initial_config &&
 	      fb_helper->funcs->initial_config(fb_helper, crtcs, modes,
+					       offsets,
 					       enabled, width, height))) {
 		memset(modes, 0, dev->mode_config.num_connector*sizeof(modes[0]));
 		memset(crtcs, 0, dev->mode_config.num_connector*sizeof(crtcs[0]));
+		memset(offsets, 0, dev->mode_config.num_connector*sizeof(offsets[0]));
 
-		if (!drm_target_cloned(fb_helper,
-				       modes, enabled, width, height) &&
-		    !drm_target_preferred(fb_helper,
-					  modes, enabled, width, height))
+		if (!drm_target_cloned(fb_helper, modes, offsets,
+				       enabled, width, height) &&
+		    !drm_target_preferred(fb_helper, modes, offsets,
+					  enabled, width, height))
 			DRM_ERROR("Unable to find initial modes\n");
 
 		DRM_DEBUG_KMS("picking CRTCs for %dx%d config\n",
@@ -1555,18 +1630,23 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper)
 	for (i = 0; i < fb_helper->connector_count; i++) {
 		struct drm_display_mode *mode = modes[i];
 		struct drm_fb_helper_crtc *fb_crtc = crtcs[i];
+		struct drm_fb_offset *offset = &offsets[i];
 		modeset = &fb_crtc->mode_set;
 
 		if (mode && fb_crtc) {
-			DRM_DEBUG_KMS("desired mode %s set on crtc %d\n",
-				      mode->name, fb_crtc->mode_set.crtc->base.id);
+			DRM_DEBUG_KMS("desired mode %s set on crtc %d (%d,%d)\n",
+				      mode->name, fb_crtc->mode_set.crtc->base.id, offset->x, offset->y);
 			fb_crtc->desired_mode = mode;
+			fb_crtc->x = offset->x;
+			fb_crtc->y = offset->y;
 			if (modeset->mode)
 				drm_mode_destroy(dev, modeset->mode);
 			modeset->mode = drm_mode_duplicate(dev,
 							   fb_crtc->desired_mode);
 			modeset->connectors[modeset->num_connectors++] = fb_helper->connector_info[i]->connector;
 			modeset->fb = fb_helper->fb;
+			modeset->x = offset->x;
+			modeset->y = offset->y;
 		}
 	}
 
@@ -1583,6 +1663,7 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper)
 out:
 	kfree(crtcs);
 	kfree(modes);
+	kfree(offsets);
 	kfree(enabled);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index f2183b554cb..850cf7d6578 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -324,6 +324,7 @@ intel_fb_helper_crtc(struct drm_fb_helper *fb_helper, struct drm_crtc *crtc)
 static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 				    struct drm_fb_helper_crtc **crtcs,
 				    struct drm_display_mode **modes,
+				    struct drm_fb_offset *offsets,
 				    bool *enabled, int width, int height)
 {
 	struct drm_device *dev = fb_helper->dev;
@@ -332,6 +333,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 	bool fallback = true;
 	int num_connectors_enabled = 0;
 	int num_connectors_detected = 0;
+	uint64_t conn_configured = 0, mask;
+	int pass = 0;
 
 	save_enabled = kcalloc(dev->mode_config.num_connector, sizeof(bool),
 			       GFP_KERNEL);
@@ -339,7 +342,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 		return false;
 
 	memcpy(save_enabled, enabled, dev->mode_config.num_connector);
-
+	mask = (1 << fb_helper->connector_count) - 1;
+retry:
 	for (i = 0; i < fb_helper->connector_count; i++) {
 		struct drm_fb_helper_connector *fb_conn;
 		struct drm_connector *connector;
@@ -349,12 +353,19 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 		fb_conn = fb_helper->connector_info[i];
 		connector = fb_conn->connector;
 
+		if (conn_configured & (1 << i))
+			continue;
+
+		if (pass == 0 && !connector->has_tile)
+			continue;
+
 		if (connector->status == connector_status_connected)
 			num_connectors_detected++;
 
 		if (!enabled[i]) {
 			DRM_DEBUG_KMS("connector %s not enabled, skipping\n",
 				      connector->name);
+			conn_configured |= (1 << i);
 			continue;
 		}
 
@@ -373,6 +384,7 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 			DRM_DEBUG_KMS("connector %s has no encoder or crtc, skipping\n",
 				      connector->name);
 			enabled[i] = false;
+			conn_configured |= (1 << i);
 			continue;
 		}
 
@@ -400,8 +412,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 
 		/* try for preferred next */
 		if (!modes[i]) {
-			DRM_DEBUG_KMS("looking for preferred mode on connector %s\n",
-				      connector->name);
+			DRM_DEBUG_KMS("looking for preferred mode on connector %s %d\n",
+				      connector->name, connector->has_tile);
 			modes[i] = drm_has_preferred_mode(fb_conn, width,
 							  height);
 		}
@@ -444,6 +456,12 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 			      modes[i]->flags & DRM_MODE_FLAG_INTERLACE ? "i" :"");
 
 		fallback = false;
+		conn_configured |= (1 << i);
+	}
+
+	if ((conn_configured & mask) != mask) {
+		pass++;
+		goto retry;
 	}
 
 	/*
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index f4ad254e348..b597068103a 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -34,9 +34,14 @@ struct drm_fb_helper;
 
 #include <linux/kgdb.h>
 
+struct drm_fb_offset {
+	int x, y;
+};
+
 struct drm_fb_helper_crtc {
 	struct drm_mode_set mode_set;
 	struct drm_display_mode *desired_mode;
+	int x, y;
 };
 
 struct drm_fb_helper_surface_size {
@@ -72,6 +77,7 @@ struct drm_fb_helper_funcs {
 	bool (*initial_config)(struct drm_fb_helper *fb_helper,
 			       struct drm_fb_helper_crtc **crtcs,
 			       struct drm_display_mode **modes,
+			       struct drm_fb_offset *offsets,
 			       bool *enabled, int width, int height);
 };
 
-- 
cgit v1.2.3-70-g09d2


From a280455fa87053eed59de8464200d03ae4caa8c3 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 27 Nov 2014 14:48:42 -0500
Subject: iov_iter.c: handle ITER_KVEC directly

... without bothering with copy_..._user()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/uio.h |  1 +
 mm/iov_iter.c       | 82 ++++++++++++++++++++++++++++++++++++++++++++---------
 2 files changed, 70 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/uio.h b/include/linux/uio.h
index 9b1581414cd..6e16945ec83 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -31,6 +31,7 @@ struct iov_iter {
 	size_t count;
 	union {
 		const struct iovec *iov;
+		const struct kvec *kvec;
 		const struct bio_vec *bvec;
 	};
 	unsigned long nr_segs;
diff --git a/mm/iov_iter.c b/mm/iov_iter.c
index 666654498cc..1618e378277 100644
--- a/mm/iov_iter.c
+++ b/mm/iov_iter.c
@@ -32,6 +32,29 @@
 	n = wanted - n;					\
 }
 
+#define iterate_kvec(i, n, __v, __p, skip, STEP) {	\
+	size_t wanted = n;				\
+	__p = i->kvec;					\
+	__v.iov_len = min(n, __p->iov_len - skip);	\
+	if (likely(__v.iov_len)) {			\
+		__v.iov_base = __p->iov_base + skip;	\
+		(void)(STEP);				\
+		skip += __v.iov_len;			\
+		n -= __v.iov_len;			\
+	}						\
+	while (unlikely(n)) {				\
+		__p++;					\
+		__v.iov_len = min(n, __p->iov_len);	\
+		if (unlikely(!__v.iov_len))		\
+			continue;			\
+		__v.iov_base = __p->iov_base;		\
+		(void)(STEP);				\
+		skip = __v.iov_len;			\
+		n -= __v.iov_len;			\
+	}						\
+	n = wanted;					\
+}
+
 #define iterate_bvec(i, n, __v, __p, skip, STEP) {	\
 	size_t wanted = n;				\
 	__p = i->bvec;					\
@@ -57,12 +80,16 @@
 	n = wanted;					\
 }
 
-#define iterate_all_kinds(i, n, v, I, B) {			\
+#define iterate_all_kinds(i, n, v, I, B, K) {			\
 	size_t skip = i->iov_offset;				\
 	if (unlikely(i->type & ITER_BVEC)) {			\
 		const struct bio_vec *bvec;			\
 		struct bio_vec v;				\
 		iterate_bvec(i, n, v, bvec, skip, (B))		\
+	} else if (unlikely(i->type & ITER_KVEC)) {		\
+		const struct kvec *kvec;			\
+		struct kvec v;					\
+		iterate_kvec(i, n, v, kvec, skip, (K))		\
 	} else {						\
 		const struct iovec *iov;			\
 		struct iovec v;					\
@@ -70,7 +97,7 @@
 	}							\
 }
 
-#define iterate_and_advance(i, n, v, I, B) {			\
+#define iterate_and_advance(i, n, v, I, B, K) {			\
 	size_t skip = i->iov_offset;				\
 	if (unlikely(i->type & ITER_BVEC)) {			\
 		const struct bio_vec *bvec;			\
@@ -82,6 +109,16 @@
 		}						\
 		i->nr_segs -= bvec - i->bvec;			\
 		i->bvec = bvec;					\
+	} else if (unlikely(i->type & ITER_KVEC)) {		\
+		const struct kvec *kvec;			\
+		struct kvec v;					\
+		iterate_kvec(i, n, v, kvec, skip, (K))		\
+		if (skip == kvec->iov_len) {			\
+			kvec++;					\
+			skip = 0;				\
+		}						\
+		i->nr_segs -= kvec - i->kvec;			\
+		i->kvec = kvec;					\
 	} else {						\
 		const struct iovec *iov;			\
 		struct iovec v;					\
@@ -270,7 +307,7 @@ done:
  */
 int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
 {
-	if (!(i->type & ITER_BVEC)) {
+	if (!(i->type & (ITER_BVEC|ITER_KVEC))) {
 		char __user *buf = i->iov->iov_base + i->iov_offset;
 		bytes = min(bytes, i->iov->iov_len - i->iov_offset);
 		return fault_in_pages_readable(buf, bytes);
@@ -284,10 +321,14 @@ void iov_iter_init(struct iov_iter *i, int direction,
 			size_t count)
 {
 	/* It will get better.  Eventually... */
-	if (segment_eq(get_fs(), KERNEL_DS))
+	if (segment_eq(get_fs(), KERNEL_DS)) {
 		direction |= ITER_KVEC;
-	i->type = direction;
-	i->iov = iov;
+		i->type = direction;
+		i->kvec = (struct kvec *)iov;
+	} else {
+		i->type = direction;
+		i->iov = iov;
+	}
 	i->nr_segs = nr_segs;
 	i->iov_offset = 0;
 	i->count = count;
@@ -328,7 +369,8 @@ size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i)
 		__copy_to_user(v.iov_base, (from += v.iov_len) - v.iov_len,
 			       v.iov_len),
 		memcpy_to_page(v.bv_page, v.bv_offset,
-			       (from += v.bv_len) - v.bv_len, v.bv_len)
+			       (from += v.bv_len) - v.bv_len, v.bv_len),
+		memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len)
 	)
 
 	return bytes;
@@ -348,7 +390,8 @@ size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 		__copy_from_user((to += v.iov_len) - v.iov_len, v.iov_base,
 				 v.iov_len),
 		memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page,
-				 v.bv_offset, v.bv_len)
+				 v.bv_offset, v.bv_len),
+		memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)
 	)
 
 	return bytes;
@@ -371,7 +414,7 @@ EXPORT_SYMBOL(copy_page_to_iter);
 size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i)
 {
-	if (i->type & ITER_BVEC) {
+	if (i->type & (ITER_BVEC|ITER_KVEC)) {
 		void *kaddr = kmap_atomic(page);
 		size_t wanted = copy_from_iter(kaddr + offset, bytes, i);
 		kunmap_atomic(kaddr);
@@ -391,7 +434,8 @@ size_t iov_iter_zero(size_t bytes, struct iov_iter *i)
 
 	iterate_and_advance(i, bytes, v,
 		__clear_user(v.iov_base, v.iov_len),
-		memzero_page(v.bv_page, v.bv_offset, v.bv_len)
+		memzero_page(v.bv_page, v.bv_offset, v.bv_len),
+		memset(v.iov_base, 0, v.iov_len)
 	)
 
 	return bytes;
@@ -406,7 +450,8 @@ size_t iov_iter_copy_from_user_atomic(struct page *page,
 		__copy_from_user_inatomic((p += v.iov_len) - v.iov_len,
 					  v.iov_base, v.iov_len),
 		memcpy_from_page((p += v.bv_len) - v.bv_len, v.bv_page,
-				 v.bv_offset, v.bv_len)
+				 v.bv_offset, v.bv_len),
+		memcpy((p += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)
 	)
 	kunmap_atomic(kaddr);
 	return bytes;
@@ -415,7 +460,7 @@ EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
 
 void iov_iter_advance(struct iov_iter *i, size_t size)
 {
-	iterate_and_advance(i, size, v, 0, 0)
+	iterate_and_advance(i, size, v, 0, 0, 0)
 }
 EXPORT_SYMBOL(iov_iter_advance);
 
@@ -443,7 +488,8 @@ unsigned long iov_iter_alignment(const struct iov_iter *i)
 
 	iterate_all_kinds(i, size, v,
 		(res |= (unsigned long)v.iov_base | v.iov_len, 0),
-		res |= v.bv_offset | v.bv_len
+		res |= v.bv_offset | v.bv_len,
+		res |= (unsigned long)v.iov_base | v.iov_len
 	)
 	return res;
 }
@@ -478,6 +524,8 @@ ssize_t iov_iter_get_pages(struct iov_iter *i,
 		*start = v.bv_offset;
 		get_page(*pages = v.bv_page);
 		return v.bv_len;
+	}),({
+		return -EFAULT;
 	})
 	)
 	return 0;
@@ -530,6 +578,8 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
 			return -ENOMEM;
 		get_page(*p = v.bv_page);
 		return v.bv_len;
+	}),({
+		return -EFAULT;
 	})
 	)
 	return 0;
@@ -554,6 +604,12 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages)
 		npages++;
 		if (npages >= maxpages)
 			return maxpages;
+	}),({
+		unsigned long p = (unsigned long)v.iov_base;
+		npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE)
+			- p / PAGE_SIZE;
+		if (npages >= maxpages)
+			return maxpages;
 	})
 	)
 	return npages;
-- 
cgit v1.2.3-70-g09d2


From 184a4bf623fa587067851d25435fcb2f41de445b Mon Sep 17 00:00:00 2001
From: Lukasz Majewski <l.majewski@samsung.com>
Date: Mon, 8 Dec 2014 18:04:21 +0100
Subject: thermal: of: Extend current of-thermal.c code to allow setting
 emulated temp

Before this change it was only possible to set get_temp() and get_trend()
methods to be used in the common code handling passing parameters via
device tree to "cpu-thermal" CPU thermal zone device.

Now it is possible to also set emulated value of temperature for debug
purposes.

Signed-off-by: Lukasz Majewski <l.majewski@samsung.com>
Acked-by: Eduardo Valentin <edubezval@gmail.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/of-thermal.c | 24 ++++++++++++++++++++++++
 include/linux/thermal.h      |  3 +++
 2 files changed, 27 insertions(+)

(limited to 'include')

diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
index e062bf59ab6..e145b66df44 100644
--- a/drivers/thermal/of-thermal.c
+++ b/drivers/thermal/of-thermal.c
@@ -161,6 +161,28 @@ of_thermal_get_trip_points(struct thermal_zone_device *tz)
 }
 EXPORT_SYMBOL_GPL(of_thermal_get_trip_points);
 
+/**
+ * of_thermal_set_emul_temp - function to set emulated temperature
+ *
+ * @tz:	pointer to a thermal zone
+ * @temp:	temperature to set
+ *
+ * This function gives the ability to set emulated value of temperature,
+ * which is handy for debugging
+ *
+ * Return: zero on success, error code otherwise
+ */
+static int of_thermal_set_emul_temp(struct thermal_zone_device *tz,
+				    unsigned long temp)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	if (!data->ops || !data->ops->set_emul_temp)
+		return -EINVAL;
+
+	return data->ops->set_emul_temp(data->sensor_data, temp);
+}
+
 static int of_thermal_get_trend(struct thermal_zone_device *tz, int trip,
 				enum thermal_trend *trend)
 {
@@ -392,6 +414,7 @@ thermal_zone_of_add_sensor(struct device_node *zone,
 
 	tzd->ops->get_temp = of_thermal_get_temp;
 	tzd->ops->get_trend = of_thermal_get_trend;
+	tzd->ops->set_emul_temp = of_thermal_set_emul_temp;
 	mutex_unlock(&tzd->lock);
 
 	return tzd;
@@ -520,6 +543,7 @@ void thermal_zone_of_sensor_unregister(struct device *dev,
 	mutex_lock(&tzd->lock);
 	tzd->ops->get_temp = NULL;
 	tzd->ops->get_trend = NULL;
+	tzd->ops->set_emul_temp = NULL;
 
 	tz->ops = NULL;
 	tz->sensor_data = NULL;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index b8d91efa854..99be7fc79c3 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -297,10 +297,13 @@ struct thermal_genl_event {
  *
  * Optional:
  * @get_trend: a pointer to a function that reads the sensor temperature trend.
+ * @set_emul_temp: a pointer to a function that sets sensor emulated
+ *		   temperature.
  */
 struct thermal_zone_of_device_ops {
 	int (*get_temp)(void *, long *);
 	int (*get_trend)(void *, long *);
+	int (*set_emul_temp)(void *, unsigned long);
 };
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 829ae9d611651467fe6cd7be834bd33ca6b28dfe Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sun, 30 Nov 2014 22:22:34 -0500
Subject: net-timestamp: allow reading recv cmsg on errqueue with origin tstamp

Allow reading of timestamps and cmsg at the same time on all relevant
socket families. One use is to correlate timestamps with egress
device, by asking for cmsg IP_PKTINFO.

on AF_INET sockets, call the relevant function (ip_cmsg_recv). To
avoid changing legacy expectations, only do so if the caller sets a
new timestamping flag SOF_TIMESTAMPING_OPT_CMSG.

on AF_INET6 sockets, IPV6_PKTINFO and all other recv cmsg are already
returned for all origins. only change is to set ifindex, which is
not initialized for all error origins.

In both cases, only generate the pktinfo message if an ifindex is
known. This is not the case for ACK timestamps.

The difference between the protocol families is probably a historical
accident as a result of the different conditions for generating cmsg
in the relevant ip(v6)_recv_error function:

ipv4:        if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) {
ipv6:        if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {

At one time, this was the same test bar for the ICMP/ICMP6
distinction. This is no longer true.

Signed-off-by: Willem de Bruijn <willemb@google.com>

----

Changes
  v1 -> v2
    large rewrite
    - integrate with existing pktinfo cmsg generation code
    - on ipv4: only send with new flag, to maintain legacy behavior
    - on ipv6: send at most a single pktinfo cmsg
    - on ipv6: initialize fields if not yet initialized

The recv cmsg interfaces are also relevant to the discussion of
whether looping packet headers is problematic. For v6, cmsgs that
identify many headers are already returned. This patch expands
that to v4. If it sounds reasonable, I will follow with patches

1. request timestamps without payload with SOF_TIMESTAMPING_OPT_TSONLY
   (http://patchwork.ozlabs.org/patch/366967/)
2. sysctl to conditionally drop all timestamps that have payload or
   cmsg from users without CAP_NET_RAW.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/timestamping.txt | 12 +++++++++++-
 include/uapi/linux/net_tstamp.h           |  3 ++-
 net/ipv4/ip_sockglue.c                    | 22 ++++++++++++++++++++--
 net/ipv6/datagram.c                       | 21 +++++++++++++++++++--
 4 files changed, 52 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt
index 1d6d02d6ba5..b08e27261ff 100644
--- a/Documentation/networking/timestamping.txt
+++ b/Documentation/networking/timestamping.txt
@@ -122,7 +122,7 @@ SOF_TIMESTAMPING_RAW_HARDWARE:
 
 1.3.3 Timestamp Options
 
-The interface supports one option
+The interface supports the options
 
 SOF_TIMESTAMPING_OPT_ID:
 
@@ -145,6 +145,16 @@ SOF_TIMESTAMPING_OPT_ID:
   stream sockets, it increments with every byte.
 
 
+SOF_TIMESTAMPING_OPT_CMSG:
+
+  Support recv() cmsg for all timestamped packets. Control messages
+  are already supported unconditionally on all packets with receive
+  timestamps and on IPv6 packets with transmit timestamp. This option
+  extends them to IPv4 packets with transmit timestamp. One use case
+  is to correlate packets with their egress device, by enabling socket
+  option IP_PKTINFO simultaneously.
+
+
 1.4 Bytestream Timestamps
 
 The SO_TIMESTAMPING interface supports timestamping of bytes in a
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index ff354021bb6..edbc888ceb5 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -23,8 +23,9 @@ enum {
 	SOF_TIMESTAMPING_OPT_ID = (1<<7),
 	SOF_TIMESTAMPING_TX_SCHED = (1<<8),
 	SOF_TIMESTAMPING_TX_ACK = (1<<9),
+	SOF_TIMESTAMPING_OPT_CMSG = (1<<10),
 
-	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_TX_ACK,
+	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_CMSG,
 	SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) |
 				 SOF_TIMESTAMPING_LAST
 };
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 59eba6c7a51..640f26c6a9f 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -399,6 +399,22 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
 		kfree_skb(skb);
 }
 
+static bool ipv4_pktinfo_prepare_errqueue(const struct sock *sk,
+					  const struct sk_buff *skb,
+					  int ee_origin)
+{
+	struct in_pktinfo *info = PKTINFO_SKB_CB(skb);
+
+	if ((ee_origin != SO_EE_ORIGIN_TIMESTAMPING) ||
+	    (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
+	    (!skb->dev))
+		return false;
+
+	info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
+	info->ipi_ifindex = skb->dev->ifindex;
+	return true;
+}
+
 /*
  *	Handle MSG_ERRQUEUE
  */
@@ -446,7 +462,9 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
 	sin = &errhdr.offender;
 	sin->sin_family = AF_UNSPEC;
-	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) {
+
+	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+	    ipv4_pktinfo_prepare_errqueue(sk, skb, serr->ee.ee_origin)) {
 		struct inet_sock *inet = inet_sk(sk);
 
 		sin->sin_family = AF_INET;
@@ -1051,7 +1069,7 @@ e_inval:
 }
 
 /**
- * ipv4_pktinfo_prepare - transfert some info from rtable to skb
+ * ipv4_pktinfo_prepare - transfer some info from rtable to skb
  * @sk: socket
  * @skb: buffer
  *
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index cc1139687fd..2464a00e36a 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -325,6 +325,16 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
 	kfree_skb(skb);
 }
 
+static void ip6_datagram_prepare_pktinfo_errqueue(struct sk_buff *skb)
+{
+	int ifindex = skb->dev ? skb->dev->ifindex : -1;
+
+	if (skb->protocol == htons(ETH_P_IPV6))
+		IP6CB(skb)->iif = ifindex;
+	else
+		PKTINFO_SKB_CB(skb)->ipi_ifindex = ifindex;
+}
+
 /*
  *	Handle MSG_ERRQUEUE
  */
@@ -388,8 +398,12 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
 		sin->sin6_port = 0;
-		if (np->rxopt.all)
+		if (np->rxopt.all) {
+			if (serr->ee.ee_origin != SO_EE_ORIGIN_ICMP &&
+			    serr->ee.ee_origin != SO_EE_ORIGIN_ICMP6)
+				ip6_datagram_prepare_pktinfo_errqueue(skb);
 			ip6_datagram_recv_common_ctl(sk, msg, skb);
+		}
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			sin->sin6_addr = ipv6_hdr(skb)->saddr;
 			if (np->rxopt.all)
@@ -491,7 +505,10 @@ void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg,
 			ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr,
 					       &src_info.ipi6_addr);
 		}
-		put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
+
+		if (src_info.ipi6_ifindex >= 0)
+			put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO,
+				 sizeof(src_info), &src_info);
 	}
 }
 
-- 
cgit v1.2.3-70-g09d2


From c3582a2c4d0baf1fa3955c8b3d3d61308df474c7 Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Mon, 1 Dec 2014 13:28:39 -0800
Subject: hyperv: Add support for vNIC hot removal

This patch adds proper handling of the vNIC hot removal event, which includes
a rescind-channel-offer message from the host side that triggers vNIC close and
removal. In this case, the notices to the host during close and removal is not
necessary because the channel is rescinded. This patch blocks these unnecessary
messages, and lets vNIC removal process complete normally.

Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/hv/channel_mgmt.c         | 2 ++
 drivers/net/hyperv/netvsc.c       | 3 +++
 drivers/net/hyperv/rndis_filter.c | 3 +++
 include/linux/hyperv.h            | 2 ++
 4 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index a2d1a9612c8..191a6a3ae6c 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -517,6 +517,8 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 		/* Just return here, no channel found */
 		return;
 
+	channel->rescind = true;
+
 	/* work is initialized for vmbus_process_rescind_offer() from
 	 * vmbus_process_offer() where the channel got created */
 	queue_work(channel->controlwq, &channel->work);
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 6fc834e4306..dd867e6cabd 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -764,6 +764,9 @@ int netvsc_send(struct hv_device *device,
 		out_channel = device->channel;
 	packet->channel = out_channel;
 
+	if (out_channel->rescind)
+		return -ENODEV;
+
 	if (packet->page_buf_cnt) {
 		ret = vmbus_sendpacket_pagebuffer(out_channel,
 						  packet->page_buf,
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 7b2c5d1e9ba..ec0c40a8f65 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -958,6 +958,9 @@ static int rndis_filter_close_device(struct rndis_device *dev)
 		return 0;
 
 	ret = rndis_filter_set_packet_filter(dev, 0);
+	if (ret == -ENODEV)
+		ret = 0;
+
 	if (ret == 0)
 		dev->state = RNDIS_DEV_INITIALIZED;
 
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 08cfaff8a07..476c685ca6f 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -650,6 +650,8 @@ struct vmbus_channel {
 	u8 monitor_grp;
 	u8 monitor_bit;
 
+	bool rescind; /* got rescind msg */
+
 	u32 ringbuffer_gpadlhandle;
 
 	/* Allocated memory for ring buffer */
-- 
cgit v1.2.3-70-g09d2


From a604ec7e9ffea22fed84db8306585090e7a6e85d Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 24 Nov 2014 01:08:00 -0500
Subject: csum_and_copy_..._iter()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/uio.h |  2 ++
 mm/iov_iter.c       | 89 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 91 insertions(+)

(limited to 'include')

diff --git a/include/linux/uio.h b/include/linux/uio.h
index 6e16945ec83..28ed2d904de 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -124,6 +124,8 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
 {
 	i->count = count;
 }
+size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
+size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 
 int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len);
 int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len);
diff --git a/mm/iov_iter.c b/mm/iov_iter.c
index 1618e378277..1d2cdeb57c5 100644
--- a/mm/iov_iter.c
+++ b/mm/iov_iter.c
@@ -3,6 +3,7 @@
 #include <linux/pagemap.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <net/checksum.h>
 
 #define iterate_iovec(i, n, __v, __p, skip, STEP) {	\
 	size_t left;					\
@@ -586,6 +587,94 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
 }
 EXPORT_SYMBOL(iov_iter_get_pages_alloc);
 
+size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum,
+			       struct iov_iter *i)
+{
+	char *to = addr;
+	__wsum sum, next;
+	size_t off = 0;
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	sum = *csum;
+	iterate_and_advance(i, bytes, v, ({
+		int err = 0;
+		next = csum_and_copy_from_user(v.iov_base, 
+					       (to += v.iov_len) - v.iov_len,
+					       v.iov_len, 0, &err);
+		if (!err) {
+			sum = csum_block_add(sum, next, off);
+			off += v.iov_len;
+		}
+		err ? v.iov_len : 0;
+	}), ({
+		char *p = kmap_atomic(v.bv_page);
+		next = csum_partial_copy_nocheck(p + v.bv_offset,
+						 (to += v.bv_len) - v.bv_len,
+						 v.bv_len, 0);
+		kunmap_atomic(p);
+		sum = csum_block_add(sum, next, off);
+		off += v.bv_len;
+	}),({
+		next = csum_partial_copy_nocheck(v.iov_base,
+						 (to += v.iov_len) - v.iov_len,
+						 v.iov_len, 0);
+		sum = csum_block_add(sum, next, off);
+		off += v.iov_len;
+	})
+	)
+	*csum = sum;
+	return bytes;
+}
+EXPORT_SYMBOL(csum_and_copy_from_iter);
+
+size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum,
+			     struct iov_iter *i)
+{
+	char *from = addr;
+	__wsum sum, next;
+	size_t off = 0;
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	sum = *csum;
+	iterate_and_advance(i, bytes, v, ({
+		int err = 0;
+		next = csum_and_copy_to_user((from += v.iov_len) - v.iov_len,
+					     v.iov_base, 
+					     v.iov_len, 0, &err);
+		if (!err) {
+			sum = csum_block_add(sum, next, off);
+			off += v.iov_len;
+		}
+		err ? v.iov_len : 0;
+	}), ({
+		char *p = kmap_atomic(v.bv_page);
+		next = csum_partial_copy_nocheck((from += v.bv_len) - v.bv_len,
+						 p + v.bv_offset,
+						 v.bv_len, 0);
+		kunmap_atomic(p);
+		sum = csum_block_add(sum, next, off);
+		off += v.bv_len;
+	}),({
+		next = csum_partial_copy_nocheck((from += v.iov_len) - v.iov_len,
+						 v.iov_base,
+						 v.iov_len, 0);
+		sum = csum_block_add(sum, next, off);
+		off += v.iov_len;
+	})
+	)
+	*csum = sum;
+	return bytes;
+}
+EXPORT_SYMBOL(csum_and_copy_to_iter);
+
 int iov_iter_npages(const struct iov_iter *i, int maxpages)
 {
 	size_t size = i->count;
-- 
cgit v1.2.3-70-g09d2


From abb78f875f3fcedb88d85eef9f7be7aa474c6727 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 24 Nov 2014 14:46:11 -0500
Subject: new helper: iov_iter_kvec()

initialization of kvec-backed iov_iter

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/uio.h |  2 ++
 mm/iov_iter.c       | 13 +++++++++++++
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/linux/uio.h b/include/linux/uio.h
index 28ed2d904de..c567655b959 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -87,6 +87,8 @@ size_t iov_iter_zero(size_t bytes, struct iov_iter *);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
 void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov,
 			unsigned long nr_segs, size_t count);
+void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *iov,
+			unsigned long nr_segs, size_t count);
 ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
 			size_t maxsize, unsigned maxpages, size_t *start);
 ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,
diff --git a/mm/iov_iter.c b/mm/iov_iter.c
index 1d2cdeb57c5..88c052e63a1 100644
--- a/mm/iov_iter.c
+++ b/mm/iov_iter.c
@@ -479,6 +479,19 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i)
 }
 EXPORT_SYMBOL(iov_iter_single_seg_count);
 
+void iov_iter_kvec(struct iov_iter *i, int direction,
+			const struct kvec *iov, unsigned long nr_segs,
+			size_t count)
+{
+	BUG_ON(!(direction & ITER_KVEC));
+	i->type = direction;
+	i->kvec = (struct kvec *)iov;
+	i->nr_segs = nr_segs;
+	i->iov_offset = 0;
+	i->count = count;
+}
+EXPORT_SYMBOL(iov_iter_kvec);
+
 unsigned long iov_iter_alignment(const struct iov_iter *i)
 {
 	unsigned long res = 0;
-- 
cgit v1.2.3-70-g09d2


From aa583096d9767892983332e7c1a984bd17e3cd39 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 27 Nov 2014 20:27:08 -0500
Subject: copy_from_iter_nocache()

BTW, do we want memcpy_nocache()?

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/uio.h |  1 +
 mm/iov_iter.c       | 21 +++++++++++++++++++++
 2 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/include/linux/uio.h b/include/linux/uio.h
index c567655b959..bd8569a14c4 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -83,6 +83,7 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
 size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i);
 size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
+size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i);
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
 void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov,
diff --git a/mm/iov_iter.c b/mm/iov_iter.c
index 88c052e63a1..a1599ca4ab0 100644
--- a/mm/iov_iter.c
+++ b/mm/iov_iter.c
@@ -399,6 +399,27 @@ size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 }
 EXPORT_SYMBOL(copy_from_iter);
 
+size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
+{
+	char *to = addr;
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	iterate_and_advance(i, bytes, v,
+		__copy_from_user_nocache((to += v.iov_len) - v.iov_len,
+					 v.iov_base, v.iov_len),
+		memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page,
+				 v.bv_offset, v.bv_len),
+		memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)
+	)
+
+	return bytes;
+}
+EXPORT_SYMBOL(copy_from_iter_nocache);
+
 size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i)
 {
-- 
cgit v1.2.3-70-g09d2


From b0ba512e25d729a43858ad1f6cb8b94dbb95dbeb Mon Sep 17 00:00:00 2001
From: Petri Gynther <pgynther@google.com>
Date: Mon, 1 Dec 2014 16:18:08 -0800
Subject: net: bcmgenet: enable driver to work without a device tree

Modify bcmgenet driver so that it can be used on Broadcom 7xxx
MIPS-based STB platforms without a device tree.

Signed-off-by: Petri Gynther <pgynther@google.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/Kconfig          |   1 -
 drivers/net/ethernet/broadcom/genet/bcmgenet.c |  31 ++++--
 drivers/net/ethernet/broadcom/genet/bcmmii.c   | 126 ++++++++++++++++++++-----
 include/linux/platform_data/bcmgenet.h         |  18 ++++
 4 files changed, 143 insertions(+), 33 deletions(-)
 create mode 100644 include/linux/platform_data/bcmgenet.h

(limited to 'include')

diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index c3e260c2173..888247ad906 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -62,7 +62,6 @@ config BCM63XX_ENET
 
 config BCMGENET
 	tristate "Broadcom GENET internal MAC support"
-	depends on OF
 	select MII
 	select PHYLIB
 	select FIXED_PHY if BCMGENET=y
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index f2fadb053d5..adfef5ca0d5 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -42,6 +42,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/phy.h>
+#include <linux/platform_data/bcmgenet.h>
 
 #include <asm/unaligned.h>
 
@@ -2586,8 +2587,9 @@ static const struct of_device_id bcmgenet_match[] = {
 
 static int bcmgenet_probe(struct platform_device *pdev)
 {
+	struct bcmgenet_platform_data *pd = pdev->dev.platform_data;
 	struct device_node *dn = pdev->dev.of_node;
-	const struct of_device_id *of_id;
+	const struct of_device_id *of_id = NULL;
 	struct bcmgenet_priv *priv;
 	struct net_device *dev;
 	const void *macaddr;
@@ -2601,9 +2603,11 @@ static int bcmgenet_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	of_id = of_match_node(bcmgenet_match, dn);
-	if (!of_id)
-		return -EINVAL;
+	if (dn) {
+		of_id = of_match_node(bcmgenet_match, dn);
+		if (!of_id)
+			return -EINVAL;
+	}
 
 	priv = netdev_priv(dev);
 	priv->irq0 = platform_get_irq(pdev, 0);
@@ -2615,11 +2619,15 @@ static int bcmgenet_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	macaddr = of_get_mac_address(dn);
-	if (!macaddr) {
-		dev_err(&pdev->dev, "can't find MAC address\n");
-		err = -EINVAL;
-		goto err;
+	if (dn) {
+		macaddr = of_get_mac_address(dn);
+		if (!macaddr) {
+			dev_err(&pdev->dev, "can't find MAC address\n");
+			err = -EINVAL;
+			goto err;
+		}
+	} else {
+		macaddr = pd->mac_address;
 	}
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -2659,7 +2667,10 @@ static int bcmgenet_probe(struct platform_device *pdev)
 
 	priv->dev = dev;
 	priv->pdev = pdev;
-	priv->version = (enum bcmgenet_version)of_id->data;
+	if (of_id)
+		priv->version = (enum bcmgenet_version)of_id->data;
+	else
+		priv->version = pd->genet_version;
 
 	priv->clk = devm_clk_get(&priv->pdev->dev, "enet");
 	if (IS_ERR(priv->clk))
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 933cd7e7cd3..446889cc3c6 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -23,6 +23,7 @@
 #include <linux/of.h>
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
+#include <linux/platform_data/bcmgenet.h>
 
 #include "bcmgenet.h"
 
@@ -312,22 +313,6 @@ static int bcmgenet_mii_probe(struct net_device *dev)
 	u32 phy_flags;
 	int ret;
 
-	if (priv->phydev) {
-		pr_info("PHY already attached\n");
-		return 0;
-	}
-
-	/* In the case of a fixed PHY, the DT node associated
-	 * to the PHY is the Ethernet MAC DT node.
-	 */
-	if (!priv->phy_dn && of_phy_is_fixed_link(dn)) {
-		ret = of_phy_register_fixed_link(dn);
-		if (ret)
-			return ret;
-
-		priv->phy_dn = of_node_get(dn);
-	}
-
 	/* Communicate the integrated PHY revision */
 	phy_flags = priv->gphy_rev;
 
@@ -337,11 +322,39 @@ static int bcmgenet_mii_probe(struct net_device *dev)
 	priv->old_duplex = -1;
 	priv->old_pause = -1;
 
-	phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup,
-				phy_flags, priv->phy_interface);
-	if (!phydev) {
-		pr_err("could not attach to PHY\n");
-		return -ENODEV;
+	if (dn) {
+		if (priv->phydev) {
+			pr_info("PHY already attached\n");
+			return 0;
+		}
+
+		/* In the case of a fixed PHY, the DT node associated
+		 * to the PHY is the Ethernet MAC DT node.
+		 */
+		if (!priv->phy_dn && of_phy_is_fixed_link(dn)) {
+			ret = of_phy_register_fixed_link(dn);
+			if (ret)
+				return ret;
+
+			priv->phy_dn = of_node_get(dn);
+		}
+
+		phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup,
+					phy_flags, priv->phy_interface);
+		if (!phydev) {
+			pr_err("could not attach to PHY\n");
+			return -ENODEV;
+		}
+	} else {
+		phydev = priv->phydev;
+		phydev->dev_flags = phy_flags;
+
+		ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup,
+					 priv->phy_interface);
+		if (ret) {
+			pr_err("could not attach to PHY\n");
+			return -ENODEV;
+		}
 	}
 
 	priv->phydev = phydev;
@@ -438,6 +451,75 @@ static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv)
 	return 0;
 }
 
+static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
+{
+	struct device *kdev = &priv->pdev->dev;
+	struct bcmgenet_platform_data *pd = kdev->platform_data;
+	struct mii_bus *mdio = priv->mii_bus;
+	struct phy_device *phydev;
+	int ret;
+
+	if (pd->phy_interface != PHY_INTERFACE_MODE_MOCA && pd->mdio_enabled) {
+		/*
+		 * Internal or external PHY with MDIO access
+		 */
+		if (pd->phy_address >= 0 && pd->phy_address < PHY_MAX_ADDR)
+			mdio->phy_mask = ~(1 << pd->phy_address);
+		else
+			mdio->phy_mask = 0;
+
+		ret = mdiobus_register(mdio);
+		if (ret) {
+			dev_err(kdev, "failed to register MDIO bus\n");
+			return ret;
+		}
+
+		if (pd->phy_address >= 0 && pd->phy_address < PHY_MAX_ADDR)
+			phydev = mdio->phy_map[pd->phy_address];
+		else
+			phydev = phy_find_first(mdio);
+
+		if (!phydev) {
+			dev_err(kdev, "failed to register PHY device\n");
+			mdiobus_unregister(mdio);
+			return -ENODEV;
+		}
+	} else {
+		/*
+		 * MoCA port or no MDIO access.
+		 * Use fixed PHY to represent the link layer.
+		 */
+		struct fixed_phy_status fphy_status = {
+			.link = 1,
+			.speed = pd->phy_speed,
+			.duplex = pd->phy_duplex,
+			.pause = 0,
+			.asym_pause = 0,
+		};
+
+		phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
+		if (!phydev || IS_ERR(phydev)) {
+			dev_err(kdev, "failed to register fixed PHY device\n");
+			return -ENODEV;
+		}
+	}
+
+	priv->phydev = phydev;
+	priv->phy_interface = pd->phy_interface;
+
+	return 0;
+}
+
+static int bcmgenet_mii_bus_init(struct bcmgenet_priv *priv)
+{
+	struct device_node *dn = priv->pdev->dev.of_node;
+
+	if (dn)
+		return bcmgenet_mii_of_init(priv);
+	else
+		return bcmgenet_mii_pd_init(priv);
+}
+
 int bcmgenet_mii_init(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
@@ -447,7 +529,7 @@ int bcmgenet_mii_init(struct net_device *dev)
 	if (ret)
 		return ret;
 
-	ret = bcmgenet_mii_of_init(priv);
+	ret = bcmgenet_mii_bus_init(priv);
 	if (ret)
 		goto out_free;
 
diff --git a/include/linux/platform_data/bcmgenet.h b/include/linux/platform_data/bcmgenet.h
new file mode 100644
index 00000000000..26af5432195
--- /dev/null
+++ b/include/linux/platform_data/bcmgenet.h
@@ -0,0 +1,18 @@
+#ifndef __LINUX_PLATFORM_DATA_BCMGENET_H__
+#define __LINUX_PLATFORM_DATA_BCMGENET_H__
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/phy.h>
+
+struct bcmgenet_platform_data {
+	bool		mdio_enabled;
+	phy_interface_t	phy_interface;
+	int		phy_address;
+	int		phy_speed;
+	int		phy_duplex;
+	u8		mac_address[ETH_ALEN];
+	int		genet_version;
+};
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From 97ede29e80eead50d8bd533cf163401b88c027be Mon Sep 17 00:00:00 2001
From: Ying Xue <ying.xue@windriver.com>
Date: Tue, 2 Dec 2014 15:00:30 +0800
Subject: tipc: convert name table read-write lock to RCU

Convert tipc name table read-write lock to RCU. After this change,
a new spin lock is used to protect name table on write side while
RCU is applied on read side.

Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Tested-by: Erik Hugne <erik.hugne@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rculist.h |  9 +++++
 net/tipc/name_distr.c   | 28 ++++++++--------
 net/tipc/name_table.c   | 87 ++++++++++++++++++++++++-------------------------
 net/tipc/name_table.h   |  4 ++-
 4 files changed, 69 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 372ad5e0dcb..aa79b3c24f6 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -542,6 +542,15 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
 	     pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\
 			typeof(*(pos)), member))
 
+/**
+ * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point
+ * @pos:	the type * to use as a loop cursor.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_from_rcu(pos, member)			\
+	for (; pos;							\
+	     pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\
+			typeof(*(pos)), member))
 
 #endif	/* __KERNEL__ */
 #endif
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index ed00929f16c..ba6083dca95 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -113,8 +113,8 @@ struct sk_buff *tipc_named_publish(struct publication *publ)
 	struct sk_buff *buf;
 	struct distr_item *item;
 
-	list_add_tail(&publ->local_list,
-		      &tipc_nametbl->publ_list[publ->scope]);
+	list_add_tail_rcu(&publ->local_list,
+			  &tipc_nametbl->publ_list[publ->scope]);
 
 	if (publ->scope == TIPC_NODE_SCOPE)
 		return NULL;
@@ -208,12 +208,12 @@ void tipc_named_node_up(u32 dnode)
 
 	__skb_queue_head_init(&head);
 
-	read_lock_bh(&tipc_nametbl_lock);
+	rcu_read_lock();
 	named_distribute(&head, dnode,
 			 &tipc_nametbl->publ_list[TIPC_CLUSTER_SCOPE]);
 	named_distribute(&head, dnode,
 			 &tipc_nametbl->publ_list[TIPC_ZONE_SCOPE]);
-	read_unlock_bh(&tipc_nametbl_lock);
+	rcu_read_unlock();
 
 	tipc_link_xmit(&head, dnode, dnode);
 }
@@ -260,12 +260,12 @@ static void tipc_publ_purge(struct publication *publ, u32 addr)
 {
 	struct publication *p;
 
-	write_lock_bh(&tipc_nametbl_lock);
+	spin_lock_bh(&tipc_nametbl_lock);
 	p = tipc_nametbl_remove_publ(publ->type, publ->lower,
 				     publ->node, publ->ref, publ->key);
 	if (p)
 		tipc_publ_unsubscribe(p, addr);
-	write_unlock_bh(&tipc_nametbl_lock);
+	spin_unlock_bh(&tipc_nametbl_lock);
 
 	if (p != publ) {
 		pr_err("Unable to remove publication from failed node\n"
@@ -274,7 +274,7 @@ static void tipc_publ_purge(struct publication *publ, u32 addr)
 		       publ->key);
 	}
 
-	kfree(p);
+	kfree_rcu(p, rcu);
 }
 
 void tipc_publ_notify(struct list_head *nsub_list, u32 addr)
@@ -311,7 +311,7 @@ static bool tipc_update_nametbl(struct distr_item *i, u32 node, u32 dtype)
 						ntohl(i->key));
 		if (publ) {
 			tipc_publ_unsubscribe(publ, node);
-			kfree(publ);
+			kfree_rcu(publ, rcu);
 			return true;
 		}
 	} else {
@@ -376,14 +376,14 @@ void tipc_named_rcv(struct sk_buff *buf)
 	u32 count = msg_data_sz(msg) / ITEM_SIZE;
 	u32 node = msg_orignode(msg);
 
-	write_lock_bh(&tipc_nametbl_lock);
+	spin_lock_bh(&tipc_nametbl_lock);
 	while (count--) {
 		if (!tipc_update_nametbl(item, node, msg_type(msg)))
 			tipc_named_add_backlog(item, msg_type(msg), node);
 		item++;
 	}
 	tipc_named_process_backlog();
-	write_unlock_bh(&tipc_nametbl_lock);
+	spin_unlock_bh(&tipc_nametbl_lock);
 	kfree_skb(buf);
 }
 
@@ -399,12 +399,12 @@ void tipc_named_reinit(void)
 	struct publication *publ;
 	int scope;
 
-	write_lock_bh(&tipc_nametbl_lock);
+	spin_lock_bh(&tipc_nametbl_lock);
 
 	for (scope = TIPC_ZONE_SCOPE; scope <= TIPC_NODE_SCOPE; scope++)
-		list_for_each_entry(publ, &tipc_nametbl->publ_list[scope],
-				    local_list)
+		list_for_each_entry_rcu(publ, &tipc_nametbl->publ_list[scope],
+					local_list)
 			publ->node = tipc_own_addr;
 
-	write_unlock_bh(&tipc_nametbl_lock);
+	spin_unlock_bh(&tipc_nametbl_lock);
 }
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 3c2e0c300fe..aafa684c4db 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -92,6 +92,7 @@ struct sub_seq {
  * @ns_list: links to adjacent name sequences in hash chain
  * @subscriptions: list of subscriptions for this 'type'
  * @lock: spinlock controlling access to publication lists of all sub-sequences
+ * @rcu: RCU callback head used for deferred freeing
  */
 struct name_seq {
 	u32 type;
@@ -101,10 +102,11 @@ struct name_seq {
 	struct hlist_node ns_list;
 	struct list_head subscriptions;
 	spinlock_t lock;
+	struct rcu_head rcu;
 };
 
 struct name_table *tipc_nametbl;
-DEFINE_RWLOCK(tipc_nametbl_lock);
+DEFINE_SPINLOCK(tipc_nametbl_lock);
 
 static int hash(int x)
 {
@@ -166,7 +168,7 @@ static struct name_seq *tipc_nameseq_create(u32 type, struct hlist_head *seq_hea
 	nseq->alloc = 1;
 	INIT_HLIST_NODE(&nseq->ns_list);
 	INIT_LIST_HEAD(&nseq->subscriptions);
-	hlist_add_head(&nseq->ns_list, seq_head);
+	hlist_add_head_rcu(&nseq->ns_list, seq_head);
 	return nseq;
 }
 
@@ -451,7 +453,7 @@ static struct name_seq *nametbl_find_seq(u32 type)
 	struct name_seq *ns;
 
 	seq_head = &tipc_nametbl->seq_hlist[hash(type)];
-	hlist_for_each_entry(ns, seq_head, ns_list) {
+	hlist_for_each_entry_rcu(ns, seq_head, ns_list) {
 		if (ns->type == type)
 			return ns;
 	}
@@ -498,10 +500,10 @@ struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower,
 	spin_lock_bh(&seq->lock);
 	publ = tipc_nameseq_remove_publ(seq, lower, node, ref, key);
 	if (!seq->first_free && list_empty(&seq->subscriptions)) {
-		hlist_del_init(&seq->ns_list);
-		spin_unlock_bh(&seq->lock);
+		hlist_del_init_rcu(&seq->ns_list);
 		kfree(seq->sseqs);
-		kfree(seq);
+		spin_unlock_bh(&seq->lock);
+		kfree_rcu(seq, rcu);
 		return publ;
 	}
 	spin_unlock_bh(&seq->lock);
@@ -533,7 +535,7 @@ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode)
 	if (!tipc_in_scope(*destnode, tipc_own_addr))
 		return 0;
 
-	read_lock_bh(&tipc_nametbl_lock);
+	rcu_read_lock();
 	seq = nametbl_find_seq(type);
 	if (unlikely(!seq))
 		goto not_found;
@@ -590,7 +592,7 @@ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode)
 no_match:
 	spin_unlock_bh(&seq->lock);
 not_found:
-	read_unlock_bh(&tipc_nametbl_lock);
+	rcu_read_unlock();
 	*destnode = node;
 	return ref;
 }
@@ -616,7 +618,7 @@ int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit,
 	struct name_info *info;
 	int res = 0;
 
-	read_lock_bh(&tipc_nametbl_lock);
+	rcu_read_lock();
 	seq = nametbl_find_seq(type);
 	if (!seq)
 		goto exit;
@@ -641,7 +643,7 @@ int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit,
 	}
 	spin_unlock_bh(&seq->lock);
 exit:
-	read_unlock_bh(&tipc_nametbl_lock);
+	rcu_read_unlock();
 	return res;
 }
 
@@ -654,11 +656,11 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper,
 	struct publication *publ;
 	struct sk_buff *buf = NULL;
 
-	write_lock_bh(&tipc_nametbl_lock);
+	spin_lock_bh(&tipc_nametbl_lock);
 	if (tipc_nametbl->local_publ_count >= TIPC_MAX_PUBLICATIONS) {
 		pr_warn("Publication failed, local publication limit reached (%u)\n",
 			TIPC_MAX_PUBLICATIONS);
-		write_unlock_bh(&tipc_nametbl_lock);
+		spin_unlock_bh(&tipc_nametbl_lock);
 		return NULL;
 	}
 
@@ -670,7 +672,7 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper,
 		/* Any pending external events? */
 		tipc_named_process_backlog();
 	}
-	write_unlock_bh(&tipc_nametbl_lock);
+	spin_unlock_bh(&tipc_nametbl_lock);
 
 	if (buf)
 		named_cluster_distribute(buf);
@@ -685,7 +687,7 @@ int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key)
 	struct publication *publ;
 	struct sk_buff *skb = NULL;
 
-	write_lock_bh(&tipc_nametbl_lock);
+	spin_lock_bh(&tipc_nametbl_lock);
 	publ = tipc_nametbl_remove_publ(type, lower, tipc_own_addr, ref, key);
 	if (likely(publ)) {
 		tipc_nametbl->local_publ_count--;
@@ -693,13 +695,13 @@ int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key)
 		/* Any pending external events? */
 		tipc_named_process_backlog();
 		list_del_init(&publ->pport_list);
-		kfree(publ);
+		kfree_rcu(publ, rcu);
 	} else {
 		pr_err("Unable to remove local publication\n"
 		       "(type=%u, lower=%u, ref=%u, key=%u)\n",
 		       type, lower, ref, key);
 	}
-	write_unlock_bh(&tipc_nametbl_lock);
+	spin_unlock_bh(&tipc_nametbl_lock);
 
 	if (skb) {
 		named_cluster_distribute(skb);
@@ -717,7 +719,7 @@ void tipc_nametbl_subscribe(struct tipc_subscription *s)
 	int index = hash(type);
 	struct name_seq *seq;
 
-	write_lock_bh(&tipc_nametbl_lock);
+	spin_lock_bh(&tipc_nametbl_lock);
 	seq = nametbl_find_seq(type);
 	if (!seq)
 		seq = tipc_nameseq_create(type,
@@ -730,7 +732,7 @@ void tipc_nametbl_subscribe(struct tipc_subscription *s)
 		pr_warn("Failed to create subscription for {%u,%u,%u}\n",
 			s->seq.type, s->seq.lower, s->seq.upper);
 	}
-	write_unlock_bh(&tipc_nametbl_lock);
+	spin_unlock_bh(&tipc_nametbl_lock);
 }
 
 /**
@@ -740,24 +742,23 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s)
 {
 	struct name_seq *seq;
 
-	write_lock_bh(&tipc_nametbl_lock);
+	spin_lock_bh(&tipc_nametbl_lock);
 	seq = nametbl_find_seq(s->seq.type);
 	if (seq != NULL) {
 		spin_lock_bh(&seq->lock);
 		list_del_init(&s->nameseq_list);
 		if (!seq->first_free && list_empty(&seq->subscriptions)) {
-			hlist_del_init(&seq->ns_list);
-			spin_unlock_bh(&seq->lock);
+			hlist_del_init_rcu(&seq->ns_list);
 			kfree(seq->sseqs);
-			kfree(seq);
+			spin_unlock_bh(&seq->lock);
+			kfree_rcu(seq, rcu);
 		} else {
 			spin_unlock_bh(&seq->lock);
 		}
 	}
-	write_unlock_bh(&tipc_nametbl_lock);
+	spin_unlock_bh(&tipc_nametbl_lock);
 }
 
-
 /**
  * subseq_list - print specified sub-sequence contents into the given buffer
  */
@@ -880,7 +881,7 @@ static int nametbl_list(char *buf, int len, u32 depth_info,
 		upbound = ~0;
 		for (i = 0; i < TIPC_NAMETBL_SIZE; i++) {
 			seq_head = &tipc_nametbl->seq_hlist[i];
-			hlist_for_each_entry(seq, seq_head, ns_list) {
+			hlist_for_each_entry_rcu(seq, seq_head, ns_list) {
 				ret += nameseq_list(seq, buf + ret, len - ret,
 						   depth, seq->type,
 						   lowbound, upbound, i);
@@ -896,7 +897,7 @@ static int nametbl_list(char *buf, int len, u32 depth_info,
 		ret += nametbl_header(buf + ret, len - ret, depth);
 		i = hash(type);
 		seq_head = &tipc_nametbl->seq_hlist[i];
-		hlist_for_each_entry(seq, seq_head, ns_list) {
+		hlist_for_each_entry_rcu(seq, seq_head, ns_list) {
 			if (seq->type == type) {
 				ret += nameseq_list(seq, buf + ret, len - ret,
 						   depth, type,
@@ -928,11 +929,11 @@ struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space)
 	pb = TLV_DATA(rep_tlv);
 	pb_len = ULTRA_STRING_MAX_LEN;
 	argv = (struct tipc_name_table_query *)TLV_DATA(req_tlv_area);
-	read_lock_bh(&tipc_nametbl_lock);
+	rcu_read_lock();
 	str_len = nametbl_list(pb, pb_len, ntohl(argv->depth),
 			       ntohl(argv->type),
 			       ntohl(argv->lowbound), ntohl(argv->upbound));
-	read_unlock_bh(&tipc_nametbl_lock);
+	rcu_read_unlock();
 	str_len += 1;	/* for "\0" */
 	skb_put(buf, TLV_SPACE(str_len));
 	TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len);
@@ -974,13 +975,13 @@ static void tipc_purge_publications(struct name_seq *seq)
 	list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) {
 		tipc_nametbl_remove_publ(publ->type, publ->lower, publ->node,
 					 publ->ref, publ->key);
-		kfree(publ);
+		kfree_rcu(publ, rcu);
 	}
-	hlist_del_init(&seq->ns_list);
+	hlist_del_init_rcu(&seq->ns_list);
+	kfree(seq->sseqs);
 	spin_lock_bh(&seq->lock);
 
-	kfree(seq->sseqs);
-	kfree(seq);
+	kfree_rcu(seq, rcu);
 }
 
 void tipc_nametbl_stop(void)
@@ -988,22 +989,22 @@ void tipc_nametbl_stop(void)
 	u32 i;
 	struct name_seq *seq;
 	struct hlist_head *seq_head;
-	struct hlist_node *safe;
 
 	/* Verify name table is empty and purge any lingering
 	 * publications, then release the name table
 	 */
-	write_lock_bh(&tipc_nametbl_lock);
+	spin_lock_bh(&tipc_nametbl_lock);
 	for (i = 0; i < TIPC_NAMETBL_SIZE; i++) {
 		if (hlist_empty(&tipc_nametbl->seq_hlist[i]))
 			continue;
 		seq_head = &tipc_nametbl->seq_hlist[i];
-		hlist_for_each_entry_safe(seq, safe, seq_head, ns_list) {
+		hlist_for_each_entry_rcu(seq, seq_head, ns_list) {
 			tipc_purge_publications(seq);
 		}
 	}
-	write_unlock_bh(&tipc_nametbl_lock);
+	spin_unlock_bh(&tipc_nametbl_lock);
 
+	synchronize_net();
 	kfree(tipc_nametbl);
 
 }
@@ -1109,7 +1110,7 @@ static int __tipc_nl_seq_list(struct tipc_nl_msg *msg, u32 *last_type,
 			      u32 *last_lower, u32 *last_publ)
 {
 	struct hlist_head *seq_head;
-	struct name_seq *seq;
+	struct name_seq *seq = NULL;
 	int err;
 	int i;
 
@@ -1126,13 +1127,13 @@ static int __tipc_nl_seq_list(struct tipc_nl_msg *msg, u32 *last_type,
 			if (!seq)
 				return -EPIPE;
 		} else {
-			seq = hlist_entry_safe((seq_head)->first,
-					       struct name_seq, ns_list);
+			hlist_for_each_entry_rcu(seq, seq_head, ns_list)
+				break;
 			if (!seq)
 				continue;
 		}
 
-		hlist_for_each_entry_from(seq, ns_list) {
+		hlist_for_each_entry_from_rcu(seq, ns_list) {
 			spin_lock_bh(&seq->lock);
 			err = __tipc_nl_subseq_list(msg, seq, last_lower,
 						    last_publ);
@@ -1165,8 +1166,7 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	msg.portid = NETLINK_CB(cb->skb).portid;
 	msg.seq = cb->nlh->nlmsg_seq;
 
-	read_lock_bh(&tipc_nametbl_lock);
-
+	rcu_read_lock();
 	err = __tipc_nl_seq_list(&msg, &last_type, &last_lower, &last_publ);
 	if (!err) {
 		done = 1;
@@ -1179,8 +1179,7 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		 */
 		cb->prev_seq = 1;
 	}
-
-	read_unlock_bh(&tipc_nametbl_lock);
+	rcu_read_unlock();
 
 	cb->args[0] = last_type;
 	cb->args[1] = last_lower;
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index c1fd734eb0d..5f0dee92010 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -62,6 +62,7 @@ struct tipc_port_list;
  * @node_list: adjacent matching name seq publications with >= node scope
  * @cluster_list: adjacent matching name seq publications with >= cluster scope
  * @zone_list: adjacent matching name seq publications with >= zone scope
+ * @rcu: RCU callback head used for deferred freeing
  *
  * Note that the node list, cluster list, and zone list are circular lists.
  */
@@ -79,6 +80,7 @@ struct publication {
 	struct list_head node_list;
 	struct list_head cluster_list;
 	struct list_head zone_list;
+	struct rcu_head rcu;
 };
 
 /**
@@ -93,7 +95,7 @@ struct name_table {
 	u32 local_publ_count;
 };
 
-extern rwlock_t tipc_nametbl_lock;
+extern spinlock_t tipc_nametbl_lock;
 extern struct name_table *tipc_nametbl;
 
 int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb);
-- 
cgit v1.2.3-70-g09d2


From 0c7aac854f52d3302b88fd599216a810f490ab1f Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@dev.mellanox.co.il>
Date: Tue, 2 Dec 2014 12:26:14 +0200
Subject: net/mlx5_core: Remove unused dev cap enum fields

These enumerations are not used so remove them.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mlx5/device.h | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 1d67fd32e71..ea4f1c46f76 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -219,23 +219,15 @@ enum {
 };
 
 enum {
-	MLX5_DEV_CAP_FLAG_RC		= 1LL <<  0,
-	MLX5_DEV_CAP_FLAG_UC		= 1LL <<  1,
-	MLX5_DEV_CAP_FLAG_UD		= 1LL <<  2,
 	MLX5_DEV_CAP_FLAG_XRC		= 1LL <<  3,
-	MLX5_DEV_CAP_FLAG_SRQ		= 1LL <<  6,
 	MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR	= 1LL <<  8,
 	MLX5_DEV_CAP_FLAG_BAD_QKEY_CNTR	= 1LL <<  9,
 	MLX5_DEV_CAP_FLAG_APM		= 1LL << 17,
 	MLX5_DEV_CAP_FLAG_ATOMIC	= 1LL << 18,
 	MLX5_DEV_CAP_FLAG_BLOCK_MCAST	= 1LL << 23,
-	MLX5_DEV_CAP_FLAG_ON_DMND_PG	= 1LL << 24,
 	MLX5_DEV_CAP_FLAG_CQ_MODER	= 1LL << 29,
 	MLX5_DEV_CAP_FLAG_RESIZE_CQ	= 1LL << 30,
-	MLX5_DEV_CAP_FLAG_RESIZE_SRQ	= 1LL << 32,
 	MLX5_DEV_CAP_FLAG_DCT		= 1LL << 37,
-	MLX5_DEV_CAP_FLAG_REMOTE_FENCE	= 1LL << 38,
-	MLX5_DEV_CAP_FLAG_TLP_HINTS	= 1LL << 39,
 	MLX5_DEV_CAP_FLAG_SIG_HAND_OVER	= 1LL << 40,
 	MLX5_DEV_CAP_FLAG_CMDIF_CSUM	= 3LL << 46,
 };
-- 
cgit v1.2.3-70-g09d2


From 9c0c112422a2a6b06fcddcaf21957676490cebba Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@redhat.com>
Date: Wed, 3 Dec 2014 08:17:33 -0800
Subject: net: Add functions for handling padding frame and adding to length

This patch adds two new helper functions skb_put_padto and eth_skb_pad.
These functions deviate from the standard skb_pad or skb_padto in that they
will also update the length and tail pointers so that they reflect the
padding added to the frame.

The eth_skb_pad helper is meant to be used with Ethernet devices to update
either Rx or Tx frames so that they report the correct size.  The
skb_put_padto helper is meant to be used primarily in the transmit path for
network devices that need frames to be padded up to some minimum size and
don't wish to simply update the length somewhere external to the frame.

The motivation behind this is that there are a number of implementations
throughout the network device drivers that are all doing the same thing,
but each a little bit differently and as a result several implementations
contain bugs such as updating the length without updating the tail offset
and other similar issues.

Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/etherdevice.h | 12 ++++++++++++
 include/linux/skbuff.h      | 24 +++++++++++++++++++++++-
 2 files changed, 35 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 733980fce8e..41c891d05f0 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -392,4 +392,16 @@ static inline unsigned long compare_ether_header(const void *a, const void *b)
 #endif
 }
 
+/**
+ * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame
+ * @skb: Buffer to pad
+ *
+ * An Ethernet frame should have a minimum size of 60 bytes.  This function
+ * takes short frames and pads them with zeros up to the 60 byte limit.
+ */
+static inline int eth_skb_pad(struct sk_buff *skb)
+{
+	return skb_put_padto(skb, ETH_ZLEN);
+}
+
 #endif	/* _LINUX_ETHERDEVICE_H */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7691ad5b477..d1e2575000b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2461,7 +2461,6 @@ static inline int skb_cow_head(struct sk_buff *skb, unsigned int headroom)
  *	is untouched. Otherwise it is extended. Returns zero on
  *	success. The skb is freed on error.
  */
- 
 static inline int skb_padto(struct sk_buff *skb, unsigned int len)
 {
 	unsigned int size = skb->len;
@@ -2470,6 +2469,29 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len)
 	return skb_pad(skb, len - size);
 }
 
+/**
+ *	skb_put_padto - increase size and pad an skbuff up to a minimal size
+ *	@skb: buffer to pad
+ *	@len: minimal length
+ *
+ *	Pads up a buffer to ensure the trailing bytes exist and are
+ *	blanked. If the buffer already contains sufficient data it
+ *	is untouched. Otherwise it is extended. Returns zero on
+ *	success. The skb is freed on error.
+ */
+static inline int skb_put_padto(struct sk_buff *skb, unsigned int len)
+{
+	unsigned int size = skb->len;
+
+	if (unlikely(size < len)) {
+		len -= size;
+		if (skb_pad(skb, len))
+			return -ENOMEM;
+		__skb_put(skb, len);
+	}
+	return 0;
+}
+
 static inline int skb_add_data(struct sk_buff *skb,
 			       char __user *from, int copy)
 {
-- 
cgit v1.2.3-70-g09d2


From 892311f66f2411b813ca631009356891a0c2b0a1 Mon Sep 17 00:00:00 2001
From: Eyal Perry <eyalpe@mellanox.com>
Date: Tue, 2 Dec 2014 18:12:10 +0200
Subject: ethtool: Support for configurable RSS hash function

This patch extends the set/get_rxfh ethtool-options for getting or
setting the RSS hash function.

It modifies drivers implementation of set/get_rxfh accordingly.

This change also delegates the responsibility of checking whether a
modification to a certain RX flow hash parameter is supported to the
driver implementation of set_rxfh.

User-kernel API is done through the new hfunc bitmask field in the
ethtool_rxfh struct. A bit set in the hfunc field is corresponding to an
index in the new string-set ETH_SS_RSS_HASH_FUNCS.

Got approval from most of the relevant driver maintainers that their
driver is using Toeplitz, and for the few that didn't answered, also
assumed it is Toeplitz.

Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Ariel Elior <ariel.elior@qlogic.com>
Cc: Prashant Sreedharan <prashant@broadcom.com>
Cc: Michael Chan <mchan@broadcom.com>
Cc: Hariprasad S <hariprasad@chelsio.com>
Cc: Sathya Perla <sathya.perla@emulex.com>
Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com>
Cc: Ajit Khaparde <ajit.khaparde@emulex.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Cc: Bruce Allan <bruce.w.allan@intel.com>
Cc: Carolyn Wyborny <carolyn.wyborny@intel.com>
Cc: Don Skidmore <donald.c.skidmore@intel.com>
Cc: Greg Rose <gregory.v.rose@intel.com>
Cc: Matthew Vick <matthew.vick@intel.com>
Cc: John Ronciak <john.ronciak@intel.com>
Cc: Mitch Williams <mitch.a.williams@intel.com>
Cc: Amir Vadai <amirv@mellanox.com>
Cc: Solarflare linux maintainers <linux-net-drivers@solarflare.com>
Cc: Shradha Shah <sshah@solarflare.com>
Cc: Shreyas Bhatewara <sbhatewara@vmware.com>
Cc: "VMware, Inc." <pv-drivers@vmware.com>
Cc: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Eyal Perry <eyalpe@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c       | 11 +++-
 .../net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c    | 20 ++++++-
 drivers/net/ethernet/broadcom/tg3.c                | 20 ++++++-
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c    | 18 +++++-
 drivers/net/ethernet/emulex/benet/be_ethtool.c     | 12 +++-
 drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c   | 12 +++-
 drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c | 17 +++++-
 drivers/net/ethernet/intel/igb/igb_ethtool.c       | 16 ++++-
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c    | 13 +++-
 drivers/net/ethernet/sfc/ethtool.c                 | 18 ++++--
 drivers/net/vmxnet3/vmxnet3_ethtool.c              | 15 ++++-
 include/linux/ethtool.h                            | 42 +++++++++----
 include/uapi/linux/ethtool.h                       | 10 +++-
 net/core/ethtool.c                                 | 69 ++++++++++++----------
 14 files changed, 223 insertions(+), 70 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
index 95d44538357..ebf48935155 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
@@ -511,7 +511,8 @@ static u32 xgbe_get_rxfh_indir_size(struct net_device *netdev)
 	return ARRAY_SIZE(pdata->rss_table);
 }
 
-static int xgbe_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key)
+static int xgbe_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
+			 u8 *hfunc)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	unsigned int i;
@@ -525,16 +526,22 @@ static int xgbe_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key)
 	if (key)
 		memcpy(key, pdata->rss_key, sizeof(pdata->rss_key));
 
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+
 	return 0;
 }
 
 static int xgbe_set_rxfh(struct net_device *netdev, const u32 *indir,
-			 const u8 *key)
+			 const u8 *key, const u8 hfunc)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
 	unsigned int ret;
 
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
 	if (indir) {
 		ret = hw_if->set_rss_lookup_table(pdata, indir);
 		if (ret)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 1edc931b145..ffe4e003e63 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -3358,12 +3358,18 @@ static u32 bnx2x_get_rxfh_indir_size(struct net_device *dev)
 	return T_ETH_INDIRECTION_TABLE_SIZE;
 }
 
-static int bnx2x_get_rxfh(struct net_device *dev, u32 *indir, u8 *key)
+static int bnx2x_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
+			  u8 *hfunc)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	u8 ind_table[T_ETH_INDIRECTION_TABLE_SIZE] = {0};
 	size_t i;
 
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+	if (!indir)
+		return 0;
+
 	/* Get the current configuration of the RSS indirection table */
 	bnx2x_get_rss_ind_table(&bp->rss_conf_obj, ind_table);
 
@@ -3383,11 +3389,21 @@ static int bnx2x_get_rxfh(struct net_device *dev, u32 *indir, u8 *key)
 }
 
 static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
-			  const u8 *key)
+			  const u8 *key, const u8 hfunc)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	size_t i;
 
+	/* We require at least one supported parameter to be changed and no
+	 * change in any of the unsupported parameters
+	 */
+	if (key ||
+	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+		return -EOPNOTSUPP;
+
+	if (!indir)
+		return 0;
+
 	for (i = 0; i < T_ETH_INDIRECTION_TABLE_SIZE; i++) {
 		/*
 		 * The same as in bnx2x_get_rxfh: we can't use a memcpy()
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 43fd1b72c1e..bb48a610b72 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -12561,22 +12561,38 @@ static u32 tg3_get_rxfh_indir_size(struct net_device *dev)
 	return size;
 }
 
-static int tg3_get_rxfh(struct net_device *dev, u32 *indir, u8 *key)
+static int tg3_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, u8 *hfunc)
 {
 	struct tg3 *tp = netdev_priv(dev);
 	int i;
 
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+	if (!indir)
+		return 0;
+
 	for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
 		indir[i] = tp->rss_ind_tbl[i];
 
 	return 0;
 }
 
-static int tg3_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key)
+static int tg3_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key,
+			const u8 hfunc)
 {
 	struct tg3 *tp = netdev_priv(dev);
 	size_t i;
 
+	/* We require at least one supported parameter to be changed and no
+	 * change in any of the unsupported parameters
+	 */
+	if (key ||
+	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+		return -EOPNOTSUPP;
+
+	if (!indir)
+		return 0;
+
 	for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
 		tp->rss_ind_tbl[i] = indir[i];
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 3aea82bb903..e7342bc8502 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2923,21 +2923,35 @@ static u32 get_rss_table_size(struct net_device *dev)
 	return pi->rss_size;
 }
 
-static int get_rss_table(struct net_device *dev, u32 *p, u8 *key)
+static int get_rss_table(struct net_device *dev, u32 *p, u8 *key, u8 *hfunc)
 {
 	const struct port_info *pi = netdev_priv(dev);
 	unsigned int n = pi->rss_size;
 
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+	if (!p)
+		return 0;
 	while (n--)
 		p[n] = pi->rss[n];
 	return 0;
 }
 
-static int set_rss_table(struct net_device *dev, const u32 *p, const u8 *key)
+static int set_rss_table(struct net_device *dev, const u32 *p, const u8 *key,
+			 const u8 hfunc)
 {
 	unsigned int i;
 	struct port_info *pi = netdev_priv(dev);
 
+	/* We require at least one supported parameter to be changed and no
+	 * change in any of the unsupported parameters
+	 */
+	if (key ||
+	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+		return -EOPNOTSUPP;
+	if (!p)
+		return 0;
+
 	for (i = 0; i < pi->rss_size; i++)
 		pi->rss[i] = p[i];
 	if (pi->adapter->flags & FULL_INIT_DONE)
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index e42a791c183..73a500ccbf6 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -1171,7 +1171,8 @@ static u32 be_get_rxfh_key_size(struct net_device *netdev)
 	return RSS_HASH_KEY_LEN;
 }
 
-static int be_get_rxfh(struct net_device *netdev, u32 *indir, u8 *hkey)
+static int be_get_rxfh(struct net_device *netdev, u32 *indir, u8 *hkey,
+		       u8 *hfunc)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	int i;
@@ -1185,16 +1186,23 @@ static int be_get_rxfh(struct net_device *netdev, u32 *indir, u8 *hkey)
 	if (hkey)
 		memcpy(hkey, rss->rss_hkey, RSS_HASH_KEY_LEN);
 
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+
 	return 0;
 }
 
 static int be_set_rxfh(struct net_device *netdev, const u32 *indir,
-		       const u8 *hkey)
+		       const u8 *hkey, const u8 hfunc)
 {
 	int rc = 0, i, j;
 	struct be_adapter *adapter = netdev_priv(netdev);
 	u8 rsstable[RSS_INDIR_TABLE_LEN];
 
+	/* We do not allow change in unsupported parameters */
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
 	if (indir) {
 		struct be_rx_obj *rxo;
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
index 2d04464e6aa..651f53bc737 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
@@ -916,11 +916,15 @@ static u32 fm10k_get_rssrk_size(struct net_device *netdev)
 	return FM10K_RSSRK_SIZE * FM10K_RSSRK_ENTRIES_PER_REG;
 }
 
-static int fm10k_get_rssh(struct net_device *netdev, u32 *indir, u8 *key)
+static int fm10k_get_rssh(struct net_device *netdev, u32 *indir, u8 *key,
+			  u8 *hfunc)
 {
 	struct fm10k_intfc *interface = netdev_priv(netdev);
 	int i, err;
 
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+
 	err = fm10k_get_reta(netdev, indir);
 	if (err || !key)
 		return err;
@@ -932,12 +936,16 @@ static int fm10k_get_rssh(struct net_device *netdev, u32 *indir, u8 *key)
 }
 
 static int fm10k_set_rssh(struct net_device *netdev, const u32 *indir,
-			  const u8 *key)
+			  const u8 *key, const u8 hfunc)
 {
 	struct fm10k_intfc *interface = netdev_priv(netdev);
 	struct fm10k_hw *hw = &interface->hw;
 	int i, err;
 
+	/* We do not allow change in unsupported parameters */
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
 	err = fm10k_set_reta(netdev, indir);
 	if (err || !key)
 		return err;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
index 69a269b23be..69b97bac182 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
@@ -627,13 +627,19 @@ static u32 i40evf_get_rxfh_indir_size(struct net_device *netdev)
  *
  * Reads the indirection table directly from the hardware. Always returns 0.
  **/
-static int i40evf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key)
+static int i40evf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
+			   u8 *hfunc)
 {
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 	struct i40e_hw *hw = &adapter->hw;
 	u32 hlut_val;
 	int i, j;
 
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+	if (!indir)
+		return 0;
+
 	for (i = 0, j = 0; i <= I40E_VFQF_HLUT_MAX_INDEX; i++) {
 		hlut_val = rd32(hw, I40E_VFQF_HLUT(i));
 		indir[j++] = hlut_val & 0xff;
@@ -654,13 +660,20 @@ static int i40evf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key)
  * returns 0 after programming the table.
  **/
 static int i40evf_set_rxfh(struct net_device *netdev, const u32 *indir,
-			   const u8 *key)
+			   const u8 *key, const u8 hfunc)
 {
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 	struct i40e_hw *hw = &adapter->hw;
 	u32 hlut_val;
 	int i, j;
 
+	/* We do not allow change in unsupported parameters */
+	if (key ||
+	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+		return -EOPNOTSUPP;
+	if (!indir)
+		return 0;
+
 	for (i = 0, j = 0; i <= I40E_VFQF_HLUT_MAX_INDEX; i++) {
 		hlut_val = indir[j++];
 		hlut_val |= indir[j++] << 8;
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 02cfd3b1476..d5673eb90c5 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -2842,11 +2842,16 @@ static u32 igb_get_rxfh_indir_size(struct net_device *netdev)
 	return IGB_RETA_SIZE;
 }
 
-static int igb_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key)
+static int igb_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
+			u8 *hfunc)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	int i;
 
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+	if (!indir)
+		return 0;
 	for (i = 0; i < IGB_RETA_SIZE; i++)
 		indir[i] = adapter->rss_indir_tbl[i];
 
@@ -2889,13 +2894,20 @@ void igb_write_rss_indir_tbl(struct igb_adapter *adapter)
 }
 
 static int igb_set_rxfh(struct net_device *netdev, const u32 *indir,
-			const u8 *key)
+			const u8 *key, const u8 hfunc)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 	int i;
 	u32 num_queues;
 
+	/* We do not allow change in unsupported parameters */
+	if (key ||
+	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+		return -EOPNOTSUPP;
+	if (!indir)
+		return 0;
+
 	num_queues = adapter->rss_queues;
 
 	switch (hw->mac.type) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index c45e06abc07..28c3fc5a079 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -978,7 +978,8 @@ static u32 mlx4_en_get_rxfh_key_size(struct net_device *netdev)
 	return MLX4_EN_RSS_KEY_SIZE;
 }
 
-static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key)
+static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key,
+			    u8 *hfunc)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_rss_map *rss_map = &priv->rss_map;
@@ -990,16 +991,20 @@ static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key)
 	rss_rings = 1 << ilog2(rss_rings);
 
 	while (n--) {
+		if (!ring_index)
+			break;
 		ring_index[n] = rss_map->qps[n % rss_rings].qpn -
 			rss_map->base_qpn;
 	}
 	if (key)
 		memcpy(key, priv->rss_key, MLX4_EN_RSS_KEY_SIZE);
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
 	return err;
 }
 
 static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
-			    const u8 *key)
+			    const u8 *key, const u8 hfunc)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
@@ -1008,6 +1013,10 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
 	int i;
 	int rss_rings = 0;
 
+	/* We do not allow change in unsupported parameters */
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
 	/* Calculate RSS table size and make sure flows are spread evenly
 	 * between rings
 	 */
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index cad258a7870..4835bc0d0de 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -1086,19 +1086,29 @@ static u32 efx_ethtool_get_rxfh_indir_size(struct net_device *net_dev)
 		0 : ARRAY_SIZE(efx->rx_indir_table));
 }
 
-static int efx_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key)
+static int efx_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
+				u8 *hfunc)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 
-	memcpy(indir, efx->rx_indir_table, sizeof(efx->rx_indir_table));
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+	if (indir)
+		memcpy(indir, efx->rx_indir_table, sizeof(efx->rx_indir_table));
 	return 0;
 }
 
-static int efx_ethtool_set_rxfh(struct net_device *net_dev,
-				const u32 *indir, const u8 *key)
+static int efx_ethtool_set_rxfh(struct net_device *net_dev, const u32 *indir,
+				const u8 *key, const u8 hfunc)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 
+	/* We do not allow change in unsupported parameters */
+	if (key ||
+	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+		return -EOPNOTSUPP;
+	if (!indir)
+		return 0;
 	memcpy(efx->rx_indir_table, indir, sizeof(efx->rx_indir_table));
 	efx->type->rx_push_rss_config(efx);
 	return 0;
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index b725fd9e780..b7b53329d57 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -583,12 +583,16 @@ vmxnet3_get_rss_indir_size(struct net_device *netdev)
 }
 
 static int
-vmxnet3_get_rss(struct net_device *netdev, u32 *p, u8 *key)
+vmxnet3_get_rss(struct net_device *netdev, u32 *p, u8 *key, u8 *hfunc)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	struct UPT1_RSSConf *rssConf = adapter->rss_conf;
 	unsigned int n = rssConf->indTableSize;
 
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+	if (!p)
+		return 0;
 	while (n--)
 		p[n] = rssConf->indTable[n];
 	return 0;
@@ -596,13 +600,20 @@ vmxnet3_get_rss(struct net_device *netdev, u32 *p, u8 *key)
 }
 
 static int
-vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key)
+vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key,
+		const u8 hfunc)
 {
 	unsigned int i;
 	unsigned long flags;
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	struct UPT1_RSSConf *rssConf = adapter->rss_conf;
 
+	/* We do not allow change in unsupported parameters */
+	if (key ||
+	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+		return -EOPNOTSUPP;
+	if (!p)
+		return 0;
 	for (i = 0; i < rssConf->indTableSize; i++)
 		rssConf->indTable[i] = p[i];
 
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index c1a2d60dfb8..653dc9c4eba 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -59,6 +59,26 @@ enum ethtool_phys_id_state {
 	ETHTOOL_ID_OFF
 };
 
+enum {
+	ETH_RSS_HASH_TOP_BIT, /* Configurable RSS hash function - Toeplitz */
+	ETH_RSS_HASH_XOR_BIT, /* Configurable RSS hash function - Xor */
+
+	/*
+	 * Add your fresh new hash function bits above and remember to update
+	 * rss_hash_func_strings[] in ethtool.c
+	 */
+	ETH_RSS_HASH_FUNCS_COUNT
+};
+
+#define __ETH_RSS_HASH_BIT(bit)	((u32)1 << (bit))
+#define __ETH_RSS_HASH(name)	__ETH_RSS_HASH_BIT(ETH_RSS_HASH_##name##_BIT)
+
+#define ETH_RSS_HASH_TOP	__ETH_RSS_HASH(TOP)
+#define ETH_RSS_HASH_XOR	__ETH_RSS_HASH(XOR)
+
+#define ETH_RSS_HASH_UNKNOWN	0
+#define ETH_RSS_HASH_NO_CHANGE	0
+
 struct net_device;
 
 /* Some generic methods drivers may use in their ethtool_ops */
@@ -158,17 +178,14 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings)
  *	Returns zero if not supported for this specific device.
  * @get_rxfh_indir_size: Get the size of the RX flow hash indirection table.
  *	Returns zero if not supported for this specific device.
- * @get_rxfh: Get the contents of the RX flow hash indirection table and hash
- *	key.
- *	Will only be called if one or both of @get_rxfh_indir_size and
- *	@get_rxfh_key_size are implemented and return non-zero.
- *	Returns a negative error code or zero.
- * @set_rxfh: Set the contents of the RX flow hash indirection table and/or
- *	hash key.  In case only the indirection table or hash key is to be
- *	changed, the other argument will be %NULL.
- *	Will only be called if one or both of @get_rxfh_indir_size and
- *	@get_rxfh_key_size are implemented and return non-zero.
+ * @get_rxfh: Get the contents of the RX flow hash indirection table, hash key
+ *	and/or hash function.
  *	Returns a negative error code or zero.
+ * @set_rxfh: Set the contents of the RX flow hash indirection table, hash
+ *	key, and/or hash function.  Arguments which are set to %NULL or zero
+ *	will remain unchanged.
+ *	Returns a negative error code or zero. An error code must be returned
+ *	if at least one unsupported change was requested.
  * @get_channels: Get number of channels.
  * @set_channels: Set number of channels.  Returns a negative error code or
  *	zero.
@@ -241,9 +258,10 @@ struct ethtool_ops {
 	int	(*reset)(struct net_device *, u32 *);
 	u32	(*get_rxfh_key_size)(struct net_device *);
 	u32	(*get_rxfh_indir_size)(struct net_device *);
-	int	(*get_rxfh)(struct net_device *, u32 *indir, u8 *key);
+	int	(*get_rxfh)(struct net_device *, u32 *indir, u8 *key,
+			    u8 *hfunc);
 	int	(*set_rxfh)(struct net_device *, const u32 *indir,
-			    const u8 *key);
+			    const u8 *key, const u8 hfunc);
 	void	(*get_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*set_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*get_dump_flag)(struct net_device *, struct ethtool_dump *);
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index eb2095b42fb..5f66d9c2889 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -534,6 +534,7 @@ struct ethtool_pauseparam {
  * @ETH_SS_NTUPLE_FILTERS: Previously used with %ETHTOOL_GRXNTUPLE;
  *	now deprecated
  * @ETH_SS_FEATURES: Device feature names
+ * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names
  */
 enum ethtool_stringset {
 	ETH_SS_TEST		= 0,
@@ -541,6 +542,7 @@ enum ethtool_stringset {
 	ETH_SS_PRIV_FLAGS,
 	ETH_SS_NTUPLE_FILTERS,
 	ETH_SS_FEATURES,
+	ETH_SS_RSS_HASH_FUNCS,
 };
 
 /**
@@ -884,6 +886,8 @@ struct ethtool_rxfh_indir {
  * @key_size: On entry, the array size of the user buffer for the hash key,
  *	which may be zero.  On return from %ETHTOOL_GRSSH, the size of the
  *	hardware hash key.
+ * @hfunc: Defines the current RSS hash function used by HW (or to be set to).
+ *	Valid values are one of the %ETH_RSS_HASH_*.
  * @rsvd:	Reserved for future extensions.
  * @rss_config: RX ring/queue index for each hash value i.e., indirection table
  *	of @indir_size __u32 elements, followed by hash key of @key_size
@@ -893,14 +897,16 @@ struct ethtool_rxfh_indir {
  * size should be returned.  For %ETHTOOL_SRSSH, an @indir_size of
  * %ETH_RXFH_INDIR_NO_CHANGE means that indir table setting is not requested
  * and a @indir_size of zero means the indir table should be reset to default
- * values.
+ * values. An hfunc of zero means that hash function setting is not requested.
  */
 struct ethtool_rxfh {
 	__u32   cmd;
 	__u32	rss_context;
 	__u32   indir_size;
 	__u32   key_size;
-	__u32	rsvd[2];
+	__u8	hfunc;
+	__u8	rsvd8[3];
+	__u32	rsvd32;
 	__u32   rss_config[0];
 };
 #define ETH_RXFH_INDIR_NO_CHANGE	0xffffffff
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 715f51f321e..550892cd6b3 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -100,6 +100,12 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_BUSY_POLL_BIT] =        "busy-poll",
 };
 
+static const char
+rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = {
+	[ETH_RSS_HASH_TOP_BIT] =	"toeplitz",
+	[ETH_RSS_HASH_XOR_BIT] =	"xor",
+};
+
 static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
 {
 	struct ethtool_gfeatures cmd = {
@@ -185,6 +191,9 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset)
 	if (sset == ETH_SS_FEATURES)
 		return ARRAY_SIZE(netdev_features_strings);
 
+	if (sset == ETH_SS_RSS_HASH_FUNCS)
+		return ARRAY_SIZE(rss_hash_func_strings);
+
 	if (ops->get_sset_count && ops->get_strings)
 		return ops->get_sset_count(dev, sset);
 	else
@@ -199,6 +208,9 @@ static void __ethtool_get_strings(struct net_device *dev,
 	if (stringset == ETH_SS_FEATURES)
 		memcpy(data, netdev_features_strings,
 			sizeof(netdev_features_strings));
+	else if (stringset == ETH_SS_RSS_HASH_FUNCS)
+		memcpy(data, rss_hash_func_strings,
+		       sizeof(rss_hash_func_strings));
 	else
 		/* ops->get_strings is valid because checked earlier */
 		ops->get_strings(dev, stringset, data);
@@ -618,7 +630,7 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 	if (!indir)
 		return -ENOMEM;
 
-	ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL);
+	ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL);
 	if (ret)
 		goto out;
 
@@ -679,7 +691,7 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 			goto out;
 	}
 
-	ret = ops->set_rxfh(dev, indir, NULL);
+	ret = ops->set_rxfh(dev, indir, NULL, ETH_RSS_HASH_NO_CHANGE);
 
 out:
 	kfree(indir);
@@ -697,12 +709,11 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	u32 total_size;
 	u32 indir_bytes;
 	u32 *indir = NULL;
+	u8 dev_hfunc = 0;
 	u8 *hkey = NULL;
 	u8 *rss_config;
 
-	if (!(dev->ethtool_ops->get_rxfh_indir_size ||
-	      dev->ethtool_ops->get_rxfh_key_size) ||
-	      !dev->ethtool_ops->get_rxfh)
+	if (!ops->get_rxfh)
 		return -EOPNOTSUPP;
 
 	if (ops->get_rxfh_indir_size)
@@ -710,16 +721,14 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	if (ops->get_rxfh_key_size)
 		dev_key_size = ops->get_rxfh_key_size(dev);
 
-	if ((dev_key_size + dev_indir_size) == 0)
-		return -EOPNOTSUPP;
-
 	if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
 		return -EFAULT;
 	user_indir_size = rxfh.indir_size;
 	user_key_size = rxfh.key_size;
 
 	/* Check that reserved fields are 0 for now */
-	if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1])
+	if (rxfh.rss_context || rxfh.rsvd8[0] || rxfh.rsvd8[1] ||
+	    rxfh.rsvd8[2] || rxfh.rsvd32)
 		return -EINVAL;
 
 	rxfh.indir_size = dev_indir_size;
@@ -727,13 +736,6 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	if (copy_to_user(useraddr, &rxfh, sizeof(rxfh)))
 		return -EFAULT;
 
-	/* If the user buffer size is 0, this is just a query for the
-	 * device table size and key size.  Otherwise, if the User size is
-	 * not equal to device table size or key size it's an error.
-	 */
-	if (!user_indir_size && !user_key_size)
-		return 0;
-
 	if ((user_indir_size && (user_indir_size != dev_indir_size)) ||
 	    (user_key_size && (user_key_size != dev_key_size)))
 		return -EINVAL;
@@ -750,14 +752,19 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	if (user_key_size)
 		hkey = rss_config + indir_bytes;
 
-	ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey);
-	if (!ret) {
-		if (copy_to_user(useraddr +
-				 offsetof(struct ethtool_rxfh, rss_config[0]),
-				 rss_config, total_size))
-			ret = -EFAULT;
-	}
+	ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey, &dev_hfunc);
+	if (ret)
+		goto out;
 
+	if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, hfunc),
+			 &dev_hfunc, sizeof(rxfh.hfunc))) {
+		ret = -EFAULT;
+	} else if (copy_to_user(useraddr +
+			      offsetof(struct ethtool_rxfh, rss_config[0]),
+			      rss_config, total_size)) {
+		ret = -EFAULT;
+	}
+out:
 	kfree(rss_config);
 
 	return ret;
@@ -776,33 +783,31 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	u8 *rss_config;
 	u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
 
-	if (!(ops->get_rxfh_indir_size || ops->get_rxfh_key_size) ||
-	    !ops->get_rxnfc || !ops->set_rxfh)
+	if (!ops->get_rxnfc || !ops->set_rxfh)
 		return -EOPNOTSUPP;
 
 	if (ops->get_rxfh_indir_size)
 		dev_indir_size = ops->get_rxfh_indir_size(dev);
 	if (ops->get_rxfh_key_size)
 		dev_key_size = dev->ethtool_ops->get_rxfh_key_size(dev);
-	if ((dev_key_size + dev_indir_size) == 0)
-		return -EOPNOTSUPP;
 
 	if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
 		return -EFAULT;
 
 	/* Check that reserved fields are 0 for now */
-	if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1])
+	if (rxfh.rss_context || rxfh.rsvd8[0] || rxfh.rsvd8[1] ||
+	    rxfh.rsvd8[2] || rxfh.rsvd32)
 		return -EINVAL;
 
-	/* If either indir or hash key is valid, proceed further.
-	 * It is not valid to request that both be unchanged.
+	/* If either indir, hash key or function is valid, proceed further.
+	 * Must request at least one change: indir size, hash key or function.
 	 */
 	if ((rxfh.indir_size &&
 	     rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE &&
 	     rxfh.indir_size != dev_indir_size) ||
 	    (rxfh.key_size && (rxfh.key_size != dev_key_size)) ||
 	    (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE &&
-	     rxfh.key_size == 0))
+	     rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE))
 		return -EINVAL;
 
 	if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
@@ -845,7 +850,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		}
 	}
 
-	ret = ops->set_rxfh(dev, indir, hkey);
+	ret = ops->set_rxfh(dev, indir, hkey, rxfh.hfunc);
 
 out:
 	kfree(rss_config);
-- 
cgit v1.2.3-70-g09d2


From a5a519b2710be43fce3cf9ce7bd8de8db3f2a9de Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@redhat.com>
Date: Tue, 2 Dec 2014 10:58:21 -0800
Subject: fib_trie: Fix /proc/net/fib_trie when CONFIG_IP_MULTIPLE_TABLES is
 not defined

In recent testing I had disabled CONFIG_IP_MULTIPLE_TABLES and as a result
when I ran "cat /proc/net/fib_trie" the main trie was displayed multiple
times.  I found that the problem line of code was in the function
fib_trie_seq_next.  Specifically the line below caused the indexes to go in
the opposite direction of our traversal:

	h = tb->tb_id & (FIB_TABLE_HASHSZ - 1);

This issue was that the RT tables are defined such that RT_TABLE_LOCAL is ID
255, while it is located at TABLE_LOCAL_INDEX of 0, and RT_TABLE_MAIN is 254
with a TABLE_MAIN_INDEX of 1.  This means that the above line will return 1
for the local table and 0 for main.  The result is that fib_trie_seq_next
will return NULL at the end of the local table, fib_trie_seq_start will
return the start of the main table, and then fib_trie_seq_next will loop on
main forever as h will always return 0.

The fix for this is to reverse the ordering of the two tables.  It has the
advantage of making it so that the tables now print in the same order
regardless of if multiple tables are enabled or not.  In order to make the
definition consistent with the multiple tables case I simply masked the to
RT_TABLE_XXX values by (FIB_TABLE_HASHSZ - 1).  This way the two table
layouts should always stay consistent.

Fixes: 93456b6 ("[IPV4]: Unify access to the routing tables")
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index dc9d2a27c31..09a819ee215 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -201,8 +201,8 @@ void fib_free_table(struct fib_table *tb);
 
 #ifndef CONFIG_IP_MULTIPLE_TABLES
 
-#define TABLE_LOCAL_INDEX	0
-#define TABLE_MAIN_INDEX	1
+#define TABLE_LOCAL_INDEX	(RT_TABLE_LOCAL & (FIB_TABLE_HASHSZ - 1))
+#define TABLE_MAIN_INDEX	(RT_TABLE_MAIN  & (FIB_TABLE_HASHSZ - 1))
 
 static inline struct fib_table *fib_get_table(struct net *net, u32 id)
 {
-- 
cgit v1.2.3-70-g09d2


From af6c9f1657ca6d2ef2b2c0e31ad17c6fbf773baf Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 19 Nov 2014 18:11:00 -0800
Subject: thermal: provide an UAPI header file

include/linux/thermal.h contains definitions for the Thermal generic
netlink family, but none of the valuable information relevant to
user-space such as the Genl family name, multicast group, version or
command set and data types is exported to user-space.

Export all the relevant generic netlink information to user-space to
make this genl family usable by user-space, and while at it, export
THERMAL_NAME_LENGTH since it limits name length for thermal_hwmon
devices.

Kbuild and MAINTAINERS are also updated accordingly to reflect this new
file: include/uapi/linux/thermal.h.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 MAINTAINERS                  |  1 +
 include/linux/thermal.h      | 31 +------------------------------
 include/uapi/linux/Kbuild    |  1 +
 include/uapi/linux/thermal.h | 35 +++++++++++++++++++++++++++++++++++
 4 files changed, 38 insertions(+), 30 deletions(-)
 create mode 100644 include/uapi/linux/thermal.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 0ff630de8a6..9c709f503c0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9295,6 +9295,7 @@ Q:	https://patchwork.kernel.org/project/linux-pm/list/
 S:	Supported
 F:	drivers/thermal/
 F:	include/linux/thermal.h
+F:	include/uapi/linux/thermal.h
 F:	include/linux/cpu_cooling.h
 F:	Documentation/devicetree/bindings/thermal/
 
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index ef90838b36a..70f87406bed 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -29,10 +29,10 @@
 #include <linux/idr.h>
 #include <linux/device.h>
 #include <linux/workqueue.h>
+#include <uapi/linux/thermal.h>
 
 #define THERMAL_TRIPS_NONE	-1
 #define THERMAL_MAX_TRIPS	12
-#define THERMAL_NAME_LENGTH	20
 
 /* invalid cooling state */
 #define THERMAL_CSTATE_INVALID -1UL
@@ -49,11 +49,6 @@
 #define MILLICELSIUS_TO_DECI_KELVIN_WITH_OFFSET(t, off) (((t) / 100) + (off))
 #define MILLICELSIUS_TO_DECI_KELVIN(t) MILLICELSIUS_TO_DECI_KELVIN_WITH_OFFSET(t, 2732)
 
-/* Adding event notification support elements */
-#define THERMAL_GENL_FAMILY_NAME                "thermal_event"
-#define THERMAL_GENL_VERSION                    0x01
-#define THERMAL_GENL_MCAST_GROUP_NAME           "thermal_mc_grp"
-
 /* Default Thermal Governor */
 #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)
 #define DEFAULT_THERMAL_GOVERNOR       "step_wise"
@@ -86,30 +81,6 @@ enum thermal_trend {
 	THERMAL_TREND_DROP_FULL, /* apply lowest cooling action */
 };
 
-/* Events supported by Thermal Netlink */
-enum events {
-	THERMAL_AUX0,
-	THERMAL_AUX1,
-	THERMAL_CRITICAL,
-	THERMAL_DEV_FAULT,
-};
-
-/* attributes of thermal_genl_family */
-enum {
-	THERMAL_GENL_ATTR_UNSPEC,
-	THERMAL_GENL_ATTR_EVENT,
-	__THERMAL_GENL_ATTR_MAX,
-};
-#define THERMAL_GENL_ATTR_MAX (__THERMAL_GENL_ATTR_MAX - 1)
-
-/* commands supported by the thermal_genl_family */
-enum {
-	THERMAL_GENL_CMD_UNSPEC,
-	THERMAL_GENL_CMD_EVENT,
-	__THERMAL_GENL_CMD_MAX,
-};
-#define THERMAL_GENL_CMD_MAX (__THERMAL_GENL_CMD_MAX - 1)
-
 struct thermal_zone_device_ops {
 	int (*bind) (struct thermal_zone_device *,
 		     struct thermal_cooling_device *);
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 4c94f31a8c9..a1943e2d126 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -383,6 +383,7 @@ header-y += tcp.h
 header-y += tcp_metrics.h
 header-y += telephony.h
 header-y += termios.h
+header-y += thermal.h
 header-y += time.h
 header-y += times.h
 header-y += timex.h
diff --git a/include/uapi/linux/thermal.h b/include/uapi/linux/thermal.h
new file mode 100644
index 00000000000..ac553585598
--- /dev/null
+++ b/include/uapi/linux/thermal.h
@@ -0,0 +1,35 @@
+#ifndef _UAPI_LINUX_THERMAL_H
+#define _UAPI_LINUX_THERMAL_H
+
+#define THERMAL_NAME_LENGTH	20
+
+/* Adding event notification support elements */
+#define THERMAL_GENL_FAMILY_NAME                "thermal_event"
+#define THERMAL_GENL_VERSION                    0x01
+#define THERMAL_GENL_MCAST_GROUP_NAME           "thermal_mc_grp"
+
+/* Events supported by Thermal Netlink */
+enum events {
+	THERMAL_AUX0,
+	THERMAL_AUX1,
+	THERMAL_CRITICAL,
+	THERMAL_DEV_FAULT,
+};
+
+/* attributes of thermal_genl_family */
+enum {
+	THERMAL_GENL_ATTR_UNSPEC,
+	THERMAL_GENL_ATTR_EVENT,
+	__THERMAL_GENL_ATTR_MAX,
+};
+#define THERMAL_GENL_ATTR_MAX (__THERMAL_GENL_ATTR_MAX - 1)
+
+/* commands supported by the thermal_genl_family */
+enum {
+	THERMAL_GENL_CMD_UNSPEC,
+	THERMAL_GENL_CMD_EVENT,
+	__THERMAL_GENL_CMD_MAX,
+};
+#define THERMAL_GENL_CMD_MAX (__THERMAL_GENL_CMD_MAX - 1)
+
+#endif /* _UAPI_LINUX_THERMAL_H */
-- 
cgit v1.2.3-70-g09d2


From 829b030e58f8349a63909c0fff2fa1913d79314c Mon Sep 17 00:00:00 2001
From: Sean Paul <seanpaul@chromium.org>
Date: Tue, 2 Dec 2014 17:39:12 -0800
Subject: backlight: lp855x: Add supply regulator to lp855x
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds a supply regulator to the lp855x platform data to facilitate
powering on/off the 3V rail attached to the controller.

Cc: Stéphane Marchesin <marcheu@chromium.org>
Cc: Aaron Durbin <adurbin@chromium.org>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Acked-by: Milo Kim <milo.kim@ti.com>
Acked-by: Bryan Wu <cooloney@gmail.com>
Acked-by: Jingoo Han <jg1.han@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 .../devicetree/bindings/video/backlight/lp855x.txt     |  2 ++
 drivers/video/backlight/lp855x_bl.c                    | 18 ++++++++++++++++++
 include/linux/platform_data/lp855x.h                   |  2 ++
 3 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/video/backlight/lp855x.txt b/Documentation/devicetree/bindings/video/backlight/lp855x.txt
index 96e83a56048..0a3ecbc3a1b 100644
--- a/Documentation/devicetree/bindings/video/backlight/lp855x.txt
+++ b/Documentation/devicetree/bindings/video/backlight/lp855x.txt
@@ -12,6 +12,7 @@ Optional properties:
   - pwm-period: PWM period value. Set only PWM input mode used (u32)
   - rom-addr: Register address of ROM area to be updated (u8)
   - rom-val: Register value to be updated (u8)
+  - power-supply: Regulator which controls the 3V rail
 
 Example:
 
@@ -56,6 +57,7 @@ Example:
 	backlight@2c {
 		compatible = "ti,lp8557";
 		reg = <0x2c>;
+		power-supply = <&backlight_vdd>;
 
 		dev-ctrl = /bits/ 8 <0x41>;
 		init-brt = /bits/ 8 <0x0a>;
diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index 257b3badd8e..a26d3bb2565 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -17,6 +17,7 @@
 #include <linux/of.h>
 #include <linux/platform_data/lp855x.h>
 #include <linux/pwm.h>
+#include <linux/regulator/consumer.h>
 
 /* LP8550/1/2/3/6 Registers */
 #define LP855X_BRIGHTNESS_CTRL		0x00
@@ -383,6 +384,13 @@ static int lp855x_parse_dt(struct lp855x *lp)
 		pdata->rom_data = &rom[0];
 	}
 
+	pdata->supply = devm_regulator_get(dev, "power");
+	if (IS_ERR(pdata->supply)) {
+		if (PTR_ERR(pdata->supply) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+		pdata->supply = NULL;
+	}
+
 	lp->pdata = pdata;
 
 	return 0;
@@ -423,6 +431,14 @@ static int lp855x_probe(struct i2c_client *cl, const struct i2c_device_id *id)
 	else
 		lp->mode = REGISTER_BASED;
 
+	if (lp->pdata->supply) {
+		ret = regulator_enable(lp->pdata->supply);
+		if (ret < 0) {
+			dev_err(&cl->dev, "failed to enable supply: %d\n", ret);
+			return ret;
+		}
+	}
+
 	i2c_set_clientdata(cl, lp);
 
 	ret = lp855x_configure(lp);
@@ -454,6 +470,8 @@ static int lp855x_remove(struct i2c_client *cl)
 
 	lp->bl->props.brightness = 0;
 	backlight_update_status(lp->bl);
+	if (lp->pdata->supply)
+		regulator_disable(lp->pdata->supply);
 	sysfs_remove_group(&lp->dev->kobj, &lp855x_attr_group);
 
 	return 0;
diff --git a/include/linux/platform_data/lp855x.h b/include/linux/platform_data/lp855x.h
index 1b2ba24e4e0..9c7fd1efe49 100644
--- a/include/linux/platform_data/lp855x.h
+++ b/include/linux/platform_data/lp855x.h
@@ -136,6 +136,7 @@ struct lp855x_rom_data {
 		Only valid when mode is PWM_BASED.
  * @size_program : total size of lp855x_rom_data
  * @rom_data : list of new eeprom/eprom registers
+ * @supply : regulator that supplies 3V input
  */
 struct lp855x_platform_data {
 	const char *name;
@@ -144,6 +145,7 @@ struct lp855x_platform_data {
 	unsigned int period_ns;
 	int size_program;
 	struct lp855x_rom_data *rom_data;
+	struct regulator *supply;
 };
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From d4024af56f7c6cdb7e721994204fb07b2cda8be9 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 27 Nov 2014 21:19:02 +0200
Subject: virtio: add low-level APIs for feature bits

Add low level APIs to test/set/clear feature bits.
For use by transports, to make it easier to
write code independent of feature bit array format.

Note: APIs is prefixed with __ and has _bit suffix
to stress its low level nature.  It's for use by transports only:
drivers should use virtio_has_feature and never need to set/clear
features.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
 include/linux/virtio_config.h | 53 ++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 50 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 7f4ef66873e..d8e28a2a573 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -77,11 +77,47 @@ void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
 					 unsigned int fbit);
 
 /**
- * virtio_has_feature - helper to determine if this device has this feature.
+ * __virtio_test_bit - helper to test feature bits. For use by transports.
+ *                     Devices should normally use virtio_has_feature,
+ *                     which includes more checks.
  * @vdev: the device
  * @fbit: the feature bit
  */
-static inline bool virtio_has_feature(const struct virtio_device *vdev,
+static inline bool __virtio_test_bit(const struct virtio_device *vdev,
+				     unsigned int fbit)
+{
+	/* Did you forget to fix assumptions on max features? */
+	if (__builtin_constant_p(fbit))
+		BUILD_BUG_ON(fbit >= 32);
+	else
+		BUG_ON(fbit >= 32);
+
+	return test_bit(fbit, vdev->features);
+}
+
+/**
+ * __virtio_set_bit - helper to set feature bits. For use by transports.
+ * @vdev: the device
+ * @fbit: the feature bit
+ */
+static inline void __virtio_set_bit(struct virtio_device *vdev,
+				    unsigned int fbit)
+{
+	/* Did you forget to fix assumptions on max features? */
+	if (__builtin_constant_p(fbit))
+		BUILD_BUG_ON(fbit >= 32);
+	else
+		BUG_ON(fbit >= 32);
+
+	set_bit(fbit, vdev->features);
+}
+
+/**
+ * __virtio_clear_bit - helper to clear feature bits. For use by transports.
+ * @vdev: the device
+ * @fbit: the feature bit
+ */
+static inline void __virtio_clear_bit(struct virtio_device *vdev,
 				      unsigned int fbit)
 {
 	/* Did you forget to fix assumptions on max features? */
@@ -90,10 +126,21 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev,
 	else
 		BUG_ON(fbit >= 32);
 
+	clear_bit(fbit, vdev->features);
+}
+
+/**
+ * virtio_has_feature - helper to determine if this device has this feature.
+ * @vdev: the device
+ * @fbit: the feature bit
+ */
+static inline bool virtio_has_feature(const struct virtio_device *vdev,
+				      unsigned int fbit)
+{
 	if (fbit < VIRTIO_TRANSPORT_F_START)
 		virtio_check_driver_offered_feature(vdev, fbit);
 
-	return test_bit(fbit, vdev->features);
+	return __virtio_test_bit(vdev, fbit);
 }
 
 static inline
-- 
cgit v1.2.3-70-g09d2


From e16e12be34648777606a2c03a3526409b38f0e63 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 7 Oct 2014 16:39:42 +0200
Subject: virtio: use u32, not bitmap for features

It seemed like a good idea to use bitmap for features
in struct virtio_device, but it's actually a pain,
and seems to become even more painful when we get more
than 32 feature bits.  Just change it to a u32 for now.

Based on patch by Rusty.

Suggested-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
 drivers/char/virtio_console.c          |  2 +-
 drivers/lguest/lguest_device.c         |  8 ++++----
 drivers/misc/mic/card/mic_virtio.c     |  2 +-
 drivers/remoteproc/remoteproc_virtio.c |  2 +-
 drivers/s390/kvm/kvm_virtio.c          |  2 +-
 drivers/s390/kvm/virtio_ccw.c          | 23 +++++++++--------------
 drivers/virtio/virtio.c                | 10 +++++-----
 drivers/virtio/virtio_mmio.c           |  8 ++------
 drivers/virtio/virtio_pci.c            |  3 +--
 drivers/virtio/virtio_ring.c           |  2 +-
 include/linux/virtio.h                 |  3 +--
 include/linux/virtio_config.h          |  6 +++---
 tools/virtio/linux/virtio.h            | 22 +---------------------
 tools/virtio/linux/virtio_config.h     |  2 +-
 tools/virtio/virtio_test.c             |  5 ++---
 tools/virtio/vringh_test.c             | 16 ++++++++--------
 16 files changed, 42 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index cf7a561fad7..8d00aa7f60f 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -355,7 +355,7 @@ static inline bool use_multiport(struct ports_device *portdev)
 	 */
 	if (!portdev->vdev)
 		return 0;
-	return portdev->vdev->features[0] & (1 << VIRTIO_CONSOLE_F_MULTIPORT);
+	return __virtio_test_bit(portdev->vdev, VIRTIO_CONSOLE_F_MULTIPORT);
 }
 
 static DEFINE_SPINLOCK(dma_bufs_lock);
diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c
index d0a1d8a45c8..97aeb7dce5f 100644
--- a/drivers/lguest/lguest_device.c
+++ b/drivers/lguest/lguest_device.c
@@ -137,14 +137,14 @@ static void lg_finalize_features(struct virtio_device *vdev)
 	vring_transport_features(vdev);
 
 	/*
-	 * The vdev->feature array is a Linux bitmask: this isn't the same as a
-	 * the simple array of bits used by lguest devices for features.  So we
-	 * do this slow, manual conversion which is completely general.
+	 * Since lguest is currently x86-only, we're little-endian.  That
+	 * means we could just memcpy.  But it's not time critical, and in
+	 * case someone copies this code, we do it the slow, obvious way.
 	 */
 	memset(out_features, 0, desc->feature_len);
 	bits = min_t(unsigned, desc->feature_len, sizeof(vdev->features)) * 8;
 	for (i = 0; i < bits; i++) {
-		if (test_bit(i, vdev->features))
+		if (__virtio_test_bit(vdev, i))
 			out_features[i / 8] |= (1 << (i % 8));
 	}
 
diff --git a/drivers/misc/mic/card/mic_virtio.c b/drivers/misc/mic/card/mic_virtio.c
index e64794730e2..4f070ad1875 100644
--- a/drivers/misc/mic/card/mic_virtio.c
+++ b/drivers/misc/mic/card/mic_virtio.c
@@ -101,7 +101,7 @@ static void mic_finalize_features(struct virtio_device *vdev)
 	bits = min_t(unsigned, feature_len,
 		sizeof(vdev->features)) * 8;
 	for (i = 0; i < bits; i++) {
-		if (test_bit(i, vdev->features))
+		if (__virtio_test_bit(vdev, i))
 			iowrite8(ioread8(&out_features[i / 8]) | (1 << (i % 8)),
 				 &out_features[i / 8]);
 	}
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index a34b50690b4..dafaf38dac0 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -231,7 +231,7 @@ static void rproc_virtio_finalize_features(struct virtio_device *vdev)
 	 * Remember the finalized features of our vdev, and provide it
 	 * to the remote processor once it is powered on.
 	 */
-	rsc->gfeatures = vdev->features[0];
+	rsc->gfeatures = vdev->features;
 }
 
 static void rproc_virtio_get(struct virtio_device *vdev, unsigned offset,
diff --git a/drivers/s390/kvm/kvm_virtio.c b/drivers/s390/kvm/kvm_virtio.c
index 643129070c5..fcd312d0c01 100644
--- a/drivers/s390/kvm/kvm_virtio.c
+++ b/drivers/s390/kvm/kvm_virtio.c
@@ -106,7 +106,7 @@ static void kvm_finalize_features(struct virtio_device *vdev)
 	memset(out_features, 0, desc->feature_len);
 	bits = min_t(unsigned, desc->feature_len, sizeof(vdev->features)) * 8;
 	for (i = 0; i < bits; i++) {
-		if (test_bit(i, vdev->features))
+		if (__virtio_test_bit(vdev, i))
 			out_features[i / 8] |= (1 << (i % 8));
 	}
 }
diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c
index bda52f18e96..1dbee95838f 100644
--- a/drivers/s390/kvm/virtio_ccw.c
+++ b/drivers/s390/kvm/virtio_ccw.c
@@ -701,7 +701,6 @@ static void virtio_ccw_finalize_features(struct virtio_device *vdev)
 {
 	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
 	struct virtio_feature_desc *features;
-	int i;
 	struct ccw1 *ccw;
 
 	ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
@@ -715,19 +714,15 @@ static void virtio_ccw_finalize_features(struct virtio_device *vdev)
 	/* Give virtio_ring a chance to accept features. */
 	vring_transport_features(vdev);
 
-	for (i = 0; i < sizeof(*vdev->features) / sizeof(features->features);
-	     i++) {
-		int highbits = i % 2 ? 32 : 0;
-		features->index = i;
-		features->features = cpu_to_le32(vdev->features[i / 2]
-						 >> highbits);
-		/* Write the feature bits to the host. */
-		ccw->cmd_code = CCW_CMD_WRITE_FEAT;
-		ccw->flags = 0;
-		ccw->count = sizeof(*features);
-		ccw->cda = (__u32)(unsigned long)features;
-		ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_FEAT);
-	}
+	features->index = 0;
+	features->features = cpu_to_le32(vdev->features);
+	/* Write the feature bits to the host. */
+	ccw->cmd_code = CCW_CMD_WRITE_FEAT;
+	ccw->flags = 0;
+	ccw->count = sizeof(*features);
+	ccw->cda = (__u32)(unsigned long)features;
+	ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_FEAT);
+
 out_free:
 	kfree(features);
 	kfree(ccw);
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index df598dd8c5c..2b9aafb4d67 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -49,9 +49,9 @@ static ssize_t features_show(struct device *_d,
 
 	/* We actually represent this as a bitstring, as it could be
 	 * arbitrary length in future. */
-	for (i = 0; i < ARRAY_SIZE(dev->features)*BITS_PER_LONG; i++)
+	for (i = 0; i < sizeof(dev->features)*8; i++)
 		len += sprintf(buf+len, "%c",
-			       test_bit(i, dev->features) ? '1' : '0');
+			       __virtio_test_bit(dev, i) ? '1' : '0');
 	len += sprintf(buf+len, "\n");
 	return len;
 }
@@ -168,18 +168,18 @@ static int virtio_dev_probe(struct device *_d)
 	device_features = dev->config->get_features(dev);
 
 	/* Features supported by both device and driver into dev->features. */
-	memset(dev->features, 0, sizeof(dev->features));
+	dev->features = 0;
 	for (i = 0; i < drv->feature_table_size; i++) {
 		unsigned int f = drv->feature_table[i];
 		BUG_ON(f >= 32);
 		if (device_features & (1 << f))
-			set_bit(f, dev->features);
+			__virtio_set_bit(dev, f);
 	}
 
 	/* Transport features always preserved to pass to finalize_features. */
 	for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++)
 		if (device_features & (1 << i))
-			set_bit(i, dev->features);
+			__virtio_set_bit(dev, i);
 
 	dev->config->finalize_features(dev);
 
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index ef9a1650bb8..eb5b0e2b434 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -155,16 +155,12 @@ static u32 vm_get_features(struct virtio_device *vdev)
 static void vm_finalize_features(struct virtio_device *vdev)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
-	int i;
 
 	/* Give virtio_ring a chance to accept features. */
 	vring_transport_features(vdev);
 
-	for (i = 0; i < ARRAY_SIZE(vdev->features); i++) {
-		writel(i, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES_SEL);
-		writel(vdev->features[i],
-				vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES);
-	}
+	writel(0, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES_SEL);
+	writel(vdev->features, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES);
 }
 
 static void vm_get(struct virtio_device *vdev, unsigned offset,
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index d34ebfa604f..4e112c15848 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -120,8 +120,7 @@ static void vp_finalize_features(struct virtio_device *vdev)
 	vring_transport_features(vdev);
 
 	/* We only support 32 feature bits. */
-	BUILD_BUG_ON(ARRAY_SIZE(vdev->features) != 1);
-	iowrite32(vdev->features[0], vp_dev->ioaddr+VIRTIO_PCI_GUEST_FEATURES);
+	iowrite32(vdev->features, vp_dev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
 }
 
 /* virtio config->get() implementation */
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 3b1f89b6e74..839247cd826 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -781,7 +781,7 @@ void vring_transport_features(struct virtio_device *vdev)
 			break;
 		default:
 			/* We don't understand this bit. */
-			clear_bit(i, vdev->features);
+			__virtio_clear_bit(vdev, i);
 		}
 	}
 }
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 65261a7244f..7828a7f47c2 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -101,8 +101,7 @@ struct virtio_device {
 	const struct virtio_config_ops *config;
 	const struct vringh_config_ops *vringh_config;
 	struct list_head vqs;
-	/* Note that this is a Linux set_bit-style bitmap. */
-	unsigned long features[1];
+	u32 features;
 	void *priv;
 };
 
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index d8e28a2a573..ffc2ae04879 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -92,7 +92,7 @@ static inline bool __virtio_test_bit(const struct virtio_device *vdev,
 	else
 		BUG_ON(fbit >= 32);
 
-	return test_bit(fbit, vdev->features);
+	return vdev->features & BIT(fbit);
 }
 
 /**
@@ -109,7 +109,7 @@ static inline void __virtio_set_bit(struct virtio_device *vdev,
 	else
 		BUG_ON(fbit >= 32);
 
-	set_bit(fbit, vdev->features);
+	vdev->features |= BIT(fbit);
 }
 
 /**
@@ -126,7 +126,7 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev,
 	else
 		BUG_ON(fbit >= 32);
 
-	clear_bit(fbit, vdev->features);
+	vdev->features &= ~BIT(fbit);
 }
 
 /**
diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h
index 5a2d1f0f6bc..72bff70bfee 100644
--- a/tools/virtio/linux/virtio.h
+++ b/tools/virtio/linux/virtio.h
@@ -6,31 +6,11 @@
 /* TODO: empty stubs for now. Broken but enough for virtio_ring.c */
 #define list_add_tail(a, b) do {} while (0)
 #define list_del(a) do {} while (0)
-
-#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
-#define BITS_PER_BYTE		8
-#define BITS_PER_LONG (sizeof(long) * BITS_PER_BYTE)
-#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
-
-/* TODO: Not atomic as it should be:
- * we don't use this for anything important. */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
-{
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-
-	*p &= ~mask;
-}
-
-static inline int test_bit(int nr, const volatile unsigned long *addr)
-{
-        return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
-}
 /* end of stubs */
 
 struct virtio_device {
 	void *dev;
-	unsigned long features[1];
+	u32 features;
 };
 
 struct virtqueue {
diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h
index 5049967f99f..83b27e8e9d7 100644
--- a/tools/virtio/linux/virtio_config.h
+++ b/tools/virtio/linux/virtio_config.h
@@ -2,5 +2,5 @@
 #define VIRTIO_TRANSPORT_F_END		32
 
 #define virtio_has_feature(dev, feature) \
-	test_bit((feature), (dev)->features)
+	(__virtio_test_bit((dev), feature))
 
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index 00ea679b382..db3437c641a 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -60,7 +60,7 @@ void vhost_vq_setup(struct vdev_info *dev, struct vq_info *info)
 {
 	struct vhost_vring_state state = { .index = info->idx };
 	struct vhost_vring_file file = { .index = info->idx };
-	unsigned long long features = dev->vdev.features[0];
+	unsigned long long features = dev->vdev.features;
 	struct vhost_vring_addr addr = {
 		.index = info->idx,
 		.desc_user_addr = (uint64_t)(unsigned long)info->vring.desc,
@@ -113,8 +113,7 @@ static void vdev_info_init(struct vdev_info* dev, unsigned long long features)
 {
 	int r;
 	memset(dev, 0, sizeof *dev);
-	dev->vdev.features[0] = features;
-	dev->vdev.features[1] = features >> 32;
+	dev->vdev.features = features;
 	dev->buf_size = 1024;
 	dev->buf = malloc(dev->buf_size);
 	assert(dev->buf);
diff --git a/tools/virtio/vringh_test.c b/tools/virtio/vringh_test.c
index 14a4f4cab5b..9d4b1bca54b 100644
--- a/tools/virtio/vringh_test.c
+++ b/tools/virtio/vringh_test.c
@@ -304,7 +304,7 @@ static int parallel_test(unsigned long features,
 		close(to_guest[1]);
 		close(to_host[0]);
 
-		gvdev.vdev.features[0] = features;
+		gvdev.vdev.features = features;
 		gvdev.to_host_fd = to_host[1];
 		gvdev.notifies = 0;
 
@@ -449,13 +449,13 @@ int main(int argc, char *argv[])
 	bool fast_vringh = false, parallel = false;
 
 	getrange = getrange_iov;
-	vdev.features[0] = 0;
+	vdev.features = 0;
 
 	while (argv[1]) {
 		if (strcmp(argv[1], "--indirect") == 0)
-			vdev.features[0] |= (1 << VIRTIO_RING_F_INDIRECT_DESC);
+			__virtio_set_bit(&vdev, VIRTIO_RING_F_INDIRECT_DESC);
 		else if (strcmp(argv[1], "--eventidx") == 0)
-			vdev.features[0] |= (1 << VIRTIO_RING_F_EVENT_IDX);
+			__virtio_set_bit(&vdev, VIRTIO_RING_F_EVENT_IDX);
 		else if (strcmp(argv[1], "--slow-range") == 0)
 			getrange = getrange_slow;
 		else if (strcmp(argv[1], "--fast-vringh") == 0)
@@ -468,7 +468,7 @@ int main(int argc, char *argv[])
 	}
 
 	if (parallel)
-		return parallel_test(vdev.features[0], getrange, fast_vringh);
+		return parallel_test(vdev.features, getrange, fast_vringh);
 
 	if (posix_memalign(&__user_addr_min, PAGE_SIZE, USER_MEM) != 0)
 		abort();
@@ -483,7 +483,7 @@ int main(int argc, char *argv[])
 
 	/* Set up host side. */
 	vring_init(&vrh.vring, RINGSIZE, __user_addr_min, ALIGN);
-	vringh_init_user(&vrh, vdev.features[0], RINGSIZE, true,
+	vringh_init_user(&vrh, vdev.features, RINGSIZE, true,
 			 vrh.vring.desc, vrh.vring.avail, vrh.vring.used);
 
 	/* No descriptor to get yet... */
@@ -652,13 +652,13 @@ int main(int argc, char *argv[])
 	}
 
 	/* Test weird (but legal!) indirect. */
-	if (vdev.features[0] & (1 << VIRTIO_RING_F_INDIRECT_DESC)) {
+	if (__virtio_test_bit(&vdev, VIRTIO_RING_F_INDIRECT_DESC)) {
 		char *data = __user_addr_max - USER_MEM/4;
 		struct vring_desc *d = __user_addr_max - USER_MEM/2;
 		struct vring vring;
 
 		/* Force creation of direct, which we modify. */
-		vdev.features[0] &= ~(1 << VIRTIO_RING_F_INDIRECT_DESC);
+		__virtio_clear_bit(&vdev, VIRTIO_RING_F_INDIRECT_DESC);
 		vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true,
 					 __user_addr_min,
 					 never_notify_host,
-- 
cgit v1.2.3-70-g09d2


From d025477368792b272802146a86e41f81a54d8a19 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 7 Oct 2014 16:39:43 +0200
Subject: virtio: add support for 64 bit features.

Change u32 to u64, and use BIT_ULL and 1ULL everywhere.

Note: transports are unchanged, and only set low 32 bit.
This guarantees that no transport sets e.g. VERSION_1
by mistake without proper support.

Based on patch by Rusty.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
 drivers/lguest/lguest_device.c         |  2 +-
 drivers/misc/mic/card/mic_virtio.c     |  2 +-
 drivers/remoteproc/remoteproc_virtio.c |  2 +-
 drivers/s390/kvm/kvm_virtio.c          |  2 +-
 drivers/s390/kvm/virtio_ccw.c          |  2 +-
 drivers/virtio/virtio.c                |  8 ++++----
 drivers/virtio/virtio_mmio.c           |  2 +-
 drivers/virtio/virtio_pci.c            |  2 +-
 include/linux/virtio.h                 |  2 +-
 include/linux/virtio_config.h          | 20 ++++++++++----------
 tools/virtio/linux/virtio.h            |  2 +-
 11 files changed, 23 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c
index 97aeb7dce5f..d81170a78a8 100644
--- a/drivers/lguest/lguest_device.c
+++ b/drivers/lguest/lguest_device.c
@@ -94,7 +94,7 @@ static unsigned desc_size(const struct lguest_device_desc *desc)
 }
 
 /* This gets the device's feature bits. */
-static u32 lg_get_features(struct virtio_device *vdev)
+static u64 lg_get_features(struct virtio_device *vdev)
 {
 	unsigned int i;
 	u32 features = 0;
diff --git a/drivers/misc/mic/card/mic_virtio.c b/drivers/misc/mic/card/mic_virtio.c
index d5da9ff646c..f5e756132bd 100644
--- a/drivers/misc/mic/card/mic_virtio.c
+++ b/drivers/misc/mic/card/mic_virtio.c
@@ -68,7 +68,7 @@ static inline struct device *mic_dev(struct mic_vdev *mvdev)
 }
 
 /* This gets the device's feature bits. */
-static u32 mic_get_features(struct virtio_device *vdev)
+static u64 mic_get_features(struct virtio_device *vdev)
 {
 	unsigned int i, bits;
 	u32 features = 0;
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index dafaf38dac0..62897db1331 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -207,7 +207,7 @@ static void rproc_virtio_reset(struct virtio_device *vdev)
 }
 
 /* provide the vdev features as retrieved from the firmware */
-static u32 rproc_virtio_get_features(struct virtio_device *vdev)
+static u64 rproc_virtio_get_features(struct virtio_device *vdev)
 {
 	struct rproc_vdev *rvdev = vdev_to_rvdev(vdev);
 	struct fw_rsc_vdev *rsc;
diff --git a/drivers/s390/kvm/kvm_virtio.c b/drivers/s390/kvm/kvm_virtio.c
index fcd312d0c01..2336c7e3b0c 100644
--- a/drivers/s390/kvm/kvm_virtio.c
+++ b/drivers/s390/kvm/kvm_virtio.c
@@ -80,7 +80,7 @@ static unsigned desc_size(const struct kvm_device_desc *desc)
 }
 
 /* This gets the device's feature bits. */
-static u32 kvm_get_features(struct virtio_device *vdev)
+static u64 kvm_get_features(struct virtio_device *vdev)
 {
 	unsigned int i;
 	u32 features = 0;
diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c
index 1dbee95838f..56d78956a8c 100644
--- a/drivers/s390/kvm/virtio_ccw.c
+++ b/drivers/s390/kvm/virtio_ccw.c
@@ -660,7 +660,7 @@ static void virtio_ccw_reset(struct virtio_device *vdev)
 	kfree(ccw);
 }
 
-static u32 virtio_ccw_get_features(struct virtio_device *vdev)
+static u64 virtio_ccw_get_features(struct virtio_device *vdev)
 {
 	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
 	struct virtio_feature_desc *features;
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 2b9aafb4d67..746d350c806 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -159,7 +159,7 @@ static int virtio_dev_probe(struct device *_d)
 	int err, i;
 	struct virtio_device *dev = dev_to_virtio(_d);
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
-	u32 device_features;
+	u64 device_features;
 
 	/* We have a driver! */
 	add_status(dev, VIRTIO_CONFIG_S_DRIVER);
@@ -171,14 +171,14 @@ static int virtio_dev_probe(struct device *_d)
 	dev->features = 0;
 	for (i = 0; i < drv->feature_table_size; i++) {
 		unsigned int f = drv->feature_table[i];
-		BUG_ON(f >= 32);
-		if (device_features & (1 << f))
+		BUG_ON(f >= 64);
+		if (device_features & (1ULL << f))
 			__virtio_set_bit(dev, f);
 	}
 
 	/* Transport features always preserved to pass to finalize_features. */
 	for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++)
-		if (device_features & (1 << i))
+		if (device_features & (1ULL << i))
 			__virtio_set_bit(dev, i);
 
 	dev->config->finalize_features(dev);
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index eb5b0e2b434..c63d0efa947 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -142,7 +142,7 @@ struct virtio_mmio_vq_info {
 
 /* Configuration interface */
 
-static u32 vm_get_features(struct virtio_device *vdev)
+static u64 vm_get_features(struct virtio_device *vdev)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 4e112c15848..7e0efa7fc38 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -102,7 +102,7 @@ static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
 }
 
 /* virtio config->get_features() implementation */
-static u32 vp_get_features(struct virtio_device *vdev)
+static u64 vp_get_features(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 7828a7f47c2..149284e5196 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -101,7 +101,7 @@ struct virtio_device {
 	const struct virtio_config_ops *config;
 	const struct vringh_config_ops *vringh_config;
 	struct list_head vqs;
-	u32 features;
+	u64 features;
 	void *priv;
 };
 
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index ffc2ae04879..f5178843957 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -66,7 +66,7 @@ struct virtio_config_ops {
 			vq_callback_t *callbacks[],
 			const char *names[]);
 	void (*del_vqs)(struct virtio_device *);
-	u32 (*get_features)(struct virtio_device *vdev);
+	u64 (*get_features)(struct virtio_device *vdev);
 	void (*finalize_features)(struct virtio_device *vdev);
 	const char *(*bus_name)(struct virtio_device *vdev);
 	int (*set_vq_affinity)(struct virtqueue *vq, int cpu);
@@ -88,11 +88,11 @@ static inline bool __virtio_test_bit(const struct virtio_device *vdev,
 {
 	/* Did you forget to fix assumptions on max features? */
 	if (__builtin_constant_p(fbit))
-		BUILD_BUG_ON(fbit >= 32);
+		BUILD_BUG_ON(fbit >= 64);
 	else
-		BUG_ON(fbit >= 32);
+		BUG_ON(fbit >= 64);
 
-	return vdev->features & BIT(fbit);
+	return vdev->features & BIT_ULL(fbit);
 }
 
 /**
@@ -105,11 +105,11 @@ static inline void __virtio_set_bit(struct virtio_device *vdev,
 {
 	/* Did you forget to fix assumptions on max features? */
 	if (__builtin_constant_p(fbit))
-		BUILD_BUG_ON(fbit >= 32);
+		BUILD_BUG_ON(fbit >= 64);
 	else
-		BUG_ON(fbit >= 32);
+		BUG_ON(fbit >= 64);
 
-	vdev->features |= BIT(fbit);
+	vdev->features |= BIT_ULL(fbit);
 }
 
 /**
@@ -122,11 +122,11 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev,
 {
 	/* Did you forget to fix assumptions on max features? */
 	if (__builtin_constant_p(fbit))
-		BUILD_BUG_ON(fbit >= 32);
+		BUILD_BUG_ON(fbit >= 64);
 	else
-		BUG_ON(fbit >= 32);
+		BUG_ON(fbit >= 64);
 
-	vdev->features &= ~BIT(fbit);
+	vdev->features &= ~BIT_ULL(fbit);
 }
 
 /**
diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h
index 72bff70bfee..8eb6421761c 100644
--- a/tools/virtio/linux/virtio.h
+++ b/tools/virtio/linux/virtio.h
@@ -10,7 +10,7 @@
 
 struct virtio_device {
 	void *dev;
-	u32 features;
+	u64 features;
 };
 
 struct virtqueue {
-- 
cgit v1.2.3-70-g09d2


From 4ec22faeb2a165b6ce7009f91309046010b3f282 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 22 Oct 2014 15:49:34 +0300
Subject: virtio: add virtio 1.0 feature bit

Based on original patches by Rusty Russell, Thomas Huth
and Cornelia Huck.

Note: at this time, we do not negotiate this feature bit
in core, drivers have to declare VERSION_1 support explicitly.

For this reason we treat this bit as a device bit
and not as a transport bit for now.

After all drivers are converted, we will be able to
move VERSION_1 to core and drop it from all drivers.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
 include/uapi/linux/virtio_config.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index 3ce768c6910..80e7381e3f1 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -54,4 +54,7 @@
 /* Can the device handle any descriptor layout? */
 #define VIRTIO_F_ANY_LAYOUT		27
 
+/* v1.0 compliant. */
+#define VIRTIO_F_VERSION_1		32
+
 #endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */
-- 
cgit v1.2.3-70-g09d2


From eef960a04354d13426c43a4e3750a5e2b383040c Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 22 Oct 2014 15:35:56 +0300
Subject: virtio: memory access APIs

virtio 1.0 makes all memory structures LE, so
we need APIs to conditionally do a byteswap on BE
architectures.

To make it easier to check code statically,
add virtio specific types for multi-byte integers
in memory.

Add low level wrappers that do a byteswap conditionally, these will be
useful e.g. for vhost.  Add high level wrappers that
query device endian-ness and act accordingly.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
 include/linux/virtio_byteorder.h  | 59 +++++++++++++++++++++++++++++++++++++++
 include/linux/virtio_config.h     | 32 +++++++++++++++++++++
 include/uapi/linux/Kbuild         |  1 +
 include/uapi/linux/virtio_ring.h  | 45 ++++++++++++++---------------
 include/uapi/linux/virtio_types.h | 46 ++++++++++++++++++++++++++++++
 5 files changed, 161 insertions(+), 22 deletions(-)
 create mode 100644 include/linux/virtio_byteorder.h
 create mode 100644 include/uapi/linux/virtio_types.h

(limited to 'include')

diff --git a/include/linux/virtio_byteorder.h b/include/linux/virtio_byteorder.h
new file mode 100644
index 00000000000..51865d05b26
--- /dev/null
+++ b/include/linux/virtio_byteorder.h
@@ -0,0 +1,59 @@
+#ifndef _LINUX_VIRTIO_BYTEORDER_H
+#define _LINUX_VIRTIO_BYTEORDER_H
+#include <linux/types.h>
+#include <uapi/linux/virtio_types.h>
+
+/*
+ * Low-level memory accessors for handling virtio in modern little endian and in
+ * compatibility native endian format.
+ */
+
+static inline u16 __virtio16_to_cpu(bool little_endian, __virtio16 val)
+{
+	if (little_endian)
+		return le16_to_cpu((__force __le16)val);
+	else
+		return (__force u16)val;
+}
+
+static inline __virtio16 __cpu_to_virtio16(bool little_endian, u16 val)
+{
+	if (little_endian)
+		return (__force __virtio16)cpu_to_le16(val);
+	else
+		return (__force __virtio16)val;
+}
+
+static inline u32 __virtio32_to_cpu(bool little_endian, __virtio32 val)
+{
+	if (little_endian)
+		return le32_to_cpu((__force __le32)val);
+	else
+		return (__force u32)val;
+}
+
+static inline __virtio32 __cpu_to_virtio32(bool little_endian, u32 val)
+{
+	if (little_endian)
+		return (__force __virtio32)cpu_to_le32(val);
+	else
+		return (__force __virtio32)val;
+}
+
+static inline u64 __virtio64_to_cpu(bool little_endian, __virtio64 val)
+{
+	if (little_endian)
+		return le64_to_cpu((__force __le64)val);
+	else
+		return (__force u64)val;
+}
+
+static inline __virtio64 __cpu_to_virtio64(bool little_endian, u64 val)
+{
+	if (little_endian)
+		return (__force __virtio64)cpu_to_le64(val);
+	else
+		return (__force __virtio64)val;
+}
+
+#endif /* _LINUX_VIRTIO_BYTEORDER */
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index f5178843957..02f0acb549d 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -4,6 +4,7 @@
 #include <linux/err.h>
 #include <linux/bug.h>
 #include <linux/virtio.h>
+#include <linux/virtio_byteorder.h>
 #include <uapi/linux/virtio_config.h>
 
 /**
@@ -199,6 +200,37 @@ int virtqueue_set_affinity(struct virtqueue *vq, int cpu)
 	return 0;
 }
 
+/* Memory accessors */
+static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val)
+{
+	return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val)
+{
+	return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val)
+{
+	return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val)
+{
+	return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val)
+{
+	return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
+{
+	return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
 /* Config space accessors. */
 #define virtio_cread(vdev, structname, member, ptr)			\
 	do {								\
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 8523f9bb72f..615f96a6022 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -423,6 +423,7 @@ header-y += virtio_blk.h
 header-y += virtio_config.h
 header-y += virtio_console.h
 header-y += virtio_ids.h
+header-y += virtio_types.h
 header-y += virtio_net.h
 header-y += virtio_pci.h
 header-y += virtio_ring.h
diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
index a99f9b7caa6..61c818a7fe7 100644
--- a/include/uapi/linux/virtio_ring.h
+++ b/include/uapi/linux/virtio_ring.h
@@ -32,6 +32,7 @@
  *
  * Copyright Rusty Russell IBM Corporation 2007. */
 #include <linux/types.h>
+#include <linux/virtio_types.h>
 
 /* This marks a buffer as continuing via the next field. */
 #define VRING_DESC_F_NEXT	1
@@ -61,32 +62,32 @@
 /* Virtio ring descriptors: 16 bytes.  These can chain together via "next". */
 struct vring_desc {
 	/* Address (guest-physical). */
-	__u64 addr;
+	__virtio64 addr;
 	/* Length. */
-	__u32 len;
+	__virtio32 len;
 	/* The flags as indicated above. */
-	__u16 flags;
+	__virtio16 flags;
 	/* We chain unused descriptors via this, too */
-	__u16 next;
+	__virtio16 next;
 };
 
 struct vring_avail {
-	__u16 flags;
-	__u16 idx;
-	__u16 ring[];
+	__virtio16 flags;
+	__virtio16 idx;
+	__virtio16 ring[];
 };
 
 /* u32 is used here for ids for padding reasons. */
 struct vring_used_elem {
 	/* Index of start of used descriptor chain. */
-	__u32 id;
+	__virtio32 id;
 	/* Total length of the descriptor chain which was used (written to) */
-	__u32 len;
+	__virtio32 len;
 };
 
 struct vring_used {
-	__u16 flags;
-	__u16 idx;
+	__virtio16 flags;
+	__virtio16 idx;
 	struct vring_used_elem ring[];
 };
 
@@ -109,25 +110,25 @@ struct vring {
  *	struct vring_desc desc[num];
  *
  *	// A ring of available descriptor heads with free-running index.
- *	__u16 avail_flags;
- *	__u16 avail_idx;
- *	__u16 available[num];
- *	__u16 used_event_idx;
+ *	__virtio16 avail_flags;
+ *	__virtio16 avail_idx;
+ *	__virtio16 available[num];
+ *	__virtio16 used_event_idx;
  *
  *	// Padding to the next align boundary.
  *	char pad[];
  *
  *	// A ring of used descriptor heads with free-running index.
- *	__u16 used_flags;
- *	__u16 used_idx;
+ *	__virtio16 used_flags;
+ *	__virtio16 used_idx;
  *	struct vring_used_elem used[num];
- *	__u16 avail_event_idx;
+ *	__virtio16 avail_event_idx;
  * };
  */
 /* We publish the used event index at the end of the available ring, and vice
  * versa. They are at the end for backwards compatibility. */
 #define vring_used_event(vr) ((vr)->avail->ring[(vr)->num])
-#define vring_avail_event(vr) (*(__u16 *)&(vr)->used->ring[(vr)->num])
+#define vring_avail_event(vr) (*(__virtio16 *)&(vr)->used->ring[(vr)->num])
 
 static inline void vring_init(struct vring *vr, unsigned int num, void *p,
 			      unsigned long align)
@@ -135,15 +136,15 @@ static inline void vring_init(struct vring *vr, unsigned int num, void *p,
 	vr->num = num;
 	vr->desc = p;
 	vr->avail = p + num*sizeof(struct vring_desc);
-	vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + sizeof(__u16)
+	vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + sizeof(__virtio16)
 		+ align-1) & ~(align - 1));
 }
 
 static inline unsigned vring_size(unsigned int num, unsigned long align)
 {
-	return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num)
+	return ((sizeof(struct vring_desc) * num + sizeof(__virtio16) * (3 + num)
 		 + align - 1) & ~(align - 1))
-		+ sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num;
+		+ sizeof(__virtio16) * 3 + sizeof(struct vring_used_elem) * num;
 }
 
 /* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */
diff --git a/include/uapi/linux/virtio_types.h b/include/uapi/linux/virtio_types.h
new file mode 100644
index 00000000000..e845e8c4cbe
--- /dev/null
+++ b/include/uapi/linux/virtio_types.h
@@ -0,0 +1,46 @@
+#ifndef _UAPI_LINUX_VIRTIO_TYPES_H
+#define _UAPI_LINUX_VIRTIO_TYPES_H
+/* Type definitions for virtio implementations.
+ *
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ * Copyright (C) 2014 Red Hat, Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ */
+#include <linux/types.h>
+
+/*
+ * __virtio{16,32,64} have the following meaning:
+ * - __u{16,32,64} for virtio devices in legacy mode, accessed in native endian
+ * - __le{16,32,64} for standard-compliant virtio devices
+ */
+
+typedef __u16 __bitwise__ __virtio16;
+typedef __u32 __bitwise__ __virtio32;
+typedef __u64 __bitwise__ __virtio64;
+
+#endif /* _UAPI_LINUX_VIRTIO_TYPES_H */
-- 
cgit v1.2.3-70-g09d2


From 92e6d7438ee631aac85258ee3d4de8c860d8c32f Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 22 Oct 2014 16:59:01 +0300
Subject: virtio_config: endian conversion for v1.0

We (ab)use virtio conversion functions for device-specific
config space accesses.

Based on original patches by Cornelia and Rusty.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.com>
---
 include/linux/virtio_config.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 02f0acb549d..1fa5faa2644 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -318,12 +318,13 @@ static inline u16 virtio_cread16(struct virtio_device *vdev,
 {
 	u16 ret;
 	vdev->config->get(vdev, offset, &ret, sizeof(ret));
-	return ret;
+	return virtio16_to_cpu(vdev, (__force __virtio16)ret);
 }
 
 static inline void virtio_cwrite16(struct virtio_device *vdev,
 				   unsigned int offset, u16 val)
 {
+	val = (__force u16)cpu_to_virtio16(vdev, val);
 	vdev->config->set(vdev, offset, &val, sizeof(val));
 }
 
@@ -332,12 +333,13 @@ static inline u32 virtio_cread32(struct virtio_device *vdev,
 {
 	u32 ret;
 	vdev->config->get(vdev, offset, &ret, sizeof(ret));
-	return ret;
+	return virtio32_to_cpu(vdev, (__force __virtio32)ret);
 }
 
 static inline void virtio_cwrite32(struct virtio_device *vdev,
 				   unsigned int offset, u32 val)
 {
+	val = (__force u32)cpu_to_virtio32(vdev, val);
 	vdev->config->set(vdev, offset, &val, sizeof(val));
 }
 
@@ -346,12 +348,13 @@ static inline u64 virtio_cread64(struct virtio_device *vdev,
 {
 	u64 ret;
 	vdev->config->get(vdev, offset, &ret, sizeof(ret));
-	return ret;
+	return virtio64_to_cpu(vdev, (__force __virtio64)ret);
 }
 
 static inline void virtio_cwrite64(struct virtio_device *vdev,
 				   unsigned int offset, u64 val)
 {
+	val = (__force u64)cpu_to_virtio64(vdev, val);
 	vdev->config->set(vdev, offset, &val, sizeof(val));
 }
 
-- 
cgit v1.2.3-70-g09d2


From 890626521503318d7ac92a4a3b9feba55c0131ec Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Date: Tue, 7 Oct 2014 16:39:47 +0200
Subject: virtio: allow transports to get avail/used addresses

For virtio-1, we can theoretically have a more complex virtqueue
layout with avail and used buffers not on a contiguous memory area
with the descriptor table. For now, it's fine for a transport driver
to stay with the old layout: It needs, however, a way to access
the locations of the avail/used rings so it can register them with
the host.

Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_ring.c | 16 ++++++++++++++++
 include/linux/virtio.h       |  3 +++
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 0d3c7373765..55532a43ead 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -827,4 +827,20 @@ void virtio_break_device(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(virtio_break_device);
 
+void *virtqueue_get_avail(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return vq->vring.avail;
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_avail);
+
+void *virtqueue_get_used(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return vq->vring.used;
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_used);
+
 MODULE_LICENSE("GPL");
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 149284e5196..d6359a5d5d4 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -75,6 +75,9 @@ unsigned int virtqueue_get_vring_size(struct virtqueue *vq);
 
 bool virtqueue_is_broken(struct virtqueue *vq);
 
+void *virtqueue_get_avail(struct virtqueue *vq);
+void *virtqueue_get_used(struct virtqueue *vq);
+
 /**
  * virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus
-- 
cgit v1.2.3-70-g09d2


From cb3f6d9da49929797f806b4e91ec005e6fc2e9c2 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 22 Oct 2014 17:41:38 +0300
Subject: virtio: set FEATURES_OK

set FEATURES_OK as per virtio 1.0 spec

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
 drivers/virtio/virtio.c            | 29 ++++++++++++++++++++++-------
 include/uapi/linux/virtio_config.h |  2 ++
 2 files changed, 24 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 746d350c806..9248125d29c 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -160,6 +160,7 @@ static int virtio_dev_probe(struct device *_d)
 	struct virtio_device *dev = dev_to_virtio(_d);
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 	u64 device_features;
+	unsigned status;
 
 	/* We have a driver! */
 	add_status(dev, VIRTIO_CONFIG_S_DRIVER);
@@ -183,18 +184,32 @@ static int virtio_dev_probe(struct device *_d)
 
 	dev->config->finalize_features(dev);
 
+	if (virtio_has_feature(dev, VIRTIO_F_VERSION_1)) {
+		add_status(dev, VIRTIO_CONFIG_S_FEATURES_OK);
+		status = dev->config->get_status(dev);
+		if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) {
+			dev_err(_d, "virtio: device refuses features: %x\n",
+			       status);
+			err = -ENODEV;
+			goto err;
+		}
+	}
+
 	err = drv->probe(dev);
 	if (err)
-		add_status(dev, VIRTIO_CONFIG_S_FAILED);
-	else {
-		add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
-		if (drv->scan)
-			drv->scan(dev);
+		goto err;
 
-		virtio_config_enable(dev);
-	}
+	add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
+	if (drv->scan)
+		drv->scan(dev);
+
+	virtio_config_enable(dev);
 
+	return 0;
+err:
+	add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return err;
+
 }
 
 static int virtio_dev_remove(struct device *_d)
diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index 80e7381e3f1..4d05671fbae 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -38,6 +38,8 @@
 #define VIRTIO_CONFIG_S_DRIVER		2
 /* Driver has used its parts of the config, and is happy */
 #define VIRTIO_CONFIG_S_DRIVER_OK	4
+/* Driver has finished configuring features */
+#define VIRTIO_CONFIG_S_FEATURES_OK	8
 /* We've given up on this device. */
 #define VIRTIO_CONFIG_S_FAILED		0x80
 
-- 
cgit v1.2.3-70-g09d2


From b3bb62d11950eb6ac87403cacd667f84fa9495bc Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 23 Oct 2014 18:07:47 +0300
Subject: virtio: add legacy feature table support

virtio-blk has some legacy feature bits that modern drivers
must not negotiate, but are needed for old legacy hosts
(that e.g. don't support virtio-scsi).
Allow a separate legacy feature table for such cases.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
 drivers/virtio/virtio.c | 25 ++++++++++++++++++++++++-
 include/linux/virtio.h  |  4 ++++
 2 files changed, 28 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 3e78f4bcfa8..f9ad99c8b35 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -113,6 +113,13 @@ void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
 	for (i = 0; i < drv->feature_table_size; i++)
 		if (drv->feature_table[i] == fbit)
 			return;
+
+	if (drv->feature_table_legacy) {
+		for (i = 0; i < drv->feature_table_size_legacy; i++)
+			if (drv->feature_table_legacy[i] == fbit)
+				return;
+	}
+
 	BUG();
 }
 EXPORT_SYMBOL_GPL(virtio_check_driver_offered_feature);
@@ -161,6 +168,7 @@ static int virtio_dev_probe(struct device *_d)
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 	u64 device_features;
 	u64 driver_features;
+	u64 driver_features_legacy;
 	unsigned status;
 
 	/* We have a driver! */
@@ -177,7 +185,22 @@ static int virtio_dev_probe(struct device *_d)
 		driver_features |= (1ULL << f);
 	}
 
-	dev->features = driver_features & device_features;
+	/* Some drivers have a separate feature table for virtio v1.0 */
+	if (drv->feature_table_legacy) {
+		driver_features_legacy = 0;
+		for (i = 0; i < drv->feature_table_size_legacy; i++) {
+			unsigned int f = drv->feature_table_legacy[i];
+			BUG_ON(f >= 64);
+			driver_features_legacy |= (1ULL << f);
+		}
+	} else {
+		driver_features_legacy = driver_features;
+	}
+
+	if (driver_features & device_features & (1ULL << VIRTIO_F_VERSION_1))
+		dev->features = driver_features & device_features;
+	else
+		dev->features = driver_features_legacy & device_features;
 
 	/* Transport features always preserved to pass to finalize_features. */
 	for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++)
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index d6359a5d5d4..f70411eb9d2 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -130,6 +130,8 @@ int virtio_device_restore(struct virtio_device *dev);
  * @id_table: the ids serviced by this driver.
  * @feature_table: an array of feature numbers supported by this driver.
  * @feature_table_size: number of entries in the feature table array.
+ * @feature_table_legacy: same as feature_table but when working in legacy mode.
+ * @feature_table_size_legacy: number of entries in feature table legacy array.
  * @probe: the function to call when a device is found.  Returns 0 or -errno.
  * @remove: the function to call when a device is removed.
  * @config_changed: optional function to call when the device configuration
@@ -140,6 +142,8 @@ struct virtio_driver {
 	const struct virtio_device_id *id_table;
 	const unsigned int *feature_table;
 	unsigned int feature_table_size;
+	const unsigned int *feature_table_legacy;
+	unsigned int feature_table_size_legacy;
 	int (*probe)(struct virtio_device *dev);
 	void (*scan)(struct virtio_device *dev);
 	void (*remove)(struct virtio_device *dev);
-- 
cgit v1.2.3-70-g09d2


From fdd819b21576c361bf0dcdd9522df4ccabf7aaa8 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 7 Oct 2014 16:39:48 +0200
Subject: virtio_net: v1.0 endianness

Based on patches by Rusty Russell, Cornelia Huck.
Note: more code changes are needed for 1.0 support
(due to different header size).
So we don't advertize support for 1.0 yet.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/net/virtio_net.c        | 33 ++++++++++++++++++++-------------
 include/uapi/linux/virtio_net.h | 15 ++++++++-------
 2 files changed, 28 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index b0bc8ead47d..c07e0302438 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -347,13 +347,14 @@ err:
 }
 
 static struct sk_buff *receive_mergeable(struct net_device *dev,
+					 struct virtnet_info *vi,
 					 struct receive_queue *rq,
 					 unsigned long ctx,
 					 unsigned int len)
 {
 	void *buf = mergeable_ctx_to_buf_address(ctx);
 	struct skb_vnet_hdr *hdr = buf;
-	int num_buf = hdr->mhdr.num_buffers;
+	u16 num_buf = virtio16_to_cpu(rq->vq->vdev, hdr->mhdr.num_buffers);
 	struct page *page = virt_to_head_page(buf);
 	int offset = buf - page_address(page);
 	unsigned int truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
@@ -369,7 +370,9 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		ctx = (unsigned long)virtqueue_get_buf(rq->vq, &len);
 		if (unlikely(!ctx)) {
 			pr_debug("%s: rx error: %d buffers out of %d missing\n",
-				 dev->name, num_buf, hdr->mhdr.num_buffers);
+				 dev->name, num_buf,
+				 virtio16_to_cpu(rq->vq->vdev,
+						 hdr->mhdr.num_buffers));
 			dev->stats.rx_length_errors++;
 			goto err_buf;
 		}
@@ -454,7 +457,7 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
 	}
 
 	if (vi->mergeable_rx_bufs)
-		skb = receive_mergeable(dev, rq, (unsigned long)buf, len);
+		skb = receive_mergeable(dev, vi, rq, (unsigned long)buf, len);
 	else if (vi->big_packets)
 		skb = receive_big(dev, rq, buf, len);
 	else
@@ -473,8 +476,8 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
 	if (hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
 		pr_debug("Needs csum!\n");
 		if (!skb_partial_csum_set(skb,
-					  hdr->hdr.csum_start,
-					  hdr->hdr.csum_offset))
+			  virtio16_to_cpu(vi->vdev, hdr->hdr.csum_start),
+			  virtio16_to_cpu(vi->vdev, hdr->hdr.csum_offset)))
 			goto frame_err;
 	} else if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -514,7 +517,8 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
 		if (hdr->hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN)
 			skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
 
-		skb_shinfo(skb)->gso_size = hdr->hdr.gso_size;
+		skb_shinfo(skb)->gso_size = virtio16_to_cpu(vi->vdev,
+							    hdr->hdr.gso_size);
 		if (skb_shinfo(skb)->gso_size == 0) {
 			net_warn_ratelimited("%s: zero gso size.\n", dev->name);
 			goto frame_err;
@@ -876,16 +880,19 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		hdr->hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-		hdr->hdr.csum_start = skb_checksum_start_offset(skb);
-		hdr->hdr.csum_offset = skb->csum_offset;
+		hdr->hdr.csum_start = cpu_to_virtio16(vi->vdev,
+						skb_checksum_start_offset(skb));
+		hdr->hdr.csum_offset = cpu_to_virtio16(vi->vdev,
+							 skb->csum_offset);
 	} else {
 		hdr->hdr.flags = 0;
 		hdr->hdr.csum_offset = hdr->hdr.csum_start = 0;
 	}
 
 	if (skb_is_gso(skb)) {
-		hdr->hdr.hdr_len = skb_headlen(skb);
-		hdr->hdr.gso_size = skb_shinfo(skb)->gso_size;
+		hdr->hdr.hdr_len = cpu_to_virtio16(vi->vdev, skb_headlen(skb));
+		hdr->hdr.gso_size = cpu_to_virtio16(vi->vdev,
+						    skb_shinfo(skb)->gso_size);
 		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
 			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
@@ -1112,7 +1119,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 	if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
 		return 0;
 
-	s.virtqueue_pairs = queue_pairs;
+	s.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
 	sg_init_one(&sg, &s, sizeof(s));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
@@ -1189,7 +1196,7 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 	sg_init_table(sg, 2);
 
 	/* Store the unicast list and count in the front of the buffer */
-	mac_data->entries = uc_count;
+	mac_data->entries = cpu_to_virtio32(vi->vdev, uc_count);
 	i = 0;
 	netdev_for_each_uc_addr(ha, dev)
 		memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN);
@@ -1200,7 +1207,7 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 	/* multicast list and count fill the end */
 	mac_data = (void *)&mac_data->macs[uc_count][0];
 
-	mac_data->entries = mc_count;
+	mac_data->entries = cpu_to_virtio32(vi->vdev, mc_count);
 	i = 0;
 	netdev_for_each_mc_addr(ha, dev)
 		memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN);
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 172a7f00780..b5f1677b291 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -28,6 +28,7 @@
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
+#include <linux/virtio_types.h>
 #include <linux/if_ether.h>
 
 /* The feature bitmap for virtio net */
@@ -84,17 +85,17 @@ struct virtio_net_hdr {
 #define VIRTIO_NET_HDR_GSO_TCPV6	4	// GSO frame, IPv6 TCP
 #define VIRTIO_NET_HDR_GSO_ECN		0x80	// TCP has ECN set
 	__u8 gso_type;
-	__u16 hdr_len;		/* Ethernet + IP + tcp/udp hdrs */
-	__u16 gso_size;		/* Bytes to append to hdr_len per frame */
-	__u16 csum_start;	/* Position to start checksumming from */
-	__u16 csum_offset;	/* Offset after that to place checksum */
+	__virtio16 hdr_len;		/* Ethernet + IP + tcp/udp hdrs */
+	__virtio16 gso_size;		/* Bytes to append to hdr_len per frame */
+	__virtio16 csum_start;	/* Position to start checksumming from */
+	__virtio16 csum_offset;	/* Offset after that to place checksum */
 };
 
 /* This is the version of the header to use when the MRG_RXBUF
  * feature has been negotiated. */
 struct virtio_net_hdr_mrg_rxbuf {
 	struct virtio_net_hdr hdr;
-	__u16 num_buffers;	/* Number of merged rx buffers */
+	__virtio16 num_buffers;	/* Number of merged rx buffers */
 };
 
 /*
@@ -149,7 +150,7 @@ typedef __u8 virtio_net_ctrl_ack;
  * VIRTIO_NET_F_CTRL_MAC_ADDR feature is available.
  */
 struct virtio_net_ctrl_mac {
-	__u32 entries;
+	__virtio32 entries;
 	__u8 macs[][ETH_ALEN];
 } __attribute__((packed));
 
@@ -193,7 +194,7 @@ struct virtio_net_ctrl_mac {
  * specified.
  */
 struct virtio_net_ctrl_mq {
-	__u16 virtqueue_pairs;
+	__virtio16 virtqueue_pairs;
 };
 
 #define VIRTIO_NET_CTRL_MQ   4
-- 
cgit v1.2.3-70-g09d2


From 19c1c5a64c3b8eeb65b63abba248b880dd584589 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 7 Oct 2014 16:39:49 +0200
Subject: virtio_blk: v1.0 support

Based on patch by Cornelia Huck.

Note: for consistency, and to avoid sparse errors,
      convert all fields, even those no longer in use
      for virtio v1.0.

Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/block/virtio_blk.c      | 70 ++++++++++++++++++++++++-----------------
 include/uapi/linux/virtio_blk.h | 15 ++++-----
 2 files changed, 49 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index c6a27d54ad6..f601f16eabf 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -80,7 +80,7 @@ static int __virtblk_add_req(struct virtqueue *vq,
 {
 	struct scatterlist hdr, status, cmd, sense, inhdr, *sgs[6];
 	unsigned int num_out = 0, num_in = 0;
-	int type = vbr->out_hdr.type & ~VIRTIO_BLK_T_OUT;
+	__virtio32 type = vbr->out_hdr.type & ~cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT);
 
 	sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
 	sgs[num_out++] = &hdr;
@@ -91,19 +91,19 @@ static int __virtblk_add_req(struct virtqueue *vq,
 	 * block, and before the normal inhdr we put the sense data and the
 	 * inhdr with additional status information.
 	 */
-	if (type == VIRTIO_BLK_T_SCSI_CMD) {
+	if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
 		sg_init_one(&cmd, vbr->req->cmd, vbr->req->cmd_len);
 		sgs[num_out++] = &cmd;
 	}
 
 	if (have_data) {
-		if (vbr->out_hdr.type & VIRTIO_BLK_T_OUT)
+		if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
 			sgs[num_out++] = data_sg;
 		else
 			sgs[num_out + num_in++] = data_sg;
 	}
 
-	if (type == VIRTIO_BLK_T_SCSI_CMD) {
+	if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
 		sg_init_one(&sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
 		sgs[num_out + num_in++] = &sense;
 		sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
@@ -119,12 +119,13 @@ static int __virtblk_add_req(struct virtqueue *vq,
 static inline void virtblk_request_done(struct request *req)
 {
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+	struct virtio_blk *vblk = req->q->queuedata;
 	int error = virtblk_result(vbr);
 
 	if (req->cmd_type == REQ_TYPE_BLOCK_PC) {
-		req->resid_len = vbr->in_hdr.residual;
-		req->sense_len = vbr->in_hdr.sense_len;
-		req->errors = vbr->in_hdr.errors;
+		req->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
+		req->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
+		req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
 	} else if (req->cmd_type == REQ_TYPE_SPECIAL) {
 		req->errors = (error != 0);
 	}
@@ -173,25 +174,25 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
 
 	vbr->req = req;
 	if (req->cmd_flags & REQ_FLUSH) {
-		vbr->out_hdr.type = VIRTIO_BLK_T_FLUSH;
+		vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_FLUSH);
 		vbr->out_hdr.sector = 0;
-		vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+		vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
 	} else {
 		switch (req->cmd_type) {
 		case REQ_TYPE_FS:
 			vbr->out_hdr.type = 0;
-			vbr->out_hdr.sector = blk_rq_pos(vbr->req);
-			vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+			vbr->out_hdr.sector = cpu_to_virtio64(vblk->vdev, blk_rq_pos(vbr->req));
+			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
 			break;
 		case REQ_TYPE_BLOCK_PC:
-			vbr->out_hdr.type = VIRTIO_BLK_T_SCSI_CMD;
+			vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_SCSI_CMD);
 			vbr->out_hdr.sector = 0;
-			vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
 			break;
 		case REQ_TYPE_SPECIAL:
-			vbr->out_hdr.type = VIRTIO_BLK_T_GET_ID;
+			vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID);
 			vbr->out_hdr.sector = 0;
-			vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
 			break;
 		default:
 			/* We don't put anything else in the queue. */
@@ -204,9 +205,9 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
 	num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
 	if (num) {
 		if (rq_data_dir(vbr->req) == WRITE)
-			vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
+			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT);
 		else
-			vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
+			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN);
 	}
 
 	spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
@@ -476,7 +477,8 @@ static int virtblk_get_cache_mode(struct virtio_device *vdev)
 				   struct virtio_blk_config, wce,
 				   &writeback);
 	if (err)
-		writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE);
+		writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE) ||
+		            virtio_has_feature(vdev, VIRTIO_F_VERSION_1);
 
 	return writeback;
 }
@@ -821,25 +823,35 @@ static const struct virtio_device_id id_table[] = {
 	{ 0 },
 };
 
-static unsigned int features[] = {
+static unsigned int features_legacy[] = {
 	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
 	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
 	VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
 	VIRTIO_BLK_F_MQ,
+}
+;
+static unsigned int features[] = {
+	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
+	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
+	VIRTIO_BLK_F_TOPOLOGY,
+	VIRTIO_BLK_F_MQ,
+	VIRTIO_F_VERSION_1,
 };
 
 static struct virtio_driver virtio_blk = {
-	.feature_table		= features,
-	.feature_table_size	= ARRAY_SIZE(features),
-	.driver.name		= KBUILD_MODNAME,
-	.driver.owner		= THIS_MODULE,
-	.id_table		= id_table,
-	.probe			= virtblk_probe,
-	.remove			= virtblk_remove,
-	.config_changed		= virtblk_config_changed,
+	.feature_table			= features,
+	.feature_table_size		= ARRAY_SIZE(features),
+	.feature_table_legacy		= features_legacy,
+	.feature_table_size_legacy	= ARRAY_SIZE(features_legacy),
+	.driver.name			= KBUILD_MODNAME,
+	.driver.owner			= THIS_MODULE,
+	.id_table			= id_table,
+	.probe				= virtblk_probe,
+	.remove				= virtblk_remove,
+	.config_changed			= virtblk_config_changed,
 #ifdef CONFIG_PM_SLEEP
-	.freeze			= virtblk_freeze,
-	.restore		= virtblk_restore,
+	.freeze				= virtblk_freeze,
+	.restore			= virtblk_restore,
 #endif
 };
 
diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h
index 9ad67b26758..247c8ba8544 100644
--- a/include/uapi/linux/virtio_blk.h
+++ b/include/uapi/linux/virtio_blk.h
@@ -28,6 +28,7 @@
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
+#include <linux/virtio_types.h>
 
 /* Feature bits */
 #define VIRTIO_BLK_F_BARRIER	0	/* Does host support barriers? */
@@ -114,18 +115,18 @@ struct virtio_blk_config {
 /* This is the first element of the read scatter-gather list. */
 struct virtio_blk_outhdr {
 	/* VIRTIO_BLK_T* */
-	__u32 type;
+	__virtio32 type;
 	/* io priority. */
-	__u32 ioprio;
+	__virtio32 ioprio;
 	/* Sector (ie. 512 byte offset) */
-	__u64 sector;
+	__virtio64 sector;
 };
 
 struct virtio_scsi_inhdr {
-	__u32 errors;
-	__u32 data_len;
-	__u32 sense_len;
-	__u32 residual;
+	__virtio32 errors;
+	__virtio32 data_len;
+	__virtio32 sense_len;
+	__virtio32 residual;
 };
 
 /* And this is the final byte of the write scatter-gather list. */
-- 
cgit v1.2.3-70-g09d2


From 031f5e0338ef672e728c878129fa044e8830c31a Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 19 Nov 2014 14:44:40 +0200
Subject: tun: move internal flag defines out of uapi

TUN_ flags are internal and never exposed
to userspace. Any application using it is almost
certainly buggy.

Move them out to tun.c.

Note: we remove these completely in follow-up patches,
this code movement is split out for ease of review.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/net/tun.c           | 72 +++++++++++++--------------------------------
 include/uapi/linux/if_tun.h | 16 ++--------
 2 files changed, 24 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9dd3746994a..b4e4ca01fac 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -103,6 +103,21 @@ do {								\
 } while (0)
 #endif
 
+/* TUN device flags */
+
+/* IFF_ATTACH_QUEUE is never stored in device flags,
+ * overload it to mean fasync when stored there.
+ */
+#define TUN_FASYNC	IFF_ATTACH_QUEUE
+#define TUN_NO_PI	IFF_NO_PI
+/* This flag has no real effect */
+#define TUN_ONE_QUEUE	IFF_ONE_QUEUE
+#define TUN_PERSIST 	IFF_PERSIST
+#define TUN_VNET_HDR 	IFF_VNET_HDR
+#define TUN_TAP_MQ      IFF_MULTI_QUEUE
+
+#define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
+		      IFF_MULTI_QUEUE)
 #define GOODCOPY_LEN 128
 
 #define FLT_EXACT_COUNT 8
@@ -1521,32 +1536,7 @@ static struct proto tun_proto = {
 
 static int tun_flags(struct tun_struct *tun)
 {
-	int flags = 0;
-
-	if (tun->flags & TUN_TUN_DEV)
-		flags |= IFF_TUN;
-	else
-		flags |= IFF_TAP;
-
-	if (tun->flags & TUN_NO_PI)
-		flags |= IFF_NO_PI;
-
-	/* This flag has no real effect.  We track the value for backwards
-	 * compatibility.
-	 */
-	if (tun->flags & TUN_ONE_QUEUE)
-		flags |= IFF_ONE_QUEUE;
-
-	if (tun->flags & TUN_VNET_HDR)
-		flags |= IFF_VNET_HDR;
-
-	if (tun->flags & TUN_TAP_MQ)
-		flags |= IFF_MULTI_QUEUE;
-
-	if (tun->flags & TUN_PERSIST)
-		flags |= IFF_PERSIST;
-
-	return flags;
+	return tun->flags & (TUN_FEATURES | IFF_PERSIST | IFF_TUN | IFF_TAP);
 }
 
 static ssize_t tun_show_flags(struct device *dev, struct device_attribute *attr,
@@ -1706,28 +1696,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 	tun_debug(KERN_INFO, tun, "tun_set_iff\n");
 
-	if (ifr->ifr_flags & IFF_NO_PI)
-		tun->flags |= TUN_NO_PI;
-	else
-		tun->flags &= ~TUN_NO_PI;
-
-	/* This flag has no real effect.  We track the value for backwards
-	 * compatibility.
-	 */
-	if (ifr->ifr_flags & IFF_ONE_QUEUE)
-		tun->flags |= TUN_ONE_QUEUE;
-	else
-		tun->flags &= ~TUN_ONE_QUEUE;
-
-	if (ifr->ifr_flags & IFF_VNET_HDR)
-		tun->flags |= TUN_VNET_HDR;
-	else
-		tun->flags &= ~TUN_VNET_HDR;
-
-	if (ifr->ifr_flags & IFF_MULTI_QUEUE)
-		tun->flags |= TUN_TAP_MQ;
-	else
-		tun->flags &= ~TUN_TAP_MQ;
+	tun->flags = (tun->flags & ~TUN_FEATURES) |
+		(ifr->ifr_flags & TUN_FEATURES);
 
 	/* Make sure persistent devices do not get stuck in
 	 * xoff state.
@@ -1890,9 +1860,9 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	if (cmd == TUNGETFEATURES) {
 		/* Currently this just means: "what IFF flags are valid?".
 		 * This is needed because we never checked for invalid flags on
-		 * TUNSETIFF. */
-		return put_user(IFF_TUN | IFF_TAP | IFF_NO_PI | IFF_ONE_QUEUE |
-				IFF_VNET_HDR | IFF_MULTI_QUEUE,
+		 * TUNSETIFF.
+		 */
+		return put_user(IFF_TUN | IFF_TAP | TUN_FEATURES,
 				(unsigned int __user*)argp);
 	} else if (cmd == TUNSETQUEUE)
 		return tun_set_queue(file, &ifr);
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index e9502dd1ee2..277a2607d16 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -22,21 +22,11 @@
 
 /* Read queue size */
 #define TUN_READQ_SIZE	500
-
-/* TUN device flags */
-#define TUN_TUN_DEV 	0x0001	
-#define TUN_TAP_DEV	0x0002
+/* TUN device type flags: deprecated. Use IFF_TUN/IFF_TAP instead. */
+#define TUN_TUN_DEV 	IFF_TUN
+#define TUN_TAP_DEV	IFF_TAP
 #define TUN_TYPE_MASK   0x000f
 
-#define TUN_FASYNC	0x0010
-#define TUN_NOCHECKSUM	0x0020
-#define TUN_NO_PI	0x0040
-/* This flag has no real effect */
-#define TUN_ONE_QUEUE	0x0080
-#define TUN_PERSIST 	0x0100	
-#define TUN_VNET_HDR 	0x0200
-#define TUN_TAP_MQ      0x0400
-
 /* Ioctl defines */
 #define TUNSETNOCSUM  _IOW('T', 200, int) 
 #define TUNSETDEBUG   _IOW('T', 201, int) 
-- 
cgit v1.2.3-70-g09d2


From e999d6ea2a4f313a5bba514b08f6f01b0c0072a9 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 18 Nov 2014 17:38:08 +0200
Subject: tun: add VNET_LE flag

virtio 1.0 modified virtio net header format,
making all fields little endian.

Users can tweak header format before submitting it to tun,
but this means more data copies where none were necessary.
And if the iovec is in RO memory, this means we might
need to split iovec also means we might in theory overflow
iovec max size.

This patch adds a simpler way for applications to handle this,
using new "little endian" flag in tun.
As a result, tun simply byte-swaps header fields as appropriate.
This is a NOP on LE architectures.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/uapi/linux/if_tun.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 277a2607d16..18b2403982f 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -57,6 +57,7 @@
 #define IFF_ONE_QUEUE	0x2000
 #define IFF_VNET_HDR	0x4000
 #define IFF_TUN_EXCL	0x8000
+#define IFF_VNET_LE	0x10000
 #define IFF_MULTI_QUEUE 0x0100
 #define IFF_ATTACH_QUEUE 0x0200
 #define IFF_DETACH_QUEUE 0x0400
-- 
cgit v1.2.3-70-g09d2


From d75dff39dfb86b0b8925f10b1f13fc353ae9f1b0 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Sun, 23 Nov 2014 17:28:57 +0200
Subject: virtio_scsi: v1.0 support

Note: for consistency, and to avoid sparse errors,
  convert all fields, even those no longer in use
  for virtio v1.0.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
---
 drivers/scsi/virtio_scsi.c  | 51 ++++++++++++++++++++++++++++-----------------
 include/linux/virtio_scsi.h | 32 +++++++++++++++-------------
 2 files changed, 49 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index b83846fc785..d9ec80698d6 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -158,7 +158,7 @@ static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf)
 		sc, resp->response, resp->status, resp->sense_len);
 
 	sc->result = resp->status;
-	virtscsi_compute_resid(sc, resp->resid);
+	virtscsi_compute_resid(sc, virtio32_to_cpu(vscsi->vdev, resp->resid));
 	switch (resp->response) {
 	case VIRTIO_SCSI_S_OK:
 		set_host_byte(sc, DID_OK);
@@ -196,10 +196,13 @@ static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf)
 		break;
 	}
 
-	WARN_ON(resp->sense_len > VIRTIO_SCSI_SENSE_SIZE);
+	WARN_ON(virtio32_to_cpu(vscsi->vdev, resp->sense_len) >
+		VIRTIO_SCSI_SENSE_SIZE);
 	if (sc->sense_buffer) {
 		memcpy(sc->sense_buffer, resp->sense,
-		       min_t(u32, resp->sense_len, VIRTIO_SCSI_SENSE_SIZE));
+		       min_t(u32,
+			     virtio32_to_cpu(vscsi->vdev, resp->sense_len),
+			     VIRTIO_SCSI_SENSE_SIZE));
 		if (resp->sense_len)
 			set_driver_byte(sc, DRIVER_SENSE);
 	}
@@ -323,7 +326,7 @@ static void virtscsi_handle_transport_reset(struct virtio_scsi *vscsi,
 	unsigned int target = event->lun[1];
 	unsigned int lun = (event->lun[2] << 8) | event->lun[3];
 
-	switch (event->reason) {
+	switch (virtio32_to_cpu(vscsi->vdev, event->reason)) {
 	case VIRTIO_SCSI_EVT_RESET_RESCAN:
 		scsi_add_device(shost, 0, target, lun);
 		break;
@@ -349,8 +352,8 @@ static void virtscsi_handle_param_change(struct virtio_scsi *vscsi,
 	struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
 	unsigned int target = event->lun[1];
 	unsigned int lun = (event->lun[2] << 8) | event->lun[3];
-	u8 asc = event->reason & 255;
-	u8 ascq = event->reason >> 8;
+	u8 asc = virtio32_to_cpu(vscsi->vdev, event->reason) & 255;
+	u8 ascq = virtio32_to_cpu(vscsi->vdev, event->reason) >> 8;
 
 	sdev = scsi_device_lookup(shost, 0, target, lun);
 	if (!sdev) {
@@ -374,12 +377,14 @@ static void virtscsi_handle_event(struct work_struct *work)
 	struct virtio_scsi *vscsi = event_node->vscsi;
 	struct virtio_scsi_event *event = &event_node->event;
 
-	if (event->event & VIRTIO_SCSI_T_EVENTS_MISSED) {
-		event->event &= ~VIRTIO_SCSI_T_EVENTS_MISSED;
+	if (event->event &
+	    cpu_to_virtio32(vscsi->vdev, VIRTIO_SCSI_T_EVENTS_MISSED)) {
+		event->event &= ~cpu_to_virtio32(vscsi->vdev,
+						   VIRTIO_SCSI_T_EVENTS_MISSED);
 		scsi_scan_host(virtio_scsi_host(vscsi->vdev));
 	}
 
-	switch (event->event) {
+	switch (virtio32_to_cpu(vscsi->vdev, event->event)) {
 	case VIRTIO_SCSI_T_NO_EVENT:
 		break;
 	case VIRTIO_SCSI_T_TRANSPORT_RESET:
@@ -482,26 +487,28 @@ static int virtscsi_kick_cmd(struct virtio_scsi_vq *vq,
 	return err;
 }
 
-static void virtio_scsi_init_hdr(struct virtio_scsi_cmd_req *cmd,
+static void virtio_scsi_init_hdr(struct virtio_device *vdev,
+				 struct virtio_scsi_cmd_req *cmd,
 				 struct scsi_cmnd *sc)
 {
 	cmd->lun[0] = 1;
 	cmd->lun[1] = sc->device->id;
 	cmd->lun[2] = (sc->device->lun >> 8) | 0x40;
 	cmd->lun[3] = sc->device->lun & 0xff;
-	cmd->tag = (unsigned long)sc;
+	cmd->tag = cpu_to_virtio64(vdev, (unsigned long)sc);
 	cmd->task_attr = VIRTIO_SCSI_S_SIMPLE;
 	cmd->prio = 0;
 	cmd->crn = 0;
 }
 
-static void virtio_scsi_init_hdr_pi(struct virtio_scsi_cmd_req_pi *cmd_pi,
+static void virtio_scsi_init_hdr_pi(struct virtio_device *vdev,
+				    struct virtio_scsi_cmd_req_pi *cmd_pi,
 				    struct scsi_cmnd *sc)
 {
 	struct request *rq = sc->request;
 	struct blk_integrity *bi;
 
-	virtio_scsi_init_hdr((struct virtio_scsi_cmd_req *)cmd_pi, sc);
+	virtio_scsi_init_hdr(vdev, (struct virtio_scsi_cmd_req *)cmd_pi, sc);
 
 	if (!rq || !scsi_prot_sg_count(sc))
 		return;
@@ -509,9 +516,13 @@ static void virtio_scsi_init_hdr_pi(struct virtio_scsi_cmd_req_pi *cmd_pi,
 	bi = blk_get_integrity(rq->rq_disk);
 
 	if (sc->sc_data_direction == DMA_TO_DEVICE)
-		cmd_pi->pi_bytesout = blk_rq_sectors(rq) * bi->tuple_size;
+		cmd_pi->pi_bytesout = cpu_to_virtio32(vdev,
+							blk_rq_sectors(rq) *
+							bi->tuple_size);
 	else if (sc->sc_data_direction == DMA_FROM_DEVICE)
-		cmd_pi->pi_bytesin = blk_rq_sectors(rq) * bi->tuple_size;
+		cmd_pi->pi_bytesin = cpu_to_virtio32(vdev,
+						       blk_rq_sectors(rq) *
+						       bi->tuple_size);
 }
 
 static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
@@ -536,11 +547,11 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
 	BUG_ON(sc->cmd_len > VIRTIO_SCSI_CDB_SIZE);
 
 	if (virtio_has_feature(vscsi->vdev, VIRTIO_SCSI_F_T10_PI)) {
-		virtio_scsi_init_hdr_pi(&cmd->req.cmd_pi, sc);
+		virtio_scsi_init_hdr_pi(vscsi->vdev, &cmd->req.cmd_pi, sc);
 		memcpy(cmd->req.cmd_pi.cdb, sc->cmnd, sc->cmd_len);
 		req_size = sizeof(cmd->req.cmd_pi);
 	} else {
-		virtio_scsi_init_hdr(&cmd->req.cmd, sc);
+		virtio_scsi_init_hdr(vscsi->vdev, &cmd->req.cmd, sc);
 		memcpy(cmd->req.cmd.cdb, sc->cmnd, sc->cmd_len);
 		req_size = sizeof(cmd->req.cmd);
 	}
@@ -655,7 +666,8 @@ static int virtscsi_device_reset(struct scsi_cmnd *sc)
 	cmd->sc = sc;
 	cmd->req.tmf = (struct virtio_scsi_ctrl_tmf_req){
 		.type = VIRTIO_SCSI_T_TMF,
-		.subtype = VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET,
+		.subtype = cpu_to_virtio32(vscsi->vdev,
+					     VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET),
 		.lun[0] = 1,
 		.lun[1] = sc->device->id,
 		.lun[2] = (sc->device->lun >> 8) | 0x40,
@@ -713,7 +725,7 @@ static int virtscsi_abort(struct scsi_cmnd *sc)
 		.lun[1] = sc->device->id,
 		.lun[2] = (sc->device->lun >> 8) | 0x40,
 		.lun[3] = sc->device->lun & 0xff,
-		.tag = (unsigned long)sc,
+		.tag = cpu_to_virtio64(vscsi->vdev, (unsigned long)sc),
 	};
 	return virtscsi_tmf(vscsi, cmd);
 }
@@ -1073,6 +1085,7 @@ static unsigned int features[] = {
 	VIRTIO_SCSI_F_HOTPLUG,
 	VIRTIO_SCSI_F_CHANGE,
 	VIRTIO_SCSI_F_T10_PI,
+	VIRTIO_F_VERSION_1,
 };
 
 static struct virtio_driver virtio_scsi_driver = {
diff --git a/include/linux/virtio_scsi.h b/include/linux/virtio_scsi.h
index de429d1f435..af448649a97 100644
--- a/include/linux/virtio_scsi.h
+++ b/include/linux/virtio_scsi.h
@@ -27,13 +27,15 @@
 #ifndef _LINUX_VIRTIO_SCSI_H
 #define _LINUX_VIRTIO_SCSI_H
 
+#include <linux/virtio_types.h>
+
 #define VIRTIO_SCSI_CDB_SIZE   32
 #define VIRTIO_SCSI_SENSE_SIZE 96
 
 /* SCSI command request, followed by data-out */
 struct virtio_scsi_cmd_req {
 	u8 lun[8];		/* Logical Unit Number */
-	u64 tag;		/* Command identifier */
+	__virtio64 tag;		/* Command identifier */
 	u8 task_attr;		/* Task attribute */
 	u8 prio;		/* SAM command priority field */
 	u8 crn;
@@ -43,20 +45,20 @@ struct virtio_scsi_cmd_req {
 /* SCSI command request, followed by protection information */
 struct virtio_scsi_cmd_req_pi {
 	u8 lun[8];		/* Logical Unit Number */
-	u64 tag;		/* Command identifier */
+	__virtio64 tag;		/* Command identifier */
 	u8 task_attr;		/* Task attribute */
 	u8 prio;		/* SAM command priority field */
 	u8 crn;
-	u32 pi_bytesout;	/* DataOUT PI Number of bytes */
-	u32 pi_bytesin;		/* DataIN PI Number of bytes */
+	__virtio32 pi_bytesout;	/* DataOUT PI Number of bytes */
+	__virtio32 pi_bytesin;		/* DataIN PI Number of bytes */
 	u8 cdb[VIRTIO_SCSI_CDB_SIZE];
 } __packed;
 
 /* Response, followed by sense data and data-in */
 struct virtio_scsi_cmd_resp {
-	u32 sense_len;		/* Sense data length */
-	u32 resid;		/* Residual bytes in data buffer */
-	u16 status_qualifier;	/* Status qualifier */
+	__virtio32 sense_len;		/* Sense data length */
+	__virtio32 resid;		/* Residual bytes in data buffer */
+	__virtio16 status_qualifier;	/* Status qualifier */
 	u8 status;		/* Command completion status */
 	u8 response;		/* Response values */
 	u8 sense[VIRTIO_SCSI_SENSE_SIZE];
@@ -64,10 +66,10 @@ struct virtio_scsi_cmd_resp {
 
 /* Task Management Request */
 struct virtio_scsi_ctrl_tmf_req {
-	u32 type;
-	u32 subtype;
+	__virtio32 type;
+	__virtio32 subtype;
 	u8 lun[8];
-	u64 tag;
+	__virtio64 tag;
 } __packed;
 
 struct virtio_scsi_ctrl_tmf_resp {
@@ -76,20 +78,20 @@ struct virtio_scsi_ctrl_tmf_resp {
 
 /* Asynchronous notification query/subscription */
 struct virtio_scsi_ctrl_an_req {
-	u32 type;
+	__virtio32 type;
 	u8 lun[8];
-	u32 event_requested;
+	__virtio32 event_requested;
 } __packed;
 
 struct virtio_scsi_ctrl_an_resp {
-	u32 event_actual;
+	__virtio32 event_actual;
 	u8 response;
 } __packed;
 
 struct virtio_scsi_event {
-	u32 event;
+	__virtio32 event;
 	u8 lun[8];
-	u32 reason;
+	__virtio32 reason;
 } __packed;
 
 struct virtio_scsi_config {
-- 
cgit v1.2.3-70-g09d2


From 106d81f58a5e7f41e857b8805e9d899e87d7a874 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Sun, 23 Nov 2014 17:45:53 +0200
Subject: virtio_scsi: move to uapi

Guests need to use virtio scsi API, so export it to uapi,
nice to e.g. qemu and will help us remember this file
affects ABI.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/virtio_scsi.h      | 164 ---------------------------------------
 include/uapi/linux/virtio_scsi.h | 164 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 164 insertions(+), 164 deletions(-)
 delete mode 100644 include/linux/virtio_scsi.h
 create mode 100644 include/uapi/linux/virtio_scsi.h

(limited to 'include')

diff --git a/include/linux/virtio_scsi.h b/include/linux/virtio_scsi.h
deleted file mode 100644
index af448649a97..00000000000
--- a/include/linux/virtio_scsi.h
+++ /dev/null
@@ -1,164 +0,0 @@
-/*
- * This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY AUTHOR AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL AUTHOR OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- */
-
-#ifndef _LINUX_VIRTIO_SCSI_H
-#define _LINUX_VIRTIO_SCSI_H
-
-#include <linux/virtio_types.h>
-
-#define VIRTIO_SCSI_CDB_SIZE   32
-#define VIRTIO_SCSI_SENSE_SIZE 96
-
-/* SCSI command request, followed by data-out */
-struct virtio_scsi_cmd_req {
-	u8 lun[8];		/* Logical Unit Number */
-	__virtio64 tag;		/* Command identifier */
-	u8 task_attr;		/* Task attribute */
-	u8 prio;		/* SAM command priority field */
-	u8 crn;
-	u8 cdb[VIRTIO_SCSI_CDB_SIZE];
-} __packed;
-
-/* SCSI command request, followed by protection information */
-struct virtio_scsi_cmd_req_pi {
-	u8 lun[8];		/* Logical Unit Number */
-	__virtio64 tag;		/* Command identifier */
-	u8 task_attr;		/* Task attribute */
-	u8 prio;		/* SAM command priority field */
-	u8 crn;
-	__virtio32 pi_bytesout;	/* DataOUT PI Number of bytes */
-	__virtio32 pi_bytesin;		/* DataIN PI Number of bytes */
-	u8 cdb[VIRTIO_SCSI_CDB_SIZE];
-} __packed;
-
-/* Response, followed by sense data and data-in */
-struct virtio_scsi_cmd_resp {
-	__virtio32 sense_len;		/* Sense data length */
-	__virtio32 resid;		/* Residual bytes in data buffer */
-	__virtio16 status_qualifier;	/* Status qualifier */
-	u8 status;		/* Command completion status */
-	u8 response;		/* Response values */
-	u8 sense[VIRTIO_SCSI_SENSE_SIZE];
-} __packed;
-
-/* Task Management Request */
-struct virtio_scsi_ctrl_tmf_req {
-	__virtio32 type;
-	__virtio32 subtype;
-	u8 lun[8];
-	__virtio64 tag;
-} __packed;
-
-struct virtio_scsi_ctrl_tmf_resp {
-	u8 response;
-} __packed;
-
-/* Asynchronous notification query/subscription */
-struct virtio_scsi_ctrl_an_req {
-	__virtio32 type;
-	u8 lun[8];
-	__virtio32 event_requested;
-} __packed;
-
-struct virtio_scsi_ctrl_an_resp {
-	__virtio32 event_actual;
-	u8 response;
-} __packed;
-
-struct virtio_scsi_event {
-	__virtio32 event;
-	u8 lun[8];
-	__virtio32 reason;
-} __packed;
-
-struct virtio_scsi_config {
-	u32 num_queues;
-	u32 seg_max;
-	u32 max_sectors;
-	u32 cmd_per_lun;
-	u32 event_info_size;
-	u32 sense_size;
-	u32 cdb_size;
-	u16 max_channel;
-	u16 max_target;
-	u32 max_lun;
-} __packed;
-
-/* Feature Bits */
-#define VIRTIO_SCSI_F_INOUT                    0
-#define VIRTIO_SCSI_F_HOTPLUG                  1
-#define VIRTIO_SCSI_F_CHANGE                   2
-#define VIRTIO_SCSI_F_T10_PI                   3
-
-/* Response codes */
-#define VIRTIO_SCSI_S_OK                       0
-#define VIRTIO_SCSI_S_OVERRUN                  1
-#define VIRTIO_SCSI_S_ABORTED                  2
-#define VIRTIO_SCSI_S_BAD_TARGET               3
-#define VIRTIO_SCSI_S_RESET                    4
-#define VIRTIO_SCSI_S_BUSY                     5
-#define VIRTIO_SCSI_S_TRANSPORT_FAILURE        6
-#define VIRTIO_SCSI_S_TARGET_FAILURE           7
-#define VIRTIO_SCSI_S_NEXUS_FAILURE            8
-#define VIRTIO_SCSI_S_FAILURE                  9
-#define VIRTIO_SCSI_S_FUNCTION_SUCCEEDED       10
-#define VIRTIO_SCSI_S_FUNCTION_REJECTED        11
-#define VIRTIO_SCSI_S_INCORRECT_LUN            12
-
-/* Controlq type codes.  */
-#define VIRTIO_SCSI_T_TMF                      0
-#define VIRTIO_SCSI_T_AN_QUERY                 1
-#define VIRTIO_SCSI_T_AN_SUBSCRIBE             2
-
-/* Valid TMF subtypes.  */
-#define VIRTIO_SCSI_T_TMF_ABORT_TASK           0
-#define VIRTIO_SCSI_T_TMF_ABORT_TASK_SET       1
-#define VIRTIO_SCSI_T_TMF_CLEAR_ACA            2
-#define VIRTIO_SCSI_T_TMF_CLEAR_TASK_SET       3
-#define VIRTIO_SCSI_T_TMF_I_T_NEXUS_RESET      4
-#define VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET   5
-#define VIRTIO_SCSI_T_TMF_QUERY_TASK           6
-#define VIRTIO_SCSI_T_TMF_QUERY_TASK_SET       7
-
-/* Events.  */
-#define VIRTIO_SCSI_T_EVENTS_MISSED            0x80000000
-#define VIRTIO_SCSI_T_NO_EVENT                 0
-#define VIRTIO_SCSI_T_TRANSPORT_RESET          1
-#define VIRTIO_SCSI_T_ASYNC_NOTIFY             2
-#define VIRTIO_SCSI_T_PARAM_CHANGE             3
-
-/* Reasons of transport reset event */
-#define VIRTIO_SCSI_EVT_RESET_HARD             0
-#define VIRTIO_SCSI_EVT_RESET_RESCAN           1
-#define VIRTIO_SCSI_EVT_RESET_REMOVED          2
-
-#define VIRTIO_SCSI_S_SIMPLE                   0
-#define VIRTIO_SCSI_S_ORDERED                  1
-#define VIRTIO_SCSI_S_HEAD                     2
-#define VIRTIO_SCSI_S_ACA                      3
-
-
-#endif /* _LINUX_VIRTIO_SCSI_H */
diff --git a/include/uapi/linux/virtio_scsi.h b/include/uapi/linux/virtio_scsi.h
new file mode 100644
index 00000000000..af448649a97
--- /dev/null
+++ b/include/uapi/linux/virtio_scsi.h
@@ -0,0 +1,164 @@
+/*
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#ifndef _LINUX_VIRTIO_SCSI_H
+#define _LINUX_VIRTIO_SCSI_H
+
+#include <linux/virtio_types.h>
+
+#define VIRTIO_SCSI_CDB_SIZE   32
+#define VIRTIO_SCSI_SENSE_SIZE 96
+
+/* SCSI command request, followed by data-out */
+struct virtio_scsi_cmd_req {
+	u8 lun[8];		/* Logical Unit Number */
+	__virtio64 tag;		/* Command identifier */
+	u8 task_attr;		/* Task attribute */
+	u8 prio;		/* SAM command priority field */
+	u8 crn;
+	u8 cdb[VIRTIO_SCSI_CDB_SIZE];
+} __packed;
+
+/* SCSI command request, followed by protection information */
+struct virtio_scsi_cmd_req_pi {
+	u8 lun[8];		/* Logical Unit Number */
+	__virtio64 tag;		/* Command identifier */
+	u8 task_attr;		/* Task attribute */
+	u8 prio;		/* SAM command priority field */
+	u8 crn;
+	__virtio32 pi_bytesout;	/* DataOUT PI Number of bytes */
+	__virtio32 pi_bytesin;		/* DataIN PI Number of bytes */
+	u8 cdb[VIRTIO_SCSI_CDB_SIZE];
+} __packed;
+
+/* Response, followed by sense data and data-in */
+struct virtio_scsi_cmd_resp {
+	__virtio32 sense_len;		/* Sense data length */
+	__virtio32 resid;		/* Residual bytes in data buffer */
+	__virtio16 status_qualifier;	/* Status qualifier */
+	u8 status;		/* Command completion status */
+	u8 response;		/* Response values */
+	u8 sense[VIRTIO_SCSI_SENSE_SIZE];
+} __packed;
+
+/* Task Management Request */
+struct virtio_scsi_ctrl_tmf_req {
+	__virtio32 type;
+	__virtio32 subtype;
+	u8 lun[8];
+	__virtio64 tag;
+} __packed;
+
+struct virtio_scsi_ctrl_tmf_resp {
+	u8 response;
+} __packed;
+
+/* Asynchronous notification query/subscription */
+struct virtio_scsi_ctrl_an_req {
+	__virtio32 type;
+	u8 lun[8];
+	__virtio32 event_requested;
+} __packed;
+
+struct virtio_scsi_ctrl_an_resp {
+	__virtio32 event_actual;
+	u8 response;
+} __packed;
+
+struct virtio_scsi_event {
+	__virtio32 event;
+	u8 lun[8];
+	__virtio32 reason;
+} __packed;
+
+struct virtio_scsi_config {
+	u32 num_queues;
+	u32 seg_max;
+	u32 max_sectors;
+	u32 cmd_per_lun;
+	u32 event_info_size;
+	u32 sense_size;
+	u32 cdb_size;
+	u16 max_channel;
+	u16 max_target;
+	u32 max_lun;
+} __packed;
+
+/* Feature Bits */
+#define VIRTIO_SCSI_F_INOUT                    0
+#define VIRTIO_SCSI_F_HOTPLUG                  1
+#define VIRTIO_SCSI_F_CHANGE                   2
+#define VIRTIO_SCSI_F_T10_PI                   3
+
+/* Response codes */
+#define VIRTIO_SCSI_S_OK                       0
+#define VIRTIO_SCSI_S_OVERRUN                  1
+#define VIRTIO_SCSI_S_ABORTED                  2
+#define VIRTIO_SCSI_S_BAD_TARGET               3
+#define VIRTIO_SCSI_S_RESET                    4
+#define VIRTIO_SCSI_S_BUSY                     5
+#define VIRTIO_SCSI_S_TRANSPORT_FAILURE        6
+#define VIRTIO_SCSI_S_TARGET_FAILURE           7
+#define VIRTIO_SCSI_S_NEXUS_FAILURE            8
+#define VIRTIO_SCSI_S_FAILURE                  9
+#define VIRTIO_SCSI_S_FUNCTION_SUCCEEDED       10
+#define VIRTIO_SCSI_S_FUNCTION_REJECTED        11
+#define VIRTIO_SCSI_S_INCORRECT_LUN            12
+
+/* Controlq type codes.  */
+#define VIRTIO_SCSI_T_TMF                      0
+#define VIRTIO_SCSI_T_AN_QUERY                 1
+#define VIRTIO_SCSI_T_AN_SUBSCRIBE             2
+
+/* Valid TMF subtypes.  */
+#define VIRTIO_SCSI_T_TMF_ABORT_TASK           0
+#define VIRTIO_SCSI_T_TMF_ABORT_TASK_SET       1
+#define VIRTIO_SCSI_T_TMF_CLEAR_ACA            2
+#define VIRTIO_SCSI_T_TMF_CLEAR_TASK_SET       3
+#define VIRTIO_SCSI_T_TMF_I_T_NEXUS_RESET      4
+#define VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET   5
+#define VIRTIO_SCSI_T_TMF_QUERY_TASK           6
+#define VIRTIO_SCSI_T_TMF_QUERY_TASK_SET       7
+
+/* Events.  */
+#define VIRTIO_SCSI_T_EVENTS_MISSED            0x80000000
+#define VIRTIO_SCSI_T_NO_EVENT                 0
+#define VIRTIO_SCSI_T_TRANSPORT_RESET          1
+#define VIRTIO_SCSI_T_ASYNC_NOTIFY             2
+#define VIRTIO_SCSI_T_PARAM_CHANGE             3
+
+/* Reasons of transport reset event */
+#define VIRTIO_SCSI_EVT_RESET_HARD             0
+#define VIRTIO_SCSI_EVT_RESET_RESCAN           1
+#define VIRTIO_SCSI_EVT_RESET_REMOVED          2
+
+#define VIRTIO_SCSI_S_SIMPLE                   0
+#define VIRTIO_SCSI_S_ORDERED                  1
+#define VIRTIO_SCSI_S_HEAD                     2
+#define VIRTIO_SCSI_S_ACA                      3
+
+
+#endif /* _LINUX_VIRTIO_SCSI_H */
-- 
cgit v1.2.3-70-g09d2


From fba7f020e80d59a90d6135b0965cd488cc86f695 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Sun, 23 Nov 2014 17:49:12 +0200
Subject: virtio_scsi: export to userspace

Replace uXX by __uXX and _packed by __attribute((packed))
as seems to be the norm for userspace headers.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/uapi/linux/Kbuild        |  1 +
 include/uapi/linux/virtio_scsi.h | 74 ++++++++++++++++++++--------------------
 2 files changed, 38 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 615f96a6022..2e8fd10f029 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -428,6 +428,7 @@ header-y += virtio_net.h
 header-y += virtio_pci.h
 header-y += virtio_ring.h
 header-y += virtio_rng.h
+header-y += virtio_scsi.h
 header-y += vm_sockets.h
 header-y += vt.h
 header-y += wait.h
diff --git a/include/uapi/linux/virtio_scsi.h b/include/uapi/linux/virtio_scsi.h
index af448649a97..42b9370771b 100644
--- a/include/uapi/linux/virtio_scsi.h
+++ b/include/uapi/linux/virtio_scsi.h
@@ -34,78 +34,78 @@
 
 /* SCSI command request, followed by data-out */
 struct virtio_scsi_cmd_req {
-	u8 lun[8];		/* Logical Unit Number */
+	__u8 lun[8];		/* Logical Unit Number */
 	__virtio64 tag;		/* Command identifier */
-	u8 task_attr;		/* Task attribute */
-	u8 prio;		/* SAM command priority field */
-	u8 crn;
-	u8 cdb[VIRTIO_SCSI_CDB_SIZE];
-} __packed;
+	__u8 task_attr;		/* Task attribute */
+	__u8 prio;		/* SAM command priority field */
+	__u8 crn;
+	__u8 cdb[VIRTIO_SCSI_CDB_SIZE];
+} __attribute__((packed));
 
 /* SCSI command request, followed by protection information */
 struct virtio_scsi_cmd_req_pi {
-	u8 lun[8];		/* Logical Unit Number */
+	__u8 lun[8];		/* Logical Unit Number */
 	__virtio64 tag;		/* Command identifier */
-	u8 task_attr;		/* Task attribute */
-	u8 prio;		/* SAM command priority field */
-	u8 crn;
+	__u8 task_attr;		/* Task attribute */
+	__u8 prio;		/* SAM command priority field */
+	__u8 crn;
 	__virtio32 pi_bytesout;	/* DataOUT PI Number of bytes */
 	__virtio32 pi_bytesin;		/* DataIN PI Number of bytes */
-	u8 cdb[VIRTIO_SCSI_CDB_SIZE];
-} __packed;
+	__u8 cdb[VIRTIO_SCSI_CDB_SIZE];
+} __attribute__((packed));
 
 /* Response, followed by sense data and data-in */
 struct virtio_scsi_cmd_resp {
 	__virtio32 sense_len;		/* Sense data length */
 	__virtio32 resid;		/* Residual bytes in data buffer */
 	__virtio16 status_qualifier;	/* Status qualifier */
-	u8 status;		/* Command completion status */
-	u8 response;		/* Response values */
-	u8 sense[VIRTIO_SCSI_SENSE_SIZE];
-} __packed;
+	__u8 status;		/* Command completion status */
+	__u8 response;		/* Response values */
+	__u8 sense[VIRTIO_SCSI_SENSE_SIZE];
+} __attribute__((packed));
 
 /* Task Management Request */
 struct virtio_scsi_ctrl_tmf_req {
 	__virtio32 type;
 	__virtio32 subtype;
-	u8 lun[8];
+	__u8 lun[8];
 	__virtio64 tag;
-} __packed;
+} __attribute__((packed));
 
 struct virtio_scsi_ctrl_tmf_resp {
-	u8 response;
-} __packed;
+	__u8 response;
+} __attribute__((packed));
 
 /* Asynchronous notification query/subscription */
 struct virtio_scsi_ctrl_an_req {
 	__virtio32 type;
-	u8 lun[8];
+	__u8 lun[8];
 	__virtio32 event_requested;
-} __packed;
+} __attribute__((packed));
 
 struct virtio_scsi_ctrl_an_resp {
 	__virtio32 event_actual;
-	u8 response;
-} __packed;
+	__u8 response;
+} __attribute__((packed));
 
 struct virtio_scsi_event {
 	__virtio32 event;
-	u8 lun[8];
+	__u8 lun[8];
 	__virtio32 reason;
-} __packed;
+} __attribute__((packed));
 
 struct virtio_scsi_config {
-	u32 num_queues;
-	u32 seg_max;
-	u32 max_sectors;
-	u32 cmd_per_lun;
-	u32 event_info_size;
-	u32 sense_size;
-	u32 cdb_size;
-	u16 max_channel;
-	u16 max_target;
-	u32 max_lun;
-} __packed;
+	__u32 num_queues;
+	__u32 seg_max;
+	__u32 max_sectors;
+	__u32 cmd_per_lun;
+	__u32 event_info_size;
+	__u32 sense_size;
+	__u32 cdb_size;
+	__u16 max_channel;
+	__u16 max_target;
+	__u32 max_lun;
+} __attribute__((packed));
 
 /* Feature Bits */
 #define VIRTIO_SCSI_F_INOUT                    0
-- 
cgit v1.2.3-70-g09d2


From 1f0f9106f92c7d49ec92baa6ac757aa8b0590eff Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Mon, 1 Dec 2014 13:17:40 +0200
Subject: virtio_console: virtio 1.0 support

Pretty straight-forward, just use accessors for all fields.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/char/virtio_console.c       | 29 +++++++++++++++++------------
 include/uapi/linux/virtio_console.h |  7 ++++---
 2 files changed, 21 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 8d00aa7f60f..775c8982136 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -566,9 +566,9 @@ static ssize_t __send_control_msg(struct ports_device *portdev, u32 port_id,
 	if (!use_multiport(portdev))
 		return 0;
 
-	cpkt.id = port_id;
-	cpkt.event = event;
-	cpkt.value = value;
+	cpkt.id = cpu_to_virtio32(portdev->vdev, port_id);
+	cpkt.event = cpu_to_virtio16(portdev->vdev, event);
+	cpkt.value = cpu_to_virtio16(portdev->vdev, value);
 
 	vq = portdev->c_ovq;
 
@@ -1602,7 +1602,8 @@ static void unplug_port(struct port *port)
 }
 
 /* Any private messages that the Host and Guest want to share */
-static void handle_control_message(struct ports_device *portdev,
+static void handle_control_message(struct virtio_device *vdev,
+				   struct ports_device *portdev,
 				   struct port_buffer *buf)
 {
 	struct virtio_console_control *cpkt;
@@ -1612,15 +1613,16 @@ static void handle_control_message(struct ports_device *portdev,
 
 	cpkt = (struct virtio_console_control *)(buf->buf + buf->offset);
 
-	port = find_port_by_id(portdev, cpkt->id);
-	if (!port && cpkt->event != VIRTIO_CONSOLE_PORT_ADD) {
+	port = find_port_by_id(portdev, virtio32_to_cpu(vdev, cpkt->id));
+	if (!port &&
+	    cpkt->event != cpu_to_virtio16(vdev, VIRTIO_CONSOLE_PORT_ADD)) {
 		/* No valid header at start of buffer.  Drop it. */
 		dev_dbg(&portdev->vdev->dev,
 			"Invalid index %u in control packet\n", cpkt->id);
 		return;
 	}
 
-	switch (cpkt->event) {
+	switch (virtio16_to_cpu(vdev, cpkt->event)) {
 	case VIRTIO_CONSOLE_PORT_ADD:
 		if (port) {
 			dev_dbg(&portdev->vdev->dev,
@@ -1628,13 +1630,15 @@ static void handle_control_message(struct ports_device *portdev,
 			send_control_msg(port, VIRTIO_CONSOLE_PORT_READY, 1);
 			break;
 		}
-		if (cpkt->id >= portdev->config.max_nr_ports) {
+		if (virtio32_to_cpu(vdev, cpkt->id) >=
+		    portdev->config.max_nr_ports) {
 			dev_warn(&portdev->vdev->dev,
-				"Request for adding port with out-of-bound id %u, max. supported id: %u\n",
+				"Request for adding port with "
+				"out-of-bound id %u, max. supported id: %u\n",
 				cpkt->id, portdev->config.max_nr_ports - 1);
 			break;
 		}
-		add_port(portdev, cpkt->id);
+		add_port(portdev, virtio32_to_cpu(vdev, cpkt->id));
 		break;
 	case VIRTIO_CONSOLE_PORT_REMOVE:
 		unplug_port(port);
@@ -1670,7 +1674,7 @@ static void handle_control_message(struct ports_device *portdev,
 		break;
 	}
 	case VIRTIO_CONSOLE_PORT_OPEN:
-		port->host_connected = cpkt->value;
+		port->host_connected = virtio16_to_cpu(vdev, cpkt->value);
 		wake_up_interruptible(&port->waitqueue);
 		/*
 		 * If the host port got closed and the host had any
@@ -1752,7 +1756,7 @@ static void control_work_handler(struct work_struct *work)
 		buf->len = len;
 		buf->offset = 0;
 
-		handle_control_message(portdev, buf);
+		handle_control_message(vq->vdev, portdev, buf);
 
 		spin_lock(&portdev->c_ivq_lock);
 		if (add_inbuf(portdev->c_ivq, buf) < 0) {
@@ -2126,6 +2130,7 @@ static struct virtio_device_id id_table[] = {
 static unsigned int features[] = {
 	VIRTIO_CONSOLE_F_SIZE,
 	VIRTIO_CONSOLE_F_MULTIPORT,
+	VIRTIO_F_VERSION_1,
 };
 
 static struct virtio_device_id rproc_serial_id_table[] = {
diff --git a/include/uapi/linux/virtio_console.h b/include/uapi/linux/virtio_console.h
index ba260dd0b33..b7fb108c931 100644
--- a/include/uapi/linux/virtio_console.h
+++ b/include/uapi/linux/virtio_console.h
@@ -32,6 +32,7 @@
 #ifndef _UAPI_LINUX_VIRTIO_CONSOLE_H
 #define _UAPI_LINUX_VIRTIO_CONSOLE_H
 #include <linux/types.h>
+#include <linux/virtio_types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
 
@@ -58,9 +59,9 @@ struct virtio_console_config {
  * particular port.
  */
 struct virtio_console_control {
-	__u32 id;		/* Port number */
-	__u16 event;		/* The kind of control event (see below) */
-	__u16 value;		/* Extra information for the key */
+	__virtio32 id;		/* Port number */
+	__virtio16 event;	/* The kind of control event (see below) */
+	__virtio16 value;	/* Extra information for the key */
 };
 
 /* Some events for control messages */
-- 
cgit v1.2.3-70-g09d2


From df1b57fe59bc5b1486fe142e6ee76c493c52c543 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Mon, 1 Dec 2014 15:50:29 +0200
Subject: virtio_balloon: add legacy_only flag

We have no plans to support virtio 1.0 in balloon driver.  Add an
explicit flag to mark it legacy only.

This will be used by follow-up patches.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_balloon.c | 1 +
 include/linux/virtio.h          | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index c9703d4d6f6..4497def48da 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -518,6 +518,7 @@ static unsigned int features[] = {
 };
 
 static struct virtio_driver virtio_balloon_driver = {
+	.legacy_only = true,
 	.feature_table = features,
 	.feature_table_size = ARRAY_SIZE(features),
 	.driver.name =	KBUILD_MODNAME,
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index f70411eb9d2..2bbf6269767 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -132,6 +132,7 @@ int virtio_device_restore(struct virtio_device *dev);
  * @feature_table_size: number of entries in the feature table array.
  * @feature_table_legacy: same as feature_table but when working in legacy mode.
  * @feature_table_size_legacy: number of entries in feature table legacy array.
+ * @legacy_only: driver does not support virtio 1.0.
  * @probe: the function to call when a device is found.  Returns 0 or -errno.
  * @remove: the function to call when a device is removed.
  * @config_changed: optional function to call when the device configuration
@@ -144,6 +145,7 @@ struct virtio_driver {
 	unsigned int feature_table_size;
 	const unsigned int *feature_table_legacy;
 	unsigned int feature_table_size_legacy;
+	bool legacy_only;
 	int (*probe)(struct virtio_device *dev);
 	void (*scan)(struct virtio_device *dev);
 	void (*remove)(struct virtio_device *dev);
-- 
cgit v1.2.3-70-g09d2


From 747ae34a6ef681fbd993be214d8c0a30bd4a2fda Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Mon, 1 Dec 2014 15:52:40 +0200
Subject: virtio: make VIRTIO_F_VERSION_1 a transport bit

Activate VIRTIO_F_VERSION_1 automatically unless legacy_only
is set.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio.c            | 6 +++++-
 drivers/virtio/virtio_ring.c       | 2 ++
 include/uapi/linux/virtio_config.h | 4 ++--
 3 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index f9ad99c8b35..fa6b75db5f1 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -197,7 +197,11 @@ static int virtio_dev_probe(struct device *_d)
 		driver_features_legacy = driver_features;
 	}
 
-	if (driver_features & device_features & (1ULL << VIRTIO_F_VERSION_1))
+	/* Detect legacy-only drivers and disable VIRTIO_F_VERSION_1. */
+	if (drv->legacy_only)
+		device_features &= ~(1ULL << VIRTIO_F_VERSION_1);
+
+	if (device_features & (1ULL << VIRTIO_F_VERSION_1))
 		dev->features = driver_features & device_features;
 	else
 		dev->features = driver_features_legacy & device_features;
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 55532a43ead..00ec6b3f96b 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -780,6 +780,8 @@ void vring_transport_features(struct virtio_device *vdev)
 			break;
 		case VIRTIO_RING_F_EVENT_IDX:
 			break;
+		case VIRTIO_F_VERSION_1:
+			break;
 		default:
 			/* We don't understand this bit. */
 			__virtio_clear_bit(vdev, i);
diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index 4d05671fbae..a6d0cdeaacd 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -43,11 +43,11 @@
 /* We've given up on this device. */
 #define VIRTIO_CONFIG_S_FAILED		0x80
 
-/* Some virtio feature bits (currently bits 28 through 31) are reserved for the
+/* Some virtio feature bits (currently bits 28 through 32) are reserved for the
  * transport being used (eg. virtio_ring), the rest are per-device feature
  * bits. */
 #define VIRTIO_TRANSPORT_F_START	28
-#define VIRTIO_TRANSPORT_F_END		32
+#define VIRTIO_TRANSPORT_F_END		33
 
 /* Do we get callbacks when the ring is completely used, even if we've
  * suppressed them? */
-- 
cgit v1.2.3-70-g09d2


From b6098c30423cb1f0f5a4d0a5495e2670e274e544 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 4 Dec 2014 18:49:58 +0200
Subject: virtio: add API to detect legacy devices

transports need to be able to detect legacy-only
devices (ATM balloon only) to use legacy path
to drive them.

Add a core API to do just that.
The implementation just blacklists balloon:
not too pretty, but let's not over-engineer.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
 drivers/virtio/virtio.c | 7 +++++++
 include/linux/virtio.h  | 2 ++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index fa6b75db5f1..224f85442f3 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -3,6 +3,7 @@
 #include <linux/virtio_config.h>
 #include <linux/module.h>
 #include <linux/idr.h>
+#include <uapi/linux/virtio_ids.h>
 
 /* Unique numbering for virtio devices. */
 static DEFINE_IDA(virtio_index_ida);
@@ -267,6 +268,12 @@ static struct bus_type virtio_bus = {
 	.remove = virtio_dev_remove,
 };
 
+bool virtio_device_is_legacy_only(struct virtio_device_id id)
+{
+	return id.device == VIRTIO_ID_BALLOON;
+}
+EXPORT_SYMBOL_GPL(virtio_device_is_legacy_only);
+
 int register_virtio_driver(struct virtio_driver *driver)
 {
 	/* Catch this early. */
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 2bbf6269767..d666bcb5740 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -108,6 +108,8 @@ struct virtio_device {
 	void *priv;
 };
 
+bool virtio_device_is_legacy_only(struct virtio_device_id id);
+
 static inline struct virtio_device *dev_to_virtio(struct device *_dev)
 {
 	return container_of(_dev, struct virtio_device, dev);
-- 
cgit v1.2.3-70-g09d2


From 5c609a5ef05d98e26778824ba84581fe5e400db6 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 4 Dec 2014 20:20:27 +0200
Subject: virtio: allow finalize_features to fail

This will make it easy for transports to validate features and return
failure.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/lguest/lguest_device.c         |  4 +++-
 drivers/misc/mic/card/mic_virtio.c     |  4 +++-
 drivers/remoteproc/remoteproc_virtio.c |  4 +++-
 drivers/s390/kvm/kvm_virtio.c          |  4 +++-
 drivers/s390/kvm/virtio_ccw.c          |  6 ++++--
 drivers/virtio/virtio.c                | 21 ++++++++++++++-------
 drivers/virtio/virtio_mmio.c           |  4 +++-
 drivers/virtio/virtio_pci.c            |  4 +++-
 include/linux/virtio_config.h          |  3 ++-
 9 files changed, 38 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c
index 9b77b6623ff..89088d6538f 100644
--- a/drivers/lguest/lguest_device.c
+++ b/drivers/lguest/lguest_device.c
@@ -126,7 +126,7 @@ static void status_notify(struct virtio_device *vdev)
  * sorted out, this routine is called so we can tell the Host which features we
  * understand and accept.
  */
-static void lg_finalize_features(struct virtio_device *vdev)
+static int lg_finalize_features(struct virtio_device *vdev)
 {
 	unsigned int i, bits;
 	struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
@@ -153,6 +153,8 @@ static void lg_finalize_features(struct virtio_device *vdev)
 
 	/* Tell Host we've finished with this device's feature negotiation */
 	status_notify(vdev);
+
+	return 0;
 }
 
 /* Once they've found a field, getting a copy of it is easy. */
diff --git a/drivers/misc/mic/card/mic_virtio.c b/drivers/misc/mic/card/mic_virtio.c
index d027d299602..e486a0c2626 100644
--- a/drivers/misc/mic/card/mic_virtio.c
+++ b/drivers/misc/mic/card/mic_virtio.c
@@ -84,7 +84,7 @@ static u64 mic_get_features(struct virtio_device *vdev)
 	return features;
 }
 
-static void mic_finalize_features(struct virtio_device *vdev)
+static int mic_finalize_features(struct virtio_device *vdev)
 {
 	unsigned int i, bits;
 	struct mic_device_desc __iomem *desc = to_micvdev(vdev)->desc;
@@ -107,6 +107,8 @@ static void mic_finalize_features(struct virtio_device *vdev)
 			iowrite8(ioread8(&out_features[i / 8]) | (1 << (i % 8)),
 				 &out_features[i / 8]);
 	}
+
+	return 0;
 }
 
 /*
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index 627737ee763..e1a10232a94 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -217,7 +217,7 @@ static u64 rproc_virtio_get_features(struct virtio_device *vdev)
 	return rsc->dfeatures;
 }
 
-static void rproc_virtio_finalize_features(struct virtio_device *vdev)
+static int rproc_virtio_finalize_features(struct virtio_device *vdev)
 {
 	struct rproc_vdev *rvdev = vdev_to_rvdev(vdev);
 	struct fw_rsc_vdev *rsc;
@@ -235,6 +235,8 @@ static void rproc_virtio_finalize_features(struct virtio_device *vdev)
 	 * to the remote processor once it is powered on.
 	 */
 	rsc->gfeatures = vdev->features;
+
+	return 0;
 }
 
 static void rproc_virtio_get(struct virtio_device *vdev, unsigned offset,
diff --git a/drivers/s390/kvm/kvm_virtio.c b/drivers/s390/kvm/kvm_virtio.c
index f5575ccdbb6..dd65c8b4c7f 100644
--- a/drivers/s390/kvm/kvm_virtio.c
+++ b/drivers/s390/kvm/kvm_virtio.c
@@ -93,7 +93,7 @@ static u64 kvm_get_features(struct virtio_device *vdev)
 	return features;
 }
 
-static void kvm_finalize_features(struct virtio_device *vdev)
+static int kvm_finalize_features(struct virtio_device *vdev)
 {
 	unsigned int i, bits;
 	struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
@@ -112,6 +112,8 @@ static void kvm_finalize_features(struct virtio_device *vdev)
 		if (__virtio_test_bit(vdev, i))
 			out_features[i / 8] |= (1 << (i % 8));
 	}
+
+	return 0;
 }
 
 /*
diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c
index c792b5fe0bc..789275fb577 100644
--- a/drivers/s390/kvm/virtio_ccw.c
+++ b/drivers/s390/kvm/virtio_ccw.c
@@ -752,7 +752,7 @@ out_free:
 	return rc;
 }
 
-static void virtio_ccw_finalize_features(struct virtio_device *vdev)
+static int virtio_ccw_finalize_features(struct virtio_device *vdev)
 {
 	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
 	struct virtio_feature_desc *features;
@@ -760,7 +760,7 @@ static void virtio_ccw_finalize_features(struct virtio_device *vdev)
 
 	ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
 	if (!ccw)
-		return;
+		return 0;
 
 	features = kzalloc(sizeof(*features), GFP_DMA | GFP_KERNEL);
 	if (!features)
@@ -793,6 +793,8 @@ static void virtio_ccw_finalize_features(struct virtio_device *vdev)
 out_free:
 	kfree(features);
 	kfree(ccw);
+
+	return 0;
 }
 
 static void virtio_ccw_get_config(struct virtio_device *vdev,
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 224f85442f3..e1673a511d1 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -212,7 +212,9 @@ static int virtio_dev_probe(struct device *_d)
 		if (device_features & (1ULL << i))
 			__virtio_set_bit(dev, i);
 
-	dev->config->finalize_features(dev);
+	err = dev->config->finalize_features(dev);
+	if (err)
+		goto err;
 
 	if (virtio_has_feature(dev, VIRTIO_F_VERSION_1)) {
 		add_status(dev, VIRTIO_CONFIG_S_FEATURES_OK);
@@ -354,6 +356,7 @@ EXPORT_SYMBOL_GPL(virtio_device_freeze);
 int virtio_device_restore(struct virtio_device *dev)
 {
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+	int ret;
 
 	/* We always start by resetting the device, in case a previous
 	 * driver messed it up. */
@@ -373,14 +376,14 @@ int virtio_device_restore(struct virtio_device *dev)
 	/* We have a driver! */
 	add_status(dev, VIRTIO_CONFIG_S_DRIVER);
 
-	dev->config->finalize_features(dev);
+	ret = dev->config->finalize_features(dev);
+	if (ret)
+		goto err;
 
 	if (drv->restore) {
-		int ret = drv->restore(dev);
-		if (ret) {
-			add_status(dev, VIRTIO_CONFIG_S_FAILED);
-			return ret;
-		}
+		ret = drv->restore(dev);
+		if (ret)
+			goto err;
 	}
 
 	/* Finally, tell the device we're all set */
@@ -389,6 +392,10 @@ int virtio_device_restore(struct virtio_device *dev)
 	virtio_config_enable(dev);
 
 	return 0;
+
+err:
+	add_status(dev, VIRTIO_CONFIG_S_FAILED);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(virtio_device_restore);
 #endif
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index aec1daee9ad..5219210d31c 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -152,7 +152,7 @@ static u64 vm_get_features(struct virtio_device *vdev)
 	return readl(vm_dev->base + VIRTIO_MMIO_HOST_FEATURES);
 }
 
-static void vm_finalize_features(struct virtio_device *vdev)
+static int vm_finalize_features(struct virtio_device *vdev)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 
@@ -164,6 +164,8 @@ static void vm_finalize_features(struct virtio_device *vdev)
 
 	writel(0, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES_SEL);
 	writel(vdev->features, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES);
+
+	return 0;
 }
 
 static void vm_get(struct virtio_device *vdev, unsigned offset,
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index dd6df979862..9be59d9f2f1 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -112,7 +112,7 @@ static u64 vp_get_features(struct virtio_device *vdev)
 }
 
 /* virtio config->finalize_features() implementation */
-static void vp_finalize_features(struct virtio_device *vdev)
+static int vp_finalize_features(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 
@@ -124,6 +124,8 @@ static void vp_finalize_features(struct virtio_device *vdev)
 
 	/* We only support 32 feature bits. */
 	iowrite32(vdev->features, vp_dev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
+
+	return 0;
 }
 
 /* virtio config->get() implementation */
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 1fa5faa2644..7979f850e7a 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -47,6 +47,7 @@
  *	vdev: the virtio_device
  *	This gives the final feature bits for the device: it can change
  *	the dev->feature bits if it wants.
+ *	Returns 0 on success or error status
  * @bus_name: return the bus name associated with the device
  *	vdev: the virtio_device
  *      This returns a pointer to the bus name a la pci_name from which
@@ -68,7 +69,7 @@ struct virtio_config_ops {
 			const char *names[]);
 	void (*del_vqs)(struct virtio_device *);
 	u64 (*get_features)(struct virtio_device *vdev);
-	void (*finalize_features)(struct virtio_device *vdev);
+	int (*finalize_features)(struct virtio_device *vdev);
 	const char *(*bus_name)(struct virtio_device *vdev);
 	int (*set_vq_affinity)(struct virtqueue *vq, int cpu);
 };
-- 
cgit v1.2.3-70-g09d2


From 4d152e2c9a6a3e3556ce5da7782a9e2836edbe0f Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Wed, 19 Nov 2014 07:51:14 -0500
Subject: sunrpc: add a generic rq_flags field to svc_rqst and move rq_secure
 to it

In a later patch, we're going to need some atomic bit flags. Since that
field will need to be an unsigned long, we mitigate that space
consumption by migrating some other bitflags to the new field. Start
with the rq_secure flag.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfscache.c            |  4 ++--
 fs/nfsd/nfsfh.c               |  2 +-
 include/linux/sunrpc/svc.h    |  4 ++--
 include/trace/events/sunrpc.h | 17 +++++++++++++----
 net/sunrpc/svc_xprt.c         |  5 ++++-
 5 files changed, 22 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 122f69185ef..83a9694ec48 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -490,7 +490,7 @@ found_entry:
 	/* From the hall of fame of impractical attacks:
 	 * Is this a user who tries to snoop on the cache? */
 	rtn = RC_DOIT;
-	if (!rqstp->rq_secure && rp->c_secure)
+	if (!test_bit(RQ_SECURE, &rqstp->rq_flags) && rp->c_secure)
 		goto out;
 
 	/* Compose RPC reply header */
@@ -579,7 +579,7 @@ nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
 	spin_lock(&b->cache_lock);
 	drc_mem_usage += bufsize;
 	lru_put_end(b, rp);
-	rp->c_secure = rqstp->rq_secure;
+	rp->c_secure = test_bit(RQ_SECURE, &rqstp->rq_flags);
 	rp->c_type = cachetype;
 	rp->c_state = RC_DONE;
 	spin_unlock(&b->cache_lock);
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 88026fc6a98..965b478d50f 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -86,7 +86,7 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
 	int flags = nfsexp_flags(rqstp, exp);
 
 	/* Check if the request originated from a secure port. */
-	if (!rqstp->rq_secure && !(flags & NFSEXP_INSECURE_PORT)) {
+	if (!test_bit(RQ_SECURE, &rqstp->rq_flags) && !(flags & NFSEXP_INSECURE_PORT)) {
 		RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
 		dprintk("nfsd: request from insecure port %s!\n",
 		        svc_print_addr(rqstp, buf, sizeof(buf)));
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 21678464883..b60eb7c3f3f 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -253,8 +253,8 @@ struct svc_rqst {
 	u32			rq_vers;	/* program version */
 	u32			rq_proc;	/* procedure number */
 	u32			rq_prot;	/* IP protocol */
-	unsigned short
-				rq_secure  : 1;	/* secure port */
+#define	RQ_SECURE	(0)			/* secure port */
+	unsigned long		rq_flags;	/* flags field */
 	unsigned short		rq_local   : 1;	/* local request */
 
 	void *			rq_argp;	/* decoded arguments */
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 171ca4ff6d9..5eb5f79d979 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -412,6 +412,10 @@ TRACE_EVENT(xs_tcp_data_recv,
 			__entry->copied, __entry->reclen, __entry->offset)
 );
 
+#define show_rqstp_flags(flags)				\
+	__print_flags(flags, "|",			\
+		{ (1UL << RQ_SECURE),	"RQ_SECURE"})
+
 TRACE_EVENT(svc_recv,
 	TP_PROTO(struct svc_rqst *rqst, int status),
 
@@ -421,16 +425,19 @@ TRACE_EVENT(svc_recv,
 		__field(struct sockaddr *, addr)
 		__field(__be32, xid)
 		__field(int, status)
+		__field(unsigned long, flags)
 	),
 
 	TP_fast_assign(
 		__entry->addr = (struct sockaddr *)&rqst->rq_addr;
 		__entry->xid = status > 0 ? rqst->rq_xid : 0;
 		__entry->status = status;
+		__entry->flags = rqst->rq_flags;
 	),
 
-	TP_printk("addr=%pIScp xid=0x%x status=%d", __entry->addr,
-			be32_to_cpu(__entry->xid), __entry->status)
+	TP_printk("addr=%pIScp xid=0x%x status=%d flags=%s", __entry->addr,
+			be32_to_cpu(__entry->xid), __entry->status,
+			show_rqstp_flags(__entry->flags))
 );
 
 DECLARE_EVENT_CLASS(svc_rqst_status,
@@ -444,6 +451,7 @@ DECLARE_EVENT_CLASS(svc_rqst_status,
 		__field(__be32, xid)
 		__field(int, dropme)
 		__field(int, status)
+		__field(unsigned long, flags)
 	),
 
 	TP_fast_assign(
@@ -451,11 +459,12 @@ DECLARE_EVENT_CLASS(svc_rqst_status,
 		__entry->xid = rqst->rq_xid;
 		__entry->dropme = (int)rqst->rq_dropme;
 		__entry->status = status;
+		__entry->flags = rqst->rq_flags;
 	),
 
-	TP_printk("addr=%pIScp rq_xid=0x%x dropme=%d status=%d",
+	TP_printk("addr=%pIScp rq_xid=0x%x dropme=%d status=%d flags=%s",
 		__entry->addr, be32_to_cpu(__entry->xid), __entry->dropme,
-		__entry->status)
+		__entry->status, show_rqstp_flags(__entry->flags))
 );
 
 DEFINE_EVENT(svc_rqst_status, svc_process,
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 5c71ccb9659..eaa9263c2d2 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -797,7 +797,10 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 
 	clear_bit(XPT_OLD, &xprt->xpt_flags);
 
-	rqstp->rq_secure = xprt->xpt_ops->xpo_secure_port(rqstp);
+	if (xprt->xpt_ops->xpo_secure_port(rqstp))
+		set_bit(RQ_SECURE, &rqstp->rq_flags);
+	else
+		clear_bit(RQ_SECURE, &rqstp->rq_flags);
 	rqstp->rq_chandle.defer = svc_defer;
 	rqstp->rq_xid = svc_getu32(&rqstp->rq_arg.head[0]);
 
-- 
cgit v1.2.3-70-g09d2


From 7501cc2bcf9a71cc1f19e38775c234815ee44578 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Wed, 19 Nov 2014 07:51:15 -0500
Subject: sunrpc: move rq_local field to rq_flags

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/vfs.c                 | 4 ++--
 include/linux/sunrpc/svc.h    | 2 +-
 include/trace/events/sunrpc.h | 3 ++-
 net/sunrpc/svcsock.c          | 5 ++++-
 4 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index f1999619d51..60c25850fb1 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -962,7 +962,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	loff_t			end = LLONG_MAX;
 	unsigned int		pflags = current->flags;
 
-	if (rqstp->rq_local)
+	if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
 		/*
 		 * We want less throttling in balance_dirty_pages()
 		 * and shrink_inactive_list() so that nfs to
@@ -1006,7 +1006,7 @@ out_nfserr:
 		err = 0;
 	else
 		err = nfserrno(host_err);
-	if (rqstp->rq_local)
+	if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
 		tsk_restore_flags(current, pflags, PF_LESS_THROTTLE);
 	return err;
 }
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index b60eb7c3f3f..a91df9047f3 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -254,8 +254,8 @@ struct svc_rqst {
 	u32			rq_proc;	/* procedure number */
 	u32			rq_prot;	/* IP protocol */
 #define	RQ_SECURE	(0)			/* secure port */
+#define	RQ_LOCAL	(1)			/* local request */
 	unsigned long		rq_flags;	/* flags field */
-	unsigned short		rq_local   : 1;	/* local request */
 
 	void *			rq_argp;	/* decoded arguments */
 	void *			rq_resp;	/* xdr'd results */
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 5eb5f79d979..98259f163cd 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -414,7 +414,8 @@ TRACE_EVENT(xs_tcp_data_recv,
 
 #define show_rqstp_flags(flags)				\
 	__print_flags(flags, "|",			\
-		{ (1UL << RQ_SECURE),	"RQ_SECURE"})
+		{ (1UL << RQ_SECURE),	"RQ_SECURE"},	\
+		{ (1UL << RQ_LOCAL),	"RQ_LOCAL"})
 
 TRACE_EVENT(svc_recv,
 	TP_PROTO(struct svc_rqst *rqst, int status),
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index f9c052d508f..cc331b6cf57 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1145,7 +1145,10 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 
 	rqstp->rq_xprt_ctxt   = NULL;
 	rqstp->rq_prot	      = IPPROTO_TCP;
-	rqstp->rq_local	      = !!test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags);
+	if (test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags))
+		set_bit(RQ_LOCAL, &rqstp->rq_flags);
+	else
+		clear_bit(RQ_LOCAL, &rqstp->rq_flags);
 
 	p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
 	calldir = p[1];
-- 
cgit v1.2.3-70-g09d2


From 30660e04b0d4bbbd15fd21098681f45a9f4080b9 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Wed, 19 Nov 2014 07:51:16 -0500
Subject: sunrpc: move rq_usedeferral flag to rq_flags

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs4proc.c            | 4 ++--
 include/linux/sunrpc/svc.h    | 2 +-
 include/trace/events/sunrpc.h | 9 +++++----
 net/sunrpc/svc.c              | 2 +-
 net/sunrpc/svc_xprt.c         | 2 +-
 5 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 74fb15eefc3..6f98393ad0d 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1370,7 +1370,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 	 * Don't use the deferral mechanism for NFSv4; compounds make it
 	 * too hard to avoid non-idempotency problems.
 	 */
-	rqstp->rq_usedeferral = false;
+	clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
 
 	/*
 	 * According to RFC3010, this takes precedence over all other errors.
@@ -1486,7 +1486,7 @@ encode_op:
 	BUG_ON(cstate->replay_owner);
 out:
 	/* Reset deferral mechanism for RPC deferrals */
-	rqstp->rq_usedeferral = true;
+	set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
 	dprintk("nfsv4 compound returned %d\n", ntohl(status));
 	return status;
 }
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index a91df9047f3..6a3cf4c76dc 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -236,7 +236,6 @@ struct svc_rqst {
 	struct svc_cred		rq_cred;	/* auth info */
 	void *			rq_xprt_ctxt;	/* transport specific context ptr */
 	struct svc_deferred_req*rq_deferred;	/* deferred request we are replaying */
-	bool			rq_usedeferral;	/* use deferral */
 
 	size_t			rq_xprt_hlen;	/* xprt header len */
 	struct xdr_buf		rq_arg;
@@ -255,6 +254,7 @@ struct svc_rqst {
 	u32			rq_prot;	/* IP protocol */
 #define	RQ_SECURE	(0)			/* secure port */
 #define	RQ_LOCAL	(1)			/* local request */
+#define	RQ_USEDEFERRAL	(2)			/* use deferral */
 	unsigned long		rq_flags;	/* flags field */
 
 	void *			rq_argp;	/* decoded arguments */
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 98259f163cd..6d1facdebc9 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -412,10 +412,11 @@ TRACE_EVENT(xs_tcp_data_recv,
 			__entry->copied, __entry->reclen, __entry->offset)
 );
 
-#define show_rqstp_flags(flags)				\
-	__print_flags(flags, "|",			\
-		{ (1UL << RQ_SECURE),	"RQ_SECURE"},	\
-		{ (1UL << RQ_LOCAL),	"RQ_LOCAL"})
+#define show_rqstp_flags(flags)						\
+	__print_flags(flags, "|",					\
+		{ (1UL << RQ_SECURE),		"RQ_SECURE"},		\
+		{ (1UL << RQ_LOCAL),		"RQ_LOCAL"},		\
+		{ (1UL << RQ_USEDEFERRAL),	"RQ_USEDEFERRAL"})
 
 TRACE_EVENT(svc_recv,
 	TP_PROTO(struct svc_rqst *rqst, int status),
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 163df468d6d..f6a8f2f7a25 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1090,7 +1090,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 	/* Will be turned off only in gss privacy case: */
 	rqstp->rq_splice_ok = true;
 	/* Will be turned off only when NFSv4 Sessions are used */
-	rqstp->rq_usedeferral = true;
+	set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
 	rqstp->rq_dropme = false;
 
 	/* Setup reply header */
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index eaa9263c2d2..a40f3755a33 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -1081,7 +1081,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
 	struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle);
 	struct svc_deferred_req *dr;
 
-	if (rqstp->rq_arg.page_len || !rqstp->rq_usedeferral)
+	if (rqstp->rq_arg.page_len || !test_bit(RQ_USEDEFERRAL, &rqstp->rq_flags))
 		return NULL; /* if more than a page, give up FIXME */
 	if (rqstp->rq_deferred) {
 		dr = rqstp->rq_deferred;
-- 
cgit v1.2.3-70-g09d2


From 78b65eb3fda95c6d131c4bbb0536e21f0bd7a7d4 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Wed, 19 Nov 2014 07:51:17 -0500
Subject: sunrpc: move rq_dropme flag into rq_flags

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfssvc.c              | 2 +-
 include/linux/sunrpc/svc.h    | 2 +-
 include/trace/events/sunrpc.h | 8 ++++----
 net/sunrpc/svc.c              | 4 ++--
 net/sunrpc/svc_xprt.c         | 2 +-
 5 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 752d56bbe0b..314f5c8f8f1 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -692,7 +692,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	/* Now call the procedure handler, and encode NFS status. */
 	nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
 	nfserr = map_new_errors(rqstp->rq_vers, nfserr);
-	if (nfserr == nfserr_dropit || rqstp->rq_dropme) {
+	if (nfserr == nfserr_dropit || test_bit(RQ_DROPME, &rqstp->rq_flags)) {
 		dprintk("nfsd: Dropping request; may be revisited later\n");
 		nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
 		return 0;
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 6a3cf4c76dc..d4ea3e5246b 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -255,6 +255,7 @@ struct svc_rqst {
 #define	RQ_SECURE	(0)			/* secure port */
 #define	RQ_LOCAL	(1)			/* local request */
 #define	RQ_USEDEFERRAL	(2)			/* use deferral */
+#define	RQ_DROPME	(3)			/* drop current reply */
 	unsigned long		rq_flags;	/* flags field */
 
 	void *			rq_argp;	/* decoded arguments */
@@ -271,7 +272,6 @@ struct svc_rqst {
 	struct cache_req	rq_chandle;	/* handle passed to caches for 
 						 * request delaying 
 						 */
-	bool			rq_dropme;
 	/* Catering to nfsd */
 	struct auth_domain *	rq_client;	/* RPC peer info */
 	struct auth_domain *	rq_gssclient;	/* "gss/"-style peer info */
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 6d1facdebc9..355671f19a9 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -416,7 +416,8 @@ TRACE_EVENT(xs_tcp_data_recv,
 	__print_flags(flags, "|",					\
 		{ (1UL << RQ_SECURE),		"RQ_SECURE"},		\
 		{ (1UL << RQ_LOCAL),		"RQ_LOCAL"},		\
-		{ (1UL << RQ_USEDEFERRAL),	"RQ_USEDEFERRAL"})
+		{ (1UL << RQ_USEDEFERRAL),	"RQ_USEDEFERRAL"},	\
+		{ (1UL << RQ_DROPME),		"RQ_DROPME"})
 
 TRACE_EVENT(svc_recv,
 	TP_PROTO(struct svc_rqst *rqst, int status),
@@ -459,13 +460,12 @@ DECLARE_EVENT_CLASS(svc_rqst_status,
 	TP_fast_assign(
 		__entry->addr = (struct sockaddr *)&rqst->rq_addr;
 		__entry->xid = rqst->rq_xid;
-		__entry->dropme = (int)rqst->rq_dropme;
 		__entry->status = status;
 		__entry->flags = rqst->rq_flags;
 	),
 
-	TP_printk("addr=%pIScp rq_xid=0x%x dropme=%d status=%d flags=%s",
-		__entry->addr, be32_to_cpu(__entry->xid), __entry->dropme,
+	TP_printk("addr=%pIScp rq_xid=0x%x status=%d flags=%s",
+		__entry->addr, be32_to_cpu(__entry->xid),
 		__entry->status, show_rqstp_flags(__entry->flags))
 );
 
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index f6a8f2f7a25..d8a9d603b78 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1091,7 +1091,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 	rqstp->rq_splice_ok = true;
 	/* Will be turned off only when NFSv4 Sessions are used */
 	set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
-	rqstp->rq_dropme = false;
+	clear_bit(RQ_DROPME, &rqstp->rq_flags);
 
 	/* Setup reply header */
 	rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
@@ -1191,7 +1191,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		*statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
 
 		/* Encode reply */
-		if (rqstp->rq_dropme) {
+		if (test_bit(RQ_DROPME, &rqstp->rq_flags)) {
 			if (procp->pc_release)
 				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
 			goto dropit;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index a40f3755a33..143c4c8ea2f 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -1110,7 +1110,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
 	}
 	svc_xprt_get(rqstp->rq_xprt);
 	dr->xprt = rqstp->rq_xprt;
-	rqstp->rq_dropme = true;
+	set_bit(RQ_DROPME, &rqstp->rq_flags);
 
 	dr->handle.revisit = svc_revisit;
 	return &dr->handle;
-- 
cgit v1.2.3-70-g09d2


From 779fb0f3af3089daa2e88cf8ef0ef0c5d2fecb40 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Wed, 19 Nov 2014 07:51:18 -0500
Subject: sunrpc: move rq_splice_ok flag into rq_flags

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs4proc.c                | 2 +-
 fs/nfsd/nfs4xdr.c                 | 8 ++++----
 fs/nfsd/vfs.c                     | 2 +-
 include/linux/sunrpc/svc.h        | 6 +++---
 include/trace/events/sunrpc.h     | 3 ++-
 net/sunrpc/auth_gss/svcauth_gss.c | 2 +-
 net/sunrpc/svc.c                  | 2 +-
 7 files changed, 13 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 6f98393ad0d..ac71d13c69e 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -773,7 +773,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * the client wants us to do more in this compound:
 	 */
 	if (!nfsd4_last_compound_op(rqstp))
-		rqstp->rq_splice_ok = false;
+		clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 
 	/* check stateid */
 	if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp),
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 0622d4f4a9a..8880ec8cfd1 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1731,7 +1731,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 	argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE;
 
 	if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack)
-		argp->rqstp->rq_splice_ok = false;
+		clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
 
 	DECODE_TAIL;
 }
@@ -3253,10 +3253,10 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 
 	p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */
 	if (!p) {
-		WARN_ON_ONCE(resp->rqstp->rq_splice_ok);
+		WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags));
 		return nfserr_resource;
 	}
-	if (resp->xdr.buf->page_len && resp->rqstp->rq_splice_ok) {
+	if (resp->xdr.buf->page_len && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) {
 		WARN_ON_ONCE(1);
 		return nfserr_resource;
 	}
@@ -3273,7 +3273,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 			goto err_truncate;
 	}
 
-	if (file->f_op->splice_read && resp->rqstp->rq_splice_ok)
+	if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags))
 		err = nfsd4_encode_splice_read(resp, read, file, maxcount);
 	else
 		err = nfsd4_encode_readv(resp, read, file, maxcount);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 60c25850fb1..cb00e48bc2b 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -902,7 +902,7 @@ static __be32
 nfsd_vfs_read(struct svc_rqst *rqstp, struct file *file,
 	      loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
 {
-	if (file->f_op->splice_read && rqstp->rq_splice_ok)
+	if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags))
 		return nfsd_splice_read(rqstp, file, offset, count);
 	else
 		return nfsd_readv(file, offset, vec, vlen, count);
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index d4ea3e5246b..2714287fc4f 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -256,6 +256,9 @@ struct svc_rqst {
 #define	RQ_LOCAL	(1)			/* local request */
 #define	RQ_USEDEFERRAL	(2)			/* use deferral */
 #define	RQ_DROPME	(3)			/* drop current reply */
+#define	RQ_SPLICE_OK	(4)			/* turned off in gss privacy
+						 * to prevent encrypting page
+						 * cache pages */
 	unsigned long		rq_flags;	/* flags field */
 
 	void *			rq_argp;	/* decoded arguments */
@@ -277,9 +280,6 @@ struct svc_rqst {
 	struct auth_domain *	rq_gssclient;	/* "gss/"-style peer info */
 	int			rq_cachetype;
 	struct svc_cacherep *	rq_cacherep;	/* cache info */
-	bool			rq_splice_ok;   /* turned off in gss privacy
-						 * to prevent encrypting page
-						 * cache pages */
 	struct task_struct	*rq_task;	/* service thread */
 };
 
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 355671f19a9..5848fc23586 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -417,7 +417,8 @@ TRACE_EVENT(xs_tcp_data_recv,
 		{ (1UL << RQ_SECURE),		"RQ_SECURE"},		\
 		{ (1UL << RQ_LOCAL),		"RQ_LOCAL"},		\
 		{ (1UL << RQ_USEDEFERRAL),	"RQ_USEDEFERRAL"},	\
-		{ (1UL << RQ_DROPME),		"RQ_DROPME"})
+		{ (1UL << RQ_DROPME),		"RQ_DROPME"},		\
+		{ (1UL << RQ_SPLICE_OK),	"RQ_SPLICE_OK"})
 
 TRACE_EVENT(svc_recv,
 	TP_PROTO(struct svc_rqst *rqst, int status),
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index de856ddf5fe..224a82f24d3 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -886,7 +886,7 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs
 	u32 priv_len, maj_stat;
 	int pad, saved_len, remaining_len, offset;
 
-	rqstp->rq_splice_ok = false;
+	clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 
 	priv_len = svc_getnl(&buf->head[0]);
 	if (rqstp->rq_deferred) {
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index d8a9d603b78..2c1c49ebd84 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1088,7 +1088,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		goto err_short_len;
 
 	/* Will be turned off only in gss privacy case: */
-	rqstp->rq_splice_ok = true;
+	set_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 	/* Will be turned off only when NFSv4 Sessions are used */
 	set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
 	clear_bit(RQ_DROPME, &rqstp->rq_flags);
-- 
cgit v1.2.3-70-g09d2


From 62978b3c619422d0ea17dbd39efdb2328295bcfb Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Wed, 19 Nov 2014 07:51:19 -0500
Subject: sunrpc: move rq_cachetype field to better optimize space

There are a couple of holes in the svc_rqst field on x86_64. Move the
rq_cachetype to a different location to eliminate both of them.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 2714287fc4f..8054a30c8a9 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -252,6 +252,7 @@ struct svc_rqst {
 	u32			rq_vers;	/* program version */
 	u32			rq_proc;	/* procedure number */
 	u32			rq_prot;	/* IP protocol */
+	int			rq_cachetype;	/* catering to nfsd */
 #define	RQ_SECURE	(0)			/* secure port */
 #define	RQ_LOCAL	(1)			/* local request */
 #define	RQ_USEDEFERRAL	(2)			/* use deferral */
@@ -278,7 +279,6 @@ struct svc_rqst {
 	/* Catering to nfsd */
 	struct auth_domain *	rq_client;	/* RPC peer info */
 	struct auth_domain *	rq_gssclient;	/* "gss/"-style peer info */
-	int			rq_cachetype;
 	struct svc_cacherep *	rq_cacherep;	/* cache info */
 	struct task_struct	*rq_task;	/* service thread */
 };
-- 
cgit v1.2.3-70-g09d2


From 4d5db3f536ae3886ac86877742e6f8ce69a5de06 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Wed, 19 Nov 2014 07:51:20 -0500
Subject: sunrpc: convert sp_task_pending flag to use atomic bitops

In a later patch, we'll want to be able to handle this flag without
holding the sp_lock. Change this field to an unsigned long flags
field, and declare a new flag in it that can be managed with atomic
bitops.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc.h | 4 +++-
 net/sunrpc/svc_xprt.c      | 7 +++----
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 8054a30c8a9..5f0ab39bf7c 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -50,7 +50,9 @@ struct svc_pool {
 	unsigned int		sp_nrthreads;	/* # of threads in pool */
 	struct list_head	sp_all_threads;	/* all server threads */
 	struct svc_pool_stats	sp_stats;	/* statistics on pool operation */
-	int			sp_task_pending;/* has pending task */
+#define	SP_TASK_PENDING		(0)		/* still work to do even if no
+						 * xprt is queued. */
+	unsigned long		sp_flags;
 } ____cacheline_aligned_in_smp;
 
 /*
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 143c4c8ea2f..37446046f4b 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -509,7 +509,7 @@ void svc_wake_up(struct svc_serv *serv)
 			 */
 			wake_up_process(rqstp->rq_task);
 		} else
-			pool->sp_task_pending = 1;
+			set_bit(SP_TASK_PENDING, &pool->sp_flags);
 		spin_unlock_bh(&pool->sp_lock);
 	}
 }
@@ -644,10 +644,9 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 		 * long for cache updates.
 		 */
 		rqstp->rq_chandle.thread_wait = 1*HZ;
-		pool->sp_task_pending = 0;
+		clear_bit(SP_TASK_PENDING, &pool->sp_flags);
 	} else {
-		if (pool->sp_task_pending) {
-			pool->sp_task_pending = 0;
+		if (test_and_clear_bit(SP_TASK_PENDING, &pool->sp_flags)) {
 			xprt = ERR_PTR(-EAGAIN);
 			goto out;
 		}
-- 
cgit v1.2.3-70-g09d2


From 812443865c5fc255363d4a684a62c086af1addca Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 21 Nov 2014 14:19:28 -0500
Subject: sunrpc: add a rcu_head to svc_rqst and use kfree_rcu to free it

...also make the manipulation of sp_all_threads list use RCU-friendly
functions.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Tested-by: Chris Worley <chris.worley@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc.h    |  2 ++
 include/trace/events/sunrpc.h |  3 ++-
 net/sunrpc/svc.c              | 10 ++++++----
 3 files changed, 10 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 5f0ab39bf7c..7f80a99c59e 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -223,6 +223,7 @@ static inline void svc_putu32(struct kvec *iov, __be32 val)
 struct svc_rqst {
 	struct list_head	rq_list;	/* idle list */
 	struct list_head	rq_all;		/* all threads list */
+	struct rcu_head		rq_rcu_head;	/* for RCU deferred kfree */
 	struct svc_xprt *	rq_xprt;	/* transport ptr */
 
 	struct sockaddr_storage	rq_addr;	/* peer address */
@@ -262,6 +263,7 @@ struct svc_rqst {
 #define	RQ_SPLICE_OK	(4)			/* turned off in gss privacy
 						 * to prevent encrypting page
 						 * cache pages */
+#define	RQ_VICTIM	(5)			/* about to be shut down */
 	unsigned long		rq_flags;	/* flags field */
 
 	void *			rq_argp;	/* decoded arguments */
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 5848fc23586..08a5fed50f3 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -418,7 +418,8 @@ TRACE_EVENT(xs_tcp_data_recv,
 		{ (1UL << RQ_LOCAL),		"RQ_LOCAL"},		\
 		{ (1UL << RQ_USEDEFERRAL),	"RQ_USEDEFERRAL"},	\
 		{ (1UL << RQ_DROPME),		"RQ_DROPME"},		\
-		{ (1UL << RQ_SPLICE_OK),	"RQ_SPLICE_OK"})
+		{ (1UL << RQ_SPLICE_OK),	"RQ_SPLICE_OK"},	\
+		{ (1UL << RQ_VICTIM),		"RQ_VICTIM"})
 
 TRACE_EVENT(svc_recv,
 	TP_PROTO(struct svc_rqst *rqst, int status),
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index a06a891012e..b90d1bca434 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -616,7 +616,7 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
 	serv->sv_nrthreads++;
 	spin_lock_bh(&pool->sp_lock);
 	pool->sp_nrthreads++;
-	list_add(&rqstp->rq_all, &pool->sp_all_threads);
+	list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads);
 	spin_unlock_bh(&pool->sp_lock);
 	rqstp->rq_server = serv;
 	rqstp->rq_pool = pool;
@@ -684,7 +684,8 @@ found_pool:
 		 * so we don't try to kill it again.
 		 */
 		rqstp = list_entry(pool->sp_all_threads.next, struct svc_rqst, rq_all);
-		list_del_init(&rqstp->rq_all);
+		set_bit(RQ_VICTIM, &rqstp->rq_flags);
+		list_del_rcu(&rqstp->rq_all);
 		task = rqstp->rq_task;
 	}
 	spin_unlock_bh(&pool->sp_lock);
@@ -782,10 +783,11 @@ svc_exit_thread(struct svc_rqst *rqstp)
 
 	spin_lock_bh(&pool->sp_lock);
 	pool->sp_nrthreads--;
-	list_del(&rqstp->rq_all);
+	if (!test_and_set_bit(RQ_VICTIM, &rqstp->rq_flags))
+		list_del_rcu(&rqstp->rq_all);
 	spin_unlock_bh(&pool->sp_lock);
 
-	kfree(rqstp);
+	kfree_rcu(rqstp, rq_rcu_head);
 
 	/* Release the server */
 	if (serv)
-- 
cgit v1.2.3-70-g09d2


From 403c7b44441d60aba7f8a134c31279ffa60ea769 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 21 Nov 2014 14:19:29 -0500
Subject: sunrpc: fix potential races in pool_stats collection

In a later patch, we'll be removing some spinlocking around the socket
and thread queueing code in order to fix some contention problems. At
that point, the stats counters will no longer be protected by the
sp_lock.

Change the counters to atomic_long_t fields, except for the
"sockets_queued" counter which will still be manipulated under a
spinlock.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Tested-by: Chris Worley <chris.worley@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc.h |  6 +++---
 net/sunrpc/svc_xprt.c      | 12 ++++++------
 2 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 7f80a99c59e..513957eba0a 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -26,10 +26,10 @@ typedef int		(*svc_thread_fn)(void *);
 
 /* statistics for svc_pool structures */
 struct svc_pool_stats {
-	unsigned long	packets;
+	atomic_long_t	packets;
 	unsigned long	sockets_queued;
-	unsigned long	threads_woken;
-	unsigned long	threads_timedout;
+	atomic_long_t	threads_woken;
+	atomic_long_t	threads_timedout;
 };
 
 /*
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index b2676e597fc..579ff224956 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -362,7 +362,7 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 	pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
 	spin_lock_bh(&pool->sp_lock);
 
-	pool->sp_stats.packets++;
+	atomic_long_inc(&pool->sp_stats.packets);
 
 	if (!list_empty(&pool->sp_threads)) {
 		rqstp = list_entry(pool->sp_threads.next,
@@ -383,7 +383,7 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 		svc_xprt_get(xprt);
 		wake_up_process(rqstp->rq_task);
 		rqstp->rq_xprt = xprt;
-		pool->sp_stats.threads_woken++;
+		atomic_long_inc(&pool->sp_stats.threads_woken);
 	} else {
 		dprintk("svc: transport %p put into queue\n", xprt);
 		list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
@@ -669,7 +669,7 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 
 		spin_lock_bh(&pool->sp_lock);
 		if (!time_left)
-			pool->sp_stats.threads_timedout++;
+			atomic_long_inc(&pool->sp_stats.threads_timedout);
 
 		xprt = rqstp->rq_xprt;
 		if (!xprt) {
@@ -1306,10 +1306,10 @@ static int svc_pool_stats_show(struct seq_file *m, void *p)
 
 	seq_printf(m, "%u %lu %lu %lu %lu\n",
 		pool->sp_id,
-		pool->sp_stats.packets,
+		(unsigned long)atomic_long_read(&pool->sp_stats.packets),
 		pool->sp_stats.sockets_queued,
-		pool->sp_stats.threads_woken,
-		pool->sp_stats.threads_timedout);
+		(unsigned long)atomic_long_read(&pool->sp_stats.threads_woken),
+		(unsigned long)atomic_long_read(&pool->sp_stats.threads_timedout));
 
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From b1691bc03d4eddb959234409167bef9be9e62d74 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 21 Nov 2014 14:19:30 -0500
Subject: sunrpc: convert to lockless lookup of queued server threads

Testing has shown that the pool->sp_lock can be a bottleneck on a busy
server. Every time data is received on a socket, the server must take
that lock in order to dequeue a thread from the sp_threads list.

Address this problem by eliminating the sp_threads list (which contains
threads that are currently idle) and replacing it with a RQ_BUSY flag in
svc_rqst. This allows us to walk the sp_all_threads list under the
rcu_read_lock and find a suitable thread for the xprt by doing a
test_and_set_bit.

Note that we do still have a potential atomicity problem however with
this approach.  We don't want svc_xprt_do_enqueue to set the
rqst->rq_xprt pointer unless a test_and_set_bit of RQ_BUSY returned
zero (which indicates that the thread was idle). But, by the time we
check that, the bit could be flipped by a waking thread.

To address this, we acquire a new per-rqst spinlock (rq_lock) and take
that before doing the test_and_set_bit. If that returns false, then we
can set rq_xprt and drop the spinlock. Then, when the thread wakes up,
it must set the bit under the same spinlock and can trust that if it was
already set then the rq_xprt is also properly set.

With this scheme, the case where we have an idle thread no longer needs
to take the highly contended pool->sp_lock at all, and that removes the
bottleneck.

That still leaves one issue: What of the case where we walk the whole
sp_all_threads list and don't find an idle thread? Because the search is
lockess, it's possible for the queueing to race with a thread that is
going to sleep. To address that, we queue the xprt and then search again.

If we find an idle thread at that point, we can't attach the xprt to it
directly since that might race with a different thread waking up and
finding it.  All we can do is wake the idle thread back up and let it
attempt to find the now-queued xprt.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Tested-by: Chris Worley <chris.worley@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc.h    |   4 +-
 include/trace/events/sunrpc.h |   3 +-
 net/sunrpc/svc.c              |   7 +-
 net/sunrpc/svc_xprt.c         | 221 ++++++++++++++++++++++++------------------
 4 files changed, 132 insertions(+), 103 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 513957eba0a..6f22cfeef5e 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -45,7 +45,6 @@ struct svc_pool_stats {
 struct svc_pool {
 	unsigned int		sp_id;	    	/* pool id; also node id on NUMA */
 	spinlock_t		sp_lock;	/* protects all fields */
-	struct list_head	sp_threads;	/* idle server threads */
 	struct list_head	sp_sockets;	/* pending sockets */
 	unsigned int		sp_nrthreads;	/* # of threads in pool */
 	struct list_head	sp_all_threads;	/* all server threads */
@@ -221,7 +220,6 @@ static inline void svc_putu32(struct kvec *iov, __be32 val)
  * processed.
  */
 struct svc_rqst {
-	struct list_head	rq_list;	/* idle list */
 	struct list_head	rq_all;		/* all threads list */
 	struct rcu_head		rq_rcu_head;	/* for RCU deferred kfree */
 	struct svc_xprt *	rq_xprt;	/* transport ptr */
@@ -264,6 +262,7 @@ struct svc_rqst {
 						 * to prevent encrypting page
 						 * cache pages */
 #define	RQ_VICTIM	(5)			/* about to be shut down */
+#define	RQ_BUSY		(6)			/* request is busy */
 	unsigned long		rq_flags;	/* flags field */
 
 	void *			rq_argp;	/* decoded arguments */
@@ -285,6 +284,7 @@ struct svc_rqst {
 	struct auth_domain *	rq_gssclient;	/* "gss/"-style peer info */
 	struct svc_cacherep *	rq_cacherep;	/* cache info */
 	struct task_struct	*rq_task;	/* service thread */
+	spinlock_t		rq_lock;	/* per-request lock */
 };
 
 #define SVC_NET(svc_rqst)	(svc_rqst->rq_xprt->xpt_net)
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 08a5fed50f3..ee4438a63a4 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -419,7 +419,8 @@ TRACE_EVENT(xs_tcp_data_recv,
 		{ (1UL << RQ_USEDEFERRAL),	"RQ_USEDEFERRAL"},	\
 		{ (1UL << RQ_DROPME),		"RQ_DROPME"},		\
 		{ (1UL << RQ_SPLICE_OK),	"RQ_SPLICE_OK"},	\
-		{ (1UL << RQ_VICTIM),		"RQ_VICTIM"})
+		{ (1UL << RQ_VICTIM),		"RQ_VICTIM"},		\
+		{ (1UL << RQ_BUSY),		"RQ_BUSY"})
 
 TRACE_EVENT(svc_recv,
 	TP_PROTO(struct svc_rqst *rqst, int status),
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index b90d1bca434..91eaef1844c 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -476,7 +476,6 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 				i, serv->sv_name);
 
 		pool->sp_id = i;
-		INIT_LIST_HEAD(&pool->sp_threads);
 		INIT_LIST_HEAD(&pool->sp_sockets);
 		INIT_LIST_HEAD(&pool->sp_all_threads);
 		spin_lock_init(&pool->sp_lock);
@@ -614,12 +613,14 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
 		goto out_enomem;
 
 	serv->sv_nrthreads++;
+	__set_bit(RQ_BUSY, &rqstp->rq_flags);
+	spin_lock_init(&rqstp->rq_lock);
+	rqstp->rq_server = serv;
+	rqstp->rq_pool = pool;
 	spin_lock_bh(&pool->sp_lock);
 	pool->sp_nrthreads++;
 	list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads);
 	spin_unlock_bh(&pool->sp_lock);
-	rqstp->rq_server = serv;
-	rqstp->rq_pool = pool;
 
 	rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node);
 	if (!rqstp->rq_argp)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 579ff224956..ed90d955f73 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -310,25 +310,6 @@ char *svc_print_addr(struct svc_rqst *rqstp, char *buf, size_t len)
 }
 EXPORT_SYMBOL_GPL(svc_print_addr);
 
-/*
- * Queue up an idle server thread.  Must have pool->sp_lock held.
- * Note: this is really a stack rather than a queue, so that we only
- * use as many different threads as we need, and the rest don't pollute
- * the cache.
- */
-static void svc_thread_enqueue(struct svc_pool *pool, struct svc_rqst *rqstp)
-{
-	list_add(&rqstp->rq_list, &pool->sp_threads);
-}
-
-/*
- * Dequeue an nfsd thread.  Must have pool->sp_lock held.
- */
-static void svc_thread_dequeue(struct svc_pool *pool, struct svc_rqst *rqstp)
-{
-	list_del(&rqstp->rq_list);
-}
-
 static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt)
 {
 	if (xprt->xpt_flags & ((1<<XPT_CONN)|(1<<XPT_CLOSE)))
@@ -343,6 +324,7 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 	struct svc_pool *pool;
 	struct svc_rqst	*rqstp;
 	int cpu;
+	bool queued = false;
 
 	if (!svc_xprt_has_something_to_do(xprt))
 		return;
@@ -360,37 +342,60 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 
 	cpu = get_cpu();
 	pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
-	spin_lock_bh(&pool->sp_lock);
 
 	atomic_long_inc(&pool->sp_stats.packets);
 
-	if (!list_empty(&pool->sp_threads)) {
-		rqstp = list_entry(pool->sp_threads.next,
-				   struct svc_rqst,
-				   rq_list);
-		dprintk("svc: transport %p served by daemon %p\n",
-			xprt, rqstp);
-		svc_thread_dequeue(pool, rqstp);
-		if (rqstp->rq_xprt)
-			printk(KERN_ERR
-				"svc_xprt_enqueue: server %p, rq_xprt=%p!\n",
-				rqstp, rqstp->rq_xprt);
-		/* Note the order of the following 3 lines:
-		 * We want to assign xprt to rqstp->rq_xprt only _after_
-		 * we've woken up the process, so that we don't race with
-		 * the lockless check in svc_get_next_xprt().
+redo_search:
+	/* find a thread for this xprt */
+	rcu_read_lock();
+	list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
+		/* Do a lockless check first */
+		if (test_bit(RQ_BUSY, &rqstp->rq_flags))
+			continue;
+
+		/*
+		 * Once the xprt has been queued, it can only be dequeued by
+		 * the task that intends to service it. All we can do at that
+		 * point is to try to wake this thread back up so that it can
+		 * do so.
 		 */
-		svc_xprt_get(xprt);
-		wake_up_process(rqstp->rq_task);
-		rqstp->rq_xprt = xprt;
+		if (!queued) {
+			spin_lock_bh(&rqstp->rq_lock);
+			if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags)) {
+				/* already busy, move on... */
+				spin_unlock_bh(&rqstp->rq_lock);
+				continue;
+			}
+
+			/* this one will do */
+			rqstp->rq_xprt = xprt;
+			svc_xprt_get(xprt);
+			spin_unlock_bh(&rqstp->rq_lock);
+		}
+		rcu_read_unlock();
+
 		atomic_long_inc(&pool->sp_stats.threads_woken);
-	} else {
+		wake_up_process(rqstp->rq_task);
+		put_cpu();
+		return;
+	}
+	rcu_read_unlock();
+
+	/*
+	 * We didn't find an idle thread to use, so we need to queue the xprt.
+	 * Do so and then search again. If we find one, we can't hook this one
+	 * up to it directly but we can wake the thread up in the hopes that it
+	 * will pick it up once it searches for a xprt to service.
+	 */
+	if (!queued) {
+		queued = true;
 		dprintk("svc: transport %p put into queue\n", xprt);
+		spin_lock_bh(&pool->sp_lock);
 		list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
 		pool->sp_stats.sockets_queued++;
+		spin_unlock_bh(&pool->sp_lock);
+		goto redo_search;
 	}
-
-	spin_unlock_bh(&pool->sp_lock);
 	put_cpu();
 }
 
@@ -408,21 +413,26 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 EXPORT_SYMBOL_GPL(svc_xprt_enqueue);
 
 /*
- * Dequeue the first transport.  Must be called with the pool->sp_lock held.
+ * Dequeue the first transport, if there is one.
  */
 static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
 {
-	struct svc_xprt	*xprt;
+	struct svc_xprt	*xprt = NULL;
 
 	if (list_empty(&pool->sp_sockets))
 		return NULL;
 
-	xprt = list_entry(pool->sp_sockets.next,
-			  struct svc_xprt, xpt_ready);
-	list_del_init(&xprt->xpt_ready);
+	spin_lock_bh(&pool->sp_lock);
+	if (likely(!list_empty(&pool->sp_sockets))) {
+		xprt = list_first_entry(&pool->sp_sockets,
+					struct svc_xprt, xpt_ready);
+		list_del_init(&xprt->xpt_ready);
+		svc_xprt_get(xprt);
 
-	dprintk("svc: transport %p dequeued, inuse=%d\n",
-		xprt, atomic_read(&xprt->xpt_ref.refcount));
+		dprintk("svc: transport %p dequeued, inuse=%d\n",
+			xprt, atomic_read(&xprt->xpt_ref.refcount));
+	}
+	spin_unlock_bh(&pool->sp_lock);
 
 	return xprt;
 }
@@ -497,16 +507,21 @@ void svc_wake_up(struct svc_serv *serv)
 
 	pool = &serv->sv_pools[0];
 
-	spin_lock_bh(&pool->sp_lock);
-	if (!list_empty(&pool->sp_threads)) {
-		rqstp = list_entry(pool->sp_threads.next,
-				   struct svc_rqst,
-				   rq_list);
+	rcu_read_lock();
+	list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
+		/* skip any that aren't queued */
+		if (test_bit(RQ_BUSY, &rqstp->rq_flags))
+			continue;
+		rcu_read_unlock();
 		dprintk("svc: daemon %p woken up.\n", rqstp);
 		wake_up_process(rqstp->rq_task);
-	} else
-		set_bit(SP_TASK_PENDING, &pool->sp_flags);
-	spin_unlock_bh(&pool->sp_lock);
+		return;
+	}
+	rcu_read_unlock();
+
+	/* No free entries available */
+	set_bit(SP_TASK_PENDING, &pool->sp_flags);
+	smp_wmb();
 }
 EXPORT_SYMBOL_GPL(svc_wake_up);
 
@@ -617,22 +632,47 @@ static int svc_alloc_arg(struct svc_rqst *rqstp)
 	return 0;
 }
 
+static bool
+rqst_should_sleep(struct svc_rqst *rqstp)
+{
+	struct svc_pool		*pool = rqstp->rq_pool;
+
+	/* did someone call svc_wake_up? */
+	if (test_and_clear_bit(SP_TASK_PENDING, &pool->sp_flags))
+		return false;
+
+	/* was a socket queued? */
+	if (!list_empty(&pool->sp_sockets))
+		return false;
+
+	/* are we shutting down? */
+	if (signalled() || kthread_should_stop())
+		return false;
+
+	/* are we freezing? */
+	if (freezing(current))
+		return false;
+
+	return true;
+}
+
 static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 {
 	struct svc_xprt *xprt;
 	struct svc_pool		*pool = rqstp->rq_pool;
 	long			time_left = 0;
 
+	/* rq_xprt should be clear on entry */
+	WARN_ON_ONCE(rqstp->rq_xprt);
+
 	/* Normally we will wait up to 5 seconds for any required
 	 * cache information to be provided.
 	 */
 	rqstp->rq_chandle.thread_wait = 5*HZ;
 
-	spin_lock_bh(&pool->sp_lock);
 	xprt = svc_xprt_dequeue(pool);
 	if (xprt) {
 		rqstp->rq_xprt = xprt;
-		svc_xprt_get(xprt);
 
 		/* As there is a shortage of threads and this request
 		 * had to be queued, don't allow the thread to wait so
@@ -640,51 +680,38 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 		 */
 		rqstp->rq_chandle.thread_wait = 1*HZ;
 		clear_bit(SP_TASK_PENDING, &pool->sp_flags);
-	} else {
-		if (test_and_clear_bit(SP_TASK_PENDING, &pool->sp_flags)) {
-			xprt = ERR_PTR(-EAGAIN);
-			goto out;
-		}
-		/*
-		 * We have to be able to interrupt this wait
-		 * to bring down the daemons ...
-		 */
-		set_current_state(TASK_INTERRUPTIBLE);
+		return xprt;
+	}
 
-		/* No data pending. Go to sleep */
-		svc_thread_enqueue(pool, rqstp);
-		spin_unlock_bh(&pool->sp_lock);
+	/*
+	 * We have to be able to interrupt this wait
+	 * to bring down the daemons ...
+	 */
+	set_current_state(TASK_INTERRUPTIBLE);
+	clear_bit(RQ_BUSY, &rqstp->rq_flags);
+	smp_mb();
+
+	if (likely(rqst_should_sleep(rqstp)))
+		time_left = schedule_timeout(timeout);
+	else
+		__set_current_state(TASK_RUNNING);
 
-		if (!(signalled() || kthread_should_stop())) {
-			time_left = schedule_timeout(timeout);
-			__set_current_state(TASK_RUNNING);
+	try_to_freeze();
 
-			try_to_freeze();
+	spin_lock_bh(&rqstp->rq_lock);
+	set_bit(RQ_BUSY, &rqstp->rq_flags);
+	spin_unlock_bh(&rqstp->rq_lock);
 
-			xprt = rqstp->rq_xprt;
-			if (xprt != NULL)
-				return xprt;
-		} else
-			__set_current_state(TASK_RUNNING);
+	xprt = rqstp->rq_xprt;
+	if (xprt != NULL)
+		return xprt;
 
-		spin_lock_bh(&pool->sp_lock);
-		if (!time_left)
-			atomic_long_inc(&pool->sp_stats.threads_timedout);
+	if (!time_left)
+		atomic_long_inc(&pool->sp_stats.threads_timedout);
 
-		xprt = rqstp->rq_xprt;
-		if (!xprt) {
-			svc_thread_dequeue(pool, rqstp);
-			spin_unlock_bh(&pool->sp_lock);
-			dprintk("svc: server %p, no data yet\n", rqstp);
-			if (signalled() || kthread_should_stop())
-				return ERR_PTR(-EINTR);
-			else
-				return ERR_PTR(-EAGAIN);
-		}
-	}
-out:
-	spin_unlock_bh(&pool->sp_lock);
-	return xprt;
+	if (signalled() || kthread_should_stop())
+		return ERR_PTR(-EINTR);
+	return ERR_PTR(-EAGAIN);
 }
 
 static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt)
-- 
cgit v1.2.3-70-g09d2


From 83a712e0afefaf68555f816ea78ecd2862c6cf30 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 21 Nov 2014 14:19:31 -0500
Subject: sunrpc: add some tracepoints around enqueue and dequeue of svc_xprt

These were useful when I was tracking down a race condition between
svc_xprt_do_enqueue and svc_get_next_xprt.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/trace/events/sunrpc.h | 94 +++++++++++++++++++++++++++++++++++++++++++
 net/sunrpc/svc_xprt.c         | 22 ++++++----
 2 files changed, 109 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index ee4438a63a4..b9c1dc6c825 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -8,6 +8,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/xprtsock.h>
+#include <linux/sunrpc/svc_xprt.h>
 #include <net/tcp_states.h>
 #include <linux/net.h>
 #include <linux/tracepoint.h>
@@ -480,6 +481,99 @@ DEFINE_EVENT(svc_rqst_status, svc_send,
 	TP_PROTO(struct svc_rqst *rqst, int status),
 	TP_ARGS(rqst, status));
 
+#define show_svc_xprt_flags(flags)					\
+	__print_flags(flags, "|",					\
+		{ (1UL << XPT_BUSY),		"XPT_BUSY"},		\
+		{ (1UL << XPT_CONN),		"XPT_CONN"},		\
+		{ (1UL << XPT_CLOSE),		"XPT_CLOSE"},		\
+		{ (1UL << XPT_DATA),		"XPT_DATA"},		\
+		{ (1UL << XPT_TEMP),		"XPT_TEMP"},		\
+		{ (1UL << XPT_DEAD),		"XPT_DEAD"},		\
+		{ (1UL << XPT_CHNGBUF),		"XPT_CHNGBUF"},		\
+		{ (1UL << XPT_DEFERRED),	"XPT_DEFERRED"},	\
+		{ (1UL << XPT_OLD),		"XPT_OLD"},		\
+		{ (1UL << XPT_LISTENER),	"XPT_LISTENER"},	\
+		{ (1UL << XPT_CACHE_AUTH),	"XPT_CACHE_AUTH"},	\
+		{ (1UL << XPT_LOCAL),		"XPT_LOCAL"})
+
+TRACE_EVENT(svc_xprt_do_enqueue,
+	TP_PROTO(struct svc_xprt *xprt, struct svc_rqst *rqst),
+
+	TP_ARGS(xprt, rqst),
+
+	TP_STRUCT__entry(
+		__field(struct svc_xprt *, xprt)
+		__field(struct svc_rqst *, rqst)
+	),
+
+	TP_fast_assign(
+		__entry->xprt = xprt;
+		__entry->rqst = rqst;
+	),
+
+	TP_printk("xprt=0x%p addr=%pIScp pid=%d flags=%s", __entry->xprt,
+		(struct sockaddr *)&__entry->xprt->xpt_remote,
+		__entry->rqst ? __entry->rqst->rq_task->pid : 0,
+		show_svc_xprt_flags(__entry->xprt->xpt_flags))
+);
+
+TRACE_EVENT(svc_xprt_dequeue,
+	TP_PROTO(struct svc_xprt *xprt),
+
+	TP_ARGS(xprt),
+
+	TP_STRUCT__entry(
+		__field(struct svc_xprt *, xprt)
+		__field_struct(struct sockaddr_storage, ss)
+		__field(unsigned long, flags)
+	),
+
+	TP_fast_assign(
+		__entry->xprt = xprt,
+		xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss));
+		__entry->flags = xprt ? xprt->xpt_flags : 0;
+	),
+
+	TP_printk("xprt=0x%p addr=%pIScp flags=%s", __entry->xprt,
+		(struct sockaddr *)&__entry->ss,
+		show_svc_xprt_flags(__entry->flags))
+);
+
+TRACE_EVENT(svc_wake_up,
+	TP_PROTO(int pid),
+
+	TP_ARGS(pid),
+
+	TP_STRUCT__entry(
+		__field(int, pid)
+	),
+
+	TP_fast_assign(
+		__entry->pid = pid;
+	),
+
+	TP_printk("pid=%d", __entry->pid)
+);
+
+TRACE_EVENT(svc_handle_xprt,
+	TP_PROTO(struct svc_xprt *xprt, int len),
+
+	TP_ARGS(xprt, len),
+
+	TP_STRUCT__entry(
+		__field(struct svc_xprt *, xprt)
+		__field(int, len)
+	),
+
+	TP_fast_assign(
+		__entry->xprt = xprt;
+		__entry->len = len;
+	),
+
+	TP_printk("xprt=0x%p addr=%pIScp len=%d flags=%s", __entry->xprt,
+		(struct sockaddr *)&__entry->xprt->xpt_remote, __entry->len,
+		show_svc_xprt_flags(__entry->xprt->xpt_flags))
+);
 #endif /* _TRACE_SUNRPC_H */
 
 #include <trace/define_trace.h>
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index ed90d955f73..73d40bd1839 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -322,12 +322,12 @@ static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt)
 static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 {
 	struct svc_pool *pool;
-	struct svc_rqst	*rqstp;
+	struct svc_rqst	*rqstp = NULL;
 	int cpu;
 	bool queued = false;
 
 	if (!svc_xprt_has_something_to_do(xprt))
-		return;
+		goto out;
 
 	/* Mark transport as busy. It will remain in this state until
 	 * the provider calls svc_xprt_received. We update XPT_BUSY
@@ -337,7 +337,7 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 	if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) {
 		/* Don't enqueue transport while already enqueued */
 		dprintk("svc: transport %p busy, not enqueued\n", xprt);
-		return;
+		goto out;
 	}
 
 	cpu = get_cpu();
@@ -377,7 +377,7 @@ redo_search:
 		atomic_long_inc(&pool->sp_stats.threads_woken);
 		wake_up_process(rqstp->rq_task);
 		put_cpu();
-		return;
+		goto out;
 	}
 	rcu_read_unlock();
 
@@ -396,7 +396,10 @@ redo_search:
 		spin_unlock_bh(&pool->sp_lock);
 		goto redo_search;
 	}
+	rqstp = NULL;
 	put_cpu();
+out:
+	trace_svc_xprt_do_enqueue(xprt, rqstp);
 }
 
 /*
@@ -420,7 +423,7 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
 	struct svc_xprt	*xprt = NULL;
 
 	if (list_empty(&pool->sp_sockets))
-		return NULL;
+		goto out;
 
 	spin_lock_bh(&pool->sp_lock);
 	if (likely(!list_empty(&pool->sp_sockets))) {
@@ -433,7 +436,8 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
 			xprt, atomic_read(&xprt->xpt_ref.refcount));
 	}
 	spin_unlock_bh(&pool->sp_lock);
-
+out:
+	trace_svc_xprt_dequeue(xprt);
 	return xprt;
 }
 
@@ -515,6 +519,7 @@ void svc_wake_up(struct svc_serv *serv)
 		rcu_read_unlock();
 		dprintk("svc: daemon %p woken up.\n", rqstp);
 		wake_up_process(rqstp->rq_task);
+		trace_svc_wake_up(rqstp->rq_task->pid);
 		return;
 	}
 	rcu_read_unlock();
@@ -522,6 +527,7 @@ void svc_wake_up(struct svc_serv *serv)
 	/* No free entries available */
 	set_bit(SP_TASK_PENDING, &pool->sp_flags);
 	smp_wmb();
+	trace_svc_wake_up(0);
 }
 EXPORT_SYMBOL_GPL(svc_wake_up);
 
@@ -740,7 +746,7 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 		dprintk("svc_recv: found XPT_CLOSE\n");
 		svc_delete_xprt(xprt);
 		/* Leave XPT_BUSY set on the dead xprt: */
-		return 0;
+		goto out;
 	}
 	if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
 		struct svc_xprt *newxpt;
@@ -771,6 +777,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 	}
 	/* clear XPT_BUSY: */
 	svc_xprt_received(xprt);
+out:
+	trace_svc_handle_xprt(xprt, len);
 	return len;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 5f4d8d97f5d979c6a62dcc45619b06d34311937c Mon Sep 17 00:00:00 2001
From: stephen hemminger <stephen@networkplumber.org>
Date: Wed, 3 Dec 2014 09:33:17 -0800
Subject: tc_act: export uapi header file

This file is used by iproute2 and should be exported.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tc_act/Kbuild | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/tc_act/Kbuild b/include/uapi/linux/tc_act/Kbuild
index 56f121605c9..b057da2b87a 100644
--- a/include/uapi/linux/tc_act/Kbuild
+++ b/include/uapi/linux/tc_act/Kbuild
@@ -7,3 +7,4 @@ header-y += tc_mirred.h
 header-y += tc_nat.h
 header-y += tc_pedit.h
 header-y += tc_skbedit.h
+header-y += tc_vlan.h
-- 
cgit v1.2.3-70-g09d2


From 395eea6ccf2b253f81b4718ffbcae67d36fe2e69 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Wed, 3 Dec 2014 13:46:24 -0800
Subject: rtnetlink: delay RTM_DELLINK notification until after ndo_uninit()

The commit 56bfa7ee7c ("unregister_netdevice : move RTM_DELLINK to
until after ndo_uninit") tried to do this ealier but while doing so
it created a problem. Unfortunately the delayed rtmsg_ifinfo() also
delayed call to fill_info(). So this translated into asking driver
to remove private state and then query it's private state. This
could have catastropic consequences.

This change breaks the rtmsg_ifinfo() into two parts - one takes the
precise snapshot of the device by called fill_info() before calling
the ndo_uninit() and the second part sends the notification using
collected snapshot.

It was brought to notice when last link is deleted from an ipvlan device
when it has free-ed the port and the subsequent .fill_info() call is
trying to get the info from the port.

kernel: [  255.139429] ------------[ cut here ]------------
kernel: [  255.139439] WARNING: CPU: 12 PID: 11173 at net/core/rtnetlink.c:2238 rtmsg_ifinfo+0x100/0x110()
kernel: [  255.139493] Modules linked in: ipvlan bonding w1_therm ds2482 wire cdc_acm ehci_pci ehci_hcd i2c_dev i2c_i801 i2c_core msr cpuid bnx2x ptp pps_core mdio libcrc32c
kernel: [  255.139513] CPU: 12 PID: 11173 Comm: ip Not tainted 3.18.0-smp-DEV #167
kernel: [  255.139514] Hardware name: Intel RML,PCH/Ibis_QC_18, BIOS 1.0.10 05/15/2012
kernel: [  255.139515]  0000000000000009 ffff880851b6b828 ffffffff815d87f4 00000000000000e0
kernel: [  255.139516]  0000000000000000 ffff880851b6b868 ffffffff8109c29c 0000000000000000
kernel: [  255.139518]  00000000ffffffa6 00000000000000d0 ffffffff81aaf580 0000000000000011
kernel: [  255.139520] Call Trace:
kernel: [  255.139527]  [<ffffffff815d87f4>] dump_stack+0x46/0x58
kernel: [  255.139531]  [<ffffffff8109c29c>] warn_slowpath_common+0x8c/0xc0
kernel: [  255.139540]  [<ffffffff8109c2ea>] warn_slowpath_null+0x1a/0x20
kernel: [  255.139544]  [<ffffffff8150d570>] rtmsg_ifinfo+0x100/0x110
kernel: [  255.139547]  [<ffffffff814f78b5>] rollback_registered_many+0x1d5/0x2d0
kernel: [  255.139549]  [<ffffffff814f79cf>] unregister_netdevice_many+0x1f/0xb0
kernel: [  255.139551]  [<ffffffff8150acab>] rtnl_dellink+0xbb/0x110
kernel: [  255.139553]  [<ffffffff8150da90>] rtnetlink_rcv_msg+0xa0/0x240
kernel: [  255.139557]  [<ffffffff81329283>] ? rhashtable_lookup_compare+0x43/0x80
kernel: [  255.139558]  [<ffffffff8150d9f0>] ? __rtnl_unlock+0x20/0x20
kernel: [  255.139562]  [<ffffffff8152cb11>] netlink_rcv_skb+0xb1/0xc0
kernel: [  255.139563]  [<ffffffff8150a495>] rtnetlink_rcv+0x25/0x40
kernel: [  255.139565]  [<ffffffff8152c398>] netlink_unicast+0x178/0x230
kernel: [  255.139567]  [<ffffffff8152c75f>] netlink_sendmsg+0x30f/0x420
kernel: [  255.139571]  [<ffffffff814e0b0c>] sock_sendmsg+0x9c/0xd0
kernel: [  255.139575]  [<ffffffff811d1d7f>] ? rw_copy_check_uvector+0x6f/0x130
kernel: [  255.139577]  [<ffffffff814e11c9>] ? copy_msghdr_from_user+0x139/0x1b0
kernel: [  255.139578]  [<ffffffff814e1774>] ___sys_sendmsg+0x304/0x310
kernel: [  255.139581]  [<ffffffff81198723>] ? handle_mm_fault+0xca3/0xde0
kernel: [  255.139585]  [<ffffffff811ebc4c>] ? destroy_inode+0x3c/0x70
kernel: [  255.139589]  [<ffffffff8108e6ec>] ? __do_page_fault+0x20c/0x500
kernel: [  255.139597]  [<ffffffff811e8336>] ? dput+0xb6/0x190
kernel: [  255.139606]  [<ffffffff811f05f6>] ? mntput+0x26/0x40
kernel: [  255.139611]  [<ffffffff811d2b94>] ? __fput+0x174/0x1e0
kernel: [  255.139613]  [<ffffffff814e2129>] __sys_sendmsg+0x49/0x90
kernel: [  255.139615]  [<ffffffff814e2182>] SyS_sendmsg+0x12/0x20
kernel: [  255.139617]  [<ffffffff815df092>] system_call_fastpath+0x12/0x17
kernel: [  255.139619] ---[ end trace 5e6703e87d984f6b ]---

Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Reported-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: David S. Miller <davem@davemloft.net>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rtnetlink.h |  5 +++++
 net/core/dev.c            | 12 +++++++++---
 net/core/rtnetlink.c      | 25 +++++++++++++++++++++----
 3 files changed, 35 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 3b0419072f8..5db76a32fca 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -17,6 +17,11 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst,
 			      u32 id, long expires, u32 error);
 
 void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags);
+struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
+				       unsigned change, gfp_t flags);
+void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev,
+		       gfp_t flags);
+
 
 /* RTNL is used as a global lock for all changes to network configuration  */
 extern void rtnl_lock(void);
diff --git a/net/core/dev.c b/net/core/dev.c
index 0814a560e5f..dd3bf582e6f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5925,6 +5925,8 @@ static void rollback_registered_many(struct list_head *head)
 	synchronize_net();
 
 	list_for_each_entry(dev, head, unreg_list) {
+		struct sk_buff *skb = NULL;
+
 		/* Shutdown queueing discipline. */
 		dev_shutdown(dev);
 
@@ -5934,6 +5936,11 @@ static void rollback_registered_many(struct list_head *head)
 		*/
 		call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 
+		if (!dev->rtnl_link_ops ||
+		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
+			skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U,
+						     GFP_KERNEL);
+
 		/*
 		 *	Flush the unicast and multicast chains
 		 */
@@ -5943,9 +5950,8 @@ static void rollback_registered_many(struct list_head *head)
 		if (dev->netdev_ops->ndo_uninit)
 			dev->netdev_ops->ndo_uninit(dev);
 
-		if (!dev->rtnl_link_ops ||
-		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
-			rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
+		if (skb)
+			rtmsg_ifinfo_send(skb, dev, GFP_KERNEL);
 
 		/* Notifier chain MUST detach us all upper devices. */
 		WARN_ON(netdev_has_any_upper_dev(dev));
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 61cb7e7cc3c..a9be2c16170 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2245,8 +2245,8 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
-		  gfp_t flags)
+struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
+				       unsigned int change, gfp_t flags)
 {
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
@@ -2264,11 +2264,28 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
 		kfree_skb(skb);
 		goto errout;
 	}
-	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
-	return;
+	return skb;
 errout:
 	if (err < 0)
 		rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+	return NULL;
+}
+
+void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags)
+{
+	struct net *net = dev_net(dev);
+
+	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
+}
+
+void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
+		  gfp_t flags)
+{
+	struct sk_buff *skb;
+
+	skb = rtmsg_ifinfo_build_skb(type, dev, change, flags);
+	if (skb)
+		rtmsg_ifinfo_send(skb, dev, flags);
 }
 EXPORT_SYMBOL(rtmsg_ifinfo);
 
-- 
cgit v1.2.3-70-g09d2


From 6ffe75eb53564953e75c051e1c28676e1e56f385 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 3 Dec 2014 17:04:39 -0800
Subject: net: avoid two atomic operations in fast clones

Commit ce1a4ea3f125 ("net: avoid one atomic operation in skb_clone()")
took the wrong way to save one atomic operation.

It is actually possible to avoid two atomic operations, if we
do not change skb->fclone values, and only rely on clone_ref
content to signal if the clone is available or not.

skb_clone() can simply use the fast clone if clone_ref is 1.

kfree_skbmem() can avoid the atomic_dec_and_test() if clone_ref is 1.

Note that because we usually free the clone before the original skb,
this particular attempt is only done for the original skb to have better
branch prediction.

SKB_FCLONE_FREE is removed.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Chris Mason <clm@fb.com>
Cc: Sabrina Dubroca <sd@queasysnail.net>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  3 +--
 net/core/skbuff.c      | 35 ++++++++++++++++++-----------------
 2 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d1e2575000b..e9281b5b7f5 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -344,7 +344,6 @@ enum {
 	SKB_FCLONE_UNAVAILABLE,	/* skb has no fclone (from head_cache) */
 	SKB_FCLONE_ORIG,	/* orig skb (from fclone_cache) */
 	SKB_FCLONE_CLONE,	/* companion fclone skb (from fclone_cache) */
-	SKB_FCLONE_FREE,	/* this companion fclone skb is available */
 };
 
 enum {
@@ -818,7 +817,7 @@ static inline bool skb_fclone_busy(const struct sock *sk,
 	fclones = container_of(skb, struct sk_buff_fclones, skb1);
 
 	return skb->fclone == SKB_FCLONE_ORIG &&
-	       fclones->skb2.fclone == SKB_FCLONE_CLONE &&
+	       atomic_read(&fclones->fclone_ref) > 1 &&
 	       fclones->skb2.sk == sk;
 }
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 92116dfe827..7a338fb55cc 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -265,7 +265,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 		skb->fclone = SKB_FCLONE_ORIG;
 		atomic_set(&fclones->fclone_ref, 1);
 
-		fclones->skb2.fclone = SKB_FCLONE_FREE;
+		fclones->skb2.fclone = SKB_FCLONE_CLONE;
 		fclones->skb2.pfmemalloc = pfmemalloc;
 	}
 out:
@@ -541,26 +541,27 @@ static void kfree_skbmem(struct sk_buff *skb)
 	switch (skb->fclone) {
 	case SKB_FCLONE_UNAVAILABLE:
 		kmem_cache_free(skbuff_head_cache, skb);
-		break;
+		return;
 
 	case SKB_FCLONE_ORIG:
 		fclones = container_of(skb, struct sk_buff_fclones, skb1);
-		if (atomic_dec_and_test(&fclones->fclone_ref))
-			kmem_cache_free(skbuff_fclone_cache, fclones);
-		break;
-
-	case SKB_FCLONE_CLONE:
-		fclones = container_of(skb, struct sk_buff_fclones, skb2);
 
-		/* The clone portion is available for
-		 * fast-cloning again.
+		/* We usually free the clone (TX completion) before original skb
+		 * This test would have no chance to be true for the clone,
+		 * while here, branch prediction will be good.
 		 */
-		skb->fclone = SKB_FCLONE_FREE;
+		if (atomic_read(&fclones->fclone_ref) == 1)
+			goto fastpath;
+		break;
 
-		if (atomic_dec_and_test(&fclones->fclone_ref))
-			kmem_cache_free(skbuff_fclone_cache, fclones);
+	default: /* SKB_FCLONE_CLONE */
+		fclones = container_of(skb, struct sk_buff_fclones, skb2);
 		break;
 	}
+	if (!atomic_dec_and_test(&fclones->fclone_ref))
+		return;
+fastpath:
+	kmem_cache_free(skbuff_fclone_cache, fclones);
 }
 
 static void skb_release_head_state(struct sk_buff *skb)
@@ -872,15 +873,15 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 	struct sk_buff_fclones *fclones = container_of(skb,
 						       struct sk_buff_fclones,
 						       skb1);
-	struct sk_buff *n = &fclones->skb2;
+	struct sk_buff *n;
 
 	if (skb_orphan_frags(skb, gfp_mask))
 		return NULL;
 
 	if (skb->fclone == SKB_FCLONE_ORIG &&
-	    n->fclone == SKB_FCLONE_FREE) {
-		n->fclone = SKB_FCLONE_CLONE;
-		atomic_inc(&fclones->fclone_ref);
+	    atomic_read(&fclones->fclone_ref) == 1) {
+		n = &fclones->skb2;
+		atomic_set(&fclones->fclone_ref, 2);
 	} else {
 		if (skb_pfmemalloc(skb))
 			gfp_mask |= __GFP_MEMALLOC;
-- 
cgit v1.2.3-70-g09d2


From d71a6fc6b97fba1de999c6f0fab5c75544afab76 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 4 Dec 2014 19:31:45 +0200
Subject: virtio: drop legacy_only driver flag

legacy_only flag is now unused, drop it from core.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
 drivers/virtio/virtio.c | 4 ----
 include/linux/virtio.h  | 2 --
 2 files changed, 6 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index e1673a511d1..f2266586878 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -198,10 +198,6 @@ static int virtio_dev_probe(struct device *_d)
 		driver_features_legacy = driver_features;
 	}
 
-	/* Detect legacy-only drivers and disable VIRTIO_F_VERSION_1. */
-	if (drv->legacy_only)
-		device_features &= ~(1ULL << VIRTIO_F_VERSION_1);
-
 	if (device_features & (1ULL << VIRTIO_F_VERSION_1))
 		dev->features = driver_features & device_features;
 	else
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index d666bcb5740..d09e0938fd6 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -134,7 +134,6 @@ int virtio_device_restore(struct virtio_device *dev);
  * @feature_table_size: number of entries in the feature table array.
  * @feature_table_legacy: same as feature_table but when working in legacy mode.
  * @feature_table_size_legacy: number of entries in feature table legacy array.
- * @legacy_only: driver does not support virtio 1.0.
  * @probe: the function to call when a device is found.  Returns 0 or -errno.
  * @remove: the function to call when a device is removed.
  * @config_changed: optional function to call when the device configuration
@@ -147,7 +146,6 @@ struct virtio_driver {
 	unsigned int feature_table_size;
 	const unsigned int *feature_table_legacy;
 	unsigned int feature_table_size_legacy;
-	bool legacy_only;
 	int (*probe)(struct virtio_device *dev);
 	void (*scan)(struct virtio_device *dev);
 	void (*remove)(struct virtio_device *dev);
-- 
cgit v1.2.3-70-g09d2


From 57d743a3dec174b8f1fbf53e93ade2fea3d32bd7 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Thu, 4 Dec 2014 21:41:18 +0100
Subject: net: sched: cls: remove unused op put from tcf_proto_ops

It is never called and implementations are void. So just remove it.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 1 -
 net/sched/cls_basic.c     | 5 -----
 net/sched/cls_bpf.c       | 5 -----
 net/sched/cls_cgroup.c    | 5 -----
 net/sched/cls_flow.c      | 5 -----
 net/sched/cls_fw.c        | 5 -----
 net/sched/cls_route.c     | 5 -----
 net/sched/cls_rsvp.h      | 5 -----
 net/sched/cls_tcindex.c   | 8 --------
 net/sched/cls_u32.c       | 5 -----
 10 files changed, 49 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d17ed6fb2f7..3d282cbb66b 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -219,7 +219,6 @@ struct tcf_proto_ops {
 	void			(*destroy)(struct tcf_proto*);
 
 	unsigned long		(*get)(struct tcf_proto*, u32 handle);
-	void			(*put)(struct tcf_proto*, unsigned long);
 	int			(*change)(struct net *net, struct sk_buff *,
 					struct tcf_proto*, unsigned long,
 					u32 handle, struct nlattr **,
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 1c122c7e054..7cf0a62fc4c 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -72,10 +72,6 @@ static unsigned long basic_get(struct tcf_proto *tp, u32 handle)
 	return l;
 }
 
-static void basic_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static int basic_init(struct tcf_proto *tp)
 {
 	struct basic_head *head;
@@ -287,7 +283,6 @@ static struct tcf_proto_ops cls_basic_ops __read_mostly = {
 	.init		=	basic_init,
 	.destroy	=	basic_destroy,
 	.get		=	basic_get,
-	.put		=	basic_put,
 	.change		=	basic_change,
 	.delete		=	basic_delete,
 	.walk		=	basic_walk,
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index d0de979c04a..84c8219c3e1 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -151,10 +151,6 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
 	return ret;
 }
 
-static void cls_bpf_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
 				   struct cls_bpf_prog *prog,
 				   unsigned long base, struct nlattr **tb,
@@ -356,7 +352,6 @@ static struct tcf_proto_ops cls_bpf_ops __read_mostly = {
 	.init		=	cls_bpf_init,
 	.destroy	=	cls_bpf_destroy,
 	.get		=	cls_bpf_get,
-	.put		=	cls_bpf_put,
 	.change		=	cls_bpf_change,
 	.delete		=	cls_bpf_delete,
 	.walk		=	cls_bpf_walk,
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index dbee65e26b3..741bfa7debb 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -67,10 +67,6 @@ static unsigned long cls_cgroup_get(struct tcf_proto *tp, u32 handle)
 	return 0UL;
 }
 
-static void cls_cgroup_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static int cls_cgroup_init(struct tcf_proto *tp)
 {
 	return 0;
@@ -213,7 +209,6 @@ static struct tcf_proto_ops cls_cgroup_ops __read_mostly = {
 	.classify	=	cls_cgroup_classify,
 	.destroy	=	cls_cgroup_destroy,
 	.get		=	cls_cgroup_get,
-	.put		=	cls_cgroup_put,
 	.delete		=	cls_cgroup_delete,
 	.walk		=	cls_cgroup_walk,
 	.dump		=	cls_cgroup_dump,
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 819c2307881..8e227180cab 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -581,10 +581,6 @@ static unsigned long flow_get(struct tcf_proto *tp, u32 handle)
 	return 0;
 }
 
-static void flow_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static int flow_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 		     struct sk_buff *skb, struct tcmsg *t)
 {
@@ -671,7 +667,6 @@ static struct tcf_proto_ops cls_flow_ops __read_mostly = {
 	.change		= flow_change,
 	.delete		= flow_delete,
 	.get		= flow_get,
-	.put		= flow_put,
 	.dump		= flow_dump,
 	.walk		= flow_walk,
 	.owner		= THIS_MODULE,
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index dbfdfd1f1a9..23fda2ac0d1 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -111,10 +111,6 @@ static unsigned long fw_get(struct tcf_proto *tp, u32 handle)
 	return 0;
 }
 
-static void fw_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static int fw_init(struct tcf_proto *tp)
 {
 	return 0;
@@ -411,7 +407,6 @@ static struct tcf_proto_ops cls_fw_ops __read_mostly = {
 	.init		=	fw_init,
 	.destroy	=	fw_destroy,
 	.get		=	fw_get,
-	.put		=	fw_put,
 	.change		=	fw_change,
 	.delete		=	fw_delete,
 	.walk		=	fw_walk,
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 109a329b719..098a27360b9 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -256,10 +256,6 @@ static unsigned long route4_get(struct tcf_proto *tp, u32 handle)
 	return 0;
 }
 
-static void route4_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static int route4_init(struct tcf_proto *tp)
 {
 	return 0;
@@ -649,7 +645,6 @@ static struct tcf_proto_ops cls_route4_ops __read_mostly = {
 	.init		=	route4_init,
 	.destroy	=	route4_destroy,
 	.get		=	route4_get,
-	.put		=	route4_put,
 	.change		=	route4_change,
 	.delete		=	route4_delete,
 	.walk		=	route4_walk,
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 6bb55f277a5..b7af3623a26 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -271,10 +271,6 @@ static unsigned long rsvp_get(struct tcf_proto *tp, u32 handle)
 	return 0;
 }
 
-static void rsvp_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static int rsvp_init(struct tcf_proto *tp)
 {
 	struct rsvp_head *data;
@@ -708,7 +704,6 @@ static struct tcf_proto_ops RSVP_OPS __read_mostly = {
 	.init		=	rsvp_init,
 	.destroy	=	rsvp_destroy,
 	.get		=	rsvp_get,
-	.put		=	rsvp_put,
 	.change		=	rsvp_change,
 	.delete		=	rsvp_delete,
 	.walk		=	rsvp_walk,
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 30f10fb07f4..0d9d8911a62 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -116,13 +116,6 @@ static unsigned long tcindex_get(struct tcf_proto *tp, u32 handle)
 	return r && tcindex_filter_is_set(r) ? (unsigned long) r : 0UL;
 }
 
-
-static void tcindex_put(struct tcf_proto *tp, unsigned long f)
-{
-	pr_debug("tcindex_put(tp %p,f 0x%lx)\n", tp, f);
-}
-
-
 static int tcindex_init(struct tcf_proto *tp)
 {
 	struct tcindex_data *p;
@@ -560,7 +553,6 @@ static struct tcf_proto_ops cls_tcindex_ops __read_mostly = {
 	.init		=	tcindex_init,
 	.destroy	=	tcindex_destroy,
 	.get		=	tcindex_get,
-	.put		=	tcindex_put,
 	.change		=	tcindex_change,
 	.delete		=	tcindex_delete,
 	.walk		=	tcindex_walk,
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 0472909bb01..09487afbfd5 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -299,10 +299,6 @@ static unsigned long u32_get(struct tcf_proto *tp, u32 handle)
 	return (unsigned long)u32_lookup_key(ht, handle);
 }
 
-static void u32_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static u32 gen_new_htid(struct tc_u_common *tp_c)
 {
 	int i = 0x800;
@@ -1021,7 +1017,6 @@ static struct tcf_proto_ops cls_u32_ops __read_mostly = {
 	.init		=	u32_init,
 	.destroy	=	u32_destroy,
 	.get		=	u32_get,
-	.put		=	u32_put,
 	.change		=	u32_change,
 	.delete		=	u32_delete,
 	.walk		=	u32_walk,
-- 
cgit v1.2.3-70-g09d2


From 6e3a8a937c2f86ee0b2d354808fc026a143b4518 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 4 Dec 2014 16:13:23 -0800
Subject: tcp_cubic: add SNMP counters to track how effective is Hystart

When deploying FQ pacing, one thing we noticed is that CUBIC Hystart
triggers too soon.

Having SNMP counters to have an idea of how often the various Hystart
methods trigger is useful prior to any modifications.

This patch adds SNMP counters tracking, how many time "ack train" or
"Delay" based Hystart triggers, and cumulative sum of cwnd at the time
Hystart decided to end SS (Slow Start)

myhost:~# nstat -a | grep Hystart
TcpExtTCPHystartTrainDetect     9                  0.0
TcpExtTCPHystartTrainCwnd       20650              0.0
TcpExtTCPHystartDelayDetect     10                 0.0
TcpExtTCPHystartDelayCwnd       360                0.0

->
 Train detection was triggered 9 times, and average cwnd was
 20650/9=2294,
 Delay detection was triggered 10 times and average cwnd was 36

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/snmp.h |  4 ++++
 net/ipv4/proc.c           |  4 ++++
 net/ipv4/tcp_cubic.c      | 31 ++++++++++++++++++++++---------
 3 files changed, 30 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 30f541b3289..b2222410001 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -266,6 +266,10 @@ enum
 	LINUX_MIB_TCPWANTZEROWINDOWADV,		/* TCPWantZeroWindowAdv */
 	LINUX_MIB_TCPSYNRETRANS,		/* TCPSynRetrans */
 	LINUX_MIB_TCPORIGDATASENT,		/* TCPOrigDataSent */
+	LINUX_MIB_TCPHYSTARTTRAINDETECT,	/* TCPHystartTrainDetect */
+	LINUX_MIB_TCPHYSTARTTRAINCWND,		/* TCPHystartTrainCwnd */
+	LINUX_MIB_TCPHYSTARTDELAYDETECT,	/* TCPHystartDelayDetect */
+	LINUX_MIB_TCPHYSTARTDELAYCWND,		/* TCPHystartDelayCwnd */
 	__LINUX_MIB_MAX
 };
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 6513ade8d6d..8f9cd200ce2 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -288,6 +288,10 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPWantZeroWindowAdv", LINUX_MIB_TCPWANTZEROWINDOWADV),
 	SNMP_MIB_ITEM("TCPSynRetrans", LINUX_MIB_TCPSYNRETRANS),
 	SNMP_MIB_ITEM("TCPOrigDataSent", LINUX_MIB_TCPORIGDATASENT),
+	SNMP_MIB_ITEM("TCPHystartTrainDetect", LINUX_MIB_TCPHYSTARTTRAINDETECT),
+	SNMP_MIB_ITEM("TCPHystartTrainCwnd", LINUX_MIB_TCPHYSTARTTRAINCWND),
+	SNMP_MIB_ITEM("TCPHystartDelayDetect", LINUX_MIB_TCPHYSTARTDELAYDETECT),
+	SNMP_MIB_ITEM("TCPHystartDelayCwnd", LINUX_MIB_TCPHYSTARTDELAYCWND),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 20de0118c98..c1d07c7ed03 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -363,16 +363,28 @@ static void hystart_update(struct sock *sk, u32 delay)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 
-	if (!(ca->found & hystart_detect)) {
+	if (ca->found & hystart_detect)
+		return;
+
+	if (hystart_detect & HYSTART_ACK_TRAIN) {
 		u32 now = bictcp_clock();
 
 		/* first detection parameter - ack-train detection */
 		if ((s32)(now - ca->last_ack) <= hystart_ack_delta) {
 			ca->last_ack = now;
-			if ((s32)(now - ca->round_start) > ca->delay_min >> 4)
+			if ((s32)(now - ca->round_start) > ca->delay_min >> 4) {
 				ca->found |= HYSTART_ACK_TRAIN;
+				NET_INC_STATS_BH(sock_net(sk),
+						 LINUX_MIB_TCPHYSTARTTRAINDETECT);
+				NET_ADD_STATS_BH(sock_net(sk),
+						 LINUX_MIB_TCPHYSTARTTRAINCWND,
+						 tp->snd_cwnd);
+				tp->snd_ssthresh = tp->snd_cwnd;
+			}
 		}
+	}
 
+	if (hystart_detect & HYSTART_DELAY) {
 		/* obtain the minimum delay of more than sampling packets */
 		if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
 			if (ca->curr_rtt == 0 || ca->curr_rtt > delay)
@@ -381,15 +393,16 @@ static void hystart_update(struct sock *sk, u32 delay)
 			ca->sample_cnt++;
 		} else {
 			if (ca->curr_rtt > ca->delay_min +
-			    HYSTART_DELAY_THRESH(ca->delay_min>>4))
+			    HYSTART_DELAY_THRESH(ca->delay_min>>4)) {
 				ca->found |= HYSTART_DELAY;
+				NET_INC_STATS_BH(sock_net(sk),
+						 LINUX_MIB_TCPHYSTARTDELAYDETECT);
+				NET_ADD_STATS_BH(sock_net(sk),
+						 LINUX_MIB_TCPHYSTARTDELAYCWND,
+						 tp->snd_cwnd);
+				tp->snd_ssthresh = tp->snd_cwnd;
+			}
 		}
-		/*
-		 * Either one of two conditions are met,
-		 * we exit from slow start immediately.
-		 */
-		if (ca->found & hystart_detect)
-			tp->snd_ssthresh = tp->snd_cwnd;
 	}
 }
 
-- 
cgit v1.2.3-70-g09d2


From dbfc4fb7d578d4f224faa6b60deb40804dfdc1b1 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Sat, 6 Dec 2014 19:19:42 +0100
Subject: dst: no need to take reference on DST_NOCACHE dsts

Since commit f8864972126899 ("ipv4: fix dst race in sk_dst_get()")
DST_NOCACHE dst_entries get freed by RCU. So there is no need to get a
reference on them when we are in rcu protected sections.

Cc: Eric Dumazet <edumazet@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h          | 23 ++---------------------
 net/core/dst.c                  | 24 ------------------------
 net/netfilter/ipvs/ip_vs_xmit.c |  4 ++--
 3 files changed, 4 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e9281b5b7f5..ef64cec4280 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -717,9 +717,6 @@ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst)
 	skb->_skb_refdst = (unsigned long)dst;
 }
 
-void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst,
-			 bool force);
-
 /**
  * skb_dst_set_noref - sets skb dst, hopefully, without taking reference
  * @skb: buffer
@@ -732,24 +729,8 @@ void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst,
  */
 static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst)
 {
-	__skb_dst_set_noref(skb, dst, false);
-}
-
-/**
- * skb_dst_set_noref_force - sets skb dst, without taking reference
- * @skb: buffer
- * @dst: dst entry
- *
- * Sets skb dst, assuming a reference was not taken on dst.
- * No reference is taken and no dst_release will be called. While for
- * cached dsts deferred reclaim is a basic feature, for entries that are
- * not cached it is caller's job to guarantee that last dst_release for
- * provided dst happens when nobody uses it, eg. after a RCU grace period.
- */
-static inline void skb_dst_set_noref_force(struct sk_buff *skb,
-					   struct dst_entry *dst)
-{
-	__skb_dst_set_noref(skb, dst, true);
+	WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF;
 }
 
 /**
diff --git a/net/core/dst.c b/net/core/dst.c
index a028409ee43..e956ce6d137 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -327,30 +327,6 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 }
 EXPORT_SYMBOL(__dst_destroy_metrics_generic);
 
-/**
- * __skb_dst_set_noref - sets skb dst, without a reference
- * @skb: buffer
- * @dst: dst entry
- * @force: if force is set, use noref version even for DST_NOCACHE entries
- *
- * Sets skb dst, assuming a reference was not taken on dst
- * skb_dst_drop() should not dst_release() this dst
- */
-void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst, bool force)
-{
-	WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
-	/* If dst not in cache, we must take a reference, because
-	 * dst_release() will destroy dst as soon as its refcount becomes zero
-	 */
-	if (unlikely((dst->flags & DST_NOCACHE) && !force)) {
-		dst_hold(dst);
-		skb_dst_set(skb, dst);
-	} else {
-		skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF;
-	}
-}
-EXPORT_SYMBOL(__skb_dst_set_noref);
-
 /* Dirty hack. We did it in 2.2 (in __dst_free),
  * we have _very_ good reasons not to repeat
  * this mistake in 2.3, but we have no choice
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 1f933136155..3aedbda7658 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -343,7 +343,7 @@ __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 	skb_dst_drop(skb);
 	if (noref) {
 		if (!local)
-			skb_dst_set_noref_force(skb, &rt->dst);
+			skb_dst_set_noref(skb, &rt->dst);
 		else
 			skb_dst_set(skb, dst_clone(&rt->dst));
 	} else
@@ -487,7 +487,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 	skb_dst_drop(skb);
 	if (noref) {
 		if (!local)
-			skb_dst_set_noref_force(skb, &rt->dst);
+			skb_dst_set_noref(skb, &rt->dst);
 		else
 			skb_dst_set(skb, dst_clone(&rt->dst));
 	} else
-- 
cgit v1.2.3-70-g09d2


From 2f33e7d59cb09d9b20d6648086b314f0ba61fb03 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Sat, 6 Dec 2014 15:53:04 -0800
Subject: netdevice: Add a function to check macvlan port

Similar to a check for macvlan device, netif_is_macvlan(), add
another function to check if a device is used as macvlan port.

Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 29c92ee9ed5..1f49aac258f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3641,6 +3641,11 @@ static inline bool netif_is_macvlan(struct net_device *dev)
 	return dev->priv_flags & IFF_MACVLAN;
 }
 
+static inline bool netif_is_macvlan_port(struct net_device *dev)
+{
+	return dev->priv_flags & IFF_MACVLAN_PORT;
+}
+
 static inline bool netif_is_bond_master(struct net_device *dev)
 {
 	return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING;
-- 
cgit v1.2.3-70-g09d2


From 5933fea7aa7237ba52d67c069c39ad5c3ab7a036 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Sat, 6 Dec 2014 15:53:33 -0800
Subject: ipvlan: move the device check function into netdevice.h

Move the port check [ipvlan_dev_master()] and device check
[ipvlan_dev_slave()] functions to netdevice.h and rename them
netif_is_ipvlan_port() and netif_is_ipvlan() resp. to be
consistent with macvlan api naming.

Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan.h      | 10 ----------
 drivers/net/ipvlan/ipvlan_main.c | 10 +++++-----
 include/linux/netdevice.h        | 10 ++++++++++
 3 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index c44d29eca6c..2729f64b3e7 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -107,16 +107,6 @@ static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d)
 	return rtnl_dereference(d->rx_handler_data);
 }
 
-static inline bool ipvlan_dev_master(struct net_device *d)
-{
-	return d->priv_flags & IFF_IPVLAN_MASTER;
-}
-
-static inline bool ipvlan_dev_slave(struct net_device *d)
-{
-	return d->priv_flags & IFF_IPVLAN_SLAVE;
-}
-
 void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev);
 void ipvlan_set_port_mode(struct ipvl_port *port, u32 nval);
 void ipvlan_init_secret(void);
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index a66ff819700..4f4099d5603 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -446,11 +446,11 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 	if (!phy_dev)
 		return -ENODEV;
 
-	if (ipvlan_dev_slave(phy_dev)) {
+	if (netif_is_ipvlan(phy_dev)) {
 		struct ipvl_dev *tmp = netdev_priv(phy_dev);
 
 		phy_dev = tmp->phy_dev;
-	} else if (!ipvlan_dev_master(phy_dev)) {
+	} else if (!netif_is_ipvlan_port(phy_dev)) {
 		err = ipvlan_port_create(phy_dev);
 		if (err < 0)
 			return err;
@@ -560,7 +560,7 @@ static int ipvlan_device_event(struct notifier_block *unused,
 	struct ipvl_port *port;
 	LIST_HEAD(lst_kill);
 
-	if (!ipvlan_dev_master(dev))
+	if (!netif_is_ipvlan_port(dev))
 		return NOTIFY_DONE;
 
 	port = ipvlan_port_get_rtnl(dev);
@@ -651,7 +651,7 @@ static int ipvlan_addr6_event(struct notifier_block *unused,
 	struct net_device *dev = (struct net_device *)if6->idev->dev;
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 
-	if (!ipvlan_dev_slave(dev))
+	if (!netif_is_ipvlan(dev))
 		return NOTIFY_DONE;
 
 	if (!ipvlan || !ipvlan->port)
@@ -723,7 +723,7 @@ static int ipvlan_addr4_event(struct notifier_block *unused,
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 	struct in_addr ip4_addr;
 
-	if (!ipvlan_dev_slave(dev))
+	if (!netif_is_ipvlan(dev))
 		return NOTIFY_DONE;
 
 	if (!ipvlan || !ipvlan->port)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1f49aac258f..c31f74d76eb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3646,6 +3646,16 @@ static inline bool netif_is_macvlan_port(struct net_device *dev)
 	return dev->priv_flags & IFF_MACVLAN_PORT;
 }
 
+static inline bool netif_is_ipvlan(struct net_device *dev)
+{
+	return dev->priv_flags & IFF_IPVLAN_SLAVE;
+}
+
+static inline bool netif_is_ipvlan_port(struct net_device *dev)
+{
+	return dev->priv_flags & IFF_IPVLAN_MASTER;
+}
+
 static inline bool netif_is_bond_master(struct net_device *dev)
 {
 	return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING;
-- 
cgit v1.2.3-70-g09d2


From f69e6d131f5dac8278ac79a902cc448364880d8b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 24 Nov 2014 13:23:40 -0500
Subject: ip_generic_getfrag, udplite_getfrag: switch to passing msghdr

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/net/udplite.h | 3 ++-
 net/ipv4/ip_output.c  | 6 +++---
 net/ipv4/raw.c        | 2 +-
 net/ipv4/udp.c        | 4 ++--
 net/ipv6/raw.c        | 2 +-
 net/ipv6/udp.c        | 2 +-
 net/l2tp/l2tp_ip6.c   | 2 +-
 7 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/udplite.h b/include/net/udplite.h
index 9a28a517940..d5baaba65b4 100644
--- a/include/net/udplite.h
+++ b/include/net/udplite.h
@@ -19,7 +19,8 @@ extern struct udp_table		udplite_table;
 static __inline__ int udplite_getfrag(void *from, char *to, int  offset,
 				      int len, int odd, struct sk_buff *skb)
 {
-	return memcpy_fromiovecend(to, (struct iovec *) from, offset, len);
+	struct msghdr *msg = from;
+	return memcpy_fromiovecend(to, msg->msg_iov, offset, len);
 }
 
 /* Designate sk as UDP-Lite socket */
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 4a929adf2ab..cdedcf14446 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -752,14 +752,14 @@ EXPORT_SYMBOL(ip_fragment);
 int
 ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
 {
-	struct iovec *iov = from;
+	struct msghdr *msg = from;
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		if (memcpy_fromiovecend(to, iov, offset, len) < 0)
+		if (memcpy_fromiovecend(to, msg->msg_iov, offset, len) < 0)
 			return -EFAULT;
 	} else {
 		__wsum csum = 0;
-		if (csum_partial_copy_fromiovecend(to, iov, offset, len, &csum) < 0)
+		if (csum_partial_copy_fromiovecend(to, msg->msg_iov, offset, len, &csum) < 0)
 			return -EFAULT;
 		skb->csum = csum_block_add(skb->csum, csum, odd);
 	}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 5c901ebf90a..5d83bd2fced 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -478,7 +478,7 @@ static int raw_getfrag(void *from, char *to, int offset, int len, int odd,
 
 	offset -= rfv->hlen;
 
-	return ip_generic_getfrag(rfv->msg->msg_iov, to, offset, len, odd, skb);
+	return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb);
 }
 
 static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index dd8e0063456..13b4dcf86ef 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1049,7 +1049,7 @@ back_from_confirm:
 
 	/* Lockless fast path for the non-corking case. */
 	if (!corkreq) {
-		skb = ip_make_skb(sk, fl4, getfrag, msg->msg_iov, ulen,
+		skb = ip_make_skb(sk, fl4, getfrag, msg, ulen,
 				  sizeof(struct udphdr), &ipc, &rt,
 				  msg->msg_flags);
 		err = PTR_ERR(skb);
@@ -1080,7 +1080,7 @@ back_from_confirm:
 
 do_append_data:
 	up->len += ulen;
-	err = ip_append_data(sk, fl4, getfrag, msg->msg_iov, ulen,
+	err = ip_append_data(sk, fl4, getfrag, msg, ulen,
 			     sizeof(struct udphdr), &ipc, &rt,
 			     corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
 	if (err)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 942f67b9127..11a9283fda5 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -727,7 +727,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd,
 
 	offset -= rfv->hlen;
 
-	return ip_generic_getfrag(rfv->msg->msg_iov, to, offset, len, odd, skb);
+	return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb);
 }
 
 static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 7f96432292c..189dc4ae3ec 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1312,7 +1312,7 @@ do_append_data:
 		dontfrag = np->dontfrag;
 	up->len += ulen;
 	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
-	err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen,
+	err = ip6_append_data(sk, getfrag, msg, ulen,
 		sizeof(struct udphdr), hlimit, tclass, opt, &fl6,
 		(struct rt6_info *)dst,
 		corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 2177b960da8..8611f1b6314 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -619,7 +619,7 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 back_from_confirm:
 	lock_sock(sk);
-	err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
+	err = ip6_append_data(sk, ip_generic_getfrag, msg,
 			      ulen, transhdrlen, hlimit, tclass, opt,
 			      &fl6, (struct rt6_info *)dst,
 			      msg->msg_flags, dontfrag);
-- 
cgit v1.2.3-70-g09d2


From f4362a2c9524678f0459cf410403f8595e5cfce5 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 24 Nov 2014 13:26:06 -0500
Subject: switch tcp_sock->ucopy from iovec (ucopy.iov) to msghdr (ucopy.msg)

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/tcp.h  | 2 +-
 net/ipv4/tcp.c       | 2 +-
 net/ipv4/tcp_input.c | 7 +++----
 3 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index f566b856789..5d9cc9cd285 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -162,7 +162,7 @@ struct tcp_sock {
 	struct {
 		struct sk_buff_head	prequeue;
 		struct task_struct	*task;
-		struct iovec		*iov;
+		struct msghdr		*msg;
 		int			memory;
 		int			len;
 	} ucopy;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index dc13a3657e8..4a96f373017 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1729,7 +1729,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) {
 				user_recv = current;
 				tp->ucopy.task = user_recv;
-				tp->ucopy.iov = msg->msg_iov;
+				tp->ucopy.msg = msg;
 			}
 
 			tp->ucopy.len = len;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 69de1a1c05c..075ab4d5af5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4421,7 +4421,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 			__set_current_state(TASK_RUNNING);
 
 			local_bh_enable();
-			if (!skb_copy_datagram_iovec(skb, 0, tp->ucopy.iov, chunk)) {
+			if (!skb_copy_datagram_msg(skb, 0, tp->ucopy.msg, chunk)) {
 				tp->ucopy.len -= chunk;
 				tp->copied_seq += chunk;
 				eaten = (chunk == skb->len);
@@ -4941,10 +4941,9 @@ static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen)
 
 	local_bh_enable();
 	if (skb_csum_unnecessary(skb))
-		err = skb_copy_datagram_iovec(skb, hlen, tp->ucopy.iov, chunk);
+		err = skb_copy_datagram_msg(skb, hlen, tp->ucopy.msg, chunk);
 	else
-		err = skb_copy_and_csum_datagram_iovec(skb, hlen,
-						       tp->ucopy.iov);
+		err = skb_copy_and_csum_datagram_msg(skb, hlen, tp->ucopy.msg);
 
 	if (!err) {
 		tp->ucopy.len -= chunk;
-- 
cgit v1.2.3-70-g09d2


From 56c39fb67cdb665ae67fba4975f5e20e6614cda6 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 24 Nov 2014 16:44:09 -0500
Subject: switch l2cap ->memcpy_fromiovec() to msghdr

it'll die soon enough - now that kvec-backed iov_iter works regardless
of set_fs(), both instances will become copy_from_iter() as soon as
we introduce ->msg_iter...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/net/bluetooth/l2cap.h | 6 +++---
 net/bluetooth/l2cap_core.c    | 4 ++--
 net/bluetooth/l2cap_sock.c    | 4 ++--
 3 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 061e648052c..4e23674d364 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -608,7 +608,7 @@ struct l2cap_ops {
 					       unsigned long len, int nb);
 	int			(*memcpy_fromiovec) (struct l2cap_chan *chan,
 						     unsigned char *kdata,
-						     struct iovec *iov,
+						     struct msghdr *msg,
 						     int len);
 };
 
@@ -905,13 +905,13 @@ static inline long l2cap_chan_no_get_sndtimeo(struct l2cap_chan *chan)
 
 static inline int l2cap_chan_no_memcpy_fromiovec(struct l2cap_chan *chan,
 						 unsigned char *kdata,
-						 struct iovec *iov,
+						 struct msghdr *msg,
 						 int len)
 {
 	/* Following is safe since for compiler definitions of kvec and
 	 * iovec are identical, yielding the same in-core layout and alignment
 	 */
-	struct kvec *vec = (struct kvec *)iov;
+	struct kvec *vec = (struct kvec *)msg->msg_iov;
 
 	while (len > 0) {
 		if (vec->iov_len) {
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 8e127317302..5201d6167ac 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -2097,7 +2097,7 @@ static inline int l2cap_skbuff_fromiovec(struct l2cap_chan *chan,
 	int sent = 0;
 
 	if (chan->ops->memcpy_fromiovec(chan, skb_put(skb, count),
-					msg->msg_iov, count))
+					msg, count))
 		return -EFAULT;
 
 	sent += count;
@@ -2118,7 +2118,7 @@ static inline int l2cap_skbuff_fromiovec(struct l2cap_chan *chan,
 		*frag = tmp;
 
 		if (chan->ops->memcpy_fromiovec(chan, skb_put(*frag, count),
-						msg->msg_iov, count))
+						msg, count))
 			return -EFAULT;
 
 		sent += count;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index b0efb720295..205b298d9ef 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1338,9 +1338,9 @@ static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan,
 
 static int l2cap_sock_memcpy_fromiovec_cb(struct l2cap_chan *chan,
 					  unsigned char *kdata,
-					  struct iovec *iov, int len)
+					  struct msghdr *msg, int len)
 {
-	return memcpy_fromiovec(kdata, iov, len);
+	return memcpy_from_msg(kdata, msg, len);
 }
 
 static void l2cap_sock_ready_cb(struct l2cap_chan *chan)
-- 
cgit v1.2.3-70-g09d2


From d838df2e5dcbb6ed4d82854869e9a30f9aeef6da Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 24 Nov 2014 19:32:50 -0500
Subject: vmci: propagate msghdr all way down to __qp_memcpy_from_queue()

... and switch it to memcpy_to_msg()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/misc/vmw_vmci/vmci_queue_pair.c | 17 +++++++++--------
 include/linux/vmw_vmci_api.h            |  5 +++--
 net/vmw_vsock/vmci_transport.c          |  4 ++--
 3 files changed, 14 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c
index 1b7b303085d..7aaaf51e159 100644
--- a/drivers/misc/vmw_vmci/vmci_queue_pair.c
+++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c
@@ -27,6 +27,7 @@
 #include <linux/uio.h>
 #include <linux/wait.h>
 #include <linux/vmalloc.h>
+#include <linux/skbuff.h>
 
 #include "vmci_handle_array.h"
 #include "vmci_queue_pair.h"
@@ -429,11 +430,11 @@ static int __qp_memcpy_from_queue(void *dest,
 			to_copy = size - bytes_copied;
 
 		if (is_iovec) {
-			struct iovec *iov = (struct iovec *)dest;
+			struct msghdr *msg = dest;
 			int err;
 
 			/* The iovec will track bytes_copied internally. */
-			err = memcpy_toiovec(iov, (u8 *)va + page_offset,
+			err = memcpy_to_msg(msg, (u8 *)va + page_offset,
 					     to_copy);
 			if (err != 0) {
 				if (kernel_if->host)
@@ -3264,13 +3265,13 @@ EXPORT_SYMBOL_GPL(vmci_qpair_enquev);
  * of bytes dequeued or < 0 on error.
  */
 ssize_t vmci_qpair_dequev(struct vmci_qp *qpair,
-			  void *iov,
+			  struct msghdr *msg,
 			  size_t iov_size,
 			  int buf_type)
 {
 	ssize_t result;
 
-	if (!qpair || !iov)
+	if (!qpair)
 		return VMCI_ERROR_INVALID_ARGS;
 
 	qp_lock(qpair);
@@ -3279,7 +3280,7 @@ ssize_t vmci_qpair_dequev(struct vmci_qp *qpair,
 		result = qp_dequeue_locked(qpair->produce_q,
 					   qpair->consume_q,
 					   qpair->consume_q_size,
-					   iov, iov_size,
+					   msg, iov_size,
 					   qp_memcpy_from_queue_iov,
 					   true);
 
@@ -3308,13 +3309,13 @@ EXPORT_SYMBOL_GPL(vmci_qpair_dequev);
  * of bytes peeked or < 0 on error.
  */
 ssize_t vmci_qpair_peekv(struct vmci_qp *qpair,
-			 void *iov,
+			 struct msghdr *msg,
 			 size_t iov_size,
 			 int buf_type)
 {
 	ssize_t result;
 
-	if (!qpair || !iov)
+	if (!qpair)
 		return VMCI_ERROR_INVALID_ARGS;
 
 	qp_lock(qpair);
@@ -3323,7 +3324,7 @@ ssize_t vmci_qpair_peekv(struct vmci_qp *qpair,
 		result = qp_dequeue_locked(qpair->produce_q,
 					   qpair->consume_q,
 					   qpair->consume_q_size,
-					   iov, iov_size,
+					   msg, iov_size,
 					   qp_memcpy_from_queue_iov,
 					   false);
 
diff --git a/include/linux/vmw_vmci_api.h b/include/linux/vmw_vmci_api.h
index 023430e265f..5691f752ce8 100644
--- a/include/linux/vmw_vmci_api.h
+++ b/include/linux/vmw_vmci_api.h
@@ -24,6 +24,7 @@
 #define VMCI_KERNEL_API_VERSION_2 2
 #define VMCI_KERNEL_API_VERSION   VMCI_KERNEL_API_VERSION_2
 
+struct msghdr;
 typedef void (vmci_device_shutdown_fn) (void *device_registration,
 					void *user_data);
 
@@ -75,8 +76,8 @@ ssize_t vmci_qpair_peek(struct vmci_qp *qpair, void *buf, size_t buf_size,
 ssize_t vmci_qpair_enquev(struct vmci_qp *qpair,
 			  void *iov, size_t iov_size, int mode);
 ssize_t vmci_qpair_dequev(struct vmci_qp *qpair,
-			  void *iov, size_t iov_size, int mode);
-ssize_t vmci_qpair_peekv(struct vmci_qp *qpair, void *iov, size_t iov_size,
+			  struct msghdr *msg, size_t iov_size, int mode);
+ssize_t vmci_qpair_peekv(struct vmci_qp *qpair, struct msghdr *msg, size_t iov_size,
 			 int mode);
 
 #endif /* !__VMW_VMCI_API_H__ */
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index c1c03895297..20a0ba3bfff 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1840,9 +1840,9 @@ static ssize_t vmci_transport_stream_dequeue(
 	int flags)
 {
 	if (flags & MSG_PEEK)
-		return vmci_qpair_peekv(vmci_trans(vsk)->qpair, msg->msg_iov, len, 0);
+		return vmci_qpair_peekv(vmci_trans(vsk)->qpair, msg, len, 0);
 	else
-		return vmci_qpair_dequev(vmci_trans(vsk)->qpair, msg->msg_iov, len, 0);
+		return vmci_qpair_dequev(vmci_trans(vsk)->qpair, msg, len, 0);
 }
 
 static ssize_t vmci_transport_stream_enqueue(
-- 
cgit v1.2.3-70-g09d2


From c0371da6047abd261bc483c744dbc7d81a116172 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 24 Nov 2014 10:42:55 -0500
Subject: put iov_iter into msghdr

Note that the code _using_ ->msg_iter at that point will be very
unhappy with anything other than unshifted iovec-backed iov_iter.
We still need to convert users to proper primitives.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 crypto/algif_hash.c            |  4 ++--
 crypto/algif_skcipher.c        |  4 ++--
 drivers/net/macvtap.c          |  8 ++------
 drivers/net/tun.c              |  8 ++------
 drivers/vhost/net.c            |  8 +++-----
 fs/afs/rxrpc.c                 | 14 ++++++--------
 include/linux/skbuff.h         | 16 ++++++++++------
 include/linux/socket.h         |  3 +--
 include/net/bluetooth/l2cap.h  |  2 +-
 include/net/udplite.h          |  3 ++-
 net/atm/common.c               |  5 +----
 net/bluetooth/6lowpan.c        |  6 +++---
 net/bluetooth/a2mp.c           |  3 +--
 net/bluetooth/smp.c            |  3 +--
 net/caif/caif_socket.c         |  2 +-
 net/compat.c                   | 10 ++++++----
 net/ipv4/ip_output.c           |  6 ++++--
 net/ipv4/ping.c                |  3 ++-
 net/ipv4/raw.c                 |  3 ++-
 net/ipv4/tcp.c                 |  6 +++---
 net/ipv4/tcp_output.c          |  2 +-
 net/ipv6/ping.c                |  3 ++-
 net/ipv6/raw.c                 |  3 ++-
 net/netlink/af_netlink.c       |  2 +-
 net/packet/af_packet.c         |  7 ++-----
 net/rds/recv.c                 |  7 ++++---
 net/rds/send.c                 |  4 +---
 net/rxrpc/ar-output.c          |  8 +++-----
 net/sctp/socket.c              |  5 +----
 net/socket.c                   | 27 ++++++++++++---------------
 net/tipc/msg.c                 |  4 ++--
 net/unix/af_unix.c             | 10 ++--------
 net/vmw_vsock/vmci_transport.c |  3 ++-
 33 files changed, 90 insertions(+), 112 deletions(-)

(limited to 'include')

diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 35c93ff11f3..83cd2cc49c9 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -42,7 +42,7 @@ static int hash_sendmsg(struct kiocb *unused, struct socket *sock,
 	struct alg_sock *ask = alg_sk(sk);
 	struct hash_ctx *ctx = ask->private;
 	unsigned long iovlen;
-	struct iovec *iov;
+	const struct iovec *iov;
 	long copied = 0;
 	int err;
 
@@ -58,7 +58,7 @@ static int hash_sendmsg(struct kiocb *unused, struct socket *sock,
 
 	ctx->more = 0;
 
-	for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0;
+	for (iov = msg->msg_iter.iov, iovlen = msg->msg_iter.nr_segs; iovlen > 0;
 	     iovlen--, iov++) {
 		unsigned long seglen = iov->iov_len;
 		char __user *from = iov->iov_base;
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index c3b482bee20..4f45dab2464 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -429,13 +429,13 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock,
 	struct skcipher_sg_list *sgl;
 	struct scatterlist *sg;
 	unsigned long iovlen;
-	struct iovec *iov;
+	const struct iovec *iov;
 	int err = -EAGAIN;
 	int used;
 	long copied = 0;
 
 	lock_sock(sk);
-	for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0;
+	for (iov = msg->msg_iter.iov, iovlen = msg->msg_iter.nr_segs; iovlen > 0;
 	     iovlen--, iov++) {
 		unsigned long seglen = iov->iov_len;
 		char __user *from = iov->iov_base;
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index ba1e5db2152..2c157cced81 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -1095,9 +1095,7 @@ static int macvtap_sendmsg(struct kiocb *iocb, struct socket *sock,
 			   struct msghdr *m, size_t total_len)
 {
 	struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock);
-	struct iov_iter from;
-	iov_iter_init(&from, WRITE, m->msg_iov, m->msg_iovlen, total_len);
-	return macvtap_get_user(q, m, &from, m->msg_flags & MSG_DONTWAIT);
+	return macvtap_get_user(q, m, &m->msg_iter, m->msg_flags & MSG_DONTWAIT);
 }
 
 static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock,
@@ -1105,12 +1103,10 @@ static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock,
 			   int flags)
 {
 	struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock);
-	struct iov_iter to;
 	int ret;
 	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
 		return -EINVAL;
-	iov_iter_init(&to, READ, m->msg_iov, m->msg_iovlen, total_len);
-	ret = macvtap_do_read(q, &to, flags & MSG_DONTWAIT);
+	ret = macvtap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT);
 	if (ret > total_len) {
 		m->msg_flags |= MSG_TRUNC;
 		ret = flags & MSG_TRUNC ? ret : total_len;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9c58286b8a4..f3e992ed87a 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1449,13 +1449,11 @@ static int tun_sendmsg(struct kiocb *iocb, struct socket *sock,
 	int ret;
 	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
 	struct tun_struct *tun = __tun_get(tfile);
-	struct iov_iter from;
 
 	if (!tun)
 		return -EBADFD;
 
-	iov_iter_init(&from, WRITE, m->msg_iov, m->msg_iovlen, total_len);
-	ret = tun_get_user(tun, tfile, m->msg_control, &from,
+	ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter,
 			   m->msg_flags & MSG_DONTWAIT);
 	tun_put(tun);
 	return ret;
@@ -1467,7 +1465,6 @@ static int tun_recvmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
 	struct tun_struct *tun = __tun_get(tfile);
-	struct iov_iter to;
 	int ret;
 
 	if (!tun)
@@ -1482,8 +1479,7 @@ static int tun_recvmsg(struct kiocb *iocb, struct socket *sock,
 					 SOL_PACKET, TUN_TX_TIMESTAMP);
 		goto out;
 	}
-	iov_iter_init(&to, READ, m->msg_iov, m->msg_iovlen, total_len);
-	ret = tun_do_read(tun, tfile, &to, flags & MSG_DONTWAIT);
+	ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT);
 	if (ret > total_len) {
 		m->msg_flags |= MSG_TRUNC;
 		ret = flags & MSG_TRUNC ? ret : total_len;
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 8dae2f724a3..9f06e70a263 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -342,7 +342,6 @@ static void handle_tx(struct vhost_net *net)
 		.msg_namelen = 0,
 		.msg_control = NULL,
 		.msg_controllen = 0,
-		.msg_iov = vq->iov,
 		.msg_flags = MSG_DONTWAIT,
 	};
 	size_t len, total_len = 0;
@@ -396,8 +395,8 @@ static void handle_tx(struct vhost_net *net)
 		}
 		/* Skip header. TODO: support TSO. */
 		s = move_iovec_hdr(vq->iov, nvq->hdr, hdr_size, out);
-		msg.msg_iovlen = out;
 		len = iov_length(vq->iov, out);
+		iov_iter_init(&msg.msg_iter, WRITE, vq->iov, out, len);
 		/* Sanity check */
 		if (!len) {
 			vq_err(vq, "Unexpected header len for TX: "
@@ -562,7 +561,6 @@ static void handle_rx(struct vhost_net *net)
 		.msg_namelen = 0,
 		.msg_control = NULL, /* FIXME: get and handle RX aux data. */
 		.msg_controllen = 0,
-		.msg_iov = vq->iov,
 		.msg_flags = MSG_DONTWAIT,
 	};
 	struct virtio_net_hdr_mrg_rxbuf hdr = {
@@ -600,7 +598,7 @@ static void handle_rx(struct vhost_net *net)
 			break;
 		/* On overrun, truncate and discard */
 		if (unlikely(headcount > UIO_MAXIOV)) {
-			msg.msg_iovlen = 1;
+			iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1);
 			err = sock->ops->recvmsg(NULL, sock, &msg,
 						 1, MSG_DONTWAIT | MSG_TRUNC);
 			pr_debug("Discarded rx packet: len %zd\n", sock_len);
@@ -626,7 +624,7 @@ static void handle_rx(struct vhost_net *net)
 			/* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF:
 			 * needed because recvmsg can modify msg_iov. */
 			copy_iovec_hdr(vq->iov, nvq->hdr, sock_hlen, in);
-		msg.msg_iovlen = in;
+		iov_iter_init(&msg.msg_iter, READ, vq->iov, in, sock_len);
 		err = sock->ops->recvmsg(NULL, sock, &msg,
 					 sock_len, MSG_DONTWAIT | MSG_TRUNC);
 		/* Userspace might have consumed the packet meanwhile:
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 03a3beb1700..06e14bfb349 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -306,8 +306,8 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg,
 
 			_debug("- range %u-%u%s",
 			       offset, to, msg->msg_flags ? " [more]" : "");
-			msg->msg_iov = (struct iovec *) iov;
-			msg->msg_iovlen = 1;
+			iov_iter_init(&msg->msg_iter, WRITE,
+				      (struct iovec *) iov, 1, to - offset);
 
 			/* have to change the state *before* sending the last
 			 * packet as RxRPC might give us the reply before it
@@ -384,8 +384,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 
 	msg.msg_name		= NULL;
 	msg.msg_namelen		= 0;
-	msg.msg_iov		= (struct iovec *) iov;
-	msg.msg_iovlen		= 1;
+	iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *)iov, 1,
+		      call->request_size);
 	msg.msg_control		= NULL;
 	msg.msg_controllen	= 0;
 	msg.msg_flags		= (call->send_pages ? MSG_MORE : 0);
@@ -778,8 +778,7 @@ void afs_send_empty_reply(struct afs_call *call)
 	iov[0].iov_len		= 0;
 	msg.msg_name		= NULL;
 	msg.msg_namelen		= 0;
-	msg.msg_iov		= iov;
-	msg.msg_iovlen		= 0;
+	iov_iter_init(&msg.msg_iter, WRITE, iov, 0, 0);	/* WTF? */
 	msg.msg_control		= NULL;
 	msg.msg_controllen	= 0;
 	msg.msg_flags		= 0;
@@ -815,8 +814,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
 	iov[0].iov_len		= len;
 	msg.msg_name		= NULL;
 	msg.msg_namelen		= 0;
-	msg.msg_iov		= iov;
-	msg.msg_iovlen		= 1;
+	iov_iter_init(&msg.msg_iter, WRITE, iov, 1, len);
 	msg.msg_control		= NULL;
 	msg.msg_controllen	= 0;
 	msg.msg_flags		= 0;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ef64cec4280..52cf1bdac0d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2646,22 +2646,24 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
 			   struct poll_table_struct *wait);
 int skb_copy_datagram_iovec(const struct sk_buff *from, int offset,
 			    struct iovec *to, int size);
+int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
+			   struct iov_iter *to, int size);
 static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
 					struct msghdr *msg, int size)
 {
-	return skb_copy_datagram_iovec(from, offset, msg->msg_iov, size);
+	/* XXX: stripping const */
+	return skb_copy_datagram_iovec(from, offset, (struct iovec *)msg->msg_iter.iov, size);
 }
 int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, int hlen,
 				     struct iovec *iov);
 static inline int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen,
 			    struct msghdr *msg)
 {
-	return skb_copy_and_csum_datagram_iovec(skb, hlen, msg->msg_iov);
+	/* XXX: stripping const */
+	return skb_copy_and_csum_datagram_iovec(skb, hlen, (struct iovec *)msg->msg_iter.iov);
 }
 int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 				 struct iov_iter *from, int len);
-int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
-			   struct iov_iter *to, int size);
 int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm);
 void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
 void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb);
@@ -2689,12 +2691,14 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
 
 static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len)
 {
-	return memcpy_fromiovec(data, msg->msg_iov, len);
+	/* XXX: stripping const */
+	return memcpy_fromiovec(data, (struct iovec *)msg->msg_iter.iov, len);
 }
 
 static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len)
 {
-	return memcpy_toiovec(msg->msg_iov, data, len);
+	/* XXX: stripping const */
+	return memcpy_toiovec((struct iovec *)msg->msg_iter.iov, data, len);
 }
 
 struct skb_checksum_ops {
diff --git a/include/linux/socket.h b/include/linux/socket.h
index de5222832be..048d6d6eed6 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -47,8 +47,7 @@ struct linger {
 struct msghdr {
 	void		*msg_name;	/* ptr to socket address structure */
 	int		msg_namelen;	/* size of socket address structure */
-	struct iovec	*msg_iov;	/* scatter/gather array */
-	__kernel_size_t	msg_iovlen;	/* # elements in msg_iov */
+	struct iov_iter	msg_iter;	/* data */
 	void		*msg_control;	/* ancillary data */
 	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
 	unsigned int	msg_flags;	/* flags on received message */
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 4e23674d364..bca6fc0a319 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -911,7 +911,7 @@ static inline int l2cap_chan_no_memcpy_fromiovec(struct l2cap_chan *chan,
 	/* Following is safe since for compiler definitions of kvec and
 	 * iovec are identical, yielding the same in-core layout and alignment
 	 */
-	struct kvec *vec = (struct kvec *)msg->msg_iov;
+	struct kvec *vec = (struct kvec *)msg->msg_iter.iov;
 
 	while (len > 0) {
 		if (vec->iov_len) {
diff --git a/include/net/udplite.h b/include/net/udplite.h
index d5baaba65b4..ae7c8d1fbca 100644
--- a/include/net/udplite.h
+++ b/include/net/udplite.h
@@ -20,7 +20,8 @@ static __inline__ int udplite_getfrag(void *from, char *to, int  offset,
 				      int len, int odd, struct sk_buff *skb)
 {
 	struct msghdr *msg = from;
-	return memcpy_fromiovecend(to, msg->msg_iov, offset, len);
+	/* XXX: stripping const */
+	return memcpy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len);
 }
 
 /* Designate sk as UDP-Lite socket */
diff --git a/net/atm/common.c b/net/atm/common.c
index f59112944c9..b84057e41bd 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -577,9 +577,6 @@ int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
 	struct atm_vcc *vcc;
 	struct sk_buff *skb;
 	int eff, error;
-	struct iov_iter from;
-
-	iov_iter_init(&from, WRITE, m->msg_iov, m->msg_iovlen, size);
 
 	lock_sock(sk);
 	if (sock->state != SS_CONNECTED) {
@@ -634,7 +631,7 @@ int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
 		goto out;
 	skb->dev = NULL; /* for paths shared with net_device interfaces */
 	ATM_SKB(skb)->atm_options = vcc->atm_options;
-	if (copy_from_iter(skb_put(skb, size), size, &from) != size) {
+	if (copy_from_iter(skb_put(skb, size), size, &m->msg_iter) != size) {
 		kfree_skb(skb);
 		error = -EFAULT;
 		goto out;
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index bdcaefd2db1..d8c67a5e7a0 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -537,12 +537,12 @@ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb,
 	 */
 	chan->data = skb;
 
-	memset(&msg, 0, sizeof(msg));
-	msg.msg_iov = (struct iovec *) &iv;
-	msg.msg_iovlen = 1;
 	iv.iov_base = skb->data;
 	iv.iov_len = skb->len;
 
+	memset(&msg, 0, sizeof(msg));
+	iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *) &iv, 1, skb->len);
+
 	err = l2cap_chan_send(chan, &msg, skb->len);
 	if (err > 0) {
 		netdev->stats.tx_bytes += err;
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 5dcade511fd..716d2a38885 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -60,8 +60,7 @@ void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data)
 
 	memset(&msg, 0, sizeof(msg));
 
-	msg.msg_iov = (struct iovec *) &iv;
-	msg.msg_iovlen = 1;
+	iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *)&iv, 1, total_len);
 
 	l2cap_chan_send(chan, &msg, total_len);
 
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 069b76e03b5..21f555b4df1 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -268,8 +268,7 @@ static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data)
 
 	memset(&msg, 0, sizeof(msg));
 
-	msg.msg_iov = (struct iovec *) &iv;
-	msg.msg_iovlen = 2;
+	iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *)iv, 2, 1 + len);
 
 	l2cap_chan_send(chan, &msg, 1 + len);
 
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index ac618b0b8a4..769b185fefb 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -535,7 +535,7 @@ static int caif_seqpkt_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		goto err;
 
 	ret = -EINVAL;
-	if (unlikely(msg->msg_iov->iov_base == NULL))
+	if (unlikely(msg->msg_iter.iov->iov_base == NULL))
 		goto err;
 	noblock = msg->msg_flags & MSG_DONTWAIT;
 
diff --git a/net/compat.c b/net/compat.c
index 062f157d2a6..3236b4167a3 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -37,13 +37,14 @@ ssize_t get_compat_msghdr(struct msghdr *kmsg,
 			  struct iovec **iov)
 {
 	compat_uptr_t uaddr, uiov, tmp3;
+	compat_size_t nr_segs;
 	ssize_t err;
 
 	if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) ||
 	    __get_user(uaddr, &umsg->msg_name) ||
 	    __get_user(kmsg->msg_namelen, &umsg->msg_namelen) ||
 	    __get_user(uiov, &umsg->msg_iov) ||
-	    __get_user(kmsg->msg_iovlen, &umsg->msg_iovlen) ||
+	    __get_user(nr_segs, &umsg->msg_iovlen) ||
 	    __get_user(tmp3, &umsg->msg_control) ||
 	    __get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
 	    __get_user(kmsg->msg_flags, &umsg->msg_flags))
@@ -68,14 +69,15 @@ ssize_t get_compat_msghdr(struct msghdr *kmsg,
 		kmsg->msg_namelen = 0;
 	}
 
-	if (kmsg->msg_iovlen > UIO_MAXIOV)
+	if (nr_segs > UIO_MAXIOV)
 		return -EMSGSIZE;
 
 	err = compat_rw_copy_check_uvector(save_addr ? READ : WRITE,
-					   compat_ptr(uiov), kmsg->msg_iovlen,
+					   compat_ptr(uiov), nr_segs,
 					   UIO_FASTIOV, *iov, iov);
 	if (err >= 0)
-		kmsg->msg_iov = *iov;
+		iov_iter_init(&kmsg->msg_iter, save_addr ? READ : WRITE,
+			      *iov, nr_segs, err);
 	return err;
 }
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index cdedcf14446..b50861b22b6 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -755,11 +755,13 @@ ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk
 	struct msghdr *msg = from;
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		if (memcpy_fromiovecend(to, msg->msg_iov, offset, len) < 0)
+		/* XXX: stripping const */
+		if (memcpy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len) < 0)
 			return -EFAULT;
 	} else {
 		__wsum csum = 0;
-		if (csum_partial_copy_fromiovecend(to, msg->msg_iov, offset, len, &csum) < 0)
+		/* XXX: stripping const */
+		if (csum_partial_copy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len, &csum) < 0)
 			return -EFAULT;
 		skb->csum = csum_block_add(skb->csum, csum, odd);
 	}
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 8dd4ae0424f..c0d82f78d36 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -811,7 +811,8 @@ back_from_confirm:
 	pfh.icmph.checksum = 0;
 	pfh.icmph.un.echo.id = inet->inet_sport;
 	pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence;
-	pfh.iov = msg->msg_iov;
+	/* XXX: stripping const */
+	pfh.iov = (struct iovec *)msg->msg_iter.iov;
 	pfh.wcheck = 0;
 	pfh.family = AF_INET;
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 5d83bd2fced..0bb68df5055 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -625,7 +625,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 back_from_confirm:
 
 	if (inet->hdrincl)
-		err = raw_send_hdrinc(sk, &fl4, msg->msg_iov, len,
+		/* XXX: stripping const */
+		err = raw_send_hdrinc(sk, &fl4, (struct iovec *)msg->msg_iter.iov, len,
 				      &rt, msg->msg_flags);
 
 	 else {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4a96f373017..54ba6209eea 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1085,7 +1085,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		size_t size)
 {
-	struct iovec *iov;
+	const struct iovec *iov;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 	int iovlen, flags, err, copied = 0;
@@ -1136,8 +1136,8 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	mss_now = tcp_send_mss(sk, &size_goal, flags);
 
 	/* Ok commence sending. */
-	iovlen = msg->msg_iovlen;
-	iov = msg->msg_iov;
+	iovlen = msg->msg_iter.nr_segs;
+	iov = msg->msg_iter.iov;
 	copied = 0;
 
 	err = -EPIPE;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f5bd4bd3f7e..3e225b03eb9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3050,7 +3050,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	syn_data->ip_summed = CHECKSUM_PARTIAL;
 	memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
 	if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space),
-					 fo->data->msg_iov, 0, space))) {
+					 fo->data->msg_iter.iov, 0, space))) {
 		kfree_skb(syn_data);
 		goto fallback;
 	}
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 5b7a1ed2aba..2d3148378a1 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -163,7 +163,8 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	pfh.icmph.checksum = 0;
 	pfh.icmph.un.echo.id = inet->inet_sport;
 	pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence;
-	pfh.iov = msg->msg_iov;
+	/* XXX: stripping const */
+	pfh.iov = (struct iovec *)msg->msg_iter.iov;
 	pfh.wcheck = 0;
 	pfh.family = AF_INET6;
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 11a9283fda5..ee25631f8c2 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -886,7 +886,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 back_from_confirm:
 	if (inet->hdrincl)
-		err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl6, &dst, msg->msg_flags);
+		/* XXX: stripping const */
+		err = rawv6_send_hdrinc(sk, (struct iovec *)msg->msg_iter.iov, len, &fl6, &dst, msg->msg_flags);
 	else {
 		lock_sock(sk);
 		err = ip6_append_data(sk, raw6_getfrag, &rfv,
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 63aa5c8acf1..cc9bcf008b0 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2305,7 +2305,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	}
 
 	if (netlink_tx_is_mmaped(sk) &&
-	    msg->msg_iov->iov_base == NULL) {
+	    msg->msg_iter.iov->iov_base == NULL) {
 		err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group,
 					   siocb);
 		goto out;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index efa84450113..ed2e620b61d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2408,11 +2408,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	unsigned short gso_type = 0;
 	int hlen, tlen;
 	int extra_len = 0;
-	struct iov_iter from;
 	ssize_t n;
 
-	iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, len);
-
 	/*
 	 *	Get and verify the address.
 	 */
@@ -2451,7 +2448,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		len -= vnet_hdr_len;
 
 		err = -EFAULT;
-		n = copy_from_iter(&vnet_hdr, vnet_hdr_len, &from);
+		n = copy_from_iter(&vnet_hdr, vnet_hdr_len, &msg->msg_iter);
 		if (n != vnet_hdr_len)
 			goto out_unlock;
 
@@ -2522,7 +2519,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	}
 
 	/* Returns -EFAULT on error */
-	err = skb_copy_datagram_from_iter(skb, offset, &from, len);
+	err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, len);
 	if (err)
 		goto out_free;
 
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 47d7b1029b3..f9ec1acd801 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -404,7 +404,6 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 	int ret = 0, nonblock = msg_flags & MSG_DONTWAIT;
 	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 	struct rds_incoming *inc = NULL;
-	struct iov_iter to;
 
 	/* udp_recvmsg()->sock_recvtimeo() gets away without locking too.. */
 	timeo = sock_rcvtimeo(sk, nonblock);
@@ -415,6 +414,7 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 		goto out;
 
 	while (1) {
+		struct iov_iter save;
 		/* If there are pending notifications, do those - and nothing else */
 		if (!list_empty(&rs->rs_notify_queue)) {
 			ret = rds_notify_queue_get(rs, msg);
@@ -450,8 +450,8 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 		rdsdebug("copying inc %p from %pI4:%u to user\n", inc,
 			 &inc->i_conn->c_faddr,
 			 ntohs(inc->i_hdr.h_sport));
-		iov_iter_init(&to, READ, msg->msg_iov, msg->msg_iovlen, size);
-		ret = inc->i_conn->c_trans->inc_copy_to_user(inc, &to);
+		save = msg->msg_iter;
+		ret = inc->i_conn->c_trans->inc_copy_to_user(inc, &msg->msg_iter);
 		if (ret < 0)
 			break;
 
@@ -464,6 +464,7 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 			rds_inc_put(inc);
 			inc = NULL;
 			rds_stats_inc(s_recv_deliver_raced);
+			msg->msg_iter = save;
 			continue;
 		}
 
diff --git a/net/rds/send.c b/net/rds/send.c
index 4de62ead1c7..40a5629a0a1 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -934,9 +934,7 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 	int queued = 0, allocated_mr = 0;
 	int nonblock = msg->msg_flags & MSG_DONTWAIT;
 	long timeo = sock_sndtimeo(sk, nonblock);
-	struct iov_iter from;
 
-	iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, payload_len);
 	/* Mirror Linux UDP mirror of BSD error message compatibility */
 	/* XXX: Perhaps MSG_MORE someday */
 	if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_CMSG_COMPAT)) {
@@ -984,7 +982,7 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 			ret = -ENOMEM;
 			goto out;
 		}
-		ret = rds_message_copy_from_user(rm, &from);
+		ret = rds_message_copy_from_user(rm, &msg->msg_iter);
 		if (ret)
 			goto out;
 	}
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c
index 0b4b9a79f5a..86e0f10aa2c 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/ar-output.c
@@ -531,14 +531,12 @@ static int rxrpc_send_data(struct kiocb *iocb,
 	struct rxrpc_skb_priv *sp;
 	unsigned char __user *from;
 	struct sk_buff *skb;
-	struct iovec *iov;
+	const struct iovec *iov;
 	struct sock *sk = &rx->sk;
 	long timeo;
 	bool more;
 	int ret, ioc, segment, copied;
 
-	_enter(",,,{%zu},%zu", msg->msg_iovlen, len);
-
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
 	/* this should be in poll */
@@ -547,8 +545,8 @@ static int rxrpc_send_data(struct kiocb *iocb,
 	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
 		return -EPIPE;
 
-	iov = msg->msg_iov;
-	ioc = msg->msg_iovlen - 1;
+	iov = msg->msg_iter.iov;
+	ioc = msg->msg_iter.nr_segs - 1;
 	from = iov->iov_base;
 	segment = iov->iov_len;
 	iov++;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 0397ac9fd98..c92f96cda69 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1609,9 +1609,6 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk,
 	__u16 sinfo_flags = 0;
 	long timeo;
 	int err;
-	struct iov_iter from;
-
-	iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, msg_len);
 
 	err = 0;
 	sp = sctp_sk(sk);
@@ -1950,7 +1947,7 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk,
 	}
 
 	/* Break the message into multiple chunks of maximum size. */
-	datamsg = sctp_datamsg_from_user(asoc, sinfo, &from);
+	datamsg = sctp_datamsg_from_user(asoc, sinfo, &msg->msg_iter);
 	if (IS_ERR(datamsg)) {
 		err = PTR_ERR(datamsg);
 		goto out_free;
diff --git a/net/socket.c b/net/socket.c
index f676ac4a370..8809afccf7f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -689,8 +689,7 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
 	 * the following is safe, since for compiler definitions of kvec and
 	 * iovec are identical, yielding the same in-core layout and alignment
 	 */
-	msg->msg_iov = (struct iovec *)vec;
-	msg->msg_iovlen = num;
+	iov_iter_init(&msg->msg_iter, WRITE, (struct iovec *)vec, num, size);
 	result = sock_sendmsg(sock, msg, size);
 	set_fs(oldfs);
 	return result;
@@ -853,7 +852,7 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
 	 * the following is safe, since for compiler definitions of kvec and
 	 * iovec are identical, yielding the same in-core layout and alignment
 	 */
-	msg->msg_iov = (struct iovec *)vec, msg->msg_iovlen = num;
+	iov_iter_init(&msg->msg_iter, READ, (struct iovec *)vec, num, size);
 	result = sock_recvmsg(sock, msg, size, flags);
 	set_fs(oldfs);
 	return result;
@@ -913,8 +912,7 @@ static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb,
 	msg->msg_namelen = 0;
 	msg->msg_control = NULL;
 	msg->msg_controllen = 0;
-	msg->msg_iov = (struct iovec *)iov;
-	msg->msg_iovlen = nr_segs;
+	iov_iter_init(&msg->msg_iter, READ, iov, nr_segs, size);
 	msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
 
 	return __sock_recvmsg(iocb, sock, msg, size, msg->msg_flags);
@@ -953,8 +951,7 @@ static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb,
 	msg->msg_namelen = 0;
 	msg->msg_control = NULL;
 	msg->msg_controllen = 0;
-	msg->msg_iov = (struct iovec *)iov;
-	msg->msg_iovlen = nr_segs;
+	iov_iter_init(&msg->msg_iter, WRITE, iov, nr_segs, size);
 	msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
 	if (sock->type == SOCK_SEQPACKET)
 		msg->msg_flags |= MSG_EOR;
@@ -1798,8 +1795,7 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
 	iov.iov_base = buff;
 	iov.iov_len = len;
 	msg.msg_name = NULL;
-	msg.msg_iov = &iov;
-	msg.msg_iovlen = 1;
+	iov_iter_init(&msg.msg_iter, WRITE, &iov, 1, len);
 	msg.msg_control = NULL;
 	msg.msg_controllen = 0;
 	msg.msg_namelen = 0;
@@ -1856,10 +1852,9 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
 
 	msg.msg_control = NULL;
 	msg.msg_controllen = 0;
-	msg.msg_iovlen = 1;
-	msg.msg_iov = &iov;
 	iov.iov_len = size;
 	iov.iov_base = ubuf;
+	iov_iter_init(&msg.msg_iter, READ, &iov, 1, size);
 	/* Save some cycles and don't copy the address if not needed */
 	msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
 	/* We assume all kernel code knows the size of sockaddr_storage */
@@ -1993,13 +1988,14 @@ static ssize_t copy_msghdr_from_user(struct msghdr *kmsg,
 {
 	struct sockaddr __user *uaddr;
 	struct iovec __user *uiov;
+	size_t nr_segs;
 	ssize_t err;
 
 	if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) ||
 	    __get_user(uaddr, &umsg->msg_name) ||
 	    __get_user(kmsg->msg_namelen, &umsg->msg_namelen) ||
 	    __get_user(uiov, &umsg->msg_iov) ||
-	    __get_user(kmsg->msg_iovlen, &umsg->msg_iovlen) ||
+	    __get_user(nr_segs, &umsg->msg_iovlen) ||
 	    __get_user(kmsg->msg_control, &umsg->msg_control) ||
 	    __get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
 	    __get_user(kmsg->msg_flags, &umsg->msg_flags))
@@ -2029,14 +2025,15 @@ static ssize_t copy_msghdr_from_user(struct msghdr *kmsg,
 		kmsg->msg_namelen = 0;
 	}
 
-	if (kmsg->msg_iovlen > UIO_MAXIOV)
+	if (nr_segs > UIO_MAXIOV)
 		return -EMSGSIZE;
 
 	err = rw_copy_check_uvector(save_addr ? READ : WRITE,
-				    uiov, kmsg->msg_iovlen,
+				    uiov, nr_segs,
 				    UIO_FASTIOV, *iov, iov);
 	if (err >= 0)
-		kmsg->msg_iov = *iov;
+		iov_iter_init(&kmsg->msg_iter, save_addr ? READ : WRITE,
+			      *iov, nr_segs, err);
 	return err;
 }
 
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 5b0659791c0..a687b30a699 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -194,7 +194,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset,
 		__skb_queue_tail(list, skb);
 		skb_copy_to_linear_data(skb, mhdr, mhsz);
 		pktpos = skb->data + mhsz;
-		if (!dsz || !memcpy_fromiovecend(pktpos, m->msg_iov, offset,
+		if (!dsz || !memcpy_fromiovecend(pktpos, m->msg_iter.iov, offset,
 						 dsz))
 			return dsz;
 		rc = -EFAULT;
@@ -224,7 +224,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset,
 		if (drem < pktrem)
 			pktrem = drem;
 
-		if (memcpy_fromiovecend(pktpos, m->msg_iov, offset, pktrem)) {
+		if (memcpy_fromiovecend(pktpos, m->msg_iter.iov, offset, pktrem)) {
 			rc = -EFAULT;
 			goto error;
 		}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 4450d622660..8e1b10274b0 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1459,9 +1459,6 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	struct scm_cookie tmp_scm;
 	int max_level;
 	int data_len = 0;
-	struct iov_iter from;
-
-	iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, len);
 
 	if (NULL == siocb->scm)
 		siocb->scm = &tmp_scm;
@@ -1519,7 +1516,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	skb_put(skb, len - data_len);
 	skb->data_len = data_len;
 	skb->len = len;
-	err = skb_copy_datagram_from_iter(skb, 0, &from, len);
+	err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, len);
 	if (err)
 		goto out_free;
 
@@ -1641,9 +1638,6 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	bool fds_sent = false;
 	int max_level;
 	int data_len;
-	struct iov_iter from;
-
-	iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, len);
 
 	if (NULL == siocb->scm)
 		siocb->scm = &tmp_scm;
@@ -1700,7 +1694,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		skb_put(skb, size - data_len);
 		skb->data_len = data_len;
 		skb->len = size;
-		err = skb_copy_datagram_from_iter(skb, 0, &from, size);
+		err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
 		if (err) {
 			kfree_skb(skb);
 			goto out_err;
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 20a0ba3bfff..02d2e522924 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1850,7 +1850,8 @@ static ssize_t vmci_transport_stream_enqueue(
 	struct msghdr *msg,
 	size_t len)
 {
-	return vmci_qpair_enquev(vmci_trans(vsk)->qpair, msg->msg_iov, len, 0);
+	/* XXX: stripping const */
+	return vmci_qpair_enquev(vmci_trans(vsk)->qpair, (struct iovec *)msg->msg_iter.iov, len, 0);
 }
 
 static s64 vmci_transport_stream_has_data(struct vsock_sock *vsk)
-- 
cgit v1.2.3-70-g09d2


From 17836394e578b8d6475ecdb309ad1356bbcf37a2 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 24 Nov 2014 17:07:38 -0500
Subject: first fruits - kill l2cap ->memcpy_fromiovec()

Just use copy_from_iter().  That's what this method is trying to do
in all cases, in a very convoluted fashion.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/net/bluetooth/l2cap.h | 29 -----------------------------
 net/bluetooth/6lowpan.c       |  3 +--
 net/bluetooth/a2mp.c          |  3 +--
 net/bluetooth/l2cap_core.c    |  7 +++----
 net/bluetooth/l2cap_sock.c    |  8 --------
 net/bluetooth/smp.c           |  4 +---
 6 files changed, 6 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index bca6fc0a319..692f786bebe 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -606,10 +606,6 @@ struct l2cap_ops {
 	struct sk_buff		*(*alloc_skb) (struct l2cap_chan *chan,
 					       unsigned long hdr_len,
 					       unsigned long len, int nb);
-	int			(*memcpy_fromiovec) (struct l2cap_chan *chan,
-						     unsigned char *kdata,
-						     struct msghdr *msg,
-						     int len);
 };
 
 struct l2cap_conn {
@@ -903,31 +899,6 @@ static inline long l2cap_chan_no_get_sndtimeo(struct l2cap_chan *chan)
 	return 0;
 }
 
-static inline int l2cap_chan_no_memcpy_fromiovec(struct l2cap_chan *chan,
-						 unsigned char *kdata,
-						 struct msghdr *msg,
-						 int len)
-{
-	/* Following is safe since for compiler definitions of kvec and
-	 * iovec are identical, yielding the same in-core layout and alignment
-	 */
-	struct kvec *vec = (struct kvec *)msg->msg_iter.iov;
-
-	while (len > 0) {
-		if (vec->iov_len) {
-			int copy = min_t(unsigned int, len, vec->iov_len);
-			memcpy(kdata, vec->iov_base, copy);
-			len -= copy;
-			kdata += copy;
-			vec->iov_base += copy;
-			vec->iov_len -= copy;
-		}
-		vec++;
-	}
-
-	return 0;
-}
-
 extern bool disable_ertm;
 
 int l2cap_init_sockets(void);
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index d8c67a5e7a0..76617be1e79 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -541,7 +541,7 @@ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb,
 	iv.iov_len = skb->len;
 
 	memset(&msg, 0, sizeof(msg));
-	iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *) &iv, 1, skb->len);
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, skb->len);
 
 	err = l2cap_chan_send(chan, &msg, skb->len);
 	if (err > 0) {
@@ -1050,7 +1050,6 @@ static const struct l2cap_ops bt_6lowpan_chan_ops = {
 	.suspend		= chan_suspend_cb,
 	.get_sndtimeo		= chan_get_sndtimeo_cb,
 	.alloc_skb		= chan_alloc_skb_cb,
-	.memcpy_fromiovec	= l2cap_chan_no_memcpy_fromiovec,
 
 	.teardown		= l2cap_chan_no_teardown,
 	.defer			= l2cap_chan_no_defer,
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 716d2a38885..cedfbda15da 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -60,7 +60,7 @@ void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data)
 
 	memset(&msg, 0, sizeof(msg));
 
-	iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *)&iv, 1, total_len);
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, total_len);
 
 	l2cap_chan_send(chan, &msg, total_len);
 
@@ -719,7 +719,6 @@ static const struct l2cap_ops a2mp_chan_ops = {
 	.resume = l2cap_chan_no_resume,
 	.set_shutdown = l2cap_chan_no_set_shutdown,
 	.get_sndtimeo = l2cap_chan_no_get_sndtimeo,
-	.memcpy_fromiovec = l2cap_chan_no_memcpy_fromiovec,
 };
 
 static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked)
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 5201d6167ac..1754040d00a 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -2096,8 +2096,7 @@ static inline int l2cap_skbuff_fromiovec(struct l2cap_chan *chan,
 	struct sk_buff **frag;
 	int sent = 0;
 
-	if (chan->ops->memcpy_fromiovec(chan, skb_put(skb, count),
-					msg, count))
+	if (copy_from_iter(skb_put(skb, count), count, &msg->msg_iter) != count)
 		return -EFAULT;
 
 	sent += count;
@@ -2117,8 +2116,8 @@ static inline int l2cap_skbuff_fromiovec(struct l2cap_chan *chan,
 
 		*frag = tmp;
 
-		if (chan->ops->memcpy_fromiovec(chan, skb_put(*frag, count),
-						msg, count))
+		if (copy_from_iter(skb_put(*frag, count), count,
+				   &msg->msg_iter) != count)
 			return -EFAULT;
 
 		sent += count;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 205b298d9ef..f65caf41953 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1336,13 +1336,6 @@ static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan,
 	return skb;
 }
 
-static int l2cap_sock_memcpy_fromiovec_cb(struct l2cap_chan *chan,
-					  unsigned char *kdata,
-					  struct msghdr *msg, int len)
-{
-	return memcpy_from_msg(kdata, msg, len);
-}
-
 static void l2cap_sock_ready_cb(struct l2cap_chan *chan)
 {
 	struct sock *sk = chan->data;
@@ -1427,7 +1420,6 @@ static const struct l2cap_ops l2cap_chan_ops = {
 	.set_shutdown		= l2cap_sock_set_shutdown_cb,
 	.get_sndtimeo		= l2cap_sock_get_sndtimeo_cb,
 	.alloc_skb		= l2cap_sock_alloc_skb_cb,
-	.memcpy_fromiovec	= l2cap_sock_memcpy_fromiovec_cb,
 };
 
 static void l2cap_sock_destruct(struct sock *sk)
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 21f555b4df1..de7dc7581ff 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -268,7 +268,7 @@ static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data)
 
 	memset(&msg, 0, sizeof(msg));
 
-	iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *)iv, 2, 1 + len);
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iv, 2, 1 + len);
 
 	l2cap_chan_send(chan, &msg, 1 + len);
 
@@ -1629,7 +1629,6 @@ static const struct l2cap_ops smp_chan_ops = {
 	.suspend		= l2cap_chan_no_suspend,
 	.set_shutdown		= l2cap_chan_no_set_shutdown,
 	.get_sndtimeo		= l2cap_chan_no_get_sndtimeo,
-	.memcpy_fromiovec	= l2cap_chan_no_memcpy_fromiovec,
 };
 
 static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan)
@@ -1678,7 +1677,6 @@ static const struct l2cap_ops smp_root_chan_ops = {
 	.resume			= l2cap_chan_no_resume,
 	.set_shutdown		= l2cap_chan_no_set_shutdown,
 	.get_sndtimeo		= l2cap_chan_no_get_sndtimeo,
-	.memcpy_fromiovec	= l2cap_chan_no_memcpy_fromiovec,
 };
 
 int smp_register(struct hci_dev *hdev)
-- 
cgit v1.2.3-70-g09d2


From e5a4b0bb803b39a36478451eae53a880d2663d5b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 24 Nov 2014 18:17:55 -0500
Subject: switch memcpy_to_msg() and skb_copy{,_and_csum}_datagram_msg() to
 primitives

... making both non-draining.  That means that tcp_recvmsg() becomes
non-draining.  And _that_ would break iscsit_do_rx_data() unless we
	a) make sure tcp_recvmsg() is uniformly non-draining (it is)
	b) make sure it copes with arbitrary (including shifted)
iov_iter (it does, all it uses is iov_iter primitives)
	c) make iscsit_do_rx_data() initialize ->msg_iter only once.

Fortunately, (c) is doable with minimal work and we are rid of one
the two places where kernel send/recvmsg users would be unhappy with
non-draining behaviour.

Actually, that makes all but one of ->recvmsg() instances iov_iter-clean.
The exception is skcipher_recvmsg() and it also isn't hard to convert
to primitives (iov_iter_get_pages() is needed there).  That'll wait
a bit - there's some interplay with ->sendmsg() path for that one.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/target/iscsi/iscsi_target_util.c | 12 +++----
 include/linux/skbuff.h                   | 16 +++-------
 net/core/datagram.c                      | 54 +++++++++++---------------------
 3 files changed, 28 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index ce87ce9bdb9..7c6a95bcb35 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -1326,21 +1326,19 @@ static int iscsit_do_rx_data(
 	struct iscsi_conn *conn,
 	struct iscsi_data_count *count)
 {
-	int data = count->data_length, rx_loop = 0, total_rx = 0, iov_len;
-	struct kvec *iov_p;
+	int data = count->data_length, rx_loop = 0, total_rx = 0;
 	struct msghdr msg;
 
 	if (!conn || !conn->sock || !conn->conn_ops)
 		return -1;
 
 	memset(&msg, 0, sizeof(struct msghdr));
-
-	iov_p = count->iov;
-	iov_len	= count->iov_count;
+	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC,
+		      count->iov, count->iov_count, data);
 
 	while (total_rx < data) {
-		rx_loop = kernel_recvmsg(conn->sock, &msg, iov_p, iov_len,
-					(data - total_rx), MSG_WAITALL);
+		rx_loop = sock_recvmsg(conn->sock, &msg,
+				      (data - total_rx), MSG_WAITALL);
 		if (rx_loop <= 0) {
 			pr_debug("rx_loop: %d total_rx: %d\n",
 				rx_loop, total_rx);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 52cf1bdac0d..4902f2df90c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2651,17 +2651,10 @@ int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
 static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
 					struct msghdr *msg, int size)
 {
-	/* XXX: stripping const */
-	return skb_copy_datagram_iovec(from, offset, (struct iovec *)msg->msg_iter.iov, size);
-}
-int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, int hlen,
-				     struct iovec *iov);
-static inline int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen,
-			    struct msghdr *msg)
-{
-	/* XXX: stripping const */
-	return skb_copy_and_csum_datagram_iovec(skb, hlen, (struct iovec *)msg->msg_iter.iov);
+	return skb_copy_datagram_iter(from, offset, &msg->msg_iter, size);
 }
+int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen,
+				   struct msghdr *msg);
 int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 				 struct iov_iter *from, int len);
 int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm);
@@ -2697,8 +2690,7 @@ static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len)
 
 static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len)
 {
-	/* XXX: stripping const */
-	return memcpy_toiovec((struct iovec *)msg->msg_iter.iov, data, len);
+	return copy_to_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT;
 }
 
 struct skb_checksum_ops {
diff --git a/net/core/datagram.c b/net/core/datagram.c
index b6e303b0f01..41075ed6bb5 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -615,27 +615,25 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
 EXPORT_SYMBOL(zerocopy_sg_from_iter);
 
 static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
-				      u8 __user *to, int len,
+				      struct iov_iter *to, int len,
 				      __wsum *csump)
 {
 	int start = skb_headlen(skb);
 	int i, copy = start - offset;
 	struct sk_buff *frag_iter;
 	int pos = 0;
+	int n;
 
 	/* Copy header. */
 	if (copy > 0) {
-		int err = 0;
 		if (copy > len)
 			copy = len;
-		*csump = csum_and_copy_to_user(skb->data + offset, to, copy,
-					       *csump, &err);
-		if (err)
+		n = csum_and_copy_to_iter(skb->data + offset, copy, csump, to);
+		if (n != copy)
 			goto fault;
 		if ((len -= copy) == 0)
 			return 0;
 		offset += copy;
-		to += copy;
 		pos = copy;
 	}
 
@@ -647,26 +645,22 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 
 		end = start + skb_frag_size(frag);
 		if ((copy = end - offset) > 0) {
-			__wsum csum2;
-			int err = 0;
-			u8  *vaddr;
+			__wsum csum2 = 0;
 			struct page *page = skb_frag_page(frag);
+			u8  *vaddr = kmap(page);
 
 			if (copy > len)
 				copy = len;
-			vaddr = kmap(page);
-			csum2 = csum_and_copy_to_user(vaddr +
-							frag->page_offset +
-							offset - start,
-						      to, copy, 0, &err);
+			n = csum_and_copy_to_iter(vaddr + frag->page_offset +
+						  offset - start, copy,
+						  &csum2, to);
 			kunmap(page);
-			if (err)
+			if (n != copy)
 				goto fault;
 			*csump = csum_block_add(*csump, csum2, pos);
 			if (!(len -= copy))
 				return 0;
 			offset += copy;
-			to += copy;
 			pos += copy;
 		}
 		start = end;
@@ -691,7 +685,6 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 			if ((len -= copy) == 0)
 				return 0;
 			offset += copy;
-			to += copy;
 			pos += copy;
 		}
 		start = end;
@@ -744,20 +737,19 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb)
 EXPORT_SYMBOL(__skb_checksum_complete);
 
 /**
- *	skb_copy_and_csum_datagram_iovec - Copy and checksum skb to user iovec.
+ *	skb_copy_and_csum_datagram_msg - Copy and checksum skb to user iovec.
  *	@skb: skbuff
  *	@hlen: hardware length
- *	@iov: io vector
+ *	@msg: destination
  *
  *	Caller _must_ check that skb will fit to this iovec.
  *
  *	Returns: 0       - success.
  *		 -EINVAL - checksum failure.
- *		 -EFAULT - fault during copy. Beware, in this case iovec
- *			   can be modified!
+ *		 -EFAULT - fault during copy.
  */
-int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
-				     int hlen, struct iovec *iov)
+int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
+				   int hlen, struct msghdr *msg)
 {
 	__wsum csum;
 	int chunk = skb->len - hlen;
@@ -765,28 +757,20 @@ int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
 	if (!chunk)
 		return 0;
 
-	/* Skip filled elements.
-	 * Pretty silly, look at memcpy_toiovec, though 8)
-	 */
-	while (!iov->iov_len)
-		iov++;
-
-	if (iov->iov_len < chunk) {
+	if (iov_iter_count(&msg->msg_iter) < chunk) {
 		if (__skb_checksum_complete(skb))
 			goto csum_error;
-		if (skb_copy_datagram_iovec(skb, hlen, iov, chunk))
+		if (skb_copy_datagram_msg(skb, hlen, msg, chunk))
 			goto fault;
 	} else {
 		csum = csum_partial(skb->data, hlen, skb->csum);
-		if (skb_copy_and_csum_datagram(skb, hlen, iov->iov_base,
+		if (skb_copy_and_csum_datagram(skb, hlen, &msg->msg_iter,
 					       chunk, &csum))
 			goto fault;
 		if (csum_fold(csum))
 			goto csum_error;
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
 			netdev_rx_csum_fault(skb->dev);
-		iov->iov_len -= chunk;
-		iov->iov_base += chunk;
 	}
 	return 0;
 csum_error:
@@ -794,7 +778,7 @@ csum_error:
 fault:
 	return -EFAULT;
 }
-EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec);
+EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
 
 /**
  * 	datagram_poll - generic datagram poll
-- 
cgit v1.2.3-70-g09d2


From d3a9632f09153bc46a8077844e05e179f1c10c3f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 24 Nov 2014 18:29:54 -0500
Subject: skb_copy_datagram_iovec() can die

no callers other than itself.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/skbuff.h |  2 --
 net/core/datagram.c    | 84 --------------------------------------------------
 2 files changed, 86 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4902f2df90c..ab0bc43c82a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2644,8 +2644,6 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
 				  int *err);
 unsigned int datagram_poll(struct file *file, struct socket *sock,
 			   struct poll_table_struct *wait);
-int skb_copy_datagram_iovec(const struct sk_buff *from, int offset,
-			    struct iovec *to, int size);
 int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
 			   struct iov_iter *to, int size);
 static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 41075ed6bb5..df493d68330 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -309,90 +309,6 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
 }
 EXPORT_SYMBOL(skb_kill_datagram);
 
-/**
- *	skb_copy_datagram_iovec - Copy a datagram to an iovec.
- *	@skb: buffer to copy
- *	@offset: offset in the buffer to start copying from
- *	@to: io vector to copy to
- *	@len: amount of data to copy from buffer to iovec
- *
- *	Note: the iovec is modified during the copy.
- */
-int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
-			    struct iovec *to, int len)
-{
-	int start = skb_headlen(skb);
-	int i, copy = start - offset;
-	struct sk_buff *frag_iter;
-
-	trace_skb_copy_datagram_iovec(skb, len);
-
-	/* Copy header. */
-	if (copy > 0) {
-		if (copy > len)
-			copy = len;
-		if (memcpy_toiovec(to, skb->data + offset, copy))
-			goto fault;
-		if ((len -= copy) == 0)
-			return 0;
-		offset += copy;
-	}
-
-	/* Copy paged appendix. Hmm... why does this look so complicated? */
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		int end;
-		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
-		WARN_ON(start > offset + len);
-
-		end = start + skb_frag_size(frag);
-		if ((copy = end - offset) > 0) {
-			int err;
-			u8  *vaddr;
-			struct page *page = skb_frag_page(frag);
-
-			if (copy > len)
-				copy = len;
-			vaddr = kmap(page);
-			err = memcpy_toiovec(to, vaddr + frag->page_offset +
-					     offset - start, copy);
-			kunmap(page);
-			if (err)
-				goto fault;
-			if (!(len -= copy))
-				return 0;
-			offset += copy;
-		}
-		start = end;
-	}
-
-	skb_walk_frags(skb, frag_iter) {
-		int end;
-
-		WARN_ON(start > offset + len);
-
-		end = start + frag_iter->len;
-		if ((copy = end - offset) > 0) {
-			if (copy > len)
-				copy = len;
-			if (skb_copy_datagram_iovec(frag_iter,
-						    offset - start,
-						    to, copy))
-				goto fault;
-			if ((len -= copy) == 0)
-				return 0;
-			offset += copy;
-		}
-		start = end;
-	}
-	if (!len)
-		return 0;
-
-fault:
-	return -EFAULT;
-}
-EXPORT_SYMBOL(skb_copy_datagram_iovec);
-
 /**
  *	skb_copy_datagram_iter - Copy a datagram to an iovec iterator.
  *	@skb: buffer to copy
-- 
cgit v1.2.3-70-g09d2


From 218321e7a0838c2be974539f0a5341b398d4432b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 24 Nov 2014 19:45:05 -0500
Subject: bury memcpy_toiovec()

no users left

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/uio.h |  1 -
 lib/iovec.c         | 25 -------------------------
 2 files changed, 26 deletions(-)

(limited to 'include')

diff --git a/include/linux/uio.h b/include/linux/uio.h
index bd8569a14c4..a41e252396c 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -131,7 +131,6 @@ size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_
 size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 
 int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len);
-int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len);
 int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
 			int offset, int len);
 int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata,
diff --git a/lib/iovec.c b/lib/iovec.c
index df3abd1eaa4..2d99cb4a500 100644
--- a/lib/iovec.c
+++ b/lib/iovec.c
@@ -27,31 +27,6 @@ int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len)
 }
 EXPORT_SYMBOL(memcpy_fromiovec);
 
-/*
- *	Copy kernel to iovec. Returns -EFAULT on error.
- *
- *	Note: this modifies the original iovec.
- */
-
-int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len)
-{
-	while (len > 0) {
-		if (iov->iov_len) {
-			int copy = min_t(unsigned int, iov->iov_len, len);
-			if (copy_to_user(iov->iov_base, kdata, copy))
-				return -EFAULT;
-			kdata += copy;
-			len -= copy;
-			iov->iov_len -= copy;
-			iov->iov_base += copy;
-		}
-		iov++;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(memcpy_toiovec);
-
 /*
  *	Copy kernel to iovec. Returns -EFAULT on error.
  */
-- 
cgit v1.2.3-70-g09d2


From 605ad7f184b60cfaacbc038aa6c55ee68dee3c89 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 7 Dec 2014 12:22:18 -0800
Subject: tcp: refine TSO autosizing

Commit 95bd09eb2750 ("tcp: TSO packets automatic sizing") tried to
control TSO size, but did this at the wrong place (sendmsg() time)

At sendmsg() time, we might have a pessimistic view of flow rate,
and we end up building very small skbs (with 2 MSS per skb).

This is bad because :

 - It sends small TSO packets even in Slow Start where rate quickly
   increases.
 - It tends to make socket write queue very big, increasing tcp_ack()
   processing time, but also increasing memory needs, not necessarily
   accounted for, as fast clones overhead is currently ignored.
 - Lower GRO efficiency and more ACK packets.

Servers with a lot of small lived connections suffer from this.

Lets instead fill skbs as much as possible (64KB of payload), but split
them at xmit time, when we have a precise idea of the flow rate.
skb split is actually quite efficient.

Patch looks bigger than necessary, because TCP Small Queue decision now
has to take place after the eventual split.

As Neal suggested, introduce a new tcp_tso_autosize() helper, so that
tcp_tso_should_defer() can be synchronized on same goal.

Rename tp->xmit_size_goal_segs to tp->gso_segs, as this variable
contains number of mss that we can put in GSO packet, and is not
related to the autosizing goal anymore.

Tested:

40 ms rtt link

nstat >/dev/null
netperf -H remote -l -2000000 -- -s 1000000
nstat | egrep "IpInReceives|IpOutRequests|TcpOutSegs|IpExtOutOctets"

Before patch :

Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/s

 87380 2000000 2000000    0.36         44.22
IpInReceives                    600                0.0
IpOutRequests                   599                0.0
TcpOutSegs                      1397               0.0
IpExtOutOctets                  2033249            0.0

After patch :

Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380 2000000 2000000    0.36       44.27
IpInReceives                    221                0.0
IpOutRequests                   232                0.0
TcpOutSegs                      1397               0.0
IpExtOutOctets                  2013953            0.0

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h   |  2 +-
 net/ipv4/tcp.c        | 60 ++++++++++++++++++---------------------------------
 net/ipv4/tcp_output.c | 59 ++++++++++++++++++++++++++++++++++----------------
 3 files changed, 63 insertions(+), 58 deletions(-)

(limited to 'include')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index f566b856789..3fa0a9669a3 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -130,7 +130,7 @@ struct tcp_sock {
 	/* inet_connection_sock has to be the first member of tcp_sock */
 	struct inet_connection_sock	inet_conn;
 	u16	tcp_header_len;	/* Bytes of tcp header to send		*/
-	u16	xmit_size_goal_segs; /* Goal for segmenting output packets */
+	u16	gso_segs;	/* Max number of segs per GSO packet	*/
 
 /*
  *	Header prediction flags
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index dc13a3657e8..427aee33ffc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -835,47 +835,29 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
 				       int large_allowed)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 xmit_size_goal, old_size_goal;
-
-	xmit_size_goal = mss_now;
-
-	if (large_allowed && sk_can_gso(sk)) {
-		u32 gso_size, hlen;
-
-		/* Maybe we should/could use sk->sk_prot->max_header here ? */
-		hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
-		       inet_csk(sk)->icsk_ext_hdr_len +
-		       tp->tcp_header_len;
-
-		/* Goal is to send at least one packet per ms,
-		 * not one big TSO packet every 100 ms.
-		 * This preserves ACK clocking and is consistent
-		 * with tcp_tso_should_defer() heuristic.
-		 */
-		gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC);
-		gso_size = max_t(u32, gso_size,
-				 sysctl_tcp_min_tso_segs * mss_now);
-
-		xmit_size_goal = min_t(u32, gso_size,
-				       sk->sk_gso_max_size - 1 - hlen);
-
-		xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
-
-		/* We try hard to avoid divides here */
-		old_size_goal = tp->xmit_size_goal_segs * mss_now;
-
-		if (likely(old_size_goal <= xmit_size_goal &&
-			   old_size_goal + mss_now > xmit_size_goal)) {
-			xmit_size_goal = old_size_goal;
-		} else {
-			tp->xmit_size_goal_segs =
-				min_t(u16, xmit_size_goal / mss_now,
-				      sk->sk_gso_max_segs);
-			xmit_size_goal = tp->xmit_size_goal_segs * mss_now;
-		}
+	u32 new_size_goal, size_goal, hlen;
+
+	if (!large_allowed || !sk_can_gso(sk))
+		return mss_now;
+
+	/* Maybe we should/could use sk->sk_prot->max_header here ? */
+	hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
+	       inet_csk(sk)->icsk_ext_hdr_len +
+	       tp->tcp_header_len;
+
+	new_size_goal = sk->sk_gso_max_size - 1 - hlen;
+	new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal);
+
+	/* We try hard to avoid divides here */
+	size_goal = tp->gso_segs * mss_now;
+	if (unlikely(new_size_goal < size_goal ||
+		     new_size_goal >= size_goal + mss_now)) {
+		tp->gso_segs = min_t(u16, new_size_goal / mss_now,
+				     sk->sk_gso_max_segs);
+		size_goal = tp->gso_segs * mss_now;
 	}
 
-	return max(xmit_size_goal, mss_now);
+	return max(size_goal, mss_now);
 }
 
 static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f5bd4bd3f7e..f37ecf53ee8 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1524,6 +1524,27 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
 		((nonagle & TCP_NAGLE_CORK) ||
 		 (!nonagle && tp->packets_out && tcp_minshall_check(tp)));
 }
+
+/* Return how many segs we'd like on a TSO packet,
+ * to send one TSO packet per ms
+ */
+static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now)
+{
+	u32 bytes, segs;
+
+	bytes = min(sk->sk_pacing_rate >> 10,
+		    sk->sk_gso_max_size - 1 - MAX_TCP_HEADER);
+
+	/* Goal is to send at least one packet per ms,
+	 * not one big TSO packet every 100 ms.
+	 * This preserves ACK clocking and is consistent
+	 * with tcp_tso_should_defer() heuristic.
+	 */
+	segs = max_t(u32, bytes / mss_now, sysctl_tcp_min_tso_segs);
+
+	return min_t(u32, segs, sk->sk_gso_max_segs);
+}
+
 /* Returns the portion of skb which can be sent right away */
 static unsigned int tcp_mss_split_point(const struct sock *sk,
 					const struct sk_buff *skb,
@@ -1731,7 +1752,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
  * This algorithm is from John Heffner.
  */
 static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
-				 bool *is_cwnd_limited)
+				 bool *is_cwnd_limited, u32 max_segs)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1761,8 +1782,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	limit = min(send_win, cong_win);
 
 	/* If a full-sized TSO skb can be sent, do it. */
-	if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
-			   tp->xmit_size_goal_segs * tp->mss_cache))
+	if (limit >= max_segs * tp->mss_cache)
 		goto send_now;
 
 	/* Middle in queue won't get any more data, full sendable already? */
@@ -1959,6 +1979,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	int cwnd_quota;
 	int result;
 	bool is_cwnd_limited = false;
+	u32 max_segs;
 
 	sent_pkts = 0;
 
@@ -1972,6 +1993,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		}
 	}
 
+	max_segs = tcp_tso_autosize(sk, mss_now);
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
@@ -2004,10 +2026,23 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 				break;
 		} else {
 			if (!push_one &&
-			    tcp_tso_should_defer(sk, skb, &is_cwnd_limited))
+			    tcp_tso_should_defer(sk, skb, &is_cwnd_limited,
+						 max_segs))
 				break;
 		}
 
+		limit = mss_now;
+		if (tso_segs > 1 && !tcp_urg_mode(tp))
+			limit = tcp_mss_split_point(sk, skb, mss_now,
+						    min_t(unsigned int,
+							  cwnd_quota,
+							  max_segs),
+						    nonagle);
+
+		if (skb->len > limit &&
+		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
+			break;
+
 		/* TCP Small Queues :
 		 * Control number of packets in qdisc/devices to two packets / or ~1 ms.
 		 * This allows for :
@@ -2018,8 +2053,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		 * of queued bytes to ensure line rate.
 		 * One example is wifi aggregation (802.11 AMPDU)
 		 */
-		limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes,
-			      sk->sk_pacing_rate >> 10);
+		limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10);
+		limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes);
 
 		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
@@ -2032,18 +2067,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 				break;
 		}
 
-		limit = mss_now;
-		if (tso_segs > 1 && !tcp_urg_mode(tp))
-			limit = tcp_mss_split_point(sk, skb, mss_now,
-						    min_t(unsigned int,
-							  cwnd_quota,
-							  sk->sk_gso_max_segs),
-						    nonagle);
-
-		if (skb->len > limit &&
-		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
-			break;
-
 		if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
 			break;
 
-- 
cgit v1.2.3-70-g09d2


From 273d2c67c3e179adb1e74f403d1e9a06e3f841b5 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 5 Dec 2014 18:01:11 -0600
Subject: userns: Don't allow setgroups until a gid mapping has been
 setablished

setgroups is unique in not needing a valid mapping before it can be called,
in the case of setgroups(0, NULL) which drops all supplemental groups.

The design of the user namespace assumes that CAP_SETGID can not actually
be used until a gid mapping is established.  Therefore add a helper function
to see if the user namespace gid mapping has been established and call
that function in the setgroups permission check.

This is part of the fix for CVE-2014-8989, being able to drop groups
without privilege using user namespaces.

Cc: stable@vger.kernel.org
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/user_namespace.h |  5 +++++
 kernel/groups.c                |  4 +++-
 kernel/user_namespace.c        | 14 ++++++++++++++
 3 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index e95372654f0..8d493083486 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -63,6 +63,7 @@ extern const struct seq_operations proc_projid_seq_operations;
 extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *);
+extern bool userns_may_setgroups(const struct user_namespace *ns);
 #else
 
 static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
@@ -87,6 +88,10 @@ static inline void put_user_ns(struct user_namespace *ns)
 {
 }
 
+static inline bool userns_may_setgroups(const struct user_namespace *ns)
+{
+	return true;
+}
 #endif
 
 #endif /* _LINUX_USER_H */
diff --git a/kernel/groups.c b/kernel/groups.c
index 02d8a251c47..664411f171b 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
+#include <linux/user_namespace.h>
 #include <asm/uaccess.h>
 
 /* init to 2 - one for init_task, one to ensure it is never freed */
@@ -217,7 +218,8 @@ bool may_setgroups(void)
 {
 	struct user_namespace *user_ns = current_user_ns();
 
-	return ns_capable(user_ns, CAP_SETGID);
+	return ns_capable(user_ns, CAP_SETGID) &&
+		userns_may_setgroups(user_ns);
 }
 
 /*
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index b99c862a2e3..27c8dab48c0 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -843,6 +843,20 @@ static bool new_idmap_permitted(const struct file *file,
 	return false;
 }
 
+bool userns_may_setgroups(const struct user_namespace *ns)
+{
+	bool allowed;
+
+	mutex_lock(&id_map_mutex);
+	/* It is not safe to use setgroups until a gid mapping in
+	 * the user namespace has been established.
+	 */
+	allowed = ns->gid_map.nr_extents != 0;
+	mutex_unlock(&id_map_mutex);
+
+	return allowed;
+}
+
 static void *userns_get(struct task_struct *task)
 {
 	struct user_namespace *user_ns;
-- 
cgit v1.2.3-70-g09d2


From fc0bdbbc67c9f7307d41f415abb1165778fe803f Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Mon, 8 Dec 2014 14:04:19 -0800
Subject: bridge: new mode flag to indicate mode 'undefined'

This patch adds mode BRIDGE_MODE_UNDEF for cases where mode is not needed.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 296a556454e..05f08695c6c 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -106,6 +106,7 @@ struct __fdb_entry {
 #define BRIDGE_MODE_VEB		0	/* Default loopback mode */
 #define BRIDGE_MODE_VEPA	1	/* 802.1Qbg defined VEPA mode */
 #define BRIDGE_MODE_SWDEV	2	/* Full switch device offload */
+#define BRIDGE_MODE_UNDEF	0xFFFF  /* mode undefined */
 
 /* Bridge management nested attributes
  * [IFLA_AF_SPEC] = {
-- 
cgit v1.2.3-70-g09d2


From 4a5fdfe8b3669070112105573f2d7c487ec7ad0d Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Mon, 8 Dec 2014 14:04:21 -0800
Subject: bridge: remove mode BRIDGE_MODE_SWDEV

This patch removes bridge mode swdev.
Users can use BRIDGE_FLAGS_SELF to indicate swdev offload
if needed.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 05f08695c6c..b03ee8f62d3 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -105,7 +105,6 @@ struct __fdb_entry {
 
 #define BRIDGE_MODE_VEB		0	/* Default loopback mode */
 #define BRIDGE_MODE_VEPA	1	/* 802.1Qbg defined VEPA mode */
-#define BRIDGE_MODE_SWDEV	2	/* Full switch device offload */
 #define BRIDGE_MODE_UNDEF	0xFFFF  /* mode undefined */
 
 /* Bridge management nested attributes
-- 
cgit v1.2.3-70-g09d2


From 8985f4ac1c42bd25799f294f4e87fa73064673c7 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Tue, 9 Dec 2014 00:10:49 +0900
Subject: ALSA: oxfw: Add hwdep interface

This interface is designed for mixer/control application. By using this
interface, an application can get information about firewire node, can
lock/unlock kernel streaming and can get notification at starting/stopping
kernel streaming.

Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Acked-by: Clemens Ladisch <clemens@ladisch.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/uapi/sound/asound.h       |   3 +-
 include/uapi/sound/firewire.h     |   3 +-
 sound/firewire/Kconfig            |   1 +
 sound/firewire/oxfw/Makefile      |   2 +-
 sound/firewire/oxfw/oxfw-hwdep.c  | 190 ++++++++++++++++++++++++++++++++++++++
 sound/firewire/oxfw/oxfw-midi.c   |  16 ++++
 sound/firewire/oxfw/oxfw-pcm.c    |  12 ++-
 sound/firewire/oxfw/oxfw-stream.c |  39 ++++++++
 sound/firewire/oxfw/oxfw.c        |   5 +
 sound/firewire/oxfw/oxfw.h        |  13 +++
 10 files changed, 280 insertions(+), 4 deletions(-)
 create mode 100644 sound/firewire/oxfw/oxfw-hwdep.c

(limited to 'include')

diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index 941d32f007d..1f23cd63595 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -96,9 +96,10 @@ enum {
 	SNDRV_HWDEP_IFACE_FW_DICE,	/* TC DICE FireWire device */
 	SNDRV_HWDEP_IFACE_FW_FIREWORKS,	/* Echo Audio Fireworks based device */
 	SNDRV_HWDEP_IFACE_FW_BEBOB,	/* BridgeCo BeBoB based device */
+	SNDRV_HWDEP_IFACE_FW_OXFW,	/* Oxford OXFW970/971 based device */
 
 	/* Don't forget to change the following: */
-	SNDRV_HWDEP_IFACE_LAST = SNDRV_HWDEP_IFACE_FW_BEBOB
+	SNDRV_HWDEP_IFACE_LAST = SNDRV_HWDEP_IFACE_FW_OXFW
 };
 
 struct snd_hwdep_info {
diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h
index af4bd136c75..49122df3b56 100644
--- a/include/uapi/sound/firewire.h
+++ b/include/uapi/sound/firewire.h
@@ -55,7 +55,8 @@ union snd_firewire_event {
 #define SNDRV_FIREWIRE_TYPE_DICE	1
 #define SNDRV_FIREWIRE_TYPE_FIREWORKS	2
 #define SNDRV_FIREWIRE_TYPE_BEBOB	3
-/* AV/C, RME, MOTU, ... */
+#define SNDRV_FIREWIRE_TYPE_OXFW	4
+/* RME, MOTU, ... */
 
 struct snd_firewire_get_info {
 	unsigned int type; /* SNDRV_FIREWIRE_TYPE_xxx */
diff --git a/sound/firewire/Kconfig b/sound/firewire/Kconfig
index 6364e5b90a0..ecec547782b 100644
--- a/sound/firewire/Kconfig
+++ b/sound/firewire/Kconfig
@@ -26,6 +26,7 @@ config SND_DICE
 config SND_OXFW
 	tristate "Oxford Semiconductor FW970/971 chipset support"
 	select SND_FIREWIRE_LIB
+	select SND_HWDEP
 	help
 	  Say Y here to include support for FireWire devices based on
 	  Oxford Semiconductor FW970/971 chipset.
diff --git a/sound/firewire/oxfw/Makefile b/sound/firewire/oxfw/Makefile
index 3904a302d48..a926850864f 100644
--- a/sound/firewire/oxfw/Makefile
+++ b/sound/firewire/oxfw/Makefile
@@ -1,3 +1,3 @@
 snd-oxfw-objs := oxfw-command.o oxfw-stream.o oxfw-control.o oxfw-pcm.o \
-		 oxfw-proc.o oxfw-midi.o oxfw.o
+		 oxfw-proc.o oxfw-midi.o oxfw-hwdep.o oxfw.o
 obj-m += snd-oxfw.o
diff --git a/sound/firewire/oxfw/oxfw-hwdep.c b/sound/firewire/oxfw/oxfw-hwdep.c
new file mode 100644
index 00000000000..ff2687ad046
--- /dev/null
+++ b/sound/firewire/oxfw/oxfw-hwdep.c
@@ -0,0 +1,190 @@
+/*
+ * oxfw_hwdep.c - a part of driver for OXFW970/971 based devices
+ *
+ * Copyright (c) 2014 Takashi Sakamoto
+ *
+ * Licensed under the terms of the GNU General Public License, version 2.
+ */
+
+/*
+ * This codes give three functionality.
+ *
+ * 1.get firewire node information
+ * 2.get notification about starting/stopping stream
+ * 3.lock/unlock stream
+ */
+
+#include "oxfw.h"
+
+static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf,  long count,
+		       loff_t *offset)
+{
+	struct snd_oxfw *oxfw = hwdep->private_data;
+	DEFINE_WAIT(wait);
+	union snd_firewire_event event;
+
+	spin_lock_irq(&oxfw->lock);
+
+	while (!oxfw->dev_lock_changed) {
+		prepare_to_wait(&oxfw->hwdep_wait, &wait, TASK_INTERRUPTIBLE);
+		spin_unlock_irq(&oxfw->lock);
+		schedule();
+		finish_wait(&oxfw->hwdep_wait, &wait);
+		if (signal_pending(current))
+			return -ERESTARTSYS;
+		spin_lock_irq(&oxfw->lock);
+	}
+
+	memset(&event, 0, sizeof(event));
+	if (oxfw->dev_lock_changed) {
+		event.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS;
+		event.lock_status.status = (oxfw->dev_lock_count > 0);
+		oxfw->dev_lock_changed = false;
+
+		count = min_t(long, count, sizeof(event.lock_status));
+	}
+
+	spin_unlock_irq(&oxfw->lock);
+
+	if (copy_to_user(buf, &event, count))
+		return -EFAULT;
+
+	return count;
+}
+
+static unsigned int hwdep_poll(struct snd_hwdep *hwdep, struct file *file,
+			       poll_table *wait)
+{
+	struct snd_oxfw *oxfw = hwdep->private_data;
+	unsigned int events;
+
+	poll_wait(file, &oxfw->hwdep_wait, wait);
+
+	spin_lock_irq(&oxfw->lock);
+	if (oxfw->dev_lock_changed)
+		events = POLLIN | POLLRDNORM;
+	else
+		events = 0;
+	spin_unlock_irq(&oxfw->lock);
+
+	return events;
+}
+
+static int hwdep_get_info(struct snd_oxfw *oxfw, void __user *arg)
+{
+	struct fw_device *dev = fw_parent_device(oxfw->unit);
+	struct snd_firewire_get_info info;
+
+	memset(&info, 0, sizeof(info));
+	info.type = SNDRV_FIREWIRE_TYPE_OXFW;
+	info.card = dev->card->index;
+	*(__be32 *)&info.guid[0] = cpu_to_be32(dev->config_rom[3]);
+	*(__be32 *)&info.guid[4] = cpu_to_be32(dev->config_rom[4]);
+	strlcpy(info.device_name, dev_name(&dev->device),
+		sizeof(info.device_name));
+
+	if (copy_to_user(arg, &info, sizeof(info)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int hwdep_lock(struct snd_oxfw *oxfw)
+{
+	int err;
+
+	spin_lock_irq(&oxfw->lock);
+
+	if (oxfw->dev_lock_count == 0) {
+		oxfw->dev_lock_count = -1;
+		err = 0;
+	} else {
+		err = -EBUSY;
+	}
+
+	spin_unlock_irq(&oxfw->lock);
+
+	return err;
+}
+
+static int hwdep_unlock(struct snd_oxfw *oxfw)
+{
+	int err;
+
+	spin_lock_irq(&oxfw->lock);
+
+	if (oxfw->dev_lock_count == -1) {
+		oxfw->dev_lock_count = 0;
+		err = 0;
+	} else {
+		err = -EBADFD;
+	}
+
+	spin_unlock_irq(&oxfw->lock);
+
+	return err;
+}
+
+static int hwdep_release(struct snd_hwdep *hwdep, struct file *file)
+{
+	struct snd_oxfw *oxfw = hwdep->private_data;
+
+	spin_lock_irq(&oxfw->lock);
+	if (oxfw->dev_lock_count == -1)
+		oxfw->dev_lock_count = 0;
+	spin_unlock_irq(&oxfw->lock);
+
+	return 0;
+}
+
+static int hwdep_ioctl(struct snd_hwdep *hwdep, struct file *file,
+		       unsigned int cmd, unsigned long arg)
+{
+	struct snd_oxfw *oxfw = hwdep->private_data;
+
+	switch (cmd) {
+	case SNDRV_FIREWIRE_IOCTL_GET_INFO:
+		return hwdep_get_info(oxfw, (void __user *)arg);
+	case SNDRV_FIREWIRE_IOCTL_LOCK:
+		return hwdep_lock(oxfw);
+	case SNDRV_FIREWIRE_IOCTL_UNLOCK:
+		return hwdep_unlock(oxfw);
+	default:
+		return -ENOIOCTLCMD;
+	}
+}
+
+#ifdef CONFIG_COMPAT
+static int hwdep_compat_ioctl(struct snd_hwdep *hwdep, struct file *file,
+			      unsigned int cmd, unsigned long arg)
+{
+	return hwdep_ioctl(hwdep, file, cmd,
+			   (unsigned long)compat_ptr(arg));
+}
+#else
+#define hwdep_compat_ioctl NULL
+#endif
+
+int snd_oxfw_create_hwdep(struct snd_oxfw *oxfw)
+{
+	static const struct snd_hwdep_ops hwdep_ops = {
+		.read		= hwdep_read,
+		.release	= hwdep_release,
+		.poll		= hwdep_poll,
+		.ioctl		= hwdep_ioctl,
+		.ioctl_compat	= hwdep_compat_ioctl,
+	};
+	struct snd_hwdep *hwdep;
+	int err;
+
+	err = snd_hwdep_new(oxfw->card, oxfw->card->driver, 0, &hwdep);
+	if (err < 0)
+		goto end;
+	strcpy(hwdep->name, oxfw->card->driver);
+	hwdep->iface = SNDRV_HWDEP_IFACE_FW_OXFW;
+	hwdep->ops = hwdep_ops;
+	hwdep->private_data = oxfw;
+	hwdep->exclusive = true;
+end:
+	return err;
+}
diff --git a/sound/firewire/oxfw/oxfw-midi.c b/sound/firewire/oxfw/oxfw-midi.c
index 334b11d1a42..540a3033851 100644
--- a/sound/firewire/oxfw/oxfw-midi.c
+++ b/sound/firewire/oxfw/oxfw-midi.c
@@ -13,6 +13,10 @@ static int midi_capture_open(struct snd_rawmidi_substream *substream)
 	struct snd_oxfw *oxfw = substream->rmidi->private_data;
 	int err;
 
+	err = snd_oxfw_stream_lock_try(oxfw);
+	if (err < 0)
+		return err;
+
 	mutex_lock(&oxfw->mutex);
 
 	oxfw->capture_substreams++;
@@ -20,6 +24,9 @@ static int midi_capture_open(struct snd_rawmidi_substream *substream)
 
 	mutex_unlock(&oxfw->mutex);
 
+	if (err < 0)
+		snd_oxfw_stream_lock_release(oxfw);
+
 	return err;
 }
 
@@ -28,6 +35,10 @@ static int midi_playback_open(struct snd_rawmidi_substream *substream)
 	struct snd_oxfw *oxfw = substream->rmidi->private_data;
 	int err;
 
+	err = snd_oxfw_stream_lock_try(oxfw);
+	if (err < 0)
+		return err;
+
 	mutex_lock(&oxfw->mutex);
 
 	oxfw->playback_substreams++;
@@ -35,6 +46,9 @@ static int midi_playback_open(struct snd_rawmidi_substream *substream)
 
 	mutex_unlock(&oxfw->mutex);
 
+	if (err < 0)
+		snd_oxfw_stream_lock_release(oxfw);
+
 	return err;
 }
 
@@ -49,6 +63,7 @@ static int midi_capture_close(struct snd_rawmidi_substream *substream)
 
 	mutex_unlock(&oxfw->mutex);
 
+	snd_oxfw_stream_lock_release(oxfw);
 	return 0;
 }
 
@@ -63,6 +78,7 @@ static int midi_playback_close(struct snd_rawmidi_substream *substream)
 
 	mutex_unlock(&oxfw->mutex);
 
+	snd_oxfw_stream_lock_release(oxfw);
 	return 0;
 }
 
diff --git a/sound/firewire/oxfw/oxfw-pcm.c b/sound/firewire/oxfw/oxfw-pcm.c
index e84fc9c4bfd..9bc556b15a9 100644
--- a/sound/firewire/oxfw/oxfw-pcm.c
+++ b/sound/firewire/oxfw/oxfw-pcm.c
@@ -192,10 +192,14 @@ static int pcm_open(struct snd_pcm_substream *substream)
 	struct snd_oxfw *oxfw = substream->private_data;
 	int err;
 
-	err = init_hw_params(oxfw, substream);
+	err = snd_oxfw_stream_lock_try(oxfw);
 	if (err < 0)
 		goto end;
 
+	err = init_hw_params(oxfw, substream);
+	if (err < 0)
+		goto err_locked;
+
 	/*
 	 * When any PCM streams are already running, the available sampling
 	 * rate is limited at current value.
@@ -210,10 +214,16 @@ static int pcm_open(struct snd_pcm_substream *substream)
 	snd_pcm_set_sync(substream);
 end:
 	return err;
+err_locked:
+	snd_oxfw_stream_lock_release(oxfw);
+	return err;
 }
 
 static int pcm_close(struct snd_pcm_substream *substream)
 {
+	struct snd_oxfw *oxfw = substream->private_data;
+
+	snd_oxfw_stream_lock_release(oxfw);
 	return 0;
 }
 
diff --git a/sound/firewire/oxfw/oxfw-stream.c b/sound/firewire/oxfw/oxfw-stream.c
index a38b3c36fac..b77cf80f167 100644
--- a/sound/firewire/oxfw/oxfw-stream.c
+++ b/sound/firewire/oxfw/oxfw-stream.c
@@ -644,3 +644,42 @@ int snd_oxfw_stream_discover(struct snd_oxfw *oxfw)
 end:
 	return err;
 }
+
+void snd_oxfw_stream_lock_changed(struct snd_oxfw *oxfw)
+{
+	oxfw->dev_lock_changed = true;
+	wake_up(&oxfw->hwdep_wait);
+}
+
+int snd_oxfw_stream_lock_try(struct snd_oxfw *oxfw)
+{
+	int err;
+
+	spin_lock_irq(&oxfw->lock);
+
+	/* user land lock this */
+	if (oxfw->dev_lock_count < 0) {
+		err = -EBUSY;
+		goto end;
+	}
+
+	/* this is the first time */
+	if (oxfw->dev_lock_count++ == 0)
+		snd_oxfw_stream_lock_changed(oxfw);
+	err = 0;
+end:
+	spin_unlock_irq(&oxfw->lock);
+	return err;
+}
+
+void snd_oxfw_stream_lock_release(struct snd_oxfw *oxfw)
+{
+	spin_lock_irq(&oxfw->lock);
+
+	if (WARN_ON(oxfw->dev_lock_count <= 0))
+		goto end;
+	if (--oxfw->dev_lock_count == 0)
+		snd_oxfw_stream_lock_changed(oxfw);
+end:
+	spin_unlock_irq(&oxfw->lock);
+}
diff --git a/sound/firewire/oxfw/oxfw.c b/sound/firewire/oxfw/oxfw.c
index 9cfbfb168da..cf1d0b55e82 100644
--- a/sound/firewire/oxfw/oxfw.c
+++ b/sound/firewire/oxfw/oxfw.c
@@ -139,6 +139,7 @@ static int oxfw_probe(struct fw_unit *unit,
 	oxfw->unit = unit;
 	oxfw->device_info = (const struct device_info *)id->driver_data;
 	spin_lock_init(&oxfw->lock);
+	init_waitqueue_head(&oxfw->hwdep_wait);
 
 	err = snd_oxfw_stream_discover(oxfw);
 	if (err < 0)
@@ -164,6 +165,10 @@ static int oxfw_probe(struct fw_unit *unit,
 	if (err < 0)
 		goto error;
 
+	err = snd_oxfw_create_hwdep(oxfw);
+	if (err < 0)
+		goto error;
+
 	err = snd_oxfw_stream_init_simplex(oxfw, &oxfw->rx_stream);
 	if (err < 0)
 		goto error;
diff --git a/sound/firewire/oxfw/oxfw.h b/sound/firewire/oxfw/oxfw.h
index 83a54fc73a1..cace5ad4fe7 100644
--- a/sound/firewire/oxfw/oxfw.h
+++ b/sound/firewire/oxfw/oxfw.h
@@ -12,6 +12,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/compat.h>
 
 #include <sound/control.h>
 #include <sound/core.h>
@@ -20,6 +21,8 @@
 #include <sound/pcm_params.h>
 #include <sound/info.h>
 #include <sound/rawmidi.h>
+#include <sound/firewire.h>
+#include <sound/hwdep.h>
 
 #include "../lib.h"
 #include "../fcp.h"
@@ -64,6 +67,10 @@ struct snd_oxfw {
 	s16 volume[6];
 	s16 volume_min;
 	s16 volume_max;
+
+	int dev_lock_count;
+	bool dev_lock_changed;
+	wait_queue_head_t hwdep_wait;
 };
 
 /*
@@ -124,6 +131,10 @@ int snd_oxfw_stream_get_current_formation(struct snd_oxfw *oxfw,
 
 int snd_oxfw_stream_discover(struct snd_oxfw *oxfw);
 
+void snd_oxfw_stream_lock_changed(struct snd_oxfw *oxfw);
+int snd_oxfw_stream_lock_try(struct snd_oxfw *oxfw);
+void snd_oxfw_stream_lock_release(struct snd_oxfw *oxfw);
+
 int snd_oxfw_create_pcm(struct snd_oxfw *oxfw);
 
 int snd_oxfw_create_mixer(struct snd_oxfw *oxfw);
@@ -131,3 +142,5 @@ int snd_oxfw_create_mixer(struct snd_oxfw *oxfw);
 void snd_oxfw_proc_init(struct snd_oxfw *oxfw);
 
 int snd_oxfw_create_midi(struct snd_oxfw *oxfw);
+
+int snd_oxfw_create_hwdep(struct snd_oxfw *oxfw);
-- 
cgit v1.2.3-70-g09d2


From a940cb34fed73b2d4809a4575f2981d5927e2c21 Mon Sep 17 00:00:00 2001
From: Punit Agrawal <punit.agrawal@arm.com>
Date: Tue, 9 Dec 2014 12:22:01 +0000
Subject: thermal: Fix cdev registration with THERMAL_NO_LIMIT on 64bit

The size of unsigned long varies between 32 and 64 bit systems while
the size of phandle arguments is always 32 bits per parameter.

On 64-bit systems, cooling devices registered via of-thermal apis fail
to bind when the min/max cooling state is specified as
THERMAL_NO_LIMIT (-1UL) as there is a mis-match between the value read
from the device tree (32bit) and the pre-processor define (64bit).

As we're unlikely to need cooling states larger than 32 bits, and for
consistency with the size of phandle arguments, explicitly limit
THERMAL_NO_LIMIT to 32 bits.

Reported-by: Hyungwoo Yang <hwoo.yang@gmail.com>
Acked-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 include/dt-bindings/thermal/thermal.h | 2 +-
 include/linux/thermal.h               | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/dt-bindings/thermal/thermal.h b/include/dt-bindings/thermal/thermal.h
index 59822a99585..b5e6b0069ac 100644
--- a/include/dt-bindings/thermal/thermal.h
+++ b/include/dt-bindings/thermal/thermal.h
@@ -11,7 +11,7 @@
 #define _DT_BINDINGS_THERMAL_THERMAL_H
 
 /* On cooling devices upper and lower limits */
-#define THERMAL_NO_LIMIT		(-1UL)
+#define THERMAL_NO_LIMIT		(~0)
 
 #endif
 
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index ef90838b36a..005586fdf82 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -38,7 +38,7 @@
 #define THERMAL_CSTATE_INVALID -1UL
 
 /* No upper/lower limit requirement */
-#define THERMAL_NO_LIMIT	THERMAL_CSTATE_INVALID
+#define THERMAL_NO_LIMIT	((u32)~0)
 
 /* Unit conversion macros */
 #define KELVIN_TO_CELSIUS(t)	(long)(((long)t-2732 >= 0) ?	\
-- 
cgit v1.2.3-70-g09d2


From ffde7328a36d16e626bae8468571858d71cd010b Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@redhat.com>
Date: Tue, 9 Dec 2014 19:40:42 -0800
Subject: net: Split netdev_alloc_frag into __alloc_page_frag and add
 __napi_alloc_frag

This patch splits the netdev_alloc_frag function up so that it can be used
on one of two page frag pools instead of being fixed on the
netdev_alloc_cache.  By doing this we can add a NAPI specific function
__napi_alloc_frag that accesses a pool that is only used from softirq
context.  The advantage to this is that we do not need to call
local_irq_save/restore which can be a significant savings.

I also took the opportunity to refactor the core bits that were placed in
__alloc_page_frag.  First I updated the allocation to do either a 32K
allocation or an order 0 page.  This is based on the changes in commmit
d9b2938aa where it was found that latencies could be reduced in case of
failures.  Then I also rewrote the logic to work from the end of the page to
the start.  By doing this the size value doesn't have to be used unless we
have run out of space for page fragments.  Finally I cleaned up the atomic
bits so that we just do an atomic_sub_and_test and if that returns true then
we set the page->_count via an atomic_set.  This way we can remove the extra
conditional for the atomic_read since it would have led to an atomic_inc in
the case of success anyway.

Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |   2 +
 net/core/skbuff.c      | 117 ++++++++++++++++++++++++++++++++-----------------
 2 files changed, 79 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ab0bc43c82a..736cc99f3f6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2164,6 +2164,8 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
 	return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC);
 }
 
+void *napi_alloc_frag(unsigned int fragsz);
+
 /**
  * __dev_alloc_pages - allocate page for network Rx
  * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7a338fb55cc..56ed17cd215 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -336,59 +336,85 @@ struct netdev_alloc_cache {
 	unsigned int		pagecnt_bias;
 };
 static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache);
+static DEFINE_PER_CPU(struct netdev_alloc_cache, napi_alloc_cache);
 
-static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
+static struct page *__page_frag_refill(struct netdev_alloc_cache *nc,
+				       gfp_t gfp_mask)
 {
-	struct netdev_alloc_cache *nc;
-	void *data = NULL;
-	int order;
-	unsigned long flags;
+	const unsigned int order = NETDEV_FRAG_PAGE_MAX_ORDER;
+	struct page *page = NULL;
+	gfp_t gfp = gfp_mask;
+
+	if (order) {
+		gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
+		page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
+		nc->frag.size = PAGE_SIZE << (page ? order : 0);
+	}
 
-	local_irq_save(flags);
-	nc = this_cpu_ptr(&netdev_alloc_cache);
-	if (unlikely(!nc->frag.page)) {
+	if (unlikely(!page))
+		page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
+
+	nc->frag.page = page;
+
+	return page;
+}
+
+static void *__alloc_page_frag(struct netdev_alloc_cache __percpu *cache,
+			       unsigned int fragsz, gfp_t gfp_mask)
+{
+	struct netdev_alloc_cache *nc = this_cpu_ptr(cache);
+	struct page *page = nc->frag.page;
+	unsigned int size;
+	int offset;
+
+	if (unlikely(!page)) {
 refill:
-		for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) {
-			gfp_t gfp = gfp_mask;
+		page = __page_frag_refill(nc, gfp_mask);
+		if (!page)
+			return NULL;
+
+		/* if size can vary use frag.size else just use PAGE_SIZE */
+		size = NETDEV_FRAG_PAGE_MAX_ORDER ? nc->frag.size : PAGE_SIZE;
 
-			if (order)
-				gfp |= __GFP_COMP | __GFP_NOWARN;
-			nc->frag.page = alloc_pages(gfp, order);
-			if (likely(nc->frag.page))
-				break;
-			if (--order < 0)
-				goto end;
-		}
-		nc->frag.size = PAGE_SIZE << order;
 		/* Even if we own the page, we do not use atomic_set().
 		 * This would break get_page_unless_zero() users.
 		 */
-		atomic_add(NETDEV_PAGECNT_MAX_BIAS - 1,
-			   &nc->frag.page->_count);
-		nc->pagecnt_bias = NETDEV_PAGECNT_MAX_BIAS;
-		nc->frag.offset = 0;
+		atomic_add(size - 1, &page->_count);
+
+		/* reset page count bias and offset to start of new frag */
+		nc->pagecnt_bias = size;
+		nc->frag.offset = size;
 	}
 
-	if (nc->frag.offset + fragsz > nc->frag.size) {
-		if (atomic_read(&nc->frag.page->_count) != nc->pagecnt_bias) {
-			if (!atomic_sub_and_test(nc->pagecnt_bias,
-						 &nc->frag.page->_count))
-				goto refill;
-			/* OK, page count is 0, we can safely set it */
-			atomic_set(&nc->frag.page->_count,
-				   NETDEV_PAGECNT_MAX_BIAS);
-		} else {
-			atomic_add(NETDEV_PAGECNT_MAX_BIAS - nc->pagecnt_bias,
-				   &nc->frag.page->_count);
-		}
-		nc->pagecnt_bias = NETDEV_PAGECNT_MAX_BIAS;
-		nc->frag.offset = 0;
+	offset = nc->frag.offset - fragsz;
+	if (unlikely(offset < 0)) {
+		if (!atomic_sub_and_test(nc->pagecnt_bias, &page->_count))
+			goto refill;
+
+		/* if size can vary use frag.size else just use PAGE_SIZE */
+		size = NETDEV_FRAG_PAGE_MAX_ORDER ? nc->frag.size : PAGE_SIZE;
+
+		/* OK, page count is 0, we can safely set it */
+		atomic_set(&page->_count, size);
+
+		/* reset page count bias and offset to start of new frag */
+		nc->pagecnt_bias = size;
+		offset = size - fragsz;
 	}
 
-	data = page_address(nc->frag.page) + nc->frag.offset;
-	nc->frag.offset += fragsz;
 	nc->pagecnt_bias--;
-end:
+	nc->frag.offset = offset;
+
+	return page_address(page) + offset;
+}
+
+static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
+{
+	unsigned long flags;
+	void *data;
+
+	local_irq_save(flags);
+	data = __alloc_page_frag(&netdev_alloc_cache, fragsz, gfp_mask);
 	local_irq_restore(flags);
 	return data;
 }
@@ -406,6 +432,17 @@ void *netdev_alloc_frag(unsigned int fragsz)
 }
 EXPORT_SYMBOL(netdev_alloc_frag);
 
+static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
+{
+	return __alloc_page_frag(&napi_alloc_cache, fragsz, gfp_mask);
+}
+
+void *napi_alloc_frag(unsigned int fragsz)
+{
+	return __napi_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
+}
+EXPORT_SYMBOL(napi_alloc_frag);
+
 /**
  *	__netdev_alloc_skb - allocate an skbuff for rx on a specific device
  *	@dev: network device to receive on
-- 
cgit v1.2.3-70-g09d2


From fd11a83dd3630ec6a60f8a702446532c5c7e1991 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@redhat.com>
Date: Tue, 9 Dec 2014 19:40:49 -0800
Subject: net: Pull out core bits of __netdev_alloc_skb and add
 __napi_alloc_skb

This change pulls the core functionality out of __netdev_alloc_skb and
places them in a new function named __alloc_rx_skb.  The reason for doing
this is to make these bits accessible to a new function __napi_alloc_skb.
In addition __alloc_rx_skb now has a new flags value that is used to
determine which page frag pool to allocate from.  If the SKB_ALLOC_NAPI
flag is set then the NAPI pool is used.  The advantage of this is that we
do not have to use local_irq_save/restore when accessing the NAPI pool from
NAPI context.

In my test setup I saw at least 11ns of savings using the napi_alloc_skb
function versus the netdev_alloc_skb function, most of this being due to
the fact that we didn't have to call local_irq_save/restore.

The main use case for napi_alloc_skb would be for things such as copybreak
or page fragment based receive paths where an skb is allocated after the
data has been received instead of before.

Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  9 ++++++
 net/core/dev.c         |  2 +-
 net/core/skbuff.c      | 74 +++++++++++++++++++++++++++++++++++++++++++++-----
 3 files changed, 77 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 736cc99f3f6..85ab7d72b54 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -151,6 +151,7 @@ struct net_device;
 struct scatterlist;
 struct pipe_inode_info;
 struct iov_iter;
+struct napi_struct;
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 struct nf_conntrack {
@@ -673,6 +674,7 @@ struct sk_buff {
 
 #define SKB_ALLOC_FCLONE	0x01
 #define SKB_ALLOC_RX		0x02
+#define SKB_ALLOC_NAPI		0x04
 
 /* Returns true if the skb was allocated from PFMEMALLOC reserves */
 static inline bool skb_pfmemalloc(const struct sk_buff *skb)
@@ -2165,6 +2167,13 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
 }
 
 void *napi_alloc_frag(unsigned int fragsz);
+struct sk_buff *__napi_alloc_skb(struct napi_struct *napi,
+				 unsigned int length, gfp_t gfp_mask);
+static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi,
+					     unsigned int length)
+{
+	return __napi_alloc_skb(napi, length, GFP_ATOMIC);
+}
 
 /**
  * __dev_alloc_pages - allocate page for network Rx
diff --git a/net/core/dev.c b/net/core/dev.c
index 3f191da383f..80f798da3d9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4172,7 +4172,7 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
 	struct sk_buff *skb = napi->skb;
 
 	if (!skb) {
-		skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD);
+		skb = napi_alloc_skb(napi, GRO_MAX_HEAD);
 		napi->skb = skb;
 	}
 	return skb;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 56ed17cd215..ae13ef6b3ea 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -444,10 +444,13 @@ void *napi_alloc_frag(unsigned int fragsz)
 EXPORT_SYMBOL(napi_alloc_frag);
 
 /**
- *	__netdev_alloc_skb - allocate an skbuff for rx on a specific device
- *	@dev: network device to receive on
+ *	__alloc_rx_skb - allocate an skbuff for rx
  *	@length: length to allocate
  *	@gfp_mask: get_free_pages mask, passed to alloc_skb
+ *	@flags:	If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for
+ *		allocations in case we have to fallback to __alloc_skb()
+ *		If SKB_ALLOC_NAPI is set, page fragment will be allocated
+ *		from napi_cache instead of netdev_cache.
  *
  *	Allocate a new &sk_buff and assign it a usage count of one. The
  *	buffer has unspecified headroom built in. Users should allocate
@@ -456,11 +459,11 @@ EXPORT_SYMBOL(napi_alloc_frag);
  *
  *	%NULL is returned if there is no free memory.
  */
-struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
-				   unsigned int length, gfp_t gfp_mask)
+static struct sk_buff *__alloc_rx_skb(unsigned int length, gfp_t gfp_mask,
+				      int flags)
 {
 	struct sk_buff *skb = NULL;
-	unsigned int fragsz = SKB_DATA_ALIGN(length + NET_SKB_PAD) +
+	unsigned int fragsz = SKB_DATA_ALIGN(length) +
 			      SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) {
@@ -469,7 +472,9 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
 		if (sk_memalloc_socks())
 			gfp_mask |= __GFP_MEMALLOC;
 
-		data = __netdev_alloc_frag(fragsz, gfp_mask);
+		data = (flags & SKB_ALLOC_NAPI) ?
+			__napi_alloc_frag(fragsz, gfp_mask) :
+			__netdev_alloc_frag(fragsz, gfp_mask);
 
 		if (likely(data)) {
 			skb = build_skb(data, fragsz);
@@ -477,17 +482,72 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
 				put_page(virt_to_head_page(data));
 		}
 	} else {
-		skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask,
+		skb = __alloc_skb(length, gfp_mask,
 				  SKB_ALLOC_RX, NUMA_NO_NODE);
 	}
+	return skb;
+}
+
+/**
+ *	__netdev_alloc_skb - allocate an skbuff for rx on a specific device
+ *	@dev: network device to receive on
+ *	@length: length to allocate
+ *	@gfp_mask: get_free_pages mask, passed to alloc_skb
+ *
+ *	Allocate a new &sk_buff and assign it a usage count of one. The
+ *	buffer has NET_SKB_PAD headroom built in. Users should allocate
+ *	the headroom they think they need without accounting for the
+ *	built in space. The built in space is used for optimisations.
+ *
+ *	%NULL is returned if there is no free memory.
+ */
+struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
+				   unsigned int length, gfp_t gfp_mask)
+{
+	struct sk_buff *skb;
+
+	length += NET_SKB_PAD;
+	skb = __alloc_rx_skb(length, gfp_mask, 0);
+
 	if (likely(skb)) {
 		skb_reserve(skb, NET_SKB_PAD);
 		skb->dev = dev;
 	}
+
 	return skb;
 }
 EXPORT_SYMBOL(__netdev_alloc_skb);
 
+/**
+ *	__napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance
+ *	@napi: napi instance this buffer was allocated for
+ *	@length: length to allocate
+ *	@gfp_mask: get_free_pages mask, passed to alloc_skb and alloc_pages
+ *
+ *	Allocate a new sk_buff for use in NAPI receive.  This buffer will
+ *	attempt to allocate the head from a special reserved region used
+ *	only for NAPI Rx allocation.  By doing this we can save several
+ *	CPU cycles by avoiding having to disable and re-enable IRQs.
+ *
+ *	%NULL is returned if there is no free memory.
+ */
+struct sk_buff *__napi_alloc_skb(struct napi_struct *napi,
+				 unsigned int length, gfp_t gfp_mask)
+{
+	struct sk_buff *skb;
+
+	length += NET_SKB_PAD + NET_IP_ALIGN;
+	skb = __alloc_rx_skb(length, gfp_mask, SKB_ALLOC_NAPI);
+
+	if (likely(skb)) {
+		skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
+		skb->dev = napi->dev;
+	}
+
+	return skb;
+}
+EXPORT_SYMBOL(__napi_alloc_skb);
+
 void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
 		     int size, unsigned int truesize)
 {
-- 
cgit v1.2.3-70-g09d2


From 0cb6c969ed9de43687abdfc63714b6fe4385d2fc Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Wed, 10 Dec 2014 16:33:12 +0100
Subject: net, lib: kill arch_fast_hash library bits

As there are now no remaining users of arch_fast_hash(), lets kill
it entirely.

This basically reverts commit 71ae8aac3e19 ("lib: introduce arch
optimized hash library") and follow-up work, that is f.e., commit
237217546d44 ("lib: hash: follow-up fixups for arch hash"),
commit e3fec2f74f7f ("lib: Add missing arch generic-y entries for
asm-generic/hash.h") and last but not least commit 6a02652df511
("perf tools: Fix include for non x86 architectures").

Cc: Francesco Fusco <fusco@ntop.org>
Cc: Thomas Graf <tgraf@suug.ch>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/alpha/include/asm/Kbuild      |  1 -
 arch/arc/include/asm/Kbuild        |  1 -
 arch/arm/include/asm/Kbuild        |  1 -
 arch/arm64/include/asm/Kbuild      |  1 -
 arch/avr32/include/asm/Kbuild      |  1 -
 arch/blackfin/include/asm/Kbuild   |  1 -
 arch/c6x/include/asm/Kbuild        |  1 -
 arch/cris/include/asm/Kbuild       |  1 -
 arch/frv/include/asm/Kbuild        |  1 -
 arch/hexagon/include/asm/Kbuild    |  1 -
 arch/ia64/include/asm/Kbuild       |  1 -
 arch/m32r/include/asm/Kbuild       |  1 -
 arch/m68k/include/asm/Kbuild       |  1 -
 arch/metag/include/asm/Kbuild      |  1 -
 arch/microblaze/include/asm/Kbuild |  1 -
 arch/mips/include/asm/Kbuild       |  1 -
 arch/mn10300/include/asm/Kbuild    |  1 -
 arch/openrisc/include/asm/Kbuild   |  1 -
 arch/parisc/include/asm/Kbuild     |  1 -
 arch/powerpc/include/asm/Kbuild    |  1 -
 arch/s390/include/asm/Kbuild       |  1 -
 arch/score/include/asm/Kbuild      |  1 -
 arch/sh/include/asm/Kbuild         |  1 -
 arch/sparc/include/asm/Kbuild      |  1 -
 arch/tile/include/asm/Kbuild       |  1 -
 arch/um/include/asm/Kbuild         |  1 -
 arch/unicore32/include/asm/Kbuild  |  1 -
 arch/x86/include/asm/hash.h        |  7 ---
 arch/x86/lib/Makefile              |  2 +-
 arch/x86/lib/hash.c                | 92 --------------------------------------
 arch/xtensa/include/asm/Kbuild     |  1 -
 include/asm-generic/hash.h         |  9 ----
 include/linux/hash.h               | 35 ---------------
 lib/Makefile                       |  2 +-
 lib/hash.c                         | 39 ----------------
 tools/perf/util/include/asm/hash.h |  6 ---
 36 files changed, 2 insertions(+), 218 deletions(-)
 delete mode 100644 arch/x86/include/asm/hash.h
 delete mode 100644 arch/x86/lib/hash.c
 delete mode 100644 include/asm-generic/hash.h
 delete mode 100644 lib/hash.c
 delete mode 100644 tools/perf/util/include/asm/hash.h

(limited to 'include')

diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index 25b49725df0..76aeb8fa551 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -3,7 +3,6 @@
 generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
-generic-y += hash.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index b8fffc1a2ac..be0c39e76f7 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -12,7 +12,6 @@ generic-y += fb.h
 generic-y += fcntl.h
 generic-y += ftrace.h
 generic-y += hardirq.h
-generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 70cd84eb7fd..fe74c0d1e48 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -7,7 +7,6 @@ generic-y += current.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
-generic-y += hash.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index dc770bd4f5a..6b61091c7f4 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -14,7 +14,6 @@ generic-y += early_ioremap.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += ftrace.h
-generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index 2a71b1cb984..528d70d47a5 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -7,7 +7,6 @@ generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += futex.h
-generic-y += hash.h
 generic-y += irq_regs.h
 generic-y += irq_work.h
 generic-y += local.h
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 46ed6bb9c67..4bd3c3cfc9a 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -10,7 +10,6 @@ generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += fb.h
 generic-y += futex.h
-generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index e77e0c1dbe7..2de73391b81 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -15,7 +15,6 @@ generic-y += exec.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += futex.h
-generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += io.h
 generic-y += ioctl.h
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index 2ca489eaadd..d5f124832fd 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -7,7 +7,6 @@ generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
-generic-y += hash.h
 generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += linkage.h
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index 3caf05cabfc..e3f81b53578 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -2,7 +2,6 @@
 generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
-generic-y += hash.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 5f234a5a232..c7a99f860b4 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -16,7 +16,6 @@ generic-y += fb.h
 generic-y += fcntl.h
 generic-y += ftrace.h
 generic-y += hardirq.h
-generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index 747320be9d0..9b41b4bcc07 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -1,7 +1,6 @@
 
 generic-y += clkdev.h
 generic-y += exec.h
-generic-y += hash.h
 generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index 3796801d6e0..2edc793372f 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -2,7 +2,6 @@
 generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
-generic-y += hash.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += module.h
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index dbaf9f3065e..9b6c691874b 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -6,7 +6,6 @@ generic-y += device.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
-generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index 7b8111c8f93..0bf5d525b94 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -13,7 +13,6 @@ generic-y += fb.h
 generic-y += fcntl.h
 generic-y += futex.h
 generic-y += hardirq.h
-generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 448143b8cab..ab564a6db5c 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -4,7 +4,6 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += device.h
 generic-y += exec.h
-generic-y += hash.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 72e1cf1cab0..200efeac418 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -3,7 +3,6 @@ generic-y += cputime.h
 generic-y += current.h
 generic-y += dma-contiguous.h
 generic-y += emergency-restart.h
-generic-y += hash.h
 generic-y += irq_work.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index 54a062cb9f2..f892d9de47d 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -3,7 +3,6 @@ generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
-generic-y += hash.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 89b61d7dc79..91f1f360a7c 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -25,7 +25,6 @@ generic-y += fcntl.h
 generic-y += ftrace.h
 generic-y += futex.h
 generic-y += hardirq.h
-generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index ffb024b8423..8686237a3c3 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -7,7 +7,6 @@ generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += exec.h
-generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += irq_regs.h
 generic-y += irq_work.h
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 31e8f59aff3..382b28e364d 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -1,6 +1,5 @@
 
 generic-y += clkdev.h
-generic-y += hash.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 773f8667658..c631f98fd52 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -1,7 +1,6 @@
 
 
 generic-y += clkdev.h
-generic-y += hash.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index 46461c19f28..83ed116d414 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -5,7 +5,6 @@ header-y +=
 generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += cputime.h
-generic-y += hash.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 5a6c9acff0d..654ebb6bd5d 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -8,7 +8,6 @@ generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
 generic-y += fcntl.h
-generic-y += hash.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index f5f94ce1692..94f36e7086a 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -6,7 +6,6 @@ generic-y += cputime.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += exec.h
-generic-y += hash.h
 generic-y += irq_regs.h
 generic-y += irq_work.h
 generic-y += linkage.h
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index e6462b8a628..b4c488b6574 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -11,7 +11,6 @@ generic-y += errno.h
 generic-y += exec.h
 generic-y += fb.h
 generic-y += fcntl.h
-generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 244b12c8cb3..9176fa11d49 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -10,7 +10,6 @@ generic-y += exec.h
 generic-y += ftrace.h
 generic-y += futex.h
 generic-y += hardirq.h
-generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += io.h
 generic-y += irq_regs.h
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 5a2bb53faa4..3e0c19d0f4c 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -16,7 +16,6 @@ generic-y += fcntl.h
 generic-y += ftrace.h
 generic-y += futex.h
 generic-y += hardirq.h
-generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
diff --git a/arch/x86/include/asm/hash.h b/arch/x86/include/asm/hash.h
deleted file mode 100644
index e8c58f88b1d..00000000000
--- a/arch/x86/include/asm/hash.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _ASM_X86_HASH_H
-#define _ASM_X86_HASH_H
-
-struct fast_hash_ops;
-extern void setup_arch_fast_hash(struct fast_hash_ops *ops);
-
-#endif /* _ASM_X86_HASH_H */
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index db92793b7e2..1530afb07c8 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -23,7 +23,7 @@ lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
 
-obj-y += msr.o msr-reg.o msr-reg-export.o hash.o
+obj-y += msr.o msr-reg.o msr-reg-export.o
 
 ifeq ($(CONFIG_X86_32),y)
         obj-y += atomic64_32.o
diff --git a/arch/x86/lib/hash.c b/arch/x86/lib/hash.c
deleted file mode 100644
index ff4fa51a5b1..00000000000
--- a/arch/x86/lib/hash.c
+++ /dev/null
@@ -1,92 +0,0 @@
-/*
- * Some portions derived from code covered by the following notice:
- *
- * Copyright (c) 2010-2013 Intel Corporation. All rights reserved.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/hash.h>
-#include <linux/init.h>
-
-#include <asm/processor.h>
-#include <asm/cpufeature.h>
-#include <asm/hash.h>
-
-static inline u32 crc32_u32(u32 crc, u32 val)
-{
-#ifdef CONFIG_AS_CRC32
-	asm ("crc32l %1,%0\n" : "+r" (crc) : "rm" (val));
-#else
-	asm (".byte 0xf2, 0x0f, 0x38, 0xf1, 0xc1" : "+a" (crc) : "c" (val));
-#endif
-	return crc;
-}
-
-static u32 intel_crc4_2_hash(const void *data, u32 len, u32 seed)
-{
-	const u32 *p32 = (const u32 *) data;
-	u32 i, tmp = 0;
-
-	for (i = 0; i < len / 4; i++)
-		seed = crc32_u32(seed, *p32++);
-
-	switch (len & 3) {
-	case 3:
-		tmp |= *((const u8 *) p32 + 2) << 16;
-		/* fallthrough */
-	case 2:
-		tmp |= *((const u8 *) p32 + 1) << 8;
-		/* fallthrough */
-	case 1:
-		tmp |= *((const u8 *) p32);
-		seed = crc32_u32(seed, tmp);
-		break;
-	}
-
-	return seed;
-}
-
-static u32 intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed)
-{
-	const u32 *p32 = (const u32 *) data;
-	u32 i;
-
-	for (i = 0; i < len; i++)
-		seed = crc32_u32(seed, *p32++);
-
-	return seed;
-}
-
-void __init setup_arch_fast_hash(struct fast_hash_ops *ops)
-{
-	if (cpu_has_xmm4_2) {
-		ops->hash  = intel_crc4_2_hash;
-		ops->hash2 = intel_crc4_2_hash2;
-	}
-}
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 105d38922c4..86a9ab2e2ca 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -9,7 +9,6 @@ generic-y += errno.h
 generic-y += exec.h
 generic-y += fcntl.h
 generic-y += hardirq.h
-generic-y += hash.h
 generic-y += ioctl.h
 generic-y += irq_regs.h
 generic-y += irq_work.h
diff --git a/include/asm-generic/hash.h b/include/asm-generic/hash.h
deleted file mode 100644
index b6312843dbd..00000000000
--- a/include/asm-generic/hash.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __ASM_GENERIC_HASH_H
-#define __ASM_GENERIC_HASH_H
-
-struct fast_hash_ops;
-static inline void setup_arch_fast_hash(struct fast_hash_ops *ops)
-{
-}
-
-#endif /* __ASM_GENERIC_HASH_H */
diff --git a/include/linux/hash.h b/include/linux/hash.h
index d0494c39939..1afde47e152 100644
--- a/include/linux/hash.h
+++ b/include/linux/hash.h
@@ -15,7 +15,6 @@
  */
 
 #include <asm/types.h>
-#include <asm/hash.h>
 #include <linux/compiler.h>
 
 /* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */
@@ -84,38 +83,4 @@ static inline u32 hash32_ptr(const void *ptr)
 	return (u32)val;
 }
 
-struct fast_hash_ops {
-	u32 (*hash)(const void *data, u32 len, u32 seed);
-	u32 (*hash2)(const u32 *data, u32 len, u32 seed);
-};
-
-/**
- *	arch_fast_hash - Caclulates a hash over a given buffer that can have
- *			 arbitrary size. This function will eventually use an
- *			 architecture-optimized hashing implementation if
- *			 available, and trades off distribution for speed.
- *
- *	@data: buffer to hash
- *	@len: length of buffer in bytes
- *	@seed: start seed
- *
- *	Returns 32bit hash.
- */
-extern u32 arch_fast_hash(const void *data, u32 len, u32 seed);
-
-/**
- *	arch_fast_hash2 - Caclulates a hash over a given buffer that has a
- *			  size that is of a multiple of 32bit words. This
- *			  function will eventually use an architecture-
- *			  optimized hashing implementation if available,
- *			  and trades off distribution for speed.
- *
- *	@data: buffer to hash (must be 32bit padded)
- *	@len: number of 32bit words
- *	@seed: start seed
- *
- *	Returns 32bit hash.
- */
-extern u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed);
-
 #endif /* _LINUX_HASH_H */
diff --git a/lib/Makefile b/lib/Makefile
index 0211d2bd5e1..4b9baa45a4d 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -26,7 +26,7 @@ obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
 	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
 	 gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \
 	 bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
-	 percpu-refcount.o percpu_ida.o hash.o rhashtable.o reciprocal_div.o
+	 percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o
 obj-y += string_helpers.o
 obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
 obj-y += kstrtox.o
diff --git a/lib/hash.c b/lib/hash.c
deleted file mode 100644
index fea973f4bd5..00000000000
--- a/lib/hash.c
+++ /dev/null
@@ -1,39 +0,0 @@
-/* General purpose hashing library
- *
- * That's a start of a kernel hashing library, which can be extended
- * with further algorithms in future. arch_fast_hash{2,}() will
- * eventually resolve to an architecture optimized implementation.
- *
- * Copyright 2013 Francesco Fusco <ffusco@redhat.com>
- * Copyright 2013 Daniel Borkmann <dborkman@redhat.com>
- * Copyright 2013 Thomas Graf <tgraf@redhat.com>
- * Licensed under the GNU General Public License, version 2.0 (GPLv2)
- */
-
-#include <linux/jhash.h>
-#include <linux/hash.h>
-#include <linux/cache.h>
-
-static struct fast_hash_ops arch_hash_ops __read_mostly = {
-	.hash  = jhash,
-	.hash2 = jhash2,
-};
-
-u32 arch_fast_hash(const void *data, u32 len, u32 seed)
-{
-	return arch_hash_ops.hash(data, len, seed);
-}
-EXPORT_SYMBOL_GPL(arch_fast_hash);
-
-u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed)
-{
-	return arch_hash_ops.hash2(data, len, seed);
-}
-EXPORT_SYMBOL_GPL(arch_fast_hash2);
-
-static int __init hashlib_init(void)
-{
-	setup_arch_fast_hash(&arch_hash_ops);
-	return 0;
-}
-early_initcall(hashlib_init);
diff --git a/tools/perf/util/include/asm/hash.h b/tools/perf/util/include/asm/hash.h
deleted file mode 100644
index d82b170bb21..00000000000
--- a/tools/perf/util/include/asm/hash.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_GENERIC_HASH_H
-#define __ASM_GENERIC_HASH_H
-
-/* Stub */
-
-#endif /* __ASM_GENERIC_HASH_H */
-- 
cgit v1.2.3-70-g09d2


From 14b7d95fd2288524c71aac48f3f7309fa6afa853 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 10 Dec 2014 08:18:50 -0800
Subject: llc: Make function pointer arrays const

It's better when function pointer arrays aren't modifiable.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/llc_c_st.h |   2 +-
 net/llc/llc_c_st.c     | 470 ++++++++++++++++++++++++-------------------------
 net/llc/llc_conn.c     |   2 +-
 3 files changed, 237 insertions(+), 237 deletions(-)

(limited to 'include')

diff --git a/include/net/llc_c_st.h b/include/net/llc_c_st.h
index 0e79cfba4b3..60e2ebb1d9b 100644
--- a/include/net/llc_c_st.h
+++ b/include/net/llc_c_st.h
@@ -36,7 +36,7 @@ struct llc_conn_state_trans {
 	llc_conn_ev_t	   ev;
 	u8		   next_state;
 	llc_conn_ev_qfyr_t *ev_qualifiers;
-	llc_conn_action_t  *ev_actions;
+	const llc_conn_action_t  *ev_actions;
 };
 
 struct llc_conn_state {
diff --git a/net/llc/llc_c_st.c b/net/llc/llc_c_st.c
index 818a9428823..3ae257dd9d4 100644
--- a/net/llc/llc_c_st.c
+++ b/net/llc/llc_c_st.c
@@ -33,7 +33,7 @@
  * LLC_CONN_STATE_AWAIT_REJ states
  */
 /* State transitions for LLC_CONN_EV_DISC_REQ event */
-static llc_conn_action_t llc_common_actions_1[] = {
+static const llc_conn_action_t llc_common_actions_1[] = {
 	[0] = llc_conn_ac_send_disc_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -50,7 +50,7 @@ static struct llc_conn_state_trans llc_common_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RESET_REQ event */
-static llc_conn_action_t llc_common_actions_2[] = {
+static const llc_conn_action_t llc_common_actions_2[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -67,7 +67,7 @@ static struct llc_conn_state_trans llc_common_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_common_actions_3[] = {
+static const llc_conn_action_t llc_common_actions_3[] = {
 	[0] = llc_conn_ac_stop_all_timers,
 	[1] = llc_conn_ac_set_vs_0,
 	[2] = llc_conn_ac_set_vr_0,
@@ -87,7 +87,7 @@ static struct llc_conn_state_trans llc_common_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_common_actions_4[] = {
+static const llc_conn_action_t llc_common_actions_4[] = {
 	[0] = llc_conn_ac_stop_all_timers,
 	[1] = llc_conn_ac_send_ua_rsp_f_set_p,
 	[2] = llc_conn_ac_disc_ind,
@@ -103,7 +103,7 @@ static struct llc_conn_state_trans llc_common_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_FRMR_RSP_Fbit_SET_X event */
-static llc_conn_action_t llc_common_actions_5[] = {
+static const llc_conn_action_t llc_common_actions_5[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -122,7 +122,7 @@ static struct llc_conn_state_trans llc_common_state_trans_5 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event */
-static llc_conn_action_t llc_common_actions_6[] = {
+static const llc_conn_action_t llc_common_actions_6[] = {
 	[0] = llc_conn_ac_disc_ind,
 	[1] = llc_conn_ac_stop_all_timers,
 	[2] = llc_conn_disc,
@@ -137,7 +137,7 @@ static struct llc_conn_state_trans llc_common_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_ZZZ_CMD_Pbit_SET_X_INVAL_Nr event */
-static llc_conn_action_t llc_common_actions_7a[] = {
+static const llc_conn_action_t llc_common_actions_7a[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -153,7 +153,7 @@ static struct llc_conn_state_trans llc_common_state_trans_7a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_X_INVAL_Ns event */
-static llc_conn_action_t llc_common_actions_7b[] = {
+static const llc_conn_action_t llc_common_actions_7b[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -169,7 +169,7 @@ static struct llc_conn_state_trans llc_common_state_trans_7b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_ZZZ_RSP_Fbit_SET_X_INVAL_Nr event */
-static llc_conn_action_t llc_common_actions_8a[] = {
+static const llc_conn_action_t llc_common_actions_8a[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -185,7 +185,7 @@ static struct llc_conn_state_trans llc_common_state_trans_8a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_X_INVAL_Ns event */
-static llc_conn_action_t llc_common_actions_8b[] = {
+static const llc_conn_action_t llc_common_actions_8b[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -201,7 +201,7 @@ static struct llc_conn_state_trans llc_common_state_trans_8b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_BAD_PDU event */
-static llc_conn_action_t llc_common_actions_8c[] = {
+static const llc_conn_action_t llc_common_actions_8c[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -217,7 +217,7 @@ static struct llc_conn_state_trans llc_common_state_trans_8c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X event */
-static llc_conn_action_t llc_common_actions_9[] = {
+static const llc_conn_action_t llc_common_actions_9[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -239,7 +239,7 @@ static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_10[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_common_actions_10[] = {
+static const llc_conn_action_t llc_common_actions_10[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -261,7 +261,7 @@ static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_common_actions_11a[] = {
+static const llc_conn_action_t llc_common_actions_11a[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -283,7 +283,7 @@ static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_common_actions_11b[] = {
+static const llc_conn_action_t llc_common_actions_11b[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -305,7 +305,7 @@ static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11c[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_common_actions_11c[] = {
+static const llc_conn_action_t llc_common_actions_11c[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -327,7 +327,7 @@ static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11d[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_common_actions_11d[] = {
+static const llc_conn_action_t llc_common_actions_11d[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -351,7 +351,7 @@ static struct llc_conn_state_trans llc_common_state_trans_end;
 
 /* LLC_CONN_STATE_ADM transitions */
 /* State transitions for LLC_CONN_EV_CONN_REQ event */
-static llc_conn_action_t llc_adm_actions_1[] = {
+static const llc_conn_action_t llc_adm_actions_1[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_set_retry_cnt_0,
@@ -367,7 +367,7 @@ static struct llc_conn_state_trans llc_adm_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_adm_actions_2[] = {
+static const llc_conn_action_t llc_adm_actions_2[] = {
 	[0] = llc_conn_ac_send_ua_rsp_f_set_p,
 	[1] = llc_conn_ac_set_vs_0,
 	[2] = llc_conn_ac_set_vr_0,
@@ -386,7 +386,7 @@ static struct llc_conn_state_trans llc_adm_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_adm_actions_3[] = {
+static const llc_conn_action_t llc_adm_actions_3[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_p,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -400,7 +400,7 @@ static struct llc_conn_state_trans llc_adm_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_adm_actions_4[] = {
+static const llc_conn_action_t llc_adm_actions_4[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_1,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -414,7 +414,7 @@ static struct llc_conn_state_trans llc_adm_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_XXX_YYY event */
-static llc_conn_action_t llc_adm_actions_5[] = {
+static const llc_conn_action_t llc_adm_actions_5[] = {
 	[0] = llc_conn_disc,
 	[1] = NULL,
 };
@@ -445,7 +445,7 @@ static struct llc_conn_state_trans *llc_adm_state_transitions[] = {
 
 /* LLC_CONN_STATE_SETUP transitions */
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_setup_actions_1[] = {
+static const llc_conn_action_t llc_setup_actions_1[] = {
 	[0] = llc_conn_ac_send_ua_rsp_f_set_p,
 	[1] = llc_conn_ac_set_vs_0,
 	[2] = llc_conn_ac_set_vr_0,
@@ -467,7 +467,7 @@ static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_2[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_setup_actions_2[] = {
+static const llc_conn_action_t llc_setup_actions_2[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_ac_set_vs_0,
 	[2] = llc_conn_ac_set_vr_0,
@@ -491,7 +491,7 @@ static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_3[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_setup_actions_3[] = {
+static const llc_conn_action_t llc_setup_actions_3[] = {
 	[0] = llc_conn_ac_set_p_flag_0,
 	[1] = llc_conn_ac_set_remote_busy_0,
 	[2] = llc_conn_ac_conn_confirm,
@@ -511,7 +511,7 @@ static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_4[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_setup_actions_4[] = {
+static const llc_conn_action_t llc_setup_actions_4[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_p,
 	[1] = llc_conn_ac_stop_ack_timer,
 	[2] = llc_conn_ac_conn_confirm,
@@ -532,7 +532,7 @@ static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_5[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_setup_actions_5[] = {
+static const llc_conn_action_t llc_setup_actions_5[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_ac_conn_confirm,
 	[2] = llc_conn_disc,
@@ -553,7 +553,7 @@ static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_7[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_setup_actions_7[] = {
+static const llc_conn_action_t llc_setup_actions_7[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -575,7 +575,7 @@ static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_8[] = {
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_setup_actions_8[] = {
+static const llc_conn_action_t llc_setup_actions_8[] = {
 	[0] = llc_conn_ac_conn_confirm,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -616,7 +616,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_1[] = {
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_1[] = {
+static const llc_conn_action_t llc_normal_actions_1[] = {
 	[0] = llc_conn_ac_send_i_as_ack,
 	[1] = llc_conn_ac_start_ack_tmr_if_not_running,
 	[2] = NULL,
@@ -637,7 +637,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_2[] = {
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_2[] = {
+static const llc_conn_action_t llc_normal_actions_2[] = {
 	[0] = llc_conn_ac_send_i_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = NULL,
@@ -658,7 +658,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_2_1[] = {
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_normal_actions_2_1[1];
+static const llc_conn_action_t llc_normal_actions_2_1[1];
 
 static struct llc_conn_state_trans llc_normal_state_trans_2_1 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -673,7 +673,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_3[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_3[] = {
+static const llc_conn_action_t llc_normal_actions_3[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rnr_xxx_x_set_0,
 	[2] = llc_conn_ac_set_data_flag_0,
@@ -693,7 +693,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_4[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_4[] = {
+static const llc_conn_action_t llc_normal_actions_4[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rnr_xxx_x_set_0,
 	[2] = llc_conn_ac_set_data_flag_0,
@@ -713,7 +713,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_5a[] = {
+static const llc_conn_action_t llc_normal_actions_5a[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -736,7 +736,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_5b[] = {
+static const llc_conn_action_t llc_normal_actions_5b[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -759,7 +759,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5c[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_5c[] = {
+static const llc_conn_action_t llc_normal_actions_5c[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -782,7 +782,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_6a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_6a[] = {
+static const llc_conn_action_t llc_normal_actions_6a[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -803,7 +803,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_6b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_6b[] = {
+static const llc_conn_action_t llc_normal_actions_6b[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -819,7 +819,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_6b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_normal_actions_7[] = {
+static const llc_conn_action_t llc_normal_actions_7[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rej_rsp_f_set_1,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -840,7 +840,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_8a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_8[] = {
+static const llc_conn_action_t llc_normal_actions_8[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -876,7 +876,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_9a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_9a[] = {
+static const llc_conn_action_t llc_normal_actions_9a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_data_ind,
@@ -897,7 +897,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_9b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_9b[] = {
+static const llc_conn_action_t llc_normal_actions_9b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_data_ind,
@@ -913,7 +913,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_9b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_normal_actions_10[] = {
+static const llc_conn_action_t llc_normal_actions_10[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_send_ack_rsp_f_set_1,
 	[2] = llc_conn_ac_rst_sendack_flag,
@@ -930,7 +930,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_10 = {
 };
 
 /* State transitions for * LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_normal_actions_11a[] = {
+static const llc_conn_action_t llc_normal_actions_11a[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -945,7 +945,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_11a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_normal_actions_11b[] = {
+static const llc_conn_action_t llc_normal_actions_11b[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -965,7 +965,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_11c[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_11c[] = {
+static const llc_conn_action_t llc_normal_actions_11c[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_inc_tx_win_size,
@@ -981,7 +981,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_11c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_normal_actions_12[] = {
+static const llc_conn_action_t llc_normal_actions_12[] = {
 	[0] = llc_conn_ac_send_ack_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_adjust_npta_by_rr,
@@ -998,7 +998,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_12 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_normal_actions_13a[] = {
+static const llc_conn_action_t llc_normal_actions_13a[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1013,7 +1013,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_13a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_normal_actions_13b[] = {
+static const llc_conn_action_t llc_normal_actions_13b[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1033,7 +1033,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_13c[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_13c[] = {
+static const llc_conn_action_t llc_normal_actions_13c[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1048,7 +1048,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_13c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_normal_actions_14[] = {
+static const llc_conn_action_t llc_normal_actions_14[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_adjust_npta_by_rnr,
@@ -1070,7 +1070,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_15a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_15a[] = {
+static const llc_conn_action_t llc_normal_actions_15a[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -1093,7 +1093,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_15b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_15b[] = {
+static const llc_conn_action_t llc_normal_actions_15b[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -1116,7 +1116,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_16a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_16a[] = {
+static const llc_conn_action_t llc_normal_actions_16a[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_dec_tx_win_size,
@@ -1138,7 +1138,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_16b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_16b[] = {
+static const llc_conn_action_t llc_normal_actions_16b[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_dec_tx_win_size,
@@ -1155,7 +1155,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_16b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_normal_actions_17[] = {
+static const llc_conn_action_t llc_normal_actions_17[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_dec_tx_win_size,
@@ -1177,7 +1177,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_18[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_18[] = {
+static const llc_conn_action_t llc_normal_actions_18[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = NULL,
@@ -1196,7 +1196,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_19[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_19[] = {
+static const llc_conn_action_t llc_normal_actions_19[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[2] = llc_conn_ac_rst_vs,
@@ -1219,7 +1219,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_20a[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_20a[] = {
+static const llc_conn_action_t llc_normal_actions_20a[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[2] = llc_conn_ac_rst_vs,
@@ -1242,7 +1242,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_20b[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_20b[] = {
+static const llc_conn_action_t llc_normal_actions_20b[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[2] = llc_conn_ac_rst_vs,
@@ -1264,7 +1264,7 @@ static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_21[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_21[] = {
+static const llc_conn_action_t llc_normal_actions_21[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = NULL,
@@ -1348,7 +1348,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_1[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_1[] = {
+static const llc_conn_action_t llc_busy_actions_1[] = {
 	[0] = llc_conn_ac_send_i_xxx_x_set_0,
 	[1] = llc_conn_ac_start_ack_tmr_if_not_running,
 	[2] = NULL,
@@ -1368,7 +1368,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_2[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_2[] = {
+static const llc_conn_action_t llc_busy_actions_2[] = {
 	[0] = llc_conn_ac_send_i_xxx_x_set_0,
 	[1] = llc_conn_ac_start_ack_tmr_if_not_running,
 	[2] = NULL,
@@ -1389,7 +1389,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_2_1[] = {
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_busy_actions_2_1[1];
+static const llc_conn_action_t llc_busy_actions_2_1[1];
 
 static struct llc_conn_state_trans llc_busy_state_trans_2_1 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -1405,7 +1405,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_3[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_3[] = {
+static const llc_conn_action_t llc_busy_actions_3[] = {
 	[0] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[1] = llc_conn_ac_start_rej_timer,
 	[2] = NULL,
@@ -1425,7 +1425,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_4[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_4[] = {
+static const llc_conn_action_t llc_busy_actions_4[] = {
 	[0] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[1] = llc_conn_ac_start_rej_timer,
 	[2] = NULL,
@@ -1445,7 +1445,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_5[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_5[] = {
+static const llc_conn_action_t llc_busy_actions_5[] = {
 	[0] = llc_conn_ac_send_rr_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -1464,7 +1464,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_6[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_6[] = {
+static const llc_conn_action_t llc_busy_actions_6[] = {
 	[0] = llc_conn_ac_send_rr_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -1483,7 +1483,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_7[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_7[] = {
+static const llc_conn_action_t llc_busy_actions_7[] = {
 	[0] = llc_conn_ac_send_rr_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -1502,7 +1502,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_8[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_8[] = {
+static const llc_conn_action_t llc_busy_actions_8[] = {
 	[0] = llc_conn_ac_send_rr_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -1520,7 +1520,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_9a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_9a[] = {
+static const llc_conn_action_t llc_busy_actions_9a[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_p_flag,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -1542,7 +1542,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_9b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_9b[] = {
+static const llc_conn_action_t llc_busy_actions_9b[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_p_flag,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -1564,7 +1564,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_10a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_10a[] = {
+static const llc_conn_action_t llc_busy_actions_10a[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_data_flag_1_if_data_flag_eq_0,
@@ -1584,7 +1584,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_10b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_10b[] = {
+static const llc_conn_action_t llc_busy_actions_10b[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_data_flag_1_if_data_flag_eq_0,
@@ -1599,7 +1599,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_10b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_busy_actions_11[] = {
+static const llc_conn_action_t llc_busy_actions_11[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_data_flag_1_if_data_flag_eq_0,
@@ -1614,7 +1614,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_11 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_busy_actions_12[] = {
+static const llc_conn_action_t llc_busy_actions_12[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rnr_rsp_f_set_1,
@@ -1637,7 +1637,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_13a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_13a[] = {
+static const llc_conn_action_t llc_busy_actions_13a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -1662,7 +1662,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_13b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_13b[] = {
+static const llc_conn_action_t llc_busy_actions_13b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -1687,7 +1687,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_14a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_14a[] = {
+static const llc_conn_action_t llc_busy_actions_14a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
@@ -1710,7 +1710,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_14b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_14b[] = {
+static const llc_conn_action_t llc_busy_actions_14b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
@@ -1728,7 +1728,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_14b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_busy_actions_15a[] = {
+static const llc_conn_action_t llc_busy_actions_15a[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -1743,7 +1743,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_15a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_busy_actions_15b[] = {
+static const llc_conn_action_t llc_busy_actions_15b[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -1763,7 +1763,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_15c[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_15c[] = {
+static const llc_conn_action_t llc_busy_actions_15c[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -1778,7 +1778,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_15c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_busy_actions_16[] = {
+static const llc_conn_action_t llc_busy_actions_16[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -1793,7 +1793,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_16 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_busy_actions_17a[] = {
+static const llc_conn_action_t llc_busy_actions_17a[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1808,7 +1808,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_17a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_busy_actions_17b[] = {
+static const llc_conn_action_t llc_busy_actions_17b[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1828,7 +1828,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_17c[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_17c[] = {
+static const llc_conn_action_t llc_busy_actions_17c[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1843,7 +1843,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_17c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_busy_actions_18[] = {
+static const llc_conn_action_t llc_busy_actions_18[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1863,7 +1863,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_19a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_19a[] = {
+static const llc_conn_action_t llc_busy_actions_19a[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -1885,7 +1885,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_19b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_19b[] = {
+static const llc_conn_action_t llc_busy_actions_19b[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -1907,7 +1907,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_20a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_20a[] = {
+static const llc_conn_action_t llc_busy_actions_20a[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_resend_i_xxx_x_set_0,
@@ -1928,7 +1928,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_20b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_20b[] = {
+static const llc_conn_action_t llc_busy_actions_20b[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_resend_i_xxx_x_set_0,
@@ -1944,7 +1944,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_20b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_busy_actions_21[] = {
+static const llc_conn_action_t llc_busy_actions_21[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_send_rnr_rsp_f_set_1,
@@ -1966,7 +1966,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_22[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_22[] = {
+static const llc_conn_action_t llc_busy_actions_22[] = {
 	[0] = llc_conn_ac_send_rnr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = NULL,
@@ -1985,7 +1985,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_23[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_23[] = {
+static const llc_conn_action_t llc_busy_actions_23[] = {
 	[0] = llc_conn_ac_send_rnr_cmd_p_set_1,
 	[1] = llc_conn_ac_rst_vs,
 	[2] = llc_conn_ac_start_p_timer,
@@ -2007,7 +2007,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_24a[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_24a[] = {
+static const llc_conn_action_t llc_busy_actions_24a[] = {
 	[0] = llc_conn_ac_send_rnr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -2029,7 +2029,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_24b[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_24b[] = {
+static const llc_conn_action_t llc_busy_actions_24b[] = {
 	[0] = llc_conn_ac_send_rnr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -2051,7 +2051,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_25[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_25[] = {
+static const llc_conn_action_t llc_busy_actions_25[] = {
 	[0] = llc_conn_ac_send_rnr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -2074,7 +2074,7 @@ static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_26[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_26[] = {
+static const llc_conn_action_t llc_busy_actions_26[] = {
 	[0] = llc_conn_ac_set_data_flag_1,
 	[1] = NULL,
 };
@@ -2161,7 +2161,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_1[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_1[] = {
+static const llc_conn_action_t llc_reject_actions_1[] = {
 	[0] = llc_conn_ac_send_i_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -2180,7 +2180,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_2[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_2[] = {
+static const llc_conn_action_t llc_reject_actions_2[] = {
 	[0] = llc_conn_ac_send_i_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -2200,7 +2200,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_2_1[] = {
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_reject_actions_2_1[1];
+static const llc_conn_action_t llc_reject_actions_2_1[1];
 
 static struct llc_conn_state_trans llc_reject_state_trans_2_1 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -2216,7 +2216,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_3[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_3[] = {
+static const llc_conn_action_t llc_reject_actions_3[] = {
 	[0] = llc_conn_ac_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_set_data_flag_2,
 	[2] = NULL,
@@ -2235,7 +2235,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_4[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_4[] = {
+static const llc_conn_action_t llc_reject_actions_4[] = {
 	[0] = llc_conn_ac_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_set_data_flag_2,
 	[2] = NULL,
@@ -2249,7 +2249,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_reject_actions_5a[] = {
+static const llc_conn_action_t llc_reject_actions_5a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_p_flag,
 	[2] = llc_conn_ac_clear_remote_busy_if_f_eq_1,
@@ -2264,7 +2264,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_5a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_reject_actions_5b[] = {
+static const llc_conn_action_t llc_reject_actions_5b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_p_flag,
 	[2] = llc_conn_ac_clear_remote_busy_if_f_eq_1,
@@ -2284,7 +2284,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_5c[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_5c[] = {
+static const llc_conn_action_t llc_reject_actions_5c[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_p_flag,
 	[2] = llc_conn_ac_clear_remote_busy_if_f_eq_1,
@@ -2299,7 +2299,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_5c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_reject_actions_6[] = {
+static const llc_conn_action_t llc_reject_actions_6[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = NULL,
@@ -2318,7 +2318,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_7a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_7a[] = {
+static const llc_conn_action_t llc_reject_actions_7a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -2343,7 +2343,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_7b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_7b[] = {
+static const llc_conn_action_t llc_reject_actions_7b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -2367,7 +2367,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_8a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_8a[] = {
+static const llc_conn_action_t llc_reject_actions_8a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_ack_xxx_x_set_0,
@@ -2389,7 +2389,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_8b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_8b[] = {
+static const llc_conn_action_t llc_reject_actions_8b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_ack_xxx_x_set_0,
@@ -2406,7 +2406,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_8b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_reject_actions_9[] = {
+static const llc_conn_action_t llc_reject_actions_9[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_ack_rsp_f_set_1,
@@ -2423,7 +2423,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_9 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_reject_actions_10a[] = {
+static const llc_conn_action_t llc_reject_actions_10a[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -2438,7 +2438,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_10a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_reject_actions_10b[] = {
+static const llc_conn_action_t llc_reject_actions_10b[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -2458,7 +2458,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_10c[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_10c[] = {
+static const llc_conn_action_t llc_reject_actions_10c[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -2473,7 +2473,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_10c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_reject_actions_11[] = {
+static const llc_conn_action_t llc_reject_actions_11[] = {
 	[0] = llc_conn_ac_send_ack_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -2488,7 +2488,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_11 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_reject_actions_12a[] = {
+static const llc_conn_action_t llc_reject_actions_12a[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -2503,7 +2503,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_12a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_reject_actions_12b[] = {
+static const llc_conn_action_t llc_reject_actions_12b[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -2523,7 +2523,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_12c[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_12c[] = {
+static const llc_conn_action_t llc_reject_actions_12c[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -2538,7 +2538,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_12c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_reject_actions_13[] = {
+static const llc_conn_action_t llc_reject_actions_13[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -2558,7 +2558,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_14a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_14a[] = {
+static const llc_conn_action_t llc_reject_actions_14a[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -2580,7 +2580,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_14b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_14b[] = {
+static const llc_conn_action_t llc_reject_actions_14b[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -2602,7 +2602,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_15a[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_15a[] = {
+static const llc_conn_action_t llc_reject_actions_15a[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_resend_i_xxx_x_set_0,
@@ -2623,7 +2623,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_15b[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_15b[] = {
+static const llc_conn_action_t llc_reject_actions_15b[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_resend_i_xxx_x_set_0,
@@ -2639,7 +2639,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_15b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_reject_actions_16[] = {
+static const llc_conn_action_t llc_reject_actions_16[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_resend_i_rsp_f_set_1,
@@ -2660,7 +2660,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_17[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_17[] = {
+static const llc_conn_action_t llc_reject_actions_17[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = NULL,
@@ -2680,7 +2680,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_18[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_18[] = {
+static const llc_conn_action_t llc_reject_actions_18[] = {
 	[0] = llc_conn_ac_send_rej_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_start_rej_timer,
@@ -2701,7 +2701,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_19[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_19[] = {
+static const llc_conn_action_t llc_reject_actions_19[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_start_rej_timer,
@@ -2724,7 +2724,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_20a[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_20a[] = {
+static const llc_conn_action_t llc_reject_actions_20a[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_start_rej_timer,
@@ -2747,7 +2747,7 @@ static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_20b[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_20b[] = {
+static const llc_conn_action_t llc_reject_actions_20b[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_start_rej_timer,
@@ -2832,7 +2832,7 @@ static llc_conn_ev_qfyr_t llc_await_ev_qfyrs_1_0[] = {
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_await_actions_1_0[1];
+static const llc_conn_action_t llc_await_actions_1_0[1];
 
 static struct llc_conn_state_trans llc_await_state_trans_1_0 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -2842,7 +2842,7 @@ static struct llc_conn_state_trans llc_await_state_trans_1_0 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_DETECTED event */
-static llc_conn_action_t llc_await_actions_1[] = {
+static const llc_conn_action_t llc_await_actions_1[] = {
 	[0] = llc_conn_ac_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_set_data_flag_0,
 	[2] = NULL,
@@ -2856,7 +2856,7 @@ static struct llc_conn_state_trans llc_await_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_actions_2[] = {
+static const llc_conn_action_t llc_await_actions_2[] = {
 	[0] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -2875,7 +2875,7 @@ static struct llc_conn_state_trans llc_await_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_actions_3a[] = {
+static const llc_conn_action_t llc_await_actions_3a[] = {
 	[0] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -2891,7 +2891,7 @@ static struct llc_conn_state_trans llc_await_state_trans_3a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_actions_3b[] = {
+static const llc_conn_action_t llc_await_actions_3b[] = {
 	[0] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -2907,7 +2907,7 @@ static struct llc_conn_state_trans llc_await_state_trans_3b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_actions_4[] = {
+static const llc_conn_action_t llc_await_actions_4[] = {
 	[0] = llc_conn_ac_send_rej_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -2924,7 +2924,7 @@ static struct llc_conn_state_trans llc_await_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_5[] = {
+static const llc_conn_action_t llc_await_actions_5[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -2943,7 +2943,7 @@ static struct llc_conn_state_trans llc_await_state_trans_5 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_6a[] = {
+static const llc_conn_action_t llc_await_actions_6a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rr_xxx_x_set_0,
@@ -2960,7 +2960,7 @@ static struct llc_conn_state_trans llc_await_state_trans_6a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_6b[] = {
+static const llc_conn_action_t llc_await_actions_6b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rr_xxx_x_set_0,
@@ -2977,7 +2977,7 @@ static struct llc_conn_state_trans llc_await_state_trans_6b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_7[] = {
+static const llc_conn_action_t llc_await_actions_7[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rr_rsp_f_set_1,
@@ -2994,7 +2994,7 @@ static struct llc_conn_state_trans llc_await_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_8a[] = {
+static const llc_conn_action_t llc_await_actions_8a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3011,7 +3011,7 @@ static struct llc_conn_state_trans llc_await_state_trans_8a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_8b[] = {
+static const llc_conn_action_t llc_await_actions_8b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3028,7 +3028,7 @@ static struct llc_conn_state_trans llc_await_state_trans_8b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_9a[] = {
+static const llc_conn_action_t llc_await_actions_9a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3043,7 +3043,7 @@ static struct llc_conn_state_trans llc_await_state_trans_9a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_9b[] = {
+static const llc_conn_action_t llc_await_actions_9b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3058,7 +3058,7 @@ static struct llc_conn_state_trans llc_await_state_trans_9b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_9c[] = {
+static const llc_conn_action_t llc_await_actions_9c[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3073,7 +3073,7 @@ static struct llc_conn_state_trans llc_await_state_trans_9c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_9d[] = {
+static const llc_conn_action_t llc_await_actions_9d[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3088,7 +3088,7 @@ static struct llc_conn_state_trans llc_await_state_trans_9d = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_10a[] = {
+static const llc_conn_action_t llc_await_actions_10a[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3104,7 +3104,7 @@ static struct llc_conn_state_trans llc_await_state_trans_10a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_10b[] = {
+static const llc_conn_action_t llc_await_actions_10b[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3120,7 +3120,7 @@ static struct llc_conn_state_trans llc_await_state_trans_10b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_11[] = {
+static const llc_conn_action_t llc_await_actions_11[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3136,7 +3136,7 @@ static struct llc_conn_state_trans llc_await_state_trans_11 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_12a[] = {
+static const llc_conn_action_t llc_await_actions_12a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -3151,7 +3151,7 @@ static struct llc_conn_state_trans llc_await_state_trans_12a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_12b[] = {
+static const llc_conn_action_t llc_await_actions_12b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -3166,7 +3166,7 @@ static struct llc_conn_state_trans llc_await_state_trans_12b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_13[] = {
+static const llc_conn_action_t llc_await_actions_13[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3187,7 +3187,7 @@ static llc_conn_ev_qfyr_t llc_await_ev_qfyrs_14[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_await_actions_14[] = {
+static const llc_conn_action_t llc_await_actions_14[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -3261,7 +3261,7 @@ static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_1_0[] = {
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_await_busy_actions_1_0[1];
+static const llc_conn_action_t llc_await_busy_actions_1_0[1];
 
 static struct llc_conn_state_trans llc_await_busy_state_trans_1_0 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -3276,7 +3276,7 @@ static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_1[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_await_busy_actions_1[] = {
+static const llc_conn_action_t llc_await_busy_actions_1[] = {
 	[0] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[1] = llc_conn_ac_start_rej_timer,
 	[2] = NULL,
@@ -3295,7 +3295,7 @@ static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_2[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_await_busy_actions_2[] = {
+static const llc_conn_action_t llc_await_busy_actions_2[] = {
 	[0] = llc_conn_ac_send_rr_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -3313,7 +3313,7 @@ static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_3[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_await_busy_actions_3[] = {
+static const llc_conn_action_t llc_await_busy_actions_3[] = {
 	[0] = llc_conn_ac_send_rr_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -3326,7 +3326,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_busy_actions_4[] = {
+static const llc_conn_action_t llc_await_busy_actions_4[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3345,7 +3345,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_busy_actions_5a[] = {
+static const llc_conn_action_t llc_await_busy_actions_5a[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3361,7 +3361,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_5a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_busy_actions_5b[] = {
+static const llc_conn_action_t llc_await_busy_actions_5b[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3377,7 +3377,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_5b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_busy_actions_6[] = {
+static const llc_conn_action_t llc_await_busy_actions_6[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3393,7 +3393,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_7[] = {
+static const llc_conn_action_t llc_await_busy_actions_7[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_inc_vr_by_1,
 	[2] = llc_conn_ac_data_ind,
@@ -3414,7 +3414,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_8a[] = {
+static const llc_conn_action_t llc_await_busy_actions_8a[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_inc_vr_by_1,
 	[2] = llc_conn_ac_data_ind,
@@ -3432,7 +3432,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_8a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_8b[] = {
+static const llc_conn_action_t llc_await_busy_actions_8b[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_inc_vr_by_1,
 	[2] = llc_conn_ac_data_ind,
@@ -3450,7 +3450,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_8b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_9[] = {
+static const llc_conn_action_t llc_await_busy_actions_9[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_inc_vr_by_1,
 	[2] = llc_conn_ac_data_ind,
@@ -3468,7 +3468,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_9 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_10a[] = {
+static const llc_conn_action_t llc_await_busy_actions_10a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3485,7 +3485,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_10a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_10b[] = {
+static const llc_conn_action_t llc_await_busy_actions_10b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3502,7 +3502,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_10b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_11a[] = {
+static const llc_conn_action_t llc_await_busy_actions_11a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3517,7 +3517,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_11a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_11b[] = {
+static const llc_conn_action_t llc_await_busy_actions_11b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3532,7 +3532,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_11b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_11c[] = {
+static const llc_conn_action_t llc_await_busy_actions_11c[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3547,7 +3547,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_11c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_11d[] = {
+static const llc_conn_action_t llc_await_busy_actions_11d[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3562,7 +3562,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_11d = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_12a[] = {
+static const llc_conn_action_t llc_await_busy_actions_12a[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3578,7 +3578,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_12a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_12b[] = {
+static const llc_conn_action_t llc_await_busy_actions_12b[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3594,7 +3594,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_12b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_13[] = {
+static const llc_conn_action_t llc_await_busy_actions_13[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3610,7 +3610,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_13 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_14a[] = {
+static const llc_conn_action_t llc_await_busy_actions_14a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -3625,7 +3625,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_14a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_14b[] = {
+static const llc_conn_action_t llc_await_busy_actions_14b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -3640,7 +3640,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_14b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_15[] = {
+static const llc_conn_action_t llc_await_busy_actions_15[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3661,7 +3661,7 @@ static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_16[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_await_busy_actions_16[] = {
+static const llc_conn_action_t llc_await_busy_actions_16[] = {
 	[0] = llc_conn_ac_send_rnr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -3737,7 +3737,7 @@ static llc_conn_ev_qfyr_t llc_await_reject_ev_qfyrs_1_0[] = {
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_await_reject_actions_1_0[1];
+static const llc_conn_action_t llc_await_reject_actions_1_0[1];
 
 static struct llc_conn_state_trans llc_await_reject_state_trans_1_0 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -3747,7 +3747,7 @@ static struct llc_conn_state_trans llc_await_reject_state_trans_1_0 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_DETECTED event */
-static llc_conn_action_t llc_await_rejct_actions_1[] = {
+static const llc_conn_action_t llc_await_rejct_actions_1[] = {
 	[0] = llc_conn_ac_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_set_data_flag_2,
 	[2] = NULL
@@ -3761,7 +3761,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_rejct_actions_2a[] = {
+static const llc_conn_action_t llc_await_rejct_actions_2a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = NULL
@@ -3775,7 +3775,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_2a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_rejct_actions_2b[] = {
+static const llc_conn_action_t llc_await_rejct_actions_2b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = NULL
@@ -3789,7 +3789,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_2b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_rejct_actions_3[] = {
+static const llc_conn_action_t llc_await_rejct_actions_3[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3804,7 +3804,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_4[] = {
+static const llc_conn_action_t llc_await_rejct_actions_4[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3824,7 +3824,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_5a[] = {
+static const llc_conn_action_t llc_await_rejct_actions_5a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rr_xxx_x_set_0,
@@ -3842,7 +3842,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_5a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_5b[] = {
+static const llc_conn_action_t llc_await_rejct_actions_5b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rr_xxx_x_set_0,
@@ -3860,7 +3860,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_5b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_6[] = {
+static const llc_conn_action_t llc_await_rejct_actions_6[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rr_rsp_f_set_1,
@@ -3878,7 +3878,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_7a[] = {
+static const llc_conn_action_t llc_await_rejct_actions_7a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3895,7 +3895,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_7a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_7b[] = {
+static const llc_conn_action_t llc_await_rejct_actions_7b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3912,7 +3912,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_7b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_rejct_actions_7c[] = {
+static const llc_conn_action_t llc_await_rejct_actions_7c[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3929,7 +3929,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_7c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_8a[] = {
+static const llc_conn_action_t llc_await_rejct_actions_8a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3944,7 +3944,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_8a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_8b[] = {
+static const llc_conn_action_t llc_await_rejct_actions_8b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3959,7 +3959,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_8b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_8c[] = {
+static const llc_conn_action_t llc_await_rejct_actions_8c[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3974,7 +3974,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_8c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_8d[] = {
+static const llc_conn_action_t llc_await_rejct_actions_8d[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3989,7 +3989,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_8d = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_9a[] = {
+static const llc_conn_action_t llc_await_rejct_actions_9a[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -4005,7 +4005,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_9a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_9b[] = {
+static const llc_conn_action_t llc_await_rejct_actions_9b[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -4021,7 +4021,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_9b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_10[] = {
+static const llc_conn_action_t llc_await_rejct_actions_10[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -4037,7 +4037,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_10 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_11a[] = {
+static const llc_conn_action_t llc_await_rejct_actions_11a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -4052,7 +4052,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_11a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_11b[] = {
+static const llc_conn_action_t llc_await_rejct_actions_11b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -4067,7 +4067,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_11b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_12[] = {
+static const llc_conn_action_t llc_await_rejct_actions_12[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -4088,7 +4088,7 @@ static llc_conn_ev_qfyr_t llc_await_rejct_ev_qfyrs_13[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_await_rejct_actions_13[] = {
+static const llc_conn_action_t llc_await_rejct_actions_13[] = {
 	[0] = llc_conn_ac_send_rej_cmd_p_set_1,
 	[1] = llc_conn_ac_stop_p_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -4163,7 +4163,7 @@ static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_1[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_1[] = {
+static const llc_conn_action_t llc_d_conn_actions_1[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_p,
 	[1] = llc_conn_ac_stop_ack_timer,
 	[2] = llc_conn_ac_disc_confirm,
@@ -4187,7 +4187,7 @@ static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_1_1[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_1_1[] = {
+static const llc_conn_action_t llc_d_conn_actions_1_1[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_p,
 	[1] = llc_conn_ac_stop_ack_timer,
 	[2] = llc_conn_disc,
@@ -4211,7 +4211,7 @@ static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_2[] = {
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_2[] = {
+static const llc_conn_action_t llc_d_conn_actions_2[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_ac_disc_confirm,
 	[2] = llc_conn_disc,
@@ -4235,7 +4235,7 @@ static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_2_1[] = {
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_2_1[] = {
+static const llc_conn_action_t llc_d_conn_actions_2_1[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -4249,7 +4249,7 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_2_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_d_conn_actions_3[] = {
+static const llc_conn_action_t llc_d_conn_actions_3[] = {
 	[0] = llc_conn_ac_send_ua_rsp_f_set_p,
 	[1] = NULL,
 };
@@ -4270,7 +4270,7 @@ static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_4[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_4[] = {
+static const llc_conn_action_t llc_d_conn_actions_4[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_ac_disc_confirm,
 	[2] = llc_conn_disc,
@@ -4293,7 +4293,7 @@ static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_4_1[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_4_1[] = {
+static const llc_conn_action_t llc_d_conn_actions_4_1[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -4316,7 +4316,7 @@ static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_5[] = {
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_d_conn_actions_5[1];
+static const llc_conn_action_t llc_d_conn_actions_5[1];
 
 static struct llc_conn_state_trans llc_d_conn_state_trans_5 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -4331,7 +4331,7 @@ static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_6[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_6[] = {
+static const llc_conn_action_t llc_d_conn_actions_6[] = {
 	[0] = llc_conn_ac_send_disc_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -4353,7 +4353,7 @@ static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_7[] = {
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_7[] = {
+static const llc_conn_action_t llc_d_conn_actions_7[] = {
 	[0] = llc_conn_ac_disc_confirm,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -4374,7 +4374,7 @@ static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_8[] = {
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_8[] = {
+static const llc_conn_action_t llc_d_conn_actions_8[] = {
 	[0] = llc_conn_disc,
 	[1] = NULL,
 };
@@ -4411,7 +4411,7 @@ static struct llc_conn_state_trans *llc_d_conn_state_transitions[] = {
 
 /* LLC_CONN_STATE_RESET transitions */
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_rst_actions_1[] = {
+static const llc_conn_action_t llc_rst_actions_1[] = {
 	[0] = llc_conn_ac_set_vs_0,
 	[1] = llc_conn_ac_set_vr_0,
 	[2] = llc_conn_ac_set_s_flag_1,
@@ -4436,7 +4436,7 @@ static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_2[] = {
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_2[] = {
+static const llc_conn_action_t llc_rst_actions_2[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_ac_set_vs_0,
 	[2] = llc_conn_ac_set_vr_0,
@@ -4464,7 +4464,7 @@ static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_2_1[] = {
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_2_1[] = {
+static const llc_conn_action_t llc_rst_actions_2_1[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_ac_set_vs_0,
 	[2] = llc_conn_ac_set_vr_0,
@@ -4489,7 +4489,7 @@ static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_3[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_3[] = {
+static const llc_conn_action_t llc_rst_actions_3[] = {
 	[0] = llc_conn_ac_set_p_flag_0,
 	[1] = llc_conn_ac_set_remote_busy_0,
 	[2] = NULL,
@@ -4510,7 +4510,7 @@ static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_4[] = {
 	[1] = llc_conn_ev_qlfy_set_status_disc,
 	[2] = NULL,
 };
-static llc_conn_action_t llc_rst_actions_4[] = {
+static const llc_conn_action_t llc_rst_actions_4[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_p,
 	[1] = llc_conn_ac_disc_ind,
 	[2] = llc_conn_ac_stop_ack_timer,
@@ -4534,7 +4534,7 @@ static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_4_1[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_4_1[] = {
+static const llc_conn_action_t llc_rst_actions_4_1[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_p,
 	[1] = llc_conn_ac_stop_ack_timer,
 	[2] = llc_conn_disc,
@@ -4557,7 +4557,7 @@ static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_5[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_5[] = {
+static const llc_conn_action_t llc_rst_actions_5[] = {
 	[0] = llc_conn_ac_disc_ind,
 	[1] = llc_conn_ac_stop_ack_timer,
 	[2] = llc_conn_disc,
@@ -4580,7 +4580,7 @@ static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_5_1[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_5_1[] = {
+static const llc_conn_action_t llc_rst_actions_5_1[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -4600,7 +4600,7 @@ static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_6[] = {
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_rst_actions_6[1];
+static const llc_conn_action_t llc_rst_actions_6[1];
 
 static struct llc_conn_state_trans llc_rst_state_trans_6 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -4616,7 +4616,7 @@ static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_7[] = {
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_7[] = {
+static const llc_conn_action_t llc_rst_actions_7[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -4638,7 +4638,7 @@ static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_8[] = {
 	[3] = llc_conn_ev_qlfy_set_status_failed,
 	[4] = NULL,
 };
-static llc_conn_action_t llc_rst_actions_8[] = {
+static const llc_conn_action_t llc_rst_actions_8[] = {
 	[0] = llc_conn_ac_disc_ind,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -4659,7 +4659,7 @@ static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_8_1[] = {
 	[3] = llc_conn_ev_qlfy_set_status_failed,
 	[4] = NULL,
 };
-static llc_conn_action_t llc_rst_actions_8_1[] = {
+static const llc_conn_action_t llc_rst_actions_8_1[] = {
 	[0] = llc_conn_ac_disc_ind,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -4698,7 +4698,7 @@ static struct llc_conn_state_trans *llc_rst_state_transitions[] = {
 
 /* LLC_CONN_STATE_ERROR transitions */
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_error_actions_1[] = {
+static const llc_conn_action_t llc_error_actions_1[] = {
 	[0] = llc_conn_ac_set_vs_0,
 	[1] = llc_conn_ac_set_vr_0,
 	[2] = llc_conn_ac_send_ua_rsp_f_set_p,
@@ -4718,7 +4718,7 @@ static struct llc_conn_state_trans llc_error_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_error_actions_2[] = {
+static const llc_conn_action_t llc_error_actions_2[] = {
 	[0] = llc_conn_ac_send_ua_rsp_f_set_p,
 	[1] = llc_conn_ac_disc_ind,
 	[2] = llc_conn_ac_stop_ack_timer,
@@ -4734,7 +4734,7 @@ static struct llc_conn_state_trans llc_error_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event */
-static llc_conn_action_t llc_error_actions_3[] = {
+static const llc_conn_action_t llc_error_actions_3[] = {
 	[0] = llc_conn_ac_disc_ind,
 	[1] = llc_conn_ac_stop_ack_timer,
 	[2] = llc_conn_disc,
@@ -4749,7 +4749,7 @@ static struct llc_conn_state_trans llc_error_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_FRMR_RSP_Fbit_SET_X event */
-static llc_conn_action_t llc_error_actions_4[] = {
+static const llc_conn_action_t llc_error_actions_4[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_set_retry_cnt_0,
@@ -4765,7 +4765,7 @@ static struct llc_conn_state_trans llc_error_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_error_actions_5[] = {
+static const llc_conn_action_t llc_error_actions_5[] = {
 	[0] = llc_conn_ac_resend_frmr_rsp_f_set_p,
 	[1] = NULL,
 };
@@ -4791,7 +4791,7 @@ static llc_conn_ev_qfyr_t llc_error_ev_qfyrs_7[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_error_actions_7[] = {
+static const llc_conn_action_t llc_error_actions_7[] = {
 	[0] = llc_conn_ac_resend_frmr_rsp_f_set_0,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -4811,7 +4811,7 @@ static llc_conn_ev_qfyr_t llc_error_ev_qfyrs_8[] = {
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_error_actions_8[] = {
+static const llc_conn_action_t llc_error_actions_8[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_set_s_flag_0,
 	[2] = llc_conn_ac_start_ack_timer,
@@ -4834,7 +4834,7 @@ static llc_conn_ev_qfyr_t llc_error_ev_qfyrs_9[] = {
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_error_actions_9[1];
+static const llc_conn_action_t llc_error_actions_9[1];
 
 static struct llc_conn_state_trans llc_error_state_trans_9 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -4866,7 +4866,7 @@ static struct llc_conn_state_trans *llc_error_state_transitions[] = {
 
 /* LLC_CONN_STATE_TEMP transitions */
 /* State transitions for LLC_CONN_EV_DISC_REQ event */
-static llc_conn_action_t llc_temp_actions_1[] = {
+static const llc_conn_action_t llc_temp_actions_1[] = {
 	[0] = llc_conn_ac_stop_all_timers,
 	[1] = llc_conn_ac_send_disc_cmd_p_set_x,
 	[2] = llc_conn_disc,
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 42dc2e45c92..75baa2b0574 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -454,7 +454,7 @@ static int llc_exec_conn_trans_actions(struct sock *sk,
 				       struct sk_buff *skb)
 {
 	int rc = 0;
-	llc_conn_action_t *next_action;
+	const llc_conn_action_t *next_action;
 
 	for (next_action = trans->ev_actions;
 	     next_action && *next_action; next_action++) {
-- 
cgit v1.2.3-70-g09d2


From 9b373069350d747c4e7ad7ea59f0fa348e860383 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 10 Dec 2014 09:43:57 -0800
Subject: llc: Make llc_conn_ev_qfyr_t function pointer arrays const

It's better when function pointer arrays aren't modifiable.

Net change from original:

$ size net/llc/built-in.o.*
   text	   data	    bss	    dec	    hex	filename
  61065	  12886	   1344	  75295	  1261f	net/llc/built-in.o.new
  47113	  27030	   1344	  75487	  126df	net/llc/built-in.o.old

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/llc_c_st.h |   2 +-
 net/llc/llc_c_st.c     | 238 ++++++++++++++++++++++++-------------------------
 net/llc/llc_conn.c     |   2 +-
 3 files changed, 121 insertions(+), 121 deletions(-)

(limited to 'include')

diff --git a/include/net/llc_c_st.h b/include/net/llc_c_st.h
index 60e2ebb1d9b..48f3f891b2f 100644
--- a/include/net/llc_c_st.h
+++ b/include/net/llc_c_st.h
@@ -35,7 +35,7 @@
 struct llc_conn_state_trans {
 	llc_conn_ev_t	   ev;
 	u8		   next_state;
-	llc_conn_ev_qfyr_t *ev_qualifiers;
+	const llc_conn_ev_qfyr_t *ev_qualifiers;
 	const llc_conn_action_t  *ev_actions;
 };
 
diff --git a/net/llc/llc_c_st.c b/net/llc/llc_c_st.c
index 3ae257dd9d4..2467573b5f8 100644
--- a/net/llc/llc_c_st.c
+++ b/net/llc/llc_c_st.c
@@ -234,7 +234,7 @@ static struct llc_conn_state_trans llc_common_state_trans_9 = {
 
 /* State transitions for LLC_CONN_EV_RX_XXX_RSP_Fbit_SET_1 event */
 #if 0
-static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_10[] = {
+static const llc_conn_ev_qfyr_t llc_common_ev_qfyrs_10[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -256,7 +256,7 @@ static struct llc_conn_state_trans llc_common_state_trans_10 = {
 #endif
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11a[] = {
+static const llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11a[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = NULL,
 };
@@ -278,7 +278,7 @@ static struct llc_conn_state_trans llc_common_state_trans_11a = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11b[] = {
+static const llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11b[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = NULL,
 };
@@ -300,7 +300,7 @@ static struct llc_conn_state_trans llc_common_state_trans_11b = {
 };
 
 /* State transitions for LLC_CONN_EV_REJ_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11c[] = {
+static const llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11c[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = NULL,
 };
@@ -322,7 +322,7 @@ static struct llc_conn_state_trans llc_common_state_trans_11c = {
 };
 
 /* State transitions for LLC_CONN_EV_BUSY_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11d[] = {
+static const llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11d[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = NULL,
 };
@@ -461,7 +461,7 @@ static struct llc_conn_state_trans llc_setup_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = llc_conn_ev_qlfy_set_status_conn,
 	[2] = NULL,
@@ -485,7 +485,7 @@ static struct llc_conn_state_trans llc_setup_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_3[] = {
+static const llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_3[] = {
 	[0] = llc_conn_ev_qlfy_s_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_conn,
 	[2] = NULL,
@@ -506,7 +506,7 @@ static struct llc_conn_state_trans llc_setup_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_4[] = {
+static const llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_4[] = {
 	[0] = llc_conn_ev_qlfy_set_status_disc,
 	[1] = NULL,
 };
@@ -527,7 +527,7 @@ static struct llc_conn_state_trans llc_setup_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_5[] = {
+static const llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_5[] = {
 	[0] = llc_conn_ev_qlfy_set_status_disc,
 	[1] = NULL,
 };
@@ -547,7 +547,7 @@ static struct llc_conn_state_trans llc_setup_state_trans_5 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_7[] = {
+static const llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_7[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = llc_conn_ev_qlfy_s_flag_eq_0,
 	[2] = NULL,
@@ -568,7 +568,7 @@ static struct llc_conn_state_trans llc_setup_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_8[] = {
+static const llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_8[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = llc_conn_ev_qlfy_s_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_set_status_failed,
@@ -609,7 +609,7 @@ static struct llc_conn_state_trans *llc_setup_state_transitions[] = {
 
 /* LLC_CONN_STATE_NORMAL transitions */
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_1[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_1[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_last_frame_eq_0,
@@ -630,7 +630,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_last_frame_eq_1,
@@ -651,7 +651,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_2_1[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_2_1[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_remote_busy,
 	[2] = NULL,
@@ -668,7 +668,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_2_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_DETECTED event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_3[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_3[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -688,7 +688,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_DETECTED event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_4[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_4[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -708,7 +708,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -731,7 +731,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_5a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -754,7 +754,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_5b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5c[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -777,7 +777,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_5c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_6a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_6a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -798,7 +798,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_6a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_6b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_6b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -835,7 +835,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_8a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_8a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
@@ -858,7 +858,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_8a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_8b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_8b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -871,7 +871,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_8b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_9a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_9a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -892,7 +892,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_9a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_9b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_9b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -960,7 +960,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_11b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_11c[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_11c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -1028,7 +1028,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_13b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_13c[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_13c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -1065,7 +1065,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_14 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_15a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_15a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -1088,7 +1088,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_15a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_15b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_15b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
@@ -1111,7 +1111,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_15b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_16a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_16a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -1133,7 +1133,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_16a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_16b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_16b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -1172,7 +1172,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_17 = {
 };
 
 /* State transitions for LLC_CONN_EV_INIT_P_F_CYCLE event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_18[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_18[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -1191,7 +1191,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_18 = {
 };
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_19[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_19[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
@@ -1213,7 +1213,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_19 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_20a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_20a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
@@ -1236,7 +1236,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_20a = {
 };
 
 /* State transitions for LLC_CONN_EV_BUSY_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_20b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_20b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
@@ -1259,7 +1259,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_20b = {
 };
 
 /* State transitions for LLC_CONN_EV_TX_BUFF_FULL event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_21[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_21[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -1342,7 +1342,7 @@ static struct llc_conn_state_trans *llc_normal_state_transitions[] = {
 
 /* LLC_CONN_STATE_BUSY transitions */
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_1[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_1[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = NULL,
@@ -1362,7 +1362,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[2] = NULL,
@@ -1382,7 +1382,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_2_1[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_2_1[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_remote_busy,
 	[2] = NULL,
@@ -1399,7 +1399,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_2_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_3[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_3[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = NULL,
@@ -1419,7 +1419,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_4[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_4[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[2] = NULL,
@@ -1439,7 +1439,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_5[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_5[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = NULL,
@@ -1458,7 +1458,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_5 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_6[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_6[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[2] = NULL,
@@ -1477,7 +1477,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_7[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_7[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_2,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = NULL,
@@ -1496,7 +1496,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_8[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_8[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_2,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[2] = NULL,
@@ -1515,7 +1515,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_8 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_X_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_9a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_9a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
@@ -1537,7 +1537,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_9a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_9b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_9b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -1559,7 +1559,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_9b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_10a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_10a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -1579,7 +1579,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_10a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_10b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_10b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -1632,7 +1632,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_12 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_13a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_13a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
@@ -1657,7 +1657,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_13a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_13b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_13b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -1682,7 +1682,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_13b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_14a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_14a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -1705,7 +1705,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_14a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_14b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_14b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -1758,7 +1758,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_15b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_15c[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_15c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -1823,7 +1823,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_17b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_17c[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_17c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -1858,7 +1858,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_18 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_19a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_19a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -1880,7 +1880,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_19a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_19b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_19b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
@@ -1902,7 +1902,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_19b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_20a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_20a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -1923,7 +1923,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_20a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_20b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_20b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -1961,7 +1961,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_21 = {
 };
 
 /* State transitions for LLC_CONN_EV_INIT_P_F_CYCLE event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_22[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_22[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -1980,7 +1980,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_22 = {
 };
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_23[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_23[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
@@ -2001,7 +2001,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_23 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_24a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_24a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
@@ -2023,7 +2023,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_24a = {
 };
 
 /* State transitions for LLC_CONN_EV_BUSY_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_24b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_24b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
@@ -2045,7 +2045,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_24b = {
 };
 
 /* State transitions for LLC_CONN_EV_REJ_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_25[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_25[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
@@ -2068,7 +2068,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_25 = {
 };
 
 /* State transitions for LLC_CONN_EV_REJ_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_26[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_26[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
@@ -2155,7 +2155,7 @@ static struct llc_conn_state_trans *llc_busy_state_transitions[] = {
 
 /* LLC_CONN_STATE_REJ transitions */
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_1[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_1[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = NULL,
@@ -2174,7 +2174,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[2] = NULL,
@@ -2193,7 +2193,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_2_1[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_2_1[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_remote_busy,
 	[2] = NULL,
@@ -2211,7 +2211,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_2_1 = {
 
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_DETECTED event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_3[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_3[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -2230,7 +2230,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_DETECTED event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_4[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_4[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -2279,7 +2279,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_5b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_5c[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_5c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -2313,7 +2313,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_7a[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_7a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
@@ -2338,7 +2338,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_7a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_7b[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_7b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -2362,7 +2362,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_7b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_8a[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_8a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -2384,7 +2384,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_8a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_8b[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_8b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -2453,7 +2453,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_10b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_10c[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_10c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -2518,7 +2518,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_12b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_12c[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_12c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -2553,7 +2553,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_13 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_14a[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_14a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -2575,7 +2575,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_14a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_14b[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_14b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
@@ -2597,7 +2597,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_14b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_15a[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_15a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -2618,7 +2618,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_15a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_15b[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_15b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
@@ -2655,7 +2655,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_16 = {
 };
 
 /* State transitions for LLC_CONN_EV_INIT_P_F_CYCLE event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_17[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_17[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -2674,7 +2674,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_17 = {
 };
 
 /* State transitions for LLC_CONN_EV_REJ_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_18[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_18[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
@@ -2696,7 +2696,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_18 = {
 };
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_19[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_19[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
@@ -2718,7 +2718,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_19 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_20a[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_20a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
@@ -2741,7 +2741,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_20a = {
 };
 
 /* State transitions for LLC_CONN_EV_BUSY_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_20b[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_20b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
@@ -2826,7 +2826,7 @@ static struct llc_conn_state_trans *llc_reject_state_transitions[] = {
 
 /* LLC_CONN_STATE_AWAIT transitions */
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_await_ev_qfyrs_1_0[] = {
+static const llc_conn_ev_qfyr_t llc_await_ev_qfyrs_1_0[] = {
 	[0] = llc_conn_ev_qlfy_set_status_refuse,
 	[1] = NULL,
 };
@@ -3182,7 +3182,7 @@ static struct llc_conn_state_trans llc_await_state_trans_13 = {
 };
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_await_ev_qfyrs_14[] = {
+static const llc_conn_ev_qfyr_t llc_await_ev_qfyrs_14[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
@@ -3255,7 +3255,7 @@ static struct llc_conn_state_trans *llc_await_state_transitions[] = {
 
 /* LLC_CONN_STATE_AWAIT_BUSY transitions */
 /* State transitions for LLC_CONN_EV_DATA_CONN_REQ event */
-static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_1_0[] = {
+static const llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_1_0[] = {
 	[0] = llc_conn_ev_qlfy_set_status_refuse,
 	[1] = NULL,
 };
@@ -3271,7 +3271,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_1_0 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_1[] = {
+static const llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_1[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_1,
 	[1] = NULL,
 };
@@ -3290,7 +3290,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_0,
 	[1] = NULL,
 };
@@ -3308,7 +3308,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_3[] = {
+static const llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_3[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_2,
 	[1] = NULL,
 };
@@ -3656,7 +3656,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_15 = {
 };
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_16[] = {
+static const llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_16[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
@@ -3731,7 +3731,7 @@ static struct llc_conn_state_trans *llc_await_busy_state_transitions[] = {
 
 /* ----------------- LLC_CONN_STATE_AWAIT_REJ transitions --------------- */
 /* State transitions for LLC_CONN_EV_DATA_CONN_REQ event */
-static llc_conn_ev_qfyr_t llc_await_reject_ev_qfyrs_1_0[] = {
+static const llc_conn_ev_qfyr_t llc_await_reject_ev_qfyrs_1_0[] = {
 	[0] = llc_conn_ev_qlfy_set_status_refuse,
 	[1] = NULL,
 };
@@ -4083,7 +4083,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_12 = {
 };
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_await_rejct_ev_qfyrs_13[] = {
+static const llc_conn_ev_qfyr_t llc_await_rejct_ev_qfyrs_13[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
@@ -4157,7 +4157,7 @@ static struct llc_conn_state_trans *llc_await_rejct_state_transitions[] = {
 /* LLC_CONN_STATE_D_CONN transitions */
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event,
  * cause_flag = 1 */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_1[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_1[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_conflict,
 	[2] = NULL,
@@ -4181,7 +4181,7 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_1 = {
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event,
  * cause_flag = 0
  */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_1_1[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_1_1[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_set_status_conflict,
 	[2] = NULL,
@@ -4204,7 +4204,7 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_1_1 = {
 /* State transitions for LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X event,
  * cause_flag = 1
  */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[2] = llc_conn_ev_qlfy_set_status_disc,
@@ -4228,7 +4228,7 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_2 = {
 /* State transitions for LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X event,
  * cause_flag = 0
  */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_2_1[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_2_1[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_set_status_disc,
@@ -4264,7 +4264,7 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_3 = {
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event,
  * cause_flag = 1
  */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_4[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_4[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_disc,
 	[2] = NULL,
@@ -4287,7 +4287,7 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_4 = {
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event,
  * cause_flag = 0
  */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_4_1[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_4_1[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_set_status_disc,
 	[2] = NULL,
@@ -4310,7 +4310,7 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_4_1 = {
  * State transition for
  * LLC_CONN_EV_DATA_CONN_REQ event
  */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_5[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_5[] = {
 	[0] = llc_conn_ev_qlfy_set_status_refuse,
 	[1] = NULL,
 };
@@ -4326,7 +4326,7 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_5 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_6[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_6[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
@@ -4346,7 +4346,7 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event, cause_flag = 1 */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_7[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_7[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[2] = llc_conn_ev_qlfy_set_status_failed,
@@ -4367,7 +4367,7 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event, cause_flag = 0 */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_8[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_8[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_set_status_failed,
@@ -4429,7 +4429,7 @@ static struct llc_conn_state_trans llc_rst_state_trans_1 = {
 /* State transitions for LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X event,
  * cause_flag = 1
  */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[2] = llc_conn_ev_qlfy_set_status_conn,
@@ -4457,7 +4457,7 @@ static struct llc_conn_state_trans llc_rst_state_trans_2 = {
 /* State transitions for LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X event,
  * cause_flag = 0
  */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_2_1[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_2_1[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_set_status_rst_done,
@@ -4483,7 +4483,7 @@ static struct llc_conn_state_trans llc_rst_state_trans_2_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_3[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_3[] = {
 	[0] = llc_conn_ev_qlfy_s_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_rst_done,
 	[2] = NULL,
@@ -4505,7 +4505,7 @@ static struct llc_conn_state_trans llc_rst_state_trans_3 = {
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event,
  * cause_flag = 1
  */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_4[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_4[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_disc,
 	[2] = NULL,
@@ -4528,7 +4528,7 @@ static struct llc_conn_state_trans llc_rst_state_trans_4 = {
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event,
  * cause_flag = 0
  */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_4_1[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_4_1[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_set_status_refuse,
 	[2] = NULL,
@@ -4551,7 +4551,7 @@ static struct llc_conn_state_trans llc_rst_state_trans_4_1 = {
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event,
  * cause_flag = 1
  */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_5[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_5[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_disc,
 	[2] = NULL,
@@ -4574,7 +4574,7 @@ static struct llc_conn_state_trans llc_rst_state_trans_5 = {
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event,
  * cause_flag = 0
  */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_5_1[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_5_1[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_set_status_refuse,
 	[2] = NULL,
@@ -4594,7 +4594,7 @@ static struct llc_conn_state_trans llc_rst_state_trans_5_1 = {
 };
 
 /* State transitions for DATA_CONN_REQ event */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_6[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_6[] = {
 	[0] = llc_conn_ev_qlfy_set_status_refuse,
 	[1] = NULL,
 };
@@ -4610,7 +4610,7 @@ static struct llc_conn_state_trans llc_rst_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_7[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_7[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = llc_conn_ev_qlfy_s_flag_eq_0,
 	[2] = NULL,
@@ -4631,7 +4631,7 @@ static struct llc_conn_state_trans llc_rst_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_8[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_8[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = llc_conn_ev_qlfy_s_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_cause_flag_eq_1,
@@ -4652,7 +4652,7 @@ static struct llc_conn_state_trans llc_rst_state_trans_8 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_8_1[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_8_1[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = llc_conn_ev_qlfy_s_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_cause_flag_eq_0,
@@ -4786,7 +4786,7 @@ static struct llc_conn_state_trans llc_error_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_error_ev_qfyrs_7[] = {
+static const llc_conn_ev_qfyr_t llc_error_ev_qfyrs_7[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
@@ -4806,7 +4806,7 @@ static struct llc_conn_state_trans llc_error_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_error_ev_qfyrs_8[] = {
+static const llc_conn_ev_qfyr_t llc_error_ev_qfyrs_8[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = NULL,
 };
@@ -4828,7 +4828,7 @@ static struct llc_conn_state_trans llc_error_state_trans_8 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_CONN_REQ event */
-static llc_conn_ev_qfyr_t llc_error_ev_qfyrs_9[] = {
+static const llc_conn_ev_qfyr_t llc_error_ev_qfyrs_9[] = {
 	[0] = llc_conn_ev_qlfy_set_status_refuse,
 	[1] = NULL,
 };
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 75baa2b0574..81a61fce3af 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -406,7 +406,7 @@ static struct llc_conn_state_trans *llc_qualify_conn_ev(struct sock *sk,
 							struct sk_buff *skb)
 {
 	struct llc_conn_state_trans **next_trans;
-	llc_conn_ev_qfyr_t *next_qualifier;
+	const llc_conn_ev_qfyr_t *next_qualifier;
 	struct llc_conn_state_ev *ev = llc_conn_ev(skb);
 	struct llc_sock *llc = llc_sk(sk);
 	struct llc_conn_state *curr_state =
-- 
cgit v1.2.3-70-g09d2


From 22bbf5f3e4e4db4a94f18d7b1ba21b5bd5fd934b Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 10 Dec 2014 09:55:50 -0800
Subject: llc: Make llc_sap_action_t function pointer arrays const

It's better when function pointer arrays aren't modifiable.

Net change:

$ size net/llc/built-in.o.*
   text	   data	    bss	    dec	    hex	filename
  61193	  12758	   1344	  75295	  1261f	net/llc/built-in.o.new
  47113	  27030	   1344	  75487	  126df	net/llc/built-in.o.old

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/llc_s_st.h |  2 +-
 net/llc/llc_s_st.c     | 20 ++++++++++----------
 net/llc/llc_sap.c      |  2 +-
 3 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/llc_s_st.h b/include/net/llc_s_st.h
index 567c681f1f3..c4359e20301 100644
--- a/include/net/llc_s_st.h
+++ b/include/net/llc_s_st.h
@@ -19,7 +19,7 @@
 struct llc_sap_state_trans {
 	llc_sap_ev_t	  ev;
 	u8		  next_state;
-	llc_sap_action_t *ev_actions;
+	const llc_sap_action_t *ev_actions;
 };
 
 struct llc_sap_state {
diff --git a/net/llc/llc_s_st.c b/net/llc/llc_s_st.c
index 135f7d80069..308c616883a 100644
--- a/net/llc/llc_s_st.c
+++ b/net/llc/llc_s_st.c
@@ -29,7 +29,7 @@ static struct llc_sap_state_trans llc_sap_state_trans_end;
 /* state LLC_SAP_STATE_INACTIVE transition for
  * LLC_SAP_EV_ACTIVATION_REQ event
  */
-static llc_sap_action_t llc_sap_inactive_state_actions_1[] = {
+static const llc_sap_action_t llc_sap_inactive_state_actions_1[] = {
 	[0] = llc_sap_action_report_status,
 	[1] = NULL,
 };
@@ -47,7 +47,7 @@ static struct llc_sap_state_trans *llc_sap_inactive_state_transitions[] = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_RX_UI event */
-static llc_sap_action_t llc_sap_active_state_actions_1[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_1[] = {
 	[0] = llc_sap_action_unitdata_ind,
 	[1] = NULL,
 };
@@ -59,7 +59,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_1 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_UNITDATA_REQ event */
-static llc_sap_action_t llc_sap_active_state_actions_2[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_2[] = {
 	[0] = llc_sap_action_send_ui,
 	[1] = NULL,
 };
@@ -71,7 +71,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_2 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_XID_REQ event */
-static llc_sap_action_t llc_sap_active_state_actions_3[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_3[] = {
 	[0] = llc_sap_action_send_xid_c,
 	[1] = NULL,
 };
@@ -83,7 +83,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_3 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_RX_XID_C event */
-static llc_sap_action_t llc_sap_active_state_actions_4[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_4[] = {
 	[0] = llc_sap_action_send_xid_r,
 	[1] = NULL,
 };
@@ -95,7 +95,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_4 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_RX_XID_R event */
-static llc_sap_action_t llc_sap_active_state_actions_5[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_5[] = {
 	[0] = llc_sap_action_xid_ind,
 	[1] = NULL,
 };
@@ -107,7 +107,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_5 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_TEST_REQ event */
-static llc_sap_action_t llc_sap_active_state_actions_6[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_6[] = {
 	[0] = llc_sap_action_send_test_c,
 	[1] = NULL,
 };
@@ -119,7 +119,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_6 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_RX_TEST_C event */
-static llc_sap_action_t llc_sap_active_state_actions_7[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_7[] = {
 	[0] = llc_sap_action_send_test_r,
 	[1] = NULL,
 };
@@ -131,7 +131,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_7 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_RX_TEST_R event */
-static llc_sap_action_t llc_sap_active_state_actions_8[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_8[] = {
 	[0] = llc_sap_action_test_ind,
 	[1] = NULL,
 };
@@ -145,7 +145,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_8 = {
 /* state LLC_SAP_STATE_ACTIVE transition for
  * LLC_SAP_EV_DEACTIVATION_REQ event
  */
-static llc_sap_action_t llc_sap_active_state_actions_9[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_9[] = {
 	[0] = llc_sap_action_report_status,
 	[1] = NULL,
 };
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index 06033f6c845..d0e1e804ebd 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -146,7 +146,7 @@ static int llc_exec_sap_trans_actions(struct llc_sap *sap,
 				      struct sk_buff *skb)
 {
 	int rc = 0;
-	llc_sap_action_t *next_action = trans->ev_actions;
+	const llc_sap_action_t *next_action = trans->ev_actions;
 
 	for (; next_action && *next_action; next_action++)
 		if ((*next_action)(sap, skb))
-- 
cgit v1.2.3-70-g09d2


From 785c20a08bead1e58ad53f2dc324782da7a0c9ea Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 10 Dec 2014 10:28:58 -0800
Subject: irda: Convert function pointer arrays and uses to const

Making things const is a good thing.

(x86-64 defconfig with all irda)
$ size net/irda/built-in.o*
   text	   data	    bss	    dec	    hex	filename
 109276	   1868	    244	 111388	  1b31c	net/irda/built-in.o.new
 108828	   2316	    244	 111388	  1b31c	net/irda/built-in.o.old

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/irda/parameters.h  | 6 +++---
 net/irda/ircomm/ircomm_param.c | 8 ++++----
 net/irda/irttp.c               | 6 ++++--
 net/irda/parameters.c          | 8 ++++----
 net/irda/qos.c                 | 6 +++---
 5 files changed, 18 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/irda/parameters.h b/include/net/irda/parameters.h
index 42713c931d1..2d9cd0007cb 100644
--- a/include/net/irda/parameters.h
+++ b/include/net/irda/parameters.h
@@ -71,17 +71,17 @@ typedef int (*PV_HANDLER)(void *self, __u8 *buf, int len, __u8 pi,
 			  PV_TYPE type, PI_HANDLER func);
 
 typedef struct {
-	PI_HANDLER func;  /* Handler for this parameter identifier */
+	const PI_HANDLER func;  /* Handler for this parameter identifier */
 	PV_TYPE    type;  /* Data type for this parameter */
 } pi_minor_info_t;
 
 typedef struct {
-	pi_minor_info_t *pi_minor_call_table;
+	const pi_minor_info_t *pi_minor_call_table;
 	int len;
 } pi_major_info_t;
 
 typedef struct {
-	pi_major_info_t *tables;
+	const pi_major_info_t *tables;
 	int              len;
 	__u8             pi_mask;
 	int              pi_major_offset;
diff --git a/net/irda/ircomm/ircomm_param.c b/net/irda/ircomm/ircomm_param.c
index 27be782be7e..3c4caa60c92 100644
--- a/net/irda/ircomm/ircomm_param.c
+++ b/net/irda/ircomm/ircomm_param.c
@@ -61,12 +61,12 @@ static int ircomm_param_dte(void *instance, irda_param_t *param, int get);
 static int ircomm_param_dce(void *instance, irda_param_t *param, int get);
 static int ircomm_param_poll(void *instance, irda_param_t *param, int get);
 
-static pi_minor_info_t pi_minor_call_table_common[] = {
+static const pi_minor_info_t pi_minor_call_table_common[] = {
 	{ ircomm_param_service_type, PV_INT_8_BITS },
 	{ ircomm_param_port_type,    PV_INT_8_BITS },
 	{ ircomm_param_port_name,    PV_STRING }
 };
-static pi_minor_info_t pi_minor_call_table_non_raw[] = {
+static const pi_minor_info_t pi_minor_call_table_non_raw[] = {
 	{ ircomm_param_data_rate,    PV_INT_32_BITS | PV_BIG_ENDIAN },
 	{ ircomm_param_data_format,  PV_INT_8_BITS },
 	{ ircomm_param_flow_control, PV_INT_8_BITS },
@@ -74,13 +74,13 @@ static pi_minor_info_t pi_minor_call_table_non_raw[] = {
 	{ ircomm_param_enq_ack,      PV_INT_16_BITS },
 	{ ircomm_param_line_status,  PV_INT_8_BITS }
 };
-static pi_minor_info_t pi_minor_call_table_9_wire[] = {
+static const pi_minor_info_t pi_minor_call_table_9_wire[] = {
 	{ ircomm_param_dte,          PV_INT_8_BITS },
 	{ ircomm_param_dce,          PV_INT_8_BITS },
 	{ ircomm_param_poll,         PV_NO_VALUE },
 };
 
-static pi_major_info_t pi_major_call_table[] = {
+static const pi_major_info_t pi_major_call_table[] = {
 	{ pi_minor_call_table_common,  3 },
 	{ pi_minor_call_table_non_raw, 6 },
 	{ pi_minor_call_table_9_wire,  3 }
diff --git a/net/irda/irttp.c b/net/irda/irttp.c
index 3ef0b08b6bf..b6ab41d5b3a 100644
--- a/net/irda/irttp.c
+++ b/net/irda/irttp.c
@@ -71,11 +71,13 @@ static void irttp_status_indication(void *instance,
 				    LINK_STATUS link, LOCK_STATUS lock);
 
 /* Information for parsing parameters in IrTTP */
-static pi_minor_info_t pi_minor_call_table[] = {
+static const pi_minor_info_t pi_minor_call_table[] = {
 	{ NULL, 0 },                                             /* 0x00 */
 	{ irttp_param_max_sdu_size, PV_INTEGER | PV_BIG_ENDIAN } /* 0x01 */
 };
-static pi_major_info_t pi_major_call_table[] = { { pi_minor_call_table, 2 } };
+static const pi_major_info_t pi_major_call_table[] = {
+	{ pi_minor_call_table, 2 }
+};
 static pi_param_info_t param_info = { pi_major_call_table, 1, 0x0f, 4 };
 
 /************************ GLOBAL PROCEDURES ************************/
diff --git a/net/irda/parameters.c b/net/irda/parameters.c
index 006786bfdd6..16ce32ffe00 100644
--- a/net/irda/parameters.c
+++ b/net/irda/parameters.c
@@ -52,7 +52,7 @@ static int irda_insert_no_value(void *self, __u8 *buf, int len, __u8 pi,
 static int irda_param_unpack(__u8 *buf, char *fmt, ...);
 
 /* Parameter value call table. Must match PV_TYPE */
-static PV_HANDLER pv_extract_table[] = {
+static const PV_HANDLER pv_extract_table[] = {
 	irda_extract_integer, /* Handler for any length integers */
 	irda_extract_integer, /* Handler for 8  bits integers */
 	irda_extract_integer, /* Handler for 16 bits integers */
@@ -62,7 +62,7 @@ static PV_HANDLER pv_extract_table[] = {
 	irda_extract_no_value /* Handler for no value parameters */
 };
 
-static PV_HANDLER pv_insert_table[] = {
+static const PV_HANDLER pv_insert_table[] = {
 	irda_insert_integer, /* Handler for any length integers */
 	irda_insert_integer, /* Handler for 8  bits integers */
 	irda_insert_integer, /* Handler for 16 bits integers */
@@ -449,7 +449,7 @@ static int irda_param_unpack(__u8 *buf, char *fmt, ...)
 int irda_param_insert(void *self, __u8 pi, __u8 *buf, int len,
 		      pi_param_info_t *info)
 {
-	pi_minor_info_t *pi_minor_info;
+	const pi_minor_info_t *pi_minor_info;
 	__u8 pi_minor;
 	__u8 pi_major;
 	int type;
@@ -504,7 +504,7 @@ EXPORT_SYMBOL(irda_param_insert);
 static int irda_param_extract(void *self, __u8 *buf, int len,
 			      pi_param_info_t *info)
 {
-	pi_minor_info_t *pi_minor_info;
+	const pi_minor_info_t *pi_minor_info;
 	__u8 pi_minor;
 	__u8 pi_major;
 	int type;
diff --git a/net/irda/qos.c b/net/irda/qos.c
index 5ed6c9a7bae..25ba8509ad3 100644
--- a/net/irda/qos.c
+++ b/net/irda/qos.c
@@ -122,7 +122,7 @@ static __u32 max_line_capacities[10][4] = {
 	{ 800000, 400000, 160000, 80000 }, /* 16000000 bps */
 };
 
-static pi_minor_info_t pi_minor_call_table_type_0[] = {
+static const pi_minor_info_t pi_minor_call_table_type_0[] = {
 	{ NULL, 0 },
 /* 01 */{ irlap_param_baud_rate,       PV_INTEGER | PV_LITTLE_ENDIAN },
 	{ NULL, 0 },
@@ -134,7 +134,7 @@ static pi_minor_info_t pi_minor_call_table_type_0[] = {
 /* 08 */{ irlap_param_link_disconnect, PV_INT_8_BITS }
 };
 
-static pi_minor_info_t pi_minor_call_table_type_1[] = {
+static const pi_minor_info_t pi_minor_call_table_type_1[] = {
 	{ NULL, 0 },
 	{ NULL, 0 },
 /* 82 */{ irlap_param_max_turn_time,   PV_INT_8_BITS },
@@ -144,7 +144,7 @@ static pi_minor_info_t pi_minor_call_table_type_1[] = {
 /* 86 */{ irlap_param_min_turn_time,   PV_INT_8_BITS },
 };
 
-static pi_major_info_t pi_major_call_table[] = {
+static const pi_major_info_t pi_major_call_table[] = {
 	{ pi_minor_call_table_type_0, 9 },
 	{ pi_minor_call_table_type_1, 7 },
 };
-- 
cgit v1.2.3-70-g09d2


From 3e32cb2e0a12b6915056ff04601cf1bb9b44f967 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 10 Dec 2014 15:42:31 -0800
Subject: mm: memcontrol: lockless page counters

Memory is internally accounted in bytes, using spinlock-protected 64-bit
counters, even though the smallest accounting delta is a page.  The
counter interface is also convoluted and does too many things.

Introduce a new lockless word-sized page counter API, then change all
memory accounting over to it.  The translation from and to bytes then only
happens when interfacing with userspace.

The removed locking overhead is noticable when scaling beyond the per-cpu
charge caches - on a 4-socket machine with 144-threads, the following test
shows the performance differences of 288 memcgs concurrently running a
page fault benchmark:

vanilla:

   18631648.500498      task-clock (msec)         #  140.643 CPUs utilized            ( +-  0.33% )
         1,380,638      context-switches          #    0.074 K/sec                    ( +-  0.75% )
            24,390      cpu-migrations            #    0.001 K/sec                    ( +-  8.44% )
     1,843,305,768      page-faults               #    0.099 M/sec                    ( +-  0.00% )
50,134,994,088,218      cycles                    #    2.691 GHz                      ( +-  0.33% )
   <not supported>      stalled-cycles-frontend
   <not supported>      stalled-cycles-backend
 8,049,712,224,651      instructions              #    0.16  insns per cycle          ( +-  0.04% )
 1,586,970,584,979      branches                  #   85.176 M/sec                    ( +-  0.05% )
     1,724,989,949      branch-misses             #    0.11% of all branches          ( +-  0.48% )

     132.474343877 seconds time elapsed                                          ( +-  0.21% )

lockless:

   12195979.037525      task-clock (msec)         #  133.480 CPUs utilized            ( +-  0.18% )
           832,850      context-switches          #    0.068 K/sec                    ( +-  0.54% )
            15,624      cpu-migrations            #    0.001 K/sec                    ( +- 10.17% )
     1,843,304,774      page-faults               #    0.151 M/sec                    ( +-  0.00% )
32,811,216,801,141      cycles                    #    2.690 GHz                      ( +-  0.18% )
   <not supported>      stalled-cycles-frontend
   <not supported>      stalled-cycles-backend
 9,999,265,091,727      instructions              #    0.30  insns per cycle          ( +-  0.10% )
 2,076,759,325,203      branches                  #  170.282 M/sec                    ( +-  0.12% )
     1,656,917,214      branch-misses             #    0.08% of all branches          ( +-  0.55% )

      91.369330729 seconds time elapsed                                          ( +-  0.45% )

On top of improved scalability, this also gets rid of the icky long long
types in the very heart of memcg, which is great for 32 bit and also makes
the code a lot more readable.

Notable differences between the old and new API:

- res_counter_charge() and res_counter_charge_nofail() become
  page_counter_try_charge() and page_counter_charge() resp. to match
  the more common kernel naming scheme of try_do()/do()

- res_counter_uncharge_until() is only ever used to cancel a local
  counter and never to uncharge bigger segments of a hierarchy, so
  it's replaced by the simpler page_counter_cancel()

- res_counter_set_limit() is replaced by page_counter_limit(), which
  expects its callers to serialize against themselves

- res_counter_memparse_write_strategy() is replaced by
  page_counter_limit(), which rounds down to the nearest page size -
  rather than up.  This is more reasonable for explicitely requested
  hard upper limits.

- to keep charging light-weight, page_counter_try_charge() charges
  speculatively, only to roll back if the result exceeds the limit.
  Because of this, a failing bigger charge can temporarily lock out
  smaller charges that would otherwise succeed.  The error is bounded
  to the difference between the smallest and the biggest possible
  charge size, so for memcg, this means that a failing THP charge can
  send base page charges into reclaim upto 2MB (4MB) before the limit
  would have been reached.  This should be acceptable.

[akpm@linux-foundation.org: add includes for WARN_ON_ONCE and memparse]
[akpm@linux-foundation.org: add includes for WARN_ON_ONCE, memparse, strncmp, and PAGE_SIZE]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/cgroups/memory.txt |   4 +-
 include/linux/memcontrol.h       |   5 +-
 include/linux/page_counter.h     |  51 ++++
 include/net/sock.h               |  26 +-
 init/Kconfig                     |   5 +-
 mm/Makefile                      |   1 +
 mm/memcontrol.c                  | 633 ++++++++++++++++++---------------------
 mm/page_counter.c                | 207 +++++++++++++
 net/ipv4/tcp_memcontrol.c        |  87 +++---
 9 files changed, 615 insertions(+), 404 deletions(-)
 create mode 100644 include/linux/page_counter.h
 create mode 100644 mm/page_counter.c

(limited to 'include')

diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 02ab997a1ed..f624727ab40 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -52,9 +52,9 @@ Brief summary of control files.
  tasks				 # attach a task(thread) and show list of threads
  cgroup.procs			 # show list of processes
  cgroup.event_control		 # an interface for event_fd()
- memory.usage_in_bytes		 # show current res_counter usage for memory
+ memory.usage_in_bytes		 # show current usage for memory
 				 (See 5.5 for details)
- memory.memsw.usage_in_bytes	 # show current res_counter usage for memory+Swap
+ memory.memsw.usage_in_bytes	 # show current usage for memory+Swap
 				 (See 5.5 for details)
  memory.limit_in_bytes		 # set/show limit of memory usage
  memory.memsw.limit_in_bytes	 # set/show limit of memory+Swap usage
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6b75640ef5a..ea007615e8f 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -447,9 +447,8 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
 	/*
 	 * __GFP_NOFAIL allocations will move on even if charging is not
 	 * possible. Therefore we don't even try, and have this allocation
-	 * unaccounted. We could in theory charge it with
-	 * res_counter_charge_nofail, but we hope those allocations are rare,
-	 * and won't be worth the trouble.
+	 * unaccounted. We could in theory charge it forcibly, but we hope
+	 * those allocations are rare, and won't be worth the trouble.
 	 */
 	if (gfp & __GFP_NOFAIL)
 		return true;
diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
new file mode 100644
index 00000000000..7cce3be99ff
--- /dev/null
+++ b/include/linux/page_counter.h
@@ -0,0 +1,51 @@
+#ifndef _LINUX_PAGE_COUNTER_H
+#define _LINUX_PAGE_COUNTER_H
+
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+#include <asm/page.h>
+
+struct page_counter {
+	atomic_long_t count;
+	unsigned long limit;
+	struct page_counter *parent;
+
+	/* legacy */
+	unsigned long watermark;
+	unsigned long failcnt;
+};
+
+#if BITS_PER_LONG == 32
+#define PAGE_COUNTER_MAX LONG_MAX
+#else
+#define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE)
+#endif
+
+static inline void page_counter_init(struct page_counter *counter,
+				     struct page_counter *parent)
+{
+	atomic_long_set(&counter->count, 0);
+	counter->limit = PAGE_COUNTER_MAX;
+	counter->parent = parent;
+}
+
+static inline unsigned long page_counter_read(struct page_counter *counter)
+{
+	return atomic_long_read(&counter->count);
+}
+
+int page_counter_cancel(struct page_counter *counter, unsigned long nr_pages);
+void page_counter_charge(struct page_counter *counter, unsigned long nr_pages);
+int page_counter_try_charge(struct page_counter *counter,
+			    unsigned long nr_pages,
+			    struct page_counter **fail);
+int page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
+int page_counter_limit(struct page_counter *counter, unsigned long limit);
+int page_counter_memparse(const char *buf, unsigned long *nr_pages);
+
+static inline void page_counter_reset_watermark(struct page_counter *counter)
+{
+	counter->watermark = page_counter_read(counter);
+}
+
+#endif /* _LINUX_PAGE_COUNTER_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index e6f235ebf6c..7ff44e062a3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -54,8 +54,8 @@
 #include <linux/security.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/page_counter.h>
 #include <linux/memcontrol.h>
-#include <linux/res_counter.h>
 #include <linux/static_key.h>
 #include <linux/aio.h>
 #include <linux/sched.h>
@@ -1062,7 +1062,7 @@ enum cg_proto_flags {
 };
 
 struct cg_proto {
-	struct res_counter	memory_allocated;	/* Current allocated memory. */
+	struct page_counter	memory_allocated;	/* Current allocated memory. */
 	struct percpu_counter	sockets_allocated;	/* Current number of sockets. */
 	int			memory_pressure;
 	long			sysctl_mem[3];
@@ -1214,34 +1214,26 @@ static inline void memcg_memory_allocated_add(struct cg_proto *prot,
 					      unsigned long amt,
 					      int *parent_status)
 {
-	struct res_counter *fail;
-	int ret;
+	page_counter_charge(&prot->memory_allocated, amt);
 
-	ret = res_counter_charge_nofail(&prot->memory_allocated,
-					amt << PAGE_SHIFT, &fail);
-	if (ret < 0)
+	if (page_counter_read(&prot->memory_allocated) >
+	    prot->memory_allocated.limit)
 		*parent_status = OVER_LIMIT;
 }
 
 static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
 					      unsigned long amt)
 {
-	res_counter_uncharge(&prot->memory_allocated, amt << PAGE_SHIFT);
-}
-
-static inline u64 memcg_memory_allocated_read(struct cg_proto *prot)
-{
-	u64 ret;
-	ret = res_counter_read_u64(&prot->memory_allocated, RES_USAGE);
-	return ret >> PAGE_SHIFT;
+	page_counter_uncharge(&prot->memory_allocated, amt);
 }
 
 static inline long
 sk_memory_allocated(const struct sock *sk)
 {
 	struct proto *prot = sk->sk_prot;
+
 	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
-		return memcg_memory_allocated_read(sk->sk_cgrp);
+		return page_counter_read(&sk->sk_cgrp->memory_allocated);
 
 	return atomic_long_read(prot->memory_allocated);
 }
@@ -1255,7 +1247,7 @@ sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status)
 		memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status);
 		/* update the root cgroup regardless */
 		atomic_long_add_return(amt, prot->memory_allocated);
-		return memcg_memory_allocated_read(sk->sk_cgrp);
+		return page_counter_read(&sk->sk_cgrp->memory_allocated);
 	}
 
 	return atomic_long_add_return(amt, prot->memory_allocated);
diff --git a/init/Kconfig b/init/Kconfig
index 903505e66d1..fd9e88791ba 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -978,9 +978,12 @@ config RESOURCE_COUNTERS
 	  This option enables controller independent resource accounting
 	  infrastructure that works with cgroups.
 
+config PAGE_COUNTER
+       bool
+
 config MEMCG
 	bool "Memory Resource Controller for Control Groups"
-	depends on RESOURCE_COUNTERS
+	select PAGE_COUNTER
 	select EVENTFD
 	help
 	  Provides a memory resource controller that manages both anonymous
diff --git a/mm/Makefile b/mm/Makefile
index 8405eb0023a..6d9f40e922f 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -55,6 +55,7 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o
+obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
 obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o vmpressure.o
 obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d6ac0e33e15..4129ad74e93 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -25,7 +25,7 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/res_counter.h>
+#include <linux/page_counter.h>
 #include <linux/memcontrol.h>
 #include <linux/cgroup.h>
 #include <linux/mm.h>
@@ -165,7 +165,7 @@ struct mem_cgroup_per_zone {
 	struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];
 
 	struct rb_node		tree_node;	/* RB tree node */
-	unsigned long long	usage_in_excess;/* Set to the value by which */
+	unsigned long		usage_in_excess;/* Set to the value by which */
 						/* the soft limit is exceeded*/
 	bool			on_tree;
 	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
@@ -198,7 +198,7 @@ static struct mem_cgroup_tree soft_limit_tree __read_mostly;
 
 struct mem_cgroup_threshold {
 	struct eventfd_ctx *eventfd;
-	u64 threshold;
+	unsigned long threshold;
 };
 
 /* For threshold */
@@ -284,10 +284,13 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
  */
 struct mem_cgroup {
 	struct cgroup_subsys_state css;
-	/*
-	 * the counter to account for memory usage
-	 */
-	struct res_counter res;
+
+	/* Accounted resources */
+	struct page_counter memory;
+	struct page_counter memsw;
+	struct page_counter kmem;
+
+	unsigned long soft_limit;
 
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
@@ -295,15 +298,6 @@ struct mem_cgroup {
 	/* css_online() has been completed */
 	int initialized;
 
-	/*
-	 * the counter to account for mem+swap usage.
-	 */
-	struct res_counter memsw;
-
-	/*
-	 * the counter to account for kernel memory usage.
-	 */
-	struct res_counter kmem;
 	/*
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
@@ -650,7 +644,7 @@ static void disarm_kmem_keys(struct mem_cgroup *memcg)
 	 * This check can't live in kmem destruction function,
 	 * since the charges will outlive the cgroup
 	 */
-	WARN_ON(res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0);
+	WARN_ON(page_counter_read(&memcg->kmem));
 }
 #else
 static void disarm_kmem_keys(struct mem_cgroup *memcg)
@@ -706,7 +700,7 @@ soft_limit_tree_from_page(struct page *page)
 
 static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz,
 					 struct mem_cgroup_tree_per_zone *mctz,
-					 unsigned long long new_usage_in_excess)
+					 unsigned long new_usage_in_excess)
 {
 	struct rb_node **p = &mctz->rb_root.rb_node;
 	struct rb_node *parent = NULL;
@@ -755,10 +749,21 @@ static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
 	spin_unlock_irqrestore(&mctz->lock, flags);
 }
 
+static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
+{
+	unsigned long nr_pages = page_counter_read(&memcg->memory);
+	unsigned long soft_limit = ACCESS_ONCE(memcg->soft_limit);
+	unsigned long excess = 0;
+
+	if (nr_pages > soft_limit)
+		excess = nr_pages - soft_limit;
+
+	return excess;
+}
 
 static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 {
-	unsigned long long excess;
+	unsigned long excess;
 	struct mem_cgroup_per_zone *mz;
 	struct mem_cgroup_tree_per_zone *mctz;
 
@@ -769,7 +774,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 	 */
 	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
 		mz = mem_cgroup_page_zoneinfo(memcg, page);
-		excess = res_counter_soft_limit_excess(&memcg->res);
+		excess = soft_limit_excess(memcg);
 		/*
 		 * We have to update the tree if mz is on RB-tree or
 		 * mem is over its softlimit.
@@ -825,7 +830,7 @@ retry:
 	 * position in the tree.
 	 */
 	__mem_cgroup_remove_exceeded(mz, mctz);
-	if (!res_counter_soft_limit_excess(&mz->memcg->res) ||
+	if (!soft_limit_excess(mz->memcg) ||
 	    !css_tryget_online(&mz->memcg->css))
 		goto retry;
 done:
@@ -1492,7 +1497,7 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 	return inactive * inactive_ratio < active;
 }
 
-#define mem_cgroup_from_res_counter(counter, member)	\
+#define mem_cgroup_from_counter(counter, member)	\
 	container_of(counter, struct mem_cgroup, member)
 
 /**
@@ -1504,12 +1509,23 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
  */
 static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
 {
-	unsigned long long margin;
+	unsigned long margin = 0;
+	unsigned long count;
+	unsigned long limit;
 
-	margin = res_counter_margin(&memcg->res);
-	if (do_swap_account)
-		margin = min(margin, res_counter_margin(&memcg->memsw));
-	return margin >> PAGE_SHIFT;
+	count = page_counter_read(&memcg->memory);
+	limit = ACCESS_ONCE(memcg->memory.limit);
+	if (count < limit)
+		margin = limit - count;
+
+	if (do_swap_account) {
+		count = page_counter_read(&memcg->memsw);
+		limit = ACCESS_ONCE(memcg->memsw.limit);
+		if (count <= limit)
+			margin = min(margin, limit - count);
+	}
+
+	return margin;
 }
 
 int mem_cgroup_swappiness(struct mem_cgroup *memcg)
@@ -1644,18 +1660,15 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 
 	rcu_read_unlock();
 
-	pr_info("memory: usage %llukB, limit %llukB, failcnt %llu\n",
-		res_counter_read_u64(&memcg->res, RES_USAGE) >> 10,
-		res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10,
-		res_counter_read_u64(&memcg->res, RES_FAILCNT));
-	pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %llu\n",
-		res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10,
-		res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10,
-		res_counter_read_u64(&memcg->memsw, RES_FAILCNT));
-	pr_info("kmem: usage %llukB, limit %llukB, failcnt %llu\n",
-		res_counter_read_u64(&memcg->kmem, RES_USAGE) >> 10,
-		res_counter_read_u64(&memcg->kmem, RES_LIMIT) >> 10,
-		res_counter_read_u64(&memcg->kmem, RES_FAILCNT));
+	pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
+		K((u64)page_counter_read(&memcg->memory)),
+		K((u64)memcg->memory.limit), memcg->memory.failcnt);
+	pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n",
+		K((u64)page_counter_read(&memcg->memsw)),
+		K((u64)memcg->memsw.limit), memcg->memsw.failcnt);
+	pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n",
+		K((u64)page_counter_read(&memcg->kmem)),
+		K((u64)memcg->kmem.limit), memcg->kmem.failcnt);
 
 	for_each_mem_cgroup_tree(iter, memcg) {
 		pr_info("Memory cgroup stats for ");
@@ -1695,28 +1708,17 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg)
 /*
  * Return the memory (and swap, if configured) limit for a memcg.
  */
-static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
+static unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg)
 {
-	u64 limit;
+	unsigned long limit;
 
-	limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
-
-	/*
-	 * Do not consider swap space if we cannot swap due to swappiness
-	 */
+	limit = memcg->memory.limit;
 	if (mem_cgroup_swappiness(memcg)) {
-		u64 memsw;
+		unsigned long memsw_limit;
 
-		limit += total_swap_pages << PAGE_SHIFT;
-		memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
-
-		/*
-		 * If memsw is finite and limits the amount of swap space
-		 * available to this memcg, return that limit.
-		 */
-		limit = min(limit, memsw);
+		memsw_limit = memcg->memsw.limit;
+		limit = min(limit + total_swap_pages, memsw_limit);
 	}
-
 	return limit;
 }
 
@@ -1740,7 +1742,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	}
 
 	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
-	totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
+	totalpages = mem_cgroup_get_limit(memcg) ? : 1;
 	for_each_mem_cgroup_tree(iter, memcg) {
 		struct css_task_iter it;
 		struct task_struct *task;
@@ -1943,7 +1945,7 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
 		.priority = 0,
 	};
 
-	excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT;
+	excess = soft_limit_excess(root_memcg);
 
 	while (1) {
 		victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
@@ -1974,7 +1976,7 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
 		total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
 						     zone, &nr_scanned);
 		*total_scanned += nr_scanned;
-		if (!res_counter_soft_limit_excess(&root_memcg->res))
+		if (!soft_limit_excess(root_memcg))
 			break;
 	}
 	mem_cgroup_iter_break(root_memcg, victim);
@@ -2316,33 +2318,31 @@ static DEFINE_MUTEX(percpu_charge_mutex);
 static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	struct memcg_stock_pcp *stock;
-	bool ret = true;
+	bool ret = false;
 
 	if (nr_pages > CHARGE_BATCH)
-		return false;
+		return ret;
 
 	stock = &get_cpu_var(memcg_stock);
-	if (memcg == stock->cached && stock->nr_pages >= nr_pages)
+	if (memcg == stock->cached && stock->nr_pages >= nr_pages) {
 		stock->nr_pages -= nr_pages;
-	else /* need to call res_counter_charge */
-		ret = false;
+		ret = true;
+	}
 	put_cpu_var(memcg_stock);
 	return ret;
 }
 
 /*
- * Returns stocks cached in percpu to res_counter and reset cached information.
+ * Returns stocks cached in percpu and reset cached information.
  */
 static void drain_stock(struct memcg_stock_pcp *stock)
 {
 	struct mem_cgroup *old = stock->cached;
 
 	if (stock->nr_pages) {
-		unsigned long bytes = stock->nr_pages * PAGE_SIZE;
-
-		res_counter_uncharge(&old->res, bytes);
+		page_counter_uncharge(&old->memory, stock->nr_pages);
 		if (do_swap_account)
-			res_counter_uncharge(&old->memsw, bytes);
+			page_counter_uncharge(&old->memsw, stock->nr_pages);
 		stock->nr_pages = 0;
 	}
 	stock->cached = NULL;
@@ -2371,7 +2371,7 @@ static void __init memcg_stock_init(void)
 }
 
 /*
- * Cache charges(val) which is from res_counter, to local per_cpu area.
+ * Cache charges(val) to local per_cpu area.
  * This will be consumed by consume_stock() function, later.
  */
 static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
@@ -2431,8 +2431,7 @@ out:
 /*
  * Tries to drain stocked charges in other cpus. This function is asynchronous
  * and just put a work per cpu for draining localy on each cpu. Caller can
- * expects some charges will be back to res_counter later but cannot wait for
- * it.
+ * expects some charges will be back later but cannot wait for it.
  */
 static void drain_all_stock_async(struct mem_cgroup *root_memcg)
 {
@@ -2506,9 +2505,8 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	unsigned int batch = max(CHARGE_BATCH, nr_pages);
 	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
 	struct mem_cgroup *mem_over_limit;
-	struct res_counter *fail_res;
+	struct page_counter *counter;
 	unsigned long nr_reclaimed;
-	unsigned long long size;
 	bool may_swap = true;
 	bool drained = false;
 	int ret = 0;
@@ -2519,16 +2517,15 @@ retry:
 	if (consume_stock(memcg, nr_pages))
 		goto done;
 
-	size = batch * PAGE_SIZE;
 	if (!do_swap_account ||
-	    !res_counter_charge(&memcg->memsw, size, &fail_res)) {
-		if (!res_counter_charge(&memcg->res, size, &fail_res))
+	    !page_counter_try_charge(&memcg->memsw, batch, &counter)) {
+		if (!page_counter_try_charge(&memcg->memory, batch, &counter))
 			goto done_restock;
 		if (do_swap_account)
-			res_counter_uncharge(&memcg->memsw, size);
-		mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
+			page_counter_uncharge(&memcg->memsw, batch);
+		mem_over_limit = mem_cgroup_from_counter(counter, memory);
 	} else {
-		mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
+		mem_over_limit = mem_cgroup_from_counter(counter, memsw);
 		may_swap = false;
 	}
 
@@ -2611,32 +2608,12 @@ done:
 
 static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
-	unsigned long bytes = nr_pages * PAGE_SIZE;
-
 	if (mem_cgroup_is_root(memcg))
 		return;
 
-	res_counter_uncharge(&memcg->res, bytes);
+	page_counter_uncharge(&memcg->memory, nr_pages);
 	if (do_swap_account)
-		res_counter_uncharge(&memcg->memsw, bytes);
-}
-
-/*
- * Cancel chrages in this cgroup....doesn't propagate to parent cgroup.
- * This is useful when moving usage to parent cgroup.
- */
-static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
-					unsigned int nr_pages)
-{
-	unsigned long bytes = nr_pages * PAGE_SIZE;
-
-	if (mem_cgroup_is_root(memcg))
-		return;
-
-	res_counter_uncharge_until(&memcg->res, memcg->res.parent, bytes);
-	if (do_swap_account)
-		res_counter_uncharge_until(&memcg->memsw,
-						memcg->memsw.parent, bytes);
+		page_counter_uncharge(&memcg->memsw, nr_pages);
 }
 
 /*
@@ -2760,8 +2737,6 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 		unlock_page_lru(page, isolated);
 }
 
-static DEFINE_MUTEX(set_limit_mutex);
-
 #ifdef CONFIG_MEMCG_KMEM
 /*
  * The memcg_slab_mutex is held whenever a per memcg kmem cache is created or
@@ -2804,16 +2779,17 @@ static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v)
 }
 #endif
 
-static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
+static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
+			     unsigned long nr_pages)
 {
-	struct res_counter *fail_res;
+	struct page_counter *counter;
 	int ret = 0;
 
-	ret = res_counter_charge(&memcg->kmem, size, &fail_res);
-	if (ret)
+	ret = page_counter_try_charge(&memcg->kmem, nr_pages, &counter);
+	if (ret < 0)
 		return ret;
 
-	ret = try_charge(memcg, gfp, size >> PAGE_SHIFT);
+	ret = try_charge(memcg, gfp, nr_pages);
 	if (ret == -EINTR)  {
 		/*
 		 * try_charge() chose to bypass to root due to OOM kill or
@@ -2830,25 +2806,25 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 		 * when the allocation triggers should have been already
 		 * directed to the root cgroup in memcontrol.h
 		 */
-		res_counter_charge_nofail(&memcg->res, size, &fail_res);
+		page_counter_charge(&memcg->memory, nr_pages);
 		if (do_swap_account)
-			res_counter_charge_nofail(&memcg->memsw, size,
-						  &fail_res);
+			page_counter_charge(&memcg->memsw, nr_pages);
 		ret = 0;
 	} else if (ret)
-		res_counter_uncharge(&memcg->kmem, size);
+		page_counter_uncharge(&memcg->kmem, nr_pages);
 
 	return ret;
 }
 
-static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size)
+static void memcg_uncharge_kmem(struct mem_cgroup *memcg,
+				unsigned long nr_pages)
 {
-	res_counter_uncharge(&memcg->res, size);
+	page_counter_uncharge(&memcg->memory, nr_pages);
 	if (do_swap_account)
-		res_counter_uncharge(&memcg->memsw, size);
+		page_counter_uncharge(&memcg->memsw, nr_pages);
 
 	/* Not down to 0 */
-	if (res_counter_uncharge(&memcg->kmem, size))
+	if (page_counter_uncharge(&memcg->kmem, nr_pages))
 		return;
 
 	/*
@@ -3124,19 +3100,21 @@ static void memcg_schedule_register_cache(struct mem_cgroup *memcg,
 
 int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order)
 {
+	unsigned int nr_pages = 1 << order;
 	int res;
 
-	res = memcg_charge_kmem(cachep->memcg_params->memcg, gfp,
-				PAGE_SIZE << order);
+	res = memcg_charge_kmem(cachep->memcg_params->memcg, gfp, nr_pages);
 	if (!res)
-		atomic_add(1 << order, &cachep->memcg_params->nr_pages);
+		atomic_add(nr_pages, &cachep->memcg_params->nr_pages);
 	return res;
 }
 
 void __memcg_uncharge_slab(struct kmem_cache *cachep, int order)
 {
-	memcg_uncharge_kmem(cachep->memcg_params->memcg, PAGE_SIZE << order);
-	atomic_sub(1 << order, &cachep->memcg_params->nr_pages);
+	unsigned int nr_pages = 1 << order;
+
+	memcg_uncharge_kmem(cachep->memcg_params->memcg, nr_pages);
+	atomic_sub(nr_pages, &cachep->memcg_params->nr_pages);
 }
 
 /*
@@ -3257,7 +3235,7 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
 		return true;
 	}
 
-	ret = memcg_charge_kmem(memcg, gfp, PAGE_SIZE << order);
+	ret = memcg_charge_kmem(memcg, gfp, 1 << order);
 	if (!ret)
 		*_memcg = memcg;
 
@@ -3274,7 +3252,7 @@ void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
 
 	/* The page allocation failed. Revert */
 	if (!page) {
-		memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
+		memcg_uncharge_kmem(memcg, 1 << order);
 		return;
 	}
 	/*
@@ -3307,7 +3285,7 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order)
 		return;
 
 	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
-	memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
+	memcg_uncharge_kmem(memcg, 1 << order);
 }
 #else
 static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg)
@@ -3485,8 +3463,12 @@ static int mem_cgroup_move_parent(struct page *page,
 
 	ret = mem_cgroup_move_account(page, nr_pages,
 				pc, child, parent);
-	if (!ret)
-		__mem_cgroup_cancel_local_charge(child, nr_pages);
+	if (!ret) {
+		/* Take charge off the local counters */
+		page_counter_cancel(&child->memory, nr_pages);
+		if (do_swap_account)
+			page_counter_cancel(&child->memsw, nr_pages);
+	}
 
 	if (nr_pages > 1)
 		compound_unlock_irqrestore(page, flags);
@@ -3516,7 +3498,7 @@ static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
  *
  * Returns 0 on success, -EINVAL on failure.
  *
- * The caller must have charged to @to, IOW, called res_counter_charge() about
+ * The caller must have charged to @to, IOW, called page_counter_charge() about
  * both res and memsw, and called css_get().
  */
 static int mem_cgroup_move_swap_account(swp_entry_t entry,
@@ -3532,7 +3514,7 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry,
 		mem_cgroup_swap_statistics(to, true);
 		/*
 		 * This function is only called from task migration context now.
-		 * It postpones res_counter and refcount handling till the end
+		 * It postpones page_counter and refcount handling till the end
 		 * of task migration(mem_cgroup_clear_mc()) for performance
 		 * improvement. But we cannot postpone css_get(to)  because if
 		 * the process that has been moved to @to does swap-in, the
@@ -3590,60 +3572,57 @@ void mem_cgroup_print_bad_page(struct page *page)
 }
 #endif
 
+static DEFINE_MUTEX(memcg_limit_mutex);
+
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
-				unsigned long long val)
+				   unsigned long limit)
 {
+	unsigned long curusage;
+	unsigned long oldusage;
+	bool enlarge = false;
 	int retry_count;
-	int ret = 0;
-	int children = mem_cgroup_count_children(memcg);
-	u64 curusage, oldusage;
-	int enlarge;
+	int ret;
 
 	/*
 	 * For keeping hierarchical_reclaim simple, how long we should retry
 	 * is depends on callers. We set our retry-count to be function
 	 * of # of children which we should visit in this loop.
 	 */
-	retry_count = MEM_CGROUP_RECLAIM_RETRIES * children;
+	retry_count = MEM_CGROUP_RECLAIM_RETRIES *
+		      mem_cgroup_count_children(memcg);
 
-	oldusage = res_counter_read_u64(&memcg->res, RES_USAGE);
+	oldusage = page_counter_read(&memcg->memory);
 
-	enlarge = 0;
-	while (retry_count) {
+	do {
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			break;
 		}
-		/*
-		 * Rather than hide all in some function, I do this in
-		 * open coded manner. You see what this really does.
-		 * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
-		 */
-		mutex_lock(&set_limit_mutex);
-		if (res_counter_read_u64(&memcg->memsw, RES_LIMIT) < val) {
+
+		mutex_lock(&memcg_limit_mutex);
+		if (limit > memcg->memsw.limit) {
+			mutex_unlock(&memcg_limit_mutex);
 			ret = -EINVAL;
-			mutex_unlock(&set_limit_mutex);
 			break;
 		}
-
-		if (res_counter_read_u64(&memcg->res, RES_LIMIT) < val)
-			enlarge = 1;
-
-		ret = res_counter_set_limit(&memcg->res, val);
-		mutex_unlock(&set_limit_mutex);
+		if (limit > memcg->memory.limit)
+			enlarge = true;
+		ret = page_counter_limit(&memcg->memory, limit);
+		mutex_unlock(&memcg_limit_mutex);
 
 		if (!ret)
 			break;
 
 		try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, true);
 
-		curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
+		curusage = page_counter_read(&memcg->memory);
 		/* Usage is reduced ? */
 		if (curusage >= oldusage)
 			retry_count--;
 		else
 			oldusage = curusage;
-	}
+	} while (retry_count);
+
 	if (!ret && enlarge)
 		memcg_oom_recover(memcg);
 
@@ -3651,52 +3630,53 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 }
 
 static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
-					unsigned long long val)
+					 unsigned long limit)
 {
+	unsigned long curusage;
+	unsigned long oldusage;
+	bool enlarge = false;
 	int retry_count;
-	u64 oldusage, curusage;
-	int children = mem_cgroup_count_children(memcg);
-	int ret = -EBUSY;
-	int enlarge = 0;
+	int ret;
 
 	/* see mem_cgroup_resize_res_limit */
-	retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
-	oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
-	while (retry_count) {
+	retry_count = MEM_CGROUP_RECLAIM_RETRIES *
+		      mem_cgroup_count_children(memcg);
+
+	oldusage = page_counter_read(&memcg->memsw);
+
+	do {
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			break;
 		}
-		/*
-		 * Rather than hide all in some function, I do this in
-		 * open coded manner. You see what this really does.
-		 * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
-		 */
-		mutex_lock(&set_limit_mutex);
-		if (res_counter_read_u64(&memcg->res, RES_LIMIT) > val) {
+
+		mutex_lock(&memcg_limit_mutex);
+		if (limit < memcg->memory.limit) {
+			mutex_unlock(&memcg_limit_mutex);
 			ret = -EINVAL;
-			mutex_unlock(&set_limit_mutex);
 			break;
 		}
-		if (res_counter_read_u64(&memcg->memsw, RES_LIMIT) < val)
-			enlarge = 1;
-		ret = res_counter_set_limit(&memcg->memsw, val);
-		mutex_unlock(&set_limit_mutex);
+		if (limit > memcg->memsw.limit)
+			enlarge = true;
+		ret = page_counter_limit(&memcg->memsw, limit);
+		mutex_unlock(&memcg_limit_mutex);
 
 		if (!ret)
 			break;
 
 		try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, false);
 
-		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+		curusage = page_counter_read(&memcg->memsw);
 		/* Usage is reduced ? */
 		if (curusage >= oldusage)
 			retry_count--;
 		else
 			oldusage = curusage;
-	}
+	} while (retry_count);
+
 	if (!ret && enlarge)
 		memcg_oom_recover(memcg);
+
 	return ret;
 }
 
@@ -3709,7 +3689,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 	unsigned long reclaimed;
 	int loop = 0;
 	struct mem_cgroup_tree_per_zone *mctz;
-	unsigned long long excess;
+	unsigned long excess;
 	unsigned long nr_scanned;
 
 	if (order > 0)
@@ -3763,7 +3743,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 			} while (1);
 		}
 		__mem_cgroup_remove_exceeded(mz, mctz);
-		excess = res_counter_soft_limit_excess(&mz->memcg->res);
+		excess = soft_limit_excess(mz->memcg);
 		/*
 		 * One school of thought says that we should not add
 		 * back the node to the tree if reclaim returns 0.
@@ -3856,7 +3836,6 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
 {
 	int node, zid;
-	u64 usage;
 
 	do {
 		/* This is for making all *used* pages to be on LRU. */
@@ -3888,9 +3867,8 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
 		 * right after the check. RES_USAGE should be safe as we always
 		 * charge before adding to the LRU.
 		 */
-		usage = res_counter_read_u64(&memcg->res, RES_USAGE) -
-			res_counter_read_u64(&memcg->kmem, RES_USAGE);
-	} while (usage > 0);
+	} while (page_counter_read(&memcg->memory) -
+		 page_counter_read(&memcg->kmem) > 0);
 }
 
 /*
@@ -3930,7 +3908,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 	/* we call try-to-free pages for make this cgroup empty */
 	lru_add_drain_all();
 	/* try to free all pages in this cgroup */
-	while (nr_retries && res_counter_read_u64(&memcg->res, RES_USAGE) > 0) {
+	while (nr_retries && page_counter_read(&memcg->memory)) {
 		int progress;
 
 		if (signal_pending(current))
@@ -4001,8 +3979,8 @@ out:
 	return retval;
 }
 
-static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *memcg,
-					       enum mem_cgroup_stat_index idx)
+static unsigned long tree_stat(struct mem_cgroup *memcg,
+			       enum mem_cgroup_stat_index idx)
 {
 	struct mem_cgroup *iter;
 	long val = 0;
@@ -4020,55 +3998,72 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 {
 	u64 val;
 
-	if (!mem_cgroup_is_root(memcg)) {
+	if (mem_cgroup_is_root(memcg)) {
+		val = tree_stat(memcg, MEM_CGROUP_STAT_CACHE);
+		val += tree_stat(memcg, MEM_CGROUP_STAT_RSS);
+		if (swap)
+			val += tree_stat(memcg, MEM_CGROUP_STAT_SWAP);
+	} else {
 		if (!swap)
-			return res_counter_read_u64(&memcg->res, RES_USAGE);
+			val = page_counter_read(&memcg->memory);
 		else
-			return res_counter_read_u64(&memcg->memsw, RES_USAGE);
+			val = page_counter_read(&memcg->memsw);
 	}
-
-	/*
-	 * Transparent hugepages are still accounted for in MEM_CGROUP_STAT_RSS
-	 * as well as in MEM_CGROUP_STAT_RSS_HUGE.
-	 */
-	val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
-	val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS);
-
-	if (swap)
-		val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAP);
-
 	return val << PAGE_SHIFT;
 }
 
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_MAX_USAGE,
+	RES_FAILCNT,
+	RES_SOFT_LIMIT,
+};
 
 static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 			       struct cftype *cft)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-	enum res_type type = MEMFILE_TYPE(cft->private);
-	int name = MEMFILE_ATTR(cft->private);
+	struct page_counter *counter;
 
-	switch (type) {
+	switch (MEMFILE_TYPE(cft->private)) {
 	case _MEM:
-		if (name == RES_USAGE)
-			return mem_cgroup_usage(memcg, false);
-		return res_counter_read_u64(&memcg->res, name);
+		counter = &memcg->memory;
+		break;
 	case _MEMSWAP:
-		if (name == RES_USAGE)
-			return mem_cgroup_usage(memcg, true);
-		return res_counter_read_u64(&memcg->memsw, name);
+		counter = &memcg->memsw;
+		break;
 	case _KMEM:
-		return res_counter_read_u64(&memcg->kmem, name);
+		counter = &memcg->kmem;
 		break;
 	default:
 		BUG();
 	}
+
+	switch (MEMFILE_ATTR(cft->private)) {
+	case RES_USAGE:
+		if (counter == &memcg->memory)
+			return mem_cgroup_usage(memcg, false);
+		if (counter == &memcg->memsw)
+			return mem_cgroup_usage(memcg, true);
+		return (u64)page_counter_read(counter) * PAGE_SIZE;
+	case RES_LIMIT:
+		return (u64)counter->limit * PAGE_SIZE;
+	case RES_MAX_USAGE:
+		return (u64)counter->watermark * PAGE_SIZE;
+	case RES_FAILCNT:
+		return counter->failcnt;
+	case RES_SOFT_LIMIT:
+		return (u64)memcg->soft_limit * PAGE_SIZE;
+	default:
+		BUG();
+	}
 }
 
 #ifdef CONFIG_MEMCG_KMEM
 /* should be called with activate_kmem_mutex held */
 static int __memcg_activate_kmem(struct mem_cgroup *memcg,
-				 unsigned long long limit)
+				 unsigned long nr_pages)
 {
 	int err = 0;
 	int memcg_id;
@@ -4115,7 +4110,7 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg,
 	 * We couldn't have accounted to this cgroup, because it hasn't got the
 	 * active bit set yet, so this should succeed.
 	 */
-	err = res_counter_set_limit(&memcg->kmem, limit);
+	err = page_counter_limit(&memcg->kmem, nr_pages);
 	VM_BUG_ON(err);
 
 	static_key_slow_inc(&memcg_kmem_enabled_key);
@@ -4131,25 +4126,27 @@ out:
 }
 
 static int memcg_activate_kmem(struct mem_cgroup *memcg,
-			       unsigned long long limit)
+			       unsigned long nr_pages)
 {
 	int ret;
 
 	mutex_lock(&activate_kmem_mutex);
-	ret = __memcg_activate_kmem(memcg, limit);
+	ret = __memcg_activate_kmem(memcg, nr_pages);
 	mutex_unlock(&activate_kmem_mutex);
 	return ret;
 }
 
 static int memcg_update_kmem_limit(struct mem_cgroup *memcg,
-				   unsigned long long val)
+				   unsigned long limit)
 {
 	int ret;
 
+	mutex_lock(&memcg_limit_mutex);
 	if (!memcg_kmem_is_active(memcg))
-		ret = memcg_activate_kmem(memcg, val);
+		ret = memcg_activate_kmem(memcg, limit);
 	else
-		ret = res_counter_set_limit(&memcg->kmem, val);
+		ret = page_counter_limit(&memcg->kmem, limit);
+	mutex_unlock(&memcg_limit_mutex);
 	return ret;
 }
 
@@ -4167,13 +4164,13 @@ static int memcg_propagate_kmem(struct mem_cgroup *memcg)
 	 * after this point, because it has at least one child already.
 	 */
 	if (memcg_kmem_is_active(parent))
-		ret = __memcg_activate_kmem(memcg, RES_COUNTER_MAX);
+		ret = __memcg_activate_kmem(memcg, PAGE_COUNTER_MAX);
 	mutex_unlock(&activate_kmem_mutex);
 	return ret;
 }
 #else
 static int memcg_update_kmem_limit(struct mem_cgroup *memcg,
-				   unsigned long long val)
+				   unsigned long limit)
 {
 	return -EINVAL;
 }
@@ -4187,110 +4184,69 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
-	enum res_type type;
-	int name;
-	unsigned long long val;
+	unsigned long nr_pages;
 	int ret;
 
 	buf = strstrip(buf);
-	type = MEMFILE_TYPE(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
+	ret = page_counter_memparse(buf, &nr_pages);
+	if (ret)
+		return ret;
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_LIMIT:
 		if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */
 			ret = -EINVAL;
 			break;
 		}
-		/* This function does all necessary parse...reuse it */
-		ret = res_counter_memparse_write_strategy(buf, &val);
-		if (ret)
+		switch (MEMFILE_TYPE(of_cft(of)->private)) {
+		case _MEM:
+			ret = mem_cgroup_resize_limit(memcg, nr_pages);
 			break;
-		if (type == _MEM)
-			ret = mem_cgroup_resize_limit(memcg, val);
-		else if (type == _MEMSWAP)
-			ret = mem_cgroup_resize_memsw_limit(memcg, val);
-		else if (type == _KMEM)
-			ret = memcg_update_kmem_limit(memcg, val);
-		else
-			return -EINVAL;
-		break;
-	case RES_SOFT_LIMIT:
-		ret = res_counter_memparse_write_strategy(buf, &val);
-		if (ret)
+		case _MEMSWAP:
+			ret = mem_cgroup_resize_memsw_limit(memcg, nr_pages);
 			break;
-		/*
-		 * For memsw, soft limits are hard to implement in terms
-		 * of semantics, for now, we support soft limits for
-		 * control without swap
-		 */
-		if (type == _MEM)
-			ret = res_counter_set_soft_limit(&memcg->res, val);
-		else
-			ret = -EINVAL;
+		case _KMEM:
+			ret = memcg_update_kmem_limit(memcg, nr_pages);
+			break;
+		}
 		break;
-	default:
-		ret = -EINVAL; /* should be BUG() ? */
+	case RES_SOFT_LIMIT:
+		memcg->soft_limit = nr_pages;
+		ret = 0;
 		break;
 	}
 	return ret ?: nbytes;
 }
 
-static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
-		unsigned long long *mem_limit, unsigned long long *memsw_limit)
-{
-	unsigned long long min_limit, min_memsw_limit, tmp;
-
-	min_limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
-	min_memsw_limit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
-	if (!memcg->use_hierarchy)
-		goto out;
-
-	while (memcg->css.parent) {
-		memcg = mem_cgroup_from_css(memcg->css.parent);
-		if (!memcg->use_hierarchy)
-			break;
-		tmp = res_counter_read_u64(&memcg->res, RES_LIMIT);
-		min_limit = min(min_limit, tmp);
-		tmp = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
-		min_memsw_limit = min(min_memsw_limit, tmp);
-	}
-out:
-	*mem_limit = min_limit;
-	*memsw_limit = min_memsw_limit;
-}
-
 static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf,
 				size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
-	int name;
-	enum res_type type;
+	struct page_counter *counter;
 
-	type = MEMFILE_TYPE(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
+	switch (MEMFILE_TYPE(of_cft(of)->private)) {
+	case _MEM:
+		counter = &memcg->memory;
+		break;
+	case _MEMSWAP:
+		counter = &memcg->memsw;
+		break;
+	case _KMEM:
+		counter = &memcg->kmem;
+		break;
+	default:
+		BUG();
+	}
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_MAX_USAGE:
-		if (type == _MEM)
-			res_counter_reset_max(&memcg->res);
-		else if (type == _MEMSWAP)
-			res_counter_reset_max(&memcg->memsw);
-		else if (type == _KMEM)
-			res_counter_reset_max(&memcg->kmem);
-		else
-			return -EINVAL;
+		page_counter_reset_watermark(counter);
 		break;
 	case RES_FAILCNT:
-		if (type == _MEM)
-			res_counter_reset_failcnt(&memcg->res);
-		else if (type == _MEMSWAP)
-			res_counter_reset_failcnt(&memcg->memsw);
-		else if (type == _KMEM)
-			res_counter_reset_failcnt(&memcg->kmem);
-		else
-			return -EINVAL;
+		counter->failcnt = 0;
 		break;
+	default:
+		BUG();
 	}
 
 	return nbytes;
@@ -4387,6 +4343,7 @@ static inline void mem_cgroup_lru_names_not_uptodate(void)
 static int memcg_stat_show(struct seq_file *m, void *v)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	unsigned long memory, memsw;
 	struct mem_cgroup *mi;
 	unsigned int i;
 
@@ -4406,14 +4363,16 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 			   mem_cgroup_nr_lru_pages(memcg, BIT(i)) * PAGE_SIZE);
 
 	/* Hierarchical information */
-	{
-		unsigned long long limit, memsw_limit;
-		memcg_get_hierarchical_limit(memcg, &limit, &memsw_limit);
-		seq_printf(m, "hierarchical_memory_limit %llu\n", limit);
-		if (do_swap_account)
-			seq_printf(m, "hierarchical_memsw_limit %llu\n",
-				   memsw_limit);
+	memory = memsw = PAGE_COUNTER_MAX;
+	for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) {
+		memory = min(memory, mi->memory.limit);
+		memsw = min(memsw, mi->memsw.limit);
 	}
+	seq_printf(m, "hierarchical_memory_limit %llu\n",
+		   (u64)memory * PAGE_SIZE);
+	if (do_swap_account)
+		seq_printf(m, "hierarchical_memsw_limit %llu\n",
+			   (u64)memsw * PAGE_SIZE);
 
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
 		long long val = 0;
@@ -4497,7 +4456,7 @@ static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css,
 static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
 {
 	struct mem_cgroup_threshold_ary *t;
-	u64 usage;
+	unsigned long usage;
 	int i;
 
 	rcu_read_lock();
@@ -4596,10 +4555,11 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
 {
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
-	u64 threshold, usage;
+	unsigned long threshold;
+	unsigned long usage;
 	int i, size, ret;
 
-	ret = res_counter_memparse_write_strategy(args, &threshold);
+	ret = page_counter_memparse(args, &threshold);
 	if (ret)
 		return ret;
 
@@ -4689,7 +4649,7 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
 {
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
-	u64 usage;
+	unsigned long usage;
 	int i, j, size;
 
 	mutex_lock(&memcg->thresholds_lock);
@@ -4883,7 +4843,7 @@ static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
 
 	memcg_kmem_mark_dead(memcg);
 
-	if (res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0)
+	if (page_counter_read(&memcg->kmem))
 		return;
 
 	if (memcg_kmem_test_and_clear_dead(memcg))
@@ -5363,9 +5323,9 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
  */
 struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 {
-	if (!memcg->res.parent)
+	if (!memcg->memory.parent)
 		return NULL;
-	return mem_cgroup_from_res_counter(memcg->res.parent, res);
+	return mem_cgroup_from_counter(memcg->memory.parent, memory);
 }
 EXPORT_SYMBOL(parent_mem_cgroup);
 
@@ -5410,9 +5370,9 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	/* root ? */
 	if (parent_css == NULL) {
 		root_mem_cgroup = memcg;
-		res_counter_init(&memcg->res, NULL);
-		res_counter_init(&memcg->memsw, NULL);
-		res_counter_init(&memcg->kmem, NULL);
+		page_counter_init(&memcg->memory, NULL);
+		page_counter_init(&memcg->memsw, NULL);
+		page_counter_init(&memcg->kmem, NULL);
 	}
 
 	memcg->last_scanned_node = MAX_NUMNODES;
@@ -5451,18 +5411,18 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	memcg->swappiness = mem_cgroup_swappiness(parent);
 
 	if (parent->use_hierarchy) {
-		res_counter_init(&memcg->res, &parent->res);
-		res_counter_init(&memcg->memsw, &parent->memsw);
-		res_counter_init(&memcg->kmem, &parent->kmem);
+		page_counter_init(&memcg->memory, &parent->memory);
+		page_counter_init(&memcg->memsw, &parent->memsw);
+		page_counter_init(&memcg->kmem, &parent->kmem);
 
 		/*
 		 * No need to take a reference to the parent because cgroup
 		 * core guarantees its existence.
 		 */
 	} else {
-		res_counter_init(&memcg->res, NULL);
-		res_counter_init(&memcg->memsw, NULL);
-		res_counter_init(&memcg->kmem, NULL);
+		page_counter_init(&memcg->memory, NULL);
+		page_counter_init(&memcg->memsw, NULL);
+		page_counter_init(&memcg->kmem, NULL);
 		/*
 		 * Deeper hierachy with use_hierarchy == false doesn't make
 		 * much sense so let cgroup subsystem know about this
@@ -5544,7 +5504,7 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 	/*
 	 * XXX: css_offline() would be where we should reparent all
 	 * memory to prepare the cgroup for destruction.  However,
-	 * memcg does not do css_tryget_online() and res_counter charging
+	 * memcg does not do css_tryget_online() and page_counter charging
 	 * under the same RCU lock region, which means that charging
 	 * could race with offlining.  Offlining only happens to
 	 * cgroups with no tasks in them but charges can show up
@@ -5564,7 +5524,7 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 	 * call_rcu()
 	 *   offline_css()
 	 *     reparent_charges()
-	 *                           res_counter_charge()
+	 *                           page_counter_try_charge()
 	 *                           css_put()
 	 *                             css_free()
 	 *                           pc->mem_cgroup = dead memcg
@@ -5599,10 +5559,10 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 
-	mem_cgroup_resize_limit(memcg, ULLONG_MAX);
-	mem_cgroup_resize_memsw_limit(memcg, ULLONG_MAX);
-	memcg_update_kmem_limit(memcg, ULLONG_MAX);
-	res_counter_set_soft_limit(&memcg->res, ULLONG_MAX);
+	mem_cgroup_resize_limit(memcg, PAGE_COUNTER_MAX);
+	mem_cgroup_resize_memsw_limit(memcg, PAGE_COUNTER_MAX);
+	memcg_update_kmem_limit(memcg, PAGE_COUNTER_MAX);
+	memcg->soft_limit = 0;
 }
 
 #ifdef CONFIG_MMU
@@ -5916,19 +5876,18 @@ static void __mem_cgroup_clear_mc(void)
 	if (mc.moved_swap) {
 		/* uncharge swap account from the old cgroup */
 		if (!mem_cgroup_is_root(mc.from))
-			res_counter_uncharge(&mc.from->memsw,
-					     PAGE_SIZE * mc.moved_swap);
-
-		for (i = 0; i < mc.moved_swap; i++)
-			css_put(&mc.from->css);
+			page_counter_uncharge(&mc.from->memsw, mc.moved_swap);
 
 		/*
-		 * we charged both to->res and to->memsw, so we should
-		 * uncharge to->res.
+		 * we charged both to->memory and to->memsw, so we
+		 * should uncharge to->memory.
 		 */
 		if (!mem_cgroup_is_root(mc.to))
-			res_counter_uncharge(&mc.to->res,
-					     PAGE_SIZE * mc.moved_swap);
+			page_counter_uncharge(&mc.to->memory, mc.moved_swap);
+
+		for (i = 0; i < mc.moved_swap; i++)
+			css_put(&mc.from->css);
+
 		/* we've already done css_get(mc.to) */
 		mc.moved_swap = 0;
 	}
@@ -6294,7 +6253,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry)
 	memcg = mem_cgroup_lookup(id);
 	if (memcg) {
 		if (!mem_cgroup_is_root(memcg))
-			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+			page_counter_uncharge(&memcg->memsw, 1);
 		mem_cgroup_swap_statistics(memcg, false);
 		css_put(&memcg->css);
 	}
@@ -6460,11 +6419,9 @@ static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
 
 	if (!mem_cgroup_is_root(memcg)) {
 		if (nr_mem)
-			res_counter_uncharge(&memcg->res,
-					     nr_mem * PAGE_SIZE);
+			page_counter_uncharge(&memcg->memory, nr_mem);
 		if (nr_memsw)
-			res_counter_uncharge(&memcg->memsw,
-					     nr_memsw * PAGE_SIZE);
+			page_counter_uncharge(&memcg->memsw, nr_memsw);
 		memcg_oom_recover(memcg);
 	}
 
diff --git a/mm/page_counter.c b/mm/page_counter.c
new file mode 100644
index 00000000000..f0cbc082542
--- /dev/null
+++ b/mm/page_counter.c
@@ -0,0 +1,207 @@
+/*
+ * Lockless hierarchical page accounting & limiting
+ *
+ * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner
+ */
+
+#include <linux/page_counter.h>
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/bug.h>
+#include <asm/page.h>
+
+/**
+ * page_counter_cancel - take pages out of the local counter
+ * @counter: counter
+ * @nr_pages: number of pages to cancel
+ *
+ * Returns whether there are remaining pages in the counter.
+ */
+int page_counter_cancel(struct page_counter *counter, unsigned long nr_pages)
+{
+	long new;
+
+	new = atomic_long_sub_return(nr_pages, &counter->count);
+
+	/* More uncharges than charges? */
+	WARN_ON_ONCE(new < 0);
+
+	return new > 0;
+}
+
+/**
+ * page_counter_charge - hierarchically charge pages
+ * @counter: counter
+ * @nr_pages: number of pages to charge
+ *
+ * NOTE: This does not consider any configured counter limits.
+ */
+void page_counter_charge(struct page_counter *counter, unsigned long nr_pages)
+{
+	struct page_counter *c;
+
+	for (c = counter; c; c = c->parent) {
+		long new;
+
+		new = atomic_long_add_return(nr_pages, &c->count);
+		/*
+		 * This is indeed racy, but we can live with some
+		 * inaccuracy in the watermark.
+		 */
+		if (new > c->watermark)
+			c->watermark = new;
+	}
+}
+
+/**
+ * page_counter_try_charge - try to hierarchically charge pages
+ * @counter: counter
+ * @nr_pages: number of pages to charge
+ * @fail: points first counter to hit its limit, if any
+ *
+ * Returns 0 on success, or -ENOMEM and @fail if the counter or one of
+ * its ancestors has hit its configured limit.
+ */
+int page_counter_try_charge(struct page_counter *counter,
+			    unsigned long nr_pages,
+			    struct page_counter **fail)
+{
+	struct page_counter *c;
+
+	for (c = counter; c; c = c->parent) {
+		long new;
+		/*
+		 * Charge speculatively to avoid an expensive CAS.  If
+		 * a bigger charge fails, it might falsely lock out a
+		 * racing smaller charge and send it into reclaim
+		 * early, but the error is limited to the difference
+		 * between the two sizes, which is less than 2M/4M in
+		 * case of a THP locking out a regular page charge.
+		 *
+		 * The atomic_long_add_return() implies a full memory
+		 * barrier between incrementing the count and reading
+		 * the limit.  When racing with page_counter_limit(),
+		 * we either see the new limit or the setter sees the
+		 * counter has changed and retries.
+		 */
+		new = atomic_long_add_return(nr_pages, &c->count);
+		if (new > c->limit) {
+			atomic_long_sub(nr_pages, &c->count);
+			/*
+			 * This is racy, but we can live with some
+			 * inaccuracy in the failcnt.
+			 */
+			c->failcnt++;
+			*fail = c;
+			goto failed;
+		}
+		/*
+		 * Just like with failcnt, we can live with some
+		 * inaccuracy in the watermark.
+		 */
+		if (new > c->watermark)
+			c->watermark = new;
+	}
+	return 0;
+
+failed:
+	for (c = counter; c != *fail; c = c->parent)
+		page_counter_cancel(c, nr_pages);
+
+	return -ENOMEM;
+}
+
+/**
+ * page_counter_uncharge - hierarchically uncharge pages
+ * @counter: counter
+ * @nr_pages: number of pages to uncharge
+ *
+ * Returns whether there are remaining charges in @counter.
+ */
+int page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages)
+{
+	struct page_counter *c;
+	int ret = 1;
+
+	for (c = counter; c; c = c->parent) {
+		int remainder;
+
+		remainder = page_counter_cancel(c, nr_pages);
+		if (c == counter && !remainder)
+			ret = 0;
+	}
+
+	return ret;
+}
+
+/**
+ * page_counter_limit - limit the number of pages allowed
+ * @counter: counter
+ * @limit: limit to set
+ *
+ * Returns 0 on success, -EBUSY if the current number of pages on the
+ * counter already exceeds the specified limit.
+ *
+ * The caller must serialize invocations on the same counter.
+ */
+int page_counter_limit(struct page_counter *counter, unsigned long limit)
+{
+	for (;;) {
+		unsigned long old;
+		long count;
+
+		/*
+		 * Update the limit while making sure that it's not
+		 * below the concurrently-changing counter value.
+		 *
+		 * The xchg implies two full memory barriers before
+		 * and after, so the read-swap-read is ordered and
+		 * ensures coherency with page_counter_try_charge():
+		 * that function modifies the count before checking
+		 * the limit, so if it sees the old limit, we see the
+		 * modified counter and retry.
+		 */
+		count = atomic_long_read(&counter->count);
+
+		if (count > limit)
+			return -EBUSY;
+
+		old = xchg(&counter->limit, limit);
+
+		if (atomic_long_read(&counter->count) <= count)
+			return 0;
+
+		counter->limit = old;
+		cond_resched();
+	}
+}
+
+/**
+ * page_counter_memparse - memparse() for page counter limits
+ * @buf: string to parse
+ * @nr_pages: returns the result in number of pages
+ *
+ * Returns -EINVAL, or 0 and @nr_pages on success.  @nr_pages will be
+ * limited to %PAGE_COUNTER_MAX.
+ */
+int page_counter_memparse(const char *buf, unsigned long *nr_pages)
+{
+	char unlimited[] = "-1";
+	char *end;
+	u64 bytes;
+
+	if (!strncmp(buf, unlimited, sizeof(unlimited))) {
+		*nr_pages = PAGE_COUNTER_MAX;
+		return 0;
+	}
+
+	bytes = memparse(buf, &end);
+	if (*end != '\0')
+		return -EINVAL;
+
+	*nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX);
+
+	return 0;
+}
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 1d191357bf8..272327134a1 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -9,13 +9,13 @@
 int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	/*
-	 * The root cgroup does not use res_counters, but rather,
+	 * The root cgroup does not use page_counters, but rather,
 	 * rely on the data already collected by the network
 	 * subsystem
 	 */
-	struct res_counter *res_parent = NULL;
-	struct cg_proto *cg_proto, *parent_cg;
 	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+	struct page_counter *counter_parent = NULL;
+	struct cg_proto *cg_proto, *parent_cg;
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
@@ -29,9 +29,9 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 
 	parent_cg = tcp_prot.proto_cgroup(parent);
 	if (parent_cg)
-		res_parent = &parent_cg->memory_allocated;
+		counter_parent = &parent_cg->memory_allocated;
 
-	res_counter_init(&cg_proto->memory_allocated, res_parent);
+	page_counter_init(&cg_proto->memory_allocated, counter_parent);
 	percpu_counter_init(&cg_proto->sockets_allocated, 0, GFP_KERNEL);
 
 	return 0;
@@ -50,7 +50,7 @@ void tcp_destroy_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(tcp_destroy_cgroup);
 
-static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
+static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages)
 {
 	struct cg_proto *cg_proto;
 	int i;
@@ -60,20 +60,17 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	if (!cg_proto)
 		return -EINVAL;
 
-	if (val > RES_COUNTER_MAX)
-		val = RES_COUNTER_MAX;
-
-	ret = res_counter_set_limit(&cg_proto->memory_allocated, val);
+	ret = page_counter_limit(&cg_proto->memory_allocated, nr_pages);
 	if (ret)
 		return ret;
 
 	for (i = 0; i < 3; i++)
-		cg_proto->sysctl_mem[i] = min_t(long, val >> PAGE_SHIFT,
+		cg_proto->sysctl_mem[i] = min_t(long, nr_pages,
 						sysctl_tcp_mem[i]);
 
-	if (val == RES_COUNTER_MAX)
+	if (nr_pages == PAGE_COUNTER_MAX)
 		clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
-	else if (val != RES_COUNTER_MAX) {
+	else {
 		/*
 		 * The active bit needs to be written after the static_key
 		 * update. This is what guarantees that the socket activation
@@ -102,11 +99,20 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	return 0;
 }
 
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_MAX_USAGE,
+	RES_FAILCNT,
+};
+
+static DEFINE_MUTEX(tcp_limit_mutex);
+
 static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
-	unsigned long long val;
+	unsigned long nr_pages;
 	int ret = 0;
 
 	buf = strstrip(buf);
@@ -114,10 +120,12 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 	switch (of_cft(of)->private) {
 	case RES_LIMIT:
 		/* see memcontrol.c */
-		ret = res_counter_memparse_write_strategy(buf, &val);
+		ret = page_counter_memparse(buf, &nr_pages);
 		if (ret)
 			break;
-		ret = tcp_update_limit(memcg, val);
+		mutex_lock(&tcp_limit_mutex);
+		ret = tcp_update_limit(memcg, nr_pages);
+		mutex_unlock(&tcp_limit_mutex);
 		break;
 	default:
 		ret = -EINVAL;
@@ -126,43 +134,36 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 	return ret ?: nbytes;
 }
 
-static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)
-{
-	struct cg_proto *cg_proto;
-
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
-		return default_val;
-
-	return res_counter_read_u64(&cg_proto->memory_allocated, type);
-}
-
-static u64 tcp_read_usage(struct mem_cgroup *memcg)
-{
-	struct cg_proto *cg_proto;
-
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
-		return atomic_long_read(&tcp_memory_allocated) << PAGE_SHIFT;
-
-	return res_counter_read_u64(&cg_proto->memory_allocated, RES_USAGE);
-}
-
 static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct cg_proto *cg_proto = tcp_prot.proto_cgroup(memcg);
 	u64 val;
 
 	switch (cft->private) {
 	case RES_LIMIT:
-		val = tcp_read_stat(memcg, RES_LIMIT, RES_COUNTER_MAX);
+		if (!cg_proto)
+			return PAGE_COUNTER_MAX;
+		val = cg_proto->memory_allocated.limit;
+		val *= PAGE_SIZE;
 		break;
 	case RES_USAGE:
-		val = tcp_read_usage(memcg);
+		if (!cg_proto)
+			val = atomic_long_read(&tcp_memory_allocated);
+		else
+			val = page_counter_read(&cg_proto->memory_allocated);
+		val *= PAGE_SIZE;
 		break;
 	case RES_FAILCNT:
+		if (!cg_proto)
+			return 0;
+		val = cg_proto->memory_allocated.failcnt;
+		break;
 	case RES_MAX_USAGE:
-		val = tcp_read_stat(memcg, cft->private, 0);
+		if (!cg_proto)
+			return 0;
+		val = cg_proto->memory_allocated.watermark;
+		val *= PAGE_SIZE;
 		break;
 	default:
 		BUG();
@@ -183,10 +184,10 @@ static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of,
 
 	switch (of_cft(of)->private) {
 	case RES_MAX_USAGE:
-		res_counter_reset_max(&cg_proto->memory_allocated);
+		page_counter_reset_watermark(&cg_proto->memory_allocated);
 		break;
 	case RES_FAILCNT:
-		res_counter_reset_failcnt(&cg_proto->memory_allocated);
+		cg_proto->memory_allocated.failcnt = 0;
 		break;
 	}
 
-- 
cgit v1.2.3-70-g09d2


From 71f87bee38edddb21d97895fa938744cf3f477bb Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 10 Dec 2014 15:42:34 -0800
Subject: mm: hugetlb_cgroup: convert to lockless page counters

Abandon the spinlock-protected byte counters in favor of the unlocked
page counters in the hugetlb controller as well.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/cgroups/hugetlb.txt |   2 +-
 include/linux/hugetlb_cgroup.h    |   1 -
 init/Kconfig                      |   3 +-
 mm/hugetlb_cgroup.c               | 103 +++++++++++++++++++++-----------------
 4 files changed, 61 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/Documentation/cgroups/hugetlb.txt b/Documentation/cgroups/hugetlb.txt
index a9faaca1f02..106245c3aec 100644
--- a/Documentation/cgroups/hugetlb.txt
+++ b/Documentation/cgroups/hugetlb.txt
@@ -29,7 +29,7 @@ Brief summary of control files
 
  hugetlb.<hugepagesize>.limit_in_bytes     # set/show limit of "hugepagesize" hugetlb usage
  hugetlb.<hugepagesize>.max_usage_in_bytes # show max "hugepagesize" hugetlb  usage recorded
- hugetlb.<hugepagesize>.usage_in_bytes     # show current res_counter usage for "hugepagesize" hugetlb
+ hugetlb.<hugepagesize>.usage_in_bytes     # show current usage for "hugepagesize" hugetlb
  hugetlb.<hugepagesize>.failcnt		   # show the number of allocation failure due to HugeTLB limit
 
 For a system supporting two hugepage size (16M and 16G) the control
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 0129f89cf98..bcc853eccc8 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -16,7 +16,6 @@
 #define _LINUX_HUGETLB_CGROUP_H
 
 #include <linux/mmdebug.h>
-#include <linux/res_counter.h>
 
 struct hugetlb_cgroup;
 /*
diff --git a/init/Kconfig b/init/Kconfig
index fd9e88791ba..a60d1442d1d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1051,7 +1051,8 @@ config MEMCG_KMEM
 
 config CGROUP_HUGETLB
 	bool "HugeTLB Resource Controller for Control Groups"
-	depends on RESOURCE_COUNTERS && HUGETLB_PAGE
+	depends on HUGETLB_PAGE
+	select PAGE_COUNTER
 	default n
 	help
 	  Provides a cgroup Resource Controller for HugeTLB pages.
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index a67c26e0f36..037e1c00a5b 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/page_counter.h>
 #include <linux/slab.h>
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
@@ -23,7 +24,7 @@ struct hugetlb_cgroup {
 	/*
 	 * the counter to account for hugepages from hugetlb.
 	 */
-	struct res_counter hugepage[HUGE_MAX_HSTATE];
+	struct page_counter hugepage[HUGE_MAX_HSTATE];
 };
 
 #define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
@@ -60,7 +61,7 @@ static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg)
 	int idx;
 
 	for (idx = 0; idx < hugetlb_max_hstate; idx++) {
-		if ((res_counter_read_u64(&h_cg->hugepage[idx], RES_USAGE)) > 0)
+		if (page_counter_read(&h_cg->hugepage[idx]))
 			return true;
 	}
 	return false;
@@ -79,12 +80,12 @@ hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	if (parent_h_cgroup) {
 		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
-			res_counter_init(&h_cgroup->hugepage[idx],
-					 &parent_h_cgroup->hugepage[idx]);
+			page_counter_init(&h_cgroup->hugepage[idx],
+					  &parent_h_cgroup->hugepage[idx]);
 	} else {
 		root_h_cgroup = h_cgroup;
 		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
-			res_counter_init(&h_cgroup->hugepage[idx], NULL);
+			page_counter_init(&h_cgroup->hugepage[idx], NULL);
 	}
 	return &h_cgroup->css;
 }
@@ -108,9 +109,8 @@ static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css)
 static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
 				       struct page *page)
 {
-	int csize;
-	struct res_counter *counter;
-	struct res_counter *fail_res;
+	unsigned int nr_pages;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *page_hcg;
 	struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg);
 
@@ -123,15 +123,15 @@ static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
 	if (!page_hcg || page_hcg != h_cg)
 		goto out;
 
-	csize = PAGE_SIZE << compound_order(page);
+	nr_pages = 1 << compound_order(page);
 	if (!parent) {
 		parent = root_h_cgroup;
 		/* root has no limit */
-		res_counter_charge_nofail(&parent->hugepage[idx],
-					  csize, &fail_res);
+		page_counter_charge(&parent->hugepage[idx], nr_pages);
 	}
 	counter = &h_cg->hugepage[idx];
-	res_counter_uncharge_until(counter, counter->parent, csize);
+	/* Take the pages off the local counter */
+	page_counter_cancel(counter, nr_pages);
 
 	set_hugetlb_cgroup(page, parent);
 out:
@@ -166,9 +166,8 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 				 struct hugetlb_cgroup **ptr)
 {
 	int ret = 0;
-	struct res_counter *fail_res;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *h_cg = NULL;
-	unsigned long csize = nr_pages * PAGE_SIZE;
 
 	if (hugetlb_cgroup_disabled())
 		goto done;
@@ -187,7 +186,7 @@ again:
 	}
 	rcu_read_unlock();
 
-	ret = res_counter_charge(&h_cg->hugepage[idx], csize, &fail_res);
+	ret = page_counter_try_charge(&h_cg->hugepage[idx], nr_pages, &counter);
 	css_put(&h_cg->css);
 done:
 	*ptr = h_cg;
@@ -213,7 +212,6 @@ void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
 				  struct page *page)
 {
 	struct hugetlb_cgroup *h_cg;
-	unsigned long csize = nr_pages * PAGE_SIZE;
 
 	if (hugetlb_cgroup_disabled())
 		return;
@@ -222,61 +220,76 @@ void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
 	if (unlikely(!h_cg))
 		return;
 	set_hugetlb_cgroup(page, NULL);
-	res_counter_uncharge(&h_cg->hugepage[idx], csize);
+	page_counter_uncharge(&h_cg->hugepage[idx], nr_pages);
 	return;
 }
 
 void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
 				    struct hugetlb_cgroup *h_cg)
 {
-	unsigned long csize = nr_pages * PAGE_SIZE;
-
 	if (hugetlb_cgroup_disabled() || !h_cg)
 		return;
 
 	if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER)
 		return;
 
-	res_counter_uncharge(&h_cg->hugepage[idx], csize);
+	page_counter_uncharge(&h_cg->hugepage[idx], nr_pages);
 	return;
 }
 
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_MAX_USAGE,
+	RES_FAILCNT,
+};
+
 static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
 				   struct cftype *cft)
 {
-	int idx, name;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
 
-	idx = MEMFILE_IDX(cft->private);
-	name = MEMFILE_ATTR(cft->private);
+	counter = &h_cg->hugepage[MEMFILE_IDX(cft->private)];
 
-	return res_counter_read_u64(&h_cg->hugepage[idx], name);
+	switch (MEMFILE_ATTR(cft->private)) {
+	case RES_USAGE:
+		return (u64)page_counter_read(counter) * PAGE_SIZE;
+	case RES_LIMIT:
+		return (u64)counter->limit * PAGE_SIZE;
+	case RES_MAX_USAGE:
+		return (u64)counter->watermark * PAGE_SIZE;
+	case RES_FAILCNT:
+		return counter->failcnt;
+	default:
+		BUG();
+	}
 }
 
+static DEFINE_MUTEX(hugetlb_limit_mutex);
+
 static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
 				    char *buf, size_t nbytes, loff_t off)
 {
-	int idx, name, ret;
-	unsigned long long val;
+	int ret, idx;
+	unsigned long nr_pages;
 	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
 
+	if (hugetlb_cgroup_is_root(h_cg)) /* Can't set limit on root */
+		return -EINVAL;
+
 	buf = strstrip(buf);
+	ret = page_counter_memparse(buf, &nr_pages);
+	if (ret)
+		return ret;
+
 	idx = MEMFILE_IDX(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_LIMIT:
-		if (hugetlb_cgroup_is_root(h_cg)) {
-			/* Can't set limit on root */
-			ret = -EINVAL;
-			break;
-		}
-		/* This function does all necessary parse...reuse it */
-		ret = res_counter_memparse_write_strategy(buf, &val);
-		if (ret)
-			break;
-		val = ALIGN(val, 1ULL << huge_page_shift(&hstates[idx]));
-		ret = res_counter_set_limit(&h_cg->hugepage[idx], val);
+		mutex_lock(&hugetlb_limit_mutex);
+		ret = page_counter_limit(&h_cg->hugepage[idx], nr_pages);
+		mutex_unlock(&hugetlb_limit_mutex);
 		break;
 	default:
 		ret = -EINVAL;
@@ -288,18 +301,18 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
 static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of,
 				    char *buf, size_t nbytes, loff_t off)
 {
-	int idx, name, ret = 0;
+	int ret = 0;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
 
-	idx = MEMFILE_IDX(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
+	counter = &h_cg->hugepage[MEMFILE_IDX(of_cft(of)->private)];
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_MAX_USAGE:
-		res_counter_reset_max(&h_cg->hugepage[idx]);
+		page_counter_reset_watermark(counter);
 		break;
 	case RES_FAILCNT:
-		res_counter_reset_failcnt(&h_cg->hugepage[idx]);
+		counter->failcnt = 0;
 		break;
 	default:
 		ret = -EINVAL;
-- 
cgit v1.2.3-70-g09d2


From 5b1efc027c0b51ca3e76f4e00c83358f8349f543 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 10 Dec 2014 15:42:37 -0800
Subject: kernel: res_counter: remove the unused API

All memory accounting and limiting has been switched over to the
lockless page counters.  Bye, res_counter!

[akpm@linux-foundation.org: update Documentation/cgroups/memory.txt]
[mhocko@suse.cz: ditch the last remainings of res_counter]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/cgroups/memory.txt           |  17 ++-
 Documentation/cgroups/resource_counter.txt | 197 -------------------------
 include/linux/res_counter.h                | 223 -----------------------------
 init/Kconfig                               |   6 -
 kernel/Makefile                            |   1 -
 kernel/res_counter.c                       | 211 ---------------------------
 6 files changed, 8 insertions(+), 647 deletions(-)
 delete mode 100644 Documentation/cgroups/resource_counter.txt
 delete mode 100644 include/linux/res_counter.h
 delete mode 100644 kernel/res_counter.c

(limited to 'include')

diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index f624727ab40..67613ff0270 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -116,16 +116,16 @@ The memory controller is the first controller developed.
 
 2.1. Design
 
-The core of the design is a counter called the res_counter. The res_counter
-tracks the current memory usage and limit of the group of processes associated
-with the controller. Each cgroup has a memory controller specific data
-structure (mem_cgroup) associated with it.
+The core of the design is a counter called the page_counter. The
+page_counter tracks the current memory usage and limit of the group of
+processes associated with the controller. Each cgroup has a memory controller
+specific data structure (mem_cgroup) associated with it.
 
 2.2. Accounting
 
 		+--------------------+
-		|  mem_cgroup     |
-		|  (res_counter)     |
+		|  mem_cgroup        |
+		|  (page_counter)    |
 		+--------------------+
 		 /            ^      \
 		/             |       \
@@ -352,9 +352,8 @@ set:
 0. Configuration
 
 a. Enable CONFIG_CGROUPS
-b. Enable CONFIG_RESOURCE_COUNTERS
-c. Enable CONFIG_MEMCG
-d. Enable CONFIG_MEMCG_SWAP (to use swap extension)
+b. Enable CONFIG_MEMCG
+c. Enable CONFIG_MEMCG_SWAP (to use swap extension)
 d. Enable CONFIG_MEMCG_KMEM (to use kmem extension)
 
 1. Prepare the cgroups (see cgroups.txt, Why are cgroups needed?)
diff --git a/Documentation/cgroups/resource_counter.txt b/Documentation/cgroups/resource_counter.txt
deleted file mode 100644
index 762ca54eb92..00000000000
--- a/Documentation/cgroups/resource_counter.txt
+++ /dev/null
@@ -1,197 +0,0 @@
-
-		The Resource Counter
-
-The resource counter, declared at include/linux/res_counter.h,
-is supposed to facilitate the resource management by controllers
-by providing common stuff for accounting.
-
-This "stuff" includes the res_counter structure and routines
-to work with it.
-
-
-
-1. Crucial parts of the res_counter structure
-
- a. unsigned long long usage
-
- 	The usage value shows the amount of a resource that is consumed
-	by a group at a given time. The units of measurement should be
-	determined by the controller that uses this counter. E.g. it can
-	be bytes, items or any other unit the controller operates on.
-
- b. unsigned long long max_usage
-
- 	The maximal value of the usage over time.
-
- 	This value is useful when gathering statistical information about
-	the particular group, as it shows the actual resource requirements
-	for a particular group, not just some usage snapshot.
-
- c. unsigned long long limit
-
- 	The maximal allowed amount of resource to consume by the group. In
-	case the group requests for more resources, so that the usage value
-	would exceed the limit, the resource allocation is rejected (see
-	the next section).
-
- d. unsigned long long failcnt
-
- 	The failcnt stands for "failures counter". This is the number of
-	resource allocation attempts that failed.
-
- c. spinlock_t lock
-
- 	Protects changes of the above values.
-
-
-
-2. Basic accounting routines
-
- a. void res_counter_init(struct res_counter *rc,
-				struct res_counter *rc_parent)
-
- 	Initializes the resource counter. As usual, should be the first
-	routine called for a new counter.
-
-	The struct res_counter *parent can be used to define a hierarchical
-	child -> parent relationship directly in the res_counter structure,
-	NULL can be used to define no relationship.
-
- c. int res_counter_charge(struct res_counter *rc, unsigned long val,
-				struct res_counter **limit_fail_at)
-
-	When a resource is about to be allocated it has to be accounted
-	with the appropriate resource counter (controller should determine
-	which one to use on its own). This operation is called "charging".
-
-	This is not very important which operation - resource allocation
-	or charging - is performed first, but
-	  * if the allocation is performed first, this may create a
-	    temporary resource over-usage by the time resource counter is
-	    charged;
-	  * if the charging is performed first, then it should be uncharged
-	    on error path (if the one is called).
-
-	If the charging fails and a hierarchical dependency exists, the
-	limit_fail_at parameter is set to the particular res_counter element
-	where the charging failed.
-
- d. u64 res_counter_uncharge(struct res_counter *rc, unsigned long val)
-
-	When a resource is released (freed) it should be de-accounted
-	from the resource counter it was accounted to.  This is called
-	"uncharging". The return value of this function indicate the amount
-	of charges still present in the counter.
-
-	The _locked routines imply that the res_counter->lock is taken.
-
- e. u64 res_counter_uncharge_until
-		(struct res_counter *rc, struct res_counter *top,
-		 unsigned long val)
-
-	Almost same as res_counter_uncharge() but propagation of uncharge
-	stops when rc == top. This is useful when kill a res_counter in
-	child cgroup.
-
- 2.1 Other accounting routines
-
-    There are more routines that may help you with common needs, like
-    checking whether the limit is reached or resetting the max_usage
-    value. They are all declared in include/linux/res_counter.h.
-
-
-
-3. Analyzing the resource counter registrations
-
- a. If the failcnt value constantly grows, this means that the counter's
-    limit is too tight. Either the group is misbehaving and consumes too
-    many resources, or the configuration is not suitable for the group
-    and the limit should be increased.
-
- b. The max_usage value can be used to quickly tune the group. One may
-    set the limits to maximal values and either load the container with
-    a common pattern or leave one for a while. After this the max_usage
-    value shows the amount of memory the container would require during
-    its common activity.
-
-    Setting the limit a bit above this value gives a pretty good
-    configuration that works in most of the cases.
-
- c. If the max_usage is much less than the limit, but the failcnt value
-    is growing, then the group tries to allocate a big chunk of resource
-    at once.
-
- d. If the max_usage is much less than the limit, but the failcnt value
-    is 0, then this group is given too high limit, that it does not
-    require. It is better to lower the limit a bit leaving more resource
-    for other groups.
-
-
-
-4. Communication with the control groups subsystem (cgroups)
-
-All the resource controllers that are using cgroups and resource counters
-should provide files (in the cgroup filesystem) to work with the resource
-counter fields. They are recommended to adhere to the following rules:
-
- a. File names
-
- 	Field name	File name
-	---------------------------------------------------
-	usage		usage_in_<unit_of_measurement>
-	max_usage	max_usage_in_<unit_of_measurement>
-	limit		limit_in_<unit_of_measurement>
-	failcnt		failcnt
-	lock		no file :)
-
- b. Reading from file should show the corresponding field value in the
-    appropriate format.
-
- c. Writing to file
-
- 	Field		Expected behavior
-	----------------------------------
-	usage		prohibited
-	max_usage	reset to usage
-	limit		set the limit
-	failcnt		reset to zero
-
-
-
-5. Usage example
-
- a. Declare a task group (take a look at cgroups subsystem for this) and
-    fold a res_counter into it
-
-	struct my_group {
-		struct res_counter res;
-
-		<other fields>
-	}
-
- b. Put hooks in resource allocation/release paths
-
- 	int alloc_something(...)
-	{
-		if (res_counter_charge(res_counter_ptr, amount) < 0)
-			return -ENOMEM;
-
-		<allocate the resource and return to the caller>
-	}
-
-	void release_something(...)
-	{
-		res_counter_uncharge(res_counter_ptr, amount);
-
-		<release the resource>
-	}
-
-    In order to keep the usage value self-consistent, both the
-    "res_counter_ptr" and the "amount" in release_something() should be
-    the same as they were in the alloc_something() when the releasing
-    resource was allocated.
-
- c. Provide the way to read res_counter values and set them (the cgroups
-    still can help with it).
-
- c. Compile and run :)
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
deleted file mode 100644
index 56b7bc32db4..00000000000
--- a/include/linux/res_counter.h
+++ /dev/null
@@ -1,223 +0,0 @@
-#ifndef __RES_COUNTER_H__
-#define __RES_COUNTER_H__
-
-/*
- * Resource Counters
- * Contain common data types and routines for resource accounting
- *
- * Copyright 2007 OpenVZ SWsoft Inc
- *
- * Author: Pavel Emelianov <xemul@openvz.org>
- *
- * See Documentation/cgroups/resource_counter.txt for more
- * info about what this counter is.
- */
-
-#include <linux/spinlock.h>
-#include <linux/errno.h>
-
-/*
- * The core object. the cgroup that wishes to account for some
- * resource may include this counter into its structures and use
- * the helpers described beyond
- */
-
-struct res_counter {
-	/*
-	 * the current resource consumption level
-	 */
-	unsigned long long usage;
-	/*
-	 * the maximal value of the usage from the counter creation
-	 */
-	unsigned long long max_usage;
-	/*
-	 * the limit that usage cannot exceed
-	 */
-	unsigned long long limit;
-	/*
-	 * the limit that usage can be exceed
-	 */
-	unsigned long long soft_limit;
-	/*
-	 * the number of unsuccessful attempts to consume the resource
-	 */
-	unsigned long long failcnt;
-	/*
-	 * the lock to protect all of the above.
-	 * the routines below consider this to be IRQ-safe
-	 */
-	spinlock_t lock;
-	/*
-	 * Parent counter, used for hierarchial resource accounting
-	 */
-	struct res_counter *parent;
-};
-
-#define RES_COUNTER_MAX ULLONG_MAX
-
-/**
- * Helpers to interact with userspace
- * res_counter_read_u64() - returns the value of the specified member.
- * res_counter_read/_write - put/get the specified fields from the
- * res_counter struct to/from the user
- *
- * @counter:     the counter in question
- * @member:  the field to work with (see RES_xxx below)
- * @buf:     the buffer to opeate on,...
- * @nbytes:  its size...
- * @pos:     and the offset.
- */
-
-u64 res_counter_read_u64(struct res_counter *counter, int member);
-
-ssize_t res_counter_read(struct res_counter *counter, int member,
-		const char __user *buf, size_t nbytes, loff_t *pos,
-		int (*read_strategy)(unsigned long long val, char *s));
-
-int res_counter_memparse_write_strategy(const char *buf,
-					unsigned long long *res);
-
-/*
- * the field descriptors. one for each member of res_counter
- */
-
-enum {
-	RES_USAGE,
-	RES_MAX_USAGE,
-	RES_LIMIT,
-	RES_FAILCNT,
-	RES_SOFT_LIMIT,
-};
-
-/*
- * helpers for accounting
- */
-
-void res_counter_init(struct res_counter *counter, struct res_counter *parent);
-
-/*
- * charge - try to consume more resource.
- *
- * @counter: the counter
- * @val: the amount of the resource. each controller defines its own
- *       units, e.g. numbers, bytes, Kbytes, etc
- *
- * returns 0 on success and <0 if the counter->usage will exceed the
- * counter->limit
- *
- * charge_nofail works the same, except that it charges the resource
- * counter unconditionally, and returns < 0 if the after the current
- * charge we are over limit.
- */
-
-int __must_check res_counter_charge(struct res_counter *counter,
-		unsigned long val, struct res_counter **limit_fail_at);
-int res_counter_charge_nofail(struct res_counter *counter,
-		unsigned long val, struct res_counter **limit_fail_at);
-
-/*
- * uncharge - tell that some portion of the resource is released
- *
- * @counter: the counter
- * @val: the amount of the resource
- *
- * these calls check for usage underflow and show a warning on the console
- *
- * returns the total charges still present in @counter.
- */
-
-u64 res_counter_uncharge(struct res_counter *counter, unsigned long val);
-
-u64 res_counter_uncharge_until(struct res_counter *counter,
-			       struct res_counter *top,
-			       unsigned long val);
-/**
- * res_counter_margin - calculate chargeable space of a counter
- * @cnt: the counter
- *
- * Returns the difference between the hard limit and the current usage
- * of resource counter @cnt.
- */
-static inline unsigned long long res_counter_margin(struct res_counter *cnt)
-{
-	unsigned long long margin;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	if (cnt->limit > cnt->usage)
-		margin = cnt->limit - cnt->usage;
-	else
-		margin = 0;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return margin;
-}
-
-/**
- * Get the difference between the usage and the soft limit
- * @cnt: The counter
- *
- * Returns 0 if usage is less than or equal to soft limit
- * The difference between usage and soft limit, otherwise.
- */
-static inline unsigned long long
-res_counter_soft_limit_excess(struct res_counter *cnt)
-{
-	unsigned long long excess;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	if (cnt->usage <= cnt->soft_limit)
-		excess = 0;
-	else
-		excess = cnt->usage - cnt->soft_limit;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return excess;
-}
-
-static inline void res_counter_reset_max(struct res_counter *cnt)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	cnt->max_usage = cnt->usage;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-}
-
-static inline void res_counter_reset_failcnt(struct res_counter *cnt)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	cnt->failcnt = 0;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-}
-
-static inline int res_counter_set_limit(struct res_counter *cnt,
-		unsigned long long limit)
-{
-	unsigned long flags;
-	int ret = -EBUSY;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	if (cnt->usage <= limit) {
-		cnt->limit = limit;
-		ret = 0;
-	}
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return ret;
-}
-
-static inline int
-res_counter_set_soft_limit(struct res_counter *cnt,
-				unsigned long long soft_limit)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	cnt->soft_limit = soft_limit;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return 0;
-}
-
-#endif
diff --git a/init/Kconfig b/init/Kconfig
index a60d1442d1d..1761c72bc1a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -972,12 +972,6 @@ config CGROUP_CPUACCT
 	  Provides a simple Resource Controller for monitoring the
 	  total CPU consumed by the tasks in a cgroup.
 
-config RESOURCE_COUNTERS
-	bool "Resource counters"
-	help
-	  This option enables controller independent resource accounting
-	  infrastructure that works with cgroups.
-
 config PAGE_COUNTER
        bool
 
diff --git a/kernel/Makefile b/kernel/Makefile
index 17ea6d4a9a2..a59481a3fa6 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -57,7 +57,6 @@ obj-$(CONFIG_UTS_NS) += utsname.o
 obj-$(CONFIG_USER_NS) += user_namespace.o
 obj-$(CONFIG_PID_NS) += pid_namespace.o
 obj-$(CONFIG_IKCONFIG) += configs.o
-obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o
 obj-$(CONFIG_SMP) += stop_machine.o
 obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
 obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
deleted file mode 100644
index e791130f85a..00000000000
--- a/kernel/res_counter.c
+++ /dev/null
@@ -1,211 +0,0 @@
-/*
- * resource cgroups
- *
- * Copyright 2007 OpenVZ SWsoft Inc
- *
- * Author: Pavel Emelianov <xemul@openvz.org>
- *
- */
-
-#include <linux/types.h>
-#include <linux/parser.h>
-#include <linux/fs.h>
-#include <linux/res_counter.h>
-#include <linux/uaccess.h>
-#include <linux/mm.h>
-
-void res_counter_init(struct res_counter *counter, struct res_counter *parent)
-{
-	spin_lock_init(&counter->lock);
-	counter->limit = RES_COUNTER_MAX;
-	counter->soft_limit = RES_COUNTER_MAX;
-	counter->parent = parent;
-}
-
-static u64 res_counter_uncharge_locked(struct res_counter *counter,
-				       unsigned long val)
-{
-	if (WARN_ON(counter->usage < val))
-		val = counter->usage;
-
-	counter->usage -= val;
-	return counter->usage;
-}
-
-static int res_counter_charge_locked(struct res_counter *counter,
-				     unsigned long val, bool force)
-{
-	int ret = 0;
-
-	if (counter->usage + val > counter->limit) {
-		counter->failcnt++;
-		ret = -ENOMEM;
-		if (!force)
-			return ret;
-	}
-
-	counter->usage += val;
-	if (counter->usage > counter->max_usage)
-		counter->max_usage = counter->usage;
-	return ret;
-}
-
-static int __res_counter_charge(struct res_counter *counter, unsigned long val,
-				struct res_counter **limit_fail_at, bool force)
-{
-	int ret, r;
-	unsigned long flags;
-	struct res_counter *c, *u;
-
-	r = ret = 0;
-	*limit_fail_at = NULL;
-	local_irq_save(flags);
-	for (c = counter; c != NULL; c = c->parent) {
-		spin_lock(&c->lock);
-		r = res_counter_charge_locked(c, val, force);
-		spin_unlock(&c->lock);
-		if (r < 0 && !ret) {
-			ret = r;
-			*limit_fail_at = c;
-			if (!force)
-				break;
-		}
-	}
-
-	if (ret < 0 && !force) {
-		for (u = counter; u != c; u = u->parent) {
-			spin_lock(&u->lock);
-			res_counter_uncharge_locked(u, val);
-			spin_unlock(&u->lock);
-		}
-	}
-	local_irq_restore(flags);
-
-	return ret;
-}
-
-int res_counter_charge(struct res_counter *counter, unsigned long val,
-			struct res_counter **limit_fail_at)
-{
-	return __res_counter_charge(counter, val, limit_fail_at, false);
-}
-
-int res_counter_charge_nofail(struct res_counter *counter, unsigned long val,
-			      struct res_counter **limit_fail_at)
-{
-	return __res_counter_charge(counter, val, limit_fail_at, true);
-}
-
-u64 res_counter_uncharge_until(struct res_counter *counter,
-			       struct res_counter *top,
-			       unsigned long val)
-{
-	unsigned long flags;
-	struct res_counter *c;
-	u64 ret = 0;
-
-	local_irq_save(flags);
-	for (c = counter; c != top; c = c->parent) {
-		u64 r;
-		spin_lock(&c->lock);
-		r = res_counter_uncharge_locked(c, val);
-		if (c == counter)
-			ret = r;
-		spin_unlock(&c->lock);
-	}
-	local_irq_restore(flags);
-	return ret;
-}
-
-u64 res_counter_uncharge(struct res_counter *counter, unsigned long val)
-{
-	return res_counter_uncharge_until(counter, NULL, val);
-}
-
-static inline unsigned long long *
-res_counter_member(struct res_counter *counter, int member)
-{
-	switch (member) {
-	case RES_USAGE:
-		return &counter->usage;
-	case RES_MAX_USAGE:
-		return &counter->max_usage;
-	case RES_LIMIT:
-		return &counter->limit;
-	case RES_FAILCNT:
-		return &counter->failcnt;
-	case RES_SOFT_LIMIT:
-		return &counter->soft_limit;
-	};
-
-	BUG();
-	return NULL;
-}
-
-ssize_t res_counter_read(struct res_counter *counter, int member,
-		const char __user *userbuf, size_t nbytes, loff_t *pos,
-		int (*read_strategy)(unsigned long long val, char *st_buf))
-{
-	unsigned long long *val;
-	char buf[64], *s;
-
-	s = buf;
-	val = res_counter_member(counter, member);
-	if (read_strategy)
-		s += read_strategy(*val, s);
-	else
-		s += sprintf(s, "%llu\n", *val);
-	return simple_read_from_buffer((void __user *)userbuf, nbytes,
-			pos, buf, s - buf);
-}
-
-#if BITS_PER_LONG == 32
-u64 res_counter_read_u64(struct res_counter *counter, int member)
-{
-	unsigned long flags;
-	u64 ret;
-
-	spin_lock_irqsave(&counter->lock, flags);
-	ret = *res_counter_member(counter, member);
-	spin_unlock_irqrestore(&counter->lock, flags);
-
-	return ret;
-}
-#else
-u64 res_counter_read_u64(struct res_counter *counter, int member)
-{
-	return *res_counter_member(counter, member);
-}
-#endif
-
-int res_counter_memparse_write_strategy(const char *buf,
-					unsigned long long *resp)
-{
-	char *end;
-	unsigned long long res;
-
-	/* return RES_COUNTER_MAX(unlimited) if "-1" is specified */
-	if (*buf == '-') {
-		int rc = kstrtoull(buf + 1, 10, &res);
-
-		if (rc)
-			return rc;
-		if (res != 1)
-			return -EINVAL;
-		*resp = RES_COUNTER_MAX;
-		return 0;
-	}
-
-	res = memparse(buf, &end);
-	if (*end != '\0')
-		return -EINVAL;
-
-	if (PAGE_ALIGN(res) >= res)
-		res = PAGE_ALIGN(res);
-	else
-		res = RES_COUNTER_MAX;
-
-	*resp = res;
-
-	return 0;
-}
-- 
cgit v1.2.3-70-g09d2


From e8ea14cc6eadfe2ea63e9989e16e62625a2619f8 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 10 Dec 2014 15:42:42 -0800
Subject: mm: memcontrol: take a css reference for each charged page

Charges currently pin the css indirectly by playing tricks during
css_offline(): user pages stall the offlining process until all of them
have been reparented, whereas kmemcg acquires a keep-alive reference if
outstanding kernel pages are detected at that point.

In preparation for removing all this complexity, make the pinning explicit
and acquire a css references for every charged page.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/cgroup.h          | 26 +++++++++++++++++++++++
 include/linux/percpu-refcount.h | 47 +++++++++++++++++++++++++++++++++--------
 mm/memcontrol.c                 | 21 ++++++++++++++----
 3 files changed, 81 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 1d519688904..9f96b25965c 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -112,6 +112,19 @@ static inline void css_get(struct cgroup_subsys_state *css)
 		percpu_ref_get(&css->refcnt);
 }
 
+/**
+ * css_get_many - obtain references on the specified css
+ * @css: target css
+ * @n: number of references to get
+ *
+ * The caller must already have a reference.
+ */
+static inline void css_get_many(struct cgroup_subsys_state *css, unsigned int n)
+{
+	if (!(css->flags & CSS_NO_REF))
+		percpu_ref_get_many(&css->refcnt, n);
+}
+
 /**
  * css_tryget - try to obtain a reference on the specified css
  * @css: target css
@@ -159,6 +172,19 @@ static inline void css_put(struct cgroup_subsys_state *css)
 		percpu_ref_put(&css->refcnt);
 }
 
+/**
+ * css_put_many - put css references
+ * @css: target css
+ * @n: number of references to put
+ *
+ * Put references obtained via css_get() and css_tryget_online().
+ */
+static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n)
+{
+	if (!(css->flags & CSS_NO_REF))
+		percpu_ref_put_many(&css->refcnt, n);
+}
+
 /* bits in struct cgroup flags field */
 enum {
 	/* Control Group requires release notifications to userspace */
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 51ce60c35f4..530b249f7ea 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -147,27 +147,41 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref,
 }
 
 /**
- * percpu_ref_get - increment a percpu refcount
+ * percpu_ref_get_many - increment a percpu refcount
  * @ref: percpu_ref to get
+ * @nr: number of references to get
  *
- * Analagous to atomic_long_inc().
+ * Analogous to atomic_long_add().
  *
  * This function is safe to call as long as @ref is between init and exit.
  */
-static inline void percpu_ref_get(struct percpu_ref *ref)
+static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr)
 {
 	unsigned long __percpu *percpu_count;
 
 	rcu_read_lock_sched();
 
 	if (__ref_is_percpu(ref, &percpu_count))
-		this_cpu_inc(*percpu_count);
+		this_cpu_add(*percpu_count, nr);
 	else
-		atomic_long_inc(&ref->count);
+		atomic_long_add(nr, &ref->count);
 
 	rcu_read_unlock_sched();
 }
 
+/**
+ * percpu_ref_get - increment a percpu refcount
+ * @ref: percpu_ref to get
+ *
+ * Analagous to atomic_long_inc().
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+static inline void percpu_ref_get(struct percpu_ref *ref)
+{
+	percpu_ref_get_many(ref, 1);
+}
+
 /**
  * percpu_ref_tryget - try to increment a percpu refcount
  * @ref: percpu_ref to try-get
@@ -231,28 +245,43 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 }
 
 /**
- * percpu_ref_put - decrement a percpu refcount
+ * percpu_ref_put_many - decrement a percpu refcount
  * @ref: percpu_ref to put
+ * @nr: number of references to put
  *
  * Decrement the refcount, and if 0, call the release function (which was passed
  * to percpu_ref_init())
  *
  * This function is safe to call as long as @ref is between init and exit.
  */
-static inline void percpu_ref_put(struct percpu_ref *ref)
+static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr)
 {
 	unsigned long __percpu *percpu_count;
 
 	rcu_read_lock_sched();
 
 	if (__ref_is_percpu(ref, &percpu_count))
-		this_cpu_dec(*percpu_count);
-	else if (unlikely(atomic_long_dec_and_test(&ref->count)))
+		this_cpu_sub(*percpu_count, nr);
+	else if (unlikely(atomic_long_sub_and_test(nr, &ref->count)))
 		ref->release(ref);
 
 	rcu_read_unlock_sched();
 }
 
+/**
+ * percpu_ref_put - decrement a percpu refcount
+ * @ref: percpu_ref to put
+ *
+ * Decrement the refcount, and if 0, call the release function (which was passed
+ * to percpu_ref_init())
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+static inline void percpu_ref_put(struct percpu_ref *ref)
+{
+	percpu_ref_put_many(ref, 1);
+}
+
 /**
  * percpu_ref_is_zero - test whether a percpu refcount reached zero
  * @ref: percpu_ref to test
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c3cd3bb77dd..f69da2ac632 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2273,6 +2273,7 @@ static void drain_stock(struct memcg_stock_pcp *stock)
 		page_counter_uncharge(&old->memory, stock->nr_pages);
 		if (do_swap_account)
 			page_counter_uncharge(&old->memsw, stock->nr_pages);
+		css_put_many(&old->css, stock->nr_pages);
 		stock->nr_pages = 0;
 	}
 	stock->cached = NULL;
@@ -2530,6 +2531,7 @@ bypass:
 	return -EINTR;
 
 done_restock:
+	css_get_many(&memcg->css, batch);
 	if (batch > nr_pages)
 		refill_stock(memcg, batch - nr_pages);
 done:
@@ -2544,6 +2546,8 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 	page_counter_uncharge(&memcg->memory, nr_pages);
 	if (do_swap_account)
 		page_counter_uncharge(&memcg->memsw, nr_pages);
+
+	css_put_many(&memcg->css, nr_pages);
 }
 
 /*
@@ -2739,6 +2743,7 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
 		page_counter_charge(&memcg->memory, nr_pages);
 		if (do_swap_account)
 			page_counter_charge(&memcg->memsw, nr_pages);
+		css_get_many(&memcg->css, nr_pages);
 		ret = 0;
 	} else if (ret)
 		page_counter_uncharge(&memcg->kmem, nr_pages);
@@ -2754,8 +2759,10 @@ static void memcg_uncharge_kmem(struct mem_cgroup *memcg,
 		page_counter_uncharge(&memcg->memsw, nr_pages);
 
 	/* Not down to 0 */
-	if (page_counter_uncharge(&memcg->kmem, nr_pages))
+	if (page_counter_uncharge(&memcg->kmem, nr_pages)) {
+		css_put_many(&memcg->css, nr_pages);
 		return;
+	}
 
 	/*
 	 * Releases a reference taken in kmem_cgroup_css_offline in case
@@ -2767,6 +2774,8 @@ static void memcg_uncharge_kmem(struct mem_cgroup *memcg,
 	 */
 	if (memcg_kmem_test_and_clear_dead(memcg))
 		css_put(&memcg->css);
+
+	css_put_many(&memcg->css, nr_pages);
 }
 
 /*
@@ -3394,10 +3403,13 @@ static int mem_cgroup_move_parent(struct page *page,
 	ret = mem_cgroup_move_account(page, nr_pages,
 				pc, child, parent);
 	if (!ret) {
+		if (!mem_cgroup_is_root(parent))
+			css_get_many(&parent->css, nr_pages);
 		/* Take charge off the local counters */
 		page_counter_cancel(&child->memory, nr_pages);
 		if (do_swap_account)
 			page_counter_cancel(&child->memsw, nr_pages);
+		css_put_many(&child->css, nr_pages);
 	}
 
 	if (nr_pages > 1)
@@ -5767,7 +5779,6 @@ static void __mem_cgroup_clear_mc(void)
 {
 	struct mem_cgroup *from = mc.from;
 	struct mem_cgroup *to = mc.to;
-	int i;
 
 	/* we must uncharge all the leftover precharges from mc.to */
 	if (mc.precharge) {
@@ -5795,8 +5806,7 @@ static void __mem_cgroup_clear_mc(void)
 		if (!mem_cgroup_is_root(mc.to))
 			page_counter_uncharge(&mc.to->memory, mc.moved_swap);
 
-		for (i = 0; i < mc.moved_swap; i++)
-			css_put(&mc.from->css);
+		css_put_many(&mc.from->css, mc.moved_swap);
 
 		/* we've already done css_get(mc.to) */
 		mc.moved_swap = 0;
@@ -6343,6 +6353,9 @@ static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
 	__this_cpu_add(memcg->stat->nr_page_events, nr_anon + nr_file);
 	memcg_check_events(memcg, dummy_page);
 	local_irq_restore(flags);
+
+	if (!mem_cgroup_is_root(memcg))
+		css_put_many(&memcg->css, max(nr_mem, nr_memsw));
 }
 
 static void uncharge_list(struct list_head *page_list)
-- 
cgit v1.2.3-70-g09d2


From 64f2199389414341ed3a570663f23616c131ba25 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 10 Dec 2014 15:42:45 -0800
Subject: mm: memcontrol: remove obsolete kmemcg pinning tricks

As charges now pin the css explicitely, there is no more need for kmemcg
to acquire a proxy reference for outstanding pages during offlining, or
maintain state to identify such "dead" groups.

This was the last user of the uncharge functions' return values, so remove
them as well.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page_counter.h |  4 +--
 mm/memcontrol.c              | 74 +-------------------------------------------
 mm/page_counter.c            | 23 +++-----------
 3 files changed, 7 insertions(+), 94 deletions(-)

(limited to 'include')

diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
index 7cce3be99ff..955421575d1 100644
--- a/include/linux/page_counter.h
+++ b/include/linux/page_counter.h
@@ -34,12 +34,12 @@ static inline unsigned long page_counter_read(struct page_counter *counter)
 	return atomic_long_read(&counter->count);
 }
 
-int page_counter_cancel(struct page_counter *counter, unsigned long nr_pages);
+void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages);
 void page_counter_charge(struct page_counter *counter, unsigned long nr_pages);
 int page_counter_try_charge(struct page_counter *counter,
 			    unsigned long nr_pages,
 			    struct page_counter **fail);
-int page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
+void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
 int page_counter_limit(struct page_counter *counter, unsigned long limit);
 int page_counter_memparse(const char *buf, unsigned long *nr_pages);
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f69da2ac632..0e6484ea268 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -369,7 +369,6 @@ struct mem_cgroup {
 /* internal only representation about the status of kmem accounting. */
 enum {
 	KMEM_ACCOUNTED_ACTIVE, /* accounted by this cgroup itself */
-	KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */
 };
 
 #ifdef CONFIG_MEMCG_KMEM
@@ -383,22 +382,6 @@ static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
 	return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
 }
 
-static void memcg_kmem_mark_dead(struct mem_cgroup *memcg)
-{
-	/*
-	 * Our caller must use css_get() first, because memcg_uncharge_kmem()
-	 * will call css_put() if it sees the memcg is dead.
-	 */
-	smp_wmb();
-	if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags))
-		set_bit(KMEM_ACCOUNTED_DEAD, &memcg->kmem_account_flags);
-}
-
-static bool memcg_kmem_test_and_clear_dead(struct mem_cgroup *memcg)
-{
-	return test_and_clear_bit(KMEM_ACCOUNTED_DEAD,
-				  &memcg->kmem_account_flags);
-}
 #endif
 
 /* Stuffs for move charges at task migration. */
@@ -2758,22 +2741,7 @@ static void memcg_uncharge_kmem(struct mem_cgroup *memcg,
 	if (do_swap_account)
 		page_counter_uncharge(&memcg->memsw, nr_pages);
 
-	/* Not down to 0 */
-	if (page_counter_uncharge(&memcg->kmem, nr_pages)) {
-		css_put_many(&memcg->css, nr_pages);
-		return;
-	}
-
-	/*
-	 * Releases a reference taken in kmem_cgroup_css_offline in case
-	 * this last uncharge is racing with the offlining code or it is
-	 * outliving the memcg existence.
-	 *
-	 * The memory barrier imposed by test&clear is paired with the
-	 * explicit one in memcg_kmem_mark_dead().
-	 */
-	if (memcg_kmem_test_and_clear_dead(memcg))
-		css_put(&memcg->css);
+	page_counter_uncharge(&memcg->kmem, nr_pages);
 
 	css_put_many(&memcg->css, nr_pages);
 }
@@ -4757,40 +4725,6 @@ static void memcg_destroy_kmem(struct mem_cgroup *memcg)
 {
 	mem_cgroup_sockets_destroy(memcg);
 }
-
-static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
-{
-	if (!memcg_kmem_is_active(memcg))
-		return;
-
-	/*
-	 * kmem charges can outlive the cgroup. In the case of slab
-	 * pages, for instance, a page contain objects from various
-	 * processes. As we prevent from taking a reference for every
-	 * such allocation we have to be careful when doing uncharge
-	 * (see memcg_uncharge_kmem) and here during offlining.
-	 *
-	 * The idea is that that only the _last_ uncharge which sees
-	 * the dead memcg will drop the last reference. An additional
-	 * reference is taken here before the group is marked dead
-	 * which is then paired with css_put during uncharge resp. here.
-	 *
-	 * Although this might sound strange as this path is called from
-	 * css_offline() when the referencemight have dropped down to 0 and
-	 * shouldn't be incremented anymore (css_tryget_online() would
-	 * fail) we do not have other options because of the kmem
-	 * allocations lifetime.
-	 */
-	css_get(&memcg->css);
-
-	memcg_kmem_mark_dead(memcg);
-
-	if (page_counter_read(&memcg->kmem))
-		return;
-
-	if (memcg_kmem_test_and_clear_dead(memcg))
-		css_put(&memcg->css);
-}
 #else
 static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
@@ -4800,10 +4734,6 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 static void memcg_destroy_kmem(struct mem_cgroup *memcg)
 {
 }
-
-static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
-{
-}
 #endif
 
 /*
@@ -5407,8 +5337,6 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	}
 	spin_unlock(&memcg->event_list_lock);
 
-	kmem_cgroup_css_offline(memcg);
-
 	/*
 	 * This requires that offlining is serialized.  Right now that is
 	 * guaranteed because css_killed_work_fn() holds the cgroup_mutex.
diff --git a/mm/page_counter.c b/mm/page_counter.c
index f0cbc082542..a009574fbba 100644
--- a/mm/page_counter.c
+++ b/mm/page_counter.c
@@ -16,19 +16,14 @@
  * page_counter_cancel - take pages out of the local counter
  * @counter: counter
  * @nr_pages: number of pages to cancel
- *
- * Returns whether there are remaining pages in the counter.
  */
-int page_counter_cancel(struct page_counter *counter, unsigned long nr_pages)
+void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages)
 {
 	long new;
 
 	new = atomic_long_sub_return(nr_pages, &counter->count);
-
 	/* More uncharges than charges? */
 	WARN_ON_ONCE(new < 0);
-
-	return new > 0;
 }
 
 /**
@@ -117,23 +112,13 @@ failed:
  * page_counter_uncharge - hierarchically uncharge pages
  * @counter: counter
  * @nr_pages: number of pages to uncharge
- *
- * Returns whether there are remaining charges in @counter.
  */
-int page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages)
+void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages)
 {
 	struct page_counter *c;
-	int ret = 1;
 
-	for (c = counter; c; c = c->parent) {
-		int remainder;
-
-		remainder = page_counter_cancel(c, nr_pages);
-		if (c == counter && !remainder)
-			ret = 0;
-	}
-
-	return ret;
+	for (c = counter; c; c = c->parent)
+		page_counter_cancel(c, nr_pages);
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 93481ff0e5a0c7636359a7ee52248856da5e7859 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Wed, 10 Dec 2014 15:43:01 -0800
Subject: mm: introduce single zone pcplists drain

The functions for draining per-cpu pages back to buddy allocators
currently always operate on all zones.  There are however several cases
where the drain is only needed in the context of a single zone, and
spilling other pcplists is a waste of time both due to the extra
spilling and later refilling.

This patch introduces new zone pointer parameter to drain_all_pages()
and changes the dummy parameter of drain_local_pages() to be also a zone
pointer.  When NULL is passed, the functions operate on all zones as
usual.  Passing a specific zone pointer reduces the work to the single
zone.

All callers are updated to pass the NULL pointer in this patch.
Conversion to single zone (where appropriate) is done in further
patches.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h |  4 +--
 mm/memory-failure.c |  4 +--
 mm/memory_hotplug.c |  4 +--
 mm/page_alloc.c     | 81 ++++++++++++++++++++++++++++++++++++-----------------
 mm/page_isolation.c |  2 +-
 5 files changed, 63 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 41b30fd4d04..07d2699cdb5 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -381,8 +381,8 @@ extern void free_kmem_pages(unsigned long addr, unsigned int order);
 
 void page_alloc_init(void);
 void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
-void drain_all_pages(void);
-void drain_local_pages(void *dummy);
+void drain_all_pages(struct zone *zone);
+void drain_local_pages(struct zone *zone);
 
 /*
  * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 8639f6b2874..851b4d7eef3 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -233,7 +233,7 @@ void shake_page(struct page *p, int access)
 		lru_add_drain_all();
 		if (PageLRU(p))
 			return;
-		drain_all_pages();
+		drain_all_pages(NULL);
 		if (PageLRU(p) || is_free_buddy_page(p))
 			return;
 	}
@@ -1661,7 +1661,7 @@ static int __soft_offline_page(struct page *page, int flags)
 			if (!is_free_buddy_page(page))
 				lru_add_drain_all();
 			if (!is_free_buddy_page(page))
-				drain_all_pages();
+				drain_all_pages(NULL);
 			SetPageHWPoison(page);
 			if (!is_free_buddy_page(page))
 				pr_info("soft offline: %#lx: page leaked\n",
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1bf4807cb21..aa0c6e5a306 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1725,7 +1725,7 @@ repeat:
 	if (drain) {
 		lru_add_drain_all();
 		cond_resched();
-		drain_all_pages();
+		drain_all_pages(NULL);
 	}
 
 	pfn = scan_movable_pages(start_pfn, end_pfn);
@@ -1747,7 +1747,7 @@ repeat:
 	lru_add_drain_all();
 	yield();
 	/* drain pcp pages, this is synchronous. */
-	drain_all_pages();
+	drain_all_pages(NULL);
 	/*
 	 * dissolve free hugepages in the memory block before doing offlining
 	 * actually in order to make hugetlbfs's object counting consistent.
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 701fe9018fd..13d5796de8f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1267,55 +1267,75 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 #endif
 
 /*
- * Drain pages of the indicated processor.
+ * Drain pcplists of the indicated processor and zone.
  *
  * The processor must either be the current processor and the
  * thread pinned to the current processor or a processor that
  * is not online.
  */
-static void drain_pages(unsigned int cpu)
+static void drain_pages_zone(unsigned int cpu, struct zone *zone)
 {
 	unsigned long flags;
-	struct zone *zone;
+	struct per_cpu_pageset *pset;
+	struct per_cpu_pages *pcp;
 
-	for_each_populated_zone(zone) {
-		struct per_cpu_pageset *pset;
-		struct per_cpu_pages *pcp;
+	local_irq_save(flags);
+	pset = per_cpu_ptr(zone->pageset, cpu);
 
-		local_irq_save(flags);
-		pset = per_cpu_ptr(zone->pageset, cpu);
+	pcp = &pset->pcp;
+	if (pcp->count) {
+		free_pcppages_bulk(zone, pcp->count, pcp);
+		pcp->count = 0;
+	}
+	local_irq_restore(flags);
+}
 
-		pcp = &pset->pcp;
-		if (pcp->count) {
-			free_pcppages_bulk(zone, pcp->count, pcp);
-			pcp->count = 0;
-		}
-		local_irq_restore(flags);
+/*
+ * Drain pcplists of all zones on the indicated processor.
+ *
+ * The processor must either be the current processor and the
+ * thread pinned to the current processor or a processor that
+ * is not online.
+ */
+static void drain_pages(unsigned int cpu)
+{
+	struct zone *zone;
+
+	for_each_populated_zone(zone) {
+		drain_pages_zone(cpu, zone);
 	}
 }
 
 /*
  * Spill all of this CPU's per-cpu pages back into the buddy allocator.
+ *
+ * The CPU has to be pinned. When zone parameter is non-NULL, spill just
+ * the single zone's pages.
  */
-void drain_local_pages(void *arg)
+void drain_local_pages(struct zone *zone)
 {
-	drain_pages(smp_processor_id());
+	int cpu = smp_processor_id();
+
+	if (zone)
+		drain_pages_zone(cpu, zone);
+	else
+		drain_pages(cpu);
 }
 
 /*
  * Spill all the per-cpu pages from all CPUs back into the buddy allocator.
  *
+ * When zone parameter is non-NULL, spill just the single zone's pages.
+ *
  * Note that this code is protected against sending an IPI to an offline
  * CPU but does not guarantee sending an IPI to newly hotplugged CPUs:
  * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but
  * nothing keeps CPUs from showing up after we populated the cpumask and
  * before the call to on_each_cpu_mask().
  */
-void drain_all_pages(void)
+void drain_all_pages(struct zone *zone)
 {
 	int cpu;
-	struct per_cpu_pageset *pcp;
-	struct zone *zone;
 
 	/*
 	 * Allocate in the BSS so we wont require allocation in
@@ -1330,20 +1350,31 @@ void drain_all_pages(void)
 	 * disables preemption as part of its processing
 	 */
 	for_each_online_cpu(cpu) {
+		struct per_cpu_pageset *pcp;
+		struct zone *z;
 		bool has_pcps = false;
-		for_each_populated_zone(zone) {
+
+		if (zone) {
 			pcp = per_cpu_ptr(zone->pageset, cpu);
-			if (pcp->pcp.count) {
+			if (pcp->pcp.count)
 				has_pcps = true;
-				break;
+		} else {
+			for_each_populated_zone(z) {
+				pcp = per_cpu_ptr(z->pageset, cpu);
+				if (pcp->pcp.count) {
+					has_pcps = true;
+					break;
+				}
 			}
 		}
+
 		if (has_pcps)
 			cpumask_set_cpu(cpu, &cpus_with_pcps);
 		else
 			cpumask_clear_cpu(cpu, &cpus_with_pcps);
 	}
-	on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1);
+	on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages,
+								zone, 1);
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -2433,7 +2464,7 @@ retry:
 	 * pages are pinned on the per-cpu lists. Drain them and try again
 	 */
 	if (!page && !drained) {
-		drain_all_pages();
+		drain_all_pages(NULL);
 		drained = true;
 		goto retry;
 	}
@@ -6385,7 +6416,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	 */
 
 	lru_add_drain_all();
-	drain_all_pages();
+	drain_all_pages(NULL);
 
 	order = 0;
 	outer_start = start;
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index c8778f7e208..f2452e5116b 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -68,7 +68,7 @@ out:
 
 	spin_unlock_irqrestore(&zone->lock, flags);
 	if (!ret)
-		drain_all_pages();
+		drain_all_pages(NULL);
 	return ret;
 }
 
-- 
cgit v1.2.3-70-g09d2


From ebff398017c69a3810bcbc5200ba224d5ccaa207 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Wed, 10 Dec 2014 15:43:22 -0800
Subject: mm, compaction: pass classzone_idx and alloc_flags to watermark
 checking

Compaction relies on zone watermark checks for decisions such as if it's
worth to start compacting in compaction_suitable() or whether compaction
should stop in compact_finished().  The watermark checks take
classzone_idx and alloc_flags parameters, which are related to the memory
allocation request.  But from the context of compaction they are currently
passed as 0, including the direct compaction which is invoked to satisfy
the allocation request, and could therefore know the proper values.

The lack of proper values can lead to mismatch between decisions taken
during compaction and decisions related to the allocation request.  Lack
of proper classzone_idx value means that lowmem_reserve is not taken into
account.  This has manifested (during recent changes to deferred
compaction) when DMA zone was used as fallback for preferred Normal zone.
compaction_suitable() without proper classzone_idx would think that the
watermarks are already satisfied, but watermark check in
get_page_from_freelist() would fail.  Because of this problem, deferring
compaction has extra complexity that can be removed in the following
patch.

The issue (not confirmed in practice) with missing alloc_flags is opposite
in nature.  For allocations that include ALLOC_HIGH, ALLOC_HIGHER or
ALLOC_CMA in alloc_flags (the last includes all MOVABLE allocations on
CMA-enabled systems) the watermark checking in compaction with 0 passed
will be stricter than in get_page_from_freelist().  In these cases
compaction might be running for a longer time than is really needed.

Another issue compaction_suitable() is that the check for "does the zone
need compaction at all?" comes only after the check "does the zone have
enough free free pages to succeed compaction".  The latter considers extra
pages for migration and can therefore in some situations fail and return
COMPACT_SKIPPED, although the high-order allocation would succeed and we
should return COMPACT_PARTIAL.

This patch fixes these problems by adding alloc_flags and classzone_idx to
struct compact_control and related functions involved in direct compaction
and watermark checking.  Where possible, all other callers of
compaction_suitable() pass proper values where those are known.  This is
currently limited to classzone_idx, which is sometimes known in kswapd
context.  However, the direct reclaim callers should_continue_reclaim()
and compaction_ready() do not currently know the proper values, so the
coordination between reclaim and compaction may still not be as accurate
as it could.  This can be fixed later, if it's shown to be an issue.

Additionaly the checks in compact_suitable() are reordered to address the
second issue described above.

The effect of this patch should be slightly better high-order allocation
success rates and/or less compaction overhead, depending on the type of
allocations and presence of CMA.  It allows simplifying deferred
compaction code in a followup patch.

When testing with stress-highalloc, there was some slight improvement
(which might be just due to variance) in success rates of non-THP-like
allocations.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Christoph Lameter <cl@linux.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h |  8 ++++++--
 mm/compaction.c            | 48 ++++++++++++++++++++++++++--------------------
 mm/internal.h              |  2 ++
 mm/page_alloc.c            |  1 +
 mm/vmscan.c                | 12 ++++++------
 5 files changed, 42 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 60bdf8dc02a..d896765a15b 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -33,10 +33,12 @@ extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
 			enum migrate_mode mode, int *contended,
+			int alloc_flags, int classzone_idx,
 			struct zone **candidate_zone);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
-extern unsigned long compaction_suitable(struct zone *zone, int order);
+extern unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx);
 
 /* Do not skip compaction more than 64 times */
 #define COMPACT_MAX_DEFER_SHIFT 6
@@ -103,6 +105,7 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
 			enum migrate_mode mode, int *contended,
+			int alloc_flags, int classzone_idx,
 			struct zone **candidate_zone)
 {
 	return COMPACT_CONTINUE;
@@ -116,7 +119,8 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat)
 {
 }
 
-static inline unsigned long compaction_suitable(struct zone *zone, int order)
+static inline unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx)
 {
 	return COMPACT_SKIPPED;
 }
diff --git a/mm/compaction.c b/mm/compaction.c
index f9792ba3537..1fc6736815e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1086,9 +1086,9 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
 
 	/* Compaction run is not finished if the watermark is not met */
 	watermark = low_wmark_pages(zone);
-	watermark += (1 << cc->order);
 
-	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
+	if (!zone_watermark_ok(zone, cc->order, watermark, cc->classzone_idx,
+							cc->alloc_flags))
 		return COMPACT_CONTINUE;
 
 	/* Direct compactor: Is a suitable page free? */
@@ -1114,7 +1114,8 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
  *   COMPACT_PARTIAL  - If the allocation would succeed without compaction
  *   COMPACT_CONTINUE - If compaction should run now
  */
-unsigned long compaction_suitable(struct zone *zone, int order)
+unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx)
 {
 	int fragindex;
 	unsigned long watermark;
@@ -1126,21 +1127,30 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 	if (order == -1)
 		return COMPACT_CONTINUE;
 
+	watermark = low_wmark_pages(zone);
+	/*
+	 * If watermarks for high-order allocation are already met, there
+	 * should be no need for compaction at all.
+	 */
+	if (zone_watermark_ok(zone, order, watermark, classzone_idx,
+								alloc_flags))
+		return COMPACT_PARTIAL;
+
 	/*
 	 * Watermarks for order-0 must be met for compaction. Note the 2UL.
 	 * This is because during migration, copies of pages need to be
 	 * allocated and for a short time, the footprint is higher
 	 */
-	watermark = low_wmark_pages(zone) + (2UL << order);
-	if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+	watermark += (2UL << order);
+	if (!zone_watermark_ok(zone, 0, watermark, classzone_idx, alloc_flags))
 		return COMPACT_SKIPPED;
 
 	/*
 	 * fragmentation index determines if allocation failures are due to
 	 * low memory or external fragmentation
 	 *
-	 * index of -1000 implies allocations might succeed depending on
-	 * watermarks
+	 * index of -1000 would imply allocations might succeed depending on
+	 * watermarks, but we already failed the high-order watermark check
 	 * index towards 0 implies failure is due to lack of memory
 	 * index towards 1000 implies failure is due to fragmentation
 	 *
@@ -1150,10 +1160,6 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 	if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
 		return COMPACT_SKIPPED;
 
-	if (fragindex == -1000 && zone_watermark_ok(zone, order, watermark,
-	    0, 0))
-		return COMPACT_PARTIAL;
-
 	return COMPACT_CONTINUE;
 }
 
@@ -1165,7 +1171,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	const int migratetype = gfpflags_to_migratetype(cc->gfp_mask);
 	const bool sync = cc->mode != MIGRATE_ASYNC;
 
-	ret = compaction_suitable(zone, cc->order);
+	ret = compaction_suitable(zone, cc->order, cc->alloc_flags,
+							cc->classzone_idx);
 	switch (ret) {
 	case COMPACT_PARTIAL:
 	case COMPACT_SKIPPED:
@@ -1254,7 +1261,8 @@ out:
 }
 
 static unsigned long compact_zone_order(struct zone *zone, int order,
-		gfp_t gfp_mask, enum migrate_mode mode, int *contended)
+		gfp_t gfp_mask, enum migrate_mode mode, int *contended,
+		int alloc_flags, int classzone_idx)
 {
 	unsigned long ret;
 	struct compact_control cc = {
@@ -1264,6 +1272,8 @@ static unsigned long compact_zone_order(struct zone *zone, int order,
 		.gfp_mask = gfp_mask,
 		.zone = zone,
 		.mode = mode,
+		.alloc_flags = alloc_flags,
+		.classzone_idx = classzone_idx,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -1295,6 +1305,7 @@ int sysctl_extfrag_threshold = 500;
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
 			enum migrate_mode mode, int *contended,
+			int alloc_flags, int classzone_idx,
 			struct zone **candidate_zone)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
@@ -1303,7 +1314,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	int rc = COMPACT_DEFERRED;
-	int alloc_flags = 0;
 	int all_zones_contended = COMPACT_CONTENDED_LOCK; /* init for &= op */
 
 	*contended = COMPACT_CONTENDED_NONE;
@@ -1312,10 +1322,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	if (!order || !may_enter_fs || !may_perform_io)
 		return COMPACT_SKIPPED;
 
-#ifdef CONFIG_CMA
-	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
-		alloc_flags |= ALLOC_CMA;
-#endif
 	/* Compact each zone in the list */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
 								nodemask) {
@@ -1326,7 +1332,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			continue;
 
 		status = compact_zone_order(zone, order, gfp_mask, mode,
-							&zone_contended);
+				&zone_contended, alloc_flags, classzone_idx);
 		rc = max(status, rc);
 		/*
 		 * It takes at least one zone that wasn't lock contended
@@ -1335,8 +1341,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 		all_zones_contended &= zone_contended;
 
 		/* If a normal allocation would succeed, stop compacting */
-		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0,
-				      alloc_flags)) {
+		if (zone_watermark_ok(zone, order, low_wmark_pages(zone),
+					classzone_idx, alloc_flags)) {
 			*candidate_zone = zone;
 			/*
 			 * We think the allocation will succeed in this zone,
diff --git a/mm/internal.h b/mm/internal.h
index a4f90ba7068..b643938fcf1 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -168,6 +168,8 @@ struct compact_control {
 
 	int order;			/* order a direct compactor needs */
 	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
+	const int alloc_flags;		/* alloc flags of a direct compactor */
+	const int classzone_idx;	/* zone index of a direct compactor */
 	struct zone *zone;
 	int contended;			/* Signal need_sched() or lock
 					 * contention detected during
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b7c18f09469..e32121fa2ba 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2341,6 +2341,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	compact_result = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, mode,
 						contended_compaction,
+						alloc_flags, classzone_idx,
 						&last_compact_zone);
 	current->flags &= ~PF_MEMALLOC;
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 53157e15706..4636d9e822c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2249,7 +2249,7 @@ static inline bool should_continue_reclaim(struct zone *zone,
 		return true;
 
 	/* If compaction would go ahead or the allocation would succeed, stop */
-	switch (compaction_suitable(zone, sc->order)) {
+	switch (compaction_suitable(zone, sc->order, 0, 0)) {
 	case COMPACT_PARTIAL:
 	case COMPACT_CONTINUE:
 		return false;
@@ -2346,7 +2346,7 @@ static inline bool compaction_ready(struct zone *zone, int order)
 	 * If compaction is not ready to start and allocation is not likely
 	 * to succeed without it, then keep reclaiming.
 	 */
-	if (compaction_suitable(zone, order) == COMPACT_SKIPPED)
+	if (compaction_suitable(zone, order, 0, 0) == COMPACT_SKIPPED)
 		return false;
 
 	return watermark_ok;
@@ -2824,8 +2824,8 @@ static bool zone_balanced(struct zone *zone, int order,
 				    balance_gap, classzone_idx, 0))
 		return false;
 
-	if (IS_ENABLED(CONFIG_COMPACTION) && order &&
-	    compaction_suitable(zone, order) == COMPACT_SKIPPED)
+	if (IS_ENABLED(CONFIG_COMPACTION) && order && compaction_suitable(zone,
+				order, 0, classzone_idx) == COMPACT_SKIPPED)
 		return false;
 
 	return true;
@@ -2952,8 +2952,8 @@ static bool kswapd_shrink_zone(struct zone *zone,
 	 * from memory. Do not reclaim more than needed for compaction.
 	 */
 	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
-			compaction_suitable(zone, sc->order) !=
-				COMPACT_SKIPPED)
+			compaction_suitable(zone, sc->order, 0, classzone_idx)
+							!= COMPACT_SKIPPED)
 		testorder = 0;
 
 	/*
-- 
cgit v1.2.3-70-g09d2


From 97d47a65be1e513edd02325ae828c9997878b578 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Wed, 10 Dec 2014 15:43:25 -0800
Subject: mm, compaction: simplify deferred compaction

Since commit 53853e2d2bfb ("mm, compaction: defer each zone individually
instead of preferred zone"), compaction is deferred for each zone where
sync direct compaction fails, and reset where it succeeds.  However, it
was observed that for DMA zone compaction often appeared to succeed
while subsequent allocation attempt would not, due to different outcome
of watermark check.

In order to properly defer compaction in this zone, the candidate zone
has to be passed back to __alloc_pages_direct_compact() and compaction
deferred in the zone after the allocation attempt fails.

The large source of mismatch between watermark check in compaction and
allocation was the lack of alloc_flags and classzone_idx values in
compaction, which has been fixed in the previous patch.  So with this
problem fixed, we can simplify the code by removing the candidate_zone
parameter and deferring in __alloc_pages_direct_compact().

After this patch, the compaction activity during stress-highalloc
benchmark is still somewhat increased, but it's negligible compared to the
increase that occurred without the better watermark checking.  This
suggests that it is still possible to apparently succeed in compaction but
fail to allocate, possibly due to parallel allocation activity.

[akpm@linux-foundation.org: fix build]
Suggested-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h |  6 ++----
 mm/compaction.c            |  5 +----
 mm/page_alloc.c            | 12 +-----------
 3 files changed, 4 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index d896765a15b..3238ffa33f6 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -33,8 +33,7 @@ extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
 			enum migrate_mode mode, int *contended,
-			int alloc_flags, int classzone_idx,
-			struct zone **candidate_zone);
+			int alloc_flags, int classzone_idx);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern unsigned long compaction_suitable(struct zone *zone, int order,
@@ -105,8 +104,7 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
 			enum migrate_mode mode, int *contended,
-			int alloc_flags, int classzone_idx,
-			struct zone **candidate_zone)
+			int alloc_flags, int classzone_idx)
 {
 	return COMPACT_CONTINUE;
 }
diff --git a/mm/compaction.c b/mm/compaction.c
index 1fc6736815e..75f4c1206d0 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1298,15 +1298,13 @@ int sysctl_extfrag_threshold = 500;
  * @mode: The migration mode for async, sync light, or sync migration
  * @contended: Return value that determines if compaction was aborted due to
  *	       need_resched() or lock contention
- * @candidate_zone: Return the zone where we think allocation should succeed
  *
  * This is the main entry point for direct page compaction.
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
 			enum migrate_mode mode, int *contended,
-			int alloc_flags, int classzone_idx,
-			struct zone **candidate_zone)
+			int alloc_flags, int classzone_idx)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
@@ -1343,7 +1341,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 		/* If a normal allocation would succeed, stop compacting */
 		if (zone_watermark_ok(zone, order, low_wmark_pages(zone),
 					classzone_idx, alloc_flags)) {
-			*candidate_zone = zone;
 			/*
 			 * We think the allocation will succeed in this zone,
 			 * but it is not certain, hence the false. The caller
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e32121fa2ba..edb0ce1e7cf 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2330,7 +2330,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	int classzone_idx, int migratetype, enum migrate_mode mode,
 	int *contended_compaction, bool *deferred_compaction)
 {
-	struct zone *last_compact_zone = NULL;
 	unsigned long compact_result;
 	struct page *page;
 
@@ -2341,8 +2340,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	compact_result = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, mode,
 						contended_compaction,
-						alloc_flags, classzone_idx,
-						&last_compact_zone);
+						alloc_flags, classzone_idx);
 	current->flags &= ~PF_MEMALLOC;
 
 	switch (compact_result) {
@@ -2379,14 +2377,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		return page;
 	}
 
-	/*
-	 * last_compact_zone is where try_to_compact_pages thought allocation
-	 * should succeed, so it did not defer compaction. But here we know
-	 * that it didn't succeed, so we do the defer.
-	 */
-	if (last_compact_zone && mode != MIGRATE_ASYNC)
-		defer_compaction(last_compact_zone, order);
-
 	/*
 	 * It's bad if compaction run occurs and fails. The most likely reason
 	 * is that pages exist, but not enough to satisfy watermarks.
-- 
cgit v1.2.3-70-g09d2


From 18eca2e636f921e6350dc31b5b450bb4102d664f Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 10 Dec 2014 15:43:57 -0800
Subject: mm: memcontrol: remove unnecessary PCG_MEMSW memory+swap charge flag

Now that mem_cgroup_swapout() fully uncharges the page, every page that is
still in use when reaching mem_cgroup_uncharge() is known to carry both
the memory and the memory+swap charge.  Simplify the uncharge path and
remove the PCG_MEMSW page flag accordingly.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page_cgroup.h |  1 -
 mm/memcontrol.c             | 34 ++++++++++++----------------------
 2 files changed, 12 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 5c831f1eca7..da62ee2be28 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -5,7 +5,6 @@ enum {
 	/* flags for mem_cgroup */
 	PCG_USED = 0x01,	/* This page is charged to a memcg */
 	PCG_MEM = 0x02,		/* This page holds a memory charge */
-	PCG_MEMSW = 0x04,	/* This page holds a memory+swap charge */
 };
 
 struct pglist_data;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 266a440c89f..baf3b535b18 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2614,7 +2614,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 	 *   have the page locked
 	 */
 	pc->mem_cgroup = memcg;
-	pc->flags = PCG_USED | PCG_MEM | (do_swap_account ? PCG_MEMSW : 0);
+	pc->flags = PCG_USED | PCG_MEM;
 
 	if (lrucare)
 		unlock_page_lru(page, isolated);
@@ -5793,7 +5793,6 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	if (!PageCgroupUsed(pc))
 		return;
 
-	VM_BUG_ON_PAGE(!(pc->flags & PCG_MEMSW), page);
 	memcg = pc->mem_cgroup;
 
 	oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
@@ -5989,17 +5988,16 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg)
 }
 
 static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
-			   unsigned long nr_mem, unsigned long nr_memsw,
 			   unsigned long nr_anon, unsigned long nr_file,
 			   unsigned long nr_huge, struct page *dummy_page)
 {
+	unsigned long nr_pages = nr_anon + nr_file;
 	unsigned long flags;
 
 	if (!mem_cgroup_is_root(memcg)) {
-		if (nr_mem)
-			page_counter_uncharge(&memcg->memory, nr_mem);
-		if (nr_memsw)
-			page_counter_uncharge(&memcg->memsw, nr_memsw);
+		page_counter_uncharge(&memcg->memory, nr_pages);
+		if (do_swap_account)
+			page_counter_uncharge(&memcg->memsw, nr_pages);
 		memcg_oom_recover(memcg);
 	}
 
@@ -6008,23 +6006,21 @@ static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
 	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_file);
 	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_huge);
 	__this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT], pgpgout);
-	__this_cpu_add(memcg->stat->nr_page_events, nr_anon + nr_file);
+	__this_cpu_add(memcg->stat->nr_page_events, nr_pages);
 	memcg_check_events(memcg, dummy_page);
 	local_irq_restore(flags);
 
 	if (!mem_cgroup_is_root(memcg))
-		css_put_many(&memcg->css, max(nr_mem, nr_memsw));
+		css_put_many(&memcg->css, nr_pages);
 }
 
 static void uncharge_list(struct list_head *page_list)
 {
 	struct mem_cgroup *memcg = NULL;
-	unsigned long nr_memsw = 0;
 	unsigned long nr_anon = 0;
 	unsigned long nr_file = 0;
 	unsigned long nr_huge = 0;
 	unsigned long pgpgout = 0;
-	unsigned long nr_mem = 0;
 	struct list_head *next;
 	struct page *page;
 
@@ -6051,10 +6047,9 @@ static void uncharge_list(struct list_head *page_list)
 
 		if (memcg != pc->mem_cgroup) {
 			if (memcg) {
-				uncharge_batch(memcg, pgpgout, nr_mem, nr_memsw,
-					       nr_anon, nr_file, nr_huge, page);
-				pgpgout = nr_mem = nr_memsw = 0;
-				nr_anon = nr_file = nr_huge = 0;
+				uncharge_batch(memcg, pgpgout, nr_anon, nr_file,
+					       nr_huge, page);
+				pgpgout = nr_anon = nr_file = nr_huge = 0;
 			}
 			memcg = pc->mem_cgroup;
 		}
@@ -6070,18 +6065,14 @@ static void uncharge_list(struct list_head *page_list)
 		else
 			nr_file += nr_pages;
 
-		if (pc->flags & PCG_MEM)
-			nr_mem += nr_pages;
-		if (pc->flags & PCG_MEMSW)
-			nr_memsw += nr_pages;
 		pc->flags = 0;
 
 		pgpgout++;
 	} while (next != page_list);
 
 	if (memcg)
-		uncharge_batch(memcg, pgpgout, nr_mem, nr_memsw,
-			       nr_anon, nr_file, nr_huge, page);
+		uncharge_batch(memcg, pgpgout, nr_anon, nr_file,
+			       nr_huge, page);
 }
 
 /**
@@ -6166,7 +6157,6 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 		return;
 
 	VM_BUG_ON_PAGE(!(pc->flags & PCG_MEM), oldpage);
-	VM_BUG_ON_PAGE(do_swap_account && !(pc->flags & PCG_MEMSW), oldpage);
 
 	if (lrucare)
 		lock_page_lru(oldpage, &isolated);
-- 
cgit v1.2.3-70-g09d2


From f4aaa8b43d90294ca7546317997c452600e9a8a7 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 10 Dec 2014 15:44:00 -0800
Subject: mm: memcontrol: remove unnecessary PCG_MEM memory charge flag

PCG_MEM is a remnant from an earlier version of 0a31bc97c80c ("mm:
memcontrol: rewrite uncharge API"), used to tell whether migration cleared
a charge while leaving pc->mem_cgroup valid and PCG_USED set.  But in the
final version, mem_cgroup_migrate() directly uncharges the source page,
rendering this distinction unnecessary.  Remove it.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page_cgroup.h | 1 -
 mm/memcontrol.c             | 4 +---
 2 files changed, 1 insertion(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index da62ee2be28..97536e68584 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -4,7 +4,6 @@
 enum {
 	/* flags for mem_cgroup */
 	PCG_USED = 0x01,	/* This page is charged to a memcg */
-	PCG_MEM = 0x02,		/* This page holds a memory charge */
 };
 
 struct pglist_data;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index baf3b535b18..3dfb56a9311 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2614,7 +2614,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 	 *   have the page locked
 	 */
 	pc->mem_cgroup = memcg;
-	pc->flags = PCG_USED | PCG_MEM;
+	pc->flags = PCG_USED;
 
 	if (lrucare)
 		unlock_page_lru(page, isolated);
@@ -6156,8 +6156,6 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 	if (!PageCgroupUsed(pc))
 		return;
 
-	VM_BUG_ON_PAGE(!(pc->flags & PCG_MEM), oldpage);
-
 	if (lrucare)
 		lock_page_lru(oldpage, &isolated);
 
-- 
cgit v1.2.3-70-g09d2


From 2983331575bfb248abfb02efb5140b4a299e3f45 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 10 Dec 2014 15:44:02 -0800
Subject: mm: memcontrol: remove unnecessary PCG_USED pc->mem_cgroup valid flag

pc->mem_cgroup had to be left intact after uncharge for the final LRU
removal, and !PCG_USED indicated whether the page was uncharged.  But
since commit 0a31bc97c80c ("mm: memcontrol: rewrite uncharge API") pages
are uncharged after the final LRU removal.  Uncharge can simply clear
the pointer and the PCG_USED/PageCgroupUsed sites can test that instead.

Because this is the last page_cgroup flag, this patch reduces the memcg
per-page overhead to a single pointer.

[akpm@linux-foundation.org: remove unneeded initialization of `memcg', per Michal]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page_cgroup.h |  10 -----
 mm/memcontrol.c             | 107 +++++++++++++++++---------------------------
 2 files changed, 41 insertions(+), 76 deletions(-)

(limited to 'include')

diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 97536e68584..1289be6b436 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -1,11 +1,6 @@
 #ifndef __LINUX_PAGE_CGROUP_H
 #define __LINUX_PAGE_CGROUP_H
 
-enum {
-	/* flags for mem_cgroup */
-	PCG_USED = 0x01,	/* This page is charged to a memcg */
-};
-
 struct pglist_data;
 
 #ifdef CONFIG_MEMCG
@@ -19,7 +14,6 @@ struct mem_cgroup;
  * then the page cgroup for pfn always exists.
  */
 struct page_cgroup {
-	unsigned long flags;
 	struct mem_cgroup *mem_cgroup;
 };
 
@@ -39,10 +33,6 @@ static inline void page_cgroup_init(void)
 
 struct page_cgroup *lookup_page_cgroup(struct page *page);
 
-static inline int PageCgroupUsed(struct page_cgroup *pc)
-{
-	return !!(pc->flags & PCG_USED);
-}
 #else /* !CONFIG_MEMCG */
 struct page_cgroup;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3dfb56a9311..09fece0eb9f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1284,14 +1284,12 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 
 	pc = lookup_page_cgroup(page);
 	memcg = pc->mem_cgroup;
-
 	/*
 	 * Swapcache readahead pages are added to the LRU - and
-	 * possibly migrated - before they are charged.  Ensure
-	 * pc->mem_cgroup is sane.
+	 * possibly migrated - before they are charged.
 	 */
-	if (!PageLRU(page) && !PageCgroupUsed(pc) && memcg != root_mem_cgroup)
-		pc->mem_cgroup = memcg = root_mem_cgroup;
+	if (!memcg)
+		memcg = root_mem_cgroup;
 
 	mz = mem_cgroup_page_zoneinfo(memcg, page);
 	lruvec = &mz->lruvec;
@@ -2151,7 +2149,7 @@ struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page,
 	pc = lookup_page_cgroup(page);
 again:
 	memcg = pc->mem_cgroup;
-	if (unlikely(!memcg || !PageCgroupUsed(pc)))
+	if (unlikely(!memcg))
 		return NULL;
 
 	*locked = false;
@@ -2159,7 +2157,7 @@ again:
 		return memcg;
 
 	move_lock_mem_cgroup(memcg, flags);
-	if (memcg != pc->mem_cgroup || !PageCgroupUsed(pc)) {
+	if (memcg != pc->mem_cgroup) {
 		move_unlock_mem_cgroup(memcg, flags);
 		goto again;
 	}
@@ -2525,7 +2523,7 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
  */
 struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 {
-	struct mem_cgroup *memcg = NULL;
+	struct mem_cgroup *memcg;
 	struct page_cgroup *pc;
 	unsigned short id;
 	swp_entry_t ent;
@@ -2533,9 +2531,10 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
 	pc = lookup_page_cgroup(page);
-	if (PageCgroupUsed(pc)) {
-		memcg = pc->mem_cgroup;
-		if (memcg && !css_tryget_online(&memcg->css))
+	memcg = pc->mem_cgroup;
+
+	if (memcg) {
+		if (!css_tryget_online(&memcg->css))
 			memcg = NULL;
 	} else if (PageSwapCache(page)) {
 		ent.val = page_private(page);
@@ -2586,7 +2585,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 	struct page_cgroup *pc = lookup_page_cgroup(page);
 	int isolated;
 
-	VM_BUG_ON_PAGE(PageCgroupUsed(pc), page);
+	VM_BUG_ON_PAGE(pc->mem_cgroup, page);
 	/*
 	 * we don't need page_cgroup_lock about tail pages, becase they are not
 	 * accessed by any other context at this point.
@@ -2601,7 +2600,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 
 	/*
 	 * Nobody should be changing or seriously looking at
-	 * pc->mem_cgroup and pc->flags at this point:
+	 * pc->mem_cgroup at this point:
 	 *
 	 * - the page is uncharged
 	 *
@@ -2614,7 +2613,6 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 	 *   have the page locked
 	 */
 	pc->mem_cgroup = memcg;
-	pc->flags = PCG_USED;
 
 	if (lrucare)
 		unlock_page_lru(page, isolated);
@@ -3126,37 +3124,22 @@ void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
 		memcg_uncharge_kmem(memcg, 1 << order);
 		return;
 	}
-	/*
-	 * The page is freshly allocated and not visible to any
-	 * outside callers yet.  Set up pc non-atomically.
-	 */
 	pc = lookup_page_cgroup(page);
 	pc->mem_cgroup = memcg;
-	pc->flags = PCG_USED;
 }
 
 void __memcg_kmem_uncharge_pages(struct page *page, int order)
 {
-	struct mem_cgroup *memcg = NULL;
-	struct page_cgroup *pc;
-
-
-	pc = lookup_page_cgroup(page);
-	if (!PageCgroupUsed(pc))
-		return;
-
-	memcg = pc->mem_cgroup;
-	pc->flags = 0;
+	struct page_cgroup *pc = lookup_page_cgroup(page);
+	struct mem_cgroup *memcg = pc->mem_cgroup;
 
-	/*
-	 * We trust that only if there is a memcg associated with the page, it
-	 * is a valid allocation
-	 */
 	if (!memcg)
 		return;
 
 	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
+
 	memcg_uncharge_kmem(memcg, 1 << order);
+	pc->mem_cgroup = NULL;
 }
 #else
 static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg)
@@ -3174,23 +3157,16 @@ static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg)
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {
-	struct page_cgroup *head_pc;
-	struct page_cgroup *pc;
-	struct mem_cgroup *memcg;
+	struct page_cgroup *pc = lookup_page_cgroup(head);
 	int i;
 
 	if (mem_cgroup_disabled())
 		return;
 
-	head_pc = lookup_page_cgroup(head);
+	for (i = 1; i < HPAGE_PMD_NR; i++)
+		pc[i].mem_cgroup = pc[0].mem_cgroup;
 
-	memcg = head_pc->mem_cgroup;
-	for (i = 1; i < HPAGE_PMD_NR; i++) {
-		pc = head_pc + i;
-		pc->mem_cgroup = memcg;
-		pc->flags = head_pc->flags;
-	}
-	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
+	__this_cpu_sub(pc[0].mem_cgroup->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
 		       HPAGE_PMD_NR);
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -3240,7 +3216,7 @@ static int mem_cgroup_move_account(struct page *page,
 		goto out;
 
 	ret = -EINVAL;
-	if (!PageCgroupUsed(pc) || pc->mem_cgroup != from)
+	if (pc->mem_cgroup != from)
 		goto out_unlock;
 
 	move_lock_mem_cgroup(from, &flags);
@@ -3350,7 +3326,7 @@ static struct page_cgroup *lookup_page_cgroup_used(struct page *page)
 	 * the first time, i.e. during boot or memory hotplug;
 	 * or when mem_cgroup_disabled().
 	 */
-	if (likely(pc) && PageCgroupUsed(pc))
+	if (likely(pc) && pc->mem_cgroup)
 		return pc;
 	return NULL;
 }
@@ -3368,10 +3344,8 @@ void mem_cgroup_print_bad_page(struct page *page)
 	struct page_cgroup *pc;
 
 	pc = lookup_page_cgroup_used(page);
-	if (pc) {
-		pr_alert("pc:%p pc->flags:%lx pc->mem_cgroup:%p\n",
-			 pc, pc->flags, pc->mem_cgroup);
-	}
+	if (pc)
+		pr_alert("pc:%p pc->mem_cgroup:%p\n", pc, pc->mem_cgroup);
 }
 #endif
 
@@ -5308,7 +5282,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 		 * mem_cgroup_move_account() checks the pc is valid or
 		 * not under LRU exclusion.
 		 */
-		if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) {
+		if (pc->mem_cgroup == mc.from) {
 			ret = MC_TARGET_PAGE;
 			if (target)
 				target->page = page;
@@ -5344,7 +5318,7 @@ static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
 	if (!move_anon())
 		return ret;
 	pc = lookup_page_cgroup(page);
-	if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) {
+	if (pc->mem_cgroup == mc.from) {
 		ret = MC_TARGET_PAGE;
 		if (target) {
 			get_page(page);
@@ -5788,18 +5762,17 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 		return;
 
 	pc = lookup_page_cgroup(page);
+	memcg = pc->mem_cgroup;
 
 	/* Readahead page, never charged */
-	if (!PageCgroupUsed(pc))
+	if (!memcg)
 		return;
 
-	memcg = pc->mem_cgroup;
-
 	oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
 	VM_BUG_ON_PAGE(oldid, page);
 	mem_cgroup_swap_statistics(memcg, true);
 
-	pc->flags = 0;
+	pc->mem_cgroup = NULL;
 
 	if (!mem_cgroup_is_root(memcg))
 		page_counter_uncharge(&memcg->memory, 1);
@@ -5874,7 +5847,7 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 		 * the page lock, which serializes swap cache removal, which
 		 * in turn serializes uncharging.
 		 */
-		if (PageCgroupUsed(pc))
+		if (pc->mem_cgroup)
 			goto out;
 	}
 
@@ -6036,13 +6009,13 @@ static void uncharge_list(struct list_head *page_list)
 		VM_BUG_ON_PAGE(page_count(page), page);
 
 		pc = lookup_page_cgroup(page);
-		if (!PageCgroupUsed(pc))
+		if (!pc->mem_cgroup)
 			continue;
 
 		/*
 		 * Nobody should be changing or seriously looking at
-		 * pc->mem_cgroup and pc->flags at this point, we have
-		 * fully exclusive access to the page.
+		 * pc->mem_cgroup at this point, we have fully
+		 * exclusive access to the page.
 		 */
 
 		if (memcg != pc->mem_cgroup) {
@@ -6065,7 +6038,7 @@ static void uncharge_list(struct list_head *page_list)
 		else
 			nr_file += nr_pages;
 
-		pc->flags = 0;
+		pc->mem_cgroup = NULL;
 
 		pgpgout++;
 	} while (next != page_list);
@@ -6091,7 +6064,7 @@ void mem_cgroup_uncharge(struct page *page)
 
 	/* Don't touch page->lru of any random page, pre-check: */
 	pc = lookup_page_cgroup(page);
-	if (!PageCgroupUsed(pc))
+	if (!pc->mem_cgroup)
 		return;
 
 	INIT_LIST_HEAD(&page->lru);
@@ -6127,6 +6100,7 @@ void mem_cgroup_uncharge_list(struct list_head *page_list)
 void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 			bool lrucare)
 {
+	struct mem_cgroup *memcg;
 	struct page_cgroup *pc;
 	int isolated;
 
@@ -6143,7 +6117,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 
 	/* Page cache replacement: new page already charged? */
 	pc = lookup_page_cgroup(newpage);
-	if (PageCgroupUsed(pc))
+	if (pc->mem_cgroup)
 		return;
 
 	/*
@@ -6153,18 +6127,19 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 	 * reclaim just put back on the LRU but has not released yet.
 	 */
 	pc = lookup_page_cgroup(oldpage);
-	if (!PageCgroupUsed(pc))
+	memcg = pc->mem_cgroup;
+	if (!memcg)
 		return;
 
 	if (lrucare)
 		lock_page_lru(oldpage, &isolated);
 
-	pc->flags = 0;
+	pc->mem_cgroup = NULL;
 
 	if (lrucare)
 		unlock_page_lru(oldpage, isolated);
 
-	commit_charge(newpage, pc->mem_cgroup, lrucare);
+	commit_charge(newpage, memcg, lrucare);
 }
 
 /*
-- 
cgit v1.2.3-70-g09d2


From 97ad2be1daf8e6f2d297aa349101b340e1327917 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Wed, 10 Dec 2014 15:44:13 -0800
Subject: mm, hugetlb: correct bit shift in hstate_sizelog()

hstate_sizelog() would shift left an int rather than long, triggering
undefined behaviour and passing an incorrect value when the requested
page size was more than 4GB, thus breaking >4GB pages.

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andrey Ryabinin <a.ryabinin@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 6e6d338641f..cdd149ca5cc 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -311,7 +311,8 @@ static inline struct hstate *hstate_sizelog(int page_size_log)
 {
 	if (!page_size_log)
 		return &default_hstate;
-	return size_to_hstate(1 << page_size_log);
+
+	return size_to_hstate(1UL << page_size_log);
 }
 
 static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
-- 
cgit v1.2.3-70-g09d2


From b047501cd9f11d5e1d54ea0f90e2b10754021a0e Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Wed, 10 Dec 2014 15:44:19 -0800
Subject: memcg: use generic slab iterators for showing slabinfo

Let's use generic slab_start/next/stop for showing memcg caches info.  In
contrast to the current implementation, this will work even if all memcg
caches' info doesn't fit into a seq buffer (a page), plus it simply looks
neater.

Actually, the main reason I do this isn't mere cleanup.  I'm going to zap
the memcg_slab_caches list, because I find it useless provided we have the
slab_caches list, and this patch is a step in this direction.

It should be noted that before this patch an attempt to read
memory.kmem.slabinfo of a cgroup that doesn't have kmem limit set resulted
in -EIO, while after this patch it will silently show nothing except the
header, but I don't think it will frustrate anyone.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/slab.h |  4 ----
 mm/memcontrol.c      | 25 ++++---------------------
 mm/slab.h            |  1 +
 mm/slab_common.c     | 25 +++++++++++++++++++------
 4 files changed, 24 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index c265bec6a57..8a2457d42fc 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -513,10 +513,6 @@ struct memcg_cache_params {
 
 int memcg_update_all_caches(int num_memcgs);
 
-struct seq_file;
-int cache_show(struct kmem_cache *s, struct seq_file *m);
-void print_slabinfo_header(struct seq_file *m);
-
 /**
  * kmalloc_array - allocate memory for an array.
  * @n: number of elements.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 32e3b191857..9d30129b0d4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2547,26 +2547,6 @@ static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p)
 	return cache_from_memcg_idx(cachep, memcg_cache_id(p->memcg));
 }
 
-#ifdef CONFIG_SLABINFO
-static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v)
-{
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
-	struct memcg_cache_params *params;
-
-	if (!memcg_kmem_is_active(memcg))
-		return -EIO;
-
-	print_slabinfo_header(m);
-
-	mutex_lock(&memcg_slab_mutex);
-	list_for_each_entry(params, &memcg->memcg_slab_caches, list)
-		cache_show(memcg_params_to_cache(params), m);
-	mutex_unlock(&memcg_slab_mutex);
-
-	return 0;
-}
-#endif
-
 static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
 			     unsigned long nr_pages)
 {
@@ -4708,7 +4688,10 @@ static struct cftype mem_cgroup_files[] = {
 #ifdef CONFIG_SLABINFO
 	{
 		.name = "kmem.slabinfo",
-		.seq_show = mem_cgroup_slabinfo_read,
+		.seq_start = slab_start,
+		.seq_next = slab_next,
+		.seq_stop = slab_stop,
+		.seq_show = memcg_slab_show,
 	},
 #endif
 #endif
diff --git a/mm/slab.h b/mm/slab.h
index 078acbcf64e..1cf4005482d 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -360,5 +360,6 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 void *slab_start(struct seq_file *m, loff_t *pos);
 void *slab_next(struct seq_file *m, void *p, loff_t *pos);
 void slab_stop(struct seq_file *m, void *p);
+int memcg_slab_show(struct seq_file *m, void *p);
 
 #endif /* MM_SLAB_H */
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 2a3f5ff410c..e03dd6f2a27 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -811,7 +811,7 @@ EXPORT_SYMBOL(kmalloc_order_trace);
 #define SLABINFO_RIGHTS S_IRUSR
 #endif
 
-void print_slabinfo_header(struct seq_file *m)
+static void print_slabinfo_header(struct seq_file *m)
 {
 	/*
 	 * Output format version, so at least we can change it
@@ -876,7 +876,7 @@ memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
 	}
 }
 
-int cache_show(struct kmem_cache *s, struct seq_file *m)
+static void cache_show(struct kmem_cache *s, struct seq_file *m)
 {
 	struct slabinfo sinfo;
 
@@ -895,7 +895,6 @@ int cache_show(struct kmem_cache *s, struct seq_file *m)
 		   sinfo.active_slabs, sinfo.num_slabs, sinfo.shared_avail);
 	slabinfo_show_stats(m, s);
 	seq_putc(m, '\n');
-	return 0;
 }
 
 static int slab_show(struct seq_file *m, void *p)
@@ -904,10 +903,24 @@ static int slab_show(struct seq_file *m, void *p)
 
 	if (p == slab_caches.next)
 		print_slabinfo_header(m);
-	if (!is_root_cache(s))
-		return 0;
-	return cache_show(s, m);
+	if (is_root_cache(s))
+		cache_show(s, m);
+	return 0;
+}
+
+#ifdef CONFIG_MEMCG_KMEM
+int memcg_slab_show(struct seq_file *m, void *p)
+{
+	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+
+	if (p == slab_caches.next)
+		print_slabinfo_header(m);
+	if (!is_root_cache(s) && s->memcg_params->memcg == memcg)
+		cache_show(s, m);
+	return 0;
 }
+#endif
 
 /*
  * slabinfo_op - iterator that generates /proc/slabinfo
-- 
cgit v1.2.3-70-g09d2


From 413918bb61b4fa027baa3e79546c47f15e4b9ea8 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 10 Dec 2014 15:44:30 -0800
Subject: mm: memcontrol: pull the NULL check from
 __mem_cgroup_same_or_subtree()

The NULL in mm_match_cgroup() comes from a possibly exiting mm->owner.  It
makes a lot more sense to check where it's looked up, rather than check
for it in __mem_cgroup_same_or_subtree() where it's unexpected.

No other callsite passes NULL to __mem_cgroup_same_or_subtree().

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 5 +++--
 mm/memcontrol.c            | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ea007615e8f..e32ab948f58 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -83,11 +83,12 @@ static inline
 bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *task_memcg;
-	bool match;
+	bool match = false;
 
 	rcu_read_lock();
 	task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
-	match = __mem_cgroup_same_or_subtree(memcg, task_memcg);
+	if (task_memcg)
+		match = __mem_cgroup_same_or_subtree(memcg, task_memcg);
 	rcu_read_unlock();
 	return match;
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 367cc57df36..e5dcebd71df 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1337,7 +1337,7 @@ bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
 {
 	if (root_memcg == memcg)
 		return true;
-	if (!root_memcg->use_hierarchy || !memcg)
+	if (!root_memcg->use_hierarchy)
 		return false;
 	return cgroup_is_descendant(memcg->css.cgroup, root_memcg->css.cgroup);
 }
-- 
cgit v1.2.3-70-g09d2


From 2314b42db67be30b747122d65c6cd2c85da34538 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 10 Dec 2014 15:44:33 -0800
Subject: mm: memcontrol: drop bogus RCU locking from
 mem_cgroup_same_or_subtree()

None of the mem_cgroup_same_or_subtree() callers actually require it to
take the RCU lock, either because they hold it themselves or they have css
references.  Remove it.

To make the API change clear, rename the leftover helper to
mem_cgroup_is_descendant() to match cgroup_is_descendant().

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 13 +++++-----
 mm/memcontrol.c            | 59 +++++++++++++---------------------------------
 mm/oom_kill.c              |  4 ++--
 3 files changed, 24 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e32ab948f58..d4575a1d6e9 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -68,10 +68,9 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
 struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
 
-bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
-				  struct mem_cgroup *memcg);
-bool task_in_mem_cgroup(struct task_struct *task,
-			const struct mem_cgroup *memcg);
+bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
+			      struct mem_cgroup *root);
+bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
 
 extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
 extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
@@ -79,8 +78,8 @@ extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
 extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css);
 
-static inline
-bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg)
+static inline bool mm_match_cgroup(struct mm_struct *mm,
+				   struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *task_memcg;
 	bool match = false;
@@ -88,7 +87,7 @@ bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg)
 	rcu_read_lock();
 	task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
 	if (task_memcg)
-		match = __mem_cgroup_same_or_subtree(memcg, task_memcg);
+		match = mem_cgroup_is_descendant(task_memcg, memcg);
 	rcu_read_unlock();
 	return match;
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e5dcebd71df..b841bf43017 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1328,41 +1328,24 @@ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
 	VM_BUG_ON((long)(*lru_size) < 0);
 }
 
-/*
- * Checks whether given mem is same or in the root_mem_cgroup's
- * hierarchy subtree
- */
-bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
-				  struct mem_cgroup *memcg)
+bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root)
 {
-	if (root_memcg == memcg)
+	if (root == memcg)
 		return true;
-	if (!root_memcg->use_hierarchy)
+	if (!root->use_hierarchy)
 		return false;
-	return cgroup_is_descendant(memcg->css.cgroup, root_memcg->css.cgroup);
-}
-
-static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
-				       struct mem_cgroup *memcg)
-{
-	bool ret;
-
-	rcu_read_lock();
-	ret = __mem_cgroup_same_or_subtree(root_memcg, memcg);
-	rcu_read_unlock();
-	return ret;
+	return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
 }
 
-bool task_in_mem_cgroup(struct task_struct *task,
-			const struct mem_cgroup *memcg)
+bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg)
 {
-	struct mem_cgroup *curr;
+	struct mem_cgroup *task_memcg;
 	struct task_struct *p;
 	bool ret;
 
 	p = find_lock_task_mm(task);
 	if (p) {
-		curr = get_mem_cgroup_from_mm(p->mm);
+		task_memcg = get_mem_cgroup_from_mm(p->mm);
 		task_unlock(p);
 	} else {
 		/*
@@ -1371,18 +1354,12 @@ bool task_in_mem_cgroup(struct task_struct *task,
 		 * killed to prevent needlessly killing additional tasks.
 		 */
 		rcu_read_lock();
-		curr = mem_cgroup_from_task(task);
-		css_get(&curr->css);
+		task_memcg = mem_cgroup_from_task(task);
+		css_get(&task_memcg->css);
 		rcu_read_unlock();
 	}
-	/*
-	 * We should check use_hierarchy of "memcg" not "curr". Because checking
-	 * use_hierarchy of "curr" here make this function true if hierarchy is
-	 * enabled in "curr" and "curr" is a child of "memcg" in *cgroup*
-	 * hierarchy(even if use_hierarchy is disabled in "memcg").
-	 */
-	ret = mem_cgroup_same_or_subtree(memcg, curr);
-	css_put(&curr->css);
+	ret = mem_cgroup_is_descendant(task_memcg, memcg);
+	css_put(&task_memcg->css);
 	return ret;
 }
 
@@ -1467,8 +1444,8 @@ static bool mem_cgroup_under_move(struct mem_cgroup *memcg)
 	if (!from)
 		goto unlock;
 
-	ret = mem_cgroup_same_or_subtree(memcg, from)
-		|| mem_cgroup_same_or_subtree(memcg, to);
+	ret = mem_cgroup_is_descendant(from, memcg) ||
+		mem_cgroup_is_descendant(to, memcg);
 unlock:
 	spin_unlock(&mc.lock);
 	return ret;
@@ -1900,12 +1877,8 @@ static int memcg_oom_wake_function(wait_queue_t *wait,
 	oom_wait_info = container_of(wait, struct oom_wait_info, wait);
 	oom_wait_memcg = oom_wait_info->memcg;
 
-	/*
-	 * Both of oom_wait_info->memcg and wake_memcg are stable under us.
-	 * Then we can use css_is_ancestor without taking care of RCU.
-	 */
-	if (!mem_cgroup_same_or_subtree(oom_wait_memcg, wake_memcg)
-		&& !mem_cgroup_same_or_subtree(wake_memcg, oom_wait_memcg))
+	if (!mem_cgroup_is_descendant(wake_memcg, oom_wait_memcg) &&
+	    !mem_cgroup_is_descendant(oom_wait_memcg, wake_memcg))
 		return 0;
 	return autoremove_wake_function(wait, mode, sync, arg);
 }
@@ -2225,7 +2198,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 		memcg = stock->cached;
 		if (!memcg || !stock->nr_pages)
 			continue;
-		if (!mem_cgroup_same_or_subtree(root_memcg, memcg))
+		if (!mem_cgroup_is_descendant(memcg, root_memcg))
 			continue;
 		if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
 			if (cpu == curcpu)
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 5340f6b9131..3b014d32615 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -119,7 +119,7 @@ found:
 
 /* return true if the task is not adequate as candidate victim task. */
 static bool oom_unkillable_task(struct task_struct *p,
-		const struct mem_cgroup *memcg, const nodemask_t *nodemask)
+		struct mem_cgroup *memcg, const nodemask_t *nodemask)
 {
 	if (is_global_init(p))
 		return true;
@@ -353,7 +353,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
  * State information includes task's pid, uid, tgid, vm size, rss, nr_ptes,
  * swapents, oom_score_adj value, and name.
  */
-static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemask)
+static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 {
 	struct task_struct *p;
 	struct task_struct *task;
-- 
cgit v1.2.3-70-g09d2


From e4bd6a0248b2a026e07c19995c41a4cb5a49d797 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.cz>
Date: Wed, 10 Dec 2014 15:44:39 -0800
Subject: mm, memcg: fix potential undefined behaviour in page stat accounting

Since commit d7365e783edb ("mm: memcontrol: fix missed end-writeback
page accounting") mem_cgroup_end_page_stat consumes locked and flags
variables directly rather than via pointers which might trigger C
undefined behavior as those variables are initialized only in the slow
path of mem_cgroup_begin_page_stat.

Although mem_cgroup_end_page_stat handles parameters correctly and
touches them only when they hold a sensible value it is caller which
loads a potentially uninitialized value which then might allow compiler
to do crazy things.

I haven't seen any warning from gcc and it seems that the current
version (4.9) doesn't exploit this type undefined behavior but Sasha has
reported the following:

  UBSan: Undefined behaviour in mm/rmap.c:1084:2
  load of value 255 is not a valid value for type '_Bool'
  CPU: 4 PID: 8304 Comm: rngd Not tainted 3.18.0-rc2-next-20141029-sasha-00039-g77ed13d-dirty #1427
  Call Trace:
    dump_stack (lib/dump_stack.c:52)
    ubsan_epilogue (lib/ubsan.c:159)
    __ubsan_handle_load_invalid_value (lib/ubsan.c:482)
    page_remove_rmap (mm/rmap.c:1084 mm/rmap.c:1096)
    unmap_page_range (./arch/x86/include/asm/atomic.h:27 include/linux/mm.h:463 mm/memory.c:1146 mm/memory.c:1258 mm/memory.c:1279 mm/memory.c:1303)
    unmap_single_vma (mm/memory.c:1348)
    unmap_vmas (mm/memory.c:1377 (discriminator 3))
    exit_mmap (mm/mmap.c:2837)
    mmput (kernel/fork.c:659)
    do_exit (./arch/x86/include/asm/thread_info.h:168 kernel/exit.c:462 kernel/exit.c:747)
    do_group_exit (include/linux/sched.h:775 kernel/exit.c:873)
    SyS_exit_group (kernel/exit.c:901)
    tracesys_phase2 (arch/x86/kernel/entry_64.S:529)

Fix this by using pointer parameters for both locked and flags and be
more robust for future compiler changes even though the current code is
implemented correctly.

Signed-off-by: Michal Hocko <mhocko@suse.cz>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 6 +++---
 mm/memcontrol.c            | 8 ++++----
 mm/page-writeback.c        | 4 ++--
 mm/rmap.c                  | 4 ++--
 4 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d4575a1d6e9..de018766be4 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -141,8 +141,8 @@ static inline bool mem_cgroup_disabled(void)
 
 struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, bool *locked,
 					      unsigned long *flags);
-void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool locked,
-			      unsigned long flags);
+void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked,
+			      unsigned long *flags);
 void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
 				 enum mem_cgroup_stat_index idx, int val);
 
@@ -297,7 +297,7 @@ static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page,
 }
 
 static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg,
-					bool locked, unsigned long flags)
+					bool *locked, unsigned long *flags)
 {
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b841bf43017..031ca345677 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2053,11 +2053,11 @@ again:
  * @locked: value received from mem_cgroup_begin_page_stat()
  * @flags: value received from mem_cgroup_begin_page_stat()
  */
-void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool locked,
-			      unsigned long flags)
+void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked,
+			      unsigned long *flags)
 {
-	if (memcg && locked)
-		spin_unlock_irqrestore(&memcg->move_lock, flags);
+	if (memcg && *locked)
+		spin_unlock_irqrestore(&memcg->move_lock, *flags);
 
 	rcu_read_unlock();
 }
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 19ceae87522..d5d81f5384d 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2357,7 +2357,7 @@ int test_clear_page_writeback(struct page *page)
 		dec_zone_page_state(page, NR_WRITEBACK);
 		inc_zone_page_state(page, NR_WRITTEN);
 	}
-	mem_cgroup_end_page_stat(memcg, locked, memcg_flags);
+	mem_cgroup_end_page_stat(memcg, &locked, &memcg_flags);
 	return ret;
 }
 
@@ -2399,7 +2399,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 		mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_WRITEBACK);
 		inc_zone_page_state(page, NR_WRITEBACK);
 	}
-	mem_cgroup_end_page_stat(memcg, locked, memcg_flags);
+	mem_cgroup_end_page_stat(memcg, &locked, &memcg_flags);
 	return ret;
 
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 3e4c7213210..45eba36fd67 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1053,7 +1053,7 @@ void page_add_file_rmap(struct page *page)
 		__inc_zone_page_state(page, NR_FILE_MAPPED);
 		mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED);
 	}
-	mem_cgroup_end_page_stat(memcg, locked, flags);
+	mem_cgroup_end_page_stat(memcg, &locked, &flags);
 }
 
 static void page_remove_file_rmap(struct page *page)
@@ -1083,7 +1083,7 @@ static void page_remove_file_rmap(struct page *page)
 	if (unlikely(PageMlocked(page)))
 		clear_page_mlock(page);
 out:
-	mem_cgroup_end_page_stat(memcg, locked, flags);
+	mem_cgroup_end_page_stat(memcg, &locked, &flags);
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 1306a85aed3ec3db98945aafb7dfbe5648a1203c Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 10 Dec 2014 15:44:52 -0800
Subject: mm: embed the memcg pointer directly into struct page

Memory cgroups used to have 5 per-page pointers.  To allow users to
disable that amount of overhead during runtime, those pointers were
allocated in a separate array, with a translation layer between them and
struct page.

There is now only one page pointer remaining: the memcg pointer, that
indicates which cgroup the page is associated with when charged.  The
complexity of runtime allocation and the runtime translation overhead is
no longer justified to save that *potential* 0.19% of memory.  With
CONFIG_SLUB, page->mem_cgroup actually sits in the doubleword padding
after the page->private member and doesn't even increase struct page,
and then this patch actually saves space.  Remaining users that care can
still compile their kernels without CONFIG_MEMCG.

     text    data     bss     dec     hex     filename
  8828345 1725264  983040 11536649 b00909  vmlinux.old
  8827425 1725264  966656 11519345 afc571  vmlinux.new

[mhocko@suse.cz: update Documentation/cgroups/memory.txt]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Konstantin Khlebnikov <koct9i@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/cgroups/memory.txt |   5 +
 include/linux/memcontrol.h       |   6 +-
 include/linux/mm_types.h         |   5 +
 include/linux/mmzone.h           |  12 --
 include/linux/page_cgroup.h      |  53 -------
 init/main.c                      |   7 -
 mm/memcontrol.c                  | 124 +++++----------
 mm/page_alloc.c                  |   2 -
 mm/page_cgroup.c                 | 319 ---------------------------------------
 9 files changed, 46 insertions(+), 487 deletions(-)

(limited to 'include')

diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 67613ff0270..46b2b508031 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -1,5 +1,10 @@
 Memory Resource Controller
 
+NOTE: This document is hopelessly outdated and it asks for a complete
+      rewrite. It still contains a useful information so we are keeping it
+      here but make sure to check the current code if you need a deeper
+      understanding.
+
 NOTE: The Memory Resource Controller has generically been referred to as the
       memory controller in this document. Do not confuse memory controller
       used here with the memory controller that is used in hardware.
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index de018766be4..c4d08087516 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -25,7 +25,6 @@
 #include <linux/jump_label.h>
 
 struct mem_cgroup;
-struct page_cgroup;
 struct page;
 struct mm_struct;
 struct kmem_cache;
@@ -466,8 +465,6 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
  * memcg_kmem_uncharge_pages: uncharge pages from memcg
  * @page: pointer to struct page being freed
  * @order: allocation order.
- *
- * there is no need to specify memcg here, since it is embedded in page_cgroup
  */
 static inline void
 memcg_kmem_uncharge_pages(struct page *page, int order)
@@ -484,8 +481,7 @@ memcg_kmem_uncharge_pages(struct page *page, int order)
  *
  * Needs to be called after memcg_kmem_newpage_charge, regardless of success or
  * failure of the allocation. if @page is NULL, this function will revert the
- * charges. Otherwise, it will commit the memcg given by @memcg to the
- * corresponding page_cgroup.
+ * charges. Otherwise, it will commit @page to @memcg.
  */
 static inline void
 memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 004e9d17b47..bf9f57529dc 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -22,6 +22,7 @@
 #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1))
 
 struct address_space;
+struct mem_cgroup;
 
 #define USE_SPLIT_PTE_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
 #define USE_SPLIT_PMD_PTLOCKS	(USE_SPLIT_PTE_PTLOCKS && \
@@ -167,6 +168,10 @@ struct page {
 		struct page *first_page;	/* Compound tail pages */
 	};
 
+#ifdef CONFIG_MEMCG
+	struct mem_cgroup *mem_cgroup;
+#endif
+
 	/*
 	 * On machines where all RAM is mapped into kernel address space,
 	 * we can simply calculate the virtual address. On machines with
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ffe66e381c0..3879d7664df 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -722,9 +722,6 @@ typedef struct pglist_data {
 	int nr_zones;
 #ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
 	struct page *node_mem_map;
-#ifdef CONFIG_MEMCG
-	struct page_cgroup *node_page_cgroup;
-#endif
 #endif
 #ifndef CONFIG_NO_BOOTMEM
 	struct bootmem_data *bdata;
@@ -1078,7 +1075,6 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn)
 #define SECTION_ALIGN_DOWN(pfn)	((pfn) & PAGE_SECTION_MASK)
 
 struct page;
-struct page_cgroup;
 struct mem_section {
 	/*
 	 * This is, logically, a pointer to an array of struct
@@ -1096,14 +1092,6 @@ struct mem_section {
 
 	/* See declaration of similar field in struct zone */
 	unsigned long *pageblock_flags;
-#ifdef CONFIG_MEMCG
-	/*
-	 * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use
-	 * section. (see memcontrol.h/page_cgroup.h about this.)
-	 */
-	struct page_cgroup *page_cgroup;
-	unsigned long pad;
-#endif
 	/*
 	 * WARNING: mem_section must be a power-of-2 in size for the
 	 * calculation and use of SECTION_ROOT_MASK to make sense.
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 1289be6b436..65be35785c8 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -1,59 +1,6 @@
 #ifndef __LINUX_PAGE_CGROUP_H
 #define __LINUX_PAGE_CGROUP_H
 
-struct pglist_data;
-
-#ifdef CONFIG_MEMCG
-struct mem_cgroup;
-
-/*
- * Page Cgroup can be considered as an extended mem_map.
- * A page_cgroup page is associated with every page descriptor. The
- * page_cgroup helps us identify information about the cgroup
- * All page cgroups are allocated at boot or memory hotplug event,
- * then the page cgroup for pfn always exists.
- */
-struct page_cgroup {
-	struct mem_cgroup *mem_cgroup;
-};
-
-extern void pgdat_page_cgroup_init(struct pglist_data *pgdat);
-
-#ifdef CONFIG_SPARSEMEM
-static inline void page_cgroup_init_flatmem(void)
-{
-}
-extern void page_cgroup_init(void);
-#else
-extern void page_cgroup_init_flatmem(void);
-static inline void page_cgroup_init(void)
-{
-}
-#endif
-
-struct page_cgroup *lookup_page_cgroup(struct page *page);
-
-#else /* !CONFIG_MEMCG */
-struct page_cgroup;
-
-static inline void pgdat_page_cgroup_init(struct pglist_data *pgdat)
-{
-}
-
-static inline struct page_cgroup *lookup_page_cgroup(struct page *page)
-{
-	return NULL;
-}
-
-static inline void page_cgroup_init(void)
-{
-}
-
-static inline void page_cgroup_init_flatmem(void)
-{
-}
-#endif /* CONFIG_MEMCG */
-
 #include <linux/swap.h>
 
 #ifdef CONFIG_MEMCG_SWAP
diff --git a/init/main.c b/init/main.c
index 321d0ceb26d..d2e4ead4891 100644
--- a/init/main.c
+++ b/init/main.c
@@ -51,7 +51,6 @@
 #include <linux/mempolicy.h>
 #include <linux/key.h>
 #include <linux/buffer_head.h>
-#include <linux/page_cgroup.h>
 #include <linux/debug_locks.h>
 #include <linux/debugobjects.h>
 #include <linux/lockdep.h>
@@ -485,11 +484,6 @@ void __init __weak thread_info_cache_init(void)
  */
 static void __init mm_init(void)
 {
-	/*
-	 * page_cgroup requires contiguous pages,
-	 * bigger than MAX_ORDER unless SPARSEMEM.
-	 */
-	page_cgroup_init_flatmem();
 	mem_init();
 	kmem_cache_init();
 	percpu_init_late();
@@ -627,7 +621,6 @@ asmlinkage __visible void __init start_kernel(void)
 		initrd_start = 0;
 	}
 #endif
-	page_cgroup_init();
 	debug_objects_mem_init();
 	kmemleak_init();
 	setup_per_cpu_pageset();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 78cb3b05a9f..b864067791d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1274,7 +1274,6 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 {
 	struct mem_cgroup_per_zone *mz;
 	struct mem_cgroup *memcg;
-	struct page_cgroup *pc;
 	struct lruvec *lruvec;
 
 	if (mem_cgroup_disabled()) {
@@ -1282,8 +1281,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 		goto out;
 	}
 
-	pc = lookup_page_cgroup(page);
-	memcg = pc->mem_cgroup;
+	memcg = page->mem_cgroup;
 	/*
 	 * Swapcache readahead pages are added to the LRU - and
 	 * possibly migrated - before they are charged.
@@ -2020,16 +2018,13 @@ struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page,
 					      unsigned long *flags)
 {
 	struct mem_cgroup *memcg;
-	struct page_cgroup *pc;
 
 	rcu_read_lock();
 
 	if (mem_cgroup_disabled())
 		return NULL;
-
-	pc = lookup_page_cgroup(page);
 again:
-	memcg = pc->mem_cgroup;
+	memcg = page->mem_cgroup;
 	if (unlikely(!memcg))
 		return NULL;
 
@@ -2038,7 +2033,7 @@ again:
 		return memcg;
 
 	spin_lock_irqsave(&memcg->move_lock, *flags);
-	if (memcg != pc->mem_cgroup) {
+	if (memcg != page->mem_cgroup) {
 		spin_unlock_irqrestore(&memcg->move_lock, *flags);
 		goto again;
 	}
@@ -2405,15 +2400,12 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 {
 	struct mem_cgroup *memcg;
-	struct page_cgroup *pc;
 	unsigned short id;
 	swp_entry_t ent;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
-	pc = lookup_page_cgroup(page);
-	memcg = pc->mem_cgroup;
-
+	memcg = page->mem_cgroup;
 	if (memcg) {
 		if (!css_tryget_online(&memcg->css))
 			memcg = NULL;
@@ -2463,10 +2455,9 @@ static void unlock_page_lru(struct page *page, int isolated)
 static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 			  bool lrucare)
 {
-	struct page_cgroup *pc = lookup_page_cgroup(page);
 	int isolated;
 
-	VM_BUG_ON_PAGE(pc->mem_cgroup, page);
+	VM_BUG_ON_PAGE(page->mem_cgroup, page);
 
 	/*
 	 * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page
@@ -2477,7 +2468,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 
 	/*
 	 * Nobody should be changing or seriously looking at
-	 * pc->mem_cgroup at this point:
+	 * page->mem_cgroup at this point:
 	 *
 	 * - the page is uncharged
 	 *
@@ -2489,7 +2480,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 	 * - a page cache insertion, a swapin fault, or a migration
 	 *   have the page locked
 	 */
-	pc->mem_cgroup = memcg;
+	page->mem_cgroup = memcg;
 
 	if (lrucare)
 		unlock_page_lru(page, isolated);
@@ -2972,8 +2963,6 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
 void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
 			      int order)
 {
-	struct page_cgroup *pc;
-
 	VM_BUG_ON(mem_cgroup_is_root(memcg));
 
 	/* The page allocation failed. Revert */
@@ -2981,14 +2970,12 @@ void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
 		memcg_uncharge_kmem(memcg, 1 << order);
 		return;
 	}
-	pc = lookup_page_cgroup(page);
-	pc->mem_cgroup = memcg;
+	page->mem_cgroup = memcg;
 }
 
 void __memcg_kmem_uncharge_pages(struct page *page, int order)
 {
-	struct page_cgroup *pc = lookup_page_cgroup(page);
-	struct mem_cgroup *memcg = pc->mem_cgroup;
+	struct mem_cgroup *memcg = page->mem_cgroup;
 
 	if (!memcg)
 		return;
@@ -2996,7 +2983,7 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order)
 	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
 
 	memcg_uncharge_kmem(memcg, 1 << order);
-	pc->mem_cgroup = NULL;
+	page->mem_cgroup = NULL;
 }
 #else
 static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg)
@@ -3014,16 +3001,15 @@ static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg)
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {
-	struct page_cgroup *pc = lookup_page_cgroup(head);
 	int i;
 
 	if (mem_cgroup_disabled())
 		return;
 
 	for (i = 1; i < HPAGE_PMD_NR; i++)
-		pc[i].mem_cgroup = pc[0].mem_cgroup;
+		head[i].mem_cgroup = head->mem_cgroup;
 
-	__this_cpu_sub(pc[0].mem_cgroup->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
+	__this_cpu_sub(head->mem_cgroup->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
 		       HPAGE_PMD_NR);
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -3032,7 +3018,6 @@ void mem_cgroup_split_huge_fixup(struct page *head)
  * mem_cgroup_move_account - move account of the page
  * @page: the page
  * @nr_pages: number of regular pages (>1 for huge pages)
- * @pc:	page_cgroup of the page.
  * @from: mem_cgroup which the page is moved from.
  * @to:	mem_cgroup which the page is moved to. @from != @to.
  *
@@ -3045,7 +3030,6 @@ void mem_cgroup_split_huge_fixup(struct page *head)
  */
 static int mem_cgroup_move_account(struct page *page,
 				   unsigned int nr_pages,
-				   struct page_cgroup *pc,
 				   struct mem_cgroup *from,
 				   struct mem_cgroup *to)
 {
@@ -3065,7 +3049,7 @@ static int mem_cgroup_move_account(struct page *page,
 		goto out;
 
 	/*
-	 * Prevent mem_cgroup_migrate() from looking at pc->mem_cgroup
+	 * Prevent mem_cgroup_migrate() from looking at page->mem_cgroup
 	 * of its source page while we change it: page migration takes
 	 * both pages off the LRU, but page cache replacement doesn't.
 	 */
@@ -3073,7 +3057,7 @@ static int mem_cgroup_move_account(struct page *page,
 		goto out;
 
 	ret = -EINVAL;
-	if (pc->mem_cgroup != from)
+	if (page->mem_cgroup != from)
 		goto out_unlock;
 
 	spin_lock_irqsave(&from->move_lock, flags);
@@ -3093,13 +3077,13 @@ static int mem_cgroup_move_account(struct page *page,
 	}
 
 	/*
-	 * It is safe to change pc->mem_cgroup here because the page
+	 * It is safe to change page->mem_cgroup here because the page
 	 * is referenced, charged, and isolated - we can't race with
 	 * uncharging, charging, migration, or LRU putback.
 	 */
 
 	/* caller should have done css_get */
-	pc->mem_cgroup = to;
+	page->mem_cgroup = to;
 	spin_unlock_irqrestore(&from->move_lock, flags);
 
 	ret = 0;
@@ -3174,36 +3158,17 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
 #endif
 
 #ifdef CONFIG_DEBUG_VM
-static struct page_cgroup *lookup_page_cgroup_used(struct page *page)
-{
-	struct page_cgroup *pc;
-
-	pc = lookup_page_cgroup(page);
-	/*
-	 * Can be NULL while feeding pages into the page allocator for
-	 * the first time, i.e. during boot or memory hotplug;
-	 * or when mem_cgroup_disabled().
-	 */
-	if (likely(pc) && pc->mem_cgroup)
-		return pc;
-	return NULL;
-}
-
 bool mem_cgroup_bad_page_check(struct page *page)
 {
 	if (mem_cgroup_disabled())
 		return false;
 
-	return lookup_page_cgroup_used(page) != NULL;
+	return page->mem_cgroup != NULL;
 }
 
 void mem_cgroup_print_bad_page(struct page *page)
 {
-	struct page_cgroup *pc;
-
-	pc = lookup_page_cgroup_used(page);
-	if (pc)
-		pr_alert("pc:%p pc->mem_cgroup:%p\n", pc, pc->mem_cgroup);
+	pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
 }
 #endif
 
@@ -5123,7 +5088,6 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 		unsigned long addr, pte_t ptent, union mc_target *target)
 {
 	struct page *page = NULL;
-	struct page_cgroup *pc;
 	enum mc_target_type ret = MC_TARGET_NONE;
 	swp_entry_t ent = { .val = 0 };
 
@@ -5137,13 +5101,12 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 	if (!page && !ent.val)
 		return ret;
 	if (page) {
-		pc = lookup_page_cgroup(page);
 		/*
 		 * Do only loose check w/o serialization.
-		 * mem_cgroup_move_account() checks the pc is valid or
+		 * mem_cgroup_move_account() checks the page is valid or
 		 * not under LRU exclusion.
 		 */
-		if (pc->mem_cgroup == mc.from) {
+		if (page->mem_cgroup == mc.from) {
 			ret = MC_TARGET_PAGE;
 			if (target)
 				target->page = page;
@@ -5171,15 +5134,13 @@ static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
 		unsigned long addr, pmd_t pmd, union mc_target *target)
 {
 	struct page *page = NULL;
-	struct page_cgroup *pc;
 	enum mc_target_type ret = MC_TARGET_NONE;
 
 	page = pmd_page(pmd);
 	VM_BUG_ON_PAGE(!page || !PageHead(page), page);
 	if (!move_anon())
 		return ret;
-	pc = lookup_page_cgroup(page);
-	if (pc->mem_cgroup == mc.from) {
+	if (page->mem_cgroup == mc.from) {
 		ret = MC_TARGET_PAGE;
 		if (target) {
 			get_page(page);
@@ -5378,7 +5339,6 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	enum mc_target_type target_type;
 	union mc_target target;
 	struct page *page;
-	struct page_cgroup *pc;
 
 	/*
 	 * We don't take compound_lock() here but no race with splitting thp
@@ -5399,9 +5359,8 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 		if (target_type == MC_TARGET_PAGE) {
 			page = target.page;
 			if (!isolate_lru_page(page)) {
-				pc = lookup_page_cgroup(page);
 				if (!mem_cgroup_move_account(page, HPAGE_PMD_NR,
-							pc, mc.from, mc.to)) {
+							     mc.from, mc.to)) {
 					mc.precharge -= HPAGE_PMD_NR;
 					mc.moved_charge += HPAGE_PMD_NR;
 				}
@@ -5429,9 +5388,7 @@ retry:
 			page = target.page;
 			if (isolate_lru_page(page))
 				goto put;
-			pc = lookup_page_cgroup(page);
-			if (!mem_cgroup_move_account(page, 1, pc,
-						     mc.from, mc.to)) {
+			if (!mem_cgroup_move_account(page, 1, mc.from, mc.to)) {
 				mc.precharge--;
 				/* we uncharge from mc.from later. */
 				mc.moved_charge++;
@@ -5619,7 +5576,6 @@ static void __init enable_swap_cgroup(void)
 void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 {
 	struct mem_cgroup *memcg;
-	struct page_cgroup *pc;
 	unsigned short oldid;
 
 	VM_BUG_ON_PAGE(PageLRU(page), page);
@@ -5628,8 +5584,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	if (!do_swap_account)
 		return;
 
-	pc = lookup_page_cgroup(page);
-	memcg = pc->mem_cgroup;
+	memcg = page->mem_cgroup;
 
 	/* Readahead page, never charged */
 	if (!memcg)
@@ -5639,7 +5594,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	VM_BUG_ON_PAGE(oldid, page);
 	mem_cgroup_swap_statistics(memcg, true);
 
-	pc->mem_cgroup = NULL;
+	page->mem_cgroup = NULL;
 
 	if (!mem_cgroup_is_root(memcg))
 		page_counter_uncharge(&memcg->memory, 1);
@@ -5706,7 +5661,6 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 		goto out;
 
 	if (PageSwapCache(page)) {
-		struct page_cgroup *pc = lookup_page_cgroup(page);
 		/*
 		 * Every swap fault against a single page tries to charge the
 		 * page, bail as early as possible.  shmem_unuse() encounters
@@ -5714,7 +5668,7 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 		 * the page lock, which serializes swap cache removal, which
 		 * in turn serializes uncharging.
 		 */
-		if (pc->mem_cgroup)
+		if (page->mem_cgroup)
 			goto out;
 	}
 
@@ -5867,7 +5821,6 @@ static void uncharge_list(struct list_head *page_list)
 	next = page_list->next;
 	do {
 		unsigned int nr_pages = 1;
-		struct page_cgroup *pc;
 
 		page = list_entry(next, struct page, lru);
 		next = page->lru.next;
@@ -5875,23 +5828,22 @@ static void uncharge_list(struct list_head *page_list)
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		VM_BUG_ON_PAGE(page_count(page), page);
 
-		pc = lookup_page_cgroup(page);
-		if (!pc->mem_cgroup)
+		if (!page->mem_cgroup)
 			continue;
 
 		/*
 		 * Nobody should be changing or seriously looking at
-		 * pc->mem_cgroup at this point, we have fully
+		 * page->mem_cgroup at this point, we have fully
 		 * exclusive access to the page.
 		 */
 
-		if (memcg != pc->mem_cgroup) {
+		if (memcg != page->mem_cgroup) {
 			if (memcg) {
 				uncharge_batch(memcg, pgpgout, nr_anon, nr_file,
 					       nr_huge, page);
 				pgpgout = nr_anon = nr_file = nr_huge = 0;
 			}
-			memcg = pc->mem_cgroup;
+			memcg = page->mem_cgroup;
 		}
 
 		if (PageTransHuge(page)) {
@@ -5905,7 +5857,7 @@ static void uncharge_list(struct list_head *page_list)
 		else
 			nr_file += nr_pages;
 
-		pc->mem_cgroup = NULL;
+		page->mem_cgroup = NULL;
 
 		pgpgout++;
 	} while (next != page_list);
@@ -5924,14 +5876,11 @@ static void uncharge_list(struct list_head *page_list)
  */
 void mem_cgroup_uncharge(struct page *page)
 {
-	struct page_cgroup *pc;
-
 	if (mem_cgroup_disabled())
 		return;
 
 	/* Don't touch page->lru of any random page, pre-check: */
-	pc = lookup_page_cgroup(page);
-	if (!pc->mem_cgroup)
+	if (!page->mem_cgroup)
 		return;
 
 	INIT_LIST_HEAD(&page->lru);
@@ -5968,7 +5917,6 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 			bool lrucare)
 {
 	struct mem_cgroup *memcg;
-	struct page_cgroup *pc;
 	int isolated;
 
 	VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
@@ -5983,8 +5931,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 		return;
 
 	/* Page cache replacement: new page already charged? */
-	pc = lookup_page_cgroup(newpage);
-	if (pc->mem_cgroup)
+	if (newpage->mem_cgroup)
 		return;
 
 	/*
@@ -5993,15 +5940,14 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 	 * uncharged page when the PFN walker finds a page that
 	 * reclaim just put back on the LRU but has not released yet.
 	 */
-	pc = lookup_page_cgroup(oldpage);
-	memcg = pc->mem_cgroup;
+	memcg = oldpage->mem_cgroup;
 	if (!memcg)
 		return;
 
 	if (lrucare)
 		lock_page_lru(oldpage, &isolated);
 
-	pc->mem_cgroup = NULL;
+	oldpage->mem_cgroup = NULL;
 
 	if (lrucare)
 		unlock_page_lru(oldpage, isolated);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 97b6966816e..22cfdeffbf6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -48,7 +48,6 @@
 #include <linux/backing-dev.h>
 #include <linux/fault-inject.h>
 #include <linux/page-isolation.h>
-#include <linux/page_cgroup.h>
 #include <linux/debugobjects.h>
 #include <linux/kmemleak.h>
 #include <linux/compaction.h>
@@ -4853,7 +4852,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 #endif
 	init_waitqueue_head(&pgdat->kswapd_wait);
 	init_waitqueue_head(&pgdat->pfmemalloc_wait);
-	pgdat_page_cgroup_init(pgdat);
 
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 5331c2bd85a..f0f31c1d4d0 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -1,326 +1,7 @@
 #include <linux/mm.h>
-#include <linux/mmzone.h>
-#include <linux/bootmem.h>
-#include <linux/bit_spinlock.h>
 #include <linux/page_cgroup.h>
-#include <linux/hash.h>
-#include <linux/slab.h>
-#include <linux/memory.h>
 #include <linux/vmalloc.h>
-#include <linux/cgroup.h>
 #include <linux/swapops.h>
-#include <linux/kmemleak.h>
-
-static unsigned long total_usage;
-
-#if !defined(CONFIG_SPARSEMEM)
-
-
-void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
-{
-	pgdat->node_page_cgroup = NULL;
-}
-
-struct page_cgroup *lookup_page_cgroup(struct page *page)
-{
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long offset;
-	struct page_cgroup *base;
-
-	base = NODE_DATA(page_to_nid(page))->node_page_cgroup;
-#ifdef CONFIG_DEBUG_VM
-	/*
-	 * The sanity checks the page allocator does upon freeing a
-	 * page can reach here before the page_cgroup arrays are
-	 * allocated when feeding a range of pages to the allocator
-	 * for the first time during bootup or memory hotplug.
-	 */
-	if (unlikely(!base))
-		return NULL;
-#endif
-	offset = pfn - NODE_DATA(page_to_nid(page))->node_start_pfn;
-	return base + offset;
-}
-
-static int __init alloc_node_page_cgroup(int nid)
-{
-	struct page_cgroup *base;
-	unsigned long table_size;
-	unsigned long nr_pages;
-
-	nr_pages = NODE_DATA(nid)->node_spanned_pages;
-	if (!nr_pages)
-		return 0;
-
-	table_size = sizeof(struct page_cgroup) * nr_pages;
-
-	base = memblock_virt_alloc_try_nid_nopanic(
-			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
-			BOOTMEM_ALLOC_ACCESSIBLE, nid);
-	if (!base)
-		return -ENOMEM;
-	NODE_DATA(nid)->node_page_cgroup = base;
-	total_usage += table_size;
-	return 0;
-}
-
-void __init page_cgroup_init_flatmem(void)
-{
-
-	int nid, fail;
-
-	if (mem_cgroup_disabled())
-		return;
-
-	for_each_online_node(nid)  {
-		fail = alloc_node_page_cgroup(nid);
-		if (fail)
-			goto fail;
-	}
-	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
-	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you"
-	" don't want memory cgroups\n");
-	return;
-fail:
-	printk(KERN_CRIT "allocation of page_cgroup failed.\n");
-	printk(KERN_CRIT "please try 'cgroup_disable=memory' boot option\n");
-	panic("Out of memory");
-}
-
-#else /* CONFIG_FLAT_NODE_MEM_MAP */
-
-struct page_cgroup *lookup_page_cgroup(struct page *page)
-{
-	unsigned long pfn = page_to_pfn(page);
-	struct mem_section *section = __pfn_to_section(pfn);
-#ifdef CONFIG_DEBUG_VM
-	/*
-	 * The sanity checks the page allocator does upon freeing a
-	 * page can reach here before the page_cgroup arrays are
-	 * allocated when feeding a range of pages to the allocator
-	 * for the first time during bootup or memory hotplug.
-	 */
-	if (!section->page_cgroup)
-		return NULL;
-#endif
-	return section->page_cgroup + pfn;
-}
-
-static void *__meminit alloc_page_cgroup(size_t size, int nid)
-{
-	gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN;
-	void *addr = NULL;
-
-	addr = alloc_pages_exact_nid(nid, size, flags);
-	if (addr) {
-		kmemleak_alloc(addr, size, 1, flags);
-		return addr;
-	}
-
-	if (node_state(nid, N_HIGH_MEMORY))
-		addr = vzalloc_node(size, nid);
-	else
-		addr = vzalloc(size);
-
-	return addr;
-}
-
-static int __meminit init_section_page_cgroup(unsigned long pfn, int nid)
-{
-	struct mem_section *section;
-	struct page_cgroup *base;
-	unsigned long table_size;
-
-	section = __pfn_to_section(pfn);
-
-	if (section->page_cgroup)
-		return 0;
-
-	table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
-	base = alloc_page_cgroup(table_size, nid);
-
-	/*
-	 * The value stored in section->page_cgroup is (base - pfn)
-	 * and it does not point to the memory block allocated above,
-	 * causing kmemleak false positives.
-	 */
-	kmemleak_not_leak(base);
-
-	if (!base) {
-		printk(KERN_ERR "page cgroup allocation failure\n");
-		return -ENOMEM;
-	}
-
-	/*
-	 * The passed "pfn" may not be aligned to SECTION.  For the calculation
-	 * we need to apply a mask.
-	 */
-	pfn &= PAGE_SECTION_MASK;
-	section->page_cgroup = base - pfn;
-	total_usage += table_size;
-	return 0;
-}
-#ifdef CONFIG_MEMORY_HOTPLUG
-static void free_page_cgroup(void *addr)
-{
-	if (is_vmalloc_addr(addr)) {
-		vfree(addr);
-	} else {
-		struct page *page = virt_to_page(addr);
-		size_t table_size =
-			sizeof(struct page_cgroup) * PAGES_PER_SECTION;
-
-		BUG_ON(PageReserved(page));
-		kmemleak_free(addr);
-		free_pages_exact(addr, table_size);
-	}
-}
-
-static void __free_page_cgroup(unsigned long pfn)
-{
-	struct mem_section *ms;
-	struct page_cgroup *base;
-
-	ms = __pfn_to_section(pfn);
-	if (!ms || !ms->page_cgroup)
-		return;
-	base = ms->page_cgroup + pfn;
-	free_page_cgroup(base);
-	ms->page_cgroup = NULL;
-}
-
-static int __meminit online_page_cgroup(unsigned long start_pfn,
-				unsigned long nr_pages,
-				int nid)
-{
-	unsigned long start, end, pfn;
-	int fail = 0;
-
-	start = SECTION_ALIGN_DOWN(start_pfn);
-	end = SECTION_ALIGN_UP(start_pfn + nr_pages);
-
-	if (nid == -1) {
-		/*
-		 * In this case, "nid" already exists and contains valid memory.
-		 * "start_pfn" passed to us is a pfn which is an arg for
-		 * online__pages(), and start_pfn should exist.
-		 */
-		nid = pfn_to_nid(start_pfn);
-		VM_BUG_ON(!node_state(nid, N_ONLINE));
-	}
-
-	for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
-		if (!pfn_present(pfn))
-			continue;
-		fail = init_section_page_cgroup(pfn, nid);
-	}
-	if (!fail)
-		return 0;
-
-	/* rollback */
-	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
-		__free_page_cgroup(pfn);
-
-	return -ENOMEM;
-}
-
-static int __meminit offline_page_cgroup(unsigned long start_pfn,
-				unsigned long nr_pages, int nid)
-{
-	unsigned long start, end, pfn;
-
-	start = SECTION_ALIGN_DOWN(start_pfn);
-	end = SECTION_ALIGN_UP(start_pfn + nr_pages);
-
-	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
-		__free_page_cgroup(pfn);
-	return 0;
-
-}
-
-static int __meminit page_cgroup_callback(struct notifier_block *self,
-			       unsigned long action, void *arg)
-{
-	struct memory_notify *mn = arg;
-	int ret = 0;
-	switch (action) {
-	case MEM_GOING_ONLINE:
-		ret = online_page_cgroup(mn->start_pfn,
-				   mn->nr_pages, mn->status_change_nid);
-		break;
-	case MEM_OFFLINE:
-		offline_page_cgroup(mn->start_pfn,
-				mn->nr_pages, mn->status_change_nid);
-		break;
-	case MEM_CANCEL_ONLINE:
-		offline_page_cgroup(mn->start_pfn,
-				mn->nr_pages, mn->status_change_nid);
-		break;
-	case MEM_GOING_OFFLINE:
-		break;
-	case MEM_ONLINE:
-	case MEM_CANCEL_OFFLINE:
-		break;
-	}
-
-	return notifier_from_errno(ret);
-}
-
-#endif
-
-void __init page_cgroup_init(void)
-{
-	unsigned long pfn;
-	int nid;
-
-	if (mem_cgroup_disabled())
-		return;
-
-	for_each_node_state(nid, N_MEMORY) {
-		unsigned long start_pfn, end_pfn;
-
-		start_pfn = node_start_pfn(nid);
-		end_pfn = node_end_pfn(nid);
-		/*
-		 * start_pfn and end_pfn may not be aligned to SECTION and the
-		 * page->flags of out of node pages are not initialized.  So we
-		 * scan [start_pfn, the biggest section's pfn < end_pfn) here.
-		 */
-		for (pfn = start_pfn;
-		     pfn < end_pfn;
-                     pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) {
-
-			if (!pfn_valid(pfn))
-				continue;
-			/*
-			 * Nodes's pfns can be overlapping.
-			 * We know some arch can have a nodes layout such as
-			 * -------------pfn-------------->
-			 * N0 | N1 | N2 | N0 | N1 | N2|....
-			 */
-			if (pfn_to_nid(pfn) != nid)
-				continue;
-			if (init_section_page_cgroup(pfn, nid))
-				goto oom;
-		}
-	}
-	hotplug_memory_notifier(page_cgroup_callback, 0);
-	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
-	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you "
-			 "don't want memory cgroups\n");
-	return;
-oom:
-	printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
-	panic("Out of memory");
-}
-
-void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
-{
-	return;
-}
-
-#endif
-
 
 #ifdef CONFIG_MEMCG_SWAP
 
-- 
cgit v1.2.3-70-g09d2


From 5d1ea48bdde67898e87d6d8f511fd097fa64c749 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 10 Dec 2014 15:44:55 -0800
Subject: mm: page_cgroup: rename file to mm/swap_cgroup.c

Now that the external page_cgroup data structure and its lookup is gone,
the only code remaining in there is swap slot accounting.

Rename it and move the conditional compilation into mm/Makefile.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Tejun Heo <tj@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 MAINTAINERS                 |   2 +-
 include/linux/page_cgroup.h |  40 ---------
 include/linux/swap_cgroup.h |  42 +++++++++
 mm/Makefile                 |   3 +-
 mm/memcontrol.c             |   2 +-
 mm/page_cgroup.c            | 211 --------------------------------------------
 mm/swap_cgroup.c            | 208 +++++++++++++++++++++++++++++++++++++++++++
 mm/swap_state.c             |   1 -
 mm/swapfile.c               |   2 +-
 9 files changed, 255 insertions(+), 256 deletions(-)
 delete mode 100644 include/linux/page_cgroup.h
 create mode 100644 include/linux/swap_cgroup.h
 delete mode 100644 mm/page_cgroup.c
 create mode 100644 mm/swap_cgroup.c

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 0d6469a2cf7..0aedd3e1804 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2606,7 +2606,7 @@ L:	cgroups@vger.kernel.org
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/memcontrol.c
-F:	mm/page_cgroup.c
+F:	mm/swap_cgroup.c
 
 CORETEMP HARDWARE MONITORING DRIVER
 M:	Fenghua Yu <fenghua.yu@intel.com>
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
deleted file mode 100644
index 65be35785c8..00000000000
--- a/include/linux/page_cgroup.h
+++ /dev/null
@@ -1,40 +0,0 @@
-#ifndef __LINUX_PAGE_CGROUP_H
-#define __LINUX_PAGE_CGROUP_H
-
-#include <linux/swap.h>
-
-#ifdef CONFIG_MEMCG_SWAP
-extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
-					unsigned short old, unsigned short new);
-extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id);
-extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent);
-extern int swap_cgroup_swapon(int type, unsigned long max_pages);
-extern void swap_cgroup_swapoff(int type);
-#else
-
-static inline
-unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
-{
-	return 0;
-}
-
-static inline
-unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
-{
-	return 0;
-}
-
-static inline int
-swap_cgroup_swapon(int type, unsigned long max_pages)
-{
-	return 0;
-}
-
-static inline void swap_cgroup_swapoff(int type)
-{
-	return;
-}
-
-#endif /* CONFIG_MEMCG_SWAP */
-
-#endif /* __LINUX_PAGE_CGROUP_H */
diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h
new file mode 100644
index 00000000000..145306bdc92
--- /dev/null
+++ b/include/linux/swap_cgroup.h
@@ -0,0 +1,42 @@
+#ifndef __LINUX_SWAP_CGROUP_H
+#define __LINUX_SWAP_CGROUP_H
+
+#include <linux/swap.h>
+
+#ifdef CONFIG_MEMCG_SWAP
+
+extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
+					unsigned short old, unsigned short new);
+extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id);
+extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent);
+extern int swap_cgroup_swapon(int type, unsigned long max_pages);
+extern void swap_cgroup_swapoff(int type);
+
+#else
+
+static inline
+unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
+{
+	return 0;
+}
+
+static inline
+unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
+{
+	return 0;
+}
+
+static inline int
+swap_cgroup_swapon(int type, unsigned long max_pages)
+{
+	return 0;
+}
+
+static inline void swap_cgroup_swapoff(int type)
+{
+	return;
+}
+
+#endif /* CONFIG_MEMCG_SWAP */
+
+#endif /* __LINUX_SWAP_CGROUP_H */
diff --git a/mm/Makefile b/mm/Makefile
index 6d9f40e922f..b3c6ce932c6 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -56,7 +56,8 @@ obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o
 obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
-obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o vmpressure.o
+obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
+obj-$(CONFIG_MEMCG_SWAP) += swap_cgroup.o
 obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
 obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b864067791d..ab270e34ba3 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -51,7 +51,7 @@
 #include <linux/seq_file.h>
 #include <linux/vmpressure.h>
 #include <linux/mm_inline.h>
-#include <linux/page_cgroup.h>
+#include <linux/swap_cgroup.h>
 #include <linux/cpu.h>
 #include <linux/oom.h>
 #include <linux/lockdep.h>
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
deleted file mode 100644
index f0f31c1d4d0..00000000000
--- a/mm/page_cgroup.c
+++ /dev/null
@@ -1,211 +0,0 @@
-#include <linux/mm.h>
-#include <linux/page_cgroup.h>
-#include <linux/vmalloc.h>
-#include <linux/swapops.h>
-
-#ifdef CONFIG_MEMCG_SWAP
-
-static DEFINE_MUTEX(swap_cgroup_mutex);
-struct swap_cgroup_ctrl {
-	struct page **map;
-	unsigned long length;
-	spinlock_t	lock;
-};
-
-static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
-
-struct swap_cgroup {
-	unsigned short		id;
-};
-#define SC_PER_PAGE	(PAGE_SIZE/sizeof(struct swap_cgroup))
-
-/*
- * SwapCgroup implements "lookup" and "exchange" operations.
- * In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge
- * against SwapCache. At swap_free(), this is accessed directly from swap.
- *
- * This means,
- *  - we have no race in "exchange" when we're accessed via SwapCache because
- *    SwapCache(and its swp_entry) is under lock.
- *  - When called via swap_free(), there is no user of this entry and no race.
- * Then, we don't need lock around "exchange".
- *
- * TODO: we can push these buffers out to HIGHMEM.
- */
-
-/*
- * allocate buffer for swap_cgroup.
- */
-static int swap_cgroup_prepare(int type)
-{
-	struct page *page;
-	struct swap_cgroup_ctrl *ctrl;
-	unsigned long idx, max;
-
-	ctrl = &swap_cgroup_ctrl[type];
-
-	for (idx = 0; idx < ctrl->length; idx++) {
-		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-		if (!page)
-			goto not_enough_page;
-		ctrl->map[idx] = page;
-	}
-	return 0;
-not_enough_page:
-	max = idx;
-	for (idx = 0; idx < max; idx++)
-		__free_page(ctrl->map[idx]);
-
-	return -ENOMEM;
-}
-
-static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent,
-					struct swap_cgroup_ctrl **ctrlp)
-{
-	pgoff_t offset = swp_offset(ent);
-	struct swap_cgroup_ctrl *ctrl;
-	struct page *mappage;
-	struct swap_cgroup *sc;
-
-	ctrl = &swap_cgroup_ctrl[swp_type(ent)];
-	if (ctrlp)
-		*ctrlp = ctrl;
-
-	mappage = ctrl->map[offset / SC_PER_PAGE];
-	sc = page_address(mappage);
-	return sc + offset % SC_PER_PAGE;
-}
-
-/**
- * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry.
- * @ent: swap entry to be cmpxchged
- * @old: old id
- * @new: new id
- *
- * Returns old id at success, 0 at failure.
- * (There is no mem_cgroup using 0 as its id)
- */
-unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
-					unsigned short old, unsigned short new)
-{
-	struct swap_cgroup_ctrl *ctrl;
-	struct swap_cgroup *sc;
-	unsigned long flags;
-	unsigned short retval;
-
-	sc = lookup_swap_cgroup(ent, &ctrl);
-
-	spin_lock_irqsave(&ctrl->lock, flags);
-	retval = sc->id;
-	if (retval == old)
-		sc->id = new;
-	else
-		retval = 0;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-	return retval;
-}
-
-/**
- * swap_cgroup_record - record mem_cgroup for this swp_entry.
- * @ent: swap entry to be recorded into
- * @id: mem_cgroup to be recorded
- *
- * Returns old value at success, 0 at failure.
- * (Of course, old value can be 0.)
- */
-unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
-{
-	struct swap_cgroup_ctrl *ctrl;
-	struct swap_cgroup *sc;
-	unsigned short old;
-	unsigned long flags;
-
-	sc = lookup_swap_cgroup(ent, &ctrl);
-
-	spin_lock_irqsave(&ctrl->lock, flags);
-	old = sc->id;
-	sc->id = id;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-
-	return old;
-}
-
-/**
- * lookup_swap_cgroup_id - lookup mem_cgroup id tied to swap entry
- * @ent: swap entry to be looked up.
- *
- * Returns ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
- */
-unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
-{
-	return lookup_swap_cgroup(ent, NULL)->id;
-}
-
-int swap_cgroup_swapon(int type, unsigned long max_pages)
-{
-	void *array;
-	unsigned long array_size;
-	unsigned long length;
-	struct swap_cgroup_ctrl *ctrl;
-
-	if (!do_swap_account)
-		return 0;
-
-	length = DIV_ROUND_UP(max_pages, SC_PER_PAGE);
-	array_size = length * sizeof(void *);
-
-	array = vzalloc(array_size);
-	if (!array)
-		goto nomem;
-
-	ctrl = &swap_cgroup_ctrl[type];
-	mutex_lock(&swap_cgroup_mutex);
-	ctrl->length = length;
-	ctrl->map = array;
-	spin_lock_init(&ctrl->lock);
-	if (swap_cgroup_prepare(type)) {
-		/* memory shortage */
-		ctrl->map = NULL;
-		ctrl->length = 0;
-		mutex_unlock(&swap_cgroup_mutex);
-		vfree(array);
-		goto nomem;
-	}
-	mutex_unlock(&swap_cgroup_mutex);
-
-	return 0;
-nomem:
-	printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
-	printk(KERN_INFO
-		"swap_cgroup can be disabled by swapaccount=0 boot option\n");
-	return -ENOMEM;
-}
-
-void swap_cgroup_swapoff(int type)
-{
-	struct page **map;
-	unsigned long i, length;
-	struct swap_cgroup_ctrl *ctrl;
-
-	if (!do_swap_account)
-		return;
-
-	mutex_lock(&swap_cgroup_mutex);
-	ctrl = &swap_cgroup_ctrl[type];
-	map = ctrl->map;
-	length = ctrl->length;
-	ctrl->map = NULL;
-	ctrl->length = 0;
-	mutex_unlock(&swap_cgroup_mutex);
-
-	if (map) {
-		for (i = 0; i < length; i++) {
-			struct page *page = map[i];
-			if (page)
-				__free_page(page);
-		}
-		vfree(map);
-	}
-}
-
-#endif
diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c
new file mode 100644
index 00000000000..b5f7f24b8dd
--- /dev/null
+++ b/mm/swap_cgroup.c
@@ -0,0 +1,208 @@
+#include <linux/swap_cgroup.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+
+#include <linux/swapops.h> /* depends on mm.h include */
+
+static DEFINE_MUTEX(swap_cgroup_mutex);
+struct swap_cgroup_ctrl {
+	struct page **map;
+	unsigned long length;
+	spinlock_t	lock;
+};
+
+static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
+
+struct swap_cgroup {
+	unsigned short		id;
+};
+#define SC_PER_PAGE	(PAGE_SIZE/sizeof(struct swap_cgroup))
+
+/*
+ * SwapCgroup implements "lookup" and "exchange" operations.
+ * In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge
+ * against SwapCache. At swap_free(), this is accessed directly from swap.
+ *
+ * This means,
+ *  - we have no race in "exchange" when we're accessed via SwapCache because
+ *    SwapCache(and its swp_entry) is under lock.
+ *  - When called via swap_free(), there is no user of this entry and no race.
+ * Then, we don't need lock around "exchange".
+ *
+ * TODO: we can push these buffers out to HIGHMEM.
+ */
+
+/*
+ * allocate buffer for swap_cgroup.
+ */
+static int swap_cgroup_prepare(int type)
+{
+	struct page *page;
+	struct swap_cgroup_ctrl *ctrl;
+	unsigned long idx, max;
+
+	ctrl = &swap_cgroup_ctrl[type];
+
+	for (idx = 0; idx < ctrl->length; idx++) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!page)
+			goto not_enough_page;
+		ctrl->map[idx] = page;
+	}
+	return 0;
+not_enough_page:
+	max = idx;
+	for (idx = 0; idx < max; idx++)
+		__free_page(ctrl->map[idx]);
+
+	return -ENOMEM;
+}
+
+static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent,
+					struct swap_cgroup_ctrl **ctrlp)
+{
+	pgoff_t offset = swp_offset(ent);
+	struct swap_cgroup_ctrl *ctrl;
+	struct page *mappage;
+	struct swap_cgroup *sc;
+
+	ctrl = &swap_cgroup_ctrl[swp_type(ent)];
+	if (ctrlp)
+		*ctrlp = ctrl;
+
+	mappage = ctrl->map[offset / SC_PER_PAGE];
+	sc = page_address(mappage);
+	return sc + offset % SC_PER_PAGE;
+}
+
+/**
+ * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry.
+ * @ent: swap entry to be cmpxchged
+ * @old: old id
+ * @new: new id
+ *
+ * Returns old id at success, 0 at failure.
+ * (There is no mem_cgroup using 0 as its id)
+ */
+unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
+					unsigned short old, unsigned short new)
+{
+	struct swap_cgroup_ctrl *ctrl;
+	struct swap_cgroup *sc;
+	unsigned long flags;
+	unsigned short retval;
+
+	sc = lookup_swap_cgroup(ent, &ctrl);
+
+	spin_lock_irqsave(&ctrl->lock, flags);
+	retval = sc->id;
+	if (retval == old)
+		sc->id = new;
+	else
+		retval = 0;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
+	return retval;
+}
+
+/**
+ * swap_cgroup_record - record mem_cgroup for this swp_entry.
+ * @ent: swap entry to be recorded into
+ * @id: mem_cgroup to be recorded
+ *
+ * Returns old value at success, 0 at failure.
+ * (Of course, old value can be 0.)
+ */
+unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
+{
+	struct swap_cgroup_ctrl *ctrl;
+	struct swap_cgroup *sc;
+	unsigned short old;
+	unsigned long flags;
+
+	sc = lookup_swap_cgroup(ent, &ctrl);
+
+	spin_lock_irqsave(&ctrl->lock, flags);
+	old = sc->id;
+	sc->id = id;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
+
+	return old;
+}
+
+/**
+ * lookup_swap_cgroup_id - lookup mem_cgroup id tied to swap entry
+ * @ent: swap entry to be looked up.
+ *
+ * Returns ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
+ */
+unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
+{
+	return lookup_swap_cgroup(ent, NULL)->id;
+}
+
+int swap_cgroup_swapon(int type, unsigned long max_pages)
+{
+	void *array;
+	unsigned long array_size;
+	unsigned long length;
+	struct swap_cgroup_ctrl *ctrl;
+
+	if (!do_swap_account)
+		return 0;
+
+	length = DIV_ROUND_UP(max_pages, SC_PER_PAGE);
+	array_size = length * sizeof(void *);
+
+	array = vzalloc(array_size);
+	if (!array)
+		goto nomem;
+
+	ctrl = &swap_cgroup_ctrl[type];
+	mutex_lock(&swap_cgroup_mutex);
+	ctrl->length = length;
+	ctrl->map = array;
+	spin_lock_init(&ctrl->lock);
+	if (swap_cgroup_prepare(type)) {
+		/* memory shortage */
+		ctrl->map = NULL;
+		ctrl->length = 0;
+		mutex_unlock(&swap_cgroup_mutex);
+		vfree(array);
+		goto nomem;
+	}
+	mutex_unlock(&swap_cgroup_mutex);
+
+	return 0;
+nomem:
+	printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
+	printk(KERN_INFO
+		"swap_cgroup can be disabled by swapaccount=0 boot option\n");
+	return -ENOMEM;
+}
+
+void swap_cgroup_swapoff(int type)
+{
+	struct page **map;
+	unsigned long i, length;
+	struct swap_cgroup_ctrl *ctrl;
+
+	if (!do_swap_account)
+		return;
+
+	mutex_lock(&swap_cgroup_mutex);
+	ctrl = &swap_cgroup_ctrl[type];
+	map = ctrl->map;
+	length = ctrl->length;
+	ctrl->map = NULL;
+	ctrl->length = 0;
+	mutex_unlock(&swap_cgroup_mutex);
+
+	if (map) {
+		for (i = 0; i < length; i++) {
+			struct page *page = map[i];
+			if (page)
+				__free_page(page);
+		}
+		vfree(map);
+	}
+}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 15444491868..9711342987a 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -17,7 +17,6 @@
 #include <linux/blkdev.h>
 #include <linux/pagevec.h>
 #include <linux/migrate.h>
-#include <linux/page_cgroup.h>
 
 #include <asm/pgtable.h>
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 8798b2e0ac5..63f55ccb9b2 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -38,7 +38,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <linux/swapops.h>
-#include <linux/page_cgroup.h>
+#include <linux/swap_cgroup.h>
 
 static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
 				 unsigned char);
-- 
cgit v1.2.3-70-g09d2


From 9edad6ea0f1416415f6fe31cc9d1dbc3817803ed Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 10 Dec 2014 15:44:58 -0800
Subject: mm: move page->mem_cgroup bad page handling into generic code

Now that the external page_cgroup data structure and its lookup is
gone, let the generic bad_page() check for page->mem_cgroup sanity.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Tejun Heo <tj@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 17 -----------------
 init/Kconfig               | 12 ------------
 mm/debug.c                 |  5 ++++-
 mm/memcontrol.c            | 15 ---------------
 mm/page_alloc.c            | 12 ++++++++----
 5 files changed, 12 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index c4d08087516..6ea9f919e88 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -173,10 +173,6 @@ static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
 void mem_cgroup_split_huge_fixup(struct page *head);
 #endif
 
-#ifdef CONFIG_DEBUG_VM
-bool mem_cgroup_bad_page_check(struct page *page);
-void mem_cgroup_print_bad_page(struct page *page);
-#endif
 #else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
@@ -346,19 +342,6 @@ void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 }
 #endif /* CONFIG_MEMCG */
 
-#if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM)
-static inline bool
-mem_cgroup_bad_page_check(struct page *page)
-{
-	return false;
-}
-
-static inline void
-mem_cgroup_print_bad_page(struct page *page)
-{
-}
-#endif
-
 enum {
 	UNDER_LIMIT,
 	SOFT_LIMIT,
diff --git a/init/Kconfig b/init/Kconfig
index 46768752130..7e9fbd48e2a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -983,18 +983,6 @@ config MEMCG
 	  Provides a memory resource controller that manages both anonymous
 	  memory and page cache. (See Documentation/cgroups/memory.txt)
 
-	  Note that setting this option increases fixed memory overhead
-	  associated with each page of memory in the system. By this,
-	  8(16)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory
-	  usage tracking struct at boot. Total amount of this is printed out
-	  at boot.
-
-	  Only enable when you're ok with these trade offs and really
-	  sure you need the memory resource controller. Even when you enable
-	  this, you can set "cgroup_disable=memory" at your boot option to
-	  disable memory resource controller and you can avoid overheads.
-	  (and lose benefits of memory resource controller)
-
 config MEMCG_SWAP
 	bool "Memory Resource Controller Swap Extension"
 	depends on MEMCG && SWAP
diff --git a/mm/debug.c b/mm/debug.c
index 5ce45c9a29b..0e58f3211f8 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -95,7 +95,10 @@ void dump_page_badflags(struct page *page, const char *reason,
 		dump_flags(page->flags & badflags,
 				pageflag_names, ARRAY_SIZE(pageflag_names));
 	}
-	mem_cgroup_print_bad_page(page);
+#ifdef CONFIG_MEMCG
+	if (page->mem_cgroup)
+		pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
+#endif
 }
 
 void dump_page(struct page *page, const char *reason)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ab270e34ba3..1869cb64d08 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3157,21 +3157,6 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
 }
 #endif
 
-#ifdef CONFIG_DEBUG_VM
-bool mem_cgroup_bad_page_check(struct page *page)
-{
-	if (mem_cgroup_disabled())
-		return false;
-
-	return page->mem_cgroup != NULL;
-}
-
-void mem_cgroup_print_bad_page(struct page *page)
-{
-	pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
-}
-#endif
-
 static DEFINE_MUTEX(memcg_limit_mutex);
 
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 22cfdeffbf6..a7198c06599 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -640,8 +640,10 @@ static inline int free_pages_check(struct page *page)
 		bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
 		bad_flags = PAGE_FLAGS_CHECK_AT_FREE;
 	}
-	if (unlikely(mem_cgroup_bad_page_check(page)))
-		bad_reason = "cgroup check failed";
+#ifdef CONFIG_MEMCG
+	if (unlikely(page->mem_cgroup))
+		bad_reason = "page still charged to cgroup";
+#endif
 	if (unlikely(bad_reason)) {
 		bad_page(page, bad_reason, bad_flags);
 		return 1;
@@ -900,8 +902,10 @@ static inline int check_new_page(struct page *page)
 		bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
 		bad_flags = PAGE_FLAGS_CHECK_AT_PREP;
 	}
-	if (unlikely(mem_cgroup_bad_page_check(page)))
-		bad_reason = "cgroup check failed";
+#ifdef CONFIG_MEMCG
+	if (unlikely(page->mem_cgroup))
+		bad_reason = "page still charged to cgroup";
+#endif
 	if (unlikely(bad_reason)) {
 		bad_page(page, bad_reason, bad_flags);
 		return 1;
-- 
cgit v1.2.3-70-g09d2


From 7c8bd2322c7fd973d089b27de55e29c92c667a06 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Wed, 10 Dec 2014 15:45:33 -0800
Subject: exit: ptrace: shift "reap dead" code from exit_ptrace() to
 forget_original_parent()

Now that forget_original_parent() uses ->ptrace_entry for EXIT_DEAD tasks,
we can simply pass "dead_children" list to exit_ptrace() and remove
another release_task() loop.  Plus this way we do not need to drop and
reacquire tasklist_lock.

Also shift the list_empty(ptraced) check, if we want this optimization it
makes sense to eliminate the function call altogether.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Aaron Tomlin <atomlin@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>,
Cc: Sterling Alexander <stalexan@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roland McGrath <roland@hack.frob.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ptrace.h |  2 +-
 kernel/exit.c          | 10 ++++------
 kernel/ptrace.c        | 23 +++--------------------
 3 files changed, 8 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index cc79eff4a1a..987a73a40ef 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -52,7 +52,7 @@ extern void ptrace_notify(int exit_code);
 extern void __ptrace_link(struct task_struct *child,
 			  struct task_struct *new_parent);
 extern void __ptrace_unlink(struct task_struct *child);
-extern void exit_ptrace(struct task_struct *tracer);
+extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead);
 #define PTRACE_MODE_READ	0x01
 #define PTRACE_MODE_ATTACH	0x02
 #define PTRACE_MODE_NOAUDIT	0x04
diff --git a/kernel/exit.c b/kernel/exit.c
index 772e9175735..9c9526d8727 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -553,13 +553,11 @@ static void forget_original_parent(struct task_struct *father)
 	LIST_HEAD(dead_children);
 
 	write_lock_irq(&tasklist_lock);
-	/*
-	 * Note that exit_ptrace() and find_new_reaper() might
-	 * drop tasklist_lock and reacquire it.
-	 */
-	exit_ptrace(father);
-	reaper = find_new_reaper(father);
+	if (unlikely(!list_empty(&father->ptraced)))
+		exit_ptrace(father, &dead_children);
 
+	/* Can drop and reacquire tasklist_lock */
+	reaper = find_new_reaper(father);
 	list_for_each_entry(p, &father->children, sibling) {
 		for_each_thread(p, t) {
 			t->real_parent = reaper;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 54e75226c2c..1eb9d90c3af 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -485,36 +485,19 @@ static int ptrace_detach(struct task_struct *child, unsigned int data)
 
 /*
  * Detach all tasks we were using ptrace on. Called with tasklist held
- * for writing, and returns with it held too. But note it can release
- * and reacquire the lock.
+ * for writing.
  */
-void exit_ptrace(struct task_struct *tracer)
-	__releases(&tasklist_lock)
-	__acquires(&tasklist_lock)
+void exit_ptrace(struct task_struct *tracer, struct list_head *dead)
 {
 	struct task_struct *p, *n;
-	LIST_HEAD(ptrace_dead);
-
-	if (likely(list_empty(&tracer->ptraced)))
-		return;
 
 	list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) {
 		if (unlikely(p->ptrace & PT_EXITKILL))
 			send_sig_info(SIGKILL, SEND_SIG_FORCED, p);
 
 		if (__ptrace_detach(tracer, p))
-			list_add(&p->ptrace_entry, &ptrace_dead);
-	}
-
-	write_unlock_irq(&tasklist_lock);
-	BUG_ON(!list_empty(&tracer->ptraced));
-
-	list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_entry) {
-		list_del_init(&p->ptrace_entry);
-		release_task(p);
+			list_add(&p->ptrace_entry, dead);
 	}
-
-	write_lock_irq(&tasklist_lock);
 }
 
 int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len)
-- 
cgit v1.2.3-70-g09d2


From f938612dd97d481b8b5bf960c992ae577f081c17 Mon Sep 17 00:00:00 2001
From: Yann Droneaud <ydroneaud@opteya.com>
Date: Wed, 10 Dec 2014 15:45:47 -0800
Subject: include/linux/file.h: remove get_unused_fd() macro

Macro get_unused_fd() is used to allocate a file descriptor with default
flags.  Those default flags (0) don't enable close-on-exec.

This can be seen as an unsafe default: in most case close-on-exec should
be enabled to not leak file descriptor across exec().

It would be better to have a "safer" default set of flags, eg.  O_CLOEXEC
must be used to enable close-on-exec.

Instead this patch removes get_unused_fd() so that out of tree modules
won't be affect by a runtime behavor change which might introduce other
kind of bugs: it's better to catch the change at build time, making it
easier to fix.

Removing the macro will also promote use of get_unused_fd_flags() (or
anon_inode_getfd()) with flags provided by userspace.  Or, if flags cannot
be given by userspace, with flags set to O_CLOEXEC by default.

Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/file.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/file.h b/include/linux/file.h
index 4d69123377a..f87d30882a2 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -66,7 +66,6 @@ extern void set_close_on_exec(unsigned int fd, int flag);
 extern bool get_close_on_exec(unsigned int fd);
 extern void put_filp(struct file *);
 extern int get_unused_fd_flags(unsigned flags);
-#define get_unused_fd() get_unused_fd_flags(0)
 extern void put_unused_fd(unsigned int fd);
 
 extern void fd_install(unsigned int fd, struct file *file);
-- 
cgit v1.2.3-70-g09d2


From 9e3961a0979817c612b10b2da4f3045ec9faa779 Mon Sep 17 00:00:00 2001
From: Prarit Bhargava <prarit@redhat.com>
Date: Wed, 10 Dec 2014 15:45:50 -0800
Subject: kernel: add panic_on_warn

There have been several times where I have had to rebuild a kernel to
cause a panic when hitting a WARN() in the code in order to get a crash
dump from a system.  Sometimes this is easy to do, other times (such as
in the case of a remote admin) it is not trivial to send new images to
the user.

A much easier method would be a switch to change the WARN() over to a
panic.  This makes debugging easier in that I can now test the actual
image the WARN() was seen on and I do not have to engage in remote
debugging.

This patch adds a panic_on_warn kernel parameter and
/proc/sys/kernel/panic_on_warn calls panic() in the
warn_slowpath_common() path.  The function will still print out the
location of the warning.

An example of the panic_on_warn output:

The first line below is from the WARN_ON() to output the WARN_ON()'s
location.  After that the panic() output is displayed.

    WARNING: CPU: 30 PID: 11698 at /home/prarit/dummy_module/dummy-module.c:25 init_dummy+0x1f/0x30 [dummy_module]()
    Kernel panic - not syncing: panic_on_warn set ...

    CPU: 30 PID: 11698 Comm: insmod Tainted: G        W  OE  3.17.0+ #57
    Hardware name: Intel Corporation S2600CP/S2600CP, BIOS RMLSDP.86I.00.29.D696.1311111329 11/11/2013
     0000000000000000 000000008e3f87df ffff88080f093c38 ffffffff81665190
     0000000000000000 ffffffff818aea3d ffff88080f093cb8 ffffffff8165e2ec
     ffffffff00000008 ffff88080f093cc8 ffff88080f093c68 000000008e3f87df
    Call Trace:
     [<ffffffff81665190>] dump_stack+0x46/0x58
     [<ffffffff8165e2ec>] panic+0xd0/0x204
     [<ffffffffa038e05f>] ? init_dummy+0x1f/0x30 [dummy_module]
     [<ffffffff81076b90>] warn_slowpath_common+0xd0/0xd0
     [<ffffffffa038e040>] ? dummy_greetings+0x40/0x40 [dummy_module]
     [<ffffffff81076c8a>] warn_slowpath_null+0x1a/0x20
     [<ffffffffa038e05f>] init_dummy+0x1f/0x30 [dummy_module]
     [<ffffffff81002144>] do_one_initcall+0xd4/0x210
     [<ffffffff811b52c2>] ? __vunmap+0xc2/0x110
     [<ffffffff810f8889>] load_module+0x16a9/0x1b30
     [<ffffffff810f3d30>] ? store_uevent+0x70/0x70
     [<ffffffff810f49b9>] ? copy_module_from_fd.isra.44+0x129/0x180
     [<ffffffff810f8ec6>] SyS_finit_module+0xa6/0xd0
     [<ffffffff8166cf29>] system_call_fastpath+0x12/0x17

Successfully tested by me.

hpa said: There is another very valid use for this: many operators would
rather a machine shuts down than being potentially compromised either
functionally or security-wise.

Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Acked-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Fabian Frederick <fabf@skynet.be>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/kdump/kdump.txt       |  7 +++++++
 Documentation/kernel-parameters.txt |  3 +++
 Documentation/sysctl/kernel.txt     | 40 ++++++++++++++++++++++++-------------
 include/linux/kernel.h              |  1 +
 include/uapi/linux/sysctl.h         |  1 +
 kernel/panic.c                      | 13 ++++++++++++
 kernel/sysctl.c                     |  9 +++++++++
 kernel/sysctl_binary.c              |  1 +
 8 files changed, 61 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
index 6c0b9f27e46..bc4bd5a44b8 100644
--- a/Documentation/kdump/kdump.txt
+++ b/Documentation/kdump/kdump.txt
@@ -471,6 +471,13 @@ format. Crash is available on Dave Anderson's site at the following URL:
 
    http://people.redhat.com/~anderson/
 
+Trigger Kdump on WARN()
+=======================
+
+The kernel parameter, panic_on_warn, calls panic() in all WARN() paths.  This
+will cause a kdump to occur at the panic() call.  In cases where a user wants
+to specify this during runtime, /proc/sys/kernel/panic_on_warn can be set to 1
+to achieve the same behaviour.
 
 Contact
 =======
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 838f3776c92..d6eb3636fe5 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2509,6 +2509,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			timeout < 0: reboot immediately
 			Format: <timeout>
 
+	panic_on_warn	panic() instead of WARN().  Useful to cause kdump
+			on a WARN().
+
 	crash_kexec_post_notifiers
 			Run kdump after running panic-notifiers and dumping
 			kmsg. This only for the users who doubt kdump always
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 57baff5bdb8..b5d0c8501a1 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -54,8 +54,9 @@ show up in /proc/sys/kernel:
 - overflowuid
 - panic
 - panic_on_oops
-- panic_on_unrecovered_nmi
 - panic_on_stackoverflow
+- panic_on_unrecovered_nmi
+- panic_on_warn
 - pid_max
 - powersave-nap               [ PPC only ]
 - printk
@@ -527,19 +528,6 @@ the recommended setting is 60.
 
 ==============================================================
 
-panic_on_unrecovered_nmi:
-
-The default Linux behaviour on an NMI of either memory or unknown is
-to continue operation. For many environments such as scientific
-computing it is preferable that the box is taken out and the error
-dealt with than an uncorrected parity/ECC error get propagated.
-
-A small number of systems do generate NMI's for bizarre random reasons
-such as power management so the default is off. That sysctl works like
-the existing panic controls already in that directory.
-
-==============================================================
-
 panic_on_oops:
 
 Controls the kernel's behaviour when an oops or BUG is encountered.
@@ -563,6 +551,30 @@ This file shows up if CONFIG_DEBUG_STACKOVERFLOW is enabled.
 
 ==============================================================
 
+panic_on_unrecovered_nmi:
+
+The default Linux behaviour on an NMI of either memory or unknown is
+to continue operation. For many environments such as scientific
+computing it is preferable that the box is taken out and the error
+dealt with than an uncorrected parity/ECC error get propagated.
+
+A small number of systems do generate NMI's for bizarre random reasons
+such as power management so the default is off. That sysctl works like
+the existing panic controls already in that directory.
+
+==============================================================
+
+panic_on_warn:
+
+Calls panic() in the WARN() path when set to 1.  This is useful to avoid
+a kernel rebuild when attempting to kdump at the location of a WARN().
+
+0: only WARN(), default behaviour.
+
+1: call panic() after printing out WARN() location.
+
+==============================================================
+
 perf_cpu_time_max_percent:
 
 Hints to the kernel how much CPU time it should be allowed to
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 446d76a87ba..233ea810703 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -427,6 +427,7 @@ extern int panic_timeout;
 extern int panic_on_oops;
 extern int panic_on_unrecovered_nmi;
 extern int panic_on_io_nmi;
+extern int panic_on_warn;
 extern int sysctl_panic_on_stackoverflow;
 /*
  * Only to be used by arch init code. If the user over-wrote the default
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 43aaba1cc03..0956373b56d 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -153,6 +153,7 @@ enum
 	KERN_MAX_LOCK_DEPTH=74, /* int: rtmutex's maximum lock depth */
 	KERN_NMI_WATCHDOG=75, /* int: enable/disable nmi watchdog */
 	KERN_PANIC_ON_NMI=76, /* int: whether we will panic on an unrecovered */
+	KERN_PANIC_ON_WARN=77, /* int: call panic() in WARN() functions */
 };
 
 
diff --git a/kernel/panic.c b/kernel/panic.c
index cf80672b792..4d8d6f906de 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -33,6 +33,7 @@ static int pause_on_oops;
 static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
 static bool crash_kexec_post_notifiers;
+int panic_on_warn __read_mostly;
 
 int panic_timeout = CONFIG_PANIC_TIMEOUT;
 EXPORT_SYMBOL_GPL(panic_timeout);
@@ -428,6 +429,17 @@ static void warn_slowpath_common(const char *file, int line, void *caller,
 	if (args)
 		vprintk(args->fmt, args->args);
 
+	if (panic_on_warn) {
+		/*
+		 * This thread may hit another WARN() in the panic path.
+		 * Resetting this prevents additional WARN() from panicking the
+		 * system on this thread.  Other threads are blocked by the
+		 * panic_mutex in panic().
+		 */
+		panic_on_warn = 0;
+		panic("panic_on_warn set ...\n");
+	}
+
 	print_modules();
 	dump_stack();
 	print_oops_end_marker();
@@ -485,6 +497,7 @@ EXPORT_SYMBOL(__stack_chk_fail);
 
 core_param(panic, panic_timeout, int, 0644);
 core_param(pause_on_oops, pause_on_oops, int, 0644);
+core_param(panic_on_warn, panic_on_warn, int, 0644);
 
 static int __init setup_crash_kexec_post_notifiers(char *s)
 {
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 15f2511a1b7..7c54ff79afd 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1104,6 +1104,15 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
+	{
+		.procname	= "panic_on_warn",
+		.data		= &panic_on_warn,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 	{ }
 };
 
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 9a4f750a296..7e7746a42a6 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -137,6 +137,7 @@ static const struct bin_table bin_kern_table[] = {
 	{ CTL_INT,	KERN_COMPAT_LOG,		"compat-log" },
 	{ CTL_INT,	KERN_MAX_LOCK_DEPTH,		"max_lock_depth" },
 	{ CTL_INT,	KERN_PANIC_ON_NMI,		"panic_on_unrecovered_nmi" },
+	{ CTL_INT,	KERN_PANIC_ON_WARN,		"panic_on_warn" },
 	{}
 };
 
-- 
cgit v1.2.3-70-g09d2


From 1dc6244bd6d4f62239487fb0befc41c63e117290 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 10 Dec 2014 15:45:53 -0800
Subject: printk: remove used-once early_vprintk

Eliminate the unlikely possibility of message interleaving for
early_printk/early_vprintk use.

early_vprintk can be done via the %pV extension so remove this
unnecessary function and change early_printk to have the equivalent
vprintk code.

All uses of early_printk already end with a newline so also remove the
unnecessary newline from the early_printk function.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Chris Metcalf <cmetcalf@tilera.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/tile/kernel/early_printk.c | 19 +++++++++++++------
 include/linux/printk.h          |  1 -
 kernel/printk/printk.c          | 19 ++++++++-----------
 3 files changed, 21 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/tile/kernel/early_printk.c b/arch/tile/kernel/early_printk.c
index b608e00e7f6..aefb2c08672 100644
--- a/arch/tile/kernel/early_printk.c
+++ b/arch/tile/kernel/early_printk.c
@@ -43,13 +43,20 @@ static struct console early_hv_console = {
 
 void early_panic(const char *fmt, ...)
 {
-	va_list ap;
+	struct va_format vaf;
+	va_list args;
+
 	arch_local_irq_disable_all();
-	va_start(ap, fmt);
-	early_printk("Kernel panic - not syncing: ");
-	early_vprintk(fmt, ap);
-	early_printk("\n");
-	va_end(ap);
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	early_printk("Kernel panic - not syncing: %pV", &vaf);
+
+	va_end(args);
+
 	dump_stack();
 	hv_halt();
 }
diff --git a/include/linux/printk.h b/include/linux/printk.h
index d78125f73ac..3dd489f2ded 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -118,7 +118,6 @@ int no_printk(const char *fmt, ...)
 #ifdef CONFIG_EARLY_PRINTK
 extern asmlinkage __printf(1, 2)
 void early_printk(const char *fmt, ...);
-void early_vprintk(const char *fmt, va_list ap);
 #else
 static inline __printf(1, 2) __cold
 void early_printk(const char *s, ...) { }
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index ced2b84b1cb..4815c98ae17 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1881,23 +1881,20 @@ static size_t cont_print_text(char *text, size_t size) { return 0; }
 #ifdef CONFIG_EARLY_PRINTK
 struct console *early_console;
 
-void early_vprintk(const char *fmt, va_list ap)
-{
-	if (early_console) {
-		char buf[512];
-		int n = vscnprintf(buf, sizeof(buf), fmt, ap);
-
-		early_console->write(early_console, buf, n);
-	}
-}
-
 asmlinkage __visible void early_printk(const char *fmt, ...)
 {
 	va_list ap;
+	char buf[512];
+	int n;
+
+	if (!early_console)
+		return;
 
 	va_start(ap, fmt);
-	early_vprintk(fmt, ap);
+	n = vscnprintf(buf, sizeof(buf), fmt, ap);
 	va_end(ap);
+
+	early_console->write(early_console, buf, n);
 }
 #endif
 
-- 
cgit v1.2.3-70-g09d2


From a39d4a857d4bb0a62d6655c0d69f7387fe1ad160 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 10 Dec 2014 15:50:15 -0800
Subject: printk: add and use LOGLEVEL_<level> defines for KERN_<LEVEL>
 equivalents

Use #defines instead of magic values.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jason Baron <jbaron@akamai.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/usb/storage/debug.c |  2 +-
 include/linux/kern_levels.h | 13 +++++++++++++
 kernel/printk/printk.c      | 28 +++++++++++++---------------
 lib/dynamic_debug.c         |  4 ++--
 4 files changed, 29 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/storage/debug.c b/drivers/usb/storage/debug.c
index 66a684a2993..2d81e1d8ee3 100644
--- a/drivers/usb/storage/debug.c
+++ b/drivers/usb/storage/debug.c
@@ -188,7 +188,7 @@ int usb_stor_dbg(const struct us_data *us, const char *fmt, ...)
 
 	va_start(args, fmt);
 
-	r = dev_vprintk_emit(7, &us->pusb_dev->dev, fmt, args);
+	r = dev_vprintk_emit(LOGLEVEL_DEBUG, &us->pusb_dev->dev, fmt, args);
 
 	va_end(args);
 
diff --git a/include/linux/kern_levels.h b/include/linux/kern_levels.h
index 866caaa9e2b..c2ce155d83c 100644
--- a/include/linux/kern_levels.h
+++ b/include/linux/kern_levels.h
@@ -22,4 +22,17 @@
  */
 #define KERN_CONT	""
 
+/* integer equivalents of KERN_<LEVEL> */
+#define LOGLEVEL_SCHED		-2	/* Deferred messages from sched code
+					 * are set to this special level */
+#define LOGLEVEL_DEFAULT	-1	/* default (or last) loglevel */
+#define LOGLEVEL_EMERG		0	/* system is unusable */
+#define LOGLEVEL_ALERT		1	/* action must be taken immediately */
+#define LOGLEVEL_CRIT		2	/* critical conditions */
+#define LOGLEVEL_ERR		3	/* error conditions */
+#define LOGLEVEL_WARNING	4	/* warning conditions */
+#define LOGLEVEL_NOTICE		5	/* normal but significant condition */
+#define LOGLEVEL_INFO		6	/* informational */
+#define LOGLEVEL_DEBUG		7	/* debug-level messages */
+
 #endif
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 4815c98ae17..1b7092dbb59 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -62,9 +62,6 @@ int console_printk[4] = {
 	CONSOLE_LOGLEVEL_DEFAULT,	/* default_console_loglevel */
 };
 
-/* Deferred messaged from sched code are marked by this special level */
-#define SCHED_MESSAGE_LOGLEVEL -2
-
 /*
  * Low level drivers may need that to know if they can schedule in
  * their unblank() callback or not. So let's export it.
@@ -1259,7 +1256,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 int do_syslog(int type, char __user *buf, int len, bool from_file)
 {
 	bool clear = false;
-	static int saved_console_loglevel = -1;
+	static int saved_console_loglevel = LOGLEVEL_DEFAULT;
 	int error;
 
 	error = check_syslog_permissions(type, from_file);
@@ -1316,15 +1313,15 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 		break;
 	/* Disable logging to console */
 	case SYSLOG_ACTION_CONSOLE_OFF:
-		if (saved_console_loglevel == -1)
+		if (saved_console_loglevel == LOGLEVEL_DEFAULT)
 			saved_console_loglevel = console_loglevel;
 		console_loglevel = minimum_console_loglevel;
 		break;
 	/* Enable logging to console */
 	case SYSLOG_ACTION_CONSOLE_ON:
-		if (saved_console_loglevel != -1) {
+		if (saved_console_loglevel != LOGLEVEL_DEFAULT) {
 			console_loglevel = saved_console_loglevel;
-			saved_console_loglevel = -1;
+			saved_console_loglevel = LOGLEVEL_DEFAULT;
 		}
 		break;
 	/* Set level of messages printed to console */
@@ -1336,7 +1333,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 			len = minimum_console_loglevel;
 		console_loglevel = len;
 		/* Implicitly re-enable logging to console */
-		saved_console_loglevel = -1;
+		saved_console_loglevel = LOGLEVEL_DEFAULT;
 		error = 0;
 		break;
 	/* Number of chars in the log buffer */
@@ -1629,8 +1626,8 @@ asmlinkage int vprintk_emit(int facility, int level,
 	/* cpu currently holding logbuf_lock in this function */
 	static volatile unsigned int logbuf_cpu = UINT_MAX;
 
-	if (level == SCHED_MESSAGE_LOGLEVEL) {
-		level = -1;
+	if (level == LOGLEVEL_SCHED) {
+		level = LOGLEVEL_DEFAULT;
 		in_sched = true;
 	}
 
@@ -1695,8 +1692,9 @@ asmlinkage int vprintk_emit(int facility, int level,
 			const char *end_of_header = printk_skip_level(text);
 			switch (kern_level) {
 			case '0' ... '7':
-				if (level == -1)
+				if (level == LOGLEVEL_DEFAULT)
 					level = kern_level - '0';
+				/* fallthrough */
 			case 'd':	/* KERN_DEFAULT */
 				lflags |= LOG_PREFIX;
 			}
@@ -1710,7 +1708,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 		}
 	}
 
-	if (level == -1)
+	if (level == LOGLEVEL_DEFAULT)
 		level = default_message_loglevel;
 
 	if (dict)
@@ -1788,7 +1786,7 @@ EXPORT_SYMBOL(vprintk_emit);
 
 asmlinkage int vprintk(const char *fmt, va_list args)
 {
-	return vprintk_emit(0, -1, NULL, 0, fmt, args);
+	return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
 }
 EXPORT_SYMBOL(vprintk);
 
@@ -1842,7 +1840,7 @@ asmlinkage __visible int printk(const char *fmt, ...)
 	}
 #endif
 	va_start(args, fmt);
-	r = vprintk_emit(0, -1, NULL, 0, fmt, args);
+	r = vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
 	va_end(args);
 
 	return r;
@@ -2631,7 +2629,7 @@ int printk_deferred(const char *fmt, ...)
 
 	preempt_disable();
 	va_start(args, fmt);
-	r = vprintk_emit(0, SCHED_MESSAGE_LOGLEVEL, NULL, 0, fmt, args);
+	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
 	va_end(args);
 
 	__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index dfba0552174..527799d4447 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -576,7 +576,7 @@ void __dynamic_dev_dbg(struct _ddebug *descriptor,
 	} else {
 		char buf[PREFIX_SIZE];
 
-		dev_printk_emit(7, dev, "%s%s %s: %pV",
+		dev_printk_emit(LOGLEVEL_DEBUG, dev, "%s%s %s: %pV",
 				dynamic_emit_prefix(descriptor, buf),
 				dev_driver_string(dev), dev_name(dev),
 				&vaf);
@@ -605,7 +605,7 @@ void __dynamic_netdev_dbg(struct _ddebug *descriptor,
 	if (dev && dev->dev.parent) {
 		char buf[PREFIX_SIZE];
 
-		dev_printk_emit(7, dev->dev.parent,
+		dev_printk_emit(LOGLEVEL_DEBUG, dev->dev.parent,
 				"%s%s %s %s%s: %pV",
 				dynamic_emit_prefix(descriptor, buf),
 				dev_driver_string(dev->dev.parent),
-- 
cgit v1.2.3-70-g09d2


From e149ed2b805fefdccf7ccdfc19eca22fdd4514ac Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 1 Nov 2014 10:57:28 -0400
Subject: take the targets of /proc/*/ns/* symlinks to separate fs

New pseudo-filesystem: nsfs.  Targets of /proc/*/ns/* live there now.
It's not mountable (not even registered, so it's not in /proc/filesystems,
etc.).  Files on it *are* bindable - we explicitly permit that in do_loopback().

This stuff lives in fs/nsfs.c now; proc_ns_fget() moved there as well.
get_proc_ns() is a macro now (it's simply returning ->i_private; would
have been an inline, if not for header ordering headache).
proc_ns_inode() is an ex-parrot.  The interface used in procfs is
ns_get_path(path, task, ops) and ns_get_name(buf, size, task, ops).

Dentries and inodes are never hashed; a non-counting reference to dentry
is stashed in ns_common (removed by ->d_prune()) and reused by ns_get_path()
if present.  See ns_get_path()/ns_prune_dentry/nsfs_evict() for details
of that mechanism.

As the result, proc_ns_follow_link() has stopped poking in nd->path.mnt;
it does nd_jump_link() on a consistent <vfsmount,dentry> pair it gets
from ns_get_path().

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/Makefile                |   2 +-
 fs/internal.h              |   5 ++
 fs/namespace.c             |   9 ++-
 fs/nsfs.c                  | 161 +++++++++++++++++++++++++++++++++++++++++++++
 fs/proc/inode.c            |   5 --
 fs/proc/namespaces.c       | 152 ++++--------------------------------------
 include/linux/ns_common.h  |   1 +
 include/linux/proc_ns.h    |  31 +++++----
 include/uapi/linux/magic.h |   1 +
 init/main.c                |   2 +
 10 files changed, 208 insertions(+), 161 deletions(-)
 create mode 100644 fs/nsfs.c

(limited to 'include')

diff --git a/fs/Makefile b/fs/Makefile
index 34a1b9dea6d..34393376eaa 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -11,7 +11,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		attr.o bad_inode.o file.o filesystems.o namespace.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o splice.o sync.o utimes.o \
-		stack.o fs_struct.o statfs.o fs_pin.o
+		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o block_dev.o direct-io.o mpage.o
diff --git a/fs/internal.h b/fs/internal.h
index 757ba2abf21..e9a61fe6757 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -147,3 +147,8 @@ extern const struct file_operations pipefifo_fops;
  */
 extern void sb_pin_kill(struct super_block *sb);
 extern void mnt_pin_kill(struct mount *m);
+
+/*
+ * fs/nsfs.c
+ */
+extern struct dentry_operations ns_dentry_operations;
diff --git a/fs/namespace.c b/fs/namespace.c
index 9dfb4cac0c4..30df6e7dd80 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1569,8 +1569,8 @@ SYSCALL_DEFINE1(oldumount, char __user *, name)
 static bool is_mnt_ns_file(struct dentry *dentry)
 {
 	/* Is this a proxy for a mount namespace? */
-	struct inode *inode = dentry->d_inode;
-	return proc_ns_inode(inode) && dentry->d_fsdata == &mntns_operations;
+	return dentry->d_op == &ns_dentry_operations &&
+	       dentry->d_fsdata == &mntns_operations;
 }
 
 struct mnt_namespace *to_mnt_ns(struct ns_common *ns)
@@ -2016,7 +2016,10 @@ static int do_loopback(struct path *path, const char *old_name,
 	if (IS_MNT_UNBINDABLE(old))
 		goto out2;
 
-	if (!check_mnt(parent) || !check_mnt(old))
+	if (!check_mnt(parent))
+		goto out2;
+
+	if (!check_mnt(old) && old_path.dentry->d_op != &ns_dentry_operations)
 		goto out2;
 
 	if (!recurse && has_locked_children(old, old_path.dentry))
diff --git a/fs/nsfs.c b/fs/nsfs.c
new file mode 100644
index 00000000000..af1b24fa899
--- /dev/null
+++ b/fs/nsfs.c
@@ -0,0 +1,161 @@
+#include <linux/mount.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/proc_ns.h>
+#include <linux/magic.h>
+#include <linux/ktime.h>
+
+static struct vfsmount *nsfs_mnt;
+
+static const struct file_operations ns_file_operations = {
+	.llseek		= no_llseek,
+};
+
+static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+	struct inode *inode = dentry->d_inode;
+	const struct proc_ns_operations *ns_ops = dentry->d_fsdata;
+
+	return dynamic_dname(dentry, buffer, buflen, "%s:[%lu]",
+		ns_ops->name, inode->i_ino);
+}
+
+static void ns_prune_dentry(struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	if (inode) {
+		struct ns_common *ns = inode->i_private;
+		atomic_long_set(&ns->stashed, 0);
+	}
+}
+
+const struct dentry_operations ns_dentry_operations =
+{
+	.d_prune	= ns_prune_dentry,
+	.d_delete	= always_delete_dentry,
+	.d_dname	= ns_dname,
+};
+
+static void nsfs_evict(struct inode *inode)
+{
+	struct ns_common *ns = inode->i_private;
+	clear_inode(inode);
+	ns->ops->put(ns);
+}
+
+void *ns_get_path(struct path *path, struct task_struct *task,
+			const struct proc_ns_operations *ns_ops)
+{
+	struct vfsmount *mnt = mntget(nsfs_mnt);
+	struct qstr qname = { .name = "", };
+	struct dentry *dentry;
+	struct inode *inode;
+	struct ns_common *ns;
+	unsigned long d;
+
+again:
+	ns = ns_ops->get(task);
+	if (!ns) {
+		mntput(mnt);
+		return ERR_PTR(-ENOENT);
+	}
+	rcu_read_lock();
+	d = atomic_long_read(&ns->stashed);
+	if (!d)
+		goto slow;
+	dentry = (struct dentry *)d;
+	if (!lockref_get_not_dead(&dentry->d_lockref))
+		goto slow;
+	rcu_read_unlock();
+	ns_ops->put(ns);
+got_it:
+	path->mnt = mnt;
+	path->dentry = dentry;
+	return NULL;
+slow:
+	rcu_read_unlock();
+	inode = new_inode_pseudo(mnt->mnt_sb);
+	if (!inode) {
+		ns_ops->put(ns);
+		mntput(mnt);
+		return ERR_PTR(-ENOMEM);
+	}
+	inode->i_ino = ns->inum;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+	inode->i_flags |= S_IMMUTABLE;
+	inode->i_mode = S_IFREG | S_IRUGO;
+	inode->i_fop = &ns_file_operations;
+	inode->i_private = ns;
+
+	dentry = d_alloc_pseudo(mnt->mnt_sb, &qname);
+	if (!dentry) {
+		iput(inode);
+		mntput(mnt);
+		return ERR_PTR(-ENOMEM);
+	}
+	d_instantiate(dentry, inode);
+	dentry->d_fsdata = (void *)ns_ops;
+	d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry);
+	if (d) {
+		d_delete(dentry);	/* make sure ->d_prune() does nothing */
+		dput(dentry);
+		cpu_relax();
+		goto again;
+	}
+	goto got_it;
+}
+
+int ns_get_name(char *buf, size_t size, struct task_struct *task,
+			const struct proc_ns_operations *ns_ops)
+{
+	struct ns_common *ns;
+	int res = -ENOENT;
+	ns = ns_ops->get(task);
+	if (ns) {
+		res = snprintf(buf, size, "%s:[%u]", ns_ops->name, ns->inum);
+		ns_ops->put(ns);
+	}
+	return res;
+}
+
+struct file *proc_ns_fget(int fd)
+{
+	struct file *file;
+
+	file = fget(fd);
+	if (!file)
+		return ERR_PTR(-EBADF);
+
+	if (file->f_op != &ns_file_operations)
+		goto out_invalid;
+
+	return file;
+
+out_invalid:
+	fput(file);
+	return ERR_PTR(-EINVAL);
+}
+
+static const struct super_operations nsfs_ops = {
+	.statfs = simple_statfs,
+	.evict_inode = nsfs_evict,
+};
+static struct dentry *nsfs_mount(struct file_system_type *fs_type,
+			int flags, const char *dev_name, void *data)
+{
+	return mount_pseudo(fs_type, "nsfs:", &nsfs_ops,
+			&ns_dentry_operations, NSFS_MAGIC);
+}
+static struct file_system_type nsfs = {
+	.name = "nsfs",
+	.mount = nsfs_mount,
+	.kill_sb = kill_anon_super,
+};
+
+void __init nsfs_init(void)
+{
+	nsfs_mnt = kern_mount(&nsfs);
+	if (IS_ERR(nsfs_mnt))
+		panic("can't set nsfs up\n");
+	nsfs_mnt->mnt_sb->s_flags &= ~MS_NOUSER;
+}
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index a212996e098..57a9be9a666 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -32,7 +32,6 @@ static void proc_evict_inode(struct inode *inode)
 {
 	struct proc_dir_entry *de;
 	struct ctl_table_header *head;
-	struct ns_common *ns;
 
 	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
@@ -49,10 +48,6 @@ static void proc_evict_inode(struct inode *inode)
 		RCU_INIT_POINTER(PROC_I(inode)->sysctl, NULL);
 		sysctl_head_put(head);
 	}
-	/* Release any associated namespace */
-	ns = PROC_I(inode)->ns.ns;
-	if (ns && ns->ops)
-		ns->ops->put(ns);
 }
 
 static struct kmem_cache * proc_inode_cachep;
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 18fc1cf899d..aaaac77abad 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -1,10 +1,6 @@
 #include <linux/proc_fs.h>
 #include <linux/nsproxy.h>
-#include <linux/sched.h>
 #include <linux/ptrace.h>
-#include <linux/fs_struct.h>
-#include <linux/mount.h>
-#include <linux/path.h>
 #include <linux/namei.h>
 #include <linux/file.h>
 #include <linux/utsname.h>
@@ -34,139 +30,45 @@ static const struct proc_ns_operations *ns_entries[] = {
 	&mntns_operations,
 };
 
-static const struct file_operations ns_file_operations = {
-	.llseek		= no_llseek,
-};
-
-static const struct inode_operations ns_inode_operations = {
-	.setattr	= proc_setattr,
-};
-
-static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
-{
-	struct inode *inode = dentry->d_inode;
-	const struct proc_ns_operations *ns_ops = dentry->d_fsdata;
-
-	return dynamic_dname(dentry, buffer, buflen, "%s:[%lu]",
-		ns_ops->name, inode->i_ino);
-}
-
-const struct dentry_operations ns_dentry_operations =
-{
-	.d_delete	= always_delete_dentry,
-	.d_dname	= ns_dname,
-};
-
-static struct dentry *proc_ns_get_dentry(struct super_block *sb,
-	struct task_struct *task, const struct proc_ns_operations *ns_ops)
-{
-	struct dentry *dentry, *result;
-	struct inode *inode;
-	struct proc_inode *ei;
-	struct qstr qname = { .name = "", };
-	struct ns_common *ns;
-
-	ns = ns_ops->get(task);
-	if (!ns)
-		return ERR_PTR(-ENOENT);
-
-	dentry = d_alloc_pseudo(sb, &qname);
-	if (!dentry) {
-		ns_ops->put(ns);
-		return ERR_PTR(-ENOMEM);
-	}
-	dentry->d_fsdata = (void *)ns_ops;
-
-	inode = iget_locked(sb, ns->inum);
-	if (!inode) {
-		dput(dentry);
-		ns_ops->put(ns);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	ei = PROC_I(inode);
-	if (inode->i_state & I_NEW) {
-		inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
-		inode->i_op = &ns_inode_operations;
-		inode->i_mode = S_IFREG | S_IRUGO;
-		inode->i_fop = &ns_file_operations;
-		ei->ns.ns_ops = ns_ops;
-		ei->ns.ns = ns;
-		unlock_new_inode(inode);
-	} else {
-		ns_ops->put(ns);
-	}
-
-	d_set_d_op(dentry, &ns_dentry_operations);
-	result = d_instantiate_unique(dentry, inode);
-	if (result) {
-		dput(dentry);
-		dentry = result;
-	}
-
-	return dentry;
-}
-
 static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
 	struct inode *inode = dentry->d_inode;
-	struct super_block *sb = inode->i_sb;
-	struct proc_inode *ei = PROC_I(inode);
+	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns.ns_ops;
 	struct task_struct *task;
 	struct path ns_path;
 	void *error = ERR_PTR(-EACCES);
 
 	task = get_proc_task(inode);
 	if (!task)
-		goto out;
+		return error;
 
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
-		goto out_put_task;
-
-	ns_path.dentry = proc_ns_get_dentry(sb, task, ei->ns.ns_ops);
-	if (IS_ERR(ns_path.dentry)) {
-		error = ERR_CAST(ns_path.dentry);
-		goto out_put_task;
+	if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+		error = ns_get_path(&ns_path, task, ns_ops);
+		if (!error)
+			nd_jump_link(nd, &ns_path);
 	}
-
-	ns_path.mnt = mntget(nd->path.mnt);
-	nd_jump_link(nd, &ns_path);
-	error = NULL;
-
-out_put_task:
 	put_task_struct(task);
-out:
 	return error;
 }
 
 static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
 	struct inode *inode = dentry->d_inode;
-	struct proc_inode *ei = PROC_I(inode);
-	const struct proc_ns_operations *ns_ops = ei->ns.ns_ops;
+	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns.ns_ops;
 	struct task_struct *task;
-	struct ns_common *ns;
 	char name[50];
 	int res = -EACCES;
 
 	task = get_proc_task(inode);
 	if (!task)
-		goto out;
-
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
-		goto out_put_task;
+		return res;
 
-	res = -ENOENT;
-	ns = ns_ops->get(task);
-	if (!ns)
-		goto out_put_task;
-
-	snprintf(name, sizeof(name), "%s:[%u]", ns_ops->name, ns->inum);
-	res = readlink_copy(buffer, buflen, name);
-	ns_ops->put(ns);
-out_put_task:
+	if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+		res = ns_get_name(name, sizeof(name), task, ns_ops);
+		if (res >= 0)
+			res = readlink_copy(buffer, buflen, name);
+	}
 	put_task_struct(task);
-out:
 	return res;
 }
 
@@ -268,31 +170,3 @@ const struct inode_operations proc_ns_dir_inode_operations = {
 	.getattr	= pid_getattr,
 	.setattr	= proc_setattr,
 };
-
-struct file *proc_ns_fget(int fd)
-{
-	struct file *file;
-
-	file = fget(fd);
-	if (!file)
-		return ERR_PTR(-EBADF);
-
-	if (file->f_op != &ns_file_operations)
-		goto out_invalid;
-
-	return file;
-
-out_invalid:
-	fput(file);
-	return ERR_PTR(-EINVAL);
-}
-
-struct ns_common *get_proc_ns(struct inode *inode)
-{
-	return PROC_I(inode)->ns.ns;
-}
-
-bool proc_ns_inode(struct inode *inode)
-{
-	return inode->i_fop == &ns_file_operations;
-}
diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index ce23cf4bbe6..85a5c8c16be 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -4,6 +4,7 @@
 struct proc_ns_operations;
 
 struct ns_common {
+	atomic_long_t stashed;
 	const struct proc_ns_operations *ops;
 	unsigned int inum;
 };
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 2837ff41cfe..42dfc615dbf 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -4,9 +4,11 @@
 #ifndef _LINUX_PROC_NS_H
 #define _LINUX_PROC_NS_H
 
+#include <linux/ns_common.h>
+
 struct pid_namespace;
 struct nsproxy;
-struct ns_common;
+struct path;
 
 struct proc_ns_operations {
 	const char *name;
@@ -38,35 +40,38 @@ enum {
 
 extern int pid_ns_prepare_proc(struct pid_namespace *ns);
 extern void pid_ns_release_proc(struct pid_namespace *ns);
-extern struct file *proc_ns_fget(int fd);
-extern struct ns_common *get_proc_ns(struct inode *);
 extern int proc_alloc_inum(unsigned int *pino);
 extern void proc_free_inum(unsigned int inum);
-extern bool proc_ns_inode(struct inode *inode);
 
 #else /* CONFIG_PROC_FS */
 
 static inline int pid_ns_prepare_proc(struct pid_namespace *ns) { return 0; }
 static inline void pid_ns_release_proc(struct pid_namespace *ns) {}
 
-static inline struct file *proc_ns_fget(int fd)
-{
-	return ERR_PTR(-EINVAL);
-}
-
-static inline struct ns_common *get_proc_ns(struct inode *inode) { return NULL; }
-
 static inline int proc_alloc_inum(unsigned int *inum)
 {
 	*inum = 1;
 	return 0;
 }
 static inline void proc_free_inum(unsigned int inum) {}
-static inline bool proc_ns_inode(struct inode *inode) { return false; }
 
 #endif /* CONFIG_PROC_FS */
 
-#define ns_alloc_inum(ns) proc_alloc_inum(&(ns)->inum)
+static inline int ns_alloc_inum(struct ns_common *ns)
+{
+	atomic_long_set(&ns->stashed, 0);
+	return proc_alloc_inum(&ns->inum);
+}
+
 #define ns_free_inum(ns) proc_free_inum((ns)->inum)
 
+extern struct file *proc_ns_fget(int fd);
+#define get_proc_ns(inode) ((struct ns_common *)(inode)->i_private)
+extern void *ns_get_path(struct path *path, struct task_struct *task,
+			const struct proc_ns_operations *ns_ops);
+
+extern int ns_get_name(char *buf, size_t size, struct task_struct *task,
+			const struct proc_ns_operations *ns_ops);
+extern void nsfs_init(void);
+
 #endif /* _LINUX_PROC_NS_H */
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index 77c60311a6c..7d664ea85eb 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -72,5 +72,6 @@
 #define MTD_INODE_FS_MAGIC      0x11307854
 #define ANON_INODE_FS_MAGIC	0x09041934
 #define BTRFS_TEST_MAGIC	0x73727279
+#define NSFS_MAGIC		0x6e736673
 
 #endif /* __LINUX_MAGIC_H__ */
diff --git a/init/main.c b/init/main.c
index 800a0daede7..bcc75057ea8 100644
--- a/init/main.c
+++ b/init/main.c
@@ -78,6 +78,7 @@
 #include <linux/context_tracking.h>
 #include <linux/random.h>
 #include <linux/list.h>
+#include <linux/proc_ns.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -660,6 +661,7 @@ asmlinkage __visible void __init start_kernel(void)
 	/* rootfs populating might need page-writeback */
 	page_writeback_init();
 	proc_root_init();
+	nsfs_init();
 	cgroup_init();
 	cpuset_init();
 	taskstats_init_early();
-- 
cgit v1.2.3-70-g09d2


From 1f55a6ec940fb45e3edaa52b6e9fc40cf8e18dcb Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 1 Nov 2014 19:30:41 -0400
Subject: make nameidata completely opaque outside of fs/namei.c

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c            | 24 ++++++++++++++++++++++++
 include/linux/namei.h | 25 +++----------------------
 2 files changed, 27 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/fs/namei.c b/fs/namei.c
index db5fe86319e..398a73b522c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -487,6 +487,18 @@ void path_put(const struct path *path)
 }
 EXPORT_SYMBOL(path_put);
 
+struct nameidata {
+	struct path	path;
+	struct qstr	last;
+	struct path	root;
+	struct inode	*inode; /* path.dentry.d_inode */
+	unsigned int	flags;
+	unsigned	seq, m_seq;
+	int		last_type;
+	unsigned	depth;
+	char *saved_names[MAX_NESTED_LINKS + 1];
+};
+
 /*
  * Path walking has 2 modes, rcu-walk and ref-walk (see
  * Documentation/filesystems/path-lookup.txt).  In situations when we can't
@@ -695,6 +707,18 @@ void nd_jump_link(struct nameidata *nd, struct path *path)
 	nd->flags |= LOOKUP_JUMPED;
 }
 
+void nd_set_link(struct nameidata *nd, char *path)
+{
+	nd->saved_names[nd->depth] = path;
+}
+EXPORT_SYMBOL(nd_set_link);
+
+char *nd_get_link(struct nameidata *nd)
+{
+	return nd->saved_names[nd->depth];
+}
+EXPORT_SYMBOL(nd_get_link);
+
 static inline void put_link(struct nameidata *nd, struct path *link, void *cookie)
 {
 	struct inode *inode = link->dentry->d_inode;
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 492de72560f..c8990779f0c 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -7,21 +7,10 @@
 #include <linux/path.h>
 
 struct vfsmount;
+struct nameidata;
 
 enum { MAX_NESTED_LINKS = 8 };
 
-struct nameidata {
-	struct path	path;
-	struct qstr	last;
-	struct path	root;
-	struct inode	*inode; /* path.dentry.d_inode */
-	unsigned int	flags;
-	unsigned	seq, m_seq;
-	int		last_type;
-	unsigned	depth;
-	char *saved_names[MAX_NESTED_LINKS + 1];
-};
-
 /*
  * Type of the last component on LOOKUP_PARENT
  */
@@ -82,16 +71,8 @@ extern struct dentry *lock_rename(struct dentry *, struct dentry *);
 extern void unlock_rename(struct dentry *, struct dentry *);
 
 extern void nd_jump_link(struct nameidata *nd, struct path *path);
-
-static inline void nd_set_link(struct nameidata *nd, char *path)
-{
-	nd->saved_names[nd->depth] = path;
-}
-
-static inline char *nd_get_link(struct nameidata *nd)
-{
-	return nd->saved_names[nd->depth];
-}
+extern void nd_set_link(struct nameidata *nd, char *path);
+extern char *nd_get_link(struct nameidata *nd);
 
 static inline void nd_terminate_link(void *name, size_t len, size_t maxlen)
 {
-- 
cgit v1.2.3-70-g09d2


From bd9b51e79cb0b8bc00a7e0076a4a8963ca4a797c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 18 Nov 2014 23:38:21 -0500
Subject: make default ->i_fop have ->open() fail with ENXIO

As it is, default ->i_fop has NULL ->open() (along with all other methods).
The only case where it matters is reopening (via procfs symlink) a file that
didn't get its ->f_op from ->i_fop - anything else will have ->i_fop assigned
to something sane (default would fail on read/write/ioctl/etc.).

	Unfortunately, such case exists - alloc_file() users, especially
anon_get_file() ones.  There we have tons of opened files of very different
kinds sharing the same inode.  As the result, attempt to reopen those via
procfs succeeds and you get a descriptor you can't do anything with.

	Moreover, in case of sockets we set ->i_fop that will only be used
on such reopen attempts - and put a failing ->open() into it to make sure
those do not succeed.

	It would be simpler to put such ->open() into default ->i_fop and leave
it unchanged both for anon inode (as we do anyway) and for socket ones.  Result:
	* everything going through do_dentry_open() works as it used to
	* sock_no_open() kludge is gone
	* attempts to reopen anon-inode files fail as they really ought to
	* ditto for aio_private_file()
	* ditto for perfmon - this one actually tried to imitate sock_no_open()
trick, but failed to set ->i_fop, so in the current tree reopens succeed and
yield completely useless descriptor.  Intent clearly had been to fail with
-ENXIO on such reopens; now it actually does.
	* everything else that used alloc_file() keeps working - it has ->i_fop
set for its inodes anyway

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/ia64/kernel/perfmon.c | 10 ----------
 fs/inode.c                 | 11 ++++++++---
 include/linux/fs.h         |  1 -
 net/Makefile               |  2 --
 net/nonet.c                | 26 --------------------------
 net/socket.c               | 19 -------------------
 6 files changed, 8 insertions(+), 61 deletions(-)
 delete mode 100644 net/nonet.c

(limited to 'include')

diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 5845ffea67c..ac4528f5acd 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -2145,22 +2145,12 @@ doit:
 	return 0;
 }
 
-static int
-pfm_no_open(struct inode *irrelevant, struct file *dontcare)
-{
-	DPRINT(("pfm_no_open called\n"));
-	return -ENXIO;
-}
-
-
-
 static const struct file_operations pfm_file_ops = {
 	.llseek		= no_llseek,
 	.read		= pfm_read,
 	.write		= pfm_write,
 	.poll		= pfm_poll,
 	.unlocked_ioctl = pfm_ioctl,
-	.open		= pfm_no_open,	/* special open code to disallow open via /proc */
 	.fasync		= pfm_fasync,
 	.release	= pfm_close,
 	.flush		= pfm_flush
diff --git a/fs/inode.c b/fs/inode.c
index 26753ba7b6d..5b83ef7fc8d 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -114,6 +114,11 @@ int proc_nr_inodes(struct ctl_table *table, int write,
 }
 #endif
 
+static int no_open(struct inode *inode, struct file *file)
+{
+	return -ENXIO;
+}
+
 /**
  * inode_init_always - perform inode structure intialisation
  * @sb: superblock inode belongs to
@@ -125,7 +130,7 @@ int proc_nr_inodes(struct ctl_table *table, int write,
 int inode_init_always(struct super_block *sb, struct inode *inode)
 {
 	static const struct inode_operations empty_iops;
-	static const struct file_operations empty_fops;
+	static const struct file_operations no_open_fops = {.open = no_open};
 	struct address_space *const mapping = &inode->i_data;
 
 	inode->i_sb = sb;
@@ -133,7 +138,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_flags = 0;
 	atomic_set(&inode->i_count, 1);
 	inode->i_op = &empty_iops;
-	inode->i_fop = &empty_fops;
+	inode->i_fop = &no_open_fops;
 	inode->__i_nlink = 1;
 	inode->i_opflags = 0;
 	i_uid_write(inode, 0);
@@ -1801,7 +1806,7 @@ void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
 	} else if (S_ISFIFO(mode))
 		inode->i_fop = &pipefifo_fops;
 	else if (S_ISSOCK(mode))
-		inode->i_fop = &bad_sock_fops;
+		;	/* leave it no_open_fops */
 	else
 		printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for"
 				  " inode %s:%lu\n", mode, inode->i_sb->s_id,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2beddc284bc..b37beaf7a3a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2151,7 +2151,6 @@ static inline int sb_is_blkdev_sb(struct super_block *sb)
 extern int sync_filesystem(struct super_block *);
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
-extern const struct file_operations bad_sock_fops;
 #ifdef CONFIG_BLOCK
 extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
 extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
diff --git a/net/Makefile b/net/Makefile
index 7ed1970074b..1f6c3e4b36d 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -5,8 +5,6 @@
 # Rewritten to use lists instead of if-statements.
 #
 
-obj-y	:= nonet.o
-
 obj-$(CONFIG_NET)		:= socket.o core/
 
 tmp-$(CONFIG_COMPAT) 		:= compat.o
diff --git a/net/nonet.c b/net/nonet.c
deleted file mode 100644
index b1a73fda9c1..00000000000
--- a/net/nonet.c
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * net/nonet.c
- *
- * Dummy functions to allow us to configure network support entirely
- * out of the kernel.
- *
- * Distributed under the terms of the GNU GPL version 2.
- * Copyright (c) Matthew Wilcox 2003
- */
-
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-
-static int sock_no_open(struct inode *irrelevant, struct file *dontcare)
-{
-	return -ENXIO;
-}
-
-const struct file_operations bad_sock_fops = {
-	.owner = THIS_MODULE,
-	.open = sock_no_open,
-	.llseek = noop_llseek,
-};
diff --git a/net/socket.c b/net/socket.c
index fe20c319a0b..850f6c38334 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -113,7 +113,6 @@ unsigned int sysctl_net_busy_read __read_mostly;
 unsigned int sysctl_net_busy_poll __read_mostly;
 #endif
 
-static int sock_no_open(struct inode *irrelevant, struct file *dontcare);
 static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
 			 unsigned long nr_segs, loff_t pos);
 static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
@@ -151,7 +150,6 @@ static const struct file_operations socket_file_ops = {
 	.compat_ioctl = compat_sock_ioctl,
 #endif
 	.mmap =		sock_mmap,
-	.open =		sock_no_open,	/* special open code to disallow open via /proc */
 	.release =	sock_close,
 	.fasync =	sock_fasync,
 	.sendpage =	sock_sendpage,
@@ -559,23 +557,6 @@ static struct socket *sock_alloc(void)
 	return sock;
 }
 
-/*
- *	In theory you can't get an open on this inode, but /proc provides
- *	a back door. Remember to keep it shut otherwise you'll let the
- *	creepy crawlies in.
- */
-
-static int sock_no_open(struct inode *irrelevant, struct file *dontcare)
-{
-	return -ENXIO;
-}
-
-const struct file_operations bad_sock_fops = {
-	.owner = THIS_MODULE,
-	.open = sock_no_open,
-	.llseek = noop_llseek,
-};
-
 /**
  *	sock_release	-	close a socket
  *	@sock: socket to close
-- 
cgit v1.2.3-70-g09d2


From 81e1dadfb5b2d47aa513ad60b1c9cf0ea17b6514 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Thu, 4 Dec 2014 11:54:43 +0530
Subject: arm: omap3: twl: remove usb phy init data

commit dbc98635e0d4 ("phy: remove the old lookup method") removes
struct phy_consumer but twl-common.c still uses the "phy_consumer"
structure resulting in the following compilation warning.

arch/arm/mach-omap2/twl-common.c:94:21: error: array type has
incomplete element type
 struct phy_consumer consumers[] = {

Removed using phy_consumer since twl4030 uses the new lookup
method.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Greg Kroah-Hartman <greg@kroah.com>
---
 arch/arm/mach-omap2/twl-common.c | 12 +-----------
 include/linux/i2c/twl.h          |  2 --
 2 files changed, 1 insertion(+), 13 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c
index b0d54dae1bc..4457e731f7a 100644
--- a/arch/arm/mach-omap2/twl-common.c
+++ b/arch/arm/mach-omap2/twl-common.c
@@ -91,18 +91,8 @@ void __init omap_pmic_late_init(void)
 }
 
 #if defined(CONFIG_ARCH_OMAP3)
-struct phy_consumer consumers[] = {
-	PHY_CONSUMER("musb-hdrc.0", "usb"),
-};
-
-struct phy_init_data init_data = {
-	.consumers = consumers,
-	.num_consumers = ARRAY_SIZE(consumers),
-};
-
 static struct twl4030_usb_data omap3_usb_pdata = {
-	.usb_mode	= T2_USB_MODE_ULPI,
-	.init_data	= &init_data,
+	.usb_mode = T2_USB_MODE_ULPI,
 };
 
 static int omap3_batt_table[] = {
diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h
index 8cfb50f3852..0bc03f100d0 100644
--- a/include/linux/i2c/twl.h
+++ b/include/linux/i2c/twl.h
@@ -26,7 +26,6 @@
 #define __TWL_H_
 
 #include <linux/types.h>
-#include <linux/phy/phy.h>
 #include <linux/input/matrix_keypad.h>
 
 /*
@@ -634,7 +633,6 @@ enum twl4030_usb_mode {
 struct twl4030_usb_data {
 	enum twl4030_usb_mode	usb_mode;
 	unsigned long		features;
-	struct phy_init_data	*init_data;
 
 	int		(*phy_init)(struct device *dev);
 	int		(*phy_exit)(struct device *dev);
-- 
cgit v1.2.3-70-g09d2


From f95b414edb18de59940dcebbefb49cf25c6d505c Mon Sep 17 00:00:00 2001
From: Gu Zheng <guz.fnst@cn.fujitsu.com>
Date: Thu, 11 Dec 2014 11:22:04 +0800
Subject: net: introduce helper macro for_each_cmsghdr

Introduce helper macro for_each_cmsghdr as a wrapper of the enumerating
cmsghdr from msghdr, just cleanup.

Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 crypto/af_alg.c        | 2 +-
 include/linux/socket.h | 4 ++++
 net/core/scm.c         | 3 +--
 net/dccp/proto.c       | 5 ++---
 net/ipv4/ip_sockglue.c | 2 +-
 net/ipv6/datagram.c    | 2 +-
 net/iucv/af_iucv.c     | 4 +---
 net/rds/send.c         | 4 ++--
 net/rxrpc/ar-output.c  | 2 +-
 net/sctp/socket.c      | 3 +--
 10 files changed, 15 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 6a3ad801158..bc21f520d48 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -399,7 +399,7 @@ int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con)
 {
 	struct cmsghdr *cmsg;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg))
 			return -EINVAL;
 		if (cmsg->cmsg_level != SOL_ALG)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 048d6d6eed6..6e49a14365d 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -103,6 +103,10 @@ struct cmsghdr {
 			     (cmsg)->cmsg_len <= (unsigned long) \
 			     ((mhdr)->msg_controllen - \
 			      ((char *)(cmsg) - (char *)(mhdr)->msg_control)))
+#define for_each_cmsghdr(cmsg, msg) \
+	for (cmsg = CMSG_FIRSTHDR(msg); \
+	     cmsg; \
+	     cmsg = CMSG_NXTHDR(msg, cmsg))
 
 /*
  *	Get the next cmsg header
diff --git a/net/core/scm.c b/net/core/scm.c
index b442e7e25e6..3b6899b7d81 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -129,8 +129,7 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
 	struct cmsghdr *cmsg;
 	int err;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg))
-	{
+	for_each_cmsghdr(cmsg, msg) {
 		err = -EINVAL;
 
 		/* Verify that cmsg_len is at least sizeof(struct cmsghdr) */
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 19f03873908..e171b780b49 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -703,7 +703,7 @@ EXPORT_SYMBOL_GPL(compat_dccp_getsockopt);
 
 static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb)
 {
-	struct cmsghdr *cmsg = CMSG_FIRSTHDR(msg);
+	struct cmsghdr *cmsg;
 
 	/*
 	 * Assign an (opaque) qpolicy priority value to skb->priority.
@@ -717,8 +717,7 @@ static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb)
 	 */
 	skb->priority = 0;
 
-	for (; cmsg != NULL; cmsg = CMSG_NXTHDR(msg, cmsg)) {
-
+	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg))
 			return -EINVAL;
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 640f26c6a9f..8a89c738b7a 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -192,7 +192,7 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 	int err, val;
 	struct cmsghdr *cmsg;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg))
 			return -EINVAL;
 #if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 2464a00e36a..100c589a2a6 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -657,7 +657,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 	int len;
 	int err = 0;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+	for_each_cmsghdr(cmsg, msg) {
 		int addr_type;
 
 		if (!CMSG_OK(msg, cmsg)) {
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 1cd3f810723..2e9953b2db8 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1070,9 +1070,7 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	txmsg.class = 0;
 
 	/* iterate over control messages */
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg;
-		cmsg = CMSG_NXTHDR(msg, cmsg)) {
-
+	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg)) {
 			err = -EINVAL;
 			goto out;
diff --git a/net/rds/send.c b/net/rds/send.c
index 40a5629a0a1..42f65d4305c 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -826,7 +826,7 @@ static int rds_rm_size(struct msghdr *msg, int data_len)
 	int cmsg_groups = 0;
 	int retval;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg))
 			return -EINVAL;
 
@@ -878,7 +878,7 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm,
 	struct cmsghdr *cmsg;
 	int ret = 0;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg))
 			return -EINVAL;
 
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c
index 86e0f10aa2c..e1a9373e597 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/ar-output.c
@@ -45,7 +45,7 @@ static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 	if (msg->msg_controllen == 0)
 		return -EINVAL;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg))
 			return -EINVAL;
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index c92f96cda69..2625eccb77d 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -6592,8 +6592,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs)
 	struct cmsghdr *cmsg;
 	struct msghdr *my_msg = (struct msghdr *)msg;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg != NULL;
-	     cmsg = CMSG_NXTHDR(my_msg, cmsg)) {
+	for_each_cmsghdr(cmsg, my_msg) {
 		if (!CMSG_OK(my_msg, cmsg))
 			return -EINVAL;
 
-- 
cgit v1.2.3-70-g09d2


From 3d2667826cbb5e2eb8d8c7ee92f74bcb00b36a2f Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 11 Dec 2014 15:54:07 +0200
Subject: virtio_config: fix virtio_cread_bytes

virtio_cread_bytes is implemented incorrectly in case length happens to
be 2,4 or 8 bytes: transports and devices will assume it's an integer
value that has to be converted to LE format.

Let's just do multiple 1-byte reads: this also makes life easier
for transports who only need to implement 1,2,4 and 8 byte reads.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_config.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 7979f850e7a..a61cd37f088 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -305,7 +305,10 @@ static inline void virtio_cread_bytes(struct virtio_device *vdev,
 				      unsigned int offset,
 				      void *buf, size_t len)
 {
-	vdev->config->get(vdev, offset, buf, len);
+	int i;
+
+	for (i = 0; i < len; i++)
+		vdev->config->get(vdev, offset + i, buf + i, 1);
 }
 
 static inline void virtio_cwrite8(struct virtio_device *vdev,
-- 
cgit v1.2.3-70-g09d2


From 3dca0f42c7baaa4e01699629da13d6556f001ebe Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 11 Dec 2014 10:57:53 +0200
Subject: net/mlx4_core: Use tasklet for user-space CQ completion events

Previously, we've fired all our completion callbacks straight from our ISR.

Some of those callbacks were lightweight (for example, mlx4_en's and
IPoIB napi callbacks), but some of them did more work (for example,
the user-space RDMA stack uverbs' completion handler). Besides that,
doing more than the minimal work in ISR is generally considered wrong,
it could even lead to a hard lockup of the system. Since when a lot
of completion events are generated by the hardware, the loop over those
events could be so long, that we'll get into a hard lockup by the system
watchdog.

In order to avoid that, add a new way of invoking completion events
callbacks. In the interrupt itself, we add the CQs which receive completion
event to a per-EQ list and schedule a tasklet. In the tasklet context
we loop over all the CQs in the list and invoke the user callback.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/cq.c           |  5 +++-
 drivers/net/ethernet/mellanox/mlx4/cq.c   | 50 +++++++++++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx4/eq.c   | 16 +++++++++-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h | 12 ++++++++
 include/linux/mlx4/device.h               |  5 ++++
 5 files changed, 86 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 1066eec854a..a3b70f6c403 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -233,7 +233,10 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 	if (err)
 		goto err_dbmap;
 
-	cq->mcq.comp  = mlx4_ib_cq_comp;
+	if (context)
+		cq->mcq.tasklet_ctx.comp = mlx4_ib_cq_comp;
+	else
+		cq->mcq.comp = mlx4_ib_cq_comp;
 	cq->mcq.event = mlx4_ib_cq_event;
 
 	if (context)
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 56022d64783..e71f31387ac 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -52,6 +52,51 @@
 #define MLX4_CQ_STATE_ARMED_SOL		( 6 <<  8)
 #define MLX4_EQ_STATE_FIRED		(10 <<  8)
 
+#define TASKLET_MAX_TIME 2
+#define TASKLET_MAX_TIME_JIFFIES msecs_to_jiffies(TASKLET_MAX_TIME)
+
+void mlx4_cq_tasklet_cb(unsigned long data)
+{
+	unsigned long flags;
+	unsigned long end = jiffies + TASKLET_MAX_TIME_JIFFIES;
+	struct mlx4_eq_tasklet *ctx = (struct mlx4_eq_tasklet *)data;
+	struct mlx4_cq *mcq, *temp;
+
+	spin_lock_irqsave(&ctx->lock, flags);
+	list_splice_tail_init(&ctx->list, &ctx->process_list);
+	spin_unlock_irqrestore(&ctx->lock, flags);
+
+	list_for_each_entry_safe(mcq, temp, &ctx->process_list, tasklet_ctx.list) {
+		list_del_init(&mcq->tasklet_ctx.list);
+		mcq->tasklet_ctx.comp(mcq);
+		if (atomic_dec_and_test(&mcq->refcount))
+			complete(&mcq->free);
+		if (time_after(jiffies, end))
+			break;
+	}
+
+	if (!list_empty(&ctx->process_list))
+		tasklet_schedule(&ctx->task);
+}
+
+static void mlx4_add_cq_to_tasklet(struct mlx4_cq *cq)
+{
+	unsigned long flags;
+	struct mlx4_eq_tasklet *tasklet_ctx = cq->tasklet_ctx.priv;
+
+	spin_lock_irqsave(&tasklet_ctx->lock, flags);
+	/* When migrating CQs between EQs will be implemented, please note
+	 * that you need to sync this point. It is possible that
+	 * while migrating a CQ, completions on the old EQs could
+	 * still arrive.
+	 */
+	if (list_empty_careful(&cq->tasklet_ctx.list)) {
+		atomic_inc(&cq->refcount);
+		list_add_tail(&cq->tasklet_ctx.list, &tasklet_ctx->list);
+	}
+	spin_unlock_irqrestore(&tasklet_ctx->lock, flags);
+}
+
 void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn)
 {
 	struct mlx4_cq *cq;
@@ -292,6 +337,11 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	cq->uar        = uar;
 	atomic_set(&cq->refcount, 1);
 	init_completion(&cq->free);
+	cq->comp = mlx4_add_cq_to_tasklet;
+	cq->tasklet_ctx.priv =
+		&priv->eq_table.eq[cq->vector].tasklet_ctx;
+	INIT_LIST_HEAD(&cq->tasklet_ctx.list);
+
 
 	cq->irq = priv->eq_table.eq[cq->vector].irq;
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index d68b264cee4..3d275fbaf0e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -450,7 +450,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_eqe *eqe;
-	int cqn;
+	int cqn = -1;
 	int eqes_found = 0;
 	int set_ci = 0;
 	int port;
@@ -758,6 +758,13 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 
 	eq_set_ci(eq, 1);
 
+	/* cqn is 24bit wide but is initialized such that its higher bits
+	 * are ones too. Thus, if we got any event, cqn's high bits should be off
+	 * and we need to schedule the tasklet.
+	 */
+	if (!(cqn & ~0xffffff))
+		tasklet_schedule(&eq->tasklet_ctx.task);
+
 	return eqes_found;
 }
 
@@ -971,6 +978,12 @@ static int mlx4_create_eq(struct mlx4_dev *dev, int nent,
 
 	eq->cons_index = 0;
 
+	INIT_LIST_HEAD(&eq->tasklet_ctx.list);
+	INIT_LIST_HEAD(&eq->tasklet_ctx.process_list);
+	spin_lock_init(&eq->tasklet_ctx.lock);
+	tasklet_init(&eq->tasklet_ctx.task, mlx4_cq_tasklet_cb,
+		     (unsigned long)&eq->tasklet_ctx);
+
 	return err;
 
 err_out_free_mtt:
@@ -1027,6 +1040,7 @@ static void mlx4_free_eq(struct mlx4_dev *dev,
 		}
 	}
 	synchronize_irq(eq->irq);
+	tasklet_disable(&eq->tasklet_ctx.task);
 
 	mlx4_mtt_cleanup(dev, &eq->mtt);
 	for (i = 0; i < npages; ++i)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index f48e7c3eecf..b67ef488c30 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -43,6 +43,8 @@
 #include <linux/timer.h>
 #include <linux/semaphore.h>
 #include <linux/workqueue.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/driver.h>
@@ -373,6 +375,14 @@ struct mlx4_srq_context {
 	__be64			db_rec_addr;
 };
 
+struct mlx4_eq_tasklet {
+	struct list_head list;
+	struct list_head process_list;
+	struct tasklet_struct task;
+	/* lock on completion tasklet list */
+	spinlock_t lock;
+};
+
 struct mlx4_eq {
 	struct mlx4_dev	       *dev;
 	void __iomem	       *doorbell;
@@ -383,6 +393,7 @@ struct mlx4_eq {
 	int			nent;
 	struct mlx4_buf_list   *page_list;
 	struct mlx4_mtt		mtt;
+	struct mlx4_eq_tasklet	tasklet_ctx;
 };
 
 struct mlx4_slave_eqe {
@@ -1146,6 +1157,7 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev);
 int mlx4_comm_cmd(struct mlx4_dev *dev, u8 cmd, u16 param,
 		  unsigned long timeout);
 
+void mlx4_cq_tasklet_cb(unsigned long data);
 void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn);
 void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type);
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index cf09e65c290..3951b5368d7 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -621,6 +621,11 @@ struct mlx4_cq {
 
 	atomic_t		refcount;
 	struct completion	free;
+	struct {
+		struct list_head list;
+		void (*comp)(struct mlx4_cq *);
+		void		*priv;
+	} tasklet_ctx;
 };
 
 struct mlx4_qp {
-- 
cgit v1.2.3-70-g09d2


From ddae0349fdb78bcc5e7219061847012aa1a29069 Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.co.il>
Date: Thu, 11 Dec 2014 10:57:54 +0200
Subject: net/mlx4: Change QP allocation scheme

When using BF (Blue-Flame), the QPN overrides the VLAN, CV, and SV fields
in the WQE. Thus, BF may only be used for QPNs with bits 6,7 unset.

The current Ethernet driver code reserves a Tx QP range with 256b alignment.

This is wrong because if there are more than 64 Tx QPs in use,
QPNs >= base + 65 will have bits 6/7 set.

This problem is not specific for the Ethernet driver, any entity that
tries to reserve more than 64 BF-enabled QPs should fail. Also, using
ranges is not necessary here and is wasteful.

The new mechanism introduced here will support reservation for
"Eth QPs eligible for BF" for all drivers: bare-metal, multi-PF, and VFs
(when hypervisors support WC in VMs). The flow we use is:

1. In mlx4_en, allocate Tx QPs one by one instead of a range allocation,
   and request "BF enabled QPs" if BF is supported for the function

2. In the ALLOC_RES FW command, change param1 to:
a. param1[23:0]  - number of QPs
b. param1[31-24] - flags controlling QPs reservation

Bit 31 refers to Eth blueflame supported QPs. Those QPs must have
bits 6 and 7 unset in order to be used in Ethernet.

Bits 24-30 of the flags are currently reserved.

When a function tries to allocate a QP, it states the required attributes
for this QP. Those attributes are considered "best-effort". If an attribute,
such as Ethernet BF enabled QP, is a must-have attribute, the function has
to check that attribute is supported before trying to do the allocation.

In a lower layer of the code, mlx4_qp_reserve_range masks out the bits
which are unsupported. If SRIOV is used, the PF validates those attributes
and masks out unsupported attributes as well. In order to notify VFs which
attributes are supported, the VF uses QUERY_FUNC_CAP command. This command's
mailbox is filled by the PF, which notifies which QP allocation attributes
it supports.

Signed-off-by: Eugenia Emantayev <eugenia@mellanox.co.il>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c                  |  2 +-
 drivers/infiniband/hw/mlx4/qp.c                    | 11 ++++--
 drivers/net/ethernet/mellanox/mlx4/alloc.c         | 43 +++++++++++++++++++---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c     | 10 +----
 drivers/net/ethernet/mellanox/mlx4/en_rx.c         |  4 +-
 drivers/net/ethernet/mellanox/mlx4/en_tx.c         | 14 +++++--
 drivers/net/ethernet/mellanox/mlx4/fw.c            | 20 +++++++++-
 drivers/net/ethernet/mellanox/mlx4/fw.h            |  1 +
 drivers/net/ethernet/mellanox/mlx4/main.c          | 11 +++++-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h          |  5 ++-
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h       |  2 +-
 drivers/net/ethernet/mellanox/mlx4/qp.c            | 24 +++++++++---
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  |  7 +++-
 include/linux/mlx4/device.h                        | 21 ++++++++++-
 14 files changed, 137 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 0c3375524a6..57ecc5b204f 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2227,7 +2227,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		ibdev->steer_qpn_count = MLX4_IB_UC_MAX_NUM_QPS;
 		err = mlx4_qp_reserve_range(dev, ibdev->steer_qpn_count,
 					    MLX4_IB_UC_STEER_QPN_ALIGN,
-					    &ibdev->steer_qpn_base);
+					    &ibdev->steer_qpn_base, 0);
 		if (err)
 			goto err_counter;
 
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 9c5150c3cb3..506d1bdad22 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -802,16 +802,19 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 			}
 		}
 	} else {
-		/* Raw packet QPNs must be aligned to 8 bits. If not, the WQE
-		 * BlueFlame setup flow wrongly causes VLAN insertion. */
+		/* Raw packet QPNs may not have bits 6,7 set in their qp_num;
+		 * otherwise, the WQE BlueFlame setup flow wrongly causes
+		 * VLAN insertion. */
 		if (init_attr->qp_type == IB_QPT_RAW_PACKET)
-			err = mlx4_qp_reserve_range(dev->dev, 1, 1 << 8, &qpn);
+			err = mlx4_qp_reserve_range(dev->dev, 1, 1, &qpn,
+						    init_attr->cap.max_send_wr ?
+						    MLX4_RESERVE_ETH_BF_QP : 0);
 		else
 			if (qp->flags & MLX4_IB_QP_NETIF)
 				err = mlx4_ib_steer_qp_alloc(dev, 1, &qpn);
 			else
 				err = mlx4_qp_reserve_range(dev->dev, 1, 1,
-							    &qpn);
+							    &qpn, 0);
 		if (err)
 			goto err_proxy;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index b0297da5030..91a8acc191b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -76,22 +76,53 @@ void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj, int use_rr)
 	mlx4_bitmap_free_range(bitmap, obj, 1, use_rr);
 }
 
-u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align)
+static unsigned long find_aligned_range(unsigned long *bitmap,
+					u32 start, u32 nbits,
+					int len, int align, u32 skip_mask)
+{
+	unsigned long end, i;
+
+again:
+	start = ALIGN(start, align);
+
+	while ((start < nbits) && (test_bit(start, bitmap) ||
+				   (start & skip_mask)))
+		start += align;
+
+	if (start >= nbits)
+		return -1;
+
+	end = start+len;
+	if (end > nbits)
+		return -1;
+
+	for (i = start + 1; i < end; i++) {
+		if (test_bit(i, bitmap) || ((u32)i & skip_mask)) {
+			start = i + 1;
+			goto again;
+		}
+	}
+
+	return start;
+}
+
+u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt,
+			    int align, u32 skip_mask)
 {
 	u32 obj;
 
-	if (likely(cnt == 1 && align == 1))
+	if (likely(cnt == 1 && align == 1 && !skip_mask))
 		return mlx4_bitmap_alloc(bitmap);
 
 	spin_lock(&bitmap->lock);
 
-	obj = bitmap_find_next_zero_area(bitmap->table, bitmap->max,
-				bitmap->last, cnt, align - 1);
+	obj = find_aligned_range(bitmap->table, bitmap->last,
+				 bitmap->max, cnt, align, skip_mask);
 	if (obj >= bitmap->max) {
 		bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
 				& bitmap->mask;
-		obj = bitmap_find_next_zero_area(bitmap->table, bitmap->max,
-						0, cnt, align - 1);
+		obj = find_aligned_range(bitmap->table, 0, bitmap->max,
+					 cnt, align, skip_mask);
 	}
 
 	if (obj < bitmap->max) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index dccf0e1f86b..c67effb05b2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -595,7 +595,7 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
 		return 0;
 	}
 
-	err = mlx4_qp_reserve_range(dev, 1, 1, qpn);
+	err = mlx4_qp_reserve_range(dev, 1, 1, qpn, 0);
 	en_dbg(DRV, priv, "Reserved qp %d\n", *qpn);
 	if (err) {
 		en_err(priv, "Failed to reserve qp for mac registration\n");
@@ -1974,15 +1974,8 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 {
 	struct mlx4_en_port_profile *prof = priv->prof;
 	int i;
-	int err;
 	int node;
 
-	err = mlx4_qp_reserve_range(priv->mdev->dev, priv->tx_ring_num, 256, &priv->base_tx_qpn);
-	if (err) {
-		en_err(priv, "failed reserving range for TX rings\n");
-		return err;
-	}
-
 	/* Create tx Rings */
 	for (i = 0; i < priv->tx_ring_num; i++) {
 		node = cpu_to_node(i % num_online_cpus());
@@ -1991,7 +1984,6 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 			goto err;
 
 		if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i],
-					   priv->base_tx_qpn + i,
 					   prof->tx_ring_size, TXBB_SIZE,
 					   node, i))
 			goto err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 69a2e1b88ea..a850f24fabd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -1131,7 +1131,7 @@ int mlx4_en_create_drop_qp(struct mlx4_en_priv *priv)
 	int err;
 	u32 qpn;
 
-	err = mlx4_qp_reserve_range(priv->mdev->dev, 1, 1, &qpn);
+	err = mlx4_qp_reserve_range(priv->mdev->dev, 1, 1, &qpn, 0);
 	if (err) {
 		en_err(priv, "Failed reserving drop qpn\n");
 		return err;
@@ -1174,7 +1174,7 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 	en_dbg(DRV, priv, "Configuring rss steering\n");
 	err = mlx4_qp_reserve_range(mdev->dev, priv->rx_ring_num,
 				    priv->rx_ring_num,
-				    &rss_map->base_qpn);
+				    &rss_map->base_qpn, 0);
 	if (err) {
 		en_err(priv, "Failed reserving %d qps\n", priv->rx_ring_num);
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index d0cecbdd9ba..a308d41e4de 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -46,7 +46,7 @@
 #include "mlx4_en.h"
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
-			   struct mlx4_en_tx_ring **pring, int qpn, u32 size,
+			   struct mlx4_en_tx_ring **pring, u32 size,
 			   u16 stride, int node, int queue_index)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
@@ -112,11 +112,17 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	       ring, ring->buf, ring->size, ring->buf_size,
 	       (unsigned long long) ring->wqres.buf.direct.map);
 
-	ring->qpn = qpn;
+	err = mlx4_qp_reserve_range(mdev->dev, 1, 1, &ring->qpn,
+				    MLX4_RESERVE_ETH_BF_QP);
+	if (err) {
+		en_err(priv, "failed reserving qp for TX ring\n");
+		goto err_map;
+	}
+
 	err = mlx4_qp_alloc(mdev->dev, ring->qpn, &ring->qp, GFP_KERNEL);
 	if (err) {
 		en_err(priv, "Failed allocating qp %d\n", ring->qpn);
-		goto err_map;
+		goto err_reserve;
 	}
 	ring->qp.event = mlx4_en_sqp_event;
 
@@ -143,6 +149,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	*pring = ring;
 	return 0;
 
+err_reserve:
+	mlx4_qp_release_range(mdev->dev, ring->qpn, 1);
 err_map:
 	mlx4_en_unmap_buffer(&ring->wqres.buf);
 err_hwq_res:
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 5089f76f060..1469b5b5be6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -266,10 +266,15 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 #define QUERY_FUNC_CAP_MTT_QUOTA_OFFSET		0x64
 #define QUERY_FUNC_CAP_MCG_QUOTA_OFFSET		0x68
 
+#define QUERY_FUNC_CAP_EXTRA_FLAGS_OFFSET	0x6c
+
 #define QUERY_FUNC_CAP_FMR_FLAG			0x80
 #define QUERY_FUNC_CAP_FLAG_RDMA		0x40
 #define QUERY_FUNC_CAP_FLAG_ETH			0x80
 #define QUERY_FUNC_CAP_FLAG_QUOTAS		0x10
+#define QUERY_FUNC_CAP_FLAG_VALID_MAILBOX	0x04
+
+#define QUERY_FUNC_CAP_EXTRA_FLAGS_BF_QP_ALLOC_FLAG	(1UL << 31)
 
 /* when opcode modifier = 1 */
 #define QUERY_FUNC_CAP_PHYS_PORT_OFFSET		0x3
@@ -339,7 +344,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 			mlx4_get_active_ports(dev, slave);
 		/* enable rdma and ethernet interfaces, and new quota locations */
 		field = (QUERY_FUNC_CAP_FLAG_ETH | QUERY_FUNC_CAP_FLAG_RDMA |
-			 QUERY_FUNC_CAP_FLAG_QUOTAS);
+			 QUERY_FUNC_CAP_FLAG_QUOTAS | QUERY_FUNC_CAP_FLAG_VALID_MAILBOX);
 		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS_OFFSET);
 
 		field = min(
@@ -401,6 +406,8 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET);
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET_DEP);
 
+		size = QUERY_FUNC_CAP_EXTRA_FLAGS_BF_QP_ALLOC_FLAG;
+		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_EXTRA_FLAGS_OFFSET);
 	} else
 		err = -EINVAL;
 
@@ -493,6 +500,17 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u8 gen_or_port,
 		MLX4_GET(size, outbox, QUERY_FUNC_CAP_RESERVED_EQ_OFFSET);
 		func_cap->reserved_eq = size & 0xFFFFFF;
 
+		func_cap->extra_flags = 0;
+
+		/* Mailbox data from 0x6c and onward should only be treated if
+		 * QUERY_FUNC_CAP_FLAG_VALID_MAILBOX is set in func_cap->flags
+		 */
+		if (func_cap->flags & QUERY_FUNC_CAP_FLAG_VALID_MAILBOX) {
+			MLX4_GET(size, outbox, QUERY_FUNC_CAP_EXTRA_FLAGS_OFFSET);
+			if (size & QUERY_FUNC_CAP_EXTRA_FLAGS_BF_QP_ALLOC_FLAG)
+				func_cap->extra_flags |= MLX4_QUERY_FUNC_FLAGS_BF_RES_QP;
+		}
+
 		goto out;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 475215ee370..0e910a452b0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -144,6 +144,7 @@ struct mlx4_func_cap {
 	u8	port_flags;
 	u8	flags1;
 	u64	phys_port_id;
+	u32	extra_flags;
 };
 
 struct mlx4_func {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 3044f9e623c..6a9a941ddf5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -466,8 +466,13 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	    mlx4_is_master(dev))
 		dev->caps.function_caps |= MLX4_FUNC_CAP_64B_EQE_CQE;
 
-	if (!mlx4_is_slave(dev))
+	if (!mlx4_is_slave(dev)) {
 		mlx4_enable_cqe_eqe_stride(dev);
+		dev->caps.alloc_res_qp_mask =
+			(dev->caps.bf_reg_size ? MLX4_RESERVE_ETH_BF_QP : 0);
+	} else {
+		dev->caps.alloc_res_qp_mask = 0;
+	}
 
 	return 0;
 }
@@ -817,6 +822,10 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 
 	slave_adjust_steering_mode(dev, &dev_cap, &hca_param);
 
+	if (func_cap.extra_flags & MLX4_QUERY_FUNC_FLAGS_BF_RES_QP &&
+	    dev->caps.bf_reg_size)
+		dev->caps.alloc_res_qp_mask |= MLX4_RESERVE_ETH_BF_QP;
+
 	return 0;
 
 err_mem:
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index b67ef488c30..6834da6c35e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -884,7 +884,8 @@ extern struct workqueue_struct *mlx4_wq;
 
 u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap);
 void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj, int use_rr);
-u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align);
+u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt,
+			    int align, u32 skip_mask);
 void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt,
 			    int use_rr);
 u32 mlx4_bitmap_avail(struct mlx4_bitmap *bitmap);
@@ -970,7 +971,7 @@ int mlx4_DMA_wrapper(struct mlx4_dev *dev, int slave,
 		     struct mlx4_cmd_mailbox *outbox,
 		     struct mlx4_cmd_info *cmd);
 int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
-			    int *base);
+			    int *base, u8 flags);
 void __mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
 int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac);
 void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index ac48a8d9150..944a112dff3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -778,7 +778,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_tx_ring **pring,
-			   int qpn, u32 size, u16 stride,
+			   u32 size, u16 stride,
 			   int node, int queue_index);
 void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_tx_ring **pring);
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 2301365c79c..40e82edac99 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -42,6 +42,10 @@
 #include "mlx4.h"
 #include "icm.h"
 
+/* QP to support BF should have bits 6,7 cleared */
+#define MLX4_BF_QP_SKIP_MASK	0xc0
+#define MLX4_MAX_BF_QP_RANGE	0x40
+
 void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type)
 {
 	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
@@ -207,26 +211,36 @@ int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 EXPORT_SYMBOL_GPL(mlx4_qp_modify);
 
 int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
-				   int *base)
+			    int *base, u8 flags)
 {
+	int bf_qp = !!(flags & (u8)MLX4_RESERVE_ETH_BF_QP);
+
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_qp_table *qp_table = &priv->qp_table;
 
-	*base = mlx4_bitmap_alloc_range(&qp_table->bitmap, cnt, align);
+	if (cnt > MLX4_MAX_BF_QP_RANGE && bf_qp)
+		return -ENOMEM;
+
+	*base = mlx4_bitmap_alloc_range(&qp_table->bitmap, cnt, align,
+					bf_qp ? MLX4_BF_QP_SKIP_MASK : 0);
 	if (*base == -1)
 		return -ENOMEM;
 
 	return 0;
 }
 
-int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base)
+int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
+			  int *base, u8 flags)
 {
 	u64 in_param = 0;
 	u64 out_param;
 	int err;
 
+	/* Turn off all unsupported QP allocation flags */
+	flags &= dev->caps.alloc_res_qp_mask;
+
 	if (mlx4_is_mfunc(dev)) {
-		set_param_l(&in_param, cnt);
+		set_param_l(&in_param, (((u32)flags) << 24) | (u32)cnt);
 		set_param_h(&in_param, align);
 		err = mlx4_cmd_imm(dev, in_param, &out_param,
 				   RES_QP, RES_OP_RESERVE,
@@ -238,7 +252,7 @@ int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base)
 		*base = get_param_l(&out_param);
 		return 0;
 	}
-	return __mlx4_qp_reserve_range(dev, cnt, align, base);
+	return __mlx4_qp_reserve_range(dev, cnt, align, base, flags);
 }
 EXPORT_SYMBOL_GPL(mlx4_qp_reserve_range);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 16f617b5749..4efbd1eca61 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -1543,16 +1543,21 @@ static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 	int align;
 	int base;
 	int qpn;
+	u8 flags;
 
 	switch (op) {
 	case RES_OP_RESERVE:
 		count = get_param_l(&in_param) & 0xffffff;
+		/* Turn off all unsupported QP allocation flags that the
+		 * slave tries to set.
+		 */
+		flags = (get_param_l(&in_param) >> 24) & dev->caps.alloc_res_qp_mask;
 		align = get_param_h(&in_param);
 		err = mlx4_grant_resource(dev, slave, RES_QP, count, 0);
 		if (err)
 			return err;
 
-		err = __mlx4_qp_reserve_range(dev, count, align, &base);
+		err = __mlx4_qp_reserve_range(dev, count, align, &base, flags);
 		if (err) {
 			mlx4_release_resource(dev, slave, RES_QP, count, 0);
 			return err;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 3951b5368d7..272aa258c03 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -194,6 +194,22 @@ enum {
 	MLX4_DEV_CAP_FLAG2_80_VFS		= 1LL <<  18
 };
 
+enum {
+	MLX4_QUERY_FUNC_FLAGS_BF_RES_QP		= 1LL << 0
+};
+
+/* bit enums for an 8-bit flags field indicating special use
+ * QPs which require special handling in qp_reserve_range.
+ * Currently, this only includes QPs used by the ETH interface,
+ * where we expect to use blueflame.  These QPs must not have
+ * bits 6 and 7 set in their qp number.
+ *
+ * This enum may use only bits 0..7.
+ */
+enum {
+	MLX4_RESERVE_ETH_BF_QP	= 1 << 7,
+};
+
 enum {
 	MLX4_DEV_CAP_64B_EQE_ENABLED	= 1LL << 0,
 	MLX4_DEV_CAP_64B_CQE_ENABLED	= 1LL << 1,
@@ -501,6 +517,7 @@ struct mlx4_caps {
 	u64			phys_port_id[MLX4_MAX_PORTS + 1];
 	int			tunnel_offload_mode;
 	u8			rx_checksum_flags_port[MLX4_MAX_PORTS + 1];
+	u8			alloc_res_qp_mask;
 };
 
 struct mlx4_buf_list {
@@ -950,8 +967,8 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 		  struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq,
 		  unsigned vector, int collapsed, int timestamp_en);
 void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq);
-
-int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base);
+int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
+			  int *base, u8 flags);
 void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
 
 int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp,
-- 
cgit v1.2.3-70-g09d2


From d57febe1a47801ef8a55dbf10672850523dfaa60 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 11 Dec 2014 10:57:57 +0200
Subject: net/mlx4: Add A0 hybrid steering

A0 hybrid steering is a form of high performance flow steering.
By using this mode, mlx4 cards use a fast limited table based steering,
in order to enable fast steering of unicast packets to a QP.

In order to implement A0 hybrid steering we allocate resources
from different zones:
(1) General range
(2) Special MAC-assigned QPs [RSS, Raw-Ethernet] each has its own region.

When we create a rss QP or a raw ethernet (A0 steerable and BF ready) QP,
we try hard to allocate the QP from range (2). Otherwise, we try hard not
to allocate from this  range. However, when the system is pushed to its
limits and one needs every resource, the allocator uses every region it can.

Meaning, when we run out of raw-eth qps, the allocator allocates from the
general range (and the special-A0 area is no longer active). If we run out
of RSS qps, the mechanism tries to allocate from the raw-eth QP zone. If that
is also exhausted, the allocator will allocate from the general range
(and the A0 region is no longer active).

Note that if a raw-eth qp is allocated from the general range, it attempts
to allocate the range such that bits 6 and 7 (blueflame bits) in the
QP number are not set.

When the feature is used in SRIOV, the VF has to notify the PF what
kind of QP attributes it needs. In order to do that, along with the
"Eth QP blueflame" bit, we reserve a new "A0 steerable QP". According
to the combination of these bits, the PF tries to allocate a suitable QP.

In order to maintain backward compatibility (with older PFs), the PF
notifies which QP attributes it supports via QUERY_FUNC_CAP command.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/qp.c                |   6 +-
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c |   2 +-
 drivers/net/ethernet/mellanox/mlx4/en_rx.c     |   3 +-
 drivers/net/ethernet/mellanox/mlx4/fw.c        |   6 +-
 drivers/net/ethernet/mellanox/mlx4/main.c      |   8 +-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h      |  13 +-
 drivers/net/ethernet/mellanox/mlx4/qp.c        | 277 +++++++++++++++++++++++--
 include/linux/mlx4/device.h                    |  10 +-
 8 files changed, 300 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 506d1bdad22..cf000b7ad64 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -807,8 +807,10 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 		 * VLAN insertion. */
 		if (init_attr->qp_type == IB_QPT_RAW_PACKET)
 			err = mlx4_qp_reserve_range(dev->dev, 1, 1, &qpn,
-						    init_attr->cap.max_send_wr ?
-						    MLX4_RESERVE_ETH_BF_QP : 0);
+						    (init_attr->cap.max_send_wr ?
+						     MLX4_RESERVE_ETH_BF_QP : 0) |
+						    (init_attr->cap.max_recv_wr ?
+						     MLX4_RESERVE_A0_QP : 0));
 		else
 			if (qp->flags & MLX4_IB_QP_NETIF)
 				err = mlx4_ib_steer_qp_alloc(dev, 1, &qpn);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index c67effb05b2..568e1f41fdd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -595,7 +595,7 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
 		return 0;
 	}
 
-	err = mlx4_qp_reserve_range(dev, 1, 1, qpn, 0);
+	err = mlx4_qp_reserve_range(dev, 1, 1, qpn, MLX4_RESERVE_A0_QP);
 	en_dbg(DRV, priv, "Reserved qp %d\n", *qpn);
 	if (err) {
 		en_err(priv, "Failed to reserve qp for mac registration\n");
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index a850f24fabd..a0474eb94aa 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -1131,7 +1131,8 @@ int mlx4_en_create_drop_qp(struct mlx4_en_priv *priv)
 	int err;
 	u32 qpn;
 
-	err = mlx4_qp_reserve_range(priv->mdev->dev, 1, 1, &qpn, 0);
+	err = mlx4_qp_reserve_range(priv->mdev->dev, 1, 1, &qpn,
+				    MLX4_RESERVE_A0_QP);
 	if (err) {
 		en_err(priv, "Failed reserving drop qpn\n");
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 1469b5b5be6..622bffaa9d7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -275,6 +275,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 #define QUERY_FUNC_CAP_FLAG_VALID_MAILBOX	0x04
 
 #define QUERY_FUNC_CAP_EXTRA_FLAGS_BF_QP_ALLOC_FLAG	(1UL << 31)
+#define QUERY_FUNC_CAP_EXTRA_FLAGS_A0_QP_ALLOC_FLAG	(1UL << 30)
 
 /* when opcode modifier = 1 */
 #define QUERY_FUNC_CAP_PHYS_PORT_OFFSET		0x3
@@ -406,7 +407,8 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET);
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET_DEP);
 
-		size = QUERY_FUNC_CAP_EXTRA_FLAGS_BF_QP_ALLOC_FLAG;
+		size = QUERY_FUNC_CAP_EXTRA_FLAGS_BF_QP_ALLOC_FLAG |
+			QUERY_FUNC_CAP_EXTRA_FLAGS_A0_QP_ALLOC_FLAG;
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_EXTRA_FLAGS_OFFSET);
 	} else
 		err = -EINVAL;
@@ -509,6 +511,8 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u8 gen_or_port,
 			MLX4_GET(size, outbox, QUERY_FUNC_CAP_EXTRA_FLAGS_OFFSET);
 			if (size & QUERY_FUNC_CAP_EXTRA_FLAGS_BF_QP_ALLOC_FLAG)
 				func_cap->extra_flags |= MLX4_QUERY_FUNC_FLAGS_BF_RES_QP;
+			if (size & QUERY_FUNC_CAP_EXTRA_FLAGS_A0_QP_ALLOC_FLAG)
+				func_cap->extra_flags |= MLX4_QUERY_FUNC_FLAGS_A0_RES_QP;
 		}
 
 		goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 6a9a941ddf5..3bfe90b95f9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -436,6 +436,8 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		(1 << dev->caps.log_num_vlans) *
 		dev->caps.num_ports;
 	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH] = MLX4_NUM_FEXCH;
+	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_RSS_RAW_ETH] =
+		MLX4_A0_STEERING_TABLE_SIZE;
 
 	dev->caps.reserved_qps = dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] +
 		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] +
@@ -469,7 +471,8 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	if (!mlx4_is_slave(dev)) {
 		mlx4_enable_cqe_eqe_stride(dev);
 		dev->caps.alloc_res_qp_mask =
-			(dev->caps.bf_reg_size ? MLX4_RESERVE_ETH_BF_QP : 0);
+			(dev->caps.bf_reg_size ? MLX4_RESERVE_ETH_BF_QP : 0) |
+			MLX4_RESERVE_A0_QP;
 	} else {
 		dev->caps.alloc_res_qp_mask = 0;
 	}
@@ -826,6 +829,9 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 	    dev->caps.bf_reg_size)
 		dev->caps.alloc_res_qp_mask |= MLX4_RESERVE_ETH_BF_QP;
 
+	if (func_cap.extra_flags & MLX4_QUERY_FUNC_FLAGS_A0_RES_QP)
+		dev->caps.alloc_res_qp_mask |= MLX4_RESERVE_A0_QP;
+
 	return 0;
 
 err_mem:
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index bc1505efa43..cebd1180702 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -682,8 +682,19 @@ struct mlx4_srq_table {
 	struct mlx4_icm_table	cmpt_table;
 };
 
+enum mlx4_qp_table_zones {
+	MLX4_QP_TABLE_ZONE_GENERAL,
+	MLX4_QP_TABLE_ZONE_RSS,
+	MLX4_QP_TABLE_ZONE_RAW_ETH,
+	MLX4_QP_TABLE_ZONE_NUM
+};
+
+#define MLX4_A0_STEERING_TABLE_SIZE    256
+
 struct mlx4_qp_table {
-	struct mlx4_bitmap	bitmap;
+	struct mlx4_bitmap	*bitmap_gen;
+	struct mlx4_zone_allocator *zones;
+	u32			zones_uids[MLX4_QP_TABLE_ZONE_NUM];
 	u32			rdmarc_base;
 	int			rdmarc_shift;
 	spinlock_t		lock;
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 8720428c980..d8d040c366f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -213,6 +213,7 @@ EXPORT_SYMBOL_GPL(mlx4_qp_modify);
 int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
 			    int *base, u8 flags)
 {
+	u32 uid;
 	int bf_qp = !!(flags & (u8)MLX4_RESERVE_ETH_BF_QP);
 
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -221,8 +222,16 @@ int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
 	if (cnt > MLX4_MAX_BF_QP_RANGE && bf_qp)
 		return -ENOMEM;
 
-	*base = mlx4_bitmap_alloc_range(&qp_table->bitmap, cnt, align,
-					bf_qp ? MLX4_BF_QP_SKIP_MASK : 0);
+	uid = MLX4_QP_TABLE_ZONE_GENERAL;
+	if (flags & (u8)MLX4_RESERVE_A0_QP) {
+		if (bf_qp)
+			uid = MLX4_QP_TABLE_ZONE_RAW_ETH;
+		else
+			uid = MLX4_QP_TABLE_ZONE_RSS;
+	}
+
+	*base = mlx4_zone_alloc_entries(qp_table->zones, uid, cnt, align,
+					bf_qp ? MLX4_BF_QP_SKIP_MASK : 0, NULL);
 	if (*base == -1)
 		return -ENOMEM;
 
@@ -263,7 +272,7 @@ void __mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
 
 	if (mlx4_is_qp_reserved(dev, (u32) base_qpn))
 		return;
-	mlx4_bitmap_free_range(&qp_table->bitmap, base_qpn, cnt, MLX4_USE_RR);
+	mlx4_zone_free_entries_unique(qp_table->zones, base_qpn, cnt);
 }
 
 void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
@@ -473,6 +482,227 @@ static int mlx4_CONF_SPECIAL_QP(struct mlx4_dev *dev, u32 base_qpn)
 			MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
 }
 
+#define MLX4_QP_TABLE_RSS_ETH_PRIORITY 2
+#define MLX4_QP_TABLE_RAW_ETH_PRIORITY 1
+#define MLX4_QP_TABLE_RAW_ETH_SIZE     256
+
+static int mlx4_create_zones(struct mlx4_dev *dev,
+			     u32 reserved_bottom_general,
+			     u32 reserved_top_general,
+			     u32 reserved_bottom_rss,
+			     u32 start_offset_rss,
+			     u32 max_table_offset)
+{
+	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
+	struct mlx4_bitmap (*bitmap)[MLX4_QP_TABLE_ZONE_NUM] = NULL;
+	int bitmap_initialized = 0;
+	u32 last_offset;
+	int k;
+	int err;
+
+	qp_table->zones = mlx4_zone_allocator_create(MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP);
+
+	if (NULL == qp_table->zones)
+		return -ENOMEM;
+
+	bitmap = kmalloc(sizeof(*bitmap), GFP_KERNEL);
+
+	if (NULL == bitmap) {
+		err = -ENOMEM;
+		goto free_zone;
+	}
+
+	err = mlx4_bitmap_init(*bitmap + MLX4_QP_TABLE_ZONE_GENERAL, dev->caps.num_qps,
+			       (1 << 23) - 1, reserved_bottom_general,
+			       reserved_top_general);
+
+	if (err)
+		goto free_bitmap;
+
+	++bitmap_initialized;
+
+	err = mlx4_zone_add_one(qp_table->zones, *bitmap + MLX4_QP_TABLE_ZONE_GENERAL,
+				MLX4_ZONE_FALLBACK_TO_HIGHER_PRIO |
+				MLX4_ZONE_USE_RR, 0,
+				0, qp_table->zones_uids + MLX4_QP_TABLE_ZONE_GENERAL);
+
+	if (err)
+		goto free_bitmap;
+
+	err = mlx4_bitmap_init(*bitmap + MLX4_QP_TABLE_ZONE_RSS,
+			       reserved_bottom_rss,
+			       reserved_bottom_rss - 1,
+			       dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
+			       reserved_bottom_rss - start_offset_rss);
+
+	if (err)
+		goto free_bitmap;
+
+	++bitmap_initialized;
+
+	err = mlx4_zone_add_one(qp_table->zones, *bitmap + MLX4_QP_TABLE_ZONE_RSS,
+				MLX4_ZONE_ALLOW_ALLOC_FROM_LOWER_PRIO |
+				MLX4_ZONE_ALLOW_ALLOC_FROM_EQ_PRIO |
+				MLX4_ZONE_USE_RR, MLX4_QP_TABLE_RSS_ETH_PRIORITY,
+				0, qp_table->zones_uids + MLX4_QP_TABLE_ZONE_RSS);
+
+	if (err)
+		goto free_bitmap;
+
+	last_offset = dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];
+	/*  We have a single zone for the A0 steering QPs area of the FW. This area
+	 *  needs to be split into subareas. One set of subareas is for RSS QPs
+	 *  (in which qp number bits 6 and/or 7 are set); the other set of subareas
+	 *  is for RAW_ETH QPs, which require that both bits 6 and 7 are zero.
+	 *  Currently, the values returned by the FW (A0 steering area starting qp number
+	 *  and A0 steering area size) are such that there are only two subareas -- one
+	 *  for RSS and one for RAW_ETH.
+	 */
+	for (k = MLX4_QP_TABLE_ZONE_RSS + 1; k < sizeof(*bitmap)/sizeof((*bitmap)[0]);
+	     k++) {
+		int size;
+		u32 offset = start_offset_rss;
+		u32 bf_mask;
+		u32 requested_size;
+
+		/* Assuming MLX4_BF_QP_SKIP_MASK is consecutive ones, this calculates
+		 * a mask of all LSB bits set until (and not including) the first
+		 * set bit of  MLX4_BF_QP_SKIP_MASK. For example, if MLX4_BF_QP_SKIP_MASK
+		 * is 0xc0, bf_mask will be 0x3f.
+		 */
+		bf_mask = (MLX4_BF_QP_SKIP_MASK & ~(MLX4_BF_QP_SKIP_MASK - 1)) - 1;
+		requested_size = min((u32)MLX4_QP_TABLE_RAW_ETH_SIZE, bf_mask + 1);
+
+		if (((last_offset & MLX4_BF_QP_SKIP_MASK) &&
+		     ((int)(max_table_offset - last_offset)) >=
+		     roundup_pow_of_two(MLX4_BF_QP_SKIP_MASK)) ||
+		    (!(last_offset & MLX4_BF_QP_SKIP_MASK) &&
+		     !((last_offset + requested_size - 1) &
+		       MLX4_BF_QP_SKIP_MASK)))
+			size = requested_size;
+		else {
+			u32 candidate_offset =
+				(last_offset | MLX4_BF_QP_SKIP_MASK | bf_mask) + 1;
+
+			if (last_offset & MLX4_BF_QP_SKIP_MASK)
+				last_offset = candidate_offset;
+
+			/* From this point, the BF bits are 0 */
+
+			if (last_offset > max_table_offset) {
+				/* need to skip */
+				size = -1;
+			} else {
+				size = min3(max_table_offset - last_offset,
+					    bf_mask - (last_offset & bf_mask),
+					    requested_size);
+				if (size < requested_size) {
+					int candidate_size;
+
+					candidate_size = min3(
+						max_table_offset - candidate_offset,
+						bf_mask - (last_offset & bf_mask),
+						requested_size);
+
+					/*  We will not take this path if last_offset was
+					 *  already set above to candidate_offset
+					 */
+					if (candidate_size > size) {
+						last_offset = candidate_offset;
+						size = candidate_size;
+					}
+				}
+			}
+		}
+
+		if (size > 0) {
+			/* mlx4_bitmap_alloc_range will find a contiguous range of "size"
+			 * QPs in which both bits 6 and 7 are zero, because we pass it the
+			 * MLX4_BF_SKIP_MASK).
+			 */
+			offset = mlx4_bitmap_alloc_range(
+					*bitmap + MLX4_QP_TABLE_ZONE_RSS,
+					size, 1,
+					MLX4_BF_QP_SKIP_MASK);
+
+			if (offset == (u32)-1) {
+				err = -ENOMEM;
+				break;
+			}
+
+			last_offset = offset + size;
+
+			err = mlx4_bitmap_init(*bitmap + k, roundup_pow_of_two(size),
+					       roundup_pow_of_two(size) - 1, 0,
+					       roundup_pow_of_two(size) - size);
+		} else {
+			/* Add an empty bitmap, we'll allocate from different zones (since
+			 * at least one is reserved)
+			 */
+			err = mlx4_bitmap_init(*bitmap + k, 1,
+					       MLX4_QP_TABLE_RAW_ETH_SIZE - 1, 0,
+					       0);
+			mlx4_bitmap_alloc_range(*bitmap + k, 1, 1, 0);
+		}
+
+		if (err)
+			break;
+
+		++bitmap_initialized;
+
+		err = mlx4_zone_add_one(qp_table->zones, *bitmap + k,
+					MLX4_ZONE_ALLOW_ALLOC_FROM_LOWER_PRIO |
+					MLX4_ZONE_ALLOW_ALLOC_FROM_EQ_PRIO |
+					MLX4_ZONE_USE_RR, MLX4_QP_TABLE_RAW_ETH_PRIORITY,
+					offset, qp_table->zones_uids + k);
+
+		if (err)
+			break;
+	}
+
+	if (err)
+		goto free_bitmap;
+
+	qp_table->bitmap_gen = *bitmap;
+
+	return err;
+
+free_bitmap:
+	for (k = 0; k < bitmap_initialized; k++)
+		mlx4_bitmap_cleanup(*bitmap + k);
+	kfree(bitmap);
+free_zone:
+	mlx4_zone_allocator_destroy(qp_table->zones);
+	return err;
+}
+
+static void mlx4_cleanup_qp_zones(struct mlx4_dev *dev)
+{
+	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
+
+	if (qp_table->zones) {
+		int i;
+
+		for (i = 0;
+		     i < sizeof(qp_table->zones_uids)/sizeof(qp_table->zones_uids[0]);
+		     i++) {
+			struct mlx4_bitmap *bitmap =
+				mlx4_zone_get_bitmap(qp_table->zones,
+						     qp_table->zones_uids[i]);
+
+			mlx4_zone_remove_one(qp_table->zones, qp_table->zones_uids[i]);
+			if (NULL == bitmap)
+				continue;
+
+			mlx4_bitmap_cleanup(bitmap);
+		}
+		mlx4_zone_allocator_destroy(qp_table->zones);
+		kfree(qp_table->bitmap_gen);
+		qp_table->bitmap_gen = NULL;
+		qp_table->zones = NULL;
+	}
+}
+
 int mlx4_init_qp_table(struct mlx4_dev *dev)
 {
 	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
@@ -480,22 +710,33 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 	int reserved_from_top = 0;
 	int reserved_from_bot;
 	int k;
+	int fixed_reserved_from_bot_rv = 0;
+	int bottom_reserved_for_rss_bitmap;
+	u32 max_table_offset = dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] +
+		MLX4_A0_STEERING_TABLE_SIZE;
 
 	spin_lock_init(&qp_table->lock);
 	INIT_RADIX_TREE(&dev->qp_table_tree, GFP_ATOMIC);
 	if (mlx4_is_slave(dev))
 		return 0;
 
-	/*
-	 * We reserve 2 extra QPs per port for the special QPs.  The
+	/* We reserve 2 extra QPs per port for the special QPs.  The
 	 * block of special QPs must be aligned to a multiple of 8, so
 	 * round up.
 	 *
 	 * We also reserve the MSB of the 24-bit QP number to indicate
 	 * that a QP is an XRC QP.
 	 */
-	dev->phys_caps.base_sqpn =
-		ALIGN(dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW], 8);
+	for (k = 0; k <= MLX4_QP_REGION_BOTTOM; k++)
+		fixed_reserved_from_bot_rv += dev->caps.reserved_qps_cnt[k];
+
+	if (fixed_reserved_from_bot_rv < max_table_offset)
+		fixed_reserved_from_bot_rv = max_table_offset;
+
+	/* We reserve at least 1 extra for bitmaps that we don't have enough space for*/
+	bottom_reserved_for_rss_bitmap =
+		roundup_pow_of_two(fixed_reserved_from_bot_rv + 1);
+	dev->phys_caps.base_sqpn = ALIGN(bottom_reserved_for_rss_bitmap, 8);
 
 	{
 		int sort[MLX4_NUM_QP_REGION];
@@ -505,8 +746,8 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 		for (i = 1; i < MLX4_NUM_QP_REGION; ++i)
 			sort[i] = i;
 
-		for (i = MLX4_NUM_QP_REGION; i > 0; --i) {
-			for (j = 2; j < i; ++j) {
+		for (i = MLX4_NUM_QP_REGION; i > MLX4_QP_REGION_BOTTOM; --i) {
+			for (j = MLX4_QP_REGION_BOTTOM + 2; j < i; ++j) {
 				if (dev->caps.reserved_qps_cnt[sort[j]] >
 				    dev->caps.reserved_qps_cnt[sort[j - 1]]) {
 					tmp             = sort[j];
@@ -516,13 +757,12 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 			}
 		}
 
-		for (i = 1; i < MLX4_NUM_QP_REGION; ++i) {
+		for (i = MLX4_QP_REGION_BOTTOM + 1; i < MLX4_NUM_QP_REGION; ++i) {
 			last_base -= dev->caps.reserved_qps_cnt[sort[i]];
 			dev->caps.reserved_qps_base[sort[i]] = last_base;
 			reserved_from_top +=
 				dev->caps.reserved_qps_cnt[sort[i]];
 		}
-
 	}
 
        /* Reserve 8 real SQPs in both native and SRIOV modes.
@@ -541,9 +781,11 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 		return -EINVAL;
 	}
 
-	err = mlx4_bitmap_init(&qp_table->bitmap, dev->caps.num_qps,
-			       (1 << 23) - 1, reserved_from_bot,
-			       reserved_from_top);
+	err = mlx4_create_zones(dev, reserved_from_bot, reserved_from_bot,
+				bottom_reserved_for_rss_bitmap,
+				fixed_reserved_from_bot_rv,
+				max_table_offset);
+
 	if (err)
 		return err;
 
@@ -579,7 +821,8 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 	err = mlx4_CONF_SPECIAL_QP(dev, dev->phys_caps.base_sqpn);
 	if (err)
 		goto err_mem;
-	return 0;
+
+	return err;
 
 err_mem:
 	kfree(dev->caps.qp0_tunnel);
@@ -588,6 +831,7 @@ err_mem:
 	kfree(dev->caps.qp1_proxy);
 	dev->caps.qp0_tunnel = dev->caps.qp0_proxy =
 		dev->caps.qp1_tunnel = dev->caps.qp1_proxy = NULL;
+	mlx4_cleanup_qp_zones(dev);
 	return err;
 }
 
@@ -597,7 +841,8 @@ void mlx4_cleanup_qp_table(struct mlx4_dev *dev)
 		return;
 
 	mlx4_CONF_SPECIAL_QP(dev, 0);
-	mlx4_bitmap_cleanup(&mlx4_priv(dev)->qp_table.bitmap);
+
+	mlx4_cleanup_qp_zones(dev);
 }
 
 int mlx4_qp_query(struct mlx4_dev *dev, struct mlx4_qp *qp,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 272aa258c03..39890cddc5f 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -195,7 +195,8 @@ enum {
 };
 
 enum {
-	MLX4_QUERY_FUNC_FLAGS_BF_RES_QP		= 1LL << 0
+	MLX4_QUERY_FUNC_FLAGS_BF_RES_QP		= 1LL << 0,
+	MLX4_QUERY_FUNC_FLAGS_A0_RES_QP		= 1LL << 1
 };
 
 /* bit enums for an 8-bit flags field indicating special use
@@ -207,6 +208,7 @@ enum {
  * This enum may use only bits 0..7.
  */
 enum {
+	MLX4_RESERVE_A0_QP	= 1 << 6,
 	MLX4_RESERVE_ETH_BF_QP	= 1 << 7,
 };
 
@@ -349,6 +351,8 @@ enum {
 
 enum mlx4_qp_region {
 	MLX4_QP_REGION_FW = 0,
+	MLX4_QP_REGION_RSS_RAW_ETH,
+	MLX4_QP_REGION_BOTTOM = MLX4_QP_REGION_RSS_RAW_ETH,
 	MLX4_QP_REGION_ETH_ADDR,
 	MLX4_QP_REGION_FC_ADDR,
 	MLX4_QP_REGION_FC_EXCH,
@@ -891,7 +895,9 @@ static inline int mlx4_num_reserved_sqps(struct mlx4_dev *dev)
 static inline int mlx4_is_qp_reserved(struct mlx4_dev *dev, u32 qpn)
 {
 	return (qpn < dev->phys_caps.base_sqpn + 8 +
-		16 * MLX4_MFUNC_MAX * !!mlx4_is_master(dev));
+		16 * MLX4_MFUNC_MAX * !!mlx4_is_master(dev) &&
+		qpn >= dev->phys_caps.base_sqpn) ||
+	       (qpn < dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW]);
 }
 
 static inline int mlx4_is_guest_proxy(struct mlx4_dev *dev, int slave, u32 qpn)
-- 
cgit v1.2.3-70-g09d2


From 7d077cd34eabb2ffd05abe0f2cad01da1ef11712 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 11 Dec 2014 10:58:00 +0200
Subject: net/mlx4: Add support for A0 steering

Add the required firmware commands for A0 steering and a way to enable
that. The firmware support focuses on INIT_HCA, QUERY_HCA, QUERY_PORT,
QUERY_DEV_CAP and QUERY_FUNC_CAP commands. Those commands are used
to configure and query the device.

The different A0 DMFS (steering) modes are:

Static - optimized performance, but flow steering rules are
limited. This mode should be choosed explicitly by the user
in order to be used.

Dynamic - this mode should be explicitly choosed by the user.
In this mode, the FW works in optimized steering mode as long as
it can and afterwards automatically drops to classic (full) DMFS.

Disable - this mode should be explicitly choosed by the user.
The user instructs the system not to use optimized steering, even if
the FW supports Dynamic A0 DMFS (and thus will be able to use optimized
steering in Default A0 DMFS mode).

Default - this mode is implicitly choosed. In this mode, if the FW
supports Dynamic A0 DMFS, it'll work in this mode. Otherwise, it'll
work at Disable A0 DMFS mode.

Under SRIOV configuration, when the A0 steering mode is enabled,
older guest VF drivers who aren't using the RX QP allocation flag
(MLX4_RESERVE_A0_QP) will get a QP from the general range and
fail when attempting to register a steering rule. To avoid that,
the PF context behaviour is changed once on A0 static mode, to
require support for the allocation flag in VF drivers too.

In order to enable A0 steering, we use log_num_mgm_entry_size param.
If the value of the parameter is not positive, we treat the absolute
value of log_num_mgm_entry_size as a bit field. Setting bit 2 of this
bit field enables static A0 steering.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c |   3 +-
 drivers/net/ethernet/mellanox/mlx4/fw.c        |  48 ++++++++-
 drivers/net/ethernet/mellanox/mlx4/fw.h        |   4 +
 drivers/net/ethernet/mellanox/mlx4/main.c      | 132 +++++++++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx4/mlx4.h      |   2 -
 drivers/net/ethernet/mellanox/mlx4/qp.c        |   4 +-
 include/linux/mlx4/device.h                    |  17 +++-
 7 files changed, 191 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 568e1f41fdd..6ff214de111 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2594,7 +2594,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
 
 	if (mdev->dev->caps.steering_mode ==
-	    MLX4_STEERING_MODE_DEVICE_MANAGED)
+	    MLX4_STEERING_MODE_DEVICE_MANAGED &&
+	    mdev->dev->caps.dmfs_high_steer_mode != MLX4_STEERING_DMFS_A0_STATIC)
 		dev->hw_features |= NETIF_F_NTUPLE;
 
 	if (mdev->dev->caps.steering_mode != MLX4_STEERING_MODE_A0)
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 073b3d1c8b9..ef3b95bac2a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -144,7 +144,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[15] = "Ethernet Backplane autoneg support",
 		[16] = "CONFIG DEV support",
 		[17] = "Asymmetric EQs support",
-		[18] = "More than 80 VFs support"
+		[18] = "More than 80 VFs support",
+		[19] = "Performance optimized for limited rule configuration flow steering support"
 	};
 	int i;
 
@@ -680,6 +681,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_FW_REASSIGN_MAC		0x9d
 #define QUERY_DEV_CAP_VXLAN			0x9e
 #define QUERY_DEV_CAP_MAD_DEMUX_OFFSET		0xb0
+#define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET	0xa8
+#define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET	0xac
 
 	dev_cap->flags2 = 0;
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
@@ -876,6 +879,13 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	if (field32 & (1 << 0))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_MAD_DEMUX;
 
+	MLX4_GET(dev_cap->dmfs_high_rate_qpn_base, outbox,
+		 QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET);
+	dev_cap->dmfs_high_rate_qpn_base &= MGM_QPN_MASK;
+	MLX4_GET(dev_cap->dmfs_high_rate_qpn_range, outbox,
+		 QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET);
+	dev_cap->dmfs_high_rate_qpn_range &= MGM_QPN_MASK;
+
 	MLX4_GET(field32, outbox, QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET);
 	if (field32 & (1 << 16))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_UPDATE_QP;
@@ -935,6 +945,10 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	mlx4_dbg(dev, "Max GSO size: %d\n", dev_cap->max_gso_sz);
 	mlx4_dbg(dev, "Max counters: %d\n", dev_cap->max_counters);
 	mlx4_dbg(dev, "Max RSS Table size: %d\n", dev_cap->max_rss_tbl_sz);
+	mlx4_dbg(dev, "DMFS high rate steer QPn base: %d\n",
+		 dev_cap->dmfs_high_rate_qpn_base);
+	mlx4_dbg(dev, "DMFS high rate steer QPn range: %d\n",
+		 dev_cap->dmfs_high_rate_qpn_range);
 
 	dump_dev_cap_flags(dev, dev_cap->flags);
 	dump_dev_cap_flags2(dev, dev_cap->flags2);
@@ -996,6 +1010,7 @@ int mlx4_QUERY_PORT(struct mlx4_dev *dev, int port, struct mlx4_port_cap *port_c
 		port_cap->supported_port_types = field & 3;
 		port_cap->suggested_type = (field >> 3) & 1;
 		port_cap->default_sense = (field >> 4) & 1;
+		port_cap->dmfs_optimized_state = (field >> 5) & 1;
 		MLX4_GET(field, outbox, QUERY_PORT_MTU_OFFSET);
 		port_cap->ib_mtu	   = field & 0xf;
 		MLX4_GET(field, outbox, QUERY_PORT_WIDTH_OFFSET);
@@ -1530,6 +1545,12 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 	struct mlx4_cmd_mailbox *mailbox;
 	__be32 *inbox;
 	int err;
+	static const u8 a0_dmfs_hw_steering[] =  {
+		[MLX4_STEERING_DMFS_A0_DEFAULT]		= 0,
+		[MLX4_STEERING_DMFS_A0_DYNAMIC]		= 1,
+		[MLX4_STEERING_DMFS_A0_STATIC]		= 2,
+		[MLX4_STEERING_DMFS_A0_DISABLE]		= 3
+	};
 
 #define INIT_HCA_IN_SIZE		 0x200
 #define INIT_HCA_VERSION_OFFSET		 0x000
@@ -1563,6 +1584,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 #define  INIT_HCA_FS_PARAM_OFFSET         0x1d0
 #define  INIT_HCA_FS_BASE_OFFSET          (INIT_HCA_FS_PARAM_OFFSET + 0x00)
 #define  INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET  (INIT_HCA_FS_PARAM_OFFSET + 0x12)
+#define  INIT_HCA_FS_A0_OFFSET		  (INIT_HCA_FS_PARAM_OFFSET + 0x18)
 #define  INIT_HCA_FS_LOG_TABLE_SZ_OFFSET  (INIT_HCA_FS_PARAM_OFFSET + 0x1b)
 #define  INIT_HCA_FS_ETH_BITS_OFFSET      (INIT_HCA_FS_PARAM_OFFSET + 0x21)
 #define  INIT_HCA_FS_ETH_NUM_ADDRS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x22)
@@ -1673,8 +1695,11 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 		/* Enable Ethernet flow steering
 		 * with udp unicast and tcp unicast
 		 */
-		MLX4_PUT(inbox, (u8) (MLX4_FS_UDP_UC_EN | MLX4_FS_TCP_UC_EN),
-			 INIT_HCA_FS_ETH_BITS_OFFSET);
+		if (dev->caps.dmfs_high_steer_mode !=
+		    MLX4_STEERING_DMFS_A0_STATIC)
+			MLX4_PUT(inbox,
+				 (u8)(MLX4_FS_UDP_UC_EN | MLX4_FS_TCP_UC_EN),
+				 INIT_HCA_FS_ETH_BITS_OFFSET);
 		MLX4_PUT(inbox, (u16) MLX4_FS_NUM_OF_L2_ADDR,
 			 INIT_HCA_FS_ETH_NUM_ADDRS_OFFSET);
 		/* Enable IPoIB flow steering
@@ -1684,6 +1709,13 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 			 INIT_HCA_FS_IB_BITS_OFFSET);
 		MLX4_PUT(inbox, (u16) MLX4_FS_NUM_OF_L2_ADDR,
 			 INIT_HCA_FS_IB_NUM_ADDRS_OFFSET);
+
+		if (dev->caps.dmfs_high_steer_mode !=
+		    MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
+			MLX4_PUT(inbox,
+				 ((u8)(a0_dmfs_hw_steering[dev->caps.dmfs_high_steer_mode]
+				       << 6)),
+				 INIT_HCA_FS_A0_OFFSET);
 	} else {
 		MLX4_PUT(inbox, param->mc_base,	INIT_HCA_MC_BASE_OFFSET);
 		MLX4_PUT(inbox, param->log_mc_entry_sz,
@@ -1734,6 +1766,12 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	u32 dword_field;
 	int err;
 	u8 byte_field;
+	static const u8 a0_dmfs_query_hw_steering[] =  {
+		[0] = MLX4_STEERING_DMFS_A0_DEFAULT,
+		[1] = MLX4_STEERING_DMFS_A0_DYNAMIC,
+		[2] = MLX4_STEERING_DMFS_A0_STATIC,
+		[3] = MLX4_STEERING_DMFS_A0_DISABLE
+	};
 
 #define QUERY_HCA_GLOBAL_CAPS_OFFSET	0x04
 #define QUERY_HCA_CORE_CLOCK_OFFSET	0x0c
@@ -1786,6 +1824,10 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 			 INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
 		MLX4_GET(param->log_mc_table_sz, outbox,
 			 INIT_HCA_FS_LOG_TABLE_SZ_OFFSET);
+		MLX4_GET(byte_field, outbox,
+			 INIT_HCA_FS_A0_OFFSET);
+		param->dmfs_high_steer_mode =
+			a0_dmfs_query_hw_steering[(byte_field >> 6) & 3];
 	} else {
 		MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET);
 		MLX4_GET(param->log_mc_entry_sz, outbox,
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 744398b7ab5..794e2826609 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -60,6 +60,7 @@ struct mlx4_port_cap {
 	int vendor_oui;
 	u16 wavelength;
 	u64 trans_code;
+	u8 dmfs_optimized_state;
 };
 
 struct mlx4_dev_cap {
@@ -124,6 +125,8 @@ struct mlx4_dev_cap {
 	int max_gso_sz;
 	int max_rss_tbl_sz;
 	u32 max_counters;
+	u32 dmfs_high_rate_qpn_base;
+	u32 dmfs_high_rate_qpn_range;
 	struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1];
 };
 
@@ -194,6 +197,7 @@ struct mlx4_init_hca_param {
 	u8  mw_enabled;  /* Enable memory windows */
 	u8  uar_page_sz; /* log pg sz in 4k chunks */
 	u8  steering_mode; /* for QUERY_HCA */
+	u8  dmfs_high_steer_mode; /* for QUERY_HCA */
 	u64 dev_cap_enabled;
 	u16 cqe_size; /* For use only when CQE stride feature enabled */
 	u16 eqe_size; /* For use only when EQE stride feature enabled */
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 6173b807298..e25436b24ce 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -105,7 +105,8 @@ MODULE_PARM_DESC(enable_64b_cqe_eqe,
 		 "Enable 64 byte CQEs/EQEs when the FW supports this (default: True)");
 
 #define PF_CONTEXT_BEHAVIOUR_MASK	(MLX4_FUNC_CAP_64B_EQE_CQE | \
-					 MLX4_FUNC_CAP_EQE_CQE_STRIDE)
+					 MLX4_FUNC_CAP_EQE_CQE_STRIDE | \
+					 MLX4_FUNC_CAP_DMFS_A0_STATIC)
 
 static char mlx4_version[] =
 	DRV_NAME ": Mellanox ConnectX core driver v"
@@ -463,8 +464,28 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		(1 << dev->caps.log_num_vlans) *
 		dev->caps.num_ports;
 	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH] = MLX4_NUM_FEXCH;
+
+	if (dev_cap->dmfs_high_rate_qpn_base > 0 &&
+	    dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FS_EN)
+		dev->caps.dmfs_high_rate_qpn_base = dev_cap->dmfs_high_rate_qpn_base;
+	else
+		dev->caps.dmfs_high_rate_qpn_base =
+			dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];
+
+	if (dev_cap->dmfs_high_rate_qpn_range > 0 &&
+	    dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FS_EN) {
+		dev->caps.dmfs_high_rate_qpn_range = dev_cap->dmfs_high_rate_qpn_range;
+		dev->caps.dmfs_high_steer_mode = MLX4_STEERING_DMFS_A0_DEFAULT;
+		dev->caps.flags2 |= MLX4_DEV_CAP_FLAG2_FS_A0;
+	} else {
+		dev->caps.dmfs_high_steer_mode = MLX4_STEERING_DMFS_A0_NOT_SUPPORTED;
+		dev->caps.dmfs_high_rate_qpn_base =
+			dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];
+		dev->caps.dmfs_high_rate_qpn_range = MLX4_A0_STEERING_TABLE_SIZE;
+	}
+
 	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_RSS_RAW_ETH] =
-		MLX4_A0_STEERING_TABLE_SIZE;
+		dev->caps.dmfs_high_rate_qpn_range;
 
 	dev->caps.reserved_qps = dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] +
 		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] +
@@ -753,7 +774,8 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 
 	if ((func_cap.pf_context_behaviour | PF_CONTEXT_BEHAVIOUR_MASK) !=
 	    PF_CONTEXT_BEHAVIOUR_MASK) {
-		mlx4_err(dev, "Unknown pf context behaviour\n");
+		mlx4_err(dev, "Unknown pf context behaviour %x known flags %x\n",
+			 func_cap.pf_context_behaviour, PF_CONTEXT_BEHAVIOUR_MASK);
 		return -ENOSYS;
 	}
 
@@ -1640,10 +1662,46 @@ static int choose_log_fs_mgm_entry_size(int qp_per_entry)
 	return (i <= MLX4_MAX_MGM_LOG_ENTRY_SIZE) ? i : -1;
 }
 
+static const char *dmfs_high_rate_steering_mode_str(int dmfs_high_steer_mode)
+{
+	switch (dmfs_high_steer_mode) {
+	case MLX4_STEERING_DMFS_A0_DEFAULT:
+		return "default performance";
+
+	case MLX4_STEERING_DMFS_A0_DYNAMIC:
+		return "dynamic hybrid mode";
+
+	case MLX4_STEERING_DMFS_A0_STATIC:
+		return "performance optimized for limited rule configuration (static)";
+
+	case MLX4_STEERING_DMFS_A0_DISABLE:
+		return "disabled performance optimized steering";
+
+	case MLX4_STEERING_DMFS_A0_NOT_SUPPORTED:
+		return "performance optimized steering not supported";
+
+	default:
+		return "Unrecognized mode";
+	}
+}
+
+#define MLX4_DMFS_A0_STEERING			(1UL << 2)
+
 static void choose_steering_mode(struct mlx4_dev *dev,
 				 struct mlx4_dev_cap *dev_cap)
 {
-	if (mlx4_log_num_mgm_entry_size == -1 &&
+	if (mlx4_log_num_mgm_entry_size <= 0) {
+		if ((-mlx4_log_num_mgm_entry_size) & MLX4_DMFS_A0_STEERING) {
+			if (dev->caps.dmfs_high_steer_mode ==
+			    MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
+				mlx4_err(dev, "DMFS high rate mode not supported\n");
+			else
+				dev->caps.dmfs_high_steer_mode =
+					MLX4_STEERING_DMFS_A0_STATIC;
+		}
+	}
+
+	if (mlx4_log_num_mgm_entry_size <= 0 &&
 	    dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN &&
 	    (!mlx4_is_mfunc(dev) ||
 	     (dev_cap->fs_max_num_qp_per_entry >= (dev->num_vfs + 1))) &&
@@ -1656,6 +1714,9 @@ static void choose_steering_mode(struct mlx4_dev *dev,
 		dev->caps.fs_log_max_ucast_qp_range_size =
 			dev_cap->fs_log_max_ucast_qp_range_size;
 	} else {
+		if (dev->caps.dmfs_high_steer_mode !=
+		    MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
+			dev->caps.dmfs_high_steer_mode = MLX4_STEERING_DMFS_A0_DISABLE;
 		if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
 		    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
 			dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
@@ -1682,7 +1743,8 @@ static void choose_tunnel_offload_mode(struct mlx4_dev *dev,
 				       struct mlx4_dev_cap *dev_cap)
 {
 	if (dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED &&
-	    dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS)
+	    dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS &&
+	    dev->caps.dmfs_high_steer_mode != MLX4_STEERING_DMFS_A0_STATIC)
 		dev->caps.tunnel_offload_mode = MLX4_TUNNEL_OFFLOAD_MODE_VXLAN;
 	else
 		dev->caps.tunnel_offload_mode = MLX4_TUNNEL_OFFLOAD_MODE_NONE;
@@ -1691,6 +1753,35 @@ static void choose_tunnel_offload_mode(struct mlx4_dev *dev,
 		 == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) ? "vxlan" : "none");
 }
 
+static int mlx4_validate_optimized_steering(struct mlx4_dev *dev)
+{
+	int i;
+	struct mlx4_port_cap port_cap;
+
+	if (dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
+		return -EINVAL;
+
+	for (i = 1; i <= dev->caps.num_ports; i++) {
+		if (mlx4_dev_port(dev, i, &port_cap)) {
+			mlx4_err(dev,
+				 "QUERY_DEV_CAP command failed, can't veify DMFS high rate steering.\n");
+		} else if ((dev->caps.dmfs_high_steer_mode !=
+			    MLX4_STEERING_DMFS_A0_DEFAULT) &&
+			   (port_cap.dmfs_optimized_state ==
+			    !!(dev->caps.dmfs_high_steer_mode ==
+			    MLX4_STEERING_DMFS_A0_DISABLE))) {
+			mlx4_err(dev,
+				 "DMFS high rate steer mode differ, driver requested %s but %s in FW.\n",
+				 dmfs_high_rate_steering_mode_str(
+					dev->caps.dmfs_high_steer_mode),
+				 (port_cap.dmfs_optimized_state ?
+					"enabled" : "disabled"));
+		}
+	}
+
+	return 0;
+}
+
 static int mlx4_init_fw(struct mlx4_dev *dev)
 {
 	struct mlx4_mod_stat_cfg   mlx4_cfg;
@@ -1743,6 +1834,10 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 		choose_steering_mode(dev, &dev_cap);
 		choose_tunnel_offload_mode(dev, &dev_cap);
 
+		if (dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_STATIC &&
+		    mlx4_is_master(dev))
+			dev->caps.function_caps |= MLX4_FUNC_CAP_DMFS_A0_STATIC;
+
 		err = mlx4_get_phys_port_id(dev);
 		if (err)
 			mlx4_err(dev, "Fail to get physical port id\n");
@@ -1829,6 +1924,24 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 				mlx4_err(dev, "Failed to map internal clock. Timestamping is not supported\n");
 			}
 		}
+
+		if (dev->caps.dmfs_high_steer_mode !=
+		    MLX4_STEERING_DMFS_A0_NOT_SUPPORTED) {
+			if (mlx4_validate_optimized_steering(dev))
+				mlx4_warn(dev, "Optimized steering validation failed\n");
+
+			if (dev->caps.dmfs_high_steer_mode ==
+			    MLX4_STEERING_DMFS_A0_DISABLE) {
+				dev->caps.dmfs_high_rate_qpn_base =
+					dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];
+				dev->caps.dmfs_high_rate_qpn_range =
+					MLX4_A0_STEERING_TABLE_SIZE;
+			}
+
+			mlx4_dbg(dev, "DMFS high rate steer mode is: %s\n",
+				 dmfs_high_rate_steering_mode_str(
+					dev->caps.dmfs_high_steer_mode));
+		}
 	} else {
 		err = mlx4_init_slave(dev);
 		if (err) {
@@ -3201,10 +3314,11 @@ static int __init mlx4_verify_params(void)
 		port_type_array[0] = true;
 	}
 
-	if (mlx4_log_num_mgm_entry_size != -1 &&
-	    (mlx4_log_num_mgm_entry_size < MLX4_MIN_MGM_LOG_ENTRY_SIZE ||
-	     mlx4_log_num_mgm_entry_size > MLX4_MAX_MGM_LOG_ENTRY_SIZE)) {
-		pr_warn("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not in legal range (-1 or %d..%d)\n",
+	if (mlx4_log_num_mgm_entry_size < -7 ||
+	    (mlx4_log_num_mgm_entry_size > 0 &&
+	     (mlx4_log_num_mgm_entry_size < MLX4_MIN_MGM_LOG_ENTRY_SIZE ||
+	      mlx4_log_num_mgm_entry_size > MLX4_MAX_MGM_LOG_ENTRY_SIZE))) {
+		pr_warn("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not in legal range (-7..0 or %d..%d)\n",
 			mlx4_log_num_mgm_entry_size,
 			MLX4_MIN_MGM_LOG_ENTRY_SIZE,
 			MLX4_MAX_MGM_LOG_ENTRY_SIZE);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index cebd1180702..bdd4eea2247 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -689,8 +689,6 @@ enum mlx4_qp_table_zones {
 	MLX4_QP_TABLE_ZONE_NUM
 };
 
-#define MLX4_A0_STEERING_TABLE_SIZE    256
-
 struct mlx4_qp_table {
 	struct mlx4_bitmap	*bitmap_gen;
 	struct mlx4_zone_allocator *zones;
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index d8d040c366f..1586ecce13c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -712,8 +712,8 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 	int k;
 	int fixed_reserved_from_bot_rv = 0;
 	int bottom_reserved_for_rss_bitmap;
-	u32 max_table_offset = dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] +
-		MLX4_A0_STEERING_TABLE_SIZE;
+	u32 max_table_offset = dev->caps.dmfs_high_rate_qpn_base +
+			dev->caps.dmfs_high_rate_qpn_range;
 
 	spin_lock_init(&qp_table->lock);
 	INIT_RADIX_TREE(&dev->qp_table_tree, GFP_ATOMIC);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 39890cddc5f..25c791e295f 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -117,6 +117,14 @@ enum {
 	MLX4_STEERING_MODE_DEVICE_MANAGED
 };
 
+enum {
+	MLX4_STEERING_DMFS_A0_DEFAULT,
+	MLX4_STEERING_DMFS_A0_DYNAMIC,
+	MLX4_STEERING_DMFS_A0_STATIC,
+	MLX4_STEERING_DMFS_A0_DISABLE,
+	MLX4_STEERING_DMFS_A0_NOT_SUPPORTED
+};
+
 static inline const char *mlx4_steering_mode_str(int steering_mode)
 {
 	switch (steering_mode) {
@@ -191,7 +199,8 @@ enum {
 	MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP	= 1LL <<  15,
 	MLX4_DEV_CAP_FLAG2_CONFIG_DEV		= 1LL <<  16,
 	MLX4_DEV_CAP_FLAG2_SYS_EQS		= 1LL <<  17,
-	MLX4_DEV_CAP_FLAG2_80_VFS		= 1LL <<  18
+	MLX4_DEV_CAP_FLAG2_80_VFS		= 1LL <<  18,
+	MLX4_DEV_CAP_FLAG2_FS_A0		= 1LL <<  19
 };
 
 enum {
@@ -225,7 +234,8 @@ enum {
 
 enum {
 	MLX4_FUNC_CAP_64B_EQE_CQE	= 1L << 0,
-	MLX4_FUNC_CAP_EQE_CQE_STRIDE	= 1L << 1
+	MLX4_FUNC_CAP_EQE_CQE_STRIDE	= 1L << 1,
+	MLX4_FUNC_CAP_DMFS_A0_STATIC	= 1L << 2
 };
 
 
@@ -482,6 +492,7 @@ struct mlx4_caps {
 	int			reserved_mcgs;
 	int			num_qp_per_mgm;
 	int			steering_mode;
+	int			dmfs_high_steer_mode;
 	int			fs_log_max_ucast_qp_range_size;
 	int			num_pds;
 	int			reserved_pds;
@@ -522,6 +533,8 @@ struct mlx4_caps {
 	int			tunnel_offload_mode;
 	u8			rx_checksum_flags_port[MLX4_MAX_PORTS + 1];
 	u8			alloc_res_qp_mask;
+	u32			dmfs_high_rate_qpn_base;
+	u32			dmfs_high_rate_qpn_range;
 };
 
 struct mlx4_buf_list {
-- 
cgit v1.2.3-70-g09d2


From 7e50387bceda4d5542e4ba87097f69071b425fe5 Mon Sep 17 00:00:00 2001
From: Corey Minyard <cminyard@mvista.com>
Date: Thu, 9 Oct 2014 07:20:32 -0500
Subject: ipmi: Move the address source to string to ipmi-generic code

It was in the system interface driver, but is generic functionality.

Signed-off-by: Corey Minyard <cminyard@mvista.com>
---
 drivers/char/ipmi/ipmi_msghandler.c | 12 ++++++++++++
 drivers/char/ipmi/ipmi_si_intf.c    | 10 +++-------
 include/linux/ipmi.h                |  1 +
 3 files changed, 16 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index f816211f062..e5d7c0b6fe3 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -474,6 +474,18 @@ static DEFINE_MUTEX(smi_watchers_mutex);
 #define ipmi_get_stat(intf, stat) \
 	((unsigned int) atomic_read(&(intf)->stats[IPMI_STAT_ ## stat]))
 
+static char *addr_src_to_str[] = { "invalid", "hotmod", "hardcoded", "SPMI",
+				   "ACPI", "SMBIOS", "PCI",
+				   "device-tree", "default" };
+
+const char *ipmi_addr_src_to_str(enum ipmi_addr_src src)
+{
+	if (src > SI_DEFAULT)
+		src = 0; /* Invalid */
+	return addr_src_to_str[src];
+}
+EXPORT_SYMBOL(ipmi_addr_src_to_str);
+
 static int is_lan_addr(struct ipmi_addr *addr)
 {
 	return addr->addr_type == IPMI_LAN_ADDR_TYPE;
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 87471198ee4..337182b5c51 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -111,10 +111,6 @@ enum si_type {
 };
 static char *si_to_str[] = { "kcs", "smic", "bt" };
 
-static char *ipmi_addr_src_to_str[] = { NULL, "hotmod", "hardcoded", "SPMI",
-					"ACPI", "SMBIOS", "PCI",
-					"device-tree", "default" };
-
 #define DEVICE_NAME "ipmi_si"
 
 static struct platform_driver ipmi_driver;
@@ -3279,8 +3275,8 @@ static int add_smi(struct smi_info *new_smi)
 	int rv = 0;
 
 	printk(KERN_INFO PFX "Adding %s-specified %s state machine",
-			ipmi_addr_src_to_str[new_smi->addr_source],
-			si_to_str[new_smi->si_type]);
+	       ipmi_addr_src_to_str(new_smi->addr_source),
+	       si_to_str[new_smi->si_type]);
 	mutex_lock(&smi_infos_lock);
 	if (!is_new_interface(new_smi)) {
 		printk(KERN_CONT " duplicate interface\n");
@@ -3310,7 +3306,7 @@ static int try_smi_init(struct smi_info *new_smi)
 	printk(KERN_INFO PFX "Trying %s-specified %s state"
 	       " machine at %s address 0x%lx, slave address 0x%x,"
 	       " irq %d\n",
-	       ipmi_addr_src_to_str[new_smi->addr_source],
+	       ipmi_addr_src_to_str(new_smi->addr_source),
 	       si_to_str[new_smi->si_type],
 	       addr_space_to_str[new_smi->io.addr_type],
 	       new_smi->io.addr_data,
diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h
index 76d2acbfa7c..47b8f8ddb2b 100644
--- a/include/linux/ipmi.h
+++ b/include/linux/ipmi.h
@@ -278,6 +278,7 @@ enum ipmi_addr_src {
 	SI_INVALID = 0, SI_HOTMOD, SI_HARDCODED, SI_SPMI, SI_ACPI, SI_SMBIOS,
 	SI_PCI,	SI_DEVICETREE, SI_DEFAULT
 };
+const char *ipmi_addr_src_to_str(enum ipmi_addr_src src);
 
 union ipmi_smi_info_union {
 	/*
-- 
cgit v1.2.3-70-g09d2


From 5a0e10ec4a82ec9e1ab9b85a0f2c2893f7ffda25 Mon Sep 17 00:00:00 2001
From: Corey Minyard <cminyard@mvista.com>
Date: Fri, 10 Oct 2014 22:11:05 -0500
Subject: ipmi: Remove useless sysfs_name parameters

It was always "bmc", so just hardcode it.  It makes no sense to
pass that in.

Signed-off-by: Corey Minyard <cminyard@mvista.com>
---
 drivers/char/ipmi/ipmi_msghandler.c | 34 +++++-----------------------------
 drivers/char/ipmi/ipmi_si_intf.c    |  1 -
 include/linux/ipmi_smi.h            |  1 -
 3 files changed, 5 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index 4539afa5b7f..5b08b92c644 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -342,7 +342,6 @@ struct ipmi_smi {
 
 	struct bmc_device *bmc;
 	char *my_dev_name;
-	char *sysfs_name;
 
 	/*
 	 * This is the lower-layer's sender routine.  Note that you
@@ -2373,11 +2372,7 @@ static void ipmi_bmc_unregister(ipmi_smi_t intf)
 {
 	struct bmc_device *bmc = intf->bmc;
 
-	if (intf->sysfs_name) {
-		sysfs_remove_link(&intf->si_dev->kobj, intf->sysfs_name);
-		kfree(intf->sysfs_name);
-		intf->sysfs_name = NULL;
-	}
+	sysfs_remove_link(&intf->si_dev->kobj, "bmc");
 	if (intf->my_dev_name) {
 		sysfs_remove_link(&bmc->pdev.dev.kobj, intf->my_dev_name);
 		kfree(intf->my_dev_name);
@@ -2417,8 +2412,7 @@ out:
 	return err;
 }
 
-static int ipmi_bmc_register(ipmi_smi_t intf, int ifnum,
-			     const char *sysfs_name)
+static int ipmi_bmc_register(ipmi_smi_t intf, int ifnum)
 {
 	int               rv;
 	struct bmc_device *bmc = intf->bmc;
@@ -2489,6 +2483,7 @@ static int ipmi_bmc_register(ipmi_smi_t intf, int ifnum,
 		bmc->pdev.id = bmc->id.device_id;
 		bmc->pdev.dev.release = release_bmc_device;
 		bmc->pdev.dev.type = &bmc_device_type;
+		kref_init(&bmc->usecount);
 
 		rv = platform_device_register(&bmc->pdev);
 		mutex_unlock(&ipmidriver_mutex);
@@ -2505,8 +2500,6 @@ static int ipmi_bmc_register(ipmi_smi_t intf, int ifnum,
 			return rv;
 		}
 
-		kref_init(&bmc->usecount);
-
 		rv = create_bmc_files(bmc);
 		if (rv) {
 			mutex_lock(&ipmidriver_mutex);
@@ -2527,20 +2520,8 @@ static int ipmi_bmc_register(ipmi_smi_t intf, int ifnum,
 	 * create symlink from system interface device to bmc device
 	 * and back.
 	 */
-	intf->sysfs_name = kstrdup(sysfs_name, GFP_KERNEL);
-	if (!intf->sysfs_name) {
-		rv = -ENOMEM;
-		printk(KERN_ERR
-		       "ipmi_msghandler: allocate link to BMC: %d\n",
-		       rv);
-		goto out_err;
-	}
-
-	rv = sysfs_create_link(&intf->si_dev->kobj,
-			       &bmc->pdev.dev.kobj, intf->sysfs_name);
+	rv = sysfs_create_link(&intf->si_dev->kobj, &bmc->pdev.dev.kobj, "bmc");
 	if (rv) {
-		kfree(intf->sysfs_name);
-		intf->sysfs_name = NULL;
 		printk(KERN_ERR
 		       "ipmi_msghandler: Unable to create bmc symlink: %d\n",
 		       rv);
@@ -2549,8 +2530,6 @@ static int ipmi_bmc_register(ipmi_smi_t intf, int ifnum,
 
 	intf->my_dev_name = kasprintf(GFP_KERNEL, "ipmi%d", ifnum);
 	if (!intf->my_dev_name) {
-		kfree(intf->sysfs_name);
-		intf->sysfs_name = NULL;
 		rv = -ENOMEM;
 		printk(KERN_ERR
 		       "ipmi_msghandler: allocate link from BMC: %d\n",
@@ -2561,8 +2540,6 @@ static int ipmi_bmc_register(ipmi_smi_t intf, int ifnum,
 	rv = sysfs_create_link(&bmc->pdev.dev.kobj, &intf->si_dev->kobj,
 			       intf->my_dev_name);
 	if (rv) {
-		kfree(intf->sysfs_name);
-		intf->sysfs_name = NULL;
 		kfree(intf->my_dev_name);
 		intf->my_dev_name = NULL;
 		printk(KERN_ERR
@@ -2761,7 +2738,6 @@ int ipmi_register_smi(struct ipmi_smi_handlers *handlers,
 		      void		       *send_info,
 		      struct ipmi_device_id    *device_id,
 		      struct device            *si_dev,
-		      const char               *sysfs_name,
 		      unsigned char            slave_addr)
 {
 	int              i, j;
@@ -2895,7 +2871,7 @@ int ipmi_register_smi(struct ipmi_smi_handlers *handlers,
 	if (rv == 0)
 		rv = add_proc_entries(intf, i);
 
-	rv = ipmi_bmc_register(intf, i, sysfs_name);
+	rv = ipmi_bmc_register(intf, i);
 
  out:
 	if (rv) {
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 337182b5c51..f474ad8a7b8 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -3429,7 +3429,6 @@ static int try_smi_init(struct smi_info *new_smi)
 			       new_smi,
 			       &new_smi->device_id,
 			       new_smi->dev,
-			       "bmc",
 			       new_smi->slave_addr);
 	if (rv) {
 		dev_err(new_smi->dev, "Unable to register device: error %d\n",
diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h
index bd349240d50..6131845016d 100644
--- a/include/linux/ipmi_smi.h
+++ b/include/linux/ipmi_smi.h
@@ -212,7 +212,6 @@ int ipmi_register_smi(struct ipmi_smi_handlers *handlers,
 		      void                     *send_info,
 		      struct ipmi_device_id    *device_id,
 		      struct device            *dev,
-		      const char               *sysfs_name,
 		      unsigned char            slave_addr);
 
 /*
-- 
cgit v1.2.3-70-g09d2


From a11213fc36d29d42ab00d400796e98fc770c93b9 Mon Sep 17 00:00:00 2001
From: Corey Minyard <cminyard@mvista.com>
Date: Fri, 10 Oct 2014 17:47:04 -0500
Subject: ipmi: Use the proper type for acpi_handle

Minor cleanup, don't use a void pointer, use the right type.

Signed-off-by: Corey Minyard <cminyard@mvista.com>
---
 include/linux/ipmi.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h
index 47b8f8ddb2b..838dbfa3c33 100644
--- a/include/linux/ipmi.h
+++ b/include/linux/ipmi.h
@@ -37,6 +37,7 @@
 
 #include <linux/list.h>
 #include <linux/proc_fs.h>
+#include <linux/acpi.h> /* For acpi_handle */
 
 struct module;
 struct device;
@@ -281,13 +282,15 @@ enum ipmi_addr_src {
 const char *ipmi_addr_src_to_str(enum ipmi_addr_src src);
 
 union ipmi_smi_info_union {
+#ifdef CONFIG_ACPI
 	/*
 	 * the acpi_info element is defined for the SI_ACPI
 	 * address type
 	 */
 	struct {
-		void *acpi_handle;
+		acpi_handle acpi_handle;
 	} acpi_info;
+#endif
 };
 
 struct ipmi_smi_info {
-- 
cgit v1.2.3-70-g09d2


From 99ab32f3b5d705be562b8c4d9dca7c1ae3dc2cdf Mon Sep 17 00:00:00 2001
From: Corey Minyard <cminyard@mvista.com>
Date: Fri, 7 Nov 2014 07:57:31 -0600
Subject: ipmi: Remove the now unused priority from SMI sender

Since the queue was moved into the message handler, the priority
field is now irrelevant.

Signed-off-by: Corey Minyard <cminyard@mvista.com>
---
 drivers/char/ipmi/ipmi_msghandler.c | 4 ++--
 drivers/char/ipmi/ipmi_si_intf.c    | 3 +--
 include/linux/ipmi_smi.h            | 9 ++++-----
 3 files changed, 7 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index b705218fbbf..5fa83f75137 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -1516,7 +1516,7 @@ static void smi_send(ipmi_smi_t intf, struct ipmi_smi_handlers *handlers,
 		spin_unlock_irqrestore(&intf->xmit_msgs_lock, flags);
 
 	if (smi_msg)
-		handlers->sender(intf->send_info, smi_msg, 0);
+		handlers->sender(intf->send_info, smi_msg);
 }
 
 /*
@@ -3908,7 +3908,7 @@ static void smi_recv_tasklet(unsigned long val)
 	if (!run_to_completion)
 		spin_unlock_irqrestore(&intf->xmit_msgs_lock, flags);
 	if (newmsg)
-		intf->handlers->sender(intf->send_info, newmsg, 0);
+		intf->handlers->sender(intf->send_info, newmsg);
 
 	handle_new_recv_msgs(intf);
 }
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index d31a7fce226..4f11301a0c4 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -892,8 +892,7 @@ static void check_start_timer_thread(struct smi_info *smi_info)
 }
 
 static void sender(void                *send_info,
-		   struct ipmi_smi_msg *msg,
-		   int                 priority)
+		   struct ipmi_smi_msg *msg)
 {
 	struct smi_info   *smi_info = send_info;
 	enum si_sm_result result;
diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h
index 6131845016d..0b1e569f5ff 100644
--- a/include/linux/ipmi_smi.h
+++ b/include/linux/ipmi_smi.h
@@ -98,12 +98,11 @@ struct ipmi_smi_handlers {
 	   operation is not allowed to fail.  If an error occurs, it
 	   should report back the error in a received message.  It may
 	   do this in the current call context, since no write locks
-	   are held when this is run.  If the priority is > 0, the
-	   message will go into a high-priority queue and be sent
-	   first.  Otherwise, it goes into a normal-priority queue. */
+	   are held when this is run.  Message are delivered one at
+	   a time by the message handler, a new message will not be
+	   delivered until the previous message is returned. */
 	void (*sender)(void                *send_info,
-		       struct ipmi_smi_msg *msg,
-		       int                 priority);
+		       struct ipmi_smi_msg *msg);
 
 	/* Called by the upper layer to request that we try to get
 	   events from the BMC we are attached to. */
-- 
cgit v1.2.3-70-g09d2


From 4b1acc43331d6c716c331a61477660dc20c8b59c Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Tue, 18 Nov 2014 17:04:53 +0100
Subject: i2c: core changes for slave support

Finally(!), make Linux support being an I2C slave. Most of the existing
infrastructure is reused. We mainly add i2c_slave_register/unregister()
calls which tells i2c bus drivers to activate the slave mode. Then, they
also get a callback to report slave events to.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/i2c-core.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/i2c.h    | 29 +++++++++++++++++++++++++++++
 2 files changed, 78 insertions(+)

(limited to 'include')

diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 3105bd273f7..c09d06bf4d9 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -24,6 +24,7 @@
    (c) 2013  Wolfram Sang <wsa@the-dreams.de>
    I2C ACPI code Copyright (C) 2014 Intel Corp
    Author: Lan Tianyu <tianyu.lan@intel.com>
+   I2C slave support (c) 2014 by Wolfram Sang <wsa@sang-engineering.com>
  */
 
 #include <linux/module.h>
@@ -2911,6 +2912,54 @@ trace:
 }
 EXPORT_SYMBOL(i2c_smbus_xfer);
 
+int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb)
+{
+	int ret;
+
+	if (!client || !slave_cb)
+		return -EINVAL;
+
+	if (!(client->flags & I2C_CLIENT_TEN)) {
+		/* Enforce stricter address checking */
+		ret = i2c_check_addr_validity(client->addr);
+		if (ret)
+			return ret;
+	}
+
+	if (!client->adapter->algo->reg_slave)
+		return -EOPNOTSUPP;
+
+	client->slave_cb = slave_cb;
+
+	i2c_lock_adapter(client->adapter);
+	ret = client->adapter->algo->reg_slave(client);
+	i2c_unlock_adapter(client->adapter);
+
+	if (ret)
+		client->slave_cb = NULL;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(i2c_slave_register);
+
+int i2c_slave_unregister(struct i2c_client *client)
+{
+	int ret;
+
+	if (!client->adapter->algo->unreg_slave)
+		return -EOPNOTSUPP;
+
+	i2c_lock_adapter(client->adapter);
+	ret = client->adapter->algo->unreg_slave(client);
+	i2c_unlock_adapter(client->adapter);
+
+	if (ret == 0)
+		client->slave_cb = NULL;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(i2c_slave_unregister);
+
 MODULE_AUTHOR("Simon G. Vogl <simon@tk.uni-linz.ac.at>");
 MODULE_DESCRIPTION("I2C-Bus main module");
 MODULE_LICENSE("GPL");
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index b556e0ab946..a720d9921b4 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -46,6 +46,8 @@ struct i2c_client;
 struct i2c_driver;
 union i2c_smbus_data;
 struct i2c_board_info;
+enum i2c_slave_event;
+typedef int (*i2c_slave_cb_t)(struct i2c_client *, enum i2c_slave_event, u8 *);
 
 struct module;
 
@@ -209,6 +211,8 @@ struct i2c_driver {
  * @irq: indicates the IRQ generated by this device (if any)
  * @detected: member of an i2c_driver.clients list or i2c-core's
  *	userspace_devices list
+ * @slave_cb: Callback when I2C slave mode of an adapter is used. The adapter
+ *	calls it to pass on slave events to the slave driver.
  *
  * An i2c_client identifies a single device (i.e. chip) connected to an
  * i2c bus. The behaviour exposed to Linux is defined by the driver
@@ -224,6 +228,7 @@ struct i2c_client {
 	struct device dev;		/* the device structure		*/
 	int irq;			/* irq issued by device		*/
 	struct list_head detected;
+	i2c_slave_cb_t slave_cb;	/* callback for slave mode	*/
 };
 #define to_i2c_client(d) container_of(d, struct i2c_client, dev)
 
@@ -246,6 +251,25 @@ static inline void i2c_set_clientdata(struct i2c_client *dev, void *data)
 	dev_set_drvdata(&dev->dev, data);
 }
 
+/* I2C slave support */
+
+enum i2c_slave_event {
+	I2C_SLAVE_REQ_READ_START,
+	I2C_SLAVE_REQ_READ_END,
+	I2C_SLAVE_REQ_WRITE_START,
+	I2C_SLAVE_REQ_WRITE_END,
+	I2C_SLAVE_STOP,
+};
+
+extern int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb);
+extern int i2c_slave_unregister(struct i2c_client *client);
+
+static inline int i2c_slave_event(struct i2c_client *client,
+				  enum i2c_slave_event event, u8 *val)
+{
+	return client->slave_cb(client, event, val);
+}
+
 /**
  * struct i2c_board_info - template for device creation
  * @type: chip type, to initialize i2c_client.name
@@ -352,6 +376,8 @@ i2c_register_board_info(int busnum, struct i2c_board_info const *info,
  *   into I2C transfers instead.
  * @functionality: Return the flags that this algorithm/adapter pair supports
  *   from the I2C_FUNC_* flags.
+ * @reg_slave: Register given client to I2C slave mode of this adapter
+ * @unreg_slave: Unregister given client from I2C slave mode of this adapter
  *
  * The following structs are for those who like to implement new bus drivers:
  * i2c_algorithm is the interface to a class of hardware solutions which can
@@ -377,6 +403,9 @@ struct i2c_algorithm {
 
 	/* To determine what the adapter supports */
 	u32 (*functionality) (struct i2c_adapter *);
+
+	int (*reg_slave)(struct i2c_client *client);
+	int (*unreg_slave)(struct i2c_client *client);
 };
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 027bc8b08242c59e19356b4b2c189f2d849ab660 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 16 Sep 2014 13:50:01 -0700
Subject: pstore-ram: Allow optional mapping with pgprot_noncached

On some ARMs the memory can be mapped pgprot_noncached() and still
be working for atomic operations. As pointed out by Colin Cross
<ccross@android.com>, in some cases you do want to use
pgprot_noncached() if the SoC supports it to see a debug printk
just before a write hanging the system.

On ARMs, the atomic operations on strongly ordered memory are
implementation defined. So let's provide an optional kernel parameter
for configuring pgprot_noncached(), and use pgprot_writecombine() by
default.

Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Rob Herring <robherring2@gmail.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Anton Vorontsov <anton@enomsg.org>
Cc: Colin Cross <ccross@android.com>
Cc: Olof Johansson <olof@lixom.net>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: stable@vger.kernel.org
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 Documentation/ramoops.txt  | 13 +++++++++++--
 fs/pstore/ram.c            | 13 +++++++++++--
 fs/pstore/ram_core.c       | 31 ++++++++++++++++++++++---------
 include/linux/pstore_ram.h |  4 +++-
 4 files changed, 47 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/Documentation/ramoops.txt b/Documentation/ramoops.txt
index 69b3cac4749..5d8675615e5 100644
--- a/Documentation/ramoops.txt
+++ b/Documentation/ramoops.txt
@@ -14,11 +14,19 @@ survive after a restart.
 
 1. Ramoops concepts
 
-Ramoops uses a predefined memory area to store the dump. The start and size of
-the memory area are set using two variables:
+Ramoops uses a predefined memory area to store the dump. The start and size
+and type of the memory area are set using three variables:
   * "mem_address" for the start
   * "mem_size" for the size. The memory size will be rounded down to a
   power of two.
+  * "mem_type" to specifiy if the memory type (default is pgprot_writecombine).
+
+Typically the default value of mem_type=0 should be used as that sets the pstore
+mapping to pgprot_writecombine. Setting mem_type=1 attempts to use
+pgprot_noncached, which only works on some platforms. This is because pstore
+depends on atomic operations. At least on ARM, pgprot_noncached causes the
+memory to be mapped strongly ordered, and atomic operations on strongly ordered
+memory are implementation defined, and won't work on many ARMs such as omaps.
 
 The memory area is divided into "record_size" chunks (also rounded down to
 power of two) and each oops/panic writes a "record_size" chunk of
@@ -55,6 +63,7 @@ Setting the ramoops parameters can be done in 2 different manners:
 static struct ramoops_platform_data ramoops_data = {
         .mem_size               = <...>,
         .mem_address            = <...>,
+        .mem_type               = <...>,
         .record_size            = <...>,
         .dump_oops              = <...>,
         .ecc                    = <...>,
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index ec881b31270..2f389ce5023 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -61,6 +61,11 @@ module_param(mem_size, ulong, 0400);
 MODULE_PARM_DESC(mem_size,
 		"size of reserved RAM used to store oops/panic logs");
 
+static unsigned int mem_type;
+module_param(mem_type, uint, 0600);
+MODULE_PARM_DESC(mem_type,
+		"set to 1 to try to use unbuffered memory (default 0)");
+
 static int dump_oops = 1;
 module_param(dump_oops, int, 0600);
 MODULE_PARM_DESC(dump_oops,
@@ -79,6 +84,7 @@ struct ramoops_context {
 	struct persistent_ram_zone *fprz;
 	phys_addr_t phys_addr;
 	unsigned long size;
+	unsigned int memtype;
 	size_t record_size;
 	size_t console_size;
 	size_t ftrace_size;
@@ -366,7 +372,8 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt,
 		size_t sz = cxt->record_size;
 
 		cxt->przs[i] = persistent_ram_new(*paddr, sz, 0,
-						  &cxt->ecc_info);
+						  &cxt->ecc_info,
+						  cxt->memtype);
 		if (IS_ERR(cxt->przs[i])) {
 			err = PTR_ERR(cxt->przs[i]);
 			dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n",
@@ -396,7 +403,7 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt,
 		return -ENOMEM;
 	}
 
-	*prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info);
+	*prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, cxt->memtype);
 	if (IS_ERR(*prz)) {
 		int err = PTR_ERR(*prz);
 
@@ -443,6 +450,7 @@ static int ramoops_probe(struct platform_device *pdev)
 
 	cxt->size = pdata->mem_size;
 	cxt->phys_addr = pdata->mem_address;
+	cxt->memtype = pdata->mem_type;
 	cxt->record_size = pdata->record_size;
 	cxt->console_size = pdata->console_size;
 	cxt->ftrace_size = pdata->ftrace_size;
@@ -572,6 +580,7 @@ static void ramoops_register_dummy(void)
 
 	dummy_data->mem_size = mem_size;
 	dummy_data->mem_address = mem_address;
+	dummy_data->mem_type = 0;
 	dummy_data->record_size = record_size;
 	dummy_data->console_size = ramoops_console_size;
 	dummy_data->ftrace_size = ramoops_ftrace_size;
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index 24f94b0f227..76c3f80efdf 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -380,7 +380,8 @@ void persistent_ram_zap(struct persistent_ram_zone *prz)
 	persistent_ram_update_header_ecc(prz);
 }
 
-static void *persistent_ram_vmap(phys_addr_t start, size_t size)
+static void *persistent_ram_vmap(phys_addr_t start, size_t size,
+		unsigned int memtype)
 {
 	struct page **pages;
 	phys_addr_t page_start;
@@ -392,7 +393,10 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size)
 	page_start = start - offset_in_page(start);
 	page_count = DIV_ROUND_UP(size + offset_in_page(start), PAGE_SIZE);
 
-	prot = pgprot_writecombine(PAGE_KERNEL);
+	if (memtype)
+		prot = pgprot_noncached(PAGE_KERNEL);
+	else
+		prot = pgprot_writecombine(PAGE_KERNEL);
 
 	pages = kmalloc_array(page_count, sizeof(struct page *), GFP_KERNEL);
 	if (!pages) {
@@ -411,8 +415,11 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size)
 	return vaddr;
 }
 
-static void *persistent_ram_iomap(phys_addr_t start, size_t size)
+static void *persistent_ram_iomap(phys_addr_t start, size_t size,
+		unsigned int memtype)
 {
+	void *va;
+
 	if (!request_mem_region(start, size, "persistent_ram")) {
 		pr_err("request mem region (0x%llx@0x%llx) failed\n",
 			(unsigned long long)size, (unsigned long long)start);
@@ -422,19 +429,24 @@ static void *persistent_ram_iomap(phys_addr_t start, size_t size)
 	buffer_start_add = buffer_start_add_locked;
 	buffer_size_add = buffer_size_add_locked;
 
-	return ioremap_wc(start, size);
+	if (memtype)
+		va = ioremap(start, size);
+	else
+		va = ioremap_wc(start, size);
+
+	return va;
 }
 
 static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size,
-		struct persistent_ram_zone *prz)
+		struct persistent_ram_zone *prz, int memtype)
 {
 	prz->paddr = start;
 	prz->size = size;
 
 	if (pfn_valid(start >> PAGE_SHIFT))
-		prz->vaddr = persistent_ram_vmap(start, size);
+		prz->vaddr = persistent_ram_vmap(start, size, memtype);
 	else
-		prz->vaddr = persistent_ram_iomap(start, size);
+		prz->vaddr = persistent_ram_iomap(start, size, memtype);
 
 	if (!prz->vaddr) {
 		pr_err("%s: Failed to map 0x%llx pages at 0x%llx\n", __func__,
@@ -500,7 +512,8 @@ void persistent_ram_free(struct persistent_ram_zone *prz)
 }
 
 struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
-			u32 sig, struct persistent_ram_ecc_info *ecc_info)
+			u32 sig, struct persistent_ram_ecc_info *ecc_info,
+			unsigned int memtype)
 {
 	struct persistent_ram_zone *prz;
 	int ret = -ENOMEM;
@@ -511,7 +524,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
 		goto err;
 	}
 
-	ret = persistent_ram_buffer_map(start, size, prz);
+	ret = persistent_ram_buffer_map(start, size, prz, memtype);
 	if (ret)
 		goto err;
 
diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h
index 9974975d40d..4af3fdc85b0 100644
--- a/include/linux/pstore_ram.h
+++ b/include/linux/pstore_ram.h
@@ -53,7 +53,8 @@ struct persistent_ram_zone {
 };
 
 struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
-			u32 sig, struct persistent_ram_ecc_info *ecc_info);
+			u32 sig, struct persistent_ram_ecc_info *ecc_info,
+			unsigned int memtype);
 void persistent_ram_free(struct persistent_ram_zone *prz);
 void persistent_ram_zap(struct persistent_ram_zone *prz);
 
@@ -76,6 +77,7 @@ ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz,
 struct ramoops_platform_data {
 	unsigned long	mem_size;
 	unsigned long	mem_address;
+	unsigned int	mem_type;
 	unsigned long	record_size;
 	unsigned long	console_size;
 	unsigned long	ftrace_size;
-- 
cgit v1.2.3-70-g09d2


From 9cc46516ddf497ea16e8d7cb986ae03a0f6b92f8 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Tue, 2 Dec 2014 12:27:26 -0600
Subject: userns: Add a knob to disable setgroups on a per user namespace basis

- Expose the knob to user space through a proc file /proc/<pid>/setgroups

  A value of "deny" means the setgroups system call is disabled in the
  current processes user namespace and can not be enabled in the
  future in this user namespace.

  A value of "allow" means the segtoups system call is enabled.

- Descendant user namespaces inherit the value of setgroups from
  their parents.

- A proc file is used (instead of a sysctl) as sysctls currently do
  not allow checking the permissions at open time.

- Writing to the proc file is restricted to before the gid_map
  for the user namespace is set.

  This ensures that disabling setgroups at a user namespace
  level will never remove the ability to call setgroups
  from a process that already has that ability.

  A process may opt in to the setgroups disable for itself by
  creating, entering and configuring a user namespace or by calling
  setns on an existing user namespace with setgroups disabled.
  Processes without privileges already can not call setgroups so this
  is a noop.  Prodcess with privilege become processes without
  privilege when entering a user namespace and as with any other path
  to dropping privilege they would not have the ability to call
  setgroups.  So this remains within the bounds of what is possible
  without a knob to disable setgroups permanently in a user namespace.

Cc: stable@vger.kernel.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/proc/base.c                 | 53 ++++++++++++++++++++++++++
 include/linux/user_namespace.h |  7 ++++
 kernel/user.c                  |  1 +
 kernel/user_namespace.c        | 85 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 146 insertions(+)

(limited to 'include')

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 772efa45a45..7dc3ea89ef1 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2464,6 +2464,57 @@ static const struct file_operations proc_projid_map_operations = {
 	.llseek		= seq_lseek,
 	.release	= proc_id_map_release,
 };
+
+static int proc_setgroups_open(struct inode *inode, struct file *file)
+{
+	struct user_namespace *ns = NULL;
+	struct task_struct *task;
+	int ret;
+
+	ret = -ESRCH;
+	task = get_proc_task(inode);
+	if (task) {
+		rcu_read_lock();
+		ns = get_user_ns(task_cred_xxx(task, user_ns));
+		rcu_read_unlock();
+		put_task_struct(task);
+	}
+	if (!ns)
+		goto err;
+
+	if (file->f_mode & FMODE_WRITE) {
+		ret = -EACCES;
+		if (!ns_capable(ns, CAP_SYS_ADMIN))
+			goto err_put_ns;
+	}
+
+	ret = single_open(file, &proc_setgroups_show, ns);
+	if (ret)
+		goto err_put_ns;
+
+	return 0;
+err_put_ns:
+	put_user_ns(ns);
+err:
+	return ret;
+}
+
+static int proc_setgroups_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	int ret = single_release(inode, file);
+	put_user_ns(ns);
+	return ret;
+}
+
+static const struct file_operations proc_setgroups_operations = {
+	.open		= proc_setgroups_open,
+	.write		= proc_setgroups_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_setgroups_release,
+};
 #endif /* CONFIG_USER_NS */
 
 static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
@@ -2572,6 +2623,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
 	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	REG("timers",	  S_IRUGO, proc_timers_operations),
@@ -2913,6 +2965,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
 	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
 };
 
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 8d493083486..9f3579ff543 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -17,6 +17,10 @@ struct uid_gid_map {	/* 64 bytes -- 1 cache line */
 	} extent[UID_GID_MAP_MAX_EXTENTS];
 };
 
+#define USERNS_SETGROUPS_ALLOWED 1UL
+
+#define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED
+
 struct user_namespace {
 	struct uid_gid_map	uid_map;
 	struct uid_gid_map	gid_map;
@@ -27,6 +31,7 @@ struct user_namespace {
 	kuid_t			owner;
 	kgid_t			group;
 	unsigned int		proc_inum;
+	unsigned long		flags;
 
 	/* Register of per-UID persistent keyrings for this namespace */
 #ifdef CONFIG_PERSISTENT_KEYRINGS
@@ -63,6 +68,8 @@ extern const struct seq_operations proc_projid_seq_operations;
 extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *);
+extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *);
+extern int proc_setgroups_show(struct seq_file *m, void *v);
 extern bool userns_may_setgroups(const struct user_namespace *ns);
 #else
 
diff --git a/kernel/user.c b/kernel/user.c
index 4efa39350e4..2d09940c963 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,7 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
+	.flags = USERNS_INIT_FLAGS,
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 	.persistent_keyring_register_sem =
 	__RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 44a555ac610..6e80f4c1322 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -100,6 +100,11 @@ int create_user_ns(struct cred *new)
 	ns->owner = owner;
 	ns->group = group;
 
+	/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */
+	mutex_lock(&userns_state_mutex);
+	ns->flags = parent_ns->flags;
+	mutex_unlock(&userns_state_mutex);
+
 	set_cred_user_ns(new, ns);
 
 #ifdef CONFIG_PERSISTENT_KEYRINGS
@@ -839,6 +844,84 @@ static bool new_idmap_permitted(const struct file *file,
 	return false;
 }
 
+int proc_setgroups_show(struct seq_file *seq, void *v)
+{
+	struct user_namespace *ns = seq->private;
+	unsigned long userns_flags = ACCESS_ONCE(ns->flags);
+
+	seq_printf(seq, "%s\n",
+		   (userns_flags & USERNS_SETGROUPS_ALLOWED) ?
+		   "allow" : "deny");
+	return 0;
+}
+
+ssize_t proc_setgroups_write(struct file *file, const char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	char kbuf[8], *pos;
+	bool setgroups_allowed;
+	ssize_t ret;
+
+	/* Only allow a very narrow range of strings to be written */
+	ret = -EINVAL;
+	if ((*ppos != 0) || (count >= sizeof(kbuf)))
+		goto out;
+
+	/* What was written? */
+	ret = -EFAULT;
+	if (copy_from_user(kbuf, buf, count))
+		goto out;
+	kbuf[count] = '\0';
+	pos = kbuf;
+
+	/* What is being requested? */
+	ret = -EINVAL;
+	if (strncmp(pos, "allow", 5) == 0) {
+		pos += 5;
+		setgroups_allowed = true;
+	}
+	else if (strncmp(pos, "deny", 4) == 0) {
+		pos += 4;
+		setgroups_allowed = false;
+	}
+	else
+		goto out;
+
+	/* Verify there is not trailing junk on the line */
+	pos = skip_spaces(pos);
+	if (*pos != '\0')
+		goto out;
+
+	ret = -EPERM;
+	mutex_lock(&userns_state_mutex);
+	if (setgroups_allowed) {
+		/* Enabling setgroups after setgroups has been disabled
+		 * is not allowed.
+		 */
+		if (!(ns->flags & USERNS_SETGROUPS_ALLOWED))
+			goto out_unlock;
+	} else {
+		/* Permanently disabling setgroups after setgroups has
+		 * been enabled by writing the gid_map is not allowed.
+		 */
+		if (ns->gid_map.nr_extents != 0)
+			goto out_unlock;
+		ns->flags &= ~USERNS_SETGROUPS_ALLOWED;
+	}
+	mutex_unlock(&userns_state_mutex);
+
+	/* Report a successful write */
+	*ppos = count;
+	ret = count;
+out:
+	return ret;
+out_unlock:
+	mutex_unlock(&userns_state_mutex);
+	goto out;
+}
+
 bool userns_may_setgroups(const struct user_namespace *ns)
 {
 	bool allowed;
@@ -848,6 +931,8 @@ bool userns_may_setgroups(const struct user_namespace *ns)
 	 * the user namespace has been established.
 	 */
 	allowed = ns->gid_map.nr_extents != 0;
+	/* Is setgroups allowed? */
+	allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED);
 	mutex_unlock(&userns_state_mutex);
 
 	return allowed;
-- 
cgit v1.2.3-70-g09d2


From 1077fa36f23e259858caf6f269a47393a5aff523 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@redhat.com>
Date: Thu, 11 Dec 2014 15:02:06 -0800
Subject: arch: Add lightweight memory barriers dma_rmb() and dma_wmb()

There are a number of situations where the mandatory barriers rmb() and
wmb() are used to order memory/memory operations in the device drivers
and those barriers are much heavier than they actually need to be.  For
example in the case of PowerPC wmb() calls the heavy-weight sync
instruction when for coherent memory operations all that is really needed
is an lsync or eieio instruction.

This commit adds a coherent only version of the mandatory memory barriers
rmb() and wmb().  In most cases this should result in the barrier being the
same as the SMP barriers for the SMP case, however in some cases we use a
barrier that is somewhere in between rmb() and smp_rmb().  For example on
ARM the rmb barriers break down as follows:

  Barrier   Call     Explanation
  --------- -------- ----------------------------------
  rmb()     dsb()    Data synchronization barrier - system
  dma_rmb() dmb(osh) data memory barrier - outer sharable
  smp_rmb() dmb(ish) data memory barrier - inner sharable

These new barriers are not as safe as the standard rmb() and wmb().
Specifically they do not guarantee ordering between coherent and incoherent
memories.  The primary use case for these would be to enforce ordering of
reads and writes when accessing coherent memory that is shared between the
CPU and a device.

It may also be noted that there is no dma_mb().  Most architectures don't
provide a good mechanism for performing a coherent only full barrier without
resorting to the same mechanism used in mb().  As such there isn't much to
be gained in trying to define such a function.

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Michael Ellerman <michael@ellerman.id.au>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: David Miller <davem@davemloft.net>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/memory-barriers.txt   | 42 +++++++++++++++++++++++++++++++++++++
 arch/arm/include/asm/barrier.h      |  4 ++++
 arch/arm64/include/asm/barrier.h    |  3 +++
 arch/ia64/include/asm/barrier.h     |  3 +++
 arch/metag/include/asm/barrier.h    | 14 ++++++-------
 arch/mips/include/asm/barrier.h     |  9 ++++----
 arch/powerpc/include/asm/barrier.h  | 13 +++++++-----
 arch/s390/include/asm/barrier.h     |  2 ++
 arch/sparc/include/asm/barrier_64.h |  3 +++
 arch/x86/include/asm/barrier.h      | 11 ++++++----
 arch/x86/um/asm/barrier.h           | 13 ++++++------
 include/asm-generic/barrier.h       |  8 +++++++
 12 files changed, 99 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 7ee2ae6d545..70a09f8a038 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1633,6 +1633,48 @@ There are some more advanced barrier functions:
      operations" subsection for information on where to use these.
 
 
+ (*) dma_wmb();
+ (*) dma_rmb();
+
+     These are for use with consistent memory to guarantee the ordering
+     of writes or reads of shared memory accessible to both the CPU and a
+     DMA capable device.
+
+     For example, consider a device driver that shares memory with a device
+     and uses a descriptor status value to indicate if the descriptor belongs
+     to the device or the CPU, and a doorbell to notify it when new
+     descriptors are available:
+
+	if (desc->status != DEVICE_OWN) {
+		/* do not read data until we own descriptor */
+		dma_rmb();
+
+		/* read/modify data */
+		read_data = desc->data;
+		desc->data = write_data;
+
+		/* flush modifications before status update */
+		dma_wmb();
+
+		/* assign ownership */
+		desc->status = DEVICE_OWN;
+
+		/* force memory to sync before notifying device via MMIO */
+		wmb();
+
+		/* notify device of new descriptors */
+		writel(DESC_NOTIFY, doorbell);
+	}
+
+     The dma_rmb() allows us guarantee the device has released ownership
+     before we read the data from the descriptor, and he dma_wmb() allows
+     us to guarantee the data is written to the descriptor before the device
+     can see it now has ownership.  The wmb() is needed to guarantee that the
+     cache coherent memory writes have completed before attempting a write to
+     the cache incoherent MMIO region.
+
+     See Documentation/DMA-API.txt for more information on consistent memory.
+
 MMIO WRITE BARRIER
 ------------------
 
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index c6a3e73a6e2..d2f81e6b8c1 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -43,10 +43,14 @@
 #define mb()		do { dsb(); outer_sync(); } while (0)
 #define rmb()		dsb()
 #define wmb()		do { dsb(st); outer_sync(); } while (0)
+#define dma_rmb()	dmb(osh)
+#define dma_wmb()	dmb(oshst)
 #else
 #define mb()		barrier()
 #define rmb()		barrier()
 #define wmb()		barrier()
+#define dma_rmb()	barrier()
+#define dma_wmb()	barrier()
 #endif
 
 #ifndef CONFIG_SMP
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 6389d60574d..a5abb0062d6 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -32,6 +32,9 @@
 #define rmb()		dsb(ld)
 #define wmb()		dsb(st)
 
+#define dma_rmb()	dmb(oshld)
+#define dma_wmb()	dmb(oshst)
+
 #ifndef CONFIG_SMP
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index e8fffb03963..f6769eb2bbf 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -39,6 +39,9 @@
 #define rmb()		mb()
 #define wmb()		mb()
 
+#define dma_rmb()	mb()
+#define dma_wmb()	mb()
+
 #ifdef CONFIG_SMP
 # define smp_mb()	mb()
 #else
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index 6d8b8c9b7c2..d703d8e26a6 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -4,8 +4,6 @@
 #include <asm/metag_mem.h>
 
 #define nop()		asm volatile ("NOP")
-#define mb()		wmb()
-#define rmb()		barrier()
 
 #ifdef CONFIG_METAG_META21
 
@@ -41,11 +39,13 @@ static inline void wr_fence(void)
 
 #endif /* !CONFIG_METAG_META21 */
 
-static inline void wmb(void)
-{
-	/* flush writes through the write combiner */
-	wr_fence();
-}
+/* flush writes through the write combiner */
+#define mb()		wr_fence()
+#define rmb()		barrier()
+#define wmb()		mb()
+
+#define dma_rmb()	rmb()
+#define dma_wmb()	wmb()
 
 #ifndef CONFIG_SMP
 #define fence()		do { } while (0)
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index 3d69aa829a7..2b8bbbcb9be 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -75,20 +75,21 @@
 
 #include <asm/wbflush.h>
 
-#define wmb()		fast_wmb()
-#define rmb()		fast_rmb()
 #define mb()		wbflush()
 #define iob()		wbflush()
 
 #else /* !CONFIG_CPU_HAS_WB */
 
-#define wmb()		fast_wmb()
-#define rmb()		fast_rmb()
 #define mb()		fast_mb()
 #define iob()		fast_iob()
 
 #endif /* !CONFIG_CPU_HAS_WB */
 
+#define wmb()		fast_wmb()
+#define rmb()		fast_rmb()
+#define dma_wmb()	fast_wmb()
+#define dma_rmb()	fast_rmb()
+
 #if defined(CONFIG_WEAK_ORDERING) && defined(CONFIG_SMP)
 # ifdef CONFIG_CPU_CAVIUM_OCTEON
 #  define smp_mb()	__sync()
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index cb6d66c6e3e..a3bf5be111f 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -36,8 +36,6 @@
 
 #define set_mb(var, value)	do { var = value; mb(); } while (0)
 
-#ifdef CONFIG_SMP
-
 #ifdef __SUBARCH_HAS_LWSYNC
 #    define SMPWMB      LWSYNC
 #else
@@ -45,12 +43,17 @@
 #endif
 
 #define __lwsync()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+#define dma_rmb()	__lwsync()
+#define dma_wmb()	__asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
+
+#ifdef CONFIG_SMP
+#define smp_lwsync()	__lwsync()
 
 #define smp_mb()	mb()
 #define smp_rmb()	__lwsync()
 #define smp_wmb()	__asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
 #else
-#define __lwsync()	barrier()
+#define smp_lwsync()	barrier()
 
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
@@ -72,7 +75,7 @@
 #define smp_store_release(p, v)						\
 do {									\
 	compiletime_assert_atomic_type(*p);				\
-	__lwsync();							\
+	smp_lwsync();							\
 	ACCESS_ONCE(*p) = (v);						\
 } while (0)
 
@@ -80,7 +83,7 @@ do {									\
 ({									\
 	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
-	__lwsync();							\
+	smp_lwsync();							\
 	___p1;								\
 })
 
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 33d191d295e..8d724718ec2 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -24,6 +24,8 @@
 
 #define rmb()				mb()
 #define wmb()				mb()
+#define dma_rmb()			rmb()
+#define dma_wmb()			wmb()
 #define smp_mb()			mb()
 #define smp_rmb()			rmb()
 #define smp_wmb()			wmb()
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 6c974c0977a..76648941fea 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -37,6 +37,9 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 #define rmb()	__asm__ __volatile__("":::"memory")
 #define wmb()	__asm__ __volatile__("":::"memory")
 
+#define dma_rmb()	rmb()
+#define dma_wmb()	wmb()
+
 #define set_mb(__var, __value) \
 	do { __var = __value; membar_safe("#StoreLoad"); } while(0)
 
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 5238000285c..2ab1eb33106 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -24,13 +24,16 @@
 #define wmb()	asm volatile("sfence" ::: "memory")
 #endif
 
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
 #ifdef CONFIG_X86_PPRO_FENCE
-# define smp_rmb()	rmb()
+#define dma_rmb()	rmb()
 #else
-# define smp_rmb()	barrier()
+#define dma_rmb()	barrier()
 #endif
+#define dma_wmb()	barrier()
+
+#ifdef CONFIG_SMP
+#define smp_mb()	mb()
+#define smp_rmb()	dma_rmb()
 #define smp_wmb()	barrier()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
 #else /* !SMP */
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index d6511d954e2..2d7d9a1f5b5 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -29,17 +29,18 @@
 
 #endif /* CONFIG_X86_32 */
 
-#ifdef CONFIG_SMP
-
-#define smp_mb()	mb()
 #ifdef CONFIG_X86_PPRO_FENCE
-#define smp_rmb()	rmb()
+#define dma_rmb()	rmb()
 #else /* CONFIG_X86_PPRO_FENCE */
-#define smp_rmb()	barrier()
+#define dma_rmb()	barrier()
 #endif /* CONFIG_X86_PPRO_FENCE */
+#define dma_wmb()	barrier()
 
-#define smp_wmb()	barrier()
+#ifdef CONFIG_SMP
 
+#define smp_mb()	mb()
+#define smp_rmb()	dma_rmb()
+#define smp_wmb()	barrier()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
 
 #else /* CONFIG_SMP */
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 1402fa85538..f5c40b0fadc 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -42,6 +42,14 @@
 #define wmb()	mb()
 #endif
 
+#ifndef dma_rmb
+#define dma_rmb()	rmb()
+#endif
+
+#ifndef dma_wmb
+#define dma_wmb()	wmb()
+#endif
+
 #ifndef read_barrier_depends
 #define read_barrier_depends()		do { } while (0)
 #endif
-- 
cgit v1.2.3-70-g09d2


From 63f13448d81c910a284b096149411a719cbed501 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Tue, 9 Dec 2014 15:37:07 -0500
Subject: powerpc: add little endian flag to syscall_get_arch()

Since both ppc and ppc64 have LE variants which are now reported by uname, add
that flag (__AUDIT_ARCH_LE) to syscall_get_arch() and add AUDIT_ARCH_PPC64LE
variant.

Without this,  perf trace and auditctl fail.

Mainline kernel reports ppc64le (per a058801) but there is no matching
AUDIT_ARCH_PPC64LE.

Since 32-bit PPC LE is not supported by audit, don't advertise it in
AUDIT_ARCH_PPC* variants.

See:
	https://www.redhat.com/archives/linux-audit/2014-August/msg00082.html
	https://www.redhat.com/archives/linux-audit/2014-December/msg00004.html

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/syscall.h | 6 +++++-
 include/uapi/linux/audit.h         | 2 ++
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index 6240698fee9..ff21b7a2f0c 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -90,6 +90,10 @@ static inline void syscall_set_arguments(struct task_struct *task,
 
 static inline int syscall_get_arch(void)
 {
-	return is_32bit_task() ? AUDIT_ARCH_PPC : AUDIT_ARCH_PPC64;
+	int arch = is_32bit_task() ? AUDIT_ARCH_PPC : AUDIT_ARCH_PPC64;
+#ifdef __LITTLE_ENDIAN__
+	arch |= __AUDIT_ARCH_LE;
+#endif
+	return arch;
 }
 #endif	/* _ASM_SYSCALL_H */
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index d4dbef14d4d..584bb0113e2 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -365,7 +365,9 @@ enum {
 #define AUDIT_ARCH_PARISC	(EM_PARISC)
 #define AUDIT_ARCH_PARISC64	(EM_PARISC|__AUDIT_ARCH_64BIT)
 #define AUDIT_ARCH_PPC		(EM_PPC)
+/* do not define AUDIT_ARCH_PPCLE since it is not supported by audit */
 #define AUDIT_ARCH_PPC64	(EM_PPC64|__AUDIT_ARCH_64BIT)
+#define AUDIT_ARCH_PPC64LE	(EM_PPC64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
 #define AUDIT_ARCH_S390		(EM_S390)
 #define AUDIT_ARCH_S390X	(EM_S390|__AUDIT_ARCH_64BIT)
 #define AUDIT_ARCH_SH		(EM_SH)
-- 
cgit v1.2.3-70-g09d2


From 7142637dd93a7e1e9f5515e6c66c7d271fa92ad2 Mon Sep 17 00:00:00 2001
From: Quentin Lambert <lambert.quentin@gmail.com>
Date: Fri, 12 Dec 2014 13:36:54 +0100
Subject: linux/interrupt.h: remove the definition of unused tasklet_hi_enable

Signed-off-by: Quentin Lambert <lambert.quentin@gmail.com>
Signed-off-by: Valentin Rothberg <valentinrothberg@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/interrupt.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 69517a24bc5..d9b05b5bf8c 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -556,12 +556,6 @@ static inline void tasklet_enable(struct tasklet_struct *t)
 	atomic_dec(&t->count);
 }
 
-static inline void tasklet_hi_enable(struct tasklet_struct *t)
-{
-	smp_mb__before_atomic();
-	atomic_dec(&t->count);
-}
-
 extern void tasklet_kill(struct tasklet_struct *t);
 extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu);
 extern void tasklet_init(struct tasklet_struct *t,
-- 
cgit v1.2.3-70-g09d2


From 175f8e2650f7ca6b33d338be3ccc1c00e89594ea Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 12 Dec 2014 22:51:58 +0100
Subject: ACPI / PM: Do not disable wakeup GPEs that have not been enabled

In some cases acpi_device_wakeup() may be called to ensure wakeup
power to be off for a given device even though that device's wakeup
GPE has not been enabled so far.  It calls acpi_disable_gpe() on a
GPE that's not enabled and this causes ACPICA to return the AE_LIMIT
status code from that call which then is reported as an error by the
ACPICA's debug facilities (if enabled).  This may lead to a fair
amount of confusion, so introduce a new ACPI device wakeup flag
to store the wakeup GPE status and avoid disabling wakeup GPEs
that have not been enabled.

Reported-and-tested-by: Venkat Raghavulu <venkat.raghavulu@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/device_pm.c | 12 ++++++++++--
 include/acpi/acpi_bus.h  |  1 +
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 076af814956..e6ff33ecd78 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -680,13 +680,21 @@ static int acpi_device_wakeup(struct acpi_device *adev, u32 target_state,
 		if (error)
 			return error;
 
+		if (adev->wakeup.flags.enabled)
+			return 0;
+
 		res = acpi_enable_gpe(wakeup->gpe_device, wakeup->gpe_number);
-		if (ACPI_FAILURE(res)) {
+		if (ACPI_SUCCESS(res)) {
+			adev->wakeup.flags.enabled = 1;
+		} else {
 			acpi_disable_wakeup_device_power(adev);
 			return -EIO;
 		}
 	} else {
-		acpi_disable_gpe(wakeup->gpe_device, wakeup->gpe_number);
+		if (adev->wakeup.flags.enabled) {
+			acpi_disable_gpe(wakeup->gpe_device, wakeup->gpe_number);
+			adev->wakeup.flags.enabled = 0;
+		}
 		acpi_disable_wakeup_device_power(adev);
 	}
 	return 0;
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index f34a0835aa4..8de31d472fa 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -312,6 +312,7 @@ struct acpi_device_wakeup_flags {
 	u8 valid:1;		/* Can successfully enable wakeup? */
 	u8 run_wake:1;		/* Run-Wake GPE devices */
 	u8 notifier_present:1;  /* Wake-up notify handler has been installed */
+	u8 enabled:1;		/* Enabled for wakeup */
 };
 
 struct acpi_device_wakeup_context {
-- 
cgit v1.2.3-70-g09d2


From 40bd62c6194bdee1bc6652b3b0aa28e34883f603 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Thu, 11 Dec 2014 11:20:36 +0100
Subject: PM: Remove the SET_PM_RUNTIME_PM_OPS() macro

There're now no users left of the SET_PM_RUNTIME_PM_OPS() macro, since
all have converted to use the SET_RUNTIME_PM_OPS() macro instead, so
let's remove it.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index 66a656eb335..8b597636461 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -351,8 +351,6 @@ struct dev_pm_ops {
 #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn)
 #endif
 
-#define SET_PM_RUNTIME_PM_OPS	SET_RUNTIME_PM_OPS
-
 /*
  * Use this if you want to use the same suspend and resume callbacks for suspend
  * to RAM and hibernation.
-- 
cgit v1.2.3-70-g09d2


From aee4e5f3d3abb7a2239dd02f6d8fb173413fd02f Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 10 Dec 2014 17:31:07 -0500
Subject: tracing/sched: Check preempt_count() for current when reading
 task->state

When recording the state of a task for the sched_switch tracepoint a check of
task_preempt_count() is performed to see if PREEMPT_ACTIVE is set. This is
because, technically, a task being preempted is really in the TASK_RUNNING
state, and that is what should be recorded when tracing a sched_switch,
even if the task put itself into another state (it hasn't scheduled out
in that state yet).

But with the change to use per_cpu preempt counts, the
task_thread_info(p)->preempt_count is no longer used, and instead
task_preempt_count(p) is used.

The problem is that this does not use the current preempt count but a stale
one from a previous sched_switch. The task_preempt_count(p) uses
saved_preempt_count and not preempt_count(). But for tracing sched_switch,
if p is current, we really want preempt_count().

I hit this bug when I was tracing sleep and the call from do_nanosleep()
scheduled out in the "RUNNING" state.

           sleep-4290  [000] 537272.259992: sched_switch:         sleep:4290 [120] R ==> swapper/0:0 [120]
           sleep-4290  [000] 537272.260015: kernel_stack:         <stack trace>
=> __schedule (ffffffff8150864a)
=> schedule (ffffffff815089f8)
=> do_nanosleep (ffffffff8150b76c)
=> hrtimer_nanosleep (ffffffff8108d66b)
=> SyS_nanosleep (ffffffff8108d750)
=> return_to_handler (ffffffff8150e8e5)
=> tracesys_phase2 (ffffffff8150c844)

After a bit of hair pulling, I found that the state was really
TASK_INTERRUPTIBLE, but the saved_preempt_count had an old PREEMPT_ACTIVE
set and caused the sched_switch tracepoint to show it as RUNNING.

Link: http://lkml.kernel.org/r/20141210174428.3cb7542a@gandalf.local.home

Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: stable@vger.kernel.org # 3.13+
Cc: Peter Zijlstra <peterz@infradead.org>
Fixes: 01028747559a "sched: Create more preempt_count accessors"
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/events/sched.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 0a68d5ae584..a7d67bc1490 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -100,7 +100,7 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
 	/*
 	 * For all intents and purposes a preempted task is a running task.
 	 */
-	if (task_preempt_count(p) & PREEMPT_ACTIVE)
+	if (preempt_count() & PREEMPT_ACTIVE)
 		state = TASK_RUNNING | TASK_STATE_MAX;
 #endif
 
-- 
cgit v1.2.3-70-g09d2


From c291ee622165cb2c8d4e7af63fffd499354a23be Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 11 Dec 2014 23:01:41 +0100
Subject: genirq: Prevent proc race against freeing of irq descriptors

Since the rework of the sparse interrupt code to actually free the
unused interrupt descriptors there exists a race between the /proc
interfaces to the irq subsystem and the code which frees the interrupt
descriptor.

CPU0				CPU1
				show_interrupts()
				  desc = irq_to_desc(X);
free_desc(desc)
  remove_from_radix_tree();
  kfree(desc);
				  raw_spinlock_irq(&desc->lock);

/proc/interrupts is the only interface which can actively corrupt
kernel memory via the lock access. /proc/stat can only read from freed
memory. Extremly hard to trigger, but possible.

The interfaces in /proc/irq/N/ are not affected by this because the
removal of the proc file is serialized in procfs against concurrent
readers/writers. The removal happens before the descriptor is freed.

For architectures which have CONFIG_SPARSE_IRQ=n this is a non issue
as the descriptor is never freed. It's merely cleared out with the irq
descriptor lock held. So any concurrent proc access will either see
the old correct value or the cleared out ones.

Protect the lookup and access to the irq descriptor in
show_interrupts() with the sparse_irq_lock.

Provide kstat_irqs_usr() which is protecting the lookup and access
with sparse_irq_lock and switch /proc/stat to use it.

Document the existing kstat_irqs interfaces so it's clear that the
caller needs to take care about protection. The users of these
interfaces are either not affected due to SPARSE_IRQ=n or already
protected against removal.

Fixes: 1f5a5b87f78f "genirq: Implement a sane sparse_irq allocator"
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
---
 fs/proc/stat.c              |  2 +-
 include/linux/kernel_stat.h |  1 +
 kernel/irq/internals.h      |  4 ++++
 kernel/irq/irqdesc.c        | 52 +++++++++++++++++++++++++++++++++++++++++++++
 kernel/irq/proc.c           | 22 ++++++++++++++++++-
 5 files changed, 79 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index bf2d03f8fd3..510413eb25b 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -159,7 +159,7 @@ static int show_stat(struct seq_file *p, void *v)
 
 	/* sum again ? it could be updated? */
 	for_each_irq_nr(j)
-		seq_put_decimal_ull(p, ' ', kstat_irqs(j));
+		seq_put_decimal_ull(p, ' ', kstat_irqs_usr(j));
 
 	seq_printf(p,
 		"\nctxt %llu\n"
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index b9376cd5a18..25a822f6f00 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -68,6 +68,7 @@ static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu)
  * Number of interrupts per specific IRQ source, since bootup
  */
 extern unsigned int kstat_irqs(unsigned int irq);
+extern unsigned int kstat_irqs_usr(unsigned int irq);
 
 /*
  * Number of interrupts per cpu, since bootup
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 4332d766619..df553b0af93 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -78,8 +78,12 @@ extern void unmask_threaded_irq(struct irq_desc *desc);
 
 #ifdef CONFIG_SPARSE_IRQ
 static inline void irq_mark_irq(unsigned int irq) { }
+extern void irq_lock_sparse(void);
+extern void irq_unlock_sparse(void);
 #else
 extern void irq_mark_irq(unsigned int irq);
+static inline void irq_lock_sparse(void) { }
+static inline void irq_unlock_sparse(void) { }
 #endif
 
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index a1782f88f0a..99793b9b6d2 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -132,6 +132,16 @@ static void free_masks(struct irq_desc *desc)
 static inline void free_masks(struct irq_desc *desc) { }
 #endif
 
+void irq_lock_sparse(void)
+{
+	mutex_lock(&sparse_irq_lock);
+}
+
+void irq_unlock_sparse(void)
+{
+	mutex_unlock(&sparse_irq_lock);
+}
+
 static struct irq_desc *alloc_desc(int irq, int node, struct module *owner)
 {
 	struct irq_desc *desc;
@@ -168,6 +178,12 @@ static void free_desc(unsigned int irq)
 
 	unregister_irq_proc(irq, desc);
 
+	/*
+	 * sparse_irq_lock protects also show_interrupts() and
+	 * kstat_irq_usr(). Once we deleted the descriptor from the
+	 * sparse tree we can free it. Access in proc will fail to
+	 * lookup the descriptor.
+	 */
 	mutex_lock(&sparse_irq_lock);
 	delete_irq_desc(irq);
 	mutex_unlock(&sparse_irq_lock);
@@ -574,6 +590,15 @@ void kstat_incr_irq_this_cpu(unsigned int irq)
 	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 }
 
+/**
+ * kstat_irqs_cpu - Get the statistics for an interrupt on a cpu
+ * @irq:	The interrupt number
+ * @cpu:	The cpu number
+ *
+ * Returns the sum of interrupt counts on @cpu since boot for
+ * @irq. The caller must ensure that the interrupt is not removed
+ * concurrently.
+ */
 unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -582,6 +607,14 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 			*per_cpu_ptr(desc->kstat_irqs, cpu) : 0;
 }
 
+/**
+ * kstat_irqs - Get the statistics for an interrupt
+ * @irq:	The interrupt number
+ *
+ * Returns the sum of interrupt counts on all cpus since boot for
+ * @irq. The caller must ensure that the interrupt is not removed
+ * concurrently.
+ */
 unsigned int kstat_irqs(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -594,3 +627,22 @@ unsigned int kstat_irqs(unsigned int irq)
 		sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
 	return sum;
 }
+
+/**
+ * kstat_irqs_usr - Get the statistics for an interrupt
+ * @irq:	The interrupt number
+ *
+ * Returns the sum of interrupt counts on all cpus since boot for
+ * @irq. Contrary to kstat_irqs() this can be called from any
+ * preemptible context. It's protected against concurrent removal of
+ * an interrupt descriptor when sparse irqs are enabled.
+ */
+unsigned int kstat_irqs_usr(unsigned int irq)
+{
+	int sum;
+
+	irq_lock_sparse();
+	sum = kstat_irqs(irq);
+	irq_unlock_sparse();
+	return sum;
+}
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index ac1ba2f1103..9dc9bfd8a67 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -15,6 +15,23 @@
 
 #include "internals.h"
 
+/*
+ * Access rules:
+ *
+ * procfs protects read/write of /proc/irq/N/ files against a
+ * concurrent free of the interrupt descriptor. remove_proc_entry()
+ * immediately prevents new read/writes to happen and waits for
+ * already running read/write functions to complete.
+ *
+ * We remove the proc entries first and then delete the interrupt
+ * descriptor from the radix tree and free it. So it is guaranteed
+ * that irq_to_desc(N) is valid as long as the read/writes are
+ * permitted by procfs.
+ *
+ * The read from /proc/interrupts is a different problem because there
+ * is no protection. So the lookup and the access to irqdesc
+ * information must be protected by sparse_irq_lock.
+ */
 static struct proc_dir_entry *root_irq_dir;
 
 #ifdef CONFIG_SMP
@@ -437,9 +454,10 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 	}
 
+	irq_lock_sparse();
 	desc = irq_to_desc(i);
 	if (!desc)
-		return 0;
+		goto outsparse;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	for_each_online_cpu(j)
@@ -479,6 +497,8 @@ int show_interrupts(struct seq_file *p, void *v)
 	seq_putc(p, '\n');
 out:
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
+outsparse:
+	irq_unlock_sparse();
 	return 0;
 }
 #endif
-- 
cgit v1.2.3-70-g09d2


From 6d3cfbe21bef5b66530b50ad16c88fdc71a04c35 Mon Sep 17 00:00:00 2001
From: Peter Maydell <peter.maydell@linaro.org>
Date: Thu, 4 Dec 2014 15:02:24 +0000
Subject: arm/arm64: KVM: vgic: move reset initialization into vgic_init_maps()

VGIC initialization currently happens in three phases:
 (1) kvm_vgic_create() (triggered by userspace GIC creation)
 (2) vgic_init_maps() (triggered by userspace GIC register read/write
     requests, or from kvm_vgic_init() if not already run)
 (3) kvm_vgic_init() (triggered by first VM run)

We were doing initialization of some state to correspond with the
state of a freshly-reset GIC in kvm_vgic_init(); this is too late,
since it will overwrite changes made by userspace using the
register access APIs before the VM is run. Move this initialization
earlier, into the vgic_init_maps() phase.

This fixes a bug where QEMU could successfully restore a saved
VM state snapshot into a VM that had already been run, but could
not restore it "from cold" using the -loadvm command line option
(the symptoms being that the restored VM would run but interrupts
were ignored).

Finally rename vgic_init_maps to vgic_init and renamed kvm_vgic_init to
kvm_vgic_map_resources.

  [ This patch is originally written by Peter Maydell, but I have
    modified it somewhat heavily, renaming various bits and moving code
    around.  If something is broken, I am to be blamed. - Christoffer ]

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Eric Auger <eric.auger@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 arch/arm/kvm/arm.c     |  6 ++--
 include/kvm/arm_vgic.h |  4 +--
 virt/kvm/arm/vgic.c    | 77 +++++++++++++++++++++-----------------------------
 3 files changed, 37 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index da87c07d857..fa4b97c5746 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -428,11 +428,11 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.has_run_once = true;
 
 	/*
-	 * Initialize the VGIC before running a vcpu the first time on
-	 * this VM.
+	 * Map the VGIC hardware resources before running a vcpu the first
+	 * time on this VM.
 	 */
 	if (unlikely(!vgic_initialized(vcpu->kvm))) {
-		ret = kvm_vgic_init(vcpu->kvm);
+		ret = kvm_vgic_map_resources(vcpu->kvm);
 		if (ret)
 			return ret;
 	}
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 206dcc3b3f7..fe9783ba924 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -274,7 +274,7 @@ struct kvm_exit_mmio;
 #ifdef CONFIG_KVM_ARM_VGIC
 int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
 int kvm_vgic_hyp_init(void);
-int kvm_vgic_init(struct kvm *kvm);
+int kvm_vgic_map_resources(struct kvm *kvm);
 int kvm_vgic_create(struct kvm *kvm);
 void kvm_vgic_destroy(struct kvm *kvm);
 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
@@ -321,7 +321,7 @@ static inline int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr,
 	return -ENXIO;
 }
 
-static inline int kvm_vgic_init(struct kvm *kvm)
+static inline int kvm_vgic_map_resources(struct kvm *kvm)
 {
 	return 0;
 }
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 21e035cc546..1ce4e364c1e 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -91,6 +91,7 @@
 #define ACCESS_WRITE_VALUE	(3 << 1)
 #define ACCESS_WRITE_MASK(x)	((x) & (3 << 1))
 
+static int vgic_init(struct kvm *kvm);
 static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
 static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu);
 static void vgic_update_state(struct kvm *kvm);
@@ -1732,39 +1733,14 @@ static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
 
 	int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8;
 	vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
-	vgic_cpu->vgic_irq_lr_map = kzalloc(nr_irqs, GFP_KERNEL);
+	vgic_cpu->vgic_irq_lr_map = kmalloc(nr_irqs, GFP_KERNEL);
 
 	if (!vgic_cpu->pending_shared || !vgic_cpu->vgic_irq_lr_map) {
 		kvm_vgic_vcpu_destroy(vcpu);
 		return -ENOMEM;
 	}
 
-	return 0;
-}
-
-/**
- * kvm_vgic_vcpu_init - Initialize per-vcpu VGIC state
- * @vcpu: pointer to the vcpu struct
- *
- * Initialize the vgic_cpu struct and vgic_dist struct fields pertaining to
- * this vcpu and enable the VGIC for this VCPU
- */
-static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
-{
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	int i;
-
-	for (i = 0; i < dist->nr_irqs; i++) {
-		if (i < VGIC_NR_PPIS)
-			vgic_bitmap_set_irq_val(&dist->irq_enabled,
-						vcpu->vcpu_id, i, 1);
-		if (i < VGIC_NR_PRIVATE_IRQS)
-			vgic_bitmap_set_irq_val(&dist->irq_cfg,
-						vcpu->vcpu_id, i, VGIC_CFG_EDGE);
-
-		vgic_cpu->vgic_irq_lr_map[i] = LR_EMPTY;
-	}
+	memset(vgic_cpu->vgic_irq_lr_map, LR_EMPTY, nr_irqs);
 
 	/*
 	 * Store the number of LRs per vcpu, so we don't have to go
@@ -1773,7 +1749,7 @@ static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	 */
 	vgic_cpu->nr_lr = vgic->nr_lr;
 
-	vgic_enable(vcpu);
+	return 0;
 }
 
 void kvm_vgic_destroy(struct kvm *kvm)
@@ -1810,12 +1786,12 @@ void kvm_vgic_destroy(struct kvm *kvm)
  * Allocate and initialize the various data structures. Must be called
  * with kvm->lock held!
  */
-static int vgic_init_maps(struct kvm *kvm)
+static int vgic_init(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct kvm_vcpu *vcpu;
 	int nr_cpus, nr_irqs;
-	int ret, i;
+	int ret, i, vcpu_id;
 
 	if (dist->nr_cpus)	/* Already allocated */
 		return 0;
@@ -1865,16 +1841,28 @@ static int vgic_init_maps(struct kvm *kvm)
 	if (ret)
 		goto out;
 
-	kvm_for_each_vcpu(i, vcpu, kvm) {
+	for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i += 4)
+		vgic_set_target_reg(kvm, 0, i);
+
+	kvm_for_each_vcpu(vcpu_id, vcpu, kvm) {
 		ret = vgic_vcpu_init_maps(vcpu, nr_irqs);
 		if (ret) {
 			kvm_err("VGIC: Failed to allocate vcpu memory\n");
 			break;
 		}
-	}
 
-	for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i += 4)
-		vgic_set_target_reg(kvm, 0, i);
+		for (i = 0; i < dist->nr_irqs; i++) {
+			if (i < VGIC_NR_PPIS)
+				vgic_bitmap_set_irq_val(&dist->irq_enabled,
+							vcpu->vcpu_id, i, 1);
+			if (i < VGIC_NR_PRIVATE_IRQS)
+				vgic_bitmap_set_irq_val(&dist->irq_cfg,
+							vcpu->vcpu_id, i,
+							VGIC_CFG_EDGE);
+		}
+
+		vgic_enable(vcpu);
+	}
 
 out:
 	if (ret)
@@ -1884,18 +1872,16 @@ out:
 }
 
 /**
- * kvm_vgic_init - Initialize global VGIC state before running any VCPUs
+ * kvm_vgic_map_resources - Configure global VGIC state before running any VCPUs
  * @kvm: pointer to the kvm struct
  *
  * Map the virtual CPU interface into the VM before running any VCPUs.  We
  * can't do this at creation time, because user space must first set the
- * virtual CPU interface address in the guest physical address space.  Also
- * initialize the ITARGETSRn regs to 0 on the emulated distributor.
+ * virtual CPU interface address in the guest physical address space.
  */
-int kvm_vgic_init(struct kvm *kvm)
+int kvm_vgic_map_resources(struct kvm *kvm)
 {
-	struct kvm_vcpu *vcpu;
-	int ret = 0, i;
+	int ret = 0;
 
 	if (!irqchip_in_kernel(kvm))
 		return 0;
@@ -1912,7 +1898,11 @@ int kvm_vgic_init(struct kvm *kvm)
 		goto out;
 	}
 
-	ret = vgic_init_maps(kvm);
+	/*
+	 * Initialize the vgic if this hasn't already been done on demand by
+	 * accessing the vgic state from userspace.
+	 */
+	ret = vgic_init(kvm);
 	if (ret) {
 		kvm_err("Unable to allocate maps\n");
 		goto out;
@@ -1926,9 +1916,6 @@ int kvm_vgic_init(struct kvm *kvm)
 		goto out;
 	}
 
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_vgic_vcpu_init(vcpu);
-
 	kvm->arch.vgic.ready = true;
 out:
 	if (ret)
@@ -2173,7 +2160,7 @@ static int vgic_attr_regs_access(struct kvm_device *dev,
 
 	mutex_lock(&dev->kvm->lock);
 
-	ret = vgic_init_maps(dev->kvm);
+	ret = vgic_init(dev->kvm);
 	if (ret)
 		goto out;
 
-- 
cgit v1.2.3-70-g09d2


From c52edf5f8caff878afc93c1b1e9a3d9490a9932f Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Tue, 9 Dec 2014 14:28:09 +0100
Subject: arm/arm64: KVM: Rename vgic_initialized to vgic_ready

The vgic_initialized() macro currently returns the state of the
vgic->ready flag, which indicates if the vgic is ready to be used when
running a VM, not specifically if its internal state has been
initialized.

Rename the macro accordingly in preparation for a more nuanced
initialization flow.

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Eric Auger <eric.auger@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 arch/arm/kvm/arm.c     | 2 +-
 include/kvm/arm_vgic.h | 4 ++--
 virt/kvm/arm/vgic.c    | 6 +++---
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index fa4b97c5746..c5a05f2c28a 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -431,7 +431,7 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	 * Map the VGIC hardware resources before running a vcpu the first
 	 * time on this VM.
 	 */
-	if (unlikely(!vgic_initialized(vcpu->kvm))) {
+	if (unlikely(!vgic_ready(vcpu->kvm))) {
 		ret = kvm_vgic_map_resources(vcpu->kvm);
 		if (ret)
 			return ret;
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index fe9783ba924..3e262b9bbdd 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -287,7 +287,7 @@ bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		      struct kvm_exit_mmio *mmio);
 
 #define irqchip_in_kernel(k)	(!!((k)->arch.vgic.in_kernel))
-#define vgic_initialized(k)	((k)->arch.vgic.ready)
+#define vgic_ready(k)		((k)->arch.vgic.ready)
 
 int vgic_v2_probe(struct device_node *vgic_node,
 		  const struct vgic_ops **ops,
@@ -369,7 +369,7 @@ static inline int irqchip_in_kernel(struct kvm *kvm)
 	return 0;
 }
 
-static inline bool vgic_initialized(struct kvm *kvm)
+static inline bool vgic_ready(struct kvm *kvm)
 {
 	return true;
 }
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 1ce4e364c1e..4edb2572ea9 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1696,7 +1696,7 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
 {
 	int vcpu_id;
 
-	if (likely(vgic_initialized(kvm))) {
+	if (likely(vgic_ready(kvm))) {
 		vcpu_id = vgic_update_irq_pending(kvm, cpuid, irq_num, level);
 		if (vcpu_id >= 0)
 			/* kick the specified vcpu */
@@ -1888,7 +1888,7 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 
 	mutex_lock(&kvm->lock);
 
-	if (vgic_initialized(kvm))
+	if (vgic_ready(kvm))
 		goto out;
 
 	if (IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_dist_base) ||
@@ -2282,7 +2282,7 @@ static int vgic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 
 		mutex_lock(&dev->kvm->lock);
 
-		if (vgic_initialized(dev->kvm) || dev->kvm->arch.vgic.nr_irqs)
+		if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_irqs)
 			ret = -EBUSY;
 		else
 			dev->kvm->arch.vgic.nr_irqs = val;
-- 
cgit v1.2.3-70-g09d2


From 1f57be289571d514b9412da2af25a64a81b8dd89 Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Tue, 9 Dec 2014 14:30:36 +0100
Subject: arm/arm64: KVM: Add (new) vgic_initialized macro

Some code paths will need to check to see if the internal state of the
vgic has been initialized (such as when creating new VCPUs), so
introduce such a macro that checks the nr_cpus field which is set when
the vgic has been initialized.

Also set nr_cpus = 0 in kvm_vgic_destroy, because the error path in
vgic_init() will call this function, and code should never errornously
assume the vgic to be properly initialized after an error.

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Eric Auger <eric.auger@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 include/kvm/arm_vgic.h | 6 ++++++
 virt/kvm/arm/vgic.c    | 3 ++-
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 3e262b9bbdd..ac4888dc86b 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -287,6 +287,7 @@ bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		      struct kvm_exit_mmio *mmio);
 
 #define irqchip_in_kernel(k)	(!!((k)->arch.vgic.in_kernel))
+#define vgic_initialized(k)	(!!((k)->arch.vgic.nr_cpus))
 #define vgic_ready(k)		((k)->arch.vgic.ready)
 
 int vgic_v2_probe(struct device_node *vgic_node,
@@ -369,6 +370,11 @@ static inline int irqchip_in_kernel(struct kvm *kvm)
 	return 0;
 }
 
+static inline bool vgic_initialized(struct kvm *kvm)
+{
+	return true;
+}
+
 static inline bool vgic_ready(struct kvm *kvm)
 {
 	return true;
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 4edb2572ea9..d862ea50216 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1780,6 +1780,7 @@ void kvm_vgic_destroy(struct kvm *kvm)
 	dist->irq_spi_cpu = NULL;
 	dist->irq_spi_target = NULL;
 	dist->irq_pending_on_cpu = NULL;
+	dist->nr_cpus = 0;
 }
 
 /*
@@ -1793,7 +1794,7 @@ static int vgic_init(struct kvm *kvm)
 	int nr_cpus, nr_irqs;
 	int ret, i, vcpu_id;
 
-	if (dist->nr_cpus)	/* Already allocated */
+	if (vgic_initialized(kvm))
 		return 0;
 
 	nr_cpus = dist->nr_cpus = atomic_read(&kvm->online_vcpus);
-- 
cgit v1.2.3-70-g09d2


From 8b28f621bea6f84d44adf7e804b73aff1e09105b Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Fri, 12 Dec 2014 16:54:18 -0800
Subject: mm,fs: introduce helpers around the i_mmap_mutex

This series is a continuation of the conversion of the i_mmap_mutex to
rwsem, following what we have for the anon memory counterpart.  With
Hugh's feedback from the first iteration.

Ultimately, the most obvious paths that require exclusive ownership of the
lock is when we modify the VMA interval tree, via
vma_interval_tree_insert() and vma_interval_tree_remove() families.  Cases
such as unmapping, where the ptes content is changed but the tree remains
untouched should make it safe to share the i_mmap_rwsem.

As such, the code of course is straightforward, however the devil is very
much in the details.  While its been tested on a number of workloads
without anything exploding, I would not be surprised if there are some
less documented/known assumptions about the lock that could suffer from
these changes.  Or maybe I'm just missing something, but either way I
believe its at the point where it could use more eyes and hopefully some
time in linux-next.

Because the lock type conversion is the heart of this patchset,
its worth noting a few comparisons between mutex vs rwsem (xadd):

  (i) Same size, no extra footprint.

  (ii) Both have CONFIG_XXX_SPIN_ON_OWNER capabilities for
       exclusive lock ownership.

  (iii) Both can be slightly unfair wrt exclusive ownership, with
        writer lock stealing properties, not necessarily respecting
        FIFO order for granting the lock when contended.

  (iv) Mutexes can be slightly faster than rwsems when
       the lock is non-contended.

  (v) Both suck at performance for debug (slowpaths), which
      shouldn't matter anyway.

Sharing the lock is obviously beneficial, and sem writer ownership is
close enough to mutexes.  The biggest winner of these changes is
migration.

As for concrete numbers, the following performance results are for a
4-socket 60-core IvyBridge-EX with 130Gb of RAM.

Both alltests and disk (xfs+ramdisk) workloads of aim7 suite do quite well
with this set, with a steady ~60% throughput (jpm) increase for alltests
and up to ~30% for disk for high amounts of concurrency.  Lower counts of
workload users (< 100) does not show much difference at all, so at least
no regressions.

                    3.18-rc1            3.18-rc1-i_mmap_rwsem
alltests-100     17918.72 (  0.00%)    28417.97 ( 58.59%)
alltests-200     16529.39 (  0.00%)    26807.92 ( 62.18%)
alltests-300     16591.17 (  0.00%)    26878.08 ( 62.00%)
alltests-400     16490.37 (  0.00%)    26664.63 ( 61.70%)
alltests-500     16593.17 (  0.00%)    26433.72 ( 59.30%)
alltests-600     16508.56 (  0.00%)    26409.20 ( 59.97%)
alltests-700     16508.19 (  0.00%)    26298.58 ( 59.31%)
alltests-800     16437.58 (  0.00%)    26433.02 ( 60.81%)
alltests-900     16418.35 (  0.00%)    26241.61 ( 59.83%)
alltests-1000    16369.00 (  0.00%)    26195.76 ( 60.03%)
alltests-1100    16330.11 (  0.00%)    26133.46 ( 60.03%)
alltests-1200    16341.30 (  0.00%)    26084.03 ( 59.62%)
alltests-1300    16304.75 (  0.00%)    26024.74 ( 59.61%)
alltests-1400    16231.08 (  0.00%)    25952.35 ( 59.89%)
alltests-1500    16168.06 (  0.00%)    25850.58 ( 59.89%)
alltests-1600    16142.56 (  0.00%)    25767.42 ( 59.62%)
alltests-1700    16118.91 (  0.00%)    25689.58 ( 59.38%)
alltests-1800    16068.06 (  0.00%)    25599.71 ( 59.32%)
alltests-1900    16046.94 (  0.00%)    25525.92 ( 59.07%)
alltests-2000    16007.26 (  0.00%)    25513.07 ( 59.38%)

disk-100          7582.14 (  0.00%)     7257.48 ( -4.28%)
disk-200          6962.44 (  0.00%)     7109.15 (  2.11%)
disk-300          6435.93 (  0.00%)     6904.75 (  7.28%)
disk-400          6370.84 (  0.00%)     6861.26 (  7.70%)
disk-500          6353.42 (  0.00%)     6846.71 (  7.76%)
disk-600          6368.82 (  0.00%)     6806.75 (  6.88%)
disk-700          6331.37 (  0.00%)     6796.01 (  7.34%)
disk-800          6324.22 (  0.00%)     6788.00 (  7.33%)
disk-900          6253.52 (  0.00%)     6750.43 (  7.95%)
disk-1000         6242.53 (  0.00%)     6855.11 (  9.81%)
disk-1100         6234.75 (  0.00%)     6858.47 ( 10.00%)
disk-1200         6312.76 (  0.00%)     6845.13 (  8.43%)
disk-1300         6309.95 (  0.00%)     6834.51 (  8.31%)
disk-1400         6171.76 (  0.00%)     6787.09 (  9.97%)
disk-1500         6139.81 (  0.00%)     6761.09 ( 10.12%)
disk-1600         4807.12 (  0.00%)     6725.33 ( 39.90%)
disk-1700         4669.50 (  0.00%)     5985.38 ( 28.18%)
disk-1800         4663.51 (  0.00%)     5972.99 ( 28.08%)
disk-1900         4674.31 (  0.00%)     5949.94 ( 27.29%)
disk-2000         4668.36 (  0.00%)     5834.93 ( 24.99%)

In addition, a 67.5% increase in successfully migrated NUMA pages, thus
improving node locality.

The patch layout is simple but designed for bisection (in case reversion
is needed if the changes break upstream) and easier review:

o Patches 1-4 convert the i_mmap lock from mutex to rwsem.
o Patches 5-10 share the lock in specific paths, each patch
  details the rationale behind why it should be safe.

This patchset has been tested with: postgres 9.4 (with brand new hugetlb
support), hugetlbfs test suite (all tests pass, in fact more tests pass
with these changes than with an upstream kernel), ltp, aim7 benchmarks,
memcached and iozone with the -B option for mmap'ing.  *Untested* paths
are nommu, memory-failure, uprobes and xip.

This patch (of 8):

Various parts of the kernel acquire and release this mutex, so add
i_mmap_lock_write() and immap_unlock_write() helper functions that will
encapsulate this logic.  The next patch will make use of these.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: "Kirill A. Shutemov" <kirill@shutemov.name>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fs.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index bb29b02d9bb..bd0a1b2f3c0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -467,6 +467,16 @@ struct block_device {
 
 int mapping_tagged(struct address_space *mapping, int tag);
 
+static inline void i_mmap_lock_write(struct address_space *mapping)
+{
+	mutex_lock(&mapping->i_mmap_mutex);
+}
+
+static inline void i_mmap_unlock_write(struct address_space *mapping)
+{
+	mutex_unlock(&mapping->i_mmap_mutex);
+}
+
 /*
  * Might pages of this file be mapped into userspace?
  */
-- 
cgit v1.2.3-70-g09d2


From c8c06efa8b552608493b7066c234cfa82c47fcea Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Fri, 12 Dec 2014 16:54:24 -0800
Subject: mm: convert i_mmap_mutex to rwsem

The i_mmap_mutex is a close cousin of the anon vma lock, both protecting
similar data, one for file backed pages and the other for anon memory.  To
this end, this lock can also be a rwsem.  In addition, there are some
important opportunities to share the lock when there are no tree
modifications.

This conversion is straightforward.  For now, all users take the write
lock.

[sfr@canb.auug.org.au: update fremap.c]
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: "Kirill A. Shutemov" <kirill@shutemov.name>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/hugetlbfs/inode.c         | 10 +++++-----
 fs/inode.c                   |  2 +-
 include/linux/fs.h           |  7 ++++---
 include/linux/mmu_notifier.h |  2 +-
 kernel/events/uprobes.c      |  2 +-
 mm/filemap.c                 | 10 +++++-----
 mm/hugetlb.c                 | 10 +++++-----
 mm/mmap.c                    |  8 ++++----
 mm/mremap.c                  |  2 +-
 mm/rmap.c                    |  6 +++---
 10 files changed, 30 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a082709aa42..5eba47f593f 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -472,12 +472,12 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 }
 
 /*
- * Hugetlbfs is not reclaimable; therefore its i_mmap_mutex will never
+ * Hugetlbfs is not reclaimable; therefore its i_mmap_rwsem will never
  * be taken from reclaim -- unlike regular filesystems. This needs an
  * annotation because huge_pmd_share() does an allocation under
- * i_mmap_mutex.
+ * i_mmap_rwsem.
  */
-static struct lock_class_key hugetlbfs_i_mmap_mutex_key;
+static struct lock_class_key hugetlbfs_i_mmap_rwsem_key;
 
 static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 					struct inode *dir,
@@ -495,8 +495,8 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		struct hugetlbfs_inode_info *info;
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
-		lockdep_set_class(&inode->i_mapping->i_mmap_mutex,
-				&hugetlbfs_i_mmap_mutex_key);
+		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
+				&hugetlbfs_i_mmap_rwsem_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
 		inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
diff --git a/fs/inode.c b/fs/inode.c
index 2ed95f7caa4..ad60555b476 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -346,7 +346,7 @@ void address_space_init_once(struct address_space *mapping)
 	memset(mapping, 0, sizeof(*mapping));
 	INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
 	spin_lock_init(&mapping->tree_lock);
-	mutex_init(&mapping->i_mmap_mutex);
+	init_rwsem(&mapping->i_mmap_rwsem);
 	INIT_LIST_HEAD(&mapping->private_list);
 	spin_lock_init(&mapping->private_lock);
 	mapping->i_mmap = RB_ROOT;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bd0a1b2f3c0..6abcd0b72ae 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -18,6 +18,7 @@
 #include <linux/pid.h>
 #include <linux/bug.h>
 #include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/capability.h>
 #include <linux/semaphore.h>
 #include <linux/fiemap.h>
@@ -401,7 +402,7 @@ struct address_space {
 	atomic_t		i_mmap_writable;/* count VM_SHARED mappings */
 	struct rb_root		i_mmap;		/* tree of private and shared mappings */
 	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
-	struct mutex		i_mmap_mutex;	/* protect tree, count, list */
+	struct rw_semaphore	i_mmap_rwsem;	/* protect tree, count, list */
 	/* Protected by tree_lock together with the radix tree */
 	unsigned long		nrpages;	/* number of total pages */
 	unsigned long		nrshadows;	/* number of shadow entries */
@@ -469,12 +470,12 @@ int mapping_tagged(struct address_space *mapping, int tag);
 
 static inline void i_mmap_lock_write(struct address_space *mapping)
 {
-	mutex_lock(&mapping->i_mmap_mutex);
+	down_write(&mapping->i_mmap_rwsem);
 }
 
 static inline void i_mmap_unlock_write(struct address_space *mapping)
 {
-	mutex_unlock(&mapping->i_mmap_mutex);
+	up_write(&mapping->i_mmap_rwsem);
 }
 
 /*
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 88787bb4b3b..ab8564b0346 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -154,7 +154,7 @@ struct mmu_notifier_ops {
  * Therefore notifier chains can only be traversed when either
  *
  * 1. mmap_sem is held.
- * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->rwsem).
+ * 2. One of the reverse map locks is held (i_mmap_rwsem or anon_vma->rwsem).
  * 3. No other concurrent thread can access the list (release)
  */
 struct mmu_notifier {
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index aac81bf9df0..1901dbfa7ce 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -731,7 +731,7 @@ build_map_info(struct address_space *mapping, loff_t offset, bool is_register)
 
 		if (!prev && !more) {
 			/*
-			 * Needs GFP_NOWAIT to avoid i_mmap_mutex recursion through
+			 * Needs GFP_NOWAIT to avoid i_mmap_rwsem recursion through
 			 * reclaim. This is optimistic, no harm done if it fails.
 			 */
 			prev = kmalloc(sizeof(struct map_info),
diff --git a/mm/filemap.c b/mm/filemap.c
index 14b4642279f..e8905bc3cbd 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -62,16 +62,16 @@
 /*
  * Lock ordering:
  *
- *  ->i_mmap_mutex		(truncate_pagecache)
+ *  ->i_mmap_rwsem		(truncate_pagecache)
  *    ->private_lock		(__free_pte->__set_page_dirty_buffers)
  *      ->swap_lock		(exclusive_swap_page, others)
  *        ->mapping->tree_lock
  *
  *  ->i_mutex
- *    ->i_mmap_mutex		(truncate->unmap_mapping_range)
+ *    ->i_mmap_rwsem		(truncate->unmap_mapping_range)
  *
  *  ->mmap_sem
- *    ->i_mmap_mutex
+ *    ->i_mmap_rwsem
  *      ->page_table_lock or pte_lock	(various, mainly in memory.c)
  *        ->mapping->tree_lock	(arch-dependent flush_dcache_mmap_lock)
  *
@@ -85,7 +85,7 @@
  *    sb_lock			(fs/fs-writeback.c)
  *    ->mapping->tree_lock	(__sync_single_inode)
  *
- *  ->i_mmap_mutex
+ *  ->i_mmap_rwsem
  *    ->anon_vma.lock		(vma_adjust)
  *
  *  ->anon_vma.lock
@@ -105,7 +105,7 @@
  *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
  *
- * ->i_mmap_mutex
+ * ->i_mmap_rwsem
  *   ->tasklist_lock            (memory_failure, collect_procs_ao)
  */
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ffe19304cc0..989cb032eaf 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2726,9 +2726,9 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 	 * on its way out.  We're lucky that the flag has such an appropriate
 	 * name, and can in fact be safely cleared here. We could clear it
 	 * before the __unmap_hugepage_range above, but all that's necessary
-	 * is to clear it before releasing the i_mmap_mutex. This works
+	 * is to clear it before releasing the i_mmap_rwsem. This works
 	 * because in the context this is called, the VMA is about to be
-	 * destroyed and the i_mmap_mutex is held.
+	 * destroyed and the i_mmap_rwsem is held.
 	 */
 	vma->vm_flags &= ~VM_MAYSHARE;
 }
@@ -3370,9 +3370,9 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		spin_unlock(ptl);
 	}
 	/*
-	 * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare
+	 * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare
 	 * may have cleared our pud entry and done put_page on the page table:
-	 * once we release i_mmap_mutex, another task can do the final put_page
+	 * once we release i_mmap_rwsem, another task can do the final put_page
 	 * and that page table be reused and filled with junk.
 	 */
 	flush_tlb_range(vma, start, end);
@@ -3525,7 +3525,7 @@ static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
  * and returns the corresponding pte. While this is not necessary for the
  * !shared pmd case because we can allocate the pmd later as well, it makes the
  * code much cleaner. pmd allocation is essential for the shared case because
- * pud has to be populated inside the same i_mmap_mutex section - otherwise
+ * pud has to be populated inside the same i_mmap_rwsem section - otherwise
  * racing tasks could either miss the sharing (see huge_pte_offset) or select a
  * bad pmd for sharing.
  */
diff --git a/mm/mmap.c b/mm/mmap.c
index ecd6ecf4877..0d84b2f86f3 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -232,7 +232,7 @@ error:
 }
 
 /*
- * Requires inode->i_mapping->i_mmap_mutex
+ * Requires inode->i_mapping->i_mmap_rwsem
  */
 static void __remove_shared_vm_struct(struct vm_area_struct *vma,
 		struct file *file, struct address_space *mapping)
@@ -2791,7 +2791,7 @@ void exit_mmap(struct mm_struct *mm)
 
 /* Insert vm structure into process list sorted by address
  * and into the inode's i_mmap tree.  If vm_file is non-NULL
- * then i_mmap_mutex is taken here.
+ * then i_mmap_rwsem is taken here.
  */
 int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
 {
@@ -3086,7 +3086,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
 		 */
 		if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags))
 			BUG();
-		mutex_lock_nest_lock(&mapping->i_mmap_mutex, &mm->mmap_sem);
+		down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_sem);
 	}
 }
 
@@ -3113,7 +3113,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
  * vma in this mm is backed by the same anon_vma or address_space.
  *
  * We can take all the locks in random order because the VM code
- * taking i_mmap_mutex or anon_vma->rwsem outside the mmap_sem never
+ * taking i_mmap_rwsem or anon_vma->rwsem outside the mmap_sem never
  * takes more than one of them in a row. Secondly we're protected
  * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex.
  *
diff --git a/mm/mremap.c b/mm/mremap.c
index 426b448d644..84aa36f9f30 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -99,7 +99,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	spinlock_t *old_ptl, *new_ptl;
 
 	/*
-	 * When need_rmap_locks is true, we take the i_mmap_mutex and anon_vma
+	 * When need_rmap_locks is true, we take the i_mmap_rwsem and anon_vma
 	 * locks to ensure that rmap will always observe either the old or the
 	 * new ptes. This is the easiest way to avoid races with
 	 * truncate_pagecache(), page migration, etc...
diff --git a/mm/rmap.c b/mm/rmap.c
index bea03f6bec6..18247f89f1a 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -23,7 +23,7 @@
  * inode->i_mutex	(while writing or truncating, not reading or faulting)
  *   mm->mmap_sem
  *     page->flags PG_locked (lock_page)
- *       mapping->i_mmap_mutex
+ *       mapping->i_mmap_rwsem
  *         anon_vma->rwsem
  *           mm->page_table_lock or pte_lock
  *             zone->lru_lock (in mark_page_accessed, isolate_lru_page)
@@ -1260,7 +1260,7 @@ out_mlock:
 	/*
 	 * We need mmap_sem locking, Otherwise VM_LOCKED check makes
 	 * unstable result and race. Plus, We can't wait here because
-	 * we now hold anon_vma->rwsem or mapping->i_mmap_mutex.
+	 * we now hold anon_vma->rwsem or mapping->i_mmap_rwsem.
 	 * if trylock failed, the page remain in evictable lru and later
 	 * vmscan could retry to move the page to unevictable lru if the
 	 * page is actually mlocked.
@@ -1684,7 +1684,7 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
 	 * The page lock not only makes sure that page->mapping cannot
 	 * suddenly be NULLified by truncation, it makes sure that the
 	 * structure at mapping cannot be freed and reused yet,
-	 * so we can safely take mapping->i_mmap_mutex.
+	 * so we can safely take mapping->i_mmap_rwsem.
 	 */
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
-- 
cgit v1.2.3-70-g09d2


From 3dec0ba0be6a532cac949e02b853021bf6d57dad Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Fri, 12 Dec 2014 16:54:27 -0800
Subject: mm/rmap: share the i_mmap_rwsem

Similarly to the anon memory counterpart, we can share the mapping's lock
ownership as the interval tree is not modified when doing doing the walk,
only the file page.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: "Kirill A. Shutemov" <kirill@shutemov.name>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fs.h | 10 ++++++++++
 mm/rmap.c          |  6 +++---
 2 files changed, 13 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6abcd0b72ae..1d1838de688 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -478,6 +478,16 @@ static inline void i_mmap_unlock_write(struct address_space *mapping)
 	up_write(&mapping->i_mmap_rwsem);
 }
 
+static inline void i_mmap_lock_read(struct address_space *mapping)
+{
+	down_read(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_unlock_read(struct address_space *mapping)
+{
+	up_read(&mapping->i_mmap_rwsem);
+}
+
 /*
  * Might pages of this file be mapped into userspace?
  */
diff --git a/mm/rmap.c b/mm/rmap.c
index 18247f89f1a..14ad2b3b0f5 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1690,7 +1690,8 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
 
 	if (!mapping)
 		return ret;
-	i_mmap_lock_write(mapping);
+
+	i_mmap_lock_read(mapping);
 	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
 		unsigned long address = vma_address(page, vma);
 
@@ -1711,9 +1712,8 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
 		goto done;
 
 	ret = rwc->file_nonlinear(page, mapping, rwc->arg);
-
 done:
-	i_mmap_unlock_write(mapping);
+	i_mmap_unlock_read(mapping);
 	return ret;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 5e19b013f55a884c59a14391b22138899d1cc4cc Mon Sep 17 00:00:00 2001
From: Michal Nazarewicz <mina86@mina86.com>
Date: Fri, 12 Dec 2014 16:54:45 -0800
Subject: lib: bitmap: add alignment offset for bitmap_find_next_zero_area()

Add a bitmap_find_next_zero_area_off() function which works like
bitmap_find_next_zero_area() function except it allows an offset to be
specified when alignment is checked.  This lets caller request a bit such
that its number plus the offset is aligned according to the mask.

[gregory.0xf0@gmail.com: Retrieved from https://patchwork.linuxtv.org/patch/6254/ and updated documentation]
Signed-off-by: Michal Nazarewicz <mina86@mina86.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Gregory Fong <gregory.0xf0@gmail.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kukjin Kim <kgene.kim@samsung.com>
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Laura Abbott <lauraa@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bitmap.h | 36 +++++++++++++++++++++++++++++++-----
 lib/bitmap.c           | 24 +++++++++++++-----------
 2 files changed, 44 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index e1c8d080c42..34e020c2364 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -45,6 +45,7 @@
  * bitmap_set(dst, pos, nbits)			Set specified bit area
  * bitmap_clear(dst, pos, nbits)		Clear specified bit area
  * bitmap_find_next_zero_area(buf, len, pos, n, mask)	Find bit free area
+ * bitmap_find_next_zero_area_off(buf, len, pos, n, mask)	as above
  * bitmap_shift_right(dst, src, n, nbits)	*dst = *src >> n
  * bitmap_shift_left(dst, src, n, nbits)	*dst = *src << n
  * bitmap_remap(dst, src, old, new, nbits)	*dst = map(old, new)(src)
@@ -114,11 +115,36 @@ extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
 
 extern void bitmap_set(unsigned long *map, unsigned int start, int len);
 extern void bitmap_clear(unsigned long *map, unsigned int start, int len);
-extern unsigned long bitmap_find_next_zero_area(unsigned long *map,
-					 unsigned long size,
-					 unsigned long start,
-					 unsigned int nr,
-					 unsigned long align_mask);
+
+extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
+						    unsigned long size,
+						    unsigned long start,
+						    unsigned int nr,
+						    unsigned long align_mask,
+						    unsigned long align_offset);
+
+/**
+ * bitmap_find_next_zero_area - find a contiguous aligned zero area
+ * @map: The address to base the search on
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ * @nr: The number of zeroed bits we're looking for
+ * @align_mask: Alignment mask for zero area
+ *
+ * The @align_mask should be one less than a power of 2; the effect is that
+ * the bit offset of all zero areas this function finds is multiples of that
+ * power of 2. A @align_mask of 0 means no alignment is required.
+ */
+static inline unsigned long
+bitmap_find_next_zero_area(unsigned long *map,
+			   unsigned long size,
+			   unsigned long start,
+			   unsigned int nr,
+			   unsigned long align_mask)
+{
+	return bitmap_find_next_zero_area_off(map, size, start, nr,
+					      align_mask, 0);
+}
 
 extern int bitmap_scnprintf(char *buf, unsigned int len,
 			const unsigned long *src, int nbits);
diff --git a/lib/bitmap.c b/lib/bitmap.c
index b499ab6ada2..969ae8fbc85 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -326,30 +326,32 @@ void bitmap_clear(unsigned long *map, unsigned int start, int len)
 }
 EXPORT_SYMBOL(bitmap_clear);
 
-/*
- * bitmap_find_next_zero_area - find a contiguous aligned zero area
+/**
+ * bitmap_find_next_zero_area_off - find a contiguous aligned zero area
  * @map: The address to base the search on
  * @size: The bitmap size in bits
  * @start: The bitnumber to start searching at
  * @nr: The number of zeroed bits we're looking for
  * @align_mask: Alignment mask for zero area
+ * @align_offset: Alignment offset for zero area.
  *
  * The @align_mask should be one less than a power of 2; the effect is that
- * the bit offset of all zero areas this function finds is multiples of that
- * power of 2. A @align_mask of 0 means no alignment is required.
+ * the bit offset of all zero areas this function finds plus @align_offset
+ * is multiple of that power of 2.
  */
-unsigned long bitmap_find_next_zero_area(unsigned long *map,
-					 unsigned long size,
-					 unsigned long start,
-					 unsigned int nr,
-					 unsigned long align_mask)
+unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
+					     unsigned long size,
+					     unsigned long start,
+					     unsigned int nr,
+					     unsigned long align_mask,
+					     unsigned long align_offset)
 {
 	unsigned long index, end, i;
 again:
 	index = find_next_zero_bit(map, size, start);
 
 	/* Align allocation */
-	index = __ALIGN_MASK(index, align_mask);
+	index = __ALIGN_MASK(index + align_offset, align_mask) - align_offset;
 
 	end = index + nr;
 	if (end > size)
@@ -361,7 +363,7 @@ again:
 	}
 	return index;
 }
-EXPORT_SYMBOL(bitmap_find_next_zero_area);
+EXPORT_SYMBOL(bitmap_find_next_zero_area_off);
 
 /*
  * Bitmap printing & parsing functions: first version by Nadia Yvette Chambers,
-- 
cgit v1.2.3-70-g09d2


From 6f185c290edec576a2cccd6670e5b8e02e6f04db Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Fri, 12 Dec 2014 16:55:15 -0800
Subject: memcg: turn memcg_kmem_skip_account into a bit field

It isn't supposed to stack, so turn it into a bit-field to save 4 bytes on
the task_struct.

Also, remove the memcg_stop/resume_kmem_account helpers - it is clearer to
set/clear the flag inline.  Regarding the overwhelming comment to the
helpers, which is removed by this patch too, we already have a compact yet
accurate explanation in memcg_schedule_cache_create, no need in yet
another one.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched.h |  7 +++++--
 mm/memcontrol.c       | 35 ++---------------------------------
 2 files changed, 7 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 55f5ee7cc3d..4cfdbcf8cf5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1364,6 +1364,10 @@ struct task_struct {
 	unsigned sched_reset_on_fork:1;
 	unsigned sched_contributes_to_load:1;
 
+#ifdef CONFIG_MEMCG_KMEM
+	unsigned memcg_kmem_skip_account:1;
+#endif
+
 	unsigned long atomic_flags; /* Flags needing atomic access. */
 
 	pid_t pid;
@@ -1679,8 +1683,7 @@ struct task_struct {
 	/* bitmask and counter of trace recursion */
 	unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
-#ifdef CONFIG_MEMCG /* memcg uses this to do batch job */
-	unsigned int memcg_kmem_skip_account;
+#ifdef CONFIG_MEMCG
 	struct memcg_oom_info {
 		struct mem_cgroup *memcg;
 		gfp_t gfp_mask;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d9fab72da52..11cbfde4dc6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2673,37 +2673,6 @@ static void memcg_unregister_cache(struct kmem_cache *cachep)
 	css_put(&memcg->css);
 }
 
-/*
- * During the creation a new cache, we need to disable our accounting mechanism
- * altogether. This is true even if we are not creating, but rather just
- * enqueing new caches to be created.
- *
- * This is because that process will trigger allocations; some visible, like
- * explicit kmallocs to auxiliary data structures, name strings and internal
- * cache structures; some well concealed, like INIT_WORK() that can allocate
- * objects during debug.
- *
- * If any allocation happens during memcg_kmem_get_cache, we will recurse back
- * to it. This may not be a bounded recursion: since the first cache creation
- * failed to complete (waiting on the allocation), we'll just try to create the
- * cache again, failing at the same point.
- *
- * memcg_kmem_get_cache is prepared to abort after seeing a positive count of
- * memcg_kmem_skip_account. So we enclose anything that might allocate memory
- * inside the following two functions.
- */
-static inline void memcg_stop_kmem_account(void)
-{
-	VM_BUG_ON(!current->mm);
-	current->memcg_kmem_skip_account++;
-}
-
-static inline void memcg_resume_kmem_account(void)
-{
-	VM_BUG_ON(!current->mm);
-	current->memcg_kmem_skip_account--;
-}
-
 int __memcg_cleanup_cache_params(struct kmem_cache *s)
 {
 	struct kmem_cache *c;
@@ -2798,9 +2767,9 @@ static void memcg_schedule_register_cache(struct mem_cgroup *memcg,
 	 * this point we can't allow ourselves back into memcg_kmem_get_cache,
 	 * the safest choice is to do it like this, wrapping the whole function.
 	 */
-	memcg_stop_kmem_account();
+	current->memcg_kmem_skip_account = 1;
 	__memcg_schedule_register_cache(memcg, cachep);
-	memcg_resume_kmem_account();
+	current->memcg_kmem_skip_account = 0;
 }
 
 int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order)
-- 
cgit v1.2.3-70-g09d2


From bd6dace78b9e4595d29892f806514518449c7489 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 12 Dec 2014 16:55:35 -0800
Subject: mm: move swp_entry_t definition to include/linux/mm_types.h

swp_entry_t being defined in include/linux/swap.h instead of
include/linux/mm_types.h causes cyclic include dependency later when
include/linux/page_cgroup.h is included from writeback path.  Move the
definition to include/linux/mm_types.h.

While at it, reformat the comment above it.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm_types.h | 8 ++++++++
 include/linux/swap.h     | 8 --------
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bf9f57529dc..fc2daffa9db 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -534,4 +534,12 @@ enum tlb_flush_reason {
 	NR_TLB_FLUSH_REASONS,
 };
 
+ /*
+  * A swap entry has to fit into a "unsigned long", as the entry is hidden
+  * in the "index" field of the swapper address space.
+  */
+typedef struct {
+	unsigned long val;
+} swp_entry_t;
+
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 37a585beef5..34e8b60ab97 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -102,14 +102,6 @@ union swap_header {
 	} info;
 };
 
- /* A swap entry has to fit into a "unsigned long", as
-  * the entry is hidden in the "index" field of the
-  * swapper address space.
-  */
-typedef struct {
-	unsigned long val;
-} swp_entry_t;
-
 /*
  * current->reclaim_state points to one of these when a task is running
  * memory reclaim
-- 
cgit v1.2.3-70-g09d2


From 056b7ccef4bc670b1ed77181159c8228de0926ab Mon Sep 17 00:00:00 2001
From: Zhang Zhen <zhenzhang.zhang@huawei.com>
Date: Fri, 12 Dec 2014 16:55:38 -0800
Subject: mm/memcontrol.c: remove the unused arg in __memcg_kmem_get_cache()

The gfp was passed in but never used in this function.

Signed-off-by: Zhang Zhen <zhenzhang.zhang@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 4 ++--
 mm/memcontrol.c            | 3 +--
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6ea9f919e88..b74942a9e22 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -401,7 +401,7 @@ int memcg_cache_id(struct mem_cgroup *memcg);
 void memcg_update_array_size(int num_groups);
 
 struct kmem_cache *
-__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
+__memcg_kmem_get_cache(struct kmem_cache *cachep);
 
 int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order);
 void __memcg_uncharge_slab(struct kmem_cache *cachep, int order);
@@ -492,7 +492,7 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 	if (unlikely(fatal_signal_pending(current)))
 		return cachep;
 
-	return __memcg_kmem_get_cache(cachep, gfp);
+	return __memcg_kmem_get_cache(cachep);
 }
 #else
 #define for_each_memcg_cache_index(_idx)	\
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 11cbfde4dc6..c6ac50e7d1c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2804,8 +2804,7 @@ void __memcg_uncharge_slab(struct kmem_cache *cachep, int order)
  * Can't be called in interrupt context or from kernel threads.
  * This function needs to be called with rcu_read_lock() held.
  */
-struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep,
-					  gfp_t gfp)
+struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep)
 {
 	struct mem_cgroup *memcg;
 	struct kmem_cache *memcg_cachep;
-- 
cgit v1.2.3-70-g09d2


From 66f2ca7e3f59312888131546176b42d6e248558a Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Fri, 12 Dec 2014 16:55:41 -0800
Subject: include/linux/kmemleak.h: needs slab.h

include/linux/kmemleak.h: In function 'kmemleak_alloc_recursive':
include/linux/kmemleak.h:43: error: 'SLAB_NOLEAKTRACE' undeclared (first use in this function)

Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kmemleak.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index 057e9597101..e705467ddb4 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -21,6 +21,8 @@
 #ifndef __KMEMLEAK_H
 #define __KMEMLEAK_H
 
+#include <linux/slab.h>
+
 #ifdef CONFIG_DEBUG_KMEMLEAK
 
 extern void kmemleak_init(void) __ref;
-- 
cgit v1.2.3-70-g09d2


From 2d48366b3ff745729815c15077508f8d7722ec5f Mon Sep 17 00:00:00 2001
From: Jianyu Zhan <nasa4836@gmail.com>
Date: Fri, 12 Dec 2014 16:55:43 -0800
Subject: mm, gfp: escalatedly define GFP_HIGHUSER and GFP_HIGHUSER_MOVABLE

GFP_USER, GFP_HIGHUSER and GFP_HIGHUSER_MOVABLE are escalatedly confined
defined, also implied by their names:

GFP_USER                                  = GFP_USER
GFP_USER + __GFP_HIGHMEM                  = GFP_HIGHUSER
GFP_USER + __GFP_HIGHMEM + __GFP_MOVABLE  = GFP_HIGHUSER_MOVABLE

So just make GFP_HIGHUSER and GFP_HIGHUSER_MOVABLE escalatedly defined to
reflect this fact.  It also makes the definition clear and texturally warn
on any furture break-up of this escalated relastionship.

Signed-off-by: Jianyu Zhan <jianyu.zhan@emc.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 07d2699cdb5..b840e3b2770 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -110,11 +110,8 @@ struct vm_area_struct;
 #define GFP_TEMPORARY	(__GFP_WAIT | __GFP_IO | __GFP_FS | \
 			 __GFP_RECLAIMABLE)
 #define GFP_USER	(__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
-#define GFP_HIGHUSER	(__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL | \
-			 __GFP_HIGHMEM)
-#define GFP_HIGHUSER_MOVABLE	(__GFP_WAIT | __GFP_IO | __GFP_FS | \
-				 __GFP_HARDWALL | __GFP_HIGHMEM | \
-				 __GFP_MOVABLE)
+#define GFP_HIGHUSER	(GFP_USER | __GFP_HIGHMEM)
+#define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE)
 #define GFP_IOFS	(__GFP_IO | __GFP_FS)
 #define GFP_TRANSHUGE	(GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
 			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
-- 
cgit v1.2.3-70-g09d2


From eefa864b701d78dc9753c70a3540a2e9ae192595 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Fri, 12 Dec 2014 16:55:46 -0800
Subject: mm/page_ext: resurrect struct page extending code for debugging

When we debug something, we'd like to insert some information to every
page.  For this purpose, we sometimes modify struct page itself.  But,
this has drawbacks.  First, it requires re-compile.  This makes us
hesitate to use the powerful debug feature so development process is
slowed down.  And, second, sometimes it is impossible to rebuild the
kernel due to third party module dependency.  At third, system behaviour
would be largely different after re-compile, because it changes size of
struct page greatly and this structure is accessed by every part of
kernel.  Keeping this as it is would be better to reproduce errornous
situation.

This feature is intended to overcome above mentioned problems.  This
feature allocates memory for extended data per page in certain place
rather than the struct page itself.  This memory can be accessed by the
accessor functions provided by this code.  During the boot process, it
checks whether allocation of huge chunk of memory is needed or not.  If
not, it avoids allocating memory at all.  With this advantage, we can
include this feature into the kernel in default and can avoid rebuild and
solve related problems.

Until now, memcg uses this technique.  But, now, memcg decides to embed
their variable to struct page itself and it's code to extend struct page
has been removed.  I'd like to use this code to develop debug feature, so
this patch resurrect it.

To help these things to work well, this patch introduces two callbacks for
clients.  One is the need callback which is mandatory if user wants to
avoid useless memory allocation at boot-time.  The other is optional, init
callback, which is used to do proper initialization after memory is
allocated.  Detailed explanation about purpose of these functions is in
code comment.  Please refer it.

Others are completely same with previous extension code in memcg.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Dave Hansen <dave@sr71.net>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Jungsoo Son <jungsoo.son@lge.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h   |  12 ++
 include/linux/page_ext.h |  59 +++++++
 init/main.c              |   7 +
 mm/Kconfig.debug         |   9 ++
 mm/Makefile              |   1 +
 mm/page_alloc.c          |   2 +
 mm/page_ext.c            | 395 +++++++++++++++++++++++++++++++++++++++++++++++
 7 files changed, 485 insertions(+)
 create mode 100644 include/linux/page_ext.h
 create mode 100644 mm/page_ext.c

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3879d7664df..2f0856d14b2 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -722,6 +722,9 @@ typedef struct pglist_data {
 	int nr_zones;
 #ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
 	struct page *node_mem_map;
+#ifdef CONFIG_PAGE_EXTENSION
+	struct page_ext *node_page_ext;
+#endif
 #endif
 #ifndef CONFIG_NO_BOOTMEM
 	struct bootmem_data *bdata;
@@ -1075,6 +1078,7 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn)
 #define SECTION_ALIGN_DOWN(pfn)	((pfn) & PAGE_SECTION_MASK)
 
 struct page;
+struct page_ext;
 struct mem_section {
 	/*
 	 * This is, logically, a pointer to an array of struct
@@ -1092,6 +1096,14 @@ struct mem_section {
 
 	/* See declaration of similar field in struct zone */
 	unsigned long *pageblock_flags;
+#ifdef CONFIG_PAGE_EXTENSION
+	/*
+	 * If !SPARSEMEM, pgdat doesn't have page_ext pointer. We use
+	 * section. (see page_ext.h about this.)
+	 */
+	struct page_ext *page_ext;
+	unsigned long pad;
+#endif
 	/*
 	 * WARNING: mem_section must be a power-of-2 in size for the
 	 * calculation and use of SECTION_ROOT_MASK to make sense.
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
new file mode 100644
index 00000000000..2ccc8b414e5
--- /dev/null
+++ b/include/linux/page_ext.h
@@ -0,0 +1,59 @@
+#ifndef __LINUX_PAGE_EXT_H
+#define __LINUX_PAGE_EXT_H
+
+struct pglist_data;
+struct page_ext_operations {
+	bool (*need)(void);
+	void (*init)(void);
+};
+
+#ifdef CONFIG_PAGE_EXTENSION
+
+/*
+ * Page Extension can be considered as an extended mem_map.
+ * A page_ext page is associated with every page descriptor. The
+ * page_ext helps us add more information about the page.
+ * All page_ext are allocated at boot or memory hotplug event,
+ * then the page_ext for pfn always exists.
+ */
+struct page_ext {
+	unsigned long flags;
+};
+
+extern void pgdat_page_ext_init(struct pglist_data *pgdat);
+
+#ifdef CONFIG_SPARSEMEM
+static inline void page_ext_init_flatmem(void)
+{
+}
+extern void page_ext_init(void);
+#else
+extern void page_ext_init_flatmem(void);
+static inline void page_ext_init(void)
+{
+}
+#endif
+
+struct page_ext *lookup_page_ext(struct page *page);
+
+#else /* !CONFIG_PAGE_EXTENSION */
+struct page_ext;
+
+static inline void pgdat_page_ext_init(struct pglist_data *pgdat)
+{
+}
+
+static inline struct page_ext *lookup_page_ext(struct page *page)
+{
+	return NULL;
+}
+
+static inline void page_ext_init(void)
+{
+}
+
+static inline void page_ext_init_flatmem(void)
+{
+}
+#endif /* CONFIG_PAGE_EXTENSION */
+#endif /* __LINUX_PAGE_EXT_H */
diff --git a/init/main.c b/init/main.c
index ca380ec685d..ed7e7ad5fee 100644
--- a/init/main.c
+++ b/init/main.c
@@ -51,6 +51,7 @@
 #include <linux/mempolicy.h>
 #include <linux/key.h>
 #include <linux/buffer_head.h>
+#include <linux/page_ext.h>
 #include <linux/debug_locks.h>
 #include <linux/debugobjects.h>
 #include <linux/lockdep.h>
@@ -484,6 +485,11 @@ void __init __weak thread_info_cache_init(void)
  */
 static void __init mm_init(void)
 {
+	/*
+	 * page_ext requires contiguous pages,
+	 * bigger than MAX_ORDER unless SPARSEMEM.
+	 */
+	page_ext_init_flatmem();
 	mem_init();
 	kmem_cache_init();
 	percpu_init_late();
@@ -621,6 +627,7 @@ asmlinkage __visible void __init start_kernel(void)
 		initrd_start = 0;
 	}
 #endif
+	page_ext_init();
 	debug_objects_mem_init();
 	kmemleak_init();
 	setup_per_cpu_pageset();
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 4b2443254de..1ba81c7769f 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -1,3 +1,12 @@
+config PAGE_EXTENSION
+	bool "Extend memmap on extra space for more information on page"
+	---help---
+	  Extend memmap on extra space for more information on page. This
+	  could be used for debugging features that need to insert extra
+	  field for every page. This extension enables us to save memory
+	  by not allocating this extra memory according to boottime
+	  configuration.
+
 config DEBUG_PAGEALLOC
 	bool "Debug page memory allocations"
 	depends on DEBUG_KERNEL
diff --git a/mm/Makefile b/mm/Makefile
index b3c6ce932c6..580cd3f392a 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -71,3 +71,4 @@ obj-$(CONFIG_ZSMALLOC)	+= zsmalloc.o
 obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o
 obj-$(CONFIG_CMA)	+= cma.o
 obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o
+obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2e8b7f39605..b64666cf586 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -48,6 +48,7 @@
 #include <linux/backing-dev.h>
 #include <linux/fault-inject.h>
 #include <linux/page-isolation.h>
+#include <linux/page_ext.h>
 #include <linux/debugobjects.h>
 #include <linux/kmemleak.h>
 #include <linux/compaction.h>
@@ -4856,6 +4857,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 #endif
 	init_waitqueue_head(&pgdat->kswapd_wait);
 	init_waitqueue_head(&pgdat->pfmemalloc_wait);
+	pgdat_page_ext_init(pgdat);
 
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
diff --git a/mm/page_ext.c b/mm/page_ext.c
new file mode 100644
index 00000000000..514a3bccd63
--- /dev/null
+++ b/mm/page_ext.c
@@ -0,0 +1,395 @@
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/bootmem.h>
+#include <linux/page_ext.h>
+#include <linux/memory.h>
+#include <linux/vmalloc.h>
+#include <linux/kmemleak.h>
+
+/*
+ * struct page extension
+ *
+ * This is the feature to manage memory for extended data per page.
+ *
+ * Until now, we must modify struct page itself to store extra data per page.
+ * This requires rebuilding the kernel and it is really time consuming process.
+ * And, sometimes, rebuild is impossible due to third party module dependency.
+ * At last, enlarging struct page could cause un-wanted system behaviour change.
+ *
+ * This feature is intended to overcome above mentioned problems. This feature
+ * allocates memory for extended data per page in certain place rather than
+ * the struct page itself. This memory can be accessed by the accessor
+ * functions provided by this code. During the boot process, it checks whether
+ * allocation of huge chunk of memory is needed or not. If not, it avoids
+ * allocating memory at all. With this advantage, we can include this feature
+ * into the kernel in default and can avoid rebuild and solve related problems.
+ *
+ * To help these things to work well, there are two callbacks for clients. One
+ * is the need callback which is mandatory if user wants to avoid useless
+ * memory allocation at boot-time. The other is optional, init callback, which
+ * is used to do proper initialization after memory is allocated.
+ *
+ * The need callback is used to decide whether extended memory allocation is
+ * needed or not. Sometimes users want to deactivate some features in this
+ * boot and extra memory would be unneccessary. In this case, to avoid
+ * allocating huge chunk of memory, each clients represent their need of
+ * extra memory through the need callback. If one of the need callbacks
+ * returns true, it means that someone needs extra memory so that
+ * page extension core should allocates memory for page extension. If
+ * none of need callbacks return true, memory isn't needed at all in this boot
+ * and page extension core can skip to allocate memory. As result,
+ * none of memory is wasted.
+ *
+ * The init callback is used to do proper initialization after page extension
+ * is completely initialized. In sparse memory system, extra memory is
+ * allocated some time later than memmap is allocated. In other words, lifetime
+ * of memory for page extension isn't same with memmap for struct page.
+ * Therefore, clients can't store extra data until page extension is
+ * initialized, even if pages are allocated and used freely. This could
+ * cause inadequate state of extra data per page, so, to prevent it, client
+ * can utilize this callback to initialize the state of it correctly.
+ */
+
+static struct page_ext_operations *page_ext_ops[] = {
+};
+
+static unsigned long total_usage;
+
+static bool __init invoke_need_callbacks(void)
+{
+	int i;
+	int entries = ARRAY_SIZE(page_ext_ops);
+
+	for (i = 0; i < entries; i++) {
+		if (page_ext_ops[i]->need && page_ext_ops[i]->need())
+			return true;
+	}
+
+	return false;
+}
+
+static void __init invoke_init_callbacks(void)
+{
+	int i;
+	int entries = ARRAY_SIZE(page_ext_ops);
+
+	for (i = 0; i < entries; i++) {
+		if (page_ext_ops[i]->init)
+			page_ext_ops[i]->init();
+	}
+}
+
+#if !defined(CONFIG_SPARSEMEM)
+
+
+void __meminit pgdat_page_ext_init(struct pglist_data *pgdat)
+{
+	pgdat->node_page_ext = NULL;
+}
+
+struct page_ext *lookup_page_ext(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long offset;
+	struct page_ext *base;
+
+	base = NODE_DATA(page_to_nid(page))->node_page_ext;
+#ifdef CONFIG_DEBUG_VM
+	/*
+	 * The sanity checks the page allocator does upon freeing a
+	 * page can reach here before the page_ext arrays are
+	 * allocated when feeding a range of pages to the allocator
+	 * for the first time during bootup or memory hotplug.
+	 */
+	if (unlikely(!base))
+		return NULL;
+#endif
+	offset = pfn - round_down(node_start_pfn(page_to_nid(page)),
+					MAX_ORDER_NR_PAGES);
+	return base + offset;
+}
+
+static int __init alloc_node_page_ext(int nid)
+{
+	struct page_ext *base;
+	unsigned long table_size;
+	unsigned long nr_pages;
+
+	nr_pages = NODE_DATA(nid)->node_spanned_pages;
+	if (!nr_pages)
+		return 0;
+
+	/*
+	 * Need extra space if node range is not aligned with
+	 * MAX_ORDER_NR_PAGES. When page allocator's buddy algorithm
+	 * checks buddy's status, range could be out of exact node range.
+	 */
+	if (!IS_ALIGNED(node_start_pfn(nid), MAX_ORDER_NR_PAGES) ||
+		!IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES))
+		nr_pages += MAX_ORDER_NR_PAGES;
+
+	table_size = sizeof(struct page_ext) * nr_pages;
+
+	base = memblock_virt_alloc_try_nid_nopanic(
+			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
+			BOOTMEM_ALLOC_ACCESSIBLE, nid);
+	if (!base)
+		return -ENOMEM;
+	NODE_DATA(nid)->node_page_ext = base;
+	total_usage += table_size;
+	return 0;
+}
+
+void __init page_ext_init_flatmem(void)
+{
+
+	int nid, fail;
+
+	if (!invoke_need_callbacks())
+		return;
+
+	for_each_online_node(nid)  {
+		fail = alloc_node_page_ext(nid);
+		if (fail)
+			goto fail;
+	}
+	pr_info("allocated %ld bytes of page_ext\n", total_usage);
+	invoke_init_callbacks();
+	return;
+
+fail:
+	pr_crit("allocation of page_ext failed.\n");
+	panic("Out of memory");
+}
+
+#else /* CONFIG_FLAT_NODE_MEM_MAP */
+
+struct page_ext *lookup_page_ext(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+	struct mem_section *section = __pfn_to_section(pfn);
+#ifdef CONFIG_DEBUG_VM
+	/*
+	 * The sanity checks the page allocator does upon freeing a
+	 * page can reach here before the page_ext arrays are
+	 * allocated when feeding a range of pages to the allocator
+	 * for the first time during bootup or memory hotplug.
+	 */
+	if (!section->page_ext)
+		return NULL;
+#endif
+	return section->page_ext + pfn;
+}
+
+static void *__meminit alloc_page_ext(size_t size, int nid)
+{
+	gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN;
+	void *addr = NULL;
+
+	addr = alloc_pages_exact_nid(nid, size, flags);
+	if (addr) {
+		kmemleak_alloc(addr, size, 1, flags);
+		return addr;
+	}
+
+	if (node_state(nid, N_HIGH_MEMORY))
+		addr = vzalloc_node(size, nid);
+	else
+		addr = vzalloc(size);
+
+	return addr;
+}
+
+static int __meminit init_section_page_ext(unsigned long pfn, int nid)
+{
+	struct mem_section *section;
+	struct page_ext *base;
+	unsigned long table_size;
+
+	section = __pfn_to_section(pfn);
+
+	if (section->page_ext)
+		return 0;
+
+	table_size = sizeof(struct page_ext) * PAGES_PER_SECTION;
+	base = alloc_page_ext(table_size, nid);
+
+	/*
+	 * The value stored in section->page_ext is (base - pfn)
+	 * and it does not point to the memory block allocated above,
+	 * causing kmemleak false positives.
+	 */
+	kmemleak_not_leak(base);
+
+	if (!base) {
+		pr_err("page ext allocation failure\n");
+		return -ENOMEM;
+	}
+
+	/*
+	 * The passed "pfn" may not be aligned to SECTION.  For the calculation
+	 * we need to apply a mask.
+	 */
+	pfn &= PAGE_SECTION_MASK;
+	section->page_ext = base - pfn;
+	total_usage += table_size;
+	return 0;
+}
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void free_page_ext(void *addr)
+{
+	if (is_vmalloc_addr(addr)) {
+		vfree(addr);
+	} else {
+		struct page *page = virt_to_page(addr);
+		size_t table_size;
+
+		table_size = sizeof(struct page_ext) * PAGES_PER_SECTION;
+
+		BUG_ON(PageReserved(page));
+		free_pages_exact(addr, table_size);
+	}
+}
+
+static void __free_page_ext(unsigned long pfn)
+{
+	struct mem_section *ms;
+	struct page_ext *base;
+
+	ms = __pfn_to_section(pfn);
+	if (!ms || !ms->page_ext)
+		return;
+	base = ms->page_ext + pfn;
+	free_page_ext(base);
+	ms->page_ext = NULL;
+}
+
+static int __meminit online_page_ext(unsigned long start_pfn,
+				unsigned long nr_pages,
+				int nid)
+{
+	unsigned long start, end, pfn;
+	int fail = 0;
+
+	start = SECTION_ALIGN_DOWN(start_pfn);
+	end = SECTION_ALIGN_UP(start_pfn + nr_pages);
+
+	if (nid == -1) {
+		/*
+		 * In this case, "nid" already exists and contains valid memory.
+		 * "start_pfn" passed to us is a pfn which is an arg for
+		 * online__pages(), and start_pfn should exist.
+		 */
+		nid = pfn_to_nid(start_pfn);
+		VM_BUG_ON(!node_state(nid, N_ONLINE));
+	}
+
+	for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
+		if (!pfn_present(pfn))
+			continue;
+		fail = init_section_page_ext(pfn, nid);
+	}
+	if (!fail)
+		return 0;
+
+	/* rollback */
+	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
+		__free_page_ext(pfn);
+
+	return -ENOMEM;
+}
+
+static int __meminit offline_page_ext(unsigned long start_pfn,
+				unsigned long nr_pages, int nid)
+{
+	unsigned long start, end, pfn;
+
+	start = SECTION_ALIGN_DOWN(start_pfn);
+	end = SECTION_ALIGN_UP(start_pfn + nr_pages);
+
+	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
+		__free_page_ext(pfn);
+	return 0;
+
+}
+
+static int __meminit page_ext_callback(struct notifier_block *self,
+			       unsigned long action, void *arg)
+{
+	struct memory_notify *mn = arg;
+	int ret = 0;
+
+	switch (action) {
+	case MEM_GOING_ONLINE:
+		ret = online_page_ext(mn->start_pfn,
+				   mn->nr_pages, mn->status_change_nid);
+		break;
+	case MEM_OFFLINE:
+		offline_page_ext(mn->start_pfn,
+				mn->nr_pages, mn->status_change_nid);
+		break;
+	case MEM_CANCEL_ONLINE:
+		offline_page_ext(mn->start_pfn,
+				mn->nr_pages, mn->status_change_nid);
+		break;
+	case MEM_GOING_OFFLINE:
+		break;
+	case MEM_ONLINE:
+	case MEM_CANCEL_OFFLINE:
+		break;
+	}
+
+	return notifier_from_errno(ret);
+}
+
+#endif
+
+void __init page_ext_init(void)
+{
+	unsigned long pfn;
+	int nid;
+
+	if (!invoke_need_callbacks())
+		return;
+
+	for_each_node_state(nid, N_MEMORY) {
+		unsigned long start_pfn, end_pfn;
+
+		start_pfn = node_start_pfn(nid);
+		end_pfn = node_end_pfn(nid);
+		/*
+		 * start_pfn and end_pfn may not be aligned to SECTION and the
+		 * page->flags of out of node pages are not initialized.  So we
+		 * scan [start_pfn, the biggest section's pfn < end_pfn) here.
+		 */
+		for (pfn = start_pfn; pfn < end_pfn;
+			pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) {
+
+			if (!pfn_valid(pfn))
+				continue;
+			/*
+			 * Nodes's pfns can be overlapping.
+			 * We know some arch can have a nodes layout such as
+			 * -------------pfn-------------->
+			 * N0 | N1 | N2 | N0 | N1 | N2|....
+			 */
+			if (pfn_to_nid(pfn) != nid)
+				continue;
+			if (init_section_page_ext(pfn, nid))
+				goto oom;
+		}
+	}
+	hotplug_memory_notifier(page_ext_callback, 0);
+	pr_info("allocated %ld bytes of page_ext\n", total_usage);
+	invoke_init_callbacks();
+	return;
+
+oom:
+	panic("Out of memory");
+}
+
+void __meminit pgdat_page_ext_init(struct pglist_data *pgdat)
+{
+}
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From e30825f1869a75b29a69dc8e0aaaaccc492092cf Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Fri, 12 Dec 2014 16:55:49 -0800
Subject: mm/debug-pagealloc: prepare boottime configurable on/off

Until now, debug-pagealloc needs extra flags in struct page, so we need to
recompile whole source code when we decide to use it.  This is really
painful, because it takes some time to recompile and sometimes rebuild is
not possible due to third party module depending on struct page.  So, we
can't use this good feature in many cases.

Now, we have the page extension feature that allows us to insert extra
flags to outside of struct page.  This gets rid of third party module
issue mentioned above.  And, this allows us to determine if we need extra
memory for this page extension in boottime.  With these property, we can
avoid using debug-pagealloc in boottime with low computational overhead in
the kernel built with CONFIG_DEBUG_PAGEALLOC.  This will help our
development process greatly.

This patch is the preparation step to achive above goal.  debug-pagealloc
originally uses extra field of struct page, but, after this patch, it will
use field of struct page_ext.  Because memory for page_ext is allocated
later than initialization of page allocator in CONFIG_SPARSEMEM, we should
disable debug-pagealloc feature temporarily until initialization of
page_ext.  This patch implements this.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Dave Hansen <dave@sr71.net>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Jungsoo Son <jungsoo.son@lge.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h               | 19 ++++++++++++++++++-
 include/linux/mm_types.h         |  4 ----
 include/linux/page-debug-flags.h | 32 --------------------------------
 include/linux/page_ext.h         | 15 +++++++++++++++
 mm/Kconfig.debug                 |  1 +
 mm/debug-pagealloc.c             | 37 +++++++++++++++++++++++++++++++++----
 mm/page_alloc.c                  | 38 +++++++++++++++++++++++++++++++++++---
 mm/page_ext.c                    |  4 ++++
 8 files changed, 106 insertions(+), 44 deletions(-)
 delete mode 100644 include/linux/page-debug-flags.h

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3b337efbe53..66560f1a056 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -19,6 +19,7 @@
 #include <linux/bit_spinlock.h>
 #include <linux/shrinker.h>
 #include <linux/resource.h>
+#include <linux/page_ext.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -2155,20 +2156,36 @@ extern void copy_user_huge_page(struct page *dst, struct page *src,
 				unsigned int pages_per_huge_page);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
 
+extern struct page_ext_operations debug_guardpage_ops;
+extern struct page_ext_operations page_poisoning_ops;
+
 #ifdef CONFIG_DEBUG_PAGEALLOC
 extern unsigned int _debug_guardpage_minorder;
+extern bool _debug_guardpage_enabled;
 
 static inline unsigned int debug_guardpage_minorder(void)
 {
 	return _debug_guardpage_minorder;
 }
 
+static inline bool debug_guardpage_enabled(void)
+{
+	return _debug_guardpage_enabled;
+}
+
 static inline bool page_is_guard(struct page *page)
 {
-	return test_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+	struct page_ext *page_ext;
+
+	if (!debug_guardpage_enabled())
+		return false;
+
+	page_ext = lookup_page_ext(page);
+	return test_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
 }
 #else
 static inline unsigned int debug_guardpage_minorder(void) { return 0; }
+static inline bool debug_guardpage_enabled(void) { return false; }
 static inline bool page_is_guard(struct page *page) { return false; }
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index fc2daffa9db..6d34aa266a8 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -10,7 +10,6 @@
 #include <linux/rwsem.h>
 #include <linux/completion.h>
 #include <linux/cpumask.h>
-#include <linux/page-debug-flags.h>
 #include <linux/uprobes.h>
 #include <linux/page-flags-layout.h>
 #include <asm/page.h>
@@ -186,9 +185,6 @@ struct page {
 	void *virtual;			/* Kernel virtual address (NULL if
 					   not kmapped, ie. highmem) */
 #endif /* WANT_PAGE_VIRTUAL */
-#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS
-	unsigned long debug_flags;	/* Use atomic bitops on this */
-#endif
 
 #ifdef CONFIG_KMEMCHECK
 	/*
diff --git a/include/linux/page-debug-flags.h b/include/linux/page-debug-flags.h
deleted file mode 100644
index 22691f61404..00000000000
--- a/include/linux/page-debug-flags.h
+++ /dev/null
@@ -1,32 +0,0 @@
-#ifndef LINUX_PAGE_DEBUG_FLAGS_H
-#define  LINUX_PAGE_DEBUG_FLAGS_H
-
-/*
- * page->debug_flags bits:
- *
- * PAGE_DEBUG_FLAG_POISON is set for poisoned pages. This is used to
- * implement generic debug pagealloc feature. The pages are filled with
- * poison patterns and set this flag after free_pages(). The poisoned
- * pages are verified whether the patterns are not corrupted and clear
- * the flag before alloc_pages().
- */
-
-enum page_debug_flags {
-	PAGE_DEBUG_FLAG_POISON,		/* Page is poisoned */
-	PAGE_DEBUG_FLAG_GUARD,
-};
-
-/*
- * Ensure that CONFIG_WANT_PAGE_DEBUG_FLAGS reliably
- * gets turned off when no debug features are enabling it!
- */
-
-#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS
-#if !defined(CONFIG_PAGE_POISONING) && \
-    !defined(CONFIG_PAGE_GUARD) \
-/* && !defined(CONFIG_PAGE_DEBUG_SOMETHING_ELSE) && ... */
-#error WANT_PAGE_DEBUG_FLAGS is turned on with no debug features!
-#endif
-#endif /* CONFIG_WANT_PAGE_DEBUG_FLAGS */
-
-#endif /* LINUX_PAGE_DEBUG_FLAGS_H */
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index 2ccc8b414e5..61c0f05f906 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -9,6 +9,21 @@ struct page_ext_operations {
 
 #ifdef CONFIG_PAGE_EXTENSION
 
+/*
+ * page_ext->flags bits:
+ *
+ * PAGE_EXT_DEBUG_POISON is set for poisoned pages. This is used to
+ * implement generic debug pagealloc feature. The pages are filled with
+ * poison patterns and set this flag after free_pages(). The poisoned
+ * pages are verified whether the patterns are not corrupted and clear
+ * the flag before alloc_pages().
+ */
+
+enum page_ext_flags {
+	PAGE_EXT_DEBUG_POISON,		/* Page is poisoned */
+	PAGE_EXT_DEBUG_GUARD,
+};
+
 /*
  * Page Extension can be considered as an extended mem_map.
  * A page_ext page is associated with every page descriptor. The
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 1ba81c7769f..56badfc4810 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -12,6 +12,7 @@ config DEBUG_PAGEALLOC
 	depends on DEBUG_KERNEL
 	depends on !HIBERNATION || ARCH_SUPPORTS_DEBUG_PAGEALLOC && !PPC && !SPARC
 	depends on !KMEMCHECK
+	select PAGE_EXTENSION
 	select PAGE_POISONING if !ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	select PAGE_GUARD if ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	---help---
diff --git a/mm/debug-pagealloc.c b/mm/debug-pagealloc.c
index 789ff70c8a4..0072f2c5333 100644
--- a/mm/debug-pagealloc.c
+++ b/mm/debug-pagealloc.c
@@ -2,23 +2,49 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
-#include <linux/page-debug-flags.h>
+#include <linux/page_ext.h>
 #include <linux/poison.h>
 #include <linux/ratelimit.h>
 
+static bool page_poisoning_enabled __read_mostly;
+
+static bool need_page_poisoning(void)
+{
+	return true;
+}
+
+static void init_page_poisoning(void)
+{
+	page_poisoning_enabled = true;
+}
+
+struct page_ext_operations page_poisoning_ops = {
+	.need = need_page_poisoning,
+	.init = init_page_poisoning,
+};
+
 static inline void set_page_poison(struct page *page)
 {
-	__set_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags);
+	struct page_ext *page_ext;
+
+	page_ext = lookup_page_ext(page);
+	__set_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
 }
 
 static inline void clear_page_poison(struct page *page)
 {
-	__clear_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags);
+	struct page_ext *page_ext;
+
+	page_ext = lookup_page_ext(page);
+	__clear_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
 }
 
 static inline bool page_poison(struct page *page)
 {
-	return test_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags);
+	struct page_ext *page_ext;
+
+	page_ext = lookup_page_ext(page);
+	return test_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
 }
 
 static void poison_page(struct page *page)
@@ -95,6 +121,9 @@ static void unpoison_pages(struct page *page, int n)
 
 void kernel_map_pages(struct page *page, int numpages, int enable)
 {
+	if (!page_poisoning_enabled)
+		return;
+
 	if (enable)
 		unpoison_pages(page, numpages);
 	else
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b64666cf586..e0a39d328ca 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -56,7 +56,7 @@
 #include <linux/prefetch.h>
 #include <linux/mm_inline.h>
 #include <linux/migrate.h>
-#include <linux/page-debug-flags.h>
+#include <linux/page_ext.h>
 #include <linux/hugetlb.h>
 #include <linux/sched/rt.h>
 
@@ -425,6 +425,22 @@ static inline void prep_zero_page(struct page *page, unsigned int order,
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 unsigned int _debug_guardpage_minorder;
+bool _debug_guardpage_enabled __read_mostly;
+
+static bool need_debug_guardpage(void)
+{
+	return true;
+}
+
+static void init_debug_guardpage(void)
+{
+	_debug_guardpage_enabled = true;
+}
+
+struct page_ext_operations debug_guardpage_ops = {
+	.need = need_debug_guardpage,
+	.init = init_debug_guardpage,
+};
 
 static int __init debug_guardpage_minorder_setup(char *buf)
 {
@@ -443,7 +459,14 @@ __setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup);
 static inline void set_page_guard(struct zone *zone, struct page *page,
 				unsigned int order, int migratetype)
 {
-	__set_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+	struct page_ext *page_ext;
+
+	if (!debug_guardpage_enabled())
+		return;
+
+	page_ext = lookup_page_ext(page);
+	__set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
+
 	INIT_LIST_HEAD(&page->lru);
 	set_page_private(page, order);
 	/* Guard pages are not available for any usage */
@@ -453,12 +476,20 @@ static inline void set_page_guard(struct zone *zone, struct page *page,
 static inline void clear_page_guard(struct zone *zone, struct page *page,
 				unsigned int order, int migratetype)
 {
-	__clear_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+	struct page_ext *page_ext;
+
+	if (!debug_guardpage_enabled())
+		return;
+
+	page_ext = lookup_page_ext(page);
+	__clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
+
 	set_page_private(page, 0);
 	if (!is_migrate_isolate(migratetype))
 		__mod_zone_freepage_state(zone, (1 << order), migratetype);
 }
 #else
+struct page_ext_operations debug_guardpage_ops = { NULL, };
 static inline void set_page_guard(struct zone *zone, struct page *page,
 				unsigned int order, int migratetype) {}
 static inline void clear_page_guard(struct zone *zone, struct page *page,
@@ -869,6 +900,7 @@ static inline void expand(struct zone *zone, struct page *page,
 		VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);
 
 		if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) &&
+			debug_guardpage_enabled() &&
 			high < debug_guardpage_minorder()) {
 			/*
 			 * Mark as guard pages (or page), that will allow to
diff --git a/mm/page_ext.c b/mm/page_ext.c
index 514a3bccd63..c2cd7b15f0d 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -51,6 +51,10 @@
  */
 
 static struct page_ext_operations *page_ext_ops[] = {
+	&debug_guardpage_ops,
+#ifdef CONFIG_PAGE_POISONING
+	&page_poisoning_ops,
+#endif
 };
 
 static unsigned long total_usage;
-- 
cgit v1.2.3-70-g09d2


From 031bc5743f158b2d5498294f489e534a31251626 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Fri, 12 Dec 2014 16:55:52 -0800
Subject: mm/debug-pagealloc: make debug-pagealloc boottime configurable

Now, we have prepared to avoid using debug-pagealloc in boottime.  So
introduce new kernel-parameter to disable debug-pagealloc in boottime, and
makes related functions to be disabled in this case.

Only non-intuitive part is change of guard page functions.  Because guard
page is effective only if debug-pagealloc is enabled, turning off
according to debug-pagealloc is reasonable thing to do.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Dave Hansen <dave@sr71.net>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Jungsoo Son <jungsoo.son@lge.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/kernel-parameters.txt |  9 +++++++++
 arch/powerpc/mm/hash_utils_64.c     |  2 +-
 arch/powerpc/mm/pgtable_32.c        |  2 +-
 arch/s390/mm/pageattr.c             |  2 +-
 arch/sparc/mm/init_64.c             |  2 +-
 arch/x86/mm/pageattr.c              |  2 +-
 include/linux/mm.h                  | 17 ++++++++++++++++-
 mm/debug-pagealloc.c                |  8 +++++++-
 mm/page_alloc.c                     | 20 ++++++++++++++++++++
 9 files changed, 57 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 24539d1c7d2..6f067954675 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -829,6 +829,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			CONFIG_DEBUG_PAGEALLOC, hence this option will not help
 			tracking down these problems.
 
+	debug_pagealloc=
+			[KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
+			parameter enables the feature at boot time. In
+			default, it is disabled. We can avoid allocating huge
+			chunk of memory for debug pagealloc if we don't enable
+			it at boot time and the system will work mostly same
+			with the kernel built without CONFIG_DEBUG_PAGEALLOC.
+			on: enable the feature
+
 	debugpat	[X86] Enable PAT debugging
 
 	decnet.addr=	[HW,NET]
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index e56a307bc67..2c2022d1605 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1514,7 +1514,7 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
 			       mmu_kernel_ssize, 0);
 }
 
-void kernel_map_pages(struct page *page, int numpages, int enable)
+void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	unsigned long flags, vaddr, lmi;
 	int i;
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index d545b123159..50fad3801f3 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -429,7 +429,7 @@ static int change_page_attr(struct page *page, int numpages, pgprot_t prot)
 }
 
 
-void kernel_map_pages(struct page *page, int numpages, int enable)
+void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (PageHighMem(page))
 		return;
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index 3fef3b29966..426c9d462d1 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -120,7 +120,7 @@ static void ipte_range(pte_t *pte, unsigned long address, int nr)
 	}
 }
 
-void kernel_map_pages(struct page *page, int numpages, int enable)
+void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	unsigned long address;
 	int nr, i, j;
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 2d91c62f7f5..3ea267c5332 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1621,7 +1621,7 @@ static void __init kernel_physical_mapping_init(void)
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-void kernel_map_pages(struct page *page, int numpages, int enable)
+void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	unsigned long phys_start = page_to_pfn(page) << PAGE_SHIFT;
 	unsigned long phys_end = phys_start + (numpages * PAGE_SIZE);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a3a5d46605d..dfaf2e0f5f8 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -1817,7 +1817,7 @@ static int __set_pages_np(struct page *page, int numpages)
 	return __change_page_attr_set_clr(&cpa, 0);
 }
 
-void kernel_map_pages(struct page *page, int numpages, int enable)
+void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (PageHighMem(page))
 		return;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 66560f1a056..8b8d77a1532 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2061,7 +2061,22 @@ static inline void vm_stat_account(struct mm_struct *mm,
 #endif /* CONFIG_PROC_FS */
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-extern void kernel_map_pages(struct page *page, int numpages, int enable);
+extern bool _debug_pagealloc_enabled;
+extern void __kernel_map_pages(struct page *page, int numpages, int enable);
+
+static inline bool debug_pagealloc_enabled(void)
+{
+	return _debug_pagealloc_enabled;
+}
+
+static inline void
+kernel_map_pages(struct page *page, int numpages, int enable)
+{
+	if (!debug_pagealloc_enabled())
+		return;
+
+	__kernel_map_pages(page, numpages, enable);
+}
 #ifdef CONFIG_HIBERNATION
 extern bool kernel_page_present(struct page *page);
 #endif /* CONFIG_HIBERNATION */
diff --git a/mm/debug-pagealloc.c b/mm/debug-pagealloc.c
index 0072f2c5333..5bf5906ce13 100644
--- a/mm/debug-pagealloc.c
+++ b/mm/debug-pagealloc.c
@@ -10,11 +10,17 @@ static bool page_poisoning_enabled __read_mostly;
 
 static bool need_page_poisoning(void)
 {
+	if (!debug_pagealloc_enabled())
+		return false;
+
 	return true;
 }
 
 static void init_page_poisoning(void)
 {
+	if (!debug_pagealloc_enabled())
+		return;
+
 	page_poisoning_enabled = true;
 }
 
@@ -119,7 +125,7 @@ static void unpoison_pages(struct page *page, int n)
 		unpoison_page(page + i);
 }
 
-void kernel_map_pages(struct page *page, int numpages, int enable)
+void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (!page_poisoning_enabled)
 		return;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e0a39d328ca..303d3851680 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -425,15 +425,35 @@ static inline void prep_zero_page(struct page *page, unsigned int order,
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 unsigned int _debug_guardpage_minorder;
+bool _debug_pagealloc_enabled __read_mostly;
 bool _debug_guardpage_enabled __read_mostly;
 
+static int __init early_debug_pagealloc(char *buf)
+{
+	if (!buf)
+		return -EINVAL;
+
+	if (strcmp(buf, "on") == 0)
+		_debug_pagealloc_enabled = true;
+
+	return 0;
+}
+early_param("debug_pagealloc", early_debug_pagealloc);
+
 static bool need_debug_guardpage(void)
 {
+	/* If we don't use debug_pagealloc, we don't need guard page */
+	if (!debug_pagealloc_enabled())
+		return false;
+
 	return true;
 }
 
 static void init_debug_guardpage(void)
 {
+	if (!debug_pagealloc_enabled())
+		return;
+
 	_debug_guardpage_enabled = true;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 9a92a6ce6f842713ccd0025c5228fe8bea61234c Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Fri, 12 Dec 2014 16:55:58 -0800
Subject: stacktrace: introduce snprint_stack_trace for buffer output

Current stacktrace only have the function for console output.  page_owner
that will be introduced in following patch needs to print the output of
stacktrace into the buffer for our own output format so so new function,
snprint_stack_trace(), is needed.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Dave Hansen <dave@sr71.net>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Jungsoo Son <jungsoo.son@lge.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/stacktrace.h |  5 +++++
 kernel/stacktrace.c        | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

(limited to 'include')

diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index 115b570e3bf..669045ab73f 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_STACKTRACE_H
 #define __LINUX_STACKTRACE_H
 
+#include <linux/types.h>
+
 struct task_struct;
 struct pt_regs;
 
@@ -20,6 +22,8 @@ extern void save_stack_trace_tsk(struct task_struct *tsk,
 				struct stack_trace *trace);
 
 extern void print_stack_trace(struct stack_trace *trace, int spaces);
+extern int snprint_stack_trace(char *buf, size_t size,
+			struct stack_trace *trace, int spaces);
 
 #ifdef CONFIG_USER_STACKTRACE_SUPPORT
 extern void save_stack_trace_user(struct stack_trace *trace);
@@ -32,6 +36,7 @@ extern void save_stack_trace_user(struct stack_trace *trace);
 # define save_stack_trace_tsk(tsk, trace)		do { } while (0)
 # define save_stack_trace_user(trace)			do { } while (0)
 # define print_stack_trace(trace, spaces)		do { } while (0)
+# define snprint_stack_trace(buf, size, trace, spaces)	do { } while (0)
 #endif
 
 #endif
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 00fe55cc5a8..b6e4c16377c 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -25,6 +25,38 @@ void print_stack_trace(struct stack_trace *trace, int spaces)
 }
 EXPORT_SYMBOL_GPL(print_stack_trace);
 
+int snprint_stack_trace(char *buf, size_t size,
+			struct stack_trace *trace, int spaces)
+{
+	int i;
+	unsigned long ip;
+	int generated;
+	int total = 0;
+
+	if (WARN_ON(!trace->entries))
+		return 0;
+
+	for (i = 0; i < trace->nr_entries; i++) {
+		ip = trace->entries[i];
+		generated = snprintf(buf, size, "%*c[<%p>] %pS\n",
+				1 + spaces, ' ', (void *) ip, (void *) ip);
+
+		total += generated;
+
+		/* Assume that generated isn't a negative number */
+		if (generated >= size) {
+			buf += size;
+			size = 0;
+		} else {
+			buf += generated;
+			size -= generated;
+		}
+	}
+
+	return total;
+}
+EXPORT_SYMBOL_GPL(snprint_stack_trace);
+
 /*
  * Architectures that do not implement save_stack_trace_tsk or
  * save_stack_trace_regs get this weak alias and a once-per-bootup warning
-- 
cgit v1.2.3-70-g09d2


From 48c96a3685795e52903e60c7ee115e5e22e7d640 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Fri, 12 Dec 2014 16:56:01 -0800
Subject: mm/page_owner: keep track of page owners

This is the page owner tracking code which is introduced so far ago.  It
is resident on Andrew's tree, though, nobody tried to upstream so it
remain as is.  Our company uses this feature actively to debug memory leak
or to find a memory hogger so I decide to upstream this feature.

This functionality help us to know who allocates the page.  When
allocating a page, we store some information about allocation in extra
memory.  Later, if we need to know status of all pages, we can get and
analyze it from this stored information.

In previous version of this feature, extra memory is statically defined in
struct page, but, in this version, extra memory is allocated outside of
struct page.  It enables us to turn on/off this feature at boottime
without considerable memory waste.

Although we already have tracepoint for tracing page allocation/free,
using it to analyze page owner is rather complex.  We need to enlarge the
trace buffer for preventing overlapping until userspace program launched.
And, launched program continually dump out the trace buffer for later
analysis and it would change system behaviour with more possibility rather
than just keeping it in memory, so bad for debug.

Moreover, we can use page_owner feature further for various purposes.  For
example, we can use it for fragmentation statistics implemented in this
patch.  And, I also plan to implement some CMA failure debugging feature
using this interface.

I'd like to give the credit for all developers contributed this feature,
but, it's not easy because I don't know exact history.  Sorry about that.
Below is people who has "Signed-off-by" in the patches in Andrew's tree.

Contributor:
Alexander Nyberg <alexn@dsv.su.se>
Mel Gorman <mgorman@suse.de>
Dave Hansen <dave@linux.vnet.ibm.com>
Minchan Kim <minchan@kernel.org>
Michal Nazarewicz <mina86@mina86.com>
Andrew Morton <akpm@linux-foundation.org>
Jungsoo Son <jungsoo.son@lge.com>

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Dave Hansen <dave@sr71.net>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Jungsoo Son <jungsoo.son@lge.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/kernel-parameters.txt |   6 +
 include/linux/page_ext.h            |  10 ++
 include/linux/page_owner.h          |  38 ++++++
 lib/Kconfig.debug                   |  16 +++
 mm/Makefile                         |   1 +
 mm/page_alloc.c                     |  11 +-
 mm/page_ext.c                       |   4 +
 mm/page_owner.c                     | 222 ++++++++++++++++++++++++++++++++++++
 mm/vmstat.c                         | 101 ++++++++++++++++
 tools/vm/Makefile                   |   4 +-
 tools/vm/page_owner_sort.c          | 144 +++++++++++++++++++++++
 11 files changed, 554 insertions(+), 3 deletions(-)
 create mode 100644 include/linux/page_owner.h
 create mode 100644 mm/page_owner.c
 create mode 100644 tools/vm/page_owner_sort.c

(limited to 'include')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 6f067954675..68153642c44 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2513,6 +2513,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	OSS		[HW,OSS]
 			See Documentation/sound/oss/oss-parameters.txt
 
+	page_owner=	[KNL] Boot-time page_owner enabling option.
+			Storage of the information about who allocated
+			each page is disabled in default. With this switch,
+			we can turn it on.
+			on: enable the feature
+
 	panic=		[KNL] Kernel behaviour on panic: delay <timeout>
 			timeout > 0: seconds before rebooting
 			timeout = 0: wait forever
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index 61c0f05f906..d2a2c84c72d 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -1,6 +1,9 @@
 #ifndef __LINUX_PAGE_EXT_H
 #define __LINUX_PAGE_EXT_H
 
+#include <linux/types.h>
+#include <linux/stacktrace.h>
+
 struct pglist_data;
 struct page_ext_operations {
 	bool (*need)(void);
@@ -22,6 +25,7 @@ struct page_ext_operations {
 enum page_ext_flags {
 	PAGE_EXT_DEBUG_POISON,		/* Page is poisoned */
 	PAGE_EXT_DEBUG_GUARD,
+	PAGE_EXT_OWNER,
 };
 
 /*
@@ -33,6 +37,12 @@ enum page_ext_flags {
  */
 struct page_ext {
 	unsigned long flags;
+#ifdef CONFIG_PAGE_OWNER
+	unsigned int order;
+	gfp_t gfp_mask;
+	struct stack_trace trace;
+	unsigned long trace_entries[8];
+#endif
 };
 
 extern void pgdat_page_ext_init(struct pglist_data *pgdat);
diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h
new file mode 100644
index 00000000000..b48c3471c25
--- /dev/null
+++ b/include/linux/page_owner.h
@@ -0,0 +1,38 @@
+#ifndef __LINUX_PAGE_OWNER_H
+#define __LINUX_PAGE_OWNER_H
+
+#ifdef CONFIG_PAGE_OWNER
+extern bool page_owner_inited;
+extern struct page_ext_operations page_owner_ops;
+
+extern void __reset_page_owner(struct page *page, unsigned int order);
+extern void __set_page_owner(struct page *page,
+			unsigned int order, gfp_t gfp_mask);
+
+static inline void reset_page_owner(struct page *page, unsigned int order)
+{
+	if (likely(!page_owner_inited))
+		return;
+
+	__reset_page_owner(page, order);
+}
+
+static inline void set_page_owner(struct page *page,
+			unsigned int order, gfp_t gfp_mask)
+{
+	if (likely(!page_owner_inited))
+		return;
+
+	__set_page_owner(page, order, gfp_mask);
+}
+#else
+static inline void reset_page_owner(struct page *page, unsigned int order)
+{
+}
+static inline void set_page_owner(struct page *page,
+			unsigned int order, gfp_t gfp_mask)
+{
+}
+
+#endif /* CONFIG_PAGE_OWNER */
+#endif /* __LINUX_PAGE_OWNER_H */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index d780351835e..5f2ce616c04 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -227,6 +227,22 @@ config UNUSED_SYMBOLS
 	  you really need it, and what the merge plan to the mainline kernel for
 	  your module is.
 
+config PAGE_OWNER
+	bool "Track page owner"
+	depends on DEBUG_KERNEL && STACKTRACE_SUPPORT
+	select DEBUG_FS
+	select STACKTRACE
+	select PAGE_EXTENSION
+	help
+	  This keeps track of what call chain is the owner of a page, may
+	  help to find bare alloc_page(s) leaks. Even if you include this
+	  feature on your build, it is disabled in default. You should pass
+	  "page_owner=on" to boot parameter in order to enable it. Eats
+	  a fair amount of memory if enabled. See tools/vm/page_owner_sort.c
+	  for user-space helper.
+
+	  If unsure, say N.
+
 config DEBUG_FS
 	bool "Debug Filesystem"
 	help
diff --git a/mm/Makefile b/mm/Makefile
index 580cd3f392a..4bf586e6637 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -63,6 +63,7 @@ obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
 obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
 obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
 obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
+obj-$(CONFIG_PAGE_OWNER) += page_owner.o
 obj-$(CONFIG_CLEANCACHE) += cleancache.o
 obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o
 obj-$(CONFIG_ZPOOL)	+= zpool.o
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 303d3851680..c13b6b29add 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -59,6 +59,7 @@
 #include <linux/page_ext.h>
 #include <linux/hugetlb.h>
 #include <linux/sched/rt.h>
+#include <linux/page_owner.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -813,6 +814,8 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
 	if (bad)
 		return false;
 
+	reset_page_owner(page, order);
+
 	if (!PageHighMem(page)) {
 		debug_check_no_locks_freed(page_address(page),
 					   PAGE_SIZE << order);
@@ -988,6 +991,8 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags)
 	if (order && (gfp_flags & __GFP_COMP))
 		prep_compound_page(page, order);
 
+	set_page_owner(page, order, gfp_flags);
+
 	return 0;
 }
 
@@ -1560,8 +1565,11 @@ void split_page(struct page *page, unsigned int order)
 		split_page(virt_to_page(page[0].shadow), order);
 #endif
 
-	for (i = 1; i < (1 << order); i++)
+	set_page_owner(page, 0, 0);
+	for (i = 1; i < (1 << order); i++) {
 		set_page_refcounted(page + i);
+		set_page_owner(page + i, 0, 0);
+	}
 }
 EXPORT_SYMBOL_GPL(split_page);
 
@@ -1601,6 +1609,7 @@ int __isolate_free_page(struct page *page, unsigned int order)
 		}
 	}
 
+	set_page_owner(page, order, 0);
 	return 1UL << order;
 }
 
diff --git a/mm/page_ext.c b/mm/page_ext.c
index c2cd7b15f0d..d86fd2f5353 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -5,6 +5,7 @@
 #include <linux/memory.h>
 #include <linux/vmalloc.h>
 #include <linux/kmemleak.h>
+#include <linux/page_owner.h>
 
 /*
  * struct page extension
@@ -55,6 +56,9 @@ static struct page_ext_operations *page_ext_ops[] = {
 #ifdef CONFIG_PAGE_POISONING
 	&page_poisoning_ops,
 #endif
+#ifdef CONFIG_PAGE_OWNER
+	&page_owner_ops,
+#endif
 };
 
 static unsigned long total_usage;
diff --git a/mm/page_owner.c b/mm/page_owner.c
new file mode 100644
index 00000000000..85eec7ea673
--- /dev/null
+++ b/mm/page_owner.c
@@ -0,0 +1,222 @@
+#include <linux/debugfs.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/bootmem.h>
+#include <linux/stacktrace.h>
+#include <linux/page_owner.h>
+#include "internal.h"
+
+static bool page_owner_disabled = true;
+bool page_owner_inited __read_mostly;
+
+static int early_page_owner_param(char *buf)
+{
+	if (!buf)
+		return -EINVAL;
+
+	if (strcmp(buf, "on") == 0)
+		page_owner_disabled = false;
+
+	return 0;
+}
+early_param("page_owner", early_page_owner_param);
+
+static bool need_page_owner(void)
+{
+	if (page_owner_disabled)
+		return false;
+
+	return true;
+}
+
+static void init_page_owner(void)
+{
+	if (page_owner_disabled)
+		return;
+
+	page_owner_inited = true;
+}
+
+struct page_ext_operations page_owner_ops = {
+	.need = need_page_owner,
+	.init = init_page_owner,
+};
+
+void __reset_page_owner(struct page *page, unsigned int order)
+{
+	int i;
+	struct page_ext *page_ext;
+
+	for (i = 0; i < (1 << order); i++) {
+		page_ext = lookup_page_ext(page + i);
+		__clear_bit(PAGE_EXT_OWNER, &page_ext->flags);
+	}
+}
+
+void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
+{
+	struct page_ext *page_ext;
+	struct stack_trace *trace;
+
+	page_ext = lookup_page_ext(page);
+
+	trace = &page_ext->trace;
+	trace->nr_entries = 0;
+	trace->max_entries = ARRAY_SIZE(page_ext->trace_entries);
+	trace->entries = &page_ext->trace_entries[0];
+	trace->skip = 3;
+	save_stack_trace(&page_ext->trace);
+
+	page_ext->order = order;
+	page_ext->gfp_mask = gfp_mask;
+
+	__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
+}
+
+static ssize_t
+print_page_owner(char __user *buf, size_t count, unsigned long pfn,
+		struct page *page, struct page_ext *page_ext)
+{
+	int ret;
+	int pageblock_mt, page_mt;
+	char *kbuf;
+
+	kbuf = kmalloc(count, GFP_KERNEL);
+	if (!kbuf)
+		return -ENOMEM;
+
+	ret = snprintf(kbuf, count,
+			"Page allocated via order %u, mask 0x%x\n",
+			page_ext->order, page_ext->gfp_mask);
+
+	if (ret >= count)
+		goto err;
+
+	/* Print information relevant to grouping pages by mobility */
+	pageblock_mt = get_pfnblock_migratetype(page, pfn);
+	page_mt  = gfpflags_to_migratetype(page_ext->gfp_mask);
+	ret += snprintf(kbuf + ret, count - ret,
+			"PFN %lu Block %lu type %d %s Flags %s%s%s%s%s%s%s%s%s%s%s%s\n",
+			pfn,
+			pfn >> pageblock_order,
+			pageblock_mt,
+			pageblock_mt != page_mt ? "Fallback" : "        ",
+			PageLocked(page)	? "K" : " ",
+			PageError(page)		? "E" : " ",
+			PageReferenced(page)	? "R" : " ",
+			PageUptodate(page)	? "U" : " ",
+			PageDirty(page)		? "D" : " ",
+			PageLRU(page)		? "L" : " ",
+			PageActive(page)	? "A" : " ",
+			PageSlab(page)		? "S" : " ",
+			PageWriteback(page)	? "W" : " ",
+			PageCompound(page)	? "C" : " ",
+			PageSwapCache(page)	? "B" : " ",
+			PageMappedToDisk(page)	? "M" : " ");
+
+	if (ret >= count)
+		goto err;
+
+	ret += snprint_stack_trace(kbuf + ret, count - ret,
+					&page_ext->trace, 0);
+	if (ret >= count)
+		goto err;
+
+	ret += snprintf(kbuf + ret, count - ret, "\n");
+	if (ret >= count)
+		goto err;
+
+	if (copy_to_user(buf, kbuf, ret))
+		ret = -EFAULT;
+
+	kfree(kbuf);
+	return ret;
+
+err:
+	kfree(kbuf);
+	return -ENOMEM;
+}
+
+static ssize_t
+read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	unsigned long pfn;
+	struct page *page;
+	struct page_ext *page_ext;
+
+	if (!page_owner_inited)
+		return -EINVAL;
+
+	page = NULL;
+	pfn = min_low_pfn + *ppos;
+
+	/* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */
+	while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0)
+		pfn++;
+
+	drain_all_pages(NULL);
+
+	/* Find an allocated page */
+	for (; pfn < max_pfn; pfn++) {
+		/*
+		 * If the new page is in a new MAX_ORDER_NR_PAGES area,
+		 * validate the area as existing, skip it if not
+		 */
+		if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) {
+			pfn += MAX_ORDER_NR_PAGES - 1;
+			continue;
+		}
+
+		/* Check for holes within a MAX_ORDER area */
+		if (!pfn_valid_within(pfn))
+			continue;
+
+		page = pfn_to_page(pfn);
+		if (PageBuddy(page)) {
+			unsigned long freepage_order = page_order_unsafe(page);
+
+			if (freepage_order < MAX_ORDER)
+				pfn += (1UL << freepage_order) - 1;
+			continue;
+		}
+
+		page_ext = lookup_page_ext(page);
+
+		/*
+		 * Pages allocated before initialization of page_owner are
+		 * non-buddy and have no page_owner info.
+		 */
+		if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
+			continue;
+
+		/* Record the next PFN to read in the file offset */
+		*ppos = (pfn - min_low_pfn) + 1;
+
+		return print_page_owner(buf, count, pfn, page, page_ext);
+	}
+
+	return 0;
+}
+
+static const struct file_operations proc_page_owner_operations = {
+	.read		= read_page_owner,
+};
+
+static int __init pageowner_init(void)
+{
+	struct dentry *dentry;
+
+	if (!page_owner_inited) {
+		pr_info("page_owner is disabled\n");
+		return 0;
+	}
+
+	dentry = debugfs_create_file("page_owner", S_IRUSR, NULL,
+			NULL, &proc_page_owner_operations);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	return 0;
+}
+module_init(pageowner_init)
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 1b12d390dc6..b090e9e3d62 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -22,6 +22,8 @@
 #include <linux/writeback.h>
 #include <linux/compaction.h>
 #include <linux/mm_inline.h>
+#include <linux/page_ext.h>
+#include <linux/page_owner.h>
 
 #include "internal.h"
 
@@ -1017,6 +1019,104 @@ static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg)
 	return 0;
 }
 
+#ifdef CONFIG_PAGE_OWNER
+static void pagetypeinfo_showmixedcount_print(struct seq_file *m,
+							pg_data_t *pgdat,
+							struct zone *zone)
+{
+	struct page *page;
+	struct page_ext *page_ext;
+	unsigned long pfn = zone->zone_start_pfn, block_end_pfn;
+	unsigned long end_pfn = pfn + zone->spanned_pages;
+	unsigned long count[MIGRATE_TYPES] = { 0, };
+	int pageblock_mt, page_mt;
+	int i;
+
+	/* Scan block by block. First and last block may be incomplete */
+	pfn = zone->zone_start_pfn;
+
+	/*
+	 * Walk the zone in pageblock_nr_pages steps. If a page block spans
+	 * a zone boundary, it will be double counted between zones. This does
+	 * not matter as the mixed block count will still be correct
+	 */
+	for (; pfn < end_pfn; ) {
+		if (!pfn_valid(pfn)) {
+			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
+			continue;
+		}
+
+		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
+		block_end_pfn = min(block_end_pfn, end_pfn);
+
+		page = pfn_to_page(pfn);
+		pageblock_mt = get_pfnblock_migratetype(page, pfn);
+
+		for (; pfn < block_end_pfn; pfn++) {
+			if (!pfn_valid_within(pfn))
+				continue;
+
+			page = pfn_to_page(pfn);
+			if (PageBuddy(page)) {
+				pfn += (1UL << page_order(page)) - 1;
+				continue;
+			}
+
+			if (PageReserved(page))
+				continue;
+
+			page_ext = lookup_page_ext(page);
+
+			if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
+				continue;
+
+			page_mt = gfpflags_to_migratetype(page_ext->gfp_mask);
+			if (pageblock_mt != page_mt) {
+				if (is_migrate_cma(pageblock_mt))
+					count[MIGRATE_MOVABLE]++;
+				else
+					count[pageblock_mt]++;
+
+				pfn = block_end_pfn;
+				break;
+			}
+			pfn += (1UL << page_ext->order) - 1;
+		}
+	}
+
+	/* Print counts */
+	seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
+	for (i = 0; i < MIGRATE_TYPES; i++)
+		seq_printf(m, "%12lu ", count[i]);
+	seq_putc(m, '\n');
+}
+#endif /* CONFIG_PAGE_OWNER */
+
+/*
+ * Print out the number of pageblocks for each migratetype that contain pages
+ * of other types. This gives an indication of how well fallbacks are being
+ * contained by rmqueue_fallback(). It requires information from PAGE_OWNER
+ * to determine what is going on
+ */
+static void pagetypeinfo_showmixedcount(struct seq_file *m, pg_data_t *pgdat)
+{
+#ifdef CONFIG_PAGE_OWNER
+	int mtype;
+
+	if (!page_owner_inited)
+		return;
+
+	drain_all_pages(NULL);
+
+	seq_printf(m, "\n%-23s", "Number of mixed blocks ");
+	for (mtype = 0; mtype < MIGRATE_TYPES; mtype++)
+		seq_printf(m, "%12s ", migratetype_names[mtype]);
+	seq_putc(m, '\n');
+
+	walk_zones_in_node(m, pgdat, pagetypeinfo_showmixedcount_print);
+#endif /* CONFIG_PAGE_OWNER */
+}
+
 /*
  * This prints out statistics in relation to grouping pages by mobility.
  * It is expensive to collect so do not constantly read the file.
@@ -1034,6 +1134,7 @@ static int pagetypeinfo_show(struct seq_file *m, void *arg)
 	seq_putc(m, '\n');
 	pagetypeinfo_showfree(m, pgdat);
 	pagetypeinfo_showblockcount(m, pgdat);
+	pagetypeinfo_showmixedcount(m, pgdat);
 
 	return 0;
 }
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
index 3d907dacf2a..ac884b65a07 100644
--- a/tools/vm/Makefile
+++ b/tools/vm/Makefile
@@ -1,6 +1,6 @@
 # Makefile for vm tools
 #
-TARGETS=page-types slabinfo
+TARGETS=page-types slabinfo page_owner_sort
 
 LIB_DIR = ../lib/api
 LIBS = $(LIB_DIR)/libapikfs.a
@@ -18,5 +18,5 @@ $(LIBS):
 	$(CC) $(CFLAGS) -o $@ $< $(LDFLAGS)
 
 clean:
-	$(RM) page-types slabinfo
+	$(RM) page-types slabinfo page_owner_sort
 	make -C $(LIB_DIR) clean
diff --git a/tools/vm/page_owner_sort.c b/tools/vm/page_owner_sort.c
new file mode 100644
index 00000000000..77147b42d59
--- /dev/null
+++ b/tools/vm/page_owner_sort.c
@@ -0,0 +1,144 @@
+/*
+ * User-space helper to sort the output of /sys/kernel/debug/page_owner
+ *
+ * Example use:
+ * cat /sys/kernel/debug/page_owner > page_owner_full.txt
+ * grep -v ^PFN page_owner_full.txt > page_owner.txt
+ * ./sort page_owner.txt sorted_page_owner.txt
+*/
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <string.h>
+
+struct block_list {
+	char *txt;
+	int len;
+	int num;
+};
+
+
+static struct block_list *list;
+static int list_size;
+static int max_size;
+
+struct block_list *block_head;
+
+int read_block(char *buf, int buf_size, FILE *fin)
+{
+	char *curr = buf, *const buf_end = buf + buf_size;
+
+	while (buf_end - curr > 1 && fgets(curr, buf_end - curr, fin)) {
+		if (*curr == '\n') /* empty line */
+			return curr - buf;
+		curr += strlen(curr);
+	}
+
+	return -1; /* EOF or no space left in buf. */
+}
+
+static int compare_txt(const void *p1, const void *p2)
+{
+	const struct block_list *l1 = p1, *l2 = p2;
+
+	return strcmp(l1->txt, l2->txt);
+}
+
+static int compare_num(const void *p1, const void *p2)
+{
+	const struct block_list *l1 = p1, *l2 = p2;
+
+	return l2->num - l1->num;
+}
+
+static void add_list(char *buf, int len)
+{
+	if (list_size != 0 &&
+	    len == list[list_size-1].len &&
+	    memcmp(buf, list[list_size-1].txt, len) == 0) {
+		list[list_size-1].num++;
+		return;
+	}
+	if (list_size == max_size) {
+		printf("max_size too small??\n");
+		exit(1);
+	}
+	list[list_size].txt = malloc(len+1);
+	list[list_size].len = len;
+	list[list_size].num = 1;
+	memcpy(list[list_size].txt, buf, len);
+	list[list_size].txt[len] = 0;
+	list_size++;
+	if (list_size % 1000 == 0) {
+		printf("loaded %d\r", list_size);
+		fflush(stdout);
+	}
+}
+
+#define BUF_SIZE	1024
+
+int main(int argc, char **argv)
+{
+	FILE *fin, *fout;
+	char buf[BUF_SIZE];
+	int ret, i, count;
+	struct block_list *list2;
+	struct stat st;
+
+	if (argc < 3) {
+		printf("Usage: ./program <input> <output>\n");
+		perror("open: ");
+		exit(1);
+	}
+
+	fin = fopen(argv[1], "r");
+	fout = fopen(argv[2], "w");
+	if (!fin || !fout) {
+		printf("Usage: ./program <input> <output>\n");
+		perror("open: ");
+		exit(1);
+	}
+
+	fstat(fileno(fin), &st);
+	max_size = st.st_size / 100; /* hack ... */
+
+	list = malloc(max_size * sizeof(*list));
+
+	for ( ; ; ) {
+		ret = read_block(buf, BUF_SIZE, fin);
+		if (ret < 0)
+			break;
+
+		add_list(buf, ret);
+	}
+
+	printf("loaded %d\n", list_size);
+
+	printf("sorting ....\n");
+
+	qsort(list, list_size, sizeof(list[0]), compare_txt);
+
+	list2 = malloc(sizeof(*list) * list_size);
+
+	printf("culling\n");
+
+	for (i = count = 0; i < list_size; i++) {
+		if (count == 0 ||
+		    strcmp(list2[count-1].txt, list[i].txt) != 0) {
+			list2[count++] = list[i];
+		} else {
+			list2[count-1].num += list[i].num;
+		}
+	}
+
+	qsort(list2, count, sizeof(list[0]), compare_num);
+
+	for (i = 0; i < count; i++)
+		fprintf(fout, "%d times:\n%s\n", list2[i].num, list2[i].txt);
+
+	return 0;
+}
-- 
cgit v1.2.3-70-g09d2


From f5f302e21257ebb0c074bbafc37606c26d28cc3d Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Fri, 12 Dec 2014 16:56:10 -0800
Subject: mm,vmacache: count number of system-wide flushes

These flushes deal with sequence number overflows, such as for long lived
threads.  These are rare, but interesting from a debugging PoV.  As such,
display the number of flushes when vmacache debugging is enabled.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vm_event_item.h | 1 +
 mm/vmacache.c                 | 2 ++
 mm/vmstat.c                   | 1 +
 3 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 730334cdf03..9246d32dc97 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -90,6 +90,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_DEBUG_VM_VMACACHE
 		VMACACHE_FIND_CALLS,
 		VMACACHE_FIND_HITS,
+		VMACACHE_FULL_FLUSHES,
 #endif
 		NR_VM_EVENT_ITEMS
 };
diff --git a/mm/vmacache.c b/mm/vmacache.c
index 9f25af825de..b6e3662fe33 100644
--- a/mm/vmacache.c
+++ b/mm/vmacache.c
@@ -17,6 +17,8 @@ void vmacache_flush_all(struct mm_struct *mm)
 {
 	struct task_struct *g, *p;
 
+	count_vm_vmacache_event(VMACACHE_FULL_FLUSHES);
+
 	/*
 	 * Single threaded tasks need not iterate the entire
 	 * list of process. We can avoid the flushing as well
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b090e9e3d62..1284f89fca0 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -900,6 +900,7 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_DEBUG_VM_VMACACHE
 	"vmacache_find_calls",
 	"vmacache_find_hits",
+	"vmacache_full_flushes",
 #endif
 #endif /* CONFIG_VM_EVENTS_COUNTERS */
 };
-- 
cgit v1.2.3-70-g09d2


From 6b4f7799c6a5703ac6b8c0649f4c22f00fa07513 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Fri, 12 Dec 2014 16:56:13 -0800
Subject: mm: vmscan: invoke slab shrinkers from shrink_zone()

The slab shrinkers are currently invoked from the zonelist walkers in
kswapd, direct reclaim, and zone reclaim, all of which roughly gauge the
eligible LRU pages and assemble a nodemask to pass to NUMA-aware
shrinkers, which then again have to walk over the nodemask.  This is
redundant code, extra runtime work, and fairly inaccurate when it comes to
the estimation of actually scannable LRU pages.  The code duplication will
only get worse when making the shrinkers cgroup-aware and requiring them
to have out-of-band cgroup hierarchy walks as well.

Instead, invoke the shrinkers from shrink_zone(), which is where all
reclaimers end up, to avoid this duplication.

Take the count for eligible LRU pages out of get_scan_count(), which
considers many more factors than just the availability of swap space, like
zone_reclaimable_pages() currently does.  Accumulate the number over all
visited lruvecs to get the per-zone value.

Some nodes have multiple zones due to memory addressing restrictions.  To
avoid putting too much pressure on the shrinkers, only invoke them once
for each such node, using the class zone of the allocation as the pivot
zone.

For now, this integrates the slab shrinking better into the reclaim logic
and gets rid of duplicative invocations from kswapd, direct reclaim, and
zone reclaim.  It also prepares for cgroup-awareness, allowing
memcg-capable shrinkers to be added at the lruvec level without much
duplication of both code and runtime work.

This changes kswapd behavior, which used to invoke the shrinkers for each
zone, but with scan ratios gathered from the entire node, resulting in
meaningless pressure quantities on multi-zone nodes.

Zone reclaim behavior also changes.  It used to shrink slabs until the
same amount of pages were shrunk as were reclaimed from the LRUs.  Now it
merely invokes the shrinkers once with the zone's scan ratio, which makes
the shrinkers go easier on caches that implement aging and would prefer
feeding back pressure from recently used slab objects to unused LRU pages.

[vdavydov@parallels.com: assure class zone is populated]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/staging/android/ashmem.c |   3 +-
 fs/drop_caches.c                 |  11 +-
 include/linux/mm.h               |   6 +-
 include/linux/shrinker.h         |   2 -
 mm/memory-failure.c              |  11 +-
 mm/page_alloc.c                  |   6 +-
 mm/vmscan.c                      | 216 ++++++++++++++++-----------------------
 7 files changed, 106 insertions(+), 149 deletions(-)

(limited to 'include')

diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index ad4f5790a76..46f8ef42559 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -418,7 +418,7 @@ out:
 }
 
 /*
- * ashmem_shrink - our cache shrinker, called from mm/vmscan.c :: shrink_slab
+ * ashmem_shrink - our cache shrinker, called from mm/vmscan.c
  *
  * 'nr_to_scan' is the number of objects to scan for freeing.
  *
@@ -785,7 +785,6 @@ static long ashmem_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 				.nr_to_scan = LONG_MAX,
 			};
 			ret = ashmem_shrink_count(&ashmem_shrinker, &sc);
-			nodes_setall(sc.nodes_to_scan);
 			ashmem_shrink_scan(&ashmem_shrinker, &sc);
 		}
 		break;
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 1de7294aad2..2bc2c87f35e 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -40,13 +40,14 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 static void drop_slab(void)
 {
 	int nr_objects;
-	struct shrink_control shrink = {
-		.gfp_mask = GFP_KERNEL,
-	};
 
-	nodes_setall(shrink.nodes_to_scan);
 	do {
-		nr_objects = shrink_slab(&shrink, 1000, 1000);
+		int nid;
+
+		nr_objects = 0;
+		for_each_online_node(nid)
+			nr_objects += shrink_node_slabs(GFP_KERNEL, nid,
+							1000, 1000);
 	} while (nr_objects > 10);
 }
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8b8d77a1532..c0a67b894c4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2110,9 +2110,9 @@ int drop_caches_sysctl_handler(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);
 #endif
 
-unsigned long shrink_slab(struct shrink_control *shrink,
-			  unsigned long nr_pages_scanned,
-			  unsigned long lru_pages);
+unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
+				unsigned long nr_scanned,
+				unsigned long nr_eligible);
 
 #ifndef CONFIG_MMU
 #define randomize_va_space 0
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 68c097077ef..f4aee75f00b 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -18,8 +18,6 @@ struct shrink_control {
 	 */
 	unsigned long nr_to_scan;
 
-	/* shrink from these nodes */
-	nodemask_t nodes_to_scan;
 	/* current node being shrunk (for NUMA aware shrinkers) */
 	int nid;
 };
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 6b94969d91c..feb803bf344 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -239,19 +239,14 @@ void shake_page(struct page *p, int access)
 	}
 
 	/*
-	 * Only call shrink_slab here (which would also shrink other caches) if
-	 * access is not potentially fatal.
+	 * Only call shrink_node_slabs here (which would also shrink
+	 * other caches) if access is not potentially fatal.
 	 */
 	if (access) {
 		int nr;
 		int nid = page_to_nid(p);
 		do {
-			struct shrink_control shrink = {
-				.gfp_mask = GFP_KERNEL,
-			};
-			node_set(nid, shrink.nodes_to_scan);
-
-			nr = shrink_slab(&shrink, 1000, 1000);
+			nr = shrink_node_slabs(GFP_KERNEL, nid, 1000, 1000);
 			if (page_count(p) == 1)
 				break;
 		} while (nr > 10);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c13b6b29add..9d387086229 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6284,9 +6284,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		if (!PageLRU(page))
 			found++;
 		/*
-		 * If there are RECLAIMABLE pages, we need to check it.
-		 * But now, memory offline itself doesn't call shrink_slab()
-		 * and it still to be fixed.
+		 * If there are RECLAIMABLE pages, we need to check
+		 * it.  But now, memory offline itself doesn't call
+		 * shrink_node_slabs() and it still to be fixed.
 		 */
 		/*
 		 * If the page is not RAM, page_count()should be 0.
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a384339bf71..bd9a72bc4a1 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -229,9 +229,10 @@ EXPORT_SYMBOL(unregister_shrinker);
 
 #define SHRINK_BATCH 128
 
-static unsigned long
-shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
-		 unsigned long nr_pages_scanned, unsigned long lru_pages)
+static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
+				  struct shrinker *shrinker,
+				  unsigned long nr_scanned,
+				  unsigned long nr_eligible)
 {
 	unsigned long freed = 0;
 	unsigned long long delta;
@@ -255,9 +256,9 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
 
 	total_scan = nr;
-	delta = (4 * nr_pages_scanned) / shrinker->seeks;
+	delta = (4 * nr_scanned) / shrinker->seeks;
 	delta *= freeable;
-	do_div(delta, lru_pages + 1);
+	do_div(delta, nr_eligible + 1);
 	total_scan += delta;
 	if (total_scan < 0) {
 		pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n",
@@ -289,8 +290,8 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 		total_scan = freeable * 2;
 
 	trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
-				nr_pages_scanned, lru_pages,
-				freeable, delta, total_scan);
+				   nr_scanned, nr_eligible,
+				   freeable, delta, total_scan);
 
 	/*
 	 * Normally, we should not scan less than batch_size objects in one
@@ -339,34 +340,37 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	return freed;
 }
 
-/*
- * Call the shrink functions to age shrinkable caches
- *
- * Here we assume it costs one seek to replace a lru page and that it also
- * takes a seek to recreate a cache object.  With this in mind we age equal
- * percentages of the lru and ageable caches.  This should balance the seeks
- * generated by these structures.
+/**
+ * shrink_node_slabs - shrink slab caches of a given node
+ * @gfp_mask: allocation context
+ * @nid: node whose slab caches to target
+ * @nr_scanned: pressure numerator
+ * @nr_eligible: pressure denominator
  *
- * If the vm encountered mapped pages on the LRU it increase the pressure on
- * slab to avoid swapping.
+ * Call the shrink functions to age shrinkable caches.
  *
- * We do weird things to avoid (scanned*seeks*entries) overflowing 32 bits.
+ * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set,
+ * unaware shrinkers will receive a node id of 0 instead.
  *
- * `lru_pages' represents the number of on-LRU pages in all the zones which
- * are eligible for the caller's allocation attempt.  It is used for balancing
- * slab reclaim versus page reclaim.
+ * @nr_scanned and @nr_eligible form a ratio that indicate how much of
+ * the available objects should be scanned.  Page reclaim for example
+ * passes the number of pages scanned and the number of pages on the
+ * LRU lists that it considered on @nid, plus a bias in @nr_scanned
+ * when it encountered mapped pages.  The ratio is further biased by
+ * the ->seeks setting of the shrink function, which indicates the
+ * cost to recreate an object relative to that of an LRU page.
  *
- * Returns the number of slab objects which we shrunk.
+ * Returns the number of reclaimed slab objects.
  */
-unsigned long shrink_slab(struct shrink_control *shrinkctl,
-			  unsigned long nr_pages_scanned,
-			  unsigned long lru_pages)
+unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
+				unsigned long nr_scanned,
+				unsigned long nr_eligible)
 {
 	struct shrinker *shrinker;
 	unsigned long freed = 0;
 
-	if (nr_pages_scanned == 0)
-		nr_pages_scanned = SWAP_CLUSTER_MAX;
+	if (nr_scanned == 0)
+		nr_scanned = SWAP_CLUSTER_MAX;
 
 	if (!down_read_trylock(&shrinker_rwsem)) {
 		/*
@@ -380,20 +384,17 @@ unsigned long shrink_slab(struct shrink_control *shrinkctl,
 	}
 
 	list_for_each_entry(shrinker, &shrinker_list, list) {
-		if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) {
-			shrinkctl->nid = 0;
-			freed += shrink_slab_node(shrinkctl, shrinker,
-					nr_pages_scanned, lru_pages);
-			continue;
-		}
+		struct shrink_control sc = {
+			.gfp_mask = gfp_mask,
+			.nid = nid,
+		};
 
-		for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
-			if (node_online(shrinkctl->nid))
-				freed += shrink_slab_node(shrinkctl, shrinker,
-						nr_pages_scanned, lru_pages);
+		if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
+			sc.nid = 0;
 
-		}
+		freed += shrink_slabs(&sc, shrinker, nr_scanned, nr_eligible);
 	}
+
 	up_read(&shrinker_rwsem);
 out:
 	cond_resched();
@@ -1876,7 +1877,8 @@ enum scan_balance {
  * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan
  */
 static void get_scan_count(struct lruvec *lruvec, int swappiness,
-			   struct scan_control *sc, unsigned long *nr)
+			   struct scan_control *sc, unsigned long *nr,
+			   unsigned long *lru_pages)
 {
 	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
 	u64 fraction[2];
@@ -2022,6 +2024,7 @@ out:
 	some_scanned = false;
 	/* Only use force_scan on second pass. */
 	for (pass = 0; !some_scanned && pass < 2; pass++) {
+		*lru_pages = 0;
 		for_each_evictable_lru(lru) {
 			int file = is_file_lru(lru);
 			unsigned long size;
@@ -2048,14 +2051,19 @@ out:
 			case SCAN_FILE:
 			case SCAN_ANON:
 				/* Scan one type exclusively */
-				if ((scan_balance == SCAN_FILE) != file)
+				if ((scan_balance == SCAN_FILE) != file) {
+					size = 0;
 					scan = 0;
+				}
 				break;
 			default:
 				/* Look ma, no brain */
 				BUG();
 			}
+
+			*lru_pages += size;
 			nr[lru] = scan;
+
 			/*
 			 * Skip the second pass and don't force_scan,
 			 * if we found something to scan.
@@ -2069,7 +2077,7 @@ out:
  * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
  */
 static void shrink_lruvec(struct lruvec *lruvec, int swappiness,
-			  struct scan_control *sc)
+			  struct scan_control *sc, unsigned long *lru_pages)
 {
 	unsigned long nr[NR_LRU_LISTS];
 	unsigned long targets[NR_LRU_LISTS];
@@ -2080,7 +2088,7 @@ static void shrink_lruvec(struct lruvec *lruvec, int swappiness,
 	struct blk_plug plug;
 	bool scan_adjusted;
 
-	get_scan_count(lruvec, swappiness, sc, nr);
+	get_scan_count(lruvec, swappiness, sc, nr, lru_pages);
 
 	/* Record the original scan target for proportional adjustments later */
 	memcpy(targets, nr, sizeof(nr));
@@ -2258,7 +2266,8 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	}
 }
 
-static bool shrink_zone(struct zone *zone, struct scan_control *sc)
+static bool shrink_zone(struct zone *zone, struct scan_control *sc,
+			bool is_classzone)
 {
 	unsigned long nr_reclaimed, nr_scanned;
 	bool reclaimable = false;
@@ -2269,6 +2278,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc)
 			.zone = zone,
 			.priority = sc->priority,
 		};
+		unsigned long zone_lru_pages = 0;
 		struct mem_cgroup *memcg;
 
 		nr_reclaimed = sc->nr_reclaimed;
@@ -2276,13 +2286,15 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc)
 
 		memcg = mem_cgroup_iter(root, NULL, &reclaim);
 		do {
+			unsigned long lru_pages;
 			struct lruvec *lruvec;
 			int swappiness;
 
 			lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 			swappiness = mem_cgroup_swappiness(memcg);
 
-			shrink_lruvec(lruvec, swappiness, sc);
+			shrink_lruvec(lruvec, swappiness, sc, &lru_pages);
+			zone_lru_pages += lru_pages;
 
 			/*
 			 * Direct reclaim and kswapd have to scan all memory
@@ -2302,6 +2314,25 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc)
 			memcg = mem_cgroup_iter(root, memcg, &reclaim);
 		} while (memcg);
 
+		/*
+		 * Shrink the slab caches in the same proportion that
+		 * the eligible LRU pages were scanned.
+		 */
+		if (global_reclaim(sc) && is_classzone) {
+			struct reclaim_state *reclaim_state;
+
+			shrink_node_slabs(sc->gfp_mask, zone_to_nid(zone),
+					  sc->nr_scanned - nr_scanned,
+					  zone_lru_pages);
+
+			reclaim_state = current->reclaim_state;
+			if (reclaim_state) {
+				sc->nr_reclaimed +=
+					reclaim_state->reclaimed_slab;
+				reclaim_state->reclaimed_slab = 0;
+			}
+		}
+
 		vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
 			   sc->nr_scanned - nr_scanned,
 			   sc->nr_reclaimed - nr_reclaimed);
@@ -2376,12 +2407,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 	struct zone *zone;
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
-	unsigned long lru_pages = 0;
-	struct reclaim_state *reclaim_state = current->reclaim_state;
 	gfp_t orig_mask;
-	struct shrink_control shrink = {
-		.gfp_mask = sc->gfp_mask,
-	};
 	enum zone_type requested_highidx = gfp_zone(sc->gfp_mask);
 	bool reclaimable = false;
 
@@ -2394,12 +2420,18 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 	if (buffer_heads_over_limit)
 		sc->gfp_mask |= __GFP_HIGHMEM;
 
-	nodes_clear(shrink.nodes_to_scan);
-
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
-					gfp_zone(sc->gfp_mask), sc->nodemask) {
+					requested_highidx, sc->nodemask) {
+		enum zone_type classzone_idx;
+
 		if (!populated_zone(zone))
 			continue;
+
+		classzone_idx = requested_highidx;
+		while (!populated_zone(zone->zone_pgdat->node_zones +
+							classzone_idx))
+			classzone_idx--;
+
 		/*
 		 * Take care memory controller reclaiming has small influence
 		 * to global LRU.
@@ -2409,9 +2441,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 						 GFP_KERNEL | __GFP_HARDWALL))
 				continue;
 
-			lru_pages += zone_reclaimable_pages(zone);
-			node_set(zone_to_nid(zone), shrink.nodes_to_scan);
-
 			if (sc->priority != DEF_PRIORITY &&
 			    !zone_reclaimable(zone))
 				continue;	/* Let kswapd poll it */
@@ -2450,7 +2479,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 			/* need some check for avoid more shrink_zone() */
 		}
 
-		if (shrink_zone(zone, sc))
+		if (shrink_zone(zone, sc, zone_idx(zone) == classzone_idx))
 			reclaimable = true;
 
 		if (global_reclaim(sc) &&
@@ -2458,20 +2487,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 			reclaimable = true;
 	}
 
-	/*
-	 * Don't shrink slabs when reclaiming memory from over limit cgroups
-	 * but do shrink slab at least once when aborting reclaim for
-	 * compaction to avoid unevenly scanning file/anon LRU pages over slab
-	 * pages.
-	 */
-	if (global_reclaim(sc)) {
-		shrink_slab(&shrink, sc->nr_scanned, lru_pages);
-		if (reclaim_state) {
-			sc->nr_reclaimed += reclaim_state->reclaimed_slab;
-			reclaim_state->reclaimed_slab = 0;
-		}
-	}
-
 	/*
 	 * Restore to original mask to avoid the impact on the caller if we
 	 * promoted it to __GFP_HIGHMEM.
@@ -2736,6 +2751,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
 	};
 	struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 	int swappiness = mem_cgroup_swappiness(memcg);
+	unsigned long lru_pages;
 
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
@@ -2751,7 +2767,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
 	 * will pick up pages from other mem cgroup's as well. We hack
 	 * the priority and make it zero.
 	 */
-	shrink_lruvec(lruvec, swappiness, &sc);
+	shrink_lruvec(lruvec, swappiness, &sc, &lru_pages);
 
 	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
 
@@ -2932,15 +2948,10 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 static bool kswapd_shrink_zone(struct zone *zone,
 			       int classzone_idx,
 			       struct scan_control *sc,
-			       unsigned long lru_pages,
 			       unsigned long *nr_attempted)
 {
 	int testorder = sc->order;
 	unsigned long balance_gap;
-	struct reclaim_state *reclaim_state = current->reclaim_state;
-	struct shrink_control shrink = {
-		.gfp_mask = sc->gfp_mask,
-	};
 	bool lowmem_pressure;
 
 	/* Reclaim above the high watermark. */
@@ -2975,13 +2986,7 @@ static bool kswapd_shrink_zone(struct zone *zone,
 						balance_gap, classzone_idx))
 		return true;
 
-	shrink_zone(zone, sc);
-	nodes_clear(shrink.nodes_to_scan);
-	node_set(zone_to_nid(zone), shrink.nodes_to_scan);
-
-	reclaim_state->reclaimed_slab = 0;
-	shrink_slab(&shrink, sc->nr_scanned, lru_pages);
-	sc->nr_reclaimed += reclaim_state->reclaimed_slab;
+	shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
 
 	/* Account for the number of pages attempted to reclaim */
 	*nr_attempted += sc->nr_to_reclaim;
@@ -3042,7 +3047,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 	count_vm_event(PAGEOUTRUN);
 
 	do {
-		unsigned long lru_pages = 0;
 		unsigned long nr_attempted = 0;
 		bool raise_priority = true;
 		bool pgdat_needs_compaction = (order > 0);
@@ -3102,8 +3106,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 			if (!populated_zone(zone))
 				continue;
 
-			lru_pages += zone_reclaimable_pages(zone);
-
 			/*
 			 * If any zone is currently balanced then kswapd will
 			 * not call compaction as it is expected that the
@@ -3159,8 +3161,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 			 * that that high watermark would be met at 100%
 			 * efficiency.
 			 */
-			if (kswapd_shrink_zone(zone, end_zone, &sc,
-					lru_pages, &nr_attempted))
+			if (kswapd_shrink_zone(zone, end_zone,
+					       &sc, &nr_attempted))
 				raise_priority = false;
 		}
 
@@ -3612,10 +3614,6 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
 		.may_swap = 1,
 	};
-	struct shrink_control shrink = {
-		.gfp_mask = sc.gfp_mask,
-	};
-	unsigned long nr_slab_pages0, nr_slab_pages1;
 
 	cond_resched();
 	/*
@@ -3634,44 +3632,10 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		 * priorities until we have enough memory freed.
 		 */
 		do {
-			shrink_zone(zone, &sc);
+			shrink_zone(zone, &sc, true);
 		} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
 	}
 
-	nr_slab_pages0 = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
-	if (nr_slab_pages0 > zone->min_slab_pages) {
-		/*
-		 * shrink_slab() does not currently allow us to determine how
-		 * many pages were freed in this zone. So we take the current
-		 * number of slab pages and shake the slab until it is reduced
-		 * by the same nr_pages that we used for reclaiming unmapped
-		 * pages.
-		 */
-		nodes_clear(shrink.nodes_to_scan);
-		node_set(zone_to_nid(zone), shrink.nodes_to_scan);
-		for (;;) {
-			unsigned long lru_pages = zone_reclaimable_pages(zone);
-
-			/* No reclaimable slab or very low memory pressure */
-			if (!shrink_slab(&shrink, sc.nr_scanned, lru_pages))
-				break;
-
-			/* Freed enough memory */
-			nr_slab_pages1 = zone_page_state(zone,
-							NR_SLAB_RECLAIMABLE);
-			if (nr_slab_pages1 + nr_pages <= nr_slab_pages0)
-				break;
-		}
-
-		/*
-		 * Update nr_reclaimed by the number of slab pages we
-		 * reclaimed from this zone.
-		 */
-		nr_slab_pages1 = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
-		if (nr_slab_pages1 < nr_slab_pages0)
-			sc.nr_reclaimed += nr_slab_pages0 - nr_slab_pages1;
-	}
-
 	p->reclaim_state = NULL;
 	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
 	lockdep_clear_current_reclaim_state();
-- 
cgit v1.2.3-70-g09d2


From d003f371b27016354c392464819530d47a915765 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Fri, 12 Dec 2014 16:56:24 -0800
Subject: oom: don't assume that a coredumping thread will exit soon

oom_kill.c assumes that PF_EXITING task should exit and free the memory
soon.  This is wrong in many ways and one important case is the coredump.
A task can sleep in exit_mm() "forever" while the coredumping sub-thread
can need more memory.

Change the PF_EXITING checks to take SIGNAL_GROUP_COREDUMP into account,
we add the new trivial helper for that.

Note: this is only the first step, this patch doesn't try to solve other
problems.  The SIGNAL_GROUP_COREDUMP check is obviously racy, a task can
participate in coredump after it was already observed in PF_EXITING state,
so TIF_MEMDIE (which also blocks oom-killer) still can be wrongly set.
fatal_signal_pending() can be true because of SIGNAL_GROUP_COREDUMP so
out_of_memory() and mem_cgroup_out_of_memory() shouldn't blindly trust it.
 And even the name/usage of the new helper is confusing, an exiting thread
can only free its ->mm if it is the only/last task in thread group.

[akpm@linux-foundation.org: add comment]
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/oom.h | 11 +++++++++++
 mm/memcontrol.c     |  2 +-
 mm/oom_kill.c       |  6 +++---
 3 files changed, 15 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/oom.h b/include/linux/oom.h
index e8d6e105872..853698c721f 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -92,6 +92,17 @@ static inline bool oom_gfp_allowed(gfp_t gfp_mask)
 
 extern struct task_struct *find_lock_task_mm(struct task_struct *p);
 
+static inline bool task_will_free_mem(struct task_struct *task)
+{
+	/*
+	 * A coredumping process may sleep for an extended period in exit_mm(),
+	 * so the oom killer cannot assume that the process will promptly exit
+	 * and release memory.
+	 */
+	return (task->flags & PF_EXITING) &&
+		!(task->signal->flags & SIGNAL_GROUP_COREDUMP);
+}
+
 /* sysctls */
 extern int sysctl_oom_dump_tasks;
 extern int sysctl_oom_kill_allocating_task;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c6ac50e7d1c..998fb1756d4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1559,7 +1559,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	 * select it.  The goal is to allow it to allocate so that it may
 	 * quickly exit and free its memory.
 	 */
-	if (fatal_signal_pending(current) || current->flags & PF_EXITING) {
+	if (fatal_signal_pending(current) || task_will_free_mem(current)) {
 		set_thread_flag(TIF_MEMDIE);
 		return;
 	}
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 864bba99273..f694ef0d9f9 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -281,7 +281,7 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
 	if (oom_task_origin(task))
 		return OOM_SCAN_SELECT;
 
-	if (task->flags & PF_EXITING && !force_kill) {
+	if (task_will_free_mem(task) && !force_kill) {
 		/*
 		 * If this task is not being ptraced on exit, then wait for it
 		 * to finish before killing some other task unnecessarily.
@@ -443,7 +443,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 * If the task is already exiting, don't alarm the sysadmin or kill
 	 * its children or threads, just set TIF_MEMDIE so it can die quickly
 	 */
-	if (p->flags & PF_EXITING) {
+	if (task_will_free_mem(p)) {
 		set_tsk_thread_flag(p, TIF_MEMDIE);
 		put_task_struct(p);
 		return;
@@ -649,7 +649,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	 * select it.  The goal is to allow it to allocate so that it may
 	 * quickly exit and free its memory.
 	 */
-	if (fatal_signal_pending(current) || current->flags & PF_EXITING) {
+	if (fatal_signal_pending(current) || task_will_free_mem(current)) {
 		set_thread_flag(TIF_MEMDIE);
 		return;
 	}
-- 
cgit v1.2.3-70-g09d2


From 8135be5a8012f4c7e95218563855e16c09a8271b Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Fri, 12 Dec 2014 16:56:38 -0800
Subject: memcg: fix possible use-after-free in memcg_kmem_get_cache()

Suppose task @t that belongs to a memory cgroup @memcg is going to
allocate an object from a kmem cache @c.  The copy of @c corresponding to
@memcg, @mc, is empty.  Then if kmem_cache_alloc races with the memory
cgroup destruction we can access the memory cgroup's copy of the cache
after it was destroyed:

CPU0				CPU1
----				----
[ current=@t
  @mc->memcg_params->nr_pages=0 ]

kmem_cache_alloc(@c):
  call memcg_kmem_get_cache(@c);
  proceed to allocation from @mc:
    alloc a page for @mc:
      ...

				move @t from @memcg
				destroy @memcg:
				  mem_cgroup_css_offline(@memcg):
				    memcg_unregister_all_caches(@memcg):
				      kmem_cache_destroy(@mc)

    add page to @mc

We could fix this issue by taking a reference to a per-memcg cache, but
that would require adding a per-cpu reference counter to per-memcg caches,
which would look cumbersome.

Instead, let's take a reference to a memory cgroup, which already has a
per-cpu reference counter, in the beginning of kmem_cache_alloc to be
dropped in the end, and move per memcg caches destruction from css offline
to css free.  As a side effect, per-memcg caches will be destroyed not one
by one, but all at once when the last page accounted to the memory cgroup
is freed.  This doesn't sound as a high price for code readability though.

Note, this patch does add some overhead to the kmem_cache_alloc hot path,
but it is pretty negligible - it's just a function call plus a per cpu
counter decrement, which is comparable to what we already have in
memcg_kmem_get_cache.  Besides, it's only relevant if there are memory
cgroups with kmem accounting enabled.  I don't think we can find a way to
handle this race w/o it, because alloc_page called from kmem_cache_alloc
may sleep so we can't flush all pending kmallocs w/o reference counting.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 14 +++++++++++--
 include/linux/slab.h       |  2 --
 mm/memcontrol.c            | 51 +++++++++++++++-------------------------------
 mm/slab.c                  |  2 ++
 mm/slub.c                  | 14 ++++++++-----
 5 files changed, 39 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index b74942a9e22..7c95af8d552 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -400,8 +400,8 @@ int memcg_cache_id(struct mem_cgroup *memcg);
 
 void memcg_update_array_size(int num_groups);
 
-struct kmem_cache *
-__memcg_kmem_get_cache(struct kmem_cache *cachep);
+struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
+void __memcg_kmem_put_cache(struct kmem_cache *cachep);
 
 int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order);
 void __memcg_uncharge_slab(struct kmem_cache *cachep, int order);
@@ -494,6 +494,12 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 
 	return __memcg_kmem_get_cache(cachep);
 }
+
+static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
+{
+	if (memcg_kmem_enabled())
+		__memcg_kmem_put_cache(cachep);
+}
 #else
 #define for_each_memcg_cache_index(_idx)	\
 	for (; NULL; )
@@ -528,6 +534,10 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
 	return cachep;
 }
+
+static inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
+{
+}
 #endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 8a2457d42fc..9a139b63706 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -493,7 +493,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
  * @memcg: pointer to the memcg this cache belongs to
  * @list: list_head for the list of all caches in this memcg
  * @root_cache: pointer to the global, root cache, this cache was derived from
- * @nr_pages: number of pages that belongs to this cache.
  */
 struct memcg_cache_params {
 	bool is_root_cache;
@@ -506,7 +505,6 @@ struct memcg_cache_params {
 			struct mem_cgroup *memcg;
 			struct list_head list;
 			struct kmem_cache *root_cache;
-			atomic_t nr_pages;
 		};
 	};
 };
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index dac81b97599..05e1584750a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2635,7 +2635,6 @@ static void memcg_register_cache(struct mem_cgroup *memcg,
 	if (!cachep)
 		return;
 
-	css_get(&memcg->css);
 	list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches);
 
 	/*
@@ -2669,9 +2668,6 @@ static void memcg_unregister_cache(struct kmem_cache *cachep)
 	list_del(&cachep->memcg_params->list);
 
 	kmem_cache_destroy(cachep);
-
-	/* drop the reference taken in memcg_register_cache */
-	css_put(&memcg->css);
 }
 
 int __memcg_cleanup_cache_params(struct kmem_cache *s)
@@ -2705,9 +2701,7 @@ static void memcg_unregister_all_caches(struct mem_cgroup *memcg)
 	mutex_lock(&memcg_slab_mutex);
 	list_for_each_entry_safe(params, tmp, &memcg->memcg_slab_caches, list) {
 		cachep = memcg_params_to_cache(params);
-		kmem_cache_shrink(cachep);
-		if (atomic_read(&cachep->memcg_params->nr_pages) == 0)
-			memcg_unregister_cache(cachep);
+		memcg_unregister_cache(cachep);
 	}
 	mutex_unlock(&memcg_slab_mutex);
 }
@@ -2742,10 +2736,10 @@ static void __memcg_schedule_register_cache(struct mem_cgroup *memcg,
 	struct memcg_register_cache_work *cw;
 
 	cw = kmalloc(sizeof(*cw), GFP_NOWAIT);
-	if (cw == NULL) {
-		css_put(&memcg->css);
+	if (!cw)
 		return;
-	}
+
+	css_get(&memcg->css);
 
 	cw->memcg = memcg;
 	cw->cachep = cachep;
@@ -2776,12 +2770,8 @@ static void memcg_schedule_register_cache(struct mem_cgroup *memcg,
 int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order)
 {
 	unsigned int nr_pages = 1 << order;
-	int res;
 
-	res = memcg_charge_kmem(cachep->memcg_params->memcg, gfp, nr_pages);
-	if (!res)
-		atomic_add(nr_pages, &cachep->memcg_params->nr_pages);
-	return res;
+	return memcg_charge_kmem(cachep->memcg_params->memcg, gfp, nr_pages);
 }
 
 void __memcg_uncharge_slab(struct kmem_cache *cachep, int order)
@@ -2789,7 +2779,6 @@ void __memcg_uncharge_slab(struct kmem_cache *cachep, int order)
 	unsigned int nr_pages = 1 << order;
 
 	memcg_uncharge_kmem(cachep->memcg_params->memcg, nr_pages);
-	atomic_sub(nr_pages, &cachep->memcg_params->nr_pages);
 }
 
 /*
@@ -2816,22 +2805,13 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep)
 	if (current->memcg_kmem_skip_account)
 		return cachep;
 
-	rcu_read_lock();
-	memcg = mem_cgroup_from_task(rcu_dereference(current->mm->owner));
-
+	memcg = get_mem_cgroup_from_mm(current->mm);
 	if (!memcg_kmem_is_active(memcg))
 		goto out;
 
 	memcg_cachep = cache_from_memcg_idx(cachep, memcg_cache_id(memcg));
-	if (likely(memcg_cachep)) {
-		cachep = memcg_cachep;
-		goto out;
-	}
-
-	/* The corresponding put will be done in the workqueue. */
-	if (!css_tryget_online(&memcg->css))
-		goto out;
-	rcu_read_unlock();
+	if (likely(memcg_cachep))
+		return memcg_cachep;
 
 	/*
 	 * If we are in a safe context (can wait, and not in interrupt
@@ -2846,12 +2826,17 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep)
 	 * defer everything.
 	 */
 	memcg_schedule_register_cache(memcg, cachep);
-	return cachep;
 out:
-	rcu_read_unlock();
+	css_put(&memcg->css);
 	return cachep;
 }
 
+void __memcg_kmem_put_cache(struct kmem_cache *cachep)
+{
+	if (!is_root_cache(cachep))
+		css_put(&cachep->memcg_params->memcg->css);
+}
+
 /*
  * We need to verify if the allocation against current->mm->owner's memcg is
  * possible for the given order. But the page is not allocated yet, so we'll
@@ -2914,10 +2899,6 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order)
 	memcg_uncharge_kmem(memcg, 1 << order);
 	page->mem_cgroup = NULL;
 }
-#else
-static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg)
-{
-}
 #endif /* CONFIG_MEMCG_KMEM */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -4188,6 +4169,7 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 
 static void memcg_destroy_kmem(struct mem_cgroup *memcg)
 {
+	memcg_unregister_all_caches(memcg);
 	mem_cgroup_sockets_destroy(memcg);
 }
 #else
@@ -4797,7 +4779,6 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	}
 	spin_unlock(&memcg->event_list_lock);
 
-	memcg_unregister_all_caches(memcg);
 	vmpressure_cleanup(&memcg->vmpressure);
 }
 
diff --git a/mm/slab.c b/mm/slab.c
index fee275b5b6b..6042fe57cc6 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3182,6 +3182,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 			memset(ptr, 0, cachep->object_size);
 	}
 
+	memcg_kmem_put_cache(cachep);
 	return ptr;
 }
 
@@ -3247,6 +3248,7 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
 			memset(objp, 0, cachep->object_size);
 	}
 
+	memcg_kmem_put_cache(cachep);
 	return objp;
 }
 
diff --git a/mm/slub.c b/mm/slub.c
index 765c5884d03..fe4db9c1723 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1233,13 +1233,17 @@ static inline void kfree_hook(const void *x)
 	kmemleak_free(x);
 }
 
-static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
+static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
+						     gfp_t flags)
 {
 	flags &= gfp_allowed_mask;
 	lockdep_trace_alloc(flags);
 	might_sleep_if(flags & __GFP_WAIT);
 
-	return should_failslab(s->object_size, flags, s->flags);
+	if (should_failslab(s->object_size, flags, s->flags))
+		return NULL;
+
+	return memcg_kmem_get_cache(s, flags);
 }
 
 static inline void slab_post_alloc_hook(struct kmem_cache *s,
@@ -1248,6 +1252,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s,
 	flags &= gfp_allowed_mask;
 	kmemcheck_slab_alloc(s, flags, object, slab_ksize(s));
 	kmemleak_alloc_recursive(object, s->object_size, 1, s->flags, flags);
+	memcg_kmem_put_cache(s);
 }
 
 static inline void slab_free_hook(struct kmem_cache *s, void *x)
@@ -2384,10 +2389,9 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s,
 	struct page *page;
 	unsigned long tid;
 
-	if (slab_pre_alloc_hook(s, gfpflags))
+	s = slab_pre_alloc_hook(s, gfpflags);
+	if (!s)
 		return NULL;
-
-	s = memcg_kmem_get_cache(s, gfpflags);
 redo:
 	/*
 	 * Must read kmem_cache cpu data via this cpu ptr. Preemption is
-- 
cgit v1.2.3-70-g09d2


From 51f39a1f0cea1cacf8c787f652f26dfee9611874 Mon Sep 17 00:00:00 2001
From: David Drysdale <drysdale@google.com>
Date: Fri, 12 Dec 2014 16:57:29 -0800
Subject: syscalls: implement execveat() system call

This patchset adds execveat(2) for x86, and is derived from Meredydd
Luff's patch from Sept 2012 (https://lkml.org/lkml/2012/9/11/528).

The primary aim of adding an execveat syscall is to allow an
implementation of fexecve(3) that does not rely on the /proc filesystem,
at least for executables (rather than scripts).  The current glibc version
of fexecve(3) is implemented via /proc, which causes problems in sandboxed
or otherwise restricted environments.

Given the desire for a /proc-free fexecve() implementation, HPA suggested
(https://lkml.org/lkml/2006/7/11/556) that an execveat(2) syscall would be
an appropriate generalization.

Also, having a new syscall means that it can take a flags argument without
back-compatibility concerns.  The current implementation just defines the
AT_EMPTY_PATH and AT_SYMLINK_NOFOLLOW flags, but other flags could be
added in future -- for example, flags for new namespaces (as suggested at
https://lkml.org/lkml/2006/7/11/474).

Related history:
 - https://lkml.org/lkml/2006/12/27/123 is an example of someone
   realizing that fexecve() is likely to fail in a chroot environment.
 - http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=514043 covered
   documenting the /proc requirement of fexecve(3) in its manpage, to
   "prevent other people from wasting their time".
 - https://bugzilla.redhat.com/show_bug.cgi?id=241609 described a
   problem where a process that did setuid() could not fexecve()
   because it no longer had access to /proc/self/fd; this has since
   been fixed.

This patch (of 4):

Add a new execveat(2) system call.  execveat() is to execve() as openat()
is to open(): it takes a file descriptor that refers to a directory, and
resolves the filename relative to that.

In addition, if the filename is empty and AT_EMPTY_PATH is specified,
execveat() executes the file to which the file descriptor refers.  This
replicates the functionality of fexecve(), which is a system call in other
UNIXen, but in Linux glibc it depends on opening "/proc/self/fd/<fd>" (and
so relies on /proc being mounted).

The filename fed to the executed program as argv[0] (or the name of the
script fed to a script interpreter) will be of the form "/dev/fd/<fd>"
(for an empty filename) or "/dev/fd/<fd>/<filename>", effectively
reflecting how the executable was found.  This does however mean that
execution of a script in a /proc-less environment won't work; also, script
execution via an O_CLOEXEC file descriptor fails (as the file will not be
accessible after exec).

Based on patches by Meredydd Luff.

Signed-off-by: David Drysdale <drysdale@google.com>
Cc: Meredydd Luff <meredydd@senatehouse.org>
Cc: Shuah Khan <shuah.kh@samsung.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Rich Felker <dalias@aerifal.cx>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/binfmt_em86.c                  |   4 ++
 fs/binfmt_misc.c                  |   4 ++
 fs/binfmt_script.c                |  10 ++++
 fs/exec.c                         | 113 +++++++++++++++++++++++++++++++++-----
 fs/namei.c                        |   2 +-
 include/linux/binfmts.h           |   4 ++
 include/linux/compat.h            |   3 +
 include/linux/fs.h                |   1 +
 include/linux/sched.h             |   4 ++
 include/linux/syscalls.h          |   5 ++
 include/uapi/asm-generic/unistd.h |   4 +-
 kernel/sys_ni.c                   |   3 +
 lib/audit.c                       |   3 +
 13 files changed, 145 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index f37b08cea1f..490538536cb 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -42,6 +42,10 @@ static int load_em86(struct linux_binprm *bprm)
 			return -ENOEXEC;
 	}
 
+	/* Need to be able to load the file after exec */
+	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
+		return -ENOENT;
+
 	allow_write_access(bprm->file);
 	fput(bprm->file);
 	bprm->file = NULL;
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 70789e198de..c04ef1d4f18 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -144,6 +144,10 @@ static int load_misc_binary(struct linux_binprm *bprm)
 	if (!fmt)
 		goto ret;
 
+	/* Need to be able to load the file after exec */
+	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
+		return -ENOENT;
+
 	if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) {
 		retval = remove_arg_zero(bprm);
 		if (retval)
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index 5027a3e1492..afdf4e3cafc 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -24,6 +24,16 @@ static int load_script(struct linux_binprm *bprm)
 
 	if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!'))
 		return -ENOEXEC;
+
+	/*
+	 * If the script filename will be inaccessible after exec, typically
+	 * because it is a "/dev/fd/<fd>/.." path against an O_CLOEXEC fd, give
+	 * up now (on the assumption that the interpreter will want to load
+	 * this file).
+	 */
+	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
+		return -ENOENT;
+
 	/*
 	 * This section does the #! interpretation.
 	 * Sorta complicated, but hopefully it will work.  -TYT
diff --git a/fs/exec.c b/fs/exec.c
index 01aebe30020..ad8798e26be 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -748,18 +748,25 @@ EXPORT_SYMBOL(setup_arg_pages);
 
 #endif /* CONFIG_MMU */
 
-static struct file *do_open_exec(struct filename *name)
+static struct file *do_open_execat(int fd, struct filename *name, int flags)
 {
 	struct file *file;
 	int err;
-	static const struct open_flags open_exec_flags = {
+	struct open_flags open_exec_flags = {
 		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
 		.acc_mode = MAY_EXEC | MAY_OPEN,
 		.intent = LOOKUP_OPEN,
 		.lookup_flags = LOOKUP_FOLLOW,
 	};
 
-	file = do_filp_open(AT_FDCWD, name, &open_exec_flags);
+	if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
+		return ERR_PTR(-EINVAL);
+	if (flags & AT_SYMLINK_NOFOLLOW)
+		open_exec_flags.lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & AT_EMPTY_PATH)
+		open_exec_flags.lookup_flags |= LOOKUP_EMPTY;
+
+	file = do_filp_open(fd, name, &open_exec_flags);
 	if (IS_ERR(file))
 		goto out;
 
@@ -770,12 +777,13 @@ static struct file *do_open_exec(struct filename *name)
 	if (file->f_path.mnt->mnt_flags & MNT_NOEXEC)
 		goto exit;
 
-	fsnotify_open(file);
-
 	err = deny_write_access(file);
 	if (err)
 		goto exit;
 
+	if (name->name[0] != '\0')
+		fsnotify_open(file);
+
 out:
 	return file;
 
@@ -787,7 +795,7 @@ exit:
 struct file *open_exec(const char *name)
 {
 	struct filename tmp = { .name = name };
-	return do_open_exec(&tmp);
+	return do_open_execat(AT_FDCWD, &tmp, 0);
 }
 EXPORT_SYMBOL(open_exec);
 
@@ -1428,10 +1436,12 @@ static int exec_binprm(struct linux_binprm *bprm)
 /*
  * sys_execve() executes a new program.
  */
-static int do_execve_common(struct filename *filename,
-				struct user_arg_ptr argv,
-				struct user_arg_ptr envp)
+static int do_execveat_common(int fd, struct filename *filename,
+			      struct user_arg_ptr argv,
+			      struct user_arg_ptr envp,
+			      int flags)
 {
+	char *pathbuf = NULL;
 	struct linux_binprm *bprm;
 	struct file *file;
 	struct files_struct *displaced;
@@ -1472,7 +1482,7 @@ static int do_execve_common(struct filename *filename,
 	check_unsafe_exec(bprm);
 	current->in_execve = 1;
 
-	file = do_open_exec(filename);
+	file = do_open_execat(fd, filename, flags);
 	retval = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto out_unmark;
@@ -1480,7 +1490,28 @@ static int do_execve_common(struct filename *filename,
 	sched_exec();
 
 	bprm->file = file;
-	bprm->filename = bprm->interp = filename->name;
+	if (fd == AT_FDCWD || filename->name[0] == '/') {
+		bprm->filename = filename->name;
+	} else {
+		if (filename->name[0] == '\0')
+			pathbuf = kasprintf(GFP_TEMPORARY, "/dev/fd/%d", fd);
+		else
+			pathbuf = kasprintf(GFP_TEMPORARY, "/dev/fd/%d/%s",
+					    fd, filename->name);
+		if (!pathbuf) {
+			retval = -ENOMEM;
+			goto out_unmark;
+		}
+		/*
+		 * Record that a name derived from an O_CLOEXEC fd will be
+		 * inaccessible after exec. Relies on having exclusive access to
+		 * current->files (due to unshare_files above).
+		 */
+		if (close_on_exec(fd, rcu_dereference_raw(current->files->fdt)))
+			bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
+		bprm->filename = pathbuf;
+	}
+	bprm->interp = bprm->filename;
 
 	retval = bprm_mm_init(bprm);
 	if (retval)
@@ -1521,6 +1552,7 @@ static int do_execve_common(struct filename *filename,
 	acct_update_integrals(current);
 	task_numa_free(current);
 	free_bprm(bprm);
+	kfree(pathbuf);
 	putname(filename);
 	if (displaced)
 		put_files_struct(displaced);
@@ -1538,6 +1570,7 @@ out_unmark:
 
 out_free:
 	free_bprm(bprm);
+	kfree(pathbuf);
 
 out_files:
 	if (displaced)
@@ -1553,7 +1586,18 @@ int do_execve(struct filename *filename,
 {
 	struct user_arg_ptr argv = { .ptr.native = __argv };
 	struct user_arg_ptr envp = { .ptr.native = __envp };
-	return do_execve_common(filename, argv, envp);
+	return do_execveat_common(AT_FDCWD, filename, argv, envp, 0);
+}
+
+int do_execveat(int fd, struct filename *filename,
+		const char __user *const __user *__argv,
+		const char __user *const __user *__envp,
+		int flags)
+{
+	struct user_arg_ptr argv = { .ptr.native = __argv };
+	struct user_arg_ptr envp = { .ptr.native = __envp };
+
+	return do_execveat_common(fd, filename, argv, envp, flags);
 }
 
 #ifdef CONFIG_COMPAT
@@ -1569,7 +1613,23 @@ static int compat_do_execve(struct filename *filename,
 		.is_compat = true,
 		.ptr.compat = __envp,
 	};
-	return do_execve_common(filename, argv, envp);
+	return do_execveat_common(AT_FDCWD, filename, argv, envp, 0);
+}
+
+static int compat_do_execveat(int fd, struct filename *filename,
+			      const compat_uptr_t __user *__argv,
+			      const compat_uptr_t __user *__envp,
+			      int flags)
+{
+	struct user_arg_ptr argv = {
+		.is_compat = true,
+		.ptr.compat = __argv,
+	};
+	struct user_arg_ptr envp = {
+		.is_compat = true,
+		.ptr.compat = __envp,
+	};
+	return do_execveat_common(fd, filename, argv, envp, flags);
 }
 #endif
 
@@ -1609,6 +1669,20 @@ SYSCALL_DEFINE3(execve,
 {
 	return do_execve(getname(filename), argv, envp);
 }
+
+SYSCALL_DEFINE5(execveat,
+		int, fd, const char __user *, filename,
+		const char __user *const __user *, argv,
+		const char __user *const __user *, envp,
+		int, flags)
+{
+	int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
+
+	return do_execveat(fd,
+			   getname_flags(filename, lookup_flags, NULL),
+			   argv, envp, flags);
+}
+
 #ifdef CONFIG_COMPAT
 COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename,
 	const compat_uptr_t __user *, argv,
@@ -1616,4 +1690,17 @@ COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename,
 {
 	return compat_do_execve(getname(filename), argv, envp);
 }
+
+COMPAT_SYSCALL_DEFINE5(execveat, int, fd,
+		       const char __user *, filename,
+		       const compat_uptr_t __user *, argv,
+		       const compat_uptr_t __user *, envp,
+		       int,  flags)
+{
+	int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
+
+	return compat_do_execveat(fd,
+				  getname_flags(filename, lookup_flags, NULL),
+				  argv, envp, flags);
+}
 #endif
diff --git a/fs/namei.c b/fs/namei.c
index db5fe86319e..ca814165d84 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -130,7 +130,7 @@ void final_putname(struct filename *name)
 
 #define EMBEDDED_NAME_MAX	(PATH_MAX - sizeof(struct filename))
 
-static struct filename *
+struct filename *
 getname_flags(const char __user *filename, int flags, int *empty)
 {
 	struct filename *result, *err;
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 61f29e5ea84..576e4639ca6 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -53,6 +53,10 @@ struct linux_binprm {
 #define BINPRM_FLAGS_EXECFD_BIT 1
 #define BINPRM_FLAGS_EXECFD (1 << BINPRM_FLAGS_EXECFD_BIT)
 
+/* filename of the binary will be inaccessible after exec */
+#define BINPRM_FLAGS_PATH_INACCESSIBLE_BIT 2
+#define BINPRM_FLAGS_PATH_INACCESSIBLE (1 << BINPRM_FLAGS_PATH_INACCESSIBLE_BIT)
+
 /* Function parameter for binfmt->coredump */
 struct coredump_params {
 	const siginfo_t *siginfo;
diff --git a/include/linux/compat.h b/include/linux/compat.h
index e6494261eaf..7450ca2ac1f 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -357,6 +357,9 @@ asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int);
 
 asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv,
 		     const compat_uptr_t __user *envp);
+asmlinkage long compat_sys_execveat(int dfd, const char __user *filename,
+		     const compat_uptr_t __user *argv,
+		     const compat_uptr_t __user *envp, int flags);
 
 asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
 		compat_ulong_t __user *outp, compat_ulong_t __user *exp,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1d1838de688..4193a0bd99b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2096,6 +2096,7 @@ extern int vfs_open(const struct path *, struct file *, const struct cred *);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
 
+extern struct filename *getname_flags(const char __user *, int, int *);
 extern struct filename *getname(const char __user *);
 extern struct filename *getname_kernel(const char *);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4cfdbcf8cf5..8db31ef98d2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2485,6 +2485,10 @@ extern void do_group_exit(int);
 extern int do_execve(struct filename *,
 		     const char __user * const __user *,
 		     const char __user * const __user *);
+extern int do_execveat(int, struct filename *,
+		       const char __user * const __user *,
+		       const char __user * const __user *,
+		       int);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index c9afdc7a7f8..85893d74490 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -877,4 +877,9 @@ asmlinkage long sys_seccomp(unsigned int op, unsigned int flags,
 asmlinkage long sys_getrandom(char __user *buf, size_t count,
 			      unsigned int flags);
 asmlinkage long sys_bpf(int cmd, union bpf_attr *attr, unsigned int size);
+
+asmlinkage long sys_execveat(int dfd, const char __user *filename,
+			const char __user *const __user *argv,
+			const char __user *const __user *envp, int flags);
+
 #endif
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 22749c13411..e016bd9b1a0 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -707,9 +707,11 @@ __SYSCALL(__NR_getrandom, sys_getrandom)
 __SYSCALL(__NR_memfd_create, sys_memfd_create)
 #define __NR_bpf 280
 __SYSCALL(__NR_bpf, sys_bpf)
+#define __NR_execveat 281
+__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
 
 #undef __NR_syscalls
-#define __NR_syscalls 281
+#define __NR_syscalls 282
 
 /*
  * All syscalls below here should go away really,
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 61eea02b53f..5adcb0ae3a5 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -226,3 +226,6 @@ cond_syscall(sys_seccomp);
 
 /* access BPF programs and maps */
 cond_syscall(sys_bpf);
+
+/* execveat */
+cond_syscall(sys_execveat);
diff --git a/lib/audit.c b/lib/audit.c
index 1d726a22565..b8fb5ee81e2 100644
--- a/lib/audit.c
+++ b/lib/audit.c
@@ -53,6 +53,9 @@ int audit_classify_syscall(int abi, unsigned syscall)
 #ifdef __NR_socketcall
 	case __NR_socketcall:
 		return 4;
+#endif
+#ifdef __NR_execveat
+	case __NR_execveat:
 #endif
 	case __NR_execve:
 		return 5;
-- 
cgit v1.2.3-70-g09d2


From 89e3f90995b370fa46922eece62ea23f039a202d Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Fri, 12 Dec 2014 16:57:57 -0800
Subject: ratelimit: add initialization macro

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Cc: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ratelimit.h | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h
index 0a260d8a18b..18102529254 100644
--- a/include/linux/ratelimit.h
+++ b/include/linux/ratelimit.h
@@ -17,14 +17,20 @@ struct ratelimit_state {
 	unsigned long	begin;
 };
 
-#define DEFINE_RATELIMIT_STATE(name, interval_init, burst_init)		\
-									\
-	struct ratelimit_state name = {					\
+#define RATELIMIT_STATE_INIT(name, interval_init, burst_init) {		\
 		.lock		= __RAW_SPIN_LOCK_UNLOCKED(name.lock),	\
 		.interval	= interval_init,			\
 		.burst		= burst_init,				\
 	}
 
+#define RATELIMIT_STATE_INIT_DISABLED					\
+	RATELIMIT_STATE_INIT(ratelimit_state, 0, DEFAULT_RATELIMIT_BURST)
+
+#define DEFINE_RATELIMIT_STATE(name, interval_init, burst_init)		\
+									\
+	struct ratelimit_state name =					\
+		RATELIMIT_STATE_INIT(name, interval_init, burst_init)	\
+
 static inline void ratelimit_state_init(struct ratelimit_state *rs,
 					int interval, int burst)
 {
-- 
cgit v1.2.3-70-g09d2


From 6adc4a22f20bbf3bbc754f1ec8c82be5dfb5c71a Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Fri, 12 Dec 2014 16:58:00 -0800
Subject: fault-inject: add ratelimit option

Current debug levels are not optimal.  Especially if one want to provoke
big numbers of faults(broken device simulator) then any verbose level will
produce giant numbers of identical logging messages.  Let's add ratelimit
parameter for that purpose.

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Acked-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fault-inject.h | 17 +++++++++++------
 lib/fault-inject.c           | 21 +++++++++++++++++----
 2 files changed, 28 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h
index c6f996f2abb..798fad9e420 100644
--- a/include/linux/fault-inject.h
+++ b/include/linux/fault-inject.h
@@ -5,6 +5,7 @@
 
 #include <linux/types.h>
 #include <linux/debugfs.h>
+#include <linux/ratelimit.h>
 #include <linux/atomic.h>
 
 /*
@@ -25,14 +26,18 @@ struct fault_attr {
 	unsigned long reject_end;
 
 	unsigned long count;
+	struct ratelimit_state ratelimit_state;
+	struct dentry *dname;
 };
 
-#define FAULT_ATTR_INITIALIZER {				\
-		.interval = 1,					\
-		.times = ATOMIC_INIT(1),			\
-		.require_end = ULONG_MAX,			\
-		.stacktrace_depth = 32,				\
-		.verbose = 2,					\
+#define FAULT_ATTR_INITIALIZER {					\
+		.interval = 1,						\
+		.times = ATOMIC_INIT(1),				\
+		.require_end = ULONG_MAX,				\
+		.stacktrace_depth = 32,					\
+		.ratelimit_state = RATELIMIT_STATE_INIT_DISABLED,	\
+		.verbose = 2,						\
+		.dname = NULL,						\
 	}
 
 #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index d7d501ea856..f1cdeb024d1 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -40,10 +40,16 @@ EXPORT_SYMBOL_GPL(setup_fault_attr);
 
 static void fail_dump(struct fault_attr *attr)
 {
-	if (attr->verbose > 0)
-		printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure\n");
-	if (attr->verbose > 1)
-		dump_stack();
+	if (attr->verbose > 0 && __ratelimit(&attr->ratelimit_state)) {
+		printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure.\n"
+		       "name %pd, interval %lu, probability %lu, "
+		       "space %d, times %d\n", attr->dname,
+		       attr->probability, attr->interval,
+		       atomic_read(&attr->space),
+		       atomic_read(&attr->times));
+		if (attr->verbose > 1)
+			dump_stack();
+	}
 }
 
 #define atomic_dec_not_zero(v)		atomic_add_unless((v), -1, 0)
@@ -202,6 +208,12 @@ struct dentry *fault_create_debugfs_attr(const char *name,
 		goto fail;
 	if (!debugfs_create_ul("verbose", mode, dir, &attr->verbose))
 		goto fail;
+	if (!debugfs_create_u32("verbose_ratelimit_interval_ms", mode, dir,
+				&attr->ratelimit_state.interval))
+		goto fail;
+	if (!debugfs_create_u32("verbose_ratelimit_burst", mode, dir,
+				&attr->ratelimit_state.burst))
+		goto fail;
 	if (!debugfs_create_bool("task-filter", mode, dir, &attr->task_filter))
 		goto fail;
 
@@ -222,6 +234,7 @@ struct dentry *fault_create_debugfs_attr(const char *name,
 
 #endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
 
+	attr->dname = dget(dir);
 	return dir;
 fail:
 	debugfs_remove_recursive(dir);
-- 
cgit v1.2.3-70-g09d2


From e843e7d2c88b7db107a86bd2c7145dc715c058f4 Mon Sep 17 00:00:00 2001
From: Manfred Spraul <manfred@colorfullife.com>
Date: Fri, 12 Dec 2014 16:58:14 -0800
Subject: ipc/sem.c: increase SEMMSL, SEMMNI, SEMOPM

a)

SysV can be abused to allocate locked kernel memory.  For most systems, a
small limit doesn't make sense, see the discussion with regards to SHMMAX.

Therefore: Increase the sysv sem limits so that all known applications
will work with these defaults.

b)

With regards to the maximum supported:
Some of the specified hard limits are not correct anymore, therefore the
patch updates the documentation.

- SEMMNI must stay below IPCMNI, which is 32768.
  As for SHMMAX: Stay a bit below this limit.

- SEMMSL was limited to 8k, to ensure that the kmalloc for the kernel array
  was limited to 16 kB (order=2)

  This doesn't apply anymore:
   - the allocation size isn't sizeof(short)*nsems anymore.
   - ipc_alloc falls back to vmalloc

- SEMOPM should stay below 1000, to limit the kmalloc in semtimedop() to an
  order=1 allocation.
  Therefore: Leave it at 500 (order=0 allocation).

Note:
If an administrator must limit the memory allocations, then he can set the
values as necessary.

Or he can disable sysv entirely (as e.g. done by Android).

Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Acked-by: Rafael Aquini <aquini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/uapi/linux/sem.h | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/sem.h b/include/uapi/linux/sem.h
index 541fce03b50..dd73b908b2f 100644
--- a/include/uapi/linux/sem.h
+++ b/include/uapi/linux/sem.h
@@ -63,10 +63,22 @@ struct  seminfo {
 	int semaem;
 };
 
-#define SEMMNI  128             /* <= IPCMNI  max # of semaphore identifiers */
-#define SEMMSL  250             /* <= 8 000 max num of semaphores per id */
+/*
+ * SEMMNI, SEMMSL and SEMMNS are default values which can be
+ * modified by sysctl.
+ * The values has been chosen to be larger than necessary for any
+ * known configuration.
+ *
+ * SEMOPM should not be increased beyond 1000, otherwise there is the
+ * risk that semop()/semtimedop() fails due to kernel memory fragmentation when
+ * allocating the sop array.
+ */
+
+
+#define SEMMNI  32000           /* <= IPCMNI  max # of semaphore identifiers */
+#define SEMMSL  32000           /* <= INT_MAX max num of semaphores per id */
 #define SEMMNS  (SEMMNI*SEMMSL) /* <= INT_MAX max # of semaphores in system */
-#define SEMOPM  32	        /* <= 1 000 max num of ops per semop call */
+#define SEMOPM  500	        /* <= 1 000 max num of ops per semop call */
 #define SEMVMX  32767           /* <= 32767 semaphore maximum value */
 #define SEMAEM  SEMVMX          /* adjust on exit max value */
 
-- 
cgit v1.2.3-70-g09d2


From 0050ee059f7fc86b1df2527aaa14ed5dc72f9973 Mon Sep 17 00:00:00 2001
From: Manfred Spraul <manfred@colorfullife.com>
Date: Fri, 12 Dec 2014 16:58:17 -0800
Subject: ipc/msg: increase MSGMNI, remove scaling

SysV can be abused to allocate locked kernel memory.  For most systems, a
small limit doesn't make sense, see the discussion with regards to SHMMAX.

Therefore: increase MSGMNI to the maximum supported.

And: If we ignore the risk of locking too much memory, then an automatic
scaling of MSGMNI doesn't make sense.  Therefore the logic can be removed.

The code preserves auto_msgmni to avoid breaking any user space applications
that expect that the value exists.

Notes:
1) If an administrator must limit the memory allocations, then he can set
MSGMNI as necessary.

Or he can disable sysv entirely (as e.g. done by Android).

2) MSGMAX and MSGMNB are intentionally not increased, as these values are used
to control latency vs. throughput:
If MSGMNB is large, then msgsnd() just returns and more messages can be queued
before a task switch to a task that calls msgrcv() is forced.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/sysctl/kernel.txt | 10 +++--
 include/linux/ipc_namespace.h   | 20 ---------
 include/uapi/linux/msg.h        | 28 +++++++++----
 ipc/Makefile                    |  2 +-
 ipc/ipc_sysctl.c                | 93 ++++++++---------------------------------
 ipc/ipcns_notifier.c            | 92 ----------------------------------------
 ipc/msg.c                       | 36 +---------------
 ipc/namespace.c                 | 22 ----------
 ipc/util.c                      | 40 ------------------
 9 files changed, 45 insertions(+), 298 deletions(-)
 delete mode 100644 ipc/ipcns_notifier.c

(limited to 'include')

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index b5d0c8501a1..75511efefc6 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -116,10 +116,12 @@ set during run time.
 
 auto_msgmni:
 
-Enables/Disables automatic recomputing of msgmni upon memory add/remove
-or upon ipc namespace creation/removal (see the msgmni description
-above). Echoing "1" into this file enables msgmni automatic recomputing.
-Echoing "0" turns it off. auto_msgmni default value is 1.
+This variable has no effect and may be removed in future kernel
+releases. Reading it always returns 0.
+Up to Linux 3.17, it enabled/disabled automatic recomputing of msgmni
+upon memory add/remove or upon ipc namespace creation/removal.
+Echoing "1" into this file enabled msgmni automatic recomputing.
+Echoing "0" turned it off. auto_msgmni default value was 1.
 
 
 ==============================================================
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index 35e7eca4e33..e365d5ec69c 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -7,15 +7,6 @@
 #include <linux/notifier.h>
 #include <linux/nsproxy.h>
 
-/*
- * ipc namespace events
- */
-#define IPCNS_MEMCHANGED   0x00000001   /* Notify lowmem size changed */
-#define IPCNS_CREATED  0x00000002   /* Notify new ipc namespace created */
-#define IPCNS_REMOVED  0x00000003   /* Notify ipc namespace removed */
-
-#define IPCNS_CALLBACK_PRI 0
-
 struct user_namespace;
 
 struct ipc_ids {
@@ -38,7 +29,6 @@ struct ipc_namespace {
 	unsigned int	msg_ctlmni;
 	atomic_t	msg_bytes;
 	atomic_t	msg_hdrs;
-	int		auto_msgmni;
 
 	size_t		shm_ctlmax;
 	size_t		shm_ctlall;
@@ -77,18 +67,8 @@ extern atomic_t nr_ipc_ns;
 extern spinlock_t mq_lock;
 
 #ifdef CONFIG_SYSVIPC
-extern int register_ipcns_notifier(struct ipc_namespace *);
-extern int cond_register_ipcns_notifier(struct ipc_namespace *);
-extern void unregister_ipcns_notifier(struct ipc_namespace *);
-extern int ipcns_notify(unsigned long);
 extern void shm_destroy_orphaned(struct ipc_namespace *ns);
 #else /* CONFIG_SYSVIPC */
-static inline int register_ipcns_notifier(struct ipc_namespace *ns)
-{ return 0; }
-static inline int cond_register_ipcns_notifier(struct ipc_namespace *ns)
-{ return 0; }
-static inline void unregister_ipcns_notifier(struct ipc_namespace *ns) { }
-static inline int ipcns_notify(unsigned long l) { return 0; }
 static inline void shm_destroy_orphaned(struct ipc_namespace *ns) {}
 #endif /* CONFIG_SYSVIPC */
 
diff --git a/include/uapi/linux/msg.h b/include/uapi/linux/msg.h
index a7037552657..f51c8001dbe 100644
--- a/include/uapi/linux/msg.h
+++ b/include/uapi/linux/msg.h
@@ -51,16 +51,28 @@ struct msginfo {
 };
 
 /*
- * Scaling factor to compute msgmni:
- * the memory dedicated to msg queues (msgmni * msgmnb) should occupy
- * at most 1/MSG_MEM_SCALE of the lowmem (see the formula in ipc/msg.c):
- * up to 8MB       : msgmni = 16 (MSGMNI)
- * 4 GB            : msgmni = 8K
- * more than 16 GB : msgmni = 32K (IPCMNI)
+ * MSGMNI, MSGMAX and MSGMNB are default values which can be
+ * modified by sysctl.
+ *
+ * MSGMNI is the upper limit for the number of messages queues per
+ * namespace.
+ * It has been chosen to be as large possible without facilitating
+ * scenarios where userspace causes overflows when adjusting the limits via
+ * operations of the form retrieve current limit; add X; update limit".
+ *
+ * MSGMNB is the default size of a new message queue. Non-root tasks can
+ * decrease the size with msgctl(IPC_SET), root tasks
+ * (actually: CAP_SYS_RESOURCE) can both increase and decrease the queue
+ * size. The optimal value is application dependent.
+ * 16384 is used because it was always used (since 0.99.10)
+ *
+ * MAXMAX is the maximum size of an individual message, it's a global
+ * (per-namespace) limit that applies for all message queues.
+ * It's set to 1/2 of MSGMNB, to ensure that at least two messages fit into
+ * the queue. This is also an arbitrary choice (since 2.6.0).
  */
-#define MSG_MEM_SCALE 32
 
-#define MSGMNI    16   /* <= IPCMNI */     /* max # of msg queue identifiers */
+#define MSGMNI 32000   /* <= IPCMNI */     /* max # of msg queue identifiers */
 #define MSGMAX  8192   /* <= INT_MAX */   /* max size of message (bytes) */
 #define MSGMNB 16384   /* <= INT_MAX */   /* default max size of a message queue */
 
diff --git a/ipc/Makefile b/ipc/Makefile
index 9075e172e52..86c7300ecdf 100644
--- a/ipc/Makefile
+++ b/ipc/Makefile
@@ -3,7 +3,7 @@
 #
 
 obj-$(CONFIG_SYSVIPC_COMPAT) += compat.o
-obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o ipcns_notifier.o syscall.o
+obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o syscall.o
 obj-$(CONFIG_SYSVIPC_SYSCTL) += ipc_sysctl.o
 obj_mq-$(CONFIG_COMPAT) += compat_mq.o
 obj-$(CONFIG_POSIX_MQUEUE) += mqueue.o msgutil.o $(obj_mq-y)
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index e8075b24749..8ad93c29f51 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -62,29 +62,6 @@ static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
 	return err;
 }
 
-static int proc_ipc_callback_dointvec_minmax(struct ctl_table *table, int write,
-	void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	struct ctl_table ipc_table;
-	size_t lenp_bef = *lenp;
-	int rc;
-
-	memcpy(&ipc_table, table, sizeof(ipc_table));
-	ipc_table.data = get_ipc(table);
-
-	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
-
-	if (write && !rc && lenp_bef == *lenp)
-		/*
-		 * Tunable has successfully been changed by hand. Disable its
-		 * automatic adjustment. This simply requires unregistering
-		 * the notifiers that trigger recalculation.
-		 */
-		unregister_ipcns_notifier(current->nsproxy->ipc_ns);
-
-	return rc;
-}
-
 static int proc_ipc_doulongvec_minmax(struct ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -96,54 +73,19 @@ static int proc_ipc_doulongvec_minmax(struct ctl_table *table, int write,
 					lenp, ppos);
 }
 
-/*
- * Routine that is called when the file "auto_msgmni" has successfully been
- * written.
- * Two values are allowed:
- * 0: unregister msgmni's callback routine from the ipc namespace notifier
- *    chain. This means that msgmni won't be recomputed anymore upon memory
- *    add/remove or ipc namespace creation/removal.
- * 1: register back the callback routine.
- */
-static void ipc_auto_callback(int val)
-{
-	if (!val)
-		unregister_ipcns_notifier(current->nsproxy->ipc_ns);
-	else {
-		/*
-		 * Re-enable automatic recomputing only if not already
-		 * enabled.
-		 */
-		recompute_msgmni(current->nsproxy->ipc_ns);
-		cond_register_ipcns_notifier(current->nsproxy->ipc_ns);
-	}
-}
-
-static int proc_ipcauto_dointvec_minmax(struct ctl_table *table, int write,
+static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table ipc_table;
-	int oldval;
-	int rc;
+	int dummy = 0;
 
 	memcpy(&ipc_table, table, sizeof(ipc_table));
-	ipc_table.data = get_ipc(table);
-	oldval = *((int *)(ipc_table.data));
+	ipc_table.data = &dummy;
 
-	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
+	if (write)
+		pr_info_once("writing to auto_msgmni has no effect");
 
-	if (write && !rc) {
-		int newval = *((int *)(ipc_table.data));
-		/*
-		 * The file "auto_msgmni" has correctly been set.
-		 * React by (un)registering the corresponding tunable, if the
-		 * value has changed.
-		 */
-		if (newval != oldval)
-			ipc_auto_callback(newval);
-	}
-
-	return rc;
+	return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 }
 
 #else
@@ -151,8 +93,7 @@ static int proc_ipcauto_dointvec_minmax(struct ctl_table *table, int write,
 #define proc_ipc_dointvec	   NULL
 #define proc_ipc_dointvec_minmax   NULL
 #define proc_ipc_dointvec_minmax_orphans   NULL
-#define proc_ipc_callback_dointvec_minmax  NULL
-#define proc_ipcauto_dointvec_minmax NULL
+#define proc_ipc_auto_msgmni	   NULL
 #endif
 
 static int zero;
@@ -204,10 +145,19 @@ static struct ctl_table ipc_kern_table[] = {
 		.data		= &init_ipc_ns.msg_ctlmni,
 		.maxlen		= sizeof(init_ipc_ns.msg_ctlmni),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_callback_dointvec_minmax,
+		.proc_handler	= proc_ipc_dointvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &int_max,
 	},
+	{
+		.procname	= "auto_msgmni",
+		.data		= NULL,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_auto_msgmni,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 	{
 		.procname	=  "msgmnb",
 		.data		= &init_ipc_ns.msg_ctlmnb,
@@ -224,15 +174,6 @@ static struct ctl_table ipc_kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_ipc_dointvec,
 	},
-	{
-		.procname	= "auto_msgmni",
-		.data		= &init_ipc_ns.auto_msgmni,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_ipcauto_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
-	},
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	{
 		.procname	= "sem_next_id",
diff --git a/ipc/ipcns_notifier.c b/ipc/ipcns_notifier.c
deleted file mode 100644
index b9b31a4f77e..00000000000
--- a/ipc/ipcns_notifier.c
+++ /dev/null
@@ -1,92 +0,0 @@
-/*
- * linux/ipc/ipcns_notifier.c
- * Copyright (C) 2007 BULL SA. Nadia Derbey
- *
- * Notification mechanism for ipc namespaces:
- * The callback routine registered in the memory chain invokes the ipcns
- * notifier chain with the IPCNS_MEMCHANGED event.
- * Each callback routine registered in the ipcns namespace recomputes msgmni
- * for the owning namespace.
- */
-
-#include <linux/msg.h>
-#include <linux/rcupdate.h>
-#include <linux/notifier.h>
-#include <linux/nsproxy.h>
-#include <linux/ipc_namespace.h>
-
-#include "util.h"
-
-
-
-static BLOCKING_NOTIFIER_HEAD(ipcns_chain);
-
-
-static int ipcns_callback(struct notifier_block *self,
-				unsigned long action, void *arg)
-{
-	struct ipc_namespace *ns;
-
-	switch (action) {
-	case IPCNS_MEMCHANGED:   /* amount of lowmem has changed */
-	case IPCNS_CREATED:
-	case IPCNS_REMOVED:
-		/*
-		 * It's time to recompute msgmni
-		 */
-		ns = container_of(self, struct ipc_namespace, ipcns_nb);
-		/*
-		 * No need to get a reference on the ns: the 1st job of
-		 * free_ipc_ns() is to unregister the callback routine.
-		 * blocking_notifier_chain_unregister takes the wr lock to do
-		 * it.
-		 * When this callback routine is called the rd lock is held by
-		 * blocking_notifier_call_chain.
-		 * So the ipc ns cannot be freed while we are here.
-		 */
-		recompute_msgmni(ns);
-		break;
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-int register_ipcns_notifier(struct ipc_namespace *ns)
-{
-	int rc;
-
-	memset(&ns->ipcns_nb, 0, sizeof(ns->ipcns_nb));
-	ns->ipcns_nb.notifier_call = ipcns_callback;
-	ns->ipcns_nb.priority = IPCNS_CALLBACK_PRI;
-	rc = blocking_notifier_chain_register(&ipcns_chain, &ns->ipcns_nb);
-	if (!rc)
-		ns->auto_msgmni = 1;
-	return rc;
-}
-
-int cond_register_ipcns_notifier(struct ipc_namespace *ns)
-{
-	int rc;
-
-	memset(&ns->ipcns_nb, 0, sizeof(ns->ipcns_nb));
-	ns->ipcns_nb.notifier_call = ipcns_callback;
-	ns->ipcns_nb.priority = IPCNS_CALLBACK_PRI;
-	rc = blocking_notifier_chain_cond_register(&ipcns_chain,
-							&ns->ipcns_nb);
-	if (!rc)
-		ns->auto_msgmni = 1;
-	return rc;
-}
-
-void unregister_ipcns_notifier(struct ipc_namespace *ns)
-{
-	blocking_notifier_chain_unregister(&ipcns_chain, &ns->ipcns_nb);
-	ns->auto_msgmni = 0;
-}
-
-int ipcns_notify(unsigned long val)
-{
-	return blocking_notifier_call_chain(&ipcns_chain, val, NULL);
-}
diff --git a/ipc/msg.c b/ipc/msg.c
index c5d8e374998..a7261d5cbc8 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -989,43 +989,12 @@ SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
 	return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill);
 }
 
-/*
- * Scale msgmni with the available lowmem size: the memory dedicated to msg
- * queues should occupy at most 1/MSG_MEM_SCALE of lowmem.
- * Also take into account the number of nsproxies created so far.
- * This should be done staying within the (MSGMNI , IPCMNI/nr_ipc_ns) range.
- */
-void recompute_msgmni(struct ipc_namespace *ns)
-{
-	struct sysinfo i;
-	unsigned long allowed;
-	int nb_ns;
-
-	si_meminfo(&i);
-	allowed = (((i.totalram - i.totalhigh) / MSG_MEM_SCALE) * i.mem_unit)
-		/ MSGMNB;
-	nb_ns = atomic_read(&nr_ipc_ns);
-	allowed /= nb_ns;
-
-	if (allowed < MSGMNI) {
-		ns->msg_ctlmni = MSGMNI;
-		return;
-	}
-
-	if (allowed > IPCMNI / nb_ns) {
-		ns->msg_ctlmni = IPCMNI / nb_ns;
-		return;
-	}
-
-	ns->msg_ctlmni = allowed;
-}
 
 void msg_init_ns(struct ipc_namespace *ns)
 {
 	ns->msg_ctlmax = MSGMAX;
 	ns->msg_ctlmnb = MSGMNB;
-
-	recompute_msgmni(ns);
+	ns->msg_ctlmni = MSGMNI;
 
 	atomic_set(&ns->msg_bytes, 0);
 	atomic_set(&ns->msg_hdrs, 0);
@@ -1069,9 +1038,6 @@ void __init msg_init(void)
 {
 	msg_init_ns(&init_ipc_ns);
 
-	printk(KERN_INFO "msgmni has been set to %d\n",
-		init_ipc_ns.msg_ctlmni);
-
 	ipc_init_proc_interface("sysvipc/msg",
 				"       key      msqid perms      cbytes       qnum lspid lrpid   uid   gid  cuid  cgid      stime      rtime      ctime\n",
 				IPC_MSG_IDS, sysvipc_msg_proc_show);
diff --git a/ipc/namespace.c b/ipc/namespace.c
index b54468e48e3..1a3ffd40356 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -45,14 +45,6 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 	msg_init_ns(ns);
 	shm_init_ns(ns);
 
-	/*
-	 * msgmni has already been computed for the new ipc ns.
-	 * Thus, do the ipcns creation notification before registering that
-	 * new ipcns in the chain.
-	 */
-	ipcns_notify(IPCNS_CREATED);
-	register_ipcns_notifier(ns);
-
 	ns->user_ns = get_user_ns(user_ns);
 
 	return ns;
@@ -99,25 +91,11 @@ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
 
 static void free_ipc_ns(struct ipc_namespace *ns)
 {
-	/*
-	 * Unregistering the hotplug notifier at the beginning guarantees
-	 * that the ipc namespace won't be freed while we are inside the
-	 * callback routine. Since the blocking_notifier_chain_XXX routines
-	 * hold a rw lock on the notifier list, unregister_ipcns_notifier()
-	 * won't take the rw lock before blocking_notifier_call_chain() has
-	 * released the rd lock.
-	 */
-	unregister_ipcns_notifier(ns);
 	sem_exit_ns(ns);
 	msg_exit_ns(ns);
 	shm_exit_ns(ns);
 	atomic_dec(&nr_ipc_ns);
 
-	/*
-	 * Do the ipcns removal notification after decrementing nr_ipc_ns in
-	 * order to have a correct value when recomputing msgmni.
-	 */
-	ipcns_notify(IPCNS_REMOVED);
 	put_user_ns(ns->user_ns);
 	proc_free_inum(ns->proc_inum);
 	kfree(ns);
diff --git a/ipc/util.c b/ipc/util.c
index 88adc329888..106bed0378a 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -71,44 +71,6 @@ struct ipc_proc_iface {
 	int (*show)(struct seq_file *, void *);
 };
 
-static void ipc_memory_notifier(struct work_struct *work)
-{
-	ipcns_notify(IPCNS_MEMCHANGED);
-}
-
-static int ipc_memory_callback(struct notifier_block *self,
-				unsigned long action, void *arg)
-{
-	static DECLARE_WORK(ipc_memory_wq, ipc_memory_notifier);
-
-	switch (action) {
-	case MEM_ONLINE:    /* memory successfully brought online */
-	case MEM_OFFLINE:   /* or offline: it's time to recompute msgmni */
-		/*
-		 * This is done by invoking the ipcns notifier chain with the
-		 * IPC_MEMCHANGED event.
-		 * In order not to keep the lock on the hotplug memory chain
-		 * for too long, queue a work item that will, when waken up,
-		 * activate the ipcns notification chain.
-		 */
-		schedule_work(&ipc_memory_wq);
-		break;
-	case MEM_GOING_ONLINE:
-	case MEM_GOING_OFFLINE:
-	case MEM_CANCEL_ONLINE:
-	case MEM_CANCEL_OFFLINE:
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block ipc_memory_nb = {
-	.notifier_call = ipc_memory_callback,
-	.priority = IPC_CALLBACK_PRI,
-};
-
 /**
  * ipc_init - initialise ipc subsystem
  *
@@ -124,8 +86,6 @@ static int __init ipc_init(void)
 	sem_init();
 	msg_init();
 	shm_init();
-	register_hotmemory_notifier(&ipc_memory_nb);
-	register_ipcns_notifier(&init_ipc_ns);
 	return 0;
 }
 device_initcall(ipc_init);
-- 
cgit v1.2.3-70-g09d2


From 0809ab69a2782afac8c4d7f3d35cd123050aab9a Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Fri, 12 Dec 2014 16:58:36 -0800
Subject: fsnotify: unify inode and mount marks handling

There's a lot of common code in inode and mount marks handling.  Factor it
out to a common helper function.

Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Eric Paris <eparis@redhat.com>
Cc: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/notify/dnotify/dnotify.c          |   4 +-
 fs/notify/fdinfo.c                   |   6 +-
 fs/notify/fsnotify.c                 |   4 +-
 fs/notify/fsnotify.h                 |  12 ++++
 fs/notify/inode_mark.c               | 113 ++++++-----------------------------
 fs/notify/inotify/inotify_fsnotify.c |   2 +-
 fs/notify/inotify/inotify_user.c     |  10 ++--
 fs/notify/mark.c                     |  89 ++++++++++++++++++++++++++-
 fs/notify/vfsmount_mark.c            | 109 ++++++---------------------------
 include/linux/fsnotify_backend.h     |  24 ++------
 kernel/audit_tree.c                  |  16 ++---
 11 files changed, 160 insertions(+), 229 deletions(-)

(limited to 'include')

diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index caaaf9dfe35..44523f4a608 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -69,8 +69,8 @@ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
 	if (old_mask == new_mask)
 		return;
 
-	if (fsn_mark->i.inode)
-		fsnotify_recalc_inode_mask(fsn_mark->i.inode);
+	if (fsn_mark->inode)
+		fsnotify_recalc_inode_mask(fsn_mark->inode);
 }
 
 /*
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index 6ffd220eb14..58b7cdb63da 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -80,7 +80,7 @@ static void inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
 		return;
 
 	inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark);
-	inode = igrab(mark->i.inode);
+	inode = igrab(mark->inode);
 	if (inode) {
 		seq_printf(m, "inotify wd:%x ino:%lx sdev:%x mask:%x ignored_mask:%x ",
 			   inode_mark->wd, inode->i_ino, inode->i_sb->s_dev,
@@ -112,7 +112,7 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
 		mflags |= FAN_MARK_IGNORED_SURV_MODIFY;
 
 	if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) {
-		inode = igrab(mark->i.inode);
+		inode = igrab(mark->inode);
 		if (!inode)
 			return;
 		seq_printf(m, "fanotify ino:%lx sdev:%x mflags:%x mask:%x ignored_mask:%x ",
@@ -122,7 +122,7 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
 		seq_putc(m, '\n');
 		iput(inode);
 	} else if (mark->flags & FSNOTIFY_MARK_FLAG_VFSMOUNT) {
-		struct mount *mnt = real_mount(mark->m.mnt);
+		struct mount *mnt = real_mount(mark->mnt);
 
 		seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x ignored_mask:%x\n",
 			   mnt->mnt_id, mflags, mark->mask, mark->ignored_mask);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 41e39102743..dd3fb0b17be 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -242,13 +242,13 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
 
 		if (inode_node) {
 			inode_mark = hlist_entry(srcu_dereference(inode_node, &fsnotify_mark_srcu),
-						 struct fsnotify_mark, i.i_list);
+						 struct fsnotify_mark, obj_list);
 			inode_group = inode_mark->group;
 		}
 
 		if (vfsmount_node) {
 			vfsmount_mark = hlist_entry(srcu_dereference(vfsmount_node, &fsnotify_mark_srcu),
-							struct fsnotify_mark, m.m_list);
+						    struct fsnotify_mark, obj_list);
 			vfsmount_group = vfsmount_mark->group;
 		}
 
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index 3b68b0ae0a9..13a00be516d 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -12,12 +12,19 @@ extern void fsnotify_flush_notify(struct fsnotify_group *group);
 /* protects reads of inode and vfsmount marks list */
 extern struct srcu_struct fsnotify_mark_srcu;
 
+/* Calculate mask of events for a list of marks */
+extern u32 fsnotify_recalc_mask(struct hlist_head *head);
+
 /* compare two groups for sorting of marks lists */
 extern int fsnotify_compare_groups(struct fsnotify_group *a,
 				   struct fsnotify_group *b);
 
 extern void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *fsn_mark,
 						__u32 mask);
+/* Add mark to a proper place in mark list */
+extern int fsnotify_add_mark_list(struct hlist_head *head,
+				  struct fsnotify_mark *mark,
+				  int allow_dups);
 /* add a mark to an inode */
 extern int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 				   struct fsnotify_group *group, struct inode *inode,
@@ -31,6 +38,11 @@ extern int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 extern void fsnotify_destroy_vfsmount_mark(struct fsnotify_mark *mark);
 /* inode specific destruction of a mark */
 extern void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark);
+/* Destroy all marks in the given list */
+extern void fsnotify_destroy_marks(struct list_head *to_free);
+/* Find mark belonging to given group in the list of marks */
+extern struct fsnotify_mark *fsnotify_find_mark(struct hlist_head *head,
+						struct fsnotify_group *group);
 /* run the list of all marks associated with inode and flag them to be freed */
 extern void fsnotify_clear_marks_by_inode(struct inode *inode);
 /* run the list of all marks associated with vfsmount and flag them to be freed */
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index dfbf5447eea..3daf513ee99 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -30,21 +30,6 @@
 
 #include "../internal.h"
 
-/*
- * Recalculate the mask of events relevant to a given inode locked.
- */
-static void fsnotify_recalc_inode_mask_locked(struct inode *inode)
-{
-	struct fsnotify_mark *mark;
-	__u32 new_mask = 0;
-
-	assert_spin_locked(&inode->i_lock);
-
-	hlist_for_each_entry(mark, &inode->i_fsnotify_marks, i.i_list)
-		new_mask |= mark->mask;
-	inode->i_fsnotify_mask = new_mask;
-}
-
 /*
  * Recalculate the inode->i_fsnotify_mask, or the mask of all FS_* event types
  * any notifier is interested in hearing for this inode.
@@ -52,7 +37,7 @@ static void fsnotify_recalc_inode_mask_locked(struct inode *inode)
 void fsnotify_recalc_inode_mask(struct inode *inode)
 {
 	spin_lock(&inode->i_lock);
-	fsnotify_recalc_inode_mask_locked(inode);
+	inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
 	spin_unlock(&inode->i_lock);
 
 	__fsnotify_update_child_dentry_flags(inode);
@@ -60,23 +45,22 @@ void fsnotify_recalc_inode_mask(struct inode *inode)
 
 void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark)
 {
-	struct inode *inode = mark->i.inode;
+	struct inode *inode = mark->inode;
 
 	BUG_ON(!mutex_is_locked(&mark->group->mark_mutex));
 	assert_spin_locked(&mark->lock);
 
 	spin_lock(&inode->i_lock);
 
-	hlist_del_init_rcu(&mark->i.i_list);
-	mark->i.inode = NULL;
+	hlist_del_init_rcu(&mark->obj_list);
+	mark->inode = NULL;
 
 	/*
 	 * this mark is now off the inode->i_fsnotify_marks list and we
 	 * hold the inode->i_lock, so this is the perfect time to update the
 	 * inode->i_fsnotify_mask
 	 */
-	fsnotify_recalc_inode_mask_locked(inode);
-
+	inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
 	spin_unlock(&inode->i_lock);
 }
 
@@ -85,30 +69,19 @@ void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark)
  */
 void fsnotify_clear_marks_by_inode(struct inode *inode)
 {
-	struct fsnotify_mark *mark, *lmark;
+	struct fsnotify_mark *mark;
 	struct hlist_node *n;
 	LIST_HEAD(free_list);
 
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry_safe(mark, n, &inode->i_fsnotify_marks, i.i_list) {
-		list_add(&mark->i.free_i_list, &free_list);
-		hlist_del_init_rcu(&mark->i.i_list);
+	hlist_for_each_entry_safe(mark, n, &inode->i_fsnotify_marks, obj_list) {
+		list_add(&mark->free_list, &free_list);
+		hlist_del_init_rcu(&mark->obj_list);
 		fsnotify_get_mark(mark);
 	}
 	spin_unlock(&inode->i_lock);
 
-	list_for_each_entry_safe(mark, lmark, &free_list, i.free_i_list) {
-		struct fsnotify_group *group;
-
-		spin_lock(&mark->lock);
-		fsnotify_get_group(mark->group);
-		group = mark->group;
-		spin_unlock(&mark->lock);
-
-		fsnotify_destroy_mark(mark, group);
-		fsnotify_put_mark(mark);
-		fsnotify_put_group(group);
-	}
+	fsnotify_destroy_marks(&free_list);
 }
 
 /*
@@ -119,27 +92,6 @@ void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
 	fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_MARK_FLAG_INODE);
 }
 
-/*
- * given a group and inode, find the mark associated with that combination.
- * if found take a reference to that mark and return it, else return NULL
- */
-static struct fsnotify_mark *fsnotify_find_inode_mark_locked(
-		struct fsnotify_group *group,
-		struct inode *inode)
-{
-	struct fsnotify_mark *mark;
-
-	assert_spin_locked(&inode->i_lock);
-
-	hlist_for_each_entry(mark, &inode->i_fsnotify_marks, i.i_list) {
-		if (mark->group == group) {
-			fsnotify_get_mark(mark);
-			return mark;
-		}
-	}
-	return NULL;
-}
-
 /*
  * given a group and inode, find the mark associated with that combination.
  * if found take a reference to that mark and return it, else return NULL
@@ -150,7 +102,7 @@ struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group,
 	struct fsnotify_mark *mark;
 
 	spin_lock(&inode->i_lock);
-	mark = fsnotify_find_inode_mark_locked(group, inode);
+	mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
 	spin_unlock(&inode->i_lock);
 
 	return mark;
@@ -168,10 +120,10 @@ void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *mark,
 	assert_spin_locked(&mark->lock);
 
 	if (mask &&
-	    mark->i.inode &&
+	    mark->inode &&
 	    !(mark->flags & FSNOTIFY_MARK_FLAG_OBJECT_PINNED)) {
 		mark->flags |= FSNOTIFY_MARK_FLAG_OBJECT_PINNED;
-		inode = igrab(mark->i.inode);
+		inode = igrab(mark->inode);
 		/*
 		 * we shouldn't be able to get here if the inode wasn't
 		 * already safely held in memory.  But bug in case it
@@ -192,9 +144,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 			    struct fsnotify_group *group, struct inode *inode,
 			    int allow_dups)
 {
-	struct fsnotify_mark *lmark, *last = NULL;
-	int ret = 0;
-	int cmp;
+	int ret;
 
 	mark->flags |= FSNOTIFY_MARK_FLAG_INODE;
 
@@ -202,37 +152,10 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 	assert_spin_locked(&mark->lock);
 
 	spin_lock(&inode->i_lock);
-
-	mark->i.inode = inode;
-
-	/* is mark the first mark? */
-	if (hlist_empty(&inode->i_fsnotify_marks)) {
-		hlist_add_head_rcu(&mark->i.i_list, &inode->i_fsnotify_marks);
-		goto out;
-	}
-
-	/* should mark be in the middle of the current list? */
-	hlist_for_each_entry(lmark, &inode->i_fsnotify_marks, i.i_list) {
-		last = lmark;
-
-		if ((lmark->group == group) && !allow_dups) {
-			ret = -EEXIST;
-			goto out;
-		}
-
-		cmp = fsnotify_compare_groups(lmark->group, mark->group);
-		if (cmp < 0)
-			continue;
-
-		hlist_add_before_rcu(&mark->i.i_list, &lmark->i.i_list);
-		goto out;
-	}
-
-	BUG_ON(last == NULL);
-	/* mark should be the last entry.  last is the current last entry */
-	hlist_add_behind_rcu(&mark->i.i_list, &last->i.i_list);
-out:
-	fsnotify_recalc_inode_mask_locked(inode);
+	mark->inode = inode;
+	ret = fsnotify_add_mark_list(&inode->i_fsnotify_marks, mark,
+				     allow_dups);
+	inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
 	spin_unlock(&inode->i_lock);
 
 	return ret;
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 7d888d77d59..2cd900c2c73 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -156,7 +156,7 @@ static int idr_callback(int id, void *p, void *data)
 	 */
 	if (fsn_mark)
 		printk(KERN_WARNING "fsn_mark->group=%p inode=%p wd=%d\n",
-			fsn_mark->group, fsn_mark->i.inode, i_mark->wd);
+			fsn_mark->group, fsn_mark->inode, i_mark->wd);
 	return 0;
 }
 
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 283aa312d74..45064869743 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -433,7 +433,7 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
 	if (wd == -1) {
 		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p"
 			" i_mark->inode=%p\n", __func__, i_mark, i_mark->wd,
-			i_mark->fsn_mark.group, i_mark->fsn_mark.i.inode);
+			i_mark->fsn_mark.group, i_mark->fsn_mark.inode);
 		goto out;
 	}
 
@@ -442,7 +442,7 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
 	if (unlikely(!found_i_mark)) {
 		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p"
 			" i_mark->inode=%p\n", __func__, i_mark, i_mark->wd,
-			i_mark->fsn_mark.group, i_mark->fsn_mark.i.inode);
+			i_mark->fsn_mark.group, i_mark->fsn_mark.inode);
 		goto out;
 	}
 
@@ -456,9 +456,9 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
 			"mark->inode=%p found_i_mark=%p found_i_mark->wd=%d "
 			"found_i_mark->group=%p found_i_mark->inode=%p\n",
 			__func__, i_mark, i_mark->wd, i_mark->fsn_mark.group,
-			i_mark->fsn_mark.i.inode, found_i_mark, found_i_mark->wd,
+			i_mark->fsn_mark.inode, found_i_mark, found_i_mark->wd,
 			found_i_mark->fsn_mark.group,
-			found_i_mark->fsn_mark.i.inode);
+			found_i_mark->fsn_mark.inode);
 		goto out;
 	}
 
@@ -470,7 +470,7 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
 	if (unlikely(atomic_read(&i_mark->fsn_mark.refcnt) < 3)) {
 		printk(KERN_ERR "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p"
 			" i_mark->inode=%p\n", __func__, i_mark, i_mark->wd,
-			i_mark->fsn_mark.group, i_mark->fsn_mark.i.inode);
+			i_mark->fsn_mark.group, i_mark->fsn_mark.inode);
 		/* we can't really recover with bad ref cnting.. */
 		BUG();
 	}
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 34c38fabf51..3942d5c9eb8 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -110,6 +110,17 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
 	}
 }
 
+/* Calculate mask of events for a list of marks */
+u32 fsnotify_recalc_mask(struct hlist_head *head)
+{
+	u32 new_mask = 0;
+	struct fsnotify_mark *mark;
+
+	hlist_for_each_entry(mark, head, obj_list)
+		new_mask |= mark->mask;
+	return new_mask;
+}
+
 /*
  * Any time a mark is getting freed we end up here.
  * The caller had better be holding a reference to this mark so we don't actually
@@ -133,7 +144,7 @@ void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
 	mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
 
 	if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) {
-		inode = mark->i.inode;
+		inode = mark->inode;
 		fsnotify_destroy_inode_mark(mark);
 	} else if (mark->flags & FSNOTIFY_MARK_FLAG_VFSMOUNT)
 		fsnotify_destroy_vfsmount_mark(mark);
@@ -192,6 +203,27 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 	mutex_unlock(&group->mark_mutex);
 }
 
+/*
+ * Destroy all marks in the given list. The marks must be already detached from
+ * the original inode / vfsmount.
+ */
+void fsnotify_destroy_marks(struct list_head *to_free)
+{
+	struct fsnotify_mark *mark, *lmark;
+	struct fsnotify_group *group;
+
+	list_for_each_entry_safe(mark, lmark, to_free, free_list) {
+		spin_lock(&mark->lock);
+		fsnotify_get_group(mark->group);
+		group = mark->group;
+		spin_unlock(&mark->lock);
+
+		fsnotify_destroy_mark(mark, group);
+		fsnotify_put_mark(mark);
+		fsnotify_put_group(group);
+	}
+}
+
 void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask)
 {
 	assert_spin_locked(&mark->lock);
@@ -245,6 +277,39 @@ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
 	return -1;
 }
 
+/* Add mark into proper place in given list of marks */
+int fsnotify_add_mark_list(struct hlist_head *head, struct fsnotify_mark *mark,
+			   int allow_dups)
+{
+	struct fsnotify_mark *lmark, *last = NULL;
+	int cmp;
+
+	/* is mark the first mark? */
+	if (hlist_empty(head)) {
+		hlist_add_head_rcu(&mark->obj_list, head);
+		return 0;
+	}
+
+	/* should mark be in the middle of the current list? */
+	hlist_for_each_entry(lmark, head, obj_list) {
+		last = lmark;
+
+		if ((lmark->group == mark->group) && !allow_dups)
+			return -EEXIST;
+
+		cmp = fsnotify_compare_groups(lmark->group, mark->group);
+		if (cmp >= 0) {
+			hlist_add_before_rcu(&mark->obj_list, &lmark->obj_list);
+			return 0;
+		}
+	}
+
+	BUG_ON(last == NULL);
+	/* mark should be the last entry.  last is the current last entry */
+	hlist_add_behind_rcu(&mark->obj_list, &last->obj_list);
+	return 0;
+}
+
 /*
  * Attach an initialized mark to a given group and fs object.
  * These marks may be used for the fsnotify backend to determine which
@@ -322,6 +387,24 @@ int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
 	return ret;
 }
 
+/*
+ * Given a list of marks, find the mark associated with given group. If found
+ * take a reference to that mark and return it, else return NULL.
+ */
+struct fsnotify_mark *fsnotify_find_mark(struct hlist_head *head,
+					 struct fsnotify_group *group)
+{
+	struct fsnotify_mark *mark;
+
+	hlist_for_each_entry(mark, head, obj_list) {
+		if (mark->group == group) {
+			fsnotify_get_mark(mark);
+			return mark;
+		}
+	}
+	return NULL;
+}
+
 /*
  * clear any marks in a group in which mark->flags & flags is true
  */
@@ -352,8 +435,8 @@ void fsnotify_clear_marks_by_group(struct fsnotify_group *group)
 void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old)
 {
 	assert_spin_locked(&old->lock);
-	new->i.inode = old->i.inode;
-	new->m.mnt = old->m.mnt;
+	new->inode = old->inode;
+	new->mnt = old->mnt;
 	if (old->group)
 		fsnotify_get_group(old->group);
 	new->group = old->group;
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index faefa72a11e..326b148e623 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -32,31 +32,20 @@
 
 void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
 {
-	struct fsnotify_mark *mark, *lmark;
+	struct fsnotify_mark *mark;
 	struct hlist_node *n;
 	struct mount *m = real_mount(mnt);
 	LIST_HEAD(free_list);
 
 	spin_lock(&mnt->mnt_root->d_lock);
-	hlist_for_each_entry_safe(mark, n, &m->mnt_fsnotify_marks, m.m_list) {
-		list_add(&mark->m.free_m_list, &free_list);
-		hlist_del_init_rcu(&mark->m.m_list);
+	hlist_for_each_entry_safe(mark, n, &m->mnt_fsnotify_marks, obj_list) {
+		list_add(&mark->free_list, &free_list);
+		hlist_del_init_rcu(&mark->obj_list);
 		fsnotify_get_mark(mark);
 	}
 	spin_unlock(&mnt->mnt_root->d_lock);
 
-	list_for_each_entry_safe(mark, lmark, &free_list, m.free_m_list) {
-		struct fsnotify_group *group;
-
-		spin_lock(&mark->lock);
-		fsnotify_get_group(mark->group);
-		group = mark->group;
-		spin_unlock(&mark->lock);
-
-		fsnotify_destroy_mark(mark, group);
-		fsnotify_put_mark(mark);
-		fsnotify_put_group(group);
-	}
+	fsnotify_destroy_marks(&free_list);
 }
 
 void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
@@ -64,67 +53,36 @@ void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
 	fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_MARK_FLAG_VFSMOUNT);
 }
 
-/*
- * Recalculate the mask of events relevant to a given vfsmount locked.
- */
-static void fsnotify_recalc_vfsmount_mask_locked(struct vfsmount *mnt)
-{
-	struct mount *m = real_mount(mnt);
-	struct fsnotify_mark *mark;
-	__u32 new_mask = 0;
-
-	assert_spin_locked(&mnt->mnt_root->d_lock);
-
-	hlist_for_each_entry(mark, &m->mnt_fsnotify_marks, m.m_list)
-		new_mask |= mark->mask;
-	m->mnt_fsnotify_mask = new_mask;
-}
-
 /*
  * Recalculate the mnt->mnt_fsnotify_mask, or the mask of all FS_* event types
  * any notifier is interested in hearing for this mount point
  */
 void fsnotify_recalc_vfsmount_mask(struct vfsmount *mnt)
 {
+	struct mount *m = real_mount(mnt);
+
 	spin_lock(&mnt->mnt_root->d_lock);
-	fsnotify_recalc_vfsmount_mask_locked(mnt);
+	m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
 	spin_unlock(&mnt->mnt_root->d_lock);
 }
 
 void fsnotify_destroy_vfsmount_mark(struct fsnotify_mark *mark)
 {
-	struct vfsmount *mnt = mark->m.mnt;
+	struct vfsmount *mnt = mark->mnt;
+	struct mount *m = real_mount(mnt);
 
 	BUG_ON(!mutex_is_locked(&mark->group->mark_mutex));
 	assert_spin_locked(&mark->lock);
 
 	spin_lock(&mnt->mnt_root->d_lock);
 
-	hlist_del_init_rcu(&mark->m.m_list);
-	mark->m.mnt = NULL;
-
-	fsnotify_recalc_vfsmount_mask_locked(mnt);
+	hlist_del_init_rcu(&mark->obj_list);
+	mark->mnt = NULL;
 
+	m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
 	spin_unlock(&mnt->mnt_root->d_lock);
 }
 
-static struct fsnotify_mark *fsnotify_find_vfsmount_mark_locked(struct fsnotify_group *group,
-								struct vfsmount *mnt)
-{
-	struct mount *m = real_mount(mnt);
-	struct fsnotify_mark *mark;
-
-	assert_spin_locked(&mnt->mnt_root->d_lock);
-
-	hlist_for_each_entry(mark, &m->mnt_fsnotify_marks, m.m_list) {
-		if (mark->group == group) {
-			fsnotify_get_mark(mark);
-			return mark;
-		}
-	}
-	return NULL;
-}
-
 /*
  * given a group and vfsmount, find the mark associated with that combination.
  * if found take a reference to that mark and return it, else return NULL
@@ -132,10 +90,11 @@ static struct fsnotify_mark *fsnotify_find_vfsmount_mark_locked(struct fsnotify_
 struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group,
 						  struct vfsmount *mnt)
 {
+	struct mount *m = real_mount(mnt);
 	struct fsnotify_mark *mark;
 
 	spin_lock(&mnt->mnt_root->d_lock);
-	mark = fsnotify_find_vfsmount_mark_locked(group, mnt);
+	mark = fsnotify_find_mark(&m->mnt_fsnotify_marks, group);
 	spin_unlock(&mnt->mnt_root->d_lock);
 
 	return mark;
@@ -151,9 +110,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 			       int allow_dups)
 {
 	struct mount *m = real_mount(mnt);
-	struct fsnotify_mark *lmark, *last = NULL;
-	int ret = 0;
-	int cmp;
+	int ret;
 
 	mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT;
 
@@ -161,37 +118,9 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 	assert_spin_locked(&mark->lock);
 
 	spin_lock(&mnt->mnt_root->d_lock);
-
-	mark->m.mnt = mnt;
-
-	/* is mark the first mark? */
-	if (hlist_empty(&m->mnt_fsnotify_marks)) {
-		hlist_add_head_rcu(&mark->m.m_list, &m->mnt_fsnotify_marks);
-		goto out;
-	}
-
-	/* should mark be in the middle of the current list? */
-	hlist_for_each_entry(lmark, &m->mnt_fsnotify_marks, m.m_list) {
-		last = lmark;
-
-		if ((lmark->group == group) && !allow_dups) {
-			ret = -EEXIST;
-			goto out;
-		}
-
-		cmp = fsnotify_compare_groups(lmark->group, mark->group);
-		if (cmp < 0)
-			continue;
-
-		hlist_add_before_rcu(&mark->m.m_list, &lmark->m.m_list);
-		goto out;
-	}
-
-	BUG_ON(last == NULL);
-	/* mark should be the last entry.  last is the current last entry */
-	hlist_add_behind_rcu(&mark->m.m_list, &last->m.m_list);
-out:
-	fsnotify_recalc_vfsmount_mask_locked(mnt);
+	mark->mnt = mnt;
+	ret = fsnotify_add_mark_list(&m->mnt_fsnotify_marks, mark, allow_dups);
+	m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
 	spin_unlock(&mnt->mnt_root->d_lock);
 
 	return ret;
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index ca060d7c4fa..442847a02b8 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -196,24 +196,6 @@ struct fsnotify_group {
 #define FSNOTIFY_EVENT_PATH	1
 #define FSNOTIFY_EVENT_INODE	2
 
-/*
- * Inode specific fields in an fsnotify_mark
- */
-struct fsnotify_inode_mark {
-	struct inode *inode;		/* inode this mark is associated with */
-	struct hlist_node i_list;	/* list of marks by inode->i_fsnotify_marks */
-	struct list_head free_i_list;	/* tmp list used when freeing this mark */
-};
-
-/*
- * Mount point specific fields in an fsnotify_mark
- */
-struct fsnotify_vfsmount_mark {
-	struct vfsmount *mnt;		/* vfsmount this mark is associated with */
-	struct hlist_node m_list;	/* list of marks by inode->i_fsnotify_marks */
-	struct list_head free_m_list;	/* tmp list used when freeing this mark */
-};
-
 /*
  * a mark is simply an object attached to an in core inode which allows an
  * fsnotify listener to indicate they are either no longer interested in events
@@ -232,9 +214,11 @@ struct fsnotify_mark {
 	struct fsnotify_group *group;	/* group this mark is for */
 	struct list_head g_list;	/* list of marks by group->i_fsnotify_marks */
 	spinlock_t lock;		/* protect group and inode */
+	struct hlist_node obj_list;	/* list of marks for inode / vfsmount */
+	struct list_head free_list;	/* tmp list used when freeing this mark */
 	union {
-		struct fsnotify_inode_mark i;
-		struct fsnotify_vfsmount_mark m;
+		struct inode *inode;	/* inode this mark is associated with */
+		struct vfsmount *mnt;	/* vfsmount this mark is associated with */
 	};
 	__u32 ignored_mask;		/* events types to ignore */
 #define FSNOTIFY_MARK_FLAG_INODE		0x01
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 80f29e01557..2e0c97427b3 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -174,9 +174,9 @@ static void insert_hash(struct audit_chunk *chunk)
 	struct fsnotify_mark *entry = &chunk->mark;
 	struct list_head *list;
 
-	if (!entry->i.inode)
+	if (!entry->inode)
 		return;
-	list = chunk_hash(entry->i.inode);
+	list = chunk_hash(entry->inode);
 	list_add_rcu(&chunk->hash, list);
 }
 
@@ -188,7 +188,7 @@ struct audit_chunk *audit_tree_lookup(const struct inode *inode)
 
 	list_for_each_entry_rcu(p, list, hash) {
 		/* mark.inode may have gone NULL, but who cares? */
-		if (p->mark.i.inode == inode) {
+		if (p->mark.inode == inode) {
 			atomic_long_inc(&p->refs);
 			return p;
 		}
@@ -231,7 +231,7 @@ static void untag_chunk(struct node *p)
 		new = alloc_chunk(size);
 
 	spin_lock(&entry->lock);
-	if (chunk->dead || !entry->i.inode) {
+	if (chunk->dead || !entry->inode) {
 		spin_unlock(&entry->lock);
 		if (new)
 			free_chunk(new);
@@ -258,7 +258,7 @@ static void untag_chunk(struct node *p)
 		goto Fallback;
 
 	fsnotify_duplicate_mark(&new->mark, entry);
-	if (fsnotify_add_mark(&new->mark, new->mark.group, new->mark.i.inode, NULL, 1)) {
+	if (fsnotify_add_mark(&new->mark, new->mark.group, new->mark.inode, NULL, 1)) {
 		fsnotify_put_mark(&new->mark);
 		goto Fallback;
 	}
@@ -386,7 +386,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	chunk_entry = &chunk->mark;
 
 	spin_lock(&old_entry->lock);
-	if (!old_entry->i.inode) {
+	if (!old_entry->inode) {
 		/* old_entry is being shot, lets just lie */
 		spin_unlock(&old_entry->lock);
 		fsnotify_put_mark(old_entry);
@@ -395,7 +395,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	}
 
 	fsnotify_duplicate_mark(chunk_entry, old_entry);
-	if (fsnotify_add_mark(chunk_entry, chunk_entry->group, chunk_entry->i.inode, NULL, 1)) {
+	if (fsnotify_add_mark(chunk_entry, chunk_entry->group, chunk_entry->inode, NULL, 1)) {
 		spin_unlock(&old_entry->lock);
 		fsnotify_put_mark(chunk_entry);
 		fsnotify_put_mark(old_entry);
@@ -611,7 +611,7 @@ void audit_trim_trees(void)
 		list_for_each_entry(node, &tree->chunks, list) {
 			struct audit_chunk *chunk = find_chunk(node);
 			/* this could be NULL if the watch is dying else where... */
-			struct inode *inode = chunk->mark.i.inode;
+			struct inode *inode = chunk->mark.inode;
 			node->index |= 1U<<31;
 			if (iterate_mounts(compare_root, inode, root_mnt))
 				node->index &= ~(1U<<31);
-- 
cgit v1.2.3-70-g09d2


From 37d469e7673a663cbf38360beb1eaa3224c9d272 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Fri, 12 Dec 2014 16:58:39 -0800
Subject: fsnotify: remove destroy_list from fsnotify_mark

destroy_list is used to track marks which still need waiting for srcu
period end before they can be freed.  However by the time mark is added to
destroy_list it isn't in group's list of marks anymore and thus we can
reuse fsnotify_mark->g_list for queueing into destroy_list.  This saves
two pointers for each fsnotify_mark.

Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Eric Paris <eparis@redhat.com>
Cc: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/notify/mark.c                 | 8 ++++----
 include/linux/fsnotify_backend.h | 7 +++++--
 2 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 3942d5c9eb8..92e48c70f0f 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -161,7 +161,7 @@ void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
 	mutex_unlock(&group->mark_mutex);
 
 	spin_lock(&destroy_lock);
-	list_add(&mark->destroy_list, &destroy_list);
+	list_add(&mark->g_list, &destroy_list);
 	spin_unlock(&destroy_lock);
 	wake_up(&destroy_waitq);
 	/*
@@ -370,7 +370,7 @@ err:
 	spin_unlock(&mark->lock);
 
 	spin_lock(&destroy_lock);
-	list_add(&mark->destroy_list, &destroy_list);
+	list_add(&mark->g_list, &destroy_list);
 	spin_unlock(&destroy_lock);
 	wake_up(&destroy_waitq);
 
@@ -469,8 +469,8 @@ static int fsnotify_mark_destroy(void *ignored)
 
 		synchronize_srcu(&fsnotify_mark_srcu);
 
-		list_for_each_entry_safe(mark, next, &private_destroy_list, destroy_list) {
-			list_del_init(&mark->destroy_list);
+		list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
+			list_del_init(&mark->g_list);
 			fsnotify_put_mark(mark);
 		}
 
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 442847a02b8..0f313f93c58 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -212,7 +212,11 @@ struct fsnotify_mark {
 	 * in kernel that found and may be using this mark. */
 	atomic_t refcnt;		/* active things looking at this mark */
 	struct fsnotify_group *group;	/* group this mark is for */
-	struct list_head g_list;	/* list of marks by group->i_fsnotify_marks */
+	struct list_head g_list;	/* list of marks by group->i_fsnotify_marks
+					 * Also reused for queueing mark into
+					 * destroy_list when it's waiting for
+					 * the end of SRCU period before it can
+					 * be freed */
 	spinlock_t lock;		/* protect group and inode */
 	struct hlist_node obj_list;	/* list of marks for inode / vfsmount */
 	struct list_head free_list;	/* tmp list used when freeing this mark */
@@ -227,7 +231,6 @@ struct fsnotify_mark {
 #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY	0x08
 #define FSNOTIFY_MARK_FLAG_ALIVE		0x10
 	unsigned int flags;		/* vfsmount or inode mark? */
-	struct list_head destroy_list;
 	void (*free_mark)(struct fsnotify_mark *mark); /* called on final put+free */
 };
 
-- 
cgit v1.2.3-70-g09d2


From 6c51ec4d18d24b2ffa69de5d60bebaeb4f8e2398 Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux.com>
Date: Fri, 12 Dec 2014 16:58:42 -0800
Subject: percpu: remove __get_cpu_var and __raw_get_cpu_var macros

No user is left in the kernel source tree.  Therefore we can drop the
definitions.

This is the final merge of the transition away from __get_cpu_var.  After
this patch the kernel will not build if anyone uses __get_cpu_var.

Signed-off-by: Christoph Lameter <cl@linux.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/percpu-defs.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 420032d41d2..57f3a1c550d 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -254,8 +254,6 @@ do {									\
 #endif	/* CONFIG_SMP */
 
 #define per_cpu(var, cpu)	(*per_cpu_ptr(&(var), cpu))
-#define __raw_get_cpu_var(var)	(*raw_cpu_ptr(&(var)))
-#define __get_cpu_var(var)	(*this_cpu_ptr(&(var)))
 
 /*
  * Must be an lvalue. Since @var must be a simple identifier,
-- 
cgit v1.2.3-70-g09d2


From e4a0d3e720e7e508749c1439b5ba3aff56c92976 Mon Sep 17 00:00:00 2001
From: Pavel Emelyanov <xemul@parallels.com>
Date: Thu, 18 Sep 2014 19:56:17 +0400
Subject: aio: Make it possible to remap aio ring

There are actually two issues this patch addresses. Let me start with
the one I tried to solve in the beginning.

So, in the checkpoint-restore project (criu) we try to dump tasks'
state and restore one back exactly as it was. One of the tasks' state
bits is rings set up with io_setup() call. There's (almost) no problems
in dumping them, there's a problem restoring them -- if I dump a task
with aio ring originally mapped at address A, I want to restore one
back at exactly the same address A. Unfortunately, the io_setup() does
not allow for that -- it mmaps the ring at whatever place mm finds
appropriate (it calls do_mmap_pgoff() with zero address and without
the MAP_FIXED flag).

To make restore possible I'm going to mremap() the freshly created ring
into the address A (under which it was seen before dump). The problem is
that the ring's virtual address is passed back to the user-space as the
context ID and this ID is then used as search key by all the other io_foo()
calls. Reworking this ID to be just some integer doesn't seem to work, as
this value is already used by libaio as a pointer using which this library
accesses memory for aio meta-data.

So, to make restore work we need to make sure that

a) ring is mapped at desired virtual address
b) kioctx->user_id matches this value

Having said that, the patch makes mremap() on aio region update the
kioctx's user_id and mmap_base values.

Here appears the 2nd issue I mentioned in the beginning of this mail.
If (regardless of the C/R dances I do) someone creates an io context
with io_setup(), then mremap()-s the ring and then destroys the context,
the kill_ioctx() routine will call munmap() on wrong (old) address.
This will result in a) aio ring remaining in memory and b) some other
vma get unexpectedly unmapped.

What do you think?

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Benjamin LaHaise <bcrl@kvack.org>
---
 fs/aio.c           | 25 +++++++++++++++++++++++++
 include/linux/fs.h |  1 +
 mm/mremap.c        |  3 ++-
 3 files changed, 28 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/aio.c b/fs/aio.c
index 14b93159ef8..bfab55607a4 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -286,12 +286,37 @@ static void aio_free_ring(struct kioctx *ctx)
 
 static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma)
 {
+	vma->vm_flags |= VM_DONTEXPAND;
 	vma->vm_ops = &generic_file_vm_ops;
 	return 0;
 }
 
+static void aio_ring_remap(struct file *file, struct vm_area_struct *vma)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct kioctx_table *table;
+	int i;
+
+	spin_lock(&mm->ioctx_lock);
+	rcu_read_lock();
+	table = rcu_dereference(mm->ioctx_table);
+	for (i = 0; i < table->nr; i++) {
+		struct kioctx *ctx;
+
+		ctx = table->table[i];
+		if (ctx && ctx->aio_ring_file == file) {
+			ctx->user_id = ctx->mmap_base = vma->vm_start;
+			break;
+		}
+	}
+
+	rcu_read_unlock();
+	spin_unlock(&mm->ioctx_lock);
+}
+
 static const struct file_operations aio_ring_fops = {
 	.mmap = aio_ring_mmap,
+	.mremap = aio_ring_remap,
 };
 
 #if IS_ENABLED(CONFIG_MIGRATION)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9ab779e8a63..85f378c55c2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1497,6 +1497,7 @@ struct file_operations {
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
+	void (*mremap)(struct file *, struct vm_area_struct *);
 	int (*open) (struct inode *, struct file *);
 	int (*flush) (struct file *, fl_owner_t id);
 	int (*release) (struct inode *, struct file *);
diff --git a/mm/mremap.c b/mm/mremap.c
index b147f66f4c4..c855922497a 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -288,7 +288,8 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 		old_len = new_len;
 		old_addr = new_addr;
 		new_addr = -ENOMEM;
-	}
+	} else if (vma->vm_file && vma->vm_file->f_op->mremap)
+		vma->vm_file->f_op->mremap(vma->vm_file, new_vma);
 
 	/* Conceal VM_ACCOUNT so old reservation is not undone */
 	if (vm_flags & VM_ACCOUNT) {
-- 
cgit v1.2.3-70-g09d2


From 0dce3771fdd1db03c6f498594a34bba5a6d1f870 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 11 Dec 2014 13:46:52 +0200
Subject: virtio_pci: add VIRTIO_PCI_NO_LEGACY

Add macro to disable all legacy register defines.
Helpful to make sure legacy macros don't leak
through into modern code.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/uapi/linux/virtio_pci.h | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index e5ec1caab82..35b552c7f33 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -41,6 +41,8 @@
 
 #include <linux/virtio_config.h>
 
+#ifndef VIRTIO_PCI_NO_LEGACY
+
 /* A 32-bit r/o bitmask of the features supported by the host */
 #define VIRTIO_PCI_HOST_FEATURES	0
 
@@ -67,16 +69,11 @@
  * a read-and-acknowledge. */
 #define VIRTIO_PCI_ISR			19
 
-/* The bit of the ISR which indicates a device configuration change. */
-#define VIRTIO_PCI_ISR_CONFIG		0x2
-
 /* MSI-X registers: only enabled if MSI-X is enabled. */
 /* A 16-bit vector for configuration changes. */
 #define VIRTIO_MSI_CONFIG_VECTOR        20
 /* A 16-bit vector for selected queue notifications. */
 #define VIRTIO_MSI_QUEUE_VECTOR         22
-/* Vector value used to disable MSI for queue */
-#define VIRTIO_MSI_NO_VECTOR            0xffff
 
 /* The remaining space is defined by each driver as the per-driver
  * configuration space */
@@ -94,4 +91,12 @@
 /* The alignment to use between consumer and producer parts of vring.
  * x86 pagesize again. */
 #define VIRTIO_PCI_VRING_ALIGN		4096
+
+#endif /* VIRTIO_PCI_NO_LEGACY */
+
+/* The bit of the ISR which indicates a device configuration change. */
+#define VIRTIO_PCI_ISR_CONFIG		0x2
+/* Vector value used to disable MSI for queue */
+#define VIRTIO_MSI_NO_VECTOR            0xffff
+
 #endif
-- 
cgit v1.2.3-70-g09d2


From d71de9ec6ba806104439d3a669befda84757b5af Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Sun, 14 Dec 2014 16:55:44 +0200
Subject: virtio: core support for config generation

virtio 1.0 spec says:

Drivers MUST NOT assume reads from fields greater than 32 bits wide are
atomic, nor are reads from multiple fields: drivers SHOULD read device
configuration space fields like so:
	u32 before, after;
	do {
		before = get_config_generation(device);
		// read config entry/entries.
		after = get_config_generation(device);
	} while (after != before);

Do exactly this, for transports that support it.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_config.h | 32 ++++++++++++++++++++++++++++----
 1 file changed, 28 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index a61cd37f088..ca3ed78e5ec 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -19,6 +19,9 @@
  *	offset: the offset of the configuration field
  *	buf: the buffer to read the field value from.
  *	len: the length of the buffer
+ * @generation: config generation counter
+ *	vdev: the virtio_device
+ *	Returns the config generation counter
  * @get_status: read the status byte
  *	vdev: the virtio_device
  *	Returns the status byte
@@ -60,6 +63,7 @@ struct virtio_config_ops {
 		    void *buf, unsigned len);
 	void (*set)(struct virtio_device *vdev, unsigned offset,
 		    const void *buf, unsigned len);
+	u32 (*generation)(struct virtio_device *vdev);
 	u8 (*get_status)(struct virtio_device *vdev);
 	void (*set_status)(struct virtio_device *vdev, u8 status);
 	void (*reset)(struct virtio_device *vdev);
@@ -301,14 +305,33 @@ static inline u8 virtio_cread8(struct virtio_device *vdev, unsigned int offset)
 	return ret;
 }
 
+/* Read @count fields, @bytes each. */
+static inline void __virtio_cread_many(struct virtio_device *vdev,
+				       unsigned int offset,
+				       void *buf, size_t count, size_t bytes)
+{
+	u32 old, gen = vdev->config->generation ?
+		vdev->config->generation(vdev) : 0;
+	int i;
+
+	do {
+		old = gen;
+
+		for (i = 0; i < count; i++)
+			vdev->config->get(vdev, offset + bytes * i,
+					  buf + i * bytes, bytes);
+
+		gen = vdev->config->generation ?
+			vdev->config->generation(vdev) : 0;
+	} while (gen != old);
+}
+
+
 static inline void virtio_cread_bytes(struct virtio_device *vdev,
 				      unsigned int offset,
 				      void *buf, size_t len)
 {
-	int i;
-
-	for (i = 0; i < len; i++)
-		vdev->config->get(vdev, offset + i, buf + i, 1);
+	__virtio_cread_many(vdev, offset, buf, len, 1);
 }
 
 static inline void virtio_cwrite8(struct virtio_device *vdev,
@@ -352,6 +375,7 @@ static inline u64 virtio_cread64(struct virtio_device *vdev,
 {
 	u64 ret;
 	vdev->config->get(vdev, offset, &ret, sizeof(ret));
+	__virtio_cread_many(vdev, offset, &ret, 1, sizeof(ret));
 	return virtio64_to_cpu(vdev, (__force __virtio64)ret);
 }
 
-- 
cgit v1.2.3-70-g09d2


From 05971120fca43e0357789a14b3386bb56eef2201 Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Fri, 12 Dec 2014 21:19:23 +0100
Subject: arm/arm64: KVM: Require in-kernel vgic for the arch timers

It is curently possible to run a VM with architected timers support
without creating an in-kernel VGIC, which will result in interrupts from
the virtual timer going nowhere.

To address this issue, move the architected timers initialization to the
time when we run a VCPU for the first time, and then only initialize
(and enable) the architected timers if we have a properly created and
initialized in-kernel VGIC.

When injecting interrupts from the virtual timer to the vgic, the
current setup should ensure that this never calls an on-demand init of
the VGIC, which is the only call path that could return an error from
kvm_vgic_inject_irq(), so capture the return value and raise a warning
if there's an error there.

We also change the kvm_timer_init() function from returning an int to be
a void function, since the function always succeeds.

Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 arch/arm/kvm/arm.c           | 13 +++++++++++--
 include/kvm/arm_arch_timer.h | 10 ++++------
 virt/kvm/arm/arch_timer.c    | 30 ++++++++++++++++++++++--------
 3 files changed, 37 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 66f37c4cdf1..2d6d9100106 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -425,6 +425,7 @@ static void update_vttbr(struct kvm *kvm)
 
 static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 {
+	struct kvm *kvm = vcpu->kvm;
 	int ret;
 
 	if (likely(vcpu->arch.has_run_once))
@@ -436,12 +437,20 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	 * Map the VGIC hardware resources before running a vcpu the first
 	 * time on this VM.
 	 */
-	if (unlikely(!vgic_ready(vcpu->kvm))) {
-		ret = kvm_vgic_map_resources(vcpu->kvm);
+	if (unlikely(!vgic_ready(kvm))) {
+		ret = kvm_vgic_map_resources(kvm);
 		if (ret)
 			return ret;
 	}
 
+	/*
+	 * Enable the arch timers only if we have an in-kernel VGIC
+	 * and it has been properly initialized, since we cannot handle
+	 * interrupts from the virtual timer with a userspace gic.
+	 */
+	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm))
+		kvm_timer_enable(kvm);
+
 	return 0;
 }
 
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index ad9db6045b2..b3f45a57834 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -60,7 +60,8 @@ struct arch_timer_cpu {
 
 #ifdef CONFIG_KVM_ARM_TIMER
 int kvm_timer_hyp_init(void);
-int kvm_timer_init(struct kvm *kvm);
+void kvm_timer_enable(struct kvm *kvm);
+void kvm_timer_init(struct kvm *kvm);
 void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
 			  const struct kvm_irq_level *irq);
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
@@ -77,11 +78,8 @@ static inline int kvm_timer_hyp_init(void)
 	return 0;
 };
 
-static inline int kvm_timer_init(struct kvm *kvm)
-{
-	return 0;
-}
-
+static inline void kvm_timer_enable(struct kvm *kvm) {}
+static inline void kvm_timer_init(struct kvm *kvm) {}
 static inline void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
 					const struct kvm_irq_level *irq) {}
 static inline void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) {}
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 22fa819a9b6..1c0772b340d 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -61,12 +61,14 @@ static void timer_disarm(struct arch_timer_cpu *timer)
 
 static void kvm_timer_inject_irq(struct kvm_vcpu *vcpu)
 {
+	int ret;
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
 
 	timer->cntv_ctl |= ARCH_TIMER_CTRL_IT_MASK;
-	kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
-			    timer->irq->irq,
-			    timer->irq->level);
+	ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+				  timer->irq->irq,
+				  timer->irq->level);
+	WARN_ON(ret);
 }
 
 static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
@@ -307,12 +309,24 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
 	timer_disarm(timer);
 }
 
-int kvm_timer_init(struct kvm *kvm)
+void kvm_timer_enable(struct kvm *kvm)
 {
-	if (timecounter && wqueue) {
-		kvm->arch.timer.cntvoff = kvm_phys_timer_read();
+	if (kvm->arch.timer.enabled)
+		return;
+
+	/*
+	 * There is a potential race here between VCPUs starting for the first
+	 * time, which may be enabling the timer multiple times.  That doesn't
+	 * hurt though, because we're just setting a variable to the same
+	 * variable that it already was.  The important thing is that all
+	 * VCPUs have the enabled variable set, before entering the guest, if
+	 * the arch timers are enabled.
+	 */
+	if (timecounter && wqueue)
 		kvm->arch.timer.enabled = 1;
-	}
+}
 
-	return 0;
+void kvm_timer_init(struct kvm *kvm)
+{
+	kvm->arch.timer.cntvoff = kvm_phys_timer_read();
 }
-- 
cgit v1.2.3-70-g09d2


From 4f7ad5211eb4d331a54f3cc6832883e5e7e95eea Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Sun, 14 Dec 2014 23:13:55 +0100
Subject: SCSI / PM: Replace CONFIG_PM_RUNTIME with CONFIG_PM

After commit b2b49ccbdd54 (PM: Kconfig: Set PM_RUNTIME if PM_SLEEP is
selected) PM_RUNTIME is always set if PM is set, so #ifdef blocks
depending on CONFIG_PM_RUNTIME may now be changed to depend on
CONFIG_PM.

Replace CONFIG_PM_RUNTIME with CONFIG_PM everywhere under
drivers/scsi/ and in include/scsi/scsi_device.h.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Aaron Lu <aaron.lu@intel.com>
Acked-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/scsi_pm.c           | 10 ----------
 drivers/scsi/scsi_priv.h         |  5 ++---
 drivers/scsi/ufs/ufshcd-pci.c    | 11 ++++-------
 drivers/scsi/ufs/ufshcd-pltfrm.c | 11 ++++-------
 include/scsi/scsi_device.h       |  4 ++--
 5 files changed, 12 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_pm.c b/drivers/scsi/scsi_pm.c
index 7454498c409..9e43ae1d216 100644
--- a/drivers/scsi/scsi_pm.c
+++ b/drivers/scsi/scsi_pm.c
@@ -213,8 +213,6 @@ static int scsi_bus_restore(struct device *dev)
 
 #endif /* CONFIG_PM_SLEEP */
 
-#ifdef CONFIG_PM_RUNTIME
-
 static int sdev_runtime_suspend(struct device *dev)
 {
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
@@ -332,14 +330,6 @@ void scsi_autopm_put_host(struct Scsi_Host *shost)
 	pm_runtime_put_sync(&shost->shost_gendev);
 }
 
-#else
-
-#define scsi_runtime_suspend	NULL
-#define scsi_runtime_resume	NULL
-#define scsi_runtime_idle	NULL
-
-#endif /* CONFIG_PM_RUNTIME */
-
 const struct dev_pm_ops scsi_bus_pm_ops = {
 	.prepare =		scsi_bus_prepare,
 	.suspend =		scsi_bus_suspend,
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 2dc4a83fb84..e3902fc6627 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -155,8 +155,7 @@ static inline void scsi_netlink_exit(void) {}
 /* scsi_pm.c */
 #ifdef CONFIG_PM
 extern const struct dev_pm_ops scsi_bus_pm_ops;
-#endif
-#ifdef CONFIG_PM_RUNTIME
+
 extern void scsi_autopm_get_target(struct scsi_target *);
 extern void scsi_autopm_put_target(struct scsi_target *);
 extern int scsi_autopm_get_host(struct Scsi_Host *);
@@ -166,7 +165,7 @@ static inline void scsi_autopm_get_target(struct scsi_target *t) {}
 static inline void scsi_autopm_put_target(struct scsi_target *t) {}
 static inline int scsi_autopm_get_host(struct Scsi_Host *h) { return 0; }
 static inline void scsi_autopm_put_host(struct Scsi_Host *h) {}
-#endif /* CONFIG_PM_RUNTIME */
+#endif /* CONFIG_PM */
 
 extern struct async_domain scsi_sd_pm_domain;
 extern struct async_domain scsi_sd_probe_domain;
diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c
index 955ed558701..d15eaa466c5 100644
--- a/drivers/scsi/ufs/ufshcd-pci.c
+++ b/drivers/scsi/ufs/ufshcd-pci.c
@@ -62,12 +62,7 @@ static int ufshcd_pci_resume(struct device *dev)
 {
 	return ufshcd_system_resume(dev_get_drvdata(dev));
 }
-#else
-#define ufshcd_pci_suspend	NULL
-#define ufshcd_pci_resume	NULL
-#endif /* CONFIG_PM */
 
-#ifdef CONFIG_PM_RUNTIME
 static int ufshcd_pci_runtime_suspend(struct device *dev)
 {
 	return ufshcd_runtime_suspend(dev_get_drvdata(dev));
@@ -80,11 +75,13 @@ static int ufshcd_pci_runtime_idle(struct device *dev)
 {
 	return ufshcd_runtime_idle(dev_get_drvdata(dev));
 }
-#else /* !CONFIG_PM_RUNTIME */
+#else /* !CONFIG_PM */
+#define ufshcd_pci_suspend	NULL
+#define ufshcd_pci_resume	NULL
 #define ufshcd_pci_runtime_suspend	NULL
 #define ufshcd_pci_runtime_resume	NULL
 #define ufshcd_pci_runtime_idle	NULL
-#endif /* CONFIG_PM_RUNTIME */
+#endif /* CONFIG_PM */
 
 /**
  * ufshcd_pci_shutdown - main function to put the controller in reset state
diff --git a/drivers/scsi/ufs/ufshcd-pltfrm.c b/drivers/scsi/ufs/ufshcd-pltfrm.c
index 1c3467b8256..76d39b617db 100644
--- a/drivers/scsi/ufs/ufshcd-pltfrm.c
+++ b/drivers/scsi/ufs/ufshcd-pltfrm.c
@@ -261,12 +261,7 @@ static int ufshcd_pltfrm_resume(struct device *dev)
 {
 	return ufshcd_system_resume(dev_get_drvdata(dev));
 }
-#else
-#define ufshcd_pltfrm_suspend	NULL
-#define ufshcd_pltfrm_resume	NULL
-#endif
 
-#ifdef CONFIG_PM_RUNTIME
 static int ufshcd_pltfrm_runtime_suspend(struct device *dev)
 {
 	return ufshcd_runtime_suspend(dev_get_drvdata(dev));
@@ -279,11 +274,13 @@ static int ufshcd_pltfrm_runtime_idle(struct device *dev)
 {
 	return ufshcd_runtime_idle(dev_get_drvdata(dev));
 }
-#else /* !CONFIG_PM_RUNTIME */
+#else /* !CONFIG_PM */
+#define ufshcd_pltfrm_suspend	NULL
+#define ufshcd_pltfrm_resume	NULL
 #define ufshcd_pltfrm_runtime_suspend	NULL
 #define ufshcd_pltfrm_runtime_resume	NULL
 #define ufshcd_pltfrm_runtime_idle	NULL
-#endif /* CONFIG_PM_RUNTIME */
+#endif /* CONFIG_PM */
 
 static void ufshcd_pltfrm_shutdown(struct platform_device *pdev)
 {
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 6364e23454d..3a4edd1f7db 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -441,13 +441,13 @@ static inline int scsi_execute_req(struct scsi_device *sdev,
 extern void sdev_disable_disk_events(struct scsi_device *sdev);
 extern void sdev_enable_disk_events(struct scsi_device *sdev);
 
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 extern int scsi_autopm_get_device(struct scsi_device *);
 extern void scsi_autopm_put_device(struct scsi_device *);
 #else
 static inline int scsi_autopm_get_device(struct scsi_device *d) { return 0; }
 static inline void scsi_autopm_put_device(struct scsi_device *d) {}
-#endif /* CONFIG_PM_RUNTIME */
+#endif /* CONFIG_PM */
 
 static inline int __must_check scsi_device_reprobe(struct scsi_device *sdev)
 {
-- 
cgit v1.2.3-70-g09d2


From 5f893b2639b21ffe6834b1aebba392c37d2b83f9 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 12 Dec 2014 20:05:10 -0500
Subject: tracing: Move enabling tracepoints to just after rcu_init()

Enabling tracepoints at boot up can be very useful. The tracepoint
can be initialized right after RCU has been. There's no need to
wait for the early_initcall() to be called. That's too late for some
things that can use tracepoints for debugging. Move the logic to
enable tracepoints out of the initcalls and into init/main.c to
right after rcu_init().

This also allows trace_printk() to be used early too.

Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1412121539300.16494@nanos
Link: http://lkml.kernel.org/r/20141214164104.307127356@goodmis.org

Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h        |  6 ++++++
 init/main.c                   |  4 ++++
 kernel/trace/trace.c          |  8 +++++++-
 kernel/trace/trace.h          | 13 +++++++++++++
 kernel/trace/trace_events.c   | 10 ++++++++--
 kernel/trace/trace_syscalls.c |  7 ++-----
 6 files changed, 40 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index ed501953f0b..f4bc14b7d44 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -39,6 +39,12 @@
 # define FTRACE_FORCE_LIST_FUNC 0
 #endif
 
+/* Main tracing buffer and events set up */
+#ifdef CONFIG_TRACING
+void trace_init(void);
+#else
+static inline void trace_init(void) { }
+#endif
 
 struct module;
 struct ftrace_hash;
diff --git a/init/main.c b/init/main.c
index 800a0daede7..70687069f8e 100644
--- a/init/main.c
+++ b/init/main.c
@@ -577,6 +577,10 @@ asmlinkage __visible void __init start_kernel(void)
 		local_irq_disable();
 	idr_init_cache();
 	rcu_init();
+
+	/* trace_printk() and trace points may be used after this */
+	trace_init();
+
 	context_tracking_init();
 	radix_tree_init();
 	/* init some links before init_ISA_irqs() */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4ceb2546c7e..ec3ca694665 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6876,6 +6876,13 @@ out:
 	return ret;
 }
 
+void __init trace_init(void)
+{
+	tracer_alloc_buffers();
+	init_ftrace_syscalls();
+	trace_event_init();	
+}
+
 __init static int clear_boot_tracer(void)
 {
 	/*
@@ -6895,6 +6902,5 @@ __init static int clear_boot_tracer(void)
 	return 0;
 }
 
-early_initcall(tracer_alloc_buffers);
 fs_initcall(tracer_init_debugfs);
 late_initcall(clear_boot_tracer);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 3255dfb054a..c138c149d6e 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1301,4 +1301,17 @@ int perf_ftrace_event_register(struct ftrace_event_call *call,
 #define perf_ftrace_event_register NULL
 #endif
 
+#ifdef CONFIG_FTRACE_SYSCALLS
+void init_ftrace_syscalls(void);
+#else
+static inline void init_ftrace_syscalls(void) { }
+#endif
+
+#ifdef CONFIG_EVENT_TRACING
+void trace_event_init(void);
+#else
+static inline void __init trace_event_init(void) { }
+#endif
+
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f9d0cbe014b..fd9deb0e03f 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2477,8 +2477,14 @@ static __init int event_trace_init(void)
 #endif
 	return 0;
 }
-early_initcall(event_trace_memsetup);
-core_initcall(event_trace_enable);
+
+void __init trace_event_init(void)
+{
+	event_trace_memsetup();
+	init_ftrace_syscalls();
+	event_trace_enable();
+}
+
 fs_initcall(event_trace_init);
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index a72f3d8d813..ec239771c17 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -514,7 +514,7 @@ unsigned long __init __weak arch_syscall_addr(int nr)
 	return (unsigned long)sys_call_table[nr];
 }
 
-static int __init init_ftrace_syscalls(void)
+void __init init_ftrace_syscalls(void)
 {
 	struct syscall_metadata *meta;
 	unsigned long addr;
@@ -524,7 +524,7 @@ static int __init init_ftrace_syscalls(void)
 				    GFP_KERNEL);
 	if (!syscalls_metadata) {
 		WARN_ON(1);
-		return -ENOMEM;
+		return;
 	}
 
 	for (i = 0; i < NR_syscalls; i++) {
@@ -536,10 +536,7 @@ static int __init init_ftrace_syscalls(void)
 		meta->syscall_nr = i;
 		syscalls_metadata[i] = meta;
 	}
-
-	return 0;
 }
-early_initcall(init_ftrace_syscalls);
 
 #ifdef CONFIG_PERF_EVENTS
 
-- 
cgit v1.2.3-70-g09d2


From 0daa2302968c13b657118d6ac92471f8fd2f3f28 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 12 Dec 2014 22:27:10 -0500
Subject: tracing: Add tp_printk cmdline to have tracepoints go to printk()

Add the kernel command line tp_printk option that will have tracepoints
that are active sent to printk() as well as to the trace buffer.

Passing "tp_printk" will activate this. To turn it off, the sysctl
/proc/sys/kernel/tracepoint_printk can have '0' echoed into it. Note,
this only works if the cmdline option is used. Echoing 1 into the sysctl
file without the cmdline option will have no affect.

Note, this is a dangerous option. Having high frequency tracepoints send
their data to printk() can possibly cause a live lock. This is another
reason why this is only active if the command line option is used.

Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1412121539300.16494@nanos

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 Documentation/kernel-parameters.txt | 18 ++++++++++++++++++
 include/linux/ftrace.h              |  1 +
 kernel/sysctl.c                     |  7 +++++++
 kernel/trace/trace.c                | 17 +++++++++++++++++
 kernel/trace/trace.h                |  1 +
 kernel/trace/trace_events.c         | 32 ++++++++++++++++++++++++++++++++
 6 files changed, 76 insertions(+)

(limited to 'include')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 1d09eb37c56..ae41f1181e9 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3500,6 +3500,24 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			See also Documentation/trace/ftrace.txt "trace options"
 			section.
 
+	tp_printk[FTRACE]
+			Have the tracepoints sent to printk as well as the
+			tracing ring buffer. This is useful for early boot up
+			where the system hangs or reboots and does not give the
+			option for reading the tracing buffer or performing a
+			ftrace_dump_on_oops.
+
+			To turn off having tracepoints sent to printk,
+			 echo 0 > /proc/sys/kernel/tracepoint_printk
+			Note, echoing 1 into this file without the
+			tracepoint_printk kernel cmdline option has no effect.
+
+			** CAUTION **
+
+			Having tracepoints sent to printk() and activating high
+			frequency tracepoints such as irq or sched, can cause
+			the system to live lock.
+
 	traceoff_on_warning
 			[FTRACE] enable this option to disable tracing when a
 			warning is hit. This turns off "tracing_on". Tracing can
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index f4bc14b7d44..1da602982cf 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -879,6 +879,7 @@ static inline int test_tsk_trace_graph(struct task_struct *tsk)
 enum ftrace_dump_mode;
 
 extern enum ftrace_dump_mode ftrace_dump_on_oops;
+extern int tracepoint_printk;
 
 extern void disable_trace_on_warning(void);
 extern int __disable_trace_on_warning;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4aada6d9fe7..bb50c218719 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -622,6 +622,13 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "tracepoint_printk",
+		.data		= &tracepoint_printk,
+		.maxlen		= sizeof(tracepoint_printk),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 #endif
 #ifdef CONFIG_KEXEC
 	{
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ec3ca694665..e890d2d4ec8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -63,6 +63,10 @@ static bool __read_mostly tracing_selftest_running;
  */
 bool __read_mostly tracing_selftest_disabled;
 
+/* Pipe tracepoints to printk */
+struct trace_iterator *tracepoint_print_iter;
+int tracepoint_printk;
+
 /* For tracers that don't implement custom flags */
 static struct tracer_opt dummy_tracer_opt[] = {
 	{ }
@@ -193,6 +197,13 @@ static int __init set_trace_boot_clock(char *str)
 }
 __setup("trace_clock=", set_trace_boot_clock);
 
+static int __init set_tracepoint_printk(char *str)
+{
+	if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0))
+		tracepoint_printk = 1;
+	return 1;
+}
+__setup("tp_printk", set_tracepoint_printk);
 
 unsigned long long ns2usecs(cycle_t nsec)
 {
@@ -6878,6 +6889,12 @@ out:
 
 void __init trace_init(void)
 {
+	if (tracepoint_printk) {
+		tracepoint_print_iter =
+			kmalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL);
+		if (WARN_ON(!tracepoint_print_iter))
+			tracepoint_printk = 0;
+	}
 	tracer_alloc_buffers();
 	init_ftrace_syscalls();
 	trace_event_init();	
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index c138c149d6e..8de48bac1ce 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1313,5 +1313,6 @@ void trace_event_init(void);
 static inline void __init trace_event_init(void) { }
 #endif
 
+extern struct trace_iterator *tracepoint_print_iter;
 
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index fd9deb0e03f..9f7175a3df7 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -212,8 +212,40 @@ void *ftrace_event_buffer_reserve(struct ftrace_event_buffer *fbuffer,
 }
 EXPORT_SYMBOL_GPL(ftrace_event_buffer_reserve);
 
+static DEFINE_SPINLOCK(tracepoint_iter_lock);
+
+static void output_printk(struct ftrace_event_buffer *fbuffer)
+{
+	struct ftrace_event_call *event_call;
+	struct trace_event *event;
+	unsigned long flags;
+	struct trace_iterator *iter = tracepoint_print_iter;
+
+	if (!iter)
+		return;
+
+	event_call = fbuffer->ftrace_file->event_call;
+	if (!event_call || !event_call->event.funcs ||
+	    !event_call->event.funcs->trace)
+		return;
+
+	event = &fbuffer->ftrace_file->event_call->event;
+
+	spin_lock_irqsave(&tracepoint_iter_lock, flags);
+	trace_seq_init(&iter->seq);
+	iter->ent = fbuffer->entry;
+	event_call->event.funcs->trace(iter, 0, event);
+	trace_seq_putc(&iter->seq, 0);
+	printk("%s", iter->seq.buffer);
+
+	spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
+}
+
 void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer)
 {
+	if (tracepoint_printk)
+		output_printk(fbuffer);
+
 	event_trigger_unlock_commit(fbuffer->ftrace_file, fbuffer->buffer,
 				    fbuffer->event, fbuffer->entry,
 				    fbuffer->flags, fbuffer->pc);
-- 
cgit v1.2.3-70-g09d2


From b97a8a90067896f99f0d636dbc2b89a953123fad Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Fri, 12 Dec 2014 00:36:06 +0200
Subject: vringh: 64 bit features

Pass u64 everywhere.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vringh.c | 4 ++--
 include/linux/vringh.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c
index 5174ebac288..ac3fe275796 100644
--- a/drivers/vhost/vringh.c
+++ b/drivers/vhost/vringh.c
@@ -577,7 +577,7 @@ static inline int xfer_to_user(void *dst, void *src, size_t len)
  * Returns an error if num is invalid: you should check pointers
  * yourself!
  */
-int vringh_init_user(struct vringh *vrh, u32 features,
+int vringh_init_user(struct vringh *vrh, u64 features,
 		     unsigned int num, bool weak_barriers,
 		     struct vring_desc __user *desc,
 		     struct vring_avail __user *avail,
@@ -836,7 +836,7 @@ static inline int xfer_kern(void *src, void *dst, size_t len)
  *
  * Returns an error if num is invalid.
  */
-int vringh_init_kern(struct vringh *vrh, u32 features,
+int vringh_init_kern(struct vringh *vrh, u64 features,
 		     unsigned int num, bool weak_barriers,
 		     struct vring_desc *desc,
 		     struct vring_avail *avail,
diff --git a/include/linux/vringh.h b/include/linux/vringh.h
index 749cde28728..f696dd0b647 100644
--- a/include/linux/vringh.h
+++ b/include/linux/vringh.h
@@ -105,7 +105,7 @@ struct vringh_kiov {
 #define VRINGH_IOV_ALLOCATED 0x8000000
 
 /* Helpers for userspace vrings. */
-int vringh_init_user(struct vringh *vrh, u32 features,
+int vringh_init_user(struct vringh *vrh, u64 features,
 		     unsigned int num, bool weak_barriers,
 		     struct vring_desc __user *desc,
 		     struct vring_avail __user *avail,
@@ -167,7 +167,7 @@ bool vringh_notify_enable_user(struct vringh *vrh);
 void vringh_notify_disable_user(struct vringh *vrh);
 
 /* Helpers for kernelspace vrings. */
-int vringh_init_kern(struct vringh *vrh, u32 features,
+int vringh_init_kern(struct vringh *vrh, u64 features,
 		     unsigned int num, bool weak_barriers,
 		     struct vring_desc *desc,
 		     struct vring_avail *avail,
-- 
cgit v1.2.3-70-g09d2


From b9f7ac8c72894c19bf258a54ecaa708df4ffbe80 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Fri, 12 Dec 2014 01:10:49 +0200
Subject: vringh: update for virtio 1.0 APIs

When switching everything over to virtio 1.0 memory access APIs,
I missed converting vringh.
Fortunately, it's straight-forward.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vringh.c | 121 ++++++++++++++++++++++++++++++-------------------
 include/linux/vringh.h |  33 ++++++++++++++
 2 files changed, 107 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c
index ac3fe275796..3bb02c60a2f 100644
--- a/drivers/vhost/vringh.c
+++ b/drivers/vhost/vringh.c
@@ -11,6 +11,7 @@
 #include <linux/uaccess.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <uapi/linux/virtio_config.h>
 
 static __printf(1,2) __cold void vringh_bad(const char *fmt, ...)
 {
@@ -28,13 +29,14 @@ static __printf(1,2) __cold void vringh_bad(const char *fmt, ...)
 
 /* Returns vring->num if empty, -ve on error. */
 static inline int __vringh_get_head(const struct vringh *vrh,
-				    int (*getu16)(u16 *val, const u16 *p),
+				    int (*getu16)(const struct vringh *vrh,
+						  u16 *val, const __virtio16 *p),
 				    u16 *last_avail_idx)
 {
 	u16 avail_idx, i, head;
 	int err;
 
-	err = getu16(&avail_idx, &vrh->vring.avail->idx);
+	err = getu16(vrh, &avail_idx, &vrh->vring.avail->idx);
 	if (err) {
 		vringh_bad("Failed to access avail idx at %p",
 			   &vrh->vring.avail->idx);
@@ -49,7 +51,7 @@ static inline int __vringh_get_head(const struct vringh *vrh,
 
 	i = *last_avail_idx & (vrh->vring.num - 1);
 
-	err = getu16(&head, &vrh->vring.avail->ring[i]);
+	err = getu16(vrh, &head, &vrh->vring.avail->ring[i]);
 	if (err) {
 		vringh_bad("Failed to read head: idx %d address %p",
 			   *last_avail_idx, &vrh->vring.avail->ring[i]);
@@ -144,28 +146,32 @@ static inline bool no_range_check(struct vringh *vrh, u64 addr, size_t *len,
 }
 
 /* No reason for this code to be inline. */
-static int move_to_indirect(int *up_next, u16 *i, void *addr,
+static int move_to_indirect(const struct vringh *vrh,
+			    int *up_next, u16 *i, void *addr,
 			    const struct vring_desc *desc,
 			    struct vring_desc **descs, int *desc_max)
 {
+	u32 len;
+
 	/* Indirect tables can't have indirect. */
 	if (*up_next != -1) {
 		vringh_bad("Multilevel indirect %u->%u", *up_next, *i);
 		return -EINVAL;
 	}
 
-	if (unlikely(desc->len % sizeof(struct vring_desc))) {
+	len = vringh32_to_cpu(vrh, desc->len);
+	if (unlikely(len % sizeof(struct vring_desc))) {
 		vringh_bad("Strange indirect len %u", desc->len);
 		return -EINVAL;
 	}
 
 	/* We will check this when we follow it! */
-	if (desc->flags & VRING_DESC_F_NEXT)
-		*up_next = desc->next;
+	if (desc->flags & cpu_to_vringh16(vrh, VRING_DESC_F_NEXT))
+		*up_next = vringh16_to_cpu(vrh, desc->next);
 	else
 		*up_next = -2;
 	*descs = addr;
-	*desc_max = desc->len / sizeof(struct vring_desc);
+	*desc_max = len / sizeof(struct vring_desc);
 
 	/* Now, start at the first indirect. */
 	*i = 0;
@@ -287,22 +293,25 @@ __vringh_iov(struct vringh *vrh, u16 i,
 		if (unlikely(err))
 			goto fail;
 
-		if (unlikely(desc.flags & VRING_DESC_F_INDIRECT)) {
+		if (unlikely(desc.flags &
+			     cpu_to_vringh16(vrh, VRING_DESC_F_INDIRECT))) {
+			u64 a = vringh64_to_cpu(vrh, desc.addr);
+
 			/* Make sure it's OK, and get offset. */
-			len = desc.len;
-			if (!rcheck(vrh, desc.addr, &len, &range, getrange)) {
+			len = vringh32_to_cpu(vrh, desc.len);
+			if (!rcheck(vrh, a, &len, &range, getrange)) {
 				err = -EINVAL;
 				goto fail;
 			}
 
-			if (unlikely(len != desc.len)) {
+			if (unlikely(len != vringh32_to_cpu(vrh, desc.len))) {
 				slow = true;
 				/* We need to save this range to use offset */
 				slowrange = range;
 			}
 
-			addr = (void *)(long)(desc.addr + range.offset);
-			err = move_to_indirect(&up_next, &i, addr, &desc,
+			addr = (void *)(long)(a + range.offset);
+			err = move_to_indirect(vrh, &up_next, &i, addr, &desc,
 					       &descs, &desc_max);
 			if (err)
 				goto fail;
@@ -315,7 +324,7 @@ __vringh_iov(struct vringh *vrh, u16 i,
 			goto fail;
 		}
 
-		if (desc.flags & VRING_DESC_F_WRITE)
+		if (desc.flags & cpu_to_vringh16(vrh, VRING_DESC_F_WRITE))
 			iov = wiov;
 		else {
 			iov = riov;
@@ -336,12 +345,14 @@ __vringh_iov(struct vringh *vrh, u16 i,
 
 	again:
 		/* Make sure it's OK, and get offset. */
-		len = desc.len;
-		if (!rcheck(vrh, desc.addr, &len, &range, getrange)) {
+		len = vringh32_to_cpu(vrh, desc.len);
+		if (!rcheck(vrh, vringh64_to_cpu(vrh, desc.addr), &len, &range,
+			    getrange)) {
 			err = -EINVAL;
 			goto fail;
 		}
-		addr = (void *)(unsigned long)(desc.addr + range.offset);
+		addr = (void *)(unsigned long)(vringh64_to_cpu(vrh, desc.addr) +
+					       range.offset);
 
 		if (unlikely(iov->used == (iov->max_num & ~VRINGH_IOV_ALLOCATED))) {
 			err = resize_iovec(iov, gfp);
@@ -353,14 +364,16 @@ __vringh_iov(struct vringh *vrh, u16 i,
 		iov->iov[iov->used].iov_len = len;
 		iov->used++;
 
-		if (unlikely(len != desc.len)) {
-			desc.len -= len;
-			desc.addr += len;
+		if (unlikely(len != vringh32_to_cpu(vrh, desc.len))) {
+			desc.len = cpu_to_vringh32(vrh,
+				   vringh32_to_cpu(vrh, desc.len) - len);
+			desc.addr = cpu_to_vringh64(vrh,
+				    vringh64_to_cpu(vrh, desc.addr) + len);
 			goto again;
 		}
 
-		if (desc.flags & VRING_DESC_F_NEXT) {
-			i = desc.next;
+		if (desc.flags & cpu_to_vringh16(vrh, VRING_DESC_F_NEXT)) {
+			i = vringh16_to_cpu(vrh, desc.next);
 		} else {
 			/* Just in case we need to finish traversing above. */
 			if (unlikely(up_next > 0)) {
@@ -387,7 +400,8 @@ fail:
 static inline int __vringh_complete(struct vringh *vrh,
 				    const struct vring_used_elem *used,
 				    unsigned int num_used,
-				    int (*putu16)(u16 *p, u16 val),
+				    int (*putu16)(const struct vringh *vrh,
+						  __virtio16 *p, u16 val),
 				    int (*putused)(struct vring_used_elem *dst,
 						   const struct vring_used_elem
 						   *src, unsigned num))
@@ -420,7 +434,7 @@ static inline int __vringh_complete(struct vringh *vrh,
 	/* Make sure buffer is written before we update index. */
 	virtio_wmb(vrh->weak_barriers);
 
-	err = putu16(&vrh->vring.used->idx, used_idx + num_used);
+	err = putu16(vrh, &vrh->vring.used->idx, used_idx + num_used);
 	if (err) {
 		vringh_bad("Failed to update used index at %p",
 			   &vrh->vring.used->idx);
@@ -433,7 +447,9 @@ static inline int __vringh_complete(struct vringh *vrh,
 
 
 static inline int __vringh_need_notify(struct vringh *vrh,
-				       int (*getu16)(u16 *val, const u16 *p))
+				       int (*getu16)(const struct vringh *vrh,
+						     u16 *val,
+						     const __virtio16 *p))
 {
 	bool notify;
 	u16 used_event;
@@ -447,7 +463,7 @@ static inline int __vringh_need_notify(struct vringh *vrh,
 	/* Old-style, without event indices. */
 	if (!vrh->event_indices) {
 		u16 flags;
-		err = getu16(&flags, &vrh->vring.avail->flags);
+		err = getu16(vrh, &flags, &vrh->vring.avail->flags);
 		if (err) {
 			vringh_bad("Failed to get flags at %p",
 				   &vrh->vring.avail->flags);
@@ -457,7 +473,7 @@ static inline int __vringh_need_notify(struct vringh *vrh,
 	}
 
 	/* Modern: we know when other side wants to know. */
-	err = getu16(&used_event, &vring_used_event(&vrh->vring));
+	err = getu16(vrh, &used_event, &vring_used_event(&vrh->vring));
 	if (err) {
 		vringh_bad("Failed to get used event idx at %p",
 			   &vring_used_event(&vrh->vring));
@@ -478,20 +494,22 @@ static inline int __vringh_need_notify(struct vringh *vrh,
 }
 
 static inline bool __vringh_notify_enable(struct vringh *vrh,
-					  int (*getu16)(u16 *val, const u16 *p),
-					  int (*putu16)(u16 *p, u16 val))
+					  int (*getu16)(const struct vringh *vrh,
+							u16 *val, const __virtio16 *p),
+					  int (*putu16)(const struct vringh *vrh,
+							__virtio16 *p, u16 val))
 {
 	u16 avail;
 
 	if (!vrh->event_indices) {
 		/* Old-school; update flags. */
-		if (putu16(&vrh->vring.used->flags, 0) != 0) {
+		if (putu16(vrh, &vrh->vring.used->flags, 0) != 0) {
 			vringh_bad("Clearing used flags %p",
 				   &vrh->vring.used->flags);
 			return true;
 		}
 	} else {
-		if (putu16(&vring_avail_event(&vrh->vring),
+		if (putu16(vrh, &vring_avail_event(&vrh->vring),
 			   vrh->last_avail_idx) != 0) {
 			vringh_bad("Updating avail event index %p",
 				   &vring_avail_event(&vrh->vring));
@@ -503,7 +521,7 @@ static inline bool __vringh_notify_enable(struct vringh *vrh,
 	 * sure it's written, then check again. */
 	virtio_mb(vrh->weak_barriers);
 
-	if (getu16(&avail, &vrh->vring.avail->idx) != 0) {
+	if (getu16(vrh, &avail, &vrh->vring.avail->idx) != 0) {
 		vringh_bad("Failed to check avail idx at %p",
 			   &vrh->vring.avail->idx);
 		return true;
@@ -516,11 +534,13 @@ static inline bool __vringh_notify_enable(struct vringh *vrh,
 }
 
 static inline void __vringh_notify_disable(struct vringh *vrh,
-					   int (*putu16)(u16 *p, u16 val))
+					   int (*putu16)(const struct vringh *vrh,
+							 __virtio16 *p, u16 val))
 {
 	if (!vrh->event_indices) {
 		/* Old-school; update flags. */
-		if (putu16(&vrh->vring.used->flags, VRING_USED_F_NO_NOTIFY)) {
+		if (putu16(vrh, &vrh->vring.used->flags,
+			   VRING_USED_F_NO_NOTIFY)) {
 			vringh_bad("Setting used flags %p",
 				   &vrh->vring.used->flags);
 		}
@@ -528,14 +548,18 @@ static inline void __vringh_notify_disable(struct vringh *vrh,
 }
 
 /* Userspace access helpers: in this case, addresses are really userspace. */
-static inline int getu16_user(u16 *val, const u16 *p)
+static inline int getu16_user(const struct vringh *vrh, u16 *val, const __virtio16 *p)
 {
-	return get_user(*val, (__force u16 __user *)p);
+	__virtio16 v = 0;
+	int rc = get_user(v, (__force __virtio16 __user *)p);
+	*val = vringh16_to_cpu(vrh, v);
+	return rc;
 }
 
-static inline int putu16_user(u16 *p, u16 val)
+static inline int putu16_user(const struct vringh *vrh, __virtio16 *p, u16 val)
 {
-	return put_user(val, (__force u16 __user *)p);
+	__virtio16 v = cpu_to_vringh16(vrh, val);
+	return put_user(v, (__force __virtio16 __user *)p);
 }
 
 static inline int copydesc_user(void *dst, const void *src, size_t len)
@@ -589,6 +613,7 @@ int vringh_init_user(struct vringh *vrh, u64 features,
 		return -EINVAL;
 	}
 
+	vrh->little_endian = (features & (1ULL << VIRTIO_F_VERSION_1));
 	vrh->event_indices = (features & (1 << VIRTIO_RING_F_EVENT_IDX));
 	vrh->weak_barriers = weak_barriers;
 	vrh->completed = 0;
@@ -729,8 +754,8 @@ int vringh_complete_user(struct vringh *vrh, u16 head, u32 len)
 {
 	struct vring_used_elem used;
 
-	used.id = head;
-	used.len = len;
+	used.id = cpu_to_vringh32(vrh, head);
+	used.len = cpu_to_vringh32(vrh, len);
 	return __vringh_complete(vrh, &used, 1, putu16_user, putused_user);
 }
 EXPORT_SYMBOL(vringh_complete_user);
@@ -792,15 +817,16 @@ int vringh_need_notify_user(struct vringh *vrh)
 EXPORT_SYMBOL(vringh_need_notify_user);
 
 /* Kernelspace access helpers. */
-static inline int getu16_kern(u16 *val, const u16 *p)
+static inline int getu16_kern(const struct vringh *vrh,
+			      u16 *val, const __virtio16 *p)
 {
-	*val = ACCESS_ONCE(*p);
+	*val = vringh16_to_cpu(vrh, ACCESS_ONCE(*p));
 	return 0;
 }
 
-static inline int putu16_kern(u16 *p, u16 val)
+static inline int putu16_kern(const struct vringh *vrh, __virtio16 *p, u16 val)
 {
-	ACCESS_ONCE(*p) = val;
+	ACCESS_ONCE(*p) = cpu_to_vringh16(vrh, val);
 	return 0;
 }
 
@@ -848,6 +874,7 @@ int vringh_init_kern(struct vringh *vrh, u64 features,
 		return -EINVAL;
 	}
 
+	vrh->little_endian = (features & (1ULL << VIRTIO_F_VERSION_1));
 	vrh->event_indices = (features & (1 << VIRTIO_RING_F_EVENT_IDX));
 	vrh->weak_barriers = weak_barriers;
 	vrh->completed = 0;
@@ -962,8 +989,8 @@ int vringh_complete_kern(struct vringh *vrh, u16 head, u32 len)
 {
 	struct vring_used_elem used;
 
-	used.id = head;
-	used.len = len;
+	used.id = cpu_to_vringh32(vrh, head);
+	used.len = cpu_to_vringh32(vrh, len);
 
 	return __vringh_complete(vrh, &used, 1, putu16_kern, putused_kern);
 }
diff --git a/include/linux/vringh.h b/include/linux/vringh.h
index f696dd0b647..a3fa537e717 100644
--- a/include/linux/vringh.h
+++ b/include/linux/vringh.h
@@ -24,12 +24,16 @@
 #ifndef _LINUX_VRINGH_H
 #define _LINUX_VRINGH_H
 #include <uapi/linux/virtio_ring.h>
+#include <linux/virtio_byteorder.h>
 #include <linux/uio.h>
 #include <linux/slab.h>
 #include <asm/barrier.h>
 
 /* virtio_ring with information needed for host access. */
 struct vringh {
+	/* Everything is little endian */
+	bool little_endian;
+
 	/* Guest publishes used event idx (note: we always do). */
 	bool event_indices;
 
@@ -222,4 +226,33 @@ static inline void vringh_notify(struct vringh *vrh)
 		vrh->notify(vrh);
 }
 
+static inline u16 vringh16_to_cpu(const struct vringh *vrh, __virtio16 val)
+{
+	return __virtio16_to_cpu(vrh->little_endian, val);
+}
+
+static inline __virtio16 cpu_to_vringh16(const struct vringh *vrh, u16 val)
+{
+	return __cpu_to_virtio16(vrh->little_endian, val);
+}
+
+static inline u32 vringh32_to_cpu(const struct vringh *vrh, __virtio32 val)
+{
+	return __virtio32_to_cpu(vrh->little_endian, val);
+}
+
+static inline __virtio32 cpu_to_vringh32(const struct vringh *vrh, u32 val)
+{
+	return __cpu_to_virtio32(vrh->little_endian, val);
+}
+
+static inline u64 vringh64_to_cpu(const struct vringh *vrh, __virtio64 val)
+{
+	return __virtio64_to_cpu(vrh->little_endian, val);
+}
+
+static inline __virtio64 cpu_to_vringh64(const struct vringh *vrh, u64 val)
+{
+	return __cpu_to_virtio64(vrh->little_endian, val);
+}
 #endif /* _LINUX_VRINGH_H */
-- 
cgit v1.2.3-70-g09d2


From 6f8e853d18a98ee95832ffebfaa288d42ae28cd5 Mon Sep 17 00:00:00 2001
From: Tero Kristo <t-kristo@ti.com>
Date: Fri, 12 Dec 2014 15:22:00 +0200
Subject: ARM: OMAP2+: clock: fix DPLL code to use new determine rate APIs

While the change for determine_rate clock operation was merged,
the OMAP counterpart using these calls was overlooked for some reason,
and caused boot failures on at least OMAP4 platforms. Fixed by updating
the DPLL API calls to use the new parameters.

Signed-off-by: Tero Kristo <t-kristo@ti.com>
Fixes: 646cafc6aa ("clk: Change clk_ops->determine_rate")
Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Acked-by: Paul Walmsley <paul@pwsan.com>
Tested-by: Kevin Hilman <khilman@linaro.org>
Reported-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Michael Turquette <mturquette@linaro.org>
---
 arch/arm/mach-omap2/dpll3xxx.c | 6 +++---
 arch/arm/mach-omap2/dpll44xx.c | 6 +++---
 include/linux/clk/ti.h         | 4 ++--
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c
index 20e120d071d..c2da2a0fe5a 100644
--- a/arch/arm/mach-omap2/dpll3xxx.c
+++ b/arch/arm/mach-omap2/dpll3xxx.c
@@ -474,7 +474,7 @@ void omap3_noncore_dpll_disable(struct clk_hw *hw)
  */
 long omap3_noncore_dpll_determine_rate(struct clk_hw *hw, unsigned long rate,
 				       unsigned long *best_parent_rate,
-				       struct clk **best_parent_clk)
+				       struct clk_hw **best_parent_clk)
 {
 	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
 	struct dpll_data *dd;
@@ -488,10 +488,10 @@ long omap3_noncore_dpll_determine_rate(struct clk_hw *hw, unsigned long rate,
 
 	if (__clk_get_rate(dd->clk_bypass) == rate &&
 	    (dd->modes & (1 << DPLL_LOW_POWER_BYPASS))) {
-		*best_parent_clk = dd->clk_bypass;
+		*best_parent_clk = __clk_get_hw(dd->clk_bypass);
 	} else {
 		rate = omap2_dpll_round_rate(hw, rate, best_parent_rate);
-		*best_parent_clk = dd->clk_ref;
+		*best_parent_clk = __clk_get_hw(dd->clk_ref);
 	}
 
 	*best_parent_rate = rate;
diff --git a/arch/arm/mach-omap2/dpll44xx.c b/arch/arm/mach-omap2/dpll44xx.c
index 535822fcf4b..0e58e5a85d5 100644
--- a/arch/arm/mach-omap2/dpll44xx.c
+++ b/arch/arm/mach-omap2/dpll44xx.c
@@ -223,7 +223,7 @@ out:
  */
 long omap4_dpll_regm4xen_determine_rate(struct clk_hw *hw, unsigned long rate,
 					unsigned long *best_parent_rate,
-					struct clk **best_parent_clk)
+					struct clk_hw **best_parent_clk)
 {
 	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
 	struct dpll_data *dd;
@@ -237,11 +237,11 @@ long omap4_dpll_regm4xen_determine_rate(struct clk_hw *hw, unsigned long rate,
 
 	if (__clk_get_rate(dd->clk_bypass) == rate &&
 	    (dd->modes & (1 << DPLL_LOW_POWER_BYPASS))) {
-		*best_parent_clk = dd->clk_bypass;
+		*best_parent_clk = __clk_get_hw(dd->clk_bypass);
 	} else {
 		rate = omap4_dpll_regm4xen_round_rate(hw, rate,
 						      best_parent_rate);
-		*best_parent_clk = dd->clk_ref;
+		*best_parent_clk = __clk_get_hw(dd->clk_ref);
 	}
 
 	*best_parent_rate = rate;
diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h
index 74e5341463c..55ef529a0db 100644
--- a/include/linux/clk/ti.h
+++ b/include/linux/clk/ti.h
@@ -264,7 +264,7 @@ int omap3_noncore_dpll_set_rate_and_parent(struct clk_hw *hw,
 long omap3_noncore_dpll_determine_rate(struct clk_hw *hw,
 				       unsigned long rate,
 				       unsigned long *best_parent_rate,
-				       struct clk **best_parent_clk);
+				       struct clk_hw **best_parent_clk);
 unsigned long omap4_dpll_regm4xen_recalc(struct clk_hw *hw,
 					 unsigned long parent_rate);
 long omap4_dpll_regm4xen_round_rate(struct clk_hw *hw,
@@ -273,7 +273,7 @@ long omap4_dpll_regm4xen_round_rate(struct clk_hw *hw,
 long omap4_dpll_regm4xen_determine_rate(struct clk_hw *hw,
 					unsigned long rate,
 					unsigned long *best_parent_rate,
-					struct clk **best_parent_clk);
+					struct clk_hw **best_parent_clk);
 u8 omap2_init_dpll_parent(struct clk_hw *hw);
 unsigned long omap3_dpll_recalc(struct clk_hw *hw, unsigned long parent_rate);
 long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate,
-- 
cgit v1.2.3-70-g09d2


From 968e78dd96443e2cc963c493070574778805e76a Mon Sep 17 00:00:00 2001
From: Haggai Eran <haggaie@mellanox.com>
Date: Thu, 11 Dec 2014 17:04:11 +0200
Subject: IB/mlx5: Enhance UMR support to allow partial page table update

The current UMR interface doesn't allow partial updates to a memory
region's page tables. This patch changes the interface to allow that.

It also changes the way the UMR operation validates the memory
region's state.  When set, IB_SEND_UMR_FAIL_IF_FREE will cause the UMR
operation to fail if the MKEY is in the free state. When it is
unchecked the operation will check that it isn't in the free state.

Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  15 ++++++
 drivers/infiniband/hw/mlx5/mr.c      |  29 +++++-----
 drivers/infiniband/hw/mlx5/qp.c      | 100 ++++++++++++++++++++++-------------
 include/linux/mlx5/device.h          |  13 +++++
 4 files changed, 109 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 29da5522207..53d19e6e69a 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -111,6 +111,8 @@ struct mlx5_ib_pd {
  */
 
 #define MLX5_IB_SEND_UMR_UNREG	IB_SEND_RESERVED_START
+#define MLX5_IB_SEND_UMR_FAIL_IF_FREE (IB_SEND_RESERVED_START << 1)
+#define MLX5_IB_SEND_UMR_UPDATE_MTT (IB_SEND_RESERVED_START << 2)
 #define MLX5_IB_QPT_REG_UMR	IB_QPT_RESERVED1
 #define MLX5_IB_WR_UMR		IB_WR_RESERVED1
 
@@ -206,6 +208,19 @@ enum mlx5_ib_qp_flags {
 	MLX5_IB_QP_SIGNATURE_HANDLING           = 1 << 1,
 };
 
+struct mlx5_umr_wr {
+	union {
+		u64			virt_addr;
+		u64			offset;
+	} target;
+	struct ib_pd		       *pd;
+	unsigned int			page_shift;
+	unsigned int			npages;
+	u32				length;
+	int				access_flags;
+	u32				mkey;
+};
+
 struct mlx5_shared_mr_info {
 	int mr_id;
 	struct ib_umem		*umem;
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 2ab081cdbca..2de4f4448f8 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -37,6 +37,7 @@
 #include <linux/export.h>
 #include <linux/delay.h>
 #include <rdma/ib_umem.h>
+#include <rdma/ib_verbs.h>
 #include "mlx5_ib.h"
 
 enum {
@@ -146,7 +147,7 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
 		mr->order = ent->order;
 		mr->umred = 1;
 		mr->dev = dev;
-		in->seg.status = 1 << 6;
+		in->seg.status = MLX5_MKEY_STATUS_FREE;
 		in->seg.xlt_oct_size = cpu_to_be32((npages + 1) / 2);
 		in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
 		in->seg.flags = MLX5_ACCESS_MODE_MTT | MLX5_PERM_UMR_EN;
@@ -678,6 +679,7 @@ static void prep_umr_reg_wqe(struct ib_pd *pd, struct ib_send_wr *wr,
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
 	struct ib_mr *mr = dev->umrc.mr;
+	struct mlx5_umr_wr *umrwr = (struct mlx5_umr_wr *)&wr->wr.fast_reg;
 
 	sg->addr = dma;
 	sg->length = ALIGN(sizeof(u64) * n, 64);
@@ -692,21 +694,24 @@ static void prep_umr_reg_wqe(struct ib_pd *pd, struct ib_send_wr *wr,
 		wr->num_sge = 0;
 
 	wr->opcode = MLX5_IB_WR_UMR;
-	wr->wr.fast_reg.page_list_len = n;
-	wr->wr.fast_reg.page_shift = page_shift;
-	wr->wr.fast_reg.rkey = key;
-	wr->wr.fast_reg.iova_start = virt_addr;
-	wr->wr.fast_reg.length = len;
-	wr->wr.fast_reg.access_flags = access_flags;
-	wr->wr.fast_reg.page_list = (struct ib_fast_reg_page_list *)pd;
+
+	umrwr->npages = n;
+	umrwr->page_shift = page_shift;
+	umrwr->mkey = key;
+	umrwr->target.virt_addr = virt_addr;
+	umrwr->length = len;
+	umrwr->access_flags = access_flags;
+	umrwr->pd = pd;
 }
 
 static void prep_umr_unreg_wqe(struct mlx5_ib_dev *dev,
 			       struct ib_send_wr *wr, u32 key)
 {
-	wr->send_flags = MLX5_IB_SEND_UMR_UNREG;
+	struct mlx5_umr_wr *umrwr = (struct mlx5_umr_wr *)&wr->wr.fast_reg;
+
+	wr->send_flags = MLX5_IB_SEND_UMR_UNREG | MLX5_IB_SEND_UMR_FAIL_IF_FREE;
 	wr->opcode = MLX5_IB_WR_UMR;
-	wr->wr.fast_reg.rkey = key;
+	umrwr->mkey = key;
 }
 
 void mlx5_umr_cq_handler(struct ib_cq *cq, void *cq_context)
@@ -1031,7 +1036,7 @@ struct ib_mr *mlx5_ib_create_mr(struct ib_pd *pd,
 		goto err_free;
 	}
 
-	in->seg.status = 1 << 6; /* free */
+	in->seg.status = MLX5_MKEY_STATUS_FREE;
 	in->seg.xlt_oct_size = cpu_to_be32(ndescs);
 	in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
 	in->seg.flags_pd = cpu_to_be32(to_mpd(pd)->pdn);
@@ -1146,7 +1151,7 @@ struct ib_mr *mlx5_ib_alloc_fast_reg_mr(struct ib_pd *pd,
 		goto err_free;
 	}
 
-	in->seg.status = 1 << 6; /* free */
+	in->seg.status = MLX5_MKEY_STATUS_FREE;
 	in->seg.xlt_oct_size = cpu_to_be32((max_page_list_len + 1) / 2);
 	in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
 	in->seg.flags = MLX5_PERM_UMR_EN | MLX5_ACCESS_MODE_MTT;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 1cae1c7132b..36e2cfe1c2f 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -70,15 +70,6 @@ static const u32 mlx5_ib_opcode[] = {
 	[MLX5_IB_WR_UMR]			= MLX5_OPCODE_UMR,
 };
 
-struct umr_wr {
-	u64				virt_addr;
-	struct ib_pd		       *pd;
-	unsigned int			page_shift;
-	unsigned int			npages;
-	u32				length;
-	int				access_flags;
-	u32				mkey;
-};
 
 static int is_qp0(enum ib_qp_type qp_type)
 {
@@ -1848,37 +1839,70 @@ static void set_frwr_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
 	umr->mkey_mask = frwr_mkey_mask();
 }
 
+static __be64 get_umr_reg_mr_mask(void)
+{
+	u64 result;
+
+	result = MLX5_MKEY_MASK_LEN		|
+		 MLX5_MKEY_MASK_PAGE_SIZE	|
+		 MLX5_MKEY_MASK_START_ADDR	|
+		 MLX5_MKEY_MASK_PD		|
+		 MLX5_MKEY_MASK_LR		|
+		 MLX5_MKEY_MASK_LW		|
+		 MLX5_MKEY_MASK_KEY		|
+		 MLX5_MKEY_MASK_RR		|
+		 MLX5_MKEY_MASK_RW		|
+		 MLX5_MKEY_MASK_A		|
+		 MLX5_MKEY_MASK_FREE;
+
+	return cpu_to_be64(result);
+}
+
+static __be64 get_umr_unreg_mr_mask(void)
+{
+	u64 result;
+
+	result = MLX5_MKEY_MASK_FREE;
+
+	return cpu_to_be64(result);
+}
+
+static __be64 get_umr_update_mtt_mask(void)
+{
+	u64 result;
+
+	result = MLX5_MKEY_MASK_FREE;
+
+	return cpu_to_be64(result);
+}
+
 static void set_reg_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
 				struct ib_send_wr *wr)
 {
-	struct umr_wr *umrwr = (struct umr_wr *)&wr->wr.fast_reg;
-	u64 mask;
+	struct mlx5_umr_wr *umrwr = (struct mlx5_umr_wr *)&wr->wr.fast_reg;
 
 	memset(umr, 0, sizeof(*umr));
 
+	if (wr->send_flags & MLX5_IB_SEND_UMR_FAIL_IF_FREE)
+		umr->flags = MLX5_UMR_CHECK_FREE; /* fail if free */
+	else
+		umr->flags = MLX5_UMR_CHECK_NOT_FREE; /* fail if not free */
+
 	if (!(wr->send_flags & MLX5_IB_SEND_UMR_UNREG)) {
-		umr->flags = 1 << 5; /* fail if not free */
 		umr->klm_octowords = get_klm_octo(umrwr->npages);
-		mask =  MLX5_MKEY_MASK_LEN		|
-			MLX5_MKEY_MASK_PAGE_SIZE	|
-			MLX5_MKEY_MASK_START_ADDR	|
-			MLX5_MKEY_MASK_PD		|
-			MLX5_MKEY_MASK_LR		|
-			MLX5_MKEY_MASK_LW		|
-			MLX5_MKEY_MASK_KEY		|
-			MLX5_MKEY_MASK_RR		|
-			MLX5_MKEY_MASK_RW		|
-			MLX5_MKEY_MASK_A		|
-			MLX5_MKEY_MASK_FREE;
-		umr->mkey_mask = cpu_to_be64(mask);
+		if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_MTT) {
+			umr->mkey_mask = get_umr_update_mtt_mask();
+			umr->bsf_octowords = get_klm_octo(umrwr->target.offset);
+			umr->flags |= MLX5_UMR_TRANSLATION_OFFSET_EN;
+		} else {
+			umr->mkey_mask = get_umr_reg_mr_mask();
+		}
 	} else {
-		umr->flags = 2 << 5; /* fail if free */
-		mask = MLX5_MKEY_MASK_FREE;
-		umr->mkey_mask = cpu_to_be64(mask);
+		umr->mkey_mask = get_umr_unreg_mr_mask();
 	}
 
 	if (!wr->num_sge)
-		umr->flags |= (1 << 7); /* inline */
+		umr->flags |= MLX5_UMR_INLINE;
 }
 
 static u8 get_umr_flags(int acc)
@@ -1895,7 +1919,7 @@ static void set_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *wr,
 {
 	memset(seg, 0, sizeof(*seg));
 	if (li) {
-		seg->status = 1 << 6;
+		seg->status = MLX5_MKEY_STATUS_FREE;
 		return;
 	}
 
@@ -1912,19 +1936,23 @@ static void set_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *wr,
 
 static void set_reg_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *wr)
 {
+	struct mlx5_umr_wr *umrwr = (struct mlx5_umr_wr *)&wr->wr.fast_reg;
+
 	memset(seg, 0, sizeof(*seg));
 	if (wr->send_flags & MLX5_IB_SEND_UMR_UNREG) {
-		seg->status = 1 << 6;
+		seg->status = MLX5_MKEY_STATUS_FREE;
 		return;
 	}
 
-	seg->flags = convert_access(wr->wr.fast_reg.access_flags);
-	seg->flags_pd = cpu_to_be32(to_mpd((struct ib_pd *)wr->wr.fast_reg.page_list)->pdn);
-	seg->start_addr = cpu_to_be64(wr->wr.fast_reg.iova_start);
-	seg->len = cpu_to_be64(wr->wr.fast_reg.length);
-	seg->log2_page_size = wr->wr.fast_reg.page_shift;
+	seg->flags = convert_access(umrwr->access_flags);
+	if (!(wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_MTT)) {
+		seg->flags_pd = cpu_to_be32(to_mpd(umrwr->pd)->pdn);
+		seg->start_addr = cpu_to_be64(umrwr->target.virt_addr);
+	}
+	seg->len = cpu_to_be64(umrwr->length);
+	seg->log2_page_size = umrwr->page_shift;
 	seg->qpn_mkey7_0 = cpu_to_be32(0xffffff00 |
-				       mlx5_mkey_variant(wr->wr.fast_reg.rkey));
+				       mlx5_mkey_variant(umrwr->mkey));
 }
 
 static void set_frwr_pages(struct mlx5_wqe_data_seg *dseg,
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index ea4f1c46f76..fa07bfda0e1 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -180,6 +180,15 @@ enum {
 	MLX5_MKEY_MASK_FREE		= 1ull << 29,
 };
 
+enum {
+	MLX5_UMR_TRANSLATION_OFFSET_EN	= (1 << 4),
+
+	MLX5_UMR_CHECK_NOT_FREE		= (1 << 5),
+	MLX5_UMR_CHECK_FREE		= (2 << 5),
+
+	MLX5_UMR_INLINE			= (1 << 7),
+};
+
 enum mlx5_event {
 	MLX5_EVENT_TYPE_COMP		   = 0x0,
 
@@ -776,6 +785,10 @@ struct mlx5_query_eq_mbox_out {
 	struct mlx5_eq_context	ctx;
 };
 
+enum {
+	MLX5_MKEY_STATUS_FREE = 1 << 6,
+};
+
 struct mlx5_mkey_seg {
 	/* This is a two bit field occupying bits 31-30.
 	 * bit 31 is always 0,
-- 
cgit v1.2.3-70-g09d2


From 406f9e5fa9a7a60b42e676841e39f2d752266814 Mon Sep 17 00:00:00 2001
From: Haggai Eran <haggaie@mellanox.com>
Date: Thu, 11 Dec 2014 17:04:12 +0200
Subject: IB/core: Replace ib_umem's offset field with a full address

In order to allow umems that do not pin memory, we need the umem to
keep track of its region's address.

This makes the offset field redundant, and so this patch removes it.

Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/umem.c               |  6 +++---
 drivers/infiniband/hw/amso1100/c2_provider.c |  2 +-
 drivers/infiniband/hw/ehca/ehca_mrmw.c       |  2 +-
 drivers/infiniband/hw/ipath/ipath_mr.c       |  2 +-
 drivers/infiniband/hw/nes/nes_verbs.c        |  6 +++---
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.c  |  2 +-
 drivers/infiniband/hw/qib/qib_mr.c           |  2 +-
 include/rdma/ib_umem.h                       | 25 ++++++++++++++++++++++++-
 8 files changed, 35 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index df0c4f605a2..e0f88329237 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -103,7 +103,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 
 	umem->context   = context;
 	umem->length    = size;
-	umem->offset    = addr & ~PAGE_MASK;
+	umem->address   = addr;
 	umem->page_size = PAGE_SIZE;
 	umem->pid       = get_task_pid(current, PIDTYPE_PID);
 	/*
@@ -132,7 +132,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	if (!vma_list)
 		umem->hugetlb = 0;
 
-	npages = PAGE_ALIGN(size + umem->offset) >> PAGE_SHIFT;
+	npages = ib_umem_num_pages(umem);
 
 	down_write(&current->mm->mmap_sem);
 
@@ -246,7 +246,7 @@ void ib_umem_release(struct ib_umem *umem)
 	if (!mm)
 		goto out;
 
-	diff = PAGE_ALIGN(umem->length + umem->offset) >> PAGE_SHIFT;
+	diff = ib_umem_num_pages(umem);
 
 	/*
 	 * We may be called with the mm's mmap_sem already held.  This
diff --git a/drivers/infiniband/hw/amso1100/c2_provider.c b/drivers/infiniband/hw/amso1100/c2_provider.c
index 2d5cbf4363e..bdf3507810c 100644
--- a/drivers/infiniband/hw/amso1100/c2_provider.c
+++ b/drivers/infiniband/hw/amso1100/c2_provider.c
@@ -476,7 +476,7 @@ static struct ib_mr *c2_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 					 c2mr->umem->page_size,
 					 i,
 					 length,
-					 c2mr->umem->offset,
+					 ib_umem_offset(c2mr->umem),
 					 &kva,
 					 c2_convert_access(acc),
 					 c2mr);
diff --git a/drivers/infiniband/hw/ehca/ehca_mrmw.c b/drivers/infiniband/hw/ehca/ehca_mrmw.c
index 3488e8c9fcb..f914b30999f 100644
--- a/drivers/infiniband/hw/ehca/ehca_mrmw.c
+++ b/drivers/infiniband/hw/ehca/ehca_mrmw.c
@@ -399,7 +399,7 @@ reg_user_mr_fallback:
 	pginfo.num_kpages = num_kpages;
 	pginfo.num_hwpages = num_hwpages;
 	pginfo.u.usr.region = e_mr->umem;
-	pginfo.next_hwpage = e_mr->umem->offset / hwpage_size;
+	pginfo.next_hwpage = ib_umem_offset(e_mr->umem) / hwpage_size;
 	pginfo.u.usr.next_sg = pginfo.u.usr.region->sg_head.sgl;
 	ret = ehca_reg_mr(shca, e_mr, (u64 *)virt, length, mr_access_flags,
 			  e_pd, &pginfo, &e_mr->ib.ib_mr.lkey,
diff --git a/drivers/infiniband/hw/ipath/ipath_mr.c b/drivers/infiniband/hw/ipath/ipath_mr.c
index 5e61e9bff69..c7278f6a821 100644
--- a/drivers/infiniband/hw/ipath/ipath_mr.c
+++ b/drivers/infiniband/hw/ipath/ipath_mr.c
@@ -214,7 +214,7 @@ struct ib_mr *ipath_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	mr->mr.user_base = start;
 	mr->mr.iova = virt_addr;
 	mr->mr.length = length;
-	mr->mr.offset = umem->offset;
+	mr->mr.offset = ib_umem_offset(umem);
 	mr->mr.access_flags = mr_access_flags;
 	mr->mr.max_segs = n;
 	mr->umem = umem;
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index fef067c959f..c0d0296e7a0 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -2341,9 +2341,9 @@ static struct ib_mr *nes_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	nes_debug(NES_DBG_MR, "User base = 0x%lX, Virt base = 0x%lX, length = %u,"
 			" offset = %u, page size = %u.\n",
 			(unsigned long int)start, (unsigned long int)virt, (u32)length,
-			region->offset, region->page_size);
+			ib_umem_offset(region), region->page_size);
 
-	skip_pages = ((u32)region->offset) >> 12;
+	skip_pages = ((u32)ib_umem_offset(region)) >> 12;
 
 	if (ib_copy_from_udata(&req, udata, sizeof(req))) {
 		ib_umem_release(region);
@@ -2408,7 +2408,7 @@ static struct ib_mr *nes_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				region_length -= skip_pages << 12;
 				for (page_index = skip_pages; page_index < chunk_pages; page_index++) {
 					skip_pages = 0;
-					if ((page_count != 0) && (page_count<<12)-(region->offset&(4096-1)) >= region->length)
+					if ((page_count != 0) && (page_count << 12) - (ib_umem_offset(region) & (4096 - 1)) >= region->length)
 						goto enough_pages;
 					if ((page_count&0x01FF) == 0) {
 						if (page_count >= 1024 * 512) {
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 4c68305ee78..b48fd01f34d 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -805,7 +805,7 @@ struct ib_mr *ocrdma_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 len,
 		goto umem_err;
 
 	mr->hwmr.pbe_size = mr->umem->page_size;
-	mr->hwmr.fbo = mr->umem->offset;
+	mr->hwmr.fbo = ib_umem_offset(mr->umem);
 	mr->hwmr.va = usr_addr;
 	mr->hwmr.len = len;
 	mr->hwmr.remote_wr = (acc & IB_ACCESS_REMOTE_WRITE) ? 1 : 0;
diff --git a/drivers/infiniband/hw/qib/qib_mr.c b/drivers/infiniband/hw/qib/qib_mr.c
index 9bbb55347cc..a77fb4fb14e 100644
--- a/drivers/infiniband/hw/qib/qib_mr.c
+++ b/drivers/infiniband/hw/qib/qib_mr.c
@@ -258,7 +258,7 @@ struct ib_mr *qib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	mr->mr.user_base = start;
 	mr->mr.iova = virt_addr;
 	mr->mr.length = length;
-	mr->mr.offset = umem->offset;
+	mr->mr.offset = ib_umem_offset(umem);
 	mr->mr.access_flags = mr_access_flags;
 	mr->umem = umem;
 
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index a2bf41e0bde..7ed6d4ff58d 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -42,7 +42,7 @@ struct ib_ucontext;
 struct ib_umem {
 	struct ib_ucontext     *context;
 	size_t			length;
-	int			offset;
+	unsigned long		address;
 	int			page_size;
 	int                     writable;
 	int                     hugetlb;
@@ -55,6 +55,29 @@ struct ib_umem {
 	int             npages;
 };
 
+/* Returns the offset of the umem start relative to the first page. */
+static inline int ib_umem_offset(struct ib_umem *umem)
+{
+	return umem->address & ((unsigned long)umem->page_size - 1);
+}
+
+/* Returns the first page of an ODP umem. */
+static inline unsigned long ib_umem_start(struct ib_umem *umem)
+{
+	return umem->address - ib_umem_offset(umem);
+}
+
+/* Returns the address of the page after the last one of an ODP umem. */
+static inline unsigned long ib_umem_end(struct ib_umem *umem)
+{
+	return PAGE_ALIGN(umem->address + umem->length);
+}
+
+static inline size_t ib_umem_num_pages(struct ib_umem *umem)
+{
+	return (ib_umem_end(umem) - ib_umem_start(umem)) >> PAGE_SHIFT;
+}
+
 #ifdef CONFIG_INFINIBAND_USER_MEM
 
 struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
-- 
cgit v1.2.3-70-g09d2


From c5d76f130b286682b64c659eaf6af701e3d79a7b Mon Sep 17 00:00:00 2001
From: Haggai Eran <haggaie@mellanox.com>
Date: Thu, 11 Dec 2014 17:04:13 +0200
Subject: IB/core: Add umem function to read data from user-space

In some drivers there's a need to read data from a user space area
that was pinned using ib_umem when running from a different process
context.

The ib_umem_copy_from function allows reading data from the physical
pages pinned in the ib_umem struct.

Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/umem.c | 34 ++++++++++++++++++++++++++++++++++
 include/rdma/ib_umem.h         |  2 ++
 2 files changed, 36 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index e0f88329237..6f152628e0d 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -292,3 +292,37 @@ int ib_umem_page_count(struct ib_umem *umem)
 	return n;
 }
 EXPORT_SYMBOL(ib_umem_page_count);
+
+/*
+ * Copy from the given ib_umem's pages to the given buffer.
+ *
+ * umem - the umem to copy from
+ * offset - offset to start copying from
+ * dst - destination buffer
+ * length - buffer length
+ *
+ * Returns 0 on success, or an error code.
+ */
+int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset,
+		      size_t length)
+{
+	size_t end = offset + length;
+	int ret;
+
+	if (offset > umem->length || length > umem->length - offset) {
+		pr_err("ib_umem_copy_from not in range. offset: %zd umem length: %zd end: %zd\n",
+		       offset, umem->length, end);
+		return -EINVAL;
+	}
+
+	ret = sg_pcopy_to_buffer(umem->sg_head.sgl, umem->nmap, dst, length,
+				 offset + ib_umem_offset(umem));
+
+	if (ret < 0)
+		return ret;
+	else if (ret != length)
+		return -EINVAL;
+	else
+		return 0;
+}
+EXPORT_SYMBOL(ib_umem_copy_from);
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 7ed6d4ff58d..45bb04bc88c 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -84,6 +84,8 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 			    size_t size, int access, int dmasync);
 void ib_umem_release(struct ib_umem *umem);
 int ib_umem_page_count(struct ib_umem *umem);
+int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset,
+		      size_t length);
 
 #else /* CONFIG_INFINIBAND_USER_MEM */
 
-- 
cgit v1.2.3-70-g09d2


From c1395a2a8c01e8a919e47d64eb3d23d00e824b8b Mon Sep 17 00:00:00 2001
From: Haggai Eran <haggaie@mellanox.com>
Date: Thu, 11 Dec 2014 17:04:14 +0200
Subject: IB/mlx5: Add function to read WQE from user-space

Add a helper function mlx5_ib_read_user_wqe to read information from
user-space owned work queues.  The function will be used in a later
patch by the page-fault handling code in mlx5_ib.

Signed-off-by: Haggai Eran <haggaie@mellanox.com>

[ Add stub for ib_umem_copy_from() for CONFIG_INFINIBAND_USER_MEM=n
  - Roland ]

Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  2 +
 drivers/infiniband/hw/mlx5/qp.c      | 71 ++++++++++++++++++++++++++++++++++++
 include/linux/mlx5/qp.h              |  3 ++
 include/rdma/ib_umem.h               |  5 ++-
 4 files changed, 80 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 53d19e6e69a..14a0311eaa1 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -503,6 +503,8 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 int mlx5_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 		      struct ib_recv_wr **bad_wr);
 void *mlx5_get_send_wqe(struct mlx5_ib_qp *qp, int n);
+int mlx5_ib_read_user_wqe(struct mlx5_ib_qp *qp, int send, int wqe_index,
+			  void *buffer, u32 length);
 struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int entries,
 				int vector, struct ib_ucontext *context,
 				struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 36e2cfe1c2f..9783c3342db 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -101,6 +101,77 @@ void *mlx5_get_send_wqe(struct mlx5_ib_qp *qp, int n)
 	return get_wqe(qp, qp->sq.offset + (n << MLX5_IB_SQ_STRIDE));
 }
 
+/**
+ * mlx5_ib_read_user_wqe() - Copy a user-space WQE to kernel space.
+ *
+ * @qp: QP to copy from.
+ * @send: copy from the send queue when non-zero, use the receive queue
+ *	  otherwise.
+ * @wqe_index:  index to start copying from. For send work queues, the
+ *		wqe_index is in units of MLX5_SEND_WQE_BB.
+ *		For receive work queue, it is the number of work queue
+ *		element in the queue.
+ * @buffer: destination buffer.
+ * @length: maximum number of bytes to copy.
+ *
+ * Copies at least a single WQE, but may copy more data.
+ *
+ * Return: the number of bytes copied, or an error code.
+ */
+int mlx5_ib_read_user_wqe(struct mlx5_ib_qp *qp, int send, int wqe_index,
+			  void *buffer, u32 length)
+{
+	struct ib_device *ibdev = qp->ibqp.device;
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+	struct mlx5_ib_wq *wq = send ? &qp->sq : &qp->rq;
+	size_t offset;
+	size_t wq_end;
+	struct ib_umem *umem = qp->umem;
+	u32 first_copy_length;
+	int wqe_length;
+	int ret;
+
+	if (wq->wqe_cnt == 0) {
+		mlx5_ib_dbg(dev, "mlx5_ib_read_user_wqe for a QP with wqe_cnt == 0. qp_type: 0x%x\n",
+			    qp->ibqp.qp_type);
+		return -EINVAL;
+	}
+
+	offset = wq->offset + ((wqe_index % wq->wqe_cnt) << wq->wqe_shift);
+	wq_end = wq->offset + (wq->wqe_cnt << wq->wqe_shift);
+
+	if (send && length < sizeof(struct mlx5_wqe_ctrl_seg))
+		return -EINVAL;
+
+	if (offset > umem->length ||
+	    (send && offset + sizeof(struct mlx5_wqe_ctrl_seg) > umem->length))
+		return -EINVAL;
+
+	first_copy_length = min_t(u32, offset + length, wq_end) - offset;
+	ret = ib_umem_copy_from(buffer, umem, offset, first_copy_length);
+	if (ret)
+		return ret;
+
+	if (send) {
+		struct mlx5_wqe_ctrl_seg *ctrl = buffer;
+		int ds = be32_to_cpu(ctrl->qpn_ds) & MLX5_WQE_CTRL_DS_MASK;
+
+		wqe_length = ds * MLX5_WQE_DS_UNITS;
+	} else {
+		wqe_length = 1 << wq->wqe_shift;
+	}
+
+	if (wqe_length <= first_copy_length)
+		return first_copy_length;
+
+	ret = ib_umem_copy_from(buffer + first_copy_length, umem, wq->offset,
+				wqe_length - first_copy_length);
+	if (ret)
+		return ret;
+
+	return wqe_length;
+}
+
 static void mlx5_ib_qp_event(struct mlx5_core_qp *qp, int type)
 {
 	struct ib_qp *ibqp = &to_mibqp(qp)->ibqp;
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 3fa075daeb1..67f4b9660b0 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -189,6 +189,9 @@ struct mlx5_wqe_ctrl_seg {
 	__be32			imm;
 };
 
+#define MLX5_WQE_CTRL_DS_MASK 0x3f
+#define MLX5_WQE_DS_UNITS 16
+
 struct mlx5_wqe_xrc_seg {
 	__be32			xrc_srqn;
 	u8			rsvd[12];
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 45bb04bc88c..a51f4091489 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -98,7 +98,10 @@ static inline struct ib_umem *ib_umem_get(struct ib_ucontext *context,
 }
 static inline void ib_umem_release(struct ib_umem *umem) { }
 static inline int ib_umem_page_count(struct ib_umem *umem) { return 0; }
-
+static inline int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset,
+		      		    size_t length) {
+	return -EINVAL;
+}
 #endif /* CONFIG_INFINIBAND_USER_MEM */
 
 #endif /* IB_UMEM_H */
-- 
cgit v1.2.3-70-g09d2


From 5a77abf9a97a7ecc8fb0f6bf4ad411fb12b02f31 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@dev.mellanox.co.il>
Date: Thu, 11 Dec 2014 17:04:15 +0200
Subject: IB/core: Add support for extended query device caps

Add extensible query device capabilities verb to allow adding new features.
ib_uverbs_ex_query_device is added and copy_query_dev_fields is used to
copy capability fields to be used by both ib_uverbs_query_device and
ib_uverbs_ex_query_device.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/uverbs.h      |   1 +
 drivers/infiniband/core/uverbs_cmd.c  | 124 +++++++++++++++++++++++-----------
 drivers/infiniband/core/uverbs_main.c |   3 +-
 include/rdma/ib_verbs.h               |   5 +-
 include/uapi/rdma/ib_user_verbs.h     |  14 +++-
 5 files changed, 103 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 643c08a025a..b716b081564 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -258,5 +258,6 @@ IB_UVERBS_DECLARE_CMD(close_xrcd);
 
 IB_UVERBS_DECLARE_EX_CMD(create_flow);
 IB_UVERBS_DECLARE_EX_CMD(destroy_flow);
+IB_UVERBS_DECLARE_EX_CMD(query_device);
 
 #endif /* UVERBS_H */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 5ba2a86aab6..c7a43624c96 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -378,6 +378,52 @@ err:
 	return ret;
 }
 
+static void copy_query_dev_fields(struct ib_uverbs_file *file,
+				  struct ib_uverbs_query_device_resp *resp,
+				  struct ib_device_attr *attr)
+{
+	resp->fw_ver		= attr->fw_ver;
+	resp->node_guid		= file->device->ib_dev->node_guid;
+	resp->sys_image_guid	= attr->sys_image_guid;
+	resp->max_mr_size	= attr->max_mr_size;
+	resp->page_size_cap	= attr->page_size_cap;
+	resp->vendor_id		= attr->vendor_id;
+	resp->vendor_part_id	= attr->vendor_part_id;
+	resp->hw_ver		= attr->hw_ver;
+	resp->max_qp		= attr->max_qp;
+	resp->max_qp_wr		= attr->max_qp_wr;
+	resp->device_cap_flags	= attr->device_cap_flags;
+	resp->max_sge		= attr->max_sge;
+	resp->max_sge_rd	= attr->max_sge_rd;
+	resp->max_cq		= attr->max_cq;
+	resp->max_cqe		= attr->max_cqe;
+	resp->max_mr		= attr->max_mr;
+	resp->max_pd		= attr->max_pd;
+	resp->max_qp_rd_atom	= attr->max_qp_rd_atom;
+	resp->max_ee_rd_atom	= attr->max_ee_rd_atom;
+	resp->max_res_rd_atom	= attr->max_res_rd_atom;
+	resp->max_qp_init_rd_atom	= attr->max_qp_init_rd_atom;
+	resp->max_ee_init_rd_atom	= attr->max_ee_init_rd_atom;
+	resp->atomic_cap		= attr->atomic_cap;
+	resp->max_ee			= attr->max_ee;
+	resp->max_rdd			= attr->max_rdd;
+	resp->max_mw			= attr->max_mw;
+	resp->max_raw_ipv6_qp		= attr->max_raw_ipv6_qp;
+	resp->max_raw_ethy_qp		= attr->max_raw_ethy_qp;
+	resp->max_mcast_grp		= attr->max_mcast_grp;
+	resp->max_mcast_qp_attach	= attr->max_mcast_qp_attach;
+	resp->max_total_mcast_qp_attach	= attr->max_total_mcast_qp_attach;
+	resp->max_ah			= attr->max_ah;
+	resp->max_fmr			= attr->max_fmr;
+	resp->max_map_per_fmr		= attr->max_map_per_fmr;
+	resp->max_srq			= attr->max_srq;
+	resp->max_srq_wr		= attr->max_srq_wr;
+	resp->max_srq_sge		= attr->max_srq_sge;
+	resp->max_pkeys			= attr->max_pkeys;
+	resp->local_ca_ack_delay	= attr->local_ca_ack_delay;
+	resp->phys_port_cnt		= file->device->ib_dev->phys_port_cnt;
+}
+
 ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file,
 			       const char __user *buf,
 			       int in_len, int out_len)
@@ -398,47 +444,7 @@ ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file,
 		return ret;
 
 	memset(&resp, 0, sizeof resp);
-
-	resp.fw_ver 		       = attr.fw_ver;
-	resp.node_guid 		       = file->device->ib_dev->node_guid;
-	resp.sys_image_guid 	       = attr.sys_image_guid;
-	resp.max_mr_size 	       = attr.max_mr_size;
-	resp.page_size_cap 	       = attr.page_size_cap;
-	resp.vendor_id 		       = attr.vendor_id;
-	resp.vendor_part_id 	       = attr.vendor_part_id;
-	resp.hw_ver 		       = attr.hw_ver;
-	resp.max_qp 		       = attr.max_qp;
-	resp.max_qp_wr 		       = attr.max_qp_wr;
-	resp.device_cap_flags 	       = attr.device_cap_flags;
-	resp.max_sge 		       = attr.max_sge;
-	resp.max_sge_rd 	       = attr.max_sge_rd;
-	resp.max_cq 		       = attr.max_cq;
-	resp.max_cqe 		       = attr.max_cqe;
-	resp.max_mr 		       = attr.max_mr;
-	resp.max_pd 		       = attr.max_pd;
-	resp.max_qp_rd_atom 	       = attr.max_qp_rd_atom;
-	resp.max_ee_rd_atom 	       = attr.max_ee_rd_atom;
-	resp.max_res_rd_atom 	       = attr.max_res_rd_atom;
-	resp.max_qp_init_rd_atom       = attr.max_qp_init_rd_atom;
-	resp.max_ee_init_rd_atom       = attr.max_ee_init_rd_atom;
-	resp.atomic_cap 	       = attr.atomic_cap;
-	resp.max_ee 		       = attr.max_ee;
-	resp.max_rdd 		       = attr.max_rdd;
-	resp.max_mw 		       = attr.max_mw;
-	resp.max_raw_ipv6_qp 	       = attr.max_raw_ipv6_qp;
-	resp.max_raw_ethy_qp 	       = attr.max_raw_ethy_qp;
-	resp.max_mcast_grp 	       = attr.max_mcast_grp;
-	resp.max_mcast_qp_attach       = attr.max_mcast_qp_attach;
-	resp.max_total_mcast_qp_attach = attr.max_total_mcast_qp_attach;
-	resp.max_ah 		       = attr.max_ah;
-	resp.max_fmr 		       = attr.max_fmr;
-	resp.max_map_per_fmr 	       = attr.max_map_per_fmr;
-	resp.max_srq 		       = attr.max_srq;
-	resp.max_srq_wr 	       = attr.max_srq_wr;
-	resp.max_srq_sge 	       = attr.max_srq_sge;
-	resp.max_pkeys 		       = attr.max_pkeys;
-	resp.local_ca_ack_delay        = attr.local_ca_ack_delay;
-	resp.phys_port_cnt	       = file->device->ib_dev->phys_port_cnt;
+	copy_query_dev_fields(file, &resp, &attr);
 
 	if (copy_to_user((void __user *) (unsigned long) cmd.response,
 			 &resp, sizeof resp))
@@ -3253,3 +3259,39 @@ ssize_t ib_uverbs_destroy_srq(struct ib_uverbs_file *file,
 
 	return ret ? ret : in_len;
 }
+
+int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
+			      struct ib_udata *ucore,
+			      struct ib_udata *uhw)
+{
+	struct ib_uverbs_ex_query_device_resp resp;
+	struct ib_uverbs_ex_query_device  cmd;
+	struct ib_device_attr attr;
+	struct ib_device *device;
+	int err;
+
+	device = file->device->ib_dev;
+	if (ucore->inlen < sizeof(cmd))
+		return -EINVAL;
+
+	err = ib_copy_from_udata(&cmd, ucore, sizeof(cmd));
+	if (err)
+		return err;
+
+	if (cmd.reserved)
+		return -EINVAL;
+
+	err = device->query_device(device, &attr);
+	if (err)
+		return err;
+
+	memset(&resp, 0, sizeof(resp));
+	copy_query_dev_fields(file, &resp.base, &attr);
+	resp.comp_mask = 0;
+
+	err = ib_copy_to_udata(ucore, &resp, sizeof(resp));
+	if (err)
+		return err;
+
+	return 0;
+}
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 71ab83fde47..97402502879 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -122,7 +122,8 @@ static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file,
 				    struct ib_udata *ucore,
 				    struct ib_udata *uhw) = {
 	[IB_USER_VERBS_EX_CMD_CREATE_FLOW]	= ib_uverbs_ex_create_flow,
-	[IB_USER_VERBS_EX_CMD_DESTROY_FLOW]	= ib_uverbs_ex_destroy_flow
+	[IB_USER_VERBS_EX_CMD_DESTROY_FLOW]	= ib_uverbs_ex_destroy_flow,
+	[IB_USER_VERBS_EX_CMD_QUERY_DEVICE]	= ib_uverbs_ex_query_device
 };
 
 static void ib_uverbs_add_one(struct ib_device *device);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 470a011d6fa..97a999f9e4d 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1662,7 +1662,10 @@ static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t
 
 static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len)
 {
-	return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0;
+	size_t copy_sz;
+
+	copy_sz = min_t(size_t, len, udata->outlen);
+	return copy_to_user(udata->outbuf, src, copy_sz) ? -EFAULT : 0;
 }
 
 /**
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 26daf55ff76..e8a96071e35 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -90,8 +90,9 @@ enum {
 };
 
 enum {
+	IB_USER_VERBS_EX_CMD_QUERY_DEVICE = IB_USER_VERBS_CMD_QUERY_DEVICE,
 	IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
-	IB_USER_VERBS_EX_CMD_DESTROY_FLOW
+	IB_USER_VERBS_EX_CMD_DESTROY_FLOW,
 };
 
 /*
@@ -201,6 +202,17 @@ struct ib_uverbs_query_device_resp {
 	__u8  reserved[4];
 };
 
+struct ib_uverbs_ex_query_device {
+	__u32 comp_mask;
+	__u32 reserved;
+};
+
+struct ib_uverbs_ex_query_device_resp {
+	struct ib_uverbs_query_device_resp base;
+	__u32 comp_mask;
+	__u32 reserved;
+};
+
 struct ib_uverbs_query_port {
 	__u64 response;
 	__u8  port_num;
-- 
cgit v1.2.3-70-g09d2


From 860f10a799c83e38a69d5a69d80da5312a4c4106 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagig@mellanox.com>
Date: Thu, 11 Dec 2014 17:04:16 +0200
Subject: IB/core: Add flags for on demand paging support

* Add a configuration option for enable on-demand paging support in
  the infiniband subsystem (CONFIG_INFINIBAND_ON_DEMAND_PAGING). In a
  later patch, this configuration option will select the MMU_NOTIFIER
  configuration option to enable mmu notifiers.
* Add a flag for on demand paging (ODP) support in the IB device capabilities.
* Add a flag to request ODP MR in the access flags to reg_mr.
* Fail registrations done with the ODP flag when the low-level driver
  doesn't support this.
* Change the conditions in which an MR will be writable to explicitly
  specify the access flags.  This is to avoid making an MR writable just
  because it is an ODP MR.
* Add a ODP capabilities to the extended query device verb.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/Kconfig           | 10 ++++++++++
 drivers/infiniband/core/umem.c       |  8 +++++---
 drivers/infiniband/core/uverbs_cmd.c | 25 +++++++++++++++++++++++++
 include/rdma/ib_verbs.h              | 28 ++++++++++++++++++++++++++--
 include/uapi/rdma/ib_user_verbs.h    | 15 +++++++++++++++
 5 files changed, 81 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 77089399359..089a2c2af32 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -38,6 +38,16 @@ config INFINIBAND_USER_MEM
 	depends on INFINIBAND_USER_ACCESS != n
 	default y
 
+config INFINIBAND_ON_DEMAND_PAGING
+	bool "InfiniBand on-demand paging support"
+	depends on INFINIBAND_USER_MEM
+	default y
+	---help---
+	  On demand paging support for the InfiniBand subsystem.
+	  Together with driver support this allows registration of
+	  memory regions without pinning their pages, fetching the
+	  pages on demand instead.
+
 config INFINIBAND_ADDR_TRANS
 	bool
 	depends on INFINIBAND
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 6f152628e0d..c328e4693d1 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -107,13 +107,15 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	umem->page_size = PAGE_SIZE;
 	umem->pid       = get_task_pid(current, PIDTYPE_PID);
 	/*
-	 * We ask for writable memory if any access flags other than
-	 * "remote read" are set.  "Local write" and "remote write"
+	 * We ask for writable memory if any of the following
+	 * access flags are set.  "Local write" and "remote write"
 	 * obviously require write access.  "Remote atomic" can do
 	 * things like fetch and add, which will modify memory, and
 	 * "MW bind" can change permissions by binding a window.
 	 */
-	umem->writable  = !!(access & ~IB_ACCESS_REMOTE_READ);
+	umem->writable  = !!(access &
+		(IB_ACCESS_LOCAL_WRITE   | IB_ACCESS_REMOTE_WRITE |
+		 IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND));
 
 	/* We assume the memory is from hugetlb until proved otherwise */
 	umem->hugetlb   = 1;
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index c7a43624c96..f9326ccda4b 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -953,6 +953,18 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file,
 		goto err_free;
 	}
 
+	if (cmd.access_flags & IB_ACCESS_ON_DEMAND) {
+		struct ib_device_attr attr;
+
+		ret = ib_query_device(pd->device, &attr);
+		if (ret || !(attr.device_cap_flags &
+				IB_DEVICE_ON_DEMAND_PAGING)) {
+			pr_debug("ODP support not available\n");
+			ret = -EINVAL;
+			goto err_put;
+		}
+	}
+
 	mr = pd->device->reg_user_mr(pd, cmd.start, cmd.length, cmd.hca_va,
 				     cmd.access_flags, &udata);
 	if (IS_ERR(mr)) {
@@ -3289,6 +3301,19 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 	copy_query_dev_fields(file, &resp.base, &attr);
 	resp.comp_mask = 0;
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	if (cmd.comp_mask & IB_USER_VERBS_EX_QUERY_DEVICE_ODP) {
+		resp.odp_caps.general_caps = attr.odp_caps.general_caps;
+		resp.odp_caps.per_transport_caps.rc_odp_caps =
+			attr.odp_caps.per_transport_caps.rc_odp_caps;
+		resp.odp_caps.per_transport_caps.uc_odp_caps =
+			attr.odp_caps.per_transport_caps.uc_odp_caps;
+		resp.odp_caps.per_transport_caps.ud_odp_caps =
+			attr.odp_caps.per_transport_caps.ud_odp_caps;
+		resp.comp_mask |= IB_USER_VERBS_EX_QUERY_DEVICE_ODP;
+	}
+#endif
+
 	err = ib_copy_to_udata(ucore, &resp, sizeof(resp));
 	if (err)
 		return err;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 97a999f9e4d..a41bc5a39eb 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -123,7 +123,8 @@ enum ib_device_cap_flags {
 	IB_DEVICE_MEM_WINDOW_TYPE_2A	= (1<<23),
 	IB_DEVICE_MEM_WINDOW_TYPE_2B	= (1<<24),
 	IB_DEVICE_MANAGED_FLOW_STEERING = (1<<29),
-	IB_DEVICE_SIGNATURE_HANDOVER	= (1<<30)
+	IB_DEVICE_SIGNATURE_HANDOVER	= (1<<30),
+	IB_DEVICE_ON_DEMAND_PAGING	= (1<<31),
 };
 
 enum ib_signature_prot_cap {
@@ -143,6 +144,27 @@ enum ib_atomic_cap {
 	IB_ATOMIC_GLOB
 };
 
+enum ib_odp_general_cap_bits {
+	IB_ODP_SUPPORT = 1 << 0,
+};
+
+enum ib_odp_transport_cap_bits {
+	IB_ODP_SUPPORT_SEND	= 1 << 0,
+	IB_ODP_SUPPORT_RECV	= 1 << 1,
+	IB_ODP_SUPPORT_WRITE	= 1 << 2,
+	IB_ODP_SUPPORT_READ	= 1 << 3,
+	IB_ODP_SUPPORT_ATOMIC	= 1 << 4,
+};
+
+struct ib_odp_caps {
+	uint64_t general_caps;
+	struct {
+		uint32_t  rc_odp_caps;
+		uint32_t  uc_odp_caps;
+		uint32_t  ud_odp_caps;
+	} per_transport_caps;
+};
+
 struct ib_device_attr {
 	u64			fw_ver;
 	__be64			sys_image_guid;
@@ -186,6 +208,7 @@ struct ib_device_attr {
 	u8			local_ca_ack_delay;
 	int			sig_prot_cap;
 	int			sig_guard_cap;
+	struct ib_odp_caps	odp_caps;
 };
 
 enum ib_mtu {
@@ -1073,7 +1096,8 @@ enum ib_access_flags {
 	IB_ACCESS_REMOTE_READ	= (1<<2),
 	IB_ACCESS_REMOTE_ATOMIC	= (1<<3),
 	IB_ACCESS_MW_BIND	= (1<<4),
-	IB_ZERO_BASED		= (1<<5)
+	IB_ZERO_BASED		= (1<<5),
+	IB_ACCESS_ON_DEMAND     = (1<<6),
 };
 
 struct ib_phys_buf {
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index e8a96071e35..4275b961bf6 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -202,15 +202,30 @@ struct ib_uverbs_query_device_resp {
 	__u8  reserved[4];
 };
 
+enum {
+	IB_USER_VERBS_EX_QUERY_DEVICE_ODP =		1ULL << 0,
+};
+
 struct ib_uverbs_ex_query_device {
 	__u32 comp_mask;
 	__u32 reserved;
 };
 
+struct ib_uverbs_odp_caps {
+	__u64 general_caps;
+	struct {
+		__u32 rc_odp_caps;
+		__u32 uc_odp_caps;
+		__u32 ud_odp_caps;
+	} per_transport_caps;
+	__u32 reserved;
+};
+
 struct ib_uverbs_ex_query_device_resp {
 	struct ib_uverbs_query_device_resp base;
 	__u32 comp_mask;
 	__u32 reserved;
+	struct ib_uverbs_odp_caps odp_caps;
 };
 
 struct ib_uverbs_query_port {
-- 
cgit v1.2.3-70-g09d2


From 8ada2c1c0c1d75a60723cd2ca7d49c594a146af6 Mon Sep 17 00:00:00 2001
From: Shachar Raindel <raindel@mellanox.com>
Date: Thu, 11 Dec 2014 17:04:17 +0200
Subject: IB/core: Add support for on demand paging regions

* Extend the umem struct to keep the ODP related data.
* Allocate and initialize the ODP related information in the umem
  (page_list, dma_list) and freeing as needed in the end of the run.
* Store a reference to the process PID struct in the ucontext.  Used to
  safely obtain the task_struct and the mm during fault handling,
  without preventing the task destruction if needed.
* Add 2 helper functions: ib_umem_odp_map_dma_pages and
  ib_umem_odp_unmap_dma_pages. These functions get the DMA addresses
  of specific pages of the umem (and, currently, pin them).
* Support for page faults only - IB core will keep the reference on
  the pages used and call put_page when freeing an ODP umem
  area. Invalidations support will be added in a later patch.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/Makefile      |   1 +
 drivers/infiniband/core/umem.c        |  24 +++
 drivers/infiniband/core/umem_odp.c    | 309 ++++++++++++++++++++++++++++++++++
 drivers/infiniband/core/uverbs_cmd.c  |   5 +
 drivers/infiniband/core/uverbs_main.c |   2 +
 include/rdma/ib_umem.h                |   2 +
 include/rdma/ib_umem_odp.h            |  97 +++++++++++
 include/rdma/ib_verbs.h               |   2 +
 8 files changed, 442 insertions(+)
 create mode 100644 drivers/infiniband/core/umem_odp.c
 create mode 100644 include/rdma/ib_umem_odp.h

(limited to 'include')

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index ffd0af6734a..c58f7913c56 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
 ib_core-y :=			packer.o ud_header.o verbs.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
+ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o
 
 ib_mad-y :=			mad.o smi.o agent.o mad_rmpp.o
 
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index c328e4693d1..5baceb79f21 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -39,6 +39,7 @@
 #include <linux/hugetlb.h>
 #include <linux/dma-attrs.h>
 #include <linux/slab.h>
+#include <rdma/ib_umem_odp.h>
 
 #include "uverbs.h"
 
@@ -69,6 +70,10 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 
 /**
  * ib_umem_get - Pin and DMA map userspace memory.
+ *
+ * If access flags indicate ODP memory, avoid pinning. Instead, stores
+ * the mm for future page fault handling.
+ *
  * @context: userspace context to pin memory for
  * @addr: userspace virtual address to start at
  * @size: length of region to pin
@@ -117,6 +122,17 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 		(IB_ACCESS_LOCAL_WRITE   | IB_ACCESS_REMOTE_WRITE |
 		 IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND));
 
+	if (access & IB_ACCESS_ON_DEMAND) {
+		ret = ib_umem_odp_get(context, umem);
+		if (ret) {
+			kfree(umem);
+			return ERR_PTR(ret);
+		}
+		return umem;
+	}
+
+	umem->odp_data = NULL;
+
 	/* We assume the memory is from hugetlb until proved otherwise */
 	umem->hugetlb   = 1;
 
@@ -237,6 +253,11 @@ void ib_umem_release(struct ib_umem *umem)
 	struct task_struct *task;
 	unsigned long diff;
 
+	if (umem->odp_data) {
+		ib_umem_odp_release(umem);
+		return;
+	}
+
 	__ib_umem_release(umem->context->device, umem, 1);
 
 	task = get_pid_task(umem->pid, PIDTYPE_PID);
@@ -285,6 +306,9 @@ int ib_umem_page_count(struct ib_umem *umem)
 	int n;
 	struct scatterlist *sg;
 
+	if (umem->odp_data)
+		return ib_umem_num_pages(umem);
+
 	shift = ilog2(umem->page_size);
 
 	n = 0;
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
new file mode 100644
index 00000000000..f889e8d793b
--- /dev/null
+++ b/drivers/infiniband/core/umem_odp.c
@@ -0,0 +1,309 @@
+/*
+ * Copyright (c) 2014 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/pid.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/vmalloc.h>
+
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_umem.h>
+#include <rdma/ib_umem_odp.h>
+
+int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem)
+{
+	int ret_val;
+	struct pid *our_pid;
+
+	/* Prevent creating ODP MRs in child processes */
+	rcu_read_lock();
+	our_pid = get_task_pid(current->group_leader, PIDTYPE_PID);
+	rcu_read_unlock();
+	put_pid(our_pid);
+	if (context->tgid != our_pid)
+		return -EINVAL;
+
+	umem->hugetlb = 0;
+	umem->odp_data = kzalloc(sizeof(*umem->odp_data), GFP_KERNEL);
+	if (!umem->odp_data)
+		return -ENOMEM;
+
+	mutex_init(&umem->odp_data->umem_mutex);
+
+	umem->odp_data->page_list = vzalloc(ib_umem_num_pages(umem) *
+					    sizeof(*umem->odp_data->page_list));
+	if (!umem->odp_data->page_list) {
+		ret_val = -ENOMEM;
+		goto out_odp_data;
+	}
+
+	umem->odp_data->dma_list = vzalloc(ib_umem_num_pages(umem) *
+					  sizeof(*umem->odp_data->dma_list));
+	if (!umem->odp_data->dma_list) {
+		ret_val = -ENOMEM;
+		goto out_page_list;
+	}
+
+	return 0;
+
+out_page_list:
+	vfree(umem->odp_data->page_list);
+out_odp_data:
+	kfree(umem->odp_data);
+	return ret_val;
+}
+
+void ib_umem_odp_release(struct ib_umem *umem)
+{
+	/*
+	 * Ensure that no more pages are mapped in the umem.
+	 *
+	 * It is the driver's responsibility to ensure, before calling us,
+	 * that the hardware will not attempt to access the MR any more.
+	 */
+	ib_umem_odp_unmap_dma_pages(umem, ib_umem_start(umem),
+				    ib_umem_end(umem));
+
+	vfree(umem->odp_data->dma_list);
+	vfree(umem->odp_data->page_list);
+	kfree(umem->odp_data);
+	kfree(umem);
+}
+
+/*
+ * Map for DMA and insert a single page into the on-demand paging page tables.
+ *
+ * @umem: the umem to insert the page to.
+ * @page_index: index in the umem to add the page to.
+ * @page: the page struct to map and add.
+ * @access_mask: access permissions needed for this page.
+ * @current_seq: sequence number for synchronization with invalidations.
+ *               the sequence number is taken from
+ *               umem->odp_data->notifiers_seq.
+ *
+ * The function returns -EFAULT if the DMA mapping operation fails.
+ *
+ * The page is released via put_page even if the operation failed. For
+ * on-demand pinning, the page is released whenever it isn't stored in the
+ * umem.
+ */
+static int ib_umem_odp_map_dma_single_page(
+		struct ib_umem *umem,
+		int page_index,
+		struct page *page,
+		u64 access_mask,
+		unsigned long current_seq)
+{
+	struct ib_device *dev = umem->context->device;
+	dma_addr_t dma_addr;
+	int stored_page = 0;
+	int ret = 0;
+
+	mutex_lock(&umem->odp_data->umem_mutex);
+	if (!(umem->odp_data->dma_list[page_index])) {
+		dma_addr = ib_dma_map_page(dev,
+					   page,
+					   0, PAGE_SIZE,
+					   DMA_BIDIRECTIONAL);
+		if (ib_dma_mapping_error(dev, dma_addr)) {
+			ret = -EFAULT;
+			goto out;
+		}
+		umem->odp_data->dma_list[page_index] = dma_addr | access_mask;
+		umem->odp_data->page_list[page_index] = page;
+		stored_page = 1;
+	} else if (umem->odp_data->page_list[page_index] == page) {
+		umem->odp_data->dma_list[page_index] |= access_mask;
+	} else {
+		pr_err("error: got different pages in IB device and from get_user_pages. IB device page: %p, gup page: %p\n",
+		       umem->odp_data->page_list[page_index], page);
+	}
+
+out:
+	mutex_unlock(&umem->odp_data->umem_mutex);
+
+	if (!stored_page)
+		put_page(page);
+
+	return ret;
+}
+
+/**
+ * ib_umem_odp_map_dma_pages - Pin and DMA map userspace memory in an ODP MR.
+ *
+ * Pins the range of pages passed in the argument, and maps them to
+ * DMA addresses. The DMA addresses of the mapped pages is updated in
+ * umem->odp_data->dma_list.
+ *
+ * Returns the number of pages mapped in success, negative error code
+ * for failure.
+ *
+ * @umem: the umem to map and pin
+ * @user_virt: the address from which we need to map.
+ * @bcnt: the minimal number of bytes to pin and map. The mapping might be
+ *        bigger due to alignment, and may also be smaller in case of an error
+ *        pinning or mapping a page. The actual pages mapped is returned in
+ *        the return value.
+ * @access_mask: bit mask of the requested access permissions for the given
+ *               range.
+ * @current_seq: the MMU notifiers sequance value for synchronization with
+ *               invalidations. the sequance number is read from
+ *               umem->odp_data->notifiers_seq before calling this function
+ */
+int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
+			      u64 access_mask, unsigned long current_seq)
+{
+	struct task_struct *owning_process  = NULL;
+	struct mm_struct   *owning_mm       = NULL;
+	struct page       **local_page_list = NULL;
+	u64 off;
+	int j, k, ret = 0, start_idx, npages = 0;
+
+	if (access_mask == 0)
+		return -EINVAL;
+
+	if (user_virt < ib_umem_start(umem) ||
+	    user_virt + bcnt > ib_umem_end(umem))
+		return -EFAULT;
+
+	local_page_list = (struct page **)__get_free_page(GFP_KERNEL);
+	if (!local_page_list)
+		return -ENOMEM;
+
+	off = user_virt & (~PAGE_MASK);
+	user_virt = user_virt & PAGE_MASK;
+	bcnt += off; /* Charge for the first page offset as well. */
+
+	owning_process = get_pid_task(umem->context->tgid, PIDTYPE_PID);
+	if (owning_process == NULL) {
+		ret = -EINVAL;
+		goto out_no_task;
+	}
+
+	owning_mm = get_task_mm(owning_process);
+	if (owning_mm == NULL) {
+		ret = -EINVAL;
+		goto out_put_task;
+	}
+
+	start_idx = (user_virt - ib_umem_start(umem)) >> PAGE_SHIFT;
+	k = start_idx;
+
+	while (bcnt > 0) {
+		const size_t gup_num_pages =
+			min_t(size_t, ALIGN(bcnt, PAGE_SIZE) / PAGE_SIZE,
+			      PAGE_SIZE / sizeof(struct page *));
+
+		down_read(&owning_mm->mmap_sem);
+		/*
+		 * Note: this might result in redundent page getting. We can
+		 * avoid this by checking dma_list to be 0 before calling
+		 * get_user_pages. However, this make the code much more
+		 * complex (and doesn't gain us much performance in most use
+		 * cases).
+		 */
+		npages = get_user_pages(owning_process, owning_mm, user_virt,
+					gup_num_pages,
+					access_mask & ODP_WRITE_ALLOWED_BIT, 0,
+					local_page_list, NULL);
+		up_read(&owning_mm->mmap_sem);
+
+		if (npages < 0)
+			break;
+
+		bcnt -= min_t(size_t, npages << PAGE_SHIFT, bcnt);
+		user_virt += npages << PAGE_SHIFT;
+		for (j = 0; j < npages; ++j) {
+			ret = ib_umem_odp_map_dma_single_page(
+				umem, k, local_page_list[j], access_mask,
+				current_seq);
+			if (ret < 0)
+				break;
+			k++;
+		}
+
+		if (ret < 0) {
+			/* Release left over pages when handling errors. */
+			for (++j; j < npages; ++j)
+				put_page(local_page_list[j]);
+			break;
+		}
+	}
+
+	if (ret >= 0) {
+		if (npages < 0 && k == start_idx)
+			ret = npages;
+		else
+			ret = k - start_idx;
+	}
+
+	mmput(owning_mm);
+out_put_task:
+	put_task_struct(owning_process);
+out_no_task:
+	free_page((unsigned long)local_page_list);
+	return ret;
+}
+EXPORT_SYMBOL(ib_umem_odp_map_dma_pages);
+
+void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 virt,
+				 u64 bound)
+{
+	int idx;
+	u64 addr;
+	struct ib_device *dev = umem->context->device;
+
+	virt  = max_t(u64, virt,  ib_umem_start(umem));
+	bound = min_t(u64, bound, ib_umem_end(umem));
+	for (addr = virt; addr < bound; addr += (u64)umem->page_size) {
+		idx = (addr - ib_umem_start(umem)) / PAGE_SIZE;
+		mutex_lock(&umem->odp_data->umem_mutex);
+		if (umem->odp_data->page_list[idx]) {
+			struct page *page = umem->odp_data->page_list[idx];
+			struct page *head_page = compound_head(page);
+			dma_addr_t dma = umem->odp_data->dma_list[idx];
+			dma_addr_t dma_addr = dma & ODP_DMA_ADDR_MASK;
+
+			WARN_ON(!dma_addr);
+
+			ib_dma_unmap_page(dev, dma_addr, PAGE_SIZE,
+					  DMA_BIDIRECTIONAL);
+			if (dma & ODP_WRITE_ALLOWED_BIT)
+				set_page_dirty_lock(head_page);
+			put_page(page);
+		}
+		mutex_unlock(&umem->odp_data->umem_mutex);
+	}
+}
+EXPORT_SYMBOL(ib_umem_odp_unmap_dma_pages);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index f9326ccda4b..70b697d8fbb 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -36,6 +36,7 @@
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 
 #include <asm/uaccess.h>
 
@@ -325,6 +326,9 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	INIT_LIST_HEAD(&ucontext->ah_list);
 	INIT_LIST_HEAD(&ucontext->xrcd_list);
 	INIT_LIST_HEAD(&ucontext->rule_list);
+	rcu_read_lock();
+	ucontext->tgid = get_task_pid(current->group_leader, PIDTYPE_PID);
+	rcu_read_unlock();
 	ucontext->closing = 0;
 
 	resp.num_comp_vectors = file->device->num_comp_vectors;
@@ -371,6 +375,7 @@ err_fd:
 	put_unused_fd(resp.async_fd);
 
 err_free:
+	put_pid(ucontext->tgid);
 	ibdev->dealloc_ucontext(ucontext);
 
 err:
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 97402502879..e6c23b9eab3 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -297,6 +297,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 		kfree(uobj);
 	}
 
+	put_pid(context->tgid);
+
 	return context->device->dealloc_ucontext(context);
 }
 
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index a51f4091489..2d83cfd7e6c 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -38,6 +38,7 @@
 #include <linux/workqueue.h>
 
 struct ib_ucontext;
+struct ib_umem_odp;
 
 struct ib_umem {
 	struct ib_ucontext     *context;
@@ -50,6 +51,7 @@ struct ib_umem {
 	struct pid             *pid;
 	struct mm_struct       *mm;
 	unsigned long		diff;
+	struct ib_umem_odp     *odp_data;
 	struct sg_table sg_head;
 	int             nmap;
 	int             npages;
diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
new file mode 100644
index 00000000000..b5a2df1923b
--- /dev/null
+++ b/include/rdma/ib_umem_odp.h
@@ -0,0 +1,97 @@
+/*
+ * Copyright (c) 2014 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef IB_UMEM_ODP_H
+#define IB_UMEM_ODP_H
+
+#include <rdma/ib_umem.h>
+
+struct ib_umem_odp {
+	/*
+	 * An array of the pages included in the on-demand paging umem.
+	 * Indices of pages that are currently not mapped into the device will
+	 * contain NULL.
+	 */
+	struct page		**page_list;
+	/*
+	 * An array of the same size as page_list, with DMA addresses mapped
+	 * for pages the pages in page_list. The lower two bits designate
+	 * access permissions. See ODP_READ_ALLOWED_BIT and
+	 * ODP_WRITE_ALLOWED_BIT.
+	 */
+	dma_addr_t		*dma_list;
+	/*
+	 * The umem_mutex protects the page_list and dma_list fields of an ODP
+	 * umem, allowing only a single thread to map/unmap pages.
+	 */
+	struct mutex		umem_mutex;
+	void			*private; /* for the HW driver to use. */
+};
+
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+
+int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem);
+
+void ib_umem_odp_release(struct ib_umem *umem);
+
+/*
+ * The lower 2 bits of the DMA address signal the R/W permissions for
+ * the entry. To upgrade the permissions, provide the appropriate
+ * bitmask to the map_dma_pages function.
+ *
+ * Be aware that upgrading a mapped address might result in change of
+ * the DMA address for the page.
+ */
+#define ODP_READ_ALLOWED_BIT  (1<<0ULL)
+#define ODP_WRITE_ALLOWED_BIT (1<<1ULL)
+
+#define ODP_DMA_ADDR_MASK (~(ODP_READ_ALLOWED_BIT | ODP_WRITE_ALLOWED_BIT))
+
+int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 start_offset, u64 bcnt,
+			      u64 access_mask, unsigned long current_seq);
+
+void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 start_offset,
+				 u64 bound);
+
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
+
+static inline int ib_umem_odp_get(struct ib_ucontext *context,
+				  struct ib_umem *umem)
+{
+	return -EINVAL;
+}
+
+static inline void ib_umem_odp_release(struct ib_umem *umem) {}
+
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
+
+#endif /* IB_UMEM_ODP_H */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index a41bc5a39eb..3af5dcad1b6 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1151,6 +1151,8 @@ struct ib_ucontext {
 	struct list_head	xrcd_list;
 	struct list_head	rule_list;
 	int			closing;
+
+	struct pid             *tgid;
 };
 
 struct ib_uobject {
-- 
cgit v1.2.3-70-g09d2


From 882214e2b12860bff1ccff15a3ec2bbb29d58c02 Mon Sep 17 00:00:00 2001
From: Haggai Eran <haggaie@mellanox.com>
Date: Thu, 11 Dec 2014 17:04:18 +0200
Subject: IB/core: Implement support for MMU notifiers regarding on demand
 paging regions

* Add an interval tree implementation for ODP umems. Create an
  interval tree for each ucontext (including a count of the number of
  ODP MRs in this context, semaphore, etc.), and register ODP umems in
  the interval tree.
* Add MMU notifiers handling functions, using the interval tree to
  notify only the relevant umems and underlying MRs.
* Register to receive MMU notifier events from the MM subsystem upon
  ODP MR registration (and unregister accordingly).
* Add a completion object to synchronize the destruction of ODP umems.
* Add mechanism to abort page faults when there's a concurrent invalidation.

The way we synchronize between concurrent invalidations and page
faults is by keeping a counter of currently running invalidations, and
a sequence number that is incremented whenever an invalidation is
caught. The page fault code checks the counter and also verifies that
the sequence number hasn't progressed before it updates the umem's
page tables. This is similar to what the kvm module does.

In order to prevent the case where we register a umem in the middle of
an ongoing notifier, we also keep a per ucontext counter of the total
number of active mmu notifiers. We only enable new umems when all the
running notifiers complete.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Yuval Dagan <yuvalda@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/Kconfig            |   1 +
 drivers/infiniband/core/Makefile      |   2 +-
 drivers/infiniband/core/umem.c        |   2 +-
 drivers/infiniband/core/umem_odp.c    | 379 +++++++++++++++++++++++++++++++++-
 drivers/infiniband/core/umem_rbtree.c |  94 +++++++++
 drivers/infiniband/core/uverbs_cmd.c  |  17 ++
 include/rdma/ib_umem_odp.h            |  65 +++++-
 include/rdma/ib_verbs.h               |  19 ++
 8 files changed, 566 insertions(+), 13 deletions(-)
 create mode 100644 drivers/infiniband/core/umem_rbtree.c

(limited to 'include')

diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 089a2c2af32..b899531498e 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -41,6 +41,7 @@ config INFINIBAND_USER_MEM
 config INFINIBAND_ON_DEMAND_PAGING
 	bool "InfiniBand on-demand paging support"
 	depends on INFINIBAND_USER_MEM
+	select MMU_NOTIFIER
 	default y
 	---help---
 	  On demand paging support for the InfiniBand subsystem.
diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index c58f7913c56..acf73676444 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -11,7 +11,7 @@ obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
 ib_core-y :=			packer.o ud_header.o verbs.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
-ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o
+ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
 
 ib_mad-y :=			mad.o smi.o agent.o mad_rmpp.o
 
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 5baceb79f21..aec7a6aa295 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -72,7 +72,7 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
  * ib_umem_get - Pin and DMA map userspace memory.
  *
  * If access flags indicate ODP memory, avoid pinning. Instead, stores
- * the mm for future page fault handling.
+ * the mm for future page fault handling in conjunction with MMU notifiers.
  *
  * @context: userspace context to pin memory for
  * @addr: userspace virtual address to start at
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index f889e8d793b..6095872549e 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -41,26 +41,235 @@
 #include <rdma/ib_umem.h>
 #include <rdma/ib_umem_odp.h>
 
+static void ib_umem_notifier_start_account(struct ib_umem *item)
+{
+	mutex_lock(&item->odp_data->umem_mutex);
+
+	/* Only update private counters for this umem if it has them.
+	 * Otherwise skip it. All page faults will be delayed for this umem. */
+	if (item->odp_data->mn_counters_active) {
+		int notifiers_count = item->odp_data->notifiers_count++;
+
+		if (notifiers_count == 0)
+			/* Initialize the completion object for waiting on
+			 * notifiers. Since notifier_count is zero, no one
+			 * should be waiting right now. */
+			reinit_completion(&item->odp_data->notifier_completion);
+	}
+	mutex_unlock(&item->odp_data->umem_mutex);
+}
+
+static void ib_umem_notifier_end_account(struct ib_umem *item)
+{
+	mutex_lock(&item->odp_data->umem_mutex);
+
+	/* Only update private counters for this umem if it has them.
+	 * Otherwise skip it. All page faults will be delayed for this umem. */
+	if (item->odp_data->mn_counters_active) {
+		/*
+		 * This sequence increase will notify the QP page fault that
+		 * the page that is going to be mapped in the spte could have
+		 * been freed.
+		 */
+		++item->odp_data->notifiers_seq;
+		if (--item->odp_data->notifiers_count == 0)
+			complete_all(&item->odp_data->notifier_completion);
+	}
+	mutex_unlock(&item->odp_data->umem_mutex);
+}
+
+/* Account for a new mmu notifier in an ib_ucontext. */
+static void ib_ucontext_notifier_start_account(struct ib_ucontext *context)
+{
+	atomic_inc(&context->notifier_count);
+}
+
+/* Account for a terminating mmu notifier in an ib_ucontext.
+ *
+ * Must be called with the ib_ucontext->umem_rwsem semaphore unlocked, since
+ * the function takes the semaphore itself. */
+static void ib_ucontext_notifier_end_account(struct ib_ucontext *context)
+{
+	int zero_notifiers = atomic_dec_and_test(&context->notifier_count);
+
+	if (zero_notifiers &&
+	    !list_empty(&context->no_private_counters)) {
+		/* No currently running mmu notifiers. Now is the chance to
+		 * add private accounting to all previously added umems. */
+		struct ib_umem_odp *odp_data, *next;
+
+		/* Prevent concurrent mmu notifiers from working on the
+		 * no_private_counters list. */
+		down_write(&context->umem_rwsem);
+
+		/* Read the notifier_count again, with the umem_rwsem
+		 * semaphore taken for write. */
+		if (!atomic_read(&context->notifier_count)) {
+			list_for_each_entry_safe(odp_data, next,
+						 &context->no_private_counters,
+						 no_private_counters) {
+				mutex_lock(&odp_data->umem_mutex);
+				odp_data->mn_counters_active = true;
+				list_del(&odp_data->no_private_counters);
+				complete_all(&odp_data->notifier_completion);
+				mutex_unlock(&odp_data->umem_mutex);
+			}
+		}
+
+		up_write(&context->umem_rwsem);
+	}
+}
+
+static int ib_umem_notifier_release_trampoline(struct ib_umem *item, u64 start,
+					       u64 end, void *cookie) {
+	/*
+	 * Increase the number of notifiers running, to
+	 * prevent any further fault handling on this MR.
+	 */
+	ib_umem_notifier_start_account(item);
+	item->odp_data->dying = 1;
+	/* Make sure that the fact the umem is dying is out before we release
+	 * all pending page faults. */
+	smp_wmb();
+	complete_all(&item->odp_data->notifier_completion);
+	item->context->invalidate_range(item, ib_umem_start(item),
+					ib_umem_end(item));
+	return 0;
+}
+
+static void ib_umem_notifier_release(struct mmu_notifier *mn,
+				     struct mm_struct *mm)
+{
+	struct ib_ucontext *context = container_of(mn, struct ib_ucontext, mn);
+
+	if (!context->invalidate_range)
+		return;
+
+	ib_ucontext_notifier_start_account(context);
+	down_read(&context->umem_rwsem);
+	rbt_ib_umem_for_each_in_range(&context->umem_tree, 0,
+				      ULLONG_MAX,
+				      ib_umem_notifier_release_trampoline,
+				      NULL);
+	up_read(&context->umem_rwsem);
+}
+
+static int invalidate_page_trampoline(struct ib_umem *item, u64 start,
+				      u64 end, void *cookie)
+{
+	ib_umem_notifier_start_account(item);
+	item->context->invalidate_range(item, start, start + PAGE_SIZE);
+	ib_umem_notifier_end_account(item);
+	return 0;
+}
+
+static void ib_umem_notifier_invalidate_page(struct mmu_notifier *mn,
+					     struct mm_struct *mm,
+					     unsigned long address)
+{
+	struct ib_ucontext *context = container_of(mn, struct ib_ucontext, mn);
+
+	if (!context->invalidate_range)
+		return;
+
+	ib_ucontext_notifier_start_account(context);
+	down_read(&context->umem_rwsem);
+	rbt_ib_umem_for_each_in_range(&context->umem_tree, address,
+				      address + PAGE_SIZE,
+				      invalidate_page_trampoline, NULL);
+	up_read(&context->umem_rwsem);
+	ib_ucontext_notifier_end_account(context);
+}
+
+static int invalidate_range_start_trampoline(struct ib_umem *item, u64 start,
+					     u64 end, void *cookie)
+{
+	ib_umem_notifier_start_account(item);
+	item->context->invalidate_range(item, start, end);
+	return 0;
+}
+
+static void ib_umem_notifier_invalidate_range_start(struct mmu_notifier *mn,
+						    struct mm_struct *mm,
+						    unsigned long start,
+						    unsigned long end)
+{
+	struct ib_ucontext *context = container_of(mn, struct ib_ucontext, mn);
+
+	if (!context->invalidate_range)
+		return;
+
+	ib_ucontext_notifier_start_account(context);
+	down_read(&context->umem_rwsem);
+	rbt_ib_umem_for_each_in_range(&context->umem_tree, start,
+				      end,
+				      invalidate_range_start_trampoline, NULL);
+	up_read(&context->umem_rwsem);
+}
+
+static int invalidate_range_end_trampoline(struct ib_umem *item, u64 start,
+					   u64 end, void *cookie)
+{
+	ib_umem_notifier_end_account(item);
+	return 0;
+}
+
+static void ib_umem_notifier_invalidate_range_end(struct mmu_notifier *mn,
+						  struct mm_struct *mm,
+						  unsigned long start,
+						  unsigned long end)
+{
+	struct ib_ucontext *context = container_of(mn, struct ib_ucontext, mn);
+
+	if (!context->invalidate_range)
+		return;
+
+	down_read(&context->umem_rwsem);
+	rbt_ib_umem_for_each_in_range(&context->umem_tree, start,
+				      end,
+				      invalidate_range_end_trampoline, NULL);
+	up_read(&context->umem_rwsem);
+	ib_ucontext_notifier_end_account(context);
+}
+
+static struct mmu_notifier_ops ib_umem_notifiers = {
+	.release                    = ib_umem_notifier_release,
+	.invalidate_page            = ib_umem_notifier_invalidate_page,
+	.invalidate_range_start     = ib_umem_notifier_invalidate_range_start,
+	.invalidate_range_end       = ib_umem_notifier_invalidate_range_end,
+};
+
 int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem)
 {
 	int ret_val;
 	struct pid *our_pid;
+	struct mm_struct *mm = get_task_mm(current);
+
+	if (!mm)
+		return -EINVAL;
 
 	/* Prevent creating ODP MRs in child processes */
 	rcu_read_lock();
 	our_pid = get_task_pid(current->group_leader, PIDTYPE_PID);
 	rcu_read_unlock();
 	put_pid(our_pid);
-	if (context->tgid != our_pid)
-		return -EINVAL;
+	if (context->tgid != our_pid) {
+		ret_val = -EINVAL;
+		goto out_mm;
+	}
 
 	umem->hugetlb = 0;
 	umem->odp_data = kzalloc(sizeof(*umem->odp_data), GFP_KERNEL);
-	if (!umem->odp_data)
-		return -ENOMEM;
+	if (!umem->odp_data) {
+		ret_val = -ENOMEM;
+		goto out_mm;
+	}
+	umem->odp_data->umem = umem;
 
 	mutex_init(&umem->odp_data->umem_mutex);
 
+	init_completion(&umem->odp_data->notifier_completion);
+
 	umem->odp_data->page_list = vzalloc(ib_umem_num_pages(umem) *
 					    sizeof(*umem->odp_data->page_list));
 	if (!umem->odp_data->page_list) {
@@ -75,17 +284,72 @@ int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem)
 		goto out_page_list;
 	}
 
+	/*
+	 * When using MMU notifiers, we will get a
+	 * notification before the "current" task (and MM) is
+	 * destroyed. We use the umem_rwsem semaphore to synchronize.
+	 */
+	down_write(&context->umem_rwsem);
+	context->odp_mrs_count++;
+	if (likely(ib_umem_start(umem) != ib_umem_end(umem)))
+		rbt_ib_umem_insert(&umem->odp_data->interval_tree,
+				   &context->umem_tree);
+	if (likely(!atomic_read(&context->notifier_count)))
+		umem->odp_data->mn_counters_active = true;
+	else
+		list_add(&umem->odp_data->no_private_counters,
+			 &context->no_private_counters);
+	downgrade_write(&context->umem_rwsem);
+
+	if (context->odp_mrs_count == 1) {
+		/*
+		 * Note that at this point, no MMU notifier is running
+		 * for this context!
+		 */
+		atomic_set(&context->notifier_count, 0);
+		INIT_HLIST_NODE(&context->mn.hlist);
+		context->mn.ops = &ib_umem_notifiers;
+		/*
+		 * Lock-dep detects a false positive for mmap_sem vs.
+		 * umem_rwsem, due to not grasping downgrade_write correctly.
+		 */
+		lockdep_off();
+		ret_val = mmu_notifier_register(&context->mn, mm);
+		lockdep_on();
+		if (ret_val) {
+			pr_err("Failed to register mmu_notifier %d\n", ret_val);
+			ret_val = -EBUSY;
+			goto out_mutex;
+		}
+	}
+
+	up_read(&context->umem_rwsem);
+
+	/*
+	 * Note that doing an mmput can cause a notifier for the relevant mm.
+	 * If the notifier is called while we hold the umem_rwsem, this will
+	 * cause a deadlock. Therefore, we release the reference only after we
+	 * released the semaphore.
+	 */
+	mmput(mm);
 	return 0;
 
+out_mutex:
+	up_read(&context->umem_rwsem);
+	vfree(umem->odp_data->dma_list);
 out_page_list:
 	vfree(umem->odp_data->page_list);
 out_odp_data:
 	kfree(umem->odp_data);
+out_mm:
+	mmput(mm);
 	return ret_val;
 }
 
 void ib_umem_odp_release(struct ib_umem *umem)
 {
+	struct ib_ucontext *context = umem->context;
+
 	/*
 	 * Ensure that no more pages are mapped in the umem.
 	 *
@@ -95,6 +359,54 @@ void ib_umem_odp_release(struct ib_umem *umem)
 	ib_umem_odp_unmap_dma_pages(umem, ib_umem_start(umem),
 				    ib_umem_end(umem));
 
+	down_write(&context->umem_rwsem);
+	if (likely(ib_umem_start(umem) != ib_umem_end(umem)))
+		rbt_ib_umem_remove(&umem->odp_data->interval_tree,
+				   &context->umem_tree);
+	context->odp_mrs_count--;
+	if (!umem->odp_data->mn_counters_active) {
+		list_del(&umem->odp_data->no_private_counters);
+		complete_all(&umem->odp_data->notifier_completion);
+	}
+
+	/*
+	 * Downgrade the lock to a read lock. This ensures that the notifiers
+	 * (who lock the mutex for reading) will be able to finish, and we
+	 * will be able to enventually obtain the mmu notifiers SRCU. Note
+	 * that since we are doing it atomically, no other user could register
+	 * and unregister while we do the check.
+	 */
+	downgrade_write(&context->umem_rwsem);
+	if (!context->odp_mrs_count) {
+		struct task_struct *owning_process = NULL;
+		struct mm_struct *owning_mm        = NULL;
+
+		owning_process = get_pid_task(context->tgid,
+					      PIDTYPE_PID);
+		if (owning_process == NULL)
+			/*
+			 * The process is already dead, notifier were removed
+			 * already.
+			 */
+			goto out;
+
+		owning_mm = get_task_mm(owning_process);
+		if (owning_mm == NULL)
+			/*
+			 * The process' mm is already dead, notifier were
+			 * removed already.
+			 */
+			goto out_put_task;
+		mmu_notifier_unregister(&context->mn, owning_mm);
+
+		mmput(owning_mm);
+
+out_put_task:
+		put_task_struct(owning_process);
+	}
+out:
+	up_read(&context->umem_rwsem);
+
 	vfree(umem->odp_data->dma_list);
 	vfree(umem->odp_data->page_list);
 	kfree(umem->odp_data);
@@ -112,7 +424,8 @@ void ib_umem_odp_release(struct ib_umem *umem)
  *               the sequence number is taken from
  *               umem->odp_data->notifiers_seq.
  *
- * The function returns -EFAULT if the DMA mapping operation fails.
+ * The function returns -EFAULT if the DMA mapping operation fails. It returns
+ * -EAGAIN if a concurrent invalidation prevents us from updating the page.
  *
  * The page is released via put_page even if the operation failed. For
  * on-demand pinning, the page is released whenever it isn't stored in the
@@ -121,6 +434,7 @@ void ib_umem_odp_release(struct ib_umem *umem)
 static int ib_umem_odp_map_dma_single_page(
 		struct ib_umem *umem,
 		int page_index,
+		u64 base_virt_addr,
 		struct page *page,
 		u64 access_mask,
 		unsigned long current_seq)
@@ -128,9 +442,19 @@ static int ib_umem_odp_map_dma_single_page(
 	struct ib_device *dev = umem->context->device;
 	dma_addr_t dma_addr;
 	int stored_page = 0;
+	int remove_existing_mapping = 0;
 	int ret = 0;
 
 	mutex_lock(&umem->odp_data->umem_mutex);
+	/*
+	 * Note: we avoid writing if seq is different from the initial seq, to
+	 * handle case of a racing notifier. This check also allows us to bail
+	 * early if we have a notifier running in parallel with us.
+	 */
+	if (ib_umem_mmu_notifier_retry(umem, current_seq)) {
+		ret = -EAGAIN;
+		goto out;
+	}
 	if (!(umem->odp_data->dma_list[page_index])) {
 		dma_addr = ib_dma_map_page(dev,
 					   page,
@@ -148,14 +472,27 @@ static int ib_umem_odp_map_dma_single_page(
 	} else {
 		pr_err("error: got different pages in IB device and from get_user_pages. IB device page: %p, gup page: %p\n",
 		       umem->odp_data->page_list[page_index], page);
+		/* Better remove the mapping now, to prevent any further
+		 * damage. */
+		remove_existing_mapping = 1;
 	}
 
 out:
 	mutex_unlock(&umem->odp_data->umem_mutex);
 
-	if (!stored_page)
+	/* On Demand Paging - avoid pinning the page */
+	if (umem->context->invalidate_range || !stored_page)
 		put_page(page);
 
+	if (remove_existing_mapping && umem->context->invalidate_range) {
+		invalidate_page_trampoline(
+			umem,
+			base_virt_addr + (page_index * PAGE_SIZE),
+			base_virt_addr + ((page_index+1)*PAGE_SIZE),
+			NULL);
+		ret = -EAGAIN;
+	}
+
 	return ret;
 }
 
@@ -168,6 +505,8 @@ out:
  *
  * Returns the number of pages mapped in success, negative error code
  * for failure.
+ * An -EAGAIN error code is returned when a concurrent mmu notifier prevents
+ * the function from completing its task.
  *
  * @umem: the umem to map and pin
  * @user_virt: the address from which we need to map.
@@ -189,6 +528,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
 	struct page       **local_page_list = NULL;
 	u64 off;
 	int j, k, ret = 0, start_idx, npages = 0;
+	u64 base_virt_addr;
 
 	if (access_mask == 0)
 		return -EINVAL;
@@ -203,6 +543,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
 
 	off = user_virt & (~PAGE_MASK);
 	user_virt = user_virt & PAGE_MASK;
+	base_virt_addr = user_virt;
 	bcnt += off; /* Charge for the first page offset as well. */
 
 	owning_process = get_pid_task(umem->context->tgid, PIDTYPE_PID);
@@ -246,8 +587,8 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
 		user_virt += npages << PAGE_SHIFT;
 		for (j = 0; j < npages; ++j) {
 			ret = ib_umem_odp_map_dma_single_page(
-				umem, k, local_page_list[j], access_mask,
-				current_seq);
+				umem, k, base_virt_addr, local_page_list[j],
+				access_mask, current_seq);
 			if (ret < 0)
 				break;
 			k++;
@@ -286,6 +627,11 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 virt,
 
 	virt  = max_t(u64, virt,  ib_umem_start(umem));
 	bound = min_t(u64, bound, ib_umem_end(umem));
+	/* Note that during the run of this function, the
+	 * notifiers_count of the MR is > 0, preventing any racing
+	 * faults from completion. We might be racing with other
+	 * invalidations, so we must make sure we free each page only
+	 * once. */
 	for (addr = virt; addr < bound; addr += (u64)umem->page_size) {
 		idx = (addr - ib_umem_start(umem)) / PAGE_SIZE;
 		mutex_lock(&umem->odp_data->umem_mutex);
@@ -300,8 +646,21 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 virt,
 			ib_dma_unmap_page(dev, dma_addr, PAGE_SIZE,
 					  DMA_BIDIRECTIONAL);
 			if (dma & ODP_WRITE_ALLOWED_BIT)
-				set_page_dirty_lock(head_page);
-			put_page(page);
+				/*
+				 * set_page_dirty prefers being called with
+				 * the page lock. However, MMU notifiers are
+				 * called sometimes with and sometimes without
+				 * the lock. We rely on the umem_mutex instead
+				 * to prevent other mmu notifiers from
+				 * continuing and allowing the page mapping to
+				 * be removed.
+				 */
+				set_page_dirty(head_page);
+			/* on demand pinning support */
+			if (!umem->context->invalidate_range)
+				put_page(page);
+			umem->odp_data->page_list[idx] = NULL;
+			umem->odp_data->dma_list[idx] = 0;
 		}
 		mutex_unlock(&umem->odp_data->umem_mutex);
 	}
diff --git a/drivers/infiniband/core/umem_rbtree.c b/drivers/infiniband/core/umem_rbtree.c
new file mode 100644
index 00000000000..727d788448f
--- /dev/null
+++ b/drivers/infiniband/core/umem_rbtree.c
@@ -0,0 +1,94 @@
+/*
+ * Copyright (c) 2014 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/interval_tree_generic.h>
+#include <linux/sched.h>
+#include <linux/gfp.h>
+#include <rdma/ib_umem_odp.h>
+
+/*
+ * The ib_umem list keeps track of memory regions for which the HW
+ * device request to receive notification when the related memory
+ * mapping is changed.
+ *
+ * ib_umem_lock protects the list.
+ */
+
+static inline u64 node_start(struct umem_odp_node *n)
+{
+	struct ib_umem_odp *umem_odp =
+			container_of(n, struct ib_umem_odp, interval_tree);
+
+	return ib_umem_start(umem_odp->umem);
+}
+
+/* Note that the representation of the intervals in the interval tree
+ * considers the ending point as contained in the interval, while the
+ * function ib_umem_end returns the first address which is not contained
+ * in the umem.
+ */
+static inline u64 node_last(struct umem_odp_node *n)
+{
+	struct ib_umem_odp *umem_odp =
+			container_of(n, struct ib_umem_odp, interval_tree);
+
+	return ib_umem_end(umem_odp->umem) - 1;
+}
+
+INTERVAL_TREE_DEFINE(struct umem_odp_node, rb, u64, __subtree_last,
+		     node_start, node_last, , rbt_ib_umem)
+
+/* @last is not a part of the interval. See comment for function
+ * node_last.
+ */
+int rbt_ib_umem_for_each_in_range(struct rb_root *root,
+				  u64 start, u64 last,
+				  umem_call_back cb,
+				  void *cookie)
+{
+	int ret_val = 0;
+	struct umem_odp_node *node;
+	struct ib_umem_odp *umem;
+
+	if (unlikely(start == last))
+		return ret_val;
+
+	for (node = rbt_ib_umem_iter_first(root, start, last - 1); node;
+			node = rbt_ib_umem_iter_next(node, start, last - 1)) {
+		umem = container_of(node, struct ib_umem_odp, interval_tree);
+		ret_val = cb(umem->umem, start, last, cookie) || ret_val;
+	}
+
+	return ret_val;
+}
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 70b697d8fbb..532d8eba8b0 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -289,6 +289,9 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	struct ib_uverbs_get_context_resp resp;
 	struct ib_udata                   udata;
 	struct ib_device                 *ibdev = file->device->ib_dev;
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	struct ib_device_attr		  dev_attr;
+#endif
 	struct ib_ucontext		 *ucontext;
 	struct file			 *filp;
 	int ret;
@@ -331,6 +334,20 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	rcu_read_unlock();
 	ucontext->closing = 0;
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	ucontext->umem_tree = RB_ROOT;
+	init_rwsem(&ucontext->umem_rwsem);
+	ucontext->odp_mrs_count = 0;
+	INIT_LIST_HEAD(&ucontext->no_private_counters);
+
+	ret = ib_query_device(ibdev, &dev_attr);
+	if (ret)
+		goto err_free;
+	if (!(dev_attr.device_cap_flags & IB_DEVICE_ON_DEMAND_PAGING))
+		ucontext->invalidate_range = NULL;
+
+#endif
+
 	resp.num_comp_vectors = file->device->num_comp_vectors;
 
 	ret = get_unused_fd_flags(O_CLOEXEC);
diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
index b5a2df1923b..3da0b167041 100644
--- a/include/rdma/ib_umem_odp.h
+++ b/include/rdma/ib_umem_odp.h
@@ -34,6 +34,13 @@
 #define IB_UMEM_ODP_H
 
 #include <rdma/ib_umem.h>
+#include <rdma/ib_verbs.h>
+#include <linux/interval_tree.h>
+
+struct umem_odp_node {
+	u64 __subtree_last;
+	struct rb_node rb;
+};
 
 struct ib_umem_odp {
 	/*
@@ -51,10 +58,27 @@ struct ib_umem_odp {
 	dma_addr_t		*dma_list;
 	/*
 	 * The umem_mutex protects the page_list and dma_list fields of an ODP
-	 * umem, allowing only a single thread to map/unmap pages.
+	 * umem, allowing only a single thread to map/unmap pages. The mutex
+	 * also protects access to the mmu notifier counters.
 	 */
 	struct mutex		umem_mutex;
 	void			*private; /* for the HW driver to use. */
+
+	/* When false, use the notifier counter in the ucontext struct. */
+	bool mn_counters_active;
+	int notifiers_seq;
+	int notifiers_count;
+
+	/* A linked list of umems that don't have private mmu notifier
+	 * counters yet. */
+	struct list_head no_private_counters;
+	struct ib_umem		*umem;
+
+	/* Tree tracking */
+	struct umem_odp_node	interval_tree;
+
+	struct completion	notifier_completion;
+	int			dying;
 };
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
@@ -82,6 +106,45 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 start_offset, u64 bcnt,
 void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 start_offset,
 				 u64 bound);
 
+void rbt_ib_umem_insert(struct umem_odp_node *node, struct rb_root *root);
+void rbt_ib_umem_remove(struct umem_odp_node *node, struct rb_root *root);
+typedef int (*umem_call_back)(struct ib_umem *item, u64 start, u64 end,
+			      void *cookie);
+/*
+ * Call the callback on each ib_umem in the range. Returns the logical or of
+ * the return values of the functions called.
+ */
+int rbt_ib_umem_for_each_in_range(struct rb_root *root, u64 start, u64 end,
+				  umem_call_back cb, void *cookie);
+
+struct umem_odp_node *rbt_ib_umem_iter_first(struct rb_root *root,
+					     u64 start, u64 last);
+struct umem_odp_node *rbt_ib_umem_iter_next(struct umem_odp_node *node,
+					    u64 start, u64 last);
+
+static inline int ib_umem_mmu_notifier_retry(struct ib_umem *item,
+					     unsigned long mmu_seq)
+{
+	/*
+	 * This code is strongly based on the KVM code from
+	 * mmu_notifier_retry. Should be called with
+	 * the relevant locks taken (item->odp_data->umem_mutex
+	 * and the ucontext umem_mutex semaphore locked for read).
+	 */
+
+	/* Do not allow page faults while the new ib_umem hasn't seen a state
+	 * with zero notifiers yet, and doesn't have its own valid set of
+	 * private counters. */
+	if (!item->odp_data->mn_counters_active)
+		return 1;
+
+	if (unlikely(item->odp_data->notifiers_count))
+		return 1;
+	if (item->odp_data->notifiers_seq != mmu_seq)
+		return 1;
+	return 0;
+}
+
 #else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 static inline int ib_umem_odp_get(struct ib_ucontext *context,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 3af5dcad1b6..0d74f1de99a 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -51,6 +51,7 @@
 #include <uapi/linux/if_ether.h>
 
 #include <linux/atomic.h>
+#include <linux/mmu_notifier.h>
 #include <asm/uaccess.h>
 
 extern struct workqueue_struct *ib_wq;
@@ -1139,6 +1140,8 @@ struct ib_fmr_attr {
 	u8	page_shift;
 };
 
+struct ib_umem;
+
 struct ib_ucontext {
 	struct ib_device       *device;
 	struct list_head	pd_list;
@@ -1153,6 +1156,22 @@ struct ib_ucontext {
 	int			closing;
 
 	struct pid             *tgid;
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	struct rb_root      umem_tree;
+	/*
+	 * Protects .umem_rbroot and tree, as well as odp_mrs_count and
+	 * mmu notifiers registration.
+	 */
+	struct rw_semaphore	umem_rwsem;
+	void (*invalidate_range)(struct ib_umem *umem,
+				 unsigned long start, unsigned long end);
+
+	struct mmu_notifier	mn;
+	atomic_t		notifier_count;
+	/* A list of umems that don't have private mmu notifier counters yet. */
+	struct list_head	no_private_counters;
+	int                     odp_mrs_count;
+#endif
 };
 
 struct ib_uobject {
-- 
cgit v1.2.3-70-g09d2


From 6cb7ff3dcfe6aad6a36a0fd0e928b5bea4fabdd5 Mon Sep 17 00:00:00 2001
From: Roland Dreier <roland@purestorage.com>
Date: Mon, 15 Dec 2014 18:17:17 -0800
Subject: mlx5_core: Re-add MLX5_DEV_CAP_FLAG_ON_DMND_PG flag

In commit 0c7aac854f52 ("net/mlx5_core: Remove unused dev cap enum
fields"), the flag MLX5_DEV_CAP_FLAG_ON_DMND_PG was removed.
Unfortunately the on-demand paging changes actually use it, so re-add
the missing flag.

Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 include/linux/mlx5/device.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index fa07bfda0e1..096abe543d2 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -234,6 +234,7 @@ enum {
 	MLX5_DEV_CAP_FLAG_APM		= 1LL << 17,
 	MLX5_DEV_CAP_FLAG_ATOMIC	= 1LL << 18,
 	MLX5_DEV_CAP_FLAG_BLOCK_MCAST	= 1LL << 23,
+	MLX5_DEV_CAP_FLAG_ON_DMND_PG	= 1LL << 24,
 	MLX5_DEV_CAP_FLAG_CQ_MODER	= 1LL << 29,
 	MLX5_DEV_CAP_FLAG_RESIZE_CQ	= 1LL << 30,
 	MLX5_DEV_CAP_FLAG_DCT		= 1LL << 37,
-- 
cgit v1.2.3-70-g09d2


From e420f0c0f3d1022789fcb59b2a0c4b979ce311ba Mon Sep 17 00:00:00 2001
From: Haggai Eran <haggaie@mellanox.com>
Date: Thu, 11 Dec 2014 17:04:19 +0200
Subject: mlx5_core: Add support for page faults events and low level handling

* Add a handler function pointer in the mlx5_core_qp struct for page
  fault events. Handle page fault events by calling the handler
  function, if not NULL.
* Add on-demand paging capability query command.
* Export command for resuming QPs after page faults.
* Add various constants related to paging support.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c |  13 ++-
 drivers/net/ethernet/mellanox/mlx5/core/fw.c |  40 +++++++++
 drivers/net/ethernet/mellanox/mlx5/core/qp.c | 119 +++++++++++++++++++++++++++
 include/linux/mlx5/device.h                  |  54 +++++++++++-
 include/linux/mlx5/driver.h                  |  12 +++
 include/linux/mlx5/qp.h                      |  55 +++++++++++++
 6 files changed, 291 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index ab684463780..da82991239a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -157,6 +157,8 @@ static const char *eqe_type_str(u8 type)
 		return "MLX5_EVENT_TYPE_CMD";
 	case MLX5_EVENT_TYPE_PAGE_REQUEST:
 		return "MLX5_EVENT_TYPE_PAGE_REQUEST";
+	case MLX5_EVENT_TYPE_PAGE_FAULT:
+		return "MLX5_EVENT_TYPE_PAGE_FAULT";
 	default:
 		return "Unrecognized event";
 	}
@@ -279,6 +281,11 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 			}
 			break;
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+		case MLX5_EVENT_TYPE_PAGE_FAULT:
+			mlx5_eq_pagefault(dev, eqe);
+			break;
+#endif
 
 		default:
 			mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n",
@@ -446,8 +453,12 @@ void mlx5_eq_cleanup(struct mlx5_core_dev *dev)
 int mlx5_start_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	u32 async_event_mask = MLX5_ASYNC_EVENT_MASK;
 	int err;
 
+	if (dev->caps.gen.flags & MLX5_DEV_CAP_FLAG_ON_DMND_PG)
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_PAGE_FAULT);
+
 	err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
 				 MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD,
 				 "mlx5_cmd_eq", &dev->priv.uuari.uars[0]);
@@ -459,7 +470,7 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 	mlx5_cmd_use_events(dev);
 
 	err = mlx5_create_map_eq(dev, &table->async_eq, MLX5_EQ_VEC_ASYNC,
-				 MLX5_NUM_ASYNC_EQE, MLX5_ASYNC_EVENT_MASK,
+				 MLX5_NUM_ASYNC_EQE, async_event_mask,
 				 "mlx5_async_eq", &dev->priv.uuari.uars[0]);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create async EQ %d\n", err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 087c4c797de..06f9036acd8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -69,6 +69,46 @@ int mlx5_cmd_query_hca_cap(struct mlx5_core_dev *dev, struct mlx5_caps *caps)
 	return mlx5_core_get_caps(dev, caps, HCA_CAP_OPMOD_GET_CUR);
 }
 
+int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *caps)
+{
+	u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)];
+	int out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	void *out;
+	int err;
+
+	if (!(dev->caps.gen.flags & MLX5_DEV_CAP_FLAG_ON_DMND_PG))
+		return -ENOTSUPP;
+
+	memset(in, 0, sizeof(in));
+	out = kzalloc(out_sz, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+	MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
+	MLX5_SET(query_hca_cap_in, in, op_mod, HCA_CAP_OPMOD_GET_ODP_CUR);
+	err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz);
+	if (err)
+		goto out;
+
+	err = mlx5_cmd_status_to_err_v2(out);
+	if (err) {
+		mlx5_core_warn(dev, "query cur hca ODP caps failed, %d\n", err);
+		goto out;
+	}
+
+	memcpy(caps, MLX5_ADDR_OF(query_hca_cap_out, out, capability_struct),
+	       sizeof(*caps));
+
+	mlx5_core_dbg(dev, "on-demand paging capabilities:\nrc: %08x\nuc: %08x\nud: %08x\n",
+		be32_to_cpu(caps->per_transport_caps.rc_odp_caps),
+		be32_to_cpu(caps->per_transport_caps.uc_odp_caps),
+		be32_to_cpu(caps->per_transport_caps.ud_odp_caps));
+
+out:
+	kfree(out);
+	return err;
+}
+EXPORT_SYMBOL(mlx5_query_odp_caps);
+
 int mlx5_cmd_init_hca(struct mlx5_core_dev *dev)
 {
 	struct mlx5_cmd_init_hca_mbox_in in;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index 5261a2b0da4..575d853dbe0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -88,6 +88,95 @@ void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
 	mlx5_core_put_rsc(common);
 }
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+void mlx5_eq_pagefault(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
+{
+	struct mlx5_eqe_page_fault *pf_eqe = &eqe->data.page_fault;
+	int qpn = be32_to_cpu(pf_eqe->flags_qpn) & MLX5_QPN_MASK;
+	struct mlx5_core_rsc_common *common = mlx5_get_rsc(dev, qpn);
+	struct mlx5_core_qp *qp =
+		container_of(common, struct mlx5_core_qp, common);
+	struct mlx5_pagefault pfault;
+
+	if (!qp) {
+		mlx5_core_warn(dev, "ODP event for non-existent QP %06x\n",
+			       qpn);
+		return;
+	}
+
+	pfault.event_subtype = eqe->sub_type;
+	pfault.flags = (be32_to_cpu(pf_eqe->flags_qpn) >> MLX5_QPN_BITS) &
+		(MLX5_PFAULT_REQUESTOR | MLX5_PFAULT_WRITE | MLX5_PFAULT_RDMA);
+	pfault.bytes_committed = be32_to_cpu(
+		pf_eqe->bytes_committed);
+
+	mlx5_core_dbg(dev,
+		      "PAGE_FAULT: subtype: 0x%02x, flags: 0x%02x,\n",
+		      eqe->sub_type, pfault.flags);
+
+	switch (eqe->sub_type) {
+	case MLX5_PFAULT_SUBTYPE_RDMA:
+		/* RDMA based event */
+		pfault.rdma.r_key =
+			be32_to_cpu(pf_eqe->rdma.r_key);
+		pfault.rdma.packet_size =
+			be16_to_cpu(pf_eqe->rdma.packet_length);
+		pfault.rdma.rdma_op_len =
+			be32_to_cpu(pf_eqe->rdma.rdma_op_len);
+		pfault.rdma.rdma_va =
+			be64_to_cpu(pf_eqe->rdma.rdma_va);
+		mlx5_core_dbg(dev,
+			      "PAGE_FAULT: qpn: 0x%06x, r_key: 0x%08x,\n",
+			      qpn, pfault.rdma.r_key);
+		mlx5_core_dbg(dev,
+			      "PAGE_FAULT: rdma_op_len: 0x%08x,\n",
+			      pfault.rdma.rdma_op_len);
+		mlx5_core_dbg(dev,
+			      "PAGE_FAULT: rdma_va: 0x%016llx,\n",
+			      pfault.rdma.rdma_va);
+		mlx5_core_dbg(dev,
+			      "PAGE_FAULT: bytes_committed: 0x%06x\n",
+			      pfault.bytes_committed);
+		break;
+
+	case MLX5_PFAULT_SUBTYPE_WQE:
+		/* WQE based event */
+		pfault.wqe.wqe_index =
+			be16_to_cpu(pf_eqe->wqe.wqe_index);
+		pfault.wqe.packet_size =
+			be16_to_cpu(pf_eqe->wqe.packet_length);
+		mlx5_core_dbg(dev,
+			      "PAGE_FAULT: qpn: 0x%06x, wqe_index: 0x%04x,\n",
+			      qpn, pfault.wqe.wqe_index);
+		mlx5_core_dbg(dev,
+			      "PAGE_FAULT: bytes_committed: 0x%06x\n",
+			      pfault.bytes_committed);
+		break;
+
+	default:
+		mlx5_core_warn(dev,
+			       "Unsupported page fault event sub-type: 0x%02hhx, QP %06x\n",
+			       eqe->sub_type, qpn);
+		/* Unsupported page faults should still be resolved by the
+		 * page fault handler
+		 */
+	}
+
+	if (qp->pfault_handler) {
+		qp->pfault_handler(qp, &pfault);
+	} else {
+		mlx5_core_err(dev,
+			      "ODP event for QP %08x, without a fault handler in QP\n",
+			      qpn);
+		/* Page fault will remain unresolved. QP will hang until it is
+		 * destroyed
+		 */
+	}
+
+	mlx5_core_put_rsc(common);
+}
+#endif
+
 int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 			struct mlx5_core_qp *qp,
 			struct mlx5_create_qp_mbox_in *in,
@@ -322,3 +411,33 @@ int mlx5_core_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn)
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_core_xrcd_dealloc);
+
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 qpn,
+				u8 flags, int error)
+{
+	struct mlx5_page_fault_resume_mbox_in in;
+	struct mlx5_page_fault_resume_mbox_out out;
+	int err;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_PAGE_FAULT_RESUME);
+	in.hdr.opmod = 0;
+	flags &= (MLX5_PAGE_FAULT_RESUME_REQUESTOR |
+		  MLX5_PAGE_FAULT_RESUME_WRITE	   |
+		  MLX5_PAGE_FAULT_RESUME_RDMA);
+	flags |= (error ? MLX5_PAGE_FAULT_RESUME_ERROR : 0);
+	in.flags_qpn = cpu_to_be32((qpn & MLX5_QPN_MASK) |
+				   (flags << MLX5_QPN_BITS));
+	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+	if (err)
+		return err;
+
+	if (out.hdr.status)
+		err = mlx5_cmd_status_to_err(&out.hdr);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_core_page_fault_resume);
+#endif
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 096abe543d2..70c28239e33 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -119,6 +119,15 @@ enum {
 	MLX5_MAX_LOG_PKEY_TABLE  = 5,
 };
 
+enum {
+	MLX5_MKEY_INBOX_PG_ACCESS = 1 << 31
+};
+
+enum {
+	MLX5_PFAULT_SUBTYPE_WQE = 0,
+	MLX5_PFAULT_SUBTYPE_RDMA = 1,
+};
+
 enum {
 	MLX5_PERM_LOCAL_READ	= 1 << 2,
 	MLX5_PERM_LOCAL_WRITE	= 1 << 3,
@@ -215,6 +224,8 @@ enum mlx5_event {
 
 	MLX5_EVENT_TYPE_CMD		   = 0x0a,
 	MLX5_EVENT_TYPE_PAGE_REQUEST	   = 0xb,
+
+	MLX5_EVENT_TYPE_PAGE_FAULT	   = 0xc,
 };
 
 enum {
@@ -300,6 +311,8 @@ enum {
 enum {
 	HCA_CAP_OPMOD_GET_MAX	= 0,
 	HCA_CAP_OPMOD_GET_CUR	= 1,
+	HCA_CAP_OPMOD_GET_ODP_MAX = 4,
+	HCA_CAP_OPMOD_GET_ODP_CUR = 5
 };
 
 struct mlx5_inbox_hdr {
@@ -329,6 +342,23 @@ struct mlx5_cmd_query_adapter_mbox_out {
 	u8			vsd_psid[16];
 };
 
+enum mlx5_odp_transport_cap_bits {
+	MLX5_ODP_SUPPORT_SEND	 = 1 << 31,
+	MLX5_ODP_SUPPORT_RECV	 = 1 << 30,
+	MLX5_ODP_SUPPORT_WRITE	 = 1 << 29,
+	MLX5_ODP_SUPPORT_READ	 = 1 << 28,
+};
+
+struct mlx5_odp_caps {
+	char reserved[0x10];
+	struct {
+		__be32			rc_odp_caps;
+		__be32			uc_odp_caps;
+		__be32			ud_odp_caps;
+	} per_transport_caps;
+	char reserved2[0xe4];
+};
+
 struct mlx5_cmd_init_hca_mbox_in {
 	struct mlx5_inbox_hdr	hdr;
 	u8			rsvd0[2];
@@ -449,6 +479,27 @@ struct mlx5_eqe_page_req {
 	__be32		rsvd1[5];
 };
 
+struct mlx5_eqe_page_fault {
+	__be32 bytes_committed;
+	union {
+		struct {
+			u16     reserved1;
+			__be16  wqe_index;
+			u16	reserved2;
+			__be16  packet_length;
+			u8	reserved3[12];
+		} __packed wqe;
+		struct {
+			__be32  r_key;
+			u16	reserved1;
+			__be16  packet_length;
+			__be32  rdma_op_len;
+			__be64  rdma_va;
+		} __packed rdma;
+	} __packed;
+	__be32 flags_qpn;
+} __packed;
+
 union ev_data {
 	__be32				raw[7];
 	struct mlx5_eqe_cmd		cmd;
@@ -460,6 +511,7 @@ union ev_data {
 	struct mlx5_eqe_congestion	cong;
 	struct mlx5_eqe_stall_vl	stall_vl;
 	struct mlx5_eqe_page_req	req_pages;
+	struct mlx5_eqe_page_fault	page_fault;
 } __packed;
 
 struct mlx5_eqe {
@@ -826,7 +878,7 @@ struct mlx5_query_special_ctxs_mbox_out {
 struct mlx5_create_mkey_mbox_in {
 	struct mlx5_inbox_hdr	hdr;
 	__be32			input_mkey_index;
-	u8			rsvd0[4];
+	__be32			flags;
 	struct mlx5_mkey_seg	seg;
 	u8			rsvd1[16];
 	__be32			xlat_oct_act_size;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index b1bf41556b3..7088dcd1921 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -113,6 +113,13 @@ enum {
 	MLX5_REG_HOST_ENDIANNESS = 0x7004,
 };
 
+enum mlx5_page_fault_resume_flags {
+	MLX5_PAGE_FAULT_RESUME_REQUESTOR = 1 << 0,
+	MLX5_PAGE_FAULT_RESUME_WRITE	 = 1 << 1,
+	MLX5_PAGE_FAULT_RESUME_RDMA	 = 1 << 2,
+	MLX5_PAGE_FAULT_RESUME_ERROR	 = 1 << 7,
+};
+
 enum dbg_rsc_type {
 	MLX5_DBG_RSC_QP,
 	MLX5_DBG_RSC_EQ,
@@ -703,6 +710,9 @@ void mlx5_eq_cleanup(struct mlx5_core_dev *dev);
 void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas);
 void mlx5_cq_completion(struct mlx5_core_dev *dev, u32 cqn);
 void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type);
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+void mlx5_eq_pagefault(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
+#endif
 void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type);
 struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn);
 void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector);
@@ -740,6 +750,8 @@ int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn,
 			 int npsvs, u32 *sig_index);
 int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num);
 void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common);
+int mlx5_query_odp_caps(struct mlx5_core_dev *dev,
+			struct mlx5_odp_caps *odp_caps);
 
 static inline u32 mlx5_mkey_to_idx(u32 mkey)
 {
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 67f4b9660b0..6b1d6f60c7e 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -50,6 +50,9 @@
 #define MLX5_BSF_APPTAG_ESCAPE	0x1
 #define MLX5_BSF_APPREF_ESCAPE	0x2
 
+#define MLX5_QPN_BITS		24
+#define MLX5_QPN_MASK		((1 << MLX5_QPN_BITS) - 1)
+
 enum mlx5_qp_optpar {
 	MLX5_QP_OPTPAR_ALT_ADDR_PATH		= 1 << 0,
 	MLX5_QP_OPTPAR_RRE			= 1 << 1,
@@ -363,9 +366,46 @@ struct mlx5_stride_block_ctrl_seg {
 	__be16		num_entries;
 };
 
+enum mlx5_pagefault_flags {
+	MLX5_PFAULT_REQUESTOR = 1 << 0,
+	MLX5_PFAULT_WRITE     = 1 << 1,
+	MLX5_PFAULT_RDMA      = 1 << 2,
+};
+
+/* Contains the details of a pagefault. */
+struct mlx5_pagefault {
+	u32			bytes_committed;
+	u8			event_subtype;
+	enum mlx5_pagefault_flags flags;
+	union {
+		/* Initiator or send message responder pagefault details. */
+		struct {
+			/* Received packet size, only valid for responders. */
+			u32	packet_size;
+			/*
+			 * WQE index. Refers to either the send queue or
+			 * receive queue, according to event_subtype.
+			 */
+			u16	wqe_index;
+		} wqe;
+		/* RDMA responder pagefault details */
+		struct {
+			u32	r_key;
+			/*
+			 * Received packet size, minimal size page fault
+			 * resolution required for forward progress.
+			 */
+			u32	packet_size;
+			u32	rdma_op_len;
+			u64	rdma_va;
+		} rdma;
+	};
+};
+
 struct mlx5_core_qp {
 	struct mlx5_core_rsc_common	common; /* must be first */
 	void (*event)		(struct mlx5_core_qp *, int);
+	void (*pfault_handler)(struct mlx5_core_qp *, struct mlx5_pagefault *);
 	int			qpn;
 	struct mlx5_rsc_debug	*dbg;
 	int			pid;
@@ -533,6 +573,17 @@ static inline struct mlx5_core_mr *__mlx5_mr_lookup(struct mlx5_core_dev *dev, u
 	return radix_tree_lookup(&dev->priv.mr_table.tree, key);
 }
 
+struct mlx5_page_fault_resume_mbox_in {
+	struct mlx5_inbox_hdr	hdr;
+	__be32			flags_qpn;
+	u8			reserved[4];
+};
+
+struct mlx5_page_fault_resume_mbox_out {
+	struct mlx5_outbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
 int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 			struct mlx5_core_qp *qp,
 			struct mlx5_create_qp_mbox_in *in,
@@ -552,6 +603,10 @@ void mlx5_init_qp_table(struct mlx5_core_dev *dev);
 void mlx5_cleanup_qp_table(struct mlx5_core_dev *dev);
 int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp);
 void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp);
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 qpn,
+				u8 context, int error);
+#endif
 
 static inline const char *mlx5_qp_type_str(int type)
 {
-- 
cgit v1.2.3-70-g09d2


From cc149f751b75211df8c41fcd60bd0006e6143ed6 Mon Sep 17 00:00:00 2001
From: Haggai Eran <haggaie@mellanox.com>
Date: Thu, 11 Dec 2014 17:04:21 +0200
Subject: IB/mlx5: Changes in memory region creation to support on-demand
 paging

This patch wraps together several changes needed for on-demand paging support
in the mlx5_ib_populate_pas function, and when registering memory regions.

* Instead of accepting a UMR bit telling the function to enable all
  access flags, the function now accepts the access flags themselves.
* For on-demand paging memory regions, fill the memory tables from the
  correct list, and enable/disable the access flags per-page according
  to whether the page is present.
* A new bit is set to enable writing of access flags when using the
  firmware create_mkey command.
* Disable contig pages when on-demand paging is enabled.

In addition the patch changes the UMR code to use PTR_ALIGN instead of
our own macro.

Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/mem.c     | 58 ++++++++++++++++++++++++++++++++++--
 drivers/infiniband/hw/mlx5/mlx5_ib.h | 12 +++++++-
 drivers/infiniband/hw/mlx5/mr.c      | 33 +++++++++++---------
 include/linux/mlx5/device.h          |  3 ++
 4 files changed, 88 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index dae07eae950..5f7b3014718 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -32,6 +32,7 @@
 
 #include <linux/module.h>
 #include <rdma/ib_umem.h>
+#include <rdma/ib_umem_odp.h>
 #include "mlx5_ib.h"
 
 /* @umem: umem object to scan
@@ -57,6 +58,17 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 	int entry;
 	unsigned long page_shift = ilog2(umem->page_size);
 
+	/* With ODP we must always match OS page size. */
+	if (umem->odp_data) {
+		*count = ib_umem_page_count(umem);
+		*shift = PAGE_SHIFT;
+		*ncont = *count;
+		if (order)
+			*order = ilog2(roundup_pow_of_two(*count));
+
+		return;
+	}
+
 	addr = addr >> page_shift;
 	tmp = (unsigned long)addr;
 	m = find_first_bit(&tmp, sizeof(tmp));
@@ -108,8 +120,32 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 	*count = i;
 }
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+static u64 umem_dma_to_mtt(dma_addr_t umem_dma)
+{
+	u64 mtt_entry = umem_dma & ODP_DMA_ADDR_MASK;
+
+	if (umem_dma & ODP_READ_ALLOWED_BIT)
+		mtt_entry |= MLX5_IB_MTT_READ;
+	if (umem_dma & ODP_WRITE_ALLOWED_BIT)
+		mtt_entry |= MLX5_IB_MTT_WRITE;
+
+	return mtt_entry;
+}
+#endif
+
+/*
+ * Populate the given array with bus addresses from the umem.
+ *
+ * dev - mlx5_ib device
+ * umem - umem to use to fill the pages
+ * page_shift - determines the page size used in the resulting array
+ * pas - bus addresses array to fill
+ * access_flags - access flags to set on all present pages.
+		  use enum mlx5_ib_mtt_access_flags for this.
+ */
 void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
-			  int page_shift, __be64 *pas, int umr)
+			  int page_shift, __be64 *pas, int access_flags)
 {
 	unsigned long umem_page_shift = ilog2(umem->page_size);
 	int shift = page_shift - umem_page_shift;
@@ -120,6 +156,23 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 	int len;
 	struct scatterlist *sg;
 	int entry;
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	const bool odp = umem->odp_data != NULL;
+
+	if (odp) {
+		int num_pages = ib_umem_num_pages(umem);
+
+		WARN_ON(shift != 0);
+		WARN_ON(access_flags != (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE));
+
+		for (i = 0; i < num_pages; ++i) {
+			dma_addr_t pa = umem->odp_data->dma_list[i];
+
+			pas[i] = cpu_to_be64(umem_dma_to_mtt(pa));
+		}
+		return;
+	}
+#endif
 
 	i = 0;
 	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
@@ -128,8 +181,7 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 		for (k = 0; k < len; k++) {
 			if (!(i & mask)) {
 				cur = base + (k << umem_page_shift);
-				if (umr)
-					cur |= 3;
+				cur |= access_flags;
 
 				pas[i >> shift] = cpu_to_be64(cur);
 				mlx5_ib_dbg(dev, "pas[%d] 0x%llx\n",
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index cc50fce8cca..83c1690e9dd 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -268,6 +268,13 @@ struct mlx5_ib_xrcd {
 	u32			xrcdn;
 };
 
+enum mlx5_ib_mtt_access_flags {
+	MLX5_IB_MTT_READ  = (1 << 0),
+	MLX5_IB_MTT_WRITE = (1 << 1),
+};
+
+#define MLX5_IB_MTT_PRESENT (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE)
+
 struct mlx5_ib_mr {
 	struct ib_mr		ibmr;
 	struct mlx5_core_mr	mmr;
@@ -552,7 +559,7 @@ void mlx5_ib_cleanup_fmr(struct mlx5_ib_dev *dev);
 void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 			int *ncont, int *order);
 void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
-			  int page_shift, __be64 *pas, int umr);
+			  int page_shift, __be64 *pas, int access_flags);
 void mlx5_ib_copy_pas(u64 *old, u64 *new, int step, int num);
 int mlx5_ib_get_cqe_size(struct mlx5_ib_dev *dev, struct ib_cq *ibcq);
 int mlx5_mr_cache_init(struct mlx5_ib_dev *dev);
@@ -588,4 +595,7 @@ static inline u8 convert_access(int acc)
 	       MLX5_PERM_LOCAL_READ;
 }
 
+#define MLX5_MAX_UMR_SHIFT 16
+#define MLX5_MAX_UMR_PAGES (1 << MLX5_MAX_UMR_SHIFT)
+
 #endif /* MLX5_IB_H */
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 2de4f4448f8..49fc3ca735a 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -48,13 +48,6 @@ enum {
 	MLX5_UMR_ALIGN	= 2048
 };
 
-static __be64 *mr_align(__be64 *ptr, int align)
-{
-	unsigned long mask = align - 1;
-
-	return (__be64 *)(((unsigned long)ptr + mask) & ~mask);
-}
-
 static int order2idx(struct mlx5_ib_dev *dev, int order)
 {
 	struct mlx5_mr_cache *cache = &dev->cache;
@@ -669,7 +662,7 @@ static int get_octo_len(u64 addr, u64 len, int page_size)
 
 static int use_umr(int order)
 {
-	return order <= 17;
+	return order <= MLX5_MAX_UMR_SHIFT;
 }
 
 static void prep_umr_reg_wqe(struct ib_pd *pd, struct ib_send_wr *wr,
@@ -747,8 +740,9 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
 	struct ib_send_wr wr, *bad;
 	struct mlx5_ib_mr *mr;
 	struct ib_sge sg;
-	int size = sizeof(u64) * npages;
+	int size;
 	__be64 *mr_pas;
+	__be64 *pas;
 	dma_addr_t dma;
 	int err = 0;
 	int i;
@@ -768,17 +762,22 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
 	if (!mr)
 		return ERR_PTR(-EAGAIN);
 
+	/* UMR copies MTTs in units of MLX5_UMR_MTT_ALIGNMENT bytes.
+	 * To avoid copying garbage after the pas array, we allocate
+	 * a little more. */
+	size = ALIGN(sizeof(u64) * npages, MLX5_UMR_MTT_ALIGNMENT);
 	mr_pas = kmalloc(size + MLX5_UMR_ALIGN - 1, GFP_KERNEL);
 	if (!mr_pas) {
 		err = -ENOMEM;
 		goto free_mr;
 	}
 
-	mlx5_ib_populate_pas(dev, umem, page_shift,
-			     mr_align(mr_pas, MLX5_UMR_ALIGN), 1);
+	pas = PTR_ALIGN(mr_pas, MLX5_UMR_ALIGN);
+	mlx5_ib_populate_pas(dev, umem, page_shift, pas, MLX5_IB_MTT_PRESENT);
+	/* Clear padding after the actual pages. */
+	memset(pas + npages, 0, size - npages * sizeof(u64));
 
-	dma = dma_map_single(ddev, mr_align(mr_pas, MLX5_UMR_ALIGN), size,
-			     DMA_TO_DEVICE);
+	dma = dma_map_single(ddev, pas, size, DMA_TO_DEVICE);
 	if (dma_mapping_error(ddev, dma)) {
 		err = -ENOMEM;
 		goto free_pas;
@@ -833,6 +832,8 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, u64 virt_addr,
 	struct mlx5_ib_mr *mr;
 	int inlen;
 	int err;
+	bool pg_cap = !!(dev->mdev->caps.gen.flags &
+			 MLX5_DEV_CAP_FLAG_ON_DMND_PG);
 
 	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
 	if (!mr)
@@ -844,8 +845,12 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, u64 virt_addr,
 		err = -ENOMEM;
 		goto err_1;
 	}
-	mlx5_ib_populate_pas(dev, umem, page_shift, in->pas, 0);
+	mlx5_ib_populate_pas(dev, umem, page_shift, in->pas,
+			     pg_cap ? MLX5_IB_MTT_PRESENT : 0);
 
+	/* The MLX5_MKEY_INBOX_PG_ACCESS bit allows setting the access flags
+	 * in the page list submitted with the command. */
+	in->flags = pg_cap ? cpu_to_be32(MLX5_MKEY_INBOX_PG_ACCESS) : 0;
 	in->seg.flags = convert_access(access_flags) |
 		MLX5_ACCESS_MODE_MTT;
 	in->seg.flags_pd = cpu_to_be32(to_mpd(pd)->pdn);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 70c28239e33..64512a7354c 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -198,6 +198,9 @@ enum {
 	MLX5_UMR_INLINE			= (1 << 7),
 };
 
+#define MLX5_UMR_MTT_ALIGNMENT 0x40
+#define MLX5_UMR_MTT_MASK      (MLX5_UMR_MTT_ALIGNMENT - 1)
+
 enum mlx5_event {
 	MLX5_EVENT_TYPE_COMP		   = 0x0,
 
-- 
cgit v1.2.3-70-g09d2


From 832a6b06ab5e13c228fc27e333ad360aa03ace6f Mon Sep 17 00:00:00 2001
From: Haggai Eran <haggaie@mellanox.com>
Date: Thu, 11 Dec 2014 17:04:22 +0200
Subject: IB/mlx5: Add mlx5_ib_update_mtt to update page tables after creation

The new function allows updating the page tables of a memory region
after it was created. This can be used to handle page faults and page
invalidations.

Since mlx5_ib_update_mtt will need to work from within page invalidation,
so it must not block on memory allocation. It employs an atomic memory
allocation mechanism that is used as a fallback when kmalloc(GFP_ATOMIC) fails.

In order to reuse code from mlx5_ib_populate_pas, the patch splits
this function and add the needed parameters.

Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/mem.c     |  19 +++--
 drivers/infiniband/hw/mlx5/mlx5_ib.h |   5 ++
 drivers/infiniband/hw/mlx5/mr.c      | 132 ++++++++++++++++++++++++++++++++++-
 include/linux/mlx5/device.h          |   1 +
 4 files changed, 149 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index 5f7b3014718..b56e4c5593e 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -140,12 +140,16 @@ static u64 umem_dma_to_mtt(dma_addr_t umem_dma)
  * dev - mlx5_ib device
  * umem - umem to use to fill the pages
  * page_shift - determines the page size used in the resulting array
+ * offset - offset into the umem to start from,
+ *          only implemented for ODP umems
+ * num_pages - total number of pages to fill
  * pas - bus addresses array to fill
  * access_flags - access flags to set on all present pages.
 		  use enum mlx5_ib_mtt_access_flags for this.
  */
-void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
-			  int page_shift, __be64 *pas, int access_flags)
+void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
+			    int page_shift, size_t offset, size_t num_pages,
+			    __be64 *pas, int access_flags)
 {
 	unsigned long umem_page_shift = ilog2(umem->page_size);
 	int shift = page_shift - umem_page_shift;
@@ -160,13 +164,11 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 	const bool odp = umem->odp_data != NULL;
 
 	if (odp) {
-		int num_pages = ib_umem_num_pages(umem);
-
 		WARN_ON(shift != 0);
 		WARN_ON(access_flags != (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE));
 
 		for (i = 0; i < num_pages; ++i) {
-			dma_addr_t pa = umem->odp_data->dma_list[i];
+			dma_addr_t pa = umem->odp_data->dma_list[offset + i];
 
 			pas[i] = cpu_to_be64(umem_dma_to_mtt(pa));
 		}
@@ -194,6 +196,13 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 	}
 }
 
+void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
+			  int page_shift, __be64 *pas, int access_flags)
+{
+	return __mlx5_ib_populate_pas(dev, umem, page_shift, 0,
+				      ib_umem_num_pages(umem), pas,
+				      access_flags);
+}
 int mlx5_ib_get_buf_offset(u64 addr, int page_shift, u32 *offset)
 {
 	u64 page_size;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 83c1690e9dd..6856e27bfb6 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -527,6 +527,8 @@ struct ib_mr *mlx5_ib_get_dma_mr(struct ib_pd *pd, int acc);
 struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				  u64 virt_addr, int access_flags,
 				  struct ib_udata *udata);
+int mlx5_ib_update_mtt(struct mlx5_ib_mr *mr, u64 start_page_index,
+		       int npages, int zap);
 int mlx5_ib_dereg_mr(struct ib_mr *ibmr);
 int mlx5_ib_destroy_mr(struct ib_mr *ibmr);
 struct ib_mr *mlx5_ib_create_mr(struct ib_pd *pd,
@@ -558,6 +560,9 @@ int mlx5_ib_init_fmr(struct mlx5_ib_dev *dev);
 void mlx5_ib_cleanup_fmr(struct mlx5_ib_dev *dev);
 void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 			int *ncont, int *order);
+void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
+			    int page_shift, size_t offset, size_t num_pages,
+			    __be64 *pas, int access_flags);
 void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 			  int page_shift, __be64 *pas, int access_flags);
 void mlx5_ib_copy_pas(u64 *old, u64 *new, int step, int num);
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 49fc3ca735a..38b06267798 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -44,9 +44,13 @@ enum {
 	MAX_PENDING_REG_MR = 8,
 };
 
-enum {
-	MLX5_UMR_ALIGN	= 2048
-};
+#define MLX5_UMR_ALIGN 2048
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+static __be64 mlx5_ib_update_mtt_emergency_buffer[
+		MLX5_UMR_MTT_MIN_CHUNK_SIZE/sizeof(__be64)]
+	__aligned(MLX5_UMR_ALIGN);
+static DEFINE_MUTEX(mlx5_ib_update_mtt_emergency_buffer_mutex);
+#endif
 
 static int order2idx(struct mlx5_ib_dev *dev, int order)
 {
@@ -822,6 +826,128 @@ free_mr:
 	return mr;
 }
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+int mlx5_ib_update_mtt(struct mlx5_ib_mr *mr, u64 start_page_index, int npages,
+		       int zap)
+{
+	struct mlx5_ib_dev *dev = mr->dev;
+	struct device *ddev = dev->ib_dev.dma_device;
+	struct umr_common *umrc = &dev->umrc;
+	struct mlx5_ib_umr_context umr_context;
+	struct ib_umem *umem = mr->umem;
+	int size;
+	__be64 *pas;
+	dma_addr_t dma;
+	struct ib_send_wr wr, *bad;
+	struct mlx5_umr_wr *umrwr = (struct mlx5_umr_wr *)&wr.wr.fast_reg;
+	struct ib_sge sg;
+	int err = 0;
+	const int page_index_alignment = MLX5_UMR_MTT_ALIGNMENT / sizeof(u64);
+	const int page_index_mask = page_index_alignment - 1;
+	size_t pages_mapped = 0;
+	size_t pages_to_map = 0;
+	size_t pages_iter = 0;
+	int use_emergency_buf = 0;
+
+	/* UMR copies MTTs in units of MLX5_UMR_MTT_ALIGNMENT bytes,
+	 * so we need to align the offset and length accordingly */
+	if (start_page_index & page_index_mask) {
+		npages += start_page_index & page_index_mask;
+		start_page_index &= ~page_index_mask;
+	}
+
+	pages_to_map = ALIGN(npages, page_index_alignment);
+
+	if (start_page_index + pages_to_map > MLX5_MAX_UMR_PAGES)
+		return -EINVAL;
+
+	size = sizeof(u64) * pages_to_map;
+	size = min_t(int, PAGE_SIZE, size);
+	/* We allocate with GFP_ATOMIC to avoid recursion into page-reclaim
+	 * code, when we are called from an invalidation. The pas buffer must
+	 * be 2k-aligned for Connect-IB. */
+	pas = (__be64 *)get_zeroed_page(GFP_ATOMIC);
+	if (!pas) {
+		mlx5_ib_warn(dev, "unable to allocate memory during MTT update, falling back to slower chunked mechanism.\n");
+		pas = mlx5_ib_update_mtt_emergency_buffer;
+		size = MLX5_UMR_MTT_MIN_CHUNK_SIZE;
+		use_emergency_buf = 1;
+		mutex_lock(&mlx5_ib_update_mtt_emergency_buffer_mutex);
+		memset(pas, 0, size);
+	}
+	pages_iter = size / sizeof(u64);
+	dma = dma_map_single(ddev, pas, size, DMA_TO_DEVICE);
+	if (dma_mapping_error(ddev, dma)) {
+		mlx5_ib_err(dev, "unable to map DMA during MTT update.\n");
+		err = -ENOMEM;
+		goto free_pas;
+	}
+
+	for (pages_mapped = 0;
+	     pages_mapped < pages_to_map && !err;
+	     pages_mapped += pages_iter, start_page_index += pages_iter) {
+		dma_sync_single_for_cpu(ddev, dma, size, DMA_TO_DEVICE);
+
+		npages = min_t(size_t,
+			       pages_iter,
+			       ib_umem_num_pages(umem) - start_page_index);
+
+		if (!zap) {
+			__mlx5_ib_populate_pas(dev, umem, PAGE_SHIFT,
+					       start_page_index, npages, pas,
+					       MLX5_IB_MTT_PRESENT);
+			/* Clear padding after the pages brought from the
+			 * umem. */
+			memset(pas + npages, 0, size - npages * sizeof(u64));
+		}
+
+		dma_sync_single_for_device(ddev, dma, size, DMA_TO_DEVICE);
+
+		memset(&wr, 0, sizeof(wr));
+		wr.wr_id = (u64)(unsigned long)&umr_context;
+
+		sg.addr = dma;
+		sg.length = ALIGN(npages * sizeof(u64),
+				MLX5_UMR_MTT_ALIGNMENT);
+		sg.lkey = dev->umrc.mr->lkey;
+
+		wr.send_flags = MLX5_IB_SEND_UMR_FAIL_IF_FREE |
+				MLX5_IB_SEND_UMR_UPDATE_MTT;
+		wr.sg_list = &sg;
+		wr.num_sge = 1;
+		wr.opcode = MLX5_IB_WR_UMR;
+		umrwr->npages = sg.length / sizeof(u64);
+		umrwr->page_shift = PAGE_SHIFT;
+		umrwr->mkey = mr->mmr.key;
+		umrwr->target.offset = start_page_index;
+
+		mlx5_ib_init_umr_context(&umr_context);
+		down(&umrc->sem);
+		err = ib_post_send(umrc->qp, &wr, &bad);
+		if (err) {
+			mlx5_ib_err(dev, "UMR post send failed, err %d\n", err);
+		} else {
+			wait_for_completion(&umr_context.done);
+			if (umr_context.status != IB_WC_SUCCESS) {
+				mlx5_ib_err(dev, "UMR completion failed, code %d\n",
+					    umr_context.status);
+				err = -EFAULT;
+			}
+		}
+		up(&umrc->sem);
+	}
+	dma_unmap_single(ddev, dma, size, DMA_TO_DEVICE);
+
+free_pas:
+	if (!use_emergency_buf)
+		free_page((unsigned long)pas);
+	else
+		mutex_unlock(&mlx5_ib_update_mtt_emergency_buffer_mutex);
+
+	return err;
+}
+#endif
+
 static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, u64 virt_addr,
 				     u64 length, struct ib_umem *umem,
 				     int npages, int page_shift,
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 64512a7354c..4e5bd813bb9 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -200,6 +200,7 @@ enum {
 
 #define MLX5_UMR_MTT_ALIGNMENT 0x40
 #define MLX5_UMR_MTT_MASK      (MLX5_UMR_MTT_ALIGNMENT - 1)
+#define MLX5_UMR_MTT_MIN_CHUNK_SIZE MLX5_UMR_MTT_ALIGNMENT
 
 enum mlx5_event {
 	MLX5_EVENT_TYPE_COMP		   = 0x0,
-- 
cgit v1.2.3-70-g09d2


From 6aec21f6a8322fa8d43df3ea7f051dfd8967f1b9 Mon Sep 17 00:00:00 2001
From: Haggai Eran <haggaie@mellanox.com>
Date: Thu, 11 Dec 2014 17:04:23 +0200
Subject: IB/mlx5: Page faults handling infrastructure

* Refactor MR registration and cleanup, and fix reg_pages accounting.
* Create a work queue to handle page fault events in a kthread context.
* Register a fault handler to get events from the core for each QP.

The registered fault handler is empty in this patch, and only a later
patch implements it.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/main.c    |  31 +++++++-
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  67 +++++++++++++++-
 drivers/infiniband/hw/mlx5/mr.c      |  45 +++++++----
 drivers/infiniband/hw/mlx5/odp.c     | 145 +++++++++++++++++++++++++++++++++++
 drivers/infiniband/hw/mlx5/qp.c      |  26 ++++++-
 include/linux/mlx5/driver.h          |   2 +-
 6 files changed, 294 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index e6d775f2446..a801baa79c8 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -864,7 +864,7 @@ static ssize_t show_reg_pages(struct device *device,
 	struct mlx5_ib_dev *dev =
 		container_of(device, struct mlx5_ib_dev, ib_dev.dev);
 
-	return sprintf(buf, "%d\n", dev->mdev->priv.reg_pages);
+	return sprintf(buf, "%d\n", atomic_read(&dev->mdev->priv.reg_pages));
 }
 
 static ssize_t show_hca(struct device *device, struct device_attribute *attr,
@@ -1389,16 +1389,19 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 		goto err_eqs;
 
 	mutex_init(&dev->cap_mask_mutex);
-	spin_lock_init(&dev->mr_lock);
 
 	err = create_dev_resources(&dev->devr);
 	if (err)
 		goto err_eqs;
 
-	err = ib_register_device(&dev->ib_dev, NULL);
+	err = mlx5_ib_odp_init_one(dev);
 	if (err)
 		goto err_rsrc;
 
+	err = ib_register_device(&dev->ib_dev, NULL);
+	if (err)
+		goto err_odp;
+
 	err = create_umr_res(dev);
 	if (err)
 		goto err_dev;
@@ -1420,6 +1423,9 @@ err_umrc:
 err_dev:
 	ib_unregister_device(&dev->ib_dev);
 
+err_odp:
+	mlx5_ib_odp_remove_one(dev);
+
 err_rsrc:
 	destroy_dev_resources(&dev->devr);
 
@@ -1435,8 +1441,10 @@ err_dealloc:
 static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 {
 	struct mlx5_ib_dev *dev = context;
+
 	ib_unregister_device(&dev->ib_dev);
 	destroy_umrc_res(dev);
+	mlx5_ib_odp_remove_one(dev);
 	destroy_dev_resources(&dev->devr);
 	free_comp_eqs(dev);
 	ib_dealloc_device(&dev->ib_dev);
@@ -1450,15 +1458,30 @@ static struct mlx5_interface mlx5_ib_interface = {
 
 static int __init mlx5_ib_init(void)
 {
+	int err;
+
 	if (deprecated_prof_sel != 2)
 		pr_warn("prof_sel is deprecated for mlx5_ib, set it for mlx5_core\n");
 
-	return mlx5_register_interface(&mlx5_ib_interface);
+	err = mlx5_ib_odp_init();
+	if (err)
+		return err;
+
+	err = mlx5_register_interface(&mlx5_ib_interface);
+	if (err)
+		goto clean_odp;
+
+	return err;
+
+clean_odp:
+	mlx5_ib_odp_cleanup();
+	return err;
 }
 
 static void __exit mlx5_ib_cleanup(void)
 {
 	mlx5_unregister_interface(&mlx5_ib_interface);
+	mlx5_ib_odp_cleanup();
 }
 
 module_init(mlx5_ib_init);
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 6856e27bfb6..c6ceec3e3d6 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -149,6 +149,29 @@ enum {
 	MLX5_QP_EMPTY
 };
 
+/*
+ * Connect-IB can trigger up to four concurrent pagefaults
+ * per-QP.
+ */
+enum mlx5_ib_pagefault_context {
+	MLX5_IB_PAGEFAULT_RESPONDER_READ,
+	MLX5_IB_PAGEFAULT_REQUESTOR_READ,
+	MLX5_IB_PAGEFAULT_RESPONDER_WRITE,
+	MLX5_IB_PAGEFAULT_REQUESTOR_WRITE,
+	MLX5_IB_PAGEFAULT_CONTEXTS
+};
+
+static inline enum mlx5_ib_pagefault_context
+	mlx5_ib_get_pagefault_context(struct mlx5_pagefault *pagefault)
+{
+	return pagefault->flags & (MLX5_PFAULT_REQUESTOR | MLX5_PFAULT_WRITE);
+}
+
+struct mlx5_ib_pfault {
+	struct work_struct	work;
+	struct mlx5_pagefault	mpfault;
+};
+
 struct mlx5_ib_qp {
 	struct ib_qp		ibqp;
 	struct mlx5_core_qp	mqp;
@@ -194,6 +217,21 @@ struct mlx5_ib_qp {
 
 	/* Store signature errors */
 	bool			signature_en;
+
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	/*
+	 * A flag that is true for QP's that are in a state that doesn't
+	 * allow page faults, and shouldn't schedule any more faults.
+	 */
+	int                     disable_page_faults;
+	/*
+	 * The disable_page_faults_lock protects a QP's disable_page_faults
+	 * field, allowing for a thread to atomically check whether the QP
+	 * allows page faults, and if so schedule a page fault.
+	 */
+	spinlock_t              disable_page_faults_lock;
+	struct mlx5_ib_pfault	pagefaults[MLX5_IB_PAGEFAULT_CONTEXTS];
+#endif
 };
 
 struct mlx5_ib_cq_buf {
@@ -392,13 +430,17 @@ struct mlx5_ib_dev {
 	struct umr_common		umrc;
 	/* sync used page count stats
 	 */
-	spinlock_t			mr_lock;
 	struct mlx5_ib_resources	devr;
 	struct mlx5_mr_cache		cache;
 	struct timer_list		delay_timer;
 	int				fill_delay;
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 	struct ib_odp_caps	odp_caps;
+	/*
+	 * Sleepable RCU that prevents destruction of MRs while they are still
+	 * being used by a page fault handler.
+	 */
+	struct srcu_struct      mr_srcu;
 #endif
 };
 
@@ -575,12 +617,33 @@ int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
 			    struct ib_mr_status *mr_status);
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+extern struct workqueue_struct *mlx5_ib_page_fault_wq;
+
 int mlx5_ib_internal_query_odp_caps(struct mlx5_ib_dev *dev);
-#else
+void mlx5_ib_mr_pfault_handler(struct mlx5_ib_qp *qp,
+			       struct mlx5_ib_pfault *pfault);
+void mlx5_ib_odp_create_qp(struct mlx5_ib_qp *qp);
+int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev);
+void mlx5_ib_odp_remove_one(struct mlx5_ib_dev *ibdev);
+int __init mlx5_ib_odp_init(void);
+void mlx5_ib_odp_cleanup(void);
+void mlx5_ib_qp_disable_pagefaults(struct mlx5_ib_qp *qp);
+void mlx5_ib_qp_enable_pagefaults(struct mlx5_ib_qp *qp);
+
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 static inline int mlx5_ib_internal_query_odp_caps(struct mlx5_ib_dev *dev)
 {
 	return 0;
 }
+
+static inline void mlx5_ib_odp_create_qp(struct mlx5_ib_qp *qp)		{}
+static inline int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev) { return 0; }
+static inline void mlx5_ib_odp_remove_one(struct mlx5_ib_dev *ibdev)	{}
+static inline int mlx5_ib_odp_init(void) { return 0; }
+static inline void mlx5_ib_odp_cleanup(void)				{}
+static inline void mlx5_ib_qp_disable_pagefaults(struct mlx5_ib_qp *qp) {}
+static inline void mlx5_ib_qp_enable_pagefaults(struct mlx5_ib_qp *qp)  {}
+
 #endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 static inline void init_query_mad(struct ib_smp *mad)
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 38b06267798..922ac85b719 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -52,6 +52,8 @@ static __be64 mlx5_ib_update_mtt_emergency_buffer[
 static DEFINE_MUTEX(mlx5_ib_update_mtt_emergency_buffer_mutex);
 #endif
 
+static int clean_mr(struct mlx5_ib_mr *mr);
+
 static int order2idx(struct mlx5_ib_dev *dev, int order)
 {
 	struct mlx5_mr_cache *cache = &dev->cache;
@@ -1049,6 +1051,10 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 			mlx5_ib_dbg(dev, "cache empty for order %d", order);
 			mr = NULL;
 		}
+	} else if (access_flags & IB_ACCESS_ON_DEMAND) {
+		err = -EINVAL;
+		pr_err("Got MR registration for ODP MR > 512MB, not supported for Connect-IB");
+		goto error;
 	}
 
 	if (!mr)
@@ -1064,9 +1070,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	mr->umem = umem;
 	mr->npages = npages;
-	spin_lock(&dev->mr_lock);
-	dev->mdev->priv.reg_pages += npages;
-	spin_unlock(&dev->mr_lock);
+	atomic_add(npages, &dev->mdev->priv.reg_pages);
 	mr->ibmr.lkey = mr->mmr.key;
 	mr->ibmr.rkey = mr->mmr.key;
 
@@ -1110,12 +1114,9 @@ error:
 	return err;
 }
 
-int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
+static int clean_mr(struct mlx5_ib_mr *mr)
 {
-	struct mlx5_ib_dev *dev = to_mdev(ibmr->device);
-	struct mlx5_ib_mr *mr = to_mmr(ibmr);
-	struct ib_umem *umem = mr->umem;
-	int npages = mr->npages;
+	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
 	int umred = mr->umred;
 	int err;
 
@@ -1135,16 +1136,32 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
 		free_cached_mr(dev, mr);
 	}
 
+	if (!umred)
+		kfree(mr);
+
+	return 0;
+}
+
+int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibmr->device);
+	struct mlx5_ib_mr *mr = to_mmr(ibmr);
+	int npages = mr->npages;
+	struct ib_umem *umem = mr->umem;
+
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	if (umem)
+		/* Wait for all running page-fault handlers to finish. */
+		synchronize_srcu(&dev->mr_srcu);
+#endif
+
+	clean_mr(mr);
+
 	if (umem) {
 		ib_umem_release(umem);
-		spin_lock(&dev->mr_lock);
-		dev->mdev->priv.reg_pages -= npages;
-		spin_unlock(&dev->mr_lock);
+		atomic_sub(npages, &dev->mdev->priv.reg_pages);
 	}
 
-	if (!umred)
-		kfree(mr);
-
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 66c39ee16af..63bbdba396f 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -32,6 +32,8 @@
 
 #include "mlx5_ib.h"
 
+struct workqueue_struct *mlx5_ib_page_fault_wq;
+
 #define COPY_ODP_BIT_MLX_TO_IB(reg, ib_caps, field_name, bit_name) do {	\
 	if (be32_to_cpu(reg.field_name) & MLX5_ODP_SUPPORT_##bit_name)	\
 		ib_caps->field_name |= IB_ODP_SUPPORT_##bit_name;	\
@@ -58,3 +60,146 @@ int mlx5_ib_internal_query_odp_caps(struct mlx5_ib_dev *dev)
 out:
 	return err;
 }
+
+static struct mlx5_ib_mr *mlx5_ib_odp_find_mr_lkey(struct mlx5_ib_dev *dev,
+						   u32 key)
+{
+	u32 base_key = mlx5_base_mkey(key);
+	struct mlx5_core_mr *mmr = __mlx5_mr_lookup(dev->mdev, base_key);
+
+	if (!mmr || mmr->key != key)
+		return NULL;
+
+	return container_of(mmr, struct mlx5_ib_mr, mmr);
+}
+
+static void mlx5_ib_page_fault_resume(struct mlx5_ib_qp *qp,
+				      struct mlx5_ib_pfault *pfault,
+				      int error) {
+	struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.pd->device);
+	int ret = mlx5_core_page_fault_resume(dev->mdev, qp->mqp.qpn,
+					      pfault->mpfault.flags,
+					      error);
+	if (ret)
+		pr_err("Failed to resolve the page fault on QP 0x%x\n",
+		       qp->mqp.qpn);
+}
+
+void mlx5_ib_mr_pfault_handler(struct mlx5_ib_qp *qp,
+			       struct mlx5_ib_pfault *pfault)
+{
+	u8 event_subtype = pfault->mpfault.event_subtype;
+
+	switch (event_subtype) {
+	default:
+		pr_warn("Invalid page fault event subtype: 0x%x\n",
+			event_subtype);
+		mlx5_ib_page_fault_resume(qp, pfault, 1);
+		break;
+	}
+}
+
+static void mlx5_ib_qp_pfault_action(struct work_struct *work)
+{
+	struct mlx5_ib_pfault *pfault = container_of(work,
+						     struct mlx5_ib_pfault,
+						     work);
+	enum mlx5_ib_pagefault_context context =
+		mlx5_ib_get_pagefault_context(&pfault->mpfault);
+	struct mlx5_ib_qp *qp = container_of(pfault, struct mlx5_ib_qp,
+					     pagefaults[context]);
+	mlx5_ib_mr_pfault_handler(qp, pfault);
+}
+
+void mlx5_ib_qp_disable_pagefaults(struct mlx5_ib_qp *qp)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&qp->disable_page_faults_lock, flags);
+	qp->disable_page_faults = 1;
+	spin_unlock_irqrestore(&qp->disable_page_faults_lock, flags);
+
+	/*
+	 * Note that at this point, we are guarenteed that no more
+	 * work queue elements will be posted to the work queue with
+	 * the QP we are closing.
+	 */
+	flush_workqueue(mlx5_ib_page_fault_wq);
+}
+
+void mlx5_ib_qp_enable_pagefaults(struct mlx5_ib_qp *qp)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&qp->disable_page_faults_lock, flags);
+	qp->disable_page_faults = 0;
+	spin_unlock_irqrestore(&qp->disable_page_faults_lock, flags);
+}
+
+static void mlx5_ib_pfault_handler(struct mlx5_core_qp *qp,
+				   struct mlx5_pagefault *pfault)
+{
+	/*
+	 * Note that we will only get one fault event per QP per context
+	 * (responder/initiator, read/write), until we resolve the page fault
+	 * with the mlx5_ib_page_fault_resume command. Since this function is
+	 * called from within the work element, there is no risk of missing
+	 * events.
+	 */
+	struct mlx5_ib_qp *mibqp = to_mibqp(qp);
+	enum mlx5_ib_pagefault_context context =
+		mlx5_ib_get_pagefault_context(pfault);
+	struct mlx5_ib_pfault *qp_pfault = &mibqp->pagefaults[context];
+
+	qp_pfault->mpfault = *pfault;
+
+	/* No need to stop interrupts here since we are in an interrupt */
+	spin_lock(&mibqp->disable_page_faults_lock);
+	if (!mibqp->disable_page_faults)
+		queue_work(mlx5_ib_page_fault_wq, &qp_pfault->work);
+	spin_unlock(&mibqp->disable_page_faults_lock);
+}
+
+void mlx5_ib_odp_create_qp(struct mlx5_ib_qp *qp)
+{
+	int i;
+
+	qp->disable_page_faults = 1;
+	spin_lock_init(&qp->disable_page_faults_lock);
+
+	qp->mqp.pfault_handler	= mlx5_ib_pfault_handler;
+
+	for (i = 0; i < MLX5_IB_PAGEFAULT_CONTEXTS; ++i)
+		INIT_WORK(&qp->pagefaults[i].work, mlx5_ib_qp_pfault_action);
+}
+
+int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev)
+{
+	int ret;
+
+	ret = init_srcu_struct(&ibdev->mr_srcu);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+void mlx5_ib_odp_remove_one(struct mlx5_ib_dev *ibdev)
+{
+	cleanup_srcu_struct(&ibdev->mr_srcu);
+}
+
+int __init mlx5_ib_odp_init(void)
+{
+	mlx5_ib_page_fault_wq =
+		create_singlethread_workqueue("mlx5_ib_page_faults");
+	if (!mlx5_ib_page_fault_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void mlx5_ib_odp_cleanup(void)
+{
+	destroy_workqueue(mlx5_ib_page_fault_wq);
+}
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 9783c3342db..be0cd358b08 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -876,6 +876,8 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	int inlen = sizeof(*in);
 	int err;
 
+	mlx5_ib_odp_create_qp(qp);
+
 	gen = &dev->mdev->caps.gen;
 	mutex_init(&qp->mutex);
 	spin_lock_init(&qp->sq.lock);
@@ -1160,11 +1162,13 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
 	in = kzalloc(sizeof(*in), GFP_KERNEL);
 	if (!in)
 		return;
-	if (qp->state != IB_QPS_RESET)
+	if (qp->state != IB_QPS_RESET) {
+		mlx5_ib_qp_disable_pagefaults(qp);
 		if (mlx5_core_qp_modify(dev->mdev, to_mlx5_state(qp->state),
 					MLX5_QP_STATE_RST, in, sizeof(*in), &qp->mqp))
 			mlx5_ib_warn(dev, "mlx5_ib: modify QP %06x to RESET failed\n",
 				     qp->mqp.qpn);
+	}
 
 	get_cqs(qp, &send_cq, &recv_cq);
 
@@ -1712,6 +1716,15 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	if (mlx5_st < 0)
 		goto out;
 
+	/* If moving to a reset or error state, we must disable page faults on
+	 * this QP and flush all current page faults. Otherwise a stale page
+	 * fault may attempt to work on this QP after it is reset and moved
+	 * again to RTS, and may cause the driver and the device to get out of
+	 * sync. */
+	if (cur_state != IB_QPS_RESET && cur_state != IB_QPS_ERR &&
+	    (new_state == IB_QPS_RESET || new_state == IB_QPS_ERR))
+		mlx5_ib_qp_disable_pagefaults(qp);
+
 	optpar = ib_mask_to_mlx5_opt(attr_mask);
 	optpar &= opt_mask[mlx5_cur][mlx5_new][mlx5_st];
 	in->optparam = cpu_to_be32(optpar);
@@ -1721,6 +1734,9 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	if (err)
 		goto out;
 
+	if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT)
+		mlx5_ib_qp_enable_pagefaults(qp);
+
 	qp->state = new_state;
 
 	if (attr_mask & IB_QP_ACCESS_FLAGS)
@@ -3026,6 +3042,14 @@ int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr
 	int mlx5_state;
 	int err = 0;
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	/*
+	 * Wait for any outstanding page faults, in case the user frees memory
+	 * based upon this query's result.
+	 */
+	flush_workqueue(mlx5_ib_page_fault_wq);
+#endif
+
 	mutex_lock(&qp->mutex);
 	outb = kzalloc(sizeof(*outb), GFP_KERNEL);
 	if (!outb) {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 7088dcd1921..166d9315fe4 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -474,7 +474,7 @@ struct mlx5_priv {
 	struct workqueue_struct *pg_wq;
 	struct rb_root		page_root;
 	int			fw_pages;
-	int			reg_pages;
+	atomic_t		reg_pages;
 	struct list_head	free_list;
 
 	struct mlx5_core_health health;
-- 
cgit v1.2.3-70-g09d2


From 7bdf65d411c1715d695be0d9a555d7f48d0a7220 Mon Sep 17 00:00:00 2001
From: Haggai Eran <haggaie@mellanox.com>
Date: Thu, 11 Dec 2014 17:04:24 +0200
Subject: IB/mlx5: Handle page faults

This patch implement a page fault handler (leaving the pages pinned as
of time being).  The page fault handler handles initiator and responder
page faults for UD/RC transports, for send/receive operations, as well
as RDMA read/write initiator support.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/odp.c | 408 +++++++++++++++++++++++++++++++++++++++
 include/linux/mlx5/qp.h          |   7 +
 2 files changed, 415 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 63bbdba396f..bd1dbe5ebc1 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -30,6 +30,9 @@
  * SOFTWARE.
  */
 
+#include <rdma/ib_umem.h>
+#include <rdma/ib_umem_odp.h>
+
 #include "mlx5_ib.h"
 
 struct workqueue_struct *mlx5_ib_page_fault_wq;
@@ -85,12 +88,417 @@ static void mlx5_ib_page_fault_resume(struct mlx5_ib_qp *qp,
 		       qp->mqp.qpn);
 }
 
+/*
+ * Handle a single data segment in a page-fault WQE.
+ *
+ * Returns number of pages retrieved on success. The caller will continue to
+ * the next data segment.
+ * Can return the following error codes:
+ * -EAGAIN to designate a temporary error. The caller will abort handling the
+ *  page fault and resolve it.
+ * -EFAULT when there's an error mapping the requested pages. The caller will
+ *  abort the page fault handling and possibly move the QP to an error state.
+ * On other errors the QP should also be closed with an error.
+ */
+static int pagefault_single_data_segment(struct mlx5_ib_qp *qp,
+					 struct mlx5_ib_pfault *pfault,
+					 u32 key, u64 io_virt, size_t bcnt,
+					 u32 *bytes_mapped)
+{
+	struct mlx5_ib_dev *mib_dev = to_mdev(qp->ibqp.pd->device);
+	int srcu_key;
+	unsigned int current_seq;
+	u64 start_idx;
+	int npages = 0, ret = 0;
+	struct mlx5_ib_mr *mr;
+	u64 access_mask = ODP_READ_ALLOWED_BIT;
+
+	srcu_key = srcu_read_lock(&mib_dev->mr_srcu);
+	mr = mlx5_ib_odp_find_mr_lkey(mib_dev, key);
+	/*
+	 * If we didn't find the MR, it means the MR was closed while we were
+	 * handling the ODP event. In this case we return -EFAULT so that the
+	 * QP will be closed.
+	 */
+	if (!mr || !mr->ibmr.pd) {
+		pr_err("Failed to find relevant mr for lkey=0x%06x, probably the MR was destroyed\n",
+		       key);
+		ret = -EFAULT;
+		goto srcu_unlock;
+	}
+	if (!mr->umem->odp_data) {
+		pr_debug("skipping non ODP MR (lkey=0x%06x) in page fault handler.\n",
+			 key);
+		if (bytes_mapped)
+			*bytes_mapped +=
+				(bcnt - pfault->mpfault.bytes_committed);
+		goto srcu_unlock;
+	}
+	if (mr->ibmr.pd != qp->ibqp.pd) {
+		pr_err("Page-fault with different PDs for QP and MR.\n");
+		ret = -EFAULT;
+		goto srcu_unlock;
+	}
+
+	current_seq = ACCESS_ONCE(mr->umem->odp_data->notifiers_seq);
+
+	/*
+	 * Avoid branches - this code will perform correctly
+	 * in all iterations (in iteration 2 and above,
+	 * bytes_committed == 0).
+	 */
+	io_virt += pfault->mpfault.bytes_committed;
+	bcnt -= pfault->mpfault.bytes_committed;
+
+	start_idx = (io_virt - (mr->mmr.iova & PAGE_MASK)) >> PAGE_SHIFT;
+
+	if (mr->umem->writable)
+		access_mask |= ODP_WRITE_ALLOWED_BIT;
+	npages = ib_umem_odp_map_dma_pages(mr->umem, io_virt, bcnt,
+					   access_mask, current_seq);
+	if (npages < 0) {
+		ret = npages;
+		goto srcu_unlock;
+	}
+
+	if (npages > 0) {
+		mutex_lock(&mr->umem->odp_data->umem_mutex);
+		/*
+		 * No need to check whether the MTTs really belong to
+		 * this MR, since ib_umem_odp_map_dma_pages already
+		 * checks this.
+		 */
+		ret = mlx5_ib_update_mtt(mr, start_idx, npages, 0);
+		mutex_unlock(&mr->umem->odp_data->umem_mutex);
+		if (ret < 0) {
+			pr_err("Failed to update mkey page tables\n");
+			goto srcu_unlock;
+		}
+
+		if (bytes_mapped) {
+			u32 new_mappings = npages * PAGE_SIZE -
+				(io_virt - round_down(io_virt, PAGE_SIZE));
+			*bytes_mapped += min_t(u32, new_mappings, bcnt);
+		}
+	}
+
+srcu_unlock:
+	srcu_read_unlock(&mib_dev->mr_srcu, srcu_key);
+	pfault->mpfault.bytes_committed = 0;
+	return ret ? ret : npages;
+}
+
+/**
+ * Parse a series of data segments for page fault handling.
+ *
+ * @qp the QP on which the fault occurred.
+ * @pfault contains page fault information.
+ * @wqe points at the first data segment in the WQE.
+ * @wqe_end points after the end of the WQE.
+ * @bytes_mapped receives the number of bytes that the function was able to
+ *               map. This allows the caller to decide intelligently whether
+ *               enough memory was mapped to resolve the page fault
+ *               successfully (e.g. enough for the next MTU, or the entire
+ *               WQE).
+ * @total_wqe_bytes receives the total data size of this WQE in bytes (minus
+ *                  the committed bytes).
+ *
+ * Returns the number of pages loaded if positive, zero for an empty WQE, or a
+ * negative error code.
+ */
+static int pagefault_data_segments(struct mlx5_ib_qp *qp,
+				   struct mlx5_ib_pfault *pfault, void *wqe,
+				   void *wqe_end, u32 *bytes_mapped,
+				   u32 *total_wqe_bytes, int receive_queue)
+{
+	int ret = 0, npages = 0;
+	u64 io_virt;
+	u32 key;
+	u32 byte_count;
+	size_t bcnt;
+	int inline_segment;
+
+	/* Skip SRQ next-WQE segment. */
+	if (receive_queue && qp->ibqp.srq)
+		wqe += sizeof(struct mlx5_wqe_srq_next_seg);
+
+	if (bytes_mapped)
+		*bytes_mapped = 0;
+	if (total_wqe_bytes)
+		*total_wqe_bytes = 0;
+
+	while (wqe < wqe_end) {
+		struct mlx5_wqe_data_seg *dseg = wqe;
+
+		io_virt = be64_to_cpu(dseg->addr);
+		key = be32_to_cpu(dseg->lkey);
+		byte_count = be32_to_cpu(dseg->byte_count);
+		inline_segment = !!(byte_count &  MLX5_INLINE_SEG);
+		bcnt	       = byte_count & ~MLX5_INLINE_SEG;
+
+		if (inline_segment) {
+			bcnt = bcnt & MLX5_WQE_INLINE_SEG_BYTE_COUNT_MASK;
+			wqe += ALIGN(sizeof(struct mlx5_wqe_inline_seg) + bcnt,
+				     16);
+		} else {
+			wqe += sizeof(*dseg);
+		}
+
+		/* receive WQE end of sg list. */
+		if (receive_queue && bcnt == 0 && key == MLX5_INVALID_LKEY &&
+		    io_virt == 0)
+			break;
+
+		if (!inline_segment && total_wqe_bytes) {
+			*total_wqe_bytes += bcnt - min_t(size_t, bcnt,
+					pfault->mpfault.bytes_committed);
+		}
+
+		/* A zero length data segment designates a length of 2GB. */
+		if (bcnt == 0)
+			bcnt = 1U << 31;
+
+		if (inline_segment || bcnt <= pfault->mpfault.bytes_committed) {
+			pfault->mpfault.bytes_committed -=
+				min_t(size_t, bcnt,
+				      pfault->mpfault.bytes_committed);
+			continue;
+		}
+
+		ret = pagefault_single_data_segment(qp, pfault, key, io_virt,
+						    bcnt, bytes_mapped);
+		if (ret < 0)
+			break;
+		npages += ret;
+	}
+
+	return ret < 0 ? ret : npages;
+}
+
+/*
+ * Parse initiator WQE. Advances the wqe pointer to point at the
+ * scatter-gather list, and set wqe_end to the end of the WQE.
+ */
+static int mlx5_ib_mr_initiator_pfault_handler(
+	struct mlx5_ib_qp *qp, struct mlx5_ib_pfault *pfault,
+	void **wqe, void **wqe_end, int wqe_length)
+{
+	struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.pd->device);
+	struct mlx5_wqe_ctrl_seg *ctrl = *wqe;
+	u16 wqe_index = pfault->mpfault.wqe.wqe_index;
+	unsigned ds, opcode;
+#if defined(DEBUG)
+	u32 ctrl_wqe_index, ctrl_qpn;
+#endif
+
+	ds = be32_to_cpu(ctrl->qpn_ds) & MLX5_WQE_CTRL_DS_MASK;
+	if (ds * MLX5_WQE_DS_UNITS > wqe_length) {
+		mlx5_ib_err(dev, "Unable to read the complete WQE. ds = 0x%x, ret = 0x%x\n",
+			    ds, wqe_length);
+		return -EFAULT;
+	}
+
+	if (ds == 0) {
+		mlx5_ib_err(dev, "Got WQE with zero DS. wqe_index=%x, qpn=%x\n",
+			    wqe_index, qp->mqp.qpn);
+		return -EFAULT;
+	}
+
+#if defined(DEBUG)
+	ctrl_wqe_index = (be32_to_cpu(ctrl->opmod_idx_opcode) &
+			MLX5_WQE_CTRL_WQE_INDEX_MASK) >>
+			MLX5_WQE_CTRL_WQE_INDEX_SHIFT;
+	if (wqe_index != ctrl_wqe_index) {
+		mlx5_ib_err(dev, "Got WQE with invalid wqe_index. wqe_index=0x%x, qpn=0x%x ctrl->wqe_index=0x%x\n",
+			    wqe_index, qp->mqp.qpn,
+			    ctrl_wqe_index);
+		return -EFAULT;
+	}
+
+	ctrl_qpn = (be32_to_cpu(ctrl->qpn_ds) & MLX5_WQE_CTRL_QPN_MASK) >>
+		MLX5_WQE_CTRL_QPN_SHIFT;
+	if (qp->mqp.qpn != ctrl_qpn) {
+		mlx5_ib_err(dev, "Got WQE with incorrect QP number. wqe_index=0x%x, qpn=0x%x ctrl->qpn=0x%x\n",
+			    wqe_index, qp->mqp.qpn,
+			    ctrl_qpn);
+		return -EFAULT;
+	}
+#endif /* DEBUG */
+
+	*wqe_end = *wqe + ds * MLX5_WQE_DS_UNITS;
+	*wqe += sizeof(*ctrl);
+
+	opcode = be32_to_cpu(ctrl->opmod_idx_opcode) &
+		 MLX5_WQE_CTRL_OPCODE_MASK;
+	switch (qp->ibqp.qp_type) {
+	case IB_QPT_RC:
+		switch (opcode) {
+		case MLX5_OPCODE_SEND:
+		case MLX5_OPCODE_SEND_IMM:
+		case MLX5_OPCODE_SEND_INVAL:
+			if (!(dev->odp_caps.per_transport_caps.rc_odp_caps &
+			      IB_ODP_SUPPORT_SEND))
+				goto invalid_transport_or_opcode;
+			break;
+		case MLX5_OPCODE_RDMA_WRITE:
+		case MLX5_OPCODE_RDMA_WRITE_IMM:
+			if (!(dev->odp_caps.per_transport_caps.rc_odp_caps &
+			      IB_ODP_SUPPORT_WRITE))
+				goto invalid_transport_or_opcode;
+			*wqe += sizeof(struct mlx5_wqe_raddr_seg);
+			break;
+		case MLX5_OPCODE_RDMA_READ:
+			if (!(dev->odp_caps.per_transport_caps.rc_odp_caps &
+			      IB_ODP_SUPPORT_READ))
+				goto invalid_transport_or_opcode;
+			*wqe += sizeof(struct mlx5_wqe_raddr_seg);
+			break;
+		default:
+			goto invalid_transport_or_opcode;
+		}
+		break;
+	case IB_QPT_UD:
+		switch (opcode) {
+		case MLX5_OPCODE_SEND:
+		case MLX5_OPCODE_SEND_IMM:
+			if (!(dev->odp_caps.per_transport_caps.ud_odp_caps &
+			      IB_ODP_SUPPORT_SEND))
+				goto invalid_transport_or_opcode;
+			*wqe += sizeof(struct mlx5_wqe_datagram_seg);
+			break;
+		default:
+			goto invalid_transport_or_opcode;
+		}
+		break;
+	default:
+invalid_transport_or_opcode:
+		mlx5_ib_err(dev, "ODP fault on QP of an unsupported opcode or transport. transport: 0x%x opcode: 0x%x.\n",
+			    qp->ibqp.qp_type, opcode);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+/*
+ * Parse responder WQE. Advances the wqe pointer to point at the
+ * scatter-gather list, and set wqe_end to the end of the WQE.
+ */
+static int mlx5_ib_mr_responder_pfault_handler(
+	struct mlx5_ib_qp *qp, struct mlx5_ib_pfault *pfault,
+	void **wqe, void **wqe_end, int wqe_length)
+{
+	struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.pd->device);
+	struct mlx5_ib_wq *wq = &qp->rq;
+	int wqe_size = 1 << wq->wqe_shift;
+
+	if (qp->ibqp.srq) {
+		mlx5_ib_err(dev, "ODP fault on SRQ is not supported\n");
+		return -EFAULT;
+	}
+
+	if (qp->wq_sig) {
+		mlx5_ib_err(dev, "ODP fault with WQE signatures is not supported\n");
+		return -EFAULT;
+	}
+
+	if (wqe_size > wqe_length) {
+		mlx5_ib_err(dev, "Couldn't read all of the receive WQE's content\n");
+		return -EFAULT;
+	}
+
+	switch (qp->ibqp.qp_type) {
+	case IB_QPT_RC:
+		if (!(dev->odp_caps.per_transport_caps.rc_odp_caps &
+		      IB_ODP_SUPPORT_RECV))
+			goto invalid_transport_or_opcode;
+		break;
+	default:
+invalid_transport_or_opcode:
+		mlx5_ib_err(dev, "ODP fault on QP of an unsupported transport. transport: 0x%x\n",
+			    qp->ibqp.qp_type);
+		return -EFAULT;
+	}
+
+	*wqe_end = *wqe + wqe_size;
+
+	return 0;
+}
+
+static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_qp *qp,
+					  struct mlx5_ib_pfault *pfault)
+{
+	struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.pd->device);
+	int ret;
+	void *wqe, *wqe_end;
+	u32 bytes_mapped, total_wqe_bytes;
+	char *buffer = NULL;
+	int resume_with_error = 0;
+	u16 wqe_index = pfault->mpfault.wqe.wqe_index;
+	int requestor = pfault->mpfault.flags & MLX5_PFAULT_REQUESTOR;
+
+	buffer = (char *)__get_free_page(GFP_KERNEL);
+	if (!buffer) {
+		mlx5_ib_err(dev, "Error allocating memory for IO page fault handling.\n");
+		resume_with_error = 1;
+		goto resolve_page_fault;
+	}
+
+	ret = mlx5_ib_read_user_wqe(qp, requestor, wqe_index, buffer,
+				    PAGE_SIZE);
+	if (ret < 0) {
+		mlx5_ib_err(dev, "Failed reading a WQE following page fault, error=%x, wqe_index=%x, qpn=%x\n",
+			    -ret, wqe_index, qp->mqp.qpn);
+		resume_with_error = 1;
+		goto resolve_page_fault;
+	}
+
+	wqe = buffer;
+	if (requestor)
+		ret = mlx5_ib_mr_initiator_pfault_handler(qp, pfault, &wqe,
+							  &wqe_end, ret);
+	else
+		ret = mlx5_ib_mr_responder_pfault_handler(qp, pfault, &wqe,
+							  &wqe_end, ret);
+	if (ret < 0) {
+		resume_with_error = 1;
+		goto resolve_page_fault;
+	}
+
+	if (wqe >= wqe_end) {
+		mlx5_ib_err(dev, "ODP fault on invalid WQE.\n");
+		resume_with_error = 1;
+		goto resolve_page_fault;
+	}
+
+	ret = pagefault_data_segments(qp, pfault, wqe, wqe_end, &bytes_mapped,
+				      &total_wqe_bytes, !requestor);
+	if (ret == -EAGAIN) {
+		goto resolve_page_fault;
+	} else if (ret < 0 || total_wqe_bytes > bytes_mapped) {
+		mlx5_ib_err(dev, "Error getting user pages for page fault. Error: 0x%x\n",
+			    -ret);
+		resume_with_error = 1;
+		goto resolve_page_fault;
+	}
+
+resolve_page_fault:
+	mlx5_ib_page_fault_resume(qp, pfault, resume_with_error);
+	mlx5_ib_dbg(dev, "PAGE FAULT completed. QP 0x%x resume_with_error=%d, flags: 0x%x\n",
+		    qp->mqp.qpn, resume_with_error, pfault->mpfault.flags);
+
+	free_page((unsigned long)buffer);
+}
+
 void mlx5_ib_mr_pfault_handler(struct mlx5_ib_qp *qp,
 			       struct mlx5_ib_pfault *pfault)
 {
 	u8 event_subtype = pfault->mpfault.event_subtype;
 
 	switch (event_subtype) {
+	case MLX5_PFAULT_SUBTYPE_WQE:
+		mlx5_ib_mr_wqe_pfault_handler(qp, pfault);
+		break;
 	default:
 		pr_warn("Invalid page fault event subtype: 0x%x\n",
 			event_subtype);
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 6b1d6f60c7e..61f7a342d1b 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -193,7 +193,12 @@ struct mlx5_wqe_ctrl_seg {
 };
 
 #define MLX5_WQE_CTRL_DS_MASK 0x3f
+#define MLX5_WQE_CTRL_QPN_MASK 0xffffff00
+#define MLX5_WQE_CTRL_QPN_SHIFT 8
 #define MLX5_WQE_DS_UNITS 16
+#define MLX5_WQE_CTRL_OPCODE_MASK 0xff
+#define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00
+#define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8
 
 struct mlx5_wqe_xrc_seg {
 	__be32			xrc_srqn;
@@ -298,6 +303,8 @@ struct mlx5_wqe_signature_seg {
 	u8	rsvd1[11];
 };
 
+#define MLX5_WQE_INLINE_SEG_BYTE_COUNT_MASK 0x3ff
+
 struct mlx5_wqe_inline_seg {
 	__be32	byte_count;
 };
-- 
cgit v1.2.3-70-g09d2


From 80e1dd82be59d247e899d8ce29389f84ed828994 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 3 Nov 2014 16:48:47 -0800
Subject: mfd: stmpe: add pull up/down register offsets for STMPE

This adds the register offsets for pull up/down for the STMPE
1601, 1801 and 24xx expanders. This is used to bias GPIO lines
and keypad lines.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/mfd/stmpe.c       | 4 ++++
 drivers/mfd/stmpe.h       | 3 +++
 include/linux/mfd/stmpe.h | 2 ++
 3 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c
index 02a17c388e8..2d29d17518c 100644
--- a/drivers/mfd/stmpe.c
+++ b/drivers/mfd/stmpe.c
@@ -519,6 +519,7 @@ static const u8 stmpe1601_regs[] = {
 	[STMPE_IDX_GPDR_LSB]	= STMPE1601_REG_GPIO_SET_DIR_LSB,
 	[STMPE_IDX_GPRER_LSB]	= STMPE1601_REG_GPIO_RE_LSB,
 	[STMPE_IDX_GPFER_LSB]	= STMPE1601_REG_GPIO_FE_LSB,
+	[STMPE_IDX_GPPUR_LSB]	= STMPE1601_REG_GPIO_PU_LSB,
 	[STMPE_IDX_GPAFR_U_MSB]	= STMPE1601_REG_GPIO_AF_U_MSB,
 	[STMPE_IDX_IEGPIOR_LSB]	= STMPE1601_REG_INT_EN_GPIO_MASK_LSB,
 	[STMPE_IDX_ISGPIOR_MSB]	= STMPE1601_REG_INT_STA_GPIO_MSB,
@@ -667,6 +668,7 @@ static const u8 stmpe1801_regs[] = {
 	[STMPE_IDX_GPDR_LSB]	= STMPE1801_REG_GPIO_SET_DIR_LOW,
 	[STMPE_IDX_GPRER_LSB]	= STMPE1801_REG_GPIO_RE_LOW,
 	[STMPE_IDX_GPFER_LSB]	= STMPE1801_REG_GPIO_FE_LOW,
+	[STMPE_IDX_GPPUR_LSB]	= STMPE1801_REG_GPIO_PULL_UP_LOW,
 	[STMPE_IDX_IEGPIOR_LSB]	= STMPE1801_REG_INT_EN_GPIO_MASK_LOW,
 	[STMPE_IDX_ISGPIOR_LSB]	= STMPE1801_REG_INT_STA_GPIO_LOW,
 };
@@ -750,6 +752,8 @@ static const u8 stmpe24xx_regs[] = {
 	[STMPE_IDX_GPDR_LSB]	= STMPE24XX_REG_GPDR_LSB,
 	[STMPE_IDX_GPRER_LSB]	= STMPE24XX_REG_GPRER_LSB,
 	[STMPE_IDX_GPFER_LSB]	= STMPE24XX_REG_GPFER_LSB,
+	[STMPE_IDX_GPPUR_LSB]	= STMPE24XX_REG_GPPUR_LSB,
+	[STMPE_IDX_GPPDR_LSB]	= STMPE24XX_REG_GPPDR_LSB,
 	[STMPE_IDX_GPAFR_U_MSB]	= STMPE24XX_REG_GPAFR_U_MSB,
 	[STMPE_IDX_IEGPIOR_LSB]	= STMPE24XX_REG_IEGPIOR_LSB,
 	[STMPE_IDX_ISGPIOR_MSB]	= STMPE24XX_REG_ISGPIOR_MSB,
diff --git a/drivers/mfd/stmpe.h b/drivers/mfd/stmpe.h
index 2d045f26f19..e00710b6393 100644
--- a/drivers/mfd/stmpe.h
+++ b/drivers/mfd/stmpe.h
@@ -188,6 +188,7 @@ int stmpe_remove(struct stmpe *stmpe);
 #define STMPE1601_REG_GPIO_ED_MSB		0x8A
 #define STMPE1601_REG_GPIO_RE_LSB		0x8D
 #define STMPE1601_REG_GPIO_FE_LSB		0x8F
+#define STMPE1601_REG_GPIO_PU_LSB		0x91
 #define STMPE1601_REG_GPIO_AF_U_MSB		0x92
 
 #define STMPE1601_SYS_CTRL_ENABLE_GPIO		(1 << 3)
@@ -276,6 +277,8 @@ int stmpe_remove(struct stmpe *stmpe);
 #define STMPE24XX_REG_GPEDR_MSB		0x8C
 #define STMPE24XX_REG_GPRER_LSB		0x91
 #define STMPE24XX_REG_GPFER_LSB		0x94
+#define STMPE24XX_REG_GPPUR_LSB		0x97
+#define STMPE24XX_REG_GPPDR_LSB		0x9a
 #define STMPE24XX_REG_GPAFR_U_MSB	0x9B
 
 #define STMPE24XX_SYS_CTRL_ENABLE_GPIO		(1 << 3)
diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h
index 575a86c7fcb..cc0deb72e46 100644
--- a/include/linux/mfd/stmpe.h
+++ b/include/linux/mfd/stmpe.h
@@ -50,6 +50,8 @@ enum {
 	STMPE_IDX_GPEDR_MSB,
 	STMPE_IDX_GPRER_LSB,
 	STMPE_IDX_GPFER_LSB,
+	STMPE_IDX_GPPUR_LSB,
+	STMPE_IDX_GPPDR_LSB,
 	STMPE_IDX_GPAFR_U_MSB,
 	STMPE_IDX_IEGPIOR_LSB,
 	STMPE_IDX_ISGPIOR_LSB,
-- 
cgit v1.2.3-70-g09d2


From a4164863e150c4991d2ac965e3fc52f9d8df3d7e Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 3 Nov 2014 16:51:26 -0800
Subject: Input: stmpe - enforce device tree only mode

The STMPE keypad controller is only used with device tree configured
systems, so force the configuration to come from device tree only, and now
actually get the rows and cols from the device tree too.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../devicetree/bindings/input/stmpe-keypad.txt     |   2 +
 drivers/input/keyboard/Kconfig                     |   1 +
 drivers/input/keyboard/stmpe-keypad.c              | 104 +++++++++------------
 include/linux/mfd/stmpe.h                          |  20 ----
 4 files changed, 48 insertions(+), 79 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/input/stmpe-keypad.txt b/Documentation/devicetree/bindings/input/stmpe-keypad.txt
index 1b97222e8a0..12bb771d66d 100644
--- a/Documentation/devicetree/bindings/input/stmpe-keypad.txt
+++ b/Documentation/devicetree/bindings/input/stmpe-keypad.txt
@@ -8,6 +8,8 @@ Optional properties:
  - debounce-interval        : Debouncing interval time in milliseconds
  - st,scan-count            : Scanning cycles elapsed before key data is updated
  - st,no-autorepeat         : If specified device will not autorepeat
+ - keypad,num-rows          : See ./matrix-keymap.txt
+ - keypad,num-columns       : See ./matrix-keymap.txt
 
 Example:
 
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index 96ee26c555e..a5d9b3f3c87 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -559,6 +559,7 @@ config KEYBOARD_SH_KEYSC
 config KEYBOARD_STMPE
 	tristate "STMPE keypad support"
 	depends on MFD_STMPE
+	depends on OF
 	select INPUT_MATRIXKMAP
 	help
 	  Say Y here if you want to use the keypad controller on STMPE I/O
diff --git a/drivers/input/keyboard/stmpe-keypad.c b/drivers/input/keyboard/stmpe-keypad.c
index c6727dda68f..8d1e7af3c5b 100644
--- a/drivers/input/keyboard/stmpe-keypad.c
+++ b/drivers/input/keyboard/stmpe-keypad.c
@@ -45,7 +45,7 @@
 #define STMPE_KEYPAD_MAX_ROWS		8
 #define STMPE_KEYPAD_MAX_COLS		8
 #define STMPE_KEYPAD_ROW_SHIFT		3
-#define STMPE_KEYPAD_KEYMAP_SIZE	\
+#define STMPE_KEYPAD_KEYMAP_MAX_SIZE \
 	(STMPE_KEYPAD_MAX_ROWS * STMPE_KEYPAD_MAX_COLS)
 
 /**
@@ -99,16 +99,30 @@ static const struct stmpe_keypad_variant stmpe_keypad_variants[] = {
 	},
 };
 
+/**
+ * struct stmpe_keypad - STMPE keypad state container
+ * @stmpe: pointer to parent STMPE device
+ * @input: spawned input device
+ * @variant: STMPE variant
+ * @debounce_ms: debounce interval, in ms.  Maximum is
+ *		 %STMPE_KEYPAD_MAX_DEBOUNCE.
+ * @scan_count: number of key scanning cycles to confirm key data.
+ *		Maximum is %STMPE_KEYPAD_MAX_SCAN_COUNT.
+ * @no_autorepeat: disable key autorepeat
+ * @rows: bitmask for the rows
+ * @cols: bitmask for the columns
+ * @keymap: the keymap
+ */
 struct stmpe_keypad {
 	struct stmpe *stmpe;
 	struct input_dev *input;
 	const struct stmpe_keypad_variant *variant;
-	const struct stmpe_keypad_platform_data *plat;
-
+	unsigned int debounce_ms;
+	unsigned int scan_count;
+	bool no_autorepeat;
 	unsigned int rows;
 	unsigned int cols;
-
-	unsigned short keymap[STMPE_KEYPAD_KEYMAP_SIZE];
+	unsigned short keymap[STMPE_KEYPAD_KEYMAP_MAX_SIZE];
 };
 
 static int stmpe_keypad_read_data(struct stmpe_keypad *keypad, u8 *data)
@@ -208,15 +222,14 @@ static int stmpe_keypad_altfunc_init(struct stmpe_keypad *keypad)
 
 static int stmpe_keypad_chip_init(struct stmpe_keypad *keypad)
 {
-	const struct stmpe_keypad_platform_data *plat = keypad->plat;
 	const struct stmpe_keypad_variant *variant = keypad->variant;
 	struct stmpe *stmpe = keypad->stmpe;
 	int ret;
 
-	if (plat->debounce_ms > STMPE_KEYPAD_MAX_DEBOUNCE)
+	if (keypad->debounce_ms > STMPE_KEYPAD_MAX_DEBOUNCE)
 		return -EINVAL;
 
-	if (plat->scan_count > STMPE_KEYPAD_MAX_SCAN_COUNT)
+	if (keypad->scan_count > STMPE_KEYPAD_MAX_SCAN_COUNT)
 		return -EINVAL;
 
 	ret = stmpe_enable(stmpe, STMPE_BLOCK_KEYPAD);
@@ -245,7 +258,7 @@ static int stmpe_keypad_chip_init(struct stmpe_keypad *keypad)
 
 	ret = stmpe_set_bits(stmpe, STMPE_KPC_CTRL_MSB,
 			     STMPE_KPC_CTRL_MSB_SCAN_COUNT,
-			     plat->scan_count << 4);
+			     keypad->scan_count << 4);
 	if (ret < 0)
 		return ret;
 
@@ -253,17 +266,18 @@ static int stmpe_keypad_chip_init(struct stmpe_keypad *keypad)
 			      STMPE_KPC_CTRL_LSB_SCAN |
 			      STMPE_KPC_CTRL_LSB_DEBOUNCE,
 			      STMPE_KPC_CTRL_LSB_SCAN |
-			      (plat->debounce_ms << 1));
+			      (keypad->debounce_ms << 1));
 }
 
-static void stmpe_keypad_fill_used_pins(struct stmpe_keypad *keypad)
+static void stmpe_keypad_fill_used_pins(struct stmpe_keypad *keypad,
+					u32 used_rows, u32 used_cols)
 {
 	int row, col;
 
-	for (row = 0; row < STMPE_KEYPAD_MAX_ROWS; row++) {
-		for (col = 0; col < STMPE_KEYPAD_MAX_COLS; col++) {
+	for (row = 0; row < used_rows; row++) {
+		for (col = 0; col < used_cols; col++) {
 			int code = MATRIX_SCAN_CODE(row, col,
-						STMPE_KEYPAD_ROW_SHIFT);
+						    STMPE_KEYPAD_ROW_SHIFT);
 			if (keypad->keymap[code] != KEY_RESERVED) {
 				keypad->rows |= 1 << row;
 				keypad->cols |= 1 << col;
@@ -272,51 +286,17 @@ static void stmpe_keypad_fill_used_pins(struct stmpe_keypad *keypad)
 	}
 }
 
-#ifdef CONFIG_OF
-static const struct stmpe_keypad_platform_data *
-stmpe_keypad_of_probe(struct device *dev)
-{
-	struct device_node *np = dev->of_node;
-	struct stmpe_keypad_platform_data *plat;
-
-	if (!np)
-		return ERR_PTR(-ENODEV);
-
-	plat = devm_kzalloc(dev, sizeof(*plat), GFP_KERNEL);
-	if (!plat)
-		return ERR_PTR(-ENOMEM);
-
-	of_property_read_u32(np, "debounce-interval", &plat->debounce_ms);
-	of_property_read_u32(np, "st,scan-count", &plat->scan_count);
-
-	plat->no_autorepeat = of_property_read_bool(np, "st,no-autorepeat");
-
-	return plat;
-}
-#else
-static inline const struct stmpe_keypad_platform_data *
-stmpe_keypad_of_probe(struct device *dev)
-{
-	return ERR_PTR(-EINVAL);
-}
-#endif
-
 static int stmpe_keypad_probe(struct platform_device *pdev)
 {
 	struct stmpe *stmpe = dev_get_drvdata(pdev->dev.parent);
-	const struct stmpe_keypad_platform_data *plat;
+	struct device_node *np = pdev->dev.of_node;
 	struct stmpe_keypad *keypad;
 	struct input_dev *input;
+	u32 rows;
+	u32 cols;
 	int error;
 	int irq;
 
-	plat = stmpe->pdata->keypad;
-	if (!plat) {
-		plat = stmpe_keypad_of_probe(&pdev->dev);
-		if (IS_ERR(plat))
-			return PTR_ERR(plat);
-	}
-
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
 		return irq;
@@ -326,6 +306,13 @@ static int stmpe_keypad_probe(struct platform_device *pdev)
 	if (!keypad)
 		return -ENOMEM;
 
+	keypad->stmpe = stmpe;
+	keypad->variant = &stmpe_keypad_variants[stmpe->partnum];
+
+	of_property_read_u32(np, "debounce-interval", &keypad->debounce_ms);
+	of_property_read_u32(np, "st,scan-count", &keypad->scan_count);
+	keypad->no_autorepeat = of_property_read_bool(np, "st,no-autorepeat");
+
 	input = devm_input_allocate_device(&pdev->dev);
 	if (!input)
 		return -ENOMEM;
@@ -334,23 +321,22 @@ static int stmpe_keypad_probe(struct platform_device *pdev)
 	input->id.bustype = BUS_I2C;
 	input->dev.parent = &pdev->dev;
 
-	error = matrix_keypad_build_keymap(plat->keymap_data, NULL,
-					   STMPE_KEYPAD_MAX_ROWS,
-					   STMPE_KEYPAD_MAX_COLS,
+	error = matrix_keypad_parse_of_params(&pdev->dev, &rows, &cols);
+	if (error)
+		return error;
+
+	error = matrix_keypad_build_keymap(NULL, NULL, rows, cols,
 					   keypad->keymap, input);
 	if (error)
 		return error;
 
 	input_set_capability(input, EV_MSC, MSC_SCAN);
-	if (!plat->no_autorepeat)
+	if (!keypad->no_autorepeat)
 		__set_bit(EV_REP, input->evbit);
 
-	stmpe_keypad_fill_used_pins(keypad);
+	stmpe_keypad_fill_used_pins(keypad, rows, cols);
 
-	keypad->stmpe = stmpe;
-	keypad->plat = plat;
 	keypad->input = input;
-	keypad->variant = &stmpe_keypad_variants[stmpe->partnum];
 
 	error = stmpe_keypad_chip_init(keypad);
 	if (error < 0)
diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h
index cc0deb72e46..f742b6717d5 100644
--- a/include/linux/mfd/stmpe.h
+++ b/include/linux/mfd/stmpe.h
@@ -115,24 +115,6 @@ extern int stmpe_set_altfunc(struct stmpe *stmpe, u32 pins,
 extern int stmpe_enable(struct stmpe *stmpe, unsigned int blocks);
 extern int stmpe_disable(struct stmpe *stmpe, unsigned int blocks);
 
-struct matrix_keymap_data;
-
-/**
- * struct stmpe_keypad_platform_data - STMPE keypad platform data
- * @keymap_data: key map table and size
- * @debounce_ms: debounce interval, in ms.  Maximum is
- *		 %STMPE_KEYPAD_MAX_DEBOUNCE.
- * @scan_count: number of key scanning cycles to confirm key data.
- *		Maximum is %STMPE_KEYPAD_MAX_SCAN_COUNT.
- * @no_autorepeat: disable key autorepeat
- */
-struct stmpe_keypad_platform_data {
-	const struct matrix_keymap_data *keymap_data;
-	unsigned int debounce_ms;
-	unsigned int scan_count;
-	bool no_autorepeat;
-};
-
 #define STMPE_GPIO_NOREQ_811_TOUCH	(0xf0)
 
 /**
@@ -201,7 +183,6 @@ struct stmpe_ts_platform_data {
  * @irq_gpio: gpio number over which irq will be requested (significant only if
  *	      irq_over_gpio is true)
  * @gpio: GPIO-specific platform data
- * @keypad: keypad-specific platform data
  * @ts: touchscreen-specific platform data
  */
 struct stmpe_platform_data {
@@ -214,7 +195,6 @@ struct stmpe_platform_data {
 	int autosleep_timeout;
 
 	struct stmpe_gpio_platform_data *gpio;
-	struct stmpe_keypad_platform_data *keypad;
 	struct stmpe_ts_platform_data *ts;
 };
 
-- 
cgit v1.2.3-70-g09d2


From cffe0a2b5a34c95a4dadc9ec7132690a5b0f6687 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Mon, 27 Oct 2014 13:21:42 +0800
Subject: x86, irq: Keep balance of IOAPIC pin reference count

To keep balance of IOAPIC pin reference count, we need to protect
pirq_enable_irq(), acpi_pci_irq_enable() and intel_mid_pci_irq_enable()
from reentrance. There are two cases which will cause reentrance.

The first case is caused by suspend/hibernation. If pcibios_disable_irq
is called during suspending/hibernating, we don't release the assigned
IRQ number, otherwise it may break the suspend/hibernation. So late when
pcibios_enable_irq is called during resume, we shouldn't allocate IRQ
number again.

The second case is that function acpi_pci_irq_enable() may be called
twice for PCI devices present at boot time as below:
1) pci_acpi_init()
	--> acpi_pci_irq_enable() if pci_routeirq is true
2) pci_enable_device()
	--> pcibios_enable_device()
		--> acpi_pci_irq_enable()
We can't kill kernel parameter pci_routeirq yet because it's still
needed for debugging purpose.

So flag irq_managed is introduced to track whether IRQ number is
assigned by OS and to protect pirq_enable_irq(), acpi_pci_irq_enable()
and intel_mid_pci_irq_enable() from reentrance.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Len Brown <lenb@kernel.org>
Link: http://lkml.kernel.org/r/1414387308-27148-13-git-send-email-jiang.liu@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/pci/intel_mid_pci.c | 10 +++++++++-
 arch/x86/pci/irq.c           |  7 ++++++-
 drivers/acpi/pci_irq.c       | 11 +++++++++--
 include/linux/pci.h          |  1 +
 4 files changed, 25 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index b9958c36407..44b9271580b 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -210,6 +210,9 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 {
 	int polarity;
 
+	if (dev->irq_managed && dev->irq > 0)
+		return 0;
+
 	if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER)
 		polarity = 0; /* active high */
 	else
@@ -224,13 +227,18 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 	if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC) < 0)
 		return -EBUSY;
 
+	dev->irq_managed = 1;
+
 	return 0;
 }
 
 static void intel_mid_pci_irq_disable(struct pci_dev *dev)
 {
-	if (!mp_should_keep_irq(&dev->dev) && dev->irq > 0)
+	if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed &&
+	    dev->irq > 0) {
 		mp_unmap_irq(dev->irq);
+		dev->irq_managed = 0;
+	}
 }
 
 struct pci_ops intel_mid_pci_ops = {
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index cb50e281d83..99884588a47 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1202,6 +1202,9 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			int irq;
 			struct io_apic_irq_attr irq_attr;
 
+			if (dev->irq_managed && dev->irq > 0)
+				return 0;
+
 			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
 						PCI_SLOT(dev->devfn),
 						pin - 1, &irq_attr);
@@ -1228,6 +1231,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			}
 			dev = temp_dev;
 			if (irq >= 0) {
+				dev->irq_managed = 1;
 				dev->irq = irq;
 				dev_info(&dev->dev, "PCI->APIC IRQ transform: "
 					 "INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
@@ -1269,8 +1273,9 @@ bool mp_should_keep_irq(struct device *dev)
 static void pirq_disable_irq(struct pci_dev *dev)
 {
 	if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
-	    dev->irq) {
+	    dev->irq_managed && dev->irq) {
 		mp_unmap_irq(dev->irq);
 		dev->irq = 0;
+		dev->irq_managed = 0;
 	}
 }
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 6e6b80eb0bb..5f1fdca65e5 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -413,6 +413,9 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		return 0;
 	}
 
+	if (dev->irq_managed && dev->irq > 0)
+		return 0;
+
 	entry = acpi_pci_irq_lookup(dev, pin);
 	if (!entry) {
 		/*
@@ -456,6 +459,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		return rc;
 	}
 	dev->irq = rc;
+	dev->irq_managed = 1;
 
 	if (link)
 		snprintf(link_desc, sizeof(link_desc), " -> Link[%s]", link);
@@ -478,7 +482,7 @@ void acpi_pci_irq_disable(struct pci_dev *dev)
 	u8 pin;
 
 	pin = dev->pin;
-	if (!pin)
+	if (!pin || !dev->irq_managed || dev->irq <= 0)
 		return;
 
 	/* Keep IOAPIC pin configuration when suspending */
@@ -506,6 +510,9 @@ void acpi_pci_irq_disable(struct pci_dev *dev)
 	 */
 
 	dev_dbg(&dev->dev, "PCI INT %c disabled\n", pin_name(pin));
-	if (gsi >= 0 && dev->irq > 0)
+	if (gsi >= 0) {
 		acpi_unregister_gsi(gsi);
+		dev->irq = 0;
+		dev->irq_managed = 0;
+	}
 }
diff --git a/include/linux/pci.h b/include/linux/pci.h
index a523cee3abb..c888c5e4e22 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -349,6 +349,7 @@ struct pci_dev {
 	unsigned int	__aer_firmware_first:1;
 	unsigned int	broken_intx_masking:1;
 	unsigned int	io_window_1k:1;	/* Intel P2P bridge 1K I/O windows */
+	unsigned int	irq_managed:1;
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 
-- 
cgit v1.2.3-70-g09d2


From e89900c9ad75a1b80e1f1f46ce9c9bb0e7ea1d96 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Mon, 27 Oct 2014 13:21:47 +0800
Subject: x86, irq: Introduce helper to check whether an IOAPIC has been
 registered

Introduce acpi_ioapic_registered() to check whether an IOAPIC has already
been registered, it will be used when enabling IOAPIC hotplug.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Acked-by: Pavel Machek <pavel@ucw.cz>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Len Brown <len.brown@intel.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Link: http://lkml.kernel.org/r/1414387308-27148-18-git-send-email-jiang.liu@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/io_apic.h |  1 +
 arch/x86/kernel/acpi/boot.c    | 22 ++++++++++++++++++++++
 arch/x86/kernel/apic/io_apic.c | 11 +++++++++++
 include/linux/acpi.h           |  1 +
 4 files changed, 35 insertions(+)

(limited to 'include')

diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index ce63cf34c93..0db2b7037e4 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -191,6 +191,7 @@ extern void mp_unmap_irq(int irq);
 extern int mp_register_ioapic(int id, u32 address, u32 gsi_base,
 			      struct ioapic_domain_cfg *cfg);
 extern int mp_unregister_ioapic(u32 gsi_base);
+extern int mp_ioapic_registered(u32 gsi_base);
 extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
 			    irq_hw_number_t hwirq);
 extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq);
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 5427d9b70f7..ddddaed9187 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -826,6 +826,28 @@ int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base)
 }
 EXPORT_SYMBOL(acpi_unregister_ioapic);
 
+/**
+ * acpi_ioapic_registered - Check whether IOAPIC assoicatied with @gsi_base
+ *			    has been registered
+ * @handle:	ACPI handle of the IOAPIC deivce
+ * @gsi_base:	GSI base associated with the IOAPIC
+ *
+ * Assume caller holds some type of lock to serialize acpi_ioapic_registered()
+ * with acpi_register_ioapic()/acpi_unregister_ioapic().
+ */
+int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base)
+{
+	int ret = 0;
+
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+	mutex_lock(&acpi_ioapic_lock);
+	ret  = mp_ioapic_registered(gsi_base);
+	mutex_unlock(&acpi_ioapic_lock);
+#endif
+
+	return ret;
+}
+
 static int __init acpi_parse_sbf(struct acpi_table_header *table)
 {
 	struct acpi_table_boot *sb;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 06a0a6ce675..1cedf410096 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -4026,6 +4026,17 @@ int mp_unregister_ioapic(u32 gsi_base)
 	return 0;
 }
 
+int mp_ioapic_registered(u32 gsi_base)
+{
+	int ioapic;
+
+	for_each_ioapic(ioapic)
+		if (ioapics[ioapic].gsi_config.gsi_base == gsi_base)
+			return 1;
+
+	return 0;
+}
+
 int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
 		     irq_hw_number_t hwirq)
 {
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 407a12f663e..a81dd437a53 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -148,6 +148,7 @@ int acpi_unmap_lsapic(int cpu);
 
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base);
 int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base);
+int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base);
 void acpi_irq_stats_init(void);
 extern u32 acpi_irq_handled;
 extern u32 acpi_irq_not_handled;
-- 
cgit v1.2.3-70-g09d2


From 5eea84f478537de769330079dc068414f9d417f4 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 16 Dec 2014 15:05:01 +0200
Subject: if_tun: add TUNSETVNETLE/TUNGETVNETLE

ifreq flags field is only 16 bit wide, so setting IFF_VNET_LE there has
no effect:
doesn't fit in two bytes.

The tests passed apparently because they have an even number of bugs,
all cancelling out.

Luckily we didn't release a kernel with this flag, so it's
not too late to fix this.

Add TUNSETVNETLE/TUNGETVNETLE to really achieve the purpose
of IFF_VNET_LE.

This has an added benefit that if we ever want a BE flag,
we won't have to deal with weird configurations like
setting both LE and BE at the same time.

IFF_VNET_LE will be dropped in a follow-up patch.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_tun.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 18b2403982f..274630caa27 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -48,6 +48,8 @@
 #define TUNSETQUEUE  _IOW('T', 217, int)
 #define TUNSETIFINDEX	_IOW('T', 218, unsigned int)
 #define TUNGETFILTER _IOR('T', 219, struct sock_fprog)
+#define TUNSETVNETLE _IOW('T', 220, int)
+#define TUNGETVNETLE _IOR('T', 221, int)
 
 /* TUNSETIFF ifr flags */
 #define IFF_TUN		0x0001
-- 
cgit v1.2.3-70-g09d2


From 9c6ab1931fd6198eab61d9d59aff9a1014637ace Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 16 Dec 2014 15:05:23 +0200
Subject: if_tun: drop broken IFF_VNET_LE

Everyone should use TUNSETVNETLE/TUNGETVNETLE instead.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_tun.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 274630caa27..50ae2433544 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -59,7 +59,6 @@
 #define IFF_ONE_QUEUE	0x2000
 #define IFF_VNET_HDR	0x4000
 #define IFF_TUN_EXCL	0x8000
-#define IFF_VNET_LE	0x10000
 #define IFF_MULTI_QUEUE 0x0100
 #define IFF_ATTACH_QUEUE 0x0200
 #define IFF_DETACH_QUEUE 0x0400
-- 
cgit v1.2.3-70-g09d2


From 6539c44d08ac2eea693b6163135169b9c8c18bb1 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 16 Dec 2014 14:30:09 -0500
Subject: net: Allow FIXED_PHY to be modular.

Otherwise we get things like:

warning: (NET_DSA_BCM_SF2 && BCMGENET && SYSTEMPORT) selects FIXED_PHY which has unmet direct dependencies (NETDEVICES && PHYLIB=y)

In order to make this work we have to rename fixed.c to fixed_phy.c
because the regulator drivers already have a module named "fixed.o".

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/Kconfig     |   4 +-
 drivers/net/phy/Makefile    |   2 +-
 drivers/net/phy/fixed.c     | 337 --------------------------------------------
 drivers/net/phy/fixed_phy.c | 337 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/phy_fixed.h   |   2 +-
 5 files changed, 341 insertions(+), 341 deletions(-)
 delete mode 100644 drivers/net/phy/fixed.c
 create mode 100644 drivers/net/phy/fixed_phy.c

(limited to 'include')

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index b4b0f804e84..a3c251b79f3 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -119,8 +119,8 @@ config MICREL_PHY
 	  Supports the KSZ9021, VSC8201, KS8001 PHYs.
 
 config FIXED_PHY
-	bool "Driver for MDIO Bus/PHY emulation with fixed speed/link PHYs"
-	depends on PHYLIB=y
+	tristate "Driver for MDIO Bus/PHY emulation with fixed speed/link PHYs"
+	depends on PHYLIB
 	---help---
 	  Adds the platform "fixed" MDIO Bus to cover the boards that use
 	  PHYs that are not connected to the real MDIO bus.
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index eb3b18b5978..501ea7699a2 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -17,7 +17,7 @@ obj-$(CONFIG_BCM87XX_PHY)	+= bcm87xx.o
 obj-$(CONFIG_ICPLUS_PHY)	+= icplus.o
 obj-$(CONFIG_REALTEK_PHY)	+= realtek.o
 obj-$(CONFIG_LSI_ET1011C_PHY)	+= et1011c.o
-obj-$(CONFIG_FIXED_PHY)		+= fixed.o
+obj-$(CONFIG_FIXED_PHY)		+= fixed_phy.o
 obj-$(CONFIG_MDIO_BITBANG)	+= mdio-bitbang.o
 obj-$(CONFIG_MDIO_GPIO)		+= mdio-gpio.o
 obj-$(CONFIG_NATIONAL_PHY)	+= national.o
diff --git a/drivers/net/phy/fixed.c b/drivers/net/phy/fixed.c
deleted file mode 100644
index 3ad0e6e16c3..00000000000
--- a/drivers/net/phy/fixed.c
+++ /dev/null
@@ -1,337 +0,0 @@
-/*
- * Fixed MDIO bus (MDIO bus emulation with fixed PHYs)
- *
- * Author: Vitaly Bordug <vbordug@ru.mvista.com>
- *         Anton Vorontsov <avorontsov@ru.mvista.com>
- *
- * Copyright (c) 2006-2007 MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/list.h>
-#include <linux/mii.h>
-#include <linux/phy.h>
-#include <linux/phy_fixed.h>
-#include <linux/err.h>
-#include <linux/slab.h>
-#include <linux/of.h>
-
-#define MII_REGS_NUM 29
-
-struct fixed_mdio_bus {
-	int irqs[PHY_MAX_ADDR];
-	struct mii_bus *mii_bus;
-	struct list_head phys;
-};
-
-struct fixed_phy {
-	int addr;
-	u16 regs[MII_REGS_NUM];
-	struct phy_device *phydev;
-	struct fixed_phy_status status;
-	int (*link_update)(struct net_device *, struct fixed_phy_status *);
-	struct list_head node;
-};
-
-static struct platform_device *pdev;
-static struct fixed_mdio_bus platform_fmb = {
-	.phys = LIST_HEAD_INIT(platform_fmb.phys),
-};
-
-static int fixed_phy_update_regs(struct fixed_phy *fp)
-{
-	u16 bmsr = BMSR_ANEGCAPABLE;
-	u16 bmcr = 0;
-	u16 lpagb = 0;
-	u16 lpa = 0;
-
-	if (fp->status.duplex) {
-		bmcr |= BMCR_FULLDPLX;
-
-		switch (fp->status.speed) {
-		case 1000:
-			bmsr |= BMSR_ESTATEN;
-			bmcr |= BMCR_SPEED1000;
-			lpagb |= LPA_1000FULL;
-			break;
-		case 100:
-			bmsr |= BMSR_100FULL;
-			bmcr |= BMCR_SPEED100;
-			lpa |= LPA_100FULL;
-			break;
-		case 10:
-			bmsr |= BMSR_10FULL;
-			lpa |= LPA_10FULL;
-			break;
-		default:
-			pr_warn("fixed phy: unknown speed\n");
-			return -EINVAL;
-		}
-	} else {
-		switch (fp->status.speed) {
-		case 1000:
-			bmsr |= BMSR_ESTATEN;
-			bmcr |= BMCR_SPEED1000;
-			lpagb |= LPA_1000HALF;
-			break;
-		case 100:
-			bmsr |= BMSR_100HALF;
-			bmcr |= BMCR_SPEED100;
-			lpa |= LPA_100HALF;
-			break;
-		case 10:
-			bmsr |= BMSR_10HALF;
-			lpa |= LPA_10HALF;
-			break;
-		default:
-			pr_warn("fixed phy: unknown speed\n");
-			return -EINVAL;
-		}
-	}
-
-	if (fp->status.link)
-		bmsr |= BMSR_LSTATUS | BMSR_ANEGCOMPLETE;
-
-	if (fp->status.pause)
-		lpa |= LPA_PAUSE_CAP;
-
-	if (fp->status.asym_pause)
-		lpa |= LPA_PAUSE_ASYM;
-
-	fp->regs[MII_PHYSID1] = 0;
-	fp->regs[MII_PHYSID2] = 0;
-
-	fp->regs[MII_BMSR] = bmsr;
-	fp->regs[MII_BMCR] = bmcr;
-	fp->regs[MII_LPA] = lpa;
-	fp->regs[MII_STAT1000] = lpagb;
-
-	return 0;
-}
-
-static int fixed_mdio_read(struct mii_bus *bus, int phy_addr, int reg_num)
-{
-	struct fixed_mdio_bus *fmb = bus->priv;
-	struct fixed_phy *fp;
-
-	if (reg_num >= MII_REGS_NUM)
-		return -1;
-
-	/* We do not support emulating Clause 45 over Clause 22 register reads
-	 * return an error instead of bogus data.
-	 */
-	switch (reg_num) {
-	case MII_MMD_CTRL:
-	case MII_MMD_DATA:
-		return -1;
-	default:
-		break;
-	}
-
-	list_for_each_entry(fp, &fmb->phys, node) {
-		if (fp->addr == phy_addr) {
-			/* Issue callback if user registered it. */
-			if (fp->link_update) {
-				fp->link_update(fp->phydev->attached_dev,
-						&fp->status);
-				fixed_phy_update_regs(fp);
-			}
-			return fp->regs[reg_num];
-		}
-	}
-
-	return 0xFFFF;
-}
-
-static int fixed_mdio_write(struct mii_bus *bus, int phy_addr, int reg_num,
-			    u16 val)
-{
-	return 0;
-}
-
-/*
- * If something weird is required to be done with link/speed,
- * network driver is able to assign a function to implement this.
- * May be useful for PHY's that need to be software-driven.
- */
-int fixed_phy_set_link_update(struct phy_device *phydev,
-			      int (*link_update)(struct net_device *,
-						 struct fixed_phy_status *))
-{
-	struct fixed_mdio_bus *fmb = &platform_fmb;
-	struct fixed_phy *fp;
-
-	if (!link_update || !phydev || !phydev->bus)
-		return -EINVAL;
-
-	list_for_each_entry(fp, &fmb->phys, node) {
-		if (fp->addr == phydev->addr) {
-			fp->link_update = link_update;
-			fp->phydev = phydev;
-			return 0;
-		}
-	}
-
-	return -ENOENT;
-}
-EXPORT_SYMBOL_GPL(fixed_phy_set_link_update);
-
-int fixed_phy_add(unsigned int irq, int phy_addr,
-		  struct fixed_phy_status *status)
-{
-	int ret;
-	struct fixed_mdio_bus *fmb = &platform_fmb;
-	struct fixed_phy *fp;
-
-	fp = kzalloc(sizeof(*fp), GFP_KERNEL);
-	if (!fp)
-		return -ENOMEM;
-
-	memset(fp->regs, 0xFF,  sizeof(fp->regs[0]) * MII_REGS_NUM);
-
-	fmb->irqs[phy_addr] = irq;
-
-	fp->addr = phy_addr;
-	fp->status = *status;
-
-	ret = fixed_phy_update_regs(fp);
-	if (ret)
-		goto err_regs;
-
-	list_add_tail(&fp->node, &fmb->phys);
-
-	return 0;
-
-err_regs:
-	kfree(fp);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(fixed_phy_add);
-
-void fixed_phy_del(int phy_addr)
-{
-	struct fixed_mdio_bus *fmb = &platform_fmb;
-	struct fixed_phy *fp, *tmp;
-
-	list_for_each_entry_safe(fp, tmp, &fmb->phys, node) {
-		if (fp->addr == phy_addr) {
-			list_del(&fp->node);
-			kfree(fp);
-			return;
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(fixed_phy_del);
-
-static int phy_fixed_addr;
-static DEFINE_SPINLOCK(phy_fixed_addr_lock);
-
-struct phy_device *fixed_phy_register(unsigned int irq,
-				      struct fixed_phy_status *status,
-				      struct device_node *np)
-{
-	struct fixed_mdio_bus *fmb = &platform_fmb;
-	struct phy_device *phy;
-	int phy_addr;
-	int ret;
-
-	/* Get the next available PHY address, up to PHY_MAX_ADDR */
-	spin_lock(&phy_fixed_addr_lock);
-	if (phy_fixed_addr == PHY_MAX_ADDR) {
-		spin_unlock(&phy_fixed_addr_lock);
-		return ERR_PTR(-ENOSPC);
-	}
-	phy_addr = phy_fixed_addr++;
-	spin_unlock(&phy_fixed_addr_lock);
-
-	ret = fixed_phy_add(PHY_POLL, phy_addr, status);
-	if (ret < 0)
-		return ERR_PTR(ret);
-
-	phy = get_phy_device(fmb->mii_bus, phy_addr, false);
-	if (!phy || IS_ERR(phy)) {
-		fixed_phy_del(phy_addr);
-		return ERR_PTR(-EINVAL);
-	}
-
-	of_node_get(np);
-	phy->dev.of_node = np;
-
-	ret = phy_device_register(phy);
-	if (ret) {
-		phy_device_free(phy);
-		of_node_put(np);
-		fixed_phy_del(phy_addr);
-		return ERR_PTR(ret);
-	}
-
-	return phy;
-}
-EXPORT_SYMBOL_GPL(fixed_phy_register);
-
-static int __init fixed_mdio_bus_init(void)
-{
-	struct fixed_mdio_bus *fmb = &platform_fmb;
-	int ret;
-
-	pdev = platform_device_register_simple("Fixed MDIO bus", 0, NULL, 0);
-	if (IS_ERR(pdev)) {
-		ret = PTR_ERR(pdev);
-		goto err_pdev;
-	}
-
-	fmb->mii_bus = mdiobus_alloc();
-	if (fmb->mii_bus == NULL) {
-		ret = -ENOMEM;
-		goto err_mdiobus_reg;
-	}
-
-	snprintf(fmb->mii_bus->id, MII_BUS_ID_SIZE, "fixed-0");
-	fmb->mii_bus->name = "Fixed MDIO Bus";
-	fmb->mii_bus->priv = fmb;
-	fmb->mii_bus->parent = &pdev->dev;
-	fmb->mii_bus->read = &fixed_mdio_read;
-	fmb->mii_bus->write = &fixed_mdio_write;
-	fmb->mii_bus->irq = fmb->irqs;
-
-	ret = mdiobus_register(fmb->mii_bus);
-	if (ret)
-		goto err_mdiobus_alloc;
-
-	return 0;
-
-err_mdiobus_alloc:
-	mdiobus_free(fmb->mii_bus);
-err_mdiobus_reg:
-	platform_device_unregister(pdev);
-err_pdev:
-	return ret;
-}
-module_init(fixed_mdio_bus_init);
-
-static void __exit fixed_mdio_bus_exit(void)
-{
-	struct fixed_mdio_bus *fmb = &platform_fmb;
-	struct fixed_phy *fp, *tmp;
-
-	mdiobus_unregister(fmb->mii_bus);
-	mdiobus_free(fmb->mii_bus);
-	platform_device_unregister(pdev);
-
-	list_for_each_entry_safe(fp, tmp, &fmb->phys, node) {
-		list_del(&fp->node);
-		kfree(fp);
-	}
-}
-module_exit(fixed_mdio_bus_exit);
-
-MODULE_DESCRIPTION("Fixed MDIO bus (MDIO bus emulation with fixed PHYs)");
-MODULE_AUTHOR("Vitaly Bordug");
-MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
new file mode 100644
index 00000000000..3ad0e6e16c3
--- /dev/null
+++ b/drivers/net/phy/fixed_phy.c
@@ -0,0 +1,337 @@
+/*
+ * Fixed MDIO bus (MDIO bus emulation with fixed PHYs)
+ *
+ * Author: Vitaly Bordug <vbordug@ru.mvista.com>
+ *         Anton Vorontsov <avorontsov@ru.mvista.com>
+ *
+ * Copyright (c) 2006-2007 MontaVista Software, Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/list.h>
+#include <linux/mii.h>
+#include <linux/phy.h>
+#include <linux/phy_fixed.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+
+#define MII_REGS_NUM 29
+
+struct fixed_mdio_bus {
+	int irqs[PHY_MAX_ADDR];
+	struct mii_bus *mii_bus;
+	struct list_head phys;
+};
+
+struct fixed_phy {
+	int addr;
+	u16 regs[MII_REGS_NUM];
+	struct phy_device *phydev;
+	struct fixed_phy_status status;
+	int (*link_update)(struct net_device *, struct fixed_phy_status *);
+	struct list_head node;
+};
+
+static struct platform_device *pdev;
+static struct fixed_mdio_bus platform_fmb = {
+	.phys = LIST_HEAD_INIT(platform_fmb.phys),
+};
+
+static int fixed_phy_update_regs(struct fixed_phy *fp)
+{
+	u16 bmsr = BMSR_ANEGCAPABLE;
+	u16 bmcr = 0;
+	u16 lpagb = 0;
+	u16 lpa = 0;
+
+	if (fp->status.duplex) {
+		bmcr |= BMCR_FULLDPLX;
+
+		switch (fp->status.speed) {
+		case 1000:
+			bmsr |= BMSR_ESTATEN;
+			bmcr |= BMCR_SPEED1000;
+			lpagb |= LPA_1000FULL;
+			break;
+		case 100:
+			bmsr |= BMSR_100FULL;
+			bmcr |= BMCR_SPEED100;
+			lpa |= LPA_100FULL;
+			break;
+		case 10:
+			bmsr |= BMSR_10FULL;
+			lpa |= LPA_10FULL;
+			break;
+		default:
+			pr_warn("fixed phy: unknown speed\n");
+			return -EINVAL;
+		}
+	} else {
+		switch (fp->status.speed) {
+		case 1000:
+			bmsr |= BMSR_ESTATEN;
+			bmcr |= BMCR_SPEED1000;
+			lpagb |= LPA_1000HALF;
+			break;
+		case 100:
+			bmsr |= BMSR_100HALF;
+			bmcr |= BMCR_SPEED100;
+			lpa |= LPA_100HALF;
+			break;
+		case 10:
+			bmsr |= BMSR_10HALF;
+			lpa |= LPA_10HALF;
+			break;
+		default:
+			pr_warn("fixed phy: unknown speed\n");
+			return -EINVAL;
+		}
+	}
+
+	if (fp->status.link)
+		bmsr |= BMSR_LSTATUS | BMSR_ANEGCOMPLETE;
+
+	if (fp->status.pause)
+		lpa |= LPA_PAUSE_CAP;
+
+	if (fp->status.asym_pause)
+		lpa |= LPA_PAUSE_ASYM;
+
+	fp->regs[MII_PHYSID1] = 0;
+	fp->regs[MII_PHYSID2] = 0;
+
+	fp->regs[MII_BMSR] = bmsr;
+	fp->regs[MII_BMCR] = bmcr;
+	fp->regs[MII_LPA] = lpa;
+	fp->regs[MII_STAT1000] = lpagb;
+
+	return 0;
+}
+
+static int fixed_mdio_read(struct mii_bus *bus, int phy_addr, int reg_num)
+{
+	struct fixed_mdio_bus *fmb = bus->priv;
+	struct fixed_phy *fp;
+
+	if (reg_num >= MII_REGS_NUM)
+		return -1;
+
+	/* We do not support emulating Clause 45 over Clause 22 register reads
+	 * return an error instead of bogus data.
+	 */
+	switch (reg_num) {
+	case MII_MMD_CTRL:
+	case MII_MMD_DATA:
+		return -1;
+	default:
+		break;
+	}
+
+	list_for_each_entry(fp, &fmb->phys, node) {
+		if (fp->addr == phy_addr) {
+			/* Issue callback if user registered it. */
+			if (fp->link_update) {
+				fp->link_update(fp->phydev->attached_dev,
+						&fp->status);
+				fixed_phy_update_regs(fp);
+			}
+			return fp->regs[reg_num];
+		}
+	}
+
+	return 0xFFFF;
+}
+
+static int fixed_mdio_write(struct mii_bus *bus, int phy_addr, int reg_num,
+			    u16 val)
+{
+	return 0;
+}
+
+/*
+ * If something weird is required to be done with link/speed,
+ * network driver is able to assign a function to implement this.
+ * May be useful for PHY's that need to be software-driven.
+ */
+int fixed_phy_set_link_update(struct phy_device *phydev,
+			      int (*link_update)(struct net_device *,
+						 struct fixed_phy_status *))
+{
+	struct fixed_mdio_bus *fmb = &platform_fmb;
+	struct fixed_phy *fp;
+
+	if (!link_update || !phydev || !phydev->bus)
+		return -EINVAL;
+
+	list_for_each_entry(fp, &fmb->phys, node) {
+		if (fp->addr == phydev->addr) {
+			fp->link_update = link_update;
+			fp->phydev = phydev;
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(fixed_phy_set_link_update);
+
+int fixed_phy_add(unsigned int irq, int phy_addr,
+		  struct fixed_phy_status *status)
+{
+	int ret;
+	struct fixed_mdio_bus *fmb = &platform_fmb;
+	struct fixed_phy *fp;
+
+	fp = kzalloc(sizeof(*fp), GFP_KERNEL);
+	if (!fp)
+		return -ENOMEM;
+
+	memset(fp->regs, 0xFF,  sizeof(fp->regs[0]) * MII_REGS_NUM);
+
+	fmb->irqs[phy_addr] = irq;
+
+	fp->addr = phy_addr;
+	fp->status = *status;
+
+	ret = fixed_phy_update_regs(fp);
+	if (ret)
+		goto err_regs;
+
+	list_add_tail(&fp->node, &fmb->phys);
+
+	return 0;
+
+err_regs:
+	kfree(fp);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(fixed_phy_add);
+
+void fixed_phy_del(int phy_addr)
+{
+	struct fixed_mdio_bus *fmb = &platform_fmb;
+	struct fixed_phy *fp, *tmp;
+
+	list_for_each_entry_safe(fp, tmp, &fmb->phys, node) {
+		if (fp->addr == phy_addr) {
+			list_del(&fp->node);
+			kfree(fp);
+			return;
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(fixed_phy_del);
+
+static int phy_fixed_addr;
+static DEFINE_SPINLOCK(phy_fixed_addr_lock);
+
+struct phy_device *fixed_phy_register(unsigned int irq,
+				      struct fixed_phy_status *status,
+				      struct device_node *np)
+{
+	struct fixed_mdio_bus *fmb = &platform_fmb;
+	struct phy_device *phy;
+	int phy_addr;
+	int ret;
+
+	/* Get the next available PHY address, up to PHY_MAX_ADDR */
+	spin_lock(&phy_fixed_addr_lock);
+	if (phy_fixed_addr == PHY_MAX_ADDR) {
+		spin_unlock(&phy_fixed_addr_lock);
+		return ERR_PTR(-ENOSPC);
+	}
+	phy_addr = phy_fixed_addr++;
+	spin_unlock(&phy_fixed_addr_lock);
+
+	ret = fixed_phy_add(PHY_POLL, phy_addr, status);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	phy = get_phy_device(fmb->mii_bus, phy_addr, false);
+	if (!phy || IS_ERR(phy)) {
+		fixed_phy_del(phy_addr);
+		return ERR_PTR(-EINVAL);
+	}
+
+	of_node_get(np);
+	phy->dev.of_node = np;
+
+	ret = phy_device_register(phy);
+	if (ret) {
+		phy_device_free(phy);
+		of_node_put(np);
+		fixed_phy_del(phy_addr);
+		return ERR_PTR(ret);
+	}
+
+	return phy;
+}
+EXPORT_SYMBOL_GPL(fixed_phy_register);
+
+static int __init fixed_mdio_bus_init(void)
+{
+	struct fixed_mdio_bus *fmb = &platform_fmb;
+	int ret;
+
+	pdev = platform_device_register_simple("Fixed MDIO bus", 0, NULL, 0);
+	if (IS_ERR(pdev)) {
+		ret = PTR_ERR(pdev);
+		goto err_pdev;
+	}
+
+	fmb->mii_bus = mdiobus_alloc();
+	if (fmb->mii_bus == NULL) {
+		ret = -ENOMEM;
+		goto err_mdiobus_reg;
+	}
+
+	snprintf(fmb->mii_bus->id, MII_BUS_ID_SIZE, "fixed-0");
+	fmb->mii_bus->name = "Fixed MDIO Bus";
+	fmb->mii_bus->priv = fmb;
+	fmb->mii_bus->parent = &pdev->dev;
+	fmb->mii_bus->read = &fixed_mdio_read;
+	fmb->mii_bus->write = &fixed_mdio_write;
+	fmb->mii_bus->irq = fmb->irqs;
+
+	ret = mdiobus_register(fmb->mii_bus);
+	if (ret)
+		goto err_mdiobus_alloc;
+
+	return 0;
+
+err_mdiobus_alloc:
+	mdiobus_free(fmb->mii_bus);
+err_mdiobus_reg:
+	platform_device_unregister(pdev);
+err_pdev:
+	return ret;
+}
+module_init(fixed_mdio_bus_init);
+
+static void __exit fixed_mdio_bus_exit(void)
+{
+	struct fixed_mdio_bus *fmb = &platform_fmb;
+	struct fixed_phy *fp, *tmp;
+
+	mdiobus_unregister(fmb->mii_bus);
+	mdiobus_free(fmb->mii_bus);
+	platform_device_unregister(pdev);
+
+	list_for_each_entry_safe(fp, tmp, &fmb->phys, node) {
+		list_del(&fp->node);
+		kfree(fp);
+	}
+}
+module_exit(fixed_mdio_bus_exit);
+
+MODULE_DESCRIPTION("Fixed MDIO bus (MDIO bus emulation with fixed PHYs)");
+MODULE_AUTHOR("Vitaly Bordug");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h
index f2ca1b45937..7e75bfe37cc 100644
--- a/include/linux/phy_fixed.h
+++ b/include/linux/phy_fixed.h
@@ -11,7 +11,7 @@ struct fixed_phy_status {
 
 struct device_node;
 
-#ifdef CONFIG_FIXED_PHY
+#if IS_ENABLED(CONFIG_FIXED_PHY)
 extern int fixed_phy_add(unsigned int irq, int phy_id,
 			 struct fixed_phy_status *status);
 extern struct phy_device *fixed_phy_register(unsigned int irq,
-- 
cgit v1.2.3-70-g09d2


From f2d27e4519e5373767815d2050293c628242e34f Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Fri, 5 Dec 2014 10:02:47 -0300
Subject: [media] v4l2-mediabus.h: use two __u16 instead of two __u32

The ycbcr_enc and quantization fields do not need a __u32. Switch to
two __u16 types, thus preserving alignment and avoiding holes in the
struct. This makes one more __u32 available for future expansion.

Suggested by Sakari Ailus.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/uapi/linux/v4l2-mediabus.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/v4l2-mediabus.h b/include/uapi/linux/v4l2-mediabus.h
index 5a86d8ede09..26db20647e6 100644
--- a/include/uapi/linux/v4l2-mediabus.h
+++ b/include/uapi/linux/v4l2-mediabus.h
@@ -31,9 +31,9 @@ struct v4l2_mbus_framefmt {
 	__u32			code;
 	__u32			field;
 	__u32			colorspace;
-	__u32			ycbcr_enc;
-	__u32			quantization;
-	__u32			reserved[5];
+	__u16			ycbcr_enc;
+	__u16			quantization;
+	__u32			reserved[6];
 };
 
 #ifndef __KERNEL__
-- 
cgit v1.2.3-70-g09d2


From 62c4cf97e82cf79446642e599d155884f600cf17 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Tue, 16 Dec 2014 01:52:08 -0500
Subject: cpuidle / ACPI: remove unused CPUIDLE_FLAG_TIME_INVALID

CPUIDLE_FLAG_TIME_INVALID is no longer checked
by menu or ladder cpuidle governors, so don't
bother setting or defining it.

It was originally invented to account for the fact that
acpi_safe_halt() enables interrupts to invoke HLT.
That would allow interrupt service routines to be included
in the last_idle duration measurements made in cpuidle_enter_state(),
potentially returning a duration much larger than reality.

But menu and ladder can gracefully handle erroneously large duration
intervals without checking for CPUIDLE_FLAG_TIME_INVALID.
Further, if they don't check CPUIDLE_FLAG_TIME_INVALID, they
can also benefit from the instances when the duration interval
is not erroneously large.

Signed-off-by: Len Brown <len.brown@intel.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/processor_idle.c | 2 --
 include/linux/cpuidle.h       | 3 ---
 2 files changed, 5 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 380b4b43f36..7afba40e350 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -985,8 +985,6 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr)
 		state->flags = 0;
 		switch (cx->type) {
 			case ACPI_STATE_C1:
-			if (cx->entry_method != ACPI_CSTATE_FFH)
-				state->flags |= CPUIDLE_FLAG_TIME_INVALID;
 
 			state->enter = acpi_idle_enter_c1;
 			state->enter_dead = acpi_idle_play_dead;
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index a07e087f54b..ab70f3bc44a 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -53,7 +53,6 @@ struct cpuidle_state {
 };
 
 /* Idle State Flags */
-#define CPUIDLE_FLAG_TIME_INVALID	(0x01) /* is residency time measurable? */
 #define CPUIDLE_FLAG_COUPLED	(0x02) /* state applies to multiple cpus */
 #define CPUIDLE_FLAG_TIMER_STOP (0x04)  /* timer is stopped on this state */
 
@@ -89,8 +88,6 @@ DECLARE_PER_CPU(struct cpuidle_device, cpuidle_dev);
 /**
  * cpuidle_get_last_residency - retrieves the last state's residency time
  * @dev: the target CPU
- *
- * NOTE: this value is invalid if CPUIDLE_FLAG_TIME_INVALID is set
  */
 static inline int cpuidle_get_last_residency(struct cpuidle_device *dev)
 {
-- 
cgit v1.2.3-70-g09d2


From 7496fcbe8a643097efc061160e1c3b65ee2fa350 Mon Sep 17 00:00:00 2001
From: Amit Daniel Kachhap <amit.daniel@samsung.com>
Date: Mon, 15 Dec 2014 09:08:59 +0530
Subject: PM / Domains: Export of_genpd_get_from_provider function

This function looks up a PM domain form the provider. This will be
useful to add parent/child domain relationship from the SoC specific
code. The caller of the function must make sure that PM domain provider
is already registered.

Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Amit Daniel Kachhap <amit.daniel@samsung.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 3 ++-
 include/linux/pm_domain.h   | 8 ++++++++
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 5d7b7548873..1bd119efaac 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2108,7 +2108,7 @@ EXPORT_SYMBOL_GPL(of_genpd_del_provider);
  * Returns a valid pointer to struct generic_pm_domain on success or ERR_PTR()
  * on failure.
  */
-static struct generic_pm_domain *of_genpd_get_from_provider(
+struct generic_pm_domain *of_genpd_get_from_provider(
 					struct of_phandle_args *genpdspec)
 {
 	struct generic_pm_domain *genpd = ERR_PTR(-ENOENT);
@@ -2128,6 +2128,7 @@ static struct generic_pm_domain *of_genpd_get_from_provider(
 
 	return genpd;
 }
+EXPORT_SYMBOL_GPL(of_genpd_get_from_provider);
 
 /**
  * genpd_dev_pm_detach - Detach a device from its PM domain.
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 1dd6c7f6416..ba7ca5468a7 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -275,6 +275,8 @@ typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args,
 int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
 			void *data);
 void of_genpd_del_provider(struct device_node *np);
+struct generic_pm_domain *of_genpd_get_from_provider(
+			struct of_phandle_args *genpdspec);
 
 struct generic_pm_domain *__of_genpd_xlate_simple(
 					struct of_phandle_args *genpdspec,
@@ -292,6 +294,12 @@ static inline int __of_genpd_add_provider(struct device_node *np,
 }
 static inline void of_genpd_del_provider(struct device_node *np) {}
 
+static inline struct generic_pm_domain *of_genpd_get_from_provider(
+			struct of_phandle_args *genpdspec)
+{
+	return NULL;
+}
+
 #define __of_genpd_xlate_simple		NULL
 #define __of_genpd_xlate_onecell	NULL
 
-- 
cgit v1.2.3-70-g09d2


From 777eda2c5b84d6f3543f4aecbf4cd1f29b222a81 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 17 Dec 2014 04:46:46 -0500
Subject: new helper: iter_is_iovec()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/uio.h | 5 +++++
 mm/filemap.c        | 2 +-
 mm/shmem.c          | 2 +-
 3 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/uio.h b/include/linux/uio.h
index a41e252396c..1c5e453f7ea 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -101,6 +101,11 @@ static inline size_t iov_iter_count(struct iov_iter *i)
 	return i->count;
 }
 
+static inline bool iter_is_iovec(struct iov_iter *i)
+{
+	return !(i->type & (ITER_BVEC | ITER_KVEC));
+}
+
 /*
  * Cap the iov_iter by given limit; note that the second argument is
  * *not* the new size - it's upper limit for such.  Passing it a value
diff --git a/mm/filemap.c b/mm/filemap.c
index e8905bc3cbd..bd8543c6508 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2464,7 +2464,7 @@ ssize_t generic_perform_write(struct file *file,
 	/*
 	 * Copies from kernel address space cannot fail (NFSD is a big user).
 	 */
-	if (segment_eq(get_fs(), KERNEL_DS))
+	if (!iter_is_iovec(i))
 		flags |= AOP_FLAG_UNINTERRUPTIBLE;
 
 	do {
diff --git a/mm/shmem.c b/mm/shmem.c
index 185836ba53e..73ba1df7c8b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1536,7 +1536,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	 * holes of a sparse file, we actually need to allocate those pages,
 	 * and even mark them dirty, so it cannot exceed the max_blocks limit.
 	 */
-	if (segment_eq(get_fs(), KERNEL_DS))
+	if (!iter_is_iovec(to))
 		sgp = SGP_DIRTY;
 
 	index = *ppos >> PAGE_CACHE_SHIFT;
-- 
cgit v1.2.3-70-g09d2


From 503ccc3fec4a56cdcfedc507cd1ea0d85e1fbfa2 Mon Sep 17 00:00:00 2001
From: Javi Merino <javi.merino@arm.com>
Date: Wed, 17 Dec 2014 11:11:24 +0000
Subject: thermal: cpu_cooling: return ERR_PTR() for !CPU_THERMAL or
 !THERMAL_OF

The documentation of of_cpufreq_cooling_register() and
cpufreq_cooling_register() say that they return ERR_PTR() on error.
Accordingly, callers only check for IS_ERR().  Therefore, make them
return ERR_PTR(-ENOSYS) as is customary in the kernel when config
options are missing.

Cc: Zhang Rui <rui.zhang@intel.com>
Cc: Eduardo Valentin <edubezval@gmail.com>
Signed-off-by: Javi Merino <javi.merino@arm.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 include/linux/cpu_cooling.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h
index c303d383def..bd955270d5a 100644
--- a/include/linux/cpu_cooling.h
+++ b/include/linux/cpu_cooling.h
@@ -50,7 +50,7 @@ static inline struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
 			    const struct cpumask *clip_cpus)
 {
-	return NULL;
+	return ERR_PTR(-ENOSYS);
 }
 #endif
 
@@ -65,13 +65,13 @@ unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq);
 static inline struct thermal_cooling_device *
 cpufreq_cooling_register(const struct cpumask *clip_cpus)
 {
-	return NULL;
+	return ERR_PTR(-ENOSYS);
 }
 static inline struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
 			    const struct cpumask *clip_cpus)
 {
-	return NULL;
+	return ERR_PTR(-ENOSYS);
 }
 static inline
 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
-- 
cgit v1.2.3-70-g09d2


From 50062175ffc844b8ff9664024c6416a37ad63c77 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 15 May 2014 05:06:42 -0400
Subject: vm_area_operations: kill ->migrate()

the only instance this method has ever grown was one in kernfs -
one that call ->migrate() of another vm_ops if it exists.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/kernfs/file.c        | 22 ----------------------
 include/linux/migrate.h | 10 ----------
 include/linux/mm.h      |  2 --
 mm/mempolicy.c          |  5 -----
 mm/migrate.c            | 21 ---------------------
 5 files changed, 60 deletions(-)

(limited to 'include')

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 697390ea47b..ddc9f9612f1 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -448,27 +448,6 @@ static struct mempolicy *kernfs_vma_get_policy(struct vm_area_struct *vma,
 	return pol;
 }
 
-static int kernfs_vma_migrate(struct vm_area_struct *vma,
-			      const nodemask_t *from, const nodemask_t *to,
-			      unsigned long flags)
-{
-	struct file *file = vma->vm_file;
-	struct kernfs_open_file *of = kernfs_of(file);
-	int ret;
-
-	if (!of->vm_ops)
-		return 0;
-
-	if (!kernfs_get_active(of->kn))
-		return 0;
-
-	ret = 0;
-	if (of->vm_ops->migrate)
-		ret = of->vm_ops->migrate(vma, from, to, flags);
-
-	kernfs_put_active(of->kn);
-	return ret;
-}
 #endif
 
 static const struct vm_operations_struct kernfs_vm_ops = {
@@ -479,7 +458,6 @@ static const struct vm_operations_struct kernfs_vm_ops = {
 #ifdef CONFIG_NUMA
 	.set_policy	= kernfs_vma_set_policy,
 	.get_policy	= kernfs_vma_get_policy,
-	.migrate	= kernfs_vma_migrate,
 #endif
 };
 
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 01aad3ed89e..fab9b32ace8 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -36,9 +36,6 @@ extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
 
 extern int migrate_prep(void);
 extern int migrate_prep_local(void);
-extern int migrate_vmas(struct mm_struct *mm,
-		const nodemask_t *from, const nodemask_t *to,
-		unsigned long flags);
 extern void migrate_page_copy(struct page *newpage, struct page *page);
 extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 				  struct page *newpage, struct page *page);
@@ -57,13 +54,6 @@ static inline int migrate_pages(struct list_head *l, new_page_t new,
 static inline int migrate_prep(void) { return -ENOSYS; }
 static inline int migrate_prep_local(void) { return -ENOSYS; }
 
-static inline int migrate_vmas(struct mm_struct *mm,
-		const nodemask_t *from, const nodemask_t *to,
-		unsigned long flags)
-{
-	return -ENOSYS;
-}
-
 static inline void migrate_page_copy(struct page *newpage,
 				     struct page *page) {}
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c0a67b894c4..f80d0194c9b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -286,8 +286,6 @@ struct vm_operations_struct {
 	 */
 	struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
 					unsigned long addr);
-	int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from,
-		const nodemask_t *to, unsigned long flags);
 #endif
 	/* called by sys_remap_file_pages() to populate non-linear mapping */
 	int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr,
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e58725aff7e..c1b273f1837 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1047,10 +1047,6 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 
 	down_read(&mm->mmap_sem);
 
-	err = migrate_vmas(mm, from, to, flags);
-	if (err)
-		goto out;
-
 	/*
 	 * Find a 'source' bit set in 'tmp' whose corresponding 'dest'
 	 * bit in 'to' is not also set in 'tmp'.  Clear the found 'source'
@@ -1130,7 +1126,6 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 		if (err < 0)
 			break;
 	}
-out:
 	up_read(&mm->mmap_sem);
 	if (err < 0)
 		return err;
diff --git a/mm/migrate.c b/mm/migrate.c
index b1d02127e1b..344cdf692fc 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1536,27 +1536,6 @@ out:
 	return err;
 }
 
-/*
- * Call migration functions in the vma_ops that may prepare
- * memory in a vm for migration. migration functions may perform
- * the migration for vmas that do not have an underlying page struct.
- */
-int migrate_vmas(struct mm_struct *mm, const nodemask_t *to,
-	const nodemask_t *from, unsigned long flags)
-{
- 	struct vm_area_struct *vma;
- 	int err = 0;
-
-	for (vma = mm->mmap; vma && !err; vma = vma->vm_next) {
- 		if (vma->vm_ops && vma->vm_ops->migrate) {
- 			err = vma->vm_ops->migrate(vma, to, from, flags);
- 			if (err)
- 				break;
- 		}
- 	}
- 	return err;
-}
-
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * Returns true if this is a safe migration target node for misplaced NUMA
-- 
cgit v1.2.3-70-g09d2


From a4d7b30df5d10bca92f8f359fc56fb8db0410f89 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Mon, 15 Dec 2014 14:47:18 +0100
Subject: drm/irq: Add drm_crtc_send_vblank_event()

This function is the KMS native variant of drm_send_vblank_event(). It
takes a struct drm_crtc * instead of a struct drm_device * and an index
of the CRTC.

Eventually the goal is to access vblank data through the CRTC only so
that the per-CRTC data can be moved to struct drm_crtc.

Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/drm/drm_irq.c | 19 +++++++++++++++++++
 include/drm/drmP.h        |  2 ++
 2 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index f5a5f18efa5..276301081aa 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -904,6 +904,8 @@ static void send_vblank_event(struct drm_device *dev,
  *
  * Updates sequence # and timestamp on event, and sends it to userspace.
  * Caller must hold event lock.
+ *
+ * This is the legacy version of drm_crtc_send_vblank_event().
  */
 void drm_send_vblank_event(struct drm_device *dev, int crtc,
 		struct drm_pending_vblank_event *e)
@@ -922,6 +924,23 @@ void drm_send_vblank_event(struct drm_device *dev, int crtc,
 }
 EXPORT_SYMBOL(drm_send_vblank_event);
 
+/**
+ * drm_crtc_send_vblank_event - helper to send vblank event after pageflip
+ * @crtc: the source CRTC of the vblank event
+ * @e: the event to send
+ *
+ * Updates sequence # and timestamp on event, and sends it to userspace.
+ * Caller must hold event lock.
+ *
+ * This is the native KMS version of drm_send_vblank_event().
+ */
+void drm_crtc_send_vblank_event(struct drm_crtc *crtc,
+				struct drm_pending_vblank_event *e)
+{
+	drm_send_vblank_event(crtc->dev, drm_crtc_index(crtc), e);
+}
+EXPORT_SYMBOL(drm_crtc_send_vblank_event);
+
 /**
  * drm_vblank_enable - enable the vblank interrupt on a CRTC
  * @dev: DRM device
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 8ba35c622e2..b78601bb7c4 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -905,6 +905,8 @@ extern u32 drm_vblank_count_and_time(struct drm_device *dev, int crtc,
 				     struct timeval *vblanktime);
 extern void drm_send_vblank_event(struct drm_device *dev, int crtc,
 				     struct drm_pending_vblank_event *e);
+extern void drm_crtc_send_vblank_event(struct drm_crtc *crtc,
+				       struct drm_pending_vblank_event *e);
 extern bool drm_handle_vblank(struct drm_device *dev, int crtc);
 extern int drm_vblank_get(struct drm_device *dev, int crtc);
 extern void drm_vblank_put(struct drm_device *dev, int crtc);
-- 
cgit v1.2.3-70-g09d2


From 115ebcd4fa90df8cfc80d2302b7afa8d39edb7e2 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Mon, 15 Dec 2014 14:47:18 +0100
Subject: drm/irq: Add drm_crtc_handle_vblank()

This function is the KMS native variant of drm_handle_vblank(). It takes
a struct drm_crtc * instead of a struct drm_device * and an index of the
CRTC.

Eventually the goal is to access vblank data through the CRTC only so
that the per-CRTC data can be moved to struct drm_crtc.

Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/drm/drm_irq.c | 20 ++++++++++++++++++++
 include/drm/drmP.h        |  1 +
 2 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 276301081aa..ece5a93a611 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -1613,6 +1613,8 @@ static void drm_handle_vblank_events(struct drm_device *dev, int crtc)
  *
  * Drivers should call this routine in their vblank interrupt handlers to
  * update the vblank counter and send any signals that may be pending.
+ *
+ * This is the legacy version of drm_crtc_handle_vblank().
  */
 bool drm_handle_vblank(struct drm_device *dev, int crtc)
 {
@@ -1689,3 +1691,21 @@ bool drm_handle_vblank(struct drm_device *dev, int crtc)
 	return true;
 }
 EXPORT_SYMBOL(drm_handle_vblank);
+
+/**
+ * drm_crtc_handle_vblank - handle a vblank event
+ * @crtc: where this event occurred
+ *
+ * Drivers should call this routine in their vblank interrupt handlers to
+ * update the vblank counter and send any signals that may be pending.
+ *
+ * This is the native KMS version of drm_handle_vblank().
+ *
+ * Returns:
+ * True if the event was successfully handled, false on failure.
+ */
+bool drm_crtc_handle_vblank(struct drm_crtc *crtc)
+{
+	return drm_handle_vblank(crtc->dev, drm_crtc_index(crtc));
+}
+EXPORT_SYMBOL(drm_crtc_handle_vblank);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index b78601bb7c4..f1f7f15ce0f 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -908,6 +908,7 @@ extern void drm_send_vblank_event(struct drm_device *dev, int crtc,
 extern void drm_crtc_send_vblank_event(struct drm_crtc *crtc,
 				       struct drm_pending_vblank_event *e);
 extern bool drm_handle_vblank(struct drm_device *dev, int crtc);
+extern bool drm_crtc_handle_vblank(struct drm_crtc *crtc);
 extern int drm_vblank_get(struct drm_device *dev, int crtc);
 extern void drm_vblank_put(struct drm_device *dev, int crtc);
 extern int drm_crtc_vblank_get(struct drm_crtc *crtc);
-- 
cgit v1.2.3-70-g09d2


From 96d3f91eb263d478777bb9bff1b1300e0c08c29e Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Tue, 16 Dec 2014 13:08:47 +0100
Subject: drm/irq: Add drm_crtc_vblank_count()

This function is the KMS native variant of drm_vblank_count(). It takes
a struct drm_crtc * instead of a struct drm_device * and an index of the
CRTC.

Eventually the goal is to access vblank data through the CRTC only so
that the per-CRTC data can be moved to struct drm_crtc.

Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/drm/drm_irq.c | 21 +++++++++++++++++++++
 include/drm/drmP.h        |  1 +
 2 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index ece5a93a611..4d79dad9d44 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -830,6 +830,8 @@ drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
  * vblank events since the system was booted, including lost events due to
  * modesetting activity.
  *
+ * This is the legacy version of drm_crtc_vblank_count().
+ *
  * Returns:
  * The software vblank counter.
  */
@@ -843,6 +845,25 @@ u32 drm_vblank_count(struct drm_device *dev, int crtc)
 }
 EXPORT_SYMBOL(drm_vblank_count);
 
+/**
+ * drm_crtc_vblank_count - retrieve "cooked" vblank counter value
+ * @crtc: which counter to retrieve
+ *
+ * Fetches the "cooked" vblank count value that represents the number of
+ * vblank events since the system was booted, including lost events due to
+ * modesetting activity.
+ *
+ * This is the native KMS version of drm_vblank_count().
+ *
+ * Returns:
+ * The software vblank counter.
+ */
+u32 drm_crtc_vblank_count(struct drm_crtc *crtc)
+{
+	return drm_vblank_count(crtc->dev, drm_crtc_index(crtc));
+}
+EXPORT_SYMBOL(drm_crtc_vblank_count);
+
 /**
  * drm_vblank_count_and_time - retrieve "cooked" vblank counter value
  * and the system timestamp corresponding to that vblank counter value.
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index f1f7f15ce0f..e1b2e8b98af 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -901,6 +901,7 @@ extern int drm_vblank_init(struct drm_device *dev, int num_crtcs);
 extern int drm_wait_vblank(struct drm_device *dev, void *data,
 			   struct drm_file *filp);
 extern u32 drm_vblank_count(struct drm_device *dev, int crtc);
+extern u32 drm_crtc_vblank_count(struct drm_crtc *crtc);
 extern u32 drm_vblank_count_and_time(struct drm_device *dev, int crtc,
 				     struct timeval *vblanktime);
 extern void drm_send_vblank_event(struct drm_device *dev, int crtc,
-- 
cgit v1.2.3-70-g09d2


From 9280be24dc9c7aaee230de3ed33f8357386de9a2 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Tue, 14 Oct 2014 10:33:35 +0800
Subject: ceph: fix file lock interruption

When a lock operation is interrupted, current code sends a unlock request to
MDS to undo the lock operation. This method does not work as expected because
the unlock request can drop locks that have already been acquired.

The fix is use the newly introduced CEPH_LOCK_FCNTL_INTR/CEPH_LOCK_FLOCK_INTR
requests to interrupt blocked file lock request. These requests do not drop
locks that have alread been acquired, they only interrupt blocked file lock
request.

Signed-off-by: Yan, Zheng <zyan@redhat.com>
---
 fs/ceph/locks.c              | 64 +++++++++++++++++++++++++++++++++++++-------
 fs/ceph/mds_client.c         |  2 ++
 fs/ceph/mds_client.h         |  6 +++++
 include/linux/ceph/ceph_fs.h |  7 +++--
 4 files changed, 67 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index fbc39c47bac..c35c5c614e3 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -9,6 +9,8 @@
 #include <linux/ceph/pagelist.h>
 
 static u64 lock_secret;
+static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
+                                         struct ceph_mds_request *req);
 
 static inline u64 secure_addr(void *addr)
 {
@@ -40,6 +42,9 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
 	u64 length = 0;
 	u64 owner;
 
+	if (operation != CEPH_MDS_OP_SETFILELOCK || cmd == CEPH_LOCK_UNLOCK)
+		wait = 0;
+
 	req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
@@ -68,6 +73,9 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
 	req->r_args.filelock_change.length = cpu_to_le64(length);
 	req->r_args.filelock_change.wait = wait;
 
+	if (wait)
+		req->r_wait_for_completion = ceph_lock_wait_for_completion;
+
 	err = ceph_mdsc_do_request(mdsc, inode, req);
 
 	if (operation == CEPH_MDS_OP_GETFILELOCK) {
@@ -96,6 +104,52 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
 	return err;
 }
 
+static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
+                                         struct ceph_mds_request *req)
+{
+	struct ceph_mds_request *intr_req;
+	struct inode *inode = req->r_inode;
+	int err, lock_type;
+
+	BUG_ON(req->r_op != CEPH_MDS_OP_SETFILELOCK);
+	if (req->r_args.filelock_change.rule == CEPH_LOCK_FCNTL)
+		lock_type = CEPH_LOCK_FCNTL_INTR;
+	else if (req->r_args.filelock_change.rule == CEPH_LOCK_FLOCK)
+		lock_type = CEPH_LOCK_FLOCK_INTR;
+	else
+		BUG_ON(1);
+	BUG_ON(req->r_args.filelock_change.type == CEPH_LOCK_UNLOCK);
+
+	err = wait_for_completion_interruptible(&req->r_completion);
+	if (!err)
+		return 0;
+
+	dout("ceph_lock_wait_for_completion: request %llu was interrupted\n",
+	     req->r_tid);
+
+	intr_req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETFILELOCK,
+					    USE_AUTH_MDS);
+	if (IS_ERR(intr_req))
+		return PTR_ERR(intr_req);
+
+	intr_req->r_inode = inode;
+	ihold(inode);
+	intr_req->r_num_caps = 1;
+
+	intr_req->r_args.filelock_change = req->r_args.filelock_change;
+	intr_req->r_args.filelock_change.rule = lock_type;
+	intr_req->r_args.filelock_change.type = CEPH_LOCK_UNLOCK;
+
+	err = ceph_mdsc_do_request(mdsc, inode, intr_req);
+	ceph_mdsc_put_request(intr_req);
+
+	if (err && err != -ERESTARTSYS)
+		return err;
+
+	wait_for_completion(&req->r_completion);
+	return 0;
+}
+
 /**
  * Attempt to set an fcntl lock.
  * For now, this just goes away to the server. Later it may be more awesome.
@@ -143,11 +197,6 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 				     err);
 			}
 		}
-
-	} else if (err == -ERESTARTSYS) {
-		dout("undoing lock\n");
-		ceph_lock_message(CEPH_LOCK_FCNTL, op, file,
-				  CEPH_LOCK_UNLOCK, 0, fl);
 	}
 	return err;
 }
@@ -186,11 +235,6 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 					  file, CEPH_LOCK_UNLOCK, 0, fl);
 			dout("got %d on flock_lock_file_wait, undid lock", err);
 		}
-	} else if (err == -ERESTARTSYS) {
-		dout("undoing lock\n");
-		ceph_lock_message(CEPH_LOCK_FLOCK,
-				  CEPH_MDS_OP_SETFILELOCK,
-				  file, CEPH_LOCK_UNLOCK, 0, fl);
 	}
 	return err;
 }
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a92d3f5c6c1..5a47ed760e6 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2208,6 +2208,8 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 			&req->r_completion, req->r_timeout);
 		if (err == 0)
 			err = -EIO;
+	} else if (req->r_wait_for_completion) {
+		err = req->r_wait_for_completion(mdsc, req);
 	} else {
 		err = wait_for_completion_killable(&req->r_completion);
 	}
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 3288359353e..230bda791d4 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -166,6 +166,11 @@ struct ceph_mds_client;
  */
 typedef void (*ceph_mds_request_callback_t) (struct ceph_mds_client *mdsc,
 					     struct ceph_mds_request *req);
+/*
+ * wait for request completion callback
+ */
+typedef int (*ceph_mds_request_wait_callback_t) (struct ceph_mds_client *mdsc,
+						 struct ceph_mds_request *req);
 
 /*
  * an in-flight mds request
@@ -239,6 +244,7 @@ struct ceph_mds_request {
 	struct completion r_completion;
 	struct completion r_safe_completion;
 	ceph_mds_request_callback_t r_callback;
+	ceph_mds_request_wait_callback_t r_wait_for_completion;
 	struct list_head  r_unsafe_item;  /* per-session unsafe list item */
 	bool		  r_got_unsafe, r_got_safe, r_got_result;
 
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 3c97d5e9b95..31d8b98b7f9 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -522,8 +522,11 @@ struct ceph_mds_reply_dirfrag {
 	__le32 dist[];
 } __attribute__ ((packed));
 
-#define CEPH_LOCK_FCNTL    1
-#define CEPH_LOCK_FLOCK    2
+#define CEPH_LOCK_FCNTL		1
+#define CEPH_LOCK_FLOCK		2
+#define CEPH_LOCK_FCNTL_INTR    3
+#define CEPH_LOCK_FLOCK_INTR    4
+
 
 #define CEPH_LOCK_SHARED   1
 #define CEPH_LOCK_EXCL     2
-- 
cgit v1.2.3-70-g09d2


From 4965fc38c460b274b2a1789e1165a25fb0409d7e Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@redhat.com>
Date: Thu, 23 Oct 2014 16:32:57 +0400
Subject: libceph: nuke ceph_kvfree()

Use kvfree() from linux/mm.h instead, which is identical.  Also fix the
ceph_buffer comment: we will allocate with kmalloc() up to 32k - the
value of PAGE_ALLOC_COSTLY_ORDER, but that really is just an
implementation detail so don't mention it at all.

Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
---
 include/linux/ceph/buffer.h  | 3 +--
 include/linux/ceph/libceph.h | 1 -
 net/ceph/buffer.c            | 4 ++--
 net/ceph/ceph_common.c       | 8 --------
 net/ceph/messenger.c         | 2 +-
 5 files changed, 4 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/buffer.h b/include/linux/ceph/buffer.h
index 07ad423cc37..07ca15e7610 100644
--- a/include/linux/ceph/buffer.h
+++ b/include/linux/ceph/buffer.h
@@ -10,8 +10,7 @@
 /*
  * a simple reference counted buffer.
  *
- * use kmalloc for small sizes (<= one page), vmalloc for larger
- * sizes.
+ * use kmalloc for smaller sizes, vmalloc for larger sizes.
  */
 struct ceph_buffer {
 	struct kref kref;
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 07bc359b88a..d293f7e3881 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -184,7 +184,6 @@ extern bool libceph_compatible(void *data);
 extern const char *ceph_msg_type_name(int type);
 extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid);
 extern void *ceph_kvmalloc(size_t size, gfp_t flags);
-extern void ceph_kvfree(const void *ptr);
 
 extern struct ceph_options *ceph_parse_options(char *options,
 			      const char *dev_name, const char *dev_name_end,
diff --git a/net/ceph/buffer.c b/net/ceph/buffer.c
index 621b5f65407..add5f921a0f 100644
--- a/net/ceph/buffer.c
+++ b/net/ceph/buffer.c
@@ -6,7 +6,7 @@
 
 #include <linux/ceph/buffer.h>
 #include <linux/ceph/decode.h>
-#include <linux/ceph/libceph.h> /* for ceph_kv{malloc,free} */
+#include <linux/ceph/libceph.h> /* for ceph_kvmalloc */
 
 struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp)
 {
@@ -35,7 +35,7 @@ void ceph_buffer_release(struct kref *kref)
 	struct ceph_buffer *b = container_of(kref, struct ceph_buffer, kref);
 
 	dout("buffer_release %p\n", b);
-	ceph_kvfree(b->vec.iov_base);
+	kvfree(b->vec.iov_base);
 	kfree(b);
 }
 EXPORT_SYMBOL(ceph_buffer_release);
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 58fbfe134f9..d361a274aee 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -184,14 +184,6 @@ void *ceph_kvmalloc(size_t size, gfp_t flags)
 	return __vmalloc(size, flags | __GFP_HIGHMEM, PAGE_KERNEL);
 }
 
-void ceph_kvfree(const void *ptr)
-{
-	if (is_vmalloc_addr(ptr))
-		vfree(ptr);
-	else
-		kfree(ptr);
-}
-
 
 static int parse_fsid(const char *str, struct ceph_fsid *fsid)
 {
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 8d1653caffd..863d07ab212 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -3288,7 +3288,7 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip)
 static void ceph_msg_free(struct ceph_msg *m)
 {
 	dout("%s %p\n", __func__, m);
-	ceph_kvfree(m->front.iov_base);
+	kvfree(m->front.iov_base);
 	kmem_cache_free(ceph_msg_cache, m);
 }
 
-- 
cgit v1.2.3-70-g09d2


From 33d07337962c7bbd2fd5cf7f1106735c9507fbe2 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Tue, 4 Nov 2014 16:33:37 +0800
Subject: libceph: message signature support

Signed-off-by: Yan, Zheng <zyan@redhat.com>
---
 fs/ceph/mds_client.c               | 16 +++++++++++
 include/linux/ceph/auth.h          | 26 +++++++++++++++++
 include/linux/ceph/ceph_features.h |  1 +
 include/linux/ceph/messenger.h     |  9 +++++-
 include/linux/ceph/msgr.h          |  8 ++++++
 net/ceph/auth_x.c                  | 58 ++++++++++++++++++++++++++++++++++++++
 net/ceph/messenger.c               | 32 +++++++++++++++++++--
 net/ceph/osd_client.c              | 16 +++++++++++
 8 files changed, 162 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index fc74617069a..9f00853f6d4 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3744,6 +3744,20 @@ static struct ceph_msg *mds_alloc_msg(struct ceph_connection *con,
 	return msg;
 }
 
+static int sign_message(struct ceph_connection *con, struct ceph_msg *msg)
+{
+       struct ceph_mds_session *s = con->private;
+       struct ceph_auth_handshake *auth = &s->s_auth;
+       return ceph_auth_sign_message(auth, msg);
+}
+
+static int check_message_signature(struct ceph_connection *con, struct ceph_msg *msg)
+{
+       struct ceph_mds_session *s = con->private;
+       struct ceph_auth_handshake *auth = &s->s_auth;
+       return ceph_auth_check_message_signature(auth, msg);
+}
+
 static const struct ceph_connection_operations mds_con_ops = {
 	.get = con_get,
 	.put = con_put,
@@ -3753,6 +3767,8 @@ static const struct ceph_connection_operations mds_con_ops = {
 	.invalidate_authorizer = invalidate_authorizer,
 	.peer_reset = peer_reset,
 	.alloc_msg = mds_alloc_msg,
+	.sign_message = sign_message,
+	.check_message_signature = check_message_signature,
 };
 
 /* eof */
diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h
index 5f338684413..260d78b587c 100644
--- a/include/linux/ceph/auth.h
+++ b/include/linux/ceph/auth.h
@@ -13,6 +13,7 @@
 
 struct ceph_auth_client;
 struct ceph_authorizer;
+struct ceph_msg;
 
 struct ceph_auth_handshake {
 	struct ceph_authorizer *authorizer;
@@ -20,6 +21,10 @@ struct ceph_auth_handshake {
 	size_t authorizer_buf_len;
 	void *authorizer_reply_buf;
 	size_t authorizer_reply_buf_len;
+	int (*sign_message)(struct ceph_auth_handshake *auth,
+			    struct ceph_msg *msg);
+	int (*check_message_signature)(struct ceph_auth_handshake *auth,
+				       struct ceph_msg *msg);
 };
 
 struct ceph_auth_client_ops {
@@ -66,6 +71,11 @@ struct ceph_auth_client_ops {
 	void (*reset)(struct ceph_auth_client *ac);
 
 	void (*destroy)(struct ceph_auth_client *ac);
+
+	int (*sign_message)(struct ceph_auth_handshake *auth,
+			    struct ceph_msg *msg);
+	int (*check_message_signature)(struct ceph_auth_handshake *auth,
+				       struct ceph_msg *msg);
 };
 
 struct ceph_auth_client {
@@ -113,4 +123,20 @@ extern int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac,
 extern void ceph_auth_invalidate_authorizer(struct ceph_auth_client *ac,
 					    int peer_type);
 
+static inline int ceph_auth_sign_message(struct ceph_auth_handshake *auth,
+					 struct ceph_msg *msg)
+{
+	if (auth->sign_message)
+		return auth->sign_message(auth, msg);
+	return 0;
+}
+
+static inline
+int ceph_auth_check_message_signature(struct ceph_auth_handshake *auth,
+				      struct ceph_msg *msg)
+{
+	if (auth->check_message_signature)
+		return auth->check_message_signature(auth, msg);
+	return 0;
+}
 #endif
diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index d12659ce550..71e05bbf8ce 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -84,6 +84,7 @@ static inline u64 ceph_sanitize_features(u64 features)
 	 CEPH_FEATURE_PGPOOL3 |			\
 	 CEPH_FEATURE_OSDENC |			\
 	 CEPH_FEATURE_CRUSH_TUNABLES |		\
+	 CEPH_FEATURE_MSG_AUTH |		\
 	 CEPH_FEATURE_CRUSH_TUNABLES2 |		\
 	 CEPH_FEATURE_REPLY_CREATE_INODE |	\
 	 CEPH_FEATURE_OSDHASHPSPOOL |		\
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 40ae58e3e9d..d9d396c1650 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -42,6 +42,10 @@ struct ceph_connection_operations {
 	struct ceph_msg * (*alloc_msg) (struct ceph_connection *con,
 					struct ceph_msg_header *hdr,
 					int *skip);
+	int (*sign_message) (struct ceph_connection *con, struct ceph_msg *msg);
+
+	int (*check_message_signature) (struct ceph_connection *con,
+					struct ceph_msg *msg);
 };
 
 /* use format string %s%d */
@@ -142,7 +146,10 @@ struct ceph_msg_data_cursor {
  */
 struct ceph_msg {
 	struct ceph_msg_header hdr;	/* header */
-	struct ceph_msg_footer footer;	/* footer */
+	union {
+		struct ceph_msg_footer footer;		/* footer */
+		struct ceph_msg_footer_old old_footer;	/* old format footer */
+	};
 	struct kvec front;              /* unaligned blobs of message */
 	struct ceph_buffer *middle;
 
diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h
index 3d94a73b5f3..cac4b28ac1c 100644
--- a/include/linux/ceph/msgr.h
+++ b/include/linux/ceph/msgr.h
@@ -164,13 +164,21 @@ struct ceph_msg_header {
 /*
  * follows data payload
  */
+struct ceph_msg_footer_old {
+	__le32 front_crc, middle_crc, data_crc;
+	__u8 flags;
+} __attribute__ ((packed));
+
 struct ceph_msg_footer {
 	__le32 front_crc, middle_crc, data_crc;
+	// sig holds the 64 bits of the digital signature for the message PLR
+	__le64  sig;
 	__u8 flags;
 } __attribute__ ((packed));
 
 #define CEPH_MSG_FOOTER_COMPLETE  (1<<0)   /* msg wasn't aborted */
 #define CEPH_MSG_FOOTER_NOCRC     (1<<1)   /* no data crc */
+#define CEPH_MSG_FOOTER_SIGNED	  (1<<2)   /* msg was signed */
 
 
 #endif
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index 77f3885c16b..15845814a0f 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -8,6 +8,7 @@
 
 #include <linux/ceph/decode.h>
 #include <linux/ceph/auth.h>
+#include <linux/ceph/messenger.h>
 
 #include "crypto.h"
 #include "auth_x.h"
@@ -567,6 +568,8 @@ static int ceph_x_create_authorizer(
 	auth->authorizer_buf_len = au->buf->vec.iov_len;
 	auth->authorizer_reply_buf = au->reply_buf;
 	auth->authorizer_reply_buf_len = sizeof (au->reply_buf);
+	auth->sign_message = ac->ops->sign_message;
+	auth->check_message_signature = ac->ops->check_message_signature;
 
 	return 0;
 }
@@ -667,6 +670,59 @@ static void ceph_x_invalidate_authorizer(struct ceph_auth_client *ac,
 		memset(&th->validity, 0, sizeof(th->validity));
 }
 
+static int calcu_signature(struct ceph_x_authorizer *au,
+			   struct ceph_msg *msg, __le64 *sig)
+{
+	int ret;
+	char tmp_enc[40];
+	__le32 tmp[5] = {
+		16u, msg->hdr.crc, msg->footer.front_crc,
+		msg->footer.middle_crc, msg->footer.data_crc,
+	};
+	ret = ceph_x_encrypt(&au->session_key, &tmp, sizeof(tmp),
+			     tmp_enc, sizeof(tmp_enc));
+	if (ret < 0)
+		return ret;
+	*sig = *(__le64*)(tmp_enc + 4);
+	return 0;
+}
+
+static int ceph_x_sign_message(struct ceph_auth_handshake *auth,
+			       struct ceph_msg *msg)
+{
+	int ret;
+	if (!auth->authorizer)
+		return 0;
+	ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer,
+			      msg, &msg->footer.sig);
+	if (ret < 0)
+		return ret;
+	msg->footer.flags |= CEPH_MSG_FOOTER_SIGNED;
+	return 0;
+}
+
+static int ceph_x_check_message_signature(struct ceph_auth_handshake *auth,
+					  struct ceph_msg *msg)
+{
+	__le64 sig_check;
+	int ret;
+
+	if (!auth->authorizer)
+		return 0;
+	ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer,
+			      msg, &sig_check);
+	if (ret < 0)
+		return ret;
+	if (sig_check == msg->footer.sig)
+		return 0;
+	if (msg->footer.flags & CEPH_MSG_FOOTER_SIGNED)
+		dout("ceph_x_check_message_signature %p has signature %llx "
+		     "expect %llx\n", msg, msg->footer.sig, sig_check);
+	else
+		dout("ceph_x_check_message_signature %p sender did not set "
+		     "CEPH_MSG_FOOTER_SIGNED\n", msg);
+	return -EBADMSG;
+}
 
 static const struct ceph_auth_client_ops ceph_x_ops = {
 	.name = "x",
@@ -681,6 +737,8 @@ static const struct ceph_auth_client_ops ceph_x_ops = {
 	.invalidate_authorizer = ceph_x_invalidate_authorizer,
 	.reset =  ceph_x_reset,
 	.destroy = ceph_x_destroy,
+	.sign_message = ceph_x_sign_message,
+	.check_message_signature = ceph_x_check_message_signature,
 };
 
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 863d07ab212..33a2f201e46 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1196,8 +1196,18 @@ static void prepare_write_message_footer(struct ceph_connection *con)
 	dout("prepare_write_message_footer %p\n", con);
 	con->out_kvec_is_msg = true;
 	con->out_kvec[v].iov_base = &m->footer;
-	con->out_kvec[v].iov_len = sizeof(m->footer);
-	con->out_kvec_bytes += sizeof(m->footer);
+	if (con->peer_features & CEPH_FEATURE_MSG_AUTH) {
+		if (con->ops->sign_message)
+			con->ops->sign_message(con, m);
+		else
+			m->footer.sig = 0;
+		con->out_kvec[v].iov_len = sizeof(m->footer);
+		con->out_kvec_bytes += sizeof(m->footer);
+	} else {
+		m->old_footer.flags = m->footer.flags;
+		con->out_kvec[v].iov_len = sizeof(m->old_footer);
+		con->out_kvec_bytes += sizeof(m->old_footer);
+	}
 	con->out_kvec_left++;
 	con->out_more = m->more_to_follow;
 	con->out_msg_done = true;
@@ -2249,6 +2259,7 @@ static int read_partial_message(struct ceph_connection *con)
 	int ret;
 	unsigned int front_len, middle_len, data_len;
 	bool do_datacrc = !con->msgr->nocrc;
+	bool need_sign = (con->peer_features & CEPH_FEATURE_MSG_AUTH);
 	u64 seq;
 	u32 crc;
 
@@ -2361,12 +2372,21 @@ static int read_partial_message(struct ceph_connection *con)
 	}
 
 	/* footer */
-	size = sizeof (m->footer);
+	if (need_sign)
+		size = sizeof(m->footer);
+	else
+		size = sizeof(m->old_footer);
+
 	end += size;
 	ret = read_partial(con, end, size, &m->footer);
 	if (ret <= 0)
 		return ret;
 
+	if (!need_sign) {
+		m->footer.flags = m->old_footer.flags;
+		m->footer.sig = 0;
+	}
+
 	dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n",
 	     m, front_len, m->footer.front_crc, middle_len,
 	     m->footer.middle_crc, data_len, m->footer.data_crc);
@@ -2390,6 +2410,12 @@ static int read_partial_message(struct ceph_connection *con)
 		return -EBADMSG;
 	}
 
+	if (need_sign && con->ops->check_message_signature &&
+	    con->ops->check_message_signature(con, m)) {
+		pr_err("read_partial_message %p signature check failed\n", m);
+		return -EBADMSG;
+	}
+
 	return 1; /* done! */
 }
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 6f164289bde..1f6c4055ada 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -2920,6 +2920,20 @@ static int invalidate_authorizer(struct ceph_connection *con)
 	return ceph_monc_validate_auth(&osdc->client->monc);
 }
 
+static int sign_message(struct ceph_connection *con, struct ceph_msg *msg)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_auth_handshake *auth = &o->o_auth;
+	return ceph_auth_sign_message(auth, msg);
+}
+
+static int check_message_signature(struct ceph_connection *con, struct ceph_msg *msg)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_auth_handshake *auth = &o->o_auth;
+	return ceph_auth_check_message_signature(auth, msg);
+}
+
 static const struct ceph_connection_operations osd_con_ops = {
 	.get = get_osd_con,
 	.put = put_osd_con,
@@ -2928,5 +2942,7 @@ static const struct ceph_connection_operations osd_con_ops = {
 	.verify_authorizer_reply = verify_authorizer_reply,
 	.invalidate_authorizer = invalidate_authorizer,
 	.alloc_msg = alloc_msg,
+	.sign_message = sign_message,
+	.check_message_signature = check_message_signature,
 	.fault = osd_reset,
 };
-- 
cgit v1.2.3-70-g09d2


From d4e1a4e0db439209672f9803f9f23b0123fb09aa Mon Sep 17 00:00:00 2001
From: John Spray <john.spray@redhat.com>
Date: Thu, 16 Oct 2014 12:05:34 +0100
Subject: libceph: update ceph_msg_header structure

2 bytes of what was reserved space is now used by userspace for the
compat_version field.

Signed-off-by: John Spray <john.spray@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
---
 include/linux/ceph/msgr.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h
index cac4b28ac1c..1c1887206ff 100644
--- a/include/linux/ceph/msgr.h
+++ b/include/linux/ceph/msgr.h
@@ -152,7 +152,8 @@ struct ceph_msg_header {
 			     receiver: mask against ~PAGE_MASK */
 
 	struct ceph_entity_name src;
-	__le32 reserved;
+	__le16 compat_version;
+	__le16 reserved;
 	__le32 crc;       /* header crc32c */
 } __attribute__ ((packed));
 
-- 
cgit v1.2.3-70-g09d2


From a3fc98005c9c6e4649d26bee0935a7048a95c9e6 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Tue, 11 Nov 2014 16:30:55 +0800
Subject: libceph: require cephx message signature by default

Signed-off-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@redhat.com>
---
 include/linux/ceph/libceph.h |  1 +
 net/ceph/ceph_common.c       | 13 +++++++++++++
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index d293f7e3881..8b11a79ca1c 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -29,6 +29,7 @@
 #define CEPH_OPT_NOSHARE          (1<<1) /* don't share client with other sbs */
 #define CEPH_OPT_MYIP             (1<<2) /* specified my ip */
 #define CEPH_OPT_NOCRC            (1<<3) /* no data crc on writes */
+#define CEPH_OPT_NOMSGAUTH	  (1<<4) /* not require cephx message signature */
 
 #define CEPH_OPT_DEFAULT   (0)
 
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index d361a274aee..5d5ab67f516 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -237,6 +237,8 @@ enum {
 	Opt_noshare,
 	Opt_crc,
 	Opt_nocrc,
+	Opt_cephx_require_signatures,
+	Opt_nocephx_require_signatures,
 };
 
 static match_table_t opt_tokens = {
@@ -255,6 +257,8 @@ static match_table_t opt_tokens = {
 	{Opt_noshare, "noshare"},
 	{Opt_crc, "crc"},
 	{Opt_nocrc, "nocrc"},
+	{Opt_cephx_require_signatures, "cephx_require_signatures"},
+	{Opt_nocephx_require_signatures, "nocephx_require_signatures"},
 	{-1, NULL}
 };
 
@@ -453,6 +457,12 @@ ceph_parse_options(char *options, const char *dev_name,
 		case Opt_nocrc:
 			opt->flags |= CEPH_OPT_NOCRC;
 			break;
+		case Opt_cephx_require_signatures:
+			opt->flags &= ~CEPH_OPT_NOMSGAUTH;
+			break;
+		case Opt_nocephx_require_signatures:
+			opt->flags |= CEPH_OPT_NOMSGAUTH;
+			break;
 
 		default:
 			BUG_ON(token);
@@ -496,6 +506,9 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
 	init_waitqueue_head(&client->auth_wq);
 	client->auth_err = 0;
 
+	if (!ceph_test_opt(client, NOMSGAUTH))
+		required_features |= CEPH_FEATURE_MSG_AUTH;
+
 	client->extra_mon_dispatch = NULL;
 	client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT |
 		supported_features;
-- 
cgit v1.2.3-70-g09d2


From d74b50bed037794135cb5a4e7418ad71d9848ce1 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Wed, 12 Nov 2014 14:00:43 +0800
Subject: libceph: add SETXATTR/CMPXATTR osd operations support

Signed-off-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@redhat.com>
---
 include/linux/ceph/osd_client.h | 10 +++++++++
 net/ceph/osd_client.c           | 47 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+)

(limited to 'include')

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 03aeb27fcc6..bcf9c2180ea 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -86,6 +86,13 @@ struct ceph_osd_req_op {
 			u32 truncate_seq;
 			struct ceph_osd_data osd_data;
 		} extent;
+		struct {
+			__le32 name_len;
+			__le32 value_len;
+			__u8 cmp_op;       /* CEPH_OSD_CMPXATTR_OP_* */
+			__u8 cmp_mode;     /* CEPH_OSD_CMPXATTR_MODE_* */
+			struct ceph_osd_data osd_data;
+		} xattr;
 		struct {
 			const char *class_name;
 			const char *method_name;
@@ -295,6 +302,9 @@ extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *,
 extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req,
 					unsigned int which, u16 opcode,
 					const char *class, const char *method);
+extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
+				 u16 opcode, const char *name, const void *value,
+				 size_t size, u8 cmp_op, u8 cmp_mode);
 extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
 					unsigned int which, u16 opcode,
 					u64 cookie, u64 version, int flag);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 1f6c4055ada..2b0555b36e4 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -292,6 +292,10 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
 		ceph_osd_data_release(&op->cls.request_data);
 		ceph_osd_data_release(&op->cls.response_data);
 		break;
+	case CEPH_OSD_OP_SETXATTR:
+	case CEPH_OSD_OP_CMPXATTR:
+		ceph_osd_data_release(&op->xattr.osd_data);
+		break;
 	default:
 		break;
 	}
@@ -545,6 +549,39 @@ void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
 }
 EXPORT_SYMBOL(osd_req_op_cls_init);
 
+int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
+			  u16 opcode, const char *name, const void *value,
+			  size_t size, u8 cmp_op, u8 cmp_mode)
+{
+	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which, opcode);
+	struct ceph_pagelist *pagelist;
+	size_t payload_len;
+
+	BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR);
+
+	pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS);
+	if (!pagelist)
+		return -ENOMEM;
+
+	ceph_pagelist_init(pagelist);
+
+	payload_len = strlen(name);
+	op->xattr.name_len = payload_len;
+	ceph_pagelist_append(pagelist, name, payload_len);
+
+	op->xattr.value_len = size;
+	ceph_pagelist_append(pagelist, value, size);
+	payload_len += size;
+
+	op->xattr.cmp_op = cmp_op;
+	op->xattr.cmp_mode = cmp_mode;
+
+	ceph_osd_data_pagelist_init(&op->xattr.osd_data, pagelist);
+	op->payload_len = payload_len;
+	return 0;
+}
+EXPORT_SYMBOL(osd_req_op_xattr_init);
+
 void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
 				unsigned int which, u16 opcode,
 				u64 cookie, u64 version, int flag)
@@ -676,6 +713,16 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
 		dst->alloc_hint.expected_write_size =
 		    cpu_to_le64(src->alloc_hint.expected_write_size);
 		break;
+	case CEPH_OSD_OP_SETXATTR:
+	case CEPH_OSD_OP_CMPXATTR:
+		dst->xattr.name_len = cpu_to_le32(src->xattr.name_len);
+		dst->xattr.value_len = cpu_to_le32(src->xattr.value_len);
+		dst->xattr.cmp_op = src->xattr.cmp_op;
+		dst->xattr.cmp_mode = src->xattr.cmp_mode;
+		osd_data = &src->xattr.osd_data;
+		ceph_osdc_msg_data_add(req->r_request, osd_data);
+		request_data_len = osd_data->pagelist->length;
+		break;
 	default:
 		pr_err("unsupported osd opcode %s\n",
 			ceph_osd_op_name(src->op));
-- 
cgit v1.2.3-70-g09d2


From 715e4cd405cfd67bd058e410b3e599bab2072645 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Thu, 13 Nov 2014 14:40:37 +0800
Subject: libceph: specify position of extent operation

allow specifying position of extent operation in multi-operations
osd request. This is required for cephfs to convert inline data to
normal data (compare xattr, then write object).

Signed-off-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@redhat.com>
---
 fs/ceph/addr.c                  |  9 ++++++---
 fs/ceph/file.c                  |  8 +++++---
 include/linux/ceph/osd_client.h |  3 ++-
 net/ceph/osd_client.c           | 19 ++++++-------------
 4 files changed, 19 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 18c06bbaf13..f2c7aa878aa 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -319,7 +319,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 	     off, len);
 	vino = ceph_vino(inode);
 	req = ceph_osdc_new_request(osdc, &ci->i_layout, vino, off, &len,
-				    1, CEPH_OSD_OP_READ,
+				    0, 1, CEPH_OSD_OP_READ,
 				    CEPH_OSD_FLAG_READ, NULL,
 				    ci->i_truncate_seq, ci->i_truncate_size,
 				    false);
@@ -750,7 +750,6 @@ retry:
 	last_snapc = snapc;
 
 	while (!done && index <= end) {
-		int num_ops = do_sync ? 2 : 1;
 		unsigned i;
 		int first;
 		pgoff_t next;
@@ -850,7 +849,8 @@ get_more_pages:
 				len = wsize;
 				req = ceph_osdc_new_request(&fsc->client->osdc,
 							&ci->i_layout, vino,
-							offset, &len, num_ops,
+							offset, &len, 0,
+							do_sync ? 2 : 1,
 							CEPH_OSD_OP_WRITE,
 							CEPH_OSD_FLAG_WRITE |
 							CEPH_OSD_FLAG_ONDISK,
@@ -862,6 +862,9 @@ get_more_pages:
 					break;
 				}
 
+				if (do_sync)
+					osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC);
+
 				req->r_callback = writepages_finish;
 				req->r_inode = inode;
 
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d7e0da8366e..c03ac4c4bcd 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -598,7 +598,7 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
 		snapc = ci->i_snap_realm->cached_context;
 		vino = ceph_vino(inode);
 		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
-					    vino, pos, &len,
+					    vino, pos, &len, 0,
 					    2,/*include a 'startsync' command*/
 					    CEPH_OSD_OP_WRITE, flags, snapc,
 					    ci->i_truncate_seq,
@@ -609,6 +609,8 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
 			break;
 		}
 
+		osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC);
+
 		n = iov_iter_get_pages_alloc(from, &pages, len, &start);
 		if (unlikely(n < 0)) {
 			ret = n;
@@ -713,7 +715,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
 		snapc = ci->i_snap_realm->cached_context;
 		vino = ceph_vino(inode);
 		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
-					    vino, pos, &len, 1,
+					    vino, pos, &len, 0, 1,
 					    CEPH_OSD_OP_WRITE, flags, snapc,
 					    ci->i_truncate_seq,
 					    ci->i_truncate_size,
@@ -1111,7 +1113,7 @@ static int ceph_zero_partial_object(struct inode *inode,
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 					ceph_vino(inode),
 					offset, length,
-					1, op,
+					0, 1, op,
 					CEPH_OSD_FLAG_WRITE |
 					CEPH_OSD_FLAG_ONDISK,
 					NULL, 0, 0, false);
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index bcf9c2180ea..5d86416d35f 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -328,7 +328,8 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
 				      struct ceph_file_layout *layout,
 				      struct ceph_vino vino,
 				      u64 offset, u64 *len,
-				      int num_ops, int opcode, int flags,
+				      unsigned int which, int num_ops,
+				      int opcode, int flags,
 				      struct ceph_snap_context *snapc,
 				      u32 truncate_seq, u64 truncate_size,
 				      bool use_mempool);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index af1b3ee195e..53299c7b0ca 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -753,7 +753,8 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
 struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 					       struct ceph_file_layout *layout,
 					       struct ceph_vino vino,
-					       u64 off, u64 *plen, int num_ops,
+					       u64 off, u64 *plen,
+					       unsigned int which, int num_ops,
 					       int opcode, int flags,
 					       struct ceph_snap_context *snapc,
 					       u32 truncate_seq,
@@ -785,7 +786,7 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 	}
 
 	if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) {
-		osd_req_op_init(req, 0, opcode);
+		osd_req_op_init(req, which, opcode);
 	} else {
 		u32 object_size = le32_to_cpu(layout->fl_object_size);
 		u32 object_base = off - objoff;
@@ -798,17 +799,9 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 					truncate_size = object_size;
 			}
 		}
-
-		osd_req_op_extent_init(req, 0, opcode, objoff, objlen,
+		osd_req_op_extent_init(req, which, opcode, objoff, objlen,
 				       truncate_size, truncate_seq);
 	}
-	/*
-	 * A second op in the ops array means the caller wants to
-	 * also issue a include a 'startsync' command so that the
-	 * osd will flush data quickly.
-	 */
-	if (num_ops > 1)
-		osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC);
 
 	req->r_base_oloc.pool = ceph_file_layout_pg_pool(*layout);
 
@@ -2675,7 +2668,7 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
 
 	dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino,
 	     vino.snap, off, *plen);
-	req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 1,
+	req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 0, 1,
 				    CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
 				    NULL, truncate_seq, truncate_size,
 				    false);
@@ -2718,7 +2711,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
 	int page_align = off & ~PAGE_MASK;
 
 	BUG_ON(vino.snap != CEPH_NOSNAP);	/* snapshots aren't writeable */
-	req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 1,
+	req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 0, 1,
 				    CEPH_OSD_OP_WRITE,
 				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
 				    snapc, truncate_seq, truncate_size,
-- 
cgit v1.2.3-70-g09d2


From 31c542a199d79f0f402c2f3e04229464510d47ec Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Fri, 14 Nov 2014 21:41:55 +0800
Subject: ceph: add inline data to pagecache

Request reply and cap message can contain inline data. add inline data
to the page cache if there is Fc cap.

Signed-off-by: Yan, Zheng <zyan@redhat.com>
---
 fs/ceph/addr.c               | 43 +++++++++++++++++++++++++++++++++++++++++++
 fs/ceph/caps.c               | 11 +++++++++++
 fs/ceph/inode.c              | 16 ++++++++++++++++
 fs/ceph/super.h              |  5 ++++-
 fs/ceph/super.h.rej          | 10 ++++++++++
 include/linux/ceph/ceph_fs.h |  1 +
 6 files changed, 85 insertions(+), 1 deletion(-)
 create mode 100644 fs/ceph/super.h.rej

(limited to 'include')

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index f2c7aa878aa..4a3f55f27ab 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1318,6 +1318,49 @@ out:
 	return ret;
 }
 
+void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
+			   char	*data, size_t len)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct page *page;
+
+	if (locked_page) {
+		page = locked_page;
+	} else {
+		if (i_size_read(inode) == 0)
+			return;
+		page = find_or_create_page(mapping, 0,
+					   mapping_gfp_mask(mapping) & ~__GFP_FS);
+		if (!page)
+			return;
+		if (PageUptodate(page)) {
+			unlock_page(page);
+			page_cache_release(page);
+			return;
+		}
+	}
+
+	dout("fill_inline_data %p %llx.%llx len %lu locked_page %p\n",
+	     inode, ceph_vinop(inode), len, locked_page);
+
+	if (len > 0) {
+		void *kaddr = kmap_atomic(page);
+		memcpy(kaddr, data, len);
+		kunmap_atomic(kaddr);
+	}
+
+	if (page != locked_page) {
+		if (len < PAGE_CACHE_SIZE)
+			zero_user_segment(page, len, PAGE_CACHE_SIZE);
+		else
+			flush_dcache_page(page);
+
+		SetPageUptodate(page);
+		unlock_page(page);
+		page_cache_release(page);
+	}
+}
+
 static struct vm_operations_struct ceph_vmops = {
 	.fault		= ceph_filemap_fault,
 	.page_mkwrite	= ceph_page_mkwrite,
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index b88ae601f30..6372eb9ce49 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2405,6 +2405,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	bool queue_invalidate = false;
 	bool queue_revalidate = false;
 	bool deleted_inode = false;
+	bool fill_inline = false;
 
 	dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
 	     inode, cap, mds, seq, ceph_cap_string(newcaps));
@@ -2578,6 +2579,13 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	}
 	BUG_ON(cap->issued & ~cap->implemented);
 
+	if (inline_version > 0 && inline_version >= ci->i_inline_version) {
+		ci->i_inline_version = inline_version;
+		if (ci->i_inline_version != CEPH_INLINE_NONE &&
+		    (newcaps & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)))
+			fill_inline = true;
+	}
+
 	spin_unlock(&ci->i_ceph_lock);
 
 	if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
@@ -2591,6 +2599,9 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 			wake = true;
 	}
 
+	if (fill_inline)
+		ceph_fill_inline_data(inode, NULL, inline_data, inline_len);
+
 	if (queue_trunc) {
 		ceph_queue_vmtruncate(inode);
 		ceph_queue_revalidate(inode);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 72607c17e6f..feea6a8f88a 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -387,6 +387,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	spin_lock_init(&ci->i_ceph_lock);
 
 	ci->i_version = 0;
+	ci->i_inline_version = 0;
 	ci->i_time_warp_seq = 0;
 	ci->i_ceph_flags = 0;
 	ci->i_ordered_count = 0;
@@ -676,6 +677,7 @@ static int fill_inode(struct inode *inode,
 	bool wake = false;
 	bool queue_trunc = false;
 	bool new_version = false;
+	bool fill_inline = false;
 
 	dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
 	     inode, ceph_vinop(inode), le64_to_cpu(info->version),
@@ -875,8 +877,22 @@ static int fill_inode(struct inode *inode,
 			   ceph_vinop(inode));
 		__ceph_get_fmode(ci, cap_fmode);
 	}
+
+	if (iinfo->inline_version > 0 &&
+	    iinfo->inline_version >= ci->i_inline_version) {
+		int cache_caps = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
+		ci->i_inline_version = iinfo->inline_version;
+		if (ci->i_inline_version != CEPH_INLINE_NONE &&
+		    (le32_to_cpu(info->cap.caps) & cache_caps))
+			fill_inline = true;
+	}
+
 	spin_unlock(&ci->i_ceph_lock);
 
+	if (fill_inline)
+		ceph_fill_inline_data(inode, NULL,
+				      iinfo->inline_data, iinfo->inline_len);
+
 	if (wake)
 		wake_up_all(&ci->i_cap_wq);
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index fc1c8255dea..b0de9162758 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -253,6 +253,7 @@ struct ceph_inode_info {
 	spinlock_t i_ceph_lock;
 
 	u64 i_version;
+	u64 i_inline_version;
 	u32 i_time_warp_seq;
 
 	unsigned i_ceph_flags;
@@ -858,7 +859,7 @@ extern int ceph_encode_dentry_release(void **p, struct dentry *dn,
 				      int mds, int drop, int unless);
 
 extern int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
-			 int *got, loff_t endoff);
+			 loff_t endoff, int *got, struct page **pinned_page);
 
 /* for counting open files by mode */
 static inline void __ceph_get_fmode(struct ceph_inode_info *ci, int mode)
@@ -880,6 +881,8 @@ extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 			    struct file *file, unsigned flags, umode_t mode,
 			    int *opened);
 extern int ceph_release(struct inode *inode, struct file *filp);
+extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
+				  char *data, size_t len);
 
 /* dir.c */
 extern const struct file_operations ceph_dir_fops;
diff --git a/fs/ceph/super.h.rej b/fs/ceph/super.h.rej
new file mode 100644
index 00000000000..88fe3dfadb2
--- /dev/null
+++ b/fs/ceph/super.h.rej
@@ -0,0 +1,10 @@
+--- fs/ceph/super.h
++++ fs/ceph/super.h
+@@ -254,6 +255,7 @@
+	spinlock_t i_ceph_lock;
+
+	u64 i_version;
++	u64 i_inline_version;
+	u32 i_time_warp_seq;
+
+	unsigned i_ceph_flags;
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 31d8b98b7f9..2d4acfa2c7b 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -552,6 +552,7 @@ struct ceph_filelock {
 
 int ceph_flags_to_mode(int flags);
 
+#define CEPH_INLINE_NONE	((__u64)-1)
 
 /* capability bits */
 #define CEPH_CAP_PIN         1  /* no specific capabilities beyond the pin */
-- 
cgit v1.2.3-70-g09d2


From 01deead041e03c9a6b4e1b2dd165dee4cced6112 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Fri, 14 Nov 2014 21:56:29 +0800
Subject: ceph: use getattr request to fetch inline data

Add a new parameter 'locked_page' to ceph_do_getattr(). If inline data
in getattr reply will be copied to the page.

Signed-off-by: Yan, Zheng <zyan@redhat.com>
---
 fs/ceph/inode.c              | 34 +++++++++++++++++++++++++---------
 fs/ceph/mds_client.h         |  1 +
 fs/ceph/super.h              |  7 ++++++-
 include/linux/ceph/ceph_fs.h |  2 ++
 4 files changed, 34 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index feea6a8f88a..0bdabd1bff8 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -659,7 +659,7 @@ void ceph_fill_file_time(struct inode *inode, int issued,
  * Populate an inode based on info from mds.  May be called on new or
  * existing inodes.
  */
-static int fill_inode(struct inode *inode,
+static int fill_inode(struct inode *inode, struct page *locked_page,
 		      struct ceph_mds_reply_info_in *iinfo,
 		      struct ceph_mds_reply_dirfrag *dirinfo,
 		      struct ceph_mds_session *session,
@@ -883,14 +883,15 @@ static int fill_inode(struct inode *inode,
 		int cache_caps = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
 		ci->i_inline_version = iinfo->inline_version;
 		if (ci->i_inline_version != CEPH_INLINE_NONE &&
-		    (le32_to_cpu(info->cap.caps) & cache_caps))
+		    (locked_page ||
+		     (le32_to_cpu(info->cap.caps) & cache_caps)))
 			fill_inline = true;
 	}
 
 	spin_unlock(&ci->i_ceph_lock);
 
 	if (fill_inline)
-		ceph_fill_inline_data(inode, NULL,
+		ceph_fill_inline_data(inode, locked_page,
 				      iinfo->inline_data, iinfo->inline_len);
 
 	if (wake)
@@ -1080,7 +1081,8 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 		struct inode *dir = req->r_locked_dir;
 
 		if (dir) {
-			err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag,
+			err = fill_inode(dir, NULL,
+					 &rinfo->diri, rinfo->dirfrag,
 					 session, req->r_request_started, -1,
 					 &req->r_caps_reservation);
 			if (err < 0)
@@ -1150,7 +1152,7 @@ retry_lookup:
 		}
 		req->r_target_inode = in;
 
-		err = fill_inode(in, &rinfo->targeti, NULL,
+		err = fill_inode(in, req->r_locked_page, &rinfo->targeti, NULL,
 				session, req->r_request_started,
 				(!req->r_aborted && rinfo->head->result == 0) ?
 				req->r_fmode : -1,
@@ -1321,7 +1323,7 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
 			dout("new_inode badness got %d\n", err);
 			continue;
 		}
-		rc = fill_inode(in, &rinfo->dir_in[i], NULL, session,
+		rc = fill_inode(in, NULL, &rinfo->dir_in[i], NULL, session,
 				req->r_request_started, -1,
 				&req->r_caps_reservation);
 		if (rc < 0) {
@@ -1437,7 +1439,7 @@ retry_lookup:
 			}
 		}
 
-		if (fill_inode(in, &rinfo->dir_in[i], NULL, session,
+		if (fill_inode(in, NULL, &rinfo->dir_in[i], NULL, session,
 			       req->r_request_started, -1,
 			       &req->r_caps_reservation) < 0) {
 			pr_err("fill_inode badness on %p\n", in);
@@ -1920,7 +1922,8 @@ out_put:
  * Verify that we have a lease on the given mask.  If not,
  * do a getattr against an mds.
  */
-int ceph_do_getattr(struct inode *inode, int mask, bool force)
+int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
+		      int mask, bool force)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -1932,7 +1935,8 @@ int ceph_do_getattr(struct inode *inode, int mask, bool force)
 		return 0;
 	}
 
-	dout("do_getattr inode %p mask %s mode 0%o\n", inode, ceph_cap_string(mask), inode->i_mode);
+	dout("do_getattr inode %p mask %s mode 0%o\n",
+	     inode, ceph_cap_string(mask), inode->i_mode);
 	if (!force && ceph_caps_issued_mask(ceph_inode(inode), mask, 1))
 		return 0;
 
@@ -1943,7 +1947,19 @@ int ceph_do_getattr(struct inode *inode, int mask, bool force)
 	ihold(inode);
 	req->r_num_caps = 1;
 	req->r_args.getattr.mask = cpu_to_le32(mask);
+	req->r_locked_page = locked_page;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
+	if (locked_page && err == 0) {
+		u64 inline_version = req->r_reply_info.targeti.inline_version;
+		if (inline_version == 0) {
+			/* the reply is supposed to contain inline data */
+			err = -EINVAL;
+		} else if (inline_version == CEPH_INLINE_NONE) {
+			err = -ENODATA;
+		} else {
+			err = req->r_reply_info.targeti.inline_len;
+		}
+	}
 	ceph_mdsc_put_request(req);
 	dout("do_getattr result=%d\n", err);
 	return err;
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 01f5e4cfd68..e2817d00f7d 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -223,6 +223,7 @@ struct ceph_mds_request {
 	int r_request_release_offset;
 	struct ceph_msg  *r_reply;
 	struct ceph_mds_reply_info_parsed r_reply_info;
+	struct page *r_locked_page;
 	int r_err;
 	bool r_aborted;
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b0de9162758..6d56fae863c 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -744,7 +744,12 @@ extern void ceph_queue_vmtruncate(struct inode *inode);
 extern void ceph_queue_invalidate(struct inode *inode);
 extern void ceph_queue_writeback(struct inode *inode);
 
-extern int ceph_do_getattr(struct inode *inode, int mask, bool force);
+extern int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
+			     int mask, bool force);
+static inline int ceph_do_getattr(struct inode *inode, int mask, bool force)
+{
+	return __ceph_do_getattr(inode, NULL, mask, force);
+}
 extern int ceph_permission(struct inode *inode, int mask);
 extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
 extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 2d4acfa2c7b..c0dadaac26e 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -617,6 +617,8 @@ int ceph_flags_to_mode(int flags);
 				 CEPH_CAP_LINK_SHARED |	\
 				 CEPH_CAP_FILE_SHARED |	\
 				 CEPH_CAP_XATTR_SHARED)
+#define CEPH_STAT_CAP_INLINE_DATA (CEPH_CAP_FILE_SHARED | \
+				   CEPH_CAP_FILE_RD)
 
 #define CEPH_CAP_ANY_SHARED (CEPH_CAP_AUTH_SHARED |			\
 			      CEPH_CAP_LINK_SHARED |			\
-- 
cgit v1.2.3-70-g09d2


From 84a1d2d1ecd9ae2fc1ae51d8529090000e88a210 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@redhat.com>
Date: Mon, 17 Nov 2014 21:45:24 +0300
Subject: libceph: fixup includes in pagelist.h

pagelist.h needs to include linux/types.h and asm/byteorder.h and not
rely on other headers pulling yet another set of headers.

Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
---
 include/linux/ceph/pagelist.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h
index 5f871d84ddc..13d71fe18b0 100644
--- a/include/linux/ceph/pagelist.h
+++ b/include/linux/ceph/pagelist.h
@@ -1,8 +1,10 @@
 #ifndef __FS_CEPH_PAGELIST_H
 #define __FS_CEPH_PAGELIST_H
 
-#include <linux/list.h>
+#include <asm/byteorder.h>
 #include <linux/atomic.h>
+#include <linux/list.h>
+#include <linux/types.h>
 
 struct ceph_pagelist {
 	struct list_head head;
-- 
cgit v1.2.3-70-g09d2


From cb5281a57214581902ac06fb83f0d6ea2d440318 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 17 Dec 2014 18:17:20 +0100
Subject: KVM: move APIC types to arch/x86/

They are not used anymore by IA64, move them away.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h | 10 ++++++++++
 arch/x86/kvm/ioapic.h           | 17 +++++++++++++++++
 include/linux/kvm_types.h       | 27 ---------------------------
 3 files changed, 27 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0c4c88c008c..d89c6b828c9 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -664,6 +664,16 @@ struct msr_data {
 	u64 data;
 };
 
+struct kvm_lapic_irq {
+	u32 vector;
+	u32 delivery_mode;
+	u32 dest_mode;
+	u32 level;
+	u32 trig_mode;
+	u32 shorthand;
+	u32 dest_id;
+};
+
 struct kvm_x86_ops {
 	int (*cpu_has_kvm_support)(void);          /* __init */
 	int (*disabled_by_bios)(void);             /* __init */
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index deac8d509f2..3c9195535ff 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -44,6 +44,23 @@ struct rtc_status {
 	DECLARE_BITMAP(dest_map, KVM_MAX_VCPUS);
 };
 
+union kvm_ioapic_redirect_entry {
+	u64 bits;
+	struct {
+		u8 vector;
+		u8 delivery_mode:3;
+		u8 dest_mode:1;
+		u8 delivery_status:1;
+		u8 polarity:1;
+		u8 remote_irr:1;
+		u8 trig_mode:1;
+		u8 mask:1;
+		u8 reserve:7;
+		u8 reserved[4];
+		u8 dest_id;
+	} fields;
+};
+
 struct kvm_ioapic {
 	u64 base_address;
 	u32 ioregsel;
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index b606bb689a3..931da7e917c 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -54,33 +54,6 @@ typedef u64            hfn_t;
 
 typedef hfn_t pfn_t;
 
-union kvm_ioapic_redirect_entry {
-	u64 bits;
-	struct {
-		u8 vector;
-		u8 delivery_mode:3;
-		u8 dest_mode:1;
-		u8 delivery_status:1;
-		u8 polarity:1;
-		u8 remote_irr:1;
-		u8 trig_mode:1;
-		u8 mask:1;
-		u8 reserve:7;
-		u8 reserved[4];
-		u8 dest_id;
-	} fields;
-};
-
-struct kvm_lapic_irq {
-	u32 vector;
-	u32 delivery_mode;
-	u32 dest_mode;
-	u32 level;
-	u32 trig_mode;
-	u32 shorthand;
-	u32 dest_id;
-};
-
 struct gfn_to_hva_cache {
 	u64 generation;
 	gpa_t gpa;
-- 
cgit v1.2.3-70-g09d2


From 230fa253df6352af12ad0a16128760b5cb3f92df Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Tue, 25 Nov 2014 10:01:16 +0100
Subject: kernel: Provide READ_ONCE and ASSIGN_ONCE

ACCESS_ONCE does not work reliably on non-scalar types. For
example gcc 4.6 and 4.7 might remove the volatile tag for such
accesses during the SRA (scalar replacement of aggregates) step
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145)

Let's provide READ_ONCE/ASSIGN_ONCE that will do all accesses via
scalar types as suggested by Linus Torvalds. Accesses larger than
the machines word size cannot be guaranteed to be atomic. These
macros will use memcpy and emit a build warning.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 include/linux/compiler.h | 74 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 74 insertions(+)

(limited to 'include')

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index d5ad7b1118f..a1c81f80978 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -186,6 +186,80 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__)
 #endif
 
+#include <uapi/linux/types.h>
+
+static __always_inline void data_access_exceeds_word_size(void)
+#ifdef __compiletime_warning
+__compiletime_warning("data access exceeds word size and won't be atomic")
+#endif
+;
+
+static __always_inline void data_access_exceeds_word_size(void)
+{
+}
+
+static __always_inline void __read_once_size(volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(__u8 *)res = *(volatile __u8 *)p; break;
+	case 2: *(__u16 *)res = *(volatile __u16 *)p; break;
+	case 4: *(__u32 *)res = *(volatile __u32 *)p; break;
+#ifdef CONFIG_64BIT
+	case 8: *(__u64 *)res = *(volatile __u64 *)p; break;
+#endif
+	default:
+		barrier();
+		__builtin_memcpy((void *)res, (const void *)p, size);
+		data_access_exceeds_word_size();
+		barrier();
+	}
+}
+
+static __always_inline void __assign_once_size(volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(volatile __u8 *)p = *(__u8 *)res; break;
+	case 2: *(volatile __u16 *)p = *(__u16 *)res; break;
+	case 4: *(volatile __u32 *)p = *(__u32 *)res; break;
+#ifdef CONFIG_64BIT
+	case 8: *(volatile __u64 *)p = *(__u64 *)res; break;
+#endif
+	default:
+		barrier();
+		__builtin_memcpy((void *)p, (const void *)res, size);
+		data_access_exceeds_word_size();
+		barrier();
+	}
+}
+
+/*
+ * Prevent the compiler from merging or refetching reads or writes. The
+ * compiler is also forbidden from reordering successive instances of
+ * READ_ONCE, ASSIGN_ONCE and ACCESS_ONCE (see below), but only when the
+ * compiler is aware of some particular ordering.  One way to make the
+ * compiler aware of ordering is to put the two invocations of READ_ONCE,
+ * ASSIGN_ONCE or ACCESS_ONCE() in different C statements.
+ *
+ * In contrast to ACCESS_ONCE these two macros will also work on aggregate
+ * data types like structs or unions. If the size of the accessed data
+ * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
+ * READ_ONCE() and ASSIGN_ONCE()  will fall back to memcpy and print a
+ * compile-time warning.
+ *
+ * Their two major use cases are: (1) Mediating communication between
+ * process-level code and irq/NMI handlers, all running on the same CPU,
+ * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
+ * mutilate accesses that either do not require ordering or that interact
+ * with an explicit memory barrier or atomic instruction that provides the
+ * required ordering.
+ */
+
+#define READ_ONCE(x) \
+	({ typeof(x) __val; __read_once_size(&x, &__val, sizeof(__val)); __val; })
+
+#define ASSIGN_ONCE(val, x) \
+	({ typeof(x) __val; __val = val; __assign_once_size(&x, &__val, sizeof(__val)); __val; })
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
-- 
cgit v1.2.3-70-g09d2


From 3875f15207f9ecb3f24a8e91e7ad196899139595 Mon Sep 17 00:00:00 2001
From: Kyle McMartin <kyle@redhat.com>
Date: Thu, 18 Dec 2014 12:57:14 -0500
Subject: uapi/linux/target_core_user.h: fix headers_install.sh badness

scripts/headers_install.sh will transform __packed to
__attribute__((packed)), so the #ifndef is not necessary.
(and, in fact, it's problematic, because we'll end up with the header
 containing:
#ifndef __attribute__((packed))
#define __attribu...
and so forth.)

Cc: stable@vger.kernel.org # 3.18
Signed-off-by: Kyle McMartin <kyle@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 include/uapi/linux/target_core_user.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h
index 7dcfbe6771b..b483d1909d3 100644
--- a/include/uapi/linux/target_core_user.h
+++ b/include/uapi/linux/target_core_user.h
@@ -6,10 +6,6 @@
 #include <linux/types.h>
 #include <linux/uio.h>
 
-#ifndef __packed
-#define __packed                        __attribute__((packed))
-#endif
-
 #define TCMU_VERSION "1.0"
 
 /*
-- 
cgit v1.2.3-70-g09d2


From e48322abb061d75096fe52d71886b237e7ae7bfb Mon Sep 17 00:00:00 2001
From: Pintu Kumar <pintu.k@samsung.com>
Date: Thu, 18 Dec 2014 16:17:15 -0800
Subject: mm: cma: split cma-reserved in dmesg log

When the system boots up, in the dmesg logs we can see the memory
statistics along with total reserved as below.  Memory: 458840k/458840k
available, 65448k reserved, 0K highmem

When CMA is enabled, still the total reserved memory remains the same.
However, the CMA memory is not considered as reserved.  But, when we see
/proc/meminfo, the CMA memory is part of free memory.  This creates
confusion.  This patch corrects the problem by properly subtracting the
CMA reserved memory from the total reserved memory in dmesg logs.

Below is the dmesg snapshot from an arm based device with 512MB RAM and
12MB single CMA region.

Before this change:
  Memory: 458840k/458840k available, 65448k reserved, 0K highmem

After this change:
  Memory: 458840k/458840k available, 53160k reserved, 12288k cma-reserved, 0K highmem

Signed-off-by: Pintu Kumar <pintu.k@samsung.com>
Signed-off-by: Vishnu Pratap Singh <vishnu.ps@samsung.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Cc: Rafael Aquini <aquini@redhat.com>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/cma.h | 1 +
 mm/cma.c            | 1 +
 mm/page_alloc.c     | 6 ++++--
 3 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/cma.h b/include/linux/cma.h
index a93438beb33..9384ba66e97 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -15,6 +15,7 @@
 
 struct cma;
 
+extern unsigned long totalcma_pages;
 extern phys_addr_t cma_get_base(struct cma *cma);
 extern unsigned long cma_get_size(struct cma *cma);
 
diff --git a/mm/cma.c b/mm/cma.c
index f8917629cbd..a85ae28709a 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -337,6 +337,7 @@ int __init cma_declare_contiguous(phys_addr_t base,
 	if (ret)
 		goto err;
 
+	totalcma_pages += (size / PAGE_SIZE);
 	pr_info("Reserved %ld MiB at %pa\n", (unsigned long)size / SZ_1M,
 		&base);
 	return 0;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fa974d87f60..7633c503a11 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -111,6 +111,7 @@ static DEFINE_SPINLOCK(managed_page_count_lock);
 
 unsigned long totalram_pages __read_mostly;
 unsigned long totalreserve_pages __read_mostly;
+unsigned long totalcma_pages __read_mostly;
 /*
  * When calculating the number of globally allowed dirty pages, there
  * is a certain number of per-zone reserves that should not be
@@ -5586,7 +5587,7 @@ void __init mem_init_print_info(const char *str)
 
 	pr_info("Memory: %luK/%luK available "
 	       "(%luK kernel code, %luK rwdata, %luK rodata, "
-	       "%luK init, %luK bss, %luK reserved"
+	       "%luK init, %luK bss, %luK reserved, %luK cma-reserved"
 #ifdef	CONFIG_HIGHMEM
 	       ", %luK highmem"
 #endif
@@ -5594,7 +5595,8 @@ void __init mem_init_print_info(const char *str)
 	       nr_free_pages() << (PAGE_SHIFT-10), physpages << (PAGE_SHIFT-10),
 	       codesize >> 10, datasize >> 10, rosize >> 10,
 	       (init_data_size + init_code_size) >> 10, bss_size >> 10,
-	       (physpages - totalram_pages) << (PAGE_SHIFT-10),
+	       (physpages - totalram_pages - totalcma_pages) << (PAGE_SHIFT-10),
+	       totalcma_pages << (PAGE_SHIFT-10),
 #ifdef	CONFIG_HIGHMEM
 	       totalhigh_pages << (PAGE_SHIFT-10),
 #endif
-- 
cgit v1.2.3-70-g09d2


From 464ed18ebdb6236fcff59d2a35d4d2e28668435a Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 19 Dec 2014 15:37:54 +0100
Subject: PM: Eliminate CONFIG_PM_RUNTIME

Having switched over all of the users of CONFIG_PM_RUNTIME to use
CONFIG_PM directly, turn the latter into a user-selectable option
and drop the former entirely from the tree.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Kevin Hilman <khilman@linaro.org>
---
 arch/arm/configs/ape6evm_defconfig         |  2 +-
 arch/arm/configs/armadillo800eva_defconfig |  2 +-
 arch/arm/configs/bcm_defconfig             |  2 +-
 arch/arm/configs/bockw_defconfig           |  2 +-
 arch/arm/configs/davinci_all_defconfig     |  2 +-
 arch/arm/configs/exynos_defconfig          |  2 +-
 arch/arm/configs/ezx_defconfig             |  1 -
 arch/arm/configs/hisi_defconfig            |  2 +-
 arch/arm/configs/imote2_defconfig          |  1 -
 arch/arm/configs/imx_v6_v7_defconfig       |  2 +-
 arch/arm/configs/keystone_defconfig        |  2 +-
 arch/arm/configs/kzm9g_defconfig           |  2 +-
 arch/arm/configs/lager_defconfig           |  2 +-
 arch/arm/configs/mackerel_defconfig        |  1 -
 arch/arm/configs/marzen_defconfig          |  2 +-
 arch/arm/configs/omap1_defconfig           |  1 -
 arch/arm/configs/prima2_defconfig          |  2 +-
 arch/arm/configs/sama5_defconfig           |  2 +-
 arch/arm/configs/shmobile_defconfig        |  2 +-
 arch/arm/configs/sunxi_defconfig           |  2 +-
 arch/arm/configs/tegra_defconfig           |  2 +-
 arch/arm/configs/u8500_defconfig           |  2 +-
 arch/arm/configs/vt8500_v6_v7_defconfig    |  2 +-
 arch/arm/mach-omap2/Kconfig                |  6 +++---
 arch/mips/configs/db1xxx_defconfig         |  2 +-
 arch/mips/configs/lemote2f_defconfig       |  1 -
 arch/mips/configs/loongson3_defconfig      |  2 +-
 arch/mips/configs/nlm_xlp_defconfig        |  2 +-
 arch/mips/configs/nlm_xlr_defconfig        |  2 +-
 arch/powerpc/configs/ps3_defconfig         |  2 +-
 arch/sh/Kconfig                            |  2 +-
 arch/sh/configs/apsh4ad0a_defconfig        |  2 +-
 arch/sh/configs/sdk7786_defconfig          |  2 +-
 drivers/usb/host/isp1760-hcd.c             |  2 +-
 drivers/usb/host/oxu210hp-hcd.c            |  2 +-
 include/linux/devfreq.h                    |  2 +-
 kernel/power/Kconfig                       | 16 ++++++----------
 37 files changed, 39 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/arch/arm/configs/ape6evm_defconfig b/arch/arm/configs/ape6evm_defconfig
index db81d8ce4c0..9e9a72e3d30 100644
--- a/arch/arm/configs/ape6evm_defconfig
+++ b/arch/arm/configs/ape6evm_defconfig
@@ -33,7 +33,7 @@ CONFIG_ARM_APPENDED_DTB=y
 CONFIG_VFP=y
 CONFIG_NEON=y
 CONFIG_BINFMT_MISC=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/armadillo800eva_defconfig b/arch/arm/configs/armadillo800eva_defconfig
index d9675c68a39..5666e3700a8 100644
--- a/arch/arm/configs/armadillo800eva_defconfig
+++ b/arch/arm/configs/armadillo800eva_defconfig
@@ -43,7 +43,7 @@ CONFIG_KEXEC=y
 CONFIG_VFP=y
 CONFIG_NEON=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/bcm_defconfig b/arch/arm/configs/bcm_defconfig
index 83a87e48901..7117662bab2 100644
--- a/arch/arm/configs/bcm_defconfig
+++ b/arch/arm/configs/bcm_defconfig
@@ -39,7 +39,7 @@ CONFIG_CPU_IDLE=y
 CONFIG_VFP=y
 CONFIG_NEON=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=y
diff --git a/arch/arm/configs/bockw_defconfig b/arch/arm/configs/bockw_defconfig
index 1dde5daa84f..3125e00f05a 100644
--- a/arch/arm/configs/bockw_defconfig
+++ b/arch/arm/configs/bockw_defconfig
@@ -29,7 +29,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_VFP=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig
index 759f9b0053e..235842c9ba9 100644
--- a/arch/arm/configs/davinci_all_defconfig
+++ b/arch/arm/configs/davinci_all_defconfig
@@ -49,7 +49,7 @@ CONFIG_CPU_FREQ_GOV_PERFORMANCE=m
 CONFIG_CPU_FREQ_GOV_POWERSAVE=m
 CONFIG_CPU_FREQ_GOV_ONDEMAND=m
 CONFIG_CPU_IDLE=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index c4199072902..5ef14de00a2 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -27,7 +27,7 @@ CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_CMDLINE="root=/dev/ram0 rw ramdisk=8192 initrd=0x41000000,8M console=ttySAC1,115200 init=/linuxrc mem=256M"
 CONFIG_VFP=y
 CONFIG_NEON=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig
index eb440aae428..ea316c4b890 100644
--- a/arch/arm/configs/ezx_defconfig
+++ b/arch/arm/configs/ezx_defconfig
@@ -39,7 +39,6 @@ CONFIG_BINFMT_AOUT=m
 CONFIG_BINFMT_MISC=m
 CONFIG_PM=y
 CONFIG_APM_EMULATION=y
-CONFIG_PM_RUNTIME=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/hisi_defconfig b/arch/arm/configs/hisi_defconfig
index 1fe3621faf6..112543665dd 100644
--- a/arch/arm/configs/hisi_defconfig
+++ b/arch/arm/configs/hisi_defconfig
@@ -18,7 +18,7 @@ CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_NEON=y
 CONFIG_ARM_ATAG_DTB_COMPAT_CMDLINE_FROM_BOOTLOADER=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig
index 182e5469266..18e59feaa30 100644
--- a/arch/arm/configs/imote2_defconfig
+++ b/arch/arm/configs/imote2_defconfig
@@ -31,7 +31,6 @@ CONFIG_BINFMT_AOUT=m
 CONFIG_BINFMT_MISC=m
 CONFIG_PM=y
 CONFIG_APM_EMULATION=y
-CONFIG_PM_RUNTIME=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index f707cd2691c..7c2075a07eb 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -54,7 +54,7 @@ CONFIG_ARM_IMX6Q_CPUFREQ=y
 CONFIG_VFP=y
 CONFIG_NEON=y
 CONFIG_BINFMT_MISC=m
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_PM_DEBUG=y
 CONFIG_PM_TEST_SUSPEND=y
 CONFIG_NET=y
diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig
index 20a3ff99fae..a2067cbfe17 100644
--- a/arch/arm/configs/keystone_defconfig
+++ b/arch/arm/configs/keystone_defconfig
@@ -30,7 +30,7 @@ CONFIG_HIGHMEM=y
 CONFIG_VFP=y
 CONFIG_NEON=y
 # CONFIG_SUSPEND is not set
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/kzm9g_defconfig b/arch/arm/configs/kzm9g_defconfig
index 8cb115d74fd..5d63fc5d2d4 100644
--- a/arch/arm/configs/kzm9g_defconfig
+++ b/arch/arm/configs/kzm9g_defconfig
@@ -43,7 +43,7 @@ CONFIG_KEXEC=y
 CONFIG_VFP=y
 CONFIG_NEON=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/lager_defconfig b/arch/arm/configs/lager_defconfig
index 929c571ea29..a82afc916a8 100644
--- a/arch/arm/configs/lager_defconfig
+++ b/arch/arm/configs/lager_defconfig
@@ -37,7 +37,7 @@ CONFIG_AUTO_ZRELADDR=y
 CONFIG_VFP=y
 CONFIG_NEON=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/mackerel_defconfig b/arch/arm/configs/mackerel_defconfig
index 57ececba2ae..05a529311b4 100644
--- a/arch/arm/configs/mackerel_defconfig
+++ b/arch/arm/configs/mackerel_defconfig
@@ -28,7 +28,6 @@ CONFIG_KEXEC=y
 CONFIG_VFP=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_PM=y
-CONFIG_PM_RUNTIME=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/marzen_defconfig b/arch/arm/configs/marzen_defconfig
index ff91630d34e..3c8b6d82318 100644
--- a/arch/arm/configs/marzen_defconfig
+++ b/arch/arm/configs/marzen_defconfig
@@ -33,7 +33,7 @@ CONFIG_ARM_APPENDED_DTB=y
 CONFIG_VFP=y
 CONFIG_KEXEC=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig
index 115cda9f326..a7dce674f1b 100644
--- a/arch/arm/configs/omap1_defconfig
+++ b/arch/arm/configs/omap1_defconfig
@@ -63,7 +63,6 @@ CONFIG_FPE_NWFPE=y
 CONFIG_BINFMT_MISC=y
 CONFIG_PM=y
 # CONFIG_SUSPEND is not set
-CONFIG_PM_RUNTIME=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/prima2_defconfig b/arch/arm/configs/prima2_defconfig
index 23591dba47a..f610230b9c1 100644
--- a/arch/arm/configs/prima2_defconfig
+++ b/arch/arm/configs/prima2_defconfig
@@ -18,7 +18,7 @@ CONFIG_PREEMPT=y
 CONFIG_AEABI=y
 CONFIG_KEXEC=y
 CONFIG_BINFMT_MISC=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig
index b58fb32770a..afa24799477 100644
--- a/arch/arm/configs/sama5_defconfig
+++ b/arch/arm/configs/sama5_defconfig
@@ -32,7 +32,7 @@ CONFIG_VFP=y
 CONFIG_NEON=y
 CONFIG_KERNEL_MODE_NEON=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_PM_DEBUG=y
 CONFIG_PM_ADVANCED_DEBUG=y
 CONFIG_NET=y
diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig
index df2c0f514b0..3df6ca0c1d1 100644
--- a/arch/arm/configs/shmobile_defconfig
+++ b/arch/arm/configs/shmobile_defconfig
@@ -39,7 +39,7 @@ CONFIG_KEXEC=y
 CONFIG_VFP=y
 CONFIG_NEON=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index f7ac0379850..7a342d2780a 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -11,7 +11,7 @@ CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_VFP=y
 CONFIG_NEON=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index 40750f93aa8..3ea9c3377cc 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -46,7 +46,7 @@ CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_IDLE=y
 CONFIG_VFP=y
 CONFIG_NEON=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig
index d219d6a4323..6a1c9898fd0 100644
--- a/arch/arm/configs/u8500_defconfig
+++ b/arch/arm/configs/u8500_defconfig
@@ -25,7 +25,7 @@ CONFIG_CPU_IDLE=y
 CONFIG_ARM_U8500_CPUIDLE=y
 CONFIG_VFP=y
 CONFIG_NEON=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm/configs/vt8500_v6_v7_defconfig b/arch/arm/configs/vt8500_v6_v7_defconfig
index 9e7a2563969..1bfaa7bfc39 100644
--- a/arch/arm/configs/vt8500_v6_v7_defconfig
+++ b/arch/arm/configs/vt8500_v6_v7_defconfig
@@ -16,7 +16,7 @@ CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_VFP=y
 CONFIG_NEON=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index f0edec199cd..6ab656cc4f1 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -15,7 +15,7 @@ config ARCH_OMAP3
 	select ARM_CPU_SUSPEND if PM
 	select OMAP_INTERCONNECT
 	select PM_OPP if PM
-	select PM_RUNTIME if CPU_IDLE
+	select PM if CPU_IDLE
 	select SOC_HAS_OMAP2_SDRC
 
 config ARCH_OMAP4
@@ -32,7 +32,7 @@ config ARCH_OMAP4
 	select PL310_ERRATA_588369 if CACHE_L2X0
 	select PL310_ERRATA_727915 if CACHE_L2X0
 	select PM_OPP if PM
-	select PM_RUNTIME if CPU_IDLE
+	select PM if CPU_IDLE
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_775420
 
@@ -103,7 +103,7 @@ config ARCH_OMAP2PLUS_TYPICAL
 	select I2C_OMAP
 	select MENELAUS if ARCH_OMAP2
 	select NEON if CPU_V7
-	select PM_RUNTIME
+	select PM
 	select REGULATOR
 	select TWL4030_CORE if ARCH_OMAP3 || ARCH_OMAP4
 	select TWL4030_POWER if ARCH_OMAP3 || ARCH_OMAP4
diff --git a/arch/mips/configs/db1xxx_defconfig b/arch/mips/configs/db1xxx_defconfig
index 46e8f7676a1..3bdb72a7036 100644
--- a/arch/mips/configs/db1xxx_defconfig
+++ b/arch/mips/configs/db1xxx_defconfig
@@ -36,7 +36,7 @@ CONFIG_PCI=y
 CONFIG_PCI_REALLOC_ENABLE_AUTO=y
 CONFIG_PCCARD=y
 CONFIG_PCMCIA_ALCHEMY_DEVBOARD=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=y
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index 227a9de3224..e51aad9a94b 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -37,7 +37,6 @@ CONFIG_MIPS32_N32=y
 CONFIG_PM=y
 CONFIG_HIBERNATION=y
 CONFIG_PM_STD_PARTITION="/dev/hda3"
-CONFIG_PM_RUNTIME=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_DEBUG=y
 CONFIG_CPU_FREQ_STAT=m
diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig
index 1c6191ebd58..7eabcd2031e 100644
--- a/arch/mips/configs/loongson3_defconfig
+++ b/arch/mips/configs/loongson3_defconfig
@@ -58,7 +58,7 @@ CONFIG_BINFMT_MISC=m
 CONFIG_MIPS32_COMPAT=y
 CONFIG_MIPS32_O32=y
 CONFIG_MIPS32_N32=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/mips/configs/nlm_xlp_defconfig b/arch/mips/configs/nlm_xlp_defconfig
index 70509a48df8..b3d1d37f85e 100644
--- a/arch/mips/configs/nlm_xlp_defconfig
+++ b/arch/mips/configs/nlm_xlp_defconfig
@@ -61,7 +61,7 @@ CONFIG_BINFMT_MISC=y
 CONFIG_MIPS32_COMPAT=y
 CONFIG_MIPS32_O32=y
 CONFIG_MIPS32_N32=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_PM_DEBUG=y
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/mips/configs/nlm_xlr_defconfig b/arch/mips/configs/nlm_xlr_defconfig
index 82207e8079f..3d8016d6cf3 100644
--- a/arch/mips/configs/nlm_xlr_defconfig
+++ b/arch/mips/configs/nlm_xlr_defconfig
@@ -41,7 +41,7 @@ CONFIG_PCI=y
 CONFIG_PCI_MSI=y
 CONFIG_PCI_DEBUG=y
 CONFIG_BINFMT_MISC=m
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_PM_DEBUG=y
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index 2e637c881d2..879de5efb07 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -36,7 +36,7 @@ CONFIG_KEXEC=y
 CONFIG_SCHED_SMT=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE=""
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_PM_DEBUG=y
 # CONFIG_SECCOMP is not set
 # CONFIG_PCI is not set
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index c6b6ee5f38b..0f09f5285d5 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -223,7 +223,7 @@ config CPU_SHX3
 config ARCH_SHMOBILE
 	bool
 	select ARCH_SUSPEND_POSSIBLE
-	select PM_RUNTIME
+	select PM
 
 config CPU_HAS_PMU
        depends on CPU_SH4 || CPU_SH4A
diff --git a/arch/sh/configs/apsh4ad0a_defconfig b/arch/sh/configs/apsh4ad0a_defconfig
index ec70475da89..a8d975793b6 100644
--- a/arch/sh/configs/apsh4ad0a_defconfig
+++ b/arch/sh/configs/apsh4ad0a_defconfig
@@ -47,7 +47,7 @@ CONFIG_PREEMPT=y
 CONFIG_BINFMT_MISC=y
 CONFIG_PM=y
 CONFIG_PM_DEBUG=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_CPU_IDLE=y
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig
index 76a76a295d7..e7e56a4131b 100644
--- a/arch/sh/configs/sdk7786_defconfig
+++ b/arch/sh/configs/sdk7786_defconfig
@@ -82,7 +82,7 @@ CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y
 CONFIG_BINFMT_MISC=y
 CONFIG_PM=y
 CONFIG_PM_DEBUG=y
-CONFIG_PM_RUNTIME=y
+CONFIG_PM=y
 CONFIG_CPU_IDLE=y
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/drivers/usb/host/isp1760-hcd.c b/drivers/usb/host/isp1760-hcd.c
index e752c3098f3..395649f357a 100644
--- a/drivers/usb/host/isp1760-hcd.c
+++ b/drivers/usb/host/isp1760-hcd.c
@@ -1739,7 +1739,7 @@ static int isp1760_hub_status_data(struct usb_hcd *hcd, char *buf)
 	int retval = 1;
 	unsigned long flags;
 
-	/* if !PM_RUNTIME, root hub timers won't get shut down ... */
+	/* if !PM, root hub timers won't get shut down ... */
 	if (!HC_IS_RUNNING(hcd->state))
 		return 0;
 
diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c
index 75811dd5a9d..036924e640f 100644
--- a/drivers/usb/host/oxu210hp-hcd.c
+++ b/drivers/usb/host/oxu210hp-hcd.c
@@ -3087,7 +3087,7 @@ static int oxu_hub_status_data(struct usb_hcd *hcd, char *buf)
 	int ports, i, retval = 1;
 	unsigned long flags;
 
-	/* if !PM_RUNTIME, root hub timers won't get shut down ... */
+	/* if !PM, root hub timers won't get shut down ... */
 	if (!HC_IS_RUNNING(hcd->state))
 		return 0;
 
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index f1863dcd83e..ce447f0f1ba 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -188,7 +188,7 @@ extern struct devfreq *devm_devfreq_add_device(struct device *dev,
 extern void devm_devfreq_remove_device(struct device *dev,
 				  struct devfreq *devfreq);
 
-/* Supposed to be called by PM_SLEEP/PM_RUNTIME callbacks */
+/* Supposed to be called by PM callbacks */
 extern int devfreq_suspend_device(struct devfreq *devfreq);
 extern int devfreq_resume_device(struct devfreq *devfreq);
 
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 6e7708c2c21..48b28d387c7 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -94,7 +94,7 @@ config PM_STD_PARTITION
 config PM_SLEEP
 	def_bool y
 	depends on SUSPEND || HIBERNATE_CALLBACKS
-	select PM_RUNTIME
+	select PM
 
 config PM_SLEEP_SMP
 	def_bool y
@@ -130,23 +130,19 @@ config PM_WAKELOCKS_GC
 	depends on PM_WAKELOCKS
 	default y
 
-config PM_RUNTIME
-	bool "Run-time PM core functionality"
+config PM
+	bool "Device power management core functionality"
 	---help---
 	  Enable functionality allowing I/O devices to be put into energy-saving
-	  (low power) states at run time (or autosuspended) after a specified
-	  period of inactivity and woken up in response to a hardware-generated
+	  (low power) states, for example after a specified period of inactivity
+	  (autosuspended), and woken up in response to a hardware-generated
 	  wake-up event or a driver's request.
 
 	  Hardware support is generally required for this functionality to work
 	  and the bus type drivers of the buses the devices are on are
-	  responsible for the actual handling of the autosuspend requests and
+	  responsible for the actual handling of device suspend requests and
 	  wake-up events.
 
-config PM
-	def_bool y
-	depends on PM_SLEEP || PM_RUNTIME
-
 config PM_DEBUG
 	bool "Power Management Debug Support"
 	depends on PM
-- 
cgit v1.2.3-70-g09d2


From 6d08acd2d32e3e877579315dc3202d7a5f336d98 Mon Sep 17 00:00:00 2001
From: stephen hemminger <stephen@networkplumber.org>
Date: Sat, 20 Dec 2014 12:15:49 -0800
Subject: in6: fix conflict with glibc

Resolve conflicts between glibc definition of IPV6 socket options
and those defined in Linux headers. Looks like earlier efforts to
solve this did not cover all the definitions.

It resolves warnings during iproute2 build.
Please consider for stable as well.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/in6.h         | 3 ++-
 include/uapi/linux/libc-compat.h | 3 +++
 2 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index 74a2a177349..79b12b004ad 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -149,7 +149,7 @@ struct in6_flowlabel_req {
 /*
  *	IPV6 socket options
  */
-
+#if __UAPI_DEF_IPV6_OPTIONS
 #define IPV6_ADDRFORM		1
 #define IPV6_2292PKTINFO	2
 #define IPV6_2292HOPOPTS	3
@@ -196,6 +196,7 @@ struct in6_flowlabel_req {
 
 #define IPV6_IPSEC_POLICY	34
 #define IPV6_XFRM_POLICY	35
+#endif
 
 /*
  * Multicast:
diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index c140620dad9..e28807ad17f 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -69,6 +69,7 @@
 #define __UAPI_DEF_SOCKADDR_IN6		0
 #define __UAPI_DEF_IPV6_MREQ		0
 #define __UAPI_DEF_IPPROTO_V6		0
+#define __UAPI_DEF_IPV6_OPTIONS		0
 
 #else
 
@@ -82,6 +83,7 @@
 #define __UAPI_DEF_SOCKADDR_IN6		1
 #define __UAPI_DEF_IPV6_MREQ		1
 #define __UAPI_DEF_IPPROTO_V6		1
+#define __UAPI_DEF_IPV6_OPTIONS		1
 
 #endif /* _NETINET_IN_H */
 
@@ -103,6 +105,7 @@
 #define __UAPI_DEF_SOCKADDR_IN6		1
 #define __UAPI_DEF_IPV6_MREQ		1
 #define __UAPI_DEF_IPPROTO_V6		1
+#define __UAPI_DEF_IPV6_OPTIONS		1
 
 /* Definitions for xattr.h */
 #define __UAPI_DEF_XATTR		1
-- 
cgit v1.2.3-70-g09d2


From 041d7b98ffe59c59fdd639931dea7d74f9aa9a59 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Tue, 23 Dec 2014 13:02:04 -0500
Subject: audit: restore AUDIT_LOGINUID unset ABI

A regression was caused by commit 780a7654cee8:
	 audit: Make testing for a valid loginuid explicit.
(which in turn attempted to fix a regression caused by e1760bd)

When audit_krule_to_data() fills in the rules to get a listing, there was a
missing clause to convert back from AUDIT_LOGINUID_SET to AUDIT_LOGINUID.

This broke userspace by not returning the same information that was sent and
expected.

The rule:
	auditctl -a exit,never -F auid=-1
gives:
	auditctl -l
		LIST_RULES: exit,never f24=0 syscall=all
when it should give:
		LIST_RULES: exit,never auid=-1 (0xffffffff) syscall=all

Tag it so that it is reported the same way it was set.  Create a new
private flags audit_krule field (pflags) to store it that won't interact with
the public one from the API.

Cc: stable@vger.kernel.org # v3.10-rc1+
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <pmoore@redhat.com>
---
 include/linux/audit.h |  4 ++++
 kernel/auditfilter.c  | 10 ++++++++++
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 36dffeccebd..93331929d64 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -47,6 +47,7 @@ struct sk_buff;
 
 struct audit_krule {
 	int			vers_ops;
+	u32			pflags;
 	u32			flags;
 	u32			listnr;
 	u32			action;
@@ -64,6 +65,9 @@ struct audit_krule {
 	u64			prio;
 };
 
+/* Flag to indicate legacy AUDIT_LOGINUID unset usage */
+#define AUDIT_LOGINUID_LEGACY		0x1
+
 struct audit_field {
 	u32				type;
 	union {
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index c0d148bd7a5..103586e239a 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -442,6 +442,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) {
 			f->type = AUDIT_LOGINUID_SET;
 			f->val = 0;
+			entry->rule.pflags |= AUDIT_LOGINUID_LEGACY;
 		}
 
 		err = audit_field_valid(entry, f);
@@ -617,6 +618,13 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
 			data->buflen += data->values[i] =
 				audit_pack_string(&bufp, krule->filterkey);
 			break;
+		case AUDIT_LOGINUID_SET:
+			if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) {
+				data->fields[i] = AUDIT_LOGINUID;
+				data->values[i] = AUDIT_UID_UNSET;
+				break;
+			}
+			/* fallthrough if set */
 		default:
 			data->values[i] = f->val;
 		}
@@ -633,6 +641,7 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b)
 	int i;
 
 	if (a->flags != b->flags ||
+	    a->pflags != b->pflags ||
 	    a->listnr != b->listnr ||
 	    a->action != b->action ||
 	    a->field_count != b->field_count)
@@ -751,6 +760,7 @@ struct audit_entry *audit_dupe_rule(struct audit_krule *old)
 	new = &entry->rule;
 	new->vers_ops = old->vers_ops;
 	new->flags = old->flags;
+	new->pflags = old->pflags;
 	new->listnr = old->listnr;
 	new->action = old->action;
 	for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
-- 
cgit v1.2.3-70-g09d2


From da6b51d007da17fd394405055e2f0109ec5f05f4 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Wed, 24 Dec 2014 13:11:17 +1000
Subject: Revert "drm/gem: Warn on illegal use of the dumb buffer interface v2"

This reverts commit 355a70183848f21198e9f6296bd646df3478a26d.

This had some bad side effects under normal operation, and should
have been dropped earlier.

Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/i915/i915_drv.c            |  2 +-
 drivers/gpu/drm/i915/i915_drv.h            |  5 ++---
 drivers/gpu/drm/i915/i915_gem.c            | 28 +++++-----------------------
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  3 ---
 drivers/gpu/drm/nouveau/nouveau_display.c  |  9 ---------
 drivers/gpu/drm/nouveau/nouveau_gem.c      |  3 ---
 drivers/gpu/drm/radeon/radeon_gem.c        | 26 ++++----------------------
 drivers/gpu/drm/radeon/radeon_object.c     |  3 ---
 include/drm/drm_gem.h                      |  7 -------
 9 files changed, 12 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index fc8cfddbf23..574057cd1d0 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1586,7 +1586,7 @@ static struct drm_driver driver = {
 	.gem_prime_import = i915_gem_prime_import,
 
 	.dumb_create = i915_gem_dumb_create,
-	.dumb_map_offset = i915_gem_dumb_map_offset,
+	.dumb_map_offset = i915_gem_mmap_gtt,
 	.dumb_destroy = drm_gem_dumb_destroy,
 	.ioctls = i915_ioctls,
 	.fops = &i915_driver_fops,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 63bcda5541e..70d0f0f06f1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2501,9 +2501,8 @@ void i915_vma_move_to_active(struct i915_vma *vma,
 int i915_gem_dumb_create(struct drm_file *file_priv,
 			 struct drm_device *dev,
 			 struct drm_mode_create_dumb *args);
-int i915_gem_dumb_map_offset(struct drm_file *file_priv,
-			     struct drm_device *dev, uint32_t handle,
-			     uint64_t *offset);
+int i915_gem_mmap_gtt(struct drm_file *file_priv, struct drm_device *dev,
+		      uint32_t handle, uint64_t *offset);
 /**
  * Returns true if seq1 is later than seq2.
  */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 4a9faea626d..52adcb680be 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -401,7 +401,6 @@ static int
 i915_gem_create(struct drm_file *file,
 		struct drm_device *dev,
 		uint64_t size,
-		bool dumb,
 		uint32_t *handle_p)
 {
 	struct drm_i915_gem_object *obj;
@@ -417,7 +416,6 @@ i915_gem_create(struct drm_file *file,
 	if (obj == NULL)
 		return -ENOMEM;
 
-	obj->base.dumb = dumb;
 	ret = drm_gem_handle_create(file, &obj->base, &handle);
 	/* drop reference from allocate - handle holds it now */
 	drm_gem_object_unreference_unlocked(&obj->base);
@@ -437,7 +435,7 @@ i915_gem_dumb_create(struct drm_file *file,
 	args->pitch = ALIGN(args->width * DIV_ROUND_UP(args->bpp, 8), 64);
 	args->size = args->pitch * args->height;
 	return i915_gem_create(file, dev,
-			       args->size, true, &args->handle);
+			       args->size, &args->handle);
 }
 
 /**
@@ -450,7 +448,7 @@ i915_gem_create_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_gem_create *args = data;
 
 	return i915_gem_create(file, dev,
-			       args->size, false, &args->handle);
+			       args->size, &args->handle);
 }
 
 static inline int
@@ -1840,10 +1838,10 @@ static void i915_gem_object_free_mmap_offset(struct drm_i915_gem_object *obj)
 	drm_gem_free_mmap_offset(&obj->base);
 }
 
-static int
+int
 i915_gem_mmap_gtt(struct drm_file *file,
 		  struct drm_device *dev,
-		  uint32_t handle, bool dumb,
+		  uint32_t handle,
 		  uint64_t *offset)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1860,13 +1858,6 @@ i915_gem_mmap_gtt(struct drm_file *file,
 		goto unlock;
 	}
 
-	/*
-	 * We don't allow dumb mmaps on objects created using another
-	 * interface.
-	 */
-	WARN_ONCE(dumb && !(obj->base.dumb || obj->base.import_attach),
-		  "Illegal dumb map of accelerated buffer.\n");
-
 	if (obj->base.size > dev_priv->gtt.mappable_end) {
 		ret = -E2BIG;
 		goto out;
@@ -1891,15 +1882,6 @@ unlock:
 	return ret;
 }
 
-int
-i915_gem_dumb_map_offset(struct drm_file *file,
-			 struct drm_device *dev,
-			 uint32_t handle,
-			 uint64_t *offset)
-{
-	return i915_gem_mmap_gtt(file, dev, handle, true, offset);
-}
-
 /**
  * i915_gem_mmap_gtt_ioctl - prepare an object for GTT mmap'ing
  * @dev: DRM device
@@ -1921,7 +1903,7 @@ i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_gem_mmap_gtt *args = data;
 
-	return i915_gem_mmap_gtt(file, dev, args->handle, false, &args->offset);
+	return i915_gem_mmap_gtt(file, dev, args->handle, &args->offset);
 }
 
 static inline int
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index f06027ba3ee..11738316394 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -121,9 +121,6 @@ eb_lookup_vmas(struct eb_vmas *eb,
 			goto err;
 		}
 
-		WARN_ONCE(obj->base.dumb,
-			  "GPU use of dumb buffer is illegal.\n");
-
 		drm_gem_object_reference(&obj->base);
 		list_add_tail(&obj->obj_exec_link, &objects);
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 5d93902a91a..f8042433752 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -876,7 +876,6 @@ nouveau_display_dumb_create(struct drm_file *file_priv, struct drm_device *dev,
 	if (ret)
 		return ret;
 
-	bo->gem.dumb = true;
 	ret = drm_gem_handle_create(file_priv, &bo->gem, &args->handle);
 	drm_gem_object_unreference_unlocked(&bo->gem);
 	return ret;
@@ -892,14 +891,6 @@ nouveau_display_dumb_map_offset(struct drm_file *file_priv,
 	gem = drm_gem_object_lookup(dev, file_priv, handle);
 	if (gem) {
 		struct nouveau_bo *bo = nouveau_gem_object(gem);
-
-		/*
-		 * We don't allow dumb mmaps on objects created using another
-		 * interface.
-		 */
-		WARN_ONCE(!(gem->dumb || gem->import_attach),
-			  "Illegal dumb map of accelerated buffer.\n");
-
 		*poffset = drm_vma_node_offset_addr(&bo->bo.vma_node);
 		drm_gem_object_unreference_unlocked(gem);
 		return 0;
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 28d51a22a4b..42c34babc2e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -444,9 +444,6 @@ validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli,
 	list_for_each_entry(nvbo, list, entry) {
 		struct drm_nouveau_gem_pushbuf_bo *b = &pbbo[nvbo->pbbo_index];
 
-		WARN_ONCE(nvbo->gem.dumb,
-			  "GPU use of dumb buffer is illegal.\n");
-
 		ret = nouveau_gem_set_domain(&nvbo->gem, b->read_domains,
 					     b->write_domains,
 					     b->valid_domains);
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index fe48f229043..a46f7373799 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -394,10 +394,9 @@ int radeon_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 	return r;
 }
 
-static int radeon_mode_mmap(struct drm_file *filp,
-			    struct drm_device *dev,
-			    uint32_t handle, bool dumb,
-			    uint64_t *offset_p)
+int radeon_mode_dumb_mmap(struct drm_file *filp,
+			  struct drm_device *dev,
+			  uint32_t handle, uint64_t *offset_p)
 {
 	struct drm_gem_object *gobj;
 	struct radeon_bo *robj;
@@ -406,14 +405,6 @@ static int radeon_mode_mmap(struct drm_file *filp,
 	if (gobj == NULL) {
 		return -ENOENT;
 	}
-
-	/*
-	 * We don't allow dumb mmaps on objects created using another
-	 * interface.
-	 */
-	WARN_ONCE(dumb && !(gobj->dumb || gobj->import_attach),
-		"Illegal dumb map of GPU buffer.\n");
-
 	robj = gem_to_radeon_bo(gobj);
 	if (radeon_ttm_tt_has_userptr(robj->tbo.ttm)) {
 		drm_gem_object_unreference_unlocked(gobj);
@@ -424,20 +415,12 @@ static int radeon_mode_mmap(struct drm_file *filp,
 	return 0;
 }
 
-int radeon_mode_dumb_mmap(struct drm_file *filp,
-			  struct drm_device *dev,
-			  uint32_t handle, uint64_t *offset_p)
-{
-	return radeon_mode_mmap(filp, dev, handle, true, offset_p);
-}
-
 int radeon_gem_mmap_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp)
 {
 	struct drm_radeon_gem_mmap *args = data;
 
-	return radeon_mode_mmap(filp, dev, args->handle, false,
-				&args->addr_ptr);
+	return radeon_mode_dumb_mmap(filp, dev, args->handle, &args->addr_ptr);
 }
 
 int radeon_gem_busy_ioctl(struct drm_device *dev, void *data,
@@ -763,7 +746,6 @@ int radeon_mode_dumb_create(struct drm_file *file_priv,
 		return -ENOMEM;
 
 	r = drm_gem_handle_create(file_priv, gobj, &handle);
-	gobj->dumb = true;
 	/* drop reference from allocate - handle holds it now */
 	drm_gem_object_unreference_unlocked(gobj);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 7d68223eb46..86fc56434b2 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -529,9 +529,6 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
 			u32 current_domain =
 				radeon_mem_type_to_domain(bo->tbo.mem.mem_type);
 
-			WARN_ONCE(bo->gem_base.dumb,
-				  "GPU use of dumb buffer is illegal.\n");
-
 			/* Check if this buffer will be moved and don't move it
 			 * if we have moved too many buffers for this IB already.
 			 *
diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
index 780511a459c..1e6ae1458f7 100644
--- a/include/drm/drm_gem.h
+++ b/include/drm/drm_gem.h
@@ -119,13 +119,6 @@ struct drm_gem_object {
 	 * simply leave it as NULL.
 	 */
 	struct dma_buf_attachment *import_attach;
-
-	/**
-	 * dumb - created as dumb buffer
-	 * Whether the gem object was created using the dumb buffer interface
-	 * as such it may not be used for GPU rendering.
-	 */
-	bool dumb;
 };
 
 void drm_gem_object_release(struct drm_gem_object *obj);
-- 
cgit v1.2.3-70-g09d2


From ef8f342b43c48035458306b5e5b3dcb949929b1d Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Tue, 23 Dec 2014 17:50:37 +0100
Subject: neigh: remove next ptr from struct neigh_table

After commit
d7480fd3b173 ("neigh: remove dynamic neigh table registration support"),
this field is not used anymore.

CC: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index eb070b3674a..76f708486aa 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -190,7 +190,6 @@ struct neigh_hash_table {
 
 
 struct neigh_table {
-	struct neigh_table	*next;
 	int			family;
 	int			entry_size;
 	int			key_len;
-- 
cgit v1.2.3-70-g09d2


From 5f35227ea34bb616c436d9da47fc325866c428f3 Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@nicira.com>
Date: Tue, 23 Dec 2014 22:37:26 -0800
Subject: net: Generalize ndo_gso_check to ndo_features_check

GSO isn't the only offload feature with restrictions that
potentially can't be expressed with the current features mechanism.
Checksum is another although it's a general issue that could in
theory apply to anything. Even if it may be possible to
implement these restrictions in other ways, it can result in
duplicate code or inefficient per-packet behavior.

This generalizes ndo_gso_check so that drivers can remove any
features that don't make sense for a given packet, similar to
netif_skb_features(). It also converts existing driver
restrictions to the new format, completing the work that was
done to support tunnel protocols since the issues apply to
checksums as well.

By actually removing features from the set that are used to do
offloading, it solves another problem with the existing
interface. In these cases, GSO would run with the original set
of features and not do anything because it appears that
segmentation is not required.

CC: Tom Herbert <therbert@google.com>
CC: Joe Stringer <joestringer@nicira.com>
CC: Eric Dumazet <edumazet@google.com>
CC: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
Acked-by:  Tom Herbert <therbert@google.com>
Fixes: 04ffcb255f22 ("net: Add ndo_gso_check")
Tested-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c |  8 ++++---
 drivers/net/ethernet/emulex/benet/be_main.c      |  8 ++++---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c   | 10 +++++----
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c |  8 ++++---
 include/linux/netdevice.h                        | 20 +++++++++--------
 include/net/vxlan.h                              | 28 ++++++++++++++++++++----
 net/core/dev.c                                   | 23 +++++++++++--------
 7 files changed, 70 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 9f5e38769a2..72eef9fc883 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12553,9 +12553,11 @@ static int bnx2x_get_phys_port_id(struct net_device *netdev,
 	return 0;
 }
 
-static bool bnx2x_gso_check(struct sk_buff *skb, struct net_device *dev)
+static netdev_features_t bnx2x_features_check(struct sk_buff *skb,
+					      struct net_device *dev,
+					      netdev_features_t features)
 {
-	return vxlan_gso_check(skb);
+	return vxlan_features_check(skb, features);
 }
 
 static const struct net_device_ops bnx2x_netdev_ops = {
@@ -12589,7 +12591,7 @@ static const struct net_device_ops bnx2x_netdev_ops = {
 #endif
 	.ndo_get_phys_port_id	= bnx2x_get_phys_port_id,
 	.ndo_set_vf_link_state	= bnx2x_set_vf_link_state,
-	.ndo_gso_check		= bnx2x_gso_check,
+	.ndo_features_check	= bnx2x_features_check,
 };
 
 static int bnx2x_set_coherency_mask(struct bnx2x *bp)
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 196073110e3..41a0a5498da 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -4459,9 +4459,11 @@ done:
 	adapter->vxlan_port_count--;
 }
 
-static bool be_gso_check(struct sk_buff *skb, struct net_device *dev)
+static netdev_features_t be_features_check(struct sk_buff *skb,
+					   struct net_device *dev,
+					   netdev_features_t features)
 {
-	return vxlan_gso_check(skb);
+	return vxlan_features_check(skb, features);
 }
 #endif
 
@@ -4492,7 +4494,7 @@ static const struct net_device_ops be_netdev_ops = {
 #ifdef CONFIG_BE2NET_VXLAN
 	.ndo_add_vxlan_port	= be_add_vxlan_port,
 	.ndo_del_vxlan_port	= be_del_vxlan_port,
-	.ndo_gso_check		= be_gso_check,
+	.ndo_features_check	= be_features_check,
 #endif
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 190cbd931f6..d0d6dc1b8e4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2365,9 +2365,11 @@ static void mlx4_en_del_vxlan_port(struct  net_device *dev,
 	queue_work(priv->mdev->workqueue, &priv->vxlan_del_task);
 }
 
-static bool mlx4_en_gso_check(struct sk_buff *skb, struct net_device *dev)
+static netdev_features_t mlx4_en_features_check(struct sk_buff *skb,
+						struct net_device *dev,
+						netdev_features_t features)
 {
-	return vxlan_gso_check(skb);
+	return vxlan_features_check(skb, features);
 }
 #endif
 
@@ -2400,7 +2402,7 @@ static const struct net_device_ops mlx4_netdev_ops = {
 #ifdef CONFIG_MLX4_EN_VXLAN
 	.ndo_add_vxlan_port	= mlx4_en_add_vxlan_port,
 	.ndo_del_vxlan_port	= mlx4_en_del_vxlan_port,
-	.ndo_gso_check		= mlx4_en_gso_check,
+	.ndo_features_check	= mlx4_en_features_check,
 #endif
 };
 
@@ -2434,7 +2436,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
 #ifdef CONFIG_MLX4_EN_VXLAN
 	.ndo_add_vxlan_port	= mlx4_en_add_vxlan_port,
 	.ndo_del_vxlan_port	= mlx4_en_del_vxlan_port,
-	.ndo_gso_check		= mlx4_en_gso_check,
+	.ndo_features_check	= mlx4_en_features_check,
 #endif
 };
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 1aa25b13ace..9929b97cfb3 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -505,9 +505,11 @@ static void qlcnic_del_vxlan_port(struct net_device *netdev,
 	adapter->flags |= QLCNIC_DEL_VXLAN_PORT;
 }
 
-static bool qlcnic_gso_check(struct sk_buff *skb, struct net_device *dev)
+static netdev_features_t qlcnic_features_check(struct sk_buff *skb,
+					       struct net_device *dev,
+					       netdev_features_t features)
 {
-	return vxlan_gso_check(skb);
+	return vxlan_features_check(skb, features);
 }
 #endif
 
@@ -532,7 +534,7 @@ static const struct net_device_ops qlcnic_netdev_ops = {
 #ifdef CONFIG_QLCNIC_VXLAN
 	.ndo_add_vxlan_port	= qlcnic_add_vxlan_port,
 	.ndo_del_vxlan_port	= qlcnic_del_vxlan_port,
-	.ndo_gso_check		= qlcnic_gso_check,
+	.ndo_features_check	= qlcnic_features_check,
 #endif
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = qlcnic_poll_controller,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c31f74d76eb..679e6e90aa4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1012,12 +1012,15 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *	Callback to use for xmit over the accelerated station. This
  *	is used in place of ndo_start_xmit on accelerated net
  *	devices.
- * bool	(*ndo_gso_check) (struct sk_buff *skb,
- *			  struct net_device *dev);
+ * netdev_features_t (*ndo_features_check) (struct sk_buff *skb,
+ *					    struct net_device *dev
+ *					    netdev_features_t features);
  *	Called by core transmit path to determine if device is capable of
- *	performing GSO on a packet. The device returns true if it is
- *	able to GSO the packet, false otherwise. If the return value is
- *	false the stack will do software GSO.
+ *	performing offload operations on a given packet. This is to give
+ *	the device an opportunity to implement any restrictions that cannot
+ *	be otherwise expressed by feature flags. The check is called with
+ *	the set of features that the stack has calculated and it returns
+ *	those the driver believes to be appropriate.
  *
  * int (*ndo_switch_parent_id_get)(struct net_device *dev,
  *				   struct netdev_phys_item_id *psid);
@@ -1178,8 +1181,9 @@ struct net_device_ops {
 							struct net_device *dev,
 							void *priv);
 	int			(*ndo_get_lock_subclass)(struct net_device *dev);
-	bool			(*ndo_gso_check) (struct sk_buff *skb,
-						  struct net_device *dev);
+	netdev_features_t	(*ndo_features_check) (struct sk_buff *skb,
+						       struct net_device *dev,
+						       netdev_features_t features);
 #ifdef CONFIG_NET_SWITCHDEV
 	int			(*ndo_switch_parent_id_get)(struct net_device *dev,
 							    struct netdev_phys_item_id *psid);
@@ -3611,8 +3615,6 @@ static inline bool netif_needs_gso(struct net_device *dev, struct sk_buff *skb,
 				   netdev_features_t features)
 {
 	return skb_is_gso(skb) && (!skb_gso_ok(skb, features) ||
-		(dev->netdev_ops->ndo_gso_check &&
-		 !dev->netdev_ops->ndo_gso_check(skb, dev)) ||
 		unlikely((skb->ip_summed != CHECKSUM_PARTIAL) &&
 			 (skb->ip_summed != CHECKSUM_UNNECESSARY)));
 }
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 57cccd0052e..903461aa564 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -1,6 +1,9 @@
 #ifndef __NET_VXLAN_H
 #define __NET_VXLAN_H 1
 
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/if_vlan.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/udp.h>
@@ -51,16 +54,33 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 		   __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
 		   __be16 src_port, __be16 dst_port, __be32 vni, bool xnet);
 
-static inline bool vxlan_gso_check(struct sk_buff *skb)
+static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
+						     netdev_features_t features)
 {
-	if ((skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) &&
+	u8 l4_hdr = 0;
+
+	if (!skb->encapsulation)
+		return features;
+
+	switch (vlan_get_protocol(skb)) {
+	case htons(ETH_P_IP):
+		l4_hdr = ip_hdr(skb)->protocol;
+		break;
+	case htons(ETH_P_IPV6):
+		l4_hdr = ipv6_hdr(skb)->nexthdr;
+		break;
+	default:
+		return features;;
+	}
+
+	if ((l4_hdr == IPPROTO_UDP) &&
 	    (skb->inner_protocol_type != ENCAP_TYPE_ETHER ||
 	     skb->inner_protocol != htons(ETH_P_TEB) ||
 	     (skb_inner_mac_header(skb) - skb_transport_header(skb) !=
 	      sizeof(struct udphdr) + sizeof(struct vxlanhdr))))
-		return false;
+		return features & ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK);
 
-	return true;
+	return features;
 }
 
 /* IP header + UDP + VXLAN + Ethernet header */
diff --git a/net/core/dev.c b/net/core/dev.c
index 0094562b732..683d493aa1b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2563,7 +2563,7 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
 
 netdev_features_t netif_skb_features(struct sk_buff *skb)
 {
-	const struct net_device *dev = skb->dev;
+	struct net_device *dev = skb->dev;
 	netdev_features_t features = dev->features;
 	u16 gso_segs = skb_shinfo(skb)->gso_segs;
 	__be16 protocol = skb->protocol;
@@ -2571,13 +2571,20 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
 	if (gso_segs > dev->gso_max_segs || gso_segs < dev->gso_min_segs)
 		features &= ~NETIF_F_GSO_MASK;
 
+	/* If encapsulation offload request, verify we are testing
+	 * hardware encapsulation features instead of standard
+	 * features for the netdev
+	 */
+	if (skb->encapsulation)
+		features &= dev->hw_enc_features;
+
 	if (!vlan_tx_tag_present(skb)) {
 		if (unlikely(protocol == htons(ETH_P_8021Q) ||
 			     protocol == htons(ETH_P_8021AD))) {
 			struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
 			protocol = veh->h_vlan_encapsulated_proto;
 		} else {
-			return harmonize_features(skb, features);
+			goto finalize;
 		}
 	}
 
@@ -2595,6 +2602,11 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
 						     NETIF_F_HW_VLAN_CTAG_TX |
 						     NETIF_F_HW_VLAN_STAG_TX);
 
+finalize:
+	if (dev->netdev_ops->ndo_features_check)
+		features &= dev->netdev_ops->ndo_features_check(skb, dev,
+								features);
+
 	return harmonize_features(skb, features);
 }
 EXPORT_SYMBOL(netif_skb_features);
@@ -2665,13 +2677,6 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 	if (unlikely(!skb))
 		goto out_null;
 
-	/* If encapsulation offload request, verify we are testing
-	 * hardware encapsulation features instead of standard
-	 * features for the netdev
-	 */
-	if (skb->encapsulation)
-		features &= dev->hw_enc_features;
-
 	if (netif_needs_gso(dev, skb, features)) {
 		struct sk_buff *segs;
 
-- 
cgit v1.2.3-70-g09d2


From f8403a2e47afb37bcd3b7e286996d138a116c39d Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 22 Dec 2014 18:56:36 +0100
Subject: genetlink: pass only network namespace to genl_has_listeners()

There's no point to force the caller to know about the internal
genl_sock to use inside struct net, just have them pass the network
namespace. This doesn't really change code generation since it's
an inline, but makes the caller less magic - there's never any
reason to pass another socket.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h    | 4 ++--
 net/openvswitch/datapath.c | 3 +--
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index af10c2cf8a1..38620da4aa7 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -395,11 +395,11 @@ static inline int genl_set_err(struct genl_family *family, struct net *net,
 }
 
 static inline int genl_has_listeners(struct genl_family *family,
-				     struct sock *sk, unsigned int group)
+				     struct net *net, unsigned int group)
 {
 	if (WARN_ON_ONCE(group >= family->n_mcgrps))
 		return -EINVAL;
 	group = family->mcgrp_offset + group;
-	return netlink_has_listeners(sk, group);
+	return netlink_has_listeners(net->genl_sock, group);
 }
 #endif	/* __NET_GENERIC_NETLINK_H */
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 332b5a03173..4e9a5f035cb 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -83,8 +83,7 @@ static bool ovs_must_notify(struct genl_family *family, struct genl_info *info,
 			    unsigned int group)
 {
 	return info->nlhdr->nlmsg_flags & NLM_F_ECHO ||
-	       genl_has_listeners(family, genl_info_net(info)->genl_sock,
-				  group);
+	       genl_has_listeners(family, genl_info_net(info), group);
 }
 
 static void ovs_notify(struct genl_family *family,
-- 
cgit v1.2.3-70-g09d2


From c380d9a7afff0e4c2e5f3c1c2dc7d2f4214dd962 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 23 Dec 2014 20:54:40 +0100
Subject: genetlink: pass multicast bind/unbind to families

In order to make the newly fixed multicast bind/unbind
functionality in generic netlink, pass them down to the
appropriate family.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h |  5 +++++
 net/netlink/genetlink.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 64 insertions(+)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 38620da4aa7..3ed31e5a445 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -31,6 +31,9 @@ struct genl_info;
  *	do additional, common, filtering and return an error
  * @post_doit: called after an operation's doit callback, it may
  *	undo operations done by pre_doit, for example release locks
+ * @mcast_bind: a socket bound to the given multicast group (which
+ *	is given as the offset into the groups array)
+ * @mcast_unbind: a socket was unbound from the given multicast group
  * @attrbuf: buffer to store parsed attributes
  * @family_list: family list
  * @mcgrps: multicast groups used by this family (private)
@@ -53,6 +56,8 @@ struct genl_family {
 	void			(*post_doit)(const struct genl_ops *ops,
 					     struct sk_buff *skb,
 					     struct genl_info *info);
+	int			(*mcast_bind)(int group);
+	void			(*mcast_unbind)(int group);
 	struct nlattr **	attrbuf;	/* private */
 	const struct genl_ops *	ops;		/* private */
 	const struct genl_multicast_group *mcgrps; /* private */
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 76393f2f4b2..05bf40bbd18 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -983,11 +983,70 @@ static struct genl_multicast_group genl_ctrl_groups[] = {
 	{ .name = "notify", },
 };
 
+static int genl_bind(int group)
+{
+	int i, err;
+	bool found = false;
+
+	down_read(&cb_lock);
+	for (i = 0; i < GENL_FAM_TAB_SIZE; i++) {
+		struct genl_family *f;
+
+		list_for_each_entry(f, genl_family_chain(i), family_list) {
+			if (group >= f->mcgrp_offset &&
+			    group < f->mcgrp_offset + f->n_mcgrps) {
+				int fam_grp = group - f->mcgrp_offset;
+
+				if (f->mcast_bind)
+					err = f->mcast_bind(fam_grp);
+				else
+					err = 0;
+				found = true;
+				break;
+			}
+		}
+	}
+	up_read(&cb_lock);
+
+	if (WARN_ON(!found))
+		err = 0;
+
+	return err;
+}
+
+static void genl_unbind(int group)
+{
+	int i;
+	bool found = false;
+
+	down_read(&cb_lock);
+	for (i = 0; i < GENL_FAM_TAB_SIZE; i++) {
+		struct genl_family *f;
+
+		list_for_each_entry(f, genl_family_chain(i), family_list) {
+			if (group >= f->mcgrp_offset &&
+			    group < f->mcgrp_offset + f->n_mcgrps) {
+				int fam_grp = group - f->mcgrp_offset;
+
+				if (f->mcast_unbind)
+					f->mcast_unbind(fam_grp);
+				found = true;
+				break;
+			}
+		}
+	}
+	up_read(&cb_lock);
+
+	WARN_ON(!found);
+}
+
 static int __net_init genl_pernet_init(struct net *net)
 {
 	struct netlink_kernel_cfg cfg = {
 		.input		= genl_rcv,
 		.flags		= NL_CFG_F_NONROOT_RECV,
+		.bind		= genl_bind,
+		.unbind		= genl_unbind,
 	};
 
 	/* we'll bump the group number right afterwards */
-- 
cgit v1.2.3-70-g09d2


From 023e2cfa36c31b0ad28c159a1bb0d61ff57334c8 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 23 Dec 2014 21:00:06 +0100
Subject: netlink/genetlink: pass network namespace to bind/unbind

Netlink families can exist in multiple namespaces, and for the most
part multicast subscriptions are per network namespace. Thus it only
makes sense to have bind/unbind notifications per network namespace.

To achieve this, pass the network namespace of a given client socket
to the bind/unbind functions.

Also do this in generic netlink, and there also make sure that any
bind for multicast groups that only exist in init_net is rejected.
This isn't really a problem if it is accepted since a client in a
different namespace will never receive any notifications from such
a group, but it can confuse the family if not rejected (it's also
possible to silently (without telling the family) accept it, but it
would also have to be ignored on unbind so families that take any
kind of action on bind/unbind won't do unnecessary work for invalid
clients like that.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netlink.h   |  4 ++--
 include/net/genetlink.h   |  4 ++--
 kernel/audit.c            |  2 +-
 net/netfilter/nfnetlink.c |  2 +-
 net/netlink/af_netlink.c  | 21 +++++++++++----------
 net/netlink/af_netlink.h  |  8 ++++----
 net/netlink/genetlink.c   | 12 +++++++-----
 7 files changed, 28 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 9e572daa15d..02fc86d2348 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -46,8 +46,8 @@ struct netlink_kernel_cfg {
 	unsigned int	flags;
 	void		(*input)(struct sk_buff *skb);
 	struct mutex	*cb_mutex;
-	int		(*bind)(int group);
-	void		(*unbind)(int group);
+	int		(*bind)(struct net *net, int group);
+	void		(*unbind)(struct net *net, int group);
 	bool		(*compare)(struct net *net, struct sock *sk);
 };
 
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 3ed31e5a445..84125088c30 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -56,8 +56,8 @@ struct genl_family {
 	void			(*post_doit)(const struct genl_ops *ops,
 					     struct sk_buff *skb,
 					     struct genl_info *info);
-	int			(*mcast_bind)(int group);
-	void			(*mcast_unbind)(int group);
+	int			(*mcast_bind)(struct net *net, int group);
+	void			(*mcast_unbind)(struct net *net, int group);
 	struct nlattr **	attrbuf;	/* private */
 	const struct genl_ops *	ops;		/* private */
 	const struct genl_multicast_group *mcgrps; /* private */
diff --git a/kernel/audit.c b/kernel/audit.c
index f8f203e8018..aba9d9fadf0 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1100,7 +1100,7 @@ static void audit_receive(struct sk_buff  *skb)
 }
 
 /* Run custom bind function on netlink socket group connect or bind requests. */
-static int audit_bind(int group)
+static int audit_bind(struct net *net, int group)
 {
 	if (!capable(CAP_AUDIT_READ))
 		return -EPERM;
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 13c2e17bbe2..cde4a6702fa 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -463,7 +463,7 @@ static void nfnetlink_rcv(struct sk_buff *skb)
 }
 
 #ifdef CONFIG_MODULES
-static int nfnetlink_bind(int group)
+static int nfnetlink_bind(struct net *net, int group)
 {
 	const struct nfnetlink_subsystem *ss;
 	int type;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index f29b63fad93..84ea76ca3f1 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1141,8 +1141,8 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	struct module *module = NULL;
 	struct mutex *cb_mutex;
 	struct netlink_sock *nlk;
-	int (*bind)(int group);
-	void (*unbind)(int group);
+	int (*bind)(struct net *net, int group);
+	void (*unbind)(struct net *net, int group);
 	int err = 0;
 
 	sock->state = SS_UNCONNECTED;
@@ -1251,7 +1251,7 @@ static int netlink_release(struct socket *sock)
 
 		for (i = 0; i < nlk->ngroups; i++)
 			if (test_bit(i, nlk->groups))
-				nlk->netlink_unbind(i + 1);
+				nlk->netlink_unbind(sock_net(sk), i + 1);
 	}
 	kfree(nlk->groups);
 	nlk->groups = NULL;
@@ -1418,8 +1418,9 @@ static int netlink_realloc_groups(struct sock *sk)
 }
 
 static void netlink_undo_bind(int group, long unsigned int groups,
-			      struct netlink_sock *nlk)
+			      struct sock *sk)
 {
+	struct netlink_sock *nlk = nlk_sk(sk);
 	int undo;
 
 	if (!nlk->netlink_unbind)
@@ -1427,7 +1428,7 @@ static void netlink_undo_bind(int group, long unsigned int groups,
 
 	for (undo = 0; undo < group; undo++)
 		if (test_bit(undo, &groups))
-			nlk->netlink_unbind(undo);
+			nlk->netlink_unbind(sock_net(sk), undo);
 }
 
 static int netlink_bind(struct socket *sock, struct sockaddr *addr,
@@ -1465,10 +1466,10 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		for (group = 0; group < nlk->ngroups; group++) {
 			if (!test_bit(group, &groups))
 				continue;
-			err = nlk->netlink_bind(group);
+			err = nlk->netlink_bind(net, group);
 			if (!err)
 				continue;
-			netlink_undo_bind(group, groups, nlk);
+			netlink_undo_bind(group, groups, sk);
 			return err;
 		}
 	}
@@ -1478,7 +1479,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			netlink_insert(sk, net, nladdr->nl_pid) :
 			netlink_autobind(sock);
 		if (err) {
-			netlink_undo_bind(nlk->ngroups, groups, nlk);
+			netlink_undo_bind(nlk->ngroups, groups, sk);
 			return err;
 		}
 	}
@@ -2129,7 +2130,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		if (!val || val - 1 >= nlk->ngroups)
 			return -EINVAL;
 		if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) {
-			err = nlk->netlink_bind(val);
+			err = nlk->netlink_bind(sock_net(sk), val);
 			if (err)
 				return err;
 		}
@@ -2138,7 +2139,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 					 optname == NETLINK_ADD_MEMBERSHIP);
 		netlink_table_ungrab();
 		if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind)
-			nlk->netlink_unbind(val);
+			nlk->netlink_unbind(sock_net(sk), val);
 
 		err = 0;
 		break;
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index b20a1731759..f123a88496f 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -39,8 +39,8 @@ struct netlink_sock {
 	struct mutex		*cb_mutex;
 	struct mutex		cb_def_mutex;
 	void			(*netlink_rcv)(struct sk_buff *skb);
-	int			(*netlink_bind)(int group);
-	void			(*netlink_unbind)(int group);
+	int			(*netlink_bind)(struct net *net, int group);
+	void			(*netlink_unbind)(struct net *net, int group);
 	struct module		*module;
 #ifdef CONFIG_NETLINK_MMAP
 	struct mutex		pg_vec_lock;
@@ -65,8 +65,8 @@ struct netlink_table {
 	unsigned int		groups;
 	struct mutex		*cb_mutex;
 	struct module		*module;
-	int			(*bind)(int group);
-	void			(*unbind)(int group);
+	int			(*bind)(struct net *net, int group);
+	void			(*unbind)(struct net *net, int group);
 	bool			(*compare)(struct net *net, struct sock *sock);
 	int			registered;
 };
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 05bf40bbd18..91566ed36c4 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -983,7 +983,7 @@ static struct genl_multicast_group genl_ctrl_groups[] = {
 	{ .name = "notify", },
 };
 
-static int genl_bind(int group)
+static int genl_bind(struct net *net, int group)
 {
 	int i, err;
 	bool found = false;
@@ -997,8 +997,10 @@ static int genl_bind(int group)
 			    group < f->mcgrp_offset + f->n_mcgrps) {
 				int fam_grp = group - f->mcgrp_offset;
 
-				if (f->mcast_bind)
-					err = f->mcast_bind(fam_grp);
+				if (!f->netnsok && net != &init_net)
+					err = -ENOENT;
+				else if (f->mcast_bind)
+					err = f->mcast_bind(net, fam_grp);
 				else
 					err = 0;
 				found = true;
@@ -1014,7 +1016,7 @@ static int genl_bind(int group)
 	return err;
 }
 
-static void genl_unbind(int group)
+static void genl_unbind(struct net *net, int group)
 {
 	int i;
 	bool found = false;
@@ -1029,7 +1031,7 @@ static void genl_unbind(int group)
 				int fam_grp = group - f->mcgrp_offset;
 
 				if (f->mcast_unbind)
-					f->mcast_unbind(fam_grp);
+					f->mcast_unbind(net, fam_grp);
 				found = true;
 				break;
 			}
-- 
cgit v1.2.3-70-g09d2


From b28e0506fafd9c987bba7a6a71ea02a37fcabdea Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 25 Dec 2014 16:03:27 +0200
Subject: virtio_ring: document alignment requirements

Host needs to know vring element alignment requirements:
simply doing alignof on structures doesn't work reliably: on some
platforms gcc has alignof(uint32_t) == 2.

Add macros for alignment as specified in virtio 1.0 cs01,
export them to userspace as well.

Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/uapi/linux/virtio_ring.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
index 61c818a7fe7..a3318f31e8e 100644
--- a/include/uapi/linux/virtio_ring.h
+++ b/include/uapi/linux/virtio_ring.h
@@ -101,6 +101,13 @@ struct vring {
 	struct vring_used *used;
 };
 
+/* Alignment requirements for vring elements.
+ * When using pre-virtio 1.0 layout, these fall out naturally.
+ */
+#define VRING_AVAIL_ALIGN_SIZE 2
+#define VRING_USED_ALIGN_SIZE 4
+#define VRING_DESC_ALIGN_SIZE 16
+
 /* The standard layout for the ring is a continuous chunk of memory which looks
  * like this.  We assume num is a power of 2.
  *
-- 
cgit v1.2.3-70-g09d2


From 45f87de57f8fad59302fd263dd81ffa4843b5b24 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.cz>
Date: Mon, 29 Dec 2014 20:30:35 +0100
Subject: mm: get rid of radix tree gfp mask for pagecache_get_page

Commit 2457aec63745 ("mm: non-atomically mark page accessed during page
cache allocation where possible") has added a separate parameter for
specifying gfp mask for radix tree allocations.

Not only this is less than optimal from the API point of view because it
is error prone, it is also buggy currently because
grab_cache_page_write_begin is using GFP_KERNEL for radix tree and if
fgp_flags doesn't contain FGP_NOFS (mostly controlled by fs by
AOP_FLAG_NOFS flag) but the mapping_gfp_mask has __GFP_FS cleared then
the radix tree allocation wouldn't obey the restriction and might
recurse into filesystem and cause deadlocks.  This is the case for most
filesystems unfortunately because only ext4 and gfs2 are using
AOP_FLAG_NOFS.

Let's simply remove radix_gfp_mask parameter because the allocation
context is same for both page cache and for the radix tree.  Just make
sure that the radix tree gets only the sane subset of the mask (e.g.  do
not pass __GFP_WRITE).

Long term it is more preferable to convert remaining users of
AOP_FLAG_NOFS to use mapping_gfp_mask instead and simplify this
interface even further.

Reported-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagemap.h | 13 ++++++-------
 mm/filemap.c            | 29 ++++++++++++-----------------
 2 files changed, 18 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 7ea069cd325..4b3736f7065 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -251,7 +251,7 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping,
 #define FGP_NOWAIT		0x00000020
 
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
-		int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask);
+		int fgp_flags, gfp_t cache_gfp_mask);
 
 /**
  * find_get_page - find and get a page reference
@@ -266,13 +266,13 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
 static inline struct page *find_get_page(struct address_space *mapping,
 					pgoff_t offset)
 {
-	return pagecache_get_page(mapping, offset, 0, 0, 0);
+	return pagecache_get_page(mapping, offset, 0, 0);
 }
 
 static inline struct page *find_get_page_flags(struct address_space *mapping,
 					pgoff_t offset, int fgp_flags)
 {
-	return pagecache_get_page(mapping, offset, fgp_flags, 0, 0);
+	return pagecache_get_page(mapping, offset, fgp_flags, 0);
 }
 
 /**
@@ -292,7 +292,7 @@ static inline struct page *find_get_page_flags(struct address_space *mapping,
 static inline struct page *find_lock_page(struct address_space *mapping,
 					pgoff_t offset)
 {
-	return pagecache_get_page(mapping, offset, FGP_LOCK, 0, 0);
+	return pagecache_get_page(mapping, offset, FGP_LOCK, 0);
 }
 
 /**
@@ -319,7 +319,7 @@ static inline struct page *find_or_create_page(struct address_space *mapping,
 {
 	return pagecache_get_page(mapping, offset,
 					FGP_LOCK|FGP_ACCESSED|FGP_CREAT,
-					gfp_mask, gfp_mask & GFP_RECLAIM_MASK);
+					gfp_mask);
 }
 
 /**
@@ -340,8 +340,7 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
 {
 	return pagecache_get_page(mapping, index,
 			FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
-			mapping_gfp_mask(mapping),
-			GFP_NOFS);
+			mapping_gfp_mask(mapping));
 }
 
 struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
diff --git a/mm/filemap.c b/mm/filemap.c
index bd8543c6508..673e4581a2e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1046,8 +1046,7 @@ EXPORT_SYMBOL(find_lock_entry);
  * @mapping: the address_space to search
  * @offset: the page index
  * @fgp_flags: PCG flags
- * @cache_gfp_mask: gfp mask to use for the page cache data page allocation
- * @radix_gfp_mask: gfp mask to use for radix tree node allocation
+ * @gfp_mask: gfp mask to use for the page cache data page allocation
  *
  * Looks up the page cache slot at @mapping & @offset.
  *
@@ -1056,11 +1055,9 @@ EXPORT_SYMBOL(find_lock_entry);
  * FGP_ACCESSED: the page will be marked accessed
  * FGP_LOCK: Page is return locked
  * FGP_CREAT: If page is not present then a new page is allocated using
- *		@cache_gfp_mask and added to the page cache and the VM's LRU
- *		list. If radix tree nodes are allocated during page cache
- *		insertion then @radix_gfp_mask is used. The page is returned
- *		locked and with an increased refcount. Otherwise, %NULL is
- *		returned.
+ *		@gfp_mask and added to the page cache and the VM's LRU
+ *		list. The page is returned locked and with an increased
+ *		refcount. Otherwise, %NULL is returned.
  *
  * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
  * if the GFP flags specified for FGP_CREAT are atomic.
@@ -1068,7 +1065,7 @@ EXPORT_SYMBOL(find_lock_entry);
  * If there is a page cache page, it is returned with an increased refcount.
  */
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
-	int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask)
+	int fgp_flags, gfp_t gfp_mask)
 {
 	struct page *page;
 
@@ -1105,13 +1102,11 @@ no_page:
 	if (!page && (fgp_flags & FGP_CREAT)) {
 		int err;
 		if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
-			cache_gfp_mask |= __GFP_WRITE;
-		if (fgp_flags & FGP_NOFS) {
-			cache_gfp_mask &= ~__GFP_FS;
-			radix_gfp_mask &= ~__GFP_FS;
-		}
+			gfp_mask |= __GFP_WRITE;
+		if (fgp_flags & FGP_NOFS)
+			gfp_mask &= ~__GFP_FS;
 
-		page = __page_cache_alloc(cache_gfp_mask);
+		page = __page_cache_alloc(gfp_mask);
 		if (!page)
 			return NULL;
 
@@ -1122,7 +1117,8 @@ no_page:
 		if (fgp_flags & FGP_ACCESSED)
 			__SetPageReferenced(page);
 
-		err = add_to_page_cache_lru(page, mapping, offset, radix_gfp_mask);
+		err = add_to_page_cache_lru(page, mapping, offset,
+				gfp_mask & GFP_RECLAIM_MASK);
 		if (unlikely(err)) {
 			page_cache_release(page);
 			page = NULL;
@@ -2443,8 +2439,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
 		fgp_flags |= FGP_NOFS;
 
 	page = pagecache_get_page(mapping, index, fgp_flags,
-			mapping_gfp_mask(mapping),
-			GFP_KERNEL);
+			mapping_gfp_mask(mapping));
 	if (page)
 		wait_for_stable_page(page);
 
-- 
cgit v1.2.3-70-g09d2


From 62f64a880af2e82d1b41cb02cb43b88d30413993 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 29 Dec 2014 19:41:40 +0100
Subject: ALSA: pcm: Fix kerneldoc for params_*() functions

Fix a copy and paste error in the kernel doc description for the params_*()
functions.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 1e7f74acc2e..b429b73e875 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -857,7 +857,7 @@ static inline unsigned int params_channels(const struct snd_pcm_hw_params *p)
 }
 
 /**
- * params_channels - Get the sample rate from the hw params
+ * params_rate - Get the sample rate from the hw params
  * @p: hw params
  */
 static inline unsigned int params_rate(const struct snd_pcm_hw_params *p)
@@ -866,7 +866,7 @@ static inline unsigned int params_rate(const struct snd_pcm_hw_params *p)
 }
 
 /**
- * params_channels - Get the period size (in frames) from the hw params
+ * params_period_size - Get the period size (in frames) from the hw params
  * @p: hw params
  */
 static inline unsigned int params_period_size(const struct snd_pcm_hw_params *p)
@@ -875,7 +875,7 @@ static inline unsigned int params_period_size(const struct snd_pcm_hw_params *p)
 }
 
 /**
- * params_channels - Get the number of periods from the hw params
+ * params_periods - Get the number of periods from the hw params
  * @p: hw params
  */
 static inline unsigned int params_periods(const struct snd_pcm_hw_params *p)
@@ -884,7 +884,7 @@ static inline unsigned int params_periods(const struct snd_pcm_hw_params *p)
 }
 
 /**
- * params_channels - Get the buffer size (in frames) from the hw params
+ * params_buffer_size - Get the buffer size (in frames) from the hw params
  * @p: hw params
  */
 static inline unsigned int params_buffer_size(const struct snd_pcm_hw_params *p)
@@ -893,7 +893,7 @@ static inline unsigned int params_buffer_size(const struct snd_pcm_hw_params *p)
 }
 
 /**
- * params_channels - Get the buffer size (in bytes) from the hw params
+ * params_buffer_bytes - Get the buffer size (in bytes) from the hw params
  * @p: hw params
  */
 static inline unsigned int params_buffer_bytes(const struct snd_pcm_hw_params *p)
-- 
cgit v1.2.3-70-g09d2


From 1e359a5de861a57aa04d92bb620f52a5c1d7f8b1 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 5 Jan 2015 10:28:49 +0100
Subject: Revert "mac80211: Fix accounting of the tailroom-needed counter"

This reverts commit ca34e3b5c808385b175650605faa29e71e91991b.

It turns out that the p54 and cw2100 drivers assume that there's
tailroom even when they don't say they really need it. However,
there's currently no way for them to explicitly say they do need
it, so for now revert this.

This fixes https://bugzilla.kernel.org/show_bug.cgi?id=90331.

Cc: stable@vger.kernel.org
Fixes: ca34e3b5c808 ("mac80211: Fix accounting of the tailroom-needed counter")
Reported-by: Christopher Chavez <chrischavez@gmx.us>
Bisected-by: Larry Finger <Larry.Finger@lwfinger.net>
Debugged-by: Christian Lamparter <chunkeey@googlemail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  7 ++-----
 net/mac80211/key.c     | 12 +++++++++---
 2 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 58d719ddaa6..29c7be8808d 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1270,8 +1270,7 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev);
  *
  * @IEEE80211_KEY_FLAG_GENERATE_IV: This flag should be set by the
  *	driver to indicate that it requires IV generation for this
- *	particular key. Setting this flag does not necessarily mean that SKBs
- *	will have sufficient tailroom for ICV or MIC.
+ *	particular key.
  * @IEEE80211_KEY_FLAG_GENERATE_MMIC: This flag should be set by
  *	the driver for a TKIP key if it requires Michael MIC
  *	generation in software.
@@ -1283,9 +1282,7 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev);
  * @IEEE80211_KEY_FLAG_PUT_IV_SPACE: This flag should be set by the driver
  *	if space should be prepared for the IV, but the IV
  *	itself should not be generated. Do not set together with
- *	@IEEE80211_KEY_FLAG_GENERATE_IV on the same key. Setting this flag does
- *	not necessarily mean that SKBs will have sufficient tailroom for ICV or
- *	MIC.
+ *	@IEEE80211_KEY_FLAG_GENERATE_IV on the same key.
  * @IEEE80211_KEY_FLAG_RX_MGMT: This key will be used to decrypt received
  *	management frames. The flag can help drivers that have a hardware
  *	crypto implementation that doesn't deal with management frames
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 0bb7038121a..bd4e46ec32b 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -140,7 +140,9 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 	if (!ret) {
 		key->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE;
 
-		if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC))
+		if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
+		      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV) ||
+		      (key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)))
 			sdata->crypto_tx_tailroom_needed_cnt--;
 
 		WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) &&
@@ -188,7 +190,9 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key)
 	sta = key->sta;
 	sdata = key->sdata;
 
-	if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC))
+	if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
+	      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV) ||
+	      (key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)))
 		increment_tailroom_need_count(sdata);
 
 	ret = drv_set_key(key->local, DISABLE_KEY, sdata,
@@ -884,7 +888,9 @@ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf)
 	if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) {
 		key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE;
 
-		if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC))
+		if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
+		      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV) ||
+		      (key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)))
 			increment_tailroom_need_count(key->sdata);
 	}
 
-- 
cgit v1.2.3-70-g09d2


From af8f3f514d193eb353f9b6cea503c55d074e6153 Mon Sep 17 00:00:00 2001
From: Hanjun Guo <hanjun.guo@linaro.com>
Date: Sun, 4 Jan 2015 18:55:02 +0800
Subject: ACPI / processor: Convert apic_id to phys_id to make it arch agnostic

apic_id in MADT table is the CPU hardware id which identify
it self in the system for x86 and ia64, OSPM will use it for
SMP init to map APIC ID to logical cpu number in the early
boot, when the DSDT/SSDT (ACPI namespace) is scanned later, the
ACPI processor driver is probed and the driver will use acpi_id
in DSDT to get the apic_id, then map to the logical cpu number
which is needed by the processor driver.

Before ACPI 5.0, only x86 and ia64 were supported in ACPI spec,
so apic_id is used both in arch code and ACPI core which is
pretty fine. Since ACPI 5.0, ARM is supported by ACPI and
APIC is not available on ARM, this will confuse people when
apic_id is both used by x86 and ARM in one function.

So convert apic_id to phys_id (which is the original meaning)
in ACPI processor dirver to make it arch agnostic, but leave the
arch dependent code unchanged, no functional change.

Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpi_processor.c | 21 +++++++++-------
 drivers/acpi/processor_core.c | 56 +++++++++++++++++++++----------------------
 include/acpi/processor.h      |  8 +++----
 3 files changed, 44 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 1fdf5e07a1c..f02b29eb0fd 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -170,7 +170,7 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	acpi_status status;
 	int ret;
 
-	if (pr->apic_id == -1)
+	if (pr->phys_id == -1)
 		return -ENODEV;
 
 	status = acpi_evaluate_integer(pr->handle, "_STA", NULL, &sta);
@@ -180,7 +180,7 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	cpu_maps_update_begin();
 	cpu_hotplug_begin();
 
-	ret = acpi_map_lsapic(pr->handle, pr->apic_id, &pr->id);
+	ret = acpi_map_lsapic(pr->handle, pr->phys_id, &pr->id);
 	if (ret)
 		goto out;
 
@@ -215,7 +215,7 @@ static int acpi_processor_get_info(struct acpi_device *device)
 	union acpi_object object = { 0 };
 	struct acpi_buffer buffer = { sizeof(union acpi_object), &object };
 	struct acpi_processor *pr = acpi_driver_data(device);
-	int apic_id, cpu_index, device_declaration = 0;
+	int phys_id, cpu_index, device_declaration = 0;
 	acpi_status status = AE_OK;
 	static int cpu0_initialized;
 	unsigned long long value;
@@ -262,15 +262,18 @@ static int acpi_processor_get_info(struct acpi_device *device)
 		pr->acpi_id = value;
 	}
 
-	apic_id = acpi_get_apicid(pr->handle, device_declaration, pr->acpi_id);
-	if (apic_id < 0)
-		acpi_handle_debug(pr->handle, "failed to get CPU APIC ID.\n");
-	pr->apic_id = apic_id;
+	phys_id = acpi_get_phys_id(pr->handle, device_declaration, pr->acpi_id);
+	if (phys_id < 0)
+		acpi_handle_debug(pr->handle, "failed to get CPU physical ID.\n");
+	pr->phys_id = phys_id;
 
-	cpu_index = acpi_map_cpuid(pr->apic_id, pr->acpi_id);
+	cpu_index = acpi_map_cpuid(pr->phys_id, pr->acpi_id);
 	if (!cpu0_initialized && !acpi_has_cpu_in_madt()) {
 		cpu0_initialized = 1;
-		/* Handle UP system running SMP kernel, with no LAPIC in MADT */
+		/*
+		 * Handle UP system running SMP kernel, with no CPU
+		 * entry in MADT
+		 */
 		if ((cpu_index == -1) && (num_online_cpus() == 1))
 			cpu_index = 0;
 	}
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index 342942f90a1..02e48394276 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -69,7 +69,7 @@ static int map_madt_entry(int type, u32 acpi_id)
 	unsigned long madt_end, entry;
 	static struct acpi_table_madt *madt;
 	static int read_madt;
-	int apic_id = -1;
+	int phys_id = -1;	/* CPU hardware ID */
 
 	if (!read_madt) {
 		if (ACPI_FAILURE(acpi_get_table(ACPI_SIG_MADT, 0,
@@ -79,7 +79,7 @@ static int map_madt_entry(int type, u32 acpi_id)
 	}
 
 	if (!madt)
-		return apic_id;
+		return phys_id;
 
 	entry = (unsigned long)madt;
 	madt_end = entry + madt->header.length;
@@ -91,18 +91,18 @@ static int map_madt_entry(int type, u32 acpi_id)
 		struct acpi_subtable_header *header =
 			(struct acpi_subtable_header *)entry;
 		if (header->type == ACPI_MADT_TYPE_LOCAL_APIC) {
-			if (!map_lapic_id(header, acpi_id, &apic_id))
+			if (!map_lapic_id(header, acpi_id, &phys_id))
 				break;
 		} else if (header->type == ACPI_MADT_TYPE_LOCAL_X2APIC) {
-			if (!map_x2apic_id(header, type, acpi_id, &apic_id))
+			if (!map_x2apic_id(header, type, acpi_id, &phys_id))
 				break;
 		} else if (header->type == ACPI_MADT_TYPE_LOCAL_SAPIC) {
-			if (!map_lsapic_id(header, type, acpi_id, &apic_id))
+			if (!map_lsapic_id(header, type, acpi_id, &phys_id))
 				break;
 		}
 		entry += header->length;
 	}
-	return apic_id;
+	return phys_id;
 }
 
 static int map_mat_entry(acpi_handle handle, int type, u32 acpi_id)
@@ -110,7 +110,7 @@ static int map_mat_entry(acpi_handle handle, int type, u32 acpi_id)
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 	union acpi_object *obj;
 	struct acpi_subtable_header *header;
-	int apic_id = -1;
+	int phys_id = -1;
 
 	if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer)))
 		goto exit;
@@ -126,38 +126,38 @@ static int map_mat_entry(acpi_handle handle, int type, u32 acpi_id)
 
 	header = (struct acpi_subtable_header *)obj->buffer.pointer;
 	if (header->type == ACPI_MADT_TYPE_LOCAL_APIC)
-		map_lapic_id(header, acpi_id, &apic_id);
+		map_lapic_id(header, acpi_id, &phys_id);
 	else if (header->type == ACPI_MADT_TYPE_LOCAL_SAPIC)
-		map_lsapic_id(header, type, acpi_id, &apic_id);
+		map_lsapic_id(header, type, acpi_id, &phys_id);
 	else if (header->type == ACPI_MADT_TYPE_LOCAL_X2APIC)
-		map_x2apic_id(header, type, acpi_id, &apic_id);
+		map_x2apic_id(header, type, acpi_id, &phys_id);
 
 exit:
 	kfree(buffer.pointer);
-	return apic_id;
+	return phys_id;
 }
 
-int acpi_get_apicid(acpi_handle handle, int type, u32 acpi_id)
+int acpi_get_phys_id(acpi_handle handle, int type, u32 acpi_id)
 {
-	int apic_id;
+	int phys_id;
 
-	apic_id = map_mat_entry(handle, type, acpi_id);
-	if (apic_id == -1)
-		apic_id = map_madt_entry(type, acpi_id);
+	phys_id = map_mat_entry(handle, type, acpi_id);
+	if (phys_id == -1)
+		phys_id = map_madt_entry(type, acpi_id);
 
-	return apic_id;
+	return phys_id;
 }
 
-int acpi_map_cpuid(int apic_id, u32 acpi_id)
+int acpi_map_cpuid(int phys_id, u32 acpi_id)
 {
 #ifdef CONFIG_SMP
 	int i;
 #endif
 
-	if (apic_id == -1) {
+	if (phys_id == -1) {
 		/*
 		 * On UP processor, there is no _MAT or MADT table.
-		 * So above apic_id is always set to -1.
+		 * So above phys_id is always set to -1.
 		 *
 		 * BIOS may define multiple CPU handles even for UP processor.
 		 * For example,
@@ -170,7 +170,7 @@ int acpi_map_cpuid(int apic_id, u32 acpi_id)
 		 *     Processor (CPU3, 0x03, 0x00000410, 0x06) {}
 		 * }
 		 *
-		 * Ignores apic_id and always returns 0 for the processor
+		 * Ignores phys_id and always returns 0 for the processor
 		 * handle with acpi id 0 if nr_cpu_ids is 1.
 		 * This should be the case if SMP tables are not found.
 		 * Return -1 for other CPU's handle.
@@ -178,28 +178,28 @@ int acpi_map_cpuid(int apic_id, u32 acpi_id)
 		if (nr_cpu_ids <= 1 && acpi_id == 0)
 			return acpi_id;
 		else
-			return apic_id;
+			return phys_id;
 	}
 
 #ifdef CONFIG_SMP
 	for_each_possible_cpu(i) {
-		if (cpu_physical_id(i) == apic_id)
+		if (cpu_physical_id(i) == phys_id)
 			return i;
 	}
 #else
 	/* In UP kernel, only processor 0 is valid */
-	if (apic_id == 0)
-		return apic_id;
+	if (phys_id == 0)
+		return phys_id;
 #endif
 	return -1;
 }
 
 int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
 {
-	int apic_id;
+	int phys_id;
 
-	apic_id = acpi_get_apicid(handle, type, acpi_id);
+	phys_id = acpi_get_phys_id(handle, type, acpi_id);
 
-	return acpi_map_cpuid(apic_id, acpi_id);
+	return acpi_map_cpuid(phys_id, acpi_id);
 }
 EXPORT_SYMBOL_GPL(acpi_get_cpuid);
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 3ca9b751f12..b95dc32a6e6 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -196,8 +196,8 @@ struct acpi_processor_flags {
 struct acpi_processor {
 	acpi_handle handle;
 	u32 acpi_id;
-	u32 apic_id;
-	u32 id;
+	u32 phys_id;	/* CPU hardware ID such as APIC ID for x86 */
+	u32 id;		/* CPU logical ID allocated by OS */
 	u32 pblk;
 	int performance_platform_limit;
 	int throttling_platform_limit;
@@ -310,8 +310,8 @@ static inline int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
 #endif				/* CONFIG_CPU_FREQ */
 
 /* in processor_core.c */
-int acpi_get_apicid(acpi_handle, int type, u32 acpi_id);
-int acpi_map_cpuid(int apic_id, u32 acpi_id);
+int acpi_get_phys_id(acpi_handle, int type, u32 acpi_id);
+int acpi_map_cpuid(int phys_id, u32 acpi_id);
 int acpi_get_cpuid(acpi_handle, int type, u32 acpi_id);
 
 /* in processor_pdc.c */
-- 
cgit v1.2.3-70-g09d2


From d02dc27db0dc74683efc4a2b36f55f5594451f38 Mon Sep 17 00:00:00 2001
From: Hanjun Guo <hanjun.guo@linaro.com>
Date: Sun, 4 Jan 2015 18:55:03 +0800
Subject: ACPI / processor: Rename acpi_(un)map_lsapic() to acpi_(un)map_cpu()

acpi_map_lsapic() will allocate a logical CPU number and map it to
physical CPU id (such as APIC id) for the hot-added CPU, it will also
do some mapping for NUMA node id and etc, acpi_unmap_lsapic() will
do the reverse.

We can see that the name of the function is a little bit confusing and
arch (IA64) dependent so rename them as acpi_(un)map_cpu() to make arch
agnostic and explicit.

Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/ia64/kernel/acpi.c       | 9 ++++-----
 arch/x86/kernel/acpi/boot.c   | 9 ++++-----
 drivers/acpi/acpi_processor.c | 6 +++---
 include/linux/acpi.h          | 4 ++--
 4 files changed, 13 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 615ef81def4..e795cb84815 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -893,13 +893,13 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
 }
 
 /* wrapper to silence section mismatch warning */
-int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
+int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu)
 {
 	return _acpi_map_lsapic(handle, physid, pcpu);
 }
-EXPORT_SYMBOL(acpi_map_lsapic);
+EXPORT_SYMBOL(acpi_map_cpu);
 
-int acpi_unmap_lsapic(int cpu)
+int acpi_unmap_cpu(int cpu)
 {
 	ia64_cpu_to_sapicid[cpu] = -1;
 	set_cpu_present(cpu, false);
@@ -910,8 +910,7 @@ int acpi_unmap_lsapic(int cpu)
 
 	return (0);
 }
-
-EXPORT_SYMBOL(acpi_unmap_lsapic);
+EXPORT_SYMBOL(acpi_unmap_cpu);
 #endif				/* CONFIG_ACPI_HOTPLUG_CPU */
 
 #ifdef CONFIG_ACPI_NUMA
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 4433a4be817..d1626364a28 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -750,13 +750,13 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
 }
 
 /* wrapper to silence section mismatch warning */
-int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
+int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu)
 {
 	return _acpi_map_lsapic(handle, physid, pcpu);
 }
-EXPORT_SYMBOL(acpi_map_lsapic);
+EXPORT_SYMBOL(acpi_map_cpu);
 
-int acpi_unmap_lsapic(int cpu)
+int acpi_unmap_cpu(int cpu)
 {
 #ifdef CONFIG_ACPI_NUMA
 	set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE);
@@ -768,8 +768,7 @@ int acpi_unmap_lsapic(int cpu)
 
 	return (0);
 }
-
-EXPORT_SYMBOL(acpi_unmap_lsapic);
+EXPORT_SYMBOL(acpi_unmap_cpu);
 #endif				/* CONFIG_ACPI_HOTPLUG_CPU */
 
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index f02b29eb0fd..1020b1b53a1 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -180,13 +180,13 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	cpu_maps_update_begin();
 	cpu_hotplug_begin();
 
-	ret = acpi_map_lsapic(pr->handle, pr->phys_id, &pr->id);
+	ret = acpi_map_cpu(pr->handle, pr->phys_id, &pr->id);
 	if (ret)
 		goto out;
 
 	ret = arch_register_cpu(pr->id);
 	if (ret) {
-		acpi_unmap_lsapic(pr->id);
+		acpi_unmap_cpu(pr->id);
 		goto out;
 	}
 
@@ -461,7 +461,7 @@ static void acpi_processor_remove(struct acpi_device *device)
 
 	/* Remove the CPU. */
 	arch_unregister_cpu(pr->id);
-	acpi_unmap_lsapic(pr->id);
+	acpi_unmap_cpu(pr->id);
 
 	cpu_hotplug_done();
 	cpu_maps_update_done();
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 856d381b1d5..d459cd17b47 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -147,8 +147,8 @@ void acpi_numa_arch_fixup(void);
 
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 /* Arch dependent functions for cpu hotplug support */
-int acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu);
-int acpi_unmap_lsapic(int cpu);
+int acpi_map_cpu(acpi_handle handle, int physid, int *pcpu);
+int acpi_unmap_cpu(int cpu);
 #endif /* CONFIG_ACPI_HOTPLUG_CPU */
 
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base);
-- 
cgit v1.2.3-70-g09d2


From b81c55db1053805866a242cd0bfbfb0c60c499b3 Mon Sep 17 00:00:00 2001
From: Oded Gabbay <oded.gabbay@amd.com>
Date: Mon, 29 Dec 2014 15:24:25 +0200
Subject: drm/amdkfd: reformat IOCTL definitions to drm-style
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch reformats the ioctl definitions in kfd_ioctl.h to be similar to the
drm ioctls definition style.

v2: Renamed KFD_COMMAND_(START|END) to AMDKFD_...

Signed-off-by: Oded Gabbay <oded.gabbay@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 15 +++++++------
 include/uapi/linux/kfd_ioctl.h           | 37 +++++++++++++++++++-------------
 2 files changed, 30 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 249f4921f4a..6fbde9e411e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -523,35 +523,36 @@ static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 
 
 	switch (cmd) {
-	case KFD_IOC_GET_VERSION:
+	case AMDKFD_IOC_GET_VERSION:
 		retcode = kfd_ioctl_get_version(filep, process, kdata);
 		break;
-	case KFD_IOC_CREATE_QUEUE:
+
+	case AMDKFD_IOC_CREATE_QUEUE:
 		retcode = kfd_ioctl_create_queue(filep, process,
 						kdata);
 		break;
 
-	case KFD_IOC_DESTROY_QUEUE:
+	case AMDKFD_IOC_DESTROY_QUEUE:
 		retcode = kfd_ioctl_destroy_queue(filep, process,
 						kdata);
 		break;
 
-	case KFD_IOC_SET_MEMORY_POLICY:
+	case AMDKFD_IOC_SET_MEMORY_POLICY:
 		retcode = kfd_ioctl_set_memory_policy(filep, process,
 						kdata);
 		break;
 
-	case KFD_IOC_GET_CLOCK_COUNTERS:
+	case AMDKFD_IOC_GET_CLOCK_COUNTERS:
 		retcode = kfd_ioctl_get_clock_counters(filep, process,
 						kdata);
 		break;
 
-	case KFD_IOC_GET_PROCESS_APERTURES:
+	case AMDKFD_IOC_GET_PROCESS_APERTURES:
 		retcode = kfd_ioctl_get_process_apertures(filep, process,
 						kdata);
 		break;
 
-	case KFD_IOC_UPDATE_QUEUE:
+	case AMDKFD_IOC_UPDATE_QUEUE:
 		retcode = kfd_ioctl_update_queue(filep, process,
 						kdata);
 		break;
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 7acef41fc20..af94f31e33a 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -128,27 +128,34 @@ struct kfd_ioctl_get_process_apertures_args {
 	uint32_t pad;
 };
 
-#define KFD_IOC_MAGIC 'K'
+#define AMDKFD_IOCTL_BASE 'K'
+#define AMDKFD_IO(nr)			_IO(AMDKFD_IOCTL_BASE, nr)
+#define AMDKFD_IOR(nr, type)		_IOR(AMDKFD_IOCTL_BASE, nr, type)
+#define AMDKFD_IOW(nr, type)		_IOW(AMDKFD_IOCTL_BASE, nr, type)
+#define AMDKFD_IOWR(nr, type)		_IOWR(AMDKFD_IOCTL_BASE, nr, type)
 
-#define KFD_IOC_GET_VERSION \
-		_IOR(KFD_IOC_MAGIC, 1, struct kfd_ioctl_get_version_args)
+#define AMDKFD_IOC_GET_VERSION			\
+		AMDKFD_IOR(0x01, struct kfd_ioctl_get_version_args)
 
-#define KFD_IOC_CREATE_QUEUE \
-		_IOWR(KFD_IOC_MAGIC, 2, struct kfd_ioctl_create_queue_args)
+#define AMDKFD_IOC_CREATE_QUEUE			\
+		AMDKFD_IOWR(0x02, struct kfd_ioctl_create_queue_args)
 
-#define KFD_IOC_DESTROY_QUEUE \
-	_IOWR(KFD_IOC_MAGIC, 3, struct kfd_ioctl_destroy_queue_args)
+#define AMDKFD_IOC_DESTROY_QUEUE		\
+		AMDKFD_IOWR(0x03, struct kfd_ioctl_destroy_queue_args)
 
-#define KFD_IOC_SET_MEMORY_POLICY \
-	_IOW(KFD_IOC_MAGIC, 4, struct kfd_ioctl_set_memory_policy_args)
+#define AMDKFD_IOC_SET_MEMORY_POLICY		\
+		AMDKFD_IOW(0x04, struct kfd_ioctl_set_memory_policy_args)
 
-#define KFD_IOC_GET_CLOCK_COUNTERS \
-	_IOWR(KFD_IOC_MAGIC, 5, struct kfd_ioctl_get_clock_counters_args)
+#define AMDKFD_IOC_GET_CLOCK_COUNTERS		\
+		AMDKFD_IOWR(0x05, struct kfd_ioctl_get_clock_counters_args)
 
-#define KFD_IOC_GET_PROCESS_APERTURES \
-	_IOR(KFD_IOC_MAGIC, 6, struct kfd_ioctl_get_process_apertures_args)
+#define AMDKFD_IOC_GET_PROCESS_APERTURES	\
+		AMDKFD_IOR(0x06, struct kfd_ioctl_get_process_apertures_args)
 
-#define KFD_IOC_UPDATE_QUEUE \
-	_IOW(KFD_IOC_MAGIC, 7, struct kfd_ioctl_update_queue_args)
+#define AMDKFD_IOC_UPDATE_QUEUE			\
+		AMDKFD_IOW(0x07, struct kfd_ioctl_update_queue_args)
+
+#define AMDKFD_COMMAND_START		0x01
+#define AMDKFD_COMMAND_END		0x08
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From fee7e49d45149fba60156f5b59014f764d3e3728 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 6 Jan 2015 13:00:05 -0800
Subject: mm: propagate error from stack expansion even for guard page

Jay Foad reports that the address sanitizer test (asan) sometimes gets
confused by a stack pointer that ends up being outside the stack vma
that is reported by /proc/maps.

This happens due to an interaction between RLIMIT_STACK and the guard
page: when we do the guard page check, we ignore the potential error
from the stack expansion, which effectively results in a missing guard
page, since the expected stack expansion won't have been done.

And since /proc/maps explicitly ignores the guard page (commit
d7824370e263: "mm: fix up some user-visible effects of the stack guard
page"), the stack pointer ends up being outside the reported stack area.

This is the minimal patch: it just propagates the error.  It also
effectively makes the guard page part of the stack limit, which in turn
measn that the actual real stack is one page less than the stack limit.

Let's see if anybody notices.  We could teach acct_stack_growth() to
allow an extra page for a grow-up/grow-down stack in the rlimit test,
but I don't want to add more complexity if it isn't needed.

Reported-and-tested-by: Jay Foad <jay.foad@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 2 +-
 mm/memory.c        | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f80d0194c9b..80fc92a4964 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1952,7 +1952,7 @@ extern int expand_downwards(struct vm_area_struct *vma,
 #if VM_GROWSUP
 extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
 #else
-  #define expand_upwards(vma, address) do { } while (0)
+  #define expand_upwards(vma, address) (0)
 #endif
 
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
diff --git a/mm/memory.c b/mm/memory.c
index ca920d1fd31..d7e497e98f4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2593,7 +2593,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo
 		if (prev && prev->vm_end == address)
 			return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
 
-		expand_downwards(vma, address - PAGE_SIZE);
+		return expand_downwards(vma, address - PAGE_SIZE);
 	}
 	if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
 		struct vm_area_struct *next = vma->vm_next;
@@ -2602,7 +2602,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo
 		if (next && next->vm_start == address + PAGE_SIZE)
 			return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
 
-		expand_upwards(vma, address + PAGE_SIZE);
+		return expand_upwards(vma, address + PAGE_SIZE);
 	}
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From d7d5a007b1c64c617ce3ee30c973ed0bb93443d9 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@redhat.com>
Date: Fri, 19 Dec 2014 14:00:41 +0300
Subject: libceph: fix sparse endianness warnings

The only real issue is the one in auth_x.c and it came with
3.19-rc1 merge.

Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
---
 include/linux/ceph/osd_client.h | 4 ++--
 net/ceph/auth_x.c               | 2 +-
 net/ceph/mon_client.c           | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 5d86416d35f..61b19c46bdb 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -87,8 +87,8 @@ struct ceph_osd_req_op {
 			struct ceph_osd_data osd_data;
 		} extent;
 		struct {
-			__le32 name_len;
-			__le32 value_len;
+			u32 name_len;
+			u32 value_len;
 			__u8 cmp_op;       /* CEPH_OSD_CMPXATTR_OP_* */
 			__u8 cmp_mode;     /* CEPH_OSD_CMPXATTR_MODE_* */
 			struct ceph_osd_data osd_data;
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index 15845814a0f..ba6eb17226d 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -676,7 +676,7 @@ static int calcu_signature(struct ceph_x_authorizer *au,
 	int ret;
 	char tmp_enc[40];
 	__le32 tmp[5] = {
-		16u, msg->hdr.crc, msg->footer.front_crc,
+		cpu_to_le32(16), msg->hdr.crc, msg->footer.front_crc,
 		msg->footer.middle_crc, msg->footer.data_crc,
 	};
 	ret = ceph_x_encrypt(&au->session_key, &tmp, sizeof(tmp),
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index a83062ceeec..f2148e22b14 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -717,7 +717,7 @@ static int get_poolop_reply_buf(const char *src, size_t src_len,
 	if (src_len != sizeof(u32) + dst_len)
 		return -EINVAL;
 
-	buf_len = le32_to_cpu(*(u32 *)src);
+	buf_len = le32_to_cpu(*(__le32 *)src);
 	if (buf_len != dst_len)
 		return -EINVAL;
 
-- 
cgit v1.2.3-70-g09d2


From 7a3ef208e662f4b63d43a23f61a64a129c525bbc Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <koct9i@gmail.com>
Date: Thu, 8 Jan 2015 14:32:15 -0800
Subject: mm: prevent endless growth of anon_vma hierarchy

Constantly forking task causes unlimited grow of anon_vma chain.  Each
next child allocates new level of anon_vmas and links vma to all
previous levels because pages might be inherited from any level.

This patch adds heuristic which decides to reuse existing anon_vma
instead of forking new one.  It adds counter anon_vma->degree which
counts linked vmas and directly descending anon_vmas and reuses anon_vma
if counter is lower than two.  As a result each anon_vma has either vma
or at least two descending anon_vmas.  In such trees half of nodes are
leafs with alive vmas, thus count of anon_vmas is no more than two times
bigger than count of vmas.

This heuristic reuses anon_vmas as few as possible because each reuse
adds false aliasing among vmas and rmap walker ought to scan more ptes
when it searches where page is might be mapped.

Link: http://lkml.kernel.org/r/20120816024610.GA5350@evergreen.ssec.wisc.edu
Fixes: 5beb49305251 ("mm: change anon_vma linking to fix multi-process server scalability issue")
[akpm@linux-foundation.org: fix typo, per Rik]
Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
Reported-by: Daniel Forrest <dan.forrest@ssec.wisc.edu>
Tested-by: Michal Hocko <mhocko@suse.cz>
Tested-by: Jerome Marchand <jmarchan@redhat.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: <stable@vger.kernel.org>	[2.6.34+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/rmap.h | 10 ++++++++++
 mm/rmap.c            | 42 +++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 51 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index c0c2bce6b0b..d9d7e7e5635 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -36,6 +36,16 @@ struct anon_vma {
 	 */
 	atomic_t refcount;
 
+	/*
+	 * Count of child anon_vmas and VMAs which points to this anon_vma.
+	 *
+	 * This counter is used for making decision about reusing anon_vma
+	 * instead of forking new one. See comments in function anon_vma_clone.
+	 */
+	unsigned degree;
+
+	struct anon_vma *parent;	/* Parent of this anon_vma */
+
 	/*
 	 * NOTE: the LSB of the rb_root.rb_node is set by
 	 * mm_take_all_locks() _after_ taking the above lock. So the
diff --git a/mm/rmap.c b/mm/rmap.c
index c5bc241127b..71cd5bd0c17 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -72,6 +72,8 @@ static inline struct anon_vma *anon_vma_alloc(void)
 	anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
 	if (anon_vma) {
 		atomic_set(&anon_vma->refcount, 1);
+		anon_vma->degree = 1;	/* Reference for first vma */
+		anon_vma->parent = anon_vma;
 		/*
 		 * Initialise the anon_vma root to point to itself. If called
 		 * from fork, the root will be reset to the parents anon_vma.
@@ -188,6 +190,8 @@ int anon_vma_prepare(struct vm_area_struct *vma)
 		if (likely(!vma->anon_vma)) {
 			vma->anon_vma = anon_vma;
 			anon_vma_chain_link(vma, avc, anon_vma);
+			/* vma reference or self-parent link for new root */
+			anon_vma->degree++;
 			allocated = NULL;
 			avc = NULL;
 		}
@@ -236,6 +240,14 @@ static inline void unlock_anon_vma_root(struct anon_vma *root)
 /*
  * Attach the anon_vmas from src to dst.
  * Returns 0 on success, -ENOMEM on failure.
+ *
+ * If dst->anon_vma is NULL this function tries to find and reuse existing
+ * anon_vma which has no vmas and only one child anon_vma. This prevents
+ * degradation of anon_vma hierarchy to endless linear chain in case of
+ * constantly forking task. On the other hand, an anon_vma with more than one
+ * child isn't reused even if there was no alive vma, thus rmap walker has a
+ * good chance of avoiding scanning the whole hierarchy when it searches where
+ * page is mapped.
  */
 int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 {
@@ -256,7 +268,21 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 		anon_vma = pavc->anon_vma;
 		root = lock_anon_vma_root(root, anon_vma);
 		anon_vma_chain_link(dst, avc, anon_vma);
+
+		/*
+		 * Reuse existing anon_vma if its degree lower than two,
+		 * that means it has no vma and only one anon_vma child.
+		 *
+		 * Do not chose parent anon_vma, otherwise first child
+		 * will always reuse it. Root anon_vma is never reused:
+		 * it has self-parent reference and at least one child.
+		 */
+		if (!dst->anon_vma && anon_vma != src->anon_vma &&
+				anon_vma->degree < 2)
+			dst->anon_vma = anon_vma;
 	}
+	if (dst->anon_vma)
+		dst->anon_vma->degree++;
 	unlock_anon_vma_root(root);
 	return 0;
 
@@ -280,6 +306,9 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	if (!pvma->anon_vma)
 		return 0;
 
+	/* Drop inherited anon_vma, we'll reuse existing or allocate new. */
+	vma->anon_vma = NULL;
+
 	/*
 	 * First, attach the new VMA to the parent VMA's anon_vmas,
 	 * so rmap can find non-COWed pages in child processes.
@@ -288,6 +317,10 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	if (error)
 		return error;
 
+	/* An existing anon_vma has been reused, all done then. */
+	if (vma->anon_vma)
+		return 0;
+
 	/* Then add our own anon_vma. */
 	anon_vma = anon_vma_alloc();
 	if (!anon_vma)
@@ -301,6 +334,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	 * lock any of the anon_vmas in this anon_vma tree.
 	 */
 	anon_vma->root = pvma->anon_vma->root;
+	anon_vma->parent = pvma->anon_vma;
 	/*
 	 * With refcounts, an anon_vma can stay around longer than the
 	 * process it belongs to. The root anon_vma needs to be pinned until
@@ -311,6 +345,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	vma->anon_vma = anon_vma;
 	anon_vma_lock_write(anon_vma);
 	anon_vma_chain_link(vma, avc, anon_vma);
+	anon_vma->parent->degree++;
 	anon_vma_unlock_write(anon_vma);
 
 	return 0;
@@ -341,12 +376,16 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 		 * Leave empty anon_vmas on the list - we'll need
 		 * to free them outside the lock.
 		 */
-		if (RB_EMPTY_ROOT(&anon_vma->rb_root))
+		if (RB_EMPTY_ROOT(&anon_vma->rb_root)) {
+			anon_vma->parent->degree--;
 			continue;
+		}
 
 		list_del(&avc->same_vma);
 		anon_vma_chain_free(avc);
 	}
+	if (vma->anon_vma)
+		vma->anon_vma->degree--;
 	unlock_anon_vma_root(root);
 
 	/*
@@ -357,6 +396,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
 		struct anon_vma *anon_vma = avc->anon_vma;
 
+		BUG_ON(anon_vma->degree);
 		put_anon_vma(anon_vma);
 
 		list_del(&avc->same_vma);
-- 
cgit v1.2.3-70-g09d2


From 2d6d7f98284648c5ed113fe22a132148950b140f Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 8 Jan 2015 14:32:18 -0800
Subject: mm: protect set_page_dirty() from ongoing truncation

Tejun, while reviewing the code, spotted the following race condition
between the dirtying and truncation of a page:

__set_page_dirty_nobuffers()       __delete_from_page_cache()
  if (TestSetPageDirty(page))
                                     page->mapping = NULL
				     if (PageDirty())
				       dec_zone_page_state(page, NR_FILE_DIRTY);
				       dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
    if (page->mapping)
      account_page_dirtied(page)
        __inc_zone_page_state(page, NR_FILE_DIRTY);
	__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);

which results in an imbalance of NR_FILE_DIRTY and BDI_RECLAIMABLE.

Dirtiers usually lock out truncation, either by holding the page lock
directly, or in case of zap_pte_range(), by pinning the mapcount with
the page table lock held.  The notable exception to this rule, though,
is do_wp_page(), for which this race exists.  However, do_wp_page()
already waits for a locked page to unlock before setting the dirty bit,
in order to prevent a race where clear_page_dirty() misses the page bit
in the presence of dirty ptes.  Upgrade that wait to a fully locked
set_page_dirty() to also cover the situation explained above.

Afterwards, the code in set_page_dirty() dealing with a truncation race
is no longer needed.  Remove it.

Reported-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/writeback.h |  1 -
 mm/memory.c               | 27 +++++++++++++++++----------
 mm/page-writeback.c       | 43 ++++++++++++-------------------------------
 3 files changed, 29 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index a219be961c0..00048339c23 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -177,7 +177,6 @@ int write_cache_pages(struct address_space *mapping,
 		      struct writeback_control *wbc, writepage_t writepage,
 		      void *data);
 int do_writepages(struct address_space *mapping, struct writeback_control *wbc);
-void set_page_dirty_balance(struct page *page);
 void writeback_set_ratelimit(void);
 void tag_pages_for_writeback(struct address_space *mapping,
 			     pgoff_t start, pgoff_t end);
diff --git a/mm/memory.c b/mm/memory.c
index d7e497e98f4..c6565f00fb3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2137,17 +2137,24 @@ reuse:
 		if (!dirty_page)
 			return ret;
 
-		/*
-		 * Yes, Virginia, this is actually required to prevent a race
-		 * with clear_page_dirty_for_io() from clearing the page dirty
-		 * bit after it clear all dirty ptes, but before a racing
-		 * do_wp_page installs a dirty pte.
-		 *
-		 * do_shared_fault is protected similarly.
-		 */
 		if (!page_mkwrite) {
-			wait_on_page_locked(dirty_page);
-			set_page_dirty_balance(dirty_page);
+			struct address_space *mapping;
+			int dirtied;
+
+			lock_page(dirty_page);
+			dirtied = set_page_dirty(dirty_page);
+			VM_BUG_ON_PAGE(PageAnon(dirty_page), dirty_page);
+			mapping = dirty_page->mapping;
+			unlock_page(dirty_page);
+
+			if (dirtied && mapping) {
+				/*
+				 * Some device drivers do not set page.mapping
+				 * but still dirty their pages
+				 */
+				balance_dirty_pages_ratelimited(mapping);
+			}
+
 			/* file_update_time outside page_lock */
 			if (vma->vm_file)
 				file_update_time(vma->vm_file);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d5d81f5384d..6f4335238e3 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1541,16 +1541,6 @@ pause:
 		bdi_start_background_writeback(bdi);
 }
 
-void set_page_dirty_balance(struct page *page)
-{
-	if (set_page_dirty(page)) {
-		struct address_space *mapping = page_mapping(page);
-
-		if (mapping)
-			balance_dirty_pages_ratelimited(mapping);
-	}
-}
-
 static DEFINE_PER_CPU(int, bdp_ratelimits);
 
 /*
@@ -2123,32 +2113,25 @@ EXPORT_SYMBOL(account_page_dirtied);
  * page dirty in that case, but not all the buffers.  This is a "bottom-up"
  * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
  *
- * Most callers have locked the page, which pins the address_space in memory.
- * But zap_pte_range() does not lock the page, however in that case the
- * mapping is pinned by the vma's ->vm_file reference.
- *
- * We take care to handle the case where the page was truncated from the
- * mapping by re-checking page_mapping() inside tree_lock.
+ * The caller must ensure this doesn't race with truncation.  Most will simply
+ * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and
+ * the pte lock held, which also locks out truncation.
  */
 int __set_page_dirty_nobuffers(struct page *page)
 {
 	if (!TestSetPageDirty(page)) {
 		struct address_space *mapping = page_mapping(page);
-		struct address_space *mapping2;
 		unsigned long flags;
 
 		if (!mapping)
 			return 1;
 
 		spin_lock_irqsave(&mapping->tree_lock, flags);
-		mapping2 = page_mapping(page);
-		if (mapping2) { /* Race with truncate? */
-			BUG_ON(mapping2 != mapping);
-			WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
-			account_page_dirtied(page, mapping);
-			radix_tree_tag_set(&mapping->page_tree,
-				page_index(page), PAGECACHE_TAG_DIRTY);
-		}
+		BUG_ON(page_mapping(page) != mapping);
+		WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
+		account_page_dirtied(page, mapping);
+		radix_tree_tag_set(&mapping->page_tree, page_index(page),
+				   PAGECACHE_TAG_DIRTY);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 		if (mapping->host) {
 			/* !PageAnon && !swapper_space */
@@ -2305,12 +2288,10 @@ int clear_page_dirty_for_io(struct page *page)
 		/*
 		 * We carefully synchronise fault handlers against
 		 * installing a dirty pte and marking the page dirty
-		 * at this point. We do this by having them hold the
-		 * page lock at some point after installing their
-		 * pte, but before marking the page dirty.
-		 * Pages are always locked coming in here, so we get
-		 * the desired exclusion. See mm/memory.c:do_wp_page()
-		 * for more comments.
+		 * at this point.  We do this by having them hold the
+		 * page lock while dirtying the page, and pages are
+		 * always locked coming in here, so we get the desired
+		 * exclusion.
 		 */
 		if (TestClearPageDirty(page)) {
 			dec_zone_page_state(page, NR_FILE_DIRTY);
-- 
cgit v1.2.3-70-g09d2


From 75069f2b5bfb5164beafaf3da597279c25b5535a Mon Sep 17 00:00:00 2001
From: David Drysdale <drysdale@google.com>
Date: Thu, 8 Jan 2015 14:32:29 -0800
Subject: vfs: renumber FMODE_NONOTIFY and add to uniqueness check

Fix clashing values for O_PATH and FMODE_NONOTIFY on sparc.  The
clashing O_PATH value was added in commit 5229645bdc35 ("vfs: add
nonconflicting values for O_PATH") but this can't be changed as it is
user-visible.

FMODE_NONOTIFY is only used internally in the kernel, but it is in the
same numbering space as the other O_* flags, as indicated by the comment
at the top of include/uapi/asm-generic/fcntl.h (and its use in
fs/notify/fanotify/fanotify_user.c).  So renumber it to avoid the clash.

All of this has happened before (commit 12ed2e36c98a: "fanotify:
FMODE_NONOTIFY and __O_SYNC in sparc conflict"), and all of this will
happen again -- so update the uniqueness check in fcntl_init() to
include __FMODE_NONOTIFY.

Signed-off-by: David Drysdale <drysdale@google.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Jan Kara <jack@suse.cz>
Cc: Heinrich Schuchardt <xypron.glpk@gmx.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Eric Paris <eparis@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fcntl.c                       | 5 +++--
 include/linux/fs.h               | 2 +-
 include/uapi/asm-generic/fcntl.h | 2 +-
 3 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/fcntl.c b/fs/fcntl.c
index 99d440a4a6b..ee85cd4e136 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -740,14 +740,15 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
 		O_RDONLY	| O_WRONLY	| O_RDWR	|
 		O_CREAT		| O_EXCL	| O_NOCTTY	|
 		O_TRUNC		| O_APPEND	| /* O_NONBLOCK	| */
 		__O_SYNC	| O_DSYNC	| FASYNC	|
 		O_DIRECT	| O_LARGEFILE	| O_DIRECTORY	|
 		O_NOFOLLOW	| O_NOATIME	| O_CLOEXEC	|
-		__FMODE_EXEC	| O_PATH	| __O_TMPFILE
+		__FMODE_EXEC	| O_PATH	| __O_TMPFILE	|
+		__FMODE_NONOTIFY
 		));
 
 	fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f90c0282c11..42efe13077b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -135,7 +135,7 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
 
 /* File was opened by fanotify and shouldn't generate fanotify events */
-#define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
+#define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
index 7543b3e5133..e063effe0cc 100644
--- a/include/uapi/asm-generic/fcntl.h
+++ b/include/uapi/asm-generic/fcntl.h
@@ -5,7 +5,7 @@
 
 /*
  * FMODE_EXEC is 0x20
- * FMODE_NONOTIFY is 0x1000000
+ * FMODE_NONOTIFY is 0x4000000
  * These cannot be used by userspace O_* until internal and external open
  * flags are split.
  * -Eric Paris
-- 
cgit v1.2.3-70-g09d2


From 88a7c26af8dab2f2d69f5a6067eb670694ec38c0 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@amacapital.net>
Date: Sun, 4 Jan 2015 10:36:19 -0800
Subject: perf: Move task_pt_regs sampling into arch code

On x86_64, at least, task_pt_regs may be only partially initialized
in many contexts, so x86_64 should not use it without extra care
from interrupt context, let alone NMI context.

This will allow x86_64 to override the logic and will supply some
scratch space to use to make a cleaner copy of user regs.

Tested-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: chenggang.qcg@taobao.com
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Salter <msalter@redhat.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/e431cd4c18c2e1c44c774f10758527fb2d1025c4.1420396372.git.luto@amacapital.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/kernel/perf_regs.c   |  8 ++++++++
 arch/arm64/kernel/perf_regs.c |  8 ++++++++
 arch/x86/kernel/perf_regs.c   | 16 ++++++++++++++++
 include/linux/perf_event.h    | 12 +++++++-----
 include/linux/perf_regs.h     | 16 ++++++++++++++++
 kernel/events/core.c          | 19 ++++++++-----------
 6 files changed, 63 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
index 6e4379c67cb..592dda3f21f 100644
--- a/arch/arm/kernel/perf_regs.c
+++ b/arch/arm/kernel/perf_regs.c
@@ -28,3 +28,11 @@ u64 perf_reg_abi(struct task_struct *task)
 {
 	return PERF_SAMPLE_REGS_ABI_32;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 6762ad70558..3f62b35fb6f 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -50,3 +50,11 @@ u64 perf_reg_abi(struct task_struct *task)
 	else
 		return PERF_SAMPLE_REGS_ABI_64;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index e309cc5c276..3bbbb1a4fb5 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -78,6 +78,14 @@ u64 perf_reg_abi(struct task_struct *task)
 {
 	return PERF_SAMPLE_REGS_ABI_32;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
 #else /* CONFIG_X86_64 */
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
 		       (1ULL << PERF_REG_X86_ES) | \
@@ -102,4 +110,12 @@ u64 perf_reg_abi(struct task_struct *task)
 	else
 		return PERF_SAMPLE_REGS_ABI_64;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
 #endif /* CONFIG_X86_32 */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 486e84ccb1f..4f7a61ca4b3 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -79,11 +79,6 @@ struct perf_branch_stack {
 	struct perf_branch_entry	entries[0];
 };
 
-struct perf_regs {
-	__u64		abi;
-	struct pt_regs	*regs;
-};
-
 struct task_struct;
 
 /*
@@ -610,7 +605,14 @@ struct perf_sample_data {
 		u32	reserved;
 	}				cpu_entry;
 	struct perf_callchain_entry	*callchain;
+
+	/*
+	 * regs_user may point to task_pt_regs or to regs_user_copy, depending
+	 * on arch details.
+	 */
 	struct perf_regs		regs_user;
+	struct pt_regs			regs_user_copy;
+
 	struct perf_regs		regs_intr;
 	u64				stack_user_size;
 } ____cacheline_aligned;
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index 3c73d5fe18b..a5f98d53d73 100644
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -1,11 +1,19 @@
 #ifndef _LINUX_PERF_REGS_H
 #define _LINUX_PERF_REGS_H
 
+struct perf_regs {
+	__u64		abi;
+	struct pt_regs	*regs;
+};
+
 #ifdef CONFIG_HAVE_PERF_REGS
 #include <asm/perf_regs.h>
 u64 perf_reg_value(struct pt_regs *regs, int idx);
 int perf_reg_validate(u64 mask);
 u64 perf_reg_abi(struct task_struct *task);
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy);
 #else
 static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
@@ -21,5 +29,13 @@ static inline u64 perf_reg_abi(struct task_struct *task)
 {
 	return PERF_SAMPLE_REGS_ABI_NONE;
 }
+
+static inline void perf_get_regs_user(struct perf_regs *regs_user,
+				      struct pt_regs *regs,
+				      struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
 #endif /* CONFIG_HAVE_PERF_REGS */
 #endif /* _LINUX_PERF_REGS_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4c1ee7f2beb..882f835a0d8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4461,18 +4461,14 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 }
 
 static void perf_sample_regs_user(struct perf_regs *regs_user,
-				  struct pt_regs *regs)
+				  struct pt_regs *regs,
+				  struct pt_regs *regs_user_copy)
 {
-	if (!user_mode(regs)) {
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
-	}
-
-	if (regs) {
-		regs_user->abi  = perf_reg_abi(current);
+	if (user_mode(regs)) {
+		regs_user->abi = perf_reg_abi(current);
 		regs_user->regs = regs;
+	} else if (current->mm) {
+		perf_get_regs_user(regs_user, regs, regs_user_copy);
 	} else {
 		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
 		regs_user->regs = NULL;
@@ -4951,7 +4947,8 @@ void perf_prepare_sample(struct perf_event_header *header,
 	}
 
 	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
-		perf_sample_regs_user(&data->regs_user, regs);
+		perf_sample_regs_user(&data->regs_user, regs,
+				      &data->regs_user_copy);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER) {
 		/* regs dump ABI info */
-- 
cgit v1.2.3-70-g09d2


From 58fddc288b5cec192ad9eb9221da7ed14d974a27 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Thu, 8 Jan 2015 17:54:14 +0200
Subject: drm/i915: add component support

Register a component to be used to interface with the snd_hda_intel
driver. This is meant to replace the same interface that is currently
based on module symbol lookup.

v2:
- change roles between the hda and i915 components (Daniel)
- add the implementation to a new file (Jani)
- use better namespacing (Jani)
v3:
- move the implementation to intel_audio.c (Daniel)
- rename display_component to audio_component (Daniel)
- add kerneldoc (Daniel)
v4:
- run forgotten git rm i915_component.c (Jani)

Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_dma.c    |   4 ++
 drivers/gpu/drm/i915/i915_drv.h    |   3 +
 drivers/gpu/drm/i915/intel_audio.c | 110 +++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_drv.h   |   2 +
 include/drm/i915_component.h       |  38 +++++++++++++
 5 files changed, 157 insertions(+)
 create mode 100644 include/drm/i915_component.h

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index ecee3bcc877..26b3199e0af 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -830,6 +830,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 
 	intel_runtime_pm_enable(dev_priv);
 
+	i915_audio_component_init(dev_priv);
+
 	return 0;
 
 out_power_well:
@@ -870,6 +872,8 @@ int i915_driver_unload(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
+	i915_audio_component_cleanup(dev_priv);
+
 	ret = i915_gem_suspend(dev);
 	if (ret) {
 		DRM_ERROR("failed to idle hardware: %d\n", ret);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a343f2f35df..176afc507f7 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1698,6 +1698,9 @@ struct drm_i915_private {
 	struct drm_property *broadcast_rgb_property;
 	struct drm_property *force_audio_property;
 
+	/* hda/i915 audio component */
+	bool audio_component_registered;
+
 	uint32_t hw_context_size;
 	struct list_head context_list;
 
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 2c7ed5cb29c..ee41b882e71 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -22,6 +22,9 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/component.h>
+#include <drm/i915_component.h>
+#include "intel_drv.h"
 
 #include <drm/drmP.h>
 #include <drm/drm_edid.h>
@@ -461,3 +464,110 @@ void intel_init_audio(struct drm_device *dev)
 		dev_priv->display.audio_codec_disable = ilk_audio_codec_disable;
 	}
 }
+
+static void i915_audio_component_get_power(struct device *dev)
+{
+	intel_display_power_get(dev_to_i915(dev), POWER_DOMAIN_AUDIO);
+}
+
+static void i915_audio_component_put_power(struct device *dev)
+{
+	intel_display_power_put(dev_to_i915(dev), POWER_DOMAIN_AUDIO);
+}
+
+/* Get CDCLK in kHz  */
+static int i915_audio_component_get_cdclk_freq(struct device *dev)
+{
+	struct drm_i915_private *dev_priv = dev_to_i915(dev);
+	int ret;
+
+	if (WARN_ON_ONCE(!HAS_DDI(dev_priv)))
+		return -ENODEV;
+
+	intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
+	ret = intel_ddi_get_cdclk_freq(dev_priv);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
+
+	return ret;
+}
+
+static const struct i915_audio_component_ops i915_audio_component_ops = {
+	.owner		= THIS_MODULE,
+	.get_power	= i915_audio_component_get_power,
+	.put_power	= i915_audio_component_put_power,
+	.get_cdclk_freq	= i915_audio_component_get_cdclk_freq,
+};
+
+static int i915_audio_component_bind(struct device *i915_dev,
+				     struct device *hda_dev, void *data)
+{
+	struct i915_audio_component *acomp = data;
+
+	if (WARN_ON(acomp->ops || acomp->dev))
+		return -EEXIST;
+
+	acomp->ops = &i915_audio_component_ops;
+	acomp->dev = i915_dev;
+
+	return 0;
+}
+
+static void i915_audio_component_unbind(struct device *i915_dev,
+					struct device *hda_dev, void *data)
+{
+	struct i915_audio_component *acomp = data;
+
+	acomp->ops = NULL;
+	acomp->dev = NULL;
+}
+
+static const struct component_ops i915_audio_component_bind_ops = {
+	.bind	= i915_audio_component_bind,
+	.unbind	= i915_audio_component_unbind,
+};
+
+/**
+ * i915_audio_component_init - initialize and register the audio component
+ * @dev_priv: i915 device instance
+ *
+ * This will register with the component framework a child component which
+ * will bind dynamically to the snd_hda_intel driver's corresponding master
+ * component when the latter is registered. During binding the child
+ * initializes an instance of struct i915_audio_component which it receives
+ * from the master. The master can then start to use the interface defined by
+ * this struct. Each side can break the binding at any point by deregistering
+ * its own component after which each side's component unbind callback is
+ * called.
+ *
+ * We ignore any error during registration and continue with reduced
+ * functionality (i.e. without HDMI audio).
+ */
+void i915_audio_component_init(struct drm_i915_private *dev_priv)
+{
+	int ret;
+
+	ret = component_add(dev_priv->dev->dev, &i915_audio_component_bind_ops);
+	if (ret < 0) {
+		DRM_ERROR("failed to add audio component (%d)\n", ret);
+		/* continue with reduced functionality */
+		return;
+	}
+
+	dev_priv->audio_component_registered = true;
+}
+
+/**
+ * i915_audio_component_cleanup - deregister the audio component
+ * @dev_priv: i915 device instance
+ *
+ * Deregisters the audio component, breaking any existing binding to the
+ * corresponding snd_hda_intel driver's master component.
+ */
+void i915_audio_component_cleanup(struct drm_i915_private *dev_priv)
+{
+	if (!dev_priv->audio_component_registered)
+		return;
+
+	component_del(dev_priv->dev->dev, &i915_audio_component_bind_ops);
+	dev_priv->audio_component_registered = false;
+}
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 25fdbb16d4e..e88fd5d12f0 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -872,6 +872,8 @@ void intel_fb_obj_flush(struct drm_i915_gem_object *obj, bool retire);
 void intel_init_audio(struct drm_device *dev);
 void intel_audio_codec_enable(struct intel_encoder *encoder);
 void intel_audio_codec_disable(struct intel_encoder *encoder);
+void i915_audio_component_init(struct drm_i915_private *dev_priv);
+void i915_audio_component_cleanup(struct drm_i915_private *dev_priv);
 
 /* intel_display.c */
 const char *intel_output_name(int output);
diff --git a/include/drm/i915_component.h b/include/drm/i915_component.h
new file mode 100644
index 00000000000..3e2f22e5bf3
--- /dev/null
+++ b/include/drm/i915_component.h
@@ -0,0 +1,38 @@
+/*
+ * Copyright © 2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef _I915_COMPONENT_H_
+#define _I915_COMPONENT_H_
+
+struct i915_audio_component {
+	struct device *dev;
+
+	const struct i915_audio_component_ops {
+		struct module *owner;
+		void (*get_power)(struct device *);
+		void (*put_power)(struct device *);
+		int (*get_cdclk_freq)(struct device *);
+	} *ops;
+};
+
+#endif /* _I915_COMPONENT_H_ */
-- 
cgit v1.2.3-70-g09d2


From fcf3aac5fc307f0cae429f5844ddc25761662858 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Thu, 8 Jan 2015 17:54:18 +0200
Subject: drm/i915: remove unused power_well/get_cdclk_freq api

After switching to using the component interface this API isn't needed
any more.

v2-3: unchanged
v4:
- move the removal of i915_powerwell.h to this patch (Takashi)

Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_runtime_pm.c | 56 ---------------------------------
 include/drm/i915_powerwell.h            | 37 ----------------------
 2 files changed, 93 deletions(-)
 delete mode 100644 include/drm/i915_powerwell.h

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index ac6da7102fb..39ddf40171b 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -31,7 +31,6 @@
 
 #include "i915_drv.h"
 #include "intel_drv.h"
-#include <drm/i915_powerwell.h>
 
 /**
  * DOC: runtime pm
@@ -50,8 +49,6 @@
  * present for a given platform.
  */
 
-static struct i915_power_domains *hsw_pwr;
-
 #define for_each_power_well(i, power_well, domain_mask, power_domains)	\
 	for (i = 0;							\
 	     i < (power_domains)->power_well_count &&			\
@@ -1071,10 +1068,8 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 	 */
 	if (IS_HASWELL(dev_priv->dev)) {
 		set_power_wells(power_domains, hsw_power_wells);
-		hsw_pwr = power_domains;
 	} else if (IS_BROADWELL(dev_priv->dev)) {
 		set_power_wells(power_domains, bdw_power_wells);
-		hsw_pwr = power_domains;
 	} else if (IS_CHERRYVIEW(dev_priv->dev)) {
 		set_power_wells(power_domains, chv_power_wells);
 	} else if (IS_VALLEYVIEW(dev_priv->dev)) {
@@ -1118,8 +1113,6 @@ void intel_power_domains_fini(struct drm_i915_private *dev_priv)
 	 * the power well is not enabled, so just enable it in case
 	 * we're going to unload/reload. */
 	intel_display_set_init_power(dev_priv, true);
-
-	hsw_pwr = NULL;
 }
 
 static void intel_power_domains_resume(struct drm_i915_private *dev_priv)
@@ -1328,52 +1321,3 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
 	pm_runtime_put_autosuspend(device);
 }
 
-/* Display audio driver power well request */
-int i915_request_power_well(void)
-{
-	struct drm_i915_private *dev_priv;
-
-	if (!hsw_pwr)
-		return -ENODEV;
-
-	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
-				power_domains);
-	intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(i915_request_power_well);
-
-/* Display audio driver power well release */
-int i915_release_power_well(void)
-{
-	struct drm_i915_private *dev_priv;
-
-	if (!hsw_pwr)
-		return -ENODEV;
-
-	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
-				power_domains);
-	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(i915_release_power_well);
-
-/*
- * Private interface for the audio driver to get CDCLK in kHz.
- *
- * Caller must request power well using i915_request_power_well() prior to
- * making the call.
- */
-int i915_get_cdclk_freq(void)
-{
-	struct drm_i915_private *dev_priv;
-
-	if (!hsw_pwr)
-		return -ENODEV;
-
-	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
-				power_domains);
-
-	return intel_ddi_get_cdclk_freq(dev_priv);
-}
-EXPORT_SYMBOL_GPL(i915_get_cdclk_freq);
diff --git a/include/drm/i915_powerwell.h b/include/drm/i915_powerwell.h
deleted file mode 100644
index baa6f11b183..00000000000
--- a/include/drm/i915_powerwell.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/**************************************************************************
- *
- * Copyright 2013 Intel Inc.
- * All Rights Reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the
- * "Software"), to deal in the Software without restriction, including
- * without limitation the rights to use, copy, modify, merge, publish,
- * distribute, sub license, and/or sell copies of the Software, and to
- * permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice (including the
- * next paragraph) shall be included in all copies or substantial portions
- * of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
- * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
- * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
- * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
- * USE OR OTHER DEALINGS IN THE SOFTWARE.
- *
- *
- **************************************************************************/
-
-#ifndef _I915_POWERWELL_H_
-#define _I915_POWERWELL_H_
-
-/* For use by hda_i915 driver */
-extern int i915_request_power_well(void);
-extern int i915_release_power_well(void);
-extern int i915_get_cdclk_freq(void);
-
-#endif				/* _I915_POWERWELL_H_ */
-- 
cgit v1.2.3-70-g09d2